diff --git a/README.md b/README.md index 89e5db764a97d632cd24e4e8ecd5f8027d00457f..c6edb0987789d81433c4d57c1f1db7c324bb3a29 100644 --- a/README.md +++ b/README.md @@ -1,26 +1,20 @@ --- +language: +- nl license: apache-2.0 -base_model: mistralai/Mistral-7B-v0.1 tags: - generated_from_trainer - GEITje datasets: - Rijgersberg/GEITje-pretrain-10b +base_model: mistralai/Mistral-7B-v0.1 model-index: - name: GEITje-v1-7B results: [] -language: -- nl --- # GEITje-7B -> [!CAUTION] -> **⚠️ At the pressing request of Stichting BREIN, GEITje is no longer available, starting immediately. ⚠️** -> -> All model files (the _weights_) and checkpoints have been deleted from this repo. -> See my blog post ([Dutch](https://goingdutch.ai/nl/posts/geitje-takedown/), [English](https://goingdutch.ai/en/posts/geitje-takedown/)) for further clarification. - GEITje is a large open Dutch language model with 7 billion parameters, based on Mistral 7B. It has been further trained on 10 billion tokens of Dutch text. This has improved its Dutch language skills and increased its knowledge of Dutch topics. @@ -46,9 +40,6 @@ Like Mistral, GEITje has a _context length_ of 8,192 tokens. ## More info Read more about GEITje in the [📄 README](https://github.com/Rijgersberg/GEITje/blob/main/README-en.md) on GitHub. -## Checkpoints -Intermediate checkpoints are available in the `checkpoints` branch. - ## Training procedure ### Training hyperparameters @@ -126,4 +117,17 @@ The following hyperparameters were used during training: - Transformers 4.36.0.dev0 - Pytorch 2.1.1+cu121 - Datasets 2.15.0 -- Tokenizers 0.15.0 \ No newline at end of file +- Tokenizers 0.15.0 +# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) +Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Rijgersberg__GEITje-7B) + +| Metric |Value| +|---------------------------------|----:| +|Avg. |50.53| +|AI2 Reasoning Challenge (25-Shot)|44.80| +|HellaSwag (10-Shot) |75.31| +|MMLU (5-Shot) |50.10| +|TruthfulQA (0-shot) |40.45| +|Winogrande (5-shot) |72.38| +|GSM8k (5-shot) |20.17| + diff --git a/checkpoint-1194/config.json b/checkpoint-1194/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-1194/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-1194/generation_config.json b/checkpoint-1194/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-1194/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-1194/model-00001-of-00003.safetensors b/checkpoint-1194/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..05f3c03eb9b8793559f51c9ac5893c7a4fdd4760 --- /dev/null +++ b/checkpoint-1194/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc967d7e09b24a15c159e3264fe80ef0ba1a91a815c33fb63e4f3294746b6c4b +size 4943162336 diff --git a/checkpoint-1194/model-00002-of-00003.safetensors b/checkpoint-1194/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cf74cee6bd89320da404699668f090e0b5fce21e --- /dev/null +++ b/checkpoint-1194/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a65f5f213c5d7467d89f5edd8350724f7fcba5488e963a4edb2075753807921 +size 4999819336 diff --git a/checkpoint-1194/model-00003-of-00003.safetensors b/checkpoint-1194/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9d0d0c7c02f50da16fdbf09ecd2388a9607253ce --- /dev/null +++ b/checkpoint-1194/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0128d7fe33e0f04806fcd8528853961f3a5337c8a4279fd12d83ac0abb917ea +size 4540516344 diff --git a/checkpoint-1194/model.safetensors.index.json b/checkpoint-1194/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-1194/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-1194/optimizer.pt b/checkpoint-1194/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..d66a0b1f788f5320462a1a463348e4e4f38625ba --- /dev/null +++ b/checkpoint-1194/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:644622e35f12e4499dc102cca00cd0c59800c73c5549380781cfe2ec48c565cc +size 14512103560 diff --git a/checkpoint-1194/rng_state_0.pth b/checkpoint-1194/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..572d9bd86f4559e91e7b9a4fdc47494e5c6e9568 --- /dev/null +++ b/checkpoint-1194/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7d7e02ffb4d440dce7ab4ce0b5617578ec9ce3672acee7434ed6f1153f1ae0c +size 15984 diff --git a/checkpoint-1194/rng_state_1.pth b/checkpoint-1194/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..0d21df4c1d8717a3994f151fbc05460a0172725e --- /dev/null +++ b/checkpoint-1194/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5b40ca759e432b2688f021b81291d74a40f56a205e9842119f7e772275eebd3 +size 15984 diff --git a/checkpoint-1194/rng_state_2.pth b/checkpoint-1194/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..6048bfa1e35e3b563aec9f5c1c6788496c3f068d --- /dev/null +++ b/checkpoint-1194/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdaef955ddd36d6bc1c40584113dd6205483e2aa85b02439b8b27e82e02a8359 +size 15984 diff --git a/checkpoint-1194/rng_state_3.pth b/checkpoint-1194/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..3722ed81a034ae380c794d8b45b0464c00099aa6 --- /dev/null +++ b/checkpoint-1194/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10b14ae5db356e6512538751d6b386c190754e307cc99cd652d5c6dd891e1f82 +size 15984 diff --git a/checkpoint-1194/rng_state_4.pth b/checkpoint-1194/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..13231ff967baa9c056d5a7ec0cc489a62679039c --- /dev/null +++ b/checkpoint-1194/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f26e28be26826eeeed244b77185c67b443ac185175f8d4bf5ba94caa8b271bc5 +size 15984 diff --git a/checkpoint-1194/rng_state_5.pth b/checkpoint-1194/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..f3401deecf687fd1382dae699b8d2e1a52949a4a --- /dev/null +++ b/checkpoint-1194/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:847cedc1d6ca26f299a132c2ade9754887374acb9d98f26594a85d4c7742d474 +size 15984 diff --git a/checkpoint-1194/rng_state_6.pth b/checkpoint-1194/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..90ab10b8ff32ba08d69bdf75cb904d226b3d9008 --- /dev/null +++ b/checkpoint-1194/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd043d1690ae0ff6991b03322799a0b28f021427b15fd9f1e5ed8b9905d9307 +size 15984 diff --git a/checkpoint-1194/rng_state_7.pth b/checkpoint-1194/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..3c6fb5670c4f108f08c81f04f22272cdd57b7745 --- /dev/null +++ b/checkpoint-1194/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:772190f7e6667c865d25fc72da7bdd1b5d39f46fe03bb5c2d754aee1ad3c99c7 +size 15984 diff --git a/checkpoint-1194/scheduler.pt b/checkpoint-1194/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..9ade7e5492fb9268b42f1fe4fbd80503595b0a64 --- /dev/null +++ b/checkpoint-1194/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16a7c4866f6e6ad2649c5b44240e22849a3ac060771cdd807355f8b2b5d00479 +size 1064 diff --git a/checkpoint-1194/special_tokens_map.json b/checkpoint-1194/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-1194/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-1194/tokenizer.model b/checkpoint-1194/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-1194/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-1194/tokenizer_config.json b/checkpoint-1194/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-1194/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-1194/trainer_state.json b/checkpoint-1194/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..d5d7d3cf5a01f16637f2539f0d06a71262f5916e --- /dev/null +++ b/checkpoint-1194/trainer_state.json @@ -0,0 +1,7232 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.12520973154362416, + "eval_steps": 199, + "global_step": 1194, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 5.341526771917809e+19, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1194/training_args.bin b/checkpoint-1194/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-1194/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-1592/config.json b/checkpoint-1592/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-1592/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-1592/generation_config.json b/checkpoint-1592/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-1592/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-1592/model-00001-of-00003.safetensors b/checkpoint-1592/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2dff699a16b5cc3e10ac35613ff4c339ce0efda1 --- /dev/null +++ b/checkpoint-1592/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0c1d973fe8dba8837f33ed095c8dc417e036ccb5aebcf451a07726d1ddea265 +size 4943162336 diff --git a/checkpoint-1592/model-00002-of-00003.safetensors b/checkpoint-1592/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..651c1c5daddc90de5c28e31b7430bd0faf90b285 --- /dev/null +++ b/checkpoint-1592/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e1efcdff5db880e764ca41478454352cdd5aad9171929c54d9c46e398f637a4 +size 4999819336 diff --git a/checkpoint-1592/model-00003-of-00003.safetensors b/checkpoint-1592/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..066a3323a9e74f8914783292a34df92ca41476bf --- /dev/null +++ b/checkpoint-1592/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4ec182fe95fb7e0f61fb9618b764e9c51ebb557fe2aa5ada24ed528354e4bf0 +size 4540516344 diff --git a/checkpoint-1592/model.safetensors.index.json b/checkpoint-1592/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-1592/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-1592/optimizer.pt b/checkpoint-1592/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..7cb15dce6877d57b79b8fec0e98ed9ee15c36e99 --- /dev/null +++ b/checkpoint-1592/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39e3f9dbe5ebdc37fcd897a04a4bda7e33a062516f4ab1c7b5fbc08d8bdc4268 +size 14512103560 diff --git a/checkpoint-1592/rng_state_0.pth b/checkpoint-1592/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..ee83ae5e323e0bb676daf05f7f41b7951b49c7af --- /dev/null +++ b/checkpoint-1592/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae9162e03c562553a5d9d13120f544d3c47ea71bb39aa44e18253675e17ed4a4 +size 15984 diff --git a/checkpoint-1592/rng_state_1.pth b/checkpoint-1592/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..0cd0edf74beb406ae74d27fac689e74cc1a7d12b --- /dev/null +++ b/checkpoint-1592/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4809456871b3a40c8db7e0926a9db11b01149a1d483fb29b16fc69dabaf36c6f +size 15984 diff --git a/checkpoint-1592/rng_state_2.pth b/checkpoint-1592/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..378e4e23e02084387cef58f5bfa08ef5b23ef1b3 --- /dev/null +++ b/checkpoint-1592/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bb6bcf25ff148b74eea7dd4895fc42e9433538fff5d75f0d2ae6cb0c2fdadf0 +size 15984 diff --git a/checkpoint-1592/rng_state_3.pth b/checkpoint-1592/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..c9d23b00a6e62ab23a83b688e4077471f0501ba0 --- /dev/null +++ b/checkpoint-1592/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f00ea04cd1a52c539d9cc948ac8a04676d6b99702acd09149565f781806f63f +size 15984 diff --git a/checkpoint-1592/rng_state_4.pth b/checkpoint-1592/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..cf6105fec105f5636599de6b5ea414adc300ed30 --- /dev/null +++ b/checkpoint-1592/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5571fb2fc1b413792b01ac691c759786855573992bab1d14875faccdaf8c881e +size 15984 diff --git a/checkpoint-1592/rng_state_5.pth b/checkpoint-1592/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..983c7580e17a958602e3218e885e88e85d4ed9a0 --- /dev/null +++ b/checkpoint-1592/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59019ba23ead9c15851cb4349397254458ce50ea3c2987090404f4f3842c6d8f +size 15984 diff --git a/checkpoint-1592/rng_state_6.pth b/checkpoint-1592/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..1f87fedb0a1eac5d251eeb1e7cf58190877f6b60 --- /dev/null +++ b/checkpoint-1592/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45fdffda57fda4a555da7a5de6fc6ec7324e0dae048b92519af6c4f6a1bc7412 +size 15984 diff --git a/checkpoint-1592/rng_state_7.pth b/checkpoint-1592/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..d32d0d7a4ca68837a8e91f7101758f2f48116bde --- /dev/null +++ b/checkpoint-1592/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62fb2c13e63aba83c4505fae1639f79a33853d8f1bebe20cecb73bf53c8e7c46 +size 15984 diff --git a/checkpoint-1592/scheduler.pt b/checkpoint-1592/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..9495fd5a953423862c7cbbd298cee9033309716d --- /dev/null +++ b/checkpoint-1592/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaeee36e9e32f47a8103c0282165dc979b2e4bb1e85781ded54e0c018f34feb4 +size 1064 diff --git a/checkpoint-1592/special_tokens_map.json b/checkpoint-1592/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-1592/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-1592/tokenizer.model b/checkpoint-1592/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-1592/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-1592/tokenizer_config.json b/checkpoint-1592/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-1592/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-1592/trainer_state.json b/checkpoint-1592/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..fe77b4acf503e868b2b0b4d94b7eb37508d0c6cb --- /dev/null +++ b/checkpoint-1592/trainer_state.json @@ -0,0 +1,9636 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.1669463087248322, + "eval_steps": 199, + "global_step": 1592, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 7.122035695890412e+19, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1592/training_args.bin b/checkpoint-1592/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-1592/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-1990/config.json b/checkpoint-1990/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-1990/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-1990/generation_config.json b/checkpoint-1990/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-1990/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-1990/model-00001-of-00003.safetensors b/checkpoint-1990/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..34ab0ce47bd5b10c93b002ab7d8f1fd47bd0caa4 --- /dev/null +++ b/checkpoint-1990/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:459ec1bc27bd2b3523fe4d6ed83f52f26c43ad0738443f101eb4bb8163c42d16 +size 4943162336 diff --git a/checkpoint-1990/model-00002-of-00003.safetensors b/checkpoint-1990/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9fbe96d524761eb2b8b1ee0413738c697a74214f --- /dev/null +++ b/checkpoint-1990/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a103645169a2888431a264ed95bb680b4fb2a216102093240643cdb341e6096 +size 4999819336 diff --git a/checkpoint-1990/model-00003-of-00003.safetensors b/checkpoint-1990/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0f1c02e473ecf0d34e7c8fd12c44a79cafe3ecd5 --- /dev/null +++ b/checkpoint-1990/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28375d257d9c63152ee1f03fda716112e2eabfad1ab554db01818e323a8588df +size 4540516344 diff --git a/checkpoint-1990/model.safetensors.index.json b/checkpoint-1990/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-1990/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-1990/optimizer.pt b/checkpoint-1990/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..136b8c5cdf044986aa14f7c6a316a5be2f38c40a --- /dev/null +++ b/checkpoint-1990/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0896ac95a388f9ba5c5ef6bcab656f87d3dd7af963f982d8668122bdd8e9d4c1 +size 14512103560 diff --git a/checkpoint-1990/rng_state_0.pth b/checkpoint-1990/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..0b8b4067e4559b34f9b554c4963fe80d7f5fe839 --- /dev/null +++ b/checkpoint-1990/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba4c26c615bd5830d41566fab54dc69174be292761b34514b27fbe82b45b630b +size 15984 diff --git a/checkpoint-1990/rng_state_1.pth b/checkpoint-1990/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..8c0265e51b5761ac9b323aa87ba00ba14b97e202 --- /dev/null +++ b/checkpoint-1990/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60c761d7f9b90c29c2d348a1133fd39be52c65e6bee4c2d179f6a6e564eb3a40 +size 15984 diff --git a/checkpoint-1990/rng_state_2.pth b/checkpoint-1990/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..f5dd5aabcd6e7332f14a4796d6ec6c758e10aea0 --- /dev/null +++ b/checkpoint-1990/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccab847cc956e055fd3f9dcce06898826d065211e945b83576c8d487f87c5469 +size 15984 diff --git a/checkpoint-1990/rng_state_3.pth b/checkpoint-1990/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..bcbdea3a573c2b7717f23e2ea0e4a6da6670d65d --- /dev/null +++ b/checkpoint-1990/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e5f1dbdcf6ec820c22fd1e4258fcd7af2a2bce65c480988d3f111aa574c9c06 +size 15984 diff --git a/checkpoint-1990/rng_state_4.pth b/checkpoint-1990/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..1cdcb8d1710063a6c30dec635b4c44e3cb6cd24e --- /dev/null +++ b/checkpoint-1990/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a23184c3e806d2649776427d1da2c0c9137f9b23a84468f3bdd5bbc75f696c9 +size 15984 diff --git a/checkpoint-1990/rng_state_5.pth b/checkpoint-1990/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..0e39323a662c284cd109b5ce8c39e8a0ce375f2c --- /dev/null +++ b/checkpoint-1990/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:382fc01b809542bf6f5e26742e3e19e80a1f189ac5de24cf8cd822e303916b83 +size 15984 diff --git a/checkpoint-1990/rng_state_6.pth b/checkpoint-1990/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..1ce685d2e57181f70debfb25eb90cb76ceaf47da --- /dev/null +++ b/checkpoint-1990/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b178265c7d2ae07bff10b7312e5e49b9f5b4914c38969d2f64a6ca006296bca +size 15984 diff --git a/checkpoint-1990/rng_state_7.pth b/checkpoint-1990/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..a5e363b8083cdd817e0b3a2e6fd1b65a905e189b --- /dev/null +++ b/checkpoint-1990/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:668825a859126c4cf32afb883895c91004130b6aee02178736ca2840e5429ad0 +size 15984 diff --git a/checkpoint-1990/scheduler.pt b/checkpoint-1990/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..df6d5b95e918f86ee7920ae61f70117518a22cc5 --- /dev/null +++ b/checkpoint-1990/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfd303fb1bde51cca6376c51db38888dc69c5b1005e5dc60fbb555d292428ffe +size 1064 diff --git a/checkpoint-1990/special_tokens_map.json b/checkpoint-1990/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-1990/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-1990/tokenizer.model b/checkpoint-1990/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-1990/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-1990/tokenizer_config.json b/checkpoint-1990/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-1990/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-1990/trainer_state.json b/checkpoint-1990/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..2b43c7a7a8072f3f344edb58748d318c0be691d2 --- /dev/null +++ b/checkpoint-1990/trainer_state.json @@ -0,0 +1,12040 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.20868288590604026, + "eval_steps": 199, + "global_step": 1990, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 8.902544619863015e+19, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1990/training_args.bin b/checkpoint-1990/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-1990/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-2388/config.json b/checkpoint-2388/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-2388/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-2388/generation_config.json b/checkpoint-2388/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-2388/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-2388/model-00001-of-00003.safetensors b/checkpoint-2388/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8798fe27620d9e1df6aa18febd9827d6246ea80a --- /dev/null +++ b/checkpoint-2388/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b3ef7041f45192f954c3b49833c08b0b110d471ee4f4f6d0b59027b4189747 +size 4943162336 diff --git a/checkpoint-2388/model-00002-of-00003.safetensors b/checkpoint-2388/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..66256ff1e072041306f5a9db4e9aef61dbb67447 --- /dev/null +++ b/checkpoint-2388/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5df41065453125761c16d9311256667fac34c2fd768f3443d9873b773e727ca +size 4999819336 diff --git a/checkpoint-2388/model-00003-of-00003.safetensors b/checkpoint-2388/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d50690d3a59549bded6c4a9cc80ac58070a59ea --- /dev/null +++ b/checkpoint-2388/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1ef33167576c92887571791ca46dfa17a42df3a1c6a93d763dbcf21ec558dec +size 4540516344 diff --git a/checkpoint-2388/model.safetensors.index.json b/checkpoint-2388/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-2388/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-2388/optimizer.pt b/checkpoint-2388/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..280cdf0ebd2983ae169bc7622822fa5f46d6b5ec --- /dev/null +++ b/checkpoint-2388/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8f849f8569e0a8e763acc5ff8f5eff47d8e2cd9d9038413c66a2a467494e2b9 +size 14512103560 diff --git a/checkpoint-2388/rng_state_0.pth b/checkpoint-2388/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..97f51b498d48145bd9cc14b35f8236b9ec95a4f7 --- /dev/null +++ b/checkpoint-2388/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1bec598899f9d59e70c1b4705ce420a1e0a670957b6c8153a589880068ae5a4 +size 15984 diff --git a/checkpoint-2388/rng_state_1.pth b/checkpoint-2388/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..08e59ac81067b262a084604cd3392250166c2841 --- /dev/null +++ b/checkpoint-2388/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c60d2348aae518f4c44693db9c9b4b3a3299c556e7f0a86c188b2e4c3e364a7c +size 15984 diff --git a/checkpoint-2388/rng_state_2.pth b/checkpoint-2388/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..20a24c17b4be2ee59cd5e6682010519318a91e58 --- /dev/null +++ b/checkpoint-2388/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffe5a79d3bcb4ce033de360bc765e616316e3562aba25887cd85c4adbb935abf +size 15984 diff --git a/checkpoint-2388/rng_state_3.pth b/checkpoint-2388/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..54050f6cf8fb847e2a926e14a7aad2647761521a --- /dev/null +++ b/checkpoint-2388/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9a9d1f6e22677721841890e6a27855857e6840137650d609eb8e4ac13b71d29 +size 15984 diff --git a/checkpoint-2388/rng_state_4.pth b/checkpoint-2388/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..263aae475c49b090bce43f143308192c5bf9a95b --- /dev/null +++ b/checkpoint-2388/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcac4ff84388a6a4fe3bcae6207c68b2ee5528fb3b6de8cc3588fe1975462aa5 +size 15984 diff --git a/checkpoint-2388/rng_state_5.pth b/checkpoint-2388/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..942ed5d60ae87dce686b33da76a34db404036dc6 --- /dev/null +++ b/checkpoint-2388/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33fce3cdf5c1b8a8a291e0c73b384e3ad5252640e21e942b44b26b8b0928ffa9 +size 15984 diff --git a/checkpoint-2388/rng_state_6.pth b/checkpoint-2388/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..57789be3df3983cb8acc1500bf6470ffadb1c578 --- /dev/null +++ b/checkpoint-2388/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:919e675f3bcaf4f3c8ba35cd8debf85aec3bbc3c8e5019b74431e0a314e4d37a +size 15984 diff --git a/checkpoint-2388/rng_state_7.pth b/checkpoint-2388/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..b32d6e2e7eb7148713b473b0c821a98e616ab6e6 --- /dev/null +++ b/checkpoint-2388/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bf6479ce82b88efc6a72a8ee512162b3d0ecab972817296d38ab9c448bb8d96 +size 15984 diff --git a/checkpoint-2388/scheduler.pt b/checkpoint-2388/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..0996b6c3aac21037be5faf794d19a1716701082d --- /dev/null +++ b/checkpoint-2388/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28565d58e33d48683de07b9c3a8b794b5fa11f1ddc86a717755b968d9db98799 +size 1064 diff --git a/checkpoint-2388/special_tokens_map.json b/checkpoint-2388/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-2388/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-2388/tokenizer.model b/checkpoint-2388/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-2388/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-2388/tokenizer_config.json b/checkpoint-2388/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-2388/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-2388/trainer_state.json b/checkpoint-2388/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..d40fdf1adaeeb37b46dcc429ec448bc5ebd2de9f --- /dev/null +++ b/checkpoint-2388/trainer_state.json @@ -0,0 +1,14444 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.25041946308724833, + "eval_steps": 199, + "global_step": 2388, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + }, + { + "epoch": 0.21, + "learning_rate": 1.928689129323009e-05, + "loss": 1.421, + "step": 1991 + }, + { + "epoch": 0.21, + "learning_rate": 1.928553323396003e-05, + "loss": 1.5625, + "step": 1992 + }, + { + "epoch": 0.21, + "learning_rate": 1.92841739306671e-05, + "loss": 1.5198, + "step": 1993 + }, + { + "epoch": 0.21, + "learning_rate": 1.9282813383533415e-05, + "loss": 1.5116, + "step": 1994 + }, + { + "epoch": 0.21, + "learning_rate": 1.9281451592741247e-05, + "loss": 1.4306, + "step": 1995 + }, + { + "epoch": 0.21, + "learning_rate": 1.9280088558473046e-05, + "loss": 1.5425, + "step": 1996 + }, + { + "epoch": 0.21, + "learning_rate": 1.9278724280911424e-05, + "loss": 1.4972, + "step": 1997 + }, + { + "epoch": 0.21, + "learning_rate": 1.9277358760239156e-05, + "loss": 1.5185, + "step": 1998 + }, + { + "epoch": 0.21, + "learning_rate": 1.9275991996639188e-05, + "loss": 1.5187, + "step": 1999 + }, + { + "epoch": 0.21, + "learning_rate": 1.927462399029463e-05, + "loss": 1.4325, + "step": 2000 + }, + { + "epoch": 0.21, + "learning_rate": 1.9273254741388763e-05, + "loss": 1.4397, + "step": 2001 + }, + { + "epoch": 0.21, + "learning_rate": 1.927188425010503e-05, + "loss": 1.5319, + "step": 2002 + }, + { + "epoch": 0.21, + "learning_rate": 1.9270512516627042e-05, + "loss": 1.5664, + "step": 2003 + }, + { + "epoch": 0.21, + "learning_rate": 1.9269139541138574e-05, + "loss": 1.5227, + "step": 2004 + }, + { + "epoch": 0.21, + "learning_rate": 1.926776532382357e-05, + "loss": 1.5187, + "step": 2005 + }, + { + "epoch": 0.21, + "learning_rate": 1.9266389864866134e-05, + "loss": 1.4029, + "step": 2006 + }, + { + "epoch": 0.21, + "learning_rate": 1.9265013164450557e-05, + "loss": 1.387, + "step": 2007 + }, + { + "epoch": 0.21, + "learning_rate": 1.9263635222761268e-05, + "loss": 1.5047, + "step": 2008 + }, + { + "epoch": 0.21, + "learning_rate": 1.9262256039982882e-05, + "loss": 1.4816, + "step": 2009 + }, + { + "epoch": 0.21, + "learning_rate": 1.9260875616300172e-05, + "loss": 1.4607, + "step": 2010 + }, + { + "epoch": 0.21, + "learning_rate": 1.9259493951898084e-05, + "loss": 1.628, + "step": 2011 + }, + { + "epoch": 0.21, + "learning_rate": 1.9258111046961714e-05, + "loss": 1.4149, + "step": 2012 + }, + { + "epoch": 0.21, + "learning_rate": 1.925672690167635e-05, + "loss": 1.5303, + "step": 2013 + }, + { + "epoch": 0.21, + "learning_rate": 1.925534151622742e-05, + "loss": 1.5198, + "step": 2014 + }, + { + "epoch": 0.21, + "learning_rate": 1.9253954890800535e-05, + "loss": 1.6422, + "step": 2015 + }, + { + "epoch": 0.21, + "learning_rate": 1.925256702558147e-05, + "loss": 1.4738, + "step": 2016 + }, + { + "epoch": 0.21, + "learning_rate": 1.925117792075616e-05, + "loss": 1.4752, + "step": 2017 + }, + { + "epoch": 0.21, + "learning_rate": 1.9249787576510713e-05, + "loss": 1.4547, + "step": 2018 + }, + { + "epoch": 0.21, + "learning_rate": 1.924839599303139e-05, + "loss": 1.4864, + "step": 2019 + }, + { + "epoch": 0.21, + "learning_rate": 1.9247003170504638e-05, + "loss": 1.5037, + "step": 2020 + }, + { + "epoch": 0.21, + "learning_rate": 1.9245609109117053e-05, + "loss": 1.5089, + "step": 2021 + }, + { + "epoch": 0.21, + "learning_rate": 1.924421380905541e-05, + "loss": 1.5616, + "step": 2022 + }, + { + "epoch": 0.21, + "learning_rate": 1.9242817270506634e-05, + "loss": 1.4592, + "step": 2023 + }, + { + "epoch": 0.21, + "learning_rate": 1.9241419493657832e-05, + "loss": 1.5592, + "step": 2024 + }, + { + "epoch": 0.21, + "learning_rate": 1.924002047869627e-05, + "loss": 1.4897, + "step": 2025 + }, + { + "epoch": 0.21, + "learning_rate": 1.9238620225809375e-05, + "loss": 1.4743, + "step": 2026 + }, + { + "epoch": 0.21, + "learning_rate": 1.923721873518475e-05, + "loss": 1.4686, + "step": 2027 + }, + { + "epoch": 0.21, + "learning_rate": 1.923581600701016e-05, + "loss": 1.461, + "step": 2028 + }, + { + "epoch": 0.21, + "learning_rate": 1.9234412041473528e-05, + "loss": 1.6622, + "step": 2029 + }, + { + "epoch": 0.21, + "learning_rate": 1.9233006838762955e-05, + "loss": 1.4707, + "step": 2030 + }, + { + "epoch": 0.21, + "learning_rate": 1.92316003990667e-05, + "loss": 1.5566, + "step": 2031 + }, + { + "epoch": 0.21, + "learning_rate": 1.9230192722573188e-05, + "loss": 1.4881, + "step": 2032 + }, + { + "epoch": 0.21, + "learning_rate": 1.9228783809471015e-05, + "loss": 1.6124, + "step": 2033 + }, + { + "epoch": 0.21, + "learning_rate": 1.9227373659948937e-05, + "loss": 1.3508, + "step": 2034 + }, + { + "epoch": 0.21, + "learning_rate": 1.9225962274195876e-05, + "loss": 1.4418, + "step": 2035 + }, + { + "epoch": 0.21, + "learning_rate": 1.9224549652400927e-05, + "loss": 1.3954, + "step": 2036 + }, + { + "epoch": 0.21, + "learning_rate": 1.922313579475334e-05, + "loss": 1.4798, + "step": 2037 + }, + { + "epoch": 0.21, + "learning_rate": 1.922172070144254e-05, + "loss": 1.4556, + "step": 2038 + }, + { + "epoch": 0.21, + "learning_rate": 1.922030437265811e-05, + "loss": 1.4987, + "step": 2039 + }, + { + "epoch": 0.21, + "learning_rate": 1.9218886808589796e-05, + "loss": 1.4857, + "step": 2040 + }, + { + "epoch": 0.21, + "learning_rate": 1.9217468009427527e-05, + "loss": 1.5289, + "step": 2041 + }, + { + "epoch": 0.21, + "learning_rate": 1.921604797536138e-05, + "loss": 1.5267, + "step": 2042 + }, + { + "epoch": 0.21, + "learning_rate": 1.9214626706581598e-05, + "loss": 1.4655, + "step": 2043 + }, + { + "epoch": 0.21, + "learning_rate": 1.9213204203278602e-05, + "loss": 1.4598, + "step": 2044 + }, + { + "epoch": 0.21, + "learning_rate": 1.9211780465642973e-05, + "loss": 1.4766, + "step": 2045 + }, + { + "epoch": 0.21, + "learning_rate": 1.921035549386545e-05, + "loss": 1.5148, + "step": 2046 + }, + { + "epoch": 0.21, + "learning_rate": 1.9208929288136933e-05, + "loss": 1.5567, + "step": 2047 + }, + { + "epoch": 0.21, + "learning_rate": 1.920750184864852e-05, + "loss": 1.4868, + "step": 2048 + }, + { + "epoch": 0.21, + "learning_rate": 1.920607317559143e-05, + "loss": 1.4752, + "step": 2049 + }, + { + "epoch": 0.21, + "learning_rate": 1.920464326915708e-05, + "loss": 1.4882, + "step": 2050 + }, + { + "epoch": 0.22, + "learning_rate": 1.9203212129537035e-05, + "loss": 1.5933, + "step": 2051 + }, + { + "epoch": 0.22, + "learning_rate": 1.9201779756923037e-05, + "loss": 1.4891, + "step": 2052 + }, + { + "epoch": 0.22, + "learning_rate": 1.9200346151506983e-05, + "loss": 1.4486, + "step": 2053 + }, + { + "epoch": 0.22, + "learning_rate": 1.9198911313480938e-05, + "loss": 1.5091, + "step": 2054 + }, + { + "epoch": 0.22, + "learning_rate": 1.919747524303714e-05, + "loss": 1.4385, + "step": 2055 + }, + { + "epoch": 0.22, + "learning_rate": 1.9196037940367974e-05, + "loss": 1.4104, + "step": 2056 + }, + { + "epoch": 0.22, + "learning_rate": 1.9194599405666015e-05, + "loss": 1.4483, + "step": 2057 + }, + { + "epoch": 0.22, + "learning_rate": 1.9193159639123976e-05, + "loss": 1.4592, + "step": 2058 + }, + { + "epoch": 0.22, + "learning_rate": 1.919171864093476e-05, + "loss": 1.4975, + "step": 2059 + }, + { + "epoch": 0.22, + "learning_rate": 1.9190276411291423e-05, + "loss": 1.4727, + "step": 2060 + }, + { + "epoch": 0.22, + "learning_rate": 1.9188832950387178e-05, + "loss": 1.4791, + "step": 2061 + }, + { + "epoch": 0.22, + "learning_rate": 1.9187388258415423e-05, + "loss": 1.3806, + "step": 2062 + }, + { + "epoch": 0.22, + "learning_rate": 1.9185942335569697e-05, + "loss": 1.4514, + "step": 2063 + }, + { + "epoch": 0.22, + "learning_rate": 1.9184495182043727e-05, + "loss": 1.4389, + "step": 2064 + }, + { + "epoch": 0.22, + "learning_rate": 1.918304679803139e-05, + "loss": 1.5088, + "step": 2065 + }, + { + "epoch": 0.22, + "learning_rate": 1.9181597183726733e-05, + "loss": 1.4665, + "step": 2066 + }, + { + "epoch": 0.22, + "learning_rate": 1.9180146339323966e-05, + "loss": 1.489, + "step": 2067 + }, + { + "epoch": 0.22, + "learning_rate": 1.9178694265017466e-05, + "loss": 1.5215, + "step": 2068 + }, + { + "epoch": 0.22, + "learning_rate": 1.9177240961001775e-05, + "loss": 1.5152, + "step": 2069 + }, + { + "epoch": 0.22, + "learning_rate": 1.9175786427471594e-05, + "loss": 1.4418, + "step": 2070 + }, + { + "epoch": 0.22, + "learning_rate": 1.91743306646218e-05, + "loss": 1.5001, + "step": 2071 + }, + { + "epoch": 0.22, + "learning_rate": 1.9172873672647417e-05, + "loss": 1.4879, + "step": 2072 + }, + { + "epoch": 0.22, + "learning_rate": 1.917141545174366e-05, + "loss": 1.5299, + "step": 2073 + }, + { + "epoch": 0.22, + "learning_rate": 1.9169956002105877e-05, + "loss": 1.4602, + "step": 2074 + }, + { + "epoch": 0.22, + "learning_rate": 1.9168495323929605e-05, + "loss": 1.4921, + "step": 2075 + }, + { + "epoch": 0.22, + "learning_rate": 1.916703341741054e-05, + "loss": 1.4659, + "step": 2076 + }, + { + "epoch": 0.22, + "learning_rate": 1.9165570282744534e-05, + "loss": 1.4707, + "step": 2077 + }, + { + "epoch": 0.22, + "learning_rate": 1.9164105920127613e-05, + "loss": 1.5354, + "step": 2078 + }, + { + "epoch": 0.22, + "learning_rate": 1.9162640329755962e-05, + "loss": 1.526, + "step": 2079 + }, + { + "epoch": 0.22, + "learning_rate": 1.916117351182593e-05, + "loss": 1.6424, + "step": 2080 + }, + { + "epoch": 0.22, + "learning_rate": 1.915970546653404e-05, + "loss": 1.5048, + "step": 2081 + }, + { + "epoch": 0.22, + "learning_rate": 1.915823619407697e-05, + "loss": 1.5344, + "step": 2082 + }, + { + "epoch": 0.22, + "learning_rate": 1.915676569465156e-05, + "loss": 1.4604, + "step": 2083 + }, + { + "epoch": 0.22, + "learning_rate": 1.9155293968454826e-05, + "loss": 1.4929, + "step": 2084 + }, + { + "epoch": 0.22, + "learning_rate": 1.9153821015683937e-05, + "loss": 1.4106, + "step": 2085 + }, + { + "epoch": 0.22, + "learning_rate": 1.915234683653623e-05, + "loss": 1.4146, + "step": 2086 + }, + { + "epoch": 0.22, + "learning_rate": 1.9150871431209207e-05, + "loss": 1.4481, + "step": 2087 + }, + { + "epoch": 0.22, + "learning_rate": 1.914939479990054e-05, + "loss": 1.5206, + "step": 2088 + }, + { + "epoch": 0.22, + "learning_rate": 1.9147916942808054e-05, + "loss": 1.5073, + "step": 2089 + }, + { + "epoch": 0.22, + "learning_rate": 1.9146437860129745e-05, + "loss": 1.5196, + "step": 2090 + }, + { + "epoch": 0.22, + "learning_rate": 1.9144957552063775e-05, + "loss": 1.5389, + "step": 2091 + }, + { + "epoch": 0.22, + "learning_rate": 1.9143476018808463e-05, + "loss": 1.5207, + "step": 2092 + }, + { + "epoch": 0.22, + "learning_rate": 1.9141993260562298e-05, + "loss": 1.3717, + "step": 2093 + }, + { + "epoch": 0.22, + "learning_rate": 1.9140509277523937e-05, + "loss": 1.471, + "step": 2094 + }, + { + "epoch": 0.22, + "learning_rate": 1.9139024069892185e-05, + "loss": 1.4553, + "step": 2095 + }, + { + "epoch": 0.22, + "learning_rate": 1.9137537637866027e-05, + "loss": 1.5311, + "step": 2096 + }, + { + "epoch": 0.22, + "learning_rate": 1.9136049981644614e-05, + "loss": 1.4369, + "step": 2097 + }, + { + "epoch": 0.22, + "learning_rate": 1.913456110142724e-05, + "loss": 1.4528, + "step": 2098 + }, + { + "epoch": 0.22, + "learning_rate": 1.9133070997413384e-05, + "loss": 1.5294, + "step": 2099 + }, + { + "epoch": 0.22, + "learning_rate": 1.9131579669802685e-05, + "loss": 1.4588, + "step": 2100 + }, + { + "epoch": 0.22, + "learning_rate": 1.9130087118794934e-05, + "loss": 1.443, + "step": 2101 + }, + { + "epoch": 0.22, + "learning_rate": 1.9128593344590102e-05, + "loss": 1.4876, + "step": 2102 + }, + { + "epoch": 0.22, + "learning_rate": 1.912709834738831e-05, + "loss": 1.4874, + "step": 2103 + }, + { + "epoch": 0.22, + "learning_rate": 1.9125602127389856e-05, + "loss": 1.4966, + "step": 2104 + }, + { + "epoch": 0.22, + "learning_rate": 1.912410468479519e-05, + "loss": 1.5747, + "step": 2105 + }, + { + "epoch": 0.22, + "learning_rate": 1.9122606019804933e-05, + "loss": 1.4025, + "step": 2106 + }, + { + "epoch": 0.22, + "learning_rate": 1.912110613261987e-05, + "loss": 1.4755, + "step": 2107 + }, + { + "epoch": 0.22, + "learning_rate": 1.911960502344094e-05, + "loss": 1.4739, + "step": 2108 + }, + { + "epoch": 0.22, + "learning_rate": 1.911810269246926e-05, + "loss": 1.4992, + "step": 2109 + }, + { + "epoch": 0.22, + "learning_rate": 1.91165991399061e-05, + "loss": 1.4435, + "step": 2110 + }, + { + "epoch": 0.22, + "learning_rate": 1.91150943659529e-05, + "loss": 1.4918, + "step": 2111 + }, + { + "epoch": 0.22, + "learning_rate": 1.9113588370811258e-05, + "loss": 1.3818, + "step": 2112 + }, + { + "epoch": 0.22, + "learning_rate": 1.911208115468294e-05, + "loss": 1.5105, + "step": 2113 + }, + { + "epoch": 0.22, + "learning_rate": 1.9110572717769878e-05, + "loss": 1.6634, + "step": 2114 + }, + { + "epoch": 0.22, + "learning_rate": 1.9109063060274158e-05, + "loss": 1.5028, + "step": 2115 + }, + { + "epoch": 0.22, + "learning_rate": 1.9107552182398037e-05, + "loss": 1.6657, + "step": 2116 + }, + { + "epoch": 0.22, + "learning_rate": 1.9106040084343935e-05, + "loss": 1.5481, + "step": 2117 + }, + { + "epoch": 0.22, + "learning_rate": 1.910452676631444e-05, + "loss": 1.4505, + "step": 2118 + }, + { + "epoch": 0.22, + "learning_rate": 1.9103012228512284e-05, + "loss": 1.5173, + "step": 2119 + }, + { + "epoch": 0.22, + "learning_rate": 1.9101496471140385e-05, + "loss": 1.3788, + "step": 2120 + }, + { + "epoch": 0.22, + "learning_rate": 1.9099979494401814e-05, + "loss": 1.4649, + "step": 2121 + }, + { + "epoch": 0.22, + "learning_rate": 1.9098461298499805e-05, + "loss": 1.4204, + "step": 2122 + }, + { + "epoch": 0.22, + "learning_rate": 1.9096941883637766e-05, + "loss": 1.4439, + "step": 2123 + }, + { + "epoch": 0.22, + "learning_rate": 1.909542125001925e-05, + "loss": 1.6615, + "step": 2124 + }, + { + "epoch": 0.22, + "learning_rate": 1.9093899397847985e-05, + "loss": 1.4763, + "step": 2125 + }, + { + "epoch": 0.22, + "learning_rate": 1.909237632732786e-05, + "loss": 1.5353, + "step": 2126 + }, + { + "epoch": 0.22, + "learning_rate": 1.909085203866293e-05, + "loss": 1.442, + "step": 2127 + }, + { + "epoch": 0.22, + "learning_rate": 1.9089326532057408e-05, + "loss": 1.4782, + "step": 2128 + }, + { + "epoch": 0.22, + "learning_rate": 1.908779980771567e-05, + "loss": 1.4933, + "step": 2129 + }, + { + "epoch": 0.22, + "learning_rate": 1.9086271865842264e-05, + "loss": 1.5285, + "step": 2130 + }, + { + "epoch": 0.22, + "learning_rate": 1.9084742706641894e-05, + "loss": 1.4736, + "step": 2131 + }, + { + "epoch": 0.22, + "learning_rate": 1.9083212330319427e-05, + "loss": 1.4496, + "step": 2132 + }, + { + "epoch": 0.22, + "learning_rate": 1.908168073707989e-05, + "loss": 1.5099, + "step": 2133 + }, + { + "epoch": 0.22, + "learning_rate": 1.9080147927128483e-05, + "loss": 1.5235, + "step": 2134 + }, + { + "epoch": 0.22, + "learning_rate": 1.9078613900670556e-05, + "loss": 1.4769, + "step": 2135 + }, + { + "epoch": 0.22, + "learning_rate": 1.907707865791164e-05, + "loss": 1.5771, + "step": 2136 + }, + { + "epoch": 0.22, + "learning_rate": 1.907554219905741e-05, + "loss": 1.5116, + "step": 2137 + }, + { + "epoch": 0.22, + "learning_rate": 1.907400452431371e-05, + "loss": 1.5161, + "step": 2138 + }, + { + "epoch": 0.22, + "learning_rate": 1.9072465633886557e-05, + "loss": 1.4356, + "step": 2139 + }, + { + "epoch": 0.22, + "learning_rate": 1.9070925527982117e-05, + "loss": 1.509, + "step": 2140 + }, + { + "epoch": 0.22, + "learning_rate": 1.9069384206806723e-05, + "loss": 1.4681, + "step": 2141 + }, + { + "epoch": 0.22, + "learning_rate": 1.9067841670566883e-05, + "loss": 1.5254, + "step": 2142 + }, + { + "epoch": 0.22, + "learning_rate": 1.9066297919469242e-05, + "loss": 1.4797, + "step": 2143 + }, + { + "epoch": 0.22, + "learning_rate": 1.9064752953720636e-05, + "loss": 1.3996, + "step": 2144 + }, + { + "epoch": 0.22, + "learning_rate": 1.9063206773528042e-05, + "loss": 1.4457, + "step": 2145 + }, + { + "epoch": 0.23, + "learning_rate": 1.9061659379098617e-05, + "loss": 1.5126, + "step": 2146 + }, + { + "epoch": 0.23, + "learning_rate": 1.9060110770639664e-05, + "loss": 1.5925, + "step": 2147 + }, + { + "epoch": 0.23, + "learning_rate": 1.905856094835866e-05, + "loss": 1.5146, + "step": 2148 + }, + { + "epoch": 0.23, + "learning_rate": 1.905700991246324e-05, + "loss": 1.7256, + "step": 2149 + }, + { + "epoch": 0.23, + "learning_rate": 1.90554576631612e-05, + "loss": 1.57, + "step": 2150 + }, + { + "epoch": 0.23, + "learning_rate": 1.905390420066051e-05, + "loss": 1.3722, + "step": 2151 + }, + { + "epoch": 0.23, + "learning_rate": 1.9052349525169292e-05, + "loss": 1.3999, + "step": 2152 + }, + { + "epoch": 0.23, + "learning_rate": 1.9050793636895828e-05, + "loss": 1.586, + "step": 2153 + }, + { + "epoch": 0.23, + "learning_rate": 1.9049236536048567e-05, + "loss": 1.4884, + "step": 2154 + }, + { + "epoch": 0.23, + "learning_rate": 1.9047678222836127e-05, + "loss": 1.5898, + "step": 2155 + }, + { + "epoch": 0.23, + "learning_rate": 1.9046118697467278e-05, + "loss": 1.569, + "step": 2156 + }, + { + "epoch": 0.23, + "learning_rate": 1.904455796015095e-05, + "loss": 1.5592, + "step": 2157 + }, + { + "epoch": 0.23, + "learning_rate": 1.9042996011096253e-05, + "loss": 1.597, + "step": 2158 + }, + { + "epoch": 0.23, + "learning_rate": 1.904143285051244e-05, + "loss": 1.422, + "step": 2159 + }, + { + "epoch": 0.23, + "learning_rate": 1.903986847860894e-05, + "loss": 1.519, + "step": 2160 + }, + { + "epoch": 0.23, + "learning_rate": 1.9038302895595334e-05, + "loss": 1.5197, + "step": 2161 + }, + { + "epoch": 0.23, + "learning_rate": 1.903673610168137e-05, + "loss": 1.4655, + "step": 2162 + }, + { + "epoch": 0.23, + "learning_rate": 1.9035168097076965e-05, + "loss": 1.3909, + "step": 2163 + }, + { + "epoch": 0.23, + "learning_rate": 1.903359888199218e-05, + "loss": 1.4877, + "step": 2164 + }, + { + "epoch": 0.23, + "learning_rate": 1.903202845663726e-05, + "loss": 1.5123, + "step": 2165 + }, + { + "epoch": 0.23, + "learning_rate": 1.9030456821222593e-05, + "loss": 1.4906, + "step": 2166 + }, + { + "epoch": 0.23, + "learning_rate": 1.9028883975958745e-05, + "loss": 1.4574, + "step": 2167 + }, + { + "epoch": 0.23, + "learning_rate": 1.9027309921056435e-05, + "loss": 1.4571, + "step": 2168 + }, + { + "epoch": 0.23, + "learning_rate": 1.902573465672654e-05, + "loss": 1.4281, + "step": 2169 + }, + { + "epoch": 0.23, + "learning_rate": 1.9024158183180116e-05, + "loss": 1.5057, + "step": 2170 + }, + { + "epoch": 0.23, + "learning_rate": 1.902258050062836e-05, + "loss": 1.4514, + "step": 2171 + }, + { + "epoch": 0.23, + "learning_rate": 1.9021001609282646e-05, + "loss": 1.5055, + "step": 2172 + }, + { + "epoch": 0.23, + "learning_rate": 1.9019421509354505e-05, + "loss": 1.4578, + "step": 2173 + }, + { + "epoch": 0.23, + "learning_rate": 1.9017840201055625e-05, + "loss": 1.459, + "step": 2174 + }, + { + "epoch": 0.23, + "learning_rate": 1.9016257684597864e-05, + "loss": 1.5059, + "step": 2175 + }, + { + "epoch": 0.23, + "learning_rate": 1.901467396019324e-05, + "loss": 1.57, + "step": 2176 + }, + { + "epoch": 0.23, + "learning_rate": 1.901308902805393e-05, + "loss": 1.4924, + "step": 2177 + }, + { + "epoch": 0.23, + "learning_rate": 1.9011502888392273e-05, + "loss": 1.4979, + "step": 2178 + }, + { + "epoch": 0.23, + "learning_rate": 1.900991554142077e-05, + "loss": 1.5321, + "step": 2179 + }, + { + "epoch": 0.23, + "learning_rate": 1.9008326987352093e-05, + "loss": 1.493, + "step": 2180 + }, + { + "epoch": 0.23, + "learning_rate": 1.9006737226399056e-05, + "loss": 1.5111, + "step": 2181 + }, + { + "epoch": 0.23, + "learning_rate": 1.900514625877465e-05, + "loss": 1.4154, + "step": 2182 + }, + { + "epoch": 0.23, + "learning_rate": 1.900355408469203e-05, + "loss": 1.4934, + "step": 2183 + }, + { + "epoch": 0.23, + "learning_rate": 1.90019607043645e-05, + "loss": 1.5975, + "step": 2184 + }, + { + "epoch": 0.23, + "learning_rate": 1.9000366118005532e-05, + "loss": 1.3537, + "step": 2185 + }, + { + "epoch": 0.23, + "learning_rate": 1.899877032582876e-05, + "loss": 1.4583, + "step": 2186 + }, + { + "epoch": 0.23, + "learning_rate": 1.8997173328047984e-05, + "loss": 1.4586, + "step": 2187 + }, + { + "epoch": 0.23, + "learning_rate": 1.8995575124877156e-05, + "loss": 1.4774, + "step": 2188 + }, + { + "epoch": 0.23, + "learning_rate": 1.8993975716530394e-05, + "loss": 1.5025, + "step": 2189 + }, + { + "epoch": 0.23, + "eval_loss": 1.5263344049453735, + "eval_runtime": 77.1492, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 2189 + }, + { + "epoch": 0.23, + "learning_rate": 1.899237510322198e-05, + "loss": 1.5438, + "step": 2190 + }, + { + "epoch": 0.23, + "learning_rate": 1.899077328516635e-05, + "loss": 1.5181, + "step": 2191 + }, + { + "epoch": 0.23, + "learning_rate": 1.8989170262578112e-05, + "loss": 1.4454, + "step": 2192 + }, + { + "epoch": 0.23, + "learning_rate": 1.8987566035672028e-05, + "loss": 1.4882, + "step": 2193 + }, + { + "epoch": 0.23, + "learning_rate": 1.8985960604663026e-05, + "loss": 1.5073, + "step": 2194 + }, + { + "epoch": 0.23, + "learning_rate": 1.8984353969766187e-05, + "loss": 1.4478, + "step": 2195 + }, + { + "epoch": 0.23, + "learning_rate": 1.8982746131196763e-05, + "loss": 1.4768, + "step": 2196 + }, + { + "epoch": 0.23, + "learning_rate": 1.8981137089170162e-05, + "loss": 1.5116, + "step": 2197 + }, + { + "epoch": 0.23, + "learning_rate": 1.8979526843901952e-05, + "loss": 1.4202, + "step": 2198 + }, + { + "epoch": 0.23, + "learning_rate": 1.8977915395607867e-05, + "loss": 1.4736, + "step": 2199 + }, + { + "epoch": 0.23, + "learning_rate": 1.89763027445038e-05, + "loss": 1.4489, + "step": 2200 + }, + { + "epoch": 0.23, + "learning_rate": 1.8974688890805804e-05, + "loss": 1.4512, + "step": 2201 + }, + { + "epoch": 0.23, + "learning_rate": 1.897307383473009e-05, + "loss": 1.5091, + "step": 2202 + }, + { + "epoch": 0.23, + "learning_rate": 1.897145757649304e-05, + "loss": 1.5512, + "step": 2203 + }, + { + "epoch": 0.23, + "learning_rate": 1.8969840116311192e-05, + "loss": 1.406, + "step": 2204 + }, + { + "epoch": 0.23, + "learning_rate": 1.896822145440124e-05, + "loss": 1.4531, + "step": 2205 + }, + { + "epoch": 0.23, + "learning_rate": 1.896660159098004e-05, + "loss": 1.4379, + "step": 2206 + }, + { + "epoch": 0.23, + "learning_rate": 1.896498052626462e-05, + "loss": 1.4783, + "step": 2207 + }, + { + "epoch": 0.23, + "learning_rate": 1.896335826047216e-05, + "loss": 1.4801, + "step": 2208 + }, + { + "epoch": 0.23, + "learning_rate": 1.896173479381999e-05, + "loss": 1.4526, + "step": 2209 + }, + { + "epoch": 0.23, + "learning_rate": 1.8960110126525627e-05, + "loss": 1.4952, + "step": 2210 + }, + { + "epoch": 0.23, + "learning_rate": 1.895848425880673e-05, + "loss": 1.5299, + "step": 2211 + }, + { + "epoch": 0.23, + "learning_rate": 1.8956857190881125e-05, + "loss": 1.5274, + "step": 2212 + }, + { + "epoch": 0.23, + "learning_rate": 1.8955228922966792e-05, + "loss": 1.4415, + "step": 2213 + }, + { + "epoch": 0.23, + "learning_rate": 1.8953599455281884e-05, + "loss": 1.5311, + "step": 2214 + }, + { + "epoch": 0.23, + "learning_rate": 1.8951968788044702e-05, + "loss": 1.4972, + "step": 2215 + }, + { + "epoch": 0.23, + "learning_rate": 1.8950336921473715e-05, + "loss": 1.4966, + "step": 2216 + }, + { + "epoch": 0.23, + "learning_rate": 1.8948703855787553e-05, + "loss": 1.4683, + "step": 2217 + }, + { + "epoch": 0.23, + "learning_rate": 1.8947069591205005e-05, + "loss": 1.503, + "step": 2218 + }, + { + "epoch": 0.23, + "learning_rate": 1.8945434127945014e-05, + "loss": 1.4902, + "step": 2219 + }, + { + "epoch": 0.23, + "learning_rate": 1.8943797466226702e-05, + "loss": 1.4835, + "step": 2220 + }, + { + "epoch": 0.23, + "learning_rate": 1.8942159606269332e-05, + "loss": 1.535, + "step": 2221 + }, + { + "epoch": 0.23, + "learning_rate": 1.8940520548292332e-05, + "loss": 1.491, + "step": 2222 + }, + { + "epoch": 0.23, + "learning_rate": 1.89388802925153e-05, + "loss": 1.5157, + "step": 2223 + }, + { + "epoch": 0.23, + "learning_rate": 1.8937238839157987e-05, + "loss": 1.4779, + "step": 2224 + }, + { + "epoch": 0.23, + "learning_rate": 1.8935596188440302e-05, + "loss": 1.4902, + "step": 2225 + }, + { + "epoch": 0.23, + "learning_rate": 1.8933952340582323e-05, + "loss": 1.4988, + "step": 2226 + }, + { + "epoch": 0.23, + "learning_rate": 1.893230729580428e-05, + "loss": 1.4568, + "step": 2227 + }, + { + "epoch": 0.23, + "learning_rate": 1.8930661054326567e-05, + "loss": 1.5163, + "step": 2228 + }, + { + "epoch": 0.23, + "learning_rate": 1.892901361636974e-05, + "loss": 1.4472, + "step": 2229 + }, + { + "epoch": 0.23, + "learning_rate": 1.892736498215451e-05, + "loss": 1.4658, + "step": 2230 + }, + { + "epoch": 0.23, + "learning_rate": 1.8925715151901754e-05, + "loss": 1.4281, + "step": 2231 + }, + { + "epoch": 0.23, + "learning_rate": 1.892406412583251e-05, + "loss": 1.415, + "step": 2232 + }, + { + "epoch": 0.23, + "learning_rate": 1.8922411904167966e-05, + "loss": 1.464, + "step": 2233 + }, + { + "epoch": 0.23, + "learning_rate": 1.892075848712948e-05, + "loss": 1.5014, + "step": 2234 + }, + { + "epoch": 0.23, + "learning_rate": 1.8919103874938568e-05, + "loss": 1.4397, + "step": 2235 + }, + { + "epoch": 0.23, + "learning_rate": 1.891744806781691e-05, + "loss": 1.5508, + "step": 2236 + }, + { + "epoch": 0.23, + "learning_rate": 1.8915791065986335e-05, + "loss": 1.4749, + "step": 2237 + }, + { + "epoch": 0.23, + "learning_rate": 1.891413286966884e-05, + "loss": 1.4538, + "step": 2238 + }, + { + "epoch": 0.23, + "learning_rate": 1.891247347908658e-05, + "loss": 1.4405, + "step": 2239 + }, + { + "epoch": 0.23, + "learning_rate": 1.8910812894461878e-05, + "loss": 1.3562, + "step": 2240 + }, + { + "epoch": 0.24, + "learning_rate": 1.89091511160172e-05, + "loss": 1.4811, + "step": 2241 + }, + { + "epoch": 0.24, + "learning_rate": 1.8907488143975186e-05, + "loss": 1.4286, + "step": 2242 + }, + { + "epoch": 0.24, + "learning_rate": 1.890582397855863e-05, + "loss": 1.4493, + "step": 2243 + }, + { + "epoch": 0.24, + "learning_rate": 1.890415861999049e-05, + "loss": 1.5639, + "step": 2244 + }, + { + "epoch": 0.24, + "learning_rate": 1.890249206849388e-05, + "loss": 1.6375, + "step": 2245 + }, + { + "epoch": 0.24, + "learning_rate": 1.890082432429208e-05, + "loss": 1.4982, + "step": 2246 + }, + { + "epoch": 0.24, + "learning_rate": 1.889915538760851e-05, + "loss": 1.492, + "step": 2247 + }, + { + "epoch": 0.24, + "learning_rate": 1.8897485258666778e-05, + "loss": 1.4294, + "step": 2248 + }, + { + "epoch": 0.24, + "learning_rate": 1.8895813937690638e-05, + "loss": 1.4617, + "step": 2249 + }, + { + "epoch": 0.24, + "learning_rate": 1.8894141424904e-05, + "loss": 1.4763, + "step": 2250 + }, + { + "epoch": 0.24, + "learning_rate": 1.8892467720530937e-05, + "loss": 1.3989, + "step": 2251 + }, + { + "epoch": 0.24, + "learning_rate": 1.8890792824795687e-05, + "loss": 1.4803, + "step": 2252 + }, + { + "epoch": 0.24, + "learning_rate": 1.8889116737922638e-05, + "loss": 1.4734, + "step": 2253 + }, + { + "epoch": 0.24, + "learning_rate": 1.8887439460136342e-05, + "loss": 1.5069, + "step": 2254 + }, + { + "epoch": 0.24, + "learning_rate": 1.8885760991661514e-05, + "loss": 1.5565, + "step": 2255 + }, + { + "epoch": 0.24, + "learning_rate": 1.8884081332723028e-05, + "loss": 1.4707, + "step": 2256 + }, + { + "epoch": 0.24, + "learning_rate": 1.8882400483545913e-05, + "loss": 1.5077, + "step": 2257 + }, + { + "epoch": 0.24, + "learning_rate": 1.888071844435536e-05, + "loss": 1.5075, + "step": 2258 + }, + { + "epoch": 0.24, + "learning_rate": 1.8879035215376717e-05, + "loss": 1.5185, + "step": 2259 + }, + { + "epoch": 0.24, + "learning_rate": 1.887735079683549e-05, + "loss": 1.6266, + "step": 2260 + }, + { + "epoch": 0.24, + "learning_rate": 1.8875665188957354e-05, + "loss": 1.5013, + "step": 2261 + }, + { + "epoch": 0.24, + "learning_rate": 1.887397839196814e-05, + "loss": 1.4362, + "step": 2262 + }, + { + "epoch": 0.24, + "learning_rate": 1.8872290406093827e-05, + "loss": 1.4718, + "step": 2263 + }, + { + "epoch": 0.24, + "learning_rate": 1.8870601231560567e-05, + "loss": 1.5202, + "step": 2264 + }, + { + "epoch": 0.24, + "learning_rate": 1.8868910868594664e-05, + "loss": 1.5168, + "step": 2265 + }, + { + "epoch": 0.24, + "learning_rate": 1.8867219317422588e-05, + "loss": 1.5142, + "step": 2266 + }, + { + "epoch": 0.24, + "learning_rate": 1.8865526578270954e-05, + "loss": 1.4885, + "step": 2267 + }, + { + "epoch": 0.24, + "learning_rate": 1.8863832651366552e-05, + "loss": 1.5441, + "step": 2268 + }, + { + "epoch": 0.24, + "learning_rate": 1.8862137536936328e-05, + "loss": 1.4647, + "step": 2269 + }, + { + "epoch": 0.24, + "learning_rate": 1.8860441235207374e-05, + "loss": 1.5352, + "step": 2270 + }, + { + "epoch": 0.24, + "learning_rate": 1.8858743746406958e-05, + "loss": 1.4568, + "step": 2271 + }, + { + "epoch": 0.24, + "learning_rate": 1.8857045070762497e-05, + "loss": 1.4865, + "step": 2272 + }, + { + "epoch": 0.24, + "learning_rate": 1.8855345208501573e-05, + "loss": 1.4637, + "step": 2273 + }, + { + "epoch": 0.24, + "learning_rate": 1.8853644159851918e-05, + "loss": 1.4348, + "step": 2274 + }, + { + "epoch": 0.24, + "learning_rate": 1.8851941925041436e-05, + "loss": 1.4413, + "step": 2275 + }, + { + "epoch": 0.24, + "learning_rate": 1.8850238504298177e-05, + "loss": 1.4434, + "step": 2276 + }, + { + "epoch": 0.24, + "learning_rate": 1.884853389785036e-05, + "loss": 1.4822, + "step": 2277 + }, + { + "epoch": 0.24, + "learning_rate": 1.8846828105926356e-05, + "loss": 1.4632, + "step": 2278 + }, + { + "epoch": 0.24, + "learning_rate": 1.8845121128754698e-05, + "loss": 1.48, + "step": 2279 + }, + { + "epoch": 0.24, + "learning_rate": 1.8843412966564078e-05, + "loss": 1.4518, + "step": 2280 + }, + { + "epoch": 0.24, + "learning_rate": 1.884170361958334e-05, + "loss": 1.4334, + "step": 2281 + }, + { + "epoch": 0.24, + "learning_rate": 1.8839993088041502e-05, + "loss": 1.5131, + "step": 2282 + }, + { + "epoch": 0.24, + "learning_rate": 1.8838281372167724e-05, + "loss": 1.508, + "step": 2283 + }, + { + "epoch": 0.24, + "learning_rate": 1.8836568472191335e-05, + "loss": 1.4086, + "step": 2284 + }, + { + "epoch": 0.24, + "learning_rate": 1.883485438834182e-05, + "loss": 1.5021, + "step": 2285 + }, + { + "epoch": 0.24, + "learning_rate": 1.8833139120848817e-05, + "loss": 1.5083, + "step": 2286 + }, + { + "epoch": 0.24, + "learning_rate": 1.8831422669942137e-05, + "loss": 1.4162, + "step": 2287 + }, + { + "epoch": 0.24, + "learning_rate": 1.8829705035851734e-05, + "loss": 1.5494, + "step": 2288 + }, + { + "epoch": 0.24, + "learning_rate": 1.8827986218807724e-05, + "loss": 1.425, + "step": 2289 + }, + { + "epoch": 0.24, + "learning_rate": 1.8826266219040396e-05, + "loss": 1.5215, + "step": 2290 + }, + { + "epoch": 0.24, + "learning_rate": 1.8824545036780172e-05, + "loss": 1.5577, + "step": 2291 + }, + { + "epoch": 0.24, + "learning_rate": 1.8822822672257655e-05, + "loss": 1.4923, + "step": 2292 + }, + { + "epoch": 0.24, + "learning_rate": 1.8821099125703595e-05, + "loss": 1.4648, + "step": 2293 + }, + { + "epoch": 0.24, + "learning_rate": 1.8819374397348902e-05, + "loss": 1.471, + "step": 2294 + }, + { + "epoch": 0.24, + "learning_rate": 1.8817648487424648e-05, + "loss": 1.5658, + "step": 2295 + }, + { + "epoch": 0.24, + "learning_rate": 1.8815921396162058e-05, + "loss": 1.5348, + "step": 2296 + }, + { + "epoch": 0.24, + "learning_rate": 1.8814193123792518e-05, + "loss": 1.4081, + "step": 2297 + }, + { + "epoch": 0.24, + "learning_rate": 1.881246367054757e-05, + "loss": 1.4762, + "step": 2298 + }, + { + "epoch": 0.24, + "learning_rate": 1.8810733036658925e-05, + "loss": 1.4399, + "step": 2299 + }, + { + "epoch": 0.24, + "learning_rate": 1.8809001222358432e-05, + "loss": 1.4763, + "step": 2300 + }, + { + "epoch": 0.24, + "learning_rate": 1.880726822787812e-05, + "loss": 1.4874, + "step": 2301 + }, + { + "epoch": 0.24, + "learning_rate": 1.880553405345016e-05, + "loss": 1.4951, + "step": 2302 + }, + { + "epoch": 0.24, + "learning_rate": 1.8803798699306887e-05, + "loss": 1.4697, + "step": 2303 + }, + { + "epoch": 0.24, + "learning_rate": 1.880206216568079e-05, + "loss": 1.481, + "step": 2304 + }, + { + "epoch": 0.24, + "learning_rate": 1.880032445280453e-05, + "loss": 1.4485, + "step": 2305 + }, + { + "epoch": 0.24, + "learning_rate": 1.879858556091091e-05, + "loss": 1.4749, + "step": 2306 + }, + { + "epoch": 0.24, + "learning_rate": 1.8796845490232894e-05, + "loss": 1.5605, + "step": 2307 + }, + { + "epoch": 0.24, + "learning_rate": 1.879510424100361e-05, + "loss": 1.4835, + "step": 2308 + }, + { + "epoch": 0.24, + "learning_rate": 1.8793361813456346e-05, + "loss": 1.4344, + "step": 2309 + }, + { + "epoch": 0.24, + "learning_rate": 1.8791618207824532e-05, + "loss": 1.4571, + "step": 2310 + }, + { + "epoch": 0.24, + "learning_rate": 1.8789873424341772e-05, + "loss": 1.482, + "step": 2311 + }, + { + "epoch": 0.24, + "learning_rate": 1.8788127463241822e-05, + "loss": 1.4736, + "step": 2312 + }, + { + "epoch": 0.24, + "learning_rate": 1.8786380324758597e-05, + "loss": 1.4807, + "step": 2313 + }, + { + "epoch": 0.24, + "learning_rate": 1.8784632009126167e-05, + "loss": 1.4418, + "step": 2314 + }, + { + "epoch": 0.24, + "learning_rate": 1.878288251657876e-05, + "loss": 1.5248, + "step": 2315 + }, + { + "epoch": 0.24, + "learning_rate": 1.8781131847350768e-05, + "loss": 1.483, + "step": 2316 + }, + { + "epoch": 0.24, + "learning_rate": 1.877938000167673e-05, + "loss": 1.5474, + "step": 2317 + }, + { + "epoch": 0.24, + "learning_rate": 1.8777626979791347e-05, + "loss": 1.4671, + "step": 2318 + }, + { + "epoch": 0.24, + "learning_rate": 1.877587278192949e-05, + "loss": 1.3049, + "step": 2319 + }, + { + "epoch": 0.24, + "learning_rate": 1.877411740832616e-05, + "loss": 1.483, + "step": 2320 + }, + { + "epoch": 0.24, + "learning_rate": 1.877236085921655e-05, + "loss": 1.508, + "step": 2321 + }, + { + "epoch": 0.24, + "learning_rate": 1.8770603134835978e-05, + "loss": 1.4854, + "step": 2322 + }, + { + "epoch": 0.24, + "learning_rate": 1.8768844235419942e-05, + "loss": 1.4808, + "step": 2323 + }, + { + "epoch": 0.24, + "learning_rate": 1.8767084161204087e-05, + "loss": 1.5352, + "step": 2324 + }, + { + "epoch": 0.24, + "learning_rate": 1.8765322912424214e-05, + "loss": 1.5628, + "step": 2325 + }, + { + "epoch": 0.24, + "learning_rate": 1.8763560489316292e-05, + "loss": 1.494, + "step": 2326 + }, + { + "epoch": 0.24, + "learning_rate": 1.876179689211643e-05, + "loss": 1.509, + "step": 2327 + }, + { + "epoch": 0.24, + "learning_rate": 1.8760032121060918e-05, + "loss": 1.5021, + "step": 2328 + }, + { + "epoch": 0.24, + "learning_rate": 1.875826617638618e-05, + "loss": 1.4179, + "step": 2329 + }, + { + "epoch": 0.24, + "learning_rate": 1.8756499058328813e-05, + "loss": 1.4302, + "step": 2330 + }, + { + "epoch": 0.24, + "learning_rate": 1.8754730767125564e-05, + "loss": 1.4959, + "step": 2331 + }, + { + "epoch": 0.24, + "learning_rate": 1.8752961303013336e-05, + "loss": 1.4423, + "step": 2332 + }, + { + "epoch": 0.24, + "learning_rate": 1.8751190666229194e-05, + "loss": 1.4564, + "step": 2333 + }, + { + "epoch": 0.24, + "learning_rate": 1.8749418857010358e-05, + "loss": 1.4775, + "step": 2334 + }, + { + "epoch": 0.24, + "learning_rate": 1.8747645875594203e-05, + "loss": 1.4182, + "step": 2335 + }, + { + "epoch": 0.24, + "learning_rate": 1.8745871722218265e-05, + "loss": 1.3957, + "step": 2336 + }, + { + "epoch": 0.25, + "learning_rate": 1.8744096397120235e-05, + "loss": 1.4633, + "step": 2337 + }, + { + "epoch": 0.25, + "learning_rate": 1.874231990053796e-05, + "loss": 1.5512, + "step": 2338 + }, + { + "epoch": 0.25, + "learning_rate": 1.8740542232709444e-05, + "loss": 1.3461, + "step": 2339 + }, + { + "epoch": 0.25, + "learning_rate": 1.8738763393872848e-05, + "loss": 1.4754, + "step": 2340 + }, + { + "epoch": 0.25, + "learning_rate": 1.8736983384266495e-05, + "loss": 1.5448, + "step": 2341 + }, + { + "epoch": 0.25, + "learning_rate": 1.8735202204128854e-05, + "loss": 1.4491, + "step": 2342 + }, + { + "epoch": 0.25, + "learning_rate": 1.8733419853698566e-05, + "loss": 1.457, + "step": 2343 + }, + { + "epoch": 0.25, + "learning_rate": 1.8731636333214414e-05, + "loss": 1.4314, + "step": 2344 + }, + { + "epoch": 0.25, + "learning_rate": 1.8729851642915345e-05, + "loss": 1.3979, + "step": 2345 + }, + { + "epoch": 0.25, + "learning_rate": 1.8728065783040464e-05, + "loss": 1.4146, + "step": 2346 + }, + { + "epoch": 0.25, + "learning_rate": 1.8726278753829027e-05, + "loss": 1.4361, + "step": 2347 + }, + { + "epoch": 0.25, + "learning_rate": 1.872449055552045e-05, + "loss": 1.4989, + "step": 2348 + }, + { + "epoch": 0.25, + "learning_rate": 1.872270118835431e-05, + "loss": 1.5062, + "step": 2349 + }, + { + "epoch": 0.25, + "learning_rate": 1.872091065257033e-05, + "loss": 1.4509, + "step": 2350 + }, + { + "epoch": 0.25, + "learning_rate": 1.8719118948408403e-05, + "loss": 1.4631, + "step": 2351 + }, + { + "epoch": 0.25, + "learning_rate": 1.8717326076108566e-05, + "loss": 1.5119, + "step": 2352 + }, + { + "epoch": 0.25, + "learning_rate": 1.8715532035911017e-05, + "loss": 1.6347, + "step": 2353 + }, + { + "epoch": 0.25, + "learning_rate": 1.8713736828056115e-05, + "loss": 1.5526, + "step": 2354 + }, + { + "epoch": 0.25, + "learning_rate": 1.8711940452784368e-05, + "loss": 1.6348, + "step": 2355 + }, + { + "epoch": 0.25, + "learning_rate": 1.871014291033645e-05, + "loss": 1.5183, + "step": 2356 + }, + { + "epoch": 0.25, + "learning_rate": 1.8708344200953182e-05, + "loss": 1.458, + "step": 2357 + }, + { + "epoch": 0.25, + "learning_rate": 1.8706544324875545e-05, + "loss": 1.524, + "step": 2358 + }, + { + "epoch": 0.25, + "learning_rate": 1.8704743282344672e-05, + "loss": 1.4479, + "step": 2359 + }, + { + "epoch": 0.25, + "learning_rate": 1.870294107360186e-05, + "loss": 1.5408, + "step": 2360 + }, + { + "epoch": 0.25, + "learning_rate": 1.8701137698888563e-05, + "loss": 1.5007, + "step": 2361 + }, + { + "epoch": 0.25, + "learning_rate": 1.8699333158446382e-05, + "loss": 1.5132, + "step": 2362 + }, + { + "epoch": 0.25, + "learning_rate": 1.869752745251708e-05, + "loss": 1.4263, + "step": 2363 + }, + { + "epoch": 0.25, + "learning_rate": 1.8695720581342574e-05, + "loss": 1.422, + "step": 2364 + }, + { + "epoch": 0.25, + "learning_rate": 1.869391254516494e-05, + "loss": 1.4411, + "step": 2365 + }, + { + "epoch": 0.25, + "learning_rate": 1.8692103344226406e-05, + "loss": 1.4594, + "step": 2366 + }, + { + "epoch": 0.25, + "learning_rate": 1.8690292978769364e-05, + "loss": 1.4992, + "step": 2367 + }, + { + "epoch": 0.25, + "learning_rate": 1.868848144903635e-05, + "loss": 1.4822, + "step": 2368 + }, + { + "epoch": 0.25, + "learning_rate": 1.8686668755270064e-05, + "loss": 1.5402, + "step": 2369 + }, + { + "epoch": 0.25, + "learning_rate": 1.8684854897713363e-05, + "loss": 1.5268, + "step": 2370 + }, + { + "epoch": 0.25, + "learning_rate": 1.8683039876609258e-05, + "loss": 1.5587, + "step": 2371 + }, + { + "epoch": 0.25, + "learning_rate": 1.868122369220091e-05, + "loss": 1.4214, + "step": 2372 + }, + { + "epoch": 0.25, + "learning_rate": 1.8679406344731645e-05, + "loss": 1.5089, + "step": 2373 + }, + { + "epoch": 0.25, + "learning_rate": 1.867758783444494e-05, + "loss": 1.5067, + "step": 2374 + }, + { + "epoch": 0.25, + "learning_rate": 1.8675768161584427e-05, + "loss": 2.0616, + "step": 2375 + }, + { + "epoch": 0.25, + "learning_rate": 1.8673947326393903e-05, + "loss": 1.5617, + "step": 2376 + }, + { + "epoch": 0.25, + "learning_rate": 1.86721253291173e-05, + "loss": 1.4422, + "step": 2377 + }, + { + "epoch": 0.25, + "learning_rate": 1.867030216999873e-05, + "loss": 1.4727, + "step": 2378 + }, + { + "epoch": 0.25, + "learning_rate": 1.8668477849282443e-05, + "loss": 1.4152, + "step": 2379 + }, + { + "epoch": 0.25, + "learning_rate": 1.8666652367212856e-05, + "loss": 1.4376, + "step": 2380 + }, + { + "epoch": 0.25, + "learning_rate": 1.8664825724034534e-05, + "loss": 1.393, + "step": 2381 + }, + { + "epoch": 0.25, + "learning_rate": 1.8662997919992197e-05, + "loss": 1.4864, + "step": 2382 + }, + { + "epoch": 0.25, + "learning_rate": 1.866116895533073e-05, + "loss": 1.4261, + "step": 2383 + }, + { + "epoch": 0.25, + "learning_rate": 1.8659338830295163e-05, + "loss": 1.4555, + "step": 2384 + }, + { + "epoch": 0.25, + "learning_rate": 1.8657507545130687e-05, + "loss": 1.4939, + "step": 2385 + }, + { + "epoch": 0.25, + "learning_rate": 1.865567510008265e-05, + "loss": 1.4123, + "step": 2386 + }, + { + "epoch": 0.25, + "learning_rate": 1.8653841495396546e-05, + "loss": 1.4459, + "step": 2387 + }, + { + "epoch": 0.25, + "learning_rate": 1.8652006731318038e-05, + "loss": 1.396, + "step": 2388 + }, + { + "epoch": 0.25, + "eval_loss": 1.5139706134796143, + "eval_runtime": 77.2904, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 2388 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 1.0683053543835619e+20, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-2388/training_args.bin b/checkpoint-2388/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-2388/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-2786/config.json b/checkpoint-2786/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-2786/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-2786/generation_config.json b/checkpoint-2786/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-2786/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-2786/model-00001-of-00003.safetensors b/checkpoint-2786/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..66d1c9eca56660fa690e92fb221bc256c3aaa236 --- /dev/null +++ b/checkpoint-2786/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:029af8178c08b65a5df5ad9f64105b81a403562cbdeb363d383f34b1d4c2d737 +size 4943162336 diff --git a/checkpoint-2786/model-00002-of-00003.safetensors b/checkpoint-2786/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fb44b1124569cb1e46e98025f4be949f406b924a --- /dev/null +++ b/checkpoint-2786/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e20c36ee5eed9d85fe20a27bac35dbf78173e20b1ef5c39b6c407bb014228db +size 4999819336 diff --git a/checkpoint-2786/model-00003-of-00003.safetensors b/checkpoint-2786/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0803e421231e243ebd9b46663fe788a9f54e9520 --- /dev/null +++ b/checkpoint-2786/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0778abc31dfc8b5b1c64fcf1b722a86d4dcb750d11193a3e2959c2f4f3955922 +size 4540516344 diff --git a/checkpoint-2786/model.safetensors.index.json b/checkpoint-2786/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-2786/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-2786/optimizer.pt b/checkpoint-2786/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..2044806ac79d0a97b13f9ddacc5490ce80b5d07d --- /dev/null +++ b/checkpoint-2786/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfe85f77ebcaa39b1a96bc0aa1a4a3785769ee84c8946987dba277f9cba4b7c3 +size 14512103560 diff --git a/checkpoint-2786/rng_state_0.pth b/checkpoint-2786/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..80f51268a9828e9592a20d8ae8b2cd4ba4bc362c --- /dev/null +++ b/checkpoint-2786/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07d994b317c4df888a1a1aabc0c532e81f1fa34c18c8313cb2feadca3bb37194 +size 15984 diff --git a/checkpoint-2786/rng_state_1.pth b/checkpoint-2786/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..62e581603d525611f9660b6e859462f72bbc9258 --- /dev/null +++ b/checkpoint-2786/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f5b05860618aa49c7f5d8c366d6ee73cf8b3b0d0adc17d9313b72621630d0aa +size 15984 diff --git a/checkpoint-2786/rng_state_2.pth b/checkpoint-2786/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..18b03e632222a58e33ea4fca874b9c52628cc5e1 --- /dev/null +++ b/checkpoint-2786/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7262faf861e984775b4fd85bc76a11b0b8b04037690e8a08a58cf9ff5328a042 +size 15984 diff --git a/checkpoint-2786/rng_state_3.pth b/checkpoint-2786/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..41735b5f7ace13ffa57ebed3e7042f1a48ac17fb --- /dev/null +++ b/checkpoint-2786/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9479cad91150e2e266d17eb95fe678579a770f6df6b53496cf72067b186b094d +size 15984 diff --git a/checkpoint-2786/rng_state_4.pth b/checkpoint-2786/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..ebbb93c1d99b1645075ea27fc9fae66992a691f5 --- /dev/null +++ b/checkpoint-2786/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:435cb6cf559e0ce3fe0d4582cac16ea40b48b7a64589952402a4c399cafbfc00 +size 15984 diff --git a/checkpoint-2786/rng_state_5.pth b/checkpoint-2786/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..0656f84b77a33c9ceba9df16f36437b55ef71bc7 --- /dev/null +++ b/checkpoint-2786/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f51001b0d8dc5792180c3a9705ccbfa66b61d46d7639afb6f7abf409629ed74f +size 15984 diff --git a/checkpoint-2786/rng_state_6.pth b/checkpoint-2786/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..32b3a313372ee4a2eeaeed69789f8fb4e2c70ad0 --- /dev/null +++ b/checkpoint-2786/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e87084f11088fdce293e1fbbb05e35f5c7385b00e2f9ba195bf61cb36f757d +size 15984 diff --git a/checkpoint-2786/rng_state_7.pth b/checkpoint-2786/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..9c5a45264129fe1d7c409a6867de1a9751476a8e --- /dev/null +++ b/checkpoint-2786/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d32e9bdd65145ae509e6c6ef4f6ea9d842f94a34c34a0d7d2ab6c248d3f2121 +size 15984 diff --git a/checkpoint-2786/scheduler.pt b/checkpoint-2786/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..ce3f742156c90d5d40184169c882d7505cedb179 --- /dev/null +++ b/checkpoint-2786/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e448b9c7e6a3e793b6e3780fc53187ceb55bb3ebf47e2b4e8162b3fa9950c03 +size 1064 diff --git a/checkpoint-2786/special_tokens_map.json b/checkpoint-2786/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-2786/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-2786/tokenizer.model b/checkpoint-2786/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-2786/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-2786/tokenizer_config.json b/checkpoint-2786/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-2786/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-2786/trainer_state.json b/checkpoint-2786/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..a2b983d8ff2ee5cb52c5b1033fae670dd1391e93 --- /dev/null +++ b/checkpoint-2786/trainer_state.json @@ -0,0 +1,16848 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.2921560402684564, + "eval_steps": 199, + "global_step": 2786, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + }, + { + "epoch": 0.21, + "learning_rate": 1.928689129323009e-05, + "loss": 1.421, + "step": 1991 + }, + { + "epoch": 0.21, + "learning_rate": 1.928553323396003e-05, + "loss": 1.5625, + "step": 1992 + }, + { + "epoch": 0.21, + "learning_rate": 1.92841739306671e-05, + "loss": 1.5198, + "step": 1993 + }, + { + "epoch": 0.21, + "learning_rate": 1.9282813383533415e-05, + "loss": 1.5116, + "step": 1994 + }, + { + "epoch": 0.21, + "learning_rate": 1.9281451592741247e-05, + "loss": 1.4306, + "step": 1995 + }, + { + "epoch": 0.21, + "learning_rate": 1.9280088558473046e-05, + "loss": 1.5425, + "step": 1996 + }, + { + "epoch": 0.21, + "learning_rate": 1.9278724280911424e-05, + "loss": 1.4972, + "step": 1997 + }, + { + "epoch": 0.21, + "learning_rate": 1.9277358760239156e-05, + "loss": 1.5185, + "step": 1998 + }, + { + "epoch": 0.21, + "learning_rate": 1.9275991996639188e-05, + "loss": 1.5187, + "step": 1999 + }, + { + "epoch": 0.21, + "learning_rate": 1.927462399029463e-05, + "loss": 1.4325, + "step": 2000 + }, + { + "epoch": 0.21, + "learning_rate": 1.9273254741388763e-05, + "loss": 1.4397, + "step": 2001 + }, + { + "epoch": 0.21, + "learning_rate": 1.927188425010503e-05, + "loss": 1.5319, + "step": 2002 + }, + { + "epoch": 0.21, + "learning_rate": 1.9270512516627042e-05, + "loss": 1.5664, + "step": 2003 + }, + { + "epoch": 0.21, + "learning_rate": 1.9269139541138574e-05, + "loss": 1.5227, + "step": 2004 + }, + { + "epoch": 0.21, + "learning_rate": 1.926776532382357e-05, + "loss": 1.5187, + "step": 2005 + }, + { + "epoch": 0.21, + "learning_rate": 1.9266389864866134e-05, + "loss": 1.4029, + "step": 2006 + }, + { + "epoch": 0.21, + "learning_rate": 1.9265013164450557e-05, + "loss": 1.387, + "step": 2007 + }, + { + "epoch": 0.21, + "learning_rate": 1.9263635222761268e-05, + "loss": 1.5047, + "step": 2008 + }, + { + "epoch": 0.21, + "learning_rate": 1.9262256039982882e-05, + "loss": 1.4816, + "step": 2009 + }, + { + "epoch": 0.21, + "learning_rate": 1.9260875616300172e-05, + "loss": 1.4607, + "step": 2010 + }, + { + "epoch": 0.21, + "learning_rate": 1.9259493951898084e-05, + "loss": 1.628, + "step": 2011 + }, + { + "epoch": 0.21, + "learning_rate": 1.9258111046961714e-05, + "loss": 1.4149, + "step": 2012 + }, + { + "epoch": 0.21, + "learning_rate": 1.925672690167635e-05, + "loss": 1.5303, + "step": 2013 + }, + { + "epoch": 0.21, + "learning_rate": 1.925534151622742e-05, + "loss": 1.5198, + "step": 2014 + }, + { + "epoch": 0.21, + "learning_rate": 1.9253954890800535e-05, + "loss": 1.6422, + "step": 2015 + }, + { + "epoch": 0.21, + "learning_rate": 1.925256702558147e-05, + "loss": 1.4738, + "step": 2016 + }, + { + "epoch": 0.21, + "learning_rate": 1.925117792075616e-05, + "loss": 1.4752, + "step": 2017 + }, + { + "epoch": 0.21, + "learning_rate": 1.9249787576510713e-05, + "loss": 1.4547, + "step": 2018 + }, + { + "epoch": 0.21, + "learning_rate": 1.924839599303139e-05, + "loss": 1.4864, + "step": 2019 + }, + { + "epoch": 0.21, + "learning_rate": 1.9247003170504638e-05, + "loss": 1.5037, + "step": 2020 + }, + { + "epoch": 0.21, + "learning_rate": 1.9245609109117053e-05, + "loss": 1.5089, + "step": 2021 + }, + { + "epoch": 0.21, + "learning_rate": 1.924421380905541e-05, + "loss": 1.5616, + "step": 2022 + }, + { + "epoch": 0.21, + "learning_rate": 1.9242817270506634e-05, + "loss": 1.4592, + "step": 2023 + }, + { + "epoch": 0.21, + "learning_rate": 1.9241419493657832e-05, + "loss": 1.5592, + "step": 2024 + }, + { + "epoch": 0.21, + "learning_rate": 1.924002047869627e-05, + "loss": 1.4897, + "step": 2025 + }, + { + "epoch": 0.21, + "learning_rate": 1.9238620225809375e-05, + "loss": 1.4743, + "step": 2026 + }, + { + "epoch": 0.21, + "learning_rate": 1.923721873518475e-05, + "loss": 1.4686, + "step": 2027 + }, + { + "epoch": 0.21, + "learning_rate": 1.923581600701016e-05, + "loss": 1.461, + "step": 2028 + }, + { + "epoch": 0.21, + "learning_rate": 1.9234412041473528e-05, + "loss": 1.6622, + "step": 2029 + }, + { + "epoch": 0.21, + "learning_rate": 1.9233006838762955e-05, + "loss": 1.4707, + "step": 2030 + }, + { + "epoch": 0.21, + "learning_rate": 1.92316003990667e-05, + "loss": 1.5566, + "step": 2031 + }, + { + "epoch": 0.21, + "learning_rate": 1.9230192722573188e-05, + "loss": 1.4881, + "step": 2032 + }, + { + "epoch": 0.21, + "learning_rate": 1.9228783809471015e-05, + "loss": 1.6124, + "step": 2033 + }, + { + "epoch": 0.21, + "learning_rate": 1.9227373659948937e-05, + "loss": 1.3508, + "step": 2034 + }, + { + "epoch": 0.21, + "learning_rate": 1.9225962274195876e-05, + "loss": 1.4418, + "step": 2035 + }, + { + "epoch": 0.21, + "learning_rate": 1.9224549652400927e-05, + "loss": 1.3954, + "step": 2036 + }, + { + "epoch": 0.21, + "learning_rate": 1.922313579475334e-05, + "loss": 1.4798, + "step": 2037 + }, + { + "epoch": 0.21, + "learning_rate": 1.922172070144254e-05, + "loss": 1.4556, + "step": 2038 + }, + { + "epoch": 0.21, + "learning_rate": 1.922030437265811e-05, + "loss": 1.4987, + "step": 2039 + }, + { + "epoch": 0.21, + "learning_rate": 1.9218886808589796e-05, + "loss": 1.4857, + "step": 2040 + }, + { + "epoch": 0.21, + "learning_rate": 1.9217468009427527e-05, + "loss": 1.5289, + "step": 2041 + }, + { + "epoch": 0.21, + "learning_rate": 1.921604797536138e-05, + "loss": 1.5267, + "step": 2042 + }, + { + "epoch": 0.21, + "learning_rate": 1.9214626706581598e-05, + "loss": 1.4655, + "step": 2043 + }, + { + "epoch": 0.21, + "learning_rate": 1.9213204203278602e-05, + "loss": 1.4598, + "step": 2044 + }, + { + "epoch": 0.21, + "learning_rate": 1.9211780465642973e-05, + "loss": 1.4766, + "step": 2045 + }, + { + "epoch": 0.21, + "learning_rate": 1.921035549386545e-05, + "loss": 1.5148, + "step": 2046 + }, + { + "epoch": 0.21, + "learning_rate": 1.9208929288136933e-05, + "loss": 1.5567, + "step": 2047 + }, + { + "epoch": 0.21, + "learning_rate": 1.920750184864852e-05, + "loss": 1.4868, + "step": 2048 + }, + { + "epoch": 0.21, + "learning_rate": 1.920607317559143e-05, + "loss": 1.4752, + "step": 2049 + }, + { + "epoch": 0.21, + "learning_rate": 1.920464326915708e-05, + "loss": 1.4882, + "step": 2050 + }, + { + "epoch": 0.22, + "learning_rate": 1.9203212129537035e-05, + "loss": 1.5933, + "step": 2051 + }, + { + "epoch": 0.22, + "learning_rate": 1.9201779756923037e-05, + "loss": 1.4891, + "step": 2052 + }, + { + "epoch": 0.22, + "learning_rate": 1.9200346151506983e-05, + "loss": 1.4486, + "step": 2053 + }, + { + "epoch": 0.22, + "learning_rate": 1.9198911313480938e-05, + "loss": 1.5091, + "step": 2054 + }, + { + "epoch": 0.22, + "learning_rate": 1.919747524303714e-05, + "loss": 1.4385, + "step": 2055 + }, + { + "epoch": 0.22, + "learning_rate": 1.9196037940367974e-05, + "loss": 1.4104, + "step": 2056 + }, + { + "epoch": 0.22, + "learning_rate": 1.9194599405666015e-05, + "loss": 1.4483, + "step": 2057 + }, + { + "epoch": 0.22, + "learning_rate": 1.9193159639123976e-05, + "loss": 1.4592, + "step": 2058 + }, + { + "epoch": 0.22, + "learning_rate": 1.919171864093476e-05, + "loss": 1.4975, + "step": 2059 + }, + { + "epoch": 0.22, + "learning_rate": 1.9190276411291423e-05, + "loss": 1.4727, + "step": 2060 + }, + { + "epoch": 0.22, + "learning_rate": 1.9188832950387178e-05, + "loss": 1.4791, + "step": 2061 + }, + { + "epoch": 0.22, + "learning_rate": 1.9187388258415423e-05, + "loss": 1.3806, + "step": 2062 + }, + { + "epoch": 0.22, + "learning_rate": 1.9185942335569697e-05, + "loss": 1.4514, + "step": 2063 + }, + { + "epoch": 0.22, + "learning_rate": 1.9184495182043727e-05, + "loss": 1.4389, + "step": 2064 + }, + { + "epoch": 0.22, + "learning_rate": 1.918304679803139e-05, + "loss": 1.5088, + "step": 2065 + }, + { + "epoch": 0.22, + "learning_rate": 1.9181597183726733e-05, + "loss": 1.4665, + "step": 2066 + }, + { + "epoch": 0.22, + "learning_rate": 1.9180146339323966e-05, + "loss": 1.489, + "step": 2067 + }, + { + "epoch": 0.22, + "learning_rate": 1.9178694265017466e-05, + "loss": 1.5215, + "step": 2068 + }, + { + "epoch": 0.22, + "learning_rate": 1.9177240961001775e-05, + "loss": 1.5152, + "step": 2069 + }, + { + "epoch": 0.22, + "learning_rate": 1.9175786427471594e-05, + "loss": 1.4418, + "step": 2070 + }, + { + "epoch": 0.22, + "learning_rate": 1.91743306646218e-05, + "loss": 1.5001, + "step": 2071 + }, + { + "epoch": 0.22, + "learning_rate": 1.9172873672647417e-05, + "loss": 1.4879, + "step": 2072 + }, + { + "epoch": 0.22, + "learning_rate": 1.917141545174366e-05, + "loss": 1.5299, + "step": 2073 + }, + { + "epoch": 0.22, + "learning_rate": 1.9169956002105877e-05, + "loss": 1.4602, + "step": 2074 + }, + { + "epoch": 0.22, + "learning_rate": 1.9168495323929605e-05, + "loss": 1.4921, + "step": 2075 + }, + { + "epoch": 0.22, + "learning_rate": 1.916703341741054e-05, + "loss": 1.4659, + "step": 2076 + }, + { + "epoch": 0.22, + "learning_rate": 1.9165570282744534e-05, + "loss": 1.4707, + "step": 2077 + }, + { + "epoch": 0.22, + "learning_rate": 1.9164105920127613e-05, + "loss": 1.5354, + "step": 2078 + }, + { + "epoch": 0.22, + "learning_rate": 1.9162640329755962e-05, + "loss": 1.526, + "step": 2079 + }, + { + "epoch": 0.22, + "learning_rate": 1.916117351182593e-05, + "loss": 1.6424, + "step": 2080 + }, + { + "epoch": 0.22, + "learning_rate": 1.915970546653404e-05, + "loss": 1.5048, + "step": 2081 + }, + { + "epoch": 0.22, + "learning_rate": 1.915823619407697e-05, + "loss": 1.5344, + "step": 2082 + }, + { + "epoch": 0.22, + "learning_rate": 1.915676569465156e-05, + "loss": 1.4604, + "step": 2083 + }, + { + "epoch": 0.22, + "learning_rate": 1.9155293968454826e-05, + "loss": 1.4929, + "step": 2084 + }, + { + "epoch": 0.22, + "learning_rate": 1.9153821015683937e-05, + "loss": 1.4106, + "step": 2085 + }, + { + "epoch": 0.22, + "learning_rate": 1.915234683653623e-05, + "loss": 1.4146, + "step": 2086 + }, + { + "epoch": 0.22, + "learning_rate": 1.9150871431209207e-05, + "loss": 1.4481, + "step": 2087 + }, + { + "epoch": 0.22, + "learning_rate": 1.914939479990054e-05, + "loss": 1.5206, + "step": 2088 + }, + { + "epoch": 0.22, + "learning_rate": 1.9147916942808054e-05, + "loss": 1.5073, + "step": 2089 + }, + { + "epoch": 0.22, + "learning_rate": 1.9146437860129745e-05, + "loss": 1.5196, + "step": 2090 + }, + { + "epoch": 0.22, + "learning_rate": 1.9144957552063775e-05, + "loss": 1.5389, + "step": 2091 + }, + { + "epoch": 0.22, + "learning_rate": 1.9143476018808463e-05, + "loss": 1.5207, + "step": 2092 + }, + { + "epoch": 0.22, + "learning_rate": 1.9141993260562298e-05, + "loss": 1.3717, + "step": 2093 + }, + { + "epoch": 0.22, + "learning_rate": 1.9140509277523937e-05, + "loss": 1.471, + "step": 2094 + }, + { + "epoch": 0.22, + "learning_rate": 1.9139024069892185e-05, + "loss": 1.4553, + "step": 2095 + }, + { + "epoch": 0.22, + "learning_rate": 1.9137537637866027e-05, + "loss": 1.5311, + "step": 2096 + }, + { + "epoch": 0.22, + "learning_rate": 1.9136049981644614e-05, + "loss": 1.4369, + "step": 2097 + }, + { + "epoch": 0.22, + "learning_rate": 1.913456110142724e-05, + "loss": 1.4528, + "step": 2098 + }, + { + "epoch": 0.22, + "learning_rate": 1.9133070997413384e-05, + "loss": 1.5294, + "step": 2099 + }, + { + "epoch": 0.22, + "learning_rate": 1.9131579669802685e-05, + "loss": 1.4588, + "step": 2100 + }, + { + "epoch": 0.22, + "learning_rate": 1.9130087118794934e-05, + "loss": 1.443, + "step": 2101 + }, + { + "epoch": 0.22, + "learning_rate": 1.9128593344590102e-05, + "loss": 1.4876, + "step": 2102 + }, + { + "epoch": 0.22, + "learning_rate": 1.912709834738831e-05, + "loss": 1.4874, + "step": 2103 + }, + { + "epoch": 0.22, + "learning_rate": 1.9125602127389856e-05, + "loss": 1.4966, + "step": 2104 + }, + { + "epoch": 0.22, + "learning_rate": 1.912410468479519e-05, + "loss": 1.5747, + "step": 2105 + }, + { + "epoch": 0.22, + "learning_rate": 1.9122606019804933e-05, + "loss": 1.4025, + "step": 2106 + }, + { + "epoch": 0.22, + "learning_rate": 1.912110613261987e-05, + "loss": 1.4755, + "step": 2107 + }, + { + "epoch": 0.22, + "learning_rate": 1.911960502344094e-05, + "loss": 1.4739, + "step": 2108 + }, + { + "epoch": 0.22, + "learning_rate": 1.911810269246926e-05, + "loss": 1.4992, + "step": 2109 + }, + { + "epoch": 0.22, + "learning_rate": 1.91165991399061e-05, + "loss": 1.4435, + "step": 2110 + }, + { + "epoch": 0.22, + "learning_rate": 1.91150943659529e-05, + "loss": 1.4918, + "step": 2111 + }, + { + "epoch": 0.22, + "learning_rate": 1.9113588370811258e-05, + "loss": 1.3818, + "step": 2112 + }, + { + "epoch": 0.22, + "learning_rate": 1.911208115468294e-05, + "loss": 1.5105, + "step": 2113 + }, + { + "epoch": 0.22, + "learning_rate": 1.9110572717769878e-05, + "loss": 1.6634, + "step": 2114 + }, + { + "epoch": 0.22, + "learning_rate": 1.9109063060274158e-05, + "loss": 1.5028, + "step": 2115 + }, + { + "epoch": 0.22, + "learning_rate": 1.9107552182398037e-05, + "loss": 1.6657, + "step": 2116 + }, + { + "epoch": 0.22, + "learning_rate": 1.9106040084343935e-05, + "loss": 1.5481, + "step": 2117 + }, + { + "epoch": 0.22, + "learning_rate": 1.910452676631444e-05, + "loss": 1.4505, + "step": 2118 + }, + { + "epoch": 0.22, + "learning_rate": 1.9103012228512284e-05, + "loss": 1.5173, + "step": 2119 + }, + { + "epoch": 0.22, + "learning_rate": 1.9101496471140385e-05, + "loss": 1.3788, + "step": 2120 + }, + { + "epoch": 0.22, + "learning_rate": 1.9099979494401814e-05, + "loss": 1.4649, + "step": 2121 + }, + { + "epoch": 0.22, + "learning_rate": 1.9098461298499805e-05, + "loss": 1.4204, + "step": 2122 + }, + { + "epoch": 0.22, + "learning_rate": 1.9096941883637766e-05, + "loss": 1.4439, + "step": 2123 + }, + { + "epoch": 0.22, + "learning_rate": 1.909542125001925e-05, + "loss": 1.6615, + "step": 2124 + }, + { + "epoch": 0.22, + "learning_rate": 1.9093899397847985e-05, + "loss": 1.4763, + "step": 2125 + }, + { + "epoch": 0.22, + "learning_rate": 1.909237632732786e-05, + "loss": 1.5353, + "step": 2126 + }, + { + "epoch": 0.22, + "learning_rate": 1.909085203866293e-05, + "loss": 1.442, + "step": 2127 + }, + { + "epoch": 0.22, + "learning_rate": 1.9089326532057408e-05, + "loss": 1.4782, + "step": 2128 + }, + { + "epoch": 0.22, + "learning_rate": 1.908779980771567e-05, + "loss": 1.4933, + "step": 2129 + }, + { + "epoch": 0.22, + "learning_rate": 1.9086271865842264e-05, + "loss": 1.5285, + "step": 2130 + }, + { + "epoch": 0.22, + "learning_rate": 1.9084742706641894e-05, + "loss": 1.4736, + "step": 2131 + }, + { + "epoch": 0.22, + "learning_rate": 1.9083212330319427e-05, + "loss": 1.4496, + "step": 2132 + }, + { + "epoch": 0.22, + "learning_rate": 1.908168073707989e-05, + "loss": 1.5099, + "step": 2133 + }, + { + "epoch": 0.22, + "learning_rate": 1.9080147927128483e-05, + "loss": 1.5235, + "step": 2134 + }, + { + "epoch": 0.22, + "learning_rate": 1.9078613900670556e-05, + "loss": 1.4769, + "step": 2135 + }, + { + "epoch": 0.22, + "learning_rate": 1.907707865791164e-05, + "loss": 1.5771, + "step": 2136 + }, + { + "epoch": 0.22, + "learning_rate": 1.907554219905741e-05, + "loss": 1.5116, + "step": 2137 + }, + { + "epoch": 0.22, + "learning_rate": 1.907400452431371e-05, + "loss": 1.5161, + "step": 2138 + }, + { + "epoch": 0.22, + "learning_rate": 1.9072465633886557e-05, + "loss": 1.4356, + "step": 2139 + }, + { + "epoch": 0.22, + "learning_rate": 1.9070925527982117e-05, + "loss": 1.509, + "step": 2140 + }, + { + "epoch": 0.22, + "learning_rate": 1.9069384206806723e-05, + "loss": 1.4681, + "step": 2141 + }, + { + "epoch": 0.22, + "learning_rate": 1.9067841670566883e-05, + "loss": 1.5254, + "step": 2142 + }, + { + "epoch": 0.22, + "learning_rate": 1.9066297919469242e-05, + "loss": 1.4797, + "step": 2143 + }, + { + "epoch": 0.22, + "learning_rate": 1.9064752953720636e-05, + "loss": 1.3996, + "step": 2144 + }, + { + "epoch": 0.22, + "learning_rate": 1.9063206773528042e-05, + "loss": 1.4457, + "step": 2145 + }, + { + "epoch": 0.23, + "learning_rate": 1.9061659379098617e-05, + "loss": 1.5126, + "step": 2146 + }, + { + "epoch": 0.23, + "learning_rate": 1.9060110770639664e-05, + "loss": 1.5925, + "step": 2147 + }, + { + "epoch": 0.23, + "learning_rate": 1.905856094835866e-05, + "loss": 1.5146, + "step": 2148 + }, + { + "epoch": 0.23, + "learning_rate": 1.905700991246324e-05, + "loss": 1.7256, + "step": 2149 + }, + { + "epoch": 0.23, + "learning_rate": 1.90554576631612e-05, + "loss": 1.57, + "step": 2150 + }, + { + "epoch": 0.23, + "learning_rate": 1.905390420066051e-05, + "loss": 1.3722, + "step": 2151 + }, + { + "epoch": 0.23, + "learning_rate": 1.9052349525169292e-05, + "loss": 1.3999, + "step": 2152 + }, + { + "epoch": 0.23, + "learning_rate": 1.9050793636895828e-05, + "loss": 1.586, + "step": 2153 + }, + { + "epoch": 0.23, + "learning_rate": 1.9049236536048567e-05, + "loss": 1.4884, + "step": 2154 + }, + { + "epoch": 0.23, + "learning_rate": 1.9047678222836127e-05, + "loss": 1.5898, + "step": 2155 + }, + { + "epoch": 0.23, + "learning_rate": 1.9046118697467278e-05, + "loss": 1.569, + "step": 2156 + }, + { + "epoch": 0.23, + "learning_rate": 1.904455796015095e-05, + "loss": 1.5592, + "step": 2157 + }, + { + "epoch": 0.23, + "learning_rate": 1.9042996011096253e-05, + "loss": 1.597, + "step": 2158 + }, + { + "epoch": 0.23, + "learning_rate": 1.904143285051244e-05, + "loss": 1.422, + "step": 2159 + }, + { + "epoch": 0.23, + "learning_rate": 1.903986847860894e-05, + "loss": 1.519, + "step": 2160 + }, + { + "epoch": 0.23, + "learning_rate": 1.9038302895595334e-05, + "loss": 1.5197, + "step": 2161 + }, + { + "epoch": 0.23, + "learning_rate": 1.903673610168137e-05, + "loss": 1.4655, + "step": 2162 + }, + { + "epoch": 0.23, + "learning_rate": 1.9035168097076965e-05, + "loss": 1.3909, + "step": 2163 + }, + { + "epoch": 0.23, + "learning_rate": 1.903359888199218e-05, + "loss": 1.4877, + "step": 2164 + }, + { + "epoch": 0.23, + "learning_rate": 1.903202845663726e-05, + "loss": 1.5123, + "step": 2165 + }, + { + "epoch": 0.23, + "learning_rate": 1.9030456821222593e-05, + "loss": 1.4906, + "step": 2166 + }, + { + "epoch": 0.23, + "learning_rate": 1.9028883975958745e-05, + "loss": 1.4574, + "step": 2167 + }, + { + "epoch": 0.23, + "learning_rate": 1.9027309921056435e-05, + "loss": 1.4571, + "step": 2168 + }, + { + "epoch": 0.23, + "learning_rate": 1.902573465672654e-05, + "loss": 1.4281, + "step": 2169 + }, + { + "epoch": 0.23, + "learning_rate": 1.9024158183180116e-05, + "loss": 1.5057, + "step": 2170 + }, + { + "epoch": 0.23, + "learning_rate": 1.902258050062836e-05, + "loss": 1.4514, + "step": 2171 + }, + { + "epoch": 0.23, + "learning_rate": 1.9021001609282646e-05, + "loss": 1.5055, + "step": 2172 + }, + { + "epoch": 0.23, + "learning_rate": 1.9019421509354505e-05, + "loss": 1.4578, + "step": 2173 + }, + { + "epoch": 0.23, + "learning_rate": 1.9017840201055625e-05, + "loss": 1.459, + "step": 2174 + }, + { + "epoch": 0.23, + "learning_rate": 1.9016257684597864e-05, + "loss": 1.5059, + "step": 2175 + }, + { + "epoch": 0.23, + "learning_rate": 1.901467396019324e-05, + "loss": 1.57, + "step": 2176 + }, + { + "epoch": 0.23, + "learning_rate": 1.901308902805393e-05, + "loss": 1.4924, + "step": 2177 + }, + { + "epoch": 0.23, + "learning_rate": 1.9011502888392273e-05, + "loss": 1.4979, + "step": 2178 + }, + { + "epoch": 0.23, + "learning_rate": 1.900991554142077e-05, + "loss": 1.5321, + "step": 2179 + }, + { + "epoch": 0.23, + "learning_rate": 1.9008326987352093e-05, + "loss": 1.493, + "step": 2180 + }, + { + "epoch": 0.23, + "learning_rate": 1.9006737226399056e-05, + "loss": 1.5111, + "step": 2181 + }, + { + "epoch": 0.23, + "learning_rate": 1.900514625877465e-05, + "loss": 1.4154, + "step": 2182 + }, + { + "epoch": 0.23, + "learning_rate": 1.900355408469203e-05, + "loss": 1.4934, + "step": 2183 + }, + { + "epoch": 0.23, + "learning_rate": 1.90019607043645e-05, + "loss": 1.5975, + "step": 2184 + }, + { + "epoch": 0.23, + "learning_rate": 1.9000366118005532e-05, + "loss": 1.3537, + "step": 2185 + }, + { + "epoch": 0.23, + "learning_rate": 1.899877032582876e-05, + "loss": 1.4583, + "step": 2186 + }, + { + "epoch": 0.23, + "learning_rate": 1.8997173328047984e-05, + "loss": 1.4586, + "step": 2187 + }, + { + "epoch": 0.23, + "learning_rate": 1.8995575124877156e-05, + "loss": 1.4774, + "step": 2188 + }, + { + "epoch": 0.23, + "learning_rate": 1.8993975716530394e-05, + "loss": 1.5025, + "step": 2189 + }, + { + "epoch": 0.23, + "eval_loss": 1.5263344049453735, + "eval_runtime": 77.1492, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 2189 + }, + { + "epoch": 0.23, + "learning_rate": 1.899237510322198e-05, + "loss": 1.5438, + "step": 2190 + }, + { + "epoch": 0.23, + "learning_rate": 1.899077328516635e-05, + "loss": 1.5181, + "step": 2191 + }, + { + "epoch": 0.23, + "learning_rate": 1.8989170262578112e-05, + "loss": 1.4454, + "step": 2192 + }, + { + "epoch": 0.23, + "learning_rate": 1.8987566035672028e-05, + "loss": 1.4882, + "step": 2193 + }, + { + "epoch": 0.23, + "learning_rate": 1.8985960604663026e-05, + "loss": 1.5073, + "step": 2194 + }, + { + "epoch": 0.23, + "learning_rate": 1.8984353969766187e-05, + "loss": 1.4478, + "step": 2195 + }, + { + "epoch": 0.23, + "learning_rate": 1.8982746131196763e-05, + "loss": 1.4768, + "step": 2196 + }, + { + "epoch": 0.23, + "learning_rate": 1.8981137089170162e-05, + "loss": 1.5116, + "step": 2197 + }, + { + "epoch": 0.23, + "learning_rate": 1.8979526843901952e-05, + "loss": 1.4202, + "step": 2198 + }, + { + "epoch": 0.23, + "learning_rate": 1.8977915395607867e-05, + "loss": 1.4736, + "step": 2199 + }, + { + "epoch": 0.23, + "learning_rate": 1.89763027445038e-05, + "loss": 1.4489, + "step": 2200 + }, + { + "epoch": 0.23, + "learning_rate": 1.8974688890805804e-05, + "loss": 1.4512, + "step": 2201 + }, + { + "epoch": 0.23, + "learning_rate": 1.897307383473009e-05, + "loss": 1.5091, + "step": 2202 + }, + { + "epoch": 0.23, + "learning_rate": 1.897145757649304e-05, + "loss": 1.5512, + "step": 2203 + }, + { + "epoch": 0.23, + "learning_rate": 1.8969840116311192e-05, + "loss": 1.406, + "step": 2204 + }, + { + "epoch": 0.23, + "learning_rate": 1.896822145440124e-05, + "loss": 1.4531, + "step": 2205 + }, + { + "epoch": 0.23, + "learning_rate": 1.896660159098004e-05, + "loss": 1.4379, + "step": 2206 + }, + { + "epoch": 0.23, + "learning_rate": 1.896498052626462e-05, + "loss": 1.4783, + "step": 2207 + }, + { + "epoch": 0.23, + "learning_rate": 1.896335826047216e-05, + "loss": 1.4801, + "step": 2208 + }, + { + "epoch": 0.23, + "learning_rate": 1.896173479381999e-05, + "loss": 1.4526, + "step": 2209 + }, + { + "epoch": 0.23, + "learning_rate": 1.8960110126525627e-05, + "loss": 1.4952, + "step": 2210 + }, + { + "epoch": 0.23, + "learning_rate": 1.895848425880673e-05, + "loss": 1.5299, + "step": 2211 + }, + { + "epoch": 0.23, + "learning_rate": 1.8956857190881125e-05, + "loss": 1.5274, + "step": 2212 + }, + { + "epoch": 0.23, + "learning_rate": 1.8955228922966792e-05, + "loss": 1.4415, + "step": 2213 + }, + { + "epoch": 0.23, + "learning_rate": 1.8953599455281884e-05, + "loss": 1.5311, + "step": 2214 + }, + { + "epoch": 0.23, + "learning_rate": 1.8951968788044702e-05, + "loss": 1.4972, + "step": 2215 + }, + { + "epoch": 0.23, + "learning_rate": 1.8950336921473715e-05, + "loss": 1.4966, + "step": 2216 + }, + { + "epoch": 0.23, + "learning_rate": 1.8948703855787553e-05, + "loss": 1.4683, + "step": 2217 + }, + { + "epoch": 0.23, + "learning_rate": 1.8947069591205005e-05, + "loss": 1.503, + "step": 2218 + }, + { + "epoch": 0.23, + "learning_rate": 1.8945434127945014e-05, + "loss": 1.4902, + "step": 2219 + }, + { + "epoch": 0.23, + "learning_rate": 1.8943797466226702e-05, + "loss": 1.4835, + "step": 2220 + }, + { + "epoch": 0.23, + "learning_rate": 1.8942159606269332e-05, + "loss": 1.535, + "step": 2221 + }, + { + "epoch": 0.23, + "learning_rate": 1.8940520548292332e-05, + "loss": 1.491, + "step": 2222 + }, + { + "epoch": 0.23, + "learning_rate": 1.89388802925153e-05, + "loss": 1.5157, + "step": 2223 + }, + { + "epoch": 0.23, + "learning_rate": 1.8937238839157987e-05, + "loss": 1.4779, + "step": 2224 + }, + { + "epoch": 0.23, + "learning_rate": 1.8935596188440302e-05, + "loss": 1.4902, + "step": 2225 + }, + { + "epoch": 0.23, + "learning_rate": 1.8933952340582323e-05, + "loss": 1.4988, + "step": 2226 + }, + { + "epoch": 0.23, + "learning_rate": 1.893230729580428e-05, + "loss": 1.4568, + "step": 2227 + }, + { + "epoch": 0.23, + "learning_rate": 1.8930661054326567e-05, + "loss": 1.5163, + "step": 2228 + }, + { + "epoch": 0.23, + "learning_rate": 1.892901361636974e-05, + "loss": 1.4472, + "step": 2229 + }, + { + "epoch": 0.23, + "learning_rate": 1.892736498215451e-05, + "loss": 1.4658, + "step": 2230 + }, + { + "epoch": 0.23, + "learning_rate": 1.8925715151901754e-05, + "loss": 1.4281, + "step": 2231 + }, + { + "epoch": 0.23, + "learning_rate": 1.892406412583251e-05, + "loss": 1.415, + "step": 2232 + }, + { + "epoch": 0.23, + "learning_rate": 1.8922411904167966e-05, + "loss": 1.464, + "step": 2233 + }, + { + "epoch": 0.23, + "learning_rate": 1.892075848712948e-05, + "loss": 1.5014, + "step": 2234 + }, + { + "epoch": 0.23, + "learning_rate": 1.8919103874938568e-05, + "loss": 1.4397, + "step": 2235 + }, + { + "epoch": 0.23, + "learning_rate": 1.891744806781691e-05, + "loss": 1.5508, + "step": 2236 + }, + { + "epoch": 0.23, + "learning_rate": 1.8915791065986335e-05, + "loss": 1.4749, + "step": 2237 + }, + { + "epoch": 0.23, + "learning_rate": 1.891413286966884e-05, + "loss": 1.4538, + "step": 2238 + }, + { + "epoch": 0.23, + "learning_rate": 1.891247347908658e-05, + "loss": 1.4405, + "step": 2239 + }, + { + "epoch": 0.23, + "learning_rate": 1.8910812894461878e-05, + "loss": 1.3562, + "step": 2240 + }, + { + "epoch": 0.24, + "learning_rate": 1.89091511160172e-05, + "loss": 1.4811, + "step": 2241 + }, + { + "epoch": 0.24, + "learning_rate": 1.8907488143975186e-05, + "loss": 1.4286, + "step": 2242 + }, + { + "epoch": 0.24, + "learning_rate": 1.890582397855863e-05, + "loss": 1.4493, + "step": 2243 + }, + { + "epoch": 0.24, + "learning_rate": 1.890415861999049e-05, + "loss": 1.5639, + "step": 2244 + }, + { + "epoch": 0.24, + "learning_rate": 1.890249206849388e-05, + "loss": 1.6375, + "step": 2245 + }, + { + "epoch": 0.24, + "learning_rate": 1.890082432429208e-05, + "loss": 1.4982, + "step": 2246 + }, + { + "epoch": 0.24, + "learning_rate": 1.889915538760851e-05, + "loss": 1.492, + "step": 2247 + }, + { + "epoch": 0.24, + "learning_rate": 1.8897485258666778e-05, + "loss": 1.4294, + "step": 2248 + }, + { + "epoch": 0.24, + "learning_rate": 1.8895813937690638e-05, + "loss": 1.4617, + "step": 2249 + }, + { + "epoch": 0.24, + "learning_rate": 1.8894141424904e-05, + "loss": 1.4763, + "step": 2250 + }, + { + "epoch": 0.24, + "learning_rate": 1.8892467720530937e-05, + "loss": 1.3989, + "step": 2251 + }, + { + "epoch": 0.24, + "learning_rate": 1.8890792824795687e-05, + "loss": 1.4803, + "step": 2252 + }, + { + "epoch": 0.24, + "learning_rate": 1.8889116737922638e-05, + "loss": 1.4734, + "step": 2253 + }, + { + "epoch": 0.24, + "learning_rate": 1.8887439460136342e-05, + "loss": 1.5069, + "step": 2254 + }, + { + "epoch": 0.24, + "learning_rate": 1.8885760991661514e-05, + "loss": 1.5565, + "step": 2255 + }, + { + "epoch": 0.24, + "learning_rate": 1.8884081332723028e-05, + "loss": 1.4707, + "step": 2256 + }, + { + "epoch": 0.24, + "learning_rate": 1.8882400483545913e-05, + "loss": 1.5077, + "step": 2257 + }, + { + "epoch": 0.24, + "learning_rate": 1.888071844435536e-05, + "loss": 1.5075, + "step": 2258 + }, + { + "epoch": 0.24, + "learning_rate": 1.8879035215376717e-05, + "loss": 1.5185, + "step": 2259 + }, + { + "epoch": 0.24, + "learning_rate": 1.887735079683549e-05, + "loss": 1.6266, + "step": 2260 + }, + { + "epoch": 0.24, + "learning_rate": 1.8875665188957354e-05, + "loss": 1.5013, + "step": 2261 + }, + { + "epoch": 0.24, + "learning_rate": 1.887397839196814e-05, + "loss": 1.4362, + "step": 2262 + }, + { + "epoch": 0.24, + "learning_rate": 1.8872290406093827e-05, + "loss": 1.4718, + "step": 2263 + }, + { + "epoch": 0.24, + "learning_rate": 1.8870601231560567e-05, + "loss": 1.5202, + "step": 2264 + }, + { + "epoch": 0.24, + "learning_rate": 1.8868910868594664e-05, + "loss": 1.5168, + "step": 2265 + }, + { + "epoch": 0.24, + "learning_rate": 1.8867219317422588e-05, + "loss": 1.5142, + "step": 2266 + }, + { + "epoch": 0.24, + "learning_rate": 1.8865526578270954e-05, + "loss": 1.4885, + "step": 2267 + }, + { + "epoch": 0.24, + "learning_rate": 1.8863832651366552e-05, + "loss": 1.5441, + "step": 2268 + }, + { + "epoch": 0.24, + "learning_rate": 1.8862137536936328e-05, + "loss": 1.4647, + "step": 2269 + }, + { + "epoch": 0.24, + "learning_rate": 1.8860441235207374e-05, + "loss": 1.5352, + "step": 2270 + }, + { + "epoch": 0.24, + "learning_rate": 1.8858743746406958e-05, + "loss": 1.4568, + "step": 2271 + }, + { + "epoch": 0.24, + "learning_rate": 1.8857045070762497e-05, + "loss": 1.4865, + "step": 2272 + }, + { + "epoch": 0.24, + "learning_rate": 1.8855345208501573e-05, + "loss": 1.4637, + "step": 2273 + }, + { + "epoch": 0.24, + "learning_rate": 1.8853644159851918e-05, + "loss": 1.4348, + "step": 2274 + }, + { + "epoch": 0.24, + "learning_rate": 1.8851941925041436e-05, + "loss": 1.4413, + "step": 2275 + }, + { + "epoch": 0.24, + "learning_rate": 1.8850238504298177e-05, + "loss": 1.4434, + "step": 2276 + }, + { + "epoch": 0.24, + "learning_rate": 1.884853389785036e-05, + "loss": 1.4822, + "step": 2277 + }, + { + "epoch": 0.24, + "learning_rate": 1.8846828105926356e-05, + "loss": 1.4632, + "step": 2278 + }, + { + "epoch": 0.24, + "learning_rate": 1.8845121128754698e-05, + "loss": 1.48, + "step": 2279 + }, + { + "epoch": 0.24, + "learning_rate": 1.8843412966564078e-05, + "loss": 1.4518, + "step": 2280 + }, + { + "epoch": 0.24, + "learning_rate": 1.884170361958334e-05, + "loss": 1.4334, + "step": 2281 + }, + { + "epoch": 0.24, + "learning_rate": 1.8839993088041502e-05, + "loss": 1.5131, + "step": 2282 + }, + { + "epoch": 0.24, + "learning_rate": 1.8838281372167724e-05, + "loss": 1.508, + "step": 2283 + }, + { + "epoch": 0.24, + "learning_rate": 1.8836568472191335e-05, + "loss": 1.4086, + "step": 2284 + }, + { + "epoch": 0.24, + "learning_rate": 1.883485438834182e-05, + "loss": 1.5021, + "step": 2285 + }, + { + "epoch": 0.24, + "learning_rate": 1.8833139120848817e-05, + "loss": 1.5083, + "step": 2286 + }, + { + "epoch": 0.24, + "learning_rate": 1.8831422669942137e-05, + "loss": 1.4162, + "step": 2287 + }, + { + "epoch": 0.24, + "learning_rate": 1.8829705035851734e-05, + "loss": 1.5494, + "step": 2288 + }, + { + "epoch": 0.24, + "learning_rate": 1.8827986218807724e-05, + "loss": 1.425, + "step": 2289 + }, + { + "epoch": 0.24, + "learning_rate": 1.8826266219040396e-05, + "loss": 1.5215, + "step": 2290 + }, + { + "epoch": 0.24, + "learning_rate": 1.8824545036780172e-05, + "loss": 1.5577, + "step": 2291 + }, + { + "epoch": 0.24, + "learning_rate": 1.8822822672257655e-05, + "loss": 1.4923, + "step": 2292 + }, + { + "epoch": 0.24, + "learning_rate": 1.8821099125703595e-05, + "loss": 1.4648, + "step": 2293 + }, + { + "epoch": 0.24, + "learning_rate": 1.8819374397348902e-05, + "loss": 1.471, + "step": 2294 + }, + { + "epoch": 0.24, + "learning_rate": 1.8817648487424648e-05, + "loss": 1.5658, + "step": 2295 + }, + { + "epoch": 0.24, + "learning_rate": 1.8815921396162058e-05, + "loss": 1.5348, + "step": 2296 + }, + { + "epoch": 0.24, + "learning_rate": 1.8814193123792518e-05, + "loss": 1.4081, + "step": 2297 + }, + { + "epoch": 0.24, + "learning_rate": 1.881246367054757e-05, + "loss": 1.4762, + "step": 2298 + }, + { + "epoch": 0.24, + "learning_rate": 1.8810733036658925e-05, + "loss": 1.4399, + "step": 2299 + }, + { + "epoch": 0.24, + "learning_rate": 1.8809001222358432e-05, + "loss": 1.4763, + "step": 2300 + }, + { + "epoch": 0.24, + "learning_rate": 1.880726822787812e-05, + "loss": 1.4874, + "step": 2301 + }, + { + "epoch": 0.24, + "learning_rate": 1.880553405345016e-05, + "loss": 1.4951, + "step": 2302 + }, + { + "epoch": 0.24, + "learning_rate": 1.8803798699306887e-05, + "loss": 1.4697, + "step": 2303 + }, + { + "epoch": 0.24, + "learning_rate": 1.880206216568079e-05, + "loss": 1.481, + "step": 2304 + }, + { + "epoch": 0.24, + "learning_rate": 1.880032445280453e-05, + "loss": 1.4485, + "step": 2305 + }, + { + "epoch": 0.24, + "learning_rate": 1.879858556091091e-05, + "loss": 1.4749, + "step": 2306 + }, + { + "epoch": 0.24, + "learning_rate": 1.8796845490232894e-05, + "loss": 1.5605, + "step": 2307 + }, + { + "epoch": 0.24, + "learning_rate": 1.879510424100361e-05, + "loss": 1.4835, + "step": 2308 + }, + { + "epoch": 0.24, + "learning_rate": 1.8793361813456346e-05, + "loss": 1.4344, + "step": 2309 + }, + { + "epoch": 0.24, + "learning_rate": 1.8791618207824532e-05, + "loss": 1.4571, + "step": 2310 + }, + { + "epoch": 0.24, + "learning_rate": 1.8789873424341772e-05, + "loss": 1.482, + "step": 2311 + }, + { + "epoch": 0.24, + "learning_rate": 1.8788127463241822e-05, + "loss": 1.4736, + "step": 2312 + }, + { + "epoch": 0.24, + "learning_rate": 1.8786380324758597e-05, + "loss": 1.4807, + "step": 2313 + }, + { + "epoch": 0.24, + "learning_rate": 1.8784632009126167e-05, + "loss": 1.4418, + "step": 2314 + }, + { + "epoch": 0.24, + "learning_rate": 1.878288251657876e-05, + "loss": 1.5248, + "step": 2315 + }, + { + "epoch": 0.24, + "learning_rate": 1.8781131847350768e-05, + "loss": 1.483, + "step": 2316 + }, + { + "epoch": 0.24, + "learning_rate": 1.877938000167673e-05, + "loss": 1.5474, + "step": 2317 + }, + { + "epoch": 0.24, + "learning_rate": 1.8777626979791347e-05, + "loss": 1.4671, + "step": 2318 + }, + { + "epoch": 0.24, + "learning_rate": 1.877587278192949e-05, + "loss": 1.3049, + "step": 2319 + }, + { + "epoch": 0.24, + "learning_rate": 1.877411740832616e-05, + "loss": 1.483, + "step": 2320 + }, + { + "epoch": 0.24, + "learning_rate": 1.877236085921655e-05, + "loss": 1.508, + "step": 2321 + }, + { + "epoch": 0.24, + "learning_rate": 1.8770603134835978e-05, + "loss": 1.4854, + "step": 2322 + }, + { + "epoch": 0.24, + "learning_rate": 1.8768844235419942e-05, + "loss": 1.4808, + "step": 2323 + }, + { + "epoch": 0.24, + "learning_rate": 1.8767084161204087e-05, + "loss": 1.5352, + "step": 2324 + }, + { + "epoch": 0.24, + "learning_rate": 1.8765322912424214e-05, + "loss": 1.5628, + "step": 2325 + }, + { + "epoch": 0.24, + "learning_rate": 1.8763560489316292e-05, + "loss": 1.494, + "step": 2326 + }, + { + "epoch": 0.24, + "learning_rate": 1.876179689211643e-05, + "loss": 1.509, + "step": 2327 + }, + { + "epoch": 0.24, + "learning_rate": 1.8760032121060918e-05, + "loss": 1.5021, + "step": 2328 + }, + { + "epoch": 0.24, + "learning_rate": 1.875826617638618e-05, + "loss": 1.4179, + "step": 2329 + }, + { + "epoch": 0.24, + "learning_rate": 1.8756499058328813e-05, + "loss": 1.4302, + "step": 2330 + }, + { + "epoch": 0.24, + "learning_rate": 1.8754730767125564e-05, + "loss": 1.4959, + "step": 2331 + }, + { + "epoch": 0.24, + "learning_rate": 1.8752961303013336e-05, + "loss": 1.4423, + "step": 2332 + }, + { + "epoch": 0.24, + "learning_rate": 1.8751190666229194e-05, + "loss": 1.4564, + "step": 2333 + }, + { + "epoch": 0.24, + "learning_rate": 1.8749418857010358e-05, + "loss": 1.4775, + "step": 2334 + }, + { + "epoch": 0.24, + "learning_rate": 1.8747645875594203e-05, + "loss": 1.4182, + "step": 2335 + }, + { + "epoch": 0.24, + "learning_rate": 1.8745871722218265e-05, + "loss": 1.3957, + "step": 2336 + }, + { + "epoch": 0.25, + "learning_rate": 1.8744096397120235e-05, + "loss": 1.4633, + "step": 2337 + }, + { + "epoch": 0.25, + "learning_rate": 1.874231990053796e-05, + "loss": 1.5512, + "step": 2338 + }, + { + "epoch": 0.25, + "learning_rate": 1.8740542232709444e-05, + "loss": 1.3461, + "step": 2339 + }, + { + "epoch": 0.25, + "learning_rate": 1.8738763393872848e-05, + "loss": 1.4754, + "step": 2340 + }, + { + "epoch": 0.25, + "learning_rate": 1.8736983384266495e-05, + "loss": 1.5448, + "step": 2341 + }, + { + "epoch": 0.25, + "learning_rate": 1.8735202204128854e-05, + "loss": 1.4491, + "step": 2342 + }, + { + "epoch": 0.25, + "learning_rate": 1.8733419853698566e-05, + "loss": 1.457, + "step": 2343 + }, + { + "epoch": 0.25, + "learning_rate": 1.8731636333214414e-05, + "loss": 1.4314, + "step": 2344 + }, + { + "epoch": 0.25, + "learning_rate": 1.8729851642915345e-05, + "loss": 1.3979, + "step": 2345 + }, + { + "epoch": 0.25, + "learning_rate": 1.8728065783040464e-05, + "loss": 1.4146, + "step": 2346 + }, + { + "epoch": 0.25, + "learning_rate": 1.8726278753829027e-05, + "loss": 1.4361, + "step": 2347 + }, + { + "epoch": 0.25, + "learning_rate": 1.872449055552045e-05, + "loss": 1.4989, + "step": 2348 + }, + { + "epoch": 0.25, + "learning_rate": 1.872270118835431e-05, + "loss": 1.5062, + "step": 2349 + }, + { + "epoch": 0.25, + "learning_rate": 1.872091065257033e-05, + "loss": 1.4509, + "step": 2350 + }, + { + "epoch": 0.25, + "learning_rate": 1.8719118948408403e-05, + "loss": 1.4631, + "step": 2351 + }, + { + "epoch": 0.25, + "learning_rate": 1.8717326076108566e-05, + "loss": 1.5119, + "step": 2352 + }, + { + "epoch": 0.25, + "learning_rate": 1.8715532035911017e-05, + "loss": 1.6347, + "step": 2353 + }, + { + "epoch": 0.25, + "learning_rate": 1.8713736828056115e-05, + "loss": 1.5526, + "step": 2354 + }, + { + "epoch": 0.25, + "learning_rate": 1.8711940452784368e-05, + "loss": 1.6348, + "step": 2355 + }, + { + "epoch": 0.25, + "learning_rate": 1.871014291033645e-05, + "loss": 1.5183, + "step": 2356 + }, + { + "epoch": 0.25, + "learning_rate": 1.8708344200953182e-05, + "loss": 1.458, + "step": 2357 + }, + { + "epoch": 0.25, + "learning_rate": 1.8706544324875545e-05, + "loss": 1.524, + "step": 2358 + }, + { + "epoch": 0.25, + "learning_rate": 1.8704743282344672e-05, + "loss": 1.4479, + "step": 2359 + }, + { + "epoch": 0.25, + "learning_rate": 1.870294107360186e-05, + "loss": 1.5408, + "step": 2360 + }, + { + "epoch": 0.25, + "learning_rate": 1.8701137698888563e-05, + "loss": 1.5007, + "step": 2361 + }, + { + "epoch": 0.25, + "learning_rate": 1.8699333158446382e-05, + "loss": 1.5132, + "step": 2362 + }, + { + "epoch": 0.25, + "learning_rate": 1.869752745251708e-05, + "loss": 1.4263, + "step": 2363 + }, + { + "epoch": 0.25, + "learning_rate": 1.8695720581342574e-05, + "loss": 1.422, + "step": 2364 + }, + { + "epoch": 0.25, + "learning_rate": 1.869391254516494e-05, + "loss": 1.4411, + "step": 2365 + }, + { + "epoch": 0.25, + "learning_rate": 1.8692103344226406e-05, + "loss": 1.4594, + "step": 2366 + }, + { + "epoch": 0.25, + "learning_rate": 1.8690292978769364e-05, + "loss": 1.4992, + "step": 2367 + }, + { + "epoch": 0.25, + "learning_rate": 1.868848144903635e-05, + "loss": 1.4822, + "step": 2368 + }, + { + "epoch": 0.25, + "learning_rate": 1.8686668755270064e-05, + "loss": 1.5402, + "step": 2369 + }, + { + "epoch": 0.25, + "learning_rate": 1.8684854897713363e-05, + "loss": 1.5268, + "step": 2370 + }, + { + "epoch": 0.25, + "learning_rate": 1.8683039876609258e-05, + "loss": 1.5587, + "step": 2371 + }, + { + "epoch": 0.25, + "learning_rate": 1.868122369220091e-05, + "loss": 1.4214, + "step": 2372 + }, + { + "epoch": 0.25, + "learning_rate": 1.8679406344731645e-05, + "loss": 1.5089, + "step": 2373 + }, + { + "epoch": 0.25, + "learning_rate": 1.867758783444494e-05, + "loss": 1.5067, + "step": 2374 + }, + { + "epoch": 0.25, + "learning_rate": 1.8675768161584427e-05, + "loss": 2.0616, + "step": 2375 + }, + { + "epoch": 0.25, + "learning_rate": 1.8673947326393903e-05, + "loss": 1.5617, + "step": 2376 + }, + { + "epoch": 0.25, + "learning_rate": 1.86721253291173e-05, + "loss": 1.4422, + "step": 2377 + }, + { + "epoch": 0.25, + "learning_rate": 1.867030216999873e-05, + "loss": 1.4727, + "step": 2378 + }, + { + "epoch": 0.25, + "learning_rate": 1.8668477849282443e-05, + "loss": 1.4152, + "step": 2379 + }, + { + "epoch": 0.25, + "learning_rate": 1.8666652367212856e-05, + "loss": 1.4376, + "step": 2380 + }, + { + "epoch": 0.25, + "learning_rate": 1.8664825724034534e-05, + "loss": 1.393, + "step": 2381 + }, + { + "epoch": 0.25, + "learning_rate": 1.8662997919992197e-05, + "loss": 1.4864, + "step": 2382 + }, + { + "epoch": 0.25, + "learning_rate": 1.866116895533073e-05, + "loss": 1.4261, + "step": 2383 + }, + { + "epoch": 0.25, + "learning_rate": 1.8659338830295163e-05, + "loss": 1.4555, + "step": 2384 + }, + { + "epoch": 0.25, + "learning_rate": 1.8657507545130687e-05, + "loss": 1.4939, + "step": 2385 + }, + { + "epoch": 0.25, + "learning_rate": 1.865567510008265e-05, + "loss": 1.4123, + "step": 2386 + }, + { + "epoch": 0.25, + "learning_rate": 1.8653841495396546e-05, + "loss": 1.4459, + "step": 2387 + }, + { + "epoch": 0.25, + "learning_rate": 1.8652006731318038e-05, + "loss": 1.396, + "step": 2388 + }, + { + "epoch": 0.25, + "eval_loss": 1.5139706134796143, + "eval_runtime": 77.2904, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 2388 + }, + { + "epoch": 0.25, + "learning_rate": 1.8650170808092936e-05, + "loss": 1.4666, + "step": 2389 + }, + { + "epoch": 0.25, + "learning_rate": 1.86483337259672e-05, + "loss": 1.5154, + "step": 2390 + }, + { + "epoch": 0.25, + "learning_rate": 1.864649548518696e-05, + "loss": 1.5163, + "step": 2391 + }, + { + "epoch": 0.25, + "learning_rate": 1.864465608599849e-05, + "loss": 1.4734, + "step": 2392 + }, + { + "epoch": 0.25, + "learning_rate": 1.864281552864822e-05, + "loss": 1.5217, + "step": 2393 + }, + { + "epoch": 0.25, + "learning_rate": 1.8640973813382737e-05, + "loss": 1.4694, + "step": 2394 + }, + { + "epoch": 0.25, + "learning_rate": 1.863913094044879e-05, + "loss": 1.4761, + "step": 2395 + }, + { + "epoch": 0.25, + "learning_rate": 1.863728691009327e-05, + "loss": 1.4766, + "step": 2396 + }, + { + "epoch": 0.25, + "learning_rate": 1.863544172256323e-05, + "loss": 1.5695, + "step": 2397 + }, + { + "epoch": 0.25, + "learning_rate": 1.8633595378105882e-05, + "loss": 1.5079, + "step": 2398 + }, + { + "epoch": 0.25, + "learning_rate": 1.8631747876968584e-05, + "loss": 1.4154, + "step": 2399 + }, + { + "epoch": 0.25, + "learning_rate": 1.862989921939886e-05, + "loss": 1.4488, + "step": 2400 + }, + { + "epoch": 0.25, + "learning_rate": 1.8628049405644376e-05, + "loss": 1.4279, + "step": 2401 + }, + { + "epoch": 0.25, + "learning_rate": 1.8626198435952966e-05, + "loss": 1.4896, + "step": 2402 + }, + { + "epoch": 0.25, + "learning_rate": 1.8624346310572602e-05, + "loss": 1.4315, + "step": 2403 + }, + { + "epoch": 0.25, + "learning_rate": 1.862249302975143e-05, + "loss": 1.4919, + "step": 2404 + }, + { + "epoch": 0.25, + "learning_rate": 1.8620638593737743e-05, + "loss": 1.4561, + "step": 2405 + }, + { + "epoch": 0.25, + "learning_rate": 1.8618783002779985e-05, + "loss": 1.4622, + "step": 2406 + }, + { + "epoch": 0.25, + "learning_rate": 1.8616926257126754e-05, + "loss": 1.4917, + "step": 2407 + }, + { + "epoch": 0.25, + "learning_rate": 1.861506835702681e-05, + "loss": 1.4962, + "step": 2408 + }, + { + "epoch": 0.25, + "learning_rate": 1.861320930272906e-05, + "loss": 1.4164, + "step": 2409 + }, + { + "epoch": 0.25, + "learning_rate": 1.8611349094482578e-05, + "loss": 1.4889, + "step": 2410 + }, + { + "epoch": 0.25, + "learning_rate": 1.8609487732536576e-05, + "loss": 1.543, + "step": 2411 + }, + { + "epoch": 0.25, + "learning_rate": 1.8607625217140433e-05, + "loss": 1.5417, + "step": 2412 + }, + { + "epoch": 0.25, + "learning_rate": 1.8605761548543674e-05, + "loss": 1.5304, + "step": 2413 + }, + { + "epoch": 0.25, + "learning_rate": 1.860389672699599e-05, + "loss": 1.4725, + "step": 2414 + }, + { + "epoch": 0.25, + "learning_rate": 1.860203075274721e-05, + "loss": 1.4745, + "step": 2415 + }, + { + "epoch": 0.25, + "learning_rate": 1.8600163626047334e-05, + "loss": 1.4656, + "step": 2416 + }, + { + "epoch": 0.25, + "learning_rate": 1.8598295347146503e-05, + "loss": 1.5287, + "step": 2417 + }, + { + "epoch": 0.25, + "learning_rate": 1.8596425916295023e-05, + "loss": 1.5024, + "step": 2418 + }, + { + "epoch": 0.25, + "learning_rate": 1.8594555333743348e-05, + "loss": 1.4527, + "step": 2419 + }, + { + "epoch": 0.25, + "learning_rate": 1.859268359974209e-05, + "loss": 1.4897, + "step": 2420 + }, + { + "epoch": 0.25, + "learning_rate": 1.859081071454201e-05, + "loss": 1.3554, + "step": 2421 + }, + { + "epoch": 0.25, + "learning_rate": 1.858893667839403e-05, + "loss": 1.4004, + "step": 2422 + }, + { + "epoch": 0.25, + "learning_rate": 1.858706149154922e-05, + "loss": 1.5582, + "step": 2423 + }, + { + "epoch": 0.25, + "learning_rate": 1.8585185154258803e-05, + "loss": 1.505, + "step": 2424 + }, + { + "epoch": 0.25, + "learning_rate": 1.858330766677417e-05, + "loss": 1.5043, + "step": 2425 + }, + { + "epoch": 0.25, + "learning_rate": 1.858142902934685e-05, + "loss": 1.439, + "step": 2426 + }, + { + "epoch": 0.25, + "learning_rate": 1.857954924222853e-05, + "loss": 1.4927, + "step": 2427 + }, + { + "epoch": 0.25, + "learning_rate": 1.8577668305671056e-05, + "loss": 1.5395, + "step": 2428 + }, + { + "epoch": 0.25, + "learning_rate": 1.8575786219926427e-05, + "loss": 1.4737, + "step": 2429 + }, + { + "epoch": 0.25, + "learning_rate": 1.8573902985246794e-05, + "loss": 1.6151, + "step": 2430 + }, + { + "epoch": 0.25, + "learning_rate": 1.857201860188446e-05, + "loss": 1.4313, + "step": 2431 + }, + { + "epoch": 0.26, + "learning_rate": 1.857013307009188e-05, + "loss": 1.4509, + "step": 2432 + }, + { + "epoch": 0.26, + "learning_rate": 1.8568246390121673e-05, + "loss": 1.3998, + "step": 2433 + }, + { + "epoch": 0.26, + "learning_rate": 1.8566358562226603e-05, + "loss": 1.5268, + "step": 2434 + }, + { + "epoch": 0.26, + "learning_rate": 1.8564469586659593e-05, + "loss": 1.4369, + "step": 2435 + }, + { + "epoch": 0.26, + "learning_rate": 1.8562579463673713e-05, + "loss": 1.4759, + "step": 2436 + }, + { + "epoch": 0.26, + "learning_rate": 1.8560688193522197e-05, + "loss": 1.4092, + "step": 2437 + }, + { + "epoch": 0.26, + "learning_rate": 1.855879577645842e-05, + "loss": 1.43, + "step": 2438 + }, + { + "epoch": 0.26, + "learning_rate": 1.855690221273592e-05, + "loss": 1.5143, + "step": 2439 + }, + { + "epoch": 0.26, + "learning_rate": 1.8555007502608385e-05, + "loss": 1.5482, + "step": 2440 + }, + { + "epoch": 0.26, + "learning_rate": 1.855311164632966e-05, + "loss": 1.4406, + "step": 2441 + }, + { + "epoch": 0.26, + "learning_rate": 1.8551214644153738e-05, + "loss": 1.4551, + "step": 2442 + }, + { + "epoch": 0.26, + "learning_rate": 1.8549316496334774e-05, + "loss": 1.4663, + "step": 2443 + }, + { + "epoch": 0.26, + "learning_rate": 1.8547417203127064e-05, + "loss": 1.4732, + "step": 2444 + }, + { + "epoch": 0.26, + "learning_rate": 1.8545516764785067e-05, + "loss": 1.5378, + "step": 2445 + }, + { + "epoch": 0.26, + "learning_rate": 1.8543615181563397e-05, + "loss": 1.4448, + "step": 2446 + }, + { + "epoch": 0.26, + "learning_rate": 1.854171245371681e-05, + "loss": 1.2861, + "step": 2447 + }, + { + "epoch": 0.26, + "learning_rate": 1.8539808581500228e-05, + "loss": 1.4405, + "step": 2448 + }, + { + "epoch": 0.26, + "learning_rate": 1.8537903565168716e-05, + "loss": 1.4876, + "step": 2449 + }, + { + "epoch": 0.26, + "learning_rate": 1.8535997404977506e-05, + "loss": 1.4119, + "step": 2450 + }, + { + "epoch": 0.26, + "learning_rate": 1.8534090101181967e-05, + "loss": 1.4451, + "step": 2451 + }, + { + "epoch": 0.26, + "learning_rate": 1.8532181654037632e-05, + "loss": 1.4035, + "step": 2452 + }, + { + "epoch": 0.26, + "learning_rate": 1.853027206380018e-05, + "loss": 1.4624, + "step": 2453 + }, + { + "epoch": 0.26, + "learning_rate": 1.852836133072545e-05, + "loss": 1.4935, + "step": 2454 + }, + { + "epoch": 0.26, + "learning_rate": 1.8526449455069434e-05, + "loss": 1.4834, + "step": 2455 + }, + { + "epoch": 0.26, + "learning_rate": 1.8524536437088266e-05, + "loss": 1.498, + "step": 2456 + }, + { + "epoch": 0.26, + "learning_rate": 1.8522622277038247e-05, + "loss": 1.3417, + "step": 2457 + }, + { + "epoch": 0.26, + "learning_rate": 1.852070697517583e-05, + "loss": 1.4455, + "step": 2458 + }, + { + "epoch": 0.26, + "learning_rate": 1.8518790531757607e-05, + "loss": 1.4119, + "step": 2459 + }, + { + "epoch": 0.26, + "learning_rate": 1.8516872947040337e-05, + "loss": 1.558, + "step": 2460 + }, + { + "epoch": 0.26, + "learning_rate": 1.8514954221280926e-05, + "loss": 1.4862, + "step": 2461 + }, + { + "epoch": 0.26, + "learning_rate": 1.8513034354736433e-05, + "loss": 1.6806, + "step": 2462 + }, + { + "epoch": 0.26, + "learning_rate": 1.8511113347664072e-05, + "loss": 1.438, + "step": 2463 + }, + { + "epoch": 0.26, + "learning_rate": 1.850919120032121e-05, + "loss": 1.4975, + "step": 2464 + }, + { + "epoch": 0.26, + "learning_rate": 1.850726791296536e-05, + "loss": 1.4409, + "step": 2465 + }, + { + "epoch": 0.26, + "learning_rate": 1.85053434858542e-05, + "loss": 1.4769, + "step": 2466 + }, + { + "epoch": 0.26, + "learning_rate": 1.8503417919245548e-05, + "loss": 1.5823, + "step": 2467 + }, + { + "epoch": 0.26, + "learning_rate": 1.8501491213397386e-05, + "loss": 1.4045, + "step": 2468 + }, + { + "epoch": 0.26, + "learning_rate": 1.8499563368567837e-05, + "loss": 1.4828, + "step": 2469 + }, + { + "epoch": 0.26, + "learning_rate": 1.849763438501519e-05, + "loss": 1.4684, + "step": 2470 + }, + { + "epoch": 0.26, + "learning_rate": 1.8495704262997873e-05, + "loss": 1.4577, + "step": 2471 + }, + { + "epoch": 0.26, + "learning_rate": 1.8493773002774475e-05, + "loss": 1.4759, + "step": 2472 + }, + { + "epoch": 0.26, + "learning_rate": 1.8491840604603736e-05, + "loss": 1.4259, + "step": 2473 + }, + { + "epoch": 0.26, + "learning_rate": 1.8489907068744543e-05, + "loss": 1.4717, + "step": 2474 + }, + { + "epoch": 0.26, + "learning_rate": 1.848797239545595e-05, + "loss": 1.4247, + "step": 2475 + }, + { + "epoch": 0.26, + "learning_rate": 1.8486036584997143e-05, + "loss": 1.4954, + "step": 2476 + }, + { + "epoch": 0.26, + "learning_rate": 1.8484099637627472e-05, + "loss": 1.4926, + "step": 2477 + }, + { + "epoch": 0.26, + "learning_rate": 1.8482161553606447e-05, + "loss": 1.487, + "step": 2478 + }, + { + "epoch": 0.26, + "learning_rate": 1.8480222333193715e-05, + "loss": 1.4553, + "step": 2479 + }, + { + "epoch": 0.26, + "learning_rate": 1.847828197664908e-05, + "loss": 1.4862, + "step": 2480 + }, + { + "epoch": 0.26, + "learning_rate": 1.8476340484232508e-05, + "loss": 1.4867, + "step": 2481 + }, + { + "epoch": 0.26, + "learning_rate": 1.8474397856204097e-05, + "loss": 1.4736, + "step": 2482 + }, + { + "epoch": 0.26, + "learning_rate": 1.8472454092824122e-05, + "loss": 1.4254, + "step": 2483 + }, + { + "epoch": 0.26, + "learning_rate": 1.8470509194352987e-05, + "loss": 1.4455, + "step": 2484 + }, + { + "epoch": 0.26, + "learning_rate": 1.8468563161051263e-05, + "loss": 1.4402, + "step": 2485 + }, + { + "epoch": 0.26, + "learning_rate": 1.846661599317967e-05, + "loss": 1.4611, + "step": 2486 + }, + { + "epoch": 0.26, + "learning_rate": 1.8464667690999073e-05, + "loss": 1.4814, + "step": 2487 + }, + { + "epoch": 0.26, + "learning_rate": 1.8462718254770503e-05, + "loss": 1.4559, + "step": 2488 + }, + { + "epoch": 0.26, + "learning_rate": 1.8460767684755127e-05, + "loss": 1.4667, + "step": 2489 + }, + { + "epoch": 0.26, + "learning_rate": 1.8458815981214274e-05, + "loss": 1.4427, + "step": 2490 + }, + { + "epoch": 0.26, + "learning_rate": 1.845686314440942e-05, + "loss": 1.4055, + "step": 2491 + }, + { + "epoch": 0.26, + "learning_rate": 1.8454909174602198e-05, + "loss": 1.5563, + "step": 2492 + }, + { + "epoch": 0.26, + "learning_rate": 1.845295407205439e-05, + "loss": 1.4631, + "step": 2493 + }, + { + "epoch": 0.26, + "learning_rate": 1.8450997837027925e-05, + "loss": 1.4887, + "step": 2494 + }, + { + "epoch": 0.26, + "learning_rate": 1.8449040469784895e-05, + "loss": 1.5212, + "step": 2495 + }, + { + "epoch": 0.26, + "learning_rate": 1.844708197058753e-05, + "loss": 1.5582, + "step": 2496 + }, + { + "epoch": 0.26, + "learning_rate": 1.844512233969822e-05, + "loss": 1.4599, + "step": 2497 + }, + { + "epoch": 0.26, + "learning_rate": 1.844316157737951e-05, + "loss": 1.4546, + "step": 2498 + }, + { + "epoch": 0.26, + "learning_rate": 1.844119968389409e-05, + "loss": 1.4631, + "step": 2499 + }, + { + "epoch": 0.26, + "learning_rate": 1.84392366595048e-05, + "loss": 1.4817, + "step": 2500 + }, + { + "epoch": 0.26, + "learning_rate": 1.8437272504474636e-05, + "loss": 1.4214, + "step": 2501 + }, + { + "epoch": 0.26, + "learning_rate": 1.8435307219066744e-05, + "loss": 1.471, + "step": 2502 + }, + { + "epoch": 0.26, + "learning_rate": 1.8433340803544424e-05, + "loss": 1.4693, + "step": 2503 + }, + { + "epoch": 0.26, + "learning_rate": 1.8431373258171127e-05, + "loss": 1.6297, + "step": 2504 + }, + { + "epoch": 0.26, + "learning_rate": 1.842940458321045e-05, + "loss": 1.5916, + "step": 2505 + }, + { + "epoch": 0.26, + "learning_rate": 1.842743477892614e-05, + "loss": 1.4754, + "step": 2506 + }, + { + "epoch": 0.26, + "learning_rate": 1.842546384558211e-05, + "loss": 1.4828, + "step": 2507 + }, + { + "epoch": 0.26, + "learning_rate": 1.842349178344241e-05, + "loss": 1.4239, + "step": 2508 + }, + { + "epoch": 0.26, + "learning_rate": 1.8421518592771243e-05, + "loss": 1.5028, + "step": 2509 + }, + { + "epoch": 0.26, + "learning_rate": 1.841954427383297e-05, + "loss": 1.4848, + "step": 2510 + }, + { + "epoch": 0.26, + "learning_rate": 1.8417568826892097e-05, + "loss": 1.4617, + "step": 2511 + }, + { + "epoch": 0.26, + "learning_rate": 1.8415592252213284e-05, + "loss": 1.4266, + "step": 2512 + }, + { + "epoch": 0.26, + "learning_rate": 1.8413614550061344e-05, + "loss": 1.4321, + "step": 2513 + }, + { + "epoch": 0.26, + "learning_rate": 1.841163572070123e-05, + "loss": 1.4693, + "step": 2514 + }, + { + "epoch": 0.26, + "learning_rate": 1.840965576439806e-05, + "loss": 1.4257, + "step": 2515 + }, + { + "epoch": 0.26, + "learning_rate": 1.84076746814171e-05, + "loss": 1.4488, + "step": 2516 + }, + { + "epoch": 0.26, + "learning_rate": 1.840569247202376e-05, + "loss": 1.5348, + "step": 2517 + }, + { + "epoch": 0.26, + "learning_rate": 1.8403709136483604e-05, + "loss": 1.477, + "step": 2518 + }, + { + "epoch": 0.26, + "learning_rate": 1.840172467506235e-05, + "loss": 1.443, + "step": 2519 + }, + { + "epoch": 0.26, + "learning_rate": 1.839973908802587e-05, + "loss": 1.4772, + "step": 2520 + }, + { + "epoch": 0.26, + "learning_rate": 1.839775237564017e-05, + "loss": 1.4443, + "step": 2521 + }, + { + "epoch": 0.26, + "learning_rate": 1.839576453817143e-05, + "loss": 1.4063, + "step": 2522 + }, + { + "epoch": 0.26, + "learning_rate": 1.8393775575885963e-05, + "loss": 1.5178, + "step": 2523 + }, + { + "epoch": 0.26, + "learning_rate": 1.8391785489050235e-05, + "loss": 1.4337, + "step": 2524 + }, + { + "epoch": 0.26, + "learning_rate": 1.8389794277930875e-05, + "loss": 1.4512, + "step": 2525 + }, + { + "epoch": 0.26, + "learning_rate": 1.838780194279465e-05, + "loss": 1.5578, + "step": 2526 + }, + { + "epoch": 0.26, + "learning_rate": 1.8385808483908484e-05, + "loss": 1.4606, + "step": 2527 + }, + { + "epoch": 0.27, + "learning_rate": 1.8383813901539444e-05, + "loss": 1.4957, + "step": 2528 + }, + { + "epoch": 0.27, + "learning_rate": 1.838181819595476e-05, + "loss": 1.4914, + "step": 2529 + }, + { + "epoch": 0.27, + "learning_rate": 1.8379821367421802e-05, + "loss": 1.4785, + "step": 2530 + }, + { + "epoch": 0.27, + "learning_rate": 1.837782341620809e-05, + "loss": 1.4052, + "step": 2531 + }, + { + "epoch": 0.27, + "learning_rate": 1.8375824342581303e-05, + "loss": 1.4807, + "step": 2532 + }, + { + "epoch": 0.27, + "learning_rate": 1.8373824146809264e-05, + "loss": 1.4313, + "step": 2533 + }, + { + "epoch": 0.27, + "learning_rate": 1.8371822829159945e-05, + "loss": 1.4374, + "step": 2534 + }, + { + "epoch": 0.27, + "learning_rate": 1.836982038990148e-05, + "loss": 1.4482, + "step": 2535 + }, + { + "epoch": 0.27, + "learning_rate": 1.8367816829302133e-05, + "loss": 1.5231, + "step": 2536 + }, + { + "epoch": 0.27, + "learning_rate": 1.8365812147630337e-05, + "loss": 1.4101, + "step": 2537 + }, + { + "epoch": 0.27, + "learning_rate": 1.8363806345154666e-05, + "loss": 1.4372, + "step": 2538 + }, + { + "epoch": 0.27, + "learning_rate": 1.8361799422143845e-05, + "loss": 1.4808, + "step": 2539 + }, + { + "epoch": 0.27, + "learning_rate": 1.835979137886675e-05, + "loss": 1.3515, + "step": 2540 + }, + { + "epoch": 0.27, + "learning_rate": 1.8357782215592412e-05, + "loss": 1.5284, + "step": 2541 + }, + { + "epoch": 0.27, + "learning_rate": 1.835577193259e-05, + "loss": 1.4222, + "step": 2542 + }, + { + "epoch": 0.27, + "learning_rate": 1.8353760530128846e-05, + "loss": 1.4522, + "step": 2543 + }, + { + "epoch": 0.27, + "learning_rate": 1.835174800847842e-05, + "loss": 1.4487, + "step": 2544 + }, + { + "epoch": 0.27, + "learning_rate": 1.8349734367908355e-05, + "loss": 1.3688, + "step": 2545 + }, + { + "epoch": 0.27, + "learning_rate": 1.8347719608688422e-05, + "loss": 1.483, + "step": 2546 + }, + { + "epoch": 0.27, + "learning_rate": 1.8345703731088554e-05, + "loss": 1.4733, + "step": 2547 + }, + { + "epoch": 0.27, + "learning_rate": 1.8343686735378816e-05, + "loss": 1.4594, + "step": 2548 + }, + { + "epoch": 0.27, + "learning_rate": 1.834166862182944e-05, + "loss": 1.4648, + "step": 2549 + }, + { + "epoch": 0.27, + "learning_rate": 1.8339649390710807e-05, + "loss": 1.5249, + "step": 2550 + }, + { + "epoch": 0.27, + "learning_rate": 1.8337629042293434e-05, + "loss": 1.4744, + "step": 2551 + }, + { + "epoch": 0.27, + "learning_rate": 1.8335607576847994e-05, + "loss": 1.5094, + "step": 2552 + }, + { + "epoch": 0.27, + "learning_rate": 1.8333584994645318e-05, + "loss": 1.5122, + "step": 2553 + }, + { + "epoch": 0.27, + "learning_rate": 1.8331561295956374e-05, + "loss": 1.537, + "step": 2554 + }, + { + "epoch": 0.27, + "learning_rate": 1.832953648105229e-05, + "loss": 1.4691, + "step": 2555 + }, + { + "epoch": 0.27, + "learning_rate": 1.8327510550204343e-05, + "loss": 1.4969, + "step": 2556 + }, + { + "epoch": 0.27, + "learning_rate": 1.8325483503683944e-05, + "loss": 1.4596, + "step": 2557 + }, + { + "epoch": 0.27, + "learning_rate": 1.8323455341762675e-05, + "loss": 1.435, + "step": 2558 + }, + { + "epoch": 0.27, + "learning_rate": 1.8321426064712255e-05, + "loss": 1.4883, + "step": 2559 + }, + { + "epoch": 0.27, + "learning_rate": 1.8319395672804554e-05, + "loss": 1.3758, + "step": 2560 + }, + { + "epoch": 0.27, + "learning_rate": 1.8317364166311592e-05, + "loss": 1.4352, + "step": 2561 + }, + { + "epoch": 0.27, + "learning_rate": 1.831533154550554e-05, + "loss": 1.5072, + "step": 2562 + }, + { + "epoch": 0.27, + "learning_rate": 1.8313297810658718e-05, + "loss": 1.4476, + "step": 2563 + }, + { + "epoch": 0.27, + "learning_rate": 1.831126296204359e-05, + "loss": 1.507, + "step": 2564 + }, + { + "epoch": 0.27, + "learning_rate": 1.8309226999932777e-05, + "loss": 1.4677, + "step": 2565 + }, + { + "epoch": 0.27, + "learning_rate": 1.8307189924599044e-05, + "loss": 1.4537, + "step": 2566 + }, + { + "epoch": 0.27, + "learning_rate": 1.8305151736315307e-05, + "loss": 1.4584, + "step": 2567 + }, + { + "epoch": 0.27, + "learning_rate": 1.8303112435354634e-05, + "loss": 1.4944, + "step": 2568 + }, + { + "epoch": 0.27, + "learning_rate": 1.8301072021990232e-05, + "loss": 1.4379, + "step": 2569 + }, + { + "epoch": 0.27, + "learning_rate": 1.8299030496495475e-05, + "loss": 1.539, + "step": 2570 + }, + { + "epoch": 0.27, + "learning_rate": 1.829698785914386e-05, + "loss": 1.4421, + "step": 2571 + }, + { + "epoch": 0.27, + "learning_rate": 1.8294944110209063e-05, + "loss": 1.4693, + "step": 2572 + }, + { + "epoch": 0.27, + "learning_rate": 1.8292899249964887e-05, + "loss": 1.3239, + "step": 2573 + }, + { + "epoch": 0.27, + "learning_rate": 1.8290853278685284e-05, + "loss": 1.472, + "step": 2574 + }, + { + "epoch": 0.27, + "learning_rate": 1.8288806196644374e-05, + "loss": 1.536, + "step": 2575 + }, + { + "epoch": 0.27, + "learning_rate": 1.8286758004116405e-05, + "loss": 1.4644, + "step": 2576 + }, + { + "epoch": 0.27, + "learning_rate": 1.8284708701375783e-05, + "loss": 1.4537, + "step": 2577 + }, + { + "epoch": 0.27, + "learning_rate": 1.8282658288697067e-05, + "loss": 1.4359, + "step": 2578 + }, + { + "epoch": 0.27, + "learning_rate": 1.8280606766354955e-05, + "loss": 1.4842, + "step": 2579 + }, + { + "epoch": 0.27, + "learning_rate": 1.8278554134624302e-05, + "loss": 1.4664, + "step": 2580 + }, + { + "epoch": 0.27, + "learning_rate": 1.8276500393780105e-05, + "loss": 1.4632, + "step": 2581 + }, + { + "epoch": 0.27, + "learning_rate": 1.827444554409751e-05, + "loss": 1.4996, + "step": 2582 + }, + { + "epoch": 0.27, + "learning_rate": 1.827238958585182e-05, + "loss": 1.3399, + "step": 2583 + }, + { + "epoch": 0.27, + "learning_rate": 1.8270332519318476e-05, + "loss": 1.3928, + "step": 2584 + }, + { + "epoch": 0.27, + "learning_rate": 1.8268274344773074e-05, + "loss": 1.4993, + "step": 2585 + }, + { + "epoch": 0.27, + "learning_rate": 1.8266215062491356e-05, + "loss": 1.5398, + "step": 2586 + }, + { + "epoch": 0.27, + "learning_rate": 1.826415467274921e-05, + "loss": 1.4353, + "step": 2587 + }, + { + "epoch": 0.27, + "eval_loss": 1.5104212760925293, + "eval_runtime": 77.3448, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2587 + }, + { + "epoch": 0.27, + "learning_rate": 1.8262093175822685e-05, + "loss": 1.4889, + "step": 2588 + }, + { + "epoch": 0.27, + "learning_rate": 1.826003057198796e-05, + "loss": 1.4912, + "step": 2589 + }, + { + "epoch": 0.27, + "learning_rate": 1.825796686152137e-05, + "loss": 1.4884, + "step": 2590 + }, + { + "epoch": 0.27, + "learning_rate": 1.8255902044699404e-05, + "loss": 1.478, + "step": 2591 + }, + { + "epoch": 0.27, + "learning_rate": 1.8253836121798692e-05, + "loss": 1.6549, + "step": 2592 + }, + { + "epoch": 0.27, + "learning_rate": 1.8251769093096018e-05, + "loss": 1.5146, + "step": 2593 + }, + { + "epoch": 0.27, + "learning_rate": 1.8249700958868306e-05, + "loss": 1.4797, + "step": 2594 + }, + { + "epoch": 0.27, + "learning_rate": 1.8247631719392634e-05, + "loss": 1.4655, + "step": 2595 + }, + { + "epoch": 0.27, + "learning_rate": 1.824556137494623e-05, + "loss": 1.4517, + "step": 2596 + }, + { + "epoch": 0.27, + "learning_rate": 1.8243489925806458e-05, + "loss": 1.4936, + "step": 2597 + }, + { + "epoch": 0.27, + "learning_rate": 1.8241417372250852e-05, + "loss": 1.4614, + "step": 2598 + }, + { + "epoch": 0.27, + "learning_rate": 1.8239343714557073e-05, + "loss": 1.4475, + "step": 2599 + }, + { + "epoch": 0.27, + "learning_rate": 1.8237268953002937e-05, + "loss": 1.5435, + "step": 2600 + }, + { + "epoch": 0.27, + "learning_rate": 1.8235193087866413e-05, + "loss": 1.4616, + "step": 2601 + }, + { + "epoch": 0.27, + "learning_rate": 1.8233116119425612e-05, + "loss": 1.4578, + "step": 2602 + }, + { + "epoch": 0.27, + "learning_rate": 1.8231038047958795e-05, + "loss": 1.434, + "step": 2603 + }, + { + "epoch": 0.27, + "learning_rate": 1.8228958873744368e-05, + "loss": 1.5335, + "step": 2604 + }, + { + "epoch": 0.27, + "learning_rate": 1.8226878597060887e-05, + "loss": 1.415, + "step": 2605 + }, + { + "epoch": 0.27, + "learning_rate": 1.8224797218187058e-05, + "loss": 1.6165, + "step": 2606 + }, + { + "epoch": 0.27, + "learning_rate": 1.822271473740173e-05, + "loss": 1.372, + "step": 2607 + }, + { + "epoch": 0.27, + "learning_rate": 1.8220631154983907e-05, + "loss": 1.4855, + "step": 2608 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218546471212727e-05, + "loss": 1.4093, + "step": 2609 + }, + { + "epoch": 0.27, + "learning_rate": 1.821646068636749e-05, + "loss": 1.4852, + "step": 2610 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214373800727637e-05, + "loss": 1.6959, + "step": 2611 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212285814572755e-05, + "loss": 1.3874, + "step": 2612 + }, + { + "epoch": 0.27, + "learning_rate": 1.821019672818258e-05, + "loss": 1.4425, + "step": 2613 + }, + { + "epoch": 0.27, + "learning_rate": 1.8208106541837e-05, + "loss": 1.6097, + "step": 2614 + }, + { + "epoch": 0.27, + "learning_rate": 1.8206015255816045e-05, + "loss": 1.5675, + "step": 2615 + }, + { + "epoch": 0.27, + "learning_rate": 1.820392287039989e-05, + "loss": 1.4039, + "step": 2616 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201829385868866e-05, + "loss": 1.4872, + "step": 2617 + }, + { + "epoch": 0.27, + "learning_rate": 1.819973480250344e-05, + "loss": 1.4645, + "step": 2618 + }, + { + "epoch": 0.27, + "learning_rate": 1.8197639120584237e-05, + "loss": 1.4923, + "step": 2619 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195542340392025e-05, + "loss": 1.4294, + "step": 2620 + }, + { + "epoch": 0.27, + "learning_rate": 1.8193444462207717e-05, + "loss": 1.4315, + "step": 2621 + }, + { + "epoch": 0.27, + "learning_rate": 1.8191345486312372e-05, + "loss": 1.3972, + "step": 2622 + }, + { + "epoch": 0.28, + "learning_rate": 1.8189245412987205e-05, + "loss": 1.462, + "step": 2623 + }, + { + "epoch": 0.28, + "learning_rate": 1.8187144242513567e-05, + "loss": 1.4738, + "step": 2624 + }, + { + "epoch": 0.28, + "learning_rate": 1.818504197517296e-05, + "loss": 1.4935, + "step": 2625 + }, + { + "epoch": 0.28, + "learning_rate": 1.8182938611247038e-05, + "loss": 1.4231, + "step": 2626 + }, + { + "epoch": 0.28, + "learning_rate": 1.81808341510176e-05, + "loss": 1.4031, + "step": 2627 + }, + { + "epoch": 0.28, + "learning_rate": 1.817872859476658e-05, + "loss": 1.5822, + "step": 2628 + }, + { + "epoch": 0.28, + "learning_rate": 1.8176621942776075e-05, + "loss": 1.432, + "step": 2629 + }, + { + "epoch": 0.28, + "learning_rate": 1.8174514195328324e-05, + "loss": 1.5565, + "step": 2630 + }, + { + "epoch": 0.28, + "learning_rate": 1.8172405352705704e-05, + "loss": 1.4895, + "step": 2631 + }, + { + "epoch": 0.28, + "learning_rate": 1.8170295415190754e-05, + "loss": 1.4032, + "step": 2632 + }, + { + "epoch": 0.28, + "learning_rate": 1.8168184383066144e-05, + "loss": 1.4253, + "step": 2633 + }, + { + "epoch": 0.28, + "learning_rate": 1.8166072256614702e-05, + "loss": 1.5162, + "step": 2634 + }, + { + "epoch": 0.28, + "learning_rate": 1.81639590361194e-05, + "loss": 1.4609, + "step": 2635 + }, + { + "epoch": 0.28, + "learning_rate": 1.816184472186335e-05, + "loss": 1.4351, + "step": 2636 + }, + { + "epoch": 0.28, + "learning_rate": 1.8159729314129823e-05, + "loss": 1.4738, + "step": 2637 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157612813202224e-05, + "loss": 1.5986, + "step": 2638 + }, + { + "epoch": 0.28, + "learning_rate": 1.815549521936411e-05, + "loss": 1.4633, + "step": 2639 + }, + { + "epoch": 0.28, + "learning_rate": 1.8153376532899184e-05, + "loss": 1.4404, + "step": 2640 + }, + { + "epoch": 0.28, + "learning_rate": 1.81512567540913e-05, + "loss": 1.4256, + "step": 2641 + }, + { + "epoch": 0.28, + "learning_rate": 1.814913588322445e-05, + "loss": 1.4054, + "step": 2642 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147013920582773e-05, + "loss": 1.4134, + "step": 2643 + }, + { + "epoch": 0.28, + "learning_rate": 1.8144890866450567e-05, + "loss": 1.4098, + "step": 2644 + }, + { + "epoch": 0.28, + "learning_rate": 1.814276672111226e-05, + "loss": 1.4593, + "step": 2645 + }, + { + "epoch": 0.28, + "learning_rate": 1.814064148485243e-05, + "loss": 1.4679, + "step": 2646 + }, + { + "epoch": 0.28, + "learning_rate": 1.8138515157955812e-05, + "loss": 1.5234, + "step": 2647 + }, + { + "epoch": 0.28, + "learning_rate": 1.8136387740707272e-05, + "loss": 1.4568, + "step": 2648 + }, + { + "epoch": 0.28, + "learning_rate": 1.8134259233391836e-05, + "loss": 1.5057, + "step": 2649 + }, + { + "epoch": 0.28, + "learning_rate": 1.8132129636294665e-05, + "loss": 1.3643, + "step": 2650 + }, + { + "epoch": 0.28, + "learning_rate": 1.812999894970107e-05, + "loss": 1.4766, + "step": 2651 + }, + { + "epoch": 0.28, + "learning_rate": 1.812786717389651e-05, + "loss": 1.5701, + "step": 2652 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125734309166587e-05, + "loss": 1.5341, + "step": 2653 + }, + { + "epoch": 0.28, + "learning_rate": 1.812360035579705e-05, + "loss": 1.3596, + "step": 2654 + }, + { + "epoch": 0.28, + "learning_rate": 1.8121465314073793e-05, + "loss": 1.4847, + "step": 2655 + }, + { + "epoch": 0.28, + "learning_rate": 1.811932918428286e-05, + "loss": 1.4664, + "step": 2656 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117191966710438e-05, + "loss": 1.4673, + "step": 2657 + }, + { + "epoch": 0.28, + "learning_rate": 1.8115053661642856e-05, + "loss": 1.4712, + "step": 2658 + }, + { + "epoch": 0.28, + "learning_rate": 1.811291426936659e-05, + "loss": 1.4458, + "step": 2659 + }, + { + "epoch": 0.28, + "learning_rate": 1.811077379016827e-05, + "loss": 1.4667, + "step": 2660 + }, + { + "epoch": 0.28, + "learning_rate": 1.810863222433466e-05, + "loss": 1.4695, + "step": 2661 + }, + { + "epoch": 0.28, + "learning_rate": 1.8106489572152677e-05, + "loss": 1.5263, + "step": 2662 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104345833909376e-05, + "loss": 1.4148, + "step": 2663 + }, + { + "epoch": 0.28, + "learning_rate": 1.8102201009891976e-05, + "loss": 1.3955, + "step": 2664 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100055100387814e-05, + "loss": 1.6056, + "step": 2665 + }, + { + "epoch": 0.28, + "learning_rate": 1.8097908105684396e-05, + "loss": 1.5394, + "step": 2666 + }, + { + "epoch": 0.28, + "learning_rate": 1.809576002606936e-05, + "loss": 1.479, + "step": 2667 + }, + { + "epoch": 0.28, + "learning_rate": 1.8093610861830494e-05, + "loss": 1.4492, + "step": 2668 + }, + { + "epoch": 0.28, + "learning_rate": 1.8091460613255728e-05, + "loss": 1.4172, + "step": 2669 + }, + { + "epoch": 0.28, + "learning_rate": 1.808930928063315e-05, + "loss": 1.4498, + "step": 2670 + }, + { + "epoch": 0.28, + "learning_rate": 1.808715686425097e-05, + "loss": 1.6203, + "step": 2671 + }, + { + "epoch": 0.28, + "learning_rate": 1.8085003364397567e-05, + "loss": 1.435, + "step": 2672 + }, + { + "epoch": 0.28, + "learning_rate": 1.808284878136145e-05, + "loss": 1.4489, + "step": 2673 + }, + { + "epoch": 0.28, + "learning_rate": 1.8080693115431277e-05, + "loss": 1.4416, + "step": 2674 + }, + { + "epoch": 0.28, + "learning_rate": 1.8078536366895853e-05, + "loss": 1.422, + "step": 2675 + }, + { + "epoch": 0.28, + "learning_rate": 1.8076378536044128e-05, + "loss": 1.4039, + "step": 2676 + }, + { + "epoch": 0.28, + "learning_rate": 1.8074219623165195e-05, + "loss": 1.4705, + "step": 2677 + }, + { + "epoch": 0.28, + "learning_rate": 1.807205962854829e-05, + "loss": 1.5031, + "step": 2678 + }, + { + "epoch": 0.28, + "learning_rate": 1.8069898552482806e-05, + "loss": 1.4812, + "step": 2679 + }, + { + "epoch": 0.28, + "learning_rate": 1.806773639525826e-05, + "loss": 1.4129, + "step": 2680 + }, + { + "epoch": 0.28, + "learning_rate": 1.8065573157164332e-05, + "loss": 1.4559, + "step": 2681 + }, + { + "epoch": 0.28, + "learning_rate": 1.806340883849084e-05, + "loss": 1.3878, + "step": 2682 + }, + { + "epoch": 0.28, + "learning_rate": 1.8061243439527744e-05, + "loss": 1.4752, + "step": 2683 + }, + { + "epoch": 0.28, + "learning_rate": 1.8059076960565156e-05, + "loss": 1.4089, + "step": 2684 + }, + { + "epoch": 0.28, + "learning_rate": 1.8056909401893326e-05, + "loss": 1.4736, + "step": 2685 + }, + { + "epoch": 0.28, + "learning_rate": 1.8054740763802654e-05, + "loss": 1.3796, + "step": 2686 + }, + { + "epoch": 0.28, + "learning_rate": 1.805257104658368e-05, + "loss": 1.4412, + "step": 2687 + }, + { + "epoch": 0.28, + "learning_rate": 1.8050400250527086e-05, + "loss": 1.4639, + "step": 2688 + }, + { + "epoch": 0.28, + "learning_rate": 1.804822837592371e-05, + "loss": 1.4076, + "step": 2689 + }, + { + "epoch": 0.28, + "learning_rate": 1.804605542306452e-05, + "loss": 1.4627, + "step": 2690 + }, + { + "epoch": 0.28, + "learning_rate": 1.8043881392240642e-05, + "loss": 1.5249, + "step": 2691 + }, + { + "epoch": 0.28, + "learning_rate": 1.804170628374334e-05, + "loss": 1.4312, + "step": 2692 + }, + { + "epoch": 0.28, + "learning_rate": 1.803953009786402e-05, + "loss": 1.5676, + "step": 2693 + }, + { + "epoch": 0.28, + "learning_rate": 1.8037352834894233e-05, + "loss": 1.5072, + "step": 2694 + }, + { + "epoch": 0.28, + "learning_rate": 1.803517449512568e-05, + "loss": 1.5662, + "step": 2695 + }, + { + "epoch": 0.28, + "learning_rate": 1.8032995078850207e-05, + "loss": 1.4771, + "step": 2696 + }, + { + "epoch": 0.28, + "learning_rate": 1.803081458635979e-05, + "loss": 1.412, + "step": 2697 + }, + { + "epoch": 0.28, + "learning_rate": 1.8028633017946564e-05, + "loss": 1.497, + "step": 2698 + }, + { + "epoch": 0.28, + "learning_rate": 1.8026450373902804e-05, + "loss": 1.4528, + "step": 2699 + }, + { + "epoch": 0.28, + "learning_rate": 1.802426665452093e-05, + "loss": 1.4785, + "step": 2700 + }, + { + "epoch": 0.28, + "learning_rate": 1.8022081860093493e-05, + "loss": 1.6411, + "step": 2701 + }, + { + "epoch": 0.28, + "learning_rate": 1.8019895990913213e-05, + "loss": 1.4459, + "step": 2702 + }, + { + "epoch": 0.28, + "learning_rate": 1.8017709047272932e-05, + "loss": 1.4418, + "step": 2703 + }, + { + "epoch": 0.28, + "learning_rate": 1.801552102946565e-05, + "loss": 1.4409, + "step": 2704 + }, + { + "epoch": 0.28, + "learning_rate": 1.8013331937784498e-05, + "loss": 1.4651, + "step": 2705 + }, + { + "epoch": 0.28, + "learning_rate": 1.8011141772522766e-05, + "loss": 1.4161, + "step": 2706 + }, + { + "epoch": 0.28, + "learning_rate": 1.8008950533973876e-05, + "loss": 1.458, + "step": 2707 + }, + { + "epoch": 0.28, + "learning_rate": 1.8006758222431398e-05, + "loss": 1.4477, + "step": 2708 + }, + { + "epoch": 0.28, + "learning_rate": 1.800456483818904e-05, + "loss": 1.4433, + "step": 2709 + }, + { + "epoch": 0.28, + "learning_rate": 1.8002370381540672e-05, + "loss": 1.5005, + "step": 2710 + }, + { + "epoch": 0.28, + "learning_rate": 1.8000174852780282e-05, + "loss": 1.4945, + "step": 2711 + }, + { + "epoch": 0.28, + "learning_rate": 1.7997978252202023e-05, + "loss": 1.4298, + "step": 2712 + }, + { + "epoch": 0.28, + "learning_rate": 1.7995780580100177e-05, + "loss": 1.3812, + "step": 2713 + }, + { + "epoch": 0.28, + "learning_rate": 1.799358183676918e-05, + "loss": 1.5559, + "step": 2714 + }, + { + "epoch": 0.28, + "learning_rate": 1.79913820225036e-05, + "loss": 1.4316, + "step": 2715 + }, + { + "epoch": 0.28, + "learning_rate": 1.798918113759817e-05, + "loss": 1.419, + "step": 2716 + }, + { + "epoch": 0.28, + "learning_rate": 1.7986979182347733e-05, + "loss": 1.43, + "step": 2717 + }, + { + "epoch": 0.29, + "learning_rate": 1.798477615704731e-05, + "loss": 1.4964, + "step": 2718 + }, + { + "epoch": 0.29, + "learning_rate": 1.7982572061992044e-05, + "loss": 1.4417, + "step": 2719 + }, + { + "epoch": 0.29, + "learning_rate": 1.7980366897477227e-05, + "loss": 1.4562, + "step": 2720 + }, + { + "epoch": 0.29, + "learning_rate": 1.7978160663798295e-05, + "loss": 1.4386, + "step": 2721 + }, + { + "epoch": 0.29, + "learning_rate": 1.7975953361250824e-05, + "loss": 1.445, + "step": 2722 + }, + { + "epoch": 0.29, + "learning_rate": 1.797374499013054e-05, + "loss": 1.4549, + "step": 2723 + }, + { + "epoch": 0.29, + "learning_rate": 1.7971535550733305e-05, + "loss": 1.5205, + "step": 2724 + }, + { + "epoch": 0.29, + "learning_rate": 1.796932504335513e-05, + "loss": 1.4632, + "step": 2725 + }, + { + "epoch": 0.29, + "learning_rate": 1.796711346829216e-05, + "loss": 1.3767, + "step": 2726 + }, + { + "epoch": 0.29, + "learning_rate": 1.79649008258407e-05, + "loss": 1.4098, + "step": 2727 + }, + { + "epoch": 0.29, + "learning_rate": 1.7962687116297178e-05, + "loss": 1.4675, + "step": 2728 + }, + { + "epoch": 0.29, + "learning_rate": 1.7960472339958176e-05, + "loss": 1.6048, + "step": 2729 + }, + { + "epoch": 0.29, + "learning_rate": 1.7958256497120418e-05, + "loss": 1.5432, + "step": 2730 + }, + { + "epoch": 0.29, + "learning_rate": 1.7956039588080774e-05, + "loss": 1.5453, + "step": 2731 + }, + { + "epoch": 0.29, + "learning_rate": 1.7953821613136246e-05, + "loss": 1.4246, + "step": 2732 + }, + { + "epoch": 0.29, + "learning_rate": 1.7951602572583988e-05, + "loss": 1.3987, + "step": 2733 + }, + { + "epoch": 0.29, + "learning_rate": 1.7949382466721295e-05, + "loss": 1.4943, + "step": 2734 + }, + { + "epoch": 0.29, + "learning_rate": 1.7947161295845606e-05, + "loss": 1.4385, + "step": 2735 + }, + { + "epoch": 0.29, + "learning_rate": 1.7944939060254497e-05, + "loss": 1.4165, + "step": 2736 + }, + { + "epoch": 0.29, + "learning_rate": 1.7942715760245692e-05, + "loss": 1.4004, + "step": 2737 + }, + { + "epoch": 0.29, + "learning_rate": 1.7940491396117063e-05, + "loss": 1.4577, + "step": 2738 + }, + { + "epoch": 0.29, + "learning_rate": 1.7938265968166602e-05, + "loss": 1.4649, + "step": 2739 + }, + { + "epoch": 0.29, + "learning_rate": 1.7936039476692473e-05, + "loss": 1.5273, + "step": 2740 + }, + { + "epoch": 0.29, + "learning_rate": 1.7933811921992962e-05, + "loss": 1.4325, + "step": 2741 + }, + { + "epoch": 0.29, + "learning_rate": 1.793158330436651e-05, + "loss": 1.4388, + "step": 2742 + }, + { + "epoch": 0.29, + "learning_rate": 1.7929353624111687e-05, + "loss": 1.4124, + "step": 2743 + }, + { + "epoch": 0.29, + "learning_rate": 1.7927122881527222e-05, + "loss": 1.5449, + "step": 2744 + }, + { + "epoch": 0.29, + "learning_rate": 1.7924891076911964e-05, + "loss": 1.4728, + "step": 2745 + }, + { + "epoch": 0.29, + "learning_rate": 1.7922658210564932e-05, + "loss": 1.5103, + "step": 2746 + }, + { + "epoch": 0.29, + "learning_rate": 1.792042428278526e-05, + "loss": 1.5975, + "step": 2747 + }, + { + "epoch": 0.29, + "learning_rate": 1.7918189293872247e-05, + "loss": 1.567, + "step": 2748 + }, + { + "epoch": 0.29, + "learning_rate": 1.7915953244125318e-05, + "loss": 1.57, + "step": 2749 + }, + { + "epoch": 0.29, + "learning_rate": 1.791371613384405e-05, + "loss": 1.4372, + "step": 2750 + }, + { + "epoch": 0.29, + "learning_rate": 1.7911477963328155e-05, + "loss": 1.4053, + "step": 2751 + }, + { + "epoch": 0.29, + "learning_rate": 1.7909238732877492e-05, + "loss": 1.3782, + "step": 2752 + }, + { + "epoch": 0.29, + "learning_rate": 1.790699844279206e-05, + "loss": 1.4401, + "step": 2753 + }, + { + "epoch": 0.29, + "learning_rate": 1.7904757093372e-05, + "loss": 1.3749, + "step": 2754 + }, + { + "epoch": 0.29, + "learning_rate": 1.79025146849176e-05, + "loss": 1.4909, + "step": 2755 + }, + { + "epoch": 0.29, + "learning_rate": 1.7900271217729273e-05, + "loss": 1.4103, + "step": 2756 + }, + { + "epoch": 0.29, + "learning_rate": 1.7898026692107597e-05, + "loss": 1.4986, + "step": 2757 + }, + { + "epoch": 0.29, + "learning_rate": 1.7895781108353278e-05, + "loss": 1.5449, + "step": 2758 + }, + { + "epoch": 0.29, + "learning_rate": 1.789353446676717e-05, + "loss": 1.5583, + "step": 2759 + }, + { + "epoch": 0.29, + "learning_rate": 1.7891286767650254e-05, + "loss": 1.5342, + "step": 2760 + }, + { + "epoch": 0.29, + "learning_rate": 1.7889038011303673e-05, + "loss": 1.4233, + "step": 2761 + }, + { + "epoch": 0.29, + "learning_rate": 1.7886788198028707e-05, + "loss": 1.3433, + "step": 2762 + }, + { + "epoch": 0.29, + "learning_rate": 1.788453732812676e-05, + "loss": 1.4451, + "step": 2763 + }, + { + "epoch": 0.29, + "learning_rate": 1.78822854018994e-05, + "loss": 1.4506, + "step": 2764 + }, + { + "epoch": 0.29, + "learning_rate": 1.7880032419648324e-05, + "loss": 1.4386, + "step": 2765 + }, + { + "epoch": 0.29, + "learning_rate": 1.7877778381675374e-05, + "loss": 1.4512, + "step": 2766 + }, + { + "epoch": 0.29, + "learning_rate": 1.7875523288282535e-05, + "loss": 1.4319, + "step": 2767 + }, + { + "epoch": 0.29, + "learning_rate": 1.7873267139771932e-05, + "loss": 1.4753, + "step": 2768 + }, + { + "epoch": 0.29, + "learning_rate": 1.787100993644583e-05, + "loss": 1.4044, + "step": 2769 + }, + { + "epoch": 0.29, + "learning_rate": 1.786875167860663e-05, + "loss": 1.4382, + "step": 2770 + }, + { + "epoch": 0.29, + "learning_rate": 1.786649236655689e-05, + "loss": 1.3977, + "step": 2771 + }, + { + "epoch": 0.29, + "learning_rate": 1.7864232000599298e-05, + "loss": 1.4473, + "step": 2772 + }, + { + "epoch": 0.29, + "learning_rate": 1.7861970581036678e-05, + "loss": 1.4666, + "step": 2773 + }, + { + "epoch": 0.29, + "learning_rate": 1.785970810817201e-05, + "loss": 1.5299, + "step": 2774 + }, + { + "epoch": 0.29, + "learning_rate": 1.7857444582308402e-05, + "loss": 1.3974, + "step": 2775 + }, + { + "epoch": 0.29, + "learning_rate": 1.7855180003749114e-05, + "loss": 1.4603, + "step": 2776 + }, + { + "epoch": 0.29, + "learning_rate": 1.7852914372797535e-05, + "loss": 1.463, + "step": 2777 + }, + { + "epoch": 0.29, + "learning_rate": 1.7850647689757205e-05, + "loss": 1.5317, + "step": 2778 + }, + { + "epoch": 0.29, + "learning_rate": 1.78483799549318e-05, + "loss": 1.4669, + "step": 2779 + }, + { + "epoch": 0.29, + "learning_rate": 1.784611116862514e-05, + "loss": 1.5293, + "step": 2780 + }, + { + "epoch": 0.29, + "learning_rate": 1.7843841331141177e-05, + "loss": 1.5802, + "step": 2781 + }, + { + "epoch": 0.29, + "learning_rate": 1.7841570442784024e-05, + "loss": 1.4486, + "step": 2782 + }, + { + "epoch": 0.29, + "learning_rate": 1.7839298503857913e-05, + "loss": 1.4674, + "step": 2783 + }, + { + "epoch": 0.29, + "learning_rate": 1.7837025514667224e-05, + "loss": 1.4662, + "step": 2784 + }, + { + "epoch": 0.29, + "learning_rate": 1.7834751475516484e-05, + "loss": 1.3555, + "step": 2785 + }, + { + "epoch": 0.29, + "learning_rate": 1.783247638671035e-05, + "loss": 1.4307, + "step": 2786 + }, + { + "epoch": 0.29, + "eval_loss": 1.500258445739746, + "eval_runtime": 77.406, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 2786 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 1.2463562467808222e+20, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-2786/training_args.bin b/checkpoint-2786/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-2786/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-3184/config.json b/checkpoint-3184/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-3184/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-3184/generation_config.json b/checkpoint-3184/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-3184/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-3184/model-00001-of-00003.safetensors b/checkpoint-3184/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..73748a5168caaa23e354b1090e67360defb51a31 --- /dev/null +++ b/checkpoint-3184/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:885d4ecf51d5de070289a289c199368506f576a207621d4f0baf5e4e7c14baa7 +size 4943162336 diff --git a/checkpoint-3184/model-00002-of-00003.safetensors b/checkpoint-3184/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..29efd4fa4368077b0192d4e0cc9aeca67a8f6208 --- /dev/null +++ b/checkpoint-3184/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cf0522c3f7461676df2bed6952dca872fc0938ab5d326f4e24b5a32fa282f8c +size 4999819336 diff --git a/checkpoint-3184/model-00003-of-00003.safetensors b/checkpoint-3184/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c1e9329805e2feebea41a8ae3940904f2b3e6753 --- /dev/null +++ b/checkpoint-3184/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:120a0c4438bb1f6733d6e58041c57032f3d0ab890e35f8db125aeae315ed4598 +size 4540516344 diff --git a/checkpoint-3184/model.safetensors.index.json b/checkpoint-3184/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-3184/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-3184/optimizer.pt b/checkpoint-3184/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..db5afe8441c7dbbc3c599227647d5392b2e59867 --- /dev/null +++ b/checkpoint-3184/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd5bf5bb69654eae3d03f968df4d1f438d245164b48eb59181782a2e66fd7db7 +size 14512103560 diff --git a/checkpoint-3184/rng_state_0.pth b/checkpoint-3184/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..d3a6ea45dd4e59b9683f66476f460fa0c77a9d66 --- /dev/null +++ b/checkpoint-3184/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a0c9979566a5d89cb3c766336548670ec6f2291deba1b7ab1764c12d3187b24 +size 15984 diff --git a/checkpoint-3184/rng_state_1.pth b/checkpoint-3184/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..42e6b0d6985c9b3f0cec701759e0b3d671c77abd --- /dev/null +++ b/checkpoint-3184/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03e36a570d6158fc25d1cf5d9f8f450fc64c5a7683330277f89ff76d5f2fc6cd +size 15984 diff --git a/checkpoint-3184/rng_state_2.pth b/checkpoint-3184/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..376994a32199299a2a48b62753947cdb1f7ad72a --- /dev/null +++ b/checkpoint-3184/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4f619cbef4b74f1680d667c8788285a602392e63bdf3760ef3a59ec8864d483 +size 15984 diff --git a/checkpoint-3184/rng_state_3.pth b/checkpoint-3184/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..6f1edb2dfec55e5cbead7ae3d14351c3650c4f77 --- /dev/null +++ b/checkpoint-3184/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fc037fba93ace1bf7ce01b1a5f7d785698d47b4cc2cedf2300bbf7a41ebf05c +size 15984 diff --git a/checkpoint-3184/rng_state_4.pth b/checkpoint-3184/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..016d34db4ec6597c207021d026234c9692c3f3ad --- /dev/null +++ b/checkpoint-3184/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ab728c2461d6d1c64f04d7cbfdfcbfa7bd7ad0ef6e19d52458501ee81b27128 +size 15984 diff --git a/checkpoint-3184/rng_state_5.pth b/checkpoint-3184/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..5d7824c2bd9e8b1cec7f0d84d673017b0da62e43 --- /dev/null +++ b/checkpoint-3184/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27530e653ebf5997ae3159cdcde264607e6a6f86b7e3c7a1b3a1e8301cd43d03 +size 15984 diff --git a/checkpoint-3184/rng_state_6.pth b/checkpoint-3184/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f41ee261ad98d2d0eb8f09167a5b32604513b56 --- /dev/null +++ b/checkpoint-3184/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1fddaeb1257697bd7c0101abf1ab23f2925d0d9165cd8bddfbd22f8444db2b7 +size 15984 diff --git a/checkpoint-3184/rng_state_7.pth b/checkpoint-3184/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..d8816834cc1c0e822e11a8df138fa41557f3a0fb --- /dev/null +++ b/checkpoint-3184/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:942af3734a320fe12a3205a47ca1cdc7d1f0996bfde86c020a35545ccd2fd418 +size 15984 diff --git a/checkpoint-3184/scheduler.pt b/checkpoint-3184/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..93f562acb04c1ab81bc245498f80fd6cae8a5fd7 --- /dev/null +++ b/checkpoint-3184/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb63386b51d94283da25a619a974b34c989fbed019ecf969d10ab8c735fc43e8 +size 1064 diff --git a/checkpoint-3184/special_tokens_map.json b/checkpoint-3184/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-3184/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-3184/tokenizer.model b/checkpoint-3184/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-3184/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-3184/tokenizer_config.json b/checkpoint-3184/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-3184/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-3184/trainer_state.json b/checkpoint-3184/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..8cc49260ea0544627ab9269b983338c0c48747ef --- /dev/null +++ b/checkpoint-3184/trainer_state.json @@ -0,0 +1,19252 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.3338926174496644, + "eval_steps": 199, + "global_step": 3184, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + }, + { + "epoch": 0.21, + "learning_rate": 1.928689129323009e-05, + "loss": 1.421, + "step": 1991 + }, + { + "epoch": 0.21, + "learning_rate": 1.928553323396003e-05, + "loss": 1.5625, + "step": 1992 + }, + { + "epoch": 0.21, + "learning_rate": 1.92841739306671e-05, + "loss": 1.5198, + "step": 1993 + }, + { + "epoch": 0.21, + "learning_rate": 1.9282813383533415e-05, + "loss": 1.5116, + "step": 1994 + }, + { + "epoch": 0.21, + "learning_rate": 1.9281451592741247e-05, + "loss": 1.4306, + "step": 1995 + }, + { + "epoch": 0.21, + "learning_rate": 1.9280088558473046e-05, + "loss": 1.5425, + "step": 1996 + }, + { + "epoch": 0.21, + "learning_rate": 1.9278724280911424e-05, + "loss": 1.4972, + "step": 1997 + }, + { + "epoch": 0.21, + "learning_rate": 1.9277358760239156e-05, + "loss": 1.5185, + "step": 1998 + }, + { + "epoch": 0.21, + "learning_rate": 1.9275991996639188e-05, + "loss": 1.5187, + "step": 1999 + }, + { + "epoch": 0.21, + "learning_rate": 1.927462399029463e-05, + "loss": 1.4325, + "step": 2000 + }, + { + "epoch": 0.21, + "learning_rate": 1.9273254741388763e-05, + "loss": 1.4397, + "step": 2001 + }, + { + "epoch": 0.21, + "learning_rate": 1.927188425010503e-05, + "loss": 1.5319, + "step": 2002 + }, + { + "epoch": 0.21, + "learning_rate": 1.9270512516627042e-05, + "loss": 1.5664, + "step": 2003 + }, + { + "epoch": 0.21, + "learning_rate": 1.9269139541138574e-05, + "loss": 1.5227, + "step": 2004 + }, + { + "epoch": 0.21, + "learning_rate": 1.926776532382357e-05, + "loss": 1.5187, + "step": 2005 + }, + { + "epoch": 0.21, + "learning_rate": 1.9266389864866134e-05, + "loss": 1.4029, + "step": 2006 + }, + { + "epoch": 0.21, + "learning_rate": 1.9265013164450557e-05, + "loss": 1.387, + "step": 2007 + }, + { + "epoch": 0.21, + "learning_rate": 1.9263635222761268e-05, + "loss": 1.5047, + "step": 2008 + }, + { + "epoch": 0.21, + "learning_rate": 1.9262256039982882e-05, + "loss": 1.4816, + "step": 2009 + }, + { + "epoch": 0.21, + "learning_rate": 1.9260875616300172e-05, + "loss": 1.4607, + "step": 2010 + }, + { + "epoch": 0.21, + "learning_rate": 1.9259493951898084e-05, + "loss": 1.628, + "step": 2011 + }, + { + "epoch": 0.21, + "learning_rate": 1.9258111046961714e-05, + "loss": 1.4149, + "step": 2012 + }, + { + "epoch": 0.21, + "learning_rate": 1.925672690167635e-05, + "loss": 1.5303, + "step": 2013 + }, + { + "epoch": 0.21, + "learning_rate": 1.925534151622742e-05, + "loss": 1.5198, + "step": 2014 + }, + { + "epoch": 0.21, + "learning_rate": 1.9253954890800535e-05, + "loss": 1.6422, + "step": 2015 + }, + { + "epoch": 0.21, + "learning_rate": 1.925256702558147e-05, + "loss": 1.4738, + "step": 2016 + }, + { + "epoch": 0.21, + "learning_rate": 1.925117792075616e-05, + "loss": 1.4752, + "step": 2017 + }, + { + "epoch": 0.21, + "learning_rate": 1.9249787576510713e-05, + "loss": 1.4547, + "step": 2018 + }, + { + "epoch": 0.21, + "learning_rate": 1.924839599303139e-05, + "loss": 1.4864, + "step": 2019 + }, + { + "epoch": 0.21, + "learning_rate": 1.9247003170504638e-05, + "loss": 1.5037, + "step": 2020 + }, + { + "epoch": 0.21, + "learning_rate": 1.9245609109117053e-05, + "loss": 1.5089, + "step": 2021 + }, + { + "epoch": 0.21, + "learning_rate": 1.924421380905541e-05, + "loss": 1.5616, + "step": 2022 + }, + { + "epoch": 0.21, + "learning_rate": 1.9242817270506634e-05, + "loss": 1.4592, + "step": 2023 + }, + { + "epoch": 0.21, + "learning_rate": 1.9241419493657832e-05, + "loss": 1.5592, + "step": 2024 + }, + { + "epoch": 0.21, + "learning_rate": 1.924002047869627e-05, + "loss": 1.4897, + "step": 2025 + }, + { + "epoch": 0.21, + "learning_rate": 1.9238620225809375e-05, + "loss": 1.4743, + "step": 2026 + }, + { + "epoch": 0.21, + "learning_rate": 1.923721873518475e-05, + "loss": 1.4686, + "step": 2027 + }, + { + "epoch": 0.21, + "learning_rate": 1.923581600701016e-05, + "loss": 1.461, + "step": 2028 + }, + { + "epoch": 0.21, + "learning_rate": 1.9234412041473528e-05, + "loss": 1.6622, + "step": 2029 + }, + { + "epoch": 0.21, + "learning_rate": 1.9233006838762955e-05, + "loss": 1.4707, + "step": 2030 + }, + { + "epoch": 0.21, + "learning_rate": 1.92316003990667e-05, + "loss": 1.5566, + "step": 2031 + }, + { + "epoch": 0.21, + "learning_rate": 1.9230192722573188e-05, + "loss": 1.4881, + "step": 2032 + }, + { + "epoch": 0.21, + "learning_rate": 1.9228783809471015e-05, + "loss": 1.6124, + "step": 2033 + }, + { + "epoch": 0.21, + "learning_rate": 1.9227373659948937e-05, + "loss": 1.3508, + "step": 2034 + }, + { + "epoch": 0.21, + "learning_rate": 1.9225962274195876e-05, + "loss": 1.4418, + "step": 2035 + }, + { + "epoch": 0.21, + "learning_rate": 1.9224549652400927e-05, + "loss": 1.3954, + "step": 2036 + }, + { + "epoch": 0.21, + "learning_rate": 1.922313579475334e-05, + "loss": 1.4798, + "step": 2037 + }, + { + "epoch": 0.21, + "learning_rate": 1.922172070144254e-05, + "loss": 1.4556, + "step": 2038 + }, + { + "epoch": 0.21, + "learning_rate": 1.922030437265811e-05, + "loss": 1.4987, + "step": 2039 + }, + { + "epoch": 0.21, + "learning_rate": 1.9218886808589796e-05, + "loss": 1.4857, + "step": 2040 + }, + { + "epoch": 0.21, + "learning_rate": 1.9217468009427527e-05, + "loss": 1.5289, + "step": 2041 + }, + { + "epoch": 0.21, + "learning_rate": 1.921604797536138e-05, + "loss": 1.5267, + "step": 2042 + }, + { + "epoch": 0.21, + "learning_rate": 1.9214626706581598e-05, + "loss": 1.4655, + "step": 2043 + }, + { + "epoch": 0.21, + "learning_rate": 1.9213204203278602e-05, + "loss": 1.4598, + "step": 2044 + }, + { + "epoch": 0.21, + "learning_rate": 1.9211780465642973e-05, + "loss": 1.4766, + "step": 2045 + }, + { + "epoch": 0.21, + "learning_rate": 1.921035549386545e-05, + "loss": 1.5148, + "step": 2046 + }, + { + "epoch": 0.21, + "learning_rate": 1.9208929288136933e-05, + "loss": 1.5567, + "step": 2047 + }, + { + "epoch": 0.21, + "learning_rate": 1.920750184864852e-05, + "loss": 1.4868, + "step": 2048 + }, + { + "epoch": 0.21, + "learning_rate": 1.920607317559143e-05, + "loss": 1.4752, + "step": 2049 + }, + { + "epoch": 0.21, + "learning_rate": 1.920464326915708e-05, + "loss": 1.4882, + "step": 2050 + }, + { + "epoch": 0.22, + "learning_rate": 1.9203212129537035e-05, + "loss": 1.5933, + "step": 2051 + }, + { + "epoch": 0.22, + "learning_rate": 1.9201779756923037e-05, + "loss": 1.4891, + "step": 2052 + }, + { + "epoch": 0.22, + "learning_rate": 1.9200346151506983e-05, + "loss": 1.4486, + "step": 2053 + }, + { + "epoch": 0.22, + "learning_rate": 1.9198911313480938e-05, + "loss": 1.5091, + "step": 2054 + }, + { + "epoch": 0.22, + "learning_rate": 1.919747524303714e-05, + "loss": 1.4385, + "step": 2055 + }, + { + "epoch": 0.22, + "learning_rate": 1.9196037940367974e-05, + "loss": 1.4104, + "step": 2056 + }, + { + "epoch": 0.22, + "learning_rate": 1.9194599405666015e-05, + "loss": 1.4483, + "step": 2057 + }, + { + "epoch": 0.22, + "learning_rate": 1.9193159639123976e-05, + "loss": 1.4592, + "step": 2058 + }, + { + "epoch": 0.22, + "learning_rate": 1.919171864093476e-05, + "loss": 1.4975, + "step": 2059 + }, + { + "epoch": 0.22, + "learning_rate": 1.9190276411291423e-05, + "loss": 1.4727, + "step": 2060 + }, + { + "epoch": 0.22, + "learning_rate": 1.9188832950387178e-05, + "loss": 1.4791, + "step": 2061 + }, + { + "epoch": 0.22, + "learning_rate": 1.9187388258415423e-05, + "loss": 1.3806, + "step": 2062 + }, + { + "epoch": 0.22, + "learning_rate": 1.9185942335569697e-05, + "loss": 1.4514, + "step": 2063 + }, + { + "epoch": 0.22, + "learning_rate": 1.9184495182043727e-05, + "loss": 1.4389, + "step": 2064 + }, + { + "epoch": 0.22, + "learning_rate": 1.918304679803139e-05, + "loss": 1.5088, + "step": 2065 + }, + { + "epoch": 0.22, + "learning_rate": 1.9181597183726733e-05, + "loss": 1.4665, + "step": 2066 + }, + { + "epoch": 0.22, + "learning_rate": 1.9180146339323966e-05, + "loss": 1.489, + "step": 2067 + }, + { + "epoch": 0.22, + "learning_rate": 1.9178694265017466e-05, + "loss": 1.5215, + "step": 2068 + }, + { + "epoch": 0.22, + "learning_rate": 1.9177240961001775e-05, + "loss": 1.5152, + "step": 2069 + }, + { + "epoch": 0.22, + "learning_rate": 1.9175786427471594e-05, + "loss": 1.4418, + "step": 2070 + }, + { + "epoch": 0.22, + "learning_rate": 1.91743306646218e-05, + "loss": 1.5001, + "step": 2071 + }, + { + "epoch": 0.22, + "learning_rate": 1.9172873672647417e-05, + "loss": 1.4879, + "step": 2072 + }, + { + "epoch": 0.22, + "learning_rate": 1.917141545174366e-05, + "loss": 1.5299, + "step": 2073 + }, + { + "epoch": 0.22, + "learning_rate": 1.9169956002105877e-05, + "loss": 1.4602, + "step": 2074 + }, + { + "epoch": 0.22, + "learning_rate": 1.9168495323929605e-05, + "loss": 1.4921, + "step": 2075 + }, + { + "epoch": 0.22, + "learning_rate": 1.916703341741054e-05, + "loss": 1.4659, + "step": 2076 + }, + { + "epoch": 0.22, + "learning_rate": 1.9165570282744534e-05, + "loss": 1.4707, + "step": 2077 + }, + { + "epoch": 0.22, + "learning_rate": 1.9164105920127613e-05, + "loss": 1.5354, + "step": 2078 + }, + { + "epoch": 0.22, + "learning_rate": 1.9162640329755962e-05, + "loss": 1.526, + "step": 2079 + }, + { + "epoch": 0.22, + "learning_rate": 1.916117351182593e-05, + "loss": 1.6424, + "step": 2080 + }, + { + "epoch": 0.22, + "learning_rate": 1.915970546653404e-05, + "loss": 1.5048, + "step": 2081 + }, + { + "epoch": 0.22, + "learning_rate": 1.915823619407697e-05, + "loss": 1.5344, + "step": 2082 + }, + { + "epoch": 0.22, + "learning_rate": 1.915676569465156e-05, + "loss": 1.4604, + "step": 2083 + }, + { + "epoch": 0.22, + "learning_rate": 1.9155293968454826e-05, + "loss": 1.4929, + "step": 2084 + }, + { + "epoch": 0.22, + "learning_rate": 1.9153821015683937e-05, + "loss": 1.4106, + "step": 2085 + }, + { + "epoch": 0.22, + "learning_rate": 1.915234683653623e-05, + "loss": 1.4146, + "step": 2086 + }, + { + "epoch": 0.22, + "learning_rate": 1.9150871431209207e-05, + "loss": 1.4481, + "step": 2087 + }, + { + "epoch": 0.22, + "learning_rate": 1.914939479990054e-05, + "loss": 1.5206, + "step": 2088 + }, + { + "epoch": 0.22, + "learning_rate": 1.9147916942808054e-05, + "loss": 1.5073, + "step": 2089 + }, + { + "epoch": 0.22, + "learning_rate": 1.9146437860129745e-05, + "loss": 1.5196, + "step": 2090 + }, + { + "epoch": 0.22, + "learning_rate": 1.9144957552063775e-05, + "loss": 1.5389, + "step": 2091 + }, + { + "epoch": 0.22, + "learning_rate": 1.9143476018808463e-05, + "loss": 1.5207, + "step": 2092 + }, + { + "epoch": 0.22, + "learning_rate": 1.9141993260562298e-05, + "loss": 1.3717, + "step": 2093 + }, + { + "epoch": 0.22, + "learning_rate": 1.9140509277523937e-05, + "loss": 1.471, + "step": 2094 + }, + { + "epoch": 0.22, + "learning_rate": 1.9139024069892185e-05, + "loss": 1.4553, + "step": 2095 + }, + { + "epoch": 0.22, + "learning_rate": 1.9137537637866027e-05, + "loss": 1.5311, + "step": 2096 + }, + { + "epoch": 0.22, + "learning_rate": 1.9136049981644614e-05, + "loss": 1.4369, + "step": 2097 + }, + { + "epoch": 0.22, + "learning_rate": 1.913456110142724e-05, + "loss": 1.4528, + "step": 2098 + }, + { + "epoch": 0.22, + "learning_rate": 1.9133070997413384e-05, + "loss": 1.5294, + "step": 2099 + }, + { + "epoch": 0.22, + "learning_rate": 1.9131579669802685e-05, + "loss": 1.4588, + "step": 2100 + }, + { + "epoch": 0.22, + "learning_rate": 1.9130087118794934e-05, + "loss": 1.443, + "step": 2101 + }, + { + "epoch": 0.22, + "learning_rate": 1.9128593344590102e-05, + "loss": 1.4876, + "step": 2102 + }, + { + "epoch": 0.22, + "learning_rate": 1.912709834738831e-05, + "loss": 1.4874, + "step": 2103 + }, + { + "epoch": 0.22, + "learning_rate": 1.9125602127389856e-05, + "loss": 1.4966, + "step": 2104 + }, + { + "epoch": 0.22, + "learning_rate": 1.912410468479519e-05, + "loss": 1.5747, + "step": 2105 + }, + { + "epoch": 0.22, + "learning_rate": 1.9122606019804933e-05, + "loss": 1.4025, + "step": 2106 + }, + { + "epoch": 0.22, + "learning_rate": 1.912110613261987e-05, + "loss": 1.4755, + "step": 2107 + }, + { + "epoch": 0.22, + "learning_rate": 1.911960502344094e-05, + "loss": 1.4739, + "step": 2108 + }, + { + "epoch": 0.22, + "learning_rate": 1.911810269246926e-05, + "loss": 1.4992, + "step": 2109 + }, + { + "epoch": 0.22, + "learning_rate": 1.91165991399061e-05, + "loss": 1.4435, + "step": 2110 + }, + { + "epoch": 0.22, + "learning_rate": 1.91150943659529e-05, + "loss": 1.4918, + "step": 2111 + }, + { + "epoch": 0.22, + "learning_rate": 1.9113588370811258e-05, + "loss": 1.3818, + "step": 2112 + }, + { + "epoch": 0.22, + "learning_rate": 1.911208115468294e-05, + "loss": 1.5105, + "step": 2113 + }, + { + "epoch": 0.22, + "learning_rate": 1.9110572717769878e-05, + "loss": 1.6634, + "step": 2114 + }, + { + "epoch": 0.22, + "learning_rate": 1.9109063060274158e-05, + "loss": 1.5028, + "step": 2115 + }, + { + "epoch": 0.22, + "learning_rate": 1.9107552182398037e-05, + "loss": 1.6657, + "step": 2116 + }, + { + "epoch": 0.22, + "learning_rate": 1.9106040084343935e-05, + "loss": 1.5481, + "step": 2117 + }, + { + "epoch": 0.22, + "learning_rate": 1.910452676631444e-05, + "loss": 1.4505, + "step": 2118 + }, + { + "epoch": 0.22, + "learning_rate": 1.9103012228512284e-05, + "loss": 1.5173, + "step": 2119 + }, + { + "epoch": 0.22, + "learning_rate": 1.9101496471140385e-05, + "loss": 1.3788, + "step": 2120 + }, + { + "epoch": 0.22, + "learning_rate": 1.9099979494401814e-05, + "loss": 1.4649, + "step": 2121 + }, + { + "epoch": 0.22, + "learning_rate": 1.9098461298499805e-05, + "loss": 1.4204, + "step": 2122 + }, + { + "epoch": 0.22, + "learning_rate": 1.9096941883637766e-05, + "loss": 1.4439, + "step": 2123 + }, + { + "epoch": 0.22, + "learning_rate": 1.909542125001925e-05, + "loss": 1.6615, + "step": 2124 + }, + { + "epoch": 0.22, + "learning_rate": 1.9093899397847985e-05, + "loss": 1.4763, + "step": 2125 + }, + { + "epoch": 0.22, + "learning_rate": 1.909237632732786e-05, + "loss": 1.5353, + "step": 2126 + }, + { + "epoch": 0.22, + "learning_rate": 1.909085203866293e-05, + "loss": 1.442, + "step": 2127 + }, + { + "epoch": 0.22, + "learning_rate": 1.9089326532057408e-05, + "loss": 1.4782, + "step": 2128 + }, + { + "epoch": 0.22, + "learning_rate": 1.908779980771567e-05, + "loss": 1.4933, + "step": 2129 + }, + { + "epoch": 0.22, + "learning_rate": 1.9086271865842264e-05, + "loss": 1.5285, + "step": 2130 + }, + { + "epoch": 0.22, + "learning_rate": 1.9084742706641894e-05, + "loss": 1.4736, + "step": 2131 + }, + { + "epoch": 0.22, + "learning_rate": 1.9083212330319427e-05, + "loss": 1.4496, + "step": 2132 + }, + { + "epoch": 0.22, + "learning_rate": 1.908168073707989e-05, + "loss": 1.5099, + "step": 2133 + }, + { + "epoch": 0.22, + "learning_rate": 1.9080147927128483e-05, + "loss": 1.5235, + "step": 2134 + }, + { + "epoch": 0.22, + "learning_rate": 1.9078613900670556e-05, + "loss": 1.4769, + "step": 2135 + }, + { + "epoch": 0.22, + "learning_rate": 1.907707865791164e-05, + "loss": 1.5771, + "step": 2136 + }, + { + "epoch": 0.22, + "learning_rate": 1.907554219905741e-05, + "loss": 1.5116, + "step": 2137 + }, + { + "epoch": 0.22, + "learning_rate": 1.907400452431371e-05, + "loss": 1.5161, + "step": 2138 + }, + { + "epoch": 0.22, + "learning_rate": 1.9072465633886557e-05, + "loss": 1.4356, + "step": 2139 + }, + { + "epoch": 0.22, + "learning_rate": 1.9070925527982117e-05, + "loss": 1.509, + "step": 2140 + }, + { + "epoch": 0.22, + "learning_rate": 1.9069384206806723e-05, + "loss": 1.4681, + "step": 2141 + }, + { + "epoch": 0.22, + "learning_rate": 1.9067841670566883e-05, + "loss": 1.5254, + "step": 2142 + }, + { + "epoch": 0.22, + "learning_rate": 1.9066297919469242e-05, + "loss": 1.4797, + "step": 2143 + }, + { + "epoch": 0.22, + "learning_rate": 1.9064752953720636e-05, + "loss": 1.3996, + "step": 2144 + }, + { + "epoch": 0.22, + "learning_rate": 1.9063206773528042e-05, + "loss": 1.4457, + "step": 2145 + }, + { + "epoch": 0.23, + "learning_rate": 1.9061659379098617e-05, + "loss": 1.5126, + "step": 2146 + }, + { + "epoch": 0.23, + "learning_rate": 1.9060110770639664e-05, + "loss": 1.5925, + "step": 2147 + }, + { + "epoch": 0.23, + "learning_rate": 1.905856094835866e-05, + "loss": 1.5146, + "step": 2148 + }, + { + "epoch": 0.23, + "learning_rate": 1.905700991246324e-05, + "loss": 1.7256, + "step": 2149 + }, + { + "epoch": 0.23, + "learning_rate": 1.90554576631612e-05, + "loss": 1.57, + "step": 2150 + }, + { + "epoch": 0.23, + "learning_rate": 1.905390420066051e-05, + "loss": 1.3722, + "step": 2151 + }, + { + "epoch": 0.23, + "learning_rate": 1.9052349525169292e-05, + "loss": 1.3999, + "step": 2152 + }, + { + "epoch": 0.23, + "learning_rate": 1.9050793636895828e-05, + "loss": 1.586, + "step": 2153 + }, + { + "epoch": 0.23, + "learning_rate": 1.9049236536048567e-05, + "loss": 1.4884, + "step": 2154 + }, + { + "epoch": 0.23, + "learning_rate": 1.9047678222836127e-05, + "loss": 1.5898, + "step": 2155 + }, + { + "epoch": 0.23, + "learning_rate": 1.9046118697467278e-05, + "loss": 1.569, + "step": 2156 + }, + { + "epoch": 0.23, + "learning_rate": 1.904455796015095e-05, + "loss": 1.5592, + "step": 2157 + }, + { + "epoch": 0.23, + "learning_rate": 1.9042996011096253e-05, + "loss": 1.597, + "step": 2158 + }, + { + "epoch": 0.23, + "learning_rate": 1.904143285051244e-05, + "loss": 1.422, + "step": 2159 + }, + { + "epoch": 0.23, + "learning_rate": 1.903986847860894e-05, + "loss": 1.519, + "step": 2160 + }, + { + "epoch": 0.23, + "learning_rate": 1.9038302895595334e-05, + "loss": 1.5197, + "step": 2161 + }, + { + "epoch": 0.23, + "learning_rate": 1.903673610168137e-05, + "loss": 1.4655, + "step": 2162 + }, + { + "epoch": 0.23, + "learning_rate": 1.9035168097076965e-05, + "loss": 1.3909, + "step": 2163 + }, + { + "epoch": 0.23, + "learning_rate": 1.903359888199218e-05, + "loss": 1.4877, + "step": 2164 + }, + { + "epoch": 0.23, + "learning_rate": 1.903202845663726e-05, + "loss": 1.5123, + "step": 2165 + }, + { + "epoch": 0.23, + "learning_rate": 1.9030456821222593e-05, + "loss": 1.4906, + "step": 2166 + }, + { + "epoch": 0.23, + "learning_rate": 1.9028883975958745e-05, + "loss": 1.4574, + "step": 2167 + }, + { + "epoch": 0.23, + "learning_rate": 1.9027309921056435e-05, + "loss": 1.4571, + "step": 2168 + }, + { + "epoch": 0.23, + "learning_rate": 1.902573465672654e-05, + "loss": 1.4281, + "step": 2169 + }, + { + "epoch": 0.23, + "learning_rate": 1.9024158183180116e-05, + "loss": 1.5057, + "step": 2170 + }, + { + "epoch": 0.23, + "learning_rate": 1.902258050062836e-05, + "loss": 1.4514, + "step": 2171 + }, + { + "epoch": 0.23, + "learning_rate": 1.9021001609282646e-05, + "loss": 1.5055, + "step": 2172 + }, + { + "epoch": 0.23, + "learning_rate": 1.9019421509354505e-05, + "loss": 1.4578, + "step": 2173 + }, + { + "epoch": 0.23, + "learning_rate": 1.9017840201055625e-05, + "loss": 1.459, + "step": 2174 + }, + { + "epoch": 0.23, + "learning_rate": 1.9016257684597864e-05, + "loss": 1.5059, + "step": 2175 + }, + { + "epoch": 0.23, + "learning_rate": 1.901467396019324e-05, + "loss": 1.57, + "step": 2176 + }, + { + "epoch": 0.23, + "learning_rate": 1.901308902805393e-05, + "loss": 1.4924, + "step": 2177 + }, + { + "epoch": 0.23, + "learning_rate": 1.9011502888392273e-05, + "loss": 1.4979, + "step": 2178 + }, + { + "epoch": 0.23, + "learning_rate": 1.900991554142077e-05, + "loss": 1.5321, + "step": 2179 + }, + { + "epoch": 0.23, + "learning_rate": 1.9008326987352093e-05, + "loss": 1.493, + "step": 2180 + }, + { + "epoch": 0.23, + "learning_rate": 1.9006737226399056e-05, + "loss": 1.5111, + "step": 2181 + }, + { + "epoch": 0.23, + "learning_rate": 1.900514625877465e-05, + "loss": 1.4154, + "step": 2182 + }, + { + "epoch": 0.23, + "learning_rate": 1.900355408469203e-05, + "loss": 1.4934, + "step": 2183 + }, + { + "epoch": 0.23, + "learning_rate": 1.90019607043645e-05, + "loss": 1.5975, + "step": 2184 + }, + { + "epoch": 0.23, + "learning_rate": 1.9000366118005532e-05, + "loss": 1.3537, + "step": 2185 + }, + { + "epoch": 0.23, + "learning_rate": 1.899877032582876e-05, + "loss": 1.4583, + "step": 2186 + }, + { + "epoch": 0.23, + "learning_rate": 1.8997173328047984e-05, + "loss": 1.4586, + "step": 2187 + }, + { + "epoch": 0.23, + "learning_rate": 1.8995575124877156e-05, + "loss": 1.4774, + "step": 2188 + }, + { + "epoch": 0.23, + "learning_rate": 1.8993975716530394e-05, + "loss": 1.5025, + "step": 2189 + }, + { + "epoch": 0.23, + "eval_loss": 1.5263344049453735, + "eval_runtime": 77.1492, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 2189 + }, + { + "epoch": 0.23, + "learning_rate": 1.899237510322198e-05, + "loss": 1.5438, + "step": 2190 + }, + { + "epoch": 0.23, + "learning_rate": 1.899077328516635e-05, + "loss": 1.5181, + "step": 2191 + }, + { + "epoch": 0.23, + "learning_rate": 1.8989170262578112e-05, + "loss": 1.4454, + "step": 2192 + }, + { + "epoch": 0.23, + "learning_rate": 1.8987566035672028e-05, + "loss": 1.4882, + "step": 2193 + }, + { + "epoch": 0.23, + "learning_rate": 1.8985960604663026e-05, + "loss": 1.5073, + "step": 2194 + }, + { + "epoch": 0.23, + "learning_rate": 1.8984353969766187e-05, + "loss": 1.4478, + "step": 2195 + }, + { + "epoch": 0.23, + "learning_rate": 1.8982746131196763e-05, + "loss": 1.4768, + "step": 2196 + }, + { + "epoch": 0.23, + "learning_rate": 1.8981137089170162e-05, + "loss": 1.5116, + "step": 2197 + }, + { + "epoch": 0.23, + "learning_rate": 1.8979526843901952e-05, + "loss": 1.4202, + "step": 2198 + }, + { + "epoch": 0.23, + "learning_rate": 1.8977915395607867e-05, + "loss": 1.4736, + "step": 2199 + }, + { + "epoch": 0.23, + "learning_rate": 1.89763027445038e-05, + "loss": 1.4489, + "step": 2200 + }, + { + "epoch": 0.23, + "learning_rate": 1.8974688890805804e-05, + "loss": 1.4512, + "step": 2201 + }, + { + "epoch": 0.23, + "learning_rate": 1.897307383473009e-05, + "loss": 1.5091, + "step": 2202 + }, + { + "epoch": 0.23, + "learning_rate": 1.897145757649304e-05, + "loss": 1.5512, + "step": 2203 + }, + { + "epoch": 0.23, + "learning_rate": 1.8969840116311192e-05, + "loss": 1.406, + "step": 2204 + }, + { + "epoch": 0.23, + "learning_rate": 1.896822145440124e-05, + "loss": 1.4531, + "step": 2205 + }, + { + "epoch": 0.23, + "learning_rate": 1.896660159098004e-05, + "loss": 1.4379, + "step": 2206 + }, + { + "epoch": 0.23, + "learning_rate": 1.896498052626462e-05, + "loss": 1.4783, + "step": 2207 + }, + { + "epoch": 0.23, + "learning_rate": 1.896335826047216e-05, + "loss": 1.4801, + "step": 2208 + }, + { + "epoch": 0.23, + "learning_rate": 1.896173479381999e-05, + "loss": 1.4526, + "step": 2209 + }, + { + "epoch": 0.23, + "learning_rate": 1.8960110126525627e-05, + "loss": 1.4952, + "step": 2210 + }, + { + "epoch": 0.23, + "learning_rate": 1.895848425880673e-05, + "loss": 1.5299, + "step": 2211 + }, + { + "epoch": 0.23, + "learning_rate": 1.8956857190881125e-05, + "loss": 1.5274, + "step": 2212 + }, + { + "epoch": 0.23, + "learning_rate": 1.8955228922966792e-05, + "loss": 1.4415, + "step": 2213 + }, + { + "epoch": 0.23, + "learning_rate": 1.8953599455281884e-05, + "loss": 1.5311, + "step": 2214 + }, + { + "epoch": 0.23, + "learning_rate": 1.8951968788044702e-05, + "loss": 1.4972, + "step": 2215 + }, + { + "epoch": 0.23, + "learning_rate": 1.8950336921473715e-05, + "loss": 1.4966, + "step": 2216 + }, + { + "epoch": 0.23, + "learning_rate": 1.8948703855787553e-05, + "loss": 1.4683, + "step": 2217 + }, + { + "epoch": 0.23, + "learning_rate": 1.8947069591205005e-05, + "loss": 1.503, + "step": 2218 + }, + { + "epoch": 0.23, + "learning_rate": 1.8945434127945014e-05, + "loss": 1.4902, + "step": 2219 + }, + { + "epoch": 0.23, + "learning_rate": 1.8943797466226702e-05, + "loss": 1.4835, + "step": 2220 + }, + { + "epoch": 0.23, + "learning_rate": 1.8942159606269332e-05, + "loss": 1.535, + "step": 2221 + }, + { + "epoch": 0.23, + "learning_rate": 1.8940520548292332e-05, + "loss": 1.491, + "step": 2222 + }, + { + "epoch": 0.23, + "learning_rate": 1.89388802925153e-05, + "loss": 1.5157, + "step": 2223 + }, + { + "epoch": 0.23, + "learning_rate": 1.8937238839157987e-05, + "loss": 1.4779, + "step": 2224 + }, + { + "epoch": 0.23, + "learning_rate": 1.8935596188440302e-05, + "loss": 1.4902, + "step": 2225 + }, + { + "epoch": 0.23, + "learning_rate": 1.8933952340582323e-05, + "loss": 1.4988, + "step": 2226 + }, + { + "epoch": 0.23, + "learning_rate": 1.893230729580428e-05, + "loss": 1.4568, + "step": 2227 + }, + { + "epoch": 0.23, + "learning_rate": 1.8930661054326567e-05, + "loss": 1.5163, + "step": 2228 + }, + { + "epoch": 0.23, + "learning_rate": 1.892901361636974e-05, + "loss": 1.4472, + "step": 2229 + }, + { + "epoch": 0.23, + "learning_rate": 1.892736498215451e-05, + "loss": 1.4658, + "step": 2230 + }, + { + "epoch": 0.23, + "learning_rate": 1.8925715151901754e-05, + "loss": 1.4281, + "step": 2231 + }, + { + "epoch": 0.23, + "learning_rate": 1.892406412583251e-05, + "loss": 1.415, + "step": 2232 + }, + { + "epoch": 0.23, + "learning_rate": 1.8922411904167966e-05, + "loss": 1.464, + "step": 2233 + }, + { + "epoch": 0.23, + "learning_rate": 1.892075848712948e-05, + "loss": 1.5014, + "step": 2234 + }, + { + "epoch": 0.23, + "learning_rate": 1.8919103874938568e-05, + "loss": 1.4397, + "step": 2235 + }, + { + "epoch": 0.23, + "learning_rate": 1.891744806781691e-05, + "loss": 1.5508, + "step": 2236 + }, + { + "epoch": 0.23, + "learning_rate": 1.8915791065986335e-05, + "loss": 1.4749, + "step": 2237 + }, + { + "epoch": 0.23, + "learning_rate": 1.891413286966884e-05, + "loss": 1.4538, + "step": 2238 + }, + { + "epoch": 0.23, + "learning_rate": 1.891247347908658e-05, + "loss": 1.4405, + "step": 2239 + }, + { + "epoch": 0.23, + "learning_rate": 1.8910812894461878e-05, + "loss": 1.3562, + "step": 2240 + }, + { + "epoch": 0.24, + "learning_rate": 1.89091511160172e-05, + "loss": 1.4811, + "step": 2241 + }, + { + "epoch": 0.24, + "learning_rate": 1.8907488143975186e-05, + "loss": 1.4286, + "step": 2242 + }, + { + "epoch": 0.24, + "learning_rate": 1.890582397855863e-05, + "loss": 1.4493, + "step": 2243 + }, + { + "epoch": 0.24, + "learning_rate": 1.890415861999049e-05, + "loss": 1.5639, + "step": 2244 + }, + { + "epoch": 0.24, + "learning_rate": 1.890249206849388e-05, + "loss": 1.6375, + "step": 2245 + }, + { + "epoch": 0.24, + "learning_rate": 1.890082432429208e-05, + "loss": 1.4982, + "step": 2246 + }, + { + "epoch": 0.24, + "learning_rate": 1.889915538760851e-05, + "loss": 1.492, + "step": 2247 + }, + { + "epoch": 0.24, + "learning_rate": 1.8897485258666778e-05, + "loss": 1.4294, + "step": 2248 + }, + { + "epoch": 0.24, + "learning_rate": 1.8895813937690638e-05, + "loss": 1.4617, + "step": 2249 + }, + { + "epoch": 0.24, + "learning_rate": 1.8894141424904e-05, + "loss": 1.4763, + "step": 2250 + }, + { + "epoch": 0.24, + "learning_rate": 1.8892467720530937e-05, + "loss": 1.3989, + "step": 2251 + }, + { + "epoch": 0.24, + "learning_rate": 1.8890792824795687e-05, + "loss": 1.4803, + "step": 2252 + }, + { + "epoch": 0.24, + "learning_rate": 1.8889116737922638e-05, + "loss": 1.4734, + "step": 2253 + }, + { + "epoch": 0.24, + "learning_rate": 1.8887439460136342e-05, + "loss": 1.5069, + "step": 2254 + }, + { + "epoch": 0.24, + "learning_rate": 1.8885760991661514e-05, + "loss": 1.5565, + "step": 2255 + }, + { + "epoch": 0.24, + "learning_rate": 1.8884081332723028e-05, + "loss": 1.4707, + "step": 2256 + }, + { + "epoch": 0.24, + "learning_rate": 1.8882400483545913e-05, + "loss": 1.5077, + "step": 2257 + }, + { + "epoch": 0.24, + "learning_rate": 1.888071844435536e-05, + "loss": 1.5075, + "step": 2258 + }, + { + "epoch": 0.24, + "learning_rate": 1.8879035215376717e-05, + "loss": 1.5185, + "step": 2259 + }, + { + "epoch": 0.24, + "learning_rate": 1.887735079683549e-05, + "loss": 1.6266, + "step": 2260 + }, + { + "epoch": 0.24, + "learning_rate": 1.8875665188957354e-05, + "loss": 1.5013, + "step": 2261 + }, + { + "epoch": 0.24, + "learning_rate": 1.887397839196814e-05, + "loss": 1.4362, + "step": 2262 + }, + { + "epoch": 0.24, + "learning_rate": 1.8872290406093827e-05, + "loss": 1.4718, + "step": 2263 + }, + { + "epoch": 0.24, + "learning_rate": 1.8870601231560567e-05, + "loss": 1.5202, + "step": 2264 + }, + { + "epoch": 0.24, + "learning_rate": 1.8868910868594664e-05, + "loss": 1.5168, + "step": 2265 + }, + { + "epoch": 0.24, + "learning_rate": 1.8867219317422588e-05, + "loss": 1.5142, + "step": 2266 + }, + { + "epoch": 0.24, + "learning_rate": 1.8865526578270954e-05, + "loss": 1.4885, + "step": 2267 + }, + { + "epoch": 0.24, + "learning_rate": 1.8863832651366552e-05, + "loss": 1.5441, + "step": 2268 + }, + { + "epoch": 0.24, + "learning_rate": 1.8862137536936328e-05, + "loss": 1.4647, + "step": 2269 + }, + { + "epoch": 0.24, + "learning_rate": 1.8860441235207374e-05, + "loss": 1.5352, + "step": 2270 + }, + { + "epoch": 0.24, + "learning_rate": 1.8858743746406958e-05, + "loss": 1.4568, + "step": 2271 + }, + { + "epoch": 0.24, + "learning_rate": 1.8857045070762497e-05, + "loss": 1.4865, + "step": 2272 + }, + { + "epoch": 0.24, + "learning_rate": 1.8855345208501573e-05, + "loss": 1.4637, + "step": 2273 + }, + { + "epoch": 0.24, + "learning_rate": 1.8853644159851918e-05, + "loss": 1.4348, + "step": 2274 + }, + { + "epoch": 0.24, + "learning_rate": 1.8851941925041436e-05, + "loss": 1.4413, + "step": 2275 + }, + { + "epoch": 0.24, + "learning_rate": 1.8850238504298177e-05, + "loss": 1.4434, + "step": 2276 + }, + { + "epoch": 0.24, + "learning_rate": 1.884853389785036e-05, + "loss": 1.4822, + "step": 2277 + }, + { + "epoch": 0.24, + "learning_rate": 1.8846828105926356e-05, + "loss": 1.4632, + "step": 2278 + }, + { + "epoch": 0.24, + "learning_rate": 1.8845121128754698e-05, + "loss": 1.48, + "step": 2279 + }, + { + "epoch": 0.24, + "learning_rate": 1.8843412966564078e-05, + "loss": 1.4518, + "step": 2280 + }, + { + "epoch": 0.24, + "learning_rate": 1.884170361958334e-05, + "loss": 1.4334, + "step": 2281 + }, + { + "epoch": 0.24, + "learning_rate": 1.8839993088041502e-05, + "loss": 1.5131, + "step": 2282 + }, + { + "epoch": 0.24, + "learning_rate": 1.8838281372167724e-05, + "loss": 1.508, + "step": 2283 + }, + { + "epoch": 0.24, + "learning_rate": 1.8836568472191335e-05, + "loss": 1.4086, + "step": 2284 + }, + { + "epoch": 0.24, + "learning_rate": 1.883485438834182e-05, + "loss": 1.5021, + "step": 2285 + }, + { + "epoch": 0.24, + "learning_rate": 1.8833139120848817e-05, + "loss": 1.5083, + "step": 2286 + }, + { + "epoch": 0.24, + "learning_rate": 1.8831422669942137e-05, + "loss": 1.4162, + "step": 2287 + }, + { + "epoch": 0.24, + "learning_rate": 1.8829705035851734e-05, + "loss": 1.5494, + "step": 2288 + }, + { + "epoch": 0.24, + "learning_rate": 1.8827986218807724e-05, + "loss": 1.425, + "step": 2289 + }, + { + "epoch": 0.24, + "learning_rate": 1.8826266219040396e-05, + "loss": 1.5215, + "step": 2290 + }, + { + "epoch": 0.24, + "learning_rate": 1.8824545036780172e-05, + "loss": 1.5577, + "step": 2291 + }, + { + "epoch": 0.24, + "learning_rate": 1.8822822672257655e-05, + "loss": 1.4923, + "step": 2292 + }, + { + "epoch": 0.24, + "learning_rate": 1.8821099125703595e-05, + "loss": 1.4648, + "step": 2293 + }, + { + "epoch": 0.24, + "learning_rate": 1.8819374397348902e-05, + "loss": 1.471, + "step": 2294 + }, + { + "epoch": 0.24, + "learning_rate": 1.8817648487424648e-05, + "loss": 1.5658, + "step": 2295 + }, + { + "epoch": 0.24, + "learning_rate": 1.8815921396162058e-05, + "loss": 1.5348, + "step": 2296 + }, + { + "epoch": 0.24, + "learning_rate": 1.8814193123792518e-05, + "loss": 1.4081, + "step": 2297 + }, + { + "epoch": 0.24, + "learning_rate": 1.881246367054757e-05, + "loss": 1.4762, + "step": 2298 + }, + { + "epoch": 0.24, + "learning_rate": 1.8810733036658925e-05, + "loss": 1.4399, + "step": 2299 + }, + { + "epoch": 0.24, + "learning_rate": 1.8809001222358432e-05, + "loss": 1.4763, + "step": 2300 + }, + { + "epoch": 0.24, + "learning_rate": 1.880726822787812e-05, + "loss": 1.4874, + "step": 2301 + }, + { + "epoch": 0.24, + "learning_rate": 1.880553405345016e-05, + "loss": 1.4951, + "step": 2302 + }, + { + "epoch": 0.24, + "learning_rate": 1.8803798699306887e-05, + "loss": 1.4697, + "step": 2303 + }, + { + "epoch": 0.24, + "learning_rate": 1.880206216568079e-05, + "loss": 1.481, + "step": 2304 + }, + { + "epoch": 0.24, + "learning_rate": 1.880032445280453e-05, + "loss": 1.4485, + "step": 2305 + }, + { + "epoch": 0.24, + "learning_rate": 1.879858556091091e-05, + "loss": 1.4749, + "step": 2306 + }, + { + "epoch": 0.24, + "learning_rate": 1.8796845490232894e-05, + "loss": 1.5605, + "step": 2307 + }, + { + "epoch": 0.24, + "learning_rate": 1.879510424100361e-05, + "loss": 1.4835, + "step": 2308 + }, + { + "epoch": 0.24, + "learning_rate": 1.8793361813456346e-05, + "loss": 1.4344, + "step": 2309 + }, + { + "epoch": 0.24, + "learning_rate": 1.8791618207824532e-05, + "loss": 1.4571, + "step": 2310 + }, + { + "epoch": 0.24, + "learning_rate": 1.8789873424341772e-05, + "loss": 1.482, + "step": 2311 + }, + { + "epoch": 0.24, + "learning_rate": 1.8788127463241822e-05, + "loss": 1.4736, + "step": 2312 + }, + { + "epoch": 0.24, + "learning_rate": 1.8786380324758597e-05, + "loss": 1.4807, + "step": 2313 + }, + { + "epoch": 0.24, + "learning_rate": 1.8784632009126167e-05, + "loss": 1.4418, + "step": 2314 + }, + { + "epoch": 0.24, + "learning_rate": 1.878288251657876e-05, + "loss": 1.5248, + "step": 2315 + }, + { + "epoch": 0.24, + "learning_rate": 1.8781131847350768e-05, + "loss": 1.483, + "step": 2316 + }, + { + "epoch": 0.24, + "learning_rate": 1.877938000167673e-05, + "loss": 1.5474, + "step": 2317 + }, + { + "epoch": 0.24, + "learning_rate": 1.8777626979791347e-05, + "loss": 1.4671, + "step": 2318 + }, + { + "epoch": 0.24, + "learning_rate": 1.877587278192949e-05, + "loss": 1.3049, + "step": 2319 + }, + { + "epoch": 0.24, + "learning_rate": 1.877411740832616e-05, + "loss": 1.483, + "step": 2320 + }, + { + "epoch": 0.24, + "learning_rate": 1.877236085921655e-05, + "loss": 1.508, + "step": 2321 + }, + { + "epoch": 0.24, + "learning_rate": 1.8770603134835978e-05, + "loss": 1.4854, + "step": 2322 + }, + { + "epoch": 0.24, + "learning_rate": 1.8768844235419942e-05, + "loss": 1.4808, + "step": 2323 + }, + { + "epoch": 0.24, + "learning_rate": 1.8767084161204087e-05, + "loss": 1.5352, + "step": 2324 + }, + { + "epoch": 0.24, + "learning_rate": 1.8765322912424214e-05, + "loss": 1.5628, + "step": 2325 + }, + { + "epoch": 0.24, + "learning_rate": 1.8763560489316292e-05, + "loss": 1.494, + "step": 2326 + }, + { + "epoch": 0.24, + "learning_rate": 1.876179689211643e-05, + "loss": 1.509, + "step": 2327 + }, + { + "epoch": 0.24, + "learning_rate": 1.8760032121060918e-05, + "loss": 1.5021, + "step": 2328 + }, + { + "epoch": 0.24, + "learning_rate": 1.875826617638618e-05, + "loss": 1.4179, + "step": 2329 + }, + { + "epoch": 0.24, + "learning_rate": 1.8756499058328813e-05, + "loss": 1.4302, + "step": 2330 + }, + { + "epoch": 0.24, + "learning_rate": 1.8754730767125564e-05, + "loss": 1.4959, + "step": 2331 + }, + { + "epoch": 0.24, + "learning_rate": 1.8752961303013336e-05, + "loss": 1.4423, + "step": 2332 + }, + { + "epoch": 0.24, + "learning_rate": 1.8751190666229194e-05, + "loss": 1.4564, + "step": 2333 + }, + { + "epoch": 0.24, + "learning_rate": 1.8749418857010358e-05, + "loss": 1.4775, + "step": 2334 + }, + { + "epoch": 0.24, + "learning_rate": 1.8747645875594203e-05, + "loss": 1.4182, + "step": 2335 + }, + { + "epoch": 0.24, + "learning_rate": 1.8745871722218265e-05, + "loss": 1.3957, + "step": 2336 + }, + { + "epoch": 0.25, + "learning_rate": 1.8744096397120235e-05, + "loss": 1.4633, + "step": 2337 + }, + { + "epoch": 0.25, + "learning_rate": 1.874231990053796e-05, + "loss": 1.5512, + "step": 2338 + }, + { + "epoch": 0.25, + "learning_rate": 1.8740542232709444e-05, + "loss": 1.3461, + "step": 2339 + }, + { + "epoch": 0.25, + "learning_rate": 1.8738763393872848e-05, + "loss": 1.4754, + "step": 2340 + }, + { + "epoch": 0.25, + "learning_rate": 1.8736983384266495e-05, + "loss": 1.5448, + "step": 2341 + }, + { + "epoch": 0.25, + "learning_rate": 1.8735202204128854e-05, + "loss": 1.4491, + "step": 2342 + }, + { + "epoch": 0.25, + "learning_rate": 1.8733419853698566e-05, + "loss": 1.457, + "step": 2343 + }, + { + "epoch": 0.25, + "learning_rate": 1.8731636333214414e-05, + "loss": 1.4314, + "step": 2344 + }, + { + "epoch": 0.25, + "learning_rate": 1.8729851642915345e-05, + "loss": 1.3979, + "step": 2345 + }, + { + "epoch": 0.25, + "learning_rate": 1.8728065783040464e-05, + "loss": 1.4146, + "step": 2346 + }, + { + "epoch": 0.25, + "learning_rate": 1.8726278753829027e-05, + "loss": 1.4361, + "step": 2347 + }, + { + "epoch": 0.25, + "learning_rate": 1.872449055552045e-05, + "loss": 1.4989, + "step": 2348 + }, + { + "epoch": 0.25, + "learning_rate": 1.872270118835431e-05, + "loss": 1.5062, + "step": 2349 + }, + { + "epoch": 0.25, + "learning_rate": 1.872091065257033e-05, + "loss": 1.4509, + "step": 2350 + }, + { + "epoch": 0.25, + "learning_rate": 1.8719118948408403e-05, + "loss": 1.4631, + "step": 2351 + }, + { + "epoch": 0.25, + "learning_rate": 1.8717326076108566e-05, + "loss": 1.5119, + "step": 2352 + }, + { + "epoch": 0.25, + "learning_rate": 1.8715532035911017e-05, + "loss": 1.6347, + "step": 2353 + }, + { + "epoch": 0.25, + "learning_rate": 1.8713736828056115e-05, + "loss": 1.5526, + "step": 2354 + }, + { + "epoch": 0.25, + "learning_rate": 1.8711940452784368e-05, + "loss": 1.6348, + "step": 2355 + }, + { + "epoch": 0.25, + "learning_rate": 1.871014291033645e-05, + "loss": 1.5183, + "step": 2356 + }, + { + "epoch": 0.25, + "learning_rate": 1.8708344200953182e-05, + "loss": 1.458, + "step": 2357 + }, + { + "epoch": 0.25, + "learning_rate": 1.8706544324875545e-05, + "loss": 1.524, + "step": 2358 + }, + { + "epoch": 0.25, + "learning_rate": 1.8704743282344672e-05, + "loss": 1.4479, + "step": 2359 + }, + { + "epoch": 0.25, + "learning_rate": 1.870294107360186e-05, + "loss": 1.5408, + "step": 2360 + }, + { + "epoch": 0.25, + "learning_rate": 1.8701137698888563e-05, + "loss": 1.5007, + "step": 2361 + }, + { + "epoch": 0.25, + "learning_rate": 1.8699333158446382e-05, + "loss": 1.5132, + "step": 2362 + }, + { + "epoch": 0.25, + "learning_rate": 1.869752745251708e-05, + "loss": 1.4263, + "step": 2363 + }, + { + "epoch": 0.25, + "learning_rate": 1.8695720581342574e-05, + "loss": 1.422, + "step": 2364 + }, + { + "epoch": 0.25, + "learning_rate": 1.869391254516494e-05, + "loss": 1.4411, + "step": 2365 + }, + { + "epoch": 0.25, + "learning_rate": 1.8692103344226406e-05, + "loss": 1.4594, + "step": 2366 + }, + { + "epoch": 0.25, + "learning_rate": 1.8690292978769364e-05, + "loss": 1.4992, + "step": 2367 + }, + { + "epoch": 0.25, + "learning_rate": 1.868848144903635e-05, + "loss": 1.4822, + "step": 2368 + }, + { + "epoch": 0.25, + "learning_rate": 1.8686668755270064e-05, + "loss": 1.5402, + "step": 2369 + }, + { + "epoch": 0.25, + "learning_rate": 1.8684854897713363e-05, + "loss": 1.5268, + "step": 2370 + }, + { + "epoch": 0.25, + "learning_rate": 1.8683039876609258e-05, + "loss": 1.5587, + "step": 2371 + }, + { + "epoch": 0.25, + "learning_rate": 1.868122369220091e-05, + "loss": 1.4214, + "step": 2372 + }, + { + "epoch": 0.25, + "learning_rate": 1.8679406344731645e-05, + "loss": 1.5089, + "step": 2373 + }, + { + "epoch": 0.25, + "learning_rate": 1.867758783444494e-05, + "loss": 1.5067, + "step": 2374 + }, + { + "epoch": 0.25, + "learning_rate": 1.8675768161584427e-05, + "loss": 2.0616, + "step": 2375 + }, + { + "epoch": 0.25, + "learning_rate": 1.8673947326393903e-05, + "loss": 1.5617, + "step": 2376 + }, + { + "epoch": 0.25, + "learning_rate": 1.86721253291173e-05, + "loss": 1.4422, + "step": 2377 + }, + { + "epoch": 0.25, + "learning_rate": 1.867030216999873e-05, + "loss": 1.4727, + "step": 2378 + }, + { + "epoch": 0.25, + "learning_rate": 1.8668477849282443e-05, + "loss": 1.4152, + "step": 2379 + }, + { + "epoch": 0.25, + "learning_rate": 1.8666652367212856e-05, + "loss": 1.4376, + "step": 2380 + }, + { + "epoch": 0.25, + "learning_rate": 1.8664825724034534e-05, + "loss": 1.393, + "step": 2381 + }, + { + "epoch": 0.25, + "learning_rate": 1.8662997919992197e-05, + "loss": 1.4864, + "step": 2382 + }, + { + "epoch": 0.25, + "learning_rate": 1.866116895533073e-05, + "loss": 1.4261, + "step": 2383 + }, + { + "epoch": 0.25, + "learning_rate": 1.8659338830295163e-05, + "loss": 1.4555, + "step": 2384 + }, + { + "epoch": 0.25, + "learning_rate": 1.8657507545130687e-05, + "loss": 1.4939, + "step": 2385 + }, + { + "epoch": 0.25, + "learning_rate": 1.865567510008265e-05, + "loss": 1.4123, + "step": 2386 + }, + { + "epoch": 0.25, + "learning_rate": 1.8653841495396546e-05, + "loss": 1.4459, + "step": 2387 + }, + { + "epoch": 0.25, + "learning_rate": 1.8652006731318038e-05, + "loss": 1.396, + "step": 2388 + }, + { + "epoch": 0.25, + "eval_loss": 1.5139706134796143, + "eval_runtime": 77.2904, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 2388 + }, + { + "epoch": 0.25, + "learning_rate": 1.8650170808092936e-05, + "loss": 1.4666, + "step": 2389 + }, + { + "epoch": 0.25, + "learning_rate": 1.86483337259672e-05, + "loss": 1.5154, + "step": 2390 + }, + { + "epoch": 0.25, + "learning_rate": 1.864649548518696e-05, + "loss": 1.5163, + "step": 2391 + }, + { + "epoch": 0.25, + "learning_rate": 1.864465608599849e-05, + "loss": 1.4734, + "step": 2392 + }, + { + "epoch": 0.25, + "learning_rate": 1.864281552864822e-05, + "loss": 1.5217, + "step": 2393 + }, + { + "epoch": 0.25, + "learning_rate": 1.8640973813382737e-05, + "loss": 1.4694, + "step": 2394 + }, + { + "epoch": 0.25, + "learning_rate": 1.863913094044879e-05, + "loss": 1.4761, + "step": 2395 + }, + { + "epoch": 0.25, + "learning_rate": 1.863728691009327e-05, + "loss": 1.4766, + "step": 2396 + }, + { + "epoch": 0.25, + "learning_rate": 1.863544172256323e-05, + "loss": 1.5695, + "step": 2397 + }, + { + "epoch": 0.25, + "learning_rate": 1.8633595378105882e-05, + "loss": 1.5079, + "step": 2398 + }, + { + "epoch": 0.25, + "learning_rate": 1.8631747876968584e-05, + "loss": 1.4154, + "step": 2399 + }, + { + "epoch": 0.25, + "learning_rate": 1.862989921939886e-05, + "loss": 1.4488, + "step": 2400 + }, + { + "epoch": 0.25, + "learning_rate": 1.8628049405644376e-05, + "loss": 1.4279, + "step": 2401 + }, + { + "epoch": 0.25, + "learning_rate": 1.8626198435952966e-05, + "loss": 1.4896, + "step": 2402 + }, + { + "epoch": 0.25, + "learning_rate": 1.8624346310572602e-05, + "loss": 1.4315, + "step": 2403 + }, + { + "epoch": 0.25, + "learning_rate": 1.862249302975143e-05, + "loss": 1.4919, + "step": 2404 + }, + { + "epoch": 0.25, + "learning_rate": 1.8620638593737743e-05, + "loss": 1.4561, + "step": 2405 + }, + { + "epoch": 0.25, + "learning_rate": 1.8618783002779985e-05, + "loss": 1.4622, + "step": 2406 + }, + { + "epoch": 0.25, + "learning_rate": 1.8616926257126754e-05, + "loss": 1.4917, + "step": 2407 + }, + { + "epoch": 0.25, + "learning_rate": 1.861506835702681e-05, + "loss": 1.4962, + "step": 2408 + }, + { + "epoch": 0.25, + "learning_rate": 1.861320930272906e-05, + "loss": 1.4164, + "step": 2409 + }, + { + "epoch": 0.25, + "learning_rate": 1.8611349094482578e-05, + "loss": 1.4889, + "step": 2410 + }, + { + "epoch": 0.25, + "learning_rate": 1.8609487732536576e-05, + "loss": 1.543, + "step": 2411 + }, + { + "epoch": 0.25, + "learning_rate": 1.8607625217140433e-05, + "loss": 1.5417, + "step": 2412 + }, + { + "epoch": 0.25, + "learning_rate": 1.8605761548543674e-05, + "loss": 1.5304, + "step": 2413 + }, + { + "epoch": 0.25, + "learning_rate": 1.860389672699599e-05, + "loss": 1.4725, + "step": 2414 + }, + { + "epoch": 0.25, + "learning_rate": 1.860203075274721e-05, + "loss": 1.4745, + "step": 2415 + }, + { + "epoch": 0.25, + "learning_rate": 1.8600163626047334e-05, + "loss": 1.4656, + "step": 2416 + }, + { + "epoch": 0.25, + "learning_rate": 1.8598295347146503e-05, + "loss": 1.5287, + "step": 2417 + }, + { + "epoch": 0.25, + "learning_rate": 1.8596425916295023e-05, + "loss": 1.5024, + "step": 2418 + }, + { + "epoch": 0.25, + "learning_rate": 1.8594555333743348e-05, + "loss": 1.4527, + "step": 2419 + }, + { + "epoch": 0.25, + "learning_rate": 1.859268359974209e-05, + "loss": 1.4897, + "step": 2420 + }, + { + "epoch": 0.25, + "learning_rate": 1.859081071454201e-05, + "loss": 1.3554, + "step": 2421 + }, + { + "epoch": 0.25, + "learning_rate": 1.858893667839403e-05, + "loss": 1.4004, + "step": 2422 + }, + { + "epoch": 0.25, + "learning_rate": 1.858706149154922e-05, + "loss": 1.5582, + "step": 2423 + }, + { + "epoch": 0.25, + "learning_rate": 1.8585185154258803e-05, + "loss": 1.505, + "step": 2424 + }, + { + "epoch": 0.25, + "learning_rate": 1.858330766677417e-05, + "loss": 1.5043, + "step": 2425 + }, + { + "epoch": 0.25, + "learning_rate": 1.858142902934685e-05, + "loss": 1.439, + "step": 2426 + }, + { + "epoch": 0.25, + "learning_rate": 1.857954924222853e-05, + "loss": 1.4927, + "step": 2427 + }, + { + "epoch": 0.25, + "learning_rate": 1.8577668305671056e-05, + "loss": 1.5395, + "step": 2428 + }, + { + "epoch": 0.25, + "learning_rate": 1.8575786219926427e-05, + "loss": 1.4737, + "step": 2429 + }, + { + "epoch": 0.25, + "learning_rate": 1.8573902985246794e-05, + "loss": 1.6151, + "step": 2430 + }, + { + "epoch": 0.25, + "learning_rate": 1.857201860188446e-05, + "loss": 1.4313, + "step": 2431 + }, + { + "epoch": 0.26, + "learning_rate": 1.857013307009188e-05, + "loss": 1.4509, + "step": 2432 + }, + { + "epoch": 0.26, + "learning_rate": 1.8568246390121673e-05, + "loss": 1.3998, + "step": 2433 + }, + { + "epoch": 0.26, + "learning_rate": 1.8566358562226603e-05, + "loss": 1.5268, + "step": 2434 + }, + { + "epoch": 0.26, + "learning_rate": 1.8564469586659593e-05, + "loss": 1.4369, + "step": 2435 + }, + { + "epoch": 0.26, + "learning_rate": 1.8562579463673713e-05, + "loss": 1.4759, + "step": 2436 + }, + { + "epoch": 0.26, + "learning_rate": 1.8560688193522197e-05, + "loss": 1.4092, + "step": 2437 + }, + { + "epoch": 0.26, + "learning_rate": 1.855879577645842e-05, + "loss": 1.43, + "step": 2438 + }, + { + "epoch": 0.26, + "learning_rate": 1.855690221273592e-05, + "loss": 1.5143, + "step": 2439 + }, + { + "epoch": 0.26, + "learning_rate": 1.8555007502608385e-05, + "loss": 1.5482, + "step": 2440 + }, + { + "epoch": 0.26, + "learning_rate": 1.855311164632966e-05, + "loss": 1.4406, + "step": 2441 + }, + { + "epoch": 0.26, + "learning_rate": 1.8551214644153738e-05, + "loss": 1.4551, + "step": 2442 + }, + { + "epoch": 0.26, + "learning_rate": 1.8549316496334774e-05, + "loss": 1.4663, + "step": 2443 + }, + { + "epoch": 0.26, + "learning_rate": 1.8547417203127064e-05, + "loss": 1.4732, + "step": 2444 + }, + { + "epoch": 0.26, + "learning_rate": 1.8545516764785067e-05, + "loss": 1.5378, + "step": 2445 + }, + { + "epoch": 0.26, + "learning_rate": 1.8543615181563397e-05, + "loss": 1.4448, + "step": 2446 + }, + { + "epoch": 0.26, + "learning_rate": 1.854171245371681e-05, + "loss": 1.2861, + "step": 2447 + }, + { + "epoch": 0.26, + "learning_rate": 1.8539808581500228e-05, + "loss": 1.4405, + "step": 2448 + }, + { + "epoch": 0.26, + "learning_rate": 1.8537903565168716e-05, + "loss": 1.4876, + "step": 2449 + }, + { + "epoch": 0.26, + "learning_rate": 1.8535997404977506e-05, + "loss": 1.4119, + "step": 2450 + }, + { + "epoch": 0.26, + "learning_rate": 1.8534090101181967e-05, + "loss": 1.4451, + "step": 2451 + }, + { + "epoch": 0.26, + "learning_rate": 1.8532181654037632e-05, + "loss": 1.4035, + "step": 2452 + }, + { + "epoch": 0.26, + "learning_rate": 1.853027206380018e-05, + "loss": 1.4624, + "step": 2453 + }, + { + "epoch": 0.26, + "learning_rate": 1.852836133072545e-05, + "loss": 1.4935, + "step": 2454 + }, + { + "epoch": 0.26, + "learning_rate": 1.8526449455069434e-05, + "loss": 1.4834, + "step": 2455 + }, + { + "epoch": 0.26, + "learning_rate": 1.8524536437088266e-05, + "loss": 1.498, + "step": 2456 + }, + { + "epoch": 0.26, + "learning_rate": 1.8522622277038247e-05, + "loss": 1.3417, + "step": 2457 + }, + { + "epoch": 0.26, + "learning_rate": 1.852070697517583e-05, + "loss": 1.4455, + "step": 2458 + }, + { + "epoch": 0.26, + "learning_rate": 1.8518790531757607e-05, + "loss": 1.4119, + "step": 2459 + }, + { + "epoch": 0.26, + "learning_rate": 1.8516872947040337e-05, + "loss": 1.558, + "step": 2460 + }, + { + "epoch": 0.26, + "learning_rate": 1.8514954221280926e-05, + "loss": 1.4862, + "step": 2461 + }, + { + "epoch": 0.26, + "learning_rate": 1.8513034354736433e-05, + "loss": 1.6806, + "step": 2462 + }, + { + "epoch": 0.26, + "learning_rate": 1.8511113347664072e-05, + "loss": 1.438, + "step": 2463 + }, + { + "epoch": 0.26, + "learning_rate": 1.850919120032121e-05, + "loss": 1.4975, + "step": 2464 + }, + { + "epoch": 0.26, + "learning_rate": 1.850726791296536e-05, + "loss": 1.4409, + "step": 2465 + }, + { + "epoch": 0.26, + "learning_rate": 1.85053434858542e-05, + "loss": 1.4769, + "step": 2466 + }, + { + "epoch": 0.26, + "learning_rate": 1.8503417919245548e-05, + "loss": 1.5823, + "step": 2467 + }, + { + "epoch": 0.26, + "learning_rate": 1.8501491213397386e-05, + "loss": 1.4045, + "step": 2468 + }, + { + "epoch": 0.26, + "learning_rate": 1.8499563368567837e-05, + "loss": 1.4828, + "step": 2469 + }, + { + "epoch": 0.26, + "learning_rate": 1.849763438501519e-05, + "loss": 1.4684, + "step": 2470 + }, + { + "epoch": 0.26, + "learning_rate": 1.8495704262997873e-05, + "loss": 1.4577, + "step": 2471 + }, + { + "epoch": 0.26, + "learning_rate": 1.8493773002774475e-05, + "loss": 1.4759, + "step": 2472 + }, + { + "epoch": 0.26, + "learning_rate": 1.8491840604603736e-05, + "loss": 1.4259, + "step": 2473 + }, + { + "epoch": 0.26, + "learning_rate": 1.8489907068744543e-05, + "loss": 1.4717, + "step": 2474 + }, + { + "epoch": 0.26, + "learning_rate": 1.848797239545595e-05, + "loss": 1.4247, + "step": 2475 + }, + { + "epoch": 0.26, + "learning_rate": 1.8486036584997143e-05, + "loss": 1.4954, + "step": 2476 + }, + { + "epoch": 0.26, + "learning_rate": 1.8484099637627472e-05, + "loss": 1.4926, + "step": 2477 + }, + { + "epoch": 0.26, + "learning_rate": 1.8482161553606447e-05, + "loss": 1.487, + "step": 2478 + }, + { + "epoch": 0.26, + "learning_rate": 1.8480222333193715e-05, + "loss": 1.4553, + "step": 2479 + }, + { + "epoch": 0.26, + "learning_rate": 1.847828197664908e-05, + "loss": 1.4862, + "step": 2480 + }, + { + "epoch": 0.26, + "learning_rate": 1.8476340484232508e-05, + "loss": 1.4867, + "step": 2481 + }, + { + "epoch": 0.26, + "learning_rate": 1.8474397856204097e-05, + "loss": 1.4736, + "step": 2482 + }, + { + "epoch": 0.26, + "learning_rate": 1.8472454092824122e-05, + "loss": 1.4254, + "step": 2483 + }, + { + "epoch": 0.26, + "learning_rate": 1.8470509194352987e-05, + "loss": 1.4455, + "step": 2484 + }, + { + "epoch": 0.26, + "learning_rate": 1.8468563161051263e-05, + "loss": 1.4402, + "step": 2485 + }, + { + "epoch": 0.26, + "learning_rate": 1.846661599317967e-05, + "loss": 1.4611, + "step": 2486 + }, + { + "epoch": 0.26, + "learning_rate": 1.8464667690999073e-05, + "loss": 1.4814, + "step": 2487 + }, + { + "epoch": 0.26, + "learning_rate": 1.8462718254770503e-05, + "loss": 1.4559, + "step": 2488 + }, + { + "epoch": 0.26, + "learning_rate": 1.8460767684755127e-05, + "loss": 1.4667, + "step": 2489 + }, + { + "epoch": 0.26, + "learning_rate": 1.8458815981214274e-05, + "loss": 1.4427, + "step": 2490 + }, + { + "epoch": 0.26, + "learning_rate": 1.845686314440942e-05, + "loss": 1.4055, + "step": 2491 + }, + { + "epoch": 0.26, + "learning_rate": 1.8454909174602198e-05, + "loss": 1.5563, + "step": 2492 + }, + { + "epoch": 0.26, + "learning_rate": 1.845295407205439e-05, + "loss": 1.4631, + "step": 2493 + }, + { + "epoch": 0.26, + "learning_rate": 1.8450997837027925e-05, + "loss": 1.4887, + "step": 2494 + }, + { + "epoch": 0.26, + "learning_rate": 1.8449040469784895e-05, + "loss": 1.5212, + "step": 2495 + }, + { + "epoch": 0.26, + "learning_rate": 1.844708197058753e-05, + "loss": 1.5582, + "step": 2496 + }, + { + "epoch": 0.26, + "learning_rate": 1.844512233969822e-05, + "loss": 1.4599, + "step": 2497 + }, + { + "epoch": 0.26, + "learning_rate": 1.844316157737951e-05, + "loss": 1.4546, + "step": 2498 + }, + { + "epoch": 0.26, + "learning_rate": 1.844119968389409e-05, + "loss": 1.4631, + "step": 2499 + }, + { + "epoch": 0.26, + "learning_rate": 1.84392366595048e-05, + "loss": 1.4817, + "step": 2500 + }, + { + "epoch": 0.26, + "learning_rate": 1.8437272504474636e-05, + "loss": 1.4214, + "step": 2501 + }, + { + "epoch": 0.26, + "learning_rate": 1.8435307219066744e-05, + "loss": 1.471, + "step": 2502 + }, + { + "epoch": 0.26, + "learning_rate": 1.8433340803544424e-05, + "loss": 1.4693, + "step": 2503 + }, + { + "epoch": 0.26, + "learning_rate": 1.8431373258171127e-05, + "loss": 1.6297, + "step": 2504 + }, + { + "epoch": 0.26, + "learning_rate": 1.842940458321045e-05, + "loss": 1.5916, + "step": 2505 + }, + { + "epoch": 0.26, + "learning_rate": 1.842743477892614e-05, + "loss": 1.4754, + "step": 2506 + }, + { + "epoch": 0.26, + "learning_rate": 1.842546384558211e-05, + "loss": 1.4828, + "step": 2507 + }, + { + "epoch": 0.26, + "learning_rate": 1.842349178344241e-05, + "loss": 1.4239, + "step": 2508 + }, + { + "epoch": 0.26, + "learning_rate": 1.8421518592771243e-05, + "loss": 1.5028, + "step": 2509 + }, + { + "epoch": 0.26, + "learning_rate": 1.841954427383297e-05, + "loss": 1.4848, + "step": 2510 + }, + { + "epoch": 0.26, + "learning_rate": 1.8417568826892097e-05, + "loss": 1.4617, + "step": 2511 + }, + { + "epoch": 0.26, + "learning_rate": 1.8415592252213284e-05, + "loss": 1.4266, + "step": 2512 + }, + { + "epoch": 0.26, + "learning_rate": 1.8413614550061344e-05, + "loss": 1.4321, + "step": 2513 + }, + { + "epoch": 0.26, + "learning_rate": 1.841163572070123e-05, + "loss": 1.4693, + "step": 2514 + }, + { + "epoch": 0.26, + "learning_rate": 1.840965576439806e-05, + "loss": 1.4257, + "step": 2515 + }, + { + "epoch": 0.26, + "learning_rate": 1.84076746814171e-05, + "loss": 1.4488, + "step": 2516 + }, + { + "epoch": 0.26, + "learning_rate": 1.840569247202376e-05, + "loss": 1.5348, + "step": 2517 + }, + { + "epoch": 0.26, + "learning_rate": 1.8403709136483604e-05, + "loss": 1.477, + "step": 2518 + }, + { + "epoch": 0.26, + "learning_rate": 1.840172467506235e-05, + "loss": 1.443, + "step": 2519 + }, + { + "epoch": 0.26, + "learning_rate": 1.839973908802587e-05, + "loss": 1.4772, + "step": 2520 + }, + { + "epoch": 0.26, + "learning_rate": 1.839775237564017e-05, + "loss": 1.4443, + "step": 2521 + }, + { + "epoch": 0.26, + "learning_rate": 1.839576453817143e-05, + "loss": 1.4063, + "step": 2522 + }, + { + "epoch": 0.26, + "learning_rate": 1.8393775575885963e-05, + "loss": 1.5178, + "step": 2523 + }, + { + "epoch": 0.26, + "learning_rate": 1.8391785489050235e-05, + "loss": 1.4337, + "step": 2524 + }, + { + "epoch": 0.26, + "learning_rate": 1.8389794277930875e-05, + "loss": 1.4512, + "step": 2525 + }, + { + "epoch": 0.26, + "learning_rate": 1.838780194279465e-05, + "loss": 1.5578, + "step": 2526 + }, + { + "epoch": 0.26, + "learning_rate": 1.8385808483908484e-05, + "loss": 1.4606, + "step": 2527 + }, + { + "epoch": 0.27, + "learning_rate": 1.8383813901539444e-05, + "loss": 1.4957, + "step": 2528 + }, + { + "epoch": 0.27, + "learning_rate": 1.838181819595476e-05, + "loss": 1.4914, + "step": 2529 + }, + { + "epoch": 0.27, + "learning_rate": 1.8379821367421802e-05, + "loss": 1.4785, + "step": 2530 + }, + { + "epoch": 0.27, + "learning_rate": 1.837782341620809e-05, + "loss": 1.4052, + "step": 2531 + }, + { + "epoch": 0.27, + "learning_rate": 1.8375824342581303e-05, + "loss": 1.4807, + "step": 2532 + }, + { + "epoch": 0.27, + "learning_rate": 1.8373824146809264e-05, + "loss": 1.4313, + "step": 2533 + }, + { + "epoch": 0.27, + "learning_rate": 1.8371822829159945e-05, + "loss": 1.4374, + "step": 2534 + }, + { + "epoch": 0.27, + "learning_rate": 1.836982038990148e-05, + "loss": 1.4482, + "step": 2535 + }, + { + "epoch": 0.27, + "learning_rate": 1.8367816829302133e-05, + "loss": 1.5231, + "step": 2536 + }, + { + "epoch": 0.27, + "learning_rate": 1.8365812147630337e-05, + "loss": 1.4101, + "step": 2537 + }, + { + "epoch": 0.27, + "learning_rate": 1.8363806345154666e-05, + "loss": 1.4372, + "step": 2538 + }, + { + "epoch": 0.27, + "learning_rate": 1.8361799422143845e-05, + "loss": 1.4808, + "step": 2539 + }, + { + "epoch": 0.27, + "learning_rate": 1.835979137886675e-05, + "loss": 1.3515, + "step": 2540 + }, + { + "epoch": 0.27, + "learning_rate": 1.8357782215592412e-05, + "loss": 1.5284, + "step": 2541 + }, + { + "epoch": 0.27, + "learning_rate": 1.835577193259e-05, + "loss": 1.4222, + "step": 2542 + }, + { + "epoch": 0.27, + "learning_rate": 1.8353760530128846e-05, + "loss": 1.4522, + "step": 2543 + }, + { + "epoch": 0.27, + "learning_rate": 1.835174800847842e-05, + "loss": 1.4487, + "step": 2544 + }, + { + "epoch": 0.27, + "learning_rate": 1.8349734367908355e-05, + "loss": 1.3688, + "step": 2545 + }, + { + "epoch": 0.27, + "learning_rate": 1.8347719608688422e-05, + "loss": 1.483, + "step": 2546 + }, + { + "epoch": 0.27, + "learning_rate": 1.8345703731088554e-05, + "loss": 1.4733, + "step": 2547 + }, + { + "epoch": 0.27, + "learning_rate": 1.8343686735378816e-05, + "loss": 1.4594, + "step": 2548 + }, + { + "epoch": 0.27, + "learning_rate": 1.834166862182944e-05, + "loss": 1.4648, + "step": 2549 + }, + { + "epoch": 0.27, + "learning_rate": 1.8339649390710807e-05, + "loss": 1.5249, + "step": 2550 + }, + { + "epoch": 0.27, + "learning_rate": 1.8337629042293434e-05, + "loss": 1.4744, + "step": 2551 + }, + { + "epoch": 0.27, + "learning_rate": 1.8335607576847994e-05, + "loss": 1.5094, + "step": 2552 + }, + { + "epoch": 0.27, + "learning_rate": 1.8333584994645318e-05, + "loss": 1.5122, + "step": 2553 + }, + { + "epoch": 0.27, + "learning_rate": 1.8331561295956374e-05, + "loss": 1.537, + "step": 2554 + }, + { + "epoch": 0.27, + "learning_rate": 1.832953648105229e-05, + "loss": 1.4691, + "step": 2555 + }, + { + "epoch": 0.27, + "learning_rate": 1.8327510550204343e-05, + "loss": 1.4969, + "step": 2556 + }, + { + "epoch": 0.27, + "learning_rate": 1.8325483503683944e-05, + "loss": 1.4596, + "step": 2557 + }, + { + "epoch": 0.27, + "learning_rate": 1.8323455341762675e-05, + "loss": 1.435, + "step": 2558 + }, + { + "epoch": 0.27, + "learning_rate": 1.8321426064712255e-05, + "loss": 1.4883, + "step": 2559 + }, + { + "epoch": 0.27, + "learning_rate": 1.8319395672804554e-05, + "loss": 1.3758, + "step": 2560 + }, + { + "epoch": 0.27, + "learning_rate": 1.8317364166311592e-05, + "loss": 1.4352, + "step": 2561 + }, + { + "epoch": 0.27, + "learning_rate": 1.831533154550554e-05, + "loss": 1.5072, + "step": 2562 + }, + { + "epoch": 0.27, + "learning_rate": 1.8313297810658718e-05, + "loss": 1.4476, + "step": 2563 + }, + { + "epoch": 0.27, + "learning_rate": 1.831126296204359e-05, + "loss": 1.507, + "step": 2564 + }, + { + "epoch": 0.27, + "learning_rate": 1.8309226999932777e-05, + "loss": 1.4677, + "step": 2565 + }, + { + "epoch": 0.27, + "learning_rate": 1.8307189924599044e-05, + "loss": 1.4537, + "step": 2566 + }, + { + "epoch": 0.27, + "learning_rate": 1.8305151736315307e-05, + "loss": 1.4584, + "step": 2567 + }, + { + "epoch": 0.27, + "learning_rate": 1.8303112435354634e-05, + "loss": 1.4944, + "step": 2568 + }, + { + "epoch": 0.27, + "learning_rate": 1.8301072021990232e-05, + "loss": 1.4379, + "step": 2569 + }, + { + "epoch": 0.27, + "learning_rate": 1.8299030496495475e-05, + "loss": 1.539, + "step": 2570 + }, + { + "epoch": 0.27, + "learning_rate": 1.829698785914386e-05, + "loss": 1.4421, + "step": 2571 + }, + { + "epoch": 0.27, + "learning_rate": 1.8294944110209063e-05, + "loss": 1.4693, + "step": 2572 + }, + { + "epoch": 0.27, + "learning_rate": 1.8292899249964887e-05, + "loss": 1.3239, + "step": 2573 + }, + { + "epoch": 0.27, + "learning_rate": 1.8290853278685284e-05, + "loss": 1.472, + "step": 2574 + }, + { + "epoch": 0.27, + "learning_rate": 1.8288806196644374e-05, + "loss": 1.536, + "step": 2575 + }, + { + "epoch": 0.27, + "learning_rate": 1.8286758004116405e-05, + "loss": 1.4644, + "step": 2576 + }, + { + "epoch": 0.27, + "learning_rate": 1.8284708701375783e-05, + "loss": 1.4537, + "step": 2577 + }, + { + "epoch": 0.27, + "learning_rate": 1.8282658288697067e-05, + "loss": 1.4359, + "step": 2578 + }, + { + "epoch": 0.27, + "learning_rate": 1.8280606766354955e-05, + "loss": 1.4842, + "step": 2579 + }, + { + "epoch": 0.27, + "learning_rate": 1.8278554134624302e-05, + "loss": 1.4664, + "step": 2580 + }, + { + "epoch": 0.27, + "learning_rate": 1.8276500393780105e-05, + "loss": 1.4632, + "step": 2581 + }, + { + "epoch": 0.27, + "learning_rate": 1.827444554409751e-05, + "loss": 1.4996, + "step": 2582 + }, + { + "epoch": 0.27, + "learning_rate": 1.827238958585182e-05, + "loss": 1.3399, + "step": 2583 + }, + { + "epoch": 0.27, + "learning_rate": 1.8270332519318476e-05, + "loss": 1.3928, + "step": 2584 + }, + { + "epoch": 0.27, + "learning_rate": 1.8268274344773074e-05, + "loss": 1.4993, + "step": 2585 + }, + { + "epoch": 0.27, + "learning_rate": 1.8266215062491356e-05, + "loss": 1.5398, + "step": 2586 + }, + { + "epoch": 0.27, + "learning_rate": 1.826415467274921e-05, + "loss": 1.4353, + "step": 2587 + }, + { + "epoch": 0.27, + "eval_loss": 1.5104212760925293, + "eval_runtime": 77.3448, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2587 + }, + { + "epoch": 0.27, + "learning_rate": 1.8262093175822685e-05, + "loss": 1.4889, + "step": 2588 + }, + { + "epoch": 0.27, + "learning_rate": 1.826003057198796e-05, + "loss": 1.4912, + "step": 2589 + }, + { + "epoch": 0.27, + "learning_rate": 1.825796686152137e-05, + "loss": 1.4884, + "step": 2590 + }, + { + "epoch": 0.27, + "learning_rate": 1.8255902044699404e-05, + "loss": 1.478, + "step": 2591 + }, + { + "epoch": 0.27, + "learning_rate": 1.8253836121798692e-05, + "loss": 1.6549, + "step": 2592 + }, + { + "epoch": 0.27, + "learning_rate": 1.8251769093096018e-05, + "loss": 1.5146, + "step": 2593 + }, + { + "epoch": 0.27, + "learning_rate": 1.8249700958868306e-05, + "loss": 1.4797, + "step": 2594 + }, + { + "epoch": 0.27, + "learning_rate": 1.8247631719392634e-05, + "loss": 1.4655, + "step": 2595 + }, + { + "epoch": 0.27, + "learning_rate": 1.824556137494623e-05, + "loss": 1.4517, + "step": 2596 + }, + { + "epoch": 0.27, + "learning_rate": 1.8243489925806458e-05, + "loss": 1.4936, + "step": 2597 + }, + { + "epoch": 0.27, + "learning_rate": 1.8241417372250852e-05, + "loss": 1.4614, + "step": 2598 + }, + { + "epoch": 0.27, + "learning_rate": 1.8239343714557073e-05, + "loss": 1.4475, + "step": 2599 + }, + { + "epoch": 0.27, + "learning_rate": 1.8237268953002937e-05, + "loss": 1.5435, + "step": 2600 + }, + { + "epoch": 0.27, + "learning_rate": 1.8235193087866413e-05, + "loss": 1.4616, + "step": 2601 + }, + { + "epoch": 0.27, + "learning_rate": 1.8233116119425612e-05, + "loss": 1.4578, + "step": 2602 + }, + { + "epoch": 0.27, + "learning_rate": 1.8231038047958795e-05, + "loss": 1.434, + "step": 2603 + }, + { + "epoch": 0.27, + "learning_rate": 1.8228958873744368e-05, + "loss": 1.5335, + "step": 2604 + }, + { + "epoch": 0.27, + "learning_rate": 1.8226878597060887e-05, + "loss": 1.415, + "step": 2605 + }, + { + "epoch": 0.27, + "learning_rate": 1.8224797218187058e-05, + "loss": 1.6165, + "step": 2606 + }, + { + "epoch": 0.27, + "learning_rate": 1.822271473740173e-05, + "loss": 1.372, + "step": 2607 + }, + { + "epoch": 0.27, + "learning_rate": 1.8220631154983907e-05, + "loss": 1.4855, + "step": 2608 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218546471212727e-05, + "loss": 1.4093, + "step": 2609 + }, + { + "epoch": 0.27, + "learning_rate": 1.821646068636749e-05, + "loss": 1.4852, + "step": 2610 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214373800727637e-05, + "loss": 1.6959, + "step": 2611 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212285814572755e-05, + "loss": 1.3874, + "step": 2612 + }, + { + "epoch": 0.27, + "learning_rate": 1.821019672818258e-05, + "loss": 1.4425, + "step": 2613 + }, + { + "epoch": 0.27, + "learning_rate": 1.8208106541837e-05, + "loss": 1.6097, + "step": 2614 + }, + { + "epoch": 0.27, + "learning_rate": 1.8206015255816045e-05, + "loss": 1.5675, + "step": 2615 + }, + { + "epoch": 0.27, + "learning_rate": 1.820392287039989e-05, + "loss": 1.4039, + "step": 2616 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201829385868866e-05, + "loss": 1.4872, + "step": 2617 + }, + { + "epoch": 0.27, + "learning_rate": 1.819973480250344e-05, + "loss": 1.4645, + "step": 2618 + }, + { + "epoch": 0.27, + "learning_rate": 1.8197639120584237e-05, + "loss": 1.4923, + "step": 2619 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195542340392025e-05, + "loss": 1.4294, + "step": 2620 + }, + { + "epoch": 0.27, + "learning_rate": 1.8193444462207717e-05, + "loss": 1.4315, + "step": 2621 + }, + { + "epoch": 0.27, + "learning_rate": 1.8191345486312372e-05, + "loss": 1.3972, + "step": 2622 + }, + { + "epoch": 0.28, + "learning_rate": 1.8189245412987205e-05, + "loss": 1.462, + "step": 2623 + }, + { + "epoch": 0.28, + "learning_rate": 1.8187144242513567e-05, + "loss": 1.4738, + "step": 2624 + }, + { + "epoch": 0.28, + "learning_rate": 1.818504197517296e-05, + "loss": 1.4935, + "step": 2625 + }, + { + "epoch": 0.28, + "learning_rate": 1.8182938611247038e-05, + "loss": 1.4231, + "step": 2626 + }, + { + "epoch": 0.28, + "learning_rate": 1.81808341510176e-05, + "loss": 1.4031, + "step": 2627 + }, + { + "epoch": 0.28, + "learning_rate": 1.817872859476658e-05, + "loss": 1.5822, + "step": 2628 + }, + { + "epoch": 0.28, + "learning_rate": 1.8176621942776075e-05, + "loss": 1.432, + "step": 2629 + }, + { + "epoch": 0.28, + "learning_rate": 1.8174514195328324e-05, + "loss": 1.5565, + "step": 2630 + }, + { + "epoch": 0.28, + "learning_rate": 1.8172405352705704e-05, + "loss": 1.4895, + "step": 2631 + }, + { + "epoch": 0.28, + "learning_rate": 1.8170295415190754e-05, + "loss": 1.4032, + "step": 2632 + }, + { + "epoch": 0.28, + "learning_rate": 1.8168184383066144e-05, + "loss": 1.4253, + "step": 2633 + }, + { + "epoch": 0.28, + "learning_rate": 1.8166072256614702e-05, + "loss": 1.5162, + "step": 2634 + }, + { + "epoch": 0.28, + "learning_rate": 1.81639590361194e-05, + "loss": 1.4609, + "step": 2635 + }, + { + "epoch": 0.28, + "learning_rate": 1.816184472186335e-05, + "loss": 1.4351, + "step": 2636 + }, + { + "epoch": 0.28, + "learning_rate": 1.8159729314129823e-05, + "loss": 1.4738, + "step": 2637 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157612813202224e-05, + "loss": 1.5986, + "step": 2638 + }, + { + "epoch": 0.28, + "learning_rate": 1.815549521936411e-05, + "loss": 1.4633, + "step": 2639 + }, + { + "epoch": 0.28, + "learning_rate": 1.8153376532899184e-05, + "loss": 1.4404, + "step": 2640 + }, + { + "epoch": 0.28, + "learning_rate": 1.81512567540913e-05, + "loss": 1.4256, + "step": 2641 + }, + { + "epoch": 0.28, + "learning_rate": 1.814913588322445e-05, + "loss": 1.4054, + "step": 2642 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147013920582773e-05, + "loss": 1.4134, + "step": 2643 + }, + { + "epoch": 0.28, + "learning_rate": 1.8144890866450567e-05, + "loss": 1.4098, + "step": 2644 + }, + { + "epoch": 0.28, + "learning_rate": 1.814276672111226e-05, + "loss": 1.4593, + "step": 2645 + }, + { + "epoch": 0.28, + "learning_rate": 1.814064148485243e-05, + "loss": 1.4679, + "step": 2646 + }, + { + "epoch": 0.28, + "learning_rate": 1.8138515157955812e-05, + "loss": 1.5234, + "step": 2647 + }, + { + "epoch": 0.28, + "learning_rate": 1.8136387740707272e-05, + "loss": 1.4568, + "step": 2648 + }, + { + "epoch": 0.28, + "learning_rate": 1.8134259233391836e-05, + "loss": 1.5057, + "step": 2649 + }, + { + "epoch": 0.28, + "learning_rate": 1.8132129636294665e-05, + "loss": 1.3643, + "step": 2650 + }, + { + "epoch": 0.28, + "learning_rate": 1.812999894970107e-05, + "loss": 1.4766, + "step": 2651 + }, + { + "epoch": 0.28, + "learning_rate": 1.812786717389651e-05, + "loss": 1.5701, + "step": 2652 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125734309166587e-05, + "loss": 1.5341, + "step": 2653 + }, + { + "epoch": 0.28, + "learning_rate": 1.812360035579705e-05, + "loss": 1.3596, + "step": 2654 + }, + { + "epoch": 0.28, + "learning_rate": 1.8121465314073793e-05, + "loss": 1.4847, + "step": 2655 + }, + { + "epoch": 0.28, + "learning_rate": 1.811932918428286e-05, + "loss": 1.4664, + "step": 2656 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117191966710438e-05, + "loss": 1.4673, + "step": 2657 + }, + { + "epoch": 0.28, + "learning_rate": 1.8115053661642856e-05, + "loss": 1.4712, + "step": 2658 + }, + { + "epoch": 0.28, + "learning_rate": 1.811291426936659e-05, + "loss": 1.4458, + "step": 2659 + }, + { + "epoch": 0.28, + "learning_rate": 1.811077379016827e-05, + "loss": 1.4667, + "step": 2660 + }, + { + "epoch": 0.28, + "learning_rate": 1.810863222433466e-05, + "loss": 1.4695, + "step": 2661 + }, + { + "epoch": 0.28, + "learning_rate": 1.8106489572152677e-05, + "loss": 1.5263, + "step": 2662 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104345833909376e-05, + "loss": 1.4148, + "step": 2663 + }, + { + "epoch": 0.28, + "learning_rate": 1.8102201009891976e-05, + "loss": 1.3955, + "step": 2664 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100055100387814e-05, + "loss": 1.6056, + "step": 2665 + }, + { + "epoch": 0.28, + "learning_rate": 1.8097908105684396e-05, + "loss": 1.5394, + "step": 2666 + }, + { + "epoch": 0.28, + "learning_rate": 1.809576002606936e-05, + "loss": 1.479, + "step": 2667 + }, + { + "epoch": 0.28, + "learning_rate": 1.8093610861830494e-05, + "loss": 1.4492, + "step": 2668 + }, + { + "epoch": 0.28, + "learning_rate": 1.8091460613255728e-05, + "loss": 1.4172, + "step": 2669 + }, + { + "epoch": 0.28, + "learning_rate": 1.808930928063315e-05, + "loss": 1.4498, + "step": 2670 + }, + { + "epoch": 0.28, + "learning_rate": 1.808715686425097e-05, + "loss": 1.6203, + "step": 2671 + }, + { + "epoch": 0.28, + "learning_rate": 1.8085003364397567e-05, + "loss": 1.435, + "step": 2672 + }, + { + "epoch": 0.28, + "learning_rate": 1.808284878136145e-05, + "loss": 1.4489, + "step": 2673 + }, + { + "epoch": 0.28, + "learning_rate": 1.8080693115431277e-05, + "loss": 1.4416, + "step": 2674 + }, + { + "epoch": 0.28, + "learning_rate": 1.8078536366895853e-05, + "loss": 1.422, + "step": 2675 + }, + { + "epoch": 0.28, + "learning_rate": 1.8076378536044128e-05, + "loss": 1.4039, + "step": 2676 + }, + { + "epoch": 0.28, + "learning_rate": 1.8074219623165195e-05, + "loss": 1.4705, + "step": 2677 + }, + { + "epoch": 0.28, + "learning_rate": 1.807205962854829e-05, + "loss": 1.5031, + "step": 2678 + }, + { + "epoch": 0.28, + "learning_rate": 1.8069898552482806e-05, + "loss": 1.4812, + "step": 2679 + }, + { + "epoch": 0.28, + "learning_rate": 1.806773639525826e-05, + "loss": 1.4129, + "step": 2680 + }, + { + "epoch": 0.28, + "learning_rate": 1.8065573157164332e-05, + "loss": 1.4559, + "step": 2681 + }, + { + "epoch": 0.28, + "learning_rate": 1.806340883849084e-05, + "loss": 1.3878, + "step": 2682 + }, + { + "epoch": 0.28, + "learning_rate": 1.8061243439527744e-05, + "loss": 1.4752, + "step": 2683 + }, + { + "epoch": 0.28, + "learning_rate": 1.8059076960565156e-05, + "loss": 1.4089, + "step": 2684 + }, + { + "epoch": 0.28, + "learning_rate": 1.8056909401893326e-05, + "loss": 1.4736, + "step": 2685 + }, + { + "epoch": 0.28, + "learning_rate": 1.8054740763802654e-05, + "loss": 1.3796, + "step": 2686 + }, + { + "epoch": 0.28, + "learning_rate": 1.805257104658368e-05, + "loss": 1.4412, + "step": 2687 + }, + { + "epoch": 0.28, + "learning_rate": 1.8050400250527086e-05, + "loss": 1.4639, + "step": 2688 + }, + { + "epoch": 0.28, + "learning_rate": 1.804822837592371e-05, + "loss": 1.4076, + "step": 2689 + }, + { + "epoch": 0.28, + "learning_rate": 1.804605542306452e-05, + "loss": 1.4627, + "step": 2690 + }, + { + "epoch": 0.28, + "learning_rate": 1.8043881392240642e-05, + "loss": 1.5249, + "step": 2691 + }, + { + "epoch": 0.28, + "learning_rate": 1.804170628374334e-05, + "loss": 1.4312, + "step": 2692 + }, + { + "epoch": 0.28, + "learning_rate": 1.803953009786402e-05, + "loss": 1.5676, + "step": 2693 + }, + { + "epoch": 0.28, + "learning_rate": 1.8037352834894233e-05, + "loss": 1.5072, + "step": 2694 + }, + { + "epoch": 0.28, + "learning_rate": 1.803517449512568e-05, + "loss": 1.5662, + "step": 2695 + }, + { + "epoch": 0.28, + "learning_rate": 1.8032995078850207e-05, + "loss": 1.4771, + "step": 2696 + }, + { + "epoch": 0.28, + "learning_rate": 1.803081458635979e-05, + "loss": 1.412, + "step": 2697 + }, + { + "epoch": 0.28, + "learning_rate": 1.8028633017946564e-05, + "loss": 1.497, + "step": 2698 + }, + { + "epoch": 0.28, + "learning_rate": 1.8026450373902804e-05, + "loss": 1.4528, + "step": 2699 + }, + { + "epoch": 0.28, + "learning_rate": 1.802426665452093e-05, + "loss": 1.4785, + "step": 2700 + }, + { + "epoch": 0.28, + "learning_rate": 1.8022081860093493e-05, + "loss": 1.6411, + "step": 2701 + }, + { + "epoch": 0.28, + "learning_rate": 1.8019895990913213e-05, + "loss": 1.4459, + "step": 2702 + }, + { + "epoch": 0.28, + "learning_rate": 1.8017709047272932e-05, + "loss": 1.4418, + "step": 2703 + }, + { + "epoch": 0.28, + "learning_rate": 1.801552102946565e-05, + "loss": 1.4409, + "step": 2704 + }, + { + "epoch": 0.28, + "learning_rate": 1.8013331937784498e-05, + "loss": 1.4651, + "step": 2705 + }, + { + "epoch": 0.28, + "learning_rate": 1.8011141772522766e-05, + "loss": 1.4161, + "step": 2706 + }, + { + "epoch": 0.28, + "learning_rate": 1.8008950533973876e-05, + "loss": 1.458, + "step": 2707 + }, + { + "epoch": 0.28, + "learning_rate": 1.8006758222431398e-05, + "loss": 1.4477, + "step": 2708 + }, + { + "epoch": 0.28, + "learning_rate": 1.800456483818904e-05, + "loss": 1.4433, + "step": 2709 + }, + { + "epoch": 0.28, + "learning_rate": 1.8002370381540672e-05, + "loss": 1.5005, + "step": 2710 + }, + { + "epoch": 0.28, + "learning_rate": 1.8000174852780282e-05, + "loss": 1.4945, + "step": 2711 + }, + { + "epoch": 0.28, + "learning_rate": 1.7997978252202023e-05, + "loss": 1.4298, + "step": 2712 + }, + { + "epoch": 0.28, + "learning_rate": 1.7995780580100177e-05, + "loss": 1.3812, + "step": 2713 + }, + { + "epoch": 0.28, + "learning_rate": 1.799358183676918e-05, + "loss": 1.5559, + "step": 2714 + }, + { + "epoch": 0.28, + "learning_rate": 1.79913820225036e-05, + "loss": 1.4316, + "step": 2715 + }, + { + "epoch": 0.28, + "learning_rate": 1.798918113759817e-05, + "loss": 1.419, + "step": 2716 + }, + { + "epoch": 0.28, + "learning_rate": 1.7986979182347733e-05, + "loss": 1.43, + "step": 2717 + }, + { + "epoch": 0.29, + "learning_rate": 1.798477615704731e-05, + "loss": 1.4964, + "step": 2718 + }, + { + "epoch": 0.29, + "learning_rate": 1.7982572061992044e-05, + "loss": 1.4417, + "step": 2719 + }, + { + "epoch": 0.29, + "learning_rate": 1.7980366897477227e-05, + "loss": 1.4562, + "step": 2720 + }, + { + "epoch": 0.29, + "learning_rate": 1.7978160663798295e-05, + "loss": 1.4386, + "step": 2721 + }, + { + "epoch": 0.29, + "learning_rate": 1.7975953361250824e-05, + "loss": 1.445, + "step": 2722 + }, + { + "epoch": 0.29, + "learning_rate": 1.797374499013054e-05, + "loss": 1.4549, + "step": 2723 + }, + { + "epoch": 0.29, + "learning_rate": 1.7971535550733305e-05, + "loss": 1.5205, + "step": 2724 + }, + { + "epoch": 0.29, + "learning_rate": 1.796932504335513e-05, + "loss": 1.4632, + "step": 2725 + }, + { + "epoch": 0.29, + "learning_rate": 1.796711346829216e-05, + "loss": 1.3767, + "step": 2726 + }, + { + "epoch": 0.29, + "learning_rate": 1.79649008258407e-05, + "loss": 1.4098, + "step": 2727 + }, + { + "epoch": 0.29, + "learning_rate": 1.7962687116297178e-05, + "loss": 1.4675, + "step": 2728 + }, + { + "epoch": 0.29, + "learning_rate": 1.7960472339958176e-05, + "loss": 1.6048, + "step": 2729 + }, + { + "epoch": 0.29, + "learning_rate": 1.7958256497120418e-05, + "loss": 1.5432, + "step": 2730 + }, + { + "epoch": 0.29, + "learning_rate": 1.7956039588080774e-05, + "loss": 1.5453, + "step": 2731 + }, + { + "epoch": 0.29, + "learning_rate": 1.7953821613136246e-05, + "loss": 1.4246, + "step": 2732 + }, + { + "epoch": 0.29, + "learning_rate": 1.7951602572583988e-05, + "loss": 1.3987, + "step": 2733 + }, + { + "epoch": 0.29, + "learning_rate": 1.7949382466721295e-05, + "loss": 1.4943, + "step": 2734 + }, + { + "epoch": 0.29, + "learning_rate": 1.7947161295845606e-05, + "loss": 1.4385, + "step": 2735 + }, + { + "epoch": 0.29, + "learning_rate": 1.7944939060254497e-05, + "loss": 1.4165, + "step": 2736 + }, + { + "epoch": 0.29, + "learning_rate": 1.7942715760245692e-05, + "loss": 1.4004, + "step": 2737 + }, + { + "epoch": 0.29, + "learning_rate": 1.7940491396117063e-05, + "loss": 1.4577, + "step": 2738 + }, + { + "epoch": 0.29, + "learning_rate": 1.7938265968166602e-05, + "loss": 1.4649, + "step": 2739 + }, + { + "epoch": 0.29, + "learning_rate": 1.7936039476692473e-05, + "loss": 1.5273, + "step": 2740 + }, + { + "epoch": 0.29, + "learning_rate": 1.7933811921992962e-05, + "loss": 1.4325, + "step": 2741 + }, + { + "epoch": 0.29, + "learning_rate": 1.793158330436651e-05, + "loss": 1.4388, + "step": 2742 + }, + { + "epoch": 0.29, + "learning_rate": 1.7929353624111687e-05, + "loss": 1.4124, + "step": 2743 + }, + { + "epoch": 0.29, + "learning_rate": 1.7927122881527222e-05, + "loss": 1.5449, + "step": 2744 + }, + { + "epoch": 0.29, + "learning_rate": 1.7924891076911964e-05, + "loss": 1.4728, + "step": 2745 + }, + { + "epoch": 0.29, + "learning_rate": 1.7922658210564932e-05, + "loss": 1.5103, + "step": 2746 + }, + { + "epoch": 0.29, + "learning_rate": 1.792042428278526e-05, + "loss": 1.5975, + "step": 2747 + }, + { + "epoch": 0.29, + "learning_rate": 1.7918189293872247e-05, + "loss": 1.567, + "step": 2748 + }, + { + "epoch": 0.29, + "learning_rate": 1.7915953244125318e-05, + "loss": 1.57, + "step": 2749 + }, + { + "epoch": 0.29, + "learning_rate": 1.791371613384405e-05, + "loss": 1.4372, + "step": 2750 + }, + { + "epoch": 0.29, + "learning_rate": 1.7911477963328155e-05, + "loss": 1.4053, + "step": 2751 + }, + { + "epoch": 0.29, + "learning_rate": 1.7909238732877492e-05, + "loss": 1.3782, + "step": 2752 + }, + { + "epoch": 0.29, + "learning_rate": 1.790699844279206e-05, + "loss": 1.4401, + "step": 2753 + }, + { + "epoch": 0.29, + "learning_rate": 1.7904757093372e-05, + "loss": 1.3749, + "step": 2754 + }, + { + "epoch": 0.29, + "learning_rate": 1.79025146849176e-05, + "loss": 1.4909, + "step": 2755 + }, + { + "epoch": 0.29, + "learning_rate": 1.7900271217729273e-05, + "loss": 1.4103, + "step": 2756 + }, + { + "epoch": 0.29, + "learning_rate": 1.7898026692107597e-05, + "loss": 1.4986, + "step": 2757 + }, + { + "epoch": 0.29, + "learning_rate": 1.7895781108353278e-05, + "loss": 1.5449, + "step": 2758 + }, + { + "epoch": 0.29, + "learning_rate": 1.789353446676717e-05, + "loss": 1.5583, + "step": 2759 + }, + { + "epoch": 0.29, + "learning_rate": 1.7891286767650254e-05, + "loss": 1.5342, + "step": 2760 + }, + { + "epoch": 0.29, + "learning_rate": 1.7889038011303673e-05, + "loss": 1.4233, + "step": 2761 + }, + { + "epoch": 0.29, + "learning_rate": 1.7886788198028707e-05, + "loss": 1.3433, + "step": 2762 + }, + { + "epoch": 0.29, + "learning_rate": 1.788453732812676e-05, + "loss": 1.4451, + "step": 2763 + }, + { + "epoch": 0.29, + "learning_rate": 1.78822854018994e-05, + "loss": 1.4506, + "step": 2764 + }, + { + "epoch": 0.29, + "learning_rate": 1.7880032419648324e-05, + "loss": 1.4386, + "step": 2765 + }, + { + "epoch": 0.29, + "learning_rate": 1.7877778381675374e-05, + "loss": 1.4512, + "step": 2766 + }, + { + "epoch": 0.29, + "learning_rate": 1.7875523288282535e-05, + "loss": 1.4319, + "step": 2767 + }, + { + "epoch": 0.29, + "learning_rate": 1.7873267139771932e-05, + "loss": 1.4753, + "step": 2768 + }, + { + "epoch": 0.29, + "learning_rate": 1.787100993644583e-05, + "loss": 1.4044, + "step": 2769 + }, + { + "epoch": 0.29, + "learning_rate": 1.786875167860663e-05, + "loss": 1.4382, + "step": 2770 + }, + { + "epoch": 0.29, + "learning_rate": 1.786649236655689e-05, + "loss": 1.3977, + "step": 2771 + }, + { + "epoch": 0.29, + "learning_rate": 1.7864232000599298e-05, + "loss": 1.4473, + "step": 2772 + }, + { + "epoch": 0.29, + "learning_rate": 1.7861970581036678e-05, + "loss": 1.4666, + "step": 2773 + }, + { + "epoch": 0.29, + "learning_rate": 1.785970810817201e-05, + "loss": 1.5299, + "step": 2774 + }, + { + "epoch": 0.29, + "learning_rate": 1.7857444582308402e-05, + "loss": 1.3974, + "step": 2775 + }, + { + "epoch": 0.29, + "learning_rate": 1.7855180003749114e-05, + "loss": 1.4603, + "step": 2776 + }, + { + "epoch": 0.29, + "learning_rate": 1.7852914372797535e-05, + "loss": 1.463, + "step": 2777 + }, + { + "epoch": 0.29, + "learning_rate": 1.7850647689757205e-05, + "loss": 1.5317, + "step": 2778 + }, + { + "epoch": 0.29, + "learning_rate": 1.78483799549318e-05, + "loss": 1.4669, + "step": 2779 + }, + { + "epoch": 0.29, + "learning_rate": 1.784611116862514e-05, + "loss": 1.5293, + "step": 2780 + }, + { + "epoch": 0.29, + "learning_rate": 1.7843841331141177e-05, + "loss": 1.5802, + "step": 2781 + }, + { + "epoch": 0.29, + "learning_rate": 1.7841570442784024e-05, + "loss": 1.4486, + "step": 2782 + }, + { + "epoch": 0.29, + "learning_rate": 1.7839298503857913e-05, + "loss": 1.4674, + "step": 2783 + }, + { + "epoch": 0.29, + "learning_rate": 1.7837025514667224e-05, + "loss": 1.4662, + "step": 2784 + }, + { + "epoch": 0.29, + "learning_rate": 1.7834751475516484e-05, + "loss": 1.3555, + "step": 2785 + }, + { + "epoch": 0.29, + "learning_rate": 1.783247638671035e-05, + "loss": 1.4307, + "step": 2786 + }, + { + "epoch": 0.29, + "eval_loss": 1.500258445739746, + "eval_runtime": 77.406, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 2786 + }, + { + "epoch": 0.29, + "learning_rate": 1.7830200248553633e-05, + "loss": 1.4596, + "step": 2787 + }, + { + "epoch": 0.29, + "learning_rate": 1.7827923061351273e-05, + "loss": 1.6118, + "step": 2788 + }, + { + "epoch": 0.29, + "learning_rate": 1.7825644825408353e-05, + "loss": 1.4782, + "step": 2789 + }, + { + "epoch": 0.29, + "learning_rate": 1.78233655410301e-05, + "loss": 1.4681, + "step": 2790 + }, + { + "epoch": 0.29, + "learning_rate": 1.782108520852188e-05, + "loss": 1.6281, + "step": 2791 + }, + { + "epoch": 0.29, + "learning_rate": 1.78188038281892e-05, + "loss": 1.4446, + "step": 2792 + }, + { + "epoch": 0.29, + "learning_rate": 1.7816521400337704e-05, + "loss": 1.479, + "step": 2793 + }, + { + "epoch": 0.29, + "learning_rate": 1.7814237925273178e-05, + "loss": 1.5457, + "step": 2794 + }, + { + "epoch": 0.29, + "learning_rate": 1.7811953403301547e-05, + "loss": 1.3928, + "step": 2795 + }, + { + "epoch": 0.29, + "learning_rate": 1.780966783472889e-05, + "loss": 1.4321, + "step": 2796 + }, + { + "epoch": 0.29, + "learning_rate": 1.78073812198614e-05, + "loss": 1.5734, + "step": 2797 + }, + { + "epoch": 0.29, + "learning_rate": 1.7805093559005432e-05, + "loss": 1.4356, + "step": 2798 + }, + { + "epoch": 0.29, + "learning_rate": 1.7802804852467473e-05, + "loss": 1.4656, + "step": 2799 + }, + { + "epoch": 0.29, + "learning_rate": 1.780051510055415e-05, + "loss": 1.4052, + "step": 2800 + }, + { + "epoch": 0.29, + "learning_rate": 1.7798224303572228e-05, + "loss": 1.4758, + "step": 2801 + }, + { + "epoch": 0.29, + "learning_rate": 1.7795932461828622e-05, + "loss": 1.4326, + "step": 2802 + }, + { + "epoch": 0.29, + "learning_rate": 1.7793639575630376e-05, + "loss": 1.3409, + "step": 2803 + }, + { + "epoch": 0.29, + "learning_rate": 1.7791345645284678e-05, + "loss": 1.4175, + "step": 2804 + }, + { + "epoch": 0.29, + "learning_rate": 1.7789050671098853e-05, + "loss": 1.383, + "step": 2805 + }, + { + "epoch": 0.29, + "learning_rate": 1.7786754653380373e-05, + "loss": 1.5162, + "step": 2806 + }, + { + "epoch": 0.29, + "learning_rate": 1.7784457592436847e-05, + "loss": 1.4899, + "step": 2807 + }, + { + "epoch": 0.29, + "learning_rate": 1.7782159488576016e-05, + "loss": 1.4874, + "step": 2808 + }, + { + "epoch": 0.29, + "learning_rate": 1.777986034210577e-05, + "loss": 1.4363, + "step": 2809 + }, + { + "epoch": 0.29, + "learning_rate": 1.7777560153334134e-05, + "loss": 1.4223, + "step": 2810 + }, + { + "epoch": 0.29, + "learning_rate": 1.7775258922569273e-05, + "loss": 1.4792, + "step": 2811 + }, + { + "epoch": 0.29, + "learning_rate": 1.77729566501195e-05, + "loss": 1.4475, + "step": 2812 + }, + { + "epoch": 0.29, + "learning_rate": 1.7770653336293253e-05, + "loss": 1.5157, + "step": 2813 + }, + { + "epoch": 0.3, + "learning_rate": 1.776834898139912e-05, + "loss": 1.389, + "step": 2814 + }, + { + "epoch": 0.3, + "learning_rate": 1.7766043585745824e-05, + "loss": 1.4358, + "step": 2815 + }, + { + "epoch": 0.3, + "learning_rate": 1.776373714964223e-05, + "loss": 1.4297, + "step": 2816 + }, + { + "epoch": 0.3, + "learning_rate": 1.7761429673397344e-05, + "loss": 1.4102, + "step": 2817 + }, + { + "epoch": 0.3, + "learning_rate": 1.77591211573203e-05, + "loss": 1.4572, + "step": 2818 + }, + { + "epoch": 0.3, + "learning_rate": 1.775681160172039e-05, + "loss": 1.448, + "step": 2819 + }, + { + "epoch": 0.3, + "learning_rate": 1.7754501006907025e-05, + "loss": 1.4426, + "step": 2820 + }, + { + "epoch": 0.3, + "learning_rate": 1.7752189373189773e-05, + "loss": 1.4566, + "step": 2821 + }, + { + "epoch": 0.3, + "learning_rate": 1.7749876700878332e-05, + "loss": 1.4267, + "step": 2822 + }, + { + "epoch": 0.3, + "learning_rate": 1.7747562990282538e-05, + "loss": 1.3951, + "step": 2823 + }, + { + "epoch": 0.3, + "learning_rate": 1.7745248241712373e-05, + "loss": 1.4668, + "step": 2824 + }, + { + "epoch": 0.3, + "learning_rate": 1.774293245547795e-05, + "loss": 1.4924, + "step": 2825 + }, + { + "epoch": 0.3, + "learning_rate": 1.7740615631889525e-05, + "loss": 1.5258, + "step": 2826 + }, + { + "epoch": 0.3, + "learning_rate": 1.7738297771257496e-05, + "loss": 1.4323, + "step": 2827 + }, + { + "epoch": 0.3, + "learning_rate": 1.7735978873892393e-05, + "loss": 1.439, + "step": 2828 + }, + { + "epoch": 0.3, + "learning_rate": 1.773365894010489e-05, + "loss": 1.5658, + "step": 2829 + }, + { + "epoch": 0.3, + "learning_rate": 1.77313379702058e-05, + "loss": 1.4607, + "step": 2830 + }, + { + "epoch": 0.3, + "learning_rate": 1.7729015964506073e-05, + "loss": 1.5544, + "step": 2831 + }, + { + "epoch": 0.3, + "learning_rate": 1.7726692923316798e-05, + "loss": 1.4232, + "step": 2832 + }, + { + "epoch": 0.3, + "learning_rate": 1.77243688469492e-05, + "loss": 1.415, + "step": 2833 + }, + { + "epoch": 0.3, + "learning_rate": 1.772204373571465e-05, + "loss": 1.4658, + "step": 2834 + }, + { + "epoch": 0.3, + "learning_rate": 1.7719717589924647e-05, + "loss": 1.4678, + "step": 2835 + }, + { + "epoch": 0.3, + "learning_rate": 1.771739040989084e-05, + "loss": 1.3021, + "step": 2836 + }, + { + "epoch": 0.3, + "learning_rate": 1.771506219592501e-05, + "loss": 1.4045, + "step": 2837 + }, + { + "epoch": 0.3, + "learning_rate": 1.7712732948339085e-05, + "loss": 1.4593, + "step": 2838 + }, + { + "epoch": 0.3, + "learning_rate": 1.7710402667445108e-05, + "loss": 1.4175, + "step": 2839 + }, + { + "epoch": 0.3, + "learning_rate": 1.770807135355529e-05, + "loss": 1.3939, + "step": 2840 + }, + { + "epoch": 0.3, + "learning_rate": 1.7705739006981963e-05, + "loss": 1.6089, + "step": 2841 + }, + { + "epoch": 0.3, + "learning_rate": 1.77034056280376e-05, + "loss": 1.3952, + "step": 2842 + }, + { + "epoch": 0.3, + "learning_rate": 1.7701071217034818e-05, + "loss": 1.5086, + "step": 2843 + }, + { + "epoch": 0.3, + "learning_rate": 1.7698735774286362e-05, + "loss": 1.4706, + "step": 2844 + }, + { + "epoch": 0.3, + "learning_rate": 1.7696399300105128e-05, + "loss": 1.4286, + "step": 2845 + }, + { + "epoch": 0.3, + "learning_rate": 1.7694061794804137e-05, + "loss": 1.4418, + "step": 2846 + }, + { + "epoch": 0.3, + "learning_rate": 1.7691723258696562e-05, + "loss": 1.516, + "step": 2847 + }, + { + "epoch": 0.3, + "learning_rate": 1.76893836920957e-05, + "loss": 1.4354, + "step": 2848 + }, + { + "epoch": 0.3, + "learning_rate": 1.7687043095314998e-05, + "loss": 1.7503, + "step": 2849 + }, + { + "epoch": 0.3, + "learning_rate": 1.7684701468668032e-05, + "loss": 1.5985, + "step": 2850 + }, + { + "epoch": 0.3, + "learning_rate": 1.768235881246852e-05, + "loss": 1.442, + "step": 2851 + }, + { + "epoch": 0.3, + "learning_rate": 1.7680015127030322e-05, + "loss": 1.4924, + "step": 2852 + }, + { + "epoch": 0.3, + "learning_rate": 1.7677670412667425e-05, + "loss": 1.4461, + "step": 2853 + }, + { + "epoch": 0.3, + "learning_rate": 1.7675324669693968e-05, + "loss": 1.3823, + "step": 2854 + }, + { + "epoch": 0.3, + "learning_rate": 1.767297789842421e-05, + "loss": 1.452, + "step": 2855 + }, + { + "epoch": 0.3, + "learning_rate": 1.767063009917257e-05, + "loss": 1.46, + "step": 2856 + }, + { + "epoch": 0.3, + "learning_rate": 1.7668281272253587e-05, + "loss": 1.4129, + "step": 2857 + }, + { + "epoch": 0.3, + "learning_rate": 1.766593141798194e-05, + "loss": 1.4057, + "step": 2858 + }, + { + "epoch": 0.3, + "learning_rate": 1.7663580536672456e-05, + "loss": 1.5162, + "step": 2859 + }, + { + "epoch": 0.3, + "learning_rate": 1.7661228628640087e-05, + "loss": 1.5177, + "step": 2860 + }, + { + "epoch": 0.3, + "learning_rate": 1.7658875694199933e-05, + "loss": 1.4548, + "step": 2861 + }, + { + "epoch": 0.3, + "learning_rate": 1.7656521733667223e-05, + "loss": 1.4511, + "step": 2862 + }, + { + "epoch": 0.3, + "learning_rate": 1.765416674735733e-05, + "loss": 1.4778, + "step": 2863 + }, + { + "epoch": 0.3, + "learning_rate": 1.765181073558576e-05, + "loss": 1.3935, + "step": 2864 + }, + { + "epoch": 0.3, + "learning_rate": 1.7649453698668156e-05, + "loss": 1.4659, + "step": 2865 + }, + { + "epoch": 0.3, + "learning_rate": 1.7647095636920305e-05, + "loss": 1.7042, + "step": 2866 + }, + { + "epoch": 0.3, + "learning_rate": 1.7644736550658124e-05, + "loss": 1.7957, + "step": 2867 + }, + { + "epoch": 0.3, + "learning_rate": 1.764237644019767e-05, + "loss": 1.5139, + "step": 2868 + }, + { + "epoch": 0.3, + "learning_rate": 1.764001530585514e-05, + "loss": 1.4117, + "step": 2869 + }, + { + "epoch": 0.3, + "learning_rate": 1.7637653147946858e-05, + "loss": 1.4837, + "step": 2870 + }, + { + "epoch": 0.3, + "learning_rate": 1.7635289966789298e-05, + "loss": 1.4379, + "step": 2871 + }, + { + "epoch": 0.3, + "learning_rate": 1.7632925762699068e-05, + "loss": 1.4491, + "step": 2872 + }, + { + "epoch": 0.3, + "learning_rate": 1.7630560535992905e-05, + "loss": 1.4006, + "step": 2873 + }, + { + "epoch": 0.3, + "learning_rate": 1.7628194286987694e-05, + "loss": 1.5484, + "step": 2874 + }, + { + "epoch": 0.3, + "learning_rate": 1.7625827016000446e-05, + "loss": 1.4926, + "step": 2875 + }, + { + "epoch": 0.3, + "learning_rate": 1.762345872334832e-05, + "loss": 1.3909, + "step": 2876 + }, + { + "epoch": 0.3, + "learning_rate": 1.76210894093486e-05, + "loss": 1.405, + "step": 2877 + }, + { + "epoch": 0.3, + "learning_rate": 1.7618719074318718e-05, + "loss": 1.4736, + "step": 2878 + }, + { + "epoch": 0.3, + "learning_rate": 1.7616347718576238e-05, + "loss": 1.4445, + "step": 2879 + }, + { + "epoch": 0.3, + "learning_rate": 1.761397534243886e-05, + "loss": 1.4878, + "step": 2880 + }, + { + "epoch": 0.3, + "learning_rate": 1.7611601946224417e-05, + "loss": 1.4414, + "step": 2881 + }, + { + "epoch": 0.3, + "learning_rate": 1.760922753025089e-05, + "loss": 1.5657, + "step": 2882 + }, + { + "epoch": 0.3, + "learning_rate": 1.7606852094836385e-05, + "loss": 1.5008, + "step": 2883 + }, + { + "epoch": 0.3, + "learning_rate": 1.7604475640299153e-05, + "loss": 1.4922, + "step": 2884 + }, + { + "epoch": 0.3, + "learning_rate": 1.7602098166957577e-05, + "loss": 1.7451, + "step": 2885 + }, + { + "epoch": 0.3, + "learning_rate": 1.759971967513017e-05, + "loss": 1.7077, + "step": 2886 + }, + { + "epoch": 0.3, + "learning_rate": 1.75973401651356e-05, + "loss": 1.3986, + "step": 2887 + }, + { + "epoch": 0.3, + "learning_rate": 1.7594959637292656e-05, + "loss": 1.3966, + "step": 2888 + }, + { + "epoch": 0.3, + "learning_rate": 1.7592578091920264e-05, + "loss": 1.4086, + "step": 2889 + }, + { + "epoch": 0.3, + "learning_rate": 1.7590195529337495e-05, + "loss": 1.4481, + "step": 2890 + }, + { + "epoch": 0.3, + "learning_rate": 1.7587811949863548e-05, + "loss": 1.3974, + "step": 2891 + }, + { + "epoch": 0.3, + "learning_rate": 1.7585427353817758e-05, + "loss": 1.5013, + "step": 2892 + }, + { + "epoch": 0.3, + "learning_rate": 1.7583041741519608e-05, + "loss": 1.5454, + "step": 2893 + }, + { + "epoch": 0.3, + "learning_rate": 1.7580655113288708e-05, + "loss": 1.5033, + "step": 2894 + }, + { + "epoch": 0.3, + "learning_rate": 1.7578267469444793e-05, + "loss": 1.4332, + "step": 2895 + }, + { + "epoch": 0.3, + "learning_rate": 1.757587881030776e-05, + "loss": 1.4667, + "step": 2896 + }, + { + "epoch": 0.3, + "learning_rate": 1.7573489136197623e-05, + "loss": 1.4314, + "step": 2897 + }, + { + "epoch": 0.3, + "learning_rate": 1.7571098447434532e-05, + "loss": 1.4514, + "step": 2898 + }, + { + "epoch": 0.3, + "learning_rate": 1.7568706744338784e-05, + "loss": 1.4872, + "step": 2899 + }, + { + "epoch": 0.3, + "learning_rate": 1.7566314027230808e-05, + "loss": 1.4841, + "step": 2900 + }, + { + "epoch": 0.3, + "learning_rate": 1.7563920296431158e-05, + "loss": 1.3964, + "step": 2901 + }, + { + "epoch": 0.3, + "learning_rate": 1.7561525552260538e-05, + "loss": 1.4932, + "step": 2902 + }, + { + "epoch": 0.3, + "learning_rate": 1.755912979503978e-05, + "loss": 1.4153, + "step": 2903 + }, + { + "epoch": 0.3, + "learning_rate": 1.755673302508986e-05, + "loss": 1.4939, + "step": 2904 + }, + { + "epoch": 0.3, + "learning_rate": 1.755433524273187e-05, + "loss": 1.4437, + "step": 2905 + }, + { + "epoch": 0.3, + "learning_rate": 1.7551936448287067e-05, + "loss": 1.486, + "step": 2906 + }, + { + "epoch": 0.3, + "learning_rate": 1.754953664207682e-05, + "loss": 1.4362, + "step": 2907 + }, + { + "epoch": 0.3, + "learning_rate": 1.7547135824422635e-05, + "loss": 1.4954, + "step": 2908 + }, + { + "epoch": 0.31, + "learning_rate": 1.7544733995646174e-05, + "loss": 1.4552, + "step": 2909 + }, + { + "epoch": 0.31, + "learning_rate": 1.7542331156069213e-05, + "loss": 1.4654, + "step": 2910 + }, + { + "epoch": 0.31, + "learning_rate": 1.753992730601367e-05, + "loss": 1.4531, + "step": 2911 + }, + { + "epoch": 0.31, + "learning_rate": 1.75375224458016e-05, + "loss": 1.4949, + "step": 2912 + }, + { + "epoch": 0.31, + "learning_rate": 1.753511657575519e-05, + "loss": 1.3998, + "step": 2913 + }, + { + "epoch": 0.31, + "learning_rate": 1.753270969619677e-05, + "loss": 1.3904, + "step": 2914 + }, + { + "epoch": 0.31, + "learning_rate": 1.7530301807448794e-05, + "loss": 1.481, + "step": 2915 + }, + { + "epoch": 0.31, + "learning_rate": 1.7527892909833864e-05, + "loss": 1.4301, + "step": 2916 + }, + { + "epoch": 0.31, + "learning_rate": 1.7525483003674707e-05, + "loss": 1.4377, + "step": 2917 + }, + { + "epoch": 0.31, + "learning_rate": 1.7523072089294188e-05, + "loss": 1.5077, + "step": 2918 + }, + { + "epoch": 0.31, + "learning_rate": 1.752066016701531e-05, + "loss": 1.3802, + "step": 2919 + }, + { + "epoch": 0.31, + "learning_rate": 1.7518247237161205e-05, + "loss": 1.3991, + "step": 2920 + }, + { + "epoch": 0.31, + "learning_rate": 1.7515833300055146e-05, + "loss": 1.4283, + "step": 2921 + }, + { + "epoch": 0.31, + "learning_rate": 1.7513418356020535e-05, + "loss": 1.3688, + "step": 2922 + }, + { + "epoch": 0.31, + "learning_rate": 1.751100240538092e-05, + "loss": 1.4336, + "step": 2923 + }, + { + "epoch": 0.31, + "learning_rate": 1.7508585448459967e-05, + "loss": 1.4302, + "step": 2924 + }, + { + "epoch": 0.31, + "learning_rate": 1.7506167485581493e-05, + "loss": 1.4293, + "step": 2925 + }, + { + "epoch": 0.31, + "learning_rate": 1.750374851706944e-05, + "loss": 1.4262, + "step": 2926 + }, + { + "epoch": 0.31, + "learning_rate": 1.7501328543247892e-05, + "loss": 1.4128, + "step": 2927 + }, + { + "epoch": 0.31, + "learning_rate": 1.7498907564441054e-05, + "loss": 1.4258, + "step": 2928 + }, + { + "epoch": 0.31, + "learning_rate": 1.749648558097328e-05, + "loss": 1.4904, + "step": 2929 + }, + { + "epoch": 0.31, + "learning_rate": 1.749406259316906e-05, + "loss": 1.4628, + "step": 2930 + }, + { + "epoch": 0.31, + "learning_rate": 1.7491638601353004e-05, + "loss": 1.4908, + "step": 2931 + }, + { + "epoch": 0.31, + "learning_rate": 1.7489213605849867e-05, + "loss": 1.4563, + "step": 2932 + }, + { + "epoch": 0.31, + "learning_rate": 1.7486787606984533e-05, + "loss": 1.5006, + "step": 2933 + }, + { + "epoch": 0.31, + "learning_rate": 1.748436060508203e-05, + "loss": 1.424, + "step": 2934 + }, + { + "epoch": 0.31, + "learning_rate": 1.7481932600467508e-05, + "loss": 1.4136, + "step": 2935 + }, + { + "epoch": 0.31, + "learning_rate": 1.747950359346626e-05, + "loss": 1.3835, + "step": 2936 + }, + { + "epoch": 0.31, + "learning_rate": 1.747707358440371e-05, + "loss": 1.5284, + "step": 2937 + }, + { + "epoch": 0.31, + "learning_rate": 1.7474642573605418e-05, + "loss": 1.4592, + "step": 2938 + }, + { + "epoch": 0.31, + "learning_rate": 1.7472210561397075e-05, + "loss": 1.5483, + "step": 2939 + }, + { + "epoch": 0.31, + "learning_rate": 1.746977754810451e-05, + "loss": 1.521, + "step": 2940 + }, + { + "epoch": 0.31, + "learning_rate": 1.7467343534053683e-05, + "loss": 1.4276, + "step": 2941 + }, + { + "epoch": 0.31, + "learning_rate": 1.746490851957069e-05, + "loss": 1.4302, + "step": 2942 + }, + { + "epoch": 0.31, + "learning_rate": 1.746247250498176e-05, + "loss": 1.4439, + "step": 2943 + }, + { + "epoch": 0.31, + "learning_rate": 1.7460035490613255e-05, + "loss": 1.4991, + "step": 2944 + }, + { + "epoch": 0.31, + "learning_rate": 1.7457597476791674e-05, + "loss": 1.4188, + "step": 2945 + }, + { + "epoch": 0.31, + "learning_rate": 1.7455158463843648e-05, + "loss": 1.4685, + "step": 2946 + }, + { + "epoch": 0.31, + "learning_rate": 1.745271845209594e-05, + "loss": 1.3811, + "step": 2947 + }, + { + "epoch": 0.31, + "learning_rate": 1.7450277441875454e-05, + "loss": 1.4869, + "step": 2948 + }, + { + "epoch": 0.31, + "learning_rate": 1.7447835433509218e-05, + "loss": 1.5001, + "step": 2949 + }, + { + "epoch": 0.31, + "learning_rate": 1.74453924273244e-05, + "loss": 1.4757, + "step": 2950 + }, + { + "epoch": 0.31, + "learning_rate": 1.74429484236483e-05, + "loss": 1.5072, + "step": 2951 + }, + { + "epoch": 0.31, + "learning_rate": 1.744050342280835e-05, + "loss": 1.4242, + "step": 2952 + }, + { + "epoch": 0.31, + "learning_rate": 1.743805742513212e-05, + "loss": 1.4462, + "step": 2953 + }, + { + "epoch": 0.31, + "learning_rate": 1.743561043094731e-05, + "loss": 1.6815, + "step": 2954 + }, + { + "epoch": 0.31, + "learning_rate": 1.7433162440581755e-05, + "loss": 1.427, + "step": 2955 + }, + { + "epoch": 0.31, + "learning_rate": 1.7430713454363423e-05, + "loss": 1.2933, + "step": 2956 + }, + { + "epoch": 0.31, + "learning_rate": 1.742826347262041e-05, + "loss": 1.4247, + "step": 2957 + }, + { + "epoch": 0.31, + "learning_rate": 1.7425812495680955e-05, + "loss": 1.399, + "step": 2958 + }, + { + "epoch": 0.31, + "learning_rate": 1.742336052387343e-05, + "loss": 1.4818, + "step": 2959 + }, + { + "epoch": 0.31, + "learning_rate": 1.742090755752633e-05, + "loss": 1.3839, + "step": 2960 + }, + { + "epoch": 0.31, + "learning_rate": 1.741845359696829e-05, + "loss": 1.4669, + "step": 2961 + }, + { + "epoch": 0.31, + "learning_rate": 1.741599864252808e-05, + "loss": 1.468, + "step": 2962 + }, + { + "epoch": 0.31, + "learning_rate": 1.74135426945346e-05, + "loss": 1.4135, + "step": 2963 + }, + { + "epoch": 0.31, + "learning_rate": 1.7411085753316882e-05, + "loss": 1.5899, + "step": 2964 + }, + { + "epoch": 0.31, + "learning_rate": 1.74086278192041e-05, + "loss": 1.6115, + "step": 2965 + }, + { + "epoch": 0.31, + "learning_rate": 1.740616889252554e-05, + "loss": 1.3988, + "step": 2966 + }, + { + "epoch": 0.31, + "learning_rate": 1.740370897361065e-05, + "loss": 1.5001, + "step": 2967 + }, + { + "epoch": 0.31, + "learning_rate": 1.740124806278899e-05, + "loss": 1.459, + "step": 2968 + }, + { + "epoch": 0.31, + "learning_rate": 1.7398786160390258e-05, + "loss": 1.4489, + "step": 2969 + }, + { + "epoch": 0.31, + "learning_rate": 1.7396323266744283e-05, + "loss": 1.4397, + "step": 2970 + }, + { + "epoch": 0.31, + "learning_rate": 1.7393859382181033e-05, + "loss": 1.4687, + "step": 2971 + }, + { + "epoch": 0.31, + "learning_rate": 1.7391394507030606e-05, + "loss": 1.4495, + "step": 2972 + }, + { + "epoch": 0.31, + "learning_rate": 1.738892864162323e-05, + "loss": 1.4745, + "step": 2973 + }, + { + "epoch": 0.31, + "learning_rate": 1.7386461786289274e-05, + "loss": 1.3943, + "step": 2974 + }, + { + "epoch": 0.31, + "learning_rate": 1.738399394135922e-05, + "loss": 1.4595, + "step": 2975 + }, + { + "epoch": 0.31, + "learning_rate": 1.738152510716371e-05, + "loss": 1.4023, + "step": 2976 + }, + { + "epoch": 0.31, + "learning_rate": 1.7379055284033493e-05, + "loss": 1.3938, + "step": 2977 + }, + { + "epoch": 0.31, + "learning_rate": 1.7376584472299468e-05, + "loss": 1.4576, + "step": 2978 + }, + { + "epoch": 0.31, + "learning_rate": 1.737411267229266e-05, + "loss": 1.424, + "step": 2979 + }, + { + "epoch": 0.31, + "learning_rate": 1.7371639884344225e-05, + "loss": 1.4224, + "step": 2980 + }, + { + "epoch": 0.31, + "learning_rate": 1.736916610878545e-05, + "loss": 1.4228, + "step": 2981 + }, + { + "epoch": 0.31, + "learning_rate": 1.7366691345947768e-05, + "loss": 1.5021, + "step": 2982 + }, + { + "epoch": 0.31, + "learning_rate": 1.736421559616272e-05, + "loss": 1.3589, + "step": 2983 + }, + { + "epoch": 0.31, + "learning_rate": 1.7361738859762007e-05, + "loss": 1.4748, + "step": 2984 + }, + { + "epoch": 0.31, + "learning_rate": 1.735926113707743e-05, + "loss": 1.3974, + "step": 2985 + }, + { + "epoch": 0.31, + "eval_loss": 1.4849082231521606, + "eval_runtime": 77.3271, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2985 + }, + { + "epoch": 0.31, + "learning_rate": 1.735678242844096e-05, + "loss": 1.392, + "step": 2986 + }, + { + "epoch": 0.31, + "learning_rate": 1.735430273418467e-05, + "loss": 1.4277, + "step": 2987 + }, + { + "epoch": 0.31, + "learning_rate": 1.735182205464077e-05, + "loss": 1.4216, + "step": 2988 + }, + { + "epoch": 0.31, + "learning_rate": 1.7349340390141617e-05, + "loss": 1.4546, + "step": 2989 + }, + { + "epoch": 0.31, + "learning_rate": 1.734685774101969e-05, + "loss": 1.4264, + "step": 2990 + }, + { + "epoch": 0.31, + "learning_rate": 1.7344374107607593e-05, + "loss": 1.4307, + "step": 2991 + }, + { + "epoch": 0.31, + "learning_rate": 1.7341889490238076e-05, + "loss": 1.4266, + "step": 2992 + }, + { + "epoch": 0.31, + "learning_rate": 1.7339403889244008e-05, + "loss": 1.4486, + "step": 2993 + }, + { + "epoch": 0.31, + "learning_rate": 1.7336917304958403e-05, + "loss": 1.4345, + "step": 2994 + }, + { + "epoch": 0.31, + "learning_rate": 1.7334429737714395e-05, + "loss": 1.476, + "step": 2995 + }, + { + "epoch": 0.31, + "learning_rate": 1.7331941187845248e-05, + "loss": 1.5148, + "step": 2996 + }, + { + "epoch": 0.31, + "learning_rate": 1.7329451655684372e-05, + "loss": 1.4026, + "step": 2997 + }, + { + "epoch": 0.31, + "learning_rate": 1.7326961141565303e-05, + "loss": 1.3935, + "step": 2998 + }, + { + "epoch": 0.31, + "learning_rate": 1.73244696458217e-05, + "loss": 1.4483, + "step": 2999 + }, + { + "epoch": 0.31, + "learning_rate": 1.7321977168787356e-05, + "loss": 1.5197, + "step": 3000 + }, + { + "epoch": 0.31, + "learning_rate": 1.7319483710796208e-05, + "loss": 1.4648, + "step": 3001 + }, + { + "epoch": 0.31, + "learning_rate": 1.7316989272182308e-05, + "loss": 1.4171, + "step": 3002 + }, + { + "epoch": 0.31, + "learning_rate": 1.731449385327985e-05, + "loss": 1.4541, + "step": 3003 + }, + { + "epoch": 0.32, + "learning_rate": 1.731199745442316e-05, + "loss": 1.4605, + "step": 3004 + }, + { + "epoch": 0.32, + "learning_rate": 1.7309500075946683e-05, + "loss": 1.5122, + "step": 3005 + }, + { + "epoch": 0.32, + "learning_rate": 1.7307001718185007e-05, + "loss": 1.5243, + "step": 3006 + }, + { + "epoch": 0.32, + "learning_rate": 1.7304502381472844e-05, + "loss": 1.4997, + "step": 3007 + }, + { + "epoch": 0.32, + "learning_rate": 1.730200206614505e-05, + "loss": 1.4891, + "step": 3008 + }, + { + "epoch": 0.32, + "learning_rate": 1.72995007725366e-05, + "loss": 1.4376, + "step": 3009 + }, + { + "epoch": 0.32, + "learning_rate": 1.7296998500982595e-05, + "loss": 1.4403, + "step": 3010 + }, + { + "epoch": 0.32, + "learning_rate": 1.7294495251818285e-05, + "loss": 1.5153, + "step": 3011 + }, + { + "epoch": 0.32, + "learning_rate": 1.729199102537904e-05, + "loss": 1.4996, + "step": 3012 + }, + { + "epoch": 0.32, + "learning_rate": 1.7289485822000356e-05, + "loss": 1.5302, + "step": 3013 + }, + { + "epoch": 0.32, + "learning_rate": 1.7286979642017867e-05, + "loss": 1.5641, + "step": 3014 + }, + { + "epoch": 0.32, + "learning_rate": 1.728447248576734e-05, + "loss": 1.438, + "step": 3015 + }, + { + "epoch": 0.32, + "learning_rate": 1.7281964353584674e-05, + "loss": 1.4796, + "step": 3016 + }, + { + "epoch": 0.32, + "learning_rate": 1.727945524580588e-05, + "loss": 1.4413, + "step": 3017 + }, + { + "epoch": 0.32, + "learning_rate": 1.727694516276713e-05, + "loss": 1.3966, + "step": 3018 + }, + { + "epoch": 0.32, + "learning_rate": 1.72744341048047e-05, + "loss": 1.5267, + "step": 3019 + }, + { + "epoch": 0.32, + "learning_rate": 1.727192207225501e-05, + "loss": 1.4284, + "step": 3020 + }, + { + "epoch": 0.32, + "learning_rate": 1.726940906545461e-05, + "loss": 1.5137, + "step": 3021 + }, + { + "epoch": 0.32, + "learning_rate": 1.7266895084740173e-05, + "loss": 1.3966, + "step": 3022 + }, + { + "epoch": 0.32, + "learning_rate": 1.7264380130448514e-05, + "loss": 1.4156, + "step": 3023 + }, + { + "epoch": 0.32, + "learning_rate": 1.726186420291657e-05, + "loss": 1.4644, + "step": 3024 + }, + { + "epoch": 0.32, + "learning_rate": 1.725934730248141e-05, + "loss": 1.4768, + "step": 3025 + }, + { + "epoch": 0.32, + "learning_rate": 1.7256829429480233e-05, + "loss": 1.4428, + "step": 3026 + }, + { + "epoch": 0.32, + "learning_rate": 1.7254310584250373e-05, + "loss": 1.4495, + "step": 3027 + }, + { + "epoch": 0.32, + "learning_rate": 1.725179076712929e-05, + "loss": 1.3867, + "step": 3028 + }, + { + "epoch": 0.32, + "learning_rate": 1.7249269978454567e-05, + "loss": 1.5011, + "step": 3029 + }, + { + "epoch": 0.32, + "learning_rate": 1.7246748218563937e-05, + "loss": 1.3916, + "step": 3030 + }, + { + "epoch": 0.32, + "learning_rate": 1.7244225487795238e-05, + "loss": 1.4984, + "step": 3031 + }, + { + "epoch": 0.32, + "learning_rate": 1.7241701786486464e-05, + "loss": 1.5776, + "step": 3032 + }, + { + "epoch": 0.32, + "learning_rate": 1.7239177114975717e-05, + "loss": 1.5018, + "step": 3033 + }, + { + "epoch": 0.32, + "learning_rate": 1.7236651473601244e-05, + "loss": 1.5042, + "step": 3034 + }, + { + "epoch": 0.32, + "learning_rate": 1.723412486270141e-05, + "loss": 1.4636, + "step": 3035 + }, + { + "epoch": 0.32, + "learning_rate": 1.723159728261472e-05, + "loss": 1.5612, + "step": 3036 + }, + { + "epoch": 0.32, + "learning_rate": 1.7229068733679803e-05, + "loss": 1.4399, + "step": 3037 + }, + { + "epoch": 0.32, + "learning_rate": 1.7226539216235424e-05, + "loss": 1.5635, + "step": 3038 + }, + { + "epoch": 0.32, + "learning_rate": 1.7224008730620468e-05, + "loss": 1.4329, + "step": 3039 + }, + { + "epoch": 0.32, + "learning_rate": 1.7221477277173956e-05, + "loss": 1.4886, + "step": 3040 + }, + { + "epoch": 0.32, + "learning_rate": 1.721894485623504e-05, + "loss": 1.4741, + "step": 3041 + }, + { + "epoch": 0.32, + "learning_rate": 1.7216411468143e-05, + "loss": 1.4678, + "step": 3042 + }, + { + "epoch": 0.32, + "learning_rate": 1.721387711323724e-05, + "loss": 1.4758, + "step": 3043 + }, + { + "epoch": 0.32, + "learning_rate": 1.72113417918573e-05, + "loss": 1.441, + "step": 3044 + }, + { + "epoch": 0.32, + "learning_rate": 1.7208805504342855e-05, + "loss": 1.4328, + "step": 3045 + }, + { + "epoch": 0.32, + "learning_rate": 1.720626825103369e-05, + "loss": 1.4254, + "step": 3046 + }, + { + "epoch": 0.32, + "learning_rate": 1.7203730032269744e-05, + "loss": 1.4462, + "step": 3047 + }, + { + "epoch": 0.32, + "learning_rate": 1.7201190848391066e-05, + "loss": 1.4826, + "step": 3048 + }, + { + "epoch": 0.32, + "learning_rate": 1.719865069973784e-05, + "loss": 1.4215, + "step": 3049 + }, + { + "epoch": 0.32, + "learning_rate": 1.7196109586650385e-05, + "loss": 1.4291, + "step": 3050 + }, + { + "epoch": 0.32, + "learning_rate": 1.7193567509469146e-05, + "loss": 1.5005, + "step": 3051 + }, + { + "epoch": 0.32, + "learning_rate": 1.719102446853469e-05, + "loss": 1.4216, + "step": 3052 + }, + { + "epoch": 0.32, + "learning_rate": 1.7188480464187725e-05, + "loss": 1.4349, + "step": 3053 + }, + { + "epoch": 0.32, + "learning_rate": 1.718593549676908e-05, + "loss": 1.4784, + "step": 3054 + }, + { + "epoch": 0.32, + "learning_rate": 1.7183389566619714e-05, + "loss": 1.4325, + "step": 3055 + }, + { + "epoch": 0.32, + "learning_rate": 1.7180842674080717e-05, + "loss": 1.5387, + "step": 3056 + }, + { + "epoch": 0.32, + "learning_rate": 1.717829481949331e-05, + "loss": 1.655, + "step": 3057 + }, + { + "epoch": 0.32, + "learning_rate": 1.717574600319883e-05, + "loss": 1.4623, + "step": 3058 + }, + { + "epoch": 0.32, + "learning_rate": 1.7173196225538768e-05, + "loss": 1.4646, + "step": 3059 + }, + { + "epoch": 0.32, + "learning_rate": 1.717064548685472e-05, + "loss": 1.4641, + "step": 3060 + }, + { + "epoch": 0.32, + "learning_rate": 1.7168093787488418e-05, + "loss": 1.4033, + "step": 3061 + }, + { + "epoch": 0.32, + "learning_rate": 1.7165541127781726e-05, + "loss": 1.4085, + "step": 3062 + }, + { + "epoch": 0.32, + "learning_rate": 1.716298750807664e-05, + "loss": 1.387, + "step": 3063 + }, + { + "epoch": 0.32, + "learning_rate": 1.7160432928715272e-05, + "loss": 1.4197, + "step": 3064 + }, + { + "epoch": 0.32, + "learning_rate": 1.7157877390039872e-05, + "loss": 1.4883, + "step": 3065 + }, + { + "epoch": 0.32, + "learning_rate": 1.7155320892392818e-05, + "loss": 1.4865, + "step": 3066 + }, + { + "epoch": 0.32, + "learning_rate": 1.715276343611662e-05, + "loss": 1.4532, + "step": 3067 + }, + { + "epoch": 0.32, + "learning_rate": 1.71502050215539e-05, + "loss": 1.3991, + "step": 3068 + }, + { + "epoch": 0.32, + "learning_rate": 1.7147645649047424e-05, + "loss": 1.4318, + "step": 3069 + }, + { + "epoch": 0.32, + "learning_rate": 1.714508531894009e-05, + "loss": 1.3616, + "step": 3070 + }, + { + "epoch": 0.32, + "learning_rate": 1.7142524031574904e-05, + "loss": 1.4481, + "step": 3071 + }, + { + "epoch": 0.32, + "learning_rate": 1.7139961787295022e-05, + "loss": 1.3897, + "step": 3072 + }, + { + "epoch": 0.32, + "learning_rate": 1.7137398586443716e-05, + "loss": 1.3128, + "step": 3073 + }, + { + "epoch": 0.32, + "learning_rate": 1.713483442936439e-05, + "loss": 1.4481, + "step": 3074 + }, + { + "epoch": 0.32, + "learning_rate": 1.713226931640057e-05, + "loss": 1.5374, + "step": 3075 + }, + { + "epoch": 0.32, + "learning_rate": 1.7129703247895923e-05, + "loss": 1.4247, + "step": 3076 + }, + { + "epoch": 0.32, + "learning_rate": 1.712713622419423e-05, + "loss": 1.4098, + "step": 3077 + }, + { + "epoch": 0.32, + "learning_rate": 1.7124568245639414e-05, + "loss": 1.4558, + "step": 3078 + }, + { + "epoch": 0.32, + "learning_rate": 1.7121999312575507e-05, + "loss": 1.4484, + "step": 3079 + }, + { + "epoch": 0.32, + "learning_rate": 1.711942942534669e-05, + "loss": 1.4236, + "step": 3080 + }, + { + "epoch": 0.32, + "learning_rate": 1.7116858584297253e-05, + "loss": 1.613, + "step": 3081 + }, + { + "epoch": 0.32, + "learning_rate": 1.711428678977163e-05, + "loss": 1.4503, + "step": 3082 + }, + { + "epoch": 0.32, + "learning_rate": 1.7111714042114376e-05, + "loss": 1.4072, + "step": 3083 + }, + { + "epoch": 0.32, + "learning_rate": 1.7109140341670168e-05, + "loss": 1.5999, + "step": 3084 + }, + { + "epoch": 0.32, + "learning_rate": 1.7106565688783815e-05, + "loss": 1.4129, + "step": 3085 + }, + { + "epoch": 0.32, + "learning_rate": 1.710399008380026e-05, + "loss": 1.3973, + "step": 3086 + }, + { + "epoch": 0.32, + "learning_rate": 1.710141352706456e-05, + "loss": 1.4292, + "step": 3087 + }, + { + "epoch": 0.32, + "learning_rate": 1.709883601892192e-05, + "loss": 1.4372, + "step": 3088 + }, + { + "epoch": 0.32, + "learning_rate": 1.7096257559717647e-05, + "loss": 1.4924, + "step": 3089 + }, + { + "epoch": 0.32, + "learning_rate": 1.7093678149797196e-05, + "loss": 1.4222, + "step": 3090 + }, + { + "epoch": 0.32, + "learning_rate": 1.7091097789506137e-05, + "loss": 1.4797, + "step": 3091 + }, + { + "epoch": 0.32, + "learning_rate": 1.7088516479190175e-05, + "loss": 1.4738, + "step": 3092 + }, + { + "epoch": 0.32, + "learning_rate": 1.708593421919514e-05, + "loss": 1.5371, + "step": 3093 + }, + { + "epoch": 0.32, + "learning_rate": 1.7083351009866988e-05, + "loss": 1.3802, + "step": 3094 + }, + { + "epoch": 0.32, + "learning_rate": 1.7080766851551795e-05, + "loss": 1.4292, + "step": 3095 + }, + { + "epoch": 0.32, + "learning_rate": 1.707818174459578e-05, + "loss": 1.4478, + "step": 3096 + }, + { + "epoch": 0.32, + "learning_rate": 1.7075595689345285e-05, + "loss": 1.4619, + "step": 3097 + }, + { + "epoch": 0.32, + "learning_rate": 1.7073008686146763e-05, + "loss": 1.4603, + "step": 3098 + }, + { + "epoch": 0.32, + "learning_rate": 1.7070420735346815e-05, + "loss": 1.4548, + "step": 3099 + }, + { + "epoch": 0.33, + "learning_rate": 1.7067831837292157e-05, + "loss": 1.3638, + "step": 3100 + }, + { + "epoch": 0.33, + "learning_rate": 1.7065241992329634e-05, + "loss": 1.4284, + "step": 3101 + }, + { + "epoch": 0.33, + "learning_rate": 1.7062651200806217e-05, + "loss": 1.386, + "step": 3102 + }, + { + "epoch": 0.33, + "learning_rate": 1.7060059463069013e-05, + "loss": 1.5483, + "step": 3103 + }, + { + "epoch": 0.33, + "learning_rate": 1.705746677946524e-05, + "loss": 1.4963, + "step": 3104 + }, + { + "epoch": 0.33, + "learning_rate": 1.7054873150342257e-05, + "loss": 1.4539, + "step": 3105 + }, + { + "epoch": 0.33, + "learning_rate": 1.705227857604754e-05, + "loss": 1.4361, + "step": 3106 + }, + { + "epoch": 0.33, + "learning_rate": 1.7049683056928695e-05, + "loss": 1.3735, + "step": 3107 + }, + { + "epoch": 0.33, + "learning_rate": 1.7047086593333454e-05, + "loss": 1.4324, + "step": 3108 + }, + { + "epoch": 0.33, + "learning_rate": 1.7044489185609685e-05, + "loss": 1.5037, + "step": 3109 + }, + { + "epoch": 0.33, + "learning_rate": 1.704189083410536e-05, + "loss": 1.3913, + "step": 3110 + }, + { + "epoch": 0.33, + "learning_rate": 1.7039291539168604e-05, + "loss": 1.3233, + "step": 3111 + }, + { + "epoch": 0.33, + "learning_rate": 1.703669130114765e-05, + "loss": 1.4897, + "step": 3112 + }, + { + "epoch": 0.33, + "learning_rate": 1.7034090120390862e-05, + "loss": 1.4843, + "step": 3113 + }, + { + "epoch": 0.33, + "learning_rate": 1.7031487997246735e-05, + "loss": 1.3674, + "step": 3114 + }, + { + "epoch": 0.33, + "learning_rate": 1.7028884932063883e-05, + "loss": 1.4475, + "step": 3115 + }, + { + "epoch": 0.33, + "learning_rate": 1.702628092519105e-05, + "loss": 1.4134, + "step": 3116 + }, + { + "epoch": 0.33, + "learning_rate": 1.7023675976977108e-05, + "loss": 1.4484, + "step": 3117 + }, + { + "epoch": 0.33, + "learning_rate": 1.702107008777106e-05, + "loss": 1.407, + "step": 3118 + }, + { + "epoch": 0.33, + "learning_rate": 1.7018463257922005e-05, + "loss": 1.5443, + "step": 3119 + }, + { + "epoch": 0.33, + "learning_rate": 1.701585548777922e-05, + "loss": 1.4548, + "step": 3120 + }, + { + "epoch": 0.33, + "learning_rate": 1.7013246777692063e-05, + "loss": 1.4252, + "step": 3121 + }, + { + "epoch": 0.33, + "learning_rate": 1.7010637128010037e-05, + "loss": 1.3748, + "step": 3122 + }, + { + "epoch": 0.33, + "learning_rate": 1.7008026539082767e-05, + "loss": 1.3804, + "step": 3123 + }, + { + "epoch": 0.33, + "learning_rate": 1.7005415011260008e-05, + "loss": 1.4203, + "step": 3124 + }, + { + "epoch": 0.33, + "learning_rate": 1.7002802544891634e-05, + "loss": 1.4195, + "step": 3125 + }, + { + "epoch": 0.33, + "learning_rate": 1.700018914032765e-05, + "loss": 1.4188, + "step": 3126 + }, + { + "epoch": 0.33, + "learning_rate": 1.699757479791819e-05, + "loss": 1.3884, + "step": 3127 + }, + { + "epoch": 0.33, + "learning_rate": 1.6994959518013502e-05, + "loss": 1.4111, + "step": 3128 + }, + { + "epoch": 0.33, + "learning_rate": 1.6992343300963963e-05, + "loss": 1.5452, + "step": 3129 + }, + { + "epoch": 0.33, + "learning_rate": 1.6989726147120087e-05, + "loss": 1.4097, + "step": 3130 + }, + { + "epoch": 0.33, + "learning_rate": 1.6987108056832506e-05, + "loss": 1.481, + "step": 3131 + }, + { + "epoch": 0.33, + "learning_rate": 1.6984489030451973e-05, + "loss": 1.4505, + "step": 3132 + }, + { + "epoch": 0.33, + "learning_rate": 1.6981869068329368e-05, + "loss": 1.4281, + "step": 3133 + }, + { + "epoch": 0.33, + "learning_rate": 1.69792481708157e-05, + "loss": 1.4555, + "step": 3134 + }, + { + "epoch": 0.33, + "learning_rate": 1.6976626338262103e-05, + "loss": 1.4525, + "step": 3135 + }, + { + "epoch": 0.33, + "learning_rate": 1.6974003571019837e-05, + "loss": 1.3765, + "step": 3136 + }, + { + "epoch": 0.33, + "learning_rate": 1.6971379869440286e-05, + "loss": 1.3998, + "step": 3137 + }, + { + "epoch": 0.33, + "learning_rate": 1.696875523387495e-05, + "loss": 1.5103, + "step": 3138 + }, + { + "epoch": 0.33, + "learning_rate": 1.6966129664675474e-05, + "loss": 1.427, + "step": 3139 + }, + { + "epoch": 0.33, + "learning_rate": 1.6963503162193612e-05, + "loss": 1.4362, + "step": 3140 + }, + { + "epoch": 0.33, + "learning_rate": 1.6960875726781246e-05, + "loss": 1.4073, + "step": 3141 + }, + { + "epoch": 0.33, + "learning_rate": 1.6958247358790388e-05, + "loss": 1.4014, + "step": 3142 + }, + { + "epoch": 0.33, + "learning_rate": 1.6955618058573165e-05, + "loss": 1.4244, + "step": 3143 + }, + { + "epoch": 0.33, + "learning_rate": 1.6952987826481847e-05, + "loss": 1.47, + "step": 3144 + }, + { + "epoch": 0.33, + "learning_rate": 1.6950356662868814e-05, + "loss": 1.5112, + "step": 3145 + }, + { + "epoch": 0.33, + "learning_rate": 1.6947724568086562e-05, + "loss": 1.3398, + "step": 3146 + }, + { + "epoch": 0.33, + "learning_rate": 1.694509154248774e-05, + "loss": 1.4584, + "step": 3147 + }, + { + "epoch": 0.33, + "learning_rate": 1.69424575864251e-05, + "loss": 1.4383, + "step": 3148 + }, + { + "epoch": 0.33, + "learning_rate": 1.6939822700251523e-05, + "loss": 1.3869, + "step": 3149 + }, + { + "epoch": 0.33, + "learning_rate": 1.6937186884320015e-05, + "loss": 1.4453, + "step": 3150 + }, + { + "epoch": 0.33, + "learning_rate": 1.6934550138983713e-05, + "loss": 1.3355, + "step": 3151 + }, + { + "epoch": 0.33, + "learning_rate": 1.6931912464595866e-05, + "loss": 1.5573, + "step": 3152 + }, + { + "epoch": 0.33, + "learning_rate": 1.6929273861509865e-05, + "loss": 1.439, + "step": 3153 + }, + { + "epoch": 0.33, + "learning_rate": 1.6926634330079203e-05, + "loss": 1.6079, + "step": 3154 + }, + { + "epoch": 0.33, + "learning_rate": 1.692399387065752e-05, + "loss": 1.6973, + "step": 3155 + }, + { + "epoch": 0.33, + "learning_rate": 1.692135248359856e-05, + "loss": 1.3769, + "step": 3156 + }, + { + "epoch": 0.33, + "learning_rate": 1.6918710169256206e-05, + "loss": 1.4454, + "step": 3157 + }, + { + "epoch": 0.33, + "learning_rate": 1.691606692798446e-05, + "loss": 1.4495, + "step": 3158 + }, + { + "epoch": 0.33, + "learning_rate": 1.691342276013745e-05, + "loss": 1.4292, + "step": 3159 + }, + { + "epoch": 0.33, + "learning_rate": 1.691077766606942e-05, + "loss": 1.4405, + "step": 3160 + }, + { + "epoch": 0.33, + "learning_rate": 1.6908131646134757e-05, + "loss": 1.3683, + "step": 3161 + }, + { + "epoch": 0.33, + "learning_rate": 1.690548470068795e-05, + "loss": 1.4731, + "step": 3162 + }, + { + "epoch": 0.33, + "learning_rate": 1.690283683008362e-05, + "loss": 1.4323, + "step": 3163 + }, + { + "epoch": 0.33, + "learning_rate": 1.6900188034676518e-05, + "loss": 1.5133, + "step": 3164 + }, + { + "epoch": 0.33, + "learning_rate": 1.6897538314821516e-05, + "loss": 1.5529, + "step": 3165 + }, + { + "epoch": 0.33, + "learning_rate": 1.6894887670873605e-05, + "loss": 1.4427, + "step": 3166 + }, + { + "epoch": 0.33, + "learning_rate": 1.6892236103187904e-05, + "loss": 1.4344, + "step": 3167 + }, + { + "epoch": 0.33, + "learning_rate": 1.6889583612119657e-05, + "loss": 1.4291, + "step": 3168 + }, + { + "epoch": 0.33, + "learning_rate": 1.6886930198024226e-05, + "loss": 1.4683, + "step": 3169 + }, + { + "epoch": 0.33, + "learning_rate": 1.6884275861257106e-05, + "loss": 1.4442, + "step": 3170 + }, + { + "epoch": 0.33, + "learning_rate": 1.6881620602173905e-05, + "loss": 1.4509, + "step": 3171 + }, + { + "epoch": 0.33, + "learning_rate": 1.6878964421130362e-05, + "loss": 1.5113, + "step": 3172 + }, + { + "epoch": 0.33, + "learning_rate": 1.6876307318482334e-05, + "loss": 1.4261, + "step": 3173 + }, + { + "epoch": 0.33, + "learning_rate": 1.6873649294585805e-05, + "loss": 1.445, + "step": 3174 + }, + { + "epoch": 0.33, + "learning_rate": 1.6870990349796886e-05, + "loss": 1.4603, + "step": 3175 + }, + { + "epoch": 0.33, + "learning_rate": 1.68683304844718e-05, + "loss": 1.41, + "step": 3176 + }, + { + "epoch": 0.33, + "learning_rate": 1.686566969896691e-05, + "loss": 1.4018, + "step": 3177 + }, + { + "epoch": 0.33, + "learning_rate": 1.6863007993638687e-05, + "loss": 1.422, + "step": 3178 + }, + { + "epoch": 0.33, + "learning_rate": 1.6860345368843727e-05, + "loss": 1.4412, + "step": 3179 + }, + { + "epoch": 0.33, + "learning_rate": 1.6857681824938768e-05, + "loss": 1.5411, + "step": 3180 + }, + { + "epoch": 0.33, + "learning_rate": 1.685501736228064e-05, + "loss": 1.4416, + "step": 3181 + }, + { + "epoch": 0.33, + "learning_rate": 1.685235198122632e-05, + "loss": 1.5113, + "step": 3182 + }, + { + "epoch": 0.33, + "learning_rate": 1.6849685682132903e-05, + "loss": 1.423, + "step": 3183 + }, + { + "epoch": 0.33, + "learning_rate": 1.68470184653576e-05, + "loss": 1.404, + "step": 3184 + }, + { + "epoch": 0.33, + "eval_loss": 1.4771089553833008, + "eval_runtime": 77.4034, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3184 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 1.4244071391780825e+20, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-3184/training_args.bin b/checkpoint-3184/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-3184/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-3582/config.json b/checkpoint-3582/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-3582/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-3582/generation_config.json b/checkpoint-3582/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-3582/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-3582/model-00001-of-00003.safetensors b/checkpoint-3582/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c2f6a9d659c4db71d7de2610a7a800f098d68269 --- /dev/null +++ b/checkpoint-3582/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03982c4aabdf52a1605104f4d58e2c7f683b340e3148ae0dd92c571a66e41792 +size 4943162336 diff --git a/checkpoint-3582/model-00002-of-00003.safetensors b/checkpoint-3582/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7212ea5cda76afff59621d0553733d9e6d5a06cc --- /dev/null +++ b/checkpoint-3582/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb9f5ca5dc9fe1c0fab27875202729a8bf6374b24f51eda570f116a15b39b851 +size 4999819336 diff --git a/checkpoint-3582/model-00003-of-00003.safetensors b/checkpoint-3582/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3eb319b3e112eb7d0eb862f3dbfdc23c008d8f03 --- /dev/null +++ b/checkpoint-3582/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecbf53c920603f11cb206ec5a525b0a73cf05cdc1665336e0c44b761d97e5b11 +size 4540516344 diff --git a/checkpoint-3582/model.safetensors.index.json b/checkpoint-3582/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-3582/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-3582/optimizer.pt b/checkpoint-3582/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..d3459c79e1eb3ecd06e2fbea10fb04ad39f70e68 --- /dev/null +++ b/checkpoint-3582/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a10e6ddbf4d30e0502eec171fa4c987c16938b325c06397aa61e4b5ebcd7b8b +size 14512103560 diff --git a/checkpoint-3582/rng_state_0.pth b/checkpoint-3582/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..8483a889f150d02b47828f389c960e8158f0178b --- /dev/null +++ b/checkpoint-3582/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5510249379d4bd7731843b6055556800ed97fda6358ff141a77df00ddc8e1a4d +size 15984 diff --git a/checkpoint-3582/rng_state_1.pth b/checkpoint-3582/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..ecc148c7d7776aa46b72d840a4437fc8d56f80d6 --- /dev/null +++ b/checkpoint-3582/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fc667634ee9903c756967f07fad7943e85da70284ee5588e235cba7f5686b51 +size 15984 diff --git a/checkpoint-3582/rng_state_2.pth b/checkpoint-3582/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..57134a0b3dad6b1c6ab55153c3a6a15ffc021461 --- /dev/null +++ b/checkpoint-3582/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d8656dbc5b8aef9b3b2a3c6843ada9a3dcf759800d8bb69f03c1eeab188a0f8 +size 15984 diff --git a/checkpoint-3582/rng_state_3.pth b/checkpoint-3582/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..269e96e19581ada043e0d4fdba9fb48480b0f7ce --- /dev/null +++ b/checkpoint-3582/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:443e35471f0855ee1c45505d670899cc6d14786fdc8947a8a7d42d87d1e21667 +size 15984 diff --git a/checkpoint-3582/rng_state_4.pth b/checkpoint-3582/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..c81783e38d22e2abcec3836ff7691dd2aaeecd40 --- /dev/null +++ b/checkpoint-3582/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45f7f10857a0bfbb73af85f384029b8392fbfefbee0de21b050fba883244c2c4 +size 15984 diff --git a/checkpoint-3582/rng_state_5.pth b/checkpoint-3582/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..690bfb816bb0bb18053e00de289f00d078360b71 --- /dev/null +++ b/checkpoint-3582/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:632333e189d17bf4deb60a342ba16da53e8056c7cac6295fad33eda84d4104a4 +size 15984 diff --git a/checkpoint-3582/rng_state_6.pth b/checkpoint-3582/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..eed1e9c13952f7544a717435f4d5ee80877637e9 --- /dev/null +++ b/checkpoint-3582/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:359d203bf20ba508cba4e15a57cbcce5e7599dfac9afecde3f9b54d9a24a18ba +size 15984 diff --git a/checkpoint-3582/rng_state_7.pth b/checkpoint-3582/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..ec22e52f596fba4f0f04a50bbfa5ed7b5b237732 --- /dev/null +++ b/checkpoint-3582/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cc09b08b3c4e19867b731c6c4acc49dd500202da095249952fda571d4a7ab4d +size 15984 diff --git a/checkpoint-3582/scheduler.pt b/checkpoint-3582/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..a9d56fc8d299f17de4d9a632148a683314fa818e --- /dev/null +++ b/checkpoint-3582/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33cb82ada7325567f56f1b660d58d83fd909c021633d72cc586e22d6b7dbb709 +size 1064 diff --git a/checkpoint-3582/special_tokens_map.json b/checkpoint-3582/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-3582/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-3582/tokenizer.model b/checkpoint-3582/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-3582/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-3582/tokenizer_config.json b/checkpoint-3582/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-3582/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-3582/trainer_state.json b/checkpoint-3582/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..1060c0da529fd45296bafbd1e38aae27f9113235 --- /dev/null +++ b/checkpoint-3582/trainer_state.json @@ -0,0 +1,21656 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.37562919463087246, + "eval_steps": 199, + "global_step": 3582, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + }, + { + "epoch": 0.21, + "learning_rate": 1.928689129323009e-05, + "loss": 1.421, + "step": 1991 + }, + { + "epoch": 0.21, + "learning_rate": 1.928553323396003e-05, + "loss": 1.5625, + "step": 1992 + }, + { + "epoch": 0.21, + "learning_rate": 1.92841739306671e-05, + "loss": 1.5198, + "step": 1993 + }, + { + "epoch": 0.21, + "learning_rate": 1.9282813383533415e-05, + "loss": 1.5116, + "step": 1994 + }, + { + "epoch": 0.21, + "learning_rate": 1.9281451592741247e-05, + "loss": 1.4306, + "step": 1995 + }, + { + "epoch": 0.21, + "learning_rate": 1.9280088558473046e-05, + "loss": 1.5425, + "step": 1996 + }, + { + "epoch": 0.21, + "learning_rate": 1.9278724280911424e-05, + "loss": 1.4972, + "step": 1997 + }, + { + "epoch": 0.21, + "learning_rate": 1.9277358760239156e-05, + "loss": 1.5185, + "step": 1998 + }, + { + "epoch": 0.21, + "learning_rate": 1.9275991996639188e-05, + "loss": 1.5187, + "step": 1999 + }, + { + "epoch": 0.21, + "learning_rate": 1.927462399029463e-05, + "loss": 1.4325, + "step": 2000 + }, + { + "epoch": 0.21, + "learning_rate": 1.9273254741388763e-05, + "loss": 1.4397, + "step": 2001 + }, + { + "epoch": 0.21, + "learning_rate": 1.927188425010503e-05, + "loss": 1.5319, + "step": 2002 + }, + { + "epoch": 0.21, + "learning_rate": 1.9270512516627042e-05, + "loss": 1.5664, + "step": 2003 + }, + { + "epoch": 0.21, + "learning_rate": 1.9269139541138574e-05, + "loss": 1.5227, + "step": 2004 + }, + { + "epoch": 0.21, + "learning_rate": 1.926776532382357e-05, + "loss": 1.5187, + "step": 2005 + }, + { + "epoch": 0.21, + "learning_rate": 1.9266389864866134e-05, + "loss": 1.4029, + "step": 2006 + }, + { + "epoch": 0.21, + "learning_rate": 1.9265013164450557e-05, + "loss": 1.387, + "step": 2007 + }, + { + "epoch": 0.21, + "learning_rate": 1.9263635222761268e-05, + "loss": 1.5047, + "step": 2008 + }, + { + "epoch": 0.21, + "learning_rate": 1.9262256039982882e-05, + "loss": 1.4816, + "step": 2009 + }, + { + "epoch": 0.21, + "learning_rate": 1.9260875616300172e-05, + "loss": 1.4607, + "step": 2010 + }, + { + "epoch": 0.21, + "learning_rate": 1.9259493951898084e-05, + "loss": 1.628, + "step": 2011 + }, + { + "epoch": 0.21, + "learning_rate": 1.9258111046961714e-05, + "loss": 1.4149, + "step": 2012 + }, + { + "epoch": 0.21, + "learning_rate": 1.925672690167635e-05, + "loss": 1.5303, + "step": 2013 + }, + { + "epoch": 0.21, + "learning_rate": 1.925534151622742e-05, + "loss": 1.5198, + "step": 2014 + }, + { + "epoch": 0.21, + "learning_rate": 1.9253954890800535e-05, + "loss": 1.6422, + "step": 2015 + }, + { + "epoch": 0.21, + "learning_rate": 1.925256702558147e-05, + "loss": 1.4738, + "step": 2016 + }, + { + "epoch": 0.21, + "learning_rate": 1.925117792075616e-05, + "loss": 1.4752, + "step": 2017 + }, + { + "epoch": 0.21, + "learning_rate": 1.9249787576510713e-05, + "loss": 1.4547, + "step": 2018 + }, + { + "epoch": 0.21, + "learning_rate": 1.924839599303139e-05, + "loss": 1.4864, + "step": 2019 + }, + { + "epoch": 0.21, + "learning_rate": 1.9247003170504638e-05, + "loss": 1.5037, + "step": 2020 + }, + { + "epoch": 0.21, + "learning_rate": 1.9245609109117053e-05, + "loss": 1.5089, + "step": 2021 + }, + { + "epoch": 0.21, + "learning_rate": 1.924421380905541e-05, + "loss": 1.5616, + "step": 2022 + }, + { + "epoch": 0.21, + "learning_rate": 1.9242817270506634e-05, + "loss": 1.4592, + "step": 2023 + }, + { + "epoch": 0.21, + "learning_rate": 1.9241419493657832e-05, + "loss": 1.5592, + "step": 2024 + }, + { + "epoch": 0.21, + "learning_rate": 1.924002047869627e-05, + "loss": 1.4897, + "step": 2025 + }, + { + "epoch": 0.21, + "learning_rate": 1.9238620225809375e-05, + "loss": 1.4743, + "step": 2026 + }, + { + "epoch": 0.21, + "learning_rate": 1.923721873518475e-05, + "loss": 1.4686, + "step": 2027 + }, + { + "epoch": 0.21, + "learning_rate": 1.923581600701016e-05, + "loss": 1.461, + "step": 2028 + }, + { + "epoch": 0.21, + "learning_rate": 1.9234412041473528e-05, + "loss": 1.6622, + "step": 2029 + }, + { + "epoch": 0.21, + "learning_rate": 1.9233006838762955e-05, + "loss": 1.4707, + "step": 2030 + }, + { + "epoch": 0.21, + "learning_rate": 1.92316003990667e-05, + "loss": 1.5566, + "step": 2031 + }, + { + "epoch": 0.21, + "learning_rate": 1.9230192722573188e-05, + "loss": 1.4881, + "step": 2032 + }, + { + "epoch": 0.21, + "learning_rate": 1.9228783809471015e-05, + "loss": 1.6124, + "step": 2033 + }, + { + "epoch": 0.21, + "learning_rate": 1.9227373659948937e-05, + "loss": 1.3508, + "step": 2034 + }, + { + "epoch": 0.21, + "learning_rate": 1.9225962274195876e-05, + "loss": 1.4418, + "step": 2035 + }, + { + "epoch": 0.21, + "learning_rate": 1.9224549652400927e-05, + "loss": 1.3954, + "step": 2036 + }, + { + "epoch": 0.21, + "learning_rate": 1.922313579475334e-05, + "loss": 1.4798, + "step": 2037 + }, + { + "epoch": 0.21, + "learning_rate": 1.922172070144254e-05, + "loss": 1.4556, + "step": 2038 + }, + { + "epoch": 0.21, + "learning_rate": 1.922030437265811e-05, + "loss": 1.4987, + "step": 2039 + }, + { + "epoch": 0.21, + "learning_rate": 1.9218886808589796e-05, + "loss": 1.4857, + "step": 2040 + }, + { + "epoch": 0.21, + "learning_rate": 1.9217468009427527e-05, + "loss": 1.5289, + "step": 2041 + }, + { + "epoch": 0.21, + "learning_rate": 1.921604797536138e-05, + "loss": 1.5267, + "step": 2042 + }, + { + "epoch": 0.21, + "learning_rate": 1.9214626706581598e-05, + "loss": 1.4655, + "step": 2043 + }, + { + "epoch": 0.21, + "learning_rate": 1.9213204203278602e-05, + "loss": 1.4598, + "step": 2044 + }, + { + "epoch": 0.21, + "learning_rate": 1.9211780465642973e-05, + "loss": 1.4766, + "step": 2045 + }, + { + "epoch": 0.21, + "learning_rate": 1.921035549386545e-05, + "loss": 1.5148, + "step": 2046 + }, + { + "epoch": 0.21, + "learning_rate": 1.9208929288136933e-05, + "loss": 1.5567, + "step": 2047 + }, + { + "epoch": 0.21, + "learning_rate": 1.920750184864852e-05, + "loss": 1.4868, + "step": 2048 + }, + { + "epoch": 0.21, + "learning_rate": 1.920607317559143e-05, + "loss": 1.4752, + "step": 2049 + }, + { + "epoch": 0.21, + "learning_rate": 1.920464326915708e-05, + "loss": 1.4882, + "step": 2050 + }, + { + "epoch": 0.22, + "learning_rate": 1.9203212129537035e-05, + "loss": 1.5933, + "step": 2051 + }, + { + "epoch": 0.22, + "learning_rate": 1.9201779756923037e-05, + "loss": 1.4891, + "step": 2052 + }, + { + "epoch": 0.22, + "learning_rate": 1.9200346151506983e-05, + "loss": 1.4486, + "step": 2053 + }, + { + "epoch": 0.22, + "learning_rate": 1.9198911313480938e-05, + "loss": 1.5091, + "step": 2054 + }, + { + "epoch": 0.22, + "learning_rate": 1.919747524303714e-05, + "loss": 1.4385, + "step": 2055 + }, + { + "epoch": 0.22, + "learning_rate": 1.9196037940367974e-05, + "loss": 1.4104, + "step": 2056 + }, + { + "epoch": 0.22, + "learning_rate": 1.9194599405666015e-05, + "loss": 1.4483, + "step": 2057 + }, + { + "epoch": 0.22, + "learning_rate": 1.9193159639123976e-05, + "loss": 1.4592, + "step": 2058 + }, + { + "epoch": 0.22, + "learning_rate": 1.919171864093476e-05, + "loss": 1.4975, + "step": 2059 + }, + { + "epoch": 0.22, + "learning_rate": 1.9190276411291423e-05, + "loss": 1.4727, + "step": 2060 + }, + { + "epoch": 0.22, + "learning_rate": 1.9188832950387178e-05, + "loss": 1.4791, + "step": 2061 + }, + { + "epoch": 0.22, + "learning_rate": 1.9187388258415423e-05, + "loss": 1.3806, + "step": 2062 + }, + { + "epoch": 0.22, + "learning_rate": 1.9185942335569697e-05, + "loss": 1.4514, + "step": 2063 + }, + { + "epoch": 0.22, + "learning_rate": 1.9184495182043727e-05, + "loss": 1.4389, + "step": 2064 + }, + { + "epoch": 0.22, + "learning_rate": 1.918304679803139e-05, + "loss": 1.5088, + "step": 2065 + }, + { + "epoch": 0.22, + "learning_rate": 1.9181597183726733e-05, + "loss": 1.4665, + "step": 2066 + }, + { + "epoch": 0.22, + "learning_rate": 1.9180146339323966e-05, + "loss": 1.489, + "step": 2067 + }, + { + "epoch": 0.22, + "learning_rate": 1.9178694265017466e-05, + "loss": 1.5215, + "step": 2068 + }, + { + "epoch": 0.22, + "learning_rate": 1.9177240961001775e-05, + "loss": 1.5152, + "step": 2069 + }, + { + "epoch": 0.22, + "learning_rate": 1.9175786427471594e-05, + "loss": 1.4418, + "step": 2070 + }, + { + "epoch": 0.22, + "learning_rate": 1.91743306646218e-05, + "loss": 1.5001, + "step": 2071 + }, + { + "epoch": 0.22, + "learning_rate": 1.9172873672647417e-05, + "loss": 1.4879, + "step": 2072 + }, + { + "epoch": 0.22, + "learning_rate": 1.917141545174366e-05, + "loss": 1.5299, + "step": 2073 + }, + { + "epoch": 0.22, + "learning_rate": 1.9169956002105877e-05, + "loss": 1.4602, + "step": 2074 + }, + { + "epoch": 0.22, + "learning_rate": 1.9168495323929605e-05, + "loss": 1.4921, + "step": 2075 + }, + { + "epoch": 0.22, + "learning_rate": 1.916703341741054e-05, + "loss": 1.4659, + "step": 2076 + }, + { + "epoch": 0.22, + "learning_rate": 1.9165570282744534e-05, + "loss": 1.4707, + "step": 2077 + }, + { + "epoch": 0.22, + "learning_rate": 1.9164105920127613e-05, + "loss": 1.5354, + "step": 2078 + }, + { + "epoch": 0.22, + "learning_rate": 1.9162640329755962e-05, + "loss": 1.526, + "step": 2079 + }, + { + "epoch": 0.22, + "learning_rate": 1.916117351182593e-05, + "loss": 1.6424, + "step": 2080 + }, + { + "epoch": 0.22, + "learning_rate": 1.915970546653404e-05, + "loss": 1.5048, + "step": 2081 + }, + { + "epoch": 0.22, + "learning_rate": 1.915823619407697e-05, + "loss": 1.5344, + "step": 2082 + }, + { + "epoch": 0.22, + "learning_rate": 1.915676569465156e-05, + "loss": 1.4604, + "step": 2083 + }, + { + "epoch": 0.22, + "learning_rate": 1.9155293968454826e-05, + "loss": 1.4929, + "step": 2084 + }, + { + "epoch": 0.22, + "learning_rate": 1.9153821015683937e-05, + "loss": 1.4106, + "step": 2085 + }, + { + "epoch": 0.22, + "learning_rate": 1.915234683653623e-05, + "loss": 1.4146, + "step": 2086 + }, + { + "epoch": 0.22, + "learning_rate": 1.9150871431209207e-05, + "loss": 1.4481, + "step": 2087 + }, + { + "epoch": 0.22, + "learning_rate": 1.914939479990054e-05, + "loss": 1.5206, + "step": 2088 + }, + { + "epoch": 0.22, + "learning_rate": 1.9147916942808054e-05, + "loss": 1.5073, + "step": 2089 + }, + { + "epoch": 0.22, + "learning_rate": 1.9146437860129745e-05, + "loss": 1.5196, + "step": 2090 + }, + { + "epoch": 0.22, + "learning_rate": 1.9144957552063775e-05, + "loss": 1.5389, + "step": 2091 + }, + { + "epoch": 0.22, + "learning_rate": 1.9143476018808463e-05, + "loss": 1.5207, + "step": 2092 + }, + { + "epoch": 0.22, + "learning_rate": 1.9141993260562298e-05, + "loss": 1.3717, + "step": 2093 + }, + { + "epoch": 0.22, + "learning_rate": 1.9140509277523937e-05, + "loss": 1.471, + "step": 2094 + }, + { + "epoch": 0.22, + "learning_rate": 1.9139024069892185e-05, + "loss": 1.4553, + "step": 2095 + }, + { + "epoch": 0.22, + "learning_rate": 1.9137537637866027e-05, + "loss": 1.5311, + "step": 2096 + }, + { + "epoch": 0.22, + "learning_rate": 1.9136049981644614e-05, + "loss": 1.4369, + "step": 2097 + }, + { + "epoch": 0.22, + "learning_rate": 1.913456110142724e-05, + "loss": 1.4528, + "step": 2098 + }, + { + "epoch": 0.22, + "learning_rate": 1.9133070997413384e-05, + "loss": 1.5294, + "step": 2099 + }, + { + "epoch": 0.22, + "learning_rate": 1.9131579669802685e-05, + "loss": 1.4588, + "step": 2100 + }, + { + "epoch": 0.22, + "learning_rate": 1.9130087118794934e-05, + "loss": 1.443, + "step": 2101 + }, + { + "epoch": 0.22, + "learning_rate": 1.9128593344590102e-05, + "loss": 1.4876, + "step": 2102 + }, + { + "epoch": 0.22, + "learning_rate": 1.912709834738831e-05, + "loss": 1.4874, + "step": 2103 + }, + { + "epoch": 0.22, + "learning_rate": 1.9125602127389856e-05, + "loss": 1.4966, + "step": 2104 + }, + { + "epoch": 0.22, + "learning_rate": 1.912410468479519e-05, + "loss": 1.5747, + "step": 2105 + }, + { + "epoch": 0.22, + "learning_rate": 1.9122606019804933e-05, + "loss": 1.4025, + "step": 2106 + }, + { + "epoch": 0.22, + "learning_rate": 1.912110613261987e-05, + "loss": 1.4755, + "step": 2107 + }, + { + "epoch": 0.22, + "learning_rate": 1.911960502344094e-05, + "loss": 1.4739, + "step": 2108 + }, + { + "epoch": 0.22, + "learning_rate": 1.911810269246926e-05, + "loss": 1.4992, + "step": 2109 + }, + { + "epoch": 0.22, + "learning_rate": 1.91165991399061e-05, + "loss": 1.4435, + "step": 2110 + }, + { + "epoch": 0.22, + "learning_rate": 1.91150943659529e-05, + "loss": 1.4918, + "step": 2111 + }, + { + "epoch": 0.22, + "learning_rate": 1.9113588370811258e-05, + "loss": 1.3818, + "step": 2112 + }, + { + "epoch": 0.22, + "learning_rate": 1.911208115468294e-05, + "loss": 1.5105, + "step": 2113 + }, + { + "epoch": 0.22, + "learning_rate": 1.9110572717769878e-05, + "loss": 1.6634, + "step": 2114 + }, + { + "epoch": 0.22, + "learning_rate": 1.9109063060274158e-05, + "loss": 1.5028, + "step": 2115 + }, + { + "epoch": 0.22, + "learning_rate": 1.9107552182398037e-05, + "loss": 1.6657, + "step": 2116 + }, + { + "epoch": 0.22, + "learning_rate": 1.9106040084343935e-05, + "loss": 1.5481, + "step": 2117 + }, + { + "epoch": 0.22, + "learning_rate": 1.910452676631444e-05, + "loss": 1.4505, + "step": 2118 + }, + { + "epoch": 0.22, + "learning_rate": 1.9103012228512284e-05, + "loss": 1.5173, + "step": 2119 + }, + { + "epoch": 0.22, + "learning_rate": 1.9101496471140385e-05, + "loss": 1.3788, + "step": 2120 + }, + { + "epoch": 0.22, + "learning_rate": 1.9099979494401814e-05, + "loss": 1.4649, + "step": 2121 + }, + { + "epoch": 0.22, + "learning_rate": 1.9098461298499805e-05, + "loss": 1.4204, + "step": 2122 + }, + { + "epoch": 0.22, + "learning_rate": 1.9096941883637766e-05, + "loss": 1.4439, + "step": 2123 + }, + { + "epoch": 0.22, + "learning_rate": 1.909542125001925e-05, + "loss": 1.6615, + "step": 2124 + }, + { + "epoch": 0.22, + "learning_rate": 1.9093899397847985e-05, + "loss": 1.4763, + "step": 2125 + }, + { + "epoch": 0.22, + "learning_rate": 1.909237632732786e-05, + "loss": 1.5353, + "step": 2126 + }, + { + "epoch": 0.22, + "learning_rate": 1.909085203866293e-05, + "loss": 1.442, + "step": 2127 + }, + { + "epoch": 0.22, + "learning_rate": 1.9089326532057408e-05, + "loss": 1.4782, + "step": 2128 + }, + { + "epoch": 0.22, + "learning_rate": 1.908779980771567e-05, + "loss": 1.4933, + "step": 2129 + }, + { + "epoch": 0.22, + "learning_rate": 1.9086271865842264e-05, + "loss": 1.5285, + "step": 2130 + }, + { + "epoch": 0.22, + "learning_rate": 1.9084742706641894e-05, + "loss": 1.4736, + "step": 2131 + }, + { + "epoch": 0.22, + "learning_rate": 1.9083212330319427e-05, + "loss": 1.4496, + "step": 2132 + }, + { + "epoch": 0.22, + "learning_rate": 1.908168073707989e-05, + "loss": 1.5099, + "step": 2133 + }, + { + "epoch": 0.22, + "learning_rate": 1.9080147927128483e-05, + "loss": 1.5235, + "step": 2134 + }, + { + "epoch": 0.22, + "learning_rate": 1.9078613900670556e-05, + "loss": 1.4769, + "step": 2135 + }, + { + "epoch": 0.22, + "learning_rate": 1.907707865791164e-05, + "loss": 1.5771, + "step": 2136 + }, + { + "epoch": 0.22, + "learning_rate": 1.907554219905741e-05, + "loss": 1.5116, + "step": 2137 + }, + { + "epoch": 0.22, + "learning_rate": 1.907400452431371e-05, + "loss": 1.5161, + "step": 2138 + }, + { + "epoch": 0.22, + "learning_rate": 1.9072465633886557e-05, + "loss": 1.4356, + "step": 2139 + }, + { + "epoch": 0.22, + "learning_rate": 1.9070925527982117e-05, + "loss": 1.509, + "step": 2140 + }, + { + "epoch": 0.22, + "learning_rate": 1.9069384206806723e-05, + "loss": 1.4681, + "step": 2141 + }, + { + "epoch": 0.22, + "learning_rate": 1.9067841670566883e-05, + "loss": 1.5254, + "step": 2142 + }, + { + "epoch": 0.22, + "learning_rate": 1.9066297919469242e-05, + "loss": 1.4797, + "step": 2143 + }, + { + "epoch": 0.22, + "learning_rate": 1.9064752953720636e-05, + "loss": 1.3996, + "step": 2144 + }, + { + "epoch": 0.22, + "learning_rate": 1.9063206773528042e-05, + "loss": 1.4457, + "step": 2145 + }, + { + "epoch": 0.23, + "learning_rate": 1.9061659379098617e-05, + "loss": 1.5126, + "step": 2146 + }, + { + "epoch": 0.23, + "learning_rate": 1.9060110770639664e-05, + "loss": 1.5925, + "step": 2147 + }, + { + "epoch": 0.23, + "learning_rate": 1.905856094835866e-05, + "loss": 1.5146, + "step": 2148 + }, + { + "epoch": 0.23, + "learning_rate": 1.905700991246324e-05, + "loss": 1.7256, + "step": 2149 + }, + { + "epoch": 0.23, + "learning_rate": 1.90554576631612e-05, + "loss": 1.57, + "step": 2150 + }, + { + "epoch": 0.23, + "learning_rate": 1.905390420066051e-05, + "loss": 1.3722, + "step": 2151 + }, + { + "epoch": 0.23, + "learning_rate": 1.9052349525169292e-05, + "loss": 1.3999, + "step": 2152 + }, + { + "epoch": 0.23, + "learning_rate": 1.9050793636895828e-05, + "loss": 1.586, + "step": 2153 + }, + { + "epoch": 0.23, + "learning_rate": 1.9049236536048567e-05, + "loss": 1.4884, + "step": 2154 + }, + { + "epoch": 0.23, + "learning_rate": 1.9047678222836127e-05, + "loss": 1.5898, + "step": 2155 + }, + { + "epoch": 0.23, + "learning_rate": 1.9046118697467278e-05, + "loss": 1.569, + "step": 2156 + }, + { + "epoch": 0.23, + "learning_rate": 1.904455796015095e-05, + "loss": 1.5592, + "step": 2157 + }, + { + "epoch": 0.23, + "learning_rate": 1.9042996011096253e-05, + "loss": 1.597, + "step": 2158 + }, + { + "epoch": 0.23, + "learning_rate": 1.904143285051244e-05, + "loss": 1.422, + "step": 2159 + }, + { + "epoch": 0.23, + "learning_rate": 1.903986847860894e-05, + "loss": 1.519, + "step": 2160 + }, + { + "epoch": 0.23, + "learning_rate": 1.9038302895595334e-05, + "loss": 1.5197, + "step": 2161 + }, + { + "epoch": 0.23, + "learning_rate": 1.903673610168137e-05, + "loss": 1.4655, + "step": 2162 + }, + { + "epoch": 0.23, + "learning_rate": 1.9035168097076965e-05, + "loss": 1.3909, + "step": 2163 + }, + { + "epoch": 0.23, + "learning_rate": 1.903359888199218e-05, + "loss": 1.4877, + "step": 2164 + }, + { + "epoch": 0.23, + "learning_rate": 1.903202845663726e-05, + "loss": 1.5123, + "step": 2165 + }, + { + "epoch": 0.23, + "learning_rate": 1.9030456821222593e-05, + "loss": 1.4906, + "step": 2166 + }, + { + "epoch": 0.23, + "learning_rate": 1.9028883975958745e-05, + "loss": 1.4574, + "step": 2167 + }, + { + "epoch": 0.23, + "learning_rate": 1.9027309921056435e-05, + "loss": 1.4571, + "step": 2168 + }, + { + "epoch": 0.23, + "learning_rate": 1.902573465672654e-05, + "loss": 1.4281, + "step": 2169 + }, + { + "epoch": 0.23, + "learning_rate": 1.9024158183180116e-05, + "loss": 1.5057, + "step": 2170 + }, + { + "epoch": 0.23, + "learning_rate": 1.902258050062836e-05, + "loss": 1.4514, + "step": 2171 + }, + { + "epoch": 0.23, + "learning_rate": 1.9021001609282646e-05, + "loss": 1.5055, + "step": 2172 + }, + { + "epoch": 0.23, + "learning_rate": 1.9019421509354505e-05, + "loss": 1.4578, + "step": 2173 + }, + { + "epoch": 0.23, + "learning_rate": 1.9017840201055625e-05, + "loss": 1.459, + "step": 2174 + }, + { + "epoch": 0.23, + "learning_rate": 1.9016257684597864e-05, + "loss": 1.5059, + "step": 2175 + }, + { + "epoch": 0.23, + "learning_rate": 1.901467396019324e-05, + "loss": 1.57, + "step": 2176 + }, + { + "epoch": 0.23, + "learning_rate": 1.901308902805393e-05, + "loss": 1.4924, + "step": 2177 + }, + { + "epoch": 0.23, + "learning_rate": 1.9011502888392273e-05, + "loss": 1.4979, + "step": 2178 + }, + { + "epoch": 0.23, + "learning_rate": 1.900991554142077e-05, + "loss": 1.5321, + "step": 2179 + }, + { + "epoch": 0.23, + "learning_rate": 1.9008326987352093e-05, + "loss": 1.493, + "step": 2180 + }, + { + "epoch": 0.23, + "learning_rate": 1.9006737226399056e-05, + "loss": 1.5111, + "step": 2181 + }, + { + "epoch": 0.23, + "learning_rate": 1.900514625877465e-05, + "loss": 1.4154, + "step": 2182 + }, + { + "epoch": 0.23, + "learning_rate": 1.900355408469203e-05, + "loss": 1.4934, + "step": 2183 + }, + { + "epoch": 0.23, + "learning_rate": 1.90019607043645e-05, + "loss": 1.5975, + "step": 2184 + }, + { + "epoch": 0.23, + "learning_rate": 1.9000366118005532e-05, + "loss": 1.3537, + "step": 2185 + }, + { + "epoch": 0.23, + "learning_rate": 1.899877032582876e-05, + "loss": 1.4583, + "step": 2186 + }, + { + "epoch": 0.23, + "learning_rate": 1.8997173328047984e-05, + "loss": 1.4586, + "step": 2187 + }, + { + "epoch": 0.23, + "learning_rate": 1.8995575124877156e-05, + "loss": 1.4774, + "step": 2188 + }, + { + "epoch": 0.23, + "learning_rate": 1.8993975716530394e-05, + "loss": 1.5025, + "step": 2189 + }, + { + "epoch": 0.23, + "eval_loss": 1.5263344049453735, + "eval_runtime": 77.1492, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 2189 + }, + { + "epoch": 0.23, + "learning_rate": 1.899237510322198e-05, + "loss": 1.5438, + "step": 2190 + }, + { + "epoch": 0.23, + "learning_rate": 1.899077328516635e-05, + "loss": 1.5181, + "step": 2191 + }, + { + "epoch": 0.23, + "learning_rate": 1.8989170262578112e-05, + "loss": 1.4454, + "step": 2192 + }, + { + "epoch": 0.23, + "learning_rate": 1.8987566035672028e-05, + "loss": 1.4882, + "step": 2193 + }, + { + "epoch": 0.23, + "learning_rate": 1.8985960604663026e-05, + "loss": 1.5073, + "step": 2194 + }, + { + "epoch": 0.23, + "learning_rate": 1.8984353969766187e-05, + "loss": 1.4478, + "step": 2195 + }, + { + "epoch": 0.23, + "learning_rate": 1.8982746131196763e-05, + "loss": 1.4768, + "step": 2196 + }, + { + "epoch": 0.23, + "learning_rate": 1.8981137089170162e-05, + "loss": 1.5116, + "step": 2197 + }, + { + "epoch": 0.23, + "learning_rate": 1.8979526843901952e-05, + "loss": 1.4202, + "step": 2198 + }, + { + "epoch": 0.23, + "learning_rate": 1.8977915395607867e-05, + "loss": 1.4736, + "step": 2199 + }, + { + "epoch": 0.23, + "learning_rate": 1.89763027445038e-05, + "loss": 1.4489, + "step": 2200 + }, + { + "epoch": 0.23, + "learning_rate": 1.8974688890805804e-05, + "loss": 1.4512, + "step": 2201 + }, + { + "epoch": 0.23, + "learning_rate": 1.897307383473009e-05, + "loss": 1.5091, + "step": 2202 + }, + { + "epoch": 0.23, + "learning_rate": 1.897145757649304e-05, + "loss": 1.5512, + "step": 2203 + }, + { + "epoch": 0.23, + "learning_rate": 1.8969840116311192e-05, + "loss": 1.406, + "step": 2204 + }, + { + "epoch": 0.23, + "learning_rate": 1.896822145440124e-05, + "loss": 1.4531, + "step": 2205 + }, + { + "epoch": 0.23, + "learning_rate": 1.896660159098004e-05, + "loss": 1.4379, + "step": 2206 + }, + { + "epoch": 0.23, + "learning_rate": 1.896498052626462e-05, + "loss": 1.4783, + "step": 2207 + }, + { + "epoch": 0.23, + "learning_rate": 1.896335826047216e-05, + "loss": 1.4801, + "step": 2208 + }, + { + "epoch": 0.23, + "learning_rate": 1.896173479381999e-05, + "loss": 1.4526, + "step": 2209 + }, + { + "epoch": 0.23, + "learning_rate": 1.8960110126525627e-05, + "loss": 1.4952, + "step": 2210 + }, + { + "epoch": 0.23, + "learning_rate": 1.895848425880673e-05, + "loss": 1.5299, + "step": 2211 + }, + { + "epoch": 0.23, + "learning_rate": 1.8956857190881125e-05, + "loss": 1.5274, + "step": 2212 + }, + { + "epoch": 0.23, + "learning_rate": 1.8955228922966792e-05, + "loss": 1.4415, + "step": 2213 + }, + { + "epoch": 0.23, + "learning_rate": 1.8953599455281884e-05, + "loss": 1.5311, + "step": 2214 + }, + { + "epoch": 0.23, + "learning_rate": 1.8951968788044702e-05, + "loss": 1.4972, + "step": 2215 + }, + { + "epoch": 0.23, + "learning_rate": 1.8950336921473715e-05, + "loss": 1.4966, + "step": 2216 + }, + { + "epoch": 0.23, + "learning_rate": 1.8948703855787553e-05, + "loss": 1.4683, + "step": 2217 + }, + { + "epoch": 0.23, + "learning_rate": 1.8947069591205005e-05, + "loss": 1.503, + "step": 2218 + }, + { + "epoch": 0.23, + "learning_rate": 1.8945434127945014e-05, + "loss": 1.4902, + "step": 2219 + }, + { + "epoch": 0.23, + "learning_rate": 1.8943797466226702e-05, + "loss": 1.4835, + "step": 2220 + }, + { + "epoch": 0.23, + "learning_rate": 1.8942159606269332e-05, + "loss": 1.535, + "step": 2221 + }, + { + "epoch": 0.23, + "learning_rate": 1.8940520548292332e-05, + "loss": 1.491, + "step": 2222 + }, + { + "epoch": 0.23, + "learning_rate": 1.89388802925153e-05, + "loss": 1.5157, + "step": 2223 + }, + { + "epoch": 0.23, + "learning_rate": 1.8937238839157987e-05, + "loss": 1.4779, + "step": 2224 + }, + { + "epoch": 0.23, + "learning_rate": 1.8935596188440302e-05, + "loss": 1.4902, + "step": 2225 + }, + { + "epoch": 0.23, + "learning_rate": 1.8933952340582323e-05, + "loss": 1.4988, + "step": 2226 + }, + { + "epoch": 0.23, + "learning_rate": 1.893230729580428e-05, + "loss": 1.4568, + "step": 2227 + }, + { + "epoch": 0.23, + "learning_rate": 1.8930661054326567e-05, + "loss": 1.5163, + "step": 2228 + }, + { + "epoch": 0.23, + "learning_rate": 1.892901361636974e-05, + "loss": 1.4472, + "step": 2229 + }, + { + "epoch": 0.23, + "learning_rate": 1.892736498215451e-05, + "loss": 1.4658, + "step": 2230 + }, + { + "epoch": 0.23, + "learning_rate": 1.8925715151901754e-05, + "loss": 1.4281, + "step": 2231 + }, + { + "epoch": 0.23, + "learning_rate": 1.892406412583251e-05, + "loss": 1.415, + "step": 2232 + }, + { + "epoch": 0.23, + "learning_rate": 1.8922411904167966e-05, + "loss": 1.464, + "step": 2233 + }, + { + "epoch": 0.23, + "learning_rate": 1.892075848712948e-05, + "loss": 1.5014, + "step": 2234 + }, + { + "epoch": 0.23, + "learning_rate": 1.8919103874938568e-05, + "loss": 1.4397, + "step": 2235 + }, + { + "epoch": 0.23, + "learning_rate": 1.891744806781691e-05, + "loss": 1.5508, + "step": 2236 + }, + { + "epoch": 0.23, + "learning_rate": 1.8915791065986335e-05, + "loss": 1.4749, + "step": 2237 + }, + { + "epoch": 0.23, + "learning_rate": 1.891413286966884e-05, + "loss": 1.4538, + "step": 2238 + }, + { + "epoch": 0.23, + "learning_rate": 1.891247347908658e-05, + "loss": 1.4405, + "step": 2239 + }, + { + "epoch": 0.23, + "learning_rate": 1.8910812894461878e-05, + "loss": 1.3562, + "step": 2240 + }, + { + "epoch": 0.24, + "learning_rate": 1.89091511160172e-05, + "loss": 1.4811, + "step": 2241 + }, + { + "epoch": 0.24, + "learning_rate": 1.8907488143975186e-05, + "loss": 1.4286, + "step": 2242 + }, + { + "epoch": 0.24, + "learning_rate": 1.890582397855863e-05, + "loss": 1.4493, + "step": 2243 + }, + { + "epoch": 0.24, + "learning_rate": 1.890415861999049e-05, + "loss": 1.5639, + "step": 2244 + }, + { + "epoch": 0.24, + "learning_rate": 1.890249206849388e-05, + "loss": 1.6375, + "step": 2245 + }, + { + "epoch": 0.24, + "learning_rate": 1.890082432429208e-05, + "loss": 1.4982, + "step": 2246 + }, + { + "epoch": 0.24, + "learning_rate": 1.889915538760851e-05, + "loss": 1.492, + "step": 2247 + }, + { + "epoch": 0.24, + "learning_rate": 1.8897485258666778e-05, + "loss": 1.4294, + "step": 2248 + }, + { + "epoch": 0.24, + "learning_rate": 1.8895813937690638e-05, + "loss": 1.4617, + "step": 2249 + }, + { + "epoch": 0.24, + "learning_rate": 1.8894141424904e-05, + "loss": 1.4763, + "step": 2250 + }, + { + "epoch": 0.24, + "learning_rate": 1.8892467720530937e-05, + "loss": 1.3989, + "step": 2251 + }, + { + "epoch": 0.24, + "learning_rate": 1.8890792824795687e-05, + "loss": 1.4803, + "step": 2252 + }, + { + "epoch": 0.24, + "learning_rate": 1.8889116737922638e-05, + "loss": 1.4734, + "step": 2253 + }, + { + "epoch": 0.24, + "learning_rate": 1.8887439460136342e-05, + "loss": 1.5069, + "step": 2254 + }, + { + "epoch": 0.24, + "learning_rate": 1.8885760991661514e-05, + "loss": 1.5565, + "step": 2255 + }, + { + "epoch": 0.24, + "learning_rate": 1.8884081332723028e-05, + "loss": 1.4707, + "step": 2256 + }, + { + "epoch": 0.24, + "learning_rate": 1.8882400483545913e-05, + "loss": 1.5077, + "step": 2257 + }, + { + "epoch": 0.24, + "learning_rate": 1.888071844435536e-05, + "loss": 1.5075, + "step": 2258 + }, + { + "epoch": 0.24, + "learning_rate": 1.8879035215376717e-05, + "loss": 1.5185, + "step": 2259 + }, + { + "epoch": 0.24, + "learning_rate": 1.887735079683549e-05, + "loss": 1.6266, + "step": 2260 + }, + { + "epoch": 0.24, + "learning_rate": 1.8875665188957354e-05, + "loss": 1.5013, + "step": 2261 + }, + { + "epoch": 0.24, + "learning_rate": 1.887397839196814e-05, + "loss": 1.4362, + "step": 2262 + }, + { + "epoch": 0.24, + "learning_rate": 1.8872290406093827e-05, + "loss": 1.4718, + "step": 2263 + }, + { + "epoch": 0.24, + "learning_rate": 1.8870601231560567e-05, + "loss": 1.5202, + "step": 2264 + }, + { + "epoch": 0.24, + "learning_rate": 1.8868910868594664e-05, + "loss": 1.5168, + "step": 2265 + }, + { + "epoch": 0.24, + "learning_rate": 1.8867219317422588e-05, + "loss": 1.5142, + "step": 2266 + }, + { + "epoch": 0.24, + "learning_rate": 1.8865526578270954e-05, + "loss": 1.4885, + "step": 2267 + }, + { + "epoch": 0.24, + "learning_rate": 1.8863832651366552e-05, + "loss": 1.5441, + "step": 2268 + }, + { + "epoch": 0.24, + "learning_rate": 1.8862137536936328e-05, + "loss": 1.4647, + "step": 2269 + }, + { + "epoch": 0.24, + "learning_rate": 1.8860441235207374e-05, + "loss": 1.5352, + "step": 2270 + }, + { + "epoch": 0.24, + "learning_rate": 1.8858743746406958e-05, + "loss": 1.4568, + "step": 2271 + }, + { + "epoch": 0.24, + "learning_rate": 1.8857045070762497e-05, + "loss": 1.4865, + "step": 2272 + }, + { + "epoch": 0.24, + "learning_rate": 1.8855345208501573e-05, + "loss": 1.4637, + "step": 2273 + }, + { + "epoch": 0.24, + "learning_rate": 1.8853644159851918e-05, + "loss": 1.4348, + "step": 2274 + }, + { + "epoch": 0.24, + "learning_rate": 1.8851941925041436e-05, + "loss": 1.4413, + "step": 2275 + }, + { + "epoch": 0.24, + "learning_rate": 1.8850238504298177e-05, + "loss": 1.4434, + "step": 2276 + }, + { + "epoch": 0.24, + "learning_rate": 1.884853389785036e-05, + "loss": 1.4822, + "step": 2277 + }, + { + "epoch": 0.24, + "learning_rate": 1.8846828105926356e-05, + "loss": 1.4632, + "step": 2278 + }, + { + "epoch": 0.24, + "learning_rate": 1.8845121128754698e-05, + "loss": 1.48, + "step": 2279 + }, + { + "epoch": 0.24, + "learning_rate": 1.8843412966564078e-05, + "loss": 1.4518, + "step": 2280 + }, + { + "epoch": 0.24, + "learning_rate": 1.884170361958334e-05, + "loss": 1.4334, + "step": 2281 + }, + { + "epoch": 0.24, + "learning_rate": 1.8839993088041502e-05, + "loss": 1.5131, + "step": 2282 + }, + { + "epoch": 0.24, + "learning_rate": 1.8838281372167724e-05, + "loss": 1.508, + "step": 2283 + }, + { + "epoch": 0.24, + "learning_rate": 1.8836568472191335e-05, + "loss": 1.4086, + "step": 2284 + }, + { + "epoch": 0.24, + "learning_rate": 1.883485438834182e-05, + "loss": 1.5021, + "step": 2285 + }, + { + "epoch": 0.24, + "learning_rate": 1.8833139120848817e-05, + "loss": 1.5083, + "step": 2286 + }, + { + "epoch": 0.24, + "learning_rate": 1.8831422669942137e-05, + "loss": 1.4162, + "step": 2287 + }, + { + "epoch": 0.24, + "learning_rate": 1.8829705035851734e-05, + "loss": 1.5494, + "step": 2288 + }, + { + "epoch": 0.24, + "learning_rate": 1.8827986218807724e-05, + "loss": 1.425, + "step": 2289 + }, + { + "epoch": 0.24, + "learning_rate": 1.8826266219040396e-05, + "loss": 1.5215, + "step": 2290 + }, + { + "epoch": 0.24, + "learning_rate": 1.8824545036780172e-05, + "loss": 1.5577, + "step": 2291 + }, + { + "epoch": 0.24, + "learning_rate": 1.8822822672257655e-05, + "loss": 1.4923, + "step": 2292 + }, + { + "epoch": 0.24, + "learning_rate": 1.8821099125703595e-05, + "loss": 1.4648, + "step": 2293 + }, + { + "epoch": 0.24, + "learning_rate": 1.8819374397348902e-05, + "loss": 1.471, + "step": 2294 + }, + { + "epoch": 0.24, + "learning_rate": 1.8817648487424648e-05, + "loss": 1.5658, + "step": 2295 + }, + { + "epoch": 0.24, + "learning_rate": 1.8815921396162058e-05, + "loss": 1.5348, + "step": 2296 + }, + { + "epoch": 0.24, + "learning_rate": 1.8814193123792518e-05, + "loss": 1.4081, + "step": 2297 + }, + { + "epoch": 0.24, + "learning_rate": 1.881246367054757e-05, + "loss": 1.4762, + "step": 2298 + }, + { + "epoch": 0.24, + "learning_rate": 1.8810733036658925e-05, + "loss": 1.4399, + "step": 2299 + }, + { + "epoch": 0.24, + "learning_rate": 1.8809001222358432e-05, + "loss": 1.4763, + "step": 2300 + }, + { + "epoch": 0.24, + "learning_rate": 1.880726822787812e-05, + "loss": 1.4874, + "step": 2301 + }, + { + "epoch": 0.24, + "learning_rate": 1.880553405345016e-05, + "loss": 1.4951, + "step": 2302 + }, + { + "epoch": 0.24, + "learning_rate": 1.8803798699306887e-05, + "loss": 1.4697, + "step": 2303 + }, + { + "epoch": 0.24, + "learning_rate": 1.880206216568079e-05, + "loss": 1.481, + "step": 2304 + }, + { + "epoch": 0.24, + "learning_rate": 1.880032445280453e-05, + "loss": 1.4485, + "step": 2305 + }, + { + "epoch": 0.24, + "learning_rate": 1.879858556091091e-05, + "loss": 1.4749, + "step": 2306 + }, + { + "epoch": 0.24, + "learning_rate": 1.8796845490232894e-05, + "loss": 1.5605, + "step": 2307 + }, + { + "epoch": 0.24, + "learning_rate": 1.879510424100361e-05, + "loss": 1.4835, + "step": 2308 + }, + { + "epoch": 0.24, + "learning_rate": 1.8793361813456346e-05, + "loss": 1.4344, + "step": 2309 + }, + { + "epoch": 0.24, + "learning_rate": 1.8791618207824532e-05, + "loss": 1.4571, + "step": 2310 + }, + { + "epoch": 0.24, + "learning_rate": 1.8789873424341772e-05, + "loss": 1.482, + "step": 2311 + }, + { + "epoch": 0.24, + "learning_rate": 1.8788127463241822e-05, + "loss": 1.4736, + "step": 2312 + }, + { + "epoch": 0.24, + "learning_rate": 1.8786380324758597e-05, + "loss": 1.4807, + "step": 2313 + }, + { + "epoch": 0.24, + "learning_rate": 1.8784632009126167e-05, + "loss": 1.4418, + "step": 2314 + }, + { + "epoch": 0.24, + "learning_rate": 1.878288251657876e-05, + "loss": 1.5248, + "step": 2315 + }, + { + "epoch": 0.24, + "learning_rate": 1.8781131847350768e-05, + "loss": 1.483, + "step": 2316 + }, + { + "epoch": 0.24, + "learning_rate": 1.877938000167673e-05, + "loss": 1.5474, + "step": 2317 + }, + { + "epoch": 0.24, + "learning_rate": 1.8777626979791347e-05, + "loss": 1.4671, + "step": 2318 + }, + { + "epoch": 0.24, + "learning_rate": 1.877587278192949e-05, + "loss": 1.3049, + "step": 2319 + }, + { + "epoch": 0.24, + "learning_rate": 1.877411740832616e-05, + "loss": 1.483, + "step": 2320 + }, + { + "epoch": 0.24, + "learning_rate": 1.877236085921655e-05, + "loss": 1.508, + "step": 2321 + }, + { + "epoch": 0.24, + "learning_rate": 1.8770603134835978e-05, + "loss": 1.4854, + "step": 2322 + }, + { + "epoch": 0.24, + "learning_rate": 1.8768844235419942e-05, + "loss": 1.4808, + "step": 2323 + }, + { + "epoch": 0.24, + "learning_rate": 1.8767084161204087e-05, + "loss": 1.5352, + "step": 2324 + }, + { + "epoch": 0.24, + "learning_rate": 1.8765322912424214e-05, + "loss": 1.5628, + "step": 2325 + }, + { + "epoch": 0.24, + "learning_rate": 1.8763560489316292e-05, + "loss": 1.494, + "step": 2326 + }, + { + "epoch": 0.24, + "learning_rate": 1.876179689211643e-05, + "loss": 1.509, + "step": 2327 + }, + { + "epoch": 0.24, + "learning_rate": 1.8760032121060918e-05, + "loss": 1.5021, + "step": 2328 + }, + { + "epoch": 0.24, + "learning_rate": 1.875826617638618e-05, + "loss": 1.4179, + "step": 2329 + }, + { + "epoch": 0.24, + "learning_rate": 1.8756499058328813e-05, + "loss": 1.4302, + "step": 2330 + }, + { + "epoch": 0.24, + "learning_rate": 1.8754730767125564e-05, + "loss": 1.4959, + "step": 2331 + }, + { + "epoch": 0.24, + "learning_rate": 1.8752961303013336e-05, + "loss": 1.4423, + "step": 2332 + }, + { + "epoch": 0.24, + "learning_rate": 1.8751190666229194e-05, + "loss": 1.4564, + "step": 2333 + }, + { + "epoch": 0.24, + "learning_rate": 1.8749418857010358e-05, + "loss": 1.4775, + "step": 2334 + }, + { + "epoch": 0.24, + "learning_rate": 1.8747645875594203e-05, + "loss": 1.4182, + "step": 2335 + }, + { + "epoch": 0.24, + "learning_rate": 1.8745871722218265e-05, + "loss": 1.3957, + "step": 2336 + }, + { + "epoch": 0.25, + "learning_rate": 1.8744096397120235e-05, + "loss": 1.4633, + "step": 2337 + }, + { + "epoch": 0.25, + "learning_rate": 1.874231990053796e-05, + "loss": 1.5512, + "step": 2338 + }, + { + "epoch": 0.25, + "learning_rate": 1.8740542232709444e-05, + "loss": 1.3461, + "step": 2339 + }, + { + "epoch": 0.25, + "learning_rate": 1.8738763393872848e-05, + "loss": 1.4754, + "step": 2340 + }, + { + "epoch": 0.25, + "learning_rate": 1.8736983384266495e-05, + "loss": 1.5448, + "step": 2341 + }, + { + "epoch": 0.25, + "learning_rate": 1.8735202204128854e-05, + "loss": 1.4491, + "step": 2342 + }, + { + "epoch": 0.25, + "learning_rate": 1.8733419853698566e-05, + "loss": 1.457, + "step": 2343 + }, + { + "epoch": 0.25, + "learning_rate": 1.8731636333214414e-05, + "loss": 1.4314, + "step": 2344 + }, + { + "epoch": 0.25, + "learning_rate": 1.8729851642915345e-05, + "loss": 1.3979, + "step": 2345 + }, + { + "epoch": 0.25, + "learning_rate": 1.8728065783040464e-05, + "loss": 1.4146, + "step": 2346 + }, + { + "epoch": 0.25, + "learning_rate": 1.8726278753829027e-05, + "loss": 1.4361, + "step": 2347 + }, + { + "epoch": 0.25, + "learning_rate": 1.872449055552045e-05, + "loss": 1.4989, + "step": 2348 + }, + { + "epoch": 0.25, + "learning_rate": 1.872270118835431e-05, + "loss": 1.5062, + "step": 2349 + }, + { + "epoch": 0.25, + "learning_rate": 1.872091065257033e-05, + "loss": 1.4509, + "step": 2350 + }, + { + "epoch": 0.25, + "learning_rate": 1.8719118948408403e-05, + "loss": 1.4631, + "step": 2351 + }, + { + "epoch": 0.25, + "learning_rate": 1.8717326076108566e-05, + "loss": 1.5119, + "step": 2352 + }, + { + "epoch": 0.25, + "learning_rate": 1.8715532035911017e-05, + "loss": 1.6347, + "step": 2353 + }, + { + "epoch": 0.25, + "learning_rate": 1.8713736828056115e-05, + "loss": 1.5526, + "step": 2354 + }, + { + "epoch": 0.25, + "learning_rate": 1.8711940452784368e-05, + "loss": 1.6348, + "step": 2355 + }, + { + "epoch": 0.25, + "learning_rate": 1.871014291033645e-05, + "loss": 1.5183, + "step": 2356 + }, + { + "epoch": 0.25, + "learning_rate": 1.8708344200953182e-05, + "loss": 1.458, + "step": 2357 + }, + { + "epoch": 0.25, + "learning_rate": 1.8706544324875545e-05, + "loss": 1.524, + "step": 2358 + }, + { + "epoch": 0.25, + "learning_rate": 1.8704743282344672e-05, + "loss": 1.4479, + "step": 2359 + }, + { + "epoch": 0.25, + "learning_rate": 1.870294107360186e-05, + "loss": 1.5408, + "step": 2360 + }, + { + "epoch": 0.25, + "learning_rate": 1.8701137698888563e-05, + "loss": 1.5007, + "step": 2361 + }, + { + "epoch": 0.25, + "learning_rate": 1.8699333158446382e-05, + "loss": 1.5132, + "step": 2362 + }, + { + "epoch": 0.25, + "learning_rate": 1.869752745251708e-05, + "loss": 1.4263, + "step": 2363 + }, + { + "epoch": 0.25, + "learning_rate": 1.8695720581342574e-05, + "loss": 1.422, + "step": 2364 + }, + { + "epoch": 0.25, + "learning_rate": 1.869391254516494e-05, + "loss": 1.4411, + "step": 2365 + }, + { + "epoch": 0.25, + "learning_rate": 1.8692103344226406e-05, + "loss": 1.4594, + "step": 2366 + }, + { + "epoch": 0.25, + "learning_rate": 1.8690292978769364e-05, + "loss": 1.4992, + "step": 2367 + }, + { + "epoch": 0.25, + "learning_rate": 1.868848144903635e-05, + "loss": 1.4822, + "step": 2368 + }, + { + "epoch": 0.25, + "learning_rate": 1.8686668755270064e-05, + "loss": 1.5402, + "step": 2369 + }, + { + "epoch": 0.25, + "learning_rate": 1.8684854897713363e-05, + "loss": 1.5268, + "step": 2370 + }, + { + "epoch": 0.25, + "learning_rate": 1.8683039876609258e-05, + "loss": 1.5587, + "step": 2371 + }, + { + "epoch": 0.25, + "learning_rate": 1.868122369220091e-05, + "loss": 1.4214, + "step": 2372 + }, + { + "epoch": 0.25, + "learning_rate": 1.8679406344731645e-05, + "loss": 1.5089, + "step": 2373 + }, + { + "epoch": 0.25, + "learning_rate": 1.867758783444494e-05, + "loss": 1.5067, + "step": 2374 + }, + { + "epoch": 0.25, + "learning_rate": 1.8675768161584427e-05, + "loss": 2.0616, + "step": 2375 + }, + { + "epoch": 0.25, + "learning_rate": 1.8673947326393903e-05, + "loss": 1.5617, + "step": 2376 + }, + { + "epoch": 0.25, + "learning_rate": 1.86721253291173e-05, + "loss": 1.4422, + "step": 2377 + }, + { + "epoch": 0.25, + "learning_rate": 1.867030216999873e-05, + "loss": 1.4727, + "step": 2378 + }, + { + "epoch": 0.25, + "learning_rate": 1.8668477849282443e-05, + "loss": 1.4152, + "step": 2379 + }, + { + "epoch": 0.25, + "learning_rate": 1.8666652367212856e-05, + "loss": 1.4376, + "step": 2380 + }, + { + "epoch": 0.25, + "learning_rate": 1.8664825724034534e-05, + "loss": 1.393, + "step": 2381 + }, + { + "epoch": 0.25, + "learning_rate": 1.8662997919992197e-05, + "loss": 1.4864, + "step": 2382 + }, + { + "epoch": 0.25, + "learning_rate": 1.866116895533073e-05, + "loss": 1.4261, + "step": 2383 + }, + { + "epoch": 0.25, + "learning_rate": 1.8659338830295163e-05, + "loss": 1.4555, + "step": 2384 + }, + { + "epoch": 0.25, + "learning_rate": 1.8657507545130687e-05, + "loss": 1.4939, + "step": 2385 + }, + { + "epoch": 0.25, + "learning_rate": 1.865567510008265e-05, + "loss": 1.4123, + "step": 2386 + }, + { + "epoch": 0.25, + "learning_rate": 1.8653841495396546e-05, + "loss": 1.4459, + "step": 2387 + }, + { + "epoch": 0.25, + "learning_rate": 1.8652006731318038e-05, + "loss": 1.396, + "step": 2388 + }, + { + "epoch": 0.25, + "eval_loss": 1.5139706134796143, + "eval_runtime": 77.2904, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 2388 + }, + { + "epoch": 0.25, + "learning_rate": 1.8650170808092936e-05, + "loss": 1.4666, + "step": 2389 + }, + { + "epoch": 0.25, + "learning_rate": 1.86483337259672e-05, + "loss": 1.5154, + "step": 2390 + }, + { + "epoch": 0.25, + "learning_rate": 1.864649548518696e-05, + "loss": 1.5163, + "step": 2391 + }, + { + "epoch": 0.25, + "learning_rate": 1.864465608599849e-05, + "loss": 1.4734, + "step": 2392 + }, + { + "epoch": 0.25, + "learning_rate": 1.864281552864822e-05, + "loss": 1.5217, + "step": 2393 + }, + { + "epoch": 0.25, + "learning_rate": 1.8640973813382737e-05, + "loss": 1.4694, + "step": 2394 + }, + { + "epoch": 0.25, + "learning_rate": 1.863913094044879e-05, + "loss": 1.4761, + "step": 2395 + }, + { + "epoch": 0.25, + "learning_rate": 1.863728691009327e-05, + "loss": 1.4766, + "step": 2396 + }, + { + "epoch": 0.25, + "learning_rate": 1.863544172256323e-05, + "loss": 1.5695, + "step": 2397 + }, + { + "epoch": 0.25, + "learning_rate": 1.8633595378105882e-05, + "loss": 1.5079, + "step": 2398 + }, + { + "epoch": 0.25, + "learning_rate": 1.8631747876968584e-05, + "loss": 1.4154, + "step": 2399 + }, + { + "epoch": 0.25, + "learning_rate": 1.862989921939886e-05, + "loss": 1.4488, + "step": 2400 + }, + { + "epoch": 0.25, + "learning_rate": 1.8628049405644376e-05, + "loss": 1.4279, + "step": 2401 + }, + { + "epoch": 0.25, + "learning_rate": 1.8626198435952966e-05, + "loss": 1.4896, + "step": 2402 + }, + { + "epoch": 0.25, + "learning_rate": 1.8624346310572602e-05, + "loss": 1.4315, + "step": 2403 + }, + { + "epoch": 0.25, + "learning_rate": 1.862249302975143e-05, + "loss": 1.4919, + "step": 2404 + }, + { + "epoch": 0.25, + "learning_rate": 1.8620638593737743e-05, + "loss": 1.4561, + "step": 2405 + }, + { + "epoch": 0.25, + "learning_rate": 1.8618783002779985e-05, + "loss": 1.4622, + "step": 2406 + }, + { + "epoch": 0.25, + "learning_rate": 1.8616926257126754e-05, + "loss": 1.4917, + "step": 2407 + }, + { + "epoch": 0.25, + "learning_rate": 1.861506835702681e-05, + "loss": 1.4962, + "step": 2408 + }, + { + "epoch": 0.25, + "learning_rate": 1.861320930272906e-05, + "loss": 1.4164, + "step": 2409 + }, + { + "epoch": 0.25, + "learning_rate": 1.8611349094482578e-05, + "loss": 1.4889, + "step": 2410 + }, + { + "epoch": 0.25, + "learning_rate": 1.8609487732536576e-05, + "loss": 1.543, + "step": 2411 + }, + { + "epoch": 0.25, + "learning_rate": 1.8607625217140433e-05, + "loss": 1.5417, + "step": 2412 + }, + { + "epoch": 0.25, + "learning_rate": 1.8605761548543674e-05, + "loss": 1.5304, + "step": 2413 + }, + { + "epoch": 0.25, + "learning_rate": 1.860389672699599e-05, + "loss": 1.4725, + "step": 2414 + }, + { + "epoch": 0.25, + "learning_rate": 1.860203075274721e-05, + "loss": 1.4745, + "step": 2415 + }, + { + "epoch": 0.25, + "learning_rate": 1.8600163626047334e-05, + "loss": 1.4656, + "step": 2416 + }, + { + "epoch": 0.25, + "learning_rate": 1.8598295347146503e-05, + "loss": 1.5287, + "step": 2417 + }, + { + "epoch": 0.25, + "learning_rate": 1.8596425916295023e-05, + "loss": 1.5024, + "step": 2418 + }, + { + "epoch": 0.25, + "learning_rate": 1.8594555333743348e-05, + "loss": 1.4527, + "step": 2419 + }, + { + "epoch": 0.25, + "learning_rate": 1.859268359974209e-05, + "loss": 1.4897, + "step": 2420 + }, + { + "epoch": 0.25, + "learning_rate": 1.859081071454201e-05, + "loss": 1.3554, + "step": 2421 + }, + { + "epoch": 0.25, + "learning_rate": 1.858893667839403e-05, + "loss": 1.4004, + "step": 2422 + }, + { + "epoch": 0.25, + "learning_rate": 1.858706149154922e-05, + "loss": 1.5582, + "step": 2423 + }, + { + "epoch": 0.25, + "learning_rate": 1.8585185154258803e-05, + "loss": 1.505, + "step": 2424 + }, + { + "epoch": 0.25, + "learning_rate": 1.858330766677417e-05, + "loss": 1.5043, + "step": 2425 + }, + { + "epoch": 0.25, + "learning_rate": 1.858142902934685e-05, + "loss": 1.439, + "step": 2426 + }, + { + "epoch": 0.25, + "learning_rate": 1.857954924222853e-05, + "loss": 1.4927, + "step": 2427 + }, + { + "epoch": 0.25, + "learning_rate": 1.8577668305671056e-05, + "loss": 1.5395, + "step": 2428 + }, + { + "epoch": 0.25, + "learning_rate": 1.8575786219926427e-05, + "loss": 1.4737, + "step": 2429 + }, + { + "epoch": 0.25, + "learning_rate": 1.8573902985246794e-05, + "loss": 1.6151, + "step": 2430 + }, + { + "epoch": 0.25, + "learning_rate": 1.857201860188446e-05, + "loss": 1.4313, + "step": 2431 + }, + { + "epoch": 0.26, + "learning_rate": 1.857013307009188e-05, + "loss": 1.4509, + "step": 2432 + }, + { + "epoch": 0.26, + "learning_rate": 1.8568246390121673e-05, + "loss": 1.3998, + "step": 2433 + }, + { + "epoch": 0.26, + "learning_rate": 1.8566358562226603e-05, + "loss": 1.5268, + "step": 2434 + }, + { + "epoch": 0.26, + "learning_rate": 1.8564469586659593e-05, + "loss": 1.4369, + "step": 2435 + }, + { + "epoch": 0.26, + "learning_rate": 1.8562579463673713e-05, + "loss": 1.4759, + "step": 2436 + }, + { + "epoch": 0.26, + "learning_rate": 1.8560688193522197e-05, + "loss": 1.4092, + "step": 2437 + }, + { + "epoch": 0.26, + "learning_rate": 1.855879577645842e-05, + "loss": 1.43, + "step": 2438 + }, + { + "epoch": 0.26, + "learning_rate": 1.855690221273592e-05, + "loss": 1.5143, + "step": 2439 + }, + { + "epoch": 0.26, + "learning_rate": 1.8555007502608385e-05, + "loss": 1.5482, + "step": 2440 + }, + { + "epoch": 0.26, + "learning_rate": 1.855311164632966e-05, + "loss": 1.4406, + "step": 2441 + }, + { + "epoch": 0.26, + "learning_rate": 1.8551214644153738e-05, + "loss": 1.4551, + "step": 2442 + }, + { + "epoch": 0.26, + "learning_rate": 1.8549316496334774e-05, + "loss": 1.4663, + "step": 2443 + }, + { + "epoch": 0.26, + "learning_rate": 1.8547417203127064e-05, + "loss": 1.4732, + "step": 2444 + }, + { + "epoch": 0.26, + "learning_rate": 1.8545516764785067e-05, + "loss": 1.5378, + "step": 2445 + }, + { + "epoch": 0.26, + "learning_rate": 1.8543615181563397e-05, + "loss": 1.4448, + "step": 2446 + }, + { + "epoch": 0.26, + "learning_rate": 1.854171245371681e-05, + "loss": 1.2861, + "step": 2447 + }, + { + "epoch": 0.26, + "learning_rate": 1.8539808581500228e-05, + "loss": 1.4405, + "step": 2448 + }, + { + "epoch": 0.26, + "learning_rate": 1.8537903565168716e-05, + "loss": 1.4876, + "step": 2449 + }, + { + "epoch": 0.26, + "learning_rate": 1.8535997404977506e-05, + "loss": 1.4119, + "step": 2450 + }, + { + "epoch": 0.26, + "learning_rate": 1.8534090101181967e-05, + "loss": 1.4451, + "step": 2451 + }, + { + "epoch": 0.26, + "learning_rate": 1.8532181654037632e-05, + "loss": 1.4035, + "step": 2452 + }, + { + "epoch": 0.26, + "learning_rate": 1.853027206380018e-05, + "loss": 1.4624, + "step": 2453 + }, + { + "epoch": 0.26, + "learning_rate": 1.852836133072545e-05, + "loss": 1.4935, + "step": 2454 + }, + { + "epoch": 0.26, + "learning_rate": 1.8526449455069434e-05, + "loss": 1.4834, + "step": 2455 + }, + { + "epoch": 0.26, + "learning_rate": 1.8524536437088266e-05, + "loss": 1.498, + "step": 2456 + }, + { + "epoch": 0.26, + "learning_rate": 1.8522622277038247e-05, + "loss": 1.3417, + "step": 2457 + }, + { + "epoch": 0.26, + "learning_rate": 1.852070697517583e-05, + "loss": 1.4455, + "step": 2458 + }, + { + "epoch": 0.26, + "learning_rate": 1.8518790531757607e-05, + "loss": 1.4119, + "step": 2459 + }, + { + "epoch": 0.26, + "learning_rate": 1.8516872947040337e-05, + "loss": 1.558, + "step": 2460 + }, + { + "epoch": 0.26, + "learning_rate": 1.8514954221280926e-05, + "loss": 1.4862, + "step": 2461 + }, + { + "epoch": 0.26, + "learning_rate": 1.8513034354736433e-05, + "loss": 1.6806, + "step": 2462 + }, + { + "epoch": 0.26, + "learning_rate": 1.8511113347664072e-05, + "loss": 1.438, + "step": 2463 + }, + { + "epoch": 0.26, + "learning_rate": 1.850919120032121e-05, + "loss": 1.4975, + "step": 2464 + }, + { + "epoch": 0.26, + "learning_rate": 1.850726791296536e-05, + "loss": 1.4409, + "step": 2465 + }, + { + "epoch": 0.26, + "learning_rate": 1.85053434858542e-05, + "loss": 1.4769, + "step": 2466 + }, + { + "epoch": 0.26, + "learning_rate": 1.8503417919245548e-05, + "loss": 1.5823, + "step": 2467 + }, + { + "epoch": 0.26, + "learning_rate": 1.8501491213397386e-05, + "loss": 1.4045, + "step": 2468 + }, + { + "epoch": 0.26, + "learning_rate": 1.8499563368567837e-05, + "loss": 1.4828, + "step": 2469 + }, + { + "epoch": 0.26, + "learning_rate": 1.849763438501519e-05, + "loss": 1.4684, + "step": 2470 + }, + { + "epoch": 0.26, + "learning_rate": 1.8495704262997873e-05, + "loss": 1.4577, + "step": 2471 + }, + { + "epoch": 0.26, + "learning_rate": 1.8493773002774475e-05, + "loss": 1.4759, + "step": 2472 + }, + { + "epoch": 0.26, + "learning_rate": 1.8491840604603736e-05, + "loss": 1.4259, + "step": 2473 + }, + { + "epoch": 0.26, + "learning_rate": 1.8489907068744543e-05, + "loss": 1.4717, + "step": 2474 + }, + { + "epoch": 0.26, + "learning_rate": 1.848797239545595e-05, + "loss": 1.4247, + "step": 2475 + }, + { + "epoch": 0.26, + "learning_rate": 1.8486036584997143e-05, + "loss": 1.4954, + "step": 2476 + }, + { + "epoch": 0.26, + "learning_rate": 1.8484099637627472e-05, + "loss": 1.4926, + "step": 2477 + }, + { + "epoch": 0.26, + "learning_rate": 1.8482161553606447e-05, + "loss": 1.487, + "step": 2478 + }, + { + "epoch": 0.26, + "learning_rate": 1.8480222333193715e-05, + "loss": 1.4553, + "step": 2479 + }, + { + "epoch": 0.26, + "learning_rate": 1.847828197664908e-05, + "loss": 1.4862, + "step": 2480 + }, + { + "epoch": 0.26, + "learning_rate": 1.8476340484232508e-05, + "loss": 1.4867, + "step": 2481 + }, + { + "epoch": 0.26, + "learning_rate": 1.8474397856204097e-05, + "loss": 1.4736, + "step": 2482 + }, + { + "epoch": 0.26, + "learning_rate": 1.8472454092824122e-05, + "loss": 1.4254, + "step": 2483 + }, + { + "epoch": 0.26, + "learning_rate": 1.8470509194352987e-05, + "loss": 1.4455, + "step": 2484 + }, + { + "epoch": 0.26, + "learning_rate": 1.8468563161051263e-05, + "loss": 1.4402, + "step": 2485 + }, + { + "epoch": 0.26, + "learning_rate": 1.846661599317967e-05, + "loss": 1.4611, + "step": 2486 + }, + { + "epoch": 0.26, + "learning_rate": 1.8464667690999073e-05, + "loss": 1.4814, + "step": 2487 + }, + { + "epoch": 0.26, + "learning_rate": 1.8462718254770503e-05, + "loss": 1.4559, + "step": 2488 + }, + { + "epoch": 0.26, + "learning_rate": 1.8460767684755127e-05, + "loss": 1.4667, + "step": 2489 + }, + { + "epoch": 0.26, + "learning_rate": 1.8458815981214274e-05, + "loss": 1.4427, + "step": 2490 + }, + { + "epoch": 0.26, + "learning_rate": 1.845686314440942e-05, + "loss": 1.4055, + "step": 2491 + }, + { + "epoch": 0.26, + "learning_rate": 1.8454909174602198e-05, + "loss": 1.5563, + "step": 2492 + }, + { + "epoch": 0.26, + "learning_rate": 1.845295407205439e-05, + "loss": 1.4631, + "step": 2493 + }, + { + "epoch": 0.26, + "learning_rate": 1.8450997837027925e-05, + "loss": 1.4887, + "step": 2494 + }, + { + "epoch": 0.26, + "learning_rate": 1.8449040469784895e-05, + "loss": 1.5212, + "step": 2495 + }, + { + "epoch": 0.26, + "learning_rate": 1.844708197058753e-05, + "loss": 1.5582, + "step": 2496 + }, + { + "epoch": 0.26, + "learning_rate": 1.844512233969822e-05, + "loss": 1.4599, + "step": 2497 + }, + { + "epoch": 0.26, + "learning_rate": 1.844316157737951e-05, + "loss": 1.4546, + "step": 2498 + }, + { + "epoch": 0.26, + "learning_rate": 1.844119968389409e-05, + "loss": 1.4631, + "step": 2499 + }, + { + "epoch": 0.26, + "learning_rate": 1.84392366595048e-05, + "loss": 1.4817, + "step": 2500 + }, + { + "epoch": 0.26, + "learning_rate": 1.8437272504474636e-05, + "loss": 1.4214, + "step": 2501 + }, + { + "epoch": 0.26, + "learning_rate": 1.8435307219066744e-05, + "loss": 1.471, + "step": 2502 + }, + { + "epoch": 0.26, + "learning_rate": 1.8433340803544424e-05, + "loss": 1.4693, + "step": 2503 + }, + { + "epoch": 0.26, + "learning_rate": 1.8431373258171127e-05, + "loss": 1.6297, + "step": 2504 + }, + { + "epoch": 0.26, + "learning_rate": 1.842940458321045e-05, + "loss": 1.5916, + "step": 2505 + }, + { + "epoch": 0.26, + "learning_rate": 1.842743477892614e-05, + "loss": 1.4754, + "step": 2506 + }, + { + "epoch": 0.26, + "learning_rate": 1.842546384558211e-05, + "loss": 1.4828, + "step": 2507 + }, + { + "epoch": 0.26, + "learning_rate": 1.842349178344241e-05, + "loss": 1.4239, + "step": 2508 + }, + { + "epoch": 0.26, + "learning_rate": 1.8421518592771243e-05, + "loss": 1.5028, + "step": 2509 + }, + { + "epoch": 0.26, + "learning_rate": 1.841954427383297e-05, + "loss": 1.4848, + "step": 2510 + }, + { + "epoch": 0.26, + "learning_rate": 1.8417568826892097e-05, + "loss": 1.4617, + "step": 2511 + }, + { + "epoch": 0.26, + "learning_rate": 1.8415592252213284e-05, + "loss": 1.4266, + "step": 2512 + }, + { + "epoch": 0.26, + "learning_rate": 1.8413614550061344e-05, + "loss": 1.4321, + "step": 2513 + }, + { + "epoch": 0.26, + "learning_rate": 1.841163572070123e-05, + "loss": 1.4693, + "step": 2514 + }, + { + "epoch": 0.26, + "learning_rate": 1.840965576439806e-05, + "loss": 1.4257, + "step": 2515 + }, + { + "epoch": 0.26, + "learning_rate": 1.84076746814171e-05, + "loss": 1.4488, + "step": 2516 + }, + { + "epoch": 0.26, + "learning_rate": 1.840569247202376e-05, + "loss": 1.5348, + "step": 2517 + }, + { + "epoch": 0.26, + "learning_rate": 1.8403709136483604e-05, + "loss": 1.477, + "step": 2518 + }, + { + "epoch": 0.26, + "learning_rate": 1.840172467506235e-05, + "loss": 1.443, + "step": 2519 + }, + { + "epoch": 0.26, + "learning_rate": 1.839973908802587e-05, + "loss": 1.4772, + "step": 2520 + }, + { + "epoch": 0.26, + "learning_rate": 1.839775237564017e-05, + "loss": 1.4443, + "step": 2521 + }, + { + "epoch": 0.26, + "learning_rate": 1.839576453817143e-05, + "loss": 1.4063, + "step": 2522 + }, + { + "epoch": 0.26, + "learning_rate": 1.8393775575885963e-05, + "loss": 1.5178, + "step": 2523 + }, + { + "epoch": 0.26, + "learning_rate": 1.8391785489050235e-05, + "loss": 1.4337, + "step": 2524 + }, + { + "epoch": 0.26, + "learning_rate": 1.8389794277930875e-05, + "loss": 1.4512, + "step": 2525 + }, + { + "epoch": 0.26, + "learning_rate": 1.838780194279465e-05, + "loss": 1.5578, + "step": 2526 + }, + { + "epoch": 0.26, + "learning_rate": 1.8385808483908484e-05, + "loss": 1.4606, + "step": 2527 + }, + { + "epoch": 0.27, + "learning_rate": 1.8383813901539444e-05, + "loss": 1.4957, + "step": 2528 + }, + { + "epoch": 0.27, + "learning_rate": 1.838181819595476e-05, + "loss": 1.4914, + "step": 2529 + }, + { + "epoch": 0.27, + "learning_rate": 1.8379821367421802e-05, + "loss": 1.4785, + "step": 2530 + }, + { + "epoch": 0.27, + "learning_rate": 1.837782341620809e-05, + "loss": 1.4052, + "step": 2531 + }, + { + "epoch": 0.27, + "learning_rate": 1.8375824342581303e-05, + "loss": 1.4807, + "step": 2532 + }, + { + "epoch": 0.27, + "learning_rate": 1.8373824146809264e-05, + "loss": 1.4313, + "step": 2533 + }, + { + "epoch": 0.27, + "learning_rate": 1.8371822829159945e-05, + "loss": 1.4374, + "step": 2534 + }, + { + "epoch": 0.27, + "learning_rate": 1.836982038990148e-05, + "loss": 1.4482, + "step": 2535 + }, + { + "epoch": 0.27, + "learning_rate": 1.8367816829302133e-05, + "loss": 1.5231, + "step": 2536 + }, + { + "epoch": 0.27, + "learning_rate": 1.8365812147630337e-05, + "loss": 1.4101, + "step": 2537 + }, + { + "epoch": 0.27, + "learning_rate": 1.8363806345154666e-05, + "loss": 1.4372, + "step": 2538 + }, + { + "epoch": 0.27, + "learning_rate": 1.8361799422143845e-05, + "loss": 1.4808, + "step": 2539 + }, + { + "epoch": 0.27, + "learning_rate": 1.835979137886675e-05, + "loss": 1.3515, + "step": 2540 + }, + { + "epoch": 0.27, + "learning_rate": 1.8357782215592412e-05, + "loss": 1.5284, + "step": 2541 + }, + { + "epoch": 0.27, + "learning_rate": 1.835577193259e-05, + "loss": 1.4222, + "step": 2542 + }, + { + "epoch": 0.27, + "learning_rate": 1.8353760530128846e-05, + "loss": 1.4522, + "step": 2543 + }, + { + "epoch": 0.27, + "learning_rate": 1.835174800847842e-05, + "loss": 1.4487, + "step": 2544 + }, + { + "epoch": 0.27, + "learning_rate": 1.8349734367908355e-05, + "loss": 1.3688, + "step": 2545 + }, + { + "epoch": 0.27, + "learning_rate": 1.8347719608688422e-05, + "loss": 1.483, + "step": 2546 + }, + { + "epoch": 0.27, + "learning_rate": 1.8345703731088554e-05, + "loss": 1.4733, + "step": 2547 + }, + { + "epoch": 0.27, + "learning_rate": 1.8343686735378816e-05, + "loss": 1.4594, + "step": 2548 + }, + { + "epoch": 0.27, + "learning_rate": 1.834166862182944e-05, + "loss": 1.4648, + "step": 2549 + }, + { + "epoch": 0.27, + "learning_rate": 1.8339649390710807e-05, + "loss": 1.5249, + "step": 2550 + }, + { + "epoch": 0.27, + "learning_rate": 1.8337629042293434e-05, + "loss": 1.4744, + "step": 2551 + }, + { + "epoch": 0.27, + "learning_rate": 1.8335607576847994e-05, + "loss": 1.5094, + "step": 2552 + }, + { + "epoch": 0.27, + "learning_rate": 1.8333584994645318e-05, + "loss": 1.5122, + "step": 2553 + }, + { + "epoch": 0.27, + "learning_rate": 1.8331561295956374e-05, + "loss": 1.537, + "step": 2554 + }, + { + "epoch": 0.27, + "learning_rate": 1.832953648105229e-05, + "loss": 1.4691, + "step": 2555 + }, + { + "epoch": 0.27, + "learning_rate": 1.8327510550204343e-05, + "loss": 1.4969, + "step": 2556 + }, + { + "epoch": 0.27, + "learning_rate": 1.8325483503683944e-05, + "loss": 1.4596, + "step": 2557 + }, + { + "epoch": 0.27, + "learning_rate": 1.8323455341762675e-05, + "loss": 1.435, + "step": 2558 + }, + { + "epoch": 0.27, + "learning_rate": 1.8321426064712255e-05, + "loss": 1.4883, + "step": 2559 + }, + { + "epoch": 0.27, + "learning_rate": 1.8319395672804554e-05, + "loss": 1.3758, + "step": 2560 + }, + { + "epoch": 0.27, + "learning_rate": 1.8317364166311592e-05, + "loss": 1.4352, + "step": 2561 + }, + { + "epoch": 0.27, + "learning_rate": 1.831533154550554e-05, + "loss": 1.5072, + "step": 2562 + }, + { + "epoch": 0.27, + "learning_rate": 1.8313297810658718e-05, + "loss": 1.4476, + "step": 2563 + }, + { + "epoch": 0.27, + "learning_rate": 1.831126296204359e-05, + "loss": 1.507, + "step": 2564 + }, + { + "epoch": 0.27, + "learning_rate": 1.8309226999932777e-05, + "loss": 1.4677, + "step": 2565 + }, + { + "epoch": 0.27, + "learning_rate": 1.8307189924599044e-05, + "loss": 1.4537, + "step": 2566 + }, + { + "epoch": 0.27, + "learning_rate": 1.8305151736315307e-05, + "loss": 1.4584, + "step": 2567 + }, + { + "epoch": 0.27, + "learning_rate": 1.8303112435354634e-05, + "loss": 1.4944, + "step": 2568 + }, + { + "epoch": 0.27, + "learning_rate": 1.8301072021990232e-05, + "loss": 1.4379, + "step": 2569 + }, + { + "epoch": 0.27, + "learning_rate": 1.8299030496495475e-05, + "loss": 1.539, + "step": 2570 + }, + { + "epoch": 0.27, + "learning_rate": 1.829698785914386e-05, + "loss": 1.4421, + "step": 2571 + }, + { + "epoch": 0.27, + "learning_rate": 1.8294944110209063e-05, + "loss": 1.4693, + "step": 2572 + }, + { + "epoch": 0.27, + "learning_rate": 1.8292899249964887e-05, + "loss": 1.3239, + "step": 2573 + }, + { + "epoch": 0.27, + "learning_rate": 1.8290853278685284e-05, + "loss": 1.472, + "step": 2574 + }, + { + "epoch": 0.27, + "learning_rate": 1.8288806196644374e-05, + "loss": 1.536, + "step": 2575 + }, + { + "epoch": 0.27, + "learning_rate": 1.8286758004116405e-05, + "loss": 1.4644, + "step": 2576 + }, + { + "epoch": 0.27, + "learning_rate": 1.8284708701375783e-05, + "loss": 1.4537, + "step": 2577 + }, + { + "epoch": 0.27, + "learning_rate": 1.8282658288697067e-05, + "loss": 1.4359, + "step": 2578 + }, + { + "epoch": 0.27, + "learning_rate": 1.8280606766354955e-05, + "loss": 1.4842, + "step": 2579 + }, + { + "epoch": 0.27, + "learning_rate": 1.8278554134624302e-05, + "loss": 1.4664, + "step": 2580 + }, + { + "epoch": 0.27, + "learning_rate": 1.8276500393780105e-05, + "loss": 1.4632, + "step": 2581 + }, + { + "epoch": 0.27, + "learning_rate": 1.827444554409751e-05, + "loss": 1.4996, + "step": 2582 + }, + { + "epoch": 0.27, + "learning_rate": 1.827238958585182e-05, + "loss": 1.3399, + "step": 2583 + }, + { + "epoch": 0.27, + "learning_rate": 1.8270332519318476e-05, + "loss": 1.3928, + "step": 2584 + }, + { + "epoch": 0.27, + "learning_rate": 1.8268274344773074e-05, + "loss": 1.4993, + "step": 2585 + }, + { + "epoch": 0.27, + "learning_rate": 1.8266215062491356e-05, + "loss": 1.5398, + "step": 2586 + }, + { + "epoch": 0.27, + "learning_rate": 1.826415467274921e-05, + "loss": 1.4353, + "step": 2587 + }, + { + "epoch": 0.27, + "eval_loss": 1.5104212760925293, + "eval_runtime": 77.3448, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2587 + }, + { + "epoch": 0.27, + "learning_rate": 1.8262093175822685e-05, + "loss": 1.4889, + "step": 2588 + }, + { + "epoch": 0.27, + "learning_rate": 1.826003057198796e-05, + "loss": 1.4912, + "step": 2589 + }, + { + "epoch": 0.27, + "learning_rate": 1.825796686152137e-05, + "loss": 1.4884, + "step": 2590 + }, + { + "epoch": 0.27, + "learning_rate": 1.8255902044699404e-05, + "loss": 1.478, + "step": 2591 + }, + { + "epoch": 0.27, + "learning_rate": 1.8253836121798692e-05, + "loss": 1.6549, + "step": 2592 + }, + { + "epoch": 0.27, + "learning_rate": 1.8251769093096018e-05, + "loss": 1.5146, + "step": 2593 + }, + { + "epoch": 0.27, + "learning_rate": 1.8249700958868306e-05, + "loss": 1.4797, + "step": 2594 + }, + { + "epoch": 0.27, + "learning_rate": 1.8247631719392634e-05, + "loss": 1.4655, + "step": 2595 + }, + { + "epoch": 0.27, + "learning_rate": 1.824556137494623e-05, + "loss": 1.4517, + "step": 2596 + }, + { + "epoch": 0.27, + "learning_rate": 1.8243489925806458e-05, + "loss": 1.4936, + "step": 2597 + }, + { + "epoch": 0.27, + "learning_rate": 1.8241417372250852e-05, + "loss": 1.4614, + "step": 2598 + }, + { + "epoch": 0.27, + "learning_rate": 1.8239343714557073e-05, + "loss": 1.4475, + "step": 2599 + }, + { + "epoch": 0.27, + "learning_rate": 1.8237268953002937e-05, + "loss": 1.5435, + "step": 2600 + }, + { + "epoch": 0.27, + "learning_rate": 1.8235193087866413e-05, + "loss": 1.4616, + "step": 2601 + }, + { + "epoch": 0.27, + "learning_rate": 1.8233116119425612e-05, + "loss": 1.4578, + "step": 2602 + }, + { + "epoch": 0.27, + "learning_rate": 1.8231038047958795e-05, + "loss": 1.434, + "step": 2603 + }, + { + "epoch": 0.27, + "learning_rate": 1.8228958873744368e-05, + "loss": 1.5335, + "step": 2604 + }, + { + "epoch": 0.27, + "learning_rate": 1.8226878597060887e-05, + "loss": 1.415, + "step": 2605 + }, + { + "epoch": 0.27, + "learning_rate": 1.8224797218187058e-05, + "loss": 1.6165, + "step": 2606 + }, + { + "epoch": 0.27, + "learning_rate": 1.822271473740173e-05, + "loss": 1.372, + "step": 2607 + }, + { + "epoch": 0.27, + "learning_rate": 1.8220631154983907e-05, + "loss": 1.4855, + "step": 2608 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218546471212727e-05, + "loss": 1.4093, + "step": 2609 + }, + { + "epoch": 0.27, + "learning_rate": 1.821646068636749e-05, + "loss": 1.4852, + "step": 2610 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214373800727637e-05, + "loss": 1.6959, + "step": 2611 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212285814572755e-05, + "loss": 1.3874, + "step": 2612 + }, + { + "epoch": 0.27, + "learning_rate": 1.821019672818258e-05, + "loss": 1.4425, + "step": 2613 + }, + { + "epoch": 0.27, + "learning_rate": 1.8208106541837e-05, + "loss": 1.6097, + "step": 2614 + }, + { + "epoch": 0.27, + "learning_rate": 1.8206015255816045e-05, + "loss": 1.5675, + "step": 2615 + }, + { + "epoch": 0.27, + "learning_rate": 1.820392287039989e-05, + "loss": 1.4039, + "step": 2616 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201829385868866e-05, + "loss": 1.4872, + "step": 2617 + }, + { + "epoch": 0.27, + "learning_rate": 1.819973480250344e-05, + "loss": 1.4645, + "step": 2618 + }, + { + "epoch": 0.27, + "learning_rate": 1.8197639120584237e-05, + "loss": 1.4923, + "step": 2619 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195542340392025e-05, + "loss": 1.4294, + "step": 2620 + }, + { + "epoch": 0.27, + "learning_rate": 1.8193444462207717e-05, + "loss": 1.4315, + "step": 2621 + }, + { + "epoch": 0.27, + "learning_rate": 1.8191345486312372e-05, + "loss": 1.3972, + "step": 2622 + }, + { + "epoch": 0.28, + "learning_rate": 1.8189245412987205e-05, + "loss": 1.462, + "step": 2623 + }, + { + "epoch": 0.28, + "learning_rate": 1.8187144242513567e-05, + "loss": 1.4738, + "step": 2624 + }, + { + "epoch": 0.28, + "learning_rate": 1.818504197517296e-05, + "loss": 1.4935, + "step": 2625 + }, + { + "epoch": 0.28, + "learning_rate": 1.8182938611247038e-05, + "loss": 1.4231, + "step": 2626 + }, + { + "epoch": 0.28, + "learning_rate": 1.81808341510176e-05, + "loss": 1.4031, + "step": 2627 + }, + { + "epoch": 0.28, + "learning_rate": 1.817872859476658e-05, + "loss": 1.5822, + "step": 2628 + }, + { + "epoch": 0.28, + "learning_rate": 1.8176621942776075e-05, + "loss": 1.432, + "step": 2629 + }, + { + "epoch": 0.28, + "learning_rate": 1.8174514195328324e-05, + "loss": 1.5565, + "step": 2630 + }, + { + "epoch": 0.28, + "learning_rate": 1.8172405352705704e-05, + "loss": 1.4895, + "step": 2631 + }, + { + "epoch": 0.28, + "learning_rate": 1.8170295415190754e-05, + "loss": 1.4032, + "step": 2632 + }, + { + "epoch": 0.28, + "learning_rate": 1.8168184383066144e-05, + "loss": 1.4253, + "step": 2633 + }, + { + "epoch": 0.28, + "learning_rate": 1.8166072256614702e-05, + "loss": 1.5162, + "step": 2634 + }, + { + "epoch": 0.28, + "learning_rate": 1.81639590361194e-05, + "loss": 1.4609, + "step": 2635 + }, + { + "epoch": 0.28, + "learning_rate": 1.816184472186335e-05, + "loss": 1.4351, + "step": 2636 + }, + { + "epoch": 0.28, + "learning_rate": 1.8159729314129823e-05, + "loss": 1.4738, + "step": 2637 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157612813202224e-05, + "loss": 1.5986, + "step": 2638 + }, + { + "epoch": 0.28, + "learning_rate": 1.815549521936411e-05, + "loss": 1.4633, + "step": 2639 + }, + { + "epoch": 0.28, + "learning_rate": 1.8153376532899184e-05, + "loss": 1.4404, + "step": 2640 + }, + { + "epoch": 0.28, + "learning_rate": 1.81512567540913e-05, + "loss": 1.4256, + "step": 2641 + }, + { + "epoch": 0.28, + "learning_rate": 1.814913588322445e-05, + "loss": 1.4054, + "step": 2642 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147013920582773e-05, + "loss": 1.4134, + "step": 2643 + }, + { + "epoch": 0.28, + "learning_rate": 1.8144890866450567e-05, + "loss": 1.4098, + "step": 2644 + }, + { + "epoch": 0.28, + "learning_rate": 1.814276672111226e-05, + "loss": 1.4593, + "step": 2645 + }, + { + "epoch": 0.28, + "learning_rate": 1.814064148485243e-05, + "loss": 1.4679, + "step": 2646 + }, + { + "epoch": 0.28, + "learning_rate": 1.8138515157955812e-05, + "loss": 1.5234, + "step": 2647 + }, + { + "epoch": 0.28, + "learning_rate": 1.8136387740707272e-05, + "loss": 1.4568, + "step": 2648 + }, + { + "epoch": 0.28, + "learning_rate": 1.8134259233391836e-05, + "loss": 1.5057, + "step": 2649 + }, + { + "epoch": 0.28, + "learning_rate": 1.8132129636294665e-05, + "loss": 1.3643, + "step": 2650 + }, + { + "epoch": 0.28, + "learning_rate": 1.812999894970107e-05, + "loss": 1.4766, + "step": 2651 + }, + { + "epoch": 0.28, + "learning_rate": 1.812786717389651e-05, + "loss": 1.5701, + "step": 2652 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125734309166587e-05, + "loss": 1.5341, + "step": 2653 + }, + { + "epoch": 0.28, + "learning_rate": 1.812360035579705e-05, + "loss": 1.3596, + "step": 2654 + }, + { + "epoch": 0.28, + "learning_rate": 1.8121465314073793e-05, + "loss": 1.4847, + "step": 2655 + }, + { + "epoch": 0.28, + "learning_rate": 1.811932918428286e-05, + "loss": 1.4664, + "step": 2656 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117191966710438e-05, + "loss": 1.4673, + "step": 2657 + }, + { + "epoch": 0.28, + "learning_rate": 1.8115053661642856e-05, + "loss": 1.4712, + "step": 2658 + }, + { + "epoch": 0.28, + "learning_rate": 1.811291426936659e-05, + "loss": 1.4458, + "step": 2659 + }, + { + "epoch": 0.28, + "learning_rate": 1.811077379016827e-05, + "loss": 1.4667, + "step": 2660 + }, + { + "epoch": 0.28, + "learning_rate": 1.810863222433466e-05, + "loss": 1.4695, + "step": 2661 + }, + { + "epoch": 0.28, + "learning_rate": 1.8106489572152677e-05, + "loss": 1.5263, + "step": 2662 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104345833909376e-05, + "loss": 1.4148, + "step": 2663 + }, + { + "epoch": 0.28, + "learning_rate": 1.8102201009891976e-05, + "loss": 1.3955, + "step": 2664 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100055100387814e-05, + "loss": 1.6056, + "step": 2665 + }, + { + "epoch": 0.28, + "learning_rate": 1.8097908105684396e-05, + "loss": 1.5394, + "step": 2666 + }, + { + "epoch": 0.28, + "learning_rate": 1.809576002606936e-05, + "loss": 1.479, + "step": 2667 + }, + { + "epoch": 0.28, + "learning_rate": 1.8093610861830494e-05, + "loss": 1.4492, + "step": 2668 + }, + { + "epoch": 0.28, + "learning_rate": 1.8091460613255728e-05, + "loss": 1.4172, + "step": 2669 + }, + { + "epoch": 0.28, + "learning_rate": 1.808930928063315e-05, + "loss": 1.4498, + "step": 2670 + }, + { + "epoch": 0.28, + "learning_rate": 1.808715686425097e-05, + "loss": 1.6203, + "step": 2671 + }, + { + "epoch": 0.28, + "learning_rate": 1.8085003364397567e-05, + "loss": 1.435, + "step": 2672 + }, + { + "epoch": 0.28, + "learning_rate": 1.808284878136145e-05, + "loss": 1.4489, + "step": 2673 + }, + { + "epoch": 0.28, + "learning_rate": 1.8080693115431277e-05, + "loss": 1.4416, + "step": 2674 + }, + { + "epoch": 0.28, + "learning_rate": 1.8078536366895853e-05, + "loss": 1.422, + "step": 2675 + }, + { + "epoch": 0.28, + "learning_rate": 1.8076378536044128e-05, + "loss": 1.4039, + "step": 2676 + }, + { + "epoch": 0.28, + "learning_rate": 1.8074219623165195e-05, + "loss": 1.4705, + "step": 2677 + }, + { + "epoch": 0.28, + "learning_rate": 1.807205962854829e-05, + "loss": 1.5031, + "step": 2678 + }, + { + "epoch": 0.28, + "learning_rate": 1.8069898552482806e-05, + "loss": 1.4812, + "step": 2679 + }, + { + "epoch": 0.28, + "learning_rate": 1.806773639525826e-05, + "loss": 1.4129, + "step": 2680 + }, + { + "epoch": 0.28, + "learning_rate": 1.8065573157164332e-05, + "loss": 1.4559, + "step": 2681 + }, + { + "epoch": 0.28, + "learning_rate": 1.806340883849084e-05, + "loss": 1.3878, + "step": 2682 + }, + { + "epoch": 0.28, + "learning_rate": 1.8061243439527744e-05, + "loss": 1.4752, + "step": 2683 + }, + { + "epoch": 0.28, + "learning_rate": 1.8059076960565156e-05, + "loss": 1.4089, + "step": 2684 + }, + { + "epoch": 0.28, + "learning_rate": 1.8056909401893326e-05, + "loss": 1.4736, + "step": 2685 + }, + { + "epoch": 0.28, + "learning_rate": 1.8054740763802654e-05, + "loss": 1.3796, + "step": 2686 + }, + { + "epoch": 0.28, + "learning_rate": 1.805257104658368e-05, + "loss": 1.4412, + "step": 2687 + }, + { + "epoch": 0.28, + "learning_rate": 1.8050400250527086e-05, + "loss": 1.4639, + "step": 2688 + }, + { + "epoch": 0.28, + "learning_rate": 1.804822837592371e-05, + "loss": 1.4076, + "step": 2689 + }, + { + "epoch": 0.28, + "learning_rate": 1.804605542306452e-05, + "loss": 1.4627, + "step": 2690 + }, + { + "epoch": 0.28, + "learning_rate": 1.8043881392240642e-05, + "loss": 1.5249, + "step": 2691 + }, + { + "epoch": 0.28, + "learning_rate": 1.804170628374334e-05, + "loss": 1.4312, + "step": 2692 + }, + { + "epoch": 0.28, + "learning_rate": 1.803953009786402e-05, + "loss": 1.5676, + "step": 2693 + }, + { + "epoch": 0.28, + "learning_rate": 1.8037352834894233e-05, + "loss": 1.5072, + "step": 2694 + }, + { + "epoch": 0.28, + "learning_rate": 1.803517449512568e-05, + "loss": 1.5662, + "step": 2695 + }, + { + "epoch": 0.28, + "learning_rate": 1.8032995078850207e-05, + "loss": 1.4771, + "step": 2696 + }, + { + "epoch": 0.28, + "learning_rate": 1.803081458635979e-05, + "loss": 1.412, + "step": 2697 + }, + { + "epoch": 0.28, + "learning_rate": 1.8028633017946564e-05, + "loss": 1.497, + "step": 2698 + }, + { + "epoch": 0.28, + "learning_rate": 1.8026450373902804e-05, + "loss": 1.4528, + "step": 2699 + }, + { + "epoch": 0.28, + "learning_rate": 1.802426665452093e-05, + "loss": 1.4785, + "step": 2700 + }, + { + "epoch": 0.28, + "learning_rate": 1.8022081860093493e-05, + "loss": 1.6411, + "step": 2701 + }, + { + "epoch": 0.28, + "learning_rate": 1.8019895990913213e-05, + "loss": 1.4459, + "step": 2702 + }, + { + "epoch": 0.28, + "learning_rate": 1.8017709047272932e-05, + "loss": 1.4418, + "step": 2703 + }, + { + "epoch": 0.28, + "learning_rate": 1.801552102946565e-05, + "loss": 1.4409, + "step": 2704 + }, + { + "epoch": 0.28, + "learning_rate": 1.8013331937784498e-05, + "loss": 1.4651, + "step": 2705 + }, + { + "epoch": 0.28, + "learning_rate": 1.8011141772522766e-05, + "loss": 1.4161, + "step": 2706 + }, + { + "epoch": 0.28, + "learning_rate": 1.8008950533973876e-05, + "loss": 1.458, + "step": 2707 + }, + { + "epoch": 0.28, + "learning_rate": 1.8006758222431398e-05, + "loss": 1.4477, + "step": 2708 + }, + { + "epoch": 0.28, + "learning_rate": 1.800456483818904e-05, + "loss": 1.4433, + "step": 2709 + }, + { + "epoch": 0.28, + "learning_rate": 1.8002370381540672e-05, + "loss": 1.5005, + "step": 2710 + }, + { + "epoch": 0.28, + "learning_rate": 1.8000174852780282e-05, + "loss": 1.4945, + "step": 2711 + }, + { + "epoch": 0.28, + "learning_rate": 1.7997978252202023e-05, + "loss": 1.4298, + "step": 2712 + }, + { + "epoch": 0.28, + "learning_rate": 1.7995780580100177e-05, + "loss": 1.3812, + "step": 2713 + }, + { + "epoch": 0.28, + "learning_rate": 1.799358183676918e-05, + "loss": 1.5559, + "step": 2714 + }, + { + "epoch": 0.28, + "learning_rate": 1.79913820225036e-05, + "loss": 1.4316, + "step": 2715 + }, + { + "epoch": 0.28, + "learning_rate": 1.798918113759817e-05, + "loss": 1.419, + "step": 2716 + }, + { + "epoch": 0.28, + "learning_rate": 1.7986979182347733e-05, + "loss": 1.43, + "step": 2717 + }, + { + "epoch": 0.29, + "learning_rate": 1.798477615704731e-05, + "loss": 1.4964, + "step": 2718 + }, + { + "epoch": 0.29, + "learning_rate": 1.7982572061992044e-05, + "loss": 1.4417, + "step": 2719 + }, + { + "epoch": 0.29, + "learning_rate": 1.7980366897477227e-05, + "loss": 1.4562, + "step": 2720 + }, + { + "epoch": 0.29, + "learning_rate": 1.7978160663798295e-05, + "loss": 1.4386, + "step": 2721 + }, + { + "epoch": 0.29, + "learning_rate": 1.7975953361250824e-05, + "loss": 1.445, + "step": 2722 + }, + { + "epoch": 0.29, + "learning_rate": 1.797374499013054e-05, + "loss": 1.4549, + "step": 2723 + }, + { + "epoch": 0.29, + "learning_rate": 1.7971535550733305e-05, + "loss": 1.5205, + "step": 2724 + }, + { + "epoch": 0.29, + "learning_rate": 1.796932504335513e-05, + "loss": 1.4632, + "step": 2725 + }, + { + "epoch": 0.29, + "learning_rate": 1.796711346829216e-05, + "loss": 1.3767, + "step": 2726 + }, + { + "epoch": 0.29, + "learning_rate": 1.79649008258407e-05, + "loss": 1.4098, + "step": 2727 + }, + { + "epoch": 0.29, + "learning_rate": 1.7962687116297178e-05, + "loss": 1.4675, + "step": 2728 + }, + { + "epoch": 0.29, + "learning_rate": 1.7960472339958176e-05, + "loss": 1.6048, + "step": 2729 + }, + { + "epoch": 0.29, + "learning_rate": 1.7958256497120418e-05, + "loss": 1.5432, + "step": 2730 + }, + { + "epoch": 0.29, + "learning_rate": 1.7956039588080774e-05, + "loss": 1.5453, + "step": 2731 + }, + { + "epoch": 0.29, + "learning_rate": 1.7953821613136246e-05, + "loss": 1.4246, + "step": 2732 + }, + { + "epoch": 0.29, + "learning_rate": 1.7951602572583988e-05, + "loss": 1.3987, + "step": 2733 + }, + { + "epoch": 0.29, + "learning_rate": 1.7949382466721295e-05, + "loss": 1.4943, + "step": 2734 + }, + { + "epoch": 0.29, + "learning_rate": 1.7947161295845606e-05, + "loss": 1.4385, + "step": 2735 + }, + { + "epoch": 0.29, + "learning_rate": 1.7944939060254497e-05, + "loss": 1.4165, + "step": 2736 + }, + { + "epoch": 0.29, + "learning_rate": 1.7942715760245692e-05, + "loss": 1.4004, + "step": 2737 + }, + { + "epoch": 0.29, + "learning_rate": 1.7940491396117063e-05, + "loss": 1.4577, + "step": 2738 + }, + { + "epoch": 0.29, + "learning_rate": 1.7938265968166602e-05, + "loss": 1.4649, + "step": 2739 + }, + { + "epoch": 0.29, + "learning_rate": 1.7936039476692473e-05, + "loss": 1.5273, + "step": 2740 + }, + { + "epoch": 0.29, + "learning_rate": 1.7933811921992962e-05, + "loss": 1.4325, + "step": 2741 + }, + { + "epoch": 0.29, + "learning_rate": 1.793158330436651e-05, + "loss": 1.4388, + "step": 2742 + }, + { + "epoch": 0.29, + "learning_rate": 1.7929353624111687e-05, + "loss": 1.4124, + "step": 2743 + }, + { + "epoch": 0.29, + "learning_rate": 1.7927122881527222e-05, + "loss": 1.5449, + "step": 2744 + }, + { + "epoch": 0.29, + "learning_rate": 1.7924891076911964e-05, + "loss": 1.4728, + "step": 2745 + }, + { + "epoch": 0.29, + "learning_rate": 1.7922658210564932e-05, + "loss": 1.5103, + "step": 2746 + }, + { + "epoch": 0.29, + "learning_rate": 1.792042428278526e-05, + "loss": 1.5975, + "step": 2747 + }, + { + "epoch": 0.29, + "learning_rate": 1.7918189293872247e-05, + "loss": 1.567, + "step": 2748 + }, + { + "epoch": 0.29, + "learning_rate": 1.7915953244125318e-05, + "loss": 1.57, + "step": 2749 + }, + { + "epoch": 0.29, + "learning_rate": 1.791371613384405e-05, + "loss": 1.4372, + "step": 2750 + }, + { + "epoch": 0.29, + "learning_rate": 1.7911477963328155e-05, + "loss": 1.4053, + "step": 2751 + }, + { + "epoch": 0.29, + "learning_rate": 1.7909238732877492e-05, + "loss": 1.3782, + "step": 2752 + }, + { + "epoch": 0.29, + "learning_rate": 1.790699844279206e-05, + "loss": 1.4401, + "step": 2753 + }, + { + "epoch": 0.29, + "learning_rate": 1.7904757093372e-05, + "loss": 1.3749, + "step": 2754 + }, + { + "epoch": 0.29, + "learning_rate": 1.79025146849176e-05, + "loss": 1.4909, + "step": 2755 + }, + { + "epoch": 0.29, + "learning_rate": 1.7900271217729273e-05, + "loss": 1.4103, + "step": 2756 + }, + { + "epoch": 0.29, + "learning_rate": 1.7898026692107597e-05, + "loss": 1.4986, + "step": 2757 + }, + { + "epoch": 0.29, + "learning_rate": 1.7895781108353278e-05, + "loss": 1.5449, + "step": 2758 + }, + { + "epoch": 0.29, + "learning_rate": 1.789353446676717e-05, + "loss": 1.5583, + "step": 2759 + }, + { + "epoch": 0.29, + "learning_rate": 1.7891286767650254e-05, + "loss": 1.5342, + "step": 2760 + }, + { + "epoch": 0.29, + "learning_rate": 1.7889038011303673e-05, + "loss": 1.4233, + "step": 2761 + }, + { + "epoch": 0.29, + "learning_rate": 1.7886788198028707e-05, + "loss": 1.3433, + "step": 2762 + }, + { + "epoch": 0.29, + "learning_rate": 1.788453732812676e-05, + "loss": 1.4451, + "step": 2763 + }, + { + "epoch": 0.29, + "learning_rate": 1.78822854018994e-05, + "loss": 1.4506, + "step": 2764 + }, + { + "epoch": 0.29, + "learning_rate": 1.7880032419648324e-05, + "loss": 1.4386, + "step": 2765 + }, + { + "epoch": 0.29, + "learning_rate": 1.7877778381675374e-05, + "loss": 1.4512, + "step": 2766 + }, + { + "epoch": 0.29, + "learning_rate": 1.7875523288282535e-05, + "loss": 1.4319, + "step": 2767 + }, + { + "epoch": 0.29, + "learning_rate": 1.7873267139771932e-05, + "loss": 1.4753, + "step": 2768 + }, + { + "epoch": 0.29, + "learning_rate": 1.787100993644583e-05, + "loss": 1.4044, + "step": 2769 + }, + { + "epoch": 0.29, + "learning_rate": 1.786875167860663e-05, + "loss": 1.4382, + "step": 2770 + }, + { + "epoch": 0.29, + "learning_rate": 1.786649236655689e-05, + "loss": 1.3977, + "step": 2771 + }, + { + "epoch": 0.29, + "learning_rate": 1.7864232000599298e-05, + "loss": 1.4473, + "step": 2772 + }, + { + "epoch": 0.29, + "learning_rate": 1.7861970581036678e-05, + "loss": 1.4666, + "step": 2773 + }, + { + "epoch": 0.29, + "learning_rate": 1.785970810817201e-05, + "loss": 1.5299, + "step": 2774 + }, + { + "epoch": 0.29, + "learning_rate": 1.7857444582308402e-05, + "loss": 1.3974, + "step": 2775 + }, + { + "epoch": 0.29, + "learning_rate": 1.7855180003749114e-05, + "loss": 1.4603, + "step": 2776 + }, + { + "epoch": 0.29, + "learning_rate": 1.7852914372797535e-05, + "loss": 1.463, + "step": 2777 + }, + { + "epoch": 0.29, + "learning_rate": 1.7850647689757205e-05, + "loss": 1.5317, + "step": 2778 + }, + { + "epoch": 0.29, + "learning_rate": 1.78483799549318e-05, + "loss": 1.4669, + "step": 2779 + }, + { + "epoch": 0.29, + "learning_rate": 1.784611116862514e-05, + "loss": 1.5293, + "step": 2780 + }, + { + "epoch": 0.29, + "learning_rate": 1.7843841331141177e-05, + "loss": 1.5802, + "step": 2781 + }, + { + "epoch": 0.29, + "learning_rate": 1.7841570442784024e-05, + "loss": 1.4486, + "step": 2782 + }, + { + "epoch": 0.29, + "learning_rate": 1.7839298503857913e-05, + "loss": 1.4674, + "step": 2783 + }, + { + "epoch": 0.29, + "learning_rate": 1.7837025514667224e-05, + "loss": 1.4662, + "step": 2784 + }, + { + "epoch": 0.29, + "learning_rate": 1.7834751475516484e-05, + "loss": 1.3555, + "step": 2785 + }, + { + "epoch": 0.29, + "learning_rate": 1.783247638671035e-05, + "loss": 1.4307, + "step": 2786 + }, + { + "epoch": 0.29, + "eval_loss": 1.500258445739746, + "eval_runtime": 77.406, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 2786 + }, + { + "epoch": 0.29, + "learning_rate": 1.7830200248553633e-05, + "loss": 1.4596, + "step": 2787 + }, + { + "epoch": 0.29, + "learning_rate": 1.7827923061351273e-05, + "loss": 1.6118, + "step": 2788 + }, + { + "epoch": 0.29, + "learning_rate": 1.7825644825408353e-05, + "loss": 1.4782, + "step": 2789 + }, + { + "epoch": 0.29, + "learning_rate": 1.78233655410301e-05, + "loss": 1.4681, + "step": 2790 + }, + { + "epoch": 0.29, + "learning_rate": 1.782108520852188e-05, + "loss": 1.6281, + "step": 2791 + }, + { + "epoch": 0.29, + "learning_rate": 1.78188038281892e-05, + "loss": 1.4446, + "step": 2792 + }, + { + "epoch": 0.29, + "learning_rate": 1.7816521400337704e-05, + "loss": 1.479, + "step": 2793 + }, + { + "epoch": 0.29, + "learning_rate": 1.7814237925273178e-05, + "loss": 1.5457, + "step": 2794 + }, + { + "epoch": 0.29, + "learning_rate": 1.7811953403301547e-05, + "loss": 1.3928, + "step": 2795 + }, + { + "epoch": 0.29, + "learning_rate": 1.780966783472889e-05, + "loss": 1.4321, + "step": 2796 + }, + { + "epoch": 0.29, + "learning_rate": 1.78073812198614e-05, + "loss": 1.5734, + "step": 2797 + }, + { + "epoch": 0.29, + "learning_rate": 1.7805093559005432e-05, + "loss": 1.4356, + "step": 2798 + }, + { + "epoch": 0.29, + "learning_rate": 1.7802804852467473e-05, + "loss": 1.4656, + "step": 2799 + }, + { + "epoch": 0.29, + "learning_rate": 1.780051510055415e-05, + "loss": 1.4052, + "step": 2800 + }, + { + "epoch": 0.29, + "learning_rate": 1.7798224303572228e-05, + "loss": 1.4758, + "step": 2801 + }, + { + "epoch": 0.29, + "learning_rate": 1.7795932461828622e-05, + "loss": 1.4326, + "step": 2802 + }, + { + "epoch": 0.29, + "learning_rate": 1.7793639575630376e-05, + "loss": 1.3409, + "step": 2803 + }, + { + "epoch": 0.29, + "learning_rate": 1.7791345645284678e-05, + "loss": 1.4175, + "step": 2804 + }, + { + "epoch": 0.29, + "learning_rate": 1.7789050671098853e-05, + "loss": 1.383, + "step": 2805 + }, + { + "epoch": 0.29, + "learning_rate": 1.7786754653380373e-05, + "loss": 1.5162, + "step": 2806 + }, + { + "epoch": 0.29, + "learning_rate": 1.7784457592436847e-05, + "loss": 1.4899, + "step": 2807 + }, + { + "epoch": 0.29, + "learning_rate": 1.7782159488576016e-05, + "loss": 1.4874, + "step": 2808 + }, + { + "epoch": 0.29, + "learning_rate": 1.777986034210577e-05, + "loss": 1.4363, + "step": 2809 + }, + { + "epoch": 0.29, + "learning_rate": 1.7777560153334134e-05, + "loss": 1.4223, + "step": 2810 + }, + { + "epoch": 0.29, + "learning_rate": 1.7775258922569273e-05, + "loss": 1.4792, + "step": 2811 + }, + { + "epoch": 0.29, + "learning_rate": 1.77729566501195e-05, + "loss": 1.4475, + "step": 2812 + }, + { + "epoch": 0.29, + "learning_rate": 1.7770653336293253e-05, + "loss": 1.5157, + "step": 2813 + }, + { + "epoch": 0.3, + "learning_rate": 1.776834898139912e-05, + "loss": 1.389, + "step": 2814 + }, + { + "epoch": 0.3, + "learning_rate": 1.7766043585745824e-05, + "loss": 1.4358, + "step": 2815 + }, + { + "epoch": 0.3, + "learning_rate": 1.776373714964223e-05, + "loss": 1.4297, + "step": 2816 + }, + { + "epoch": 0.3, + "learning_rate": 1.7761429673397344e-05, + "loss": 1.4102, + "step": 2817 + }, + { + "epoch": 0.3, + "learning_rate": 1.77591211573203e-05, + "loss": 1.4572, + "step": 2818 + }, + { + "epoch": 0.3, + "learning_rate": 1.775681160172039e-05, + "loss": 1.448, + "step": 2819 + }, + { + "epoch": 0.3, + "learning_rate": 1.7754501006907025e-05, + "loss": 1.4426, + "step": 2820 + }, + { + "epoch": 0.3, + "learning_rate": 1.7752189373189773e-05, + "loss": 1.4566, + "step": 2821 + }, + { + "epoch": 0.3, + "learning_rate": 1.7749876700878332e-05, + "loss": 1.4267, + "step": 2822 + }, + { + "epoch": 0.3, + "learning_rate": 1.7747562990282538e-05, + "loss": 1.3951, + "step": 2823 + }, + { + "epoch": 0.3, + "learning_rate": 1.7745248241712373e-05, + "loss": 1.4668, + "step": 2824 + }, + { + "epoch": 0.3, + "learning_rate": 1.774293245547795e-05, + "loss": 1.4924, + "step": 2825 + }, + { + "epoch": 0.3, + "learning_rate": 1.7740615631889525e-05, + "loss": 1.5258, + "step": 2826 + }, + { + "epoch": 0.3, + "learning_rate": 1.7738297771257496e-05, + "loss": 1.4323, + "step": 2827 + }, + { + "epoch": 0.3, + "learning_rate": 1.7735978873892393e-05, + "loss": 1.439, + "step": 2828 + }, + { + "epoch": 0.3, + "learning_rate": 1.773365894010489e-05, + "loss": 1.5658, + "step": 2829 + }, + { + "epoch": 0.3, + "learning_rate": 1.77313379702058e-05, + "loss": 1.4607, + "step": 2830 + }, + { + "epoch": 0.3, + "learning_rate": 1.7729015964506073e-05, + "loss": 1.5544, + "step": 2831 + }, + { + "epoch": 0.3, + "learning_rate": 1.7726692923316798e-05, + "loss": 1.4232, + "step": 2832 + }, + { + "epoch": 0.3, + "learning_rate": 1.77243688469492e-05, + "loss": 1.415, + "step": 2833 + }, + { + "epoch": 0.3, + "learning_rate": 1.772204373571465e-05, + "loss": 1.4658, + "step": 2834 + }, + { + "epoch": 0.3, + "learning_rate": 1.7719717589924647e-05, + "loss": 1.4678, + "step": 2835 + }, + { + "epoch": 0.3, + "learning_rate": 1.771739040989084e-05, + "loss": 1.3021, + "step": 2836 + }, + { + "epoch": 0.3, + "learning_rate": 1.771506219592501e-05, + "loss": 1.4045, + "step": 2837 + }, + { + "epoch": 0.3, + "learning_rate": 1.7712732948339085e-05, + "loss": 1.4593, + "step": 2838 + }, + { + "epoch": 0.3, + "learning_rate": 1.7710402667445108e-05, + "loss": 1.4175, + "step": 2839 + }, + { + "epoch": 0.3, + "learning_rate": 1.770807135355529e-05, + "loss": 1.3939, + "step": 2840 + }, + { + "epoch": 0.3, + "learning_rate": 1.7705739006981963e-05, + "loss": 1.6089, + "step": 2841 + }, + { + "epoch": 0.3, + "learning_rate": 1.77034056280376e-05, + "loss": 1.3952, + "step": 2842 + }, + { + "epoch": 0.3, + "learning_rate": 1.7701071217034818e-05, + "loss": 1.5086, + "step": 2843 + }, + { + "epoch": 0.3, + "learning_rate": 1.7698735774286362e-05, + "loss": 1.4706, + "step": 2844 + }, + { + "epoch": 0.3, + "learning_rate": 1.7696399300105128e-05, + "loss": 1.4286, + "step": 2845 + }, + { + "epoch": 0.3, + "learning_rate": 1.7694061794804137e-05, + "loss": 1.4418, + "step": 2846 + }, + { + "epoch": 0.3, + "learning_rate": 1.7691723258696562e-05, + "loss": 1.516, + "step": 2847 + }, + { + "epoch": 0.3, + "learning_rate": 1.76893836920957e-05, + "loss": 1.4354, + "step": 2848 + }, + { + "epoch": 0.3, + "learning_rate": 1.7687043095314998e-05, + "loss": 1.7503, + "step": 2849 + }, + { + "epoch": 0.3, + "learning_rate": 1.7684701468668032e-05, + "loss": 1.5985, + "step": 2850 + }, + { + "epoch": 0.3, + "learning_rate": 1.768235881246852e-05, + "loss": 1.442, + "step": 2851 + }, + { + "epoch": 0.3, + "learning_rate": 1.7680015127030322e-05, + "loss": 1.4924, + "step": 2852 + }, + { + "epoch": 0.3, + "learning_rate": 1.7677670412667425e-05, + "loss": 1.4461, + "step": 2853 + }, + { + "epoch": 0.3, + "learning_rate": 1.7675324669693968e-05, + "loss": 1.3823, + "step": 2854 + }, + { + "epoch": 0.3, + "learning_rate": 1.767297789842421e-05, + "loss": 1.452, + "step": 2855 + }, + { + "epoch": 0.3, + "learning_rate": 1.767063009917257e-05, + "loss": 1.46, + "step": 2856 + }, + { + "epoch": 0.3, + "learning_rate": 1.7668281272253587e-05, + "loss": 1.4129, + "step": 2857 + }, + { + "epoch": 0.3, + "learning_rate": 1.766593141798194e-05, + "loss": 1.4057, + "step": 2858 + }, + { + "epoch": 0.3, + "learning_rate": 1.7663580536672456e-05, + "loss": 1.5162, + "step": 2859 + }, + { + "epoch": 0.3, + "learning_rate": 1.7661228628640087e-05, + "loss": 1.5177, + "step": 2860 + }, + { + "epoch": 0.3, + "learning_rate": 1.7658875694199933e-05, + "loss": 1.4548, + "step": 2861 + }, + { + "epoch": 0.3, + "learning_rate": 1.7656521733667223e-05, + "loss": 1.4511, + "step": 2862 + }, + { + "epoch": 0.3, + "learning_rate": 1.765416674735733e-05, + "loss": 1.4778, + "step": 2863 + }, + { + "epoch": 0.3, + "learning_rate": 1.765181073558576e-05, + "loss": 1.3935, + "step": 2864 + }, + { + "epoch": 0.3, + "learning_rate": 1.7649453698668156e-05, + "loss": 1.4659, + "step": 2865 + }, + { + "epoch": 0.3, + "learning_rate": 1.7647095636920305e-05, + "loss": 1.7042, + "step": 2866 + }, + { + "epoch": 0.3, + "learning_rate": 1.7644736550658124e-05, + "loss": 1.7957, + "step": 2867 + }, + { + "epoch": 0.3, + "learning_rate": 1.764237644019767e-05, + "loss": 1.5139, + "step": 2868 + }, + { + "epoch": 0.3, + "learning_rate": 1.764001530585514e-05, + "loss": 1.4117, + "step": 2869 + }, + { + "epoch": 0.3, + "learning_rate": 1.7637653147946858e-05, + "loss": 1.4837, + "step": 2870 + }, + { + "epoch": 0.3, + "learning_rate": 1.7635289966789298e-05, + "loss": 1.4379, + "step": 2871 + }, + { + "epoch": 0.3, + "learning_rate": 1.7632925762699068e-05, + "loss": 1.4491, + "step": 2872 + }, + { + "epoch": 0.3, + "learning_rate": 1.7630560535992905e-05, + "loss": 1.4006, + "step": 2873 + }, + { + "epoch": 0.3, + "learning_rate": 1.7628194286987694e-05, + "loss": 1.5484, + "step": 2874 + }, + { + "epoch": 0.3, + "learning_rate": 1.7625827016000446e-05, + "loss": 1.4926, + "step": 2875 + }, + { + "epoch": 0.3, + "learning_rate": 1.762345872334832e-05, + "loss": 1.3909, + "step": 2876 + }, + { + "epoch": 0.3, + "learning_rate": 1.76210894093486e-05, + "loss": 1.405, + "step": 2877 + }, + { + "epoch": 0.3, + "learning_rate": 1.7618719074318718e-05, + "loss": 1.4736, + "step": 2878 + }, + { + "epoch": 0.3, + "learning_rate": 1.7616347718576238e-05, + "loss": 1.4445, + "step": 2879 + }, + { + "epoch": 0.3, + "learning_rate": 1.761397534243886e-05, + "loss": 1.4878, + "step": 2880 + }, + { + "epoch": 0.3, + "learning_rate": 1.7611601946224417e-05, + "loss": 1.4414, + "step": 2881 + }, + { + "epoch": 0.3, + "learning_rate": 1.760922753025089e-05, + "loss": 1.5657, + "step": 2882 + }, + { + "epoch": 0.3, + "learning_rate": 1.7606852094836385e-05, + "loss": 1.5008, + "step": 2883 + }, + { + "epoch": 0.3, + "learning_rate": 1.7604475640299153e-05, + "loss": 1.4922, + "step": 2884 + }, + { + "epoch": 0.3, + "learning_rate": 1.7602098166957577e-05, + "loss": 1.7451, + "step": 2885 + }, + { + "epoch": 0.3, + "learning_rate": 1.759971967513017e-05, + "loss": 1.7077, + "step": 2886 + }, + { + "epoch": 0.3, + "learning_rate": 1.75973401651356e-05, + "loss": 1.3986, + "step": 2887 + }, + { + "epoch": 0.3, + "learning_rate": 1.7594959637292656e-05, + "loss": 1.3966, + "step": 2888 + }, + { + "epoch": 0.3, + "learning_rate": 1.7592578091920264e-05, + "loss": 1.4086, + "step": 2889 + }, + { + "epoch": 0.3, + "learning_rate": 1.7590195529337495e-05, + "loss": 1.4481, + "step": 2890 + }, + { + "epoch": 0.3, + "learning_rate": 1.7587811949863548e-05, + "loss": 1.3974, + "step": 2891 + }, + { + "epoch": 0.3, + "learning_rate": 1.7585427353817758e-05, + "loss": 1.5013, + "step": 2892 + }, + { + "epoch": 0.3, + "learning_rate": 1.7583041741519608e-05, + "loss": 1.5454, + "step": 2893 + }, + { + "epoch": 0.3, + "learning_rate": 1.7580655113288708e-05, + "loss": 1.5033, + "step": 2894 + }, + { + "epoch": 0.3, + "learning_rate": 1.7578267469444793e-05, + "loss": 1.4332, + "step": 2895 + }, + { + "epoch": 0.3, + "learning_rate": 1.757587881030776e-05, + "loss": 1.4667, + "step": 2896 + }, + { + "epoch": 0.3, + "learning_rate": 1.7573489136197623e-05, + "loss": 1.4314, + "step": 2897 + }, + { + "epoch": 0.3, + "learning_rate": 1.7571098447434532e-05, + "loss": 1.4514, + "step": 2898 + }, + { + "epoch": 0.3, + "learning_rate": 1.7568706744338784e-05, + "loss": 1.4872, + "step": 2899 + }, + { + "epoch": 0.3, + "learning_rate": 1.7566314027230808e-05, + "loss": 1.4841, + "step": 2900 + }, + { + "epoch": 0.3, + "learning_rate": 1.7563920296431158e-05, + "loss": 1.3964, + "step": 2901 + }, + { + "epoch": 0.3, + "learning_rate": 1.7561525552260538e-05, + "loss": 1.4932, + "step": 2902 + }, + { + "epoch": 0.3, + "learning_rate": 1.755912979503978e-05, + "loss": 1.4153, + "step": 2903 + }, + { + "epoch": 0.3, + "learning_rate": 1.755673302508986e-05, + "loss": 1.4939, + "step": 2904 + }, + { + "epoch": 0.3, + "learning_rate": 1.755433524273187e-05, + "loss": 1.4437, + "step": 2905 + }, + { + "epoch": 0.3, + "learning_rate": 1.7551936448287067e-05, + "loss": 1.486, + "step": 2906 + }, + { + "epoch": 0.3, + "learning_rate": 1.754953664207682e-05, + "loss": 1.4362, + "step": 2907 + }, + { + "epoch": 0.3, + "learning_rate": 1.7547135824422635e-05, + "loss": 1.4954, + "step": 2908 + }, + { + "epoch": 0.31, + "learning_rate": 1.7544733995646174e-05, + "loss": 1.4552, + "step": 2909 + }, + { + "epoch": 0.31, + "learning_rate": 1.7542331156069213e-05, + "loss": 1.4654, + "step": 2910 + }, + { + "epoch": 0.31, + "learning_rate": 1.753992730601367e-05, + "loss": 1.4531, + "step": 2911 + }, + { + "epoch": 0.31, + "learning_rate": 1.75375224458016e-05, + "loss": 1.4949, + "step": 2912 + }, + { + "epoch": 0.31, + "learning_rate": 1.753511657575519e-05, + "loss": 1.3998, + "step": 2913 + }, + { + "epoch": 0.31, + "learning_rate": 1.753270969619677e-05, + "loss": 1.3904, + "step": 2914 + }, + { + "epoch": 0.31, + "learning_rate": 1.7530301807448794e-05, + "loss": 1.481, + "step": 2915 + }, + { + "epoch": 0.31, + "learning_rate": 1.7527892909833864e-05, + "loss": 1.4301, + "step": 2916 + }, + { + "epoch": 0.31, + "learning_rate": 1.7525483003674707e-05, + "loss": 1.4377, + "step": 2917 + }, + { + "epoch": 0.31, + "learning_rate": 1.7523072089294188e-05, + "loss": 1.5077, + "step": 2918 + }, + { + "epoch": 0.31, + "learning_rate": 1.752066016701531e-05, + "loss": 1.3802, + "step": 2919 + }, + { + "epoch": 0.31, + "learning_rate": 1.7518247237161205e-05, + "loss": 1.3991, + "step": 2920 + }, + { + "epoch": 0.31, + "learning_rate": 1.7515833300055146e-05, + "loss": 1.4283, + "step": 2921 + }, + { + "epoch": 0.31, + "learning_rate": 1.7513418356020535e-05, + "loss": 1.3688, + "step": 2922 + }, + { + "epoch": 0.31, + "learning_rate": 1.751100240538092e-05, + "loss": 1.4336, + "step": 2923 + }, + { + "epoch": 0.31, + "learning_rate": 1.7508585448459967e-05, + "loss": 1.4302, + "step": 2924 + }, + { + "epoch": 0.31, + "learning_rate": 1.7506167485581493e-05, + "loss": 1.4293, + "step": 2925 + }, + { + "epoch": 0.31, + "learning_rate": 1.750374851706944e-05, + "loss": 1.4262, + "step": 2926 + }, + { + "epoch": 0.31, + "learning_rate": 1.7501328543247892e-05, + "loss": 1.4128, + "step": 2927 + }, + { + "epoch": 0.31, + "learning_rate": 1.7498907564441054e-05, + "loss": 1.4258, + "step": 2928 + }, + { + "epoch": 0.31, + "learning_rate": 1.749648558097328e-05, + "loss": 1.4904, + "step": 2929 + }, + { + "epoch": 0.31, + "learning_rate": 1.749406259316906e-05, + "loss": 1.4628, + "step": 2930 + }, + { + "epoch": 0.31, + "learning_rate": 1.7491638601353004e-05, + "loss": 1.4908, + "step": 2931 + }, + { + "epoch": 0.31, + "learning_rate": 1.7489213605849867e-05, + "loss": 1.4563, + "step": 2932 + }, + { + "epoch": 0.31, + "learning_rate": 1.7486787606984533e-05, + "loss": 1.5006, + "step": 2933 + }, + { + "epoch": 0.31, + "learning_rate": 1.748436060508203e-05, + "loss": 1.424, + "step": 2934 + }, + { + "epoch": 0.31, + "learning_rate": 1.7481932600467508e-05, + "loss": 1.4136, + "step": 2935 + }, + { + "epoch": 0.31, + "learning_rate": 1.747950359346626e-05, + "loss": 1.3835, + "step": 2936 + }, + { + "epoch": 0.31, + "learning_rate": 1.747707358440371e-05, + "loss": 1.5284, + "step": 2937 + }, + { + "epoch": 0.31, + "learning_rate": 1.7474642573605418e-05, + "loss": 1.4592, + "step": 2938 + }, + { + "epoch": 0.31, + "learning_rate": 1.7472210561397075e-05, + "loss": 1.5483, + "step": 2939 + }, + { + "epoch": 0.31, + "learning_rate": 1.746977754810451e-05, + "loss": 1.521, + "step": 2940 + }, + { + "epoch": 0.31, + "learning_rate": 1.7467343534053683e-05, + "loss": 1.4276, + "step": 2941 + }, + { + "epoch": 0.31, + "learning_rate": 1.746490851957069e-05, + "loss": 1.4302, + "step": 2942 + }, + { + "epoch": 0.31, + "learning_rate": 1.746247250498176e-05, + "loss": 1.4439, + "step": 2943 + }, + { + "epoch": 0.31, + "learning_rate": 1.7460035490613255e-05, + "loss": 1.4991, + "step": 2944 + }, + { + "epoch": 0.31, + "learning_rate": 1.7457597476791674e-05, + "loss": 1.4188, + "step": 2945 + }, + { + "epoch": 0.31, + "learning_rate": 1.7455158463843648e-05, + "loss": 1.4685, + "step": 2946 + }, + { + "epoch": 0.31, + "learning_rate": 1.745271845209594e-05, + "loss": 1.3811, + "step": 2947 + }, + { + "epoch": 0.31, + "learning_rate": 1.7450277441875454e-05, + "loss": 1.4869, + "step": 2948 + }, + { + "epoch": 0.31, + "learning_rate": 1.7447835433509218e-05, + "loss": 1.5001, + "step": 2949 + }, + { + "epoch": 0.31, + "learning_rate": 1.74453924273244e-05, + "loss": 1.4757, + "step": 2950 + }, + { + "epoch": 0.31, + "learning_rate": 1.74429484236483e-05, + "loss": 1.5072, + "step": 2951 + }, + { + "epoch": 0.31, + "learning_rate": 1.744050342280835e-05, + "loss": 1.4242, + "step": 2952 + }, + { + "epoch": 0.31, + "learning_rate": 1.743805742513212e-05, + "loss": 1.4462, + "step": 2953 + }, + { + "epoch": 0.31, + "learning_rate": 1.743561043094731e-05, + "loss": 1.6815, + "step": 2954 + }, + { + "epoch": 0.31, + "learning_rate": 1.7433162440581755e-05, + "loss": 1.427, + "step": 2955 + }, + { + "epoch": 0.31, + "learning_rate": 1.7430713454363423e-05, + "loss": 1.2933, + "step": 2956 + }, + { + "epoch": 0.31, + "learning_rate": 1.742826347262041e-05, + "loss": 1.4247, + "step": 2957 + }, + { + "epoch": 0.31, + "learning_rate": 1.7425812495680955e-05, + "loss": 1.399, + "step": 2958 + }, + { + "epoch": 0.31, + "learning_rate": 1.742336052387343e-05, + "loss": 1.4818, + "step": 2959 + }, + { + "epoch": 0.31, + "learning_rate": 1.742090755752633e-05, + "loss": 1.3839, + "step": 2960 + }, + { + "epoch": 0.31, + "learning_rate": 1.741845359696829e-05, + "loss": 1.4669, + "step": 2961 + }, + { + "epoch": 0.31, + "learning_rate": 1.741599864252808e-05, + "loss": 1.468, + "step": 2962 + }, + { + "epoch": 0.31, + "learning_rate": 1.74135426945346e-05, + "loss": 1.4135, + "step": 2963 + }, + { + "epoch": 0.31, + "learning_rate": 1.7411085753316882e-05, + "loss": 1.5899, + "step": 2964 + }, + { + "epoch": 0.31, + "learning_rate": 1.74086278192041e-05, + "loss": 1.6115, + "step": 2965 + }, + { + "epoch": 0.31, + "learning_rate": 1.740616889252554e-05, + "loss": 1.3988, + "step": 2966 + }, + { + "epoch": 0.31, + "learning_rate": 1.740370897361065e-05, + "loss": 1.5001, + "step": 2967 + }, + { + "epoch": 0.31, + "learning_rate": 1.740124806278899e-05, + "loss": 1.459, + "step": 2968 + }, + { + "epoch": 0.31, + "learning_rate": 1.7398786160390258e-05, + "loss": 1.4489, + "step": 2969 + }, + { + "epoch": 0.31, + "learning_rate": 1.7396323266744283e-05, + "loss": 1.4397, + "step": 2970 + }, + { + "epoch": 0.31, + "learning_rate": 1.7393859382181033e-05, + "loss": 1.4687, + "step": 2971 + }, + { + "epoch": 0.31, + "learning_rate": 1.7391394507030606e-05, + "loss": 1.4495, + "step": 2972 + }, + { + "epoch": 0.31, + "learning_rate": 1.738892864162323e-05, + "loss": 1.4745, + "step": 2973 + }, + { + "epoch": 0.31, + "learning_rate": 1.7386461786289274e-05, + "loss": 1.3943, + "step": 2974 + }, + { + "epoch": 0.31, + "learning_rate": 1.738399394135922e-05, + "loss": 1.4595, + "step": 2975 + }, + { + "epoch": 0.31, + "learning_rate": 1.738152510716371e-05, + "loss": 1.4023, + "step": 2976 + }, + { + "epoch": 0.31, + "learning_rate": 1.7379055284033493e-05, + "loss": 1.3938, + "step": 2977 + }, + { + "epoch": 0.31, + "learning_rate": 1.7376584472299468e-05, + "loss": 1.4576, + "step": 2978 + }, + { + "epoch": 0.31, + "learning_rate": 1.737411267229266e-05, + "loss": 1.424, + "step": 2979 + }, + { + "epoch": 0.31, + "learning_rate": 1.7371639884344225e-05, + "loss": 1.4224, + "step": 2980 + }, + { + "epoch": 0.31, + "learning_rate": 1.736916610878545e-05, + "loss": 1.4228, + "step": 2981 + }, + { + "epoch": 0.31, + "learning_rate": 1.7366691345947768e-05, + "loss": 1.5021, + "step": 2982 + }, + { + "epoch": 0.31, + "learning_rate": 1.736421559616272e-05, + "loss": 1.3589, + "step": 2983 + }, + { + "epoch": 0.31, + "learning_rate": 1.7361738859762007e-05, + "loss": 1.4748, + "step": 2984 + }, + { + "epoch": 0.31, + "learning_rate": 1.735926113707743e-05, + "loss": 1.3974, + "step": 2985 + }, + { + "epoch": 0.31, + "eval_loss": 1.4849082231521606, + "eval_runtime": 77.3271, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2985 + }, + { + "epoch": 0.31, + "learning_rate": 1.735678242844096e-05, + "loss": 1.392, + "step": 2986 + }, + { + "epoch": 0.31, + "learning_rate": 1.735430273418467e-05, + "loss": 1.4277, + "step": 2987 + }, + { + "epoch": 0.31, + "learning_rate": 1.735182205464077e-05, + "loss": 1.4216, + "step": 2988 + }, + { + "epoch": 0.31, + "learning_rate": 1.7349340390141617e-05, + "loss": 1.4546, + "step": 2989 + }, + { + "epoch": 0.31, + "learning_rate": 1.734685774101969e-05, + "loss": 1.4264, + "step": 2990 + }, + { + "epoch": 0.31, + "learning_rate": 1.7344374107607593e-05, + "loss": 1.4307, + "step": 2991 + }, + { + "epoch": 0.31, + "learning_rate": 1.7341889490238076e-05, + "loss": 1.4266, + "step": 2992 + }, + { + "epoch": 0.31, + "learning_rate": 1.7339403889244008e-05, + "loss": 1.4486, + "step": 2993 + }, + { + "epoch": 0.31, + "learning_rate": 1.7336917304958403e-05, + "loss": 1.4345, + "step": 2994 + }, + { + "epoch": 0.31, + "learning_rate": 1.7334429737714395e-05, + "loss": 1.476, + "step": 2995 + }, + { + "epoch": 0.31, + "learning_rate": 1.7331941187845248e-05, + "loss": 1.5148, + "step": 2996 + }, + { + "epoch": 0.31, + "learning_rate": 1.7329451655684372e-05, + "loss": 1.4026, + "step": 2997 + }, + { + "epoch": 0.31, + "learning_rate": 1.7326961141565303e-05, + "loss": 1.3935, + "step": 2998 + }, + { + "epoch": 0.31, + "learning_rate": 1.73244696458217e-05, + "loss": 1.4483, + "step": 2999 + }, + { + "epoch": 0.31, + "learning_rate": 1.7321977168787356e-05, + "loss": 1.5197, + "step": 3000 + }, + { + "epoch": 0.31, + "learning_rate": 1.7319483710796208e-05, + "loss": 1.4648, + "step": 3001 + }, + { + "epoch": 0.31, + "learning_rate": 1.7316989272182308e-05, + "loss": 1.4171, + "step": 3002 + }, + { + "epoch": 0.31, + "learning_rate": 1.731449385327985e-05, + "loss": 1.4541, + "step": 3003 + }, + { + "epoch": 0.32, + "learning_rate": 1.731199745442316e-05, + "loss": 1.4605, + "step": 3004 + }, + { + "epoch": 0.32, + "learning_rate": 1.7309500075946683e-05, + "loss": 1.5122, + "step": 3005 + }, + { + "epoch": 0.32, + "learning_rate": 1.7307001718185007e-05, + "loss": 1.5243, + "step": 3006 + }, + { + "epoch": 0.32, + "learning_rate": 1.7304502381472844e-05, + "loss": 1.4997, + "step": 3007 + }, + { + "epoch": 0.32, + "learning_rate": 1.730200206614505e-05, + "loss": 1.4891, + "step": 3008 + }, + { + "epoch": 0.32, + "learning_rate": 1.72995007725366e-05, + "loss": 1.4376, + "step": 3009 + }, + { + "epoch": 0.32, + "learning_rate": 1.7296998500982595e-05, + "loss": 1.4403, + "step": 3010 + }, + { + "epoch": 0.32, + "learning_rate": 1.7294495251818285e-05, + "loss": 1.5153, + "step": 3011 + }, + { + "epoch": 0.32, + "learning_rate": 1.729199102537904e-05, + "loss": 1.4996, + "step": 3012 + }, + { + "epoch": 0.32, + "learning_rate": 1.7289485822000356e-05, + "loss": 1.5302, + "step": 3013 + }, + { + "epoch": 0.32, + "learning_rate": 1.7286979642017867e-05, + "loss": 1.5641, + "step": 3014 + }, + { + "epoch": 0.32, + "learning_rate": 1.728447248576734e-05, + "loss": 1.438, + "step": 3015 + }, + { + "epoch": 0.32, + "learning_rate": 1.7281964353584674e-05, + "loss": 1.4796, + "step": 3016 + }, + { + "epoch": 0.32, + "learning_rate": 1.727945524580588e-05, + "loss": 1.4413, + "step": 3017 + }, + { + "epoch": 0.32, + "learning_rate": 1.727694516276713e-05, + "loss": 1.3966, + "step": 3018 + }, + { + "epoch": 0.32, + "learning_rate": 1.72744341048047e-05, + "loss": 1.5267, + "step": 3019 + }, + { + "epoch": 0.32, + "learning_rate": 1.727192207225501e-05, + "loss": 1.4284, + "step": 3020 + }, + { + "epoch": 0.32, + "learning_rate": 1.726940906545461e-05, + "loss": 1.5137, + "step": 3021 + }, + { + "epoch": 0.32, + "learning_rate": 1.7266895084740173e-05, + "loss": 1.3966, + "step": 3022 + }, + { + "epoch": 0.32, + "learning_rate": 1.7264380130448514e-05, + "loss": 1.4156, + "step": 3023 + }, + { + "epoch": 0.32, + "learning_rate": 1.726186420291657e-05, + "loss": 1.4644, + "step": 3024 + }, + { + "epoch": 0.32, + "learning_rate": 1.725934730248141e-05, + "loss": 1.4768, + "step": 3025 + }, + { + "epoch": 0.32, + "learning_rate": 1.7256829429480233e-05, + "loss": 1.4428, + "step": 3026 + }, + { + "epoch": 0.32, + "learning_rate": 1.7254310584250373e-05, + "loss": 1.4495, + "step": 3027 + }, + { + "epoch": 0.32, + "learning_rate": 1.725179076712929e-05, + "loss": 1.3867, + "step": 3028 + }, + { + "epoch": 0.32, + "learning_rate": 1.7249269978454567e-05, + "loss": 1.5011, + "step": 3029 + }, + { + "epoch": 0.32, + "learning_rate": 1.7246748218563937e-05, + "loss": 1.3916, + "step": 3030 + }, + { + "epoch": 0.32, + "learning_rate": 1.7244225487795238e-05, + "loss": 1.4984, + "step": 3031 + }, + { + "epoch": 0.32, + "learning_rate": 1.7241701786486464e-05, + "loss": 1.5776, + "step": 3032 + }, + { + "epoch": 0.32, + "learning_rate": 1.7239177114975717e-05, + "loss": 1.5018, + "step": 3033 + }, + { + "epoch": 0.32, + "learning_rate": 1.7236651473601244e-05, + "loss": 1.5042, + "step": 3034 + }, + { + "epoch": 0.32, + "learning_rate": 1.723412486270141e-05, + "loss": 1.4636, + "step": 3035 + }, + { + "epoch": 0.32, + "learning_rate": 1.723159728261472e-05, + "loss": 1.5612, + "step": 3036 + }, + { + "epoch": 0.32, + "learning_rate": 1.7229068733679803e-05, + "loss": 1.4399, + "step": 3037 + }, + { + "epoch": 0.32, + "learning_rate": 1.7226539216235424e-05, + "loss": 1.5635, + "step": 3038 + }, + { + "epoch": 0.32, + "learning_rate": 1.7224008730620468e-05, + "loss": 1.4329, + "step": 3039 + }, + { + "epoch": 0.32, + "learning_rate": 1.7221477277173956e-05, + "loss": 1.4886, + "step": 3040 + }, + { + "epoch": 0.32, + "learning_rate": 1.721894485623504e-05, + "loss": 1.4741, + "step": 3041 + }, + { + "epoch": 0.32, + "learning_rate": 1.7216411468143e-05, + "loss": 1.4678, + "step": 3042 + }, + { + "epoch": 0.32, + "learning_rate": 1.721387711323724e-05, + "loss": 1.4758, + "step": 3043 + }, + { + "epoch": 0.32, + "learning_rate": 1.72113417918573e-05, + "loss": 1.441, + "step": 3044 + }, + { + "epoch": 0.32, + "learning_rate": 1.7208805504342855e-05, + "loss": 1.4328, + "step": 3045 + }, + { + "epoch": 0.32, + "learning_rate": 1.720626825103369e-05, + "loss": 1.4254, + "step": 3046 + }, + { + "epoch": 0.32, + "learning_rate": 1.7203730032269744e-05, + "loss": 1.4462, + "step": 3047 + }, + { + "epoch": 0.32, + "learning_rate": 1.7201190848391066e-05, + "loss": 1.4826, + "step": 3048 + }, + { + "epoch": 0.32, + "learning_rate": 1.719865069973784e-05, + "loss": 1.4215, + "step": 3049 + }, + { + "epoch": 0.32, + "learning_rate": 1.7196109586650385e-05, + "loss": 1.4291, + "step": 3050 + }, + { + "epoch": 0.32, + "learning_rate": 1.7193567509469146e-05, + "loss": 1.5005, + "step": 3051 + }, + { + "epoch": 0.32, + "learning_rate": 1.719102446853469e-05, + "loss": 1.4216, + "step": 3052 + }, + { + "epoch": 0.32, + "learning_rate": 1.7188480464187725e-05, + "loss": 1.4349, + "step": 3053 + }, + { + "epoch": 0.32, + "learning_rate": 1.718593549676908e-05, + "loss": 1.4784, + "step": 3054 + }, + { + "epoch": 0.32, + "learning_rate": 1.7183389566619714e-05, + "loss": 1.4325, + "step": 3055 + }, + { + "epoch": 0.32, + "learning_rate": 1.7180842674080717e-05, + "loss": 1.5387, + "step": 3056 + }, + { + "epoch": 0.32, + "learning_rate": 1.717829481949331e-05, + "loss": 1.655, + "step": 3057 + }, + { + "epoch": 0.32, + "learning_rate": 1.717574600319883e-05, + "loss": 1.4623, + "step": 3058 + }, + { + "epoch": 0.32, + "learning_rate": 1.7173196225538768e-05, + "loss": 1.4646, + "step": 3059 + }, + { + "epoch": 0.32, + "learning_rate": 1.717064548685472e-05, + "loss": 1.4641, + "step": 3060 + }, + { + "epoch": 0.32, + "learning_rate": 1.7168093787488418e-05, + "loss": 1.4033, + "step": 3061 + }, + { + "epoch": 0.32, + "learning_rate": 1.7165541127781726e-05, + "loss": 1.4085, + "step": 3062 + }, + { + "epoch": 0.32, + "learning_rate": 1.716298750807664e-05, + "loss": 1.387, + "step": 3063 + }, + { + "epoch": 0.32, + "learning_rate": 1.7160432928715272e-05, + "loss": 1.4197, + "step": 3064 + }, + { + "epoch": 0.32, + "learning_rate": 1.7157877390039872e-05, + "loss": 1.4883, + "step": 3065 + }, + { + "epoch": 0.32, + "learning_rate": 1.7155320892392818e-05, + "loss": 1.4865, + "step": 3066 + }, + { + "epoch": 0.32, + "learning_rate": 1.715276343611662e-05, + "loss": 1.4532, + "step": 3067 + }, + { + "epoch": 0.32, + "learning_rate": 1.71502050215539e-05, + "loss": 1.3991, + "step": 3068 + }, + { + "epoch": 0.32, + "learning_rate": 1.7147645649047424e-05, + "loss": 1.4318, + "step": 3069 + }, + { + "epoch": 0.32, + "learning_rate": 1.714508531894009e-05, + "loss": 1.3616, + "step": 3070 + }, + { + "epoch": 0.32, + "learning_rate": 1.7142524031574904e-05, + "loss": 1.4481, + "step": 3071 + }, + { + "epoch": 0.32, + "learning_rate": 1.7139961787295022e-05, + "loss": 1.3897, + "step": 3072 + }, + { + "epoch": 0.32, + "learning_rate": 1.7137398586443716e-05, + "loss": 1.3128, + "step": 3073 + }, + { + "epoch": 0.32, + "learning_rate": 1.713483442936439e-05, + "loss": 1.4481, + "step": 3074 + }, + { + "epoch": 0.32, + "learning_rate": 1.713226931640057e-05, + "loss": 1.5374, + "step": 3075 + }, + { + "epoch": 0.32, + "learning_rate": 1.7129703247895923e-05, + "loss": 1.4247, + "step": 3076 + }, + { + "epoch": 0.32, + "learning_rate": 1.712713622419423e-05, + "loss": 1.4098, + "step": 3077 + }, + { + "epoch": 0.32, + "learning_rate": 1.7124568245639414e-05, + "loss": 1.4558, + "step": 3078 + }, + { + "epoch": 0.32, + "learning_rate": 1.7121999312575507e-05, + "loss": 1.4484, + "step": 3079 + }, + { + "epoch": 0.32, + "learning_rate": 1.711942942534669e-05, + "loss": 1.4236, + "step": 3080 + }, + { + "epoch": 0.32, + "learning_rate": 1.7116858584297253e-05, + "loss": 1.613, + "step": 3081 + }, + { + "epoch": 0.32, + "learning_rate": 1.711428678977163e-05, + "loss": 1.4503, + "step": 3082 + }, + { + "epoch": 0.32, + "learning_rate": 1.7111714042114376e-05, + "loss": 1.4072, + "step": 3083 + }, + { + "epoch": 0.32, + "learning_rate": 1.7109140341670168e-05, + "loss": 1.5999, + "step": 3084 + }, + { + "epoch": 0.32, + "learning_rate": 1.7106565688783815e-05, + "loss": 1.4129, + "step": 3085 + }, + { + "epoch": 0.32, + "learning_rate": 1.710399008380026e-05, + "loss": 1.3973, + "step": 3086 + }, + { + "epoch": 0.32, + "learning_rate": 1.710141352706456e-05, + "loss": 1.4292, + "step": 3087 + }, + { + "epoch": 0.32, + "learning_rate": 1.709883601892192e-05, + "loss": 1.4372, + "step": 3088 + }, + { + "epoch": 0.32, + "learning_rate": 1.7096257559717647e-05, + "loss": 1.4924, + "step": 3089 + }, + { + "epoch": 0.32, + "learning_rate": 1.7093678149797196e-05, + "loss": 1.4222, + "step": 3090 + }, + { + "epoch": 0.32, + "learning_rate": 1.7091097789506137e-05, + "loss": 1.4797, + "step": 3091 + }, + { + "epoch": 0.32, + "learning_rate": 1.7088516479190175e-05, + "loss": 1.4738, + "step": 3092 + }, + { + "epoch": 0.32, + "learning_rate": 1.708593421919514e-05, + "loss": 1.5371, + "step": 3093 + }, + { + "epoch": 0.32, + "learning_rate": 1.7083351009866988e-05, + "loss": 1.3802, + "step": 3094 + }, + { + "epoch": 0.32, + "learning_rate": 1.7080766851551795e-05, + "loss": 1.4292, + "step": 3095 + }, + { + "epoch": 0.32, + "learning_rate": 1.707818174459578e-05, + "loss": 1.4478, + "step": 3096 + }, + { + "epoch": 0.32, + "learning_rate": 1.7075595689345285e-05, + "loss": 1.4619, + "step": 3097 + }, + { + "epoch": 0.32, + "learning_rate": 1.7073008686146763e-05, + "loss": 1.4603, + "step": 3098 + }, + { + "epoch": 0.32, + "learning_rate": 1.7070420735346815e-05, + "loss": 1.4548, + "step": 3099 + }, + { + "epoch": 0.33, + "learning_rate": 1.7067831837292157e-05, + "loss": 1.3638, + "step": 3100 + }, + { + "epoch": 0.33, + "learning_rate": 1.7065241992329634e-05, + "loss": 1.4284, + "step": 3101 + }, + { + "epoch": 0.33, + "learning_rate": 1.7062651200806217e-05, + "loss": 1.386, + "step": 3102 + }, + { + "epoch": 0.33, + "learning_rate": 1.7060059463069013e-05, + "loss": 1.5483, + "step": 3103 + }, + { + "epoch": 0.33, + "learning_rate": 1.705746677946524e-05, + "loss": 1.4963, + "step": 3104 + }, + { + "epoch": 0.33, + "learning_rate": 1.7054873150342257e-05, + "loss": 1.4539, + "step": 3105 + }, + { + "epoch": 0.33, + "learning_rate": 1.705227857604754e-05, + "loss": 1.4361, + "step": 3106 + }, + { + "epoch": 0.33, + "learning_rate": 1.7049683056928695e-05, + "loss": 1.3735, + "step": 3107 + }, + { + "epoch": 0.33, + "learning_rate": 1.7047086593333454e-05, + "loss": 1.4324, + "step": 3108 + }, + { + "epoch": 0.33, + "learning_rate": 1.7044489185609685e-05, + "loss": 1.5037, + "step": 3109 + }, + { + "epoch": 0.33, + "learning_rate": 1.704189083410536e-05, + "loss": 1.3913, + "step": 3110 + }, + { + "epoch": 0.33, + "learning_rate": 1.7039291539168604e-05, + "loss": 1.3233, + "step": 3111 + }, + { + "epoch": 0.33, + "learning_rate": 1.703669130114765e-05, + "loss": 1.4897, + "step": 3112 + }, + { + "epoch": 0.33, + "learning_rate": 1.7034090120390862e-05, + "loss": 1.4843, + "step": 3113 + }, + { + "epoch": 0.33, + "learning_rate": 1.7031487997246735e-05, + "loss": 1.3674, + "step": 3114 + }, + { + "epoch": 0.33, + "learning_rate": 1.7028884932063883e-05, + "loss": 1.4475, + "step": 3115 + }, + { + "epoch": 0.33, + "learning_rate": 1.702628092519105e-05, + "loss": 1.4134, + "step": 3116 + }, + { + "epoch": 0.33, + "learning_rate": 1.7023675976977108e-05, + "loss": 1.4484, + "step": 3117 + }, + { + "epoch": 0.33, + "learning_rate": 1.702107008777106e-05, + "loss": 1.407, + "step": 3118 + }, + { + "epoch": 0.33, + "learning_rate": 1.7018463257922005e-05, + "loss": 1.5443, + "step": 3119 + }, + { + "epoch": 0.33, + "learning_rate": 1.701585548777922e-05, + "loss": 1.4548, + "step": 3120 + }, + { + "epoch": 0.33, + "learning_rate": 1.7013246777692063e-05, + "loss": 1.4252, + "step": 3121 + }, + { + "epoch": 0.33, + "learning_rate": 1.7010637128010037e-05, + "loss": 1.3748, + "step": 3122 + }, + { + "epoch": 0.33, + "learning_rate": 1.7008026539082767e-05, + "loss": 1.3804, + "step": 3123 + }, + { + "epoch": 0.33, + "learning_rate": 1.7005415011260008e-05, + "loss": 1.4203, + "step": 3124 + }, + { + "epoch": 0.33, + "learning_rate": 1.7002802544891634e-05, + "loss": 1.4195, + "step": 3125 + }, + { + "epoch": 0.33, + "learning_rate": 1.700018914032765e-05, + "loss": 1.4188, + "step": 3126 + }, + { + "epoch": 0.33, + "learning_rate": 1.699757479791819e-05, + "loss": 1.3884, + "step": 3127 + }, + { + "epoch": 0.33, + "learning_rate": 1.6994959518013502e-05, + "loss": 1.4111, + "step": 3128 + }, + { + "epoch": 0.33, + "learning_rate": 1.6992343300963963e-05, + "loss": 1.5452, + "step": 3129 + }, + { + "epoch": 0.33, + "learning_rate": 1.6989726147120087e-05, + "loss": 1.4097, + "step": 3130 + }, + { + "epoch": 0.33, + "learning_rate": 1.6987108056832506e-05, + "loss": 1.481, + "step": 3131 + }, + { + "epoch": 0.33, + "learning_rate": 1.6984489030451973e-05, + "loss": 1.4505, + "step": 3132 + }, + { + "epoch": 0.33, + "learning_rate": 1.6981869068329368e-05, + "loss": 1.4281, + "step": 3133 + }, + { + "epoch": 0.33, + "learning_rate": 1.69792481708157e-05, + "loss": 1.4555, + "step": 3134 + }, + { + "epoch": 0.33, + "learning_rate": 1.6976626338262103e-05, + "loss": 1.4525, + "step": 3135 + }, + { + "epoch": 0.33, + "learning_rate": 1.6974003571019837e-05, + "loss": 1.3765, + "step": 3136 + }, + { + "epoch": 0.33, + "learning_rate": 1.6971379869440286e-05, + "loss": 1.3998, + "step": 3137 + }, + { + "epoch": 0.33, + "learning_rate": 1.696875523387495e-05, + "loss": 1.5103, + "step": 3138 + }, + { + "epoch": 0.33, + "learning_rate": 1.6966129664675474e-05, + "loss": 1.427, + "step": 3139 + }, + { + "epoch": 0.33, + "learning_rate": 1.6963503162193612e-05, + "loss": 1.4362, + "step": 3140 + }, + { + "epoch": 0.33, + "learning_rate": 1.6960875726781246e-05, + "loss": 1.4073, + "step": 3141 + }, + { + "epoch": 0.33, + "learning_rate": 1.6958247358790388e-05, + "loss": 1.4014, + "step": 3142 + }, + { + "epoch": 0.33, + "learning_rate": 1.6955618058573165e-05, + "loss": 1.4244, + "step": 3143 + }, + { + "epoch": 0.33, + "learning_rate": 1.6952987826481847e-05, + "loss": 1.47, + "step": 3144 + }, + { + "epoch": 0.33, + "learning_rate": 1.6950356662868814e-05, + "loss": 1.5112, + "step": 3145 + }, + { + "epoch": 0.33, + "learning_rate": 1.6947724568086562e-05, + "loss": 1.3398, + "step": 3146 + }, + { + "epoch": 0.33, + "learning_rate": 1.694509154248774e-05, + "loss": 1.4584, + "step": 3147 + }, + { + "epoch": 0.33, + "learning_rate": 1.69424575864251e-05, + "loss": 1.4383, + "step": 3148 + }, + { + "epoch": 0.33, + "learning_rate": 1.6939822700251523e-05, + "loss": 1.3869, + "step": 3149 + }, + { + "epoch": 0.33, + "learning_rate": 1.6937186884320015e-05, + "loss": 1.4453, + "step": 3150 + }, + { + "epoch": 0.33, + "learning_rate": 1.6934550138983713e-05, + "loss": 1.3355, + "step": 3151 + }, + { + "epoch": 0.33, + "learning_rate": 1.6931912464595866e-05, + "loss": 1.5573, + "step": 3152 + }, + { + "epoch": 0.33, + "learning_rate": 1.6929273861509865e-05, + "loss": 1.439, + "step": 3153 + }, + { + "epoch": 0.33, + "learning_rate": 1.6926634330079203e-05, + "loss": 1.6079, + "step": 3154 + }, + { + "epoch": 0.33, + "learning_rate": 1.692399387065752e-05, + "loss": 1.6973, + "step": 3155 + }, + { + "epoch": 0.33, + "learning_rate": 1.692135248359856e-05, + "loss": 1.3769, + "step": 3156 + }, + { + "epoch": 0.33, + "learning_rate": 1.6918710169256206e-05, + "loss": 1.4454, + "step": 3157 + }, + { + "epoch": 0.33, + "learning_rate": 1.691606692798446e-05, + "loss": 1.4495, + "step": 3158 + }, + { + "epoch": 0.33, + "learning_rate": 1.691342276013745e-05, + "loss": 1.4292, + "step": 3159 + }, + { + "epoch": 0.33, + "learning_rate": 1.691077766606942e-05, + "loss": 1.4405, + "step": 3160 + }, + { + "epoch": 0.33, + "learning_rate": 1.6908131646134757e-05, + "loss": 1.3683, + "step": 3161 + }, + { + "epoch": 0.33, + "learning_rate": 1.690548470068795e-05, + "loss": 1.4731, + "step": 3162 + }, + { + "epoch": 0.33, + "learning_rate": 1.690283683008362e-05, + "loss": 1.4323, + "step": 3163 + }, + { + "epoch": 0.33, + "learning_rate": 1.6900188034676518e-05, + "loss": 1.5133, + "step": 3164 + }, + { + "epoch": 0.33, + "learning_rate": 1.6897538314821516e-05, + "loss": 1.5529, + "step": 3165 + }, + { + "epoch": 0.33, + "learning_rate": 1.6894887670873605e-05, + "loss": 1.4427, + "step": 3166 + }, + { + "epoch": 0.33, + "learning_rate": 1.6892236103187904e-05, + "loss": 1.4344, + "step": 3167 + }, + { + "epoch": 0.33, + "learning_rate": 1.6889583612119657e-05, + "loss": 1.4291, + "step": 3168 + }, + { + "epoch": 0.33, + "learning_rate": 1.6886930198024226e-05, + "loss": 1.4683, + "step": 3169 + }, + { + "epoch": 0.33, + "learning_rate": 1.6884275861257106e-05, + "loss": 1.4442, + "step": 3170 + }, + { + "epoch": 0.33, + "learning_rate": 1.6881620602173905e-05, + "loss": 1.4509, + "step": 3171 + }, + { + "epoch": 0.33, + "learning_rate": 1.6878964421130362e-05, + "loss": 1.5113, + "step": 3172 + }, + { + "epoch": 0.33, + "learning_rate": 1.6876307318482334e-05, + "loss": 1.4261, + "step": 3173 + }, + { + "epoch": 0.33, + "learning_rate": 1.6873649294585805e-05, + "loss": 1.445, + "step": 3174 + }, + { + "epoch": 0.33, + "learning_rate": 1.6870990349796886e-05, + "loss": 1.4603, + "step": 3175 + }, + { + "epoch": 0.33, + "learning_rate": 1.68683304844718e-05, + "loss": 1.41, + "step": 3176 + }, + { + "epoch": 0.33, + "learning_rate": 1.686566969896691e-05, + "loss": 1.4018, + "step": 3177 + }, + { + "epoch": 0.33, + "learning_rate": 1.6863007993638687e-05, + "loss": 1.422, + "step": 3178 + }, + { + "epoch": 0.33, + "learning_rate": 1.6860345368843727e-05, + "loss": 1.4412, + "step": 3179 + }, + { + "epoch": 0.33, + "learning_rate": 1.6857681824938768e-05, + "loss": 1.5411, + "step": 3180 + }, + { + "epoch": 0.33, + "learning_rate": 1.685501736228064e-05, + "loss": 1.4416, + "step": 3181 + }, + { + "epoch": 0.33, + "learning_rate": 1.685235198122632e-05, + "loss": 1.5113, + "step": 3182 + }, + { + "epoch": 0.33, + "learning_rate": 1.6849685682132903e-05, + "loss": 1.423, + "step": 3183 + }, + { + "epoch": 0.33, + "learning_rate": 1.68470184653576e-05, + "loss": 1.404, + "step": 3184 + }, + { + "epoch": 0.33, + "eval_loss": 1.4771089553833008, + "eval_runtime": 77.4034, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3184 + }, + { + "epoch": 0.33, + "learning_rate": 1.6844350331257747e-05, + "loss": 1.4624, + "step": 3185 + }, + { + "epoch": 0.33, + "learning_rate": 1.6841681280190814e-05, + "loss": 1.4306, + "step": 3186 + }, + { + "epoch": 0.33, + "learning_rate": 1.683901131251438e-05, + "loss": 1.42, + "step": 3187 + }, + { + "epoch": 0.33, + "learning_rate": 1.6836340428586155e-05, + "loss": 1.4787, + "step": 3188 + }, + { + "epoch": 0.33, + "learning_rate": 1.6833668628763965e-05, + "loss": 1.3485, + "step": 3189 + }, + { + "epoch": 0.33, + "learning_rate": 1.683099591340576e-05, + "loss": 1.3674, + "step": 3190 + }, + { + "epoch": 0.33, + "learning_rate": 1.6828322282869627e-05, + "loss": 1.5187, + "step": 3191 + }, + { + "epoch": 0.33, + "learning_rate": 1.682564773751375e-05, + "loss": 1.4847, + "step": 3192 + }, + { + "epoch": 0.33, + "learning_rate": 1.682297227769646e-05, + "loss": 1.4815, + "step": 3193 + }, + { + "epoch": 0.33, + "learning_rate": 1.682029590377619e-05, + "loss": 1.4281, + "step": 3194 + }, + { + "epoch": 0.34, + "learning_rate": 1.6817618616111517e-05, + "loss": 1.4734, + "step": 3195 + }, + { + "epoch": 0.34, + "learning_rate": 1.681494041506112e-05, + "loss": 1.4861, + "step": 3196 + }, + { + "epoch": 0.34, + "learning_rate": 1.6812261300983808e-05, + "loss": 1.4372, + "step": 3197 + }, + { + "epoch": 0.34, + "learning_rate": 1.680958127423852e-05, + "loss": 1.4396, + "step": 3198 + }, + { + "epoch": 0.34, + "learning_rate": 1.680690033518431e-05, + "loss": 1.4225, + "step": 3199 + }, + { + "epoch": 0.34, + "learning_rate": 1.6804218484180347e-05, + "loss": 1.4925, + "step": 3200 + }, + { + "epoch": 0.34, + "learning_rate": 1.6801535721585942e-05, + "loss": 1.4306, + "step": 3201 + }, + { + "epoch": 0.34, + "learning_rate": 1.6798852047760506e-05, + "loss": 1.4298, + "step": 3202 + }, + { + "epoch": 0.34, + "learning_rate": 1.6796167463063588e-05, + "loss": 1.4725, + "step": 3203 + }, + { + "epoch": 0.34, + "learning_rate": 1.679348196785485e-05, + "loss": 1.4648, + "step": 3204 + }, + { + "epoch": 0.34, + "learning_rate": 1.6790795562494087e-05, + "loss": 1.4152, + "step": 3205 + }, + { + "epoch": 0.34, + "learning_rate": 1.6788108247341198e-05, + "loss": 1.4637, + "step": 3206 + }, + { + "epoch": 0.34, + "learning_rate": 1.6785420022756216e-05, + "loss": 1.4077, + "step": 3207 + }, + { + "epoch": 0.34, + "learning_rate": 1.67827308890993e-05, + "loss": 1.4585, + "step": 3208 + }, + { + "epoch": 0.34, + "learning_rate": 1.678004084673072e-05, + "loss": 1.3747, + "step": 3209 + }, + { + "epoch": 0.34, + "learning_rate": 1.6777349896010876e-05, + "loss": 1.4264, + "step": 3210 + }, + { + "epoch": 0.34, + "learning_rate": 1.677465803730028e-05, + "loss": 1.4178, + "step": 3211 + }, + { + "epoch": 0.34, + "learning_rate": 1.6771965270959584e-05, + "loss": 1.3876, + "step": 3212 + }, + { + "epoch": 0.34, + "learning_rate": 1.6769271597349538e-05, + "loss": 1.4658, + "step": 3213 + }, + { + "epoch": 0.34, + "learning_rate": 1.6766577016831026e-05, + "loss": 1.3968, + "step": 3214 + }, + { + "epoch": 0.34, + "learning_rate": 1.676388152976506e-05, + "loss": 1.5015, + "step": 3215 + }, + { + "epoch": 0.34, + "learning_rate": 1.6761185136512756e-05, + "loss": 1.4121, + "step": 3216 + }, + { + "epoch": 0.34, + "learning_rate": 1.675848783743537e-05, + "loss": 1.4146, + "step": 3217 + }, + { + "epoch": 0.34, + "learning_rate": 1.675578963289427e-05, + "loss": 1.4113, + "step": 3218 + }, + { + "epoch": 0.34, + "learning_rate": 1.6753090523250937e-05, + "loss": 1.4048, + "step": 3219 + }, + { + "epoch": 0.34, + "learning_rate": 1.6750390508866994e-05, + "loss": 1.4959, + "step": 3220 + }, + { + "epoch": 0.34, + "learning_rate": 1.6747689590104167e-05, + "loss": 1.4445, + "step": 3221 + }, + { + "epoch": 0.34, + "learning_rate": 1.6744987767324312e-05, + "loss": 1.4611, + "step": 3222 + }, + { + "epoch": 0.34, + "learning_rate": 1.67422850408894e-05, + "loss": 1.4141, + "step": 3223 + }, + { + "epoch": 0.34, + "learning_rate": 1.6739581411161535e-05, + "loss": 1.4218, + "step": 3224 + }, + { + "epoch": 0.34, + "learning_rate": 1.6736876878502925e-05, + "loss": 1.4266, + "step": 3225 + }, + { + "epoch": 0.34, + "learning_rate": 1.6734171443275913e-05, + "loss": 1.4941, + "step": 3226 + }, + { + "epoch": 0.34, + "learning_rate": 1.6731465105842955e-05, + "loss": 1.4294, + "step": 3227 + }, + { + "epoch": 0.34, + "learning_rate": 1.6728757866566635e-05, + "loss": 1.4189, + "step": 3228 + }, + { + "epoch": 0.34, + "learning_rate": 1.6726049725809647e-05, + "loss": 1.4713, + "step": 3229 + }, + { + "epoch": 0.34, + "learning_rate": 1.6723340683934818e-05, + "loss": 1.4203, + "step": 3230 + }, + { + "epoch": 0.34, + "learning_rate": 1.6720630741305088e-05, + "loss": 1.4112, + "step": 3231 + }, + { + "epoch": 0.34, + "learning_rate": 1.6717919898283523e-05, + "loss": 1.3811, + "step": 3232 + }, + { + "epoch": 0.34, + "learning_rate": 1.6715208155233296e-05, + "loss": 1.4242, + "step": 3233 + }, + { + "epoch": 0.34, + "learning_rate": 1.6712495512517725e-05, + "loss": 1.4207, + "step": 3234 + }, + { + "epoch": 0.34, + "learning_rate": 1.6709781970500222e-05, + "loss": 1.4888, + "step": 3235 + }, + { + "epoch": 0.34, + "learning_rate": 1.670706752954434e-05, + "loss": 1.4501, + "step": 3236 + }, + { + "epoch": 0.34, + "learning_rate": 1.670435219001374e-05, + "loss": 1.4367, + "step": 3237 + }, + { + "epoch": 0.34, + "learning_rate": 1.6701635952272212e-05, + "loss": 1.3959, + "step": 3238 + }, + { + "epoch": 0.34, + "learning_rate": 1.6698918816683655e-05, + "loss": 1.4257, + "step": 3239 + }, + { + "epoch": 0.34, + "learning_rate": 1.6696200783612102e-05, + "loss": 1.4718, + "step": 3240 + }, + { + "epoch": 0.34, + "learning_rate": 1.6693481853421697e-05, + "loss": 1.5899, + "step": 3241 + }, + { + "epoch": 0.34, + "learning_rate": 1.6690762026476707e-05, + "loss": 1.418, + "step": 3242 + }, + { + "epoch": 0.34, + "learning_rate": 1.668804130314152e-05, + "loss": 1.4076, + "step": 3243 + }, + { + "epoch": 0.34, + "learning_rate": 1.6685319683780645e-05, + "loss": 1.4571, + "step": 3244 + }, + { + "epoch": 0.34, + "learning_rate": 1.66825971687587e-05, + "loss": 1.4066, + "step": 3245 + }, + { + "epoch": 0.34, + "learning_rate": 1.6679873758440442e-05, + "loss": 1.4639, + "step": 3246 + }, + { + "epoch": 0.34, + "learning_rate": 1.6677149453190732e-05, + "loss": 1.453, + "step": 3247 + }, + { + "epoch": 0.34, + "learning_rate": 1.6674424253374558e-05, + "loss": 1.4262, + "step": 3248 + }, + { + "epoch": 0.34, + "learning_rate": 1.667169815935703e-05, + "loss": 1.3687, + "step": 3249 + }, + { + "epoch": 0.34, + "learning_rate": 1.6668971171503372e-05, + "loss": 1.5557, + "step": 3250 + }, + { + "epoch": 0.34, + "learning_rate": 1.6666243290178933e-05, + "loss": 1.4639, + "step": 3251 + }, + { + "epoch": 0.34, + "learning_rate": 1.6663514515749172e-05, + "loss": 1.4334, + "step": 3252 + }, + { + "epoch": 0.34, + "learning_rate": 1.6660784848579685e-05, + "loss": 1.3523, + "step": 3253 + }, + { + "epoch": 0.34, + "learning_rate": 1.6658054289036166e-05, + "loss": 1.3738, + "step": 3254 + }, + { + "epoch": 0.34, + "learning_rate": 1.665532283748445e-05, + "loss": 1.4159, + "step": 3255 + }, + { + "epoch": 0.34, + "learning_rate": 1.6652590494290474e-05, + "loss": 1.3609, + "step": 3256 + }, + { + "epoch": 0.34, + "learning_rate": 1.6649857259820303e-05, + "loss": 1.4449, + "step": 3257 + }, + { + "epoch": 0.34, + "learning_rate": 1.6647123134440126e-05, + "loss": 1.424, + "step": 3258 + }, + { + "epoch": 0.34, + "learning_rate": 1.664438811851624e-05, + "loss": 1.4737, + "step": 3259 + }, + { + "epoch": 0.34, + "learning_rate": 1.6641652212415066e-05, + "loss": 1.2717, + "step": 3260 + }, + { + "epoch": 0.34, + "learning_rate": 1.663891541650315e-05, + "loss": 1.4845, + "step": 3261 + }, + { + "epoch": 0.34, + "learning_rate": 1.663617773114715e-05, + "loss": 1.4115, + "step": 3262 + }, + { + "epoch": 0.34, + "learning_rate": 1.663343915671384e-05, + "loss": 1.4237, + "step": 3263 + }, + { + "epoch": 0.34, + "learning_rate": 1.6630699693570127e-05, + "loss": 1.4209, + "step": 3264 + }, + { + "epoch": 0.34, + "learning_rate": 1.6627959342083026e-05, + "loss": 1.506, + "step": 3265 + }, + { + "epoch": 0.34, + "learning_rate": 1.6625218102619672e-05, + "loss": 1.4466, + "step": 3266 + }, + { + "epoch": 0.34, + "learning_rate": 1.6622475975547324e-05, + "loss": 1.4129, + "step": 3267 + }, + { + "epoch": 0.34, + "learning_rate": 1.661973296123335e-05, + "loss": 1.4152, + "step": 3268 + }, + { + "epoch": 0.34, + "learning_rate": 1.661698906004525e-05, + "loss": 1.43, + "step": 3269 + }, + { + "epoch": 0.34, + "learning_rate": 1.661424427235064e-05, + "loss": 1.4701, + "step": 3270 + }, + { + "epoch": 0.34, + "learning_rate": 1.6611498598517238e-05, + "loss": 1.4598, + "step": 3271 + }, + { + "epoch": 0.34, + "learning_rate": 1.66087520389129e-05, + "loss": 1.4795, + "step": 3272 + }, + { + "epoch": 0.34, + "learning_rate": 1.6606004593905595e-05, + "loss": 1.5264, + "step": 3273 + }, + { + "epoch": 0.34, + "learning_rate": 1.6603256263863415e-05, + "loss": 1.4412, + "step": 3274 + }, + { + "epoch": 0.34, + "learning_rate": 1.6600507049154556e-05, + "loss": 1.45, + "step": 3275 + }, + { + "epoch": 0.34, + "learning_rate": 1.659775695014735e-05, + "loss": 1.4985, + "step": 3276 + }, + { + "epoch": 0.34, + "learning_rate": 1.659500596721024e-05, + "loss": 1.496, + "step": 3277 + }, + { + "epoch": 0.34, + "learning_rate": 1.6592254100711775e-05, + "loss": 1.4386, + "step": 3278 + }, + { + "epoch": 0.34, + "learning_rate": 1.658950135102065e-05, + "loss": 1.4073, + "step": 3279 + }, + { + "epoch": 0.34, + "learning_rate": 1.658674771850565e-05, + "loss": 1.3912, + "step": 3280 + }, + { + "epoch": 0.34, + "learning_rate": 1.6583993203535702e-05, + "loss": 1.3628, + "step": 3281 + }, + { + "epoch": 0.34, + "learning_rate": 1.658123780647983e-05, + "loss": 1.6089, + "step": 3282 + }, + { + "epoch": 0.34, + "learning_rate": 1.6578481527707196e-05, + "loss": 1.2367, + "step": 3283 + }, + { + "epoch": 0.34, + "learning_rate": 1.657572436758706e-05, + "loss": 1.4058, + "step": 3284 + }, + { + "epoch": 0.34, + "learning_rate": 1.6572966326488825e-05, + "loss": 1.4067, + "step": 3285 + }, + { + "epoch": 0.34, + "learning_rate": 1.657020740478198e-05, + "loss": 1.4187, + "step": 3286 + }, + { + "epoch": 0.34, + "learning_rate": 1.6567447602836166e-05, + "loss": 1.4599, + "step": 3287 + }, + { + "epoch": 0.34, + "learning_rate": 1.6564686921021115e-05, + "loss": 1.432, + "step": 3288 + }, + { + "epoch": 0.34, + "learning_rate": 1.6561925359706693e-05, + "loss": 1.3941, + "step": 3289 + }, + { + "epoch": 0.35, + "learning_rate": 1.6559162919262874e-05, + "loss": 1.3644, + "step": 3290 + }, + { + "epoch": 0.35, + "learning_rate": 1.6556399600059756e-05, + "loss": 1.4628, + "step": 3291 + }, + { + "epoch": 0.35, + "learning_rate": 1.6553635402467555e-05, + "loss": 1.4355, + "step": 3292 + }, + { + "epoch": 0.35, + "learning_rate": 1.6550870326856596e-05, + "loss": 1.4627, + "step": 3293 + }, + { + "epoch": 0.35, + "learning_rate": 1.6548104373597335e-05, + "loss": 1.442, + "step": 3294 + }, + { + "epoch": 0.35, + "learning_rate": 1.6545337543060338e-05, + "loss": 1.3991, + "step": 3295 + }, + { + "epoch": 0.35, + "learning_rate": 1.6542569835616283e-05, + "loss": 1.4193, + "step": 3296 + }, + { + "epoch": 0.35, + "learning_rate": 1.6539801251635982e-05, + "loss": 1.4792, + "step": 3297 + }, + { + "epoch": 0.35, + "learning_rate": 1.653703179149034e-05, + "loss": 1.4735, + "step": 3298 + }, + { + "epoch": 0.35, + "learning_rate": 1.6534261455550408e-05, + "loss": 1.451, + "step": 3299 + }, + { + "epoch": 0.35, + "learning_rate": 1.653149024418733e-05, + "loss": 1.3975, + "step": 3300 + }, + { + "epoch": 0.35, + "learning_rate": 1.652871815777238e-05, + "loss": 1.4843, + "step": 3301 + }, + { + "epoch": 0.35, + "learning_rate": 1.6525945196676948e-05, + "loss": 1.4782, + "step": 3302 + }, + { + "epoch": 0.35, + "learning_rate": 1.652317136127254e-05, + "loss": 1.3865, + "step": 3303 + }, + { + "epoch": 0.35, + "learning_rate": 1.6520396651930777e-05, + "loss": 1.4359, + "step": 3304 + }, + { + "epoch": 0.35, + "learning_rate": 1.6517621069023397e-05, + "loss": 1.4289, + "step": 3305 + }, + { + "epoch": 0.35, + "learning_rate": 1.651484461292226e-05, + "loss": 1.3526, + "step": 3306 + }, + { + "epoch": 0.35, + "learning_rate": 1.6512067283999336e-05, + "loss": 1.3671, + "step": 3307 + }, + { + "epoch": 0.35, + "learning_rate": 1.650928908262672e-05, + "loss": 1.6041, + "step": 3308 + }, + { + "epoch": 0.35, + "learning_rate": 1.650651000917662e-05, + "loss": 1.4322, + "step": 3309 + }, + { + "epoch": 0.35, + "learning_rate": 1.6503730064021354e-05, + "loss": 1.3992, + "step": 3310 + }, + { + "epoch": 0.35, + "learning_rate": 1.650094924753337e-05, + "loss": 1.4928, + "step": 3311 + }, + { + "epoch": 0.35, + "learning_rate": 1.6498167560085222e-05, + "loss": 1.4075, + "step": 3312 + }, + { + "epoch": 0.35, + "learning_rate": 1.6495385002049583e-05, + "loss": 1.4535, + "step": 3313 + }, + { + "epoch": 0.35, + "learning_rate": 1.6492601573799253e-05, + "loss": 1.4221, + "step": 3314 + }, + { + "epoch": 0.35, + "learning_rate": 1.6489817275707133e-05, + "loss": 1.3688, + "step": 3315 + }, + { + "epoch": 0.35, + "learning_rate": 1.6487032108146243e-05, + "loss": 1.3889, + "step": 3316 + }, + { + "epoch": 0.35, + "learning_rate": 1.6484246071489733e-05, + "loss": 1.3942, + "step": 3317 + }, + { + "epoch": 0.35, + "learning_rate": 1.6481459166110858e-05, + "loss": 1.4004, + "step": 3318 + }, + { + "epoch": 0.35, + "learning_rate": 1.647867139238299e-05, + "loss": 1.7308, + "step": 3319 + }, + { + "epoch": 0.35, + "learning_rate": 1.6475882750679622e-05, + "loss": 1.5001, + "step": 3320 + }, + { + "epoch": 0.35, + "learning_rate": 1.647309324137435e-05, + "loss": 1.4325, + "step": 3321 + }, + { + "epoch": 0.35, + "learning_rate": 1.6470302864840913e-05, + "loss": 1.4494, + "step": 3322 + }, + { + "epoch": 0.35, + "learning_rate": 1.6467511621453136e-05, + "loss": 1.4418, + "step": 3323 + }, + { + "epoch": 0.35, + "learning_rate": 1.646471951158498e-05, + "loss": 1.4046, + "step": 3324 + }, + { + "epoch": 0.35, + "learning_rate": 1.6461926535610517e-05, + "loss": 1.5031, + "step": 3325 + }, + { + "epoch": 0.35, + "learning_rate": 1.645913269390393e-05, + "loss": 1.4813, + "step": 3326 + }, + { + "epoch": 0.35, + "learning_rate": 1.6456337986839525e-05, + "loss": 1.3842, + "step": 3327 + }, + { + "epoch": 0.35, + "learning_rate": 1.645354241479172e-05, + "loss": 1.4539, + "step": 3328 + }, + { + "epoch": 0.35, + "learning_rate": 1.6450745978135048e-05, + "loss": 1.4503, + "step": 3329 + }, + { + "epoch": 0.35, + "learning_rate": 1.6447948677244163e-05, + "loss": 1.3741, + "step": 3330 + }, + { + "epoch": 0.35, + "learning_rate": 1.6445150512493832e-05, + "loss": 1.425, + "step": 3331 + }, + { + "epoch": 0.35, + "learning_rate": 1.644235148425893e-05, + "loss": 1.4277, + "step": 3332 + }, + { + "epoch": 0.35, + "learning_rate": 1.6439551592914464e-05, + "loss": 1.4918, + "step": 3333 + }, + { + "epoch": 0.35, + "learning_rate": 1.6436750838835543e-05, + "loss": 1.3364, + "step": 3334 + }, + { + "epoch": 0.35, + "learning_rate": 1.6433949222397397e-05, + "loss": 1.4741, + "step": 3335 + }, + { + "epoch": 0.35, + "learning_rate": 1.643114674397537e-05, + "loss": 1.3867, + "step": 3336 + }, + { + "epoch": 0.35, + "learning_rate": 1.642834340394492e-05, + "loss": 1.3817, + "step": 3337 + }, + { + "epoch": 0.35, + "learning_rate": 1.6425539202681625e-05, + "loss": 1.4308, + "step": 3338 + }, + { + "epoch": 0.35, + "learning_rate": 1.6422734140561178e-05, + "loss": 1.4401, + "step": 3339 + }, + { + "epoch": 0.35, + "learning_rate": 1.641992821795938e-05, + "loss": 1.4338, + "step": 3340 + }, + { + "epoch": 0.35, + "learning_rate": 1.641712143525216e-05, + "loss": 1.3804, + "step": 3341 + }, + { + "epoch": 0.35, + "learning_rate": 1.6414313792815546e-05, + "loss": 1.371, + "step": 3342 + }, + { + "epoch": 0.35, + "learning_rate": 1.6411505291025695e-05, + "loss": 1.4102, + "step": 3343 + }, + { + "epoch": 0.35, + "learning_rate": 1.6408695930258875e-05, + "loss": 1.4433, + "step": 3344 + }, + { + "epoch": 0.35, + "learning_rate": 1.6405885710891467e-05, + "loss": 1.3895, + "step": 3345 + }, + { + "epoch": 0.35, + "learning_rate": 1.6403074633299966e-05, + "loss": 1.4321, + "step": 3346 + }, + { + "epoch": 0.35, + "learning_rate": 1.640026269786098e-05, + "loss": 1.4207, + "step": 3347 + }, + { + "epoch": 0.35, + "learning_rate": 1.639744990495125e-05, + "loss": 1.3758, + "step": 3348 + }, + { + "epoch": 0.35, + "learning_rate": 1.6394636254947612e-05, + "loss": 1.4203, + "step": 3349 + }, + { + "epoch": 0.35, + "learning_rate": 1.6391821748227013e-05, + "loss": 1.4596, + "step": 3350 + }, + { + "epoch": 0.35, + "learning_rate": 1.6389006385166537e-05, + "loss": 1.4344, + "step": 3351 + }, + { + "epoch": 0.35, + "learning_rate": 1.6386190166143366e-05, + "loss": 1.4048, + "step": 3352 + }, + { + "epoch": 0.35, + "learning_rate": 1.6383373091534798e-05, + "loss": 1.4348, + "step": 3353 + }, + { + "epoch": 0.35, + "learning_rate": 1.638055516171825e-05, + "loss": 1.4972, + "step": 3354 + }, + { + "epoch": 0.35, + "learning_rate": 1.6377736377071258e-05, + "loss": 1.4685, + "step": 3355 + }, + { + "epoch": 0.35, + "learning_rate": 1.637491673797146e-05, + "loss": 1.4093, + "step": 3356 + }, + { + "epoch": 0.35, + "learning_rate": 1.6372096244796616e-05, + "loss": 1.4452, + "step": 3357 + }, + { + "epoch": 0.35, + "learning_rate": 1.63692748979246e-05, + "loss": 1.4458, + "step": 3358 + }, + { + "epoch": 0.35, + "learning_rate": 1.6366452697733404e-05, + "loss": 1.4187, + "step": 3359 + }, + { + "epoch": 0.35, + "learning_rate": 1.6363629644601126e-05, + "loss": 1.4052, + "step": 3360 + }, + { + "epoch": 0.35, + "learning_rate": 1.6360805738905984e-05, + "loss": 1.439, + "step": 3361 + }, + { + "epoch": 0.35, + "learning_rate": 1.635798098102631e-05, + "loss": 1.4131, + "step": 3362 + }, + { + "epoch": 0.35, + "learning_rate": 1.6355155371340544e-05, + "loss": 1.4391, + "step": 3363 + }, + { + "epoch": 0.35, + "learning_rate": 1.6352328910227252e-05, + "loss": 1.4318, + "step": 3364 + }, + { + "epoch": 0.35, + "learning_rate": 1.63495015980651e-05, + "loss": 1.5112, + "step": 3365 + }, + { + "epoch": 0.35, + "learning_rate": 1.6346673435232884e-05, + "loss": 1.4688, + "step": 3366 + }, + { + "epoch": 0.35, + "learning_rate": 1.6343844422109496e-05, + "loss": 1.3807, + "step": 3367 + }, + { + "epoch": 0.35, + "learning_rate": 1.634101455907396e-05, + "loss": 1.4083, + "step": 3368 + }, + { + "epoch": 0.35, + "learning_rate": 1.6338183846505394e-05, + "loss": 1.3566, + "step": 3369 + }, + { + "epoch": 0.35, + "learning_rate": 1.633535228478305e-05, + "loss": 1.4287, + "step": 3370 + }, + { + "epoch": 0.35, + "learning_rate": 1.6332519874286285e-05, + "loss": 1.3494, + "step": 3371 + }, + { + "epoch": 0.35, + "learning_rate": 1.6329686615394558e-05, + "loss": 1.3813, + "step": 3372 + }, + { + "epoch": 0.35, + "learning_rate": 1.6326852508487468e-05, + "loss": 1.4241, + "step": 3373 + }, + { + "epoch": 0.35, + "learning_rate": 1.63240175539447e-05, + "loss": 1.424, + "step": 3374 + }, + { + "epoch": 0.35, + "learning_rate": 1.632118175214607e-05, + "loss": 1.4212, + "step": 3375 + }, + { + "epoch": 0.35, + "learning_rate": 1.6318345103471504e-05, + "loss": 1.4671, + "step": 3376 + }, + { + "epoch": 0.35, + "learning_rate": 1.6315507608301044e-05, + "loss": 1.4593, + "step": 3377 + }, + { + "epoch": 0.35, + "learning_rate": 1.631266926701483e-05, + "loss": 1.7816, + "step": 3378 + }, + { + "epoch": 0.35, + "learning_rate": 1.6309830079993134e-05, + "loss": 1.5134, + "step": 3379 + }, + { + "epoch": 0.35, + "learning_rate": 1.6306990047616334e-05, + "loss": 0.8933, + "step": 3380 + }, + { + "epoch": 0.35, + "learning_rate": 1.630414917026492e-05, + "loss": 1.1033, + "step": 3381 + }, + { + "epoch": 0.35, + "learning_rate": 1.6301307448319497e-05, + "loss": 1.3494, + "step": 3382 + }, + { + "epoch": 0.35, + "learning_rate": 1.6298464882160784e-05, + "loss": 1.4299, + "step": 3383 + }, + { + "epoch": 0.35, + "eval_loss": 1.482450008392334, + "eval_runtime": 77.3737, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3383 + }, + { + "epoch": 0.35, + "learning_rate": 1.629562147216961e-05, + "loss": 1.3971, + "step": 3384 + }, + { + "epoch": 0.35, + "learning_rate": 1.6292777218726917e-05, + "loss": 1.3706, + "step": 3385 + }, + { + "epoch": 0.36, + "learning_rate": 1.6289932122213765e-05, + "loss": 1.4524, + "step": 3386 + }, + { + "epoch": 0.36, + "learning_rate": 1.6287086183011328e-05, + "loss": 1.4595, + "step": 3387 + }, + { + "epoch": 0.36, + "learning_rate": 1.628423940150088e-05, + "loss": 1.492, + "step": 3388 + }, + { + "epoch": 0.36, + "learning_rate": 1.628139177806382e-05, + "loss": 1.5576, + "step": 3389 + }, + { + "epoch": 0.36, + "learning_rate": 1.6278543313081657e-05, + "loss": 1.4615, + "step": 3390 + }, + { + "epoch": 0.36, + "learning_rate": 1.6275694006936015e-05, + "loss": 1.3456, + "step": 3391 + }, + { + "epoch": 0.36, + "learning_rate": 1.627284386000862e-05, + "loss": 1.4254, + "step": 3392 + }, + { + "epoch": 0.36, + "learning_rate": 1.6269992872681325e-05, + "loss": 1.433, + "step": 3393 + }, + { + "epoch": 0.36, + "learning_rate": 1.626714104533609e-05, + "loss": 1.5291, + "step": 3394 + }, + { + "epoch": 0.36, + "learning_rate": 1.626428837835498e-05, + "loss": 1.4502, + "step": 3395 + }, + { + "epoch": 0.36, + "learning_rate": 1.626143487212019e-05, + "loss": 1.3756, + "step": 3396 + }, + { + "epoch": 0.36, + "learning_rate": 1.6258580527014002e-05, + "loss": 1.414, + "step": 3397 + }, + { + "epoch": 0.36, + "learning_rate": 1.6255725343418835e-05, + "loss": 1.6289, + "step": 3398 + }, + { + "epoch": 0.36, + "learning_rate": 1.6252869321717208e-05, + "loss": 1.4862, + "step": 3399 + }, + { + "epoch": 0.36, + "learning_rate": 1.6250012462291756e-05, + "loss": 1.4213, + "step": 3400 + }, + { + "epoch": 0.36, + "learning_rate": 1.6247154765525217e-05, + "loss": 1.524, + "step": 3401 + }, + { + "epoch": 0.36, + "learning_rate": 1.624429623180046e-05, + "loss": 1.6013, + "step": 3402 + }, + { + "epoch": 0.36, + "learning_rate": 1.624143686150045e-05, + "loss": 1.4557, + "step": 3403 + }, + { + "epoch": 0.36, + "learning_rate": 1.6238576655008266e-05, + "loss": 1.3831, + "step": 3404 + }, + { + "epoch": 0.36, + "learning_rate": 1.6235715612707105e-05, + "loss": 1.4008, + "step": 3405 + }, + { + "epoch": 0.36, + "learning_rate": 1.623285373498028e-05, + "loss": 1.4848, + "step": 3406 + }, + { + "epoch": 0.36, + "learning_rate": 1.6229991022211197e-05, + "loss": 1.4459, + "step": 3407 + }, + { + "epoch": 0.36, + "learning_rate": 1.6227127474783393e-05, + "loss": 1.4334, + "step": 3408 + }, + { + "epoch": 0.36, + "learning_rate": 1.6224263093080507e-05, + "loss": 1.4123, + "step": 3409 + }, + { + "epoch": 0.36, + "learning_rate": 1.6221397877486294e-05, + "loss": 1.3691, + "step": 3410 + }, + { + "epoch": 0.36, + "learning_rate": 1.6218531828384618e-05, + "loss": 1.4128, + "step": 3411 + }, + { + "epoch": 0.36, + "learning_rate": 1.6215664946159457e-05, + "loss": 1.3642, + "step": 3412 + }, + { + "epoch": 0.36, + "learning_rate": 1.6212797231194902e-05, + "loss": 1.4311, + "step": 3413 + }, + { + "epoch": 0.36, + "learning_rate": 1.6209928683875152e-05, + "loss": 1.4695, + "step": 3414 + }, + { + "epoch": 0.36, + "learning_rate": 1.6207059304584514e-05, + "loss": 1.3871, + "step": 3415 + }, + { + "epoch": 0.36, + "learning_rate": 1.6204189093707414e-05, + "loss": 1.4219, + "step": 3416 + }, + { + "epoch": 0.36, + "learning_rate": 1.620131805162839e-05, + "loss": 1.6199, + "step": 3417 + }, + { + "epoch": 0.36, + "learning_rate": 1.619844617873208e-05, + "loss": 1.4433, + "step": 3418 + }, + { + "epoch": 0.36, + "learning_rate": 1.619557347540325e-05, + "loss": 1.4773, + "step": 3419 + }, + { + "epoch": 0.36, + "learning_rate": 1.6192699942026763e-05, + "loss": 1.4551, + "step": 3420 + }, + { + "epoch": 0.36, + "learning_rate": 1.6189825578987603e-05, + "loss": 1.4903, + "step": 3421 + }, + { + "epoch": 0.36, + "learning_rate": 1.6186950386670855e-05, + "loss": 1.473, + "step": 3422 + }, + { + "epoch": 0.36, + "learning_rate": 1.6184074365461722e-05, + "loss": 1.4082, + "step": 3423 + }, + { + "epoch": 0.36, + "learning_rate": 1.6181197515745523e-05, + "loss": 1.4746, + "step": 3424 + }, + { + "epoch": 0.36, + "learning_rate": 1.6178319837907674e-05, + "loss": 1.449, + "step": 3425 + }, + { + "epoch": 0.36, + "learning_rate": 1.6175441332333715e-05, + "loss": 1.377, + "step": 3426 + }, + { + "epoch": 0.36, + "learning_rate": 1.617256199940929e-05, + "loss": 1.2364, + "step": 3427 + }, + { + "epoch": 0.36, + "learning_rate": 1.6169681839520155e-05, + "loss": 1.4437, + "step": 3428 + }, + { + "epoch": 0.36, + "learning_rate": 1.616680085305218e-05, + "loss": 1.4726, + "step": 3429 + }, + { + "epoch": 0.36, + "learning_rate": 1.616391904039134e-05, + "loss": 1.4824, + "step": 3430 + }, + { + "epoch": 0.36, + "learning_rate": 1.616103640192373e-05, + "loss": 1.4052, + "step": 3431 + }, + { + "epoch": 0.36, + "learning_rate": 1.6158152938035537e-05, + "loss": 1.4131, + "step": 3432 + }, + { + "epoch": 0.36, + "learning_rate": 1.6155268649113084e-05, + "loss": 1.4267, + "step": 3433 + }, + { + "epoch": 0.36, + "learning_rate": 1.6152383535542786e-05, + "loss": 1.3735, + "step": 3434 + }, + { + "epoch": 0.36, + "learning_rate": 1.6149497597711175e-05, + "loss": 1.4249, + "step": 3435 + }, + { + "epoch": 0.36, + "learning_rate": 1.614661083600489e-05, + "loss": 1.4312, + "step": 3436 + }, + { + "epoch": 0.36, + "learning_rate": 1.6143723250810686e-05, + "loss": 1.4831, + "step": 3437 + }, + { + "epoch": 0.36, + "learning_rate": 1.6140834842515425e-05, + "loss": 1.4183, + "step": 3438 + }, + { + "epoch": 0.36, + "learning_rate": 1.6137945611506078e-05, + "loss": 1.3908, + "step": 3439 + }, + { + "epoch": 0.36, + "learning_rate": 1.613505555816973e-05, + "loss": 1.425, + "step": 3440 + }, + { + "epoch": 0.36, + "learning_rate": 1.613216468289357e-05, + "loss": 1.3589, + "step": 3441 + }, + { + "epoch": 0.36, + "learning_rate": 1.6129272986064903e-05, + "loss": 1.4272, + "step": 3442 + }, + { + "epoch": 0.36, + "learning_rate": 1.6126380468071142e-05, + "loss": 1.4337, + "step": 3443 + }, + { + "epoch": 0.36, + "learning_rate": 1.6123487129299817e-05, + "loss": 1.3872, + "step": 3444 + }, + { + "epoch": 0.36, + "learning_rate": 1.612059297013855e-05, + "loss": 1.374, + "step": 3445 + }, + { + "epoch": 0.36, + "learning_rate": 1.611769799097509e-05, + "loss": 1.314, + "step": 3446 + }, + { + "epoch": 0.36, + "learning_rate": 1.6114802192197284e-05, + "loss": 1.3951, + "step": 3447 + }, + { + "epoch": 0.36, + "learning_rate": 1.6111905574193102e-05, + "loss": 1.4732, + "step": 3448 + }, + { + "epoch": 0.36, + "learning_rate": 1.6109008137350614e-05, + "loss": 1.3575, + "step": 3449 + }, + { + "epoch": 0.36, + "learning_rate": 1.6106109882058e-05, + "loss": 1.4606, + "step": 3450 + }, + { + "epoch": 0.36, + "learning_rate": 1.6103210808703554e-05, + "loss": 1.4357, + "step": 3451 + }, + { + "epoch": 0.36, + "learning_rate": 1.6100310917675678e-05, + "loss": 0.8456, + "step": 3452 + }, + { + "epoch": 0.36, + "learning_rate": 1.609741020936288e-05, + "loss": 1.07, + "step": 3453 + }, + { + "epoch": 0.36, + "learning_rate": 1.6094508684153782e-05, + "loss": 1.4435, + "step": 3454 + }, + { + "epoch": 0.36, + "learning_rate": 1.609160634243711e-05, + "loss": 1.3696, + "step": 3455 + }, + { + "epoch": 0.36, + "learning_rate": 1.6088703184601712e-05, + "loss": 1.4012, + "step": 3456 + }, + { + "epoch": 0.36, + "learning_rate": 1.608579921103653e-05, + "loss": 1.5212, + "step": 3457 + }, + { + "epoch": 0.36, + "learning_rate": 1.608289442213062e-05, + "loss": 1.4339, + "step": 3458 + }, + { + "epoch": 0.36, + "learning_rate": 1.607998881827316e-05, + "loss": 1.4901, + "step": 3459 + }, + { + "epoch": 0.36, + "learning_rate": 1.6077082399853412e-05, + "loss": 1.4822, + "step": 3460 + }, + { + "epoch": 0.36, + "learning_rate": 1.607417516726077e-05, + "loss": 1.3696, + "step": 3461 + }, + { + "epoch": 0.36, + "learning_rate": 1.6071267120884727e-05, + "loss": 1.4434, + "step": 3462 + }, + { + "epoch": 0.36, + "learning_rate": 1.6068358261114886e-05, + "loss": 1.3916, + "step": 3463 + }, + { + "epoch": 0.36, + "learning_rate": 1.606544858834096e-05, + "loss": 1.422, + "step": 3464 + }, + { + "epoch": 0.36, + "learning_rate": 1.6062538102952763e-05, + "loss": 1.367, + "step": 3465 + }, + { + "epoch": 0.36, + "learning_rate": 1.605962680534024e-05, + "loss": 1.3788, + "step": 3466 + }, + { + "epoch": 0.36, + "learning_rate": 1.605671469589342e-05, + "loss": 1.4366, + "step": 3467 + }, + { + "epoch": 0.36, + "learning_rate": 1.6053801775002453e-05, + "loss": 1.4027, + "step": 3468 + }, + { + "epoch": 0.36, + "learning_rate": 1.6050888043057595e-05, + "loss": 1.4386, + "step": 3469 + }, + { + "epoch": 0.36, + "learning_rate": 1.6047973500449212e-05, + "loss": 1.4675, + "step": 3470 + }, + { + "epoch": 0.36, + "learning_rate": 1.6045058147567778e-05, + "loss": 1.6936, + "step": 3471 + }, + { + "epoch": 0.36, + "learning_rate": 1.6042141984803875e-05, + "loss": 1.4858, + "step": 3472 + }, + { + "epoch": 0.36, + "learning_rate": 1.6039225012548196e-05, + "loss": 1.5004, + "step": 3473 + }, + { + "epoch": 0.36, + "learning_rate": 1.6036307231191534e-05, + "loss": 1.4969, + "step": 3474 + }, + { + "epoch": 0.36, + "learning_rate": 1.6033388641124803e-05, + "loss": 1.4027, + "step": 3475 + }, + { + "epoch": 0.36, + "learning_rate": 1.6030469242739016e-05, + "loss": 1.4741, + "step": 3476 + }, + { + "epoch": 0.36, + "learning_rate": 1.60275490364253e-05, + "loss": 1.3887, + "step": 3477 + }, + { + "epoch": 0.36, + "learning_rate": 1.602462802257488e-05, + "loss": 1.6735, + "step": 3478 + }, + { + "epoch": 0.36, + "learning_rate": 1.602170620157911e-05, + "loss": 1.4997, + "step": 3479 + }, + { + "epoch": 0.36, + "learning_rate": 1.601878357382943e-05, + "loss": 1.3973, + "step": 3480 + }, + { + "epoch": 0.37, + "learning_rate": 1.6015860139717398e-05, + "loss": 1.416, + "step": 3481 + }, + { + "epoch": 0.37, + "learning_rate": 1.6012935899634682e-05, + "loss": 1.4102, + "step": 3482 + }, + { + "epoch": 0.37, + "learning_rate": 1.601001085397305e-05, + "loss": 1.4248, + "step": 3483 + }, + { + "epoch": 0.37, + "learning_rate": 1.6007085003124386e-05, + "loss": 1.3909, + "step": 3484 + }, + { + "epoch": 0.37, + "learning_rate": 1.600415834748068e-05, + "loss": 1.4029, + "step": 3485 + }, + { + "epoch": 0.37, + "learning_rate": 1.6001230887434024e-05, + "loss": 1.4219, + "step": 3486 + }, + { + "epoch": 0.37, + "learning_rate": 1.5998302623376633e-05, + "loss": 1.4008, + "step": 3487 + }, + { + "epoch": 0.37, + "learning_rate": 1.5995373555700806e-05, + "loss": 1.5163, + "step": 3488 + }, + { + "epoch": 0.37, + "learning_rate": 1.599244368479897e-05, + "loss": 1.4541, + "step": 3489 + }, + { + "epoch": 0.37, + "learning_rate": 1.598951301106365e-05, + "loss": 1.4454, + "step": 3490 + }, + { + "epoch": 0.37, + "learning_rate": 1.598658153488748e-05, + "loss": 1.1014, + "step": 3491 + }, + { + "epoch": 0.37, + "learning_rate": 1.598364925666321e-05, + "loss": 1.407, + "step": 3492 + }, + { + "epoch": 0.37, + "learning_rate": 1.5980716176783682e-05, + "loss": 1.5046, + "step": 3493 + }, + { + "epoch": 0.37, + "learning_rate": 1.5977782295641857e-05, + "loss": 1.4265, + "step": 3494 + }, + { + "epoch": 0.37, + "learning_rate": 1.5974847613630796e-05, + "loss": 1.46, + "step": 3495 + }, + { + "epoch": 0.37, + "learning_rate": 1.5971912131143677e-05, + "loss": 1.3996, + "step": 3496 + }, + { + "epoch": 0.37, + "learning_rate": 1.5968975848573772e-05, + "loss": 1.4719, + "step": 3497 + }, + { + "epoch": 0.37, + "learning_rate": 1.596603876631447e-05, + "loss": 1.43, + "step": 3498 + }, + { + "epoch": 0.37, + "learning_rate": 1.596310088475927e-05, + "loss": 1.4109, + "step": 3499 + }, + { + "epoch": 0.37, + "learning_rate": 1.5960162204301768e-05, + "loss": 1.3612, + "step": 3500 + }, + { + "epoch": 0.37, + "learning_rate": 1.5957222725335672e-05, + "loss": 1.5045, + "step": 3501 + }, + { + "epoch": 0.37, + "learning_rate": 1.5954282448254794e-05, + "loss": 1.5323, + "step": 3502 + }, + { + "epoch": 0.37, + "learning_rate": 1.595134137345306e-05, + "loss": 1.4518, + "step": 3503 + }, + { + "epoch": 0.37, + "learning_rate": 1.5948399501324495e-05, + "loss": 1.6131, + "step": 3504 + }, + { + "epoch": 0.37, + "learning_rate": 1.594545683226324e-05, + "loss": 1.5076, + "step": 3505 + }, + { + "epoch": 0.37, + "learning_rate": 1.594251336666353e-05, + "loss": 1.482, + "step": 3506 + }, + { + "epoch": 0.37, + "learning_rate": 1.5939569104919716e-05, + "loss": 1.4429, + "step": 3507 + }, + { + "epoch": 0.37, + "learning_rate": 1.5936624047426254e-05, + "loss": 1.4662, + "step": 3508 + }, + { + "epoch": 0.37, + "learning_rate": 1.5933678194577708e-05, + "loss": 1.425, + "step": 3509 + }, + { + "epoch": 0.37, + "learning_rate": 1.5930731546768744e-05, + "loss": 1.4312, + "step": 3510 + }, + { + "epoch": 0.37, + "learning_rate": 1.592778410439414e-05, + "loss": 1.4336, + "step": 3511 + }, + { + "epoch": 0.37, + "learning_rate": 1.5924835867848775e-05, + "loss": 1.4197, + "step": 3512 + }, + { + "epoch": 0.37, + "learning_rate": 1.5921886837527638e-05, + "loss": 1.4456, + "step": 3513 + }, + { + "epoch": 0.37, + "learning_rate": 1.5918937013825823e-05, + "loss": 1.4394, + "step": 3514 + }, + { + "epoch": 0.37, + "learning_rate": 1.5915986397138526e-05, + "loss": 1.3606, + "step": 3515 + }, + { + "epoch": 0.37, + "learning_rate": 1.591303498786106e-05, + "loss": 1.4382, + "step": 3516 + }, + { + "epoch": 0.37, + "learning_rate": 1.591008278638884e-05, + "loss": 1.4185, + "step": 3517 + }, + { + "epoch": 0.37, + "learning_rate": 1.5907129793117374e-05, + "loss": 1.6692, + "step": 3518 + }, + { + "epoch": 0.37, + "learning_rate": 1.59041760084423e-05, + "loss": 1.501, + "step": 3519 + }, + { + "epoch": 0.37, + "learning_rate": 1.5901221432759345e-05, + "loss": 1.5753, + "step": 3520 + }, + { + "epoch": 0.37, + "learning_rate": 1.589826606646434e-05, + "loss": 1.4795, + "step": 3521 + }, + { + "epoch": 0.37, + "learning_rate": 1.5895309909953236e-05, + "loss": 1.4379, + "step": 3522 + }, + { + "epoch": 0.37, + "learning_rate": 1.5892352963622078e-05, + "loss": 1.3426, + "step": 3523 + }, + { + "epoch": 0.37, + "learning_rate": 1.5889395227867025e-05, + "loss": 1.4048, + "step": 3524 + }, + { + "epoch": 0.37, + "learning_rate": 1.5886436703084332e-05, + "loss": 1.4303, + "step": 3525 + }, + { + "epoch": 0.37, + "learning_rate": 1.5883477389670367e-05, + "loss": 1.3684, + "step": 3526 + }, + { + "epoch": 0.37, + "learning_rate": 1.5880517288021602e-05, + "loss": 1.3701, + "step": 3527 + }, + { + "epoch": 0.37, + "learning_rate": 1.587755639853462e-05, + "loss": 1.4308, + "step": 3528 + }, + { + "epoch": 0.37, + "learning_rate": 1.5874594721606096e-05, + "loss": 1.3981, + "step": 3529 + }, + { + "epoch": 0.37, + "learning_rate": 1.5871632257632823e-05, + "loss": 1.5906, + "step": 3530 + }, + { + "epoch": 0.37, + "learning_rate": 1.5868669007011696e-05, + "loss": 1.4642, + "step": 3531 + }, + { + "epoch": 0.37, + "learning_rate": 1.586570497013971e-05, + "loss": 1.411, + "step": 3532 + }, + { + "epoch": 0.37, + "learning_rate": 1.586274014741397e-05, + "loss": 1.3942, + "step": 3533 + }, + { + "epoch": 0.37, + "learning_rate": 1.5859774539231693e-05, + "loss": 1.3952, + "step": 3534 + }, + { + "epoch": 0.37, + "learning_rate": 1.585680814599019e-05, + "loss": 1.4009, + "step": 3535 + }, + { + "epoch": 0.37, + "learning_rate": 1.585384096808688e-05, + "loss": 1.3238, + "step": 3536 + }, + { + "epoch": 0.37, + "learning_rate": 1.585087300591929e-05, + "loss": 1.346, + "step": 3537 + }, + { + "epoch": 0.37, + "learning_rate": 1.584790425988505e-05, + "loss": 1.3739, + "step": 3538 + }, + { + "epoch": 0.37, + "learning_rate": 1.5844934730381895e-05, + "loss": 1.4264, + "step": 3539 + }, + { + "epoch": 0.37, + "learning_rate": 1.5841964417807668e-05, + "loss": 1.4675, + "step": 3540 + }, + { + "epoch": 0.37, + "learning_rate": 1.5838993322560314e-05, + "loss": 1.3337, + "step": 3541 + }, + { + "epoch": 0.37, + "learning_rate": 1.5836021445037883e-05, + "loss": 1.4052, + "step": 3542 + }, + { + "epoch": 0.37, + "learning_rate": 1.583304878563853e-05, + "loss": 1.4311, + "step": 3543 + }, + { + "epoch": 0.37, + "learning_rate": 1.5830075344760513e-05, + "loss": 1.386, + "step": 3544 + }, + { + "epoch": 0.37, + "learning_rate": 1.58271011228022e-05, + "loss": 1.387, + "step": 3545 + }, + { + "epoch": 0.37, + "learning_rate": 1.582412612016206e-05, + "loss": 1.3601, + "step": 3546 + }, + { + "epoch": 0.37, + "learning_rate": 1.5821150337238663e-05, + "loss": 1.5111, + "step": 3547 + }, + { + "epoch": 0.37, + "learning_rate": 1.5818173774430697e-05, + "loss": 1.471, + "step": 3548 + }, + { + "epoch": 0.37, + "learning_rate": 1.581519643213693e-05, + "loss": 1.4442, + "step": 3549 + }, + { + "epoch": 0.37, + "learning_rate": 1.5812218310756263e-05, + "loss": 1.467, + "step": 3550 + }, + { + "epoch": 0.37, + "learning_rate": 1.5809239410687683e-05, + "loss": 1.3731, + "step": 3551 + }, + { + "epoch": 0.37, + "learning_rate": 1.5806259732330286e-05, + "loss": 1.4072, + "step": 3552 + }, + { + "epoch": 0.37, + "learning_rate": 1.5803279276083268e-05, + "loss": 1.3636, + "step": 3553 + }, + { + "epoch": 0.37, + "learning_rate": 1.5800298042345938e-05, + "loss": 1.3915, + "step": 3554 + }, + { + "epoch": 0.37, + "learning_rate": 1.5797316031517705e-05, + "loss": 1.5038, + "step": 3555 + }, + { + "epoch": 0.37, + "learning_rate": 1.5794333243998082e-05, + "loss": 1.4455, + "step": 3556 + }, + { + "epoch": 0.37, + "learning_rate": 1.5791349680186684e-05, + "loss": 1.5062, + "step": 3557 + }, + { + "epoch": 0.37, + "learning_rate": 1.5788365340483234e-05, + "loss": 1.3899, + "step": 3558 + }, + { + "epoch": 0.37, + "learning_rate": 1.5785380225287554e-05, + "loss": 1.4946, + "step": 3559 + }, + { + "epoch": 0.37, + "learning_rate": 1.5782394334999572e-05, + "loss": 1.3859, + "step": 3560 + }, + { + "epoch": 0.37, + "learning_rate": 1.577940767001933e-05, + "loss": 1.541, + "step": 3561 + }, + { + "epoch": 0.37, + "learning_rate": 1.5776420230746952e-05, + "loss": 1.4952, + "step": 3562 + }, + { + "epoch": 0.37, + "learning_rate": 1.5773432017582684e-05, + "loss": 1.6055, + "step": 3563 + }, + { + "epoch": 0.37, + "learning_rate": 1.577044303092687e-05, + "loss": 1.4661, + "step": 3564 + }, + { + "epoch": 0.37, + "learning_rate": 1.576745327117996e-05, + "loss": 1.4082, + "step": 3565 + }, + { + "epoch": 0.37, + "learning_rate": 1.5764462738742493e-05, + "loss": 1.4005, + "step": 3566 + }, + { + "epoch": 0.37, + "learning_rate": 1.5761471434015137e-05, + "loss": 1.3959, + "step": 3567 + }, + { + "epoch": 0.37, + "learning_rate": 1.5758479357398645e-05, + "loss": 1.4567, + "step": 3568 + }, + { + "epoch": 0.37, + "learning_rate": 1.575548650929388e-05, + "loss": 1.3791, + "step": 3569 + }, + { + "epoch": 0.37, + "learning_rate": 1.57524928901018e-05, + "loss": 1.4428, + "step": 3570 + }, + { + "epoch": 0.37, + "learning_rate": 1.5749498500223486e-05, + "loss": 1.3864, + "step": 3571 + }, + { + "epoch": 0.37, + "learning_rate": 1.5746503340060097e-05, + "loss": 1.4019, + "step": 3572 + }, + { + "epoch": 0.37, + "learning_rate": 1.574350741001291e-05, + "loss": 1.5436, + "step": 3573 + }, + { + "epoch": 0.37, + "learning_rate": 1.5740510710483308e-05, + "loss": 1.4637, + "step": 3574 + }, + { + "epoch": 0.37, + "learning_rate": 1.5737513241872767e-05, + "loss": 1.5097, + "step": 3575 + }, + { + "epoch": 0.38, + "learning_rate": 1.5734515004582873e-05, + "loss": 1.5143, + "step": 3576 + }, + { + "epoch": 0.38, + "learning_rate": 1.5731515999015315e-05, + "loss": 1.3926, + "step": 3577 + }, + { + "epoch": 0.38, + "learning_rate": 1.5728516225571874e-05, + "loss": 1.4242, + "step": 3578 + }, + { + "epoch": 0.38, + "learning_rate": 1.5725515684654453e-05, + "loss": 1.4429, + "step": 3579 + }, + { + "epoch": 0.38, + "learning_rate": 1.572251437666504e-05, + "loss": 1.4638, + "step": 3580 + }, + { + "epoch": 0.38, + "learning_rate": 1.5719512302005735e-05, + "loss": 1.3381, + "step": 3581 + }, + { + "epoch": 0.38, + "learning_rate": 1.571650946107874e-05, + "loss": 1.4342, + "step": 3582 + }, + { + "epoch": 0.38, + "eval_loss": 1.4705015420913696, + "eval_runtime": 77.3664, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3582 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 1.6024580315753428e+20, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-3582/training_args.bin b/checkpoint-3582/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-3582/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-398/config.json b/checkpoint-398/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-398/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-398/generation_config.json b/checkpoint-398/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-398/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-398/model-00001-of-00003.safetensors b/checkpoint-398/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..61f8f51989f3fb0dd16098c08ba51ecab1ecbbc3 --- /dev/null +++ b/checkpoint-398/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfb4e7464e276b6d23a8a2f8ef19ace0cb4d4210f2703547df3e678d600b9a73 +size 4943162336 diff --git a/checkpoint-398/model-00002-of-00003.safetensors b/checkpoint-398/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..39c7624766ab7de52cf42a434a2dd97b81781940 --- /dev/null +++ b/checkpoint-398/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0a03e122f1146d9ffdeb7aa00b004130f8865e5ea3bdd551ae3e36308028a0c +size 4999819336 diff --git a/checkpoint-398/model-00003-of-00003.safetensors b/checkpoint-398/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..11d62fbb88a0dc062eba043e2adccd1dc7cd4eb2 --- /dev/null +++ b/checkpoint-398/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1c25557a83599b86737a2971380c5e570703a5ad0f443a4a09b6832e33a469b +size 4540516344 diff --git a/checkpoint-398/model.safetensors.index.json b/checkpoint-398/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-398/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-398/optimizer.pt b/checkpoint-398/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..fe55e4870609ab2294ad2fcf3a1a6c9c86b297cc --- /dev/null +++ b/checkpoint-398/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7841637a5f39b255fe8b4989aaf0fb180633a33f7dba9a3735378ddc60c4ae12 +size 14512103560 diff --git a/checkpoint-398/rng_state_0.pth b/checkpoint-398/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..35252259eb09d8de259231f63f19e786e44bc7b0 --- /dev/null +++ b/checkpoint-398/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08282b46825aa78d10fe10e3fea89555c5b5a691b261a3ddfd58fcb58370edff +size 15984 diff --git a/checkpoint-398/rng_state_1.pth b/checkpoint-398/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..eeb7d8df6ed170dd98dba8737bc9dd038af61afd --- /dev/null +++ b/checkpoint-398/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbab71d98a3a9a92df82a6bba463947327c3a1bcf35cd9f4f46114641fc42dd9 +size 15984 diff --git a/checkpoint-398/rng_state_2.pth b/checkpoint-398/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..e144a445ffd57fbb5be9b5131f17149bde6c4ff5 --- /dev/null +++ b/checkpoint-398/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caac82d57d878d30219a4f9ec289a97ff90c53afc160b968f251b3fd3454b8d8 +size 15984 diff --git a/checkpoint-398/rng_state_3.pth b/checkpoint-398/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..a10f35268ac2a0cb68abc0b78ba5b150b0f29d78 --- /dev/null +++ b/checkpoint-398/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19762d2d370222b01817da11bbaa6665d542293373186d66f754e7246bb861ed +size 15984 diff --git a/checkpoint-398/rng_state_4.pth b/checkpoint-398/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..e6ef21562e384e0889ec2400e8f84b6b0bc59035 --- /dev/null +++ b/checkpoint-398/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00c7508b346a7d3c5c23392845f1d013331114ade778794b76e919cb3ed5d33e +size 15984 diff --git a/checkpoint-398/rng_state_5.pth b/checkpoint-398/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..126662e5f97dd3f9cd7fb87e70843d3d5532dde3 --- /dev/null +++ b/checkpoint-398/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b89de7d14dd20a191f56b74c816ef8b7fe5c171e31efbeadbf321c4539ed68c3 +size 15984 diff --git a/checkpoint-398/rng_state_6.pth b/checkpoint-398/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..d4e6b27cc99b0fa8e6bbf967892f9304b444d81d --- /dev/null +++ b/checkpoint-398/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c71152053553e6e22d670fbc4fd7550bf8a046b54cad7b71869787986a6a42c +size 15984 diff --git a/checkpoint-398/rng_state_7.pth b/checkpoint-398/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..14e214a61e5311f2b7edf2200ec0365ed2dcc5e1 --- /dev/null +++ b/checkpoint-398/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b67db12a26a26ffe03d9afc84a43857eb2e5b2fec2dd189653b415f74208190 +size 15984 diff --git a/checkpoint-398/scheduler.pt b/checkpoint-398/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae9dbb6e7d56b745c094b2ffcd6d4982eb25729d --- /dev/null +++ b/checkpoint-398/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:354c6e1f0c1593c9a355bd337ec4d2e78152ff86359c50bd9c6c8af224e59dda +size 1064 diff --git a/checkpoint-398/special_tokens_map.json b/checkpoint-398/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-398/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-398/tokenizer.model b/checkpoint-398/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-398/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-398/tokenizer_config.json b/checkpoint-398/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-398/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-398/trainer_state.json b/checkpoint-398/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..280ea34c68d76d50fde9021afb66005941a56f12 --- /dev/null +++ b/checkpoint-398/trainer_state.json @@ -0,0 +1,2424 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.04173657718120805, + "eval_steps": 199, + "global_step": 398, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 1.780508923972603e+19, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-398/training_args.bin b/checkpoint-398/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-398/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-3980/config.json b/checkpoint-3980/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-3980/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-3980/generation_config.json b/checkpoint-3980/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-3980/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-3980/model-00001-of-00003.safetensors b/checkpoint-3980/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..36d0b9a08eb18b697fa9d7cfe77c31b4ebf1fa99 --- /dev/null +++ b/checkpoint-3980/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2597f1b83f2140fc11b34e23d30a1141f6afebbf3688aca04a1b06e41f20ba03 +size 4943162336 diff --git a/checkpoint-3980/model-00002-of-00003.safetensors b/checkpoint-3980/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2016100fcf1db7f1ccda6900266d00f9193f86ce --- /dev/null +++ b/checkpoint-3980/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:befe9720974650a437940699b28fb951c67264a9c6c80413844d6502a432087f +size 4999819336 diff --git a/checkpoint-3980/model-00003-of-00003.safetensors b/checkpoint-3980/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1e07e36093ce3d22e7dce505ec761917af7cb4ce --- /dev/null +++ b/checkpoint-3980/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9442e5aaa8fb1f7947fcfeba9c5a6c652706c2f6ff62541b18d555829b1fecb +size 4540516344 diff --git a/checkpoint-3980/model.safetensors.index.json b/checkpoint-3980/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-3980/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-3980/optimizer.pt b/checkpoint-3980/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..805c5ba34a5f9d1d9e718b3ba9c2db8dd43f2667 --- /dev/null +++ b/checkpoint-3980/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cd13982668b1b579fb12c10a91a74fbf891158e1e8202dc43b2a84bda59a547 +size 14512103560 diff --git a/checkpoint-3980/rng_state_0.pth b/checkpoint-3980/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..ff4e21da8ecaf3f1372449bbeb0e63a6d4cc958d --- /dev/null +++ b/checkpoint-3980/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e130d1863d00ae1dd3fcda6965ee955535fc41fccbf0e8e5180feeae82230859 +size 15984 diff --git a/checkpoint-3980/rng_state_1.pth b/checkpoint-3980/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..eebf396bd71b4986e6cdcffa4d6183b1da1023d9 --- /dev/null +++ b/checkpoint-3980/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38a0bd73f24f92e9f35076e28562a135316e508c049328542ef38455ec5d9e27 +size 15984 diff --git a/checkpoint-3980/rng_state_2.pth b/checkpoint-3980/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..f9c25be7d041b120f430a1d5891a66ac3fd86443 --- /dev/null +++ b/checkpoint-3980/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d61eb034a8cd4e97cff715cad1115d6f82a8d574822a796ff36bc37add8eb7c5 +size 15984 diff --git a/checkpoint-3980/rng_state_3.pth b/checkpoint-3980/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..22e426f3c7dcc1bad198da19f12db4dab9da9e74 --- /dev/null +++ b/checkpoint-3980/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9514ccff01a64d3814b885efa3d70c91036573ae2800e7f6e079eb57bb2c3a4 +size 15984 diff --git a/checkpoint-3980/rng_state_4.pth b/checkpoint-3980/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..13606cb32f3b2b110ff04ad6f689c04ad4955b17 --- /dev/null +++ b/checkpoint-3980/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e7809a9b06e7f3cd7bdaa78797c848d3852c6fa406da741fe8f6ca848b06788 +size 15984 diff --git a/checkpoint-3980/rng_state_5.pth b/checkpoint-3980/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..5652db63db0783003ff1812572377141feb8cf36 --- /dev/null +++ b/checkpoint-3980/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f279045fb5076c6bded286c635cef1a4ed4a9eb0b04fdbdf9d7f0d8d58002fe +size 15984 diff --git a/checkpoint-3980/rng_state_6.pth b/checkpoint-3980/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..5742a9a8a537338341a31508ba70fa7449c43183 --- /dev/null +++ b/checkpoint-3980/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25937bc8ad7c01f12ab5bbb4608d4476d51c9a1009b84fc9c92f223235e135ad +size 15984 diff --git a/checkpoint-3980/rng_state_7.pth b/checkpoint-3980/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..928070d6dcb1b303b290bd76159c96b47b92722b --- /dev/null +++ b/checkpoint-3980/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:683f3da1be97f6622bb41c0c819a35cc250ff0f8e5d0d0048c42366f7fc913e3 +size 15984 diff --git a/checkpoint-3980/scheduler.pt b/checkpoint-3980/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..db7f8d03ba647b6222b9588fbbc56e500d2204b4 --- /dev/null +++ b/checkpoint-3980/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a34b3fa5c3e8668385911117c030d01f09c0a16b98109f8a22c742bae99434b3 +size 1064 diff --git a/checkpoint-3980/special_tokens_map.json b/checkpoint-3980/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-3980/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-3980/tokenizer.model b/checkpoint-3980/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-3980/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-3980/tokenizer_config.json b/checkpoint-3980/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-3980/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-3980/trainer_state.json b/checkpoint-3980/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..b3a8c434e8be18022f1771613f98fc39050b6dc6 --- /dev/null +++ b/checkpoint-3980/trainer_state.json @@ -0,0 +1,24060 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.4173657718120805, + "eval_steps": 199, + "global_step": 3980, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + }, + { + "epoch": 0.21, + "learning_rate": 1.928689129323009e-05, + "loss": 1.421, + "step": 1991 + }, + { + "epoch": 0.21, + "learning_rate": 1.928553323396003e-05, + "loss": 1.5625, + "step": 1992 + }, + { + "epoch": 0.21, + "learning_rate": 1.92841739306671e-05, + "loss": 1.5198, + "step": 1993 + }, + { + "epoch": 0.21, + "learning_rate": 1.9282813383533415e-05, + "loss": 1.5116, + "step": 1994 + }, + { + "epoch": 0.21, + "learning_rate": 1.9281451592741247e-05, + "loss": 1.4306, + "step": 1995 + }, + { + "epoch": 0.21, + "learning_rate": 1.9280088558473046e-05, + "loss": 1.5425, + "step": 1996 + }, + { + "epoch": 0.21, + "learning_rate": 1.9278724280911424e-05, + "loss": 1.4972, + "step": 1997 + }, + { + "epoch": 0.21, + "learning_rate": 1.9277358760239156e-05, + "loss": 1.5185, + "step": 1998 + }, + { + "epoch": 0.21, + "learning_rate": 1.9275991996639188e-05, + "loss": 1.5187, + "step": 1999 + }, + { + "epoch": 0.21, + "learning_rate": 1.927462399029463e-05, + "loss": 1.4325, + "step": 2000 + }, + { + "epoch": 0.21, + "learning_rate": 1.9273254741388763e-05, + "loss": 1.4397, + "step": 2001 + }, + { + "epoch": 0.21, + "learning_rate": 1.927188425010503e-05, + "loss": 1.5319, + "step": 2002 + }, + { + "epoch": 0.21, + "learning_rate": 1.9270512516627042e-05, + "loss": 1.5664, + "step": 2003 + }, + { + "epoch": 0.21, + "learning_rate": 1.9269139541138574e-05, + "loss": 1.5227, + "step": 2004 + }, + { + "epoch": 0.21, + "learning_rate": 1.926776532382357e-05, + "loss": 1.5187, + "step": 2005 + }, + { + "epoch": 0.21, + "learning_rate": 1.9266389864866134e-05, + "loss": 1.4029, + "step": 2006 + }, + { + "epoch": 0.21, + "learning_rate": 1.9265013164450557e-05, + "loss": 1.387, + "step": 2007 + }, + { + "epoch": 0.21, + "learning_rate": 1.9263635222761268e-05, + "loss": 1.5047, + "step": 2008 + }, + { + "epoch": 0.21, + "learning_rate": 1.9262256039982882e-05, + "loss": 1.4816, + "step": 2009 + }, + { + "epoch": 0.21, + "learning_rate": 1.9260875616300172e-05, + "loss": 1.4607, + "step": 2010 + }, + { + "epoch": 0.21, + "learning_rate": 1.9259493951898084e-05, + "loss": 1.628, + "step": 2011 + }, + { + "epoch": 0.21, + "learning_rate": 1.9258111046961714e-05, + "loss": 1.4149, + "step": 2012 + }, + { + "epoch": 0.21, + "learning_rate": 1.925672690167635e-05, + "loss": 1.5303, + "step": 2013 + }, + { + "epoch": 0.21, + "learning_rate": 1.925534151622742e-05, + "loss": 1.5198, + "step": 2014 + }, + { + "epoch": 0.21, + "learning_rate": 1.9253954890800535e-05, + "loss": 1.6422, + "step": 2015 + }, + { + "epoch": 0.21, + "learning_rate": 1.925256702558147e-05, + "loss": 1.4738, + "step": 2016 + }, + { + "epoch": 0.21, + "learning_rate": 1.925117792075616e-05, + "loss": 1.4752, + "step": 2017 + }, + { + "epoch": 0.21, + "learning_rate": 1.9249787576510713e-05, + "loss": 1.4547, + "step": 2018 + }, + { + "epoch": 0.21, + "learning_rate": 1.924839599303139e-05, + "loss": 1.4864, + "step": 2019 + }, + { + "epoch": 0.21, + "learning_rate": 1.9247003170504638e-05, + "loss": 1.5037, + "step": 2020 + }, + { + "epoch": 0.21, + "learning_rate": 1.9245609109117053e-05, + "loss": 1.5089, + "step": 2021 + }, + { + "epoch": 0.21, + "learning_rate": 1.924421380905541e-05, + "loss": 1.5616, + "step": 2022 + }, + { + "epoch": 0.21, + "learning_rate": 1.9242817270506634e-05, + "loss": 1.4592, + "step": 2023 + }, + { + "epoch": 0.21, + "learning_rate": 1.9241419493657832e-05, + "loss": 1.5592, + "step": 2024 + }, + { + "epoch": 0.21, + "learning_rate": 1.924002047869627e-05, + "loss": 1.4897, + "step": 2025 + }, + { + "epoch": 0.21, + "learning_rate": 1.9238620225809375e-05, + "loss": 1.4743, + "step": 2026 + }, + { + "epoch": 0.21, + "learning_rate": 1.923721873518475e-05, + "loss": 1.4686, + "step": 2027 + }, + { + "epoch": 0.21, + "learning_rate": 1.923581600701016e-05, + "loss": 1.461, + "step": 2028 + }, + { + "epoch": 0.21, + "learning_rate": 1.9234412041473528e-05, + "loss": 1.6622, + "step": 2029 + }, + { + "epoch": 0.21, + "learning_rate": 1.9233006838762955e-05, + "loss": 1.4707, + "step": 2030 + }, + { + "epoch": 0.21, + "learning_rate": 1.92316003990667e-05, + "loss": 1.5566, + "step": 2031 + }, + { + "epoch": 0.21, + "learning_rate": 1.9230192722573188e-05, + "loss": 1.4881, + "step": 2032 + }, + { + "epoch": 0.21, + "learning_rate": 1.9228783809471015e-05, + "loss": 1.6124, + "step": 2033 + }, + { + "epoch": 0.21, + "learning_rate": 1.9227373659948937e-05, + "loss": 1.3508, + "step": 2034 + }, + { + "epoch": 0.21, + "learning_rate": 1.9225962274195876e-05, + "loss": 1.4418, + "step": 2035 + }, + { + "epoch": 0.21, + "learning_rate": 1.9224549652400927e-05, + "loss": 1.3954, + "step": 2036 + }, + { + "epoch": 0.21, + "learning_rate": 1.922313579475334e-05, + "loss": 1.4798, + "step": 2037 + }, + { + "epoch": 0.21, + "learning_rate": 1.922172070144254e-05, + "loss": 1.4556, + "step": 2038 + }, + { + "epoch": 0.21, + "learning_rate": 1.922030437265811e-05, + "loss": 1.4987, + "step": 2039 + }, + { + "epoch": 0.21, + "learning_rate": 1.9218886808589796e-05, + "loss": 1.4857, + "step": 2040 + }, + { + "epoch": 0.21, + "learning_rate": 1.9217468009427527e-05, + "loss": 1.5289, + "step": 2041 + }, + { + "epoch": 0.21, + "learning_rate": 1.921604797536138e-05, + "loss": 1.5267, + "step": 2042 + }, + { + "epoch": 0.21, + "learning_rate": 1.9214626706581598e-05, + "loss": 1.4655, + "step": 2043 + }, + { + "epoch": 0.21, + "learning_rate": 1.9213204203278602e-05, + "loss": 1.4598, + "step": 2044 + }, + { + "epoch": 0.21, + "learning_rate": 1.9211780465642973e-05, + "loss": 1.4766, + "step": 2045 + }, + { + "epoch": 0.21, + "learning_rate": 1.921035549386545e-05, + "loss": 1.5148, + "step": 2046 + }, + { + "epoch": 0.21, + "learning_rate": 1.9208929288136933e-05, + "loss": 1.5567, + "step": 2047 + }, + { + "epoch": 0.21, + "learning_rate": 1.920750184864852e-05, + "loss": 1.4868, + "step": 2048 + }, + { + "epoch": 0.21, + "learning_rate": 1.920607317559143e-05, + "loss": 1.4752, + "step": 2049 + }, + { + "epoch": 0.21, + "learning_rate": 1.920464326915708e-05, + "loss": 1.4882, + "step": 2050 + }, + { + "epoch": 0.22, + "learning_rate": 1.9203212129537035e-05, + "loss": 1.5933, + "step": 2051 + }, + { + "epoch": 0.22, + "learning_rate": 1.9201779756923037e-05, + "loss": 1.4891, + "step": 2052 + }, + { + "epoch": 0.22, + "learning_rate": 1.9200346151506983e-05, + "loss": 1.4486, + "step": 2053 + }, + { + "epoch": 0.22, + "learning_rate": 1.9198911313480938e-05, + "loss": 1.5091, + "step": 2054 + }, + { + "epoch": 0.22, + "learning_rate": 1.919747524303714e-05, + "loss": 1.4385, + "step": 2055 + }, + { + "epoch": 0.22, + "learning_rate": 1.9196037940367974e-05, + "loss": 1.4104, + "step": 2056 + }, + { + "epoch": 0.22, + "learning_rate": 1.9194599405666015e-05, + "loss": 1.4483, + "step": 2057 + }, + { + "epoch": 0.22, + "learning_rate": 1.9193159639123976e-05, + "loss": 1.4592, + "step": 2058 + }, + { + "epoch": 0.22, + "learning_rate": 1.919171864093476e-05, + "loss": 1.4975, + "step": 2059 + }, + { + "epoch": 0.22, + "learning_rate": 1.9190276411291423e-05, + "loss": 1.4727, + "step": 2060 + }, + { + "epoch": 0.22, + "learning_rate": 1.9188832950387178e-05, + "loss": 1.4791, + "step": 2061 + }, + { + "epoch": 0.22, + "learning_rate": 1.9187388258415423e-05, + "loss": 1.3806, + "step": 2062 + }, + { + "epoch": 0.22, + "learning_rate": 1.9185942335569697e-05, + "loss": 1.4514, + "step": 2063 + }, + { + "epoch": 0.22, + "learning_rate": 1.9184495182043727e-05, + "loss": 1.4389, + "step": 2064 + }, + { + "epoch": 0.22, + "learning_rate": 1.918304679803139e-05, + "loss": 1.5088, + "step": 2065 + }, + { + "epoch": 0.22, + "learning_rate": 1.9181597183726733e-05, + "loss": 1.4665, + "step": 2066 + }, + { + "epoch": 0.22, + "learning_rate": 1.9180146339323966e-05, + "loss": 1.489, + "step": 2067 + }, + { + "epoch": 0.22, + "learning_rate": 1.9178694265017466e-05, + "loss": 1.5215, + "step": 2068 + }, + { + "epoch": 0.22, + "learning_rate": 1.9177240961001775e-05, + "loss": 1.5152, + "step": 2069 + }, + { + "epoch": 0.22, + "learning_rate": 1.9175786427471594e-05, + "loss": 1.4418, + "step": 2070 + }, + { + "epoch": 0.22, + "learning_rate": 1.91743306646218e-05, + "loss": 1.5001, + "step": 2071 + }, + { + "epoch": 0.22, + "learning_rate": 1.9172873672647417e-05, + "loss": 1.4879, + "step": 2072 + }, + { + "epoch": 0.22, + "learning_rate": 1.917141545174366e-05, + "loss": 1.5299, + "step": 2073 + }, + { + "epoch": 0.22, + "learning_rate": 1.9169956002105877e-05, + "loss": 1.4602, + "step": 2074 + }, + { + "epoch": 0.22, + "learning_rate": 1.9168495323929605e-05, + "loss": 1.4921, + "step": 2075 + }, + { + "epoch": 0.22, + "learning_rate": 1.916703341741054e-05, + "loss": 1.4659, + "step": 2076 + }, + { + "epoch": 0.22, + "learning_rate": 1.9165570282744534e-05, + "loss": 1.4707, + "step": 2077 + }, + { + "epoch": 0.22, + "learning_rate": 1.9164105920127613e-05, + "loss": 1.5354, + "step": 2078 + }, + { + "epoch": 0.22, + "learning_rate": 1.9162640329755962e-05, + "loss": 1.526, + "step": 2079 + }, + { + "epoch": 0.22, + "learning_rate": 1.916117351182593e-05, + "loss": 1.6424, + "step": 2080 + }, + { + "epoch": 0.22, + "learning_rate": 1.915970546653404e-05, + "loss": 1.5048, + "step": 2081 + }, + { + "epoch": 0.22, + "learning_rate": 1.915823619407697e-05, + "loss": 1.5344, + "step": 2082 + }, + { + "epoch": 0.22, + "learning_rate": 1.915676569465156e-05, + "loss": 1.4604, + "step": 2083 + }, + { + "epoch": 0.22, + "learning_rate": 1.9155293968454826e-05, + "loss": 1.4929, + "step": 2084 + }, + { + "epoch": 0.22, + "learning_rate": 1.9153821015683937e-05, + "loss": 1.4106, + "step": 2085 + }, + { + "epoch": 0.22, + "learning_rate": 1.915234683653623e-05, + "loss": 1.4146, + "step": 2086 + }, + { + "epoch": 0.22, + "learning_rate": 1.9150871431209207e-05, + "loss": 1.4481, + "step": 2087 + }, + { + "epoch": 0.22, + "learning_rate": 1.914939479990054e-05, + "loss": 1.5206, + "step": 2088 + }, + { + "epoch": 0.22, + "learning_rate": 1.9147916942808054e-05, + "loss": 1.5073, + "step": 2089 + }, + { + "epoch": 0.22, + "learning_rate": 1.9146437860129745e-05, + "loss": 1.5196, + "step": 2090 + }, + { + "epoch": 0.22, + "learning_rate": 1.9144957552063775e-05, + "loss": 1.5389, + "step": 2091 + }, + { + "epoch": 0.22, + "learning_rate": 1.9143476018808463e-05, + "loss": 1.5207, + "step": 2092 + }, + { + "epoch": 0.22, + "learning_rate": 1.9141993260562298e-05, + "loss": 1.3717, + "step": 2093 + }, + { + "epoch": 0.22, + "learning_rate": 1.9140509277523937e-05, + "loss": 1.471, + "step": 2094 + }, + { + "epoch": 0.22, + "learning_rate": 1.9139024069892185e-05, + "loss": 1.4553, + "step": 2095 + }, + { + "epoch": 0.22, + "learning_rate": 1.9137537637866027e-05, + "loss": 1.5311, + "step": 2096 + }, + { + "epoch": 0.22, + "learning_rate": 1.9136049981644614e-05, + "loss": 1.4369, + "step": 2097 + }, + { + "epoch": 0.22, + "learning_rate": 1.913456110142724e-05, + "loss": 1.4528, + "step": 2098 + }, + { + "epoch": 0.22, + "learning_rate": 1.9133070997413384e-05, + "loss": 1.5294, + "step": 2099 + }, + { + "epoch": 0.22, + "learning_rate": 1.9131579669802685e-05, + "loss": 1.4588, + "step": 2100 + }, + { + "epoch": 0.22, + "learning_rate": 1.9130087118794934e-05, + "loss": 1.443, + "step": 2101 + }, + { + "epoch": 0.22, + "learning_rate": 1.9128593344590102e-05, + "loss": 1.4876, + "step": 2102 + }, + { + "epoch": 0.22, + "learning_rate": 1.912709834738831e-05, + "loss": 1.4874, + "step": 2103 + }, + { + "epoch": 0.22, + "learning_rate": 1.9125602127389856e-05, + "loss": 1.4966, + "step": 2104 + }, + { + "epoch": 0.22, + "learning_rate": 1.912410468479519e-05, + "loss": 1.5747, + "step": 2105 + }, + { + "epoch": 0.22, + "learning_rate": 1.9122606019804933e-05, + "loss": 1.4025, + "step": 2106 + }, + { + "epoch": 0.22, + "learning_rate": 1.912110613261987e-05, + "loss": 1.4755, + "step": 2107 + }, + { + "epoch": 0.22, + "learning_rate": 1.911960502344094e-05, + "loss": 1.4739, + "step": 2108 + }, + { + "epoch": 0.22, + "learning_rate": 1.911810269246926e-05, + "loss": 1.4992, + "step": 2109 + }, + { + "epoch": 0.22, + "learning_rate": 1.91165991399061e-05, + "loss": 1.4435, + "step": 2110 + }, + { + "epoch": 0.22, + "learning_rate": 1.91150943659529e-05, + "loss": 1.4918, + "step": 2111 + }, + { + "epoch": 0.22, + "learning_rate": 1.9113588370811258e-05, + "loss": 1.3818, + "step": 2112 + }, + { + "epoch": 0.22, + "learning_rate": 1.911208115468294e-05, + "loss": 1.5105, + "step": 2113 + }, + { + "epoch": 0.22, + "learning_rate": 1.9110572717769878e-05, + "loss": 1.6634, + "step": 2114 + }, + { + "epoch": 0.22, + "learning_rate": 1.9109063060274158e-05, + "loss": 1.5028, + "step": 2115 + }, + { + "epoch": 0.22, + "learning_rate": 1.9107552182398037e-05, + "loss": 1.6657, + "step": 2116 + }, + { + "epoch": 0.22, + "learning_rate": 1.9106040084343935e-05, + "loss": 1.5481, + "step": 2117 + }, + { + "epoch": 0.22, + "learning_rate": 1.910452676631444e-05, + "loss": 1.4505, + "step": 2118 + }, + { + "epoch": 0.22, + "learning_rate": 1.9103012228512284e-05, + "loss": 1.5173, + "step": 2119 + }, + { + "epoch": 0.22, + "learning_rate": 1.9101496471140385e-05, + "loss": 1.3788, + "step": 2120 + }, + { + "epoch": 0.22, + "learning_rate": 1.9099979494401814e-05, + "loss": 1.4649, + "step": 2121 + }, + { + "epoch": 0.22, + "learning_rate": 1.9098461298499805e-05, + "loss": 1.4204, + "step": 2122 + }, + { + "epoch": 0.22, + "learning_rate": 1.9096941883637766e-05, + "loss": 1.4439, + "step": 2123 + }, + { + "epoch": 0.22, + "learning_rate": 1.909542125001925e-05, + "loss": 1.6615, + "step": 2124 + }, + { + "epoch": 0.22, + "learning_rate": 1.9093899397847985e-05, + "loss": 1.4763, + "step": 2125 + }, + { + "epoch": 0.22, + "learning_rate": 1.909237632732786e-05, + "loss": 1.5353, + "step": 2126 + }, + { + "epoch": 0.22, + "learning_rate": 1.909085203866293e-05, + "loss": 1.442, + "step": 2127 + }, + { + "epoch": 0.22, + "learning_rate": 1.9089326532057408e-05, + "loss": 1.4782, + "step": 2128 + }, + { + "epoch": 0.22, + "learning_rate": 1.908779980771567e-05, + "loss": 1.4933, + "step": 2129 + }, + { + "epoch": 0.22, + "learning_rate": 1.9086271865842264e-05, + "loss": 1.5285, + "step": 2130 + }, + { + "epoch": 0.22, + "learning_rate": 1.9084742706641894e-05, + "loss": 1.4736, + "step": 2131 + }, + { + "epoch": 0.22, + "learning_rate": 1.9083212330319427e-05, + "loss": 1.4496, + "step": 2132 + }, + { + "epoch": 0.22, + "learning_rate": 1.908168073707989e-05, + "loss": 1.5099, + "step": 2133 + }, + { + "epoch": 0.22, + "learning_rate": 1.9080147927128483e-05, + "loss": 1.5235, + "step": 2134 + }, + { + "epoch": 0.22, + "learning_rate": 1.9078613900670556e-05, + "loss": 1.4769, + "step": 2135 + }, + { + "epoch": 0.22, + "learning_rate": 1.907707865791164e-05, + "loss": 1.5771, + "step": 2136 + }, + { + "epoch": 0.22, + "learning_rate": 1.907554219905741e-05, + "loss": 1.5116, + "step": 2137 + }, + { + "epoch": 0.22, + "learning_rate": 1.907400452431371e-05, + "loss": 1.5161, + "step": 2138 + }, + { + "epoch": 0.22, + "learning_rate": 1.9072465633886557e-05, + "loss": 1.4356, + "step": 2139 + }, + { + "epoch": 0.22, + "learning_rate": 1.9070925527982117e-05, + "loss": 1.509, + "step": 2140 + }, + { + "epoch": 0.22, + "learning_rate": 1.9069384206806723e-05, + "loss": 1.4681, + "step": 2141 + }, + { + "epoch": 0.22, + "learning_rate": 1.9067841670566883e-05, + "loss": 1.5254, + "step": 2142 + }, + { + "epoch": 0.22, + "learning_rate": 1.9066297919469242e-05, + "loss": 1.4797, + "step": 2143 + }, + { + "epoch": 0.22, + "learning_rate": 1.9064752953720636e-05, + "loss": 1.3996, + "step": 2144 + }, + { + "epoch": 0.22, + "learning_rate": 1.9063206773528042e-05, + "loss": 1.4457, + "step": 2145 + }, + { + "epoch": 0.23, + "learning_rate": 1.9061659379098617e-05, + "loss": 1.5126, + "step": 2146 + }, + { + "epoch": 0.23, + "learning_rate": 1.9060110770639664e-05, + "loss": 1.5925, + "step": 2147 + }, + { + "epoch": 0.23, + "learning_rate": 1.905856094835866e-05, + "loss": 1.5146, + "step": 2148 + }, + { + "epoch": 0.23, + "learning_rate": 1.905700991246324e-05, + "loss": 1.7256, + "step": 2149 + }, + { + "epoch": 0.23, + "learning_rate": 1.90554576631612e-05, + "loss": 1.57, + "step": 2150 + }, + { + "epoch": 0.23, + "learning_rate": 1.905390420066051e-05, + "loss": 1.3722, + "step": 2151 + }, + { + "epoch": 0.23, + "learning_rate": 1.9052349525169292e-05, + "loss": 1.3999, + "step": 2152 + }, + { + "epoch": 0.23, + "learning_rate": 1.9050793636895828e-05, + "loss": 1.586, + "step": 2153 + }, + { + "epoch": 0.23, + "learning_rate": 1.9049236536048567e-05, + "loss": 1.4884, + "step": 2154 + }, + { + "epoch": 0.23, + "learning_rate": 1.9047678222836127e-05, + "loss": 1.5898, + "step": 2155 + }, + { + "epoch": 0.23, + "learning_rate": 1.9046118697467278e-05, + "loss": 1.569, + "step": 2156 + }, + { + "epoch": 0.23, + "learning_rate": 1.904455796015095e-05, + "loss": 1.5592, + "step": 2157 + }, + { + "epoch": 0.23, + "learning_rate": 1.9042996011096253e-05, + "loss": 1.597, + "step": 2158 + }, + { + "epoch": 0.23, + "learning_rate": 1.904143285051244e-05, + "loss": 1.422, + "step": 2159 + }, + { + "epoch": 0.23, + "learning_rate": 1.903986847860894e-05, + "loss": 1.519, + "step": 2160 + }, + { + "epoch": 0.23, + "learning_rate": 1.9038302895595334e-05, + "loss": 1.5197, + "step": 2161 + }, + { + "epoch": 0.23, + "learning_rate": 1.903673610168137e-05, + "loss": 1.4655, + "step": 2162 + }, + { + "epoch": 0.23, + "learning_rate": 1.9035168097076965e-05, + "loss": 1.3909, + "step": 2163 + }, + { + "epoch": 0.23, + "learning_rate": 1.903359888199218e-05, + "loss": 1.4877, + "step": 2164 + }, + { + "epoch": 0.23, + "learning_rate": 1.903202845663726e-05, + "loss": 1.5123, + "step": 2165 + }, + { + "epoch": 0.23, + "learning_rate": 1.9030456821222593e-05, + "loss": 1.4906, + "step": 2166 + }, + { + "epoch": 0.23, + "learning_rate": 1.9028883975958745e-05, + "loss": 1.4574, + "step": 2167 + }, + { + "epoch": 0.23, + "learning_rate": 1.9027309921056435e-05, + "loss": 1.4571, + "step": 2168 + }, + { + "epoch": 0.23, + "learning_rate": 1.902573465672654e-05, + "loss": 1.4281, + "step": 2169 + }, + { + "epoch": 0.23, + "learning_rate": 1.9024158183180116e-05, + "loss": 1.5057, + "step": 2170 + }, + { + "epoch": 0.23, + "learning_rate": 1.902258050062836e-05, + "loss": 1.4514, + "step": 2171 + }, + { + "epoch": 0.23, + "learning_rate": 1.9021001609282646e-05, + "loss": 1.5055, + "step": 2172 + }, + { + "epoch": 0.23, + "learning_rate": 1.9019421509354505e-05, + "loss": 1.4578, + "step": 2173 + }, + { + "epoch": 0.23, + "learning_rate": 1.9017840201055625e-05, + "loss": 1.459, + "step": 2174 + }, + { + "epoch": 0.23, + "learning_rate": 1.9016257684597864e-05, + "loss": 1.5059, + "step": 2175 + }, + { + "epoch": 0.23, + "learning_rate": 1.901467396019324e-05, + "loss": 1.57, + "step": 2176 + }, + { + "epoch": 0.23, + "learning_rate": 1.901308902805393e-05, + "loss": 1.4924, + "step": 2177 + }, + { + "epoch": 0.23, + "learning_rate": 1.9011502888392273e-05, + "loss": 1.4979, + "step": 2178 + }, + { + "epoch": 0.23, + "learning_rate": 1.900991554142077e-05, + "loss": 1.5321, + "step": 2179 + }, + { + "epoch": 0.23, + "learning_rate": 1.9008326987352093e-05, + "loss": 1.493, + "step": 2180 + }, + { + "epoch": 0.23, + "learning_rate": 1.9006737226399056e-05, + "loss": 1.5111, + "step": 2181 + }, + { + "epoch": 0.23, + "learning_rate": 1.900514625877465e-05, + "loss": 1.4154, + "step": 2182 + }, + { + "epoch": 0.23, + "learning_rate": 1.900355408469203e-05, + "loss": 1.4934, + "step": 2183 + }, + { + "epoch": 0.23, + "learning_rate": 1.90019607043645e-05, + "loss": 1.5975, + "step": 2184 + }, + { + "epoch": 0.23, + "learning_rate": 1.9000366118005532e-05, + "loss": 1.3537, + "step": 2185 + }, + { + "epoch": 0.23, + "learning_rate": 1.899877032582876e-05, + "loss": 1.4583, + "step": 2186 + }, + { + "epoch": 0.23, + "learning_rate": 1.8997173328047984e-05, + "loss": 1.4586, + "step": 2187 + }, + { + "epoch": 0.23, + "learning_rate": 1.8995575124877156e-05, + "loss": 1.4774, + "step": 2188 + }, + { + "epoch": 0.23, + "learning_rate": 1.8993975716530394e-05, + "loss": 1.5025, + "step": 2189 + }, + { + "epoch": 0.23, + "eval_loss": 1.5263344049453735, + "eval_runtime": 77.1492, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 2189 + }, + { + "epoch": 0.23, + "learning_rate": 1.899237510322198e-05, + "loss": 1.5438, + "step": 2190 + }, + { + "epoch": 0.23, + "learning_rate": 1.899077328516635e-05, + "loss": 1.5181, + "step": 2191 + }, + { + "epoch": 0.23, + "learning_rate": 1.8989170262578112e-05, + "loss": 1.4454, + "step": 2192 + }, + { + "epoch": 0.23, + "learning_rate": 1.8987566035672028e-05, + "loss": 1.4882, + "step": 2193 + }, + { + "epoch": 0.23, + "learning_rate": 1.8985960604663026e-05, + "loss": 1.5073, + "step": 2194 + }, + { + "epoch": 0.23, + "learning_rate": 1.8984353969766187e-05, + "loss": 1.4478, + "step": 2195 + }, + { + "epoch": 0.23, + "learning_rate": 1.8982746131196763e-05, + "loss": 1.4768, + "step": 2196 + }, + { + "epoch": 0.23, + "learning_rate": 1.8981137089170162e-05, + "loss": 1.5116, + "step": 2197 + }, + { + "epoch": 0.23, + "learning_rate": 1.8979526843901952e-05, + "loss": 1.4202, + "step": 2198 + }, + { + "epoch": 0.23, + "learning_rate": 1.8977915395607867e-05, + "loss": 1.4736, + "step": 2199 + }, + { + "epoch": 0.23, + "learning_rate": 1.89763027445038e-05, + "loss": 1.4489, + "step": 2200 + }, + { + "epoch": 0.23, + "learning_rate": 1.8974688890805804e-05, + "loss": 1.4512, + "step": 2201 + }, + { + "epoch": 0.23, + "learning_rate": 1.897307383473009e-05, + "loss": 1.5091, + "step": 2202 + }, + { + "epoch": 0.23, + "learning_rate": 1.897145757649304e-05, + "loss": 1.5512, + "step": 2203 + }, + { + "epoch": 0.23, + "learning_rate": 1.8969840116311192e-05, + "loss": 1.406, + "step": 2204 + }, + { + "epoch": 0.23, + "learning_rate": 1.896822145440124e-05, + "loss": 1.4531, + "step": 2205 + }, + { + "epoch": 0.23, + "learning_rate": 1.896660159098004e-05, + "loss": 1.4379, + "step": 2206 + }, + { + "epoch": 0.23, + "learning_rate": 1.896498052626462e-05, + "loss": 1.4783, + "step": 2207 + }, + { + "epoch": 0.23, + "learning_rate": 1.896335826047216e-05, + "loss": 1.4801, + "step": 2208 + }, + { + "epoch": 0.23, + "learning_rate": 1.896173479381999e-05, + "loss": 1.4526, + "step": 2209 + }, + { + "epoch": 0.23, + "learning_rate": 1.8960110126525627e-05, + "loss": 1.4952, + "step": 2210 + }, + { + "epoch": 0.23, + "learning_rate": 1.895848425880673e-05, + "loss": 1.5299, + "step": 2211 + }, + { + "epoch": 0.23, + "learning_rate": 1.8956857190881125e-05, + "loss": 1.5274, + "step": 2212 + }, + { + "epoch": 0.23, + "learning_rate": 1.8955228922966792e-05, + "loss": 1.4415, + "step": 2213 + }, + { + "epoch": 0.23, + "learning_rate": 1.8953599455281884e-05, + "loss": 1.5311, + "step": 2214 + }, + { + "epoch": 0.23, + "learning_rate": 1.8951968788044702e-05, + "loss": 1.4972, + "step": 2215 + }, + { + "epoch": 0.23, + "learning_rate": 1.8950336921473715e-05, + "loss": 1.4966, + "step": 2216 + }, + { + "epoch": 0.23, + "learning_rate": 1.8948703855787553e-05, + "loss": 1.4683, + "step": 2217 + }, + { + "epoch": 0.23, + "learning_rate": 1.8947069591205005e-05, + "loss": 1.503, + "step": 2218 + }, + { + "epoch": 0.23, + "learning_rate": 1.8945434127945014e-05, + "loss": 1.4902, + "step": 2219 + }, + { + "epoch": 0.23, + "learning_rate": 1.8943797466226702e-05, + "loss": 1.4835, + "step": 2220 + }, + { + "epoch": 0.23, + "learning_rate": 1.8942159606269332e-05, + "loss": 1.535, + "step": 2221 + }, + { + "epoch": 0.23, + "learning_rate": 1.8940520548292332e-05, + "loss": 1.491, + "step": 2222 + }, + { + "epoch": 0.23, + "learning_rate": 1.89388802925153e-05, + "loss": 1.5157, + "step": 2223 + }, + { + "epoch": 0.23, + "learning_rate": 1.8937238839157987e-05, + "loss": 1.4779, + "step": 2224 + }, + { + "epoch": 0.23, + "learning_rate": 1.8935596188440302e-05, + "loss": 1.4902, + "step": 2225 + }, + { + "epoch": 0.23, + "learning_rate": 1.8933952340582323e-05, + "loss": 1.4988, + "step": 2226 + }, + { + "epoch": 0.23, + "learning_rate": 1.893230729580428e-05, + "loss": 1.4568, + "step": 2227 + }, + { + "epoch": 0.23, + "learning_rate": 1.8930661054326567e-05, + "loss": 1.5163, + "step": 2228 + }, + { + "epoch": 0.23, + "learning_rate": 1.892901361636974e-05, + "loss": 1.4472, + "step": 2229 + }, + { + "epoch": 0.23, + "learning_rate": 1.892736498215451e-05, + "loss": 1.4658, + "step": 2230 + }, + { + "epoch": 0.23, + "learning_rate": 1.8925715151901754e-05, + "loss": 1.4281, + "step": 2231 + }, + { + "epoch": 0.23, + "learning_rate": 1.892406412583251e-05, + "loss": 1.415, + "step": 2232 + }, + { + "epoch": 0.23, + "learning_rate": 1.8922411904167966e-05, + "loss": 1.464, + "step": 2233 + }, + { + "epoch": 0.23, + "learning_rate": 1.892075848712948e-05, + "loss": 1.5014, + "step": 2234 + }, + { + "epoch": 0.23, + "learning_rate": 1.8919103874938568e-05, + "loss": 1.4397, + "step": 2235 + }, + { + "epoch": 0.23, + "learning_rate": 1.891744806781691e-05, + "loss": 1.5508, + "step": 2236 + }, + { + "epoch": 0.23, + "learning_rate": 1.8915791065986335e-05, + "loss": 1.4749, + "step": 2237 + }, + { + "epoch": 0.23, + "learning_rate": 1.891413286966884e-05, + "loss": 1.4538, + "step": 2238 + }, + { + "epoch": 0.23, + "learning_rate": 1.891247347908658e-05, + "loss": 1.4405, + "step": 2239 + }, + { + "epoch": 0.23, + "learning_rate": 1.8910812894461878e-05, + "loss": 1.3562, + "step": 2240 + }, + { + "epoch": 0.24, + "learning_rate": 1.89091511160172e-05, + "loss": 1.4811, + "step": 2241 + }, + { + "epoch": 0.24, + "learning_rate": 1.8907488143975186e-05, + "loss": 1.4286, + "step": 2242 + }, + { + "epoch": 0.24, + "learning_rate": 1.890582397855863e-05, + "loss": 1.4493, + "step": 2243 + }, + { + "epoch": 0.24, + "learning_rate": 1.890415861999049e-05, + "loss": 1.5639, + "step": 2244 + }, + { + "epoch": 0.24, + "learning_rate": 1.890249206849388e-05, + "loss": 1.6375, + "step": 2245 + }, + { + "epoch": 0.24, + "learning_rate": 1.890082432429208e-05, + "loss": 1.4982, + "step": 2246 + }, + { + "epoch": 0.24, + "learning_rate": 1.889915538760851e-05, + "loss": 1.492, + "step": 2247 + }, + { + "epoch": 0.24, + "learning_rate": 1.8897485258666778e-05, + "loss": 1.4294, + "step": 2248 + }, + { + "epoch": 0.24, + "learning_rate": 1.8895813937690638e-05, + "loss": 1.4617, + "step": 2249 + }, + { + "epoch": 0.24, + "learning_rate": 1.8894141424904e-05, + "loss": 1.4763, + "step": 2250 + }, + { + "epoch": 0.24, + "learning_rate": 1.8892467720530937e-05, + "loss": 1.3989, + "step": 2251 + }, + { + "epoch": 0.24, + "learning_rate": 1.8890792824795687e-05, + "loss": 1.4803, + "step": 2252 + }, + { + "epoch": 0.24, + "learning_rate": 1.8889116737922638e-05, + "loss": 1.4734, + "step": 2253 + }, + { + "epoch": 0.24, + "learning_rate": 1.8887439460136342e-05, + "loss": 1.5069, + "step": 2254 + }, + { + "epoch": 0.24, + "learning_rate": 1.8885760991661514e-05, + "loss": 1.5565, + "step": 2255 + }, + { + "epoch": 0.24, + "learning_rate": 1.8884081332723028e-05, + "loss": 1.4707, + "step": 2256 + }, + { + "epoch": 0.24, + "learning_rate": 1.8882400483545913e-05, + "loss": 1.5077, + "step": 2257 + }, + { + "epoch": 0.24, + "learning_rate": 1.888071844435536e-05, + "loss": 1.5075, + "step": 2258 + }, + { + "epoch": 0.24, + "learning_rate": 1.8879035215376717e-05, + "loss": 1.5185, + "step": 2259 + }, + { + "epoch": 0.24, + "learning_rate": 1.887735079683549e-05, + "loss": 1.6266, + "step": 2260 + }, + { + "epoch": 0.24, + "learning_rate": 1.8875665188957354e-05, + "loss": 1.5013, + "step": 2261 + }, + { + "epoch": 0.24, + "learning_rate": 1.887397839196814e-05, + "loss": 1.4362, + "step": 2262 + }, + { + "epoch": 0.24, + "learning_rate": 1.8872290406093827e-05, + "loss": 1.4718, + "step": 2263 + }, + { + "epoch": 0.24, + "learning_rate": 1.8870601231560567e-05, + "loss": 1.5202, + "step": 2264 + }, + { + "epoch": 0.24, + "learning_rate": 1.8868910868594664e-05, + "loss": 1.5168, + "step": 2265 + }, + { + "epoch": 0.24, + "learning_rate": 1.8867219317422588e-05, + "loss": 1.5142, + "step": 2266 + }, + { + "epoch": 0.24, + "learning_rate": 1.8865526578270954e-05, + "loss": 1.4885, + "step": 2267 + }, + { + "epoch": 0.24, + "learning_rate": 1.8863832651366552e-05, + "loss": 1.5441, + "step": 2268 + }, + { + "epoch": 0.24, + "learning_rate": 1.8862137536936328e-05, + "loss": 1.4647, + "step": 2269 + }, + { + "epoch": 0.24, + "learning_rate": 1.8860441235207374e-05, + "loss": 1.5352, + "step": 2270 + }, + { + "epoch": 0.24, + "learning_rate": 1.8858743746406958e-05, + "loss": 1.4568, + "step": 2271 + }, + { + "epoch": 0.24, + "learning_rate": 1.8857045070762497e-05, + "loss": 1.4865, + "step": 2272 + }, + { + "epoch": 0.24, + "learning_rate": 1.8855345208501573e-05, + "loss": 1.4637, + "step": 2273 + }, + { + "epoch": 0.24, + "learning_rate": 1.8853644159851918e-05, + "loss": 1.4348, + "step": 2274 + }, + { + "epoch": 0.24, + "learning_rate": 1.8851941925041436e-05, + "loss": 1.4413, + "step": 2275 + }, + { + "epoch": 0.24, + "learning_rate": 1.8850238504298177e-05, + "loss": 1.4434, + "step": 2276 + }, + { + "epoch": 0.24, + "learning_rate": 1.884853389785036e-05, + "loss": 1.4822, + "step": 2277 + }, + { + "epoch": 0.24, + "learning_rate": 1.8846828105926356e-05, + "loss": 1.4632, + "step": 2278 + }, + { + "epoch": 0.24, + "learning_rate": 1.8845121128754698e-05, + "loss": 1.48, + "step": 2279 + }, + { + "epoch": 0.24, + "learning_rate": 1.8843412966564078e-05, + "loss": 1.4518, + "step": 2280 + }, + { + "epoch": 0.24, + "learning_rate": 1.884170361958334e-05, + "loss": 1.4334, + "step": 2281 + }, + { + "epoch": 0.24, + "learning_rate": 1.8839993088041502e-05, + "loss": 1.5131, + "step": 2282 + }, + { + "epoch": 0.24, + "learning_rate": 1.8838281372167724e-05, + "loss": 1.508, + "step": 2283 + }, + { + "epoch": 0.24, + "learning_rate": 1.8836568472191335e-05, + "loss": 1.4086, + "step": 2284 + }, + { + "epoch": 0.24, + "learning_rate": 1.883485438834182e-05, + "loss": 1.5021, + "step": 2285 + }, + { + "epoch": 0.24, + "learning_rate": 1.8833139120848817e-05, + "loss": 1.5083, + "step": 2286 + }, + { + "epoch": 0.24, + "learning_rate": 1.8831422669942137e-05, + "loss": 1.4162, + "step": 2287 + }, + { + "epoch": 0.24, + "learning_rate": 1.8829705035851734e-05, + "loss": 1.5494, + "step": 2288 + }, + { + "epoch": 0.24, + "learning_rate": 1.8827986218807724e-05, + "loss": 1.425, + "step": 2289 + }, + { + "epoch": 0.24, + "learning_rate": 1.8826266219040396e-05, + "loss": 1.5215, + "step": 2290 + }, + { + "epoch": 0.24, + "learning_rate": 1.8824545036780172e-05, + "loss": 1.5577, + "step": 2291 + }, + { + "epoch": 0.24, + "learning_rate": 1.8822822672257655e-05, + "loss": 1.4923, + "step": 2292 + }, + { + "epoch": 0.24, + "learning_rate": 1.8821099125703595e-05, + "loss": 1.4648, + "step": 2293 + }, + { + "epoch": 0.24, + "learning_rate": 1.8819374397348902e-05, + "loss": 1.471, + "step": 2294 + }, + { + "epoch": 0.24, + "learning_rate": 1.8817648487424648e-05, + "loss": 1.5658, + "step": 2295 + }, + { + "epoch": 0.24, + "learning_rate": 1.8815921396162058e-05, + "loss": 1.5348, + "step": 2296 + }, + { + "epoch": 0.24, + "learning_rate": 1.8814193123792518e-05, + "loss": 1.4081, + "step": 2297 + }, + { + "epoch": 0.24, + "learning_rate": 1.881246367054757e-05, + "loss": 1.4762, + "step": 2298 + }, + { + "epoch": 0.24, + "learning_rate": 1.8810733036658925e-05, + "loss": 1.4399, + "step": 2299 + }, + { + "epoch": 0.24, + "learning_rate": 1.8809001222358432e-05, + "loss": 1.4763, + "step": 2300 + }, + { + "epoch": 0.24, + "learning_rate": 1.880726822787812e-05, + "loss": 1.4874, + "step": 2301 + }, + { + "epoch": 0.24, + "learning_rate": 1.880553405345016e-05, + "loss": 1.4951, + "step": 2302 + }, + { + "epoch": 0.24, + "learning_rate": 1.8803798699306887e-05, + "loss": 1.4697, + "step": 2303 + }, + { + "epoch": 0.24, + "learning_rate": 1.880206216568079e-05, + "loss": 1.481, + "step": 2304 + }, + { + "epoch": 0.24, + "learning_rate": 1.880032445280453e-05, + "loss": 1.4485, + "step": 2305 + }, + { + "epoch": 0.24, + "learning_rate": 1.879858556091091e-05, + "loss": 1.4749, + "step": 2306 + }, + { + "epoch": 0.24, + "learning_rate": 1.8796845490232894e-05, + "loss": 1.5605, + "step": 2307 + }, + { + "epoch": 0.24, + "learning_rate": 1.879510424100361e-05, + "loss": 1.4835, + "step": 2308 + }, + { + "epoch": 0.24, + "learning_rate": 1.8793361813456346e-05, + "loss": 1.4344, + "step": 2309 + }, + { + "epoch": 0.24, + "learning_rate": 1.8791618207824532e-05, + "loss": 1.4571, + "step": 2310 + }, + { + "epoch": 0.24, + "learning_rate": 1.8789873424341772e-05, + "loss": 1.482, + "step": 2311 + }, + { + "epoch": 0.24, + "learning_rate": 1.8788127463241822e-05, + "loss": 1.4736, + "step": 2312 + }, + { + "epoch": 0.24, + "learning_rate": 1.8786380324758597e-05, + "loss": 1.4807, + "step": 2313 + }, + { + "epoch": 0.24, + "learning_rate": 1.8784632009126167e-05, + "loss": 1.4418, + "step": 2314 + }, + { + "epoch": 0.24, + "learning_rate": 1.878288251657876e-05, + "loss": 1.5248, + "step": 2315 + }, + { + "epoch": 0.24, + "learning_rate": 1.8781131847350768e-05, + "loss": 1.483, + "step": 2316 + }, + { + "epoch": 0.24, + "learning_rate": 1.877938000167673e-05, + "loss": 1.5474, + "step": 2317 + }, + { + "epoch": 0.24, + "learning_rate": 1.8777626979791347e-05, + "loss": 1.4671, + "step": 2318 + }, + { + "epoch": 0.24, + "learning_rate": 1.877587278192949e-05, + "loss": 1.3049, + "step": 2319 + }, + { + "epoch": 0.24, + "learning_rate": 1.877411740832616e-05, + "loss": 1.483, + "step": 2320 + }, + { + "epoch": 0.24, + "learning_rate": 1.877236085921655e-05, + "loss": 1.508, + "step": 2321 + }, + { + "epoch": 0.24, + "learning_rate": 1.8770603134835978e-05, + "loss": 1.4854, + "step": 2322 + }, + { + "epoch": 0.24, + "learning_rate": 1.8768844235419942e-05, + "loss": 1.4808, + "step": 2323 + }, + { + "epoch": 0.24, + "learning_rate": 1.8767084161204087e-05, + "loss": 1.5352, + "step": 2324 + }, + { + "epoch": 0.24, + "learning_rate": 1.8765322912424214e-05, + "loss": 1.5628, + "step": 2325 + }, + { + "epoch": 0.24, + "learning_rate": 1.8763560489316292e-05, + "loss": 1.494, + "step": 2326 + }, + { + "epoch": 0.24, + "learning_rate": 1.876179689211643e-05, + "loss": 1.509, + "step": 2327 + }, + { + "epoch": 0.24, + "learning_rate": 1.8760032121060918e-05, + "loss": 1.5021, + "step": 2328 + }, + { + "epoch": 0.24, + "learning_rate": 1.875826617638618e-05, + "loss": 1.4179, + "step": 2329 + }, + { + "epoch": 0.24, + "learning_rate": 1.8756499058328813e-05, + "loss": 1.4302, + "step": 2330 + }, + { + "epoch": 0.24, + "learning_rate": 1.8754730767125564e-05, + "loss": 1.4959, + "step": 2331 + }, + { + "epoch": 0.24, + "learning_rate": 1.8752961303013336e-05, + "loss": 1.4423, + "step": 2332 + }, + { + "epoch": 0.24, + "learning_rate": 1.8751190666229194e-05, + "loss": 1.4564, + "step": 2333 + }, + { + "epoch": 0.24, + "learning_rate": 1.8749418857010358e-05, + "loss": 1.4775, + "step": 2334 + }, + { + "epoch": 0.24, + "learning_rate": 1.8747645875594203e-05, + "loss": 1.4182, + "step": 2335 + }, + { + "epoch": 0.24, + "learning_rate": 1.8745871722218265e-05, + "loss": 1.3957, + "step": 2336 + }, + { + "epoch": 0.25, + "learning_rate": 1.8744096397120235e-05, + "loss": 1.4633, + "step": 2337 + }, + { + "epoch": 0.25, + "learning_rate": 1.874231990053796e-05, + "loss": 1.5512, + "step": 2338 + }, + { + "epoch": 0.25, + "learning_rate": 1.8740542232709444e-05, + "loss": 1.3461, + "step": 2339 + }, + { + "epoch": 0.25, + "learning_rate": 1.8738763393872848e-05, + "loss": 1.4754, + "step": 2340 + }, + { + "epoch": 0.25, + "learning_rate": 1.8736983384266495e-05, + "loss": 1.5448, + "step": 2341 + }, + { + "epoch": 0.25, + "learning_rate": 1.8735202204128854e-05, + "loss": 1.4491, + "step": 2342 + }, + { + "epoch": 0.25, + "learning_rate": 1.8733419853698566e-05, + "loss": 1.457, + "step": 2343 + }, + { + "epoch": 0.25, + "learning_rate": 1.8731636333214414e-05, + "loss": 1.4314, + "step": 2344 + }, + { + "epoch": 0.25, + "learning_rate": 1.8729851642915345e-05, + "loss": 1.3979, + "step": 2345 + }, + { + "epoch": 0.25, + "learning_rate": 1.8728065783040464e-05, + "loss": 1.4146, + "step": 2346 + }, + { + "epoch": 0.25, + "learning_rate": 1.8726278753829027e-05, + "loss": 1.4361, + "step": 2347 + }, + { + "epoch": 0.25, + "learning_rate": 1.872449055552045e-05, + "loss": 1.4989, + "step": 2348 + }, + { + "epoch": 0.25, + "learning_rate": 1.872270118835431e-05, + "loss": 1.5062, + "step": 2349 + }, + { + "epoch": 0.25, + "learning_rate": 1.872091065257033e-05, + "loss": 1.4509, + "step": 2350 + }, + { + "epoch": 0.25, + "learning_rate": 1.8719118948408403e-05, + "loss": 1.4631, + "step": 2351 + }, + { + "epoch": 0.25, + "learning_rate": 1.8717326076108566e-05, + "loss": 1.5119, + "step": 2352 + }, + { + "epoch": 0.25, + "learning_rate": 1.8715532035911017e-05, + "loss": 1.6347, + "step": 2353 + }, + { + "epoch": 0.25, + "learning_rate": 1.8713736828056115e-05, + "loss": 1.5526, + "step": 2354 + }, + { + "epoch": 0.25, + "learning_rate": 1.8711940452784368e-05, + "loss": 1.6348, + "step": 2355 + }, + { + "epoch": 0.25, + "learning_rate": 1.871014291033645e-05, + "loss": 1.5183, + "step": 2356 + }, + { + "epoch": 0.25, + "learning_rate": 1.8708344200953182e-05, + "loss": 1.458, + "step": 2357 + }, + { + "epoch": 0.25, + "learning_rate": 1.8706544324875545e-05, + "loss": 1.524, + "step": 2358 + }, + { + "epoch": 0.25, + "learning_rate": 1.8704743282344672e-05, + "loss": 1.4479, + "step": 2359 + }, + { + "epoch": 0.25, + "learning_rate": 1.870294107360186e-05, + "loss": 1.5408, + "step": 2360 + }, + { + "epoch": 0.25, + "learning_rate": 1.8701137698888563e-05, + "loss": 1.5007, + "step": 2361 + }, + { + "epoch": 0.25, + "learning_rate": 1.8699333158446382e-05, + "loss": 1.5132, + "step": 2362 + }, + { + "epoch": 0.25, + "learning_rate": 1.869752745251708e-05, + "loss": 1.4263, + "step": 2363 + }, + { + "epoch": 0.25, + "learning_rate": 1.8695720581342574e-05, + "loss": 1.422, + "step": 2364 + }, + { + "epoch": 0.25, + "learning_rate": 1.869391254516494e-05, + "loss": 1.4411, + "step": 2365 + }, + { + "epoch": 0.25, + "learning_rate": 1.8692103344226406e-05, + "loss": 1.4594, + "step": 2366 + }, + { + "epoch": 0.25, + "learning_rate": 1.8690292978769364e-05, + "loss": 1.4992, + "step": 2367 + }, + { + "epoch": 0.25, + "learning_rate": 1.868848144903635e-05, + "loss": 1.4822, + "step": 2368 + }, + { + "epoch": 0.25, + "learning_rate": 1.8686668755270064e-05, + "loss": 1.5402, + "step": 2369 + }, + { + "epoch": 0.25, + "learning_rate": 1.8684854897713363e-05, + "loss": 1.5268, + "step": 2370 + }, + { + "epoch": 0.25, + "learning_rate": 1.8683039876609258e-05, + "loss": 1.5587, + "step": 2371 + }, + { + "epoch": 0.25, + "learning_rate": 1.868122369220091e-05, + "loss": 1.4214, + "step": 2372 + }, + { + "epoch": 0.25, + "learning_rate": 1.8679406344731645e-05, + "loss": 1.5089, + "step": 2373 + }, + { + "epoch": 0.25, + "learning_rate": 1.867758783444494e-05, + "loss": 1.5067, + "step": 2374 + }, + { + "epoch": 0.25, + "learning_rate": 1.8675768161584427e-05, + "loss": 2.0616, + "step": 2375 + }, + { + "epoch": 0.25, + "learning_rate": 1.8673947326393903e-05, + "loss": 1.5617, + "step": 2376 + }, + { + "epoch": 0.25, + "learning_rate": 1.86721253291173e-05, + "loss": 1.4422, + "step": 2377 + }, + { + "epoch": 0.25, + "learning_rate": 1.867030216999873e-05, + "loss": 1.4727, + "step": 2378 + }, + { + "epoch": 0.25, + "learning_rate": 1.8668477849282443e-05, + "loss": 1.4152, + "step": 2379 + }, + { + "epoch": 0.25, + "learning_rate": 1.8666652367212856e-05, + "loss": 1.4376, + "step": 2380 + }, + { + "epoch": 0.25, + "learning_rate": 1.8664825724034534e-05, + "loss": 1.393, + "step": 2381 + }, + { + "epoch": 0.25, + "learning_rate": 1.8662997919992197e-05, + "loss": 1.4864, + "step": 2382 + }, + { + "epoch": 0.25, + "learning_rate": 1.866116895533073e-05, + "loss": 1.4261, + "step": 2383 + }, + { + "epoch": 0.25, + "learning_rate": 1.8659338830295163e-05, + "loss": 1.4555, + "step": 2384 + }, + { + "epoch": 0.25, + "learning_rate": 1.8657507545130687e-05, + "loss": 1.4939, + "step": 2385 + }, + { + "epoch": 0.25, + "learning_rate": 1.865567510008265e-05, + "loss": 1.4123, + "step": 2386 + }, + { + "epoch": 0.25, + "learning_rate": 1.8653841495396546e-05, + "loss": 1.4459, + "step": 2387 + }, + { + "epoch": 0.25, + "learning_rate": 1.8652006731318038e-05, + "loss": 1.396, + "step": 2388 + }, + { + "epoch": 0.25, + "eval_loss": 1.5139706134796143, + "eval_runtime": 77.2904, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 2388 + }, + { + "epoch": 0.25, + "learning_rate": 1.8650170808092936e-05, + "loss": 1.4666, + "step": 2389 + }, + { + "epoch": 0.25, + "learning_rate": 1.86483337259672e-05, + "loss": 1.5154, + "step": 2390 + }, + { + "epoch": 0.25, + "learning_rate": 1.864649548518696e-05, + "loss": 1.5163, + "step": 2391 + }, + { + "epoch": 0.25, + "learning_rate": 1.864465608599849e-05, + "loss": 1.4734, + "step": 2392 + }, + { + "epoch": 0.25, + "learning_rate": 1.864281552864822e-05, + "loss": 1.5217, + "step": 2393 + }, + { + "epoch": 0.25, + "learning_rate": 1.8640973813382737e-05, + "loss": 1.4694, + "step": 2394 + }, + { + "epoch": 0.25, + "learning_rate": 1.863913094044879e-05, + "loss": 1.4761, + "step": 2395 + }, + { + "epoch": 0.25, + "learning_rate": 1.863728691009327e-05, + "loss": 1.4766, + "step": 2396 + }, + { + "epoch": 0.25, + "learning_rate": 1.863544172256323e-05, + "loss": 1.5695, + "step": 2397 + }, + { + "epoch": 0.25, + "learning_rate": 1.8633595378105882e-05, + "loss": 1.5079, + "step": 2398 + }, + { + "epoch": 0.25, + "learning_rate": 1.8631747876968584e-05, + "loss": 1.4154, + "step": 2399 + }, + { + "epoch": 0.25, + "learning_rate": 1.862989921939886e-05, + "loss": 1.4488, + "step": 2400 + }, + { + "epoch": 0.25, + "learning_rate": 1.8628049405644376e-05, + "loss": 1.4279, + "step": 2401 + }, + { + "epoch": 0.25, + "learning_rate": 1.8626198435952966e-05, + "loss": 1.4896, + "step": 2402 + }, + { + "epoch": 0.25, + "learning_rate": 1.8624346310572602e-05, + "loss": 1.4315, + "step": 2403 + }, + { + "epoch": 0.25, + "learning_rate": 1.862249302975143e-05, + "loss": 1.4919, + "step": 2404 + }, + { + "epoch": 0.25, + "learning_rate": 1.8620638593737743e-05, + "loss": 1.4561, + "step": 2405 + }, + { + "epoch": 0.25, + "learning_rate": 1.8618783002779985e-05, + "loss": 1.4622, + "step": 2406 + }, + { + "epoch": 0.25, + "learning_rate": 1.8616926257126754e-05, + "loss": 1.4917, + "step": 2407 + }, + { + "epoch": 0.25, + "learning_rate": 1.861506835702681e-05, + "loss": 1.4962, + "step": 2408 + }, + { + "epoch": 0.25, + "learning_rate": 1.861320930272906e-05, + "loss": 1.4164, + "step": 2409 + }, + { + "epoch": 0.25, + "learning_rate": 1.8611349094482578e-05, + "loss": 1.4889, + "step": 2410 + }, + { + "epoch": 0.25, + "learning_rate": 1.8609487732536576e-05, + "loss": 1.543, + "step": 2411 + }, + { + "epoch": 0.25, + "learning_rate": 1.8607625217140433e-05, + "loss": 1.5417, + "step": 2412 + }, + { + "epoch": 0.25, + "learning_rate": 1.8605761548543674e-05, + "loss": 1.5304, + "step": 2413 + }, + { + "epoch": 0.25, + "learning_rate": 1.860389672699599e-05, + "loss": 1.4725, + "step": 2414 + }, + { + "epoch": 0.25, + "learning_rate": 1.860203075274721e-05, + "loss": 1.4745, + "step": 2415 + }, + { + "epoch": 0.25, + "learning_rate": 1.8600163626047334e-05, + "loss": 1.4656, + "step": 2416 + }, + { + "epoch": 0.25, + "learning_rate": 1.8598295347146503e-05, + "loss": 1.5287, + "step": 2417 + }, + { + "epoch": 0.25, + "learning_rate": 1.8596425916295023e-05, + "loss": 1.5024, + "step": 2418 + }, + { + "epoch": 0.25, + "learning_rate": 1.8594555333743348e-05, + "loss": 1.4527, + "step": 2419 + }, + { + "epoch": 0.25, + "learning_rate": 1.859268359974209e-05, + "loss": 1.4897, + "step": 2420 + }, + { + "epoch": 0.25, + "learning_rate": 1.859081071454201e-05, + "loss": 1.3554, + "step": 2421 + }, + { + "epoch": 0.25, + "learning_rate": 1.858893667839403e-05, + "loss": 1.4004, + "step": 2422 + }, + { + "epoch": 0.25, + "learning_rate": 1.858706149154922e-05, + "loss": 1.5582, + "step": 2423 + }, + { + "epoch": 0.25, + "learning_rate": 1.8585185154258803e-05, + "loss": 1.505, + "step": 2424 + }, + { + "epoch": 0.25, + "learning_rate": 1.858330766677417e-05, + "loss": 1.5043, + "step": 2425 + }, + { + "epoch": 0.25, + "learning_rate": 1.858142902934685e-05, + "loss": 1.439, + "step": 2426 + }, + { + "epoch": 0.25, + "learning_rate": 1.857954924222853e-05, + "loss": 1.4927, + "step": 2427 + }, + { + "epoch": 0.25, + "learning_rate": 1.8577668305671056e-05, + "loss": 1.5395, + "step": 2428 + }, + { + "epoch": 0.25, + "learning_rate": 1.8575786219926427e-05, + "loss": 1.4737, + "step": 2429 + }, + { + "epoch": 0.25, + "learning_rate": 1.8573902985246794e-05, + "loss": 1.6151, + "step": 2430 + }, + { + "epoch": 0.25, + "learning_rate": 1.857201860188446e-05, + "loss": 1.4313, + "step": 2431 + }, + { + "epoch": 0.26, + "learning_rate": 1.857013307009188e-05, + "loss": 1.4509, + "step": 2432 + }, + { + "epoch": 0.26, + "learning_rate": 1.8568246390121673e-05, + "loss": 1.3998, + "step": 2433 + }, + { + "epoch": 0.26, + "learning_rate": 1.8566358562226603e-05, + "loss": 1.5268, + "step": 2434 + }, + { + "epoch": 0.26, + "learning_rate": 1.8564469586659593e-05, + "loss": 1.4369, + "step": 2435 + }, + { + "epoch": 0.26, + "learning_rate": 1.8562579463673713e-05, + "loss": 1.4759, + "step": 2436 + }, + { + "epoch": 0.26, + "learning_rate": 1.8560688193522197e-05, + "loss": 1.4092, + "step": 2437 + }, + { + "epoch": 0.26, + "learning_rate": 1.855879577645842e-05, + "loss": 1.43, + "step": 2438 + }, + { + "epoch": 0.26, + "learning_rate": 1.855690221273592e-05, + "loss": 1.5143, + "step": 2439 + }, + { + "epoch": 0.26, + "learning_rate": 1.8555007502608385e-05, + "loss": 1.5482, + "step": 2440 + }, + { + "epoch": 0.26, + "learning_rate": 1.855311164632966e-05, + "loss": 1.4406, + "step": 2441 + }, + { + "epoch": 0.26, + "learning_rate": 1.8551214644153738e-05, + "loss": 1.4551, + "step": 2442 + }, + { + "epoch": 0.26, + "learning_rate": 1.8549316496334774e-05, + "loss": 1.4663, + "step": 2443 + }, + { + "epoch": 0.26, + "learning_rate": 1.8547417203127064e-05, + "loss": 1.4732, + "step": 2444 + }, + { + "epoch": 0.26, + "learning_rate": 1.8545516764785067e-05, + "loss": 1.5378, + "step": 2445 + }, + { + "epoch": 0.26, + "learning_rate": 1.8543615181563397e-05, + "loss": 1.4448, + "step": 2446 + }, + { + "epoch": 0.26, + "learning_rate": 1.854171245371681e-05, + "loss": 1.2861, + "step": 2447 + }, + { + "epoch": 0.26, + "learning_rate": 1.8539808581500228e-05, + "loss": 1.4405, + "step": 2448 + }, + { + "epoch": 0.26, + "learning_rate": 1.8537903565168716e-05, + "loss": 1.4876, + "step": 2449 + }, + { + "epoch": 0.26, + "learning_rate": 1.8535997404977506e-05, + "loss": 1.4119, + "step": 2450 + }, + { + "epoch": 0.26, + "learning_rate": 1.8534090101181967e-05, + "loss": 1.4451, + "step": 2451 + }, + { + "epoch": 0.26, + "learning_rate": 1.8532181654037632e-05, + "loss": 1.4035, + "step": 2452 + }, + { + "epoch": 0.26, + "learning_rate": 1.853027206380018e-05, + "loss": 1.4624, + "step": 2453 + }, + { + "epoch": 0.26, + "learning_rate": 1.852836133072545e-05, + "loss": 1.4935, + "step": 2454 + }, + { + "epoch": 0.26, + "learning_rate": 1.8526449455069434e-05, + "loss": 1.4834, + "step": 2455 + }, + { + "epoch": 0.26, + "learning_rate": 1.8524536437088266e-05, + "loss": 1.498, + "step": 2456 + }, + { + "epoch": 0.26, + "learning_rate": 1.8522622277038247e-05, + "loss": 1.3417, + "step": 2457 + }, + { + "epoch": 0.26, + "learning_rate": 1.852070697517583e-05, + "loss": 1.4455, + "step": 2458 + }, + { + "epoch": 0.26, + "learning_rate": 1.8518790531757607e-05, + "loss": 1.4119, + "step": 2459 + }, + { + "epoch": 0.26, + "learning_rate": 1.8516872947040337e-05, + "loss": 1.558, + "step": 2460 + }, + { + "epoch": 0.26, + "learning_rate": 1.8514954221280926e-05, + "loss": 1.4862, + "step": 2461 + }, + { + "epoch": 0.26, + "learning_rate": 1.8513034354736433e-05, + "loss": 1.6806, + "step": 2462 + }, + { + "epoch": 0.26, + "learning_rate": 1.8511113347664072e-05, + "loss": 1.438, + "step": 2463 + }, + { + "epoch": 0.26, + "learning_rate": 1.850919120032121e-05, + "loss": 1.4975, + "step": 2464 + }, + { + "epoch": 0.26, + "learning_rate": 1.850726791296536e-05, + "loss": 1.4409, + "step": 2465 + }, + { + "epoch": 0.26, + "learning_rate": 1.85053434858542e-05, + "loss": 1.4769, + "step": 2466 + }, + { + "epoch": 0.26, + "learning_rate": 1.8503417919245548e-05, + "loss": 1.5823, + "step": 2467 + }, + { + "epoch": 0.26, + "learning_rate": 1.8501491213397386e-05, + "loss": 1.4045, + "step": 2468 + }, + { + "epoch": 0.26, + "learning_rate": 1.8499563368567837e-05, + "loss": 1.4828, + "step": 2469 + }, + { + "epoch": 0.26, + "learning_rate": 1.849763438501519e-05, + "loss": 1.4684, + "step": 2470 + }, + { + "epoch": 0.26, + "learning_rate": 1.8495704262997873e-05, + "loss": 1.4577, + "step": 2471 + }, + { + "epoch": 0.26, + "learning_rate": 1.8493773002774475e-05, + "loss": 1.4759, + "step": 2472 + }, + { + "epoch": 0.26, + "learning_rate": 1.8491840604603736e-05, + "loss": 1.4259, + "step": 2473 + }, + { + "epoch": 0.26, + "learning_rate": 1.8489907068744543e-05, + "loss": 1.4717, + "step": 2474 + }, + { + "epoch": 0.26, + "learning_rate": 1.848797239545595e-05, + "loss": 1.4247, + "step": 2475 + }, + { + "epoch": 0.26, + "learning_rate": 1.8486036584997143e-05, + "loss": 1.4954, + "step": 2476 + }, + { + "epoch": 0.26, + "learning_rate": 1.8484099637627472e-05, + "loss": 1.4926, + "step": 2477 + }, + { + "epoch": 0.26, + "learning_rate": 1.8482161553606447e-05, + "loss": 1.487, + "step": 2478 + }, + { + "epoch": 0.26, + "learning_rate": 1.8480222333193715e-05, + "loss": 1.4553, + "step": 2479 + }, + { + "epoch": 0.26, + "learning_rate": 1.847828197664908e-05, + "loss": 1.4862, + "step": 2480 + }, + { + "epoch": 0.26, + "learning_rate": 1.8476340484232508e-05, + "loss": 1.4867, + "step": 2481 + }, + { + "epoch": 0.26, + "learning_rate": 1.8474397856204097e-05, + "loss": 1.4736, + "step": 2482 + }, + { + "epoch": 0.26, + "learning_rate": 1.8472454092824122e-05, + "loss": 1.4254, + "step": 2483 + }, + { + "epoch": 0.26, + "learning_rate": 1.8470509194352987e-05, + "loss": 1.4455, + "step": 2484 + }, + { + "epoch": 0.26, + "learning_rate": 1.8468563161051263e-05, + "loss": 1.4402, + "step": 2485 + }, + { + "epoch": 0.26, + "learning_rate": 1.846661599317967e-05, + "loss": 1.4611, + "step": 2486 + }, + { + "epoch": 0.26, + "learning_rate": 1.8464667690999073e-05, + "loss": 1.4814, + "step": 2487 + }, + { + "epoch": 0.26, + "learning_rate": 1.8462718254770503e-05, + "loss": 1.4559, + "step": 2488 + }, + { + "epoch": 0.26, + "learning_rate": 1.8460767684755127e-05, + "loss": 1.4667, + "step": 2489 + }, + { + "epoch": 0.26, + "learning_rate": 1.8458815981214274e-05, + "loss": 1.4427, + "step": 2490 + }, + { + "epoch": 0.26, + "learning_rate": 1.845686314440942e-05, + "loss": 1.4055, + "step": 2491 + }, + { + "epoch": 0.26, + "learning_rate": 1.8454909174602198e-05, + "loss": 1.5563, + "step": 2492 + }, + { + "epoch": 0.26, + "learning_rate": 1.845295407205439e-05, + "loss": 1.4631, + "step": 2493 + }, + { + "epoch": 0.26, + "learning_rate": 1.8450997837027925e-05, + "loss": 1.4887, + "step": 2494 + }, + { + "epoch": 0.26, + "learning_rate": 1.8449040469784895e-05, + "loss": 1.5212, + "step": 2495 + }, + { + "epoch": 0.26, + "learning_rate": 1.844708197058753e-05, + "loss": 1.5582, + "step": 2496 + }, + { + "epoch": 0.26, + "learning_rate": 1.844512233969822e-05, + "loss": 1.4599, + "step": 2497 + }, + { + "epoch": 0.26, + "learning_rate": 1.844316157737951e-05, + "loss": 1.4546, + "step": 2498 + }, + { + "epoch": 0.26, + "learning_rate": 1.844119968389409e-05, + "loss": 1.4631, + "step": 2499 + }, + { + "epoch": 0.26, + "learning_rate": 1.84392366595048e-05, + "loss": 1.4817, + "step": 2500 + }, + { + "epoch": 0.26, + "learning_rate": 1.8437272504474636e-05, + "loss": 1.4214, + "step": 2501 + }, + { + "epoch": 0.26, + "learning_rate": 1.8435307219066744e-05, + "loss": 1.471, + "step": 2502 + }, + { + "epoch": 0.26, + "learning_rate": 1.8433340803544424e-05, + "loss": 1.4693, + "step": 2503 + }, + { + "epoch": 0.26, + "learning_rate": 1.8431373258171127e-05, + "loss": 1.6297, + "step": 2504 + }, + { + "epoch": 0.26, + "learning_rate": 1.842940458321045e-05, + "loss": 1.5916, + "step": 2505 + }, + { + "epoch": 0.26, + "learning_rate": 1.842743477892614e-05, + "loss": 1.4754, + "step": 2506 + }, + { + "epoch": 0.26, + "learning_rate": 1.842546384558211e-05, + "loss": 1.4828, + "step": 2507 + }, + { + "epoch": 0.26, + "learning_rate": 1.842349178344241e-05, + "loss": 1.4239, + "step": 2508 + }, + { + "epoch": 0.26, + "learning_rate": 1.8421518592771243e-05, + "loss": 1.5028, + "step": 2509 + }, + { + "epoch": 0.26, + "learning_rate": 1.841954427383297e-05, + "loss": 1.4848, + "step": 2510 + }, + { + "epoch": 0.26, + "learning_rate": 1.8417568826892097e-05, + "loss": 1.4617, + "step": 2511 + }, + { + "epoch": 0.26, + "learning_rate": 1.8415592252213284e-05, + "loss": 1.4266, + "step": 2512 + }, + { + "epoch": 0.26, + "learning_rate": 1.8413614550061344e-05, + "loss": 1.4321, + "step": 2513 + }, + { + "epoch": 0.26, + "learning_rate": 1.841163572070123e-05, + "loss": 1.4693, + "step": 2514 + }, + { + "epoch": 0.26, + "learning_rate": 1.840965576439806e-05, + "loss": 1.4257, + "step": 2515 + }, + { + "epoch": 0.26, + "learning_rate": 1.84076746814171e-05, + "loss": 1.4488, + "step": 2516 + }, + { + "epoch": 0.26, + "learning_rate": 1.840569247202376e-05, + "loss": 1.5348, + "step": 2517 + }, + { + "epoch": 0.26, + "learning_rate": 1.8403709136483604e-05, + "loss": 1.477, + "step": 2518 + }, + { + "epoch": 0.26, + "learning_rate": 1.840172467506235e-05, + "loss": 1.443, + "step": 2519 + }, + { + "epoch": 0.26, + "learning_rate": 1.839973908802587e-05, + "loss": 1.4772, + "step": 2520 + }, + { + "epoch": 0.26, + "learning_rate": 1.839775237564017e-05, + "loss": 1.4443, + "step": 2521 + }, + { + "epoch": 0.26, + "learning_rate": 1.839576453817143e-05, + "loss": 1.4063, + "step": 2522 + }, + { + "epoch": 0.26, + "learning_rate": 1.8393775575885963e-05, + "loss": 1.5178, + "step": 2523 + }, + { + "epoch": 0.26, + "learning_rate": 1.8391785489050235e-05, + "loss": 1.4337, + "step": 2524 + }, + { + "epoch": 0.26, + "learning_rate": 1.8389794277930875e-05, + "loss": 1.4512, + "step": 2525 + }, + { + "epoch": 0.26, + "learning_rate": 1.838780194279465e-05, + "loss": 1.5578, + "step": 2526 + }, + { + "epoch": 0.26, + "learning_rate": 1.8385808483908484e-05, + "loss": 1.4606, + "step": 2527 + }, + { + "epoch": 0.27, + "learning_rate": 1.8383813901539444e-05, + "loss": 1.4957, + "step": 2528 + }, + { + "epoch": 0.27, + "learning_rate": 1.838181819595476e-05, + "loss": 1.4914, + "step": 2529 + }, + { + "epoch": 0.27, + "learning_rate": 1.8379821367421802e-05, + "loss": 1.4785, + "step": 2530 + }, + { + "epoch": 0.27, + "learning_rate": 1.837782341620809e-05, + "loss": 1.4052, + "step": 2531 + }, + { + "epoch": 0.27, + "learning_rate": 1.8375824342581303e-05, + "loss": 1.4807, + "step": 2532 + }, + { + "epoch": 0.27, + "learning_rate": 1.8373824146809264e-05, + "loss": 1.4313, + "step": 2533 + }, + { + "epoch": 0.27, + "learning_rate": 1.8371822829159945e-05, + "loss": 1.4374, + "step": 2534 + }, + { + "epoch": 0.27, + "learning_rate": 1.836982038990148e-05, + "loss": 1.4482, + "step": 2535 + }, + { + "epoch": 0.27, + "learning_rate": 1.8367816829302133e-05, + "loss": 1.5231, + "step": 2536 + }, + { + "epoch": 0.27, + "learning_rate": 1.8365812147630337e-05, + "loss": 1.4101, + "step": 2537 + }, + { + "epoch": 0.27, + "learning_rate": 1.8363806345154666e-05, + "loss": 1.4372, + "step": 2538 + }, + { + "epoch": 0.27, + "learning_rate": 1.8361799422143845e-05, + "loss": 1.4808, + "step": 2539 + }, + { + "epoch": 0.27, + "learning_rate": 1.835979137886675e-05, + "loss": 1.3515, + "step": 2540 + }, + { + "epoch": 0.27, + "learning_rate": 1.8357782215592412e-05, + "loss": 1.5284, + "step": 2541 + }, + { + "epoch": 0.27, + "learning_rate": 1.835577193259e-05, + "loss": 1.4222, + "step": 2542 + }, + { + "epoch": 0.27, + "learning_rate": 1.8353760530128846e-05, + "loss": 1.4522, + "step": 2543 + }, + { + "epoch": 0.27, + "learning_rate": 1.835174800847842e-05, + "loss": 1.4487, + "step": 2544 + }, + { + "epoch": 0.27, + "learning_rate": 1.8349734367908355e-05, + "loss": 1.3688, + "step": 2545 + }, + { + "epoch": 0.27, + "learning_rate": 1.8347719608688422e-05, + "loss": 1.483, + "step": 2546 + }, + { + "epoch": 0.27, + "learning_rate": 1.8345703731088554e-05, + "loss": 1.4733, + "step": 2547 + }, + { + "epoch": 0.27, + "learning_rate": 1.8343686735378816e-05, + "loss": 1.4594, + "step": 2548 + }, + { + "epoch": 0.27, + "learning_rate": 1.834166862182944e-05, + "loss": 1.4648, + "step": 2549 + }, + { + "epoch": 0.27, + "learning_rate": 1.8339649390710807e-05, + "loss": 1.5249, + "step": 2550 + }, + { + "epoch": 0.27, + "learning_rate": 1.8337629042293434e-05, + "loss": 1.4744, + "step": 2551 + }, + { + "epoch": 0.27, + "learning_rate": 1.8335607576847994e-05, + "loss": 1.5094, + "step": 2552 + }, + { + "epoch": 0.27, + "learning_rate": 1.8333584994645318e-05, + "loss": 1.5122, + "step": 2553 + }, + { + "epoch": 0.27, + "learning_rate": 1.8331561295956374e-05, + "loss": 1.537, + "step": 2554 + }, + { + "epoch": 0.27, + "learning_rate": 1.832953648105229e-05, + "loss": 1.4691, + "step": 2555 + }, + { + "epoch": 0.27, + "learning_rate": 1.8327510550204343e-05, + "loss": 1.4969, + "step": 2556 + }, + { + "epoch": 0.27, + "learning_rate": 1.8325483503683944e-05, + "loss": 1.4596, + "step": 2557 + }, + { + "epoch": 0.27, + "learning_rate": 1.8323455341762675e-05, + "loss": 1.435, + "step": 2558 + }, + { + "epoch": 0.27, + "learning_rate": 1.8321426064712255e-05, + "loss": 1.4883, + "step": 2559 + }, + { + "epoch": 0.27, + "learning_rate": 1.8319395672804554e-05, + "loss": 1.3758, + "step": 2560 + }, + { + "epoch": 0.27, + "learning_rate": 1.8317364166311592e-05, + "loss": 1.4352, + "step": 2561 + }, + { + "epoch": 0.27, + "learning_rate": 1.831533154550554e-05, + "loss": 1.5072, + "step": 2562 + }, + { + "epoch": 0.27, + "learning_rate": 1.8313297810658718e-05, + "loss": 1.4476, + "step": 2563 + }, + { + "epoch": 0.27, + "learning_rate": 1.831126296204359e-05, + "loss": 1.507, + "step": 2564 + }, + { + "epoch": 0.27, + "learning_rate": 1.8309226999932777e-05, + "loss": 1.4677, + "step": 2565 + }, + { + "epoch": 0.27, + "learning_rate": 1.8307189924599044e-05, + "loss": 1.4537, + "step": 2566 + }, + { + "epoch": 0.27, + "learning_rate": 1.8305151736315307e-05, + "loss": 1.4584, + "step": 2567 + }, + { + "epoch": 0.27, + "learning_rate": 1.8303112435354634e-05, + "loss": 1.4944, + "step": 2568 + }, + { + "epoch": 0.27, + "learning_rate": 1.8301072021990232e-05, + "loss": 1.4379, + "step": 2569 + }, + { + "epoch": 0.27, + "learning_rate": 1.8299030496495475e-05, + "loss": 1.539, + "step": 2570 + }, + { + "epoch": 0.27, + "learning_rate": 1.829698785914386e-05, + "loss": 1.4421, + "step": 2571 + }, + { + "epoch": 0.27, + "learning_rate": 1.8294944110209063e-05, + "loss": 1.4693, + "step": 2572 + }, + { + "epoch": 0.27, + "learning_rate": 1.8292899249964887e-05, + "loss": 1.3239, + "step": 2573 + }, + { + "epoch": 0.27, + "learning_rate": 1.8290853278685284e-05, + "loss": 1.472, + "step": 2574 + }, + { + "epoch": 0.27, + "learning_rate": 1.8288806196644374e-05, + "loss": 1.536, + "step": 2575 + }, + { + "epoch": 0.27, + "learning_rate": 1.8286758004116405e-05, + "loss": 1.4644, + "step": 2576 + }, + { + "epoch": 0.27, + "learning_rate": 1.8284708701375783e-05, + "loss": 1.4537, + "step": 2577 + }, + { + "epoch": 0.27, + "learning_rate": 1.8282658288697067e-05, + "loss": 1.4359, + "step": 2578 + }, + { + "epoch": 0.27, + "learning_rate": 1.8280606766354955e-05, + "loss": 1.4842, + "step": 2579 + }, + { + "epoch": 0.27, + "learning_rate": 1.8278554134624302e-05, + "loss": 1.4664, + "step": 2580 + }, + { + "epoch": 0.27, + "learning_rate": 1.8276500393780105e-05, + "loss": 1.4632, + "step": 2581 + }, + { + "epoch": 0.27, + "learning_rate": 1.827444554409751e-05, + "loss": 1.4996, + "step": 2582 + }, + { + "epoch": 0.27, + "learning_rate": 1.827238958585182e-05, + "loss": 1.3399, + "step": 2583 + }, + { + "epoch": 0.27, + "learning_rate": 1.8270332519318476e-05, + "loss": 1.3928, + "step": 2584 + }, + { + "epoch": 0.27, + "learning_rate": 1.8268274344773074e-05, + "loss": 1.4993, + "step": 2585 + }, + { + "epoch": 0.27, + "learning_rate": 1.8266215062491356e-05, + "loss": 1.5398, + "step": 2586 + }, + { + "epoch": 0.27, + "learning_rate": 1.826415467274921e-05, + "loss": 1.4353, + "step": 2587 + }, + { + "epoch": 0.27, + "eval_loss": 1.5104212760925293, + "eval_runtime": 77.3448, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2587 + }, + { + "epoch": 0.27, + "learning_rate": 1.8262093175822685e-05, + "loss": 1.4889, + "step": 2588 + }, + { + "epoch": 0.27, + "learning_rate": 1.826003057198796e-05, + "loss": 1.4912, + "step": 2589 + }, + { + "epoch": 0.27, + "learning_rate": 1.825796686152137e-05, + "loss": 1.4884, + "step": 2590 + }, + { + "epoch": 0.27, + "learning_rate": 1.8255902044699404e-05, + "loss": 1.478, + "step": 2591 + }, + { + "epoch": 0.27, + "learning_rate": 1.8253836121798692e-05, + "loss": 1.6549, + "step": 2592 + }, + { + "epoch": 0.27, + "learning_rate": 1.8251769093096018e-05, + "loss": 1.5146, + "step": 2593 + }, + { + "epoch": 0.27, + "learning_rate": 1.8249700958868306e-05, + "loss": 1.4797, + "step": 2594 + }, + { + "epoch": 0.27, + "learning_rate": 1.8247631719392634e-05, + "loss": 1.4655, + "step": 2595 + }, + { + "epoch": 0.27, + "learning_rate": 1.824556137494623e-05, + "loss": 1.4517, + "step": 2596 + }, + { + "epoch": 0.27, + "learning_rate": 1.8243489925806458e-05, + "loss": 1.4936, + "step": 2597 + }, + { + "epoch": 0.27, + "learning_rate": 1.8241417372250852e-05, + "loss": 1.4614, + "step": 2598 + }, + { + "epoch": 0.27, + "learning_rate": 1.8239343714557073e-05, + "loss": 1.4475, + "step": 2599 + }, + { + "epoch": 0.27, + "learning_rate": 1.8237268953002937e-05, + "loss": 1.5435, + "step": 2600 + }, + { + "epoch": 0.27, + "learning_rate": 1.8235193087866413e-05, + "loss": 1.4616, + "step": 2601 + }, + { + "epoch": 0.27, + "learning_rate": 1.8233116119425612e-05, + "loss": 1.4578, + "step": 2602 + }, + { + "epoch": 0.27, + "learning_rate": 1.8231038047958795e-05, + "loss": 1.434, + "step": 2603 + }, + { + "epoch": 0.27, + "learning_rate": 1.8228958873744368e-05, + "loss": 1.5335, + "step": 2604 + }, + { + "epoch": 0.27, + "learning_rate": 1.8226878597060887e-05, + "loss": 1.415, + "step": 2605 + }, + { + "epoch": 0.27, + "learning_rate": 1.8224797218187058e-05, + "loss": 1.6165, + "step": 2606 + }, + { + "epoch": 0.27, + "learning_rate": 1.822271473740173e-05, + "loss": 1.372, + "step": 2607 + }, + { + "epoch": 0.27, + "learning_rate": 1.8220631154983907e-05, + "loss": 1.4855, + "step": 2608 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218546471212727e-05, + "loss": 1.4093, + "step": 2609 + }, + { + "epoch": 0.27, + "learning_rate": 1.821646068636749e-05, + "loss": 1.4852, + "step": 2610 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214373800727637e-05, + "loss": 1.6959, + "step": 2611 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212285814572755e-05, + "loss": 1.3874, + "step": 2612 + }, + { + "epoch": 0.27, + "learning_rate": 1.821019672818258e-05, + "loss": 1.4425, + "step": 2613 + }, + { + "epoch": 0.27, + "learning_rate": 1.8208106541837e-05, + "loss": 1.6097, + "step": 2614 + }, + { + "epoch": 0.27, + "learning_rate": 1.8206015255816045e-05, + "loss": 1.5675, + "step": 2615 + }, + { + "epoch": 0.27, + "learning_rate": 1.820392287039989e-05, + "loss": 1.4039, + "step": 2616 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201829385868866e-05, + "loss": 1.4872, + "step": 2617 + }, + { + "epoch": 0.27, + "learning_rate": 1.819973480250344e-05, + "loss": 1.4645, + "step": 2618 + }, + { + "epoch": 0.27, + "learning_rate": 1.8197639120584237e-05, + "loss": 1.4923, + "step": 2619 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195542340392025e-05, + "loss": 1.4294, + "step": 2620 + }, + { + "epoch": 0.27, + "learning_rate": 1.8193444462207717e-05, + "loss": 1.4315, + "step": 2621 + }, + { + "epoch": 0.27, + "learning_rate": 1.8191345486312372e-05, + "loss": 1.3972, + "step": 2622 + }, + { + "epoch": 0.28, + "learning_rate": 1.8189245412987205e-05, + "loss": 1.462, + "step": 2623 + }, + { + "epoch": 0.28, + "learning_rate": 1.8187144242513567e-05, + "loss": 1.4738, + "step": 2624 + }, + { + "epoch": 0.28, + "learning_rate": 1.818504197517296e-05, + "loss": 1.4935, + "step": 2625 + }, + { + "epoch": 0.28, + "learning_rate": 1.8182938611247038e-05, + "loss": 1.4231, + "step": 2626 + }, + { + "epoch": 0.28, + "learning_rate": 1.81808341510176e-05, + "loss": 1.4031, + "step": 2627 + }, + { + "epoch": 0.28, + "learning_rate": 1.817872859476658e-05, + "loss": 1.5822, + "step": 2628 + }, + { + "epoch": 0.28, + "learning_rate": 1.8176621942776075e-05, + "loss": 1.432, + "step": 2629 + }, + { + "epoch": 0.28, + "learning_rate": 1.8174514195328324e-05, + "loss": 1.5565, + "step": 2630 + }, + { + "epoch": 0.28, + "learning_rate": 1.8172405352705704e-05, + "loss": 1.4895, + "step": 2631 + }, + { + "epoch": 0.28, + "learning_rate": 1.8170295415190754e-05, + "loss": 1.4032, + "step": 2632 + }, + { + "epoch": 0.28, + "learning_rate": 1.8168184383066144e-05, + "loss": 1.4253, + "step": 2633 + }, + { + "epoch": 0.28, + "learning_rate": 1.8166072256614702e-05, + "loss": 1.5162, + "step": 2634 + }, + { + "epoch": 0.28, + "learning_rate": 1.81639590361194e-05, + "loss": 1.4609, + "step": 2635 + }, + { + "epoch": 0.28, + "learning_rate": 1.816184472186335e-05, + "loss": 1.4351, + "step": 2636 + }, + { + "epoch": 0.28, + "learning_rate": 1.8159729314129823e-05, + "loss": 1.4738, + "step": 2637 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157612813202224e-05, + "loss": 1.5986, + "step": 2638 + }, + { + "epoch": 0.28, + "learning_rate": 1.815549521936411e-05, + "loss": 1.4633, + "step": 2639 + }, + { + "epoch": 0.28, + "learning_rate": 1.8153376532899184e-05, + "loss": 1.4404, + "step": 2640 + }, + { + "epoch": 0.28, + "learning_rate": 1.81512567540913e-05, + "loss": 1.4256, + "step": 2641 + }, + { + "epoch": 0.28, + "learning_rate": 1.814913588322445e-05, + "loss": 1.4054, + "step": 2642 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147013920582773e-05, + "loss": 1.4134, + "step": 2643 + }, + { + "epoch": 0.28, + "learning_rate": 1.8144890866450567e-05, + "loss": 1.4098, + "step": 2644 + }, + { + "epoch": 0.28, + "learning_rate": 1.814276672111226e-05, + "loss": 1.4593, + "step": 2645 + }, + { + "epoch": 0.28, + "learning_rate": 1.814064148485243e-05, + "loss": 1.4679, + "step": 2646 + }, + { + "epoch": 0.28, + "learning_rate": 1.8138515157955812e-05, + "loss": 1.5234, + "step": 2647 + }, + { + "epoch": 0.28, + "learning_rate": 1.8136387740707272e-05, + "loss": 1.4568, + "step": 2648 + }, + { + "epoch": 0.28, + "learning_rate": 1.8134259233391836e-05, + "loss": 1.5057, + "step": 2649 + }, + { + "epoch": 0.28, + "learning_rate": 1.8132129636294665e-05, + "loss": 1.3643, + "step": 2650 + }, + { + "epoch": 0.28, + "learning_rate": 1.812999894970107e-05, + "loss": 1.4766, + "step": 2651 + }, + { + "epoch": 0.28, + "learning_rate": 1.812786717389651e-05, + "loss": 1.5701, + "step": 2652 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125734309166587e-05, + "loss": 1.5341, + "step": 2653 + }, + { + "epoch": 0.28, + "learning_rate": 1.812360035579705e-05, + "loss": 1.3596, + "step": 2654 + }, + { + "epoch": 0.28, + "learning_rate": 1.8121465314073793e-05, + "loss": 1.4847, + "step": 2655 + }, + { + "epoch": 0.28, + "learning_rate": 1.811932918428286e-05, + "loss": 1.4664, + "step": 2656 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117191966710438e-05, + "loss": 1.4673, + "step": 2657 + }, + { + "epoch": 0.28, + "learning_rate": 1.8115053661642856e-05, + "loss": 1.4712, + "step": 2658 + }, + { + "epoch": 0.28, + "learning_rate": 1.811291426936659e-05, + "loss": 1.4458, + "step": 2659 + }, + { + "epoch": 0.28, + "learning_rate": 1.811077379016827e-05, + "loss": 1.4667, + "step": 2660 + }, + { + "epoch": 0.28, + "learning_rate": 1.810863222433466e-05, + "loss": 1.4695, + "step": 2661 + }, + { + "epoch": 0.28, + "learning_rate": 1.8106489572152677e-05, + "loss": 1.5263, + "step": 2662 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104345833909376e-05, + "loss": 1.4148, + "step": 2663 + }, + { + "epoch": 0.28, + "learning_rate": 1.8102201009891976e-05, + "loss": 1.3955, + "step": 2664 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100055100387814e-05, + "loss": 1.6056, + "step": 2665 + }, + { + "epoch": 0.28, + "learning_rate": 1.8097908105684396e-05, + "loss": 1.5394, + "step": 2666 + }, + { + "epoch": 0.28, + "learning_rate": 1.809576002606936e-05, + "loss": 1.479, + "step": 2667 + }, + { + "epoch": 0.28, + "learning_rate": 1.8093610861830494e-05, + "loss": 1.4492, + "step": 2668 + }, + { + "epoch": 0.28, + "learning_rate": 1.8091460613255728e-05, + "loss": 1.4172, + "step": 2669 + }, + { + "epoch": 0.28, + "learning_rate": 1.808930928063315e-05, + "loss": 1.4498, + "step": 2670 + }, + { + "epoch": 0.28, + "learning_rate": 1.808715686425097e-05, + "loss": 1.6203, + "step": 2671 + }, + { + "epoch": 0.28, + "learning_rate": 1.8085003364397567e-05, + "loss": 1.435, + "step": 2672 + }, + { + "epoch": 0.28, + "learning_rate": 1.808284878136145e-05, + "loss": 1.4489, + "step": 2673 + }, + { + "epoch": 0.28, + "learning_rate": 1.8080693115431277e-05, + "loss": 1.4416, + "step": 2674 + }, + { + "epoch": 0.28, + "learning_rate": 1.8078536366895853e-05, + "loss": 1.422, + "step": 2675 + }, + { + "epoch": 0.28, + "learning_rate": 1.8076378536044128e-05, + "loss": 1.4039, + "step": 2676 + }, + { + "epoch": 0.28, + "learning_rate": 1.8074219623165195e-05, + "loss": 1.4705, + "step": 2677 + }, + { + "epoch": 0.28, + "learning_rate": 1.807205962854829e-05, + "loss": 1.5031, + "step": 2678 + }, + { + "epoch": 0.28, + "learning_rate": 1.8069898552482806e-05, + "loss": 1.4812, + "step": 2679 + }, + { + "epoch": 0.28, + "learning_rate": 1.806773639525826e-05, + "loss": 1.4129, + "step": 2680 + }, + { + "epoch": 0.28, + "learning_rate": 1.8065573157164332e-05, + "loss": 1.4559, + "step": 2681 + }, + { + "epoch": 0.28, + "learning_rate": 1.806340883849084e-05, + "loss": 1.3878, + "step": 2682 + }, + { + "epoch": 0.28, + "learning_rate": 1.8061243439527744e-05, + "loss": 1.4752, + "step": 2683 + }, + { + "epoch": 0.28, + "learning_rate": 1.8059076960565156e-05, + "loss": 1.4089, + "step": 2684 + }, + { + "epoch": 0.28, + "learning_rate": 1.8056909401893326e-05, + "loss": 1.4736, + "step": 2685 + }, + { + "epoch": 0.28, + "learning_rate": 1.8054740763802654e-05, + "loss": 1.3796, + "step": 2686 + }, + { + "epoch": 0.28, + "learning_rate": 1.805257104658368e-05, + "loss": 1.4412, + "step": 2687 + }, + { + "epoch": 0.28, + "learning_rate": 1.8050400250527086e-05, + "loss": 1.4639, + "step": 2688 + }, + { + "epoch": 0.28, + "learning_rate": 1.804822837592371e-05, + "loss": 1.4076, + "step": 2689 + }, + { + "epoch": 0.28, + "learning_rate": 1.804605542306452e-05, + "loss": 1.4627, + "step": 2690 + }, + { + "epoch": 0.28, + "learning_rate": 1.8043881392240642e-05, + "loss": 1.5249, + "step": 2691 + }, + { + "epoch": 0.28, + "learning_rate": 1.804170628374334e-05, + "loss": 1.4312, + "step": 2692 + }, + { + "epoch": 0.28, + "learning_rate": 1.803953009786402e-05, + "loss": 1.5676, + "step": 2693 + }, + { + "epoch": 0.28, + "learning_rate": 1.8037352834894233e-05, + "loss": 1.5072, + "step": 2694 + }, + { + "epoch": 0.28, + "learning_rate": 1.803517449512568e-05, + "loss": 1.5662, + "step": 2695 + }, + { + "epoch": 0.28, + "learning_rate": 1.8032995078850207e-05, + "loss": 1.4771, + "step": 2696 + }, + { + "epoch": 0.28, + "learning_rate": 1.803081458635979e-05, + "loss": 1.412, + "step": 2697 + }, + { + "epoch": 0.28, + "learning_rate": 1.8028633017946564e-05, + "loss": 1.497, + "step": 2698 + }, + { + "epoch": 0.28, + "learning_rate": 1.8026450373902804e-05, + "loss": 1.4528, + "step": 2699 + }, + { + "epoch": 0.28, + "learning_rate": 1.802426665452093e-05, + "loss": 1.4785, + "step": 2700 + }, + { + "epoch": 0.28, + "learning_rate": 1.8022081860093493e-05, + "loss": 1.6411, + "step": 2701 + }, + { + "epoch": 0.28, + "learning_rate": 1.8019895990913213e-05, + "loss": 1.4459, + "step": 2702 + }, + { + "epoch": 0.28, + "learning_rate": 1.8017709047272932e-05, + "loss": 1.4418, + "step": 2703 + }, + { + "epoch": 0.28, + "learning_rate": 1.801552102946565e-05, + "loss": 1.4409, + "step": 2704 + }, + { + "epoch": 0.28, + "learning_rate": 1.8013331937784498e-05, + "loss": 1.4651, + "step": 2705 + }, + { + "epoch": 0.28, + "learning_rate": 1.8011141772522766e-05, + "loss": 1.4161, + "step": 2706 + }, + { + "epoch": 0.28, + "learning_rate": 1.8008950533973876e-05, + "loss": 1.458, + "step": 2707 + }, + { + "epoch": 0.28, + "learning_rate": 1.8006758222431398e-05, + "loss": 1.4477, + "step": 2708 + }, + { + "epoch": 0.28, + "learning_rate": 1.800456483818904e-05, + "loss": 1.4433, + "step": 2709 + }, + { + "epoch": 0.28, + "learning_rate": 1.8002370381540672e-05, + "loss": 1.5005, + "step": 2710 + }, + { + "epoch": 0.28, + "learning_rate": 1.8000174852780282e-05, + "loss": 1.4945, + "step": 2711 + }, + { + "epoch": 0.28, + "learning_rate": 1.7997978252202023e-05, + "loss": 1.4298, + "step": 2712 + }, + { + "epoch": 0.28, + "learning_rate": 1.7995780580100177e-05, + "loss": 1.3812, + "step": 2713 + }, + { + "epoch": 0.28, + "learning_rate": 1.799358183676918e-05, + "loss": 1.5559, + "step": 2714 + }, + { + "epoch": 0.28, + "learning_rate": 1.79913820225036e-05, + "loss": 1.4316, + "step": 2715 + }, + { + "epoch": 0.28, + "learning_rate": 1.798918113759817e-05, + "loss": 1.419, + "step": 2716 + }, + { + "epoch": 0.28, + "learning_rate": 1.7986979182347733e-05, + "loss": 1.43, + "step": 2717 + }, + { + "epoch": 0.29, + "learning_rate": 1.798477615704731e-05, + "loss": 1.4964, + "step": 2718 + }, + { + "epoch": 0.29, + "learning_rate": 1.7982572061992044e-05, + "loss": 1.4417, + "step": 2719 + }, + { + "epoch": 0.29, + "learning_rate": 1.7980366897477227e-05, + "loss": 1.4562, + "step": 2720 + }, + { + "epoch": 0.29, + "learning_rate": 1.7978160663798295e-05, + "loss": 1.4386, + "step": 2721 + }, + { + "epoch": 0.29, + "learning_rate": 1.7975953361250824e-05, + "loss": 1.445, + "step": 2722 + }, + { + "epoch": 0.29, + "learning_rate": 1.797374499013054e-05, + "loss": 1.4549, + "step": 2723 + }, + { + "epoch": 0.29, + "learning_rate": 1.7971535550733305e-05, + "loss": 1.5205, + "step": 2724 + }, + { + "epoch": 0.29, + "learning_rate": 1.796932504335513e-05, + "loss": 1.4632, + "step": 2725 + }, + { + "epoch": 0.29, + "learning_rate": 1.796711346829216e-05, + "loss": 1.3767, + "step": 2726 + }, + { + "epoch": 0.29, + "learning_rate": 1.79649008258407e-05, + "loss": 1.4098, + "step": 2727 + }, + { + "epoch": 0.29, + "learning_rate": 1.7962687116297178e-05, + "loss": 1.4675, + "step": 2728 + }, + { + "epoch": 0.29, + "learning_rate": 1.7960472339958176e-05, + "loss": 1.6048, + "step": 2729 + }, + { + "epoch": 0.29, + "learning_rate": 1.7958256497120418e-05, + "loss": 1.5432, + "step": 2730 + }, + { + "epoch": 0.29, + "learning_rate": 1.7956039588080774e-05, + "loss": 1.5453, + "step": 2731 + }, + { + "epoch": 0.29, + "learning_rate": 1.7953821613136246e-05, + "loss": 1.4246, + "step": 2732 + }, + { + "epoch": 0.29, + "learning_rate": 1.7951602572583988e-05, + "loss": 1.3987, + "step": 2733 + }, + { + "epoch": 0.29, + "learning_rate": 1.7949382466721295e-05, + "loss": 1.4943, + "step": 2734 + }, + { + "epoch": 0.29, + "learning_rate": 1.7947161295845606e-05, + "loss": 1.4385, + "step": 2735 + }, + { + "epoch": 0.29, + "learning_rate": 1.7944939060254497e-05, + "loss": 1.4165, + "step": 2736 + }, + { + "epoch": 0.29, + "learning_rate": 1.7942715760245692e-05, + "loss": 1.4004, + "step": 2737 + }, + { + "epoch": 0.29, + "learning_rate": 1.7940491396117063e-05, + "loss": 1.4577, + "step": 2738 + }, + { + "epoch": 0.29, + "learning_rate": 1.7938265968166602e-05, + "loss": 1.4649, + "step": 2739 + }, + { + "epoch": 0.29, + "learning_rate": 1.7936039476692473e-05, + "loss": 1.5273, + "step": 2740 + }, + { + "epoch": 0.29, + "learning_rate": 1.7933811921992962e-05, + "loss": 1.4325, + "step": 2741 + }, + { + "epoch": 0.29, + "learning_rate": 1.793158330436651e-05, + "loss": 1.4388, + "step": 2742 + }, + { + "epoch": 0.29, + "learning_rate": 1.7929353624111687e-05, + "loss": 1.4124, + "step": 2743 + }, + { + "epoch": 0.29, + "learning_rate": 1.7927122881527222e-05, + "loss": 1.5449, + "step": 2744 + }, + { + "epoch": 0.29, + "learning_rate": 1.7924891076911964e-05, + "loss": 1.4728, + "step": 2745 + }, + { + "epoch": 0.29, + "learning_rate": 1.7922658210564932e-05, + "loss": 1.5103, + "step": 2746 + }, + { + "epoch": 0.29, + "learning_rate": 1.792042428278526e-05, + "loss": 1.5975, + "step": 2747 + }, + { + "epoch": 0.29, + "learning_rate": 1.7918189293872247e-05, + "loss": 1.567, + "step": 2748 + }, + { + "epoch": 0.29, + "learning_rate": 1.7915953244125318e-05, + "loss": 1.57, + "step": 2749 + }, + { + "epoch": 0.29, + "learning_rate": 1.791371613384405e-05, + "loss": 1.4372, + "step": 2750 + }, + { + "epoch": 0.29, + "learning_rate": 1.7911477963328155e-05, + "loss": 1.4053, + "step": 2751 + }, + { + "epoch": 0.29, + "learning_rate": 1.7909238732877492e-05, + "loss": 1.3782, + "step": 2752 + }, + { + "epoch": 0.29, + "learning_rate": 1.790699844279206e-05, + "loss": 1.4401, + "step": 2753 + }, + { + "epoch": 0.29, + "learning_rate": 1.7904757093372e-05, + "loss": 1.3749, + "step": 2754 + }, + { + "epoch": 0.29, + "learning_rate": 1.79025146849176e-05, + "loss": 1.4909, + "step": 2755 + }, + { + "epoch": 0.29, + "learning_rate": 1.7900271217729273e-05, + "loss": 1.4103, + "step": 2756 + }, + { + "epoch": 0.29, + "learning_rate": 1.7898026692107597e-05, + "loss": 1.4986, + "step": 2757 + }, + { + "epoch": 0.29, + "learning_rate": 1.7895781108353278e-05, + "loss": 1.5449, + "step": 2758 + }, + { + "epoch": 0.29, + "learning_rate": 1.789353446676717e-05, + "loss": 1.5583, + "step": 2759 + }, + { + "epoch": 0.29, + "learning_rate": 1.7891286767650254e-05, + "loss": 1.5342, + "step": 2760 + }, + { + "epoch": 0.29, + "learning_rate": 1.7889038011303673e-05, + "loss": 1.4233, + "step": 2761 + }, + { + "epoch": 0.29, + "learning_rate": 1.7886788198028707e-05, + "loss": 1.3433, + "step": 2762 + }, + { + "epoch": 0.29, + "learning_rate": 1.788453732812676e-05, + "loss": 1.4451, + "step": 2763 + }, + { + "epoch": 0.29, + "learning_rate": 1.78822854018994e-05, + "loss": 1.4506, + "step": 2764 + }, + { + "epoch": 0.29, + "learning_rate": 1.7880032419648324e-05, + "loss": 1.4386, + "step": 2765 + }, + { + "epoch": 0.29, + "learning_rate": 1.7877778381675374e-05, + "loss": 1.4512, + "step": 2766 + }, + { + "epoch": 0.29, + "learning_rate": 1.7875523288282535e-05, + "loss": 1.4319, + "step": 2767 + }, + { + "epoch": 0.29, + "learning_rate": 1.7873267139771932e-05, + "loss": 1.4753, + "step": 2768 + }, + { + "epoch": 0.29, + "learning_rate": 1.787100993644583e-05, + "loss": 1.4044, + "step": 2769 + }, + { + "epoch": 0.29, + "learning_rate": 1.786875167860663e-05, + "loss": 1.4382, + "step": 2770 + }, + { + "epoch": 0.29, + "learning_rate": 1.786649236655689e-05, + "loss": 1.3977, + "step": 2771 + }, + { + "epoch": 0.29, + "learning_rate": 1.7864232000599298e-05, + "loss": 1.4473, + "step": 2772 + }, + { + "epoch": 0.29, + "learning_rate": 1.7861970581036678e-05, + "loss": 1.4666, + "step": 2773 + }, + { + "epoch": 0.29, + "learning_rate": 1.785970810817201e-05, + "loss": 1.5299, + "step": 2774 + }, + { + "epoch": 0.29, + "learning_rate": 1.7857444582308402e-05, + "loss": 1.3974, + "step": 2775 + }, + { + "epoch": 0.29, + "learning_rate": 1.7855180003749114e-05, + "loss": 1.4603, + "step": 2776 + }, + { + "epoch": 0.29, + "learning_rate": 1.7852914372797535e-05, + "loss": 1.463, + "step": 2777 + }, + { + "epoch": 0.29, + "learning_rate": 1.7850647689757205e-05, + "loss": 1.5317, + "step": 2778 + }, + { + "epoch": 0.29, + "learning_rate": 1.78483799549318e-05, + "loss": 1.4669, + "step": 2779 + }, + { + "epoch": 0.29, + "learning_rate": 1.784611116862514e-05, + "loss": 1.5293, + "step": 2780 + }, + { + "epoch": 0.29, + "learning_rate": 1.7843841331141177e-05, + "loss": 1.5802, + "step": 2781 + }, + { + "epoch": 0.29, + "learning_rate": 1.7841570442784024e-05, + "loss": 1.4486, + "step": 2782 + }, + { + "epoch": 0.29, + "learning_rate": 1.7839298503857913e-05, + "loss": 1.4674, + "step": 2783 + }, + { + "epoch": 0.29, + "learning_rate": 1.7837025514667224e-05, + "loss": 1.4662, + "step": 2784 + }, + { + "epoch": 0.29, + "learning_rate": 1.7834751475516484e-05, + "loss": 1.3555, + "step": 2785 + }, + { + "epoch": 0.29, + "learning_rate": 1.783247638671035e-05, + "loss": 1.4307, + "step": 2786 + }, + { + "epoch": 0.29, + "eval_loss": 1.500258445739746, + "eval_runtime": 77.406, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 2786 + }, + { + "epoch": 0.29, + "learning_rate": 1.7830200248553633e-05, + "loss": 1.4596, + "step": 2787 + }, + { + "epoch": 0.29, + "learning_rate": 1.7827923061351273e-05, + "loss": 1.6118, + "step": 2788 + }, + { + "epoch": 0.29, + "learning_rate": 1.7825644825408353e-05, + "loss": 1.4782, + "step": 2789 + }, + { + "epoch": 0.29, + "learning_rate": 1.78233655410301e-05, + "loss": 1.4681, + "step": 2790 + }, + { + "epoch": 0.29, + "learning_rate": 1.782108520852188e-05, + "loss": 1.6281, + "step": 2791 + }, + { + "epoch": 0.29, + "learning_rate": 1.78188038281892e-05, + "loss": 1.4446, + "step": 2792 + }, + { + "epoch": 0.29, + "learning_rate": 1.7816521400337704e-05, + "loss": 1.479, + "step": 2793 + }, + { + "epoch": 0.29, + "learning_rate": 1.7814237925273178e-05, + "loss": 1.5457, + "step": 2794 + }, + { + "epoch": 0.29, + "learning_rate": 1.7811953403301547e-05, + "loss": 1.3928, + "step": 2795 + }, + { + "epoch": 0.29, + "learning_rate": 1.780966783472889e-05, + "loss": 1.4321, + "step": 2796 + }, + { + "epoch": 0.29, + "learning_rate": 1.78073812198614e-05, + "loss": 1.5734, + "step": 2797 + }, + { + "epoch": 0.29, + "learning_rate": 1.7805093559005432e-05, + "loss": 1.4356, + "step": 2798 + }, + { + "epoch": 0.29, + "learning_rate": 1.7802804852467473e-05, + "loss": 1.4656, + "step": 2799 + }, + { + "epoch": 0.29, + "learning_rate": 1.780051510055415e-05, + "loss": 1.4052, + "step": 2800 + }, + { + "epoch": 0.29, + "learning_rate": 1.7798224303572228e-05, + "loss": 1.4758, + "step": 2801 + }, + { + "epoch": 0.29, + "learning_rate": 1.7795932461828622e-05, + "loss": 1.4326, + "step": 2802 + }, + { + "epoch": 0.29, + "learning_rate": 1.7793639575630376e-05, + "loss": 1.3409, + "step": 2803 + }, + { + "epoch": 0.29, + "learning_rate": 1.7791345645284678e-05, + "loss": 1.4175, + "step": 2804 + }, + { + "epoch": 0.29, + "learning_rate": 1.7789050671098853e-05, + "loss": 1.383, + "step": 2805 + }, + { + "epoch": 0.29, + "learning_rate": 1.7786754653380373e-05, + "loss": 1.5162, + "step": 2806 + }, + { + "epoch": 0.29, + "learning_rate": 1.7784457592436847e-05, + "loss": 1.4899, + "step": 2807 + }, + { + "epoch": 0.29, + "learning_rate": 1.7782159488576016e-05, + "loss": 1.4874, + "step": 2808 + }, + { + "epoch": 0.29, + "learning_rate": 1.777986034210577e-05, + "loss": 1.4363, + "step": 2809 + }, + { + "epoch": 0.29, + "learning_rate": 1.7777560153334134e-05, + "loss": 1.4223, + "step": 2810 + }, + { + "epoch": 0.29, + "learning_rate": 1.7775258922569273e-05, + "loss": 1.4792, + "step": 2811 + }, + { + "epoch": 0.29, + "learning_rate": 1.77729566501195e-05, + "loss": 1.4475, + "step": 2812 + }, + { + "epoch": 0.29, + "learning_rate": 1.7770653336293253e-05, + "loss": 1.5157, + "step": 2813 + }, + { + "epoch": 0.3, + "learning_rate": 1.776834898139912e-05, + "loss": 1.389, + "step": 2814 + }, + { + "epoch": 0.3, + "learning_rate": 1.7766043585745824e-05, + "loss": 1.4358, + "step": 2815 + }, + { + "epoch": 0.3, + "learning_rate": 1.776373714964223e-05, + "loss": 1.4297, + "step": 2816 + }, + { + "epoch": 0.3, + "learning_rate": 1.7761429673397344e-05, + "loss": 1.4102, + "step": 2817 + }, + { + "epoch": 0.3, + "learning_rate": 1.77591211573203e-05, + "loss": 1.4572, + "step": 2818 + }, + { + "epoch": 0.3, + "learning_rate": 1.775681160172039e-05, + "loss": 1.448, + "step": 2819 + }, + { + "epoch": 0.3, + "learning_rate": 1.7754501006907025e-05, + "loss": 1.4426, + "step": 2820 + }, + { + "epoch": 0.3, + "learning_rate": 1.7752189373189773e-05, + "loss": 1.4566, + "step": 2821 + }, + { + "epoch": 0.3, + "learning_rate": 1.7749876700878332e-05, + "loss": 1.4267, + "step": 2822 + }, + { + "epoch": 0.3, + "learning_rate": 1.7747562990282538e-05, + "loss": 1.3951, + "step": 2823 + }, + { + "epoch": 0.3, + "learning_rate": 1.7745248241712373e-05, + "loss": 1.4668, + "step": 2824 + }, + { + "epoch": 0.3, + "learning_rate": 1.774293245547795e-05, + "loss": 1.4924, + "step": 2825 + }, + { + "epoch": 0.3, + "learning_rate": 1.7740615631889525e-05, + "loss": 1.5258, + "step": 2826 + }, + { + "epoch": 0.3, + "learning_rate": 1.7738297771257496e-05, + "loss": 1.4323, + "step": 2827 + }, + { + "epoch": 0.3, + "learning_rate": 1.7735978873892393e-05, + "loss": 1.439, + "step": 2828 + }, + { + "epoch": 0.3, + "learning_rate": 1.773365894010489e-05, + "loss": 1.5658, + "step": 2829 + }, + { + "epoch": 0.3, + "learning_rate": 1.77313379702058e-05, + "loss": 1.4607, + "step": 2830 + }, + { + "epoch": 0.3, + "learning_rate": 1.7729015964506073e-05, + "loss": 1.5544, + "step": 2831 + }, + { + "epoch": 0.3, + "learning_rate": 1.7726692923316798e-05, + "loss": 1.4232, + "step": 2832 + }, + { + "epoch": 0.3, + "learning_rate": 1.77243688469492e-05, + "loss": 1.415, + "step": 2833 + }, + { + "epoch": 0.3, + "learning_rate": 1.772204373571465e-05, + "loss": 1.4658, + "step": 2834 + }, + { + "epoch": 0.3, + "learning_rate": 1.7719717589924647e-05, + "loss": 1.4678, + "step": 2835 + }, + { + "epoch": 0.3, + "learning_rate": 1.771739040989084e-05, + "loss": 1.3021, + "step": 2836 + }, + { + "epoch": 0.3, + "learning_rate": 1.771506219592501e-05, + "loss": 1.4045, + "step": 2837 + }, + { + "epoch": 0.3, + "learning_rate": 1.7712732948339085e-05, + "loss": 1.4593, + "step": 2838 + }, + { + "epoch": 0.3, + "learning_rate": 1.7710402667445108e-05, + "loss": 1.4175, + "step": 2839 + }, + { + "epoch": 0.3, + "learning_rate": 1.770807135355529e-05, + "loss": 1.3939, + "step": 2840 + }, + { + "epoch": 0.3, + "learning_rate": 1.7705739006981963e-05, + "loss": 1.6089, + "step": 2841 + }, + { + "epoch": 0.3, + "learning_rate": 1.77034056280376e-05, + "loss": 1.3952, + "step": 2842 + }, + { + "epoch": 0.3, + "learning_rate": 1.7701071217034818e-05, + "loss": 1.5086, + "step": 2843 + }, + { + "epoch": 0.3, + "learning_rate": 1.7698735774286362e-05, + "loss": 1.4706, + "step": 2844 + }, + { + "epoch": 0.3, + "learning_rate": 1.7696399300105128e-05, + "loss": 1.4286, + "step": 2845 + }, + { + "epoch": 0.3, + "learning_rate": 1.7694061794804137e-05, + "loss": 1.4418, + "step": 2846 + }, + { + "epoch": 0.3, + "learning_rate": 1.7691723258696562e-05, + "loss": 1.516, + "step": 2847 + }, + { + "epoch": 0.3, + "learning_rate": 1.76893836920957e-05, + "loss": 1.4354, + "step": 2848 + }, + { + "epoch": 0.3, + "learning_rate": 1.7687043095314998e-05, + "loss": 1.7503, + "step": 2849 + }, + { + "epoch": 0.3, + "learning_rate": 1.7684701468668032e-05, + "loss": 1.5985, + "step": 2850 + }, + { + "epoch": 0.3, + "learning_rate": 1.768235881246852e-05, + "loss": 1.442, + "step": 2851 + }, + { + "epoch": 0.3, + "learning_rate": 1.7680015127030322e-05, + "loss": 1.4924, + "step": 2852 + }, + { + "epoch": 0.3, + "learning_rate": 1.7677670412667425e-05, + "loss": 1.4461, + "step": 2853 + }, + { + "epoch": 0.3, + "learning_rate": 1.7675324669693968e-05, + "loss": 1.3823, + "step": 2854 + }, + { + "epoch": 0.3, + "learning_rate": 1.767297789842421e-05, + "loss": 1.452, + "step": 2855 + }, + { + "epoch": 0.3, + "learning_rate": 1.767063009917257e-05, + "loss": 1.46, + "step": 2856 + }, + { + "epoch": 0.3, + "learning_rate": 1.7668281272253587e-05, + "loss": 1.4129, + "step": 2857 + }, + { + "epoch": 0.3, + "learning_rate": 1.766593141798194e-05, + "loss": 1.4057, + "step": 2858 + }, + { + "epoch": 0.3, + "learning_rate": 1.7663580536672456e-05, + "loss": 1.5162, + "step": 2859 + }, + { + "epoch": 0.3, + "learning_rate": 1.7661228628640087e-05, + "loss": 1.5177, + "step": 2860 + }, + { + "epoch": 0.3, + "learning_rate": 1.7658875694199933e-05, + "loss": 1.4548, + "step": 2861 + }, + { + "epoch": 0.3, + "learning_rate": 1.7656521733667223e-05, + "loss": 1.4511, + "step": 2862 + }, + { + "epoch": 0.3, + "learning_rate": 1.765416674735733e-05, + "loss": 1.4778, + "step": 2863 + }, + { + "epoch": 0.3, + "learning_rate": 1.765181073558576e-05, + "loss": 1.3935, + "step": 2864 + }, + { + "epoch": 0.3, + "learning_rate": 1.7649453698668156e-05, + "loss": 1.4659, + "step": 2865 + }, + { + "epoch": 0.3, + "learning_rate": 1.7647095636920305e-05, + "loss": 1.7042, + "step": 2866 + }, + { + "epoch": 0.3, + "learning_rate": 1.7644736550658124e-05, + "loss": 1.7957, + "step": 2867 + }, + { + "epoch": 0.3, + "learning_rate": 1.764237644019767e-05, + "loss": 1.5139, + "step": 2868 + }, + { + "epoch": 0.3, + "learning_rate": 1.764001530585514e-05, + "loss": 1.4117, + "step": 2869 + }, + { + "epoch": 0.3, + "learning_rate": 1.7637653147946858e-05, + "loss": 1.4837, + "step": 2870 + }, + { + "epoch": 0.3, + "learning_rate": 1.7635289966789298e-05, + "loss": 1.4379, + "step": 2871 + }, + { + "epoch": 0.3, + "learning_rate": 1.7632925762699068e-05, + "loss": 1.4491, + "step": 2872 + }, + { + "epoch": 0.3, + "learning_rate": 1.7630560535992905e-05, + "loss": 1.4006, + "step": 2873 + }, + { + "epoch": 0.3, + "learning_rate": 1.7628194286987694e-05, + "loss": 1.5484, + "step": 2874 + }, + { + "epoch": 0.3, + "learning_rate": 1.7625827016000446e-05, + "loss": 1.4926, + "step": 2875 + }, + { + "epoch": 0.3, + "learning_rate": 1.762345872334832e-05, + "loss": 1.3909, + "step": 2876 + }, + { + "epoch": 0.3, + "learning_rate": 1.76210894093486e-05, + "loss": 1.405, + "step": 2877 + }, + { + "epoch": 0.3, + "learning_rate": 1.7618719074318718e-05, + "loss": 1.4736, + "step": 2878 + }, + { + "epoch": 0.3, + "learning_rate": 1.7616347718576238e-05, + "loss": 1.4445, + "step": 2879 + }, + { + "epoch": 0.3, + "learning_rate": 1.761397534243886e-05, + "loss": 1.4878, + "step": 2880 + }, + { + "epoch": 0.3, + "learning_rate": 1.7611601946224417e-05, + "loss": 1.4414, + "step": 2881 + }, + { + "epoch": 0.3, + "learning_rate": 1.760922753025089e-05, + "loss": 1.5657, + "step": 2882 + }, + { + "epoch": 0.3, + "learning_rate": 1.7606852094836385e-05, + "loss": 1.5008, + "step": 2883 + }, + { + "epoch": 0.3, + "learning_rate": 1.7604475640299153e-05, + "loss": 1.4922, + "step": 2884 + }, + { + "epoch": 0.3, + "learning_rate": 1.7602098166957577e-05, + "loss": 1.7451, + "step": 2885 + }, + { + "epoch": 0.3, + "learning_rate": 1.759971967513017e-05, + "loss": 1.7077, + "step": 2886 + }, + { + "epoch": 0.3, + "learning_rate": 1.75973401651356e-05, + "loss": 1.3986, + "step": 2887 + }, + { + "epoch": 0.3, + "learning_rate": 1.7594959637292656e-05, + "loss": 1.3966, + "step": 2888 + }, + { + "epoch": 0.3, + "learning_rate": 1.7592578091920264e-05, + "loss": 1.4086, + "step": 2889 + }, + { + "epoch": 0.3, + "learning_rate": 1.7590195529337495e-05, + "loss": 1.4481, + "step": 2890 + }, + { + "epoch": 0.3, + "learning_rate": 1.7587811949863548e-05, + "loss": 1.3974, + "step": 2891 + }, + { + "epoch": 0.3, + "learning_rate": 1.7585427353817758e-05, + "loss": 1.5013, + "step": 2892 + }, + { + "epoch": 0.3, + "learning_rate": 1.7583041741519608e-05, + "loss": 1.5454, + "step": 2893 + }, + { + "epoch": 0.3, + "learning_rate": 1.7580655113288708e-05, + "loss": 1.5033, + "step": 2894 + }, + { + "epoch": 0.3, + "learning_rate": 1.7578267469444793e-05, + "loss": 1.4332, + "step": 2895 + }, + { + "epoch": 0.3, + "learning_rate": 1.757587881030776e-05, + "loss": 1.4667, + "step": 2896 + }, + { + "epoch": 0.3, + "learning_rate": 1.7573489136197623e-05, + "loss": 1.4314, + "step": 2897 + }, + { + "epoch": 0.3, + "learning_rate": 1.7571098447434532e-05, + "loss": 1.4514, + "step": 2898 + }, + { + "epoch": 0.3, + "learning_rate": 1.7568706744338784e-05, + "loss": 1.4872, + "step": 2899 + }, + { + "epoch": 0.3, + "learning_rate": 1.7566314027230808e-05, + "loss": 1.4841, + "step": 2900 + }, + { + "epoch": 0.3, + "learning_rate": 1.7563920296431158e-05, + "loss": 1.3964, + "step": 2901 + }, + { + "epoch": 0.3, + "learning_rate": 1.7561525552260538e-05, + "loss": 1.4932, + "step": 2902 + }, + { + "epoch": 0.3, + "learning_rate": 1.755912979503978e-05, + "loss": 1.4153, + "step": 2903 + }, + { + "epoch": 0.3, + "learning_rate": 1.755673302508986e-05, + "loss": 1.4939, + "step": 2904 + }, + { + "epoch": 0.3, + "learning_rate": 1.755433524273187e-05, + "loss": 1.4437, + "step": 2905 + }, + { + "epoch": 0.3, + "learning_rate": 1.7551936448287067e-05, + "loss": 1.486, + "step": 2906 + }, + { + "epoch": 0.3, + "learning_rate": 1.754953664207682e-05, + "loss": 1.4362, + "step": 2907 + }, + { + "epoch": 0.3, + "learning_rate": 1.7547135824422635e-05, + "loss": 1.4954, + "step": 2908 + }, + { + "epoch": 0.31, + "learning_rate": 1.7544733995646174e-05, + "loss": 1.4552, + "step": 2909 + }, + { + "epoch": 0.31, + "learning_rate": 1.7542331156069213e-05, + "loss": 1.4654, + "step": 2910 + }, + { + "epoch": 0.31, + "learning_rate": 1.753992730601367e-05, + "loss": 1.4531, + "step": 2911 + }, + { + "epoch": 0.31, + "learning_rate": 1.75375224458016e-05, + "loss": 1.4949, + "step": 2912 + }, + { + "epoch": 0.31, + "learning_rate": 1.753511657575519e-05, + "loss": 1.3998, + "step": 2913 + }, + { + "epoch": 0.31, + "learning_rate": 1.753270969619677e-05, + "loss": 1.3904, + "step": 2914 + }, + { + "epoch": 0.31, + "learning_rate": 1.7530301807448794e-05, + "loss": 1.481, + "step": 2915 + }, + { + "epoch": 0.31, + "learning_rate": 1.7527892909833864e-05, + "loss": 1.4301, + "step": 2916 + }, + { + "epoch": 0.31, + "learning_rate": 1.7525483003674707e-05, + "loss": 1.4377, + "step": 2917 + }, + { + "epoch": 0.31, + "learning_rate": 1.7523072089294188e-05, + "loss": 1.5077, + "step": 2918 + }, + { + "epoch": 0.31, + "learning_rate": 1.752066016701531e-05, + "loss": 1.3802, + "step": 2919 + }, + { + "epoch": 0.31, + "learning_rate": 1.7518247237161205e-05, + "loss": 1.3991, + "step": 2920 + }, + { + "epoch": 0.31, + "learning_rate": 1.7515833300055146e-05, + "loss": 1.4283, + "step": 2921 + }, + { + "epoch": 0.31, + "learning_rate": 1.7513418356020535e-05, + "loss": 1.3688, + "step": 2922 + }, + { + "epoch": 0.31, + "learning_rate": 1.751100240538092e-05, + "loss": 1.4336, + "step": 2923 + }, + { + "epoch": 0.31, + "learning_rate": 1.7508585448459967e-05, + "loss": 1.4302, + "step": 2924 + }, + { + "epoch": 0.31, + "learning_rate": 1.7506167485581493e-05, + "loss": 1.4293, + "step": 2925 + }, + { + "epoch": 0.31, + "learning_rate": 1.750374851706944e-05, + "loss": 1.4262, + "step": 2926 + }, + { + "epoch": 0.31, + "learning_rate": 1.7501328543247892e-05, + "loss": 1.4128, + "step": 2927 + }, + { + "epoch": 0.31, + "learning_rate": 1.7498907564441054e-05, + "loss": 1.4258, + "step": 2928 + }, + { + "epoch": 0.31, + "learning_rate": 1.749648558097328e-05, + "loss": 1.4904, + "step": 2929 + }, + { + "epoch": 0.31, + "learning_rate": 1.749406259316906e-05, + "loss": 1.4628, + "step": 2930 + }, + { + "epoch": 0.31, + "learning_rate": 1.7491638601353004e-05, + "loss": 1.4908, + "step": 2931 + }, + { + "epoch": 0.31, + "learning_rate": 1.7489213605849867e-05, + "loss": 1.4563, + "step": 2932 + }, + { + "epoch": 0.31, + "learning_rate": 1.7486787606984533e-05, + "loss": 1.5006, + "step": 2933 + }, + { + "epoch": 0.31, + "learning_rate": 1.748436060508203e-05, + "loss": 1.424, + "step": 2934 + }, + { + "epoch": 0.31, + "learning_rate": 1.7481932600467508e-05, + "loss": 1.4136, + "step": 2935 + }, + { + "epoch": 0.31, + "learning_rate": 1.747950359346626e-05, + "loss": 1.3835, + "step": 2936 + }, + { + "epoch": 0.31, + "learning_rate": 1.747707358440371e-05, + "loss": 1.5284, + "step": 2937 + }, + { + "epoch": 0.31, + "learning_rate": 1.7474642573605418e-05, + "loss": 1.4592, + "step": 2938 + }, + { + "epoch": 0.31, + "learning_rate": 1.7472210561397075e-05, + "loss": 1.5483, + "step": 2939 + }, + { + "epoch": 0.31, + "learning_rate": 1.746977754810451e-05, + "loss": 1.521, + "step": 2940 + }, + { + "epoch": 0.31, + "learning_rate": 1.7467343534053683e-05, + "loss": 1.4276, + "step": 2941 + }, + { + "epoch": 0.31, + "learning_rate": 1.746490851957069e-05, + "loss": 1.4302, + "step": 2942 + }, + { + "epoch": 0.31, + "learning_rate": 1.746247250498176e-05, + "loss": 1.4439, + "step": 2943 + }, + { + "epoch": 0.31, + "learning_rate": 1.7460035490613255e-05, + "loss": 1.4991, + "step": 2944 + }, + { + "epoch": 0.31, + "learning_rate": 1.7457597476791674e-05, + "loss": 1.4188, + "step": 2945 + }, + { + "epoch": 0.31, + "learning_rate": 1.7455158463843648e-05, + "loss": 1.4685, + "step": 2946 + }, + { + "epoch": 0.31, + "learning_rate": 1.745271845209594e-05, + "loss": 1.3811, + "step": 2947 + }, + { + "epoch": 0.31, + "learning_rate": 1.7450277441875454e-05, + "loss": 1.4869, + "step": 2948 + }, + { + "epoch": 0.31, + "learning_rate": 1.7447835433509218e-05, + "loss": 1.5001, + "step": 2949 + }, + { + "epoch": 0.31, + "learning_rate": 1.74453924273244e-05, + "loss": 1.4757, + "step": 2950 + }, + { + "epoch": 0.31, + "learning_rate": 1.74429484236483e-05, + "loss": 1.5072, + "step": 2951 + }, + { + "epoch": 0.31, + "learning_rate": 1.744050342280835e-05, + "loss": 1.4242, + "step": 2952 + }, + { + "epoch": 0.31, + "learning_rate": 1.743805742513212e-05, + "loss": 1.4462, + "step": 2953 + }, + { + "epoch": 0.31, + "learning_rate": 1.743561043094731e-05, + "loss": 1.6815, + "step": 2954 + }, + { + "epoch": 0.31, + "learning_rate": 1.7433162440581755e-05, + "loss": 1.427, + "step": 2955 + }, + { + "epoch": 0.31, + "learning_rate": 1.7430713454363423e-05, + "loss": 1.2933, + "step": 2956 + }, + { + "epoch": 0.31, + "learning_rate": 1.742826347262041e-05, + "loss": 1.4247, + "step": 2957 + }, + { + "epoch": 0.31, + "learning_rate": 1.7425812495680955e-05, + "loss": 1.399, + "step": 2958 + }, + { + "epoch": 0.31, + "learning_rate": 1.742336052387343e-05, + "loss": 1.4818, + "step": 2959 + }, + { + "epoch": 0.31, + "learning_rate": 1.742090755752633e-05, + "loss": 1.3839, + "step": 2960 + }, + { + "epoch": 0.31, + "learning_rate": 1.741845359696829e-05, + "loss": 1.4669, + "step": 2961 + }, + { + "epoch": 0.31, + "learning_rate": 1.741599864252808e-05, + "loss": 1.468, + "step": 2962 + }, + { + "epoch": 0.31, + "learning_rate": 1.74135426945346e-05, + "loss": 1.4135, + "step": 2963 + }, + { + "epoch": 0.31, + "learning_rate": 1.7411085753316882e-05, + "loss": 1.5899, + "step": 2964 + }, + { + "epoch": 0.31, + "learning_rate": 1.74086278192041e-05, + "loss": 1.6115, + "step": 2965 + }, + { + "epoch": 0.31, + "learning_rate": 1.740616889252554e-05, + "loss": 1.3988, + "step": 2966 + }, + { + "epoch": 0.31, + "learning_rate": 1.740370897361065e-05, + "loss": 1.5001, + "step": 2967 + }, + { + "epoch": 0.31, + "learning_rate": 1.740124806278899e-05, + "loss": 1.459, + "step": 2968 + }, + { + "epoch": 0.31, + "learning_rate": 1.7398786160390258e-05, + "loss": 1.4489, + "step": 2969 + }, + { + "epoch": 0.31, + "learning_rate": 1.7396323266744283e-05, + "loss": 1.4397, + "step": 2970 + }, + { + "epoch": 0.31, + "learning_rate": 1.7393859382181033e-05, + "loss": 1.4687, + "step": 2971 + }, + { + "epoch": 0.31, + "learning_rate": 1.7391394507030606e-05, + "loss": 1.4495, + "step": 2972 + }, + { + "epoch": 0.31, + "learning_rate": 1.738892864162323e-05, + "loss": 1.4745, + "step": 2973 + }, + { + "epoch": 0.31, + "learning_rate": 1.7386461786289274e-05, + "loss": 1.3943, + "step": 2974 + }, + { + "epoch": 0.31, + "learning_rate": 1.738399394135922e-05, + "loss": 1.4595, + "step": 2975 + }, + { + "epoch": 0.31, + "learning_rate": 1.738152510716371e-05, + "loss": 1.4023, + "step": 2976 + }, + { + "epoch": 0.31, + "learning_rate": 1.7379055284033493e-05, + "loss": 1.3938, + "step": 2977 + }, + { + "epoch": 0.31, + "learning_rate": 1.7376584472299468e-05, + "loss": 1.4576, + "step": 2978 + }, + { + "epoch": 0.31, + "learning_rate": 1.737411267229266e-05, + "loss": 1.424, + "step": 2979 + }, + { + "epoch": 0.31, + "learning_rate": 1.7371639884344225e-05, + "loss": 1.4224, + "step": 2980 + }, + { + "epoch": 0.31, + "learning_rate": 1.736916610878545e-05, + "loss": 1.4228, + "step": 2981 + }, + { + "epoch": 0.31, + "learning_rate": 1.7366691345947768e-05, + "loss": 1.5021, + "step": 2982 + }, + { + "epoch": 0.31, + "learning_rate": 1.736421559616272e-05, + "loss": 1.3589, + "step": 2983 + }, + { + "epoch": 0.31, + "learning_rate": 1.7361738859762007e-05, + "loss": 1.4748, + "step": 2984 + }, + { + "epoch": 0.31, + "learning_rate": 1.735926113707743e-05, + "loss": 1.3974, + "step": 2985 + }, + { + "epoch": 0.31, + "eval_loss": 1.4849082231521606, + "eval_runtime": 77.3271, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2985 + }, + { + "epoch": 0.31, + "learning_rate": 1.735678242844096e-05, + "loss": 1.392, + "step": 2986 + }, + { + "epoch": 0.31, + "learning_rate": 1.735430273418467e-05, + "loss": 1.4277, + "step": 2987 + }, + { + "epoch": 0.31, + "learning_rate": 1.735182205464077e-05, + "loss": 1.4216, + "step": 2988 + }, + { + "epoch": 0.31, + "learning_rate": 1.7349340390141617e-05, + "loss": 1.4546, + "step": 2989 + }, + { + "epoch": 0.31, + "learning_rate": 1.734685774101969e-05, + "loss": 1.4264, + "step": 2990 + }, + { + "epoch": 0.31, + "learning_rate": 1.7344374107607593e-05, + "loss": 1.4307, + "step": 2991 + }, + { + "epoch": 0.31, + "learning_rate": 1.7341889490238076e-05, + "loss": 1.4266, + "step": 2992 + }, + { + "epoch": 0.31, + "learning_rate": 1.7339403889244008e-05, + "loss": 1.4486, + "step": 2993 + }, + { + "epoch": 0.31, + "learning_rate": 1.7336917304958403e-05, + "loss": 1.4345, + "step": 2994 + }, + { + "epoch": 0.31, + "learning_rate": 1.7334429737714395e-05, + "loss": 1.476, + "step": 2995 + }, + { + "epoch": 0.31, + "learning_rate": 1.7331941187845248e-05, + "loss": 1.5148, + "step": 2996 + }, + { + "epoch": 0.31, + "learning_rate": 1.7329451655684372e-05, + "loss": 1.4026, + "step": 2997 + }, + { + "epoch": 0.31, + "learning_rate": 1.7326961141565303e-05, + "loss": 1.3935, + "step": 2998 + }, + { + "epoch": 0.31, + "learning_rate": 1.73244696458217e-05, + "loss": 1.4483, + "step": 2999 + }, + { + "epoch": 0.31, + "learning_rate": 1.7321977168787356e-05, + "loss": 1.5197, + "step": 3000 + }, + { + "epoch": 0.31, + "learning_rate": 1.7319483710796208e-05, + "loss": 1.4648, + "step": 3001 + }, + { + "epoch": 0.31, + "learning_rate": 1.7316989272182308e-05, + "loss": 1.4171, + "step": 3002 + }, + { + "epoch": 0.31, + "learning_rate": 1.731449385327985e-05, + "loss": 1.4541, + "step": 3003 + }, + { + "epoch": 0.32, + "learning_rate": 1.731199745442316e-05, + "loss": 1.4605, + "step": 3004 + }, + { + "epoch": 0.32, + "learning_rate": 1.7309500075946683e-05, + "loss": 1.5122, + "step": 3005 + }, + { + "epoch": 0.32, + "learning_rate": 1.7307001718185007e-05, + "loss": 1.5243, + "step": 3006 + }, + { + "epoch": 0.32, + "learning_rate": 1.7304502381472844e-05, + "loss": 1.4997, + "step": 3007 + }, + { + "epoch": 0.32, + "learning_rate": 1.730200206614505e-05, + "loss": 1.4891, + "step": 3008 + }, + { + "epoch": 0.32, + "learning_rate": 1.72995007725366e-05, + "loss": 1.4376, + "step": 3009 + }, + { + "epoch": 0.32, + "learning_rate": 1.7296998500982595e-05, + "loss": 1.4403, + "step": 3010 + }, + { + "epoch": 0.32, + "learning_rate": 1.7294495251818285e-05, + "loss": 1.5153, + "step": 3011 + }, + { + "epoch": 0.32, + "learning_rate": 1.729199102537904e-05, + "loss": 1.4996, + "step": 3012 + }, + { + "epoch": 0.32, + "learning_rate": 1.7289485822000356e-05, + "loss": 1.5302, + "step": 3013 + }, + { + "epoch": 0.32, + "learning_rate": 1.7286979642017867e-05, + "loss": 1.5641, + "step": 3014 + }, + { + "epoch": 0.32, + "learning_rate": 1.728447248576734e-05, + "loss": 1.438, + "step": 3015 + }, + { + "epoch": 0.32, + "learning_rate": 1.7281964353584674e-05, + "loss": 1.4796, + "step": 3016 + }, + { + "epoch": 0.32, + "learning_rate": 1.727945524580588e-05, + "loss": 1.4413, + "step": 3017 + }, + { + "epoch": 0.32, + "learning_rate": 1.727694516276713e-05, + "loss": 1.3966, + "step": 3018 + }, + { + "epoch": 0.32, + "learning_rate": 1.72744341048047e-05, + "loss": 1.5267, + "step": 3019 + }, + { + "epoch": 0.32, + "learning_rate": 1.727192207225501e-05, + "loss": 1.4284, + "step": 3020 + }, + { + "epoch": 0.32, + "learning_rate": 1.726940906545461e-05, + "loss": 1.5137, + "step": 3021 + }, + { + "epoch": 0.32, + "learning_rate": 1.7266895084740173e-05, + "loss": 1.3966, + "step": 3022 + }, + { + "epoch": 0.32, + "learning_rate": 1.7264380130448514e-05, + "loss": 1.4156, + "step": 3023 + }, + { + "epoch": 0.32, + "learning_rate": 1.726186420291657e-05, + "loss": 1.4644, + "step": 3024 + }, + { + "epoch": 0.32, + "learning_rate": 1.725934730248141e-05, + "loss": 1.4768, + "step": 3025 + }, + { + "epoch": 0.32, + "learning_rate": 1.7256829429480233e-05, + "loss": 1.4428, + "step": 3026 + }, + { + "epoch": 0.32, + "learning_rate": 1.7254310584250373e-05, + "loss": 1.4495, + "step": 3027 + }, + { + "epoch": 0.32, + "learning_rate": 1.725179076712929e-05, + "loss": 1.3867, + "step": 3028 + }, + { + "epoch": 0.32, + "learning_rate": 1.7249269978454567e-05, + "loss": 1.5011, + "step": 3029 + }, + { + "epoch": 0.32, + "learning_rate": 1.7246748218563937e-05, + "loss": 1.3916, + "step": 3030 + }, + { + "epoch": 0.32, + "learning_rate": 1.7244225487795238e-05, + "loss": 1.4984, + "step": 3031 + }, + { + "epoch": 0.32, + "learning_rate": 1.7241701786486464e-05, + "loss": 1.5776, + "step": 3032 + }, + { + "epoch": 0.32, + "learning_rate": 1.7239177114975717e-05, + "loss": 1.5018, + "step": 3033 + }, + { + "epoch": 0.32, + "learning_rate": 1.7236651473601244e-05, + "loss": 1.5042, + "step": 3034 + }, + { + "epoch": 0.32, + "learning_rate": 1.723412486270141e-05, + "loss": 1.4636, + "step": 3035 + }, + { + "epoch": 0.32, + "learning_rate": 1.723159728261472e-05, + "loss": 1.5612, + "step": 3036 + }, + { + "epoch": 0.32, + "learning_rate": 1.7229068733679803e-05, + "loss": 1.4399, + "step": 3037 + }, + { + "epoch": 0.32, + "learning_rate": 1.7226539216235424e-05, + "loss": 1.5635, + "step": 3038 + }, + { + "epoch": 0.32, + "learning_rate": 1.7224008730620468e-05, + "loss": 1.4329, + "step": 3039 + }, + { + "epoch": 0.32, + "learning_rate": 1.7221477277173956e-05, + "loss": 1.4886, + "step": 3040 + }, + { + "epoch": 0.32, + "learning_rate": 1.721894485623504e-05, + "loss": 1.4741, + "step": 3041 + }, + { + "epoch": 0.32, + "learning_rate": 1.7216411468143e-05, + "loss": 1.4678, + "step": 3042 + }, + { + "epoch": 0.32, + "learning_rate": 1.721387711323724e-05, + "loss": 1.4758, + "step": 3043 + }, + { + "epoch": 0.32, + "learning_rate": 1.72113417918573e-05, + "loss": 1.441, + "step": 3044 + }, + { + "epoch": 0.32, + "learning_rate": 1.7208805504342855e-05, + "loss": 1.4328, + "step": 3045 + }, + { + "epoch": 0.32, + "learning_rate": 1.720626825103369e-05, + "loss": 1.4254, + "step": 3046 + }, + { + "epoch": 0.32, + "learning_rate": 1.7203730032269744e-05, + "loss": 1.4462, + "step": 3047 + }, + { + "epoch": 0.32, + "learning_rate": 1.7201190848391066e-05, + "loss": 1.4826, + "step": 3048 + }, + { + "epoch": 0.32, + "learning_rate": 1.719865069973784e-05, + "loss": 1.4215, + "step": 3049 + }, + { + "epoch": 0.32, + "learning_rate": 1.7196109586650385e-05, + "loss": 1.4291, + "step": 3050 + }, + { + "epoch": 0.32, + "learning_rate": 1.7193567509469146e-05, + "loss": 1.5005, + "step": 3051 + }, + { + "epoch": 0.32, + "learning_rate": 1.719102446853469e-05, + "loss": 1.4216, + "step": 3052 + }, + { + "epoch": 0.32, + "learning_rate": 1.7188480464187725e-05, + "loss": 1.4349, + "step": 3053 + }, + { + "epoch": 0.32, + "learning_rate": 1.718593549676908e-05, + "loss": 1.4784, + "step": 3054 + }, + { + "epoch": 0.32, + "learning_rate": 1.7183389566619714e-05, + "loss": 1.4325, + "step": 3055 + }, + { + "epoch": 0.32, + "learning_rate": 1.7180842674080717e-05, + "loss": 1.5387, + "step": 3056 + }, + { + "epoch": 0.32, + "learning_rate": 1.717829481949331e-05, + "loss": 1.655, + "step": 3057 + }, + { + "epoch": 0.32, + "learning_rate": 1.717574600319883e-05, + "loss": 1.4623, + "step": 3058 + }, + { + "epoch": 0.32, + "learning_rate": 1.7173196225538768e-05, + "loss": 1.4646, + "step": 3059 + }, + { + "epoch": 0.32, + "learning_rate": 1.717064548685472e-05, + "loss": 1.4641, + "step": 3060 + }, + { + "epoch": 0.32, + "learning_rate": 1.7168093787488418e-05, + "loss": 1.4033, + "step": 3061 + }, + { + "epoch": 0.32, + "learning_rate": 1.7165541127781726e-05, + "loss": 1.4085, + "step": 3062 + }, + { + "epoch": 0.32, + "learning_rate": 1.716298750807664e-05, + "loss": 1.387, + "step": 3063 + }, + { + "epoch": 0.32, + "learning_rate": 1.7160432928715272e-05, + "loss": 1.4197, + "step": 3064 + }, + { + "epoch": 0.32, + "learning_rate": 1.7157877390039872e-05, + "loss": 1.4883, + "step": 3065 + }, + { + "epoch": 0.32, + "learning_rate": 1.7155320892392818e-05, + "loss": 1.4865, + "step": 3066 + }, + { + "epoch": 0.32, + "learning_rate": 1.715276343611662e-05, + "loss": 1.4532, + "step": 3067 + }, + { + "epoch": 0.32, + "learning_rate": 1.71502050215539e-05, + "loss": 1.3991, + "step": 3068 + }, + { + "epoch": 0.32, + "learning_rate": 1.7147645649047424e-05, + "loss": 1.4318, + "step": 3069 + }, + { + "epoch": 0.32, + "learning_rate": 1.714508531894009e-05, + "loss": 1.3616, + "step": 3070 + }, + { + "epoch": 0.32, + "learning_rate": 1.7142524031574904e-05, + "loss": 1.4481, + "step": 3071 + }, + { + "epoch": 0.32, + "learning_rate": 1.7139961787295022e-05, + "loss": 1.3897, + "step": 3072 + }, + { + "epoch": 0.32, + "learning_rate": 1.7137398586443716e-05, + "loss": 1.3128, + "step": 3073 + }, + { + "epoch": 0.32, + "learning_rate": 1.713483442936439e-05, + "loss": 1.4481, + "step": 3074 + }, + { + "epoch": 0.32, + "learning_rate": 1.713226931640057e-05, + "loss": 1.5374, + "step": 3075 + }, + { + "epoch": 0.32, + "learning_rate": 1.7129703247895923e-05, + "loss": 1.4247, + "step": 3076 + }, + { + "epoch": 0.32, + "learning_rate": 1.712713622419423e-05, + "loss": 1.4098, + "step": 3077 + }, + { + "epoch": 0.32, + "learning_rate": 1.7124568245639414e-05, + "loss": 1.4558, + "step": 3078 + }, + { + "epoch": 0.32, + "learning_rate": 1.7121999312575507e-05, + "loss": 1.4484, + "step": 3079 + }, + { + "epoch": 0.32, + "learning_rate": 1.711942942534669e-05, + "loss": 1.4236, + "step": 3080 + }, + { + "epoch": 0.32, + "learning_rate": 1.7116858584297253e-05, + "loss": 1.613, + "step": 3081 + }, + { + "epoch": 0.32, + "learning_rate": 1.711428678977163e-05, + "loss": 1.4503, + "step": 3082 + }, + { + "epoch": 0.32, + "learning_rate": 1.7111714042114376e-05, + "loss": 1.4072, + "step": 3083 + }, + { + "epoch": 0.32, + "learning_rate": 1.7109140341670168e-05, + "loss": 1.5999, + "step": 3084 + }, + { + "epoch": 0.32, + "learning_rate": 1.7106565688783815e-05, + "loss": 1.4129, + "step": 3085 + }, + { + "epoch": 0.32, + "learning_rate": 1.710399008380026e-05, + "loss": 1.3973, + "step": 3086 + }, + { + "epoch": 0.32, + "learning_rate": 1.710141352706456e-05, + "loss": 1.4292, + "step": 3087 + }, + { + "epoch": 0.32, + "learning_rate": 1.709883601892192e-05, + "loss": 1.4372, + "step": 3088 + }, + { + "epoch": 0.32, + "learning_rate": 1.7096257559717647e-05, + "loss": 1.4924, + "step": 3089 + }, + { + "epoch": 0.32, + "learning_rate": 1.7093678149797196e-05, + "loss": 1.4222, + "step": 3090 + }, + { + "epoch": 0.32, + "learning_rate": 1.7091097789506137e-05, + "loss": 1.4797, + "step": 3091 + }, + { + "epoch": 0.32, + "learning_rate": 1.7088516479190175e-05, + "loss": 1.4738, + "step": 3092 + }, + { + "epoch": 0.32, + "learning_rate": 1.708593421919514e-05, + "loss": 1.5371, + "step": 3093 + }, + { + "epoch": 0.32, + "learning_rate": 1.7083351009866988e-05, + "loss": 1.3802, + "step": 3094 + }, + { + "epoch": 0.32, + "learning_rate": 1.7080766851551795e-05, + "loss": 1.4292, + "step": 3095 + }, + { + "epoch": 0.32, + "learning_rate": 1.707818174459578e-05, + "loss": 1.4478, + "step": 3096 + }, + { + "epoch": 0.32, + "learning_rate": 1.7075595689345285e-05, + "loss": 1.4619, + "step": 3097 + }, + { + "epoch": 0.32, + "learning_rate": 1.7073008686146763e-05, + "loss": 1.4603, + "step": 3098 + }, + { + "epoch": 0.32, + "learning_rate": 1.7070420735346815e-05, + "loss": 1.4548, + "step": 3099 + }, + { + "epoch": 0.33, + "learning_rate": 1.7067831837292157e-05, + "loss": 1.3638, + "step": 3100 + }, + { + "epoch": 0.33, + "learning_rate": 1.7065241992329634e-05, + "loss": 1.4284, + "step": 3101 + }, + { + "epoch": 0.33, + "learning_rate": 1.7062651200806217e-05, + "loss": 1.386, + "step": 3102 + }, + { + "epoch": 0.33, + "learning_rate": 1.7060059463069013e-05, + "loss": 1.5483, + "step": 3103 + }, + { + "epoch": 0.33, + "learning_rate": 1.705746677946524e-05, + "loss": 1.4963, + "step": 3104 + }, + { + "epoch": 0.33, + "learning_rate": 1.7054873150342257e-05, + "loss": 1.4539, + "step": 3105 + }, + { + "epoch": 0.33, + "learning_rate": 1.705227857604754e-05, + "loss": 1.4361, + "step": 3106 + }, + { + "epoch": 0.33, + "learning_rate": 1.7049683056928695e-05, + "loss": 1.3735, + "step": 3107 + }, + { + "epoch": 0.33, + "learning_rate": 1.7047086593333454e-05, + "loss": 1.4324, + "step": 3108 + }, + { + "epoch": 0.33, + "learning_rate": 1.7044489185609685e-05, + "loss": 1.5037, + "step": 3109 + }, + { + "epoch": 0.33, + "learning_rate": 1.704189083410536e-05, + "loss": 1.3913, + "step": 3110 + }, + { + "epoch": 0.33, + "learning_rate": 1.7039291539168604e-05, + "loss": 1.3233, + "step": 3111 + }, + { + "epoch": 0.33, + "learning_rate": 1.703669130114765e-05, + "loss": 1.4897, + "step": 3112 + }, + { + "epoch": 0.33, + "learning_rate": 1.7034090120390862e-05, + "loss": 1.4843, + "step": 3113 + }, + { + "epoch": 0.33, + "learning_rate": 1.7031487997246735e-05, + "loss": 1.3674, + "step": 3114 + }, + { + "epoch": 0.33, + "learning_rate": 1.7028884932063883e-05, + "loss": 1.4475, + "step": 3115 + }, + { + "epoch": 0.33, + "learning_rate": 1.702628092519105e-05, + "loss": 1.4134, + "step": 3116 + }, + { + "epoch": 0.33, + "learning_rate": 1.7023675976977108e-05, + "loss": 1.4484, + "step": 3117 + }, + { + "epoch": 0.33, + "learning_rate": 1.702107008777106e-05, + "loss": 1.407, + "step": 3118 + }, + { + "epoch": 0.33, + "learning_rate": 1.7018463257922005e-05, + "loss": 1.5443, + "step": 3119 + }, + { + "epoch": 0.33, + "learning_rate": 1.701585548777922e-05, + "loss": 1.4548, + "step": 3120 + }, + { + "epoch": 0.33, + "learning_rate": 1.7013246777692063e-05, + "loss": 1.4252, + "step": 3121 + }, + { + "epoch": 0.33, + "learning_rate": 1.7010637128010037e-05, + "loss": 1.3748, + "step": 3122 + }, + { + "epoch": 0.33, + "learning_rate": 1.7008026539082767e-05, + "loss": 1.3804, + "step": 3123 + }, + { + "epoch": 0.33, + "learning_rate": 1.7005415011260008e-05, + "loss": 1.4203, + "step": 3124 + }, + { + "epoch": 0.33, + "learning_rate": 1.7002802544891634e-05, + "loss": 1.4195, + "step": 3125 + }, + { + "epoch": 0.33, + "learning_rate": 1.700018914032765e-05, + "loss": 1.4188, + "step": 3126 + }, + { + "epoch": 0.33, + "learning_rate": 1.699757479791819e-05, + "loss": 1.3884, + "step": 3127 + }, + { + "epoch": 0.33, + "learning_rate": 1.6994959518013502e-05, + "loss": 1.4111, + "step": 3128 + }, + { + "epoch": 0.33, + "learning_rate": 1.6992343300963963e-05, + "loss": 1.5452, + "step": 3129 + }, + { + "epoch": 0.33, + "learning_rate": 1.6989726147120087e-05, + "loss": 1.4097, + "step": 3130 + }, + { + "epoch": 0.33, + "learning_rate": 1.6987108056832506e-05, + "loss": 1.481, + "step": 3131 + }, + { + "epoch": 0.33, + "learning_rate": 1.6984489030451973e-05, + "loss": 1.4505, + "step": 3132 + }, + { + "epoch": 0.33, + "learning_rate": 1.6981869068329368e-05, + "loss": 1.4281, + "step": 3133 + }, + { + "epoch": 0.33, + "learning_rate": 1.69792481708157e-05, + "loss": 1.4555, + "step": 3134 + }, + { + "epoch": 0.33, + "learning_rate": 1.6976626338262103e-05, + "loss": 1.4525, + "step": 3135 + }, + { + "epoch": 0.33, + "learning_rate": 1.6974003571019837e-05, + "loss": 1.3765, + "step": 3136 + }, + { + "epoch": 0.33, + "learning_rate": 1.6971379869440286e-05, + "loss": 1.3998, + "step": 3137 + }, + { + "epoch": 0.33, + "learning_rate": 1.696875523387495e-05, + "loss": 1.5103, + "step": 3138 + }, + { + "epoch": 0.33, + "learning_rate": 1.6966129664675474e-05, + "loss": 1.427, + "step": 3139 + }, + { + "epoch": 0.33, + "learning_rate": 1.6963503162193612e-05, + "loss": 1.4362, + "step": 3140 + }, + { + "epoch": 0.33, + "learning_rate": 1.6960875726781246e-05, + "loss": 1.4073, + "step": 3141 + }, + { + "epoch": 0.33, + "learning_rate": 1.6958247358790388e-05, + "loss": 1.4014, + "step": 3142 + }, + { + "epoch": 0.33, + "learning_rate": 1.6955618058573165e-05, + "loss": 1.4244, + "step": 3143 + }, + { + "epoch": 0.33, + "learning_rate": 1.6952987826481847e-05, + "loss": 1.47, + "step": 3144 + }, + { + "epoch": 0.33, + "learning_rate": 1.6950356662868814e-05, + "loss": 1.5112, + "step": 3145 + }, + { + "epoch": 0.33, + "learning_rate": 1.6947724568086562e-05, + "loss": 1.3398, + "step": 3146 + }, + { + "epoch": 0.33, + "learning_rate": 1.694509154248774e-05, + "loss": 1.4584, + "step": 3147 + }, + { + "epoch": 0.33, + "learning_rate": 1.69424575864251e-05, + "loss": 1.4383, + "step": 3148 + }, + { + "epoch": 0.33, + "learning_rate": 1.6939822700251523e-05, + "loss": 1.3869, + "step": 3149 + }, + { + "epoch": 0.33, + "learning_rate": 1.6937186884320015e-05, + "loss": 1.4453, + "step": 3150 + }, + { + "epoch": 0.33, + "learning_rate": 1.6934550138983713e-05, + "loss": 1.3355, + "step": 3151 + }, + { + "epoch": 0.33, + "learning_rate": 1.6931912464595866e-05, + "loss": 1.5573, + "step": 3152 + }, + { + "epoch": 0.33, + "learning_rate": 1.6929273861509865e-05, + "loss": 1.439, + "step": 3153 + }, + { + "epoch": 0.33, + "learning_rate": 1.6926634330079203e-05, + "loss": 1.6079, + "step": 3154 + }, + { + "epoch": 0.33, + "learning_rate": 1.692399387065752e-05, + "loss": 1.6973, + "step": 3155 + }, + { + "epoch": 0.33, + "learning_rate": 1.692135248359856e-05, + "loss": 1.3769, + "step": 3156 + }, + { + "epoch": 0.33, + "learning_rate": 1.6918710169256206e-05, + "loss": 1.4454, + "step": 3157 + }, + { + "epoch": 0.33, + "learning_rate": 1.691606692798446e-05, + "loss": 1.4495, + "step": 3158 + }, + { + "epoch": 0.33, + "learning_rate": 1.691342276013745e-05, + "loss": 1.4292, + "step": 3159 + }, + { + "epoch": 0.33, + "learning_rate": 1.691077766606942e-05, + "loss": 1.4405, + "step": 3160 + }, + { + "epoch": 0.33, + "learning_rate": 1.6908131646134757e-05, + "loss": 1.3683, + "step": 3161 + }, + { + "epoch": 0.33, + "learning_rate": 1.690548470068795e-05, + "loss": 1.4731, + "step": 3162 + }, + { + "epoch": 0.33, + "learning_rate": 1.690283683008362e-05, + "loss": 1.4323, + "step": 3163 + }, + { + "epoch": 0.33, + "learning_rate": 1.6900188034676518e-05, + "loss": 1.5133, + "step": 3164 + }, + { + "epoch": 0.33, + "learning_rate": 1.6897538314821516e-05, + "loss": 1.5529, + "step": 3165 + }, + { + "epoch": 0.33, + "learning_rate": 1.6894887670873605e-05, + "loss": 1.4427, + "step": 3166 + }, + { + "epoch": 0.33, + "learning_rate": 1.6892236103187904e-05, + "loss": 1.4344, + "step": 3167 + }, + { + "epoch": 0.33, + "learning_rate": 1.6889583612119657e-05, + "loss": 1.4291, + "step": 3168 + }, + { + "epoch": 0.33, + "learning_rate": 1.6886930198024226e-05, + "loss": 1.4683, + "step": 3169 + }, + { + "epoch": 0.33, + "learning_rate": 1.6884275861257106e-05, + "loss": 1.4442, + "step": 3170 + }, + { + "epoch": 0.33, + "learning_rate": 1.6881620602173905e-05, + "loss": 1.4509, + "step": 3171 + }, + { + "epoch": 0.33, + "learning_rate": 1.6878964421130362e-05, + "loss": 1.5113, + "step": 3172 + }, + { + "epoch": 0.33, + "learning_rate": 1.6876307318482334e-05, + "loss": 1.4261, + "step": 3173 + }, + { + "epoch": 0.33, + "learning_rate": 1.6873649294585805e-05, + "loss": 1.445, + "step": 3174 + }, + { + "epoch": 0.33, + "learning_rate": 1.6870990349796886e-05, + "loss": 1.4603, + "step": 3175 + }, + { + "epoch": 0.33, + "learning_rate": 1.68683304844718e-05, + "loss": 1.41, + "step": 3176 + }, + { + "epoch": 0.33, + "learning_rate": 1.686566969896691e-05, + "loss": 1.4018, + "step": 3177 + }, + { + "epoch": 0.33, + "learning_rate": 1.6863007993638687e-05, + "loss": 1.422, + "step": 3178 + }, + { + "epoch": 0.33, + "learning_rate": 1.6860345368843727e-05, + "loss": 1.4412, + "step": 3179 + }, + { + "epoch": 0.33, + "learning_rate": 1.6857681824938768e-05, + "loss": 1.5411, + "step": 3180 + }, + { + "epoch": 0.33, + "learning_rate": 1.685501736228064e-05, + "loss": 1.4416, + "step": 3181 + }, + { + "epoch": 0.33, + "learning_rate": 1.685235198122632e-05, + "loss": 1.5113, + "step": 3182 + }, + { + "epoch": 0.33, + "learning_rate": 1.6849685682132903e-05, + "loss": 1.423, + "step": 3183 + }, + { + "epoch": 0.33, + "learning_rate": 1.68470184653576e-05, + "loss": 1.404, + "step": 3184 + }, + { + "epoch": 0.33, + "eval_loss": 1.4771089553833008, + "eval_runtime": 77.4034, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3184 + }, + { + "epoch": 0.33, + "learning_rate": 1.6844350331257747e-05, + "loss": 1.4624, + "step": 3185 + }, + { + "epoch": 0.33, + "learning_rate": 1.6841681280190814e-05, + "loss": 1.4306, + "step": 3186 + }, + { + "epoch": 0.33, + "learning_rate": 1.683901131251438e-05, + "loss": 1.42, + "step": 3187 + }, + { + "epoch": 0.33, + "learning_rate": 1.6836340428586155e-05, + "loss": 1.4787, + "step": 3188 + }, + { + "epoch": 0.33, + "learning_rate": 1.6833668628763965e-05, + "loss": 1.3485, + "step": 3189 + }, + { + "epoch": 0.33, + "learning_rate": 1.683099591340576e-05, + "loss": 1.3674, + "step": 3190 + }, + { + "epoch": 0.33, + "learning_rate": 1.6828322282869627e-05, + "loss": 1.5187, + "step": 3191 + }, + { + "epoch": 0.33, + "learning_rate": 1.682564773751375e-05, + "loss": 1.4847, + "step": 3192 + }, + { + "epoch": 0.33, + "learning_rate": 1.682297227769646e-05, + "loss": 1.4815, + "step": 3193 + }, + { + "epoch": 0.33, + "learning_rate": 1.682029590377619e-05, + "loss": 1.4281, + "step": 3194 + }, + { + "epoch": 0.34, + "learning_rate": 1.6817618616111517e-05, + "loss": 1.4734, + "step": 3195 + }, + { + "epoch": 0.34, + "learning_rate": 1.681494041506112e-05, + "loss": 1.4861, + "step": 3196 + }, + { + "epoch": 0.34, + "learning_rate": 1.6812261300983808e-05, + "loss": 1.4372, + "step": 3197 + }, + { + "epoch": 0.34, + "learning_rate": 1.680958127423852e-05, + "loss": 1.4396, + "step": 3198 + }, + { + "epoch": 0.34, + "learning_rate": 1.680690033518431e-05, + "loss": 1.4225, + "step": 3199 + }, + { + "epoch": 0.34, + "learning_rate": 1.6804218484180347e-05, + "loss": 1.4925, + "step": 3200 + }, + { + "epoch": 0.34, + "learning_rate": 1.6801535721585942e-05, + "loss": 1.4306, + "step": 3201 + }, + { + "epoch": 0.34, + "learning_rate": 1.6798852047760506e-05, + "loss": 1.4298, + "step": 3202 + }, + { + "epoch": 0.34, + "learning_rate": 1.6796167463063588e-05, + "loss": 1.4725, + "step": 3203 + }, + { + "epoch": 0.34, + "learning_rate": 1.679348196785485e-05, + "loss": 1.4648, + "step": 3204 + }, + { + "epoch": 0.34, + "learning_rate": 1.6790795562494087e-05, + "loss": 1.4152, + "step": 3205 + }, + { + "epoch": 0.34, + "learning_rate": 1.6788108247341198e-05, + "loss": 1.4637, + "step": 3206 + }, + { + "epoch": 0.34, + "learning_rate": 1.6785420022756216e-05, + "loss": 1.4077, + "step": 3207 + }, + { + "epoch": 0.34, + "learning_rate": 1.67827308890993e-05, + "loss": 1.4585, + "step": 3208 + }, + { + "epoch": 0.34, + "learning_rate": 1.678004084673072e-05, + "loss": 1.3747, + "step": 3209 + }, + { + "epoch": 0.34, + "learning_rate": 1.6777349896010876e-05, + "loss": 1.4264, + "step": 3210 + }, + { + "epoch": 0.34, + "learning_rate": 1.677465803730028e-05, + "loss": 1.4178, + "step": 3211 + }, + { + "epoch": 0.34, + "learning_rate": 1.6771965270959584e-05, + "loss": 1.3876, + "step": 3212 + }, + { + "epoch": 0.34, + "learning_rate": 1.6769271597349538e-05, + "loss": 1.4658, + "step": 3213 + }, + { + "epoch": 0.34, + "learning_rate": 1.6766577016831026e-05, + "loss": 1.3968, + "step": 3214 + }, + { + "epoch": 0.34, + "learning_rate": 1.676388152976506e-05, + "loss": 1.5015, + "step": 3215 + }, + { + "epoch": 0.34, + "learning_rate": 1.6761185136512756e-05, + "loss": 1.4121, + "step": 3216 + }, + { + "epoch": 0.34, + "learning_rate": 1.675848783743537e-05, + "loss": 1.4146, + "step": 3217 + }, + { + "epoch": 0.34, + "learning_rate": 1.675578963289427e-05, + "loss": 1.4113, + "step": 3218 + }, + { + "epoch": 0.34, + "learning_rate": 1.6753090523250937e-05, + "loss": 1.4048, + "step": 3219 + }, + { + "epoch": 0.34, + "learning_rate": 1.6750390508866994e-05, + "loss": 1.4959, + "step": 3220 + }, + { + "epoch": 0.34, + "learning_rate": 1.6747689590104167e-05, + "loss": 1.4445, + "step": 3221 + }, + { + "epoch": 0.34, + "learning_rate": 1.6744987767324312e-05, + "loss": 1.4611, + "step": 3222 + }, + { + "epoch": 0.34, + "learning_rate": 1.67422850408894e-05, + "loss": 1.4141, + "step": 3223 + }, + { + "epoch": 0.34, + "learning_rate": 1.6739581411161535e-05, + "loss": 1.4218, + "step": 3224 + }, + { + "epoch": 0.34, + "learning_rate": 1.6736876878502925e-05, + "loss": 1.4266, + "step": 3225 + }, + { + "epoch": 0.34, + "learning_rate": 1.6734171443275913e-05, + "loss": 1.4941, + "step": 3226 + }, + { + "epoch": 0.34, + "learning_rate": 1.6731465105842955e-05, + "loss": 1.4294, + "step": 3227 + }, + { + "epoch": 0.34, + "learning_rate": 1.6728757866566635e-05, + "loss": 1.4189, + "step": 3228 + }, + { + "epoch": 0.34, + "learning_rate": 1.6726049725809647e-05, + "loss": 1.4713, + "step": 3229 + }, + { + "epoch": 0.34, + "learning_rate": 1.6723340683934818e-05, + "loss": 1.4203, + "step": 3230 + }, + { + "epoch": 0.34, + "learning_rate": 1.6720630741305088e-05, + "loss": 1.4112, + "step": 3231 + }, + { + "epoch": 0.34, + "learning_rate": 1.6717919898283523e-05, + "loss": 1.3811, + "step": 3232 + }, + { + "epoch": 0.34, + "learning_rate": 1.6715208155233296e-05, + "loss": 1.4242, + "step": 3233 + }, + { + "epoch": 0.34, + "learning_rate": 1.6712495512517725e-05, + "loss": 1.4207, + "step": 3234 + }, + { + "epoch": 0.34, + "learning_rate": 1.6709781970500222e-05, + "loss": 1.4888, + "step": 3235 + }, + { + "epoch": 0.34, + "learning_rate": 1.670706752954434e-05, + "loss": 1.4501, + "step": 3236 + }, + { + "epoch": 0.34, + "learning_rate": 1.670435219001374e-05, + "loss": 1.4367, + "step": 3237 + }, + { + "epoch": 0.34, + "learning_rate": 1.6701635952272212e-05, + "loss": 1.3959, + "step": 3238 + }, + { + "epoch": 0.34, + "learning_rate": 1.6698918816683655e-05, + "loss": 1.4257, + "step": 3239 + }, + { + "epoch": 0.34, + "learning_rate": 1.6696200783612102e-05, + "loss": 1.4718, + "step": 3240 + }, + { + "epoch": 0.34, + "learning_rate": 1.6693481853421697e-05, + "loss": 1.5899, + "step": 3241 + }, + { + "epoch": 0.34, + "learning_rate": 1.6690762026476707e-05, + "loss": 1.418, + "step": 3242 + }, + { + "epoch": 0.34, + "learning_rate": 1.668804130314152e-05, + "loss": 1.4076, + "step": 3243 + }, + { + "epoch": 0.34, + "learning_rate": 1.6685319683780645e-05, + "loss": 1.4571, + "step": 3244 + }, + { + "epoch": 0.34, + "learning_rate": 1.66825971687587e-05, + "loss": 1.4066, + "step": 3245 + }, + { + "epoch": 0.34, + "learning_rate": 1.6679873758440442e-05, + "loss": 1.4639, + "step": 3246 + }, + { + "epoch": 0.34, + "learning_rate": 1.6677149453190732e-05, + "loss": 1.453, + "step": 3247 + }, + { + "epoch": 0.34, + "learning_rate": 1.6674424253374558e-05, + "loss": 1.4262, + "step": 3248 + }, + { + "epoch": 0.34, + "learning_rate": 1.667169815935703e-05, + "loss": 1.3687, + "step": 3249 + }, + { + "epoch": 0.34, + "learning_rate": 1.6668971171503372e-05, + "loss": 1.5557, + "step": 3250 + }, + { + "epoch": 0.34, + "learning_rate": 1.6666243290178933e-05, + "loss": 1.4639, + "step": 3251 + }, + { + "epoch": 0.34, + "learning_rate": 1.6663514515749172e-05, + "loss": 1.4334, + "step": 3252 + }, + { + "epoch": 0.34, + "learning_rate": 1.6660784848579685e-05, + "loss": 1.3523, + "step": 3253 + }, + { + "epoch": 0.34, + "learning_rate": 1.6658054289036166e-05, + "loss": 1.3738, + "step": 3254 + }, + { + "epoch": 0.34, + "learning_rate": 1.665532283748445e-05, + "loss": 1.4159, + "step": 3255 + }, + { + "epoch": 0.34, + "learning_rate": 1.6652590494290474e-05, + "loss": 1.3609, + "step": 3256 + }, + { + "epoch": 0.34, + "learning_rate": 1.6649857259820303e-05, + "loss": 1.4449, + "step": 3257 + }, + { + "epoch": 0.34, + "learning_rate": 1.6647123134440126e-05, + "loss": 1.424, + "step": 3258 + }, + { + "epoch": 0.34, + "learning_rate": 1.664438811851624e-05, + "loss": 1.4737, + "step": 3259 + }, + { + "epoch": 0.34, + "learning_rate": 1.6641652212415066e-05, + "loss": 1.2717, + "step": 3260 + }, + { + "epoch": 0.34, + "learning_rate": 1.663891541650315e-05, + "loss": 1.4845, + "step": 3261 + }, + { + "epoch": 0.34, + "learning_rate": 1.663617773114715e-05, + "loss": 1.4115, + "step": 3262 + }, + { + "epoch": 0.34, + "learning_rate": 1.663343915671384e-05, + "loss": 1.4237, + "step": 3263 + }, + { + "epoch": 0.34, + "learning_rate": 1.6630699693570127e-05, + "loss": 1.4209, + "step": 3264 + }, + { + "epoch": 0.34, + "learning_rate": 1.6627959342083026e-05, + "loss": 1.506, + "step": 3265 + }, + { + "epoch": 0.34, + "learning_rate": 1.6625218102619672e-05, + "loss": 1.4466, + "step": 3266 + }, + { + "epoch": 0.34, + "learning_rate": 1.6622475975547324e-05, + "loss": 1.4129, + "step": 3267 + }, + { + "epoch": 0.34, + "learning_rate": 1.661973296123335e-05, + "loss": 1.4152, + "step": 3268 + }, + { + "epoch": 0.34, + "learning_rate": 1.661698906004525e-05, + "loss": 1.43, + "step": 3269 + }, + { + "epoch": 0.34, + "learning_rate": 1.661424427235064e-05, + "loss": 1.4701, + "step": 3270 + }, + { + "epoch": 0.34, + "learning_rate": 1.6611498598517238e-05, + "loss": 1.4598, + "step": 3271 + }, + { + "epoch": 0.34, + "learning_rate": 1.66087520389129e-05, + "loss": 1.4795, + "step": 3272 + }, + { + "epoch": 0.34, + "learning_rate": 1.6606004593905595e-05, + "loss": 1.5264, + "step": 3273 + }, + { + "epoch": 0.34, + "learning_rate": 1.6603256263863415e-05, + "loss": 1.4412, + "step": 3274 + }, + { + "epoch": 0.34, + "learning_rate": 1.6600507049154556e-05, + "loss": 1.45, + "step": 3275 + }, + { + "epoch": 0.34, + "learning_rate": 1.659775695014735e-05, + "loss": 1.4985, + "step": 3276 + }, + { + "epoch": 0.34, + "learning_rate": 1.659500596721024e-05, + "loss": 1.496, + "step": 3277 + }, + { + "epoch": 0.34, + "learning_rate": 1.6592254100711775e-05, + "loss": 1.4386, + "step": 3278 + }, + { + "epoch": 0.34, + "learning_rate": 1.658950135102065e-05, + "loss": 1.4073, + "step": 3279 + }, + { + "epoch": 0.34, + "learning_rate": 1.658674771850565e-05, + "loss": 1.3912, + "step": 3280 + }, + { + "epoch": 0.34, + "learning_rate": 1.6583993203535702e-05, + "loss": 1.3628, + "step": 3281 + }, + { + "epoch": 0.34, + "learning_rate": 1.658123780647983e-05, + "loss": 1.6089, + "step": 3282 + }, + { + "epoch": 0.34, + "learning_rate": 1.6578481527707196e-05, + "loss": 1.2367, + "step": 3283 + }, + { + "epoch": 0.34, + "learning_rate": 1.657572436758706e-05, + "loss": 1.4058, + "step": 3284 + }, + { + "epoch": 0.34, + "learning_rate": 1.6572966326488825e-05, + "loss": 1.4067, + "step": 3285 + }, + { + "epoch": 0.34, + "learning_rate": 1.657020740478198e-05, + "loss": 1.4187, + "step": 3286 + }, + { + "epoch": 0.34, + "learning_rate": 1.6567447602836166e-05, + "loss": 1.4599, + "step": 3287 + }, + { + "epoch": 0.34, + "learning_rate": 1.6564686921021115e-05, + "loss": 1.432, + "step": 3288 + }, + { + "epoch": 0.34, + "learning_rate": 1.6561925359706693e-05, + "loss": 1.3941, + "step": 3289 + }, + { + "epoch": 0.35, + "learning_rate": 1.6559162919262874e-05, + "loss": 1.3644, + "step": 3290 + }, + { + "epoch": 0.35, + "learning_rate": 1.6556399600059756e-05, + "loss": 1.4628, + "step": 3291 + }, + { + "epoch": 0.35, + "learning_rate": 1.6553635402467555e-05, + "loss": 1.4355, + "step": 3292 + }, + { + "epoch": 0.35, + "learning_rate": 1.6550870326856596e-05, + "loss": 1.4627, + "step": 3293 + }, + { + "epoch": 0.35, + "learning_rate": 1.6548104373597335e-05, + "loss": 1.442, + "step": 3294 + }, + { + "epoch": 0.35, + "learning_rate": 1.6545337543060338e-05, + "loss": 1.3991, + "step": 3295 + }, + { + "epoch": 0.35, + "learning_rate": 1.6542569835616283e-05, + "loss": 1.4193, + "step": 3296 + }, + { + "epoch": 0.35, + "learning_rate": 1.6539801251635982e-05, + "loss": 1.4792, + "step": 3297 + }, + { + "epoch": 0.35, + "learning_rate": 1.653703179149034e-05, + "loss": 1.4735, + "step": 3298 + }, + { + "epoch": 0.35, + "learning_rate": 1.6534261455550408e-05, + "loss": 1.451, + "step": 3299 + }, + { + "epoch": 0.35, + "learning_rate": 1.653149024418733e-05, + "loss": 1.3975, + "step": 3300 + }, + { + "epoch": 0.35, + "learning_rate": 1.652871815777238e-05, + "loss": 1.4843, + "step": 3301 + }, + { + "epoch": 0.35, + "learning_rate": 1.6525945196676948e-05, + "loss": 1.4782, + "step": 3302 + }, + { + "epoch": 0.35, + "learning_rate": 1.652317136127254e-05, + "loss": 1.3865, + "step": 3303 + }, + { + "epoch": 0.35, + "learning_rate": 1.6520396651930777e-05, + "loss": 1.4359, + "step": 3304 + }, + { + "epoch": 0.35, + "learning_rate": 1.6517621069023397e-05, + "loss": 1.4289, + "step": 3305 + }, + { + "epoch": 0.35, + "learning_rate": 1.651484461292226e-05, + "loss": 1.3526, + "step": 3306 + }, + { + "epoch": 0.35, + "learning_rate": 1.6512067283999336e-05, + "loss": 1.3671, + "step": 3307 + }, + { + "epoch": 0.35, + "learning_rate": 1.650928908262672e-05, + "loss": 1.6041, + "step": 3308 + }, + { + "epoch": 0.35, + "learning_rate": 1.650651000917662e-05, + "loss": 1.4322, + "step": 3309 + }, + { + "epoch": 0.35, + "learning_rate": 1.6503730064021354e-05, + "loss": 1.3992, + "step": 3310 + }, + { + "epoch": 0.35, + "learning_rate": 1.650094924753337e-05, + "loss": 1.4928, + "step": 3311 + }, + { + "epoch": 0.35, + "learning_rate": 1.6498167560085222e-05, + "loss": 1.4075, + "step": 3312 + }, + { + "epoch": 0.35, + "learning_rate": 1.6495385002049583e-05, + "loss": 1.4535, + "step": 3313 + }, + { + "epoch": 0.35, + "learning_rate": 1.6492601573799253e-05, + "loss": 1.4221, + "step": 3314 + }, + { + "epoch": 0.35, + "learning_rate": 1.6489817275707133e-05, + "loss": 1.3688, + "step": 3315 + }, + { + "epoch": 0.35, + "learning_rate": 1.6487032108146243e-05, + "loss": 1.3889, + "step": 3316 + }, + { + "epoch": 0.35, + "learning_rate": 1.6484246071489733e-05, + "loss": 1.3942, + "step": 3317 + }, + { + "epoch": 0.35, + "learning_rate": 1.6481459166110858e-05, + "loss": 1.4004, + "step": 3318 + }, + { + "epoch": 0.35, + "learning_rate": 1.647867139238299e-05, + "loss": 1.7308, + "step": 3319 + }, + { + "epoch": 0.35, + "learning_rate": 1.6475882750679622e-05, + "loss": 1.5001, + "step": 3320 + }, + { + "epoch": 0.35, + "learning_rate": 1.647309324137435e-05, + "loss": 1.4325, + "step": 3321 + }, + { + "epoch": 0.35, + "learning_rate": 1.6470302864840913e-05, + "loss": 1.4494, + "step": 3322 + }, + { + "epoch": 0.35, + "learning_rate": 1.6467511621453136e-05, + "loss": 1.4418, + "step": 3323 + }, + { + "epoch": 0.35, + "learning_rate": 1.646471951158498e-05, + "loss": 1.4046, + "step": 3324 + }, + { + "epoch": 0.35, + "learning_rate": 1.6461926535610517e-05, + "loss": 1.5031, + "step": 3325 + }, + { + "epoch": 0.35, + "learning_rate": 1.645913269390393e-05, + "loss": 1.4813, + "step": 3326 + }, + { + "epoch": 0.35, + "learning_rate": 1.6456337986839525e-05, + "loss": 1.3842, + "step": 3327 + }, + { + "epoch": 0.35, + "learning_rate": 1.645354241479172e-05, + "loss": 1.4539, + "step": 3328 + }, + { + "epoch": 0.35, + "learning_rate": 1.6450745978135048e-05, + "loss": 1.4503, + "step": 3329 + }, + { + "epoch": 0.35, + "learning_rate": 1.6447948677244163e-05, + "loss": 1.3741, + "step": 3330 + }, + { + "epoch": 0.35, + "learning_rate": 1.6445150512493832e-05, + "loss": 1.425, + "step": 3331 + }, + { + "epoch": 0.35, + "learning_rate": 1.644235148425893e-05, + "loss": 1.4277, + "step": 3332 + }, + { + "epoch": 0.35, + "learning_rate": 1.6439551592914464e-05, + "loss": 1.4918, + "step": 3333 + }, + { + "epoch": 0.35, + "learning_rate": 1.6436750838835543e-05, + "loss": 1.3364, + "step": 3334 + }, + { + "epoch": 0.35, + "learning_rate": 1.6433949222397397e-05, + "loss": 1.4741, + "step": 3335 + }, + { + "epoch": 0.35, + "learning_rate": 1.643114674397537e-05, + "loss": 1.3867, + "step": 3336 + }, + { + "epoch": 0.35, + "learning_rate": 1.642834340394492e-05, + "loss": 1.3817, + "step": 3337 + }, + { + "epoch": 0.35, + "learning_rate": 1.6425539202681625e-05, + "loss": 1.4308, + "step": 3338 + }, + { + "epoch": 0.35, + "learning_rate": 1.6422734140561178e-05, + "loss": 1.4401, + "step": 3339 + }, + { + "epoch": 0.35, + "learning_rate": 1.641992821795938e-05, + "loss": 1.4338, + "step": 3340 + }, + { + "epoch": 0.35, + "learning_rate": 1.641712143525216e-05, + "loss": 1.3804, + "step": 3341 + }, + { + "epoch": 0.35, + "learning_rate": 1.6414313792815546e-05, + "loss": 1.371, + "step": 3342 + }, + { + "epoch": 0.35, + "learning_rate": 1.6411505291025695e-05, + "loss": 1.4102, + "step": 3343 + }, + { + "epoch": 0.35, + "learning_rate": 1.6408695930258875e-05, + "loss": 1.4433, + "step": 3344 + }, + { + "epoch": 0.35, + "learning_rate": 1.6405885710891467e-05, + "loss": 1.3895, + "step": 3345 + }, + { + "epoch": 0.35, + "learning_rate": 1.6403074633299966e-05, + "loss": 1.4321, + "step": 3346 + }, + { + "epoch": 0.35, + "learning_rate": 1.640026269786098e-05, + "loss": 1.4207, + "step": 3347 + }, + { + "epoch": 0.35, + "learning_rate": 1.639744990495125e-05, + "loss": 1.3758, + "step": 3348 + }, + { + "epoch": 0.35, + "learning_rate": 1.6394636254947612e-05, + "loss": 1.4203, + "step": 3349 + }, + { + "epoch": 0.35, + "learning_rate": 1.6391821748227013e-05, + "loss": 1.4596, + "step": 3350 + }, + { + "epoch": 0.35, + "learning_rate": 1.6389006385166537e-05, + "loss": 1.4344, + "step": 3351 + }, + { + "epoch": 0.35, + "learning_rate": 1.6386190166143366e-05, + "loss": 1.4048, + "step": 3352 + }, + { + "epoch": 0.35, + "learning_rate": 1.6383373091534798e-05, + "loss": 1.4348, + "step": 3353 + }, + { + "epoch": 0.35, + "learning_rate": 1.638055516171825e-05, + "loss": 1.4972, + "step": 3354 + }, + { + "epoch": 0.35, + "learning_rate": 1.6377736377071258e-05, + "loss": 1.4685, + "step": 3355 + }, + { + "epoch": 0.35, + "learning_rate": 1.637491673797146e-05, + "loss": 1.4093, + "step": 3356 + }, + { + "epoch": 0.35, + "learning_rate": 1.6372096244796616e-05, + "loss": 1.4452, + "step": 3357 + }, + { + "epoch": 0.35, + "learning_rate": 1.63692748979246e-05, + "loss": 1.4458, + "step": 3358 + }, + { + "epoch": 0.35, + "learning_rate": 1.6366452697733404e-05, + "loss": 1.4187, + "step": 3359 + }, + { + "epoch": 0.35, + "learning_rate": 1.6363629644601126e-05, + "loss": 1.4052, + "step": 3360 + }, + { + "epoch": 0.35, + "learning_rate": 1.6360805738905984e-05, + "loss": 1.439, + "step": 3361 + }, + { + "epoch": 0.35, + "learning_rate": 1.635798098102631e-05, + "loss": 1.4131, + "step": 3362 + }, + { + "epoch": 0.35, + "learning_rate": 1.6355155371340544e-05, + "loss": 1.4391, + "step": 3363 + }, + { + "epoch": 0.35, + "learning_rate": 1.6352328910227252e-05, + "loss": 1.4318, + "step": 3364 + }, + { + "epoch": 0.35, + "learning_rate": 1.63495015980651e-05, + "loss": 1.5112, + "step": 3365 + }, + { + "epoch": 0.35, + "learning_rate": 1.6346673435232884e-05, + "loss": 1.4688, + "step": 3366 + }, + { + "epoch": 0.35, + "learning_rate": 1.6343844422109496e-05, + "loss": 1.3807, + "step": 3367 + }, + { + "epoch": 0.35, + "learning_rate": 1.634101455907396e-05, + "loss": 1.4083, + "step": 3368 + }, + { + "epoch": 0.35, + "learning_rate": 1.6338183846505394e-05, + "loss": 1.3566, + "step": 3369 + }, + { + "epoch": 0.35, + "learning_rate": 1.633535228478305e-05, + "loss": 1.4287, + "step": 3370 + }, + { + "epoch": 0.35, + "learning_rate": 1.6332519874286285e-05, + "loss": 1.3494, + "step": 3371 + }, + { + "epoch": 0.35, + "learning_rate": 1.6329686615394558e-05, + "loss": 1.3813, + "step": 3372 + }, + { + "epoch": 0.35, + "learning_rate": 1.6326852508487468e-05, + "loss": 1.4241, + "step": 3373 + }, + { + "epoch": 0.35, + "learning_rate": 1.63240175539447e-05, + "loss": 1.424, + "step": 3374 + }, + { + "epoch": 0.35, + "learning_rate": 1.632118175214607e-05, + "loss": 1.4212, + "step": 3375 + }, + { + "epoch": 0.35, + "learning_rate": 1.6318345103471504e-05, + "loss": 1.4671, + "step": 3376 + }, + { + "epoch": 0.35, + "learning_rate": 1.6315507608301044e-05, + "loss": 1.4593, + "step": 3377 + }, + { + "epoch": 0.35, + "learning_rate": 1.631266926701483e-05, + "loss": 1.7816, + "step": 3378 + }, + { + "epoch": 0.35, + "learning_rate": 1.6309830079993134e-05, + "loss": 1.5134, + "step": 3379 + }, + { + "epoch": 0.35, + "learning_rate": 1.6306990047616334e-05, + "loss": 0.8933, + "step": 3380 + }, + { + "epoch": 0.35, + "learning_rate": 1.630414917026492e-05, + "loss": 1.1033, + "step": 3381 + }, + { + "epoch": 0.35, + "learning_rate": 1.6301307448319497e-05, + "loss": 1.3494, + "step": 3382 + }, + { + "epoch": 0.35, + "learning_rate": 1.6298464882160784e-05, + "loss": 1.4299, + "step": 3383 + }, + { + "epoch": 0.35, + "eval_loss": 1.482450008392334, + "eval_runtime": 77.3737, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3383 + }, + { + "epoch": 0.35, + "learning_rate": 1.629562147216961e-05, + "loss": 1.3971, + "step": 3384 + }, + { + "epoch": 0.35, + "learning_rate": 1.6292777218726917e-05, + "loss": 1.3706, + "step": 3385 + }, + { + "epoch": 0.36, + "learning_rate": 1.6289932122213765e-05, + "loss": 1.4524, + "step": 3386 + }, + { + "epoch": 0.36, + "learning_rate": 1.6287086183011328e-05, + "loss": 1.4595, + "step": 3387 + }, + { + "epoch": 0.36, + "learning_rate": 1.628423940150088e-05, + "loss": 1.492, + "step": 3388 + }, + { + "epoch": 0.36, + "learning_rate": 1.628139177806382e-05, + "loss": 1.5576, + "step": 3389 + }, + { + "epoch": 0.36, + "learning_rate": 1.6278543313081657e-05, + "loss": 1.4615, + "step": 3390 + }, + { + "epoch": 0.36, + "learning_rate": 1.6275694006936015e-05, + "loss": 1.3456, + "step": 3391 + }, + { + "epoch": 0.36, + "learning_rate": 1.627284386000862e-05, + "loss": 1.4254, + "step": 3392 + }, + { + "epoch": 0.36, + "learning_rate": 1.6269992872681325e-05, + "loss": 1.433, + "step": 3393 + }, + { + "epoch": 0.36, + "learning_rate": 1.626714104533609e-05, + "loss": 1.5291, + "step": 3394 + }, + { + "epoch": 0.36, + "learning_rate": 1.626428837835498e-05, + "loss": 1.4502, + "step": 3395 + }, + { + "epoch": 0.36, + "learning_rate": 1.626143487212019e-05, + "loss": 1.3756, + "step": 3396 + }, + { + "epoch": 0.36, + "learning_rate": 1.6258580527014002e-05, + "loss": 1.414, + "step": 3397 + }, + { + "epoch": 0.36, + "learning_rate": 1.6255725343418835e-05, + "loss": 1.6289, + "step": 3398 + }, + { + "epoch": 0.36, + "learning_rate": 1.6252869321717208e-05, + "loss": 1.4862, + "step": 3399 + }, + { + "epoch": 0.36, + "learning_rate": 1.6250012462291756e-05, + "loss": 1.4213, + "step": 3400 + }, + { + "epoch": 0.36, + "learning_rate": 1.6247154765525217e-05, + "loss": 1.524, + "step": 3401 + }, + { + "epoch": 0.36, + "learning_rate": 1.624429623180046e-05, + "loss": 1.6013, + "step": 3402 + }, + { + "epoch": 0.36, + "learning_rate": 1.624143686150045e-05, + "loss": 1.4557, + "step": 3403 + }, + { + "epoch": 0.36, + "learning_rate": 1.6238576655008266e-05, + "loss": 1.3831, + "step": 3404 + }, + { + "epoch": 0.36, + "learning_rate": 1.6235715612707105e-05, + "loss": 1.4008, + "step": 3405 + }, + { + "epoch": 0.36, + "learning_rate": 1.623285373498028e-05, + "loss": 1.4848, + "step": 3406 + }, + { + "epoch": 0.36, + "learning_rate": 1.6229991022211197e-05, + "loss": 1.4459, + "step": 3407 + }, + { + "epoch": 0.36, + "learning_rate": 1.6227127474783393e-05, + "loss": 1.4334, + "step": 3408 + }, + { + "epoch": 0.36, + "learning_rate": 1.6224263093080507e-05, + "loss": 1.4123, + "step": 3409 + }, + { + "epoch": 0.36, + "learning_rate": 1.6221397877486294e-05, + "loss": 1.3691, + "step": 3410 + }, + { + "epoch": 0.36, + "learning_rate": 1.6218531828384618e-05, + "loss": 1.4128, + "step": 3411 + }, + { + "epoch": 0.36, + "learning_rate": 1.6215664946159457e-05, + "loss": 1.3642, + "step": 3412 + }, + { + "epoch": 0.36, + "learning_rate": 1.6212797231194902e-05, + "loss": 1.4311, + "step": 3413 + }, + { + "epoch": 0.36, + "learning_rate": 1.6209928683875152e-05, + "loss": 1.4695, + "step": 3414 + }, + { + "epoch": 0.36, + "learning_rate": 1.6207059304584514e-05, + "loss": 1.3871, + "step": 3415 + }, + { + "epoch": 0.36, + "learning_rate": 1.6204189093707414e-05, + "loss": 1.4219, + "step": 3416 + }, + { + "epoch": 0.36, + "learning_rate": 1.620131805162839e-05, + "loss": 1.6199, + "step": 3417 + }, + { + "epoch": 0.36, + "learning_rate": 1.619844617873208e-05, + "loss": 1.4433, + "step": 3418 + }, + { + "epoch": 0.36, + "learning_rate": 1.619557347540325e-05, + "loss": 1.4773, + "step": 3419 + }, + { + "epoch": 0.36, + "learning_rate": 1.6192699942026763e-05, + "loss": 1.4551, + "step": 3420 + }, + { + "epoch": 0.36, + "learning_rate": 1.6189825578987603e-05, + "loss": 1.4903, + "step": 3421 + }, + { + "epoch": 0.36, + "learning_rate": 1.6186950386670855e-05, + "loss": 1.473, + "step": 3422 + }, + { + "epoch": 0.36, + "learning_rate": 1.6184074365461722e-05, + "loss": 1.4082, + "step": 3423 + }, + { + "epoch": 0.36, + "learning_rate": 1.6181197515745523e-05, + "loss": 1.4746, + "step": 3424 + }, + { + "epoch": 0.36, + "learning_rate": 1.6178319837907674e-05, + "loss": 1.449, + "step": 3425 + }, + { + "epoch": 0.36, + "learning_rate": 1.6175441332333715e-05, + "loss": 1.377, + "step": 3426 + }, + { + "epoch": 0.36, + "learning_rate": 1.617256199940929e-05, + "loss": 1.2364, + "step": 3427 + }, + { + "epoch": 0.36, + "learning_rate": 1.6169681839520155e-05, + "loss": 1.4437, + "step": 3428 + }, + { + "epoch": 0.36, + "learning_rate": 1.616680085305218e-05, + "loss": 1.4726, + "step": 3429 + }, + { + "epoch": 0.36, + "learning_rate": 1.616391904039134e-05, + "loss": 1.4824, + "step": 3430 + }, + { + "epoch": 0.36, + "learning_rate": 1.616103640192373e-05, + "loss": 1.4052, + "step": 3431 + }, + { + "epoch": 0.36, + "learning_rate": 1.6158152938035537e-05, + "loss": 1.4131, + "step": 3432 + }, + { + "epoch": 0.36, + "learning_rate": 1.6155268649113084e-05, + "loss": 1.4267, + "step": 3433 + }, + { + "epoch": 0.36, + "learning_rate": 1.6152383535542786e-05, + "loss": 1.3735, + "step": 3434 + }, + { + "epoch": 0.36, + "learning_rate": 1.6149497597711175e-05, + "loss": 1.4249, + "step": 3435 + }, + { + "epoch": 0.36, + "learning_rate": 1.614661083600489e-05, + "loss": 1.4312, + "step": 3436 + }, + { + "epoch": 0.36, + "learning_rate": 1.6143723250810686e-05, + "loss": 1.4831, + "step": 3437 + }, + { + "epoch": 0.36, + "learning_rate": 1.6140834842515425e-05, + "loss": 1.4183, + "step": 3438 + }, + { + "epoch": 0.36, + "learning_rate": 1.6137945611506078e-05, + "loss": 1.3908, + "step": 3439 + }, + { + "epoch": 0.36, + "learning_rate": 1.613505555816973e-05, + "loss": 1.425, + "step": 3440 + }, + { + "epoch": 0.36, + "learning_rate": 1.613216468289357e-05, + "loss": 1.3589, + "step": 3441 + }, + { + "epoch": 0.36, + "learning_rate": 1.6129272986064903e-05, + "loss": 1.4272, + "step": 3442 + }, + { + "epoch": 0.36, + "learning_rate": 1.6126380468071142e-05, + "loss": 1.4337, + "step": 3443 + }, + { + "epoch": 0.36, + "learning_rate": 1.6123487129299817e-05, + "loss": 1.3872, + "step": 3444 + }, + { + "epoch": 0.36, + "learning_rate": 1.612059297013855e-05, + "loss": 1.374, + "step": 3445 + }, + { + "epoch": 0.36, + "learning_rate": 1.611769799097509e-05, + "loss": 1.314, + "step": 3446 + }, + { + "epoch": 0.36, + "learning_rate": 1.6114802192197284e-05, + "loss": 1.3951, + "step": 3447 + }, + { + "epoch": 0.36, + "learning_rate": 1.6111905574193102e-05, + "loss": 1.4732, + "step": 3448 + }, + { + "epoch": 0.36, + "learning_rate": 1.6109008137350614e-05, + "loss": 1.3575, + "step": 3449 + }, + { + "epoch": 0.36, + "learning_rate": 1.6106109882058e-05, + "loss": 1.4606, + "step": 3450 + }, + { + "epoch": 0.36, + "learning_rate": 1.6103210808703554e-05, + "loss": 1.4357, + "step": 3451 + }, + { + "epoch": 0.36, + "learning_rate": 1.6100310917675678e-05, + "loss": 0.8456, + "step": 3452 + }, + { + "epoch": 0.36, + "learning_rate": 1.609741020936288e-05, + "loss": 1.07, + "step": 3453 + }, + { + "epoch": 0.36, + "learning_rate": 1.6094508684153782e-05, + "loss": 1.4435, + "step": 3454 + }, + { + "epoch": 0.36, + "learning_rate": 1.609160634243711e-05, + "loss": 1.3696, + "step": 3455 + }, + { + "epoch": 0.36, + "learning_rate": 1.6088703184601712e-05, + "loss": 1.4012, + "step": 3456 + }, + { + "epoch": 0.36, + "learning_rate": 1.608579921103653e-05, + "loss": 1.5212, + "step": 3457 + }, + { + "epoch": 0.36, + "learning_rate": 1.608289442213062e-05, + "loss": 1.4339, + "step": 3458 + }, + { + "epoch": 0.36, + "learning_rate": 1.607998881827316e-05, + "loss": 1.4901, + "step": 3459 + }, + { + "epoch": 0.36, + "learning_rate": 1.6077082399853412e-05, + "loss": 1.4822, + "step": 3460 + }, + { + "epoch": 0.36, + "learning_rate": 1.607417516726077e-05, + "loss": 1.3696, + "step": 3461 + }, + { + "epoch": 0.36, + "learning_rate": 1.6071267120884727e-05, + "loss": 1.4434, + "step": 3462 + }, + { + "epoch": 0.36, + "learning_rate": 1.6068358261114886e-05, + "loss": 1.3916, + "step": 3463 + }, + { + "epoch": 0.36, + "learning_rate": 1.606544858834096e-05, + "loss": 1.422, + "step": 3464 + }, + { + "epoch": 0.36, + "learning_rate": 1.6062538102952763e-05, + "loss": 1.367, + "step": 3465 + }, + { + "epoch": 0.36, + "learning_rate": 1.605962680534024e-05, + "loss": 1.3788, + "step": 3466 + }, + { + "epoch": 0.36, + "learning_rate": 1.605671469589342e-05, + "loss": 1.4366, + "step": 3467 + }, + { + "epoch": 0.36, + "learning_rate": 1.6053801775002453e-05, + "loss": 1.4027, + "step": 3468 + }, + { + "epoch": 0.36, + "learning_rate": 1.6050888043057595e-05, + "loss": 1.4386, + "step": 3469 + }, + { + "epoch": 0.36, + "learning_rate": 1.6047973500449212e-05, + "loss": 1.4675, + "step": 3470 + }, + { + "epoch": 0.36, + "learning_rate": 1.6045058147567778e-05, + "loss": 1.6936, + "step": 3471 + }, + { + "epoch": 0.36, + "learning_rate": 1.6042141984803875e-05, + "loss": 1.4858, + "step": 3472 + }, + { + "epoch": 0.36, + "learning_rate": 1.6039225012548196e-05, + "loss": 1.5004, + "step": 3473 + }, + { + "epoch": 0.36, + "learning_rate": 1.6036307231191534e-05, + "loss": 1.4969, + "step": 3474 + }, + { + "epoch": 0.36, + "learning_rate": 1.6033388641124803e-05, + "loss": 1.4027, + "step": 3475 + }, + { + "epoch": 0.36, + "learning_rate": 1.6030469242739016e-05, + "loss": 1.4741, + "step": 3476 + }, + { + "epoch": 0.36, + "learning_rate": 1.60275490364253e-05, + "loss": 1.3887, + "step": 3477 + }, + { + "epoch": 0.36, + "learning_rate": 1.602462802257488e-05, + "loss": 1.6735, + "step": 3478 + }, + { + "epoch": 0.36, + "learning_rate": 1.602170620157911e-05, + "loss": 1.4997, + "step": 3479 + }, + { + "epoch": 0.36, + "learning_rate": 1.601878357382943e-05, + "loss": 1.3973, + "step": 3480 + }, + { + "epoch": 0.37, + "learning_rate": 1.6015860139717398e-05, + "loss": 1.416, + "step": 3481 + }, + { + "epoch": 0.37, + "learning_rate": 1.6012935899634682e-05, + "loss": 1.4102, + "step": 3482 + }, + { + "epoch": 0.37, + "learning_rate": 1.601001085397305e-05, + "loss": 1.4248, + "step": 3483 + }, + { + "epoch": 0.37, + "learning_rate": 1.6007085003124386e-05, + "loss": 1.3909, + "step": 3484 + }, + { + "epoch": 0.37, + "learning_rate": 1.600415834748068e-05, + "loss": 1.4029, + "step": 3485 + }, + { + "epoch": 0.37, + "learning_rate": 1.6001230887434024e-05, + "loss": 1.4219, + "step": 3486 + }, + { + "epoch": 0.37, + "learning_rate": 1.5998302623376633e-05, + "loss": 1.4008, + "step": 3487 + }, + { + "epoch": 0.37, + "learning_rate": 1.5995373555700806e-05, + "loss": 1.5163, + "step": 3488 + }, + { + "epoch": 0.37, + "learning_rate": 1.599244368479897e-05, + "loss": 1.4541, + "step": 3489 + }, + { + "epoch": 0.37, + "learning_rate": 1.598951301106365e-05, + "loss": 1.4454, + "step": 3490 + }, + { + "epoch": 0.37, + "learning_rate": 1.598658153488748e-05, + "loss": 1.1014, + "step": 3491 + }, + { + "epoch": 0.37, + "learning_rate": 1.598364925666321e-05, + "loss": 1.407, + "step": 3492 + }, + { + "epoch": 0.37, + "learning_rate": 1.5980716176783682e-05, + "loss": 1.5046, + "step": 3493 + }, + { + "epoch": 0.37, + "learning_rate": 1.5977782295641857e-05, + "loss": 1.4265, + "step": 3494 + }, + { + "epoch": 0.37, + "learning_rate": 1.5974847613630796e-05, + "loss": 1.46, + "step": 3495 + }, + { + "epoch": 0.37, + "learning_rate": 1.5971912131143677e-05, + "loss": 1.3996, + "step": 3496 + }, + { + "epoch": 0.37, + "learning_rate": 1.5968975848573772e-05, + "loss": 1.4719, + "step": 3497 + }, + { + "epoch": 0.37, + "learning_rate": 1.596603876631447e-05, + "loss": 1.43, + "step": 3498 + }, + { + "epoch": 0.37, + "learning_rate": 1.596310088475927e-05, + "loss": 1.4109, + "step": 3499 + }, + { + "epoch": 0.37, + "learning_rate": 1.5960162204301768e-05, + "loss": 1.3612, + "step": 3500 + }, + { + "epoch": 0.37, + "learning_rate": 1.5957222725335672e-05, + "loss": 1.5045, + "step": 3501 + }, + { + "epoch": 0.37, + "learning_rate": 1.5954282448254794e-05, + "loss": 1.5323, + "step": 3502 + }, + { + "epoch": 0.37, + "learning_rate": 1.595134137345306e-05, + "loss": 1.4518, + "step": 3503 + }, + { + "epoch": 0.37, + "learning_rate": 1.5948399501324495e-05, + "loss": 1.6131, + "step": 3504 + }, + { + "epoch": 0.37, + "learning_rate": 1.594545683226324e-05, + "loss": 1.5076, + "step": 3505 + }, + { + "epoch": 0.37, + "learning_rate": 1.594251336666353e-05, + "loss": 1.482, + "step": 3506 + }, + { + "epoch": 0.37, + "learning_rate": 1.5939569104919716e-05, + "loss": 1.4429, + "step": 3507 + }, + { + "epoch": 0.37, + "learning_rate": 1.5936624047426254e-05, + "loss": 1.4662, + "step": 3508 + }, + { + "epoch": 0.37, + "learning_rate": 1.5933678194577708e-05, + "loss": 1.425, + "step": 3509 + }, + { + "epoch": 0.37, + "learning_rate": 1.5930731546768744e-05, + "loss": 1.4312, + "step": 3510 + }, + { + "epoch": 0.37, + "learning_rate": 1.592778410439414e-05, + "loss": 1.4336, + "step": 3511 + }, + { + "epoch": 0.37, + "learning_rate": 1.5924835867848775e-05, + "loss": 1.4197, + "step": 3512 + }, + { + "epoch": 0.37, + "learning_rate": 1.5921886837527638e-05, + "loss": 1.4456, + "step": 3513 + }, + { + "epoch": 0.37, + "learning_rate": 1.5918937013825823e-05, + "loss": 1.4394, + "step": 3514 + }, + { + "epoch": 0.37, + "learning_rate": 1.5915986397138526e-05, + "loss": 1.3606, + "step": 3515 + }, + { + "epoch": 0.37, + "learning_rate": 1.591303498786106e-05, + "loss": 1.4382, + "step": 3516 + }, + { + "epoch": 0.37, + "learning_rate": 1.591008278638884e-05, + "loss": 1.4185, + "step": 3517 + }, + { + "epoch": 0.37, + "learning_rate": 1.5907129793117374e-05, + "loss": 1.6692, + "step": 3518 + }, + { + "epoch": 0.37, + "learning_rate": 1.59041760084423e-05, + "loss": 1.501, + "step": 3519 + }, + { + "epoch": 0.37, + "learning_rate": 1.5901221432759345e-05, + "loss": 1.5753, + "step": 3520 + }, + { + "epoch": 0.37, + "learning_rate": 1.589826606646434e-05, + "loss": 1.4795, + "step": 3521 + }, + { + "epoch": 0.37, + "learning_rate": 1.5895309909953236e-05, + "loss": 1.4379, + "step": 3522 + }, + { + "epoch": 0.37, + "learning_rate": 1.5892352963622078e-05, + "loss": 1.3426, + "step": 3523 + }, + { + "epoch": 0.37, + "learning_rate": 1.5889395227867025e-05, + "loss": 1.4048, + "step": 3524 + }, + { + "epoch": 0.37, + "learning_rate": 1.5886436703084332e-05, + "loss": 1.4303, + "step": 3525 + }, + { + "epoch": 0.37, + "learning_rate": 1.5883477389670367e-05, + "loss": 1.3684, + "step": 3526 + }, + { + "epoch": 0.37, + "learning_rate": 1.5880517288021602e-05, + "loss": 1.3701, + "step": 3527 + }, + { + "epoch": 0.37, + "learning_rate": 1.587755639853462e-05, + "loss": 1.4308, + "step": 3528 + }, + { + "epoch": 0.37, + "learning_rate": 1.5874594721606096e-05, + "loss": 1.3981, + "step": 3529 + }, + { + "epoch": 0.37, + "learning_rate": 1.5871632257632823e-05, + "loss": 1.5906, + "step": 3530 + }, + { + "epoch": 0.37, + "learning_rate": 1.5868669007011696e-05, + "loss": 1.4642, + "step": 3531 + }, + { + "epoch": 0.37, + "learning_rate": 1.586570497013971e-05, + "loss": 1.411, + "step": 3532 + }, + { + "epoch": 0.37, + "learning_rate": 1.586274014741397e-05, + "loss": 1.3942, + "step": 3533 + }, + { + "epoch": 0.37, + "learning_rate": 1.5859774539231693e-05, + "loss": 1.3952, + "step": 3534 + }, + { + "epoch": 0.37, + "learning_rate": 1.585680814599019e-05, + "loss": 1.4009, + "step": 3535 + }, + { + "epoch": 0.37, + "learning_rate": 1.585384096808688e-05, + "loss": 1.3238, + "step": 3536 + }, + { + "epoch": 0.37, + "learning_rate": 1.585087300591929e-05, + "loss": 1.346, + "step": 3537 + }, + { + "epoch": 0.37, + "learning_rate": 1.584790425988505e-05, + "loss": 1.3739, + "step": 3538 + }, + { + "epoch": 0.37, + "learning_rate": 1.5844934730381895e-05, + "loss": 1.4264, + "step": 3539 + }, + { + "epoch": 0.37, + "learning_rate": 1.5841964417807668e-05, + "loss": 1.4675, + "step": 3540 + }, + { + "epoch": 0.37, + "learning_rate": 1.5838993322560314e-05, + "loss": 1.3337, + "step": 3541 + }, + { + "epoch": 0.37, + "learning_rate": 1.5836021445037883e-05, + "loss": 1.4052, + "step": 3542 + }, + { + "epoch": 0.37, + "learning_rate": 1.583304878563853e-05, + "loss": 1.4311, + "step": 3543 + }, + { + "epoch": 0.37, + "learning_rate": 1.5830075344760513e-05, + "loss": 1.386, + "step": 3544 + }, + { + "epoch": 0.37, + "learning_rate": 1.58271011228022e-05, + "loss": 1.387, + "step": 3545 + }, + { + "epoch": 0.37, + "learning_rate": 1.582412612016206e-05, + "loss": 1.3601, + "step": 3546 + }, + { + "epoch": 0.37, + "learning_rate": 1.5821150337238663e-05, + "loss": 1.5111, + "step": 3547 + }, + { + "epoch": 0.37, + "learning_rate": 1.5818173774430697e-05, + "loss": 1.471, + "step": 3548 + }, + { + "epoch": 0.37, + "learning_rate": 1.581519643213693e-05, + "loss": 1.4442, + "step": 3549 + }, + { + "epoch": 0.37, + "learning_rate": 1.5812218310756263e-05, + "loss": 1.467, + "step": 3550 + }, + { + "epoch": 0.37, + "learning_rate": 1.5809239410687683e-05, + "loss": 1.3731, + "step": 3551 + }, + { + "epoch": 0.37, + "learning_rate": 1.5806259732330286e-05, + "loss": 1.4072, + "step": 3552 + }, + { + "epoch": 0.37, + "learning_rate": 1.5803279276083268e-05, + "loss": 1.3636, + "step": 3553 + }, + { + "epoch": 0.37, + "learning_rate": 1.5800298042345938e-05, + "loss": 1.3915, + "step": 3554 + }, + { + "epoch": 0.37, + "learning_rate": 1.5797316031517705e-05, + "loss": 1.5038, + "step": 3555 + }, + { + "epoch": 0.37, + "learning_rate": 1.5794333243998082e-05, + "loss": 1.4455, + "step": 3556 + }, + { + "epoch": 0.37, + "learning_rate": 1.5791349680186684e-05, + "loss": 1.5062, + "step": 3557 + }, + { + "epoch": 0.37, + "learning_rate": 1.5788365340483234e-05, + "loss": 1.3899, + "step": 3558 + }, + { + "epoch": 0.37, + "learning_rate": 1.5785380225287554e-05, + "loss": 1.4946, + "step": 3559 + }, + { + "epoch": 0.37, + "learning_rate": 1.5782394334999572e-05, + "loss": 1.3859, + "step": 3560 + }, + { + "epoch": 0.37, + "learning_rate": 1.577940767001933e-05, + "loss": 1.541, + "step": 3561 + }, + { + "epoch": 0.37, + "learning_rate": 1.5776420230746952e-05, + "loss": 1.4952, + "step": 3562 + }, + { + "epoch": 0.37, + "learning_rate": 1.5773432017582684e-05, + "loss": 1.6055, + "step": 3563 + }, + { + "epoch": 0.37, + "learning_rate": 1.577044303092687e-05, + "loss": 1.4661, + "step": 3564 + }, + { + "epoch": 0.37, + "learning_rate": 1.576745327117996e-05, + "loss": 1.4082, + "step": 3565 + }, + { + "epoch": 0.37, + "learning_rate": 1.5764462738742493e-05, + "loss": 1.4005, + "step": 3566 + }, + { + "epoch": 0.37, + "learning_rate": 1.5761471434015137e-05, + "loss": 1.3959, + "step": 3567 + }, + { + "epoch": 0.37, + "learning_rate": 1.5758479357398645e-05, + "loss": 1.4567, + "step": 3568 + }, + { + "epoch": 0.37, + "learning_rate": 1.575548650929388e-05, + "loss": 1.3791, + "step": 3569 + }, + { + "epoch": 0.37, + "learning_rate": 1.57524928901018e-05, + "loss": 1.4428, + "step": 3570 + }, + { + "epoch": 0.37, + "learning_rate": 1.5749498500223486e-05, + "loss": 1.3864, + "step": 3571 + }, + { + "epoch": 0.37, + "learning_rate": 1.5746503340060097e-05, + "loss": 1.4019, + "step": 3572 + }, + { + "epoch": 0.37, + "learning_rate": 1.574350741001291e-05, + "loss": 1.5436, + "step": 3573 + }, + { + "epoch": 0.37, + "learning_rate": 1.5740510710483308e-05, + "loss": 1.4637, + "step": 3574 + }, + { + "epoch": 0.37, + "learning_rate": 1.5737513241872767e-05, + "loss": 1.5097, + "step": 3575 + }, + { + "epoch": 0.38, + "learning_rate": 1.5734515004582873e-05, + "loss": 1.5143, + "step": 3576 + }, + { + "epoch": 0.38, + "learning_rate": 1.5731515999015315e-05, + "loss": 1.3926, + "step": 3577 + }, + { + "epoch": 0.38, + "learning_rate": 1.5728516225571874e-05, + "loss": 1.4242, + "step": 3578 + }, + { + "epoch": 0.38, + "learning_rate": 1.5725515684654453e-05, + "loss": 1.4429, + "step": 3579 + }, + { + "epoch": 0.38, + "learning_rate": 1.572251437666504e-05, + "loss": 1.4638, + "step": 3580 + }, + { + "epoch": 0.38, + "learning_rate": 1.5719512302005735e-05, + "loss": 1.3381, + "step": 3581 + }, + { + "epoch": 0.38, + "learning_rate": 1.571650946107874e-05, + "loss": 1.4342, + "step": 3582 + }, + { + "epoch": 0.38, + "eval_loss": 1.4705015420913696, + "eval_runtime": 77.3664, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3582 + }, + { + "epoch": 0.38, + "learning_rate": 1.571350585428636e-05, + "loss": 1.3991, + "step": 3583 + }, + { + "epoch": 0.38, + "learning_rate": 1.5710501482030998e-05, + "loss": 1.4274, + "step": 3584 + }, + { + "epoch": 0.38, + "learning_rate": 1.5707496344715166e-05, + "loss": 1.438, + "step": 3585 + }, + { + "epoch": 0.38, + "learning_rate": 1.570449044274147e-05, + "loss": 1.4453, + "step": 3586 + }, + { + "epoch": 0.38, + "learning_rate": 1.570148377651263e-05, + "loss": 1.4022, + "step": 3587 + }, + { + "epoch": 0.38, + "learning_rate": 1.5698476346431454e-05, + "loss": 1.4312, + "step": 3588 + }, + { + "epoch": 0.38, + "learning_rate": 1.569546815290087e-05, + "loss": 1.4329, + "step": 3589 + }, + { + "epoch": 0.38, + "learning_rate": 1.569245919632389e-05, + "loss": 1.4036, + "step": 3590 + }, + { + "epoch": 0.38, + "learning_rate": 1.5689449477103644e-05, + "loss": 1.412, + "step": 3591 + }, + { + "epoch": 0.38, + "learning_rate": 1.5686438995643353e-05, + "loss": 1.4492, + "step": 3592 + }, + { + "epoch": 0.38, + "learning_rate": 1.5683427752346343e-05, + "loss": 1.4555, + "step": 3593 + }, + { + "epoch": 0.38, + "learning_rate": 1.5680415747616047e-05, + "loss": 1.5594, + "step": 3594 + }, + { + "epoch": 0.38, + "learning_rate": 1.5677402981855993e-05, + "loss": 1.4813, + "step": 3595 + }, + { + "epoch": 0.38, + "learning_rate": 1.567438945546982e-05, + "loss": 1.5919, + "step": 3596 + }, + { + "epoch": 0.38, + "learning_rate": 1.5671375168861255e-05, + "loss": 1.4235, + "step": 3597 + }, + { + "epoch": 0.38, + "learning_rate": 1.5668360122434135e-05, + "loss": 1.441, + "step": 3598 + }, + { + "epoch": 0.38, + "learning_rate": 1.566534431659241e-05, + "loss": 1.5847, + "step": 3599 + }, + { + "epoch": 0.38, + "learning_rate": 1.566232775174011e-05, + "loss": 1.6123, + "step": 3600 + }, + { + "epoch": 0.38, + "learning_rate": 1.5659310428281374e-05, + "loss": 1.4916, + "step": 3601 + }, + { + "epoch": 0.38, + "learning_rate": 1.5656292346620457e-05, + "loss": 1.4603, + "step": 3602 + }, + { + "epoch": 0.38, + "learning_rate": 1.56532735071617e-05, + "loss": 1.4423, + "step": 3603 + }, + { + "epoch": 0.38, + "learning_rate": 1.5650253910309547e-05, + "loss": 1.4814, + "step": 3604 + }, + { + "epoch": 0.38, + "learning_rate": 1.5647233556468552e-05, + "loss": 1.4015, + "step": 3605 + }, + { + "epoch": 0.38, + "learning_rate": 1.564421244604336e-05, + "loss": 1.3798, + "step": 3606 + }, + { + "epoch": 0.38, + "learning_rate": 1.5641190579438723e-05, + "loss": 1.4259, + "step": 3607 + }, + { + "epoch": 0.38, + "learning_rate": 1.5638167957059493e-05, + "loss": 1.3493, + "step": 3608 + }, + { + "epoch": 0.38, + "learning_rate": 1.5635144579310626e-05, + "loss": 1.3433, + "step": 3609 + }, + { + "epoch": 0.38, + "learning_rate": 1.5632120446597177e-05, + "loss": 1.4661, + "step": 3610 + }, + { + "epoch": 0.38, + "learning_rate": 1.5629095559324297e-05, + "loss": 1.4205, + "step": 3611 + }, + { + "epoch": 0.38, + "learning_rate": 1.562606991789725e-05, + "loss": 1.3976, + "step": 3612 + }, + { + "epoch": 0.38, + "learning_rate": 1.5623043522721393e-05, + "loss": 1.4261, + "step": 3613 + }, + { + "epoch": 0.38, + "learning_rate": 1.562001637420218e-05, + "loss": 1.4358, + "step": 3614 + }, + { + "epoch": 0.38, + "learning_rate": 1.5616988472745175e-05, + "loss": 1.437, + "step": 3615 + }, + { + "epoch": 0.38, + "learning_rate": 1.561395981875604e-05, + "loss": 1.3735, + "step": 3616 + }, + { + "epoch": 0.38, + "learning_rate": 1.5610930412640532e-05, + "loss": 1.4357, + "step": 3617 + }, + { + "epoch": 0.38, + "learning_rate": 1.560790025480452e-05, + "loss": 1.4003, + "step": 3618 + }, + { + "epoch": 0.38, + "learning_rate": 1.5604869345653965e-05, + "loss": 1.4127, + "step": 3619 + }, + { + "epoch": 0.38, + "learning_rate": 1.5601837685594927e-05, + "loss": 1.4666, + "step": 3620 + }, + { + "epoch": 0.38, + "learning_rate": 1.5598805275033574e-05, + "loss": 1.4106, + "step": 3621 + }, + { + "epoch": 0.38, + "learning_rate": 1.5595772114376174e-05, + "loss": 1.3857, + "step": 3622 + }, + { + "epoch": 0.38, + "learning_rate": 1.5592738204029086e-05, + "loss": 1.4704, + "step": 3623 + }, + { + "epoch": 0.38, + "learning_rate": 1.558970354439878e-05, + "loss": 1.4649, + "step": 3624 + }, + { + "epoch": 0.38, + "learning_rate": 1.5586668135891824e-05, + "loss": 1.4812, + "step": 3625 + }, + { + "epoch": 0.38, + "learning_rate": 1.5583631978914882e-05, + "loss": 1.3507, + "step": 3626 + }, + { + "epoch": 0.38, + "learning_rate": 1.5580595073874718e-05, + "loss": 1.3762, + "step": 3627 + }, + { + "epoch": 0.38, + "learning_rate": 1.557755742117821e-05, + "loss": 1.4169, + "step": 3628 + }, + { + "epoch": 0.38, + "learning_rate": 1.557451902123231e-05, + "loss": 1.4098, + "step": 3629 + }, + { + "epoch": 0.38, + "learning_rate": 1.55714798744441e-05, + "loss": 1.5526, + "step": 3630 + }, + { + "epoch": 0.38, + "learning_rate": 1.556843998122074e-05, + "loss": 1.4414, + "step": 3631 + }, + { + "epoch": 0.38, + "learning_rate": 1.5565399341969497e-05, + "loss": 1.4134, + "step": 3632 + }, + { + "epoch": 0.38, + "learning_rate": 1.556235795709774e-05, + "loss": 1.4718, + "step": 3633 + }, + { + "epoch": 0.38, + "learning_rate": 1.5559315827012937e-05, + "loss": 1.412, + "step": 3634 + }, + { + "epoch": 0.38, + "learning_rate": 1.5556272952122657e-05, + "loss": 1.4119, + "step": 3635 + }, + { + "epoch": 0.38, + "learning_rate": 1.5553229332834564e-05, + "loss": 1.3999, + "step": 3636 + }, + { + "epoch": 0.38, + "learning_rate": 1.5550184969556428e-05, + "loss": 1.4626, + "step": 3637 + }, + { + "epoch": 0.38, + "learning_rate": 1.5547139862696113e-05, + "loss": 1.3811, + "step": 3638 + }, + { + "epoch": 0.38, + "learning_rate": 1.5544094012661583e-05, + "loss": 1.4053, + "step": 3639 + }, + { + "epoch": 0.38, + "learning_rate": 1.5541047419860907e-05, + "loss": 1.4059, + "step": 3640 + }, + { + "epoch": 0.38, + "learning_rate": 1.553800008470225e-05, + "loss": 1.4717, + "step": 3641 + }, + { + "epoch": 0.38, + "learning_rate": 1.553495200759388e-05, + "loss": 1.399, + "step": 3642 + }, + { + "epoch": 0.38, + "learning_rate": 1.5531903188944154e-05, + "loss": 1.4143, + "step": 3643 + }, + { + "epoch": 0.38, + "learning_rate": 1.5528853629161536e-05, + "loss": 1.4414, + "step": 3644 + }, + { + "epoch": 0.38, + "learning_rate": 1.5525803328654592e-05, + "loss": 1.4206, + "step": 3645 + }, + { + "epoch": 0.38, + "learning_rate": 1.5522752287831982e-05, + "loss": 1.3869, + "step": 3646 + }, + { + "epoch": 0.38, + "learning_rate": 1.551970050710247e-05, + "loss": 1.5434, + "step": 3647 + }, + { + "epoch": 0.38, + "learning_rate": 1.5516647986874914e-05, + "loss": 1.4574, + "step": 3648 + }, + { + "epoch": 0.38, + "learning_rate": 1.5513594727558273e-05, + "loss": 1.4353, + "step": 3649 + }, + { + "epoch": 0.38, + "learning_rate": 1.5510540729561606e-05, + "loss": 1.4122, + "step": 3650 + }, + { + "epoch": 0.38, + "learning_rate": 1.550748599329407e-05, + "loss": 1.4077, + "step": 3651 + }, + { + "epoch": 0.38, + "learning_rate": 1.550443051916492e-05, + "loss": 1.4433, + "step": 3652 + }, + { + "epoch": 0.38, + "learning_rate": 1.5501374307583514e-05, + "loss": 1.54, + "step": 3653 + }, + { + "epoch": 0.38, + "learning_rate": 1.5498317358959302e-05, + "loss": 1.4522, + "step": 3654 + }, + { + "epoch": 0.38, + "learning_rate": 1.5495259673701842e-05, + "loss": 1.4175, + "step": 3655 + }, + { + "epoch": 0.38, + "learning_rate": 1.5492201252220777e-05, + "loss": 1.4637, + "step": 3656 + }, + { + "epoch": 0.38, + "learning_rate": 1.5489142094925863e-05, + "loss": 1.4701, + "step": 3657 + }, + { + "epoch": 0.38, + "learning_rate": 1.548608220222695e-05, + "loss": 1.4095, + "step": 3658 + }, + { + "epoch": 0.38, + "learning_rate": 1.548302157453398e-05, + "loss": 1.3903, + "step": 3659 + }, + { + "epoch": 0.38, + "learning_rate": 1.5479960212257002e-05, + "loss": 1.4062, + "step": 3660 + }, + { + "epoch": 0.38, + "learning_rate": 1.5476898115806157e-05, + "loss": 1.4706, + "step": 3661 + }, + { + "epoch": 0.38, + "learning_rate": 1.547383528559169e-05, + "loss": 1.4423, + "step": 3662 + }, + { + "epoch": 0.38, + "learning_rate": 1.547077172202394e-05, + "loss": 1.4418, + "step": 3663 + }, + { + "epoch": 0.38, + "learning_rate": 1.5467707425513347e-05, + "loss": 1.4553, + "step": 3664 + }, + { + "epoch": 0.38, + "learning_rate": 1.5464642396470443e-05, + "loss": 1.435, + "step": 3665 + }, + { + "epoch": 0.38, + "learning_rate": 1.5461576635305873e-05, + "loss": 1.4105, + "step": 3666 + }, + { + "epoch": 0.38, + "learning_rate": 1.5458510142430364e-05, + "loss": 1.4118, + "step": 3667 + }, + { + "epoch": 0.38, + "learning_rate": 1.5455442918254746e-05, + "loss": 1.4096, + "step": 3668 + }, + { + "epoch": 0.38, + "learning_rate": 1.545237496318995e-05, + "loss": 1.4248, + "step": 3669 + }, + { + "epoch": 0.38, + "learning_rate": 1.5449306277647003e-05, + "loss": 1.4591, + "step": 3670 + }, + { + "epoch": 0.38, + "learning_rate": 1.544623686203703e-05, + "loss": 1.4764, + "step": 3671 + }, + { + "epoch": 0.39, + "learning_rate": 1.5443166716771255e-05, + "loss": 1.4329, + "step": 3672 + }, + { + "epoch": 0.39, + "learning_rate": 1.5440095842260995e-05, + "loss": 1.4023, + "step": 3673 + }, + { + "epoch": 0.39, + "learning_rate": 1.5437024238917674e-05, + "loss": 1.3802, + "step": 3674 + }, + { + "epoch": 0.39, + "learning_rate": 1.5433951907152806e-05, + "loss": 1.4627, + "step": 3675 + }, + { + "epoch": 0.39, + "learning_rate": 1.5430878847378e-05, + "loss": 1.5164, + "step": 3676 + }, + { + "epoch": 0.39, + "learning_rate": 1.542780506000497e-05, + "loss": 1.3546, + "step": 3677 + }, + { + "epoch": 0.39, + "learning_rate": 1.542473054544553e-05, + "loss": 1.4415, + "step": 3678 + }, + { + "epoch": 0.39, + "learning_rate": 1.5421655304111573e-05, + "loss": 1.4093, + "step": 3679 + }, + { + "epoch": 0.39, + "learning_rate": 1.5418579336415114e-05, + "loss": 1.3943, + "step": 3680 + }, + { + "epoch": 0.39, + "learning_rate": 1.5415502642768252e-05, + "loss": 1.3659, + "step": 3681 + }, + { + "epoch": 0.39, + "learning_rate": 1.541242522358318e-05, + "loss": 1.4322, + "step": 3682 + }, + { + "epoch": 0.39, + "learning_rate": 1.5409347079272198e-05, + "loss": 1.4064, + "step": 3683 + }, + { + "epoch": 0.39, + "learning_rate": 1.5406268210247693e-05, + "loss": 1.4031, + "step": 3684 + }, + { + "epoch": 0.39, + "learning_rate": 1.540318861692216e-05, + "loss": 1.3449, + "step": 3685 + }, + { + "epoch": 0.39, + "learning_rate": 1.5400108299708182e-05, + "loss": 1.5536, + "step": 3686 + }, + { + "epoch": 0.39, + "learning_rate": 1.5397027259018442e-05, + "loss": 1.4106, + "step": 3687 + }, + { + "epoch": 0.39, + "learning_rate": 1.5393945495265722e-05, + "loss": 1.4309, + "step": 3688 + }, + { + "epoch": 0.39, + "learning_rate": 1.53908630088629e-05, + "loss": 1.3765, + "step": 3689 + }, + { + "epoch": 0.39, + "learning_rate": 1.5387779800222947e-05, + "loss": 1.3809, + "step": 3690 + }, + { + "epoch": 0.39, + "learning_rate": 1.5384695869758938e-05, + "loss": 1.4758, + "step": 3691 + }, + { + "epoch": 0.39, + "learning_rate": 1.5381611217884032e-05, + "loss": 1.4249, + "step": 3692 + }, + { + "epoch": 0.39, + "learning_rate": 1.5378525845011503e-05, + "loss": 1.4133, + "step": 3693 + }, + { + "epoch": 0.39, + "learning_rate": 1.5375439751554708e-05, + "loss": 1.418, + "step": 3694 + }, + { + "epoch": 0.39, + "learning_rate": 1.53723529379271e-05, + "loss": 1.441, + "step": 3695 + }, + { + "epoch": 0.39, + "learning_rate": 1.536926540454224e-05, + "loss": 1.3919, + "step": 3696 + }, + { + "epoch": 0.39, + "learning_rate": 1.5366177151813775e-05, + "loss": 1.3722, + "step": 3697 + }, + { + "epoch": 0.39, + "learning_rate": 1.536308818015545e-05, + "loss": 1.4727, + "step": 3698 + }, + { + "epoch": 0.39, + "learning_rate": 1.535999848998111e-05, + "loss": 1.442, + "step": 3699 + }, + { + "epoch": 0.39, + "learning_rate": 1.535690808170469e-05, + "loss": 1.3884, + "step": 3700 + }, + { + "epoch": 0.39, + "learning_rate": 1.535381695574023e-05, + "loss": 1.3226, + "step": 3701 + }, + { + "epoch": 0.39, + "learning_rate": 1.535072511250186e-05, + "loss": 1.4403, + "step": 3702 + }, + { + "epoch": 0.39, + "learning_rate": 1.5347632552403808e-05, + "loss": 1.4144, + "step": 3703 + }, + { + "epoch": 0.39, + "learning_rate": 1.5344539275860395e-05, + "loss": 1.3514, + "step": 3704 + }, + { + "epoch": 0.39, + "learning_rate": 1.5341445283286044e-05, + "loss": 1.519, + "step": 3705 + }, + { + "epoch": 0.39, + "learning_rate": 1.5338350575095268e-05, + "loss": 1.4251, + "step": 3706 + }, + { + "epoch": 0.39, + "learning_rate": 1.5335255151702685e-05, + "loss": 1.392, + "step": 3707 + }, + { + "epoch": 0.39, + "learning_rate": 1.533215901352299e-05, + "loss": 1.3838, + "step": 3708 + }, + { + "epoch": 0.39, + "learning_rate": 1.532906216097099e-05, + "loss": 1.444, + "step": 3709 + }, + { + "epoch": 0.39, + "learning_rate": 1.5325964594461594e-05, + "loss": 1.3459, + "step": 3710 + }, + { + "epoch": 0.39, + "learning_rate": 1.5322866314409783e-05, + "loss": 1.4155, + "step": 3711 + }, + { + "epoch": 0.39, + "learning_rate": 1.5319767321230657e-05, + "loss": 1.4057, + "step": 3712 + }, + { + "epoch": 0.39, + "learning_rate": 1.5316667615339392e-05, + "loss": 1.382, + "step": 3713 + }, + { + "epoch": 0.39, + "learning_rate": 1.5313567197151277e-05, + "loss": 1.3634, + "step": 3714 + }, + { + "epoch": 0.39, + "learning_rate": 1.5310466067081688e-05, + "loss": 1.3434, + "step": 3715 + }, + { + "epoch": 0.39, + "learning_rate": 1.530736422554609e-05, + "loss": 1.4553, + "step": 3716 + }, + { + "epoch": 0.39, + "learning_rate": 1.5304261672960055e-05, + "loss": 1.4193, + "step": 3717 + }, + { + "epoch": 0.39, + "learning_rate": 1.5301158409739242e-05, + "loss": 1.3955, + "step": 3718 + }, + { + "epoch": 0.39, + "learning_rate": 1.5298054436299413e-05, + "loss": 1.4592, + "step": 3719 + }, + { + "epoch": 0.39, + "learning_rate": 1.529494975305642e-05, + "loss": 1.738, + "step": 3720 + }, + { + "epoch": 0.39, + "learning_rate": 1.529184436042621e-05, + "loss": 1.438, + "step": 3721 + }, + { + "epoch": 0.39, + "learning_rate": 1.528873825882482e-05, + "loss": 1.3445, + "step": 3722 + }, + { + "epoch": 0.39, + "learning_rate": 1.5285631448668395e-05, + "loss": 1.4168, + "step": 3723 + }, + { + "epoch": 0.39, + "learning_rate": 1.528252393037317e-05, + "loss": 1.4088, + "step": 3724 + }, + { + "epoch": 0.39, + "learning_rate": 1.5279415704355468e-05, + "loss": 1.4484, + "step": 3725 + }, + { + "epoch": 0.39, + "learning_rate": 1.5276306771031708e-05, + "loss": 1.4706, + "step": 3726 + }, + { + "epoch": 0.39, + "learning_rate": 1.527319713081841e-05, + "loss": 1.3466, + "step": 3727 + }, + { + "epoch": 0.39, + "learning_rate": 1.5270086784132196e-05, + "loss": 1.427, + "step": 3728 + }, + { + "epoch": 0.39, + "learning_rate": 1.5266975731389754e-05, + "loss": 1.4596, + "step": 3729 + }, + { + "epoch": 0.39, + "learning_rate": 1.52638639730079e-05, + "loss": 1.405, + "step": 3730 + }, + { + "epoch": 0.39, + "learning_rate": 1.5260751509403518e-05, + "loss": 1.4572, + "step": 3731 + }, + { + "epoch": 0.39, + "learning_rate": 1.5257638340993608e-05, + "loss": 1.3827, + "step": 3732 + }, + { + "epoch": 0.39, + "learning_rate": 1.5254524468195251e-05, + "loss": 1.3712, + "step": 3733 + }, + { + "epoch": 0.39, + "learning_rate": 1.5251409891425626e-05, + "loss": 1.4541, + "step": 3734 + }, + { + "epoch": 0.39, + "learning_rate": 1.5248294611102006e-05, + "loss": 1.5279, + "step": 3735 + }, + { + "epoch": 0.39, + "learning_rate": 1.5245178627641759e-05, + "loss": 1.3722, + "step": 3736 + }, + { + "epoch": 0.39, + "learning_rate": 1.5242061941462348e-05, + "loss": 1.5158, + "step": 3737 + }, + { + "epoch": 0.39, + "learning_rate": 1.523894455298132e-05, + "loss": 1.4274, + "step": 3738 + }, + { + "epoch": 0.39, + "learning_rate": 1.5235826462616338e-05, + "loss": 1.4543, + "step": 3739 + }, + { + "epoch": 0.39, + "learning_rate": 1.5232707670785144e-05, + "loss": 1.5011, + "step": 3740 + }, + { + "epoch": 0.39, + "learning_rate": 1.5229588177905568e-05, + "loss": 1.24, + "step": 3741 + }, + { + "epoch": 0.39, + "learning_rate": 1.5226467984395544e-05, + "loss": 1.4253, + "step": 3742 + }, + { + "epoch": 0.39, + "learning_rate": 1.5223347090673102e-05, + "loss": 1.3736, + "step": 3743 + }, + { + "epoch": 0.39, + "learning_rate": 1.522022549715636e-05, + "loss": 1.4587, + "step": 3744 + }, + { + "epoch": 0.39, + "learning_rate": 1.521710320426353e-05, + "loss": 1.5024, + "step": 3745 + }, + { + "epoch": 0.39, + "learning_rate": 1.521398021241292e-05, + "loss": 1.427, + "step": 3746 + }, + { + "epoch": 0.39, + "learning_rate": 1.5210856522022929e-05, + "loss": 1.3387, + "step": 3747 + }, + { + "epoch": 0.39, + "learning_rate": 1.5207732133512055e-05, + "loss": 1.3819, + "step": 3748 + }, + { + "epoch": 0.39, + "learning_rate": 1.5204607047298883e-05, + "loss": 1.4571, + "step": 3749 + }, + { + "epoch": 0.39, + "learning_rate": 1.5201481263802094e-05, + "loss": 1.3592, + "step": 3750 + }, + { + "epoch": 0.39, + "learning_rate": 1.5198354783440464e-05, + "loss": 1.3912, + "step": 3751 + }, + { + "epoch": 0.39, + "learning_rate": 1.519522760663286e-05, + "loss": 1.4986, + "step": 3752 + }, + { + "epoch": 0.39, + "learning_rate": 1.5192099733798243e-05, + "loss": 1.4106, + "step": 3753 + }, + { + "epoch": 0.39, + "learning_rate": 1.5188971165355667e-05, + "loss": 1.4145, + "step": 3754 + }, + { + "epoch": 0.39, + "learning_rate": 1.5185841901724282e-05, + "loss": 1.3915, + "step": 3755 + }, + { + "epoch": 0.39, + "learning_rate": 1.5182711943323329e-05, + "loss": 1.4014, + "step": 3756 + }, + { + "epoch": 0.39, + "learning_rate": 1.5179581290572141e-05, + "loss": 1.3651, + "step": 3757 + }, + { + "epoch": 0.39, + "learning_rate": 1.5176449943890147e-05, + "loss": 1.3653, + "step": 3758 + }, + { + "epoch": 0.39, + "learning_rate": 1.5173317903696862e-05, + "loss": 1.4486, + "step": 3759 + }, + { + "epoch": 0.39, + "learning_rate": 1.5170185170411906e-05, + "loss": 1.4459, + "step": 3760 + }, + { + "epoch": 0.39, + "learning_rate": 1.5167051744454977e-05, + "loss": 1.4215, + "step": 3761 + }, + { + "epoch": 0.39, + "learning_rate": 1.5163917626245877e-05, + "loss": 1.4379, + "step": 3762 + }, + { + "epoch": 0.39, + "learning_rate": 1.51607828162045e-05, + "loss": 1.4147, + "step": 3763 + }, + { + "epoch": 0.39, + "learning_rate": 1.5157647314750827e-05, + "loss": 1.4011, + "step": 3764 + }, + { + "epoch": 0.39, + "learning_rate": 1.5154511122304936e-05, + "loss": 1.4309, + "step": 3765 + }, + { + "epoch": 0.39, + "learning_rate": 1.5151374239286993e-05, + "loss": 1.4382, + "step": 3766 + }, + { + "epoch": 0.4, + "learning_rate": 1.5148236666117266e-05, + "loss": 1.405, + "step": 3767 + }, + { + "epoch": 0.4, + "learning_rate": 1.5145098403216104e-05, + "loss": 1.4223, + "step": 3768 + }, + { + "epoch": 0.4, + "learning_rate": 1.5141959451003951e-05, + "loss": 1.4084, + "step": 3769 + }, + { + "epoch": 0.4, + "learning_rate": 1.5138819809901356e-05, + "loss": 1.4063, + "step": 3770 + }, + { + "epoch": 0.4, + "learning_rate": 1.513567948032894e-05, + "loss": 1.3299, + "step": 3771 + }, + { + "epoch": 0.4, + "learning_rate": 1.5132538462707431e-05, + "loss": 1.3901, + "step": 3772 + }, + { + "epoch": 0.4, + "learning_rate": 1.5129396757457646e-05, + "loss": 1.4249, + "step": 3773 + }, + { + "epoch": 0.4, + "learning_rate": 1.512625436500049e-05, + "loss": 1.4087, + "step": 3774 + }, + { + "epoch": 0.4, + "learning_rate": 1.5123111285756964e-05, + "loss": 1.3521, + "step": 3775 + }, + { + "epoch": 0.4, + "learning_rate": 1.5119967520148163e-05, + "loss": 1.4097, + "step": 3776 + }, + { + "epoch": 0.4, + "learning_rate": 1.5116823068595261e-05, + "loss": 1.4871, + "step": 3777 + }, + { + "epoch": 0.4, + "learning_rate": 1.5113677931519543e-05, + "loss": 1.44, + "step": 3778 + }, + { + "epoch": 0.4, + "learning_rate": 1.5110532109342377e-05, + "loss": 1.4518, + "step": 3779 + }, + { + "epoch": 0.4, + "learning_rate": 1.5107385602485214e-05, + "loss": 1.3961, + "step": 3780 + }, + { + "epoch": 0.4, + "learning_rate": 1.5104238411369614e-05, + "loss": 1.4341, + "step": 3781 + }, + { + "epoch": 0.4, + "eval_loss": 1.4642821550369263, + "eval_runtime": 77.3595, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 3781 + }, + { + "epoch": 0.4, + "learning_rate": 1.5101090536417218e-05, + "loss": 1.403, + "step": 3782 + }, + { + "epoch": 0.4, + "learning_rate": 1.5097941978049754e-05, + "loss": 1.4103, + "step": 3783 + }, + { + "epoch": 0.4, + "learning_rate": 1.5094792736689052e-05, + "loss": 1.3478, + "step": 3784 + }, + { + "epoch": 0.4, + "learning_rate": 1.5091642812757035e-05, + "loss": 1.4134, + "step": 3785 + }, + { + "epoch": 0.4, + "learning_rate": 1.5088492206675701e-05, + "loss": 1.4134, + "step": 3786 + }, + { + "epoch": 0.4, + "learning_rate": 1.5085340918867162e-05, + "loss": 1.1494, + "step": 3787 + }, + { + "epoch": 0.4, + "learning_rate": 1.5082188949753598e-05, + "loss": 1.2385, + "step": 3788 + }, + { + "epoch": 0.4, + "learning_rate": 1.5079036299757299e-05, + "loss": 1.4258, + "step": 3789 + }, + { + "epoch": 0.4, + "learning_rate": 1.5075882969300639e-05, + "loss": 1.3781, + "step": 3790 + }, + { + "epoch": 0.4, + "learning_rate": 1.507272895880608e-05, + "loss": 1.5096, + "step": 3791 + }, + { + "epoch": 0.4, + "learning_rate": 1.5069574268696179e-05, + "loss": 1.366, + "step": 3792 + }, + { + "epoch": 0.4, + "learning_rate": 1.5066418899393584e-05, + "loss": 1.3792, + "step": 3793 + }, + { + "epoch": 0.4, + "learning_rate": 1.506326285132104e-05, + "loss": 1.4987, + "step": 3794 + }, + { + "epoch": 0.4, + "learning_rate": 1.5060106124901364e-05, + "loss": 1.445, + "step": 3795 + }, + { + "epoch": 0.4, + "learning_rate": 1.5056948720557482e-05, + "loss": 1.5071, + "step": 3796 + }, + { + "epoch": 0.4, + "learning_rate": 1.505379063871241e-05, + "loss": 1.4029, + "step": 3797 + }, + { + "epoch": 0.4, + "learning_rate": 1.5050631879789244e-05, + "loss": 1.5263, + "step": 3798 + }, + { + "epoch": 0.4, + "learning_rate": 1.5047472444211175e-05, + "loss": 1.3906, + "step": 3799 + }, + { + "epoch": 0.4, + "learning_rate": 1.5044312332401494e-05, + "loss": 1.7352, + "step": 3800 + }, + { + "epoch": 0.4, + "learning_rate": 1.5041151544783565e-05, + "loss": 1.3946, + "step": 3801 + }, + { + "epoch": 0.4, + "learning_rate": 1.5037990081780862e-05, + "loss": 1.3592, + "step": 3802 + }, + { + "epoch": 0.4, + "learning_rate": 1.503482794381693e-05, + "loss": 1.3991, + "step": 3803 + }, + { + "epoch": 0.4, + "learning_rate": 1.5031665131315423e-05, + "loss": 1.4271, + "step": 3804 + }, + { + "epoch": 0.4, + "learning_rate": 1.502850164470007e-05, + "loss": 1.4305, + "step": 3805 + }, + { + "epoch": 0.4, + "learning_rate": 1.5025337484394701e-05, + "loss": 1.4116, + "step": 3806 + }, + { + "epoch": 0.4, + "learning_rate": 1.5022172650823232e-05, + "loss": 1.4242, + "step": 3807 + }, + { + "epoch": 0.4, + "learning_rate": 1.5019007144409667e-05, + "loss": 1.4427, + "step": 3808 + }, + { + "epoch": 0.4, + "learning_rate": 1.5015840965578106e-05, + "loss": 1.3705, + "step": 3809 + }, + { + "epoch": 0.4, + "learning_rate": 1.5012674114752732e-05, + "loss": 1.4498, + "step": 3810 + }, + { + "epoch": 0.4, + "learning_rate": 1.5009506592357822e-05, + "loss": 1.489, + "step": 3811 + }, + { + "epoch": 0.4, + "learning_rate": 1.5006338398817746e-05, + "loss": 1.4801, + "step": 3812 + }, + { + "epoch": 0.4, + "learning_rate": 1.5003169534556956e-05, + "loss": 1.3468, + "step": 3813 + }, + { + "epoch": 0.4, + "learning_rate": 1.5000000000000002e-05, + "loss": 1.4211, + "step": 3814 + }, + { + "epoch": 0.4, + "learning_rate": 1.4996829795571518e-05, + "loss": 1.4683, + "step": 3815 + }, + { + "epoch": 0.4, + "learning_rate": 1.499365892169623e-05, + "loss": 1.4441, + "step": 3816 + }, + { + "epoch": 0.4, + "learning_rate": 1.4990487378798958e-05, + "loss": 1.4368, + "step": 3817 + }, + { + "epoch": 0.4, + "learning_rate": 1.4987315167304602e-05, + "loss": 1.4097, + "step": 3818 + }, + { + "epoch": 0.4, + "learning_rate": 1.4984142287638155e-05, + "loss": 1.4238, + "step": 3819 + }, + { + "epoch": 0.4, + "learning_rate": 1.4980968740224708e-05, + "loss": 1.497, + "step": 3820 + }, + { + "epoch": 0.4, + "learning_rate": 1.4977794525489433e-05, + "loss": 1.3989, + "step": 3821 + }, + { + "epoch": 0.4, + "learning_rate": 1.4974619643857588e-05, + "loss": 1.4415, + "step": 3822 + }, + { + "epoch": 0.4, + "learning_rate": 1.4971444095754533e-05, + "loss": 1.3931, + "step": 3823 + }, + { + "epoch": 0.4, + "learning_rate": 1.4968267881605705e-05, + "loss": 1.3426, + "step": 3824 + }, + { + "epoch": 0.4, + "learning_rate": 1.4965091001836636e-05, + "loss": 1.644, + "step": 3825 + }, + { + "epoch": 0.4, + "learning_rate": 1.4961913456872945e-05, + "loss": 1.3903, + "step": 3826 + }, + { + "epoch": 0.4, + "learning_rate": 1.4958735247140345e-05, + "loss": 1.3764, + "step": 3827 + }, + { + "epoch": 0.4, + "learning_rate": 1.4955556373064632e-05, + "loss": 1.5484, + "step": 3828 + }, + { + "epoch": 0.4, + "learning_rate": 1.4952376835071696e-05, + "loss": 1.5696, + "step": 3829 + }, + { + "epoch": 0.4, + "learning_rate": 1.4949196633587509e-05, + "loss": 1.3844, + "step": 3830 + }, + { + "epoch": 0.4, + "learning_rate": 1.494601576903814e-05, + "loss": 1.3868, + "step": 3831 + }, + { + "epoch": 0.4, + "learning_rate": 1.4942834241849741e-05, + "loss": 1.4229, + "step": 3832 + }, + { + "epoch": 0.4, + "learning_rate": 1.4939652052448557e-05, + "loss": 1.4062, + "step": 3833 + }, + { + "epoch": 0.4, + "learning_rate": 1.4936469201260915e-05, + "loss": 1.3955, + "step": 3834 + }, + { + "epoch": 0.4, + "learning_rate": 1.4933285688713239e-05, + "loss": 1.3959, + "step": 3835 + }, + { + "epoch": 0.4, + "learning_rate": 1.4930101515232038e-05, + "loss": 1.4652, + "step": 3836 + }, + { + "epoch": 0.4, + "learning_rate": 1.4926916681243913e-05, + "loss": 1.5253, + "step": 3837 + }, + { + "epoch": 0.4, + "learning_rate": 1.4923731187175539e-05, + "loss": 1.4694, + "step": 3838 + }, + { + "epoch": 0.4, + "learning_rate": 1.4920545033453702e-05, + "loss": 1.3859, + "step": 3839 + }, + { + "epoch": 0.4, + "learning_rate": 1.4917358220505259e-05, + "loss": 1.4157, + "step": 3840 + }, + { + "epoch": 0.4, + "learning_rate": 1.4914170748757159e-05, + "loss": 1.4491, + "step": 3841 + }, + { + "epoch": 0.4, + "learning_rate": 1.4910982618636445e-05, + "loss": 1.4464, + "step": 3842 + }, + { + "epoch": 0.4, + "learning_rate": 1.4907793830570246e-05, + "loss": 1.3771, + "step": 3843 + }, + { + "epoch": 0.4, + "learning_rate": 1.4904604384985775e-05, + "loss": 1.3673, + "step": 3844 + }, + { + "epoch": 0.4, + "learning_rate": 1.4901414282310334e-05, + "loss": 1.4429, + "step": 3845 + }, + { + "epoch": 0.4, + "learning_rate": 1.4898223522971318e-05, + "loss": 1.4905, + "step": 3846 + }, + { + "epoch": 0.4, + "learning_rate": 1.4895032107396205e-05, + "loss": 1.4039, + "step": 3847 + }, + { + "epoch": 0.4, + "learning_rate": 1.4891840036012566e-05, + "loss": 1.4082, + "step": 3848 + }, + { + "epoch": 0.4, + "learning_rate": 1.4888647309248052e-05, + "loss": 1.3643, + "step": 3849 + }, + { + "epoch": 0.4, + "learning_rate": 1.4885453927530408e-05, + "loss": 1.3116, + "step": 3850 + }, + { + "epoch": 0.4, + "learning_rate": 1.4882259891287467e-05, + "loss": 1.4278, + "step": 3851 + }, + { + "epoch": 0.4, + "learning_rate": 1.4879065200947148e-05, + "loss": 1.3712, + "step": 3852 + }, + { + "epoch": 0.4, + "learning_rate": 1.4875869856937449e-05, + "loss": 1.387, + "step": 3853 + }, + { + "epoch": 0.4, + "learning_rate": 1.4872673859686475e-05, + "loss": 1.5053, + "step": 3854 + }, + { + "epoch": 0.4, + "learning_rate": 1.4869477209622404e-05, + "loss": 1.4427, + "step": 3855 + }, + { + "epoch": 0.4, + "learning_rate": 1.4866279907173502e-05, + "loss": 1.3404, + "step": 3856 + }, + { + "epoch": 0.4, + "learning_rate": 1.4863081952768126e-05, + "loss": 1.3126, + "step": 3857 + }, + { + "epoch": 0.4, + "learning_rate": 1.4859883346834725e-05, + "loss": 1.4588, + "step": 3858 + }, + { + "epoch": 0.4, + "learning_rate": 1.4856684089801822e-05, + "loss": 1.408, + "step": 3859 + }, + { + "epoch": 0.4, + "learning_rate": 1.4853484182098044e-05, + "loss": 1.4356, + "step": 3860 + }, + { + "epoch": 0.4, + "learning_rate": 1.4850283624152088e-05, + "loss": 1.3768, + "step": 3861 + }, + { + "epoch": 0.4, + "learning_rate": 1.4847082416392753e-05, + "loss": 1.4563, + "step": 3862 + }, + { + "epoch": 0.41, + "learning_rate": 1.4843880559248915e-05, + "loss": 1.3648, + "step": 3863 + }, + { + "epoch": 0.41, + "learning_rate": 1.4840678053149542e-05, + "loss": 1.4146, + "step": 3864 + }, + { + "epoch": 0.41, + "learning_rate": 1.4837474898523686e-05, + "loss": 1.4423, + "step": 3865 + }, + { + "epoch": 0.41, + "learning_rate": 1.4834271095800487e-05, + "loss": 1.3351, + "step": 3866 + }, + { + "epoch": 0.41, + "learning_rate": 1.4831066645409178e-05, + "loss": 1.4534, + "step": 3867 + }, + { + "epoch": 0.41, + "learning_rate": 1.4827861547779066e-05, + "loss": 1.4763, + "step": 3868 + }, + { + "epoch": 0.41, + "learning_rate": 1.4824655803339553e-05, + "loss": 1.4019, + "step": 3869 + }, + { + "epoch": 0.41, + "learning_rate": 1.4821449412520132e-05, + "loss": 1.4223, + "step": 3870 + }, + { + "epoch": 0.41, + "learning_rate": 1.4818242375750371e-05, + "loss": 1.4065, + "step": 3871 + }, + { + "epoch": 0.41, + "learning_rate": 1.481503469345993e-05, + "loss": 1.587, + "step": 3872 + }, + { + "epoch": 0.41, + "learning_rate": 1.4811826366078562e-05, + "loss": 1.3746, + "step": 3873 + }, + { + "epoch": 0.41, + "learning_rate": 1.4808617394036096e-05, + "loss": 1.3425, + "step": 3874 + }, + { + "epoch": 0.41, + "learning_rate": 1.480540777776245e-05, + "loss": 0.6637, + "step": 3875 + }, + { + "epoch": 0.41, + "learning_rate": 1.4802197517687634e-05, + "loss": 1.3366, + "step": 3876 + }, + { + "epoch": 0.41, + "learning_rate": 1.479898661424174e-05, + "loss": 1.4033, + "step": 3877 + }, + { + "epoch": 0.41, + "learning_rate": 1.4795775067854947e-05, + "loss": 1.4005, + "step": 3878 + }, + { + "epoch": 0.41, + "learning_rate": 1.4792562878957516e-05, + "loss": 1.3651, + "step": 3879 + }, + { + "epoch": 0.41, + "learning_rate": 1.47893500479798e-05, + "loss": 1.4185, + "step": 3880 + }, + { + "epoch": 0.41, + "learning_rate": 1.4786136575352236e-05, + "loss": 1.4394, + "step": 3881 + }, + { + "epoch": 0.41, + "learning_rate": 1.478292246150535e-05, + "loss": 1.7243, + "step": 3882 + }, + { + "epoch": 0.41, + "learning_rate": 1.4779707706869744e-05, + "loss": 1.3574, + "step": 3883 + }, + { + "epoch": 0.41, + "learning_rate": 1.4776492311876116e-05, + "loss": 1.4031, + "step": 3884 + }, + { + "epoch": 0.41, + "learning_rate": 1.4773276276955248e-05, + "loss": 1.4351, + "step": 3885 + }, + { + "epoch": 0.41, + "learning_rate": 1.4770059602538002e-05, + "loss": 1.3922, + "step": 3886 + }, + { + "epoch": 0.41, + "learning_rate": 1.4766842289055333e-05, + "loss": 1.3374, + "step": 3887 + }, + { + "epoch": 0.41, + "learning_rate": 1.4763624336938278e-05, + "loss": 1.428, + "step": 3888 + }, + { + "epoch": 0.41, + "learning_rate": 1.476040574661796e-05, + "loss": 1.6087, + "step": 3889 + }, + { + "epoch": 0.41, + "learning_rate": 1.4757186518525586e-05, + "loss": 1.4054, + "step": 3890 + }, + { + "epoch": 0.41, + "learning_rate": 1.4753966653092447e-05, + "loss": 1.2595, + "step": 3891 + }, + { + "epoch": 0.41, + "learning_rate": 1.475074615074993e-05, + "loss": 1.4052, + "step": 3892 + }, + { + "epoch": 0.41, + "learning_rate": 1.4747525011929492e-05, + "loss": 1.4296, + "step": 3893 + }, + { + "epoch": 0.41, + "learning_rate": 1.4744303237062689e-05, + "loss": 1.3718, + "step": 3894 + }, + { + "epoch": 0.41, + "learning_rate": 1.4741080826581151e-05, + "loss": 1.4498, + "step": 3895 + }, + { + "epoch": 0.41, + "learning_rate": 1.4737857780916602e-05, + "loss": 1.4029, + "step": 3896 + }, + { + "epoch": 0.41, + "learning_rate": 1.4734634100500846e-05, + "loss": 1.4136, + "step": 3897 + }, + { + "epoch": 0.41, + "learning_rate": 1.4731409785765774e-05, + "loss": 1.348, + "step": 3898 + }, + { + "epoch": 0.41, + "learning_rate": 1.4728184837143355e-05, + "loss": 1.3407, + "step": 3899 + }, + { + "epoch": 0.41, + "learning_rate": 1.472495925506566e-05, + "loss": 1.3737, + "step": 3900 + }, + { + "epoch": 0.41, + "learning_rate": 1.4721733039964826e-05, + "loss": 2.2305, + "step": 3901 + }, + { + "epoch": 0.41, + "learning_rate": 1.4718506192273087e-05, + "loss": 1.4506, + "step": 3902 + }, + { + "epoch": 0.41, + "learning_rate": 1.4715278712422754e-05, + "loss": 1.3657, + "step": 3903 + }, + { + "epoch": 0.41, + "learning_rate": 1.471205060084623e-05, + "loss": 1.4644, + "step": 3904 + }, + { + "epoch": 0.41, + "learning_rate": 1.4708821857976001e-05, + "loss": 1.4823, + "step": 3905 + }, + { + "epoch": 0.41, + "learning_rate": 1.4705592484244628e-05, + "loss": 1.3392, + "step": 3906 + }, + { + "epoch": 0.41, + "learning_rate": 1.4702362480084769e-05, + "loss": 1.3302, + "step": 3907 + }, + { + "epoch": 0.41, + "learning_rate": 1.4699131845929163e-05, + "loss": 1.8952, + "step": 3908 + }, + { + "epoch": 0.41, + "learning_rate": 1.469590058221063e-05, + "loss": 1.4982, + "step": 3909 + }, + { + "epoch": 0.41, + "learning_rate": 1.4692668689362074e-05, + "loss": 1.407, + "step": 3910 + }, + { + "epoch": 0.41, + "learning_rate": 1.4689436167816489e-05, + "loss": 1.3911, + "step": 3911 + }, + { + "epoch": 0.41, + "learning_rate": 1.4686203018006948e-05, + "loss": 1.3421, + "step": 3912 + }, + { + "epoch": 0.41, + "learning_rate": 1.4682969240366612e-05, + "loss": 1.4627, + "step": 3913 + }, + { + "epoch": 0.41, + "learning_rate": 1.4679734835328718e-05, + "loss": 1.394, + "step": 3914 + }, + { + "epoch": 0.41, + "learning_rate": 1.4676499803326603e-05, + "loss": 1.4484, + "step": 3915 + }, + { + "epoch": 0.41, + "learning_rate": 1.4673264144793673e-05, + "loss": 1.4665, + "step": 3916 + }, + { + "epoch": 0.41, + "learning_rate": 1.4670027860163422e-05, + "loss": 1.3191, + "step": 3917 + }, + { + "epoch": 0.41, + "learning_rate": 1.466679094986943e-05, + "loss": 1.4748, + "step": 3918 + }, + { + "epoch": 0.41, + "learning_rate": 1.4663553414345361e-05, + "loss": 1.2467, + "step": 3919 + }, + { + "epoch": 0.41, + "learning_rate": 1.466031525402496e-05, + "loss": 1.4279, + "step": 3920 + }, + { + "epoch": 0.41, + "learning_rate": 1.4657076469342059e-05, + "loss": 1.3822, + "step": 3921 + }, + { + "epoch": 0.41, + "learning_rate": 1.4653837060730566e-05, + "loss": 1.3659, + "step": 3922 + }, + { + "epoch": 0.41, + "learning_rate": 1.465059702862449e-05, + "loss": 1.3663, + "step": 3923 + }, + { + "epoch": 0.41, + "learning_rate": 1.4647356373457902e-05, + "loss": 1.4371, + "step": 3924 + }, + { + "epoch": 0.41, + "learning_rate": 1.4644115095664972e-05, + "loss": 1.3473, + "step": 3925 + }, + { + "epoch": 0.41, + "learning_rate": 1.4640873195679944e-05, + "loss": 1.4797, + "step": 3926 + }, + { + "epoch": 0.41, + "learning_rate": 1.463763067393715e-05, + "loss": 1.3973, + "step": 3927 + }, + { + "epoch": 0.41, + "learning_rate": 1.4634387530871008e-05, + "loss": 1.3899, + "step": 3928 + }, + { + "epoch": 0.41, + "learning_rate": 1.4631143766916015e-05, + "loss": 1.3828, + "step": 3929 + }, + { + "epoch": 0.41, + "learning_rate": 1.4627899382506745e-05, + "loss": 1.4569, + "step": 3930 + }, + { + "epoch": 0.41, + "learning_rate": 1.4624654378077872e-05, + "loss": 1.4011, + "step": 3931 + }, + { + "epoch": 0.41, + "learning_rate": 1.462140875406414e-05, + "loss": 1.3859, + "step": 3932 + }, + { + "epoch": 0.41, + "learning_rate": 1.4618162510900376e-05, + "loss": 1.4518, + "step": 3933 + }, + { + "epoch": 0.41, + "learning_rate": 1.4614915649021493e-05, + "loss": 1.4399, + "step": 3934 + }, + { + "epoch": 0.41, + "learning_rate": 1.4611668168862495e-05, + "loss": 1.4034, + "step": 3935 + }, + { + "epoch": 0.41, + "learning_rate": 1.4608420070858452e-05, + "loss": 1.3919, + "step": 3936 + }, + { + "epoch": 0.41, + "learning_rate": 1.4605171355444528e-05, + "loss": 1.391, + "step": 3937 + }, + { + "epoch": 0.41, + "learning_rate": 1.460192202305597e-05, + "loss": 1.3717, + "step": 3938 + }, + { + "epoch": 0.41, + "learning_rate": 1.4598672074128103e-05, + "loss": 1.4351, + "step": 3939 + }, + { + "epoch": 0.41, + "learning_rate": 1.4595421509096339e-05, + "loss": 1.4202, + "step": 3940 + }, + { + "epoch": 0.41, + "learning_rate": 1.4592170328396165e-05, + "loss": 1.3559, + "step": 3941 + }, + { + "epoch": 0.41, + "learning_rate": 1.458891853246316e-05, + "loss": 1.5878, + "step": 3942 + }, + { + "epoch": 0.41, + "learning_rate": 1.4585666121732982e-05, + "loss": 1.3818, + "step": 3943 + }, + { + "epoch": 0.41, + "learning_rate": 1.4582413096641369e-05, + "loss": 1.4009, + "step": 3944 + }, + { + "epoch": 0.41, + "learning_rate": 1.457915945762414e-05, + "loss": 1.3937, + "step": 3945 + }, + { + "epoch": 0.41, + "learning_rate": 1.4575905205117203e-05, + "loss": 1.381, + "step": 3946 + }, + { + "epoch": 0.41, + "learning_rate": 1.457265033955654e-05, + "loss": 1.3844, + "step": 3947 + }, + { + "epoch": 0.41, + "learning_rate": 1.4569394861378226e-05, + "loss": 1.4059, + "step": 3948 + }, + { + "epoch": 0.41, + "learning_rate": 1.4566138771018403e-05, + "loss": 1.3698, + "step": 3949 + }, + { + "epoch": 0.41, + "learning_rate": 1.4562882068913311e-05, + "loss": 1.4253, + "step": 3950 + }, + { + "epoch": 0.41, + "learning_rate": 1.455962475549926e-05, + "loss": 1.4284, + "step": 3951 + }, + { + "epoch": 0.41, + "learning_rate": 1.4556366831212647e-05, + "loss": 1.4279, + "step": 3952 + }, + { + "epoch": 0.41, + "learning_rate": 1.4553108296489951e-05, + "loss": 1.3072, + "step": 3953 + }, + { + "epoch": 0.41, + "learning_rate": 1.4549849151767731e-05, + "loss": 1.4175, + "step": 3954 + }, + { + "epoch": 0.41, + "learning_rate": 1.4546589397482632e-05, + "loss": 1.5042, + "step": 3955 + }, + { + "epoch": 0.41, + "learning_rate": 1.4543329034071371e-05, + "loss": 1.4363, + "step": 3956 + }, + { + "epoch": 0.41, + "learning_rate": 1.454006806197076e-05, + "loss": 1.4111, + "step": 3957 + }, + { + "epoch": 0.42, + "learning_rate": 1.453680648161768e-05, + "loss": 1.3817, + "step": 3958 + }, + { + "epoch": 0.42, + "learning_rate": 1.45335442934491e-05, + "loss": 1.4689, + "step": 3959 + }, + { + "epoch": 0.42, + "learning_rate": 1.4530281497902072e-05, + "loss": 1.4164, + "step": 3960 + }, + { + "epoch": 0.42, + "learning_rate": 1.4527018095413726e-05, + "loss": 1.3943, + "step": 3961 + }, + { + "epoch": 0.42, + "learning_rate": 1.4523754086421271e-05, + "loss": 1.3851, + "step": 3962 + }, + { + "epoch": 0.42, + "learning_rate": 1.4520489471362003e-05, + "loss": 1.3907, + "step": 3963 + }, + { + "epoch": 0.42, + "learning_rate": 1.4517224250673297e-05, + "loss": 1.2877, + "step": 3964 + }, + { + "epoch": 0.42, + "learning_rate": 1.4513958424792605e-05, + "loss": 1.4696, + "step": 3965 + }, + { + "epoch": 0.42, + "learning_rate": 1.4510691994157471e-05, + "loss": 1.3785, + "step": 3966 + }, + { + "epoch": 0.42, + "learning_rate": 1.4507424959205505e-05, + "loss": 1.3652, + "step": 3967 + }, + { + "epoch": 0.42, + "learning_rate": 1.4504157320374408e-05, + "loss": 1.4198, + "step": 3968 + }, + { + "epoch": 0.42, + "learning_rate": 1.4500889078101962e-05, + "loss": 1.3476, + "step": 3969 + }, + { + "epoch": 0.42, + "learning_rate": 1.4497620232826028e-05, + "loss": 1.4356, + "step": 3970 + }, + { + "epoch": 0.42, + "learning_rate": 1.4494350784984543e-05, + "loss": 1.4993, + "step": 3971 + }, + { + "epoch": 0.42, + "learning_rate": 1.4491080735015533e-05, + "loss": 1.4022, + "step": 3972 + }, + { + "epoch": 0.42, + "learning_rate": 1.44878100833571e-05, + "loss": 1.4074, + "step": 3973 + }, + { + "epoch": 0.42, + "learning_rate": 1.4484538830447423e-05, + "loss": 1.412, + "step": 3974 + }, + { + "epoch": 0.42, + "learning_rate": 1.4481266976724772e-05, + "loss": 1.3872, + "step": 3975 + }, + { + "epoch": 0.42, + "learning_rate": 1.4477994522627485e-05, + "loss": 1.4575, + "step": 3976 + }, + { + "epoch": 0.42, + "learning_rate": 1.4474721468593995e-05, + "loss": 1.3768, + "step": 3977 + }, + { + "epoch": 0.42, + "learning_rate": 1.44714478150628e-05, + "loss": 1.4173, + "step": 3978 + }, + { + "epoch": 0.42, + "learning_rate": 1.4468173562472489e-05, + "loss": 1.3896, + "step": 3979 + }, + { + "epoch": 0.42, + "learning_rate": 1.4464898711261725e-05, + "loss": 1.4535, + "step": 3980 + }, + { + "epoch": 0.42, + "eval_loss": 1.4580057859420776, + "eval_runtime": 77.4537, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 3980 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 1.780508923972603e+20, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-3980/training_args.bin b/checkpoint-3980/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-3980/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-4378/config.json b/checkpoint-4378/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-4378/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-4378/generation_config.json b/checkpoint-4378/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-4378/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-4378/model-00001-of-00003.safetensors b/checkpoint-4378/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f2218ad2f57faedc2d8f57d8d08a9d887c998f7b --- /dev/null +++ b/checkpoint-4378/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b2f10491f6a4c9a81fa98838c56e0c0dc15ab2b5e1eb595e73b2202eddc795b +size 4943162336 diff --git a/checkpoint-4378/model-00002-of-00003.safetensors b/checkpoint-4378/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5fc93a383b218567fc45f51dd53cd59ad42ebfde --- /dev/null +++ b/checkpoint-4378/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ef047abf777d4ea8d03a857c71b8610c5fac54e736ff84a2fe5f7a1e5c348ff +size 4999819336 diff --git a/checkpoint-4378/model-00003-of-00003.safetensors b/checkpoint-4378/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..821dc9237e02f7c28f22e1c7b367c3918ed9da2f --- /dev/null +++ b/checkpoint-4378/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc2307fa28eef9674d546ef104bc4345074ed8ea054553f5411e74527afae5bb +size 4540516344 diff --git a/checkpoint-4378/model.safetensors.index.json b/checkpoint-4378/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-4378/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-4378/optimizer.pt b/checkpoint-4378/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..bfc87c2e392b548c178b4d15b404f7664845b29d --- /dev/null +++ b/checkpoint-4378/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05642e262792fbe2f50786f92a25c5aa8911980def623bcfb31e9ff1b2adaffe +size 14512103560 diff --git a/checkpoint-4378/rng_state_0.pth b/checkpoint-4378/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..64110d7df213f2c1477d5deeb42f377ce3f16561 --- /dev/null +++ b/checkpoint-4378/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f43f0f70b0dbcc678819df90ae1498097a1a40b141c1b3634f47415b4753e46 +size 15984 diff --git a/checkpoint-4378/rng_state_1.pth b/checkpoint-4378/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..c142cb457f34a9cbc1283279dd22bfebb4736043 --- /dev/null +++ b/checkpoint-4378/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fea0bf58d3a4bfd4cd6e77b671fd76d0f08457d71ef115ed0b7a79d932ccecb +size 15984 diff --git a/checkpoint-4378/rng_state_2.pth b/checkpoint-4378/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..8271c9d62fa47c674c1b31af887486741158480d --- /dev/null +++ b/checkpoint-4378/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:485de881ac346a0d6293f173c620168e2c1c78bb56e9d35b719fe68b9599381c +size 15984 diff --git a/checkpoint-4378/rng_state_3.pth b/checkpoint-4378/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..95c8f6622b054c357c43a3d3a639266aed66c4a8 --- /dev/null +++ b/checkpoint-4378/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb3995c042fb6720f0e6292f2cdbc61899166b759822de9794a63f951332b53d +size 15984 diff --git a/checkpoint-4378/rng_state_4.pth b/checkpoint-4378/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..47b4183577f97c606b478d4239c98658edb8e24d --- /dev/null +++ b/checkpoint-4378/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dc5d0e51cb62121ef22456f6c04b602c2ee63280f1aa9215b5f6ca9ffd945a1 +size 15984 diff --git a/checkpoint-4378/rng_state_5.pth b/checkpoint-4378/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..3e0c7bc1e8320fff16eb12d62f98831d7b4a9baf --- /dev/null +++ b/checkpoint-4378/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf6f7a95413d841f5781a52bd24e6916b171c6b1eae7a534a1e53e4a4d75dda +size 15984 diff --git a/checkpoint-4378/rng_state_6.pth b/checkpoint-4378/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..c2e871831d0ed3b0d078f894c507966f89044a82 --- /dev/null +++ b/checkpoint-4378/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8b59e0c70f333ceeb5e4b4cd778af69cd56a780cd649d81f2b1589c1edb774f +size 15984 diff --git a/checkpoint-4378/rng_state_7.pth b/checkpoint-4378/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..3d467be75d6972b217159ffc2954b5f3f611ab70 --- /dev/null +++ b/checkpoint-4378/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab4acc6cc8c266eed2b1e03455904bdc72f90eae6636da6366d4a9d998a1c278 +size 15984 diff --git a/checkpoint-4378/scheduler.pt b/checkpoint-4378/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..a504b0132f04295902f7c6f96bc6737fd0d6954b --- /dev/null +++ b/checkpoint-4378/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1af220a371509501d386fd9ff9f0356b89a6a12c29fc11e6831618a46a1aa76f +size 1064 diff --git a/checkpoint-4378/special_tokens_map.json b/checkpoint-4378/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-4378/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-4378/tokenizer.model b/checkpoint-4378/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-4378/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-4378/tokenizer_config.json b/checkpoint-4378/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-4378/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-4378/trainer_state.json b/checkpoint-4378/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..dedcd756e0784564529045f7153d356900b54c10 --- /dev/null +++ b/checkpoint-4378/trainer_state.json @@ -0,0 +1,26464 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.4591023489932886, + "eval_steps": 199, + "global_step": 4378, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + }, + { + "epoch": 0.21, + "learning_rate": 1.928689129323009e-05, + "loss": 1.421, + "step": 1991 + }, + { + "epoch": 0.21, + "learning_rate": 1.928553323396003e-05, + "loss": 1.5625, + "step": 1992 + }, + { + "epoch": 0.21, + "learning_rate": 1.92841739306671e-05, + "loss": 1.5198, + "step": 1993 + }, + { + "epoch": 0.21, + "learning_rate": 1.9282813383533415e-05, + "loss": 1.5116, + "step": 1994 + }, + { + "epoch": 0.21, + "learning_rate": 1.9281451592741247e-05, + "loss": 1.4306, + "step": 1995 + }, + { + "epoch": 0.21, + "learning_rate": 1.9280088558473046e-05, + "loss": 1.5425, + "step": 1996 + }, + { + "epoch": 0.21, + "learning_rate": 1.9278724280911424e-05, + "loss": 1.4972, + "step": 1997 + }, + { + "epoch": 0.21, + "learning_rate": 1.9277358760239156e-05, + "loss": 1.5185, + "step": 1998 + }, + { + "epoch": 0.21, + "learning_rate": 1.9275991996639188e-05, + "loss": 1.5187, + "step": 1999 + }, + { + "epoch": 0.21, + "learning_rate": 1.927462399029463e-05, + "loss": 1.4325, + "step": 2000 + }, + { + "epoch": 0.21, + "learning_rate": 1.9273254741388763e-05, + "loss": 1.4397, + "step": 2001 + }, + { + "epoch": 0.21, + "learning_rate": 1.927188425010503e-05, + "loss": 1.5319, + "step": 2002 + }, + { + "epoch": 0.21, + "learning_rate": 1.9270512516627042e-05, + "loss": 1.5664, + "step": 2003 + }, + { + "epoch": 0.21, + "learning_rate": 1.9269139541138574e-05, + "loss": 1.5227, + "step": 2004 + }, + { + "epoch": 0.21, + "learning_rate": 1.926776532382357e-05, + "loss": 1.5187, + "step": 2005 + }, + { + "epoch": 0.21, + "learning_rate": 1.9266389864866134e-05, + "loss": 1.4029, + "step": 2006 + }, + { + "epoch": 0.21, + "learning_rate": 1.9265013164450557e-05, + "loss": 1.387, + "step": 2007 + }, + { + "epoch": 0.21, + "learning_rate": 1.9263635222761268e-05, + "loss": 1.5047, + "step": 2008 + }, + { + "epoch": 0.21, + "learning_rate": 1.9262256039982882e-05, + "loss": 1.4816, + "step": 2009 + }, + { + "epoch": 0.21, + "learning_rate": 1.9260875616300172e-05, + "loss": 1.4607, + "step": 2010 + }, + { + "epoch": 0.21, + "learning_rate": 1.9259493951898084e-05, + "loss": 1.628, + "step": 2011 + }, + { + "epoch": 0.21, + "learning_rate": 1.9258111046961714e-05, + "loss": 1.4149, + "step": 2012 + }, + { + "epoch": 0.21, + "learning_rate": 1.925672690167635e-05, + "loss": 1.5303, + "step": 2013 + }, + { + "epoch": 0.21, + "learning_rate": 1.925534151622742e-05, + "loss": 1.5198, + "step": 2014 + }, + { + "epoch": 0.21, + "learning_rate": 1.9253954890800535e-05, + "loss": 1.6422, + "step": 2015 + }, + { + "epoch": 0.21, + "learning_rate": 1.925256702558147e-05, + "loss": 1.4738, + "step": 2016 + }, + { + "epoch": 0.21, + "learning_rate": 1.925117792075616e-05, + "loss": 1.4752, + "step": 2017 + }, + { + "epoch": 0.21, + "learning_rate": 1.9249787576510713e-05, + "loss": 1.4547, + "step": 2018 + }, + { + "epoch": 0.21, + "learning_rate": 1.924839599303139e-05, + "loss": 1.4864, + "step": 2019 + }, + { + "epoch": 0.21, + "learning_rate": 1.9247003170504638e-05, + "loss": 1.5037, + "step": 2020 + }, + { + "epoch": 0.21, + "learning_rate": 1.9245609109117053e-05, + "loss": 1.5089, + "step": 2021 + }, + { + "epoch": 0.21, + "learning_rate": 1.924421380905541e-05, + "loss": 1.5616, + "step": 2022 + }, + { + "epoch": 0.21, + "learning_rate": 1.9242817270506634e-05, + "loss": 1.4592, + "step": 2023 + }, + { + "epoch": 0.21, + "learning_rate": 1.9241419493657832e-05, + "loss": 1.5592, + "step": 2024 + }, + { + "epoch": 0.21, + "learning_rate": 1.924002047869627e-05, + "loss": 1.4897, + "step": 2025 + }, + { + "epoch": 0.21, + "learning_rate": 1.9238620225809375e-05, + "loss": 1.4743, + "step": 2026 + }, + { + "epoch": 0.21, + "learning_rate": 1.923721873518475e-05, + "loss": 1.4686, + "step": 2027 + }, + { + "epoch": 0.21, + "learning_rate": 1.923581600701016e-05, + "loss": 1.461, + "step": 2028 + }, + { + "epoch": 0.21, + "learning_rate": 1.9234412041473528e-05, + "loss": 1.6622, + "step": 2029 + }, + { + "epoch": 0.21, + "learning_rate": 1.9233006838762955e-05, + "loss": 1.4707, + "step": 2030 + }, + { + "epoch": 0.21, + "learning_rate": 1.92316003990667e-05, + "loss": 1.5566, + "step": 2031 + }, + { + "epoch": 0.21, + "learning_rate": 1.9230192722573188e-05, + "loss": 1.4881, + "step": 2032 + }, + { + "epoch": 0.21, + "learning_rate": 1.9228783809471015e-05, + "loss": 1.6124, + "step": 2033 + }, + { + "epoch": 0.21, + "learning_rate": 1.9227373659948937e-05, + "loss": 1.3508, + "step": 2034 + }, + { + "epoch": 0.21, + "learning_rate": 1.9225962274195876e-05, + "loss": 1.4418, + "step": 2035 + }, + { + "epoch": 0.21, + "learning_rate": 1.9224549652400927e-05, + "loss": 1.3954, + "step": 2036 + }, + { + "epoch": 0.21, + "learning_rate": 1.922313579475334e-05, + "loss": 1.4798, + "step": 2037 + }, + { + "epoch": 0.21, + "learning_rate": 1.922172070144254e-05, + "loss": 1.4556, + "step": 2038 + }, + { + "epoch": 0.21, + "learning_rate": 1.922030437265811e-05, + "loss": 1.4987, + "step": 2039 + }, + { + "epoch": 0.21, + "learning_rate": 1.9218886808589796e-05, + "loss": 1.4857, + "step": 2040 + }, + { + "epoch": 0.21, + "learning_rate": 1.9217468009427527e-05, + "loss": 1.5289, + "step": 2041 + }, + { + "epoch": 0.21, + "learning_rate": 1.921604797536138e-05, + "loss": 1.5267, + "step": 2042 + }, + { + "epoch": 0.21, + "learning_rate": 1.9214626706581598e-05, + "loss": 1.4655, + "step": 2043 + }, + { + "epoch": 0.21, + "learning_rate": 1.9213204203278602e-05, + "loss": 1.4598, + "step": 2044 + }, + { + "epoch": 0.21, + "learning_rate": 1.9211780465642973e-05, + "loss": 1.4766, + "step": 2045 + }, + { + "epoch": 0.21, + "learning_rate": 1.921035549386545e-05, + "loss": 1.5148, + "step": 2046 + }, + { + "epoch": 0.21, + "learning_rate": 1.9208929288136933e-05, + "loss": 1.5567, + "step": 2047 + }, + { + "epoch": 0.21, + "learning_rate": 1.920750184864852e-05, + "loss": 1.4868, + "step": 2048 + }, + { + "epoch": 0.21, + "learning_rate": 1.920607317559143e-05, + "loss": 1.4752, + "step": 2049 + }, + { + "epoch": 0.21, + "learning_rate": 1.920464326915708e-05, + "loss": 1.4882, + "step": 2050 + }, + { + "epoch": 0.22, + "learning_rate": 1.9203212129537035e-05, + "loss": 1.5933, + "step": 2051 + }, + { + "epoch": 0.22, + "learning_rate": 1.9201779756923037e-05, + "loss": 1.4891, + "step": 2052 + }, + { + "epoch": 0.22, + "learning_rate": 1.9200346151506983e-05, + "loss": 1.4486, + "step": 2053 + }, + { + "epoch": 0.22, + "learning_rate": 1.9198911313480938e-05, + "loss": 1.5091, + "step": 2054 + }, + { + "epoch": 0.22, + "learning_rate": 1.919747524303714e-05, + "loss": 1.4385, + "step": 2055 + }, + { + "epoch": 0.22, + "learning_rate": 1.9196037940367974e-05, + "loss": 1.4104, + "step": 2056 + }, + { + "epoch": 0.22, + "learning_rate": 1.9194599405666015e-05, + "loss": 1.4483, + "step": 2057 + }, + { + "epoch": 0.22, + "learning_rate": 1.9193159639123976e-05, + "loss": 1.4592, + "step": 2058 + }, + { + "epoch": 0.22, + "learning_rate": 1.919171864093476e-05, + "loss": 1.4975, + "step": 2059 + }, + { + "epoch": 0.22, + "learning_rate": 1.9190276411291423e-05, + "loss": 1.4727, + "step": 2060 + }, + { + "epoch": 0.22, + "learning_rate": 1.9188832950387178e-05, + "loss": 1.4791, + "step": 2061 + }, + { + "epoch": 0.22, + "learning_rate": 1.9187388258415423e-05, + "loss": 1.3806, + "step": 2062 + }, + { + "epoch": 0.22, + "learning_rate": 1.9185942335569697e-05, + "loss": 1.4514, + "step": 2063 + }, + { + "epoch": 0.22, + "learning_rate": 1.9184495182043727e-05, + "loss": 1.4389, + "step": 2064 + }, + { + "epoch": 0.22, + "learning_rate": 1.918304679803139e-05, + "loss": 1.5088, + "step": 2065 + }, + { + "epoch": 0.22, + "learning_rate": 1.9181597183726733e-05, + "loss": 1.4665, + "step": 2066 + }, + { + "epoch": 0.22, + "learning_rate": 1.9180146339323966e-05, + "loss": 1.489, + "step": 2067 + }, + { + "epoch": 0.22, + "learning_rate": 1.9178694265017466e-05, + "loss": 1.5215, + "step": 2068 + }, + { + "epoch": 0.22, + "learning_rate": 1.9177240961001775e-05, + "loss": 1.5152, + "step": 2069 + }, + { + "epoch": 0.22, + "learning_rate": 1.9175786427471594e-05, + "loss": 1.4418, + "step": 2070 + }, + { + "epoch": 0.22, + "learning_rate": 1.91743306646218e-05, + "loss": 1.5001, + "step": 2071 + }, + { + "epoch": 0.22, + "learning_rate": 1.9172873672647417e-05, + "loss": 1.4879, + "step": 2072 + }, + { + "epoch": 0.22, + "learning_rate": 1.917141545174366e-05, + "loss": 1.5299, + "step": 2073 + }, + { + "epoch": 0.22, + "learning_rate": 1.9169956002105877e-05, + "loss": 1.4602, + "step": 2074 + }, + { + "epoch": 0.22, + "learning_rate": 1.9168495323929605e-05, + "loss": 1.4921, + "step": 2075 + }, + { + "epoch": 0.22, + "learning_rate": 1.916703341741054e-05, + "loss": 1.4659, + "step": 2076 + }, + { + "epoch": 0.22, + "learning_rate": 1.9165570282744534e-05, + "loss": 1.4707, + "step": 2077 + }, + { + "epoch": 0.22, + "learning_rate": 1.9164105920127613e-05, + "loss": 1.5354, + "step": 2078 + }, + { + "epoch": 0.22, + "learning_rate": 1.9162640329755962e-05, + "loss": 1.526, + "step": 2079 + }, + { + "epoch": 0.22, + "learning_rate": 1.916117351182593e-05, + "loss": 1.6424, + "step": 2080 + }, + { + "epoch": 0.22, + "learning_rate": 1.915970546653404e-05, + "loss": 1.5048, + "step": 2081 + }, + { + "epoch": 0.22, + "learning_rate": 1.915823619407697e-05, + "loss": 1.5344, + "step": 2082 + }, + { + "epoch": 0.22, + "learning_rate": 1.915676569465156e-05, + "loss": 1.4604, + "step": 2083 + }, + { + "epoch": 0.22, + "learning_rate": 1.9155293968454826e-05, + "loss": 1.4929, + "step": 2084 + }, + { + "epoch": 0.22, + "learning_rate": 1.9153821015683937e-05, + "loss": 1.4106, + "step": 2085 + }, + { + "epoch": 0.22, + "learning_rate": 1.915234683653623e-05, + "loss": 1.4146, + "step": 2086 + }, + { + "epoch": 0.22, + "learning_rate": 1.9150871431209207e-05, + "loss": 1.4481, + "step": 2087 + }, + { + "epoch": 0.22, + "learning_rate": 1.914939479990054e-05, + "loss": 1.5206, + "step": 2088 + }, + { + "epoch": 0.22, + "learning_rate": 1.9147916942808054e-05, + "loss": 1.5073, + "step": 2089 + }, + { + "epoch": 0.22, + "learning_rate": 1.9146437860129745e-05, + "loss": 1.5196, + "step": 2090 + }, + { + "epoch": 0.22, + "learning_rate": 1.9144957552063775e-05, + "loss": 1.5389, + "step": 2091 + }, + { + "epoch": 0.22, + "learning_rate": 1.9143476018808463e-05, + "loss": 1.5207, + "step": 2092 + }, + { + "epoch": 0.22, + "learning_rate": 1.9141993260562298e-05, + "loss": 1.3717, + "step": 2093 + }, + { + "epoch": 0.22, + "learning_rate": 1.9140509277523937e-05, + "loss": 1.471, + "step": 2094 + }, + { + "epoch": 0.22, + "learning_rate": 1.9139024069892185e-05, + "loss": 1.4553, + "step": 2095 + }, + { + "epoch": 0.22, + "learning_rate": 1.9137537637866027e-05, + "loss": 1.5311, + "step": 2096 + }, + { + "epoch": 0.22, + "learning_rate": 1.9136049981644614e-05, + "loss": 1.4369, + "step": 2097 + }, + { + "epoch": 0.22, + "learning_rate": 1.913456110142724e-05, + "loss": 1.4528, + "step": 2098 + }, + { + "epoch": 0.22, + "learning_rate": 1.9133070997413384e-05, + "loss": 1.5294, + "step": 2099 + }, + { + "epoch": 0.22, + "learning_rate": 1.9131579669802685e-05, + "loss": 1.4588, + "step": 2100 + }, + { + "epoch": 0.22, + "learning_rate": 1.9130087118794934e-05, + "loss": 1.443, + "step": 2101 + }, + { + "epoch": 0.22, + "learning_rate": 1.9128593344590102e-05, + "loss": 1.4876, + "step": 2102 + }, + { + "epoch": 0.22, + "learning_rate": 1.912709834738831e-05, + "loss": 1.4874, + "step": 2103 + }, + { + "epoch": 0.22, + "learning_rate": 1.9125602127389856e-05, + "loss": 1.4966, + "step": 2104 + }, + { + "epoch": 0.22, + "learning_rate": 1.912410468479519e-05, + "loss": 1.5747, + "step": 2105 + }, + { + "epoch": 0.22, + "learning_rate": 1.9122606019804933e-05, + "loss": 1.4025, + "step": 2106 + }, + { + "epoch": 0.22, + "learning_rate": 1.912110613261987e-05, + "loss": 1.4755, + "step": 2107 + }, + { + "epoch": 0.22, + "learning_rate": 1.911960502344094e-05, + "loss": 1.4739, + "step": 2108 + }, + { + "epoch": 0.22, + "learning_rate": 1.911810269246926e-05, + "loss": 1.4992, + "step": 2109 + }, + { + "epoch": 0.22, + "learning_rate": 1.91165991399061e-05, + "loss": 1.4435, + "step": 2110 + }, + { + "epoch": 0.22, + "learning_rate": 1.91150943659529e-05, + "loss": 1.4918, + "step": 2111 + }, + { + "epoch": 0.22, + "learning_rate": 1.9113588370811258e-05, + "loss": 1.3818, + "step": 2112 + }, + { + "epoch": 0.22, + "learning_rate": 1.911208115468294e-05, + "loss": 1.5105, + "step": 2113 + }, + { + "epoch": 0.22, + "learning_rate": 1.9110572717769878e-05, + "loss": 1.6634, + "step": 2114 + }, + { + "epoch": 0.22, + "learning_rate": 1.9109063060274158e-05, + "loss": 1.5028, + "step": 2115 + }, + { + "epoch": 0.22, + "learning_rate": 1.9107552182398037e-05, + "loss": 1.6657, + "step": 2116 + }, + { + "epoch": 0.22, + "learning_rate": 1.9106040084343935e-05, + "loss": 1.5481, + "step": 2117 + }, + { + "epoch": 0.22, + "learning_rate": 1.910452676631444e-05, + "loss": 1.4505, + "step": 2118 + }, + { + "epoch": 0.22, + "learning_rate": 1.9103012228512284e-05, + "loss": 1.5173, + "step": 2119 + }, + { + "epoch": 0.22, + "learning_rate": 1.9101496471140385e-05, + "loss": 1.3788, + "step": 2120 + }, + { + "epoch": 0.22, + "learning_rate": 1.9099979494401814e-05, + "loss": 1.4649, + "step": 2121 + }, + { + "epoch": 0.22, + "learning_rate": 1.9098461298499805e-05, + "loss": 1.4204, + "step": 2122 + }, + { + "epoch": 0.22, + "learning_rate": 1.9096941883637766e-05, + "loss": 1.4439, + "step": 2123 + }, + { + "epoch": 0.22, + "learning_rate": 1.909542125001925e-05, + "loss": 1.6615, + "step": 2124 + }, + { + "epoch": 0.22, + "learning_rate": 1.9093899397847985e-05, + "loss": 1.4763, + "step": 2125 + }, + { + "epoch": 0.22, + "learning_rate": 1.909237632732786e-05, + "loss": 1.5353, + "step": 2126 + }, + { + "epoch": 0.22, + "learning_rate": 1.909085203866293e-05, + "loss": 1.442, + "step": 2127 + }, + { + "epoch": 0.22, + "learning_rate": 1.9089326532057408e-05, + "loss": 1.4782, + "step": 2128 + }, + { + "epoch": 0.22, + "learning_rate": 1.908779980771567e-05, + "loss": 1.4933, + "step": 2129 + }, + { + "epoch": 0.22, + "learning_rate": 1.9086271865842264e-05, + "loss": 1.5285, + "step": 2130 + }, + { + "epoch": 0.22, + "learning_rate": 1.9084742706641894e-05, + "loss": 1.4736, + "step": 2131 + }, + { + "epoch": 0.22, + "learning_rate": 1.9083212330319427e-05, + "loss": 1.4496, + "step": 2132 + }, + { + "epoch": 0.22, + "learning_rate": 1.908168073707989e-05, + "loss": 1.5099, + "step": 2133 + }, + { + "epoch": 0.22, + "learning_rate": 1.9080147927128483e-05, + "loss": 1.5235, + "step": 2134 + }, + { + "epoch": 0.22, + "learning_rate": 1.9078613900670556e-05, + "loss": 1.4769, + "step": 2135 + }, + { + "epoch": 0.22, + "learning_rate": 1.907707865791164e-05, + "loss": 1.5771, + "step": 2136 + }, + { + "epoch": 0.22, + "learning_rate": 1.907554219905741e-05, + "loss": 1.5116, + "step": 2137 + }, + { + "epoch": 0.22, + "learning_rate": 1.907400452431371e-05, + "loss": 1.5161, + "step": 2138 + }, + { + "epoch": 0.22, + "learning_rate": 1.9072465633886557e-05, + "loss": 1.4356, + "step": 2139 + }, + { + "epoch": 0.22, + "learning_rate": 1.9070925527982117e-05, + "loss": 1.509, + "step": 2140 + }, + { + "epoch": 0.22, + "learning_rate": 1.9069384206806723e-05, + "loss": 1.4681, + "step": 2141 + }, + { + "epoch": 0.22, + "learning_rate": 1.9067841670566883e-05, + "loss": 1.5254, + "step": 2142 + }, + { + "epoch": 0.22, + "learning_rate": 1.9066297919469242e-05, + "loss": 1.4797, + "step": 2143 + }, + { + "epoch": 0.22, + "learning_rate": 1.9064752953720636e-05, + "loss": 1.3996, + "step": 2144 + }, + { + "epoch": 0.22, + "learning_rate": 1.9063206773528042e-05, + "loss": 1.4457, + "step": 2145 + }, + { + "epoch": 0.23, + "learning_rate": 1.9061659379098617e-05, + "loss": 1.5126, + "step": 2146 + }, + { + "epoch": 0.23, + "learning_rate": 1.9060110770639664e-05, + "loss": 1.5925, + "step": 2147 + }, + { + "epoch": 0.23, + "learning_rate": 1.905856094835866e-05, + "loss": 1.5146, + "step": 2148 + }, + { + "epoch": 0.23, + "learning_rate": 1.905700991246324e-05, + "loss": 1.7256, + "step": 2149 + }, + { + "epoch": 0.23, + "learning_rate": 1.90554576631612e-05, + "loss": 1.57, + "step": 2150 + }, + { + "epoch": 0.23, + "learning_rate": 1.905390420066051e-05, + "loss": 1.3722, + "step": 2151 + }, + { + "epoch": 0.23, + "learning_rate": 1.9052349525169292e-05, + "loss": 1.3999, + "step": 2152 + }, + { + "epoch": 0.23, + "learning_rate": 1.9050793636895828e-05, + "loss": 1.586, + "step": 2153 + }, + { + "epoch": 0.23, + "learning_rate": 1.9049236536048567e-05, + "loss": 1.4884, + "step": 2154 + }, + { + "epoch": 0.23, + "learning_rate": 1.9047678222836127e-05, + "loss": 1.5898, + "step": 2155 + }, + { + "epoch": 0.23, + "learning_rate": 1.9046118697467278e-05, + "loss": 1.569, + "step": 2156 + }, + { + "epoch": 0.23, + "learning_rate": 1.904455796015095e-05, + "loss": 1.5592, + "step": 2157 + }, + { + "epoch": 0.23, + "learning_rate": 1.9042996011096253e-05, + "loss": 1.597, + "step": 2158 + }, + { + "epoch": 0.23, + "learning_rate": 1.904143285051244e-05, + "loss": 1.422, + "step": 2159 + }, + { + "epoch": 0.23, + "learning_rate": 1.903986847860894e-05, + "loss": 1.519, + "step": 2160 + }, + { + "epoch": 0.23, + "learning_rate": 1.9038302895595334e-05, + "loss": 1.5197, + "step": 2161 + }, + { + "epoch": 0.23, + "learning_rate": 1.903673610168137e-05, + "loss": 1.4655, + "step": 2162 + }, + { + "epoch": 0.23, + "learning_rate": 1.9035168097076965e-05, + "loss": 1.3909, + "step": 2163 + }, + { + "epoch": 0.23, + "learning_rate": 1.903359888199218e-05, + "loss": 1.4877, + "step": 2164 + }, + { + "epoch": 0.23, + "learning_rate": 1.903202845663726e-05, + "loss": 1.5123, + "step": 2165 + }, + { + "epoch": 0.23, + "learning_rate": 1.9030456821222593e-05, + "loss": 1.4906, + "step": 2166 + }, + { + "epoch": 0.23, + "learning_rate": 1.9028883975958745e-05, + "loss": 1.4574, + "step": 2167 + }, + { + "epoch": 0.23, + "learning_rate": 1.9027309921056435e-05, + "loss": 1.4571, + "step": 2168 + }, + { + "epoch": 0.23, + "learning_rate": 1.902573465672654e-05, + "loss": 1.4281, + "step": 2169 + }, + { + "epoch": 0.23, + "learning_rate": 1.9024158183180116e-05, + "loss": 1.5057, + "step": 2170 + }, + { + "epoch": 0.23, + "learning_rate": 1.902258050062836e-05, + "loss": 1.4514, + "step": 2171 + }, + { + "epoch": 0.23, + "learning_rate": 1.9021001609282646e-05, + "loss": 1.5055, + "step": 2172 + }, + { + "epoch": 0.23, + "learning_rate": 1.9019421509354505e-05, + "loss": 1.4578, + "step": 2173 + }, + { + "epoch": 0.23, + "learning_rate": 1.9017840201055625e-05, + "loss": 1.459, + "step": 2174 + }, + { + "epoch": 0.23, + "learning_rate": 1.9016257684597864e-05, + "loss": 1.5059, + "step": 2175 + }, + { + "epoch": 0.23, + "learning_rate": 1.901467396019324e-05, + "loss": 1.57, + "step": 2176 + }, + { + "epoch": 0.23, + "learning_rate": 1.901308902805393e-05, + "loss": 1.4924, + "step": 2177 + }, + { + "epoch": 0.23, + "learning_rate": 1.9011502888392273e-05, + "loss": 1.4979, + "step": 2178 + }, + { + "epoch": 0.23, + "learning_rate": 1.900991554142077e-05, + "loss": 1.5321, + "step": 2179 + }, + { + "epoch": 0.23, + "learning_rate": 1.9008326987352093e-05, + "loss": 1.493, + "step": 2180 + }, + { + "epoch": 0.23, + "learning_rate": 1.9006737226399056e-05, + "loss": 1.5111, + "step": 2181 + }, + { + "epoch": 0.23, + "learning_rate": 1.900514625877465e-05, + "loss": 1.4154, + "step": 2182 + }, + { + "epoch": 0.23, + "learning_rate": 1.900355408469203e-05, + "loss": 1.4934, + "step": 2183 + }, + { + "epoch": 0.23, + "learning_rate": 1.90019607043645e-05, + "loss": 1.5975, + "step": 2184 + }, + { + "epoch": 0.23, + "learning_rate": 1.9000366118005532e-05, + "loss": 1.3537, + "step": 2185 + }, + { + "epoch": 0.23, + "learning_rate": 1.899877032582876e-05, + "loss": 1.4583, + "step": 2186 + }, + { + "epoch": 0.23, + "learning_rate": 1.8997173328047984e-05, + "loss": 1.4586, + "step": 2187 + }, + { + "epoch": 0.23, + "learning_rate": 1.8995575124877156e-05, + "loss": 1.4774, + "step": 2188 + }, + { + "epoch": 0.23, + "learning_rate": 1.8993975716530394e-05, + "loss": 1.5025, + "step": 2189 + }, + { + "epoch": 0.23, + "eval_loss": 1.5263344049453735, + "eval_runtime": 77.1492, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 2189 + }, + { + "epoch": 0.23, + "learning_rate": 1.899237510322198e-05, + "loss": 1.5438, + "step": 2190 + }, + { + "epoch": 0.23, + "learning_rate": 1.899077328516635e-05, + "loss": 1.5181, + "step": 2191 + }, + { + "epoch": 0.23, + "learning_rate": 1.8989170262578112e-05, + "loss": 1.4454, + "step": 2192 + }, + { + "epoch": 0.23, + "learning_rate": 1.8987566035672028e-05, + "loss": 1.4882, + "step": 2193 + }, + { + "epoch": 0.23, + "learning_rate": 1.8985960604663026e-05, + "loss": 1.5073, + "step": 2194 + }, + { + "epoch": 0.23, + "learning_rate": 1.8984353969766187e-05, + "loss": 1.4478, + "step": 2195 + }, + { + "epoch": 0.23, + "learning_rate": 1.8982746131196763e-05, + "loss": 1.4768, + "step": 2196 + }, + { + "epoch": 0.23, + "learning_rate": 1.8981137089170162e-05, + "loss": 1.5116, + "step": 2197 + }, + { + "epoch": 0.23, + "learning_rate": 1.8979526843901952e-05, + "loss": 1.4202, + "step": 2198 + }, + { + "epoch": 0.23, + "learning_rate": 1.8977915395607867e-05, + "loss": 1.4736, + "step": 2199 + }, + { + "epoch": 0.23, + "learning_rate": 1.89763027445038e-05, + "loss": 1.4489, + "step": 2200 + }, + { + "epoch": 0.23, + "learning_rate": 1.8974688890805804e-05, + "loss": 1.4512, + "step": 2201 + }, + { + "epoch": 0.23, + "learning_rate": 1.897307383473009e-05, + "loss": 1.5091, + "step": 2202 + }, + { + "epoch": 0.23, + "learning_rate": 1.897145757649304e-05, + "loss": 1.5512, + "step": 2203 + }, + { + "epoch": 0.23, + "learning_rate": 1.8969840116311192e-05, + "loss": 1.406, + "step": 2204 + }, + { + "epoch": 0.23, + "learning_rate": 1.896822145440124e-05, + "loss": 1.4531, + "step": 2205 + }, + { + "epoch": 0.23, + "learning_rate": 1.896660159098004e-05, + "loss": 1.4379, + "step": 2206 + }, + { + "epoch": 0.23, + "learning_rate": 1.896498052626462e-05, + "loss": 1.4783, + "step": 2207 + }, + { + "epoch": 0.23, + "learning_rate": 1.896335826047216e-05, + "loss": 1.4801, + "step": 2208 + }, + { + "epoch": 0.23, + "learning_rate": 1.896173479381999e-05, + "loss": 1.4526, + "step": 2209 + }, + { + "epoch": 0.23, + "learning_rate": 1.8960110126525627e-05, + "loss": 1.4952, + "step": 2210 + }, + { + "epoch": 0.23, + "learning_rate": 1.895848425880673e-05, + "loss": 1.5299, + "step": 2211 + }, + { + "epoch": 0.23, + "learning_rate": 1.8956857190881125e-05, + "loss": 1.5274, + "step": 2212 + }, + { + "epoch": 0.23, + "learning_rate": 1.8955228922966792e-05, + "loss": 1.4415, + "step": 2213 + }, + { + "epoch": 0.23, + "learning_rate": 1.8953599455281884e-05, + "loss": 1.5311, + "step": 2214 + }, + { + "epoch": 0.23, + "learning_rate": 1.8951968788044702e-05, + "loss": 1.4972, + "step": 2215 + }, + { + "epoch": 0.23, + "learning_rate": 1.8950336921473715e-05, + "loss": 1.4966, + "step": 2216 + }, + { + "epoch": 0.23, + "learning_rate": 1.8948703855787553e-05, + "loss": 1.4683, + "step": 2217 + }, + { + "epoch": 0.23, + "learning_rate": 1.8947069591205005e-05, + "loss": 1.503, + "step": 2218 + }, + { + "epoch": 0.23, + "learning_rate": 1.8945434127945014e-05, + "loss": 1.4902, + "step": 2219 + }, + { + "epoch": 0.23, + "learning_rate": 1.8943797466226702e-05, + "loss": 1.4835, + "step": 2220 + }, + { + "epoch": 0.23, + "learning_rate": 1.8942159606269332e-05, + "loss": 1.535, + "step": 2221 + }, + { + "epoch": 0.23, + "learning_rate": 1.8940520548292332e-05, + "loss": 1.491, + "step": 2222 + }, + { + "epoch": 0.23, + "learning_rate": 1.89388802925153e-05, + "loss": 1.5157, + "step": 2223 + }, + { + "epoch": 0.23, + "learning_rate": 1.8937238839157987e-05, + "loss": 1.4779, + "step": 2224 + }, + { + "epoch": 0.23, + "learning_rate": 1.8935596188440302e-05, + "loss": 1.4902, + "step": 2225 + }, + { + "epoch": 0.23, + "learning_rate": 1.8933952340582323e-05, + "loss": 1.4988, + "step": 2226 + }, + { + "epoch": 0.23, + "learning_rate": 1.893230729580428e-05, + "loss": 1.4568, + "step": 2227 + }, + { + "epoch": 0.23, + "learning_rate": 1.8930661054326567e-05, + "loss": 1.5163, + "step": 2228 + }, + { + "epoch": 0.23, + "learning_rate": 1.892901361636974e-05, + "loss": 1.4472, + "step": 2229 + }, + { + "epoch": 0.23, + "learning_rate": 1.892736498215451e-05, + "loss": 1.4658, + "step": 2230 + }, + { + "epoch": 0.23, + "learning_rate": 1.8925715151901754e-05, + "loss": 1.4281, + "step": 2231 + }, + { + "epoch": 0.23, + "learning_rate": 1.892406412583251e-05, + "loss": 1.415, + "step": 2232 + }, + { + "epoch": 0.23, + "learning_rate": 1.8922411904167966e-05, + "loss": 1.464, + "step": 2233 + }, + { + "epoch": 0.23, + "learning_rate": 1.892075848712948e-05, + "loss": 1.5014, + "step": 2234 + }, + { + "epoch": 0.23, + "learning_rate": 1.8919103874938568e-05, + "loss": 1.4397, + "step": 2235 + }, + { + "epoch": 0.23, + "learning_rate": 1.891744806781691e-05, + "loss": 1.5508, + "step": 2236 + }, + { + "epoch": 0.23, + "learning_rate": 1.8915791065986335e-05, + "loss": 1.4749, + "step": 2237 + }, + { + "epoch": 0.23, + "learning_rate": 1.891413286966884e-05, + "loss": 1.4538, + "step": 2238 + }, + { + "epoch": 0.23, + "learning_rate": 1.891247347908658e-05, + "loss": 1.4405, + "step": 2239 + }, + { + "epoch": 0.23, + "learning_rate": 1.8910812894461878e-05, + "loss": 1.3562, + "step": 2240 + }, + { + "epoch": 0.24, + "learning_rate": 1.89091511160172e-05, + "loss": 1.4811, + "step": 2241 + }, + { + "epoch": 0.24, + "learning_rate": 1.8907488143975186e-05, + "loss": 1.4286, + "step": 2242 + }, + { + "epoch": 0.24, + "learning_rate": 1.890582397855863e-05, + "loss": 1.4493, + "step": 2243 + }, + { + "epoch": 0.24, + "learning_rate": 1.890415861999049e-05, + "loss": 1.5639, + "step": 2244 + }, + { + "epoch": 0.24, + "learning_rate": 1.890249206849388e-05, + "loss": 1.6375, + "step": 2245 + }, + { + "epoch": 0.24, + "learning_rate": 1.890082432429208e-05, + "loss": 1.4982, + "step": 2246 + }, + { + "epoch": 0.24, + "learning_rate": 1.889915538760851e-05, + "loss": 1.492, + "step": 2247 + }, + { + "epoch": 0.24, + "learning_rate": 1.8897485258666778e-05, + "loss": 1.4294, + "step": 2248 + }, + { + "epoch": 0.24, + "learning_rate": 1.8895813937690638e-05, + "loss": 1.4617, + "step": 2249 + }, + { + "epoch": 0.24, + "learning_rate": 1.8894141424904e-05, + "loss": 1.4763, + "step": 2250 + }, + { + "epoch": 0.24, + "learning_rate": 1.8892467720530937e-05, + "loss": 1.3989, + "step": 2251 + }, + { + "epoch": 0.24, + "learning_rate": 1.8890792824795687e-05, + "loss": 1.4803, + "step": 2252 + }, + { + "epoch": 0.24, + "learning_rate": 1.8889116737922638e-05, + "loss": 1.4734, + "step": 2253 + }, + { + "epoch": 0.24, + "learning_rate": 1.8887439460136342e-05, + "loss": 1.5069, + "step": 2254 + }, + { + "epoch": 0.24, + "learning_rate": 1.8885760991661514e-05, + "loss": 1.5565, + "step": 2255 + }, + { + "epoch": 0.24, + "learning_rate": 1.8884081332723028e-05, + "loss": 1.4707, + "step": 2256 + }, + { + "epoch": 0.24, + "learning_rate": 1.8882400483545913e-05, + "loss": 1.5077, + "step": 2257 + }, + { + "epoch": 0.24, + "learning_rate": 1.888071844435536e-05, + "loss": 1.5075, + "step": 2258 + }, + { + "epoch": 0.24, + "learning_rate": 1.8879035215376717e-05, + "loss": 1.5185, + "step": 2259 + }, + { + "epoch": 0.24, + "learning_rate": 1.887735079683549e-05, + "loss": 1.6266, + "step": 2260 + }, + { + "epoch": 0.24, + "learning_rate": 1.8875665188957354e-05, + "loss": 1.5013, + "step": 2261 + }, + { + "epoch": 0.24, + "learning_rate": 1.887397839196814e-05, + "loss": 1.4362, + "step": 2262 + }, + { + "epoch": 0.24, + "learning_rate": 1.8872290406093827e-05, + "loss": 1.4718, + "step": 2263 + }, + { + "epoch": 0.24, + "learning_rate": 1.8870601231560567e-05, + "loss": 1.5202, + "step": 2264 + }, + { + "epoch": 0.24, + "learning_rate": 1.8868910868594664e-05, + "loss": 1.5168, + "step": 2265 + }, + { + "epoch": 0.24, + "learning_rate": 1.8867219317422588e-05, + "loss": 1.5142, + "step": 2266 + }, + { + "epoch": 0.24, + "learning_rate": 1.8865526578270954e-05, + "loss": 1.4885, + "step": 2267 + }, + { + "epoch": 0.24, + "learning_rate": 1.8863832651366552e-05, + "loss": 1.5441, + "step": 2268 + }, + { + "epoch": 0.24, + "learning_rate": 1.8862137536936328e-05, + "loss": 1.4647, + "step": 2269 + }, + { + "epoch": 0.24, + "learning_rate": 1.8860441235207374e-05, + "loss": 1.5352, + "step": 2270 + }, + { + "epoch": 0.24, + "learning_rate": 1.8858743746406958e-05, + "loss": 1.4568, + "step": 2271 + }, + { + "epoch": 0.24, + "learning_rate": 1.8857045070762497e-05, + "loss": 1.4865, + "step": 2272 + }, + { + "epoch": 0.24, + "learning_rate": 1.8855345208501573e-05, + "loss": 1.4637, + "step": 2273 + }, + { + "epoch": 0.24, + "learning_rate": 1.8853644159851918e-05, + "loss": 1.4348, + "step": 2274 + }, + { + "epoch": 0.24, + "learning_rate": 1.8851941925041436e-05, + "loss": 1.4413, + "step": 2275 + }, + { + "epoch": 0.24, + "learning_rate": 1.8850238504298177e-05, + "loss": 1.4434, + "step": 2276 + }, + { + "epoch": 0.24, + "learning_rate": 1.884853389785036e-05, + "loss": 1.4822, + "step": 2277 + }, + { + "epoch": 0.24, + "learning_rate": 1.8846828105926356e-05, + "loss": 1.4632, + "step": 2278 + }, + { + "epoch": 0.24, + "learning_rate": 1.8845121128754698e-05, + "loss": 1.48, + "step": 2279 + }, + { + "epoch": 0.24, + "learning_rate": 1.8843412966564078e-05, + "loss": 1.4518, + "step": 2280 + }, + { + "epoch": 0.24, + "learning_rate": 1.884170361958334e-05, + "loss": 1.4334, + "step": 2281 + }, + { + "epoch": 0.24, + "learning_rate": 1.8839993088041502e-05, + "loss": 1.5131, + "step": 2282 + }, + { + "epoch": 0.24, + "learning_rate": 1.8838281372167724e-05, + "loss": 1.508, + "step": 2283 + }, + { + "epoch": 0.24, + "learning_rate": 1.8836568472191335e-05, + "loss": 1.4086, + "step": 2284 + }, + { + "epoch": 0.24, + "learning_rate": 1.883485438834182e-05, + "loss": 1.5021, + "step": 2285 + }, + { + "epoch": 0.24, + "learning_rate": 1.8833139120848817e-05, + "loss": 1.5083, + "step": 2286 + }, + { + "epoch": 0.24, + "learning_rate": 1.8831422669942137e-05, + "loss": 1.4162, + "step": 2287 + }, + { + "epoch": 0.24, + "learning_rate": 1.8829705035851734e-05, + "loss": 1.5494, + "step": 2288 + }, + { + "epoch": 0.24, + "learning_rate": 1.8827986218807724e-05, + "loss": 1.425, + "step": 2289 + }, + { + "epoch": 0.24, + "learning_rate": 1.8826266219040396e-05, + "loss": 1.5215, + "step": 2290 + }, + { + "epoch": 0.24, + "learning_rate": 1.8824545036780172e-05, + "loss": 1.5577, + "step": 2291 + }, + { + "epoch": 0.24, + "learning_rate": 1.8822822672257655e-05, + "loss": 1.4923, + "step": 2292 + }, + { + "epoch": 0.24, + "learning_rate": 1.8821099125703595e-05, + "loss": 1.4648, + "step": 2293 + }, + { + "epoch": 0.24, + "learning_rate": 1.8819374397348902e-05, + "loss": 1.471, + "step": 2294 + }, + { + "epoch": 0.24, + "learning_rate": 1.8817648487424648e-05, + "loss": 1.5658, + "step": 2295 + }, + { + "epoch": 0.24, + "learning_rate": 1.8815921396162058e-05, + "loss": 1.5348, + "step": 2296 + }, + { + "epoch": 0.24, + "learning_rate": 1.8814193123792518e-05, + "loss": 1.4081, + "step": 2297 + }, + { + "epoch": 0.24, + "learning_rate": 1.881246367054757e-05, + "loss": 1.4762, + "step": 2298 + }, + { + "epoch": 0.24, + "learning_rate": 1.8810733036658925e-05, + "loss": 1.4399, + "step": 2299 + }, + { + "epoch": 0.24, + "learning_rate": 1.8809001222358432e-05, + "loss": 1.4763, + "step": 2300 + }, + { + "epoch": 0.24, + "learning_rate": 1.880726822787812e-05, + "loss": 1.4874, + "step": 2301 + }, + { + "epoch": 0.24, + "learning_rate": 1.880553405345016e-05, + "loss": 1.4951, + "step": 2302 + }, + { + "epoch": 0.24, + "learning_rate": 1.8803798699306887e-05, + "loss": 1.4697, + "step": 2303 + }, + { + "epoch": 0.24, + "learning_rate": 1.880206216568079e-05, + "loss": 1.481, + "step": 2304 + }, + { + "epoch": 0.24, + "learning_rate": 1.880032445280453e-05, + "loss": 1.4485, + "step": 2305 + }, + { + "epoch": 0.24, + "learning_rate": 1.879858556091091e-05, + "loss": 1.4749, + "step": 2306 + }, + { + "epoch": 0.24, + "learning_rate": 1.8796845490232894e-05, + "loss": 1.5605, + "step": 2307 + }, + { + "epoch": 0.24, + "learning_rate": 1.879510424100361e-05, + "loss": 1.4835, + "step": 2308 + }, + { + "epoch": 0.24, + "learning_rate": 1.8793361813456346e-05, + "loss": 1.4344, + "step": 2309 + }, + { + "epoch": 0.24, + "learning_rate": 1.8791618207824532e-05, + "loss": 1.4571, + "step": 2310 + }, + { + "epoch": 0.24, + "learning_rate": 1.8789873424341772e-05, + "loss": 1.482, + "step": 2311 + }, + { + "epoch": 0.24, + "learning_rate": 1.8788127463241822e-05, + "loss": 1.4736, + "step": 2312 + }, + { + "epoch": 0.24, + "learning_rate": 1.8786380324758597e-05, + "loss": 1.4807, + "step": 2313 + }, + { + "epoch": 0.24, + "learning_rate": 1.8784632009126167e-05, + "loss": 1.4418, + "step": 2314 + }, + { + "epoch": 0.24, + "learning_rate": 1.878288251657876e-05, + "loss": 1.5248, + "step": 2315 + }, + { + "epoch": 0.24, + "learning_rate": 1.8781131847350768e-05, + "loss": 1.483, + "step": 2316 + }, + { + "epoch": 0.24, + "learning_rate": 1.877938000167673e-05, + "loss": 1.5474, + "step": 2317 + }, + { + "epoch": 0.24, + "learning_rate": 1.8777626979791347e-05, + "loss": 1.4671, + "step": 2318 + }, + { + "epoch": 0.24, + "learning_rate": 1.877587278192949e-05, + "loss": 1.3049, + "step": 2319 + }, + { + "epoch": 0.24, + "learning_rate": 1.877411740832616e-05, + "loss": 1.483, + "step": 2320 + }, + { + "epoch": 0.24, + "learning_rate": 1.877236085921655e-05, + "loss": 1.508, + "step": 2321 + }, + { + "epoch": 0.24, + "learning_rate": 1.8770603134835978e-05, + "loss": 1.4854, + "step": 2322 + }, + { + "epoch": 0.24, + "learning_rate": 1.8768844235419942e-05, + "loss": 1.4808, + "step": 2323 + }, + { + "epoch": 0.24, + "learning_rate": 1.8767084161204087e-05, + "loss": 1.5352, + "step": 2324 + }, + { + "epoch": 0.24, + "learning_rate": 1.8765322912424214e-05, + "loss": 1.5628, + "step": 2325 + }, + { + "epoch": 0.24, + "learning_rate": 1.8763560489316292e-05, + "loss": 1.494, + "step": 2326 + }, + { + "epoch": 0.24, + "learning_rate": 1.876179689211643e-05, + "loss": 1.509, + "step": 2327 + }, + { + "epoch": 0.24, + "learning_rate": 1.8760032121060918e-05, + "loss": 1.5021, + "step": 2328 + }, + { + "epoch": 0.24, + "learning_rate": 1.875826617638618e-05, + "loss": 1.4179, + "step": 2329 + }, + { + "epoch": 0.24, + "learning_rate": 1.8756499058328813e-05, + "loss": 1.4302, + "step": 2330 + }, + { + "epoch": 0.24, + "learning_rate": 1.8754730767125564e-05, + "loss": 1.4959, + "step": 2331 + }, + { + "epoch": 0.24, + "learning_rate": 1.8752961303013336e-05, + "loss": 1.4423, + "step": 2332 + }, + { + "epoch": 0.24, + "learning_rate": 1.8751190666229194e-05, + "loss": 1.4564, + "step": 2333 + }, + { + "epoch": 0.24, + "learning_rate": 1.8749418857010358e-05, + "loss": 1.4775, + "step": 2334 + }, + { + "epoch": 0.24, + "learning_rate": 1.8747645875594203e-05, + "loss": 1.4182, + "step": 2335 + }, + { + "epoch": 0.24, + "learning_rate": 1.8745871722218265e-05, + "loss": 1.3957, + "step": 2336 + }, + { + "epoch": 0.25, + "learning_rate": 1.8744096397120235e-05, + "loss": 1.4633, + "step": 2337 + }, + { + "epoch": 0.25, + "learning_rate": 1.874231990053796e-05, + "loss": 1.5512, + "step": 2338 + }, + { + "epoch": 0.25, + "learning_rate": 1.8740542232709444e-05, + "loss": 1.3461, + "step": 2339 + }, + { + "epoch": 0.25, + "learning_rate": 1.8738763393872848e-05, + "loss": 1.4754, + "step": 2340 + }, + { + "epoch": 0.25, + "learning_rate": 1.8736983384266495e-05, + "loss": 1.5448, + "step": 2341 + }, + { + "epoch": 0.25, + "learning_rate": 1.8735202204128854e-05, + "loss": 1.4491, + "step": 2342 + }, + { + "epoch": 0.25, + "learning_rate": 1.8733419853698566e-05, + "loss": 1.457, + "step": 2343 + }, + { + "epoch": 0.25, + "learning_rate": 1.8731636333214414e-05, + "loss": 1.4314, + "step": 2344 + }, + { + "epoch": 0.25, + "learning_rate": 1.8729851642915345e-05, + "loss": 1.3979, + "step": 2345 + }, + { + "epoch": 0.25, + "learning_rate": 1.8728065783040464e-05, + "loss": 1.4146, + "step": 2346 + }, + { + "epoch": 0.25, + "learning_rate": 1.8726278753829027e-05, + "loss": 1.4361, + "step": 2347 + }, + { + "epoch": 0.25, + "learning_rate": 1.872449055552045e-05, + "loss": 1.4989, + "step": 2348 + }, + { + "epoch": 0.25, + "learning_rate": 1.872270118835431e-05, + "loss": 1.5062, + "step": 2349 + }, + { + "epoch": 0.25, + "learning_rate": 1.872091065257033e-05, + "loss": 1.4509, + "step": 2350 + }, + { + "epoch": 0.25, + "learning_rate": 1.8719118948408403e-05, + "loss": 1.4631, + "step": 2351 + }, + { + "epoch": 0.25, + "learning_rate": 1.8717326076108566e-05, + "loss": 1.5119, + "step": 2352 + }, + { + "epoch": 0.25, + "learning_rate": 1.8715532035911017e-05, + "loss": 1.6347, + "step": 2353 + }, + { + "epoch": 0.25, + "learning_rate": 1.8713736828056115e-05, + "loss": 1.5526, + "step": 2354 + }, + { + "epoch": 0.25, + "learning_rate": 1.8711940452784368e-05, + "loss": 1.6348, + "step": 2355 + }, + { + "epoch": 0.25, + "learning_rate": 1.871014291033645e-05, + "loss": 1.5183, + "step": 2356 + }, + { + "epoch": 0.25, + "learning_rate": 1.8708344200953182e-05, + "loss": 1.458, + "step": 2357 + }, + { + "epoch": 0.25, + "learning_rate": 1.8706544324875545e-05, + "loss": 1.524, + "step": 2358 + }, + { + "epoch": 0.25, + "learning_rate": 1.8704743282344672e-05, + "loss": 1.4479, + "step": 2359 + }, + { + "epoch": 0.25, + "learning_rate": 1.870294107360186e-05, + "loss": 1.5408, + "step": 2360 + }, + { + "epoch": 0.25, + "learning_rate": 1.8701137698888563e-05, + "loss": 1.5007, + "step": 2361 + }, + { + "epoch": 0.25, + "learning_rate": 1.8699333158446382e-05, + "loss": 1.5132, + "step": 2362 + }, + { + "epoch": 0.25, + "learning_rate": 1.869752745251708e-05, + "loss": 1.4263, + "step": 2363 + }, + { + "epoch": 0.25, + "learning_rate": 1.8695720581342574e-05, + "loss": 1.422, + "step": 2364 + }, + { + "epoch": 0.25, + "learning_rate": 1.869391254516494e-05, + "loss": 1.4411, + "step": 2365 + }, + { + "epoch": 0.25, + "learning_rate": 1.8692103344226406e-05, + "loss": 1.4594, + "step": 2366 + }, + { + "epoch": 0.25, + "learning_rate": 1.8690292978769364e-05, + "loss": 1.4992, + "step": 2367 + }, + { + "epoch": 0.25, + "learning_rate": 1.868848144903635e-05, + "loss": 1.4822, + "step": 2368 + }, + { + "epoch": 0.25, + "learning_rate": 1.8686668755270064e-05, + "loss": 1.5402, + "step": 2369 + }, + { + "epoch": 0.25, + "learning_rate": 1.8684854897713363e-05, + "loss": 1.5268, + "step": 2370 + }, + { + "epoch": 0.25, + "learning_rate": 1.8683039876609258e-05, + "loss": 1.5587, + "step": 2371 + }, + { + "epoch": 0.25, + "learning_rate": 1.868122369220091e-05, + "loss": 1.4214, + "step": 2372 + }, + { + "epoch": 0.25, + "learning_rate": 1.8679406344731645e-05, + "loss": 1.5089, + "step": 2373 + }, + { + "epoch": 0.25, + "learning_rate": 1.867758783444494e-05, + "loss": 1.5067, + "step": 2374 + }, + { + "epoch": 0.25, + "learning_rate": 1.8675768161584427e-05, + "loss": 2.0616, + "step": 2375 + }, + { + "epoch": 0.25, + "learning_rate": 1.8673947326393903e-05, + "loss": 1.5617, + "step": 2376 + }, + { + "epoch": 0.25, + "learning_rate": 1.86721253291173e-05, + "loss": 1.4422, + "step": 2377 + }, + { + "epoch": 0.25, + "learning_rate": 1.867030216999873e-05, + "loss": 1.4727, + "step": 2378 + }, + { + "epoch": 0.25, + "learning_rate": 1.8668477849282443e-05, + "loss": 1.4152, + "step": 2379 + }, + { + "epoch": 0.25, + "learning_rate": 1.8666652367212856e-05, + "loss": 1.4376, + "step": 2380 + }, + { + "epoch": 0.25, + "learning_rate": 1.8664825724034534e-05, + "loss": 1.393, + "step": 2381 + }, + { + "epoch": 0.25, + "learning_rate": 1.8662997919992197e-05, + "loss": 1.4864, + "step": 2382 + }, + { + "epoch": 0.25, + "learning_rate": 1.866116895533073e-05, + "loss": 1.4261, + "step": 2383 + }, + { + "epoch": 0.25, + "learning_rate": 1.8659338830295163e-05, + "loss": 1.4555, + "step": 2384 + }, + { + "epoch": 0.25, + "learning_rate": 1.8657507545130687e-05, + "loss": 1.4939, + "step": 2385 + }, + { + "epoch": 0.25, + "learning_rate": 1.865567510008265e-05, + "loss": 1.4123, + "step": 2386 + }, + { + "epoch": 0.25, + "learning_rate": 1.8653841495396546e-05, + "loss": 1.4459, + "step": 2387 + }, + { + "epoch": 0.25, + "learning_rate": 1.8652006731318038e-05, + "loss": 1.396, + "step": 2388 + }, + { + "epoch": 0.25, + "eval_loss": 1.5139706134796143, + "eval_runtime": 77.2904, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 2388 + }, + { + "epoch": 0.25, + "learning_rate": 1.8650170808092936e-05, + "loss": 1.4666, + "step": 2389 + }, + { + "epoch": 0.25, + "learning_rate": 1.86483337259672e-05, + "loss": 1.5154, + "step": 2390 + }, + { + "epoch": 0.25, + "learning_rate": 1.864649548518696e-05, + "loss": 1.5163, + "step": 2391 + }, + { + "epoch": 0.25, + "learning_rate": 1.864465608599849e-05, + "loss": 1.4734, + "step": 2392 + }, + { + "epoch": 0.25, + "learning_rate": 1.864281552864822e-05, + "loss": 1.5217, + "step": 2393 + }, + { + "epoch": 0.25, + "learning_rate": 1.8640973813382737e-05, + "loss": 1.4694, + "step": 2394 + }, + { + "epoch": 0.25, + "learning_rate": 1.863913094044879e-05, + "loss": 1.4761, + "step": 2395 + }, + { + "epoch": 0.25, + "learning_rate": 1.863728691009327e-05, + "loss": 1.4766, + "step": 2396 + }, + { + "epoch": 0.25, + "learning_rate": 1.863544172256323e-05, + "loss": 1.5695, + "step": 2397 + }, + { + "epoch": 0.25, + "learning_rate": 1.8633595378105882e-05, + "loss": 1.5079, + "step": 2398 + }, + { + "epoch": 0.25, + "learning_rate": 1.8631747876968584e-05, + "loss": 1.4154, + "step": 2399 + }, + { + "epoch": 0.25, + "learning_rate": 1.862989921939886e-05, + "loss": 1.4488, + "step": 2400 + }, + { + "epoch": 0.25, + "learning_rate": 1.8628049405644376e-05, + "loss": 1.4279, + "step": 2401 + }, + { + "epoch": 0.25, + "learning_rate": 1.8626198435952966e-05, + "loss": 1.4896, + "step": 2402 + }, + { + "epoch": 0.25, + "learning_rate": 1.8624346310572602e-05, + "loss": 1.4315, + "step": 2403 + }, + { + "epoch": 0.25, + "learning_rate": 1.862249302975143e-05, + "loss": 1.4919, + "step": 2404 + }, + { + "epoch": 0.25, + "learning_rate": 1.8620638593737743e-05, + "loss": 1.4561, + "step": 2405 + }, + { + "epoch": 0.25, + "learning_rate": 1.8618783002779985e-05, + "loss": 1.4622, + "step": 2406 + }, + { + "epoch": 0.25, + "learning_rate": 1.8616926257126754e-05, + "loss": 1.4917, + "step": 2407 + }, + { + "epoch": 0.25, + "learning_rate": 1.861506835702681e-05, + "loss": 1.4962, + "step": 2408 + }, + { + "epoch": 0.25, + "learning_rate": 1.861320930272906e-05, + "loss": 1.4164, + "step": 2409 + }, + { + "epoch": 0.25, + "learning_rate": 1.8611349094482578e-05, + "loss": 1.4889, + "step": 2410 + }, + { + "epoch": 0.25, + "learning_rate": 1.8609487732536576e-05, + "loss": 1.543, + "step": 2411 + }, + { + "epoch": 0.25, + "learning_rate": 1.8607625217140433e-05, + "loss": 1.5417, + "step": 2412 + }, + { + "epoch": 0.25, + "learning_rate": 1.8605761548543674e-05, + "loss": 1.5304, + "step": 2413 + }, + { + "epoch": 0.25, + "learning_rate": 1.860389672699599e-05, + "loss": 1.4725, + "step": 2414 + }, + { + "epoch": 0.25, + "learning_rate": 1.860203075274721e-05, + "loss": 1.4745, + "step": 2415 + }, + { + "epoch": 0.25, + "learning_rate": 1.8600163626047334e-05, + "loss": 1.4656, + "step": 2416 + }, + { + "epoch": 0.25, + "learning_rate": 1.8598295347146503e-05, + "loss": 1.5287, + "step": 2417 + }, + { + "epoch": 0.25, + "learning_rate": 1.8596425916295023e-05, + "loss": 1.5024, + "step": 2418 + }, + { + "epoch": 0.25, + "learning_rate": 1.8594555333743348e-05, + "loss": 1.4527, + "step": 2419 + }, + { + "epoch": 0.25, + "learning_rate": 1.859268359974209e-05, + "loss": 1.4897, + "step": 2420 + }, + { + "epoch": 0.25, + "learning_rate": 1.859081071454201e-05, + "loss": 1.3554, + "step": 2421 + }, + { + "epoch": 0.25, + "learning_rate": 1.858893667839403e-05, + "loss": 1.4004, + "step": 2422 + }, + { + "epoch": 0.25, + "learning_rate": 1.858706149154922e-05, + "loss": 1.5582, + "step": 2423 + }, + { + "epoch": 0.25, + "learning_rate": 1.8585185154258803e-05, + "loss": 1.505, + "step": 2424 + }, + { + "epoch": 0.25, + "learning_rate": 1.858330766677417e-05, + "loss": 1.5043, + "step": 2425 + }, + { + "epoch": 0.25, + "learning_rate": 1.858142902934685e-05, + "loss": 1.439, + "step": 2426 + }, + { + "epoch": 0.25, + "learning_rate": 1.857954924222853e-05, + "loss": 1.4927, + "step": 2427 + }, + { + "epoch": 0.25, + "learning_rate": 1.8577668305671056e-05, + "loss": 1.5395, + "step": 2428 + }, + { + "epoch": 0.25, + "learning_rate": 1.8575786219926427e-05, + "loss": 1.4737, + "step": 2429 + }, + { + "epoch": 0.25, + "learning_rate": 1.8573902985246794e-05, + "loss": 1.6151, + "step": 2430 + }, + { + "epoch": 0.25, + "learning_rate": 1.857201860188446e-05, + "loss": 1.4313, + "step": 2431 + }, + { + "epoch": 0.26, + "learning_rate": 1.857013307009188e-05, + "loss": 1.4509, + "step": 2432 + }, + { + "epoch": 0.26, + "learning_rate": 1.8568246390121673e-05, + "loss": 1.3998, + "step": 2433 + }, + { + "epoch": 0.26, + "learning_rate": 1.8566358562226603e-05, + "loss": 1.5268, + "step": 2434 + }, + { + "epoch": 0.26, + "learning_rate": 1.8564469586659593e-05, + "loss": 1.4369, + "step": 2435 + }, + { + "epoch": 0.26, + "learning_rate": 1.8562579463673713e-05, + "loss": 1.4759, + "step": 2436 + }, + { + "epoch": 0.26, + "learning_rate": 1.8560688193522197e-05, + "loss": 1.4092, + "step": 2437 + }, + { + "epoch": 0.26, + "learning_rate": 1.855879577645842e-05, + "loss": 1.43, + "step": 2438 + }, + { + "epoch": 0.26, + "learning_rate": 1.855690221273592e-05, + "loss": 1.5143, + "step": 2439 + }, + { + "epoch": 0.26, + "learning_rate": 1.8555007502608385e-05, + "loss": 1.5482, + "step": 2440 + }, + { + "epoch": 0.26, + "learning_rate": 1.855311164632966e-05, + "loss": 1.4406, + "step": 2441 + }, + { + "epoch": 0.26, + "learning_rate": 1.8551214644153738e-05, + "loss": 1.4551, + "step": 2442 + }, + { + "epoch": 0.26, + "learning_rate": 1.8549316496334774e-05, + "loss": 1.4663, + "step": 2443 + }, + { + "epoch": 0.26, + "learning_rate": 1.8547417203127064e-05, + "loss": 1.4732, + "step": 2444 + }, + { + "epoch": 0.26, + "learning_rate": 1.8545516764785067e-05, + "loss": 1.5378, + "step": 2445 + }, + { + "epoch": 0.26, + "learning_rate": 1.8543615181563397e-05, + "loss": 1.4448, + "step": 2446 + }, + { + "epoch": 0.26, + "learning_rate": 1.854171245371681e-05, + "loss": 1.2861, + "step": 2447 + }, + { + "epoch": 0.26, + "learning_rate": 1.8539808581500228e-05, + "loss": 1.4405, + "step": 2448 + }, + { + "epoch": 0.26, + "learning_rate": 1.8537903565168716e-05, + "loss": 1.4876, + "step": 2449 + }, + { + "epoch": 0.26, + "learning_rate": 1.8535997404977506e-05, + "loss": 1.4119, + "step": 2450 + }, + { + "epoch": 0.26, + "learning_rate": 1.8534090101181967e-05, + "loss": 1.4451, + "step": 2451 + }, + { + "epoch": 0.26, + "learning_rate": 1.8532181654037632e-05, + "loss": 1.4035, + "step": 2452 + }, + { + "epoch": 0.26, + "learning_rate": 1.853027206380018e-05, + "loss": 1.4624, + "step": 2453 + }, + { + "epoch": 0.26, + "learning_rate": 1.852836133072545e-05, + "loss": 1.4935, + "step": 2454 + }, + { + "epoch": 0.26, + "learning_rate": 1.8526449455069434e-05, + "loss": 1.4834, + "step": 2455 + }, + { + "epoch": 0.26, + "learning_rate": 1.8524536437088266e-05, + "loss": 1.498, + "step": 2456 + }, + { + "epoch": 0.26, + "learning_rate": 1.8522622277038247e-05, + "loss": 1.3417, + "step": 2457 + }, + { + "epoch": 0.26, + "learning_rate": 1.852070697517583e-05, + "loss": 1.4455, + "step": 2458 + }, + { + "epoch": 0.26, + "learning_rate": 1.8518790531757607e-05, + "loss": 1.4119, + "step": 2459 + }, + { + "epoch": 0.26, + "learning_rate": 1.8516872947040337e-05, + "loss": 1.558, + "step": 2460 + }, + { + "epoch": 0.26, + "learning_rate": 1.8514954221280926e-05, + "loss": 1.4862, + "step": 2461 + }, + { + "epoch": 0.26, + "learning_rate": 1.8513034354736433e-05, + "loss": 1.6806, + "step": 2462 + }, + { + "epoch": 0.26, + "learning_rate": 1.8511113347664072e-05, + "loss": 1.438, + "step": 2463 + }, + { + "epoch": 0.26, + "learning_rate": 1.850919120032121e-05, + "loss": 1.4975, + "step": 2464 + }, + { + "epoch": 0.26, + "learning_rate": 1.850726791296536e-05, + "loss": 1.4409, + "step": 2465 + }, + { + "epoch": 0.26, + "learning_rate": 1.85053434858542e-05, + "loss": 1.4769, + "step": 2466 + }, + { + "epoch": 0.26, + "learning_rate": 1.8503417919245548e-05, + "loss": 1.5823, + "step": 2467 + }, + { + "epoch": 0.26, + "learning_rate": 1.8501491213397386e-05, + "loss": 1.4045, + "step": 2468 + }, + { + "epoch": 0.26, + "learning_rate": 1.8499563368567837e-05, + "loss": 1.4828, + "step": 2469 + }, + { + "epoch": 0.26, + "learning_rate": 1.849763438501519e-05, + "loss": 1.4684, + "step": 2470 + }, + { + "epoch": 0.26, + "learning_rate": 1.8495704262997873e-05, + "loss": 1.4577, + "step": 2471 + }, + { + "epoch": 0.26, + "learning_rate": 1.8493773002774475e-05, + "loss": 1.4759, + "step": 2472 + }, + { + "epoch": 0.26, + "learning_rate": 1.8491840604603736e-05, + "loss": 1.4259, + "step": 2473 + }, + { + "epoch": 0.26, + "learning_rate": 1.8489907068744543e-05, + "loss": 1.4717, + "step": 2474 + }, + { + "epoch": 0.26, + "learning_rate": 1.848797239545595e-05, + "loss": 1.4247, + "step": 2475 + }, + { + "epoch": 0.26, + "learning_rate": 1.8486036584997143e-05, + "loss": 1.4954, + "step": 2476 + }, + { + "epoch": 0.26, + "learning_rate": 1.8484099637627472e-05, + "loss": 1.4926, + "step": 2477 + }, + { + "epoch": 0.26, + "learning_rate": 1.8482161553606447e-05, + "loss": 1.487, + "step": 2478 + }, + { + "epoch": 0.26, + "learning_rate": 1.8480222333193715e-05, + "loss": 1.4553, + "step": 2479 + }, + { + "epoch": 0.26, + "learning_rate": 1.847828197664908e-05, + "loss": 1.4862, + "step": 2480 + }, + { + "epoch": 0.26, + "learning_rate": 1.8476340484232508e-05, + "loss": 1.4867, + "step": 2481 + }, + { + "epoch": 0.26, + "learning_rate": 1.8474397856204097e-05, + "loss": 1.4736, + "step": 2482 + }, + { + "epoch": 0.26, + "learning_rate": 1.8472454092824122e-05, + "loss": 1.4254, + "step": 2483 + }, + { + "epoch": 0.26, + "learning_rate": 1.8470509194352987e-05, + "loss": 1.4455, + "step": 2484 + }, + { + "epoch": 0.26, + "learning_rate": 1.8468563161051263e-05, + "loss": 1.4402, + "step": 2485 + }, + { + "epoch": 0.26, + "learning_rate": 1.846661599317967e-05, + "loss": 1.4611, + "step": 2486 + }, + { + "epoch": 0.26, + "learning_rate": 1.8464667690999073e-05, + "loss": 1.4814, + "step": 2487 + }, + { + "epoch": 0.26, + "learning_rate": 1.8462718254770503e-05, + "loss": 1.4559, + "step": 2488 + }, + { + "epoch": 0.26, + "learning_rate": 1.8460767684755127e-05, + "loss": 1.4667, + "step": 2489 + }, + { + "epoch": 0.26, + "learning_rate": 1.8458815981214274e-05, + "loss": 1.4427, + "step": 2490 + }, + { + "epoch": 0.26, + "learning_rate": 1.845686314440942e-05, + "loss": 1.4055, + "step": 2491 + }, + { + "epoch": 0.26, + "learning_rate": 1.8454909174602198e-05, + "loss": 1.5563, + "step": 2492 + }, + { + "epoch": 0.26, + "learning_rate": 1.845295407205439e-05, + "loss": 1.4631, + "step": 2493 + }, + { + "epoch": 0.26, + "learning_rate": 1.8450997837027925e-05, + "loss": 1.4887, + "step": 2494 + }, + { + "epoch": 0.26, + "learning_rate": 1.8449040469784895e-05, + "loss": 1.5212, + "step": 2495 + }, + { + "epoch": 0.26, + "learning_rate": 1.844708197058753e-05, + "loss": 1.5582, + "step": 2496 + }, + { + "epoch": 0.26, + "learning_rate": 1.844512233969822e-05, + "loss": 1.4599, + "step": 2497 + }, + { + "epoch": 0.26, + "learning_rate": 1.844316157737951e-05, + "loss": 1.4546, + "step": 2498 + }, + { + "epoch": 0.26, + "learning_rate": 1.844119968389409e-05, + "loss": 1.4631, + "step": 2499 + }, + { + "epoch": 0.26, + "learning_rate": 1.84392366595048e-05, + "loss": 1.4817, + "step": 2500 + }, + { + "epoch": 0.26, + "learning_rate": 1.8437272504474636e-05, + "loss": 1.4214, + "step": 2501 + }, + { + "epoch": 0.26, + "learning_rate": 1.8435307219066744e-05, + "loss": 1.471, + "step": 2502 + }, + { + "epoch": 0.26, + "learning_rate": 1.8433340803544424e-05, + "loss": 1.4693, + "step": 2503 + }, + { + "epoch": 0.26, + "learning_rate": 1.8431373258171127e-05, + "loss": 1.6297, + "step": 2504 + }, + { + "epoch": 0.26, + "learning_rate": 1.842940458321045e-05, + "loss": 1.5916, + "step": 2505 + }, + { + "epoch": 0.26, + "learning_rate": 1.842743477892614e-05, + "loss": 1.4754, + "step": 2506 + }, + { + "epoch": 0.26, + "learning_rate": 1.842546384558211e-05, + "loss": 1.4828, + "step": 2507 + }, + { + "epoch": 0.26, + "learning_rate": 1.842349178344241e-05, + "loss": 1.4239, + "step": 2508 + }, + { + "epoch": 0.26, + "learning_rate": 1.8421518592771243e-05, + "loss": 1.5028, + "step": 2509 + }, + { + "epoch": 0.26, + "learning_rate": 1.841954427383297e-05, + "loss": 1.4848, + "step": 2510 + }, + { + "epoch": 0.26, + "learning_rate": 1.8417568826892097e-05, + "loss": 1.4617, + "step": 2511 + }, + { + "epoch": 0.26, + "learning_rate": 1.8415592252213284e-05, + "loss": 1.4266, + "step": 2512 + }, + { + "epoch": 0.26, + "learning_rate": 1.8413614550061344e-05, + "loss": 1.4321, + "step": 2513 + }, + { + "epoch": 0.26, + "learning_rate": 1.841163572070123e-05, + "loss": 1.4693, + "step": 2514 + }, + { + "epoch": 0.26, + "learning_rate": 1.840965576439806e-05, + "loss": 1.4257, + "step": 2515 + }, + { + "epoch": 0.26, + "learning_rate": 1.84076746814171e-05, + "loss": 1.4488, + "step": 2516 + }, + { + "epoch": 0.26, + "learning_rate": 1.840569247202376e-05, + "loss": 1.5348, + "step": 2517 + }, + { + "epoch": 0.26, + "learning_rate": 1.8403709136483604e-05, + "loss": 1.477, + "step": 2518 + }, + { + "epoch": 0.26, + "learning_rate": 1.840172467506235e-05, + "loss": 1.443, + "step": 2519 + }, + { + "epoch": 0.26, + "learning_rate": 1.839973908802587e-05, + "loss": 1.4772, + "step": 2520 + }, + { + "epoch": 0.26, + "learning_rate": 1.839775237564017e-05, + "loss": 1.4443, + "step": 2521 + }, + { + "epoch": 0.26, + "learning_rate": 1.839576453817143e-05, + "loss": 1.4063, + "step": 2522 + }, + { + "epoch": 0.26, + "learning_rate": 1.8393775575885963e-05, + "loss": 1.5178, + "step": 2523 + }, + { + "epoch": 0.26, + "learning_rate": 1.8391785489050235e-05, + "loss": 1.4337, + "step": 2524 + }, + { + "epoch": 0.26, + "learning_rate": 1.8389794277930875e-05, + "loss": 1.4512, + "step": 2525 + }, + { + "epoch": 0.26, + "learning_rate": 1.838780194279465e-05, + "loss": 1.5578, + "step": 2526 + }, + { + "epoch": 0.26, + "learning_rate": 1.8385808483908484e-05, + "loss": 1.4606, + "step": 2527 + }, + { + "epoch": 0.27, + "learning_rate": 1.8383813901539444e-05, + "loss": 1.4957, + "step": 2528 + }, + { + "epoch": 0.27, + "learning_rate": 1.838181819595476e-05, + "loss": 1.4914, + "step": 2529 + }, + { + "epoch": 0.27, + "learning_rate": 1.8379821367421802e-05, + "loss": 1.4785, + "step": 2530 + }, + { + "epoch": 0.27, + "learning_rate": 1.837782341620809e-05, + "loss": 1.4052, + "step": 2531 + }, + { + "epoch": 0.27, + "learning_rate": 1.8375824342581303e-05, + "loss": 1.4807, + "step": 2532 + }, + { + "epoch": 0.27, + "learning_rate": 1.8373824146809264e-05, + "loss": 1.4313, + "step": 2533 + }, + { + "epoch": 0.27, + "learning_rate": 1.8371822829159945e-05, + "loss": 1.4374, + "step": 2534 + }, + { + "epoch": 0.27, + "learning_rate": 1.836982038990148e-05, + "loss": 1.4482, + "step": 2535 + }, + { + "epoch": 0.27, + "learning_rate": 1.8367816829302133e-05, + "loss": 1.5231, + "step": 2536 + }, + { + "epoch": 0.27, + "learning_rate": 1.8365812147630337e-05, + "loss": 1.4101, + "step": 2537 + }, + { + "epoch": 0.27, + "learning_rate": 1.8363806345154666e-05, + "loss": 1.4372, + "step": 2538 + }, + { + "epoch": 0.27, + "learning_rate": 1.8361799422143845e-05, + "loss": 1.4808, + "step": 2539 + }, + { + "epoch": 0.27, + "learning_rate": 1.835979137886675e-05, + "loss": 1.3515, + "step": 2540 + }, + { + "epoch": 0.27, + "learning_rate": 1.8357782215592412e-05, + "loss": 1.5284, + "step": 2541 + }, + { + "epoch": 0.27, + "learning_rate": 1.835577193259e-05, + "loss": 1.4222, + "step": 2542 + }, + { + "epoch": 0.27, + "learning_rate": 1.8353760530128846e-05, + "loss": 1.4522, + "step": 2543 + }, + { + "epoch": 0.27, + "learning_rate": 1.835174800847842e-05, + "loss": 1.4487, + "step": 2544 + }, + { + "epoch": 0.27, + "learning_rate": 1.8349734367908355e-05, + "loss": 1.3688, + "step": 2545 + }, + { + "epoch": 0.27, + "learning_rate": 1.8347719608688422e-05, + "loss": 1.483, + "step": 2546 + }, + { + "epoch": 0.27, + "learning_rate": 1.8345703731088554e-05, + "loss": 1.4733, + "step": 2547 + }, + { + "epoch": 0.27, + "learning_rate": 1.8343686735378816e-05, + "loss": 1.4594, + "step": 2548 + }, + { + "epoch": 0.27, + "learning_rate": 1.834166862182944e-05, + "loss": 1.4648, + "step": 2549 + }, + { + "epoch": 0.27, + "learning_rate": 1.8339649390710807e-05, + "loss": 1.5249, + "step": 2550 + }, + { + "epoch": 0.27, + "learning_rate": 1.8337629042293434e-05, + "loss": 1.4744, + "step": 2551 + }, + { + "epoch": 0.27, + "learning_rate": 1.8335607576847994e-05, + "loss": 1.5094, + "step": 2552 + }, + { + "epoch": 0.27, + "learning_rate": 1.8333584994645318e-05, + "loss": 1.5122, + "step": 2553 + }, + { + "epoch": 0.27, + "learning_rate": 1.8331561295956374e-05, + "loss": 1.537, + "step": 2554 + }, + { + "epoch": 0.27, + "learning_rate": 1.832953648105229e-05, + "loss": 1.4691, + "step": 2555 + }, + { + "epoch": 0.27, + "learning_rate": 1.8327510550204343e-05, + "loss": 1.4969, + "step": 2556 + }, + { + "epoch": 0.27, + "learning_rate": 1.8325483503683944e-05, + "loss": 1.4596, + "step": 2557 + }, + { + "epoch": 0.27, + "learning_rate": 1.8323455341762675e-05, + "loss": 1.435, + "step": 2558 + }, + { + "epoch": 0.27, + "learning_rate": 1.8321426064712255e-05, + "loss": 1.4883, + "step": 2559 + }, + { + "epoch": 0.27, + "learning_rate": 1.8319395672804554e-05, + "loss": 1.3758, + "step": 2560 + }, + { + "epoch": 0.27, + "learning_rate": 1.8317364166311592e-05, + "loss": 1.4352, + "step": 2561 + }, + { + "epoch": 0.27, + "learning_rate": 1.831533154550554e-05, + "loss": 1.5072, + "step": 2562 + }, + { + "epoch": 0.27, + "learning_rate": 1.8313297810658718e-05, + "loss": 1.4476, + "step": 2563 + }, + { + "epoch": 0.27, + "learning_rate": 1.831126296204359e-05, + "loss": 1.507, + "step": 2564 + }, + { + "epoch": 0.27, + "learning_rate": 1.8309226999932777e-05, + "loss": 1.4677, + "step": 2565 + }, + { + "epoch": 0.27, + "learning_rate": 1.8307189924599044e-05, + "loss": 1.4537, + "step": 2566 + }, + { + "epoch": 0.27, + "learning_rate": 1.8305151736315307e-05, + "loss": 1.4584, + "step": 2567 + }, + { + "epoch": 0.27, + "learning_rate": 1.8303112435354634e-05, + "loss": 1.4944, + "step": 2568 + }, + { + "epoch": 0.27, + "learning_rate": 1.8301072021990232e-05, + "loss": 1.4379, + "step": 2569 + }, + { + "epoch": 0.27, + "learning_rate": 1.8299030496495475e-05, + "loss": 1.539, + "step": 2570 + }, + { + "epoch": 0.27, + "learning_rate": 1.829698785914386e-05, + "loss": 1.4421, + "step": 2571 + }, + { + "epoch": 0.27, + "learning_rate": 1.8294944110209063e-05, + "loss": 1.4693, + "step": 2572 + }, + { + "epoch": 0.27, + "learning_rate": 1.8292899249964887e-05, + "loss": 1.3239, + "step": 2573 + }, + { + "epoch": 0.27, + "learning_rate": 1.8290853278685284e-05, + "loss": 1.472, + "step": 2574 + }, + { + "epoch": 0.27, + "learning_rate": 1.8288806196644374e-05, + "loss": 1.536, + "step": 2575 + }, + { + "epoch": 0.27, + "learning_rate": 1.8286758004116405e-05, + "loss": 1.4644, + "step": 2576 + }, + { + "epoch": 0.27, + "learning_rate": 1.8284708701375783e-05, + "loss": 1.4537, + "step": 2577 + }, + { + "epoch": 0.27, + "learning_rate": 1.8282658288697067e-05, + "loss": 1.4359, + "step": 2578 + }, + { + "epoch": 0.27, + "learning_rate": 1.8280606766354955e-05, + "loss": 1.4842, + "step": 2579 + }, + { + "epoch": 0.27, + "learning_rate": 1.8278554134624302e-05, + "loss": 1.4664, + "step": 2580 + }, + { + "epoch": 0.27, + "learning_rate": 1.8276500393780105e-05, + "loss": 1.4632, + "step": 2581 + }, + { + "epoch": 0.27, + "learning_rate": 1.827444554409751e-05, + "loss": 1.4996, + "step": 2582 + }, + { + "epoch": 0.27, + "learning_rate": 1.827238958585182e-05, + "loss": 1.3399, + "step": 2583 + }, + { + "epoch": 0.27, + "learning_rate": 1.8270332519318476e-05, + "loss": 1.3928, + "step": 2584 + }, + { + "epoch": 0.27, + "learning_rate": 1.8268274344773074e-05, + "loss": 1.4993, + "step": 2585 + }, + { + "epoch": 0.27, + "learning_rate": 1.8266215062491356e-05, + "loss": 1.5398, + "step": 2586 + }, + { + "epoch": 0.27, + "learning_rate": 1.826415467274921e-05, + "loss": 1.4353, + "step": 2587 + }, + { + "epoch": 0.27, + "eval_loss": 1.5104212760925293, + "eval_runtime": 77.3448, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2587 + }, + { + "epoch": 0.27, + "learning_rate": 1.8262093175822685e-05, + "loss": 1.4889, + "step": 2588 + }, + { + "epoch": 0.27, + "learning_rate": 1.826003057198796e-05, + "loss": 1.4912, + "step": 2589 + }, + { + "epoch": 0.27, + "learning_rate": 1.825796686152137e-05, + "loss": 1.4884, + "step": 2590 + }, + { + "epoch": 0.27, + "learning_rate": 1.8255902044699404e-05, + "loss": 1.478, + "step": 2591 + }, + { + "epoch": 0.27, + "learning_rate": 1.8253836121798692e-05, + "loss": 1.6549, + "step": 2592 + }, + { + "epoch": 0.27, + "learning_rate": 1.8251769093096018e-05, + "loss": 1.5146, + "step": 2593 + }, + { + "epoch": 0.27, + "learning_rate": 1.8249700958868306e-05, + "loss": 1.4797, + "step": 2594 + }, + { + "epoch": 0.27, + "learning_rate": 1.8247631719392634e-05, + "loss": 1.4655, + "step": 2595 + }, + { + "epoch": 0.27, + "learning_rate": 1.824556137494623e-05, + "loss": 1.4517, + "step": 2596 + }, + { + "epoch": 0.27, + "learning_rate": 1.8243489925806458e-05, + "loss": 1.4936, + "step": 2597 + }, + { + "epoch": 0.27, + "learning_rate": 1.8241417372250852e-05, + "loss": 1.4614, + "step": 2598 + }, + { + "epoch": 0.27, + "learning_rate": 1.8239343714557073e-05, + "loss": 1.4475, + "step": 2599 + }, + { + "epoch": 0.27, + "learning_rate": 1.8237268953002937e-05, + "loss": 1.5435, + "step": 2600 + }, + { + "epoch": 0.27, + "learning_rate": 1.8235193087866413e-05, + "loss": 1.4616, + "step": 2601 + }, + { + "epoch": 0.27, + "learning_rate": 1.8233116119425612e-05, + "loss": 1.4578, + "step": 2602 + }, + { + "epoch": 0.27, + "learning_rate": 1.8231038047958795e-05, + "loss": 1.434, + "step": 2603 + }, + { + "epoch": 0.27, + "learning_rate": 1.8228958873744368e-05, + "loss": 1.5335, + "step": 2604 + }, + { + "epoch": 0.27, + "learning_rate": 1.8226878597060887e-05, + "loss": 1.415, + "step": 2605 + }, + { + "epoch": 0.27, + "learning_rate": 1.8224797218187058e-05, + "loss": 1.6165, + "step": 2606 + }, + { + "epoch": 0.27, + "learning_rate": 1.822271473740173e-05, + "loss": 1.372, + "step": 2607 + }, + { + "epoch": 0.27, + "learning_rate": 1.8220631154983907e-05, + "loss": 1.4855, + "step": 2608 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218546471212727e-05, + "loss": 1.4093, + "step": 2609 + }, + { + "epoch": 0.27, + "learning_rate": 1.821646068636749e-05, + "loss": 1.4852, + "step": 2610 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214373800727637e-05, + "loss": 1.6959, + "step": 2611 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212285814572755e-05, + "loss": 1.3874, + "step": 2612 + }, + { + "epoch": 0.27, + "learning_rate": 1.821019672818258e-05, + "loss": 1.4425, + "step": 2613 + }, + { + "epoch": 0.27, + "learning_rate": 1.8208106541837e-05, + "loss": 1.6097, + "step": 2614 + }, + { + "epoch": 0.27, + "learning_rate": 1.8206015255816045e-05, + "loss": 1.5675, + "step": 2615 + }, + { + "epoch": 0.27, + "learning_rate": 1.820392287039989e-05, + "loss": 1.4039, + "step": 2616 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201829385868866e-05, + "loss": 1.4872, + "step": 2617 + }, + { + "epoch": 0.27, + "learning_rate": 1.819973480250344e-05, + "loss": 1.4645, + "step": 2618 + }, + { + "epoch": 0.27, + "learning_rate": 1.8197639120584237e-05, + "loss": 1.4923, + "step": 2619 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195542340392025e-05, + "loss": 1.4294, + "step": 2620 + }, + { + "epoch": 0.27, + "learning_rate": 1.8193444462207717e-05, + "loss": 1.4315, + "step": 2621 + }, + { + "epoch": 0.27, + "learning_rate": 1.8191345486312372e-05, + "loss": 1.3972, + "step": 2622 + }, + { + "epoch": 0.28, + "learning_rate": 1.8189245412987205e-05, + "loss": 1.462, + "step": 2623 + }, + { + "epoch": 0.28, + "learning_rate": 1.8187144242513567e-05, + "loss": 1.4738, + "step": 2624 + }, + { + "epoch": 0.28, + "learning_rate": 1.818504197517296e-05, + "loss": 1.4935, + "step": 2625 + }, + { + "epoch": 0.28, + "learning_rate": 1.8182938611247038e-05, + "loss": 1.4231, + "step": 2626 + }, + { + "epoch": 0.28, + "learning_rate": 1.81808341510176e-05, + "loss": 1.4031, + "step": 2627 + }, + { + "epoch": 0.28, + "learning_rate": 1.817872859476658e-05, + "loss": 1.5822, + "step": 2628 + }, + { + "epoch": 0.28, + "learning_rate": 1.8176621942776075e-05, + "loss": 1.432, + "step": 2629 + }, + { + "epoch": 0.28, + "learning_rate": 1.8174514195328324e-05, + "loss": 1.5565, + "step": 2630 + }, + { + "epoch": 0.28, + "learning_rate": 1.8172405352705704e-05, + "loss": 1.4895, + "step": 2631 + }, + { + "epoch": 0.28, + "learning_rate": 1.8170295415190754e-05, + "loss": 1.4032, + "step": 2632 + }, + { + "epoch": 0.28, + "learning_rate": 1.8168184383066144e-05, + "loss": 1.4253, + "step": 2633 + }, + { + "epoch": 0.28, + "learning_rate": 1.8166072256614702e-05, + "loss": 1.5162, + "step": 2634 + }, + { + "epoch": 0.28, + "learning_rate": 1.81639590361194e-05, + "loss": 1.4609, + "step": 2635 + }, + { + "epoch": 0.28, + "learning_rate": 1.816184472186335e-05, + "loss": 1.4351, + "step": 2636 + }, + { + "epoch": 0.28, + "learning_rate": 1.8159729314129823e-05, + "loss": 1.4738, + "step": 2637 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157612813202224e-05, + "loss": 1.5986, + "step": 2638 + }, + { + "epoch": 0.28, + "learning_rate": 1.815549521936411e-05, + "loss": 1.4633, + "step": 2639 + }, + { + "epoch": 0.28, + "learning_rate": 1.8153376532899184e-05, + "loss": 1.4404, + "step": 2640 + }, + { + "epoch": 0.28, + "learning_rate": 1.81512567540913e-05, + "loss": 1.4256, + "step": 2641 + }, + { + "epoch": 0.28, + "learning_rate": 1.814913588322445e-05, + "loss": 1.4054, + "step": 2642 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147013920582773e-05, + "loss": 1.4134, + "step": 2643 + }, + { + "epoch": 0.28, + "learning_rate": 1.8144890866450567e-05, + "loss": 1.4098, + "step": 2644 + }, + { + "epoch": 0.28, + "learning_rate": 1.814276672111226e-05, + "loss": 1.4593, + "step": 2645 + }, + { + "epoch": 0.28, + "learning_rate": 1.814064148485243e-05, + "loss": 1.4679, + "step": 2646 + }, + { + "epoch": 0.28, + "learning_rate": 1.8138515157955812e-05, + "loss": 1.5234, + "step": 2647 + }, + { + "epoch": 0.28, + "learning_rate": 1.8136387740707272e-05, + "loss": 1.4568, + "step": 2648 + }, + { + "epoch": 0.28, + "learning_rate": 1.8134259233391836e-05, + "loss": 1.5057, + "step": 2649 + }, + { + "epoch": 0.28, + "learning_rate": 1.8132129636294665e-05, + "loss": 1.3643, + "step": 2650 + }, + { + "epoch": 0.28, + "learning_rate": 1.812999894970107e-05, + "loss": 1.4766, + "step": 2651 + }, + { + "epoch": 0.28, + "learning_rate": 1.812786717389651e-05, + "loss": 1.5701, + "step": 2652 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125734309166587e-05, + "loss": 1.5341, + "step": 2653 + }, + { + "epoch": 0.28, + "learning_rate": 1.812360035579705e-05, + "loss": 1.3596, + "step": 2654 + }, + { + "epoch": 0.28, + "learning_rate": 1.8121465314073793e-05, + "loss": 1.4847, + "step": 2655 + }, + { + "epoch": 0.28, + "learning_rate": 1.811932918428286e-05, + "loss": 1.4664, + "step": 2656 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117191966710438e-05, + "loss": 1.4673, + "step": 2657 + }, + { + "epoch": 0.28, + "learning_rate": 1.8115053661642856e-05, + "loss": 1.4712, + "step": 2658 + }, + { + "epoch": 0.28, + "learning_rate": 1.811291426936659e-05, + "loss": 1.4458, + "step": 2659 + }, + { + "epoch": 0.28, + "learning_rate": 1.811077379016827e-05, + "loss": 1.4667, + "step": 2660 + }, + { + "epoch": 0.28, + "learning_rate": 1.810863222433466e-05, + "loss": 1.4695, + "step": 2661 + }, + { + "epoch": 0.28, + "learning_rate": 1.8106489572152677e-05, + "loss": 1.5263, + "step": 2662 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104345833909376e-05, + "loss": 1.4148, + "step": 2663 + }, + { + "epoch": 0.28, + "learning_rate": 1.8102201009891976e-05, + "loss": 1.3955, + "step": 2664 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100055100387814e-05, + "loss": 1.6056, + "step": 2665 + }, + { + "epoch": 0.28, + "learning_rate": 1.8097908105684396e-05, + "loss": 1.5394, + "step": 2666 + }, + { + "epoch": 0.28, + "learning_rate": 1.809576002606936e-05, + "loss": 1.479, + "step": 2667 + }, + { + "epoch": 0.28, + "learning_rate": 1.8093610861830494e-05, + "loss": 1.4492, + "step": 2668 + }, + { + "epoch": 0.28, + "learning_rate": 1.8091460613255728e-05, + "loss": 1.4172, + "step": 2669 + }, + { + "epoch": 0.28, + "learning_rate": 1.808930928063315e-05, + "loss": 1.4498, + "step": 2670 + }, + { + "epoch": 0.28, + "learning_rate": 1.808715686425097e-05, + "loss": 1.6203, + "step": 2671 + }, + { + "epoch": 0.28, + "learning_rate": 1.8085003364397567e-05, + "loss": 1.435, + "step": 2672 + }, + { + "epoch": 0.28, + "learning_rate": 1.808284878136145e-05, + "loss": 1.4489, + "step": 2673 + }, + { + "epoch": 0.28, + "learning_rate": 1.8080693115431277e-05, + "loss": 1.4416, + "step": 2674 + }, + { + "epoch": 0.28, + "learning_rate": 1.8078536366895853e-05, + "loss": 1.422, + "step": 2675 + }, + { + "epoch": 0.28, + "learning_rate": 1.8076378536044128e-05, + "loss": 1.4039, + "step": 2676 + }, + { + "epoch": 0.28, + "learning_rate": 1.8074219623165195e-05, + "loss": 1.4705, + "step": 2677 + }, + { + "epoch": 0.28, + "learning_rate": 1.807205962854829e-05, + "loss": 1.5031, + "step": 2678 + }, + { + "epoch": 0.28, + "learning_rate": 1.8069898552482806e-05, + "loss": 1.4812, + "step": 2679 + }, + { + "epoch": 0.28, + "learning_rate": 1.806773639525826e-05, + "loss": 1.4129, + "step": 2680 + }, + { + "epoch": 0.28, + "learning_rate": 1.8065573157164332e-05, + "loss": 1.4559, + "step": 2681 + }, + { + "epoch": 0.28, + "learning_rate": 1.806340883849084e-05, + "loss": 1.3878, + "step": 2682 + }, + { + "epoch": 0.28, + "learning_rate": 1.8061243439527744e-05, + "loss": 1.4752, + "step": 2683 + }, + { + "epoch": 0.28, + "learning_rate": 1.8059076960565156e-05, + "loss": 1.4089, + "step": 2684 + }, + { + "epoch": 0.28, + "learning_rate": 1.8056909401893326e-05, + "loss": 1.4736, + "step": 2685 + }, + { + "epoch": 0.28, + "learning_rate": 1.8054740763802654e-05, + "loss": 1.3796, + "step": 2686 + }, + { + "epoch": 0.28, + "learning_rate": 1.805257104658368e-05, + "loss": 1.4412, + "step": 2687 + }, + { + "epoch": 0.28, + "learning_rate": 1.8050400250527086e-05, + "loss": 1.4639, + "step": 2688 + }, + { + "epoch": 0.28, + "learning_rate": 1.804822837592371e-05, + "loss": 1.4076, + "step": 2689 + }, + { + "epoch": 0.28, + "learning_rate": 1.804605542306452e-05, + "loss": 1.4627, + "step": 2690 + }, + { + "epoch": 0.28, + "learning_rate": 1.8043881392240642e-05, + "loss": 1.5249, + "step": 2691 + }, + { + "epoch": 0.28, + "learning_rate": 1.804170628374334e-05, + "loss": 1.4312, + "step": 2692 + }, + { + "epoch": 0.28, + "learning_rate": 1.803953009786402e-05, + "loss": 1.5676, + "step": 2693 + }, + { + "epoch": 0.28, + "learning_rate": 1.8037352834894233e-05, + "loss": 1.5072, + "step": 2694 + }, + { + "epoch": 0.28, + "learning_rate": 1.803517449512568e-05, + "loss": 1.5662, + "step": 2695 + }, + { + "epoch": 0.28, + "learning_rate": 1.8032995078850207e-05, + "loss": 1.4771, + "step": 2696 + }, + { + "epoch": 0.28, + "learning_rate": 1.803081458635979e-05, + "loss": 1.412, + "step": 2697 + }, + { + "epoch": 0.28, + "learning_rate": 1.8028633017946564e-05, + "loss": 1.497, + "step": 2698 + }, + { + "epoch": 0.28, + "learning_rate": 1.8026450373902804e-05, + "loss": 1.4528, + "step": 2699 + }, + { + "epoch": 0.28, + "learning_rate": 1.802426665452093e-05, + "loss": 1.4785, + "step": 2700 + }, + { + "epoch": 0.28, + "learning_rate": 1.8022081860093493e-05, + "loss": 1.6411, + "step": 2701 + }, + { + "epoch": 0.28, + "learning_rate": 1.8019895990913213e-05, + "loss": 1.4459, + "step": 2702 + }, + { + "epoch": 0.28, + "learning_rate": 1.8017709047272932e-05, + "loss": 1.4418, + "step": 2703 + }, + { + "epoch": 0.28, + "learning_rate": 1.801552102946565e-05, + "loss": 1.4409, + "step": 2704 + }, + { + "epoch": 0.28, + "learning_rate": 1.8013331937784498e-05, + "loss": 1.4651, + "step": 2705 + }, + { + "epoch": 0.28, + "learning_rate": 1.8011141772522766e-05, + "loss": 1.4161, + "step": 2706 + }, + { + "epoch": 0.28, + "learning_rate": 1.8008950533973876e-05, + "loss": 1.458, + "step": 2707 + }, + { + "epoch": 0.28, + "learning_rate": 1.8006758222431398e-05, + "loss": 1.4477, + "step": 2708 + }, + { + "epoch": 0.28, + "learning_rate": 1.800456483818904e-05, + "loss": 1.4433, + "step": 2709 + }, + { + "epoch": 0.28, + "learning_rate": 1.8002370381540672e-05, + "loss": 1.5005, + "step": 2710 + }, + { + "epoch": 0.28, + "learning_rate": 1.8000174852780282e-05, + "loss": 1.4945, + "step": 2711 + }, + { + "epoch": 0.28, + "learning_rate": 1.7997978252202023e-05, + "loss": 1.4298, + "step": 2712 + }, + { + "epoch": 0.28, + "learning_rate": 1.7995780580100177e-05, + "loss": 1.3812, + "step": 2713 + }, + { + "epoch": 0.28, + "learning_rate": 1.799358183676918e-05, + "loss": 1.5559, + "step": 2714 + }, + { + "epoch": 0.28, + "learning_rate": 1.79913820225036e-05, + "loss": 1.4316, + "step": 2715 + }, + { + "epoch": 0.28, + "learning_rate": 1.798918113759817e-05, + "loss": 1.419, + "step": 2716 + }, + { + "epoch": 0.28, + "learning_rate": 1.7986979182347733e-05, + "loss": 1.43, + "step": 2717 + }, + { + "epoch": 0.29, + "learning_rate": 1.798477615704731e-05, + "loss": 1.4964, + "step": 2718 + }, + { + "epoch": 0.29, + "learning_rate": 1.7982572061992044e-05, + "loss": 1.4417, + "step": 2719 + }, + { + "epoch": 0.29, + "learning_rate": 1.7980366897477227e-05, + "loss": 1.4562, + "step": 2720 + }, + { + "epoch": 0.29, + "learning_rate": 1.7978160663798295e-05, + "loss": 1.4386, + "step": 2721 + }, + { + "epoch": 0.29, + "learning_rate": 1.7975953361250824e-05, + "loss": 1.445, + "step": 2722 + }, + { + "epoch": 0.29, + "learning_rate": 1.797374499013054e-05, + "loss": 1.4549, + "step": 2723 + }, + { + "epoch": 0.29, + "learning_rate": 1.7971535550733305e-05, + "loss": 1.5205, + "step": 2724 + }, + { + "epoch": 0.29, + "learning_rate": 1.796932504335513e-05, + "loss": 1.4632, + "step": 2725 + }, + { + "epoch": 0.29, + "learning_rate": 1.796711346829216e-05, + "loss": 1.3767, + "step": 2726 + }, + { + "epoch": 0.29, + "learning_rate": 1.79649008258407e-05, + "loss": 1.4098, + "step": 2727 + }, + { + "epoch": 0.29, + "learning_rate": 1.7962687116297178e-05, + "loss": 1.4675, + "step": 2728 + }, + { + "epoch": 0.29, + "learning_rate": 1.7960472339958176e-05, + "loss": 1.6048, + "step": 2729 + }, + { + "epoch": 0.29, + "learning_rate": 1.7958256497120418e-05, + "loss": 1.5432, + "step": 2730 + }, + { + "epoch": 0.29, + "learning_rate": 1.7956039588080774e-05, + "loss": 1.5453, + "step": 2731 + }, + { + "epoch": 0.29, + "learning_rate": 1.7953821613136246e-05, + "loss": 1.4246, + "step": 2732 + }, + { + "epoch": 0.29, + "learning_rate": 1.7951602572583988e-05, + "loss": 1.3987, + "step": 2733 + }, + { + "epoch": 0.29, + "learning_rate": 1.7949382466721295e-05, + "loss": 1.4943, + "step": 2734 + }, + { + "epoch": 0.29, + "learning_rate": 1.7947161295845606e-05, + "loss": 1.4385, + "step": 2735 + }, + { + "epoch": 0.29, + "learning_rate": 1.7944939060254497e-05, + "loss": 1.4165, + "step": 2736 + }, + { + "epoch": 0.29, + "learning_rate": 1.7942715760245692e-05, + "loss": 1.4004, + "step": 2737 + }, + { + "epoch": 0.29, + "learning_rate": 1.7940491396117063e-05, + "loss": 1.4577, + "step": 2738 + }, + { + "epoch": 0.29, + "learning_rate": 1.7938265968166602e-05, + "loss": 1.4649, + "step": 2739 + }, + { + "epoch": 0.29, + "learning_rate": 1.7936039476692473e-05, + "loss": 1.5273, + "step": 2740 + }, + { + "epoch": 0.29, + "learning_rate": 1.7933811921992962e-05, + "loss": 1.4325, + "step": 2741 + }, + { + "epoch": 0.29, + "learning_rate": 1.793158330436651e-05, + "loss": 1.4388, + "step": 2742 + }, + { + "epoch": 0.29, + "learning_rate": 1.7929353624111687e-05, + "loss": 1.4124, + "step": 2743 + }, + { + "epoch": 0.29, + "learning_rate": 1.7927122881527222e-05, + "loss": 1.5449, + "step": 2744 + }, + { + "epoch": 0.29, + "learning_rate": 1.7924891076911964e-05, + "loss": 1.4728, + "step": 2745 + }, + { + "epoch": 0.29, + "learning_rate": 1.7922658210564932e-05, + "loss": 1.5103, + "step": 2746 + }, + { + "epoch": 0.29, + "learning_rate": 1.792042428278526e-05, + "loss": 1.5975, + "step": 2747 + }, + { + "epoch": 0.29, + "learning_rate": 1.7918189293872247e-05, + "loss": 1.567, + "step": 2748 + }, + { + "epoch": 0.29, + "learning_rate": 1.7915953244125318e-05, + "loss": 1.57, + "step": 2749 + }, + { + "epoch": 0.29, + "learning_rate": 1.791371613384405e-05, + "loss": 1.4372, + "step": 2750 + }, + { + "epoch": 0.29, + "learning_rate": 1.7911477963328155e-05, + "loss": 1.4053, + "step": 2751 + }, + { + "epoch": 0.29, + "learning_rate": 1.7909238732877492e-05, + "loss": 1.3782, + "step": 2752 + }, + { + "epoch": 0.29, + "learning_rate": 1.790699844279206e-05, + "loss": 1.4401, + "step": 2753 + }, + { + "epoch": 0.29, + "learning_rate": 1.7904757093372e-05, + "loss": 1.3749, + "step": 2754 + }, + { + "epoch": 0.29, + "learning_rate": 1.79025146849176e-05, + "loss": 1.4909, + "step": 2755 + }, + { + "epoch": 0.29, + "learning_rate": 1.7900271217729273e-05, + "loss": 1.4103, + "step": 2756 + }, + { + "epoch": 0.29, + "learning_rate": 1.7898026692107597e-05, + "loss": 1.4986, + "step": 2757 + }, + { + "epoch": 0.29, + "learning_rate": 1.7895781108353278e-05, + "loss": 1.5449, + "step": 2758 + }, + { + "epoch": 0.29, + "learning_rate": 1.789353446676717e-05, + "loss": 1.5583, + "step": 2759 + }, + { + "epoch": 0.29, + "learning_rate": 1.7891286767650254e-05, + "loss": 1.5342, + "step": 2760 + }, + { + "epoch": 0.29, + "learning_rate": 1.7889038011303673e-05, + "loss": 1.4233, + "step": 2761 + }, + { + "epoch": 0.29, + "learning_rate": 1.7886788198028707e-05, + "loss": 1.3433, + "step": 2762 + }, + { + "epoch": 0.29, + "learning_rate": 1.788453732812676e-05, + "loss": 1.4451, + "step": 2763 + }, + { + "epoch": 0.29, + "learning_rate": 1.78822854018994e-05, + "loss": 1.4506, + "step": 2764 + }, + { + "epoch": 0.29, + "learning_rate": 1.7880032419648324e-05, + "loss": 1.4386, + "step": 2765 + }, + { + "epoch": 0.29, + "learning_rate": 1.7877778381675374e-05, + "loss": 1.4512, + "step": 2766 + }, + { + "epoch": 0.29, + "learning_rate": 1.7875523288282535e-05, + "loss": 1.4319, + "step": 2767 + }, + { + "epoch": 0.29, + "learning_rate": 1.7873267139771932e-05, + "loss": 1.4753, + "step": 2768 + }, + { + "epoch": 0.29, + "learning_rate": 1.787100993644583e-05, + "loss": 1.4044, + "step": 2769 + }, + { + "epoch": 0.29, + "learning_rate": 1.786875167860663e-05, + "loss": 1.4382, + "step": 2770 + }, + { + "epoch": 0.29, + "learning_rate": 1.786649236655689e-05, + "loss": 1.3977, + "step": 2771 + }, + { + "epoch": 0.29, + "learning_rate": 1.7864232000599298e-05, + "loss": 1.4473, + "step": 2772 + }, + { + "epoch": 0.29, + "learning_rate": 1.7861970581036678e-05, + "loss": 1.4666, + "step": 2773 + }, + { + "epoch": 0.29, + "learning_rate": 1.785970810817201e-05, + "loss": 1.5299, + "step": 2774 + }, + { + "epoch": 0.29, + "learning_rate": 1.7857444582308402e-05, + "loss": 1.3974, + "step": 2775 + }, + { + "epoch": 0.29, + "learning_rate": 1.7855180003749114e-05, + "loss": 1.4603, + "step": 2776 + }, + { + "epoch": 0.29, + "learning_rate": 1.7852914372797535e-05, + "loss": 1.463, + "step": 2777 + }, + { + "epoch": 0.29, + "learning_rate": 1.7850647689757205e-05, + "loss": 1.5317, + "step": 2778 + }, + { + "epoch": 0.29, + "learning_rate": 1.78483799549318e-05, + "loss": 1.4669, + "step": 2779 + }, + { + "epoch": 0.29, + "learning_rate": 1.784611116862514e-05, + "loss": 1.5293, + "step": 2780 + }, + { + "epoch": 0.29, + "learning_rate": 1.7843841331141177e-05, + "loss": 1.5802, + "step": 2781 + }, + { + "epoch": 0.29, + "learning_rate": 1.7841570442784024e-05, + "loss": 1.4486, + "step": 2782 + }, + { + "epoch": 0.29, + "learning_rate": 1.7839298503857913e-05, + "loss": 1.4674, + "step": 2783 + }, + { + "epoch": 0.29, + "learning_rate": 1.7837025514667224e-05, + "loss": 1.4662, + "step": 2784 + }, + { + "epoch": 0.29, + "learning_rate": 1.7834751475516484e-05, + "loss": 1.3555, + "step": 2785 + }, + { + "epoch": 0.29, + "learning_rate": 1.783247638671035e-05, + "loss": 1.4307, + "step": 2786 + }, + { + "epoch": 0.29, + "eval_loss": 1.500258445739746, + "eval_runtime": 77.406, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 2786 + }, + { + "epoch": 0.29, + "learning_rate": 1.7830200248553633e-05, + "loss": 1.4596, + "step": 2787 + }, + { + "epoch": 0.29, + "learning_rate": 1.7827923061351273e-05, + "loss": 1.6118, + "step": 2788 + }, + { + "epoch": 0.29, + "learning_rate": 1.7825644825408353e-05, + "loss": 1.4782, + "step": 2789 + }, + { + "epoch": 0.29, + "learning_rate": 1.78233655410301e-05, + "loss": 1.4681, + "step": 2790 + }, + { + "epoch": 0.29, + "learning_rate": 1.782108520852188e-05, + "loss": 1.6281, + "step": 2791 + }, + { + "epoch": 0.29, + "learning_rate": 1.78188038281892e-05, + "loss": 1.4446, + "step": 2792 + }, + { + "epoch": 0.29, + "learning_rate": 1.7816521400337704e-05, + "loss": 1.479, + "step": 2793 + }, + { + "epoch": 0.29, + "learning_rate": 1.7814237925273178e-05, + "loss": 1.5457, + "step": 2794 + }, + { + "epoch": 0.29, + "learning_rate": 1.7811953403301547e-05, + "loss": 1.3928, + "step": 2795 + }, + { + "epoch": 0.29, + "learning_rate": 1.780966783472889e-05, + "loss": 1.4321, + "step": 2796 + }, + { + "epoch": 0.29, + "learning_rate": 1.78073812198614e-05, + "loss": 1.5734, + "step": 2797 + }, + { + "epoch": 0.29, + "learning_rate": 1.7805093559005432e-05, + "loss": 1.4356, + "step": 2798 + }, + { + "epoch": 0.29, + "learning_rate": 1.7802804852467473e-05, + "loss": 1.4656, + "step": 2799 + }, + { + "epoch": 0.29, + "learning_rate": 1.780051510055415e-05, + "loss": 1.4052, + "step": 2800 + }, + { + "epoch": 0.29, + "learning_rate": 1.7798224303572228e-05, + "loss": 1.4758, + "step": 2801 + }, + { + "epoch": 0.29, + "learning_rate": 1.7795932461828622e-05, + "loss": 1.4326, + "step": 2802 + }, + { + "epoch": 0.29, + "learning_rate": 1.7793639575630376e-05, + "loss": 1.3409, + "step": 2803 + }, + { + "epoch": 0.29, + "learning_rate": 1.7791345645284678e-05, + "loss": 1.4175, + "step": 2804 + }, + { + "epoch": 0.29, + "learning_rate": 1.7789050671098853e-05, + "loss": 1.383, + "step": 2805 + }, + { + "epoch": 0.29, + "learning_rate": 1.7786754653380373e-05, + "loss": 1.5162, + "step": 2806 + }, + { + "epoch": 0.29, + "learning_rate": 1.7784457592436847e-05, + "loss": 1.4899, + "step": 2807 + }, + { + "epoch": 0.29, + "learning_rate": 1.7782159488576016e-05, + "loss": 1.4874, + "step": 2808 + }, + { + "epoch": 0.29, + "learning_rate": 1.777986034210577e-05, + "loss": 1.4363, + "step": 2809 + }, + { + "epoch": 0.29, + "learning_rate": 1.7777560153334134e-05, + "loss": 1.4223, + "step": 2810 + }, + { + "epoch": 0.29, + "learning_rate": 1.7775258922569273e-05, + "loss": 1.4792, + "step": 2811 + }, + { + "epoch": 0.29, + "learning_rate": 1.77729566501195e-05, + "loss": 1.4475, + "step": 2812 + }, + { + "epoch": 0.29, + "learning_rate": 1.7770653336293253e-05, + "loss": 1.5157, + "step": 2813 + }, + { + "epoch": 0.3, + "learning_rate": 1.776834898139912e-05, + "loss": 1.389, + "step": 2814 + }, + { + "epoch": 0.3, + "learning_rate": 1.7766043585745824e-05, + "loss": 1.4358, + "step": 2815 + }, + { + "epoch": 0.3, + "learning_rate": 1.776373714964223e-05, + "loss": 1.4297, + "step": 2816 + }, + { + "epoch": 0.3, + "learning_rate": 1.7761429673397344e-05, + "loss": 1.4102, + "step": 2817 + }, + { + "epoch": 0.3, + "learning_rate": 1.77591211573203e-05, + "loss": 1.4572, + "step": 2818 + }, + { + "epoch": 0.3, + "learning_rate": 1.775681160172039e-05, + "loss": 1.448, + "step": 2819 + }, + { + "epoch": 0.3, + "learning_rate": 1.7754501006907025e-05, + "loss": 1.4426, + "step": 2820 + }, + { + "epoch": 0.3, + "learning_rate": 1.7752189373189773e-05, + "loss": 1.4566, + "step": 2821 + }, + { + "epoch": 0.3, + "learning_rate": 1.7749876700878332e-05, + "loss": 1.4267, + "step": 2822 + }, + { + "epoch": 0.3, + "learning_rate": 1.7747562990282538e-05, + "loss": 1.3951, + "step": 2823 + }, + { + "epoch": 0.3, + "learning_rate": 1.7745248241712373e-05, + "loss": 1.4668, + "step": 2824 + }, + { + "epoch": 0.3, + "learning_rate": 1.774293245547795e-05, + "loss": 1.4924, + "step": 2825 + }, + { + "epoch": 0.3, + "learning_rate": 1.7740615631889525e-05, + "loss": 1.5258, + "step": 2826 + }, + { + "epoch": 0.3, + "learning_rate": 1.7738297771257496e-05, + "loss": 1.4323, + "step": 2827 + }, + { + "epoch": 0.3, + "learning_rate": 1.7735978873892393e-05, + "loss": 1.439, + "step": 2828 + }, + { + "epoch": 0.3, + "learning_rate": 1.773365894010489e-05, + "loss": 1.5658, + "step": 2829 + }, + { + "epoch": 0.3, + "learning_rate": 1.77313379702058e-05, + "loss": 1.4607, + "step": 2830 + }, + { + "epoch": 0.3, + "learning_rate": 1.7729015964506073e-05, + "loss": 1.5544, + "step": 2831 + }, + { + "epoch": 0.3, + "learning_rate": 1.7726692923316798e-05, + "loss": 1.4232, + "step": 2832 + }, + { + "epoch": 0.3, + "learning_rate": 1.77243688469492e-05, + "loss": 1.415, + "step": 2833 + }, + { + "epoch": 0.3, + "learning_rate": 1.772204373571465e-05, + "loss": 1.4658, + "step": 2834 + }, + { + "epoch": 0.3, + "learning_rate": 1.7719717589924647e-05, + "loss": 1.4678, + "step": 2835 + }, + { + "epoch": 0.3, + "learning_rate": 1.771739040989084e-05, + "loss": 1.3021, + "step": 2836 + }, + { + "epoch": 0.3, + "learning_rate": 1.771506219592501e-05, + "loss": 1.4045, + "step": 2837 + }, + { + "epoch": 0.3, + "learning_rate": 1.7712732948339085e-05, + "loss": 1.4593, + "step": 2838 + }, + { + "epoch": 0.3, + "learning_rate": 1.7710402667445108e-05, + "loss": 1.4175, + "step": 2839 + }, + { + "epoch": 0.3, + "learning_rate": 1.770807135355529e-05, + "loss": 1.3939, + "step": 2840 + }, + { + "epoch": 0.3, + "learning_rate": 1.7705739006981963e-05, + "loss": 1.6089, + "step": 2841 + }, + { + "epoch": 0.3, + "learning_rate": 1.77034056280376e-05, + "loss": 1.3952, + "step": 2842 + }, + { + "epoch": 0.3, + "learning_rate": 1.7701071217034818e-05, + "loss": 1.5086, + "step": 2843 + }, + { + "epoch": 0.3, + "learning_rate": 1.7698735774286362e-05, + "loss": 1.4706, + "step": 2844 + }, + { + "epoch": 0.3, + "learning_rate": 1.7696399300105128e-05, + "loss": 1.4286, + "step": 2845 + }, + { + "epoch": 0.3, + "learning_rate": 1.7694061794804137e-05, + "loss": 1.4418, + "step": 2846 + }, + { + "epoch": 0.3, + "learning_rate": 1.7691723258696562e-05, + "loss": 1.516, + "step": 2847 + }, + { + "epoch": 0.3, + "learning_rate": 1.76893836920957e-05, + "loss": 1.4354, + "step": 2848 + }, + { + "epoch": 0.3, + "learning_rate": 1.7687043095314998e-05, + "loss": 1.7503, + "step": 2849 + }, + { + "epoch": 0.3, + "learning_rate": 1.7684701468668032e-05, + "loss": 1.5985, + "step": 2850 + }, + { + "epoch": 0.3, + "learning_rate": 1.768235881246852e-05, + "loss": 1.442, + "step": 2851 + }, + { + "epoch": 0.3, + "learning_rate": 1.7680015127030322e-05, + "loss": 1.4924, + "step": 2852 + }, + { + "epoch": 0.3, + "learning_rate": 1.7677670412667425e-05, + "loss": 1.4461, + "step": 2853 + }, + { + "epoch": 0.3, + "learning_rate": 1.7675324669693968e-05, + "loss": 1.3823, + "step": 2854 + }, + { + "epoch": 0.3, + "learning_rate": 1.767297789842421e-05, + "loss": 1.452, + "step": 2855 + }, + { + "epoch": 0.3, + "learning_rate": 1.767063009917257e-05, + "loss": 1.46, + "step": 2856 + }, + { + "epoch": 0.3, + "learning_rate": 1.7668281272253587e-05, + "loss": 1.4129, + "step": 2857 + }, + { + "epoch": 0.3, + "learning_rate": 1.766593141798194e-05, + "loss": 1.4057, + "step": 2858 + }, + { + "epoch": 0.3, + "learning_rate": 1.7663580536672456e-05, + "loss": 1.5162, + "step": 2859 + }, + { + "epoch": 0.3, + "learning_rate": 1.7661228628640087e-05, + "loss": 1.5177, + "step": 2860 + }, + { + "epoch": 0.3, + "learning_rate": 1.7658875694199933e-05, + "loss": 1.4548, + "step": 2861 + }, + { + "epoch": 0.3, + "learning_rate": 1.7656521733667223e-05, + "loss": 1.4511, + "step": 2862 + }, + { + "epoch": 0.3, + "learning_rate": 1.765416674735733e-05, + "loss": 1.4778, + "step": 2863 + }, + { + "epoch": 0.3, + "learning_rate": 1.765181073558576e-05, + "loss": 1.3935, + "step": 2864 + }, + { + "epoch": 0.3, + "learning_rate": 1.7649453698668156e-05, + "loss": 1.4659, + "step": 2865 + }, + { + "epoch": 0.3, + "learning_rate": 1.7647095636920305e-05, + "loss": 1.7042, + "step": 2866 + }, + { + "epoch": 0.3, + "learning_rate": 1.7644736550658124e-05, + "loss": 1.7957, + "step": 2867 + }, + { + "epoch": 0.3, + "learning_rate": 1.764237644019767e-05, + "loss": 1.5139, + "step": 2868 + }, + { + "epoch": 0.3, + "learning_rate": 1.764001530585514e-05, + "loss": 1.4117, + "step": 2869 + }, + { + "epoch": 0.3, + "learning_rate": 1.7637653147946858e-05, + "loss": 1.4837, + "step": 2870 + }, + { + "epoch": 0.3, + "learning_rate": 1.7635289966789298e-05, + "loss": 1.4379, + "step": 2871 + }, + { + "epoch": 0.3, + "learning_rate": 1.7632925762699068e-05, + "loss": 1.4491, + "step": 2872 + }, + { + "epoch": 0.3, + "learning_rate": 1.7630560535992905e-05, + "loss": 1.4006, + "step": 2873 + }, + { + "epoch": 0.3, + "learning_rate": 1.7628194286987694e-05, + "loss": 1.5484, + "step": 2874 + }, + { + "epoch": 0.3, + "learning_rate": 1.7625827016000446e-05, + "loss": 1.4926, + "step": 2875 + }, + { + "epoch": 0.3, + "learning_rate": 1.762345872334832e-05, + "loss": 1.3909, + "step": 2876 + }, + { + "epoch": 0.3, + "learning_rate": 1.76210894093486e-05, + "loss": 1.405, + "step": 2877 + }, + { + "epoch": 0.3, + "learning_rate": 1.7618719074318718e-05, + "loss": 1.4736, + "step": 2878 + }, + { + "epoch": 0.3, + "learning_rate": 1.7616347718576238e-05, + "loss": 1.4445, + "step": 2879 + }, + { + "epoch": 0.3, + "learning_rate": 1.761397534243886e-05, + "loss": 1.4878, + "step": 2880 + }, + { + "epoch": 0.3, + "learning_rate": 1.7611601946224417e-05, + "loss": 1.4414, + "step": 2881 + }, + { + "epoch": 0.3, + "learning_rate": 1.760922753025089e-05, + "loss": 1.5657, + "step": 2882 + }, + { + "epoch": 0.3, + "learning_rate": 1.7606852094836385e-05, + "loss": 1.5008, + "step": 2883 + }, + { + "epoch": 0.3, + "learning_rate": 1.7604475640299153e-05, + "loss": 1.4922, + "step": 2884 + }, + { + "epoch": 0.3, + "learning_rate": 1.7602098166957577e-05, + "loss": 1.7451, + "step": 2885 + }, + { + "epoch": 0.3, + "learning_rate": 1.759971967513017e-05, + "loss": 1.7077, + "step": 2886 + }, + { + "epoch": 0.3, + "learning_rate": 1.75973401651356e-05, + "loss": 1.3986, + "step": 2887 + }, + { + "epoch": 0.3, + "learning_rate": 1.7594959637292656e-05, + "loss": 1.3966, + "step": 2888 + }, + { + "epoch": 0.3, + "learning_rate": 1.7592578091920264e-05, + "loss": 1.4086, + "step": 2889 + }, + { + "epoch": 0.3, + "learning_rate": 1.7590195529337495e-05, + "loss": 1.4481, + "step": 2890 + }, + { + "epoch": 0.3, + "learning_rate": 1.7587811949863548e-05, + "loss": 1.3974, + "step": 2891 + }, + { + "epoch": 0.3, + "learning_rate": 1.7585427353817758e-05, + "loss": 1.5013, + "step": 2892 + }, + { + "epoch": 0.3, + "learning_rate": 1.7583041741519608e-05, + "loss": 1.5454, + "step": 2893 + }, + { + "epoch": 0.3, + "learning_rate": 1.7580655113288708e-05, + "loss": 1.5033, + "step": 2894 + }, + { + "epoch": 0.3, + "learning_rate": 1.7578267469444793e-05, + "loss": 1.4332, + "step": 2895 + }, + { + "epoch": 0.3, + "learning_rate": 1.757587881030776e-05, + "loss": 1.4667, + "step": 2896 + }, + { + "epoch": 0.3, + "learning_rate": 1.7573489136197623e-05, + "loss": 1.4314, + "step": 2897 + }, + { + "epoch": 0.3, + "learning_rate": 1.7571098447434532e-05, + "loss": 1.4514, + "step": 2898 + }, + { + "epoch": 0.3, + "learning_rate": 1.7568706744338784e-05, + "loss": 1.4872, + "step": 2899 + }, + { + "epoch": 0.3, + "learning_rate": 1.7566314027230808e-05, + "loss": 1.4841, + "step": 2900 + }, + { + "epoch": 0.3, + "learning_rate": 1.7563920296431158e-05, + "loss": 1.3964, + "step": 2901 + }, + { + "epoch": 0.3, + "learning_rate": 1.7561525552260538e-05, + "loss": 1.4932, + "step": 2902 + }, + { + "epoch": 0.3, + "learning_rate": 1.755912979503978e-05, + "loss": 1.4153, + "step": 2903 + }, + { + "epoch": 0.3, + "learning_rate": 1.755673302508986e-05, + "loss": 1.4939, + "step": 2904 + }, + { + "epoch": 0.3, + "learning_rate": 1.755433524273187e-05, + "loss": 1.4437, + "step": 2905 + }, + { + "epoch": 0.3, + "learning_rate": 1.7551936448287067e-05, + "loss": 1.486, + "step": 2906 + }, + { + "epoch": 0.3, + "learning_rate": 1.754953664207682e-05, + "loss": 1.4362, + "step": 2907 + }, + { + "epoch": 0.3, + "learning_rate": 1.7547135824422635e-05, + "loss": 1.4954, + "step": 2908 + }, + { + "epoch": 0.31, + "learning_rate": 1.7544733995646174e-05, + "loss": 1.4552, + "step": 2909 + }, + { + "epoch": 0.31, + "learning_rate": 1.7542331156069213e-05, + "loss": 1.4654, + "step": 2910 + }, + { + "epoch": 0.31, + "learning_rate": 1.753992730601367e-05, + "loss": 1.4531, + "step": 2911 + }, + { + "epoch": 0.31, + "learning_rate": 1.75375224458016e-05, + "loss": 1.4949, + "step": 2912 + }, + { + "epoch": 0.31, + "learning_rate": 1.753511657575519e-05, + "loss": 1.3998, + "step": 2913 + }, + { + "epoch": 0.31, + "learning_rate": 1.753270969619677e-05, + "loss": 1.3904, + "step": 2914 + }, + { + "epoch": 0.31, + "learning_rate": 1.7530301807448794e-05, + "loss": 1.481, + "step": 2915 + }, + { + "epoch": 0.31, + "learning_rate": 1.7527892909833864e-05, + "loss": 1.4301, + "step": 2916 + }, + { + "epoch": 0.31, + "learning_rate": 1.7525483003674707e-05, + "loss": 1.4377, + "step": 2917 + }, + { + "epoch": 0.31, + "learning_rate": 1.7523072089294188e-05, + "loss": 1.5077, + "step": 2918 + }, + { + "epoch": 0.31, + "learning_rate": 1.752066016701531e-05, + "loss": 1.3802, + "step": 2919 + }, + { + "epoch": 0.31, + "learning_rate": 1.7518247237161205e-05, + "loss": 1.3991, + "step": 2920 + }, + { + "epoch": 0.31, + "learning_rate": 1.7515833300055146e-05, + "loss": 1.4283, + "step": 2921 + }, + { + "epoch": 0.31, + "learning_rate": 1.7513418356020535e-05, + "loss": 1.3688, + "step": 2922 + }, + { + "epoch": 0.31, + "learning_rate": 1.751100240538092e-05, + "loss": 1.4336, + "step": 2923 + }, + { + "epoch": 0.31, + "learning_rate": 1.7508585448459967e-05, + "loss": 1.4302, + "step": 2924 + }, + { + "epoch": 0.31, + "learning_rate": 1.7506167485581493e-05, + "loss": 1.4293, + "step": 2925 + }, + { + "epoch": 0.31, + "learning_rate": 1.750374851706944e-05, + "loss": 1.4262, + "step": 2926 + }, + { + "epoch": 0.31, + "learning_rate": 1.7501328543247892e-05, + "loss": 1.4128, + "step": 2927 + }, + { + "epoch": 0.31, + "learning_rate": 1.7498907564441054e-05, + "loss": 1.4258, + "step": 2928 + }, + { + "epoch": 0.31, + "learning_rate": 1.749648558097328e-05, + "loss": 1.4904, + "step": 2929 + }, + { + "epoch": 0.31, + "learning_rate": 1.749406259316906e-05, + "loss": 1.4628, + "step": 2930 + }, + { + "epoch": 0.31, + "learning_rate": 1.7491638601353004e-05, + "loss": 1.4908, + "step": 2931 + }, + { + "epoch": 0.31, + "learning_rate": 1.7489213605849867e-05, + "loss": 1.4563, + "step": 2932 + }, + { + "epoch": 0.31, + "learning_rate": 1.7486787606984533e-05, + "loss": 1.5006, + "step": 2933 + }, + { + "epoch": 0.31, + "learning_rate": 1.748436060508203e-05, + "loss": 1.424, + "step": 2934 + }, + { + "epoch": 0.31, + "learning_rate": 1.7481932600467508e-05, + "loss": 1.4136, + "step": 2935 + }, + { + "epoch": 0.31, + "learning_rate": 1.747950359346626e-05, + "loss": 1.3835, + "step": 2936 + }, + { + "epoch": 0.31, + "learning_rate": 1.747707358440371e-05, + "loss": 1.5284, + "step": 2937 + }, + { + "epoch": 0.31, + "learning_rate": 1.7474642573605418e-05, + "loss": 1.4592, + "step": 2938 + }, + { + "epoch": 0.31, + "learning_rate": 1.7472210561397075e-05, + "loss": 1.5483, + "step": 2939 + }, + { + "epoch": 0.31, + "learning_rate": 1.746977754810451e-05, + "loss": 1.521, + "step": 2940 + }, + { + "epoch": 0.31, + "learning_rate": 1.7467343534053683e-05, + "loss": 1.4276, + "step": 2941 + }, + { + "epoch": 0.31, + "learning_rate": 1.746490851957069e-05, + "loss": 1.4302, + "step": 2942 + }, + { + "epoch": 0.31, + "learning_rate": 1.746247250498176e-05, + "loss": 1.4439, + "step": 2943 + }, + { + "epoch": 0.31, + "learning_rate": 1.7460035490613255e-05, + "loss": 1.4991, + "step": 2944 + }, + { + "epoch": 0.31, + "learning_rate": 1.7457597476791674e-05, + "loss": 1.4188, + "step": 2945 + }, + { + "epoch": 0.31, + "learning_rate": 1.7455158463843648e-05, + "loss": 1.4685, + "step": 2946 + }, + { + "epoch": 0.31, + "learning_rate": 1.745271845209594e-05, + "loss": 1.3811, + "step": 2947 + }, + { + "epoch": 0.31, + "learning_rate": 1.7450277441875454e-05, + "loss": 1.4869, + "step": 2948 + }, + { + "epoch": 0.31, + "learning_rate": 1.7447835433509218e-05, + "loss": 1.5001, + "step": 2949 + }, + { + "epoch": 0.31, + "learning_rate": 1.74453924273244e-05, + "loss": 1.4757, + "step": 2950 + }, + { + "epoch": 0.31, + "learning_rate": 1.74429484236483e-05, + "loss": 1.5072, + "step": 2951 + }, + { + "epoch": 0.31, + "learning_rate": 1.744050342280835e-05, + "loss": 1.4242, + "step": 2952 + }, + { + "epoch": 0.31, + "learning_rate": 1.743805742513212e-05, + "loss": 1.4462, + "step": 2953 + }, + { + "epoch": 0.31, + "learning_rate": 1.743561043094731e-05, + "loss": 1.6815, + "step": 2954 + }, + { + "epoch": 0.31, + "learning_rate": 1.7433162440581755e-05, + "loss": 1.427, + "step": 2955 + }, + { + "epoch": 0.31, + "learning_rate": 1.7430713454363423e-05, + "loss": 1.2933, + "step": 2956 + }, + { + "epoch": 0.31, + "learning_rate": 1.742826347262041e-05, + "loss": 1.4247, + "step": 2957 + }, + { + "epoch": 0.31, + "learning_rate": 1.7425812495680955e-05, + "loss": 1.399, + "step": 2958 + }, + { + "epoch": 0.31, + "learning_rate": 1.742336052387343e-05, + "loss": 1.4818, + "step": 2959 + }, + { + "epoch": 0.31, + "learning_rate": 1.742090755752633e-05, + "loss": 1.3839, + "step": 2960 + }, + { + "epoch": 0.31, + "learning_rate": 1.741845359696829e-05, + "loss": 1.4669, + "step": 2961 + }, + { + "epoch": 0.31, + "learning_rate": 1.741599864252808e-05, + "loss": 1.468, + "step": 2962 + }, + { + "epoch": 0.31, + "learning_rate": 1.74135426945346e-05, + "loss": 1.4135, + "step": 2963 + }, + { + "epoch": 0.31, + "learning_rate": 1.7411085753316882e-05, + "loss": 1.5899, + "step": 2964 + }, + { + "epoch": 0.31, + "learning_rate": 1.74086278192041e-05, + "loss": 1.6115, + "step": 2965 + }, + { + "epoch": 0.31, + "learning_rate": 1.740616889252554e-05, + "loss": 1.3988, + "step": 2966 + }, + { + "epoch": 0.31, + "learning_rate": 1.740370897361065e-05, + "loss": 1.5001, + "step": 2967 + }, + { + "epoch": 0.31, + "learning_rate": 1.740124806278899e-05, + "loss": 1.459, + "step": 2968 + }, + { + "epoch": 0.31, + "learning_rate": 1.7398786160390258e-05, + "loss": 1.4489, + "step": 2969 + }, + { + "epoch": 0.31, + "learning_rate": 1.7396323266744283e-05, + "loss": 1.4397, + "step": 2970 + }, + { + "epoch": 0.31, + "learning_rate": 1.7393859382181033e-05, + "loss": 1.4687, + "step": 2971 + }, + { + "epoch": 0.31, + "learning_rate": 1.7391394507030606e-05, + "loss": 1.4495, + "step": 2972 + }, + { + "epoch": 0.31, + "learning_rate": 1.738892864162323e-05, + "loss": 1.4745, + "step": 2973 + }, + { + "epoch": 0.31, + "learning_rate": 1.7386461786289274e-05, + "loss": 1.3943, + "step": 2974 + }, + { + "epoch": 0.31, + "learning_rate": 1.738399394135922e-05, + "loss": 1.4595, + "step": 2975 + }, + { + "epoch": 0.31, + "learning_rate": 1.738152510716371e-05, + "loss": 1.4023, + "step": 2976 + }, + { + "epoch": 0.31, + "learning_rate": 1.7379055284033493e-05, + "loss": 1.3938, + "step": 2977 + }, + { + "epoch": 0.31, + "learning_rate": 1.7376584472299468e-05, + "loss": 1.4576, + "step": 2978 + }, + { + "epoch": 0.31, + "learning_rate": 1.737411267229266e-05, + "loss": 1.424, + "step": 2979 + }, + { + "epoch": 0.31, + "learning_rate": 1.7371639884344225e-05, + "loss": 1.4224, + "step": 2980 + }, + { + "epoch": 0.31, + "learning_rate": 1.736916610878545e-05, + "loss": 1.4228, + "step": 2981 + }, + { + "epoch": 0.31, + "learning_rate": 1.7366691345947768e-05, + "loss": 1.5021, + "step": 2982 + }, + { + "epoch": 0.31, + "learning_rate": 1.736421559616272e-05, + "loss": 1.3589, + "step": 2983 + }, + { + "epoch": 0.31, + "learning_rate": 1.7361738859762007e-05, + "loss": 1.4748, + "step": 2984 + }, + { + "epoch": 0.31, + "learning_rate": 1.735926113707743e-05, + "loss": 1.3974, + "step": 2985 + }, + { + "epoch": 0.31, + "eval_loss": 1.4849082231521606, + "eval_runtime": 77.3271, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2985 + }, + { + "epoch": 0.31, + "learning_rate": 1.735678242844096e-05, + "loss": 1.392, + "step": 2986 + }, + { + "epoch": 0.31, + "learning_rate": 1.735430273418467e-05, + "loss": 1.4277, + "step": 2987 + }, + { + "epoch": 0.31, + "learning_rate": 1.735182205464077e-05, + "loss": 1.4216, + "step": 2988 + }, + { + "epoch": 0.31, + "learning_rate": 1.7349340390141617e-05, + "loss": 1.4546, + "step": 2989 + }, + { + "epoch": 0.31, + "learning_rate": 1.734685774101969e-05, + "loss": 1.4264, + "step": 2990 + }, + { + "epoch": 0.31, + "learning_rate": 1.7344374107607593e-05, + "loss": 1.4307, + "step": 2991 + }, + { + "epoch": 0.31, + "learning_rate": 1.7341889490238076e-05, + "loss": 1.4266, + "step": 2992 + }, + { + "epoch": 0.31, + "learning_rate": 1.7339403889244008e-05, + "loss": 1.4486, + "step": 2993 + }, + { + "epoch": 0.31, + "learning_rate": 1.7336917304958403e-05, + "loss": 1.4345, + "step": 2994 + }, + { + "epoch": 0.31, + "learning_rate": 1.7334429737714395e-05, + "loss": 1.476, + "step": 2995 + }, + { + "epoch": 0.31, + "learning_rate": 1.7331941187845248e-05, + "loss": 1.5148, + "step": 2996 + }, + { + "epoch": 0.31, + "learning_rate": 1.7329451655684372e-05, + "loss": 1.4026, + "step": 2997 + }, + { + "epoch": 0.31, + "learning_rate": 1.7326961141565303e-05, + "loss": 1.3935, + "step": 2998 + }, + { + "epoch": 0.31, + "learning_rate": 1.73244696458217e-05, + "loss": 1.4483, + "step": 2999 + }, + { + "epoch": 0.31, + "learning_rate": 1.7321977168787356e-05, + "loss": 1.5197, + "step": 3000 + }, + { + "epoch": 0.31, + "learning_rate": 1.7319483710796208e-05, + "loss": 1.4648, + "step": 3001 + }, + { + "epoch": 0.31, + "learning_rate": 1.7316989272182308e-05, + "loss": 1.4171, + "step": 3002 + }, + { + "epoch": 0.31, + "learning_rate": 1.731449385327985e-05, + "loss": 1.4541, + "step": 3003 + }, + { + "epoch": 0.32, + "learning_rate": 1.731199745442316e-05, + "loss": 1.4605, + "step": 3004 + }, + { + "epoch": 0.32, + "learning_rate": 1.7309500075946683e-05, + "loss": 1.5122, + "step": 3005 + }, + { + "epoch": 0.32, + "learning_rate": 1.7307001718185007e-05, + "loss": 1.5243, + "step": 3006 + }, + { + "epoch": 0.32, + "learning_rate": 1.7304502381472844e-05, + "loss": 1.4997, + "step": 3007 + }, + { + "epoch": 0.32, + "learning_rate": 1.730200206614505e-05, + "loss": 1.4891, + "step": 3008 + }, + { + "epoch": 0.32, + "learning_rate": 1.72995007725366e-05, + "loss": 1.4376, + "step": 3009 + }, + { + "epoch": 0.32, + "learning_rate": 1.7296998500982595e-05, + "loss": 1.4403, + "step": 3010 + }, + { + "epoch": 0.32, + "learning_rate": 1.7294495251818285e-05, + "loss": 1.5153, + "step": 3011 + }, + { + "epoch": 0.32, + "learning_rate": 1.729199102537904e-05, + "loss": 1.4996, + "step": 3012 + }, + { + "epoch": 0.32, + "learning_rate": 1.7289485822000356e-05, + "loss": 1.5302, + "step": 3013 + }, + { + "epoch": 0.32, + "learning_rate": 1.7286979642017867e-05, + "loss": 1.5641, + "step": 3014 + }, + { + "epoch": 0.32, + "learning_rate": 1.728447248576734e-05, + "loss": 1.438, + "step": 3015 + }, + { + "epoch": 0.32, + "learning_rate": 1.7281964353584674e-05, + "loss": 1.4796, + "step": 3016 + }, + { + "epoch": 0.32, + "learning_rate": 1.727945524580588e-05, + "loss": 1.4413, + "step": 3017 + }, + { + "epoch": 0.32, + "learning_rate": 1.727694516276713e-05, + "loss": 1.3966, + "step": 3018 + }, + { + "epoch": 0.32, + "learning_rate": 1.72744341048047e-05, + "loss": 1.5267, + "step": 3019 + }, + { + "epoch": 0.32, + "learning_rate": 1.727192207225501e-05, + "loss": 1.4284, + "step": 3020 + }, + { + "epoch": 0.32, + "learning_rate": 1.726940906545461e-05, + "loss": 1.5137, + "step": 3021 + }, + { + "epoch": 0.32, + "learning_rate": 1.7266895084740173e-05, + "loss": 1.3966, + "step": 3022 + }, + { + "epoch": 0.32, + "learning_rate": 1.7264380130448514e-05, + "loss": 1.4156, + "step": 3023 + }, + { + "epoch": 0.32, + "learning_rate": 1.726186420291657e-05, + "loss": 1.4644, + "step": 3024 + }, + { + "epoch": 0.32, + "learning_rate": 1.725934730248141e-05, + "loss": 1.4768, + "step": 3025 + }, + { + "epoch": 0.32, + "learning_rate": 1.7256829429480233e-05, + "loss": 1.4428, + "step": 3026 + }, + { + "epoch": 0.32, + "learning_rate": 1.7254310584250373e-05, + "loss": 1.4495, + "step": 3027 + }, + { + "epoch": 0.32, + "learning_rate": 1.725179076712929e-05, + "loss": 1.3867, + "step": 3028 + }, + { + "epoch": 0.32, + "learning_rate": 1.7249269978454567e-05, + "loss": 1.5011, + "step": 3029 + }, + { + "epoch": 0.32, + "learning_rate": 1.7246748218563937e-05, + "loss": 1.3916, + "step": 3030 + }, + { + "epoch": 0.32, + "learning_rate": 1.7244225487795238e-05, + "loss": 1.4984, + "step": 3031 + }, + { + "epoch": 0.32, + "learning_rate": 1.7241701786486464e-05, + "loss": 1.5776, + "step": 3032 + }, + { + "epoch": 0.32, + "learning_rate": 1.7239177114975717e-05, + "loss": 1.5018, + "step": 3033 + }, + { + "epoch": 0.32, + "learning_rate": 1.7236651473601244e-05, + "loss": 1.5042, + "step": 3034 + }, + { + "epoch": 0.32, + "learning_rate": 1.723412486270141e-05, + "loss": 1.4636, + "step": 3035 + }, + { + "epoch": 0.32, + "learning_rate": 1.723159728261472e-05, + "loss": 1.5612, + "step": 3036 + }, + { + "epoch": 0.32, + "learning_rate": 1.7229068733679803e-05, + "loss": 1.4399, + "step": 3037 + }, + { + "epoch": 0.32, + "learning_rate": 1.7226539216235424e-05, + "loss": 1.5635, + "step": 3038 + }, + { + "epoch": 0.32, + "learning_rate": 1.7224008730620468e-05, + "loss": 1.4329, + "step": 3039 + }, + { + "epoch": 0.32, + "learning_rate": 1.7221477277173956e-05, + "loss": 1.4886, + "step": 3040 + }, + { + "epoch": 0.32, + "learning_rate": 1.721894485623504e-05, + "loss": 1.4741, + "step": 3041 + }, + { + "epoch": 0.32, + "learning_rate": 1.7216411468143e-05, + "loss": 1.4678, + "step": 3042 + }, + { + "epoch": 0.32, + "learning_rate": 1.721387711323724e-05, + "loss": 1.4758, + "step": 3043 + }, + { + "epoch": 0.32, + "learning_rate": 1.72113417918573e-05, + "loss": 1.441, + "step": 3044 + }, + { + "epoch": 0.32, + "learning_rate": 1.7208805504342855e-05, + "loss": 1.4328, + "step": 3045 + }, + { + "epoch": 0.32, + "learning_rate": 1.720626825103369e-05, + "loss": 1.4254, + "step": 3046 + }, + { + "epoch": 0.32, + "learning_rate": 1.7203730032269744e-05, + "loss": 1.4462, + "step": 3047 + }, + { + "epoch": 0.32, + "learning_rate": 1.7201190848391066e-05, + "loss": 1.4826, + "step": 3048 + }, + { + "epoch": 0.32, + "learning_rate": 1.719865069973784e-05, + "loss": 1.4215, + "step": 3049 + }, + { + "epoch": 0.32, + "learning_rate": 1.7196109586650385e-05, + "loss": 1.4291, + "step": 3050 + }, + { + "epoch": 0.32, + "learning_rate": 1.7193567509469146e-05, + "loss": 1.5005, + "step": 3051 + }, + { + "epoch": 0.32, + "learning_rate": 1.719102446853469e-05, + "loss": 1.4216, + "step": 3052 + }, + { + "epoch": 0.32, + "learning_rate": 1.7188480464187725e-05, + "loss": 1.4349, + "step": 3053 + }, + { + "epoch": 0.32, + "learning_rate": 1.718593549676908e-05, + "loss": 1.4784, + "step": 3054 + }, + { + "epoch": 0.32, + "learning_rate": 1.7183389566619714e-05, + "loss": 1.4325, + "step": 3055 + }, + { + "epoch": 0.32, + "learning_rate": 1.7180842674080717e-05, + "loss": 1.5387, + "step": 3056 + }, + { + "epoch": 0.32, + "learning_rate": 1.717829481949331e-05, + "loss": 1.655, + "step": 3057 + }, + { + "epoch": 0.32, + "learning_rate": 1.717574600319883e-05, + "loss": 1.4623, + "step": 3058 + }, + { + "epoch": 0.32, + "learning_rate": 1.7173196225538768e-05, + "loss": 1.4646, + "step": 3059 + }, + { + "epoch": 0.32, + "learning_rate": 1.717064548685472e-05, + "loss": 1.4641, + "step": 3060 + }, + { + "epoch": 0.32, + "learning_rate": 1.7168093787488418e-05, + "loss": 1.4033, + "step": 3061 + }, + { + "epoch": 0.32, + "learning_rate": 1.7165541127781726e-05, + "loss": 1.4085, + "step": 3062 + }, + { + "epoch": 0.32, + "learning_rate": 1.716298750807664e-05, + "loss": 1.387, + "step": 3063 + }, + { + "epoch": 0.32, + "learning_rate": 1.7160432928715272e-05, + "loss": 1.4197, + "step": 3064 + }, + { + "epoch": 0.32, + "learning_rate": 1.7157877390039872e-05, + "loss": 1.4883, + "step": 3065 + }, + { + "epoch": 0.32, + "learning_rate": 1.7155320892392818e-05, + "loss": 1.4865, + "step": 3066 + }, + { + "epoch": 0.32, + "learning_rate": 1.715276343611662e-05, + "loss": 1.4532, + "step": 3067 + }, + { + "epoch": 0.32, + "learning_rate": 1.71502050215539e-05, + "loss": 1.3991, + "step": 3068 + }, + { + "epoch": 0.32, + "learning_rate": 1.7147645649047424e-05, + "loss": 1.4318, + "step": 3069 + }, + { + "epoch": 0.32, + "learning_rate": 1.714508531894009e-05, + "loss": 1.3616, + "step": 3070 + }, + { + "epoch": 0.32, + "learning_rate": 1.7142524031574904e-05, + "loss": 1.4481, + "step": 3071 + }, + { + "epoch": 0.32, + "learning_rate": 1.7139961787295022e-05, + "loss": 1.3897, + "step": 3072 + }, + { + "epoch": 0.32, + "learning_rate": 1.7137398586443716e-05, + "loss": 1.3128, + "step": 3073 + }, + { + "epoch": 0.32, + "learning_rate": 1.713483442936439e-05, + "loss": 1.4481, + "step": 3074 + }, + { + "epoch": 0.32, + "learning_rate": 1.713226931640057e-05, + "loss": 1.5374, + "step": 3075 + }, + { + "epoch": 0.32, + "learning_rate": 1.7129703247895923e-05, + "loss": 1.4247, + "step": 3076 + }, + { + "epoch": 0.32, + "learning_rate": 1.712713622419423e-05, + "loss": 1.4098, + "step": 3077 + }, + { + "epoch": 0.32, + "learning_rate": 1.7124568245639414e-05, + "loss": 1.4558, + "step": 3078 + }, + { + "epoch": 0.32, + "learning_rate": 1.7121999312575507e-05, + "loss": 1.4484, + "step": 3079 + }, + { + "epoch": 0.32, + "learning_rate": 1.711942942534669e-05, + "loss": 1.4236, + "step": 3080 + }, + { + "epoch": 0.32, + "learning_rate": 1.7116858584297253e-05, + "loss": 1.613, + "step": 3081 + }, + { + "epoch": 0.32, + "learning_rate": 1.711428678977163e-05, + "loss": 1.4503, + "step": 3082 + }, + { + "epoch": 0.32, + "learning_rate": 1.7111714042114376e-05, + "loss": 1.4072, + "step": 3083 + }, + { + "epoch": 0.32, + "learning_rate": 1.7109140341670168e-05, + "loss": 1.5999, + "step": 3084 + }, + { + "epoch": 0.32, + "learning_rate": 1.7106565688783815e-05, + "loss": 1.4129, + "step": 3085 + }, + { + "epoch": 0.32, + "learning_rate": 1.710399008380026e-05, + "loss": 1.3973, + "step": 3086 + }, + { + "epoch": 0.32, + "learning_rate": 1.710141352706456e-05, + "loss": 1.4292, + "step": 3087 + }, + { + "epoch": 0.32, + "learning_rate": 1.709883601892192e-05, + "loss": 1.4372, + "step": 3088 + }, + { + "epoch": 0.32, + "learning_rate": 1.7096257559717647e-05, + "loss": 1.4924, + "step": 3089 + }, + { + "epoch": 0.32, + "learning_rate": 1.7093678149797196e-05, + "loss": 1.4222, + "step": 3090 + }, + { + "epoch": 0.32, + "learning_rate": 1.7091097789506137e-05, + "loss": 1.4797, + "step": 3091 + }, + { + "epoch": 0.32, + "learning_rate": 1.7088516479190175e-05, + "loss": 1.4738, + "step": 3092 + }, + { + "epoch": 0.32, + "learning_rate": 1.708593421919514e-05, + "loss": 1.5371, + "step": 3093 + }, + { + "epoch": 0.32, + "learning_rate": 1.7083351009866988e-05, + "loss": 1.3802, + "step": 3094 + }, + { + "epoch": 0.32, + "learning_rate": 1.7080766851551795e-05, + "loss": 1.4292, + "step": 3095 + }, + { + "epoch": 0.32, + "learning_rate": 1.707818174459578e-05, + "loss": 1.4478, + "step": 3096 + }, + { + "epoch": 0.32, + "learning_rate": 1.7075595689345285e-05, + "loss": 1.4619, + "step": 3097 + }, + { + "epoch": 0.32, + "learning_rate": 1.7073008686146763e-05, + "loss": 1.4603, + "step": 3098 + }, + { + "epoch": 0.32, + "learning_rate": 1.7070420735346815e-05, + "loss": 1.4548, + "step": 3099 + }, + { + "epoch": 0.33, + "learning_rate": 1.7067831837292157e-05, + "loss": 1.3638, + "step": 3100 + }, + { + "epoch": 0.33, + "learning_rate": 1.7065241992329634e-05, + "loss": 1.4284, + "step": 3101 + }, + { + "epoch": 0.33, + "learning_rate": 1.7062651200806217e-05, + "loss": 1.386, + "step": 3102 + }, + { + "epoch": 0.33, + "learning_rate": 1.7060059463069013e-05, + "loss": 1.5483, + "step": 3103 + }, + { + "epoch": 0.33, + "learning_rate": 1.705746677946524e-05, + "loss": 1.4963, + "step": 3104 + }, + { + "epoch": 0.33, + "learning_rate": 1.7054873150342257e-05, + "loss": 1.4539, + "step": 3105 + }, + { + "epoch": 0.33, + "learning_rate": 1.705227857604754e-05, + "loss": 1.4361, + "step": 3106 + }, + { + "epoch": 0.33, + "learning_rate": 1.7049683056928695e-05, + "loss": 1.3735, + "step": 3107 + }, + { + "epoch": 0.33, + "learning_rate": 1.7047086593333454e-05, + "loss": 1.4324, + "step": 3108 + }, + { + "epoch": 0.33, + "learning_rate": 1.7044489185609685e-05, + "loss": 1.5037, + "step": 3109 + }, + { + "epoch": 0.33, + "learning_rate": 1.704189083410536e-05, + "loss": 1.3913, + "step": 3110 + }, + { + "epoch": 0.33, + "learning_rate": 1.7039291539168604e-05, + "loss": 1.3233, + "step": 3111 + }, + { + "epoch": 0.33, + "learning_rate": 1.703669130114765e-05, + "loss": 1.4897, + "step": 3112 + }, + { + "epoch": 0.33, + "learning_rate": 1.7034090120390862e-05, + "loss": 1.4843, + "step": 3113 + }, + { + "epoch": 0.33, + "learning_rate": 1.7031487997246735e-05, + "loss": 1.3674, + "step": 3114 + }, + { + "epoch": 0.33, + "learning_rate": 1.7028884932063883e-05, + "loss": 1.4475, + "step": 3115 + }, + { + "epoch": 0.33, + "learning_rate": 1.702628092519105e-05, + "loss": 1.4134, + "step": 3116 + }, + { + "epoch": 0.33, + "learning_rate": 1.7023675976977108e-05, + "loss": 1.4484, + "step": 3117 + }, + { + "epoch": 0.33, + "learning_rate": 1.702107008777106e-05, + "loss": 1.407, + "step": 3118 + }, + { + "epoch": 0.33, + "learning_rate": 1.7018463257922005e-05, + "loss": 1.5443, + "step": 3119 + }, + { + "epoch": 0.33, + "learning_rate": 1.701585548777922e-05, + "loss": 1.4548, + "step": 3120 + }, + { + "epoch": 0.33, + "learning_rate": 1.7013246777692063e-05, + "loss": 1.4252, + "step": 3121 + }, + { + "epoch": 0.33, + "learning_rate": 1.7010637128010037e-05, + "loss": 1.3748, + "step": 3122 + }, + { + "epoch": 0.33, + "learning_rate": 1.7008026539082767e-05, + "loss": 1.3804, + "step": 3123 + }, + { + "epoch": 0.33, + "learning_rate": 1.7005415011260008e-05, + "loss": 1.4203, + "step": 3124 + }, + { + "epoch": 0.33, + "learning_rate": 1.7002802544891634e-05, + "loss": 1.4195, + "step": 3125 + }, + { + "epoch": 0.33, + "learning_rate": 1.700018914032765e-05, + "loss": 1.4188, + "step": 3126 + }, + { + "epoch": 0.33, + "learning_rate": 1.699757479791819e-05, + "loss": 1.3884, + "step": 3127 + }, + { + "epoch": 0.33, + "learning_rate": 1.6994959518013502e-05, + "loss": 1.4111, + "step": 3128 + }, + { + "epoch": 0.33, + "learning_rate": 1.6992343300963963e-05, + "loss": 1.5452, + "step": 3129 + }, + { + "epoch": 0.33, + "learning_rate": 1.6989726147120087e-05, + "loss": 1.4097, + "step": 3130 + }, + { + "epoch": 0.33, + "learning_rate": 1.6987108056832506e-05, + "loss": 1.481, + "step": 3131 + }, + { + "epoch": 0.33, + "learning_rate": 1.6984489030451973e-05, + "loss": 1.4505, + "step": 3132 + }, + { + "epoch": 0.33, + "learning_rate": 1.6981869068329368e-05, + "loss": 1.4281, + "step": 3133 + }, + { + "epoch": 0.33, + "learning_rate": 1.69792481708157e-05, + "loss": 1.4555, + "step": 3134 + }, + { + "epoch": 0.33, + "learning_rate": 1.6976626338262103e-05, + "loss": 1.4525, + "step": 3135 + }, + { + "epoch": 0.33, + "learning_rate": 1.6974003571019837e-05, + "loss": 1.3765, + "step": 3136 + }, + { + "epoch": 0.33, + "learning_rate": 1.6971379869440286e-05, + "loss": 1.3998, + "step": 3137 + }, + { + "epoch": 0.33, + "learning_rate": 1.696875523387495e-05, + "loss": 1.5103, + "step": 3138 + }, + { + "epoch": 0.33, + "learning_rate": 1.6966129664675474e-05, + "loss": 1.427, + "step": 3139 + }, + { + "epoch": 0.33, + "learning_rate": 1.6963503162193612e-05, + "loss": 1.4362, + "step": 3140 + }, + { + "epoch": 0.33, + "learning_rate": 1.6960875726781246e-05, + "loss": 1.4073, + "step": 3141 + }, + { + "epoch": 0.33, + "learning_rate": 1.6958247358790388e-05, + "loss": 1.4014, + "step": 3142 + }, + { + "epoch": 0.33, + "learning_rate": 1.6955618058573165e-05, + "loss": 1.4244, + "step": 3143 + }, + { + "epoch": 0.33, + "learning_rate": 1.6952987826481847e-05, + "loss": 1.47, + "step": 3144 + }, + { + "epoch": 0.33, + "learning_rate": 1.6950356662868814e-05, + "loss": 1.5112, + "step": 3145 + }, + { + "epoch": 0.33, + "learning_rate": 1.6947724568086562e-05, + "loss": 1.3398, + "step": 3146 + }, + { + "epoch": 0.33, + "learning_rate": 1.694509154248774e-05, + "loss": 1.4584, + "step": 3147 + }, + { + "epoch": 0.33, + "learning_rate": 1.69424575864251e-05, + "loss": 1.4383, + "step": 3148 + }, + { + "epoch": 0.33, + "learning_rate": 1.6939822700251523e-05, + "loss": 1.3869, + "step": 3149 + }, + { + "epoch": 0.33, + "learning_rate": 1.6937186884320015e-05, + "loss": 1.4453, + "step": 3150 + }, + { + "epoch": 0.33, + "learning_rate": 1.6934550138983713e-05, + "loss": 1.3355, + "step": 3151 + }, + { + "epoch": 0.33, + "learning_rate": 1.6931912464595866e-05, + "loss": 1.5573, + "step": 3152 + }, + { + "epoch": 0.33, + "learning_rate": 1.6929273861509865e-05, + "loss": 1.439, + "step": 3153 + }, + { + "epoch": 0.33, + "learning_rate": 1.6926634330079203e-05, + "loss": 1.6079, + "step": 3154 + }, + { + "epoch": 0.33, + "learning_rate": 1.692399387065752e-05, + "loss": 1.6973, + "step": 3155 + }, + { + "epoch": 0.33, + "learning_rate": 1.692135248359856e-05, + "loss": 1.3769, + "step": 3156 + }, + { + "epoch": 0.33, + "learning_rate": 1.6918710169256206e-05, + "loss": 1.4454, + "step": 3157 + }, + { + "epoch": 0.33, + "learning_rate": 1.691606692798446e-05, + "loss": 1.4495, + "step": 3158 + }, + { + "epoch": 0.33, + "learning_rate": 1.691342276013745e-05, + "loss": 1.4292, + "step": 3159 + }, + { + "epoch": 0.33, + "learning_rate": 1.691077766606942e-05, + "loss": 1.4405, + "step": 3160 + }, + { + "epoch": 0.33, + "learning_rate": 1.6908131646134757e-05, + "loss": 1.3683, + "step": 3161 + }, + { + "epoch": 0.33, + "learning_rate": 1.690548470068795e-05, + "loss": 1.4731, + "step": 3162 + }, + { + "epoch": 0.33, + "learning_rate": 1.690283683008362e-05, + "loss": 1.4323, + "step": 3163 + }, + { + "epoch": 0.33, + "learning_rate": 1.6900188034676518e-05, + "loss": 1.5133, + "step": 3164 + }, + { + "epoch": 0.33, + "learning_rate": 1.6897538314821516e-05, + "loss": 1.5529, + "step": 3165 + }, + { + "epoch": 0.33, + "learning_rate": 1.6894887670873605e-05, + "loss": 1.4427, + "step": 3166 + }, + { + "epoch": 0.33, + "learning_rate": 1.6892236103187904e-05, + "loss": 1.4344, + "step": 3167 + }, + { + "epoch": 0.33, + "learning_rate": 1.6889583612119657e-05, + "loss": 1.4291, + "step": 3168 + }, + { + "epoch": 0.33, + "learning_rate": 1.6886930198024226e-05, + "loss": 1.4683, + "step": 3169 + }, + { + "epoch": 0.33, + "learning_rate": 1.6884275861257106e-05, + "loss": 1.4442, + "step": 3170 + }, + { + "epoch": 0.33, + "learning_rate": 1.6881620602173905e-05, + "loss": 1.4509, + "step": 3171 + }, + { + "epoch": 0.33, + "learning_rate": 1.6878964421130362e-05, + "loss": 1.5113, + "step": 3172 + }, + { + "epoch": 0.33, + "learning_rate": 1.6876307318482334e-05, + "loss": 1.4261, + "step": 3173 + }, + { + "epoch": 0.33, + "learning_rate": 1.6873649294585805e-05, + "loss": 1.445, + "step": 3174 + }, + { + "epoch": 0.33, + "learning_rate": 1.6870990349796886e-05, + "loss": 1.4603, + "step": 3175 + }, + { + "epoch": 0.33, + "learning_rate": 1.68683304844718e-05, + "loss": 1.41, + "step": 3176 + }, + { + "epoch": 0.33, + "learning_rate": 1.686566969896691e-05, + "loss": 1.4018, + "step": 3177 + }, + { + "epoch": 0.33, + "learning_rate": 1.6863007993638687e-05, + "loss": 1.422, + "step": 3178 + }, + { + "epoch": 0.33, + "learning_rate": 1.6860345368843727e-05, + "loss": 1.4412, + "step": 3179 + }, + { + "epoch": 0.33, + "learning_rate": 1.6857681824938768e-05, + "loss": 1.5411, + "step": 3180 + }, + { + "epoch": 0.33, + "learning_rate": 1.685501736228064e-05, + "loss": 1.4416, + "step": 3181 + }, + { + "epoch": 0.33, + "learning_rate": 1.685235198122632e-05, + "loss": 1.5113, + "step": 3182 + }, + { + "epoch": 0.33, + "learning_rate": 1.6849685682132903e-05, + "loss": 1.423, + "step": 3183 + }, + { + "epoch": 0.33, + "learning_rate": 1.68470184653576e-05, + "loss": 1.404, + "step": 3184 + }, + { + "epoch": 0.33, + "eval_loss": 1.4771089553833008, + "eval_runtime": 77.4034, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3184 + }, + { + "epoch": 0.33, + "learning_rate": 1.6844350331257747e-05, + "loss": 1.4624, + "step": 3185 + }, + { + "epoch": 0.33, + "learning_rate": 1.6841681280190814e-05, + "loss": 1.4306, + "step": 3186 + }, + { + "epoch": 0.33, + "learning_rate": 1.683901131251438e-05, + "loss": 1.42, + "step": 3187 + }, + { + "epoch": 0.33, + "learning_rate": 1.6836340428586155e-05, + "loss": 1.4787, + "step": 3188 + }, + { + "epoch": 0.33, + "learning_rate": 1.6833668628763965e-05, + "loss": 1.3485, + "step": 3189 + }, + { + "epoch": 0.33, + "learning_rate": 1.683099591340576e-05, + "loss": 1.3674, + "step": 3190 + }, + { + "epoch": 0.33, + "learning_rate": 1.6828322282869627e-05, + "loss": 1.5187, + "step": 3191 + }, + { + "epoch": 0.33, + "learning_rate": 1.682564773751375e-05, + "loss": 1.4847, + "step": 3192 + }, + { + "epoch": 0.33, + "learning_rate": 1.682297227769646e-05, + "loss": 1.4815, + "step": 3193 + }, + { + "epoch": 0.33, + "learning_rate": 1.682029590377619e-05, + "loss": 1.4281, + "step": 3194 + }, + { + "epoch": 0.34, + "learning_rate": 1.6817618616111517e-05, + "loss": 1.4734, + "step": 3195 + }, + { + "epoch": 0.34, + "learning_rate": 1.681494041506112e-05, + "loss": 1.4861, + "step": 3196 + }, + { + "epoch": 0.34, + "learning_rate": 1.6812261300983808e-05, + "loss": 1.4372, + "step": 3197 + }, + { + "epoch": 0.34, + "learning_rate": 1.680958127423852e-05, + "loss": 1.4396, + "step": 3198 + }, + { + "epoch": 0.34, + "learning_rate": 1.680690033518431e-05, + "loss": 1.4225, + "step": 3199 + }, + { + "epoch": 0.34, + "learning_rate": 1.6804218484180347e-05, + "loss": 1.4925, + "step": 3200 + }, + { + "epoch": 0.34, + "learning_rate": 1.6801535721585942e-05, + "loss": 1.4306, + "step": 3201 + }, + { + "epoch": 0.34, + "learning_rate": 1.6798852047760506e-05, + "loss": 1.4298, + "step": 3202 + }, + { + "epoch": 0.34, + "learning_rate": 1.6796167463063588e-05, + "loss": 1.4725, + "step": 3203 + }, + { + "epoch": 0.34, + "learning_rate": 1.679348196785485e-05, + "loss": 1.4648, + "step": 3204 + }, + { + "epoch": 0.34, + "learning_rate": 1.6790795562494087e-05, + "loss": 1.4152, + "step": 3205 + }, + { + "epoch": 0.34, + "learning_rate": 1.6788108247341198e-05, + "loss": 1.4637, + "step": 3206 + }, + { + "epoch": 0.34, + "learning_rate": 1.6785420022756216e-05, + "loss": 1.4077, + "step": 3207 + }, + { + "epoch": 0.34, + "learning_rate": 1.67827308890993e-05, + "loss": 1.4585, + "step": 3208 + }, + { + "epoch": 0.34, + "learning_rate": 1.678004084673072e-05, + "loss": 1.3747, + "step": 3209 + }, + { + "epoch": 0.34, + "learning_rate": 1.6777349896010876e-05, + "loss": 1.4264, + "step": 3210 + }, + { + "epoch": 0.34, + "learning_rate": 1.677465803730028e-05, + "loss": 1.4178, + "step": 3211 + }, + { + "epoch": 0.34, + "learning_rate": 1.6771965270959584e-05, + "loss": 1.3876, + "step": 3212 + }, + { + "epoch": 0.34, + "learning_rate": 1.6769271597349538e-05, + "loss": 1.4658, + "step": 3213 + }, + { + "epoch": 0.34, + "learning_rate": 1.6766577016831026e-05, + "loss": 1.3968, + "step": 3214 + }, + { + "epoch": 0.34, + "learning_rate": 1.676388152976506e-05, + "loss": 1.5015, + "step": 3215 + }, + { + "epoch": 0.34, + "learning_rate": 1.6761185136512756e-05, + "loss": 1.4121, + "step": 3216 + }, + { + "epoch": 0.34, + "learning_rate": 1.675848783743537e-05, + "loss": 1.4146, + "step": 3217 + }, + { + "epoch": 0.34, + "learning_rate": 1.675578963289427e-05, + "loss": 1.4113, + "step": 3218 + }, + { + "epoch": 0.34, + "learning_rate": 1.6753090523250937e-05, + "loss": 1.4048, + "step": 3219 + }, + { + "epoch": 0.34, + "learning_rate": 1.6750390508866994e-05, + "loss": 1.4959, + "step": 3220 + }, + { + "epoch": 0.34, + "learning_rate": 1.6747689590104167e-05, + "loss": 1.4445, + "step": 3221 + }, + { + "epoch": 0.34, + "learning_rate": 1.6744987767324312e-05, + "loss": 1.4611, + "step": 3222 + }, + { + "epoch": 0.34, + "learning_rate": 1.67422850408894e-05, + "loss": 1.4141, + "step": 3223 + }, + { + "epoch": 0.34, + "learning_rate": 1.6739581411161535e-05, + "loss": 1.4218, + "step": 3224 + }, + { + "epoch": 0.34, + "learning_rate": 1.6736876878502925e-05, + "loss": 1.4266, + "step": 3225 + }, + { + "epoch": 0.34, + "learning_rate": 1.6734171443275913e-05, + "loss": 1.4941, + "step": 3226 + }, + { + "epoch": 0.34, + "learning_rate": 1.6731465105842955e-05, + "loss": 1.4294, + "step": 3227 + }, + { + "epoch": 0.34, + "learning_rate": 1.6728757866566635e-05, + "loss": 1.4189, + "step": 3228 + }, + { + "epoch": 0.34, + "learning_rate": 1.6726049725809647e-05, + "loss": 1.4713, + "step": 3229 + }, + { + "epoch": 0.34, + "learning_rate": 1.6723340683934818e-05, + "loss": 1.4203, + "step": 3230 + }, + { + "epoch": 0.34, + "learning_rate": 1.6720630741305088e-05, + "loss": 1.4112, + "step": 3231 + }, + { + "epoch": 0.34, + "learning_rate": 1.6717919898283523e-05, + "loss": 1.3811, + "step": 3232 + }, + { + "epoch": 0.34, + "learning_rate": 1.6715208155233296e-05, + "loss": 1.4242, + "step": 3233 + }, + { + "epoch": 0.34, + "learning_rate": 1.6712495512517725e-05, + "loss": 1.4207, + "step": 3234 + }, + { + "epoch": 0.34, + "learning_rate": 1.6709781970500222e-05, + "loss": 1.4888, + "step": 3235 + }, + { + "epoch": 0.34, + "learning_rate": 1.670706752954434e-05, + "loss": 1.4501, + "step": 3236 + }, + { + "epoch": 0.34, + "learning_rate": 1.670435219001374e-05, + "loss": 1.4367, + "step": 3237 + }, + { + "epoch": 0.34, + "learning_rate": 1.6701635952272212e-05, + "loss": 1.3959, + "step": 3238 + }, + { + "epoch": 0.34, + "learning_rate": 1.6698918816683655e-05, + "loss": 1.4257, + "step": 3239 + }, + { + "epoch": 0.34, + "learning_rate": 1.6696200783612102e-05, + "loss": 1.4718, + "step": 3240 + }, + { + "epoch": 0.34, + "learning_rate": 1.6693481853421697e-05, + "loss": 1.5899, + "step": 3241 + }, + { + "epoch": 0.34, + "learning_rate": 1.6690762026476707e-05, + "loss": 1.418, + "step": 3242 + }, + { + "epoch": 0.34, + "learning_rate": 1.668804130314152e-05, + "loss": 1.4076, + "step": 3243 + }, + { + "epoch": 0.34, + "learning_rate": 1.6685319683780645e-05, + "loss": 1.4571, + "step": 3244 + }, + { + "epoch": 0.34, + "learning_rate": 1.66825971687587e-05, + "loss": 1.4066, + "step": 3245 + }, + { + "epoch": 0.34, + "learning_rate": 1.6679873758440442e-05, + "loss": 1.4639, + "step": 3246 + }, + { + "epoch": 0.34, + "learning_rate": 1.6677149453190732e-05, + "loss": 1.453, + "step": 3247 + }, + { + "epoch": 0.34, + "learning_rate": 1.6674424253374558e-05, + "loss": 1.4262, + "step": 3248 + }, + { + "epoch": 0.34, + "learning_rate": 1.667169815935703e-05, + "loss": 1.3687, + "step": 3249 + }, + { + "epoch": 0.34, + "learning_rate": 1.6668971171503372e-05, + "loss": 1.5557, + "step": 3250 + }, + { + "epoch": 0.34, + "learning_rate": 1.6666243290178933e-05, + "loss": 1.4639, + "step": 3251 + }, + { + "epoch": 0.34, + "learning_rate": 1.6663514515749172e-05, + "loss": 1.4334, + "step": 3252 + }, + { + "epoch": 0.34, + "learning_rate": 1.6660784848579685e-05, + "loss": 1.3523, + "step": 3253 + }, + { + "epoch": 0.34, + "learning_rate": 1.6658054289036166e-05, + "loss": 1.3738, + "step": 3254 + }, + { + "epoch": 0.34, + "learning_rate": 1.665532283748445e-05, + "loss": 1.4159, + "step": 3255 + }, + { + "epoch": 0.34, + "learning_rate": 1.6652590494290474e-05, + "loss": 1.3609, + "step": 3256 + }, + { + "epoch": 0.34, + "learning_rate": 1.6649857259820303e-05, + "loss": 1.4449, + "step": 3257 + }, + { + "epoch": 0.34, + "learning_rate": 1.6647123134440126e-05, + "loss": 1.424, + "step": 3258 + }, + { + "epoch": 0.34, + "learning_rate": 1.664438811851624e-05, + "loss": 1.4737, + "step": 3259 + }, + { + "epoch": 0.34, + "learning_rate": 1.6641652212415066e-05, + "loss": 1.2717, + "step": 3260 + }, + { + "epoch": 0.34, + "learning_rate": 1.663891541650315e-05, + "loss": 1.4845, + "step": 3261 + }, + { + "epoch": 0.34, + "learning_rate": 1.663617773114715e-05, + "loss": 1.4115, + "step": 3262 + }, + { + "epoch": 0.34, + "learning_rate": 1.663343915671384e-05, + "loss": 1.4237, + "step": 3263 + }, + { + "epoch": 0.34, + "learning_rate": 1.6630699693570127e-05, + "loss": 1.4209, + "step": 3264 + }, + { + "epoch": 0.34, + "learning_rate": 1.6627959342083026e-05, + "loss": 1.506, + "step": 3265 + }, + { + "epoch": 0.34, + "learning_rate": 1.6625218102619672e-05, + "loss": 1.4466, + "step": 3266 + }, + { + "epoch": 0.34, + "learning_rate": 1.6622475975547324e-05, + "loss": 1.4129, + "step": 3267 + }, + { + "epoch": 0.34, + "learning_rate": 1.661973296123335e-05, + "loss": 1.4152, + "step": 3268 + }, + { + "epoch": 0.34, + "learning_rate": 1.661698906004525e-05, + "loss": 1.43, + "step": 3269 + }, + { + "epoch": 0.34, + "learning_rate": 1.661424427235064e-05, + "loss": 1.4701, + "step": 3270 + }, + { + "epoch": 0.34, + "learning_rate": 1.6611498598517238e-05, + "loss": 1.4598, + "step": 3271 + }, + { + "epoch": 0.34, + "learning_rate": 1.66087520389129e-05, + "loss": 1.4795, + "step": 3272 + }, + { + "epoch": 0.34, + "learning_rate": 1.6606004593905595e-05, + "loss": 1.5264, + "step": 3273 + }, + { + "epoch": 0.34, + "learning_rate": 1.6603256263863415e-05, + "loss": 1.4412, + "step": 3274 + }, + { + "epoch": 0.34, + "learning_rate": 1.6600507049154556e-05, + "loss": 1.45, + "step": 3275 + }, + { + "epoch": 0.34, + "learning_rate": 1.659775695014735e-05, + "loss": 1.4985, + "step": 3276 + }, + { + "epoch": 0.34, + "learning_rate": 1.659500596721024e-05, + "loss": 1.496, + "step": 3277 + }, + { + "epoch": 0.34, + "learning_rate": 1.6592254100711775e-05, + "loss": 1.4386, + "step": 3278 + }, + { + "epoch": 0.34, + "learning_rate": 1.658950135102065e-05, + "loss": 1.4073, + "step": 3279 + }, + { + "epoch": 0.34, + "learning_rate": 1.658674771850565e-05, + "loss": 1.3912, + "step": 3280 + }, + { + "epoch": 0.34, + "learning_rate": 1.6583993203535702e-05, + "loss": 1.3628, + "step": 3281 + }, + { + "epoch": 0.34, + "learning_rate": 1.658123780647983e-05, + "loss": 1.6089, + "step": 3282 + }, + { + "epoch": 0.34, + "learning_rate": 1.6578481527707196e-05, + "loss": 1.2367, + "step": 3283 + }, + { + "epoch": 0.34, + "learning_rate": 1.657572436758706e-05, + "loss": 1.4058, + "step": 3284 + }, + { + "epoch": 0.34, + "learning_rate": 1.6572966326488825e-05, + "loss": 1.4067, + "step": 3285 + }, + { + "epoch": 0.34, + "learning_rate": 1.657020740478198e-05, + "loss": 1.4187, + "step": 3286 + }, + { + "epoch": 0.34, + "learning_rate": 1.6567447602836166e-05, + "loss": 1.4599, + "step": 3287 + }, + { + "epoch": 0.34, + "learning_rate": 1.6564686921021115e-05, + "loss": 1.432, + "step": 3288 + }, + { + "epoch": 0.34, + "learning_rate": 1.6561925359706693e-05, + "loss": 1.3941, + "step": 3289 + }, + { + "epoch": 0.35, + "learning_rate": 1.6559162919262874e-05, + "loss": 1.3644, + "step": 3290 + }, + { + "epoch": 0.35, + "learning_rate": 1.6556399600059756e-05, + "loss": 1.4628, + "step": 3291 + }, + { + "epoch": 0.35, + "learning_rate": 1.6553635402467555e-05, + "loss": 1.4355, + "step": 3292 + }, + { + "epoch": 0.35, + "learning_rate": 1.6550870326856596e-05, + "loss": 1.4627, + "step": 3293 + }, + { + "epoch": 0.35, + "learning_rate": 1.6548104373597335e-05, + "loss": 1.442, + "step": 3294 + }, + { + "epoch": 0.35, + "learning_rate": 1.6545337543060338e-05, + "loss": 1.3991, + "step": 3295 + }, + { + "epoch": 0.35, + "learning_rate": 1.6542569835616283e-05, + "loss": 1.4193, + "step": 3296 + }, + { + "epoch": 0.35, + "learning_rate": 1.6539801251635982e-05, + "loss": 1.4792, + "step": 3297 + }, + { + "epoch": 0.35, + "learning_rate": 1.653703179149034e-05, + "loss": 1.4735, + "step": 3298 + }, + { + "epoch": 0.35, + "learning_rate": 1.6534261455550408e-05, + "loss": 1.451, + "step": 3299 + }, + { + "epoch": 0.35, + "learning_rate": 1.653149024418733e-05, + "loss": 1.3975, + "step": 3300 + }, + { + "epoch": 0.35, + "learning_rate": 1.652871815777238e-05, + "loss": 1.4843, + "step": 3301 + }, + { + "epoch": 0.35, + "learning_rate": 1.6525945196676948e-05, + "loss": 1.4782, + "step": 3302 + }, + { + "epoch": 0.35, + "learning_rate": 1.652317136127254e-05, + "loss": 1.3865, + "step": 3303 + }, + { + "epoch": 0.35, + "learning_rate": 1.6520396651930777e-05, + "loss": 1.4359, + "step": 3304 + }, + { + "epoch": 0.35, + "learning_rate": 1.6517621069023397e-05, + "loss": 1.4289, + "step": 3305 + }, + { + "epoch": 0.35, + "learning_rate": 1.651484461292226e-05, + "loss": 1.3526, + "step": 3306 + }, + { + "epoch": 0.35, + "learning_rate": 1.6512067283999336e-05, + "loss": 1.3671, + "step": 3307 + }, + { + "epoch": 0.35, + "learning_rate": 1.650928908262672e-05, + "loss": 1.6041, + "step": 3308 + }, + { + "epoch": 0.35, + "learning_rate": 1.650651000917662e-05, + "loss": 1.4322, + "step": 3309 + }, + { + "epoch": 0.35, + "learning_rate": 1.6503730064021354e-05, + "loss": 1.3992, + "step": 3310 + }, + { + "epoch": 0.35, + "learning_rate": 1.650094924753337e-05, + "loss": 1.4928, + "step": 3311 + }, + { + "epoch": 0.35, + "learning_rate": 1.6498167560085222e-05, + "loss": 1.4075, + "step": 3312 + }, + { + "epoch": 0.35, + "learning_rate": 1.6495385002049583e-05, + "loss": 1.4535, + "step": 3313 + }, + { + "epoch": 0.35, + "learning_rate": 1.6492601573799253e-05, + "loss": 1.4221, + "step": 3314 + }, + { + "epoch": 0.35, + "learning_rate": 1.6489817275707133e-05, + "loss": 1.3688, + "step": 3315 + }, + { + "epoch": 0.35, + "learning_rate": 1.6487032108146243e-05, + "loss": 1.3889, + "step": 3316 + }, + { + "epoch": 0.35, + "learning_rate": 1.6484246071489733e-05, + "loss": 1.3942, + "step": 3317 + }, + { + "epoch": 0.35, + "learning_rate": 1.6481459166110858e-05, + "loss": 1.4004, + "step": 3318 + }, + { + "epoch": 0.35, + "learning_rate": 1.647867139238299e-05, + "loss": 1.7308, + "step": 3319 + }, + { + "epoch": 0.35, + "learning_rate": 1.6475882750679622e-05, + "loss": 1.5001, + "step": 3320 + }, + { + "epoch": 0.35, + "learning_rate": 1.647309324137435e-05, + "loss": 1.4325, + "step": 3321 + }, + { + "epoch": 0.35, + "learning_rate": 1.6470302864840913e-05, + "loss": 1.4494, + "step": 3322 + }, + { + "epoch": 0.35, + "learning_rate": 1.6467511621453136e-05, + "loss": 1.4418, + "step": 3323 + }, + { + "epoch": 0.35, + "learning_rate": 1.646471951158498e-05, + "loss": 1.4046, + "step": 3324 + }, + { + "epoch": 0.35, + "learning_rate": 1.6461926535610517e-05, + "loss": 1.5031, + "step": 3325 + }, + { + "epoch": 0.35, + "learning_rate": 1.645913269390393e-05, + "loss": 1.4813, + "step": 3326 + }, + { + "epoch": 0.35, + "learning_rate": 1.6456337986839525e-05, + "loss": 1.3842, + "step": 3327 + }, + { + "epoch": 0.35, + "learning_rate": 1.645354241479172e-05, + "loss": 1.4539, + "step": 3328 + }, + { + "epoch": 0.35, + "learning_rate": 1.6450745978135048e-05, + "loss": 1.4503, + "step": 3329 + }, + { + "epoch": 0.35, + "learning_rate": 1.6447948677244163e-05, + "loss": 1.3741, + "step": 3330 + }, + { + "epoch": 0.35, + "learning_rate": 1.6445150512493832e-05, + "loss": 1.425, + "step": 3331 + }, + { + "epoch": 0.35, + "learning_rate": 1.644235148425893e-05, + "loss": 1.4277, + "step": 3332 + }, + { + "epoch": 0.35, + "learning_rate": 1.6439551592914464e-05, + "loss": 1.4918, + "step": 3333 + }, + { + "epoch": 0.35, + "learning_rate": 1.6436750838835543e-05, + "loss": 1.3364, + "step": 3334 + }, + { + "epoch": 0.35, + "learning_rate": 1.6433949222397397e-05, + "loss": 1.4741, + "step": 3335 + }, + { + "epoch": 0.35, + "learning_rate": 1.643114674397537e-05, + "loss": 1.3867, + "step": 3336 + }, + { + "epoch": 0.35, + "learning_rate": 1.642834340394492e-05, + "loss": 1.3817, + "step": 3337 + }, + { + "epoch": 0.35, + "learning_rate": 1.6425539202681625e-05, + "loss": 1.4308, + "step": 3338 + }, + { + "epoch": 0.35, + "learning_rate": 1.6422734140561178e-05, + "loss": 1.4401, + "step": 3339 + }, + { + "epoch": 0.35, + "learning_rate": 1.641992821795938e-05, + "loss": 1.4338, + "step": 3340 + }, + { + "epoch": 0.35, + "learning_rate": 1.641712143525216e-05, + "loss": 1.3804, + "step": 3341 + }, + { + "epoch": 0.35, + "learning_rate": 1.6414313792815546e-05, + "loss": 1.371, + "step": 3342 + }, + { + "epoch": 0.35, + "learning_rate": 1.6411505291025695e-05, + "loss": 1.4102, + "step": 3343 + }, + { + "epoch": 0.35, + "learning_rate": 1.6408695930258875e-05, + "loss": 1.4433, + "step": 3344 + }, + { + "epoch": 0.35, + "learning_rate": 1.6405885710891467e-05, + "loss": 1.3895, + "step": 3345 + }, + { + "epoch": 0.35, + "learning_rate": 1.6403074633299966e-05, + "loss": 1.4321, + "step": 3346 + }, + { + "epoch": 0.35, + "learning_rate": 1.640026269786098e-05, + "loss": 1.4207, + "step": 3347 + }, + { + "epoch": 0.35, + "learning_rate": 1.639744990495125e-05, + "loss": 1.3758, + "step": 3348 + }, + { + "epoch": 0.35, + "learning_rate": 1.6394636254947612e-05, + "loss": 1.4203, + "step": 3349 + }, + { + "epoch": 0.35, + "learning_rate": 1.6391821748227013e-05, + "loss": 1.4596, + "step": 3350 + }, + { + "epoch": 0.35, + "learning_rate": 1.6389006385166537e-05, + "loss": 1.4344, + "step": 3351 + }, + { + "epoch": 0.35, + "learning_rate": 1.6386190166143366e-05, + "loss": 1.4048, + "step": 3352 + }, + { + "epoch": 0.35, + "learning_rate": 1.6383373091534798e-05, + "loss": 1.4348, + "step": 3353 + }, + { + "epoch": 0.35, + "learning_rate": 1.638055516171825e-05, + "loss": 1.4972, + "step": 3354 + }, + { + "epoch": 0.35, + "learning_rate": 1.6377736377071258e-05, + "loss": 1.4685, + "step": 3355 + }, + { + "epoch": 0.35, + "learning_rate": 1.637491673797146e-05, + "loss": 1.4093, + "step": 3356 + }, + { + "epoch": 0.35, + "learning_rate": 1.6372096244796616e-05, + "loss": 1.4452, + "step": 3357 + }, + { + "epoch": 0.35, + "learning_rate": 1.63692748979246e-05, + "loss": 1.4458, + "step": 3358 + }, + { + "epoch": 0.35, + "learning_rate": 1.6366452697733404e-05, + "loss": 1.4187, + "step": 3359 + }, + { + "epoch": 0.35, + "learning_rate": 1.6363629644601126e-05, + "loss": 1.4052, + "step": 3360 + }, + { + "epoch": 0.35, + "learning_rate": 1.6360805738905984e-05, + "loss": 1.439, + "step": 3361 + }, + { + "epoch": 0.35, + "learning_rate": 1.635798098102631e-05, + "loss": 1.4131, + "step": 3362 + }, + { + "epoch": 0.35, + "learning_rate": 1.6355155371340544e-05, + "loss": 1.4391, + "step": 3363 + }, + { + "epoch": 0.35, + "learning_rate": 1.6352328910227252e-05, + "loss": 1.4318, + "step": 3364 + }, + { + "epoch": 0.35, + "learning_rate": 1.63495015980651e-05, + "loss": 1.5112, + "step": 3365 + }, + { + "epoch": 0.35, + "learning_rate": 1.6346673435232884e-05, + "loss": 1.4688, + "step": 3366 + }, + { + "epoch": 0.35, + "learning_rate": 1.6343844422109496e-05, + "loss": 1.3807, + "step": 3367 + }, + { + "epoch": 0.35, + "learning_rate": 1.634101455907396e-05, + "loss": 1.4083, + "step": 3368 + }, + { + "epoch": 0.35, + "learning_rate": 1.6338183846505394e-05, + "loss": 1.3566, + "step": 3369 + }, + { + "epoch": 0.35, + "learning_rate": 1.633535228478305e-05, + "loss": 1.4287, + "step": 3370 + }, + { + "epoch": 0.35, + "learning_rate": 1.6332519874286285e-05, + "loss": 1.3494, + "step": 3371 + }, + { + "epoch": 0.35, + "learning_rate": 1.6329686615394558e-05, + "loss": 1.3813, + "step": 3372 + }, + { + "epoch": 0.35, + "learning_rate": 1.6326852508487468e-05, + "loss": 1.4241, + "step": 3373 + }, + { + "epoch": 0.35, + "learning_rate": 1.63240175539447e-05, + "loss": 1.424, + "step": 3374 + }, + { + "epoch": 0.35, + "learning_rate": 1.632118175214607e-05, + "loss": 1.4212, + "step": 3375 + }, + { + "epoch": 0.35, + "learning_rate": 1.6318345103471504e-05, + "loss": 1.4671, + "step": 3376 + }, + { + "epoch": 0.35, + "learning_rate": 1.6315507608301044e-05, + "loss": 1.4593, + "step": 3377 + }, + { + "epoch": 0.35, + "learning_rate": 1.631266926701483e-05, + "loss": 1.7816, + "step": 3378 + }, + { + "epoch": 0.35, + "learning_rate": 1.6309830079993134e-05, + "loss": 1.5134, + "step": 3379 + }, + { + "epoch": 0.35, + "learning_rate": 1.6306990047616334e-05, + "loss": 0.8933, + "step": 3380 + }, + { + "epoch": 0.35, + "learning_rate": 1.630414917026492e-05, + "loss": 1.1033, + "step": 3381 + }, + { + "epoch": 0.35, + "learning_rate": 1.6301307448319497e-05, + "loss": 1.3494, + "step": 3382 + }, + { + "epoch": 0.35, + "learning_rate": 1.6298464882160784e-05, + "loss": 1.4299, + "step": 3383 + }, + { + "epoch": 0.35, + "eval_loss": 1.482450008392334, + "eval_runtime": 77.3737, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3383 + }, + { + "epoch": 0.35, + "learning_rate": 1.629562147216961e-05, + "loss": 1.3971, + "step": 3384 + }, + { + "epoch": 0.35, + "learning_rate": 1.6292777218726917e-05, + "loss": 1.3706, + "step": 3385 + }, + { + "epoch": 0.36, + "learning_rate": 1.6289932122213765e-05, + "loss": 1.4524, + "step": 3386 + }, + { + "epoch": 0.36, + "learning_rate": 1.6287086183011328e-05, + "loss": 1.4595, + "step": 3387 + }, + { + "epoch": 0.36, + "learning_rate": 1.628423940150088e-05, + "loss": 1.492, + "step": 3388 + }, + { + "epoch": 0.36, + "learning_rate": 1.628139177806382e-05, + "loss": 1.5576, + "step": 3389 + }, + { + "epoch": 0.36, + "learning_rate": 1.6278543313081657e-05, + "loss": 1.4615, + "step": 3390 + }, + { + "epoch": 0.36, + "learning_rate": 1.6275694006936015e-05, + "loss": 1.3456, + "step": 3391 + }, + { + "epoch": 0.36, + "learning_rate": 1.627284386000862e-05, + "loss": 1.4254, + "step": 3392 + }, + { + "epoch": 0.36, + "learning_rate": 1.6269992872681325e-05, + "loss": 1.433, + "step": 3393 + }, + { + "epoch": 0.36, + "learning_rate": 1.626714104533609e-05, + "loss": 1.5291, + "step": 3394 + }, + { + "epoch": 0.36, + "learning_rate": 1.626428837835498e-05, + "loss": 1.4502, + "step": 3395 + }, + { + "epoch": 0.36, + "learning_rate": 1.626143487212019e-05, + "loss": 1.3756, + "step": 3396 + }, + { + "epoch": 0.36, + "learning_rate": 1.6258580527014002e-05, + "loss": 1.414, + "step": 3397 + }, + { + "epoch": 0.36, + "learning_rate": 1.6255725343418835e-05, + "loss": 1.6289, + "step": 3398 + }, + { + "epoch": 0.36, + "learning_rate": 1.6252869321717208e-05, + "loss": 1.4862, + "step": 3399 + }, + { + "epoch": 0.36, + "learning_rate": 1.6250012462291756e-05, + "loss": 1.4213, + "step": 3400 + }, + { + "epoch": 0.36, + "learning_rate": 1.6247154765525217e-05, + "loss": 1.524, + "step": 3401 + }, + { + "epoch": 0.36, + "learning_rate": 1.624429623180046e-05, + "loss": 1.6013, + "step": 3402 + }, + { + "epoch": 0.36, + "learning_rate": 1.624143686150045e-05, + "loss": 1.4557, + "step": 3403 + }, + { + "epoch": 0.36, + "learning_rate": 1.6238576655008266e-05, + "loss": 1.3831, + "step": 3404 + }, + { + "epoch": 0.36, + "learning_rate": 1.6235715612707105e-05, + "loss": 1.4008, + "step": 3405 + }, + { + "epoch": 0.36, + "learning_rate": 1.623285373498028e-05, + "loss": 1.4848, + "step": 3406 + }, + { + "epoch": 0.36, + "learning_rate": 1.6229991022211197e-05, + "loss": 1.4459, + "step": 3407 + }, + { + "epoch": 0.36, + "learning_rate": 1.6227127474783393e-05, + "loss": 1.4334, + "step": 3408 + }, + { + "epoch": 0.36, + "learning_rate": 1.6224263093080507e-05, + "loss": 1.4123, + "step": 3409 + }, + { + "epoch": 0.36, + "learning_rate": 1.6221397877486294e-05, + "loss": 1.3691, + "step": 3410 + }, + { + "epoch": 0.36, + "learning_rate": 1.6218531828384618e-05, + "loss": 1.4128, + "step": 3411 + }, + { + "epoch": 0.36, + "learning_rate": 1.6215664946159457e-05, + "loss": 1.3642, + "step": 3412 + }, + { + "epoch": 0.36, + "learning_rate": 1.6212797231194902e-05, + "loss": 1.4311, + "step": 3413 + }, + { + "epoch": 0.36, + "learning_rate": 1.6209928683875152e-05, + "loss": 1.4695, + "step": 3414 + }, + { + "epoch": 0.36, + "learning_rate": 1.6207059304584514e-05, + "loss": 1.3871, + "step": 3415 + }, + { + "epoch": 0.36, + "learning_rate": 1.6204189093707414e-05, + "loss": 1.4219, + "step": 3416 + }, + { + "epoch": 0.36, + "learning_rate": 1.620131805162839e-05, + "loss": 1.6199, + "step": 3417 + }, + { + "epoch": 0.36, + "learning_rate": 1.619844617873208e-05, + "loss": 1.4433, + "step": 3418 + }, + { + "epoch": 0.36, + "learning_rate": 1.619557347540325e-05, + "loss": 1.4773, + "step": 3419 + }, + { + "epoch": 0.36, + "learning_rate": 1.6192699942026763e-05, + "loss": 1.4551, + "step": 3420 + }, + { + "epoch": 0.36, + "learning_rate": 1.6189825578987603e-05, + "loss": 1.4903, + "step": 3421 + }, + { + "epoch": 0.36, + "learning_rate": 1.6186950386670855e-05, + "loss": 1.473, + "step": 3422 + }, + { + "epoch": 0.36, + "learning_rate": 1.6184074365461722e-05, + "loss": 1.4082, + "step": 3423 + }, + { + "epoch": 0.36, + "learning_rate": 1.6181197515745523e-05, + "loss": 1.4746, + "step": 3424 + }, + { + "epoch": 0.36, + "learning_rate": 1.6178319837907674e-05, + "loss": 1.449, + "step": 3425 + }, + { + "epoch": 0.36, + "learning_rate": 1.6175441332333715e-05, + "loss": 1.377, + "step": 3426 + }, + { + "epoch": 0.36, + "learning_rate": 1.617256199940929e-05, + "loss": 1.2364, + "step": 3427 + }, + { + "epoch": 0.36, + "learning_rate": 1.6169681839520155e-05, + "loss": 1.4437, + "step": 3428 + }, + { + "epoch": 0.36, + "learning_rate": 1.616680085305218e-05, + "loss": 1.4726, + "step": 3429 + }, + { + "epoch": 0.36, + "learning_rate": 1.616391904039134e-05, + "loss": 1.4824, + "step": 3430 + }, + { + "epoch": 0.36, + "learning_rate": 1.616103640192373e-05, + "loss": 1.4052, + "step": 3431 + }, + { + "epoch": 0.36, + "learning_rate": 1.6158152938035537e-05, + "loss": 1.4131, + "step": 3432 + }, + { + "epoch": 0.36, + "learning_rate": 1.6155268649113084e-05, + "loss": 1.4267, + "step": 3433 + }, + { + "epoch": 0.36, + "learning_rate": 1.6152383535542786e-05, + "loss": 1.3735, + "step": 3434 + }, + { + "epoch": 0.36, + "learning_rate": 1.6149497597711175e-05, + "loss": 1.4249, + "step": 3435 + }, + { + "epoch": 0.36, + "learning_rate": 1.614661083600489e-05, + "loss": 1.4312, + "step": 3436 + }, + { + "epoch": 0.36, + "learning_rate": 1.6143723250810686e-05, + "loss": 1.4831, + "step": 3437 + }, + { + "epoch": 0.36, + "learning_rate": 1.6140834842515425e-05, + "loss": 1.4183, + "step": 3438 + }, + { + "epoch": 0.36, + "learning_rate": 1.6137945611506078e-05, + "loss": 1.3908, + "step": 3439 + }, + { + "epoch": 0.36, + "learning_rate": 1.613505555816973e-05, + "loss": 1.425, + "step": 3440 + }, + { + "epoch": 0.36, + "learning_rate": 1.613216468289357e-05, + "loss": 1.3589, + "step": 3441 + }, + { + "epoch": 0.36, + "learning_rate": 1.6129272986064903e-05, + "loss": 1.4272, + "step": 3442 + }, + { + "epoch": 0.36, + "learning_rate": 1.6126380468071142e-05, + "loss": 1.4337, + "step": 3443 + }, + { + "epoch": 0.36, + "learning_rate": 1.6123487129299817e-05, + "loss": 1.3872, + "step": 3444 + }, + { + "epoch": 0.36, + "learning_rate": 1.612059297013855e-05, + "loss": 1.374, + "step": 3445 + }, + { + "epoch": 0.36, + "learning_rate": 1.611769799097509e-05, + "loss": 1.314, + "step": 3446 + }, + { + "epoch": 0.36, + "learning_rate": 1.6114802192197284e-05, + "loss": 1.3951, + "step": 3447 + }, + { + "epoch": 0.36, + "learning_rate": 1.6111905574193102e-05, + "loss": 1.4732, + "step": 3448 + }, + { + "epoch": 0.36, + "learning_rate": 1.6109008137350614e-05, + "loss": 1.3575, + "step": 3449 + }, + { + "epoch": 0.36, + "learning_rate": 1.6106109882058e-05, + "loss": 1.4606, + "step": 3450 + }, + { + "epoch": 0.36, + "learning_rate": 1.6103210808703554e-05, + "loss": 1.4357, + "step": 3451 + }, + { + "epoch": 0.36, + "learning_rate": 1.6100310917675678e-05, + "loss": 0.8456, + "step": 3452 + }, + { + "epoch": 0.36, + "learning_rate": 1.609741020936288e-05, + "loss": 1.07, + "step": 3453 + }, + { + "epoch": 0.36, + "learning_rate": 1.6094508684153782e-05, + "loss": 1.4435, + "step": 3454 + }, + { + "epoch": 0.36, + "learning_rate": 1.609160634243711e-05, + "loss": 1.3696, + "step": 3455 + }, + { + "epoch": 0.36, + "learning_rate": 1.6088703184601712e-05, + "loss": 1.4012, + "step": 3456 + }, + { + "epoch": 0.36, + "learning_rate": 1.608579921103653e-05, + "loss": 1.5212, + "step": 3457 + }, + { + "epoch": 0.36, + "learning_rate": 1.608289442213062e-05, + "loss": 1.4339, + "step": 3458 + }, + { + "epoch": 0.36, + "learning_rate": 1.607998881827316e-05, + "loss": 1.4901, + "step": 3459 + }, + { + "epoch": 0.36, + "learning_rate": 1.6077082399853412e-05, + "loss": 1.4822, + "step": 3460 + }, + { + "epoch": 0.36, + "learning_rate": 1.607417516726077e-05, + "loss": 1.3696, + "step": 3461 + }, + { + "epoch": 0.36, + "learning_rate": 1.6071267120884727e-05, + "loss": 1.4434, + "step": 3462 + }, + { + "epoch": 0.36, + "learning_rate": 1.6068358261114886e-05, + "loss": 1.3916, + "step": 3463 + }, + { + "epoch": 0.36, + "learning_rate": 1.606544858834096e-05, + "loss": 1.422, + "step": 3464 + }, + { + "epoch": 0.36, + "learning_rate": 1.6062538102952763e-05, + "loss": 1.367, + "step": 3465 + }, + { + "epoch": 0.36, + "learning_rate": 1.605962680534024e-05, + "loss": 1.3788, + "step": 3466 + }, + { + "epoch": 0.36, + "learning_rate": 1.605671469589342e-05, + "loss": 1.4366, + "step": 3467 + }, + { + "epoch": 0.36, + "learning_rate": 1.6053801775002453e-05, + "loss": 1.4027, + "step": 3468 + }, + { + "epoch": 0.36, + "learning_rate": 1.6050888043057595e-05, + "loss": 1.4386, + "step": 3469 + }, + { + "epoch": 0.36, + "learning_rate": 1.6047973500449212e-05, + "loss": 1.4675, + "step": 3470 + }, + { + "epoch": 0.36, + "learning_rate": 1.6045058147567778e-05, + "loss": 1.6936, + "step": 3471 + }, + { + "epoch": 0.36, + "learning_rate": 1.6042141984803875e-05, + "loss": 1.4858, + "step": 3472 + }, + { + "epoch": 0.36, + "learning_rate": 1.6039225012548196e-05, + "loss": 1.5004, + "step": 3473 + }, + { + "epoch": 0.36, + "learning_rate": 1.6036307231191534e-05, + "loss": 1.4969, + "step": 3474 + }, + { + "epoch": 0.36, + "learning_rate": 1.6033388641124803e-05, + "loss": 1.4027, + "step": 3475 + }, + { + "epoch": 0.36, + "learning_rate": 1.6030469242739016e-05, + "loss": 1.4741, + "step": 3476 + }, + { + "epoch": 0.36, + "learning_rate": 1.60275490364253e-05, + "loss": 1.3887, + "step": 3477 + }, + { + "epoch": 0.36, + "learning_rate": 1.602462802257488e-05, + "loss": 1.6735, + "step": 3478 + }, + { + "epoch": 0.36, + "learning_rate": 1.602170620157911e-05, + "loss": 1.4997, + "step": 3479 + }, + { + "epoch": 0.36, + "learning_rate": 1.601878357382943e-05, + "loss": 1.3973, + "step": 3480 + }, + { + "epoch": 0.37, + "learning_rate": 1.6015860139717398e-05, + "loss": 1.416, + "step": 3481 + }, + { + "epoch": 0.37, + "learning_rate": 1.6012935899634682e-05, + "loss": 1.4102, + "step": 3482 + }, + { + "epoch": 0.37, + "learning_rate": 1.601001085397305e-05, + "loss": 1.4248, + "step": 3483 + }, + { + "epoch": 0.37, + "learning_rate": 1.6007085003124386e-05, + "loss": 1.3909, + "step": 3484 + }, + { + "epoch": 0.37, + "learning_rate": 1.600415834748068e-05, + "loss": 1.4029, + "step": 3485 + }, + { + "epoch": 0.37, + "learning_rate": 1.6001230887434024e-05, + "loss": 1.4219, + "step": 3486 + }, + { + "epoch": 0.37, + "learning_rate": 1.5998302623376633e-05, + "loss": 1.4008, + "step": 3487 + }, + { + "epoch": 0.37, + "learning_rate": 1.5995373555700806e-05, + "loss": 1.5163, + "step": 3488 + }, + { + "epoch": 0.37, + "learning_rate": 1.599244368479897e-05, + "loss": 1.4541, + "step": 3489 + }, + { + "epoch": 0.37, + "learning_rate": 1.598951301106365e-05, + "loss": 1.4454, + "step": 3490 + }, + { + "epoch": 0.37, + "learning_rate": 1.598658153488748e-05, + "loss": 1.1014, + "step": 3491 + }, + { + "epoch": 0.37, + "learning_rate": 1.598364925666321e-05, + "loss": 1.407, + "step": 3492 + }, + { + "epoch": 0.37, + "learning_rate": 1.5980716176783682e-05, + "loss": 1.5046, + "step": 3493 + }, + { + "epoch": 0.37, + "learning_rate": 1.5977782295641857e-05, + "loss": 1.4265, + "step": 3494 + }, + { + "epoch": 0.37, + "learning_rate": 1.5974847613630796e-05, + "loss": 1.46, + "step": 3495 + }, + { + "epoch": 0.37, + "learning_rate": 1.5971912131143677e-05, + "loss": 1.3996, + "step": 3496 + }, + { + "epoch": 0.37, + "learning_rate": 1.5968975848573772e-05, + "loss": 1.4719, + "step": 3497 + }, + { + "epoch": 0.37, + "learning_rate": 1.596603876631447e-05, + "loss": 1.43, + "step": 3498 + }, + { + "epoch": 0.37, + "learning_rate": 1.596310088475927e-05, + "loss": 1.4109, + "step": 3499 + }, + { + "epoch": 0.37, + "learning_rate": 1.5960162204301768e-05, + "loss": 1.3612, + "step": 3500 + }, + { + "epoch": 0.37, + "learning_rate": 1.5957222725335672e-05, + "loss": 1.5045, + "step": 3501 + }, + { + "epoch": 0.37, + "learning_rate": 1.5954282448254794e-05, + "loss": 1.5323, + "step": 3502 + }, + { + "epoch": 0.37, + "learning_rate": 1.595134137345306e-05, + "loss": 1.4518, + "step": 3503 + }, + { + "epoch": 0.37, + "learning_rate": 1.5948399501324495e-05, + "loss": 1.6131, + "step": 3504 + }, + { + "epoch": 0.37, + "learning_rate": 1.594545683226324e-05, + "loss": 1.5076, + "step": 3505 + }, + { + "epoch": 0.37, + "learning_rate": 1.594251336666353e-05, + "loss": 1.482, + "step": 3506 + }, + { + "epoch": 0.37, + "learning_rate": 1.5939569104919716e-05, + "loss": 1.4429, + "step": 3507 + }, + { + "epoch": 0.37, + "learning_rate": 1.5936624047426254e-05, + "loss": 1.4662, + "step": 3508 + }, + { + "epoch": 0.37, + "learning_rate": 1.5933678194577708e-05, + "loss": 1.425, + "step": 3509 + }, + { + "epoch": 0.37, + "learning_rate": 1.5930731546768744e-05, + "loss": 1.4312, + "step": 3510 + }, + { + "epoch": 0.37, + "learning_rate": 1.592778410439414e-05, + "loss": 1.4336, + "step": 3511 + }, + { + "epoch": 0.37, + "learning_rate": 1.5924835867848775e-05, + "loss": 1.4197, + "step": 3512 + }, + { + "epoch": 0.37, + "learning_rate": 1.5921886837527638e-05, + "loss": 1.4456, + "step": 3513 + }, + { + "epoch": 0.37, + "learning_rate": 1.5918937013825823e-05, + "loss": 1.4394, + "step": 3514 + }, + { + "epoch": 0.37, + "learning_rate": 1.5915986397138526e-05, + "loss": 1.3606, + "step": 3515 + }, + { + "epoch": 0.37, + "learning_rate": 1.591303498786106e-05, + "loss": 1.4382, + "step": 3516 + }, + { + "epoch": 0.37, + "learning_rate": 1.591008278638884e-05, + "loss": 1.4185, + "step": 3517 + }, + { + "epoch": 0.37, + "learning_rate": 1.5907129793117374e-05, + "loss": 1.6692, + "step": 3518 + }, + { + "epoch": 0.37, + "learning_rate": 1.59041760084423e-05, + "loss": 1.501, + "step": 3519 + }, + { + "epoch": 0.37, + "learning_rate": 1.5901221432759345e-05, + "loss": 1.5753, + "step": 3520 + }, + { + "epoch": 0.37, + "learning_rate": 1.589826606646434e-05, + "loss": 1.4795, + "step": 3521 + }, + { + "epoch": 0.37, + "learning_rate": 1.5895309909953236e-05, + "loss": 1.4379, + "step": 3522 + }, + { + "epoch": 0.37, + "learning_rate": 1.5892352963622078e-05, + "loss": 1.3426, + "step": 3523 + }, + { + "epoch": 0.37, + "learning_rate": 1.5889395227867025e-05, + "loss": 1.4048, + "step": 3524 + }, + { + "epoch": 0.37, + "learning_rate": 1.5886436703084332e-05, + "loss": 1.4303, + "step": 3525 + }, + { + "epoch": 0.37, + "learning_rate": 1.5883477389670367e-05, + "loss": 1.3684, + "step": 3526 + }, + { + "epoch": 0.37, + "learning_rate": 1.5880517288021602e-05, + "loss": 1.3701, + "step": 3527 + }, + { + "epoch": 0.37, + "learning_rate": 1.587755639853462e-05, + "loss": 1.4308, + "step": 3528 + }, + { + "epoch": 0.37, + "learning_rate": 1.5874594721606096e-05, + "loss": 1.3981, + "step": 3529 + }, + { + "epoch": 0.37, + "learning_rate": 1.5871632257632823e-05, + "loss": 1.5906, + "step": 3530 + }, + { + "epoch": 0.37, + "learning_rate": 1.5868669007011696e-05, + "loss": 1.4642, + "step": 3531 + }, + { + "epoch": 0.37, + "learning_rate": 1.586570497013971e-05, + "loss": 1.411, + "step": 3532 + }, + { + "epoch": 0.37, + "learning_rate": 1.586274014741397e-05, + "loss": 1.3942, + "step": 3533 + }, + { + "epoch": 0.37, + "learning_rate": 1.5859774539231693e-05, + "loss": 1.3952, + "step": 3534 + }, + { + "epoch": 0.37, + "learning_rate": 1.585680814599019e-05, + "loss": 1.4009, + "step": 3535 + }, + { + "epoch": 0.37, + "learning_rate": 1.585384096808688e-05, + "loss": 1.3238, + "step": 3536 + }, + { + "epoch": 0.37, + "learning_rate": 1.585087300591929e-05, + "loss": 1.346, + "step": 3537 + }, + { + "epoch": 0.37, + "learning_rate": 1.584790425988505e-05, + "loss": 1.3739, + "step": 3538 + }, + { + "epoch": 0.37, + "learning_rate": 1.5844934730381895e-05, + "loss": 1.4264, + "step": 3539 + }, + { + "epoch": 0.37, + "learning_rate": 1.5841964417807668e-05, + "loss": 1.4675, + "step": 3540 + }, + { + "epoch": 0.37, + "learning_rate": 1.5838993322560314e-05, + "loss": 1.3337, + "step": 3541 + }, + { + "epoch": 0.37, + "learning_rate": 1.5836021445037883e-05, + "loss": 1.4052, + "step": 3542 + }, + { + "epoch": 0.37, + "learning_rate": 1.583304878563853e-05, + "loss": 1.4311, + "step": 3543 + }, + { + "epoch": 0.37, + "learning_rate": 1.5830075344760513e-05, + "loss": 1.386, + "step": 3544 + }, + { + "epoch": 0.37, + "learning_rate": 1.58271011228022e-05, + "loss": 1.387, + "step": 3545 + }, + { + "epoch": 0.37, + "learning_rate": 1.582412612016206e-05, + "loss": 1.3601, + "step": 3546 + }, + { + "epoch": 0.37, + "learning_rate": 1.5821150337238663e-05, + "loss": 1.5111, + "step": 3547 + }, + { + "epoch": 0.37, + "learning_rate": 1.5818173774430697e-05, + "loss": 1.471, + "step": 3548 + }, + { + "epoch": 0.37, + "learning_rate": 1.581519643213693e-05, + "loss": 1.4442, + "step": 3549 + }, + { + "epoch": 0.37, + "learning_rate": 1.5812218310756263e-05, + "loss": 1.467, + "step": 3550 + }, + { + "epoch": 0.37, + "learning_rate": 1.5809239410687683e-05, + "loss": 1.3731, + "step": 3551 + }, + { + "epoch": 0.37, + "learning_rate": 1.5806259732330286e-05, + "loss": 1.4072, + "step": 3552 + }, + { + "epoch": 0.37, + "learning_rate": 1.5803279276083268e-05, + "loss": 1.3636, + "step": 3553 + }, + { + "epoch": 0.37, + "learning_rate": 1.5800298042345938e-05, + "loss": 1.3915, + "step": 3554 + }, + { + "epoch": 0.37, + "learning_rate": 1.5797316031517705e-05, + "loss": 1.5038, + "step": 3555 + }, + { + "epoch": 0.37, + "learning_rate": 1.5794333243998082e-05, + "loss": 1.4455, + "step": 3556 + }, + { + "epoch": 0.37, + "learning_rate": 1.5791349680186684e-05, + "loss": 1.5062, + "step": 3557 + }, + { + "epoch": 0.37, + "learning_rate": 1.5788365340483234e-05, + "loss": 1.3899, + "step": 3558 + }, + { + "epoch": 0.37, + "learning_rate": 1.5785380225287554e-05, + "loss": 1.4946, + "step": 3559 + }, + { + "epoch": 0.37, + "learning_rate": 1.5782394334999572e-05, + "loss": 1.3859, + "step": 3560 + }, + { + "epoch": 0.37, + "learning_rate": 1.577940767001933e-05, + "loss": 1.541, + "step": 3561 + }, + { + "epoch": 0.37, + "learning_rate": 1.5776420230746952e-05, + "loss": 1.4952, + "step": 3562 + }, + { + "epoch": 0.37, + "learning_rate": 1.5773432017582684e-05, + "loss": 1.6055, + "step": 3563 + }, + { + "epoch": 0.37, + "learning_rate": 1.577044303092687e-05, + "loss": 1.4661, + "step": 3564 + }, + { + "epoch": 0.37, + "learning_rate": 1.576745327117996e-05, + "loss": 1.4082, + "step": 3565 + }, + { + "epoch": 0.37, + "learning_rate": 1.5764462738742493e-05, + "loss": 1.4005, + "step": 3566 + }, + { + "epoch": 0.37, + "learning_rate": 1.5761471434015137e-05, + "loss": 1.3959, + "step": 3567 + }, + { + "epoch": 0.37, + "learning_rate": 1.5758479357398645e-05, + "loss": 1.4567, + "step": 3568 + }, + { + "epoch": 0.37, + "learning_rate": 1.575548650929388e-05, + "loss": 1.3791, + "step": 3569 + }, + { + "epoch": 0.37, + "learning_rate": 1.57524928901018e-05, + "loss": 1.4428, + "step": 3570 + }, + { + "epoch": 0.37, + "learning_rate": 1.5749498500223486e-05, + "loss": 1.3864, + "step": 3571 + }, + { + "epoch": 0.37, + "learning_rate": 1.5746503340060097e-05, + "loss": 1.4019, + "step": 3572 + }, + { + "epoch": 0.37, + "learning_rate": 1.574350741001291e-05, + "loss": 1.5436, + "step": 3573 + }, + { + "epoch": 0.37, + "learning_rate": 1.5740510710483308e-05, + "loss": 1.4637, + "step": 3574 + }, + { + "epoch": 0.37, + "learning_rate": 1.5737513241872767e-05, + "loss": 1.5097, + "step": 3575 + }, + { + "epoch": 0.38, + "learning_rate": 1.5734515004582873e-05, + "loss": 1.5143, + "step": 3576 + }, + { + "epoch": 0.38, + "learning_rate": 1.5731515999015315e-05, + "loss": 1.3926, + "step": 3577 + }, + { + "epoch": 0.38, + "learning_rate": 1.5728516225571874e-05, + "loss": 1.4242, + "step": 3578 + }, + { + "epoch": 0.38, + "learning_rate": 1.5725515684654453e-05, + "loss": 1.4429, + "step": 3579 + }, + { + "epoch": 0.38, + "learning_rate": 1.572251437666504e-05, + "loss": 1.4638, + "step": 3580 + }, + { + "epoch": 0.38, + "learning_rate": 1.5719512302005735e-05, + "loss": 1.3381, + "step": 3581 + }, + { + "epoch": 0.38, + "learning_rate": 1.571650946107874e-05, + "loss": 1.4342, + "step": 3582 + }, + { + "epoch": 0.38, + "eval_loss": 1.4705015420913696, + "eval_runtime": 77.3664, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3582 + }, + { + "epoch": 0.38, + "learning_rate": 1.571350585428636e-05, + "loss": 1.3991, + "step": 3583 + }, + { + "epoch": 0.38, + "learning_rate": 1.5710501482030998e-05, + "loss": 1.4274, + "step": 3584 + }, + { + "epoch": 0.38, + "learning_rate": 1.5707496344715166e-05, + "loss": 1.438, + "step": 3585 + }, + { + "epoch": 0.38, + "learning_rate": 1.570449044274147e-05, + "loss": 1.4453, + "step": 3586 + }, + { + "epoch": 0.38, + "learning_rate": 1.570148377651263e-05, + "loss": 1.4022, + "step": 3587 + }, + { + "epoch": 0.38, + "learning_rate": 1.5698476346431454e-05, + "loss": 1.4312, + "step": 3588 + }, + { + "epoch": 0.38, + "learning_rate": 1.569546815290087e-05, + "loss": 1.4329, + "step": 3589 + }, + { + "epoch": 0.38, + "learning_rate": 1.569245919632389e-05, + "loss": 1.4036, + "step": 3590 + }, + { + "epoch": 0.38, + "learning_rate": 1.5689449477103644e-05, + "loss": 1.412, + "step": 3591 + }, + { + "epoch": 0.38, + "learning_rate": 1.5686438995643353e-05, + "loss": 1.4492, + "step": 3592 + }, + { + "epoch": 0.38, + "learning_rate": 1.5683427752346343e-05, + "loss": 1.4555, + "step": 3593 + }, + { + "epoch": 0.38, + "learning_rate": 1.5680415747616047e-05, + "loss": 1.5594, + "step": 3594 + }, + { + "epoch": 0.38, + "learning_rate": 1.5677402981855993e-05, + "loss": 1.4813, + "step": 3595 + }, + { + "epoch": 0.38, + "learning_rate": 1.567438945546982e-05, + "loss": 1.5919, + "step": 3596 + }, + { + "epoch": 0.38, + "learning_rate": 1.5671375168861255e-05, + "loss": 1.4235, + "step": 3597 + }, + { + "epoch": 0.38, + "learning_rate": 1.5668360122434135e-05, + "loss": 1.441, + "step": 3598 + }, + { + "epoch": 0.38, + "learning_rate": 1.566534431659241e-05, + "loss": 1.5847, + "step": 3599 + }, + { + "epoch": 0.38, + "learning_rate": 1.566232775174011e-05, + "loss": 1.6123, + "step": 3600 + }, + { + "epoch": 0.38, + "learning_rate": 1.5659310428281374e-05, + "loss": 1.4916, + "step": 3601 + }, + { + "epoch": 0.38, + "learning_rate": 1.5656292346620457e-05, + "loss": 1.4603, + "step": 3602 + }, + { + "epoch": 0.38, + "learning_rate": 1.56532735071617e-05, + "loss": 1.4423, + "step": 3603 + }, + { + "epoch": 0.38, + "learning_rate": 1.5650253910309547e-05, + "loss": 1.4814, + "step": 3604 + }, + { + "epoch": 0.38, + "learning_rate": 1.5647233556468552e-05, + "loss": 1.4015, + "step": 3605 + }, + { + "epoch": 0.38, + "learning_rate": 1.564421244604336e-05, + "loss": 1.3798, + "step": 3606 + }, + { + "epoch": 0.38, + "learning_rate": 1.5641190579438723e-05, + "loss": 1.4259, + "step": 3607 + }, + { + "epoch": 0.38, + "learning_rate": 1.5638167957059493e-05, + "loss": 1.3493, + "step": 3608 + }, + { + "epoch": 0.38, + "learning_rate": 1.5635144579310626e-05, + "loss": 1.3433, + "step": 3609 + }, + { + "epoch": 0.38, + "learning_rate": 1.5632120446597177e-05, + "loss": 1.4661, + "step": 3610 + }, + { + "epoch": 0.38, + "learning_rate": 1.5629095559324297e-05, + "loss": 1.4205, + "step": 3611 + }, + { + "epoch": 0.38, + "learning_rate": 1.562606991789725e-05, + "loss": 1.3976, + "step": 3612 + }, + { + "epoch": 0.38, + "learning_rate": 1.5623043522721393e-05, + "loss": 1.4261, + "step": 3613 + }, + { + "epoch": 0.38, + "learning_rate": 1.562001637420218e-05, + "loss": 1.4358, + "step": 3614 + }, + { + "epoch": 0.38, + "learning_rate": 1.5616988472745175e-05, + "loss": 1.437, + "step": 3615 + }, + { + "epoch": 0.38, + "learning_rate": 1.561395981875604e-05, + "loss": 1.3735, + "step": 3616 + }, + { + "epoch": 0.38, + "learning_rate": 1.5610930412640532e-05, + "loss": 1.4357, + "step": 3617 + }, + { + "epoch": 0.38, + "learning_rate": 1.560790025480452e-05, + "loss": 1.4003, + "step": 3618 + }, + { + "epoch": 0.38, + "learning_rate": 1.5604869345653965e-05, + "loss": 1.4127, + "step": 3619 + }, + { + "epoch": 0.38, + "learning_rate": 1.5601837685594927e-05, + "loss": 1.4666, + "step": 3620 + }, + { + "epoch": 0.38, + "learning_rate": 1.5598805275033574e-05, + "loss": 1.4106, + "step": 3621 + }, + { + "epoch": 0.38, + "learning_rate": 1.5595772114376174e-05, + "loss": 1.3857, + "step": 3622 + }, + { + "epoch": 0.38, + "learning_rate": 1.5592738204029086e-05, + "loss": 1.4704, + "step": 3623 + }, + { + "epoch": 0.38, + "learning_rate": 1.558970354439878e-05, + "loss": 1.4649, + "step": 3624 + }, + { + "epoch": 0.38, + "learning_rate": 1.5586668135891824e-05, + "loss": 1.4812, + "step": 3625 + }, + { + "epoch": 0.38, + "learning_rate": 1.5583631978914882e-05, + "loss": 1.3507, + "step": 3626 + }, + { + "epoch": 0.38, + "learning_rate": 1.5580595073874718e-05, + "loss": 1.3762, + "step": 3627 + }, + { + "epoch": 0.38, + "learning_rate": 1.557755742117821e-05, + "loss": 1.4169, + "step": 3628 + }, + { + "epoch": 0.38, + "learning_rate": 1.557451902123231e-05, + "loss": 1.4098, + "step": 3629 + }, + { + "epoch": 0.38, + "learning_rate": 1.55714798744441e-05, + "loss": 1.5526, + "step": 3630 + }, + { + "epoch": 0.38, + "learning_rate": 1.556843998122074e-05, + "loss": 1.4414, + "step": 3631 + }, + { + "epoch": 0.38, + "learning_rate": 1.5565399341969497e-05, + "loss": 1.4134, + "step": 3632 + }, + { + "epoch": 0.38, + "learning_rate": 1.556235795709774e-05, + "loss": 1.4718, + "step": 3633 + }, + { + "epoch": 0.38, + "learning_rate": 1.5559315827012937e-05, + "loss": 1.412, + "step": 3634 + }, + { + "epoch": 0.38, + "learning_rate": 1.5556272952122657e-05, + "loss": 1.4119, + "step": 3635 + }, + { + "epoch": 0.38, + "learning_rate": 1.5553229332834564e-05, + "loss": 1.3999, + "step": 3636 + }, + { + "epoch": 0.38, + "learning_rate": 1.5550184969556428e-05, + "loss": 1.4626, + "step": 3637 + }, + { + "epoch": 0.38, + "learning_rate": 1.5547139862696113e-05, + "loss": 1.3811, + "step": 3638 + }, + { + "epoch": 0.38, + "learning_rate": 1.5544094012661583e-05, + "loss": 1.4053, + "step": 3639 + }, + { + "epoch": 0.38, + "learning_rate": 1.5541047419860907e-05, + "loss": 1.4059, + "step": 3640 + }, + { + "epoch": 0.38, + "learning_rate": 1.553800008470225e-05, + "loss": 1.4717, + "step": 3641 + }, + { + "epoch": 0.38, + "learning_rate": 1.553495200759388e-05, + "loss": 1.399, + "step": 3642 + }, + { + "epoch": 0.38, + "learning_rate": 1.5531903188944154e-05, + "loss": 1.4143, + "step": 3643 + }, + { + "epoch": 0.38, + "learning_rate": 1.5528853629161536e-05, + "loss": 1.4414, + "step": 3644 + }, + { + "epoch": 0.38, + "learning_rate": 1.5525803328654592e-05, + "loss": 1.4206, + "step": 3645 + }, + { + "epoch": 0.38, + "learning_rate": 1.5522752287831982e-05, + "loss": 1.3869, + "step": 3646 + }, + { + "epoch": 0.38, + "learning_rate": 1.551970050710247e-05, + "loss": 1.5434, + "step": 3647 + }, + { + "epoch": 0.38, + "learning_rate": 1.5516647986874914e-05, + "loss": 1.4574, + "step": 3648 + }, + { + "epoch": 0.38, + "learning_rate": 1.5513594727558273e-05, + "loss": 1.4353, + "step": 3649 + }, + { + "epoch": 0.38, + "learning_rate": 1.5510540729561606e-05, + "loss": 1.4122, + "step": 3650 + }, + { + "epoch": 0.38, + "learning_rate": 1.550748599329407e-05, + "loss": 1.4077, + "step": 3651 + }, + { + "epoch": 0.38, + "learning_rate": 1.550443051916492e-05, + "loss": 1.4433, + "step": 3652 + }, + { + "epoch": 0.38, + "learning_rate": 1.5501374307583514e-05, + "loss": 1.54, + "step": 3653 + }, + { + "epoch": 0.38, + "learning_rate": 1.5498317358959302e-05, + "loss": 1.4522, + "step": 3654 + }, + { + "epoch": 0.38, + "learning_rate": 1.5495259673701842e-05, + "loss": 1.4175, + "step": 3655 + }, + { + "epoch": 0.38, + "learning_rate": 1.5492201252220777e-05, + "loss": 1.4637, + "step": 3656 + }, + { + "epoch": 0.38, + "learning_rate": 1.5489142094925863e-05, + "loss": 1.4701, + "step": 3657 + }, + { + "epoch": 0.38, + "learning_rate": 1.548608220222695e-05, + "loss": 1.4095, + "step": 3658 + }, + { + "epoch": 0.38, + "learning_rate": 1.548302157453398e-05, + "loss": 1.3903, + "step": 3659 + }, + { + "epoch": 0.38, + "learning_rate": 1.5479960212257002e-05, + "loss": 1.4062, + "step": 3660 + }, + { + "epoch": 0.38, + "learning_rate": 1.5476898115806157e-05, + "loss": 1.4706, + "step": 3661 + }, + { + "epoch": 0.38, + "learning_rate": 1.547383528559169e-05, + "loss": 1.4423, + "step": 3662 + }, + { + "epoch": 0.38, + "learning_rate": 1.547077172202394e-05, + "loss": 1.4418, + "step": 3663 + }, + { + "epoch": 0.38, + "learning_rate": 1.5467707425513347e-05, + "loss": 1.4553, + "step": 3664 + }, + { + "epoch": 0.38, + "learning_rate": 1.5464642396470443e-05, + "loss": 1.435, + "step": 3665 + }, + { + "epoch": 0.38, + "learning_rate": 1.5461576635305873e-05, + "loss": 1.4105, + "step": 3666 + }, + { + "epoch": 0.38, + "learning_rate": 1.5458510142430364e-05, + "loss": 1.4118, + "step": 3667 + }, + { + "epoch": 0.38, + "learning_rate": 1.5455442918254746e-05, + "loss": 1.4096, + "step": 3668 + }, + { + "epoch": 0.38, + "learning_rate": 1.545237496318995e-05, + "loss": 1.4248, + "step": 3669 + }, + { + "epoch": 0.38, + "learning_rate": 1.5449306277647003e-05, + "loss": 1.4591, + "step": 3670 + }, + { + "epoch": 0.38, + "learning_rate": 1.544623686203703e-05, + "loss": 1.4764, + "step": 3671 + }, + { + "epoch": 0.39, + "learning_rate": 1.5443166716771255e-05, + "loss": 1.4329, + "step": 3672 + }, + { + "epoch": 0.39, + "learning_rate": 1.5440095842260995e-05, + "loss": 1.4023, + "step": 3673 + }, + { + "epoch": 0.39, + "learning_rate": 1.5437024238917674e-05, + "loss": 1.3802, + "step": 3674 + }, + { + "epoch": 0.39, + "learning_rate": 1.5433951907152806e-05, + "loss": 1.4627, + "step": 3675 + }, + { + "epoch": 0.39, + "learning_rate": 1.5430878847378e-05, + "loss": 1.5164, + "step": 3676 + }, + { + "epoch": 0.39, + "learning_rate": 1.542780506000497e-05, + "loss": 1.3546, + "step": 3677 + }, + { + "epoch": 0.39, + "learning_rate": 1.542473054544553e-05, + "loss": 1.4415, + "step": 3678 + }, + { + "epoch": 0.39, + "learning_rate": 1.5421655304111573e-05, + "loss": 1.4093, + "step": 3679 + }, + { + "epoch": 0.39, + "learning_rate": 1.5418579336415114e-05, + "loss": 1.3943, + "step": 3680 + }, + { + "epoch": 0.39, + "learning_rate": 1.5415502642768252e-05, + "loss": 1.3659, + "step": 3681 + }, + { + "epoch": 0.39, + "learning_rate": 1.541242522358318e-05, + "loss": 1.4322, + "step": 3682 + }, + { + "epoch": 0.39, + "learning_rate": 1.5409347079272198e-05, + "loss": 1.4064, + "step": 3683 + }, + { + "epoch": 0.39, + "learning_rate": 1.5406268210247693e-05, + "loss": 1.4031, + "step": 3684 + }, + { + "epoch": 0.39, + "learning_rate": 1.540318861692216e-05, + "loss": 1.3449, + "step": 3685 + }, + { + "epoch": 0.39, + "learning_rate": 1.5400108299708182e-05, + "loss": 1.5536, + "step": 3686 + }, + { + "epoch": 0.39, + "learning_rate": 1.5397027259018442e-05, + "loss": 1.4106, + "step": 3687 + }, + { + "epoch": 0.39, + "learning_rate": 1.5393945495265722e-05, + "loss": 1.4309, + "step": 3688 + }, + { + "epoch": 0.39, + "learning_rate": 1.53908630088629e-05, + "loss": 1.3765, + "step": 3689 + }, + { + "epoch": 0.39, + "learning_rate": 1.5387779800222947e-05, + "loss": 1.3809, + "step": 3690 + }, + { + "epoch": 0.39, + "learning_rate": 1.5384695869758938e-05, + "loss": 1.4758, + "step": 3691 + }, + { + "epoch": 0.39, + "learning_rate": 1.5381611217884032e-05, + "loss": 1.4249, + "step": 3692 + }, + { + "epoch": 0.39, + "learning_rate": 1.5378525845011503e-05, + "loss": 1.4133, + "step": 3693 + }, + { + "epoch": 0.39, + "learning_rate": 1.5375439751554708e-05, + "loss": 1.418, + "step": 3694 + }, + { + "epoch": 0.39, + "learning_rate": 1.53723529379271e-05, + "loss": 1.441, + "step": 3695 + }, + { + "epoch": 0.39, + "learning_rate": 1.536926540454224e-05, + "loss": 1.3919, + "step": 3696 + }, + { + "epoch": 0.39, + "learning_rate": 1.5366177151813775e-05, + "loss": 1.3722, + "step": 3697 + }, + { + "epoch": 0.39, + "learning_rate": 1.536308818015545e-05, + "loss": 1.4727, + "step": 3698 + }, + { + "epoch": 0.39, + "learning_rate": 1.535999848998111e-05, + "loss": 1.442, + "step": 3699 + }, + { + "epoch": 0.39, + "learning_rate": 1.535690808170469e-05, + "loss": 1.3884, + "step": 3700 + }, + { + "epoch": 0.39, + "learning_rate": 1.535381695574023e-05, + "loss": 1.3226, + "step": 3701 + }, + { + "epoch": 0.39, + "learning_rate": 1.535072511250186e-05, + "loss": 1.4403, + "step": 3702 + }, + { + "epoch": 0.39, + "learning_rate": 1.5347632552403808e-05, + "loss": 1.4144, + "step": 3703 + }, + { + "epoch": 0.39, + "learning_rate": 1.5344539275860395e-05, + "loss": 1.3514, + "step": 3704 + }, + { + "epoch": 0.39, + "learning_rate": 1.5341445283286044e-05, + "loss": 1.519, + "step": 3705 + }, + { + "epoch": 0.39, + "learning_rate": 1.5338350575095268e-05, + "loss": 1.4251, + "step": 3706 + }, + { + "epoch": 0.39, + "learning_rate": 1.5335255151702685e-05, + "loss": 1.392, + "step": 3707 + }, + { + "epoch": 0.39, + "learning_rate": 1.533215901352299e-05, + "loss": 1.3838, + "step": 3708 + }, + { + "epoch": 0.39, + "learning_rate": 1.532906216097099e-05, + "loss": 1.444, + "step": 3709 + }, + { + "epoch": 0.39, + "learning_rate": 1.5325964594461594e-05, + "loss": 1.3459, + "step": 3710 + }, + { + "epoch": 0.39, + "learning_rate": 1.5322866314409783e-05, + "loss": 1.4155, + "step": 3711 + }, + { + "epoch": 0.39, + "learning_rate": 1.5319767321230657e-05, + "loss": 1.4057, + "step": 3712 + }, + { + "epoch": 0.39, + "learning_rate": 1.5316667615339392e-05, + "loss": 1.382, + "step": 3713 + }, + { + "epoch": 0.39, + "learning_rate": 1.5313567197151277e-05, + "loss": 1.3634, + "step": 3714 + }, + { + "epoch": 0.39, + "learning_rate": 1.5310466067081688e-05, + "loss": 1.3434, + "step": 3715 + }, + { + "epoch": 0.39, + "learning_rate": 1.530736422554609e-05, + "loss": 1.4553, + "step": 3716 + }, + { + "epoch": 0.39, + "learning_rate": 1.5304261672960055e-05, + "loss": 1.4193, + "step": 3717 + }, + { + "epoch": 0.39, + "learning_rate": 1.5301158409739242e-05, + "loss": 1.3955, + "step": 3718 + }, + { + "epoch": 0.39, + "learning_rate": 1.5298054436299413e-05, + "loss": 1.4592, + "step": 3719 + }, + { + "epoch": 0.39, + "learning_rate": 1.529494975305642e-05, + "loss": 1.738, + "step": 3720 + }, + { + "epoch": 0.39, + "learning_rate": 1.529184436042621e-05, + "loss": 1.438, + "step": 3721 + }, + { + "epoch": 0.39, + "learning_rate": 1.528873825882482e-05, + "loss": 1.3445, + "step": 3722 + }, + { + "epoch": 0.39, + "learning_rate": 1.5285631448668395e-05, + "loss": 1.4168, + "step": 3723 + }, + { + "epoch": 0.39, + "learning_rate": 1.528252393037317e-05, + "loss": 1.4088, + "step": 3724 + }, + { + "epoch": 0.39, + "learning_rate": 1.5279415704355468e-05, + "loss": 1.4484, + "step": 3725 + }, + { + "epoch": 0.39, + "learning_rate": 1.5276306771031708e-05, + "loss": 1.4706, + "step": 3726 + }, + { + "epoch": 0.39, + "learning_rate": 1.527319713081841e-05, + "loss": 1.3466, + "step": 3727 + }, + { + "epoch": 0.39, + "learning_rate": 1.5270086784132196e-05, + "loss": 1.427, + "step": 3728 + }, + { + "epoch": 0.39, + "learning_rate": 1.5266975731389754e-05, + "loss": 1.4596, + "step": 3729 + }, + { + "epoch": 0.39, + "learning_rate": 1.52638639730079e-05, + "loss": 1.405, + "step": 3730 + }, + { + "epoch": 0.39, + "learning_rate": 1.5260751509403518e-05, + "loss": 1.4572, + "step": 3731 + }, + { + "epoch": 0.39, + "learning_rate": 1.5257638340993608e-05, + "loss": 1.3827, + "step": 3732 + }, + { + "epoch": 0.39, + "learning_rate": 1.5254524468195251e-05, + "loss": 1.3712, + "step": 3733 + }, + { + "epoch": 0.39, + "learning_rate": 1.5251409891425626e-05, + "loss": 1.4541, + "step": 3734 + }, + { + "epoch": 0.39, + "learning_rate": 1.5248294611102006e-05, + "loss": 1.5279, + "step": 3735 + }, + { + "epoch": 0.39, + "learning_rate": 1.5245178627641759e-05, + "loss": 1.3722, + "step": 3736 + }, + { + "epoch": 0.39, + "learning_rate": 1.5242061941462348e-05, + "loss": 1.5158, + "step": 3737 + }, + { + "epoch": 0.39, + "learning_rate": 1.523894455298132e-05, + "loss": 1.4274, + "step": 3738 + }, + { + "epoch": 0.39, + "learning_rate": 1.5235826462616338e-05, + "loss": 1.4543, + "step": 3739 + }, + { + "epoch": 0.39, + "learning_rate": 1.5232707670785144e-05, + "loss": 1.5011, + "step": 3740 + }, + { + "epoch": 0.39, + "learning_rate": 1.5229588177905568e-05, + "loss": 1.24, + "step": 3741 + }, + { + "epoch": 0.39, + "learning_rate": 1.5226467984395544e-05, + "loss": 1.4253, + "step": 3742 + }, + { + "epoch": 0.39, + "learning_rate": 1.5223347090673102e-05, + "loss": 1.3736, + "step": 3743 + }, + { + "epoch": 0.39, + "learning_rate": 1.522022549715636e-05, + "loss": 1.4587, + "step": 3744 + }, + { + "epoch": 0.39, + "learning_rate": 1.521710320426353e-05, + "loss": 1.5024, + "step": 3745 + }, + { + "epoch": 0.39, + "learning_rate": 1.521398021241292e-05, + "loss": 1.427, + "step": 3746 + }, + { + "epoch": 0.39, + "learning_rate": 1.5210856522022929e-05, + "loss": 1.3387, + "step": 3747 + }, + { + "epoch": 0.39, + "learning_rate": 1.5207732133512055e-05, + "loss": 1.3819, + "step": 3748 + }, + { + "epoch": 0.39, + "learning_rate": 1.5204607047298883e-05, + "loss": 1.4571, + "step": 3749 + }, + { + "epoch": 0.39, + "learning_rate": 1.5201481263802094e-05, + "loss": 1.3592, + "step": 3750 + }, + { + "epoch": 0.39, + "learning_rate": 1.5198354783440464e-05, + "loss": 1.3912, + "step": 3751 + }, + { + "epoch": 0.39, + "learning_rate": 1.519522760663286e-05, + "loss": 1.4986, + "step": 3752 + }, + { + "epoch": 0.39, + "learning_rate": 1.5192099733798243e-05, + "loss": 1.4106, + "step": 3753 + }, + { + "epoch": 0.39, + "learning_rate": 1.5188971165355667e-05, + "loss": 1.4145, + "step": 3754 + }, + { + "epoch": 0.39, + "learning_rate": 1.5185841901724282e-05, + "loss": 1.3915, + "step": 3755 + }, + { + "epoch": 0.39, + "learning_rate": 1.5182711943323329e-05, + "loss": 1.4014, + "step": 3756 + }, + { + "epoch": 0.39, + "learning_rate": 1.5179581290572141e-05, + "loss": 1.3651, + "step": 3757 + }, + { + "epoch": 0.39, + "learning_rate": 1.5176449943890147e-05, + "loss": 1.3653, + "step": 3758 + }, + { + "epoch": 0.39, + "learning_rate": 1.5173317903696862e-05, + "loss": 1.4486, + "step": 3759 + }, + { + "epoch": 0.39, + "learning_rate": 1.5170185170411906e-05, + "loss": 1.4459, + "step": 3760 + }, + { + "epoch": 0.39, + "learning_rate": 1.5167051744454977e-05, + "loss": 1.4215, + "step": 3761 + }, + { + "epoch": 0.39, + "learning_rate": 1.5163917626245877e-05, + "loss": 1.4379, + "step": 3762 + }, + { + "epoch": 0.39, + "learning_rate": 1.51607828162045e-05, + "loss": 1.4147, + "step": 3763 + }, + { + "epoch": 0.39, + "learning_rate": 1.5157647314750827e-05, + "loss": 1.4011, + "step": 3764 + }, + { + "epoch": 0.39, + "learning_rate": 1.5154511122304936e-05, + "loss": 1.4309, + "step": 3765 + }, + { + "epoch": 0.39, + "learning_rate": 1.5151374239286993e-05, + "loss": 1.4382, + "step": 3766 + }, + { + "epoch": 0.4, + "learning_rate": 1.5148236666117266e-05, + "loss": 1.405, + "step": 3767 + }, + { + "epoch": 0.4, + "learning_rate": 1.5145098403216104e-05, + "loss": 1.4223, + "step": 3768 + }, + { + "epoch": 0.4, + "learning_rate": 1.5141959451003951e-05, + "loss": 1.4084, + "step": 3769 + }, + { + "epoch": 0.4, + "learning_rate": 1.5138819809901356e-05, + "loss": 1.4063, + "step": 3770 + }, + { + "epoch": 0.4, + "learning_rate": 1.513567948032894e-05, + "loss": 1.3299, + "step": 3771 + }, + { + "epoch": 0.4, + "learning_rate": 1.5132538462707431e-05, + "loss": 1.3901, + "step": 3772 + }, + { + "epoch": 0.4, + "learning_rate": 1.5129396757457646e-05, + "loss": 1.4249, + "step": 3773 + }, + { + "epoch": 0.4, + "learning_rate": 1.512625436500049e-05, + "loss": 1.4087, + "step": 3774 + }, + { + "epoch": 0.4, + "learning_rate": 1.5123111285756964e-05, + "loss": 1.3521, + "step": 3775 + }, + { + "epoch": 0.4, + "learning_rate": 1.5119967520148163e-05, + "loss": 1.4097, + "step": 3776 + }, + { + "epoch": 0.4, + "learning_rate": 1.5116823068595261e-05, + "loss": 1.4871, + "step": 3777 + }, + { + "epoch": 0.4, + "learning_rate": 1.5113677931519543e-05, + "loss": 1.44, + "step": 3778 + }, + { + "epoch": 0.4, + "learning_rate": 1.5110532109342377e-05, + "loss": 1.4518, + "step": 3779 + }, + { + "epoch": 0.4, + "learning_rate": 1.5107385602485214e-05, + "loss": 1.3961, + "step": 3780 + }, + { + "epoch": 0.4, + "learning_rate": 1.5104238411369614e-05, + "loss": 1.4341, + "step": 3781 + }, + { + "epoch": 0.4, + "eval_loss": 1.4642821550369263, + "eval_runtime": 77.3595, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 3781 + }, + { + "epoch": 0.4, + "learning_rate": 1.5101090536417218e-05, + "loss": 1.403, + "step": 3782 + }, + { + "epoch": 0.4, + "learning_rate": 1.5097941978049754e-05, + "loss": 1.4103, + "step": 3783 + }, + { + "epoch": 0.4, + "learning_rate": 1.5094792736689052e-05, + "loss": 1.3478, + "step": 3784 + }, + { + "epoch": 0.4, + "learning_rate": 1.5091642812757035e-05, + "loss": 1.4134, + "step": 3785 + }, + { + "epoch": 0.4, + "learning_rate": 1.5088492206675701e-05, + "loss": 1.4134, + "step": 3786 + }, + { + "epoch": 0.4, + "learning_rate": 1.5085340918867162e-05, + "loss": 1.1494, + "step": 3787 + }, + { + "epoch": 0.4, + "learning_rate": 1.5082188949753598e-05, + "loss": 1.2385, + "step": 3788 + }, + { + "epoch": 0.4, + "learning_rate": 1.5079036299757299e-05, + "loss": 1.4258, + "step": 3789 + }, + { + "epoch": 0.4, + "learning_rate": 1.5075882969300639e-05, + "loss": 1.3781, + "step": 3790 + }, + { + "epoch": 0.4, + "learning_rate": 1.507272895880608e-05, + "loss": 1.5096, + "step": 3791 + }, + { + "epoch": 0.4, + "learning_rate": 1.5069574268696179e-05, + "loss": 1.366, + "step": 3792 + }, + { + "epoch": 0.4, + "learning_rate": 1.5066418899393584e-05, + "loss": 1.3792, + "step": 3793 + }, + { + "epoch": 0.4, + "learning_rate": 1.506326285132104e-05, + "loss": 1.4987, + "step": 3794 + }, + { + "epoch": 0.4, + "learning_rate": 1.5060106124901364e-05, + "loss": 1.445, + "step": 3795 + }, + { + "epoch": 0.4, + "learning_rate": 1.5056948720557482e-05, + "loss": 1.5071, + "step": 3796 + }, + { + "epoch": 0.4, + "learning_rate": 1.505379063871241e-05, + "loss": 1.4029, + "step": 3797 + }, + { + "epoch": 0.4, + "learning_rate": 1.5050631879789244e-05, + "loss": 1.5263, + "step": 3798 + }, + { + "epoch": 0.4, + "learning_rate": 1.5047472444211175e-05, + "loss": 1.3906, + "step": 3799 + }, + { + "epoch": 0.4, + "learning_rate": 1.5044312332401494e-05, + "loss": 1.7352, + "step": 3800 + }, + { + "epoch": 0.4, + "learning_rate": 1.5041151544783565e-05, + "loss": 1.3946, + "step": 3801 + }, + { + "epoch": 0.4, + "learning_rate": 1.5037990081780862e-05, + "loss": 1.3592, + "step": 3802 + }, + { + "epoch": 0.4, + "learning_rate": 1.503482794381693e-05, + "loss": 1.3991, + "step": 3803 + }, + { + "epoch": 0.4, + "learning_rate": 1.5031665131315423e-05, + "loss": 1.4271, + "step": 3804 + }, + { + "epoch": 0.4, + "learning_rate": 1.502850164470007e-05, + "loss": 1.4305, + "step": 3805 + }, + { + "epoch": 0.4, + "learning_rate": 1.5025337484394701e-05, + "loss": 1.4116, + "step": 3806 + }, + { + "epoch": 0.4, + "learning_rate": 1.5022172650823232e-05, + "loss": 1.4242, + "step": 3807 + }, + { + "epoch": 0.4, + "learning_rate": 1.5019007144409667e-05, + "loss": 1.4427, + "step": 3808 + }, + { + "epoch": 0.4, + "learning_rate": 1.5015840965578106e-05, + "loss": 1.3705, + "step": 3809 + }, + { + "epoch": 0.4, + "learning_rate": 1.5012674114752732e-05, + "loss": 1.4498, + "step": 3810 + }, + { + "epoch": 0.4, + "learning_rate": 1.5009506592357822e-05, + "loss": 1.489, + "step": 3811 + }, + { + "epoch": 0.4, + "learning_rate": 1.5006338398817746e-05, + "loss": 1.4801, + "step": 3812 + }, + { + "epoch": 0.4, + "learning_rate": 1.5003169534556956e-05, + "loss": 1.3468, + "step": 3813 + }, + { + "epoch": 0.4, + "learning_rate": 1.5000000000000002e-05, + "loss": 1.4211, + "step": 3814 + }, + { + "epoch": 0.4, + "learning_rate": 1.4996829795571518e-05, + "loss": 1.4683, + "step": 3815 + }, + { + "epoch": 0.4, + "learning_rate": 1.499365892169623e-05, + "loss": 1.4441, + "step": 3816 + }, + { + "epoch": 0.4, + "learning_rate": 1.4990487378798958e-05, + "loss": 1.4368, + "step": 3817 + }, + { + "epoch": 0.4, + "learning_rate": 1.4987315167304602e-05, + "loss": 1.4097, + "step": 3818 + }, + { + "epoch": 0.4, + "learning_rate": 1.4984142287638155e-05, + "loss": 1.4238, + "step": 3819 + }, + { + "epoch": 0.4, + "learning_rate": 1.4980968740224708e-05, + "loss": 1.497, + "step": 3820 + }, + { + "epoch": 0.4, + "learning_rate": 1.4977794525489433e-05, + "loss": 1.3989, + "step": 3821 + }, + { + "epoch": 0.4, + "learning_rate": 1.4974619643857588e-05, + "loss": 1.4415, + "step": 3822 + }, + { + "epoch": 0.4, + "learning_rate": 1.4971444095754533e-05, + "loss": 1.3931, + "step": 3823 + }, + { + "epoch": 0.4, + "learning_rate": 1.4968267881605705e-05, + "loss": 1.3426, + "step": 3824 + }, + { + "epoch": 0.4, + "learning_rate": 1.4965091001836636e-05, + "loss": 1.644, + "step": 3825 + }, + { + "epoch": 0.4, + "learning_rate": 1.4961913456872945e-05, + "loss": 1.3903, + "step": 3826 + }, + { + "epoch": 0.4, + "learning_rate": 1.4958735247140345e-05, + "loss": 1.3764, + "step": 3827 + }, + { + "epoch": 0.4, + "learning_rate": 1.4955556373064632e-05, + "loss": 1.5484, + "step": 3828 + }, + { + "epoch": 0.4, + "learning_rate": 1.4952376835071696e-05, + "loss": 1.5696, + "step": 3829 + }, + { + "epoch": 0.4, + "learning_rate": 1.4949196633587509e-05, + "loss": 1.3844, + "step": 3830 + }, + { + "epoch": 0.4, + "learning_rate": 1.494601576903814e-05, + "loss": 1.3868, + "step": 3831 + }, + { + "epoch": 0.4, + "learning_rate": 1.4942834241849741e-05, + "loss": 1.4229, + "step": 3832 + }, + { + "epoch": 0.4, + "learning_rate": 1.4939652052448557e-05, + "loss": 1.4062, + "step": 3833 + }, + { + "epoch": 0.4, + "learning_rate": 1.4936469201260915e-05, + "loss": 1.3955, + "step": 3834 + }, + { + "epoch": 0.4, + "learning_rate": 1.4933285688713239e-05, + "loss": 1.3959, + "step": 3835 + }, + { + "epoch": 0.4, + "learning_rate": 1.4930101515232038e-05, + "loss": 1.4652, + "step": 3836 + }, + { + "epoch": 0.4, + "learning_rate": 1.4926916681243913e-05, + "loss": 1.5253, + "step": 3837 + }, + { + "epoch": 0.4, + "learning_rate": 1.4923731187175539e-05, + "loss": 1.4694, + "step": 3838 + }, + { + "epoch": 0.4, + "learning_rate": 1.4920545033453702e-05, + "loss": 1.3859, + "step": 3839 + }, + { + "epoch": 0.4, + "learning_rate": 1.4917358220505259e-05, + "loss": 1.4157, + "step": 3840 + }, + { + "epoch": 0.4, + "learning_rate": 1.4914170748757159e-05, + "loss": 1.4491, + "step": 3841 + }, + { + "epoch": 0.4, + "learning_rate": 1.4910982618636445e-05, + "loss": 1.4464, + "step": 3842 + }, + { + "epoch": 0.4, + "learning_rate": 1.4907793830570246e-05, + "loss": 1.3771, + "step": 3843 + }, + { + "epoch": 0.4, + "learning_rate": 1.4904604384985775e-05, + "loss": 1.3673, + "step": 3844 + }, + { + "epoch": 0.4, + "learning_rate": 1.4901414282310334e-05, + "loss": 1.4429, + "step": 3845 + }, + { + "epoch": 0.4, + "learning_rate": 1.4898223522971318e-05, + "loss": 1.4905, + "step": 3846 + }, + { + "epoch": 0.4, + "learning_rate": 1.4895032107396205e-05, + "loss": 1.4039, + "step": 3847 + }, + { + "epoch": 0.4, + "learning_rate": 1.4891840036012566e-05, + "loss": 1.4082, + "step": 3848 + }, + { + "epoch": 0.4, + "learning_rate": 1.4888647309248052e-05, + "loss": 1.3643, + "step": 3849 + }, + { + "epoch": 0.4, + "learning_rate": 1.4885453927530408e-05, + "loss": 1.3116, + "step": 3850 + }, + { + "epoch": 0.4, + "learning_rate": 1.4882259891287467e-05, + "loss": 1.4278, + "step": 3851 + }, + { + "epoch": 0.4, + "learning_rate": 1.4879065200947148e-05, + "loss": 1.3712, + "step": 3852 + }, + { + "epoch": 0.4, + "learning_rate": 1.4875869856937449e-05, + "loss": 1.387, + "step": 3853 + }, + { + "epoch": 0.4, + "learning_rate": 1.4872673859686475e-05, + "loss": 1.5053, + "step": 3854 + }, + { + "epoch": 0.4, + "learning_rate": 1.4869477209622404e-05, + "loss": 1.4427, + "step": 3855 + }, + { + "epoch": 0.4, + "learning_rate": 1.4866279907173502e-05, + "loss": 1.3404, + "step": 3856 + }, + { + "epoch": 0.4, + "learning_rate": 1.4863081952768126e-05, + "loss": 1.3126, + "step": 3857 + }, + { + "epoch": 0.4, + "learning_rate": 1.4859883346834725e-05, + "loss": 1.4588, + "step": 3858 + }, + { + "epoch": 0.4, + "learning_rate": 1.4856684089801822e-05, + "loss": 1.408, + "step": 3859 + }, + { + "epoch": 0.4, + "learning_rate": 1.4853484182098044e-05, + "loss": 1.4356, + "step": 3860 + }, + { + "epoch": 0.4, + "learning_rate": 1.4850283624152088e-05, + "loss": 1.3768, + "step": 3861 + }, + { + "epoch": 0.4, + "learning_rate": 1.4847082416392753e-05, + "loss": 1.4563, + "step": 3862 + }, + { + "epoch": 0.41, + "learning_rate": 1.4843880559248915e-05, + "loss": 1.3648, + "step": 3863 + }, + { + "epoch": 0.41, + "learning_rate": 1.4840678053149542e-05, + "loss": 1.4146, + "step": 3864 + }, + { + "epoch": 0.41, + "learning_rate": 1.4837474898523686e-05, + "loss": 1.4423, + "step": 3865 + }, + { + "epoch": 0.41, + "learning_rate": 1.4834271095800487e-05, + "loss": 1.3351, + "step": 3866 + }, + { + "epoch": 0.41, + "learning_rate": 1.4831066645409178e-05, + "loss": 1.4534, + "step": 3867 + }, + { + "epoch": 0.41, + "learning_rate": 1.4827861547779066e-05, + "loss": 1.4763, + "step": 3868 + }, + { + "epoch": 0.41, + "learning_rate": 1.4824655803339553e-05, + "loss": 1.4019, + "step": 3869 + }, + { + "epoch": 0.41, + "learning_rate": 1.4821449412520132e-05, + "loss": 1.4223, + "step": 3870 + }, + { + "epoch": 0.41, + "learning_rate": 1.4818242375750371e-05, + "loss": 1.4065, + "step": 3871 + }, + { + "epoch": 0.41, + "learning_rate": 1.481503469345993e-05, + "loss": 1.587, + "step": 3872 + }, + { + "epoch": 0.41, + "learning_rate": 1.4811826366078562e-05, + "loss": 1.3746, + "step": 3873 + }, + { + "epoch": 0.41, + "learning_rate": 1.4808617394036096e-05, + "loss": 1.3425, + "step": 3874 + }, + { + "epoch": 0.41, + "learning_rate": 1.480540777776245e-05, + "loss": 0.6637, + "step": 3875 + }, + { + "epoch": 0.41, + "learning_rate": 1.4802197517687634e-05, + "loss": 1.3366, + "step": 3876 + }, + { + "epoch": 0.41, + "learning_rate": 1.479898661424174e-05, + "loss": 1.4033, + "step": 3877 + }, + { + "epoch": 0.41, + "learning_rate": 1.4795775067854947e-05, + "loss": 1.4005, + "step": 3878 + }, + { + "epoch": 0.41, + "learning_rate": 1.4792562878957516e-05, + "loss": 1.3651, + "step": 3879 + }, + { + "epoch": 0.41, + "learning_rate": 1.47893500479798e-05, + "loss": 1.4185, + "step": 3880 + }, + { + "epoch": 0.41, + "learning_rate": 1.4786136575352236e-05, + "loss": 1.4394, + "step": 3881 + }, + { + "epoch": 0.41, + "learning_rate": 1.478292246150535e-05, + "loss": 1.7243, + "step": 3882 + }, + { + "epoch": 0.41, + "learning_rate": 1.4779707706869744e-05, + "loss": 1.3574, + "step": 3883 + }, + { + "epoch": 0.41, + "learning_rate": 1.4776492311876116e-05, + "loss": 1.4031, + "step": 3884 + }, + { + "epoch": 0.41, + "learning_rate": 1.4773276276955248e-05, + "loss": 1.4351, + "step": 3885 + }, + { + "epoch": 0.41, + "learning_rate": 1.4770059602538002e-05, + "loss": 1.3922, + "step": 3886 + }, + { + "epoch": 0.41, + "learning_rate": 1.4766842289055333e-05, + "loss": 1.3374, + "step": 3887 + }, + { + "epoch": 0.41, + "learning_rate": 1.4763624336938278e-05, + "loss": 1.428, + "step": 3888 + }, + { + "epoch": 0.41, + "learning_rate": 1.476040574661796e-05, + "loss": 1.6087, + "step": 3889 + }, + { + "epoch": 0.41, + "learning_rate": 1.4757186518525586e-05, + "loss": 1.4054, + "step": 3890 + }, + { + "epoch": 0.41, + "learning_rate": 1.4753966653092447e-05, + "loss": 1.2595, + "step": 3891 + }, + { + "epoch": 0.41, + "learning_rate": 1.475074615074993e-05, + "loss": 1.4052, + "step": 3892 + }, + { + "epoch": 0.41, + "learning_rate": 1.4747525011929492e-05, + "loss": 1.4296, + "step": 3893 + }, + { + "epoch": 0.41, + "learning_rate": 1.4744303237062689e-05, + "loss": 1.3718, + "step": 3894 + }, + { + "epoch": 0.41, + "learning_rate": 1.4741080826581151e-05, + "loss": 1.4498, + "step": 3895 + }, + { + "epoch": 0.41, + "learning_rate": 1.4737857780916602e-05, + "loss": 1.4029, + "step": 3896 + }, + { + "epoch": 0.41, + "learning_rate": 1.4734634100500846e-05, + "loss": 1.4136, + "step": 3897 + }, + { + "epoch": 0.41, + "learning_rate": 1.4731409785765774e-05, + "loss": 1.348, + "step": 3898 + }, + { + "epoch": 0.41, + "learning_rate": 1.4728184837143355e-05, + "loss": 1.3407, + "step": 3899 + }, + { + "epoch": 0.41, + "learning_rate": 1.472495925506566e-05, + "loss": 1.3737, + "step": 3900 + }, + { + "epoch": 0.41, + "learning_rate": 1.4721733039964826e-05, + "loss": 2.2305, + "step": 3901 + }, + { + "epoch": 0.41, + "learning_rate": 1.4718506192273087e-05, + "loss": 1.4506, + "step": 3902 + }, + { + "epoch": 0.41, + "learning_rate": 1.4715278712422754e-05, + "loss": 1.3657, + "step": 3903 + }, + { + "epoch": 0.41, + "learning_rate": 1.471205060084623e-05, + "loss": 1.4644, + "step": 3904 + }, + { + "epoch": 0.41, + "learning_rate": 1.4708821857976001e-05, + "loss": 1.4823, + "step": 3905 + }, + { + "epoch": 0.41, + "learning_rate": 1.4705592484244628e-05, + "loss": 1.3392, + "step": 3906 + }, + { + "epoch": 0.41, + "learning_rate": 1.4702362480084769e-05, + "loss": 1.3302, + "step": 3907 + }, + { + "epoch": 0.41, + "learning_rate": 1.4699131845929163e-05, + "loss": 1.8952, + "step": 3908 + }, + { + "epoch": 0.41, + "learning_rate": 1.469590058221063e-05, + "loss": 1.4982, + "step": 3909 + }, + { + "epoch": 0.41, + "learning_rate": 1.4692668689362074e-05, + "loss": 1.407, + "step": 3910 + }, + { + "epoch": 0.41, + "learning_rate": 1.4689436167816489e-05, + "loss": 1.3911, + "step": 3911 + }, + { + "epoch": 0.41, + "learning_rate": 1.4686203018006948e-05, + "loss": 1.3421, + "step": 3912 + }, + { + "epoch": 0.41, + "learning_rate": 1.4682969240366612e-05, + "loss": 1.4627, + "step": 3913 + }, + { + "epoch": 0.41, + "learning_rate": 1.4679734835328718e-05, + "loss": 1.394, + "step": 3914 + }, + { + "epoch": 0.41, + "learning_rate": 1.4676499803326603e-05, + "loss": 1.4484, + "step": 3915 + }, + { + "epoch": 0.41, + "learning_rate": 1.4673264144793673e-05, + "loss": 1.4665, + "step": 3916 + }, + { + "epoch": 0.41, + "learning_rate": 1.4670027860163422e-05, + "loss": 1.3191, + "step": 3917 + }, + { + "epoch": 0.41, + "learning_rate": 1.466679094986943e-05, + "loss": 1.4748, + "step": 3918 + }, + { + "epoch": 0.41, + "learning_rate": 1.4663553414345361e-05, + "loss": 1.2467, + "step": 3919 + }, + { + "epoch": 0.41, + "learning_rate": 1.466031525402496e-05, + "loss": 1.4279, + "step": 3920 + }, + { + "epoch": 0.41, + "learning_rate": 1.4657076469342059e-05, + "loss": 1.3822, + "step": 3921 + }, + { + "epoch": 0.41, + "learning_rate": 1.4653837060730566e-05, + "loss": 1.3659, + "step": 3922 + }, + { + "epoch": 0.41, + "learning_rate": 1.465059702862449e-05, + "loss": 1.3663, + "step": 3923 + }, + { + "epoch": 0.41, + "learning_rate": 1.4647356373457902e-05, + "loss": 1.4371, + "step": 3924 + }, + { + "epoch": 0.41, + "learning_rate": 1.4644115095664972e-05, + "loss": 1.3473, + "step": 3925 + }, + { + "epoch": 0.41, + "learning_rate": 1.4640873195679944e-05, + "loss": 1.4797, + "step": 3926 + }, + { + "epoch": 0.41, + "learning_rate": 1.463763067393715e-05, + "loss": 1.3973, + "step": 3927 + }, + { + "epoch": 0.41, + "learning_rate": 1.4634387530871008e-05, + "loss": 1.3899, + "step": 3928 + }, + { + "epoch": 0.41, + "learning_rate": 1.4631143766916015e-05, + "loss": 1.3828, + "step": 3929 + }, + { + "epoch": 0.41, + "learning_rate": 1.4627899382506745e-05, + "loss": 1.4569, + "step": 3930 + }, + { + "epoch": 0.41, + "learning_rate": 1.4624654378077872e-05, + "loss": 1.4011, + "step": 3931 + }, + { + "epoch": 0.41, + "learning_rate": 1.462140875406414e-05, + "loss": 1.3859, + "step": 3932 + }, + { + "epoch": 0.41, + "learning_rate": 1.4618162510900376e-05, + "loss": 1.4518, + "step": 3933 + }, + { + "epoch": 0.41, + "learning_rate": 1.4614915649021493e-05, + "loss": 1.4399, + "step": 3934 + }, + { + "epoch": 0.41, + "learning_rate": 1.4611668168862495e-05, + "loss": 1.4034, + "step": 3935 + }, + { + "epoch": 0.41, + "learning_rate": 1.4608420070858452e-05, + "loss": 1.3919, + "step": 3936 + }, + { + "epoch": 0.41, + "learning_rate": 1.4605171355444528e-05, + "loss": 1.391, + "step": 3937 + }, + { + "epoch": 0.41, + "learning_rate": 1.460192202305597e-05, + "loss": 1.3717, + "step": 3938 + }, + { + "epoch": 0.41, + "learning_rate": 1.4598672074128103e-05, + "loss": 1.4351, + "step": 3939 + }, + { + "epoch": 0.41, + "learning_rate": 1.4595421509096339e-05, + "loss": 1.4202, + "step": 3940 + }, + { + "epoch": 0.41, + "learning_rate": 1.4592170328396165e-05, + "loss": 1.3559, + "step": 3941 + }, + { + "epoch": 0.41, + "learning_rate": 1.458891853246316e-05, + "loss": 1.5878, + "step": 3942 + }, + { + "epoch": 0.41, + "learning_rate": 1.4585666121732982e-05, + "loss": 1.3818, + "step": 3943 + }, + { + "epoch": 0.41, + "learning_rate": 1.4582413096641369e-05, + "loss": 1.4009, + "step": 3944 + }, + { + "epoch": 0.41, + "learning_rate": 1.457915945762414e-05, + "loss": 1.3937, + "step": 3945 + }, + { + "epoch": 0.41, + "learning_rate": 1.4575905205117203e-05, + "loss": 1.381, + "step": 3946 + }, + { + "epoch": 0.41, + "learning_rate": 1.457265033955654e-05, + "loss": 1.3844, + "step": 3947 + }, + { + "epoch": 0.41, + "learning_rate": 1.4569394861378226e-05, + "loss": 1.4059, + "step": 3948 + }, + { + "epoch": 0.41, + "learning_rate": 1.4566138771018403e-05, + "loss": 1.3698, + "step": 3949 + }, + { + "epoch": 0.41, + "learning_rate": 1.4562882068913311e-05, + "loss": 1.4253, + "step": 3950 + }, + { + "epoch": 0.41, + "learning_rate": 1.455962475549926e-05, + "loss": 1.4284, + "step": 3951 + }, + { + "epoch": 0.41, + "learning_rate": 1.4556366831212647e-05, + "loss": 1.4279, + "step": 3952 + }, + { + "epoch": 0.41, + "learning_rate": 1.4553108296489951e-05, + "loss": 1.3072, + "step": 3953 + }, + { + "epoch": 0.41, + "learning_rate": 1.4549849151767731e-05, + "loss": 1.4175, + "step": 3954 + }, + { + "epoch": 0.41, + "learning_rate": 1.4546589397482632e-05, + "loss": 1.5042, + "step": 3955 + }, + { + "epoch": 0.41, + "learning_rate": 1.4543329034071371e-05, + "loss": 1.4363, + "step": 3956 + }, + { + "epoch": 0.41, + "learning_rate": 1.454006806197076e-05, + "loss": 1.4111, + "step": 3957 + }, + { + "epoch": 0.42, + "learning_rate": 1.453680648161768e-05, + "loss": 1.3817, + "step": 3958 + }, + { + "epoch": 0.42, + "learning_rate": 1.45335442934491e-05, + "loss": 1.4689, + "step": 3959 + }, + { + "epoch": 0.42, + "learning_rate": 1.4530281497902072e-05, + "loss": 1.4164, + "step": 3960 + }, + { + "epoch": 0.42, + "learning_rate": 1.4527018095413726e-05, + "loss": 1.3943, + "step": 3961 + }, + { + "epoch": 0.42, + "learning_rate": 1.4523754086421271e-05, + "loss": 1.3851, + "step": 3962 + }, + { + "epoch": 0.42, + "learning_rate": 1.4520489471362003e-05, + "loss": 1.3907, + "step": 3963 + }, + { + "epoch": 0.42, + "learning_rate": 1.4517224250673297e-05, + "loss": 1.2877, + "step": 3964 + }, + { + "epoch": 0.42, + "learning_rate": 1.4513958424792605e-05, + "loss": 1.4696, + "step": 3965 + }, + { + "epoch": 0.42, + "learning_rate": 1.4510691994157471e-05, + "loss": 1.3785, + "step": 3966 + }, + { + "epoch": 0.42, + "learning_rate": 1.4507424959205505e-05, + "loss": 1.3652, + "step": 3967 + }, + { + "epoch": 0.42, + "learning_rate": 1.4504157320374408e-05, + "loss": 1.4198, + "step": 3968 + }, + { + "epoch": 0.42, + "learning_rate": 1.4500889078101962e-05, + "loss": 1.3476, + "step": 3969 + }, + { + "epoch": 0.42, + "learning_rate": 1.4497620232826028e-05, + "loss": 1.4356, + "step": 3970 + }, + { + "epoch": 0.42, + "learning_rate": 1.4494350784984543e-05, + "loss": 1.4993, + "step": 3971 + }, + { + "epoch": 0.42, + "learning_rate": 1.4491080735015533e-05, + "loss": 1.4022, + "step": 3972 + }, + { + "epoch": 0.42, + "learning_rate": 1.44878100833571e-05, + "loss": 1.4074, + "step": 3973 + }, + { + "epoch": 0.42, + "learning_rate": 1.4484538830447423e-05, + "loss": 1.412, + "step": 3974 + }, + { + "epoch": 0.42, + "learning_rate": 1.4481266976724772e-05, + "loss": 1.3872, + "step": 3975 + }, + { + "epoch": 0.42, + "learning_rate": 1.4477994522627485e-05, + "loss": 1.4575, + "step": 3976 + }, + { + "epoch": 0.42, + "learning_rate": 1.4474721468593995e-05, + "loss": 1.3768, + "step": 3977 + }, + { + "epoch": 0.42, + "learning_rate": 1.44714478150628e-05, + "loss": 1.4173, + "step": 3978 + }, + { + "epoch": 0.42, + "learning_rate": 1.4468173562472489e-05, + "loss": 1.3896, + "step": 3979 + }, + { + "epoch": 0.42, + "learning_rate": 1.4464898711261725e-05, + "loss": 1.4535, + "step": 3980 + }, + { + "epoch": 0.42, + "eval_loss": 1.4580057859420776, + "eval_runtime": 77.4537, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 3980 + }, + { + "epoch": 0.42, + "learning_rate": 1.4461623261869258e-05, + "loss": 1.4046, + "step": 3981 + }, + { + "epoch": 0.42, + "learning_rate": 1.445834721473391e-05, + "loss": 1.37, + "step": 3982 + }, + { + "epoch": 0.42, + "learning_rate": 1.4455070570294588e-05, + "loss": 1.4566, + "step": 3983 + }, + { + "epoch": 0.42, + "learning_rate": 1.445179332899028e-05, + "loss": 1.4513, + "step": 3984 + }, + { + "epoch": 0.42, + "learning_rate": 1.4448515491260051e-05, + "loss": 1.3893, + "step": 3985 + }, + { + "epoch": 0.42, + "learning_rate": 1.4445237057543047e-05, + "loss": 1.3955, + "step": 3986 + }, + { + "epoch": 0.42, + "learning_rate": 1.4441958028278493e-05, + "loss": 1.4861, + "step": 3987 + }, + { + "epoch": 0.42, + "learning_rate": 1.4438678403905697e-05, + "loss": 1.4601, + "step": 3988 + }, + { + "epoch": 0.42, + "learning_rate": 1.4435398184864043e-05, + "loss": 1.398, + "step": 3989 + }, + { + "epoch": 0.42, + "learning_rate": 1.4432117371592995e-05, + "loss": 1.4392, + "step": 3990 + }, + { + "epoch": 0.42, + "learning_rate": 1.4428835964532098e-05, + "loss": 1.3772, + "step": 3991 + }, + { + "epoch": 0.42, + "learning_rate": 1.4425553964120979e-05, + "loss": 1.4241, + "step": 3992 + }, + { + "epoch": 0.42, + "learning_rate": 1.4422271370799338e-05, + "loss": 1.3237, + "step": 3993 + }, + { + "epoch": 0.42, + "learning_rate": 1.4418988185006964e-05, + "loss": 1.3813, + "step": 3994 + }, + { + "epoch": 0.42, + "learning_rate": 1.4415704407183709e-05, + "loss": 1.6139, + "step": 3995 + }, + { + "epoch": 0.42, + "learning_rate": 1.4412420037769525e-05, + "loss": 1.4431, + "step": 3996 + }, + { + "epoch": 0.42, + "learning_rate": 1.440913507720443e-05, + "loss": 1.3862, + "step": 3997 + }, + { + "epoch": 0.42, + "learning_rate": 1.4405849525928523e-05, + "loss": 1.3895, + "step": 3998 + }, + { + "epoch": 0.42, + "learning_rate": 1.4402563384381981e-05, + "loss": 1.4068, + "step": 3999 + }, + { + "epoch": 0.42, + "learning_rate": 1.4399276653005072e-05, + "loss": 1.4501, + "step": 4000 + }, + { + "epoch": 0.42, + "learning_rate": 1.4395989332238124e-05, + "loss": 1.3165, + "step": 4001 + }, + { + "epoch": 0.42, + "learning_rate": 1.4392701422521555e-05, + "loss": 1.3783, + "step": 4002 + }, + { + "epoch": 0.42, + "learning_rate": 1.4389412924295865e-05, + "loss": 1.343, + "step": 4003 + }, + { + "epoch": 0.42, + "learning_rate": 1.4386123838001625e-05, + "loss": 1.3456, + "step": 4004 + }, + { + "epoch": 0.42, + "learning_rate": 1.4382834164079486e-05, + "loss": 1.3689, + "step": 4005 + }, + { + "epoch": 0.42, + "learning_rate": 1.4379543902970183e-05, + "loss": 1.3789, + "step": 4006 + }, + { + "epoch": 0.42, + "learning_rate": 1.4376253055114528e-05, + "loss": 1.4912, + "step": 4007 + }, + { + "epoch": 0.42, + "learning_rate": 1.4372961620953407e-05, + "loss": 1.3692, + "step": 4008 + }, + { + "epoch": 0.42, + "learning_rate": 1.436966960092779e-05, + "loss": 1.4901, + "step": 4009 + }, + { + "epoch": 0.42, + "learning_rate": 1.4366376995478717e-05, + "loss": 1.4431, + "step": 4010 + }, + { + "epoch": 0.42, + "learning_rate": 1.436308380504732e-05, + "loss": 1.4626, + "step": 4011 + }, + { + "epoch": 0.42, + "learning_rate": 1.4359790030074798e-05, + "loss": 1.4241, + "step": 4012 + }, + { + "epoch": 0.42, + "learning_rate": 1.4356495671002435e-05, + "loss": 1.3834, + "step": 4013 + }, + { + "epoch": 0.42, + "learning_rate": 1.4353200728271586e-05, + "loss": 1.3626, + "step": 4014 + }, + { + "epoch": 0.42, + "learning_rate": 1.4349905202323692e-05, + "loss": 1.3557, + "step": 4015 + }, + { + "epoch": 0.42, + "learning_rate": 1.434660909360027e-05, + "loss": 1.4077, + "step": 4016 + }, + { + "epoch": 0.42, + "learning_rate": 1.4343312402542911e-05, + "loss": 1.4337, + "step": 4017 + }, + { + "epoch": 0.42, + "learning_rate": 1.4340015129593286e-05, + "loss": 1.419, + "step": 4018 + }, + { + "epoch": 0.42, + "learning_rate": 1.4336717275193148e-05, + "loss": 1.3768, + "step": 4019 + }, + { + "epoch": 0.42, + "learning_rate": 1.4333418839784326e-05, + "loss": 1.383, + "step": 4020 + }, + { + "epoch": 0.42, + "learning_rate": 1.4330119823808719e-05, + "loss": 1.3951, + "step": 4021 + }, + { + "epoch": 0.42, + "learning_rate": 1.4326820227708316e-05, + "loss": 1.3985, + "step": 4022 + }, + { + "epoch": 0.42, + "learning_rate": 1.4323520051925177e-05, + "loss": 1.356, + "step": 4023 + }, + { + "epoch": 0.42, + "learning_rate": 1.4320219296901439e-05, + "loss": 1.5017, + "step": 4024 + }, + { + "epoch": 0.42, + "learning_rate": 1.4316917963079322e-05, + "loss": 1.3594, + "step": 4025 + }, + { + "epoch": 0.42, + "learning_rate": 1.4313616050901114e-05, + "loss": 1.6028, + "step": 4026 + }, + { + "epoch": 0.42, + "learning_rate": 1.4310313560809193e-05, + "loss": 1.4132, + "step": 4027 + }, + { + "epoch": 0.42, + "learning_rate": 1.4307010493246006e-05, + "loss": 1.2969, + "step": 4028 + }, + { + "epoch": 0.42, + "learning_rate": 1.4303706848654073e-05, + "loss": 1.5224, + "step": 4029 + }, + { + "epoch": 0.42, + "learning_rate": 1.4300402627476007e-05, + "loss": 1.3386, + "step": 4030 + }, + { + "epoch": 0.42, + "learning_rate": 1.429709783015448e-05, + "loss": 1.3554, + "step": 4031 + }, + { + "epoch": 0.42, + "learning_rate": 1.4293792457132259e-05, + "loss": 1.3386, + "step": 4032 + }, + { + "epoch": 0.42, + "learning_rate": 1.429048650885217e-05, + "loss": 1.4613, + "step": 4033 + }, + { + "epoch": 0.42, + "learning_rate": 1.4287179985757132e-05, + "loss": 1.3632, + "step": 4034 + }, + { + "epoch": 0.42, + "learning_rate": 1.428387288829013e-05, + "loss": 1.3835, + "step": 4035 + }, + { + "epoch": 0.42, + "learning_rate": 1.4280565216894234e-05, + "loss": 1.3711, + "step": 4036 + }, + { + "epoch": 0.42, + "learning_rate": 1.4277256972012582e-05, + "loss": 1.3385, + "step": 4037 + }, + { + "epoch": 0.42, + "learning_rate": 1.4273948154088395e-05, + "loss": 1.4607, + "step": 4038 + }, + { + "epoch": 0.42, + "learning_rate": 1.4270638763564973e-05, + "loss": 1.4042, + "step": 4039 + }, + { + "epoch": 0.42, + "learning_rate": 1.4267328800885687e-05, + "loss": 1.4006, + "step": 4040 + }, + { + "epoch": 0.42, + "learning_rate": 1.4264018266493987e-05, + "loss": 1.386, + "step": 4041 + }, + { + "epoch": 0.42, + "learning_rate": 1.4260707160833401e-05, + "loss": 1.3487, + "step": 4042 + }, + { + "epoch": 0.42, + "learning_rate": 1.4257395484347529e-05, + "loss": 1.4199, + "step": 4043 + }, + { + "epoch": 0.42, + "learning_rate": 1.4254083237480054e-05, + "loss": 1.3236, + "step": 4044 + }, + { + "epoch": 0.42, + "learning_rate": 1.4250770420674726e-05, + "loss": 1.4056, + "step": 4045 + }, + { + "epoch": 0.42, + "learning_rate": 1.4247457034375387e-05, + "loss": 1.4391, + "step": 4046 + }, + { + "epoch": 0.42, + "learning_rate": 1.4244143079025938e-05, + "loss": 1.3935, + "step": 4047 + }, + { + "epoch": 0.42, + "learning_rate": 1.4240828555070368e-05, + "loss": 1.3623, + "step": 4048 + }, + { + "epoch": 0.42, + "learning_rate": 1.4237513462952733e-05, + "loss": 1.3254, + "step": 4049 + }, + { + "epoch": 0.42, + "learning_rate": 1.4234197803117174e-05, + "loss": 1.4217, + "step": 4050 + }, + { + "epoch": 0.42, + "learning_rate": 1.4230881576007904e-05, + "loss": 1.435, + "step": 4051 + }, + { + "epoch": 0.42, + "learning_rate": 1.422756478206921e-05, + "loss": 1.3687, + "step": 4052 + }, + { + "epoch": 0.43, + "learning_rate": 1.4224247421745464e-05, + "loss": 1.3965, + "step": 4053 + }, + { + "epoch": 0.43, + "learning_rate": 1.4220929495481097e-05, + "loss": 1.4159, + "step": 4054 + }, + { + "epoch": 0.43, + "learning_rate": 1.4217611003720632e-05, + "loss": 1.3632, + "step": 4055 + }, + { + "epoch": 0.43, + "learning_rate": 1.4214291946908661e-05, + "loss": 1.403, + "step": 4056 + }, + { + "epoch": 0.43, + "learning_rate": 1.4210972325489854e-05, + "loss": 1.4093, + "step": 4057 + }, + { + "epoch": 0.43, + "learning_rate": 1.4207652139908952e-05, + "loss": 1.4551, + "step": 4058 + }, + { + "epoch": 0.43, + "learning_rate": 1.4204331390610775e-05, + "loss": 1.4162, + "step": 4059 + }, + { + "epoch": 0.43, + "learning_rate": 1.4201010078040216e-05, + "loss": 1.4492, + "step": 4060 + }, + { + "epoch": 0.43, + "learning_rate": 1.419768820264225e-05, + "loss": 1.4449, + "step": 4061 + }, + { + "epoch": 0.43, + "learning_rate": 1.4194365764861922e-05, + "loss": 1.3382, + "step": 4062 + }, + { + "epoch": 0.43, + "learning_rate": 1.419104276514435e-05, + "loss": 1.3899, + "step": 4063 + }, + { + "epoch": 0.43, + "learning_rate": 1.4187719203934734e-05, + "loss": 1.3513, + "step": 4064 + }, + { + "epoch": 0.43, + "learning_rate": 1.4184395081678344e-05, + "loss": 1.3954, + "step": 4065 + }, + { + "epoch": 0.43, + "learning_rate": 1.4181070398820528e-05, + "loss": 1.442, + "step": 4066 + }, + { + "epoch": 0.43, + "learning_rate": 1.4177745155806708e-05, + "loss": 1.3907, + "step": 4067 + }, + { + "epoch": 0.43, + "learning_rate": 1.417441935308238e-05, + "loss": 1.3757, + "step": 4068 + }, + { + "epoch": 0.43, + "learning_rate": 1.4171092991093118e-05, + "loss": 1.3507, + "step": 4069 + }, + { + "epoch": 0.43, + "learning_rate": 1.4167766070284568e-05, + "loss": 1.4136, + "step": 4070 + }, + { + "epoch": 0.43, + "learning_rate": 1.4164438591102452e-05, + "loss": 1.3835, + "step": 4071 + }, + { + "epoch": 0.43, + "learning_rate": 1.4161110553992565e-05, + "loss": 1.4981, + "step": 4072 + }, + { + "epoch": 0.43, + "learning_rate": 1.415778195940078e-05, + "loss": 1.4387, + "step": 4073 + }, + { + "epoch": 0.43, + "learning_rate": 1.4154452807773047e-05, + "loss": 1.333, + "step": 4074 + }, + { + "epoch": 0.43, + "learning_rate": 1.4151123099555377e-05, + "loss": 1.3558, + "step": 4075 + }, + { + "epoch": 0.43, + "learning_rate": 1.4147792835193875e-05, + "loss": 1.4655, + "step": 4076 + }, + { + "epoch": 0.43, + "learning_rate": 1.4144462015134708e-05, + "loss": 1.4402, + "step": 4077 + }, + { + "epoch": 0.43, + "learning_rate": 1.4141130639824119e-05, + "loss": 1.4227, + "step": 4078 + }, + { + "epoch": 0.43, + "learning_rate": 1.4137798709708423e-05, + "loss": 1.4039, + "step": 4079 + }, + { + "epoch": 0.43, + "learning_rate": 1.4134466225234023e-05, + "loss": 1.3593, + "step": 4080 + }, + { + "epoch": 0.43, + "learning_rate": 1.4131133186847377e-05, + "loss": 1.372, + "step": 4081 + }, + { + "epoch": 0.43, + "learning_rate": 1.412779959499503e-05, + "loss": 1.4487, + "step": 4082 + }, + { + "epoch": 0.43, + "learning_rate": 1.4124465450123599e-05, + "loss": 1.3972, + "step": 4083 + }, + { + "epoch": 0.43, + "learning_rate": 1.4121130752679772e-05, + "loss": 1.3768, + "step": 4084 + }, + { + "epoch": 0.43, + "learning_rate": 1.4117795503110313e-05, + "loss": 1.3827, + "step": 4085 + }, + { + "epoch": 0.43, + "learning_rate": 1.4114459701862062e-05, + "loss": 1.3922, + "step": 4086 + }, + { + "epoch": 0.43, + "learning_rate": 1.4111123349381925e-05, + "loss": 1.3736, + "step": 4087 + }, + { + "epoch": 0.43, + "learning_rate": 1.4107786446116894e-05, + "loss": 1.4338, + "step": 4088 + }, + { + "epoch": 0.43, + "learning_rate": 1.4104448992514023e-05, + "loss": 1.347, + "step": 4089 + }, + { + "epoch": 0.43, + "learning_rate": 1.410111098902045e-05, + "loss": 1.3915, + "step": 4090 + }, + { + "epoch": 0.43, + "learning_rate": 1.4097772436083377e-05, + "loss": 1.3656, + "step": 4091 + }, + { + "epoch": 0.43, + "learning_rate": 1.4094433334150087e-05, + "loss": 1.3461, + "step": 4092 + }, + { + "epoch": 0.43, + "learning_rate": 1.4091093683667934e-05, + "loss": 1.7345, + "step": 4093 + }, + { + "epoch": 0.43, + "learning_rate": 1.4087753485084343e-05, + "loss": 1.6204, + "step": 4094 + }, + { + "epoch": 0.43, + "learning_rate": 1.4084412738846816e-05, + "loss": 1.4074, + "step": 4095 + }, + { + "epoch": 0.43, + "learning_rate": 1.408107144540293e-05, + "loss": 1.3776, + "step": 4096 + }, + { + "epoch": 0.43, + "learning_rate": 1.407772960520033e-05, + "loss": 1.4079, + "step": 4097 + }, + { + "epoch": 0.43, + "learning_rate": 1.4074387218686734e-05, + "loss": 1.4254, + "step": 4098 + }, + { + "epoch": 0.43, + "learning_rate": 1.407104428630994e-05, + "loss": 1.38, + "step": 4099 + }, + { + "epoch": 0.43, + "learning_rate": 1.4067700808517815e-05, + "loss": 1.4175, + "step": 4100 + }, + { + "epoch": 0.43, + "learning_rate": 1.4064356785758298e-05, + "loss": 1.4085, + "step": 4101 + }, + { + "epoch": 0.43, + "learning_rate": 1.4061012218479397e-05, + "loss": 1.4529, + "step": 4102 + }, + { + "epoch": 0.43, + "learning_rate": 1.405766710712921e-05, + "loss": 1.4836, + "step": 4103 + }, + { + "epoch": 0.43, + "learning_rate": 1.4054321452155885e-05, + "loss": 1.3915, + "step": 4104 + }, + { + "epoch": 0.43, + "learning_rate": 1.4050975254007659e-05, + "loss": 1.3044, + "step": 4105 + }, + { + "epoch": 0.43, + "learning_rate": 1.4047628513132835e-05, + "loss": 1.373, + "step": 4106 + }, + { + "epoch": 0.43, + "learning_rate": 1.4044281229979793e-05, + "loss": 1.4266, + "step": 4107 + }, + { + "epoch": 0.43, + "learning_rate": 1.4040933404996977e-05, + "loss": 1.3898, + "step": 4108 + }, + { + "epoch": 0.43, + "learning_rate": 1.4037585038632915e-05, + "loss": 0.9326, + "step": 4109 + }, + { + "epoch": 0.43, + "learning_rate": 1.40342361313362e-05, + "loss": 1.0831, + "step": 4110 + }, + { + "epoch": 0.43, + "learning_rate": 1.40308866835555e-05, + "loss": 1.3898, + "step": 4111 + }, + { + "epoch": 0.43, + "learning_rate": 1.4027536695739554e-05, + "loss": 1.5058, + "step": 4112 + }, + { + "epoch": 0.43, + "learning_rate": 1.4024186168337175e-05, + "loss": 1.3635, + "step": 4113 + }, + { + "epoch": 0.43, + "learning_rate": 1.4020835101797248e-05, + "loss": 1.3871, + "step": 4114 + }, + { + "epoch": 0.43, + "learning_rate": 1.401748349656873e-05, + "loss": 1.3478, + "step": 4115 + }, + { + "epoch": 0.43, + "learning_rate": 1.4014131353100648e-05, + "loss": 1.3356, + "step": 4116 + }, + { + "epoch": 0.43, + "learning_rate": 1.4010778671842107e-05, + "loss": 1.3954, + "step": 4117 + }, + { + "epoch": 0.43, + "learning_rate": 1.4007425453242274e-05, + "loss": 1.3307, + "step": 4118 + }, + { + "epoch": 0.43, + "learning_rate": 1.4004071697750398e-05, + "loss": 1.4508, + "step": 4119 + }, + { + "epoch": 0.43, + "learning_rate": 1.4000717405815799e-05, + "loss": 1.3752, + "step": 4120 + }, + { + "epoch": 0.43, + "learning_rate": 1.399736257788786e-05, + "loss": 1.3654, + "step": 4121 + }, + { + "epoch": 0.43, + "learning_rate": 1.3994007214416046e-05, + "loss": 1.4505, + "step": 4122 + }, + { + "epoch": 0.43, + "learning_rate": 1.3990651315849886e-05, + "loss": 1.4307, + "step": 4123 + }, + { + "epoch": 0.43, + "learning_rate": 1.398729488263899e-05, + "loss": 1.4481, + "step": 4124 + }, + { + "epoch": 0.43, + "learning_rate": 1.3983937915233026e-05, + "loss": 1.4755, + "step": 4125 + }, + { + "epoch": 0.43, + "learning_rate": 1.3980580414081746e-05, + "loss": 1.3402, + "step": 4126 + }, + { + "epoch": 0.43, + "learning_rate": 1.3977222379634969e-05, + "loss": 1.3636, + "step": 4127 + }, + { + "epoch": 0.43, + "learning_rate": 1.3973863812342585e-05, + "loss": 1.4165, + "step": 4128 + }, + { + "epoch": 0.43, + "learning_rate": 1.3970504712654554e-05, + "loss": 1.3832, + "step": 4129 + }, + { + "epoch": 0.43, + "learning_rate": 1.3967145081020912e-05, + "loss": 1.4236, + "step": 4130 + }, + { + "epoch": 0.43, + "learning_rate": 1.396378491789176e-05, + "loss": 1.5022, + "step": 4131 + }, + { + "epoch": 0.43, + "learning_rate": 1.3960424223717276e-05, + "loss": 1.3806, + "step": 4132 + }, + { + "epoch": 0.43, + "learning_rate": 1.3957062998947707e-05, + "loss": 1.3649, + "step": 4133 + }, + { + "epoch": 0.43, + "learning_rate": 1.3953701244033368e-05, + "loss": 1.3787, + "step": 4134 + }, + { + "epoch": 0.43, + "learning_rate": 1.395033895942465e-05, + "loss": 1.3551, + "step": 4135 + }, + { + "epoch": 0.43, + "learning_rate": 1.394697614557201e-05, + "loss": 1.3881, + "step": 4136 + }, + { + "epoch": 0.43, + "learning_rate": 1.3943612802925983e-05, + "loss": 1.4848, + "step": 4137 + }, + { + "epoch": 0.43, + "learning_rate": 1.3940248931937169e-05, + "loss": 1.425, + "step": 4138 + }, + { + "epoch": 0.43, + "learning_rate": 1.3936884533056238e-05, + "loss": 1.4054, + "step": 4139 + }, + { + "epoch": 0.43, + "learning_rate": 1.3933519606733934e-05, + "loss": 1.4028, + "step": 4140 + }, + { + "epoch": 0.43, + "learning_rate": 1.3930154153421072e-05, + "loss": 1.4439, + "step": 4141 + }, + { + "epoch": 0.43, + "learning_rate": 1.3926788173568536e-05, + "loss": 1.4482, + "step": 4142 + }, + { + "epoch": 0.43, + "learning_rate": 1.392342166762728e-05, + "loss": 1.393, + "step": 4143 + }, + { + "epoch": 0.43, + "learning_rate": 1.3920054636048328e-05, + "loss": 1.4097, + "step": 4144 + }, + { + "epoch": 0.43, + "learning_rate": 1.391668707928278e-05, + "loss": 1.5142, + "step": 4145 + }, + { + "epoch": 0.43, + "learning_rate": 1.3913318997781797e-05, + "loss": 1.4118, + "step": 4146 + }, + { + "epoch": 0.43, + "learning_rate": 1.390995039199662e-05, + "loss": 1.4067, + "step": 4147 + }, + { + "epoch": 0.43, + "learning_rate": 1.3906581262378552e-05, + "loss": 1.5214, + "step": 4148 + }, + { + "epoch": 0.44, + "learning_rate": 1.3903211609378971e-05, + "loss": 1.3618, + "step": 4149 + }, + { + "epoch": 0.44, + "learning_rate": 1.3899841433449327e-05, + "loss": 1.338, + "step": 4150 + }, + { + "epoch": 0.44, + "learning_rate": 1.3896470735041132e-05, + "loss": 1.3901, + "step": 4151 + }, + { + "epoch": 0.44, + "learning_rate": 1.3893099514605971e-05, + "loss": 1.4502, + "step": 4152 + }, + { + "epoch": 0.44, + "learning_rate": 1.388972777259551e-05, + "loss": 1.4141, + "step": 4153 + }, + { + "epoch": 0.44, + "learning_rate": 1.3886355509461471e-05, + "loss": 1.3876, + "step": 4154 + }, + { + "epoch": 0.44, + "learning_rate": 1.388298272565565e-05, + "loss": 1.4275, + "step": 4155 + }, + { + "epoch": 0.44, + "learning_rate": 1.3879609421629909e-05, + "loss": 1.3559, + "step": 4156 + }, + { + "epoch": 0.44, + "learning_rate": 1.3876235597836195e-05, + "loss": 1.416, + "step": 4157 + }, + { + "epoch": 0.44, + "learning_rate": 1.3872861254726506e-05, + "loss": 1.437, + "step": 4158 + }, + { + "epoch": 0.44, + "learning_rate": 1.3869486392752918e-05, + "loss": 1.3794, + "step": 4159 + }, + { + "epoch": 0.44, + "learning_rate": 1.3866111012367577e-05, + "loss": 1.4094, + "step": 4160 + }, + { + "epoch": 0.44, + "learning_rate": 1.3862735114022694e-05, + "loss": 1.3957, + "step": 4161 + }, + { + "epoch": 0.44, + "learning_rate": 1.3859358698170559e-05, + "loss": 1.3582, + "step": 4162 + }, + { + "epoch": 0.44, + "learning_rate": 1.3855981765263523e-05, + "loss": 1.4159, + "step": 4163 + }, + { + "epoch": 0.44, + "learning_rate": 1.3852604315754e-05, + "loss": 1.3498, + "step": 4164 + }, + { + "epoch": 0.44, + "learning_rate": 1.3849226350094491e-05, + "loss": 1.3951, + "step": 4165 + }, + { + "epoch": 0.44, + "learning_rate": 1.3845847868737559e-05, + "loss": 1.4087, + "step": 4166 + }, + { + "epoch": 0.44, + "learning_rate": 1.3842468872135821e-05, + "loss": 1.4318, + "step": 4167 + }, + { + "epoch": 0.44, + "learning_rate": 1.3839089360741989e-05, + "loss": 1.4174, + "step": 4168 + }, + { + "epoch": 0.44, + "learning_rate": 1.3835709335008822e-05, + "loss": 1.4499, + "step": 4169 + }, + { + "epoch": 0.44, + "learning_rate": 1.383232879538916e-05, + "loss": 1.3554, + "step": 4170 + }, + { + "epoch": 0.44, + "learning_rate": 1.3828947742335905e-05, + "loss": 1.3873, + "step": 4171 + }, + { + "epoch": 0.44, + "learning_rate": 1.382556617630204e-05, + "loss": 1.3804, + "step": 4172 + }, + { + "epoch": 0.44, + "learning_rate": 1.3822184097740598e-05, + "loss": 1.3856, + "step": 4173 + }, + { + "epoch": 0.44, + "learning_rate": 1.3818801507104697e-05, + "loss": 1.3901, + "step": 4174 + }, + { + "epoch": 0.44, + "learning_rate": 1.381541840484751e-05, + "loss": 1.3714, + "step": 4175 + }, + { + "epoch": 0.44, + "learning_rate": 1.3812034791422297e-05, + "loss": 1.4945, + "step": 4176 + }, + { + "epoch": 0.44, + "learning_rate": 1.3808650667282368e-05, + "loss": 1.429, + "step": 4177 + }, + { + "epoch": 0.44, + "learning_rate": 1.3805266032881108e-05, + "loss": 1.3903, + "step": 4178 + }, + { + "epoch": 0.44, + "learning_rate": 1.3801880888671972e-05, + "loss": 1.4799, + "step": 4179 + }, + { + "epoch": 0.44, + "eval_loss": 1.4521424770355225, + "eval_runtime": 77.3596, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 4179 + }, + { + "epoch": 0.44, + "learning_rate": 1.3798495235108484e-05, + "loss": 1.3912, + "step": 4180 + }, + { + "epoch": 0.44, + "learning_rate": 1.3795109072644235e-05, + "loss": 1.5837, + "step": 4181 + }, + { + "epoch": 0.44, + "learning_rate": 1.379172240173288e-05, + "loss": 1.4255, + "step": 4182 + }, + { + "epoch": 0.44, + "learning_rate": 1.3788335222828148e-05, + "loss": 1.4666, + "step": 4183 + }, + { + "epoch": 0.44, + "learning_rate": 1.3784947536383837e-05, + "loss": 1.3964, + "step": 4184 + }, + { + "epoch": 0.44, + "learning_rate": 1.3781559342853807e-05, + "loss": 1.336, + "step": 4185 + }, + { + "epoch": 0.44, + "learning_rate": 1.3778170642691986e-05, + "loss": 1.4352, + "step": 4186 + }, + { + "epoch": 0.44, + "learning_rate": 1.377478143635238e-05, + "loss": 1.3262, + "step": 4187 + }, + { + "epoch": 0.44, + "learning_rate": 1.3771391724289047e-05, + "loss": 1.3969, + "step": 4188 + }, + { + "epoch": 0.44, + "learning_rate": 1.376800150695613e-05, + "loss": 1.4211, + "step": 4189 + }, + { + "epoch": 0.44, + "learning_rate": 1.3764610784807824e-05, + "loss": 1.4338, + "step": 4190 + }, + { + "epoch": 0.44, + "learning_rate": 1.3761219558298403e-05, + "loss": 1.3815, + "step": 4191 + }, + { + "epoch": 0.44, + "learning_rate": 1.3757827827882203e-05, + "loss": 1.3805, + "step": 4192 + }, + { + "epoch": 0.44, + "learning_rate": 1.3754435594013627e-05, + "loss": 1.4071, + "step": 4193 + }, + { + "epoch": 0.44, + "learning_rate": 1.3751042857147145e-05, + "loss": 1.343, + "step": 4194 + }, + { + "epoch": 0.44, + "learning_rate": 1.3747649617737304e-05, + "loss": 1.4129, + "step": 4195 + }, + { + "epoch": 0.44, + "learning_rate": 1.3744255876238708e-05, + "loss": 1.3939, + "step": 4196 + }, + { + "epoch": 0.44, + "learning_rate": 1.3740861633106029e-05, + "loss": 1.3963, + "step": 4197 + }, + { + "epoch": 0.44, + "learning_rate": 1.3737466888794008e-05, + "loss": 1.5181, + "step": 4198 + }, + { + "epoch": 0.44, + "learning_rate": 1.3734071643757456e-05, + "loss": 1.4397, + "step": 4199 + }, + { + "epoch": 0.44, + "learning_rate": 1.373067589845125e-05, + "loss": 1.6293, + "step": 4200 + }, + { + "epoch": 0.44, + "learning_rate": 1.3727279653330328e-05, + "loss": 1.3498, + "step": 4201 + }, + { + "epoch": 0.44, + "learning_rate": 1.37238829088497e-05, + "loss": 1.4509, + "step": 4202 + }, + { + "epoch": 0.44, + "learning_rate": 1.3720485665464446e-05, + "loss": 1.4477, + "step": 4203 + }, + { + "epoch": 0.44, + "learning_rate": 1.3717087923629709e-05, + "loss": 1.4399, + "step": 4204 + }, + { + "epoch": 0.44, + "learning_rate": 1.3713689683800695e-05, + "loss": 1.4417, + "step": 4205 + }, + { + "epoch": 0.44, + "learning_rate": 1.3710290946432685e-05, + "loss": 1.3957, + "step": 4206 + }, + { + "epoch": 0.44, + "learning_rate": 1.3706891711981021e-05, + "loss": 1.4476, + "step": 4207 + }, + { + "epoch": 0.44, + "learning_rate": 1.3703491980901113e-05, + "loss": 1.3894, + "step": 4208 + }, + { + "epoch": 0.44, + "learning_rate": 1.3700091753648437e-05, + "loss": 1.4745, + "step": 4209 + }, + { + "epoch": 0.44, + "learning_rate": 1.369669103067854e-05, + "loss": 1.4038, + "step": 4210 + }, + { + "epoch": 0.44, + "learning_rate": 1.3693289812447023e-05, + "loss": 1.4151, + "step": 4211 + }, + { + "epoch": 0.44, + "learning_rate": 1.3689888099409572e-05, + "loss": 1.4214, + "step": 4212 + }, + { + "epoch": 0.44, + "learning_rate": 1.368648589202192e-05, + "loss": 1.4287, + "step": 4213 + }, + { + "epoch": 0.44, + "learning_rate": 1.3683083190739883e-05, + "loss": 1.345, + "step": 4214 + }, + { + "epoch": 0.44, + "learning_rate": 1.367967999601933e-05, + "loss": 1.3022, + "step": 4215 + }, + { + "epoch": 0.44, + "learning_rate": 1.3676276308316207e-05, + "loss": 1.3971, + "step": 4216 + }, + { + "epoch": 0.44, + "learning_rate": 1.3672872128086514e-05, + "loss": 1.3335, + "step": 4217 + }, + { + "epoch": 0.44, + "learning_rate": 1.366946745578633e-05, + "loss": 1.3988, + "step": 4218 + }, + { + "epoch": 0.44, + "learning_rate": 1.366606229187179e-05, + "loss": 1.4508, + "step": 4219 + }, + { + "epoch": 0.44, + "learning_rate": 1.3662656636799099e-05, + "loss": 1.3814, + "step": 4220 + }, + { + "epoch": 0.44, + "learning_rate": 1.3659250491024527e-05, + "loss": 1.4128, + "step": 4221 + }, + { + "epoch": 0.44, + "learning_rate": 1.3655843855004411e-05, + "loss": 1.3893, + "step": 4222 + }, + { + "epoch": 0.44, + "learning_rate": 1.3652436729195154e-05, + "loss": 1.2551, + "step": 4223 + }, + { + "epoch": 0.44, + "learning_rate": 1.3649029114053219e-05, + "loss": 1.4386, + "step": 4224 + }, + { + "epoch": 0.44, + "learning_rate": 1.364562101003514e-05, + "loss": 1.4028, + "step": 4225 + }, + { + "epoch": 0.44, + "learning_rate": 1.364221241759752e-05, + "loss": 1.4351, + "step": 4226 + }, + { + "epoch": 0.44, + "learning_rate": 1.363880333719702e-05, + "loss": 1.3941, + "step": 4227 + }, + { + "epoch": 0.44, + "learning_rate": 1.3635393769290368e-05, + "loss": 1.3879, + "step": 4228 + }, + { + "epoch": 0.44, + "learning_rate": 1.3631983714334358e-05, + "loss": 1.3773, + "step": 4229 + }, + { + "epoch": 0.44, + "learning_rate": 1.3628573172785853e-05, + "loss": 1.3679, + "step": 4230 + }, + { + "epoch": 0.44, + "learning_rate": 1.3625162145101776e-05, + "loss": 1.3705, + "step": 4231 + }, + { + "epoch": 0.44, + "learning_rate": 1.3621750631739114e-05, + "loss": 1.8157, + "step": 4232 + }, + { + "epoch": 0.44, + "learning_rate": 1.3618338633154928e-05, + "loss": 1.4056, + "step": 4233 + }, + { + "epoch": 0.44, + "learning_rate": 1.3614926149806334e-05, + "loss": 1.3716, + "step": 4234 + }, + { + "epoch": 0.44, + "learning_rate": 1.3611513182150523e-05, + "loss": 1.3766, + "step": 4235 + }, + { + "epoch": 0.44, + "learning_rate": 1.3608099730644733e-05, + "loss": 1.41, + "step": 4236 + }, + { + "epoch": 0.44, + "learning_rate": 1.3604685795746291e-05, + "loss": 1.421, + "step": 4237 + }, + { + "epoch": 0.44, + "learning_rate": 1.360127137791257e-05, + "loss": 1.3679, + "step": 4238 + }, + { + "epoch": 0.44, + "learning_rate": 1.3597856477601018e-05, + "loss": 1.4615, + "step": 4239 + }, + { + "epoch": 0.44, + "learning_rate": 1.359444109526914e-05, + "loss": 1.3418, + "step": 4240 + }, + { + "epoch": 0.44, + "learning_rate": 1.3591025231374513e-05, + "loss": 1.3631, + "step": 4241 + }, + { + "epoch": 0.44, + "learning_rate": 1.3587608886374772e-05, + "loss": 1.3802, + "step": 4242 + }, + { + "epoch": 0.44, + "learning_rate": 1.3584192060727622e-05, + "loss": 1.4156, + "step": 4243 + }, + { + "epoch": 0.45, + "learning_rate": 1.3580774754890827e-05, + "loss": 1.4161, + "step": 4244 + }, + { + "epoch": 0.45, + "learning_rate": 1.3577356969322222e-05, + "loss": 1.3535, + "step": 4245 + }, + { + "epoch": 0.45, + "learning_rate": 1.3573938704479699e-05, + "loss": 1.3859, + "step": 4246 + }, + { + "epoch": 0.45, + "learning_rate": 1.357051996082122e-05, + "loss": 1.3595, + "step": 4247 + }, + { + "epoch": 0.45, + "learning_rate": 1.3567100738804806e-05, + "loss": 1.4191, + "step": 4248 + }, + { + "epoch": 0.45, + "learning_rate": 1.3563681038888548e-05, + "loss": 1.4186, + "step": 4249 + }, + { + "epoch": 0.45, + "learning_rate": 1.3560260861530596e-05, + "loss": 1.43, + "step": 4250 + }, + { + "epoch": 0.45, + "learning_rate": 1.3556840207189168e-05, + "loss": 1.4139, + "step": 4251 + }, + { + "epoch": 0.45, + "learning_rate": 1.3553419076322539e-05, + "loss": 1.4005, + "step": 4252 + }, + { + "epoch": 0.45, + "learning_rate": 1.3549997469389058e-05, + "loss": 1.3468, + "step": 4253 + }, + { + "epoch": 0.45, + "learning_rate": 1.3546575386847132e-05, + "loss": 1.3756, + "step": 4254 + }, + { + "epoch": 0.45, + "learning_rate": 1.3543152829155226e-05, + "loss": 1.4063, + "step": 4255 + }, + { + "epoch": 0.45, + "learning_rate": 1.3539729796771884e-05, + "loss": 1.4666, + "step": 4256 + }, + { + "epoch": 0.45, + "learning_rate": 1.3536306290155694e-05, + "loss": 1.4212, + "step": 4257 + }, + { + "epoch": 0.45, + "learning_rate": 1.3532882309765332e-05, + "loss": 1.4883, + "step": 4258 + }, + { + "epoch": 0.45, + "learning_rate": 1.3529457856059507e-05, + "loss": 1.6641, + "step": 4259 + }, + { + "epoch": 0.45, + "learning_rate": 1.3526032929497022e-05, + "loss": 1.3659, + "step": 4260 + }, + { + "epoch": 0.45, + "learning_rate": 1.3522607530536717e-05, + "loss": 1.5945, + "step": 4261 + }, + { + "epoch": 0.45, + "learning_rate": 1.351918165963752e-05, + "loss": 1.3643, + "step": 4262 + }, + { + "epoch": 0.45, + "learning_rate": 1.3515755317258397e-05, + "loss": 1.3442, + "step": 4263 + }, + { + "epoch": 0.45, + "learning_rate": 1.3512328503858398e-05, + "loss": 1.3982, + "step": 4264 + }, + { + "epoch": 0.45, + "learning_rate": 1.3508901219896624e-05, + "loss": 1.4985, + "step": 4265 + }, + { + "epoch": 0.45, + "learning_rate": 1.350547346583225e-05, + "loss": 1.3319, + "step": 4266 + }, + { + "epoch": 0.45, + "learning_rate": 1.3502045242124497e-05, + "loss": 1.3961, + "step": 4267 + }, + { + "epoch": 0.45, + "learning_rate": 1.3498616549232665e-05, + "loss": 1.4565, + "step": 4268 + }, + { + "epoch": 0.45, + "learning_rate": 1.349518738761611e-05, + "loss": 1.375, + "step": 4269 + }, + { + "epoch": 0.45, + "learning_rate": 1.3491757757734254e-05, + "loss": 1.3005, + "step": 4270 + }, + { + "epoch": 0.45, + "learning_rate": 1.348832766004657e-05, + "loss": 1.3185, + "step": 4271 + }, + { + "epoch": 0.45, + "learning_rate": 1.3484897095012613e-05, + "loss": 1.4449, + "step": 4272 + }, + { + "epoch": 0.45, + "learning_rate": 1.3481466063091988e-05, + "loss": 1.3587, + "step": 4273 + }, + { + "epoch": 0.45, + "learning_rate": 1.3478034564744362e-05, + "loss": 1.3844, + "step": 4274 + }, + { + "epoch": 0.45, + "learning_rate": 1.3474602600429468e-05, + "loss": 1.4471, + "step": 4275 + }, + { + "epoch": 0.45, + "learning_rate": 1.3471170170607105e-05, + "loss": 1.4686, + "step": 4276 + }, + { + "epoch": 0.45, + "learning_rate": 1.3467737275737127e-05, + "loss": 1.312, + "step": 4277 + }, + { + "epoch": 0.45, + "learning_rate": 1.3464303916279453e-05, + "loss": 1.407, + "step": 4278 + }, + { + "epoch": 0.45, + "learning_rate": 1.346087009269407e-05, + "loss": 1.364, + "step": 4279 + }, + { + "epoch": 0.45, + "learning_rate": 1.3457435805441016e-05, + "loss": 1.4103, + "step": 4280 + }, + { + "epoch": 0.45, + "learning_rate": 1.3454001054980403e-05, + "loss": 1.4243, + "step": 4281 + }, + { + "epoch": 0.45, + "learning_rate": 1.3450565841772392e-05, + "loss": 1.3879, + "step": 4282 + }, + { + "epoch": 0.45, + "learning_rate": 1.344713016627722e-05, + "loss": 1.4688, + "step": 4283 + }, + { + "epoch": 0.45, + "learning_rate": 1.3443694028955176e-05, + "loss": 1.3983, + "step": 4284 + }, + { + "epoch": 0.45, + "learning_rate": 1.344025743026662e-05, + "loss": 1.4316, + "step": 4285 + }, + { + "epoch": 0.45, + "learning_rate": 1.3436820370671956e-05, + "loss": 1.3643, + "step": 4286 + }, + { + "epoch": 0.45, + "learning_rate": 1.3433382850631673e-05, + "loss": 1.4566, + "step": 4287 + }, + { + "epoch": 0.45, + "learning_rate": 1.3429944870606301e-05, + "loss": 1.1263, + "step": 4288 + }, + { + "epoch": 0.45, + "learning_rate": 1.3426506431056452e-05, + "loss": 1.2463, + "step": 4289 + }, + { + "epoch": 0.45, + "learning_rate": 1.342306753244278e-05, + "loss": 1.4753, + "step": 4290 + }, + { + "epoch": 0.45, + "learning_rate": 1.3419628175226012e-05, + "loss": 1.3789, + "step": 4291 + }, + { + "epoch": 0.45, + "learning_rate": 1.3416188359866932e-05, + "loss": 1.3906, + "step": 4292 + }, + { + "epoch": 0.45, + "learning_rate": 1.3412748086826389e-05, + "loss": 1.3995, + "step": 4293 + }, + { + "epoch": 0.45, + "learning_rate": 1.3409307356565288e-05, + "loss": 1.4906, + "step": 4294 + }, + { + "epoch": 0.45, + "learning_rate": 1.3405866169544602e-05, + "loss": 1.3951, + "step": 4295 + }, + { + "epoch": 0.45, + "learning_rate": 1.3402424526225359e-05, + "loss": 1.3753, + "step": 4296 + }, + { + "epoch": 0.45, + "learning_rate": 1.3398982427068654e-05, + "loss": 1.3686, + "step": 4297 + }, + { + "epoch": 0.45, + "learning_rate": 1.3395539872535636e-05, + "loss": 1.3612, + "step": 4298 + }, + { + "epoch": 0.45, + "learning_rate": 1.3392096863087522e-05, + "loss": 1.4043, + "step": 4299 + }, + { + "epoch": 0.45, + "learning_rate": 1.3388653399185585e-05, + "loss": 1.4068, + "step": 4300 + }, + { + "epoch": 0.45, + "learning_rate": 1.338520948129116e-05, + "loss": 1.4066, + "step": 4301 + }, + { + "epoch": 0.45, + "learning_rate": 1.3381765109865646e-05, + "loss": 1.4944, + "step": 4302 + }, + { + "epoch": 0.45, + "learning_rate": 1.3378320285370496e-05, + "loss": 1.3575, + "step": 4303 + }, + { + "epoch": 0.45, + "learning_rate": 1.3374875008267236e-05, + "loss": 1.3807, + "step": 4304 + }, + { + "epoch": 0.45, + "learning_rate": 1.3371429279017437e-05, + "loss": 1.4389, + "step": 4305 + }, + { + "epoch": 0.45, + "learning_rate": 1.3367983098082739e-05, + "loss": 1.4858, + "step": 4306 + }, + { + "epoch": 0.45, + "learning_rate": 1.3364536465924844e-05, + "loss": 1.3282, + "step": 4307 + }, + { + "epoch": 0.45, + "learning_rate": 1.3361089383005515e-05, + "loss": 1.4306, + "step": 4308 + }, + { + "epoch": 0.45, + "learning_rate": 1.3357641849786566e-05, + "loss": 1.3892, + "step": 4309 + }, + { + "epoch": 0.45, + "learning_rate": 1.3354193866729883e-05, + "loss": 1.3621, + "step": 4310 + }, + { + "epoch": 0.45, + "learning_rate": 1.3350745434297401e-05, + "loss": 1.3476, + "step": 4311 + }, + { + "epoch": 0.45, + "learning_rate": 1.334729655295113e-05, + "loss": 1.4477, + "step": 4312 + }, + { + "epoch": 0.45, + "learning_rate": 1.3343847223153123e-05, + "loss": 1.3585, + "step": 4313 + }, + { + "epoch": 0.45, + "learning_rate": 1.334039744536551e-05, + "loss": 1.3616, + "step": 4314 + }, + { + "epoch": 0.45, + "learning_rate": 1.3336947220050462e-05, + "loss": 1.3579, + "step": 4315 + }, + { + "epoch": 0.45, + "learning_rate": 1.3333496547670232e-05, + "loss": 1.3557, + "step": 4316 + }, + { + "epoch": 0.45, + "learning_rate": 1.3330045428687113e-05, + "loss": 1.4443, + "step": 4317 + }, + { + "epoch": 0.45, + "learning_rate": 1.332659386356347e-05, + "loss": 1.3621, + "step": 4318 + }, + { + "epoch": 0.45, + "learning_rate": 1.3323141852761726e-05, + "loss": 1.3295, + "step": 4319 + }, + { + "epoch": 0.45, + "learning_rate": 1.3319689396744358e-05, + "loss": 1.4187, + "step": 4320 + }, + { + "epoch": 0.45, + "learning_rate": 1.3316236495973905e-05, + "loss": 1.335, + "step": 4321 + }, + { + "epoch": 0.45, + "learning_rate": 1.331278315091297e-05, + "loss": 1.4382, + "step": 4322 + }, + { + "epoch": 0.45, + "learning_rate": 1.3309329362024212e-05, + "loss": 1.4244, + "step": 4323 + }, + { + "epoch": 0.45, + "learning_rate": 1.3305875129770351e-05, + "loss": 1.488, + "step": 4324 + }, + { + "epoch": 0.45, + "learning_rate": 1.3302420454614165e-05, + "loss": 1.3369, + "step": 4325 + }, + { + "epoch": 0.45, + "learning_rate": 1.3298965337018487e-05, + "loss": 1.3648, + "step": 4326 + }, + { + "epoch": 0.45, + "learning_rate": 1.3295509777446226e-05, + "loss": 1.3924, + "step": 4327 + }, + { + "epoch": 0.45, + "learning_rate": 1.3292053776360324e-05, + "loss": 1.3789, + "step": 4328 + }, + { + "epoch": 0.45, + "learning_rate": 1.3288597334223802e-05, + "loss": 1.3902, + "step": 4329 + }, + { + "epoch": 0.45, + "learning_rate": 1.3285140451499735e-05, + "loss": 1.4057, + "step": 4330 + }, + { + "epoch": 0.45, + "learning_rate": 1.328168312865126e-05, + "loss": 1.4536, + "step": 4331 + }, + { + "epoch": 0.45, + "learning_rate": 1.3278225366141565e-05, + "loss": 1.3075, + "step": 4332 + }, + { + "epoch": 0.45, + "learning_rate": 1.3274767164433901e-05, + "loss": 1.4579, + "step": 4333 + }, + { + "epoch": 0.45, + "learning_rate": 1.3271308523991579e-05, + "loss": 1.3906, + "step": 4334 + }, + { + "epoch": 0.45, + "learning_rate": 1.326784944527797e-05, + "loss": 1.3992, + "step": 4335 + }, + { + "epoch": 0.45, + "learning_rate": 1.3264389928756498e-05, + "loss": 1.4001, + "step": 4336 + }, + { + "epoch": 0.45, + "learning_rate": 1.3260929974890653e-05, + "loss": 1.2948, + "step": 4337 + }, + { + "epoch": 0.45, + "learning_rate": 1.3257469584143976e-05, + "loss": 1.4041, + "step": 4338 + }, + { + "epoch": 0.46, + "learning_rate": 1.3254008756980076e-05, + "loss": 1.5035, + "step": 4339 + }, + { + "epoch": 0.46, + "learning_rate": 1.3250547493862609e-05, + "loss": 1.4867, + "step": 4340 + }, + { + "epoch": 0.46, + "learning_rate": 1.3247085795255302e-05, + "loss": 1.3612, + "step": 4341 + }, + { + "epoch": 0.46, + "learning_rate": 1.3243623661621925e-05, + "loss": 1.4193, + "step": 4342 + }, + { + "epoch": 0.46, + "learning_rate": 1.3240161093426322e-05, + "loss": 1.3596, + "step": 4343 + }, + { + "epoch": 0.46, + "learning_rate": 1.3236698091132383e-05, + "loss": 1.4448, + "step": 4344 + }, + { + "epoch": 0.46, + "learning_rate": 1.3233234655204066e-05, + "loss": 1.3924, + "step": 4345 + }, + { + "epoch": 0.46, + "learning_rate": 1.322977078610538e-05, + "loss": 1.3552, + "step": 4346 + }, + { + "epoch": 0.46, + "learning_rate": 1.3226306484300395e-05, + "loss": 1.3949, + "step": 4347 + }, + { + "epoch": 0.46, + "learning_rate": 1.322284175025324e-05, + "loss": 1.399, + "step": 4348 + }, + { + "epoch": 0.46, + "learning_rate": 1.3219376584428094e-05, + "loss": 1.4755, + "step": 4349 + }, + { + "epoch": 0.46, + "learning_rate": 1.3215910987289212e-05, + "loss": 1.3877, + "step": 4350 + }, + { + "epoch": 0.46, + "learning_rate": 1.3212444959300882e-05, + "loss": 1.3916, + "step": 4351 + }, + { + "epoch": 0.46, + "learning_rate": 1.3208978500927472e-05, + "loss": 1.3462, + "step": 4352 + }, + { + "epoch": 0.46, + "learning_rate": 1.3205511612633392e-05, + "loss": 1.3834, + "step": 4353 + }, + { + "epoch": 0.46, + "learning_rate": 1.3202044294883123e-05, + "loss": 1.3843, + "step": 4354 + }, + { + "epoch": 0.46, + "learning_rate": 1.3198576548141189e-05, + "loss": 1.2439, + "step": 4355 + }, + { + "epoch": 0.46, + "learning_rate": 1.3195108372872181e-05, + "loss": 1.4106, + "step": 4356 + }, + { + "epoch": 0.46, + "learning_rate": 1.3191639769540746e-05, + "loss": 1.4417, + "step": 4357 + }, + { + "epoch": 0.46, + "learning_rate": 1.3188170738611596e-05, + "loss": 1.4393, + "step": 4358 + }, + { + "epoch": 0.46, + "learning_rate": 1.3184701280549476e-05, + "loss": 1.4616, + "step": 4359 + }, + { + "epoch": 0.46, + "learning_rate": 1.3181231395819218e-05, + "loss": 1.3215, + "step": 4360 + }, + { + "epoch": 0.46, + "learning_rate": 1.3177761084885689e-05, + "loss": 1.368, + "step": 4361 + }, + { + "epoch": 0.46, + "learning_rate": 1.317429034821383e-05, + "loss": 1.3247, + "step": 4362 + }, + { + "epoch": 0.46, + "learning_rate": 1.3170819186268618e-05, + "loss": 1.4512, + "step": 4363 + }, + { + "epoch": 0.46, + "learning_rate": 1.3167347599515111e-05, + "loss": 1.3129, + "step": 4364 + }, + { + "epoch": 0.46, + "learning_rate": 1.3163875588418404e-05, + "loss": 1.3934, + "step": 4365 + }, + { + "epoch": 0.46, + "learning_rate": 1.3160403153443666e-05, + "loss": 1.4518, + "step": 4366 + }, + { + "epoch": 0.46, + "learning_rate": 1.3156930295056105e-05, + "loss": 1.3959, + "step": 4367 + }, + { + "epoch": 0.46, + "learning_rate": 1.3153457013721e-05, + "loss": 1.3475, + "step": 4368 + }, + { + "epoch": 0.46, + "learning_rate": 1.3149983309903687e-05, + "loss": 1.4102, + "step": 4369 + }, + { + "epoch": 0.46, + "learning_rate": 1.3146509184069538e-05, + "loss": 1.3674, + "step": 4370 + }, + { + "epoch": 0.46, + "learning_rate": 1.314303463668401e-05, + "loss": 1.3739, + "step": 4371 + }, + { + "epoch": 0.46, + "learning_rate": 1.3139559668212596e-05, + "loss": 1.4249, + "step": 4372 + }, + { + "epoch": 0.46, + "learning_rate": 1.3136084279120857e-05, + "loss": 1.4473, + "step": 4373 + }, + { + "epoch": 0.46, + "learning_rate": 1.3132608469874404e-05, + "loss": 1.4443, + "step": 4374 + }, + { + "epoch": 0.46, + "learning_rate": 1.3129132240938905e-05, + "loss": 1.3534, + "step": 4375 + }, + { + "epoch": 0.46, + "learning_rate": 1.3125655592780083e-05, + "loss": 1.5663, + "step": 4376 + }, + { + "epoch": 0.46, + "learning_rate": 1.3122178525863727e-05, + "loss": 1.3465, + "step": 4377 + }, + { + "epoch": 0.46, + "learning_rate": 1.3118701040655669e-05, + "loss": 1.35, + "step": 4378 + }, + { + "epoch": 0.46, + "eval_loss": 1.447788953781128, + "eval_runtime": 77.4473, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4378 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 1.9585598163698634e+20, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-4378/training_args.bin b/checkpoint-4378/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-4378/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-4776/config.json b/checkpoint-4776/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-4776/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-4776/generation_config.json b/checkpoint-4776/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-4776/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-4776/model-00001-of-00003.safetensors b/checkpoint-4776/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8321cbb9f008fc275d5cc36bbd638e3c53e29704 --- /dev/null +++ b/checkpoint-4776/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c8ff47b65039afa6ca10801393b9d904c1068f480535269aaf98c0460e14a5d +size 4943162336 diff --git a/checkpoint-4776/model-00002-of-00003.safetensors b/checkpoint-4776/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5e9f3d8cc2d9c53ce411695e49a0c24dcb39ed1c --- /dev/null +++ b/checkpoint-4776/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4aa4e03d24926a06d836ba79f2520d677f909c83be52b309b10d5c2e901bb39 +size 4999819336 diff --git a/checkpoint-4776/model-00003-of-00003.safetensors b/checkpoint-4776/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f49354f6b4c2bf9df2d15b0c5418881acea5e71c --- /dev/null +++ b/checkpoint-4776/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c407dd4c5873d6f214e4da6fecc28a5d0c2121a58b6bc8594ca6e3b561a4665 +size 4540516344 diff --git a/checkpoint-4776/model.safetensors.index.json b/checkpoint-4776/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-4776/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-4776/optimizer.pt b/checkpoint-4776/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..404bc8096b62db6056d38e39e142b9b071a0c619 --- /dev/null +++ b/checkpoint-4776/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3bcd234e0575db4ef60853cf291f250c50328a8c969be9e23304df3cbad625a +size 14512103560 diff --git a/checkpoint-4776/rng_state_0.pth b/checkpoint-4776/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..17419668361c887387305186f79bf766c133d948 --- /dev/null +++ b/checkpoint-4776/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6118faeaee4fdfaa13ac70fa72cfa116964f5a3b96fac7723d08df58a38b397c +size 15984 diff --git a/checkpoint-4776/rng_state_1.pth b/checkpoint-4776/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..4b73890794d1b35d2ed61c585f2b8f6f751bf95c --- /dev/null +++ b/checkpoint-4776/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dfa684751cc5b0d0c6c20837671c3f615d1dea15a14f377cd3f328d98685be6 +size 15984 diff --git a/checkpoint-4776/rng_state_2.pth b/checkpoint-4776/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..3b07fdc075039346ac84a63c86d5c331b72bd6c4 --- /dev/null +++ b/checkpoint-4776/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6288d8200e463b5ae8ad06a62ffa8cc379f48c86fd01515a13181f976efa71a +size 15984 diff --git a/checkpoint-4776/rng_state_3.pth b/checkpoint-4776/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..7ae496b0f7c94e28920f5d5728ea7218cc42cb44 --- /dev/null +++ b/checkpoint-4776/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd3d0484a9201a8efbd51326113ef6b44a0b272cfa40529d39c56a9d67deac8e +size 15984 diff --git a/checkpoint-4776/rng_state_4.pth b/checkpoint-4776/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..3b1b72e7eb800ef3f86a0e4914d857ba8903ddf3 --- /dev/null +++ b/checkpoint-4776/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:426c6fc3fcaae6fad4fdb83d268d91ed94e3e0e88bed483e185a78e86a9692b3 +size 15984 diff --git a/checkpoint-4776/rng_state_5.pth b/checkpoint-4776/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..8d72cb416d17bfba78bc4c5b47a8b1f4458e9085 --- /dev/null +++ b/checkpoint-4776/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d089430782ecc3b7446f527601b569a4990fdd9f8d96c18c87dc8d503cbdb70 +size 15984 diff --git a/checkpoint-4776/rng_state_6.pth b/checkpoint-4776/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..3fc4c545d555b83f84b52444db4591003ffb4eec --- /dev/null +++ b/checkpoint-4776/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b61f73069ccc96351c7253c2334d20c170e92750457b685c9d79286d288292e9 +size 15984 diff --git a/checkpoint-4776/rng_state_7.pth b/checkpoint-4776/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..9d0fd0f6b10569fbf101f1dce8ca5d75afd1277f --- /dev/null +++ b/checkpoint-4776/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e70ddcc8f9ba6c0be1ac8d1ba2f06e8a4253e0a843f3a263a85c073416ca948d +size 15984 diff --git a/checkpoint-4776/scheduler.pt b/checkpoint-4776/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..d87e36e1b14f606ed38d23acfed5b4811ccf1943 --- /dev/null +++ b/checkpoint-4776/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4609165dd25e24a937eff154baa106380b8b53029e3e1a5e00d6fe0d4e0ee310 +size 1064 diff --git a/checkpoint-4776/special_tokens_map.json b/checkpoint-4776/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-4776/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-4776/tokenizer.model b/checkpoint-4776/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-4776/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-4776/tokenizer_config.json b/checkpoint-4776/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-4776/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-4776/trainer_state.json b/checkpoint-4776/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..af58b6d539b601fe1af31a4a61a95b100ddc2cb7 --- /dev/null +++ b/checkpoint-4776/trainer_state.json @@ -0,0 +1,28868 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.5008389261744967, + "eval_steps": 199, + "global_step": 4776, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + }, + { + "epoch": 0.21, + "learning_rate": 1.928689129323009e-05, + "loss": 1.421, + "step": 1991 + }, + { + "epoch": 0.21, + "learning_rate": 1.928553323396003e-05, + "loss": 1.5625, + "step": 1992 + }, + { + "epoch": 0.21, + "learning_rate": 1.92841739306671e-05, + "loss": 1.5198, + "step": 1993 + }, + { + "epoch": 0.21, + "learning_rate": 1.9282813383533415e-05, + "loss": 1.5116, + "step": 1994 + }, + { + "epoch": 0.21, + "learning_rate": 1.9281451592741247e-05, + "loss": 1.4306, + "step": 1995 + }, + { + "epoch": 0.21, + "learning_rate": 1.9280088558473046e-05, + "loss": 1.5425, + "step": 1996 + }, + { + "epoch": 0.21, + "learning_rate": 1.9278724280911424e-05, + "loss": 1.4972, + "step": 1997 + }, + { + "epoch": 0.21, + "learning_rate": 1.9277358760239156e-05, + "loss": 1.5185, + "step": 1998 + }, + { + "epoch": 0.21, + "learning_rate": 1.9275991996639188e-05, + "loss": 1.5187, + "step": 1999 + }, + { + "epoch": 0.21, + "learning_rate": 1.927462399029463e-05, + "loss": 1.4325, + "step": 2000 + }, + { + "epoch": 0.21, + "learning_rate": 1.9273254741388763e-05, + "loss": 1.4397, + "step": 2001 + }, + { + "epoch": 0.21, + "learning_rate": 1.927188425010503e-05, + "loss": 1.5319, + "step": 2002 + }, + { + "epoch": 0.21, + "learning_rate": 1.9270512516627042e-05, + "loss": 1.5664, + "step": 2003 + }, + { + "epoch": 0.21, + "learning_rate": 1.9269139541138574e-05, + "loss": 1.5227, + "step": 2004 + }, + { + "epoch": 0.21, + "learning_rate": 1.926776532382357e-05, + "loss": 1.5187, + "step": 2005 + }, + { + "epoch": 0.21, + "learning_rate": 1.9266389864866134e-05, + "loss": 1.4029, + "step": 2006 + }, + { + "epoch": 0.21, + "learning_rate": 1.9265013164450557e-05, + "loss": 1.387, + "step": 2007 + }, + { + "epoch": 0.21, + "learning_rate": 1.9263635222761268e-05, + "loss": 1.5047, + "step": 2008 + }, + { + "epoch": 0.21, + "learning_rate": 1.9262256039982882e-05, + "loss": 1.4816, + "step": 2009 + }, + { + "epoch": 0.21, + "learning_rate": 1.9260875616300172e-05, + "loss": 1.4607, + "step": 2010 + }, + { + "epoch": 0.21, + "learning_rate": 1.9259493951898084e-05, + "loss": 1.628, + "step": 2011 + }, + { + "epoch": 0.21, + "learning_rate": 1.9258111046961714e-05, + "loss": 1.4149, + "step": 2012 + }, + { + "epoch": 0.21, + "learning_rate": 1.925672690167635e-05, + "loss": 1.5303, + "step": 2013 + }, + { + "epoch": 0.21, + "learning_rate": 1.925534151622742e-05, + "loss": 1.5198, + "step": 2014 + }, + { + "epoch": 0.21, + "learning_rate": 1.9253954890800535e-05, + "loss": 1.6422, + "step": 2015 + }, + { + "epoch": 0.21, + "learning_rate": 1.925256702558147e-05, + "loss": 1.4738, + "step": 2016 + }, + { + "epoch": 0.21, + "learning_rate": 1.925117792075616e-05, + "loss": 1.4752, + "step": 2017 + }, + { + "epoch": 0.21, + "learning_rate": 1.9249787576510713e-05, + "loss": 1.4547, + "step": 2018 + }, + { + "epoch": 0.21, + "learning_rate": 1.924839599303139e-05, + "loss": 1.4864, + "step": 2019 + }, + { + "epoch": 0.21, + "learning_rate": 1.9247003170504638e-05, + "loss": 1.5037, + "step": 2020 + }, + { + "epoch": 0.21, + "learning_rate": 1.9245609109117053e-05, + "loss": 1.5089, + "step": 2021 + }, + { + "epoch": 0.21, + "learning_rate": 1.924421380905541e-05, + "loss": 1.5616, + "step": 2022 + }, + { + "epoch": 0.21, + "learning_rate": 1.9242817270506634e-05, + "loss": 1.4592, + "step": 2023 + }, + { + "epoch": 0.21, + "learning_rate": 1.9241419493657832e-05, + "loss": 1.5592, + "step": 2024 + }, + { + "epoch": 0.21, + "learning_rate": 1.924002047869627e-05, + "loss": 1.4897, + "step": 2025 + }, + { + "epoch": 0.21, + "learning_rate": 1.9238620225809375e-05, + "loss": 1.4743, + "step": 2026 + }, + { + "epoch": 0.21, + "learning_rate": 1.923721873518475e-05, + "loss": 1.4686, + "step": 2027 + }, + { + "epoch": 0.21, + "learning_rate": 1.923581600701016e-05, + "loss": 1.461, + "step": 2028 + }, + { + "epoch": 0.21, + "learning_rate": 1.9234412041473528e-05, + "loss": 1.6622, + "step": 2029 + }, + { + "epoch": 0.21, + "learning_rate": 1.9233006838762955e-05, + "loss": 1.4707, + "step": 2030 + }, + { + "epoch": 0.21, + "learning_rate": 1.92316003990667e-05, + "loss": 1.5566, + "step": 2031 + }, + { + "epoch": 0.21, + "learning_rate": 1.9230192722573188e-05, + "loss": 1.4881, + "step": 2032 + }, + { + "epoch": 0.21, + "learning_rate": 1.9228783809471015e-05, + "loss": 1.6124, + "step": 2033 + }, + { + "epoch": 0.21, + "learning_rate": 1.9227373659948937e-05, + "loss": 1.3508, + "step": 2034 + }, + { + "epoch": 0.21, + "learning_rate": 1.9225962274195876e-05, + "loss": 1.4418, + "step": 2035 + }, + { + "epoch": 0.21, + "learning_rate": 1.9224549652400927e-05, + "loss": 1.3954, + "step": 2036 + }, + { + "epoch": 0.21, + "learning_rate": 1.922313579475334e-05, + "loss": 1.4798, + "step": 2037 + }, + { + "epoch": 0.21, + "learning_rate": 1.922172070144254e-05, + "loss": 1.4556, + "step": 2038 + }, + { + "epoch": 0.21, + "learning_rate": 1.922030437265811e-05, + "loss": 1.4987, + "step": 2039 + }, + { + "epoch": 0.21, + "learning_rate": 1.9218886808589796e-05, + "loss": 1.4857, + "step": 2040 + }, + { + "epoch": 0.21, + "learning_rate": 1.9217468009427527e-05, + "loss": 1.5289, + "step": 2041 + }, + { + "epoch": 0.21, + "learning_rate": 1.921604797536138e-05, + "loss": 1.5267, + "step": 2042 + }, + { + "epoch": 0.21, + "learning_rate": 1.9214626706581598e-05, + "loss": 1.4655, + "step": 2043 + }, + { + "epoch": 0.21, + "learning_rate": 1.9213204203278602e-05, + "loss": 1.4598, + "step": 2044 + }, + { + "epoch": 0.21, + "learning_rate": 1.9211780465642973e-05, + "loss": 1.4766, + "step": 2045 + }, + { + "epoch": 0.21, + "learning_rate": 1.921035549386545e-05, + "loss": 1.5148, + "step": 2046 + }, + { + "epoch": 0.21, + "learning_rate": 1.9208929288136933e-05, + "loss": 1.5567, + "step": 2047 + }, + { + "epoch": 0.21, + "learning_rate": 1.920750184864852e-05, + "loss": 1.4868, + "step": 2048 + }, + { + "epoch": 0.21, + "learning_rate": 1.920607317559143e-05, + "loss": 1.4752, + "step": 2049 + }, + { + "epoch": 0.21, + "learning_rate": 1.920464326915708e-05, + "loss": 1.4882, + "step": 2050 + }, + { + "epoch": 0.22, + "learning_rate": 1.9203212129537035e-05, + "loss": 1.5933, + "step": 2051 + }, + { + "epoch": 0.22, + "learning_rate": 1.9201779756923037e-05, + "loss": 1.4891, + "step": 2052 + }, + { + "epoch": 0.22, + "learning_rate": 1.9200346151506983e-05, + "loss": 1.4486, + "step": 2053 + }, + { + "epoch": 0.22, + "learning_rate": 1.9198911313480938e-05, + "loss": 1.5091, + "step": 2054 + }, + { + "epoch": 0.22, + "learning_rate": 1.919747524303714e-05, + "loss": 1.4385, + "step": 2055 + }, + { + "epoch": 0.22, + "learning_rate": 1.9196037940367974e-05, + "loss": 1.4104, + "step": 2056 + }, + { + "epoch": 0.22, + "learning_rate": 1.9194599405666015e-05, + "loss": 1.4483, + "step": 2057 + }, + { + "epoch": 0.22, + "learning_rate": 1.9193159639123976e-05, + "loss": 1.4592, + "step": 2058 + }, + { + "epoch": 0.22, + "learning_rate": 1.919171864093476e-05, + "loss": 1.4975, + "step": 2059 + }, + { + "epoch": 0.22, + "learning_rate": 1.9190276411291423e-05, + "loss": 1.4727, + "step": 2060 + }, + { + "epoch": 0.22, + "learning_rate": 1.9188832950387178e-05, + "loss": 1.4791, + "step": 2061 + }, + { + "epoch": 0.22, + "learning_rate": 1.9187388258415423e-05, + "loss": 1.3806, + "step": 2062 + }, + { + "epoch": 0.22, + "learning_rate": 1.9185942335569697e-05, + "loss": 1.4514, + "step": 2063 + }, + { + "epoch": 0.22, + "learning_rate": 1.9184495182043727e-05, + "loss": 1.4389, + "step": 2064 + }, + { + "epoch": 0.22, + "learning_rate": 1.918304679803139e-05, + "loss": 1.5088, + "step": 2065 + }, + { + "epoch": 0.22, + "learning_rate": 1.9181597183726733e-05, + "loss": 1.4665, + "step": 2066 + }, + { + "epoch": 0.22, + "learning_rate": 1.9180146339323966e-05, + "loss": 1.489, + "step": 2067 + }, + { + "epoch": 0.22, + "learning_rate": 1.9178694265017466e-05, + "loss": 1.5215, + "step": 2068 + }, + { + "epoch": 0.22, + "learning_rate": 1.9177240961001775e-05, + "loss": 1.5152, + "step": 2069 + }, + { + "epoch": 0.22, + "learning_rate": 1.9175786427471594e-05, + "loss": 1.4418, + "step": 2070 + }, + { + "epoch": 0.22, + "learning_rate": 1.91743306646218e-05, + "loss": 1.5001, + "step": 2071 + }, + { + "epoch": 0.22, + "learning_rate": 1.9172873672647417e-05, + "loss": 1.4879, + "step": 2072 + }, + { + "epoch": 0.22, + "learning_rate": 1.917141545174366e-05, + "loss": 1.5299, + "step": 2073 + }, + { + "epoch": 0.22, + "learning_rate": 1.9169956002105877e-05, + "loss": 1.4602, + "step": 2074 + }, + { + "epoch": 0.22, + "learning_rate": 1.9168495323929605e-05, + "loss": 1.4921, + "step": 2075 + }, + { + "epoch": 0.22, + "learning_rate": 1.916703341741054e-05, + "loss": 1.4659, + "step": 2076 + }, + { + "epoch": 0.22, + "learning_rate": 1.9165570282744534e-05, + "loss": 1.4707, + "step": 2077 + }, + { + "epoch": 0.22, + "learning_rate": 1.9164105920127613e-05, + "loss": 1.5354, + "step": 2078 + }, + { + "epoch": 0.22, + "learning_rate": 1.9162640329755962e-05, + "loss": 1.526, + "step": 2079 + }, + { + "epoch": 0.22, + "learning_rate": 1.916117351182593e-05, + "loss": 1.6424, + "step": 2080 + }, + { + "epoch": 0.22, + "learning_rate": 1.915970546653404e-05, + "loss": 1.5048, + "step": 2081 + }, + { + "epoch": 0.22, + "learning_rate": 1.915823619407697e-05, + "loss": 1.5344, + "step": 2082 + }, + { + "epoch": 0.22, + "learning_rate": 1.915676569465156e-05, + "loss": 1.4604, + "step": 2083 + }, + { + "epoch": 0.22, + "learning_rate": 1.9155293968454826e-05, + "loss": 1.4929, + "step": 2084 + }, + { + "epoch": 0.22, + "learning_rate": 1.9153821015683937e-05, + "loss": 1.4106, + "step": 2085 + }, + { + "epoch": 0.22, + "learning_rate": 1.915234683653623e-05, + "loss": 1.4146, + "step": 2086 + }, + { + "epoch": 0.22, + "learning_rate": 1.9150871431209207e-05, + "loss": 1.4481, + "step": 2087 + }, + { + "epoch": 0.22, + "learning_rate": 1.914939479990054e-05, + "loss": 1.5206, + "step": 2088 + }, + { + "epoch": 0.22, + "learning_rate": 1.9147916942808054e-05, + "loss": 1.5073, + "step": 2089 + }, + { + "epoch": 0.22, + "learning_rate": 1.9146437860129745e-05, + "loss": 1.5196, + "step": 2090 + }, + { + "epoch": 0.22, + "learning_rate": 1.9144957552063775e-05, + "loss": 1.5389, + "step": 2091 + }, + { + "epoch": 0.22, + "learning_rate": 1.9143476018808463e-05, + "loss": 1.5207, + "step": 2092 + }, + { + "epoch": 0.22, + "learning_rate": 1.9141993260562298e-05, + "loss": 1.3717, + "step": 2093 + }, + { + "epoch": 0.22, + "learning_rate": 1.9140509277523937e-05, + "loss": 1.471, + "step": 2094 + }, + { + "epoch": 0.22, + "learning_rate": 1.9139024069892185e-05, + "loss": 1.4553, + "step": 2095 + }, + { + "epoch": 0.22, + "learning_rate": 1.9137537637866027e-05, + "loss": 1.5311, + "step": 2096 + }, + { + "epoch": 0.22, + "learning_rate": 1.9136049981644614e-05, + "loss": 1.4369, + "step": 2097 + }, + { + "epoch": 0.22, + "learning_rate": 1.913456110142724e-05, + "loss": 1.4528, + "step": 2098 + }, + { + "epoch": 0.22, + "learning_rate": 1.9133070997413384e-05, + "loss": 1.5294, + "step": 2099 + }, + { + "epoch": 0.22, + "learning_rate": 1.9131579669802685e-05, + "loss": 1.4588, + "step": 2100 + }, + { + "epoch": 0.22, + "learning_rate": 1.9130087118794934e-05, + "loss": 1.443, + "step": 2101 + }, + { + "epoch": 0.22, + "learning_rate": 1.9128593344590102e-05, + "loss": 1.4876, + "step": 2102 + }, + { + "epoch": 0.22, + "learning_rate": 1.912709834738831e-05, + "loss": 1.4874, + "step": 2103 + }, + { + "epoch": 0.22, + "learning_rate": 1.9125602127389856e-05, + "loss": 1.4966, + "step": 2104 + }, + { + "epoch": 0.22, + "learning_rate": 1.912410468479519e-05, + "loss": 1.5747, + "step": 2105 + }, + { + "epoch": 0.22, + "learning_rate": 1.9122606019804933e-05, + "loss": 1.4025, + "step": 2106 + }, + { + "epoch": 0.22, + "learning_rate": 1.912110613261987e-05, + "loss": 1.4755, + "step": 2107 + }, + { + "epoch": 0.22, + "learning_rate": 1.911960502344094e-05, + "loss": 1.4739, + "step": 2108 + }, + { + "epoch": 0.22, + "learning_rate": 1.911810269246926e-05, + "loss": 1.4992, + "step": 2109 + }, + { + "epoch": 0.22, + "learning_rate": 1.91165991399061e-05, + "loss": 1.4435, + "step": 2110 + }, + { + "epoch": 0.22, + "learning_rate": 1.91150943659529e-05, + "loss": 1.4918, + "step": 2111 + }, + { + "epoch": 0.22, + "learning_rate": 1.9113588370811258e-05, + "loss": 1.3818, + "step": 2112 + }, + { + "epoch": 0.22, + "learning_rate": 1.911208115468294e-05, + "loss": 1.5105, + "step": 2113 + }, + { + "epoch": 0.22, + "learning_rate": 1.9110572717769878e-05, + "loss": 1.6634, + "step": 2114 + }, + { + "epoch": 0.22, + "learning_rate": 1.9109063060274158e-05, + "loss": 1.5028, + "step": 2115 + }, + { + "epoch": 0.22, + "learning_rate": 1.9107552182398037e-05, + "loss": 1.6657, + "step": 2116 + }, + { + "epoch": 0.22, + "learning_rate": 1.9106040084343935e-05, + "loss": 1.5481, + "step": 2117 + }, + { + "epoch": 0.22, + "learning_rate": 1.910452676631444e-05, + "loss": 1.4505, + "step": 2118 + }, + { + "epoch": 0.22, + "learning_rate": 1.9103012228512284e-05, + "loss": 1.5173, + "step": 2119 + }, + { + "epoch": 0.22, + "learning_rate": 1.9101496471140385e-05, + "loss": 1.3788, + "step": 2120 + }, + { + "epoch": 0.22, + "learning_rate": 1.9099979494401814e-05, + "loss": 1.4649, + "step": 2121 + }, + { + "epoch": 0.22, + "learning_rate": 1.9098461298499805e-05, + "loss": 1.4204, + "step": 2122 + }, + { + "epoch": 0.22, + "learning_rate": 1.9096941883637766e-05, + "loss": 1.4439, + "step": 2123 + }, + { + "epoch": 0.22, + "learning_rate": 1.909542125001925e-05, + "loss": 1.6615, + "step": 2124 + }, + { + "epoch": 0.22, + "learning_rate": 1.9093899397847985e-05, + "loss": 1.4763, + "step": 2125 + }, + { + "epoch": 0.22, + "learning_rate": 1.909237632732786e-05, + "loss": 1.5353, + "step": 2126 + }, + { + "epoch": 0.22, + "learning_rate": 1.909085203866293e-05, + "loss": 1.442, + "step": 2127 + }, + { + "epoch": 0.22, + "learning_rate": 1.9089326532057408e-05, + "loss": 1.4782, + "step": 2128 + }, + { + "epoch": 0.22, + "learning_rate": 1.908779980771567e-05, + "loss": 1.4933, + "step": 2129 + }, + { + "epoch": 0.22, + "learning_rate": 1.9086271865842264e-05, + "loss": 1.5285, + "step": 2130 + }, + { + "epoch": 0.22, + "learning_rate": 1.9084742706641894e-05, + "loss": 1.4736, + "step": 2131 + }, + { + "epoch": 0.22, + "learning_rate": 1.9083212330319427e-05, + "loss": 1.4496, + "step": 2132 + }, + { + "epoch": 0.22, + "learning_rate": 1.908168073707989e-05, + "loss": 1.5099, + "step": 2133 + }, + { + "epoch": 0.22, + "learning_rate": 1.9080147927128483e-05, + "loss": 1.5235, + "step": 2134 + }, + { + "epoch": 0.22, + "learning_rate": 1.9078613900670556e-05, + "loss": 1.4769, + "step": 2135 + }, + { + "epoch": 0.22, + "learning_rate": 1.907707865791164e-05, + "loss": 1.5771, + "step": 2136 + }, + { + "epoch": 0.22, + "learning_rate": 1.907554219905741e-05, + "loss": 1.5116, + "step": 2137 + }, + { + "epoch": 0.22, + "learning_rate": 1.907400452431371e-05, + "loss": 1.5161, + "step": 2138 + }, + { + "epoch": 0.22, + "learning_rate": 1.9072465633886557e-05, + "loss": 1.4356, + "step": 2139 + }, + { + "epoch": 0.22, + "learning_rate": 1.9070925527982117e-05, + "loss": 1.509, + "step": 2140 + }, + { + "epoch": 0.22, + "learning_rate": 1.9069384206806723e-05, + "loss": 1.4681, + "step": 2141 + }, + { + "epoch": 0.22, + "learning_rate": 1.9067841670566883e-05, + "loss": 1.5254, + "step": 2142 + }, + { + "epoch": 0.22, + "learning_rate": 1.9066297919469242e-05, + "loss": 1.4797, + "step": 2143 + }, + { + "epoch": 0.22, + "learning_rate": 1.9064752953720636e-05, + "loss": 1.3996, + "step": 2144 + }, + { + "epoch": 0.22, + "learning_rate": 1.9063206773528042e-05, + "loss": 1.4457, + "step": 2145 + }, + { + "epoch": 0.23, + "learning_rate": 1.9061659379098617e-05, + "loss": 1.5126, + "step": 2146 + }, + { + "epoch": 0.23, + "learning_rate": 1.9060110770639664e-05, + "loss": 1.5925, + "step": 2147 + }, + { + "epoch": 0.23, + "learning_rate": 1.905856094835866e-05, + "loss": 1.5146, + "step": 2148 + }, + { + "epoch": 0.23, + "learning_rate": 1.905700991246324e-05, + "loss": 1.7256, + "step": 2149 + }, + { + "epoch": 0.23, + "learning_rate": 1.90554576631612e-05, + "loss": 1.57, + "step": 2150 + }, + { + "epoch": 0.23, + "learning_rate": 1.905390420066051e-05, + "loss": 1.3722, + "step": 2151 + }, + { + "epoch": 0.23, + "learning_rate": 1.9052349525169292e-05, + "loss": 1.3999, + "step": 2152 + }, + { + "epoch": 0.23, + "learning_rate": 1.9050793636895828e-05, + "loss": 1.586, + "step": 2153 + }, + { + "epoch": 0.23, + "learning_rate": 1.9049236536048567e-05, + "loss": 1.4884, + "step": 2154 + }, + { + "epoch": 0.23, + "learning_rate": 1.9047678222836127e-05, + "loss": 1.5898, + "step": 2155 + }, + { + "epoch": 0.23, + "learning_rate": 1.9046118697467278e-05, + "loss": 1.569, + "step": 2156 + }, + { + "epoch": 0.23, + "learning_rate": 1.904455796015095e-05, + "loss": 1.5592, + "step": 2157 + }, + { + "epoch": 0.23, + "learning_rate": 1.9042996011096253e-05, + "loss": 1.597, + "step": 2158 + }, + { + "epoch": 0.23, + "learning_rate": 1.904143285051244e-05, + "loss": 1.422, + "step": 2159 + }, + { + "epoch": 0.23, + "learning_rate": 1.903986847860894e-05, + "loss": 1.519, + "step": 2160 + }, + { + "epoch": 0.23, + "learning_rate": 1.9038302895595334e-05, + "loss": 1.5197, + "step": 2161 + }, + { + "epoch": 0.23, + "learning_rate": 1.903673610168137e-05, + "loss": 1.4655, + "step": 2162 + }, + { + "epoch": 0.23, + "learning_rate": 1.9035168097076965e-05, + "loss": 1.3909, + "step": 2163 + }, + { + "epoch": 0.23, + "learning_rate": 1.903359888199218e-05, + "loss": 1.4877, + "step": 2164 + }, + { + "epoch": 0.23, + "learning_rate": 1.903202845663726e-05, + "loss": 1.5123, + "step": 2165 + }, + { + "epoch": 0.23, + "learning_rate": 1.9030456821222593e-05, + "loss": 1.4906, + "step": 2166 + }, + { + "epoch": 0.23, + "learning_rate": 1.9028883975958745e-05, + "loss": 1.4574, + "step": 2167 + }, + { + "epoch": 0.23, + "learning_rate": 1.9027309921056435e-05, + "loss": 1.4571, + "step": 2168 + }, + { + "epoch": 0.23, + "learning_rate": 1.902573465672654e-05, + "loss": 1.4281, + "step": 2169 + }, + { + "epoch": 0.23, + "learning_rate": 1.9024158183180116e-05, + "loss": 1.5057, + "step": 2170 + }, + { + "epoch": 0.23, + "learning_rate": 1.902258050062836e-05, + "loss": 1.4514, + "step": 2171 + }, + { + "epoch": 0.23, + "learning_rate": 1.9021001609282646e-05, + "loss": 1.5055, + "step": 2172 + }, + { + "epoch": 0.23, + "learning_rate": 1.9019421509354505e-05, + "loss": 1.4578, + "step": 2173 + }, + { + "epoch": 0.23, + "learning_rate": 1.9017840201055625e-05, + "loss": 1.459, + "step": 2174 + }, + { + "epoch": 0.23, + "learning_rate": 1.9016257684597864e-05, + "loss": 1.5059, + "step": 2175 + }, + { + "epoch": 0.23, + "learning_rate": 1.901467396019324e-05, + "loss": 1.57, + "step": 2176 + }, + { + "epoch": 0.23, + "learning_rate": 1.901308902805393e-05, + "loss": 1.4924, + "step": 2177 + }, + { + "epoch": 0.23, + "learning_rate": 1.9011502888392273e-05, + "loss": 1.4979, + "step": 2178 + }, + { + "epoch": 0.23, + "learning_rate": 1.900991554142077e-05, + "loss": 1.5321, + "step": 2179 + }, + { + "epoch": 0.23, + "learning_rate": 1.9008326987352093e-05, + "loss": 1.493, + "step": 2180 + }, + { + "epoch": 0.23, + "learning_rate": 1.9006737226399056e-05, + "loss": 1.5111, + "step": 2181 + }, + { + "epoch": 0.23, + "learning_rate": 1.900514625877465e-05, + "loss": 1.4154, + "step": 2182 + }, + { + "epoch": 0.23, + "learning_rate": 1.900355408469203e-05, + "loss": 1.4934, + "step": 2183 + }, + { + "epoch": 0.23, + "learning_rate": 1.90019607043645e-05, + "loss": 1.5975, + "step": 2184 + }, + { + "epoch": 0.23, + "learning_rate": 1.9000366118005532e-05, + "loss": 1.3537, + "step": 2185 + }, + { + "epoch": 0.23, + "learning_rate": 1.899877032582876e-05, + "loss": 1.4583, + "step": 2186 + }, + { + "epoch": 0.23, + "learning_rate": 1.8997173328047984e-05, + "loss": 1.4586, + "step": 2187 + }, + { + "epoch": 0.23, + "learning_rate": 1.8995575124877156e-05, + "loss": 1.4774, + "step": 2188 + }, + { + "epoch": 0.23, + "learning_rate": 1.8993975716530394e-05, + "loss": 1.5025, + "step": 2189 + }, + { + "epoch": 0.23, + "eval_loss": 1.5263344049453735, + "eval_runtime": 77.1492, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 2189 + }, + { + "epoch": 0.23, + "learning_rate": 1.899237510322198e-05, + "loss": 1.5438, + "step": 2190 + }, + { + "epoch": 0.23, + "learning_rate": 1.899077328516635e-05, + "loss": 1.5181, + "step": 2191 + }, + { + "epoch": 0.23, + "learning_rate": 1.8989170262578112e-05, + "loss": 1.4454, + "step": 2192 + }, + { + "epoch": 0.23, + "learning_rate": 1.8987566035672028e-05, + "loss": 1.4882, + "step": 2193 + }, + { + "epoch": 0.23, + "learning_rate": 1.8985960604663026e-05, + "loss": 1.5073, + "step": 2194 + }, + { + "epoch": 0.23, + "learning_rate": 1.8984353969766187e-05, + "loss": 1.4478, + "step": 2195 + }, + { + "epoch": 0.23, + "learning_rate": 1.8982746131196763e-05, + "loss": 1.4768, + "step": 2196 + }, + { + "epoch": 0.23, + "learning_rate": 1.8981137089170162e-05, + "loss": 1.5116, + "step": 2197 + }, + { + "epoch": 0.23, + "learning_rate": 1.8979526843901952e-05, + "loss": 1.4202, + "step": 2198 + }, + { + "epoch": 0.23, + "learning_rate": 1.8977915395607867e-05, + "loss": 1.4736, + "step": 2199 + }, + { + "epoch": 0.23, + "learning_rate": 1.89763027445038e-05, + "loss": 1.4489, + "step": 2200 + }, + { + "epoch": 0.23, + "learning_rate": 1.8974688890805804e-05, + "loss": 1.4512, + "step": 2201 + }, + { + "epoch": 0.23, + "learning_rate": 1.897307383473009e-05, + "loss": 1.5091, + "step": 2202 + }, + { + "epoch": 0.23, + "learning_rate": 1.897145757649304e-05, + "loss": 1.5512, + "step": 2203 + }, + { + "epoch": 0.23, + "learning_rate": 1.8969840116311192e-05, + "loss": 1.406, + "step": 2204 + }, + { + "epoch": 0.23, + "learning_rate": 1.896822145440124e-05, + "loss": 1.4531, + "step": 2205 + }, + { + "epoch": 0.23, + "learning_rate": 1.896660159098004e-05, + "loss": 1.4379, + "step": 2206 + }, + { + "epoch": 0.23, + "learning_rate": 1.896498052626462e-05, + "loss": 1.4783, + "step": 2207 + }, + { + "epoch": 0.23, + "learning_rate": 1.896335826047216e-05, + "loss": 1.4801, + "step": 2208 + }, + { + "epoch": 0.23, + "learning_rate": 1.896173479381999e-05, + "loss": 1.4526, + "step": 2209 + }, + { + "epoch": 0.23, + "learning_rate": 1.8960110126525627e-05, + "loss": 1.4952, + "step": 2210 + }, + { + "epoch": 0.23, + "learning_rate": 1.895848425880673e-05, + "loss": 1.5299, + "step": 2211 + }, + { + "epoch": 0.23, + "learning_rate": 1.8956857190881125e-05, + "loss": 1.5274, + "step": 2212 + }, + { + "epoch": 0.23, + "learning_rate": 1.8955228922966792e-05, + "loss": 1.4415, + "step": 2213 + }, + { + "epoch": 0.23, + "learning_rate": 1.8953599455281884e-05, + "loss": 1.5311, + "step": 2214 + }, + { + "epoch": 0.23, + "learning_rate": 1.8951968788044702e-05, + "loss": 1.4972, + "step": 2215 + }, + { + "epoch": 0.23, + "learning_rate": 1.8950336921473715e-05, + "loss": 1.4966, + "step": 2216 + }, + { + "epoch": 0.23, + "learning_rate": 1.8948703855787553e-05, + "loss": 1.4683, + "step": 2217 + }, + { + "epoch": 0.23, + "learning_rate": 1.8947069591205005e-05, + "loss": 1.503, + "step": 2218 + }, + { + "epoch": 0.23, + "learning_rate": 1.8945434127945014e-05, + "loss": 1.4902, + "step": 2219 + }, + { + "epoch": 0.23, + "learning_rate": 1.8943797466226702e-05, + "loss": 1.4835, + "step": 2220 + }, + { + "epoch": 0.23, + "learning_rate": 1.8942159606269332e-05, + "loss": 1.535, + "step": 2221 + }, + { + "epoch": 0.23, + "learning_rate": 1.8940520548292332e-05, + "loss": 1.491, + "step": 2222 + }, + { + "epoch": 0.23, + "learning_rate": 1.89388802925153e-05, + "loss": 1.5157, + "step": 2223 + }, + { + "epoch": 0.23, + "learning_rate": 1.8937238839157987e-05, + "loss": 1.4779, + "step": 2224 + }, + { + "epoch": 0.23, + "learning_rate": 1.8935596188440302e-05, + "loss": 1.4902, + "step": 2225 + }, + { + "epoch": 0.23, + "learning_rate": 1.8933952340582323e-05, + "loss": 1.4988, + "step": 2226 + }, + { + "epoch": 0.23, + "learning_rate": 1.893230729580428e-05, + "loss": 1.4568, + "step": 2227 + }, + { + "epoch": 0.23, + "learning_rate": 1.8930661054326567e-05, + "loss": 1.5163, + "step": 2228 + }, + { + "epoch": 0.23, + "learning_rate": 1.892901361636974e-05, + "loss": 1.4472, + "step": 2229 + }, + { + "epoch": 0.23, + "learning_rate": 1.892736498215451e-05, + "loss": 1.4658, + "step": 2230 + }, + { + "epoch": 0.23, + "learning_rate": 1.8925715151901754e-05, + "loss": 1.4281, + "step": 2231 + }, + { + "epoch": 0.23, + "learning_rate": 1.892406412583251e-05, + "loss": 1.415, + "step": 2232 + }, + { + "epoch": 0.23, + "learning_rate": 1.8922411904167966e-05, + "loss": 1.464, + "step": 2233 + }, + { + "epoch": 0.23, + "learning_rate": 1.892075848712948e-05, + "loss": 1.5014, + "step": 2234 + }, + { + "epoch": 0.23, + "learning_rate": 1.8919103874938568e-05, + "loss": 1.4397, + "step": 2235 + }, + { + "epoch": 0.23, + "learning_rate": 1.891744806781691e-05, + "loss": 1.5508, + "step": 2236 + }, + { + "epoch": 0.23, + "learning_rate": 1.8915791065986335e-05, + "loss": 1.4749, + "step": 2237 + }, + { + "epoch": 0.23, + "learning_rate": 1.891413286966884e-05, + "loss": 1.4538, + "step": 2238 + }, + { + "epoch": 0.23, + "learning_rate": 1.891247347908658e-05, + "loss": 1.4405, + "step": 2239 + }, + { + "epoch": 0.23, + "learning_rate": 1.8910812894461878e-05, + "loss": 1.3562, + "step": 2240 + }, + { + "epoch": 0.24, + "learning_rate": 1.89091511160172e-05, + "loss": 1.4811, + "step": 2241 + }, + { + "epoch": 0.24, + "learning_rate": 1.8907488143975186e-05, + "loss": 1.4286, + "step": 2242 + }, + { + "epoch": 0.24, + "learning_rate": 1.890582397855863e-05, + "loss": 1.4493, + "step": 2243 + }, + { + "epoch": 0.24, + "learning_rate": 1.890415861999049e-05, + "loss": 1.5639, + "step": 2244 + }, + { + "epoch": 0.24, + "learning_rate": 1.890249206849388e-05, + "loss": 1.6375, + "step": 2245 + }, + { + "epoch": 0.24, + "learning_rate": 1.890082432429208e-05, + "loss": 1.4982, + "step": 2246 + }, + { + "epoch": 0.24, + "learning_rate": 1.889915538760851e-05, + "loss": 1.492, + "step": 2247 + }, + { + "epoch": 0.24, + "learning_rate": 1.8897485258666778e-05, + "loss": 1.4294, + "step": 2248 + }, + { + "epoch": 0.24, + "learning_rate": 1.8895813937690638e-05, + "loss": 1.4617, + "step": 2249 + }, + { + "epoch": 0.24, + "learning_rate": 1.8894141424904e-05, + "loss": 1.4763, + "step": 2250 + }, + { + "epoch": 0.24, + "learning_rate": 1.8892467720530937e-05, + "loss": 1.3989, + "step": 2251 + }, + { + "epoch": 0.24, + "learning_rate": 1.8890792824795687e-05, + "loss": 1.4803, + "step": 2252 + }, + { + "epoch": 0.24, + "learning_rate": 1.8889116737922638e-05, + "loss": 1.4734, + "step": 2253 + }, + { + "epoch": 0.24, + "learning_rate": 1.8887439460136342e-05, + "loss": 1.5069, + "step": 2254 + }, + { + "epoch": 0.24, + "learning_rate": 1.8885760991661514e-05, + "loss": 1.5565, + "step": 2255 + }, + { + "epoch": 0.24, + "learning_rate": 1.8884081332723028e-05, + "loss": 1.4707, + "step": 2256 + }, + { + "epoch": 0.24, + "learning_rate": 1.8882400483545913e-05, + "loss": 1.5077, + "step": 2257 + }, + { + "epoch": 0.24, + "learning_rate": 1.888071844435536e-05, + "loss": 1.5075, + "step": 2258 + }, + { + "epoch": 0.24, + "learning_rate": 1.8879035215376717e-05, + "loss": 1.5185, + "step": 2259 + }, + { + "epoch": 0.24, + "learning_rate": 1.887735079683549e-05, + "loss": 1.6266, + "step": 2260 + }, + { + "epoch": 0.24, + "learning_rate": 1.8875665188957354e-05, + "loss": 1.5013, + "step": 2261 + }, + { + "epoch": 0.24, + "learning_rate": 1.887397839196814e-05, + "loss": 1.4362, + "step": 2262 + }, + { + "epoch": 0.24, + "learning_rate": 1.8872290406093827e-05, + "loss": 1.4718, + "step": 2263 + }, + { + "epoch": 0.24, + "learning_rate": 1.8870601231560567e-05, + "loss": 1.5202, + "step": 2264 + }, + { + "epoch": 0.24, + "learning_rate": 1.8868910868594664e-05, + "loss": 1.5168, + "step": 2265 + }, + { + "epoch": 0.24, + "learning_rate": 1.8867219317422588e-05, + "loss": 1.5142, + "step": 2266 + }, + { + "epoch": 0.24, + "learning_rate": 1.8865526578270954e-05, + "loss": 1.4885, + "step": 2267 + }, + { + "epoch": 0.24, + "learning_rate": 1.8863832651366552e-05, + "loss": 1.5441, + "step": 2268 + }, + { + "epoch": 0.24, + "learning_rate": 1.8862137536936328e-05, + "loss": 1.4647, + "step": 2269 + }, + { + "epoch": 0.24, + "learning_rate": 1.8860441235207374e-05, + "loss": 1.5352, + "step": 2270 + }, + { + "epoch": 0.24, + "learning_rate": 1.8858743746406958e-05, + "loss": 1.4568, + "step": 2271 + }, + { + "epoch": 0.24, + "learning_rate": 1.8857045070762497e-05, + "loss": 1.4865, + "step": 2272 + }, + { + "epoch": 0.24, + "learning_rate": 1.8855345208501573e-05, + "loss": 1.4637, + "step": 2273 + }, + { + "epoch": 0.24, + "learning_rate": 1.8853644159851918e-05, + "loss": 1.4348, + "step": 2274 + }, + { + "epoch": 0.24, + "learning_rate": 1.8851941925041436e-05, + "loss": 1.4413, + "step": 2275 + }, + { + "epoch": 0.24, + "learning_rate": 1.8850238504298177e-05, + "loss": 1.4434, + "step": 2276 + }, + { + "epoch": 0.24, + "learning_rate": 1.884853389785036e-05, + "loss": 1.4822, + "step": 2277 + }, + { + "epoch": 0.24, + "learning_rate": 1.8846828105926356e-05, + "loss": 1.4632, + "step": 2278 + }, + { + "epoch": 0.24, + "learning_rate": 1.8845121128754698e-05, + "loss": 1.48, + "step": 2279 + }, + { + "epoch": 0.24, + "learning_rate": 1.8843412966564078e-05, + "loss": 1.4518, + "step": 2280 + }, + { + "epoch": 0.24, + "learning_rate": 1.884170361958334e-05, + "loss": 1.4334, + "step": 2281 + }, + { + "epoch": 0.24, + "learning_rate": 1.8839993088041502e-05, + "loss": 1.5131, + "step": 2282 + }, + { + "epoch": 0.24, + "learning_rate": 1.8838281372167724e-05, + "loss": 1.508, + "step": 2283 + }, + { + "epoch": 0.24, + "learning_rate": 1.8836568472191335e-05, + "loss": 1.4086, + "step": 2284 + }, + { + "epoch": 0.24, + "learning_rate": 1.883485438834182e-05, + "loss": 1.5021, + "step": 2285 + }, + { + "epoch": 0.24, + "learning_rate": 1.8833139120848817e-05, + "loss": 1.5083, + "step": 2286 + }, + { + "epoch": 0.24, + "learning_rate": 1.8831422669942137e-05, + "loss": 1.4162, + "step": 2287 + }, + { + "epoch": 0.24, + "learning_rate": 1.8829705035851734e-05, + "loss": 1.5494, + "step": 2288 + }, + { + "epoch": 0.24, + "learning_rate": 1.8827986218807724e-05, + "loss": 1.425, + "step": 2289 + }, + { + "epoch": 0.24, + "learning_rate": 1.8826266219040396e-05, + "loss": 1.5215, + "step": 2290 + }, + { + "epoch": 0.24, + "learning_rate": 1.8824545036780172e-05, + "loss": 1.5577, + "step": 2291 + }, + { + "epoch": 0.24, + "learning_rate": 1.8822822672257655e-05, + "loss": 1.4923, + "step": 2292 + }, + { + "epoch": 0.24, + "learning_rate": 1.8821099125703595e-05, + "loss": 1.4648, + "step": 2293 + }, + { + "epoch": 0.24, + "learning_rate": 1.8819374397348902e-05, + "loss": 1.471, + "step": 2294 + }, + { + "epoch": 0.24, + "learning_rate": 1.8817648487424648e-05, + "loss": 1.5658, + "step": 2295 + }, + { + "epoch": 0.24, + "learning_rate": 1.8815921396162058e-05, + "loss": 1.5348, + "step": 2296 + }, + { + "epoch": 0.24, + "learning_rate": 1.8814193123792518e-05, + "loss": 1.4081, + "step": 2297 + }, + { + "epoch": 0.24, + "learning_rate": 1.881246367054757e-05, + "loss": 1.4762, + "step": 2298 + }, + { + "epoch": 0.24, + "learning_rate": 1.8810733036658925e-05, + "loss": 1.4399, + "step": 2299 + }, + { + "epoch": 0.24, + "learning_rate": 1.8809001222358432e-05, + "loss": 1.4763, + "step": 2300 + }, + { + "epoch": 0.24, + "learning_rate": 1.880726822787812e-05, + "loss": 1.4874, + "step": 2301 + }, + { + "epoch": 0.24, + "learning_rate": 1.880553405345016e-05, + "loss": 1.4951, + "step": 2302 + }, + { + "epoch": 0.24, + "learning_rate": 1.8803798699306887e-05, + "loss": 1.4697, + "step": 2303 + }, + { + "epoch": 0.24, + "learning_rate": 1.880206216568079e-05, + "loss": 1.481, + "step": 2304 + }, + { + "epoch": 0.24, + "learning_rate": 1.880032445280453e-05, + "loss": 1.4485, + "step": 2305 + }, + { + "epoch": 0.24, + "learning_rate": 1.879858556091091e-05, + "loss": 1.4749, + "step": 2306 + }, + { + "epoch": 0.24, + "learning_rate": 1.8796845490232894e-05, + "loss": 1.5605, + "step": 2307 + }, + { + "epoch": 0.24, + "learning_rate": 1.879510424100361e-05, + "loss": 1.4835, + "step": 2308 + }, + { + "epoch": 0.24, + "learning_rate": 1.8793361813456346e-05, + "loss": 1.4344, + "step": 2309 + }, + { + "epoch": 0.24, + "learning_rate": 1.8791618207824532e-05, + "loss": 1.4571, + "step": 2310 + }, + { + "epoch": 0.24, + "learning_rate": 1.8789873424341772e-05, + "loss": 1.482, + "step": 2311 + }, + { + "epoch": 0.24, + "learning_rate": 1.8788127463241822e-05, + "loss": 1.4736, + "step": 2312 + }, + { + "epoch": 0.24, + "learning_rate": 1.8786380324758597e-05, + "loss": 1.4807, + "step": 2313 + }, + { + "epoch": 0.24, + "learning_rate": 1.8784632009126167e-05, + "loss": 1.4418, + "step": 2314 + }, + { + "epoch": 0.24, + "learning_rate": 1.878288251657876e-05, + "loss": 1.5248, + "step": 2315 + }, + { + "epoch": 0.24, + "learning_rate": 1.8781131847350768e-05, + "loss": 1.483, + "step": 2316 + }, + { + "epoch": 0.24, + "learning_rate": 1.877938000167673e-05, + "loss": 1.5474, + "step": 2317 + }, + { + "epoch": 0.24, + "learning_rate": 1.8777626979791347e-05, + "loss": 1.4671, + "step": 2318 + }, + { + "epoch": 0.24, + "learning_rate": 1.877587278192949e-05, + "loss": 1.3049, + "step": 2319 + }, + { + "epoch": 0.24, + "learning_rate": 1.877411740832616e-05, + "loss": 1.483, + "step": 2320 + }, + { + "epoch": 0.24, + "learning_rate": 1.877236085921655e-05, + "loss": 1.508, + "step": 2321 + }, + { + "epoch": 0.24, + "learning_rate": 1.8770603134835978e-05, + "loss": 1.4854, + "step": 2322 + }, + { + "epoch": 0.24, + "learning_rate": 1.8768844235419942e-05, + "loss": 1.4808, + "step": 2323 + }, + { + "epoch": 0.24, + "learning_rate": 1.8767084161204087e-05, + "loss": 1.5352, + "step": 2324 + }, + { + "epoch": 0.24, + "learning_rate": 1.8765322912424214e-05, + "loss": 1.5628, + "step": 2325 + }, + { + "epoch": 0.24, + "learning_rate": 1.8763560489316292e-05, + "loss": 1.494, + "step": 2326 + }, + { + "epoch": 0.24, + "learning_rate": 1.876179689211643e-05, + "loss": 1.509, + "step": 2327 + }, + { + "epoch": 0.24, + "learning_rate": 1.8760032121060918e-05, + "loss": 1.5021, + "step": 2328 + }, + { + "epoch": 0.24, + "learning_rate": 1.875826617638618e-05, + "loss": 1.4179, + "step": 2329 + }, + { + "epoch": 0.24, + "learning_rate": 1.8756499058328813e-05, + "loss": 1.4302, + "step": 2330 + }, + { + "epoch": 0.24, + "learning_rate": 1.8754730767125564e-05, + "loss": 1.4959, + "step": 2331 + }, + { + "epoch": 0.24, + "learning_rate": 1.8752961303013336e-05, + "loss": 1.4423, + "step": 2332 + }, + { + "epoch": 0.24, + "learning_rate": 1.8751190666229194e-05, + "loss": 1.4564, + "step": 2333 + }, + { + "epoch": 0.24, + "learning_rate": 1.8749418857010358e-05, + "loss": 1.4775, + "step": 2334 + }, + { + "epoch": 0.24, + "learning_rate": 1.8747645875594203e-05, + "loss": 1.4182, + "step": 2335 + }, + { + "epoch": 0.24, + "learning_rate": 1.8745871722218265e-05, + "loss": 1.3957, + "step": 2336 + }, + { + "epoch": 0.25, + "learning_rate": 1.8744096397120235e-05, + "loss": 1.4633, + "step": 2337 + }, + { + "epoch": 0.25, + "learning_rate": 1.874231990053796e-05, + "loss": 1.5512, + "step": 2338 + }, + { + "epoch": 0.25, + "learning_rate": 1.8740542232709444e-05, + "loss": 1.3461, + "step": 2339 + }, + { + "epoch": 0.25, + "learning_rate": 1.8738763393872848e-05, + "loss": 1.4754, + "step": 2340 + }, + { + "epoch": 0.25, + "learning_rate": 1.8736983384266495e-05, + "loss": 1.5448, + "step": 2341 + }, + { + "epoch": 0.25, + "learning_rate": 1.8735202204128854e-05, + "loss": 1.4491, + "step": 2342 + }, + { + "epoch": 0.25, + "learning_rate": 1.8733419853698566e-05, + "loss": 1.457, + "step": 2343 + }, + { + "epoch": 0.25, + "learning_rate": 1.8731636333214414e-05, + "loss": 1.4314, + "step": 2344 + }, + { + "epoch": 0.25, + "learning_rate": 1.8729851642915345e-05, + "loss": 1.3979, + "step": 2345 + }, + { + "epoch": 0.25, + "learning_rate": 1.8728065783040464e-05, + "loss": 1.4146, + "step": 2346 + }, + { + "epoch": 0.25, + "learning_rate": 1.8726278753829027e-05, + "loss": 1.4361, + "step": 2347 + }, + { + "epoch": 0.25, + "learning_rate": 1.872449055552045e-05, + "loss": 1.4989, + "step": 2348 + }, + { + "epoch": 0.25, + "learning_rate": 1.872270118835431e-05, + "loss": 1.5062, + "step": 2349 + }, + { + "epoch": 0.25, + "learning_rate": 1.872091065257033e-05, + "loss": 1.4509, + "step": 2350 + }, + { + "epoch": 0.25, + "learning_rate": 1.8719118948408403e-05, + "loss": 1.4631, + "step": 2351 + }, + { + "epoch": 0.25, + "learning_rate": 1.8717326076108566e-05, + "loss": 1.5119, + "step": 2352 + }, + { + "epoch": 0.25, + "learning_rate": 1.8715532035911017e-05, + "loss": 1.6347, + "step": 2353 + }, + { + "epoch": 0.25, + "learning_rate": 1.8713736828056115e-05, + "loss": 1.5526, + "step": 2354 + }, + { + "epoch": 0.25, + "learning_rate": 1.8711940452784368e-05, + "loss": 1.6348, + "step": 2355 + }, + { + "epoch": 0.25, + "learning_rate": 1.871014291033645e-05, + "loss": 1.5183, + "step": 2356 + }, + { + "epoch": 0.25, + "learning_rate": 1.8708344200953182e-05, + "loss": 1.458, + "step": 2357 + }, + { + "epoch": 0.25, + "learning_rate": 1.8706544324875545e-05, + "loss": 1.524, + "step": 2358 + }, + { + "epoch": 0.25, + "learning_rate": 1.8704743282344672e-05, + "loss": 1.4479, + "step": 2359 + }, + { + "epoch": 0.25, + "learning_rate": 1.870294107360186e-05, + "loss": 1.5408, + "step": 2360 + }, + { + "epoch": 0.25, + "learning_rate": 1.8701137698888563e-05, + "loss": 1.5007, + "step": 2361 + }, + { + "epoch": 0.25, + "learning_rate": 1.8699333158446382e-05, + "loss": 1.5132, + "step": 2362 + }, + { + "epoch": 0.25, + "learning_rate": 1.869752745251708e-05, + "loss": 1.4263, + "step": 2363 + }, + { + "epoch": 0.25, + "learning_rate": 1.8695720581342574e-05, + "loss": 1.422, + "step": 2364 + }, + { + "epoch": 0.25, + "learning_rate": 1.869391254516494e-05, + "loss": 1.4411, + "step": 2365 + }, + { + "epoch": 0.25, + "learning_rate": 1.8692103344226406e-05, + "loss": 1.4594, + "step": 2366 + }, + { + "epoch": 0.25, + "learning_rate": 1.8690292978769364e-05, + "loss": 1.4992, + "step": 2367 + }, + { + "epoch": 0.25, + "learning_rate": 1.868848144903635e-05, + "loss": 1.4822, + "step": 2368 + }, + { + "epoch": 0.25, + "learning_rate": 1.8686668755270064e-05, + "loss": 1.5402, + "step": 2369 + }, + { + "epoch": 0.25, + "learning_rate": 1.8684854897713363e-05, + "loss": 1.5268, + "step": 2370 + }, + { + "epoch": 0.25, + "learning_rate": 1.8683039876609258e-05, + "loss": 1.5587, + "step": 2371 + }, + { + "epoch": 0.25, + "learning_rate": 1.868122369220091e-05, + "loss": 1.4214, + "step": 2372 + }, + { + "epoch": 0.25, + "learning_rate": 1.8679406344731645e-05, + "loss": 1.5089, + "step": 2373 + }, + { + "epoch": 0.25, + "learning_rate": 1.867758783444494e-05, + "loss": 1.5067, + "step": 2374 + }, + { + "epoch": 0.25, + "learning_rate": 1.8675768161584427e-05, + "loss": 2.0616, + "step": 2375 + }, + { + "epoch": 0.25, + "learning_rate": 1.8673947326393903e-05, + "loss": 1.5617, + "step": 2376 + }, + { + "epoch": 0.25, + "learning_rate": 1.86721253291173e-05, + "loss": 1.4422, + "step": 2377 + }, + { + "epoch": 0.25, + "learning_rate": 1.867030216999873e-05, + "loss": 1.4727, + "step": 2378 + }, + { + "epoch": 0.25, + "learning_rate": 1.8668477849282443e-05, + "loss": 1.4152, + "step": 2379 + }, + { + "epoch": 0.25, + "learning_rate": 1.8666652367212856e-05, + "loss": 1.4376, + "step": 2380 + }, + { + "epoch": 0.25, + "learning_rate": 1.8664825724034534e-05, + "loss": 1.393, + "step": 2381 + }, + { + "epoch": 0.25, + "learning_rate": 1.8662997919992197e-05, + "loss": 1.4864, + "step": 2382 + }, + { + "epoch": 0.25, + "learning_rate": 1.866116895533073e-05, + "loss": 1.4261, + "step": 2383 + }, + { + "epoch": 0.25, + "learning_rate": 1.8659338830295163e-05, + "loss": 1.4555, + "step": 2384 + }, + { + "epoch": 0.25, + "learning_rate": 1.8657507545130687e-05, + "loss": 1.4939, + "step": 2385 + }, + { + "epoch": 0.25, + "learning_rate": 1.865567510008265e-05, + "loss": 1.4123, + "step": 2386 + }, + { + "epoch": 0.25, + "learning_rate": 1.8653841495396546e-05, + "loss": 1.4459, + "step": 2387 + }, + { + "epoch": 0.25, + "learning_rate": 1.8652006731318038e-05, + "loss": 1.396, + "step": 2388 + }, + { + "epoch": 0.25, + "eval_loss": 1.5139706134796143, + "eval_runtime": 77.2904, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 2388 + }, + { + "epoch": 0.25, + "learning_rate": 1.8650170808092936e-05, + "loss": 1.4666, + "step": 2389 + }, + { + "epoch": 0.25, + "learning_rate": 1.86483337259672e-05, + "loss": 1.5154, + "step": 2390 + }, + { + "epoch": 0.25, + "learning_rate": 1.864649548518696e-05, + "loss": 1.5163, + "step": 2391 + }, + { + "epoch": 0.25, + "learning_rate": 1.864465608599849e-05, + "loss": 1.4734, + "step": 2392 + }, + { + "epoch": 0.25, + "learning_rate": 1.864281552864822e-05, + "loss": 1.5217, + "step": 2393 + }, + { + "epoch": 0.25, + "learning_rate": 1.8640973813382737e-05, + "loss": 1.4694, + "step": 2394 + }, + { + "epoch": 0.25, + "learning_rate": 1.863913094044879e-05, + "loss": 1.4761, + "step": 2395 + }, + { + "epoch": 0.25, + "learning_rate": 1.863728691009327e-05, + "loss": 1.4766, + "step": 2396 + }, + { + "epoch": 0.25, + "learning_rate": 1.863544172256323e-05, + "loss": 1.5695, + "step": 2397 + }, + { + "epoch": 0.25, + "learning_rate": 1.8633595378105882e-05, + "loss": 1.5079, + "step": 2398 + }, + { + "epoch": 0.25, + "learning_rate": 1.8631747876968584e-05, + "loss": 1.4154, + "step": 2399 + }, + { + "epoch": 0.25, + "learning_rate": 1.862989921939886e-05, + "loss": 1.4488, + "step": 2400 + }, + { + "epoch": 0.25, + "learning_rate": 1.8628049405644376e-05, + "loss": 1.4279, + "step": 2401 + }, + { + "epoch": 0.25, + "learning_rate": 1.8626198435952966e-05, + "loss": 1.4896, + "step": 2402 + }, + { + "epoch": 0.25, + "learning_rate": 1.8624346310572602e-05, + "loss": 1.4315, + "step": 2403 + }, + { + "epoch": 0.25, + "learning_rate": 1.862249302975143e-05, + "loss": 1.4919, + "step": 2404 + }, + { + "epoch": 0.25, + "learning_rate": 1.8620638593737743e-05, + "loss": 1.4561, + "step": 2405 + }, + { + "epoch": 0.25, + "learning_rate": 1.8618783002779985e-05, + "loss": 1.4622, + "step": 2406 + }, + { + "epoch": 0.25, + "learning_rate": 1.8616926257126754e-05, + "loss": 1.4917, + "step": 2407 + }, + { + "epoch": 0.25, + "learning_rate": 1.861506835702681e-05, + "loss": 1.4962, + "step": 2408 + }, + { + "epoch": 0.25, + "learning_rate": 1.861320930272906e-05, + "loss": 1.4164, + "step": 2409 + }, + { + "epoch": 0.25, + "learning_rate": 1.8611349094482578e-05, + "loss": 1.4889, + "step": 2410 + }, + { + "epoch": 0.25, + "learning_rate": 1.8609487732536576e-05, + "loss": 1.543, + "step": 2411 + }, + { + "epoch": 0.25, + "learning_rate": 1.8607625217140433e-05, + "loss": 1.5417, + "step": 2412 + }, + { + "epoch": 0.25, + "learning_rate": 1.8605761548543674e-05, + "loss": 1.5304, + "step": 2413 + }, + { + "epoch": 0.25, + "learning_rate": 1.860389672699599e-05, + "loss": 1.4725, + "step": 2414 + }, + { + "epoch": 0.25, + "learning_rate": 1.860203075274721e-05, + "loss": 1.4745, + "step": 2415 + }, + { + "epoch": 0.25, + "learning_rate": 1.8600163626047334e-05, + "loss": 1.4656, + "step": 2416 + }, + { + "epoch": 0.25, + "learning_rate": 1.8598295347146503e-05, + "loss": 1.5287, + "step": 2417 + }, + { + "epoch": 0.25, + "learning_rate": 1.8596425916295023e-05, + "loss": 1.5024, + "step": 2418 + }, + { + "epoch": 0.25, + "learning_rate": 1.8594555333743348e-05, + "loss": 1.4527, + "step": 2419 + }, + { + "epoch": 0.25, + "learning_rate": 1.859268359974209e-05, + "loss": 1.4897, + "step": 2420 + }, + { + "epoch": 0.25, + "learning_rate": 1.859081071454201e-05, + "loss": 1.3554, + "step": 2421 + }, + { + "epoch": 0.25, + "learning_rate": 1.858893667839403e-05, + "loss": 1.4004, + "step": 2422 + }, + { + "epoch": 0.25, + "learning_rate": 1.858706149154922e-05, + "loss": 1.5582, + "step": 2423 + }, + { + "epoch": 0.25, + "learning_rate": 1.8585185154258803e-05, + "loss": 1.505, + "step": 2424 + }, + { + "epoch": 0.25, + "learning_rate": 1.858330766677417e-05, + "loss": 1.5043, + "step": 2425 + }, + { + "epoch": 0.25, + "learning_rate": 1.858142902934685e-05, + "loss": 1.439, + "step": 2426 + }, + { + "epoch": 0.25, + "learning_rate": 1.857954924222853e-05, + "loss": 1.4927, + "step": 2427 + }, + { + "epoch": 0.25, + "learning_rate": 1.8577668305671056e-05, + "loss": 1.5395, + "step": 2428 + }, + { + "epoch": 0.25, + "learning_rate": 1.8575786219926427e-05, + "loss": 1.4737, + "step": 2429 + }, + { + "epoch": 0.25, + "learning_rate": 1.8573902985246794e-05, + "loss": 1.6151, + "step": 2430 + }, + { + "epoch": 0.25, + "learning_rate": 1.857201860188446e-05, + "loss": 1.4313, + "step": 2431 + }, + { + "epoch": 0.26, + "learning_rate": 1.857013307009188e-05, + "loss": 1.4509, + "step": 2432 + }, + { + "epoch": 0.26, + "learning_rate": 1.8568246390121673e-05, + "loss": 1.3998, + "step": 2433 + }, + { + "epoch": 0.26, + "learning_rate": 1.8566358562226603e-05, + "loss": 1.5268, + "step": 2434 + }, + { + "epoch": 0.26, + "learning_rate": 1.8564469586659593e-05, + "loss": 1.4369, + "step": 2435 + }, + { + "epoch": 0.26, + "learning_rate": 1.8562579463673713e-05, + "loss": 1.4759, + "step": 2436 + }, + { + "epoch": 0.26, + "learning_rate": 1.8560688193522197e-05, + "loss": 1.4092, + "step": 2437 + }, + { + "epoch": 0.26, + "learning_rate": 1.855879577645842e-05, + "loss": 1.43, + "step": 2438 + }, + { + "epoch": 0.26, + "learning_rate": 1.855690221273592e-05, + "loss": 1.5143, + "step": 2439 + }, + { + "epoch": 0.26, + "learning_rate": 1.8555007502608385e-05, + "loss": 1.5482, + "step": 2440 + }, + { + "epoch": 0.26, + "learning_rate": 1.855311164632966e-05, + "loss": 1.4406, + "step": 2441 + }, + { + "epoch": 0.26, + "learning_rate": 1.8551214644153738e-05, + "loss": 1.4551, + "step": 2442 + }, + { + "epoch": 0.26, + "learning_rate": 1.8549316496334774e-05, + "loss": 1.4663, + "step": 2443 + }, + { + "epoch": 0.26, + "learning_rate": 1.8547417203127064e-05, + "loss": 1.4732, + "step": 2444 + }, + { + "epoch": 0.26, + "learning_rate": 1.8545516764785067e-05, + "loss": 1.5378, + "step": 2445 + }, + { + "epoch": 0.26, + "learning_rate": 1.8543615181563397e-05, + "loss": 1.4448, + "step": 2446 + }, + { + "epoch": 0.26, + "learning_rate": 1.854171245371681e-05, + "loss": 1.2861, + "step": 2447 + }, + { + "epoch": 0.26, + "learning_rate": 1.8539808581500228e-05, + "loss": 1.4405, + "step": 2448 + }, + { + "epoch": 0.26, + "learning_rate": 1.8537903565168716e-05, + "loss": 1.4876, + "step": 2449 + }, + { + "epoch": 0.26, + "learning_rate": 1.8535997404977506e-05, + "loss": 1.4119, + "step": 2450 + }, + { + "epoch": 0.26, + "learning_rate": 1.8534090101181967e-05, + "loss": 1.4451, + "step": 2451 + }, + { + "epoch": 0.26, + "learning_rate": 1.8532181654037632e-05, + "loss": 1.4035, + "step": 2452 + }, + { + "epoch": 0.26, + "learning_rate": 1.853027206380018e-05, + "loss": 1.4624, + "step": 2453 + }, + { + "epoch": 0.26, + "learning_rate": 1.852836133072545e-05, + "loss": 1.4935, + "step": 2454 + }, + { + "epoch": 0.26, + "learning_rate": 1.8526449455069434e-05, + "loss": 1.4834, + "step": 2455 + }, + { + "epoch": 0.26, + "learning_rate": 1.8524536437088266e-05, + "loss": 1.498, + "step": 2456 + }, + { + "epoch": 0.26, + "learning_rate": 1.8522622277038247e-05, + "loss": 1.3417, + "step": 2457 + }, + { + "epoch": 0.26, + "learning_rate": 1.852070697517583e-05, + "loss": 1.4455, + "step": 2458 + }, + { + "epoch": 0.26, + "learning_rate": 1.8518790531757607e-05, + "loss": 1.4119, + "step": 2459 + }, + { + "epoch": 0.26, + "learning_rate": 1.8516872947040337e-05, + "loss": 1.558, + "step": 2460 + }, + { + "epoch": 0.26, + "learning_rate": 1.8514954221280926e-05, + "loss": 1.4862, + "step": 2461 + }, + { + "epoch": 0.26, + "learning_rate": 1.8513034354736433e-05, + "loss": 1.6806, + "step": 2462 + }, + { + "epoch": 0.26, + "learning_rate": 1.8511113347664072e-05, + "loss": 1.438, + "step": 2463 + }, + { + "epoch": 0.26, + "learning_rate": 1.850919120032121e-05, + "loss": 1.4975, + "step": 2464 + }, + { + "epoch": 0.26, + "learning_rate": 1.850726791296536e-05, + "loss": 1.4409, + "step": 2465 + }, + { + "epoch": 0.26, + "learning_rate": 1.85053434858542e-05, + "loss": 1.4769, + "step": 2466 + }, + { + "epoch": 0.26, + "learning_rate": 1.8503417919245548e-05, + "loss": 1.5823, + "step": 2467 + }, + { + "epoch": 0.26, + "learning_rate": 1.8501491213397386e-05, + "loss": 1.4045, + "step": 2468 + }, + { + "epoch": 0.26, + "learning_rate": 1.8499563368567837e-05, + "loss": 1.4828, + "step": 2469 + }, + { + "epoch": 0.26, + "learning_rate": 1.849763438501519e-05, + "loss": 1.4684, + "step": 2470 + }, + { + "epoch": 0.26, + "learning_rate": 1.8495704262997873e-05, + "loss": 1.4577, + "step": 2471 + }, + { + "epoch": 0.26, + "learning_rate": 1.8493773002774475e-05, + "loss": 1.4759, + "step": 2472 + }, + { + "epoch": 0.26, + "learning_rate": 1.8491840604603736e-05, + "loss": 1.4259, + "step": 2473 + }, + { + "epoch": 0.26, + "learning_rate": 1.8489907068744543e-05, + "loss": 1.4717, + "step": 2474 + }, + { + "epoch": 0.26, + "learning_rate": 1.848797239545595e-05, + "loss": 1.4247, + "step": 2475 + }, + { + "epoch": 0.26, + "learning_rate": 1.8486036584997143e-05, + "loss": 1.4954, + "step": 2476 + }, + { + "epoch": 0.26, + "learning_rate": 1.8484099637627472e-05, + "loss": 1.4926, + "step": 2477 + }, + { + "epoch": 0.26, + "learning_rate": 1.8482161553606447e-05, + "loss": 1.487, + "step": 2478 + }, + { + "epoch": 0.26, + "learning_rate": 1.8480222333193715e-05, + "loss": 1.4553, + "step": 2479 + }, + { + "epoch": 0.26, + "learning_rate": 1.847828197664908e-05, + "loss": 1.4862, + "step": 2480 + }, + { + "epoch": 0.26, + "learning_rate": 1.8476340484232508e-05, + "loss": 1.4867, + "step": 2481 + }, + { + "epoch": 0.26, + "learning_rate": 1.8474397856204097e-05, + "loss": 1.4736, + "step": 2482 + }, + { + "epoch": 0.26, + "learning_rate": 1.8472454092824122e-05, + "loss": 1.4254, + "step": 2483 + }, + { + "epoch": 0.26, + "learning_rate": 1.8470509194352987e-05, + "loss": 1.4455, + "step": 2484 + }, + { + "epoch": 0.26, + "learning_rate": 1.8468563161051263e-05, + "loss": 1.4402, + "step": 2485 + }, + { + "epoch": 0.26, + "learning_rate": 1.846661599317967e-05, + "loss": 1.4611, + "step": 2486 + }, + { + "epoch": 0.26, + "learning_rate": 1.8464667690999073e-05, + "loss": 1.4814, + "step": 2487 + }, + { + "epoch": 0.26, + "learning_rate": 1.8462718254770503e-05, + "loss": 1.4559, + "step": 2488 + }, + { + "epoch": 0.26, + "learning_rate": 1.8460767684755127e-05, + "loss": 1.4667, + "step": 2489 + }, + { + "epoch": 0.26, + "learning_rate": 1.8458815981214274e-05, + "loss": 1.4427, + "step": 2490 + }, + { + "epoch": 0.26, + "learning_rate": 1.845686314440942e-05, + "loss": 1.4055, + "step": 2491 + }, + { + "epoch": 0.26, + "learning_rate": 1.8454909174602198e-05, + "loss": 1.5563, + "step": 2492 + }, + { + "epoch": 0.26, + "learning_rate": 1.845295407205439e-05, + "loss": 1.4631, + "step": 2493 + }, + { + "epoch": 0.26, + "learning_rate": 1.8450997837027925e-05, + "loss": 1.4887, + "step": 2494 + }, + { + "epoch": 0.26, + "learning_rate": 1.8449040469784895e-05, + "loss": 1.5212, + "step": 2495 + }, + { + "epoch": 0.26, + "learning_rate": 1.844708197058753e-05, + "loss": 1.5582, + "step": 2496 + }, + { + "epoch": 0.26, + "learning_rate": 1.844512233969822e-05, + "loss": 1.4599, + "step": 2497 + }, + { + "epoch": 0.26, + "learning_rate": 1.844316157737951e-05, + "loss": 1.4546, + "step": 2498 + }, + { + "epoch": 0.26, + "learning_rate": 1.844119968389409e-05, + "loss": 1.4631, + "step": 2499 + }, + { + "epoch": 0.26, + "learning_rate": 1.84392366595048e-05, + "loss": 1.4817, + "step": 2500 + }, + { + "epoch": 0.26, + "learning_rate": 1.8437272504474636e-05, + "loss": 1.4214, + "step": 2501 + }, + { + "epoch": 0.26, + "learning_rate": 1.8435307219066744e-05, + "loss": 1.471, + "step": 2502 + }, + { + "epoch": 0.26, + "learning_rate": 1.8433340803544424e-05, + "loss": 1.4693, + "step": 2503 + }, + { + "epoch": 0.26, + "learning_rate": 1.8431373258171127e-05, + "loss": 1.6297, + "step": 2504 + }, + { + "epoch": 0.26, + "learning_rate": 1.842940458321045e-05, + "loss": 1.5916, + "step": 2505 + }, + { + "epoch": 0.26, + "learning_rate": 1.842743477892614e-05, + "loss": 1.4754, + "step": 2506 + }, + { + "epoch": 0.26, + "learning_rate": 1.842546384558211e-05, + "loss": 1.4828, + "step": 2507 + }, + { + "epoch": 0.26, + "learning_rate": 1.842349178344241e-05, + "loss": 1.4239, + "step": 2508 + }, + { + "epoch": 0.26, + "learning_rate": 1.8421518592771243e-05, + "loss": 1.5028, + "step": 2509 + }, + { + "epoch": 0.26, + "learning_rate": 1.841954427383297e-05, + "loss": 1.4848, + "step": 2510 + }, + { + "epoch": 0.26, + "learning_rate": 1.8417568826892097e-05, + "loss": 1.4617, + "step": 2511 + }, + { + "epoch": 0.26, + "learning_rate": 1.8415592252213284e-05, + "loss": 1.4266, + "step": 2512 + }, + { + "epoch": 0.26, + "learning_rate": 1.8413614550061344e-05, + "loss": 1.4321, + "step": 2513 + }, + { + "epoch": 0.26, + "learning_rate": 1.841163572070123e-05, + "loss": 1.4693, + "step": 2514 + }, + { + "epoch": 0.26, + "learning_rate": 1.840965576439806e-05, + "loss": 1.4257, + "step": 2515 + }, + { + "epoch": 0.26, + "learning_rate": 1.84076746814171e-05, + "loss": 1.4488, + "step": 2516 + }, + { + "epoch": 0.26, + "learning_rate": 1.840569247202376e-05, + "loss": 1.5348, + "step": 2517 + }, + { + "epoch": 0.26, + "learning_rate": 1.8403709136483604e-05, + "loss": 1.477, + "step": 2518 + }, + { + "epoch": 0.26, + "learning_rate": 1.840172467506235e-05, + "loss": 1.443, + "step": 2519 + }, + { + "epoch": 0.26, + "learning_rate": 1.839973908802587e-05, + "loss": 1.4772, + "step": 2520 + }, + { + "epoch": 0.26, + "learning_rate": 1.839775237564017e-05, + "loss": 1.4443, + "step": 2521 + }, + { + "epoch": 0.26, + "learning_rate": 1.839576453817143e-05, + "loss": 1.4063, + "step": 2522 + }, + { + "epoch": 0.26, + "learning_rate": 1.8393775575885963e-05, + "loss": 1.5178, + "step": 2523 + }, + { + "epoch": 0.26, + "learning_rate": 1.8391785489050235e-05, + "loss": 1.4337, + "step": 2524 + }, + { + "epoch": 0.26, + "learning_rate": 1.8389794277930875e-05, + "loss": 1.4512, + "step": 2525 + }, + { + "epoch": 0.26, + "learning_rate": 1.838780194279465e-05, + "loss": 1.5578, + "step": 2526 + }, + { + "epoch": 0.26, + "learning_rate": 1.8385808483908484e-05, + "loss": 1.4606, + "step": 2527 + }, + { + "epoch": 0.27, + "learning_rate": 1.8383813901539444e-05, + "loss": 1.4957, + "step": 2528 + }, + { + "epoch": 0.27, + "learning_rate": 1.838181819595476e-05, + "loss": 1.4914, + "step": 2529 + }, + { + "epoch": 0.27, + "learning_rate": 1.8379821367421802e-05, + "loss": 1.4785, + "step": 2530 + }, + { + "epoch": 0.27, + "learning_rate": 1.837782341620809e-05, + "loss": 1.4052, + "step": 2531 + }, + { + "epoch": 0.27, + "learning_rate": 1.8375824342581303e-05, + "loss": 1.4807, + "step": 2532 + }, + { + "epoch": 0.27, + "learning_rate": 1.8373824146809264e-05, + "loss": 1.4313, + "step": 2533 + }, + { + "epoch": 0.27, + "learning_rate": 1.8371822829159945e-05, + "loss": 1.4374, + "step": 2534 + }, + { + "epoch": 0.27, + "learning_rate": 1.836982038990148e-05, + "loss": 1.4482, + "step": 2535 + }, + { + "epoch": 0.27, + "learning_rate": 1.8367816829302133e-05, + "loss": 1.5231, + "step": 2536 + }, + { + "epoch": 0.27, + "learning_rate": 1.8365812147630337e-05, + "loss": 1.4101, + "step": 2537 + }, + { + "epoch": 0.27, + "learning_rate": 1.8363806345154666e-05, + "loss": 1.4372, + "step": 2538 + }, + { + "epoch": 0.27, + "learning_rate": 1.8361799422143845e-05, + "loss": 1.4808, + "step": 2539 + }, + { + "epoch": 0.27, + "learning_rate": 1.835979137886675e-05, + "loss": 1.3515, + "step": 2540 + }, + { + "epoch": 0.27, + "learning_rate": 1.8357782215592412e-05, + "loss": 1.5284, + "step": 2541 + }, + { + "epoch": 0.27, + "learning_rate": 1.835577193259e-05, + "loss": 1.4222, + "step": 2542 + }, + { + "epoch": 0.27, + "learning_rate": 1.8353760530128846e-05, + "loss": 1.4522, + "step": 2543 + }, + { + "epoch": 0.27, + "learning_rate": 1.835174800847842e-05, + "loss": 1.4487, + "step": 2544 + }, + { + "epoch": 0.27, + "learning_rate": 1.8349734367908355e-05, + "loss": 1.3688, + "step": 2545 + }, + { + "epoch": 0.27, + "learning_rate": 1.8347719608688422e-05, + "loss": 1.483, + "step": 2546 + }, + { + "epoch": 0.27, + "learning_rate": 1.8345703731088554e-05, + "loss": 1.4733, + "step": 2547 + }, + { + "epoch": 0.27, + "learning_rate": 1.8343686735378816e-05, + "loss": 1.4594, + "step": 2548 + }, + { + "epoch": 0.27, + "learning_rate": 1.834166862182944e-05, + "loss": 1.4648, + "step": 2549 + }, + { + "epoch": 0.27, + "learning_rate": 1.8339649390710807e-05, + "loss": 1.5249, + "step": 2550 + }, + { + "epoch": 0.27, + "learning_rate": 1.8337629042293434e-05, + "loss": 1.4744, + "step": 2551 + }, + { + "epoch": 0.27, + "learning_rate": 1.8335607576847994e-05, + "loss": 1.5094, + "step": 2552 + }, + { + "epoch": 0.27, + "learning_rate": 1.8333584994645318e-05, + "loss": 1.5122, + "step": 2553 + }, + { + "epoch": 0.27, + "learning_rate": 1.8331561295956374e-05, + "loss": 1.537, + "step": 2554 + }, + { + "epoch": 0.27, + "learning_rate": 1.832953648105229e-05, + "loss": 1.4691, + "step": 2555 + }, + { + "epoch": 0.27, + "learning_rate": 1.8327510550204343e-05, + "loss": 1.4969, + "step": 2556 + }, + { + "epoch": 0.27, + "learning_rate": 1.8325483503683944e-05, + "loss": 1.4596, + "step": 2557 + }, + { + "epoch": 0.27, + "learning_rate": 1.8323455341762675e-05, + "loss": 1.435, + "step": 2558 + }, + { + "epoch": 0.27, + "learning_rate": 1.8321426064712255e-05, + "loss": 1.4883, + "step": 2559 + }, + { + "epoch": 0.27, + "learning_rate": 1.8319395672804554e-05, + "loss": 1.3758, + "step": 2560 + }, + { + "epoch": 0.27, + "learning_rate": 1.8317364166311592e-05, + "loss": 1.4352, + "step": 2561 + }, + { + "epoch": 0.27, + "learning_rate": 1.831533154550554e-05, + "loss": 1.5072, + "step": 2562 + }, + { + "epoch": 0.27, + "learning_rate": 1.8313297810658718e-05, + "loss": 1.4476, + "step": 2563 + }, + { + "epoch": 0.27, + "learning_rate": 1.831126296204359e-05, + "loss": 1.507, + "step": 2564 + }, + { + "epoch": 0.27, + "learning_rate": 1.8309226999932777e-05, + "loss": 1.4677, + "step": 2565 + }, + { + "epoch": 0.27, + "learning_rate": 1.8307189924599044e-05, + "loss": 1.4537, + "step": 2566 + }, + { + "epoch": 0.27, + "learning_rate": 1.8305151736315307e-05, + "loss": 1.4584, + "step": 2567 + }, + { + "epoch": 0.27, + "learning_rate": 1.8303112435354634e-05, + "loss": 1.4944, + "step": 2568 + }, + { + "epoch": 0.27, + "learning_rate": 1.8301072021990232e-05, + "loss": 1.4379, + "step": 2569 + }, + { + "epoch": 0.27, + "learning_rate": 1.8299030496495475e-05, + "loss": 1.539, + "step": 2570 + }, + { + "epoch": 0.27, + "learning_rate": 1.829698785914386e-05, + "loss": 1.4421, + "step": 2571 + }, + { + "epoch": 0.27, + "learning_rate": 1.8294944110209063e-05, + "loss": 1.4693, + "step": 2572 + }, + { + "epoch": 0.27, + "learning_rate": 1.8292899249964887e-05, + "loss": 1.3239, + "step": 2573 + }, + { + "epoch": 0.27, + "learning_rate": 1.8290853278685284e-05, + "loss": 1.472, + "step": 2574 + }, + { + "epoch": 0.27, + "learning_rate": 1.8288806196644374e-05, + "loss": 1.536, + "step": 2575 + }, + { + "epoch": 0.27, + "learning_rate": 1.8286758004116405e-05, + "loss": 1.4644, + "step": 2576 + }, + { + "epoch": 0.27, + "learning_rate": 1.8284708701375783e-05, + "loss": 1.4537, + "step": 2577 + }, + { + "epoch": 0.27, + "learning_rate": 1.8282658288697067e-05, + "loss": 1.4359, + "step": 2578 + }, + { + "epoch": 0.27, + "learning_rate": 1.8280606766354955e-05, + "loss": 1.4842, + "step": 2579 + }, + { + "epoch": 0.27, + "learning_rate": 1.8278554134624302e-05, + "loss": 1.4664, + "step": 2580 + }, + { + "epoch": 0.27, + "learning_rate": 1.8276500393780105e-05, + "loss": 1.4632, + "step": 2581 + }, + { + "epoch": 0.27, + "learning_rate": 1.827444554409751e-05, + "loss": 1.4996, + "step": 2582 + }, + { + "epoch": 0.27, + "learning_rate": 1.827238958585182e-05, + "loss": 1.3399, + "step": 2583 + }, + { + "epoch": 0.27, + "learning_rate": 1.8270332519318476e-05, + "loss": 1.3928, + "step": 2584 + }, + { + "epoch": 0.27, + "learning_rate": 1.8268274344773074e-05, + "loss": 1.4993, + "step": 2585 + }, + { + "epoch": 0.27, + "learning_rate": 1.8266215062491356e-05, + "loss": 1.5398, + "step": 2586 + }, + { + "epoch": 0.27, + "learning_rate": 1.826415467274921e-05, + "loss": 1.4353, + "step": 2587 + }, + { + "epoch": 0.27, + "eval_loss": 1.5104212760925293, + "eval_runtime": 77.3448, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2587 + }, + { + "epoch": 0.27, + "learning_rate": 1.8262093175822685e-05, + "loss": 1.4889, + "step": 2588 + }, + { + "epoch": 0.27, + "learning_rate": 1.826003057198796e-05, + "loss": 1.4912, + "step": 2589 + }, + { + "epoch": 0.27, + "learning_rate": 1.825796686152137e-05, + "loss": 1.4884, + "step": 2590 + }, + { + "epoch": 0.27, + "learning_rate": 1.8255902044699404e-05, + "loss": 1.478, + "step": 2591 + }, + { + "epoch": 0.27, + "learning_rate": 1.8253836121798692e-05, + "loss": 1.6549, + "step": 2592 + }, + { + "epoch": 0.27, + "learning_rate": 1.8251769093096018e-05, + "loss": 1.5146, + "step": 2593 + }, + { + "epoch": 0.27, + "learning_rate": 1.8249700958868306e-05, + "loss": 1.4797, + "step": 2594 + }, + { + "epoch": 0.27, + "learning_rate": 1.8247631719392634e-05, + "loss": 1.4655, + "step": 2595 + }, + { + "epoch": 0.27, + "learning_rate": 1.824556137494623e-05, + "loss": 1.4517, + "step": 2596 + }, + { + "epoch": 0.27, + "learning_rate": 1.8243489925806458e-05, + "loss": 1.4936, + "step": 2597 + }, + { + "epoch": 0.27, + "learning_rate": 1.8241417372250852e-05, + "loss": 1.4614, + "step": 2598 + }, + { + "epoch": 0.27, + "learning_rate": 1.8239343714557073e-05, + "loss": 1.4475, + "step": 2599 + }, + { + "epoch": 0.27, + "learning_rate": 1.8237268953002937e-05, + "loss": 1.5435, + "step": 2600 + }, + { + "epoch": 0.27, + "learning_rate": 1.8235193087866413e-05, + "loss": 1.4616, + "step": 2601 + }, + { + "epoch": 0.27, + "learning_rate": 1.8233116119425612e-05, + "loss": 1.4578, + "step": 2602 + }, + { + "epoch": 0.27, + "learning_rate": 1.8231038047958795e-05, + "loss": 1.434, + "step": 2603 + }, + { + "epoch": 0.27, + "learning_rate": 1.8228958873744368e-05, + "loss": 1.5335, + "step": 2604 + }, + { + "epoch": 0.27, + "learning_rate": 1.8226878597060887e-05, + "loss": 1.415, + "step": 2605 + }, + { + "epoch": 0.27, + "learning_rate": 1.8224797218187058e-05, + "loss": 1.6165, + "step": 2606 + }, + { + "epoch": 0.27, + "learning_rate": 1.822271473740173e-05, + "loss": 1.372, + "step": 2607 + }, + { + "epoch": 0.27, + "learning_rate": 1.8220631154983907e-05, + "loss": 1.4855, + "step": 2608 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218546471212727e-05, + "loss": 1.4093, + "step": 2609 + }, + { + "epoch": 0.27, + "learning_rate": 1.821646068636749e-05, + "loss": 1.4852, + "step": 2610 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214373800727637e-05, + "loss": 1.6959, + "step": 2611 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212285814572755e-05, + "loss": 1.3874, + "step": 2612 + }, + { + "epoch": 0.27, + "learning_rate": 1.821019672818258e-05, + "loss": 1.4425, + "step": 2613 + }, + { + "epoch": 0.27, + "learning_rate": 1.8208106541837e-05, + "loss": 1.6097, + "step": 2614 + }, + { + "epoch": 0.27, + "learning_rate": 1.8206015255816045e-05, + "loss": 1.5675, + "step": 2615 + }, + { + "epoch": 0.27, + "learning_rate": 1.820392287039989e-05, + "loss": 1.4039, + "step": 2616 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201829385868866e-05, + "loss": 1.4872, + "step": 2617 + }, + { + "epoch": 0.27, + "learning_rate": 1.819973480250344e-05, + "loss": 1.4645, + "step": 2618 + }, + { + "epoch": 0.27, + "learning_rate": 1.8197639120584237e-05, + "loss": 1.4923, + "step": 2619 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195542340392025e-05, + "loss": 1.4294, + "step": 2620 + }, + { + "epoch": 0.27, + "learning_rate": 1.8193444462207717e-05, + "loss": 1.4315, + "step": 2621 + }, + { + "epoch": 0.27, + "learning_rate": 1.8191345486312372e-05, + "loss": 1.3972, + "step": 2622 + }, + { + "epoch": 0.28, + "learning_rate": 1.8189245412987205e-05, + "loss": 1.462, + "step": 2623 + }, + { + "epoch": 0.28, + "learning_rate": 1.8187144242513567e-05, + "loss": 1.4738, + "step": 2624 + }, + { + "epoch": 0.28, + "learning_rate": 1.818504197517296e-05, + "loss": 1.4935, + "step": 2625 + }, + { + "epoch": 0.28, + "learning_rate": 1.8182938611247038e-05, + "loss": 1.4231, + "step": 2626 + }, + { + "epoch": 0.28, + "learning_rate": 1.81808341510176e-05, + "loss": 1.4031, + "step": 2627 + }, + { + "epoch": 0.28, + "learning_rate": 1.817872859476658e-05, + "loss": 1.5822, + "step": 2628 + }, + { + "epoch": 0.28, + "learning_rate": 1.8176621942776075e-05, + "loss": 1.432, + "step": 2629 + }, + { + "epoch": 0.28, + "learning_rate": 1.8174514195328324e-05, + "loss": 1.5565, + "step": 2630 + }, + { + "epoch": 0.28, + "learning_rate": 1.8172405352705704e-05, + "loss": 1.4895, + "step": 2631 + }, + { + "epoch": 0.28, + "learning_rate": 1.8170295415190754e-05, + "loss": 1.4032, + "step": 2632 + }, + { + "epoch": 0.28, + "learning_rate": 1.8168184383066144e-05, + "loss": 1.4253, + "step": 2633 + }, + { + "epoch": 0.28, + "learning_rate": 1.8166072256614702e-05, + "loss": 1.5162, + "step": 2634 + }, + { + "epoch": 0.28, + "learning_rate": 1.81639590361194e-05, + "loss": 1.4609, + "step": 2635 + }, + { + "epoch": 0.28, + "learning_rate": 1.816184472186335e-05, + "loss": 1.4351, + "step": 2636 + }, + { + "epoch": 0.28, + "learning_rate": 1.8159729314129823e-05, + "loss": 1.4738, + "step": 2637 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157612813202224e-05, + "loss": 1.5986, + "step": 2638 + }, + { + "epoch": 0.28, + "learning_rate": 1.815549521936411e-05, + "loss": 1.4633, + "step": 2639 + }, + { + "epoch": 0.28, + "learning_rate": 1.8153376532899184e-05, + "loss": 1.4404, + "step": 2640 + }, + { + "epoch": 0.28, + "learning_rate": 1.81512567540913e-05, + "loss": 1.4256, + "step": 2641 + }, + { + "epoch": 0.28, + "learning_rate": 1.814913588322445e-05, + "loss": 1.4054, + "step": 2642 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147013920582773e-05, + "loss": 1.4134, + "step": 2643 + }, + { + "epoch": 0.28, + "learning_rate": 1.8144890866450567e-05, + "loss": 1.4098, + "step": 2644 + }, + { + "epoch": 0.28, + "learning_rate": 1.814276672111226e-05, + "loss": 1.4593, + "step": 2645 + }, + { + "epoch": 0.28, + "learning_rate": 1.814064148485243e-05, + "loss": 1.4679, + "step": 2646 + }, + { + "epoch": 0.28, + "learning_rate": 1.8138515157955812e-05, + "loss": 1.5234, + "step": 2647 + }, + { + "epoch": 0.28, + "learning_rate": 1.8136387740707272e-05, + "loss": 1.4568, + "step": 2648 + }, + { + "epoch": 0.28, + "learning_rate": 1.8134259233391836e-05, + "loss": 1.5057, + "step": 2649 + }, + { + "epoch": 0.28, + "learning_rate": 1.8132129636294665e-05, + "loss": 1.3643, + "step": 2650 + }, + { + "epoch": 0.28, + "learning_rate": 1.812999894970107e-05, + "loss": 1.4766, + "step": 2651 + }, + { + "epoch": 0.28, + "learning_rate": 1.812786717389651e-05, + "loss": 1.5701, + "step": 2652 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125734309166587e-05, + "loss": 1.5341, + "step": 2653 + }, + { + "epoch": 0.28, + "learning_rate": 1.812360035579705e-05, + "loss": 1.3596, + "step": 2654 + }, + { + "epoch": 0.28, + "learning_rate": 1.8121465314073793e-05, + "loss": 1.4847, + "step": 2655 + }, + { + "epoch": 0.28, + "learning_rate": 1.811932918428286e-05, + "loss": 1.4664, + "step": 2656 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117191966710438e-05, + "loss": 1.4673, + "step": 2657 + }, + { + "epoch": 0.28, + "learning_rate": 1.8115053661642856e-05, + "loss": 1.4712, + "step": 2658 + }, + { + "epoch": 0.28, + "learning_rate": 1.811291426936659e-05, + "loss": 1.4458, + "step": 2659 + }, + { + "epoch": 0.28, + "learning_rate": 1.811077379016827e-05, + "loss": 1.4667, + "step": 2660 + }, + { + "epoch": 0.28, + "learning_rate": 1.810863222433466e-05, + "loss": 1.4695, + "step": 2661 + }, + { + "epoch": 0.28, + "learning_rate": 1.8106489572152677e-05, + "loss": 1.5263, + "step": 2662 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104345833909376e-05, + "loss": 1.4148, + "step": 2663 + }, + { + "epoch": 0.28, + "learning_rate": 1.8102201009891976e-05, + "loss": 1.3955, + "step": 2664 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100055100387814e-05, + "loss": 1.6056, + "step": 2665 + }, + { + "epoch": 0.28, + "learning_rate": 1.8097908105684396e-05, + "loss": 1.5394, + "step": 2666 + }, + { + "epoch": 0.28, + "learning_rate": 1.809576002606936e-05, + "loss": 1.479, + "step": 2667 + }, + { + "epoch": 0.28, + "learning_rate": 1.8093610861830494e-05, + "loss": 1.4492, + "step": 2668 + }, + { + "epoch": 0.28, + "learning_rate": 1.8091460613255728e-05, + "loss": 1.4172, + "step": 2669 + }, + { + "epoch": 0.28, + "learning_rate": 1.808930928063315e-05, + "loss": 1.4498, + "step": 2670 + }, + { + "epoch": 0.28, + "learning_rate": 1.808715686425097e-05, + "loss": 1.6203, + "step": 2671 + }, + { + "epoch": 0.28, + "learning_rate": 1.8085003364397567e-05, + "loss": 1.435, + "step": 2672 + }, + { + "epoch": 0.28, + "learning_rate": 1.808284878136145e-05, + "loss": 1.4489, + "step": 2673 + }, + { + "epoch": 0.28, + "learning_rate": 1.8080693115431277e-05, + "loss": 1.4416, + "step": 2674 + }, + { + "epoch": 0.28, + "learning_rate": 1.8078536366895853e-05, + "loss": 1.422, + "step": 2675 + }, + { + "epoch": 0.28, + "learning_rate": 1.8076378536044128e-05, + "loss": 1.4039, + "step": 2676 + }, + { + "epoch": 0.28, + "learning_rate": 1.8074219623165195e-05, + "loss": 1.4705, + "step": 2677 + }, + { + "epoch": 0.28, + "learning_rate": 1.807205962854829e-05, + "loss": 1.5031, + "step": 2678 + }, + { + "epoch": 0.28, + "learning_rate": 1.8069898552482806e-05, + "loss": 1.4812, + "step": 2679 + }, + { + "epoch": 0.28, + "learning_rate": 1.806773639525826e-05, + "loss": 1.4129, + "step": 2680 + }, + { + "epoch": 0.28, + "learning_rate": 1.8065573157164332e-05, + "loss": 1.4559, + "step": 2681 + }, + { + "epoch": 0.28, + "learning_rate": 1.806340883849084e-05, + "loss": 1.3878, + "step": 2682 + }, + { + "epoch": 0.28, + "learning_rate": 1.8061243439527744e-05, + "loss": 1.4752, + "step": 2683 + }, + { + "epoch": 0.28, + "learning_rate": 1.8059076960565156e-05, + "loss": 1.4089, + "step": 2684 + }, + { + "epoch": 0.28, + "learning_rate": 1.8056909401893326e-05, + "loss": 1.4736, + "step": 2685 + }, + { + "epoch": 0.28, + "learning_rate": 1.8054740763802654e-05, + "loss": 1.3796, + "step": 2686 + }, + { + "epoch": 0.28, + "learning_rate": 1.805257104658368e-05, + "loss": 1.4412, + "step": 2687 + }, + { + "epoch": 0.28, + "learning_rate": 1.8050400250527086e-05, + "loss": 1.4639, + "step": 2688 + }, + { + "epoch": 0.28, + "learning_rate": 1.804822837592371e-05, + "loss": 1.4076, + "step": 2689 + }, + { + "epoch": 0.28, + "learning_rate": 1.804605542306452e-05, + "loss": 1.4627, + "step": 2690 + }, + { + "epoch": 0.28, + "learning_rate": 1.8043881392240642e-05, + "loss": 1.5249, + "step": 2691 + }, + { + "epoch": 0.28, + "learning_rate": 1.804170628374334e-05, + "loss": 1.4312, + "step": 2692 + }, + { + "epoch": 0.28, + "learning_rate": 1.803953009786402e-05, + "loss": 1.5676, + "step": 2693 + }, + { + "epoch": 0.28, + "learning_rate": 1.8037352834894233e-05, + "loss": 1.5072, + "step": 2694 + }, + { + "epoch": 0.28, + "learning_rate": 1.803517449512568e-05, + "loss": 1.5662, + "step": 2695 + }, + { + "epoch": 0.28, + "learning_rate": 1.8032995078850207e-05, + "loss": 1.4771, + "step": 2696 + }, + { + "epoch": 0.28, + "learning_rate": 1.803081458635979e-05, + "loss": 1.412, + "step": 2697 + }, + { + "epoch": 0.28, + "learning_rate": 1.8028633017946564e-05, + "loss": 1.497, + "step": 2698 + }, + { + "epoch": 0.28, + "learning_rate": 1.8026450373902804e-05, + "loss": 1.4528, + "step": 2699 + }, + { + "epoch": 0.28, + "learning_rate": 1.802426665452093e-05, + "loss": 1.4785, + "step": 2700 + }, + { + "epoch": 0.28, + "learning_rate": 1.8022081860093493e-05, + "loss": 1.6411, + "step": 2701 + }, + { + "epoch": 0.28, + "learning_rate": 1.8019895990913213e-05, + "loss": 1.4459, + "step": 2702 + }, + { + "epoch": 0.28, + "learning_rate": 1.8017709047272932e-05, + "loss": 1.4418, + "step": 2703 + }, + { + "epoch": 0.28, + "learning_rate": 1.801552102946565e-05, + "loss": 1.4409, + "step": 2704 + }, + { + "epoch": 0.28, + "learning_rate": 1.8013331937784498e-05, + "loss": 1.4651, + "step": 2705 + }, + { + "epoch": 0.28, + "learning_rate": 1.8011141772522766e-05, + "loss": 1.4161, + "step": 2706 + }, + { + "epoch": 0.28, + "learning_rate": 1.8008950533973876e-05, + "loss": 1.458, + "step": 2707 + }, + { + "epoch": 0.28, + "learning_rate": 1.8006758222431398e-05, + "loss": 1.4477, + "step": 2708 + }, + { + "epoch": 0.28, + "learning_rate": 1.800456483818904e-05, + "loss": 1.4433, + "step": 2709 + }, + { + "epoch": 0.28, + "learning_rate": 1.8002370381540672e-05, + "loss": 1.5005, + "step": 2710 + }, + { + "epoch": 0.28, + "learning_rate": 1.8000174852780282e-05, + "loss": 1.4945, + "step": 2711 + }, + { + "epoch": 0.28, + "learning_rate": 1.7997978252202023e-05, + "loss": 1.4298, + "step": 2712 + }, + { + "epoch": 0.28, + "learning_rate": 1.7995780580100177e-05, + "loss": 1.3812, + "step": 2713 + }, + { + "epoch": 0.28, + "learning_rate": 1.799358183676918e-05, + "loss": 1.5559, + "step": 2714 + }, + { + "epoch": 0.28, + "learning_rate": 1.79913820225036e-05, + "loss": 1.4316, + "step": 2715 + }, + { + "epoch": 0.28, + "learning_rate": 1.798918113759817e-05, + "loss": 1.419, + "step": 2716 + }, + { + "epoch": 0.28, + "learning_rate": 1.7986979182347733e-05, + "loss": 1.43, + "step": 2717 + }, + { + "epoch": 0.29, + "learning_rate": 1.798477615704731e-05, + "loss": 1.4964, + "step": 2718 + }, + { + "epoch": 0.29, + "learning_rate": 1.7982572061992044e-05, + "loss": 1.4417, + "step": 2719 + }, + { + "epoch": 0.29, + "learning_rate": 1.7980366897477227e-05, + "loss": 1.4562, + "step": 2720 + }, + { + "epoch": 0.29, + "learning_rate": 1.7978160663798295e-05, + "loss": 1.4386, + "step": 2721 + }, + { + "epoch": 0.29, + "learning_rate": 1.7975953361250824e-05, + "loss": 1.445, + "step": 2722 + }, + { + "epoch": 0.29, + "learning_rate": 1.797374499013054e-05, + "loss": 1.4549, + "step": 2723 + }, + { + "epoch": 0.29, + "learning_rate": 1.7971535550733305e-05, + "loss": 1.5205, + "step": 2724 + }, + { + "epoch": 0.29, + "learning_rate": 1.796932504335513e-05, + "loss": 1.4632, + "step": 2725 + }, + { + "epoch": 0.29, + "learning_rate": 1.796711346829216e-05, + "loss": 1.3767, + "step": 2726 + }, + { + "epoch": 0.29, + "learning_rate": 1.79649008258407e-05, + "loss": 1.4098, + "step": 2727 + }, + { + "epoch": 0.29, + "learning_rate": 1.7962687116297178e-05, + "loss": 1.4675, + "step": 2728 + }, + { + "epoch": 0.29, + "learning_rate": 1.7960472339958176e-05, + "loss": 1.6048, + "step": 2729 + }, + { + "epoch": 0.29, + "learning_rate": 1.7958256497120418e-05, + "loss": 1.5432, + "step": 2730 + }, + { + "epoch": 0.29, + "learning_rate": 1.7956039588080774e-05, + "loss": 1.5453, + "step": 2731 + }, + { + "epoch": 0.29, + "learning_rate": 1.7953821613136246e-05, + "loss": 1.4246, + "step": 2732 + }, + { + "epoch": 0.29, + "learning_rate": 1.7951602572583988e-05, + "loss": 1.3987, + "step": 2733 + }, + { + "epoch": 0.29, + "learning_rate": 1.7949382466721295e-05, + "loss": 1.4943, + "step": 2734 + }, + { + "epoch": 0.29, + "learning_rate": 1.7947161295845606e-05, + "loss": 1.4385, + "step": 2735 + }, + { + "epoch": 0.29, + "learning_rate": 1.7944939060254497e-05, + "loss": 1.4165, + "step": 2736 + }, + { + "epoch": 0.29, + "learning_rate": 1.7942715760245692e-05, + "loss": 1.4004, + "step": 2737 + }, + { + "epoch": 0.29, + "learning_rate": 1.7940491396117063e-05, + "loss": 1.4577, + "step": 2738 + }, + { + "epoch": 0.29, + "learning_rate": 1.7938265968166602e-05, + "loss": 1.4649, + "step": 2739 + }, + { + "epoch": 0.29, + "learning_rate": 1.7936039476692473e-05, + "loss": 1.5273, + "step": 2740 + }, + { + "epoch": 0.29, + "learning_rate": 1.7933811921992962e-05, + "loss": 1.4325, + "step": 2741 + }, + { + "epoch": 0.29, + "learning_rate": 1.793158330436651e-05, + "loss": 1.4388, + "step": 2742 + }, + { + "epoch": 0.29, + "learning_rate": 1.7929353624111687e-05, + "loss": 1.4124, + "step": 2743 + }, + { + "epoch": 0.29, + "learning_rate": 1.7927122881527222e-05, + "loss": 1.5449, + "step": 2744 + }, + { + "epoch": 0.29, + "learning_rate": 1.7924891076911964e-05, + "loss": 1.4728, + "step": 2745 + }, + { + "epoch": 0.29, + "learning_rate": 1.7922658210564932e-05, + "loss": 1.5103, + "step": 2746 + }, + { + "epoch": 0.29, + "learning_rate": 1.792042428278526e-05, + "loss": 1.5975, + "step": 2747 + }, + { + "epoch": 0.29, + "learning_rate": 1.7918189293872247e-05, + "loss": 1.567, + "step": 2748 + }, + { + "epoch": 0.29, + "learning_rate": 1.7915953244125318e-05, + "loss": 1.57, + "step": 2749 + }, + { + "epoch": 0.29, + "learning_rate": 1.791371613384405e-05, + "loss": 1.4372, + "step": 2750 + }, + { + "epoch": 0.29, + "learning_rate": 1.7911477963328155e-05, + "loss": 1.4053, + "step": 2751 + }, + { + "epoch": 0.29, + "learning_rate": 1.7909238732877492e-05, + "loss": 1.3782, + "step": 2752 + }, + { + "epoch": 0.29, + "learning_rate": 1.790699844279206e-05, + "loss": 1.4401, + "step": 2753 + }, + { + "epoch": 0.29, + "learning_rate": 1.7904757093372e-05, + "loss": 1.3749, + "step": 2754 + }, + { + "epoch": 0.29, + "learning_rate": 1.79025146849176e-05, + "loss": 1.4909, + "step": 2755 + }, + { + "epoch": 0.29, + "learning_rate": 1.7900271217729273e-05, + "loss": 1.4103, + "step": 2756 + }, + { + "epoch": 0.29, + "learning_rate": 1.7898026692107597e-05, + "loss": 1.4986, + "step": 2757 + }, + { + "epoch": 0.29, + "learning_rate": 1.7895781108353278e-05, + "loss": 1.5449, + "step": 2758 + }, + { + "epoch": 0.29, + "learning_rate": 1.789353446676717e-05, + "loss": 1.5583, + "step": 2759 + }, + { + "epoch": 0.29, + "learning_rate": 1.7891286767650254e-05, + "loss": 1.5342, + "step": 2760 + }, + { + "epoch": 0.29, + "learning_rate": 1.7889038011303673e-05, + "loss": 1.4233, + "step": 2761 + }, + { + "epoch": 0.29, + "learning_rate": 1.7886788198028707e-05, + "loss": 1.3433, + "step": 2762 + }, + { + "epoch": 0.29, + "learning_rate": 1.788453732812676e-05, + "loss": 1.4451, + "step": 2763 + }, + { + "epoch": 0.29, + "learning_rate": 1.78822854018994e-05, + "loss": 1.4506, + "step": 2764 + }, + { + "epoch": 0.29, + "learning_rate": 1.7880032419648324e-05, + "loss": 1.4386, + "step": 2765 + }, + { + "epoch": 0.29, + "learning_rate": 1.7877778381675374e-05, + "loss": 1.4512, + "step": 2766 + }, + { + "epoch": 0.29, + "learning_rate": 1.7875523288282535e-05, + "loss": 1.4319, + "step": 2767 + }, + { + "epoch": 0.29, + "learning_rate": 1.7873267139771932e-05, + "loss": 1.4753, + "step": 2768 + }, + { + "epoch": 0.29, + "learning_rate": 1.787100993644583e-05, + "loss": 1.4044, + "step": 2769 + }, + { + "epoch": 0.29, + "learning_rate": 1.786875167860663e-05, + "loss": 1.4382, + "step": 2770 + }, + { + "epoch": 0.29, + "learning_rate": 1.786649236655689e-05, + "loss": 1.3977, + "step": 2771 + }, + { + "epoch": 0.29, + "learning_rate": 1.7864232000599298e-05, + "loss": 1.4473, + "step": 2772 + }, + { + "epoch": 0.29, + "learning_rate": 1.7861970581036678e-05, + "loss": 1.4666, + "step": 2773 + }, + { + "epoch": 0.29, + "learning_rate": 1.785970810817201e-05, + "loss": 1.5299, + "step": 2774 + }, + { + "epoch": 0.29, + "learning_rate": 1.7857444582308402e-05, + "loss": 1.3974, + "step": 2775 + }, + { + "epoch": 0.29, + "learning_rate": 1.7855180003749114e-05, + "loss": 1.4603, + "step": 2776 + }, + { + "epoch": 0.29, + "learning_rate": 1.7852914372797535e-05, + "loss": 1.463, + "step": 2777 + }, + { + "epoch": 0.29, + "learning_rate": 1.7850647689757205e-05, + "loss": 1.5317, + "step": 2778 + }, + { + "epoch": 0.29, + "learning_rate": 1.78483799549318e-05, + "loss": 1.4669, + "step": 2779 + }, + { + "epoch": 0.29, + "learning_rate": 1.784611116862514e-05, + "loss": 1.5293, + "step": 2780 + }, + { + "epoch": 0.29, + "learning_rate": 1.7843841331141177e-05, + "loss": 1.5802, + "step": 2781 + }, + { + "epoch": 0.29, + "learning_rate": 1.7841570442784024e-05, + "loss": 1.4486, + "step": 2782 + }, + { + "epoch": 0.29, + "learning_rate": 1.7839298503857913e-05, + "loss": 1.4674, + "step": 2783 + }, + { + "epoch": 0.29, + "learning_rate": 1.7837025514667224e-05, + "loss": 1.4662, + "step": 2784 + }, + { + "epoch": 0.29, + "learning_rate": 1.7834751475516484e-05, + "loss": 1.3555, + "step": 2785 + }, + { + "epoch": 0.29, + "learning_rate": 1.783247638671035e-05, + "loss": 1.4307, + "step": 2786 + }, + { + "epoch": 0.29, + "eval_loss": 1.500258445739746, + "eval_runtime": 77.406, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 2786 + }, + { + "epoch": 0.29, + "learning_rate": 1.7830200248553633e-05, + "loss": 1.4596, + "step": 2787 + }, + { + "epoch": 0.29, + "learning_rate": 1.7827923061351273e-05, + "loss": 1.6118, + "step": 2788 + }, + { + "epoch": 0.29, + "learning_rate": 1.7825644825408353e-05, + "loss": 1.4782, + "step": 2789 + }, + { + "epoch": 0.29, + "learning_rate": 1.78233655410301e-05, + "loss": 1.4681, + "step": 2790 + }, + { + "epoch": 0.29, + "learning_rate": 1.782108520852188e-05, + "loss": 1.6281, + "step": 2791 + }, + { + "epoch": 0.29, + "learning_rate": 1.78188038281892e-05, + "loss": 1.4446, + "step": 2792 + }, + { + "epoch": 0.29, + "learning_rate": 1.7816521400337704e-05, + "loss": 1.479, + "step": 2793 + }, + { + "epoch": 0.29, + "learning_rate": 1.7814237925273178e-05, + "loss": 1.5457, + "step": 2794 + }, + { + "epoch": 0.29, + "learning_rate": 1.7811953403301547e-05, + "loss": 1.3928, + "step": 2795 + }, + { + "epoch": 0.29, + "learning_rate": 1.780966783472889e-05, + "loss": 1.4321, + "step": 2796 + }, + { + "epoch": 0.29, + "learning_rate": 1.78073812198614e-05, + "loss": 1.5734, + "step": 2797 + }, + { + "epoch": 0.29, + "learning_rate": 1.7805093559005432e-05, + "loss": 1.4356, + "step": 2798 + }, + { + "epoch": 0.29, + "learning_rate": 1.7802804852467473e-05, + "loss": 1.4656, + "step": 2799 + }, + { + "epoch": 0.29, + "learning_rate": 1.780051510055415e-05, + "loss": 1.4052, + "step": 2800 + }, + { + "epoch": 0.29, + "learning_rate": 1.7798224303572228e-05, + "loss": 1.4758, + "step": 2801 + }, + { + "epoch": 0.29, + "learning_rate": 1.7795932461828622e-05, + "loss": 1.4326, + "step": 2802 + }, + { + "epoch": 0.29, + "learning_rate": 1.7793639575630376e-05, + "loss": 1.3409, + "step": 2803 + }, + { + "epoch": 0.29, + "learning_rate": 1.7791345645284678e-05, + "loss": 1.4175, + "step": 2804 + }, + { + "epoch": 0.29, + "learning_rate": 1.7789050671098853e-05, + "loss": 1.383, + "step": 2805 + }, + { + "epoch": 0.29, + "learning_rate": 1.7786754653380373e-05, + "loss": 1.5162, + "step": 2806 + }, + { + "epoch": 0.29, + "learning_rate": 1.7784457592436847e-05, + "loss": 1.4899, + "step": 2807 + }, + { + "epoch": 0.29, + "learning_rate": 1.7782159488576016e-05, + "loss": 1.4874, + "step": 2808 + }, + { + "epoch": 0.29, + "learning_rate": 1.777986034210577e-05, + "loss": 1.4363, + "step": 2809 + }, + { + "epoch": 0.29, + "learning_rate": 1.7777560153334134e-05, + "loss": 1.4223, + "step": 2810 + }, + { + "epoch": 0.29, + "learning_rate": 1.7775258922569273e-05, + "loss": 1.4792, + "step": 2811 + }, + { + "epoch": 0.29, + "learning_rate": 1.77729566501195e-05, + "loss": 1.4475, + "step": 2812 + }, + { + "epoch": 0.29, + "learning_rate": 1.7770653336293253e-05, + "loss": 1.5157, + "step": 2813 + }, + { + "epoch": 0.3, + "learning_rate": 1.776834898139912e-05, + "loss": 1.389, + "step": 2814 + }, + { + "epoch": 0.3, + "learning_rate": 1.7766043585745824e-05, + "loss": 1.4358, + "step": 2815 + }, + { + "epoch": 0.3, + "learning_rate": 1.776373714964223e-05, + "loss": 1.4297, + "step": 2816 + }, + { + "epoch": 0.3, + "learning_rate": 1.7761429673397344e-05, + "loss": 1.4102, + "step": 2817 + }, + { + "epoch": 0.3, + "learning_rate": 1.77591211573203e-05, + "loss": 1.4572, + "step": 2818 + }, + { + "epoch": 0.3, + "learning_rate": 1.775681160172039e-05, + "loss": 1.448, + "step": 2819 + }, + { + "epoch": 0.3, + "learning_rate": 1.7754501006907025e-05, + "loss": 1.4426, + "step": 2820 + }, + { + "epoch": 0.3, + "learning_rate": 1.7752189373189773e-05, + "loss": 1.4566, + "step": 2821 + }, + { + "epoch": 0.3, + "learning_rate": 1.7749876700878332e-05, + "loss": 1.4267, + "step": 2822 + }, + { + "epoch": 0.3, + "learning_rate": 1.7747562990282538e-05, + "loss": 1.3951, + "step": 2823 + }, + { + "epoch": 0.3, + "learning_rate": 1.7745248241712373e-05, + "loss": 1.4668, + "step": 2824 + }, + { + "epoch": 0.3, + "learning_rate": 1.774293245547795e-05, + "loss": 1.4924, + "step": 2825 + }, + { + "epoch": 0.3, + "learning_rate": 1.7740615631889525e-05, + "loss": 1.5258, + "step": 2826 + }, + { + "epoch": 0.3, + "learning_rate": 1.7738297771257496e-05, + "loss": 1.4323, + "step": 2827 + }, + { + "epoch": 0.3, + "learning_rate": 1.7735978873892393e-05, + "loss": 1.439, + "step": 2828 + }, + { + "epoch": 0.3, + "learning_rate": 1.773365894010489e-05, + "loss": 1.5658, + "step": 2829 + }, + { + "epoch": 0.3, + "learning_rate": 1.77313379702058e-05, + "loss": 1.4607, + "step": 2830 + }, + { + "epoch": 0.3, + "learning_rate": 1.7729015964506073e-05, + "loss": 1.5544, + "step": 2831 + }, + { + "epoch": 0.3, + "learning_rate": 1.7726692923316798e-05, + "loss": 1.4232, + "step": 2832 + }, + { + "epoch": 0.3, + "learning_rate": 1.77243688469492e-05, + "loss": 1.415, + "step": 2833 + }, + { + "epoch": 0.3, + "learning_rate": 1.772204373571465e-05, + "loss": 1.4658, + "step": 2834 + }, + { + "epoch": 0.3, + "learning_rate": 1.7719717589924647e-05, + "loss": 1.4678, + "step": 2835 + }, + { + "epoch": 0.3, + "learning_rate": 1.771739040989084e-05, + "loss": 1.3021, + "step": 2836 + }, + { + "epoch": 0.3, + "learning_rate": 1.771506219592501e-05, + "loss": 1.4045, + "step": 2837 + }, + { + "epoch": 0.3, + "learning_rate": 1.7712732948339085e-05, + "loss": 1.4593, + "step": 2838 + }, + { + "epoch": 0.3, + "learning_rate": 1.7710402667445108e-05, + "loss": 1.4175, + "step": 2839 + }, + { + "epoch": 0.3, + "learning_rate": 1.770807135355529e-05, + "loss": 1.3939, + "step": 2840 + }, + { + "epoch": 0.3, + "learning_rate": 1.7705739006981963e-05, + "loss": 1.6089, + "step": 2841 + }, + { + "epoch": 0.3, + "learning_rate": 1.77034056280376e-05, + "loss": 1.3952, + "step": 2842 + }, + { + "epoch": 0.3, + "learning_rate": 1.7701071217034818e-05, + "loss": 1.5086, + "step": 2843 + }, + { + "epoch": 0.3, + "learning_rate": 1.7698735774286362e-05, + "loss": 1.4706, + "step": 2844 + }, + { + "epoch": 0.3, + "learning_rate": 1.7696399300105128e-05, + "loss": 1.4286, + "step": 2845 + }, + { + "epoch": 0.3, + "learning_rate": 1.7694061794804137e-05, + "loss": 1.4418, + "step": 2846 + }, + { + "epoch": 0.3, + "learning_rate": 1.7691723258696562e-05, + "loss": 1.516, + "step": 2847 + }, + { + "epoch": 0.3, + "learning_rate": 1.76893836920957e-05, + "loss": 1.4354, + "step": 2848 + }, + { + "epoch": 0.3, + "learning_rate": 1.7687043095314998e-05, + "loss": 1.7503, + "step": 2849 + }, + { + "epoch": 0.3, + "learning_rate": 1.7684701468668032e-05, + "loss": 1.5985, + "step": 2850 + }, + { + "epoch": 0.3, + "learning_rate": 1.768235881246852e-05, + "loss": 1.442, + "step": 2851 + }, + { + "epoch": 0.3, + "learning_rate": 1.7680015127030322e-05, + "loss": 1.4924, + "step": 2852 + }, + { + "epoch": 0.3, + "learning_rate": 1.7677670412667425e-05, + "loss": 1.4461, + "step": 2853 + }, + { + "epoch": 0.3, + "learning_rate": 1.7675324669693968e-05, + "loss": 1.3823, + "step": 2854 + }, + { + "epoch": 0.3, + "learning_rate": 1.767297789842421e-05, + "loss": 1.452, + "step": 2855 + }, + { + "epoch": 0.3, + "learning_rate": 1.767063009917257e-05, + "loss": 1.46, + "step": 2856 + }, + { + "epoch": 0.3, + "learning_rate": 1.7668281272253587e-05, + "loss": 1.4129, + "step": 2857 + }, + { + "epoch": 0.3, + "learning_rate": 1.766593141798194e-05, + "loss": 1.4057, + "step": 2858 + }, + { + "epoch": 0.3, + "learning_rate": 1.7663580536672456e-05, + "loss": 1.5162, + "step": 2859 + }, + { + "epoch": 0.3, + "learning_rate": 1.7661228628640087e-05, + "loss": 1.5177, + "step": 2860 + }, + { + "epoch": 0.3, + "learning_rate": 1.7658875694199933e-05, + "loss": 1.4548, + "step": 2861 + }, + { + "epoch": 0.3, + "learning_rate": 1.7656521733667223e-05, + "loss": 1.4511, + "step": 2862 + }, + { + "epoch": 0.3, + "learning_rate": 1.765416674735733e-05, + "loss": 1.4778, + "step": 2863 + }, + { + "epoch": 0.3, + "learning_rate": 1.765181073558576e-05, + "loss": 1.3935, + "step": 2864 + }, + { + "epoch": 0.3, + "learning_rate": 1.7649453698668156e-05, + "loss": 1.4659, + "step": 2865 + }, + { + "epoch": 0.3, + "learning_rate": 1.7647095636920305e-05, + "loss": 1.7042, + "step": 2866 + }, + { + "epoch": 0.3, + "learning_rate": 1.7644736550658124e-05, + "loss": 1.7957, + "step": 2867 + }, + { + "epoch": 0.3, + "learning_rate": 1.764237644019767e-05, + "loss": 1.5139, + "step": 2868 + }, + { + "epoch": 0.3, + "learning_rate": 1.764001530585514e-05, + "loss": 1.4117, + "step": 2869 + }, + { + "epoch": 0.3, + "learning_rate": 1.7637653147946858e-05, + "loss": 1.4837, + "step": 2870 + }, + { + "epoch": 0.3, + "learning_rate": 1.7635289966789298e-05, + "loss": 1.4379, + "step": 2871 + }, + { + "epoch": 0.3, + "learning_rate": 1.7632925762699068e-05, + "loss": 1.4491, + "step": 2872 + }, + { + "epoch": 0.3, + "learning_rate": 1.7630560535992905e-05, + "loss": 1.4006, + "step": 2873 + }, + { + "epoch": 0.3, + "learning_rate": 1.7628194286987694e-05, + "loss": 1.5484, + "step": 2874 + }, + { + "epoch": 0.3, + "learning_rate": 1.7625827016000446e-05, + "loss": 1.4926, + "step": 2875 + }, + { + "epoch": 0.3, + "learning_rate": 1.762345872334832e-05, + "loss": 1.3909, + "step": 2876 + }, + { + "epoch": 0.3, + "learning_rate": 1.76210894093486e-05, + "loss": 1.405, + "step": 2877 + }, + { + "epoch": 0.3, + "learning_rate": 1.7618719074318718e-05, + "loss": 1.4736, + "step": 2878 + }, + { + "epoch": 0.3, + "learning_rate": 1.7616347718576238e-05, + "loss": 1.4445, + "step": 2879 + }, + { + "epoch": 0.3, + "learning_rate": 1.761397534243886e-05, + "loss": 1.4878, + "step": 2880 + }, + { + "epoch": 0.3, + "learning_rate": 1.7611601946224417e-05, + "loss": 1.4414, + "step": 2881 + }, + { + "epoch": 0.3, + "learning_rate": 1.760922753025089e-05, + "loss": 1.5657, + "step": 2882 + }, + { + "epoch": 0.3, + "learning_rate": 1.7606852094836385e-05, + "loss": 1.5008, + "step": 2883 + }, + { + "epoch": 0.3, + "learning_rate": 1.7604475640299153e-05, + "loss": 1.4922, + "step": 2884 + }, + { + "epoch": 0.3, + "learning_rate": 1.7602098166957577e-05, + "loss": 1.7451, + "step": 2885 + }, + { + "epoch": 0.3, + "learning_rate": 1.759971967513017e-05, + "loss": 1.7077, + "step": 2886 + }, + { + "epoch": 0.3, + "learning_rate": 1.75973401651356e-05, + "loss": 1.3986, + "step": 2887 + }, + { + "epoch": 0.3, + "learning_rate": 1.7594959637292656e-05, + "loss": 1.3966, + "step": 2888 + }, + { + "epoch": 0.3, + "learning_rate": 1.7592578091920264e-05, + "loss": 1.4086, + "step": 2889 + }, + { + "epoch": 0.3, + "learning_rate": 1.7590195529337495e-05, + "loss": 1.4481, + "step": 2890 + }, + { + "epoch": 0.3, + "learning_rate": 1.7587811949863548e-05, + "loss": 1.3974, + "step": 2891 + }, + { + "epoch": 0.3, + "learning_rate": 1.7585427353817758e-05, + "loss": 1.5013, + "step": 2892 + }, + { + "epoch": 0.3, + "learning_rate": 1.7583041741519608e-05, + "loss": 1.5454, + "step": 2893 + }, + { + "epoch": 0.3, + "learning_rate": 1.7580655113288708e-05, + "loss": 1.5033, + "step": 2894 + }, + { + "epoch": 0.3, + "learning_rate": 1.7578267469444793e-05, + "loss": 1.4332, + "step": 2895 + }, + { + "epoch": 0.3, + "learning_rate": 1.757587881030776e-05, + "loss": 1.4667, + "step": 2896 + }, + { + "epoch": 0.3, + "learning_rate": 1.7573489136197623e-05, + "loss": 1.4314, + "step": 2897 + }, + { + "epoch": 0.3, + "learning_rate": 1.7571098447434532e-05, + "loss": 1.4514, + "step": 2898 + }, + { + "epoch": 0.3, + "learning_rate": 1.7568706744338784e-05, + "loss": 1.4872, + "step": 2899 + }, + { + "epoch": 0.3, + "learning_rate": 1.7566314027230808e-05, + "loss": 1.4841, + "step": 2900 + }, + { + "epoch": 0.3, + "learning_rate": 1.7563920296431158e-05, + "loss": 1.3964, + "step": 2901 + }, + { + "epoch": 0.3, + "learning_rate": 1.7561525552260538e-05, + "loss": 1.4932, + "step": 2902 + }, + { + "epoch": 0.3, + "learning_rate": 1.755912979503978e-05, + "loss": 1.4153, + "step": 2903 + }, + { + "epoch": 0.3, + "learning_rate": 1.755673302508986e-05, + "loss": 1.4939, + "step": 2904 + }, + { + "epoch": 0.3, + "learning_rate": 1.755433524273187e-05, + "loss": 1.4437, + "step": 2905 + }, + { + "epoch": 0.3, + "learning_rate": 1.7551936448287067e-05, + "loss": 1.486, + "step": 2906 + }, + { + "epoch": 0.3, + "learning_rate": 1.754953664207682e-05, + "loss": 1.4362, + "step": 2907 + }, + { + "epoch": 0.3, + "learning_rate": 1.7547135824422635e-05, + "loss": 1.4954, + "step": 2908 + }, + { + "epoch": 0.31, + "learning_rate": 1.7544733995646174e-05, + "loss": 1.4552, + "step": 2909 + }, + { + "epoch": 0.31, + "learning_rate": 1.7542331156069213e-05, + "loss": 1.4654, + "step": 2910 + }, + { + "epoch": 0.31, + "learning_rate": 1.753992730601367e-05, + "loss": 1.4531, + "step": 2911 + }, + { + "epoch": 0.31, + "learning_rate": 1.75375224458016e-05, + "loss": 1.4949, + "step": 2912 + }, + { + "epoch": 0.31, + "learning_rate": 1.753511657575519e-05, + "loss": 1.3998, + "step": 2913 + }, + { + "epoch": 0.31, + "learning_rate": 1.753270969619677e-05, + "loss": 1.3904, + "step": 2914 + }, + { + "epoch": 0.31, + "learning_rate": 1.7530301807448794e-05, + "loss": 1.481, + "step": 2915 + }, + { + "epoch": 0.31, + "learning_rate": 1.7527892909833864e-05, + "loss": 1.4301, + "step": 2916 + }, + { + "epoch": 0.31, + "learning_rate": 1.7525483003674707e-05, + "loss": 1.4377, + "step": 2917 + }, + { + "epoch": 0.31, + "learning_rate": 1.7523072089294188e-05, + "loss": 1.5077, + "step": 2918 + }, + { + "epoch": 0.31, + "learning_rate": 1.752066016701531e-05, + "loss": 1.3802, + "step": 2919 + }, + { + "epoch": 0.31, + "learning_rate": 1.7518247237161205e-05, + "loss": 1.3991, + "step": 2920 + }, + { + "epoch": 0.31, + "learning_rate": 1.7515833300055146e-05, + "loss": 1.4283, + "step": 2921 + }, + { + "epoch": 0.31, + "learning_rate": 1.7513418356020535e-05, + "loss": 1.3688, + "step": 2922 + }, + { + "epoch": 0.31, + "learning_rate": 1.751100240538092e-05, + "loss": 1.4336, + "step": 2923 + }, + { + "epoch": 0.31, + "learning_rate": 1.7508585448459967e-05, + "loss": 1.4302, + "step": 2924 + }, + { + "epoch": 0.31, + "learning_rate": 1.7506167485581493e-05, + "loss": 1.4293, + "step": 2925 + }, + { + "epoch": 0.31, + "learning_rate": 1.750374851706944e-05, + "loss": 1.4262, + "step": 2926 + }, + { + "epoch": 0.31, + "learning_rate": 1.7501328543247892e-05, + "loss": 1.4128, + "step": 2927 + }, + { + "epoch": 0.31, + "learning_rate": 1.7498907564441054e-05, + "loss": 1.4258, + "step": 2928 + }, + { + "epoch": 0.31, + "learning_rate": 1.749648558097328e-05, + "loss": 1.4904, + "step": 2929 + }, + { + "epoch": 0.31, + "learning_rate": 1.749406259316906e-05, + "loss": 1.4628, + "step": 2930 + }, + { + "epoch": 0.31, + "learning_rate": 1.7491638601353004e-05, + "loss": 1.4908, + "step": 2931 + }, + { + "epoch": 0.31, + "learning_rate": 1.7489213605849867e-05, + "loss": 1.4563, + "step": 2932 + }, + { + "epoch": 0.31, + "learning_rate": 1.7486787606984533e-05, + "loss": 1.5006, + "step": 2933 + }, + { + "epoch": 0.31, + "learning_rate": 1.748436060508203e-05, + "loss": 1.424, + "step": 2934 + }, + { + "epoch": 0.31, + "learning_rate": 1.7481932600467508e-05, + "loss": 1.4136, + "step": 2935 + }, + { + "epoch": 0.31, + "learning_rate": 1.747950359346626e-05, + "loss": 1.3835, + "step": 2936 + }, + { + "epoch": 0.31, + "learning_rate": 1.747707358440371e-05, + "loss": 1.5284, + "step": 2937 + }, + { + "epoch": 0.31, + "learning_rate": 1.7474642573605418e-05, + "loss": 1.4592, + "step": 2938 + }, + { + "epoch": 0.31, + "learning_rate": 1.7472210561397075e-05, + "loss": 1.5483, + "step": 2939 + }, + { + "epoch": 0.31, + "learning_rate": 1.746977754810451e-05, + "loss": 1.521, + "step": 2940 + }, + { + "epoch": 0.31, + "learning_rate": 1.7467343534053683e-05, + "loss": 1.4276, + "step": 2941 + }, + { + "epoch": 0.31, + "learning_rate": 1.746490851957069e-05, + "loss": 1.4302, + "step": 2942 + }, + { + "epoch": 0.31, + "learning_rate": 1.746247250498176e-05, + "loss": 1.4439, + "step": 2943 + }, + { + "epoch": 0.31, + "learning_rate": 1.7460035490613255e-05, + "loss": 1.4991, + "step": 2944 + }, + { + "epoch": 0.31, + "learning_rate": 1.7457597476791674e-05, + "loss": 1.4188, + "step": 2945 + }, + { + "epoch": 0.31, + "learning_rate": 1.7455158463843648e-05, + "loss": 1.4685, + "step": 2946 + }, + { + "epoch": 0.31, + "learning_rate": 1.745271845209594e-05, + "loss": 1.3811, + "step": 2947 + }, + { + "epoch": 0.31, + "learning_rate": 1.7450277441875454e-05, + "loss": 1.4869, + "step": 2948 + }, + { + "epoch": 0.31, + "learning_rate": 1.7447835433509218e-05, + "loss": 1.5001, + "step": 2949 + }, + { + "epoch": 0.31, + "learning_rate": 1.74453924273244e-05, + "loss": 1.4757, + "step": 2950 + }, + { + "epoch": 0.31, + "learning_rate": 1.74429484236483e-05, + "loss": 1.5072, + "step": 2951 + }, + { + "epoch": 0.31, + "learning_rate": 1.744050342280835e-05, + "loss": 1.4242, + "step": 2952 + }, + { + "epoch": 0.31, + "learning_rate": 1.743805742513212e-05, + "loss": 1.4462, + "step": 2953 + }, + { + "epoch": 0.31, + "learning_rate": 1.743561043094731e-05, + "loss": 1.6815, + "step": 2954 + }, + { + "epoch": 0.31, + "learning_rate": 1.7433162440581755e-05, + "loss": 1.427, + "step": 2955 + }, + { + "epoch": 0.31, + "learning_rate": 1.7430713454363423e-05, + "loss": 1.2933, + "step": 2956 + }, + { + "epoch": 0.31, + "learning_rate": 1.742826347262041e-05, + "loss": 1.4247, + "step": 2957 + }, + { + "epoch": 0.31, + "learning_rate": 1.7425812495680955e-05, + "loss": 1.399, + "step": 2958 + }, + { + "epoch": 0.31, + "learning_rate": 1.742336052387343e-05, + "loss": 1.4818, + "step": 2959 + }, + { + "epoch": 0.31, + "learning_rate": 1.742090755752633e-05, + "loss": 1.3839, + "step": 2960 + }, + { + "epoch": 0.31, + "learning_rate": 1.741845359696829e-05, + "loss": 1.4669, + "step": 2961 + }, + { + "epoch": 0.31, + "learning_rate": 1.741599864252808e-05, + "loss": 1.468, + "step": 2962 + }, + { + "epoch": 0.31, + "learning_rate": 1.74135426945346e-05, + "loss": 1.4135, + "step": 2963 + }, + { + "epoch": 0.31, + "learning_rate": 1.7411085753316882e-05, + "loss": 1.5899, + "step": 2964 + }, + { + "epoch": 0.31, + "learning_rate": 1.74086278192041e-05, + "loss": 1.6115, + "step": 2965 + }, + { + "epoch": 0.31, + "learning_rate": 1.740616889252554e-05, + "loss": 1.3988, + "step": 2966 + }, + { + "epoch": 0.31, + "learning_rate": 1.740370897361065e-05, + "loss": 1.5001, + "step": 2967 + }, + { + "epoch": 0.31, + "learning_rate": 1.740124806278899e-05, + "loss": 1.459, + "step": 2968 + }, + { + "epoch": 0.31, + "learning_rate": 1.7398786160390258e-05, + "loss": 1.4489, + "step": 2969 + }, + { + "epoch": 0.31, + "learning_rate": 1.7396323266744283e-05, + "loss": 1.4397, + "step": 2970 + }, + { + "epoch": 0.31, + "learning_rate": 1.7393859382181033e-05, + "loss": 1.4687, + "step": 2971 + }, + { + "epoch": 0.31, + "learning_rate": 1.7391394507030606e-05, + "loss": 1.4495, + "step": 2972 + }, + { + "epoch": 0.31, + "learning_rate": 1.738892864162323e-05, + "loss": 1.4745, + "step": 2973 + }, + { + "epoch": 0.31, + "learning_rate": 1.7386461786289274e-05, + "loss": 1.3943, + "step": 2974 + }, + { + "epoch": 0.31, + "learning_rate": 1.738399394135922e-05, + "loss": 1.4595, + "step": 2975 + }, + { + "epoch": 0.31, + "learning_rate": 1.738152510716371e-05, + "loss": 1.4023, + "step": 2976 + }, + { + "epoch": 0.31, + "learning_rate": 1.7379055284033493e-05, + "loss": 1.3938, + "step": 2977 + }, + { + "epoch": 0.31, + "learning_rate": 1.7376584472299468e-05, + "loss": 1.4576, + "step": 2978 + }, + { + "epoch": 0.31, + "learning_rate": 1.737411267229266e-05, + "loss": 1.424, + "step": 2979 + }, + { + "epoch": 0.31, + "learning_rate": 1.7371639884344225e-05, + "loss": 1.4224, + "step": 2980 + }, + { + "epoch": 0.31, + "learning_rate": 1.736916610878545e-05, + "loss": 1.4228, + "step": 2981 + }, + { + "epoch": 0.31, + "learning_rate": 1.7366691345947768e-05, + "loss": 1.5021, + "step": 2982 + }, + { + "epoch": 0.31, + "learning_rate": 1.736421559616272e-05, + "loss": 1.3589, + "step": 2983 + }, + { + "epoch": 0.31, + "learning_rate": 1.7361738859762007e-05, + "loss": 1.4748, + "step": 2984 + }, + { + "epoch": 0.31, + "learning_rate": 1.735926113707743e-05, + "loss": 1.3974, + "step": 2985 + }, + { + "epoch": 0.31, + "eval_loss": 1.4849082231521606, + "eval_runtime": 77.3271, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2985 + }, + { + "epoch": 0.31, + "learning_rate": 1.735678242844096e-05, + "loss": 1.392, + "step": 2986 + }, + { + "epoch": 0.31, + "learning_rate": 1.735430273418467e-05, + "loss": 1.4277, + "step": 2987 + }, + { + "epoch": 0.31, + "learning_rate": 1.735182205464077e-05, + "loss": 1.4216, + "step": 2988 + }, + { + "epoch": 0.31, + "learning_rate": 1.7349340390141617e-05, + "loss": 1.4546, + "step": 2989 + }, + { + "epoch": 0.31, + "learning_rate": 1.734685774101969e-05, + "loss": 1.4264, + "step": 2990 + }, + { + "epoch": 0.31, + "learning_rate": 1.7344374107607593e-05, + "loss": 1.4307, + "step": 2991 + }, + { + "epoch": 0.31, + "learning_rate": 1.7341889490238076e-05, + "loss": 1.4266, + "step": 2992 + }, + { + "epoch": 0.31, + "learning_rate": 1.7339403889244008e-05, + "loss": 1.4486, + "step": 2993 + }, + { + "epoch": 0.31, + "learning_rate": 1.7336917304958403e-05, + "loss": 1.4345, + "step": 2994 + }, + { + "epoch": 0.31, + "learning_rate": 1.7334429737714395e-05, + "loss": 1.476, + "step": 2995 + }, + { + "epoch": 0.31, + "learning_rate": 1.7331941187845248e-05, + "loss": 1.5148, + "step": 2996 + }, + { + "epoch": 0.31, + "learning_rate": 1.7329451655684372e-05, + "loss": 1.4026, + "step": 2997 + }, + { + "epoch": 0.31, + "learning_rate": 1.7326961141565303e-05, + "loss": 1.3935, + "step": 2998 + }, + { + "epoch": 0.31, + "learning_rate": 1.73244696458217e-05, + "loss": 1.4483, + "step": 2999 + }, + { + "epoch": 0.31, + "learning_rate": 1.7321977168787356e-05, + "loss": 1.5197, + "step": 3000 + }, + { + "epoch": 0.31, + "learning_rate": 1.7319483710796208e-05, + "loss": 1.4648, + "step": 3001 + }, + { + "epoch": 0.31, + "learning_rate": 1.7316989272182308e-05, + "loss": 1.4171, + "step": 3002 + }, + { + "epoch": 0.31, + "learning_rate": 1.731449385327985e-05, + "loss": 1.4541, + "step": 3003 + }, + { + "epoch": 0.32, + "learning_rate": 1.731199745442316e-05, + "loss": 1.4605, + "step": 3004 + }, + { + "epoch": 0.32, + "learning_rate": 1.7309500075946683e-05, + "loss": 1.5122, + "step": 3005 + }, + { + "epoch": 0.32, + "learning_rate": 1.7307001718185007e-05, + "loss": 1.5243, + "step": 3006 + }, + { + "epoch": 0.32, + "learning_rate": 1.7304502381472844e-05, + "loss": 1.4997, + "step": 3007 + }, + { + "epoch": 0.32, + "learning_rate": 1.730200206614505e-05, + "loss": 1.4891, + "step": 3008 + }, + { + "epoch": 0.32, + "learning_rate": 1.72995007725366e-05, + "loss": 1.4376, + "step": 3009 + }, + { + "epoch": 0.32, + "learning_rate": 1.7296998500982595e-05, + "loss": 1.4403, + "step": 3010 + }, + { + "epoch": 0.32, + "learning_rate": 1.7294495251818285e-05, + "loss": 1.5153, + "step": 3011 + }, + { + "epoch": 0.32, + "learning_rate": 1.729199102537904e-05, + "loss": 1.4996, + "step": 3012 + }, + { + "epoch": 0.32, + "learning_rate": 1.7289485822000356e-05, + "loss": 1.5302, + "step": 3013 + }, + { + "epoch": 0.32, + "learning_rate": 1.7286979642017867e-05, + "loss": 1.5641, + "step": 3014 + }, + { + "epoch": 0.32, + "learning_rate": 1.728447248576734e-05, + "loss": 1.438, + "step": 3015 + }, + { + "epoch": 0.32, + "learning_rate": 1.7281964353584674e-05, + "loss": 1.4796, + "step": 3016 + }, + { + "epoch": 0.32, + "learning_rate": 1.727945524580588e-05, + "loss": 1.4413, + "step": 3017 + }, + { + "epoch": 0.32, + "learning_rate": 1.727694516276713e-05, + "loss": 1.3966, + "step": 3018 + }, + { + "epoch": 0.32, + "learning_rate": 1.72744341048047e-05, + "loss": 1.5267, + "step": 3019 + }, + { + "epoch": 0.32, + "learning_rate": 1.727192207225501e-05, + "loss": 1.4284, + "step": 3020 + }, + { + "epoch": 0.32, + "learning_rate": 1.726940906545461e-05, + "loss": 1.5137, + "step": 3021 + }, + { + "epoch": 0.32, + "learning_rate": 1.7266895084740173e-05, + "loss": 1.3966, + "step": 3022 + }, + { + "epoch": 0.32, + "learning_rate": 1.7264380130448514e-05, + "loss": 1.4156, + "step": 3023 + }, + { + "epoch": 0.32, + "learning_rate": 1.726186420291657e-05, + "loss": 1.4644, + "step": 3024 + }, + { + "epoch": 0.32, + "learning_rate": 1.725934730248141e-05, + "loss": 1.4768, + "step": 3025 + }, + { + "epoch": 0.32, + "learning_rate": 1.7256829429480233e-05, + "loss": 1.4428, + "step": 3026 + }, + { + "epoch": 0.32, + "learning_rate": 1.7254310584250373e-05, + "loss": 1.4495, + "step": 3027 + }, + { + "epoch": 0.32, + "learning_rate": 1.725179076712929e-05, + "loss": 1.3867, + "step": 3028 + }, + { + "epoch": 0.32, + "learning_rate": 1.7249269978454567e-05, + "loss": 1.5011, + "step": 3029 + }, + { + "epoch": 0.32, + "learning_rate": 1.7246748218563937e-05, + "loss": 1.3916, + "step": 3030 + }, + { + "epoch": 0.32, + "learning_rate": 1.7244225487795238e-05, + "loss": 1.4984, + "step": 3031 + }, + { + "epoch": 0.32, + "learning_rate": 1.7241701786486464e-05, + "loss": 1.5776, + "step": 3032 + }, + { + "epoch": 0.32, + "learning_rate": 1.7239177114975717e-05, + "loss": 1.5018, + "step": 3033 + }, + { + "epoch": 0.32, + "learning_rate": 1.7236651473601244e-05, + "loss": 1.5042, + "step": 3034 + }, + { + "epoch": 0.32, + "learning_rate": 1.723412486270141e-05, + "loss": 1.4636, + "step": 3035 + }, + { + "epoch": 0.32, + "learning_rate": 1.723159728261472e-05, + "loss": 1.5612, + "step": 3036 + }, + { + "epoch": 0.32, + "learning_rate": 1.7229068733679803e-05, + "loss": 1.4399, + "step": 3037 + }, + { + "epoch": 0.32, + "learning_rate": 1.7226539216235424e-05, + "loss": 1.5635, + "step": 3038 + }, + { + "epoch": 0.32, + "learning_rate": 1.7224008730620468e-05, + "loss": 1.4329, + "step": 3039 + }, + { + "epoch": 0.32, + "learning_rate": 1.7221477277173956e-05, + "loss": 1.4886, + "step": 3040 + }, + { + "epoch": 0.32, + "learning_rate": 1.721894485623504e-05, + "loss": 1.4741, + "step": 3041 + }, + { + "epoch": 0.32, + "learning_rate": 1.7216411468143e-05, + "loss": 1.4678, + "step": 3042 + }, + { + "epoch": 0.32, + "learning_rate": 1.721387711323724e-05, + "loss": 1.4758, + "step": 3043 + }, + { + "epoch": 0.32, + "learning_rate": 1.72113417918573e-05, + "loss": 1.441, + "step": 3044 + }, + { + "epoch": 0.32, + "learning_rate": 1.7208805504342855e-05, + "loss": 1.4328, + "step": 3045 + }, + { + "epoch": 0.32, + "learning_rate": 1.720626825103369e-05, + "loss": 1.4254, + "step": 3046 + }, + { + "epoch": 0.32, + "learning_rate": 1.7203730032269744e-05, + "loss": 1.4462, + "step": 3047 + }, + { + "epoch": 0.32, + "learning_rate": 1.7201190848391066e-05, + "loss": 1.4826, + "step": 3048 + }, + { + "epoch": 0.32, + "learning_rate": 1.719865069973784e-05, + "loss": 1.4215, + "step": 3049 + }, + { + "epoch": 0.32, + "learning_rate": 1.7196109586650385e-05, + "loss": 1.4291, + "step": 3050 + }, + { + "epoch": 0.32, + "learning_rate": 1.7193567509469146e-05, + "loss": 1.5005, + "step": 3051 + }, + { + "epoch": 0.32, + "learning_rate": 1.719102446853469e-05, + "loss": 1.4216, + "step": 3052 + }, + { + "epoch": 0.32, + "learning_rate": 1.7188480464187725e-05, + "loss": 1.4349, + "step": 3053 + }, + { + "epoch": 0.32, + "learning_rate": 1.718593549676908e-05, + "loss": 1.4784, + "step": 3054 + }, + { + "epoch": 0.32, + "learning_rate": 1.7183389566619714e-05, + "loss": 1.4325, + "step": 3055 + }, + { + "epoch": 0.32, + "learning_rate": 1.7180842674080717e-05, + "loss": 1.5387, + "step": 3056 + }, + { + "epoch": 0.32, + "learning_rate": 1.717829481949331e-05, + "loss": 1.655, + "step": 3057 + }, + { + "epoch": 0.32, + "learning_rate": 1.717574600319883e-05, + "loss": 1.4623, + "step": 3058 + }, + { + "epoch": 0.32, + "learning_rate": 1.7173196225538768e-05, + "loss": 1.4646, + "step": 3059 + }, + { + "epoch": 0.32, + "learning_rate": 1.717064548685472e-05, + "loss": 1.4641, + "step": 3060 + }, + { + "epoch": 0.32, + "learning_rate": 1.7168093787488418e-05, + "loss": 1.4033, + "step": 3061 + }, + { + "epoch": 0.32, + "learning_rate": 1.7165541127781726e-05, + "loss": 1.4085, + "step": 3062 + }, + { + "epoch": 0.32, + "learning_rate": 1.716298750807664e-05, + "loss": 1.387, + "step": 3063 + }, + { + "epoch": 0.32, + "learning_rate": 1.7160432928715272e-05, + "loss": 1.4197, + "step": 3064 + }, + { + "epoch": 0.32, + "learning_rate": 1.7157877390039872e-05, + "loss": 1.4883, + "step": 3065 + }, + { + "epoch": 0.32, + "learning_rate": 1.7155320892392818e-05, + "loss": 1.4865, + "step": 3066 + }, + { + "epoch": 0.32, + "learning_rate": 1.715276343611662e-05, + "loss": 1.4532, + "step": 3067 + }, + { + "epoch": 0.32, + "learning_rate": 1.71502050215539e-05, + "loss": 1.3991, + "step": 3068 + }, + { + "epoch": 0.32, + "learning_rate": 1.7147645649047424e-05, + "loss": 1.4318, + "step": 3069 + }, + { + "epoch": 0.32, + "learning_rate": 1.714508531894009e-05, + "loss": 1.3616, + "step": 3070 + }, + { + "epoch": 0.32, + "learning_rate": 1.7142524031574904e-05, + "loss": 1.4481, + "step": 3071 + }, + { + "epoch": 0.32, + "learning_rate": 1.7139961787295022e-05, + "loss": 1.3897, + "step": 3072 + }, + { + "epoch": 0.32, + "learning_rate": 1.7137398586443716e-05, + "loss": 1.3128, + "step": 3073 + }, + { + "epoch": 0.32, + "learning_rate": 1.713483442936439e-05, + "loss": 1.4481, + "step": 3074 + }, + { + "epoch": 0.32, + "learning_rate": 1.713226931640057e-05, + "loss": 1.5374, + "step": 3075 + }, + { + "epoch": 0.32, + "learning_rate": 1.7129703247895923e-05, + "loss": 1.4247, + "step": 3076 + }, + { + "epoch": 0.32, + "learning_rate": 1.712713622419423e-05, + "loss": 1.4098, + "step": 3077 + }, + { + "epoch": 0.32, + "learning_rate": 1.7124568245639414e-05, + "loss": 1.4558, + "step": 3078 + }, + { + "epoch": 0.32, + "learning_rate": 1.7121999312575507e-05, + "loss": 1.4484, + "step": 3079 + }, + { + "epoch": 0.32, + "learning_rate": 1.711942942534669e-05, + "loss": 1.4236, + "step": 3080 + }, + { + "epoch": 0.32, + "learning_rate": 1.7116858584297253e-05, + "loss": 1.613, + "step": 3081 + }, + { + "epoch": 0.32, + "learning_rate": 1.711428678977163e-05, + "loss": 1.4503, + "step": 3082 + }, + { + "epoch": 0.32, + "learning_rate": 1.7111714042114376e-05, + "loss": 1.4072, + "step": 3083 + }, + { + "epoch": 0.32, + "learning_rate": 1.7109140341670168e-05, + "loss": 1.5999, + "step": 3084 + }, + { + "epoch": 0.32, + "learning_rate": 1.7106565688783815e-05, + "loss": 1.4129, + "step": 3085 + }, + { + "epoch": 0.32, + "learning_rate": 1.710399008380026e-05, + "loss": 1.3973, + "step": 3086 + }, + { + "epoch": 0.32, + "learning_rate": 1.710141352706456e-05, + "loss": 1.4292, + "step": 3087 + }, + { + "epoch": 0.32, + "learning_rate": 1.709883601892192e-05, + "loss": 1.4372, + "step": 3088 + }, + { + "epoch": 0.32, + "learning_rate": 1.7096257559717647e-05, + "loss": 1.4924, + "step": 3089 + }, + { + "epoch": 0.32, + "learning_rate": 1.7093678149797196e-05, + "loss": 1.4222, + "step": 3090 + }, + { + "epoch": 0.32, + "learning_rate": 1.7091097789506137e-05, + "loss": 1.4797, + "step": 3091 + }, + { + "epoch": 0.32, + "learning_rate": 1.7088516479190175e-05, + "loss": 1.4738, + "step": 3092 + }, + { + "epoch": 0.32, + "learning_rate": 1.708593421919514e-05, + "loss": 1.5371, + "step": 3093 + }, + { + "epoch": 0.32, + "learning_rate": 1.7083351009866988e-05, + "loss": 1.3802, + "step": 3094 + }, + { + "epoch": 0.32, + "learning_rate": 1.7080766851551795e-05, + "loss": 1.4292, + "step": 3095 + }, + { + "epoch": 0.32, + "learning_rate": 1.707818174459578e-05, + "loss": 1.4478, + "step": 3096 + }, + { + "epoch": 0.32, + "learning_rate": 1.7075595689345285e-05, + "loss": 1.4619, + "step": 3097 + }, + { + "epoch": 0.32, + "learning_rate": 1.7073008686146763e-05, + "loss": 1.4603, + "step": 3098 + }, + { + "epoch": 0.32, + "learning_rate": 1.7070420735346815e-05, + "loss": 1.4548, + "step": 3099 + }, + { + "epoch": 0.33, + "learning_rate": 1.7067831837292157e-05, + "loss": 1.3638, + "step": 3100 + }, + { + "epoch": 0.33, + "learning_rate": 1.7065241992329634e-05, + "loss": 1.4284, + "step": 3101 + }, + { + "epoch": 0.33, + "learning_rate": 1.7062651200806217e-05, + "loss": 1.386, + "step": 3102 + }, + { + "epoch": 0.33, + "learning_rate": 1.7060059463069013e-05, + "loss": 1.5483, + "step": 3103 + }, + { + "epoch": 0.33, + "learning_rate": 1.705746677946524e-05, + "loss": 1.4963, + "step": 3104 + }, + { + "epoch": 0.33, + "learning_rate": 1.7054873150342257e-05, + "loss": 1.4539, + "step": 3105 + }, + { + "epoch": 0.33, + "learning_rate": 1.705227857604754e-05, + "loss": 1.4361, + "step": 3106 + }, + { + "epoch": 0.33, + "learning_rate": 1.7049683056928695e-05, + "loss": 1.3735, + "step": 3107 + }, + { + "epoch": 0.33, + "learning_rate": 1.7047086593333454e-05, + "loss": 1.4324, + "step": 3108 + }, + { + "epoch": 0.33, + "learning_rate": 1.7044489185609685e-05, + "loss": 1.5037, + "step": 3109 + }, + { + "epoch": 0.33, + "learning_rate": 1.704189083410536e-05, + "loss": 1.3913, + "step": 3110 + }, + { + "epoch": 0.33, + "learning_rate": 1.7039291539168604e-05, + "loss": 1.3233, + "step": 3111 + }, + { + "epoch": 0.33, + "learning_rate": 1.703669130114765e-05, + "loss": 1.4897, + "step": 3112 + }, + { + "epoch": 0.33, + "learning_rate": 1.7034090120390862e-05, + "loss": 1.4843, + "step": 3113 + }, + { + "epoch": 0.33, + "learning_rate": 1.7031487997246735e-05, + "loss": 1.3674, + "step": 3114 + }, + { + "epoch": 0.33, + "learning_rate": 1.7028884932063883e-05, + "loss": 1.4475, + "step": 3115 + }, + { + "epoch": 0.33, + "learning_rate": 1.702628092519105e-05, + "loss": 1.4134, + "step": 3116 + }, + { + "epoch": 0.33, + "learning_rate": 1.7023675976977108e-05, + "loss": 1.4484, + "step": 3117 + }, + { + "epoch": 0.33, + "learning_rate": 1.702107008777106e-05, + "loss": 1.407, + "step": 3118 + }, + { + "epoch": 0.33, + "learning_rate": 1.7018463257922005e-05, + "loss": 1.5443, + "step": 3119 + }, + { + "epoch": 0.33, + "learning_rate": 1.701585548777922e-05, + "loss": 1.4548, + "step": 3120 + }, + { + "epoch": 0.33, + "learning_rate": 1.7013246777692063e-05, + "loss": 1.4252, + "step": 3121 + }, + { + "epoch": 0.33, + "learning_rate": 1.7010637128010037e-05, + "loss": 1.3748, + "step": 3122 + }, + { + "epoch": 0.33, + "learning_rate": 1.7008026539082767e-05, + "loss": 1.3804, + "step": 3123 + }, + { + "epoch": 0.33, + "learning_rate": 1.7005415011260008e-05, + "loss": 1.4203, + "step": 3124 + }, + { + "epoch": 0.33, + "learning_rate": 1.7002802544891634e-05, + "loss": 1.4195, + "step": 3125 + }, + { + "epoch": 0.33, + "learning_rate": 1.700018914032765e-05, + "loss": 1.4188, + "step": 3126 + }, + { + "epoch": 0.33, + "learning_rate": 1.699757479791819e-05, + "loss": 1.3884, + "step": 3127 + }, + { + "epoch": 0.33, + "learning_rate": 1.6994959518013502e-05, + "loss": 1.4111, + "step": 3128 + }, + { + "epoch": 0.33, + "learning_rate": 1.6992343300963963e-05, + "loss": 1.5452, + "step": 3129 + }, + { + "epoch": 0.33, + "learning_rate": 1.6989726147120087e-05, + "loss": 1.4097, + "step": 3130 + }, + { + "epoch": 0.33, + "learning_rate": 1.6987108056832506e-05, + "loss": 1.481, + "step": 3131 + }, + { + "epoch": 0.33, + "learning_rate": 1.6984489030451973e-05, + "loss": 1.4505, + "step": 3132 + }, + { + "epoch": 0.33, + "learning_rate": 1.6981869068329368e-05, + "loss": 1.4281, + "step": 3133 + }, + { + "epoch": 0.33, + "learning_rate": 1.69792481708157e-05, + "loss": 1.4555, + "step": 3134 + }, + { + "epoch": 0.33, + "learning_rate": 1.6976626338262103e-05, + "loss": 1.4525, + "step": 3135 + }, + { + "epoch": 0.33, + "learning_rate": 1.6974003571019837e-05, + "loss": 1.3765, + "step": 3136 + }, + { + "epoch": 0.33, + "learning_rate": 1.6971379869440286e-05, + "loss": 1.3998, + "step": 3137 + }, + { + "epoch": 0.33, + "learning_rate": 1.696875523387495e-05, + "loss": 1.5103, + "step": 3138 + }, + { + "epoch": 0.33, + "learning_rate": 1.6966129664675474e-05, + "loss": 1.427, + "step": 3139 + }, + { + "epoch": 0.33, + "learning_rate": 1.6963503162193612e-05, + "loss": 1.4362, + "step": 3140 + }, + { + "epoch": 0.33, + "learning_rate": 1.6960875726781246e-05, + "loss": 1.4073, + "step": 3141 + }, + { + "epoch": 0.33, + "learning_rate": 1.6958247358790388e-05, + "loss": 1.4014, + "step": 3142 + }, + { + "epoch": 0.33, + "learning_rate": 1.6955618058573165e-05, + "loss": 1.4244, + "step": 3143 + }, + { + "epoch": 0.33, + "learning_rate": 1.6952987826481847e-05, + "loss": 1.47, + "step": 3144 + }, + { + "epoch": 0.33, + "learning_rate": 1.6950356662868814e-05, + "loss": 1.5112, + "step": 3145 + }, + { + "epoch": 0.33, + "learning_rate": 1.6947724568086562e-05, + "loss": 1.3398, + "step": 3146 + }, + { + "epoch": 0.33, + "learning_rate": 1.694509154248774e-05, + "loss": 1.4584, + "step": 3147 + }, + { + "epoch": 0.33, + "learning_rate": 1.69424575864251e-05, + "loss": 1.4383, + "step": 3148 + }, + { + "epoch": 0.33, + "learning_rate": 1.6939822700251523e-05, + "loss": 1.3869, + "step": 3149 + }, + { + "epoch": 0.33, + "learning_rate": 1.6937186884320015e-05, + "loss": 1.4453, + "step": 3150 + }, + { + "epoch": 0.33, + "learning_rate": 1.6934550138983713e-05, + "loss": 1.3355, + "step": 3151 + }, + { + "epoch": 0.33, + "learning_rate": 1.6931912464595866e-05, + "loss": 1.5573, + "step": 3152 + }, + { + "epoch": 0.33, + "learning_rate": 1.6929273861509865e-05, + "loss": 1.439, + "step": 3153 + }, + { + "epoch": 0.33, + "learning_rate": 1.6926634330079203e-05, + "loss": 1.6079, + "step": 3154 + }, + { + "epoch": 0.33, + "learning_rate": 1.692399387065752e-05, + "loss": 1.6973, + "step": 3155 + }, + { + "epoch": 0.33, + "learning_rate": 1.692135248359856e-05, + "loss": 1.3769, + "step": 3156 + }, + { + "epoch": 0.33, + "learning_rate": 1.6918710169256206e-05, + "loss": 1.4454, + "step": 3157 + }, + { + "epoch": 0.33, + "learning_rate": 1.691606692798446e-05, + "loss": 1.4495, + "step": 3158 + }, + { + "epoch": 0.33, + "learning_rate": 1.691342276013745e-05, + "loss": 1.4292, + "step": 3159 + }, + { + "epoch": 0.33, + "learning_rate": 1.691077766606942e-05, + "loss": 1.4405, + "step": 3160 + }, + { + "epoch": 0.33, + "learning_rate": 1.6908131646134757e-05, + "loss": 1.3683, + "step": 3161 + }, + { + "epoch": 0.33, + "learning_rate": 1.690548470068795e-05, + "loss": 1.4731, + "step": 3162 + }, + { + "epoch": 0.33, + "learning_rate": 1.690283683008362e-05, + "loss": 1.4323, + "step": 3163 + }, + { + "epoch": 0.33, + "learning_rate": 1.6900188034676518e-05, + "loss": 1.5133, + "step": 3164 + }, + { + "epoch": 0.33, + "learning_rate": 1.6897538314821516e-05, + "loss": 1.5529, + "step": 3165 + }, + { + "epoch": 0.33, + "learning_rate": 1.6894887670873605e-05, + "loss": 1.4427, + "step": 3166 + }, + { + "epoch": 0.33, + "learning_rate": 1.6892236103187904e-05, + "loss": 1.4344, + "step": 3167 + }, + { + "epoch": 0.33, + "learning_rate": 1.6889583612119657e-05, + "loss": 1.4291, + "step": 3168 + }, + { + "epoch": 0.33, + "learning_rate": 1.6886930198024226e-05, + "loss": 1.4683, + "step": 3169 + }, + { + "epoch": 0.33, + "learning_rate": 1.6884275861257106e-05, + "loss": 1.4442, + "step": 3170 + }, + { + "epoch": 0.33, + "learning_rate": 1.6881620602173905e-05, + "loss": 1.4509, + "step": 3171 + }, + { + "epoch": 0.33, + "learning_rate": 1.6878964421130362e-05, + "loss": 1.5113, + "step": 3172 + }, + { + "epoch": 0.33, + "learning_rate": 1.6876307318482334e-05, + "loss": 1.4261, + "step": 3173 + }, + { + "epoch": 0.33, + "learning_rate": 1.6873649294585805e-05, + "loss": 1.445, + "step": 3174 + }, + { + "epoch": 0.33, + "learning_rate": 1.6870990349796886e-05, + "loss": 1.4603, + "step": 3175 + }, + { + "epoch": 0.33, + "learning_rate": 1.68683304844718e-05, + "loss": 1.41, + "step": 3176 + }, + { + "epoch": 0.33, + "learning_rate": 1.686566969896691e-05, + "loss": 1.4018, + "step": 3177 + }, + { + "epoch": 0.33, + "learning_rate": 1.6863007993638687e-05, + "loss": 1.422, + "step": 3178 + }, + { + "epoch": 0.33, + "learning_rate": 1.6860345368843727e-05, + "loss": 1.4412, + "step": 3179 + }, + { + "epoch": 0.33, + "learning_rate": 1.6857681824938768e-05, + "loss": 1.5411, + "step": 3180 + }, + { + "epoch": 0.33, + "learning_rate": 1.685501736228064e-05, + "loss": 1.4416, + "step": 3181 + }, + { + "epoch": 0.33, + "learning_rate": 1.685235198122632e-05, + "loss": 1.5113, + "step": 3182 + }, + { + "epoch": 0.33, + "learning_rate": 1.6849685682132903e-05, + "loss": 1.423, + "step": 3183 + }, + { + "epoch": 0.33, + "learning_rate": 1.68470184653576e-05, + "loss": 1.404, + "step": 3184 + }, + { + "epoch": 0.33, + "eval_loss": 1.4771089553833008, + "eval_runtime": 77.4034, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3184 + }, + { + "epoch": 0.33, + "learning_rate": 1.6844350331257747e-05, + "loss": 1.4624, + "step": 3185 + }, + { + "epoch": 0.33, + "learning_rate": 1.6841681280190814e-05, + "loss": 1.4306, + "step": 3186 + }, + { + "epoch": 0.33, + "learning_rate": 1.683901131251438e-05, + "loss": 1.42, + "step": 3187 + }, + { + "epoch": 0.33, + "learning_rate": 1.6836340428586155e-05, + "loss": 1.4787, + "step": 3188 + }, + { + "epoch": 0.33, + "learning_rate": 1.6833668628763965e-05, + "loss": 1.3485, + "step": 3189 + }, + { + "epoch": 0.33, + "learning_rate": 1.683099591340576e-05, + "loss": 1.3674, + "step": 3190 + }, + { + "epoch": 0.33, + "learning_rate": 1.6828322282869627e-05, + "loss": 1.5187, + "step": 3191 + }, + { + "epoch": 0.33, + "learning_rate": 1.682564773751375e-05, + "loss": 1.4847, + "step": 3192 + }, + { + "epoch": 0.33, + "learning_rate": 1.682297227769646e-05, + "loss": 1.4815, + "step": 3193 + }, + { + "epoch": 0.33, + "learning_rate": 1.682029590377619e-05, + "loss": 1.4281, + "step": 3194 + }, + { + "epoch": 0.34, + "learning_rate": 1.6817618616111517e-05, + "loss": 1.4734, + "step": 3195 + }, + { + "epoch": 0.34, + "learning_rate": 1.681494041506112e-05, + "loss": 1.4861, + "step": 3196 + }, + { + "epoch": 0.34, + "learning_rate": 1.6812261300983808e-05, + "loss": 1.4372, + "step": 3197 + }, + { + "epoch": 0.34, + "learning_rate": 1.680958127423852e-05, + "loss": 1.4396, + "step": 3198 + }, + { + "epoch": 0.34, + "learning_rate": 1.680690033518431e-05, + "loss": 1.4225, + "step": 3199 + }, + { + "epoch": 0.34, + "learning_rate": 1.6804218484180347e-05, + "loss": 1.4925, + "step": 3200 + }, + { + "epoch": 0.34, + "learning_rate": 1.6801535721585942e-05, + "loss": 1.4306, + "step": 3201 + }, + { + "epoch": 0.34, + "learning_rate": 1.6798852047760506e-05, + "loss": 1.4298, + "step": 3202 + }, + { + "epoch": 0.34, + "learning_rate": 1.6796167463063588e-05, + "loss": 1.4725, + "step": 3203 + }, + { + "epoch": 0.34, + "learning_rate": 1.679348196785485e-05, + "loss": 1.4648, + "step": 3204 + }, + { + "epoch": 0.34, + "learning_rate": 1.6790795562494087e-05, + "loss": 1.4152, + "step": 3205 + }, + { + "epoch": 0.34, + "learning_rate": 1.6788108247341198e-05, + "loss": 1.4637, + "step": 3206 + }, + { + "epoch": 0.34, + "learning_rate": 1.6785420022756216e-05, + "loss": 1.4077, + "step": 3207 + }, + { + "epoch": 0.34, + "learning_rate": 1.67827308890993e-05, + "loss": 1.4585, + "step": 3208 + }, + { + "epoch": 0.34, + "learning_rate": 1.678004084673072e-05, + "loss": 1.3747, + "step": 3209 + }, + { + "epoch": 0.34, + "learning_rate": 1.6777349896010876e-05, + "loss": 1.4264, + "step": 3210 + }, + { + "epoch": 0.34, + "learning_rate": 1.677465803730028e-05, + "loss": 1.4178, + "step": 3211 + }, + { + "epoch": 0.34, + "learning_rate": 1.6771965270959584e-05, + "loss": 1.3876, + "step": 3212 + }, + { + "epoch": 0.34, + "learning_rate": 1.6769271597349538e-05, + "loss": 1.4658, + "step": 3213 + }, + { + "epoch": 0.34, + "learning_rate": 1.6766577016831026e-05, + "loss": 1.3968, + "step": 3214 + }, + { + "epoch": 0.34, + "learning_rate": 1.676388152976506e-05, + "loss": 1.5015, + "step": 3215 + }, + { + "epoch": 0.34, + "learning_rate": 1.6761185136512756e-05, + "loss": 1.4121, + "step": 3216 + }, + { + "epoch": 0.34, + "learning_rate": 1.675848783743537e-05, + "loss": 1.4146, + "step": 3217 + }, + { + "epoch": 0.34, + "learning_rate": 1.675578963289427e-05, + "loss": 1.4113, + "step": 3218 + }, + { + "epoch": 0.34, + "learning_rate": 1.6753090523250937e-05, + "loss": 1.4048, + "step": 3219 + }, + { + "epoch": 0.34, + "learning_rate": 1.6750390508866994e-05, + "loss": 1.4959, + "step": 3220 + }, + { + "epoch": 0.34, + "learning_rate": 1.6747689590104167e-05, + "loss": 1.4445, + "step": 3221 + }, + { + "epoch": 0.34, + "learning_rate": 1.6744987767324312e-05, + "loss": 1.4611, + "step": 3222 + }, + { + "epoch": 0.34, + "learning_rate": 1.67422850408894e-05, + "loss": 1.4141, + "step": 3223 + }, + { + "epoch": 0.34, + "learning_rate": 1.6739581411161535e-05, + "loss": 1.4218, + "step": 3224 + }, + { + "epoch": 0.34, + "learning_rate": 1.6736876878502925e-05, + "loss": 1.4266, + "step": 3225 + }, + { + "epoch": 0.34, + "learning_rate": 1.6734171443275913e-05, + "loss": 1.4941, + "step": 3226 + }, + { + "epoch": 0.34, + "learning_rate": 1.6731465105842955e-05, + "loss": 1.4294, + "step": 3227 + }, + { + "epoch": 0.34, + "learning_rate": 1.6728757866566635e-05, + "loss": 1.4189, + "step": 3228 + }, + { + "epoch": 0.34, + "learning_rate": 1.6726049725809647e-05, + "loss": 1.4713, + "step": 3229 + }, + { + "epoch": 0.34, + "learning_rate": 1.6723340683934818e-05, + "loss": 1.4203, + "step": 3230 + }, + { + "epoch": 0.34, + "learning_rate": 1.6720630741305088e-05, + "loss": 1.4112, + "step": 3231 + }, + { + "epoch": 0.34, + "learning_rate": 1.6717919898283523e-05, + "loss": 1.3811, + "step": 3232 + }, + { + "epoch": 0.34, + "learning_rate": 1.6715208155233296e-05, + "loss": 1.4242, + "step": 3233 + }, + { + "epoch": 0.34, + "learning_rate": 1.6712495512517725e-05, + "loss": 1.4207, + "step": 3234 + }, + { + "epoch": 0.34, + "learning_rate": 1.6709781970500222e-05, + "loss": 1.4888, + "step": 3235 + }, + { + "epoch": 0.34, + "learning_rate": 1.670706752954434e-05, + "loss": 1.4501, + "step": 3236 + }, + { + "epoch": 0.34, + "learning_rate": 1.670435219001374e-05, + "loss": 1.4367, + "step": 3237 + }, + { + "epoch": 0.34, + "learning_rate": 1.6701635952272212e-05, + "loss": 1.3959, + "step": 3238 + }, + { + "epoch": 0.34, + "learning_rate": 1.6698918816683655e-05, + "loss": 1.4257, + "step": 3239 + }, + { + "epoch": 0.34, + "learning_rate": 1.6696200783612102e-05, + "loss": 1.4718, + "step": 3240 + }, + { + "epoch": 0.34, + "learning_rate": 1.6693481853421697e-05, + "loss": 1.5899, + "step": 3241 + }, + { + "epoch": 0.34, + "learning_rate": 1.6690762026476707e-05, + "loss": 1.418, + "step": 3242 + }, + { + "epoch": 0.34, + "learning_rate": 1.668804130314152e-05, + "loss": 1.4076, + "step": 3243 + }, + { + "epoch": 0.34, + "learning_rate": 1.6685319683780645e-05, + "loss": 1.4571, + "step": 3244 + }, + { + "epoch": 0.34, + "learning_rate": 1.66825971687587e-05, + "loss": 1.4066, + "step": 3245 + }, + { + "epoch": 0.34, + "learning_rate": 1.6679873758440442e-05, + "loss": 1.4639, + "step": 3246 + }, + { + "epoch": 0.34, + "learning_rate": 1.6677149453190732e-05, + "loss": 1.453, + "step": 3247 + }, + { + "epoch": 0.34, + "learning_rate": 1.6674424253374558e-05, + "loss": 1.4262, + "step": 3248 + }, + { + "epoch": 0.34, + "learning_rate": 1.667169815935703e-05, + "loss": 1.3687, + "step": 3249 + }, + { + "epoch": 0.34, + "learning_rate": 1.6668971171503372e-05, + "loss": 1.5557, + "step": 3250 + }, + { + "epoch": 0.34, + "learning_rate": 1.6666243290178933e-05, + "loss": 1.4639, + "step": 3251 + }, + { + "epoch": 0.34, + "learning_rate": 1.6663514515749172e-05, + "loss": 1.4334, + "step": 3252 + }, + { + "epoch": 0.34, + "learning_rate": 1.6660784848579685e-05, + "loss": 1.3523, + "step": 3253 + }, + { + "epoch": 0.34, + "learning_rate": 1.6658054289036166e-05, + "loss": 1.3738, + "step": 3254 + }, + { + "epoch": 0.34, + "learning_rate": 1.665532283748445e-05, + "loss": 1.4159, + "step": 3255 + }, + { + "epoch": 0.34, + "learning_rate": 1.6652590494290474e-05, + "loss": 1.3609, + "step": 3256 + }, + { + "epoch": 0.34, + "learning_rate": 1.6649857259820303e-05, + "loss": 1.4449, + "step": 3257 + }, + { + "epoch": 0.34, + "learning_rate": 1.6647123134440126e-05, + "loss": 1.424, + "step": 3258 + }, + { + "epoch": 0.34, + "learning_rate": 1.664438811851624e-05, + "loss": 1.4737, + "step": 3259 + }, + { + "epoch": 0.34, + "learning_rate": 1.6641652212415066e-05, + "loss": 1.2717, + "step": 3260 + }, + { + "epoch": 0.34, + "learning_rate": 1.663891541650315e-05, + "loss": 1.4845, + "step": 3261 + }, + { + "epoch": 0.34, + "learning_rate": 1.663617773114715e-05, + "loss": 1.4115, + "step": 3262 + }, + { + "epoch": 0.34, + "learning_rate": 1.663343915671384e-05, + "loss": 1.4237, + "step": 3263 + }, + { + "epoch": 0.34, + "learning_rate": 1.6630699693570127e-05, + "loss": 1.4209, + "step": 3264 + }, + { + "epoch": 0.34, + "learning_rate": 1.6627959342083026e-05, + "loss": 1.506, + "step": 3265 + }, + { + "epoch": 0.34, + "learning_rate": 1.6625218102619672e-05, + "loss": 1.4466, + "step": 3266 + }, + { + "epoch": 0.34, + "learning_rate": 1.6622475975547324e-05, + "loss": 1.4129, + "step": 3267 + }, + { + "epoch": 0.34, + "learning_rate": 1.661973296123335e-05, + "loss": 1.4152, + "step": 3268 + }, + { + "epoch": 0.34, + "learning_rate": 1.661698906004525e-05, + "loss": 1.43, + "step": 3269 + }, + { + "epoch": 0.34, + "learning_rate": 1.661424427235064e-05, + "loss": 1.4701, + "step": 3270 + }, + { + "epoch": 0.34, + "learning_rate": 1.6611498598517238e-05, + "loss": 1.4598, + "step": 3271 + }, + { + "epoch": 0.34, + "learning_rate": 1.66087520389129e-05, + "loss": 1.4795, + "step": 3272 + }, + { + "epoch": 0.34, + "learning_rate": 1.6606004593905595e-05, + "loss": 1.5264, + "step": 3273 + }, + { + "epoch": 0.34, + "learning_rate": 1.6603256263863415e-05, + "loss": 1.4412, + "step": 3274 + }, + { + "epoch": 0.34, + "learning_rate": 1.6600507049154556e-05, + "loss": 1.45, + "step": 3275 + }, + { + "epoch": 0.34, + "learning_rate": 1.659775695014735e-05, + "loss": 1.4985, + "step": 3276 + }, + { + "epoch": 0.34, + "learning_rate": 1.659500596721024e-05, + "loss": 1.496, + "step": 3277 + }, + { + "epoch": 0.34, + "learning_rate": 1.6592254100711775e-05, + "loss": 1.4386, + "step": 3278 + }, + { + "epoch": 0.34, + "learning_rate": 1.658950135102065e-05, + "loss": 1.4073, + "step": 3279 + }, + { + "epoch": 0.34, + "learning_rate": 1.658674771850565e-05, + "loss": 1.3912, + "step": 3280 + }, + { + "epoch": 0.34, + "learning_rate": 1.6583993203535702e-05, + "loss": 1.3628, + "step": 3281 + }, + { + "epoch": 0.34, + "learning_rate": 1.658123780647983e-05, + "loss": 1.6089, + "step": 3282 + }, + { + "epoch": 0.34, + "learning_rate": 1.6578481527707196e-05, + "loss": 1.2367, + "step": 3283 + }, + { + "epoch": 0.34, + "learning_rate": 1.657572436758706e-05, + "loss": 1.4058, + "step": 3284 + }, + { + "epoch": 0.34, + "learning_rate": 1.6572966326488825e-05, + "loss": 1.4067, + "step": 3285 + }, + { + "epoch": 0.34, + "learning_rate": 1.657020740478198e-05, + "loss": 1.4187, + "step": 3286 + }, + { + "epoch": 0.34, + "learning_rate": 1.6567447602836166e-05, + "loss": 1.4599, + "step": 3287 + }, + { + "epoch": 0.34, + "learning_rate": 1.6564686921021115e-05, + "loss": 1.432, + "step": 3288 + }, + { + "epoch": 0.34, + "learning_rate": 1.6561925359706693e-05, + "loss": 1.3941, + "step": 3289 + }, + { + "epoch": 0.35, + "learning_rate": 1.6559162919262874e-05, + "loss": 1.3644, + "step": 3290 + }, + { + "epoch": 0.35, + "learning_rate": 1.6556399600059756e-05, + "loss": 1.4628, + "step": 3291 + }, + { + "epoch": 0.35, + "learning_rate": 1.6553635402467555e-05, + "loss": 1.4355, + "step": 3292 + }, + { + "epoch": 0.35, + "learning_rate": 1.6550870326856596e-05, + "loss": 1.4627, + "step": 3293 + }, + { + "epoch": 0.35, + "learning_rate": 1.6548104373597335e-05, + "loss": 1.442, + "step": 3294 + }, + { + "epoch": 0.35, + "learning_rate": 1.6545337543060338e-05, + "loss": 1.3991, + "step": 3295 + }, + { + "epoch": 0.35, + "learning_rate": 1.6542569835616283e-05, + "loss": 1.4193, + "step": 3296 + }, + { + "epoch": 0.35, + "learning_rate": 1.6539801251635982e-05, + "loss": 1.4792, + "step": 3297 + }, + { + "epoch": 0.35, + "learning_rate": 1.653703179149034e-05, + "loss": 1.4735, + "step": 3298 + }, + { + "epoch": 0.35, + "learning_rate": 1.6534261455550408e-05, + "loss": 1.451, + "step": 3299 + }, + { + "epoch": 0.35, + "learning_rate": 1.653149024418733e-05, + "loss": 1.3975, + "step": 3300 + }, + { + "epoch": 0.35, + "learning_rate": 1.652871815777238e-05, + "loss": 1.4843, + "step": 3301 + }, + { + "epoch": 0.35, + "learning_rate": 1.6525945196676948e-05, + "loss": 1.4782, + "step": 3302 + }, + { + "epoch": 0.35, + "learning_rate": 1.652317136127254e-05, + "loss": 1.3865, + "step": 3303 + }, + { + "epoch": 0.35, + "learning_rate": 1.6520396651930777e-05, + "loss": 1.4359, + "step": 3304 + }, + { + "epoch": 0.35, + "learning_rate": 1.6517621069023397e-05, + "loss": 1.4289, + "step": 3305 + }, + { + "epoch": 0.35, + "learning_rate": 1.651484461292226e-05, + "loss": 1.3526, + "step": 3306 + }, + { + "epoch": 0.35, + "learning_rate": 1.6512067283999336e-05, + "loss": 1.3671, + "step": 3307 + }, + { + "epoch": 0.35, + "learning_rate": 1.650928908262672e-05, + "loss": 1.6041, + "step": 3308 + }, + { + "epoch": 0.35, + "learning_rate": 1.650651000917662e-05, + "loss": 1.4322, + "step": 3309 + }, + { + "epoch": 0.35, + "learning_rate": 1.6503730064021354e-05, + "loss": 1.3992, + "step": 3310 + }, + { + "epoch": 0.35, + "learning_rate": 1.650094924753337e-05, + "loss": 1.4928, + "step": 3311 + }, + { + "epoch": 0.35, + "learning_rate": 1.6498167560085222e-05, + "loss": 1.4075, + "step": 3312 + }, + { + "epoch": 0.35, + "learning_rate": 1.6495385002049583e-05, + "loss": 1.4535, + "step": 3313 + }, + { + "epoch": 0.35, + "learning_rate": 1.6492601573799253e-05, + "loss": 1.4221, + "step": 3314 + }, + { + "epoch": 0.35, + "learning_rate": 1.6489817275707133e-05, + "loss": 1.3688, + "step": 3315 + }, + { + "epoch": 0.35, + "learning_rate": 1.6487032108146243e-05, + "loss": 1.3889, + "step": 3316 + }, + { + "epoch": 0.35, + "learning_rate": 1.6484246071489733e-05, + "loss": 1.3942, + "step": 3317 + }, + { + "epoch": 0.35, + "learning_rate": 1.6481459166110858e-05, + "loss": 1.4004, + "step": 3318 + }, + { + "epoch": 0.35, + "learning_rate": 1.647867139238299e-05, + "loss": 1.7308, + "step": 3319 + }, + { + "epoch": 0.35, + "learning_rate": 1.6475882750679622e-05, + "loss": 1.5001, + "step": 3320 + }, + { + "epoch": 0.35, + "learning_rate": 1.647309324137435e-05, + "loss": 1.4325, + "step": 3321 + }, + { + "epoch": 0.35, + "learning_rate": 1.6470302864840913e-05, + "loss": 1.4494, + "step": 3322 + }, + { + "epoch": 0.35, + "learning_rate": 1.6467511621453136e-05, + "loss": 1.4418, + "step": 3323 + }, + { + "epoch": 0.35, + "learning_rate": 1.646471951158498e-05, + "loss": 1.4046, + "step": 3324 + }, + { + "epoch": 0.35, + "learning_rate": 1.6461926535610517e-05, + "loss": 1.5031, + "step": 3325 + }, + { + "epoch": 0.35, + "learning_rate": 1.645913269390393e-05, + "loss": 1.4813, + "step": 3326 + }, + { + "epoch": 0.35, + "learning_rate": 1.6456337986839525e-05, + "loss": 1.3842, + "step": 3327 + }, + { + "epoch": 0.35, + "learning_rate": 1.645354241479172e-05, + "loss": 1.4539, + "step": 3328 + }, + { + "epoch": 0.35, + "learning_rate": 1.6450745978135048e-05, + "loss": 1.4503, + "step": 3329 + }, + { + "epoch": 0.35, + "learning_rate": 1.6447948677244163e-05, + "loss": 1.3741, + "step": 3330 + }, + { + "epoch": 0.35, + "learning_rate": 1.6445150512493832e-05, + "loss": 1.425, + "step": 3331 + }, + { + "epoch": 0.35, + "learning_rate": 1.644235148425893e-05, + "loss": 1.4277, + "step": 3332 + }, + { + "epoch": 0.35, + "learning_rate": 1.6439551592914464e-05, + "loss": 1.4918, + "step": 3333 + }, + { + "epoch": 0.35, + "learning_rate": 1.6436750838835543e-05, + "loss": 1.3364, + "step": 3334 + }, + { + "epoch": 0.35, + "learning_rate": 1.6433949222397397e-05, + "loss": 1.4741, + "step": 3335 + }, + { + "epoch": 0.35, + "learning_rate": 1.643114674397537e-05, + "loss": 1.3867, + "step": 3336 + }, + { + "epoch": 0.35, + "learning_rate": 1.642834340394492e-05, + "loss": 1.3817, + "step": 3337 + }, + { + "epoch": 0.35, + "learning_rate": 1.6425539202681625e-05, + "loss": 1.4308, + "step": 3338 + }, + { + "epoch": 0.35, + "learning_rate": 1.6422734140561178e-05, + "loss": 1.4401, + "step": 3339 + }, + { + "epoch": 0.35, + "learning_rate": 1.641992821795938e-05, + "loss": 1.4338, + "step": 3340 + }, + { + "epoch": 0.35, + "learning_rate": 1.641712143525216e-05, + "loss": 1.3804, + "step": 3341 + }, + { + "epoch": 0.35, + "learning_rate": 1.6414313792815546e-05, + "loss": 1.371, + "step": 3342 + }, + { + "epoch": 0.35, + "learning_rate": 1.6411505291025695e-05, + "loss": 1.4102, + "step": 3343 + }, + { + "epoch": 0.35, + "learning_rate": 1.6408695930258875e-05, + "loss": 1.4433, + "step": 3344 + }, + { + "epoch": 0.35, + "learning_rate": 1.6405885710891467e-05, + "loss": 1.3895, + "step": 3345 + }, + { + "epoch": 0.35, + "learning_rate": 1.6403074633299966e-05, + "loss": 1.4321, + "step": 3346 + }, + { + "epoch": 0.35, + "learning_rate": 1.640026269786098e-05, + "loss": 1.4207, + "step": 3347 + }, + { + "epoch": 0.35, + "learning_rate": 1.639744990495125e-05, + "loss": 1.3758, + "step": 3348 + }, + { + "epoch": 0.35, + "learning_rate": 1.6394636254947612e-05, + "loss": 1.4203, + "step": 3349 + }, + { + "epoch": 0.35, + "learning_rate": 1.6391821748227013e-05, + "loss": 1.4596, + "step": 3350 + }, + { + "epoch": 0.35, + "learning_rate": 1.6389006385166537e-05, + "loss": 1.4344, + "step": 3351 + }, + { + "epoch": 0.35, + "learning_rate": 1.6386190166143366e-05, + "loss": 1.4048, + "step": 3352 + }, + { + "epoch": 0.35, + "learning_rate": 1.6383373091534798e-05, + "loss": 1.4348, + "step": 3353 + }, + { + "epoch": 0.35, + "learning_rate": 1.638055516171825e-05, + "loss": 1.4972, + "step": 3354 + }, + { + "epoch": 0.35, + "learning_rate": 1.6377736377071258e-05, + "loss": 1.4685, + "step": 3355 + }, + { + "epoch": 0.35, + "learning_rate": 1.637491673797146e-05, + "loss": 1.4093, + "step": 3356 + }, + { + "epoch": 0.35, + "learning_rate": 1.6372096244796616e-05, + "loss": 1.4452, + "step": 3357 + }, + { + "epoch": 0.35, + "learning_rate": 1.63692748979246e-05, + "loss": 1.4458, + "step": 3358 + }, + { + "epoch": 0.35, + "learning_rate": 1.6366452697733404e-05, + "loss": 1.4187, + "step": 3359 + }, + { + "epoch": 0.35, + "learning_rate": 1.6363629644601126e-05, + "loss": 1.4052, + "step": 3360 + }, + { + "epoch": 0.35, + "learning_rate": 1.6360805738905984e-05, + "loss": 1.439, + "step": 3361 + }, + { + "epoch": 0.35, + "learning_rate": 1.635798098102631e-05, + "loss": 1.4131, + "step": 3362 + }, + { + "epoch": 0.35, + "learning_rate": 1.6355155371340544e-05, + "loss": 1.4391, + "step": 3363 + }, + { + "epoch": 0.35, + "learning_rate": 1.6352328910227252e-05, + "loss": 1.4318, + "step": 3364 + }, + { + "epoch": 0.35, + "learning_rate": 1.63495015980651e-05, + "loss": 1.5112, + "step": 3365 + }, + { + "epoch": 0.35, + "learning_rate": 1.6346673435232884e-05, + "loss": 1.4688, + "step": 3366 + }, + { + "epoch": 0.35, + "learning_rate": 1.6343844422109496e-05, + "loss": 1.3807, + "step": 3367 + }, + { + "epoch": 0.35, + "learning_rate": 1.634101455907396e-05, + "loss": 1.4083, + "step": 3368 + }, + { + "epoch": 0.35, + "learning_rate": 1.6338183846505394e-05, + "loss": 1.3566, + "step": 3369 + }, + { + "epoch": 0.35, + "learning_rate": 1.633535228478305e-05, + "loss": 1.4287, + "step": 3370 + }, + { + "epoch": 0.35, + "learning_rate": 1.6332519874286285e-05, + "loss": 1.3494, + "step": 3371 + }, + { + "epoch": 0.35, + "learning_rate": 1.6329686615394558e-05, + "loss": 1.3813, + "step": 3372 + }, + { + "epoch": 0.35, + "learning_rate": 1.6326852508487468e-05, + "loss": 1.4241, + "step": 3373 + }, + { + "epoch": 0.35, + "learning_rate": 1.63240175539447e-05, + "loss": 1.424, + "step": 3374 + }, + { + "epoch": 0.35, + "learning_rate": 1.632118175214607e-05, + "loss": 1.4212, + "step": 3375 + }, + { + "epoch": 0.35, + "learning_rate": 1.6318345103471504e-05, + "loss": 1.4671, + "step": 3376 + }, + { + "epoch": 0.35, + "learning_rate": 1.6315507608301044e-05, + "loss": 1.4593, + "step": 3377 + }, + { + "epoch": 0.35, + "learning_rate": 1.631266926701483e-05, + "loss": 1.7816, + "step": 3378 + }, + { + "epoch": 0.35, + "learning_rate": 1.6309830079993134e-05, + "loss": 1.5134, + "step": 3379 + }, + { + "epoch": 0.35, + "learning_rate": 1.6306990047616334e-05, + "loss": 0.8933, + "step": 3380 + }, + { + "epoch": 0.35, + "learning_rate": 1.630414917026492e-05, + "loss": 1.1033, + "step": 3381 + }, + { + "epoch": 0.35, + "learning_rate": 1.6301307448319497e-05, + "loss": 1.3494, + "step": 3382 + }, + { + "epoch": 0.35, + "learning_rate": 1.6298464882160784e-05, + "loss": 1.4299, + "step": 3383 + }, + { + "epoch": 0.35, + "eval_loss": 1.482450008392334, + "eval_runtime": 77.3737, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3383 + }, + { + "epoch": 0.35, + "learning_rate": 1.629562147216961e-05, + "loss": 1.3971, + "step": 3384 + }, + { + "epoch": 0.35, + "learning_rate": 1.6292777218726917e-05, + "loss": 1.3706, + "step": 3385 + }, + { + "epoch": 0.36, + "learning_rate": 1.6289932122213765e-05, + "loss": 1.4524, + "step": 3386 + }, + { + "epoch": 0.36, + "learning_rate": 1.6287086183011328e-05, + "loss": 1.4595, + "step": 3387 + }, + { + "epoch": 0.36, + "learning_rate": 1.628423940150088e-05, + "loss": 1.492, + "step": 3388 + }, + { + "epoch": 0.36, + "learning_rate": 1.628139177806382e-05, + "loss": 1.5576, + "step": 3389 + }, + { + "epoch": 0.36, + "learning_rate": 1.6278543313081657e-05, + "loss": 1.4615, + "step": 3390 + }, + { + "epoch": 0.36, + "learning_rate": 1.6275694006936015e-05, + "loss": 1.3456, + "step": 3391 + }, + { + "epoch": 0.36, + "learning_rate": 1.627284386000862e-05, + "loss": 1.4254, + "step": 3392 + }, + { + "epoch": 0.36, + "learning_rate": 1.6269992872681325e-05, + "loss": 1.433, + "step": 3393 + }, + { + "epoch": 0.36, + "learning_rate": 1.626714104533609e-05, + "loss": 1.5291, + "step": 3394 + }, + { + "epoch": 0.36, + "learning_rate": 1.626428837835498e-05, + "loss": 1.4502, + "step": 3395 + }, + { + "epoch": 0.36, + "learning_rate": 1.626143487212019e-05, + "loss": 1.3756, + "step": 3396 + }, + { + "epoch": 0.36, + "learning_rate": 1.6258580527014002e-05, + "loss": 1.414, + "step": 3397 + }, + { + "epoch": 0.36, + "learning_rate": 1.6255725343418835e-05, + "loss": 1.6289, + "step": 3398 + }, + { + "epoch": 0.36, + "learning_rate": 1.6252869321717208e-05, + "loss": 1.4862, + "step": 3399 + }, + { + "epoch": 0.36, + "learning_rate": 1.6250012462291756e-05, + "loss": 1.4213, + "step": 3400 + }, + { + "epoch": 0.36, + "learning_rate": 1.6247154765525217e-05, + "loss": 1.524, + "step": 3401 + }, + { + "epoch": 0.36, + "learning_rate": 1.624429623180046e-05, + "loss": 1.6013, + "step": 3402 + }, + { + "epoch": 0.36, + "learning_rate": 1.624143686150045e-05, + "loss": 1.4557, + "step": 3403 + }, + { + "epoch": 0.36, + "learning_rate": 1.6238576655008266e-05, + "loss": 1.3831, + "step": 3404 + }, + { + "epoch": 0.36, + "learning_rate": 1.6235715612707105e-05, + "loss": 1.4008, + "step": 3405 + }, + { + "epoch": 0.36, + "learning_rate": 1.623285373498028e-05, + "loss": 1.4848, + "step": 3406 + }, + { + "epoch": 0.36, + "learning_rate": 1.6229991022211197e-05, + "loss": 1.4459, + "step": 3407 + }, + { + "epoch": 0.36, + "learning_rate": 1.6227127474783393e-05, + "loss": 1.4334, + "step": 3408 + }, + { + "epoch": 0.36, + "learning_rate": 1.6224263093080507e-05, + "loss": 1.4123, + "step": 3409 + }, + { + "epoch": 0.36, + "learning_rate": 1.6221397877486294e-05, + "loss": 1.3691, + "step": 3410 + }, + { + "epoch": 0.36, + "learning_rate": 1.6218531828384618e-05, + "loss": 1.4128, + "step": 3411 + }, + { + "epoch": 0.36, + "learning_rate": 1.6215664946159457e-05, + "loss": 1.3642, + "step": 3412 + }, + { + "epoch": 0.36, + "learning_rate": 1.6212797231194902e-05, + "loss": 1.4311, + "step": 3413 + }, + { + "epoch": 0.36, + "learning_rate": 1.6209928683875152e-05, + "loss": 1.4695, + "step": 3414 + }, + { + "epoch": 0.36, + "learning_rate": 1.6207059304584514e-05, + "loss": 1.3871, + "step": 3415 + }, + { + "epoch": 0.36, + "learning_rate": 1.6204189093707414e-05, + "loss": 1.4219, + "step": 3416 + }, + { + "epoch": 0.36, + "learning_rate": 1.620131805162839e-05, + "loss": 1.6199, + "step": 3417 + }, + { + "epoch": 0.36, + "learning_rate": 1.619844617873208e-05, + "loss": 1.4433, + "step": 3418 + }, + { + "epoch": 0.36, + "learning_rate": 1.619557347540325e-05, + "loss": 1.4773, + "step": 3419 + }, + { + "epoch": 0.36, + "learning_rate": 1.6192699942026763e-05, + "loss": 1.4551, + "step": 3420 + }, + { + "epoch": 0.36, + "learning_rate": 1.6189825578987603e-05, + "loss": 1.4903, + "step": 3421 + }, + { + "epoch": 0.36, + "learning_rate": 1.6186950386670855e-05, + "loss": 1.473, + "step": 3422 + }, + { + "epoch": 0.36, + "learning_rate": 1.6184074365461722e-05, + "loss": 1.4082, + "step": 3423 + }, + { + "epoch": 0.36, + "learning_rate": 1.6181197515745523e-05, + "loss": 1.4746, + "step": 3424 + }, + { + "epoch": 0.36, + "learning_rate": 1.6178319837907674e-05, + "loss": 1.449, + "step": 3425 + }, + { + "epoch": 0.36, + "learning_rate": 1.6175441332333715e-05, + "loss": 1.377, + "step": 3426 + }, + { + "epoch": 0.36, + "learning_rate": 1.617256199940929e-05, + "loss": 1.2364, + "step": 3427 + }, + { + "epoch": 0.36, + "learning_rate": 1.6169681839520155e-05, + "loss": 1.4437, + "step": 3428 + }, + { + "epoch": 0.36, + "learning_rate": 1.616680085305218e-05, + "loss": 1.4726, + "step": 3429 + }, + { + "epoch": 0.36, + "learning_rate": 1.616391904039134e-05, + "loss": 1.4824, + "step": 3430 + }, + { + "epoch": 0.36, + "learning_rate": 1.616103640192373e-05, + "loss": 1.4052, + "step": 3431 + }, + { + "epoch": 0.36, + "learning_rate": 1.6158152938035537e-05, + "loss": 1.4131, + "step": 3432 + }, + { + "epoch": 0.36, + "learning_rate": 1.6155268649113084e-05, + "loss": 1.4267, + "step": 3433 + }, + { + "epoch": 0.36, + "learning_rate": 1.6152383535542786e-05, + "loss": 1.3735, + "step": 3434 + }, + { + "epoch": 0.36, + "learning_rate": 1.6149497597711175e-05, + "loss": 1.4249, + "step": 3435 + }, + { + "epoch": 0.36, + "learning_rate": 1.614661083600489e-05, + "loss": 1.4312, + "step": 3436 + }, + { + "epoch": 0.36, + "learning_rate": 1.6143723250810686e-05, + "loss": 1.4831, + "step": 3437 + }, + { + "epoch": 0.36, + "learning_rate": 1.6140834842515425e-05, + "loss": 1.4183, + "step": 3438 + }, + { + "epoch": 0.36, + "learning_rate": 1.6137945611506078e-05, + "loss": 1.3908, + "step": 3439 + }, + { + "epoch": 0.36, + "learning_rate": 1.613505555816973e-05, + "loss": 1.425, + "step": 3440 + }, + { + "epoch": 0.36, + "learning_rate": 1.613216468289357e-05, + "loss": 1.3589, + "step": 3441 + }, + { + "epoch": 0.36, + "learning_rate": 1.6129272986064903e-05, + "loss": 1.4272, + "step": 3442 + }, + { + "epoch": 0.36, + "learning_rate": 1.6126380468071142e-05, + "loss": 1.4337, + "step": 3443 + }, + { + "epoch": 0.36, + "learning_rate": 1.6123487129299817e-05, + "loss": 1.3872, + "step": 3444 + }, + { + "epoch": 0.36, + "learning_rate": 1.612059297013855e-05, + "loss": 1.374, + "step": 3445 + }, + { + "epoch": 0.36, + "learning_rate": 1.611769799097509e-05, + "loss": 1.314, + "step": 3446 + }, + { + "epoch": 0.36, + "learning_rate": 1.6114802192197284e-05, + "loss": 1.3951, + "step": 3447 + }, + { + "epoch": 0.36, + "learning_rate": 1.6111905574193102e-05, + "loss": 1.4732, + "step": 3448 + }, + { + "epoch": 0.36, + "learning_rate": 1.6109008137350614e-05, + "loss": 1.3575, + "step": 3449 + }, + { + "epoch": 0.36, + "learning_rate": 1.6106109882058e-05, + "loss": 1.4606, + "step": 3450 + }, + { + "epoch": 0.36, + "learning_rate": 1.6103210808703554e-05, + "loss": 1.4357, + "step": 3451 + }, + { + "epoch": 0.36, + "learning_rate": 1.6100310917675678e-05, + "loss": 0.8456, + "step": 3452 + }, + { + "epoch": 0.36, + "learning_rate": 1.609741020936288e-05, + "loss": 1.07, + "step": 3453 + }, + { + "epoch": 0.36, + "learning_rate": 1.6094508684153782e-05, + "loss": 1.4435, + "step": 3454 + }, + { + "epoch": 0.36, + "learning_rate": 1.609160634243711e-05, + "loss": 1.3696, + "step": 3455 + }, + { + "epoch": 0.36, + "learning_rate": 1.6088703184601712e-05, + "loss": 1.4012, + "step": 3456 + }, + { + "epoch": 0.36, + "learning_rate": 1.608579921103653e-05, + "loss": 1.5212, + "step": 3457 + }, + { + "epoch": 0.36, + "learning_rate": 1.608289442213062e-05, + "loss": 1.4339, + "step": 3458 + }, + { + "epoch": 0.36, + "learning_rate": 1.607998881827316e-05, + "loss": 1.4901, + "step": 3459 + }, + { + "epoch": 0.36, + "learning_rate": 1.6077082399853412e-05, + "loss": 1.4822, + "step": 3460 + }, + { + "epoch": 0.36, + "learning_rate": 1.607417516726077e-05, + "loss": 1.3696, + "step": 3461 + }, + { + "epoch": 0.36, + "learning_rate": 1.6071267120884727e-05, + "loss": 1.4434, + "step": 3462 + }, + { + "epoch": 0.36, + "learning_rate": 1.6068358261114886e-05, + "loss": 1.3916, + "step": 3463 + }, + { + "epoch": 0.36, + "learning_rate": 1.606544858834096e-05, + "loss": 1.422, + "step": 3464 + }, + { + "epoch": 0.36, + "learning_rate": 1.6062538102952763e-05, + "loss": 1.367, + "step": 3465 + }, + { + "epoch": 0.36, + "learning_rate": 1.605962680534024e-05, + "loss": 1.3788, + "step": 3466 + }, + { + "epoch": 0.36, + "learning_rate": 1.605671469589342e-05, + "loss": 1.4366, + "step": 3467 + }, + { + "epoch": 0.36, + "learning_rate": 1.6053801775002453e-05, + "loss": 1.4027, + "step": 3468 + }, + { + "epoch": 0.36, + "learning_rate": 1.6050888043057595e-05, + "loss": 1.4386, + "step": 3469 + }, + { + "epoch": 0.36, + "learning_rate": 1.6047973500449212e-05, + "loss": 1.4675, + "step": 3470 + }, + { + "epoch": 0.36, + "learning_rate": 1.6045058147567778e-05, + "loss": 1.6936, + "step": 3471 + }, + { + "epoch": 0.36, + "learning_rate": 1.6042141984803875e-05, + "loss": 1.4858, + "step": 3472 + }, + { + "epoch": 0.36, + "learning_rate": 1.6039225012548196e-05, + "loss": 1.5004, + "step": 3473 + }, + { + "epoch": 0.36, + "learning_rate": 1.6036307231191534e-05, + "loss": 1.4969, + "step": 3474 + }, + { + "epoch": 0.36, + "learning_rate": 1.6033388641124803e-05, + "loss": 1.4027, + "step": 3475 + }, + { + "epoch": 0.36, + "learning_rate": 1.6030469242739016e-05, + "loss": 1.4741, + "step": 3476 + }, + { + "epoch": 0.36, + "learning_rate": 1.60275490364253e-05, + "loss": 1.3887, + "step": 3477 + }, + { + "epoch": 0.36, + "learning_rate": 1.602462802257488e-05, + "loss": 1.6735, + "step": 3478 + }, + { + "epoch": 0.36, + "learning_rate": 1.602170620157911e-05, + "loss": 1.4997, + "step": 3479 + }, + { + "epoch": 0.36, + "learning_rate": 1.601878357382943e-05, + "loss": 1.3973, + "step": 3480 + }, + { + "epoch": 0.37, + "learning_rate": 1.6015860139717398e-05, + "loss": 1.416, + "step": 3481 + }, + { + "epoch": 0.37, + "learning_rate": 1.6012935899634682e-05, + "loss": 1.4102, + "step": 3482 + }, + { + "epoch": 0.37, + "learning_rate": 1.601001085397305e-05, + "loss": 1.4248, + "step": 3483 + }, + { + "epoch": 0.37, + "learning_rate": 1.6007085003124386e-05, + "loss": 1.3909, + "step": 3484 + }, + { + "epoch": 0.37, + "learning_rate": 1.600415834748068e-05, + "loss": 1.4029, + "step": 3485 + }, + { + "epoch": 0.37, + "learning_rate": 1.6001230887434024e-05, + "loss": 1.4219, + "step": 3486 + }, + { + "epoch": 0.37, + "learning_rate": 1.5998302623376633e-05, + "loss": 1.4008, + "step": 3487 + }, + { + "epoch": 0.37, + "learning_rate": 1.5995373555700806e-05, + "loss": 1.5163, + "step": 3488 + }, + { + "epoch": 0.37, + "learning_rate": 1.599244368479897e-05, + "loss": 1.4541, + "step": 3489 + }, + { + "epoch": 0.37, + "learning_rate": 1.598951301106365e-05, + "loss": 1.4454, + "step": 3490 + }, + { + "epoch": 0.37, + "learning_rate": 1.598658153488748e-05, + "loss": 1.1014, + "step": 3491 + }, + { + "epoch": 0.37, + "learning_rate": 1.598364925666321e-05, + "loss": 1.407, + "step": 3492 + }, + { + "epoch": 0.37, + "learning_rate": 1.5980716176783682e-05, + "loss": 1.5046, + "step": 3493 + }, + { + "epoch": 0.37, + "learning_rate": 1.5977782295641857e-05, + "loss": 1.4265, + "step": 3494 + }, + { + "epoch": 0.37, + "learning_rate": 1.5974847613630796e-05, + "loss": 1.46, + "step": 3495 + }, + { + "epoch": 0.37, + "learning_rate": 1.5971912131143677e-05, + "loss": 1.3996, + "step": 3496 + }, + { + "epoch": 0.37, + "learning_rate": 1.5968975848573772e-05, + "loss": 1.4719, + "step": 3497 + }, + { + "epoch": 0.37, + "learning_rate": 1.596603876631447e-05, + "loss": 1.43, + "step": 3498 + }, + { + "epoch": 0.37, + "learning_rate": 1.596310088475927e-05, + "loss": 1.4109, + "step": 3499 + }, + { + "epoch": 0.37, + "learning_rate": 1.5960162204301768e-05, + "loss": 1.3612, + "step": 3500 + }, + { + "epoch": 0.37, + "learning_rate": 1.5957222725335672e-05, + "loss": 1.5045, + "step": 3501 + }, + { + "epoch": 0.37, + "learning_rate": 1.5954282448254794e-05, + "loss": 1.5323, + "step": 3502 + }, + { + "epoch": 0.37, + "learning_rate": 1.595134137345306e-05, + "loss": 1.4518, + "step": 3503 + }, + { + "epoch": 0.37, + "learning_rate": 1.5948399501324495e-05, + "loss": 1.6131, + "step": 3504 + }, + { + "epoch": 0.37, + "learning_rate": 1.594545683226324e-05, + "loss": 1.5076, + "step": 3505 + }, + { + "epoch": 0.37, + "learning_rate": 1.594251336666353e-05, + "loss": 1.482, + "step": 3506 + }, + { + "epoch": 0.37, + "learning_rate": 1.5939569104919716e-05, + "loss": 1.4429, + "step": 3507 + }, + { + "epoch": 0.37, + "learning_rate": 1.5936624047426254e-05, + "loss": 1.4662, + "step": 3508 + }, + { + "epoch": 0.37, + "learning_rate": 1.5933678194577708e-05, + "loss": 1.425, + "step": 3509 + }, + { + "epoch": 0.37, + "learning_rate": 1.5930731546768744e-05, + "loss": 1.4312, + "step": 3510 + }, + { + "epoch": 0.37, + "learning_rate": 1.592778410439414e-05, + "loss": 1.4336, + "step": 3511 + }, + { + "epoch": 0.37, + "learning_rate": 1.5924835867848775e-05, + "loss": 1.4197, + "step": 3512 + }, + { + "epoch": 0.37, + "learning_rate": 1.5921886837527638e-05, + "loss": 1.4456, + "step": 3513 + }, + { + "epoch": 0.37, + "learning_rate": 1.5918937013825823e-05, + "loss": 1.4394, + "step": 3514 + }, + { + "epoch": 0.37, + "learning_rate": 1.5915986397138526e-05, + "loss": 1.3606, + "step": 3515 + }, + { + "epoch": 0.37, + "learning_rate": 1.591303498786106e-05, + "loss": 1.4382, + "step": 3516 + }, + { + "epoch": 0.37, + "learning_rate": 1.591008278638884e-05, + "loss": 1.4185, + "step": 3517 + }, + { + "epoch": 0.37, + "learning_rate": 1.5907129793117374e-05, + "loss": 1.6692, + "step": 3518 + }, + { + "epoch": 0.37, + "learning_rate": 1.59041760084423e-05, + "loss": 1.501, + "step": 3519 + }, + { + "epoch": 0.37, + "learning_rate": 1.5901221432759345e-05, + "loss": 1.5753, + "step": 3520 + }, + { + "epoch": 0.37, + "learning_rate": 1.589826606646434e-05, + "loss": 1.4795, + "step": 3521 + }, + { + "epoch": 0.37, + "learning_rate": 1.5895309909953236e-05, + "loss": 1.4379, + "step": 3522 + }, + { + "epoch": 0.37, + "learning_rate": 1.5892352963622078e-05, + "loss": 1.3426, + "step": 3523 + }, + { + "epoch": 0.37, + "learning_rate": 1.5889395227867025e-05, + "loss": 1.4048, + "step": 3524 + }, + { + "epoch": 0.37, + "learning_rate": 1.5886436703084332e-05, + "loss": 1.4303, + "step": 3525 + }, + { + "epoch": 0.37, + "learning_rate": 1.5883477389670367e-05, + "loss": 1.3684, + "step": 3526 + }, + { + "epoch": 0.37, + "learning_rate": 1.5880517288021602e-05, + "loss": 1.3701, + "step": 3527 + }, + { + "epoch": 0.37, + "learning_rate": 1.587755639853462e-05, + "loss": 1.4308, + "step": 3528 + }, + { + "epoch": 0.37, + "learning_rate": 1.5874594721606096e-05, + "loss": 1.3981, + "step": 3529 + }, + { + "epoch": 0.37, + "learning_rate": 1.5871632257632823e-05, + "loss": 1.5906, + "step": 3530 + }, + { + "epoch": 0.37, + "learning_rate": 1.5868669007011696e-05, + "loss": 1.4642, + "step": 3531 + }, + { + "epoch": 0.37, + "learning_rate": 1.586570497013971e-05, + "loss": 1.411, + "step": 3532 + }, + { + "epoch": 0.37, + "learning_rate": 1.586274014741397e-05, + "loss": 1.3942, + "step": 3533 + }, + { + "epoch": 0.37, + "learning_rate": 1.5859774539231693e-05, + "loss": 1.3952, + "step": 3534 + }, + { + "epoch": 0.37, + "learning_rate": 1.585680814599019e-05, + "loss": 1.4009, + "step": 3535 + }, + { + "epoch": 0.37, + "learning_rate": 1.585384096808688e-05, + "loss": 1.3238, + "step": 3536 + }, + { + "epoch": 0.37, + "learning_rate": 1.585087300591929e-05, + "loss": 1.346, + "step": 3537 + }, + { + "epoch": 0.37, + "learning_rate": 1.584790425988505e-05, + "loss": 1.3739, + "step": 3538 + }, + { + "epoch": 0.37, + "learning_rate": 1.5844934730381895e-05, + "loss": 1.4264, + "step": 3539 + }, + { + "epoch": 0.37, + "learning_rate": 1.5841964417807668e-05, + "loss": 1.4675, + "step": 3540 + }, + { + "epoch": 0.37, + "learning_rate": 1.5838993322560314e-05, + "loss": 1.3337, + "step": 3541 + }, + { + "epoch": 0.37, + "learning_rate": 1.5836021445037883e-05, + "loss": 1.4052, + "step": 3542 + }, + { + "epoch": 0.37, + "learning_rate": 1.583304878563853e-05, + "loss": 1.4311, + "step": 3543 + }, + { + "epoch": 0.37, + "learning_rate": 1.5830075344760513e-05, + "loss": 1.386, + "step": 3544 + }, + { + "epoch": 0.37, + "learning_rate": 1.58271011228022e-05, + "loss": 1.387, + "step": 3545 + }, + { + "epoch": 0.37, + "learning_rate": 1.582412612016206e-05, + "loss": 1.3601, + "step": 3546 + }, + { + "epoch": 0.37, + "learning_rate": 1.5821150337238663e-05, + "loss": 1.5111, + "step": 3547 + }, + { + "epoch": 0.37, + "learning_rate": 1.5818173774430697e-05, + "loss": 1.471, + "step": 3548 + }, + { + "epoch": 0.37, + "learning_rate": 1.581519643213693e-05, + "loss": 1.4442, + "step": 3549 + }, + { + "epoch": 0.37, + "learning_rate": 1.5812218310756263e-05, + "loss": 1.467, + "step": 3550 + }, + { + "epoch": 0.37, + "learning_rate": 1.5809239410687683e-05, + "loss": 1.3731, + "step": 3551 + }, + { + "epoch": 0.37, + "learning_rate": 1.5806259732330286e-05, + "loss": 1.4072, + "step": 3552 + }, + { + "epoch": 0.37, + "learning_rate": 1.5803279276083268e-05, + "loss": 1.3636, + "step": 3553 + }, + { + "epoch": 0.37, + "learning_rate": 1.5800298042345938e-05, + "loss": 1.3915, + "step": 3554 + }, + { + "epoch": 0.37, + "learning_rate": 1.5797316031517705e-05, + "loss": 1.5038, + "step": 3555 + }, + { + "epoch": 0.37, + "learning_rate": 1.5794333243998082e-05, + "loss": 1.4455, + "step": 3556 + }, + { + "epoch": 0.37, + "learning_rate": 1.5791349680186684e-05, + "loss": 1.5062, + "step": 3557 + }, + { + "epoch": 0.37, + "learning_rate": 1.5788365340483234e-05, + "loss": 1.3899, + "step": 3558 + }, + { + "epoch": 0.37, + "learning_rate": 1.5785380225287554e-05, + "loss": 1.4946, + "step": 3559 + }, + { + "epoch": 0.37, + "learning_rate": 1.5782394334999572e-05, + "loss": 1.3859, + "step": 3560 + }, + { + "epoch": 0.37, + "learning_rate": 1.577940767001933e-05, + "loss": 1.541, + "step": 3561 + }, + { + "epoch": 0.37, + "learning_rate": 1.5776420230746952e-05, + "loss": 1.4952, + "step": 3562 + }, + { + "epoch": 0.37, + "learning_rate": 1.5773432017582684e-05, + "loss": 1.6055, + "step": 3563 + }, + { + "epoch": 0.37, + "learning_rate": 1.577044303092687e-05, + "loss": 1.4661, + "step": 3564 + }, + { + "epoch": 0.37, + "learning_rate": 1.576745327117996e-05, + "loss": 1.4082, + "step": 3565 + }, + { + "epoch": 0.37, + "learning_rate": 1.5764462738742493e-05, + "loss": 1.4005, + "step": 3566 + }, + { + "epoch": 0.37, + "learning_rate": 1.5761471434015137e-05, + "loss": 1.3959, + "step": 3567 + }, + { + "epoch": 0.37, + "learning_rate": 1.5758479357398645e-05, + "loss": 1.4567, + "step": 3568 + }, + { + "epoch": 0.37, + "learning_rate": 1.575548650929388e-05, + "loss": 1.3791, + "step": 3569 + }, + { + "epoch": 0.37, + "learning_rate": 1.57524928901018e-05, + "loss": 1.4428, + "step": 3570 + }, + { + "epoch": 0.37, + "learning_rate": 1.5749498500223486e-05, + "loss": 1.3864, + "step": 3571 + }, + { + "epoch": 0.37, + "learning_rate": 1.5746503340060097e-05, + "loss": 1.4019, + "step": 3572 + }, + { + "epoch": 0.37, + "learning_rate": 1.574350741001291e-05, + "loss": 1.5436, + "step": 3573 + }, + { + "epoch": 0.37, + "learning_rate": 1.5740510710483308e-05, + "loss": 1.4637, + "step": 3574 + }, + { + "epoch": 0.37, + "learning_rate": 1.5737513241872767e-05, + "loss": 1.5097, + "step": 3575 + }, + { + "epoch": 0.38, + "learning_rate": 1.5734515004582873e-05, + "loss": 1.5143, + "step": 3576 + }, + { + "epoch": 0.38, + "learning_rate": 1.5731515999015315e-05, + "loss": 1.3926, + "step": 3577 + }, + { + "epoch": 0.38, + "learning_rate": 1.5728516225571874e-05, + "loss": 1.4242, + "step": 3578 + }, + { + "epoch": 0.38, + "learning_rate": 1.5725515684654453e-05, + "loss": 1.4429, + "step": 3579 + }, + { + "epoch": 0.38, + "learning_rate": 1.572251437666504e-05, + "loss": 1.4638, + "step": 3580 + }, + { + "epoch": 0.38, + "learning_rate": 1.5719512302005735e-05, + "loss": 1.3381, + "step": 3581 + }, + { + "epoch": 0.38, + "learning_rate": 1.571650946107874e-05, + "loss": 1.4342, + "step": 3582 + }, + { + "epoch": 0.38, + "eval_loss": 1.4705015420913696, + "eval_runtime": 77.3664, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3582 + }, + { + "epoch": 0.38, + "learning_rate": 1.571350585428636e-05, + "loss": 1.3991, + "step": 3583 + }, + { + "epoch": 0.38, + "learning_rate": 1.5710501482030998e-05, + "loss": 1.4274, + "step": 3584 + }, + { + "epoch": 0.38, + "learning_rate": 1.5707496344715166e-05, + "loss": 1.438, + "step": 3585 + }, + { + "epoch": 0.38, + "learning_rate": 1.570449044274147e-05, + "loss": 1.4453, + "step": 3586 + }, + { + "epoch": 0.38, + "learning_rate": 1.570148377651263e-05, + "loss": 1.4022, + "step": 3587 + }, + { + "epoch": 0.38, + "learning_rate": 1.5698476346431454e-05, + "loss": 1.4312, + "step": 3588 + }, + { + "epoch": 0.38, + "learning_rate": 1.569546815290087e-05, + "loss": 1.4329, + "step": 3589 + }, + { + "epoch": 0.38, + "learning_rate": 1.569245919632389e-05, + "loss": 1.4036, + "step": 3590 + }, + { + "epoch": 0.38, + "learning_rate": 1.5689449477103644e-05, + "loss": 1.412, + "step": 3591 + }, + { + "epoch": 0.38, + "learning_rate": 1.5686438995643353e-05, + "loss": 1.4492, + "step": 3592 + }, + { + "epoch": 0.38, + "learning_rate": 1.5683427752346343e-05, + "loss": 1.4555, + "step": 3593 + }, + { + "epoch": 0.38, + "learning_rate": 1.5680415747616047e-05, + "loss": 1.5594, + "step": 3594 + }, + { + "epoch": 0.38, + "learning_rate": 1.5677402981855993e-05, + "loss": 1.4813, + "step": 3595 + }, + { + "epoch": 0.38, + "learning_rate": 1.567438945546982e-05, + "loss": 1.5919, + "step": 3596 + }, + { + "epoch": 0.38, + "learning_rate": 1.5671375168861255e-05, + "loss": 1.4235, + "step": 3597 + }, + { + "epoch": 0.38, + "learning_rate": 1.5668360122434135e-05, + "loss": 1.441, + "step": 3598 + }, + { + "epoch": 0.38, + "learning_rate": 1.566534431659241e-05, + "loss": 1.5847, + "step": 3599 + }, + { + "epoch": 0.38, + "learning_rate": 1.566232775174011e-05, + "loss": 1.6123, + "step": 3600 + }, + { + "epoch": 0.38, + "learning_rate": 1.5659310428281374e-05, + "loss": 1.4916, + "step": 3601 + }, + { + "epoch": 0.38, + "learning_rate": 1.5656292346620457e-05, + "loss": 1.4603, + "step": 3602 + }, + { + "epoch": 0.38, + "learning_rate": 1.56532735071617e-05, + "loss": 1.4423, + "step": 3603 + }, + { + "epoch": 0.38, + "learning_rate": 1.5650253910309547e-05, + "loss": 1.4814, + "step": 3604 + }, + { + "epoch": 0.38, + "learning_rate": 1.5647233556468552e-05, + "loss": 1.4015, + "step": 3605 + }, + { + "epoch": 0.38, + "learning_rate": 1.564421244604336e-05, + "loss": 1.3798, + "step": 3606 + }, + { + "epoch": 0.38, + "learning_rate": 1.5641190579438723e-05, + "loss": 1.4259, + "step": 3607 + }, + { + "epoch": 0.38, + "learning_rate": 1.5638167957059493e-05, + "loss": 1.3493, + "step": 3608 + }, + { + "epoch": 0.38, + "learning_rate": 1.5635144579310626e-05, + "loss": 1.3433, + "step": 3609 + }, + { + "epoch": 0.38, + "learning_rate": 1.5632120446597177e-05, + "loss": 1.4661, + "step": 3610 + }, + { + "epoch": 0.38, + "learning_rate": 1.5629095559324297e-05, + "loss": 1.4205, + "step": 3611 + }, + { + "epoch": 0.38, + "learning_rate": 1.562606991789725e-05, + "loss": 1.3976, + "step": 3612 + }, + { + "epoch": 0.38, + "learning_rate": 1.5623043522721393e-05, + "loss": 1.4261, + "step": 3613 + }, + { + "epoch": 0.38, + "learning_rate": 1.562001637420218e-05, + "loss": 1.4358, + "step": 3614 + }, + { + "epoch": 0.38, + "learning_rate": 1.5616988472745175e-05, + "loss": 1.437, + "step": 3615 + }, + { + "epoch": 0.38, + "learning_rate": 1.561395981875604e-05, + "loss": 1.3735, + "step": 3616 + }, + { + "epoch": 0.38, + "learning_rate": 1.5610930412640532e-05, + "loss": 1.4357, + "step": 3617 + }, + { + "epoch": 0.38, + "learning_rate": 1.560790025480452e-05, + "loss": 1.4003, + "step": 3618 + }, + { + "epoch": 0.38, + "learning_rate": 1.5604869345653965e-05, + "loss": 1.4127, + "step": 3619 + }, + { + "epoch": 0.38, + "learning_rate": 1.5601837685594927e-05, + "loss": 1.4666, + "step": 3620 + }, + { + "epoch": 0.38, + "learning_rate": 1.5598805275033574e-05, + "loss": 1.4106, + "step": 3621 + }, + { + "epoch": 0.38, + "learning_rate": 1.5595772114376174e-05, + "loss": 1.3857, + "step": 3622 + }, + { + "epoch": 0.38, + "learning_rate": 1.5592738204029086e-05, + "loss": 1.4704, + "step": 3623 + }, + { + "epoch": 0.38, + "learning_rate": 1.558970354439878e-05, + "loss": 1.4649, + "step": 3624 + }, + { + "epoch": 0.38, + "learning_rate": 1.5586668135891824e-05, + "loss": 1.4812, + "step": 3625 + }, + { + "epoch": 0.38, + "learning_rate": 1.5583631978914882e-05, + "loss": 1.3507, + "step": 3626 + }, + { + "epoch": 0.38, + "learning_rate": 1.5580595073874718e-05, + "loss": 1.3762, + "step": 3627 + }, + { + "epoch": 0.38, + "learning_rate": 1.557755742117821e-05, + "loss": 1.4169, + "step": 3628 + }, + { + "epoch": 0.38, + "learning_rate": 1.557451902123231e-05, + "loss": 1.4098, + "step": 3629 + }, + { + "epoch": 0.38, + "learning_rate": 1.55714798744441e-05, + "loss": 1.5526, + "step": 3630 + }, + { + "epoch": 0.38, + "learning_rate": 1.556843998122074e-05, + "loss": 1.4414, + "step": 3631 + }, + { + "epoch": 0.38, + "learning_rate": 1.5565399341969497e-05, + "loss": 1.4134, + "step": 3632 + }, + { + "epoch": 0.38, + "learning_rate": 1.556235795709774e-05, + "loss": 1.4718, + "step": 3633 + }, + { + "epoch": 0.38, + "learning_rate": 1.5559315827012937e-05, + "loss": 1.412, + "step": 3634 + }, + { + "epoch": 0.38, + "learning_rate": 1.5556272952122657e-05, + "loss": 1.4119, + "step": 3635 + }, + { + "epoch": 0.38, + "learning_rate": 1.5553229332834564e-05, + "loss": 1.3999, + "step": 3636 + }, + { + "epoch": 0.38, + "learning_rate": 1.5550184969556428e-05, + "loss": 1.4626, + "step": 3637 + }, + { + "epoch": 0.38, + "learning_rate": 1.5547139862696113e-05, + "loss": 1.3811, + "step": 3638 + }, + { + "epoch": 0.38, + "learning_rate": 1.5544094012661583e-05, + "loss": 1.4053, + "step": 3639 + }, + { + "epoch": 0.38, + "learning_rate": 1.5541047419860907e-05, + "loss": 1.4059, + "step": 3640 + }, + { + "epoch": 0.38, + "learning_rate": 1.553800008470225e-05, + "loss": 1.4717, + "step": 3641 + }, + { + "epoch": 0.38, + "learning_rate": 1.553495200759388e-05, + "loss": 1.399, + "step": 3642 + }, + { + "epoch": 0.38, + "learning_rate": 1.5531903188944154e-05, + "loss": 1.4143, + "step": 3643 + }, + { + "epoch": 0.38, + "learning_rate": 1.5528853629161536e-05, + "loss": 1.4414, + "step": 3644 + }, + { + "epoch": 0.38, + "learning_rate": 1.5525803328654592e-05, + "loss": 1.4206, + "step": 3645 + }, + { + "epoch": 0.38, + "learning_rate": 1.5522752287831982e-05, + "loss": 1.3869, + "step": 3646 + }, + { + "epoch": 0.38, + "learning_rate": 1.551970050710247e-05, + "loss": 1.5434, + "step": 3647 + }, + { + "epoch": 0.38, + "learning_rate": 1.5516647986874914e-05, + "loss": 1.4574, + "step": 3648 + }, + { + "epoch": 0.38, + "learning_rate": 1.5513594727558273e-05, + "loss": 1.4353, + "step": 3649 + }, + { + "epoch": 0.38, + "learning_rate": 1.5510540729561606e-05, + "loss": 1.4122, + "step": 3650 + }, + { + "epoch": 0.38, + "learning_rate": 1.550748599329407e-05, + "loss": 1.4077, + "step": 3651 + }, + { + "epoch": 0.38, + "learning_rate": 1.550443051916492e-05, + "loss": 1.4433, + "step": 3652 + }, + { + "epoch": 0.38, + "learning_rate": 1.5501374307583514e-05, + "loss": 1.54, + "step": 3653 + }, + { + "epoch": 0.38, + "learning_rate": 1.5498317358959302e-05, + "loss": 1.4522, + "step": 3654 + }, + { + "epoch": 0.38, + "learning_rate": 1.5495259673701842e-05, + "loss": 1.4175, + "step": 3655 + }, + { + "epoch": 0.38, + "learning_rate": 1.5492201252220777e-05, + "loss": 1.4637, + "step": 3656 + }, + { + "epoch": 0.38, + "learning_rate": 1.5489142094925863e-05, + "loss": 1.4701, + "step": 3657 + }, + { + "epoch": 0.38, + "learning_rate": 1.548608220222695e-05, + "loss": 1.4095, + "step": 3658 + }, + { + "epoch": 0.38, + "learning_rate": 1.548302157453398e-05, + "loss": 1.3903, + "step": 3659 + }, + { + "epoch": 0.38, + "learning_rate": 1.5479960212257002e-05, + "loss": 1.4062, + "step": 3660 + }, + { + "epoch": 0.38, + "learning_rate": 1.5476898115806157e-05, + "loss": 1.4706, + "step": 3661 + }, + { + "epoch": 0.38, + "learning_rate": 1.547383528559169e-05, + "loss": 1.4423, + "step": 3662 + }, + { + "epoch": 0.38, + "learning_rate": 1.547077172202394e-05, + "loss": 1.4418, + "step": 3663 + }, + { + "epoch": 0.38, + "learning_rate": 1.5467707425513347e-05, + "loss": 1.4553, + "step": 3664 + }, + { + "epoch": 0.38, + "learning_rate": 1.5464642396470443e-05, + "loss": 1.435, + "step": 3665 + }, + { + "epoch": 0.38, + "learning_rate": 1.5461576635305873e-05, + "loss": 1.4105, + "step": 3666 + }, + { + "epoch": 0.38, + "learning_rate": 1.5458510142430364e-05, + "loss": 1.4118, + "step": 3667 + }, + { + "epoch": 0.38, + "learning_rate": 1.5455442918254746e-05, + "loss": 1.4096, + "step": 3668 + }, + { + "epoch": 0.38, + "learning_rate": 1.545237496318995e-05, + "loss": 1.4248, + "step": 3669 + }, + { + "epoch": 0.38, + "learning_rate": 1.5449306277647003e-05, + "loss": 1.4591, + "step": 3670 + }, + { + "epoch": 0.38, + "learning_rate": 1.544623686203703e-05, + "loss": 1.4764, + "step": 3671 + }, + { + "epoch": 0.39, + "learning_rate": 1.5443166716771255e-05, + "loss": 1.4329, + "step": 3672 + }, + { + "epoch": 0.39, + "learning_rate": 1.5440095842260995e-05, + "loss": 1.4023, + "step": 3673 + }, + { + "epoch": 0.39, + "learning_rate": 1.5437024238917674e-05, + "loss": 1.3802, + "step": 3674 + }, + { + "epoch": 0.39, + "learning_rate": 1.5433951907152806e-05, + "loss": 1.4627, + "step": 3675 + }, + { + "epoch": 0.39, + "learning_rate": 1.5430878847378e-05, + "loss": 1.5164, + "step": 3676 + }, + { + "epoch": 0.39, + "learning_rate": 1.542780506000497e-05, + "loss": 1.3546, + "step": 3677 + }, + { + "epoch": 0.39, + "learning_rate": 1.542473054544553e-05, + "loss": 1.4415, + "step": 3678 + }, + { + "epoch": 0.39, + "learning_rate": 1.5421655304111573e-05, + "loss": 1.4093, + "step": 3679 + }, + { + "epoch": 0.39, + "learning_rate": 1.5418579336415114e-05, + "loss": 1.3943, + "step": 3680 + }, + { + "epoch": 0.39, + "learning_rate": 1.5415502642768252e-05, + "loss": 1.3659, + "step": 3681 + }, + { + "epoch": 0.39, + "learning_rate": 1.541242522358318e-05, + "loss": 1.4322, + "step": 3682 + }, + { + "epoch": 0.39, + "learning_rate": 1.5409347079272198e-05, + "loss": 1.4064, + "step": 3683 + }, + { + "epoch": 0.39, + "learning_rate": 1.5406268210247693e-05, + "loss": 1.4031, + "step": 3684 + }, + { + "epoch": 0.39, + "learning_rate": 1.540318861692216e-05, + "loss": 1.3449, + "step": 3685 + }, + { + "epoch": 0.39, + "learning_rate": 1.5400108299708182e-05, + "loss": 1.5536, + "step": 3686 + }, + { + "epoch": 0.39, + "learning_rate": 1.5397027259018442e-05, + "loss": 1.4106, + "step": 3687 + }, + { + "epoch": 0.39, + "learning_rate": 1.5393945495265722e-05, + "loss": 1.4309, + "step": 3688 + }, + { + "epoch": 0.39, + "learning_rate": 1.53908630088629e-05, + "loss": 1.3765, + "step": 3689 + }, + { + "epoch": 0.39, + "learning_rate": 1.5387779800222947e-05, + "loss": 1.3809, + "step": 3690 + }, + { + "epoch": 0.39, + "learning_rate": 1.5384695869758938e-05, + "loss": 1.4758, + "step": 3691 + }, + { + "epoch": 0.39, + "learning_rate": 1.5381611217884032e-05, + "loss": 1.4249, + "step": 3692 + }, + { + "epoch": 0.39, + "learning_rate": 1.5378525845011503e-05, + "loss": 1.4133, + "step": 3693 + }, + { + "epoch": 0.39, + "learning_rate": 1.5375439751554708e-05, + "loss": 1.418, + "step": 3694 + }, + { + "epoch": 0.39, + "learning_rate": 1.53723529379271e-05, + "loss": 1.441, + "step": 3695 + }, + { + "epoch": 0.39, + "learning_rate": 1.536926540454224e-05, + "loss": 1.3919, + "step": 3696 + }, + { + "epoch": 0.39, + "learning_rate": 1.5366177151813775e-05, + "loss": 1.3722, + "step": 3697 + }, + { + "epoch": 0.39, + "learning_rate": 1.536308818015545e-05, + "loss": 1.4727, + "step": 3698 + }, + { + "epoch": 0.39, + "learning_rate": 1.535999848998111e-05, + "loss": 1.442, + "step": 3699 + }, + { + "epoch": 0.39, + "learning_rate": 1.535690808170469e-05, + "loss": 1.3884, + "step": 3700 + }, + { + "epoch": 0.39, + "learning_rate": 1.535381695574023e-05, + "loss": 1.3226, + "step": 3701 + }, + { + "epoch": 0.39, + "learning_rate": 1.535072511250186e-05, + "loss": 1.4403, + "step": 3702 + }, + { + "epoch": 0.39, + "learning_rate": 1.5347632552403808e-05, + "loss": 1.4144, + "step": 3703 + }, + { + "epoch": 0.39, + "learning_rate": 1.5344539275860395e-05, + "loss": 1.3514, + "step": 3704 + }, + { + "epoch": 0.39, + "learning_rate": 1.5341445283286044e-05, + "loss": 1.519, + "step": 3705 + }, + { + "epoch": 0.39, + "learning_rate": 1.5338350575095268e-05, + "loss": 1.4251, + "step": 3706 + }, + { + "epoch": 0.39, + "learning_rate": 1.5335255151702685e-05, + "loss": 1.392, + "step": 3707 + }, + { + "epoch": 0.39, + "learning_rate": 1.533215901352299e-05, + "loss": 1.3838, + "step": 3708 + }, + { + "epoch": 0.39, + "learning_rate": 1.532906216097099e-05, + "loss": 1.444, + "step": 3709 + }, + { + "epoch": 0.39, + "learning_rate": 1.5325964594461594e-05, + "loss": 1.3459, + "step": 3710 + }, + { + "epoch": 0.39, + "learning_rate": 1.5322866314409783e-05, + "loss": 1.4155, + "step": 3711 + }, + { + "epoch": 0.39, + "learning_rate": 1.5319767321230657e-05, + "loss": 1.4057, + "step": 3712 + }, + { + "epoch": 0.39, + "learning_rate": 1.5316667615339392e-05, + "loss": 1.382, + "step": 3713 + }, + { + "epoch": 0.39, + "learning_rate": 1.5313567197151277e-05, + "loss": 1.3634, + "step": 3714 + }, + { + "epoch": 0.39, + "learning_rate": 1.5310466067081688e-05, + "loss": 1.3434, + "step": 3715 + }, + { + "epoch": 0.39, + "learning_rate": 1.530736422554609e-05, + "loss": 1.4553, + "step": 3716 + }, + { + "epoch": 0.39, + "learning_rate": 1.5304261672960055e-05, + "loss": 1.4193, + "step": 3717 + }, + { + "epoch": 0.39, + "learning_rate": 1.5301158409739242e-05, + "loss": 1.3955, + "step": 3718 + }, + { + "epoch": 0.39, + "learning_rate": 1.5298054436299413e-05, + "loss": 1.4592, + "step": 3719 + }, + { + "epoch": 0.39, + "learning_rate": 1.529494975305642e-05, + "loss": 1.738, + "step": 3720 + }, + { + "epoch": 0.39, + "learning_rate": 1.529184436042621e-05, + "loss": 1.438, + "step": 3721 + }, + { + "epoch": 0.39, + "learning_rate": 1.528873825882482e-05, + "loss": 1.3445, + "step": 3722 + }, + { + "epoch": 0.39, + "learning_rate": 1.5285631448668395e-05, + "loss": 1.4168, + "step": 3723 + }, + { + "epoch": 0.39, + "learning_rate": 1.528252393037317e-05, + "loss": 1.4088, + "step": 3724 + }, + { + "epoch": 0.39, + "learning_rate": 1.5279415704355468e-05, + "loss": 1.4484, + "step": 3725 + }, + { + "epoch": 0.39, + "learning_rate": 1.5276306771031708e-05, + "loss": 1.4706, + "step": 3726 + }, + { + "epoch": 0.39, + "learning_rate": 1.527319713081841e-05, + "loss": 1.3466, + "step": 3727 + }, + { + "epoch": 0.39, + "learning_rate": 1.5270086784132196e-05, + "loss": 1.427, + "step": 3728 + }, + { + "epoch": 0.39, + "learning_rate": 1.5266975731389754e-05, + "loss": 1.4596, + "step": 3729 + }, + { + "epoch": 0.39, + "learning_rate": 1.52638639730079e-05, + "loss": 1.405, + "step": 3730 + }, + { + "epoch": 0.39, + "learning_rate": 1.5260751509403518e-05, + "loss": 1.4572, + "step": 3731 + }, + { + "epoch": 0.39, + "learning_rate": 1.5257638340993608e-05, + "loss": 1.3827, + "step": 3732 + }, + { + "epoch": 0.39, + "learning_rate": 1.5254524468195251e-05, + "loss": 1.3712, + "step": 3733 + }, + { + "epoch": 0.39, + "learning_rate": 1.5251409891425626e-05, + "loss": 1.4541, + "step": 3734 + }, + { + "epoch": 0.39, + "learning_rate": 1.5248294611102006e-05, + "loss": 1.5279, + "step": 3735 + }, + { + "epoch": 0.39, + "learning_rate": 1.5245178627641759e-05, + "loss": 1.3722, + "step": 3736 + }, + { + "epoch": 0.39, + "learning_rate": 1.5242061941462348e-05, + "loss": 1.5158, + "step": 3737 + }, + { + "epoch": 0.39, + "learning_rate": 1.523894455298132e-05, + "loss": 1.4274, + "step": 3738 + }, + { + "epoch": 0.39, + "learning_rate": 1.5235826462616338e-05, + "loss": 1.4543, + "step": 3739 + }, + { + "epoch": 0.39, + "learning_rate": 1.5232707670785144e-05, + "loss": 1.5011, + "step": 3740 + }, + { + "epoch": 0.39, + "learning_rate": 1.5229588177905568e-05, + "loss": 1.24, + "step": 3741 + }, + { + "epoch": 0.39, + "learning_rate": 1.5226467984395544e-05, + "loss": 1.4253, + "step": 3742 + }, + { + "epoch": 0.39, + "learning_rate": 1.5223347090673102e-05, + "loss": 1.3736, + "step": 3743 + }, + { + "epoch": 0.39, + "learning_rate": 1.522022549715636e-05, + "loss": 1.4587, + "step": 3744 + }, + { + "epoch": 0.39, + "learning_rate": 1.521710320426353e-05, + "loss": 1.5024, + "step": 3745 + }, + { + "epoch": 0.39, + "learning_rate": 1.521398021241292e-05, + "loss": 1.427, + "step": 3746 + }, + { + "epoch": 0.39, + "learning_rate": 1.5210856522022929e-05, + "loss": 1.3387, + "step": 3747 + }, + { + "epoch": 0.39, + "learning_rate": 1.5207732133512055e-05, + "loss": 1.3819, + "step": 3748 + }, + { + "epoch": 0.39, + "learning_rate": 1.5204607047298883e-05, + "loss": 1.4571, + "step": 3749 + }, + { + "epoch": 0.39, + "learning_rate": 1.5201481263802094e-05, + "loss": 1.3592, + "step": 3750 + }, + { + "epoch": 0.39, + "learning_rate": 1.5198354783440464e-05, + "loss": 1.3912, + "step": 3751 + }, + { + "epoch": 0.39, + "learning_rate": 1.519522760663286e-05, + "loss": 1.4986, + "step": 3752 + }, + { + "epoch": 0.39, + "learning_rate": 1.5192099733798243e-05, + "loss": 1.4106, + "step": 3753 + }, + { + "epoch": 0.39, + "learning_rate": 1.5188971165355667e-05, + "loss": 1.4145, + "step": 3754 + }, + { + "epoch": 0.39, + "learning_rate": 1.5185841901724282e-05, + "loss": 1.3915, + "step": 3755 + }, + { + "epoch": 0.39, + "learning_rate": 1.5182711943323329e-05, + "loss": 1.4014, + "step": 3756 + }, + { + "epoch": 0.39, + "learning_rate": 1.5179581290572141e-05, + "loss": 1.3651, + "step": 3757 + }, + { + "epoch": 0.39, + "learning_rate": 1.5176449943890147e-05, + "loss": 1.3653, + "step": 3758 + }, + { + "epoch": 0.39, + "learning_rate": 1.5173317903696862e-05, + "loss": 1.4486, + "step": 3759 + }, + { + "epoch": 0.39, + "learning_rate": 1.5170185170411906e-05, + "loss": 1.4459, + "step": 3760 + }, + { + "epoch": 0.39, + "learning_rate": 1.5167051744454977e-05, + "loss": 1.4215, + "step": 3761 + }, + { + "epoch": 0.39, + "learning_rate": 1.5163917626245877e-05, + "loss": 1.4379, + "step": 3762 + }, + { + "epoch": 0.39, + "learning_rate": 1.51607828162045e-05, + "loss": 1.4147, + "step": 3763 + }, + { + "epoch": 0.39, + "learning_rate": 1.5157647314750827e-05, + "loss": 1.4011, + "step": 3764 + }, + { + "epoch": 0.39, + "learning_rate": 1.5154511122304936e-05, + "loss": 1.4309, + "step": 3765 + }, + { + "epoch": 0.39, + "learning_rate": 1.5151374239286993e-05, + "loss": 1.4382, + "step": 3766 + }, + { + "epoch": 0.4, + "learning_rate": 1.5148236666117266e-05, + "loss": 1.405, + "step": 3767 + }, + { + "epoch": 0.4, + "learning_rate": 1.5145098403216104e-05, + "loss": 1.4223, + "step": 3768 + }, + { + "epoch": 0.4, + "learning_rate": 1.5141959451003951e-05, + "loss": 1.4084, + "step": 3769 + }, + { + "epoch": 0.4, + "learning_rate": 1.5138819809901356e-05, + "loss": 1.4063, + "step": 3770 + }, + { + "epoch": 0.4, + "learning_rate": 1.513567948032894e-05, + "loss": 1.3299, + "step": 3771 + }, + { + "epoch": 0.4, + "learning_rate": 1.5132538462707431e-05, + "loss": 1.3901, + "step": 3772 + }, + { + "epoch": 0.4, + "learning_rate": 1.5129396757457646e-05, + "loss": 1.4249, + "step": 3773 + }, + { + "epoch": 0.4, + "learning_rate": 1.512625436500049e-05, + "loss": 1.4087, + "step": 3774 + }, + { + "epoch": 0.4, + "learning_rate": 1.5123111285756964e-05, + "loss": 1.3521, + "step": 3775 + }, + { + "epoch": 0.4, + "learning_rate": 1.5119967520148163e-05, + "loss": 1.4097, + "step": 3776 + }, + { + "epoch": 0.4, + "learning_rate": 1.5116823068595261e-05, + "loss": 1.4871, + "step": 3777 + }, + { + "epoch": 0.4, + "learning_rate": 1.5113677931519543e-05, + "loss": 1.44, + "step": 3778 + }, + { + "epoch": 0.4, + "learning_rate": 1.5110532109342377e-05, + "loss": 1.4518, + "step": 3779 + }, + { + "epoch": 0.4, + "learning_rate": 1.5107385602485214e-05, + "loss": 1.3961, + "step": 3780 + }, + { + "epoch": 0.4, + "learning_rate": 1.5104238411369614e-05, + "loss": 1.4341, + "step": 3781 + }, + { + "epoch": 0.4, + "eval_loss": 1.4642821550369263, + "eval_runtime": 77.3595, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 3781 + }, + { + "epoch": 0.4, + "learning_rate": 1.5101090536417218e-05, + "loss": 1.403, + "step": 3782 + }, + { + "epoch": 0.4, + "learning_rate": 1.5097941978049754e-05, + "loss": 1.4103, + "step": 3783 + }, + { + "epoch": 0.4, + "learning_rate": 1.5094792736689052e-05, + "loss": 1.3478, + "step": 3784 + }, + { + "epoch": 0.4, + "learning_rate": 1.5091642812757035e-05, + "loss": 1.4134, + "step": 3785 + }, + { + "epoch": 0.4, + "learning_rate": 1.5088492206675701e-05, + "loss": 1.4134, + "step": 3786 + }, + { + "epoch": 0.4, + "learning_rate": 1.5085340918867162e-05, + "loss": 1.1494, + "step": 3787 + }, + { + "epoch": 0.4, + "learning_rate": 1.5082188949753598e-05, + "loss": 1.2385, + "step": 3788 + }, + { + "epoch": 0.4, + "learning_rate": 1.5079036299757299e-05, + "loss": 1.4258, + "step": 3789 + }, + { + "epoch": 0.4, + "learning_rate": 1.5075882969300639e-05, + "loss": 1.3781, + "step": 3790 + }, + { + "epoch": 0.4, + "learning_rate": 1.507272895880608e-05, + "loss": 1.5096, + "step": 3791 + }, + { + "epoch": 0.4, + "learning_rate": 1.5069574268696179e-05, + "loss": 1.366, + "step": 3792 + }, + { + "epoch": 0.4, + "learning_rate": 1.5066418899393584e-05, + "loss": 1.3792, + "step": 3793 + }, + { + "epoch": 0.4, + "learning_rate": 1.506326285132104e-05, + "loss": 1.4987, + "step": 3794 + }, + { + "epoch": 0.4, + "learning_rate": 1.5060106124901364e-05, + "loss": 1.445, + "step": 3795 + }, + { + "epoch": 0.4, + "learning_rate": 1.5056948720557482e-05, + "loss": 1.5071, + "step": 3796 + }, + { + "epoch": 0.4, + "learning_rate": 1.505379063871241e-05, + "loss": 1.4029, + "step": 3797 + }, + { + "epoch": 0.4, + "learning_rate": 1.5050631879789244e-05, + "loss": 1.5263, + "step": 3798 + }, + { + "epoch": 0.4, + "learning_rate": 1.5047472444211175e-05, + "loss": 1.3906, + "step": 3799 + }, + { + "epoch": 0.4, + "learning_rate": 1.5044312332401494e-05, + "loss": 1.7352, + "step": 3800 + }, + { + "epoch": 0.4, + "learning_rate": 1.5041151544783565e-05, + "loss": 1.3946, + "step": 3801 + }, + { + "epoch": 0.4, + "learning_rate": 1.5037990081780862e-05, + "loss": 1.3592, + "step": 3802 + }, + { + "epoch": 0.4, + "learning_rate": 1.503482794381693e-05, + "loss": 1.3991, + "step": 3803 + }, + { + "epoch": 0.4, + "learning_rate": 1.5031665131315423e-05, + "loss": 1.4271, + "step": 3804 + }, + { + "epoch": 0.4, + "learning_rate": 1.502850164470007e-05, + "loss": 1.4305, + "step": 3805 + }, + { + "epoch": 0.4, + "learning_rate": 1.5025337484394701e-05, + "loss": 1.4116, + "step": 3806 + }, + { + "epoch": 0.4, + "learning_rate": 1.5022172650823232e-05, + "loss": 1.4242, + "step": 3807 + }, + { + "epoch": 0.4, + "learning_rate": 1.5019007144409667e-05, + "loss": 1.4427, + "step": 3808 + }, + { + "epoch": 0.4, + "learning_rate": 1.5015840965578106e-05, + "loss": 1.3705, + "step": 3809 + }, + { + "epoch": 0.4, + "learning_rate": 1.5012674114752732e-05, + "loss": 1.4498, + "step": 3810 + }, + { + "epoch": 0.4, + "learning_rate": 1.5009506592357822e-05, + "loss": 1.489, + "step": 3811 + }, + { + "epoch": 0.4, + "learning_rate": 1.5006338398817746e-05, + "loss": 1.4801, + "step": 3812 + }, + { + "epoch": 0.4, + "learning_rate": 1.5003169534556956e-05, + "loss": 1.3468, + "step": 3813 + }, + { + "epoch": 0.4, + "learning_rate": 1.5000000000000002e-05, + "loss": 1.4211, + "step": 3814 + }, + { + "epoch": 0.4, + "learning_rate": 1.4996829795571518e-05, + "loss": 1.4683, + "step": 3815 + }, + { + "epoch": 0.4, + "learning_rate": 1.499365892169623e-05, + "loss": 1.4441, + "step": 3816 + }, + { + "epoch": 0.4, + "learning_rate": 1.4990487378798958e-05, + "loss": 1.4368, + "step": 3817 + }, + { + "epoch": 0.4, + "learning_rate": 1.4987315167304602e-05, + "loss": 1.4097, + "step": 3818 + }, + { + "epoch": 0.4, + "learning_rate": 1.4984142287638155e-05, + "loss": 1.4238, + "step": 3819 + }, + { + "epoch": 0.4, + "learning_rate": 1.4980968740224708e-05, + "loss": 1.497, + "step": 3820 + }, + { + "epoch": 0.4, + "learning_rate": 1.4977794525489433e-05, + "loss": 1.3989, + "step": 3821 + }, + { + "epoch": 0.4, + "learning_rate": 1.4974619643857588e-05, + "loss": 1.4415, + "step": 3822 + }, + { + "epoch": 0.4, + "learning_rate": 1.4971444095754533e-05, + "loss": 1.3931, + "step": 3823 + }, + { + "epoch": 0.4, + "learning_rate": 1.4968267881605705e-05, + "loss": 1.3426, + "step": 3824 + }, + { + "epoch": 0.4, + "learning_rate": 1.4965091001836636e-05, + "loss": 1.644, + "step": 3825 + }, + { + "epoch": 0.4, + "learning_rate": 1.4961913456872945e-05, + "loss": 1.3903, + "step": 3826 + }, + { + "epoch": 0.4, + "learning_rate": 1.4958735247140345e-05, + "loss": 1.3764, + "step": 3827 + }, + { + "epoch": 0.4, + "learning_rate": 1.4955556373064632e-05, + "loss": 1.5484, + "step": 3828 + }, + { + "epoch": 0.4, + "learning_rate": 1.4952376835071696e-05, + "loss": 1.5696, + "step": 3829 + }, + { + "epoch": 0.4, + "learning_rate": 1.4949196633587509e-05, + "loss": 1.3844, + "step": 3830 + }, + { + "epoch": 0.4, + "learning_rate": 1.494601576903814e-05, + "loss": 1.3868, + "step": 3831 + }, + { + "epoch": 0.4, + "learning_rate": 1.4942834241849741e-05, + "loss": 1.4229, + "step": 3832 + }, + { + "epoch": 0.4, + "learning_rate": 1.4939652052448557e-05, + "loss": 1.4062, + "step": 3833 + }, + { + "epoch": 0.4, + "learning_rate": 1.4936469201260915e-05, + "loss": 1.3955, + "step": 3834 + }, + { + "epoch": 0.4, + "learning_rate": 1.4933285688713239e-05, + "loss": 1.3959, + "step": 3835 + }, + { + "epoch": 0.4, + "learning_rate": 1.4930101515232038e-05, + "loss": 1.4652, + "step": 3836 + }, + { + "epoch": 0.4, + "learning_rate": 1.4926916681243913e-05, + "loss": 1.5253, + "step": 3837 + }, + { + "epoch": 0.4, + "learning_rate": 1.4923731187175539e-05, + "loss": 1.4694, + "step": 3838 + }, + { + "epoch": 0.4, + "learning_rate": 1.4920545033453702e-05, + "loss": 1.3859, + "step": 3839 + }, + { + "epoch": 0.4, + "learning_rate": 1.4917358220505259e-05, + "loss": 1.4157, + "step": 3840 + }, + { + "epoch": 0.4, + "learning_rate": 1.4914170748757159e-05, + "loss": 1.4491, + "step": 3841 + }, + { + "epoch": 0.4, + "learning_rate": 1.4910982618636445e-05, + "loss": 1.4464, + "step": 3842 + }, + { + "epoch": 0.4, + "learning_rate": 1.4907793830570246e-05, + "loss": 1.3771, + "step": 3843 + }, + { + "epoch": 0.4, + "learning_rate": 1.4904604384985775e-05, + "loss": 1.3673, + "step": 3844 + }, + { + "epoch": 0.4, + "learning_rate": 1.4901414282310334e-05, + "loss": 1.4429, + "step": 3845 + }, + { + "epoch": 0.4, + "learning_rate": 1.4898223522971318e-05, + "loss": 1.4905, + "step": 3846 + }, + { + "epoch": 0.4, + "learning_rate": 1.4895032107396205e-05, + "loss": 1.4039, + "step": 3847 + }, + { + "epoch": 0.4, + "learning_rate": 1.4891840036012566e-05, + "loss": 1.4082, + "step": 3848 + }, + { + "epoch": 0.4, + "learning_rate": 1.4888647309248052e-05, + "loss": 1.3643, + "step": 3849 + }, + { + "epoch": 0.4, + "learning_rate": 1.4885453927530408e-05, + "loss": 1.3116, + "step": 3850 + }, + { + "epoch": 0.4, + "learning_rate": 1.4882259891287467e-05, + "loss": 1.4278, + "step": 3851 + }, + { + "epoch": 0.4, + "learning_rate": 1.4879065200947148e-05, + "loss": 1.3712, + "step": 3852 + }, + { + "epoch": 0.4, + "learning_rate": 1.4875869856937449e-05, + "loss": 1.387, + "step": 3853 + }, + { + "epoch": 0.4, + "learning_rate": 1.4872673859686475e-05, + "loss": 1.5053, + "step": 3854 + }, + { + "epoch": 0.4, + "learning_rate": 1.4869477209622404e-05, + "loss": 1.4427, + "step": 3855 + }, + { + "epoch": 0.4, + "learning_rate": 1.4866279907173502e-05, + "loss": 1.3404, + "step": 3856 + }, + { + "epoch": 0.4, + "learning_rate": 1.4863081952768126e-05, + "loss": 1.3126, + "step": 3857 + }, + { + "epoch": 0.4, + "learning_rate": 1.4859883346834725e-05, + "loss": 1.4588, + "step": 3858 + }, + { + "epoch": 0.4, + "learning_rate": 1.4856684089801822e-05, + "loss": 1.408, + "step": 3859 + }, + { + "epoch": 0.4, + "learning_rate": 1.4853484182098044e-05, + "loss": 1.4356, + "step": 3860 + }, + { + "epoch": 0.4, + "learning_rate": 1.4850283624152088e-05, + "loss": 1.3768, + "step": 3861 + }, + { + "epoch": 0.4, + "learning_rate": 1.4847082416392753e-05, + "loss": 1.4563, + "step": 3862 + }, + { + "epoch": 0.41, + "learning_rate": 1.4843880559248915e-05, + "loss": 1.3648, + "step": 3863 + }, + { + "epoch": 0.41, + "learning_rate": 1.4840678053149542e-05, + "loss": 1.4146, + "step": 3864 + }, + { + "epoch": 0.41, + "learning_rate": 1.4837474898523686e-05, + "loss": 1.4423, + "step": 3865 + }, + { + "epoch": 0.41, + "learning_rate": 1.4834271095800487e-05, + "loss": 1.3351, + "step": 3866 + }, + { + "epoch": 0.41, + "learning_rate": 1.4831066645409178e-05, + "loss": 1.4534, + "step": 3867 + }, + { + "epoch": 0.41, + "learning_rate": 1.4827861547779066e-05, + "loss": 1.4763, + "step": 3868 + }, + { + "epoch": 0.41, + "learning_rate": 1.4824655803339553e-05, + "loss": 1.4019, + "step": 3869 + }, + { + "epoch": 0.41, + "learning_rate": 1.4821449412520132e-05, + "loss": 1.4223, + "step": 3870 + }, + { + "epoch": 0.41, + "learning_rate": 1.4818242375750371e-05, + "loss": 1.4065, + "step": 3871 + }, + { + "epoch": 0.41, + "learning_rate": 1.481503469345993e-05, + "loss": 1.587, + "step": 3872 + }, + { + "epoch": 0.41, + "learning_rate": 1.4811826366078562e-05, + "loss": 1.3746, + "step": 3873 + }, + { + "epoch": 0.41, + "learning_rate": 1.4808617394036096e-05, + "loss": 1.3425, + "step": 3874 + }, + { + "epoch": 0.41, + "learning_rate": 1.480540777776245e-05, + "loss": 0.6637, + "step": 3875 + }, + { + "epoch": 0.41, + "learning_rate": 1.4802197517687634e-05, + "loss": 1.3366, + "step": 3876 + }, + { + "epoch": 0.41, + "learning_rate": 1.479898661424174e-05, + "loss": 1.4033, + "step": 3877 + }, + { + "epoch": 0.41, + "learning_rate": 1.4795775067854947e-05, + "loss": 1.4005, + "step": 3878 + }, + { + "epoch": 0.41, + "learning_rate": 1.4792562878957516e-05, + "loss": 1.3651, + "step": 3879 + }, + { + "epoch": 0.41, + "learning_rate": 1.47893500479798e-05, + "loss": 1.4185, + "step": 3880 + }, + { + "epoch": 0.41, + "learning_rate": 1.4786136575352236e-05, + "loss": 1.4394, + "step": 3881 + }, + { + "epoch": 0.41, + "learning_rate": 1.478292246150535e-05, + "loss": 1.7243, + "step": 3882 + }, + { + "epoch": 0.41, + "learning_rate": 1.4779707706869744e-05, + "loss": 1.3574, + "step": 3883 + }, + { + "epoch": 0.41, + "learning_rate": 1.4776492311876116e-05, + "loss": 1.4031, + "step": 3884 + }, + { + "epoch": 0.41, + "learning_rate": 1.4773276276955248e-05, + "loss": 1.4351, + "step": 3885 + }, + { + "epoch": 0.41, + "learning_rate": 1.4770059602538002e-05, + "loss": 1.3922, + "step": 3886 + }, + { + "epoch": 0.41, + "learning_rate": 1.4766842289055333e-05, + "loss": 1.3374, + "step": 3887 + }, + { + "epoch": 0.41, + "learning_rate": 1.4763624336938278e-05, + "loss": 1.428, + "step": 3888 + }, + { + "epoch": 0.41, + "learning_rate": 1.476040574661796e-05, + "loss": 1.6087, + "step": 3889 + }, + { + "epoch": 0.41, + "learning_rate": 1.4757186518525586e-05, + "loss": 1.4054, + "step": 3890 + }, + { + "epoch": 0.41, + "learning_rate": 1.4753966653092447e-05, + "loss": 1.2595, + "step": 3891 + }, + { + "epoch": 0.41, + "learning_rate": 1.475074615074993e-05, + "loss": 1.4052, + "step": 3892 + }, + { + "epoch": 0.41, + "learning_rate": 1.4747525011929492e-05, + "loss": 1.4296, + "step": 3893 + }, + { + "epoch": 0.41, + "learning_rate": 1.4744303237062689e-05, + "loss": 1.3718, + "step": 3894 + }, + { + "epoch": 0.41, + "learning_rate": 1.4741080826581151e-05, + "loss": 1.4498, + "step": 3895 + }, + { + "epoch": 0.41, + "learning_rate": 1.4737857780916602e-05, + "loss": 1.4029, + "step": 3896 + }, + { + "epoch": 0.41, + "learning_rate": 1.4734634100500846e-05, + "loss": 1.4136, + "step": 3897 + }, + { + "epoch": 0.41, + "learning_rate": 1.4731409785765774e-05, + "loss": 1.348, + "step": 3898 + }, + { + "epoch": 0.41, + "learning_rate": 1.4728184837143355e-05, + "loss": 1.3407, + "step": 3899 + }, + { + "epoch": 0.41, + "learning_rate": 1.472495925506566e-05, + "loss": 1.3737, + "step": 3900 + }, + { + "epoch": 0.41, + "learning_rate": 1.4721733039964826e-05, + "loss": 2.2305, + "step": 3901 + }, + { + "epoch": 0.41, + "learning_rate": 1.4718506192273087e-05, + "loss": 1.4506, + "step": 3902 + }, + { + "epoch": 0.41, + "learning_rate": 1.4715278712422754e-05, + "loss": 1.3657, + "step": 3903 + }, + { + "epoch": 0.41, + "learning_rate": 1.471205060084623e-05, + "loss": 1.4644, + "step": 3904 + }, + { + "epoch": 0.41, + "learning_rate": 1.4708821857976001e-05, + "loss": 1.4823, + "step": 3905 + }, + { + "epoch": 0.41, + "learning_rate": 1.4705592484244628e-05, + "loss": 1.3392, + "step": 3906 + }, + { + "epoch": 0.41, + "learning_rate": 1.4702362480084769e-05, + "loss": 1.3302, + "step": 3907 + }, + { + "epoch": 0.41, + "learning_rate": 1.4699131845929163e-05, + "loss": 1.8952, + "step": 3908 + }, + { + "epoch": 0.41, + "learning_rate": 1.469590058221063e-05, + "loss": 1.4982, + "step": 3909 + }, + { + "epoch": 0.41, + "learning_rate": 1.4692668689362074e-05, + "loss": 1.407, + "step": 3910 + }, + { + "epoch": 0.41, + "learning_rate": 1.4689436167816489e-05, + "loss": 1.3911, + "step": 3911 + }, + { + "epoch": 0.41, + "learning_rate": 1.4686203018006948e-05, + "loss": 1.3421, + "step": 3912 + }, + { + "epoch": 0.41, + "learning_rate": 1.4682969240366612e-05, + "loss": 1.4627, + "step": 3913 + }, + { + "epoch": 0.41, + "learning_rate": 1.4679734835328718e-05, + "loss": 1.394, + "step": 3914 + }, + { + "epoch": 0.41, + "learning_rate": 1.4676499803326603e-05, + "loss": 1.4484, + "step": 3915 + }, + { + "epoch": 0.41, + "learning_rate": 1.4673264144793673e-05, + "loss": 1.4665, + "step": 3916 + }, + { + "epoch": 0.41, + "learning_rate": 1.4670027860163422e-05, + "loss": 1.3191, + "step": 3917 + }, + { + "epoch": 0.41, + "learning_rate": 1.466679094986943e-05, + "loss": 1.4748, + "step": 3918 + }, + { + "epoch": 0.41, + "learning_rate": 1.4663553414345361e-05, + "loss": 1.2467, + "step": 3919 + }, + { + "epoch": 0.41, + "learning_rate": 1.466031525402496e-05, + "loss": 1.4279, + "step": 3920 + }, + { + "epoch": 0.41, + "learning_rate": 1.4657076469342059e-05, + "loss": 1.3822, + "step": 3921 + }, + { + "epoch": 0.41, + "learning_rate": 1.4653837060730566e-05, + "loss": 1.3659, + "step": 3922 + }, + { + "epoch": 0.41, + "learning_rate": 1.465059702862449e-05, + "loss": 1.3663, + "step": 3923 + }, + { + "epoch": 0.41, + "learning_rate": 1.4647356373457902e-05, + "loss": 1.4371, + "step": 3924 + }, + { + "epoch": 0.41, + "learning_rate": 1.4644115095664972e-05, + "loss": 1.3473, + "step": 3925 + }, + { + "epoch": 0.41, + "learning_rate": 1.4640873195679944e-05, + "loss": 1.4797, + "step": 3926 + }, + { + "epoch": 0.41, + "learning_rate": 1.463763067393715e-05, + "loss": 1.3973, + "step": 3927 + }, + { + "epoch": 0.41, + "learning_rate": 1.4634387530871008e-05, + "loss": 1.3899, + "step": 3928 + }, + { + "epoch": 0.41, + "learning_rate": 1.4631143766916015e-05, + "loss": 1.3828, + "step": 3929 + }, + { + "epoch": 0.41, + "learning_rate": 1.4627899382506745e-05, + "loss": 1.4569, + "step": 3930 + }, + { + "epoch": 0.41, + "learning_rate": 1.4624654378077872e-05, + "loss": 1.4011, + "step": 3931 + }, + { + "epoch": 0.41, + "learning_rate": 1.462140875406414e-05, + "loss": 1.3859, + "step": 3932 + }, + { + "epoch": 0.41, + "learning_rate": 1.4618162510900376e-05, + "loss": 1.4518, + "step": 3933 + }, + { + "epoch": 0.41, + "learning_rate": 1.4614915649021493e-05, + "loss": 1.4399, + "step": 3934 + }, + { + "epoch": 0.41, + "learning_rate": 1.4611668168862495e-05, + "loss": 1.4034, + "step": 3935 + }, + { + "epoch": 0.41, + "learning_rate": 1.4608420070858452e-05, + "loss": 1.3919, + "step": 3936 + }, + { + "epoch": 0.41, + "learning_rate": 1.4605171355444528e-05, + "loss": 1.391, + "step": 3937 + }, + { + "epoch": 0.41, + "learning_rate": 1.460192202305597e-05, + "loss": 1.3717, + "step": 3938 + }, + { + "epoch": 0.41, + "learning_rate": 1.4598672074128103e-05, + "loss": 1.4351, + "step": 3939 + }, + { + "epoch": 0.41, + "learning_rate": 1.4595421509096339e-05, + "loss": 1.4202, + "step": 3940 + }, + { + "epoch": 0.41, + "learning_rate": 1.4592170328396165e-05, + "loss": 1.3559, + "step": 3941 + }, + { + "epoch": 0.41, + "learning_rate": 1.458891853246316e-05, + "loss": 1.5878, + "step": 3942 + }, + { + "epoch": 0.41, + "learning_rate": 1.4585666121732982e-05, + "loss": 1.3818, + "step": 3943 + }, + { + "epoch": 0.41, + "learning_rate": 1.4582413096641369e-05, + "loss": 1.4009, + "step": 3944 + }, + { + "epoch": 0.41, + "learning_rate": 1.457915945762414e-05, + "loss": 1.3937, + "step": 3945 + }, + { + "epoch": 0.41, + "learning_rate": 1.4575905205117203e-05, + "loss": 1.381, + "step": 3946 + }, + { + "epoch": 0.41, + "learning_rate": 1.457265033955654e-05, + "loss": 1.3844, + "step": 3947 + }, + { + "epoch": 0.41, + "learning_rate": 1.4569394861378226e-05, + "loss": 1.4059, + "step": 3948 + }, + { + "epoch": 0.41, + "learning_rate": 1.4566138771018403e-05, + "loss": 1.3698, + "step": 3949 + }, + { + "epoch": 0.41, + "learning_rate": 1.4562882068913311e-05, + "loss": 1.4253, + "step": 3950 + }, + { + "epoch": 0.41, + "learning_rate": 1.455962475549926e-05, + "loss": 1.4284, + "step": 3951 + }, + { + "epoch": 0.41, + "learning_rate": 1.4556366831212647e-05, + "loss": 1.4279, + "step": 3952 + }, + { + "epoch": 0.41, + "learning_rate": 1.4553108296489951e-05, + "loss": 1.3072, + "step": 3953 + }, + { + "epoch": 0.41, + "learning_rate": 1.4549849151767731e-05, + "loss": 1.4175, + "step": 3954 + }, + { + "epoch": 0.41, + "learning_rate": 1.4546589397482632e-05, + "loss": 1.5042, + "step": 3955 + }, + { + "epoch": 0.41, + "learning_rate": 1.4543329034071371e-05, + "loss": 1.4363, + "step": 3956 + }, + { + "epoch": 0.41, + "learning_rate": 1.454006806197076e-05, + "loss": 1.4111, + "step": 3957 + }, + { + "epoch": 0.42, + "learning_rate": 1.453680648161768e-05, + "loss": 1.3817, + "step": 3958 + }, + { + "epoch": 0.42, + "learning_rate": 1.45335442934491e-05, + "loss": 1.4689, + "step": 3959 + }, + { + "epoch": 0.42, + "learning_rate": 1.4530281497902072e-05, + "loss": 1.4164, + "step": 3960 + }, + { + "epoch": 0.42, + "learning_rate": 1.4527018095413726e-05, + "loss": 1.3943, + "step": 3961 + }, + { + "epoch": 0.42, + "learning_rate": 1.4523754086421271e-05, + "loss": 1.3851, + "step": 3962 + }, + { + "epoch": 0.42, + "learning_rate": 1.4520489471362003e-05, + "loss": 1.3907, + "step": 3963 + }, + { + "epoch": 0.42, + "learning_rate": 1.4517224250673297e-05, + "loss": 1.2877, + "step": 3964 + }, + { + "epoch": 0.42, + "learning_rate": 1.4513958424792605e-05, + "loss": 1.4696, + "step": 3965 + }, + { + "epoch": 0.42, + "learning_rate": 1.4510691994157471e-05, + "loss": 1.3785, + "step": 3966 + }, + { + "epoch": 0.42, + "learning_rate": 1.4507424959205505e-05, + "loss": 1.3652, + "step": 3967 + }, + { + "epoch": 0.42, + "learning_rate": 1.4504157320374408e-05, + "loss": 1.4198, + "step": 3968 + }, + { + "epoch": 0.42, + "learning_rate": 1.4500889078101962e-05, + "loss": 1.3476, + "step": 3969 + }, + { + "epoch": 0.42, + "learning_rate": 1.4497620232826028e-05, + "loss": 1.4356, + "step": 3970 + }, + { + "epoch": 0.42, + "learning_rate": 1.4494350784984543e-05, + "loss": 1.4993, + "step": 3971 + }, + { + "epoch": 0.42, + "learning_rate": 1.4491080735015533e-05, + "loss": 1.4022, + "step": 3972 + }, + { + "epoch": 0.42, + "learning_rate": 1.44878100833571e-05, + "loss": 1.4074, + "step": 3973 + }, + { + "epoch": 0.42, + "learning_rate": 1.4484538830447423e-05, + "loss": 1.412, + "step": 3974 + }, + { + "epoch": 0.42, + "learning_rate": 1.4481266976724772e-05, + "loss": 1.3872, + "step": 3975 + }, + { + "epoch": 0.42, + "learning_rate": 1.4477994522627485e-05, + "loss": 1.4575, + "step": 3976 + }, + { + "epoch": 0.42, + "learning_rate": 1.4474721468593995e-05, + "loss": 1.3768, + "step": 3977 + }, + { + "epoch": 0.42, + "learning_rate": 1.44714478150628e-05, + "loss": 1.4173, + "step": 3978 + }, + { + "epoch": 0.42, + "learning_rate": 1.4468173562472489e-05, + "loss": 1.3896, + "step": 3979 + }, + { + "epoch": 0.42, + "learning_rate": 1.4464898711261725e-05, + "loss": 1.4535, + "step": 3980 + }, + { + "epoch": 0.42, + "eval_loss": 1.4580057859420776, + "eval_runtime": 77.4537, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 3980 + }, + { + "epoch": 0.42, + "learning_rate": 1.4461623261869258e-05, + "loss": 1.4046, + "step": 3981 + }, + { + "epoch": 0.42, + "learning_rate": 1.445834721473391e-05, + "loss": 1.37, + "step": 3982 + }, + { + "epoch": 0.42, + "learning_rate": 1.4455070570294588e-05, + "loss": 1.4566, + "step": 3983 + }, + { + "epoch": 0.42, + "learning_rate": 1.445179332899028e-05, + "loss": 1.4513, + "step": 3984 + }, + { + "epoch": 0.42, + "learning_rate": 1.4448515491260051e-05, + "loss": 1.3893, + "step": 3985 + }, + { + "epoch": 0.42, + "learning_rate": 1.4445237057543047e-05, + "loss": 1.3955, + "step": 3986 + }, + { + "epoch": 0.42, + "learning_rate": 1.4441958028278493e-05, + "loss": 1.4861, + "step": 3987 + }, + { + "epoch": 0.42, + "learning_rate": 1.4438678403905697e-05, + "loss": 1.4601, + "step": 3988 + }, + { + "epoch": 0.42, + "learning_rate": 1.4435398184864043e-05, + "loss": 1.398, + "step": 3989 + }, + { + "epoch": 0.42, + "learning_rate": 1.4432117371592995e-05, + "loss": 1.4392, + "step": 3990 + }, + { + "epoch": 0.42, + "learning_rate": 1.4428835964532098e-05, + "loss": 1.3772, + "step": 3991 + }, + { + "epoch": 0.42, + "learning_rate": 1.4425553964120979e-05, + "loss": 1.4241, + "step": 3992 + }, + { + "epoch": 0.42, + "learning_rate": 1.4422271370799338e-05, + "loss": 1.3237, + "step": 3993 + }, + { + "epoch": 0.42, + "learning_rate": 1.4418988185006964e-05, + "loss": 1.3813, + "step": 3994 + }, + { + "epoch": 0.42, + "learning_rate": 1.4415704407183709e-05, + "loss": 1.6139, + "step": 3995 + }, + { + "epoch": 0.42, + "learning_rate": 1.4412420037769525e-05, + "loss": 1.4431, + "step": 3996 + }, + { + "epoch": 0.42, + "learning_rate": 1.440913507720443e-05, + "loss": 1.3862, + "step": 3997 + }, + { + "epoch": 0.42, + "learning_rate": 1.4405849525928523e-05, + "loss": 1.3895, + "step": 3998 + }, + { + "epoch": 0.42, + "learning_rate": 1.4402563384381981e-05, + "loss": 1.4068, + "step": 3999 + }, + { + "epoch": 0.42, + "learning_rate": 1.4399276653005072e-05, + "loss": 1.4501, + "step": 4000 + }, + { + "epoch": 0.42, + "learning_rate": 1.4395989332238124e-05, + "loss": 1.3165, + "step": 4001 + }, + { + "epoch": 0.42, + "learning_rate": 1.4392701422521555e-05, + "loss": 1.3783, + "step": 4002 + }, + { + "epoch": 0.42, + "learning_rate": 1.4389412924295865e-05, + "loss": 1.343, + "step": 4003 + }, + { + "epoch": 0.42, + "learning_rate": 1.4386123838001625e-05, + "loss": 1.3456, + "step": 4004 + }, + { + "epoch": 0.42, + "learning_rate": 1.4382834164079486e-05, + "loss": 1.3689, + "step": 4005 + }, + { + "epoch": 0.42, + "learning_rate": 1.4379543902970183e-05, + "loss": 1.3789, + "step": 4006 + }, + { + "epoch": 0.42, + "learning_rate": 1.4376253055114528e-05, + "loss": 1.4912, + "step": 4007 + }, + { + "epoch": 0.42, + "learning_rate": 1.4372961620953407e-05, + "loss": 1.3692, + "step": 4008 + }, + { + "epoch": 0.42, + "learning_rate": 1.436966960092779e-05, + "loss": 1.4901, + "step": 4009 + }, + { + "epoch": 0.42, + "learning_rate": 1.4366376995478717e-05, + "loss": 1.4431, + "step": 4010 + }, + { + "epoch": 0.42, + "learning_rate": 1.436308380504732e-05, + "loss": 1.4626, + "step": 4011 + }, + { + "epoch": 0.42, + "learning_rate": 1.4359790030074798e-05, + "loss": 1.4241, + "step": 4012 + }, + { + "epoch": 0.42, + "learning_rate": 1.4356495671002435e-05, + "loss": 1.3834, + "step": 4013 + }, + { + "epoch": 0.42, + "learning_rate": 1.4353200728271586e-05, + "loss": 1.3626, + "step": 4014 + }, + { + "epoch": 0.42, + "learning_rate": 1.4349905202323692e-05, + "loss": 1.3557, + "step": 4015 + }, + { + "epoch": 0.42, + "learning_rate": 1.434660909360027e-05, + "loss": 1.4077, + "step": 4016 + }, + { + "epoch": 0.42, + "learning_rate": 1.4343312402542911e-05, + "loss": 1.4337, + "step": 4017 + }, + { + "epoch": 0.42, + "learning_rate": 1.4340015129593286e-05, + "loss": 1.419, + "step": 4018 + }, + { + "epoch": 0.42, + "learning_rate": 1.4336717275193148e-05, + "loss": 1.3768, + "step": 4019 + }, + { + "epoch": 0.42, + "learning_rate": 1.4333418839784326e-05, + "loss": 1.383, + "step": 4020 + }, + { + "epoch": 0.42, + "learning_rate": 1.4330119823808719e-05, + "loss": 1.3951, + "step": 4021 + }, + { + "epoch": 0.42, + "learning_rate": 1.4326820227708316e-05, + "loss": 1.3985, + "step": 4022 + }, + { + "epoch": 0.42, + "learning_rate": 1.4323520051925177e-05, + "loss": 1.356, + "step": 4023 + }, + { + "epoch": 0.42, + "learning_rate": 1.4320219296901439e-05, + "loss": 1.5017, + "step": 4024 + }, + { + "epoch": 0.42, + "learning_rate": 1.4316917963079322e-05, + "loss": 1.3594, + "step": 4025 + }, + { + "epoch": 0.42, + "learning_rate": 1.4313616050901114e-05, + "loss": 1.6028, + "step": 4026 + }, + { + "epoch": 0.42, + "learning_rate": 1.4310313560809193e-05, + "loss": 1.4132, + "step": 4027 + }, + { + "epoch": 0.42, + "learning_rate": 1.4307010493246006e-05, + "loss": 1.2969, + "step": 4028 + }, + { + "epoch": 0.42, + "learning_rate": 1.4303706848654073e-05, + "loss": 1.5224, + "step": 4029 + }, + { + "epoch": 0.42, + "learning_rate": 1.4300402627476007e-05, + "loss": 1.3386, + "step": 4030 + }, + { + "epoch": 0.42, + "learning_rate": 1.429709783015448e-05, + "loss": 1.3554, + "step": 4031 + }, + { + "epoch": 0.42, + "learning_rate": 1.4293792457132259e-05, + "loss": 1.3386, + "step": 4032 + }, + { + "epoch": 0.42, + "learning_rate": 1.429048650885217e-05, + "loss": 1.4613, + "step": 4033 + }, + { + "epoch": 0.42, + "learning_rate": 1.4287179985757132e-05, + "loss": 1.3632, + "step": 4034 + }, + { + "epoch": 0.42, + "learning_rate": 1.428387288829013e-05, + "loss": 1.3835, + "step": 4035 + }, + { + "epoch": 0.42, + "learning_rate": 1.4280565216894234e-05, + "loss": 1.3711, + "step": 4036 + }, + { + "epoch": 0.42, + "learning_rate": 1.4277256972012582e-05, + "loss": 1.3385, + "step": 4037 + }, + { + "epoch": 0.42, + "learning_rate": 1.4273948154088395e-05, + "loss": 1.4607, + "step": 4038 + }, + { + "epoch": 0.42, + "learning_rate": 1.4270638763564973e-05, + "loss": 1.4042, + "step": 4039 + }, + { + "epoch": 0.42, + "learning_rate": 1.4267328800885687e-05, + "loss": 1.4006, + "step": 4040 + }, + { + "epoch": 0.42, + "learning_rate": 1.4264018266493987e-05, + "loss": 1.386, + "step": 4041 + }, + { + "epoch": 0.42, + "learning_rate": 1.4260707160833401e-05, + "loss": 1.3487, + "step": 4042 + }, + { + "epoch": 0.42, + "learning_rate": 1.4257395484347529e-05, + "loss": 1.4199, + "step": 4043 + }, + { + "epoch": 0.42, + "learning_rate": 1.4254083237480054e-05, + "loss": 1.3236, + "step": 4044 + }, + { + "epoch": 0.42, + "learning_rate": 1.4250770420674726e-05, + "loss": 1.4056, + "step": 4045 + }, + { + "epoch": 0.42, + "learning_rate": 1.4247457034375387e-05, + "loss": 1.4391, + "step": 4046 + }, + { + "epoch": 0.42, + "learning_rate": 1.4244143079025938e-05, + "loss": 1.3935, + "step": 4047 + }, + { + "epoch": 0.42, + "learning_rate": 1.4240828555070368e-05, + "loss": 1.3623, + "step": 4048 + }, + { + "epoch": 0.42, + "learning_rate": 1.4237513462952733e-05, + "loss": 1.3254, + "step": 4049 + }, + { + "epoch": 0.42, + "learning_rate": 1.4234197803117174e-05, + "loss": 1.4217, + "step": 4050 + }, + { + "epoch": 0.42, + "learning_rate": 1.4230881576007904e-05, + "loss": 1.435, + "step": 4051 + }, + { + "epoch": 0.42, + "learning_rate": 1.422756478206921e-05, + "loss": 1.3687, + "step": 4052 + }, + { + "epoch": 0.43, + "learning_rate": 1.4224247421745464e-05, + "loss": 1.3965, + "step": 4053 + }, + { + "epoch": 0.43, + "learning_rate": 1.4220929495481097e-05, + "loss": 1.4159, + "step": 4054 + }, + { + "epoch": 0.43, + "learning_rate": 1.4217611003720632e-05, + "loss": 1.3632, + "step": 4055 + }, + { + "epoch": 0.43, + "learning_rate": 1.4214291946908661e-05, + "loss": 1.403, + "step": 4056 + }, + { + "epoch": 0.43, + "learning_rate": 1.4210972325489854e-05, + "loss": 1.4093, + "step": 4057 + }, + { + "epoch": 0.43, + "learning_rate": 1.4207652139908952e-05, + "loss": 1.4551, + "step": 4058 + }, + { + "epoch": 0.43, + "learning_rate": 1.4204331390610775e-05, + "loss": 1.4162, + "step": 4059 + }, + { + "epoch": 0.43, + "learning_rate": 1.4201010078040216e-05, + "loss": 1.4492, + "step": 4060 + }, + { + "epoch": 0.43, + "learning_rate": 1.419768820264225e-05, + "loss": 1.4449, + "step": 4061 + }, + { + "epoch": 0.43, + "learning_rate": 1.4194365764861922e-05, + "loss": 1.3382, + "step": 4062 + }, + { + "epoch": 0.43, + "learning_rate": 1.419104276514435e-05, + "loss": 1.3899, + "step": 4063 + }, + { + "epoch": 0.43, + "learning_rate": 1.4187719203934734e-05, + "loss": 1.3513, + "step": 4064 + }, + { + "epoch": 0.43, + "learning_rate": 1.4184395081678344e-05, + "loss": 1.3954, + "step": 4065 + }, + { + "epoch": 0.43, + "learning_rate": 1.4181070398820528e-05, + "loss": 1.442, + "step": 4066 + }, + { + "epoch": 0.43, + "learning_rate": 1.4177745155806708e-05, + "loss": 1.3907, + "step": 4067 + }, + { + "epoch": 0.43, + "learning_rate": 1.417441935308238e-05, + "loss": 1.3757, + "step": 4068 + }, + { + "epoch": 0.43, + "learning_rate": 1.4171092991093118e-05, + "loss": 1.3507, + "step": 4069 + }, + { + "epoch": 0.43, + "learning_rate": 1.4167766070284568e-05, + "loss": 1.4136, + "step": 4070 + }, + { + "epoch": 0.43, + "learning_rate": 1.4164438591102452e-05, + "loss": 1.3835, + "step": 4071 + }, + { + "epoch": 0.43, + "learning_rate": 1.4161110553992565e-05, + "loss": 1.4981, + "step": 4072 + }, + { + "epoch": 0.43, + "learning_rate": 1.415778195940078e-05, + "loss": 1.4387, + "step": 4073 + }, + { + "epoch": 0.43, + "learning_rate": 1.4154452807773047e-05, + "loss": 1.333, + "step": 4074 + }, + { + "epoch": 0.43, + "learning_rate": 1.4151123099555377e-05, + "loss": 1.3558, + "step": 4075 + }, + { + "epoch": 0.43, + "learning_rate": 1.4147792835193875e-05, + "loss": 1.4655, + "step": 4076 + }, + { + "epoch": 0.43, + "learning_rate": 1.4144462015134708e-05, + "loss": 1.4402, + "step": 4077 + }, + { + "epoch": 0.43, + "learning_rate": 1.4141130639824119e-05, + "loss": 1.4227, + "step": 4078 + }, + { + "epoch": 0.43, + "learning_rate": 1.4137798709708423e-05, + "loss": 1.4039, + "step": 4079 + }, + { + "epoch": 0.43, + "learning_rate": 1.4134466225234023e-05, + "loss": 1.3593, + "step": 4080 + }, + { + "epoch": 0.43, + "learning_rate": 1.4131133186847377e-05, + "loss": 1.372, + "step": 4081 + }, + { + "epoch": 0.43, + "learning_rate": 1.412779959499503e-05, + "loss": 1.4487, + "step": 4082 + }, + { + "epoch": 0.43, + "learning_rate": 1.4124465450123599e-05, + "loss": 1.3972, + "step": 4083 + }, + { + "epoch": 0.43, + "learning_rate": 1.4121130752679772e-05, + "loss": 1.3768, + "step": 4084 + }, + { + "epoch": 0.43, + "learning_rate": 1.4117795503110313e-05, + "loss": 1.3827, + "step": 4085 + }, + { + "epoch": 0.43, + "learning_rate": 1.4114459701862062e-05, + "loss": 1.3922, + "step": 4086 + }, + { + "epoch": 0.43, + "learning_rate": 1.4111123349381925e-05, + "loss": 1.3736, + "step": 4087 + }, + { + "epoch": 0.43, + "learning_rate": 1.4107786446116894e-05, + "loss": 1.4338, + "step": 4088 + }, + { + "epoch": 0.43, + "learning_rate": 1.4104448992514023e-05, + "loss": 1.347, + "step": 4089 + }, + { + "epoch": 0.43, + "learning_rate": 1.410111098902045e-05, + "loss": 1.3915, + "step": 4090 + }, + { + "epoch": 0.43, + "learning_rate": 1.4097772436083377e-05, + "loss": 1.3656, + "step": 4091 + }, + { + "epoch": 0.43, + "learning_rate": 1.4094433334150087e-05, + "loss": 1.3461, + "step": 4092 + }, + { + "epoch": 0.43, + "learning_rate": 1.4091093683667934e-05, + "loss": 1.7345, + "step": 4093 + }, + { + "epoch": 0.43, + "learning_rate": 1.4087753485084343e-05, + "loss": 1.6204, + "step": 4094 + }, + { + "epoch": 0.43, + "learning_rate": 1.4084412738846816e-05, + "loss": 1.4074, + "step": 4095 + }, + { + "epoch": 0.43, + "learning_rate": 1.408107144540293e-05, + "loss": 1.3776, + "step": 4096 + }, + { + "epoch": 0.43, + "learning_rate": 1.407772960520033e-05, + "loss": 1.4079, + "step": 4097 + }, + { + "epoch": 0.43, + "learning_rate": 1.4074387218686734e-05, + "loss": 1.4254, + "step": 4098 + }, + { + "epoch": 0.43, + "learning_rate": 1.407104428630994e-05, + "loss": 1.38, + "step": 4099 + }, + { + "epoch": 0.43, + "learning_rate": 1.4067700808517815e-05, + "loss": 1.4175, + "step": 4100 + }, + { + "epoch": 0.43, + "learning_rate": 1.4064356785758298e-05, + "loss": 1.4085, + "step": 4101 + }, + { + "epoch": 0.43, + "learning_rate": 1.4061012218479397e-05, + "loss": 1.4529, + "step": 4102 + }, + { + "epoch": 0.43, + "learning_rate": 1.405766710712921e-05, + "loss": 1.4836, + "step": 4103 + }, + { + "epoch": 0.43, + "learning_rate": 1.4054321452155885e-05, + "loss": 1.3915, + "step": 4104 + }, + { + "epoch": 0.43, + "learning_rate": 1.4050975254007659e-05, + "loss": 1.3044, + "step": 4105 + }, + { + "epoch": 0.43, + "learning_rate": 1.4047628513132835e-05, + "loss": 1.373, + "step": 4106 + }, + { + "epoch": 0.43, + "learning_rate": 1.4044281229979793e-05, + "loss": 1.4266, + "step": 4107 + }, + { + "epoch": 0.43, + "learning_rate": 1.4040933404996977e-05, + "loss": 1.3898, + "step": 4108 + }, + { + "epoch": 0.43, + "learning_rate": 1.4037585038632915e-05, + "loss": 0.9326, + "step": 4109 + }, + { + "epoch": 0.43, + "learning_rate": 1.40342361313362e-05, + "loss": 1.0831, + "step": 4110 + }, + { + "epoch": 0.43, + "learning_rate": 1.40308866835555e-05, + "loss": 1.3898, + "step": 4111 + }, + { + "epoch": 0.43, + "learning_rate": 1.4027536695739554e-05, + "loss": 1.5058, + "step": 4112 + }, + { + "epoch": 0.43, + "learning_rate": 1.4024186168337175e-05, + "loss": 1.3635, + "step": 4113 + }, + { + "epoch": 0.43, + "learning_rate": 1.4020835101797248e-05, + "loss": 1.3871, + "step": 4114 + }, + { + "epoch": 0.43, + "learning_rate": 1.401748349656873e-05, + "loss": 1.3478, + "step": 4115 + }, + { + "epoch": 0.43, + "learning_rate": 1.4014131353100648e-05, + "loss": 1.3356, + "step": 4116 + }, + { + "epoch": 0.43, + "learning_rate": 1.4010778671842107e-05, + "loss": 1.3954, + "step": 4117 + }, + { + "epoch": 0.43, + "learning_rate": 1.4007425453242274e-05, + "loss": 1.3307, + "step": 4118 + }, + { + "epoch": 0.43, + "learning_rate": 1.4004071697750398e-05, + "loss": 1.4508, + "step": 4119 + }, + { + "epoch": 0.43, + "learning_rate": 1.4000717405815799e-05, + "loss": 1.3752, + "step": 4120 + }, + { + "epoch": 0.43, + "learning_rate": 1.399736257788786e-05, + "loss": 1.3654, + "step": 4121 + }, + { + "epoch": 0.43, + "learning_rate": 1.3994007214416046e-05, + "loss": 1.4505, + "step": 4122 + }, + { + "epoch": 0.43, + "learning_rate": 1.3990651315849886e-05, + "loss": 1.4307, + "step": 4123 + }, + { + "epoch": 0.43, + "learning_rate": 1.398729488263899e-05, + "loss": 1.4481, + "step": 4124 + }, + { + "epoch": 0.43, + "learning_rate": 1.3983937915233026e-05, + "loss": 1.4755, + "step": 4125 + }, + { + "epoch": 0.43, + "learning_rate": 1.3980580414081746e-05, + "loss": 1.3402, + "step": 4126 + }, + { + "epoch": 0.43, + "learning_rate": 1.3977222379634969e-05, + "loss": 1.3636, + "step": 4127 + }, + { + "epoch": 0.43, + "learning_rate": 1.3973863812342585e-05, + "loss": 1.4165, + "step": 4128 + }, + { + "epoch": 0.43, + "learning_rate": 1.3970504712654554e-05, + "loss": 1.3832, + "step": 4129 + }, + { + "epoch": 0.43, + "learning_rate": 1.3967145081020912e-05, + "loss": 1.4236, + "step": 4130 + }, + { + "epoch": 0.43, + "learning_rate": 1.396378491789176e-05, + "loss": 1.5022, + "step": 4131 + }, + { + "epoch": 0.43, + "learning_rate": 1.3960424223717276e-05, + "loss": 1.3806, + "step": 4132 + }, + { + "epoch": 0.43, + "learning_rate": 1.3957062998947707e-05, + "loss": 1.3649, + "step": 4133 + }, + { + "epoch": 0.43, + "learning_rate": 1.3953701244033368e-05, + "loss": 1.3787, + "step": 4134 + }, + { + "epoch": 0.43, + "learning_rate": 1.395033895942465e-05, + "loss": 1.3551, + "step": 4135 + }, + { + "epoch": 0.43, + "learning_rate": 1.394697614557201e-05, + "loss": 1.3881, + "step": 4136 + }, + { + "epoch": 0.43, + "learning_rate": 1.3943612802925983e-05, + "loss": 1.4848, + "step": 4137 + }, + { + "epoch": 0.43, + "learning_rate": 1.3940248931937169e-05, + "loss": 1.425, + "step": 4138 + }, + { + "epoch": 0.43, + "learning_rate": 1.3936884533056238e-05, + "loss": 1.4054, + "step": 4139 + }, + { + "epoch": 0.43, + "learning_rate": 1.3933519606733934e-05, + "loss": 1.4028, + "step": 4140 + }, + { + "epoch": 0.43, + "learning_rate": 1.3930154153421072e-05, + "loss": 1.4439, + "step": 4141 + }, + { + "epoch": 0.43, + "learning_rate": 1.3926788173568536e-05, + "loss": 1.4482, + "step": 4142 + }, + { + "epoch": 0.43, + "learning_rate": 1.392342166762728e-05, + "loss": 1.393, + "step": 4143 + }, + { + "epoch": 0.43, + "learning_rate": 1.3920054636048328e-05, + "loss": 1.4097, + "step": 4144 + }, + { + "epoch": 0.43, + "learning_rate": 1.391668707928278e-05, + "loss": 1.5142, + "step": 4145 + }, + { + "epoch": 0.43, + "learning_rate": 1.3913318997781797e-05, + "loss": 1.4118, + "step": 4146 + }, + { + "epoch": 0.43, + "learning_rate": 1.390995039199662e-05, + "loss": 1.4067, + "step": 4147 + }, + { + "epoch": 0.43, + "learning_rate": 1.3906581262378552e-05, + "loss": 1.5214, + "step": 4148 + }, + { + "epoch": 0.44, + "learning_rate": 1.3903211609378971e-05, + "loss": 1.3618, + "step": 4149 + }, + { + "epoch": 0.44, + "learning_rate": 1.3899841433449327e-05, + "loss": 1.338, + "step": 4150 + }, + { + "epoch": 0.44, + "learning_rate": 1.3896470735041132e-05, + "loss": 1.3901, + "step": 4151 + }, + { + "epoch": 0.44, + "learning_rate": 1.3893099514605971e-05, + "loss": 1.4502, + "step": 4152 + }, + { + "epoch": 0.44, + "learning_rate": 1.388972777259551e-05, + "loss": 1.4141, + "step": 4153 + }, + { + "epoch": 0.44, + "learning_rate": 1.3886355509461471e-05, + "loss": 1.3876, + "step": 4154 + }, + { + "epoch": 0.44, + "learning_rate": 1.388298272565565e-05, + "loss": 1.4275, + "step": 4155 + }, + { + "epoch": 0.44, + "learning_rate": 1.3879609421629909e-05, + "loss": 1.3559, + "step": 4156 + }, + { + "epoch": 0.44, + "learning_rate": 1.3876235597836195e-05, + "loss": 1.416, + "step": 4157 + }, + { + "epoch": 0.44, + "learning_rate": 1.3872861254726506e-05, + "loss": 1.437, + "step": 4158 + }, + { + "epoch": 0.44, + "learning_rate": 1.3869486392752918e-05, + "loss": 1.3794, + "step": 4159 + }, + { + "epoch": 0.44, + "learning_rate": 1.3866111012367577e-05, + "loss": 1.4094, + "step": 4160 + }, + { + "epoch": 0.44, + "learning_rate": 1.3862735114022694e-05, + "loss": 1.3957, + "step": 4161 + }, + { + "epoch": 0.44, + "learning_rate": 1.3859358698170559e-05, + "loss": 1.3582, + "step": 4162 + }, + { + "epoch": 0.44, + "learning_rate": 1.3855981765263523e-05, + "loss": 1.4159, + "step": 4163 + }, + { + "epoch": 0.44, + "learning_rate": 1.3852604315754e-05, + "loss": 1.3498, + "step": 4164 + }, + { + "epoch": 0.44, + "learning_rate": 1.3849226350094491e-05, + "loss": 1.3951, + "step": 4165 + }, + { + "epoch": 0.44, + "learning_rate": 1.3845847868737559e-05, + "loss": 1.4087, + "step": 4166 + }, + { + "epoch": 0.44, + "learning_rate": 1.3842468872135821e-05, + "loss": 1.4318, + "step": 4167 + }, + { + "epoch": 0.44, + "learning_rate": 1.3839089360741989e-05, + "loss": 1.4174, + "step": 4168 + }, + { + "epoch": 0.44, + "learning_rate": 1.3835709335008822e-05, + "loss": 1.4499, + "step": 4169 + }, + { + "epoch": 0.44, + "learning_rate": 1.383232879538916e-05, + "loss": 1.3554, + "step": 4170 + }, + { + "epoch": 0.44, + "learning_rate": 1.3828947742335905e-05, + "loss": 1.3873, + "step": 4171 + }, + { + "epoch": 0.44, + "learning_rate": 1.382556617630204e-05, + "loss": 1.3804, + "step": 4172 + }, + { + "epoch": 0.44, + "learning_rate": 1.3822184097740598e-05, + "loss": 1.3856, + "step": 4173 + }, + { + "epoch": 0.44, + "learning_rate": 1.3818801507104697e-05, + "loss": 1.3901, + "step": 4174 + }, + { + "epoch": 0.44, + "learning_rate": 1.381541840484751e-05, + "loss": 1.3714, + "step": 4175 + }, + { + "epoch": 0.44, + "learning_rate": 1.3812034791422297e-05, + "loss": 1.4945, + "step": 4176 + }, + { + "epoch": 0.44, + "learning_rate": 1.3808650667282368e-05, + "loss": 1.429, + "step": 4177 + }, + { + "epoch": 0.44, + "learning_rate": 1.3805266032881108e-05, + "loss": 1.3903, + "step": 4178 + }, + { + "epoch": 0.44, + "learning_rate": 1.3801880888671972e-05, + "loss": 1.4799, + "step": 4179 + }, + { + "epoch": 0.44, + "eval_loss": 1.4521424770355225, + "eval_runtime": 77.3596, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 4179 + }, + { + "epoch": 0.44, + "learning_rate": 1.3798495235108484e-05, + "loss": 1.3912, + "step": 4180 + }, + { + "epoch": 0.44, + "learning_rate": 1.3795109072644235e-05, + "loss": 1.5837, + "step": 4181 + }, + { + "epoch": 0.44, + "learning_rate": 1.379172240173288e-05, + "loss": 1.4255, + "step": 4182 + }, + { + "epoch": 0.44, + "learning_rate": 1.3788335222828148e-05, + "loss": 1.4666, + "step": 4183 + }, + { + "epoch": 0.44, + "learning_rate": 1.3784947536383837e-05, + "loss": 1.3964, + "step": 4184 + }, + { + "epoch": 0.44, + "learning_rate": 1.3781559342853807e-05, + "loss": 1.336, + "step": 4185 + }, + { + "epoch": 0.44, + "learning_rate": 1.3778170642691986e-05, + "loss": 1.4352, + "step": 4186 + }, + { + "epoch": 0.44, + "learning_rate": 1.377478143635238e-05, + "loss": 1.3262, + "step": 4187 + }, + { + "epoch": 0.44, + "learning_rate": 1.3771391724289047e-05, + "loss": 1.3969, + "step": 4188 + }, + { + "epoch": 0.44, + "learning_rate": 1.376800150695613e-05, + "loss": 1.4211, + "step": 4189 + }, + { + "epoch": 0.44, + "learning_rate": 1.3764610784807824e-05, + "loss": 1.4338, + "step": 4190 + }, + { + "epoch": 0.44, + "learning_rate": 1.3761219558298403e-05, + "loss": 1.3815, + "step": 4191 + }, + { + "epoch": 0.44, + "learning_rate": 1.3757827827882203e-05, + "loss": 1.3805, + "step": 4192 + }, + { + "epoch": 0.44, + "learning_rate": 1.3754435594013627e-05, + "loss": 1.4071, + "step": 4193 + }, + { + "epoch": 0.44, + "learning_rate": 1.3751042857147145e-05, + "loss": 1.343, + "step": 4194 + }, + { + "epoch": 0.44, + "learning_rate": 1.3747649617737304e-05, + "loss": 1.4129, + "step": 4195 + }, + { + "epoch": 0.44, + "learning_rate": 1.3744255876238708e-05, + "loss": 1.3939, + "step": 4196 + }, + { + "epoch": 0.44, + "learning_rate": 1.3740861633106029e-05, + "loss": 1.3963, + "step": 4197 + }, + { + "epoch": 0.44, + "learning_rate": 1.3737466888794008e-05, + "loss": 1.5181, + "step": 4198 + }, + { + "epoch": 0.44, + "learning_rate": 1.3734071643757456e-05, + "loss": 1.4397, + "step": 4199 + }, + { + "epoch": 0.44, + "learning_rate": 1.373067589845125e-05, + "loss": 1.6293, + "step": 4200 + }, + { + "epoch": 0.44, + "learning_rate": 1.3727279653330328e-05, + "loss": 1.3498, + "step": 4201 + }, + { + "epoch": 0.44, + "learning_rate": 1.37238829088497e-05, + "loss": 1.4509, + "step": 4202 + }, + { + "epoch": 0.44, + "learning_rate": 1.3720485665464446e-05, + "loss": 1.4477, + "step": 4203 + }, + { + "epoch": 0.44, + "learning_rate": 1.3717087923629709e-05, + "loss": 1.4399, + "step": 4204 + }, + { + "epoch": 0.44, + "learning_rate": 1.3713689683800695e-05, + "loss": 1.4417, + "step": 4205 + }, + { + "epoch": 0.44, + "learning_rate": 1.3710290946432685e-05, + "loss": 1.3957, + "step": 4206 + }, + { + "epoch": 0.44, + "learning_rate": 1.3706891711981021e-05, + "loss": 1.4476, + "step": 4207 + }, + { + "epoch": 0.44, + "learning_rate": 1.3703491980901113e-05, + "loss": 1.3894, + "step": 4208 + }, + { + "epoch": 0.44, + "learning_rate": 1.3700091753648437e-05, + "loss": 1.4745, + "step": 4209 + }, + { + "epoch": 0.44, + "learning_rate": 1.369669103067854e-05, + "loss": 1.4038, + "step": 4210 + }, + { + "epoch": 0.44, + "learning_rate": 1.3693289812447023e-05, + "loss": 1.4151, + "step": 4211 + }, + { + "epoch": 0.44, + "learning_rate": 1.3689888099409572e-05, + "loss": 1.4214, + "step": 4212 + }, + { + "epoch": 0.44, + "learning_rate": 1.368648589202192e-05, + "loss": 1.4287, + "step": 4213 + }, + { + "epoch": 0.44, + "learning_rate": 1.3683083190739883e-05, + "loss": 1.345, + "step": 4214 + }, + { + "epoch": 0.44, + "learning_rate": 1.367967999601933e-05, + "loss": 1.3022, + "step": 4215 + }, + { + "epoch": 0.44, + "learning_rate": 1.3676276308316207e-05, + "loss": 1.3971, + "step": 4216 + }, + { + "epoch": 0.44, + "learning_rate": 1.3672872128086514e-05, + "loss": 1.3335, + "step": 4217 + }, + { + "epoch": 0.44, + "learning_rate": 1.366946745578633e-05, + "loss": 1.3988, + "step": 4218 + }, + { + "epoch": 0.44, + "learning_rate": 1.366606229187179e-05, + "loss": 1.4508, + "step": 4219 + }, + { + "epoch": 0.44, + "learning_rate": 1.3662656636799099e-05, + "loss": 1.3814, + "step": 4220 + }, + { + "epoch": 0.44, + "learning_rate": 1.3659250491024527e-05, + "loss": 1.4128, + "step": 4221 + }, + { + "epoch": 0.44, + "learning_rate": 1.3655843855004411e-05, + "loss": 1.3893, + "step": 4222 + }, + { + "epoch": 0.44, + "learning_rate": 1.3652436729195154e-05, + "loss": 1.2551, + "step": 4223 + }, + { + "epoch": 0.44, + "learning_rate": 1.3649029114053219e-05, + "loss": 1.4386, + "step": 4224 + }, + { + "epoch": 0.44, + "learning_rate": 1.364562101003514e-05, + "loss": 1.4028, + "step": 4225 + }, + { + "epoch": 0.44, + "learning_rate": 1.364221241759752e-05, + "loss": 1.4351, + "step": 4226 + }, + { + "epoch": 0.44, + "learning_rate": 1.363880333719702e-05, + "loss": 1.3941, + "step": 4227 + }, + { + "epoch": 0.44, + "learning_rate": 1.3635393769290368e-05, + "loss": 1.3879, + "step": 4228 + }, + { + "epoch": 0.44, + "learning_rate": 1.3631983714334358e-05, + "loss": 1.3773, + "step": 4229 + }, + { + "epoch": 0.44, + "learning_rate": 1.3628573172785853e-05, + "loss": 1.3679, + "step": 4230 + }, + { + "epoch": 0.44, + "learning_rate": 1.3625162145101776e-05, + "loss": 1.3705, + "step": 4231 + }, + { + "epoch": 0.44, + "learning_rate": 1.3621750631739114e-05, + "loss": 1.8157, + "step": 4232 + }, + { + "epoch": 0.44, + "learning_rate": 1.3618338633154928e-05, + "loss": 1.4056, + "step": 4233 + }, + { + "epoch": 0.44, + "learning_rate": 1.3614926149806334e-05, + "loss": 1.3716, + "step": 4234 + }, + { + "epoch": 0.44, + "learning_rate": 1.3611513182150523e-05, + "loss": 1.3766, + "step": 4235 + }, + { + "epoch": 0.44, + "learning_rate": 1.3608099730644733e-05, + "loss": 1.41, + "step": 4236 + }, + { + "epoch": 0.44, + "learning_rate": 1.3604685795746291e-05, + "loss": 1.421, + "step": 4237 + }, + { + "epoch": 0.44, + "learning_rate": 1.360127137791257e-05, + "loss": 1.3679, + "step": 4238 + }, + { + "epoch": 0.44, + "learning_rate": 1.3597856477601018e-05, + "loss": 1.4615, + "step": 4239 + }, + { + "epoch": 0.44, + "learning_rate": 1.359444109526914e-05, + "loss": 1.3418, + "step": 4240 + }, + { + "epoch": 0.44, + "learning_rate": 1.3591025231374513e-05, + "loss": 1.3631, + "step": 4241 + }, + { + "epoch": 0.44, + "learning_rate": 1.3587608886374772e-05, + "loss": 1.3802, + "step": 4242 + }, + { + "epoch": 0.44, + "learning_rate": 1.3584192060727622e-05, + "loss": 1.4156, + "step": 4243 + }, + { + "epoch": 0.45, + "learning_rate": 1.3580774754890827e-05, + "loss": 1.4161, + "step": 4244 + }, + { + "epoch": 0.45, + "learning_rate": 1.3577356969322222e-05, + "loss": 1.3535, + "step": 4245 + }, + { + "epoch": 0.45, + "learning_rate": 1.3573938704479699e-05, + "loss": 1.3859, + "step": 4246 + }, + { + "epoch": 0.45, + "learning_rate": 1.357051996082122e-05, + "loss": 1.3595, + "step": 4247 + }, + { + "epoch": 0.45, + "learning_rate": 1.3567100738804806e-05, + "loss": 1.4191, + "step": 4248 + }, + { + "epoch": 0.45, + "learning_rate": 1.3563681038888548e-05, + "loss": 1.4186, + "step": 4249 + }, + { + "epoch": 0.45, + "learning_rate": 1.3560260861530596e-05, + "loss": 1.43, + "step": 4250 + }, + { + "epoch": 0.45, + "learning_rate": 1.3556840207189168e-05, + "loss": 1.4139, + "step": 4251 + }, + { + "epoch": 0.45, + "learning_rate": 1.3553419076322539e-05, + "loss": 1.4005, + "step": 4252 + }, + { + "epoch": 0.45, + "learning_rate": 1.3549997469389058e-05, + "loss": 1.3468, + "step": 4253 + }, + { + "epoch": 0.45, + "learning_rate": 1.3546575386847132e-05, + "loss": 1.3756, + "step": 4254 + }, + { + "epoch": 0.45, + "learning_rate": 1.3543152829155226e-05, + "loss": 1.4063, + "step": 4255 + }, + { + "epoch": 0.45, + "learning_rate": 1.3539729796771884e-05, + "loss": 1.4666, + "step": 4256 + }, + { + "epoch": 0.45, + "learning_rate": 1.3536306290155694e-05, + "loss": 1.4212, + "step": 4257 + }, + { + "epoch": 0.45, + "learning_rate": 1.3532882309765332e-05, + "loss": 1.4883, + "step": 4258 + }, + { + "epoch": 0.45, + "learning_rate": 1.3529457856059507e-05, + "loss": 1.6641, + "step": 4259 + }, + { + "epoch": 0.45, + "learning_rate": 1.3526032929497022e-05, + "loss": 1.3659, + "step": 4260 + }, + { + "epoch": 0.45, + "learning_rate": 1.3522607530536717e-05, + "loss": 1.5945, + "step": 4261 + }, + { + "epoch": 0.45, + "learning_rate": 1.351918165963752e-05, + "loss": 1.3643, + "step": 4262 + }, + { + "epoch": 0.45, + "learning_rate": 1.3515755317258397e-05, + "loss": 1.3442, + "step": 4263 + }, + { + "epoch": 0.45, + "learning_rate": 1.3512328503858398e-05, + "loss": 1.3982, + "step": 4264 + }, + { + "epoch": 0.45, + "learning_rate": 1.3508901219896624e-05, + "loss": 1.4985, + "step": 4265 + }, + { + "epoch": 0.45, + "learning_rate": 1.350547346583225e-05, + "loss": 1.3319, + "step": 4266 + }, + { + "epoch": 0.45, + "learning_rate": 1.3502045242124497e-05, + "loss": 1.3961, + "step": 4267 + }, + { + "epoch": 0.45, + "learning_rate": 1.3498616549232665e-05, + "loss": 1.4565, + "step": 4268 + }, + { + "epoch": 0.45, + "learning_rate": 1.349518738761611e-05, + "loss": 1.375, + "step": 4269 + }, + { + "epoch": 0.45, + "learning_rate": 1.3491757757734254e-05, + "loss": 1.3005, + "step": 4270 + }, + { + "epoch": 0.45, + "learning_rate": 1.348832766004657e-05, + "loss": 1.3185, + "step": 4271 + }, + { + "epoch": 0.45, + "learning_rate": 1.3484897095012613e-05, + "loss": 1.4449, + "step": 4272 + }, + { + "epoch": 0.45, + "learning_rate": 1.3481466063091988e-05, + "loss": 1.3587, + "step": 4273 + }, + { + "epoch": 0.45, + "learning_rate": 1.3478034564744362e-05, + "loss": 1.3844, + "step": 4274 + }, + { + "epoch": 0.45, + "learning_rate": 1.3474602600429468e-05, + "loss": 1.4471, + "step": 4275 + }, + { + "epoch": 0.45, + "learning_rate": 1.3471170170607105e-05, + "loss": 1.4686, + "step": 4276 + }, + { + "epoch": 0.45, + "learning_rate": 1.3467737275737127e-05, + "loss": 1.312, + "step": 4277 + }, + { + "epoch": 0.45, + "learning_rate": 1.3464303916279453e-05, + "loss": 1.407, + "step": 4278 + }, + { + "epoch": 0.45, + "learning_rate": 1.346087009269407e-05, + "loss": 1.364, + "step": 4279 + }, + { + "epoch": 0.45, + "learning_rate": 1.3457435805441016e-05, + "loss": 1.4103, + "step": 4280 + }, + { + "epoch": 0.45, + "learning_rate": 1.3454001054980403e-05, + "loss": 1.4243, + "step": 4281 + }, + { + "epoch": 0.45, + "learning_rate": 1.3450565841772392e-05, + "loss": 1.3879, + "step": 4282 + }, + { + "epoch": 0.45, + "learning_rate": 1.344713016627722e-05, + "loss": 1.4688, + "step": 4283 + }, + { + "epoch": 0.45, + "learning_rate": 1.3443694028955176e-05, + "loss": 1.3983, + "step": 4284 + }, + { + "epoch": 0.45, + "learning_rate": 1.344025743026662e-05, + "loss": 1.4316, + "step": 4285 + }, + { + "epoch": 0.45, + "learning_rate": 1.3436820370671956e-05, + "loss": 1.3643, + "step": 4286 + }, + { + "epoch": 0.45, + "learning_rate": 1.3433382850631673e-05, + "loss": 1.4566, + "step": 4287 + }, + { + "epoch": 0.45, + "learning_rate": 1.3429944870606301e-05, + "loss": 1.1263, + "step": 4288 + }, + { + "epoch": 0.45, + "learning_rate": 1.3426506431056452e-05, + "loss": 1.2463, + "step": 4289 + }, + { + "epoch": 0.45, + "learning_rate": 1.342306753244278e-05, + "loss": 1.4753, + "step": 4290 + }, + { + "epoch": 0.45, + "learning_rate": 1.3419628175226012e-05, + "loss": 1.3789, + "step": 4291 + }, + { + "epoch": 0.45, + "learning_rate": 1.3416188359866932e-05, + "loss": 1.3906, + "step": 4292 + }, + { + "epoch": 0.45, + "learning_rate": 1.3412748086826389e-05, + "loss": 1.3995, + "step": 4293 + }, + { + "epoch": 0.45, + "learning_rate": 1.3409307356565288e-05, + "loss": 1.4906, + "step": 4294 + }, + { + "epoch": 0.45, + "learning_rate": 1.3405866169544602e-05, + "loss": 1.3951, + "step": 4295 + }, + { + "epoch": 0.45, + "learning_rate": 1.3402424526225359e-05, + "loss": 1.3753, + "step": 4296 + }, + { + "epoch": 0.45, + "learning_rate": 1.3398982427068654e-05, + "loss": 1.3686, + "step": 4297 + }, + { + "epoch": 0.45, + "learning_rate": 1.3395539872535636e-05, + "loss": 1.3612, + "step": 4298 + }, + { + "epoch": 0.45, + "learning_rate": 1.3392096863087522e-05, + "loss": 1.4043, + "step": 4299 + }, + { + "epoch": 0.45, + "learning_rate": 1.3388653399185585e-05, + "loss": 1.4068, + "step": 4300 + }, + { + "epoch": 0.45, + "learning_rate": 1.338520948129116e-05, + "loss": 1.4066, + "step": 4301 + }, + { + "epoch": 0.45, + "learning_rate": 1.3381765109865646e-05, + "loss": 1.4944, + "step": 4302 + }, + { + "epoch": 0.45, + "learning_rate": 1.3378320285370496e-05, + "loss": 1.3575, + "step": 4303 + }, + { + "epoch": 0.45, + "learning_rate": 1.3374875008267236e-05, + "loss": 1.3807, + "step": 4304 + }, + { + "epoch": 0.45, + "learning_rate": 1.3371429279017437e-05, + "loss": 1.4389, + "step": 4305 + }, + { + "epoch": 0.45, + "learning_rate": 1.3367983098082739e-05, + "loss": 1.4858, + "step": 4306 + }, + { + "epoch": 0.45, + "learning_rate": 1.3364536465924844e-05, + "loss": 1.3282, + "step": 4307 + }, + { + "epoch": 0.45, + "learning_rate": 1.3361089383005515e-05, + "loss": 1.4306, + "step": 4308 + }, + { + "epoch": 0.45, + "learning_rate": 1.3357641849786566e-05, + "loss": 1.3892, + "step": 4309 + }, + { + "epoch": 0.45, + "learning_rate": 1.3354193866729883e-05, + "loss": 1.3621, + "step": 4310 + }, + { + "epoch": 0.45, + "learning_rate": 1.3350745434297401e-05, + "loss": 1.3476, + "step": 4311 + }, + { + "epoch": 0.45, + "learning_rate": 1.334729655295113e-05, + "loss": 1.4477, + "step": 4312 + }, + { + "epoch": 0.45, + "learning_rate": 1.3343847223153123e-05, + "loss": 1.3585, + "step": 4313 + }, + { + "epoch": 0.45, + "learning_rate": 1.334039744536551e-05, + "loss": 1.3616, + "step": 4314 + }, + { + "epoch": 0.45, + "learning_rate": 1.3336947220050462e-05, + "loss": 1.3579, + "step": 4315 + }, + { + "epoch": 0.45, + "learning_rate": 1.3333496547670232e-05, + "loss": 1.3557, + "step": 4316 + }, + { + "epoch": 0.45, + "learning_rate": 1.3330045428687113e-05, + "loss": 1.4443, + "step": 4317 + }, + { + "epoch": 0.45, + "learning_rate": 1.332659386356347e-05, + "loss": 1.3621, + "step": 4318 + }, + { + "epoch": 0.45, + "learning_rate": 1.3323141852761726e-05, + "loss": 1.3295, + "step": 4319 + }, + { + "epoch": 0.45, + "learning_rate": 1.3319689396744358e-05, + "loss": 1.4187, + "step": 4320 + }, + { + "epoch": 0.45, + "learning_rate": 1.3316236495973905e-05, + "loss": 1.335, + "step": 4321 + }, + { + "epoch": 0.45, + "learning_rate": 1.331278315091297e-05, + "loss": 1.4382, + "step": 4322 + }, + { + "epoch": 0.45, + "learning_rate": 1.3309329362024212e-05, + "loss": 1.4244, + "step": 4323 + }, + { + "epoch": 0.45, + "learning_rate": 1.3305875129770351e-05, + "loss": 1.488, + "step": 4324 + }, + { + "epoch": 0.45, + "learning_rate": 1.3302420454614165e-05, + "loss": 1.3369, + "step": 4325 + }, + { + "epoch": 0.45, + "learning_rate": 1.3298965337018487e-05, + "loss": 1.3648, + "step": 4326 + }, + { + "epoch": 0.45, + "learning_rate": 1.3295509777446226e-05, + "loss": 1.3924, + "step": 4327 + }, + { + "epoch": 0.45, + "learning_rate": 1.3292053776360324e-05, + "loss": 1.3789, + "step": 4328 + }, + { + "epoch": 0.45, + "learning_rate": 1.3288597334223802e-05, + "loss": 1.3902, + "step": 4329 + }, + { + "epoch": 0.45, + "learning_rate": 1.3285140451499735e-05, + "loss": 1.4057, + "step": 4330 + }, + { + "epoch": 0.45, + "learning_rate": 1.328168312865126e-05, + "loss": 1.4536, + "step": 4331 + }, + { + "epoch": 0.45, + "learning_rate": 1.3278225366141565e-05, + "loss": 1.3075, + "step": 4332 + }, + { + "epoch": 0.45, + "learning_rate": 1.3274767164433901e-05, + "loss": 1.4579, + "step": 4333 + }, + { + "epoch": 0.45, + "learning_rate": 1.3271308523991579e-05, + "loss": 1.3906, + "step": 4334 + }, + { + "epoch": 0.45, + "learning_rate": 1.326784944527797e-05, + "loss": 1.3992, + "step": 4335 + }, + { + "epoch": 0.45, + "learning_rate": 1.3264389928756498e-05, + "loss": 1.4001, + "step": 4336 + }, + { + "epoch": 0.45, + "learning_rate": 1.3260929974890653e-05, + "loss": 1.2948, + "step": 4337 + }, + { + "epoch": 0.45, + "learning_rate": 1.3257469584143976e-05, + "loss": 1.4041, + "step": 4338 + }, + { + "epoch": 0.46, + "learning_rate": 1.3254008756980076e-05, + "loss": 1.5035, + "step": 4339 + }, + { + "epoch": 0.46, + "learning_rate": 1.3250547493862609e-05, + "loss": 1.4867, + "step": 4340 + }, + { + "epoch": 0.46, + "learning_rate": 1.3247085795255302e-05, + "loss": 1.3612, + "step": 4341 + }, + { + "epoch": 0.46, + "learning_rate": 1.3243623661621925e-05, + "loss": 1.4193, + "step": 4342 + }, + { + "epoch": 0.46, + "learning_rate": 1.3240161093426322e-05, + "loss": 1.3596, + "step": 4343 + }, + { + "epoch": 0.46, + "learning_rate": 1.3236698091132383e-05, + "loss": 1.4448, + "step": 4344 + }, + { + "epoch": 0.46, + "learning_rate": 1.3233234655204066e-05, + "loss": 1.3924, + "step": 4345 + }, + { + "epoch": 0.46, + "learning_rate": 1.322977078610538e-05, + "loss": 1.3552, + "step": 4346 + }, + { + "epoch": 0.46, + "learning_rate": 1.3226306484300395e-05, + "loss": 1.3949, + "step": 4347 + }, + { + "epoch": 0.46, + "learning_rate": 1.322284175025324e-05, + "loss": 1.399, + "step": 4348 + }, + { + "epoch": 0.46, + "learning_rate": 1.3219376584428094e-05, + "loss": 1.4755, + "step": 4349 + }, + { + "epoch": 0.46, + "learning_rate": 1.3215910987289212e-05, + "loss": 1.3877, + "step": 4350 + }, + { + "epoch": 0.46, + "learning_rate": 1.3212444959300882e-05, + "loss": 1.3916, + "step": 4351 + }, + { + "epoch": 0.46, + "learning_rate": 1.3208978500927472e-05, + "loss": 1.3462, + "step": 4352 + }, + { + "epoch": 0.46, + "learning_rate": 1.3205511612633392e-05, + "loss": 1.3834, + "step": 4353 + }, + { + "epoch": 0.46, + "learning_rate": 1.3202044294883123e-05, + "loss": 1.3843, + "step": 4354 + }, + { + "epoch": 0.46, + "learning_rate": 1.3198576548141189e-05, + "loss": 1.2439, + "step": 4355 + }, + { + "epoch": 0.46, + "learning_rate": 1.3195108372872181e-05, + "loss": 1.4106, + "step": 4356 + }, + { + "epoch": 0.46, + "learning_rate": 1.3191639769540746e-05, + "loss": 1.4417, + "step": 4357 + }, + { + "epoch": 0.46, + "learning_rate": 1.3188170738611596e-05, + "loss": 1.4393, + "step": 4358 + }, + { + "epoch": 0.46, + "learning_rate": 1.3184701280549476e-05, + "loss": 1.4616, + "step": 4359 + }, + { + "epoch": 0.46, + "learning_rate": 1.3181231395819218e-05, + "loss": 1.3215, + "step": 4360 + }, + { + "epoch": 0.46, + "learning_rate": 1.3177761084885689e-05, + "loss": 1.368, + "step": 4361 + }, + { + "epoch": 0.46, + "learning_rate": 1.317429034821383e-05, + "loss": 1.3247, + "step": 4362 + }, + { + "epoch": 0.46, + "learning_rate": 1.3170819186268618e-05, + "loss": 1.4512, + "step": 4363 + }, + { + "epoch": 0.46, + "learning_rate": 1.3167347599515111e-05, + "loss": 1.3129, + "step": 4364 + }, + { + "epoch": 0.46, + "learning_rate": 1.3163875588418404e-05, + "loss": 1.3934, + "step": 4365 + }, + { + "epoch": 0.46, + "learning_rate": 1.3160403153443666e-05, + "loss": 1.4518, + "step": 4366 + }, + { + "epoch": 0.46, + "learning_rate": 1.3156930295056105e-05, + "loss": 1.3959, + "step": 4367 + }, + { + "epoch": 0.46, + "learning_rate": 1.3153457013721e-05, + "loss": 1.3475, + "step": 4368 + }, + { + "epoch": 0.46, + "learning_rate": 1.3149983309903687e-05, + "loss": 1.4102, + "step": 4369 + }, + { + "epoch": 0.46, + "learning_rate": 1.3146509184069538e-05, + "loss": 1.3674, + "step": 4370 + }, + { + "epoch": 0.46, + "learning_rate": 1.314303463668401e-05, + "loss": 1.3739, + "step": 4371 + }, + { + "epoch": 0.46, + "learning_rate": 1.3139559668212596e-05, + "loss": 1.4249, + "step": 4372 + }, + { + "epoch": 0.46, + "learning_rate": 1.3136084279120857e-05, + "loss": 1.4473, + "step": 4373 + }, + { + "epoch": 0.46, + "learning_rate": 1.3132608469874404e-05, + "loss": 1.4443, + "step": 4374 + }, + { + "epoch": 0.46, + "learning_rate": 1.3129132240938905e-05, + "loss": 1.3534, + "step": 4375 + }, + { + "epoch": 0.46, + "learning_rate": 1.3125655592780083e-05, + "loss": 1.5663, + "step": 4376 + }, + { + "epoch": 0.46, + "learning_rate": 1.3122178525863727e-05, + "loss": 1.3465, + "step": 4377 + }, + { + "epoch": 0.46, + "learning_rate": 1.3118701040655669e-05, + "loss": 1.35, + "step": 4378 + }, + { + "epoch": 0.46, + "eval_loss": 1.447788953781128, + "eval_runtime": 77.4473, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4378 + }, + { + "epoch": 0.46, + "learning_rate": 1.3115223137621804e-05, + "loss": 1.343, + "step": 4379 + }, + { + "epoch": 0.46, + "learning_rate": 1.3111744817228078e-05, + "loss": 1.4227, + "step": 4380 + }, + { + "epoch": 0.46, + "learning_rate": 1.3108266079940508e-05, + "loss": 1.3982, + "step": 4381 + }, + { + "epoch": 0.46, + "learning_rate": 1.3104786926225141e-05, + "loss": 1.4211, + "step": 4382 + }, + { + "epoch": 0.46, + "learning_rate": 1.3101307356548103e-05, + "loss": 1.382, + "step": 4383 + }, + { + "epoch": 0.46, + "learning_rate": 1.3097827371375562e-05, + "loss": 1.4637, + "step": 4384 + }, + { + "epoch": 0.46, + "learning_rate": 1.3094346971173754e-05, + "loss": 1.4572, + "step": 4385 + }, + { + "epoch": 0.46, + "learning_rate": 1.3090866156408956e-05, + "loss": 1.5113, + "step": 4386 + }, + { + "epoch": 0.46, + "learning_rate": 1.3087384927547512e-05, + "loss": 1.2197, + "step": 4387 + }, + { + "epoch": 0.46, + "learning_rate": 1.3083903285055813e-05, + "loss": 1.3861, + "step": 4388 + }, + { + "epoch": 0.46, + "learning_rate": 1.3080421229400315e-05, + "loss": 1.4754, + "step": 4389 + }, + { + "epoch": 0.46, + "learning_rate": 1.307693876104752e-05, + "loss": 1.3588, + "step": 4390 + }, + { + "epoch": 0.46, + "learning_rate": 1.3073455880463987e-05, + "loss": 1.3995, + "step": 4391 + }, + { + "epoch": 0.46, + "learning_rate": 1.3069972588116341e-05, + "loss": 1.354, + "step": 4392 + }, + { + "epoch": 0.46, + "learning_rate": 1.3066488884471244e-05, + "loss": 1.3378, + "step": 4393 + }, + { + "epoch": 0.46, + "learning_rate": 1.306300476999543e-05, + "loss": 1.5951, + "step": 4394 + }, + { + "epoch": 0.46, + "learning_rate": 1.305952024515568e-05, + "loss": 1.3661, + "step": 4395 + }, + { + "epoch": 0.46, + "learning_rate": 1.3056035310418826e-05, + "loss": 1.4066, + "step": 4396 + }, + { + "epoch": 0.46, + "learning_rate": 1.3052549966251764e-05, + "loss": 1.3687, + "step": 4397 + }, + { + "epoch": 0.46, + "learning_rate": 1.3049064213121438e-05, + "loss": 1.4573, + "step": 4398 + }, + { + "epoch": 0.46, + "learning_rate": 1.3045578051494852e-05, + "loss": 1.3519, + "step": 4399 + }, + { + "epoch": 0.46, + "learning_rate": 1.3042091481839063e-05, + "loss": 1.2803, + "step": 4400 + }, + { + "epoch": 0.46, + "learning_rate": 1.3038604504621173e-05, + "loss": 1.4014, + "step": 4401 + }, + { + "epoch": 0.46, + "learning_rate": 1.3035117120308358e-05, + "loss": 1.4534, + "step": 4402 + }, + { + "epoch": 0.46, + "learning_rate": 1.3031629329367832e-05, + "loss": 1.4747, + "step": 4403 + }, + { + "epoch": 0.46, + "learning_rate": 1.3028141132266877e-05, + "loss": 1.374, + "step": 4404 + }, + { + "epoch": 0.46, + "learning_rate": 1.3024652529472807e-05, + "loss": 1.4328, + "step": 4405 + }, + { + "epoch": 0.46, + "learning_rate": 1.302116352145302e-05, + "loss": 1.468, + "step": 4406 + }, + { + "epoch": 0.46, + "learning_rate": 1.3017674108674942e-05, + "loss": 1.2947, + "step": 4407 + }, + { + "epoch": 0.46, + "learning_rate": 1.3014184291606077e-05, + "loss": 1.3682, + "step": 4408 + }, + { + "epoch": 0.46, + "learning_rate": 1.3010694070713959e-05, + "loss": 1.3651, + "step": 4409 + }, + { + "epoch": 0.46, + "learning_rate": 1.3007203446466194e-05, + "loss": 1.418, + "step": 4410 + }, + { + "epoch": 0.46, + "learning_rate": 1.3003712419330433e-05, + "loss": 1.416, + "step": 4411 + }, + { + "epoch": 0.46, + "learning_rate": 1.300022098977439e-05, + "loss": 1.2979, + "step": 4412 + }, + { + "epoch": 0.46, + "learning_rate": 1.2996729158265819e-05, + "loss": 1.3868, + "step": 4413 + }, + { + "epoch": 0.46, + "learning_rate": 1.2993236925272542e-05, + "loss": 1.3102, + "step": 4414 + }, + { + "epoch": 0.46, + "learning_rate": 1.2989744291262422e-05, + "loss": 1.3506, + "step": 4415 + }, + { + "epoch": 0.46, + "learning_rate": 1.2986251256703388e-05, + "loss": 1.4018, + "step": 4416 + }, + { + "epoch": 0.46, + "learning_rate": 1.2982757822063417e-05, + "loss": 1.4081, + "step": 4417 + }, + { + "epoch": 0.46, + "learning_rate": 1.2979263987810533e-05, + "loss": 1.3592, + "step": 4418 + }, + { + "epoch": 0.46, + "learning_rate": 1.297576975441283e-05, + "loss": 1.4287, + "step": 4419 + }, + { + "epoch": 0.46, + "learning_rate": 1.2972275122338433e-05, + "loss": 1.4099, + "step": 4420 + }, + { + "epoch": 0.46, + "learning_rate": 1.2968780092055546e-05, + "loss": 1.4005, + "step": 4421 + }, + { + "epoch": 0.46, + "learning_rate": 1.2965284664032401e-05, + "loss": 1.365, + "step": 4422 + }, + { + "epoch": 0.46, + "learning_rate": 1.2961788838737309e-05, + "loss": 1.3588, + "step": 4423 + }, + { + "epoch": 0.46, + "learning_rate": 1.2958292616638606e-05, + "loss": 1.3702, + "step": 4424 + }, + { + "epoch": 0.46, + "learning_rate": 1.2954795998204708e-05, + "loss": 1.3487, + "step": 4425 + }, + { + "epoch": 0.46, + "learning_rate": 1.2951298983904063e-05, + "loss": 1.4395, + "step": 4426 + }, + { + "epoch": 0.46, + "learning_rate": 1.2947801574205193e-05, + "loss": 1.3523, + "step": 4427 + }, + { + "epoch": 0.46, + "learning_rate": 1.2944303769576645e-05, + "loss": 1.3125, + "step": 4428 + }, + { + "epoch": 0.46, + "learning_rate": 1.2940805570487048e-05, + "loss": 1.5476, + "step": 4429 + }, + { + "epoch": 0.46, + "learning_rate": 1.2937306977405062e-05, + "loss": 1.4076, + "step": 4430 + }, + { + "epoch": 0.46, + "learning_rate": 1.2933807990799418e-05, + "loss": 1.3007, + "step": 4431 + }, + { + "epoch": 0.46, + "learning_rate": 1.293030861113888e-05, + "loss": 1.3566, + "step": 4432 + }, + { + "epoch": 0.46, + "learning_rate": 1.2926808838892285e-05, + "loss": 1.3907, + "step": 4433 + }, + { + "epoch": 0.46, + "learning_rate": 1.2923308674528501e-05, + "loss": 1.379, + "step": 4434 + }, + { + "epoch": 0.47, + "learning_rate": 1.2919808118516475e-05, + "loss": 1.4319, + "step": 4435 + }, + { + "epoch": 0.47, + "learning_rate": 1.2916307171325176e-05, + "loss": 1.3392, + "step": 4436 + }, + { + "epoch": 0.47, + "learning_rate": 1.291280583342365e-05, + "loss": 1.401, + "step": 4437 + }, + { + "epoch": 0.47, + "learning_rate": 1.2909304105280984e-05, + "loss": 1.3939, + "step": 4438 + }, + { + "epoch": 0.47, + "learning_rate": 1.2905801987366322e-05, + "loss": 1.4676, + "step": 4439 + }, + { + "epoch": 0.47, + "learning_rate": 1.2902299480148855e-05, + "loss": 1.3957, + "step": 4440 + }, + { + "epoch": 0.47, + "learning_rate": 1.2898796584097828e-05, + "loss": 1.3587, + "step": 4441 + }, + { + "epoch": 0.47, + "learning_rate": 1.2895293299682545e-05, + "loss": 1.5809, + "step": 4442 + }, + { + "epoch": 0.47, + "learning_rate": 1.289178962737235e-05, + "loss": 1.3436, + "step": 4443 + }, + { + "epoch": 0.47, + "learning_rate": 1.2888285567636647e-05, + "loss": 1.4535, + "step": 4444 + }, + { + "epoch": 0.47, + "learning_rate": 1.2884781120944889e-05, + "loss": 1.3377, + "step": 4445 + }, + { + "epoch": 0.47, + "learning_rate": 1.2881276287766587e-05, + "loss": 0.8221, + "step": 4446 + }, + { + "epoch": 0.47, + "learning_rate": 1.2877771068571288e-05, + "loss": 0.7259, + "step": 4447 + }, + { + "epoch": 0.47, + "learning_rate": 1.2874265463828612e-05, + "loss": 0.8279, + "step": 4448 + }, + { + "epoch": 0.47, + "learning_rate": 1.2870759474008213e-05, + "loss": 1.3523, + "step": 4449 + }, + { + "epoch": 0.47, + "learning_rate": 1.2867253099579808e-05, + "loss": 1.3658, + "step": 4450 + }, + { + "epoch": 0.47, + "learning_rate": 1.2863746341013158e-05, + "loss": 1.4112, + "step": 4451 + }, + { + "epoch": 0.47, + "learning_rate": 1.2860239198778085e-05, + "loss": 1.389, + "step": 4452 + }, + { + "epoch": 0.47, + "learning_rate": 1.2856731673344442e-05, + "loss": 1.4066, + "step": 4453 + }, + { + "epoch": 0.47, + "learning_rate": 1.2853223765182165e-05, + "loss": 1.3267, + "step": 4454 + }, + { + "epoch": 0.47, + "learning_rate": 1.2849715474761209e-05, + "loss": 1.3381, + "step": 4455 + }, + { + "epoch": 0.47, + "learning_rate": 1.2846206802551602e-05, + "loss": 1.2882, + "step": 4456 + }, + { + "epoch": 0.47, + "learning_rate": 1.2842697749023414e-05, + "loss": 1.3199, + "step": 4457 + }, + { + "epoch": 0.47, + "learning_rate": 1.2839188314646771e-05, + "loss": 1.3896, + "step": 4458 + }, + { + "epoch": 0.47, + "learning_rate": 1.2835678499891842e-05, + "loss": 1.3186, + "step": 4459 + }, + { + "epoch": 0.47, + "learning_rate": 1.283216830522885e-05, + "loss": 1.3466, + "step": 4460 + }, + { + "epoch": 0.47, + "learning_rate": 1.2828657731128083e-05, + "loss": 1.4678, + "step": 4461 + }, + { + "epoch": 0.47, + "learning_rate": 1.2825146778059857e-05, + "loss": 1.4408, + "step": 4462 + }, + { + "epoch": 0.47, + "learning_rate": 1.2821635446494553e-05, + "loss": 1.3672, + "step": 4463 + }, + { + "epoch": 0.47, + "learning_rate": 1.2818123736902597e-05, + "loss": 1.3836, + "step": 4464 + }, + { + "epoch": 0.47, + "learning_rate": 1.2814611649754472e-05, + "loss": 1.3493, + "step": 4465 + }, + { + "epoch": 0.47, + "learning_rate": 1.2811099185520704e-05, + "loss": 1.3584, + "step": 4466 + }, + { + "epoch": 0.47, + "learning_rate": 1.2807586344671875e-05, + "loss": 1.3551, + "step": 4467 + }, + { + "epoch": 0.47, + "learning_rate": 1.2804073127678612e-05, + "loss": 1.3254, + "step": 4468 + }, + { + "epoch": 0.47, + "learning_rate": 1.28005595350116e-05, + "loss": 1.3405, + "step": 4469 + }, + { + "epoch": 0.47, + "learning_rate": 1.2797045567141568e-05, + "loss": 1.3432, + "step": 4470 + }, + { + "epoch": 0.47, + "learning_rate": 1.2793531224539297e-05, + "loss": 1.4347, + "step": 4471 + }, + { + "epoch": 0.47, + "learning_rate": 1.279001650767562e-05, + "loss": 1.3304, + "step": 4472 + }, + { + "epoch": 0.47, + "learning_rate": 1.278650141702142e-05, + "loss": 1.3244, + "step": 4473 + }, + { + "epoch": 0.47, + "learning_rate": 1.2782985953047625e-05, + "loss": 1.3756, + "step": 4474 + }, + { + "epoch": 0.47, + "learning_rate": 1.2779470116225219e-05, + "loss": 1.5468, + "step": 4475 + }, + { + "epoch": 0.47, + "learning_rate": 1.2775953907025232e-05, + "loss": 1.4316, + "step": 4476 + }, + { + "epoch": 0.47, + "learning_rate": 1.2772437325918752e-05, + "loss": 1.3724, + "step": 4477 + }, + { + "epoch": 0.47, + "learning_rate": 1.27689203733769e-05, + "loss": 1.4458, + "step": 4478 + }, + { + "epoch": 0.47, + "learning_rate": 1.2765403049870865e-05, + "loss": 1.3622, + "step": 4479 + }, + { + "epoch": 0.47, + "learning_rate": 1.2761885355871875e-05, + "loss": 1.3875, + "step": 4480 + }, + { + "epoch": 0.47, + "learning_rate": 1.2758367291851217e-05, + "loss": 1.3577, + "step": 4481 + }, + { + "epoch": 0.47, + "learning_rate": 1.2754848858280211e-05, + "loss": 1.4256, + "step": 4482 + }, + { + "epoch": 0.47, + "learning_rate": 1.2751330055630242e-05, + "loss": 1.3771, + "step": 4483 + }, + { + "epoch": 0.47, + "learning_rate": 1.274781088437274e-05, + "loss": 1.357, + "step": 4484 + }, + { + "epoch": 0.47, + "learning_rate": 1.274429134497918e-05, + "loss": 1.3634, + "step": 4485 + }, + { + "epoch": 0.47, + "learning_rate": 1.2740771437921096e-05, + "loss": 1.3661, + "step": 4486 + }, + { + "epoch": 0.47, + "learning_rate": 1.2737251163670057e-05, + "loss": 1.3819, + "step": 4487 + }, + { + "epoch": 0.47, + "learning_rate": 1.2733730522697696e-05, + "loss": 1.4491, + "step": 4488 + }, + { + "epoch": 0.47, + "learning_rate": 1.2730209515475687e-05, + "loss": 1.3857, + "step": 4489 + }, + { + "epoch": 0.47, + "learning_rate": 1.2726688142475751e-05, + "loss": 1.3837, + "step": 4490 + }, + { + "epoch": 0.47, + "learning_rate": 1.2723166404169663e-05, + "loss": 1.3755, + "step": 4491 + }, + { + "epoch": 0.47, + "learning_rate": 1.271964430102925e-05, + "loss": 1.3767, + "step": 4492 + }, + { + "epoch": 0.47, + "learning_rate": 1.2716121833526376e-05, + "loss": 1.4416, + "step": 4493 + }, + { + "epoch": 0.47, + "learning_rate": 1.2712599002132966e-05, + "loss": 1.5573, + "step": 4494 + }, + { + "epoch": 0.47, + "learning_rate": 1.2709075807320988e-05, + "loss": 1.365, + "step": 4495 + }, + { + "epoch": 0.47, + "learning_rate": 1.270555224956246e-05, + "loss": 1.3862, + "step": 4496 + }, + { + "epoch": 0.47, + "learning_rate": 1.2702028329329445e-05, + "loss": 1.3003, + "step": 4497 + }, + { + "epoch": 0.47, + "learning_rate": 1.2698504047094064e-05, + "loss": 1.3806, + "step": 4498 + }, + { + "epoch": 0.47, + "learning_rate": 1.269497940332847e-05, + "loss": 1.5425, + "step": 4499 + }, + { + "epoch": 0.47, + "learning_rate": 1.269145439850489e-05, + "loss": 1.3541, + "step": 4500 + }, + { + "epoch": 0.47, + "learning_rate": 1.268792903309557e-05, + "loss": 1.4337, + "step": 4501 + }, + { + "epoch": 0.47, + "learning_rate": 1.2684403307572825e-05, + "loss": 1.4004, + "step": 4502 + }, + { + "epoch": 0.47, + "learning_rate": 1.268087722240901e-05, + "loss": 1.9453, + "step": 4503 + }, + { + "epoch": 0.47, + "learning_rate": 1.2677350778076532e-05, + "loss": 1.3907, + "step": 4504 + }, + { + "epoch": 0.47, + "learning_rate": 1.2673823975047839e-05, + "loss": 1.4993, + "step": 4505 + }, + { + "epoch": 0.47, + "learning_rate": 1.2670296813795432e-05, + "loss": 1.4386, + "step": 4506 + }, + { + "epoch": 0.47, + "learning_rate": 1.266676929479187e-05, + "loss": 1.4944, + "step": 4507 + }, + { + "epoch": 0.47, + "learning_rate": 1.266324141850974e-05, + "loss": 1.4311, + "step": 4508 + }, + { + "epoch": 0.47, + "learning_rate": 1.265971318542169e-05, + "loss": 1.3607, + "step": 4509 + }, + { + "epoch": 0.47, + "learning_rate": 1.2656184596000412e-05, + "loss": 1.4007, + "step": 4510 + }, + { + "epoch": 0.47, + "learning_rate": 1.2652655650718645e-05, + "loss": 1.4561, + "step": 4511 + }, + { + "epoch": 0.47, + "learning_rate": 1.2649126350049181e-05, + "loss": 1.4321, + "step": 4512 + }, + { + "epoch": 0.47, + "learning_rate": 1.2645596694464851e-05, + "loss": 1.2856, + "step": 4513 + }, + { + "epoch": 0.47, + "learning_rate": 1.2642066684438543e-05, + "loss": 1.3979, + "step": 4514 + }, + { + "epoch": 0.47, + "learning_rate": 1.2638536320443184e-05, + "loss": 1.4977, + "step": 4515 + }, + { + "epoch": 0.47, + "learning_rate": 1.2635005602951752e-05, + "loss": 1.377, + "step": 4516 + }, + { + "epoch": 0.47, + "learning_rate": 1.2631474532437275e-05, + "loss": 1.4266, + "step": 4517 + }, + { + "epoch": 0.47, + "learning_rate": 1.2627943109372822e-05, + "loss": 1.409, + "step": 4518 + }, + { + "epoch": 0.47, + "learning_rate": 1.2624411334231519e-05, + "loss": 1.3374, + "step": 4519 + }, + { + "epoch": 0.47, + "learning_rate": 1.2620879207486525e-05, + "loss": 1.3765, + "step": 4520 + }, + { + "epoch": 0.47, + "learning_rate": 1.2617346729611061e-05, + "loss": 1.3805, + "step": 4521 + }, + { + "epoch": 0.47, + "learning_rate": 1.2613813901078384e-05, + "loss": 1.3326, + "step": 4522 + }, + { + "epoch": 0.47, + "learning_rate": 1.2610280722361807e-05, + "loss": 1.3909, + "step": 4523 + }, + { + "epoch": 0.47, + "learning_rate": 1.260674719393468e-05, + "loss": 1.3815, + "step": 4524 + }, + { + "epoch": 0.47, + "learning_rate": 1.2603213316270409e-05, + "loss": 1.5589, + "step": 4525 + }, + { + "epoch": 0.47, + "learning_rate": 1.2599679089842437e-05, + "loss": 1.4416, + "step": 4526 + }, + { + "epoch": 0.47, + "learning_rate": 1.259614451512427e-05, + "loss": 1.3529, + "step": 4527 + }, + { + "epoch": 0.47, + "learning_rate": 1.2592609592589437e-05, + "loss": 1.3135, + "step": 4528 + }, + { + "epoch": 0.47, + "learning_rate": 1.2589074322711535e-05, + "loss": 1.4177, + "step": 4529 + }, + { + "epoch": 0.48, + "learning_rate": 1.25855387059642e-05, + "loss": 1.353, + "step": 4530 + }, + { + "epoch": 0.48, + "learning_rate": 1.2582002742821111e-05, + "loss": 1.431, + "step": 4531 + }, + { + "epoch": 0.48, + "learning_rate": 1.2578466433755998e-05, + "loss": 1.3803, + "step": 4532 + }, + { + "epoch": 0.48, + "learning_rate": 1.257492977924263e-05, + "loss": 1.3774, + "step": 4533 + }, + { + "epoch": 0.48, + "learning_rate": 1.2571392779754836e-05, + "loss": 1.4339, + "step": 4534 + }, + { + "epoch": 0.48, + "learning_rate": 1.256785543576648e-05, + "loss": 1.4097, + "step": 4535 + }, + { + "epoch": 0.48, + "learning_rate": 1.2564317747751473e-05, + "loss": 1.4223, + "step": 4536 + }, + { + "epoch": 0.48, + "learning_rate": 1.2560779716183775e-05, + "loss": 1.5148, + "step": 4537 + }, + { + "epoch": 0.48, + "learning_rate": 1.2557241341537394e-05, + "loss": 1.3547, + "step": 4538 + }, + { + "epoch": 0.48, + "learning_rate": 1.255370262428638e-05, + "loss": 1.393, + "step": 4539 + }, + { + "epoch": 0.48, + "learning_rate": 1.2550163564904829e-05, + "loss": 1.3312, + "step": 4540 + }, + { + "epoch": 0.48, + "learning_rate": 1.2546624163866882e-05, + "loss": 1.4193, + "step": 4541 + }, + { + "epoch": 0.48, + "learning_rate": 1.2543084421646735e-05, + "loss": 1.4161, + "step": 4542 + }, + { + "epoch": 0.48, + "learning_rate": 1.2539544338718614e-05, + "loss": 1.4224, + "step": 4543 + }, + { + "epoch": 0.48, + "learning_rate": 1.2536003915556805e-05, + "loss": 1.3484, + "step": 4544 + }, + { + "epoch": 0.48, + "learning_rate": 1.253246315263563e-05, + "loss": 1.4492, + "step": 4545 + }, + { + "epoch": 0.48, + "learning_rate": 1.2528922050429467e-05, + "loss": 1.3549, + "step": 4546 + }, + { + "epoch": 0.48, + "learning_rate": 1.252538060941272e-05, + "loss": 1.45, + "step": 4547 + }, + { + "epoch": 0.48, + "learning_rate": 1.2521838830059865e-05, + "loss": 1.3499, + "step": 4548 + }, + { + "epoch": 0.48, + "learning_rate": 1.2518296712845399e-05, + "loss": 1.3786, + "step": 4549 + }, + { + "epoch": 0.48, + "learning_rate": 1.2514754258243884e-05, + "loss": 1.3394, + "step": 4550 + }, + { + "epoch": 0.48, + "learning_rate": 1.2511211466729909e-05, + "loss": 1.2849, + "step": 4551 + }, + { + "epoch": 0.48, + "learning_rate": 1.250766833877812e-05, + "loss": 1.374, + "step": 4552 + }, + { + "epoch": 0.48, + "learning_rate": 1.2504124874863211e-05, + "loss": 1.3084, + "step": 4553 + }, + { + "epoch": 0.48, + "learning_rate": 1.2500581075459905e-05, + "loss": 1.3348, + "step": 4554 + }, + { + "epoch": 0.48, + "learning_rate": 1.249703694104299e-05, + "loss": 1.3797, + "step": 4555 + }, + { + "epoch": 0.48, + "learning_rate": 1.2493492472087279e-05, + "loss": 1.3371, + "step": 4556 + }, + { + "epoch": 0.48, + "learning_rate": 1.248994766906765e-05, + "loss": 1.3974, + "step": 4557 + }, + { + "epoch": 0.48, + "learning_rate": 1.2486402532459007e-05, + "loss": 1.388, + "step": 4558 + }, + { + "epoch": 0.48, + "learning_rate": 1.2482857062736313e-05, + "loss": 1.3619, + "step": 4559 + }, + { + "epoch": 0.48, + "learning_rate": 1.2479311260374565e-05, + "loss": 1.4123, + "step": 4560 + }, + { + "epoch": 0.48, + "learning_rate": 1.2475765125848814e-05, + "loss": 1.5485, + "step": 4561 + }, + { + "epoch": 0.48, + "learning_rate": 1.247221865963415e-05, + "loss": 1.4965, + "step": 4562 + }, + { + "epoch": 0.48, + "learning_rate": 1.2468671862205705e-05, + "loss": 1.4352, + "step": 4563 + }, + { + "epoch": 0.48, + "learning_rate": 1.246512473403866e-05, + "loss": 1.3935, + "step": 4564 + }, + { + "epoch": 0.48, + "learning_rate": 1.2461577275608243e-05, + "loss": 1.3798, + "step": 4565 + }, + { + "epoch": 0.48, + "learning_rate": 1.2458029487389718e-05, + "loss": 1.4039, + "step": 4566 + }, + { + "epoch": 0.48, + "learning_rate": 1.2454481369858397e-05, + "loss": 1.3723, + "step": 4567 + }, + { + "epoch": 0.48, + "learning_rate": 1.245093292348964e-05, + "loss": 1.3713, + "step": 4568 + }, + { + "epoch": 0.48, + "learning_rate": 1.2447384148758847e-05, + "loss": 1.4083, + "step": 4569 + }, + { + "epoch": 0.48, + "learning_rate": 1.244383504614146e-05, + "loss": 1.2811, + "step": 4570 + }, + { + "epoch": 0.48, + "learning_rate": 1.2440285616112968e-05, + "loss": 1.3509, + "step": 4571 + }, + { + "epoch": 0.48, + "learning_rate": 1.2436735859148905e-05, + "loss": 1.3481, + "step": 4572 + }, + { + "epoch": 0.48, + "learning_rate": 1.2433185775724847e-05, + "loss": 1.4168, + "step": 4573 + }, + { + "epoch": 0.48, + "learning_rate": 1.2429635366316418e-05, + "loss": 1.3671, + "step": 4574 + }, + { + "epoch": 0.48, + "learning_rate": 1.2426084631399271e-05, + "loss": 1.6514, + "step": 4575 + }, + { + "epoch": 0.48, + "learning_rate": 1.2422533571449123e-05, + "loss": 1.3564, + "step": 4576 + }, + { + "epoch": 0.48, + "learning_rate": 1.2418982186941721e-05, + "loss": 1.4586, + "step": 4577 + }, + { + "epoch": 0.48, + "eval_loss": 1.4425245523452759, + "eval_runtime": 77.3853, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 4577 + }, + { + "epoch": 0.48, + "learning_rate": 1.2415430478352858e-05, + "loss": 1.3922, + "step": 4578 + }, + { + "epoch": 0.48, + "learning_rate": 1.2411878446158374e-05, + "loss": 1.3903, + "step": 4579 + }, + { + "epoch": 0.48, + "learning_rate": 1.240832609083415e-05, + "loss": 1.3537, + "step": 4580 + }, + { + "epoch": 0.48, + "learning_rate": 1.2404773412856113e-05, + "loss": 1.356, + "step": 4581 + }, + { + "epoch": 0.48, + "learning_rate": 1.2401220412700223e-05, + "loss": 1.4483, + "step": 4582 + }, + { + "epoch": 0.48, + "learning_rate": 1.2397667090842496e-05, + "loss": 1.3926, + "step": 4583 + }, + { + "epoch": 0.48, + "learning_rate": 1.2394113447758986e-05, + "loss": 1.4816, + "step": 4584 + }, + { + "epoch": 0.48, + "learning_rate": 1.2390559483925788e-05, + "loss": 1.3742, + "step": 4585 + }, + { + "epoch": 0.48, + "learning_rate": 1.2387005199819044e-05, + "loss": 1.4476, + "step": 4586 + }, + { + "epoch": 0.48, + "learning_rate": 1.2383450595914932e-05, + "loss": 1.4029, + "step": 4587 + }, + { + "epoch": 0.48, + "learning_rate": 1.2379895672689683e-05, + "loss": 1.4797, + "step": 4588 + }, + { + "epoch": 0.48, + "learning_rate": 1.2376340430619565e-05, + "loss": 1.3366, + "step": 4589 + }, + { + "epoch": 0.48, + "learning_rate": 1.2372784870180885e-05, + "loss": 1.4226, + "step": 4590 + }, + { + "epoch": 0.48, + "learning_rate": 1.2369228991849997e-05, + "loss": 1.3668, + "step": 4591 + }, + { + "epoch": 0.48, + "learning_rate": 1.2365672796103305e-05, + "loss": 1.4932, + "step": 4592 + }, + { + "epoch": 0.48, + "learning_rate": 1.236211628341724e-05, + "loss": 1.4088, + "step": 4593 + }, + { + "epoch": 0.48, + "learning_rate": 1.2358559454268284e-05, + "loss": 1.3616, + "step": 4594 + }, + { + "epoch": 0.48, + "learning_rate": 1.2355002309132961e-05, + "loss": 1.4345, + "step": 4595 + }, + { + "epoch": 0.48, + "learning_rate": 1.2351444848487844e-05, + "loss": 1.4025, + "step": 4596 + }, + { + "epoch": 0.48, + "learning_rate": 1.2347887072809533e-05, + "loss": 1.3895, + "step": 4597 + }, + { + "epoch": 0.48, + "learning_rate": 1.2344328982574678e-05, + "loss": 1.3326, + "step": 4598 + }, + { + "epoch": 0.48, + "learning_rate": 1.234077057825998e-05, + "loss": 1.4249, + "step": 4599 + }, + { + "epoch": 0.48, + "learning_rate": 1.2337211860342167e-05, + "loss": 1.3649, + "step": 4600 + }, + { + "epoch": 0.48, + "learning_rate": 1.2333652829298016e-05, + "loss": 1.3831, + "step": 4601 + }, + { + "epoch": 0.48, + "learning_rate": 1.2330093485604346e-05, + "loss": 1.3748, + "step": 4602 + }, + { + "epoch": 0.48, + "learning_rate": 1.2326533829738022e-05, + "loss": 1.386, + "step": 4603 + }, + { + "epoch": 0.48, + "learning_rate": 1.2322973862175941e-05, + "loss": 1.3923, + "step": 4604 + }, + { + "epoch": 0.48, + "learning_rate": 1.2319413583395052e-05, + "loss": 1.3638, + "step": 4605 + }, + { + "epoch": 0.48, + "learning_rate": 1.2315852993872335e-05, + "loss": 1.3476, + "step": 4606 + }, + { + "epoch": 0.48, + "learning_rate": 1.2312292094084824e-05, + "loss": 1.3581, + "step": 4607 + }, + { + "epoch": 0.48, + "learning_rate": 1.2308730884509583e-05, + "loss": 1.3554, + "step": 4608 + }, + { + "epoch": 0.48, + "learning_rate": 1.2305169365623724e-05, + "loss": 1.3676, + "step": 4609 + }, + { + "epoch": 0.48, + "learning_rate": 1.2301607537904399e-05, + "loss": 1.24, + "step": 4610 + }, + { + "epoch": 0.48, + "learning_rate": 1.2298045401828803e-05, + "loss": 1.3295, + "step": 4611 + }, + { + "epoch": 0.48, + "learning_rate": 1.2294482957874169e-05, + "loss": 1.5684, + "step": 4612 + }, + { + "epoch": 0.48, + "learning_rate": 1.2290920206517774e-05, + "loss": 1.3403, + "step": 4613 + }, + { + "epoch": 0.48, + "learning_rate": 1.2287357148236933e-05, + "loss": 1.349, + "step": 4614 + }, + { + "epoch": 0.48, + "learning_rate": 1.2283793783509008e-05, + "loss": 1.4261, + "step": 4615 + }, + { + "epoch": 0.48, + "learning_rate": 1.2280230112811395e-05, + "loss": 1.322, + "step": 4616 + }, + { + "epoch": 0.48, + "learning_rate": 1.2276666136621538e-05, + "loss": 1.3399, + "step": 4617 + }, + { + "epoch": 0.48, + "learning_rate": 1.2273101855416912e-05, + "loss": 1.3878, + "step": 4618 + }, + { + "epoch": 0.48, + "learning_rate": 1.2269537269675044e-05, + "loss": 1.4733, + "step": 4619 + }, + { + "epoch": 0.48, + "learning_rate": 1.2265972379873497e-05, + "loss": 1.419, + "step": 4620 + }, + { + "epoch": 0.48, + "learning_rate": 1.226240718648987e-05, + "loss": 1.3918, + "step": 4621 + }, + { + "epoch": 0.48, + "learning_rate": 1.2258841690001815e-05, + "loss": 1.3398, + "step": 4622 + }, + { + "epoch": 0.48, + "learning_rate": 1.225527589088701e-05, + "loss": 1.4091, + "step": 4623 + }, + { + "epoch": 0.48, + "learning_rate": 1.2251709789623185e-05, + "loss": 1.3291, + "step": 4624 + }, + { + "epoch": 0.49, + "learning_rate": 1.2248143386688101e-05, + "loss": 1.4288, + "step": 4625 + }, + { + "epoch": 0.49, + "learning_rate": 1.224457668255957e-05, + "loss": 1.2942, + "step": 4626 + }, + { + "epoch": 0.49, + "learning_rate": 1.2241009677715437e-05, + "loss": 1.4014, + "step": 4627 + }, + { + "epoch": 0.49, + "learning_rate": 1.2237442372633586e-05, + "loss": 1.3823, + "step": 4628 + }, + { + "epoch": 0.49, + "learning_rate": 1.2233874767791945e-05, + "loss": 1.3556, + "step": 4629 + }, + { + "epoch": 0.49, + "learning_rate": 1.2230306863668485e-05, + "loss": 1.411, + "step": 4630 + }, + { + "epoch": 0.49, + "learning_rate": 1.2226738660741212e-05, + "loss": 1.4347, + "step": 4631 + }, + { + "epoch": 0.49, + "learning_rate": 1.2223170159488169e-05, + "loss": 1.3095, + "step": 4632 + }, + { + "epoch": 0.49, + "learning_rate": 1.221960136038745e-05, + "loss": 1.4272, + "step": 4633 + }, + { + "epoch": 0.49, + "learning_rate": 1.221603226391718e-05, + "loss": 1.367, + "step": 4634 + }, + { + "epoch": 0.49, + "learning_rate": 1.2212462870555523e-05, + "loss": 1.3357, + "step": 4635 + }, + { + "epoch": 0.49, + "learning_rate": 1.220889318078069e-05, + "loss": 1.3634, + "step": 4636 + }, + { + "epoch": 0.49, + "learning_rate": 1.2205323195070927e-05, + "loss": 1.4143, + "step": 4637 + }, + { + "epoch": 0.49, + "learning_rate": 1.2201752913904519e-05, + "loss": 1.4865, + "step": 4638 + }, + { + "epoch": 0.49, + "learning_rate": 1.2198182337759794e-05, + "loss": 1.451, + "step": 4639 + }, + { + "epoch": 0.49, + "learning_rate": 1.2194611467115116e-05, + "loss": 1.3953, + "step": 4640 + }, + { + "epoch": 0.49, + "learning_rate": 1.2191040302448887e-05, + "loss": 1.4099, + "step": 4641 + }, + { + "epoch": 0.49, + "learning_rate": 1.2187468844239559e-05, + "loss": 1.3338, + "step": 4642 + }, + { + "epoch": 0.49, + "learning_rate": 1.2183897092965609e-05, + "loss": 1.4392, + "step": 4643 + }, + { + "epoch": 0.49, + "learning_rate": 1.2180325049105559e-05, + "loss": 1.3196, + "step": 4644 + }, + { + "epoch": 0.49, + "learning_rate": 1.2176752713137977e-05, + "loss": 1.3727, + "step": 4645 + }, + { + "epoch": 0.49, + "learning_rate": 1.2173180085541464e-05, + "loss": 1.3118, + "step": 4646 + }, + { + "epoch": 0.49, + "learning_rate": 1.2169607166794655e-05, + "loss": 1.3695, + "step": 4647 + }, + { + "epoch": 0.49, + "learning_rate": 1.2166033957376231e-05, + "loss": 1.3568, + "step": 4648 + }, + { + "epoch": 0.49, + "learning_rate": 1.216246045776491e-05, + "loss": 1.3492, + "step": 4649 + }, + { + "epoch": 0.49, + "learning_rate": 1.2158886668439455e-05, + "loss": 1.3445, + "step": 4650 + }, + { + "epoch": 0.49, + "learning_rate": 1.2155312589878654e-05, + "loss": 1.3756, + "step": 4651 + }, + { + "epoch": 0.49, + "learning_rate": 1.2151738222561344e-05, + "loss": 1.3681, + "step": 4652 + }, + { + "epoch": 0.49, + "learning_rate": 1.2148163566966403e-05, + "loss": 1.4345, + "step": 4653 + }, + { + "epoch": 0.49, + "learning_rate": 1.2144588623572738e-05, + "loss": 1.5102, + "step": 4654 + }, + { + "epoch": 0.49, + "learning_rate": 1.2141013392859297e-05, + "loss": 1.3531, + "step": 4655 + }, + { + "epoch": 0.49, + "learning_rate": 1.2137437875305075e-05, + "loss": 1.3824, + "step": 4656 + }, + { + "epoch": 0.49, + "learning_rate": 1.2133862071389099e-05, + "loss": 1.4227, + "step": 4657 + }, + { + "epoch": 0.49, + "learning_rate": 1.2130285981590433e-05, + "loss": 1.3479, + "step": 4658 + }, + { + "epoch": 0.49, + "learning_rate": 1.2126709606388181e-05, + "loss": 1.381, + "step": 4659 + }, + { + "epoch": 0.49, + "learning_rate": 1.2123132946261485e-05, + "loss": 1.3847, + "step": 4660 + }, + { + "epoch": 0.49, + "learning_rate": 1.2119556001689527e-05, + "loss": 1.3549, + "step": 4661 + }, + { + "epoch": 0.49, + "learning_rate": 1.2115978773151527e-05, + "loss": 1.3754, + "step": 4662 + }, + { + "epoch": 0.49, + "learning_rate": 1.2112401261126736e-05, + "loss": 1.3329, + "step": 4663 + }, + { + "epoch": 0.49, + "learning_rate": 1.2108823466094453e-05, + "loss": 1.4228, + "step": 4664 + }, + { + "epoch": 0.49, + "learning_rate": 1.2105245388534013e-05, + "loss": 1.4138, + "step": 4665 + }, + { + "epoch": 0.49, + "learning_rate": 1.2101667028924782e-05, + "loss": 1.3538, + "step": 4666 + }, + { + "epoch": 0.49, + "learning_rate": 1.2098088387746168e-05, + "loss": 1.4848, + "step": 4667 + }, + { + "epoch": 0.49, + "learning_rate": 1.2094509465477619e-05, + "loss": 1.5719, + "step": 4668 + }, + { + "epoch": 0.49, + "learning_rate": 1.209093026259862e-05, + "loss": 1.3863, + "step": 4669 + }, + { + "epoch": 0.49, + "learning_rate": 1.2087350779588691e-05, + "loss": 1.4425, + "step": 4670 + }, + { + "epoch": 0.49, + "learning_rate": 1.2083771016927386e-05, + "loss": 1.3655, + "step": 4671 + }, + { + "epoch": 0.49, + "learning_rate": 1.208019097509431e-05, + "loss": 1.3629, + "step": 4672 + }, + { + "epoch": 0.49, + "learning_rate": 1.2076610654569092e-05, + "loss": 1.3849, + "step": 4673 + }, + { + "epoch": 0.49, + "learning_rate": 1.20730300558314e-05, + "loss": 1.3763, + "step": 4674 + }, + { + "epoch": 0.49, + "learning_rate": 1.2069449179360945e-05, + "loss": 1.5316, + "step": 4675 + }, + { + "epoch": 0.49, + "learning_rate": 1.2065868025637476e-05, + "loss": 1.2873, + "step": 4676 + }, + { + "epoch": 0.49, + "learning_rate": 1.2062286595140773e-05, + "loss": 1.3642, + "step": 4677 + }, + { + "epoch": 0.49, + "learning_rate": 1.2058704888350652e-05, + "loss": 1.3782, + "step": 4678 + }, + { + "epoch": 0.49, + "learning_rate": 1.2055122905746972e-05, + "loss": 1.4597, + "step": 4679 + }, + { + "epoch": 0.49, + "learning_rate": 1.205154064780963e-05, + "loss": 1.3952, + "step": 4680 + }, + { + "epoch": 0.49, + "learning_rate": 1.2047958115018554e-05, + "loss": 1.4012, + "step": 4681 + }, + { + "epoch": 0.49, + "learning_rate": 1.204437530785371e-05, + "loss": 1.3432, + "step": 4682 + }, + { + "epoch": 0.49, + "learning_rate": 1.2040792226795101e-05, + "loss": 1.4111, + "step": 4683 + }, + { + "epoch": 0.49, + "learning_rate": 1.2037208872322773e-05, + "loss": 1.4357, + "step": 4684 + }, + { + "epoch": 0.49, + "learning_rate": 1.2033625244916803e-05, + "loss": 1.3908, + "step": 4685 + }, + { + "epoch": 0.49, + "learning_rate": 1.2030041345057298e-05, + "loss": 1.3804, + "step": 4686 + }, + { + "epoch": 0.49, + "learning_rate": 1.2026457173224412e-05, + "loss": 1.4523, + "step": 4687 + }, + { + "epoch": 0.49, + "learning_rate": 1.2022872729898336e-05, + "loss": 1.4266, + "step": 4688 + }, + { + "epoch": 0.49, + "learning_rate": 1.201928801555929e-05, + "loss": 1.3345, + "step": 4689 + }, + { + "epoch": 0.49, + "learning_rate": 1.2015703030687532e-05, + "loss": 1.1714, + "step": 4690 + }, + { + "epoch": 0.49, + "learning_rate": 1.2012117775763361e-05, + "loss": 1.3899, + "step": 4691 + }, + { + "epoch": 0.49, + "learning_rate": 1.2008532251267109e-05, + "loss": 1.43, + "step": 4692 + }, + { + "epoch": 0.49, + "learning_rate": 1.2004946457679144e-05, + "loss": 1.4302, + "step": 4693 + }, + { + "epoch": 0.49, + "learning_rate": 1.2001360395479865e-05, + "loss": 1.3452, + "step": 4694 + }, + { + "epoch": 0.49, + "learning_rate": 1.1997774065149716e-05, + "loss": 1.3383, + "step": 4695 + }, + { + "epoch": 0.49, + "learning_rate": 1.1994187467169176e-05, + "loss": 1.3677, + "step": 4696 + }, + { + "epoch": 0.49, + "learning_rate": 1.1990600602018755e-05, + "loss": 1.4486, + "step": 4697 + }, + { + "epoch": 0.49, + "learning_rate": 1.1987013470178998e-05, + "loss": 1.4059, + "step": 4698 + }, + { + "epoch": 0.49, + "learning_rate": 1.198342607213049e-05, + "loss": 1.3558, + "step": 4699 + }, + { + "epoch": 0.49, + "learning_rate": 1.1979838408353854e-05, + "loss": 1.3931, + "step": 4700 + }, + { + "epoch": 0.49, + "learning_rate": 1.197625047932974e-05, + "loss": 1.5409, + "step": 4701 + }, + { + "epoch": 0.49, + "learning_rate": 1.197266228553884e-05, + "loss": 1.4878, + "step": 4702 + }, + { + "epoch": 0.49, + "learning_rate": 1.196907382746188e-05, + "loss": 1.3581, + "step": 4703 + }, + { + "epoch": 0.49, + "learning_rate": 1.1965485105579621e-05, + "loss": 1.3617, + "step": 4704 + }, + { + "epoch": 0.49, + "learning_rate": 1.1961896120372857e-05, + "loss": 1.399, + "step": 4705 + }, + { + "epoch": 0.49, + "learning_rate": 1.1958306872322425e-05, + "loss": 1.3861, + "step": 4706 + }, + { + "epoch": 0.49, + "learning_rate": 1.1954717361909186e-05, + "loss": 1.4719, + "step": 4707 + }, + { + "epoch": 0.49, + "learning_rate": 1.195112758961405e-05, + "loss": 1.393, + "step": 4708 + }, + { + "epoch": 0.49, + "learning_rate": 1.1947537555917947e-05, + "loss": 1.4252, + "step": 4709 + }, + { + "epoch": 0.49, + "learning_rate": 1.194394726130185e-05, + "loss": 1.4187, + "step": 4710 + }, + { + "epoch": 0.49, + "learning_rate": 1.1940356706246772e-05, + "loss": 1.4822, + "step": 4711 + }, + { + "epoch": 0.49, + "learning_rate": 1.193676589123375e-05, + "loss": 1.4259, + "step": 4712 + }, + { + "epoch": 0.49, + "learning_rate": 1.1933174816743857e-05, + "loss": 1.4226, + "step": 4713 + }, + { + "epoch": 0.49, + "learning_rate": 1.1929583483258216e-05, + "loss": 1.3701, + "step": 4714 + }, + { + "epoch": 0.49, + "learning_rate": 1.1925991891257967e-05, + "loss": 1.406, + "step": 4715 + }, + { + "epoch": 0.49, + "learning_rate": 1.1922400041224288e-05, + "loss": 1.4593, + "step": 4716 + }, + { + "epoch": 0.49, + "learning_rate": 1.1918807933638401e-05, + "loss": 1.3443, + "step": 4717 + }, + { + "epoch": 0.49, + "learning_rate": 1.1915215568981552e-05, + "loss": 1.3523, + "step": 4718 + }, + { + "epoch": 0.49, + "learning_rate": 1.1911622947735027e-05, + "loss": 1.3175, + "step": 4719 + }, + { + "epoch": 0.49, + "learning_rate": 1.1908030070380143e-05, + "loss": 1.3974, + "step": 4720 + }, + { + "epoch": 0.5, + "learning_rate": 1.1904436937398257e-05, + "loss": 1.386, + "step": 4721 + }, + { + "epoch": 0.5, + "learning_rate": 1.1900843549270753e-05, + "loss": 1.3684, + "step": 4722 + }, + { + "epoch": 0.5, + "learning_rate": 1.1897249906479054e-05, + "loss": 1.383, + "step": 4723 + }, + { + "epoch": 0.5, + "learning_rate": 1.1893656009504617e-05, + "loss": 1.38, + "step": 4724 + }, + { + "epoch": 0.5, + "learning_rate": 1.1890061858828928e-05, + "loss": 1.3844, + "step": 4725 + }, + { + "epoch": 0.5, + "learning_rate": 1.1886467454933515e-05, + "loss": 1.3252, + "step": 4726 + }, + { + "epoch": 0.5, + "learning_rate": 1.1882872798299934e-05, + "loss": 1.3434, + "step": 4727 + }, + { + "epoch": 0.5, + "learning_rate": 1.1879277889409779e-05, + "loss": 1.4115, + "step": 4728 + }, + { + "epoch": 0.5, + "learning_rate": 1.1875682728744669e-05, + "loss": 1.1911, + "step": 4729 + }, + { + "epoch": 0.5, + "learning_rate": 1.1872087316786272e-05, + "loss": 1.2794, + "step": 4730 + }, + { + "epoch": 0.5, + "learning_rate": 1.1868491654016274e-05, + "loss": 1.3961, + "step": 4731 + }, + { + "epoch": 0.5, + "learning_rate": 1.1864895740916404e-05, + "loss": 1.4965, + "step": 4732 + }, + { + "epoch": 0.5, + "learning_rate": 1.1861299577968419e-05, + "loss": 1.3932, + "step": 4733 + }, + { + "epoch": 0.5, + "learning_rate": 1.185770316565412e-05, + "loss": 1.3926, + "step": 4734 + }, + { + "epoch": 0.5, + "learning_rate": 1.1854106504455327e-05, + "loss": 1.3964, + "step": 4735 + }, + { + "epoch": 0.5, + "learning_rate": 1.1850509594853901e-05, + "loss": 1.3666, + "step": 4736 + }, + { + "epoch": 0.5, + "learning_rate": 1.1846912437331736e-05, + "loss": 1.4364, + "step": 4737 + }, + { + "epoch": 0.5, + "learning_rate": 1.1843315032370762e-05, + "loss": 1.3537, + "step": 4738 + }, + { + "epoch": 0.5, + "learning_rate": 1.1839717380452935e-05, + "loss": 1.4083, + "step": 4739 + }, + { + "epoch": 0.5, + "learning_rate": 1.1836119482060247e-05, + "loss": 1.3881, + "step": 4740 + }, + { + "epoch": 0.5, + "learning_rate": 1.1832521337674727e-05, + "loss": 1.4127, + "step": 4741 + }, + { + "epoch": 0.5, + "learning_rate": 1.1828922947778436e-05, + "loss": 1.3433, + "step": 4742 + }, + { + "epoch": 0.5, + "learning_rate": 1.1825324312853461e-05, + "loss": 1.486, + "step": 4743 + }, + { + "epoch": 0.5, + "learning_rate": 1.1821725433381925e-05, + "loss": 1.335, + "step": 4744 + }, + { + "epoch": 0.5, + "learning_rate": 1.1818126309845993e-05, + "loss": 1.3827, + "step": 4745 + }, + { + "epoch": 0.5, + "learning_rate": 1.181452694272785e-05, + "loss": 1.3146, + "step": 4746 + }, + { + "epoch": 0.5, + "learning_rate": 1.1810927332509717e-05, + "loss": 1.3543, + "step": 4747 + }, + { + "epoch": 0.5, + "learning_rate": 1.1807327479673852e-05, + "loss": 1.3544, + "step": 4748 + }, + { + "epoch": 0.5, + "learning_rate": 1.1803727384702543e-05, + "loss": 1.3677, + "step": 4749 + }, + { + "epoch": 0.5, + "learning_rate": 1.1800127048078111e-05, + "loss": 1.3842, + "step": 4750 + }, + { + "epoch": 0.5, + "learning_rate": 1.1796526470282907e-05, + "loss": 1.3495, + "step": 4751 + }, + { + "epoch": 0.5, + "learning_rate": 1.1792925651799314e-05, + "loss": 1.481, + "step": 4752 + }, + { + "epoch": 0.5, + "learning_rate": 1.1789324593109754e-05, + "loss": 1.3482, + "step": 4753 + }, + { + "epoch": 0.5, + "learning_rate": 1.1785723294696673e-05, + "loss": 1.2805, + "step": 4754 + }, + { + "epoch": 0.5, + "learning_rate": 1.1782121757042555e-05, + "loss": 1.3458, + "step": 4755 + }, + { + "epoch": 0.5, + "learning_rate": 1.1778519980629907e-05, + "loss": 1.3937, + "step": 4756 + }, + { + "epoch": 0.5, + "learning_rate": 1.1774917965941284e-05, + "loss": 1.3873, + "step": 4757 + }, + { + "epoch": 0.5, + "learning_rate": 1.1771315713459258e-05, + "loss": 1.3512, + "step": 4758 + }, + { + "epoch": 0.5, + "learning_rate": 1.1767713223666436e-05, + "loss": 1.4465, + "step": 4759 + }, + { + "epoch": 0.5, + "learning_rate": 1.1764110497045463e-05, + "loss": 1.4233, + "step": 4760 + }, + { + "epoch": 0.5, + "learning_rate": 1.1760507534079011e-05, + "loss": 1.4818, + "step": 4761 + }, + { + "epoch": 0.5, + "learning_rate": 1.1756904335249786e-05, + "loss": 1.2933, + "step": 4762 + }, + { + "epoch": 0.5, + "learning_rate": 1.1753300901040518e-05, + "loss": 1.3524, + "step": 4763 + }, + { + "epoch": 0.5, + "learning_rate": 1.1749697231933981e-05, + "loss": 1.4909, + "step": 4764 + }, + { + "epoch": 0.5, + "learning_rate": 1.1746093328412975e-05, + "loss": 1.2912, + "step": 4765 + }, + { + "epoch": 0.5, + "learning_rate": 1.1742489190960325e-05, + "loss": 1.3372, + "step": 4766 + }, + { + "epoch": 0.5, + "learning_rate": 1.1738884820058893e-05, + "loss": 1.3036, + "step": 4767 + }, + { + "epoch": 0.5, + "learning_rate": 1.1735280216191578e-05, + "loss": 1.3189, + "step": 4768 + }, + { + "epoch": 0.5, + "learning_rate": 1.1731675379841298e-05, + "loss": 1.4146, + "step": 4769 + }, + { + "epoch": 0.5, + "learning_rate": 1.1728070311491013e-05, + "loss": 1.3309, + "step": 4770 + }, + { + "epoch": 0.5, + "learning_rate": 1.1724465011623705e-05, + "loss": 1.3427, + "step": 4771 + }, + { + "epoch": 0.5, + "learning_rate": 1.1720859480722395e-05, + "loss": 1.4033, + "step": 4772 + }, + { + "epoch": 0.5, + "learning_rate": 1.1717253719270135e-05, + "loss": 1.3832, + "step": 4773 + }, + { + "epoch": 0.5, + "learning_rate": 1.1713647727749994e-05, + "loss": 1.4074, + "step": 4774 + }, + { + "epoch": 0.5, + "learning_rate": 1.1710041506645092e-05, + "loss": 1.3579, + "step": 4775 + }, + { + "epoch": 0.5, + "learning_rate": 1.1706435056438564e-05, + "loss": 1.3685, + "step": 4776 + }, + { + "epoch": 0.5, + "eval_loss": 1.436767816543579, + "eval_runtime": 77.4332, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4776 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 2.1366107087671237e+20, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-4776/training_args.bin b/checkpoint-4776/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-4776/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-5174/config.json b/checkpoint-5174/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-5174/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-5174/generation_config.json b/checkpoint-5174/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-5174/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-5174/model-00001-of-00003.safetensors b/checkpoint-5174/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f731b0d926ff691b5b43ba5984cc77db2a57b700 --- /dev/null +++ b/checkpoint-5174/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ec1aec8696620b4c2315b094211cb9c7e19592f4ee1d352c581cc4cdad87173 +size 4943162336 diff --git a/checkpoint-5174/model-00002-of-00003.safetensors b/checkpoint-5174/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a08cf8e6a3a1b4ba7aa27fe0256d00a917eb6c55 --- /dev/null +++ b/checkpoint-5174/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83212938ac2a762c1353612521246d6b787fcd736b8a1e15a227fe2ee17a642e +size 4999819336 diff --git a/checkpoint-5174/model-00003-of-00003.safetensors b/checkpoint-5174/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5d36ccf6a4d0ea0cd0c5438c0a0374f9ffc8bdcf --- /dev/null +++ b/checkpoint-5174/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e0d185e905b9c6cefc81d9f89e2c3223b5743284ef8f562dd2d025cbe725fc5 +size 4540516344 diff --git a/checkpoint-5174/model.safetensors.index.json b/checkpoint-5174/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-5174/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-5174/optimizer.pt b/checkpoint-5174/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..5937b6330a9216ad7aa97008858d7e2d23ad10f5 --- /dev/null +++ b/checkpoint-5174/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:894844cd8b31f8e709bf012dd8017d43a7eecc69c89e48e1c79d95e859d36c0d +size 14512103560 diff --git a/checkpoint-5174/rng_state_0.pth b/checkpoint-5174/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..86408ca0126a2007b1f688d7134272139235668f --- /dev/null +++ b/checkpoint-5174/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c49abc3bdedbec1fc8e1028ef422150f19ee7470d7b542e1ad8869fc044d2af +size 15984 diff --git a/checkpoint-5174/rng_state_1.pth b/checkpoint-5174/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..da431e21281a617214b25ac268116ced796e57a1 --- /dev/null +++ b/checkpoint-5174/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df12ca4106ff0831785a55b5da88f6c86f6f67bd3d09b2dced4f20b539b14f72 +size 15984 diff --git a/checkpoint-5174/rng_state_2.pth b/checkpoint-5174/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..3ff6bb2b9de93faafadd32d778abfbbeac092706 --- /dev/null +++ b/checkpoint-5174/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05fc0786faff729a3a1582f98b806b68d4f0b76aebb25cbad4431b73176b11c1 +size 15984 diff --git a/checkpoint-5174/rng_state_3.pth b/checkpoint-5174/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..c53a40a8335108bdab972cbb3a28247571563d5b --- /dev/null +++ b/checkpoint-5174/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3117e1218a2dd3f7f8c516a840af48f6b93660d852cca124269f78c21f8577c +size 15984 diff --git a/checkpoint-5174/rng_state_4.pth b/checkpoint-5174/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..c1b8b8773c31bcf3a1235ba9a7f9beef664cdd1b --- /dev/null +++ b/checkpoint-5174/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdaa30c82476bf6a65e4eb9ca2ae7b95f1b38f41a6f5b2f1cbdda9af86a4a7a0 +size 15984 diff --git a/checkpoint-5174/rng_state_5.pth b/checkpoint-5174/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..79bf075b2e11d7bd06559c8bffb7735f376bf7e0 --- /dev/null +++ b/checkpoint-5174/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09cdde6931807139efa184e8a98108b74bb05730bc511336966b254b68dc93ee +size 15984 diff --git a/checkpoint-5174/rng_state_6.pth b/checkpoint-5174/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..917d5d872d05ef6e2f260f02ac532661ffb6e49e --- /dev/null +++ b/checkpoint-5174/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a2268136932c55b3857d38c7cf3fc4bd3cdad532c156b9addebc6d26374374a +size 15984 diff --git a/checkpoint-5174/rng_state_7.pth b/checkpoint-5174/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..50f09fc27b6e9049c9efc08bd1ffe08625e3d5dc --- /dev/null +++ b/checkpoint-5174/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56cd9a502015b79e0ab94c92a04bd96c99aaf79ef8d64bf81d81eb702c10c2a8 +size 15984 diff --git a/checkpoint-5174/scheduler.pt b/checkpoint-5174/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..b3be9b4eca70aaf62616d0f6ebd5557ade404669 --- /dev/null +++ b/checkpoint-5174/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8075791c70d13276e27fd92724c22709bdab19c1281341aeef3de8f0994f7ffd +size 1064 diff --git a/checkpoint-5174/special_tokens_map.json b/checkpoint-5174/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-5174/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-5174/tokenizer.model b/checkpoint-5174/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-5174/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-5174/tokenizer_config.json b/checkpoint-5174/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-5174/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-5174/trainer_state.json b/checkpoint-5174/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..766a17410c525cc7e020dc3a9b69faf65abdece8 --- /dev/null +++ b/checkpoint-5174/trainer_state.json @@ -0,0 +1,31272 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.5425755033557047, + "eval_steps": 199, + "global_step": 5174, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + }, + { + "epoch": 0.21, + "learning_rate": 1.928689129323009e-05, + "loss": 1.421, + "step": 1991 + }, + { + "epoch": 0.21, + "learning_rate": 1.928553323396003e-05, + "loss": 1.5625, + "step": 1992 + }, + { + "epoch": 0.21, + "learning_rate": 1.92841739306671e-05, + "loss": 1.5198, + "step": 1993 + }, + { + "epoch": 0.21, + "learning_rate": 1.9282813383533415e-05, + "loss": 1.5116, + "step": 1994 + }, + { + "epoch": 0.21, + "learning_rate": 1.9281451592741247e-05, + "loss": 1.4306, + "step": 1995 + }, + { + "epoch": 0.21, + "learning_rate": 1.9280088558473046e-05, + "loss": 1.5425, + "step": 1996 + }, + { + "epoch": 0.21, + "learning_rate": 1.9278724280911424e-05, + "loss": 1.4972, + "step": 1997 + }, + { + "epoch": 0.21, + "learning_rate": 1.9277358760239156e-05, + "loss": 1.5185, + "step": 1998 + }, + { + "epoch": 0.21, + "learning_rate": 1.9275991996639188e-05, + "loss": 1.5187, + "step": 1999 + }, + { + "epoch": 0.21, + "learning_rate": 1.927462399029463e-05, + "loss": 1.4325, + "step": 2000 + }, + { + "epoch": 0.21, + "learning_rate": 1.9273254741388763e-05, + "loss": 1.4397, + "step": 2001 + }, + { + "epoch": 0.21, + "learning_rate": 1.927188425010503e-05, + "loss": 1.5319, + "step": 2002 + }, + { + "epoch": 0.21, + "learning_rate": 1.9270512516627042e-05, + "loss": 1.5664, + "step": 2003 + }, + { + "epoch": 0.21, + "learning_rate": 1.9269139541138574e-05, + "loss": 1.5227, + "step": 2004 + }, + { + "epoch": 0.21, + "learning_rate": 1.926776532382357e-05, + "loss": 1.5187, + "step": 2005 + }, + { + "epoch": 0.21, + "learning_rate": 1.9266389864866134e-05, + "loss": 1.4029, + "step": 2006 + }, + { + "epoch": 0.21, + "learning_rate": 1.9265013164450557e-05, + "loss": 1.387, + "step": 2007 + }, + { + "epoch": 0.21, + "learning_rate": 1.9263635222761268e-05, + "loss": 1.5047, + "step": 2008 + }, + { + "epoch": 0.21, + "learning_rate": 1.9262256039982882e-05, + "loss": 1.4816, + "step": 2009 + }, + { + "epoch": 0.21, + "learning_rate": 1.9260875616300172e-05, + "loss": 1.4607, + "step": 2010 + }, + { + "epoch": 0.21, + "learning_rate": 1.9259493951898084e-05, + "loss": 1.628, + "step": 2011 + }, + { + "epoch": 0.21, + "learning_rate": 1.9258111046961714e-05, + "loss": 1.4149, + "step": 2012 + }, + { + "epoch": 0.21, + "learning_rate": 1.925672690167635e-05, + "loss": 1.5303, + "step": 2013 + }, + { + "epoch": 0.21, + "learning_rate": 1.925534151622742e-05, + "loss": 1.5198, + "step": 2014 + }, + { + "epoch": 0.21, + "learning_rate": 1.9253954890800535e-05, + "loss": 1.6422, + "step": 2015 + }, + { + "epoch": 0.21, + "learning_rate": 1.925256702558147e-05, + "loss": 1.4738, + "step": 2016 + }, + { + "epoch": 0.21, + "learning_rate": 1.925117792075616e-05, + "loss": 1.4752, + "step": 2017 + }, + { + "epoch": 0.21, + "learning_rate": 1.9249787576510713e-05, + "loss": 1.4547, + "step": 2018 + }, + { + "epoch": 0.21, + "learning_rate": 1.924839599303139e-05, + "loss": 1.4864, + "step": 2019 + }, + { + "epoch": 0.21, + "learning_rate": 1.9247003170504638e-05, + "loss": 1.5037, + "step": 2020 + }, + { + "epoch": 0.21, + "learning_rate": 1.9245609109117053e-05, + "loss": 1.5089, + "step": 2021 + }, + { + "epoch": 0.21, + "learning_rate": 1.924421380905541e-05, + "loss": 1.5616, + "step": 2022 + }, + { + "epoch": 0.21, + "learning_rate": 1.9242817270506634e-05, + "loss": 1.4592, + "step": 2023 + }, + { + "epoch": 0.21, + "learning_rate": 1.9241419493657832e-05, + "loss": 1.5592, + "step": 2024 + }, + { + "epoch": 0.21, + "learning_rate": 1.924002047869627e-05, + "loss": 1.4897, + "step": 2025 + }, + { + "epoch": 0.21, + "learning_rate": 1.9238620225809375e-05, + "loss": 1.4743, + "step": 2026 + }, + { + "epoch": 0.21, + "learning_rate": 1.923721873518475e-05, + "loss": 1.4686, + "step": 2027 + }, + { + "epoch": 0.21, + "learning_rate": 1.923581600701016e-05, + "loss": 1.461, + "step": 2028 + }, + { + "epoch": 0.21, + "learning_rate": 1.9234412041473528e-05, + "loss": 1.6622, + "step": 2029 + }, + { + "epoch": 0.21, + "learning_rate": 1.9233006838762955e-05, + "loss": 1.4707, + "step": 2030 + }, + { + "epoch": 0.21, + "learning_rate": 1.92316003990667e-05, + "loss": 1.5566, + "step": 2031 + }, + { + "epoch": 0.21, + "learning_rate": 1.9230192722573188e-05, + "loss": 1.4881, + "step": 2032 + }, + { + "epoch": 0.21, + "learning_rate": 1.9228783809471015e-05, + "loss": 1.6124, + "step": 2033 + }, + { + "epoch": 0.21, + "learning_rate": 1.9227373659948937e-05, + "loss": 1.3508, + "step": 2034 + }, + { + "epoch": 0.21, + "learning_rate": 1.9225962274195876e-05, + "loss": 1.4418, + "step": 2035 + }, + { + "epoch": 0.21, + "learning_rate": 1.9224549652400927e-05, + "loss": 1.3954, + "step": 2036 + }, + { + "epoch": 0.21, + "learning_rate": 1.922313579475334e-05, + "loss": 1.4798, + "step": 2037 + }, + { + "epoch": 0.21, + "learning_rate": 1.922172070144254e-05, + "loss": 1.4556, + "step": 2038 + }, + { + "epoch": 0.21, + "learning_rate": 1.922030437265811e-05, + "loss": 1.4987, + "step": 2039 + }, + { + "epoch": 0.21, + "learning_rate": 1.9218886808589796e-05, + "loss": 1.4857, + "step": 2040 + }, + { + "epoch": 0.21, + "learning_rate": 1.9217468009427527e-05, + "loss": 1.5289, + "step": 2041 + }, + { + "epoch": 0.21, + "learning_rate": 1.921604797536138e-05, + "loss": 1.5267, + "step": 2042 + }, + { + "epoch": 0.21, + "learning_rate": 1.9214626706581598e-05, + "loss": 1.4655, + "step": 2043 + }, + { + "epoch": 0.21, + "learning_rate": 1.9213204203278602e-05, + "loss": 1.4598, + "step": 2044 + }, + { + "epoch": 0.21, + "learning_rate": 1.9211780465642973e-05, + "loss": 1.4766, + "step": 2045 + }, + { + "epoch": 0.21, + "learning_rate": 1.921035549386545e-05, + "loss": 1.5148, + "step": 2046 + }, + { + "epoch": 0.21, + "learning_rate": 1.9208929288136933e-05, + "loss": 1.5567, + "step": 2047 + }, + { + "epoch": 0.21, + "learning_rate": 1.920750184864852e-05, + "loss": 1.4868, + "step": 2048 + }, + { + "epoch": 0.21, + "learning_rate": 1.920607317559143e-05, + "loss": 1.4752, + "step": 2049 + }, + { + "epoch": 0.21, + "learning_rate": 1.920464326915708e-05, + "loss": 1.4882, + "step": 2050 + }, + { + "epoch": 0.22, + "learning_rate": 1.9203212129537035e-05, + "loss": 1.5933, + "step": 2051 + }, + { + "epoch": 0.22, + "learning_rate": 1.9201779756923037e-05, + "loss": 1.4891, + "step": 2052 + }, + { + "epoch": 0.22, + "learning_rate": 1.9200346151506983e-05, + "loss": 1.4486, + "step": 2053 + }, + { + "epoch": 0.22, + "learning_rate": 1.9198911313480938e-05, + "loss": 1.5091, + "step": 2054 + }, + { + "epoch": 0.22, + "learning_rate": 1.919747524303714e-05, + "loss": 1.4385, + "step": 2055 + }, + { + "epoch": 0.22, + "learning_rate": 1.9196037940367974e-05, + "loss": 1.4104, + "step": 2056 + }, + { + "epoch": 0.22, + "learning_rate": 1.9194599405666015e-05, + "loss": 1.4483, + "step": 2057 + }, + { + "epoch": 0.22, + "learning_rate": 1.9193159639123976e-05, + "loss": 1.4592, + "step": 2058 + }, + { + "epoch": 0.22, + "learning_rate": 1.919171864093476e-05, + "loss": 1.4975, + "step": 2059 + }, + { + "epoch": 0.22, + "learning_rate": 1.9190276411291423e-05, + "loss": 1.4727, + "step": 2060 + }, + { + "epoch": 0.22, + "learning_rate": 1.9188832950387178e-05, + "loss": 1.4791, + "step": 2061 + }, + { + "epoch": 0.22, + "learning_rate": 1.9187388258415423e-05, + "loss": 1.3806, + "step": 2062 + }, + { + "epoch": 0.22, + "learning_rate": 1.9185942335569697e-05, + "loss": 1.4514, + "step": 2063 + }, + { + "epoch": 0.22, + "learning_rate": 1.9184495182043727e-05, + "loss": 1.4389, + "step": 2064 + }, + { + "epoch": 0.22, + "learning_rate": 1.918304679803139e-05, + "loss": 1.5088, + "step": 2065 + }, + { + "epoch": 0.22, + "learning_rate": 1.9181597183726733e-05, + "loss": 1.4665, + "step": 2066 + }, + { + "epoch": 0.22, + "learning_rate": 1.9180146339323966e-05, + "loss": 1.489, + "step": 2067 + }, + { + "epoch": 0.22, + "learning_rate": 1.9178694265017466e-05, + "loss": 1.5215, + "step": 2068 + }, + { + "epoch": 0.22, + "learning_rate": 1.9177240961001775e-05, + "loss": 1.5152, + "step": 2069 + }, + { + "epoch": 0.22, + "learning_rate": 1.9175786427471594e-05, + "loss": 1.4418, + "step": 2070 + }, + { + "epoch": 0.22, + "learning_rate": 1.91743306646218e-05, + "loss": 1.5001, + "step": 2071 + }, + { + "epoch": 0.22, + "learning_rate": 1.9172873672647417e-05, + "loss": 1.4879, + "step": 2072 + }, + { + "epoch": 0.22, + "learning_rate": 1.917141545174366e-05, + "loss": 1.5299, + "step": 2073 + }, + { + "epoch": 0.22, + "learning_rate": 1.9169956002105877e-05, + "loss": 1.4602, + "step": 2074 + }, + { + "epoch": 0.22, + "learning_rate": 1.9168495323929605e-05, + "loss": 1.4921, + "step": 2075 + }, + { + "epoch": 0.22, + "learning_rate": 1.916703341741054e-05, + "loss": 1.4659, + "step": 2076 + }, + { + "epoch": 0.22, + "learning_rate": 1.9165570282744534e-05, + "loss": 1.4707, + "step": 2077 + }, + { + "epoch": 0.22, + "learning_rate": 1.9164105920127613e-05, + "loss": 1.5354, + "step": 2078 + }, + { + "epoch": 0.22, + "learning_rate": 1.9162640329755962e-05, + "loss": 1.526, + "step": 2079 + }, + { + "epoch": 0.22, + "learning_rate": 1.916117351182593e-05, + "loss": 1.6424, + "step": 2080 + }, + { + "epoch": 0.22, + "learning_rate": 1.915970546653404e-05, + "loss": 1.5048, + "step": 2081 + }, + { + "epoch": 0.22, + "learning_rate": 1.915823619407697e-05, + "loss": 1.5344, + "step": 2082 + }, + { + "epoch": 0.22, + "learning_rate": 1.915676569465156e-05, + "loss": 1.4604, + "step": 2083 + }, + { + "epoch": 0.22, + "learning_rate": 1.9155293968454826e-05, + "loss": 1.4929, + "step": 2084 + }, + { + "epoch": 0.22, + "learning_rate": 1.9153821015683937e-05, + "loss": 1.4106, + "step": 2085 + }, + { + "epoch": 0.22, + "learning_rate": 1.915234683653623e-05, + "loss": 1.4146, + "step": 2086 + }, + { + "epoch": 0.22, + "learning_rate": 1.9150871431209207e-05, + "loss": 1.4481, + "step": 2087 + }, + { + "epoch": 0.22, + "learning_rate": 1.914939479990054e-05, + "loss": 1.5206, + "step": 2088 + }, + { + "epoch": 0.22, + "learning_rate": 1.9147916942808054e-05, + "loss": 1.5073, + "step": 2089 + }, + { + "epoch": 0.22, + "learning_rate": 1.9146437860129745e-05, + "loss": 1.5196, + "step": 2090 + }, + { + "epoch": 0.22, + "learning_rate": 1.9144957552063775e-05, + "loss": 1.5389, + "step": 2091 + }, + { + "epoch": 0.22, + "learning_rate": 1.9143476018808463e-05, + "loss": 1.5207, + "step": 2092 + }, + { + "epoch": 0.22, + "learning_rate": 1.9141993260562298e-05, + "loss": 1.3717, + "step": 2093 + }, + { + "epoch": 0.22, + "learning_rate": 1.9140509277523937e-05, + "loss": 1.471, + "step": 2094 + }, + { + "epoch": 0.22, + "learning_rate": 1.9139024069892185e-05, + "loss": 1.4553, + "step": 2095 + }, + { + "epoch": 0.22, + "learning_rate": 1.9137537637866027e-05, + "loss": 1.5311, + "step": 2096 + }, + { + "epoch": 0.22, + "learning_rate": 1.9136049981644614e-05, + "loss": 1.4369, + "step": 2097 + }, + { + "epoch": 0.22, + "learning_rate": 1.913456110142724e-05, + "loss": 1.4528, + "step": 2098 + }, + { + "epoch": 0.22, + "learning_rate": 1.9133070997413384e-05, + "loss": 1.5294, + "step": 2099 + }, + { + "epoch": 0.22, + "learning_rate": 1.9131579669802685e-05, + "loss": 1.4588, + "step": 2100 + }, + { + "epoch": 0.22, + "learning_rate": 1.9130087118794934e-05, + "loss": 1.443, + "step": 2101 + }, + { + "epoch": 0.22, + "learning_rate": 1.9128593344590102e-05, + "loss": 1.4876, + "step": 2102 + }, + { + "epoch": 0.22, + "learning_rate": 1.912709834738831e-05, + "loss": 1.4874, + "step": 2103 + }, + { + "epoch": 0.22, + "learning_rate": 1.9125602127389856e-05, + "loss": 1.4966, + "step": 2104 + }, + { + "epoch": 0.22, + "learning_rate": 1.912410468479519e-05, + "loss": 1.5747, + "step": 2105 + }, + { + "epoch": 0.22, + "learning_rate": 1.9122606019804933e-05, + "loss": 1.4025, + "step": 2106 + }, + { + "epoch": 0.22, + "learning_rate": 1.912110613261987e-05, + "loss": 1.4755, + "step": 2107 + }, + { + "epoch": 0.22, + "learning_rate": 1.911960502344094e-05, + "loss": 1.4739, + "step": 2108 + }, + { + "epoch": 0.22, + "learning_rate": 1.911810269246926e-05, + "loss": 1.4992, + "step": 2109 + }, + { + "epoch": 0.22, + "learning_rate": 1.91165991399061e-05, + "loss": 1.4435, + "step": 2110 + }, + { + "epoch": 0.22, + "learning_rate": 1.91150943659529e-05, + "loss": 1.4918, + "step": 2111 + }, + { + "epoch": 0.22, + "learning_rate": 1.9113588370811258e-05, + "loss": 1.3818, + "step": 2112 + }, + { + "epoch": 0.22, + "learning_rate": 1.911208115468294e-05, + "loss": 1.5105, + "step": 2113 + }, + { + "epoch": 0.22, + "learning_rate": 1.9110572717769878e-05, + "loss": 1.6634, + "step": 2114 + }, + { + "epoch": 0.22, + "learning_rate": 1.9109063060274158e-05, + "loss": 1.5028, + "step": 2115 + }, + { + "epoch": 0.22, + "learning_rate": 1.9107552182398037e-05, + "loss": 1.6657, + "step": 2116 + }, + { + "epoch": 0.22, + "learning_rate": 1.9106040084343935e-05, + "loss": 1.5481, + "step": 2117 + }, + { + "epoch": 0.22, + "learning_rate": 1.910452676631444e-05, + "loss": 1.4505, + "step": 2118 + }, + { + "epoch": 0.22, + "learning_rate": 1.9103012228512284e-05, + "loss": 1.5173, + "step": 2119 + }, + { + "epoch": 0.22, + "learning_rate": 1.9101496471140385e-05, + "loss": 1.3788, + "step": 2120 + }, + { + "epoch": 0.22, + "learning_rate": 1.9099979494401814e-05, + "loss": 1.4649, + "step": 2121 + }, + { + "epoch": 0.22, + "learning_rate": 1.9098461298499805e-05, + "loss": 1.4204, + "step": 2122 + }, + { + "epoch": 0.22, + "learning_rate": 1.9096941883637766e-05, + "loss": 1.4439, + "step": 2123 + }, + { + "epoch": 0.22, + "learning_rate": 1.909542125001925e-05, + "loss": 1.6615, + "step": 2124 + }, + { + "epoch": 0.22, + "learning_rate": 1.9093899397847985e-05, + "loss": 1.4763, + "step": 2125 + }, + { + "epoch": 0.22, + "learning_rate": 1.909237632732786e-05, + "loss": 1.5353, + "step": 2126 + }, + { + "epoch": 0.22, + "learning_rate": 1.909085203866293e-05, + "loss": 1.442, + "step": 2127 + }, + { + "epoch": 0.22, + "learning_rate": 1.9089326532057408e-05, + "loss": 1.4782, + "step": 2128 + }, + { + "epoch": 0.22, + "learning_rate": 1.908779980771567e-05, + "loss": 1.4933, + "step": 2129 + }, + { + "epoch": 0.22, + "learning_rate": 1.9086271865842264e-05, + "loss": 1.5285, + "step": 2130 + }, + { + "epoch": 0.22, + "learning_rate": 1.9084742706641894e-05, + "loss": 1.4736, + "step": 2131 + }, + { + "epoch": 0.22, + "learning_rate": 1.9083212330319427e-05, + "loss": 1.4496, + "step": 2132 + }, + { + "epoch": 0.22, + "learning_rate": 1.908168073707989e-05, + "loss": 1.5099, + "step": 2133 + }, + { + "epoch": 0.22, + "learning_rate": 1.9080147927128483e-05, + "loss": 1.5235, + "step": 2134 + }, + { + "epoch": 0.22, + "learning_rate": 1.9078613900670556e-05, + "loss": 1.4769, + "step": 2135 + }, + { + "epoch": 0.22, + "learning_rate": 1.907707865791164e-05, + "loss": 1.5771, + "step": 2136 + }, + { + "epoch": 0.22, + "learning_rate": 1.907554219905741e-05, + "loss": 1.5116, + "step": 2137 + }, + { + "epoch": 0.22, + "learning_rate": 1.907400452431371e-05, + "loss": 1.5161, + "step": 2138 + }, + { + "epoch": 0.22, + "learning_rate": 1.9072465633886557e-05, + "loss": 1.4356, + "step": 2139 + }, + { + "epoch": 0.22, + "learning_rate": 1.9070925527982117e-05, + "loss": 1.509, + "step": 2140 + }, + { + "epoch": 0.22, + "learning_rate": 1.9069384206806723e-05, + "loss": 1.4681, + "step": 2141 + }, + { + "epoch": 0.22, + "learning_rate": 1.9067841670566883e-05, + "loss": 1.5254, + "step": 2142 + }, + { + "epoch": 0.22, + "learning_rate": 1.9066297919469242e-05, + "loss": 1.4797, + "step": 2143 + }, + { + "epoch": 0.22, + "learning_rate": 1.9064752953720636e-05, + "loss": 1.3996, + "step": 2144 + }, + { + "epoch": 0.22, + "learning_rate": 1.9063206773528042e-05, + "loss": 1.4457, + "step": 2145 + }, + { + "epoch": 0.23, + "learning_rate": 1.9061659379098617e-05, + "loss": 1.5126, + "step": 2146 + }, + { + "epoch": 0.23, + "learning_rate": 1.9060110770639664e-05, + "loss": 1.5925, + "step": 2147 + }, + { + "epoch": 0.23, + "learning_rate": 1.905856094835866e-05, + "loss": 1.5146, + "step": 2148 + }, + { + "epoch": 0.23, + "learning_rate": 1.905700991246324e-05, + "loss": 1.7256, + "step": 2149 + }, + { + "epoch": 0.23, + "learning_rate": 1.90554576631612e-05, + "loss": 1.57, + "step": 2150 + }, + { + "epoch": 0.23, + "learning_rate": 1.905390420066051e-05, + "loss": 1.3722, + "step": 2151 + }, + { + "epoch": 0.23, + "learning_rate": 1.9052349525169292e-05, + "loss": 1.3999, + "step": 2152 + }, + { + "epoch": 0.23, + "learning_rate": 1.9050793636895828e-05, + "loss": 1.586, + "step": 2153 + }, + { + "epoch": 0.23, + "learning_rate": 1.9049236536048567e-05, + "loss": 1.4884, + "step": 2154 + }, + { + "epoch": 0.23, + "learning_rate": 1.9047678222836127e-05, + "loss": 1.5898, + "step": 2155 + }, + { + "epoch": 0.23, + "learning_rate": 1.9046118697467278e-05, + "loss": 1.569, + "step": 2156 + }, + { + "epoch": 0.23, + "learning_rate": 1.904455796015095e-05, + "loss": 1.5592, + "step": 2157 + }, + { + "epoch": 0.23, + "learning_rate": 1.9042996011096253e-05, + "loss": 1.597, + "step": 2158 + }, + { + "epoch": 0.23, + "learning_rate": 1.904143285051244e-05, + "loss": 1.422, + "step": 2159 + }, + { + "epoch": 0.23, + "learning_rate": 1.903986847860894e-05, + "loss": 1.519, + "step": 2160 + }, + { + "epoch": 0.23, + "learning_rate": 1.9038302895595334e-05, + "loss": 1.5197, + "step": 2161 + }, + { + "epoch": 0.23, + "learning_rate": 1.903673610168137e-05, + "loss": 1.4655, + "step": 2162 + }, + { + "epoch": 0.23, + "learning_rate": 1.9035168097076965e-05, + "loss": 1.3909, + "step": 2163 + }, + { + "epoch": 0.23, + "learning_rate": 1.903359888199218e-05, + "loss": 1.4877, + "step": 2164 + }, + { + "epoch": 0.23, + "learning_rate": 1.903202845663726e-05, + "loss": 1.5123, + "step": 2165 + }, + { + "epoch": 0.23, + "learning_rate": 1.9030456821222593e-05, + "loss": 1.4906, + "step": 2166 + }, + { + "epoch": 0.23, + "learning_rate": 1.9028883975958745e-05, + "loss": 1.4574, + "step": 2167 + }, + { + "epoch": 0.23, + "learning_rate": 1.9027309921056435e-05, + "loss": 1.4571, + "step": 2168 + }, + { + "epoch": 0.23, + "learning_rate": 1.902573465672654e-05, + "loss": 1.4281, + "step": 2169 + }, + { + "epoch": 0.23, + "learning_rate": 1.9024158183180116e-05, + "loss": 1.5057, + "step": 2170 + }, + { + "epoch": 0.23, + "learning_rate": 1.902258050062836e-05, + "loss": 1.4514, + "step": 2171 + }, + { + "epoch": 0.23, + "learning_rate": 1.9021001609282646e-05, + "loss": 1.5055, + "step": 2172 + }, + { + "epoch": 0.23, + "learning_rate": 1.9019421509354505e-05, + "loss": 1.4578, + "step": 2173 + }, + { + "epoch": 0.23, + "learning_rate": 1.9017840201055625e-05, + "loss": 1.459, + "step": 2174 + }, + { + "epoch": 0.23, + "learning_rate": 1.9016257684597864e-05, + "loss": 1.5059, + "step": 2175 + }, + { + "epoch": 0.23, + "learning_rate": 1.901467396019324e-05, + "loss": 1.57, + "step": 2176 + }, + { + "epoch": 0.23, + "learning_rate": 1.901308902805393e-05, + "loss": 1.4924, + "step": 2177 + }, + { + "epoch": 0.23, + "learning_rate": 1.9011502888392273e-05, + "loss": 1.4979, + "step": 2178 + }, + { + "epoch": 0.23, + "learning_rate": 1.900991554142077e-05, + "loss": 1.5321, + "step": 2179 + }, + { + "epoch": 0.23, + "learning_rate": 1.9008326987352093e-05, + "loss": 1.493, + "step": 2180 + }, + { + "epoch": 0.23, + "learning_rate": 1.9006737226399056e-05, + "loss": 1.5111, + "step": 2181 + }, + { + "epoch": 0.23, + "learning_rate": 1.900514625877465e-05, + "loss": 1.4154, + "step": 2182 + }, + { + "epoch": 0.23, + "learning_rate": 1.900355408469203e-05, + "loss": 1.4934, + "step": 2183 + }, + { + "epoch": 0.23, + "learning_rate": 1.90019607043645e-05, + "loss": 1.5975, + "step": 2184 + }, + { + "epoch": 0.23, + "learning_rate": 1.9000366118005532e-05, + "loss": 1.3537, + "step": 2185 + }, + { + "epoch": 0.23, + "learning_rate": 1.899877032582876e-05, + "loss": 1.4583, + "step": 2186 + }, + { + "epoch": 0.23, + "learning_rate": 1.8997173328047984e-05, + "loss": 1.4586, + "step": 2187 + }, + { + "epoch": 0.23, + "learning_rate": 1.8995575124877156e-05, + "loss": 1.4774, + "step": 2188 + }, + { + "epoch": 0.23, + "learning_rate": 1.8993975716530394e-05, + "loss": 1.5025, + "step": 2189 + }, + { + "epoch": 0.23, + "eval_loss": 1.5263344049453735, + "eval_runtime": 77.1492, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 2189 + }, + { + "epoch": 0.23, + "learning_rate": 1.899237510322198e-05, + "loss": 1.5438, + "step": 2190 + }, + { + "epoch": 0.23, + "learning_rate": 1.899077328516635e-05, + "loss": 1.5181, + "step": 2191 + }, + { + "epoch": 0.23, + "learning_rate": 1.8989170262578112e-05, + "loss": 1.4454, + "step": 2192 + }, + { + "epoch": 0.23, + "learning_rate": 1.8987566035672028e-05, + "loss": 1.4882, + "step": 2193 + }, + { + "epoch": 0.23, + "learning_rate": 1.8985960604663026e-05, + "loss": 1.5073, + "step": 2194 + }, + { + "epoch": 0.23, + "learning_rate": 1.8984353969766187e-05, + "loss": 1.4478, + "step": 2195 + }, + { + "epoch": 0.23, + "learning_rate": 1.8982746131196763e-05, + "loss": 1.4768, + "step": 2196 + }, + { + "epoch": 0.23, + "learning_rate": 1.8981137089170162e-05, + "loss": 1.5116, + "step": 2197 + }, + { + "epoch": 0.23, + "learning_rate": 1.8979526843901952e-05, + "loss": 1.4202, + "step": 2198 + }, + { + "epoch": 0.23, + "learning_rate": 1.8977915395607867e-05, + "loss": 1.4736, + "step": 2199 + }, + { + "epoch": 0.23, + "learning_rate": 1.89763027445038e-05, + "loss": 1.4489, + "step": 2200 + }, + { + "epoch": 0.23, + "learning_rate": 1.8974688890805804e-05, + "loss": 1.4512, + "step": 2201 + }, + { + "epoch": 0.23, + "learning_rate": 1.897307383473009e-05, + "loss": 1.5091, + "step": 2202 + }, + { + "epoch": 0.23, + "learning_rate": 1.897145757649304e-05, + "loss": 1.5512, + "step": 2203 + }, + { + "epoch": 0.23, + "learning_rate": 1.8969840116311192e-05, + "loss": 1.406, + "step": 2204 + }, + { + "epoch": 0.23, + "learning_rate": 1.896822145440124e-05, + "loss": 1.4531, + "step": 2205 + }, + { + "epoch": 0.23, + "learning_rate": 1.896660159098004e-05, + "loss": 1.4379, + "step": 2206 + }, + { + "epoch": 0.23, + "learning_rate": 1.896498052626462e-05, + "loss": 1.4783, + "step": 2207 + }, + { + "epoch": 0.23, + "learning_rate": 1.896335826047216e-05, + "loss": 1.4801, + "step": 2208 + }, + { + "epoch": 0.23, + "learning_rate": 1.896173479381999e-05, + "loss": 1.4526, + "step": 2209 + }, + { + "epoch": 0.23, + "learning_rate": 1.8960110126525627e-05, + "loss": 1.4952, + "step": 2210 + }, + { + "epoch": 0.23, + "learning_rate": 1.895848425880673e-05, + "loss": 1.5299, + "step": 2211 + }, + { + "epoch": 0.23, + "learning_rate": 1.8956857190881125e-05, + "loss": 1.5274, + "step": 2212 + }, + { + "epoch": 0.23, + "learning_rate": 1.8955228922966792e-05, + "loss": 1.4415, + "step": 2213 + }, + { + "epoch": 0.23, + "learning_rate": 1.8953599455281884e-05, + "loss": 1.5311, + "step": 2214 + }, + { + "epoch": 0.23, + "learning_rate": 1.8951968788044702e-05, + "loss": 1.4972, + "step": 2215 + }, + { + "epoch": 0.23, + "learning_rate": 1.8950336921473715e-05, + "loss": 1.4966, + "step": 2216 + }, + { + "epoch": 0.23, + "learning_rate": 1.8948703855787553e-05, + "loss": 1.4683, + "step": 2217 + }, + { + "epoch": 0.23, + "learning_rate": 1.8947069591205005e-05, + "loss": 1.503, + "step": 2218 + }, + { + "epoch": 0.23, + "learning_rate": 1.8945434127945014e-05, + "loss": 1.4902, + "step": 2219 + }, + { + "epoch": 0.23, + "learning_rate": 1.8943797466226702e-05, + "loss": 1.4835, + "step": 2220 + }, + { + "epoch": 0.23, + "learning_rate": 1.8942159606269332e-05, + "loss": 1.535, + "step": 2221 + }, + { + "epoch": 0.23, + "learning_rate": 1.8940520548292332e-05, + "loss": 1.491, + "step": 2222 + }, + { + "epoch": 0.23, + "learning_rate": 1.89388802925153e-05, + "loss": 1.5157, + "step": 2223 + }, + { + "epoch": 0.23, + "learning_rate": 1.8937238839157987e-05, + "loss": 1.4779, + "step": 2224 + }, + { + "epoch": 0.23, + "learning_rate": 1.8935596188440302e-05, + "loss": 1.4902, + "step": 2225 + }, + { + "epoch": 0.23, + "learning_rate": 1.8933952340582323e-05, + "loss": 1.4988, + "step": 2226 + }, + { + "epoch": 0.23, + "learning_rate": 1.893230729580428e-05, + "loss": 1.4568, + "step": 2227 + }, + { + "epoch": 0.23, + "learning_rate": 1.8930661054326567e-05, + "loss": 1.5163, + "step": 2228 + }, + { + "epoch": 0.23, + "learning_rate": 1.892901361636974e-05, + "loss": 1.4472, + "step": 2229 + }, + { + "epoch": 0.23, + "learning_rate": 1.892736498215451e-05, + "loss": 1.4658, + "step": 2230 + }, + { + "epoch": 0.23, + "learning_rate": 1.8925715151901754e-05, + "loss": 1.4281, + "step": 2231 + }, + { + "epoch": 0.23, + "learning_rate": 1.892406412583251e-05, + "loss": 1.415, + "step": 2232 + }, + { + "epoch": 0.23, + "learning_rate": 1.8922411904167966e-05, + "loss": 1.464, + "step": 2233 + }, + { + "epoch": 0.23, + "learning_rate": 1.892075848712948e-05, + "loss": 1.5014, + "step": 2234 + }, + { + "epoch": 0.23, + "learning_rate": 1.8919103874938568e-05, + "loss": 1.4397, + "step": 2235 + }, + { + "epoch": 0.23, + "learning_rate": 1.891744806781691e-05, + "loss": 1.5508, + "step": 2236 + }, + { + "epoch": 0.23, + "learning_rate": 1.8915791065986335e-05, + "loss": 1.4749, + "step": 2237 + }, + { + "epoch": 0.23, + "learning_rate": 1.891413286966884e-05, + "loss": 1.4538, + "step": 2238 + }, + { + "epoch": 0.23, + "learning_rate": 1.891247347908658e-05, + "loss": 1.4405, + "step": 2239 + }, + { + "epoch": 0.23, + "learning_rate": 1.8910812894461878e-05, + "loss": 1.3562, + "step": 2240 + }, + { + "epoch": 0.24, + "learning_rate": 1.89091511160172e-05, + "loss": 1.4811, + "step": 2241 + }, + { + "epoch": 0.24, + "learning_rate": 1.8907488143975186e-05, + "loss": 1.4286, + "step": 2242 + }, + { + "epoch": 0.24, + "learning_rate": 1.890582397855863e-05, + "loss": 1.4493, + "step": 2243 + }, + { + "epoch": 0.24, + "learning_rate": 1.890415861999049e-05, + "loss": 1.5639, + "step": 2244 + }, + { + "epoch": 0.24, + "learning_rate": 1.890249206849388e-05, + "loss": 1.6375, + "step": 2245 + }, + { + "epoch": 0.24, + "learning_rate": 1.890082432429208e-05, + "loss": 1.4982, + "step": 2246 + }, + { + "epoch": 0.24, + "learning_rate": 1.889915538760851e-05, + "loss": 1.492, + "step": 2247 + }, + { + "epoch": 0.24, + "learning_rate": 1.8897485258666778e-05, + "loss": 1.4294, + "step": 2248 + }, + { + "epoch": 0.24, + "learning_rate": 1.8895813937690638e-05, + "loss": 1.4617, + "step": 2249 + }, + { + "epoch": 0.24, + "learning_rate": 1.8894141424904e-05, + "loss": 1.4763, + "step": 2250 + }, + { + "epoch": 0.24, + "learning_rate": 1.8892467720530937e-05, + "loss": 1.3989, + "step": 2251 + }, + { + "epoch": 0.24, + "learning_rate": 1.8890792824795687e-05, + "loss": 1.4803, + "step": 2252 + }, + { + "epoch": 0.24, + "learning_rate": 1.8889116737922638e-05, + "loss": 1.4734, + "step": 2253 + }, + { + "epoch": 0.24, + "learning_rate": 1.8887439460136342e-05, + "loss": 1.5069, + "step": 2254 + }, + { + "epoch": 0.24, + "learning_rate": 1.8885760991661514e-05, + "loss": 1.5565, + "step": 2255 + }, + { + "epoch": 0.24, + "learning_rate": 1.8884081332723028e-05, + "loss": 1.4707, + "step": 2256 + }, + { + "epoch": 0.24, + "learning_rate": 1.8882400483545913e-05, + "loss": 1.5077, + "step": 2257 + }, + { + "epoch": 0.24, + "learning_rate": 1.888071844435536e-05, + "loss": 1.5075, + "step": 2258 + }, + { + "epoch": 0.24, + "learning_rate": 1.8879035215376717e-05, + "loss": 1.5185, + "step": 2259 + }, + { + "epoch": 0.24, + "learning_rate": 1.887735079683549e-05, + "loss": 1.6266, + "step": 2260 + }, + { + "epoch": 0.24, + "learning_rate": 1.8875665188957354e-05, + "loss": 1.5013, + "step": 2261 + }, + { + "epoch": 0.24, + "learning_rate": 1.887397839196814e-05, + "loss": 1.4362, + "step": 2262 + }, + { + "epoch": 0.24, + "learning_rate": 1.8872290406093827e-05, + "loss": 1.4718, + "step": 2263 + }, + { + "epoch": 0.24, + "learning_rate": 1.8870601231560567e-05, + "loss": 1.5202, + "step": 2264 + }, + { + "epoch": 0.24, + "learning_rate": 1.8868910868594664e-05, + "loss": 1.5168, + "step": 2265 + }, + { + "epoch": 0.24, + "learning_rate": 1.8867219317422588e-05, + "loss": 1.5142, + "step": 2266 + }, + { + "epoch": 0.24, + "learning_rate": 1.8865526578270954e-05, + "loss": 1.4885, + "step": 2267 + }, + { + "epoch": 0.24, + "learning_rate": 1.8863832651366552e-05, + "loss": 1.5441, + "step": 2268 + }, + { + "epoch": 0.24, + "learning_rate": 1.8862137536936328e-05, + "loss": 1.4647, + "step": 2269 + }, + { + "epoch": 0.24, + "learning_rate": 1.8860441235207374e-05, + "loss": 1.5352, + "step": 2270 + }, + { + "epoch": 0.24, + "learning_rate": 1.8858743746406958e-05, + "loss": 1.4568, + "step": 2271 + }, + { + "epoch": 0.24, + "learning_rate": 1.8857045070762497e-05, + "loss": 1.4865, + "step": 2272 + }, + { + "epoch": 0.24, + "learning_rate": 1.8855345208501573e-05, + "loss": 1.4637, + "step": 2273 + }, + { + "epoch": 0.24, + "learning_rate": 1.8853644159851918e-05, + "loss": 1.4348, + "step": 2274 + }, + { + "epoch": 0.24, + "learning_rate": 1.8851941925041436e-05, + "loss": 1.4413, + "step": 2275 + }, + { + "epoch": 0.24, + "learning_rate": 1.8850238504298177e-05, + "loss": 1.4434, + "step": 2276 + }, + { + "epoch": 0.24, + "learning_rate": 1.884853389785036e-05, + "loss": 1.4822, + "step": 2277 + }, + { + "epoch": 0.24, + "learning_rate": 1.8846828105926356e-05, + "loss": 1.4632, + "step": 2278 + }, + { + "epoch": 0.24, + "learning_rate": 1.8845121128754698e-05, + "loss": 1.48, + "step": 2279 + }, + { + "epoch": 0.24, + "learning_rate": 1.8843412966564078e-05, + "loss": 1.4518, + "step": 2280 + }, + { + "epoch": 0.24, + "learning_rate": 1.884170361958334e-05, + "loss": 1.4334, + "step": 2281 + }, + { + "epoch": 0.24, + "learning_rate": 1.8839993088041502e-05, + "loss": 1.5131, + "step": 2282 + }, + { + "epoch": 0.24, + "learning_rate": 1.8838281372167724e-05, + "loss": 1.508, + "step": 2283 + }, + { + "epoch": 0.24, + "learning_rate": 1.8836568472191335e-05, + "loss": 1.4086, + "step": 2284 + }, + { + "epoch": 0.24, + "learning_rate": 1.883485438834182e-05, + "loss": 1.5021, + "step": 2285 + }, + { + "epoch": 0.24, + "learning_rate": 1.8833139120848817e-05, + "loss": 1.5083, + "step": 2286 + }, + { + "epoch": 0.24, + "learning_rate": 1.8831422669942137e-05, + "loss": 1.4162, + "step": 2287 + }, + { + "epoch": 0.24, + "learning_rate": 1.8829705035851734e-05, + "loss": 1.5494, + "step": 2288 + }, + { + "epoch": 0.24, + "learning_rate": 1.8827986218807724e-05, + "loss": 1.425, + "step": 2289 + }, + { + "epoch": 0.24, + "learning_rate": 1.8826266219040396e-05, + "loss": 1.5215, + "step": 2290 + }, + { + "epoch": 0.24, + "learning_rate": 1.8824545036780172e-05, + "loss": 1.5577, + "step": 2291 + }, + { + "epoch": 0.24, + "learning_rate": 1.8822822672257655e-05, + "loss": 1.4923, + "step": 2292 + }, + { + "epoch": 0.24, + "learning_rate": 1.8821099125703595e-05, + "loss": 1.4648, + "step": 2293 + }, + { + "epoch": 0.24, + "learning_rate": 1.8819374397348902e-05, + "loss": 1.471, + "step": 2294 + }, + { + "epoch": 0.24, + "learning_rate": 1.8817648487424648e-05, + "loss": 1.5658, + "step": 2295 + }, + { + "epoch": 0.24, + "learning_rate": 1.8815921396162058e-05, + "loss": 1.5348, + "step": 2296 + }, + { + "epoch": 0.24, + "learning_rate": 1.8814193123792518e-05, + "loss": 1.4081, + "step": 2297 + }, + { + "epoch": 0.24, + "learning_rate": 1.881246367054757e-05, + "loss": 1.4762, + "step": 2298 + }, + { + "epoch": 0.24, + "learning_rate": 1.8810733036658925e-05, + "loss": 1.4399, + "step": 2299 + }, + { + "epoch": 0.24, + "learning_rate": 1.8809001222358432e-05, + "loss": 1.4763, + "step": 2300 + }, + { + "epoch": 0.24, + "learning_rate": 1.880726822787812e-05, + "loss": 1.4874, + "step": 2301 + }, + { + "epoch": 0.24, + "learning_rate": 1.880553405345016e-05, + "loss": 1.4951, + "step": 2302 + }, + { + "epoch": 0.24, + "learning_rate": 1.8803798699306887e-05, + "loss": 1.4697, + "step": 2303 + }, + { + "epoch": 0.24, + "learning_rate": 1.880206216568079e-05, + "loss": 1.481, + "step": 2304 + }, + { + "epoch": 0.24, + "learning_rate": 1.880032445280453e-05, + "loss": 1.4485, + "step": 2305 + }, + { + "epoch": 0.24, + "learning_rate": 1.879858556091091e-05, + "loss": 1.4749, + "step": 2306 + }, + { + "epoch": 0.24, + "learning_rate": 1.8796845490232894e-05, + "loss": 1.5605, + "step": 2307 + }, + { + "epoch": 0.24, + "learning_rate": 1.879510424100361e-05, + "loss": 1.4835, + "step": 2308 + }, + { + "epoch": 0.24, + "learning_rate": 1.8793361813456346e-05, + "loss": 1.4344, + "step": 2309 + }, + { + "epoch": 0.24, + "learning_rate": 1.8791618207824532e-05, + "loss": 1.4571, + "step": 2310 + }, + { + "epoch": 0.24, + "learning_rate": 1.8789873424341772e-05, + "loss": 1.482, + "step": 2311 + }, + { + "epoch": 0.24, + "learning_rate": 1.8788127463241822e-05, + "loss": 1.4736, + "step": 2312 + }, + { + "epoch": 0.24, + "learning_rate": 1.8786380324758597e-05, + "loss": 1.4807, + "step": 2313 + }, + { + "epoch": 0.24, + "learning_rate": 1.8784632009126167e-05, + "loss": 1.4418, + "step": 2314 + }, + { + "epoch": 0.24, + "learning_rate": 1.878288251657876e-05, + "loss": 1.5248, + "step": 2315 + }, + { + "epoch": 0.24, + "learning_rate": 1.8781131847350768e-05, + "loss": 1.483, + "step": 2316 + }, + { + "epoch": 0.24, + "learning_rate": 1.877938000167673e-05, + "loss": 1.5474, + "step": 2317 + }, + { + "epoch": 0.24, + "learning_rate": 1.8777626979791347e-05, + "loss": 1.4671, + "step": 2318 + }, + { + "epoch": 0.24, + "learning_rate": 1.877587278192949e-05, + "loss": 1.3049, + "step": 2319 + }, + { + "epoch": 0.24, + "learning_rate": 1.877411740832616e-05, + "loss": 1.483, + "step": 2320 + }, + { + "epoch": 0.24, + "learning_rate": 1.877236085921655e-05, + "loss": 1.508, + "step": 2321 + }, + { + "epoch": 0.24, + "learning_rate": 1.8770603134835978e-05, + "loss": 1.4854, + "step": 2322 + }, + { + "epoch": 0.24, + "learning_rate": 1.8768844235419942e-05, + "loss": 1.4808, + "step": 2323 + }, + { + "epoch": 0.24, + "learning_rate": 1.8767084161204087e-05, + "loss": 1.5352, + "step": 2324 + }, + { + "epoch": 0.24, + "learning_rate": 1.8765322912424214e-05, + "loss": 1.5628, + "step": 2325 + }, + { + "epoch": 0.24, + "learning_rate": 1.8763560489316292e-05, + "loss": 1.494, + "step": 2326 + }, + { + "epoch": 0.24, + "learning_rate": 1.876179689211643e-05, + "loss": 1.509, + "step": 2327 + }, + { + "epoch": 0.24, + "learning_rate": 1.8760032121060918e-05, + "loss": 1.5021, + "step": 2328 + }, + { + "epoch": 0.24, + "learning_rate": 1.875826617638618e-05, + "loss": 1.4179, + "step": 2329 + }, + { + "epoch": 0.24, + "learning_rate": 1.8756499058328813e-05, + "loss": 1.4302, + "step": 2330 + }, + { + "epoch": 0.24, + "learning_rate": 1.8754730767125564e-05, + "loss": 1.4959, + "step": 2331 + }, + { + "epoch": 0.24, + "learning_rate": 1.8752961303013336e-05, + "loss": 1.4423, + "step": 2332 + }, + { + "epoch": 0.24, + "learning_rate": 1.8751190666229194e-05, + "loss": 1.4564, + "step": 2333 + }, + { + "epoch": 0.24, + "learning_rate": 1.8749418857010358e-05, + "loss": 1.4775, + "step": 2334 + }, + { + "epoch": 0.24, + "learning_rate": 1.8747645875594203e-05, + "loss": 1.4182, + "step": 2335 + }, + { + "epoch": 0.24, + "learning_rate": 1.8745871722218265e-05, + "loss": 1.3957, + "step": 2336 + }, + { + "epoch": 0.25, + "learning_rate": 1.8744096397120235e-05, + "loss": 1.4633, + "step": 2337 + }, + { + "epoch": 0.25, + "learning_rate": 1.874231990053796e-05, + "loss": 1.5512, + "step": 2338 + }, + { + "epoch": 0.25, + "learning_rate": 1.8740542232709444e-05, + "loss": 1.3461, + "step": 2339 + }, + { + "epoch": 0.25, + "learning_rate": 1.8738763393872848e-05, + "loss": 1.4754, + "step": 2340 + }, + { + "epoch": 0.25, + "learning_rate": 1.8736983384266495e-05, + "loss": 1.5448, + "step": 2341 + }, + { + "epoch": 0.25, + "learning_rate": 1.8735202204128854e-05, + "loss": 1.4491, + "step": 2342 + }, + { + "epoch": 0.25, + "learning_rate": 1.8733419853698566e-05, + "loss": 1.457, + "step": 2343 + }, + { + "epoch": 0.25, + "learning_rate": 1.8731636333214414e-05, + "loss": 1.4314, + "step": 2344 + }, + { + "epoch": 0.25, + "learning_rate": 1.8729851642915345e-05, + "loss": 1.3979, + "step": 2345 + }, + { + "epoch": 0.25, + "learning_rate": 1.8728065783040464e-05, + "loss": 1.4146, + "step": 2346 + }, + { + "epoch": 0.25, + "learning_rate": 1.8726278753829027e-05, + "loss": 1.4361, + "step": 2347 + }, + { + "epoch": 0.25, + "learning_rate": 1.872449055552045e-05, + "loss": 1.4989, + "step": 2348 + }, + { + "epoch": 0.25, + "learning_rate": 1.872270118835431e-05, + "loss": 1.5062, + "step": 2349 + }, + { + "epoch": 0.25, + "learning_rate": 1.872091065257033e-05, + "loss": 1.4509, + "step": 2350 + }, + { + "epoch": 0.25, + "learning_rate": 1.8719118948408403e-05, + "loss": 1.4631, + "step": 2351 + }, + { + "epoch": 0.25, + "learning_rate": 1.8717326076108566e-05, + "loss": 1.5119, + "step": 2352 + }, + { + "epoch": 0.25, + "learning_rate": 1.8715532035911017e-05, + "loss": 1.6347, + "step": 2353 + }, + { + "epoch": 0.25, + "learning_rate": 1.8713736828056115e-05, + "loss": 1.5526, + "step": 2354 + }, + { + "epoch": 0.25, + "learning_rate": 1.8711940452784368e-05, + "loss": 1.6348, + "step": 2355 + }, + { + "epoch": 0.25, + "learning_rate": 1.871014291033645e-05, + "loss": 1.5183, + "step": 2356 + }, + { + "epoch": 0.25, + "learning_rate": 1.8708344200953182e-05, + "loss": 1.458, + "step": 2357 + }, + { + "epoch": 0.25, + "learning_rate": 1.8706544324875545e-05, + "loss": 1.524, + "step": 2358 + }, + { + "epoch": 0.25, + "learning_rate": 1.8704743282344672e-05, + "loss": 1.4479, + "step": 2359 + }, + { + "epoch": 0.25, + "learning_rate": 1.870294107360186e-05, + "loss": 1.5408, + "step": 2360 + }, + { + "epoch": 0.25, + "learning_rate": 1.8701137698888563e-05, + "loss": 1.5007, + "step": 2361 + }, + { + "epoch": 0.25, + "learning_rate": 1.8699333158446382e-05, + "loss": 1.5132, + "step": 2362 + }, + { + "epoch": 0.25, + "learning_rate": 1.869752745251708e-05, + "loss": 1.4263, + "step": 2363 + }, + { + "epoch": 0.25, + "learning_rate": 1.8695720581342574e-05, + "loss": 1.422, + "step": 2364 + }, + { + "epoch": 0.25, + "learning_rate": 1.869391254516494e-05, + "loss": 1.4411, + "step": 2365 + }, + { + "epoch": 0.25, + "learning_rate": 1.8692103344226406e-05, + "loss": 1.4594, + "step": 2366 + }, + { + "epoch": 0.25, + "learning_rate": 1.8690292978769364e-05, + "loss": 1.4992, + "step": 2367 + }, + { + "epoch": 0.25, + "learning_rate": 1.868848144903635e-05, + "loss": 1.4822, + "step": 2368 + }, + { + "epoch": 0.25, + "learning_rate": 1.8686668755270064e-05, + "loss": 1.5402, + "step": 2369 + }, + { + "epoch": 0.25, + "learning_rate": 1.8684854897713363e-05, + "loss": 1.5268, + "step": 2370 + }, + { + "epoch": 0.25, + "learning_rate": 1.8683039876609258e-05, + "loss": 1.5587, + "step": 2371 + }, + { + "epoch": 0.25, + "learning_rate": 1.868122369220091e-05, + "loss": 1.4214, + "step": 2372 + }, + { + "epoch": 0.25, + "learning_rate": 1.8679406344731645e-05, + "loss": 1.5089, + "step": 2373 + }, + { + "epoch": 0.25, + "learning_rate": 1.867758783444494e-05, + "loss": 1.5067, + "step": 2374 + }, + { + "epoch": 0.25, + "learning_rate": 1.8675768161584427e-05, + "loss": 2.0616, + "step": 2375 + }, + { + "epoch": 0.25, + "learning_rate": 1.8673947326393903e-05, + "loss": 1.5617, + "step": 2376 + }, + { + "epoch": 0.25, + "learning_rate": 1.86721253291173e-05, + "loss": 1.4422, + "step": 2377 + }, + { + "epoch": 0.25, + "learning_rate": 1.867030216999873e-05, + "loss": 1.4727, + "step": 2378 + }, + { + "epoch": 0.25, + "learning_rate": 1.8668477849282443e-05, + "loss": 1.4152, + "step": 2379 + }, + { + "epoch": 0.25, + "learning_rate": 1.8666652367212856e-05, + "loss": 1.4376, + "step": 2380 + }, + { + "epoch": 0.25, + "learning_rate": 1.8664825724034534e-05, + "loss": 1.393, + "step": 2381 + }, + { + "epoch": 0.25, + "learning_rate": 1.8662997919992197e-05, + "loss": 1.4864, + "step": 2382 + }, + { + "epoch": 0.25, + "learning_rate": 1.866116895533073e-05, + "loss": 1.4261, + "step": 2383 + }, + { + "epoch": 0.25, + "learning_rate": 1.8659338830295163e-05, + "loss": 1.4555, + "step": 2384 + }, + { + "epoch": 0.25, + "learning_rate": 1.8657507545130687e-05, + "loss": 1.4939, + "step": 2385 + }, + { + "epoch": 0.25, + "learning_rate": 1.865567510008265e-05, + "loss": 1.4123, + "step": 2386 + }, + { + "epoch": 0.25, + "learning_rate": 1.8653841495396546e-05, + "loss": 1.4459, + "step": 2387 + }, + { + "epoch": 0.25, + "learning_rate": 1.8652006731318038e-05, + "loss": 1.396, + "step": 2388 + }, + { + "epoch": 0.25, + "eval_loss": 1.5139706134796143, + "eval_runtime": 77.2904, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 2388 + }, + { + "epoch": 0.25, + "learning_rate": 1.8650170808092936e-05, + "loss": 1.4666, + "step": 2389 + }, + { + "epoch": 0.25, + "learning_rate": 1.86483337259672e-05, + "loss": 1.5154, + "step": 2390 + }, + { + "epoch": 0.25, + "learning_rate": 1.864649548518696e-05, + "loss": 1.5163, + "step": 2391 + }, + { + "epoch": 0.25, + "learning_rate": 1.864465608599849e-05, + "loss": 1.4734, + "step": 2392 + }, + { + "epoch": 0.25, + "learning_rate": 1.864281552864822e-05, + "loss": 1.5217, + "step": 2393 + }, + { + "epoch": 0.25, + "learning_rate": 1.8640973813382737e-05, + "loss": 1.4694, + "step": 2394 + }, + { + "epoch": 0.25, + "learning_rate": 1.863913094044879e-05, + "loss": 1.4761, + "step": 2395 + }, + { + "epoch": 0.25, + "learning_rate": 1.863728691009327e-05, + "loss": 1.4766, + "step": 2396 + }, + { + "epoch": 0.25, + "learning_rate": 1.863544172256323e-05, + "loss": 1.5695, + "step": 2397 + }, + { + "epoch": 0.25, + "learning_rate": 1.8633595378105882e-05, + "loss": 1.5079, + "step": 2398 + }, + { + "epoch": 0.25, + "learning_rate": 1.8631747876968584e-05, + "loss": 1.4154, + "step": 2399 + }, + { + "epoch": 0.25, + "learning_rate": 1.862989921939886e-05, + "loss": 1.4488, + "step": 2400 + }, + { + "epoch": 0.25, + "learning_rate": 1.8628049405644376e-05, + "loss": 1.4279, + "step": 2401 + }, + { + "epoch": 0.25, + "learning_rate": 1.8626198435952966e-05, + "loss": 1.4896, + "step": 2402 + }, + { + "epoch": 0.25, + "learning_rate": 1.8624346310572602e-05, + "loss": 1.4315, + "step": 2403 + }, + { + "epoch": 0.25, + "learning_rate": 1.862249302975143e-05, + "loss": 1.4919, + "step": 2404 + }, + { + "epoch": 0.25, + "learning_rate": 1.8620638593737743e-05, + "loss": 1.4561, + "step": 2405 + }, + { + "epoch": 0.25, + "learning_rate": 1.8618783002779985e-05, + "loss": 1.4622, + "step": 2406 + }, + { + "epoch": 0.25, + "learning_rate": 1.8616926257126754e-05, + "loss": 1.4917, + "step": 2407 + }, + { + "epoch": 0.25, + "learning_rate": 1.861506835702681e-05, + "loss": 1.4962, + "step": 2408 + }, + { + "epoch": 0.25, + "learning_rate": 1.861320930272906e-05, + "loss": 1.4164, + "step": 2409 + }, + { + "epoch": 0.25, + "learning_rate": 1.8611349094482578e-05, + "loss": 1.4889, + "step": 2410 + }, + { + "epoch": 0.25, + "learning_rate": 1.8609487732536576e-05, + "loss": 1.543, + "step": 2411 + }, + { + "epoch": 0.25, + "learning_rate": 1.8607625217140433e-05, + "loss": 1.5417, + "step": 2412 + }, + { + "epoch": 0.25, + "learning_rate": 1.8605761548543674e-05, + "loss": 1.5304, + "step": 2413 + }, + { + "epoch": 0.25, + "learning_rate": 1.860389672699599e-05, + "loss": 1.4725, + "step": 2414 + }, + { + "epoch": 0.25, + "learning_rate": 1.860203075274721e-05, + "loss": 1.4745, + "step": 2415 + }, + { + "epoch": 0.25, + "learning_rate": 1.8600163626047334e-05, + "loss": 1.4656, + "step": 2416 + }, + { + "epoch": 0.25, + "learning_rate": 1.8598295347146503e-05, + "loss": 1.5287, + "step": 2417 + }, + { + "epoch": 0.25, + "learning_rate": 1.8596425916295023e-05, + "loss": 1.5024, + "step": 2418 + }, + { + "epoch": 0.25, + "learning_rate": 1.8594555333743348e-05, + "loss": 1.4527, + "step": 2419 + }, + { + "epoch": 0.25, + "learning_rate": 1.859268359974209e-05, + "loss": 1.4897, + "step": 2420 + }, + { + "epoch": 0.25, + "learning_rate": 1.859081071454201e-05, + "loss": 1.3554, + "step": 2421 + }, + { + "epoch": 0.25, + "learning_rate": 1.858893667839403e-05, + "loss": 1.4004, + "step": 2422 + }, + { + "epoch": 0.25, + "learning_rate": 1.858706149154922e-05, + "loss": 1.5582, + "step": 2423 + }, + { + "epoch": 0.25, + "learning_rate": 1.8585185154258803e-05, + "loss": 1.505, + "step": 2424 + }, + { + "epoch": 0.25, + "learning_rate": 1.858330766677417e-05, + "loss": 1.5043, + "step": 2425 + }, + { + "epoch": 0.25, + "learning_rate": 1.858142902934685e-05, + "loss": 1.439, + "step": 2426 + }, + { + "epoch": 0.25, + "learning_rate": 1.857954924222853e-05, + "loss": 1.4927, + "step": 2427 + }, + { + "epoch": 0.25, + "learning_rate": 1.8577668305671056e-05, + "loss": 1.5395, + "step": 2428 + }, + { + "epoch": 0.25, + "learning_rate": 1.8575786219926427e-05, + "loss": 1.4737, + "step": 2429 + }, + { + "epoch": 0.25, + "learning_rate": 1.8573902985246794e-05, + "loss": 1.6151, + "step": 2430 + }, + { + "epoch": 0.25, + "learning_rate": 1.857201860188446e-05, + "loss": 1.4313, + "step": 2431 + }, + { + "epoch": 0.26, + "learning_rate": 1.857013307009188e-05, + "loss": 1.4509, + "step": 2432 + }, + { + "epoch": 0.26, + "learning_rate": 1.8568246390121673e-05, + "loss": 1.3998, + "step": 2433 + }, + { + "epoch": 0.26, + "learning_rate": 1.8566358562226603e-05, + "loss": 1.5268, + "step": 2434 + }, + { + "epoch": 0.26, + "learning_rate": 1.8564469586659593e-05, + "loss": 1.4369, + "step": 2435 + }, + { + "epoch": 0.26, + "learning_rate": 1.8562579463673713e-05, + "loss": 1.4759, + "step": 2436 + }, + { + "epoch": 0.26, + "learning_rate": 1.8560688193522197e-05, + "loss": 1.4092, + "step": 2437 + }, + { + "epoch": 0.26, + "learning_rate": 1.855879577645842e-05, + "loss": 1.43, + "step": 2438 + }, + { + "epoch": 0.26, + "learning_rate": 1.855690221273592e-05, + "loss": 1.5143, + "step": 2439 + }, + { + "epoch": 0.26, + "learning_rate": 1.8555007502608385e-05, + "loss": 1.5482, + "step": 2440 + }, + { + "epoch": 0.26, + "learning_rate": 1.855311164632966e-05, + "loss": 1.4406, + "step": 2441 + }, + { + "epoch": 0.26, + "learning_rate": 1.8551214644153738e-05, + "loss": 1.4551, + "step": 2442 + }, + { + "epoch": 0.26, + "learning_rate": 1.8549316496334774e-05, + "loss": 1.4663, + "step": 2443 + }, + { + "epoch": 0.26, + "learning_rate": 1.8547417203127064e-05, + "loss": 1.4732, + "step": 2444 + }, + { + "epoch": 0.26, + "learning_rate": 1.8545516764785067e-05, + "loss": 1.5378, + "step": 2445 + }, + { + "epoch": 0.26, + "learning_rate": 1.8543615181563397e-05, + "loss": 1.4448, + "step": 2446 + }, + { + "epoch": 0.26, + "learning_rate": 1.854171245371681e-05, + "loss": 1.2861, + "step": 2447 + }, + { + "epoch": 0.26, + "learning_rate": 1.8539808581500228e-05, + "loss": 1.4405, + "step": 2448 + }, + { + "epoch": 0.26, + "learning_rate": 1.8537903565168716e-05, + "loss": 1.4876, + "step": 2449 + }, + { + "epoch": 0.26, + "learning_rate": 1.8535997404977506e-05, + "loss": 1.4119, + "step": 2450 + }, + { + "epoch": 0.26, + "learning_rate": 1.8534090101181967e-05, + "loss": 1.4451, + "step": 2451 + }, + { + "epoch": 0.26, + "learning_rate": 1.8532181654037632e-05, + "loss": 1.4035, + "step": 2452 + }, + { + "epoch": 0.26, + "learning_rate": 1.853027206380018e-05, + "loss": 1.4624, + "step": 2453 + }, + { + "epoch": 0.26, + "learning_rate": 1.852836133072545e-05, + "loss": 1.4935, + "step": 2454 + }, + { + "epoch": 0.26, + "learning_rate": 1.8526449455069434e-05, + "loss": 1.4834, + "step": 2455 + }, + { + "epoch": 0.26, + "learning_rate": 1.8524536437088266e-05, + "loss": 1.498, + "step": 2456 + }, + { + "epoch": 0.26, + "learning_rate": 1.8522622277038247e-05, + "loss": 1.3417, + "step": 2457 + }, + { + "epoch": 0.26, + "learning_rate": 1.852070697517583e-05, + "loss": 1.4455, + "step": 2458 + }, + { + "epoch": 0.26, + "learning_rate": 1.8518790531757607e-05, + "loss": 1.4119, + "step": 2459 + }, + { + "epoch": 0.26, + "learning_rate": 1.8516872947040337e-05, + "loss": 1.558, + "step": 2460 + }, + { + "epoch": 0.26, + "learning_rate": 1.8514954221280926e-05, + "loss": 1.4862, + "step": 2461 + }, + { + "epoch": 0.26, + "learning_rate": 1.8513034354736433e-05, + "loss": 1.6806, + "step": 2462 + }, + { + "epoch": 0.26, + "learning_rate": 1.8511113347664072e-05, + "loss": 1.438, + "step": 2463 + }, + { + "epoch": 0.26, + "learning_rate": 1.850919120032121e-05, + "loss": 1.4975, + "step": 2464 + }, + { + "epoch": 0.26, + "learning_rate": 1.850726791296536e-05, + "loss": 1.4409, + "step": 2465 + }, + { + "epoch": 0.26, + "learning_rate": 1.85053434858542e-05, + "loss": 1.4769, + "step": 2466 + }, + { + "epoch": 0.26, + "learning_rate": 1.8503417919245548e-05, + "loss": 1.5823, + "step": 2467 + }, + { + "epoch": 0.26, + "learning_rate": 1.8501491213397386e-05, + "loss": 1.4045, + "step": 2468 + }, + { + "epoch": 0.26, + "learning_rate": 1.8499563368567837e-05, + "loss": 1.4828, + "step": 2469 + }, + { + "epoch": 0.26, + "learning_rate": 1.849763438501519e-05, + "loss": 1.4684, + "step": 2470 + }, + { + "epoch": 0.26, + "learning_rate": 1.8495704262997873e-05, + "loss": 1.4577, + "step": 2471 + }, + { + "epoch": 0.26, + "learning_rate": 1.8493773002774475e-05, + "loss": 1.4759, + "step": 2472 + }, + { + "epoch": 0.26, + "learning_rate": 1.8491840604603736e-05, + "loss": 1.4259, + "step": 2473 + }, + { + "epoch": 0.26, + "learning_rate": 1.8489907068744543e-05, + "loss": 1.4717, + "step": 2474 + }, + { + "epoch": 0.26, + "learning_rate": 1.848797239545595e-05, + "loss": 1.4247, + "step": 2475 + }, + { + "epoch": 0.26, + "learning_rate": 1.8486036584997143e-05, + "loss": 1.4954, + "step": 2476 + }, + { + "epoch": 0.26, + "learning_rate": 1.8484099637627472e-05, + "loss": 1.4926, + "step": 2477 + }, + { + "epoch": 0.26, + "learning_rate": 1.8482161553606447e-05, + "loss": 1.487, + "step": 2478 + }, + { + "epoch": 0.26, + "learning_rate": 1.8480222333193715e-05, + "loss": 1.4553, + "step": 2479 + }, + { + "epoch": 0.26, + "learning_rate": 1.847828197664908e-05, + "loss": 1.4862, + "step": 2480 + }, + { + "epoch": 0.26, + "learning_rate": 1.8476340484232508e-05, + "loss": 1.4867, + "step": 2481 + }, + { + "epoch": 0.26, + "learning_rate": 1.8474397856204097e-05, + "loss": 1.4736, + "step": 2482 + }, + { + "epoch": 0.26, + "learning_rate": 1.8472454092824122e-05, + "loss": 1.4254, + "step": 2483 + }, + { + "epoch": 0.26, + "learning_rate": 1.8470509194352987e-05, + "loss": 1.4455, + "step": 2484 + }, + { + "epoch": 0.26, + "learning_rate": 1.8468563161051263e-05, + "loss": 1.4402, + "step": 2485 + }, + { + "epoch": 0.26, + "learning_rate": 1.846661599317967e-05, + "loss": 1.4611, + "step": 2486 + }, + { + "epoch": 0.26, + "learning_rate": 1.8464667690999073e-05, + "loss": 1.4814, + "step": 2487 + }, + { + "epoch": 0.26, + "learning_rate": 1.8462718254770503e-05, + "loss": 1.4559, + "step": 2488 + }, + { + "epoch": 0.26, + "learning_rate": 1.8460767684755127e-05, + "loss": 1.4667, + "step": 2489 + }, + { + "epoch": 0.26, + "learning_rate": 1.8458815981214274e-05, + "loss": 1.4427, + "step": 2490 + }, + { + "epoch": 0.26, + "learning_rate": 1.845686314440942e-05, + "loss": 1.4055, + "step": 2491 + }, + { + "epoch": 0.26, + "learning_rate": 1.8454909174602198e-05, + "loss": 1.5563, + "step": 2492 + }, + { + "epoch": 0.26, + "learning_rate": 1.845295407205439e-05, + "loss": 1.4631, + "step": 2493 + }, + { + "epoch": 0.26, + "learning_rate": 1.8450997837027925e-05, + "loss": 1.4887, + "step": 2494 + }, + { + "epoch": 0.26, + "learning_rate": 1.8449040469784895e-05, + "loss": 1.5212, + "step": 2495 + }, + { + "epoch": 0.26, + "learning_rate": 1.844708197058753e-05, + "loss": 1.5582, + "step": 2496 + }, + { + "epoch": 0.26, + "learning_rate": 1.844512233969822e-05, + "loss": 1.4599, + "step": 2497 + }, + { + "epoch": 0.26, + "learning_rate": 1.844316157737951e-05, + "loss": 1.4546, + "step": 2498 + }, + { + "epoch": 0.26, + "learning_rate": 1.844119968389409e-05, + "loss": 1.4631, + "step": 2499 + }, + { + "epoch": 0.26, + "learning_rate": 1.84392366595048e-05, + "loss": 1.4817, + "step": 2500 + }, + { + "epoch": 0.26, + "learning_rate": 1.8437272504474636e-05, + "loss": 1.4214, + "step": 2501 + }, + { + "epoch": 0.26, + "learning_rate": 1.8435307219066744e-05, + "loss": 1.471, + "step": 2502 + }, + { + "epoch": 0.26, + "learning_rate": 1.8433340803544424e-05, + "loss": 1.4693, + "step": 2503 + }, + { + "epoch": 0.26, + "learning_rate": 1.8431373258171127e-05, + "loss": 1.6297, + "step": 2504 + }, + { + "epoch": 0.26, + "learning_rate": 1.842940458321045e-05, + "loss": 1.5916, + "step": 2505 + }, + { + "epoch": 0.26, + "learning_rate": 1.842743477892614e-05, + "loss": 1.4754, + "step": 2506 + }, + { + "epoch": 0.26, + "learning_rate": 1.842546384558211e-05, + "loss": 1.4828, + "step": 2507 + }, + { + "epoch": 0.26, + "learning_rate": 1.842349178344241e-05, + "loss": 1.4239, + "step": 2508 + }, + { + "epoch": 0.26, + "learning_rate": 1.8421518592771243e-05, + "loss": 1.5028, + "step": 2509 + }, + { + "epoch": 0.26, + "learning_rate": 1.841954427383297e-05, + "loss": 1.4848, + "step": 2510 + }, + { + "epoch": 0.26, + "learning_rate": 1.8417568826892097e-05, + "loss": 1.4617, + "step": 2511 + }, + { + "epoch": 0.26, + "learning_rate": 1.8415592252213284e-05, + "loss": 1.4266, + "step": 2512 + }, + { + "epoch": 0.26, + "learning_rate": 1.8413614550061344e-05, + "loss": 1.4321, + "step": 2513 + }, + { + "epoch": 0.26, + "learning_rate": 1.841163572070123e-05, + "loss": 1.4693, + "step": 2514 + }, + { + "epoch": 0.26, + "learning_rate": 1.840965576439806e-05, + "loss": 1.4257, + "step": 2515 + }, + { + "epoch": 0.26, + "learning_rate": 1.84076746814171e-05, + "loss": 1.4488, + "step": 2516 + }, + { + "epoch": 0.26, + "learning_rate": 1.840569247202376e-05, + "loss": 1.5348, + "step": 2517 + }, + { + "epoch": 0.26, + "learning_rate": 1.8403709136483604e-05, + "loss": 1.477, + "step": 2518 + }, + { + "epoch": 0.26, + "learning_rate": 1.840172467506235e-05, + "loss": 1.443, + "step": 2519 + }, + { + "epoch": 0.26, + "learning_rate": 1.839973908802587e-05, + "loss": 1.4772, + "step": 2520 + }, + { + "epoch": 0.26, + "learning_rate": 1.839775237564017e-05, + "loss": 1.4443, + "step": 2521 + }, + { + "epoch": 0.26, + "learning_rate": 1.839576453817143e-05, + "loss": 1.4063, + "step": 2522 + }, + { + "epoch": 0.26, + "learning_rate": 1.8393775575885963e-05, + "loss": 1.5178, + "step": 2523 + }, + { + "epoch": 0.26, + "learning_rate": 1.8391785489050235e-05, + "loss": 1.4337, + "step": 2524 + }, + { + "epoch": 0.26, + "learning_rate": 1.8389794277930875e-05, + "loss": 1.4512, + "step": 2525 + }, + { + "epoch": 0.26, + "learning_rate": 1.838780194279465e-05, + "loss": 1.5578, + "step": 2526 + }, + { + "epoch": 0.26, + "learning_rate": 1.8385808483908484e-05, + "loss": 1.4606, + "step": 2527 + }, + { + "epoch": 0.27, + "learning_rate": 1.8383813901539444e-05, + "loss": 1.4957, + "step": 2528 + }, + { + "epoch": 0.27, + "learning_rate": 1.838181819595476e-05, + "loss": 1.4914, + "step": 2529 + }, + { + "epoch": 0.27, + "learning_rate": 1.8379821367421802e-05, + "loss": 1.4785, + "step": 2530 + }, + { + "epoch": 0.27, + "learning_rate": 1.837782341620809e-05, + "loss": 1.4052, + "step": 2531 + }, + { + "epoch": 0.27, + "learning_rate": 1.8375824342581303e-05, + "loss": 1.4807, + "step": 2532 + }, + { + "epoch": 0.27, + "learning_rate": 1.8373824146809264e-05, + "loss": 1.4313, + "step": 2533 + }, + { + "epoch": 0.27, + "learning_rate": 1.8371822829159945e-05, + "loss": 1.4374, + "step": 2534 + }, + { + "epoch": 0.27, + "learning_rate": 1.836982038990148e-05, + "loss": 1.4482, + "step": 2535 + }, + { + "epoch": 0.27, + "learning_rate": 1.8367816829302133e-05, + "loss": 1.5231, + "step": 2536 + }, + { + "epoch": 0.27, + "learning_rate": 1.8365812147630337e-05, + "loss": 1.4101, + "step": 2537 + }, + { + "epoch": 0.27, + "learning_rate": 1.8363806345154666e-05, + "loss": 1.4372, + "step": 2538 + }, + { + "epoch": 0.27, + "learning_rate": 1.8361799422143845e-05, + "loss": 1.4808, + "step": 2539 + }, + { + "epoch": 0.27, + "learning_rate": 1.835979137886675e-05, + "loss": 1.3515, + "step": 2540 + }, + { + "epoch": 0.27, + "learning_rate": 1.8357782215592412e-05, + "loss": 1.5284, + "step": 2541 + }, + { + "epoch": 0.27, + "learning_rate": 1.835577193259e-05, + "loss": 1.4222, + "step": 2542 + }, + { + "epoch": 0.27, + "learning_rate": 1.8353760530128846e-05, + "loss": 1.4522, + "step": 2543 + }, + { + "epoch": 0.27, + "learning_rate": 1.835174800847842e-05, + "loss": 1.4487, + "step": 2544 + }, + { + "epoch": 0.27, + "learning_rate": 1.8349734367908355e-05, + "loss": 1.3688, + "step": 2545 + }, + { + "epoch": 0.27, + "learning_rate": 1.8347719608688422e-05, + "loss": 1.483, + "step": 2546 + }, + { + "epoch": 0.27, + "learning_rate": 1.8345703731088554e-05, + "loss": 1.4733, + "step": 2547 + }, + { + "epoch": 0.27, + "learning_rate": 1.8343686735378816e-05, + "loss": 1.4594, + "step": 2548 + }, + { + "epoch": 0.27, + "learning_rate": 1.834166862182944e-05, + "loss": 1.4648, + "step": 2549 + }, + { + "epoch": 0.27, + "learning_rate": 1.8339649390710807e-05, + "loss": 1.5249, + "step": 2550 + }, + { + "epoch": 0.27, + "learning_rate": 1.8337629042293434e-05, + "loss": 1.4744, + "step": 2551 + }, + { + "epoch": 0.27, + "learning_rate": 1.8335607576847994e-05, + "loss": 1.5094, + "step": 2552 + }, + { + "epoch": 0.27, + "learning_rate": 1.8333584994645318e-05, + "loss": 1.5122, + "step": 2553 + }, + { + "epoch": 0.27, + "learning_rate": 1.8331561295956374e-05, + "loss": 1.537, + "step": 2554 + }, + { + "epoch": 0.27, + "learning_rate": 1.832953648105229e-05, + "loss": 1.4691, + "step": 2555 + }, + { + "epoch": 0.27, + "learning_rate": 1.8327510550204343e-05, + "loss": 1.4969, + "step": 2556 + }, + { + "epoch": 0.27, + "learning_rate": 1.8325483503683944e-05, + "loss": 1.4596, + "step": 2557 + }, + { + "epoch": 0.27, + "learning_rate": 1.8323455341762675e-05, + "loss": 1.435, + "step": 2558 + }, + { + "epoch": 0.27, + "learning_rate": 1.8321426064712255e-05, + "loss": 1.4883, + "step": 2559 + }, + { + "epoch": 0.27, + "learning_rate": 1.8319395672804554e-05, + "loss": 1.3758, + "step": 2560 + }, + { + "epoch": 0.27, + "learning_rate": 1.8317364166311592e-05, + "loss": 1.4352, + "step": 2561 + }, + { + "epoch": 0.27, + "learning_rate": 1.831533154550554e-05, + "loss": 1.5072, + "step": 2562 + }, + { + "epoch": 0.27, + "learning_rate": 1.8313297810658718e-05, + "loss": 1.4476, + "step": 2563 + }, + { + "epoch": 0.27, + "learning_rate": 1.831126296204359e-05, + "loss": 1.507, + "step": 2564 + }, + { + "epoch": 0.27, + "learning_rate": 1.8309226999932777e-05, + "loss": 1.4677, + "step": 2565 + }, + { + "epoch": 0.27, + "learning_rate": 1.8307189924599044e-05, + "loss": 1.4537, + "step": 2566 + }, + { + "epoch": 0.27, + "learning_rate": 1.8305151736315307e-05, + "loss": 1.4584, + "step": 2567 + }, + { + "epoch": 0.27, + "learning_rate": 1.8303112435354634e-05, + "loss": 1.4944, + "step": 2568 + }, + { + "epoch": 0.27, + "learning_rate": 1.8301072021990232e-05, + "loss": 1.4379, + "step": 2569 + }, + { + "epoch": 0.27, + "learning_rate": 1.8299030496495475e-05, + "loss": 1.539, + "step": 2570 + }, + { + "epoch": 0.27, + "learning_rate": 1.829698785914386e-05, + "loss": 1.4421, + "step": 2571 + }, + { + "epoch": 0.27, + "learning_rate": 1.8294944110209063e-05, + "loss": 1.4693, + "step": 2572 + }, + { + "epoch": 0.27, + "learning_rate": 1.8292899249964887e-05, + "loss": 1.3239, + "step": 2573 + }, + { + "epoch": 0.27, + "learning_rate": 1.8290853278685284e-05, + "loss": 1.472, + "step": 2574 + }, + { + "epoch": 0.27, + "learning_rate": 1.8288806196644374e-05, + "loss": 1.536, + "step": 2575 + }, + { + "epoch": 0.27, + "learning_rate": 1.8286758004116405e-05, + "loss": 1.4644, + "step": 2576 + }, + { + "epoch": 0.27, + "learning_rate": 1.8284708701375783e-05, + "loss": 1.4537, + "step": 2577 + }, + { + "epoch": 0.27, + "learning_rate": 1.8282658288697067e-05, + "loss": 1.4359, + "step": 2578 + }, + { + "epoch": 0.27, + "learning_rate": 1.8280606766354955e-05, + "loss": 1.4842, + "step": 2579 + }, + { + "epoch": 0.27, + "learning_rate": 1.8278554134624302e-05, + "loss": 1.4664, + "step": 2580 + }, + { + "epoch": 0.27, + "learning_rate": 1.8276500393780105e-05, + "loss": 1.4632, + "step": 2581 + }, + { + "epoch": 0.27, + "learning_rate": 1.827444554409751e-05, + "loss": 1.4996, + "step": 2582 + }, + { + "epoch": 0.27, + "learning_rate": 1.827238958585182e-05, + "loss": 1.3399, + "step": 2583 + }, + { + "epoch": 0.27, + "learning_rate": 1.8270332519318476e-05, + "loss": 1.3928, + "step": 2584 + }, + { + "epoch": 0.27, + "learning_rate": 1.8268274344773074e-05, + "loss": 1.4993, + "step": 2585 + }, + { + "epoch": 0.27, + "learning_rate": 1.8266215062491356e-05, + "loss": 1.5398, + "step": 2586 + }, + { + "epoch": 0.27, + "learning_rate": 1.826415467274921e-05, + "loss": 1.4353, + "step": 2587 + }, + { + "epoch": 0.27, + "eval_loss": 1.5104212760925293, + "eval_runtime": 77.3448, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2587 + }, + { + "epoch": 0.27, + "learning_rate": 1.8262093175822685e-05, + "loss": 1.4889, + "step": 2588 + }, + { + "epoch": 0.27, + "learning_rate": 1.826003057198796e-05, + "loss": 1.4912, + "step": 2589 + }, + { + "epoch": 0.27, + "learning_rate": 1.825796686152137e-05, + "loss": 1.4884, + "step": 2590 + }, + { + "epoch": 0.27, + "learning_rate": 1.8255902044699404e-05, + "loss": 1.478, + "step": 2591 + }, + { + "epoch": 0.27, + "learning_rate": 1.8253836121798692e-05, + "loss": 1.6549, + "step": 2592 + }, + { + "epoch": 0.27, + "learning_rate": 1.8251769093096018e-05, + "loss": 1.5146, + "step": 2593 + }, + { + "epoch": 0.27, + "learning_rate": 1.8249700958868306e-05, + "loss": 1.4797, + "step": 2594 + }, + { + "epoch": 0.27, + "learning_rate": 1.8247631719392634e-05, + "loss": 1.4655, + "step": 2595 + }, + { + "epoch": 0.27, + "learning_rate": 1.824556137494623e-05, + "loss": 1.4517, + "step": 2596 + }, + { + "epoch": 0.27, + "learning_rate": 1.8243489925806458e-05, + "loss": 1.4936, + "step": 2597 + }, + { + "epoch": 0.27, + "learning_rate": 1.8241417372250852e-05, + "loss": 1.4614, + "step": 2598 + }, + { + "epoch": 0.27, + "learning_rate": 1.8239343714557073e-05, + "loss": 1.4475, + "step": 2599 + }, + { + "epoch": 0.27, + "learning_rate": 1.8237268953002937e-05, + "loss": 1.5435, + "step": 2600 + }, + { + "epoch": 0.27, + "learning_rate": 1.8235193087866413e-05, + "loss": 1.4616, + "step": 2601 + }, + { + "epoch": 0.27, + "learning_rate": 1.8233116119425612e-05, + "loss": 1.4578, + "step": 2602 + }, + { + "epoch": 0.27, + "learning_rate": 1.8231038047958795e-05, + "loss": 1.434, + "step": 2603 + }, + { + "epoch": 0.27, + "learning_rate": 1.8228958873744368e-05, + "loss": 1.5335, + "step": 2604 + }, + { + "epoch": 0.27, + "learning_rate": 1.8226878597060887e-05, + "loss": 1.415, + "step": 2605 + }, + { + "epoch": 0.27, + "learning_rate": 1.8224797218187058e-05, + "loss": 1.6165, + "step": 2606 + }, + { + "epoch": 0.27, + "learning_rate": 1.822271473740173e-05, + "loss": 1.372, + "step": 2607 + }, + { + "epoch": 0.27, + "learning_rate": 1.8220631154983907e-05, + "loss": 1.4855, + "step": 2608 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218546471212727e-05, + "loss": 1.4093, + "step": 2609 + }, + { + "epoch": 0.27, + "learning_rate": 1.821646068636749e-05, + "loss": 1.4852, + "step": 2610 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214373800727637e-05, + "loss": 1.6959, + "step": 2611 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212285814572755e-05, + "loss": 1.3874, + "step": 2612 + }, + { + "epoch": 0.27, + "learning_rate": 1.821019672818258e-05, + "loss": 1.4425, + "step": 2613 + }, + { + "epoch": 0.27, + "learning_rate": 1.8208106541837e-05, + "loss": 1.6097, + "step": 2614 + }, + { + "epoch": 0.27, + "learning_rate": 1.8206015255816045e-05, + "loss": 1.5675, + "step": 2615 + }, + { + "epoch": 0.27, + "learning_rate": 1.820392287039989e-05, + "loss": 1.4039, + "step": 2616 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201829385868866e-05, + "loss": 1.4872, + "step": 2617 + }, + { + "epoch": 0.27, + "learning_rate": 1.819973480250344e-05, + "loss": 1.4645, + "step": 2618 + }, + { + "epoch": 0.27, + "learning_rate": 1.8197639120584237e-05, + "loss": 1.4923, + "step": 2619 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195542340392025e-05, + "loss": 1.4294, + "step": 2620 + }, + { + "epoch": 0.27, + "learning_rate": 1.8193444462207717e-05, + "loss": 1.4315, + "step": 2621 + }, + { + "epoch": 0.27, + "learning_rate": 1.8191345486312372e-05, + "loss": 1.3972, + "step": 2622 + }, + { + "epoch": 0.28, + "learning_rate": 1.8189245412987205e-05, + "loss": 1.462, + "step": 2623 + }, + { + "epoch": 0.28, + "learning_rate": 1.8187144242513567e-05, + "loss": 1.4738, + "step": 2624 + }, + { + "epoch": 0.28, + "learning_rate": 1.818504197517296e-05, + "loss": 1.4935, + "step": 2625 + }, + { + "epoch": 0.28, + "learning_rate": 1.8182938611247038e-05, + "loss": 1.4231, + "step": 2626 + }, + { + "epoch": 0.28, + "learning_rate": 1.81808341510176e-05, + "loss": 1.4031, + "step": 2627 + }, + { + "epoch": 0.28, + "learning_rate": 1.817872859476658e-05, + "loss": 1.5822, + "step": 2628 + }, + { + "epoch": 0.28, + "learning_rate": 1.8176621942776075e-05, + "loss": 1.432, + "step": 2629 + }, + { + "epoch": 0.28, + "learning_rate": 1.8174514195328324e-05, + "loss": 1.5565, + "step": 2630 + }, + { + "epoch": 0.28, + "learning_rate": 1.8172405352705704e-05, + "loss": 1.4895, + "step": 2631 + }, + { + "epoch": 0.28, + "learning_rate": 1.8170295415190754e-05, + "loss": 1.4032, + "step": 2632 + }, + { + "epoch": 0.28, + "learning_rate": 1.8168184383066144e-05, + "loss": 1.4253, + "step": 2633 + }, + { + "epoch": 0.28, + "learning_rate": 1.8166072256614702e-05, + "loss": 1.5162, + "step": 2634 + }, + { + "epoch": 0.28, + "learning_rate": 1.81639590361194e-05, + "loss": 1.4609, + "step": 2635 + }, + { + "epoch": 0.28, + "learning_rate": 1.816184472186335e-05, + "loss": 1.4351, + "step": 2636 + }, + { + "epoch": 0.28, + "learning_rate": 1.8159729314129823e-05, + "loss": 1.4738, + "step": 2637 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157612813202224e-05, + "loss": 1.5986, + "step": 2638 + }, + { + "epoch": 0.28, + "learning_rate": 1.815549521936411e-05, + "loss": 1.4633, + "step": 2639 + }, + { + "epoch": 0.28, + "learning_rate": 1.8153376532899184e-05, + "loss": 1.4404, + "step": 2640 + }, + { + "epoch": 0.28, + "learning_rate": 1.81512567540913e-05, + "loss": 1.4256, + "step": 2641 + }, + { + "epoch": 0.28, + "learning_rate": 1.814913588322445e-05, + "loss": 1.4054, + "step": 2642 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147013920582773e-05, + "loss": 1.4134, + "step": 2643 + }, + { + "epoch": 0.28, + "learning_rate": 1.8144890866450567e-05, + "loss": 1.4098, + "step": 2644 + }, + { + "epoch": 0.28, + "learning_rate": 1.814276672111226e-05, + "loss": 1.4593, + "step": 2645 + }, + { + "epoch": 0.28, + "learning_rate": 1.814064148485243e-05, + "loss": 1.4679, + "step": 2646 + }, + { + "epoch": 0.28, + "learning_rate": 1.8138515157955812e-05, + "loss": 1.5234, + "step": 2647 + }, + { + "epoch": 0.28, + "learning_rate": 1.8136387740707272e-05, + "loss": 1.4568, + "step": 2648 + }, + { + "epoch": 0.28, + "learning_rate": 1.8134259233391836e-05, + "loss": 1.5057, + "step": 2649 + }, + { + "epoch": 0.28, + "learning_rate": 1.8132129636294665e-05, + "loss": 1.3643, + "step": 2650 + }, + { + "epoch": 0.28, + "learning_rate": 1.812999894970107e-05, + "loss": 1.4766, + "step": 2651 + }, + { + "epoch": 0.28, + "learning_rate": 1.812786717389651e-05, + "loss": 1.5701, + "step": 2652 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125734309166587e-05, + "loss": 1.5341, + "step": 2653 + }, + { + "epoch": 0.28, + "learning_rate": 1.812360035579705e-05, + "loss": 1.3596, + "step": 2654 + }, + { + "epoch": 0.28, + "learning_rate": 1.8121465314073793e-05, + "loss": 1.4847, + "step": 2655 + }, + { + "epoch": 0.28, + "learning_rate": 1.811932918428286e-05, + "loss": 1.4664, + "step": 2656 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117191966710438e-05, + "loss": 1.4673, + "step": 2657 + }, + { + "epoch": 0.28, + "learning_rate": 1.8115053661642856e-05, + "loss": 1.4712, + "step": 2658 + }, + { + "epoch": 0.28, + "learning_rate": 1.811291426936659e-05, + "loss": 1.4458, + "step": 2659 + }, + { + "epoch": 0.28, + "learning_rate": 1.811077379016827e-05, + "loss": 1.4667, + "step": 2660 + }, + { + "epoch": 0.28, + "learning_rate": 1.810863222433466e-05, + "loss": 1.4695, + "step": 2661 + }, + { + "epoch": 0.28, + "learning_rate": 1.8106489572152677e-05, + "loss": 1.5263, + "step": 2662 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104345833909376e-05, + "loss": 1.4148, + "step": 2663 + }, + { + "epoch": 0.28, + "learning_rate": 1.8102201009891976e-05, + "loss": 1.3955, + "step": 2664 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100055100387814e-05, + "loss": 1.6056, + "step": 2665 + }, + { + "epoch": 0.28, + "learning_rate": 1.8097908105684396e-05, + "loss": 1.5394, + "step": 2666 + }, + { + "epoch": 0.28, + "learning_rate": 1.809576002606936e-05, + "loss": 1.479, + "step": 2667 + }, + { + "epoch": 0.28, + "learning_rate": 1.8093610861830494e-05, + "loss": 1.4492, + "step": 2668 + }, + { + "epoch": 0.28, + "learning_rate": 1.8091460613255728e-05, + "loss": 1.4172, + "step": 2669 + }, + { + "epoch": 0.28, + "learning_rate": 1.808930928063315e-05, + "loss": 1.4498, + "step": 2670 + }, + { + "epoch": 0.28, + "learning_rate": 1.808715686425097e-05, + "loss": 1.6203, + "step": 2671 + }, + { + "epoch": 0.28, + "learning_rate": 1.8085003364397567e-05, + "loss": 1.435, + "step": 2672 + }, + { + "epoch": 0.28, + "learning_rate": 1.808284878136145e-05, + "loss": 1.4489, + "step": 2673 + }, + { + "epoch": 0.28, + "learning_rate": 1.8080693115431277e-05, + "loss": 1.4416, + "step": 2674 + }, + { + "epoch": 0.28, + "learning_rate": 1.8078536366895853e-05, + "loss": 1.422, + "step": 2675 + }, + { + "epoch": 0.28, + "learning_rate": 1.8076378536044128e-05, + "loss": 1.4039, + "step": 2676 + }, + { + "epoch": 0.28, + "learning_rate": 1.8074219623165195e-05, + "loss": 1.4705, + "step": 2677 + }, + { + "epoch": 0.28, + "learning_rate": 1.807205962854829e-05, + "loss": 1.5031, + "step": 2678 + }, + { + "epoch": 0.28, + "learning_rate": 1.8069898552482806e-05, + "loss": 1.4812, + "step": 2679 + }, + { + "epoch": 0.28, + "learning_rate": 1.806773639525826e-05, + "loss": 1.4129, + "step": 2680 + }, + { + "epoch": 0.28, + "learning_rate": 1.8065573157164332e-05, + "loss": 1.4559, + "step": 2681 + }, + { + "epoch": 0.28, + "learning_rate": 1.806340883849084e-05, + "loss": 1.3878, + "step": 2682 + }, + { + "epoch": 0.28, + "learning_rate": 1.8061243439527744e-05, + "loss": 1.4752, + "step": 2683 + }, + { + "epoch": 0.28, + "learning_rate": 1.8059076960565156e-05, + "loss": 1.4089, + "step": 2684 + }, + { + "epoch": 0.28, + "learning_rate": 1.8056909401893326e-05, + "loss": 1.4736, + "step": 2685 + }, + { + "epoch": 0.28, + "learning_rate": 1.8054740763802654e-05, + "loss": 1.3796, + "step": 2686 + }, + { + "epoch": 0.28, + "learning_rate": 1.805257104658368e-05, + "loss": 1.4412, + "step": 2687 + }, + { + "epoch": 0.28, + "learning_rate": 1.8050400250527086e-05, + "loss": 1.4639, + "step": 2688 + }, + { + "epoch": 0.28, + "learning_rate": 1.804822837592371e-05, + "loss": 1.4076, + "step": 2689 + }, + { + "epoch": 0.28, + "learning_rate": 1.804605542306452e-05, + "loss": 1.4627, + "step": 2690 + }, + { + "epoch": 0.28, + "learning_rate": 1.8043881392240642e-05, + "loss": 1.5249, + "step": 2691 + }, + { + "epoch": 0.28, + "learning_rate": 1.804170628374334e-05, + "loss": 1.4312, + "step": 2692 + }, + { + "epoch": 0.28, + "learning_rate": 1.803953009786402e-05, + "loss": 1.5676, + "step": 2693 + }, + { + "epoch": 0.28, + "learning_rate": 1.8037352834894233e-05, + "loss": 1.5072, + "step": 2694 + }, + { + "epoch": 0.28, + "learning_rate": 1.803517449512568e-05, + "loss": 1.5662, + "step": 2695 + }, + { + "epoch": 0.28, + "learning_rate": 1.8032995078850207e-05, + "loss": 1.4771, + "step": 2696 + }, + { + "epoch": 0.28, + "learning_rate": 1.803081458635979e-05, + "loss": 1.412, + "step": 2697 + }, + { + "epoch": 0.28, + "learning_rate": 1.8028633017946564e-05, + "loss": 1.497, + "step": 2698 + }, + { + "epoch": 0.28, + "learning_rate": 1.8026450373902804e-05, + "loss": 1.4528, + "step": 2699 + }, + { + "epoch": 0.28, + "learning_rate": 1.802426665452093e-05, + "loss": 1.4785, + "step": 2700 + }, + { + "epoch": 0.28, + "learning_rate": 1.8022081860093493e-05, + "loss": 1.6411, + "step": 2701 + }, + { + "epoch": 0.28, + "learning_rate": 1.8019895990913213e-05, + "loss": 1.4459, + "step": 2702 + }, + { + "epoch": 0.28, + "learning_rate": 1.8017709047272932e-05, + "loss": 1.4418, + "step": 2703 + }, + { + "epoch": 0.28, + "learning_rate": 1.801552102946565e-05, + "loss": 1.4409, + "step": 2704 + }, + { + "epoch": 0.28, + "learning_rate": 1.8013331937784498e-05, + "loss": 1.4651, + "step": 2705 + }, + { + "epoch": 0.28, + "learning_rate": 1.8011141772522766e-05, + "loss": 1.4161, + "step": 2706 + }, + { + "epoch": 0.28, + "learning_rate": 1.8008950533973876e-05, + "loss": 1.458, + "step": 2707 + }, + { + "epoch": 0.28, + "learning_rate": 1.8006758222431398e-05, + "loss": 1.4477, + "step": 2708 + }, + { + "epoch": 0.28, + "learning_rate": 1.800456483818904e-05, + "loss": 1.4433, + "step": 2709 + }, + { + "epoch": 0.28, + "learning_rate": 1.8002370381540672e-05, + "loss": 1.5005, + "step": 2710 + }, + { + "epoch": 0.28, + "learning_rate": 1.8000174852780282e-05, + "loss": 1.4945, + "step": 2711 + }, + { + "epoch": 0.28, + "learning_rate": 1.7997978252202023e-05, + "loss": 1.4298, + "step": 2712 + }, + { + "epoch": 0.28, + "learning_rate": 1.7995780580100177e-05, + "loss": 1.3812, + "step": 2713 + }, + { + "epoch": 0.28, + "learning_rate": 1.799358183676918e-05, + "loss": 1.5559, + "step": 2714 + }, + { + "epoch": 0.28, + "learning_rate": 1.79913820225036e-05, + "loss": 1.4316, + "step": 2715 + }, + { + "epoch": 0.28, + "learning_rate": 1.798918113759817e-05, + "loss": 1.419, + "step": 2716 + }, + { + "epoch": 0.28, + "learning_rate": 1.7986979182347733e-05, + "loss": 1.43, + "step": 2717 + }, + { + "epoch": 0.29, + "learning_rate": 1.798477615704731e-05, + "loss": 1.4964, + "step": 2718 + }, + { + "epoch": 0.29, + "learning_rate": 1.7982572061992044e-05, + "loss": 1.4417, + "step": 2719 + }, + { + "epoch": 0.29, + "learning_rate": 1.7980366897477227e-05, + "loss": 1.4562, + "step": 2720 + }, + { + "epoch": 0.29, + "learning_rate": 1.7978160663798295e-05, + "loss": 1.4386, + "step": 2721 + }, + { + "epoch": 0.29, + "learning_rate": 1.7975953361250824e-05, + "loss": 1.445, + "step": 2722 + }, + { + "epoch": 0.29, + "learning_rate": 1.797374499013054e-05, + "loss": 1.4549, + "step": 2723 + }, + { + "epoch": 0.29, + "learning_rate": 1.7971535550733305e-05, + "loss": 1.5205, + "step": 2724 + }, + { + "epoch": 0.29, + "learning_rate": 1.796932504335513e-05, + "loss": 1.4632, + "step": 2725 + }, + { + "epoch": 0.29, + "learning_rate": 1.796711346829216e-05, + "loss": 1.3767, + "step": 2726 + }, + { + "epoch": 0.29, + "learning_rate": 1.79649008258407e-05, + "loss": 1.4098, + "step": 2727 + }, + { + "epoch": 0.29, + "learning_rate": 1.7962687116297178e-05, + "loss": 1.4675, + "step": 2728 + }, + { + "epoch": 0.29, + "learning_rate": 1.7960472339958176e-05, + "loss": 1.6048, + "step": 2729 + }, + { + "epoch": 0.29, + "learning_rate": 1.7958256497120418e-05, + "loss": 1.5432, + "step": 2730 + }, + { + "epoch": 0.29, + "learning_rate": 1.7956039588080774e-05, + "loss": 1.5453, + "step": 2731 + }, + { + "epoch": 0.29, + "learning_rate": 1.7953821613136246e-05, + "loss": 1.4246, + "step": 2732 + }, + { + "epoch": 0.29, + "learning_rate": 1.7951602572583988e-05, + "loss": 1.3987, + "step": 2733 + }, + { + "epoch": 0.29, + "learning_rate": 1.7949382466721295e-05, + "loss": 1.4943, + "step": 2734 + }, + { + "epoch": 0.29, + "learning_rate": 1.7947161295845606e-05, + "loss": 1.4385, + "step": 2735 + }, + { + "epoch": 0.29, + "learning_rate": 1.7944939060254497e-05, + "loss": 1.4165, + "step": 2736 + }, + { + "epoch": 0.29, + "learning_rate": 1.7942715760245692e-05, + "loss": 1.4004, + "step": 2737 + }, + { + "epoch": 0.29, + "learning_rate": 1.7940491396117063e-05, + "loss": 1.4577, + "step": 2738 + }, + { + "epoch": 0.29, + "learning_rate": 1.7938265968166602e-05, + "loss": 1.4649, + "step": 2739 + }, + { + "epoch": 0.29, + "learning_rate": 1.7936039476692473e-05, + "loss": 1.5273, + "step": 2740 + }, + { + "epoch": 0.29, + "learning_rate": 1.7933811921992962e-05, + "loss": 1.4325, + "step": 2741 + }, + { + "epoch": 0.29, + "learning_rate": 1.793158330436651e-05, + "loss": 1.4388, + "step": 2742 + }, + { + "epoch": 0.29, + "learning_rate": 1.7929353624111687e-05, + "loss": 1.4124, + "step": 2743 + }, + { + "epoch": 0.29, + "learning_rate": 1.7927122881527222e-05, + "loss": 1.5449, + "step": 2744 + }, + { + "epoch": 0.29, + "learning_rate": 1.7924891076911964e-05, + "loss": 1.4728, + "step": 2745 + }, + { + "epoch": 0.29, + "learning_rate": 1.7922658210564932e-05, + "loss": 1.5103, + "step": 2746 + }, + { + "epoch": 0.29, + "learning_rate": 1.792042428278526e-05, + "loss": 1.5975, + "step": 2747 + }, + { + "epoch": 0.29, + "learning_rate": 1.7918189293872247e-05, + "loss": 1.567, + "step": 2748 + }, + { + "epoch": 0.29, + "learning_rate": 1.7915953244125318e-05, + "loss": 1.57, + "step": 2749 + }, + { + "epoch": 0.29, + "learning_rate": 1.791371613384405e-05, + "loss": 1.4372, + "step": 2750 + }, + { + "epoch": 0.29, + "learning_rate": 1.7911477963328155e-05, + "loss": 1.4053, + "step": 2751 + }, + { + "epoch": 0.29, + "learning_rate": 1.7909238732877492e-05, + "loss": 1.3782, + "step": 2752 + }, + { + "epoch": 0.29, + "learning_rate": 1.790699844279206e-05, + "loss": 1.4401, + "step": 2753 + }, + { + "epoch": 0.29, + "learning_rate": 1.7904757093372e-05, + "loss": 1.3749, + "step": 2754 + }, + { + "epoch": 0.29, + "learning_rate": 1.79025146849176e-05, + "loss": 1.4909, + "step": 2755 + }, + { + "epoch": 0.29, + "learning_rate": 1.7900271217729273e-05, + "loss": 1.4103, + "step": 2756 + }, + { + "epoch": 0.29, + "learning_rate": 1.7898026692107597e-05, + "loss": 1.4986, + "step": 2757 + }, + { + "epoch": 0.29, + "learning_rate": 1.7895781108353278e-05, + "loss": 1.5449, + "step": 2758 + }, + { + "epoch": 0.29, + "learning_rate": 1.789353446676717e-05, + "loss": 1.5583, + "step": 2759 + }, + { + "epoch": 0.29, + "learning_rate": 1.7891286767650254e-05, + "loss": 1.5342, + "step": 2760 + }, + { + "epoch": 0.29, + "learning_rate": 1.7889038011303673e-05, + "loss": 1.4233, + "step": 2761 + }, + { + "epoch": 0.29, + "learning_rate": 1.7886788198028707e-05, + "loss": 1.3433, + "step": 2762 + }, + { + "epoch": 0.29, + "learning_rate": 1.788453732812676e-05, + "loss": 1.4451, + "step": 2763 + }, + { + "epoch": 0.29, + "learning_rate": 1.78822854018994e-05, + "loss": 1.4506, + "step": 2764 + }, + { + "epoch": 0.29, + "learning_rate": 1.7880032419648324e-05, + "loss": 1.4386, + "step": 2765 + }, + { + "epoch": 0.29, + "learning_rate": 1.7877778381675374e-05, + "loss": 1.4512, + "step": 2766 + }, + { + "epoch": 0.29, + "learning_rate": 1.7875523288282535e-05, + "loss": 1.4319, + "step": 2767 + }, + { + "epoch": 0.29, + "learning_rate": 1.7873267139771932e-05, + "loss": 1.4753, + "step": 2768 + }, + { + "epoch": 0.29, + "learning_rate": 1.787100993644583e-05, + "loss": 1.4044, + "step": 2769 + }, + { + "epoch": 0.29, + "learning_rate": 1.786875167860663e-05, + "loss": 1.4382, + "step": 2770 + }, + { + "epoch": 0.29, + "learning_rate": 1.786649236655689e-05, + "loss": 1.3977, + "step": 2771 + }, + { + "epoch": 0.29, + "learning_rate": 1.7864232000599298e-05, + "loss": 1.4473, + "step": 2772 + }, + { + "epoch": 0.29, + "learning_rate": 1.7861970581036678e-05, + "loss": 1.4666, + "step": 2773 + }, + { + "epoch": 0.29, + "learning_rate": 1.785970810817201e-05, + "loss": 1.5299, + "step": 2774 + }, + { + "epoch": 0.29, + "learning_rate": 1.7857444582308402e-05, + "loss": 1.3974, + "step": 2775 + }, + { + "epoch": 0.29, + "learning_rate": 1.7855180003749114e-05, + "loss": 1.4603, + "step": 2776 + }, + { + "epoch": 0.29, + "learning_rate": 1.7852914372797535e-05, + "loss": 1.463, + "step": 2777 + }, + { + "epoch": 0.29, + "learning_rate": 1.7850647689757205e-05, + "loss": 1.5317, + "step": 2778 + }, + { + "epoch": 0.29, + "learning_rate": 1.78483799549318e-05, + "loss": 1.4669, + "step": 2779 + }, + { + "epoch": 0.29, + "learning_rate": 1.784611116862514e-05, + "loss": 1.5293, + "step": 2780 + }, + { + "epoch": 0.29, + "learning_rate": 1.7843841331141177e-05, + "loss": 1.5802, + "step": 2781 + }, + { + "epoch": 0.29, + "learning_rate": 1.7841570442784024e-05, + "loss": 1.4486, + "step": 2782 + }, + { + "epoch": 0.29, + "learning_rate": 1.7839298503857913e-05, + "loss": 1.4674, + "step": 2783 + }, + { + "epoch": 0.29, + "learning_rate": 1.7837025514667224e-05, + "loss": 1.4662, + "step": 2784 + }, + { + "epoch": 0.29, + "learning_rate": 1.7834751475516484e-05, + "loss": 1.3555, + "step": 2785 + }, + { + "epoch": 0.29, + "learning_rate": 1.783247638671035e-05, + "loss": 1.4307, + "step": 2786 + }, + { + "epoch": 0.29, + "eval_loss": 1.500258445739746, + "eval_runtime": 77.406, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 2786 + }, + { + "epoch": 0.29, + "learning_rate": 1.7830200248553633e-05, + "loss": 1.4596, + "step": 2787 + }, + { + "epoch": 0.29, + "learning_rate": 1.7827923061351273e-05, + "loss": 1.6118, + "step": 2788 + }, + { + "epoch": 0.29, + "learning_rate": 1.7825644825408353e-05, + "loss": 1.4782, + "step": 2789 + }, + { + "epoch": 0.29, + "learning_rate": 1.78233655410301e-05, + "loss": 1.4681, + "step": 2790 + }, + { + "epoch": 0.29, + "learning_rate": 1.782108520852188e-05, + "loss": 1.6281, + "step": 2791 + }, + { + "epoch": 0.29, + "learning_rate": 1.78188038281892e-05, + "loss": 1.4446, + "step": 2792 + }, + { + "epoch": 0.29, + "learning_rate": 1.7816521400337704e-05, + "loss": 1.479, + "step": 2793 + }, + { + "epoch": 0.29, + "learning_rate": 1.7814237925273178e-05, + "loss": 1.5457, + "step": 2794 + }, + { + "epoch": 0.29, + "learning_rate": 1.7811953403301547e-05, + "loss": 1.3928, + "step": 2795 + }, + { + "epoch": 0.29, + "learning_rate": 1.780966783472889e-05, + "loss": 1.4321, + "step": 2796 + }, + { + "epoch": 0.29, + "learning_rate": 1.78073812198614e-05, + "loss": 1.5734, + "step": 2797 + }, + { + "epoch": 0.29, + "learning_rate": 1.7805093559005432e-05, + "loss": 1.4356, + "step": 2798 + }, + { + "epoch": 0.29, + "learning_rate": 1.7802804852467473e-05, + "loss": 1.4656, + "step": 2799 + }, + { + "epoch": 0.29, + "learning_rate": 1.780051510055415e-05, + "loss": 1.4052, + "step": 2800 + }, + { + "epoch": 0.29, + "learning_rate": 1.7798224303572228e-05, + "loss": 1.4758, + "step": 2801 + }, + { + "epoch": 0.29, + "learning_rate": 1.7795932461828622e-05, + "loss": 1.4326, + "step": 2802 + }, + { + "epoch": 0.29, + "learning_rate": 1.7793639575630376e-05, + "loss": 1.3409, + "step": 2803 + }, + { + "epoch": 0.29, + "learning_rate": 1.7791345645284678e-05, + "loss": 1.4175, + "step": 2804 + }, + { + "epoch": 0.29, + "learning_rate": 1.7789050671098853e-05, + "loss": 1.383, + "step": 2805 + }, + { + "epoch": 0.29, + "learning_rate": 1.7786754653380373e-05, + "loss": 1.5162, + "step": 2806 + }, + { + "epoch": 0.29, + "learning_rate": 1.7784457592436847e-05, + "loss": 1.4899, + "step": 2807 + }, + { + "epoch": 0.29, + "learning_rate": 1.7782159488576016e-05, + "loss": 1.4874, + "step": 2808 + }, + { + "epoch": 0.29, + "learning_rate": 1.777986034210577e-05, + "loss": 1.4363, + "step": 2809 + }, + { + "epoch": 0.29, + "learning_rate": 1.7777560153334134e-05, + "loss": 1.4223, + "step": 2810 + }, + { + "epoch": 0.29, + "learning_rate": 1.7775258922569273e-05, + "loss": 1.4792, + "step": 2811 + }, + { + "epoch": 0.29, + "learning_rate": 1.77729566501195e-05, + "loss": 1.4475, + "step": 2812 + }, + { + "epoch": 0.29, + "learning_rate": 1.7770653336293253e-05, + "loss": 1.5157, + "step": 2813 + }, + { + "epoch": 0.3, + "learning_rate": 1.776834898139912e-05, + "loss": 1.389, + "step": 2814 + }, + { + "epoch": 0.3, + "learning_rate": 1.7766043585745824e-05, + "loss": 1.4358, + "step": 2815 + }, + { + "epoch": 0.3, + "learning_rate": 1.776373714964223e-05, + "loss": 1.4297, + "step": 2816 + }, + { + "epoch": 0.3, + "learning_rate": 1.7761429673397344e-05, + "loss": 1.4102, + "step": 2817 + }, + { + "epoch": 0.3, + "learning_rate": 1.77591211573203e-05, + "loss": 1.4572, + "step": 2818 + }, + { + "epoch": 0.3, + "learning_rate": 1.775681160172039e-05, + "loss": 1.448, + "step": 2819 + }, + { + "epoch": 0.3, + "learning_rate": 1.7754501006907025e-05, + "loss": 1.4426, + "step": 2820 + }, + { + "epoch": 0.3, + "learning_rate": 1.7752189373189773e-05, + "loss": 1.4566, + "step": 2821 + }, + { + "epoch": 0.3, + "learning_rate": 1.7749876700878332e-05, + "loss": 1.4267, + "step": 2822 + }, + { + "epoch": 0.3, + "learning_rate": 1.7747562990282538e-05, + "loss": 1.3951, + "step": 2823 + }, + { + "epoch": 0.3, + "learning_rate": 1.7745248241712373e-05, + "loss": 1.4668, + "step": 2824 + }, + { + "epoch": 0.3, + "learning_rate": 1.774293245547795e-05, + "loss": 1.4924, + "step": 2825 + }, + { + "epoch": 0.3, + "learning_rate": 1.7740615631889525e-05, + "loss": 1.5258, + "step": 2826 + }, + { + "epoch": 0.3, + "learning_rate": 1.7738297771257496e-05, + "loss": 1.4323, + "step": 2827 + }, + { + "epoch": 0.3, + "learning_rate": 1.7735978873892393e-05, + "loss": 1.439, + "step": 2828 + }, + { + "epoch": 0.3, + "learning_rate": 1.773365894010489e-05, + "loss": 1.5658, + "step": 2829 + }, + { + "epoch": 0.3, + "learning_rate": 1.77313379702058e-05, + "loss": 1.4607, + "step": 2830 + }, + { + "epoch": 0.3, + "learning_rate": 1.7729015964506073e-05, + "loss": 1.5544, + "step": 2831 + }, + { + "epoch": 0.3, + "learning_rate": 1.7726692923316798e-05, + "loss": 1.4232, + "step": 2832 + }, + { + "epoch": 0.3, + "learning_rate": 1.77243688469492e-05, + "loss": 1.415, + "step": 2833 + }, + { + "epoch": 0.3, + "learning_rate": 1.772204373571465e-05, + "loss": 1.4658, + "step": 2834 + }, + { + "epoch": 0.3, + "learning_rate": 1.7719717589924647e-05, + "loss": 1.4678, + "step": 2835 + }, + { + "epoch": 0.3, + "learning_rate": 1.771739040989084e-05, + "loss": 1.3021, + "step": 2836 + }, + { + "epoch": 0.3, + "learning_rate": 1.771506219592501e-05, + "loss": 1.4045, + "step": 2837 + }, + { + "epoch": 0.3, + "learning_rate": 1.7712732948339085e-05, + "loss": 1.4593, + "step": 2838 + }, + { + "epoch": 0.3, + "learning_rate": 1.7710402667445108e-05, + "loss": 1.4175, + "step": 2839 + }, + { + "epoch": 0.3, + "learning_rate": 1.770807135355529e-05, + "loss": 1.3939, + "step": 2840 + }, + { + "epoch": 0.3, + "learning_rate": 1.7705739006981963e-05, + "loss": 1.6089, + "step": 2841 + }, + { + "epoch": 0.3, + "learning_rate": 1.77034056280376e-05, + "loss": 1.3952, + "step": 2842 + }, + { + "epoch": 0.3, + "learning_rate": 1.7701071217034818e-05, + "loss": 1.5086, + "step": 2843 + }, + { + "epoch": 0.3, + "learning_rate": 1.7698735774286362e-05, + "loss": 1.4706, + "step": 2844 + }, + { + "epoch": 0.3, + "learning_rate": 1.7696399300105128e-05, + "loss": 1.4286, + "step": 2845 + }, + { + "epoch": 0.3, + "learning_rate": 1.7694061794804137e-05, + "loss": 1.4418, + "step": 2846 + }, + { + "epoch": 0.3, + "learning_rate": 1.7691723258696562e-05, + "loss": 1.516, + "step": 2847 + }, + { + "epoch": 0.3, + "learning_rate": 1.76893836920957e-05, + "loss": 1.4354, + "step": 2848 + }, + { + "epoch": 0.3, + "learning_rate": 1.7687043095314998e-05, + "loss": 1.7503, + "step": 2849 + }, + { + "epoch": 0.3, + "learning_rate": 1.7684701468668032e-05, + "loss": 1.5985, + "step": 2850 + }, + { + "epoch": 0.3, + "learning_rate": 1.768235881246852e-05, + "loss": 1.442, + "step": 2851 + }, + { + "epoch": 0.3, + "learning_rate": 1.7680015127030322e-05, + "loss": 1.4924, + "step": 2852 + }, + { + "epoch": 0.3, + "learning_rate": 1.7677670412667425e-05, + "loss": 1.4461, + "step": 2853 + }, + { + "epoch": 0.3, + "learning_rate": 1.7675324669693968e-05, + "loss": 1.3823, + "step": 2854 + }, + { + "epoch": 0.3, + "learning_rate": 1.767297789842421e-05, + "loss": 1.452, + "step": 2855 + }, + { + "epoch": 0.3, + "learning_rate": 1.767063009917257e-05, + "loss": 1.46, + "step": 2856 + }, + { + "epoch": 0.3, + "learning_rate": 1.7668281272253587e-05, + "loss": 1.4129, + "step": 2857 + }, + { + "epoch": 0.3, + "learning_rate": 1.766593141798194e-05, + "loss": 1.4057, + "step": 2858 + }, + { + "epoch": 0.3, + "learning_rate": 1.7663580536672456e-05, + "loss": 1.5162, + "step": 2859 + }, + { + "epoch": 0.3, + "learning_rate": 1.7661228628640087e-05, + "loss": 1.5177, + "step": 2860 + }, + { + "epoch": 0.3, + "learning_rate": 1.7658875694199933e-05, + "loss": 1.4548, + "step": 2861 + }, + { + "epoch": 0.3, + "learning_rate": 1.7656521733667223e-05, + "loss": 1.4511, + "step": 2862 + }, + { + "epoch": 0.3, + "learning_rate": 1.765416674735733e-05, + "loss": 1.4778, + "step": 2863 + }, + { + "epoch": 0.3, + "learning_rate": 1.765181073558576e-05, + "loss": 1.3935, + "step": 2864 + }, + { + "epoch": 0.3, + "learning_rate": 1.7649453698668156e-05, + "loss": 1.4659, + "step": 2865 + }, + { + "epoch": 0.3, + "learning_rate": 1.7647095636920305e-05, + "loss": 1.7042, + "step": 2866 + }, + { + "epoch": 0.3, + "learning_rate": 1.7644736550658124e-05, + "loss": 1.7957, + "step": 2867 + }, + { + "epoch": 0.3, + "learning_rate": 1.764237644019767e-05, + "loss": 1.5139, + "step": 2868 + }, + { + "epoch": 0.3, + "learning_rate": 1.764001530585514e-05, + "loss": 1.4117, + "step": 2869 + }, + { + "epoch": 0.3, + "learning_rate": 1.7637653147946858e-05, + "loss": 1.4837, + "step": 2870 + }, + { + "epoch": 0.3, + "learning_rate": 1.7635289966789298e-05, + "loss": 1.4379, + "step": 2871 + }, + { + "epoch": 0.3, + "learning_rate": 1.7632925762699068e-05, + "loss": 1.4491, + "step": 2872 + }, + { + "epoch": 0.3, + "learning_rate": 1.7630560535992905e-05, + "loss": 1.4006, + "step": 2873 + }, + { + "epoch": 0.3, + "learning_rate": 1.7628194286987694e-05, + "loss": 1.5484, + "step": 2874 + }, + { + "epoch": 0.3, + "learning_rate": 1.7625827016000446e-05, + "loss": 1.4926, + "step": 2875 + }, + { + "epoch": 0.3, + "learning_rate": 1.762345872334832e-05, + "loss": 1.3909, + "step": 2876 + }, + { + "epoch": 0.3, + "learning_rate": 1.76210894093486e-05, + "loss": 1.405, + "step": 2877 + }, + { + "epoch": 0.3, + "learning_rate": 1.7618719074318718e-05, + "loss": 1.4736, + "step": 2878 + }, + { + "epoch": 0.3, + "learning_rate": 1.7616347718576238e-05, + "loss": 1.4445, + "step": 2879 + }, + { + "epoch": 0.3, + "learning_rate": 1.761397534243886e-05, + "loss": 1.4878, + "step": 2880 + }, + { + "epoch": 0.3, + "learning_rate": 1.7611601946224417e-05, + "loss": 1.4414, + "step": 2881 + }, + { + "epoch": 0.3, + "learning_rate": 1.760922753025089e-05, + "loss": 1.5657, + "step": 2882 + }, + { + "epoch": 0.3, + "learning_rate": 1.7606852094836385e-05, + "loss": 1.5008, + "step": 2883 + }, + { + "epoch": 0.3, + "learning_rate": 1.7604475640299153e-05, + "loss": 1.4922, + "step": 2884 + }, + { + "epoch": 0.3, + "learning_rate": 1.7602098166957577e-05, + "loss": 1.7451, + "step": 2885 + }, + { + "epoch": 0.3, + "learning_rate": 1.759971967513017e-05, + "loss": 1.7077, + "step": 2886 + }, + { + "epoch": 0.3, + "learning_rate": 1.75973401651356e-05, + "loss": 1.3986, + "step": 2887 + }, + { + "epoch": 0.3, + "learning_rate": 1.7594959637292656e-05, + "loss": 1.3966, + "step": 2888 + }, + { + "epoch": 0.3, + "learning_rate": 1.7592578091920264e-05, + "loss": 1.4086, + "step": 2889 + }, + { + "epoch": 0.3, + "learning_rate": 1.7590195529337495e-05, + "loss": 1.4481, + "step": 2890 + }, + { + "epoch": 0.3, + "learning_rate": 1.7587811949863548e-05, + "loss": 1.3974, + "step": 2891 + }, + { + "epoch": 0.3, + "learning_rate": 1.7585427353817758e-05, + "loss": 1.5013, + "step": 2892 + }, + { + "epoch": 0.3, + "learning_rate": 1.7583041741519608e-05, + "loss": 1.5454, + "step": 2893 + }, + { + "epoch": 0.3, + "learning_rate": 1.7580655113288708e-05, + "loss": 1.5033, + "step": 2894 + }, + { + "epoch": 0.3, + "learning_rate": 1.7578267469444793e-05, + "loss": 1.4332, + "step": 2895 + }, + { + "epoch": 0.3, + "learning_rate": 1.757587881030776e-05, + "loss": 1.4667, + "step": 2896 + }, + { + "epoch": 0.3, + "learning_rate": 1.7573489136197623e-05, + "loss": 1.4314, + "step": 2897 + }, + { + "epoch": 0.3, + "learning_rate": 1.7571098447434532e-05, + "loss": 1.4514, + "step": 2898 + }, + { + "epoch": 0.3, + "learning_rate": 1.7568706744338784e-05, + "loss": 1.4872, + "step": 2899 + }, + { + "epoch": 0.3, + "learning_rate": 1.7566314027230808e-05, + "loss": 1.4841, + "step": 2900 + }, + { + "epoch": 0.3, + "learning_rate": 1.7563920296431158e-05, + "loss": 1.3964, + "step": 2901 + }, + { + "epoch": 0.3, + "learning_rate": 1.7561525552260538e-05, + "loss": 1.4932, + "step": 2902 + }, + { + "epoch": 0.3, + "learning_rate": 1.755912979503978e-05, + "loss": 1.4153, + "step": 2903 + }, + { + "epoch": 0.3, + "learning_rate": 1.755673302508986e-05, + "loss": 1.4939, + "step": 2904 + }, + { + "epoch": 0.3, + "learning_rate": 1.755433524273187e-05, + "loss": 1.4437, + "step": 2905 + }, + { + "epoch": 0.3, + "learning_rate": 1.7551936448287067e-05, + "loss": 1.486, + "step": 2906 + }, + { + "epoch": 0.3, + "learning_rate": 1.754953664207682e-05, + "loss": 1.4362, + "step": 2907 + }, + { + "epoch": 0.3, + "learning_rate": 1.7547135824422635e-05, + "loss": 1.4954, + "step": 2908 + }, + { + "epoch": 0.31, + "learning_rate": 1.7544733995646174e-05, + "loss": 1.4552, + "step": 2909 + }, + { + "epoch": 0.31, + "learning_rate": 1.7542331156069213e-05, + "loss": 1.4654, + "step": 2910 + }, + { + "epoch": 0.31, + "learning_rate": 1.753992730601367e-05, + "loss": 1.4531, + "step": 2911 + }, + { + "epoch": 0.31, + "learning_rate": 1.75375224458016e-05, + "loss": 1.4949, + "step": 2912 + }, + { + "epoch": 0.31, + "learning_rate": 1.753511657575519e-05, + "loss": 1.3998, + "step": 2913 + }, + { + "epoch": 0.31, + "learning_rate": 1.753270969619677e-05, + "loss": 1.3904, + "step": 2914 + }, + { + "epoch": 0.31, + "learning_rate": 1.7530301807448794e-05, + "loss": 1.481, + "step": 2915 + }, + { + "epoch": 0.31, + "learning_rate": 1.7527892909833864e-05, + "loss": 1.4301, + "step": 2916 + }, + { + "epoch": 0.31, + "learning_rate": 1.7525483003674707e-05, + "loss": 1.4377, + "step": 2917 + }, + { + "epoch": 0.31, + "learning_rate": 1.7523072089294188e-05, + "loss": 1.5077, + "step": 2918 + }, + { + "epoch": 0.31, + "learning_rate": 1.752066016701531e-05, + "loss": 1.3802, + "step": 2919 + }, + { + "epoch": 0.31, + "learning_rate": 1.7518247237161205e-05, + "loss": 1.3991, + "step": 2920 + }, + { + "epoch": 0.31, + "learning_rate": 1.7515833300055146e-05, + "loss": 1.4283, + "step": 2921 + }, + { + "epoch": 0.31, + "learning_rate": 1.7513418356020535e-05, + "loss": 1.3688, + "step": 2922 + }, + { + "epoch": 0.31, + "learning_rate": 1.751100240538092e-05, + "loss": 1.4336, + "step": 2923 + }, + { + "epoch": 0.31, + "learning_rate": 1.7508585448459967e-05, + "loss": 1.4302, + "step": 2924 + }, + { + "epoch": 0.31, + "learning_rate": 1.7506167485581493e-05, + "loss": 1.4293, + "step": 2925 + }, + { + "epoch": 0.31, + "learning_rate": 1.750374851706944e-05, + "loss": 1.4262, + "step": 2926 + }, + { + "epoch": 0.31, + "learning_rate": 1.7501328543247892e-05, + "loss": 1.4128, + "step": 2927 + }, + { + "epoch": 0.31, + "learning_rate": 1.7498907564441054e-05, + "loss": 1.4258, + "step": 2928 + }, + { + "epoch": 0.31, + "learning_rate": 1.749648558097328e-05, + "loss": 1.4904, + "step": 2929 + }, + { + "epoch": 0.31, + "learning_rate": 1.749406259316906e-05, + "loss": 1.4628, + "step": 2930 + }, + { + "epoch": 0.31, + "learning_rate": 1.7491638601353004e-05, + "loss": 1.4908, + "step": 2931 + }, + { + "epoch": 0.31, + "learning_rate": 1.7489213605849867e-05, + "loss": 1.4563, + "step": 2932 + }, + { + "epoch": 0.31, + "learning_rate": 1.7486787606984533e-05, + "loss": 1.5006, + "step": 2933 + }, + { + "epoch": 0.31, + "learning_rate": 1.748436060508203e-05, + "loss": 1.424, + "step": 2934 + }, + { + "epoch": 0.31, + "learning_rate": 1.7481932600467508e-05, + "loss": 1.4136, + "step": 2935 + }, + { + "epoch": 0.31, + "learning_rate": 1.747950359346626e-05, + "loss": 1.3835, + "step": 2936 + }, + { + "epoch": 0.31, + "learning_rate": 1.747707358440371e-05, + "loss": 1.5284, + "step": 2937 + }, + { + "epoch": 0.31, + "learning_rate": 1.7474642573605418e-05, + "loss": 1.4592, + "step": 2938 + }, + { + "epoch": 0.31, + "learning_rate": 1.7472210561397075e-05, + "loss": 1.5483, + "step": 2939 + }, + { + "epoch": 0.31, + "learning_rate": 1.746977754810451e-05, + "loss": 1.521, + "step": 2940 + }, + { + "epoch": 0.31, + "learning_rate": 1.7467343534053683e-05, + "loss": 1.4276, + "step": 2941 + }, + { + "epoch": 0.31, + "learning_rate": 1.746490851957069e-05, + "loss": 1.4302, + "step": 2942 + }, + { + "epoch": 0.31, + "learning_rate": 1.746247250498176e-05, + "loss": 1.4439, + "step": 2943 + }, + { + "epoch": 0.31, + "learning_rate": 1.7460035490613255e-05, + "loss": 1.4991, + "step": 2944 + }, + { + "epoch": 0.31, + "learning_rate": 1.7457597476791674e-05, + "loss": 1.4188, + "step": 2945 + }, + { + "epoch": 0.31, + "learning_rate": 1.7455158463843648e-05, + "loss": 1.4685, + "step": 2946 + }, + { + "epoch": 0.31, + "learning_rate": 1.745271845209594e-05, + "loss": 1.3811, + "step": 2947 + }, + { + "epoch": 0.31, + "learning_rate": 1.7450277441875454e-05, + "loss": 1.4869, + "step": 2948 + }, + { + "epoch": 0.31, + "learning_rate": 1.7447835433509218e-05, + "loss": 1.5001, + "step": 2949 + }, + { + "epoch": 0.31, + "learning_rate": 1.74453924273244e-05, + "loss": 1.4757, + "step": 2950 + }, + { + "epoch": 0.31, + "learning_rate": 1.74429484236483e-05, + "loss": 1.5072, + "step": 2951 + }, + { + "epoch": 0.31, + "learning_rate": 1.744050342280835e-05, + "loss": 1.4242, + "step": 2952 + }, + { + "epoch": 0.31, + "learning_rate": 1.743805742513212e-05, + "loss": 1.4462, + "step": 2953 + }, + { + "epoch": 0.31, + "learning_rate": 1.743561043094731e-05, + "loss": 1.6815, + "step": 2954 + }, + { + "epoch": 0.31, + "learning_rate": 1.7433162440581755e-05, + "loss": 1.427, + "step": 2955 + }, + { + "epoch": 0.31, + "learning_rate": 1.7430713454363423e-05, + "loss": 1.2933, + "step": 2956 + }, + { + "epoch": 0.31, + "learning_rate": 1.742826347262041e-05, + "loss": 1.4247, + "step": 2957 + }, + { + "epoch": 0.31, + "learning_rate": 1.7425812495680955e-05, + "loss": 1.399, + "step": 2958 + }, + { + "epoch": 0.31, + "learning_rate": 1.742336052387343e-05, + "loss": 1.4818, + "step": 2959 + }, + { + "epoch": 0.31, + "learning_rate": 1.742090755752633e-05, + "loss": 1.3839, + "step": 2960 + }, + { + "epoch": 0.31, + "learning_rate": 1.741845359696829e-05, + "loss": 1.4669, + "step": 2961 + }, + { + "epoch": 0.31, + "learning_rate": 1.741599864252808e-05, + "loss": 1.468, + "step": 2962 + }, + { + "epoch": 0.31, + "learning_rate": 1.74135426945346e-05, + "loss": 1.4135, + "step": 2963 + }, + { + "epoch": 0.31, + "learning_rate": 1.7411085753316882e-05, + "loss": 1.5899, + "step": 2964 + }, + { + "epoch": 0.31, + "learning_rate": 1.74086278192041e-05, + "loss": 1.6115, + "step": 2965 + }, + { + "epoch": 0.31, + "learning_rate": 1.740616889252554e-05, + "loss": 1.3988, + "step": 2966 + }, + { + "epoch": 0.31, + "learning_rate": 1.740370897361065e-05, + "loss": 1.5001, + "step": 2967 + }, + { + "epoch": 0.31, + "learning_rate": 1.740124806278899e-05, + "loss": 1.459, + "step": 2968 + }, + { + "epoch": 0.31, + "learning_rate": 1.7398786160390258e-05, + "loss": 1.4489, + "step": 2969 + }, + { + "epoch": 0.31, + "learning_rate": 1.7396323266744283e-05, + "loss": 1.4397, + "step": 2970 + }, + { + "epoch": 0.31, + "learning_rate": 1.7393859382181033e-05, + "loss": 1.4687, + "step": 2971 + }, + { + "epoch": 0.31, + "learning_rate": 1.7391394507030606e-05, + "loss": 1.4495, + "step": 2972 + }, + { + "epoch": 0.31, + "learning_rate": 1.738892864162323e-05, + "loss": 1.4745, + "step": 2973 + }, + { + "epoch": 0.31, + "learning_rate": 1.7386461786289274e-05, + "loss": 1.3943, + "step": 2974 + }, + { + "epoch": 0.31, + "learning_rate": 1.738399394135922e-05, + "loss": 1.4595, + "step": 2975 + }, + { + "epoch": 0.31, + "learning_rate": 1.738152510716371e-05, + "loss": 1.4023, + "step": 2976 + }, + { + "epoch": 0.31, + "learning_rate": 1.7379055284033493e-05, + "loss": 1.3938, + "step": 2977 + }, + { + "epoch": 0.31, + "learning_rate": 1.7376584472299468e-05, + "loss": 1.4576, + "step": 2978 + }, + { + "epoch": 0.31, + "learning_rate": 1.737411267229266e-05, + "loss": 1.424, + "step": 2979 + }, + { + "epoch": 0.31, + "learning_rate": 1.7371639884344225e-05, + "loss": 1.4224, + "step": 2980 + }, + { + "epoch": 0.31, + "learning_rate": 1.736916610878545e-05, + "loss": 1.4228, + "step": 2981 + }, + { + "epoch": 0.31, + "learning_rate": 1.7366691345947768e-05, + "loss": 1.5021, + "step": 2982 + }, + { + "epoch": 0.31, + "learning_rate": 1.736421559616272e-05, + "loss": 1.3589, + "step": 2983 + }, + { + "epoch": 0.31, + "learning_rate": 1.7361738859762007e-05, + "loss": 1.4748, + "step": 2984 + }, + { + "epoch": 0.31, + "learning_rate": 1.735926113707743e-05, + "loss": 1.3974, + "step": 2985 + }, + { + "epoch": 0.31, + "eval_loss": 1.4849082231521606, + "eval_runtime": 77.3271, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2985 + }, + { + "epoch": 0.31, + "learning_rate": 1.735678242844096e-05, + "loss": 1.392, + "step": 2986 + }, + { + "epoch": 0.31, + "learning_rate": 1.735430273418467e-05, + "loss": 1.4277, + "step": 2987 + }, + { + "epoch": 0.31, + "learning_rate": 1.735182205464077e-05, + "loss": 1.4216, + "step": 2988 + }, + { + "epoch": 0.31, + "learning_rate": 1.7349340390141617e-05, + "loss": 1.4546, + "step": 2989 + }, + { + "epoch": 0.31, + "learning_rate": 1.734685774101969e-05, + "loss": 1.4264, + "step": 2990 + }, + { + "epoch": 0.31, + "learning_rate": 1.7344374107607593e-05, + "loss": 1.4307, + "step": 2991 + }, + { + "epoch": 0.31, + "learning_rate": 1.7341889490238076e-05, + "loss": 1.4266, + "step": 2992 + }, + { + "epoch": 0.31, + "learning_rate": 1.7339403889244008e-05, + "loss": 1.4486, + "step": 2993 + }, + { + "epoch": 0.31, + "learning_rate": 1.7336917304958403e-05, + "loss": 1.4345, + "step": 2994 + }, + { + "epoch": 0.31, + "learning_rate": 1.7334429737714395e-05, + "loss": 1.476, + "step": 2995 + }, + { + "epoch": 0.31, + "learning_rate": 1.7331941187845248e-05, + "loss": 1.5148, + "step": 2996 + }, + { + "epoch": 0.31, + "learning_rate": 1.7329451655684372e-05, + "loss": 1.4026, + "step": 2997 + }, + { + "epoch": 0.31, + "learning_rate": 1.7326961141565303e-05, + "loss": 1.3935, + "step": 2998 + }, + { + "epoch": 0.31, + "learning_rate": 1.73244696458217e-05, + "loss": 1.4483, + "step": 2999 + }, + { + "epoch": 0.31, + "learning_rate": 1.7321977168787356e-05, + "loss": 1.5197, + "step": 3000 + }, + { + "epoch": 0.31, + "learning_rate": 1.7319483710796208e-05, + "loss": 1.4648, + "step": 3001 + }, + { + "epoch": 0.31, + "learning_rate": 1.7316989272182308e-05, + "loss": 1.4171, + "step": 3002 + }, + { + "epoch": 0.31, + "learning_rate": 1.731449385327985e-05, + "loss": 1.4541, + "step": 3003 + }, + { + "epoch": 0.32, + "learning_rate": 1.731199745442316e-05, + "loss": 1.4605, + "step": 3004 + }, + { + "epoch": 0.32, + "learning_rate": 1.7309500075946683e-05, + "loss": 1.5122, + "step": 3005 + }, + { + "epoch": 0.32, + "learning_rate": 1.7307001718185007e-05, + "loss": 1.5243, + "step": 3006 + }, + { + "epoch": 0.32, + "learning_rate": 1.7304502381472844e-05, + "loss": 1.4997, + "step": 3007 + }, + { + "epoch": 0.32, + "learning_rate": 1.730200206614505e-05, + "loss": 1.4891, + "step": 3008 + }, + { + "epoch": 0.32, + "learning_rate": 1.72995007725366e-05, + "loss": 1.4376, + "step": 3009 + }, + { + "epoch": 0.32, + "learning_rate": 1.7296998500982595e-05, + "loss": 1.4403, + "step": 3010 + }, + { + "epoch": 0.32, + "learning_rate": 1.7294495251818285e-05, + "loss": 1.5153, + "step": 3011 + }, + { + "epoch": 0.32, + "learning_rate": 1.729199102537904e-05, + "loss": 1.4996, + "step": 3012 + }, + { + "epoch": 0.32, + "learning_rate": 1.7289485822000356e-05, + "loss": 1.5302, + "step": 3013 + }, + { + "epoch": 0.32, + "learning_rate": 1.7286979642017867e-05, + "loss": 1.5641, + "step": 3014 + }, + { + "epoch": 0.32, + "learning_rate": 1.728447248576734e-05, + "loss": 1.438, + "step": 3015 + }, + { + "epoch": 0.32, + "learning_rate": 1.7281964353584674e-05, + "loss": 1.4796, + "step": 3016 + }, + { + "epoch": 0.32, + "learning_rate": 1.727945524580588e-05, + "loss": 1.4413, + "step": 3017 + }, + { + "epoch": 0.32, + "learning_rate": 1.727694516276713e-05, + "loss": 1.3966, + "step": 3018 + }, + { + "epoch": 0.32, + "learning_rate": 1.72744341048047e-05, + "loss": 1.5267, + "step": 3019 + }, + { + "epoch": 0.32, + "learning_rate": 1.727192207225501e-05, + "loss": 1.4284, + "step": 3020 + }, + { + "epoch": 0.32, + "learning_rate": 1.726940906545461e-05, + "loss": 1.5137, + "step": 3021 + }, + { + "epoch": 0.32, + "learning_rate": 1.7266895084740173e-05, + "loss": 1.3966, + "step": 3022 + }, + { + "epoch": 0.32, + "learning_rate": 1.7264380130448514e-05, + "loss": 1.4156, + "step": 3023 + }, + { + "epoch": 0.32, + "learning_rate": 1.726186420291657e-05, + "loss": 1.4644, + "step": 3024 + }, + { + "epoch": 0.32, + "learning_rate": 1.725934730248141e-05, + "loss": 1.4768, + "step": 3025 + }, + { + "epoch": 0.32, + "learning_rate": 1.7256829429480233e-05, + "loss": 1.4428, + "step": 3026 + }, + { + "epoch": 0.32, + "learning_rate": 1.7254310584250373e-05, + "loss": 1.4495, + "step": 3027 + }, + { + "epoch": 0.32, + "learning_rate": 1.725179076712929e-05, + "loss": 1.3867, + "step": 3028 + }, + { + "epoch": 0.32, + "learning_rate": 1.7249269978454567e-05, + "loss": 1.5011, + "step": 3029 + }, + { + "epoch": 0.32, + "learning_rate": 1.7246748218563937e-05, + "loss": 1.3916, + "step": 3030 + }, + { + "epoch": 0.32, + "learning_rate": 1.7244225487795238e-05, + "loss": 1.4984, + "step": 3031 + }, + { + "epoch": 0.32, + "learning_rate": 1.7241701786486464e-05, + "loss": 1.5776, + "step": 3032 + }, + { + "epoch": 0.32, + "learning_rate": 1.7239177114975717e-05, + "loss": 1.5018, + "step": 3033 + }, + { + "epoch": 0.32, + "learning_rate": 1.7236651473601244e-05, + "loss": 1.5042, + "step": 3034 + }, + { + "epoch": 0.32, + "learning_rate": 1.723412486270141e-05, + "loss": 1.4636, + "step": 3035 + }, + { + "epoch": 0.32, + "learning_rate": 1.723159728261472e-05, + "loss": 1.5612, + "step": 3036 + }, + { + "epoch": 0.32, + "learning_rate": 1.7229068733679803e-05, + "loss": 1.4399, + "step": 3037 + }, + { + "epoch": 0.32, + "learning_rate": 1.7226539216235424e-05, + "loss": 1.5635, + "step": 3038 + }, + { + "epoch": 0.32, + "learning_rate": 1.7224008730620468e-05, + "loss": 1.4329, + "step": 3039 + }, + { + "epoch": 0.32, + "learning_rate": 1.7221477277173956e-05, + "loss": 1.4886, + "step": 3040 + }, + { + "epoch": 0.32, + "learning_rate": 1.721894485623504e-05, + "loss": 1.4741, + "step": 3041 + }, + { + "epoch": 0.32, + "learning_rate": 1.7216411468143e-05, + "loss": 1.4678, + "step": 3042 + }, + { + "epoch": 0.32, + "learning_rate": 1.721387711323724e-05, + "loss": 1.4758, + "step": 3043 + }, + { + "epoch": 0.32, + "learning_rate": 1.72113417918573e-05, + "loss": 1.441, + "step": 3044 + }, + { + "epoch": 0.32, + "learning_rate": 1.7208805504342855e-05, + "loss": 1.4328, + "step": 3045 + }, + { + "epoch": 0.32, + "learning_rate": 1.720626825103369e-05, + "loss": 1.4254, + "step": 3046 + }, + { + "epoch": 0.32, + "learning_rate": 1.7203730032269744e-05, + "loss": 1.4462, + "step": 3047 + }, + { + "epoch": 0.32, + "learning_rate": 1.7201190848391066e-05, + "loss": 1.4826, + "step": 3048 + }, + { + "epoch": 0.32, + "learning_rate": 1.719865069973784e-05, + "loss": 1.4215, + "step": 3049 + }, + { + "epoch": 0.32, + "learning_rate": 1.7196109586650385e-05, + "loss": 1.4291, + "step": 3050 + }, + { + "epoch": 0.32, + "learning_rate": 1.7193567509469146e-05, + "loss": 1.5005, + "step": 3051 + }, + { + "epoch": 0.32, + "learning_rate": 1.719102446853469e-05, + "loss": 1.4216, + "step": 3052 + }, + { + "epoch": 0.32, + "learning_rate": 1.7188480464187725e-05, + "loss": 1.4349, + "step": 3053 + }, + { + "epoch": 0.32, + "learning_rate": 1.718593549676908e-05, + "loss": 1.4784, + "step": 3054 + }, + { + "epoch": 0.32, + "learning_rate": 1.7183389566619714e-05, + "loss": 1.4325, + "step": 3055 + }, + { + "epoch": 0.32, + "learning_rate": 1.7180842674080717e-05, + "loss": 1.5387, + "step": 3056 + }, + { + "epoch": 0.32, + "learning_rate": 1.717829481949331e-05, + "loss": 1.655, + "step": 3057 + }, + { + "epoch": 0.32, + "learning_rate": 1.717574600319883e-05, + "loss": 1.4623, + "step": 3058 + }, + { + "epoch": 0.32, + "learning_rate": 1.7173196225538768e-05, + "loss": 1.4646, + "step": 3059 + }, + { + "epoch": 0.32, + "learning_rate": 1.717064548685472e-05, + "loss": 1.4641, + "step": 3060 + }, + { + "epoch": 0.32, + "learning_rate": 1.7168093787488418e-05, + "loss": 1.4033, + "step": 3061 + }, + { + "epoch": 0.32, + "learning_rate": 1.7165541127781726e-05, + "loss": 1.4085, + "step": 3062 + }, + { + "epoch": 0.32, + "learning_rate": 1.716298750807664e-05, + "loss": 1.387, + "step": 3063 + }, + { + "epoch": 0.32, + "learning_rate": 1.7160432928715272e-05, + "loss": 1.4197, + "step": 3064 + }, + { + "epoch": 0.32, + "learning_rate": 1.7157877390039872e-05, + "loss": 1.4883, + "step": 3065 + }, + { + "epoch": 0.32, + "learning_rate": 1.7155320892392818e-05, + "loss": 1.4865, + "step": 3066 + }, + { + "epoch": 0.32, + "learning_rate": 1.715276343611662e-05, + "loss": 1.4532, + "step": 3067 + }, + { + "epoch": 0.32, + "learning_rate": 1.71502050215539e-05, + "loss": 1.3991, + "step": 3068 + }, + { + "epoch": 0.32, + "learning_rate": 1.7147645649047424e-05, + "loss": 1.4318, + "step": 3069 + }, + { + "epoch": 0.32, + "learning_rate": 1.714508531894009e-05, + "loss": 1.3616, + "step": 3070 + }, + { + "epoch": 0.32, + "learning_rate": 1.7142524031574904e-05, + "loss": 1.4481, + "step": 3071 + }, + { + "epoch": 0.32, + "learning_rate": 1.7139961787295022e-05, + "loss": 1.3897, + "step": 3072 + }, + { + "epoch": 0.32, + "learning_rate": 1.7137398586443716e-05, + "loss": 1.3128, + "step": 3073 + }, + { + "epoch": 0.32, + "learning_rate": 1.713483442936439e-05, + "loss": 1.4481, + "step": 3074 + }, + { + "epoch": 0.32, + "learning_rate": 1.713226931640057e-05, + "loss": 1.5374, + "step": 3075 + }, + { + "epoch": 0.32, + "learning_rate": 1.7129703247895923e-05, + "loss": 1.4247, + "step": 3076 + }, + { + "epoch": 0.32, + "learning_rate": 1.712713622419423e-05, + "loss": 1.4098, + "step": 3077 + }, + { + "epoch": 0.32, + "learning_rate": 1.7124568245639414e-05, + "loss": 1.4558, + "step": 3078 + }, + { + "epoch": 0.32, + "learning_rate": 1.7121999312575507e-05, + "loss": 1.4484, + "step": 3079 + }, + { + "epoch": 0.32, + "learning_rate": 1.711942942534669e-05, + "loss": 1.4236, + "step": 3080 + }, + { + "epoch": 0.32, + "learning_rate": 1.7116858584297253e-05, + "loss": 1.613, + "step": 3081 + }, + { + "epoch": 0.32, + "learning_rate": 1.711428678977163e-05, + "loss": 1.4503, + "step": 3082 + }, + { + "epoch": 0.32, + "learning_rate": 1.7111714042114376e-05, + "loss": 1.4072, + "step": 3083 + }, + { + "epoch": 0.32, + "learning_rate": 1.7109140341670168e-05, + "loss": 1.5999, + "step": 3084 + }, + { + "epoch": 0.32, + "learning_rate": 1.7106565688783815e-05, + "loss": 1.4129, + "step": 3085 + }, + { + "epoch": 0.32, + "learning_rate": 1.710399008380026e-05, + "loss": 1.3973, + "step": 3086 + }, + { + "epoch": 0.32, + "learning_rate": 1.710141352706456e-05, + "loss": 1.4292, + "step": 3087 + }, + { + "epoch": 0.32, + "learning_rate": 1.709883601892192e-05, + "loss": 1.4372, + "step": 3088 + }, + { + "epoch": 0.32, + "learning_rate": 1.7096257559717647e-05, + "loss": 1.4924, + "step": 3089 + }, + { + "epoch": 0.32, + "learning_rate": 1.7093678149797196e-05, + "loss": 1.4222, + "step": 3090 + }, + { + "epoch": 0.32, + "learning_rate": 1.7091097789506137e-05, + "loss": 1.4797, + "step": 3091 + }, + { + "epoch": 0.32, + "learning_rate": 1.7088516479190175e-05, + "loss": 1.4738, + "step": 3092 + }, + { + "epoch": 0.32, + "learning_rate": 1.708593421919514e-05, + "loss": 1.5371, + "step": 3093 + }, + { + "epoch": 0.32, + "learning_rate": 1.7083351009866988e-05, + "loss": 1.3802, + "step": 3094 + }, + { + "epoch": 0.32, + "learning_rate": 1.7080766851551795e-05, + "loss": 1.4292, + "step": 3095 + }, + { + "epoch": 0.32, + "learning_rate": 1.707818174459578e-05, + "loss": 1.4478, + "step": 3096 + }, + { + "epoch": 0.32, + "learning_rate": 1.7075595689345285e-05, + "loss": 1.4619, + "step": 3097 + }, + { + "epoch": 0.32, + "learning_rate": 1.7073008686146763e-05, + "loss": 1.4603, + "step": 3098 + }, + { + "epoch": 0.32, + "learning_rate": 1.7070420735346815e-05, + "loss": 1.4548, + "step": 3099 + }, + { + "epoch": 0.33, + "learning_rate": 1.7067831837292157e-05, + "loss": 1.3638, + "step": 3100 + }, + { + "epoch": 0.33, + "learning_rate": 1.7065241992329634e-05, + "loss": 1.4284, + "step": 3101 + }, + { + "epoch": 0.33, + "learning_rate": 1.7062651200806217e-05, + "loss": 1.386, + "step": 3102 + }, + { + "epoch": 0.33, + "learning_rate": 1.7060059463069013e-05, + "loss": 1.5483, + "step": 3103 + }, + { + "epoch": 0.33, + "learning_rate": 1.705746677946524e-05, + "loss": 1.4963, + "step": 3104 + }, + { + "epoch": 0.33, + "learning_rate": 1.7054873150342257e-05, + "loss": 1.4539, + "step": 3105 + }, + { + "epoch": 0.33, + "learning_rate": 1.705227857604754e-05, + "loss": 1.4361, + "step": 3106 + }, + { + "epoch": 0.33, + "learning_rate": 1.7049683056928695e-05, + "loss": 1.3735, + "step": 3107 + }, + { + "epoch": 0.33, + "learning_rate": 1.7047086593333454e-05, + "loss": 1.4324, + "step": 3108 + }, + { + "epoch": 0.33, + "learning_rate": 1.7044489185609685e-05, + "loss": 1.5037, + "step": 3109 + }, + { + "epoch": 0.33, + "learning_rate": 1.704189083410536e-05, + "loss": 1.3913, + "step": 3110 + }, + { + "epoch": 0.33, + "learning_rate": 1.7039291539168604e-05, + "loss": 1.3233, + "step": 3111 + }, + { + "epoch": 0.33, + "learning_rate": 1.703669130114765e-05, + "loss": 1.4897, + "step": 3112 + }, + { + "epoch": 0.33, + "learning_rate": 1.7034090120390862e-05, + "loss": 1.4843, + "step": 3113 + }, + { + "epoch": 0.33, + "learning_rate": 1.7031487997246735e-05, + "loss": 1.3674, + "step": 3114 + }, + { + "epoch": 0.33, + "learning_rate": 1.7028884932063883e-05, + "loss": 1.4475, + "step": 3115 + }, + { + "epoch": 0.33, + "learning_rate": 1.702628092519105e-05, + "loss": 1.4134, + "step": 3116 + }, + { + "epoch": 0.33, + "learning_rate": 1.7023675976977108e-05, + "loss": 1.4484, + "step": 3117 + }, + { + "epoch": 0.33, + "learning_rate": 1.702107008777106e-05, + "loss": 1.407, + "step": 3118 + }, + { + "epoch": 0.33, + "learning_rate": 1.7018463257922005e-05, + "loss": 1.5443, + "step": 3119 + }, + { + "epoch": 0.33, + "learning_rate": 1.701585548777922e-05, + "loss": 1.4548, + "step": 3120 + }, + { + "epoch": 0.33, + "learning_rate": 1.7013246777692063e-05, + "loss": 1.4252, + "step": 3121 + }, + { + "epoch": 0.33, + "learning_rate": 1.7010637128010037e-05, + "loss": 1.3748, + "step": 3122 + }, + { + "epoch": 0.33, + "learning_rate": 1.7008026539082767e-05, + "loss": 1.3804, + "step": 3123 + }, + { + "epoch": 0.33, + "learning_rate": 1.7005415011260008e-05, + "loss": 1.4203, + "step": 3124 + }, + { + "epoch": 0.33, + "learning_rate": 1.7002802544891634e-05, + "loss": 1.4195, + "step": 3125 + }, + { + "epoch": 0.33, + "learning_rate": 1.700018914032765e-05, + "loss": 1.4188, + "step": 3126 + }, + { + "epoch": 0.33, + "learning_rate": 1.699757479791819e-05, + "loss": 1.3884, + "step": 3127 + }, + { + "epoch": 0.33, + "learning_rate": 1.6994959518013502e-05, + "loss": 1.4111, + "step": 3128 + }, + { + "epoch": 0.33, + "learning_rate": 1.6992343300963963e-05, + "loss": 1.5452, + "step": 3129 + }, + { + "epoch": 0.33, + "learning_rate": 1.6989726147120087e-05, + "loss": 1.4097, + "step": 3130 + }, + { + "epoch": 0.33, + "learning_rate": 1.6987108056832506e-05, + "loss": 1.481, + "step": 3131 + }, + { + "epoch": 0.33, + "learning_rate": 1.6984489030451973e-05, + "loss": 1.4505, + "step": 3132 + }, + { + "epoch": 0.33, + "learning_rate": 1.6981869068329368e-05, + "loss": 1.4281, + "step": 3133 + }, + { + "epoch": 0.33, + "learning_rate": 1.69792481708157e-05, + "loss": 1.4555, + "step": 3134 + }, + { + "epoch": 0.33, + "learning_rate": 1.6976626338262103e-05, + "loss": 1.4525, + "step": 3135 + }, + { + "epoch": 0.33, + "learning_rate": 1.6974003571019837e-05, + "loss": 1.3765, + "step": 3136 + }, + { + "epoch": 0.33, + "learning_rate": 1.6971379869440286e-05, + "loss": 1.3998, + "step": 3137 + }, + { + "epoch": 0.33, + "learning_rate": 1.696875523387495e-05, + "loss": 1.5103, + "step": 3138 + }, + { + "epoch": 0.33, + "learning_rate": 1.6966129664675474e-05, + "loss": 1.427, + "step": 3139 + }, + { + "epoch": 0.33, + "learning_rate": 1.6963503162193612e-05, + "loss": 1.4362, + "step": 3140 + }, + { + "epoch": 0.33, + "learning_rate": 1.6960875726781246e-05, + "loss": 1.4073, + "step": 3141 + }, + { + "epoch": 0.33, + "learning_rate": 1.6958247358790388e-05, + "loss": 1.4014, + "step": 3142 + }, + { + "epoch": 0.33, + "learning_rate": 1.6955618058573165e-05, + "loss": 1.4244, + "step": 3143 + }, + { + "epoch": 0.33, + "learning_rate": 1.6952987826481847e-05, + "loss": 1.47, + "step": 3144 + }, + { + "epoch": 0.33, + "learning_rate": 1.6950356662868814e-05, + "loss": 1.5112, + "step": 3145 + }, + { + "epoch": 0.33, + "learning_rate": 1.6947724568086562e-05, + "loss": 1.3398, + "step": 3146 + }, + { + "epoch": 0.33, + "learning_rate": 1.694509154248774e-05, + "loss": 1.4584, + "step": 3147 + }, + { + "epoch": 0.33, + "learning_rate": 1.69424575864251e-05, + "loss": 1.4383, + "step": 3148 + }, + { + "epoch": 0.33, + "learning_rate": 1.6939822700251523e-05, + "loss": 1.3869, + "step": 3149 + }, + { + "epoch": 0.33, + "learning_rate": 1.6937186884320015e-05, + "loss": 1.4453, + "step": 3150 + }, + { + "epoch": 0.33, + "learning_rate": 1.6934550138983713e-05, + "loss": 1.3355, + "step": 3151 + }, + { + "epoch": 0.33, + "learning_rate": 1.6931912464595866e-05, + "loss": 1.5573, + "step": 3152 + }, + { + "epoch": 0.33, + "learning_rate": 1.6929273861509865e-05, + "loss": 1.439, + "step": 3153 + }, + { + "epoch": 0.33, + "learning_rate": 1.6926634330079203e-05, + "loss": 1.6079, + "step": 3154 + }, + { + "epoch": 0.33, + "learning_rate": 1.692399387065752e-05, + "loss": 1.6973, + "step": 3155 + }, + { + "epoch": 0.33, + "learning_rate": 1.692135248359856e-05, + "loss": 1.3769, + "step": 3156 + }, + { + "epoch": 0.33, + "learning_rate": 1.6918710169256206e-05, + "loss": 1.4454, + "step": 3157 + }, + { + "epoch": 0.33, + "learning_rate": 1.691606692798446e-05, + "loss": 1.4495, + "step": 3158 + }, + { + "epoch": 0.33, + "learning_rate": 1.691342276013745e-05, + "loss": 1.4292, + "step": 3159 + }, + { + "epoch": 0.33, + "learning_rate": 1.691077766606942e-05, + "loss": 1.4405, + "step": 3160 + }, + { + "epoch": 0.33, + "learning_rate": 1.6908131646134757e-05, + "loss": 1.3683, + "step": 3161 + }, + { + "epoch": 0.33, + "learning_rate": 1.690548470068795e-05, + "loss": 1.4731, + "step": 3162 + }, + { + "epoch": 0.33, + "learning_rate": 1.690283683008362e-05, + "loss": 1.4323, + "step": 3163 + }, + { + "epoch": 0.33, + "learning_rate": 1.6900188034676518e-05, + "loss": 1.5133, + "step": 3164 + }, + { + "epoch": 0.33, + "learning_rate": 1.6897538314821516e-05, + "loss": 1.5529, + "step": 3165 + }, + { + "epoch": 0.33, + "learning_rate": 1.6894887670873605e-05, + "loss": 1.4427, + "step": 3166 + }, + { + "epoch": 0.33, + "learning_rate": 1.6892236103187904e-05, + "loss": 1.4344, + "step": 3167 + }, + { + "epoch": 0.33, + "learning_rate": 1.6889583612119657e-05, + "loss": 1.4291, + "step": 3168 + }, + { + "epoch": 0.33, + "learning_rate": 1.6886930198024226e-05, + "loss": 1.4683, + "step": 3169 + }, + { + "epoch": 0.33, + "learning_rate": 1.6884275861257106e-05, + "loss": 1.4442, + "step": 3170 + }, + { + "epoch": 0.33, + "learning_rate": 1.6881620602173905e-05, + "loss": 1.4509, + "step": 3171 + }, + { + "epoch": 0.33, + "learning_rate": 1.6878964421130362e-05, + "loss": 1.5113, + "step": 3172 + }, + { + "epoch": 0.33, + "learning_rate": 1.6876307318482334e-05, + "loss": 1.4261, + "step": 3173 + }, + { + "epoch": 0.33, + "learning_rate": 1.6873649294585805e-05, + "loss": 1.445, + "step": 3174 + }, + { + "epoch": 0.33, + "learning_rate": 1.6870990349796886e-05, + "loss": 1.4603, + "step": 3175 + }, + { + "epoch": 0.33, + "learning_rate": 1.68683304844718e-05, + "loss": 1.41, + "step": 3176 + }, + { + "epoch": 0.33, + "learning_rate": 1.686566969896691e-05, + "loss": 1.4018, + "step": 3177 + }, + { + "epoch": 0.33, + "learning_rate": 1.6863007993638687e-05, + "loss": 1.422, + "step": 3178 + }, + { + "epoch": 0.33, + "learning_rate": 1.6860345368843727e-05, + "loss": 1.4412, + "step": 3179 + }, + { + "epoch": 0.33, + "learning_rate": 1.6857681824938768e-05, + "loss": 1.5411, + "step": 3180 + }, + { + "epoch": 0.33, + "learning_rate": 1.685501736228064e-05, + "loss": 1.4416, + "step": 3181 + }, + { + "epoch": 0.33, + "learning_rate": 1.685235198122632e-05, + "loss": 1.5113, + "step": 3182 + }, + { + "epoch": 0.33, + "learning_rate": 1.6849685682132903e-05, + "loss": 1.423, + "step": 3183 + }, + { + "epoch": 0.33, + "learning_rate": 1.68470184653576e-05, + "loss": 1.404, + "step": 3184 + }, + { + "epoch": 0.33, + "eval_loss": 1.4771089553833008, + "eval_runtime": 77.4034, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3184 + }, + { + "epoch": 0.33, + "learning_rate": 1.6844350331257747e-05, + "loss": 1.4624, + "step": 3185 + }, + { + "epoch": 0.33, + "learning_rate": 1.6841681280190814e-05, + "loss": 1.4306, + "step": 3186 + }, + { + "epoch": 0.33, + "learning_rate": 1.683901131251438e-05, + "loss": 1.42, + "step": 3187 + }, + { + "epoch": 0.33, + "learning_rate": 1.6836340428586155e-05, + "loss": 1.4787, + "step": 3188 + }, + { + "epoch": 0.33, + "learning_rate": 1.6833668628763965e-05, + "loss": 1.3485, + "step": 3189 + }, + { + "epoch": 0.33, + "learning_rate": 1.683099591340576e-05, + "loss": 1.3674, + "step": 3190 + }, + { + "epoch": 0.33, + "learning_rate": 1.6828322282869627e-05, + "loss": 1.5187, + "step": 3191 + }, + { + "epoch": 0.33, + "learning_rate": 1.682564773751375e-05, + "loss": 1.4847, + "step": 3192 + }, + { + "epoch": 0.33, + "learning_rate": 1.682297227769646e-05, + "loss": 1.4815, + "step": 3193 + }, + { + "epoch": 0.33, + "learning_rate": 1.682029590377619e-05, + "loss": 1.4281, + "step": 3194 + }, + { + "epoch": 0.34, + "learning_rate": 1.6817618616111517e-05, + "loss": 1.4734, + "step": 3195 + }, + { + "epoch": 0.34, + "learning_rate": 1.681494041506112e-05, + "loss": 1.4861, + "step": 3196 + }, + { + "epoch": 0.34, + "learning_rate": 1.6812261300983808e-05, + "loss": 1.4372, + "step": 3197 + }, + { + "epoch": 0.34, + "learning_rate": 1.680958127423852e-05, + "loss": 1.4396, + "step": 3198 + }, + { + "epoch": 0.34, + "learning_rate": 1.680690033518431e-05, + "loss": 1.4225, + "step": 3199 + }, + { + "epoch": 0.34, + "learning_rate": 1.6804218484180347e-05, + "loss": 1.4925, + "step": 3200 + }, + { + "epoch": 0.34, + "learning_rate": 1.6801535721585942e-05, + "loss": 1.4306, + "step": 3201 + }, + { + "epoch": 0.34, + "learning_rate": 1.6798852047760506e-05, + "loss": 1.4298, + "step": 3202 + }, + { + "epoch": 0.34, + "learning_rate": 1.6796167463063588e-05, + "loss": 1.4725, + "step": 3203 + }, + { + "epoch": 0.34, + "learning_rate": 1.679348196785485e-05, + "loss": 1.4648, + "step": 3204 + }, + { + "epoch": 0.34, + "learning_rate": 1.6790795562494087e-05, + "loss": 1.4152, + "step": 3205 + }, + { + "epoch": 0.34, + "learning_rate": 1.6788108247341198e-05, + "loss": 1.4637, + "step": 3206 + }, + { + "epoch": 0.34, + "learning_rate": 1.6785420022756216e-05, + "loss": 1.4077, + "step": 3207 + }, + { + "epoch": 0.34, + "learning_rate": 1.67827308890993e-05, + "loss": 1.4585, + "step": 3208 + }, + { + "epoch": 0.34, + "learning_rate": 1.678004084673072e-05, + "loss": 1.3747, + "step": 3209 + }, + { + "epoch": 0.34, + "learning_rate": 1.6777349896010876e-05, + "loss": 1.4264, + "step": 3210 + }, + { + "epoch": 0.34, + "learning_rate": 1.677465803730028e-05, + "loss": 1.4178, + "step": 3211 + }, + { + "epoch": 0.34, + "learning_rate": 1.6771965270959584e-05, + "loss": 1.3876, + "step": 3212 + }, + { + "epoch": 0.34, + "learning_rate": 1.6769271597349538e-05, + "loss": 1.4658, + "step": 3213 + }, + { + "epoch": 0.34, + "learning_rate": 1.6766577016831026e-05, + "loss": 1.3968, + "step": 3214 + }, + { + "epoch": 0.34, + "learning_rate": 1.676388152976506e-05, + "loss": 1.5015, + "step": 3215 + }, + { + "epoch": 0.34, + "learning_rate": 1.6761185136512756e-05, + "loss": 1.4121, + "step": 3216 + }, + { + "epoch": 0.34, + "learning_rate": 1.675848783743537e-05, + "loss": 1.4146, + "step": 3217 + }, + { + "epoch": 0.34, + "learning_rate": 1.675578963289427e-05, + "loss": 1.4113, + "step": 3218 + }, + { + "epoch": 0.34, + "learning_rate": 1.6753090523250937e-05, + "loss": 1.4048, + "step": 3219 + }, + { + "epoch": 0.34, + "learning_rate": 1.6750390508866994e-05, + "loss": 1.4959, + "step": 3220 + }, + { + "epoch": 0.34, + "learning_rate": 1.6747689590104167e-05, + "loss": 1.4445, + "step": 3221 + }, + { + "epoch": 0.34, + "learning_rate": 1.6744987767324312e-05, + "loss": 1.4611, + "step": 3222 + }, + { + "epoch": 0.34, + "learning_rate": 1.67422850408894e-05, + "loss": 1.4141, + "step": 3223 + }, + { + "epoch": 0.34, + "learning_rate": 1.6739581411161535e-05, + "loss": 1.4218, + "step": 3224 + }, + { + "epoch": 0.34, + "learning_rate": 1.6736876878502925e-05, + "loss": 1.4266, + "step": 3225 + }, + { + "epoch": 0.34, + "learning_rate": 1.6734171443275913e-05, + "loss": 1.4941, + "step": 3226 + }, + { + "epoch": 0.34, + "learning_rate": 1.6731465105842955e-05, + "loss": 1.4294, + "step": 3227 + }, + { + "epoch": 0.34, + "learning_rate": 1.6728757866566635e-05, + "loss": 1.4189, + "step": 3228 + }, + { + "epoch": 0.34, + "learning_rate": 1.6726049725809647e-05, + "loss": 1.4713, + "step": 3229 + }, + { + "epoch": 0.34, + "learning_rate": 1.6723340683934818e-05, + "loss": 1.4203, + "step": 3230 + }, + { + "epoch": 0.34, + "learning_rate": 1.6720630741305088e-05, + "loss": 1.4112, + "step": 3231 + }, + { + "epoch": 0.34, + "learning_rate": 1.6717919898283523e-05, + "loss": 1.3811, + "step": 3232 + }, + { + "epoch": 0.34, + "learning_rate": 1.6715208155233296e-05, + "loss": 1.4242, + "step": 3233 + }, + { + "epoch": 0.34, + "learning_rate": 1.6712495512517725e-05, + "loss": 1.4207, + "step": 3234 + }, + { + "epoch": 0.34, + "learning_rate": 1.6709781970500222e-05, + "loss": 1.4888, + "step": 3235 + }, + { + "epoch": 0.34, + "learning_rate": 1.670706752954434e-05, + "loss": 1.4501, + "step": 3236 + }, + { + "epoch": 0.34, + "learning_rate": 1.670435219001374e-05, + "loss": 1.4367, + "step": 3237 + }, + { + "epoch": 0.34, + "learning_rate": 1.6701635952272212e-05, + "loss": 1.3959, + "step": 3238 + }, + { + "epoch": 0.34, + "learning_rate": 1.6698918816683655e-05, + "loss": 1.4257, + "step": 3239 + }, + { + "epoch": 0.34, + "learning_rate": 1.6696200783612102e-05, + "loss": 1.4718, + "step": 3240 + }, + { + "epoch": 0.34, + "learning_rate": 1.6693481853421697e-05, + "loss": 1.5899, + "step": 3241 + }, + { + "epoch": 0.34, + "learning_rate": 1.6690762026476707e-05, + "loss": 1.418, + "step": 3242 + }, + { + "epoch": 0.34, + "learning_rate": 1.668804130314152e-05, + "loss": 1.4076, + "step": 3243 + }, + { + "epoch": 0.34, + "learning_rate": 1.6685319683780645e-05, + "loss": 1.4571, + "step": 3244 + }, + { + "epoch": 0.34, + "learning_rate": 1.66825971687587e-05, + "loss": 1.4066, + "step": 3245 + }, + { + "epoch": 0.34, + "learning_rate": 1.6679873758440442e-05, + "loss": 1.4639, + "step": 3246 + }, + { + "epoch": 0.34, + "learning_rate": 1.6677149453190732e-05, + "loss": 1.453, + "step": 3247 + }, + { + "epoch": 0.34, + "learning_rate": 1.6674424253374558e-05, + "loss": 1.4262, + "step": 3248 + }, + { + "epoch": 0.34, + "learning_rate": 1.667169815935703e-05, + "loss": 1.3687, + "step": 3249 + }, + { + "epoch": 0.34, + "learning_rate": 1.6668971171503372e-05, + "loss": 1.5557, + "step": 3250 + }, + { + "epoch": 0.34, + "learning_rate": 1.6666243290178933e-05, + "loss": 1.4639, + "step": 3251 + }, + { + "epoch": 0.34, + "learning_rate": 1.6663514515749172e-05, + "loss": 1.4334, + "step": 3252 + }, + { + "epoch": 0.34, + "learning_rate": 1.6660784848579685e-05, + "loss": 1.3523, + "step": 3253 + }, + { + "epoch": 0.34, + "learning_rate": 1.6658054289036166e-05, + "loss": 1.3738, + "step": 3254 + }, + { + "epoch": 0.34, + "learning_rate": 1.665532283748445e-05, + "loss": 1.4159, + "step": 3255 + }, + { + "epoch": 0.34, + "learning_rate": 1.6652590494290474e-05, + "loss": 1.3609, + "step": 3256 + }, + { + "epoch": 0.34, + "learning_rate": 1.6649857259820303e-05, + "loss": 1.4449, + "step": 3257 + }, + { + "epoch": 0.34, + "learning_rate": 1.6647123134440126e-05, + "loss": 1.424, + "step": 3258 + }, + { + "epoch": 0.34, + "learning_rate": 1.664438811851624e-05, + "loss": 1.4737, + "step": 3259 + }, + { + "epoch": 0.34, + "learning_rate": 1.6641652212415066e-05, + "loss": 1.2717, + "step": 3260 + }, + { + "epoch": 0.34, + "learning_rate": 1.663891541650315e-05, + "loss": 1.4845, + "step": 3261 + }, + { + "epoch": 0.34, + "learning_rate": 1.663617773114715e-05, + "loss": 1.4115, + "step": 3262 + }, + { + "epoch": 0.34, + "learning_rate": 1.663343915671384e-05, + "loss": 1.4237, + "step": 3263 + }, + { + "epoch": 0.34, + "learning_rate": 1.6630699693570127e-05, + "loss": 1.4209, + "step": 3264 + }, + { + "epoch": 0.34, + "learning_rate": 1.6627959342083026e-05, + "loss": 1.506, + "step": 3265 + }, + { + "epoch": 0.34, + "learning_rate": 1.6625218102619672e-05, + "loss": 1.4466, + "step": 3266 + }, + { + "epoch": 0.34, + "learning_rate": 1.6622475975547324e-05, + "loss": 1.4129, + "step": 3267 + }, + { + "epoch": 0.34, + "learning_rate": 1.661973296123335e-05, + "loss": 1.4152, + "step": 3268 + }, + { + "epoch": 0.34, + "learning_rate": 1.661698906004525e-05, + "loss": 1.43, + "step": 3269 + }, + { + "epoch": 0.34, + "learning_rate": 1.661424427235064e-05, + "loss": 1.4701, + "step": 3270 + }, + { + "epoch": 0.34, + "learning_rate": 1.6611498598517238e-05, + "loss": 1.4598, + "step": 3271 + }, + { + "epoch": 0.34, + "learning_rate": 1.66087520389129e-05, + "loss": 1.4795, + "step": 3272 + }, + { + "epoch": 0.34, + "learning_rate": 1.6606004593905595e-05, + "loss": 1.5264, + "step": 3273 + }, + { + "epoch": 0.34, + "learning_rate": 1.6603256263863415e-05, + "loss": 1.4412, + "step": 3274 + }, + { + "epoch": 0.34, + "learning_rate": 1.6600507049154556e-05, + "loss": 1.45, + "step": 3275 + }, + { + "epoch": 0.34, + "learning_rate": 1.659775695014735e-05, + "loss": 1.4985, + "step": 3276 + }, + { + "epoch": 0.34, + "learning_rate": 1.659500596721024e-05, + "loss": 1.496, + "step": 3277 + }, + { + "epoch": 0.34, + "learning_rate": 1.6592254100711775e-05, + "loss": 1.4386, + "step": 3278 + }, + { + "epoch": 0.34, + "learning_rate": 1.658950135102065e-05, + "loss": 1.4073, + "step": 3279 + }, + { + "epoch": 0.34, + "learning_rate": 1.658674771850565e-05, + "loss": 1.3912, + "step": 3280 + }, + { + "epoch": 0.34, + "learning_rate": 1.6583993203535702e-05, + "loss": 1.3628, + "step": 3281 + }, + { + "epoch": 0.34, + "learning_rate": 1.658123780647983e-05, + "loss": 1.6089, + "step": 3282 + }, + { + "epoch": 0.34, + "learning_rate": 1.6578481527707196e-05, + "loss": 1.2367, + "step": 3283 + }, + { + "epoch": 0.34, + "learning_rate": 1.657572436758706e-05, + "loss": 1.4058, + "step": 3284 + }, + { + "epoch": 0.34, + "learning_rate": 1.6572966326488825e-05, + "loss": 1.4067, + "step": 3285 + }, + { + "epoch": 0.34, + "learning_rate": 1.657020740478198e-05, + "loss": 1.4187, + "step": 3286 + }, + { + "epoch": 0.34, + "learning_rate": 1.6567447602836166e-05, + "loss": 1.4599, + "step": 3287 + }, + { + "epoch": 0.34, + "learning_rate": 1.6564686921021115e-05, + "loss": 1.432, + "step": 3288 + }, + { + "epoch": 0.34, + "learning_rate": 1.6561925359706693e-05, + "loss": 1.3941, + "step": 3289 + }, + { + "epoch": 0.35, + "learning_rate": 1.6559162919262874e-05, + "loss": 1.3644, + "step": 3290 + }, + { + "epoch": 0.35, + "learning_rate": 1.6556399600059756e-05, + "loss": 1.4628, + "step": 3291 + }, + { + "epoch": 0.35, + "learning_rate": 1.6553635402467555e-05, + "loss": 1.4355, + "step": 3292 + }, + { + "epoch": 0.35, + "learning_rate": 1.6550870326856596e-05, + "loss": 1.4627, + "step": 3293 + }, + { + "epoch": 0.35, + "learning_rate": 1.6548104373597335e-05, + "loss": 1.442, + "step": 3294 + }, + { + "epoch": 0.35, + "learning_rate": 1.6545337543060338e-05, + "loss": 1.3991, + "step": 3295 + }, + { + "epoch": 0.35, + "learning_rate": 1.6542569835616283e-05, + "loss": 1.4193, + "step": 3296 + }, + { + "epoch": 0.35, + "learning_rate": 1.6539801251635982e-05, + "loss": 1.4792, + "step": 3297 + }, + { + "epoch": 0.35, + "learning_rate": 1.653703179149034e-05, + "loss": 1.4735, + "step": 3298 + }, + { + "epoch": 0.35, + "learning_rate": 1.6534261455550408e-05, + "loss": 1.451, + "step": 3299 + }, + { + "epoch": 0.35, + "learning_rate": 1.653149024418733e-05, + "loss": 1.3975, + "step": 3300 + }, + { + "epoch": 0.35, + "learning_rate": 1.652871815777238e-05, + "loss": 1.4843, + "step": 3301 + }, + { + "epoch": 0.35, + "learning_rate": 1.6525945196676948e-05, + "loss": 1.4782, + "step": 3302 + }, + { + "epoch": 0.35, + "learning_rate": 1.652317136127254e-05, + "loss": 1.3865, + "step": 3303 + }, + { + "epoch": 0.35, + "learning_rate": 1.6520396651930777e-05, + "loss": 1.4359, + "step": 3304 + }, + { + "epoch": 0.35, + "learning_rate": 1.6517621069023397e-05, + "loss": 1.4289, + "step": 3305 + }, + { + "epoch": 0.35, + "learning_rate": 1.651484461292226e-05, + "loss": 1.3526, + "step": 3306 + }, + { + "epoch": 0.35, + "learning_rate": 1.6512067283999336e-05, + "loss": 1.3671, + "step": 3307 + }, + { + "epoch": 0.35, + "learning_rate": 1.650928908262672e-05, + "loss": 1.6041, + "step": 3308 + }, + { + "epoch": 0.35, + "learning_rate": 1.650651000917662e-05, + "loss": 1.4322, + "step": 3309 + }, + { + "epoch": 0.35, + "learning_rate": 1.6503730064021354e-05, + "loss": 1.3992, + "step": 3310 + }, + { + "epoch": 0.35, + "learning_rate": 1.650094924753337e-05, + "loss": 1.4928, + "step": 3311 + }, + { + "epoch": 0.35, + "learning_rate": 1.6498167560085222e-05, + "loss": 1.4075, + "step": 3312 + }, + { + "epoch": 0.35, + "learning_rate": 1.6495385002049583e-05, + "loss": 1.4535, + "step": 3313 + }, + { + "epoch": 0.35, + "learning_rate": 1.6492601573799253e-05, + "loss": 1.4221, + "step": 3314 + }, + { + "epoch": 0.35, + "learning_rate": 1.6489817275707133e-05, + "loss": 1.3688, + "step": 3315 + }, + { + "epoch": 0.35, + "learning_rate": 1.6487032108146243e-05, + "loss": 1.3889, + "step": 3316 + }, + { + "epoch": 0.35, + "learning_rate": 1.6484246071489733e-05, + "loss": 1.3942, + "step": 3317 + }, + { + "epoch": 0.35, + "learning_rate": 1.6481459166110858e-05, + "loss": 1.4004, + "step": 3318 + }, + { + "epoch": 0.35, + "learning_rate": 1.647867139238299e-05, + "loss": 1.7308, + "step": 3319 + }, + { + "epoch": 0.35, + "learning_rate": 1.6475882750679622e-05, + "loss": 1.5001, + "step": 3320 + }, + { + "epoch": 0.35, + "learning_rate": 1.647309324137435e-05, + "loss": 1.4325, + "step": 3321 + }, + { + "epoch": 0.35, + "learning_rate": 1.6470302864840913e-05, + "loss": 1.4494, + "step": 3322 + }, + { + "epoch": 0.35, + "learning_rate": 1.6467511621453136e-05, + "loss": 1.4418, + "step": 3323 + }, + { + "epoch": 0.35, + "learning_rate": 1.646471951158498e-05, + "loss": 1.4046, + "step": 3324 + }, + { + "epoch": 0.35, + "learning_rate": 1.6461926535610517e-05, + "loss": 1.5031, + "step": 3325 + }, + { + "epoch": 0.35, + "learning_rate": 1.645913269390393e-05, + "loss": 1.4813, + "step": 3326 + }, + { + "epoch": 0.35, + "learning_rate": 1.6456337986839525e-05, + "loss": 1.3842, + "step": 3327 + }, + { + "epoch": 0.35, + "learning_rate": 1.645354241479172e-05, + "loss": 1.4539, + "step": 3328 + }, + { + "epoch": 0.35, + "learning_rate": 1.6450745978135048e-05, + "loss": 1.4503, + "step": 3329 + }, + { + "epoch": 0.35, + "learning_rate": 1.6447948677244163e-05, + "loss": 1.3741, + "step": 3330 + }, + { + "epoch": 0.35, + "learning_rate": 1.6445150512493832e-05, + "loss": 1.425, + "step": 3331 + }, + { + "epoch": 0.35, + "learning_rate": 1.644235148425893e-05, + "loss": 1.4277, + "step": 3332 + }, + { + "epoch": 0.35, + "learning_rate": 1.6439551592914464e-05, + "loss": 1.4918, + "step": 3333 + }, + { + "epoch": 0.35, + "learning_rate": 1.6436750838835543e-05, + "loss": 1.3364, + "step": 3334 + }, + { + "epoch": 0.35, + "learning_rate": 1.6433949222397397e-05, + "loss": 1.4741, + "step": 3335 + }, + { + "epoch": 0.35, + "learning_rate": 1.643114674397537e-05, + "loss": 1.3867, + "step": 3336 + }, + { + "epoch": 0.35, + "learning_rate": 1.642834340394492e-05, + "loss": 1.3817, + "step": 3337 + }, + { + "epoch": 0.35, + "learning_rate": 1.6425539202681625e-05, + "loss": 1.4308, + "step": 3338 + }, + { + "epoch": 0.35, + "learning_rate": 1.6422734140561178e-05, + "loss": 1.4401, + "step": 3339 + }, + { + "epoch": 0.35, + "learning_rate": 1.641992821795938e-05, + "loss": 1.4338, + "step": 3340 + }, + { + "epoch": 0.35, + "learning_rate": 1.641712143525216e-05, + "loss": 1.3804, + "step": 3341 + }, + { + "epoch": 0.35, + "learning_rate": 1.6414313792815546e-05, + "loss": 1.371, + "step": 3342 + }, + { + "epoch": 0.35, + "learning_rate": 1.6411505291025695e-05, + "loss": 1.4102, + "step": 3343 + }, + { + "epoch": 0.35, + "learning_rate": 1.6408695930258875e-05, + "loss": 1.4433, + "step": 3344 + }, + { + "epoch": 0.35, + "learning_rate": 1.6405885710891467e-05, + "loss": 1.3895, + "step": 3345 + }, + { + "epoch": 0.35, + "learning_rate": 1.6403074633299966e-05, + "loss": 1.4321, + "step": 3346 + }, + { + "epoch": 0.35, + "learning_rate": 1.640026269786098e-05, + "loss": 1.4207, + "step": 3347 + }, + { + "epoch": 0.35, + "learning_rate": 1.639744990495125e-05, + "loss": 1.3758, + "step": 3348 + }, + { + "epoch": 0.35, + "learning_rate": 1.6394636254947612e-05, + "loss": 1.4203, + "step": 3349 + }, + { + "epoch": 0.35, + "learning_rate": 1.6391821748227013e-05, + "loss": 1.4596, + "step": 3350 + }, + { + "epoch": 0.35, + "learning_rate": 1.6389006385166537e-05, + "loss": 1.4344, + "step": 3351 + }, + { + "epoch": 0.35, + "learning_rate": 1.6386190166143366e-05, + "loss": 1.4048, + "step": 3352 + }, + { + "epoch": 0.35, + "learning_rate": 1.6383373091534798e-05, + "loss": 1.4348, + "step": 3353 + }, + { + "epoch": 0.35, + "learning_rate": 1.638055516171825e-05, + "loss": 1.4972, + "step": 3354 + }, + { + "epoch": 0.35, + "learning_rate": 1.6377736377071258e-05, + "loss": 1.4685, + "step": 3355 + }, + { + "epoch": 0.35, + "learning_rate": 1.637491673797146e-05, + "loss": 1.4093, + "step": 3356 + }, + { + "epoch": 0.35, + "learning_rate": 1.6372096244796616e-05, + "loss": 1.4452, + "step": 3357 + }, + { + "epoch": 0.35, + "learning_rate": 1.63692748979246e-05, + "loss": 1.4458, + "step": 3358 + }, + { + "epoch": 0.35, + "learning_rate": 1.6366452697733404e-05, + "loss": 1.4187, + "step": 3359 + }, + { + "epoch": 0.35, + "learning_rate": 1.6363629644601126e-05, + "loss": 1.4052, + "step": 3360 + }, + { + "epoch": 0.35, + "learning_rate": 1.6360805738905984e-05, + "loss": 1.439, + "step": 3361 + }, + { + "epoch": 0.35, + "learning_rate": 1.635798098102631e-05, + "loss": 1.4131, + "step": 3362 + }, + { + "epoch": 0.35, + "learning_rate": 1.6355155371340544e-05, + "loss": 1.4391, + "step": 3363 + }, + { + "epoch": 0.35, + "learning_rate": 1.6352328910227252e-05, + "loss": 1.4318, + "step": 3364 + }, + { + "epoch": 0.35, + "learning_rate": 1.63495015980651e-05, + "loss": 1.5112, + "step": 3365 + }, + { + "epoch": 0.35, + "learning_rate": 1.6346673435232884e-05, + "loss": 1.4688, + "step": 3366 + }, + { + "epoch": 0.35, + "learning_rate": 1.6343844422109496e-05, + "loss": 1.3807, + "step": 3367 + }, + { + "epoch": 0.35, + "learning_rate": 1.634101455907396e-05, + "loss": 1.4083, + "step": 3368 + }, + { + "epoch": 0.35, + "learning_rate": 1.6338183846505394e-05, + "loss": 1.3566, + "step": 3369 + }, + { + "epoch": 0.35, + "learning_rate": 1.633535228478305e-05, + "loss": 1.4287, + "step": 3370 + }, + { + "epoch": 0.35, + "learning_rate": 1.6332519874286285e-05, + "loss": 1.3494, + "step": 3371 + }, + { + "epoch": 0.35, + "learning_rate": 1.6329686615394558e-05, + "loss": 1.3813, + "step": 3372 + }, + { + "epoch": 0.35, + "learning_rate": 1.6326852508487468e-05, + "loss": 1.4241, + "step": 3373 + }, + { + "epoch": 0.35, + "learning_rate": 1.63240175539447e-05, + "loss": 1.424, + "step": 3374 + }, + { + "epoch": 0.35, + "learning_rate": 1.632118175214607e-05, + "loss": 1.4212, + "step": 3375 + }, + { + "epoch": 0.35, + "learning_rate": 1.6318345103471504e-05, + "loss": 1.4671, + "step": 3376 + }, + { + "epoch": 0.35, + "learning_rate": 1.6315507608301044e-05, + "loss": 1.4593, + "step": 3377 + }, + { + "epoch": 0.35, + "learning_rate": 1.631266926701483e-05, + "loss": 1.7816, + "step": 3378 + }, + { + "epoch": 0.35, + "learning_rate": 1.6309830079993134e-05, + "loss": 1.5134, + "step": 3379 + }, + { + "epoch": 0.35, + "learning_rate": 1.6306990047616334e-05, + "loss": 0.8933, + "step": 3380 + }, + { + "epoch": 0.35, + "learning_rate": 1.630414917026492e-05, + "loss": 1.1033, + "step": 3381 + }, + { + "epoch": 0.35, + "learning_rate": 1.6301307448319497e-05, + "loss": 1.3494, + "step": 3382 + }, + { + "epoch": 0.35, + "learning_rate": 1.6298464882160784e-05, + "loss": 1.4299, + "step": 3383 + }, + { + "epoch": 0.35, + "eval_loss": 1.482450008392334, + "eval_runtime": 77.3737, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3383 + }, + { + "epoch": 0.35, + "learning_rate": 1.629562147216961e-05, + "loss": 1.3971, + "step": 3384 + }, + { + "epoch": 0.35, + "learning_rate": 1.6292777218726917e-05, + "loss": 1.3706, + "step": 3385 + }, + { + "epoch": 0.36, + "learning_rate": 1.6289932122213765e-05, + "loss": 1.4524, + "step": 3386 + }, + { + "epoch": 0.36, + "learning_rate": 1.6287086183011328e-05, + "loss": 1.4595, + "step": 3387 + }, + { + "epoch": 0.36, + "learning_rate": 1.628423940150088e-05, + "loss": 1.492, + "step": 3388 + }, + { + "epoch": 0.36, + "learning_rate": 1.628139177806382e-05, + "loss": 1.5576, + "step": 3389 + }, + { + "epoch": 0.36, + "learning_rate": 1.6278543313081657e-05, + "loss": 1.4615, + "step": 3390 + }, + { + "epoch": 0.36, + "learning_rate": 1.6275694006936015e-05, + "loss": 1.3456, + "step": 3391 + }, + { + "epoch": 0.36, + "learning_rate": 1.627284386000862e-05, + "loss": 1.4254, + "step": 3392 + }, + { + "epoch": 0.36, + "learning_rate": 1.6269992872681325e-05, + "loss": 1.433, + "step": 3393 + }, + { + "epoch": 0.36, + "learning_rate": 1.626714104533609e-05, + "loss": 1.5291, + "step": 3394 + }, + { + "epoch": 0.36, + "learning_rate": 1.626428837835498e-05, + "loss": 1.4502, + "step": 3395 + }, + { + "epoch": 0.36, + "learning_rate": 1.626143487212019e-05, + "loss": 1.3756, + "step": 3396 + }, + { + "epoch": 0.36, + "learning_rate": 1.6258580527014002e-05, + "loss": 1.414, + "step": 3397 + }, + { + "epoch": 0.36, + "learning_rate": 1.6255725343418835e-05, + "loss": 1.6289, + "step": 3398 + }, + { + "epoch": 0.36, + "learning_rate": 1.6252869321717208e-05, + "loss": 1.4862, + "step": 3399 + }, + { + "epoch": 0.36, + "learning_rate": 1.6250012462291756e-05, + "loss": 1.4213, + "step": 3400 + }, + { + "epoch": 0.36, + "learning_rate": 1.6247154765525217e-05, + "loss": 1.524, + "step": 3401 + }, + { + "epoch": 0.36, + "learning_rate": 1.624429623180046e-05, + "loss": 1.6013, + "step": 3402 + }, + { + "epoch": 0.36, + "learning_rate": 1.624143686150045e-05, + "loss": 1.4557, + "step": 3403 + }, + { + "epoch": 0.36, + "learning_rate": 1.6238576655008266e-05, + "loss": 1.3831, + "step": 3404 + }, + { + "epoch": 0.36, + "learning_rate": 1.6235715612707105e-05, + "loss": 1.4008, + "step": 3405 + }, + { + "epoch": 0.36, + "learning_rate": 1.623285373498028e-05, + "loss": 1.4848, + "step": 3406 + }, + { + "epoch": 0.36, + "learning_rate": 1.6229991022211197e-05, + "loss": 1.4459, + "step": 3407 + }, + { + "epoch": 0.36, + "learning_rate": 1.6227127474783393e-05, + "loss": 1.4334, + "step": 3408 + }, + { + "epoch": 0.36, + "learning_rate": 1.6224263093080507e-05, + "loss": 1.4123, + "step": 3409 + }, + { + "epoch": 0.36, + "learning_rate": 1.6221397877486294e-05, + "loss": 1.3691, + "step": 3410 + }, + { + "epoch": 0.36, + "learning_rate": 1.6218531828384618e-05, + "loss": 1.4128, + "step": 3411 + }, + { + "epoch": 0.36, + "learning_rate": 1.6215664946159457e-05, + "loss": 1.3642, + "step": 3412 + }, + { + "epoch": 0.36, + "learning_rate": 1.6212797231194902e-05, + "loss": 1.4311, + "step": 3413 + }, + { + "epoch": 0.36, + "learning_rate": 1.6209928683875152e-05, + "loss": 1.4695, + "step": 3414 + }, + { + "epoch": 0.36, + "learning_rate": 1.6207059304584514e-05, + "loss": 1.3871, + "step": 3415 + }, + { + "epoch": 0.36, + "learning_rate": 1.6204189093707414e-05, + "loss": 1.4219, + "step": 3416 + }, + { + "epoch": 0.36, + "learning_rate": 1.620131805162839e-05, + "loss": 1.6199, + "step": 3417 + }, + { + "epoch": 0.36, + "learning_rate": 1.619844617873208e-05, + "loss": 1.4433, + "step": 3418 + }, + { + "epoch": 0.36, + "learning_rate": 1.619557347540325e-05, + "loss": 1.4773, + "step": 3419 + }, + { + "epoch": 0.36, + "learning_rate": 1.6192699942026763e-05, + "loss": 1.4551, + "step": 3420 + }, + { + "epoch": 0.36, + "learning_rate": 1.6189825578987603e-05, + "loss": 1.4903, + "step": 3421 + }, + { + "epoch": 0.36, + "learning_rate": 1.6186950386670855e-05, + "loss": 1.473, + "step": 3422 + }, + { + "epoch": 0.36, + "learning_rate": 1.6184074365461722e-05, + "loss": 1.4082, + "step": 3423 + }, + { + "epoch": 0.36, + "learning_rate": 1.6181197515745523e-05, + "loss": 1.4746, + "step": 3424 + }, + { + "epoch": 0.36, + "learning_rate": 1.6178319837907674e-05, + "loss": 1.449, + "step": 3425 + }, + { + "epoch": 0.36, + "learning_rate": 1.6175441332333715e-05, + "loss": 1.377, + "step": 3426 + }, + { + "epoch": 0.36, + "learning_rate": 1.617256199940929e-05, + "loss": 1.2364, + "step": 3427 + }, + { + "epoch": 0.36, + "learning_rate": 1.6169681839520155e-05, + "loss": 1.4437, + "step": 3428 + }, + { + "epoch": 0.36, + "learning_rate": 1.616680085305218e-05, + "loss": 1.4726, + "step": 3429 + }, + { + "epoch": 0.36, + "learning_rate": 1.616391904039134e-05, + "loss": 1.4824, + "step": 3430 + }, + { + "epoch": 0.36, + "learning_rate": 1.616103640192373e-05, + "loss": 1.4052, + "step": 3431 + }, + { + "epoch": 0.36, + "learning_rate": 1.6158152938035537e-05, + "loss": 1.4131, + "step": 3432 + }, + { + "epoch": 0.36, + "learning_rate": 1.6155268649113084e-05, + "loss": 1.4267, + "step": 3433 + }, + { + "epoch": 0.36, + "learning_rate": 1.6152383535542786e-05, + "loss": 1.3735, + "step": 3434 + }, + { + "epoch": 0.36, + "learning_rate": 1.6149497597711175e-05, + "loss": 1.4249, + "step": 3435 + }, + { + "epoch": 0.36, + "learning_rate": 1.614661083600489e-05, + "loss": 1.4312, + "step": 3436 + }, + { + "epoch": 0.36, + "learning_rate": 1.6143723250810686e-05, + "loss": 1.4831, + "step": 3437 + }, + { + "epoch": 0.36, + "learning_rate": 1.6140834842515425e-05, + "loss": 1.4183, + "step": 3438 + }, + { + "epoch": 0.36, + "learning_rate": 1.6137945611506078e-05, + "loss": 1.3908, + "step": 3439 + }, + { + "epoch": 0.36, + "learning_rate": 1.613505555816973e-05, + "loss": 1.425, + "step": 3440 + }, + { + "epoch": 0.36, + "learning_rate": 1.613216468289357e-05, + "loss": 1.3589, + "step": 3441 + }, + { + "epoch": 0.36, + "learning_rate": 1.6129272986064903e-05, + "loss": 1.4272, + "step": 3442 + }, + { + "epoch": 0.36, + "learning_rate": 1.6126380468071142e-05, + "loss": 1.4337, + "step": 3443 + }, + { + "epoch": 0.36, + "learning_rate": 1.6123487129299817e-05, + "loss": 1.3872, + "step": 3444 + }, + { + "epoch": 0.36, + "learning_rate": 1.612059297013855e-05, + "loss": 1.374, + "step": 3445 + }, + { + "epoch": 0.36, + "learning_rate": 1.611769799097509e-05, + "loss": 1.314, + "step": 3446 + }, + { + "epoch": 0.36, + "learning_rate": 1.6114802192197284e-05, + "loss": 1.3951, + "step": 3447 + }, + { + "epoch": 0.36, + "learning_rate": 1.6111905574193102e-05, + "loss": 1.4732, + "step": 3448 + }, + { + "epoch": 0.36, + "learning_rate": 1.6109008137350614e-05, + "loss": 1.3575, + "step": 3449 + }, + { + "epoch": 0.36, + "learning_rate": 1.6106109882058e-05, + "loss": 1.4606, + "step": 3450 + }, + { + "epoch": 0.36, + "learning_rate": 1.6103210808703554e-05, + "loss": 1.4357, + "step": 3451 + }, + { + "epoch": 0.36, + "learning_rate": 1.6100310917675678e-05, + "loss": 0.8456, + "step": 3452 + }, + { + "epoch": 0.36, + "learning_rate": 1.609741020936288e-05, + "loss": 1.07, + "step": 3453 + }, + { + "epoch": 0.36, + "learning_rate": 1.6094508684153782e-05, + "loss": 1.4435, + "step": 3454 + }, + { + "epoch": 0.36, + "learning_rate": 1.609160634243711e-05, + "loss": 1.3696, + "step": 3455 + }, + { + "epoch": 0.36, + "learning_rate": 1.6088703184601712e-05, + "loss": 1.4012, + "step": 3456 + }, + { + "epoch": 0.36, + "learning_rate": 1.608579921103653e-05, + "loss": 1.5212, + "step": 3457 + }, + { + "epoch": 0.36, + "learning_rate": 1.608289442213062e-05, + "loss": 1.4339, + "step": 3458 + }, + { + "epoch": 0.36, + "learning_rate": 1.607998881827316e-05, + "loss": 1.4901, + "step": 3459 + }, + { + "epoch": 0.36, + "learning_rate": 1.6077082399853412e-05, + "loss": 1.4822, + "step": 3460 + }, + { + "epoch": 0.36, + "learning_rate": 1.607417516726077e-05, + "loss": 1.3696, + "step": 3461 + }, + { + "epoch": 0.36, + "learning_rate": 1.6071267120884727e-05, + "loss": 1.4434, + "step": 3462 + }, + { + "epoch": 0.36, + "learning_rate": 1.6068358261114886e-05, + "loss": 1.3916, + "step": 3463 + }, + { + "epoch": 0.36, + "learning_rate": 1.606544858834096e-05, + "loss": 1.422, + "step": 3464 + }, + { + "epoch": 0.36, + "learning_rate": 1.6062538102952763e-05, + "loss": 1.367, + "step": 3465 + }, + { + "epoch": 0.36, + "learning_rate": 1.605962680534024e-05, + "loss": 1.3788, + "step": 3466 + }, + { + "epoch": 0.36, + "learning_rate": 1.605671469589342e-05, + "loss": 1.4366, + "step": 3467 + }, + { + "epoch": 0.36, + "learning_rate": 1.6053801775002453e-05, + "loss": 1.4027, + "step": 3468 + }, + { + "epoch": 0.36, + "learning_rate": 1.6050888043057595e-05, + "loss": 1.4386, + "step": 3469 + }, + { + "epoch": 0.36, + "learning_rate": 1.6047973500449212e-05, + "loss": 1.4675, + "step": 3470 + }, + { + "epoch": 0.36, + "learning_rate": 1.6045058147567778e-05, + "loss": 1.6936, + "step": 3471 + }, + { + "epoch": 0.36, + "learning_rate": 1.6042141984803875e-05, + "loss": 1.4858, + "step": 3472 + }, + { + "epoch": 0.36, + "learning_rate": 1.6039225012548196e-05, + "loss": 1.5004, + "step": 3473 + }, + { + "epoch": 0.36, + "learning_rate": 1.6036307231191534e-05, + "loss": 1.4969, + "step": 3474 + }, + { + "epoch": 0.36, + "learning_rate": 1.6033388641124803e-05, + "loss": 1.4027, + "step": 3475 + }, + { + "epoch": 0.36, + "learning_rate": 1.6030469242739016e-05, + "loss": 1.4741, + "step": 3476 + }, + { + "epoch": 0.36, + "learning_rate": 1.60275490364253e-05, + "loss": 1.3887, + "step": 3477 + }, + { + "epoch": 0.36, + "learning_rate": 1.602462802257488e-05, + "loss": 1.6735, + "step": 3478 + }, + { + "epoch": 0.36, + "learning_rate": 1.602170620157911e-05, + "loss": 1.4997, + "step": 3479 + }, + { + "epoch": 0.36, + "learning_rate": 1.601878357382943e-05, + "loss": 1.3973, + "step": 3480 + }, + { + "epoch": 0.37, + "learning_rate": 1.6015860139717398e-05, + "loss": 1.416, + "step": 3481 + }, + { + "epoch": 0.37, + "learning_rate": 1.6012935899634682e-05, + "loss": 1.4102, + "step": 3482 + }, + { + "epoch": 0.37, + "learning_rate": 1.601001085397305e-05, + "loss": 1.4248, + "step": 3483 + }, + { + "epoch": 0.37, + "learning_rate": 1.6007085003124386e-05, + "loss": 1.3909, + "step": 3484 + }, + { + "epoch": 0.37, + "learning_rate": 1.600415834748068e-05, + "loss": 1.4029, + "step": 3485 + }, + { + "epoch": 0.37, + "learning_rate": 1.6001230887434024e-05, + "loss": 1.4219, + "step": 3486 + }, + { + "epoch": 0.37, + "learning_rate": 1.5998302623376633e-05, + "loss": 1.4008, + "step": 3487 + }, + { + "epoch": 0.37, + "learning_rate": 1.5995373555700806e-05, + "loss": 1.5163, + "step": 3488 + }, + { + "epoch": 0.37, + "learning_rate": 1.599244368479897e-05, + "loss": 1.4541, + "step": 3489 + }, + { + "epoch": 0.37, + "learning_rate": 1.598951301106365e-05, + "loss": 1.4454, + "step": 3490 + }, + { + "epoch": 0.37, + "learning_rate": 1.598658153488748e-05, + "loss": 1.1014, + "step": 3491 + }, + { + "epoch": 0.37, + "learning_rate": 1.598364925666321e-05, + "loss": 1.407, + "step": 3492 + }, + { + "epoch": 0.37, + "learning_rate": 1.5980716176783682e-05, + "loss": 1.5046, + "step": 3493 + }, + { + "epoch": 0.37, + "learning_rate": 1.5977782295641857e-05, + "loss": 1.4265, + "step": 3494 + }, + { + "epoch": 0.37, + "learning_rate": 1.5974847613630796e-05, + "loss": 1.46, + "step": 3495 + }, + { + "epoch": 0.37, + "learning_rate": 1.5971912131143677e-05, + "loss": 1.3996, + "step": 3496 + }, + { + "epoch": 0.37, + "learning_rate": 1.5968975848573772e-05, + "loss": 1.4719, + "step": 3497 + }, + { + "epoch": 0.37, + "learning_rate": 1.596603876631447e-05, + "loss": 1.43, + "step": 3498 + }, + { + "epoch": 0.37, + "learning_rate": 1.596310088475927e-05, + "loss": 1.4109, + "step": 3499 + }, + { + "epoch": 0.37, + "learning_rate": 1.5960162204301768e-05, + "loss": 1.3612, + "step": 3500 + }, + { + "epoch": 0.37, + "learning_rate": 1.5957222725335672e-05, + "loss": 1.5045, + "step": 3501 + }, + { + "epoch": 0.37, + "learning_rate": 1.5954282448254794e-05, + "loss": 1.5323, + "step": 3502 + }, + { + "epoch": 0.37, + "learning_rate": 1.595134137345306e-05, + "loss": 1.4518, + "step": 3503 + }, + { + "epoch": 0.37, + "learning_rate": 1.5948399501324495e-05, + "loss": 1.6131, + "step": 3504 + }, + { + "epoch": 0.37, + "learning_rate": 1.594545683226324e-05, + "loss": 1.5076, + "step": 3505 + }, + { + "epoch": 0.37, + "learning_rate": 1.594251336666353e-05, + "loss": 1.482, + "step": 3506 + }, + { + "epoch": 0.37, + "learning_rate": 1.5939569104919716e-05, + "loss": 1.4429, + "step": 3507 + }, + { + "epoch": 0.37, + "learning_rate": 1.5936624047426254e-05, + "loss": 1.4662, + "step": 3508 + }, + { + "epoch": 0.37, + "learning_rate": 1.5933678194577708e-05, + "loss": 1.425, + "step": 3509 + }, + { + "epoch": 0.37, + "learning_rate": 1.5930731546768744e-05, + "loss": 1.4312, + "step": 3510 + }, + { + "epoch": 0.37, + "learning_rate": 1.592778410439414e-05, + "loss": 1.4336, + "step": 3511 + }, + { + "epoch": 0.37, + "learning_rate": 1.5924835867848775e-05, + "loss": 1.4197, + "step": 3512 + }, + { + "epoch": 0.37, + "learning_rate": 1.5921886837527638e-05, + "loss": 1.4456, + "step": 3513 + }, + { + "epoch": 0.37, + "learning_rate": 1.5918937013825823e-05, + "loss": 1.4394, + "step": 3514 + }, + { + "epoch": 0.37, + "learning_rate": 1.5915986397138526e-05, + "loss": 1.3606, + "step": 3515 + }, + { + "epoch": 0.37, + "learning_rate": 1.591303498786106e-05, + "loss": 1.4382, + "step": 3516 + }, + { + "epoch": 0.37, + "learning_rate": 1.591008278638884e-05, + "loss": 1.4185, + "step": 3517 + }, + { + "epoch": 0.37, + "learning_rate": 1.5907129793117374e-05, + "loss": 1.6692, + "step": 3518 + }, + { + "epoch": 0.37, + "learning_rate": 1.59041760084423e-05, + "loss": 1.501, + "step": 3519 + }, + { + "epoch": 0.37, + "learning_rate": 1.5901221432759345e-05, + "loss": 1.5753, + "step": 3520 + }, + { + "epoch": 0.37, + "learning_rate": 1.589826606646434e-05, + "loss": 1.4795, + "step": 3521 + }, + { + "epoch": 0.37, + "learning_rate": 1.5895309909953236e-05, + "loss": 1.4379, + "step": 3522 + }, + { + "epoch": 0.37, + "learning_rate": 1.5892352963622078e-05, + "loss": 1.3426, + "step": 3523 + }, + { + "epoch": 0.37, + "learning_rate": 1.5889395227867025e-05, + "loss": 1.4048, + "step": 3524 + }, + { + "epoch": 0.37, + "learning_rate": 1.5886436703084332e-05, + "loss": 1.4303, + "step": 3525 + }, + { + "epoch": 0.37, + "learning_rate": 1.5883477389670367e-05, + "loss": 1.3684, + "step": 3526 + }, + { + "epoch": 0.37, + "learning_rate": 1.5880517288021602e-05, + "loss": 1.3701, + "step": 3527 + }, + { + "epoch": 0.37, + "learning_rate": 1.587755639853462e-05, + "loss": 1.4308, + "step": 3528 + }, + { + "epoch": 0.37, + "learning_rate": 1.5874594721606096e-05, + "loss": 1.3981, + "step": 3529 + }, + { + "epoch": 0.37, + "learning_rate": 1.5871632257632823e-05, + "loss": 1.5906, + "step": 3530 + }, + { + "epoch": 0.37, + "learning_rate": 1.5868669007011696e-05, + "loss": 1.4642, + "step": 3531 + }, + { + "epoch": 0.37, + "learning_rate": 1.586570497013971e-05, + "loss": 1.411, + "step": 3532 + }, + { + "epoch": 0.37, + "learning_rate": 1.586274014741397e-05, + "loss": 1.3942, + "step": 3533 + }, + { + "epoch": 0.37, + "learning_rate": 1.5859774539231693e-05, + "loss": 1.3952, + "step": 3534 + }, + { + "epoch": 0.37, + "learning_rate": 1.585680814599019e-05, + "loss": 1.4009, + "step": 3535 + }, + { + "epoch": 0.37, + "learning_rate": 1.585384096808688e-05, + "loss": 1.3238, + "step": 3536 + }, + { + "epoch": 0.37, + "learning_rate": 1.585087300591929e-05, + "loss": 1.346, + "step": 3537 + }, + { + "epoch": 0.37, + "learning_rate": 1.584790425988505e-05, + "loss": 1.3739, + "step": 3538 + }, + { + "epoch": 0.37, + "learning_rate": 1.5844934730381895e-05, + "loss": 1.4264, + "step": 3539 + }, + { + "epoch": 0.37, + "learning_rate": 1.5841964417807668e-05, + "loss": 1.4675, + "step": 3540 + }, + { + "epoch": 0.37, + "learning_rate": 1.5838993322560314e-05, + "loss": 1.3337, + "step": 3541 + }, + { + "epoch": 0.37, + "learning_rate": 1.5836021445037883e-05, + "loss": 1.4052, + "step": 3542 + }, + { + "epoch": 0.37, + "learning_rate": 1.583304878563853e-05, + "loss": 1.4311, + "step": 3543 + }, + { + "epoch": 0.37, + "learning_rate": 1.5830075344760513e-05, + "loss": 1.386, + "step": 3544 + }, + { + "epoch": 0.37, + "learning_rate": 1.58271011228022e-05, + "loss": 1.387, + "step": 3545 + }, + { + "epoch": 0.37, + "learning_rate": 1.582412612016206e-05, + "loss": 1.3601, + "step": 3546 + }, + { + "epoch": 0.37, + "learning_rate": 1.5821150337238663e-05, + "loss": 1.5111, + "step": 3547 + }, + { + "epoch": 0.37, + "learning_rate": 1.5818173774430697e-05, + "loss": 1.471, + "step": 3548 + }, + { + "epoch": 0.37, + "learning_rate": 1.581519643213693e-05, + "loss": 1.4442, + "step": 3549 + }, + { + "epoch": 0.37, + "learning_rate": 1.5812218310756263e-05, + "loss": 1.467, + "step": 3550 + }, + { + "epoch": 0.37, + "learning_rate": 1.5809239410687683e-05, + "loss": 1.3731, + "step": 3551 + }, + { + "epoch": 0.37, + "learning_rate": 1.5806259732330286e-05, + "loss": 1.4072, + "step": 3552 + }, + { + "epoch": 0.37, + "learning_rate": 1.5803279276083268e-05, + "loss": 1.3636, + "step": 3553 + }, + { + "epoch": 0.37, + "learning_rate": 1.5800298042345938e-05, + "loss": 1.3915, + "step": 3554 + }, + { + "epoch": 0.37, + "learning_rate": 1.5797316031517705e-05, + "loss": 1.5038, + "step": 3555 + }, + { + "epoch": 0.37, + "learning_rate": 1.5794333243998082e-05, + "loss": 1.4455, + "step": 3556 + }, + { + "epoch": 0.37, + "learning_rate": 1.5791349680186684e-05, + "loss": 1.5062, + "step": 3557 + }, + { + "epoch": 0.37, + "learning_rate": 1.5788365340483234e-05, + "loss": 1.3899, + "step": 3558 + }, + { + "epoch": 0.37, + "learning_rate": 1.5785380225287554e-05, + "loss": 1.4946, + "step": 3559 + }, + { + "epoch": 0.37, + "learning_rate": 1.5782394334999572e-05, + "loss": 1.3859, + "step": 3560 + }, + { + "epoch": 0.37, + "learning_rate": 1.577940767001933e-05, + "loss": 1.541, + "step": 3561 + }, + { + "epoch": 0.37, + "learning_rate": 1.5776420230746952e-05, + "loss": 1.4952, + "step": 3562 + }, + { + "epoch": 0.37, + "learning_rate": 1.5773432017582684e-05, + "loss": 1.6055, + "step": 3563 + }, + { + "epoch": 0.37, + "learning_rate": 1.577044303092687e-05, + "loss": 1.4661, + "step": 3564 + }, + { + "epoch": 0.37, + "learning_rate": 1.576745327117996e-05, + "loss": 1.4082, + "step": 3565 + }, + { + "epoch": 0.37, + "learning_rate": 1.5764462738742493e-05, + "loss": 1.4005, + "step": 3566 + }, + { + "epoch": 0.37, + "learning_rate": 1.5761471434015137e-05, + "loss": 1.3959, + "step": 3567 + }, + { + "epoch": 0.37, + "learning_rate": 1.5758479357398645e-05, + "loss": 1.4567, + "step": 3568 + }, + { + "epoch": 0.37, + "learning_rate": 1.575548650929388e-05, + "loss": 1.3791, + "step": 3569 + }, + { + "epoch": 0.37, + "learning_rate": 1.57524928901018e-05, + "loss": 1.4428, + "step": 3570 + }, + { + "epoch": 0.37, + "learning_rate": 1.5749498500223486e-05, + "loss": 1.3864, + "step": 3571 + }, + { + "epoch": 0.37, + "learning_rate": 1.5746503340060097e-05, + "loss": 1.4019, + "step": 3572 + }, + { + "epoch": 0.37, + "learning_rate": 1.574350741001291e-05, + "loss": 1.5436, + "step": 3573 + }, + { + "epoch": 0.37, + "learning_rate": 1.5740510710483308e-05, + "loss": 1.4637, + "step": 3574 + }, + { + "epoch": 0.37, + "learning_rate": 1.5737513241872767e-05, + "loss": 1.5097, + "step": 3575 + }, + { + "epoch": 0.38, + "learning_rate": 1.5734515004582873e-05, + "loss": 1.5143, + "step": 3576 + }, + { + "epoch": 0.38, + "learning_rate": 1.5731515999015315e-05, + "loss": 1.3926, + "step": 3577 + }, + { + "epoch": 0.38, + "learning_rate": 1.5728516225571874e-05, + "loss": 1.4242, + "step": 3578 + }, + { + "epoch": 0.38, + "learning_rate": 1.5725515684654453e-05, + "loss": 1.4429, + "step": 3579 + }, + { + "epoch": 0.38, + "learning_rate": 1.572251437666504e-05, + "loss": 1.4638, + "step": 3580 + }, + { + "epoch": 0.38, + "learning_rate": 1.5719512302005735e-05, + "loss": 1.3381, + "step": 3581 + }, + { + "epoch": 0.38, + "learning_rate": 1.571650946107874e-05, + "loss": 1.4342, + "step": 3582 + }, + { + "epoch": 0.38, + "eval_loss": 1.4705015420913696, + "eval_runtime": 77.3664, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3582 + }, + { + "epoch": 0.38, + "learning_rate": 1.571350585428636e-05, + "loss": 1.3991, + "step": 3583 + }, + { + "epoch": 0.38, + "learning_rate": 1.5710501482030998e-05, + "loss": 1.4274, + "step": 3584 + }, + { + "epoch": 0.38, + "learning_rate": 1.5707496344715166e-05, + "loss": 1.438, + "step": 3585 + }, + { + "epoch": 0.38, + "learning_rate": 1.570449044274147e-05, + "loss": 1.4453, + "step": 3586 + }, + { + "epoch": 0.38, + "learning_rate": 1.570148377651263e-05, + "loss": 1.4022, + "step": 3587 + }, + { + "epoch": 0.38, + "learning_rate": 1.5698476346431454e-05, + "loss": 1.4312, + "step": 3588 + }, + { + "epoch": 0.38, + "learning_rate": 1.569546815290087e-05, + "loss": 1.4329, + "step": 3589 + }, + { + "epoch": 0.38, + "learning_rate": 1.569245919632389e-05, + "loss": 1.4036, + "step": 3590 + }, + { + "epoch": 0.38, + "learning_rate": 1.5689449477103644e-05, + "loss": 1.412, + "step": 3591 + }, + { + "epoch": 0.38, + "learning_rate": 1.5686438995643353e-05, + "loss": 1.4492, + "step": 3592 + }, + { + "epoch": 0.38, + "learning_rate": 1.5683427752346343e-05, + "loss": 1.4555, + "step": 3593 + }, + { + "epoch": 0.38, + "learning_rate": 1.5680415747616047e-05, + "loss": 1.5594, + "step": 3594 + }, + { + "epoch": 0.38, + "learning_rate": 1.5677402981855993e-05, + "loss": 1.4813, + "step": 3595 + }, + { + "epoch": 0.38, + "learning_rate": 1.567438945546982e-05, + "loss": 1.5919, + "step": 3596 + }, + { + "epoch": 0.38, + "learning_rate": 1.5671375168861255e-05, + "loss": 1.4235, + "step": 3597 + }, + { + "epoch": 0.38, + "learning_rate": 1.5668360122434135e-05, + "loss": 1.441, + "step": 3598 + }, + { + "epoch": 0.38, + "learning_rate": 1.566534431659241e-05, + "loss": 1.5847, + "step": 3599 + }, + { + "epoch": 0.38, + "learning_rate": 1.566232775174011e-05, + "loss": 1.6123, + "step": 3600 + }, + { + "epoch": 0.38, + "learning_rate": 1.5659310428281374e-05, + "loss": 1.4916, + "step": 3601 + }, + { + "epoch": 0.38, + "learning_rate": 1.5656292346620457e-05, + "loss": 1.4603, + "step": 3602 + }, + { + "epoch": 0.38, + "learning_rate": 1.56532735071617e-05, + "loss": 1.4423, + "step": 3603 + }, + { + "epoch": 0.38, + "learning_rate": 1.5650253910309547e-05, + "loss": 1.4814, + "step": 3604 + }, + { + "epoch": 0.38, + "learning_rate": 1.5647233556468552e-05, + "loss": 1.4015, + "step": 3605 + }, + { + "epoch": 0.38, + "learning_rate": 1.564421244604336e-05, + "loss": 1.3798, + "step": 3606 + }, + { + "epoch": 0.38, + "learning_rate": 1.5641190579438723e-05, + "loss": 1.4259, + "step": 3607 + }, + { + "epoch": 0.38, + "learning_rate": 1.5638167957059493e-05, + "loss": 1.3493, + "step": 3608 + }, + { + "epoch": 0.38, + "learning_rate": 1.5635144579310626e-05, + "loss": 1.3433, + "step": 3609 + }, + { + "epoch": 0.38, + "learning_rate": 1.5632120446597177e-05, + "loss": 1.4661, + "step": 3610 + }, + { + "epoch": 0.38, + "learning_rate": 1.5629095559324297e-05, + "loss": 1.4205, + "step": 3611 + }, + { + "epoch": 0.38, + "learning_rate": 1.562606991789725e-05, + "loss": 1.3976, + "step": 3612 + }, + { + "epoch": 0.38, + "learning_rate": 1.5623043522721393e-05, + "loss": 1.4261, + "step": 3613 + }, + { + "epoch": 0.38, + "learning_rate": 1.562001637420218e-05, + "loss": 1.4358, + "step": 3614 + }, + { + "epoch": 0.38, + "learning_rate": 1.5616988472745175e-05, + "loss": 1.437, + "step": 3615 + }, + { + "epoch": 0.38, + "learning_rate": 1.561395981875604e-05, + "loss": 1.3735, + "step": 3616 + }, + { + "epoch": 0.38, + "learning_rate": 1.5610930412640532e-05, + "loss": 1.4357, + "step": 3617 + }, + { + "epoch": 0.38, + "learning_rate": 1.560790025480452e-05, + "loss": 1.4003, + "step": 3618 + }, + { + "epoch": 0.38, + "learning_rate": 1.5604869345653965e-05, + "loss": 1.4127, + "step": 3619 + }, + { + "epoch": 0.38, + "learning_rate": 1.5601837685594927e-05, + "loss": 1.4666, + "step": 3620 + }, + { + "epoch": 0.38, + "learning_rate": 1.5598805275033574e-05, + "loss": 1.4106, + "step": 3621 + }, + { + "epoch": 0.38, + "learning_rate": 1.5595772114376174e-05, + "loss": 1.3857, + "step": 3622 + }, + { + "epoch": 0.38, + "learning_rate": 1.5592738204029086e-05, + "loss": 1.4704, + "step": 3623 + }, + { + "epoch": 0.38, + "learning_rate": 1.558970354439878e-05, + "loss": 1.4649, + "step": 3624 + }, + { + "epoch": 0.38, + "learning_rate": 1.5586668135891824e-05, + "loss": 1.4812, + "step": 3625 + }, + { + "epoch": 0.38, + "learning_rate": 1.5583631978914882e-05, + "loss": 1.3507, + "step": 3626 + }, + { + "epoch": 0.38, + "learning_rate": 1.5580595073874718e-05, + "loss": 1.3762, + "step": 3627 + }, + { + "epoch": 0.38, + "learning_rate": 1.557755742117821e-05, + "loss": 1.4169, + "step": 3628 + }, + { + "epoch": 0.38, + "learning_rate": 1.557451902123231e-05, + "loss": 1.4098, + "step": 3629 + }, + { + "epoch": 0.38, + "learning_rate": 1.55714798744441e-05, + "loss": 1.5526, + "step": 3630 + }, + { + "epoch": 0.38, + "learning_rate": 1.556843998122074e-05, + "loss": 1.4414, + "step": 3631 + }, + { + "epoch": 0.38, + "learning_rate": 1.5565399341969497e-05, + "loss": 1.4134, + "step": 3632 + }, + { + "epoch": 0.38, + "learning_rate": 1.556235795709774e-05, + "loss": 1.4718, + "step": 3633 + }, + { + "epoch": 0.38, + "learning_rate": 1.5559315827012937e-05, + "loss": 1.412, + "step": 3634 + }, + { + "epoch": 0.38, + "learning_rate": 1.5556272952122657e-05, + "loss": 1.4119, + "step": 3635 + }, + { + "epoch": 0.38, + "learning_rate": 1.5553229332834564e-05, + "loss": 1.3999, + "step": 3636 + }, + { + "epoch": 0.38, + "learning_rate": 1.5550184969556428e-05, + "loss": 1.4626, + "step": 3637 + }, + { + "epoch": 0.38, + "learning_rate": 1.5547139862696113e-05, + "loss": 1.3811, + "step": 3638 + }, + { + "epoch": 0.38, + "learning_rate": 1.5544094012661583e-05, + "loss": 1.4053, + "step": 3639 + }, + { + "epoch": 0.38, + "learning_rate": 1.5541047419860907e-05, + "loss": 1.4059, + "step": 3640 + }, + { + "epoch": 0.38, + "learning_rate": 1.553800008470225e-05, + "loss": 1.4717, + "step": 3641 + }, + { + "epoch": 0.38, + "learning_rate": 1.553495200759388e-05, + "loss": 1.399, + "step": 3642 + }, + { + "epoch": 0.38, + "learning_rate": 1.5531903188944154e-05, + "loss": 1.4143, + "step": 3643 + }, + { + "epoch": 0.38, + "learning_rate": 1.5528853629161536e-05, + "loss": 1.4414, + "step": 3644 + }, + { + "epoch": 0.38, + "learning_rate": 1.5525803328654592e-05, + "loss": 1.4206, + "step": 3645 + }, + { + "epoch": 0.38, + "learning_rate": 1.5522752287831982e-05, + "loss": 1.3869, + "step": 3646 + }, + { + "epoch": 0.38, + "learning_rate": 1.551970050710247e-05, + "loss": 1.5434, + "step": 3647 + }, + { + "epoch": 0.38, + "learning_rate": 1.5516647986874914e-05, + "loss": 1.4574, + "step": 3648 + }, + { + "epoch": 0.38, + "learning_rate": 1.5513594727558273e-05, + "loss": 1.4353, + "step": 3649 + }, + { + "epoch": 0.38, + "learning_rate": 1.5510540729561606e-05, + "loss": 1.4122, + "step": 3650 + }, + { + "epoch": 0.38, + "learning_rate": 1.550748599329407e-05, + "loss": 1.4077, + "step": 3651 + }, + { + "epoch": 0.38, + "learning_rate": 1.550443051916492e-05, + "loss": 1.4433, + "step": 3652 + }, + { + "epoch": 0.38, + "learning_rate": 1.5501374307583514e-05, + "loss": 1.54, + "step": 3653 + }, + { + "epoch": 0.38, + "learning_rate": 1.5498317358959302e-05, + "loss": 1.4522, + "step": 3654 + }, + { + "epoch": 0.38, + "learning_rate": 1.5495259673701842e-05, + "loss": 1.4175, + "step": 3655 + }, + { + "epoch": 0.38, + "learning_rate": 1.5492201252220777e-05, + "loss": 1.4637, + "step": 3656 + }, + { + "epoch": 0.38, + "learning_rate": 1.5489142094925863e-05, + "loss": 1.4701, + "step": 3657 + }, + { + "epoch": 0.38, + "learning_rate": 1.548608220222695e-05, + "loss": 1.4095, + "step": 3658 + }, + { + "epoch": 0.38, + "learning_rate": 1.548302157453398e-05, + "loss": 1.3903, + "step": 3659 + }, + { + "epoch": 0.38, + "learning_rate": 1.5479960212257002e-05, + "loss": 1.4062, + "step": 3660 + }, + { + "epoch": 0.38, + "learning_rate": 1.5476898115806157e-05, + "loss": 1.4706, + "step": 3661 + }, + { + "epoch": 0.38, + "learning_rate": 1.547383528559169e-05, + "loss": 1.4423, + "step": 3662 + }, + { + "epoch": 0.38, + "learning_rate": 1.547077172202394e-05, + "loss": 1.4418, + "step": 3663 + }, + { + "epoch": 0.38, + "learning_rate": 1.5467707425513347e-05, + "loss": 1.4553, + "step": 3664 + }, + { + "epoch": 0.38, + "learning_rate": 1.5464642396470443e-05, + "loss": 1.435, + "step": 3665 + }, + { + "epoch": 0.38, + "learning_rate": 1.5461576635305873e-05, + "loss": 1.4105, + "step": 3666 + }, + { + "epoch": 0.38, + "learning_rate": 1.5458510142430364e-05, + "loss": 1.4118, + "step": 3667 + }, + { + "epoch": 0.38, + "learning_rate": 1.5455442918254746e-05, + "loss": 1.4096, + "step": 3668 + }, + { + "epoch": 0.38, + "learning_rate": 1.545237496318995e-05, + "loss": 1.4248, + "step": 3669 + }, + { + "epoch": 0.38, + "learning_rate": 1.5449306277647003e-05, + "loss": 1.4591, + "step": 3670 + }, + { + "epoch": 0.38, + "learning_rate": 1.544623686203703e-05, + "loss": 1.4764, + "step": 3671 + }, + { + "epoch": 0.39, + "learning_rate": 1.5443166716771255e-05, + "loss": 1.4329, + "step": 3672 + }, + { + "epoch": 0.39, + "learning_rate": 1.5440095842260995e-05, + "loss": 1.4023, + "step": 3673 + }, + { + "epoch": 0.39, + "learning_rate": 1.5437024238917674e-05, + "loss": 1.3802, + "step": 3674 + }, + { + "epoch": 0.39, + "learning_rate": 1.5433951907152806e-05, + "loss": 1.4627, + "step": 3675 + }, + { + "epoch": 0.39, + "learning_rate": 1.5430878847378e-05, + "loss": 1.5164, + "step": 3676 + }, + { + "epoch": 0.39, + "learning_rate": 1.542780506000497e-05, + "loss": 1.3546, + "step": 3677 + }, + { + "epoch": 0.39, + "learning_rate": 1.542473054544553e-05, + "loss": 1.4415, + "step": 3678 + }, + { + "epoch": 0.39, + "learning_rate": 1.5421655304111573e-05, + "loss": 1.4093, + "step": 3679 + }, + { + "epoch": 0.39, + "learning_rate": 1.5418579336415114e-05, + "loss": 1.3943, + "step": 3680 + }, + { + "epoch": 0.39, + "learning_rate": 1.5415502642768252e-05, + "loss": 1.3659, + "step": 3681 + }, + { + "epoch": 0.39, + "learning_rate": 1.541242522358318e-05, + "loss": 1.4322, + "step": 3682 + }, + { + "epoch": 0.39, + "learning_rate": 1.5409347079272198e-05, + "loss": 1.4064, + "step": 3683 + }, + { + "epoch": 0.39, + "learning_rate": 1.5406268210247693e-05, + "loss": 1.4031, + "step": 3684 + }, + { + "epoch": 0.39, + "learning_rate": 1.540318861692216e-05, + "loss": 1.3449, + "step": 3685 + }, + { + "epoch": 0.39, + "learning_rate": 1.5400108299708182e-05, + "loss": 1.5536, + "step": 3686 + }, + { + "epoch": 0.39, + "learning_rate": 1.5397027259018442e-05, + "loss": 1.4106, + "step": 3687 + }, + { + "epoch": 0.39, + "learning_rate": 1.5393945495265722e-05, + "loss": 1.4309, + "step": 3688 + }, + { + "epoch": 0.39, + "learning_rate": 1.53908630088629e-05, + "loss": 1.3765, + "step": 3689 + }, + { + "epoch": 0.39, + "learning_rate": 1.5387779800222947e-05, + "loss": 1.3809, + "step": 3690 + }, + { + "epoch": 0.39, + "learning_rate": 1.5384695869758938e-05, + "loss": 1.4758, + "step": 3691 + }, + { + "epoch": 0.39, + "learning_rate": 1.5381611217884032e-05, + "loss": 1.4249, + "step": 3692 + }, + { + "epoch": 0.39, + "learning_rate": 1.5378525845011503e-05, + "loss": 1.4133, + "step": 3693 + }, + { + "epoch": 0.39, + "learning_rate": 1.5375439751554708e-05, + "loss": 1.418, + "step": 3694 + }, + { + "epoch": 0.39, + "learning_rate": 1.53723529379271e-05, + "loss": 1.441, + "step": 3695 + }, + { + "epoch": 0.39, + "learning_rate": 1.536926540454224e-05, + "loss": 1.3919, + "step": 3696 + }, + { + "epoch": 0.39, + "learning_rate": 1.5366177151813775e-05, + "loss": 1.3722, + "step": 3697 + }, + { + "epoch": 0.39, + "learning_rate": 1.536308818015545e-05, + "loss": 1.4727, + "step": 3698 + }, + { + "epoch": 0.39, + "learning_rate": 1.535999848998111e-05, + "loss": 1.442, + "step": 3699 + }, + { + "epoch": 0.39, + "learning_rate": 1.535690808170469e-05, + "loss": 1.3884, + "step": 3700 + }, + { + "epoch": 0.39, + "learning_rate": 1.535381695574023e-05, + "loss": 1.3226, + "step": 3701 + }, + { + "epoch": 0.39, + "learning_rate": 1.535072511250186e-05, + "loss": 1.4403, + "step": 3702 + }, + { + "epoch": 0.39, + "learning_rate": 1.5347632552403808e-05, + "loss": 1.4144, + "step": 3703 + }, + { + "epoch": 0.39, + "learning_rate": 1.5344539275860395e-05, + "loss": 1.3514, + "step": 3704 + }, + { + "epoch": 0.39, + "learning_rate": 1.5341445283286044e-05, + "loss": 1.519, + "step": 3705 + }, + { + "epoch": 0.39, + "learning_rate": 1.5338350575095268e-05, + "loss": 1.4251, + "step": 3706 + }, + { + "epoch": 0.39, + "learning_rate": 1.5335255151702685e-05, + "loss": 1.392, + "step": 3707 + }, + { + "epoch": 0.39, + "learning_rate": 1.533215901352299e-05, + "loss": 1.3838, + "step": 3708 + }, + { + "epoch": 0.39, + "learning_rate": 1.532906216097099e-05, + "loss": 1.444, + "step": 3709 + }, + { + "epoch": 0.39, + "learning_rate": 1.5325964594461594e-05, + "loss": 1.3459, + "step": 3710 + }, + { + "epoch": 0.39, + "learning_rate": 1.5322866314409783e-05, + "loss": 1.4155, + "step": 3711 + }, + { + "epoch": 0.39, + "learning_rate": 1.5319767321230657e-05, + "loss": 1.4057, + "step": 3712 + }, + { + "epoch": 0.39, + "learning_rate": 1.5316667615339392e-05, + "loss": 1.382, + "step": 3713 + }, + { + "epoch": 0.39, + "learning_rate": 1.5313567197151277e-05, + "loss": 1.3634, + "step": 3714 + }, + { + "epoch": 0.39, + "learning_rate": 1.5310466067081688e-05, + "loss": 1.3434, + "step": 3715 + }, + { + "epoch": 0.39, + "learning_rate": 1.530736422554609e-05, + "loss": 1.4553, + "step": 3716 + }, + { + "epoch": 0.39, + "learning_rate": 1.5304261672960055e-05, + "loss": 1.4193, + "step": 3717 + }, + { + "epoch": 0.39, + "learning_rate": 1.5301158409739242e-05, + "loss": 1.3955, + "step": 3718 + }, + { + "epoch": 0.39, + "learning_rate": 1.5298054436299413e-05, + "loss": 1.4592, + "step": 3719 + }, + { + "epoch": 0.39, + "learning_rate": 1.529494975305642e-05, + "loss": 1.738, + "step": 3720 + }, + { + "epoch": 0.39, + "learning_rate": 1.529184436042621e-05, + "loss": 1.438, + "step": 3721 + }, + { + "epoch": 0.39, + "learning_rate": 1.528873825882482e-05, + "loss": 1.3445, + "step": 3722 + }, + { + "epoch": 0.39, + "learning_rate": 1.5285631448668395e-05, + "loss": 1.4168, + "step": 3723 + }, + { + "epoch": 0.39, + "learning_rate": 1.528252393037317e-05, + "loss": 1.4088, + "step": 3724 + }, + { + "epoch": 0.39, + "learning_rate": 1.5279415704355468e-05, + "loss": 1.4484, + "step": 3725 + }, + { + "epoch": 0.39, + "learning_rate": 1.5276306771031708e-05, + "loss": 1.4706, + "step": 3726 + }, + { + "epoch": 0.39, + "learning_rate": 1.527319713081841e-05, + "loss": 1.3466, + "step": 3727 + }, + { + "epoch": 0.39, + "learning_rate": 1.5270086784132196e-05, + "loss": 1.427, + "step": 3728 + }, + { + "epoch": 0.39, + "learning_rate": 1.5266975731389754e-05, + "loss": 1.4596, + "step": 3729 + }, + { + "epoch": 0.39, + "learning_rate": 1.52638639730079e-05, + "loss": 1.405, + "step": 3730 + }, + { + "epoch": 0.39, + "learning_rate": 1.5260751509403518e-05, + "loss": 1.4572, + "step": 3731 + }, + { + "epoch": 0.39, + "learning_rate": 1.5257638340993608e-05, + "loss": 1.3827, + "step": 3732 + }, + { + "epoch": 0.39, + "learning_rate": 1.5254524468195251e-05, + "loss": 1.3712, + "step": 3733 + }, + { + "epoch": 0.39, + "learning_rate": 1.5251409891425626e-05, + "loss": 1.4541, + "step": 3734 + }, + { + "epoch": 0.39, + "learning_rate": 1.5248294611102006e-05, + "loss": 1.5279, + "step": 3735 + }, + { + "epoch": 0.39, + "learning_rate": 1.5245178627641759e-05, + "loss": 1.3722, + "step": 3736 + }, + { + "epoch": 0.39, + "learning_rate": 1.5242061941462348e-05, + "loss": 1.5158, + "step": 3737 + }, + { + "epoch": 0.39, + "learning_rate": 1.523894455298132e-05, + "loss": 1.4274, + "step": 3738 + }, + { + "epoch": 0.39, + "learning_rate": 1.5235826462616338e-05, + "loss": 1.4543, + "step": 3739 + }, + { + "epoch": 0.39, + "learning_rate": 1.5232707670785144e-05, + "loss": 1.5011, + "step": 3740 + }, + { + "epoch": 0.39, + "learning_rate": 1.5229588177905568e-05, + "loss": 1.24, + "step": 3741 + }, + { + "epoch": 0.39, + "learning_rate": 1.5226467984395544e-05, + "loss": 1.4253, + "step": 3742 + }, + { + "epoch": 0.39, + "learning_rate": 1.5223347090673102e-05, + "loss": 1.3736, + "step": 3743 + }, + { + "epoch": 0.39, + "learning_rate": 1.522022549715636e-05, + "loss": 1.4587, + "step": 3744 + }, + { + "epoch": 0.39, + "learning_rate": 1.521710320426353e-05, + "loss": 1.5024, + "step": 3745 + }, + { + "epoch": 0.39, + "learning_rate": 1.521398021241292e-05, + "loss": 1.427, + "step": 3746 + }, + { + "epoch": 0.39, + "learning_rate": 1.5210856522022929e-05, + "loss": 1.3387, + "step": 3747 + }, + { + "epoch": 0.39, + "learning_rate": 1.5207732133512055e-05, + "loss": 1.3819, + "step": 3748 + }, + { + "epoch": 0.39, + "learning_rate": 1.5204607047298883e-05, + "loss": 1.4571, + "step": 3749 + }, + { + "epoch": 0.39, + "learning_rate": 1.5201481263802094e-05, + "loss": 1.3592, + "step": 3750 + }, + { + "epoch": 0.39, + "learning_rate": 1.5198354783440464e-05, + "loss": 1.3912, + "step": 3751 + }, + { + "epoch": 0.39, + "learning_rate": 1.519522760663286e-05, + "loss": 1.4986, + "step": 3752 + }, + { + "epoch": 0.39, + "learning_rate": 1.5192099733798243e-05, + "loss": 1.4106, + "step": 3753 + }, + { + "epoch": 0.39, + "learning_rate": 1.5188971165355667e-05, + "loss": 1.4145, + "step": 3754 + }, + { + "epoch": 0.39, + "learning_rate": 1.5185841901724282e-05, + "loss": 1.3915, + "step": 3755 + }, + { + "epoch": 0.39, + "learning_rate": 1.5182711943323329e-05, + "loss": 1.4014, + "step": 3756 + }, + { + "epoch": 0.39, + "learning_rate": 1.5179581290572141e-05, + "loss": 1.3651, + "step": 3757 + }, + { + "epoch": 0.39, + "learning_rate": 1.5176449943890147e-05, + "loss": 1.3653, + "step": 3758 + }, + { + "epoch": 0.39, + "learning_rate": 1.5173317903696862e-05, + "loss": 1.4486, + "step": 3759 + }, + { + "epoch": 0.39, + "learning_rate": 1.5170185170411906e-05, + "loss": 1.4459, + "step": 3760 + }, + { + "epoch": 0.39, + "learning_rate": 1.5167051744454977e-05, + "loss": 1.4215, + "step": 3761 + }, + { + "epoch": 0.39, + "learning_rate": 1.5163917626245877e-05, + "loss": 1.4379, + "step": 3762 + }, + { + "epoch": 0.39, + "learning_rate": 1.51607828162045e-05, + "loss": 1.4147, + "step": 3763 + }, + { + "epoch": 0.39, + "learning_rate": 1.5157647314750827e-05, + "loss": 1.4011, + "step": 3764 + }, + { + "epoch": 0.39, + "learning_rate": 1.5154511122304936e-05, + "loss": 1.4309, + "step": 3765 + }, + { + "epoch": 0.39, + "learning_rate": 1.5151374239286993e-05, + "loss": 1.4382, + "step": 3766 + }, + { + "epoch": 0.4, + "learning_rate": 1.5148236666117266e-05, + "loss": 1.405, + "step": 3767 + }, + { + "epoch": 0.4, + "learning_rate": 1.5145098403216104e-05, + "loss": 1.4223, + "step": 3768 + }, + { + "epoch": 0.4, + "learning_rate": 1.5141959451003951e-05, + "loss": 1.4084, + "step": 3769 + }, + { + "epoch": 0.4, + "learning_rate": 1.5138819809901356e-05, + "loss": 1.4063, + "step": 3770 + }, + { + "epoch": 0.4, + "learning_rate": 1.513567948032894e-05, + "loss": 1.3299, + "step": 3771 + }, + { + "epoch": 0.4, + "learning_rate": 1.5132538462707431e-05, + "loss": 1.3901, + "step": 3772 + }, + { + "epoch": 0.4, + "learning_rate": 1.5129396757457646e-05, + "loss": 1.4249, + "step": 3773 + }, + { + "epoch": 0.4, + "learning_rate": 1.512625436500049e-05, + "loss": 1.4087, + "step": 3774 + }, + { + "epoch": 0.4, + "learning_rate": 1.5123111285756964e-05, + "loss": 1.3521, + "step": 3775 + }, + { + "epoch": 0.4, + "learning_rate": 1.5119967520148163e-05, + "loss": 1.4097, + "step": 3776 + }, + { + "epoch": 0.4, + "learning_rate": 1.5116823068595261e-05, + "loss": 1.4871, + "step": 3777 + }, + { + "epoch": 0.4, + "learning_rate": 1.5113677931519543e-05, + "loss": 1.44, + "step": 3778 + }, + { + "epoch": 0.4, + "learning_rate": 1.5110532109342377e-05, + "loss": 1.4518, + "step": 3779 + }, + { + "epoch": 0.4, + "learning_rate": 1.5107385602485214e-05, + "loss": 1.3961, + "step": 3780 + }, + { + "epoch": 0.4, + "learning_rate": 1.5104238411369614e-05, + "loss": 1.4341, + "step": 3781 + }, + { + "epoch": 0.4, + "eval_loss": 1.4642821550369263, + "eval_runtime": 77.3595, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 3781 + }, + { + "epoch": 0.4, + "learning_rate": 1.5101090536417218e-05, + "loss": 1.403, + "step": 3782 + }, + { + "epoch": 0.4, + "learning_rate": 1.5097941978049754e-05, + "loss": 1.4103, + "step": 3783 + }, + { + "epoch": 0.4, + "learning_rate": 1.5094792736689052e-05, + "loss": 1.3478, + "step": 3784 + }, + { + "epoch": 0.4, + "learning_rate": 1.5091642812757035e-05, + "loss": 1.4134, + "step": 3785 + }, + { + "epoch": 0.4, + "learning_rate": 1.5088492206675701e-05, + "loss": 1.4134, + "step": 3786 + }, + { + "epoch": 0.4, + "learning_rate": 1.5085340918867162e-05, + "loss": 1.1494, + "step": 3787 + }, + { + "epoch": 0.4, + "learning_rate": 1.5082188949753598e-05, + "loss": 1.2385, + "step": 3788 + }, + { + "epoch": 0.4, + "learning_rate": 1.5079036299757299e-05, + "loss": 1.4258, + "step": 3789 + }, + { + "epoch": 0.4, + "learning_rate": 1.5075882969300639e-05, + "loss": 1.3781, + "step": 3790 + }, + { + "epoch": 0.4, + "learning_rate": 1.507272895880608e-05, + "loss": 1.5096, + "step": 3791 + }, + { + "epoch": 0.4, + "learning_rate": 1.5069574268696179e-05, + "loss": 1.366, + "step": 3792 + }, + { + "epoch": 0.4, + "learning_rate": 1.5066418899393584e-05, + "loss": 1.3792, + "step": 3793 + }, + { + "epoch": 0.4, + "learning_rate": 1.506326285132104e-05, + "loss": 1.4987, + "step": 3794 + }, + { + "epoch": 0.4, + "learning_rate": 1.5060106124901364e-05, + "loss": 1.445, + "step": 3795 + }, + { + "epoch": 0.4, + "learning_rate": 1.5056948720557482e-05, + "loss": 1.5071, + "step": 3796 + }, + { + "epoch": 0.4, + "learning_rate": 1.505379063871241e-05, + "loss": 1.4029, + "step": 3797 + }, + { + "epoch": 0.4, + "learning_rate": 1.5050631879789244e-05, + "loss": 1.5263, + "step": 3798 + }, + { + "epoch": 0.4, + "learning_rate": 1.5047472444211175e-05, + "loss": 1.3906, + "step": 3799 + }, + { + "epoch": 0.4, + "learning_rate": 1.5044312332401494e-05, + "loss": 1.7352, + "step": 3800 + }, + { + "epoch": 0.4, + "learning_rate": 1.5041151544783565e-05, + "loss": 1.3946, + "step": 3801 + }, + { + "epoch": 0.4, + "learning_rate": 1.5037990081780862e-05, + "loss": 1.3592, + "step": 3802 + }, + { + "epoch": 0.4, + "learning_rate": 1.503482794381693e-05, + "loss": 1.3991, + "step": 3803 + }, + { + "epoch": 0.4, + "learning_rate": 1.5031665131315423e-05, + "loss": 1.4271, + "step": 3804 + }, + { + "epoch": 0.4, + "learning_rate": 1.502850164470007e-05, + "loss": 1.4305, + "step": 3805 + }, + { + "epoch": 0.4, + "learning_rate": 1.5025337484394701e-05, + "loss": 1.4116, + "step": 3806 + }, + { + "epoch": 0.4, + "learning_rate": 1.5022172650823232e-05, + "loss": 1.4242, + "step": 3807 + }, + { + "epoch": 0.4, + "learning_rate": 1.5019007144409667e-05, + "loss": 1.4427, + "step": 3808 + }, + { + "epoch": 0.4, + "learning_rate": 1.5015840965578106e-05, + "loss": 1.3705, + "step": 3809 + }, + { + "epoch": 0.4, + "learning_rate": 1.5012674114752732e-05, + "loss": 1.4498, + "step": 3810 + }, + { + "epoch": 0.4, + "learning_rate": 1.5009506592357822e-05, + "loss": 1.489, + "step": 3811 + }, + { + "epoch": 0.4, + "learning_rate": 1.5006338398817746e-05, + "loss": 1.4801, + "step": 3812 + }, + { + "epoch": 0.4, + "learning_rate": 1.5003169534556956e-05, + "loss": 1.3468, + "step": 3813 + }, + { + "epoch": 0.4, + "learning_rate": 1.5000000000000002e-05, + "loss": 1.4211, + "step": 3814 + }, + { + "epoch": 0.4, + "learning_rate": 1.4996829795571518e-05, + "loss": 1.4683, + "step": 3815 + }, + { + "epoch": 0.4, + "learning_rate": 1.499365892169623e-05, + "loss": 1.4441, + "step": 3816 + }, + { + "epoch": 0.4, + "learning_rate": 1.4990487378798958e-05, + "loss": 1.4368, + "step": 3817 + }, + { + "epoch": 0.4, + "learning_rate": 1.4987315167304602e-05, + "loss": 1.4097, + "step": 3818 + }, + { + "epoch": 0.4, + "learning_rate": 1.4984142287638155e-05, + "loss": 1.4238, + "step": 3819 + }, + { + "epoch": 0.4, + "learning_rate": 1.4980968740224708e-05, + "loss": 1.497, + "step": 3820 + }, + { + "epoch": 0.4, + "learning_rate": 1.4977794525489433e-05, + "loss": 1.3989, + "step": 3821 + }, + { + "epoch": 0.4, + "learning_rate": 1.4974619643857588e-05, + "loss": 1.4415, + "step": 3822 + }, + { + "epoch": 0.4, + "learning_rate": 1.4971444095754533e-05, + "loss": 1.3931, + "step": 3823 + }, + { + "epoch": 0.4, + "learning_rate": 1.4968267881605705e-05, + "loss": 1.3426, + "step": 3824 + }, + { + "epoch": 0.4, + "learning_rate": 1.4965091001836636e-05, + "loss": 1.644, + "step": 3825 + }, + { + "epoch": 0.4, + "learning_rate": 1.4961913456872945e-05, + "loss": 1.3903, + "step": 3826 + }, + { + "epoch": 0.4, + "learning_rate": 1.4958735247140345e-05, + "loss": 1.3764, + "step": 3827 + }, + { + "epoch": 0.4, + "learning_rate": 1.4955556373064632e-05, + "loss": 1.5484, + "step": 3828 + }, + { + "epoch": 0.4, + "learning_rate": 1.4952376835071696e-05, + "loss": 1.5696, + "step": 3829 + }, + { + "epoch": 0.4, + "learning_rate": 1.4949196633587509e-05, + "loss": 1.3844, + "step": 3830 + }, + { + "epoch": 0.4, + "learning_rate": 1.494601576903814e-05, + "loss": 1.3868, + "step": 3831 + }, + { + "epoch": 0.4, + "learning_rate": 1.4942834241849741e-05, + "loss": 1.4229, + "step": 3832 + }, + { + "epoch": 0.4, + "learning_rate": 1.4939652052448557e-05, + "loss": 1.4062, + "step": 3833 + }, + { + "epoch": 0.4, + "learning_rate": 1.4936469201260915e-05, + "loss": 1.3955, + "step": 3834 + }, + { + "epoch": 0.4, + "learning_rate": 1.4933285688713239e-05, + "loss": 1.3959, + "step": 3835 + }, + { + "epoch": 0.4, + "learning_rate": 1.4930101515232038e-05, + "loss": 1.4652, + "step": 3836 + }, + { + "epoch": 0.4, + "learning_rate": 1.4926916681243913e-05, + "loss": 1.5253, + "step": 3837 + }, + { + "epoch": 0.4, + "learning_rate": 1.4923731187175539e-05, + "loss": 1.4694, + "step": 3838 + }, + { + "epoch": 0.4, + "learning_rate": 1.4920545033453702e-05, + "loss": 1.3859, + "step": 3839 + }, + { + "epoch": 0.4, + "learning_rate": 1.4917358220505259e-05, + "loss": 1.4157, + "step": 3840 + }, + { + "epoch": 0.4, + "learning_rate": 1.4914170748757159e-05, + "loss": 1.4491, + "step": 3841 + }, + { + "epoch": 0.4, + "learning_rate": 1.4910982618636445e-05, + "loss": 1.4464, + "step": 3842 + }, + { + "epoch": 0.4, + "learning_rate": 1.4907793830570246e-05, + "loss": 1.3771, + "step": 3843 + }, + { + "epoch": 0.4, + "learning_rate": 1.4904604384985775e-05, + "loss": 1.3673, + "step": 3844 + }, + { + "epoch": 0.4, + "learning_rate": 1.4901414282310334e-05, + "loss": 1.4429, + "step": 3845 + }, + { + "epoch": 0.4, + "learning_rate": 1.4898223522971318e-05, + "loss": 1.4905, + "step": 3846 + }, + { + "epoch": 0.4, + "learning_rate": 1.4895032107396205e-05, + "loss": 1.4039, + "step": 3847 + }, + { + "epoch": 0.4, + "learning_rate": 1.4891840036012566e-05, + "loss": 1.4082, + "step": 3848 + }, + { + "epoch": 0.4, + "learning_rate": 1.4888647309248052e-05, + "loss": 1.3643, + "step": 3849 + }, + { + "epoch": 0.4, + "learning_rate": 1.4885453927530408e-05, + "loss": 1.3116, + "step": 3850 + }, + { + "epoch": 0.4, + "learning_rate": 1.4882259891287467e-05, + "loss": 1.4278, + "step": 3851 + }, + { + "epoch": 0.4, + "learning_rate": 1.4879065200947148e-05, + "loss": 1.3712, + "step": 3852 + }, + { + "epoch": 0.4, + "learning_rate": 1.4875869856937449e-05, + "loss": 1.387, + "step": 3853 + }, + { + "epoch": 0.4, + "learning_rate": 1.4872673859686475e-05, + "loss": 1.5053, + "step": 3854 + }, + { + "epoch": 0.4, + "learning_rate": 1.4869477209622404e-05, + "loss": 1.4427, + "step": 3855 + }, + { + "epoch": 0.4, + "learning_rate": 1.4866279907173502e-05, + "loss": 1.3404, + "step": 3856 + }, + { + "epoch": 0.4, + "learning_rate": 1.4863081952768126e-05, + "loss": 1.3126, + "step": 3857 + }, + { + "epoch": 0.4, + "learning_rate": 1.4859883346834725e-05, + "loss": 1.4588, + "step": 3858 + }, + { + "epoch": 0.4, + "learning_rate": 1.4856684089801822e-05, + "loss": 1.408, + "step": 3859 + }, + { + "epoch": 0.4, + "learning_rate": 1.4853484182098044e-05, + "loss": 1.4356, + "step": 3860 + }, + { + "epoch": 0.4, + "learning_rate": 1.4850283624152088e-05, + "loss": 1.3768, + "step": 3861 + }, + { + "epoch": 0.4, + "learning_rate": 1.4847082416392753e-05, + "loss": 1.4563, + "step": 3862 + }, + { + "epoch": 0.41, + "learning_rate": 1.4843880559248915e-05, + "loss": 1.3648, + "step": 3863 + }, + { + "epoch": 0.41, + "learning_rate": 1.4840678053149542e-05, + "loss": 1.4146, + "step": 3864 + }, + { + "epoch": 0.41, + "learning_rate": 1.4837474898523686e-05, + "loss": 1.4423, + "step": 3865 + }, + { + "epoch": 0.41, + "learning_rate": 1.4834271095800487e-05, + "loss": 1.3351, + "step": 3866 + }, + { + "epoch": 0.41, + "learning_rate": 1.4831066645409178e-05, + "loss": 1.4534, + "step": 3867 + }, + { + "epoch": 0.41, + "learning_rate": 1.4827861547779066e-05, + "loss": 1.4763, + "step": 3868 + }, + { + "epoch": 0.41, + "learning_rate": 1.4824655803339553e-05, + "loss": 1.4019, + "step": 3869 + }, + { + "epoch": 0.41, + "learning_rate": 1.4821449412520132e-05, + "loss": 1.4223, + "step": 3870 + }, + { + "epoch": 0.41, + "learning_rate": 1.4818242375750371e-05, + "loss": 1.4065, + "step": 3871 + }, + { + "epoch": 0.41, + "learning_rate": 1.481503469345993e-05, + "loss": 1.587, + "step": 3872 + }, + { + "epoch": 0.41, + "learning_rate": 1.4811826366078562e-05, + "loss": 1.3746, + "step": 3873 + }, + { + "epoch": 0.41, + "learning_rate": 1.4808617394036096e-05, + "loss": 1.3425, + "step": 3874 + }, + { + "epoch": 0.41, + "learning_rate": 1.480540777776245e-05, + "loss": 0.6637, + "step": 3875 + }, + { + "epoch": 0.41, + "learning_rate": 1.4802197517687634e-05, + "loss": 1.3366, + "step": 3876 + }, + { + "epoch": 0.41, + "learning_rate": 1.479898661424174e-05, + "loss": 1.4033, + "step": 3877 + }, + { + "epoch": 0.41, + "learning_rate": 1.4795775067854947e-05, + "loss": 1.4005, + "step": 3878 + }, + { + "epoch": 0.41, + "learning_rate": 1.4792562878957516e-05, + "loss": 1.3651, + "step": 3879 + }, + { + "epoch": 0.41, + "learning_rate": 1.47893500479798e-05, + "loss": 1.4185, + "step": 3880 + }, + { + "epoch": 0.41, + "learning_rate": 1.4786136575352236e-05, + "loss": 1.4394, + "step": 3881 + }, + { + "epoch": 0.41, + "learning_rate": 1.478292246150535e-05, + "loss": 1.7243, + "step": 3882 + }, + { + "epoch": 0.41, + "learning_rate": 1.4779707706869744e-05, + "loss": 1.3574, + "step": 3883 + }, + { + "epoch": 0.41, + "learning_rate": 1.4776492311876116e-05, + "loss": 1.4031, + "step": 3884 + }, + { + "epoch": 0.41, + "learning_rate": 1.4773276276955248e-05, + "loss": 1.4351, + "step": 3885 + }, + { + "epoch": 0.41, + "learning_rate": 1.4770059602538002e-05, + "loss": 1.3922, + "step": 3886 + }, + { + "epoch": 0.41, + "learning_rate": 1.4766842289055333e-05, + "loss": 1.3374, + "step": 3887 + }, + { + "epoch": 0.41, + "learning_rate": 1.4763624336938278e-05, + "loss": 1.428, + "step": 3888 + }, + { + "epoch": 0.41, + "learning_rate": 1.476040574661796e-05, + "loss": 1.6087, + "step": 3889 + }, + { + "epoch": 0.41, + "learning_rate": 1.4757186518525586e-05, + "loss": 1.4054, + "step": 3890 + }, + { + "epoch": 0.41, + "learning_rate": 1.4753966653092447e-05, + "loss": 1.2595, + "step": 3891 + }, + { + "epoch": 0.41, + "learning_rate": 1.475074615074993e-05, + "loss": 1.4052, + "step": 3892 + }, + { + "epoch": 0.41, + "learning_rate": 1.4747525011929492e-05, + "loss": 1.4296, + "step": 3893 + }, + { + "epoch": 0.41, + "learning_rate": 1.4744303237062689e-05, + "loss": 1.3718, + "step": 3894 + }, + { + "epoch": 0.41, + "learning_rate": 1.4741080826581151e-05, + "loss": 1.4498, + "step": 3895 + }, + { + "epoch": 0.41, + "learning_rate": 1.4737857780916602e-05, + "loss": 1.4029, + "step": 3896 + }, + { + "epoch": 0.41, + "learning_rate": 1.4734634100500846e-05, + "loss": 1.4136, + "step": 3897 + }, + { + "epoch": 0.41, + "learning_rate": 1.4731409785765774e-05, + "loss": 1.348, + "step": 3898 + }, + { + "epoch": 0.41, + "learning_rate": 1.4728184837143355e-05, + "loss": 1.3407, + "step": 3899 + }, + { + "epoch": 0.41, + "learning_rate": 1.472495925506566e-05, + "loss": 1.3737, + "step": 3900 + }, + { + "epoch": 0.41, + "learning_rate": 1.4721733039964826e-05, + "loss": 2.2305, + "step": 3901 + }, + { + "epoch": 0.41, + "learning_rate": 1.4718506192273087e-05, + "loss": 1.4506, + "step": 3902 + }, + { + "epoch": 0.41, + "learning_rate": 1.4715278712422754e-05, + "loss": 1.3657, + "step": 3903 + }, + { + "epoch": 0.41, + "learning_rate": 1.471205060084623e-05, + "loss": 1.4644, + "step": 3904 + }, + { + "epoch": 0.41, + "learning_rate": 1.4708821857976001e-05, + "loss": 1.4823, + "step": 3905 + }, + { + "epoch": 0.41, + "learning_rate": 1.4705592484244628e-05, + "loss": 1.3392, + "step": 3906 + }, + { + "epoch": 0.41, + "learning_rate": 1.4702362480084769e-05, + "loss": 1.3302, + "step": 3907 + }, + { + "epoch": 0.41, + "learning_rate": 1.4699131845929163e-05, + "loss": 1.8952, + "step": 3908 + }, + { + "epoch": 0.41, + "learning_rate": 1.469590058221063e-05, + "loss": 1.4982, + "step": 3909 + }, + { + "epoch": 0.41, + "learning_rate": 1.4692668689362074e-05, + "loss": 1.407, + "step": 3910 + }, + { + "epoch": 0.41, + "learning_rate": 1.4689436167816489e-05, + "loss": 1.3911, + "step": 3911 + }, + { + "epoch": 0.41, + "learning_rate": 1.4686203018006948e-05, + "loss": 1.3421, + "step": 3912 + }, + { + "epoch": 0.41, + "learning_rate": 1.4682969240366612e-05, + "loss": 1.4627, + "step": 3913 + }, + { + "epoch": 0.41, + "learning_rate": 1.4679734835328718e-05, + "loss": 1.394, + "step": 3914 + }, + { + "epoch": 0.41, + "learning_rate": 1.4676499803326603e-05, + "loss": 1.4484, + "step": 3915 + }, + { + "epoch": 0.41, + "learning_rate": 1.4673264144793673e-05, + "loss": 1.4665, + "step": 3916 + }, + { + "epoch": 0.41, + "learning_rate": 1.4670027860163422e-05, + "loss": 1.3191, + "step": 3917 + }, + { + "epoch": 0.41, + "learning_rate": 1.466679094986943e-05, + "loss": 1.4748, + "step": 3918 + }, + { + "epoch": 0.41, + "learning_rate": 1.4663553414345361e-05, + "loss": 1.2467, + "step": 3919 + }, + { + "epoch": 0.41, + "learning_rate": 1.466031525402496e-05, + "loss": 1.4279, + "step": 3920 + }, + { + "epoch": 0.41, + "learning_rate": 1.4657076469342059e-05, + "loss": 1.3822, + "step": 3921 + }, + { + "epoch": 0.41, + "learning_rate": 1.4653837060730566e-05, + "loss": 1.3659, + "step": 3922 + }, + { + "epoch": 0.41, + "learning_rate": 1.465059702862449e-05, + "loss": 1.3663, + "step": 3923 + }, + { + "epoch": 0.41, + "learning_rate": 1.4647356373457902e-05, + "loss": 1.4371, + "step": 3924 + }, + { + "epoch": 0.41, + "learning_rate": 1.4644115095664972e-05, + "loss": 1.3473, + "step": 3925 + }, + { + "epoch": 0.41, + "learning_rate": 1.4640873195679944e-05, + "loss": 1.4797, + "step": 3926 + }, + { + "epoch": 0.41, + "learning_rate": 1.463763067393715e-05, + "loss": 1.3973, + "step": 3927 + }, + { + "epoch": 0.41, + "learning_rate": 1.4634387530871008e-05, + "loss": 1.3899, + "step": 3928 + }, + { + "epoch": 0.41, + "learning_rate": 1.4631143766916015e-05, + "loss": 1.3828, + "step": 3929 + }, + { + "epoch": 0.41, + "learning_rate": 1.4627899382506745e-05, + "loss": 1.4569, + "step": 3930 + }, + { + "epoch": 0.41, + "learning_rate": 1.4624654378077872e-05, + "loss": 1.4011, + "step": 3931 + }, + { + "epoch": 0.41, + "learning_rate": 1.462140875406414e-05, + "loss": 1.3859, + "step": 3932 + }, + { + "epoch": 0.41, + "learning_rate": 1.4618162510900376e-05, + "loss": 1.4518, + "step": 3933 + }, + { + "epoch": 0.41, + "learning_rate": 1.4614915649021493e-05, + "loss": 1.4399, + "step": 3934 + }, + { + "epoch": 0.41, + "learning_rate": 1.4611668168862495e-05, + "loss": 1.4034, + "step": 3935 + }, + { + "epoch": 0.41, + "learning_rate": 1.4608420070858452e-05, + "loss": 1.3919, + "step": 3936 + }, + { + "epoch": 0.41, + "learning_rate": 1.4605171355444528e-05, + "loss": 1.391, + "step": 3937 + }, + { + "epoch": 0.41, + "learning_rate": 1.460192202305597e-05, + "loss": 1.3717, + "step": 3938 + }, + { + "epoch": 0.41, + "learning_rate": 1.4598672074128103e-05, + "loss": 1.4351, + "step": 3939 + }, + { + "epoch": 0.41, + "learning_rate": 1.4595421509096339e-05, + "loss": 1.4202, + "step": 3940 + }, + { + "epoch": 0.41, + "learning_rate": 1.4592170328396165e-05, + "loss": 1.3559, + "step": 3941 + }, + { + "epoch": 0.41, + "learning_rate": 1.458891853246316e-05, + "loss": 1.5878, + "step": 3942 + }, + { + "epoch": 0.41, + "learning_rate": 1.4585666121732982e-05, + "loss": 1.3818, + "step": 3943 + }, + { + "epoch": 0.41, + "learning_rate": 1.4582413096641369e-05, + "loss": 1.4009, + "step": 3944 + }, + { + "epoch": 0.41, + "learning_rate": 1.457915945762414e-05, + "loss": 1.3937, + "step": 3945 + }, + { + "epoch": 0.41, + "learning_rate": 1.4575905205117203e-05, + "loss": 1.381, + "step": 3946 + }, + { + "epoch": 0.41, + "learning_rate": 1.457265033955654e-05, + "loss": 1.3844, + "step": 3947 + }, + { + "epoch": 0.41, + "learning_rate": 1.4569394861378226e-05, + "loss": 1.4059, + "step": 3948 + }, + { + "epoch": 0.41, + "learning_rate": 1.4566138771018403e-05, + "loss": 1.3698, + "step": 3949 + }, + { + "epoch": 0.41, + "learning_rate": 1.4562882068913311e-05, + "loss": 1.4253, + "step": 3950 + }, + { + "epoch": 0.41, + "learning_rate": 1.455962475549926e-05, + "loss": 1.4284, + "step": 3951 + }, + { + "epoch": 0.41, + "learning_rate": 1.4556366831212647e-05, + "loss": 1.4279, + "step": 3952 + }, + { + "epoch": 0.41, + "learning_rate": 1.4553108296489951e-05, + "loss": 1.3072, + "step": 3953 + }, + { + "epoch": 0.41, + "learning_rate": 1.4549849151767731e-05, + "loss": 1.4175, + "step": 3954 + }, + { + "epoch": 0.41, + "learning_rate": 1.4546589397482632e-05, + "loss": 1.5042, + "step": 3955 + }, + { + "epoch": 0.41, + "learning_rate": 1.4543329034071371e-05, + "loss": 1.4363, + "step": 3956 + }, + { + "epoch": 0.41, + "learning_rate": 1.454006806197076e-05, + "loss": 1.4111, + "step": 3957 + }, + { + "epoch": 0.42, + "learning_rate": 1.453680648161768e-05, + "loss": 1.3817, + "step": 3958 + }, + { + "epoch": 0.42, + "learning_rate": 1.45335442934491e-05, + "loss": 1.4689, + "step": 3959 + }, + { + "epoch": 0.42, + "learning_rate": 1.4530281497902072e-05, + "loss": 1.4164, + "step": 3960 + }, + { + "epoch": 0.42, + "learning_rate": 1.4527018095413726e-05, + "loss": 1.3943, + "step": 3961 + }, + { + "epoch": 0.42, + "learning_rate": 1.4523754086421271e-05, + "loss": 1.3851, + "step": 3962 + }, + { + "epoch": 0.42, + "learning_rate": 1.4520489471362003e-05, + "loss": 1.3907, + "step": 3963 + }, + { + "epoch": 0.42, + "learning_rate": 1.4517224250673297e-05, + "loss": 1.2877, + "step": 3964 + }, + { + "epoch": 0.42, + "learning_rate": 1.4513958424792605e-05, + "loss": 1.4696, + "step": 3965 + }, + { + "epoch": 0.42, + "learning_rate": 1.4510691994157471e-05, + "loss": 1.3785, + "step": 3966 + }, + { + "epoch": 0.42, + "learning_rate": 1.4507424959205505e-05, + "loss": 1.3652, + "step": 3967 + }, + { + "epoch": 0.42, + "learning_rate": 1.4504157320374408e-05, + "loss": 1.4198, + "step": 3968 + }, + { + "epoch": 0.42, + "learning_rate": 1.4500889078101962e-05, + "loss": 1.3476, + "step": 3969 + }, + { + "epoch": 0.42, + "learning_rate": 1.4497620232826028e-05, + "loss": 1.4356, + "step": 3970 + }, + { + "epoch": 0.42, + "learning_rate": 1.4494350784984543e-05, + "loss": 1.4993, + "step": 3971 + }, + { + "epoch": 0.42, + "learning_rate": 1.4491080735015533e-05, + "loss": 1.4022, + "step": 3972 + }, + { + "epoch": 0.42, + "learning_rate": 1.44878100833571e-05, + "loss": 1.4074, + "step": 3973 + }, + { + "epoch": 0.42, + "learning_rate": 1.4484538830447423e-05, + "loss": 1.412, + "step": 3974 + }, + { + "epoch": 0.42, + "learning_rate": 1.4481266976724772e-05, + "loss": 1.3872, + "step": 3975 + }, + { + "epoch": 0.42, + "learning_rate": 1.4477994522627485e-05, + "loss": 1.4575, + "step": 3976 + }, + { + "epoch": 0.42, + "learning_rate": 1.4474721468593995e-05, + "loss": 1.3768, + "step": 3977 + }, + { + "epoch": 0.42, + "learning_rate": 1.44714478150628e-05, + "loss": 1.4173, + "step": 3978 + }, + { + "epoch": 0.42, + "learning_rate": 1.4468173562472489e-05, + "loss": 1.3896, + "step": 3979 + }, + { + "epoch": 0.42, + "learning_rate": 1.4464898711261725e-05, + "loss": 1.4535, + "step": 3980 + }, + { + "epoch": 0.42, + "eval_loss": 1.4580057859420776, + "eval_runtime": 77.4537, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 3980 + }, + { + "epoch": 0.42, + "learning_rate": 1.4461623261869258e-05, + "loss": 1.4046, + "step": 3981 + }, + { + "epoch": 0.42, + "learning_rate": 1.445834721473391e-05, + "loss": 1.37, + "step": 3982 + }, + { + "epoch": 0.42, + "learning_rate": 1.4455070570294588e-05, + "loss": 1.4566, + "step": 3983 + }, + { + "epoch": 0.42, + "learning_rate": 1.445179332899028e-05, + "loss": 1.4513, + "step": 3984 + }, + { + "epoch": 0.42, + "learning_rate": 1.4448515491260051e-05, + "loss": 1.3893, + "step": 3985 + }, + { + "epoch": 0.42, + "learning_rate": 1.4445237057543047e-05, + "loss": 1.3955, + "step": 3986 + }, + { + "epoch": 0.42, + "learning_rate": 1.4441958028278493e-05, + "loss": 1.4861, + "step": 3987 + }, + { + "epoch": 0.42, + "learning_rate": 1.4438678403905697e-05, + "loss": 1.4601, + "step": 3988 + }, + { + "epoch": 0.42, + "learning_rate": 1.4435398184864043e-05, + "loss": 1.398, + "step": 3989 + }, + { + "epoch": 0.42, + "learning_rate": 1.4432117371592995e-05, + "loss": 1.4392, + "step": 3990 + }, + { + "epoch": 0.42, + "learning_rate": 1.4428835964532098e-05, + "loss": 1.3772, + "step": 3991 + }, + { + "epoch": 0.42, + "learning_rate": 1.4425553964120979e-05, + "loss": 1.4241, + "step": 3992 + }, + { + "epoch": 0.42, + "learning_rate": 1.4422271370799338e-05, + "loss": 1.3237, + "step": 3993 + }, + { + "epoch": 0.42, + "learning_rate": 1.4418988185006964e-05, + "loss": 1.3813, + "step": 3994 + }, + { + "epoch": 0.42, + "learning_rate": 1.4415704407183709e-05, + "loss": 1.6139, + "step": 3995 + }, + { + "epoch": 0.42, + "learning_rate": 1.4412420037769525e-05, + "loss": 1.4431, + "step": 3996 + }, + { + "epoch": 0.42, + "learning_rate": 1.440913507720443e-05, + "loss": 1.3862, + "step": 3997 + }, + { + "epoch": 0.42, + "learning_rate": 1.4405849525928523e-05, + "loss": 1.3895, + "step": 3998 + }, + { + "epoch": 0.42, + "learning_rate": 1.4402563384381981e-05, + "loss": 1.4068, + "step": 3999 + }, + { + "epoch": 0.42, + "learning_rate": 1.4399276653005072e-05, + "loss": 1.4501, + "step": 4000 + }, + { + "epoch": 0.42, + "learning_rate": 1.4395989332238124e-05, + "loss": 1.3165, + "step": 4001 + }, + { + "epoch": 0.42, + "learning_rate": 1.4392701422521555e-05, + "loss": 1.3783, + "step": 4002 + }, + { + "epoch": 0.42, + "learning_rate": 1.4389412924295865e-05, + "loss": 1.343, + "step": 4003 + }, + { + "epoch": 0.42, + "learning_rate": 1.4386123838001625e-05, + "loss": 1.3456, + "step": 4004 + }, + { + "epoch": 0.42, + "learning_rate": 1.4382834164079486e-05, + "loss": 1.3689, + "step": 4005 + }, + { + "epoch": 0.42, + "learning_rate": 1.4379543902970183e-05, + "loss": 1.3789, + "step": 4006 + }, + { + "epoch": 0.42, + "learning_rate": 1.4376253055114528e-05, + "loss": 1.4912, + "step": 4007 + }, + { + "epoch": 0.42, + "learning_rate": 1.4372961620953407e-05, + "loss": 1.3692, + "step": 4008 + }, + { + "epoch": 0.42, + "learning_rate": 1.436966960092779e-05, + "loss": 1.4901, + "step": 4009 + }, + { + "epoch": 0.42, + "learning_rate": 1.4366376995478717e-05, + "loss": 1.4431, + "step": 4010 + }, + { + "epoch": 0.42, + "learning_rate": 1.436308380504732e-05, + "loss": 1.4626, + "step": 4011 + }, + { + "epoch": 0.42, + "learning_rate": 1.4359790030074798e-05, + "loss": 1.4241, + "step": 4012 + }, + { + "epoch": 0.42, + "learning_rate": 1.4356495671002435e-05, + "loss": 1.3834, + "step": 4013 + }, + { + "epoch": 0.42, + "learning_rate": 1.4353200728271586e-05, + "loss": 1.3626, + "step": 4014 + }, + { + "epoch": 0.42, + "learning_rate": 1.4349905202323692e-05, + "loss": 1.3557, + "step": 4015 + }, + { + "epoch": 0.42, + "learning_rate": 1.434660909360027e-05, + "loss": 1.4077, + "step": 4016 + }, + { + "epoch": 0.42, + "learning_rate": 1.4343312402542911e-05, + "loss": 1.4337, + "step": 4017 + }, + { + "epoch": 0.42, + "learning_rate": 1.4340015129593286e-05, + "loss": 1.419, + "step": 4018 + }, + { + "epoch": 0.42, + "learning_rate": 1.4336717275193148e-05, + "loss": 1.3768, + "step": 4019 + }, + { + "epoch": 0.42, + "learning_rate": 1.4333418839784326e-05, + "loss": 1.383, + "step": 4020 + }, + { + "epoch": 0.42, + "learning_rate": 1.4330119823808719e-05, + "loss": 1.3951, + "step": 4021 + }, + { + "epoch": 0.42, + "learning_rate": 1.4326820227708316e-05, + "loss": 1.3985, + "step": 4022 + }, + { + "epoch": 0.42, + "learning_rate": 1.4323520051925177e-05, + "loss": 1.356, + "step": 4023 + }, + { + "epoch": 0.42, + "learning_rate": 1.4320219296901439e-05, + "loss": 1.5017, + "step": 4024 + }, + { + "epoch": 0.42, + "learning_rate": 1.4316917963079322e-05, + "loss": 1.3594, + "step": 4025 + }, + { + "epoch": 0.42, + "learning_rate": 1.4313616050901114e-05, + "loss": 1.6028, + "step": 4026 + }, + { + "epoch": 0.42, + "learning_rate": 1.4310313560809193e-05, + "loss": 1.4132, + "step": 4027 + }, + { + "epoch": 0.42, + "learning_rate": 1.4307010493246006e-05, + "loss": 1.2969, + "step": 4028 + }, + { + "epoch": 0.42, + "learning_rate": 1.4303706848654073e-05, + "loss": 1.5224, + "step": 4029 + }, + { + "epoch": 0.42, + "learning_rate": 1.4300402627476007e-05, + "loss": 1.3386, + "step": 4030 + }, + { + "epoch": 0.42, + "learning_rate": 1.429709783015448e-05, + "loss": 1.3554, + "step": 4031 + }, + { + "epoch": 0.42, + "learning_rate": 1.4293792457132259e-05, + "loss": 1.3386, + "step": 4032 + }, + { + "epoch": 0.42, + "learning_rate": 1.429048650885217e-05, + "loss": 1.4613, + "step": 4033 + }, + { + "epoch": 0.42, + "learning_rate": 1.4287179985757132e-05, + "loss": 1.3632, + "step": 4034 + }, + { + "epoch": 0.42, + "learning_rate": 1.428387288829013e-05, + "loss": 1.3835, + "step": 4035 + }, + { + "epoch": 0.42, + "learning_rate": 1.4280565216894234e-05, + "loss": 1.3711, + "step": 4036 + }, + { + "epoch": 0.42, + "learning_rate": 1.4277256972012582e-05, + "loss": 1.3385, + "step": 4037 + }, + { + "epoch": 0.42, + "learning_rate": 1.4273948154088395e-05, + "loss": 1.4607, + "step": 4038 + }, + { + "epoch": 0.42, + "learning_rate": 1.4270638763564973e-05, + "loss": 1.4042, + "step": 4039 + }, + { + "epoch": 0.42, + "learning_rate": 1.4267328800885687e-05, + "loss": 1.4006, + "step": 4040 + }, + { + "epoch": 0.42, + "learning_rate": 1.4264018266493987e-05, + "loss": 1.386, + "step": 4041 + }, + { + "epoch": 0.42, + "learning_rate": 1.4260707160833401e-05, + "loss": 1.3487, + "step": 4042 + }, + { + "epoch": 0.42, + "learning_rate": 1.4257395484347529e-05, + "loss": 1.4199, + "step": 4043 + }, + { + "epoch": 0.42, + "learning_rate": 1.4254083237480054e-05, + "loss": 1.3236, + "step": 4044 + }, + { + "epoch": 0.42, + "learning_rate": 1.4250770420674726e-05, + "loss": 1.4056, + "step": 4045 + }, + { + "epoch": 0.42, + "learning_rate": 1.4247457034375387e-05, + "loss": 1.4391, + "step": 4046 + }, + { + "epoch": 0.42, + "learning_rate": 1.4244143079025938e-05, + "loss": 1.3935, + "step": 4047 + }, + { + "epoch": 0.42, + "learning_rate": 1.4240828555070368e-05, + "loss": 1.3623, + "step": 4048 + }, + { + "epoch": 0.42, + "learning_rate": 1.4237513462952733e-05, + "loss": 1.3254, + "step": 4049 + }, + { + "epoch": 0.42, + "learning_rate": 1.4234197803117174e-05, + "loss": 1.4217, + "step": 4050 + }, + { + "epoch": 0.42, + "learning_rate": 1.4230881576007904e-05, + "loss": 1.435, + "step": 4051 + }, + { + "epoch": 0.42, + "learning_rate": 1.422756478206921e-05, + "loss": 1.3687, + "step": 4052 + }, + { + "epoch": 0.43, + "learning_rate": 1.4224247421745464e-05, + "loss": 1.3965, + "step": 4053 + }, + { + "epoch": 0.43, + "learning_rate": 1.4220929495481097e-05, + "loss": 1.4159, + "step": 4054 + }, + { + "epoch": 0.43, + "learning_rate": 1.4217611003720632e-05, + "loss": 1.3632, + "step": 4055 + }, + { + "epoch": 0.43, + "learning_rate": 1.4214291946908661e-05, + "loss": 1.403, + "step": 4056 + }, + { + "epoch": 0.43, + "learning_rate": 1.4210972325489854e-05, + "loss": 1.4093, + "step": 4057 + }, + { + "epoch": 0.43, + "learning_rate": 1.4207652139908952e-05, + "loss": 1.4551, + "step": 4058 + }, + { + "epoch": 0.43, + "learning_rate": 1.4204331390610775e-05, + "loss": 1.4162, + "step": 4059 + }, + { + "epoch": 0.43, + "learning_rate": 1.4201010078040216e-05, + "loss": 1.4492, + "step": 4060 + }, + { + "epoch": 0.43, + "learning_rate": 1.419768820264225e-05, + "loss": 1.4449, + "step": 4061 + }, + { + "epoch": 0.43, + "learning_rate": 1.4194365764861922e-05, + "loss": 1.3382, + "step": 4062 + }, + { + "epoch": 0.43, + "learning_rate": 1.419104276514435e-05, + "loss": 1.3899, + "step": 4063 + }, + { + "epoch": 0.43, + "learning_rate": 1.4187719203934734e-05, + "loss": 1.3513, + "step": 4064 + }, + { + "epoch": 0.43, + "learning_rate": 1.4184395081678344e-05, + "loss": 1.3954, + "step": 4065 + }, + { + "epoch": 0.43, + "learning_rate": 1.4181070398820528e-05, + "loss": 1.442, + "step": 4066 + }, + { + "epoch": 0.43, + "learning_rate": 1.4177745155806708e-05, + "loss": 1.3907, + "step": 4067 + }, + { + "epoch": 0.43, + "learning_rate": 1.417441935308238e-05, + "loss": 1.3757, + "step": 4068 + }, + { + "epoch": 0.43, + "learning_rate": 1.4171092991093118e-05, + "loss": 1.3507, + "step": 4069 + }, + { + "epoch": 0.43, + "learning_rate": 1.4167766070284568e-05, + "loss": 1.4136, + "step": 4070 + }, + { + "epoch": 0.43, + "learning_rate": 1.4164438591102452e-05, + "loss": 1.3835, + "step": 4071 + }, + { + "epoch": 0.43, + "learning_rate": 1.4161110553992565e-05, + "loss": 1.4981, + "step": 4072 + }, + { + "epoch": 0.43, + "learning_rate": 1.415778195940078e-05, + "loss": 1.4387, + "step": 4073 + }, + { + "epoch": 0.43, + "learning_rate": 1.4154452807773047e-05, + "loss": 1.333, + "step": 4074 + }, + { + "epoch": 0.43, + "learning_rate": 1.4151123099555377e-05, + "loss": 1.3558, + "step": 4075 + }, + { + "epoch": 0.43, + "learning_rate": 1.4147792835193875e-05, + "loss": 1.4655, + "step": 4076 + }, + { + "epoch": 0.43, + "learning_rate": 1.4144462015134708e-05, + "loss": 1.4402, + "step": 4077 + }, + { + "epoch": 0.43, + "learning_rate": 1.4141130639824119e-05, + "loss": 1.4227, + "step": 4078 + }, + { + "epoch": 0.43, + "learning_rate": 1.4137798709708423e-05, + "loss": 1.4039, + "step": 4079 + }, + { + "epoch": 0.43, + "learning_rate": 1.4134466225234023e-05, + "loss": 1.3593, + "step": 4080 + }, + { + "epoch": 0.43, + "learning_rate": 1.4131133186847377e-05, + "loss": 1.372, + "step": 4081 + }, + { + "epoch": 0.43, + "learning_rate": 1.412779959499503e-05, + "loss": 1.4487, + "step": 4082 + }, + { + "epoch": 0.43, + "learning_rate": 1.4124465450123599e-05, + "loss": 1.3972, + "step": 4083 + }, + { + "epoch": 0.43, + "learning_rate": 1.4121130752679772e-05, + "loss": 1.3768, + "step": 4084 + }, + { + "epoch": 0.43, + "learning_rate": 1.4117795503110313e-05, + "loss": 1.3827, + "step": 4085 + }, + { + "epoch": 0.43, + "learning_rate": 1.4114459701862062e-05, + "loss": 1.3922, + "step": 4086 + }, + { + "epoch": 0.43, + "learning_rate": 1.4111123349381925e-05, + "loss": 1.3736, + "step": 4087 + }, + { + "epoch": 0.43, + "learning_rate": 1.4107786446116894e-05, + "loss": 1.4338, + "step": 4088 + }, + { + "epoch": 0.43, + "learning_rate": 1.4104448992514023e-05, + "loss": 1.347, + "step": 4089 + }, + { + "epoch": 0.43, + "learning_rate": 1.410111098902045e-05, + "loss": 1.3915, + "step": 4090 + }, + { + "epoch": 0.43, + "learning_rate": 1.4097772436083377e-05, + "loss": 1.3656, + "step": 4091 + }, + { + "epoch": 0.43, + "learning_rate": 1.4094433334150087e-05, + "loss": 1.3461, + "step": 4092 + }, + { + "epoch": 0.43, + "learning_rate": 1.4091093683667934e-05, + "loss": 1.7345, + "step": 4093 + }, + { + "epoch": 0.43, + "learning_rate": 1.4087753485084343e-05, + "loss": 1.6204, + "step": 4094 + }, + { + "epoch": 0.43, + "learning_rate": 1.4084412738846816e-05, + "loss": 1.4074, + "step": 4095 + }, + { + "epoch": 0.43, + "learning_rate": 1.408107144540293e-05, + "loss": 1.3776, + "step": 4096 + }, + { + "epoch": 0.43, + "learning_rate": 1.407772960520033e-05, + "loss": 1.4079, + "step": 4097 + }, + { + "epoch": 0.43, + "learning_rate": 1.4074387218686734e-05, + "loss": 1.4254, + "step": 4098 + }, + { + "epoch": 0.43, + "learning_rate": 1.407104428630994e-05, + "loss": 1.38, + "step": 4099 + }, + { + "epoch": 0.43, + "learning_rate": 1.4067700808517815e-05, + "loss": 1.4175, + "step": 4100 + }, + { + "epoch": 0.43, + "learning_rate": 1.4064356785758298e-05, + "loss": 1.4085, + "step": 4101 + }, + { + "epoch": 0.43, + "learning_rate": 1.4061012218479397e-05, + "loss": 1.4529, + "step": 4102 + }, + { + "epoch": 0.43, + "learning_rate": 1.405766710712921e-05, + "loss": 1.4836, + "step": 4103 + }, + { + "epoch": 0.43, + "learning_rate": 1.4054321452155885e-05, + "loss": 1.3915, + "step": 4104 + }, + { + "epoch": 0.43, + "learning_rate": 1.4050975254007659e-05, + "loss": 1.3044, + "step": 4105 + }, + { + "epoch": 0.43, + "learning_rate": 1.4047628513132835e-05, + "loss": 1.373, + "step": 4106 + }, + { + "epoch": 0.43, + "learning_rate": 1.4044281229979793e-05, + "loss": 1.4266, + "step": 4107 + }, + { + "epoch": 0.43, + "learning_rate": 1.4040933404996977e-05, + "loss": 1.3898, + "step": 4108 + }, + { + "epoch": 0.43, + "learning_rate": 1.4037585038632915e-05, + "loss": 0.9326, + "step": 4109 + }, + { + "epoch": 0.43, + "learning_rate": 1.40342361313362e-05, + "loss": 1.0831, + "step": 4110 + }, + { + "epoch": 0.43, + "learning_rate": 1.40308866835555e-05, + "loss": 1.3898, + "step": 4111 + }, + { + "epoch": 0.43, + "learning_rate": 1.4027536695739554e-05, + "loss": 1.5058, + "step": 4112 + }, + { + "epoch": 0.43, + "learning_rate": 1.4024186168337175e-05, + "loss": 1.3635, + "step": 4113 + }, + { + "epoch": 0.43, + "learning_rate": 1.4020835101797248e-05, + "loss": 1.3871, + "step": 4114 + }, + { + "epoch": 0.43, + "learning_rate": 1.401748349656873e-05, + "loss": 1.3478, + "step": 4115 + }, + { + "epoch": 0.43, + "learning_rate": 1.4014131353100648e-05, + "loss": 1.3356, + "step": 4116 + }, + { + "epoch": 0.43, + "learning_rate": 1.4010778671842107e-05, + "loss": 1.3954, + "step": 4117 + }, + { + "epoch": 0.43, + "learning_rate": 1.4007425453242274e-05, + "loss": 1.3307, + "step": 4118 + }, + { + "epoch": 0.43, + "learning_rate": 1.4004071697750398e-05, + "loss": 1.4508, + "step": 4119 + }, + { + "epoch": 0.43, + "learning_rate": 1.4000717405815799e-05, + "loss": 1.3752, + "step": 4120 + }, + { + "epoch": 0.43, + "learning_rate": 1.399736257788786e-05, + "loss": 1.3654, + "step": 4121 + }, + { + "epoch": 0.43, + "learning_rate": 1.3994007214416046e-05, + "loss": 1.4505, + "step": 4122 + }, + { + "epoch": 0.43, + "learning_rate": 1.3990651315849886e-05, + "loss": 1.4307, + "step": 4123 + }, + { + "epoch": 0.43, + "learning_rate": 1.398729488263899e-05, + "loss": 1.4481, + "step": 4124 + }, + { + "epoch": 0.43, + "learning_rate": 1.3983937915233026e-05, + "loss": 1.4755, + "step": 4125 + }, + { + "epoch": 0.43, + "learning_rate": 1.3980580414081746e-05, + "loss": 1.3402, + "step": 4126 + }, + { + "epoch": 0.43, + "learning_rate": 1.3977222379634969e-05, + "loss": 1.3636, + "step": 4127 + }, + { + "epoch": 0.43, + "learning_rate": 1.3973863812342585e-05, + "loss": 1.4165, + "step": 4128 + }, + { + "epoch": 0.43, + "learning_rate": 1.3970504712654554e-05, + "loss": 1.3832, + "step": 4129 + }, + { + "epoch": 0.43, + "learning_rate": 1.3967145081020912e-05, + "loss": 1.4236, + "step": 4130 + }, + { + "epoch": 0.43, + "learning_rate": 1.396378491789176e-05, + "loss": 1.5022, + "step": 4131 + }, + { + "epoch": 0.43, + "learning_rate": 1.3960424223717276e-05, + "loss": 1.3806, + "step": 4132 + }, + { + "epoch": 0.43, + "learning_rate": 1.3957062998947707e-05, + "loss": 1.3649, + "step": 4133 + }, + { + "epoch": 0.43, + "learning_rate": 1.3953701244033368e-05, + "loss": 1.3787, + "step": 4134 + }, + { + "epoch": 0.43, + "learning_rate": 1.395033895942465e-05, + "loss": 1.3551, + "step": 4135 + }, + { + "epoch": 0.43, + "learning_rate": 1.394697614557201e-05, + "loss": 1.3881, + "step": 4136 + }, + { + "epoch": 0.43, + "learning_rate": 1.3943612802925983e-05, + "loss": 1.4848, + "step": 4137 + }, + { + "epoch": 0.43, + "learning_rate": 1.3940248931937169e-05, + "loss": 1.425, + "step": 4138 + }, + { + "epoch": 0.43, + "learning_rate": 1.3936884533056238e-05, + "loss": 1.4054, + "step": 4139 + }, + { + "epoch": 0.43, + "learning_rate": 1.3933519606733934e-05, + "loss": 1.4028, + "step": 4140 + }, + { + "epoch": 0.43, + "learning_rate": 1.3930154153421072e-05, + "loss": 1.4439, + "step": 4141 + }, + { + "epoch": 0.43, + "learning_rate": 1.3926788173568536e-05, + "loss": 1.4482, + "step": 4142 + }, + { + "epoch": 0.43, + "learning_rate": 1.392342166762728e-05, + "loss": 1.393, + "step": 4143 + }, + { + "epoch": 0.43, + "learning_rate": 1.3920054636048328e-05, + "loss": 1.4097, + "step": 4144 + }, + { + "epoch": 0.43, + "learning_rate": 1.391668707928278e-05, + "loss": 1.5142, + "step": 4145 + }, + { + "epoch": 0.43, + "learning_rate": 1.3913318997781797e-05, + "loss": 1.4118, + "step": 4146 + }, + { + "epoch": 0.43, + "learning_rate": 1.390995039199662e-05, + "loss": 1.4067, + "step": 4147 + }, + { + "epoch": 0.43, + "learning_rate": 1.3906581262378552e-05, + "loss": 1.5214, + "step": 4148 + }, + { + "epoch": 0.44, + "learning_rate": 1.3903211609378971e-05, + "loss": 1.3618, + "step": 4149 + }, + { + "epoch": 0.44, + "learning_rate": 1.3899841433449327e-05, + "loss": 1.338, + "step": 4150 + }, + { + "epoch": 0.44, + "learning_rate": 1.3896470735041132e-05, + "loss": 1.3901, + "step": 4151 + }, + { + "epoch": 0.44, + "learning_rate": 1.3893099514605971e-05, + "loss": 1.4502, + "step": 4152 + }, + { + "epoch": 0.44, + "learning_rate": 1.388972777259551e-05, + "loss": 1.4141, + "step": 4153 + }, + { + "epoch": 0.44, + "learning_rate": 1.3886355509461471e-05, + "loss": 1.3876, + "step": 4154 + }, + { + "epoch": 0.44, + "learning_rate": 1.388298272565565e-05, + "loss": 1.4275, + "step": 4155 + }, + { + "epoch": 0.44, + "learning_rate": 1.3879609421629909e-05, + "loss": 1.3559, + "step": 4156 + }, + { + "epoch": 0.44, + "learning_rate": 1.3876235597836195e-05, + "loss": 1.416, + "step": 4157 + }, + { + "epoch": 0.44, + "learning_rate": 1.3872861254726506e-05, + "loss": 1.437, + "step": 4158 + }, + { + "epoch": 0.44, + "learning_rate": 1.3869486392752918e-05, + "loss": 1.3794, + "step": 4159 + }, + { + "epoch": 0.44, + "learning_rate": 1.3866111012367577e-05, + "loss": 1.4094, + "step": 4160 + }, + { + "epoch": 0.44, + "learning_rate": 1.3862735114022694e-05, + "loss": 1.3957, + "step": 4161 + }, + { + "epoch": 0.44, + "learning_rate": 1.3859358698170559e-05, + "loss": 1.3582, + "step": 4162 + }, + { + "epoch": 0.44, + "learning_rate": 1.3855981765263523e-05, + "loss": 1.4159, + "step": 4163 + }, + { + "epoch": 0.44, + "learning_rate": 1.3852604315754e-05, + "loss": 1.3498, + "step": 4164 + }, + { + "epoch": 0.44, + "learning_rate": 1.3849226350094491e-05, + "loss": 1.3951, + "step": 4165 + }, + { + "epoch": 0.44, + "learning_rate": 1.3845847868737559e-05, + "loss": 1.4087, + "step": 4166 + }, + { + "epoch": 0.44, + "learning_rate": 1.3842468872135821e-05, + "loss": 1.4318, + "step": 4167 + }, + { + "epoch": 0.44, + "learning_rate": 1.3839089360741989e-05, + "loss": 1.4174, + "step": 4168 + }, + { + "epoch": 0.44, + "learning_rate": 1.3835709335008822e-05, + "loss": 1.4499, + "step": 4169 + }, + { + "epoch": 0.44, + "learning_rate": 1.383232879538916e-05, + "loss": 1.3554, + "step": 4170 + }, + { + "epoch": 0.44, + "learning_rate": 1.3828947742335905e-05, + "loss": 1.3873, + "step": 4171 + }, + { + "epoch": 0.44, + "learning_rate": 1.382556617630204e-05, + "loss": 1.3804, + "step": 4172 + }, + { + "epoch": 0.44, + "learning_rate": 1.3822184097740598e-05, + "loss": 1.3856, + "step": 4173 + }, + { + "epoch": 0.44, + "learning_rate": 1.3818801507104697e-05, + "loss": 1.3901, + "step": 4174 + }, + { + "epoch": 0.44, + "learning_rate": 1.381541840484751e-05, + "loss": 1.3714, + "step": 4175 + }, + { + "epoch": 0.44, + "learning_rate": 1.3812034791422297e-05, + "loss": 1.4945, + "step": 4176 + }, + { + "epoch": 0.44, + "learning_rate": 1.3808650667282368e-05, + "loss": 1.429, + "step": 4177 + }, + { + "epoch": 0.44, + "learning_rate": 1.3805266032881108e-05, + "loss": 1.3903, + "step": 4178 + }, + { + "epoch": 0.44, + "learning_rate": 1.3801880888671972e-05, + "loss": 1.4799, + "step": 4179 + }, + { + "epoch": 0.44, + "eval_loss": 1.4521424770355225, + "eval_runtime": 77.3596, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 4179 + }, + { + "epoch": 0.44, + "learning_rate": 1.3798495235108484e-05, + "loss": 1.3912, + "step": 4180 + }, + { + "epoch": 0.44, + "learning_rate": 1.3795109072644235e-05, + "loss": 1.5837, + "step": 4181 + }, + { + "epoch": 0.44, + "learning_rate": 1.379172240173288e-05, + "loss": 1.4255, + "step": 4182 + }, + { + "epoch": 0.44, + "learning_rate": 1.3788335222828148e-05, + "loss": 1.4666, + "step": 4183 + }, + { + "epoch": 0.44, + "learning_rate": 1.3784947536383837e-05, + "loss": 1.3964, + "step": 4184 + }, + { + "epoch": 0.44, + "learning_rate": 1.3781559342853807e-05, + "loss": 1.336, + "step": 4185 + }, + { + "epoch": 0.44, + "learning_rate": 1.3778170642691986e-05, + "loss": 1.4352, + "step": 4186 + }, + { + "epoch": 0.44, + "learning_rate": 1.377478143635238e-05, + "loss": 1.3262, + "step": 4187 + }, + { + "epoch": 0.44, + "learning_rate": 1.3771391724289047e-05, + "loss": 1.3969, + "step": 4188 + }, + { + "epoch": 0.44, + "learning_rate": 1.376800150695613e-05, + "loss": 1.4211, + "step": 4189 + }, + { + "epoch": 0.44, + "learning_rate": 1.3764610784807824e-05, + "loss": 1.4338, + "step": 4190 + }, + { + "epoch": 0.44, + "learning_rate": 1.3761219558298403e-05, + "loss": 1.3815, + "step": 4191 + }, + { + "epoch": 0.44, + "learning_rate": 1.3757827827882203e-05, + "loss": 1.3805, + "step": 4192 + }, + { + "epoch": 0.44, + "learning_rate": 1.3754435594013627e-05, + "loss": 1.4071, + "step": 4193 + }, + { + "epoch": 0.44, + "learning_rate": 1.3751042857147145e-05, + "loss": 1.343, + "step": 4194 + }, + { + "epoch": 0.44, + "learning_rate": 1.3747649617737304e-05, + "loss": 1.4129, + "step": 4195 + }, + { + "epoch": 0.44, + "learning_rate": 1.3744255876238708e-05, + "loss": 1.3939, + "step": 4196 + }, + { + "epoch": 0.44, + "learning_rate": 1.3740861633106029e-05, + "loss": 1.3963, + "step": 4197 + }, + { + "epoch": 0.44, + "learning_rate": 1.3737466888794008e-05, + "loss": 1.5181, + "step": 4198 + }, + { + "epoch": 0.44, + "learning_rate": 1.3734071643757456e-05, + "loss": 1.4397, + "step": 4199 + }, + { + "epoch": 0.44, + "learning_rate": 1.373067589845125e-05, + "loss": 1.6293, + "step": 4200 + }, + { + "epoch": 0.44, + "learning_rate": 1.3727279653330328e-05, + "loss": 1.3498, + "step": 4201 + }, + { + "epoch": 0.44, + "learning_rate": 1.37238829088497e-05, + "loss": 1.4509, + "step": 4202 + }, + { + "epoch": 0.44, + "learning_rate": 1.3720485665464446e-05, + "loss": 1.4477, + "step": 4203 + }, + { + "epoch": 0.44, + "learning_rate": 1.3717087923629709e-05, + "loss": 1.4399, + "step": 4204 + }, + { + "epoch": 0.44, + "learning_rate": 1.3713689683800695e-05, + "loss": 1.4417, + "step": 4205 + }, + { + "epoch": 0.44, + "learning_rate": 1.3710290946432685e-05, + "loss": 1.3957, + "step": 4206 + }, + { + "epoch": 0.44, + "learning_rate": 1.3706891711981021e-05, + "loss": 1.4476, + "step": 4207 + }, + { + "epoch": 0.44, + "learning_rate": 1.3703491980901113e-05, + "loss": 1.3894, + "step": 4208 + }, + { + "epoch": 0.44, + "learning_rate": 1.3700091753648437e-05, + "loss": 1.4745, + "step": 4209 + }, + { + "epoch": 0.44, + "learning_rate": 1.369669103067854e-05, + "loss": 1.4038, + "step": 4210 + }, + { + "epoch": 0.44, + "learning_rate": 1.3693289812447023e-05, + "loss": 1.4151, + "step": 4211 + }, + { + "epoch": 0.44, + "learning_rate": 1.3689888099409572e-05, + "loss": 1.4214, + "step": 4212 + }, + { + "epoch": 0.44, + "learning_rate": 1.368648589202192e-05, + "loss": 1.4287, + "step": 4213 + }, + { + "epoch": 0.44, + "learning_rate": 1.3683083190739883e-05, + "loss": 1.345, + "step": 4214 + }, + { + "epoch": 0.44, + "learning_rate": 1.367967999601933e-05, + "loss": 1.3022, + "step": 4215 + }, + { + "epoch": 0.44, + "learning_rate": 1.3676276308316207e-05, + "loss": 1.3971, + "step": 4216 + }, + { + "epoch": 0.44, + "learning_rate": 1.3672872128086514e-05, + "loss": 1.3335, + "step": 4217 + }, + { + "epoch": 0.44, + "learning_rate": 1.366946745578633e-05, + "loss": 1.3988, + "step": 4218 + }, + { + "epoch": 0.44, + "learning_rate": 1.366606229187179e-05, + "loss": 1.4508, + "step": 4219 + }, + { + "epoch": 0.44, + "learning_rate": 1.3662656636799099e-05, + "loss": 1.3814, + "step": 4220 + }, + { + "epoch": 0.44, + "learning_rate": 1.3659250491024527e-05, + "loss": 1.4128, + "step": 4221 + }, + { + "epoch": 0.44, + "learning_rate": 1.3655843855004411e-05, + "loss": 1.3893, + "step": 4222 + }, + { + "epoch": 0.44, + "learning_rate": 1.3652436729195154e-05, + "loss": 1.2551, + "step": 4223 + }, + { + "epoch": 0.44, + "learning_rate": 1.3649029114053219e-05, + "loss": 1.4386, + "step": 4224 + }, + { + "epoch": 0.44, + "learning_rate": 1.364562101003514e-05, + "loss": 1.4028, + "step": 4225 + }, + { + "epoch": 0.44, + "learning_rate": 1.364221241759752e-05, + "loss": 1.4351, + "step": 4226 + }, + { + "epoch": 0.44, + "learning_rate": 1.363880333719702e-05, + "loss": 1.3941, + "step": 4227 + }, + { + "epoch": 0.44, + "learning_rate": 1.3635393769290368e-05, + "loss": 1.3879, + "step": 4228 + }, + { + "epoch": 0.44, + "learning_rate": 1.3631983714334358e-05, + "loss": 1.3773, + "step": 4229 + }, + { + "epoch": 0.44, + "learning_rate": 1.3628573172785853e-05, + "loss": 1.3679, + "step": 4230 + }, + { + "epoch": 0.44, + "learning_rate": 1.3625162145101776e-05, + "loss": 1.3705, + "step": 4231 + }, + { + "epoch": 0.44, + "learning_rate": 1.3621750631739114e-05, + "loss": 1.8157, + "step": 4232 + }, + { + "epoch": 0.44, + "learning_rate": 1.3618338633154928e-05, + "loss": 1.4056, + "step": 4233 + }, + { + "epoch": 0.44, + "learning_rate": 1.3614926149806334e-05, + "loss": 1.3716, + "step": 4234 + }, + { + "epoch": 0.44, + "learning_rate": 1.3611513182150523e-05, + "loss": 1.3766, + "step": 4235 + }, + { + "epoch": 0.44, + "learning_rate": 1.3608099730644733e-05, + "loss": 1.41, + "step": 4236 + }, + { + "epoch": 0.44, + "learning_rate": 1.3604685795746291e-05, + "loss": 1.421, + "step": 4237 + }, + { + "epoch": 0.44, + "learning_rate": 1.360127137791257e-05, + "loss": 1.3679, + "step": 4238 + }, + { + "epoch": 0.44, + "learning_rate": 1.3597856477601018e-05, + "loss": 1.4615, + "step": 4239 + }, + { + "epoch": 0.44, + "learning_rate": 1.359444109526914e-05, + "loss": 1.3418, + "step": 4240 + }, + { + "epoch": 0.44, + "learning_rate": 1.3591025231374513e-05, + "loss": 1.3631, + "step": 4241 + }, + { + "epoch": 0.44, + "learning_rate": 1.3587608886374772e-05, + "loss": 1.3802, + "step": 4242 + }, + { + "epoch": 0.44, + "learning_rate": 1.3584192060727622e-05, + "loss": 1.4156, + "step": 4243 + }, + { + "epoch": 0.45, + "learning_rate": 1.3580774754890827e-05, + "loss": 1.4161, + "step": 4244 + }, + { + "epoch": 0.45, + "learning_rate": 1.3577356969322222e-05, + "loss": 1.3535, + "step": 4245 + }, + { + "epoch": 0.45, + "learning_rate": 1.3573938704479699e-05, + "loss": 1.3859, + "step": 4246 + }, + { + "epoch": 0.45, + "learning_rate": 1.357051996082122e-05, + "loss": 1.3595, + "step": 4247 + }, + { + "epoch": 0.45, + "learning_rate": 1.3567100738804806e-05, + "loss": 1.4191, + "step": 4248 + }, + { + "epoch": 0.45, + "learning_rate": 1.3563681038888548e-05, + "loss": 1.4186, + "step": 4249 + }, + { + "epoch": 0.45, + "learning_rate": 1.3560260861530596e-05, + "loss": 1.43, + "step": 4250 + }, + { + "epoch": 0.45, + "learning_rate": 1.3556840207189168e-05, + "loss": 1.4139, + "step": 4251 + }, + { + "epoch": 0.45, + "learning_rate": 1.3553419076322539e-05, + "loss": 1.4005, + "step": 4252 + }, + { + "epoch": 0.45, + "learning_rate": 1.3549997469389058e-05, + "loss": 1.3468, + "step": 4253 + }, + { + "epoch": 0.45, + "learning_rate": 1.3546575386847132e-05, + "loss": 1.3756, + "step": 4254 + }, + { + "epoch": 0.45, + "learning_rate": 1.3543152829155226e-05, + "loss": 1.4063, + "step": 4255 + }, + { + "epoch": 0.45, + "learning_rate": 1.3539729796771884e-05, + "loss": 1.4666, + "step": 4256 + }, + { + "epoch": 0.45, + "learning_rate": 1.3536306290155694e-05, + "loss": 1.4212, + "step": 4257 + }, + { + "epoch": 0.45, + "learning_rate": 1.3532882309765332e-05, + "loss": 1.4883, + "step": 4258 + }, + { + "epoch": 0.45, + "learning_rate": 1.3529457856059507e-05, + "loss": 1.6641, + "step": 4259 + }, + { + "epoch": 0.45, + "learning_rate": 1.3526032929497022e-05, + "loss": 1.3659, + "step": 4260 + }, + { + "epoch": 0.45, + "learning_rate": 1.3522607530536717e-05, + "loss": 1.5945, + "step": 4261 + }, + { + "epoch": 0.45, + "learning_rate": 1.351918165963752e-05, + "loss": 1.3643, + "step": 4262 + }, + { + "epoch": 0.45, + "learning_rate": 1.3515755317258397e-05, + "loss": 1.3442, + "step": 4263 + }, + { + "epoch": 0.45, + "learning_rate": 1.3512328503858398e-05, + "loss": 1.3982, + "step": 4264 + }, + { + "epoch": 0.45, + "learning_rate": 1.3508901219896624e-05, + "loss": 1.4985, + "step": 4265 + }, + { + "epoch": 0.45, + "learning_rate": 1.350547346583225e-05, + "loss": 1.3319, + "step": 4266 + }, + { + "epoch": 0.45, + "learning_rate": 1.3502045242124497e-05, + "loss": 1.3961, + "step": 4267 + }, + { + "epoch": 0.45, + "learning_rate": 1.3498616549232665e-05, + "loss": 1.4565, + "step": 4268 + }, + { + "epoch": 0.45, + "learning_rate": 1.349518738761611e-05, + "loss": 1.375, + "step": 4269 + }, + { + "epoch": 0.45, + "learning_rate": 1.3491757757734254e-05, + "loss": 1.3005, + "step": 4270 + }, + { + "epoch": 0.45, + "learning_rate": 1.348832766004657e-05, + "loss": 1.3185, + "step": 4271 + }, + { + "epoch": 0.45, + "learning_rate": 1.3484897095012613e-05, + "loss": 1.4449, + "step": 4272 + }, + { + "epoch": 0.45, + "learning_rate": 1.3481466063091988e-05, + "loss": 1.3587, + "step": 4273 + }, + { + "epoch": 0.45, + "learning_rate": 1.3478034564744362e-05, + "loss": 1.3844, + "step": 4274 + }, + { + "epoch": 0.45, + "learning_rate": 1.3474602600429468e-05, + "loss": 1.4471, + "step": 4275 + }, + { + "epoch": 0.45, + "learning_rate": 1.3471170170607105e-05, + "loss": 1.4686, + "step": 4276 + }, + { + "epoch": 0.45, + "learning_rate": 1.3467737275737127e-05, + "loss": 1.312, + "step": 4277 + }, + { + "epoch": 0.45, + "learning_rate": 1.3464303916279453e-05, + "loss": 1.407, + "step": 4278 + }, + { + "epoch": 0.45, + "learning_rate": 1.346087009269407e-05, + "loss": 1.364, + "step": 4279 + }, + { + "epoch": 0.45, + "learning_rate": 1.3457435805441016e-05, + "loss": 1.4103, + "step": 4280 + }, + { + "epoch": 0.45, + "learning_rate": 1.3454001054980403e-05, + "loss": 1.4243, + "step": 4281 + }, + { + "epoch": 0.45, + "learning_rate": 1.3450565841772392e-05, + "loss": 1.3879, + "step": 4282 + }, + { + "epoch": 0.45, + "learning_rate": 1.344713016627722e-05, + "loss": 1.4688, + "step": 4283 + }, + { + "epoch": 0.45, + "learning_rate": 1.3443694028955176e-05, + "loss": 1.3983, + "step": 4284 + }, + { + "epoch": 0.45, + "learning_rate": 1.344025743026662e-05, + "loss": 1.4316, + "step": 4285 + }, + { + "epoch": 0.45, + "learning_rate": 1.3436820370671956e-05, + "loss": 1.3643, + "step": 4286 + }, + { + "epoch": 0.45, + "learning_rate": 1.3433382850631673e-05, + "loss": 1.4566, + "step": 4287 + }, + { + "epoch": 0.45, + "learning_rate": 1.3429944870606301e-05, + "loss": 1.1263, + "step": 4288 + }, + { + "epoch": 0.45, + "learning_rate": 1.3426506431056452e-05, + "loss": 1.2463, + "step": 4289 + }, + { + "epoch": 0.45, + "learning_rate": 1.342306753244278e-05, + "loss": 1.4753, + "step": 4290 + }, + { + "epoch": 0.45, + "learning_rate": 1.3419628175226012e-05, + "loss": 1.3789, + "step": 4291 + }, + { + "epoch": 0.45, + "learning_rate": 1.3416188359866932e-05, + "loss": 1.3906, + "step": 4292 + }, + { + "epoch": 0.45, + "learning_rate": 1.3412748086826389e-05, + "loss": 1.3995, + "step": 4293 + }, + { + "epoch": 0.45, + "learning_rate": 1.3409307356565288e-05, + "loss": 1.4906, + "step": 4294 + }, + { + "epoch": 0.45, + "learning_rate": 1.3405866169544602e-05, + "loss": 1.3951, + "step": 4295 + }, + { + "epoch": 0.45, + "learning_rate": 1.3402424526225359e-05, + "loss": 1.3753, + "step": 4296 + }, + { + "epoch": 0.45, + "learning_rate": 1.3398982427068654e-05, + "loss": 1.3686, + "step": 4297 + }, + { + "epoch": 0.45, + "learning_rate": 1.3395539872535636e-05, + "loss": 1.3612, + "step": 4298 + }, + { + "epoch": 0.45, + "learning_rate": 1.3392096863087522e-05, + "loss": 1.4043, + "step": 4299 + }, + { + "epoch": 0.45, + "learning_rate": 1.3388653399185585e-05, + "loss": 1.4068, + "step": 4300 + }, + { + "epoch": 0.45, + "learning_rate": 1.338520948129116e-05, + "loss": 1.4066, + "step": 4301 + }, + { + "epoch": 0.45, + "learning_rate": 1.3381765109865646e-05, + "loss": 1.4944, + "step": 4302 + }, + { + "epoch": 0.45, + "learning_rate": 1.3378320285370496e-05, + "loss": 1.3575, + "step": 4303 + }, + { + "epoch": 0.45, + "learning_rate": 1.3374875008267236e-05, + "loss": 1.3807, + "step": 4304 + }, + { + "epoch": 0.45, + "learning_rate": 1.3371429279017437e-05, + "loss": 1.4389, + "step": 4305 + }, + { + "epoch": 0.45, + "learning_rate": 1.3367983098082739e-05, + "loss": 1.4858, + "step": 4306 + }, + { + "epoch": 0.45, + "learning_rate": 1.3364536465924844e-05, + "loss": 1.3282, + "step": 4307 + }, + { + "epoch": 0.45, + "learning_rate": 1.3361089383005515e-05, + "loss": 1.4306, + "step": 4308 + }, + { + "epoch": 0.45, + "learning_rate": 1.3357641849786566e-05, + "loss": 1.3892, + "step": 4309 + }, + { + "epoch": 0.45, + "learning_rate": 1.3354193866729883e-05, + "loss": 1.3621, + "step": 4310 + }, + { + "epoch": 0.45, + "learning_rate": 1.3350745434297401e-05, + "loss": 1.3476, + "step": 4311 + }, + { + "epoch": 0.45, + "learning_rate": 1.334729655295113e-05, + "loss": 1.4477, + "step": 4312 + }, + { + "epoch": 0.45, + "learning_rate": 1.3343847223153123e-05, + "loss": 1.3585, + "step": 4313 + }, + { + "epoch": 0.45, + "learning_rate": 1.334039744536551e-05, + "loss": 1.3616, + "step": 4314 + }, + { + "epoch": 0.45, + "learning_rate": 1.3336947220050462e-05, + "loss": 1.3579, + "step": 4315 + }, + { + "epoch": 0.45, + "learning_rate": 1.3333496547670232e-05, + "loss": 1.3557, + "step": 4316 + }, + { + "epoch": 0.45, + "learning_rate": 1.3330045428687113e-05, + "loss": 1.4443, + "step": 4317 + }, + { + "epoch": 0.45, + "learning_rate": 1.332659386356347e-05, + "loss": 1.3621, + "step": 4318 + }, + { + "epoch": 0.45, + "learning_rate": 1.3323141852761726e-05, + "loss": 1.3295, + "step": 4319 + }, + { + "epoch": 0.45, + "learning_rate": 1.3319689396744358e-05, + "loss": 1.4187, + "step": 4320 + }, + { + "epoch": 0.45, + "learning_rate": 1.3316236495973905e-05, + "loss": 1.335, + "step": 4321 + }, + { + "epoch": 0.45, + "learning_rate": 1.331278315091297e-05, + "loss": 1.4382, + "step": 4322 + }, + { + "epoch": 0.45, + "learning_rate": 1.3309329362024212e-05, + "loss": 1.4244, + "step": 4323 + }, + { + "epoch": 0.45, + "learning_rate": 1.3305875129770351e-05, + "loss": 1.488, + "step": 4324 + }, + { + "epoch": 0.45, + "learning_rate": 1.3302420454614165e-05, + "loss": 1.3369, + "step": 4325 + }, + { + "epoch": 0.45, + "learning_rate": 1.3298965337018487e-05, + "loss": 1.3648, + "step": 4326 + }, + { + "epoch": 0.45, + "learning_rate": 1.3295509777446226e-05, + "loss": 1.3924, + "step": 4327 + }, + { + "epoch": 0.45, + "learning_rate": 1.3292053776360324e-05, + "loss": 1.3789, + "step": 4328 + }, + { + "epoch": 0.45, + "learning_rate": 1.3288597334223802e-05, + "loss": 1.3902, + "step": 4329 + }, + { + "epoch": 0.45, + "learning_rate": 1.3285140451499735e-05, + "loss": 1.4057, + "step": 4330 + }, + { + "epoch": 0.45, + "learning_rate": 1.328168312865126e-05, + "loss": 1.4536, + "step": 4331 + }, + { + "epoch": 0.45, + "learning_rate": 1.3278225366141565e-05, + "loss": 1.3075, + "step": 4332 + }, + { + "epoch": 0.45, + "learning_rate": 1.3274767164433901e-05, + "loss": 1.4579, + "step": 4333 + }, + { + "epoch": 0.45, + "learning_rate": 1.3271308523991579e-05, + "loss": 1.3906, + "step": 4334 + }, + { + "epoch": 0.45, + "learning_rate": 1.326784944527797e-05, + "loss": 1.3992, + "step": 4335 + }, + { + "epoch": 0.45, + "learning_rate": 1.3264389928756498e-05, + "loss": 1.4001, + "step": 4336 + }, + { + "epoch": 0.45, + "learning_rate": 1.3260929974890653e-05, + "loss": 1.2948, + "step": 4337 + }, + { + "epoch": 0.45, + "learning_rate": 1.3257469584143976e-05, + "loss": 1.4041, + "step": 4338 + }, + { + "epoch": 0.46, + "learning_rate": 1.3254008756980076e-05, + "loss": 1.5035, + "step": 4339 + }, + { + "epoch": 0.46, + "learning_rate": 1.3250547493862609e-05, + "loss": 1.4867, + "step": 4340 + }, + { + "epoch": 0.46, + "learning_rate": 1.3247085795255302e-05, + "loss": 1.3612, + "step": 4341 + }, + { + "epoch": 0.46, + "learning_rate": 1.3243623661621925e-05, + "loss": 1.4193, + "step": 4342 + }, + { + "epoch": 0.46, + "learning_rate": 1.3240161093426322e-05, + "loss": 1.3596, + "step": 4343 + }, + { + "epoch": 0.46, + "learning_rate": 1.3236698091132383e-05, + "loss": 1.4448, + "step": 4344 + }, + { + "epoch": 0.46, + "learning_rate": 1.3233234655204066e-05, + "loss": 1.3924, + "step": 4345 + }, + { + "epoch": 0.46, + "learning_rate": 1.322977078610538e-05, + "loss": 1.3552, + "step": 4346 + }, + { + "epoch": 0.46, + "learning_rate": 1.3226306484300395e-05, + "loss": 1.3949, + "step": 4347 + }, + { + "epoch": 0.46, + "learning_rate": 1.322284175025324e-05, + "loss": 1.399, + "step": 4348 + }, + { + "epoch": 0.46, + "learning_rate": 1.3219376584428094e-05, + "loss": 1.4755, + "step": 4349 + }, + { + "epoch": 0.46, + "learning_rate": 1.3215910987289212e-05, + "loss": 1.3877, + "step": 4350 + }, + { + "epoch": 0.46, + "learning_rate": 1.3212444959300882e-05, + "loss": 1.3916, + "step": 4351 + }, + { + "epoch": 0.46, + "learning_rate": 1.3208978500927472e-05, + "loss": 1.3462, + "step": 4352 + }, + { + "epoch": 0.46, + "learning_rate": 1.3205511612633392e-05, + "loss": 1.3834, + "step": 4353 + }, + { + "epoch": 0.46, + "learning_rate": 1.3202044294883123e-05, + "loss": 1.3843, + "step": 4354 + }, + { + "epoch": 0.46, + "learning_rate": 1.3198576548141189e-05, + "loss": 1.2439, + "step": 4355 + }, + { + "epoch": 0.46, + "learning_rate": 1.3195108372872181e-05, + "loss": 1.4106, + "step": 4356 + }, + { + "epoch": 0.46, + "learning_rate": 1.3191639769540746e-05, + "loss": 1.4417, + "step": 4357 + }, + { + "epoch": 0.46, + "learning_rate": 1.3188170738611596e-05, + "loss": 1.4393, + "step": 4358 + }, + { + "epoch": 0.46, + "learning_rate": 1.3184701280549476e-05, + "loss": 1.4616, + "step": 4359 + }, + { + "epoch": 0.46, + "learning_rate": 1.3181231395819218e-05, + "loss": 1.3215, + "step": 4360 + }, + { + "epoch": 0.46, + "learning_rate": 1.3177761084885689e-05, + "loss": 1.368, + "step": 4361 + }, + { + "epoch": 0.46, + "learning_rate": 1.317429034821383e-05, + "loss": 1.3247, + "step": 4362 + }, + { + "epoch": 0.46, + "learning_rate": 1.3170819186268618e-05, + "loss": 1.4512, + "step": 4363 + }, + { + "epoch": 0.46, + "learning_rate": 1.3167347599515111e-05, + "loss": 1.3129, + "step": 4364 + }, + { + "epoch": 0.46, + "learning_rate": 1.3163875588418404e-05, + "loss": 1.3934, + "step": 4365 + }, + { + "epoch": 0.46, + "learning_rate": 1.3160403153443666e-05, + "loss": 1.4518, + "step": 4366 + }, + { + "epoch": 0.46, + "learning_rate": 1.3156930295056105e-05, + "loss": 1.3959, + "step": 4367 + }, + { + "epoch": 0.46, + "learning_rate": 1.3153457013721e-05, + "loss": 1.3475, + "step": 4368 + }, + { + "epoch": 0.46, + "learning_rate": 1.3149983309903687e-05, + "loss": 1.4102, + "step": 4369 + }, + { + "epoch": 0.46, + "learning_rate": 1.3146509184069538e-05, + "loss": 1.3674, + "step": 4370 + }, + { + "epoch": 0.46, + "learning_rate": 1.314303463668401e-05, + "loss": 1.3739, + "step": 4371 + }, + { + "epoch": 0.46, + "learning_rate": 1.3139559668212596e-05, + "loss": 1.4249, + "step": 4372 + }, + { + "epoch": 0.46, + "learning_rate": 1.3136084279120857e-05, + "loss": 1.4473, + "step": 4373 + }, + { + "epoch": 0.46, + "learning_rate": 1.3132608469874404e-05, + "loss": 1.4443, + "step": 4374 + }, + { + "epoch": 0.46, + "learning_rate": 1.3129132240938905e-05, + "loss": 1.3534, + "step": 4375 + }, + { + "epoch": 0.46, + "learning_rate": 1.3125655592780083e-05, + "loss": 1.5663, + "step": 4376 + }, + { + "epoch": 0.46, + "learning_rate": 1.3122178525863727e-05, + "loss": 1.3465, + "step": 4377 + }, + { + "epoch": 0.46, + "learning_rate": 1.3118701040655669e-05, + "loss": 1.35, + "step": 4378 + }, + { + "epoch": 0.46, + "eval_loss": 1.447788953781128, + "eval_runtime": 77.4473, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4378 + }, + { + "epoch": 0.46, + "learning_rate": 1.3115223137621804e-05, + "loss": 1.343, + "step": 4379 + }, + { + "epoch": 0.46, + "learning_rate": 1.3111744817228078e-05, + "loss": 1.4227, + "step": 4380 + }, + { + "epoch": 0.46, + "learning_rate": 1.3108266079940508e-05, + "loss": 1.3982, + "step": 4381 + }, + { + "epoch": 0.46, + "learning_rate": 1.3104786926225141e-05, + "loss": 1.4211, + "step": 4382 + }, + { + "epoch": 0.46, + "learning_rate": 1.3101307356548103e-05, + "loss": 1.382, + "step": 4383 + }, + { + "epoch": 0.46, + "learning_rate": 1.3097827371375562e-05, + "loss": 1.4637, + "step": 4384 + }, + { + "epoch": 0.46, + "learning_rate": 1.3094346971173754e-05, + "loss": 1.4572, + "step": 4385 + }, + { + "epoch": 0.46, + "learning_rate": 1.3090866156408956e-05, + "loss": 1.5113, + "step": 4386 + }, + { + "epoch": 0.46, + "learning_rate": 1.3087384927547512e-05, + "loss": 1.2197, + "step": 4387 + }, + { + "epoch": 0.46, + "learning_rate": 1.3083903285055813e-05, + "loss": 1.3861, + "step": 4388 + }, + { + "epoch": 0.46, + "learning_rate": 1.3080421229400315e-05, + "loss": 1.4754, + "step": 4389 + }, + { + "epoch": 0.46, + "learning_rate": 1.307693876104752e-05, + "loss": 1.3588, + "step": 4390 + }, + { + "epoch": 0.46, + "learning_rate": 1.3073455880463987e-05, + "loss": 1.3995, + "step": 4391 + }, + { + "epoch": 0.46, + "learning_rate": 1.3069972588116341e-05, + "loss": 1.354, + "step": 4392 + }, + { + "epoch": 0.46, + "learning_rate": 1.3066488884471244e-05, + "loss": 1.3378, + "step": 4393 + }, + { + "epoch": 0.46, + "learning_rate": 1.306300476999543e-05, + "loss": 1.5951, + "step": 4394 + }, + { + "epoch": 0.46, + "learning_rate": 1.305952024515568e-05, + "loss": 1.3661, + "step": 4395 + }, + { + "epoch": 0.46, + "learning_rate": 1.3056035310418826e-05, + "loss": 1.4066, + "step": 4396 + }, + { + "epoch": 0.46, + "learning_rate": 1.3052549966251764e-05, + "loss": 1.3687, + "step": 4397 + }, + { + "epoch": 0.46, + "learning_rate": 1.3049064213121438e-05, + "loss": 1.4573, + "step": 4398 + }, + { + "epoch": 0.46, + "learning_rate": 1.3045578051494852e-05, + "loss": 1.3519, + "step": 4399 + }, + { + "epoch": 0.46, + "learning_rate": 1.3042091481839063e-05, + "loss": 1.2803, + "step": 4400 + }, + { + "epoch": 0.46, + "learning_rate": 1.3038604504621173e-05, + "loss": 1.4014, + "step": 4401 + }, + { + "epoch": 0.46, + "learning_rate": 1.3035117120308358e-05, + "loss": 1.4534, + "step": 4402 + }, + { + "epoch": 0.46, + "learning_rate": 1.3031629329367832e-05, + "loss": 1.4747, + "step": 4403 + }, + { + "epoch": 0.46, + "learning_rate": 1.3028141132266877e-05, + "loss": 1.374, + "step": 4404 + }, + { + "epoch": 0.46, + "learning_rate": 1.3024652529472807e-05, + "loss": 1.4328, + "step": 4405 + }, + { + "epoch": 0.46, + "learning_rate": 1.302116352145302e-05, + "loss": 1.468, + "step": 4406 + }, + { + "epoch": 0.46, + "learning_rate": 1.3017674108674942e-05, + "loss": 1.2947, + "step": 4407 + }, + { + "epoch": 0.46, + "learning_rate": 1.3014184291606077e-05, + "loss": 1.3682, + "step": 4408 + }, + { + "epoch": 0.46, + "learning_rate": 1.3010694070713959e-05, + "loss": 1.3651, + "step": 4409 + }, + { + "epoch": 0.46, + "learning_rate": 1.3007203446466194e-05, + "loss": 1.418, + "step": 4410 + }, + { + "epoch": 0.46, + "learning_rate": 1.3003712419330433e-05, + "loss": 1.416, + "step": 4411 + }, + { + "epoch": 0.46, + "learning_rate": 1.300022098977439e-05, + "loss": 1.2979, + "step": 4412 + }, + { + "epoch": 0.46, + "learning_rate": 1.2996729158265819e-05, + "loss": 1.3868, + "step": 4413 + }, + { + "epoch": 0.46, + "learning_rate": 1.2993236925272542e-05, + "loss": 1.3102, + "step": 4414 + }, + { + "epoch": 0.46, + "learning_rate": 1.2989744291262422e-05, + "loss": 1.3506, + "step": 4415 + }, + { + "epoch": 0.46, + "learning_rate": 1.2986251256703388e-05, + "loss": 1.4018, + "step": 4416 + }, + { + "epoch": 0.46, + "learning_rate": 1.2982757822063417e-05, + "loss": 1.4081, + "step": 4417 + }, + { + "epoch": 0.46, + "learning_rate": 1.2979263987810533e-05, + "loss": 1.3592, + "step": 4418 + }, + { + "epoch": 0.46, + "learning_rate": 1.297576975441283e-05, + "loss": 1.4287, + "step": 4419 + }, + { + "epoch": 0.46, + "learning_rate": 1.2972275122338433e-05, + "loss": 1.4099, + "step": 4420 + }, + { + "epoch": 0.46, + "learning_rate": 1.2968780092055546e-05, + "loss": 1.4005, + "step": 4421 + }, + { + "epoch": 0.46, + "learning_rate": 1.2965284664032401e-05, + "loss": 1.365, + "step": 4422 + }, + { + "epoch": 0.46, + "learning_rate": 1.2961788838737309e-05, + "loss": 1.3588, + "step": 4423 + }, + { + "epoch": 0.46, + "learning_rate": 1.2958292616638606e-05, + "loss": 1.3702, + "step": 4424 + }, + { + "epoch": 0.46, + "learning_rate": 1.2954795998204708e-05, + "loss": 1.3487, + "step": 4425 + }, + { + "epoch": 0.46, + "learning_rate": 1.2951298983904063e-05, + "loss": 1.4395, + "step": 4426 + }, + { + "epoch": 0.46, + "learning_rate": 1.2947801574205193e-05, + "loss": 1.3523, + "step": 4427 + }, + { + "epoch": 0.46, + "learning_rate": 1.2944303769576645e-05, + "loss": 1.3125, + "step": 4428 + }, + { + "epoch": 0.46, + "learning_rate": 1.2940805570487048e-05, + "loss": 1.5476, + "step": 4429 + }, + { + "epoch": 0.46, + "learning_rate": 1.2937306977405062e-05, + "loss": 1.4076, + "step": 4430 + }, + { + "epoch": 0.46, + "learning_rate": 1.2933807990799418e-05, + "loss": 1.3007, + "step": 4431 + }, + { + "epoch": 0.46, + "learning_rate": 1.293030861113888e-05, + "loss": 1.3566, + "step": 4432 + }, + { + "epoch": 0.46, + "learning_rate": 1.2926808838892285e-05, + "loss": 1.3907, + "step": 4433 + }, + { + "epoch": 0.46, + "learning_rate": 1.2923308674528501e-05, + "loss": 1.379, + "step": 4434 + }, + { + "epoch": 0.47, + "learning_rate": 1.2919808118516475e-05, + "loss": 1.4319, + "step": 4435 + }, + { + "epoch": 0.47, + "learning_rate": 1.2916307171325176e-05, + "loss": 1.3392, + "step": 4436 + }, + { + "epoch": 0.47, + "learning_rate": 1.291280583342365e-05, + "loss": 1.401, + "step": 4437 + }, + { + "epoch": 0.47, + "learning_rate": 1.2909304105280984e-05, + "loss": 1.3939, + "step": 4438 + }, + { + "epoch": 0.47, + "learning_rate": 1.2905801987366322e-05, + "loss": 1.4676, + "step": 4439 + }, + { + "epoch": 0.47, + "learning_rate": 1.2902299480148855e-05, + "loss": 1.3957, + "step": 4440 + }, + { + "epoch": 0.47, + "learning_rate": 1.2898796584097828e-05, + "loss": 1.3587, + "step": 4441 + }, + { + "epoch": 0.47, + "learning_rate": 1.2895293299682545e-05, + "loss": 1.5809, + "step": 4442 + }, + { + "epoch": 0.47, + "learning_rate": 1.289178962737235e-05, + "loss": 1.3436, + "step": 4443 + }, + { + "epoch": 0.47, + "learning_rate": 1.2888285567636647e-05, + "loss": 1.4535, + "step": 4444 + }, + { + "epoch": 0.47, + "learning_rate": 1.2884781120944889e-05, + "loss": 1.3377, + "step": 4445 + }, + { + "epoch": 0.47, + "learning_rate": 1.2881276287766587e-05, + "loss": 0.8221, + "step": 4446 + }, + { + "epoch": 0.47, + "learning_rate": 1.2877771068571288e-05, + "loss": 0.7259, + "step": 4447 + }, + { + "epoch": 0.47, + "learning_rate": 1.2874265463828612e-05, + "loss": 0.8279, + "step": 4448 + }, + { + "epoch": 0.47, + "learning_rate": 1.2870759474008213e-05, + "loss": 1.3523, + "step": 4449 + }, + { + "epoch": 0.47, + "learning_rate": 1.2867253099579808e-05, + "loss": 1.3658, + "step": 4450 + }, + { + "epoch": 0.47, + "learning_rate": 1.2863746341013158e-05, + "loss": 1.4112, + "step": 4451 + }, + { + "epoch": 0.47, + "learning_rate": 1.2860239198778085e-05, + "loss": 1.389, + "step": 4452 + }, + { + "epoch": 0.47, + "learning_rate": 1.2856731673344442e-05, + "loss": 1.4066, + "step": 4453 + }, + { + "epoch": 0.47, + "learning_rate": 1.2853223765182165e-05, + "loss": 1.3267, + "step": 4454 + }, + { + "epoch": 0.47, + "learning_rate": 1.2849715474761209e-05, + "loss": 1.3381, + "step": 4455 + }, + { + "epoch": 0.47, + "learning_rate": 1.2846206802551602e-05, + "loss": 1.2882, + "step": 4456 + }, + { + "epoch": 0.47, + "learning_rate": 1.2842697749023414e-05, + "loss": 1.3199, + "step": 4457 + }, + { + "epoch": 0.47, + "learning_rate": 1.2839188314646771e-05, + "loss": 1.3896, + "step": 4458 + }, + { + "epoch": 0.47, + "learning_rate": 1.2835678499891842e-05, + "loss": 1.3186, + "step": 4459 + }, + { + "epoch": 0.47, + "learning_rate": 1.283216830522885e-05, + "loss": 1.3466, + "step": 4460 + }, + { + "epoch": 0.47, + "learning_rate": 1.2828657731128083e-05, + "loss": 1.4678, + "step": 4461 + }, + { + "epoch": 0.47, + "learning_rate": 1.2825146778059857e-05, + "loss": 1.4408, + "step": 4462 + }, + { + "epoch": 0.47, + "learning_rate": 1.2821635446494553e-05, + "loss": 1.3672, + "step": 4463 + }, + { + "epoch": 0.47, + "learning_rate": 1.2818123736902597e-05, + "loss": 1.3836, + "step": 4464 + }, + { + "epoch": 0.47, + "learning_rate": 1.2814611649754472e-05, + "loss": 1.3493, + "step": 4465 + }, + { + "epoch": 0.47, + "learning_rate": 1.2811099185520704e-05, + "loss": 1.3584, + "step": 4466 + }, + { + "epoch": 0.47, + "learning_rate": 1.2807586344671875e-05, + "loss": 1.3551, + "step": 4467 + }, + { + "epoch": 0.47, + "learning_rate": 1.2804073127678612e-05, + "loss": 1.3254, + "step": 4468 + }, + { + "epoch": 0.47, + "learning_rate": 1.28005595350116e-05, + "loss": 1.3405, + "step": 4469 + }, + { + "epoch": 0.47, + "learning_rate": 1.2797045567141568e-05, + "loss": 1.3432, + "step": 4470 + }, + { + "epoch": 0.47, + "learning_rate": 1.2793531224539297e-05, + "loss": 1.4347, + "step": 4471 + }, + { + "epoch": 0.47, + "learning_rate": 1.279001650767562e-05, + "loss": 1.3304, + "step": 4472 + }, + { + "epoch": 0.47, + "learning_rate": 1.278650141702142e-05, + "loss": 1.3244, + "step": 4473 + }, + { + "epoch": 0.47, + "learning_rate": 1.2782985953047625e-05, + "loss": 1.3756, + "step": 4474 + }, + { + "epoch": 0.47, + "learning_rate": 1.2779470116225219e-05, + "loss": 1.5468, + "step": 4475 + }, + { + "epoch": 0.47, + "learning_rate": 1.2775953907025232e-05, + "loss": 1.4316, + "step": 4476 + }, + { + "epoch": 0.47, + "learning_rate": 1.2772437325918752e-05, + "loss": 1.3724, + "step": 4477 + }, + { + "epoch": 0.47, + "learning_rate": 1.27689203733769e-05, + "loss": 1.4458, + "step": 4478 + }, + { + "epoch": 0.47, + "learning_rate": 1.2765403049870865e-05, + "loss": 1.3622, + "step": 4479 + }, + { + "epoch": 0.47, + "learning_rate": 1.2761885355871875e-05, + "loss": 1.3875, + "step": 4480 + }, + { + "epoch": 0.47, + "learning_rate": 1.2758367291851217e-05, + "loss": 1.3577, + "step": 4481 + }, + { + "epoch": 0.47, + "learning_rate": 1.2754848858280211e-05, + "loss": 1.4256, + "step": 4482 + }, + { + "epoch": 0.47, + "learning_rate": 1.2751330055630242e-05, + "loss": 1.3771, + "step": 4483 + }, + { + "epoch": 0.47, + "learning_rate": 1.274781088437274e-05, + "loss": 1.357, + "step": 4484 + }, + { + "epoch": 0.47, + "learning_rate": 1.274429134497918e-05, + "loss": 1.3634, + "step": 4485 + }, + { + "epoch": 0.47, + "learning_rate": 1.2740771437921096e-05, + "loss": 1.3661, + "step": 4486 + }, + { + "epoch": 0.47, + "learning_rate": 1.2737251163670057e-05, + "loss": 1.3819, + "step": 4487 + }, + { + "epoch": 0.47, + "learning_rate": 1.2733730522697696e-05, + "loss": 1.4491, + "step": 4488 + }, + { + "epoch": 0.47, + "learning_rate": 1.2730209515475687e-05, + "loss": 1.3857, + "step": 4489 + }, + { + "epoch": 0.47, + "learning_rate": 1.2726688142475751e-05, + "loss": 1.3837, + "step": 4490 + }, + { + "epoch": 0.47, + "learning_rate": 1.2723166404169663e-05, + "loss": 1.3755, + "step": 4491 + }, + { + "epoch": 0.47, + "learning_rate": 1.271964430102925e-05, + "loss": 1.3767, + "step": 4492 + }, + { + "epoch": 0.47, + "learning_rate": 1.2716121833526376e-05, + "loss": 1.4416, + "step": 4493 + }, + { + "epoch": 0.47, + "learning_rate": 1.2712599002132966e-05, + "loss": 1.5573, + "step": 4494 + }, + { + "epoch": 0.47, + "learning_rate": 1.2709075807320988e-05, + "loss": 1.365, + "step": 4495 + }, + { + "epoch": 0.47, + "learning_rate": 1.270555224956246e-05, + "loss": 1.3862, + "step": 4496 + }, + { + "epoch": 0.47, + "learning_rate": 1.2702028329329445e-05, + "loss": 1.3003, + "step": 4497 + }, + { + "epoch": 0.47, + "learning_rate": 1.2698504047094064e-05, + "loss": 1.3806, + "step": 4498 + }, + { + "epoch": 0.47, + "learning_rate": 1.269497940332847e-05, + "loss": 1.5425, + "step": 4499 + }, + { + "epoch": 0.47, + "learning_rate": 1.269145439850489e-05, + "loss": 1.3541, + "step": 4500 + }, + { + "epoch": 0.47, + "learning_rate": 1.268792903309557e-05, + "loss": 1.4337, + "step": 4501 + }, + { + "epoch": 0.47, + "learning_rate": 1.2684403307572825e-05, + "loss": 1.4004, + "step": 4502 + }, + { + "epoch": 0.47, + "learning_rate": 1.268087722240901e-05, + "loss": 1.9453, + "step": 4503 + }, + { + "epoch": 0.47, + "learning_rate": 1.2677350778076532e-05, + "loss": 1.3907, + "step": 4504 + }, + { + "epoch": 0.47, + "learning_rate": 1.2673823975047839e-05, + "loss": 1.4993, + "step": 4505 + }, + { + "epoch": 0.47, + "learning_rate": 1.2670296813795432e-05, + "loss": 1.4386, + "step": 4506 + }, + { + "epoch": 0.47, + "learning_rate": 1.266676929479187e-05, + "loss": 1.4944, + "step": 4507 + }, + { + "epoch": 0.47, + "learning_rate": 1.266324141850974e-05, + "loss": 1.4311, + "step": 4508 + }, + { + "epoch": 0.47, + "learning_rate": 1.265971318542169e-05, + "loss": 1.3607, + "step": 4509 + }, + { + "epoch": 0.47, + "learning_rate": 1.2656184596000412e-05, + "loss": 1.4007, + "step": 4510 + }, + { + "epoch": 0.47, + "learning_rate": 1.2652655650718645e-05, + "loss": 1.4561, + "step": 4511 + }, + { + "epoch": 0.47, + "learning_rate": 1.2649126350049181e-05, + "loss": 1.4321, + "step": 4512 + }, + { + "epoch": 0.47, + "learning_rate": 1.2645596694464851e-05, + "loss": 1.2856, + "step": 4513 + }, + { + "epoch": 0.47, + "learning_rate": 1.2642066684438543e-05, + "loss": 1.3979, + "step": 4514 + }, + { + "epoch": 0.47, + "learning_rate": 1.2638536320443184e-05, + "loss": 1.4977, + "step": 4515 + }, + { + "epoch": 0.47, + "learning_rate": 1.2635005602951752e-05, + "loss": 1.377, + "step": 4516 + }, + { + "epoch": 0.47, + "learning_rate": 1.2631474532437275e-05, + "loss": 1.4266, + "step": 4517 + }, + { + "epoch": 0.47, + "learning_rate": 1.2627943109372822e-05, + "loss": 1.409, + "step": 4518 + }, + { + "epoch": 0.47, + "learning_rate": 1.2624411334231519e-05, + "loss": 1.3374, + "step": 4519 + }, + { + "epoch": 0.47, + "learning_rate": 1.2620879207486525e-05, + "loss": 1.3765, + "step": 4520 + }, + { + "epoch": 0.47, + "learning_rate": 1.2617346729611061e-05, + "loss": 1.3805, + "step": 4521 + }, + { + "epoch": 0.47, + "learning_rate": 1.2613813901078384e-05, + "loss": 1.3326, + "step": 4522 + }, + { + "epoch": 0.47, + "learning_rate": 1.2610280722361807e-05, + "loss": 1.3909, + "step": 4523 + }, + { + "epoch": 0.47, + "learning_rate": 1.260674719393468e-05, + "loss": 1.3815, + "step": 4524 + }, + { + "epoch": 0.47, + "learning_rate": 1.2603213316270409e-05, + "loss": 1.5589, + "step": 4525 + }, + { + "epoch": 0.47, + "learning_rate": 1.2599679089842437e-05, + "loss": 1.4416, + "step": 4526 + }, + { + "epoch": 0.47, + "learning_rate": 1.259614451512427e-05, + "loss": 1.3529, + "step": 4527 + }, + { + "epoch": 0.47, + "learning_rate": 1.2592609592589437e-05, + "loss": 1.3135, + "step": 4528 + }, + { + "epoch": 0.47, + "learning_rate": 1.2589074322711535e-05, + "loss": 1.4177, + "step": 4529 + }, + { + "epoch": 0.48, + "learning_rate": 1.25855387059642e-05, + "loss": 1.353, + "step": 4530 + }, + { + "epoch": 0.48, + "learning_rate": 1.2582002742821111e-05, + "loss": 1.431, + "step": 4531 + }, + { + "epoch": 0.48, + "learning_rate": 1.2578466433755998e-05, + "loss": 1.3803, + "step": 4532 + }, + { + "epoch": 0.48, + "learning_rate": 1.257492977924263e-05, + "loss": 1.3774, + "step": 4533 + }, + { + "epoch": 0.48, + "learning_rate": 1.2571392779754836e-05, + "loss": 1.4339, + "step": 4534 + }, + { + "epoch": 0.48, + "learning_rate": 1.256785543576648e-05, + "loss": 1.4097, + "step": 4535 + }, + { + "epoch": 0.48, + "learning_rate": 1.2564317747751473e-05, + "loss": 1.4223, + "step": 4536 + }, + { + "epoch": 0.48, + "learning_rate": 1.2560779716183775e-05, + "loss": 1.5148, + "step": 4537 + }, + { + "epoch": 0.48, + "learning_rate": 1.2557241341537394e-05, + "loss": 1.3547, + "step": 4538 + }, + { + "epoch": 0.48, + "learning_rate": 1.255370262428638e-05, + "loss": 1.393, + "step": 4539 + }, + { + "epoch": 0.48, + "learning_rate": 1.2550163564904829e-05, + "loss": 1.3312, + "step": 4540 + }, + { + "epoch": 0.48, + "learning_rate": 1.2546624163866882e-05, + "loss": 1.4193, + "step": 4541 + }, + { + "epoch": 0.48, + "learning_rate": 1.2543084421646735e-05, + "loss": 1.4161, + "step": 4542 + }, + { + "epoch": 0.48, + "learning_rate": 1.2539544338718614e-05, + "loss": 1.4224, + "step": 4543 + }, + { + "epoch": 0.48, + "learning_rate": 1.2536003915556805e-05, + "loss": 1.3484, + "step": 4544 + }, + { + "epoch": 0.48, + "learning_rate": 1.253246315263563e-05, + "loss": 1.4492, + "step": 4545 + }, + { + "epoch": 0.48, + "learning_rate": 1.2528922050429467e-05, + "loss": 1.3549, + "step": 4546 + }, + { + "epoch": 0.48, + "learning_rate": 1.252538060941272e-05, + "loss": 1.45, + "step": 4547 + }, + { + "epoch": 0.48, + "learning_rate": 1.2521838830059865e-05, + "loss": 1.3499, + "step": 4548 + }, + { + "epoch": 0.48, + "learning_rate": 1.2518296712845399e-05, + "loss": 1.3786, + "step": 4549 + }, + { + "epoch": 0.48, + "learning_rate": 1.2514754258243884e-05, + "loss": 1.3394, + "step": 4550 + }, + { + "epoch": 0.48, + "learning_rate": 1.2511211466729909e-05, + "loss": 1.2849, + "step": 4551 + }, + { + "epoch": 0.48, + "learning_rate": 1.250766833877812e-05, + "loss": 1.374, + "step": 4552 + }, + { + "epoch": 0.48, + "learning_rate": 1.2504124874863211e-05, + "loss": 1.3084, + "step": 4553 + }, + { + "epoch": 0.48, + "learning_rate": 1.2500581075459905e-05, + "loss": 1.3348, + "step": 4554 + }, + { + "epoch": 0.48, + "learning_rate": 1.249703694104299e-05, + "loss": 1.3797, + "step": 4555 + }, + { + "epoch": 0.48, + "learning_rate": 1.2493492472087279e-05, + "loss": 1.3371, + "step": 4556 + }, + { + "epoch": 0.48, + "learning_rate": 1.248994766906765e-05, + "loss": 1.3974, + "step": 4557 + }, + { + "epoch": 0.48, + "learning_rate": 1.2486402532459007e-05, + "loss": 1.388, + "step": 4558 + }, + { + "epoch": 0.48, + "learning_rate": 1.2482857062736313e-05, + "loss": 1.3619, + "step": 4559 + }, + { + "epoch": 0.48, + "learning_rate": 1.2479311260374565e-05, + "loss": 1.4123, + "step": 4560 + }, + { + "epoch": 0.48, + "learning_rate": 1.2475765125848814e-05, + "loss": 1.5485, + "step": 4561 + }, + { + "epoch": 0.48, + "learning_rate": 1.247221865963415e-05, + "loss": 1.4965, + "step": 4562 + }, + { + "epoch": 0.48, + "learning_rate": 1.2468671862205705e-05, + "loss": 1.4352, + "step": 4563 + }, + { + "epoch": 0.48, + "learning_rate": 1.246512473403866e-05, + "loss": 1.3935, + "step": 4564 + }, + { + "epoch": 0.48, + "learning_rate": 1.2461577275608243e-05, + "loss": 1.3798, + "step": 4565 + }, + { + "epoch": 0.48, + "learning_rate": 1.2458029487389718e-05, + "loss": 1.4039, + "step": 4566 + }, + { + "epoch": 0.48, + "learning_rate": 1.2454481369858397e-05, + "loss": 1.3723, + "step": 4567 + }, + { + "epoch": 0.48, + "learning_rate": 1.245093292348964e-05, + "loss": 1.3713, + "step": 4568 + }, + { + "epoch": 0.48, + "learning_rate": 1.2447384148758847e-05, + "loss": 1.4083, + "step": 4569 + }, + { + "epoch": 0.48, + "learning_rate": 1.244383504614146e-05, + "loss": 1.2811, + "step": 4570 + }, + { + "epoch": 0.48, + "learning_rate": 1.2440285616112968e-05, + "loss": 1.3509, + "step": 4571 + }, + { + "epoch": 0.48, + "learning_rate": 1.2436735859148905e-05, + "loss": 1.3481, + "step": 4572 + }, + { + "epoch": 0.48, + "learning_rate": 1.2433185775724847e-05, + "loss": 1.4168, + "step": 4573 + }, + { + "epoch": 0.48, + "learning_rate": 1.2429635366316418e-05, + "loss": 1.3671, + "step": 4574 + }, + { + "epoch": 0.48, + "learning_rate": 1.2426084631399271e-05, + "loss": 1.6514, + "step": 4575 + }, + { + "epoch": 0.48, + "learning_rate": 1.2422533571449123e-05, + "loss": 1.3564, + "step": 4576 + }, + { + "epoch": 0.48, + "learning_rate": 1.2418982186941721e-05, + "loss": 1.4586, + "step": 4577 + }, + { + "epoch": 0.48, + "eval_loss": 1.4425245523452759, + "eval_runtime": 77.3853, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 4577 + }, + { + "epoch": 0.48, + "learning_rate": 1.2415430478352858e-05, + "loss": 1.3922, + "step": 4578 + }, + { + "epoch": 0.48, + "learning_rate": 1.2411878446158374e-05, + "loss": 1.3903, + "step": 4579 + }, + { + "epoch": 0.48, + "learning_rate": 1.240832609083415e-05, + "loss": 1.3537, + "step": 4580 + }, + { + "epoch": 0.48, + "learning_rate": 1.2404773412856113e-05, + "loss": 1.356, + "step": 4581 + }, + { + "epoch": 0.48, + "learning_rate": 1.2401220412700223e-05, + "loss": 1.4483, + "step": 4582 + }, + { + "epoch": 0.48, + "learning_rate": 1.2397667090842496e-05, + "loss": 1.3926, + "step": 4583 + }, + { + "epoch": 0.48, + "learning_rate": 1.2394113447758986e-05, + "loss": 1.4816, + "step": 4584 + }, + { + "epoch": 0.48, + "learning_rate": 1.2390559483925788e-05, + "loss": 1.3742, + "step": 4585 + }, + { + "epoch": 0.48, + "learning_rate": 1.2387005199819044e-05, + "loss": 1.4476, + "step": 4586 + }, + { + "epoch": 0.48, + "learning_rate": 1.2383450595914932e-05, + "loss": 1.4029, + "step": 4587 + }, + { + "epoch": 0.48, + "learning_rate": 1.2379895672689683e-05, + "loss": 1.4797, + "step": 4588 + }, + { + "epoch": 0.48, + "learning_rate": 1.2376340430619565e-05, + "loss": 1.3366, + "step": 4589 + }, + { + "epoch": 0.48, + "learning_rate": 1.2372784870180885e-05, + "loss": 1.4226, + "step": 4590 + }, + { + "epoch": 0.48, + "learning_rate": 1.2369228991849997e-05, + "loss": 1.3668, + "step": 4591 + }, + { + "epoch": 0.48, + "learning_rate": 1.2365672796103305e-05, + "loss": 1.4932, + "step": 4592 + }, + { + "epoch": 0.48, + "learning_rate": 1.236211628341724e-05, + "loss": 1.4088, + "step": 4593 + }, + { + "epoch": 0.48, + "learning_rate": 1.2358559454268284e-05, + "loss": 1.3616, + "step": 4594 + }, + { + "epoch": 0.48, + "learning_rate": 1.2355002309132961e-05, + "loss": 1.4345, + "step": 4595 + }, + { + "epoch": 0.48, + "learning_rate": 1.2351444848487844e-05, + "loss": 1.4025, + "step": 4596 + }, + { + "epoch": 0.48, + "learning_rate": 1.2347887072809533e-05, + "loss": 1.3895, + "step": 4597 + }, + { + "epoch": 0.48, + "learning_rate": 1.2344328982574678e-05, + "loss": 1.3326, + "step": 4598 + }, + { + "epoch": 0.48, + "learning_rate": 1.234077057825998e-05, + "loss": 1.4249, + "step": 4599 + }, + { + "epoch": 0.48, + "learning_rate": 1.2337211860342167e-05, + "loss": 1.3649, + "step": 4600 + }, + { + "epoch": 0.48, + "learning_rate": 1.2333652829298016e-05, + "loss": 1.3831, + "step": 4601 + }, + { + "epoch": 0.48, + "learning_rate": 1.2330093485604346e-05, + "loss": 1.3748, + "step": 4602 + }, + { + "epoch": 0.48, + "learning_rate": 1.2326533829738022e-05, + "loss": 1.386, + "step": 4603 + }, + { + "epoch": 0.48, + "learning_rate": 1.2322973862175941e-05, + "loss": 1.3923, + "step": 4604 + }, + { + "epoch": 0.48, + "learning_rate": 1.2319413583395052e-05, + "loss": 1.3638, + "step": 4605 + }, + { + "epoch": 0.48, + "learning_rate": 1.2315852993872335e-05, + "loss": 1.3476, + "step": 4606 + }, + { + "epoch": 0.48, + "learning_rate": 1.2312292094084824e-05, + "loss": 1.3581, + "step": 4607 + }, + { + "epoch": 0.48, + "learning_rate": 1.2308730884509583e-05, + "loss": 1.3554, + "step": 4608 + }, + { + "epoch": 0.48, + "learning_rate": 1.2305169365623724e-05, + "loss": 1.3676, + "step": 4609 + }, + { + "epoch": 0.48, + "learning_rate": 1.2301607537904399e-05, + "loss": 1.24, + "step": 4610 + }, + { + "epoch": 0.48, + "learning_rate": 1.2298045401828803e-05, + "loss": 1.3295, + "step": 4611 + }, + { + "epoch": 0.48, + "learning_rate": 1.2294482957874169e-05, + "loss": 1.5684, + "step": 4612 + }, + { + "epoch": 0.48, + "learning_rate": 1.2290920206517774e-05, + "loss": 1.3403, + "step": 4613 + }, + { + "epoch": 0.48, + "learning_rate": 1.2287357148236933e-05, + "loss": 1.349, + "step": 4614 + }, + { + "epoch": 0.48, + "learning_rate": 1.2283793783509008e-05, + "loss": 1.4261, + "step": 4615 + }, + { + "epoch": 0.48, + "learning_rate": 1.2280230112811395e-05, + "loss": 1.322, + "step": 4616 + }, + { + "epoch": 0.48, + "learning_rate": 1.2276666136621538e-05, + "loss": 1.3399, + "step": 4617 + }, + { + "epoch": 0.48, + "learning_rate": 1.2273101855416912e-05, + "loss": 1.3878, + "step": 4618 + }, + { + "epoch": 0.48, + "learning_rate": 1.2269537269675044e-05, + "loss": 1.4733, + "step": 4619 + }, + { + "epoch": 0.48, + "learning_rate": 1.2265972379873497e-05, + "loss": 1.419, + "step": 4620 + }, + { + "epoch": 0.48, + "learning_rate": 1.226240718648987e-05, + "loss": 1.3918, + "step": 4621 + }, + { + "epoch": 0.48, + "learning_rate": 1.2258841690001815e-05, + "loss": 1.3398, + "step": 4622 + }, + { + "epoch": 0.48, + "learning_rate": 1.225527589088701e-05, + "loss": 1.4091, + "step": 4623 + }, + { + "epoch": 0.48, + "learning_rate": 1.2251709789623185e-05, + "loss": 1.3291, + "step": 4624 + }, + { + "epoch": 0.49, + "learning_rate": 1.2248143386688101e-05, + "loss": 1.4288, + "step": 4625 + }, + { + "epoch": 0.49, + "learning_rate": 1.224457668255957e-05, + "loss": 1.2942, + "step": 4626 + }, + { + "epoch": 0.49, + "learning_rate": 1.2241009677715437e-05, + "loss": 1.4014, + "step": 4627 + }, + { + "epoch": 0.49, + "learning_rate": 1.2237442372633586e-05, + "loss": 1.3823, + "step": 4628 + }, + { + "epoch": 0.49, + "learning_rate": 1.2233874767791945e-05, + "loss": 1.3556, + "step": 4629 + }, + { + "epoch": 0.49, + "learning_rate": 1.2230306863668485e-05, + "loss": 1.411, + "step": 4630 + }, + { + "epoch": 0.49, + "learning_rate": 1.2226738660741212e-05, + "loss": 1.4347, + "step": 4631 + }, + { + "epoch": 0.49, + "learning_rate": 1.2223170159488169e-05, + "loss": 1.3095, + "step": 4632 + }, + { + "epoch": 0.49, + "learning_rate": 1.221960136038745e-05, + "loss": 1.4272, + "step": 4633 + }, + { + "epoch": 0.49, + "learning_rate": 1.221603226391718e-05, + "loss": 1.367, + "step": 4634 + }, + { + "epoch": 0.49, + "learning_rate": 1.2212462870555523e-05, + "loss": 1.3357, + "step": 4635 + }, + { + "epoch": 0.49, + "learning_rate": 1.220889318078069e-05, + "loss": 1.3634, + "step": 4636 + }, + { + "epoch": 0.49, + "learning_rate": 1.2205323195070927e-05, + "loss": 1.4143, + "step": 4637 + }, + { + "epoch": 0.49, + "learning_rate": 1.2201752913904519e-05, + "loss": 1.4865, + "step": 4638 + }, + { + "epoch": 0.49, + "learning_rate": 1.2198182337759794e-05, + "loss": 1.451, + "step": 4639 + }, + { + "epoch": 0.49, + "learning_rate": 1.2194611467115116e-05, + "loss": 1.3953, + "step": 4640 + }, + { + "epoch": 0.49, + "learning_rate": 1.2191040302448887e-05, + "loss": 1.4099, + "step": 4641 + }, + { + "epoch": 0.49, + "learning_rate": 1.2187468844239559e-05, + "loss": 1.3338, + "step": 4642 + }, + { + "epoch": 0.49, + "learning_rate": 1.2183897092965609e-05, + "loss": 1.4392, + "step": 4643 + }, + { + "epoch": 0.49, + "learning_rate": 1.2180325049105559e-05, + "loss": 1.3196, + "step": 4644 + }, + { + "epoch": 0.49, + "learning_rate": 1.2176752713137977e-05, + "loss": 1.3727, + "step": 4645 + }, + { + "epoch": 0.49, + "learning_rate": 1.2173180085541464e-05, + "loss": 1.3118, + "step": 4646 + }, + { + "epoch": 0.49, + "learning_rate": 1.2169607166794655e-05, + "loss": 1.3695, + "step": 4647 + }, + { + "epoch": 0.49, + "learning_rate": 1.2166033957376231e-05, + "loss": 1.3568, + "step": 4648 + }, + { + "epoch": 0.49, + "learning_rate": 1.216246045776491e-05, + "loss": 1.3492, + "step": 4649 + }, + { + "epoch": 0.49, + "learning_rate": 1.2158886668439455e-05, + "loss": 1.3445, + "step": 4650 + }, + { + "epoch": 0.49, + "learning_rate": 1.2155312589878654e-05, + "loss": 1.3756, + "step": 4651 + }, + { + "epoch": 0.49, + "learning_rate": 1.2151738222561344e-05, + "loss": 1.3681, + "step": 4652 + }, + { + "epoch": 0.49, + "learning_rate": 1.2148163566966403e-05, + "loss": 1.4345, + "step": 4653 + }, + { + "epoch": 0.49, + "learning_rate": 1.2144588623572738e-05, + "loss": 1.5102, + "step": 4654 + }, + { + "epoch": 0.49, + "learning_rate": 1.2141013392859297e-05, + "loss": 1.3531, + "step": 4655 + }, + { + "epoch": 0.49, + "learning_rate": 1.2137437875305075e-05, + "loss": 1.3824, + "step": 4656 + }, + { + "epoch": 0.49, + "learning_rate": 1.2133862071389099e-05, + "loss": 1.4227, + "step": 4657 + }, + { + "epoch": 0.49, + "learning_rate": 1.2130285981590433e-05, + "loss": 1.3479, + "step": 4658 + }, + { + "epoch": 0.49, + "learning_rate": 1.2126709606388181e-05, + "loss": 1.381, + "step": 4659 + }, + { + "epoch": 0.49, + "learning_rate": 1.2123132946261485e-05, + "loss": 1.3847, + "step": 4660 + }, + { + "epoch": 0.49, + "learning_rate": 1.2119556001689527e-05, + "loss": 1.3549, + "step": 4661 + }, + { + "epoch": 0.49, + "learning_rate": 1.2115978773151527e-05, + "loss": 1.3754, + "step": 4662 + }, + { + "epoch": 0.49, + "learning_rate": 1.2112401261126736e-05, + "loss": 1.3329, + "step": 4663 + }, + { + "epoch": 0.49, + "learning_rate": 1.2108823466094453e-05, + "loss": 1.4228, + "step": 4664 + }, + { + "epoch": 0.49, + "learning_rate": 1.2105245388534013e-05, + "loss": 1.4138, + "step": 4665 + }, + { + "epoch": 0.49, + "learning_rate": 1.2101667028924782e-05, + "loss": 1.3538, + "step": 4666 + }, + { + "epoch": 0.49, + "learning_rate": 1.2098088387746168e-05, + "loss": 1.4848, + "step": 4667 + }, + { + "epoch": 0.49, + "learning_rate": 1.2094509465477619e-05, + "loss": 1.5719, + "step": 4668 + }, + { + "epoch": 0.49, + "learning_rate": 1.209093026259862e-05, + "loss": 1.3863, + "step": 4669 + }, + { + "epoch": 0.49, + "learning_rate": 1.2087350779588691e-05, + "loss": 1.4425, + "step": 4670 + }, + { + "epoch": 0.49, + "learning_rate": 1.2083771016927386e-05, + "loss": 1.3655, + "step": 4671 + }, + { + "epoch": 0.49, + "learning_rate": 1.208019097509431e-05, + "loss": 1.3629, + "step": 4672 + }, + { + "epoch": 0.49, + "learning_rate": 1.2076610654569092e-05, + "loss": 1.3849, + "step": 4673 + }, + { + "epoch": 0.49, + "learning_rate": 1.20730300558314e-05, + "loss": 1.3763, + "step": 4674 + }, + { + "epoch": 0.49, + "learning_rate": 1.2069449179360945e-05, + "loss": 1.5316, + "step": 4675 + }, + { + "epoch": 0.49, + "learning_rate": 1.2065868025637476e-05, + "loss": 1.2873, + "step": 4676 + }, + { + "epoch": 0.49, + "learning_rate": 1.2062286595140773e-05, + "loss": 1.3642, + "step": 4677 + }, + { + "epoch": 0.49, + "learning_rate": 1.2058704888350652e-05, + "loss": 1.3782, + "step": 4678 + }, + { + "epoch": 0.49, + "learning_rate": 1.2055122905746972e-05, + "loss": 1.4597, + "step": 4679 + }, + { + "epoch": 0.49, + "learning_rate": 1.205154064780963e-05, + "loss": 1.3952, + "step": 4680 + }, + { + "epoch": 0.49, + "learning_rate": 1.2047958115018554e-05, + "loss": 1.4012, + "step": 4681 + }, + { + "epoch": 0.49, + "learning_rate": 1.204437530785371e-05, + "loss": 1.3432, + "step": 4682 + }, + { + "epoch": 0.49, + "learning_rate": 1.2040792226795101e-05, + "loss": 1.4111, + "step": 4683 + }, + { + "epoch": 0.49, + "learning_rate": 1.2037208872322773e-05, + "loss": 1.4357, + "step": 4684 + }, + { + "epoch": 0.49, + "learning_rate": 1.2033625244916803e-05, + "loss": 1.3908, + "step": 4685 + }, + { + "epoch": 0.49, + "learning_rate": 1.2030041345057298e-05, + "loss": 1.3804, + "step": 4686 + }, + { + "epoch": 0.49, + "learning_rate": 1.2026457173224412e-05, + "loss": 1.4523, + "step": 4687 + }, + { + "epoch": 0.49, + "learning_rate": 1.2022872729898336e-05, + "loss": 1.4266, + "step": 4688 + }, + { + "epoch": 0.49, + "learning_rate": 1.201928801555929e-05, + "loss": 1.3345, + "step": 4689 + }, + { + "epoch": 0.49, + "learning_rate": 1.2015703030687532e-05, + "loss": 1.1714, + "step": 4690 + }, + { + "epoch": 0.49, + "learning_rate": 1.2012117775763361e-05, + "loss": 1.3899, + "step": 4691 + }, + { + "epoch": 0.49, + "learning_rate": 1.2008532251267109e-05, + "loss": 1.43, + "step": 4692 + }, + { + "epoch": 0.49, + "learning_rate": 1.2004946457679144e-05, + "loss": 1.4302, + "step": 4693 + }, + { + "epoch": 0.49, + "learning_rate": 1.2001360395479865e-05, + "loss": 1.3452, + "step": 4694 + }, + { + "epoch": 0.49, + "learning_rate": 1.1997774065149716e-05, + "loss": 1.3383, + "step": 4695 + }, + { + "epoch": 0.49, + "learning_rate": 1.1994187467169176e-05, + "loss": 1.3677, + "step": 4696 + }, + { + "epoch": 0.49, + "learning_rate": 1.1990600602018755e-05, + "loss": 1.4486, + "step": 4697 + }, + { + "epoch": 0.49, + "learning_rate": 1.1987013470178998e-05, + "loss": 1.4059, + "step": 4698 + }, + { + "epoch": 0.49, + "learning_rate": 1.198342607213049e-05, + "loss": 1.3558, + "step": 4699 + }, + { + "epoch": 0.49, + "learning_rate": 1.1979838408353854e-05, + "loss": 1.3931, + "step": 4700 + }, + { + "epoch": 0.49, + "learning_rate": 1.197625047932974e-05, + "loss": 1.5409, + "step": 4701 + }, + { + "epoch": 0.49, + "learning_rate": 1.197266228553884e-05, + "loss": 1.4878, + "step": 4702 + }, + { + "epoch": 0.49, + "learning_rate": 1.196907382746188e-05, + "loss": 1.3581, + "step": 4703 + }, + { + "epoch": 0.49, + "learning_rate": 1.1965485105579621e-05, + "loss": 1.3617, + "step": 4704 + }, + { + "epoch": 0.49, + "learning_rate": 1.1961896120372857e-05, + "loss": 1.399, + "step": 4705 + }, + { + "epoch": 0.49, + "learning_rate": 1.1958306872322425e-05, + "loss": 1.3861, + "step": 4706 + }, + { + "epoch": 0.49, + "learning_rate": 1.1954717361909186e-05, + "loss": 1.4719, + "step": 4707 + }, + { + "epoch": 0.49, + "learning_rate": 1.195112758961405e-05, + "loss": 1.393, + "step": 4708 + }, + { + "epoch": 0.49, + "learning_rate": 1.1947537555917947e-05, + "loss": 1.4252, + "step": 4709 + }, + { + "epoch": 0.49, + "learning_rate": 1.194394726130185e-05, + "loss": 1.4187, + "step": 4710 + }, + { + "epoch": 0.49, + "learning_rate": 1.1940356706246772e-05, + "loss": 1.4822, + "step": 4711 + }, + { + "epoch": 0.49, + "learning_rate": 1.193676589123375e-05, + "loss": 1.4259, + "step": 4712 + }, + { + "epoch": 0.49, + "learning_rate": 1.1933174816743857e-05, + "loss": 1.4226, + "step": 4713 + }, + { + "epoch": 0.49, + "learning_rate": 1.1929583483258216e-05, + "loss": 1.3701, + "step": 4714 + }, + { + "epoch": 0.49, + "learning_rate": 1.1925991891257967e-05, + "loss": 1.406, + "step": 4715 + }, + { + "epoch": 0.49, + "learning_rate": 1.1922400041224288e-05, + "loss": 1.4593, + "step": 4716 + }, + { + "epoch": 0.49, + "learning_rate": 1.1918807933638401e-05, + "loss": 1.3443, + "step": 4717 + }, + { + "epoch": 0.49, + "learning_rate": 1.1915215568981552e-05, + "loss": 1.3523, + "step": 4718 + }, + { + "epoch": 0.49, + "learning_rate": 1.1911622947735027e-05, + "loss": 1.3175, + "step": 4719 + }, + { + "epoch": 0.49, + "learning_rate": 1.1908030070380143e-05, + "loss": 1.3974, + "step": 4720 + }, + { + "epoch": 0.5, + "learning_rate": 1.1904436937398257e-05, + "loss": 1.386, + "step": 4721 + }, + { + "epoch": 0.5, + "learning_rate": 1.1900843549270753e-05, + "loss": 1.3684, + "step": 4722 + }, + { + "epoch": 0.5, + "learning_rate": 1.1897249906479054e-05, + "loss": 1.383, + "step": 4723 + }, + { + "epoch": 0.5, + "learning_rate": 1.1893656009504617e-05, + "loss": 1.38, + "step": 4724 + }, + { + "epoch": 0.5, + "learning_rate": 1.1890061858828928e-05, + "loss": 1.3844, + "step": 4725 + }, + { + "epoch": 0.5, + "learning_rate": 1.1886467454933515e-05, + "loss": 1.3252, + "step": 4726 + }, + { + "epoch": 0.5, + "learning_rate": 1.1882872798299934e-05, + "loss": 1.3434, + "step": 4727 + }, + { + "epoch": 0.5, + "learning_rate": 1.1879277889409779e-05, + "loss": 1.4115, + "step": 4728 + }, + { + "epoch": 0.5, + "learning_rate": 1.1875682728744669e-05, + "loss": 1.1911, + "step": 4729 + }, + { + "epoch": 0.5, + "learning_rate": 1.1872087316786272e-05, + "loss": 1.2794, + "step": 4730 + }, + { + "epoch": 0.5, + "learning_rate": 1.1868491654016274e-05, + "loss": 1.3961, + "step": 4731 + }, + { + "epoch": 0.5, + "learning_rate": 1.1864895740916404e-05, + "loss": 1.4965, + "step": 4732 + }, + { + "epoch": 0.5, + "learning_rate": 1.1861299577968419e-05, + "loss": 1.3932, + "step": 4733 + }, + { + "epoch": 0.5, + "learning_rate": 1.185770316565412e-05, + "loss": 1.3926, + "step": 4734 + }, + { + "epoch": 0.5, + "learning_rate": 1.1854106504455327e-05, + "loss": 1.3964, + "step": 4735 + }, + { + "epoch": 0.5, + "learning_rate": 1.1850509594853901e-05, + "loss": 1.3666, + "step": 4736 + }, + { + "epoch": 0.5, + "learning_rate": 1.1846912437331736e-05, + "loss": 1.4364, + "step": 4737 + }, + { + "epoch": 0.5, + "learning_rate": 1.1843315032370762e-05, + "loss": 1.3537, + "step": 4738 + }, + { + "epoch": 0.5, + "learning_rate": 1.1839717380452935e-05, + "loss": 1.4083, + "step": 4739 + }, + { + "epoch": 0.5, + "learning_rate": 1.1836119482060247e-05, + "loss": 1.3881, + "step": 4740 + }, + { + "epoch": 0.5, + "learning_rate": 1.1832521337674727e-05, + "loss": 1.4127, + "step": 4741 + }, + { + "epoch": 0.5, + "learning_rate": 1.1828922947778436e-05, + "loss": 1.3433, + "step": 4742 + }, + { + "epoch": 0.5, + "learning_rate": 1.1825324312853461e-05, + "loss": 1.486, + "step": 4743 + }, + { + "epoch": 0.5, + "learning_rate": 1.1821725433381925e-05, + "loss": 1.335, + "step": 4744 + }, + { + "epoch": 0.5, + "learning_rate": 1.1818126309845993e-05, + "loss": 1.3827, + "step": 4745 + }, + { + "epoch": 0.5, + "learning_rate": 1.181452694272785e-05, + "loss": 1.3146, + "step": 4746 + }, + { + "epoch": 0.5, + "learning_rate": 1.1810927332509717e-05, + "loss": 1.3543, + "step": 4747 + }, + { + "epoch": 0.5, + "learning_rate": 1.1807327479673852e-05, + "loss": 1.3544, + "step": 4748 + }, + { + "epoch": 0.5, + "learning_rate": 1.1803727384702543e-05, + "loss": 1.3677, + "step": 4749 + }, + { + "epoch": 0.5, + "learning_rate": 1.1800127048078111e-05, + "loss": 1.3842, + "step": 4750 + }, + { + "epoch": 0.5, + "learning_rate": 1.1796526470282907e-05, + "loss": 1.3495, + "step": 4751 + }, + { + "epoch": 0.5, + "learning_rate": 1.1792925651799314e-05, + "loss": 1.481, + "step": 4752 + }, + { + "epoch": 0.5, + "learning_rate": 1.1789324593109754e-05, + "loss": 1.3482, + "step": 4753 + }, + { + "epoch": 0.5, + "learning_rate": 1.1785723294696673e-05, + "loss": 1.2805, + "step": 4754 + }, + { + "epoch": 0.5, + "learning_rate": 1.1782121757042555e-05, + "loss": 1.3458, + "step": 4755 + }, + { + "epoch": 0.5, + "learning_rate": 1.1778519980629907e-05, + "loss": 1.3937, + "step": 4756 + }, + { + "epoch": 0.5, + "learning_rate": 1.1774917965941284e-05, + "loss": 1.3873, + "step": 4757 + }, + { + "epoch": 0.5, + "learning_rate": 1.1771315713459258e-05, + "loss": 1.3512, + "step": 4758 + }, + { + "epoch": 0.5, + "learning_rate": 1.1767713223666436e-05, + "loss": 1.4465, + "step": 4759 + }, + { + "epoch": 0.5, + "learning_rate": 1.1764110497045463e-05, + "loss": 1.4233, + "step": 4760 + }, + { + "epoch": 0.5, + "learning_rate": 1.1760507534079011e-05, + "loss": 1.4818, + "step": 4761 + }, + { + "epoch": 0.5, + "learning_rate": 1.1756904335249786e-05, + "loss": 1.2933, + "step": 4762 + }, + { + "epoch": 0.5, + "learning_rate": 1.1753300901040518e-05, + "loss": 1.3524, + "step": 4763 + }, + { + "epoch": 0.5, + "learning_rate": 1.1749697231933981e-05, + "loss": 1.4909, + "step": 4764 + }, + { + "epoch": 0.5, + "learning_rate": 1.1746093328412975e-05, + "loss": 1.2912, + "step": 4765 + }, + { + "epoch": 0.5, + "learning_rate": 1.1742489190960325e-05, + "loss": 1.3372, + "step": 4766 + }, + { + "epoch": 0.5, + "learning_rate": 1.1738884820058893e-05, + "loss": 1.3036, + "step": 4767 + }, + { + "epoch": 0.5, + "learning_rate": 1.1735280216191578e-05, + "loss": 1.3189, + "step": 4768 + }, + { + "epoch": 0.5, + "learning_rate": 1.1731675379841298e-05, + "loss": 1.4146, + "step": 4769 + }, + { + "epoch": 0.5, + "learning_rate": 1.1728070311491013e-05, + "loss": 1.3309, + "step": 4770 + }, + { + "epoch": 0.5, + "learning_rate": 1.1724465011623705e-05, + "loss": 1.3427, + "step": 4771 + }, + { + "epoch": 0.5, + "learning_rate": 1.1720859480722395e-05, + "loss": 1.4033, + "step": 4772 + }, + { + "epoch": 0.5, + "learning_rate": 1.1717253719270135e-05, + "loss": 1.3832, + "step": 4773 + }, + { + "epoch": 0.5, + "learning_rate": 1.1713647727749994e-05, + "loss": 1.4074, + "step": 4774 + }, + { + "epoch": 0.5, + "learning_rate": 1.1710041506645092e-05, + "loss": 1.3579, + "step": 4775 + }, + { + "epoch": 0.5, + "learning_rate": 1.1706435056438564e-05, + "loss": 1.3685, + "step": 4776 + }, + { + "epoch": 0.5, + "eval_loss": 1.436767816543579, + "eval_runtime": 77.4332, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4776 + }, + { + "epoch": 0.5, + "learning_rate": 1.1702828377613584e-05, + "loss": 1.5843, + "step": 4777 + }, + { + "epoch": 0.5, + "learning_rate": 1.1699221470653355e-05, + "loss": 1.4168, + "step": 4778 + }, + { + "epoch": 0.5, + "learning_rate": 1.1695614336041108e-05, + "loss": 1.3515, + "step": 4779 + }, + { + "epoch": 0.5, + "learning_rate": 1.169200697426011e-05, + "loss": 1.3214, + "step": 4780 + }, + { + "epoch": 0.5, + "learning_rate": 1.1688399385793652e-05, + "loss": 1.3728, + "step": 4781 + }, + { + "epoch": 0.5, + "learning_rate": 1.1684791571125054e-05, + "loss": 1.3759, + "step": 4782 + }, + { + "epoch": 0.5, + "learning_rate": 1.1681183530737678e-05, + "loss": 1.4955, + "step": 4783 + }, + { + "epoch": 0.5, + "learning_rate": 1.1677575265114904e-05, + "loss": 1.4284, + "step": 4784 + }, + { + "epoch": 0.5, + "learning_rate": 1.1673966774740151e-05, + "loss": 1.3725, + "step": 4785 + }, + { + "epoch": 0.5, + "learning_rate": 1.1670358060096858e-05, + "loss": 1.3612, + "step": 4786 + }, + { + "epoch": 0.5, + "learning_rate": 1.1666749121668506e-05, + "loss": 1.3021, + "step": 4787 + }, + { + "epoch": 0.5, + "learning_rate": 1.1663139959938597e-05, + "loss": 1.4399, + "step": 4788 + }, + { + "epoch": 0.5, + "learning_rate": 1.1659530575390668e-05, + "loss": 1.3511, + "step": 4789 + }, + { + "epoch": 0.5, + "learning_rate": 1.1655920968508276e-05, + "loss": 1.4211, + "step": 4790 + }, + { + "epoch": 0.5, + "learning_rate": 1.1652311139775028e-05, + "loss": 1.343, + "step": 4791 + }, + { + "epoch": 0.5, + "learning_rate": 1.1648701089674541e-05, + "loss": 1.3838, + "step": 4792 + }, + { + "epoch": 0.5, + "learning_rate": 1.164509081869047e-05, + "loss": 1.342, + "step": 4793 + }, + { + "epoch": 0.5, + "learning_rate": 1.1641480327306494e-05, + "loss": 1.3831, + "step": 4794 + }, + { + "epoch": 0.5, + "learning_rate": 1.1637869616006335e-05, + "loss": 1.4102, + "step": 4795 + }, + { + "epoch": 0.5, + "learning_rate": 1.1634258685273732e-05, + "loss": 1.4184, + "step": 4796 + }, + { + "epoch": 0.5, + "learning_rate": 1.1630647535592455e-05, + "loss": 1.3974, + "step": 4797 + }, + { + "epoch": 0.5, + "learning_rate": 1.1627036167446302e-05, + "loss": 1.251, + "step": 4798 + }, + { + "epoch": 0.5, + "learning_rate": 1.1623424581319113e-05, + "loss": 1.3485, + "step": 4799 + }, + { + "epoch": 0.5, + "learning_rate": 1.1619812777694742e-05, + "loss": 1.3544, + "step": 4800 + }, + { + "epoch": 0.5, + "learning_rate": 1.1616200757057076e-05, + "loss": 1.3772, + "step": 4801 + }, + { + "epoch": 0.5, + "learning_rate": 1.1612588519890038e-05, + "loss": 1.3082, + "step": 4802 + }, + { + "epoch": 0.5, + "learning_rate": 1.160897606667757e-05, + "loss": 1.3634, + "step": 4803 + }, + { + "epoch": 0.5, + "learning_rate": 1.1605363397903655e-05, + "loss": 1.3682, + "step": 4804 + }, + { + "epoch": 0.5, + "learning_rate": 1.1601750514052288e-05, + "loss": 1.3258, + "step": 4805 + }, + { + "epoch": 0.5, + "learning_rate": 1.1598137415607511e-05, + "loss": 1.279, + "step": 4806 + }, + { + "epoch": 0.5, + "learning_rate": 1.1594524103053382e-05, + "loss": 1.3759, + "step": 4807 + }, + { + "epoch": 0.5, + "learning_rate": 1.1590910576873995e-05, + "loss": 1.5404, + "step": 4808 + }, + { + "epoch": 0.5, + "learning_rate": 1.1587296837553463e-05, + "loss": 1.4949, + "step": 4809 + }, + { + "epoch": 0.5, + "learning_rate": 1.1583682885575943e-05, + "loss": 1.3501, + "step": 4810 + }, + { + "epoch": 0.5, + "learning_rate": 1.1580068721425608e-05, + "loss": 1.3898, + "step": 4811 + }, + { + "epoch": 0.5, + "learning_rate": 1.157645434558666e-05, + "loss": 1.3265, + "step": 4812 + }, + { + "epoch": 0.5, + "learning_rate": 1.1572839758543338e-05, + "loss": 1.3454, + "step": 4813 + }, + { + "epoch": 0.5, + "learning_rate": 1.1569224960779899e-05, + "loss": 1.4065, + "step": 4814 + }, + { + "epoch": 0.5, + "learning_rate": 1.156560995278064e-05, + "loss": 1.4932, + "step": 4815 + }, + { + "epoch": 0.51, + "learning_rate": 1.156199473502987e-05, + "loss": 1.4224, + "step": 4816 + }, + { + "epoch": 0.51, + "learning_rate": 1.1558379308011937e-05, + "loss": 1.3884, + "step": 4817 + }, + { + "epoch": 0.51, + "learning_rate": 1.1554763672211222e-05, + "loss": 1.3355, + "step": 4818 + }, + { + "epoch": 0.51, + "learning_rate": 1.1551147828112124e-05, + "loss": 1.4281, + "step": 4819 + }, + { + "epoch": 0.51, + "learning_rate": 1.1547531776199072e-05, + "loss": 1.3148, + "step": 4820 + }, + { + "epoch": 0.51, + "learning_rate": 1.1543915516956523e-05, + "loss": 1.3255, + "step": 4821 + }, + { + "epoch": 0.51, + "learning_rate": 1.1540299050868966e-05, + "loss": 1.3361, + "step": 4822 + }, + { + "epoch": 0.51, + "learning_rate": 1.1536682378420912e-05, + "loss": 1.3377, + "step": 4823 + }, + { + "epoch": 0.51, + "learning_rate": 1.1533065500096901e-05, + "loss": 1.4205, + "step": 4824 + }, + { + "epoch": 0.51, + "learning_rate": 1.1529448416381505e-05, + "loss": 1.4193, + "step": 4825 + }, + { + "epoch": 0.51, + "learning_rate": 1.1525831127759322e-05, + "loss": 1.37, + "step": 4826 + }, + { + "epoch": 0.51, + "learning_rate": 1.1522213634714971e-05, + "loss": 1.3642, + "step": 4827 + }, + { + "epoch": 0.51, + "learning_rate": 1.1518595937733103e-05, + "loss": 1.4834, + "step": 4828 + }, + { + "epoch": 0.51, + "learning_rate": 1.1514978037298402e-05, + "loss": 1.2864, + "step": 4829 + }, + { + "epoch": 0.51, + "learning_rate": 1.1511359933895567e-05, + "loss": 1.3468, + "step": 4830 + }, + { + "epoch": 0.51, + "learning_rate": 1.1507741628009337e-05, + "loss": 1.328, + "step": 4831 + }, + { + "epoch": 0.51, + "learning_rate": 1.1504123120124466e-05, + "loss": 1.3489, + "step": 4832 + }, + { + "epoch": 0.51, + "learning_rate": 1.1500504410725746e-05, + "loss": 1.4031, + "step": 4833 + }, + { + "epoch": 0.51, + "learning_rate": 1.149688550029799e-05, + "loss": 1.3482, + "step": 4834 + }, + { + "epoch": 0.51, + "learning_rate": 1.1493266389326037e-05, + "loss": 1.3674, + "step": 4835 + }, + { + "epoch": 0.51, + "learning_rate": 1.1489647078294753e-05, + "loss": 1.2895, + "step": 4836 + }, + { + "epoch": 0.51, + "learning_rate": 1.148602756768904e-05, + "loss": 1.4071, + "step": 4837 + }, + { + "epoch": 0.51, + "learning_rate": 1.1482407857993814e-05, + "loss": 1.5218, + "step": 4838 + }, + { + "epoch": 0.51, + "learning_rate": 1.1478787949694024e-05, + "loss": 1.4577, + "step": 4839 + }, + { + "epoch": 0.51, + "learning_rate": 1.1475167843274643e-05, + "loss": 1.3817, + "step": 4840 + }, + { + "epoch": 0.51, + "learning_rate": 1.1471547539220678e-05, + "loss": 1.3072, + "step": 4841 + }, + { + "epoch": 0.51, + "learning_rate": 1.146792703801715e-05, + "loss": 1.3737, + "step": 4842 + }, + { + "epoch": 0.51, + "learning_rate": 1.1464306340149119e-05, + "loss": 1.4001, + "step": 4843 + }, + { + "epoch": 0.51, + "learning_rate": 1.1460685446101658e-05, + "loss": 1.3963, + "step": 4844 + }, + { + "epoch": 0.51, + "learning_rate": 1.1457064356359882e-05, + "loss": 1.4061, + "step": 4845 + }, + { + "epoch": 0.51, + "learning_rate": 1.145344307140892e-05, + "loss": 1.4211, + "step": 4846 + }, + { + "epoch": 0.51, + "learning_rate": 1.144982159173393e-05, + "loss": 1.3197, + "step": 4847 + }, + { + "epoch": 0.51, + "learning_rate": 1.14461999178201e-05, + "loss": 1.3549, + "step": 4848 + }, + { + "epoch": 0.51, + "learning_rate": 1.1442578050152639e-05, + "loss": 1.3889, + "step": 4849 + }, + { + "epoch": 0.51, + "learning_rate": 1.1438955989216787e-05, + "loss": 1.3847, + "step": 4850 + }, + { + "epoch": 0.51, + "learning_rate": 1.1435333735497803e-05, + "loss": 1.3586, + "step": 4851 + }, + { + "epoch": 0.51, + "learning_rate": 1.1431711289480978e-05, + "loss": 1.503, + "step": 4852 + }, + { + "epoch": 0.51, + "learning_rate": 1.1428088651651627e-05, + "loss": 1.3654, + "step": 4853 + }, + { + "epoch": 0.51, + "learning_rate": 1.1424465822495092e-05, + "loss": 1.3741, + "step": 4854 + }, + { + "epoch": 0.51, + "learning_rate": 1.1420842802496737e-05, + "loss": 1.5437, + "step": 4855 + }, + { + "epoch": 0.51, + "learning_rate": 1.1417219592141953e-05, + "loss": 1.2179, + "step": 4856 + }, + { + "epoch": 0.51, + "learning_rate": 1.1413596191916159e-05, + "loss": 1.3939, + "step": 4857 + }, + { + "epoch": 0.51, + "learning_rate": 1.1409972602304796e-05, + "loss": 1.3383, + "step": 4858 + }, + { + "epoch": 0.51, + "learning_rate": 1.140634882379333e-05, + "loss": 1.3664, + "step": 4859 + }, + { + "epoch": 0.51, + "learning_rate": 1.1402724856867258e-05, + "loss": 1.4002, + "step": 4860 + }, + { + "epoch": 0.51, + "learning_rate": 1.1399100702012098e-05, + "loss": 1.2975, + "step": 4861 + }, + { + "epoch": 0.51, + "learning_rate": 1.1395476359713394e-05, + "loss": 1.3564, + "step": 4862 + }, + { + "epoch": 0.51, + "learning_rate": 1.1391851830456708e-05, + "loss": 1.3574, + "step": 4863 + }, + { + "epoch": 0.51, + "learning_rate": 1.1388227114727644e-05, + "loss": 1.3407, + "step": 4864 + }, + { + "epoch": 0.51, + "learning_rate": 1.1384602213011815e-05, + "loss": 1.3603, + "step": 4865 + }, + { + "epoch": 0.51, + "learning_rate": 1.1380977125794866e-05, + "loss": 1.3465, + "step": 4866 + }, + { + "epoch": 0.51, + "learning_rate": 1.1377351853562461e-05, + "loss": 1.3744, + "step": 4867 + }, + { + "epoch": 0.51, + "learning_rate": 1.1373726396800304e-05, + "loss": 1.3248, + "step": 4868 + }, + { + "epoch": 0.51, + "learning_rate": 1.1370100755994102e-05, + "loss": 1.3352, + "step": 4869 + }, + { + "epoch": 0.51, + "learning_rate": 1.1366474931629603e-05, + "loss": 1.3299, + "step": 4870 + }, + { + "epoch": 0.51, + "learning_rate": 1.1362848924192575e-05, + "loss": 1.344, + "step": 4871 + }, + { + "epoch": 0.51, + "learning_rate": 1.1359222734168809e-05, + "loss": 1.3209, + "step": 4872 + }, + { + "epoch": 0.51, + "learning_rate": 1.135559636204412e-05, + "loss": 1.3927, + "step": 4873 + }, + { + "epoch": 0.51, + "learning_rate": 1.1351969808304349e-05, + "loss": 1.3717, + "step": 4874 + }, + { + "epoch": 0.51, + "learning_rate": 1.1348343073435362e-05, + "loss": 1.3813, + "step": 4875 + }, + { + "epoch": 0.51, + "learning_rate": 1.1344716157923046e-05, + "loss": 1.236, + "step": 4876 + }, + { + "epoch": 0.51, + "learning_rate": 1.1341089062253319e-05, + "loss": 1.2591, + "step": 4877 + }, + { + "epoch": 0.51, + "learning_rate": 1.1337461786912112e-05, + "loss": 1.3211, + "step": 4878 + }, + { + "epoch": 0.51, + "learning_rate": 1.1333834332385394e-05, + "loss": 1.4534, + "step": 4879 + }, + { + "epoch": 0.51, + "learning_rate": 1.1330206699159145e-05, + "loss": 1.346, + "step": 4880 + }, + { + "epoch": 0.51, + "learning_rate": 1.132657888771938e-05, + "loss": 1.3952, + "step": 4881 + }, + { + "epoch": 0.51, + "learning_rate": 1.1322950898552125e-05, + "loss": 1.3008, + "step": 4882 + }, + { + "epoch": 0.51, + "learning_rate": 1.1319322732143445e-05, + "loss": 1.3201, + "step": 4883 + }, + { + "epoch": 0.51, + "learning_rate": 1.1315694388979416e-05, + "loss": 1.3761, + "step": 4884 + }, + { + "epoch": 0.51, + "learning_rate": 1.1312065869546147e-05, + "loss": 1.343, + "step": 4885 + }, + { + "epoch": 0.51, + "learning_rate": 1.1308437174329761e-05, + "loss": 1.3741, + "step": 4886 + }, + { + "epoch": 0.51, + "learning_rate": 1.1304808303816413e-05, + "loss": 1.402, + "step": 4887 + }, + { + "epoch": 0.51, + "learning_rate": 1.130117925849228e-05, + "loss": 1.3834, + "step": 4888 + }, + { + "epoch": 0.51, + "learning_rate": 1.1297550038843559e-05, + "loss": 1.3342, + "step": 4889 + }, + { + "epoch": 0.51, + "learning_rate": 1.1293920645356471e-05, + "loss": 1.3207, + "step": 4890 + }, + { + "epoch": 0.51, + "learning_rate": 1.1290291078517264e-05, + "loss": 1.4274, + "step": 4891 + }, + { + "epoch": 0.51, + "learning_rate": 1.1286661338812203e-05, + "loss": 1.328, + "step": 4892 + }, + { + "epoch": 0.51, + "learning_rate": 1.1283031426727584e-05, + "loss": 1.3823, + "step": 4893 + }, + { + "epoch": 0.51, + "learning_rate": 1.127940134274972e-05, + "loss": 1.3612, + "step": 4894 + }, + { + "epoch": 0.51, + "learning_rate": 1.127577108736495e-05, + "loss": 1.375, + "step": 4895 + }, + { + "epoch": 0.51, + "learning_rate": 1.1272140661059636e-05, + "loss": 1.3531, + "step": 4896 + }, + { + "epoch": 0.51, + "learning_rate": 1.1268510064320155e-05, + "loss": 1.3636, + "step": 4897 + }, + { + "epoch": 0.51, + "learning_rate": 1.1264879297632923e-05, + "loss": 1.3524, + "step": 4898 + }, + { + "epoch": 0.51, + "learning_rate": 1.1261248361484363e-05, + "loss": 1.3865, + "step": 4899 + }, + { + "epoch": 0.51, + "learning_rate": 1.125761725636093e-05, + "loss": 1.4069, + "step": 4900 + }, + { + "epoch": 0.51, + "learning_rate": 1.1253985982749098e-05, + "loss": 1.4643, + "step": 4901 + }, + { + "epoch": 0.51, + "learning_rate": 1.1250354541135364e-05, + "loss": 1.4506, + "step": 4902 + }, + { + "epoch": 0.51, + "learning_rate": 1.124672293200625e-05, + "loss": 1.3857, + "step": 4903 + }, + { + "epoch": 0.51, + "learning_rate": 1.1243091155848295e-05, + "loss": 1.3554, + "step": 4904 + }, + { + "epoch": 0.51, + "learning_rate": 1.1239459213148065e-05, + "loss": 1.4071, + "step": 4905 + }, + { + "epoch": 0.51, + "learning_rate": 1.1235827104392148e-05, + "loss": 1.3981, + "step": 4906 + }, + { + "epoch": 0.51, + "learning_rate": 1.1232194830067153e-05, + "loss": 1.4913, + "step": 4907 + }, + { + "epoch": 0.51, + "learning_rate": 1.1228562390659712e-05, + "loss": 1.3343, + "step": 4908 + }, + { + "epoch": 0.51, + "learning_rate": 1.1224929786656474e-05, + "loss": 1.3832, + "step": 4909 + }, + { + "epoch": 0.51, + "learning_rate": 1.122129701854412e-05, + "loss": 1.367, + "step": 4910 + }, + { + "epoch": 0.51, + "learning_rate": 1.1217664086809345e-05, + "loss": 1.4108, + "step": 4911 + }, + { + "epoch": 0.52, + "learning_rate": 1.1214030991938872e-05, + "loss": 1.3981, + "step": 4912 + }, + { + "epoch": 0.52, + "learning_rate": 1.1210397734419436e-05, + "loss": 1.5266, + "step": 4913 + }, + { + "epoch": 0.52, + "learning_rate": 1.1206764314737806e-05, + "loss": 1.337, + "step": 4914 + }, + { + "epoch": 0.52, + "learning_rate": 1.1203130733380765e-05, + "loss": 1.3784, + "step": 4915 + }, + { + "epoch": 0.52, + "learning_rate": 1.1199496990835117e-05, + "loss": 1.3048, + "step": 4916 + }, + { + "epoch": 0.52, + "learning_rate": 1.1195863087587692e-05, + "loss": 1.2977, + "step": 4917 + }, + { + "epoch": 0.52, + "learning_rate": 1.1192229024125344e-05, + "loss": 1.3304, + "step": 4918 + }, + { + "epoch": 0.52, + "learning_rate": 1.1188594800934938e-05, + "loss": 1.4102, + "step": 4919 + }, + { + "epoch": 0.52, + "learning_rate": 1.1184960418503366e-05, + "loss": 1.3932, + "step": 4920 + }, + { + "epoch": 0.52, + "learning_rate": 1.1181325877317547e-05, + "loss": 1.4985, + "step": 4921 + }, + { + "epoch": 0.52, + "learning_rate": 1.1177691177864415e-05, + "loss": 1.4596, + "step": 4922 + }, + { + "epoch": 0.52, + "learning_rate": 1.1174056320630924e-05, + "loss": 1.3559, + "step": 4923 + }, + { + "epoch": 0.52, + "learning_rate": 1.117042130610405e-05, + "loss": 1.4128, + "step": 4924 + }, + { + "epoch": 0.52, + "learning_rate": 1.1166786134770795e-05, + "loss": 1.3343, + "step": 4925 + }, + { + "epoch": 0.52, + "learning_rate": 1.116315080711818e-05, + "loss": 1.332, + "step": 4926 + }, + { + "epoch": 0.52, + "learning_rate": 1.115951532363324e-05, + "loss": 1.3616, + "step": 4927 + }, + { + "epoch": 0.52, + "learning_rate": 1.1155879684803041e-05, + "loss": 1.4074, + "step": 4928 + }, + { + "epoch": 0.52, + "learning_rate": 1.1152243891114665e-05, + "loss": 1.303, + "step": 4929 + }, + { + "epoch": 0.52, + "learning_rate": 1.1148607943055212e-05, + "loss": 1.4799, + "step": 4930 + }, + { + "epoch": 0.52, + "learning_rate": 1.1144971841111807e-05, + "loss": 1.3881, + "step": 4931 + }, + { + "epoch": 0.52, + "learning_rate": 1.1141335585771593e-05, + "loss": 1.338, + "step": 4932 + }, + { + "epoch": 0.52, + "learning_rate": 1.1137699177521738e-05, + "loss": 1.3289, + "step": 4933 + }, + { + "epoch": 0.52, + "learning_rate": 1.1134062616849426e-05, + "loss": 1.377, + "step": 4934 + }, + { + "epoch": 0.52, + "learning_rate": 1.1130425904241862e-05, + "loss": 1.3596, + "step": 4935 + }, + { + "epoch": 0.52, + "learning_rate": 1.112678904018627e-05, + "loss": 1.4264, + "step": 4936 + }, + { + "epoch": 0.52, + "learning_rate": 1.1123152025169898e-05, + "loss": 1.3526, + "step": 4937 + }, + { + "epoch": 0.52, + "learning_rate": 1.1119514859680016e-05, + "loss": 1.3271, + "step": 4938 + }, + { + "epoch": 0.52, + "learning_rate": 1.1115877544203905e-05, + "loss": 1.3907, + "step": 4939 + }, + { + "epoch": 0.52, + "learning_rate": 1.1112240079228878e-05, + "loss": 1.3415, + "step": 4940 + }, + { + "epoch": 0.52, + "learning_rate": 1.1108602465242258e-05, + "loss": 1.3875, + "step": 4941 + }, + { + "epoch": 0.52, + "learning_rate": 1.110496470273139e-05, + "loss": 1.3964, + "step": 4942 + }, + { + "epoch": 0.52, + "learning_rate": 1.1101326792183645e-05, + "loss": 1.3448, + "step": 4943 + }, + { + "epoch": 0.52, + "learning_rate": 1.1097688734086407e-05, + "loss": 1.3522, + "step": 4944 + }, + { + "epoch": 0.52, + "learning_rate": 1.1094050528927082e-05, + "loss": 1.2742, + "step": 4945 + }, + { + "epoch": 0.52, + "learning_rate": 1.1090412177193097e-05, + "loss": 1.417, + "step": 4946 + }, + { + "epoch": 0.52, + "learning_rate": 1.1086773679371898e-05, + "loss": 1.3993, + "step": 4947 + }, + { + "epoch": 0.52, + "learning_rate": 1.108313503595095e-05, + "loss": 1.3783, + "step": 4948 + }, + { + "epoch": 0.52, + "learning_rate": 1.1079496247417736e-05, + "loss": 1.3975, + "step": 4949 + }, + { + "epoch": 0.52, + "learning_rate": 1.1075857314259763e-05, + "loss": 1.4256, + "step": 4950 + }, + { + "epoch": 0.52, + "learning_rate": 1.1072218236964551e-05, + "loss": 1.3547, + "step": 4951 + }, + { + "epoch": 0.52, + "learning_rate": 1.106857901601965e-05, + "loss": 1.4243, + "step": 4952 + }, + { + "epoch": 0.52, + "learning_rate": 1.1064939651912612e-05, + "loss": 1.4259, + "step": 4953 + }, + { + "epoch": 0.52, + "learning_rate": 1.1061300145131027e-05, + "loss": 1.4323, + "step": 4954 + }, + { + "epoch": 0.52, + "learning_rate": 1.1057660496162488e-05, + "loss": 1.3608, + "step": 4955 + }, + { + "epoch": 0.52, + "learning_rate": 1.1054020705494622e-05, + "loss": 1.3703, + "step": 4956 + }, + { + "epoch": 0.52, + "learning_rate": 1.105038077361506e-05, + "loss": 1.3953, + "step": 4957 + }, + { + "epoch": 0.52, + "learning_rate": 1.1046740701011467e-05, + "loss": 1.392, + "step": 4958 + }, + { + "epoch": 0.52, + "learning_rate": 1.1043100488171513e-05, + "loss": 1.4101, + "step": 4959 + }, + { + "epoch": 0.52, + "learning_rate": 1.1039460135582894e-05, + "loss": 1.5432, + "step": 4960 + }, + { + "epoch": 0.52, + "learning_rate": 1.1035819643733326e-05, + "loss": 1.3822, + "step": 4961 + }, + { + "epoch": 0.52, + "learning_rate": 1.103217901311054e-05, + "loss": 1.3816, + "step": 4962 + }, + { + "epoch": 0.52, + "learning_rate": 1.1028538244202287e-05, + "loss": 1.3137, + "step": 4963 + }, + { + "epoch": 0.52, + "learning_rate": 1.102489733749634e-05, + "loss": 1.3791, + "step": 4964 + }, + { + "epoch": 0.52, + "learning_rate": 1.102125629348048e-05, + "loss": 1.3751, + "step": 4965 + }, + { + "epoch": 0.52, + "learning_rate": 1.1017615112642518e-05, + "loss": 1.3287, + "step": 4966 + }, + { + "epoch": 0.52, + "learning_rate": 1.1013973795470277e-05, + "loss": 1.3187, + "step": 4967 + }, + { + "epoch": 0.52, + "learning_rate": 1.1010332342451602e-05, + "loss": 1.3174, + "step": 4968 + }, + { + "epoch": 0.52, + "learning_rate": 1.1006690754074351e-05, + "loss": 1.3544, + "step": 4969 + }, + { + "epoch": 0.52, + "learning_rate": 1.1003049030826404e-05, + "loss": 1.3789, + "step": 4970 + }, + { + "epoch": 0.52, + "learning_rate": 1.0999407173195662e-05, + "loss": 1.4561, + "step": 4971 + }, + { + "epoch": 0.52, + "learning_rate": 1.0995765181670039e-05, + "loss": 1.3963, + "step": 4972 + }, + { + "epoch": 0.52, + "learning_rate": 1.0992123056737464e-05, + "loss": 1.3519, + "step": 4973 + }, + { + "epoch": 0.52, + "learning_rate": 1.0988480798885892e-05, + "loss": 1.3945, + "step": 4974 + }, + { + "epoch": 0.52, + "learning_rate": 1.0984838408603294e-05, + "loss": 1.4572, + "step": 4975 + }, + { + "epoch": 0.52, + "eval_loss": 1.4313459396362305, + "eval_runtime": 77.4808, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 4975 + }, + { + "epoch": 0.52, + "learning_rate": 1.0981195886377652e-05, + "loss": 1.3493, + "step": 4976 + }, + { + "epoch": 0.52, + "learning_rate": 1.0977553232696972e-05, + "loss": 1.3734, + "step": 4977 + }, + { + "epoch": 0.52, + "learning_rate": 1.0973910448049273e-05, + "loss": 1.3484, + "step": 4978 + }, + { + "epoch": 0.52, + "learning_rate": 1.09702675329226e-05, + "loss": 1.4288, + "step": 4979 + }, + { + "epoch": 0.52, + "learning_rate": 1.096662448780501e-05, + "loss": 1.3748, + "step": 4980 + }, + { + "epoch": 0.52, + "learning_rate": 1.0962981313184575e-05, + "loss": 1.3485, + "step": 4981 + }, + { + "epoch": 0.52, + "learning_rate": 1.0959338009549383e-05, + "loss": 1.3606, + "step": 4982 + }, + { + "epoch": 0.52, + "learning_rate": 1.095569457738755e-05, + "loss": 1.3963, + "step": 4983 + }, + { + "epoch": 0.52, + "learning_rate": 1.09520510171872e-05, + "loss": 1.2986, + "step": 4984 + }, + { + "epoch": 0.52, + "learning_rate": 1.0948407329436474e-05, + "loss": 1.3505, + "step": 4985 + }, + { + "epoch": 0.52, + "learning_rate": 1.0944763514623535e-05, + "loss": 1.4649, + "step": 4986 + }, + { + "epoch": 0.52, + "learning_rate": 1.0941119573236564e-05, + "loss": 1.4743, + "step": 4987 + }, + { + "epoch": 0.52, + "learning_rate": 1.0937475505763745e-05, + "loss": 1.3934, + "step": 4988 + }, + { + "epoch": 0.52, + "learning_rate": 1.09338313126933e-05, + "loss": 1.4225, + "step": 4989 + }, + { + "epoch": 0.52, + "learning_rate": 1.0930186994513453e-05, + "loss": 1.3626, + "step": 4990 + }, + { + "epoch": 0.52, + "learning_rate": 1.0926542551712446e-05, + "loss": 1.3614, + "step": 4991 + }, + { + "epoch": 0.52, + "learning_rate": 1.0922897984778546e-05, + "loss": 1.3766, + "step": 4992 + }, + { + "epoch": 0.52, + "learning_rate": 1.0919253294200027e-05, + "loss": 1.3295, + "step": 4993 + }, + { + "epoch": 0.52, + "learning_rate": 1.091560848046519e-05, + "loss": 1.3802, + "step": 4994 + }, + { + "epoch": 0.52, + "learning_rate": 1.091196354406234e-05, + "loss": 1.2976, + "step": 4995 + }, + { + "epoch": 0.52, + "learning_rate": 1.090831848547981e-05, + "loss": 1.3928, + "step": 4996 + }, + { + "epoch": 0.52, + "learning_rate": 1.0904673305205937e-05, + "loss": 1.3717, + "step": 4997 + }, + { + "epoch": 0.52, + "learning_rate": 1.0901028003729089e-05, + "loss": 1.3164, + "step": 4998 + }, + { + "epoch": 0.52, + "learning_rate": 1.0897382581537638e-05, + "loss": 1.3462, + "step": 4999 + }, + { + "epoch": 0.52, + "learning_rate": 1.0893737039119981e-05, + "loss": 1.3643, + "step": 5000 + }, + { + "epoch": 0.52, + "learning_rate": 1.089009137696452e-05, + "loss": 1.3452, + "step": 5001 + }, + { + "epoch": 0.52, + "learning_rate": 1.0886445595559686e-05, + "loss": 1.358, + "step": 5002 + }, + { + "epoch": 0.52, + "learning_rate": 1.0882799695393922e-05, + "loss": 1.4569, + "step": 5003 + }, + { + "epoch": 0.52, + "learning_rate": 1.0879153676955681e-05, + "loss": 1.2832, + "step": 5004 + }, + { + "epoch": 0.52, + "learning_rate": 1.0875507540733435e-05, + "loss": 1.4089, + "step": 5005 + }, + { + "epoch": 0.52, + "learning_rate": 1.087186128721567e-05, + "loss": 1.3178, + "step": 5006 + }, + { + "epoch": 0.53, + "learning_rate": 1.0868214916890902e-05, + "loss": 1.4883, + "step": 5007 + }, + { + "epoch": 0.53, + "learning_rate": 1.0864568430247638e-05, + "loss": 1.3991, + "step": 5008 + }, + { + "epoch": 0.53, + "learning_rate": 1.0860921827774422e-05, + "loss": 1.4507, + "step": 5009 + }, + { + "epoch": 0.53, + "learning_rate": 1.08572751099598e-05, + "loss": 1.3578, + "step": 5010 + }, + { + "epoch": 0.53, + "learning_rate": 1.0853628277292341e-05, + "loss": 1.4231, + "step": 5011 + }, + { + "epoch": 0.53, + "learning_rate": 1.0849981330260624e-05, + "loss": 1.4835, + "step": 5012 + }, + { + "epoch": 0.53, + "learning_rate": 1.084633426935325e-05, + "loss": 1.4511, + "step": 5013 + }, + { + "epoch": 0.53, + "learning_rate": 1.084268709505883e-05, + "loss": 1.3889, + "step": 5014 + }, + { + "epoch": 0.53, + "learning_rate": 1.0839039807865992e-05, + "loss": 1.355, + "step": 5015 + }, + { + "epoch": 0.53, + "learning_rate": 1.0835392408263375e-05, + "loss": 1.4829, + "step": 5016 + }, + { + "epoch": 0.53, + "learning_rate": 1.0831744896739643e-05, + "loss": 1.3019, + "step": 5017 + }, + { + "epoch": 0.53, + "learning_rate": 1.0828097273783465e-05, + "loss": 1.3418, + "step": 5018 + }, + { + "epoch": 0.53, + "learning_rate": 1.082444953988353e-05, + "loss": 1.4276, + "step": 5019 + }, + { + "epoch": 0.53, + "learning_rate": 1.0820801695528537e-05, + "loss": 1.2816, + "step": 5020 + }, + { + "epoch": 0.53, + "learning_rate": 1.081715374120721e-05, + "loss": 1.5144, + "step": 5021 + }, + { + "epoch": 0.53, + "learning_rate": 1.0813505677408278e-05, + "loss": 1.4063, + "step": 5022 + }, + { + "epoch": 0.53, + "learning_rate": 1.0809857504620487e-05, + "loss": 1.4011, + "step": 5023 + }, + { + "epoch": 0.53, + "learning_rate": 1.0806209223332598e-05, + "loss": 1.373, + "step": 5024 + }, + { + "epoch": 0.53, + "learning_rate": 1.0802560834033388e-05, + "loss": 1.6259, + "step": 5025 + }, + { + "epoch": 0.53, + "learning_rate": 1.0798912337211648e-05, + "loss": 1.4487, + "step": 5026 + }, + { + "epoch": 0.53, + "learning_rate": 1.0795263733356184e-05, + "loss": 1.3056, + "step": 5027 + }, + { + "epoch": 0.53, + "learning_rate": 1.079161502295581e-05, + "loss": 1.2871, + "step": 5028 + }, + { + "epoch": 0.53, + "learning_rate": 1.0787966206499363e-05, + "loss": 1.413, + "step": 5029 + }, + { + "epoch": 0.53, + "learning_rate": 1.0784317284475694e-05, + "loss": 1.3682, + "step": 5030 + }, + { + "epoch": 0.53, + "learning_rate": 1.0780668257373659e-05, + "loss": 1.493, + "step": 5031 + }, + { + "epoch": 0.53, + "learning_rate": 1.0777019125682136e-05, + "loss": 1.6823, + "step": 5032 + }, + { + "epoch": 0.53, + "learning_rate": 1.0773369889890015e-05, + "loss": 1.358, + "step": 5033 + }, + { + "epoch": 0.53, + "learning_rate": 1.07697205504862e-05, + "loss": 1.3532, + "step": 5034 + }, + { + "epoch": 0.53, + "learning_rate": 1.0766071107959608e-05, + "loss": 1.3432, + "step": 5035 + }, + { + "epoch": 0.53, + "learning_rate": 1.0762421562799173e-05, + "loss": 1.3575, + "step": 5036 + }, + { + "epoch": 0.53, + "learning_rate": 1.0758771915493838e-05, + "loss": 1.0924, + "step": 5037 + }, + { + "epoch": 0.53, + "learning_rate": 1.075512216653256e-05, + "loss": 0.7405, + "step": 5038 + }, + { + "epoch": 0.53, + "learning_rate": 1.0751472316404315e-05, + "loss": 0.7134, + "step": 5039 + }, + { + "epoch": 0.53, + "learning_rate": 1.0747822365598088e-05, + "loss": 1.0904, + "step": 5040 + }, + { + "epoch": 0.53, + "learning_rate": 1.0744172314602881e-05, + "loss": 1.4353, + "step": 5041 + }, + { + "epoch": 0.53, + "learning_rate": 1.0740522163907702e-05, + "loss": 1.361, + "step": 5042 + }, + { + "epoch": 0.53, + "learning_rate": 1.073687191400158e-05, + "loss": 1.4024, + "step": 5043 + }, + { + "epoch": 0.53, + "learning_rate": 1.0733221565373557e-05, + "loss": 1.328, + "step": 5044 + }, + { + "epoch": 0.53, + "learning_rate": 1.0729571118512683e-05, + "loss": 1.3309, + "step": 5045 + }, + { + "epoch": 0.53, + "learning_rate": 1.0725920573908024e-05, + "loss": 1.3819, + "step": 5046 + }, + { + "epoch": 0.53, + "learning_rate": 1.0722269932048659e-05, + "loss": 1.3467, + "step": 5047 + }, + { + "epoch": 0.53, + "learning_rate": 1.0718619193423683e-05, + "loss": 1.3036, + "step": 5048 + }, + { + "epoch": 0.53, + "learning_rate": 1.07149683585222e-05, + "loss": 1.3297, + "step": 5049 + }, + { + "epoch": 0.53, + "learning_rate": 1.0711317427833328e-05, + "loss": 1.3439, + "step": 5050 + }, + { + "epoch": 0.53, + "learning_rate": 1.0707666401846192e-05, + "loss": 1.4167, + "step": 5051 + }, + { + "epoch": 0.53, + "learning_rate": 1.0704015281049944e-05, + "loss": 1.4217, + "step": 5052 + }, + { + "epoch": 0.53, + "learning_rate": 1.070036406593374e-05, + "loss": 1.3394, + "step": 5053 + }, + { + "epoch": 0.53, + "learning_rate": 1.0696712756986745e-05, + "loss": 1.3242, + "step": 5054 + }, + { + "epoch": 0.53, + "learning_rate": 1.0693061354698143e-05, + "loss": 1.3957, + "step": 5055 + }, + { + "epoch": 0.53, + "learning_rate": 1.0689409859557123e-05, + "loss": 1.37, + "step": 5056 + }, + { + "epoch": 0.53, + "learning_rate": 1.0685758272052902e-05, + "loss": 1.4524, + "step": 5057 + }, + { + "epoch": 0.53, + "learning_rate": 1.0682106592674688e-05, + "loss": 1.528, + "step": 5058 + }, + { + "epoch": 0.53, + "learning_rate": 1.0678454821911719e-05, + "loss": 1.3613, + "step": 5059 + }, + { + "epoch": 0.53, + "learning_rate": 1.0674802960253234e-05, + "loss": 1.308, + "step": 5060 + }, + { + "epoch": 0.53, + "learning_rate": 1.0671151008188494e-05, + "loss": 1.3343, + "step": 5061 + }, + { + "epoch": 0.53, + "learning_rate": 1.066749896620676e-05, + "loss": 1.365, + "step": 5062 + }, + { + "epoch": 0.53, + "learning_rate": 1.0663846834797316e-05, + "loss": 1.4077, + "step": 5063 + }, + { + "epoch": 0.53, + "learning_rate": 1.0660194614449455e-05, + "loss": 1.324, + "step": 5064 + }, + { + "epoch": 0.53, + "learning_rate": 1.0656542305652478e-05, + "loss": 1.3623, + "step": 5065 + }, + { + "epoch": 0.53, + "learning_rate": 1.0652889908895701e-05, + "loss": 1.4079, + "step": 5066 + }, + { + "epoch": 0.53, + "learning_rate": 1.0649237424668451e-05, + "loss": 1.3089, + "step": 5067 + }, + { + "epoch": 0.53, + "learning_rate": 1.0645584853460069e-05, + "loss": 1.3967, + "step": 5068 + }, + { + "epoch": 0.53, + "learning_rate": 1.0641932195759905e-05, + "loss": 1.3639, + "step": 5069 + }, + { + "epoch": 0.53, + "learning_rate": 1.0638279452057319e-05, + "loss": 1.5919, + "step": 5070 + }, + { + "epoch": 0.53, + "learning_rate": 1.0634626622841686e-05, + "loss": 1.3348, + "step": 5071 + }, + { + "epoch": 0.53, + "learning_rate": 1.0630973708602395e-05, + "loss": 1.3146, + "step": 5072 + }, + { + "epoch": 0.53, + "learning_rate": 1.0627320709828836e-05, + "loss": 1.3375, + "step": 5073 + }, + { + "epoch": 0.53, + "learning_rate": 1.062366762701042e-05, + "loss": 1.3908, + "step": 5074 + }, + { + "epoch": 0.53, + "learning_rate": 1.0620014460636568e-05, + "loss": 1.3726, + "step": 5075 + }, + { + "epoch": 0.53, + "learning_rate": 1.061636121119671e-05, + "loss": 1.2348, + "step": 5076 + }, + { + "epoch": 0.53, + "learning_rate": 1.0612707879180284e-05, + "loss": 1.2957, + "step": 5077 + }, + { + "epoch": 0.53, + "learning_rate": 1.0609054465076749e-05, + "loss": 1.4202, + "step": 5078 + }, + { + "epoch": 0.53, + "learning_rate": 1.060540096937556e-05, + "loss": 1.5809, + "step": 5079 + }, + { + "epoch": 0.53, + "learning_rate": 1.0601747392566202e-05, + "loss": 1.3741, + "step": 5080 + }, + { + "epoch": 0.53, + "learning_rate": 1.059809373513815e-05, + "loss": 1.3537, + "step": 5081 + }, + { + "epoch": 0.53, + "learning_rate": 1.0594439997580907e-05, + "loss": 1.332, + "step": 5082 + }, + { + "epoch": 0.53, + "learning_rate": 1.0590786180383981e-05, + "loss": 1.3267, + "step": 5083 + }, + { + "epoch": 0.53, + "learning_rate": 1.0587132284036883e-05, + "loss": 1.3552, + "step": 5084 + }, + { + "epoch": 0.53, + "learning_rate": 1.0583478309029143e-05, + "loss": 1.2837, + "step": 5085 + }, + { + "epoch": 0.53, + "learning_rate": 1.0579824255850304e-05, + "loss": 1.4311, + "step": 5086 + }, + { + "epoch": 0.53, + "learning_rate": 1.0576170124989915e-05, + "loss": 1.4394, + "step": 5087 + }, + { + "epoch": 0.53, + "learning_rate": 1.0572515916937531e-05, + "loss": 1.3185, + "step": 5088 + }, + { + "epoch": 0.53, + "learning_rate": 1.0568861632182723e-05, + "loss": 1.4212, + "step": 5089 + }, + { + "epoch": 0.53, + "learning_rate": 1.0565207271215075e-05, + "loss": 1.0951, + "step": 5090 + }, + { + "epoch": 0.53, + "learning_rate": 1.0561552834524176e-05, + "loss": 1.4174, + "step": 5091 + }, + { + "epoch": 0.53, + "learning_rate": 1.0557898322599624e-05, + "loss": 1.3349, + "step": 5092 + }, + { + "epoch": 0.53, + "learning_rate": 1.0554243735931031e-05, + "loss": 1.399, + "step": 5093 + }, + { + "epoch": 0.53, + "learning_rate": 1.055058907500802e-05, + "loss": 1.4016, + "step": 5094 + }, + { + "epoch": 0.53, + "learning_rate": 1.0546934340320219e-05, + "loss": 1.3227, + "step": 5095 + }, + { + "epoch": 0.53, + "learning_rate": 1.0543279532357269e-05, + "loss": 1.4017, + "step": 5096 + }, + { + "epoch": 0.53, + "learning_rate": 1.053962465160882e-05, + "loss": 1.3937, + "step": 5097 + }, + { + "epoch": 0.53, + "learning_rate": 1.0535969698564532e-05, + "loss": 1.2405, + "step": 5098 + }, + { + "epoch": 0.53, + "learning_rate": 1.0532314673714081e-05, + "loss": 1.2939, + "step": 5099 + }, + { + "epoch": 0.53, + "learning_rate": 1.0528659577547136e-05, + "loss": 1.4165, + "step": 5100 + }, + { + "epoch": 0.53, + "learning_rate": 1.0525004410553394e-05, + "loss": 1.309, + "step": 5101 + }, + { + "epoch": 0.54, + "learning_rate": 1.0521349173222549e-05, + "loss": 1.4078, + "step": 5102 + }, + { + "epoch": 0.54, + "learning_rate": 1.0517693866044312e-05, + "loss": 1.4026, + "step": 5103 + }, + { + "epoch": 0.54, + "learning_rate": 1.0514038489508396e-05, + "loss": 1.3098, + "step": 5104 + }, + { + "epoch": 0.54, + "learning_rate": 1.0510383044104533e-05, + "loss": 1.2886, + "step": 5105 + }, + { + "epoch": 0.54, + "learning_rate": 1.0506727530322454e-05, + "loss": 1.3114, + "step": 5106 + }, + { + "epoch": 0.54, + "learning_rate": 1.0503071948651908e-05, + "loss": 1.2823, + "step": 5107 + }, + { + "epoch": 0.54, + "learning_rate": 1.0499416299582643e-05, + "loss": 1.4654, + "step": 5108 + }, + { + "epoch": 0.54, + "learning_rate": 1.0495760583604431e-05, + "loss": 1.4043, + "step": 5109 + }, + { + "epoch": 0.54, + "learning_rate": 1.0492104801207035e-05, + "loss": 1.3113, + "step": 5110 + }, + { + "epoch": 0.54, + "learning_rate": 1.0488448952880243e-05, + "loss": 1.3285, + "step": 5111 + }, + { + "epoch": 0.54, + "learning_rate": 1.048479303911384e-05, + "loss": 1.3918, + "step": 5112 + }, + { + "epoch": 0.54, + "learning_rate": 1.0481137060397623e-05, + "loss": 1.346, + "step": 5113 + }, + { + "epoch": 0.54, + "learning_rate": 1.0477481017221407e-05, + "loss": 1.3777, + "step": 5114 + }, + { + "epoch": 0.54, + "learning_rate": 1.0473824910075003e-05, + "loss": 1.3494, + "step": 5115 + }, + { + "epoch": 0.54, + "learning_rate": 1.0470168739448232e-05, + "loss": 1.4173, + "step": 5116 + }, + { + "epoch": 0.54, + "learning_rate": 1.0466512505830932e-05, + "loss": 1.4313, + "step": 5117 + }, + { + "epoch": 0.54, + "learning_rate": 1.0462856209712944e-05, + "loss": 1.335, + "step": 5118 + }, + { + "epoch": 0.54, + "learning_rate": 1.0459199851584117e-05, + "loss": 1.37, + "step": 5119 + }, + { + "epoch": 0.54, + "learning_rate": 1.0455543431934307e-05, + "loss": 1.3504, + "step": 5120 + }, + { + "epoch": 0.54, + "learning_rate": 1.0451886951253381e-05, + "loss": 1.4148, + "step": 5121 + }, + { + "epoch": 0.54, + "learning_rate": 1.0448230410031218e-05, + "loss": 1.3974, + "step": 5122 + }, + { + "epoch": 0.54, + "learning_rate": 1.0444573808757694e-05, + "loss": 1.3644, + "step": 5123 + }, + { + "epoch": 0.54, + "learning_rate": 1.0440917147922705e-05, + "loss": 1.4024, + "step": 5124 + }, + { + "epoch": 0.54, + "learning_rate": 1.0437260428016143e-05, + "loss": 1.3925, + "step": 5125 + }, + { + "epoch": 0.54, + "learning_rate": 1.0433603649527923e-05, + "loss": 1.2907, + "step": 5126 + }, + { + "epoch": 0.54, + "learning_rate": 1.0429946812947953e-05, + "loss": 1.3453, + "step": 5127 + }, + { + "epoch": 0.54, + "learning_rate": 1.0426289918766157e-05, + "loss": 1.3856, + "step": 5128 + }, + { + "epoch": 0.54, + "learning_rate": 1.0422632967472465e-05, + "loss": 1.3309, + "step": 5129 + }, + { + "epoch": 0.54, + "learning_rate": 1.0418975959556819e-05, + "loss": 1.3757, + "step": 5130 + }, + { + "epoch": 0.54, + "learning_rate": 1.0415318895509152e-05, + "loss": 1.406, + "step": 5131 + }, + { + "epoch": 0.54, + "learning_rate": 1.041166177581943e-05, + "loss": 1.3265, + "step": 5132 + }, + { + "epoch": 0.54, + "learning_rate": 1.0408004600977606e-05, + "loss": 1.3377, + "step": 5133 + }, + { + "epoch": 0.54, + "learning_rate": 1.040434737147365e-05, + "loss": 1.3647, + "step": 5134 + }, + { + "epoch": 0.54, + "learning_rate": 1.0400690087797531e-05, + "loss": 1.3262, + "step": 5135 + }, + { + "epoch": 0.54, + "learning_rate": 1.039703275043924e-05, + "loss": 1.3924, + "step": 5136 + }, + { + "epoch": 0.54, + "learning_rate": 1.039337535988876e-05, + "loss": 1.3018, + "step": 5137 + }, + { + "epoch": 0.54, + "learning_rate": 1.038971791663609e-05, + "loss": 1.385, + "step": 5138 + }, + { + "epoch": 0.54, + "learning_rate": 1.0386060421171232e-05, + "loss": 1.3435, + "step": 5139 + }, + { + "epoch": 0.54, + "learning_rate": 1.0382402873984197e-05, + "loss": 1.4023, + "step": 5140 + }, + { + "epoch": 0.54, + "learning_rate": 1.0378745275565003e-05, + "loss": 1.369, + "step": 5141 + }, + { + "epoch": 0.54, + "learning_rate": 1.0375087626403675e-05, + "loss": 1.3199, + "step": 5142 + }, + { + "epoch": 0.54, + "learning_rate": 1.037142992699024e-05, + "loss": 1.4247, + "step": 5143 + }, + { + "epoch": 0.54, + "learning_rate": 1.0367772177814736e-05, + "loss": 1.4015, + "step": 5144 + }, + { + "epoch": 0.54, + "learning_rate": 1.0364114379367217e-05, + "loss": 1.3519, + "step": 5145 + }, + { + "epoch": 0.54, + "learning_rate": 1.0360456532137722e-05, + "loss": 1.3478, + "step": 5146 + }, + { + "epoch": 0.54, + "learning_rate": 1.0356798636616314e-05, + "loss": 1.4876, + "step": 5147 + }, + { + "epoch": 0.54, + "learning_rate": 1.0353140693293056e-05, + "loss": 1.6481, + "step": 5148 + }, + { + "epoch": 0.54, + "learning_rate": 1.034948270265802e-05, + "loss": 1.3851, + "step": 5149 + }, + { + "epoch": 0.54, + "learning_rate": 1.0345824665201281e-05, + "loss": 1.4037, + "step": 5150 + }, + { + "epoch": 0.54, + "learning_rate": 1.0342166581412923e-05, + "loss": 1.3138, + "step": 5151 + }, + { + "epoch": 0.54, + "learning_rate": 1.0338508451783032e-05, + "loss": 1.3536, + "step": 5152 + }, + { + "epoch": 0.54, + "learning_rate": 1.0334850276801712e-05, + "loss": 1.3244, + "step": 5153 + }, + { + "epoch": 0.54, + "learning_rate": 1.0331192056959052e-05, + "loss": 1.3677, + "step": 5154 + }, + { + "epoch": 0.54, + "learning_rate": 1.032753379274517e-05, + "loss": 1.3439, + "step": 5155 + }, + { + "epoch": 0.54, + "learning_rate": 1.0323875484650171e-05, + "loss": 1.365, + "step": 5156 + }, + { + "epoch": 0.54, + "learning_rate": 1.0320217133164186e-05, + "loss": 1.3838, + "step": 5157 + }, + { + "epoch": 0.54, + "learning_rate": 1.0316558738777328e-05, + "loss": 1.3312, + "step": 5158 + }, + { + "epoch": 0.54, + "learning_rate": 1.0312900301979733e-05, + "loss": 1.369, + "step": 5159 + }, + { + "epoch": 0.54, + "learning_rate": 1.030924182326154e-05, + "loss": 1.2712, + "step": 5160 + }, + { + "epoch": 0.54, + "learning_rate": 1.0305583303112887e-05, + "loss": 1.3141, + "step": 5161 + }, + { + "epoch": 0.54, + "learning_rate": 1.030192474202392e-05, + "loss": 1.3708, + "step": 5162 + }, + { + "epoch": 0.54, + "learning_rate": 1.0298266140484798e-05, + "loss": 1.3724, + "step": 5163 + }, + { + "epoch": 0.54, + "learning_rate": 1.0294607498985678e-05, + "loss": 1.3208, + "step": 5164 + }, + { + "epoch": 0.54, + "learning_rate": 1.0290948818016722e-05, + "loss": 1.3379, + "step": 5165 + }, + { + "epoch": 0.54, + "learning_rate": 1.0287290098068099e-05, + "loss": 1.3236, + "step": 5166 + }, + { + "epoch": 0.54, + "learning_rate": 1.0283631339629982e-05, + "loss": 1.3437, + "step": 5167 + }, + { + "epoch": 0.54, + "learning_rate": 1.0279972543192561e-05, + "loss": 1.3381, + "step": 5168 + }, + { + "epoch": 0.54, + "learning_rate": 1.0276313709246007e-05, + "loss": 1.4287, + "step": 5169 + }, + { + "epoch": 0.54, + "learning_rate": 1.0272654838280515e-05, + "loss": 1.3587, + "step": 5170 + }, + { + "epoch": 0.54, + "learning_rate": 1.0268995930786283e-05, + "loss": 1.2982, + "step": 5171 + }, + { + "epoch": 0.54, + "learning_rate": 1.0265336987253509e-05, + "loss": 1.3416, + "step": 5172 + }, + { + "epoch": 0.54, + "learning_rate": 1.0261678008172393e-05, + "loss": 1.3827, + "step": 5173 + }, + { + "epoch": 0.54, + "learning_rate": 1.025801899403315e-05, + "loss": 1.3293, + "step": 5174 + }, + { + "epoch": 0.54, + "eval_loss": 1.4264723062515259, + "eval_runtime": 77.4376, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 5174 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 2.314661601164384e+20, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-5174/training_args.bin b/checkpoint-5174/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-5174/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-5572/config.json b/checkpoint-5572/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-5572/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-5572/generation_config.json b/checkpoint-5572/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-5572/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-5572/model-00001-of-00003.safetensors b/checkpoint-5572/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ccf54db4affb1c8795251811f7841fc4d96e8f7a --- /dev/null +++ b/checkpoint-5572/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf323361e2f362c905d95f30661cbeedb21126bfa3964e1dd032728862b21115 +size 4943162336 diff --git a/checkpoint-5572/model-00002-of-00003.safetensors b/checkpoint-5572/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c0b3289d4cecd77a23801d6b680390ea885eb00 --- /dev/null +++ b/checkpoint-5572/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f70412c6b2eb852d9a6e156794ab987169d920f6f69b13d6fd9209b3037c1be +size 4999819336 diff --git a/checkpoint-5572/model-00003-of-00003.safetensors b/checkpoint-5572/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..91a201121a85296d8bdcaebe548f1844fadbdbe3 --- /dev/null +++ b/checkpoint-5572/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:846f0b96703fbcecc7756c41c4bebb2edd417ee6bc46aba2407f9cd4177eb581 +size 4540516344 diff --git a/checkpoint-5572/model.safetensors.index.json b/checkpoint-5572/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-5572/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-5572/optimizer.pt b/checkpoint-5572/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..b7ca1ed757901890b985aa29b77db285e4a04a62 --- /dev/null +++ b/checkpoint-5572/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8798fe4c88d2e98a0d0281b52031648aebd98523f269aa919537348cbd8814a +size 14512103560 diff --git a/checkpoint-5572/rng_state_0.pth b/checkpoint-5572/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..903b2f220a3396c2fef1d5f1b403631f7fca3507 --- /dev/null +++ b/checkpoint-5572/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a205f64c86d241517037857e791fc7cdcfd1b2d8a26ca46ff4e6430fc9491c64 +size 15984 diff --git a/checkpoint-5572/rng_state_1.pth b/checkpoint-5572/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..11486f9780be3e5b6735a2d4180900fc09aac7cd --- /dev/null +++ b/checkpoint-5572/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:384e04a3f342b13aa2aff82b03d67994ff48a7b6e7d90ad53291b0ccf1124755 +size 15984 diff --git a/checkpoint-5572/rng_state_2.pth b/checkpoint-5572/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..cd0f3344a92bedf201434197e7bc4b07b639c8dc --- /dev/null +++ b/checkpoint-5572/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c75af15b2dde4bfa82f45cc3b48588a123bca20dd4b565a0312d5c1198d8bca9 +size 15984 diff --git a/checkpoint-5572/rng_state_3.pth b/checkpoint-5572/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..451a9794707919839e8f7850f16e4c37436786ea --- /dev/null +++ b/checkpoint-5572/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8162e1d617d2045c999376967bb33455e9055c2882d00e9e6c3e5639106c7cf2 +size 15984 diff --git a/checkpoint-5572/rng_state_4.pth b/checkpoint-5572/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..fc44c6be06092753994a1e6a0001456709914b68 --- /dev/null +++ b/checkpoint-5572/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37df018beaaf1bcb0a0451dcfd03f257c34b245315c9d5243bad309614abb972 +size 15984 diff --git a/checkpoint-5572/rng_state_5.pth b/checkpoint-5572/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..8314612be9f02c2f45b1e5e5f4fdd7f001d4787f --- /dev/null +++ b/checkpoint-5572/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc45f95eb705f82fae244f5f5bb1d1d060492c8b55aba2aa58162687e28952bc +size 15984 diff --git a/checkpoint-5572/rng_state_6.pth b/checkpoint-5572/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..d5550947b9eae3707b39874ef2ebb39f95c5962f --- /dev/null +++ b/checkpoint-5572/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8ed548560db42b0406ce39f0d4bce5fac64c200cc3ab9248f1dd703dde9dfef +size 15984 diff --git a/checkpoint-5572/rng_state_7.pth b/checkpoint-5572/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..e0a3d86d5e778071b9376d188cc34b0ad166d91f --- /dev/null +++ b/checkpoint-5572/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:865e7aa49ec74e2e8e5ffbc2b62c9edb6308476119fe3e77f2fe29961dd5deaf +size 15984 diff --git a/checkpoint-5572/scheduler.pt b/checkpoint-5572/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..f15fefc89d2dd3f9f9c59ccb53bebcef713a3d5a --- /dev/null +++ b/checkpoint-5572/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bdde67bc4ebd6169be2cee92cbdb4549735d2be5b449a75f7c01dfabef8ec27 +size 1064 diff --git a/checkpoint-5572/special_tokens_map.json b/checkpoint-5572/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-5572/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-5572/tokenizer.model b/checkpoint-5572/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-5572/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-5572/tokenizer_config.json b/checkpoint-5572/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-5572/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-5572/trainer_state.json b/checkpoint-5572/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..44d90a3db522fd9fb38510f0fc1973c719afa0f8 --- /dev/null +++ b/checkpoint-5572/trainer_state.json @@ -0,0 +1,33676 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.5843120805369127, + "eval_steps": 199, + "global_step": 5572, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + }, + { + "epoch": 0.21, + "learning_rate": 1.928689129323009e-05, + "loss": 1.421, + "step": 1991 + }, + { + "epoch": 0.21, + "learning_rate": 1.928553323396003e-05, + "loss": 1.5625, + "step": 1992 + }, + { + "epoch": 0.21, + "learning_rate": 1.92841739306671e-05, + "loss": 1.5198, + "step": 1993 + }, + { + "epoch": 0.21, + "learning_rate": 1.9282813383533415e-05, + "loss": 1.5116, + "step": 1994 + }, + { + "epoch": 0.21, + "learning_rate": 1.9281451592741247e-05, + "loss": 1.4306, + "step": 1995 + }, + { + "epoch": 0.21, + "learning_rate": 1.9280088558473046e-05, + "loss": 1.5425, + "step": 1996 + }, + { + "epoch": 0.21, + "learning_rate": 1.9278724280911424e-05, + "loss": 1.4972, + "step": 1997 + }, + { + "epoch": 0.21, + "learning_rate": 1.9277358760239156e-05, + "loss": 1.5185, + "step": 1998 + }, + { + "epoch": 0.21, + "learning_rate": 1.9275991996639188e-05, + "loss": 1.5187, + "step": 1999 + }, + { + "epoch": 0.21, + "learning_rate": 1.927462399029463e-05, + "loss": 1.4325, + "step": 2000 + }, + { + "epoch": 0.21, + "learning_rate": 1.9273254741388763e-05, + "loss": 1.4397, + "step": 2001 + }, + { + "epoch": 0.21, + "learning_rate": 1.927188425010503e-05, + "loss": 1.5319, + "step": 2002 + }, + { + "epoch": 0.21, + "learning_rate": 1.9270512516627042e-05, + "loss": 1.5664, + "step": 2003 + }, + { + "epoch": 0.21, + "learning_rate": 1.9269139541138574e-05, + "loss": 1.5227, + "step": 2004 + }, + { + "epoch": 0.21, + "learning_rate": 1.926776532382357e-05, + "loss": 1.5187, + "step": 2005 + }, + { + "epoch": 0.21, + "learning_rate": 1.9266389864866134e-05, + "loss": 1.4029, + "step": 2006 + }, + { + "epoch": 0.21, + "learning_rate": 1.9265013164450557e-05, + "loss": 1.387, + "step": 2007 + }, + { + "epoch": 0.21, + "learning_rate": 1.9263635222761268e-05, + "loss": 1.5047, + "step": 2008 + }, + { + "epoch": 0.21, + "learning_rate": 1.9262256039982882e-05, + "loss": 1.4816, + "step": 2009 + }, + { + "epoch": 0.21, + "learning_rate": 1.9260875616300172e-05, + "loss": 1.4607, + "step": 2010 + }, + { + "epoch": 0.21, + "learning_rate": 1.9259493951898084e-05, + "loss": 1.628, + "step": 2011 + }, + { + "epoch": 0.21, + "learning_rate": 1.9258111046961714e-05, + "loss": 1.4149, + "step": 2012 + }, + { + "epoch": 0.21, + "learning_rate": 1.925672690167635e-05, + "loss": 1.5303, + "step": 2013 + }, + { + "epoch": 0.21, + "learning_rate": 1.925534151622742e-05, + "loss": 1.5198, + "step": 2014 + }, + { + "epoch": 0.21, + "learning_rate": 1.9253954890800535e-05, + "loss": 1.6422, + "step": 2015 + }, + { + "epoch": 0.21, + "learning_rate": 1.925256702558147e-05, + "loss": 1.4738, + "step": 2016 + }, + { + "epoch": 0.21, + "learning_rate": 1.925117792075616e-05, + "loss": 1.4752, + "step": 2017 + }, + { + "epoch": 0.21, + "learning_rate": 1.9249787576510713e-05, + "loss": 1.4547, + "step": 2018 + }, + { + "epoch": 0.21, + "learning_rate": 1.924839599303139e-05, + "loss": 1.4864, + "step": 2019 + }, + { + "epoch": 0.21, + "learning_rate": 1.9247003170504638e-05, + "loss": 1.5037, + "step": 2020 + }, + { + "epoch": 0.21, + "learning_rate": 1.9245609109117053e-05, + "loss": 1.5089, + "step": 2021 + }, + { + "epoch": 0.21, + "learning_rate": 1.924421380905541e-05, + "loss": 1.5616, + "step": 2022 + }, + { + "epoch": 0.21, + "learning_rate": 1.9242817270506634e-05, + "loss": 1.4592, + "step": 2023 + }, + { + "epoch": 0.21, + "learning_rate": 1.9241419493657832e-05, + "loss": 1.5592, + "step": 2024 + }, + { + "epoch": 0.21, + "learning_rate": 1.924002047869627e-05, + "loss": 1.4897, + "step": 2025 + }, + { + "epoch": 0.21, + "learning_rate": 1.9238620225809375e-05, + "loss": 1.4743, + "step": 2026 + }, + { + "epoch": 0.21, + "learning_rate": 1.923721873518475e-05, + "loss": 1.4686, + "step": 2027 + }, + { + "epoch": 0.21, + "learning_rate": 1.923581600701016e-05, + "loss": 1.461, + "step": 2028 + }, + { + "epoch": 0.21, + "learning_rate": 1.9234412041473528e-05, + "loss": 1.6622, + "step": 2029 + }, + { + "epoch": 0.21, + "learning_rate": 1.9233006838762955e-05, + "loss": 1.4707, + "step": 2030 + }, + { + "epoch": 0.21, + "learning_rate": 1.92316003990667e-05, + "loss": 1.5566, + "step": 2031 + }, + { + "epoch": 0.21, + "learning_rate": 1.9230192722573188e-05, + "loss": 1.4881, + "step": 2032 + }, + { + "epoch": 0.21, + "learning_rate": 1.9228783809471015e-05, + "loss": 1.6124, + "step": 2033 + }, + { + "epoch": 0.21, + "learning_rate": 1.9227373659948937e-05, + "loss": 1.3508, + "step": 2034 + }, + { + "epoch": 0.21, + "learning_rate": 1.9225962274195876e-05, + "loss": 1.4418, + "step": 2035 + }, + { + "epoch": 0.21, + "learning_rate": 1.9224549652400927e-05, + "loss": 1.3954, + "step": 2036 + }, + { + "epoch": 0.21, + "learning_rate": 1.922313579475334e-05, + "loss": 1.4798, + "step": 2037 + }, + { + "epoch": 0.21, + "learning_rate": 1.922172070144254e-05, + "loss": 1.4556, + "step": 2038 + }, + { + "epoch": 0.21, + "learning_rate": 1.922030437265811e-05, + "loss": 1.4987, + "step": 2039 + }, + { + "epoch": 0.21, + "learning_rate": 1.9218886808589796e-05, + "loss": 1.4857, + "step": 2040 + }, + { + "epoch": 0.21, + "learning_rate": 1.9217468009427527e-05, + "loss": 1.5289, + "step": 2041 + }, + { + "epoch": 0.21, + "learning_rate": 1.921604797536138e-05, + "loss": 1.5267, + "step": 2042 + }, + { + "epoch": 0.21, + "learning_rate": 1.9214626706581598e-05, + "loss": 1.4655, + "step": 2043 + }, + { + "epoch": 0.21, + "learning_rate": 1.9213204203278602e-05, + "loss": 1.4598, + "step": 2044 + }, + { + "epoch": 0.21, + "learning_rate": 1.9211780465642973e-05, + "loss": 1.4766, + "step": 2045 + }, + { + "epoch": 0.21, + "learning_rate": 1.921035549386545e-05, + "loss": 1.5148, + "step": 2046 + }, + { + "epoch": 0.21, + "learning_rate": 1.9208929288136933e-05, + "loss": 1.5567, + "step": 2047 + }, + { + "epoch": 0.21, + "learning_rate": 1.920750184864852e-05, + "loss": 1.4868, + "step": 2048 + }, + { + "epoch": 0.21, + "learning_rate": 1.920607317559143e-05, + "loss": 1.4752, + "step": 2049 + }, + { + "epoch": 0.21, + "learning_rate": 1.920464326915708e-05, + "loss": 1.4882, + "step": 2050 + }, + { + "epoch": 0.22, + "learning_rate": 1.9203212129537035e-05, + "loss": 1.5933, + "step": 2051 + }, + { + "epoch": 0.22, + "learning_rate": 1.9201779756923037e-05, + "loss": 1.4891, + "step": 2052 + }, + { + "epoch": 0.22, + "learning_rate": 1.9200346151506983e-05, + "loss": 1.4486, + "step": 2053 + }, + { + "epoch": 0.22, + "learning_rate": 1.9198911313480938e-05, + "loss": 1.5091, + "step": 2054 + }, + { + "epoch": 0.22, + "learning_rate": 1.919747524303714e-05, + "loss": 1.4385, + "step": 2055 + }, + { + "epoch": 0.22, + "learning_rate": 1.9196037940367974e-05, + "loss": 1.4104, + "step": 2056 + }, + { + "epoch": 0.22, + "learning_rate": 1.9194599405666015e-05, + "loss": 1.4483, + "step": 2057 + }, + { + "epoch": 0.22, + "learning_rate": 1.9193159639123976e-05, + "loss": 1.4592, + "step": 2058 + }, + { + "epoch": 0.22, + "learning_rate": 1.919171864093476e-05, + "loss": 1.4975, + "step": 2059 + }, + { + "epoch": 0.22, + "learning_rate": 1.9190276411291423e-05, + "loss": 1.4727, + "step": 2060 + }, + { + "epoch": 0.22, + "learning_rate": 1.9188832950387178e-05, + "loss": 1.4791, + "step": 2061 + }, + { + "epoch": 0.22, + "learning_rate": 1.9187388258415423e-05, + "loss": 1.3806, + "step": 2062 + }, + { + "epoch": 0.22, + "learning_rate": 1.9185942335569697e-05, + "loss": 1.4514, + "step": 2063 + }, + { + "epoch": 0.22, + "learning_rate": 1.9184495182043727e-05, + "loss": 1.4389, + "step": 2064 + }, + { + "epoch": 0.22, + "learning_rate": 1.918304679803139e-05, + "loss": 1.5088, + "step": 2065 + }, + { + "epoch": 0.22, + "learning_rate": 1.9181597183726733e-05, + "loss": 1.4665, + "step": 2066 + }, + { + "epoch": 0.22, + "learning_rate": 1.9180146339323966e-05, + "loss": 1.489, + "step": 2067 + }, + { + "epoch": 0.22, + "learning_rate": 1.9178694265017466e-05, + "loss": 1.5215, + "step": 2068 + }, + { + "epoch": 0.22, + "learning_rate": 1.9177240961001775e-05, + "loss": 1.5152, + "step": 2069 + }, + { + "epoch": 0.22, + "learning_rate": 1.9175786427471594e-05, + "loss": 1.4418, + "step": 2070 + }, + { + "epoch": 0.22, + "learning_rate": 1.91743306646218e-05, + "loss": 1.5001, + "step": 2071 + }, + { + "epoch": 0.22, + "learning_rate": 1.9172873672647417e-05, + "loss": 1.4879, + "step": 2072 + }, + { + "epoch": 0.22, + "learning_rate": 1.917141545174366e-05, + "loss": 1.5299, + "step": 2073 + }, + { + "epoch": 0.22, + "learning_rate": 1.9169956002105877e-05, + "loss": 1.4602, + "step": 2074 + }, + { + "epoch": 0.22, + "learning_rate": 1.9168495323929605e-05, + "loss": 1.4921, + "step": 2075 + }, + { + "epoch": 0.22, + "learning_rate": 1.916703341741054e-05, + "loss": 1.4659, + "step": 2076 + }, + { + "epoch": 0.22, + "learning_rate": 1.9165570282744534e-05, + "loss": 1.4707, + "step": 2077 + }, + { + "epoch": 0.22, + "learning_rate": 1.9164105920127613e-05, + "loss": 1.5354, + "step": 2078 + }, + { + "epoch": 0.22, + "learning_rate": 1.9162640329755962e-05, + "loss": 1.526, + "step": 2079 + }, + { + "epoch": 0.22, + "learning_rate": 1.916117351182593e-05, + "loss": 1.6424, + "step": 2080 + }, + { + "epoch": 0.22, + "learning_rate": 1.915970546653404e-05, + "loss": 1.5048, + "step": 2081 + }, + { + "epoch": 0.22, + "learning_rate": 1.915823619407697e-05, + "loss": 1.5344, + "step": 2082 + }, + { + "epoch": 0.22, + "learning_rate": 1.915676569465156e-05, + "loss": 1.4604, + "step": 2083 + }, + { + "epoch": 0.22, + "learning_rate": 1.9155293968454826e-05, + "loss": 1.4929, + "step": 2084 + }, + { + "epoch": 0.22, + "learning_rate": 1.9153821015683937e-05, + "loss": 1.4106, + "step": 2085 + }, + { + "epoch": 0.22, + "learning_rate": 1.915234683653623e-05, + "loss": 1.4146, + "step": 2086 + }, + { + "epoch": 0.22, + "learning_rate": 1.9150871431209207e-05, + "loss": 1.4481, + "step": 2087 + }, + { + "epoch": 0.22, + "learning_rate": 1.914939479990054e-05, + "loss": 1.5206, + "step": 2088 + }, + { + "epoch": 0.22, + "learning_rate": 1.9147916942808054e-05, + "loss": 1.5073, + "step": 2089 + }, + { + "epoch": 0.22, + "learning_rate": 1.9146437860129745e-05, + "loss": 1.5196, + "step": 2090 + }, + { + "epoch": 0.22, + "learning_rate": 1.9144957552063775e-05, + "loss": 1.5389, + "step": 2091 + }, + { + "epoch": 0.22, + "learning_rate": 1.9143476018808463e-05, + "loss": 1.5207, + "step": 2092 + }, + { + "epoch": 0.22, + "learning_rate": 1.9141993260562298e-05, + "loss": 1.3717, + "step": 2093 + }, + { + "epoch": 0.22, + "learning_rate": 1.9140509277523937e-05, + "loss": 1.471, + "step": 2094 + }, + { + "epoch": 0.22, + "learning_rate": 1.9139024069892185e-05, + "loss": 1.4553, + "step": 2095 + }, + { + "epoch": 0.22, + "learning_rate": 1.9137537637866027e-05, + "loss": 1.5311, + "step": 2096 + }, + { + "epoch": 0.22, + "learning_rate": 1.9136049981644614e-05, + "loss": 1.4369, + "step": 2097 + }, + { + "epoch": 0.22, + "learning_rate": 1.913456110142724e-05, + "loss": 1.4528, + "step": 2098 + }, + { + "epoch": 0.22, + "learning_rate": 1.9133070997413384e-05, + "loss": 1.5294, + "step": 2099 + }, + { + "epoch": 0.22, + "learning_rate": 1.9131579669802685e-05, + "loss": 1.4588, + "step": 2100 + }, + { + "epoch": 0.22, + "learning_rate": 1.9130087118794934e-05, + "loss": 1.443, + "step": 2101 + }, + { + "epoch": 0.22, + "learning_rate": 1.9128593344590102e-05, + "loss": 1.4876, + "step": 2102 + }, + { + "epoch": 0.22, + "learning_rate": 1.912709834738831e-05, + "loss": 1.4874, + "step": 2103 + }, + { + "epoch": 0.22, + "learning_rate": 1.9125602127389856e-05, + "loss": 1.4966, + "step": 2104 + }, + { + "epoch": 0.22, + "learning_rate": 1.912410468479519e-05, + "loss": 1.5747, + "step": 2105 + }, + { + "epoch": 0.22, + "learning_rate": 1.9122606019804933e-05, + "loss": 1.4025, + "step": 2106 + }, + { + "epoch": 0.22, + "learning_rate": 1.912110613261987e-05, + "loss": 1.4755, + "step": 2107 + }, + { + "epoch": 0.22, + "learning_rate": 1.911960502344094e-05, + "loss": 1.4739, + "step": 2108 + }, + { + "epoch": 0.22, + "learning_rate": 1.911810269246926e-05, + "loss": 1.4992, + "step": 2109 + }, + { + "epoch": 0.22, + "learning_rate": 1.91165991399061e-05, + "loss": 1.4435, + "step": 2110 + }, + { + "epoch": 0.22, + "learning_rate": 1.91150943659529e-05, + "loss": 1.4918, + "step": 2111 + }, + { + "epoch": 0.22, + "learning_rate": 1.9113588370811258e-05, + "loss": 1.3818, + "step": 2112 + }, + { + "epoch": 0.22, + "learning_rate": 1.911208115468294e-05, + "loss": 1.5105, + "step": 2113 + }, + { + "epoch": 0.22, + "learning_rate": 1.9110572717769878e-05, + "loss": 1.6634, + "step": 2114 + }, + { + "epoch": 0.22, + "learning_rate": 1.9109063060274158e-05, + "loss": 1.5028, + "step": 2115 + }, + { + "epoch": 0.22, + "learning_rate": 1.9107552182398037e-05, + "loss": 1.6657, + "step": 2116 + }, + { + "epoch": 0.22, + "learning_rate": 1.9106040084343935e-05, + "loss": 1.5481, + "step": 2117 + }, + { + "epoch": 0.22, + "learning_rate": 1.910452676631444e-05, + "loss": 1.4505, + "step": 2118 + }, + { + "epoch": 0.22, + "learning_rate": 1.9103012228512284e-05, + "loss": 1.5173, + "step": 2119 + }, + { + "epoch": 0.22, + "learning_rate": 1.9101496471140385e-05, + "loss": 1.3788, + "step": 2120 + }, + { + "epoch": 0.22, + "learning_rate": 1.9099979494401814e-05, + "loss": 1.4649, + "step": 2121 + }, + { + "epoch": 0.22, + "learning_rate": 1.9098461298499805e-05, + "loss": 1.4204, + "step": 2122 + }, + { + "epoch": 0.22, + "learning_rate": 1.9096941883637766e-05, + "loss": 1.4439, + "step": 2123 + }, + { + "epoch": 0.22, + "learning_rate": 1.909542125001925e-05, + "loss": 1.6615, + "step": 2124 + }, + { + "epoch": 0.22, + "learning_rate": 1.9093899397847985e-05, + "loss": 1.4763, + "step": 2125 + }, + { + "epoch": 0.22, + "learning_rate": 1.909237632732786e-05, + "loss": 1.5353, + "step": 2126 + }, + { + "epoch": 0.22, + "learning_rate": 1.909085203866293e-05, + "loss": 1.442, + "step": 2127 + }, + { + "epoch": 0.22, + "learning_rate": 1.9089326532057408e-05, + "loss": 1.4782, + "step": 2128 + }, + { + "epoch": 0.22, + "learning_rate": 1.908779980771567e-05, + "loss": 1.4933, + "step": 2129 + }, + { + "epoch": 0.22, + "learning_rate": 1.9086271865842264e-05, + "loss": 1.5285, + "step": 2130 + }, + { + "epoch": 0.22, + "learning_rate": 1.9084742706641894e-05, + "loss": 1.4736, + "step": 2131 + }, + { + "epoch": 0.22, + "learning_rate": 1.9083212330319427e-05, + "loss": 1.4496, + "step": 2132 + }, + { + "epoch": 0.22, + "learning_rate": 1.908168073707989e-05, + "loss": 1.5099, + "step": 2133 + }, + { + "epoch": 0.22, + "learning_rate": 1.9080147927128483e-05, + "loss": 1.5235, + "step": 2134 + }, + { + "epoch": 0.22, + "learning_rate": 1.9078613900670556e-05, + "loss": 1.4769, + "step": 2135 + }, + { + "epoch": 0.22, + "learning_rate": 1.907707865791164e-05, + "loss": 1.5771, + "step": 2136 + }, + { + "epoch": 0.22, + "learning_rate": 1.907554219905741e-05, + "loss": 1.5116, + "step": 2137 + }, + { + "epoch": 0.22, + "learning_rate": 1.907400452431371e-05, + "loss": 1.5161, + "step": 2138 + }, + { + "epoch": 0.22, + "learning_rate": 1.9072465633886557e-05, + "loss": 1.4356, + "step": 2139 + }, + { + "epoch": 0.22, + "learning_rate": 1.9070925527982117e-05, + "loss": 1.509, + "step": 2140 + }, + { + "epoch": 0.22, + "learning_rate": 1.9069384206806723e-05, + "loss": 1.4681, + "step": 2141 + }, + { + "epoch": 0.22, + "learning_rate": 1.9067841670566883e-05, + "loss": 1.5254, + "step": 2142 + }, + { + "epoch": 0.22, + "learning_rate": 1.9066297919469242e-05, + "loss": 1.4797, + "step": 2143 + }, + { + "epoch": 0.22, + "learning_rate": 1.9064752953720636e-05, + "loss": 1.3996, + "step": 2144 + }, + { + "epoch": 0.22, + "learning_rate": 1.9063206773528042e-05, + "loss": 1.4457, + "step": 2145 + }, + { + "epoch": 0.23, + "learning_rate": 1.9061659379098617e-05, + "loss": 1.5126, + "step": 2146 + }, + { + "epoch": 0.23, + "learning_rate": 1.9060110770639664e-05, + "loss": 1.5925, + "step": 2147 + }, + { + "epoch": 0.23, + "learning_rate": 1.905856094835866e-05, + "loss": 1.5146, + "step": 2148 + }, + { + "epoch": 0.23, + "learning_rate": 1.905700991246324e-05, + "loss": 1.7256, + "step": 2149 + }, + { + "epoch": 0.23, + "learning_rate": 1.90554576631612e-05, + "loss": 1.57, + "step": 2150 + }, + { + "epoch": 0.23, + "learning_rate": 1.905390420066051e-05, + "loss": 1.3722, + "step": 2151 + }, + { + "epoch": 0.23, + "learning_rate": 1.9052349525169292e-05, + "loss": 1.3999, + "step": 2152 + }, + { + "epoch": 0.23, + "learning_rate": 1.9050793636895828e-05, + "loss": 1.586, + "step": 2153 + }, + { + "epoch": 0.23, + "learning_rate": 1.9049236536048567e-05, + "loss": 1.4884, + "step": 2154 + }, + { + "epoch": 0.23, + "learning_rate": 1.9047678222836127e-05, + "loss": 1.5898, + "step": 2155 + }, + { + "epoch": 0.23, + "learning_rate": 1.9046118697467278e-05, + "loss": 1.569, + "step": 2156 + }, + { + "epoch": 0.23, + "learning_rate": 1.904455796015095e-05, + "loss": 1.5592, + "step": 2157 + }, + { + "epoch": 0.23, + "learning_rate": 1.9042996011096253e-05, + "loss": 1.597, + "step": 2158 + }, + { + "epoch": 0.23, + "learning_rate": 1.904143285051244e-05, + "loss": 1.422, + "step": 2159 + }, + { + "epoch": 0.23, + "learning_rate": 1.903986847860894e-05, + "loss": 1.519, + "step": 2160 + }, + { + "epoch": 0.23, + "learning_rate": 1.9038302895595334e-05, + "loss": 1.5197, + "step": 2161 + }, + { + "epoch": 0.23, + "learning_rate": 1.903673610168137e-05, + "loss": 1.4655, + "step": 2162 + }, + { + "epoch": 0.23, + "learning_rate": 1.9035168097076965e-05, + "loss": 1.3909, + "step": 2163 + }, + { + "epoch": 0.23, + "learning_rate": 1.903359888199218e-05, + "loss": 1.4877, + "step": 2164 + }, + { + "epoch": 0.23, + "learning_rate": 1.903202845663726e-05, + "loss": 1.5123, + "step": 2165 + }, + { + "epoch": 0.23, + "learning_rate": 1.9030456821222593e-05, + "loss": 1.4906, + "step": 2166 + }, + { + "epoch": 0.23, + "learning_rate": 1.9028883975958745e-05, + "loss": 1.4574, + "step": 2167 + }, + { + "epoch": 0.23, + "learning_rate": 1.9027309921056435e-05, + "loss": 1.4571, + "step": 2168 + }, + { + "epoch": 0.23, + "learning_rate": 1.902573465672654e-05, + "loss": 1.4281, + "step": 2169 + }, + { + "epoch": 0.23, + "learning_rate": 1.9024158183180116e-05, + "loss": 1.5057, + "step": 2170 + }, + { + "epoch": 0.23, + "learning_rate": 1.902258050062836e-05, + "loss": 1.4514, + "step": 2171 + }, + { + "epoch": 0.23, + "learning_rate": 1.9021001609282646e-05, + "loss": 1.5055, + "step": 2172 + }, + { + "epoch": 0.23, + "learning_rate": 1.9019421509354505e-05, + "loss": 1.4578, + "step": 2173 + }, + { + "epoch": 0.23, + "learning_rate": 1.9017840201055625e-05, + "loss": 1.459, + "step": 2174 + }, + { + "epoch": 0.23, + "learning_rate": 1.9016257684597864e-05, + "loss": 1.5059, + "step": 2175 + }, + { + "epoch": 0.23, + "learning_rate": 1.901467396019324e-05, + "loss": 1.57, + "step": 2176 + }, + { + "epoch": 0.23, + "learning_rate": 1.901308902805393e-05, + "loss": 1.4924, + "step": 2177 + }, + { + "epoch": 0.23, + "learning_rate": 1.9011502888392273e-05, + "loss": 1.4979, + "step": 2178 + }, + { + "epoch": 0.23, + "learning_rate": 1.900991554142077e-05, + "loss": 1.5321, + "step": 2179 + }, + { + "epoch": 0.23, + "learning_rate": 1.9008326987352093e-05, + "loss": 1.493, + "step": 2180 + }, + { + "epoch": 0.23, + "learning_rate": 1.9006737226399056e-05, + "loss": 1.5111, + "step": 2181 + }, + { + "epoch": 0.23, + "learning_rate": 1.900514625877465e-05, + "loss": 1.4154, + "step": 2182 + }, + { + "epoch": 0.23, + "learning_rate": 1.900355408469203e-05, + "loss": 1.4934, + "step": 2183 + }, + { + "epoch": 0.23, + "learning_rate": 1.90019607043645e-05, + "loss": 1.5975, + "step": 2184 + }, + { + "epoch": 0.23, + "learning_rate": 1.9000366118005532e-05, + "loss": 1.3537, + "step": 2185 + }, + { + "epoch": 0.23, + "learning_rate": 1.899877032582876e-05, + "loss": 1.4583, + "step": 2186 + }, + { + "epoch": 0.23, + "learning_rate": 1.8997173328047984e-05, + "loss": 1.4586, + "step": 2187 + }, + { + "epoch": 0.23, + "learning_rate": 1.8995575124877156e-05, + "loss": 1.4774, + "step": 2188 + }, + { + "epoch": 0.23, + "learning_rate": 1.8993975716530394e-05, + "loss": 1.5025, + "step": 2189 + }, + { + "epoch": 0.23, + "eval_loss": 1.5263344049453735, + "eval_runtime": 77.1492, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 2189 + }, + { + "epoch": 0.23, + "learning_rate": 1.899237510322198e-05, + "loss": 1.5438, + "step": 2190 + }, + { + "epoch": 0.23, + "learning_rate": 1.899077328516635e-05, + "loss": 1.5181, + "step": 2191 + }, + { + "epoch": 0.23, + "learning_rate": 1.8989170262578112e-05, + "loss": 1.4454, + "step": 2192 + }, + { + "epoch": 0.23, + "learning_rate": 1.8987566035672028e-05, + "loss": 1.4882, + "step": 2193 + }, + { + "epoch": 0.23, + "learning_rate": 1.8985960604663026e-05, + "loss": 1.5073, + "step": 2194 + }, + { + "epoch": 0.23, + "learning_rate": 1.8984353969766187e-05, + "loss": 1.4478, + "step": 2195 + }, + { + "epoch": 0.23, + "learning_rate": 1.8982746131196763e-05, + "loss": 1.4768, + "step": 2196 + }, + { + "epoch": 0.23, + "learning_rate": 1.8981137089170162e-05, + "loss": 1.5116, + "step": 2197 + }, + { + "epoch": 0.23, + "learning_rate": 1.8979526843901952e-05, + "loss": 1.4202, + "step": 2198 + }, + { + "epoch": 0.23, + "learning_rate": 1.8977915395607867e-05, + "loss": 1.4736, + "step": 2199 + }, + { + "epoch": 0.23, + "learning_rate": 1.89763027445038e-05, + "loss": 1.4489, + "step": 2200 + }, + { + "epoch": 0.23, + "learning_rate": 1.8974688890805804e-05, + "loss": 1.4512, + "step": 2201 + }, + { + "epoch": 0.23, + "learning_rate": 1.897307383473009e-05, + "loss": 1.5091, + "step": 2202 + }, + { + "epoch": 0.23, + "learning_rate": 1.897145757649304e-05, + "loss": 1.5512, + "step": 2203 + }, + { + "epoch": 0.23, + "learning_rate": 1.8969840116311192e-05, + "loss": 1.406, + "step": 2204 + }, + { + "epoch": 0.23, + "learning_rate": 1.896822145440124e-05, + "loss": 1.4531, + "step": 2205 + }, + { + "epoch": 0.23, + "learning_rate": 1.896660159098004e-05, + "loss": 1.4379, + "step": 2206 + }, + { + "epoch": 0.23, + "learning_rate": 1.896498052626462e-05, + "loss": 1.4783, + "step": 2207 + }, + { + "epoch": 0.23, + "learning_rate": 1.896335826047216e-05, + "loss": 1.4801, + "step": 2208 + }, + { + "epoch": 0.23, + "learning_rate": 1.896173479381999e-05, + "loss": 1.4526, + "step": 2209 + }, + { + "epoch": 0.23, + "learning_rate": 1.8960110126525627e-05, + "loss": 1.4952, + "step": 2210 + }, + { + "epoch": 0.23, + "learning_rate": 1.895848425880673e-05, + "loss": 1.5299, + "step": 2211 + }, + { + "epoch": 0.23, + "learning_rate": 1.8956857190881125e-05, + "loss": 1.5274, + "step": 2212 + }, + { + "epoch": 0.23, + "learning_rate": 1.8955228922966792e-05, + "loss": 1.4415, + "step": 2213 + }, + { + "epoch": 0.23, + "learning_rate": 1.8953599455281884e-05, + "loss": 1.5311, + "step": 2214 + }, + { + "epoch": 0.23, + "learning_rate": 1.8951968788044702e-05, + "loss": 1.4972, + "step": 2215 + }, + { + "epoch": 0.23, + "learning_rate": 1.8950336921473715e-05, + "loss": 1.4966, + "step": 2216 + }, + { + "epoch": 0.23, + "learning_rate": 1.8948703855787553e-05, + "loss": 1.4683, + "step": 2217 + }, + { + "epoch": 0.23, + "learning_rate": 1.8947069591205005e-05, + "loss": 1.503, + "step": 2218 + }, + { + "epoch": 0.23, + "learning_rate": 1.8945434127945014e-05, + "loss": 1.4902, + "step": 2219 + }, + { + "epoch": 0.23, + "learning_rate": 1.8943797466226702e-05, + "loss": 1.4835, + "step": 2220 + }, + { + "epoch": 0.23, + "learning_rate": 1.8942159606269332e-05, + "loss": 1.535, + "step": 2221 + }, + { + "epoch": 0.23, + "learning_rate": 1.8940520548292332e-05, + "loss": 1.491, + "step": 2222 + }, + { + "epoch": 0.23, + "learning_rate": 1.89388802925153e-05, + "loss": 1.5157, + "step": 2223 + }, + { + "epoch": 0.23, + "learning_rate": 1.8937238839157987e-05, + "loss": 1.4779, + "step": 2224 + }, + { + "epoch": 0.23, + "learning_rate": 1.8935596188440302e-05, + "loss": 1.4902, + "step": 2225 + }, + { + "epoch": 0.23, + "learning_rate": 1.8933952340582323e-05, + "loss": 1.4988, + "step": 2226 + }, + { + "epoch": 0.23, + "learning_rate": 1.893230729580428e-05, + "loss": 1.4568, + "step": 2227 + }, + { + "epoch": 0.23, + "learning_rate": 1.8930661054326567e-05, + "loss": 1.5163, + "step": 2228 + }, + { + "epoch": 0.23, + "learning_rate": 1.892901361636974e-05, + "loss": 1.4472, + "step": 2229 + }, + { + "epoch": 0.23, + "learning_rate": 1.892736498215451e-05, + "loss": 1.4658, + "step": 2230 + }, + { + "epoch": 0.23, + "learning_rate": 1.8925715151901754e-05, + "loss": 1.4281, + "step": 2231 + }, + { + "epoch": 0.23, + "learning_rate": 1.892406412583251e-05, + "loss": 1.415, + "step": 2232 + }, + { + "epoch": 0.23, + "learning_rate": 1.8922411904167966e-05, + "loss": 1.464, + "step": 2233 + }, + { + "epoch": 0.23, + "learning_rate": 1.892075848712948e-05, + "loss": 1.5014, + "step": 2234 + }, + { + "epoch": 0.23, + "learning_rate": 1.8919103874938568e-05, + "loss": 1.4397, + "step": 2235 + }, + { + "epoch": 0.23, + "learning_rate": 1.891744806781691e-05, + "loss": 1.5508, + "step": 2236 + }, + { + "epoch": 0.23, + "learning_rate": 1.8915791065986335e-05, + "loss": 1.4749, + "step": 2237 + }, + { + "epoch": 0.23, + "learning_rate": 1.891413286966884e-05, + "loss": 1.4538, + "step": 2238 + }, + { + "epoch": 0.23, + "learning_rate": 1.891247347908658e-05, + "loss": 1.4405, + "step": 2239 + }, + { + "epoch": 0.23, + "learning_rate": 1.8910812894461878e-05, + "loss": 1.3562, + "step": 2240 + }, + { + "epoch": 0.24, + "learning_rate": 1.89091511160172e-05, + "loss": 1.4811, + "step": 2241 + }, + { + "epoch": 0.24, + "learning_rate": 1.8907488143975186e-05, + "loss": 1.4286, + "step": 2242 + }, + { + "epoch": 0.24, + "learning_rate": 1.890582397855863e-05, + "loss": 1.4493, + "step": 2243 + }, + { + "epoch": 0.24, + "learning_rate": 1.890415861999049e-05, + "loss": 1.5639, + "step": 2244 + }, + { + "epoch": 0.24, + "learning_rate": 1.890249206849388e-05, + "loss": 1.6375, + "step": 2245 + }, + { + "epoch": 0.24, + "learning_rate": 1.890082432429208e-05, + "loss": 1.4982, + "step": 2246 + }, + { + "epoch": 0.24, + "learning_rate": 1.889915538760851e-05, + "loss": 1.492, + "step": 2247 + }, + { + "epoch": 0.24, + "learning_rate": 1.8897485258666778e-05, + "loss": 1.4294, + "step": 2248 + }, + { + "epoch": 0.24, + "learning_rate": 1.8895813937690638e-05, + "loss": 1.4617, + "step": 2249 + }, + { + "epoch": 0.24, + "learning_rate": 1.8894141424904e-05, + "loss": 1.4763, + "step": 2250 + }, + { + "epoch": 0.24, + "learning_rate": 1.8892467720530937e-05, + "loss": 1.3989, + "step": 2251 + }, + { + "epoch": 0.24, + "learning_rate": 1.8890792824795687e-05, + "loss": 1.4803, + "step": 2252 + }, + { + "epoch": 0.24, + "learning_rate": 1.8889116737922638e-05, + "loss": 1.4734, + "step": 2253 + }, + { + "epoch": 0.24, + "learning_rate": 1.8887439460136342e-05, + "loss": 1.5069, + "step": 2254 + }, + { + "epoch": 0.24, + "learning_rate": 1.8885760991661514e-05, + "loss": 1.5565, + "step": 2255 + }, + { + "epoch": 0.24, + "learning_rate": 1.8884081332723028e-05, + "loss": 1.4707, + "step": 2256 + }, + { + "epoch": 0.24, + "learning_rate": 1.8882400483545913e-05, + "loss": 1.5077, + "step": 2257 + }, + { + "epoch": 0.24, + "learning_rate": 1.888071844435536e-05, + "loss": 1.5075, + "step": 2258 + }, + { + "epoch": 0.24, + "learning_rate": 1.8879035215376717e-05, + "loss": 1.5185, + "step": 2259 + }, + { + "epoch": 0.24, + "learning_rate": 1.887735079683549e-05, + "loss": 1.6266, + "step": 2260 + }, + { + "epoch": 0.24, + "learning_rate": 1.8875665188957354e-05, + "loss": 1.5013, + "step": 2261 + }, + { + "epoch": 0.24, + "learning_rate": 1.887397839196814e-05, + "loss": 1.4362, + "step": 2262 + }, + { + "epoch": 0.24, + "learning_rate": 1.8872290406093827e-05, + "loss": 1.4718, + "step": 2263 + }, + { + "epoch": 0.24, + "learning_rate": 1.8870601231560567e-05, + "loss": 1.5202, + "step": 2264 + }, + { + "epoch": 0.24, + "learning_rate": 1.8868910868594664e-05, + "loss": 1.5168, + "step": 2265 + }, + { + "epoch": 0.24, + "learning_rate": 1.8867219317422588e-05, + "loss": 1.5142, + "step": 2266 + }, + { + "epoch": 0.24, + "learning_rate": 1.8865526578270954e-05, + "loss": 1.4885, + "step": 2267 + }, + { + "epoch": 0.24, + "learning_rate": 1.8863832651366552e-05, + "loss": 1.5441, + "step": 2268 + }, + { + "epoch": 0.24, + "learning_rate": 1.8862137536936328e-05, + "loss": 1.4647, + "step": 2269 + }, + { + "epoch": 0.24, + "learning_rate": 1.8860441235207374e-05, + "loss": 1.5352, + "step": 2270 + }, + { + "epoch": 0.24, + "learning_rate": 1.8858743746406958e-05, + "loss": 1.4568, + "step": 2271 + }, + { + "epoch": 0.24, + "learning_rate": 1.8857045070762497e-05, + "loss": 1.4865, + "step": 2272 + }, + { + "epoch": 0.24, + "learning_rate": 1.8855345208501573e-05, + "loss": 1.4637, + "step": 2273 + }, + { + "epoch": 0.24, + "learning_rate": 1.8853644159851918e-05, + "loss": 1.4348, + "step": 2274 + }, + { + "epoch": 0.24, + "learning_rate": 1.8851941925041436e-05, + "loss": 1.4413, + "step": 2275 + }, + { + "epoch": 0.24, + "learning_rate": 1.8850238504298177e-05, + "loss": 1.4434, + "step": 2276 + }, + { + "epoch": 0.24, + "learning_rate": 1.884853389785036e-05, + "loss": 1.4822, + "step": 2277 + }, + { + "epoch": 0.24, + "learning_rate": 1.8846828105926356e-05, + "loss": 1.4632, + "step": 2278 + }, + { + "epoch": 0.24, + "learning_rate": 1.8845121128754698e-05, + "loss": 1.48, + "step": 2279 + }, + { + "epoch": 0.24, + "learning_rate": 1.8843412966564078e-05, + "loss": 1.4518, + "step": 2280 + }, + { + "epoch": 0.24, + "learning_rate": 1.884170361958334e-05, + "loss": 1.4334, + "step": 2281 + }, + { + "epoch": 0.24, + "learning_rate": 1.8839993088041502e-05, + "loss": 1.5131, + "step": 2282 + }, + { + "epoch": 0.24, + "learning_rate": 1.8838281372167724e-05, + "loss": 1.508, + "step": 2283 + }, + { + "epoch": 0.24, + "learning_rate": 1.8836568472191335e-05, + "loss": 1.4086, + "step": 2284 + }, + { + "epoch": 0.24, + "learning_rate": 1.883485438834182e-05, + "loss": 1.5021, + "step": 2285 + }, + { + "epoch": 0.24, + "learning_rate": 1.8833139120848817e-05, + "loss": 1.5083, + "step": 2286 + }, + { + "epoch": 0.24, + "learning_rate": 1.8831422669942137e-05, + "loss": 1.4162, + "step": 2287 + }, + { + "epoch": 0.24, + "learning_rate": 1.8829705035851734e-05, + "loss": 1.5494, + "step": 2288 + }, + { + "epoch": 0.24, + "learning_rate": 1.8827986218807724e-05, + "loss": 1.425, + "step": 2289 + }, + { + "epoch": 0.24, + "learning_rate": 1.8826266219040396e-05, + "loss": 1.5215, + "step": 2290 + }, + { + "epoch": 0.24, + "learning_rate": 1.8824545036780172e-05, + "loss": 1.5577, + "step": 2291 + }, + { + "epoch": 0.24, + "learning_rate": 1.8822822672257655e-05, + "loss": 1.4923, + "step": 2292 + }, + { + "epoch": 0.24, + "learning_rate": 1.8821099125703595e-05, + "loss": 1.4648, + "step": 2293 + }, + { + "epoch": 0.24, + "learning_rate": 1.8819374397348902e-05, + "loss": 1.471, + "step": 2294 + }, + { + "epoch": 0.24, + "learning_rate": 1.8817648487424648e-05, + "loss": 1.5658, + "step": 2295 + }, + { + "epoch": 0.24, + "learning_rate": 1.8815921396162058e-05, + "loss": 1.5348, + "step": 2296 + }, + { + "epoch": 0.24, + "learning_rate": 1.8814193123792518e-05, + "loss": 1.4081, + "step": 2297 + }, + { + "epoch": 0.24, + "learning_rate": 1.881246367054757e-05, + "loss": 1.4762, + "step": 2298 + }, + { + "epoch": 0.24, + "learning_rate": 1.8810733036658925e-05, + "loss": 1.4399, + "step": 2299 + }, + { + "epoch": 0.24, + "learning_rate": 1.8809001222358432e-05, + "loss": 1.4763, + "step": 2300 + }, + { + "epoch": 0.24, + "learning_rate": 1.880726822787812e-05, + "loss": 1.4874, + "step": 2301 + }, + { + "epoch": 0.24, + "learning_rate": 1.880553405345016e-05, + "loss": 1.4951, + "step": 2302 + }, + { + "epoch": 0.24, + "learning_rate": 1.8803798699306887e-05, + "loss": 1.4697, + "step": 2303 + }, + { + "epoch": 0.24, + "learning_rate": 1.880206216568079e-05, + "loss": 1.481, + "step": 2304 + }, + { + "epoch": 0.24, + "learning_rate": 1.880032445280453e-05, + "loss": 1.4485, + "step": 2305 + }, + { + "epoch": 0.24, + "learning_rate": 1.879858556091091e-05, + "loss": 1.4749, + "step": 2306 + }, + { + "epoch": 0.24, + "learning_rate": 1.8796845490232894e-05, + "loss": 1.5605, + "step": 2307 + }, + { + "epoch": 0.24, + "learning_rate": 1.879510424100361e-05, + "loss": 1.4835, + "step": 2308 + }, + { + "epoch": 0.24, + "learning_rate": 1.8793361813456346e-05, + "loss": 1.4344, + "step": 2309 + }, + { + "epoch": 0.24, + "learning_rate": 1.8791618207824532e-05, + "loss": 1.4571, + "step": 2310 + }, + { + "epoch": 0.24, + "learning_rate": 1.8789873424341772e-05, + "loss": 1.482, + "step": 2311 + }, + { + "epoch": 0.24, + "learning_rate": 1.8788127463241822e-05, + "loss": 1.4736, + "step": 2312 + }, + { + "epoch": 0.24, + "learning_rate": 1.8786380324758597e-05, + "loss": 1.4807, + "step": 2313 + }, + { + "epoch": 0.24, + "learning_rate": 1.8784632009126167e-05, + "loss": 1.4418, + "step": 2314 + }, + { + "epoch": 0.24, + "learning_rate": 1.878288251657876e-05, + "loss": 1.5248, + "step": 2315 + }, + { + "epoch": 0.24, + "learning_rate": 1.8781131847350768e-05, + "loss": 1.483, + "step": 2316 + }, + { + "epoch": 0.24, + "learning_rate": 1.877938000167673e-05, + "loss": 1.5474, + "step": 2317 + }, + { + "epoch": 0.24, + "learning_rate": 1.8777626979791347e-05, + "loss": 1.4671, + "step": 2318 + }, + { + "epoch": 0.24, + "learning_rate": 1.877587278192949e-05, + "loss": 1.3049, + "step": 2319 + }, + { + "epoch": 0.24, + "learning_rate": 1.877411740832616e-05, + "loss": 1.483, + "step": 2320 + }, + { + "epoch": 0.24, + "learning_rate": 1.877236085921655e-05, + "loss": 1.508, + "step": 2321 + }, + { + "epoch": 0.24, + "learning_rate": 1.8770603134835978e-05, + "loss": 1.4854, + "step": 2322 + }, + { + "epoch": 0.24, + "learning_rate": 1.8768844235419942e-05, + "loss": 1.4808, + "step": 2323 + }, + { + "epoch": 0.24, + "learning_rate": 1.8767084161204087e-05, + "loss": 1.5352, + "step": 2324 + }, + { + "epoch": 0.24, + "learning_rate": 1.8765322912424214e-05, + "loss": 1.5628, + "step": 2325 + }, + { + "epoch": 0.24, + "learning_rate": 1.8763560489316292e-05, + "loss": 1.494, + "step": 2326 + }, + { + "epoch": 0.24, + "learning_rate": 1.876179689211643e-05, + "loss": 1.509, + "step": 2327 + }, + { + "epoch": 0.24, + "learning_rate": 1.8760032121060918e-05, + "loss": 1.5021, + "step": 2328 + }, + { + "epoch": 0.24, + "learning_rate": 1.875826617638618e-05, + "loss": 1.4179, + "step": 2329 + }, + { + "epoch": 0.24, + "learning_rate": 1.8756499058328813e-05, + "loss": 1.4302, + "step": 2330 + }, + { + "epoch": 0.24, + "learning_rate": 1.8754730767125564e-05, + "loss": 1.4959, + "step": 2331 + }, + { + "epoch": 0.24, + "learning_rate": 1.8752961303013336e-05, + "loss": 1.4423, + "step": 2332 + }, + { + "epoch": 0.24, + "learning_rate": 1.8751190666229194e-05, + "loss": 1.4564, + "step": 2333 + }, + { + "epoch": 0.24, + "learning_rate": 1.8749418857010358e-05, + "loss": 1.4775, + "step": 2334 + }, + { + "epoch": 0.24, + "learning_rate": 1.8747645875594203e-05, + "loss": 1.4182, + "step": 2335 + }, + { + "epoch": 0.24, + "learning_rate": 1.8745871722218265e-05, + "loss": 1.3957, + "step": 2336 + }, + { + "epoch": 0.25, + "learning_rate": 1.8744096397120235e-05, + "loss": 1.4633, + "step": 2337 + }, + { + "epoch": 0.25, + "learning_rate": 1.874231990053796e-05, + "loss": 1.5512, + "step": 2338 + }, + { + "epoch": 0.25, + "learning_rate": 1.8740542232709444e-05, + "loss": 1.3461, + "step": 2339 + }, + { + "epoch": 0.25, + "learning_rate": 1.8738763393872848e-05, + "loss": 1.4754, + "step": 2340 + }, + { + "epoch": 0.25, + "learning_rate": 1.8736983384266495e-05, + "loss": 1.5448, + "step": 2341 + }, + { + "epoch": 0.25, + "learning_rate": 1.8735202204128854e-05, + "loss": 1.4491, + "step": 2342 + }, + { + "epoch": 0.25, + "learning_rate": 1.8733419853698566e-05, + "loss": 1.457, + "step": 2343 + }, + { + "epoch": 0.25, + "learning_rate": 1.8731636333214414e-05, + "loss": 1.4314, + "step": 2344 + }, + { + "epoch": 0.25, + "learning_rate": 1.8729851642915345e-05, + "loss": 1.3979, + "step": 2345 + }, + { + "epoch": 0.25, + "learning_rate": 1.8728065783040464e-05, + "loss": 1.4146, + "step": 2346 + }, + { + "epoch": 0.25, + "learning_rate": 1.8726278753829027e-05, + "loss": 1.4361, + "step": 2347 + }, + { + "epoch": 0.25, + "learning_rate": 1.872449055552045e-05, + "loss": 1.4989, + "step": 2348 + }, + { + "epoch": 0.25, + "learning_rate": 1.872270118835431e-05, + "loss": 1.5062, + "step": 2349 + }, + { + "epoch": 0.25, + "learning_rate": 1.872091065257033e-05, + "loss": 1.4509, + "step": 2350 + }, + { + "epoch": 0.25, + "learning_rate": 1.8719118948408403e-05, + "loss": 1.4631, + "step": 2351 + }, + { + "epoch": 0.25, + "learning_rate": 1.8717326076108566e-05, + "loss": 1.5119, + "step": 2352 + }, + { + "epoch": 0.25, + "learning_rate": 1.8715532035911017e-05, + "loss": 1.6347, + "step": 2353 + }, + { + "epoch": 0.25, + "learning_rate": 1.8713736828056115e-05, + "loss": 1.5526, + "step": 2354 + }, + { + "epoch": 0.25, + "learning_rate": 1.8711940452784368e-05, + "loss": 1.6348, + "step": 2355 + }, + { + "epoch": 0.25, + "learning_rate": 1.871014291033645e-05, + "loss": 1.5183, + "step": 2356 + }, + { + "epoch": 0.25, + "learning_rate": 1.8708344200953182e-05, + "loss": 1.458, + "step": 2357 + }, + { + "epoch": 0.25, + "learning_rate": 1.8706544324875545e-05, + "loss": 1.524, + "step": 2358 + }, + { + "epoch": 0.25, + "learning_rate": 1.8704743282344672e-05, + "loss": 1.4479, + "step": 2359 + }, + { + "epoch": 0.25, + "learning_rate": 1.870294107360186e-05, + "loss": 1.5408, + "step": 2360 + }, + { + "epoch": 0.25, + "learning_rate": 1.8701137698888563e-05, + "loss": 1.5007, + "step": 2361 + }, + { + "epoch": 0.25, + "learning_rate": 1.8699333158446382e-05, + "loss": 1.5132, + "step": 2362 + }, + { + "epoch": 0.25, + "learning_rate": 1.869752745251708e-05, + "loss": 1.4263, + "step": 2363 + }, + { + "epoch": 0.25, + "learning_rate": 1.8695720581342574e-05, + "loss": 1.422, + "step": 2364 + }, + { + "epoch": 0.25, + "learning_rate": 1.869391254516494e-05, + "loss": 1.4411, + "step": 2365 + }, + { + "epoch": 0.25, + "learning_rate": 1.8692103344226406e-05, + "loss": 1.4594, + "step": 2366 + }, + { + "epoch": 0.25, + "learning_rate": 1.8690292978769364e-05, + "loss": 1.4992, + "step": 2367 + }, + { + "epoch": 0.25, + "learning_rate": 1.868848144903635e-05, + "loss": 1.4822, + "step": 2368 + }, + { + "epoch": 0.25, + "learning_rate": 1.8686668755270064e-05, + "loss": 1.5402, + "step": 2369 + }, + { + "epoch": 0.25, + "learning_rate": 1.8684854897713363e-05, + "loss": 1.5268, + "step": 2370 + }, + { + "epoch": 0.25, + "learning_rate": 1.8683039876609258e-05, + "loss": 1.5587, + "step": 2371 + }, + { + "epoch": 0.25, + "learning_rate": 1.868122369220091e-05, + "loss": 1.4214, + "step": 2372 + }, + { + "epoch": 0.25, + "learning_rate": 1.8679406344731645e-05, + "loss": 1.5089, + "step": 2373 + }, + { + "epoch": 0.25, + "learning_rate": 1.867758783444494e-05, + "loss": 1.5067, + "step": 2374 + }, + { + "epoch": 0.25, + "learning_rate": 1.8675768161584427e-05, + "loss": 2.0616, + "step": 2375 + }, + { + "epoch": 0.25, + "learning_rate": 1.8673947326393903e-05, + "loss": 1.5617, + "step": 2376 + }, + { + "epoch": 0.25, + "learning_rate": 1.86721253291173e-05, + "loss": 1.4422, + "step": 2377 + }, + { + "epoch": 0.25, + "learning_rate": 1.867030216999873e-05, + "loss": 1.4727, + "step": 2378 + }, + { + "epoch": 0.25, + "learning_rate": 1.8668477849282443e-05, + "loss": 1.4152, + "step": 2379 + }, + { + "epoch": 0.25, + "learning_rate": 1.8666652367212856e-05, + "loss": 1.4376, + "step": 2380 + }, + { + "epoch": 0.25, + "learning_rate": 1.8664825724034534e-05, + "loss": 1.393, + "step": 2381 + }, + { + "epoch": 0.25, + "learning_rate": 1.8662997919992197e-05, + "loss": 1.4864, + "step": 2382 + }, + { + "epoch": 0.25, + "learning_rate": 1.866116895533073e-05, + "loss": 1.4261, + "step": 2383 + }, + { + "epoch": 0.25, + "learning_rate": 1.8659338830295163e-05, + "loss": 1.4555, + "step": 2384 + }, + { + "epoch": 0.25, + "learning_rate": 1.8657507545130687e-05, + "loss": 1.4939, + "step": 2385 + }, + { + "epoch": 0.25, + "learning_rate": 1.865567510008265e-05, + "loss": 1.4123, + "step": 2386 + }, + { + "epoch": 0.25, + "learning_rate": 1.8653841495396546e-05, + "loss": 1.4459, + "step": 2387 + }, + { + "epoch": 0.25, + "learning_rate": 1.8652006731318038e-05, + "loss": 1.396, + "step": 2388 + }, + { + "epoch": 0.25, + "eval_loss": 1.5139706134796143, + "eval_runtime": 77.2904, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 2388 + }, + { + "epoch": 0.25, + "learning_rate": 1.8650170808092936e-05, + "loss": 1.4666, + "step": 2389 + }, + { + "epoch": 0.25, + "learning_rate": 1.86483337259672e-05, + "loss": 1.5154, + "step": 2390 + }, + { + "epoch": 0.25, + "learning_rate": 1.864649548518696e-05, + "loss": 1.5163, + "step": 2391 + }, + { + "epoch": 0.25, + "learning_rate": 1.864465608599849e-05, + "loss": 1.4734, + "step": 2392 + }, + { + "epoch": 0.25, + "learning_rate": 1.864281552864822e-05, + "loss": 1.5217, + "step": 2393 + }, + { + "epoch": 0.25, + "learning_rate": 1.8640973813382737e-05, + "loss": 1.4694, + "step": 2394 + }, + { + "epoch": 0.25, + "learning_rate": 1.863913094044879e-05, + "loss": 1.4761, + "step": 2395 + }, + { + "epoch": 0.25, + "learning_rate": 1.863728691009327e-05, + "loss": 1.4766, + "step": 2396 + }, + { + "epoch": 0.25, + "learning_rate": 1.863544172256323e-05, + "loss": 1.5695, + "step": 2397 + }, + { + "epoch": 0.25, + "learning_rate": 1.8633595378105882e-05, + "loss": 1.5079, + "step": 2398 + }, + { + "epoch": 0.25, + "learning_rate": 1.8631747876968584e-05, + "loss": 1.4154, + "step": 2399 + }, + { + "epoch": 0.25, + "learning_rate": 1.862989921939886e-05, + "loss": 1.4488, + "step": 2400 + }, + { + "epoch": 0.25, + "learning_rate": 1.8628049405644376e-05, + "loss": 1.4279, + "step": 2401 + }, + { + "epoch": 0.25, + "learning_rate": 1.8626198435952966e-05, + "loss": 1.4896, + "step": 2402 + }, + { + "epoch": 0.25, + "learning_rate": 1.8624346310572602e-05, + "loss": 1.4315, + "step": 2403 + }, + { + "epoch": 0.25, + "learning_rate": 1.862249302975143e-05, + "loss": 1.4919, + "step": 2404 + }, + { + "epoch": 0.25, + "learning_rate": 1.8620638593737743e-05, + "loss": 1.4561, + "step": 2405 + }, + { + "epoch": 0.25, + "learning_rate": 1.8618783002779985e-05, + "loss": 1.4622, + "step": 2406 + }, + { + "epoch": 0.25, + "learning_rate": 1.8616926257126754e-05, + "loss": 1.4917, + "step": 2407 + }, + { + "epoch": 0.25, + "learning_rate": 1.861506835702681e-05, + "loss": 1.4962, + "step": 2408 + }, + { + "epoch": 0.25, + "learning_rate": 1.861320930272906e-05, + "loss": 1.4164, + "step": 2409 + }, + { + "epoch": 0.25, + "learning_rate": 1.8611349094482578e-05, + "loss": 1.4889, + "step": 2410 + }, + { + "epoch": 0.25, + "learning_rate": 1.8609487732536576e-05, + "loss": 1.543, + "step": 2411 + }, + { + "epoch": 0.25, + "learning_rate": 1.8607625217140433e-05, + "loss": 1.5417, + "step": 2412 + }, + { + "epoch": 0.25, + "learning_rate": 1.8605761548543674e-05, + "loss": 1.5304, + "step": 2413 + }, + { + "epoch": 0.25, + "learning_rate": 1.860389672699599e-05, + "loss": 1.4725, + "step": 2414 + }, + { + "epoch": 0.25, + "learning_rate": 1.860203075274721e-05, + "loss": 1.4745, + "step": 2415 + }, + { + "epoch": 0.25, + "learning_rate": 1.8600163626047334e-05, + "loss": 1.4656, + "step": 2416 + }, + { + "epoch": 0.25, + "learning_rate": 1.8598295347146503e-05, + "loss": 1.5287, + "step": 2417 + }, + { + "epoch": 0.25, + "learning_rate": 1.8596425916295023e-05, + "loss": 1.5024, + "step": 2418 + }, + { + "epoch": 0.25, + "learning_rate": 1.8594555333743348e-05, + "loss": 1.4527, + "step": 2419 + }, + { + "epoch": 0.25, + "learning_rate": 1.859268359974209e-05, + "loss": 1.4897, + "step": 2420 + }, + { + "epoch": 0.25, + "learning_rate": 1.859081071454201e-05, + "loss": 1.3554, + "step": 2421 + }, + { + "epoch": 0.25, + "learning_rate": 1.858893667839403e-05, + "loss": 1.4004, + "step": 2422 + }, + { + "epoch": 0.25, + "learning_rate": 1.858706149154922e-05, + "loss": 1.5582, + "step": 2423 + }, + { + "epoch": 0.25, + "learning_rate": 1.8585185154258803e-05, + "loss": 1.505, + "step": 2424 + }, + { + "epoch": 0.25, + "learning_rate": 1.858330766677417e-05, + "loss": 1.5043, + "step": 2425 + }, + { + "epoch": 0.25, + "learning_rate": 1.858142902934685e-05, + "loss": 1.439, + "step": 2426 + }, + { + "epoch": 0.25, + "learning_rate": 1.857954924222853e-05, + "loss": 1.4927, + "step": 2427 + }, + { + "epoch": 0.25, + "learning_rate": 1.8577668305671056e-05, + "loss": 1.5395, + "step": 2428 + }, + { + "epoch": 0.25, + "learning_rate": 1.8575786219926427e-05, + "loss": 1.4737, + "step": 2429 + }, + { + "epoch": 0.25, + "learning_rate": 1.8573902985246794e-05, + "loss": 1.6151, + "step": 2430 + }, + { + "epoch": 0.25, + "learning_rate": 1.857201860188446e-05, + "loss": 1.4313, + "step": 2431 + }, + { + "epoch": 0.26, + "learning_rate": 1.857013307009188e-05, + "loss": 1.4509, + "step": 2432 + }, + { + "epoch": 0.26, + "learning_rate": 1.8568246390121673e-05, + "loss": 1.3998, + "step": 2433 + }, + { + "epoch": 0.26, + "learning_rate": 1.8566358562226603e-05, + "loss": 1.5268, + "step": 2434 + }, + { + "epoch": 0.26, + "learning_rate": 1.8564469586659593e-05, + "loss": 1.4369, + "step": 2435 + }, + { + "epoch": 0.26, + "learning_rate": 1.8562579463673713e-05, + "loss": 1.4759, + "step": 2436 + }, + { + "epoch": 0.26, + "learning_rate": 1.8560688193522197e-05, + "loss": 1.4092, + "step": 2437 + }, + { + "epoch": 0.26, + "learning_rate": 1.855879577645842e-05, + "loss": 1.43, + "step": 2438 + }, + { + "epoch": 0.26, + "learning_rate": 1.855690221273592e-05, + "loss": 1.5143, + "step": 2439 + }, + { + "epoch": 0.26, + "learning_rate": 1.8555007502608385e-05, + "loss": 1.5482, + "step": 2440 + }, + { + "epoch": 0.26, + "learning_rate": 1.855311164632966e-05, + "loss": 1.4406, + "step": 2441 + }, + { + "epoch": 0.26, + "learning_rate": 1.8551214644153738e-05, + "loss": 1.4551, + "step": 2442 + }, + { + "epoch": 0.26, + "learning_rate": 1.8549316496334774e-05, + "loss": 1.4663, + "step": 2443 + }, + { + "epoch": 0.26, + "learning_rate": 1.8547417203127064e-05, + "loss": 1.4732, + "step": 2444 + }, + { + "epoch": 0.26, + "learning_rate": 1.8545516764785067e-05, + "loss": 1.5378, + "step": 2445 + }, + { + "epoch": 0.26, + "learning_rate": 1.8543615181563397e-05, + "loss": 1.4448, + "step": 2446 + }, + { + "epoch": 0.26, + "learning_rate": 1.854171245371681e-05, + "loss": 1.2861, + "step": 2447 + }, + { + "epoch": 0.26, + "learning_rate": 1.8539808581500228e-05, + "loss": 1.4405, + "step": 2448 + }, + { + "epoch": 0.26, + "learning_rate": 1.8537903565168716e-05, + "loss": 1.4876, + "step": 2449 + }, + { + "epoch": 0.26, + "learning_rate": 1.8535997404977506e-05, + "loss": 1.4119, + "step": 2450 + }, + { + "epoch": 0.26, + "learning_rate": 1.8534090101181967e-05, + "loss": 1.4451, + "step": 2451 + }, + { + "epoch": 0.26, + "learning_rate": 1.8532181654037632e-05, + "loss": 1.4035, + "step": 2452 + }, + { + "epoch": 0.26, + "learning_rate": 1.853027206380018e-05, + "loss": 1.4624, + "step": 2453 + }, + { + "epoch": 0.26, + "learning_rate": 1.852836133072545e-05, + "loss": 1.4935, + "step": 2454 + }, + { + "epoch": 0.26, + "learning_rate": 1.8526449455069434e-05, + "loss": 1.4834, + "step": 2455 + }, + { + "epoch": 0.26, + "learning_rate": 1.8524536437088266e-05, + "loss": 1.498, + "step": 2456 + }, + { + "epoch": 0.26, + "learning_rate": 1.8522622277038247e-05, + "loss": 1.3417, + "step": 2457 + }, + { + "epoch": 0.26, + "learning_rate": 1.852070697517583e-05, + "loss": 1.4455, + "step": 2458 + }, + { + "epoch": 0.26, + "learning_rate": 1.8518790531757607e-05, + "loss": 1.4119, + "step": 2459 + }, + { + "epoch": 0.26, + "learning_rate": 1.8516872947040337e-05, + "loss": 1.558, + "step": 2460 + }, + { + "epoch": 0.26, + "learning_rate": 1.8514954221280926e-05, + "loss": 1.4862, + "step": 2461 + }, + { + "epoch": 0.26, + "learning_rate": 1.8513034354736433e-05, + "loss": 1.6806, + "step": 2462 + }, + { + "epoch": 0.26, + "learning_rate": 1.8511113347664072e-05, + "loss": 1.438, + "step": 2463 + }, + { + "epoch": 0.26, + "learning_rate": 1.850919120032121e-05, + "loss": 1.4975, + "step": 2464 + }, + { + "epoch": 0.26, + "learning_rate": 1.850726791296536e-05, + "loss": 1.4409, + "step": 2465 + }, + { + "epoch": 0.26, + "learning_rate": 1.85053434858542e-05, + "loss": 1.4769, + "step": 2466 + }, + { + "epoch": 0.26, + "learning_rate": 1.8503417919245548e-05, + "loss": 1.5823, + "step": 2467 + }, + { + "epoch": 0.26, + "learning_rate": 1.8501491213397386e-05, + "loss": 1.4045, + "step": 2468 + }, + { + "epoch": 0.26, + "learning_rate": 1.8499563368567837e-05, + "loss": 1.4828, + "step": 2469 + }, + { + "epoch": 0.26, + "learning_rate": 1.849763438501519e-05, + "loss": 1.4684, + "step": 2470 + }, + { + "epoch": 0.26, + "learning_rate": 1.8495704262997873e-05, + "loss": 1.4577, + "step": 2471 + }, + { + "epoch": 0.26, + "learning_rate": 1.8493773002774475e-05, + "loss": 1.4759, + "step": 2472 + }, + { + "epoch": 0.26, + "learning_rate": 1.8491840604603736e-05, + "loss": 1.4259, + "step": 2473 + }, + { + "epoch": 0.26, + "learning_rate": 1.8489907068744543e-05, + "loss": 1.4717, + "step": 2474 + }, + { + "epoch": 0.26, + "learning_rate": 1.848797239545595e-05, + "loss": 1.4247, + "step": 2475 + }, + { + "epoch": 0.26, + "learning_rate": 1.8486036584997143e-05, + "loss": 1.4954, + "step": 2476 + }, + { + "epoch": 0.26, + "learning_rate": 1.8484099637627472e-05, + "loss": 1.4926, + "step": 2477 + }, + { + "epoch": 0.26, + "learning_rate": 1.8482161553606447e-05, + "loss": 1.487, + "step": 2478 + }, + { + "epoch": 0.26, + "learning_rate": 1.8480222333193715e-05, + "loss": 1.4553, + "step": 2479 + }, + { + "epoch": 0.26, + "learning_rate": 1.847828197664908e-05, + "loss": 1.4862, + "step": 2480 + }, + { + "epoch": 0.26, + "learning_rate": 1.8476340484232508e-05, + "loss": 1.4867, + "step": 2481 + }, + { + "epoch": 0.26, + "learning_rate": 1.8474397856204097e-05, + "loss": 1.4736, + "step": 2482 + }, + { + "epoch": 0.26, + "learning_rate": 1.8472454092824122e-05, + "loss": 1.4254, + "step": 2483 + }, + { + "epoch": 0.26, + "learning_rate": 1.8470509194352987e-05, + "loss": 1.4455, + "step": 2484 + }, + { + "epoch": 0.26, + "learning_rate": 1.8468563161051263e-05, + "loss": 1.4402, + "step": 2485 + }, + { + "epoch": 0.26, + "learning_rate": 1.846661599317967e-05, + "loss": 1.4611, + "step": 2486 + }, + { + "epoch": 0.26, + "learning_rate": 1.8464667690999073e-05, + "loss": 1.4814, + "step": 2487 + }, + { + "epoch": 0.26, + "learning_rate": 1.8462718254770503e-05, + "loss": 1.4559, + "step": 2488 + }, + { + "epoch": 0.26, + "learning_rate": 1.8460767684755127e-05, + "loss": 1.4667, + "step": 2489 + }, + { + "epoch": 0.26, + "learning_rate": 1.8458815981214274e-05, + "loss": 1.4427, + "step": 2490 + }, + { + "epoch": 0.26, + "learning_rate": 1.845686314440942e-05, + "loss": 1.4055, + "step": 2491 + }, + { + "epoch": 0.26, + "learning_rate": 1.8454909174602198e-05, + "loss": 1.5563, + "step": 2492 + }, + { + "epoch": 0.26, + "learning_rate": 1.845295407205439e-05, + "loss": 1.4631, + "step": 2493 + }, + { + "epoch": 0.26, + "learning_rate": 1.8450997837027925e-05, + "loss": 1.4887, + "step": 2494 + }, + { + "epoch": 0.26, + "learning_rate": 1.8449040469784895e-05, + "loss": 1.5212, + "step": 2495 + }, + { + "epoch": 0.26, + "learning_rate": 1.844708197058753e-05, + "loss": 1.5582, + "step": 2496 + }, + { + "epoch": 0.26, + "learning_rate": 1.844512233969822e-05, + "loss": 1.4599, + "step": 2497 + }, + { + "epoch": 0.26, + "learning_rate": 1.844316157737951e-05, + "loss": 1.4546, + "step": 2498 + }, + { + "epoch": 0.26, + "learning_rate": 1.844119968389409e-05, + "loss": 1.4631, + "step": 2499 + }, + { + "epoch": 0.26, + "learning_rate": 1.84392366595048e-05, + "loss": 1.4817, + "step": 2500 + }, + { + "epoch": 0.26, + "learning_rate": 1.8437272504474636e-05, + "loss": 1.4214, + "step": 2501 + }, + { + "epoch": 0.26, + "learning_rate": 1.8435307219066744e-05, + "loss": 1.471, + "step": 2502 + }, + { + "epoch": 0.26, + "learning_rate": 1.8433340803544424e-05, + "loss": 1.4693, + "step": 2503 + }, + { + "epoch": 0.26, + "learning_rate": 1.8431373258171127e-05, + "loss": 1.6297, + "step": 2504 + }, + { + "epoch": 0.26, + "learning_rate": 1.842940458321045e-05, + "loss": 1.5916, + "step": 2505 + }, + { + "epoch": 0.26, + "learning_rate": 1.842743477892614e-05, + "loss": 1.4754, + "step": 2506 + }, + { + "epoch": 0.26, + "learning_rate": 1.842546384558211e-05, + "loss": 1.4828, + "step": 2507 + }, + { + "epoch": 0.26, + "learning_rate": 1.842349178344241e-05, + "loss": 1.4239, + "step": 2508 + }, + { + "epoch": 0.26, + "learning_rate": 1.8421518592771243e-05, + "loss": 1.5028, + "step": 2509 + }, + { + "epoch": 0.26, + "learning_rate": 1.841954427383297e-05, + "loss": 1.4848, + "step": 2510 + }, + { + "epoch": 0.26, + "learning_rate": 1.8417568826892097e-05, + "loss": 1.4617, + "step": 2511 + }, + { + "epoch": 0.26, + "learning_rate": 1.8415592252213284e-05, + "loss": 1.4266, + "step": 2512 + }, + { + "epoch": 0.26, + "learning_rate": 1.8413614550061344e-05, + "loss": 1.4321, + "step": 2513 + }, + { + "epoch": 0.26, + "learning_rate": 1.841163572070123e-05, + "loss": 1.4693, + "step": 2514 + }, + { + "epoch": 0.26, + "learning_rate": 1.840965576439806e-05, + "loss": 1.4257, + "step": 2515 + }, + { + "epoch": 0.26, + "learning_rate": 1.84076746814171e-05, + "loss": 1.4488, + "step": 2516 + }, + { + "epoch": 0.26, + "learning_rate": 1.840569247202376e-05, + "loss": 1.5348, + "step": 2517 + }, + { + "epoch": 0.26, + "learning_rate": 1.8403709136483604e-05, + "loss": 1.477, + "step": 2518 + }, + { + "epoch": 0.26, + "learning_rate": 1.840172467506235e-05, + "loss": 1.443, + "step": 2519 + }, + { + "epoch": 0.26, + "learning_rate": 1.839973908802587e-05, + "loss": 1.4772, + "step": 2520 + }, + { + "epoch": 0.26, + "learning_rate": 1.839775237564017e-05, + "loss": 1.4443, + "step": 2521 + }, + { + "epoch": 0.26, + "learning_rate": 1.839576453817143e-05, + "loss": 1.4063, + "step": 2522 + }, + { + "epoch": 0.26, + "learning_rate": 1.8393775575885963e-05, + "loss": 1.5178, + "step": 2523 + }, + { + "epoch": 0.26, + "learning_rate": 1.8391785489050235e-05, + "loss": 1.4337, + "step": 2524 + }, + { + "epoch": 0.26, + "learning_rate": 1.8389794277930875e-05, + "loss": 1.4512, + "step": 2525 + }, + { + "epoch": 0.26, + "learning_rate": 1.838780194279465e-05, + "loss": 1.5578, + "step": 2526 + }, + { + "epoch": 0.26, + "learning_rate": 1.8385808483908484e-05, + "loss": 1.4606, + "step": 2527 + }, + { + "epoch": 0.27, + "learning_rate": 1.8383813901539444e-05, + "loss": 1.4957, + "step": 2528 + }, + { + "epoch": 0.27, + "learning_rate": 1.838181819595476e-05, + "loss": 1.4914, + "step": 2529 + }, + { + "epoch": 0.27, + "learning_rate": 1.8379821367421802e-05, + "loss": 1.4785, + "step": 2530 + }, + { + "epoch": 0.27, + "learning_rate": 1.837782341620809e-05, + "loss": 1.4052, + "step": 2531 + }, + { + "epoch": 0.27, + "learning_rate": 1.8375824342581303e-05, + "loss": 1.4807, + "step": 2532 + }, + { + "epoch": 0.27, + "learning_rate": 1.8373824146809264e-05, + "loss": 1.4313, + "step": 2533 + }, + { + "epoch": 0.27, + "learning_rate": 1.8371822829159945e-05, + "loss": 1.4374, + "step": 2534 + }, + { + "epoch": 0.27, + "learning_rate": 1.836982038990148e-05, + "loss": 1.4482, + "step": 2535 + }, + { + "epoch": 0.27, + "learning_rate": 1.8367816829302133e-05, + "loss": 1.5231, + "step": 2536 + }, + { + "epoch": 0.27, + "learning_rate": 1.8365812147630337e-05, + "loss": 1.4101, + "step": 2537 + }, + { + "epoch": 0.27, + "learning_rate": 1.8363806345154666e-05, + "loss": 1.4372, + "step": 2538 + }, + { + "epoch": 0.27, + "learning_rate": 1.8361799422143845e-05, + "loss": 1.4808, + "step": 2539 + }, + { + "epoch": 0.27, + "learning_rate": 1.835979137886675e-05, + "loss": 1.3515, + "step": 2540 + }, + { + "epoch": 0.27, + "learning_rate": 1.8357782215592412e-05, + "loss": 1.5284, + "step": 2541 + }, + { + "epoch": 0.27, + "learning_rate": 1.835577193259e-05, + "loss": 1.4222, + "step": 2542 + }, + { + "epoch": 0.27, + "learning_rate": 1.8353760530128846e-05, + "loss": 1.4522, + "step": 2543 + }, + { + "epoch": 0.27, + "learning_rate": 1.835174800847842e-05, + "loss": 1.4487, + "step": 2544 + }, + { + "epoch": 0.27, + "learning_rate": 1.8349734367908355e-05, + "loss": 1.3688, + "step": 2545 + }, + { + "epoch": 0.27, + "learning_rate": 1.8347719608688422e-05, + "loss": 1.483, + "step": 2546 + }, + { + "epoch": 0.27, + "learning_rate": 1.8345703731088554e-05, + "loss": 1.4733, + "step": 2547 + }, + { + "epoch": 0.27, + "learning_rate": 1.8343686735378816e-05, + "loss": 1.4594, + "step": 2548 + }, + { + "epoch": 0.27, + "learning_rate": 1.834166862182944e-05, + "loss": 1.4648, + "step": 2549 + }, + { + "epoch": 0.27, + "learning_rate": 1.8339649390710807e-05, + "loss": 1.5249, + "step": 2550 + }, + { + "epoch": 0.27, + "learning_rate": 1.8337629042293434e-05, + "loss": 1.4744, + "step": 2551 + }, + { + "epoch": 0.27, + "learning_rate": 1.8335607576847994e-05, + "loss": 1.5094, + "step": 2552 + }, + { + "epoch": 0.27, + "learning_rate": 1.8333584994645318e-05, + "loss": 1.5122, + "step": 2553 + }, + { + "epoch": 0.27, + "learning_rate": 1.8331561295956374e-05, + "loss": 1.537, + "step": 2554 + }, + { + "epoch": 0.27, + "learning_rate": 1.832953648105229e-05, + "loss": 1.4691, + "step": 2555 + }, + { + "epoch": 0.27, + "learning_rate": 1.8327510550204343e-05, + "loss": 1.4969, + "step": 2556 + }, + { + "epoch": 0.27, + "learning_rate": 1.8325483503683944e-05, + "loss": 1.4596, + "step": 2557 + }, + { + "epoch": 0.27, + "learning_rate": 1.8323455341762675e-05, + "loss": 1.435, + "step": 2558 + }, + { + "epoch": 0.27, + "learning_rate": 1.8321426064712255e-05, + "loss": 1.4883, + "step": 2559 + }, + { + "epoch": 0.27, + "learning_rate": 1.8319395672804554e-05, + "loss": 1.3758, + "step": 2560 + }, + { + "epoch": 0.27, + "learning_rate": 1.8317364166311592e-05, + "loss": 1.4352, + "step": 2561 + }, + { + "epoch": 0.27, + "learning_rate": 1.831533154550554e-05, + "loss": 1.5072, + "step": 2562 + }, + { + "epoch": 0.27, + "learning_rate": 1.8313297810658718e-05, + "loss": 1.4476, + "step": 2563 + }, + { + "epoch": 0.27, + "learning_rate": 1.831126296204359e-05, + "loss": 1.507, + "step": 2564 + }, + { + "epoch": 0.27, + "learning_rate": 1.8309226999932777e-05, + "loss": 1.4677, + "step": 2565 + }, + { + "epoch": 0.27, + "learning_rate": 1.8307189924599044e-05, + "loss": 1.4537, + "step": 2566 + }, + { + "epoch": 0.27, + "learning_rate": 1.8305151736315307e-05, + "loss": 1.4584, + "step": 2567 + }, + { + "epoch": 0.27, + "learning_rate": 1.8303112435354634e-05, + "loss": 1.4944, + "step": 2568 + }, + { + "epoch": 0.27, + "learning_rate": 1.8301072021990232e-05, + "loss": 1.4379, + "step": 2569 + }, + { + "epoch": 0.27, + "learning_rate": 1.8299030496495475e-05, + "loss": 1.539, + "step": 2570 + }, + { + "epoch": 0.27, + "learning_rate": 1.829698785914386e-05, + "loss": 1.4421, + "step": 2571 + }, + { + "epoch": 0.27, + "learning_rate": 1.8294944110209063e-05, + "loss": 1.4693, + "step": 2572 + }, + { + "epoch": 0.27, + "learning_rate": 1.8292899249964887e-05, + "loss": 1.3239, + "step": 2573 + }, + { + "epoch": 0.27, + "learning_rate": 1.8290853278685284e-05, + "loss": 1.472, + "step": 2574 + }, + { + "epoch": 0.27, + "learning_rate": 1.8288806196644374e-05, + "loss": 1.536, + "step": 2575 + }, + { + "epoch": 0.27, + "learning_rate": 1.8286758004116405e-05, + "loss": 1.4644, + "step": 2576 + }, + { + "epoch": 0.27, + "learning_rate": 1.8284708701375783e-05, + "loss": 1.4537, + "step": 2577 + }, + { + "epoch": 0.27, + "learning_rate": 1.8282658288697067e-05, + "loss": 1.4359, + "step": 2578 + }, + { + "epoch": 0.27, + "learning_rate": 1.8280606766354955e-05, + "loss": 1.4842, + "step": 2579 + }, + { + "epoch": 0.27, + "learning_rate": 1.8278554134624302e-05, + "loss": 1.4664, + "step": 2580 + }, + { + "epoch": 0.27, + "learning_rate": 1.8276500393780105e-05, + "loss": 1.4632, + "step": 2581 + }, + { + "epoch": 0.27, + "learning_rate": 1.827444554409751e-05, + "loss": 1.4996, + "step": 2582 + }, + { + "epoch": 0.27, + "learning_rate": 1.827238958585182e-05, + "loss": 1.3399, + "step": 2583 + }, + { + "epoch": 0.27, + "learning_rate": 1.8270332519318476e-05, + "loss": 1.3928, + "step": 2584 + }, + { + "epoch": 0.27, + "learning_rate": 1.8268274344773074e-05, + "loss": 1.4993, + "step": 2585 + }, + { + "epoch": 0.27, + "learning_rate": 1.8266215062491356e-05, + "loss": 1.5398, + "step": 2586 + }, + { + "epoch": 0.27, + "learning_rate": 1.826415467274921e-05, + "loss": 1.4353, + "step": 2587 + }, + { + "epoch": 0.27, + "eval_loss": 1.5104212760925293, + "eval_runtime": 77.3448, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2587 + }, + { + "epoch": 0.27, + "learning_rate": 1.8262093175822685e-05, + "loss": 1.4889, + "step": 2588 + }, + { + "epoch": 0.27, + "learning_rate": 1.826003057198796e-05, + "loss": 1.4912, + "step": 2589 + }, + { + "epoch": 0.27, + "learning_rate": 1.825796686152137e-05, + "loss": 1.4884, + "step": 2590 + }, + { + "epoch": 0.27, + "learning_rate": 1.8255902044699404e-05, + "loss": 1.478, + "step": 2591 + }, + { + "epoch": 0.27, + "learning_rate": 1.8253836121798692e-05, + "loss": 1.6549, + "step": 2592 + }, + { + "epoch": 0.27, + "learning_rate": 1.8251769093096018e-05, + "loss": 1.5146, + "step": 2593 + }, + { + "epoch": 0.27, + "learning_rate": 1.8249700958868306e-05, + "loss": 1.4797, + "step": 2594 + }, + { + "epoch": 0.27, + "learning_rate": 1.8247631719392634e-05, + "loss": 1.4655, + "step": 2595 + }, + { + "epoch": 0.27, + "learning_rate": 1.824556137494623e-05, + "loss": 1.4517, + "step": 2596 + }, + { + "epoch": 0.27, + "learning_rate": 1.8243489925806458e-05, + "loss": 1.4936, + "step": 2597 + }, + { + "epoch": 0.27, + "learning_rate": 1.8241417372250852e-05, + "loss": 1.4614, + "step": 2598 + }, + { + "epoch": 0.27, + "learning_rate": 1.8239343714557073e-05, + "loss": 1.4475, + "step": 2599 + }, + { + "epoch": 0.27, + "learning_rate": 1.8237268953002937e-05, + "loss": 1.5435, + "step": 2600 + }, + { + "epoch": 0.27, + "learning_rate": 1.8235193087866413e-05, + "loss": 1.4616, + "step": 2601 + }, + { + "epoch": 0.27, + "learning_rate": 1.8233116119425612e-05, + "loss": 1.4578, + "step": 2602 + }, + { + "epoch": 0.27, + "learning_rate": 1.8231038047958795e-05, + "loss": 1.434, + "step": 2603 + }, + { + "epoch": 0.27, + "learning_rate": 1.8228958873744368e-05, + "loss": 1.5335, + "step": 2604 + }, + { + "epoch": 0.27, + "learning_rate": 1.8226878597060887e-05, + "loss": 1.415, + "step": 2605 + }, + { + "epoch": 0.27, + "learning_rate": 1.8224797218187058e-05, + "loss": 1.6165, + "step": 2606 + }, + { + "epoch": 0.27, + "learning_rate": 1.822271473740173e-05, + "loss": 1.372, + "step": 2607 + }, + { + "epoch": 0.27, + "learning_rate": 1.8220631154983907e-05, + "loss": 1.4855, + "step": 2608 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218546471212727e-05, + "loss": 1.4093, + "step": 2609 + }, + { + "epoch": 0.27, + "learning_rate": 1.821646068636749e-05, + "loss": 1.4852, + "step": 2610 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214373800727637e-05, + "loss": 1.6959, + "step": 2611 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212285814572755e-05, + "loss": 1.3874, + "step": 2612 + }, + { + "epoch": 0.27, + "learning_rate": 1.821019672818258e-05, + "loss": 1.4425, + "step": 2613 + }, + { + "epoch": 0.27, + "learning_rate": 1.8208106541837e-05, + "loss": 1.6097, + "step": 2614 + }, + { + "epoch": 0.27, + "learning_rate": 1.8206015255816045e-05, + "loss": 1.5675, + "step": 2615 + }, + { + "epoch": 0.27, + "learning_rate": 1.820392287039989e-05, + "loss": 1.4039, + "step": 2616 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201829385868866e-05, + "loss": 1.4872, + "step": 2617 + }, + { + "epoch": 0.27, + "learning_rate": 1.819973480250344e-05, + "loss": 1.4645, + "step": 2618 + }, + { + "epoch": 0.27, + "learning_rate": 1.8197639120584237e-05, + "loss": 1.4923, + "step": 2619 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195542340392025e-05, + "loss": 1.4294, + "step": 2620 + }, + { + "epoch": 0.27, + "learning_rate": 1.8193444462207717e-05, + "loss": 1.4315, + "step": 2621 + }, + { + "epoch": 0.27, + "learning_rate": 1.8191345486312372e-05, + "loss": 1.3972, + "step": 2622 + }, + { + "epoch": 0.28, + "learning_rate": 1.8189245412987205e-05, + "loss": 1.462, + "step": 2623 + }, + { + "epoch": 0.28, + "learning_rate": 1.8187144242513567e-05, + "loss": 1.4738, + "step": 2624 + }, + { + "epoch": 0.28, + "learning_rate": 1.818504197517296e-05, + "loss": 1.4935, + "step": 2625 + }, + { + "epoch": 0.28, + "learning_rate": 1.8182938611247038e-05, + "loss": 1.4231, + "step": 2626 + }, + { + "epoch": 0.28, + "learning_rate": 1.81808341510176e-05, + "loss": 1.4031, + "step": 2627 + }, + { + "epoch": 0.28, + "learning_rate": 1.817872859476658e-05, + "loss": 1.5822, + "step": 2628 + }, + { + "epoch": 0.28, + "learning_rate": 1.8176621942776075e-05, + "loss": 1.432, + "step": 2629 + }, + { + "epoch": 0.28, + "learning_rate": 1.8174514195328324e-05, + "loss": 1.5565, + "step": 2630 + }, + { + "epoch": 0.28, + "learning_rate": 1.8172405352705704e-05, + "loss": 1.4895, + "step": 2631 + }, + { + "epoch": 0.28, + "learning_rate": 1.8170295415190754e-05, + "loss": 1.4032, + "step": 2632 + }, + { + "epoch": 0.28, + "learning_rate": 1.8168184383066144e-05, + "loss": 1.4253, + "step": 2633 + }, + { + "epoch": 0.28, + "learning_rate": 1.8166072256614702e-05, + "loss": 1.5162, + "step": 2634 + }, + { + "epoch": 0.28, + "learning_rate": 1.81639590361194e-05, + "loss": 1.4609, + "step": 2635 + }, + { + "epoch": 0.28, + "learning_rate": 1.816184472186335e-05, + "loss": 1.4351, + "step": 2636 + }, + { + "epoch": 0.28, + "learning_rate": 1.8159729314129823e-05, + "loss": 1.4738, + "step": 2637 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157612813202224e-05, + "loss": 1.5986, + "step": 2638 + }, + { + "epoch": 0.28, + "learning_rate": 1.815549521936411e-05, + "loss": 1.4633, + "step": 2639 + }, + { + "epoch": 0.28, + "learning_rate": 1.8153376532899184e-05, + "loss": 1.4404, + "step": 2640 + }, + { + "epoch": 0.28, + "learning_rate": 1.81512567540913e-05, + "loss": 1.4256, + "step": 2641 + }, + { + "epoch": 0.28, + "learning_rate": 1.814913588322445e-05, + "loss": 1.4054, + "step": 2642 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147013920582773e-05, + "loss": 1.4134, + "step": 2643 + }, + { + "epoch": 0.28, + "learning_rate": 1.8144890866450567e-05, + "loss": 1.4098, + "step": 2644 + }, + { + "epoch": 0.28, + "learning_rate": 1.814276672111226e-05, + "loss": 1.4593, + "step": 2645 + }, + { + "epoch": 0.28, + "learning_rate": 1.814064148485243e-05, + "loss": 1.4679, + "step": 2646 + }, + { + "epoch": 0.28, + "learning_rate": 1.8138515157955812e-05, + "loss": 1.5234, + "step": 2647 + }, + { + "epoch": 0.28, + "learning_rate": 1.8136387740707272e-05, + "loss": 1.4568, + "step": 2648 + }, + { + "epoch": 0.28, + "learning_rate": 1.8134259233391836e-05, + "loss": 1.5057, + "step": 2649 + }, + { + "epoch": 0.28, + "learning_rate": 1.8132129636294665e-05, + "loss": 1.3643, + "step": 2650 + }, + { + "epoch": 0.28, + "learning_rate": 1.812999894970107e-05, + "loss": 1.4766, + "step": 2651 + }, + { + "epoch": 0.28, + "learning_rate": 1.812786717389651e-05, + "loss": 1.5701, + "step": 2652 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125734309166587e-05, + "loss": 1.5341, + "step": 2653 + }, + { + "epoch": 0.28, + "learning_rate": 1.812360035579705e-05, + "loss": 1.3596, + "step": 2654 + }, + { + "epoch": 0.28, + "learning_rate": 1.8121465314073793e-05, + "loss": 1.4847, + "step": 2655 + }, + { + "epoch": 0.28, + "learning_rate": 1.811932918428286e-05, + "loss": 1.4664, + "step": 2656 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117191966710438e-05, + "loss": 1.4673, + "step": 2657 + }, + { + "epoch": 0.28, + "learning_rate": 1.8115053661642856e-05, + "loss": 1.4712, + "step": 2658 + }, + { + "epoch": 0.28, + "learning_rate": 1.811291426936659e-05, + "loss": 1.4458, + "step": 2659 + }, + { + "epoch": 0.28, + "learning_rate": 1.811077379016827e-05, + "loss": 1.4667, + "step": 2660 + }, + { + "epoch": 0.28, + "learning_rate": 1.810863222433466e-05, + "loss": 1.4695, + "step": 2661 + }, + { + "epoch": 0.28, + "learning_rate": 1.8106489572152677e-05, + "loss": 1.5263, + "step": 2662 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104345833909376e-05, + "loss": 1.4148, + "step": 2663 + }, + { + "epoch": 0.28, + "learning_rate": 1.8102201009891976e-05, + "loss": 1.3955, + "step": 2664 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100055100387814e-05, + "loss": 1.6056, + "step": 2665 + }, + { + "epoch": 0.28, + "learning_rate": 1.8097908105684396e-05, + "loss": 1.5394, + "step": 2666 + }, + { + "epoch": 0.28, + "learning_rate": 1.809576002606936e-05, + "loss": 1.479, + "step": 2667 + }, + { + "epoch": 0.28, + "learning_rate": 1.8093610861830494e-05, + "loss": 1.4492, + "step": 2668 + }, + { + "epoch": 0.28, + "learning_rate": 1.8091460613255728e-05, + "loss": 1.4172, + "step": 2669 + }, + { + "epoch": 0.28, + "learning_rate": 1.808930928063315e-05, + "loss": 1.4498, + "step": 2670 + }, + { + "epoch": 0.28, + "learning_rate": 1.808715686425097e-05, + "loss": 1.6203, + "step": 2671 + }, + { + "epoch": 0.28, + "learning_rate": 1.8085003364397567e-05, + "loss": 1.435, + "step": 2672 + }, + { + "epoch": 0.28, + "learning_rate": 1.808284878136145e-05, + "loss": 1.4489, + "step": 2673 + }, + { + "epoch": 0.28, + "learning_rate": 1.8080693115431277e-05, + "loss": 1.4416, + "step": 2674 + }, + { + "epoch": 0.28, + "learning_rate": 1.8078536366895853e-05, + "loss": 1.422, + "step": 2675 + }, + { + "epoch": 0.28, + "learning_rate": 1.8076378536044128e-05, + "loss": 1.4039, + "step": 2676 + }, + { + "epoch": 0.28, + "learning_rate": 1.8074219623165195e-05, + "loss": 1.4705, + "step": 2677 + }, + { + "epoch": 0.28, + "learning_rate": 1.807205962854829e-05, + "loss": 1.5031, + "step": 2678 + }, + { + "epoch": 0.28, + "learning_rate": 1.8069898552482806e-05, + "loss": 1.4812, + "step": 2679 + }, + { + "epoch": 0.28, + "learning_rate": 1.806773639525826e-05, + "loss": 1.4129, + "step": 2680 + }, + { + "epoch": 0.28, + "learning_rate": 1.8065573157164332e-05, + "loss": 1.4559, + "step": 2681 + }, + { + "epoch": 0.28, + "learning_rate": 1.806340883849084e-05, + "loss": 1.3878, + "step": 2682 + }, + { + "epoch": 0.28, + "learning_rate": 1.8061243439527744e-05, + "loss": 1.4752, + "step": 2683 + }, + { + "epoch": 0.28, + "learning_rate": 1.8059076960565156e-05, + "loss": 1.4089, + "step": 2684 + }, + { + "epoch": 0.28, + "learning_rate": 1.8056909401893326e-05, + "loss": 1.4736, + "step": 2685 + }, + { + "epoch": 0.28, + "learning_rate": 1.8054740763802654e-05, + "loss": 1.3796, + "step": 2686 + }, + { + "epoch": 0.28, + "learning_rate": 1.805257104658368e-05, + "loss": 1.4412, + "step": 2687 + }, + { + "epoch": 0.28, + "learning_rate": 1.8050400250527086e-05, + "loss": 1.4639, + "step": 2688 + }, + { + "epoch": 0.28, + "learning_rate": 1.804822837592371e-05, + "loss": 1.4076, + "step": 2689 + }, + { + "epoch": 0.28, + "learning_rate": 1.804605542306452e-05, + "loss": 1.4627, + "step": 2690 + }, + { + "epoch": 0.28, + "learning_rate": 1.8043881392240642e-05, + "loss": 1.5249, + "step": 2691 + }, + { + "epoch": 0.28, + "learning_rate": 1.804170628374334e-05, + "loss": 1.4312, + "step": 2692 + }, + { + "epoch": 0.28, + "learning_rate": 1.803953009786402e-05, + "loss": 1.5676, + "step": 2693 + }, + { + "epoch": 0.28, + "learning_rate": 1.8037352834894233e-05, + "loss": 1.5072, + "step": 2694 + }, + { + "epoch": 0.28, + "learning_rate": 1.803517449512568e-05, + "loss": 1.5662, + "step": 2695 + }, + { + "epoch": 0.28, + "learning_rate": 1.8032995078850207e-05, + "loss": 1.4771, + "step": 2696 + }, + { + "epoch": 0.28, + "learning_rate": 1.803081458635979e-05, + "loss": 1.412, + "step": 2697 + }, + { + "epoch": 0.28, + "learning_rate": 1.8028633017946564e-05, + "loss": 1.497, + "step": 2698 + }, + { + "epoch": 0.28, + "learning_rate": 1.8026450373902804e-05, + "loss": 1.4528, + "step": 2699 + }, + { + "epoch": 0.28, + "learning_rate": 1.802426665452093e-05, + "loss": 1.4785, + "step": 2700 + }, + { + "epoch": 0.28, + "learning_rate": 1.8022081860093493e-05, + "loss": 1.6411, + "step": 2701 + }, + { + "epoch": 0.28, + "learning_rate": 1.8019895990913213e-05, + "loss": 1.4459, + "step": 2702 + }, + { + "epoch": 0.28, + "learning_rate": 1.8017709047272932e-05, + "loss": 1.4418, + "step": 2703 + }, + { + "epoch": 0.28, + "learning_rate": 1.801552102946565e-05, + "loss": 1.4409, + "step": 2704 + }, + { + "epoch": 0.28, + "learning_rate": 1.8013331937784498e-05, + "loss": 1.4651, + "step": 2705 + }, + { + "epoch": 0.28, + "learning_rate": 1.8011141772522766e-05, + "loss": 1.4161, + "step": 2706 + }, + { + "epoch": 0.28, + "learning_rate": 1.8008950533973876e-05, + "loss": 1.458, + "step": 2707 + }, + { + "epoch": 0.28, + "learning_rate": 1.8006758222431398e-05, + "loss": 1.4477, + "step": 2708 + }, + { + "epoch": 0.28, + "learning_rate": 1.800456483818904e-05, + "loss": 1.4433, + "step": 2709 + }, + { + "epoch": 0.28, + "learning_rate": 1.8002370381540672e-05, + "loss": 1.5005, + "step": 2710 + }, + { + "epoch": 0.28, + "learning_rate": 1.8000174852780282e-05, + "loss": 1.4945, + "step": 2711 + }, + { + "epoch": 0.28, + "learning_rate": 1.7997978252202023e-05, + "loss": 1.4298, + "step": 2712 + }, + { + "epoch": 0.28, + "learning_rate": 1.7995780580100177e-05, + "loss": 1.3812, + "step": 2713 + }, + { + "epoch": 0.28, + "learning_rate": 1.799358183676918e-05, + "loss": 1.5559, + "step": 2714 + }, + { + "epoch": 0.28, + "learning_rate": 1.79913820225036e-05, + "loss": 1.4316, + "step": 2715 + }, + { + "epoch": 0.28, + "learning_rate": 1.798918113759817e-05, + "loss": 1.419, + "step": 2716 + }, + { + "epoch": 0.28, + "learning_rate": 1.7986979182347733e-05, + "loss": 1.43, + "step": 2717 + }, + { + "epoch": 0.29, + "learning_rate": 1.798477615704731e-05, + "loss": 1.4964, + "step": 2718 + }, + { + "epoch": 0.29, + "learning_rate": 1.7982572061992044e-05, + "loss": 1.4417, + "step": 2719 + }, + { + "epoch": 0.29, + "learning_rate": 1.7980366897477227e-05, + "loss": 1.4562, + "step": 2720 + }, + { + "epoch": 0.29, + "learning_rate": 1.7978160663798295e-05, + "loss": 1.4386, + "step": 2721 + }, + { + "epoch": 0.29, + "learning_rate": 1.7975953361250824e-05, + "loss": 1.445, + "step": 2722 + }, + { + "epoch": 0.29, + "learning_rate": 1.797374499013054e-05, + "loss": 1.4549, + "step": 2723 + }, + { + "epoch": 0.29, + "learning_rate": 1.7971535550733305e-05, + "loss": 1.5205, + "step": 2724 + }, + { + "epoch": 0.29, + "learning_rate": 1.796932504335513e-05, + "loss": 1.4632, + "step": 2725 + }, + { + "epoch": 0.29, + "learning_rate": 1.796711346829216e-05, + "loss": 1.3767, + "step": 2726 + }, + { + "epoch": 0.29, + "learning_rate": 1.79649008258407e-05, + "loss": 1.4098, + "step": 2727 + }, + { + "epoch": 0.29, + "learning_rate": 1.7962687116297178e-05, + "loss": 1.4675, + "step": 2728 + }, + { + "epoch": 0.29, + "learning_rate": 1.7960472339958176e-05, + "loss": 1.6048, + "step": 2729 + }, + { + "epoch": 0.29, + "learning_rate": 1.7958256497120418e-05, + "loss": 1.5432, + "step": 2730 + }, + { + "epoch": 0.29, + "learning_rate": 1.7956039588080774e-05, + "loss": 1.5453, + "step": 2731 + }, + { + "epoch": 0.29, + "learning_rate": 1.7953821613136246e-05, + "loss": 1.4246, + "step": 2732 + }, + { + "epoch": 0.29, + "learning_rate": 1.7951602572583988e-05, + "loss": 1.3987, + "step": 2733 + }, + { + "epoch": 0.29, + "learning_rate": 1.7949382466721295e-05, + "loss": 1.4943, + "step": 2734 + }, + { + "epoch": 0.29, + "learning_rate": 1.7947161295845606e-05, + "loss": 1.4385, + "step": 2735 + }, + { + "epoch": 0.29, + "learning_rate": 1.7944939060254497e-05, + "loss": 1.4165, + "step": 2736 + }, + { + "epoch": 0.29, + "learning_rate": 1.7942715760245692e-05, + "loss": 1.4004, + "step": 2737 + }, + { + "epoch": 0.29, + "learning_rate": 1.7940491396117063e-05, + "loss": 1.4577, + "step": 2738 + }, + { + "epoch": 0.29, + "learning_rate": 1.7938265968166602e-05, + "loss": 1.4649, + "step": 2739 + }, + { + "epoch": 0.29, + "learning_rate": 1.7936039476692473e-05, + "loss": 1.5273, + "step": 2740 + }, + { + "epoch": 0.29, + "learning_rate": 1.7933811921992962e-05, + "loss": 1.4325, + "step": 2741 + }, + { + "epoch": 0.29, + "learning_rate": 1.793158330436651e-05, + "loss": 1.4388, + "step": 2742 + }, + { + "epoch": 0.29, + "learning_rate": 1.7929353624111687e-05, + "loss": 1.4124, + "step": 2743 + }, + { + "epoch": 0.29, + "learning_rate": 1.7927122881527222e-05, + "loss": 1.5449, + "step": 2744 + }, + { + "epoch": 0.29, + "learning_rate": 1.7924891076911964e-05, + "loss": 1.4728, + "step": 2745 + }, + { + "epoch": 0.29, + "learning_rate": 1.7922658210564932e-05, + "loss": 1.5103, + "step": 2746 + }, + { + "epoch": 0.29, + "learning_rate": 1.792042428278526e-05, + "loss": 1.5975, + "step": 2747 + }, + { + "epoch": 0.29, + "learning_rate": 1.7918189293872247e-05, + "loss": 1.567, + "step": 2748 + }, + { + "epoch": 0.29, + "learning_rate": 1.7915953244125318e-05, + "loss": 1.57, + "step": 2749 + }, + { + "epoch": 0.29, + "learning_rate": 1.791371613384405e-05, + "loss": 1.4372, + "step": 2750 + }, + { + "epoch": 0.29, + "learning_rate": 1.7911477963328155e-05, + "loss": 1.4053, + "step": 2751 + }, + { + "epoch": 0.29, + "learning_rate": 1.7909238732877492e-05, + "loss": 1.3782, + "step": 2752 + }, + { + "epoch": 0.29, + "learning_rate": 1.790699844279206e-05, + "loss": 1.4401, + "step": 2753 + }, + { + "epoch": 0.29, + "learning_rate": 1.7904757093372e-05, + "loss": 1.3749, + "step": 2754 + }, + { + "epoch": 0.29, + "learning_rate": 1.79025146849176e-05, + "loss": 1.4909, + "step": 2755 + }, + { + "epoch": 0.29, + "learning_rate": 1.7900271217729273e-05, + "loss": 1.4103, + "step": 2756 + }, + { + "epoch": 0.29, + "learning_rate": 1.7898026692107597e-05, + "loss": 1.4986, + "step": 2757 + }, + { + "epoch": 0.29, + "learning_rate": 1.7895781108353278e-05, + "loss": 1.5449, + "step": 2758 + }, + { + "epoch": 0.29, + "learning_rate": 1.789353446676717e-05, + "loss": 1.5583, + "step": 2759 + }, + { + "epoch": 0.29, + "learning_rate": 1.7891286767650254e-05, + "loss": 1.5342, + "step": 2760 + }, + { + "epoch": 0.29, + "learning_rate": 1.7889038011303673e-05, + "loss": 1.4233, + "step": 2761 + }, + { + "epoch": 0.29, + "learning_rate": 1.7886788198028707e-05, + "loss": 1.3433, + "step": 2762 + }, + { + "epoch": 0.29, + "learning_rate": 1.788453732812676e-05, + "loss": 1.4451, + "step": 2763 + }, + { + "epoch": 0.29, + "learning_rate": 1.78822854018994e-05, + "loss": 1.4506, + "step": 2764 + }, + { + "epoch": 0.29, + "learning_rate": 1.7880032419648324e-05, + "loss": 1.4386, + "step": 2765 + }, + { + "epoch": 0.29, + "learning_rate": 1.7877778381675374e-05, + "loss": 1.4512, + "step": 2766 + }, + { + "epoch": 0.29, + "learning_rate": 1.7875523288282535e-05, + "loss": 1.4319, + "step": 2767 + }, + { + "epoch": 0.29, + "learning_rate": 1.7873267139771932e-05, + "loss": 1.4753, + "step": 2768 + }, + { + "epoch": 0.29, + "learning_rate": 1.787100993644583e-05, + "loss": 1.4044, + "step": 2769 + }, + { + "epoch": 0.29, + "learning_rate": 1.786875167860663e-05, + "loss": 1.4382, + "step": 2770 + }, + { + "epoch": 0.29, + "learning_rate": 1.786649236655689e-05, + "loss": 1.3977, + "step": 2771 + }, + { + "epoch": 0.29, + "learning_rate": 1.7864232000599298e-05, + "loss": 1.4473, + "step": 2772 + }, + { + "epoch": 0.29, + "learning_rate": 1.7861970581036678e-05, + "loss": 1.4666, + "step": 2773 + }, + { + "epoch": 0.29, + "learning_rate": 1.785970810817201e-05, + "loss": 1.5299, + "step": 2774 + }, + { + "epoch": 0.29, + "learning_rate": 1.7857444582308402e-05, + "loss": 1.3974, + "step": 2775 + }, + { + "epoch": 0.29, + "learning_rate": 1.7855180003749114e-05, + "loss": 1.4603, + "step": 2776 + }, + { + "epoch": 0.29, + "learning_rate": 1.7852914372797535e-05, + "loss": 1.463, + "step": 2777 + }, + { + "epoch": 0.29, + "learning_rate": 1.7850647689757205e-05, + "loss": 1.5317, + "step": 2778 + }, + { + "epoch": 0.29, + "learning_rate": 1.78483799549318e-05, + "loss": 1.4669, + "step": 2779 + }, + { + "epoch": 0.29, + "learning_rate": 1.784611116862514e-05, + "loss": 1.5293, + "step": 2780 + }, + { + "epoch": 0.29, + "learning_rate": 1.7843841331141177e-05, + "loss": 1.5802, + "step": 2781 + }, + { + "epoch": 0.29, + "learning_rate": 1.7841570442784024e-05, + "loss": 1.4486, + "step": 2782 + }, + { + "epoch": 0.29, + "learning_rate": 1.7839298503857913e-05, + "loss": 1.4674, + "step": 2783 + }, + { + "epoch": 0.29, + "learning_rate": 1.7837025514667224e-05, + "loss": 1.4662, + "step": 2784 + }, + { + "epoch": 0.29, + "learning_rate": 1.7834751475516484e-05, + "loss": 1.3555, + "step": 2785 + }, + { + "epoch": 0.29, + "learning_rate": 1.783247638671035e-05, + "loss": 1.4307, + "step": 2786 + }, + { + "epoch": 0.29, + "eval_loss": 1.500258445739746, + "eval_runtime": 77.406, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 2786 + }, + { + "epoch": 0.29, + "learning_rate": 1.7830200248553633e-05, + "loss": 1.4596, + "step": 2787 + }, + { + "epoch": 0.29, + "learning_rate": 1.7827923061351273e-05, + "loss": 1.6118, + "step": 2788 + }, + { + "epoch": 0.29, + "learning_rate": 1.7825644825408353e-05, + "loss": 1.4782, + "step": 2789 + }, + { + "epoch": 0.29, + "learning_rate": 1.78233655410301e-05, + "loss": 1.4681, + "step": 2790 + }, + { + "epoch": 0.29, + "learning_rate": 1.782108520852188e-05, + "loss": 1.6281, + "step": 2791 + }, + { + "epoch": 0.29, + "learning_rate": 1.78188038281892e-05, + "loss": 1.4446, + "step": 2792 + }, + { + "epoch": 0.29, + "learning_rate": 1.7816521400337704e-05, + "loss": 1.479, + "step": 2793 + }, + { + "epoch": 0.29, + "learning_rate": 1.7814237925273178e-05, + "loss": 1.5457, + "step": 2794 + }, + { + "epoch": 0.29, + "learning_rate": 1.7811953403301547e-05, + "loss": 1.3928, + "step": 2795 + }, + { + "epoch": 0.29, + "learning_rate": 1.780966783472889e-05, + "loss": 1.4321, + "step": 2796 + }, + { + "epoch": 0.29, + "learning_rate": 1.78073812198614e-05, + "loss": 1.5734, + "step": 2797 + }, + { + "epoch": 0.29, + "learning_rate": 1.7805093559005432e-05, + "loss": 1.4356, + "step": 2798 + }, + { + "epoch": 0.29, + "learning_rate": 1.7802804852467473e-05, + "loss": 1.4656, + "step": 2799 + }, + { + "epoch": 0.29, + "learning_rate": 1.780051510055415e-05, + "loss": 1.4052, + "step": 2800 + }, + { + "epoch": 0.29, + "learning_rate": 1.7798224303572228e-05, + "loss": 1.4758, + "step": 2801 + }, + { + "epoch": 0.29, + "learning_rate": 1.7795932461828622e-05, + "loss": 1.4326, + "step": 2802 + }, + { + "epoch": 0.29, + "learning_rate": 1.7793639575630376e-05, + "loss": 1.3409, + "step": 2803 + }, + { + "epoch": 0.29, + "learning_rate": 1.7791345645284678e-05, + "loss": 1.4175, + "step": 2804 + }, + { + "epoch": 0.29, + "learning_rate": 1.7789050671098853e-05, + "loss": 1.383, + "step": 2805 + }, + { + "epoch": 0.29, + "learning_rate": 1.7786754653380373e-05, + "loss": 1.5162, + "step": 2806 + }, + { + "epoch": 0.29, + "learning_rate": 1.7784457592436847e-05, + "loss": 1.4899, + "step": 2807 + }, + { + "epoch": 0.29, + "learning_rate": 1.7782159488576016e-05, + "loss": 1.4874, + "step": 2808 + }, + { + "epoch": 0.29, + "learning_rate": 1.777986034210577e-05, + "loss": 1.4363, + "step": 2809 + }, + { + "epoch": 0.29, + "learning_rate": 1.7777560153334134e-05, + "loss": 1.4223, + "step": 2810 + }, + { + "epoch": 0.29, + "learning_rate": 1.7775258922569273e-05, + "loss": 1.4792, + "step": 2811 + }, + { + "epoch": 0.29, + "learning_rate": 1.77729566501195e-05, + "loss": 1.4475, + "step": 2812 + }, + { + "epoch": 0.29, + "learning_rate": 1.7770653336293253e-05, + "loss": 1.5157, + "step": 2813 + }, + { + "epoch": 0.3, + "learning_rate": 1.776834898139912e-05, + "loss": 1.389, + "step": 2814 + }, + { + "epoch": 0.3, + "learning_rate": 1.7766043585745824e-05, + "loss": 1.4358, + "step": 2815 + }, + { + "epoch": 0.3, + "learning_rate": 1.776373714964223e-05, + "loss": 1.4297, + "step": 2816 + }, + { + "epoch": 0.3, + "learning_rate": 1.7761429673397344e-05, + "loss": 1.4102, + "step": 2817 + }, + { + "epoch": 0.3, + "learning_rate": 1.77591211573203e-05, + "loss": 1.4572, + "step": 2818 + }, + { + "epoch": 0.3, + "learning_rate": 1.775681160172039e-05, + "loss": 1.448, + "step": 2819 + }, + { + "epoch": 0.3, + "learning_rate": 1.7754501006907025e-05, + "loss": 1.4426, + "step": 2820 + }, + { + "epoch": 0.3, + "learning_rate": 1.7752189373189773e-05, + "loss": 1.4566, + "step": 2821 + }, + { + "epoch": 0.3, + "learning_rate": 1.7749876700878332e-05, + "loss": 1.4267, + "step": 2822 + }, + { + "epoch": 0.3, + "learning_rate": 1.7747562990282538e-05, + "loss": 1.3951, + "step": 2823 + }, + { + "epoch": 0.3, + "learning_rate": 1.7745248241712373e-05, + "loss": 1.4668, + "step": 2824 + }, + { + "epoch": 0.3, + "learning_rate": 1.774293245547795e-05, + "loss": 1.4924, + "step": 2825 + }, + { + "epoch": 0.3, + "learning_rate": 1.7740615631889525e-05, + "loss": 1.5258, + "step": 2826 + }, + { + "epoch": 0.3, + "learning_rate": 1.7738297771257496e-05, + "loss": 1.4323, + "step": 2827 + }, + { + "epoch": 0.3, + "learning_rate": 1.7735978873892393e-05, + "loss": 1.439, + "step": 2828 + }, + { + "epoch": 0.3, + "learning_rate": 1.773365894010489e-05, + "loss": 1.5658, + "step": 2829 + }, + { + "epoch": 0.3, + "learning_rate": 1.77313379702058e-05, + "loss": 1.4607, + "step": 2830 + }, + { + "epoch": 0.3, + "learning_rate": 1.7729015964506073e-05, + "loss": 1.5544, + "step": 2831 + }, + { + "epoch": 0.3, + "learning_rate": 1.7726692923316798e-05, + "loss": 1.4232, + "step": 2832 + }, + { + "epoch": 0.3, + "learning_rate": 1.77243688469492e-05, + "loss": 1.415, + "step": 2833 + }, + { + "epoch": 0.3, + "learning_rate": 1.772204373571465e-05, + "loss": 1.4658, + "step": 2834 + }, + { + "epoch": 0.3, + "learning_rate": 1.7719717589924647e-05, + "loss": 1.4678, + "step": 2835 + }, + { + "epoch": 0.3, + "learning_rate": 1.771739040989084e-05, + "loss": 1.3021, + "step": 2836 + }, + { + "epoch": 0.3, + "learning_rate": 1.771506219592501e-05, + "loss": 1.4045, + "step": 2837 + }, + { + "epoch": 0.3, + "learning_rate": 1.7712732948339085e-05, + "loss": 1.4593, + "step": 2838 + }, + { + "epoch": 0.3, + "learning_rate": 1.7710402667445108e-05, + "loss": 1.4175, + "step": 2839 + }, + { + "epoch": 0.3, + "learning_rate": 1.770807135355529e-05, + "loss": 1.3939, + "step": 2840 + }, + { + "epoch": 0.3, + "learning_rate": 1.7705739006981963e-05, + "loss": 1.6089, + "step": 2841 + }, + { + "epoch": 0.3, + "learning_rate": 1.77034056280376e-05, + "loss": 1.3952, + "step": 2842 + }, + { + "epoch": 0.3, + "learning_rate": 1.7701071217034818e-05, + "loss": 1.5086, + "step": 2843 + }, + { + "epoch": 0.3, + "learning_rate": 1.7698735774286362e-05, + "loss": 1.4706, + "step": 2844 + }, + { + "epoch": 0.3, + "learning_rate": 1.7696399300105128e-05, + "loss": 1.4286, + "step": 2845 + }, + { + "epoch": 0.3, + "learning_rate": 1.7694061794804137e-05, + "loss": 1.4418, + "step": 2846 + }, + { + "epoch": 0.3, + "learning_rate": 1.7691723258696562e-05, + "loss": 1.516, + "step": 2847 + }, + { + "epoch": 0.3, + "learning_rate": 1.76893836920957e-05, + "loss": 1.4354, + "step": 2848 + }, + { + "epoch": 0.3, + "learning_rate": 1.7687043095314998e-05, + "loss": 1.7503, + "step": 2849 + }, + { + "epoch": 0.3, + "learning_rate": 1.7684701468668032e-05, + "loss": 1.5985, + "step": 2850 + }, + { + "epoch": 0.3, + "learning_rate": 1.768235881246852e-05, + "loss": 1.442, + "step": 2851 + }, + { + "epoch": 0.3, + "learning_rate": 1.7680015127030322e-05, + "loss": 1.4924, + "step": 2852 + }, + { + "epoch": 0.3, + "learning_rate": 1.7677670412667425e-05, + "loss": 1.4461, + "step": 2853 + }, + { + "epoch": 0.3, + "learning_rate": 1.7675324669693968e-05, + "loss": 1.3823, + "step": 2854 + }, + { + "epoch": 0.3, + "learning_rate": 1.767297789842421e-05, + "loss": 1.452, + "step": 2855 + }, + { + "epoch": 0.3, + "learning_rate": 1.767063009917257e-05, + "loss": 1.46, + "step": 2856 + }, + { + "epoch": 0.3, + "learning_rate": 1.7668281272253587e-05, + "loss": 1.4129, + "step": 2857 + }, + { + "epoch": 0.3, + "learning_rate": 1.766593141798194e-05, + "loss": 1.4057, + "step": 2858 + }, + { + "epoch": 0.3, + "learning_rate": 1.7663580536672456e-05, + "loss": 1.5162, + "step": 2859 + }, + { + "epoch": 0.3, + "learning_rate": 1.7661228628640087e-05, + "loss": 1.5177, + "step": 2860 + }, + { + "epoch": 0.3, + "learning_rate": 1.7658875694199933e-05, + "loss": 1.4548, + "step": 2861 + }, + { + "epoch": 0.3, + "learning_rate": 1.7656521733667223e-05, + "loss": 1.4511, + "step": 2862 + }, + { + "epoch": 0.3, + "learning_rate": 1.765416674735733e-05, + "loss": 1.4778, + "step": 2863 + }, + { + "epoch": 0.3, + "learning_rate": 1.765181073558576e-05, + "loss": 1.3935, + "step": 2864 + }, + { + "epoch": 0.3, + "learning_rate": 1.7649453698668156e-05, + "loss": 1.4659, + "step": 2865 + }, + { + "epoch": 0.3, + "learning_rate": 1.7647095636920305e-05, + "loss": 1.7042, + "step": 2866 + }, + { + "epoch": 0.3, + "learning_rate": 1.7644736550658124e-05, + "loss": 1.7957, + "step": 2867 + }, + { + "epoch": 0.3, + "learning_rate": 1.764237644019767e-05, + "loss": 1.5139, + "step": 2868 + }, + { + "epoch": 0.3, + "learning_rate": 1.764001530585514e-05, + "loss": 1.4117, + "step": 2869 + }, + { + "epoch": 0.3, + "learning_rate": 1.7637653147946858e-05, + "loss": 1.4837, + "step": 2870 + }, + { + "epoch": 0.3, + "learning_rate": 1.7635289966789298e-05, + "loss": 1.4379, + "step": 2871 + }, + { + "epoch": 0.3, + "learning_rate": 1.7632925762699068e-05, + "loss": 1.4491, + "step": 2872 + }, + { + "epoch": 0.3, + "learning_rate": 1.7630560535992905e-05, + "loss": 1.4006, + "step": 2873 + }, + { + "epoch": 0.3, + "learning_rate": 1.7628194286987694e-05, + "loss": 1.5484, + "step": 2874 + }, + { + "epoch": 0.3, + "learning_rate": 1.7625827016000446e-05, + "loss": 1.4926, + "step": 2875 + }, + { + "epoch": 0.3, + "learning_rate": 1.762345872334832e-05, + "loss": 1.3909, + "step": 2876 + }, + { + "epoch": 0.3, + "learning_rate": 1.76210894093486e-05, + "loss": 1.405, + "step": 2877 + }, + { + "epoch": 0.3, + "learning_rate": 1.7618719074318718e-05, + "loss": 1.4736, + "step": 2878 + }, + { + "epoch": 0.3, + "learning_rate": 1.7616347718576238e-05, + "loss": 1.4445, + "step": 2879 + }, + { + "epoch": 0.3, + "learning_rate": 1.761397534243886e-05, + "loss": 1.4878, + "step": 2880 + }, + { + "epoch": 0.3, + "learning_rate": 1.7611601946224417e-05, + "loss": 1.4414, + "step": 2881 + }, + { + "epoch": 0.3, + "learning_rate": 1.760922753025089e-05, + "loss": 1.5657, + "step": 2882 + }, + { + "epoch": 0.3, + "learning_rate": 1.7606852094836385e-05, + "loss": 1.5008, + "step": 2883 + }, + { + "epoch": 0.3, + "learning_rate": 1.7604475640299153e-05, + "loss": 1.4922, + "step": 2884 + }, + { + "epoch": 0.3, + "learning_rate": 1.7602098166957577e-05, + "loss": 1.7451, + "step": 2885 + }, + { + "epoch": 0.3, + "learning_rate": 1.759971967513017e-05, + "loss": 1.7077, + "step": 2886 + }, + { + "epoch": 0.3, + "learning_rate": 1.75973401651356e-05, + "loss": 1.3986, + "step": 2887 + }, + { + "epoch": 0.3, + "learning_rate": 1.7594959637292656e-05, + "loss": 1.3966, + "step": 2888 + }, + { + "epoch": 0.3, + "learning_rate": 1.7592578091920264e-05, + "loss": 1.4086, + "step": 2889 + }, + { + "epoch": 0.3, + "learning_rate": 1.7590195529337495e-05, + "loss": 1.4481, + "step": 2890 + }, + { + "epoch": 0.3, + "learning_rate": 1.7587811949863548e-05, + "loss": 1.3974, + "step": 2891 + }, + { + "epoch": 0.3, + "learning_rate": 1.7585427353817758e-05, + "loss": 1.5013, + "step": 2892 + }, + { + "epoch": 0.3, + "learning_rate": 1.7583041741519608e-05, + "loss": 1.5454, + "step": 2893 + }, + { + "epoch": 0.3, + "learning_rate": 1.7580655113288708e-05, + "loss": 1.5033, + "step": 2894 + }, + { + "epoch": 0.3, + "learning_rate": 1.7578267469444793e-05, + "loss": 1.4332, + "step": 2895 + }, + { + "epoch": 0.3, + "learning_rate": 1.757587881030776e-05, + "loss": 1.4667, + "step": 2896 + }, + { + "epoch": 0.3, + "learning_rate": 1.7573489136197623e-05, + "loss": 1.4314, + "step": 2897 + }, + { + "epoch": 0.3, + "learning_rate": 1.7571098447434532e-05, + "loss": 1.4514, + "step": 2898 + }, + { + "epoch": 0.3, + "learning_rate": 1.7568706744338784e-05, + "loss": 1.4872, + "step": 2899 + }, + { + "epoch": 0.3, + "learning_rate": 1.7566314027230808e-05, + "loss": 1.4841, + "step": 2900 + }, + { + "epoch": 0.3, + "learning_rate": 1.7563920296431158e-05, + "loss": 1.3964, + "step": 2901 + }, + { + "epoch": 0.3, + "learning_rate": 1.7561525552260538e-05, + "loss": 1.4932, + "step": 2902 + }, + { + "epoch": 0.3, + "learning_rate": 1.755912979503978e-05, + "loss": 1.4153, + "step": 2903 + }, + { + "epoch": 0.3, + "learning_rate": 1.755673302508986e-05, + "loss": 1.4939, + "step": 2904 + }, + { + "epoch": 0.3, + "learning_rate": 1.755433524273187e-05, + "loss": 1.4437, + "step": 2905 + }, + { + "epoch": 0.3, + "learning_rate": 1.7551936448287067e-05, + "loss": 1.486, + "step": 2906 + }, + { + "epoch": 0.3, + "learning_rate": 1.754953664207682e-05, + "loss": 1.4362, + "step": 2907 + }, + { + "epoch": 0.3, + "learning_rate": 1.7547135824422635e-05, + "loss": 1.4954, + "step": 2908 + }, + { + "epoch": 0.31, + "learning_rate": 1.7544733995646174e-05, + "loss": 1.4552, + "step": 2909 + }, + { + "epoch": 0.31, + "learning_rate": 1.7542331156069213e-05, + "loss": 1.4654, + "step": 2910 + }, + { + "epoch": 0.31, + "learning_rate": 1.753992730601367e-05, + "loss": 1.4531, + "step": 2911 + }, + { + "epoch": 0.31, + "learning_rate": 1.75375224458016e-05, + "loss": 1.4949, + "step": 2912 + }, + { + "epoch": 0.31, + "learning_rate": 1.753511657575519e-05, + "loss": 1.3998, + "step": 2913 + }, + { + "epoch": 0.31, + "learning_rate": 1.753270969619677e-05, + "loss": 1.3904, + "step": 2914 + }, + { + "epoch": 0.31, + "learning_rate": 1.7530301807448794e-05, + "loss": 1.481, + "step": 2915 + }, + { + "epoch": 0.31, + "learning_rate": 1.7527892909833864e-05, + "loss": 1.4301, + "step": 2916 + }, + { + "epoch": 0.31, + "learning_rate": 1.7525483003674707e-05, + "loss": 1.4377, + "step": 2917 + }, + { + "epoch": 0.31, + "learning_rate": 1.7523072089294188e-05, + "loss": 1.5077, + "step": 2918 + }, + { + "epoch": 0.31, + "learning_rate": 1.752066016701531e-05, + "loss": 1.3802, + "step": 2919 + }, + { + "epoch": 0.31, + "learning_rate": 1.7518247237161205e-05, + "loss": 1.3991, + "step": 2920 + }, + { + "epoch": 0.31, + "learning_rate": 1.7515833300055146e-05, + "loss": 1.4283, + "step": 2921 + }, + { + "epoch": 0.31, + "learning_rate": 1.7513418356020535e-05, + "loss": 1.3688, + "step": 2922 + }, + { + "epoch": 0.31, + "learning_rate": 1.751100240538092e-05, + "loss": 1.4336, + "step": 2923 + }, + { + "epoch": 0.31, + "learning_rate": 1.7508585448459967e-05, + "loss": 1.4302, + "step": 2924 + }, + { + "epoch": 0.31, + "learning_rate": 1.7506167485581493e-05, + "loss": 1.4293, + "step": 2925 + }, + { + "epoch": 0.31, + "learning_rate": 1.750374851706944e-05, + "loss": 1.4262, + "step": 2926 + }, + { + "epoch": 0.31, + "learning_rate": 1.7501328543247892e-05, + "loss": 1.4128, + "step": 2927 + }, + { + "epoch": 0.31, + "learning_rate": 1.7498907564441054e-05, + "loss": 1.4258, + "step": 2928 + }, + { + "epoch": 0.31, + "learning_rate": 1.749648558097328e-05, + "loss": 1.4904, + "step": 2929 + }, + { + "epoch": 0.31, + "learning_rate": 1.749406259316906e-05, + "loss": 1.4628, + "step": 2930 + }, + { + "epoch": 0.31, + "learning_rate": 1.7491638601353004e-05, + "loss": 1.4908, + "step": 2931 + }, + { + "epoch": 0.31, + "learning_rate": 1.7489213605849867e-05, + "loss": 1.4563, + "step": 2932 + }, + { + "epoch": 0.31, + "learning_rate": 1.7486787606984533e-05, + "loss": 1.5006, + "step": 2933 + }, + { + "epoch": 0.31, + "learning_rate": 1.748436060508203e-05, + "loss": 1.424, + "step": 2934 + }, + { + "epoch": 0.31, + "learning_rate": 1.7481932600467508e-05, + "loss": 1.4136, + "step": 2935 + }, + { + "epoch": 0.31, + "learning_rate": 1.747950359346626e-05, + "loss": 1.3835, + "step": 2936 + }, + { + "epoch": 0.31, + "learning_rate": 1.747707358440371e-05, + "loss": 1.5284, + "step": 2937 + }, + { + "epoch": 0.31, + "learning_rate": 1.7474642573605418e-05, + "loss": 1.4592, + "step": 2938 + }, + { + "epoch": 0.31, + "learning_rate": 1.7472210561397075e-05, + "loss": 1.5483, + "step": 2939 + }, + { + "epoch": 0.31, + "learning_rate": 1.746977754810451e-05, + "loss": 1.521, + "step": 2940 + }, + { + "epoch": 0.31, + "learning_rate": 1.7467343534053683e-05, + "loss": 1.4276, + "step": 2941 + }, + { + "epoch": 0.31, + "learning_rate": 1.746490851957069e-05, + "loss": 1.4302, + "step": 2942 + }, + { + "epoch": 0.31, + "learning_rate": 1.746247250498176e-05, + "loss": 1.4439, + "step": 2943 + }, + { + "epoch": 0.31, + "learning_rate": 1.7460035490613255e-05, + "loss": 1.4991, + "step": 2944 + }, + { + "epoch": 0.31, + "learning_rate": 1.7457597476791674e-05, + "loss": 1.4188, + "step": 2945 + }, + { + "epoch": 0.31, + "learning_rate": 1.7455158463843648e-05, + "loss": 1.4685, + "step": 2946 + }, + { + "epoch": 0.31, + "learning_rate": 1.745271845209594e-05, + "loss": 1.3811, + "step": 2947 + }, + { + "epoch": 0.31, + "learning_rate": 1.7450277441875454e-05, + "loss": 1.4869, + "step": 2948 + }, + { + "epoch": 0.31, + "learning_rate": 1.7447835433509218e-05, + "loss": 1.5001, + "step": 2949 + }, + { + "epoch": 0.31, + "learning_rate": 1.74453924273244e-05, + "loss": 1.4757, + "step": 2950 + }, + { + "epoch": 0.31, + "learning_rate": 1.74429484236483e-05, + "loss": 1.5072, + "step": 2951 + }, + { + "epoch": 0.31, + "learning_rate": 1.744050342280835e-05, + "loss": 1.4242, + "step": 2952 + }, + { + "epoch": 0.31, + "learning_rate": 1.743805742513212e-05, + "loss": 1.4462, + "step": 2953 + }, + { + "epoch": 0.31, + "learning_rate": 1.743561043094731e-05, + "loss": 1.6815, + "step": 2954 + }, + { + "epoch": 0.31, + "learning_rate": 1.7433162440581755e-05, + "loss": 1.427, + "step": 2955 + }, + { + "epoch": 0.31, + "learning_rate": 1.7430713454363423e-05, + "loss": 1.2933, + "step": 2956 + }, + { + "epoch": 0.31, + "learning_rate": 1.742826347262041e-05, + "loss": 1.4247, + "step": 2957 + }, + { + "epoch": 0.31, + "learning_rate": 1.7425812495680955e-05, + "loss": 1.399, + "step": 2958 + }, + { + "epoch": 0.31, + "learning_rate": 1.742336052387343e-05, + "loss": 1.4818, + "step": 2959 + }, + { + "epoch": 0.31, + "learning_rate": 1.742090755752633e-05, + "loss": 1.3839, + "step": 2960 + }, + { + "epoch": 0.31, + "learning_rate": 1.741845359696829e-05, + "loss": 1.4669, + "step": 2961 + }, + { + "epoch": 0.31, + "learning_rate": 1.741599864252808e-05, + "loss": 1.468, + "step": 2962 + }, + { + "epoch": 0.31, + "learning_rate": 1.74135426945346e-05, + "loss": 1.4135, + "step": 2963 + }, + { + "epoch": 0.31, + "learning_rate": 1.7411085753316882e-05, + "loss": 1.5899, + "step": 2964 + }, + { + "epoch": 0.31, + "learning_rate": 1.74086278192041e-05, + "loss": 1.6115, + "step": 2965 + }, + { + "epoch": 0.31, + "learning_rate": 1.740616889252554e-05, + "loss": 1.3988, + "step": 2966 + }, + { + "epoch": 0.31, + "learning_rate": 1.740370897361065e-05, + "loss": 1.5001, + "step": 2967 + }, + { + "epoch": 0.31, + "learning_rate": 1.740124806278899e-05, + "loss": 1.459, + "step": 2968 + }, + { + "epoch": 0.31, + "learning_rate": 1.7398786160390258e-05, + "loss": 1.4489, + "step": 2969 + }, + { + "epoch": 0.31, + "learning_rate": 1.7396323266744283e-05, + "loss": 1.4397, + "step": 2970 + }, + { + "epoch": 0.31, + "learning_rate": 1.7393859382181033e-05, + "loss": 1.4687, + "step": 2971 + }, + { + "epoch": 0.31, + "learning_rate": 1.7391394507030606e-05, + "loss": 1.4495, + "step": 2972 + }, + { + "epoch": 0.31, + "learning_rate": 1.738892864162323e-05, + "loss": 1.4745, + "step": 2973 + }, + { + "epoch": 0.31, + "learning_rate": 1.7386461786289274e-05, + "loss": 1.3943, + "step": 2974 + }, + { + "epoch": 0.31, + "learning_rate": 1.738399394135922e-05, + "loss": 1.4595, + "step": 2975 + }, + { + "epoch": 0.31, + "learning_rate": 1.738152510716371e-05, + "loss": 1.4023, + "step": 2976 + }, + { + "epoch": 0.31, + "learning_rate": 1.7379055284033493e-05, + "loss": 1.3938, + "step": 2977 + }, + { + "epoch": 0.31, + "learning_rate": 1.7376584472299468e-05, + "loss": 1.4576, + "step": 2978 + }, + { + "epoch": 0.31, + "learning_rate": 1.737411267229266e-05, + "loss": 1.424, + "step": 2979 + }, + { + "epoch": 0.31, + "learning_rate": 1.7371639884344225e-05, + "loss": 1.4224, + "step": 2980 + }, + { + "epoch": 0.31, + "learning_rate": 1.736916610878545e-05, + "loss": 1.4228, + "step": 2981 + }, + { + "epoch": 0.31, + "learning_rate": 1.7366691345947768e-05, + "loss": 1.5021, + "step": 2982 + }, + { + "epoch": 0.31, + "learning_rate": 1.736421559616272e-05, + "loss": 1.3589, + "step": 2983 + }, + { + "epoch": 0.31, + "learning_rate": 1.7361738859762007e-05, + "loss": 1.4748, + "step": 2984 + }, + { + "epoch": 0.31, + "learning_rate": 1.735926113707743e-05, + "loss": 1.3974, + "step": 2985 + }, + { + "epoch": 0.31, + "eval_loss": 1.4849082231521606, + "eval_runtime": 77.3271, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2985 + }, + { + "epoch": 0.31, + "learning_rate": 1.735678242844096e-05, + "loss": 1.392, + "step": 2986 + }, + { + "epoch": 0.31, + "learning_rate": 1.735430273418467e-05, + "loss": 1.4277, + "step": 2987 + }, + { + "epoch": 0.31, + "learning_rate": 1.735182205464077e-05, + "loss": 1.4216, + "step": 2988 + }, + { + "epoch": 0.31, + "learning_rate": 1.7349340390141617e-05, + "loss": 1.4546, + "step": 2989 + }, + { + "epoch": 0.31, + "learning_rate": 1.734685774101969e-05, + "loss": 1.4264, + "step": 2990 + }, + { + "epoch": 0.31, + "learning_rate": 1.7344374107607593e-05, + "loss": 1.4307, + "step": 2991 + }, + { + "epoch": 0.31, + "learning_rate": 1.7341889490238076e-05, + "loss": 1.4266, + "step": 2992 + }, + { + "epoch": 0.31, + "learning_rate": 1.7339403889244008e-05, + "loss": 1.4486, + "step": 2993 + }, + { + "epoch": 0.31, + "learning_rate": 1.7336917304958403e-05, + "loss": 1.4345, + "step": 2994 + }, + { + "epoch": 0.31, + "learning_rate": 1.7334429737714395e-05, + "loss": 1.476, + "step": 2995 + }, + { + "epoch": 0.31, + "learning_rate": 1.7331941187845248e-05, + "loss": 1.5148, + "step": 2996 + }, + { + "epoch": 0.31, + "learning_rate": 1.7329451655684372e-05, + "loss": 1.4026, + "step": 2997 + }, + { + "epoch": 0.31, + "learning_rate": 1.7326961141565303e-05, + "loss": 1.3935, + "step": 2998 + }, + { + "epoch": 0.31, + "learning_rate": 1.73244696458217e-05, + "loss": 1.4483, + "step": 2999 + }, + { + "epoch": 0.31, + "learning_rate": 1.7321977168787356e-05, + "loss": 1.5197, + "step": 3000 + }, + { + "epoch": 0.31, + "learning_rate": 1.7319483710796208e-05, + "loss": 1.4648, + "step": 3001 + }, + { + "epoch": 0.31, + "learning_rate": 1.7316989272182308e-05, + "loss": 1.4171, + "step": 3002 + }, + { + "epoch": 0.31, + "learning_rate": 1.731449385327985e-05, + "loss": 1.4541, + "step": 3003 + }, + { + "epoch": 0.32, + "learning_rate": 1.731199745442316e-05, + "loss": 1.4605, + "step": 3004 + }, + { + "epoch": 0.32, + "learning_rate": 1.7309500075946683e-05, + "loss": 1.5122, + "step": 3005 + }, + { + "epoch": 0.32, + "learning_rate": 1.7307001718185007e-05, + "loss": 1.5243, + "step": 3006 + }, + { + "epoch": 0.32, + "learning_rate": 1.7304502381472844e-05, + "loss": 1.4997, + "step": 3007 + }, + { + "epoch": 0.32, + "learning_rate": 1.730200206614505e-05, + "loss": 1.4891, + "step": 3008 + }, + { + "epoch": 0.32, + "learning_rate": 1.72995007725366e-05, + "loss": 1.4376, + "step": 3009 + }, + { + "epoch": 0.32, + "learning_rate": 1.7296998500982595e-05, + "loss": 1.4403, + "step": 3010 + }, + { + "epoch": 0.32, + "learning_rate": 1.7294495251818285e-05, + "loss": 1.5153, + "step": 3011 + }, + { + "epoch": 0.32, + "learning_rate": 1.729199102537904e-05, + "loss": 1.4996, + "step": 3012 + }, + { + "epoch": 0.32, + "learning_rate": 1.7289485822000356e-05, + "loss": 1.5302, + "step": 3013 + }, + { + "epoch": 0.32, + "learning_rate": 1.7286979642017867e-05, + "loss": 1.5641, + "step": 3014 + }, + { + "epoch": 0.32, + "learning_rate": 1.728447248576734e-05, + "loss": 1.438, + "step": 3015 + }, + { + "epoch": 0.32, + "learning_rate": 1.7281964353584674e-05, + "loss": 1.4796, + "step": 3016 + }, + { + "epoch": 0.32, + "learning_rate": 1.727945524580588e-05, + "loss": 1.4413, + "step": 3017 + }, + { + "epoch": 0.32, + "learning_rate": 1.727694516276713e-05, + "loss": 1.3966, + "step": 3018 + }, + { + "epoch": 0.32, + "learning_rate": 1.72744341048047e-05, + "loss": 1.5267, + "step": 3019 + }, + { + "epoch": 0.32, + "learning_rate": 1.727192207225501e-05, + "loss": 1.4284, + "step": 3020 + }, + { + "epoch": 0.32, + "learning_rate": 1.726940906545461e-05, + "loss": 1.5137, + "step": 3021 + }, + { + "epoch": 0.32, + "learning_rate": 1.7266895084740173e-05, + "loss": 1.3966, + "step": 3022 + }, + { + "epoch": 0.32, + "learning_rate": 1.7264380130448514e-05, + "loss": 1.4156, + "step": 3023 + }, + { + "epoch": 0.32, + "learning_rate": 1.726186420291657e-05, + "loss": 1.4644, + "step": 3024 + }, + { + "epoch": 0.32, + "learning_rate": 1.725934730248141e-05, + "loss": 1.4768, + "step": 3025 + }, + { + "epoch": 0.32, + "learning_rate": 1.7256829429480233e-05, + "loss": 1.4428, + "step": 3026 + }, + { + "epoch": 0.32, + "learning_rate": 1.7254310584250373e-05, + "loss": 1.4495, + "step": 3027 + }, + { + "epoch": 0.32, + "learning_rate": 1.725179076712929e-05, + "loss": 1.3867, + "step": 3028 + }, + { + "epoch": 0.32, + "learning_rate": 1.7249269978454567e-05, + "loss": 1.5011, + "step": 3029 + }, + { + "epoch": 0.32, + "learning_rate": 1.7246748218563937e-05, + "loss": 1.3916, + "step": 3030 + }, + { + "epoch": 0.32, + "learning_rate": 1.7244225487795238e-05, + "loss": 1.4984, + "step": 3031 + }, + { + "epoch": 0.32, + "learning_rate": 1.7241701786486464e-05, + "loss": 1.5776, + "step": 3032 + }, + { + "epoch": 0.32, + "learning_rate": 1.7239177114975717e-05, + "loss": 1.5018, + "step": 3033 + }, + { + "epoch": 0.32, + "learning_rate": 1.7236651473601244e-05, + "loss": 1.5042, + "step": 3034 + }, + { + "epoch": 0.32, + "learning_rate": 1.723412486270141e-05, + "loss": 1.4636, + "step": 3035 + }, + { + "epoch": 0.32, + "learning_rate": 1.723159728261472e-05, + "loss": 1.5612, + "step": 3036 + }, + { + "epoch": 0.32, + "learning_rate": 1.7229068733679803e-05, + "loss": 1.4399, + "step": 3037 + }, + { + "epoch": 0.32, + "learning_rate": 1.7226539216235424e-05, + "loss": 1.5635, + "step": 3038 + }, + { + "epoch": 0.32, + "learning_rate": 1.7224008730620468e-05, + "loss": 1.4329, + "step": 3039 + }, + { + "epoch": 0.32, + "learning_rate": 1.7221477277173956e-05, + "loss": 1.4886, + "step": 3040 + }, + { + "epoch": 0.32, + "learning_rate": 1.721894485623504e-05, + "loss": 1.4741, + "step": 3041 + }, + { + "epoch": 0.32, + "learning_rate": 1.7216411468143e-05, + "loss": 1.4678, + "step": 3042 + }, + { + "epoch": 0.32, + "learning_rate": 1.721387711323724e-05, + "loss": 1.4758, + "step": 3043 + }, + { + "epoch": 0.32, + "learning_rate": 1.72113417918573e-05, + "loss": 1.441, + "step": 3044 + }, + { + "epoch": 0.32, + "learning_rate": 1.7208805504342855e-05, + "loss": 1.4328, + "step": 3045 + }, + { + "epoch": 0.32, + "learning_rate": 1.720626825103369e-05, + "loss": 1.4254, + "step": 3046 + }, + { + "epoch": 0.32, + "learning_rate": 1.7203730032269744e-05, + "loss": 1.4462, + "step": 3047 + }, + { + "epoch": 0.32, + "learning_rate": 1.7201190848391066e-05, + "loss": 1.4826, + "step": 3048 + }, + { + "epoch": 0.32, + "learning_rate": 1.719865069973784e-05, + "loss": 1.4215, + "step": 3049 + }, + { + "epoch": 0.32, + "learning_rate": 1.7196109586650385e-05, + "loss": 1.4291, + "step": 3050 + }, + { + "epoch": 0.32, + "learning_rate": 1.7193567509469146e-05, + "loss": 1.5005, + "step": 3051 + }, + { + "epoch": 0.32, + "learning_rate": 1.719102446853469e-05, + "loss": 1.4216, + "step": 3052 + }, + { + "epoch": 0.32, + "learning_rate": 1.7188480464187725e-05, + "loss": 1.4349, + "step": 3053 + }, + { + "epoch": 0.32, + "learning_rate": 1.718593549676908e-05, + "loss": 1.4784, + "step": 3054 + }, + { + "epoch": 0.32, + "learning_rate": 1.7183389566619714e-05, + "loss": 1.4325, + "step": 3055 + }, + { + "epoch": 0.32, + "learning_rate": 1.7180842674080717e-05, + "loss": 1.5387, + "step": 3056 + }, + { + "epoch": 0.32, + "learning_rate": 1.717829481949331e-05, + "loss": 1.655, + "step": 3057 + }, + { + "epoch": 0.32, + "learning_rate": 1.717574600319883e-05, + "loss": 1.4623, + "step": 3058 + }, + { + "epoch": 0.32, + "learning_rate": 1.7173196225538768e-05, + "loss": 1.4646, + "step": 3059 + }, + { + "epoch": 0.32, + "learning_rate": 1.717064548685472e-05, + "loss": 1.4641, + "step": 3060 + }, + { + "epoch": 0.32, + "learning_rate": 1.7168093787488418e-05, + "loss": 1.4033, + "step": 3061 + }, + { + "epoch": 0.32, + "learning_rate": 1.7165541127781726e-05, + "loss": 1.4085, + "step": 3062 + }, + { + "epoch": 0.32, + "learning_rate": 1.716298750807664e-05, + "loss": 1.387, + "step": 3063 + }, + { + "epoch": 0.32, + "learning_rate": 1.7160432928715272e-05, + "loss": 1.4197, + "step": 3064 + }, + { + "epoch": 0.32, + "learning_rate": 1.7157877390039872e-05, + "loss": 1.4883, + "step": 3065 + }, + { + "epoch": 0.32, + "learning_rate": 1.7155320892392818e-05, + "loss": 1.4865, + "step": 3066 + }, + { + "epoch": 0.32, + "learning_rate": 1.715276343611662e-05, + "loss": 1.4532, + "step": 3067 + }, + { + "epoch": 0.32, + "learning_rate": 1.71502050215539e-05, + "loss": 1.3991, + "step": 3068 + }, + { + "epoch": 0.32, + "learning_rate": 1.7147645649047424e-05, + "loss": 1.4318, + "step": 3069 + }, + { + "epoch": 0.32, + "learning_rate": 1.714508531894009e-05, + "loss": 1.3616, + "step": 3070 + }, + { + "epoch": 0.32, + "learning_rate": 1.7142524031574904e-05, + "loss": 1.4481, + "step": 3071 + }, + { + "epoch": 0.32, + "learning_rate": 1.7139961787295022e-05, + "loss": 1.3897, + "step": 3072 + }, + { + "epoch": 0.32, + "learning_rate": 1.7137398586443716e-05, + "loss": 1.3128, + "step": 3073 + }, + { + "epoch": 0.32, + "learning_rate": 1.713483442936439e-05, + "loss": 1.4481, + "step": 3074 + }, + { + "epoch": 0.32, + "learning_rate": 1.713226931640057e-05, + "loss": 1.5374, + "step": 3075 + }, + { + "epoch": 0.32, + "learning_rate": 1.7129703247895923e-05, + "loss": 1.4247, + "step": 3076 + }, + { + "epoch": 0.32, + "learning_rate": 1.712713622419423e-05, + "loss": 1.4098, + "step": 3077 + }, + { + "epoch": 0.32, + "learning_rate": 1.7124568245639414e-05, + "loss": 1.4558, + "step": 3078 + }, + { + "epoch": 0.32, + "learning_rate": 1.7121999312575507e-05, + "loss": 1.4484, + "step": 3079 + }, + { + "epoch": 0.32, + "learning_rate": 1.711942942534669e-05, + "loss": 1.4236, + "step": 3080 + }, + { + "epoch": 0.32, + "learning_rate": 1.7116858584297253e-05, + "loss": 1.613, + "step": 3081 + }, + { + "epoch": 0.32, + "learning_rate": 1.711428678977163e-05, + "loss": 1.4503, + "step": 3082 + }, + { + "epoch": 0.32, + "learning_rate": 1.7111714042114376e-05, + "loss": 1.4072, + "step": 3083 + }, + { + "epoch": 0.32, + "learning_rate": 1.7109140341670168e-05, + "loss": 1.5999, + "step": 3084 + }, + { + "epoch": 0.32, + "learning_rate": 1.7106565688783815e-05, + "loss": 1.4129, + "step": 3085 + }, + { + "epoch": 0.32, + "learning_rate": 1.710399008380026e-05, + "loss": 1.3973, + "step": 3086 + }, + { + "epoch": 0.32, + "learning_rate": 1.710141352706456e-05, + "loss": 1.4292, + "step": 3087 + }, + { + "epoch": 0.32, + "learning_rate": 1.709883601892192e-05, + "loss": 1.4372, + "step": 3088 + }, + { + "epoch": 0.32, + "learning_rate": 1.7096257559717647e-05, + "loss": 1.4924, + "step": 3089 + }, + { + "epoch": 0.32, + "learning_rate": 1.7093678149797196e-05, + "loss": 1.4222, + "step": 3090 + }, + { + "epoch": 0.32, + "learning_rate": 1.7091097789506137e-05, + "loss": 1.4797, + "step": 3091 + }, + { + "epoch": 0.32, + "learning_rate": 1.7088516479190175e-05, + "loss": 1.4738, + "step": 3092 + }, + { + "epoch": 0.32, + "learning_rate": 1.708593421919514e-05, + "loss": 1.5371, + "step": 3093 + }, + { + "epoch": 0.32, + "learning_rate": 1.7083351009866988e-05, + "loss": 1.3802, + "step": 3094 + }, + { + "epoch": 0.32, + "learning_rate": 1.7080766851551795e-05, + "loss": 1.4292, + "step": 3095 + }, + { + "epoch": 0.32, + "learning_rate": 1.707818174459578e-05, + "loss": 1.4478, + "step": 3096 + }, + { + "epoch": 0.32, + "learning_rate": 1.7075595689345285e-05, + "loss": 1.4619, + "step": 3097 + }, + { + "epoch": 0.32, + "learning_rate": 1.7073008686146763e-05, + "loss": 1.4603, + "step": 3098 + }, + { + "epoch": 0.32, + "learning_rate": 1.7070420735346815e-05, + "loss": 1.4548, + "step": 3099 + }, + { + "epoch": 0.33, + "learning_rate": 1.7067831837292157e-05, + "loss": 1.3638, + "step": 3100 + }, + { + "epoch": 0.33, + "learning_rate": 1.7065241992329634e-05, + "loss": 1.4284, + "step": 3101 + }, + { + "epoch": 0.33, + "learning_rate": 1.7062651200806217e-05, + "loss": 1.386, + "step": 3102 + }, + { + "epoch": 0.33, + "learning_rate": 1.7060059463069013e-05, + "loss": 1.5483, + "step": 3103 + }, + { + "epoch": 0.33, + "learning_rate": 1.705746677946524e-05, + "loss": 1.4963, + "step": 3104 + }, + { + "epoch": 0.33, + "learning_rate": 1.7054873150342257e-05, + "loss": 1.4539, + "step": 3105 + }, + { + "epoch": 0.33, + "learning_rate": 1.705227857604754e-05, + "loss": 1.4361, + "step": 3106 + }, + { + "epoch": 0.33, + "learning_rate": 1.7049683056928695e-05, + "loss": 1.3735, + "step": 3107 + }, + { + "epoch": 0.33, + "learning_rate": 1.7047086593333454e-05, + "loss": 1.4324, + "step": 3108 + }, + { + "epoch": 0.33, + "learning_rate": 1.7044489185609685e-05, + "loss": 1.5037, + "step": 3109 + }, + { + "epoch": 0.33, + "learning_rate": 1.704189083410536e-05, + "loss": 1.3913, + "step": 3110 + }, + { + "epoch": 0.33, + "learning_rate": 1.7039291539168604e-05, + "loss": 1.3233, + "step": 3111 + }, + { + "epoch": 0.33, + "learning_rate": 1.703669130114765e-05, + "loss": 1.4897, + "step": 3112 + }, + { + "epoch": 0.33, + "learning_rate": 1.7034090120390862e-05, + "loss": 1.4843, + "step": 3113 + }, + { + "epoch": 0.33, + "learning_rate": 1.7031487997246735e-05, + "loss": 1.3674, + "step": 3114 + }, + { + "epoch": 0.33, + "learning_rate": 1.7028884932063883e-05, + "loss": 1.4475, + "step": 3115 + }, + { + "epoch": 0.33, + "learning_rate": 1.702628092519105e-05, + "loss": 1.4134, + "step": 3116 + }, + { + "epoch": 0.33, + "learning_rate": 1.7023675976977108e-05, + "loss": 1.4484, + "step": 3117 + }, + { + "epoch": 0.33, + "learning_rate": 1.702107008777106e-05, + "loss": 1.407, + "step": 3118 + }, + { + "epoch": 0.33, + "learning_rate": 1.7018463257922005e-05, + "loss": 1.5443, + "step": 3119 + }, + { + "epoch": 0.33, + "learning_rate": 1.701585548777922e-05, + "loss": 1.4548, + "step": 3120 + }, + { + "epoch": 0.33, + "learning_rate": 1.7013246777692063e-05, + "loss": 1.4252, + "step": 3121 + }, + { + "epoch": 0.33, + "learning_rate": 1.7010637128010037e-05, + "loss": 1.3748, + "step": 3122 + }, + { + "epoch": 0.33, + "learning_rate": 1.7008026539082767e-05, + "loss": 1.3804, + "step": 3123 + }, + { + "epoch": 0.33, + "learning_rate": 1.7005415011260008e-05, + "loss": 1.4203, + "step": 3124 + }, + { + "epoch": 0.33, + "learning_rate": 1.7002802544891634e-05, + "loss": 1.4195, + "step": 3125 + }, + { + "epoch": 0.33, + "learning_rate": 1.700018914032765e-05, + "loss": 1.4188, + "step": 3126 + }, + { + "epoch": 0.33, + "learning_rate": 1.699757479791819e-05, + "loss": 1.3884, + "step": 3127 + }, + { + "epoch": 0.33, + "learning_rate": 1.6994959518013502e-05, + "loss": 1.4111, + "step": 3128 + }, + { + "epoch": 0.33, + "learning_rate": 1.6992343300963963e-05, + "loss": 1.5452, + "step": 3129 + }, + { + "epoch": 0.33, + "learning_rate": 1.6989726147120087e-05, + "loss": 1.4097, + "step": 3130 + }, + { + "epoch": 0.33, + "learning_rate": 1.6987108056832506e-05, + "loss": 1.481, + "step": 3131 + }, + { + "epoch": 0.33, + "learning_rate": 1.6984489030451973e-05, + "loss": 1.4505, + "step": 3132 + }, + { + "epoch": 0.33, + "learning_rate": 1.6981869068329368e-05, + "loss": 1.4281, + "step": 3133 + }, + { + "epoch": 0.33, + "learning_rate": 1.69792481708157e-05, + "loss": 1.4555, + "step": 3134 + }, + { + "epoch": 0.33, + "learning_rate": 1.6976626338262103e-05, + "loss": 1.4525, + "step": 3135 + }, + { + "epoch": 0.33, + "learning_rate": 1.6974003571019837e-05, + "loss": 1.3765, + "step": 3136 + }, + { + "epoch": 0.33, + "learning_rate": 1.6971379869440286e-05, + "loss": 1.3998, + "step": 3137 + }, + { + "epoch": 0.33, + "learning_rate": 1.696875523387495e-05, + "loss": 1.5103, + "step": 3138 + }, + { + "epoch": 0.33, + "learning_rate": 1.6966129664675474e-05, + "loss": 1.427, + "step": 3139 + }, + { + "epoch": 0.33, + "learning_rate": 1.6963503162193612e-05, + "loss": 1.4362, + "step": 3140 + }, + { + "epoch": 0.33, + "learning_rate": 1.6960875726781246e-05, + "loss": 1.4073, + "step": 3141 + }, + { + "epoch": 0.33, + "learning_rate": 1.6958247358790388e-05, + "loss": 1.4014, + "step": 3142 + }, + { + "epoch": 0.33, + "learning_rate": 1.6955618058573165e-05, + "loss": 1.4244, + "step": 3143 + }, + { + "epoch": 0.33, + "learning_rate": 1.6952987826481847e-05, + "loss": 1.47, + "step": 3144 + }, + { + "epoch": 0.33, + "learning_rate": 1.6950356662868814e-05, + "loss": 1.5112, + "step": 3145 + }, + { + "epoch": 0.33, + "learning_rate": 1.6947724568086562e-05, + "loss": 1.3398, + "step": 3146 + }, + { + "epoch": 0.33, + "learning_rate": 1.694509154248774e-05, + "loss": 1.4584, + "step": 3147 + }, + { + "epoch": 0.33, + "learning_rate": 1.69424575864251e-05, + "loss": 1.4383, + "step": 3148 + }, + { + "epoch": 0.33, + "learning_rate": 1.6939822700251523e-05, + "loss": 1.3869, + "step": 3149 + }, + { + "epoch": 0.33, + "learning_rate": 1.6937186884320015e-05, + "loss": 1.4453, + "step": 3150 + }, + { + "epoch": 0.33, + "learning_rate": 1.6934550138983713e-05, + "loss": 1.3355, + "step": 3151 + }, + { + "epoch": 0.33, + "learning_rate": 1.6931912464595866e-05, + "loss": 1.5573, + "step": 3152 + }, + { + "epoch": 0.33, + "learning_rate": 1.6929273861509865e-05, + "loss": 1.439, + "step": 3153 + }, + { + "epoch": 0.33, + "learning_rate": 1.6926634330079203e-05, + "loss": 1.6079, + "step": 3154 + }, + { + "epoch": 0.33, + "learning_rate": 1.692399387065752e-05, + "loss": 1.6973, + "step": 3155 + }, + { + "epoch": 0.33, + "learning_rate": 1.692135248359856e-05, + "loss": 1.3769, + "step": 3156 + }, + { + "epoch": 0.33, + "learning_rate": 1.6918710169256206e-05, + "loss": 1.4454, + "step": 3157 + }, + { + "epoch": 0.33, + "learning_rate": 1.691606692798446e-05, + "loss": 1.4495, + "step": 3158 + }, + { + "epoch": 0.33, + "learning_rate": 1.691342276013745e-05, + "loss": 1.4292, + "step": 3159 + }, + { + "epoch": 0.33, + "learning_rate": 1.691077766606942e-05, + "loss": 1.4405, + "step": 3160 + }, + { + "epoch": 0.33, + "learning_rate": 1.6908131646134757e-05, + "loss": 1.3683, + "step": 3161 + }, + { + "epoch": 0.33, + "learning_rate": 1.690548470068795e-05, + "loss": 1.4731, + "step": 3162 + }, + { + "epoch": 0.33, + "learning_rate": 1.690283683008362e-05, + "loss": 1.4323, + "step": 3163 + }, + { + "epoch": 0.33, + "learning_rate": 1.6900188034676518e-05, + "loss": 1.5133, + "step": 3164 + }, + { + "epoch": 0.33, + "learning_rate": 1.6897538314821516e-05, + "loss": 1.5529, + "step": 3165 + }, + { + "epoch": 0.33, + "learning_rate": 1.6894887670873605e-05, + "loss": 1.4427, + "step": 3166 + }, + { + "epoch": 0.33, + "learning_rate": 1.6892236103187904e-05, + "loss": 1.4344, + "step": 3167 + }, + { + "epoch": 0.33, + "learning_rate": 1.6889583612119657e-05, + "loss": 1.4291, + "step": 3168 + }, + { + "epoch": 0.33, + "learning_rate": 1.6886930198024226e-05, + "loss": 1.4683, + "step": 3169 + }, + { + "epoch": 0.33, + "learning_rate": 1.6884275861257106e-05, + "loss": 1.4442, + "step": 3170 + }, + { + "epoch": 0.33, + "learning_rate": 1.6881620602173905e-05, + "loss": 1.4509, + "step": 3171 + }, + { + "epoch": 0.33, + "learning_rate": 1.6878964421130362e-05, + "loss": 1.5113, + "step": 3172 + }, + { + "epoch": 0.33, + "learning_rate": 1.6876307318482334e-05, + "loss": 1.4261, + "step": 3173 + }, + { + "epoch": 0.33, + "learning_rate": 1.6873649294585805e-05, + "loss": 1.445, + "step": 3174 + }, + { + "epoch": 0.33, + "learning_rate": 1.6870990349796886e-05, + "loss": 1.4603, + "step": 3175 + }, + { + "epoch": 0.33, + "learning_rate": 1.68683304844718e-05, + "loss": 1.41, + "step": 3176 + }, + { + "epoch": 0.33, + "learning_rate": 1.686566969896691e-05, + "loss": 1.4018, + "step": 3177 + }, + { + "epoch": 0.33, + "learning_rate": 1.6863007993638687e-05, + "loss": 1.422, + "step": 3178 + }, + { + "epoch": 0.33, + "learning_rate": 1.6860345368843727e-05, + "loss": 1.4412, + "step": 3179 + }, + { + "epoch": 0.33, + "learning_rate": 1.6857681824938768e-05, + "loss": 1.5411, + "step": 3180 + }, + { + "epoch": 0.33, + "learning_rate": 1.685501736228064e-05, + "loss": 1.4416, + "step": 3181 + }, + { + "epoch": 0.33, + "learning_rate": 1.685235198122632e-05, + "loss": 1.5113, + "step": 3182 + }, + { + "epoch": 0.33, + "learning_rate": 1.6849685682132903e-05, + "loss": 1.423, + "step": 3183 + }, + { + "epoch": 0.33, + "learning_rate": 1.68470184653576e-05, + "loss": 1.404, + "step": 3184 + }, + { + "epoch": 0.33, + "eval_loss": 1.4771089553833008, + "eval_runtime": 77.4034, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3184 + }, + { + "epoch": 0.33, + "learning_rate": 1.6844350331257747e-05, + "loss": 1.4624, + "step": 3185 + }, + { + "epoch": 0.33, + "learning_rate": 1.6841681280190814e-05, + "loss": 1.4306, + "step": 3186 + }, + { + "epoch": 0.33, + "learning_rate": 1.683901131251438e-05, + "loss": 1.42, + "step": 3187 + }, + { + "epoch": 0.33, + "learning_rate": 1.6836340428586155e-05, + "loss": 1.4787, + "step": 3188 + }, + { + "epoch": 0.33, + "learning_rate": 1.6833668628763965e-05, + "loss": 1.3485, + "step": 3189 + }, + { + "epoch": 0.33, + "learning_rate": 1.683099591340576e-05, + "loss": 1.3674, + "step": 3190 + }, + { + "epoch": 0.33, + "learning_rate": 1.6828322282869627e-05, + "loss": 1.5187, + "step": 3191 + }, + { + "epoch": 0.33, + "learning_rate": 1.682564773751375e-05, + "loss": 1.4847, + "step": 3192 + }, + { + "epoch": 0.33, + "learning_rate": 1.682297227769646e-05, + "loss": 1.4815, + "step": 3193 + }, + { + "epoch": 0.33, + "learning_rate": 1.682029590377619e-05, + "loss": 1.4281, + "step": 3194 + }, + { + "epoch": 0.34, + "learning_rate": 1.6817618616111517e-05, + "loss": 1.4734, + "step": 3195 + }, + { + "epoch": 0.34, + "learning_rate": 1.681494041506112e-05, + "loss": 1.4861, + "step": 3196 + }, + { + "epoch": 0.34, + "learning_rate": 1.6812261300983808e-05, + "loss": 1.4372, + "step": 3197 + }, + { + "epoch": 0.34, + "learning_rate": 1.680958127423852e-05, + "loss": 1.4396, + "step": 3198 + }, + { + "epoch": 0.34, + "learning_rate": 1.680690033518431e-05, + "loss": 1.4225, + "step": 3199 + }, + { + "epoch": 0.34, + "learning_rate": 1.6804218484180347e-05, + "loss": 1.4925, + "step": 3200 + }, + { + "epoch": 0.34, + "learning_rate": 1.6801535721585942e-05, + "loss": 1.4306, + "step": 3201 + }, + { + "epoch": 0.34, + "learning_rate": 1.6798852047760506e-05, + "loss": 1.4298, + "step": 3202 + }, + { + "epoch": 0.34, + "learning_rate": 1.6796167463063588e-05, + "loss": 1.4725, + "step": 3203 + }, + { + "epoch": 0.34, + "learning_rate": 1.679348196785485e-05, + "loss": 1.4648, + "step": 3204 + }, + { + "epoch": 0.34, + "learning_rate": 1.6790795562494087e-05, + "loss": 1.4152, + "step": 3205 + }, + { + "epoch": 0.34, + "learning_rate": 1.6788108247341198e-05, + "loss": 1.4637, + "step": 3206 + }, + { + "epoch": 0.34, + "learning_rate": 1.6785420022756216e-05, + "loss": 1.4077, + "step": 3207 + }, + { + "epoch": 0.34, + "learning_rate": 1.67827308890993e-05, + "loss": 1.4585, + "step": 3208 + }, + { + "epoch": 0.34, + "learning_rate": 1.678004084673072e-05, + "loss": 1.3747, + "step": 3209 + }, + { + "epoch": 0.34, + "learning_rate": 1.6777349896010876e-05, + "loss": 1.4264, + "step": 3210 + }, + { + "epoch": 0.34, + "learning_rate": 1.677465803730028e-05, + "loss": 1.4178, + "step": 3211 + }, + { + "epoch": 0.34, + "learning_rate": 1.6771965270959584e-05, + "loss": 1.3876, + "step": 3212 + }, + { + "epoch": 0.34, + "learning_rate": 1.6769271597349538e-05, + "loss": 1.4658, + "step": 3213 + }, + { + "epoch": 0.34, + "learning_rate": 1.6766577016831026e-05, + "loss": 1.3968, + "step": 3214 + }, + { + "epoch": 0.34, + "learning_rate": 1.676388152976506e-05, + "loss": 1.5015, + "step": 3215 + }, + { + "epoch": 0.34, + "learning_rate": 1.6761185136512756e-05, + "loss": 1.4121, + "step": 3216 + }, + { + "epoch": 0.34, + "learning_rate": 1.675848783743537e-05, + "loss": 1.4146, + "step": 3217 + }, + { + "epoch": 0.34, + "learning_rate": 1.675578963289427e-05, + "loss": 1.4113, + "step": 3218 + }, + { + "epoch": 0.34, + "learning_rate": 1.6753090523250937e-05, + "loss": 1.4048, + "step": 3219 + }, + { + "epoch": 0.34, + "learning_rate": 1.6750390508866994e-05, + "loss": 1.4959, + "step": 3220 + }, + { + "epoch": 0.34, + "learning_rate": 1.6747689590104167e-05, + "loss": 1.4445, + "step": 3221 + }, + { + "epoch": 0.34, + "learning_rate": 1.6744987767324312e-05, + "loss": 1.4611, + "step": 3222 + }, + { + "epoch": 0.34, + "learning_rate": 1.67422850408894e-05, + "loss": 1.4141, + "step": 3223 + }, + { + "epoch": 0.34, + "learning_rate": 1.6739581411161535e-05, + "loss": 1.4218, + "step": 3224 + }, + { + "epoch": 0.34, + "learning_rate": 1.6736876878502925e-05, + "loss": 1.4266, + "step": 3225 + }, + { + "epoch": 0.34, + "learning_rate": 1.6734171443275913e-05, + "loss": 1.4941, + "step": 3226 + }, + { + "epoch": 0.34, + "learning_rate": 1.6731465105842955e-05, + "loss": 1.4294, + "step": 3227 + }, + { + "epoch": 0.34, + "learning_rate": 1.6728757866566635e-05, + "loss": 1.4189, + "step": 3228 + }, + { + "epoch": 0.34, + "learning_rate": 1.6726049725809647e-05, + "loss": 1.4713, + "step": 3229 + }, + { + "epoch": 0.34, + "learning_rate": 1.6723340683934818e-05, + "loss": 1.4203, + "step": 3230 + }, + { + "epoch": 0.34, + "learning_rate": 1.6720630741305088e-05, + "loss": 1.4112, + "step": 3231 + }, + { + "epoch": 0.34, + "learning_rate": 1.6717919898283523e-05, + "loss": 1.3811, + "step": 3232 + }, + { + "epoch": 0.34, + "learning_rate": 1.6715208155233296e-05, + "loss": 1.4242, + "step": 3233 + }, + { + "epoch": 0.34, + "learning_rate": 1.6712495512517725e-05, + "loss": 1.4207, + "step": 3234 + }, + { + "epoch": 0.34, + "learning_rate": 1.6709781970500222e-05, + "loss": 1.4888, + "step": 3235 + }, + { + "epoch": 0.34, + "learning_rate": 1.670706752954434e-05, + "loss": 1.4501, + "step": 3236 + }, + { + "epoch": 0.34, + "learning_rate": 1.670435219001374e-05, + "loss": 1.4367, + "step": 3237 + }, + { + "epoch": 0.34, + "learning_rate": 1.6701635952272212e-05, + "loss": 1.3959, + "step": 3238 + }, + { + "epoch": 0.34, + "learning_rate": 1.6698918816683655e-05, + "loss": 1.4257, + "step": 3239 + }, + { + "epoch": 0.34, + "learning_rate": 1.6696200783612102e-05, + "loss": 1.4718, + "step": 3240 + }, + { + "epoch": 0.34, + "learning_rate": 1.6693481853421697e-05, + "loss": 1.5899, + "step": 3241 + }, + { + "epoch": 0.34, + "learning_rate": 1.6690762026476707e-05, + "loss": 1.418, + "step": 3242 + }, + { + "epoch": 0.34, + "learning_rate": 1.668804130314152e-05, + "loss": 1.4076, + "step": 3243 + }, + { + "epoch": 0.34, + "learning_rate": 1.6685319683780645e-05, + "loss": 1.4571, + "step": 3244 + }, + { + "epoch": 0.34, + "learning_rate": 1.66825971687587e-05, + "loss": 1.4066, + "step": 3245 + }, + { + "epoch": 0.34, + "learning_rate": 1.6679873758440442e-05, + "loss": 1.4639, + "step": 3246 + }, + { + "epoch": 0.34, + "learning_rate": 1.6677149453190732e-05, + "loss": 1.453, + "step": 3247 + }, + { + "epoch": 0.34, + "learning_rate": 1.6674424253374558e-05, + "loss": 1.4262, + "step": 3248 + }, + { + "epoch": 0.34, + "learning_rate": 1.667169815935703e-05, + "loss": 1.3687, + "step": 3249 + }, + { + "epoch": 0.34, + "learning_rate": 1.6668971171503372e-05, + "loss": 1.5557, + "step": 3250 + }, + { + "epoch": 0.34, + "learning_rate": 1.6666243290178933e-05, + "loss": 1.4639, + "step": 3251 + }, + { + "epoch": 0.34, + "learning_rate": 1.6663514515749172e-05, + "loss": 1.4334, + "step": 3252 + }, + { + "epoch": 0.34, + "learning_rate": 1.6660784848579685e-05, + "loss": 1.3523, + "step": 3253 + }, + { + "epoch": 0.34, + "learning_rate": 1.6658054289036166e-05, + "loss": 1.3738, + "step": 3254 + }, + { + "epoch": 0.34, + "learning_rate": 1.665532283748445e-05, + "loss": 1.4159, + "step": 3255 + }, + { + "epoch": 0.34, + "learning_rate": 1.6652590494290474e-05, + "loss": 1.3609, + "step": 3256 + }, + { + "epoch": 0.34, + "learning_rate": 1.6649857259820303e-05, + "loss": 1.4449, + "step": 3257 + }, + { + "epoch": 0.34, + "learning_rate": 1.6647123134440126e-05, + "loss": 1.424, + "step": 3258 + }, + { + "epoch": 0.34, + "learning_rate": 1.664438811851624e-05, + "loss": 1.4737, + "step": 3259 + }, + { + "epoch": 0.34, + "learning_rate": 1.6641652212415066e-05, + "loss": 1.2717, + "step": 3260 + }, + { + "epoch": 0.34, + "learning_rate": 1.663891541650315e-05, + "loss": 1.4845, + "step": 3261 + }, + { + "epoch": 0.34, + "learning_rate": 1.663617773114715e-05, + "loss": 1.4115, + "step": 3262 + }, + { + "epoch": 0.34, + "learning_rate": 1.663343915671384e-05, + "loss": 1.4237, + "step": 3263 + }, + { + "epoch": 0.34, + "learning_rate": 1.6630699693570127e-05, + "loss": 1.4209, + "step": 3264 + }, + { + "epoch": 0.34, + "learning_rate": 1.6627959342083026e-05, + "loss": 1.506, + "step": 3265 + }, + { + "epoch": 0.34, + "learning_rate": 1.6625218102619672e-05, + "loss": 1.4466, + "step": 3266 + }, + { + "epoch": 0.34, + "learning_rate": 1.6622475975547324e-05, + "loss": 1.4129, + "step": 3267 + }, + { + "epoch": 0.34, + "learning_rate": 1.661973296123335e-05, + "loss": 1.4152, + "step": 3268 + }, + { + "epoch": 0.34, + "learning_rate": 1.661698906004525e-05, + "loss": 1.43, + "step": 3269 + }, + { + "epoch": 0.34, + "learning_rate": 1.661424427235064e-05, + "loss": 1.4701, + "step": 3270 + }, + { + "epoch": 0.34, + "learning_rate": 1.6611498598517238e-05, + "loss": 1.4598, + "step": 3271 + }, + { + "epoch": 0.34, + "learning_rate": 1.66087520389129e-05, + "loss": 1.4795, + "step": 3272 + }, + { + "epoch": 0.34, + "learning_rate": 1.6606004593905595e-05, + "loss": 1.5264, + "step": 3273 + }, + { + "epoch": 0.34, + "learning_rate": 1.6603256263863415e-05, + "loss": 1.4412, + "step": 3274 + }, + { + "epoch": 0.34, + "learning_rate": 1.6600507049154556e-05, + "loss": 1.45, + "step": 3275 + }, + { + "epoch": 0.34, + "learning_rate": 1.659775695014735e-05, + "loss": 1.4985, + "step": 3276 + }, + { + "epoch": 0.34, + "learning_rate": 1.659500596721024e-05, + "loss": 1.496, + "step": 3277 + }, + { + "epoch": 0.34, + "learning_rate": 1.6592254100711775e-05, + "loss": 1.4386, + "step": 3278 + }, + { + "epoch": 0.34, + "learning_rate": 1.658950135102065e-05, + "loss": 1.4073, + "step": 3279 + }, + { + "epoch": 0.34, + "learning_rate": 1.658674771850565e-05, + "loss": 1.3912, + "step": 3280 + }, + { + "epoch": 0.34, + "learning_rate": 1.6583993203535702e-05, + "loss": 1.3628, + "step": 3281 + }, + { + "epoch": 0.34, + "learning_rate": 1.658123780647983e-05, + "loss": 1.6089, + "step": 3282 + }, + { + "epoch": 0.34, + "learning_rate": 1.6578481527707196e-05, + "loss": 1.2367, + "step": 3283 + }, + { + "epoch": 0.34, + "learning_rate": 1.657572436758706e-05, + "loss": 1.4058, + "step": 3284 + }, + { + "epoch": 0.34, + "learning_rate": 1.6572966326488825e-05, + "loss": 1.4067, + "step": 3285 + }, + { + "epoch": 0.34, + "learning_rate": 1.657020740478198e-05, + "loss": 1.4187, + "step": 3286 + }, + { + "epoch": 0.34, + "learning_rate": 1.6567447602836166e-05, + "loss": 1.4599, + "step": 3287 + }, + { + "epoch": 0.34, + "learning_rate": 1.6564686921021115e-05, + "loss": 1.432, + "step": 3288 + }, + { + "epoch": 0.34, + "learning_rate": 1.6561925359706693e-05, + "loss": 1.3941, + "step": 3289 + }, + { + "epoch": 0.35, + "learning_rate": 1.6559162919262874e-05, + "loss": 1.3644, + "step": 3290 + }, + { + "epoch": 0.35, + "learning_rate": 1.6556399600059756e-05, + "loss": 1.4628, + "step": 3291 + }, + { + "epoch": 0.35, + "learning_rate": 1.6553635402467555e-05, + "loss": 1.4355, + "step": 3292 + }, + { + "epoch": 0.35, + "learning_rate": 1.6550870326856596e-05, + "loss": 1.4627, + "step": 3293 + }, + { + "epoch": 0.35, + "learning_rate": 1.6548104373597335e-05, + "loss": 1.442, + "step": 3294 + }, + { + "epoch": 0.35, + "learning_rate": 1.6545337543060338e-05, + "loss": 1.3991, + "step": 3295 + }, + { + "epoch": 0.35, + "learning_rate": 1.6542569835616283e-05, + "loss": 1.4193, + "step": 3296 + }, + { + "epoch": 0.35, + "learning_rate": 1.6539801251635982e-05, + "loss": 1.4792, + "step": 3297 + }, + { + "epoch": 0.35, + "learning_rate": 1.653703179149034e-05, + "loss": 1.4735, + "step": 3298 + }, + { + "epoch": 0.35, + "learning_rate": 1.6534261455550408e-05, + "loss": 1.451, + "step": 3299 + }, + { + "epoch": 0.35, + "learning_rate": 1.653149024418733e-05, + "loss": 1.3975, + "step": 3300 + }, + { + "epoch": 0.35, + "learning_rate": 1.652871815777238e-05, + "loss": 1.4843, + "step": 3301 + }, + { + "epoch": 0.35, + "learning_rate": 1.6525945196676948e-05, + "loss": 1.4782, + "step": 3302 + }, + { + "epoch": 0.35, + "learning_rate": 1.652317136127254e-05, + "loss": 1.3865, + "step": 3303 + }, + { + "epoch": 0.35, + "learning_rate": 1.6520396651930777e-05, + "loss": 1.4359, + "step": 3304 + }, + { + "epoch": 0.35, + "learning_rate": 1.6517621069023397e-05, + "loss": 1.4289, + "step": 3305 + }, + { + "epoch": 0.35, + "learning_rate": 1.651484461292226e-05, + "loss": 1.3526, + "step": 3306 + }, + { + "epoch": 0.35, + "learning_rate": 1.6512067283999336e-05, + "loss": 1.3671, + "step": 3307 + }, + { + "epoch": 0.35, + "learning_rate": 1.650928908262672e-05, + "loss": 1.6041, + "step": 3308 + }, + { + "epoch": 0.35, + "learning_rate": 1.650651000917662e-05, + "loss": 1.4322, + "step": 3309 + }, + { + "epoch": 0.35, + "learning_rate": 1.6503730064021354e-05, + "loss": 1.3992, + "step": 3310 + }, + { + "epoch": 0.35, + "learning_rate": 1.650094924753337e-05, + "loss": 1.4928, + "step": 3311 + }, + { + "epoch": 0.35, + "learning_rate": 1.6498167560085222e-05, + "loss": 1.4075, + "step": 3312 + }, + { + "epoch": 0.35, + "learning_rate": 1.6495385002049583e-05, + "loss": 1.4535, + "step": 3313 + }, + { + "epoch": 0.35, + "learning_rate": 1.6492601573799253e-05, + "loss": 1.4221, + "step": 3314 + }, + { + "epoch": 0.35, + "learning_rate": 1.6489817275707133e-05, + "loss": 1.3688, + "step": 3315 + }, + { + "epoch": 0.35, + "learning_rate": 1.6487032108146243e-05, + "loss": 1.3889, + "step": 3316 + }, + { + "epoch": 0.35, + "learning_rate": 1.6484246071489733e-05, + "loss": 1.3942, + "step": 3317 + }, + { + "epoch": 0.35, + "learning_rate": 1.6481459166110858e-05, + "loss": 1.4004, + "step": 3318 + }, + { + "epoch": 0.35, + "learning_rate": 1.647867139238299e-05, + "loss": 1.7308, + "step": 3319 + }, + { + "epoch": 0.35, + "learning_rate": 1.6475882750679622e-05, + "loss": 1.5001, + "step": 3320 + }, + { + "epoch": 0.35, + "learning_rate": 1.647309324137435e-05, + "loss": 1.4325, + "step": 3321 + }, + { + "epoch": 0.35, + "learning_rate": 1.6470302864840913e-05, + "loss": 1.4494, + "step": 3322 + }, + { + "epoch": 0.35, + "learning_rate": 1.6467511621453136e-05, + "loss": 1.4418, + "step": 3323 + }, + { + "epoch": 0.35, + "learning_rate": 1.646471951158498e-05, + "loss": 1.4046, + "step": 3324 + }, + { + "epoch": 0.35, + "learning_rate": 1.6461926535610517e-05, + "loss": 1.5031, + "step": 3325 + }, + { + "epoch": 0.35, + "learning_rate": 1.645913269390393e-05, + "loss": 1.4813, + "step": 3326 + }, + { + "epoch": 0.35, + "learning_rate": 1.6456337986839525e-05, + "loss": 1.3842, + "step": 3327 + }, + { + "epoch": 0.35, + "learning_rate": 1.645354241479172e-05, + "loss": 1.4539, + "step": 3328 + }, + { + "epoch": 0.35, + "learning_rate": 1.6450745978135048e-05, + "loss": 1.4503, + "step": 3329 + }, + { + "epoch": 0.35, + "learning_rate": 1.6447948677244163e-05, + "loss": 1.3741, + "step": 3330 + }, + { + "epoch": 0.35, + "learning_rate": 1.6445150512493832e-05, + "loss": 1.425, + "step": 3331 + }, + { + "epoch": 0.35, + "learning_rate": 1.644235148425893e-05, + "loss": 1.4277, + "step": 3332 + }, + { + "epoch": 0.35, + "learning_rate": 1.6439551592914464e-05, + "loss": 1.4918, + "step": 3333 + }, + { + "epoch": 0.35, + "learning_rate": 1.6436750838835543e-05, + "loss": 1.3364, + "step": 3334 + }, + { + "epoch": 0.35, + "learning_rate": 1.6433949222397397e-05, + "loss": 1.4741, + "step": 3335 + }, + { + "epoch": 0.35, + "learning_rate": 1.643114674397537e-05, + "loss": 1.3867, + "step": 3336 + }, + { + "epoch": 0.35, + "learning_rate": 1.642834340394492e-05, + "loss": 1.3817, + "step": 3337 + }, + { + "epoch": 0.35, + "learning_rate": 1.6425539202681625e-05, + "loss": 1.4308, + "step": 3338 + }, + { + "epoch": 0.35, + "learning_rate": 1.6422734140561178e-05, + "loss": 1.4401, + "step": 3339 + }, + { + "epoch": 0.35, + "learning_rate": 1.641992821795938e-05, + "loss": 1.4338, + "step": 3340 + }, + { + "epoch": 0.35, + "learning_rate": 1.641712143525216e-05, + "loss": 1.3804, + "step": 3341 + }, + { + "epoch": 0.35, + "learning_rate": 1.6414313792815546e-05, + "loss": 1.371, + "step": 3342 + }, + { + "epoch": 0.35, + "learning_rate": 1.6411505291025695e-05, + "loss": 1.4102, + "step": 3343 + }, + { + "epoch": 0.35, + "learning_rate": 1.6408695930258875e-05, + "loss": 1.4433, + "step": 3344 + }, + { + "epoch": 0.35, + "learning_rate": 1.6405885710891467e-05, + "loss": 1.3895, + "step": 3345 + }, + { + "epoch": 0.35, + "learning_rate": 1.6403074633299966e-05, + "loss": 1.4321, + "step": 3346 + }, + { + "epoch": 0.35, + "learning_rate": 1.640026269786098e-05, + "loss": 1.4207, + "step": 3347 + }, + { + "epoch": 0.35, + "learning_rate": 1.639744990495125e-05, + "loss": 1.3758, + "step": 3348 + }, + { + "epoch": 0.35, + "learning_rate": 1.6394636254947612e-05, + "loss": 1.4203, + "step": 3349 + }, + { + "epoch": 0.35, + "learning_rate": 1.6391821748227013e-05, + "loss": 1.4596, + "step": 3350 + }, + { + "epoch": 0.35, + "learning_rate": 1.6389006385166537e-05, + "loss": 1.4344, + "step": 3351 + }, + { + "epoch": 0.35, + "learning_rate": 1.6386190166143366e-05, + "loss": 1.4048, + "step": 3352 + }, + { + "epoch": 0.35, + "learning_rate": 1.6383373091534798e-05, + "loss": 1.4348, + "step": 3353 + }, + { + "epoch": 0.35, + "learning_rate": 1.638055516171825e-05, + "loss": 1.4972, + "step": 3354 + }, + { + "epoch": 0.35, + "learning_rate": 1.6377736377071258e-05, + "loss": 1.4685, + "step": 3355 + }, + { + "epoch": 0.35, + "learning_rate": 1.637491673797146e-05, + "loss": 1.4093, + "step": 3356 + }, + { + "epoch": 0.35, + "learning_rate": 1.6372096244796616e-05, + "loss": 1.4452, + "step": 3357 + }, + { + "epoch": 0.35, + "learning_rate": 1.63692748979246e-05, + "loss": 1.4458, + "step": 3358 + }, + { + "epoch": 0.35, + "learning_rate": 1.6366452697733404e-05, + "loss": 1.4187, + "step": 3359 + }, + { + "epoch": 0.35, + "learning_rate": 1.6363629644601126e-05, + "loss": 1.4052, + "step": 3360 + }, + { + "epoch": 0.35, + "learning_rate": 1.6360805738905984e-05, + "loss": 1.439, + "step": 3361 + }, + { + "epoch": 0.35, + "learning_rate": 1.635798098102631e-05, + "loss": 1.4131, + "step": 3362 + }, + { + "epoch": 0.35, + "learning_rate": 1.6355155371340544e-05, + "loss": 1.4391, + "step": 3363 + }, + { + "epoch": 0.35, + "learning_rate": 1.6352328910227252e-05, + "loss": 1.4318, + "step": 3364 + }, + { + "epoch": 0.35, + "learning_rate": 1.63495015980651e-05, + "loss": 1.5112, + "step": 3365 + }, + { + "epoch": 0.35, + "learning_rate": 1.6346673435232884e-05, + "loss": 1.4688, + "step": 3366 + }, + { + "epoch": 0.35, + "learning_rate": 1.6343844422109496e-05, + "loss": 1.3807, + "step": 3367 + }, + { + "epoch": 0.35, + "learning_rate": 1.634101455907396e-05, + "loss": 1.4083, + "step": 3368 + }, + { + "epoch": 0.35, + "learning_rate": 1.6338183846505394e-05, + "loss": 1.3566, + "step": 3369 + }, + { + "epoch": 0.35, + "learning_rate": 1.633535228478305e-05, + "loss": 1.4287, + "step": 3370 + }, + { + "epoch": 0.35, + "learning_rate": 1.6332519874286285e-05, + "loss": 1.3494, + "step": 3371 + }, + { + "epoch": 0.35, + "learning_rate": 1.6329686615394558e-05, + "loss": 1.3813, + "step": 3372 + }, + { + "epoch": 0.35, + "learning_rate": 1.6326852508487468e-05, + "loss": 1.4241, + "step": 3373 + }, + { + "epoch": 0.35, + "learning_rate": 1.63240175539447e-05, + "loss": 1.424, + "step": 3374 + }, + { + "epoch": 0.35, + "learning_rate": 1.632118175214607e-05, + "loss": 1.4212, + "step": 3375 + }, + { + "epoch": 0.35, + "learning_rate": 1.6318345103471504e-05, + "loss": 1.4671, + "step": 3376 + }, + { + "epoch": 0.35, + "learning_rate": 1.6315507608301044e-05, + "loss": 1.4593, + "step": 3377 + }, + { + "epoch": 0.35, + "learning_rate": 1.631266926701483e-05, + "loss": 1.7816, + "step": 3378 + }, + { + "epoch": 0.35, + "learning_rate": 1.6309830079993134e-05, + "loss": 1.5134, + "step": 3379 + }, + { + "epoch": 0.35, + "learning_rate": 1.6306990047616334e-05, + "loss": 0.8933, + "step": 3380 + }, + { + "epoch": 0.35, + "learning_rate": 1.630414917026492e-05, + "loss": 1.1033, + "step": 3381 + }, + { + "epoch": 0.35, + "learning_rate": 1.6301307448319497e-05, + "loss": 1.3494, + "step": 3382 + }, + { + "epoch": 0.35, + "learning_rate": 1.6298464882160784e-05, + "loss": 1.4299, + "step": 3383 + }, + { + "epoch": 0.35, + "eval_loss": 1.482450008392334, + "eval_runtime": 77.3737, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3383 + }, + { + "epoch": 0.35, + "learning_rate": 1.629562147216961e-05, + "loss": 1.3971, + "step": 3384 + }, + { + "epoch": 0.35, + "learning_rate": 1.6292777218726917e-05, + "loss": 1.3706, + "step": 3385 + }, + { + "epoch": 0.36, + "learning_rate": 1.6289932122213765e-05, + "loss": 1.4524, + "step": 3386 + }, + { + "epoch": 0.36, + "learning_rate": 1.6287086183011328e-05, + "loss": 1.4595, + "step": 3387 + }, + { + "epoch": 0.36, + "learning_rate": 1.628423940150088e-05, + "loss": 1.492, + "step": 3388 + }, + { + "epoch": 0.36, + "learning_rate": 1.628139177806382e-05, + "loss": 1.5576, + "step": 3389 + }, + { + "epoch": 0.36, + "learning_rate": 1.6278543313081657e-05, + "loss": 1.4615, + "step": 3390 + }, + { + "epoch": 0.36, + "learning_rate": 1.6275694006936015e-05, + "loss": 1.3456, + "step": 3391 + }, + { + "epoch": 0.36, + "learning_rate": 1.627284386000862e-05, + "loss": 1.4254, + "step": 3392 + }, + { + "epoch": 0.36, + "learning_rate": 1.6269992872681325e-05, + "loss": 1.433, + "step": 3393 + }, + { + "epoch": 0.36, + "learning_rate": 1.626714104533609e-05, + "loss": 1.5291, + "step": 3394 + }, + { + "epoch": 0.36, + "learning_rate": 1.626428837835498e-05, + "loss": 1.4502, + "step": 3395 + }, + { + "epoch": 0.36, + "learning_rate": 1.626143487212019e-05, + "loss": 1.3756, + "step": 3396 + }, + { + "epoch": 0.36, + "learning_rate": 1.6258580527014002e-05, + "loss": 1.414, + "step": 3397 + }, + { + "epoch": 0.36, + "learning_rate": 1.6255725343418835e-05, + "loss": 1.6289, + "step": 3398 + }, + { + "epoch": 0.36, + "learning_rate": 1.6252869321717208e-05, + "loss": 1.4862, + "step": 3399 + }, + { + "epoch": 0.36, + "learning_rate": 1.6250012462291756e-05, + "loss": 1.4213, + "step": 3400 + }, + { + "epoch": 0.36, + "learning_rate": 1.6247154765525217e-05, + "loss": 1.524, + "step": 3401 + }, + { + "epoch": 0.36, + "learning_rate": 1.624429623180046e-05, + "loss": 1.6013, + "step": 3402 + }, + { + "epoch": 0.36, + "learning_rate": 1.624143686150045e-05, + "loss": 1.4557, + "step": 3403 + }, + { + "epoch": 0.36, + "learning_rate": 1.6238576655008266e-05, + "loss": 1.3831, + "step": 3404 + }, + { + "epoch": 0.36, + "learning_rate": 1.6235715612707105e-05, + "loss": 1.4008, + "step": 3405 + }, + { + "epoch": 0.36, + "learning_rate": 1.623285373498028e-05, + "loss": 1.4848, + "step": 3406 + }, + { + "epoch": 0.36, + "learning_rate": 1.6229991022211197e-05, + "loss": 1.4459, + "step": 3407 + }, + { + "epoch": 0.36, + "learning_rate": 1.6227127474783393e-05, + "loss": 1.4334, + "step": 3408 + }, + { + "epoch": 0.36, + "learning_rate": 1.6224263093080507e-05, + "loss": 1.4123, + "step": 3409 + }, + { + "epoch": 0.36, + "learning_rate": 1.6221397877486294e-05, + "loss": 1.3691, + "step": 3410 + }, + { + "epoch": 0.36, + "learning_rate": 1.6218531828384618e-05, + "loss": 1.4128, + "step": 3411 + }, + { + "epoch": 0.36, + "learning_rate": 1.6215664946159457e-05, + "loss": 1.3642, + "step": 3412 + }, + { + "epoch": 0.36, + "learning_rate": 1.6212797231194902e-05, + "loss": 1.4311, + "step": 3413 + }, + { + "epoch": 0.36, + "learning_rate": 1.6209928683875152e-05, + "loss": 1.4695, + "step": 3414 + }, + { + "epoch": 0.36, + "learning_rate": 1.6207059304584514e-05, + "loss": 1.3871, + "step": 3415 + }, + { + "epoch": 0.36, + "learning_rate": 1.6204189093707414e-05, + "loss": 1.4219, + "step": 3416 + }, + { + "epoch": 0.36, + "learning_rate": 1.620131805162839e-05, + "loss": 1.6199, + "step": 3417 + }, + { + "epoch": 0.36, + "learning_rate": 1.619844617873208e-05, + "loss": 1.4433, + "step": 3418 + }, + { + "epoch": 0.36, + "learning_rate": 1.619557347540325e-05, + "loss": 1.4773, + "step": 3419 + }, + { + "epoch": 0.36, + "learning_rate": 1.6192699942026763e-05, + "loss": 1.4551, + "step": 3420 + }, + { + "epoch": 0.36, + "learning_rate": 1.6189825578987603e-05, + "loss": 1.4903, + "step": 3421 + }, + { + "epoch": 0.36, + "learning_rate": 1.6186950386670855e-05, + "loss": 1.473, + "step": 3422 + }, + { + "epoch": 0.36, + "learning_rate": 1.6184074365461722e-05, + "loss": 1.4082, + "step": 3423 + }, + { + "epoch": 0.36, + "learning_rate": 1.6181197515745523e-05, + "loss": 1.4746, + "step": 3424 + }, + { + "epoch": 0.36, + "learning_rate": 1.6178319837907674e-05, + "loss": 1.449, + "step": 3425 + }, + { + "epoch": 0.36, + "learning_rate": 1.6175441332333715e-05, + "loss": 1.377, + "step": 3426 + }, + { + "epoch": 0.36, + "learning_rate": 1.617256199940929e-05, + "loss": 1.2364, + "step": 3427 + }, + { + "epoch": 0.36, + "learning_rate": 1.6169681839520155e-05, + "loss": 1.4437, + "step": 3428 + }, + { + "epoch": 0.36, + "learning_rate": 1.616680085305218e-05, + "loss": 1.4726, + "step": 3429 + }, + { + "epoch": 0.36, + "learning_rate": 1.616391904039134e-05, + "loss": 1.4824, + "step": 3430 + }, + { + "epoch": 0.36, + "learning_rate": 1.616103640192373e-05, + "loss": 1.4052, + "step": 3431 + }, + { + "epoch": 0.36, + "learning_rate": 1.6158152938035537e-05, + "loss": 1.4131, + "step": 3432 + }, + { + "epoch": 0.36, + "learning_rate": 1.6155268649113084e-05, + "loss": 1.4267, + "step": 3433 + }, + { + "epoch": 0.36, + "learning_rate": 1.6152383535542786e-05, + "loss": 1.3735, + "step": 3434 + }, + { + "epoch": 0.36, + "learning_rate": 1.6149497597711175e-05, + "loss": 1.4249, + "step": 3435 + }, + { + "epoch": 0.36, + "learning_rate": 1.614661083600489e-05, + "loss": 1.4312, + "step": 3436 + }, + { + "epoch": 0.36, + "learning_rate": 1.6143723250810686e-05, + "loss": 1.4831, + "step": 3437 + }, + { + "epoch": 0.36, + "learning_rate": 1.6140834842515425e-05, + "loss": 1.4183, + "step": 3438 + }, + { + "epoch": 0.36, + "learning_rate": 1.6137945611506078e-05, + "loss": 1.3908, + "step": 3439 + }, + { + "epoch": 0.36, + "learning_rate": 1.613505555816973e-05, + "loss": 1.425, + "step": 3440 + }, + { + "epoch": 0.36, + "learning_rate": 1.613216468289357e-05, + "loss": 1.3589, + "step": 3441 + }, + { + "epoch": 0.36, + "learning_rate": 1.6129272986064903e-05, + "loss": 1.4272, + "step": 3442 + }, + { + "epoch": 0.36, + "learning_rate": 1.6126380468071142e-05, + "loss": 1.4337, + "step": 3443 + }, + { + "epoch": 0.36, + "learning_rate": 1.6123487129299817e-05, + "loss": 1.3872, + "step": 3444 + }, + { + "epoch": 0.36, + "learning_rate": 1.612059297013855e-05, + "loss": 1.374, + "step": 3445 + }, + { + "epoch": 0.36, + "learning_rate": 1.611769799097509e-05, + "loss": 1.314, + "step": 3446 + }, + { + "epoch": 0.36, + "learning_rate": 1.6114802192197284e-05, + "loss": 1.3951, + "step": 3447 + }, + { + "epoch": 0.36, + "learning_rate": 1.6111905574193102e-05, + "loss": 1.4732, + "step": 3448 + }, + { + "epoch": 0.36, + "learning_rate": 1.6109008137350614e-05, + "loss": 1.3575, + "step": 3449 + }, + { + "epoch": 0.36, + "learning_rate": 1.6106109882058e-05, + "loss": 1.4606, + "step": 3450 + }, + { + "epoch": 0.36, + "learning_rate": 1.6103210808703554e-05, + "loss": 1.4357, + "step": 3451 + }, + { + "epoch": 0.36, + "learning_rate": 1.6100310917675678e-05, + "loss": 0.8456, + "step": 3452 + }, + { + "epoch": 0.36, + "learning_rate": 1.609741020936288e-05, + "loss": 1.07, + "step": 3453 + }, + { + "epoch": 0.36, + "learning_rate": 1.6094508684153782e-05, + "loss": 1.4435, + "step": 3454 + }, + { + "epoch": 0.36, + "learning_rate": 1.609160634243711e-05, + "loss": 1.3696, + "step": 3455 + }, + { + "epoch": 0.36, + "learning_rate": 1.6088703184601712e-05, + "loss": 1.4012, + "step": 3456 + }, + { + "epoch": 0.36, + "learning_rate": 1.608579921103653e-05, + "loss": 1.5212, + "step": 3457 + }, + { + "epoch": 0.36, + "learning_rate": 1.608289442213062e-05, + "loss": 1.4339, + "step": 3458 + }, + { + "epoch": 0.36, + "learning_rate": 1.607998881827316e-05, + "loss": 1.4901, + "step": 3459 + }, + { + "epoch": 0.36, + "learning_rate": 1.6077082399853412e-05, + "loss": 1.4822, + "step": 3460 + }, + { + "epoch": 0.36, + "learning_rate": 1.607417516726077e-05, + "loss": 1.3696, + "step": 3461 + }, + { + "epoch": 0.36, + "learning_rate": 1.6071267120884727e-05, + "loss": 1.4434, + "step": 3462 + }, + { + "epoch": 0.36, + "learning_rate": 1.6068358261114886e-05, + "loss": 1.3916, + "step": 3463 + }, + { + "epoch": 0.36, + "learning_rate": 1.606544858834096e-05, + "loss": 1.422, + "step": 3464 + }, + { + "epoch": 0.36, + "learning_rate": 1.6062538102952763e-05, + "loss": 1.367, + "step": 3465 + }, + { + "epoch": 0.36, + "learning_rate": 1.605962680534024e-05, + "loss": 1.3788, + "step": 3466 + }, + { + "epoch": 0.36, + "learning_rate": 1.605671469589342e-05, + "loss": 1.4366, + "step": 3467 + }, + { + "epoch": 0.36, + "learning_rate": 1.6053801775002453e-05, + "loss": 1.4027, + "step": 3468 + }, + { + "epoch": 0.36, + "learning_rate": 1.6050888043057595e-05, + "loss": 1.4386, + "step": 3469 + }, + { + "epoch": 0.36, + "learning_rate": 1.6047973500449212e-05, + "loss": 1.4675, + "step": 3470 + }, + { + "epoch": 0.36, + "learning_rate": 1.6045058147567778e-05, + "loss": 1.6936, + "step": 3471 + }, + { + "epoch": 0.36, + "learning_rate": 1.6042141984803875e-05, + "loss": 1.4858, + "step": 3472 + }, + { + "epoch": 0.36, + "learning_rate": 1.6039225012548196e-05, + "loss": 1.5004, + "step": 3473 + }, + { + "epoch": 0.36, + "learning_rate": 1.6036307231191534e-05, + "loss": 1.4969, + "step": 3474 + }, + { + "epoch": 0.36, + "learning_rate": 1.6033388641124803e-05, + "loss": 1.4027, + "step": 3475 + }, + { + "epoch": 0.36, + "learning_rate": 1.6030469242739016e-05, + "loss": 1.4741, + "step": 3476 + }, + { + "epoch": 0.36, + "learning_rate": 1.60275490364253e-05, + "loss": 1.3887, + "step": 3477 + }, + { + "epoch": 0.36, + "learning_rate": 1.602462802257488e-05, + "loss": 1.6735, + "step": 3478 + }, + { + "epoch": 0.36, + "learning_rate": 1.602170620157911e-05, + "loss": 1.4997, + "step": 3479 + }, + { + "epoch": 0.36, + "learning_rate": 1.601878357382943e-05, + "loss": 1.3973, + "step": 3480 + }, + { + "epoch": 0.37, + "learning_rate": 1.6015860139717398e-05, + "loss": 1.416, + "step": 3481 + }, + { + "epoch": 0.37, + "learning_rate": 1.6012935899634682e-05, + "loss": 1.4102, + "step": 3482 + }, + { + "epoch": 0.37, + "learning_rate": 1.601001085397305e-05, + "loss": 1.4248, + "step": 3483 + }, + { + "epoch": 0.37, + "learning_rate": 1.6007085003124386e-05, + "loss": 1.3909, + "step": 3484 + }, + { + "epoch": 0.37, + "learning_rate": 1.600415834748068e-05, + "loss": 1.4029, + "step": 3485 + }, + { + "epoch": 0.37, + "learning_rate": 1.6001230887434024e-05, + "loss": 1.4219, + "step": 3486 + }, + { + "epoch": 0.37, + "learning_rate": 1.5998302623376633e-05, + "loss": 1.4008, + "step": 3487 + }, + { + "epoch": 0.37, + "learning_rate": 1.5995373555700806e-05, + "loss": 1.5163, + "step": 3488 + }, + { + "epoch": 0.37, + "learning_rate": 1.599244368479897e-05, + "loss": 1.4541, + "step": 3489 + }, + { + "epoch": 0.37, + "learning_rate": 1.598951301106365e-05, + "loss": 1.4454, + "step": 3490 + }, + { + "epoch": 0.37, + "learning_rate": 1.598658153488748e-05, + "loss": 1.1014, + "step": 3491 + }, + { + "epoch": 0.37, + "learning_rate": 1.598364925666321e-05, + "loss": 1.407, + "step": 3492 + }, + { + "epoch": 0.37, + "learning_rate": 1.5980716176783682e-05, + "loss": 1.5046, + "step": 3493 + }, + { + "epoch": 0.37, + "learning_rate": 1.5977782295641857e-05, + "loss": 1.4265, + "step": 3494 + }, + { + "epoch": 0.37, + "learning_rate": 1.5974847613630796e-05, + "loss": 1.46, + "step": 3495 + }, + { + "epoch": 0.37, + "learning_rate": 1.5971912131143677e-05, + "loss": 1.3996, + "step": 3496 + }, + { + "epoch": 0.37, + "learning_rate": 1.5968975848573772e-05, + "loss": 1.4719, + "step": 3497 + }, + { + "epoch": 0.37, + "learning_rate": 1.596603876631447e-05, + "loss": 1.43, + "step": 3498 + }, + { + "epoch": 0.37, + "learning_rate": 1.596310088475927e-05, + "loss": 1.4109, + "step": 3499 + }, + { + "epoch": 0.37, + "learning_rate": 1.5960162204301768e-05, + "loss": 1.3612, + "step": 3500 + }, + { + "epoch": 0.37, + "learning_rate": 1.5957222725335672e-05, + "loss": 1.5045, + "step": 3501 + }, + { + "epoch": 0.37, + "learning_rate": 1.5954282448254794e-05, + "loss": 1.5323, + "step": 3502 + }, + { + "epoch": 0.37, + "learning_rate": 1.595134137345306e-05, + "loss": 1.4518, + "step": 3503 + }, + { + "epoch": 0.37, + "learning_rate": 1.5948399501324495e-05, + "loss": 1.6131, + "step": 3504 + }, + { + "epoch": 0.37, + "learning_rate": 1.594545683226324e-05, + "loss": 1.5076, + "step": 3505 + }, + { + "epoch": 0.37, + "learning_rate": 1.594251336666353e-05, + "loss": 1.482, + "step": 3506 + }, + { + "epoch": 0.37, + "learning_rate": 1.5939569104919716e-05, + "loss": 1.4429, + "step": 3507 + }, + { + "epoch": 0.37, + "learning_rate": 1.5936624047426254e-05, + "loss": 1.4662, + "step": 3508 + }, + { + "epoch": 0.37, + "learning_rate": 1.5933678194577708e-05, + "loss": 1.425, + "step": 3509 + }, + { + "epoch": 0.37, + "learning_rate": 1.5930731546768744e-05, + "loss": 1.4312, + "step": 3510 + }, + { + "epoch": 0.37, + "learning_rate": 1.592778410439414e-05, + "loss": 1.4336, + "step": 3511 + }, + { + "epoch": 0.37, + "learning_rate": 1.5924835867848775e-05, + "loss": 1.4197, + "step": 3512 + }, + { + "epoch": 0.37, + "learning_rate": 1.5921886837527638e-05, + "loss": 1.4456, + "step": 3513 + }, + { + "epoch": 0.37, + "learning_rate": 1.5918937013825823e-05, + "loss": 1.4394, + "step": 3514 + }, + { + "epoch": 0.37, + "learning_rate": 1.5915986397138526e-05, + "loss": 1.3606, + "step": 3515 + }, + { + "epoch": 0.37, + "learning_rate": 1.591303498786106e-05, + "loss": 1.4382, + "step": 3516 + }, + { + "epoch": 0.37, + "learning_rate": 1.591008278638884e-05, + "loss": 1.4185, + "step": 3517 + }, + { + "epoch": 0.37, + "learning_rate": 1.5907129793117374e-05, + "loss": 1.6692, + "step": 3518 + }, + { + "epoch": 0.37, + "learning_rate": 1.59041760084423e-05, + "loss": 1.501, + "step": 3519 + }, + { + "epoch": 0.37, + "learning_rate": 1.5901221432759345e-05, + "loss": 1.5753, + "step": 3520 + }, + { + "epoch": 0.37, + "learning_rate": 1.589826606646434e-05, + "loss": 1.4795, + "step": 3521 + }, + { + "epoch": 0.37, + "learning_rate": 1.5895309909953236e-05, + "loss": 1.4379, + "step": 3522 + }, + { + "epoch": 0.37, + "learning_rate": 1.5892352963622078e-05, + "loss": 1.3426, + "step": 3523 + }, + { + "epoch": 0.37, + "learning_rate": 1.5889395227867025e-05, + "loss": 1.4048, + "step": 3524 + }, + { + "epoch": 0.37, + "learning_rate": 1.5886436703084332e-05, + "loss": 1.4303, + "step": 3525 + }, + { + "epoch": 0.37, + "learning_rate": 1.5883477389670367e-05, + "loss": 1.3684, + "step": 3526 + }, + { + "epoch": 0.37, + "learning_rate": 1.5880517288021602e-05, + "loss": 1.3701, + "step": 3527 + }, + { + "epoch": 0.37, + "learning_rate": 1.587755639853462e-05, + "loss": 1.4308, + "step": 3528 + }, + { + "epoch": 0.37, + "learning_rate": 1.5874594721606096e-05, + "loss": 1.3981, + "step": 3529 + }, + { + "epoch": 0.37, + "learning_rate": 1.5871632257632823e-05, + "loss": 1.5906, + "step": 3530 + }, + { + "epoch": 0.37, + "learning_rate": 1.5868669007011696e-05, + "loss": 1.4642, + "step": 3531 + }, + { + "epoch": 0.37, + "learning_rate": 1.586570497013971e-05, + "loss": 1.411, + "step": 3532 + }, + { + "epoch": 0.37, + "learning_rate": 1.586274014741397e-05, + "loss": 1.3942, + "step": 3533 + }, + { + "epoch": 0.37, + "learning_rate": 1.5859774539231693e-05, + "loss": 1.3952, + "step": 3534 + }, + { + "epoch": 0.37, + "learning_rate": 1.585680814599019e-05, + "loss": 1.4009, + "step": 3535 + }, + { + "epoch": 0.37, + "learning_rate": 1.585384096808688e-05, + "loss": 1.3238, + "step": 3536 + }, + { + "epoch": 0.37, + "learning_rate": 1.585087300591929e-05, + "loss": 1.346, + "step": 3537 + }, + { + "epoch": 0.37, + "learning_rate": 1.584790425988505e-05, + "loss": 1.3739, + "step": 3538 + }, + { + "epoch": 0.37, + "learning_rate": 1.5844934730381895e-05, + "loss": 1.4264, + "step": 3539 + }, + { + "epoch": 0.37, + "learning_rate": 1.5841964417807668e-05, + "loss": 1.4675, + "step": 3540 + }, + { + "epoch": 0.37, + "learning_rate": 1.5838993322560314e-05, + "loss": 1.3337, + "step": 3541 + }, + { + "epoch": 0.37, + "learning_rate": 1.5836021445037883e-05, + "loss": 1.4052, + "step": 3542 + }, + { + "epoch": 0.37, + "learning_rate": 1.583304878563853e-05, + "loss": 1.4311, + "step": 3543 + }, + { + "epoch": 0.37, + "learning_rate": 1.5830075344760513e-05, + "loss": 1.386, + "step": 3544 + }, + { + "epoch": 0.37, + "learning_rate": 1.58271011228022e-05, + "loss": 1.387, + "step": 3545 + }, + { + "epoch": 0.37, + "learning_rate": 1.582412612016206e-05, + "loss": 1.3601, + "step": 3546 + }, + { + "epoch": 0.37, + "learning_rate": 1.5821150337238663e-05, + "loss": 1.5111, + "step": 3547 + }, + { + "epoch": 0.37, + "learning_rate": 1.5818173774430697e-05, + "loss": 1.471, + "step": 3548 + }, + { + "epoch": 0.37, + "learning_rate": 1.581519643213693e-05, + "loss": 1.4442, + "step": 3549 + }, + { + "epoch": 0.37, + "learning_rate": 1.5812218310756263e-05, + "loss": 1.467, + "step": 3550 + }, + { + "epoch": 0.37, + "learning_rate": 1.5809239410687683e-05, + "loss": 1.3731, + "step": 3551 + }, + { + "epoch": 0.37, + "learning_rate": 1.5806259732330286e-05, + "loss": 1.4072, + "step": 3552 + }, + { + "epoch": 0.37, + "learning_rate": 1.5803279276083268e-05, + "loss": 1.3636, + "step": 3553 + }, + { + "epoch": 0.37, + "learning_rate": 1.5800298042345938e-05, + "loss": 1.3915, + "step": 3554 + }, + { + "epoch": 0.37, + "learning_rate": 1.5797316031517705e-05, + "loss": 1.5038, + "step": 3555 + }, + { + "epoch": 0.37, + "learning_rate": 1.5794333243998082e-05, + "loss": 1.4455, + "step": 3556 + }, + { + "epoch": 0.37, + "learning_rate": 1.5791349680186684e-05, + "loss": 1.5062, + "step": 3557 + }, + { + "epoch": 0.37, + "learning_rate": 1.5788365340483234e-05, + "loss": 1.3899, + "step": 3558 + }, + { + "epoch": 0.37, + "learning_rate": 1.5785380225287554e-05, + "loss": 1.4946, + "step": 3559 + }, + { + "epoch": 0.37, + "learning_rate": 1.5782394334999572e-05, + "loss": 1.3859, + "step": 3560 + }, + { + "epoch": 0.37, + "learning_rate": 1.577940767001933e-05, + "loss": 1.541, + "step": 3561 + }, + { + "epoch": 0.37, + "learning_rate": 1.5776420230746952e-05, + "loss": 1.4952, + "step": 3562 + }, + { + "epoch": 0.37, + "learning_rate": 1.5773432017582684e-05, + "loss": 1.6055, + "step": 3563 + }, + { + "epoch": 0.37, + "learning_rate": 1.577044303092687e-05, + "loss": 1.4661, + "step": 3564 + }, + { + "epoch": 0.37, + "learning_rate": 1.576745327117996e-05, + "loss": 1.4082, + "step": 3565 + }, + { + "epoch": 0.37, + "learning_rate": 1.5764462738742493e-05, + "loss": 1.4005, + "step": 3566 + }, + { + "epoch": 0.37, + "learning_rate": 1.5761471434015137e-05, + "loss": 1.3959, + "step": 3567 + }, + { + "epoch": 0.37, + "learning_rate": 1.5758479357398645e-05, + "loss": 1.4567, + "step": 3568 + }, + { + "epoch": 0.37, + "learning_rate": 1.575548650929388e-05, + "loss": 1.3791, + "step": 3569 + }, + { + "epoch": 0.37, + "learning_rate": 1.57524928901018e-05, + "loss": 1.4428, + "step": 3570 + }, + { + "epoch": 0.37, + "learning_rate": 1.5749498500223486e-05, + "loss": 1.3864, + "step": 3571 + }, + { + "epoch": 0.37, + "learning_rate": 1.5746503340060097e-05, + "loss": 1.4019, + "step": 3572 + }, + { + "epoch": 0.37, + "learning_rate": 1.574350741001291e-05, + "loss": 1.5436, + "step": 3573 + }, + { + "epoch": 0.37, + "learning_rate": 1.5740510710483308e-05, + "loss": 1.4637, + "step": 3574 + }, + { + "epoch": 0.37, + "learning_rate": 1.5737513241872767e-05, + "loss": 1.5097, + "step": 3575 + }, + { + "epoch": 0.38, + "learning_rate": 1.5734515004582873e-05, + "loss": 1.5143, + "step": 3576 + }, + { + "epoch": 0.38, + "learning_rate": 1.5731515999015315e-05, + "loss": 1.3926, + "step": 3577 + }, + { + "epoch": 0.38, + "learning_rate": 1.5728516225571874e-05, + "loss": 1.4242, + "step": 3578 + }, + { + "epoch": 0.38, + "learning_rate": 1.5725515684654453e-05, + "loss": 1.4429, + "step": 3579 + }, + { + "epoch": 0.38, + "learning_rate": 1.572251437666504e-05, + "loss": 1.4638, + "step": 3580 + }, + { + "epoch": 0.38, + "learning_rate": 1.5719512302005735e-05, + "loss": 1.3381, + "step": 3581 + }, + { + "epoch": 0.38, + "learning_rate": 1.571650946107874e-05, + "loss": 1.4342, + "step": 3582 + }, + { + "epoch": 0.38, + "eval_loss": 1.4705015420913696, + "eval_runtime": 77.3664, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3582 + }, + { + "epoch": 0.38, + "learning_rate": 1.571350585428636e-05, + "loss": 1.3991, + "step": 3583 + }, + { + "epoch": 0.38, + "learning_rate": 1.5710501482030998e-05, + "loss": 1.4274, + "step": 3584 + }, + { + "epoch": 0.38, + "learning_rate": 1.5707496344715166e-05, + "loss": 1.438, + "step": 3585 + }, + { + "epoch": 0.38, + "learning_rate": 1.570449044274147e-05, + "loss": 1.4453, + "step": 3586 + }, + { + "epoch": 0.38, + "learning_rate": 1.570148377651263e-05, + "loss": 1.4022, + "step": 3587 + }, + { + "epoch": 0.38, + "learning_rate": 1.5698476346431454e-05, + "loss": 1.4312, + "step": 3588 + }, + { + "epoch": 0.38, + "learning_rate": 1.569546815290087e-05, + "loss": 1.4329, + "step": 3589 + }, + { + "epoch": 0.38, + "learning_rate": 1.569245919632389e-05, + "loss": 1.4036, + "step": 3590 + }, + { + "epoch": 0.38, + "learning_rate": 1.5689449477103644e-05, + "loss": 1.412, + "step": 3591 + }, + { + "epoch": 0.38, + "learning_rate": 1.5686438995643353e-05, + "loss": 1.4492, + "step": 3592 + }, + { + "epoch": 0.38, + "learning_rate": 1.5683427752346343e-05, + "loss": 1.4555, + "step": 3593 + }, + { + "epoch": 0.38, + "learning_rate": 1.5680415747616047e-05, + "loss": 1.5594, + "step": 3594 + }, + { + "epoch": 0.38, + "learning_rate": 1.5677402981855993e-05, + "loss": 1.4813, + "step": 3595 + }, + { + "epoch": 0.38, + "learning_rate": 1.567438945546982e-05, + "loss": 1.5919, + "step": 3596 + }, + { + "epoch": 0.38, + "learning_rate": 1.5671375168861255e-05, + "loss": 1.4235, + "step": 3597 + }, + { + "epoch": 0.38, + "learning_rate": 1.5668360122434135e-05, + "loss": 1.441, + "step": 3598 + }, + { + "epoch": 0.38, + "learning_rate": 1.566534431659241e-05, + "loss": 1.5847, + "step": 3599 + }, + { + "epoch": 0.38, + "learning_rate": 1.566232775174011e-05, + "loss": 1.6123, + "step": 3600 + }, + { + "epoch": 0.38, + "learning_rate": 1.5659310428281374e-05, + "loss": 1.4916, + "step": 3601 + }, + { + "epoch": 0.38, + "learning_rate": 1.5656292346620457e-05, + "loss": 1.4603, + "step": 3602 + }, + { + "epoch": 0.38, + "learning_rate": 1.56532735071617e-05, + "loss": 1.4423, + "step": 3603 + }, + { + "epoch": 0.38, + "learning_rate": 1.5650253910309547e-05, + "loss": 1.4814, + "step": 3604 + }, + { + "epoch": 0.38, + "learning_rate": 1.5647233556468552e-05, + "loss": 1.4015, + "step": 3605 + }, + { + "epoch": 0.38, + "learning_rate": 1.564421244604336e-05, + "loss": 1.3798, + "step": 3606 + }, + { + "epoch": 0.38, + "learning_rate": 1.5641190579438723e-05, + "loss": 1.4259, + "step": 3607 + }, + { + "epoch": 0.38, + "learning_rate": 1.5638167957059493e-05, + "loss": 1.3493, + "step": 3608 + }, + { + "epoch": 0.38, + "learning_rate": 1.5635144579310626e-05, + "loss": 1.3433, + "step": 3609 + }, + { + "epoch": 0.38, + "learning_rate": 1.5632120446597177e-05, + "loss": 1.4661, + "step": 3610 + }, + { + "epoch": 0.38, + "learning_rate": 1.5629095559324297e-05, + "loss": 1.4205, + "step": 3611 + }, + { + "epoch": 0.38, + "learning_rate": 1.562606991789725e-05, + "loss": 1.3976, + "step": 3612 + }, + { + "epoch": 0.38, + "learning_rate": 1.5623043522721393e-05, + "loss": 1.4261, + "step": 3613 + }, + { + "epoch": 0.38, + "learning_rate": 1.562001637420218e-05, + "loss": 1.4358, + "step": 3614 + }, + { + "epoch": 0.38, + "learning_rate": 1.5616988472745175e-05, + "loss": 1.437, + "step": 3615 + }, + { + "epoch": 0.38, + "learning_rate": 1.561395981875604e-05, + "loss": 1.3735, + "step": 3616 + }, + { + "epoch": 0.38, + "learning_rate": 1.5610930412640532e-05, + "loss": 1.4357, + "step": 3617 + }, + { + "epoch": 0.38, + "learning_rate": 1.560790025480452e-05, + "loss": 1.4003, + "step": 3618 + }, + { + "epoch": 0.38, + "learning_rate": 1.5604869345653965e-05, + "loss": 1.4127, + "step": 3619 + }, + { + "epoch": 0.38, + "learning_rate": 1.5601837685594927e-05, + "loss": 1.4666, + "step": 3620 + }, + { + "epoch": 0.38, + "learning_rate": 1.5598805275033574e-05, + "loss": 1.4106, + "step": 3621 + }, + { + "epoch": 0.38, + "learning_rate": 1.5595772114376174e-05, + "loss": 1.3857, + "step": 3622 + }, + { + "epoch": 0.38, + "learning_rate": 1.5592738204029086e-05, + "loss": 1.4704, + "step": 3623 + }, + { + "epoch": 0.38, + "learning_rate": 1.558970354439878e-05, + "loss": 1.4649, + "step": 3624 + }, + { + "epoch": 0.38, + "learning_rate": 1.5586668135891824e-05, + "loss": 1.4812, + "step": 3625 + }, + { + "epoch": 0.38, + "learning_rate": 1.5583631978914882e-05, + "loss": 1.3507, + "step": 3626 + }, + { + "epoch": 0.38, + "learning_rate": 1.5580595073874718e-05, + "loss": 1.3762, + "step": 3627 + }, + { + "epoch": 0.38, + "learning_rate": 1.557755742117821e-05, + "loss": 1.4169, + "step": 3628 + }, + { + "epoch": 0.38, + "learning_rate": 1.557451902123231e-05, + "loss": 1.4098, + "step": 3629 + }, + { + "epoch": 0.38, + "learning_rate": 1.55714798744441e-05, + "loss": 1.5526, + "step": 3630 + }, + { + "epoch": 0.38, + "learning_rate": 1.556843998122074e-05, + "loss": 1.4414, + "step": 3631 + }, + { + "epoch": 0.38, + "learning_rate": 1.5565399341969497e-05, + "loss": 1.4134, + "step": 3632 + }, + { + "epoch": 0.38, + "learning_rate": 1.556235795709774e-05, + "loss": 1.4718, + "step": 3633 + }, + { + "epoch": 0.38, + "learning_rate": 1.5559315827012937e-05, + "loss": 1.412, + "step": 3634 + }, + { + "epoch": 0.38, + "learning_rate": 1.5556272952122657e-05, + "loss": 1.4119, + "step": 3635 + }, + { + "epoch": 0.38, + "learning_rate": 1.5553229332834564e-05, + "loss": 1.3999, + "step": 3636 + }, + { + "epoch": 0.38, + "learning_rate": 1.5550184969556428e-05, + "loss": 1.4626, + "step": 3637 + }, + { + "epoch": 0.38, + "learning_rate": 1.5547139862696113e-05, + "loss": 1.3811, + "step": 3638 + }, + { + "epoch": 0.38, + "learning_rate": 1.5544094012661583e-05, + "loss": 1.4053, + "step": 3639 + }, + { + "epoch": 0.38, + "learning_rate": 1.5541047419860907e-05, + "loss": 1.4059, + "step": 3640 + }, + { + "epoch": 0.38, + "learning_rate": 1.553800008470225e-05, + "loss": 1.4717, + "step": 3641 + }, + { + "epoch": 0.38, + "learning_rate": 1.553495200759388e-05, + "loss": 1.399, + "step": 3642 + }, + { + "epoch": 0.38, + "learning_rate": 1.5531903188944154e-05, + "loss": 1.4143, + "step": 3643 + }, + { + "epoch": 0.38, + "learning_rate": 1.5528853629161536e-05, + "loss": 1.4414, + "step": 3644 + }, + { + "epoch": 0.38, + "learning_rate": 1.5525803328654592e-05, + "loss": 1.4206, + "step": 3645 + }, + { + "epoch": 0.38, + "learning_rate": 1.5522752287831982e-05, + "loss": 1.3869, + "step": 3646 + }, + { + "epoch": 0.38, + "learning_rate": 1.551970050710247e-05, + "loss": 1.5434, + "step": 3647 + }, + { + "epoch": 0.38, + "learning_rate": 1.5516647986874914e-05, + "loss": 1.4574, + "step": 3648 + }, + { + "epoch": 0.38, + "learning_rate": 1.5513594727558273e-05, + "loss": 1.4353, + "step": 3649 + }, + { + "epoch": 0.38, + "learning_rate": 1.5510540729561606e-05, + "loss": 1.4122, + "step": 3650 + }, + { + "epoch": 0.38, + "learning_rate": 1.550748599329407e-05, + "loss": 1.4077, + "step": 3651 + }, + { + "epoch": 0.38, + "learning_rate": 1.550443051916492e-05, + "loss": 1.4433, + "step": 3652 + }, + { + "epoch": 0.38, + "learning_rate": 1.5501374307583514e-05, + "loss": 1.54, + "step": 3653 + }, + { + "epoch": 0.38, + "learning_rate": 1.5498317358959302e-05, + "loss": 1.4522, + "step": 3654 + }, + { + "epoch": 0.38, + "learning_rate": 1.5495259673701842e-05, + "loss": 1.4175, + "step": 3655 + }, + { + "epoch": 0.38, + "learning_rate": 1.5492201252220777e-05, + "loss": 1.4637, + "step": 3656 + }, + { + "epoch": 0.38, + "learning_rate": 1.5489142094925863e-05, + "loss": 1.4701, + "step": 3657 + }, + { + "epoch": 0.38, + "learning_rate": 1.548608220222695e-05, + "loss": 1.4095, + "step": 3658 + }, + { + "epoch": 0.38, + "learning_rate": 1.548302157453398e-05, + "loss": 1.3903, + "step": 3659 + }, + { + "epoch": 0.38, + "learning_rate": 1.5479960212257002e-05, + "loss": 1.4062, + "step": 3660 + }, + { + "epoch": 0.38, + "learning_rate": 1.5476898115806157e-05, + "loss": 1.4706, + "step": 3661 + }, + { + "epoch": 0.38, + "learning_rate": 1.547383528559169e-05, + "loss": 1.4423, + "step": 3662 + }, + { + "epoch": 0.38, + "learning_rate": 1.547077172202394e-05, + "loss": 1.4418, + "step": 3663 + }, + { + "epoch": 0.38, + "learning_rate": 1.5467707425513347e-05, + "loss": 1.4553, + "step": 3664 + }, + { + "epoch": 0.38, + "learning_rate": 1.5464642396470443e-05, + "loss": 1.435, + "step": 3665 + }, + { + "epoch": 0.38, + "learning_rate": 1.5461576635305873e-05, + "loss": 1.4105, + "step": 3666 + }, + { + "epoch": 0.38, + "learning_rate": 1.5458510142430364e-05, + "loss": 1.4118, + "step": 3667 + }, + { + "epoch": 0.38, + "learning_rate": 1.5455442918254746e-05, + "loss": 1.4096, + "step": 3668 + }, + { + "epoch": 0.38, + "learning_rate": 1.545237496318995e-05, + "loss": 1.4248, + "step": 3669 + }, + { + "epoch": 0.38, + "learning_rate": 1.5449306277647003e-05, + "loss": 1.4591, + "step": 3670 + }, + { + "epoch": 0.38, + "learning_rate": 1.544623686203703e-05, + "loss": 1.4764, + "step": 3671 + }, + { + "epoch": 0.39, + "learning_rate": 1.5443166716771255e-05, + "loss": 1.4329, + "step": 3672 + }, + { + "epoch": 0.39, + "learning_rate": 1.5440095842260995e-05, + "loss": 1.4023, + "step": 3673 + }, + { + "epoch": 0.39, + "learning_rate": 1.5437024238917674e-05, + "loss": 1.3802, + "step": 3674 + }, + { + "epoch": 0.39, + "learning_rate": 1.5433951907152806e-05, + "loss": 1.4627, + "step": 3675 + }, + { + "epoch": 0.39, + "learning_rate": 1.5430878847378e-05, + "loss": 1.5164, + "step": 3676 + }, + { + "epoch": 0.39, + "learning_rate": 1.542780506000497e-05, + "loss": 1.3546, + "step": 3677 + }, + { + "epoch": 0.39, + "learning_rate": 1.542473054544553e-05, + "loss": 1.4415, + "step": 3678 + }, + { + "epoch": 0.39, + "learning_rate": 1.5421655304111573e-05, + "loss": 1.4093, + "step": 3679 + }, + { + "epoch": 0.39, + "learning_rate": 1.5418579336415114e-05, + "loss": 1.3943, + "step": 3680 + }, + { + "epoch": 0.39, + "learning_rate": 1.5415502642768252e-05, + "loss": 1.3659, + "step": 3681 + }, + { + "epoch": 0.39, + "learning_rate": 1.541242522358318e-05, + "loss": 1.4322, + "step": 3682 + }, + { + "epoch": 0.39, + "learning_rate": 1.5409347079272198e-05, + "loss": 1.4064, + "step": 3683 + }, + { + "epoch": 0.39, + "learning_rate": 1.5406268210247693e-05, + "loss": 1.4031, + "step": 3684 + }, + { + "epoch": 0.39, + "learning_rate": 1.540318861692216e-05, + "loss": 1.3449, + "step": 3685 + }, + { + "epoch": 0.39, + "learning_rate": 1.5400108299708182e-05, + "loss": 1.5536, + "step": 3686 + }, + { + "epoch": 0.39, + "learning_rate": 1.5397027259018442e-05, + "loss": 1.4106, + "step": 3687 + }, + { + "epoch": 0.39, + "learning_rate": 1.5393945495265722e-05, + "loss": 1.4309, + "step": 3688 + }, + { + "epoch": 0.39, + "learning_rate": 1.53908630088629e-05, + "loss": 1.3765, + "step": 3689 + }, + { + "epoch": 0.39, + "learning_rate": 1.5387779800222947e-05, + "loss": 1.3809, + "step": 3690 + }, + { + "epoch": 0.39, + "learning_rate": 1.5384695869758938e-05, + "loss": 1.4758, + "step": 3691 + }, + { + "epoch": 0.39, + "learning_rate": 1.5381611217884032e-05, + "loss": 1.4249, + "step": 3692 + }, + { + "epoch": 0.39, + "learning_rate": 1.5378525845011503e-05, + "loss": 1.4133, + "step": 3693 + }, + { + "epoch": 0.39, + "learning_rate": 1.5375439751554708e-05, + "loss": 1.418, + "step": 3694 + }, + { + "epoch": 0.39, + "learning_rate": 1.53723529379271e-05, + "loss": 1.441, + "step": 3695 + }, + { + "epoch": 0.39, + "learning_rate": 1.536926540454224e-05, + "loss": 1.3919, + "step": 3696 + }, + { + "epoch": 0.39, + "learning_rate": 1.5366177151813775e-05, + "loss": 1.3722, + "step": 3697 + }, + { + "epoch": 0.39, + "learning_rate": 1.536308818015545e-05, + "loss": 1.4727, + "step": 3698 + }, + { + "epoch": 0.39, + "learning_rate": 1.535999848998111e-05, + "loss": 1.442, + "step": 3699 + }, + { + "epoch": 0.39, + "learning_rate": 1.535690808170469e-05, + "loss": 1.3884, + "step": 3700 + }, + { + "epoch": 0.39, + "learning_rate": 1.535381695574023e-05, + "loss": 1.3226, + "step": 3701 + }, + { + "epoch": 0.39, + "learning_rate": 1.535072511250186e-05, + "loss": 1.4403, + "step": 3702 + }, + { + "epoch": 0.39, + "learning_rate": 1.5347632552403808e-05, + "loss": 1.4144, + "step": 3703 + }, + { + "epoch": 0.39, + "learning_rate": 1.5344539275860395e-05, + "loss": 1.3514, + "step": 3704 + }, + { + "epoch": 0.39, + "learning_rate": 1.5341445283286044e-05, + "loss": 1.519, + "step": 3705 + }, + { + "epoch": 0.39, + "learning_rate": 1.5338350575095268e-05, + "loss": 1.4251, + "step": 3706 + }, + { + "epoch": 0.39, + "learning_rate": 1.5335255151702685e-05, + "loss": 1.392, + "step": 3707 + }, + { + "epoch": 0.39, + "learning_rate": 1.533215901352299e-05, + "loss": 1.3838, + "step": 3708 + }, + { + "epoch": 0.39, + "learning_rate": 1.532906216097099e-05, + "loss": 1.444, + "step": 3709 + }, + { + "epoch": 0.39, + "learning_rate": 1.5325964594461594e-05, + "loss": 1.3459, + "step": 3710 + }, + { + "epoch": 0.39, + "learning_rate": 1.5322866314409783e-05, + "loss": 1.4155, + "step": 3711 + }, + { + "epoch": 0.39, + "learning_rate": 1.5319767321230657e-05, + "loss": 1.4057, + "step": 3712 + }, + { + "epoch": 0.39, + "learning_rate": 1.5316667615339392e-05, + "loss": 1.382, + "step": 3713 + }, + { + "epoch": 0.39, + "learning_rate": 1.5313567197151277e-05, + "loss": 1.3634, + "step": 3714 + }, + { + "epoch": 0.39, + "learning_rate": 1.5310466067081688e-05, + "loss": 1.3434, + "step": 3715 + }, + { + "epoch": 0.39, + "learning_rate": 1.530736422554609e-05, + "loss": 1.4553, + "step": 3716 + }, + { + "epoch": 0.39, + "learning_rate": 1.5304261672960055e-05, + "loss": 1.4193, + "step": 3717 + }, + { + "epoch": 0.39, + "learning_rate": 1.5301158409739242e-05, + "loss": 1.3955, + "step": 3718 + }, + { + "epoch": 0.39, + "learning_rate": 1.5298054436299413e-05, + "loss": 1.4592, + "step": 3719 + }, + { + "epoch": 0.39, + "learning_rate": 1.529494975305642e-05, + "loss": 1.738, + "step": 3720 + }, + { + "epoch": 0.39, + "learning_rate": 1.529184436042621e-05, + "loss": 1.438, + "step": 3721 + }, + { + "epoch": 0.39, + "learning_rate": 1.528873825882482e-05, + "loss": 1.3445, + "step": 3722 + }, + { + "epoch": 0.39, + "learning_rate": 1.5285631448668395e-05, + "loss": 1.4168, + "step": 3723 + }, + { + "epoch": 0.39, + "learning_rate": 1.528252393037317e-05, + "loss": 1.4088, + "step": 3724 + }, + { + "epoch": 0.39, + "learning_rate": 1.5279415704355468e-05, + "loss": 1.4484, + "step": 3725 + }, + { + "epoch": 0.39, + "learning_rate": 1.5276306771031708e-05, + "loss": 1.4706, + "step": 3726 + }, + { + "epoch": 0.39, + "learning_rate": 1.527319713081841e-05, + "loss": 1.3466, + "step": 3727 + }, + { + "epoch": 0.39, + "learning_rate": 1.5270086784132196e-05, + "loss": 1.427, + "step": 3728 + }, + { + "epoch": 0.39, + "learning_rate": 1.5266975731389754e-05, + "loss": 1.4596, + "step": 3729 + }, + { + "epoch": 0.39, + "learning_rate": 1.52638639730079e-05, + "loss": 1.405, + "step": 3730 + }, + { + "epoch": 0.39, + "learning_rate": 1.5260751509403518e-05, + "loss": 1.4572, + "step": 3731 + }, + { + "epoch": 0.39, + "learning_rate": 1.5257638340993608e-05, + "loss": 1.3827, + "step": 3732 + }, + { + "epoch": 0.39, + "learning_rate": 1.5254524468195251e-05, + "loss": 1.3712, + "step": 3733 + }, + { + "epoch": 0.39, + "learning_rate": 1.5251409891425626e-05, + "loss": 1.4541, + "step": 3734 + }, + { + "epoch": 0.39, + "learning_rate": 1.5248294611102006e-05, + "loss": 1.5279, + "step": 3735 + }, + { + "epoch": 0.39, + "learning_rate": 1.5245178627641759e-05, + "loss": 1.3722, + "step": 3736 + }, + { + "epoch": 0.39, + "learning_rate": 1.5242061941462348e-05, + "loss": 1.5158, + "step": 3737 + }, + { + "epoch": 0.39, + "learning_rate": 1.523894455298132e-05, + "loss": 1.4274, + "step": 3738 + }, + { + "epoch": 0.39, + "learning_rate": 1.5235826462616338e-05, + "loss": 1.4543, + "step": 3739 + }, + { + "epoch": 0.39, + "learning_rate": 1.5232707670785144e-05, + "loss": 1.5011, + "step": 3740 + }, + { + "epoch": 0.39, + "learning_rate": 1.5229588177905568e-05, + "loss": 1.24, + "step": 3741 + }, + { + "epoch": 0.39, + "learning_rate": 1.5226467984395544e-05, + "loss": 1.4253, + "step": 3742 + }, + { + "epoch": 0.39, + "learning_rate": 1.5223347090673102e-05, + "loss": 1.3736, + "step": 3743 + }, + { + "epoch": 0.39, + "learning_rate": 1.522022549715636e-05, + "loss": 1.4587, + "step": 3744 + }, + { + "epoch": 0.39, + "learning_rate": 1.521710320426353e-05, + "loss": 1.5024, + "step": 3745 + }, + { + "epoch": 0.39, + "learning_rate": 1.521398021241292e-05, + "loss": 1.427, + "step": 3746 + }, + { + "epoch": 0.39, + "learning_rate": 1.5210856522022929e-05, + "loss": 1.3387, + "step": 3747 + }, + { + "epoch": 0.39, + "learning_rate": 1.5207732133512055e-05, + "loss": 1.3819, + "step": 3748 + }, + { + "epoch": 0.39, + "learning_rate": 1.5204607047298883e-05, + "loss": 1.4571, + "step": 3749 + }, + { + "epoch": 0.39, + "learning_rate": 1.5201481263802094e-05, + "loss": 1.3592, + "step": 3750 + }, + { + "epoch": 0.39, + "learning_rate": 1.5198354783440464e-05, + "loss": 1.3912, + "step": 3751 + }, + { + "epoch": 0.39, + "learning_rate": 1.519522760663286e-05, + "loss": 1.4986, + "step": 3752 + }, + { + "epoch": 0.39, + "learning_rate": 1.5192099733798243e-05, + "loss": 1.4106, + "step": 3753 + }, + { + "epoch": 0.39, + "learning_rate": 1.5188971165355667e-05, + "loss": 1.4145, + "step": 3754 + }, + { + "epoch": 0.39, + "learning_rate": 1.5185841901724282e-05, + "loss": 1.3915, + "step": 3755 + }, + { + "epoch": 0.39, + "learning_rate": 1.5182711943323329e-05, + "loss": 1.4014, + "step": 3756 + }, + { + "epoch": 0.39, + "learning_rate": 1.5179581290572141e-05, + "loss": 1.3651, + "step": 3757 + }, + { + "epoch": 0.39, + "learning_rate": 1.5176449943890147e-05, + "loss": 1.3653, + "step": 3758 + }, + { + "epoch": 0.39, + "learning_rate": 1.5173317903696862e-05, + "loss": 1.4486, + "step": 3759 + }, + { + "epoch": 0.39, + "learning_rate": 1.5170185170411906e-05, + "loss": 1.4459, + "step": 3760 + }, + { + "epoch": 0.39, + "learning_rate": 1.5167051744454977e-05, + "loss": 1.4215, + "step": 3761 + }, + { + "epoch": 0.39, + "learning_rate": 1.5163917626245877e-05, + "loss": 1.4379, + "step": 3762 + }, + { + "epoch": 0.39, + "learning_rate": 1.51607828162045e-05, + "loss": 1.4147, + "step": 3763 + }, + { + "epoch": 0.39, + "learning_rate": 1.5157647314750827e-05, + "loss": 1.4011, + "step": 3764 + }, + { + "epoch": 0.39, + "learning_rate": 1.5154511122304936e-05, + "loss": 1.4309, + "step": 3765 + }, + { + "epoch": 0.39, + "learning_rate": 1.5151374239286993e-05, + "loss": 1.4382, + "step": 3766 + }, + { + "epoch": 0.4, + "learning_rate": 1.5148236666117266e-05, + "loss": 1.405, + "step": 3767 + }, + { + "epoch": 0.4, + "learning_rate": 1.5145098403216104e-05, + "loss": 1.4223, + "step": 3768 + }, + { + "epoch": 0.4, + "learning_rate": 1.5141959451003951e-05, + "loss": 1.4084, + "step": 3769 + }, + { + "epoch": 0.4, + "learning_rate": 1.5138819809901356e-05, + "loss": 1.4063, + "step": 3770 + }, + { + "epoch": 0.4, + "learning_rate": 1.513567948032894e-05, + "loss": 1.3299, + "step": 3771 + }, + { + "epoch": 0.4, + "learning_rate": 1.5132538462707431e-05, + "loss": 1.3901, + "step": 3772 + }, + { + "epoch": 0.4, + "learning_rate": 1.5129396757457646e-05, + "loss": 1.4249, + "step": 3773 + }, + { + "epoch": 0.4, + "learning_rate": 1.512625436500049e-05, + "loss": 1.4087, + "step": 3774 + }, + { + "epoch": 0.4, + "learning_rate": 1.5123111285756964e-05, + "loss": 1.3521, + "step": 3775 + }, + { + "epoch": 0.4, + "learning_rate": 1.5119967520148163e-05, + "loss": 1.4097, + "step": 3776 + }, + { + "epoch": 0.4, + "learning_rate": 1.5116823068595261e-05, + "loss": 1.4871, + "step": 3777 + }, + { + "epoch": 0.4, + "learning_rate": 1.5113677931519543e-05, + "loss": 1.44, + "step": 3778 + }, + { + "epoch": 0.4, + "learning_rate": 1.5110532109342377e-05, + "loss": 1.4518, + "step": 3779 + }, + { + "epoch": 0.4, + "learning_rate": 1.5107385602485214e-05, + "loss": 1.3961, + "step": 3780 + }, + { + "epoch": 0.4, + "learning_rate": 1.5104238411369614e-05, + "loss": 1.4341, + "step": 3781 + }, + { + "epoch": 0.4, + "eval_loss": 1.4642821550369263, + "eval_runtime": 77.3595, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 3781 + }, + { + "epoch": 0.4, + "learning_rate": 1.5101090536417218e-05, + "loss": 1.403, + "step": 3782 + }, + { + "epoch": 0.4, + "learning_rate": 1.5097941978049754e-05, + "loss": 1.4103, + "step": 3783 + }, + { + "epoch": 0.4, + "learning_rate": 1.5094792736689052e-05, + "loss": 1.3478, + "step": 3784 + }, + { + "epoch": 0.4, + "learning_rate": 1.5091642812757035e-05, + "loss": 1.4134, + "step": 3785 + }, + { + "epoch": 0.4, + "learning_rate": 1.5088492206675701e-05, + "loss": 1.4134, + "step": 3786 + }, + { + "epoch": 0.4, + "learning_rate": 1.5085340918867162e-05, + "loss": 1.1494, + "step": 3787 + }, + { + "epoch": 0.4, + "learning_rate": 1.5082188949753598e-05, + "loss": 1.2385, + "step": 3788 + }, + { + "epoch": 0.4, + "learning_rate": 1.5079036299757299e-05, + "loss": 1.4258, + "step": 3789 + }, + { + "epoch": 0.4, + "learning_rate": 1.5075882969300639e-05, + "loss": 1.3781, + "step": 3790 + }, + { + "epoch": 0.4, + "learning_rate": 1.507272895880608e-05, + "loss": 1.5096, + "step": 3791 + }, + { + "epoch": 0.4, + "learning_rate": 1.5069574268696179e-05, + "loss": 1.366, + "step": 3792 + }, + { + "epoch": 0.4, + "learning_rate": 1.5066418899393584e-05, + "loss": 1.3792, + "step": 3793 + }, + { + "epoch": 0.4, + "learning_rate": 1.506326285132104e-05, + "loss": 1.4987, + "step": 3794 + }, + { + "epoch": 0.4, + "learning_rate": 1.5060106124901364e-05, + "loss": 1.445, + "step": 3795 + }, + { + "epoch": 0.4, + "learning_rate": 1.5056948720557482e-05, + "loss": 1.5071, + "step": 3796 + }, + { + "epoch": 0.4, + "learning_rate": 1.505379063871241e-05, + "loss": 1.4029, + "step": 3797 + }, + { + "epoch": 0.4, + "learning_rate": 1.5050631879789244e-05, + "loss": 1.5263, + "step": 3798 + }, + { + "epoch": 0.4, + "learning_rate": 1.5047472444211175e-05, + "loss": 1.3906, + "step": 3799 + }, + { + "epoch": 0.4, + "learning_rate": 1.5044312332401494e-05, + "loss": 1.7352, + "step": 3800 + }, + { + "epoch": 0.4, + "learning_rate": 1.5041151544783565e-05, + "loss": 1.3946, + "step": 3801 + }, + { + "epoch": 0.4, + "learning_rate": 1.5037990081780862e-05, + "loss": 1.3592, + "step": 3802 + }, + { + "epoch": 0.4, + "learning_rate": 1.503482794381693e-05, + "loss": 1.3991, + "step": 3803 + }, + { + "epoch": 0.4, + "learning_rate": 1.5031665131315423e-05, + "loss": 1.4271, + "step": 3804 + }, + { + "epoch": 0.4, + "learning_rate": 1.502850164470007e-05, + "loss": 1.4305, + "step": 3805 + }, + { + "epoch": 0.4, + "learning_rate": 1.5025337484394701e-05, + "loss": 1.4116, + "step": 3806 + }, + { + "epoch": 0.4, + "learning_rate": 1.5022172650823232e-05, + "loss": 1.4242, + "step": 3807 + }, + { + "epoch": 0.4, + "learning_rate": 1.5019007144409667e-05, + "loss": 1.4427, + "step": 3808 + }, + { + "epoch": 0.4, + "learning_rate": 1.5015840965578106e-05, + "loss": 1.3705, + "step": 3809 + }, + { + "epoch": 0.4, + "learning_rate": 1.5012674114752732e-05, + "loss": 1.4498, + "step": 3810 + }, + { + "epoch": 0.4, + "learning_rate": 1.5009506592357822e-05, + "loss": 1.489, + "step": 3811 + }, + { + "epoch": 0.4, + "learning_rate": 1.5006338398817746e-05, + "loss": 1.4801, + "step": 3812 + }, + { + "epoch": 0.4, + "learning_rate": 1.5003169534556956e-05, + "loss": 1.3468, + "step": 3813 + }, + { + "epoch": 0.4, + "learning_rate": 1.5000000000000002e-05, + "loss": 1.4211, + "step": 3814 + }, + { + "epoch": 0.4, + "learning_rate": 1.4996829795571518e-05, + "loss": 1.4683, + "step": 3815 + }, + { + "epoch": 0.4, + "learning_rate": 1.499365892169623e-05, + "loss": 1.4441, + "step": 3816 + }, + { + "epoch": 0.4, + "learning_rate": 1.4990487378798958e-05, + "loss": 1.4368, + "step": 3817 + }, + { + "epoch": 0.4, + "learning_rate": 1.4987315167304602e-05, + "loss": 1.4097, + "step": 3818 + }, + { + "epoch": 0.4, + "learning_rate": 1.4984142287638155e-05, + "loss": 1.4238, + "step": 3819 + }, + { + "epoch": 0.4, + "learning_rate": 1.4980968740224708e-05, + "loss": 1.497, + "step": 3820 + }, + { + "epoch": 0.4, + "learning_rate": 1.4977794525489433e-05, + "loss": 1.3989, + "step": 3821 + }, + { + "epoch": 0.4, + "learning_rate": 1.4974619643857588e-05, + "loss": 1.4415, + "step": 3822 + }, + { + "epoch": 0.4, + "learning_rate": 1.4971444095754533e-05, + "loss": 1.3931, + "step": 3823 + }, + { + "epoch": 0.4, + "learning_rate": 1.4968267881605705e-05, + "loss": 1.3426, + "step": 3824 + }, + { + "epoch": 0.4, + "learning_rate": 1.4965091001836636e-05, + "loss": 1.644, + "step": 3825 + }, + { + "epoch": 0.4, + "learning_rate": 1.4961913456872945e-05, + "loss": 1.3903, + "step": 3826 + }, + { + "epoch": 0.4, + "learning_rate": 1.4958735247140345e-05, + "loss": 1.3764, + "step": 3827 + }, + { + "epoch": 0.4, + "learning_rate": 1.4955556373064632e-05, + "loss": 1.5484, + "step": 3828 + }, + { + "epoch": 0.4, + "learning_rate": 1.4952376835071696e-05, + "loss": 1.5696, + "step": 3829 + }, + { + "epoch": 0.4, + "learning_rate": 1.4949196633587509e-05, + "loss": 1.3844, + "step": 3830 + }, + { + "epoch": 0.4, + "learning_rate": 1.494601576903814e-05, + "loss": 1.3868, + "step": 3831 + }, + { + "epoch": 0.4, + "learning_rate": 1.4942834241849741e-05, + "loss": 1.4229, + "step": 3832 + }, + { + "epoch": 0.4, + "learning_rate": 1.4939652052448557e-05, + "loss": 1.4062, + "step": 3833 + }, + { + "epoch": 0.4, + "learning_rate": 1.4936469201260915e-05, + "loss": 1.3955, + "step": 3834 + }, + { + "epoch": 0.4, + "learning_rate": 1.4933285688713239e-05, + "loss": 1.3959, + "step": 3835 + }, + { + "epoch": 0.4, + "learning_rate": 1.4930101515232038e-05, + "loss": 1.4652, + "step": 3836 + }, + { + "epoch": 0.4, + "learning_rate": 1.4926916681243913e-05, + "loss": 1.5253, + "step": 3837 + }, + { + "epoch": 0.4, + "learning_rate": 1.4923731187175539e-05, + "loss": 1.4694, + "step": 3838 + }, + { + "epoch": 0.4, + "learning_rate": 1.4920545033453702e-05, + "loss": 1.3859, + "step": 3839 + }, + { + "epoch": 0.4, + "learning_rate": 1.4917358220505259e-05, + "loss": 1.4157, + "step": 3840 + }, + { + "epoch": 0.4, + "learning_rate": 1.4914170748757159e-05, + "loss": 1.4491, + "step": 3841 + }, + { + "epoch": 0.4, + "learning_rate": 1.4910982618636445e-05, + "loss": 1.4464, + "step": 3842 + }, + { + "epoch": 0.4, + "learning_rate": 1.4907793830570246e-05, + "loss": 1.3771, + "step": 3843 + }, + { + "epoch": 0.4, + "learning_rate": 1.4904604384985775e-05, + "loss": 1.3673, + "step": 3844 + }, + { + "epoch": 0.4, + "learning_rate": 1.4901414282310334e-05, + "loss": 1.4429, + "step": 3845 + }, + { + "epoch": 0.4, + "learning_rate": 1.4898223522971318e-05, + "loss": 1.4905, + "step": 3846 + }, + { + "epoch": 0.4, + "learning_rate": 1.4895032107396205e-05, + "loss": 1.4039, + "step": 3847 + }, + { + "epoch": 0.4, + "learning_rate": 1.4891840036012566e-05, + "loss": 1.4082, + "step": 3848 + }, + { + "epoch": 0.4, + "learning_rate": 1.4888647309248052e-05, + "loss": 1.3643, + "step": 3849 + }, + { + "epoch": 0.4, + "learning_rate": 1.4885453927530408e-05, + "loss": 1.3116, + "step": 3850 + }, + { + "epoch": 0.4, + "learning_rate": 1.4882259891287467e-05, + "loss": 1.4278, + "step": 3851 + }, + { + "epoch": 0.4, + "learning_rate": 1.4879065200947148e-05, + "loss": 1.3712, + "step": 3852 + }, + { + "epoch": 0.4, + "learning_rate": 1.4875869856937449e-05, + "loss": 1.387, + "step": 3853 + }, + { + "epoch": 0.4, + "learning_rate": 1.4872673859686475e-05, + "loss": 1.5053, + "step": 3854 + }, + { + "epoch": 0.4, + "learning_rate": 1.4869477209622404e-05, + "loss": 1.4427, + "step": 3855 + }, + { + "epoch": 0.4, + "learning_rate": 1.4866279907173502e-05, + "loss": 1.3404, + "step": 3856 + }, + { + "epoch": 0.4, + "learning_rate": 1.4863081952768126e-05, + "loss": 1.3126, + "step": 3857 + }, + { + "epoch": 0.4, + "learning_rate": 1.4859883346834725e-05, + "loss": 1.4588, + "step": 3858 + }, + { + "epoch": 0.4, + "learning_rate": 1.4856684089801822e-05, + "loss": 1.408, + "step": 3859 + }, + { + "epoch": 0.4, + "learning_rate": 1.4853484182098044e-05, + "loss": 1.4356, + "step": 3860 + }, + { + "epoch": 0.4, + "learning_rate": 1.4850283624152088e-05, + "loss": 1.3768, + "step": 3861 + }, + { + "epoch": 0.4, + "learning_rate": 1.4847082416392753e-05, + "loss": 1.4563, + "step": 3862 + }, + { + "epoch": 0.41, + "learning_rate": 1.4843880559248915e-05, + "loss": 1.3648, + "step": 3863 + }, + { + "epoch": 0.41, + "learning_rate": 1.4840678053149542e-05, + "loss": 1.4146, + "step": 3864 + }, + { + "epoch": 0.41, + "learning_rate": 1.4837474898523686e-05, + "loss": 1.4423, + "step": 3865 + }, + { + "epoch": 0.41, + "learning_rate": 1.4834271095800487e-05, + "loss": 1.3351, + "step": 3866 + }, + { + "epoch": 0.41, + "learning_rate": 1.4831066645409178e-05, + "loss": 1.4534, + "step": 3867 + }, + { + "epoch": 0.41, + "learning_rate": 1.4827861547779066e-05, + "loss": 1.4763, + "step": 3868 + }, + { + "epoch": 0.41, + "learning_rate": 1.4824655803339553e-05, + "loss": 1.4019, + "step": 3869 + }, + { + "epoch": 0.41, + "learning_rate": 1.4821449412520132e-05, + "loss": 1.4223, + "step": 3870 + }, + { + "epoch": 0.41, + "learning_rate": 1.4818242375750371e-05, + "loss": 1.4065, + "step": 3871 + }, + { + "epoch": 0.41, + "learning_rate": 1.481503469345993e-05, + "loss": 1.587, + "step": 3872 + }, + { + "epoch": 0.41, + "learning_rate": 1.4811826366078562e-05, + "loss": 1.3746, + "step": 3873 + }, + { + "epoch": 0.41, + "learning_rate": 1.4808617394036096e-05, + "loss": 1.3425, + "step": 3874 + }, + { + "epoch": 0.41, + "learning_rate": 1.480540777776245e-05, + "loss": 0.6637, + "step": 3875 + }, + { + "epoch": 0.41, + "learning_rate": 1.4802197517687634e-05, + "loss": 1.3366, + "step": 3876 + }, + { + "epoch": 0.41, + "learning_rate": 1.479898661424174e-05, + "loss": 1.4033, + "step": 3877 + }, + { + "epoch": 0.41, + "learning_rate": 1.4795775067854947e-05, + "loss": 1.4005, + "step": 3878 + }, + { + "epoch": 0.41, + "learning_rate": 1.4792562878957516e-05, + "loss": 1.3651, + "step": 3879 + }, + { + "epoch": 0.41, + "learning_rate": 1.47893500479798e-05, + "loss": 1.4185, + "step": 3880 + }, + { + "epoch": 0.41, + "learning_rate": 1.4786136575352236e-05, + "loss": 1.4394, + "step": 3881 + }, + { + "epoch": 0.41, + "learning_rate": 1.478292246150535e-05, + "loss": 1.7243, + "step": 3882 + }, + { + "epoch": 0.41, + "learning_rate": 1.4779707706869744e-05, + "loss": 1.3574, + "step": 3883 + }, + { + "epoch": 0.41, + "learning_rate": 1.4776492311876116e-05, + "loss": 1.4031, + "step": 3884 + }, + { + "epoch": 0.41, + "learning_rate": 1.4773276276955248e-05, + "loss": 1.4351, + "step": 3885 + }, + { + "epoch": 0.41, + "learning_rate": 1.4770059602538002e-05, + "loss": 1.3922, + "step": 3886 + }, + { + "epoch": 0.41, + "learning_rate": 1.4766842289055333e-05, + "loss": 1.3374, + "step": 3887 + }, + { + "epoch": 0.41, + "learning_rate": 1.4763624336938278e-05, + "loss": 1.428, + "step": 3888 + }, + { + "epoch": 0.41, + "learning_rate": 1.476040574661796e-05, + "loss": 1.6087, + "step": 3889 + }, + { + "epoch": 0.41, + "learning_rate": 1.4757186518525586e-05, + "loss": 1.4054, + "step": 3890 + }, + { + "epoch": 0.41, + "learning_rate": 1.4753966653092447e-05, + "loss": 1.2595, + "step": 3891 + }, + { + "epoch": 0.41, + "learning_rate": 1.475074615074993e-05, + "loss": 1.4052, + "step": 3892 + }, + { + "epoch": 0.41, + "learning_rate": 1.4747525011929492e-05, + "loss": 1.4296, + "step": 3893 + }, + { + "epoch": 0.41, + "learning_rate": 1.4744303237062689e-05, + "loss": 1.3718, + "step": 3894 + }, + { + "epoch": 0.41, + "learning_rate": 1.4741080826581151e-05, + "loss": 1.4498, + "step": 3895 + }, + { + "epoch": 0.41, + "learning_rate": 1.4737857780916602e-05, + "loss": 1.4029, + "step": 3896 + }, + { + "epoch": 0.41, + "learning_rate": 1.4734634100500846e-05, + "loss": 1.4136, + "step": 3897 + }, + { + "epoch": 0.41, + "learning_rate": 1.4731409785765774e-05, + "loss": 1.348, + "step": 3898 + }, + { + "epoch": 0.41, + "learning_rate": 1.4728184837143355e-05, + "loss": 1.3407, + "step": 3899 + }, + { + "epoch": 0.41, + "learning_rate": 1.472495925506566e-05, + "loss": 1.3737, + "step": 3900 + }, + { + "epoch": 0.41, + "learning_rate": 1.4721733039964826e-05, + "loss": 2.2305, + "step": 3901 + }, + { + "epoch": 0.41, + "learning_rate": 1.4718506192273087e-05, + "loss": 1.4506, + "step": 3902 + }, + { + "epoch": 0.41, + "learning_rate": 1.4715278712422754e-05, + "loss": 1.3657, + "step": 3903 + }, + { + "epoch": 0.41, + "learning_rate": 1.471205060084623e-05, + "loss": 1.4644, + "step": 3904 + }, + { + "epoch": 0.41, + "learning_rate": 1.4708821857976001e-05, + "loss": 1.4823, + "step": 3905 + }, + { + "epoch": 0.41, + "learning_rate": 1.4705592484244628e-05, + "loss": 1.3392, + "step": 3906 + }, + { + "epoch": 0.41, + "learning_rate": 1.4702362480084769e-05, + "loss": 1.3302, + "step": 3907 + }, + { + "epoch": 0.41, + "learning_rate": 1.4699131845929163e-05, + "loss": 1.8952, + "step": 3908 + }, + { + "epoch": 0.41, + "learning_rate": 1.469590058221063e-05, + "loss": 1.4982, + "step": 3909 + }, + { + "epoch": 0.41, + "learning_rate": 1.4692668689362074e-05, + "loss": 1.407, + "step": 3910 + }, + { + "epoch": 0.41, + "learning_rate": 1.4689436167816489e-05, + "loss": 1.3911, + "step": 3911 + }, + { + "epoch": 0.41, + "learning_rate": 1.4686203018006948e-05, + "loss": 1.3421, + "step": 3912 + }, + { + "epoch": 0.41, + "learning_rate": 1.4682969240366612e-05, + "loss": 1.4627, + "step": 3913 + }, + { + "epoch": 0.41, + "learning_rate": 1.4679734835328718e-05, + "loss": 1.394, + "step": 3914 + }, + { + "epoch": 0.41, + "learning_rate": 1.4676499803326603e-05, + "loss": 1.4484, + "step": 3915 + }, + { + "epoch": 0.41, + "learning_rate": 1.4673264144793673e-05, + "loss": 1.4665, + "step": 3916 + }, + { + "epoch": 0.41, + "learning_rate": 1.4670027860163422e-05, + "loss": 1.3191, + "step": 3917 + }, + { + "epoch": 0.41, + "learning_rate": 1.466679094986943e-05, + "loss": 1.4748, + "step": 3918 + }, + { + "epoch": 0.41, + "learning_rate": 1.4663553414345361e-05, + "loss": 1.2467, + "step": 3919 + }, + { + "epoch": 0.41, + "learning_rate": 1.466031525402496e-05, + "loss": 1.4279, + "step": 3920 + }, + { + "epoch": 0.41, + "learning_rate": 1.4657076469342059e-05, + "loss": 1.3822, + "step": 3921 + }, + { + "epoch": 0.41, + "learning_rate": 1.4653837060730566e-05, + "loss": 1.3659, + "step": 3922 + }, + { + "epoch": 0.41, + "learning_rate": 1.465059702862449e-05, + "loss": 1.3663, + "step": 3923 + }, + { + "epoch": 0.41, + "learning_rate": 1.4647356373457902e-05, + "loss": 1.4371, + "step": 3924 + }, + { + "epoch": 0.41, + "learning_rate": 1.4644115095664972e-05, + "loss": 1.3473, + "step": 3925 + }, + { + "epoch": 0.41, + "learning_rate": 1.4640873195679944e-05, + "loss": 1.4797, + "step": 3926 + }, + { + "epoch": 0.41, + "learning_rate": 1.463763067393715e-05, + "loss": 1.3973, + "step": 3927 + }, + { + "epoch": 0.41, + "learning_rate": 1.4634387530871008e-05, + "loss": 1.3899, + "step": 3928 + }, + { + "epoch": 0.41, + "learning_rate": 1.4631143766916015e-05, + "loss": 1.3828, + "step": 3929 + }, + { + "epoch": 0.41, + "learning_rate": 1.4627899382506745e-05, + "loss": 1.4569, + "step": 3930 + }, + { + "epoch": 0.41, + "learning_rate": 1.4624654378077872e-05, + "loss": 1.4011, + "step": 3931 + }, + { + "epoch": 0.41, + "learning_rate": 1.462140875406414e-05, + "loss": 1.3859, + "step": 3932 + }, + { + "epoch": 0.41, + "learning_rate": 1.4618162510900376e-05, + "loss": 1.4518, + "step": 3933 + }, + { + "epoch": 0.41, + "learning_rate": 1.4614915649021493e-05, + "loss": 1.4399, + "step": 3934 + }, + { + "epoch": 0.41, + "learning_rate": 1.4611668168862495e-05, + "loss": 1.4034, + "step": 3935 + }, + { + "epoch": 0.41, + "learning_rate": 1.4608420070858452e-05, + "loss": 1.3919, + "step": 3936 + }, + { + "epoch": 0.41, + "learning_rate": 1.4605171355444528e-05, + "loss": 1.391, + "step": 3937 + }, + { + "epoch": 0.41, + "learning_rate": 1.460192202305597e-05, + "loss": 1.3717, + "step": 3938 + }, + { + "epoch": 0.41, + "learning_rate": 1.4598672074128103e-05, + "loss": 1.4351, + "step": 3939 + }, + { + "epoch": 0.41, + "learning_rate": 1.4595421509096339e-05, + "loss": 1.4202, + "step": 3940 + }, + { + "epoch": 0.41, + "learning_rate": 1.4592170328396165e-05, + "loss": 1.3559, + "step": 3941 + }, + { + "epoch": 0.41, + "learning_rate": 1.458891853246316e-05, + "loss": 1.5878, + "step": 3942 + }, + { + "epoch": 0.41, + "learning_rate": 1.4585666121732982e-05, + "loss": 1.3818, + "step": 3943 + }, + { + "epoch": 0.41, + "learning_rate": 1.4582413096641369e-05, + "loss": 1.4009, + "step": 3944 + }, + { + "epoch": 0.41, + "learning_rate": 1.457915945762414e-05, + "loss": 1.3937, + "step": 3945 + }, + { + "epoch": 0.41, + "learning_rate": 1.4575905205117203e-05, + "loss": 1.381, + "step": 3946 + }, + { + "epoch": 0.41, + "learning_rate": 1.457265033955654e-05, + "loss": 1.3844, + "step": 3947 + }, + { + "epoch": 0.41, + "learning_rate": 1.4569394861378226e-05, + "loss": 1.4059, + "step": 3948 + }, + { + "epoch": 0.41, + "learning_rate": 1.4566138771018403e-05, + "loss": 1.3698, + "step": 3949 + }, + { + "epoch": 0.41, + "learning_rate": 1.4562882068913311e-05, + "loss": 1.4253, + "step": 3950 + }, + { + "epoch": 0.41, + "learning_rate": 1.455962475549926e-05, + "loss": 1.4284, + "step": 3951 + }, + { + "epoch": 0.41, + "learning_rate": 1.4556366831212647e-05, + "loss": 1.4279, + "step": 3952 + }, + { + "epoch": 0.41, + "learning_rate": 1.4553108296489951e-05, + "loss": 1.3072, + "step": 3953 + }, + { + "epoch": 0.41, + "learning_rate": 1.4549849151767731e-05, + "loss": 1.4175, + "step": 3954 + }, + { + "epoch": 0.41, + "learning_rate": 1.4546589397482632e-05, + "loss": 1.5042, + "step": 3955 + }, + { + "epoch": 0.41, + "learning_rate": 1.4543329034071371e-05, + "loss": 1.4363, + "step": 3956 + }, + { + "epoch": 0.41, + "learning_rate": 1.454006806197076e-05, + "loss": 1.4111, + "step": 3957 + }, + { + "epoch": 0.42, + "learning_rate": 1.453680648161768e-05, + "loss": 1.3817, + "step": 3958 + }, + { + "epoch": 0.42, + "learning_rate": 1.45335442934491e-05, + "loss": 1.4689, + "step": 3959 + }, + { + "epoch": 0.42, + "learning_rate": 1.4530281497902072e-05, + "loss": 1.4164, + "step": 3960 + }, + { + "epoch": 0.42, + "learning_rate": 1.4527018095413726e-05, + "loss": 1.3943, + "step": 3961 + }, + { + "epoch": 0.42, + "learning_rate": 1.4523754086421271e-05, + "loss": 1.3851, + "step": 3962 + }, + { + "epoch": 0.42, + "learning_rate": 1.4520489471362003e-05, + "loss": 1.3907, + "step": 3963 + }, + { + "epoch": 0.42, + "learning_rate": 1.4517224250673297e-05, + "loss": 1.2877, + "step": 3964 + }, + { + "epoch": 0.42, + "learning_rate": 1.4513958424792605e-05, + "loss": 1.4696, + "step": 3965 + }, + { + "epoch": 0.42, + "learning_rate": 1.4510691994157471e-05, + "loss": 1.3785, + "step": 3966 + }, + { + "epoch": 0.42, + "learning_rate": 1.4507424959205505e-05, + "loss": 1.3652, + "step": 3967 + }, + { + "epoch": 0.42, + "learning_rate": 1.4504157320374408e-05, + "loss": 1.4198, + "step": 3968 + }, + { + "epoch": 0.42, + "learning_rate": 1.4500889078101962e-05, + "loss": 1.3476, + "step": 3969 + }, + { + "epoch": 0.42, + "learning_rate": 1.4497620232826028e-05, + "loss": 1.4356, + "step": 3970 + }, + { + "epoch": 0.42, + "learning_rate": 1.4494350784984543e-05, + "loss": 1.4993, + "step": 3971 + }, + { + "epoch": 0.42, + "learning_rate": 1.4491080735015533e-05, + "loss": 1.4022, + "step": 3972 + }, + { + "epoch": 0.42, + "learning_rate": 1.44878100833571e-05, + "loss": 1.4074, + "step": 3973 + }, + { + "epoch": 0.42, + "learning_rate": 1.4484538830447423e-05, + "loss": 1.412, + "step": 3974 + }, + { + "epoch": 0.42, + "learning_rate": 1.4481266976724772e-05, + "loss": 1.3872, + "step": 3975 + }, + { + "epoch": 0.42, + "learning_rate": 1.4477994522627485e-05, + "loss": 1.4575, + "step": 3976 + }, + { + "epoch": 0.42, + "learning_rate": 1.4474721468593995e-05, + "loss": 1.3768, + "step": 3977 + }, + { + "epoch": 0.42, + "learning_rate": 1.44714478150628e-05, + "loss": 1.4173, + "step": 3978 + }, + { + "epoch": 0.42, + "learning_rate": 1.4468173562472489e-05, + "loss": 1.3896, + "step": 3979 + }, + { + "epoch": 0.42, + "learning_rate": 1.4464898711261725e-05, + "loss": 1.4535, + "step": 3980 + }, + { + "epoch": 0.42, + "eval_loss": 1.4580057859420776, + "eval_runtime": 77.4537, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 3980 + }, + { + "epoch": 0.42, + "learning_rate": 1.4461623261869258e-05, + "loss": 1.4046, + "step": 3981 + }, + { + "epoch": 0.42, + "learning_rate": 1.445834721473391e-05, + "loss": 1.37, + "step": 3982 + }, + { + "epoch": 0.42, + "learning_rate": 1.4455070570294588e-05, + "loss": 1.4566, + "step": 3983 + }, + { + "epoch": 0.42, + "learning_rate": 1.445179332899028e-05, + "loss": 1.4513, + "step": 3984 + }, + { + "epoch": 0.42, + "learning_rate": 1.4448515491260051e-05, + "loss": 1.3893, + "step": 3985 + }, + { + "epoch": 0.42, + "learning_rate": 1.4445237057543047e-05, + "loss": 1.3955, + "step": 3986 + }, + { + "epoch": 0.42, + "learning_rate": 1.4441958028278493e-05, + "loss": 1.4861, + "step": 3987 + }, + { + "epoch": 0.42, + "learning_rate": 1.4438678403905697e-05, + "loss": 1.4601, + "step": 3988 + }, + { + "epoch": 0.42, + "learning_rate": 1.4435398184864043e-05, + "loss": 1.398, + "step": 3989 + }, + { + "epoch": 0.42, + "learning_rate": 1.4432117371592995e-05, + "loss": 1.4392, + "step": 3990 + }, + { + "epoch": 0.42, + "learning_rate": 1.4428835964532098e-05, + "loss": 1.3772, + "step": 3991 + }, + { + "epoch": 0.42, + "learning_rate": 1.4425553964120979e-05, + "loss": 1.4241, + "step": 3992 + }, + { + "epoch": 0.42, + "learning_rate": 1.4422271370799338e-05, + "loss": 1.3237, + "step": 3993 + }, + { + "epoch": 0.42, + "learning_rate": 1.4418988185006964e-05, + "loss": 1.3813, + "step": 3994 + }, + { + "epoch": 0.42, + "learning_rate": 1.4415704407183709e-05, + "loss": 1.6139, + "step": 3995 + }, + { + "epoch": 0.42, + "learning_rate": 1.4412420037769525e-05, + "loss": 1.4431, + "step": 3996 + }, + { + "epoch": 0.42, + "learning_rate": 1.440913507720443e-05, + "loss": 1.3862, + "step": 3997 + }, + { + "epoch": 0.42, + "learning_rate": 1.4405849525928523e-05, + "loss": 1.3895, + "step": 3998 + }, + { + "epoch": 0.42, + "learning_rate": 1.4402563384381981e-05, + "loss": 1.4068, + "step": 3999 + }, + { + "epoch": 0.42, + "learning_rate": 1.4399276653005072e-05, + "loss": 1.4501, + "step": 4000 + }, + { + "epoch": 0.42, + "learning_rate": 1.4395989332238124e-05, + "loss": 1.3165, + "step": 4001 + }, + { + "epoch": 0.42, + "learning_rate": 1.4392701422521555e-05, + "loss": 1.3783, + "step": 4002 + }, + { + "epoch": 0.42, + "learning_rate": 1.4389412924295865e-05, + "loss": 1.343, + "step": 4003 + }, + { + "epoch": 0.42, + "learning_rate": 1.4386123838001625e-05, + "loss": 1.3456, + "step": 4004 + }, + { + "epoch": 0.42, + "learning_rate": 1.4382834164079486e-05, + "loss": 1.3689, + "step": 4005 + }, + { + "epoch": 0.42, + "learning_rate": 1.4379543902970183e-05, + "loss": 1.3789, + "step": 4006 + }, + { + "epoch": 0.42, + "learning_rate": 1.4376253055114528e-05, + "loss": 1.4912, + "step": 4007 + }, + { + "epoch": 0.42, + "learning_rate": 1.4372961620953407e-05, + "loss": 1.3692, + "step": 4008 + }, + { + "epoch": 0.42, + "learning_rate": 1.436966960092779e-05, + "loss": 1.4901, + "step": 4009 + }, + { + "epoch": 0.42, + "learning_rate": 1.4366376995478717e-05, + "loss": 1.4431, + "step": 4010 + }, + { + "epoch": 0.42, + "learning_rate": 1.436308380504732e-05, + "loss": 1.4626, + "step": 4011 + }, + { + "epoch": 0.42, + "learning_rate": 1.4359790030074798e-05, + "loss": 1.4241, + "step": 4012 + }, + { + "epoch": 0.42, + "learning_rate": 1.4356495671002435e-05, + "loss": 1.3834, + "step": 4013 + }, + { + "epoch": 0.42, + "learning_rate": 1.4353200728271586e-05, + "loss": 1.3626, + "step": 4014 + }, + { + "epoch": 0.42, + "learning_rate": 1.4349905202323692e-05, + "loss": 1.3557, + "step": 4015 + }, + { + "epoch": 0.42, + "learning_rate": 1.434660909360027e-05, + "loss": 1.4077, + "step": 4016 + }, + { + "epoch": 0.42, + "learning_rate": 1.4343312402542911e-05, + "loss": 1.4337, + "step": 4017 + }, + { + "epoch": 0.42, + "learning_rate": 1.4340015129593286e-05, + "loss": 1.419, + "step": 4018 + }, + { + "epoch": 0.42, + "learning_rate": 1.4336717275193148e-05, + "loss": 1.3768, + "step": 4019 + }, + { + "epoch": 0.42, + "learning_rate": 1.4333418839784326e-05, + "loss": 1.383, + "step": 4020 + }, + { + "epoch": 0.42, + "learning_rate": 1.4330119823808719e-05, + "loss": 1.3951, + "step": 4021 + }, + { + "epoch": 0.42, + "learning_rate": 1.4326820227708316e-05, + "loss": 1.3985, + "step": 4022 + }, + { + "epoch": 0.42, + "learning_rate": 1.4323520051925177e-05, + "loss": 1.356, + "step": 4023 + }, + { + "epoch": 0.42, + "learning_rate": 1.4320219296901439e-05, + "loss": 1.5017, + "step": 4024 + }, + { + "epoch": 0.42, + "learning_rate": 1.4316917963079322e-05, + "loss": 1.3594, + "step": 4025 + }, + { + "epoch": 0.42, + "learning_rate": 1.4313616050901114e-05, + "loss": 1.6028, + "step": 4026 + }, + { + "epoch": 0.42, + "learning_rate": 1.4310313560809193e-05, + "loss": 1.4132, + "step": 4027 + }, + { + "epoch": 0.42, + "learning_rate": 1.4307010493246006e-05, + "loss": 1.2969, + "step": 4028 + }, + { + "epoch": 0.42, + "learning_rate": 1.4303706848654073e-05, + "loss": 1.5224, + "step": 4029 + }, + { + "epoch": 0.42, + "learning_rate": 1.4300402627476007e-05, + "loss": 1.3386, + "step": 4030 + }, + { + "epoch": 0.42, + "learning_rate": 1.429709783015448e-05, + "loss": 1.3554, + "step": 4031 + }, + { + "epoch": 0.42, + "learning_rate": 1.4293792457132259e-05, + "loss": 1.3386, + "step": 4032 + }, + { + "epoch": 0.42, + "learning_rate": 1.429048650885217e-05, + "loss": 1.4613, + "step": 4033 + }, + { + "epoch": 0.42, + "learning_rate": 1.4287179985757132e-05, + "loss": 1.3632, + "step": 4034 + }, + { + "epoch": 0.42, + "learning_rate": 1.428387288829013e-05, + "loss": 1.3835, + "step": 4035 + }, + { + "epoch": 0.42, + "learning_rate": 1.4280565216894234e-05, + "loss": 1.3711, + "step": 4036 + }, + { + "epoch": 0.42, + "learning_rate": 1.4277256972012582e-05, + "loss": 1.3385, + "step": 4037 + }, + { + "epoch": 0.42, + "learning_rate": 1.4273948154088395e-05, + "loss": 1.4607, + "step": 4038 + }, + { + "epoch": 0.42, + "learning_rate": 1.4270638763564973e-05, + "loss": 1.4042, + "step": 4039 + }, + { + "epoch": 0.42, + "learning_rate": 1.4267328800885687e-05, + "loss": 1.4006, + "step": 4040 + }, + { + "epoch": 0.42, + "learning_rate": 1.4264018266493987e-05, + "loss": 1.386, + "step": 4041 + }, + { + "epoch": 0.42, + "learning_rate": 1.4260707160833401e-05, + "loss": 1.3487, + "step": 4042 + }, + { + "epoch": 0.42, + "learning_rate": 1.4257395484347529e-05, + "loss": 1.4199, + "step": 4043 + }, + { + "epoch": 0.42, + "learning_rate": 1.4254083237480054e-05, + "loss": 1.3236, + "step": 4044 + }, + { + "epoch": 0.42, + "learning_rate": 1.4250770420674726e-05, + "loss": 1.4056, + "step": 4045 + }, + { + "epoch": 0.42, + "learning_rate": 1.4247457034375387e-05, + "loss": 1.4391, + "step": 4046 + }, + { + "epoch": 0.42, + "learning_rate": 1.4244143079025938e-05, + "loss": 1.3935, + "step": 4047 + }, + { + "epoch": 0.42, + "learning_rate": 1.4240828555070368e-05, + "loss": 1.3623, + "step": 4048 + }, + { + "epoch": 0.42, + "learning_rate": 1.4237513462952733e-05, + "loss": 1.3254, + "step": 4049 + }, + { + "epoch": 0.42, + "learning_rate": 1.4234197803117174e-05, + "loss": 1.4217, + "step": 4050 + }, + { + "epoch": 0.42, + "learning_rate": 1.4230881576007904e-05, + "loss": 1.435, + "step": 4051 + }, + { + "epoch": 0.42, + "learning_rate": 1.422756478206921e-05, + "loss": 1.3687, + "step": 4052 + }, + { + "epoch": 0.43, + "learning_rate": 1.4224247421745464e-05, + "loss": 1.3965, + "step": 4053 + }, + { + "epoch": 0.43, + "learning_rate": 1.4220929495481097e-05, + "loss": 1.4159, + "step": 4054 + }, + { + "epoch": 0.43, + "learning_rate": 1.4217611003720632e-05, + "loss": 1.3632, + "step": 4055 + }, + { + "epoch": 0.43, + "learning_rate": 1.4214291946908661e-05, + "loss": 1.403, + "step": 4056 + }, + { + "epoch": 0.43, + "learning_rate": 1.4210972325489854e-05, + "loss": 1.4093, + "step": 4057 + }, + { + "epoch": 0.43, + "learning_rate": 1.4207652139908952e-05, + "loss": 1.4551, + "step": 4058 + }, + { + "epoch": 0.43, + "learning_rate": 1.4204331390610775e-05, + "loss": 1.4162, + "step": 4059 + }, + { + "epoch": 0.43, + "learning_rate": 1.4201010078040216e-05, + "loss": 1.4492, + "step": 4060 + }, + { + "epoch": 0.43, + "learning_rate": 1.419768820264225e-05, + "loss": 1.4449, + "step": 4061 + }, + { + "epoch": 0.43, + "learning_rate": 1.4194365764861922e-05, + "loss": 1.3382, + "step": 4062 + }, + { + "epoch": 0.43, + "learning_rate": 1.419104276514435e-05, + "loss": 1.3899, + "step": 4063 + }, + { + "epoch": 0.43, + "learning_rate": 1.4187719203934734e-05, + "loss": 1.3513, + "step": 4064 + }, + { + "epoch": 0.43, + "learning_rate": 1.4184395081678344e-05, + "loss": 1.3954, + "step": 4065 + }, + { + "epoch": 0.43, + "learning_rate": 1.4181070398820528e-05, + "loss": 1.442, + "step": 4066 + }, + { + "epoch": 0.43, + "learning_rate": 1.4177745155806708e-05, + "loss": 1.3907, + "step": 4067 + }, + { + "epoch": 0.43, + "learning_rate": 1.417441935308238e-05, + "loss": 1.3757, + "step": 4068 + }, + { + "epoch": 0.43, + "learning_rate": 1.4171092991093118e-05, + "loss": 1.3507, + "step": 4069 + }, + { + "epoch": 0.43, + "learning_rate": 1.4167766070284568e-05, + "loss": 1.4136, + "step": 4070 + }, + { + "epoch": 0.43, + "learning_rate": 1.4164438591102452e-05, + "loss": 1.3835, + "step": 4071 + }, + { + "epoch": 0.43, + "learning_rate": 1.4161110553992565e-05, + "loss": 1.4981, + "step": 4072 + }, + { + "epoch": 0.43, + "learning_rate": 1.415778195940078e-05, + "loss": 1.4387, + "step": 4073 + }, + { + "epoch": 0.43, + "learning_rate": 1.4154452807773047e-05, + "loss": 1.333, + "step": 4074 + }, + { + "epoch": 0.43, + "learning_rate": 1.4151123099555377e-05, + "loss": 1.3558, + "step": 4075 + }, + { + "epoch": 0.43, + "learning_rate": 1.4147792835193875e-05, + "loss": 1.4655, + "step": 4076 + }, + { + "epoch": 0.43, + "learning_rate": 1.4144462015134708e-05, + "loss": 1.4402, + "step": 4077 + }, + { + "epoch": 0.43, + "learning_rate": 1.4141130639824119e-05, + "loss": 1.4227, + "step": 4078 + }, + { + "epoch": 0.43, + "learning_rate": 1.4137798709708423e-05, + "loss": 1.4039, + "step": 4079 + }, + { + "epoch": 0.43, + "learning_rate": 1.4134466225234023e-05, + "loss": 1.3593, + "step": 4080 + }, + { + "epoch": 0.43, + "learning_rate": 1.4131133186847377e-05, + "loss": 1.372, + "step": 4081 + }, + { + "epoch": 0.43, + "learning_rate": 1.412779959499503e-05, + "loss": 1.4487, + "step": 4082 + }, + { + "epoch": 0.43, + "learning_rate": 1.4124465450123599e-05, + "loss": 1.3972, + "step": 4083 + }, + { + "epoch": 0.43, + "learning_rate": 1.4121130752679772e-05, + "loss": 1.3768, + "step": 4084 + }, + { + "epoch": 0.43, + "learning_rate": 1.4117795503110313e-05, + "loss": 1.3827, + "step": 4085 + }, + { + "epoch": 0.43, + "learning_rate": 1.4114459701862062e-05, + "loss": 1.3922, + "step": 4086 + }, + { + "epoch": 0.43, + "learning_rate": 1.4111123349381925e-05, + "loss": 1.3736, + "step": 4087 + }, + { + "epoch": 0.43, + "learning_rate": 1.4107786446116894e-05, + "loss": 1.4338, + "step": 4088 + }, + { + "epoch": 0.43, + "learning_rate": 1.4104448992514023e-05, + "loss": 1.347, + "step": 4089 + }, + { + "epoch": 0.43, + "learning_rate": 1.410111098902045e-05, + "loss": 1.3915, + "step": 4090 + }, + { + "epoch": 0.43, + "learning_rate": 1.4097772436083377e-05, + "loss": 1.3656, + "step": 4091 + }, + { + "epoch": 0.43, + "learning_rate": 1.4094433334150087e-05, + "loss": 1.3461, + "step": 4092 + }, + { + "epoch": 0.43, + "learning_rate": 1.4091093683667934e-05, + "loss": 1.7345, + "step": 4093 + }, + { + "epoch": 0.43, + "learning_rate": 1.4087753485084343e-05, + "loss": 1.6204, + "step": 4094 + }, + { + "epoch": 0.43, + "learning_rate": 1.4084412738846816e-05, + "loss": 1.4074, + "step": 4095 + }, + { + "epoch": 0.43, + "learning_rate": 1.408107144540293e-05, + "loss": 1.3776, + "step": 4096 + }, + { + "epoch": 0.43, + "learning_rate": 1.407772960520033e-05, + "loss": 1.4079, + "step": 4097 + }, + { + "epoch": 0.43, + "learning_rate": 1.4074387218686734e-05, + "loss": 1.4254, + "step": 4098 + }, + { + "epoch": 0.43, + "learning_rate": 1.407104428630994e-05, + "loss": 1.38, + "step": 4099 + }, + { + "epoch": 0.43, + "learning_rate": 1.4067700808517815e-05, + "loss": 1.4175, + "step": 4100 + }, + { + "epoch": 0.43, + "learning_rate": 1.4064356785758298e-05, + "loss": 1.4085, + "step": 4101 + }, + { + "epoch": 0.43, + "learning_rate": 1.4061012218479397e-05, + "loss": 1.4529, + "step": 4102 + }, + { + "epoch": 0.43, + "learning_rate": 1.405766710712921e-05, + "loss": 1.4836, + "step": 4103 + }, + { + "epoch": 0.43, + "learning_rate": 1.4054321452155885e-05, + "loss": 1.3915, + "step": 4104 + }, + { + "epoch": 0.43, + "learning_rate": 1.4050975254007659e-05, + "loss": 1.3044, + "step": 4105 + }, + { + "epoch": 0.43, + "learning_rate": 1.4047628513132835e-05, + "loss": 1.373, + "step": 4106 + }, + { + "epoch": 0.43, + "learning_rate": 1.4044281229979793e-05, + "loss": 1.4266, + "step": 4107 + }, + { + "epoch": 0.43, + "learning_rate": 1.4040933404996977e-05, + "loss": 1.3898, + "step": 4108 + }, + { + "epoch": 0.43, + "learning_rate": 1.4037585038632915e-05, + "loss": 0.9326, + "step": 4109 + }, + { + "epoch": 0.43, + "learning_rate": 1.40342361313362e-05, + "loss": 1.0831, + "step": 4110 + }, + { + "epoch": 0.43, + "learning_rate": 1.40308866835555e-05, + "loss": 1.3898, + "step": 4111 + }, + { + "epoch": 0.43, + "learning_rate": 1.4027536695739554e-05, + "loss": 1.5058, + "step": 4112 + }, + { + "epoch": 0.43, + "learning_rate": 1.4024186168337175e-05, + "loss": 1.3635, + "step": 4113 + }, + { + "epoch": 0.43, + "learning_rate": 1.4020835101797248e-05, + "loss": 1.3871, + "step": 4114 + }, + { + "epoch": 0.43, + "learning_rate": 1.401748349656873e-05, + "loss": 1.3478, + "step": 4115 + }, + { + "epoch": 0.43, + "learning_rate": 1.4014131353100648e-05, + "loss": 1.3356, + "step": 4116 + }, + { + "epoch": 0.43, + "learning_rate": 1.4010778671842107e-05, + "loss": 1.3954, + "step": 4117 + }, + { + "epoch": 0.43, + "learning_rate": 1.4007425453242274e-05, + "loss": 1.3307, + "step": 4118 + }, + { + "epoch": 0.43, + "learning_rate": 1.4004071697750398e-05, + "loss": 1.4508, + "step": 4119 + }, + { + "epoch": 0.43, + "learning_rate": 1.4000717405815799e-05, + "loss": 1.3752, + "step": 4120 + }, + { + "epoch": 0.43, + "learning_rate": 1.399736257788786e-05, + "loss": 1.3654, + "step": 4121 + }, + { + "epoch": 0.43, + "learning_rate": 1.3994007214416046e-05, + "loss": 1.4505, + "step": 4122 + }, + { + "epoch": 0.43, + "learning_rate": 1.3990651315849886e-05, + "loss": 1.4307, + "step": 4123 + }, + { + "epoch": 0.43, + "learning_rate": 1.398729488263899e-05, + "loss": 1.4481, + "step": 4124 + }, + { + "epoch": 0.43, + "learning_rate": 1.3983937915233026e-05, + "loss": 1.4755, + "step": 4125 + }, + { + "epoch": 0.43, + "learning_rate": 1.3980580414081746e-05, + "loss": 1.3402, + "step": 4126 + }, + { + "epoch": 0.43, + "learning_rate": 1.3977222379634969e-05, + "loss": 1.3636, + "step": 4127 + }, + { + "epoch": 0.43, + "learning_rate": 1.3973863812342585e-05, + "loss": 1.4165, + "step": 4128 + }, + { + "epoch": 0.43, + "learning_rate": 1.3970504712654554e-05, + "loss": 1.3832, + "step": 4129 + }, + { + "epoch": 0.43, + "learning_rate": 1.3967145081020912e-05, + "loss": 1.4236, + "step": 4130 + }, + { + "epoch": 0.43, + "learning_rate": 1.396378491789176e-05, + "loss": 1.5022, + "step": 4131 + }, + { + "epoch": 0.43, + "learning_rate": 1.3960424223717276e-05, + "loss": 1.3806, + "step": 4132 + }, + { + "epoch": 0.43, + "learning_rate": 1.3957062998947707e-05, + "loss": 1.3649, + "step": 4133 + }, + { + "epoch": 0.43, + "learning_rate": 1.3953701244033368e-05, + "loss": 1.3787, + "step": 4134 + }, + { + "epoch": 0.43, + "learning_rate": 1.395033895942465e-05, + "loss": 1.3551, + "step": 4135 + }, + { + "epoch": 0.43, + "learning_rate": 1.394697614557201e-05, + "loss": 1.3881, + "step": 4136 + }, + { + "epoch": 0.43, + "learning_rate": 1.3943612802925983e-05, + "loss": 1.4848, + "step": 4137 + }, + { + "epoch": 0.43, + "learning_rate": 1.3940248931937169e-05, + "loss": 1.425, + "step": 4138 + }, + { + "epoch": 0.43, + "learning_rate": 1.3936884533056238e-05, + "loss": 1.4054, + "step": 4139 + }, + { + "epoch": 0.43, + "learning_rate": 1.3933519606733934e-05, + "loss": 1.4028, + "step": 4140 + }, + { + "epoch": 0.43, + "learning_rate": 1.3930154153421072e-05, + "loss": 1.4439, + "step": 4141 + }, + { + "epoch": 0.43, + "learning_rate": 1.3926788173568536e-05, + "loss": 1.4482, + "step": 4142 + }, + { + "epoch": 0.43, + "learning_rate": 1.392342166762728e-05, + "loss": 1.393, + "step": 4143 + }, + { + "epoch": 0.43, + "learning_rate": 1.3920054636048328e-05, + "loss": 1.4097, + "step": 4144 + }, + { + "epoch": 0.43, + "learning_rate": 1.391668707928278e-05, + "loss": 1.5142, + "step": 4145 + }, + { + "epoch": 0.43, + "learning_rate": 1.3913318997781797e-05, + "loss": 1.4118, + "step": 4146 + }, + { + "epoch": 0.43, + "learning_rate": 1.390995039199662e-05, + "loss": 1.4067, + "step": 4147 + }, + { + "epoch": 0.43, + "learning_rate": 1.3906581262378552e-05, + "loss": 1.5214, + "step": 4148 + }, + { + "epoch": 0.44, + "learning_rate": 1.3903211609378971e-05, + "loss": 1.3618, + "step": 4149 + }, + { + "epoch": 0.44, + "learning_rate": 1.3899841433449327e-05, + "loss": 1.338, + "step": 4150 + }, + { + "epoch": 0.44, + "learning_rate": 1.3896470735041132e-05, + "loss": 1.3901, + "step": 4151 + }, + { + "epoch": 0.44, + "learning_rate": 1.3893099514605971e-05, + "loss": 1.4502, + "step": 4152 + }, + { + "epoch": 0.44, + "learning_rate": 1.388972777259551e-05, + "loss": 1.4141, + "step": 4153 + }, + { + "epoch": 0.44, + "learning_rate": 1.3886355509461471e-05, + "loss": 1.3876, + "step": 4154 + }, + { + "epoch": 0.44, + "learning_rate": 1.388298272565565e-05, + "loss": 1.4275, + "step": 4155 + }, + { + "epoch": 0.44, + "learning_rate": 1.3879609421629909e-05, + "loss": 1.3559, + "step": 4156 + }, + { + "epoch": 0.44, + "learning_rate": 1.3876235597836195e-05, + "loss": 1.416, + "step": 4157 + }, + { + "epoch": 0.44, + "learning_rate": 1.3872861254726506e-05, + "loss": 1.437, + "step": 4158 + }, + { + "epoch": 0.44, + "learning_rate": 1.3869486392752918e-05, + "loss": 1.3794, + "step": 4159 + }, + { + "epoch": 0.44, + "learning_rate": 1.3866111012367577e-05, + "loss": 1.4094, + "step": 4160 + }, + { + "epoch": 0.44, + "learning_rate": 1.3862735114022694e-05, + "loss": 1.3957, + "step": 4161 + }, + { + "epoch": 0.44, + "learning_rate": 1.3859358698170559e-05, + "loss": 1.3582, + "step": 4162 + }, + { + "epoch": 0.44, + "learning_rate": 1.3855981765263523e-05, + "loss": 1.4159, + "step": 4163 + }, + { + "epoch": 0.44, + "learning_rate": 1.3852604315754e-05, + "loss": 1.3498, + "step": 4164 + }, + { + "epoch": 0.44, + "learning_rate": 1.3849226350094491e-05, + "loss": 1.3951, + "step": 4165 + }, + { + "epoch": 0.44, + "learning_rate": 1.3845847868737559e-05, + "loss": 1.4087, + "step": 4166 + }, + { + "epoch": 0.44, + "learning_rate": 1.3842468872135821e-05, + "loss": 1.4318, + "step": 4167 + }, + { + "epoch": 0.44, + "learning_rate": 1.3839089360741989e-05, + "loss": 1.4174, + "step": 4168 + }, + { + "epoch": 0.44, + "learning_rate": 1.3835709335008822e-05, + "loss": 1.4499, + "step": 4169 + }, + { + "epoch": 0.44, + "learning_rate": 1.383232879538916e-05, + "loss": 1.3554, + "step": 4170 + }, + { + "epoch": 0.44, + "learning_rate": 1.3828947742335905e-05, + "loss": 1.3873, + "step": 4171 + }, + { + "epoch": 0.44, + "learning_rate": 1.382556617630204e-05, + "loss": 1.3804, + "step": 4172 + }, + { + "epoch": 0.44, + "learning_rate": 1.3822184097740598e-05, + "loss": 1.3856, + "step": 4173 + }, + { + "epoch": 0.44, + "learning_rate": 1.3818801507104697e-05, + "loss": 1.3901, + "step": 4174 + }, + { + "epoch": 0.44, + "learning_rate": 1.381541840484751e-05, + "loss": 1.3714, + "step": 4175 + }, + { + "epoch": 0.44, + "learning_rate": 1.3812034791422297e-05, + "loss": 1.4945, + "step": 4176 + }, + { + "epoch": 0.44, + "learning_rate": 1.3808650667282368e-05, + "loss": 1.429, + "step": 4177 + }, + { + "epoch": 0.44, + "learning_rate": 1.3805266032881108e-05, + "loss": 1.3903, + "step": 4178 + }, + { + "epoch": 0.44, + "learning_rate": 1.3801880888671972e-05, + "loss": 1.4799, + "step": 4179 + }, + { + "epoch": 0.44, + "eval_loss": 1.4521424770355225, + "eval_runtime": 77.3596, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 4179 + }, + { + "epoch": 0.44, + "learning_rate": 1.3798495235108484e-05, + "loss": 1.3912, + "step": 4180 + }, + { + "epoch": 0.44, + "learning_rate": 1.3795109072644235e-05, + "loss": 1.5837, + "step": 4181 + }, + { + "epoch": 0.44, + "learning_rate": 1.379172240173288e-05, + "loss": 1.4255, + "step": 4182 + }, + { + "epoch": 0.44, + "learning_rate": 1.3788335222828148e-05, + "loss": 1.4666, + "step": 4183 + }, + { + "epoch": 0.44, + "learning_rate": 1.3784947536383837e-05, + "loss": 1.3964, + "step": 4184 + }, + { + "epoch": 0.44, + "learning_rate": 1.3781559342853807e-05, + "loss": 1.336, + "step": 4185 + }, + { + "epoch": 0.44, + "learning_rate": 1.3778170642691986e-05, + "loss": 1.4352, + "step": 4186 + }, + { + "epoch": 0.44, + "learning_rate": 1.377478143635238e-05, + "loss": 1.3262, + "step": 4187 + }, + { + "epoch": 0.44, + "learning_rate": 1.3771391724289047e-05, + "loss": 1.3969, + "step": 4188 + }, + { + "epoch": 0.44, + "learning_rate": 1.376800150695613e-05, + "loss": 1.4211, + "step": 4189 + }, + { + "epoch": 0.44, + "learning_rate": 1.3764610784807824e-05, + "loss": 1.4338, + "step": 4190 + }, + { + "epoch": 0.44, + "learning_rate": 1.3761219558298403e-05, + "loss": 1.3815, + "step": 4191 + }, + { + "epoch": 0.44, + "learning_rate": 1.3757827827882203e-05, + "loss": 1.3805, + "step": 4192 + }, + { + "epoch": 0.44, + "learning_rate": 1.3754435594013627e-05, + "loss": 1.4071, + "step": 4193 + }, + { + "epoch": 0.44, + "learning_rate": 1.3751042857147145e-05, + "loss": 1.343, + "step": 4194 + }, + { + "epoch": 0.44, + "learning_rate": 1.3747649617737304e-05, + "loss": 1.4129, + "step": 4195 + }, + { + "epoch": 0.44, + "learning_rate": 1.3744255876238708e-05, + "loss": 1.3939, + "step": 4196 + }, + { + "epoch": 0.44, + "learning_rate": 1.3740861633106029e-05, + "loss": 1.3963, + "step": 4197 + }, + { + "epoch": 0.44, + "learning_rate": 1.3737466888794008e-05, + "loss": 1.5181, + "step": 4198 + }, + { + "epoch": 0.44, + "learning_rate": 1.3734071643757456e-05, + "loss": 1.4397, + "step": 4199 + }, + { + "epoch": 0.44, + "learning_rate": 1.373067589845125e-05, + "loss": 1.6293, + "step": 4200 + }, + { + "epoch": 0.44, + "learning_rate": 1.3727279653330328e-05, + "loss": 1.3498, + "step": 4201 + }, + { + "epoch": 0.44, + "learning_rate": 1.37238829088497e-05, + "loss": 1.4509, + "step": 4202 + }, + { + "epoch": 0.44, + "learning_rate": 1.3720485665464446e-05, + "loss": 1.4477, + "step": 4203 + }, + { + "epoch": 0.44, + "learning_rate": 1.3717087923629709e-05, + "loss": 1.4399, + "step": 4204 + }, + { + "epoch": 0.44, + "learning_rate": 1.3713689683800695e-05, + "loss": 1.4417, + "step": 4205 + }, + { + "epoch": 0.44, + "learning_rate": 1.3710290946432685e-05, + "loss": 1.3957, + "step": 4206 + }, + { + "epoch": 0.44, + "learning_rate": 1.3706891711981021e-05, + "loss": 1.4476, + "step": 4207 + }, + { + "epoch": 0.44, + "learning_rate": 1.3703491980901113e-05, + "loss": 1.3894, + "step": 4208 + }, + { + "epoch": 0.44, + "learning_rate": 1.3700091753648437e-05, + "loss": 1.4745, + "step": 4209 + }, + { + "epoch": 0.44, + "learning_rate": 1.369669103067854e-05, + "loss": 1.4038, + "step": 4210 + }, + { + "epoch": 0.44, + "learning_rate": 1.3693289812447023e-05, + "loss": 1.4151, + "step": 4211 + }, + { + "epoch": 0.44, + "learning_rate": 1.3689888099409572e-05, + "loss": 1.4214, + "step": 4212 + }, + { + "epoch": 0.44, + "learning_rate": 1.368648589202192e-05, + "loss": 1.4287, + "step": 4213 + }, + { + "epoch": 0.44, + "learning_rate": 1.3683083190739883e-05, + "loss": 1.345, + "step": 4214 + }, + { + "epoch": 0.44, + "learning_rate": 1.367967999601933e-05, + "loss": 1.3022, + "step": 4215 + }, + { + "epoch": 0.44, + "learning_rate": 1.3676276308316207e-05, + "loss": 1.3971, + "step": 4216 + }, + { + "epoch": 0.44, + "learning_rate": 1.3672872128086514e-05, + "loss": 1.3335, + "step": 4217 + }, + { + "epoch": 0.44, + "learning_rate": 1.366946745578633e-05, + "loss": 1.3988, + "step": 4218 + }, + { + "epoch": 0.44, + "learning_rate": 1.366606229187179e-05, + "loss": 1.4508, + "step": 4219 + }, + { + "epoch": 0.44, + "learning_rate": 1.3662656636799099e-05, + "loss": 1.3814, + "step": 4220 + }, + { + "epoch": 0.44, + "learning_rate": 1.3659250491024527e-05, + "loss": 1.4128, + "step": 4221 + }, + { + "epoch": 0.44, + "learning_rate": 1.3655843855004411e-05, + "loss": 1.3893, + "step": 4222 + }, + { + "epoch": 0.44, + "learning_rate": 1.3652436729195154e-05, + "loss": 1.2551, + "step": 4223 + }, + { + "epoch": 0.44, + "learning_rate": 1.3649029114053219e-05, + "loss": 1.4386, + "step": 4224 + }, + { + "epoch": 0.44, + "learning_rate": 1.364562101003514e-05, + "loss": 1.4028, + "step": 4225 + }, + { + "epoch": 0.44, + "learning_rate": 1.364221241759752e-05, + "loss": 1.4351, + "step": 4226 + }, + { + "epoch": 0.44, + "learning_rate": 1.363880333719702e-05, + "loss": 1.3941, + "step": 4227 + }, + { + "epoch": 0.44, + "learning_rate": 1.3635393769290368e-05, + "loss": 1.3879, + "step": 4228 + }, + { + "epoch": 0.44, + "learning_rate": 1.3631983714334358e-05, + "loss": 1.3773, + "step": 4229 + }, + { + "epoch": 0.44, + "learning_rate": 1.3628573172785853e-05, + "loss": 1.3679, + "step": 4230 + }, + { + "epoch": 0.44, + "learning_rate": 1.3625162145101776e-05, + "loss": 1.3705, + "step": 4231 + }, + { + "epoch": 0.44, + "learning_rate": 1.3621750631739114e-05, + "loss": 1.8157, + "step": 4232 + }, + { + "epoch": 0.44, + "learning_rate": 1.3618338633154928e-05, + "loss": 1.4056, + "step": 4233 + }, + { + "epoch": 0.44, + "learning_rate": 1.3614926149806334e-05, + "loss": 1.3716, + "step": 4234 + }, + { + "epoch": 0.44, + "learning_rate": 1.3611513182150523e-05, + "loss": 1.3766, + "step": 4235 + }, + { + "epoch": 0.44, + "learning_rate": 1.3608099730644733e-05, + "loss": 1.41, + "step": 4236 + }, + { + "epoch": 0.44, + "learning_rate": 1.3604685795746291e-05, + "loss": 1.421, + "step": 4237 + }, + { + "epoch": 0.44, + "learning_rate": 1.360127137791257e-05, + "loss": 1.3679, + "step": 4238 + }, + { + "epoch": 0.44, + "learning_rate": 1.3597856477601018e-05, + "loss": 1.4615, + "step": 4239 + }, + { + "epoch": 0.44, + "learning_rate": 1.359444109526914e-05, + "loss": 1.3418, + "step": 4240 + }, + { + "epoch": 0.44, + "learning_rate": 1.3591025231374513e-05, + "loss": 1.3631, + "step": 4241 + }, + { + "epoch": 0.44, + "learning_rate": 1.3587608886374772e-05, + "loss": 1.3802, + "step": 4242 + }, + { + "epoch": 0.44, + "learning_rate": 1.3584192060727622e-05, + "loss": 1.4156, + "step": 4243 + }, + { + "epoch": 0.45, + "learning_rate": 1.3580774754890827e-05, + "loss": 1.4161, + "step": 4244 + }, + { + "epoch": 0.45, + "learning_rate": 1.3577356969322222e-05, + "loss": 1.3535, + "step": 4245 + }, + { + "epoch": 0.45, + "learning_rate": 1.3573938704479699e-05, + "loss": 1.3859, + "step": 4246 + }, + { + "epoch": 0.45, + "learning_rate": 1.357051996082122e-05, + "loss": 1.3595, + "step": 4247 + }, + { + "epoch": 0.45, + "learning_rate": 1.3567100738804806e-05, + "loss": 1.4191, + "step": 4248 + }, + { + "epoch": 0.45, + "learning_rate": 1.3563681038888548e-05, + "loss": 1.4186, + "step": 4249 + }, + { + "epoch": 0.45, + "learning_rate": 1.3560260861530596e-05, + "loss": 1.43, + "step": 4250 + }, + { + "epoch": 0.45, + "learning_rate": 1.3556840207189168e-05, + "loss": 1.4139, + "step": 4251 + }, + { + "epoch": 0.45, + "learning_rate": 1.3553419076322539e-05, + "loss": 1.4005, + "step": 4252 + }, + { + "epoch": 0.45, + "learning_rate": 1.3549997469389058e-05, + "loss": 1.3468, + "step": 4253 + }, + { + "epoch": 0.45, + "learning_rate": 1.3546575386847132e-05, + "loss": 1.3756, + "step": 4254 + }, + { + "epoch": 0.45, + "learning_rate": 1.3543152829155226e-05, + "loss": 1.4063, + "step": 4255 + }, + { + "epoch": 0.45, + "learning_rate": 1.3539729796771884e-05, + "loss": 1.4666, + "step": 4256 + }, + { + "epoch": 0.45, + "learning_rate": 1.3536306290155694e-05, + "loss": 1.4212, + "step": 4257 + }, + { + "epoch": 0.45, + "learning_rate": 1.3532882309765332e-05, + "loss": 1.4883, + "step": 4258 + }, + { + "epoch": 0.45, + "learning_rate": 1.3529457856059507e-05, + "loss": 1.6641, + "step": 4259 + }, + { + "epoch": 0.45, + "learning_rate": 1.3526032929497022e-05, + "loss": 1.3659, + "step": 4260 + }, + { + "epoch": 0.45, + "learning_rate": 1.3522607530536717e-05, + "loss": 1.5945, + "step": 4261 + }, + { + "epoch": 0.45, + "learning_rate": 1.351918165963752e-05, + "loss": 1.3643, + "step": 4262 + }, + { + "epoch": 0.45, + "learning_rate": 1.3515755317258397e-05, + "loss": 1.3442, + "step": 4263 + }, + { + "epoch": 0.45, + "learning_rate": 1.3512328503858398e-05, + "loss": 1.3982, + "step": 4264 + }, + { + "epoch": 0.45, + "learning_rate": 1.3508901219896624e-05, + "loss": 1.4985, + "step": 4265 + }, + { + "epoch": 0.45, + "learning_rate": 1.350547346583225e-05, + "loss": 1.3319, + "step": 4266 + }, + { + "epoch": 0.45, + "learning_rate": 1.3502045242124497e-05, + "loss": 1.3961, + "step": 4267 + }, + { + "epoch": 0.45, + "learning_rate": 1.3498616549232665e-05, + "loss": 1.4565, + "step": 4268 + }, + { + "epoch": 0.45, + "learning_rate": 1.349518738761611e-05, + "loss": 1.375, + "step": 4269 + }, + { + "epoch": 0.45, + "learning_rate": 1.3491757757734254e-05, + "loss": 1.3005, + "step": 4270 + }, + { + "epoch": 0.45, + "learning_rate": 1.348832766004657e-05, + "loss": 1.3185, + "step": 4271 + }, + { + "epoch": 0.45, + "learning_rate": 1.3484897095012613e-05, + "loss": 1.4449, + "step": 4272 + }, + { + "epoch": 0.45, + "learning_rate": 1.3481466063091988e-05, + "loss": 1.3587, + "step": 4273 + }, + { + "epoch": 0.45, + "learning_rate": 1.3478034564744362e-05, + "loss": 1.3844, + "step": 4274 + }, + { + "epoch": 0.45, + "learning_rate": 1.3474602600429468e-05, + "loss": 1.4471, + "step": 4275 + }, + { + "epoch": 0.45, + "learning_rate": 1.3471170170607105e-05, + "loss": 1.4686, + "step": 4276 + }, + { + "epoch": 0.45, + "learning_rate": 1.3467737275737127e-05, + "loss": 1.312, + "step": 4277 + }, + { + "epoch": 0.45, + "learning_rate": 1.3464303916279453e-05, + "loss": 1.407, + "step": 4278 + }, + { + "epoch": 0.45, + "learning_rate": 1.346087009269407e-05, + "loss": 1.364, + "step": 4279 + }, + { + "epoch": 0.45, + "learning_rate": 1.3457435805441016e-05, + "loss": 1.4103, + "step": 4280 + }, + { + "epoch": 0.45, + "learning_rate": 1.3454001054980403e-05, + "loss": 1.4243, + "step": 4281 + }, + { + "epoch": 0.45, + "learning_rate": 1.3450565841772392e-05, + "loss": 1.3879, + "step": 4282 + }, + { + "epoch": 0.45, + "learning_rate": 1.344713016627722e-05, + "loss": 1.4688, + "step": 4283 + }, + { + "epoch": 0.45, + "learning_rate": 1.3443694028955176e-05, + "loss": 1.3983, + "step": 4284 + }, + { + "epoch": 0.45, + "learning_rate": 1.344025743026662e-05, + "loss": 1.4316, + "step": 4285 + }, + { + "epoch": 0.45, + "learning_rate": 1.3436820370671956e-05, + "loss": 1.3643, + "step": 4286 + }, + { + "epoch": 0.45, + "learning_rate": 1.3433382850631673e-05, + "loss": 1.4566, + "step": 4287 + }, + { + "epoch": 0.45, + "learning_rate": 1.3429944870606301e-05, + "loss": 1.1263, + "step": 4288 + }, + { + "epoch": 0.45, + "learning_rate": 1.3426506431056452e-05, + "loss": 1.2463, + "step": 4289 + }, + { + "epoch": 0.45, + "learning_rate": 1.342306753244278e-05, + "loss": 1.4753, + "step": 4290 + }, + { + "epoch": 0.45, + "learning_rate": 1.3419628175226012e-05, + "loss": 1.3789, + "step": 4291 + }, + { + "epoch": 0.45, + "learning_rate": 1.3416188359866932e-05, + "loss": 1.3906, + "step": 4292 + }, + { + "epoch": 0.45, + "learning_rate": 1.3412748086826389e-05, + "loss": 1.3995, + "step": 4293 + }, + { + "epoch": 0.45, + "learning_rate": 1.3409307356565288e-05, + "loss": 1.4906, + "step": 4294 + }, + { + "epoch": 0.45, + "learning_rate": 1.3405866169544602e-05, + "loss": 1.3951, + "step": 4295 + }, + { + "epoch": 0.45, + "learning_rate": 1.3402424526225359e-05, + "loss": 1.3753, + "step": 4296 + }, + { + "epoch": 0.45, + "learning_rate": 1.3398982427068654e-05, + "loss": 1.3686, + "step": 4297 + }, + { + "epoch": 0.45, + "learning_rate": 1.3395539872535636e-05, + "loss": 1.3612, + "step": 4298 + }, + { + "epoch": 0.45, + "learning_rate": 1.3392096863087522e-05, + "loss": 1.4043, + "step": 4299 + }, + { + "epoch": 0.45, + "learning_rate": 1.3388653399185585e-05, + "loss": 1.4068, + "step": 4300 + }, + { + "epoch": 0.45, + "learning_rate": 1.338520948129116e-05, + "loss": 1.4066, + "step": 4301 + }, + { + "epoch": 0.45, + "learning_rate": 1.3381765109865646e-05, + "loss": 1.4944, + "step": 4302 + }, + { + "epoch": 0.45, + "learning_rate": 1.3378320285370496e-05, + "loss": 1.3575, + "step": 4303 + }, + { + "epoch": 0.45, + "learning_rate": 1.3374875008267236e-05, + "loss": 1.3807, + "step": 4304 + }, + { + "epoch": 0.45, + "learning_rate": 1.3371429279017437e-05, + "loss": 1.4389, + "step": 4305 + }, + { + "epoch": 0.45, + "learning_rate": 1.3367983098082739e-05, + "loss": 1.4858, + "step": 4306 + }, + { + "epoch": 0.45, + "learning_rate": 1.3364536465924844e-05, + "loss": 1.3282, + "step": 4307 + }, + { + "epoch": 0.45, + "learning_rate": 1.3361089383005515e-05, + "loss": 1.4306, + "step": 4308 + }, + { + "epoch": 0.45, + "learning_rate": 1.3357641849786566e-05, + "loss": 1.3892, + "step": 4309 + }, + { + "epoch": 0.45, + "learning_rate": 1.3354193866729883e-05, + "loss": 1.3621, + "step": 4310 + }, + { + "epoch": 0.45, + "learning_rate": 1.3350745434297401e-05, + "loss": 1.3476, + "step": 4311 + }, + { + "epoch": 0.45, + "learning_rate": 1.334729655295113e-05, + "loss": 1.4477, + "step": 4312 + }, + { + "epoch": 0.45, + "learning_rate": 1.3343847223153123e-05, + "loss": 1.3585, + "step": 4313 + }, + { + "epoch": 0.45, + "learning_rate": 1.334039744536551e-05, + "loss": 1.3616, + "step": 4314 + }, + { + "epoch": 0.45, + "learning_rate": 1.3336947220050462e-05, + "loss": 1.3579, + "step": 4315 + }, + { + "epoch": 0.45, + "learning_rate": 1.3333496547670232e-05, + "loss": 1.3557, + "step": 4316 + }, + { + "epoch": 0.45, + "learning_rate": 1.3330045428687113e-05, + "loss": 1.4443, + "step": 4317 + }, + { + "epoch": 0.45, + "learning_rate": 1.332659386356347e-05, + "loss": 1.3621, + "step": 4318 + }, + { + "epoch": 0.45, + "learning_rate": 1.3323141852761726e-05, + "loss": 1.3295, + "step": 4319 + }, + { + "epoch": 0.45, + "learning_rate": 1.3319689396744358e-05, + "loss": 1.4187, + "step": 4320 + }, + { + "epoch": 0.45, + "learning_rate": 1.3316236495973905e-05, + "loss": 1.335, + "step": 4321 + }, + { + "epoch": 0.45, + "learning_rate": 1.331278315091297e-05, + "loss": 1.4382, + "step": 4322 + }, + { + "epoch": 0.45, + "learning_rate": 1.3309329362024212e-05, + "loss": 1.4244, + "step": 4323 + }, + { + "epoch": 0.45, + "learning_rate": 1.3305875129770351e-05, + "loss": 1.488, + "step": 4324 + }, + { + "epoch": 0.45, + "learning_rate": 1.3302420454614165e-05, + "loss": 1.3369, + "step": 4325 + }, + { + "epoch": 0.45, + "learning_rate": 1.3298965337018487e-05, + "loss": 1.3648, + "step": 4326 + }, + { + "epoch": 0.45, + "learning_rate": 1.3295509777446226e-05, + "loss": 1.3924, + "step": 4327 + }, + { + "epoch": 0.45, + "learning_rate": 1.3292053776360324e-05, + "loss": 1.3789, + "step": 4328 + }, + { + "epoch": 0.45, + "learning_rate": 1.3288597334223802e-05, + "loss": 1.3902, + "step": 4329 + }, + { + "epoch": 0.45, + "learning_rate": 1.3285140451499735e-05, + "loss": 1.4057, + "step": 4330 + }, + { + "epoch": 0.45, + "learning_rate": 1.328168312865126e-05, + "loss": 1.4536, + "step": 4331 + }, + { + "epoch": 0.45, + "learning_rate": 1.3278225366141565e-05, + "loss": 1.3075, + "step": 4332 + }, + { + "epoch": 0.45, + "learning_rate": 1.3274767164433901e-05, + "loss": 1.4579, + "step": 4333 + }, + { + "epoch": 0.45, + "learning_rate": 1.3271308523991579e-05, + "loss": 1.3906, + "step": 4334 + }, + { + "epoch": 0.45, + "learning_rate": 1.326784944527797e-05, + "loss": 1.3992, + "step": 4335 + }, + { + "epoch": 0.45, + "learning_rate": 1.3264389928756498e-05, + "loss": 1.4001, + "step": 4336 + }, + { + "epoch": 0.45, + "learning_rate": 1.3260929974890653e-05, + "loss": 1.2948, + "step": 4337 + }, + { + "epoch": 0.45, + "learning_rate": 1.3257469584143976e-05, + "loss": 1.4041, + "step": 4338 + }, + { + "epoch": 0.46, + "learning_rate": 1.3254008756980076e-05, + "loss": 1.5035, + "step": 4339 + }, + { + "epoch": 0.46, + "learning_rate": 1.3250547493862609e-05, + "loss": 1.4867, + "step": 4340 + }, + { + "epoch": 0.46, + "learning_rate": 1.3247085795255302e-05, + "loss": 1.3612, + "step": 4341 + }, + { + "epoch": 0.46, + "learning_rate": 1.3243623661621925e-05, + "loss": 1.4193, + "step": 4342 + }, + { + "epoch": 0.46, + "learning_rate": 1.3240161093426322e-05, + "loss": 1.3596, + "step": 4343 + }, + { + "epoch": 0.46, + "learning_rate": 1.3236698091132383e-05, + "loss": 1.4448, + "step": 4344 + }, + { + "epoch": 0.46, + "learning_rate": 1.3233234655204066e-05, + "loss": 1.3924, + "step": 4345 + }, + { + "epoch": 0.46, + "learning_rate": 1.322977078610538e-05, + "loss": 1.3552, + "step": 4346 + }, + { + "epoch": 0.46, + "learning_rate": 1.3226306484300395e-05, + "loss": 1.3949, + "step": 4347 + }, + { + "epoch": 0.46, + "learning_rate": 1.322284175025324e-05, + "loss": 1.399, + "step": 4348 + }, + { + "epoch": 0.46, + "learning_rate": 1.3219376584428094e-05, + "loss": 1.4755, + "step": 4349 + }, + { + "epoch": 0.46, + "learning_rate": 1.3215910987289212e-05, + "loss": 1.3877, + "step": 4350 + }, + { + "epoch": 0.46, + "learning_rate": 1.3212444959300882e-05, + "loss": 1.3916, + "step": 4351 + }, + { + "epoch": 0.46, + "learning_rate": 1.3208978500927472e-05, + "loss": 1.3462, + "step": 4352 + }, + { + "epoch": 0.46, + "learning_rate": 1.3205511612633392e-05, + "loss": 1.3834, + "step": 4353 + }, + { + "epoch": 0.46, + "learning_rate": 1.3202044294883123e-05, + "loss": 1.3843, + "step": 4354 + }, + { + "epoch": 0.46, + "learning_rate": 1.3198576548141189e-05, + "loss": 1.2439, + "step": 4355 + }, + { + "epoch": 0.46, + "learning_rate": 1.3195108372872181e-05, + "loss": 1.4106, + "step": 4356 + }, + { + "epoch": 0.46, + "learning_rate": 1.3191639769540746e-05, + "loss": 1.4417, + "step": 4357 + }, + { + "epoch": 0.46, + "learning_rate": 1.3188170738611596e-05, + "loss": 1.4393, + "step": 4358 + }, + { + "epoch": 0.46, + "learning_rate": 1.3184701280549476e-05, + "loss": 1.4616, + "step": 4359 + }, + { + "epoch": 0.46, + "learning_rate": 1.3181231395819218e-05, + "loss": 1.3215, + "step": 4360 + }, + { + "epoch": 0.46, + "learning_rate": 1.3177761084885689e-05, + "loss": 1.368, + "step": 4361 + }, + { + "epoch": 0.46, + "learning_rate": 1.317429034821383e-05, + "loss": 1.3247, + "step": 4362 + }, + { + "epoch": 0.46, + "learning_rate": 1.3170819186268618e-05, + "loss": 1.4512, + "step": 4363 + }, + { + "epoch": 0.46, + "learning_rate": 1.3167347599515111e-05, + "loss": 1.3129, + "step": 4364 + }, + { + "epoch": 0.46, + "learning_rate": 1.3163875588418404e-05, + "loss": 1.3934, + "step": 4365 + }, + { + "epoch": 0.46, + "learning_rate": 1.3160403153443666e-05, + "loss": 1.4518, + "step": 4366 + }, + { + "epoch": 0.46, + "learning_rate": 1.3156930295056105e-05, + "loss": 1.3959, + "step": 4367 + }, + { + "epoch": 0.46, + "learning_rate": 1.3153457013721e-05, + "loss": 1.3475, + "step": 4368 + }, + { + "epoch": 0.46, + "learning_rate": 1.3149983309903687e-05, + "loss": 1.4102, + "step": 4369 + }, + { + "epoch": 0.46, + "learning_rate": 1.3146509184069538e-05, + "loss": 1.3674, + "step": 4370 + }, + { + "epoch": 0.46, + "learning_rate": 1.314303463668401e-05, + "loss": 1.3739, + "step": 4371 + }, + { + "epoch": 0.46, + "learning_rate": 1.3139559668212596e-05, + "loss": 1.4249, + "step": 4372 + }, + { + "epoch": 0.46, + "learning_rate": 1.3136084279120857e-05, + "loss": 1.4473, + "step": 4373 + }, + { + "epoch": 0.46, + "learning_rate": 1.3132608469874404e-05, + "loss": 1.4443, + "step": 4374 + }, + { + "epoch": 0.46, + "learning_rate": 1.3129132240938905e-05, + "loss": 1.3534, + "step": 4375 + }, + { + "epoch": 0.46, + "learning_rate": 1.3125655592780083e-05, + "loss": 1.5663, + "step": 4376 + }, + { + "epoch": 0.46, + "learning_rate": 1.3122178525863727e-05, + "loss": 1.3465, + "step": 4377 + }, + { + "epoch": 0.46, + "learning_rate": 1.3118701040655669e-05, + "loss": 1.35, + "step": 4378 + }, + { + "epoch": 0.46, + "eval_loss": 1.447788953781128, + "eval_runtime": 77.4473, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4378 + }, + { + "epoch": 0.46, + "learning_rate": 1.3115223137621804e-05, + "loss": 1.343, + "step": 4379 + }, + { + "epoch": 0.46, + "learning_rate": 1.3111744817228078e-05, + "loss": 1.4227, + "step": 4380 + }, + { + "epoch": 0.46, + "learning_rate": 1.3108266079940508e-05, + "loss": 1.3982, + "step": 4381 + }, + { + "epoch": 0.46, + "learning_rate": 1.3104786926225141e-05, + "loss": 1.4211, + "step": 4382 + }, + { + "epoch": 0.46, + "learning_rate": 1.3101307356548103e-05, + "loss": 1.382, + "step": 4383 + }, + { + "epoch": 0.46, + "learning_rate": 1.3097827371375562e-05, + "loss": 1.4637, + "step": 4384 + }, + { + "epoch": 0.46, + "learning_rate": 1.3094346971173754e-05, + "loss": 1.4572, + "step": 4385 + }, + { + "epoch": 0.46, + "learning_rate": 1.3090866156408956e-05, + "loss": 1.5113, + "step": 4386 + }, + { + "epoch": 0.46, + "learning_rate": 1.3087384927547512e-05, + "loss": 1.2197, + "step": 4387 + }, + { + "epoch": 0.46, + "learning_rate": 1.3083903285055813e-05, + "loss": 1.3861, + "step": 4388 + }, + { + "epoch": 0.46, + "learning_rate": 1.3080421229400315e-05, + "loss": 1.4754, + "step": 4389 + }, + { + "epoch": 0.46, + "learning_rate": 1.307693876104752e-05, + "loss": 1.3588, + "step": 4390 + }, + { + "epoch": 0.46, + "learning_rate": 1.3073455880463987e-05, + "loss": 1.3995, + "step": 4391 + }, + { + "epoch": 0.46, + "learning_rate": 1.3069972588116341e-05, + "loss": 1.354, + "step": 4392 + }, + { + "epoch": 0.46, + "learning_rate": 1.3066488884471244e-05, + "loss": 1.3378, + "step": 4393 + }, + { + "epoch": 0.46, + "learning_rate": 1.306300476999543e-05, + "loss": 1.5951, + "step": 4394 + }, + { + "epoch": 0.46, + "learning_rate": 1.305952024515568e-05, + "loss": 1.3661, + "step": 4395 + }, + { + "epoch": 0.46, + "learning_rate": 1.3056035310418826e-05, + "loss": 1.4066, + "step": 4396 + }, + { + "epoch": 0.46, + "learning_rate": 1.3052549966251764e-05, + "loss": 1.3687, + "step": 4397 + }, + { + "epoch": 0.46, + "learning_rate": 1.3049064213121438e-05, + "loss": 1.4573, + "step": 4398 + }, + { + "epoch": 0.46, + "learning_rate": 1.3045578051494852e-05, + "loss": 1.3519, + "step": 4399 + }, + { + "epoch": 0.46, + "learning_rate": 1.3042091481839063e-05, + "loss": 1.2803, + "step": 4400 + }, + { + "epoch": 0.46, + "learning_rate": 1.3038604504621173e-05, + "loss": 1.4014, + "step": 4401 + }, + { + "epoch": 0.46, + "learning_rate": 1.3035117120308358e-05, + "loss": 1.4534, + "step": 4402 + }, + { + "epoch": 0.46, + "learning_rate": 1.3031629329367832e-05, + "loss": 1.4747, + "step": 4403 + }, + { + "epoch": 0.46, + "learning_rate": 1.3028141132266877e-05, + "loss": 1.374, + "step": 4404 + }, + { + "epoch": 0.46, + "learning_rate": 1.3024652529472807e-05, + "loss": 1.4328, + "step": 4405 + }, + { + "epoch": 0.46, + "learning_rate": 1.302116352145302e-05, + "loss": 1.468, + "step": 4406 + }, + { + "epoch": 0.46, + "learning_rate": 1.3017674108674942e-05, + "loss": 1.2947, + "step": 4407 + }, + { + "epoch": 0.46, + "learning_rate": 1.3014184291606077e-05, + "loss": 1.3682, + "step": 4408 + }, + { + "epoch": 0.46, + "learning_rate": 1.3010694070713959e-05, + "loss": 1.3651, + "step": 4409 + }, + { + "epoch": 0.46, + "learning_rate": 1.3007203446466194e-05, + "loss": 1.418, + "step": 4410 + }, + { + "epoch": 0.46, + "learning_rate": 1.3003712419330433e-05, + "loss": 1.416, + "step": 4411 + }, + { + "epoch": 0.46, + "learning_rate": 1.300022098977439e-05, + "loss": 1.2979, + "step": 4412 + }, + { + "epoch": 0.46, + "learning_rate": 1.2996729158265819e-05, + "loss": 1.3868, + "step": 4413 + }, + { + "epoch": 0.46, + "learning_rate": 1.2993236925272542e-05, + "loss": 1.3102, + "step": 4414 + }, + { + "epoch": 0.46, + "learning_rate": 1.2989744291262422e-05, + "loss": 1.3506, + "step": 4415 + }, + { + "epoch": 0.46, + "learning_rate": 1.2986251256703388e-05, + "loss": 1.4018, + "step": 4416 + }, + { + "epoch": 0.46, + "learning_rate": 1.2982757822063417e-05, + "loss": 1.4081, + "step": 4417 + }, + { + "epoch": 0.46, + "learning_rate": 1.2979263987810533e-05, + "loss": 1.3592, + "step": 4418 + }, + { + "epoch": 0.46, + "learning_rate": 1.297576975441283e-05, + "loss": 1.4287, + "step": 4419 + }, + { + "epoch": 0.46, + "learning_rate": 1.2972275122338433e-05, + "loss": 1.4099, + "step": 4420 + }, + { + "epoch": 0.46, + "learning_rate": 1.2968780092055546e-05, + "loss": 1.4005, + "step": 4421 + }, + { + "epoch": 0.46, + "learning_rate": 1.2965284664032401e-05, + "loss": 1.365, + "step": 4422 + }, + { + "epoch": 0.46, + "learning_rate": 1.2961788838737309e-05, + "loss": 1.3588, + "step": 4423 + }, + { + "epoch": 0.46, + "learning_rate": 1.2958292616638606e-05, + "loss": 1.3702, + "step": 4424 + }, + { + "epoch": 0.46, + "learning_rate": 1.2954795998204708e-05, + "loss": 1.3487, + "step": 4425 + }, + { + "epoch": 0.46, + "learning_rate": 1.2951298983904063e-05, + "loss": 1.4395, + "step": 4426 + }, + { + "epoch": 0.46, + "learning_rate": 1.2947801574205193e-05, + "loss": 1.3523, + "step": 4427 + }, + { + "epoch": 0.46, + "learning_rate": 1.2944303769576645e-05, + "loss": 1.3125, + "step": 4428 + }, + { + "epoch": 0.46, + "learning_rate": 1.2940805570487048e-05, + "loss": 1.5476, + "step": 4429 + }, + { + "epoch": 0.46, + "learning_rate": 1.2937306977405062e-05, + "loss": 1.4076, + "step": 4430 + }, + { + "epoch": 0.46, + "learning_rate": 1.2933807990799418e-05, + "loss": 1.3007, + "step": 4431 + }, + { + "epoch": 0.46, + "learning_rate": 1.293030861113888e-05, + "loss": 1.3566, + "step": 4432 + }, + { + "epoch": 0.46, + "learning_rate": 1.2926808838892285e-05, + "loss": 1.3907, + "step": 4433 + }, + { + "epoch": 0.46, + "learning_rate": 1.2923308674528501e-05, + "loss": 1.379, + "step": 4434 + }, + { + "epoch": 0.47, + "learning_rate": 1.2919808118516475e-05, + "loss": 1.4319, + "step": 4435 + }, + { + "epoch": 0.47, + "learning_rate": 1.2916307171325176e-05, + "loss": 1.3392, + "step": 4436 + }, + { + "epoch": 0.47, + "learning_rate": 1.291280583342365e-05, + "loss": 1.401, + "step": 4437 + }, + { + "epoch": 0.47, + "learning_rate": 1.2909304105280984e-05, + "loss": 1.3939, + "step": 4438 + }, + { + "epoch": 0.47, + "learning_rate": 1.2905801987366322e-05, + "loss": 1.4676, + "step": 4439 + }, + { + "epoch": 0.47, + "learning_rate": 1.2902299480148855e-05, + "loss": 1.3957, + "step": 4440 + }, + { + "epoch": 0.47, + "learning_rate": 1.2898796584097828e-05, + "loss": 1.3587, + "step": 4441 + }, + { + "epoch": 0.47, + "learning_rate": 1.2895293299682545e-05, + "loss": 1.5809, + "step": 4442 + }, + { + "epoch": 0.47, + "learning_rate": 1.289178962737235e-05, + "loss": 1.3436, + "step": 4443 + }, + { + "epoch": 0.47, + "learning_rate": 1.2888285567636647e-05, + "loss": 1.4535, + "step": 4444 + }, + { + "epoch": 0.47, + "learning_rate": 1.2884781120944889e-05, + "loss": 1.3377, + "step": 4445 + }, + { + "epoch": 0.47, + "learning_rate": 1.2881276287766587e-05, + "loss": 0.8221, + "step": 4446 + }, + { + "epoch": 0.47, + "learning_rate": 1.2877771068571288e-05, + "loss": 0.7259, + "step": 4447 + }, + { + "epoch": 0.47, + "learning_rate": 1.2874265463828612e-05, + "loss": 0.8279, + "step": 4448 + }, + { + "epoch": 0.47, + "learning_rate": 1.2870759474008213e-05, + "loss": 1.3523, + "step": 4449 + }, + { + "epoch": 0.47, + "learning_rate": 1.2867253099579808e-05, + "loss": 1.3658, + "step": 4450 + }, + { + "epoch": 0.47, + "learning_rate": 1.2863746341013158e-05, + "loss": 1.4112, + "step": 4451 + }, + { + "epoch": 0.47, + "learning_rate": 1.2860239198778085e-05, + "loss": 1.389, + "step": 4452 + }, + { + "epoch": 0.47, + "learning_rate": 1.2856731673344442e-05, + "loss": 1.4066, + "step": 4453 + }, + { + "epoch": 0.47, + "learning_rate": 1.2853223765182165e-05, + "loss": 1.3267, + "step": 4454 + }, + { + "epoch": 0.47, + "learning_rate": 1.2849715474761209e-05, + "loss": 1.3381, + "step": 4455 + }, + { + "epoch": 0.47, + "learning_rate": 1.2846206802551602e-05, + "loss": 1.2882, + "step": 4456 + }, + { + "epoch": 0.47, + "learning_rate": 1.2842697749023414e-05, + "loss": 1.3199, + "step": 4457 + }, + { + "epoch": 0.47, + "learning_rate": 1.2839188314646771e-05, + "loss": 1.3896, + "step": 4458 + }, + { + "epoch": 0.47, + "learning_rate": 1.2835678499891842e-05, + "loss": 1.3186, + "step": 4459 + }, + { + "epoch": 0.47, + "learning_rate": 1.283216830522885e-05, + "loss": 1.3466, + "step": 4460 + }, + { + "epoch": 0.47, + "learning_rate": 1.2828657731128083e-05, + "loss": 1.4678, + "step": 4461 + }, + { + "epoch": 0.47, + "learning_rate": 1.2825146778059857e-05, + "loss": 1.4408, + "step": 4462 + }, + { + "epoch": 0.47, + "learning_rate": 1.2821635446494553e-05, + "loss": 1.3672, + "step": 4463 + }, + { + "epoch": 0.47, + "learning_rate": 1.2818123736902597e-05, + "loss": 1.3836, + "step": 4464 + }, + { + "epoch": 0.47, + "learning_rate": 1.2814611649754472e-05, + "loss": 1.3493, + "step": 4465 + }, + { + "epoch": 0.47, + "learning_rate": 1.2811099185520704e-05, + "loss": 1.3584, + "step": 4466 + }, + { + "epoch": 0.47, + "learning_rate": 1.2807586344671875e-05, + "loss": 1.3551, + "step": 4467 + }, + { + "epoch": 0.47, + "learning_rate": 1.2804073127678612e-05, + "loss": 1.3254, + "step": 4468 + }, + { + "epoch": 0.47, + "learning_rate": 1.28005595350116e-05, + "loss": 1.3405, + "step": 4469 + }, + { + "epoch": 0.47, + "learning_rate": 1.2797045567141568e-05, + "loss": 1.3432, + "step": 4470 + }, + { + "epoch": 0.47, + "learning_rate": 1.2793531224539297e-05, + "loss": 1.4347, + "step": 4471 + }, + { + "epoch": 0.47, + "learning_rate": 1.279001650767562e-05, + "loss": 1.3304, + "step": 4472 + }, + { + "epoch": 0.47, + "learning_rate": 1.278650141702142e-05, + "loss": 1.3244, + "step": 4473 + }, + { + "epoch": 0.47, + "learning_rate": 1.2782985953047625e-05, + "loss": 1.3756, + "step": 4474 + }, + { + "epoch": 0.47, + "learning_rate": 1.2779470116225219e-05, + "loss": 1.5468, + "step": 4475 + }, + { + "epoch": 0.47, + "learning_rate": 1.2775953907025232e-05, + "loss": 1.4316, + "step": 4476 + }, + { + "epoch": 0.47, + "learning_rate": 1.2772437325918752e-05, + "loss": 1.3724, + "step": 4477 + }, + { + "epoch": 0.47, + "learning_rate": 1.27689203733769e-05, + "loss": 1.4458, + "step": 4478 + }, + { + "epoch": 0.47, + "learning_rate": 1.2765403049870865e-05, + "loss": 1.3622, + "step": 4479 + }, + { + "epoch": 0.47, + "learning_rate": 1.2761885355871875e-05, + "loss": 1.3875, + "step": 4480 + }, + { + "epoch": 0.47, + "learning_rate": 1.2758367291851217e-05, + "loss": 1.3577, + "step": 4481 + }, + { + "epoch": 0.47, + "learning_rate": 1.2754848858280211e-05, + "loss": 1.4256, + "step": 4482 + }, + { + "epoch": 0.47, + "learning_rate": 1.2751330055630242e-05, + "loss": 1.3771, + "step": 4483 + }, + { + "epoch": 0.47, + "learning_rate": 1.274781088437274e-05, + "loss": 1.357, + "step": 4484 + }, + { + "epoch": 0.47, + "learning_rate": 1.274429134497918e-05, + "loss": 1.3634, + "step": 4485 + }, + { + "epoch": 0.47, + "learning_rate": 1.2740771437921096e-05, + "loss": 1.3661, + "step": 4486 + }, + { + "epoch": 0.47, + "learning_rate": 1.2737251163670057e-05, + "loss": 1.3819, + "step": 4487 + }, + { + "epoch": 0.47, + "learning_rate": 1.2733730522697696e-05, + "loss": 1.4491, + "step": 4488 + }, + { + "epoch": 0.47, + "learning_rate": 1.2730209515475687e-05, + "loss": 1.3857, + "step": 4489 + }, + { + "epoch": 0.47, + "learning_rate": 1.2726688142475751e-05, + "loss": 1.3837, + "step": 4490 + }, + { + "epoch": 0.47, + "learning_rate": 1.2723166404169663e-05, + "loss": 1.3755, + "step": 4491 + }, + { + "epoch": 0.47, + "learning_rate": 1.271964430102925e-05, + "loss": 1.3767, + "step": 4492 + }, + { + "epoch": 0.47, + "learning_rate": 1.2716121833526376e-05, + "loss": 1.4416, + "step": 4493 + }, + { + "epoch": 0.47, + "learning_rate": 1.2712599002132966e-05, + "loss": 1.5573, + "step": 4494 + }, + { + "epoch": 0.47, + "learning_rate": 1.2709075807320988e-05, + "loss": 1.365, + "step": 4495 + }, + { + "epoch": 0.47, + "learning_rate": 1.270555224956246e-05, + "loss": 1.3862, + "step": 4496 + }, + { + "epoch": 0.47, + "learning_rate": 1.2702028329329445e-05, + "loss": 1.3003, + "step": 4497 + }, + { + "epoch": 0.47, + "learning_rate": 1.2698504047094064e-05, + "loss": 1.3806, + "step": 4498 + }, + { + "epoch": 0.47, + "learning_rate": 1.269497940332847e-05, + "loss": 1.5425, + "step": 4499 + }, + { + "epoch": 0.47, + "learning_rate": 1.269145439850489e-05, + "loss": 1.3541, + "step": 4500 + }, + { + "epoch": 0.47, + "learning_rate": 1.268792903309557e-05, + "loss": 1.4337, + "step": 4501 + }, + { + "epoch": 0.47, + "learning_rate": 1.2684403307572825e-05, + "loss": 1.4004, + "step": 4502 + }, + { + "epoch": 0.47, + "learning_rate": 1.268087722240901e-05, + "loss": 1.9453, + "step": 4503 + }, + { + "epoch": 0.47, + "learning_rate": 1.2677350778076532e-05, + "loss": 1.3907, + "step": 4504 + }, + { + "epoch": 0.47, + "learning_rate": 1.2673823975047839e-05, + "loss": 1.4993, + "step": 4505 + }, + { + "epoch": 0.47, + "learning_rate": 1.2670296813795432e-05, + "loss": 1.4386, + "step": 4506 + }, + { + "epoch": 0.47, + "learning_rate": 1.266676929479187e-05, + "loss": 1.4944, + "step": 4507 + }, + { + "epoch": 0.47, + "learning_rate": 1.266324141850974e-05, + "loss": 1.4311, + "step": 4508 + }, + { + "epoch": 0.47, + "learning_rate": 1.265971318542169e-05, + "loss": 1.3607, + "step": 4509 + }, + { + "epoch": 0.47, + "learning_rate": 1.2656184596000412e-05, + "loss": 1.4007, + "step": 4510 + }, + { + "epoch": 0.47, + "learning_rate": 1.2652655650718645e-05, + "loss": 1.4561, + "step": 4511 + }, + { + "epoch": 0.47, + "learning_rate": 1.2649126350049181e-05, + "loss": 1.4321, + "step": 4512 + }, + { + "epoch": 0.47, + "learning_rate": 1.2645596694464851e-05, + "loss": 1.2856, + "step": 4513 + }, + { + "epoch": 0.47, + "learning_rate": 1.2642066684438543e-05, + "loss": 1.3979, + "step": 4514 + }, + { + "epoch": 0.47, + "learning_rate": 1.2638536320443184e-05, + "loss": 1.4977, + "step": 4515 + }, + { + "epoch": 0.47, + "learning_rate": 1.2635005602951752e-05, + "loss": 1.377, + "step": 4516 + }, + { + "epoch": 0.47, + "learning_rate": 1.2631474532437275e-05, + "loss": 1.4266, + "step": 4517 + }, + { + "epoch": 0.47, + "learning_rate": 1.2627943109372822e-05, + "loss": 1.409, + "step": 4518 + }, + { + "epoch": 0.47, + "learning_rate": 1.2624411334231519e-05, + "loss": 1.3374, + "step": 4519 + }, + { + "epoch": 0.47, + "learning_rate": 1.2620879207486525e-05, + "loss": 1.3765, + "step": 4520 + }, + { + "epoch": 0.47, + "learning_rate": 1.2617346729611061e-05, + "loss": 1.3805, + "step": 4521 + }, + { + "epoch": 0.47, + "learning_rate": 1.2613813901078384e-05, + "loss": 1.3326, + "step": 4522 + }, + { + "epoch": 0.47, + "learning_rate": 1.2610280722361807e-05, + "loss": 1.3909, + "step": 4523 + }, + { + "epoch": 0.47, + "learning_rate": 1.260674719393468e-05, + "loss": 1.3815, + "step": 4524 + }, + { + "epoch": 0.47, + "learning_rate": 1.2603213316270409e-05, + "loss": 1.5589, + "step": 4525 + }, + { + "epoch": 0.47, + "learning_rate": 1.2599679089842437e-05, + "loss": 1.4416, + "step": 4526 + }, + { + "epoch": 0.47, + "learning_rate": 1.259614451512427e-05, + "loss": 1.3529, + "step": 4527 + }, + { + "epoch": 0.47, + "learning_rate": 1.2592609592589437e-05, + "loss": 1.3135, + "step": 4528 + }, + { + "epoch": 0.47, + "learning_rate": 1.2589074322711535e-05, + "loss": 1.4177, + "step": 4529 + }, + { + "epoch": 0.48, + "learning_rate": 1.25855387059642e-05, + "loss": 1.353, + "step": 4530 + }, + { + "epoch": 0.48, + "learning_rate": 1.2582002742821111e-05, + "loss": 1.431, + "step": 4531 + }, + { + "epoch": 0.48, + "learning_rate": 1.2578466433755998e-05, + "loss": 1.3803, + "step": 4532 + }, + { + "epoch": 0.48, + "learning_rate": 1.257492977924263e-05, + "loss": 1.3774, + "step": 4533 + }, + { + "epoch": 0.48, + "learning_rate": 1.2571392779754836e-05, + "loss": 1.4339, + "step": 4534 + }, + { + "epoch": 0.48, + "learning_rate": 1.256785543576648e-05, + "loss": 1.4097, + "step": 4535 + }, + { + "epoch": 0.48, + "learning_rate": 1.2564317747751473e-05, + "loss": 1.4223, + "step": 4536 + }, + { + "epoch": 0.48, + "learning_rate": 1.2560779716183775e-05, + "loss": 1.5148, + "step": 4537 + }, + { + "epoch": 0.48, + "learning_rate": 1.2557241341537394e-05, + "loss": 1.3547, + "step": 4538 + }, + { + "epoch": 0.48, + "learning_rate": 1.255370262428638e-05, + "loss": 1.393, + "step": 4539 + }, + { + "epoch": 0.48, + "learning_rate": 1.2550163564904829e-05, + "loss": 1.3312, + "step": 4540 + }, + { + "epoch": 0.48, + "learning_rate": 1.2546624163866882e-05, + "loss": 1.4193, + "step": 4541 + }, + { + "epoch": 0.48, + "learning_rate": 1.2543084421646735e-05, + "loss": 1.4161, + "step": 4542 + }, + { + "epoch": 0.48, + "learning_rate": 1.2539544338718614e-05, + "loss": 1.4224, + "step": 4543 + }, + { + "epoch": 0.48, + "learning_rate": 1.2536003915556805e-05, + "loss": 1.3484, + "step": 4544 + }, + { + "epoch": 0.48, + "learning_rate": 1.253246315263563e-05, + "loss": 1.4492, + "step": 4545 + }, + { + "epoch": 0.48, + "learning_rate": 1.2528922050429467e-05, + "loss": 1.3549, + "step": 4546 + }, + { + "epoch": 0.48, + "learning_rate": 1.252538060941272e-05, + "loss": 1.45, + "step": 4547 + }, + { + "epoch": 0.48, + "learning_rate": 1.2521838830059865e-05, + "loss": 1.3499, + "step": 4548 + }, + { + "epoch": 0.48, + "learning_rate": 1.2518296712845399e-05, + "loss": 1.3786, + "step": 4549 + }, + { + "epoch": 0.48, + "learning_rate": 1.2514754258243884e-05, + "loss": 1.3394, + "step": 4550 + }, + { + "epoch": 0.48, + "learning_rate": 1.2511211466729909e-05, + "loss": 1.2849, + "step": 4551 + }, + { + "epoch": 0.48, + "learning_rate": 1.250766833877812e-05, + "loss": 1.374, + "step": 4552 + }, + { + "epoch": 0.48, + "learning_rate": 1.2504124874863211e-05, + "loss": 1.3084, + "step": 4553 + }, + { + "epoch": 0.48, + "learning_rate": 1.2500581075459905e-05, + "loss": 1.3348, + "step": 4554 + }, + { + "epoch": 0.48, + "learning_rate": 1.249703694104299e-05, + "loss": 1.3797, + "step": 4555 + }, + { + "epoch": 0.48, + "learning_rate": 1.2493492472087279e-05, + "loss": 1.3371, + "step": 4556 + }, + { + "epoch": 0.48, + "learning_rate": 1.248994766906765e-05, + "loss": 1.3974, + "step": 4557 + }, + { + "epoch": 0.48, + "learning_rate": 1.2486402532459007e-05, + "loss": 1.388, + "step": 4558 + }, + { + "epoch": 0.48, + "learning_rate": 1.2482857062736313e-05, + "loss": 1.3619, + "step": 4559 + }, + { + "epoch": 0.48, + "learning_rate": 1.2479311260374565e-05, + "loss": 1.4123, + "step": 4560 + }, + { + "epoch": 0.48, + "learning_rate": 1.2475765125848814e-05, + "loss": 1.5485, + "step": 4561 + }, + { + "epoch": 0.48, + "learning_rate": 1.247221865963415e-05, + "loss": 1.4965, + "step": 4562 + }, + { + "epoch": 0.48, + "learning_rate": 1.2468671862205705e-05, + "loss": 1.4352, + "step": 4563 + }, + { + "epoch": 0.48, + "learning_rate": 1.246512473403866e-05, + "loss": 1.3935, + "step": 4564 + }, + { + "epoch": 0.48, + "learning_rate": 1.2461577275608243e-05, + "loss": 1.3798, + "step": 4565 + }, + { + "epoch": 0.48, + "learning_rate": 1.2458029487389718e-05, + "loss": 1.4039, + "step": 4566 + }, + { + "epoch": 0.48, + "learning_rate": 1.2454481369858397e-05, + "loss": 1.3723, + "step": 4567 + }, + { + "epoch": 0.48, + "learning_rate": 1.245093292348964e-05, + "loss": 1.3713, + "step": 4568 + }, + { + "epoch": 0.48, + "learning_rate": 1.2447384148758847e-05, + "loss": 1.4083, + "step": 4569 + }, + { + "epoch": 0.48, + "learning_rate": 1.244383504614146e-05, + "loss": 1.2811, + "step": 4570 + }, + { + "epoch": 0.48, + "learning_rate": 1.2440285616112968e-05, + "loss": 1.3509, + "step": 4571 + }, + { + "epoch": 0.48, + "learning_rate": 1.2436735859148905e-05, + "loss": 1.3481, + "step": 4572 + }, + { + "epoch": 0.48, + "learning_rate": 1.2433185775724847e-05, + "loss": 1.4168, + "step": 4573 + }, + { + "epoch": 0.48, + "learning_rate": 1.2429635366316418e-05, + "loss": 1.3671, + "step": 4574 + }, + { + "epoch": 0.48, + "learning_rate": 1.2426084631399271e-05, + "loss": 1.6514, + "step": 4575 + }, + { + "epoch": 0.48, + "learning_rate": 1.2422533571449123e-05, + "loss": 1.3564, + "step": 4576 + }, + { + "epoch": 0.48, + "learning_rate": 1.2418982186941721e-05, + "loss": 1.4586, + "step": 4577 + }, + { + "epoch": 0.48, + "eval_loss": 1.4425245523452759, + "eval_runtime": 77.3853, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 4577 + }, + { + "epoch": 0.48, + "learning_rate": 1.2415430478352858e-05, + "loss": 1.3922, + "step": 4578 + }, + { + "epoch": 0.48, + "learning_rate": 1.2411878446158374e-05, + "loss": 1.3903, + "step": 4579 + }, + { + "epoch": 0.48, + "learning_rate": 1.240832609083415e-05, + "loss": 1.3537, + "step": 4580 + }, + { + "epoch": 0.48, + "learning_rate": 1.2404773412856113e-05, + "loss": 1.356, + "step": 4581 + }, + { + "epoch": 0.48, + "learning_rate": 1.2401220412700223e-05, + "loss": 1.4483, + "step": 4582 + }, + { + "epoch": 0.48, + "learning_rate": 1.2397667090842496e-05, + "loss": 1.3926, + "step": 4583 + }, + { + "epoch": 0.48, + "learning_rate": 1.2394113447758986e-05, + "loss": 1.4816, + "step": 4584 + }, + { + "epoch": 0.48, + "learning_rate": 1.2390559483925788e-05, + "loss": 1.3742, + "step": 4585 + }, + { + "epoch": 0.48, + "learning_rate": 1.2387005199819044e-05, + "loss": 1.4476, + "step": 4586 + }, + { + "epoch": 0.48, + "learning_rate": 1.2383450595914932e-05, + "loss": 1.4029, + "step": 4587 + }, + { + "epoch": 0.48, + "learning_rate": 1.2379895672689683e-05, + "loss": 1.4797, + "step": 4588 + }, + { + "epoch": 0.48, + "learning_rate": 1.2376340430619565e-05, + "loss": 1.3366, + "step": 4589 + }, + { + "epoch": 0.48, + "learning_rate": 1.2372784870180885e-05, + "loss": 1.4226, + "step": 4590 + }, + { + "epoch": 0.48, + "learning_rate": 1.2369228991849997e-05, + "loss": 1.3668, + "step": 4591 + }, + { + "epoch": 0.48, + "learning_rate": 1.2365672796103305e-05, + "loss": 1.4932, + "step": 4592 + }, + { + "epoch": 0.48, + "learning_rate": 1.236211628341724e-05, + "loss": 1.4088, + "step": 4593 + }, + { + "epoch": 0.48, + "learning_rate": 1.2358559454268284e-05, + "loss": 1.3616, + "step": 4594 + }, + { + "epoch": 0.48, + "learning_rate": 1.2355002309132961e-05, + "loss": 1.4345, + "step": 4595 + }, + { + "epoch": 0.48, + "learning_rate": 1.2351444848487844e-05, + "loss": 1.4025, + "step": 4596 + }, + { + "epoch": 0.48, + "learning_rate": 1.2347887072809533e-05, + "loss": 1.3895, + "step": 4597 + }, + { + "epoch": 0.48, + "learning_rate": 1.2344328982574678e-05, + "loss": 1.3326, + "step": 4598 + }, + { + "epoch": 0.48, + "learning_rate": 1.234077057825998e-05, + "loss": 1.4249, + "step": 4599 + }, + { + "epoch": 0.48, + "learning_rate": 1.2337211860342167e-05, + "loss": 1.3649, + "step": 4600 + }, + { + "epoch": 0.48, + "learning_rate": 1.2333652829298016e-05, + "loss": 1.3831, + "step": 4601 + }, + { + "epoch": 0.48, + "learning_rate": 1.2330093485604346e-05, + "loss": 1.3748, + "step": 4602 + }, + { + "epoch": 0.48, + "learning_rate": 1.2326533829738022e-05, + "loss": 1.386, + "step": 4603 + }, + { + "epoch": 0.48, + "learning_rate": 1.2322973862175941e-05, + "loss": 1.3923, + "step": 4604 + }, + { + "epoch": 0.48, + "learning_rate": 1.2319413583395052e-05, + "loss": 1.3638, + "step": 4605 + }, + { + "epoch": 0.48, + "learning_rate": 1.2315852993872335e-05, + "loss": 1.3476, + "step": 4606 + }, + { + "epoch": 0.48, + "learning_rate": 1.2312292094084824e-05, + "loss": 1.3581, + "step": 4607 + }, + { + "epoch": 0.48, + "learning_rate": 1.2308730884509583e-05, + "loss": 1.3554, + "step": 4608 + }, + { + "epoch": 0.48, + "learning_rate": 1.2305169365623724e-05, + "loss": 1.3676, + "step": 4609 + }, + { + "epoch": 0.48, + "learning_rate": 1.2301607537904399e-05, + "loss": 1.24, + "step": 4610 + }, + { + "epoch": 0.48, + "learning_rate": 1.2298045401828803e-05, + "loss": 1.3295, + "step": 4611 + }, + { + "epoch": 0.48, + "learning_rate": 1.2294482957874169e-05, + "loss": 1.5684, + "step": 4612 + }, + { + "epoch": 0.48, + "learning_rate": 1.2290920206517774e-05, + "loss": 1.3403, + "step": 4613 + }, + { + "epoch": 0.48, + "learning_rate": 1.2287357148236933e-05, + "loss": 1.349, + "step": 4614 + }, + { + "epoch": 0.48, + "learning_rate": 1.2283793783509008e-05, + "loss": 1.4261, + "step": 4615 + }, + { + "epoch": 0.48, + "learning_rate": 1.2280230112811395e-05, + "loss": 1.322, + "step": 4616 + }, + { + "epoch": 0.48, + "learning_rate": 1.2276666136621538e-05, + "loss": 1.3399, + "step": 4617 + }, + { + "epoch": 0.48, + "learning_rate": 1.2273101855416912e-05, + "loss": 1.3878, + "step": 4618 + }, + { + "epoch": 0.48, + "learning_rate": 1.2269537269675044e-05, + "loss": 1.4733, + "step": 4619 + }, + { + "epoch": 0.48, + "learning_rate": 1.2265972379873497e-05, + "loss": 1.419, + "step": 4620 + }, + { + "epoch": 0.48, + "learning_rate": 1.226240718648987e-05, + "loss": 1.3918, + "step": 4621 + }, + { + "epoch": 0.48, + "learning_rate": 1.2258841690001815e-05, + "loss": 1.3398, + "step": 4622 + }, + { + "epoch": 0.48, + "learning_rate": 1.225527589088701e-05, + "loss": 1.4091, + "step": 4623 + }, + { + "epoch": 0.48, + "learning_rate": 1.2251709789623185e-05, + "loss": 1.3291, + "step": 4624 + }, + { + "epoch": 0.49, + "learning_rate": 1.2248143386688101e-05, + "loss": 1.4288, + "step": 4625 + }, + { + "epoch": 0.49, + "learning_rate": 1.224457668255957e-05, + "loss": 1.2942, + "step": 4626 + }, + { + "epoch": 0.49, + "learning_rate": 1.2241009677715437e-05, + "loss": 1.4014, + "step": 4627 + }, + { + "epoch": 0.49, + "learning_rate": 1.2237442372633586e-05, + "loss": 1.3823, + "step": 4628 + }, + { + "epoch": 0.49, + "learning_rate": 1.2233874767791945e-05, + "loss": 1.3556, + "step": 4629 + }, + { + "epoch": 0.49, + "learning_rate": 1.2230306863668485e-05, + "loss": 1.411, + "step": 4630 + }, + { + "epoch": 0.49, + "learning_rate": 1.2226738660741212e-05, + "loss": 1.4347, + "step": 4631 + }, + { + "epoch": 0.49, + "learning_rate": 1.2223170159488169e-05, + "loss": 1.3095, + "step": 4632 + }, + { + "epoch": 0.49, + "learning_rate": 1.221960136038745e-05, + "loss": 1.4272, + "step": 4633 + }, + { + "epoch": 0.49, + "learning_rate": 1.221603226391718e-05, + "loss": 1.367, + "step": 4634 + }, + { + "epoch": 0.49, + "learning_rate": 1.2212462870555523e-05, + "loss": 1.3357, + "step": 4635 + }, + { + "epoch": 0.49, + "learning_rate": 1.220889318078069e-05, + "loss": 1.3634, + "step": 4636 + }, + { + "epoch": 0.49, + "learning_rate": 1.2205323195070927e-05, + "loss": 1.4143, + "step": 4637 + }, + { + "epoch": 0.49, + "learning_rate": 1.2201752913904519e-05, + "loss": 1.4865, + "step": 4638 + }, + { + "epoch": 0.49, + "learning_rate": 1.2198182337759794e-05, + "loss": 1.451, + "step": 4639 + }, + { + "epoch": 0.49, + "learning_rate": 1.2194611467115116e-05, + "loss": 1.3953, + "step": 4640 + }, + { + "epoch": 0.49, + "learning_rate": 1.2191040302448887e-05, + "loss": 1.4099, + "step": 4641 + }, + { + "epoch": 0.49, + "learning_rate": 1.2187468844239559e-05, + "loss": 1.3338, + "step": 4642 + }, + { + "epoch": 0.49, + "learning_rate": 1.2183897092965609e-05, + "loss": 1.4392, + "step": 4643 + }, + { + "epoch": 0.49, + "learning_rate": 1.2180325049105559e-05, + "loss": 1.3196, + "step": 4644 + }, + { + "epoch": 0.49, + "learning_rate": 1.2176752713137977e-05, + "loss": 1.3727, + "step": 4645 + }, + { + "epoch": 0.49, + "learning_rate": 1.2173180085541464e-05, + "loss": 1.3118, + "step": 4646 + }, + { + "epoch": 0.49, + "learning_rate": 1.2169607166794655e-05, + "loss": 1.3695, + "step": 4647 + }, + { + "epoch": 0.49, + "learning_rate": 1.2166033957376231e-05, + "loss": 1.3568, + "step": 4648 + }, + { + "epoch": 0.49, + "learning_rate": 1.216246045776491e-05, + "loss": 1.3492, + "step": 4649 + }, + { + "epoch": 0.49, + "learning_rate": 1.2158886668439455e-05, + "loss": 1.3445, + "step": 4650 + }, + { + "epoch": 0.49, + "learning_rate": 1.2155312589878654e-05, + "loss": 1.3756, + "step": 4651 + }, + { + "epoch": 0.49, + "learning_rate": 1.2151738222561344e-05, + "loss": 1.3681, + "step": 4652 + }, + { + "epoch": 0.49, + "learning_rate": 1.2148163566966403e-05, + "loss": 1.4345, + "step": 4653 + }, + { + "epoch": 0.49, + "learning_rate": 1.2144588623572738e-05, + "loss": 1.5102, + "step": 4654 + }, + { + "epoch": 0.49, + "learning_rate": 1.2141013392859297e-05, + "loss": 1.3531, + "step": 4655 + }, + { + "epoch": 0.49, + "learning_rate": 1.2137437875305075e-05, + "loss": 1.3824, + "step": 4656 + }, + { + "epoch": 0.49, + "learning_rate": 1.2133862071389099e-05, + "loss": 1.4227, + "step": 4657 + }, + { + "epoch": 0.49, + "learning_rate": 1.2130285981590433e-05, + "loss": 1.3479, + "step": 4658 + }, + { + "epoch": 0.49, + "learning_rate": 1.2126709606388181e-05, + "loss": 1.381, + "step": 4659 + }, + { + "epoch": 0.49, + "learning_rate": 1.2123132946261485e-05, + "loss": 1.3847, + "step": 4660 + }, + { + "epoch": 0.49, + "learning_rate": 1.2119556001689527e-05, + "loss": 1.3549, + "step": 4661 + }, + { + "epoch": 0.49, + "learning_rate": 1.2115978773151527e-05, + "loss": 1.3754, + "step": 4662 + }, + { + "epoch": 0.49, + "learning_rate": 1.2112401261126736e-05, + "loss": 1.3329, + "step": 4663 + }, + { + "epoch": 0.49, + "learning_rate": 1.2108823466094453e-05, + "loss": 1.4228, + "step": 4664 + }, + { + "epoch": 0.49, + "learning_rate": 1.2105245388534013e-05, + "loss": 1.4138, + "step": 4665 + }, + { + "epoch": 0.49, + "learning_rate": 1.2101667028924782e-05, + "loss": 1.3538, + "step": 4666 + }, + { + "epoch": 0.49, + "learning_rate": 1.2098088387746168e-05, + "loss": 1.4848, + "step": 4667 + }, + { + "epoch": 0.49, + "learning_rate": 1.2094509465477619e-05, + "loss": 1.5719, + "step": 4668 + }, + { + "epoch": 0.49, + "learning_rate": 1.209093026259862e-05, + "loss": 1.3863, + "step": 4669 + }, + { + "epoch": 0.49, + "learning_rate": 1.2087350779588691e-05, + "loss": 1.4425, + "step": 4670 + }, + { + "epoch": 0.49, + "learning_rate": 1.2083771016927386e-05, + "loss": 1.3655, + "step": 4671 + }, + { + "epoch": 0.49, + "learning_rate": 1.208019097509431e-05, + "loss": 1.3629, + "step": 4672 + }, + { + "epoch": 0.49, + "learning_rate": 1.2076610654569092e-05, + "loss": 1.3849, + "step": 4673 + }, + { + "epoch": 0.49, + "learning_rate": 1.20730300558314e-05, + "loss": 1.3763, + "step": 4674 + }, + { + "epoch": 0.49, + "learning_rate": 1.2069449179360945e-05, + "loss": 1.5316, + "step": 4675 + }, + { + "epoch": 0.49, + "learning_rate": 1.2065868025637476e-05, + "loss": 1.2873, + "step": 4676 + }, + { + "epoch": 0.49, + "learning_rate": 1.2062286595140773e-05, + "loss": 1.3642, + "step": 4677 + }, + { + "epoch": 0.49, + "learning_rate": 1.2058704888350652e-05, + "loss": 1.3782, + "step": 4678 + }, + { + "epoch": 0.49, + "learning_rate": 1.2055122905746972e-05, + "loss": 1.4597, + "step": 4679 + }, + { + "epoch": 0.49, + "learning_rate": 1.205154064780963e-05, + "loss": 1.3952, + "step": 4680 + }, + { + "epoch": 0.49, + "learning_rate": 1.2047958115018554e-05, + "loss": 1.4012, + "step": 4681 + }, + { + "epoch": 0.49, + "learning_rate": 1.204437530785371e-05, + "loss": 1.3432, + "step": 4682 + }, + { + "epoch": 0.49, + "learning_rate": 1.2040792226795101e-05, + "loss": 1.4111, + "step": 4683 + }, + { + "epoch": 0.49, + "learning_rate": 1.2037208872322773e-05, + "loss": 1.4357, + "step": 4684 + }, + { + "epoch": 0.49, + "learning_rate": 1.2033625244916803e-05, + "loss": 1.3908, + "step": 4685 + }, + { + "epoch": 0.49, + "learning_rate": 1.2030041345057298e-05, + "loss": 1.3804, + "step": 4686 + }, + { + "epoch": 0.49, + "learning_rate": 1.2026457173224412e-05, + "loss": 1.4523, + "step": 4687 + }, + { + "epoch": 0.49, + "learning_rate": 1.2022872729898336e-05, + "loss": 1.4266, + "step": 4688 + }, + { + "epoch": 0.49, + "learning_rate": 1.201928801555929e-05, + "loss": 1.3345, + "step": 4689 + }, + { + "epoch": 0.49, + "learning_rate": 1.2015703030687532e-05, + "loss": 1.1714, + "step": 4690 + }, + { + "epoch": 0.49, + "learning_rate": 1.2012117775763361e-05, + "loss": 1.3899, + "step": 4691 + }, + { + "epoch": 0.49, + "learning_rate": 1.2008532251267109e-05, + "loss": 1.43, + "step": 4692 + }, + { + "epoch": 0.49, + "learning_rate": 1.2004946457679144e-05, + "loss": 1.4302, + "step": 4693 + }, + { + "epoch": 0.49, + "learning_rate": 1.2001360395479865e-05, + "loss": 1.3452, + "step": 4694 + }, + { + "epoch": 0.49, + "learning_rate": 1.1997774065149716e-05, + "loss": 1.3383, + "step": 4695 + }, + { + "epoch": 0.49, + "learning_rate": 1.1994187467169176e-05, + "loss": 1.3677, + "step": 4696 + }, + { + "epoch": 0.49, + "learning_rate": 1.1990600602018755e-05, + "loss": 1.4486, + "step": 4697 + }, + { + "epoch": 0.49, + "learning_rate": 1.1987013470178998e-05, + "loss": 1.4059, + "step": 4698 + }, + { + "epoch": 0.49, + "learning_rate": 1.198342607213049e-05, + "loss": 1.3558, + "step": 4699 + }, + { + "epoch": 0.49, + "learning_rate": 1.1979838408353854e-05, + "loss": 1.3931, + "step": 4700 + }, + { + "epoch": 0.49, + "learning_rate": 1.197625047932974e-05, + "loss": 1.5409, + "step": 4701 + }, + { + "epoch": 0.49, + "learning_rate": 1.197266228553884e-05, + "loss": 1.4878, + "step": 4702 + }, + { + "epoch": 0.49, + "learning_rate": 1.196907382746188e-05, + "loss": 1.3581, + "step": 4703 + }, + { + "epoch": 0.49, + "learning_rate": 1.1965485105579621e-05, + "loss": 1.3617, + "step": 4704 + }, + { + "epoch": 0.49, + "learning_rate": 1.1961896120372857e-05, + "loss": 1.399, + "step": 4705 + }, + { + "epoch": 0.49, + "learning_rate": 1.1958306872322425e-05, + "loss": 1.3861, + "step": 4706 + }, + { + "epoch": 0.49, + "learning_rate": 1.1954717361909186e-05, + "loss": 1.4719, + "step": 4707 + }, + { + "epoch": 0.49, + "learning_rate": 1.195112758961405e-05, + "loss": 1.393, + "step": 4708 + }, + { + "epoch": 0.49, + "learning_rate": 1.1947537555917947e-05, + "loss": 1.4252, + "step": 4709 + }, + { + "epoch": 0.49, + "learning_rate": 1.194394726130185e-05, + "loss": 1.4187, + "step": 4710 + }, + { + "epoch": 0.49, + "learning_rate": 1.1940356706246772e-05, + "loss": 1.4822, + "step": 4711 + }, + { + "epoch": 0.49, + "learning_rate": 1.193676589123375e-05, + "loss": 1.4259, + "step": 4712 + }, + { + "epoch": 0.49, + "learning_rate": 1.1933174816743857e-05, + "loss": 1.4226, + "step": 4713 + }, + { + "epoch": 0.49, + "learning_rate": 1.1929583483258216e-05, + "loss": 1.3701, + "step": 4714 + }, + { + "epoch": 0.49, + "learning_rate": 1.1925991891257967e-05, + "loss": 1.406, + "step": 4715 + }, + { + "epoch": 0.49, + "learning_rate": 1.1922400041224288e-05, + "loss": 1.4593, + "step": 4716 + }, + { + "epoch": 0.49, + "learning_rate": 1.1918807933638401e-05, + "loss": 1.3443, + "step": 4717 + }, + { + "epoch": 0.49, + "learning_rate": 1.1915215568981552e-05, + "loss": 1.3523, + "step": 4718 + }, + { + "epoch": 0.49, + "learning_rate": 1.1911622947735027e-05, + "loss": 1.3175, + "step": 4719 + }, + { + "epoch": 0.49, + "learning_rate": 1.1908030070380143e-05, + "loss": 1.3974, + "step": 4720 + }, + { + "epoch": 0.5, + "learning_rate": 1.1904436937398257e-05, + "loss": 1.386, + "step": 4721 + }, + { + "epoch": 0.5, + "learning_rate": 1.1900843549270753e-05, + "loss": 1.3684, + "step": 4722 + }, + { + "epoch": 0.5, + "learning_rate": 1.1897249906479054e-05, + "loss": 1.383, + "step": 4723 + }, + { + "epoch": 0.5, + "learning_rate": 1.1893656009504617e-05, + "loss": 1.38, + "step": 4724 + }, + { + "epoch": 0.5, + "learning_rate": 1.1890061858828928e-05, + "loss": 1.3844, + "step": 4725 + }, + { + "epoch": 0.5, + "learning_rate": 1.1886467454933515e-05, + "loss": 1.3252, + "step": 4726 + }, + { + "epoch": 0.5, + "learning_rate": 1.1882872798299934e-05, + "loss": 1.3434, + "step": 4727 + }, + { + "epoch": 0.5, + "learning_rate": 1.1879277889409779e-05, + "loss": 1.4115, + "step": 4728 + }, + { + "epoch": 0.5, + "learning_rate": 1.1875682728744669e-05, + "loss": 1.1911, + "step": 4729 + }, + { + "epoch": 0.5, + "learning_rate": 1.1872087316786272e-05, + "loss": 1.2794, + "step": 4730 + }, + { + "epoch": 0.5, + "learning_rate": 1.1868491654016274e-05, + "loss": 1.3961, + "step": 4731 + }, + { + "epoch": 0.5, + "learning_rate": 1.1864895740916404e-05, + "loss": 1.4965, + "step": 4732 + }, + { + "epoch": 0.5, + "learning_rate": 1.1861299577968419e-05, + "loss": 1.3932, + "step": 4733 + }, + { + "epoch": 0.5, + "learning_rate": 1.185770316565412e-05, + "loss": 1.3926, + "step": 4734 + }, + { + "epoch": 0.5, + "learning_rate": 1.1854106504455327e-05, + "loss": 1.3964, + "step": 4735 + }, + { + "epoch": 0.5, + "learning_rate": 1.1850509594853901e-05, + "loss": 1.3666, + "step": 4736 + }, + { + "epoch": 0.5, + "learning_rate": 1.1846912437331736e-05, + "loss": 1.4364, + "step": 4737 + }, + { + "epoch": 0.5, + "learning_rate": 1.1843315032370762e-05, + "loss": 1.3537, + "step": 4738 + }, + { + "epoch": 0.5, + "learning_rate": 1.1839717380452935e-05, + "loss": 1.4083, + "step": 4739 + }, + { + "epoch": 0.5, + "learning_rate": 1.1836119482060247e-05, + "loss": 1.3881, + "step": 4740 + }, + { + "epoch": 0.5, + "learning_rate": 1.1832521337674727e-05, + "loss": 1.4127, + "step": 4741 + }, + { + "epoch": 0.5, + "learning_rate": 1.1828922947778436e-05, + "loss": 1.3433, + "step": 4742 + }, + { + "epoch": 0.5, + "learning_rate": 1.1825324312853461e-05, + "loss": 1.486, + "step": 4743 + }, + { + "epoch": 0.5, + "learning_rate": 1.1821725433381925e-05, + "loss": 1.335, + "step": 4744 + }, + { + "epoch": 0.5, + "learning_rate": 1.1818126309845993e-05, + "loss": 1.3827, + "step": 4745 + }, + { + "epoch": 0.5, + "learning_rate": 1.181452694272785e-05, + "loss": 1.3146, + "step": 4746 + }, + { + "epoch": 0.5, + "learning_rate": 1.1810927332509717e-05, + "loss": 1.3543, + "step": 4747 + }, + { + "epoch": 0.5, + "learning_rate": 1.1807327479673852e-05, + "loss": 1.3544, + "step": 4748 + }, + { + "epoch": 0.5, + "learning_rate": 1.1803727384702543e-05, + "loss": 1.3677, + "step": 4749 + }, + { + "epoch": 0.5, + "learning_rate": 1.1800127048078111e-05, + "loss": 1.3842, + "step": 4750 + }, + { + "epoch": 0.5, + "learning_rate": 1.1796526470282907e-05, + "loss": 1.3495, + "step": 4751 + }, + { + "epoch": 0.5, + "learning_rate": 1.1792925651799314e-05, + "loss": 1.481, + "step": 4752 + }, + { + "epoch": 0.5, + "learning_rate": 1.1789324593109754e-05, + "loss": 1.3482, + "step": 4753 + }, + { + "epoch": 0.5, + "learning_rate": 1.1785723294696673e-05, + "loss": 1.2805, + "step": 4754 + }, + { + "epoch": 0.5, + "learning_rate": 1.1782121757042555e-05, + "loss": 1.3458, + "step": 4755 + }, + { + "epoch": 0.5, + "learning_rate": 1.1778519980629907e-05, + "loss": 1.3937, + "step": 4756 + }, + { + "epoch": 0.5, + "learning_rate": 1.1774917965941284e-05, + "loss": 1.3873, + "step": 4757 + }, + { + "epoch": 0.5, + "learning_rate": 1.1771315713459258e-05, + "loss": 1.3512, + "step": 4758 + }, + { + "epoch": 0.5, + "learning_rate": 1.1767713223666436e-05, + "loss": 1.4465, + "step": 4759 + }, + { + "epoch": 0.5, + "learning_rate": 1.1764110497045463e-05, + "loss": 1.4233, + "step": 4760 + }, + { + "epoch": 0.5, + "learning_rate": 1.1760507534079011e-05, + "loss": 1.4818, + "step": 4761 + }, + { + "epoch": 0.5, + "learning_rate": 1.1756904335249786e-05, + "loss": 1.2933, + "step": 4762 + }, + { + "epoch": 0.5, + "learning_rate": 1.1753300901040518e-05, + "loss": 1.3524, + "step": 4763 + }, + { + "epoch": 0.5, + "learning_rate": 1.1749697231933981e-05, + "loss": 1.4909, + "step": 4764 + }, + { + "epoch": 0.5, + "learning_rate": 1.1746093328412975e-05, + "loss": 1.2912, + "step": 4765 + }, + { + "epoch": 0.5, + "learning_rate": 1.1742489190960325e-05, + "loss": 1.3372, + "step": 4766 + }, + { + "epoch": 0.5, + "learning_rate": 1.1738884820058893e-05, + "loss": 1.3036, + "step": 4767 + }, + { + "epoch": 0.5, + "learning_rate": 1.1735280216191578e-05, + "loss": 1.3189, + "step": 4768 + }, + { + "epoch": 0.5, + "learning_rate": 1.1731675379841298e-05, + "loss": 1.4146, + "step": 4769 + }, + { + "epoch": 0.5, + "learning_rate": 1.1728070311491013e-05, + "loss": 1.3309, + "step": 4770 + }, + { + "epoch": 0.5, + "learning_rate": 1.1724465011623705e-05, + "loss": 1.3427, + "step": 4771 + }, + { + "epoch": 0.5, + "learning_rate": 1.1720859480722395e-05, + "loss": 1.4033, + "step": 4772 + }, + { + "epoch": 0.5, + "learning_rate": 1.1717253719270135e-05, + "loss": 1.3832, + "step": 4773 + }, + { + "epoch": 0.5, + "learning_rate": 1.1713647727749994e-05, + "loss": 1.4074, + "step": 4774 + }, + { + "epoch": 0.5, + "learning_rate": 1.1710041506645092e-05, + "loss": 1.3579, + "step": 4775 + }, + { + "epoch": 0.5, + "learning_rate": 1.1706435056438564e-05, + "loss": 1.3685, + "step": 4776 + }, + { + "epoch": 0.5, + "eval_loss": 1.436767816543579, + "eval_runtime": 77.4332, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4776 + }, + { + "epoch": 0.5, + "learning_rate": 1.1702828377613584e-05, + "loss": 1.5843, + "step": 4777 + }, + { + "epoch": 0.5, + "learning_rate": 1.1699221470653355e-05, + "loss": 1.4168, + "step": 4778 + }, + { + "epoch": 0.5, + "learning_rate": 1.1695614336041108e-05, + "loss": 1.3515, + "step": 4779 + }, + { + "epoch": 0.5, + "learning_rate": 1.169200697426011e-05, + "loss": 1.3214, + "step": 4780 + }, + { + "epoch": 0.5, + "learning_rate": 1.1688399385793652e-05, + "loss": 1.3728, + "step": 4781 + }, + { + "epoch": 0.5, + "learning_rate": 1.1684791571125054e-05, + "loss": 1.3759, + "step": 4782 + }, + { + "epoch": 0.5, + "learning_rate": 1.1681183530737678e-05, + "loss": 1.4955, + "step": 4783 + }, + { + "epoch": 0.5, + "learning_rate": 1.1677575265114904e-05, + "loss": 1.4284, + "step": 4784 + }, + { + "epoch": 0.5, + "learning_rate": 1.1673966774740151e-05, + "loss": 1.3725, + "step": 4785 + }, + { + "epoch": 0.5, + "learning_rate": 1.1670358060096858e-05, + "loss": 1.3612, + "step": 4786 + }, + { + "epoch": 0.5, + "learning_rate": 1.1666749121668506e-05, + "loss": 1.3021, + "step": 4787 + }, + { + "epoch": 0.5, + "learning_rate": 1.1663139959938597e-05, + "loss": 1.4399, + "step": 4788 + }, + { + "epoch": 0.5, + "learning_rate": 1.1659530575390668e-05, + "loss": 1.3511, + "step": 4789 + }, + { + "epoch": 0.5, + "learning_rate": 1.1655920968508276e-05, + "loss": 1.4211, + "step": 4790 + }, + { + "epoch": 0.5, + "learning_rate": 1.1652311139775028e-05, + "loss": 1.343, + "step": 4791 + }, + { + "epoch": 0.5, + "learning_rate": 1.1648701089674541e-05, + "loss": 1.3838, + "step": 4792 + }, + { + "epoch": 0.5, + "learning_rate": 1.164509081869047e-05, + "loss": 1.342, + "step": 4793 + }, + { + "epoch": 0.5, + "learning_rate": 1.1641480327306494e-05, + "loss": 1.3831, + "step": 4794 + }, + { + "epoch": 0.5, + "learning_rate": 1.1637869616006335e-05, + "loss": 1.4102, + "step": 4795 + }, + { + "epoch": 0.5, + "learning_rate": 1.1634258685273732e-05, + "loss": 1.4184, + "step": 4796 + }, + { + "epoch": 0.5, + "learning_rate": 1.1630647535592455e-05, + "loss": 1.3974, + "step": 4797 + }, + { + "epoch": 0.5, + "learning_rate": 1.1627036167446302e-05, + "loss": 1.251, + "step": 4798 + }, + { + "epoch": 0.5, + "learning_rate": 1.1623424581319113e-05, + "loss": 1.3485, + "step": 4799 + }, + { + "epoch": 0.5, + "learning_rate": 1.1619812777694742e-05, + "loss": 1.3544, + "step": 4800 + }, + { + "epoch": 0.5, + "learning_rate": 1.1616200757057076e-05, + "loss": 1.3772, + "step": 4801 + }, + { + "epoch": 0.5, + "learning_rate": 1.1612588519890038e-05, + "loss": 1.3082, + "step": 4802 + }, + { + "epoch": 0.5, + "learning_rate": 1.160897606667757e-05, + "loss": 1.3634, + "step": 4803 + }, + { + "epoch": 0.5, + "learning_rate": 1.1605363397903655e-05, + "loss": 1.3682, + "step": 4804 + }, + { + "epoch": 0.5, + "learning_rate": 1.1601750514052288e-05, + "loss": 1.3258, + "step": 4805 + }, + { + "epoch": 0.5, + "learning_rate": 1.1598137415607511e-05, + "loss": 1.279, + "step": 4806 + }, + { + "epoch": 0.5, + "learning_rate": 1.1594524103053382e-05, + "loss": 1.3759, + "step": 4807 + }, + { + "epoch": 0.5, + "learning_rate": 1.1590910576873995e-05, + "loss": 1.5404, + "step": 4808 + }, + { + "epoch": 0.5, + "learning_rate": 1.1587296837553463e-05, + "loss": 1.4949, + "step": 4809 + }, + { + "epoch": 0.5, + "learning_rate": 1.1583682885575943e-05, + "loss": 1.3501, + "step": 4810 + }, + { + "epoch": 0.5, + "learning_rate": 1.1580068721425608e-05, + "loss": 1.3898, + "step": 4811 + }, + { + "epoch": 0.5, + "learning_rate": 1.157645434558666e-05, + "loss": 1.3265, + "step": 4812 + }, + { + "epoch": 0.5, + "learning_rate": 1.1572839758543338e-05, + "loss": 1.3454, + "step": 4813 + }, + { + "epoch": 0.5, + "learning_rate": 1.1569224960779899e-05, + "loss": 1.4065, + "step": 4814 + }, + { + "epoch": 0.5, + "learning_rate": 1.156560995278064e-05, + "loss": 1.4932, + "step": 4815 + }, + { + "epoch": 0.51, + "learning_rate": 1.156199473502987e-05, + "loss": 1.4224, + "step": 4816 + }, + { + "epoch": 0.51, + "learning_rate": 1.1558379308011937e-05, + "loss": 1.3884, + "step": 4817 + }, + { + "epoch": 0.51, + "learning_rate": 1.1554763672211222e-05, + "loss": 1.3355, + "step": 4818 + }, + { + "epoch": 0.51, + "learning_rate": 1.1551147828112124e-05, + "loss": 1.4281, + "step": 4819 + }, + { + "epoch": 0.51, + "learning_rate": 1.1547531776199072e-05, + "loss": 1.3148, + "step": 4820 + }, + { + "epoch": 0.51, + "learning_rate": 1.1543915516956523e-05, + "loss": 1.3255, + "step": 4821 + }, + { + "epoch": 0.51, + "learning_rate": 1.1540299050868966e-05, + "loss": 1.3361, + "step": 4822 + }, + { + "epoch": 0.51, + "learning_rate": 1.1536682378420912e-05, + "loss": 1.3377, + "step": 4823 + }, + { + "epoch": 0.51, + "learning_rate": 1.1533065500096901e-05, + "loss": 1.4205, + "step": 4824 + }, + { + "epoch": 0.51, + "learning_rate": 1.1529448416381505e-05, + "loss": 1.4193, + "step": 4825 + }, + { + "epoch": 0.51, + "learning_rate": 1.1525831127759322e-05, + "loss": 1.37, + "step": 4826 + }, + { + "epoch": 0.51, + "learning_rate": 1.1522213634714971e-05, + "loss": 1.3642, + "step": 4827 + }, + { + "epoch": 0.51, + "learning_rate": 1.1518595937733103e-05, + "loss": 1.4834, + "step": 4828 + }, + { + "epoch": 0.51, + "learning_rate": 1.1514978037298402e-05, + "loss": 1.2864, + "step": 4829 + }, + { + "epoch": 0.51, + "learning_rate": 1.1511359933895567e-05, + "loss": 1.3468, + "step": 4830 + }, + { + "epoch": 0.51, + "learning_rate": 1.1507741628009337e-05, + "loss": 1.328, + "step": 4831 + }, + { + "epoch": 0.51, + "learning_rate": 1.1504123120124466e-05, + "loss": 1.3489, + "step": 4832 + }, + { + "epoch": 0.51, + "learning_rate": 1.1500504410725746e-05, + "loss": 1.4031, + "step": 4833 + }, + { + "epoch": 0.51, + "learning_rate": 1.149688550029799e-05, + "loss": 1.3482, + "step": 4834 + }, + { + "epoch": 0.51, + "learning_rate": 1.1493266389326037e-05, + "loss": 1.3674, + "step": 4835 + }, + { + "epoch": 0.51, + "learning_rate": 1.1489647078294753e-05, + "loss": 1.2895, + "step": 4836 + }, + { + "epoch": 0.51, + "learning_rate": 1.148602756768904e-05, + "loss": 1.4071, + "step": 4837 + }, + { + "epoch": 0.51, + "learning_rate": 1.1482407857993814e-05, + "loss": 1.5218, + "step": 4838 + }, + { + "epoch": 0.51, + "learning_rate": 1.1478787949694024e-05, + "loss": 1.4577, + "step": 4839 + }, + { + "epoch": 0.51, + "learning_rate": 1.1475167843274643e-05, + "loss": 1.3817, + "step": 4840 + }, + { + "epoch": 0.51, + "learning_rate": 1.1471547539220678e-05, + "loss": 1.3072, + "step": 4841 + }, + { + "epoch": 0.51, + "learning_rate": 1.146792703801715e-05, + "loss": 1.3737, + "step": 4842 + }, + { + "epoch": 0.51, + "learning_rate": 1.1464306340149119e-05, + "loss": 1.4001, + "step": 4843 + }, + { + "epoch": 0.51, + "learning_rate": 1.1460685446101658e-05, + "loss": 1.3963, + "step": 4844 + }, + { + "epoch": 0.51, + "learning_rate": 1.1457064356359882e-05, + "loss": 1.4061, + "step": 4845 + }, + { + "epoch": 0.51, + "learning_rate": 1.145344307140892e-05, + "loss": 1.4211, + "step": 4846 + }, + { + "epoch": 0.51, + "learning_rate": 1.144982159173393e-05, + "loss": 1.3197, + "step": 4847 + }, + { + "epoch": 0.51, + "learning_rate": 1.14461999178201e-05, + "loss": 1.3549, + "step": 4848 + }, + { + "epoch": 0.51, + "learning_rate": 1.1442578050152639e-05, + "loss": 1.3889, + "step": 4849 + }, + { + "epoch": 0.51, + "learning_rate": 1.1438955989216787e-05, + "loss": 1.3847, + "step": 4850 + }, + { + "epoch": 0.51, + "learning_rate": 1.1435333735497803e-05, + "loss": 1.3586, + "step": 4851 + }, + { + "epoch": 0.51, + "learning_rate": 1.1431711289480978e-05, + "loss": 1.503, + "step": 4852 + }, + { + "epoch": 0.51, + "learning_rate": 1.1428088651651627e-05, + "loss": 1.3654, + "step": 4853 + }, + { + "epoch": 0.51, + "learning_rate": 1.1424465822495092e-05, + "loss": 1.3741, + "step": 4854 + }, + { + "epoch": 0.51, + "learning_rate": 1.1420842802496737e-05, + "loss": 1.5437, + "step": 4855 + }, + { + "epoch": 0.51, + "learning_rate": 1.1417219592141953e-05, + "loss": 1.2179, + "step": 4856 + }, + { + "epoch": 0.51, + "learning_rate": 1.1413596191916159e-05, + "loss": 1.3939, + "step": 4857 + }, + { + "epoch": 0.51, + "learning_rate": 1.1409972602304796e-05, + "loss": 1.3383, + "step": 4858 + }, + { + "epoch": 0.51, + "learning_rate": 1.140634882379333e-05, + "loss": 1.3664, + "step": 4859 + }, + { + "epoch": 0.51, + "learning_rate": 1.1402724856867258e-05, + "loss": 1.4002, + "step": 4860 + }, + { + "epoch": 0.51, + "learning_rate": 1.1399100702012098e-05, + "loss": 1.2975, + "step": 4861 + }, + { + "epoch": 0.51, + "learning_rate": 1.1395476359713394e-05, + "loss": 1.3564, + "step": 4862 + }, + { + "epoch": 0.51, + "learning_rate": 1.1391851830456708e-05, + "loss": 1.3574, + "step": 4863 + }, + { + "epoch": 0.51, + "learning_rate": 1.1388227114727644e-05, + "loss": 1.3407, + "step": 4864 + }, + { + "epoch": 0.51, + "learning_rate": 1.1384602213011815e-05, + "loss": 1.3603, + "step": 4865 + }, + { + "epoch": 0.51, + "learning_rate": 1.1380977125794866e-05, + "loss": 1.3465, + "step": 4866 + }, + { + "epoch": 0.51, + "learning_rate": 1.1377351853562461e-05, + "loss": 1.3744, + "step": 4867 + }, + { + "epoch": 0.51, + "learning_rate": 1.1373726396800304e-05, + "loss": 1.3248, + "step": 4868 + }, + { + "epoch": 0.51, + "learning_rate": 1.1370100755994102e-05, + "loss": 1.3352, + "step": 4869 + }, + { + "epoch": 0.51, + "learning_rate": 1.1366474931629603e-05, + "loss": 1.3299, + "step": 4870 + }, + { + "epoch": 0.51, + "learning_rate": 1.1362848924192575e-05, + "loss": 1.344, + "step": 4871 + }, + { + "epoch": 0.51, + "learning_rate": 1.1359222734168809e-05, + "loss": 1.3209, + "step": 4872 + }, + { + "epoch": 0.51, + "learning_rate": 1.135559636204412e-05, + "loss": 1.3927, + "step": 4873 + }, + { + "epoch": 0.51, + "learning_rate": 1.1351969808304349e-05, + "loss": 1.3717, + "step": 4874 + }, + { + "epoch": 0.51, + "learning_rate": 1.1348343073435362e-05, + "loss": 1.3813, + "step": 4875 + }, + { + "epoch": 0.51, + "learning_rate": 1.1344716157923046e-05, + "loss": 1.236, + "step": 4876 + }, + { + "epoch": 0.51, + "learning_rate": 1.1341089062253319e-05, + "loss": 1.2591, + "step": 4877 + }, + { + "epoch": 0.51, + "learning_rate": 1.1337461786912112e-05, + "loss": 1.3211, + "step": 4878 + }, + { + "epoch": 0.51, + "learning_rate": 1.1333834332385394e-05, + "loss": 1.4534, + "step": 4879 + }, + { + "epoch": 0.51, + "learning_rate": 1.1330206699159145e-05, + "loss": 1.346, + "step": 4880 + }, + { + "epoch": 0.51, + "learning_rate": 1.132657888771938e-05, + "loss": 1.3952, + "step": 4881 + }, + { + "epoch": 0.51, + "learning_rate": 1.1322950898552125e-05, + "loss": 1.3008, + "step": 4882 + }, + { + "epoch": 0.51, + "learning_rate": 1.1319322732143445e-05, + "loss": 1.3201, + "step": 4883 + }, + { + "epoch": 0.51, + "learning_rate": 1.1315694388979416e-05, + "loss": 1.3761, + "step": 4884 + }, + { + "epoch": 0.51, + "learning_rate": 1.1312065869546147e-05, + "loss": 1.343, + "step": 4885 + }, + { + "epoch": 0.51, + "learning_rate": 1.1308437174329761e-05, + "loss": 1.3741, + "step": 4886 + }, + { + "epoch": 0.51, + "learning_rate": 1.1304808303816413e-05, + "loss": 1.402, + "step": 4887 + }, + { + "epoch": 0.51, + "learning_rate": 1.130117925849228e-05, + "loss": 1.3834, + "step": 4888 + }, + { + "epoch": 0.51, + "learning_rate": 1.1297550038843559e-05, + "loss": 1.3342, + "step": 4889 + }, + { + "epoch": 0.51, + "learning_rate": 1.1293920645356471e-05, + "loss": 1.3207, + "step": 4890 + }, + { + "epoch": 0.51, + "learning_rate": 1.1290291078517264e-05, + "loss": 1.4274, + "step": 4891 + }, + { + "epoch": 0.51, + "learning_rate": 1.1286661338812203e-05, + "loss": 1.328, + "step": 4892 + }, + { + "epoch": 0.51, + "learning_rate": 1.1283031426727584e-05, + "loss": 1.3823, + "step": 4893 + }, + { + "epoch": 0.51, + "learning_rate": 1.127940134274972e-05, + "loss": 1.3612, + "step": 4894 + }, + { + "epoch": 0.51, + "learning_rate": 1.127577108736495e-05, + "loss": 1.375, + "step": 4895 + }, + { + "epoch": 0.51, + "learning_rate": 1.1272140661059636e-05, + "loss": 1.3531, + "step": 4896 + }, + { + "epoch": 0.51, + "learning_rate": 1.1268510064320155e-05, + "loss": 1.3636, + "step": 4897 + }, + { + "epoch": 0.51, + "learning_rate": 1.1264879297632923e-05, + "loss": 1.3524, + "step": 4898 + }, + { + "epoch": 0.51, + "learning_rate": 1.1261248361484363e-05, + "loss": 1.3865, + "step": 4899 + }, + { + "epoch": 0.51, + "learning_rate": 1.125761725636093e-05, + "loss": 1.4069, + "step": 4900 + }, + { + "epoch": 0.51, + "learning_rate": 1.1253985982749098e-05, + "loss": 1.4643, + "step": 4901 + }, + { + "epoch": 0.51, + "learning_rate": 1.1250354541135364e-05, + "loss": 1.4506, + "step": 4902 + }, + { + "epoch": 0.51, + "learning_rate": 1.124672293200625e-05, + "loss": 1.3857, + "step": 4903 + }, + { + "epoch": 0.51, + "learning_rate": 1.1243091155848295e-05, + "loss": 1.3554, + "step": 4904 + }, + { + "epoch": 0.51, + "learning_rate": 1.1239459213148065e-05, + "loss": 1.4071, + "step": 4905 + }, + { + "epoch": 0.51, + "learning_rate": 1.1235827104392148e-05, + "loss": 1.3981, + "step": 4906 + }, + { + "epoch": 0.51, + "learning_rate": 1.1232194830067153e-05, + "loss": 1.4913, + "step": 4907 + }, + { + "epoch": 0.51, + "learning_rate": 1.1228562390659712e-05, + "loss": 1.3343, + "step": 4908 + }, + { + "epoch": 0.51, + "learning_rate": 1.1224929786656474e-05, + "loss": 1.3832, + "step": 4909 + }, + { + "epoch": 0.51, + "learning_rate": 1.122129701854412e-05, + "loss": 1.367, + "step": 4910 + }, + { + "epoch": 0.51, + "learning_rate": 1.1217664086809345e-05, + "loss": 1.4108, + "step": 4911 + }, + { + "epoch": 0.52, + "learning_rate": 1.1214030991938872e-05, + "loss": 1.3981, + "step": 4912 + }, + { + "epoch": 0.52, + "learning_rate": 1.1210397734419436e-05, + "loss": 1.5266, + "step": 4913 + }, + { + "epoch": 0.52, + "learning_rate": 1.1206764314737806e-05, + "loss": 1.337, + "step": 4914 + }, + { + "epoch": 0.52, + "learning_rate": 1.1203130733380765e-05, + "loss": 1.3784, + "step": 4915 + }, + { + "epoch": 0.52, + "learning_rate": 1.1199496990835117e-05, + "loss": 1.3048, + "step": 4916 + }, + { + "epoch": 0.52, + "learning_rate": 1.1195863087587692e-05, + "loss": 1.2977, + "step": 4917 + }, + { + "epoch": 0.52, + "learning_rate": 1.1192229024125344e-05, + "loss": 1.3304, + "step": 4918 + }, + { + "epoch": 0.52, + "learning_rate": 1.1188594800934938e-05, + "loss": 1.4102, + "step": 4919 + }, + { + "epoch": 0.52, + "learning_rate": 1.1184960418503366e-05, + "loss": 1.3932, + "step": 4920 + }, + { + "epoch": 0.52, + "learning_rate": 1.1181325877317547e-05, + "loss": 1.4985, + "step": 4921 + }, + { + "epoch": 0.52, + "learning_rate": 1.1177691177864415e-05, + "loss": 1.4596, + "step": 4922 + }, + { + "epoch": 0.52, + "learning_rate": 1.1174056320630924e-05, + "loss": 1.3559, + "step": 4923 + }, + { + "epoch": 0.52, + "learning_rate": 1.117042130610405e-05, + "loss": 1.4128, + "step": 4924 + }, + { + "epoch": 0.52, + "learning_rate": 1.1166786134770795e-05, + "loss": 1.3343, + "step": 4925 + }, + { + "epoch": 0.52, + "learning_rate": 1.116315080711818e-05, + "loss": 1.332, + "step": 4926 + }, + { + "epoch": 0.52, + "learning_rate": 1.115951532363324e-05, + "loss": 1.3616, + "step": 4927 + }, + { + "epoch": 0.52, + "learning_rate": 1.1155879684803041e-05, + "loss": 1.4074, + "step": 4928 + }, + { + "epoch": 0.52, + "learning_rate": 1.1152243891114665e-05, + "loss": 1.303, + "step": 4929 + }, + { + "epoch": 0.52, + "learning_rate": 1.1148607943055212e-05, + "loss": 1.4799, + "step": 4930 + }, + { + "epoch": 0.52, + "learning_rate": 1.1144971841111807e-05, + "loss": 1.3881, + "step": 4931 + }, + { + "epoch": 0.52, + "learning_rate": 1.1141335585771593e-05, + "loss": 1.338, + "step": 4932 + }, + { + "epoch": 0.52, + "learning_rate": 1.1137699177521738e-05, + "loss": 1.3289, + "step": 4933 + }, + { + "epoch": 0.52, + "learning_rate": 1.1134062616849426e-05, + "loss": 1.377, + "step": 4934 + }, + { + "epoch": 0.52, + "learning_rate": 1.1130425904241862e-05, + "loss": 1.3596, + "step": 4935 + }, + { + "epoch": 0.52, + "learning_rate": 1.112678904018627e-05, + "loss": 1.4264, + "step": 4936 + }, + { + "epoch": 0.52, + "learning_rate": 1.1123152025169898e-05, + "loss": 1.3526, + "step": 4937 + }, + { + "epoch": 0.52, + "learning_rate": 1.1119514859680016e-05, + "loss": 1.3271, + "step": 4938 + }, + { + "epoch": 0.52, + "learning_rate": 1.1115877544203905e-05, + "loss": 1.3907, + "step": 4939 + }, + { + "epoch": 0.52, + "learning_rate": 1.1112240079228878e-05, + "loss": 1.3415, + "step": 4940 + }, + { + "epoch": 0.52, + "learning_rate": 1.1108602465242258e-05, + "loss": 1.3875, + "step": 4941 + }, + { + "epoch": 0.52, + "learning_rate": 1.110496470273139e-05, + "loss": 1.3964, + "step": 4942 + }, + { + "epoch": 0.52, + "learning_rate": 1.1101326792183645e-05, + "loss": 1.3448, + "step": 4943 + }, + { + "epoch": 0.52, + "learning_rate": 1.1097688734086407e-05, + "loss": 1.3522, + "step": 4944 + }, + { + "epoch": 0.52, + "learning_rate": 1.1094050528927082e-05, + "loss": 1.2742, + "step": 4945 + }, + { + "epoch": 0.52, + "learning_rate": 1.1090412177193097e-05, + "loss": 1.417, + "step": 4946 + }, + { + "epoch": 0.52, + "learning_rate": 1.1086773679371898e-05, + "loss": 1.3993, + "step": 4947 + }, + { + "epoch": 0.52, + "learning_rate": 1.108313503595095e-05, + "loss": 1.3783, + "step": 4948 + }, + { + "epoch": 0.52, + "learning_rate": 1.1079496247417736e-05, + "loss": 1.3975, + "step": 4949 + }, + { + "epoch": 0.52, + "learning_rate": 1.1075857314259763e-05, + "loss": 1.4256, + "step": 4950 + }, + { + "epoch": 0.52, + "learning_rate": 1.1072218236964551e-05, + "loss": 1.3547, + "step": 4951 + }, + { + "epoch": 0.52, + "learning_rate": 1.106857901601965e-05, + "loss": 1.4243, + "step": 4952 + }, + { + "epoch": 0.52, + "learning_rate": 1.1064939651912612e-05, + "loss": 1.4259, + "step": 4953 + }, + { + "epoch": 0.52, + "learning_rate": 1.1061300145131027e-05, + "loss": 1.4323, + "step": 4954 + }, + { + "epoch": 0.52, + "learning_rate": 1.1057660496162488e-05, + "loss": 1.3608, + "step": 4955 + }, + { + "epoch": 0.52, + "learning_rate": 1.1054020705494622e-05, + "loss": 1.3703, + "step": 4956 + }, + { + "epoch": 0.52, + "learning_rate": 1.105038077361506e-05, + "loss": 1.3953, + "step": 4957 + }, + { + "epoch": 0.52, + "learning_rate": 1.1046740701011467e-05, + "loss": 1.392, + "step": 4958 + }, + { + "epoch": 0.52, + "learning_rate": 1.1043100488171513e-05, + "loss": 1.4101, + "step": 4959 + }, + { + "epoch": 0.52, + "learning_rate": 1.1039460135582894e-05, + "loss": 1.5432, + "step": 4960 + }, + { + "epoch": 0.52, + "learning_rate": 1.1035819643733326e-05, + "loss": 1.3822, + "step": 4961 + }, + { + "epoch": 0.52, + "learning_rate": 1.103217901311054e-05, + "loss": 1.3816, + "step": 4962 + }, + { + "epoch": 0.52, + "learning_rate": 1.1028538244202287e-05, + "loss": 1.3137, + "step": 4963 + }, + { + "epoch": 0.52, + "learning_rate": 1.102489733749634e-05, + "loss": 1.3791, + "step": 4964 + }, + { + "epoch": 0.52, + "learning_rate": 1.102125629348048e-05, + "loss": 1.3751, + "step": 4965 + }, + { + "epoch": 0.52, + "learning_rate": 1.1017615112642518e-05, + "loss": 1.3287, + "step": 4966 + }, + { + "epoch": 0.52, + "learning_rate": 1.1013973795470277e-05, + "loss": 1.3187, + "step": 4967 + }, + { + "epoch": 0.52, + "learning_rate": 1.1010332342451602e-05, + "loss": 1.3174, + "step": 4968 + }, + { + "epoch": 0.52, + "learning_rate": 1.1006690754074351e-05, + "loss": 1.3544, + "step": 4969 + }, + { + "epoch": 0.52, + "learning_rate": 1.1003049030826404e-05, + "loss": 1.3789, + "step": 4970 + }, + { + "epoch": 0.52, + "learning_rate": 1.0999407173195662e-05, + "loss": 1.4561, + "step": 4971 + }, + { + "epoch": 0.52, + "learning_rate": 1.0995765181670039e-05, + "loss": 1.3963, + "step": 4972 + }, + { + "epoch": 0.52, + "learning_rate": 1.0992123056737464e-05, + "loss": 1.3519, + "step": 4973 + }, + { + "epoch": 0.52, + "learning_rate": 1.0988480798885892e-05, + "loss": 1.3945, + "step": 4974 + }, + { + "epoch": 0.52, + "learning_rate": 1.0984838408603294e-05, + "loss": 1.4572, + "step": 4975 + }, + { + "epoch": 0.52, + "eval_loss": 1.4313459396362305, + "eval_runtime": 77.4808, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 4975 + }, + { + "epoch": 0.52, + "learning_rate": 1.0981195886377652e-05, + "loss": 1.3493, + "step": 4976 + }, + { + "epoch": 0.52, + "learning_rate": 1.0977553232696972e-05, + "loss": 1.3734, + "step": 4977 + }, + { + "epoch": 0.52, + "learning_rate": 1.0973910448049273e-05, + "loss": 1.3484, + "step": 4978 + }, + { + "epoch": 0.52, + "learning_rate": 1.09702675329226e-05, + "loss": 1.4288, + "step": 4979 + }, + { + "epoch": 0.52, + "learning_rate": 1.096662448780501e-05, + "loss": 1.3748, + "step": 4980 + }, + { + "epoch": 0.52, + "learning_rate": 1.0962981313184575e-05, + "loss": 1.3485, + "step": 4981 + }, + { + "epoch": 0.52, + "learning_rate": 1.0959338009549383e-05, + "loss": 1.3606, + "step": 4982 + }, + { + "epoch": 0.52, + "learning_rate": 1.095569457738755e-05, + "loss": 1.3963, + "step": 4983 + }, + { + "epoch": 0.52, + "learning_rate": 1.09520510171872e-05, + "loss": 1.2986, + "step": 4984 + }, + { + "epoch": 0.52, + "learning_rate": 1.0948407329436474e-05, + "loss": 1.3505, + "step": 4985 + }, + { + "epoch": 0.52, + "learning_rate": 1.0944763514623535e-05, + "loss": 1.4649, + "step": 4986 + }, + { + "epoch": 0.52, + "learning_rate": 1.0941119573236564e-05, + "loss": 1.4743, + "step": 4987 + }, + { + "epoch": 0.52, + "learning_rate": 1.0937475505763745e-05, + "loss": 1.3934, + "step": 4988 + }, + { + "epoch": 0.52, + "learning_rate": 1.09338313126933e-05, + "loss": 1.4225, + "step": 4989 + }, + { + "epoch": 0.52, + "learning_rate": 1.0930186994513453e-05, + "loss": 1.3626, + "step": 4990 + }, + { + "epoch": 0.52, + "learning_rate": 1.0926542551712446e-05, + "loss": 1.3614, + "step": 4991 + }, + { + "epoch": 0.52, + "learning_rate": 1.0922897984778546e-05, + "loss": 1.3766, + "step": 4992 + }, + { + "epoch": 0.52, + "learning_rate": 1.0919253294200027e-05, + "loss": 1.3295, + "step": 4993 + }, + { + "epoch": 0.52, + "learning_rate": 1.091560848046519e-05, + "loss": 1.3802, + "step": 4994 + }, + { + "epoch": 0.52, + "learning_rate": 1.091196354406234e-05, + "loss": 1.2976, + "step": 4995 + }, + { + "epoch": 0.52, + "learning_rate": 1.090831848547981e-05, + "loss": 1.3928, + "step": 4996 + }, + { + "epoch": 0.52, + "learning_rate": 1.0904673305205937e-05, + "loss": 1.3717, + "step": 4997 + }, + { + "epoch": 0.52, + "learning_rate": 1.0901028003729089e-05, + "loss": 1.3164, + "step": 4998 + }, + { + "epoch": 0.52, + "learning_rate": 1.0897382581537638e-05, + "loss": 1.3462, + "step": 4999 + }, + { + "epoch": 0.52, + "learning_rate": 1.0893737039119981e-05, + "loss": 1.3643, + "step": 5000 + }, + { + "epoch": 0.52, + "learning_rate": 1.089009137696452e-05, + "loss": 1.3452, + "step": 5001 + }, + { + "epoch": 0.52, + "learning_rate": 1.0886445595559686e-05, + "loss": 1.358, + "step": 5002 + }, + { + "epoch": 0.52, + "learning_rate": 1.0882799695393922e-05, + "loss": 1.4569, + "step": 5003 + }, + { + "epoch": 0.52, + "learning_rate": 1.0879153676955681e-05, + "loss": 1.2832, + "step": 5004 + }, + { + "epoch": 0.52, + "learning_rate": 1.0875507540733435e-05, + "loss": 1.4089, + "step": 5005 + }, + { + "epoch": 0.52, + "learning_rate": 1.087186128721567e-05, + "loss": 1.3178, + "step": 5006 + }, + { + "epoch": 0.53, + "learning_rate": 1.0868214916890902e-05, + "loss": 1.4883, + "step": 5007 + }, + { + "epoch": 0.53, + "learning_rate": 1.0864568430247638e-05, + "loss": 1.3991, + "step": 5008 + }, + { + "epoch": 0.53, + "learning_rate": 1.0860921827774422e-05, + "loss": 1.4507, + "step": 5009 + }, + { + "epoch": 0.53, + "learning_rate": 1.08572751099598e-05, + "loss": 1.3578, + "step": 5010 + }, + { + "epoch": 0.53, + "learning_rate": 1.0853628277292341e-05, + "loss": 1.4231, + "step": 5011 + }, + { + "epoch": 0.53, + "learning_rate": 1.0849981330260624e-05, + "loss": 1.4835, + "step": 5012 + }, + { + "epoch": 0.53, + "learning_rate": 1.084633426935325e-05, + "loss": 1.4511, + "step": 5013 + }, + { + "epoch": 0.53, + "learning_rate": 1.084268709505883e-05, + "loss": 1.3889, + "step": 5014 + }, + { + "epoch": 0.53, + "learning_rate": 1.0839039807865992e-05, + "loss": 1.355, + "step": 5015 + }, + { + "epoch": 0.53, + "learning_rate": 1.0835392408263375e-05, + "loss": 1.4829, + "step": 5016 + }, + { + "epoch": 0.53, + "learning_rate": 1.0831744896739643e-05, + "loss": 1.3019, + "step": 5017 + }, + { + "epoch": 0.53, + "learning_rate": 1.0828097273783465e-05, + "loss": 1.3418, + "step": 5018 + }, + { + "epoch": 0.53, + "learning_rate": 1.082444953988353e-05, + "loss": 1.4276, + "step": 5019 + }, + { + "epoch": 0.53, + "learning_rate": 1.0820801695528537e-05, + "loss": 1.2816, + "step": 5020 + }, + { + "epoch": 0.53, + "learning_rate": 1.081715374120721e-05, + "loss": 1.5144, + "step": 5021 + }, + { + "epoch": 0.53, + "learning_rate": 1.0813505677408278e-05, + "loss": 1.4063, + "step": 5022 + }, + { + "epoch": 0.53, + "learning_rate": 1.0809857504620487e-05, + "loss": 1.4011, + "step": 5023 + }, + { + "epoch": 0.53, + "learning_rate": 1.0806209223332598e-05, + "loss": 1.373, + "step": 5024 + }, + { + "epoch": 0.53, + "learning_rate": 1.0802560834033388e-05, + "loss": 1.6259, + "step": 5025 + }, + { + "epoch": 0.53, + "learning_rate": 1.0798912337211648e-05, + "loss": 1.4487, + "step": 5026 + }, + { + "epoch": 0.53, + "learning_rate": 1.0795263733356184e-05, + "loss": 1.3056, + "step": 5027 + }, + { + "epoch": 0.53, + "learning_rate": 1.079161502295581e-05, + "loss": 1.2871, + "step": 5028 + }, + { + "epoch": 0.53, + "learning_rate": 1.0787966206499363e-05, + "loss": 1.413, + "step": 5029 + }, + { + "epoch": 0.53, + "learning_rate": 1.0784317284475694e-05, + "loss": 1.3682, + "step": 5030 + }, + { + "epoch": 0.53, + "learning_rate": 1.0780668257373659e-05, + "loss": 1.493, + "step": 5031 + }, + { + "epoch": 0.53, + "learning_rate": 1.0777019125682136e-05, + "loss": 1.6823, + "step": 5032 + }, + { + "epoch": 0.53, + "learning_rate": 1.0773369889890015e-05, + "loss": 1.358, + "step": 5033 + }, + { + "epoch": 0.53, + "learning_rate": 1.07697205504862e-05, + "loss": 1.3532, + "step": 5034 + }, + { + "epoch": 0.53, + "learning_rate": 1.0766071107959608e-05, + "loss": 1.3432, + "step": 5035 + }, + { + "epoch": 0.53, + "learning_rate": 1.0762421562799173e-05, + "loss": 1.3575, + "step": 5036 + }, + { + "epoch": 0.53, + "learning_rate": 1.0758771915493838e-05, + "loss": 1.0924, + "step": 5037 + }, + { + "epoch": 0.53, + "learning_rate": 1.075512216653256e-05, + "loss": 0.7405, + "step": 5038 + }, + { + "epoch": 0.53, + "learning_rate": 1.0751472316404315e-05, + "loss": 0.7134, + "step": 5039 + }, + { + "epoch": 0.53, + "learning_rate": 1.0747822365598088e-05, + "loss": 1.0904, + "step": 5040 + }, + { + "epoch": 0.53, + "learning_rate": 1.0744172314602881e-05, + "loss": 1.4353, + "step": 5041 + }, + { + "epoch": 0.53, + "learning_rate": 1.0740522163907702e-05, + "loss": 1.361, + "step": 5042 + }, + { + "epoch": 0.53, + "learning_rate": 1.073687191400158e-05, + "loss": 1.4024, + "step": 5043 + }, + { + "epoch": 0.53, + "learning_rate": 1.0733221565373557e-05, + "loss": 1.328, + "step": 5044 + }, + { + "epoch": 0.53, + "learning_rate": 1.0729571118512683e-05, + "loss": 1.3309, + "step": 5045 + }, + { + "epoch": 0.53, + "learning_rate": 1.0725920573908024e-05, + "loss": 1.3819, + "step": 5046 + }, + { + "epoch": 0.53, + "learning_rate": 1.0722269932048659e-05, + "loss": 1.3467, + "step": 5047 + }, + { + "epoch": 0.53, + "learning_rate": 1.0718619193423683e-05, + "loss": 1.3036, + "step": 5048 + }, + { + "epoch": 0.53, + "learning_rate": 1.07149683585222e-05, + "loss": 1.3297, + "step": 5049 + }, + { + "epoch": 0.53, + "learning_rate": 1.0711317427833328e-05, + "loss": 1.3439, + "step": 5050 + }, + { + "epoch": 0.53, + "learning_rate": 1.0707666401846192e-05, + "loss": 1.4167, + "step": 5051 + }, + { + "epoch": 0.53, + "learning_rate": 1.0704015281049944e-05, + "loss": 1.4217, + "step": 5052 + }, + { + "epoch": 0.53, + "learning_rate": 1.070036406593374e-05, + "loss": 1.3394, + "step": 5053 + }, + { + "epoch": 0.53, + "learning_rate": 1.0696712756986745e-05, + "loss": 1.3242, + "step": 5054 + }, + { + "epoch": 0.53, + "learning_rate": 1.0693061354698143e-05, + "loss": 1.3957, + "step": 5055 + }, + { + "epoch": 0.53, + "learning_rate": 1.0689409859557123e-05, + "loss": 1.37, + "step": 5056 + }, + { + "epoch": 0.53, + "learning_rate": 1.0685758272052902e-05, + "loss": 1.4524, + "step": 5057 + }, + { + "epoch": 0.53, + "learning_rate": 1.0682106592674688e-05, + "loss": 1.528, + "step": 5058 + }, + { + "epoch": 0.53, + "learning_rate": 1.0678454821911719e-05, + "loss": 1.3613, + "step": 5059 + }, + { + "epoch": 0.53, + "learning_rate": 1.0674802960253234e-05, + "loss": 1.308, + "step": 5060 + }, + { + "epoch": 0.53, + "learning_rate": 1.0671151008188494e-05, + "loss": 1.3343, + "step": 5061 + }, + { + "epoch": 0.53, + "learning_rate": 1.066749896620676e-05, + "loss": 1.365, + "step": 5062 + }, + { + "epoch": 0.53, + "learning_rate": 1.0663846834797316e-05, + "loss": 1.4077, + "step": 5063 + }, + { + "epoch": 0.53, + "learning_rate": 1.0660194614449455e-05, + "loss": 1.324, + "step": 5064 + }, + { + "epoch": 0.53, + "learning_rate": 1.0656542305652478e-05, + "loss": 1.3623, + "step": 5065 + }, + { + "epoch": 0.53, + "learning_rate": 1.0652889908895701e-05, + "loss": 1.4079, + "step": 5066 + }, + { + "epoch": 0.53, + "learning_rate": 1.0649237424668451e-05, + "loss": 1.3089, + "step": 5067 + }, + { + "epoch": 0.53, + "learning_rate": 1.0645584853460069e-05, + "loss": 1.3967, + "step": 5068 + }, + { + "epoch": 0.53, + "learning_rate": 1.0641932195759905e-05, + "loss": 1.3639, + "step": 5069 + }, + { + "epoch": 0.53, + "learning_rate": 1.0638279452057319e-05, + "loss": 1.5919, + "step": 5070 + }, + { + "epoch": 0.53, + "learning_rate": 1.0634626622841686e-05, + "loss": 1.3348, + "step": 5071 + }, + { + "epoch": 0.53, + "learning_rate": 1.0630973708602395e-05, + "loss": 1.3146, + "step": 5072 + }, + { + "epoch": 0.53, + "learning_rate": 1.0627320709828836e-05, + "loss": 1.3375, + "step": 5073 + }, + { + "epoch": 0.53, + "learning_rate": 1.062366762701042e-05, + "loss": 1.3908, + "step": 5074 + }, + { + "epoch": 0.53, + "learning_rate": 1.0620014460636568e-05, + "loss": 1.3726, + "step": 5075 + }, + { + "epoch": 0.53, + "learning_rate": 1.061636121119671e-05, + "loss": 1.2348, + "step": 5076 + }, + { + "epoch": 0.53, + "learning_rate": 1.0612707879180284e-05, + "loss": 1.2957, + "step": 5077 + }, + { + "epoch": 0.53, + "learning_rate": 1.0609054465076749e-05, + "loss": 1.4202, + "step": 5078 + }, + { + "epoch": 0.53, + "learning_rate": 1.060540096937556e-05, + "loss": 1.5809, + "step": 5079 + }, + { + "epoch": 0.53, + "learning_rate": 1.0601747392566202e-05, + "loss": 1.3741, + "step": 5080 + }, + { + "epoch": 0.53, + "learning_rate": 1.059809373513815e-05, + "loss": 1.3537, + "step": 5081 + }, + { + "epoch": 0.53, + "learning_rate": 1.0594439997580907e-05, + "loss": 1.332, + "step": 5082 + }, + { + "epoch": 0.53, + "learning_rate": 1.0590786180383981e-05, + "loss": 1.3267, + "step": 5083 + }, + { + "epoch": 0.53, + "learning_rate": 1.0587132284036883e-05, + "loss": 1.3552, + "step": 5084 + }, + { + "epoch": 0.53, + "learning_rate": 1.0583478309029143e-05, + "loss": 1.2837, + "step": 5085 + }, + { + "epoch": 0.53, + "learning_rate": 1.0579824255850304e-05, + "loss": 1.4311, + "step": 5086 + }, + { + "epoch": 0.53, + "learning_rate": 1.0576170124989915e-05, + "loss": 1.4394, + "step": 5087 + }, + { + "epoch": 0.53, + "learning_rate": 1.0572515916937531e-05, + "loss": 1.3185, + "step": 5088 + }, + { + "epoch": 0.53, + "learning_rate": 1.0568861632182723e-05, + "loss": 1.4212, + "step": 5089 + }, + { + "epoch": 0.53, + "learning_rate": 1.0565207271215075e-05, + "loss": 1.0951, + "step": 5090 + }, + { + "epoch": 0.53, + "learning_rate": 1.0561552834524176e-05, + "loss": 1.4174, + "step": 5091 + }, + { + "epoch": 0.53, + "learning_rate": 1.0557898322599624e-05, + "loss": 1.3349, + "step": 5092 + }, + { + "epoch": 0.53, + "learning_rate": 1.0554243735931031e-05, + "loss": 1.399, + "step": 5093 + }, + { + "epoch": 0.53, + "learning_rate": 1.055058907500802e-05, + "loss": 1.4016, + "step": 5094 + }, + { + "epoch": 0.53, + "learning_rate": 1.0546934340320219e-05, + "loss": 1.3227, + "step": 5095 + }, + { + "epoch": 0.53, + "learning_rate": 1.0543279532357269e-05, + "loss": 1.4017, + "step": 5096 + }, + { + "epoch": 0.53, + "learning_rate": 1.053962465160882e-05, + "loss": 1.3937, + "step": 5097 + }, + { + "epoch": 0.53, + "learning_rate": 1.0535969698564532e-05, + "loss": 1.2405, + "step": 5098 + }, + { + "epoch": 0.53, + "learning_rate": 1.0532314673714081e-05, + "loss": 1.2939, + "step": 5099 + }, + { + "epoch": 0.53, + "learning_rate": 1.0528659577547136e-05, + "loss": 1.4165, + "step": 5100 + }, + { + "epoch": 0.53, + "learning_rate": 1.0525004410553394e-05, + "loss": 1.309, + "step": 5101 + }, + { + "epoch": 0.54, + "learning_rate": 1.0521349173222549e-05, + "loss": 1.4078, + "step": 5102 + }, + { + "epoch": 0.54, + "learning_rate": 1.0517693866044312e-05, + "loss": 1.4026, + "step": 5103 + }, + { + "epoch": 0.54, + "learning_rate": 1.0514038489508396e-05, + "loss": 1.3098, + "step": 5104 + }, + { + "epoch": 0.54, + "learning_rate": 1.0510383044104533e-05, + "loss": 1.2886, + "step": 5105 + }, + { + "epoch": 0.54, + "learning_rate": 1.0506727530322454e-05, + "loss": 1.3114, + "step": 5106 + }, + { + "epoch": 0.54, + "learning_rate": 1.0503071948651908e-05, + "loss": 1.2823, + "step": 5107 + }, + { + "epoch": 0.54, + "learning_rate": 1.0499416299582643e-05, + "loss": 1.4654, + "step": 5108 + }, + { + "epoch": 0.54, + "learning_rate": 1.0495760583604431e-05, + "loss": 1.4043, + "step": 5109 + }, + { + "epoch": 0.54, + "learning_rate": 1.0492104801207035e-05, + "loss": 1.3113, + "step": 5110 + }, + { + "epoch": 0.54, + "learning_rate": 1.0488448952880243e-05, + "loss": 1.3285, + "step": 5111 + }, + { + "epoch": 0.54, + "learning_rate": 1.048479303911384e-05, + "loss": 1.3918, + "step": 5112 + }, + { + "epoch": 0.54, + "learning_rate": 1.0481137060397623e-05, + "loss": 1.346, + "step": 5113 + }, + { + "epoch": 0.54, + "learning_rate": 1.0477481017221407e-05, + "loss": 1.3777, + "step": 5114 + }, + { + "epoch": 0.54, + "learning_rate": 1.0473824910075003e-05, + "loss": 1.3494, + "step": 5115 + }, + { + "epoch": 0.54, + "learning_rate": 1.0470168739448232e-05, + "loss": 1.4173, + "step": 5116 + }, + { + "epoch": 0.54, + "learning_rate": 1.0466512505830932e-05, + "loss": 1.4313, + "step": 5117 + }, + { + "epoch": 0.54, + "learning_rate": 1.0462856209712944e-05, + "loss": 1.335, + "step": 5118 + }, + { + "epoch": 0.54, + "learning_rate": 1.0459199851584117e-05, + "loss": 1.37, + "step": 5119 + }, + { + "epoch": 0.54, + "learning_rate": 1.0455543431934307e-05, + "loss": 1.3504, + "step": 5120 + }, + { + "epoch": 0.54, + "learning_rate": 1.0451886951253381e-05, + "loss": 1.4148, + "step": 5121 + }, + { + "epoch": 0.54, + "learning_rate": 1.0448230410031218e-05, + "loss": 1.3974, + "step": 5122 + }, + { + "epoch": 0.54, + "learning_rate": 1.0444573808757694e-05, + "loss": 1.3644, + "step": 5123 + }, + { + "epoch": 0.54, + "learning_rate": 1.0440917147922705e-05, + "loss": 1.4024, + "step": 5124 + }, + { + "epoch": 0.54, + "learning_rate": 1.0437260428016143e-05, + "loss": 1.3925, + "step": 5125 + }, + { + "epoch": 0.54, + "learning_rate": 1.0433603649527923e-05, + "loss": 1.2907, + "step": 5126 + }, + { + "epoch": 0.54, + "learning_rate": 1.0429946812947953e-05, + "loss": 1.3453, + "step": 5127 + }, + { + "epoch": 0.54, + "learning_rate": 1.0426289918766157e-05, + "loss": 1.3856, + "step": 5128 + }, + { + "epoch": 0.54, + "learning_rate": 1.0422632967472465e-05, + "loss": 1.3309, + "step": 5129 + }, + { + "epoch": 0.54, + "learning_rate": 1.0418975959556819e-05, + "loss": 1.3757, + "step": 5130 + }, + { + "epoch": 0.54, + "learning_rate": 1.0415318895509152e-05, + "loss": 1.406, + "step": 5131 + }, + { + "epoch": 0.54, + "learning_rate": 1.041166177581943e-05, + "loss": 1.3265, + "step": 5132 + }, + { + "epoch": 0.54, + "learning_rate": 1.0408004600977606e-05, + "loss": 1.3377, + "step": 5133 + }, + { + "epoch": 0.54, + "learning_rate": 1.040434737147365e-05, + "loss": 1.3647, + "step": 5134 + }, + { + "epoch": 0.54, + "learning_rate": 1.0400690087797531e-05, + "loss": 1.3262, + "step": 5135 + }, + { + "epoch": 0.54, + "learning_rate": 1.039703275043924e-05, + "loss": 1.3924, + "step": 5136 + }, + { + "epoch": 0.54, + "learning_rate": 1.039337535988876e-05, + "loss": 1.3018, + "step": 5137 + }, + { + "epoch": 0.54, + "learning_rate": 1.038971791663609e-05, + "loss": 1.385, + "step": 5138 + }, + { + "epoch": 0.54, + "learning_rate": 1.0386060421171232e-05, + "loss": 1.3435, + "step": 5139 + }, + { + "epoch": 0.54, + "learning_rate": 1.0382402873984197e-05, + "loss": 1.4023, + "step": 5140 + }, + { + "epoch": 0.54, + "learning_rate": 1.0378745275565003e-05, + "loss": 1.369, + "step": 5141 + }, + { + "epoch": 0.54, + "learning_rate": 1.0375087626403675e-05, + "loss": 1.3199, + "step": 5142 + }, + { + "epoch": 0.54, + "learning_rate": 1.037142992699024e-05, + "loss": 1.4247, + "step": 5143 + }, + { + "epoch": 0.54, + "learning_rate": 1.0367772177814736e-05, + "loss": 1.4015, + "step": 5144 + }, + { + "epoch": 0.54, + "learning_rate": 1.0364114379367217e-05, + "loss": 1.3519, + "step": 5145 + }, + { + "epoch": 0.54, + "learning_rate": 1.0360456532137722e-05, + "loss": 1.3478, + "step": 5146 + }, + { + "epoch": 0.54, + "learning_rate": 1.0356798636616314e-05, + "loss": 1.4876, + "step": 5147 + }, + { + "epoch": 0.54, + "learning_rate": 1.0353140693293056e-05, + "loss": 1.6481, + "step": 5148 + }, + { + "epoch": 0.54, + "learning_rate": 1.034948270265802e-05, + "loss": 1.3851, + "step": 5149 + }, + { + "epoch": 0.54, + "learning_rate": 1.0345824665201281e-05, + "loss": 1.4037, + "step": 5150 + }, + { + "epoch": 0.54, + "learning_rate": 1.0342166581412923e-05, + "loss": 1.3138, + "step": 5151 + }, + { + "epoch": 0.54, + "learning_rate": 1.0338508451783032e-05, + "loss": 1.3536, + "step": 5152 + }, + { + "epoch": 0.54, + "learning_rate": 1.0334850276801712e-05, + "loss": 1.3244, + "step": 5153 + }, + { + "epoch": 0.54, + "learning_rate": 1.0331192056959052e-05, + "loss": 1.3677, + "step": 5154 + }, + { + "epoch": 0.54, + "learning_rate": 1.032753379274517e-05, + "loss": 1.3439, + "step": 5155 + }, + { + "epoch": 0.54, + "learning_rate": 1.0323875484650171e-05, + "loss": 1.365, + "step": 5156 + }, + { + "epoch": 0.54, + "learning_rate": 1.0320217133164186e-05, + "loss": 1.3838, + "step": 5157 + }, + { + "epoch": 0.54, + "learning_rate": 1.0316558738777328e-05, + "loss": 1.3312, + "step": 5158 + }, + { + "epoch": 0.54, + "learning_rate": 1.0312900301979733e-05, + "loss": 1.369, + "step": 5159 + }, + { + "epoch": 0.54, + "learning_rate": 1.030924182326154e-05, + "loss": 1.2712, + "step": 5160 + }, + { + "epoch": 0.54, + "learning_rate": 1.0305583303112887e-05, + "loss": 1.3141, + "step": 5161 + }, + { + "epoch": 0.54, + "learning_rate": 1.030192474202392e-05, + "loss": 1.3708, + "step": 5162 + }, + { + "epoch": 0.54, + "learning_rate": 1.0298266140484798e-05, + "loss": 1.3724, + "step": 5163 + }, + { + "epoch": 0.54, + "learning_rate": 1.0294607498985678e-05, + "loss": 1.3208, + "step": 5164 + }, + { + "epoch": 0.54, + "learning_rate": 1.0290948818016722e-05, + "loss": 1.3379, + "step": 5165 + }, + { + "epoch": 0.54, + "learning_rate": 1.0287290098068099e-05, + "loss": 1.3236, + "step": 5166 + }, + { + "epoch": 0.54, + "learning_rate": 1.0283631339629982e-05, + "loss": 1.3437, + "step": 5167 + }, + { + "epoch": 0.54, + "learning_rate": 1.0279972543192561e-05, + "loss": 1.3381, + "step": 5168 + }, + { + "epoch": 0.54, + "learning_rate": 1.0276313709246007e-05, + "loss": 1.4287, + "step": 5169 + }, + { + "epoch": 0.54, + "learning_rate": 1.0272654838280515e-05, + "loss": 1.3587, + "step": 5170 + }, + { + "epoch": 0.54, + "learning_rate": 1.0268995930786283e-05, + "loss": 1.2982, + "step": 5171 + }, + { + "epoch": 0.54, + "learning_rate": 1.0265336987253509e-05, + "loss": 1.3416, + "step": 5172 + }, + { + "epoch": 0.54, + "learning_rate": 1.0261678008172393e-05, + "loss": 1.3827, + "step": 5173 + }, + { + "epoch": 0.54, + "learning_rate": 1.025801899403315e-05, + "loss": 1.3293, + "step": 5174 + }, + { + "epoch": 0.54, + "eval_loss": 1.4264723062515259, + "eval_runtime": 77.4376, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 5174 + }, + { + "epoch": 0.54, + "learning_rate": 1.0254359945325987e-05, + "loss": 1.3811, + "step": 5175 + }, + { + "epoch": 0.54, + "learning_rate": 1.0250700862541135e-05, + "loss": 1.3423, + "step": 5176 + }, + { + "epoch": 0.54, + "learning_rate": 1.02470417461688e-05, + "loss": 1.3641, + "step": 5177 + }, + { + "epoch": 0.54, + "learning_rate": 1.0243382596699226e-05, + "loss": 1.3211, + "step": 5178 + }, + { + "epoch": 0.54, + "learning_rate": 1.023972341462263e-05, + "loss": 1.4008, + "step": 5179 + }, + { + "epoch": 0.54, + "learning_rate": 1.0236064200429263e-05, + "loss": 1.404, + "step": 5180 + }, + { + "epoch": 0.54, + "learning_rate": 1.0232404954609353e-05, + "loss": 1.3359, + "step": 5181 + }, + { + "epoch": 0.54, + "learning_rate": 1.0228745677653155e-05, + "loss": 1.4069, + "step": 5182 + }, + { + "epoch": 0.54, + "learning_rate": 1.0225086370050914e-05, + "loss": 1.3343, + "step": 5183 + }, + { + "epoch": 0.54, + "learning_rate": 1.0221427032292881e-05, + "loss": 1.3109, + "step": 5184 + }, + { + "epoch": 0.54, + "learning_rate": 1.0217767664869312e-05, + "loss": 1.3611, + "step": 5185 + }, + { + "epoch": 0.54, + "learning_rate": 1.0214108268270476e-05, + "loss": 1.4072, + "step": 5186 + }, + { + "epoch": 0.54, + "learning_rate": 1.0210448842986631e-05, + "loss": 1.3602, + "step": 5187 + }, + { + "epoch": 0.54, + "learning_rate": 1.0206789389508047e-05, + "loss": 1.413, + "step": 5188 + }, + { + "epoch": 0.54, + "learning_rate": 1.0203129908325e-05, + "loss": 1.3209, + "step": 5189 + }, + { + "epoch": 0.54, + "learning_rate": 1.0199470399927764e-05, + "loss": 1.3714, + "step": 5190 + }, + { + "epoch": 0.54, + "learning_rate": 1.0195810864806623e-05, + "loss": 1.3556, + "step": 5191 + }, + { + "epoch": 0.54, + "learning_rate": 1.0192151303451852e-05, + "loss": 1.4116, + "step": 5192 + }, + { + "epoch": 0.54, + "learning_rate": 1.0188491716353745e-05, + "loss": 1.4102, + "step": 5193 + }, + { + "epoch": 0.54, + "learning_rate": 1.0184832104002592e-05, + "loss": 1.4849, + "step": 5194 + }, + { + "epoch": 0.54, + "learning_rate": 1.0181172466888689e-05, + "loss": 1.5395, + "step": 5195 + }, + { + "epoch": 0.54, + "learning_rate": 1.0177512805502325e-05, + "loss": 1.3627, + "step": 5196 + }, + { + "epoch": 0.54, + "learning_rate": 1.017385312033381e-05, + "loss": 1.4152, + "step": 5197 + }, + { + "epoch": 0.55, + "learning_rate": 1.0170193411873442e-05, + "loss": 1.3641, + "step": 5198 + }, + { + "epoch": 0.55, + "learning_rate": 1.0166533680611533e-05, + "loss": 1.3074, + "step": 5199 + }, + { + "epoch": 0.55, + "learning_rate": 1.0162873927038386e-05, + "loss": 1.35, + "step": 5200 + }, + { + "epoch": 0.55, + "learning_rate": 1.015921415164432e-05, + "loss": 1.3551, + "step": 5201 + }, + { + "epoch": 0.55, + "learning_rate": 1.0155554354919643e-05, + "loss": 1.3421, + "step": 5202 + }, + { + "epoch": 0.55, + "learning_rate": 1.0151894537354687e-05, + "loss": 1.4132, + "step": 5203 + }, + { + "epoch": 0.55, + "learning_rate": 1.0148234699439764e-05, + "loss": 1.351, + "step": 5204 + }, + { + "epoch": 0.55, + "learning_rate": 1.0144574841665198e-05, + "loss": 1.3745, + "step": 5205 + }, + { + "epoch": 0.55, + "learning_rate": 1.0140914964521316e-05, + "loss": 1.3151, + "step": 5206 + }, + { + "epoch": 0.55, + "learning_rate": 1.0137255068498456e-05, + "loss": 1.4903, + "step": 5207 + }, + { + "epoch": 0.55, + "learning_rate": 1.0133595154086937e-05, + "loss": 1.3945, + "step": 5208 + }, + { + "epoch": 0.55, + "learning_rate": 1.0129935221777104e-05, + "loss": 1.3924, + "step": 5209 + }, + { + "epoch": 0.55, + "learning_rate": 1.0126275272059286e-05, + "loss": 1.4191, + "step": 5210 + }, + { + "epoch": 0.55, + "learning_rate": 1.012261530542383e-05, + "loss": 1.3408, + "step": 5211 + }, + { + "epoch": 0.55, + "learning_rate": 1.0118955322361071e-05, + "loss": 1.3582, + "step": 5212 + }, + { + "epoch": 0.55, + "learning_rate": 1.0115295323361354e-05, + "loss": 1.3703, + "step": 5213 + }, + { + "epoch": 0.55, + "learning_rate": 1.011163530891503e-05, + "loss": 1.4181, + "step": 5214 + }, + { + "epoch": 0.55, + "learning_rate": 1.0107975279512442e-05, + "loss": 1.5019, + "step": 5215 + }, + { + "epoch": 0.55, + "learning_rate": 1.010431523564394e-05, + "loss": 1.3151, + "step": 5216 + }, + { + "epoch": 0.55, + "learning_rate": 1.0100655177799874e-05, + "loss": 1.4036, + "step": 5217 + }, + { + "epoch": 0.55, + "learning_rate": 1.0096995106470606e-05, + "loss": 1.3584, + "step": 5218 + }, + { + "epoch": 0.55, + "learning_rate": 1.0093335022146482e-05, + "loss": 1.3618, + "step": 5219 + }, + { + "epoch": 0.55, + "learning_rate": 1.0089674925317865e-05, + "loss": 1.3295, + "step": 5220 + }, + { + "epoch": 0.55, + "learning_rate": 1.0086014816475108e-05, + "loss": 1.3968, + "step": 5221 + }, + { + "epoch": 0.55, + "learning_rate": 1.0082354696108586e-05, + "loss": 1.2847, + "step": 5222 + }, + { + "epoch": 0.55, + "learning_rate": 1.007869456470864e-05, + "loss": 1.4461, + "step": 5223 + }, + { + "epoch": 0.55, + "learning_rate": 1.007503442276565e-05, + "loss": 1.3813, + "step": 5224 + }, + { + "epoch": 0.55, + "learning_rate": 1.007137427076997e-05, + "loss": 1.3833, + "step": 5225 + }, + { + "epoch": 0.55, + "learning_rate": 1.006771410921198e-05, + "loss": 1.4024, + "step": 5226 + }, + { + "epoch": 0.55, + "learning_rate": 1.0064053938582032e-05, + "loss": 1.3357, + "step": 5227 + }, + { + "epoch": 0.55, + "learning_rate": 1.0060393759370506e-05, + "loss": 1.35, + "step": 5228 + }, + { + "epoch": 0.55, + "learning_rate": 1.0056733572067765e-05, + "loss": 1.3512, + "step": 5229 + }, + { + "epoch": 0.55, + "learning_rate": 1.0053073377164186e-05, + "loss": 1.3852, + "step": 5230 + }, + { + "epoch": 0.55, + "learning_rate": 1.0049413175150135e-05, + "loss": 1.3502, + "step": 5231 + }, + { + "epoch": 0.55, + "learning_rate": 1.004575296651599e-05, + "loss": 1.4637, + "step": 5232 + }, + { + "epoch": 0.55, + "learning_rate": 1.0042092751752123e-05, + "loss": 1.3877, + "step": 5233 + }, + { + "epoch": 0.55, + "learning_rate": 1.0038432531348909e-05, + "loss": 1.3804, + "step": 5234 + }, + { + "epoch": 0.55, + "learning_rate": 1.0034772305796723e-05, + "loss": 1.3613, + "step": 5235 + }, + { + "epoch": 0.55, + "learning_rate": 1.003111207558594e-05, + "loss": 1.3218, + "step": 5236 + }, + { + "epoch": 0.55, + "learning_rate": 1.0027451841206944e-05, + "loss": 1.3554, + "step": 5237 + }, + { + "epoch": 0.55, + "learning_rate": 1.0023791603150099e-05, + "loss": 1.372, + "step": 5238 + }, + { + "epoch": 0.55, + "learning_rate": 1.0020131361905793e-05, + "loss": 1.3544, + "step": 5239 + }, + { + "epoch": 0.55, + "learning_rate": 1.0016471117964404e-05, + "loss": 1.3472, + "step": 5240 + }, + { + "epoch": 0.55, + "learning_rate": 1.001281087181631e-05, + "loss": 1.4247, + "step": 5241 + }, + { + "epoch": 0.55, + "learning_rate": 1.0009150623951883e-05, + "loss": 1.2685, + "step": 5242 + }, + { + "epoch": 0.55, + "learning_rate": 1.000549037486151e-05, + "loss": 1.4036, + "step": 5243 + }, + { + "epoch": 0.55, + "learning_rate": 1.0001830125035565e-05, + "loss": 1.3602, + "step": 5244 + }, + { + "epoch": 0.55, + "learning_rate": 9.998169874964437e-06, + "loss": 1.3784, + "step": 5245 + }, + { + "epoch": 0.55, + "learning_rate": 9.994509625138496e-06, + "loss": 1.3389, + "step": 5246 + }, + { + "epoch": 0.55, + "learning_rate": 9.990849376048119e-06, + "loss": 1.4561, + "step": 5247 + }, + { + "epoch": 0.55, + "learning_rate": 9.987189128183695e-06, + "loss": 1.3876, + "step": 5248 + }, + { + "epoch": 0.55, + "learning_rate": 9.9835288820356e-06, + "loss": 1.3362, + "step": 5249 + }, + { + "epoch": 0.55, + "learning_rate": 9.97986863809421e-06, + "loss": 1.3449, + "step": 5250 + }, + { + "epoch": 0.55, + "learning_rate": 9.9762083968499e-06, + "loss": 1.3521, + "step": 5251 + }, + { + "epoch": 0.55, + "learning_rate": 9.972548158793061e-06, + "loss": 1.4452, + "step": 5252 + }, + { + "epoch": 0.55, + "learning_rate": 9.968887924414062e-06, + "loss": 1.4126, + "step": 5253 + }, + { + "epoch": 0.55, + "learning_rate": 9.965227694203282e-06, + "loss": 1.3054, + "step": 5254 + }, + { + "epoch": 0.55, + "learning_rate": 9.961567468651093e-06, + "loss": 1.3771, + "step": 5255 + }, + { + "epoch": 0.55, + "learning_rate": 9.957907248247878e-06, + "loss": 1.3566, + "step": 5256 + }, + { + "epoch": 0.55, + "learning_rate": 9.954247033484014e-06, + "loss": 1.4765, + "step": 5257 + }, + { + "epoch": 0.55, + "learning_rate": 9.950586824849865e-06, + "loss": 1.4749, + "step": 5258 + }, + { + "epoch": 0.55, + "learning_rate": 9.946926622835815e-06, + "loss": 1.3679, + "step": 5259 + }, + { + "epoch": 0.55, + "learning_rate": 9.943266427932238e-06, + "loss": 1.2671, + "step": 5260 + }, + { + "epoch": 0.55, + "learning_rate": 9.9396062406295e-06, + "loss": 1.3485, + "step": 5261 + }, + { + "epoch": 0.55, + "learning_rate": 9.935946061417968e-06, + "loss": 1.3136, + "step": 5262 + }, + { + "epoch": 0.55, + "learning_rate": 9.932285890788024e-06, + "loss": 1.3954, + "step": 5263 + }, + { + "epoch": 0.55, + "learning_rate": 9.928625729230031e-06, + "loss": 1.428, + "step": 5264 + }, + { + "epoch": 0.55, + "learning_rate": 9.924965577234356e-06, + "loss": 1.4144, + "step": 5265 + }, + { + "epoch": 0.55, + "learning_rate": 9.92130543529136e-06, + "loss": 1.3361, + "step": 5266 + }, + { + "epoch": 0.55, + "learning_rate": 9.91764530389142e-06, + "loss": 1.4503, + "step": 5267 + }, + { + "epoch": 0.55, + "learning_rate": 9.913985183524893e-06, + "loss": 1.3431, + "step": 5268 + }, + { + "epoch": 0.55, + "learning_rate": 9.91032507468214e-06, + "loss": 1.3206, + "step": 5269 + }, + { + "epoch": 0.55, + "learning_rate": 9.906664977853518e-06, + "loss": 1.4568, + "step": 5270 + }, + { + "epoch": 0.55, + "learning_rate": 9.903004893529397e-06, + "loss": 1.3591, + "step": 5271 + }, + { + "epoch": 0.55, + "learning_rate": 9.899344822200127e-06, + "loss": 1.3382, + "step": 5272 + }, + { + "epoch": 0.55, + "learning_rate": 9.895684764356066e-06, + "loss": 1.3008, + "step": 5273 + }, + { + "epoch": 0.55, + "learning_rate": 9.89202472048756e-06, + "loss": 1.316, + "step": 5274 + }, + { + "epoch": 0.55, + "learning_rate": 9.888364691084971e-06, + "loss": 1.4246, + "step": 5275 + }, + { + "epoch": 0.55, + "learning_rate": 9.88470467663865e-06, + "loss": 1.3615, + "step": 5276 + }, + { + "epoch": 0.55, + "learning_rate": 9.881044677638934e-06, + "loss": 1.3418, + "step": 5277 + }, + { + "epoch": 0.55, + "learning_rate": 9.877384694576172e-06, + "loss": 1.249, + "step": 5278 + }, + { + "epoch": 0.55, + "learning_rate": 9.873724727940715e-06, + "loss": 1.2779, + "step": 5279 + }, + { + "epoch": 0.55, + "learning_rate": 9.870064778222903e-06, + "loss": 1.3529, + "step": 5280 + }, + { + "epoch": 0.55, + "learning_rate": 9.866404845913065e-06, + "loss": 1.3204, + "step": 5281 + }, + { + "epoch": 0.55, + "learning_rate": 9.862744931501548e-06, + "loss": 1.3537, + "step": 5282 + }, + { + "epoch": 0.55, + "learning_rate": 9.859085035478687e-06, + "loss": 1.3681, + "step": 5283 + }, + { + "epoch": 0.55, + "learning_rate": 9.855425158334809e-06, + "loss": 1.3983, + "step": 5284 + }, + { + "epoch": 0.55, + "learning_rate": 9.851765300560238e-06, + "loss": 1.401, + "step": 5285 + }, + { + "epoch": 0.55, + "learning_rate": 9.848105462645315e-06, + "loss": 1.3073, + "step": 5286 + }, + { + "epoch": 0.55, + "learning_rate": 9.844445645080358e-06, + "loss": 1.3162, + "step": 5287 + }, + { + "epoch": 0.55, + "learning_rate": 9.840785848355685e-06, + "loss": 1.3345, + "step": 5288 + }, + { + "epoch": 0.55, + "learning_rate": 9.837126072961616e-06, + "loss": 1.4241, + "step": 5289 + }, + { + "epoch": 0.55, + "learning_rate": 9.83346631938847e-06, + "loss": 1.3339, + "step": 5290 + }, + { + "epoch": 0.55, + "learning_rate": 9.829806588126561e-06, + "loss": 1.3507, + "step": 5291 + }, + { + "epoch": 0.55, + "learning_rate": 9.826146879666196e-06, + "loss": 1.2806, + "step": 5292 + }, + { + "epoch": 0.56, + "learning_rate": 9.822487194497675e-06, + "loss": 1.3952, + "step": 5293 + }, + { + "epoch": 0.56, + "learning_rate": 9.818827533111314e-06, + "loss": 1.3319, + "step": 5294 + }, + { + "epoch": 0.56, + "learning_rate": 9.81516789599741e-06, + "loss": 1.351, + "step": 5295 + }, + { + "epoch": 0.56, + "learning_rate": 9.811508283646258e-06, + "loss": 1.4076, + "step": 5296 + }, + { + "epoch": 0.56, + "learning_rate": 9.80784869654815e-06, + "loss": 1.3271, + "step": 5297 + }, + { + "epoch": 0.56, + "learning_rate": 9.80418913519338e-06, + "loss": 1.4059, + "step": 5298 + }, + { + "epoch": 0.56, + "learning_rate": 9.80052960007224e-06, + "loss": 1.4146, + "step": 5299 + }, + { + "epoch": 0.56, + "learning_rate": 9.796870091675005e-06, + "loss": 1.3454, + "step": 5300 + }, + { + "epoch": 0.56, + "learning_rate": 9.793210610491953e-06, + "loss": 1.4376, + "step": 5301 + }, + { + "epoch": 0.56, + "learning_rate": 9.789551157013372e-06, + "loss": 1.3437, + "step": 5302 + }, + { + "epoch": 0.56, + "learning_rate": 9.78589173172953e-06, + "loss": 1.3073, + "step": 5303 + }, + { + "epoch": 0.56, + "learning_rate": 9.782232335130688e-06, + "loss": 1.2989, + "step": 5304 + }, + { + "epoch": 0.56, + "learning_rate": 9.778572967707122e-06, + "loss": 1.4028, + "step": 5305 + }, + { + "epoch": 0.56, + "learning_rate": 9.77491362994909e-06, + "loss": 1.3096, + "step": 5306 + }, + { + "epoch": 0.56, + "learning_rate": 9.77125432234685e-06, + "loss": 1.3719, + "step": 5307 + }, + { + "epoch": 0.56, + "learning_rate": 9.767595045390647e-06, + "loss": 1.3271, + "step": 5308 + }, + { + "epoch": 0.56, + "learning_rate": 9.763935799570739e-06, + "loss": 1.3693, + "step": 5309 + }, + { + "epoch": 0.56, + "learning_rate": 9.760276585377371e-06, + "loss": 1.3586, + "step": 5310 + }, + { + "epoch": 0.56, + "learning_rate": 9.756617403300781e-06, + "loss": 1.3423, + "step": 5311 + }, + { + "epoch": 0.56, + "learning_rate": 9.7529582538312e-06, + "loss": 1.388, + "step": 5312 + }, + { + "epoch": 0.56, + "learning_rate": 9.74929913745887e-06, + "loss": 1.3594, + "step": 5313 + }, + { + "epoch": 0.56, + "learning_rate": 9.745640054674015e-06, + "loss": 1.2831, + "step": 5314 + }, + { + "epoch": 0.56, + "learning_rate": 9.741981005966856e-06, + "loss": 1.4207, + "step": 5315 + }, + { + "epoch": 0.56, + "learning_rate": 9.738321991827609e-06, + "loss": 1.2807, + "step": 5316 + }, + { + "epoch": 0.56, + "learning_rate": 9.734663012746493e-06, + "loss": 1.3396, + "step": 5317 + }, + { + "epoch": 0.56, + "learning_rate": 9.731004069213722e-06, + "loss": 1.3666, + "step": 5318 + }, + { + "epoch": 0.56, + "learning_rate": 9.72734516171949e-06, + "loss": 1.3466, + "step": 5319 + }, + { + "epoch": 0.56, + "learning_rate": 9.723686290753995e-06, + "loss": 1.4478, + "step": 5320 + }, + { + "epoch": 0.56, + "learning_rate": 9.720027456807442e-06, + "loss": 1.316, + "step": 5321 + }, + { + "epoch": 0.56, + "learning_rate": 9.71636866037002e-06, + "loss": 1.3762, + "step": 5322 + }, + { + "epoch": 0.56, + "learning_rate": 9.712709901931906e-06, + "loss": 1.4156, + "step": 5323 + }, + { + "epoch": 0.56, + "learning_rate": 9.70905118198328e-06, + "loss": 1.2452, + "step": 5324 + }, + { + "epoch": 0.56, + "learning_rate": 9.705392501014325e-06, + "loss": 1.3771, + "step": 5325 + }, + { + "epoch": 0.56, + "learning_rate": 9.701733859515205e-06, + "loss": 1.3433, + "step": 5326 + }, + { + "epoch": 0.56, + "learning_rate": 9.698075257976079e-06, + "loss": 1.3702, + "step": 5327 + }, + { + "epoch": 0.56, + "learning_rate": 9.694416696887115e-06, + "loss": 1.295, + "step": 5328 + }, + { + "epoch": 0.56, + "learning_rate": 9.690758176738463e-06, + "loss": 1.3462, + "step": 5329 + }, + { + "epoch": 0.56, + "learning_rate": 9.68709969802027e-06, + "loss": 1.5304, + "step": 5330 + }, + { + "epoch": 0.56, + "learning_rate": 9.683441261222672e-06, + "loss": 1.3518, + "step": 5331 + }, + { + "epoch": 0.56, + "learning_rate": 9.679782866835816e-06, + "loss": 1.3778, + "step": 5332 + }, + { + "epoch": 0.56, + "learning_rate": 9.67612451534983e-06, + "loss": 1.3731, + "step": 5333 + }, + { + "epoch": 0.56, + "learning_rate": 9.672466207254837e-06, + "loss": 1.3315, + "step": 5334 + }, + { + "epoch": 0.56, + "learning_rate": 9.66880794304095e-06, + "loss": 1.3105, + "step": 5335 + }, + { + "epoch": 0.56, + "learning_rate": 9.665149723198293e-06, + "loss": 1.3903, + "step": 5336 + }, + { + "epoch": 0.56, + "learning_rate": 9.661491548216972e-06, + "loss": 1.3554, + "step": 5337 + }, + { + "epoch": 0.56, + "learning_rate": 9.657833418587084e-06, + "loss": 1.3231, + "step": 5338 + }, + { + "epoch": 0.56, + "learning_rate": 9.65417533479872e-06, + "loss": 1.352, + "step": 5339 + }, + { + "epoch": 0.56, + "learning_rate": 9.650517297341983e-06, + "loss": 1.3957, + "step": 5340 + }, + { + "epoch": 0.56, + "learning_rate": 9.646859306706948e-06, + "loss": 1.3938, + "step": 5341 + }, + { + "epoch": 0.56, + "learning_rate": 9.643201363383693e-06, + "loss": 1.3038, + "step": 5342 + }, + { + "epoch": 0.56, + "learning_rate": 9.63954346786228e-06, + "loss": 1.2973, + "step": 5343 + }, + { + "epoch": 0.56, + "learning_rate": 9.635885620632786e-06, + "loss": 1.379, + "step": 5344 + }, + { + "epoch": 0.56, + "learning_rate": 9.632227822185266e-06, + "loss": 1.5377, + "step": 5345 + }, + { + "epoch": 0.56, + "learning_rate": 9.628570073009767e-06, + "loss": 1.4573, + "step": 5346 + }, + { + "epoch": 0.56, + "learning_rate": 9.624912373596329e-06, + "loss": 1.3394, + "step": 5347 + }, + { + "epoch": 0.56, + "learning_rate": 9.621254724434999e-06, + "loss": 1.4157, + "step": 5348 + }, + { + "epoch": 0.56, + "learning_rate": 9.617597126015808e-06, + "loss": 1.3526, + "step": 5349 + }, + { + "epoch": 0.56, + "learning_rate": 9.61393957882877e-06, + "loss": 1.3795, + "step": 5350 + }, + { + "epoch": 0.56, + "learning_rate": 9.610282083363913e-06, + "loss": 1.3765, + "step": 5351 + }, + { + "epoch": 0.56, + "learning_rate": 9.606624640111243e-06, + "loss": 1.3512, + "step": 5352 + }, + { + "epoch": 0.56, + "learning_rate": 9.602967249560766e-06, + "loss": 1.3298, + "step": 5353 + }, + { + "epoch": 0.56, + "learning_rate": 9.599309912202469e-06, + "loss": 1.3093, + "step": 5354 + }, + { + "epoch": 0.56, + "learning_rate": 9.595652628526354e-06, + "loss": 1.3353, + "step": 5355 + }, + { + "epoch": 0.56, + "learning_rate": 9.591995399022397e-06, + "loss": 1.3081, + "step": 5356 + }, + { + "epoch": 0.56, + "learning_rate": 9.588338224180576e-06, + "loss": 1.343, + "step": 5357 + }, + { + "epoch": 0.56, + "learning_rate": 9.584681104490848e-06, + "loss": 1.3275, + "step": 5358 + }, + { + "epoch": 0.56, + "learning_rate": 9.581024040443185e-06, + "loss": 1.3399, + "step": 5359 + }, + { + "epoch": 0.56, + "learning_rate": 9.577367032527538e-06, + "loss": 1.3181, + "step": 5360 + }, + { + "epoch": 0.56, + "learning_rate": 9.573710081233846e-06, + "loss": 1.3531, + "step": 5361 + }, + { + "epoch": 0.56, + "learning_rate": 9.570053187052049e-06, + "loss": 1.4056, + "step": 5362 + }, + { + "epoch": 0.56, + "learning_rate": 9.566396350472079e-06, + "loss": 1.3303, + "step": 5363 + }, + { + "epoch": 0.56, + "learning_rate": 9.56273957198386e-06, + "loss": 1.3506, + "step": 5364 + }, + { + "epoch": 0.56, + "learning_rate": 9.559082852077302e-06, + "loss": 1.4588, + "step": 5365 + }, + { + "epoch": 0.56, + "learning_rate": 9.555426191242307e-06, + "loss": 1.3434, + "step": 5366 + }, + { + "epoch": 0.56, + "learning_rate": 9.551769589968784e-06, + "loss": 1.3508, + "step": 5367 + }, + { + "epoch": 0.56, + "learning_rate": 9.548113048746622e-06, + "loss": 1.3701, + "step": 5368 + }, + { + "epoch": 0.56, + "learning_rate": 9.544456568065698e-06, + "loss": 1.3664, + "step": 5369 + }, + { + "epoch": 0.56, + "learning_rate": 9.540800148415885e-06, + "loss": 1.6697, + "step": 5370 + }, + { + "epoch": 0.56, + "learning_rate": 9.537143790287057e-06, + "loss": 1.5298, + "step": 5371 + }, + { + "epoch": 0.56, + "learning_rate": 9.533487494169073e-06, + "loss": 1.3884, + "step": 5372 + }, + { + "epoch": 0.56, + "learning_rate": 9.52983126055177e-06, + "loss": 1.403, + "step": 5373 + }, + { + "epoch": 0.56, + "eval_loss": 1.4240995645523071, + "eval_runtime": 77.4615, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 5373 + }, + { + "epoch": 0.56, + "learning_rate": 9.526175089925e-06, + "loss": 1.3141, + "step": 5374 + }, + { + "epoch": 0.56, + "learning_rate": 9.522518982778596e-06, + "loss": 1.3733, + "step": 5375 + }, + { + "epoch": 0.56, + "learning_rate": 9.51886293960238e-06, + "loss": 1.3095, + "step": 5376 + }, + { + "epoch": 0.56, + "learning_rate": 9.515206960886162e-06, + "loss": 1.3713, + "step": 5377 + }, + { + "epoch": 0.56, + "learning_rate": 9.51155104711976e-06, + "loss": 1.3585, + "step": 5378 + }, + { + "epoch": 0.56, + "learning_rate": 9.507895198792967e-06, + "loss": 1.3473, + "step": 5379 + }, + { + "epoch": 0.56, + "learning_rate": 9.504239416395576e-06, + "loss": 1.3282, + "step": 5380 + }, + { + "epoch": 0.56, + "learning_rate": 9.500583700417357e-06, + "loss": 1.3655, + "step": 5381 + }, + { + "epoch": 0.56, + "learning_rate": 9.496928051348095e-06, + "loss": 1.4512, + "step": 5382 + }, + { + "epoch": 0.56, + "learning_rate": 9.49327246967755e-06, + "loss": 1.4071, + "step": 5383 + }, + { + "epoch": 0.56, + "learning_rate": 9.489616955895472e-06, + "loss": 1.3703, + "step": 5384 + }, + { + "epoch": 0.56, + "learning_rate": 9.485961510491604e-06, + "loss": 1.3358, + "step": 5385 + }, + { + "epoch": 0.56, + "learning_rate": 9.482306133955691e-06, + "loss": 1.3505, + "step": 5386 + }, + { + "epoch": 0.56, + "learning_rate": 9.478650826777457e-06, + "loss": 1.2578, + "step": 5387 + }, + { + "epoch": 0.57, + "learning_rate": 9.474995589446612e-06, + "loss": 1.4298, + "step": 5388 + }, + { + "epoch": 0.57, + "learning_rate": 9.471340422452864e-06, + "loss": 1.4044, + "step": 5389 + }, + { + "epoch": 0.57, + "learning_rate": 9.467685326285922e-06, + "loss": 1.3524, + "step": 5390 + }, + { + "epoch": 0.57, + "learning_rate": 9.46403030143547e-06, + "loss": 1.3017, + "step": 5391 + }, + { + "epoch": 0.57, + "learning_rate": 9.460375348391185e-06, + "loss": 1.3361, + "step": 5392 + }, + { + "epoch": 0.57, + "learning_rate": 9.456720467642733e-06, + "loss": 1.3182, + "step": 5393 + }, + { + "epoch": 0.57, + "learning_rate": 9.453065659679785e-06, + "loss": 1.3869, + "step": 5394 + }, + { + "epoch": 0.57, + "learning_rate": 9.449410924991986e-06, + "loss": 1.3161, + "step": 5395 + }, + { + "epoch": 0.57, + "learning_rate": 9.44575626406897e-06, + "loss": 1.3, + "step": 5396 + }, + { + "epoch": 0.57, + "learning_rate": 9.442101677400378e-06, + "loss": 1.5103, + "step": 5397 + }, + { + "epoch": 0.57, + "learning_rate": 9.438447165475828e-06, + "loss": 1.3511, + "step": 5398 + }, + { + "epoch": 0.57, + "learning_rate": 9.43479272878493e-06, + "loss": 1.3461, + "step": 5399 + }, + { + "epoch": 0.57, + "learning_rate": 9.431138367817277e-06, + "loss": 1.2657, + "step": 5400 + }, + { + "epoch": 0.57, + "learning_rate": 9.427484083062472e-06, + "loss": 1.3736, + "step": 5401 + }, + { + "epoch": 0.57, + "learning_rate": 9.423829875010089e-06, + "loss": 1.3476, + "step": 5402 + }, + { + "epoch": 0.57, + "learning_rate": 9.4201757441497e-06, + "loss": 1.3495, + "step": 5403 + }, + { + "epoch": 0.57, + "learning_rate": 9.416521690970857e-06, + "loss": 1.387, + "step": 5404 + }, + { + "epoch": 0.57, + "learning_rate": 9.41286771596312e-06, + "loss": 1.2829, + "step": 5405 + }, + { + "epoch": 0.57, + "learning_rate": 9.409213819616022e-06, + "loss": 1.3544, + "step": 5406 + }, + { + "epoch": 0.57, + "learning_rate": 9.405560002419098e-06, + "loss": 1.3202, + "step": 5407 + }, + { + "epoch": 0.57, + "learning_rate": 9.40190626486185e-06, + "loss": 1.3034, + "step": 5408 + }, + { + "epoch": 0.57, + "learning_rate": 9.398252607433801e-06, + "loss": 1.3223, + "step": 5409 + }, + { + "epoch": 0.57, + "learning_rate": 9.394599030624443e-06, + "loss": 1.3327, + "step": 5410 + }, + { + "epoch": 0.57, + "learning_rate": 9.390945534923258e-06, + "loss": 1.3248, + "step": 5411 + }, + { + "epoch": 0.57, + "learning_rate": 9.387292120819716e-06, + "loss": 1.3084, + "step": 5412 + }, + { + "epoch": 0.57, + "learning_rate": 9.383638788803291e-06, + "loss": 1.344, + "step": 5413 + }, + { + "epoch": 0.57, + "learning_rate": 9.379985539363436e-06, + "loss": 1.3354, + "step": 5414 + }, + { + "epoch": 0.57, + "learning_rate": 9.376332372989586e-06, + "loss": 1.3291, + "step": 5415 + }, + { + "epoch": 0.57, + "learning_rate": 9.372679290171167e-06, + "loss": 1.3468, + "step": 5416 + }, + { + "epoch": 0.57, + "learning_rate": 9.36902629139761e-06, + "loss": 1.3481, + "step": 5417 + }, + { + "epoch": 0.57, + "learning_rate": 9.36537337715832e-06, + "loss": 1.3309, + "step": 5418 + }, + { + "epoch": 0.57, + "learning_rate": 9.361720547942683e-06, + "loss": 1.362, + "step": 5419 + }, + { + "epoch": 0.57, + "learning_rate": 9.358067804240098e-06, + "loss": 1.3647, + "step": 5420 + }, + { + "epoch": 0.57, + "learning_rate": 9.354415146539933e-06, + "loss": 1.4511, + "step": 5421 + }, + { + "epoch": 0.57, + "learning_rate": 9.350762575331554e-06, + "loss": 1.3379, + "step": 5422 + }, + { + "epoch": 0.57, + "learning_rate": 9.3471100911043e-06, + "loss": 1.5468, + "step": 5423 + }, + { + "epoch": 0.57, + "learning_rate": 9.343457694347524e-06, + "loss": 1.4259, + "step": 5424 + }, + { + "epoch": 0.57, + "learning_rate": 9.339805385550548e-06, + "loss": 1.3816, + "step": 5425 + }, + { + "epoch": 0.57, + "learning_rate": 9.336153165202689e-06, + "loss": 1.3627, + "step": 5426 + }, + { + "epoch": 0.57, + "learning_rate": 9.332501033793242e-06, + "loss": 1.3338, + "step": 5427 + }, + { + "epoch": 0.57, + "learning_rate": 9.328848991811509e-06, + "loss": 1.2946, + "step": 5428 + }, + { + "epoch": 0.57, + "learning_rate": 9.325197039746769e-06, + "loss": 1.3405, + "step": 5429 + }, + { + "epoch": 0.57, + "learning_rate": 9.321545178088288e-06, + "loss": 1.3549, + "step": 5430 + }, + { + "epoch": 0.57, + "learning_rate": 9.317893407325314e-06, + "loss": 1.3225, + "step": 5431 + }, + { + "epoch": 0.57, + "learning_rate": 9.314241727947101e-06, + "loss": 1.3457, + "step": 5432 + }, + { + "epoch": 0.57, + "learning_rate": 9.310590140442878e-06, + "loss": 1.311, + "step": 5433 + }, + { + "epoch": 0.57, + "learning_rate": 9.306938645301862e-06, + "loss": 1.3615, + "step": 5434 + }, + { + "epoch": 0.57, + "learning_rate": 9.303287243013255e-06, + "loss": 1.3495, + "step": 5435 + }, + { + "epoch": 0.57, + "learning_rate": 9.29963593406626e-06, + "loss": 1.3899, + "step": 5436 + }, + { + "epoch": 0.57, + "learning_rate": 9.295984718950058e-06, + "loss": 1.3189, + "step": 5437 + }, + { + "epoch": 0.57, + "learning_rate": 9.292333598153813e-06, + "loss": 1.4199, + "step": 5438 + }, + { + "epoch": 0.57, + "learning_rate": 9.288682572166677e-06, + "loss": 1.4751, + "step": 5439 + }, + { + "epoch": 0.57, + "learning_rate": 9.285031641477804e-06, + "loss": 1.3435, + "step": 5440 + }, + { + "epoch": 0.57, + "learning_rate": 9.281380806576322e-06, + "loss": 1.2954, + "step": 5441 + }, + { + "epoch": 0.57, + "learning_rate": 9.277730067951341e-06, + "loss": 1.3414, + "step": 5442 + }, + { + "epoch": 0.57, + "learning_rate": 9.274079426091978e-06, + "loss": 1.3642, + "step": 5443 + }, + { + "epoch": 0.57, + "learning_rate": 9.27042888148732e-06, + "loss": 1.3651, + "step": 5444 + }, + { + "epoch": 0.57, + "learning_rate": 9.266778434626448e-06, + "loss": 1.3995, + "step": 5445 + }, + { + "epoch": 0.57, + "learning_rate": 9.263128085998421e-06, + "loss": 1.2692, + "step": 5446 + }, + { + "epoch": 0.57, + "learning_rate": 9.2594778360923e-06, + "loss": 1.4355, + "step": 5447 + }, + { + "epoch": 0.57, + "learning_rate": 9.255827685397124e-06, + "loss": 1.4262, + "step": 5448 + }, + { + "epoch": 0.57, + "learning_rate": 9.252177634401917e-06, + "loss": 1.3372, + "step": 5449 + }, + { + "epoch": 0.57, + "learning_rate": 9.248527683595685e-06, + "loss": 1.4603, + "step": 5450 + }, + { + "epoch": 0.57, + "learning_rate": 9.24487783346744e-06, + "loss": 1.446, + "step": 5451 + }, + { + "epoch": 0.57, + "learning_rate": 9.241228084506167e-06, + "loss": 1.4088, + "step": 5452 + }, + { + "epoch": 0.57, + "learning_rate": 9.237578437200832e-06, + "loss": 1.3074, + "step": 5453 + }, + { + "epoch": 0.57, + "learning_rate": 9.233928892040392e-06, + "loss": 1.4347, + "step": 5454 + }, + { + "epoch": 0.57, + "learning_rate": 9.230279449513802e-06, + "loss": 1.2982, + "step": 5455 + }, + { + "epoch": 0.57, + "learning_rate": 9.226630110109988e-06, + "loss": 1.2928, + "step": 5456 + }, + { + "epoch": 0.57, + "learning_rate": 9.222980874317869e-06, + "loss": 1.2849, + "step": 5457 + }, + { + "epoch": 0.57, + "learning_rate": 9.219331742626343e-06, + "loss": 1.3137, + "step": 5458 + }, + { + "epoch": 0.57, + "learning_rate": 9.215682715524309e-06, + "loss": 1.3523, + "step": 5459 + }, + { + "epoch": 0.57, + "learning_rate": 9.21203379350064e-06, + "loss": 1.381, + "step": 5460 + }, + { + "epoch": 0.57, + "learning_rate": 9.208384977044191e-06, + "loss": 1.286, + "step": 5461 + }, + { + "epoch": 0.57, + "learning_rate": 9.204736266643819e-06, + "loss": 1.3467, + "step": 5462 + }, + { + "epoch": 0.57, + "learning_rate": 9.201087662788353e-06, + "loss": 1.3582, + "step": 5463 + }, + { + "epoch": 0.57, + "learning_rate": 9.197439165966617e-06, + "loss": 1.3912, + "step": 5464 + }, + { + "epoch": 0.57, + "learning_rate": 9.193790776667402e-06, + "loss": 1.3144, + "step": 5465 + }, + { + "epoch": 0.57, + "learning_rate": 9.190142495379515e-06, + "loss": 1.3403, + "step": 5466 + }, + { + "epoch": 0.57, + "learning_rate": 9.186494322591725e-06, + "loss": 1.3253, + "step": 5467 + }, + { + "epoch": 0.57, + "learning_rate": 9.182846258792794e-06, + "loss": 1.2908, + "step": 5468 + }, + { + "epoch": 0.57, + "learning_rate": 9.179198304471463e-06, + "loss": 1.3486, + "step": 5469 + }, + { + "epoch": 0.57, + "learning_rate": 9.175550460116473e-06, + "loss": 1.3915, + "step": 5470 + }, + { + "epoch": 0.57, + "learning_rate": 9.171902726216538e-06, + "loss": 1.3441, + "step": 5471 + }, + { + "epoch": 0.57, + "learning_rate": 9.168255103260362e-06, + "loss": 1.3196, + "step": 5472 + }, + { + "epoch": 0.57, + "learning_rate": 9.164607591736627e-06, + "loss": 1.3279, + "step": 5473 + }, + { + "epoch": 0.57, + "learning_rate": 9.160960192134011e-06, + "loss": 1.2643, + "step": 5474 + }, + { + "epoch": 0.57, + "learning_rate": 9.157312904941174e-06, + "loss": 1.3327, + "step": 5475 + }, + { + "epoch": 0.57, + "learning_rate": 9.153665730646756e-06, + "loss": 1.4016, + "step": 5476 + }, + { + "epoch": 0.57, + "learning_rate": 9.150018669739378e-06, + "loss": 1.3614, + "step": 5477 + }, + { + "epoch": 0.57, + "learning_rate": 9.146371722707662e-06, + "loss": 1.3469, + "step": 5478 + }, + { + "epoch": 0.57, + "learning_rate": 9.142724890040204e-06, + "loss": 1.3625, + "step": 5479 + }, + { + "epoch": 0.57, + "learning_rate": 9.139078172225585e-06, + "loss": 1.3879, + "step": 5480 + }, + { + "epoch": 0.57, + "learning_rate": 9.135431569752362e-06, + "loss": 1.3738, + "step": 5481 + }, + { + "epoch": 0.57, + "learning_rate": 9.131785083109101e-06, + "loss": 1.3507, + "step": 5482 + }, + { + "epoch": 0.57, + "learning_rate": 9.128138712784331e-06, + "loss": 1.3681, + "step": 5483 + }, + { + "epoch": 0.58, + "learning_rate": 9.124492459266567e-06, + "loss": 1.332, + "step": 5484 + }, + { + "epoch": 0.58, + "learning_rate": 9.12084632304432e-06, + "loss": 1.4746, + "step": 5485 + }, + { + "epoch": 0.58, + "learning_rate": 9.11720030460608e-06, + "loss": 1.2775, + "step": 5486 + }, + { + "epoch": 0.58, + "learning_rate": 9.113554404440317e-06, + "loss": 1.2567, + "step": 5487 + }, + { + "epoch": 0.58, + "learning_rate": 9.10990862303548e-06, + "loss": 1.3935, + "step": 5488 + }, + { + "epoch": 0.58, + "learning_rate": 9.106262960880024e-06, + "loss": 1.3544, + "step": 5489 + }, + { + "epoch": 0.58, + "learning_rate": 9.102617418462365e-06, + "loss": 1.4023, + "step": 5490 + }, + { + "epoch": 0.58, + "learning_rate": 9.098971996270918e-06, + "loss": 1.3759, + "step": 5491 + }, + { + "epoch": 0.58, + "learning_rate": 9.095326694794064e-06, + "loss": 1.4165, + "step": 5492 + }, + { + "epoch": 0.58, + "learning_rate": 9.091681514520194e-06, + "loss": 1.3189, + "step": 5493 + }, + { + "epoch": 0.58, + "learning_rate": 9.088036455937663e-06, + "loss": 1.3135, + "step": 5494 + }, + { + "epoch": 0.58, + "learning_rate": 9.084391519534815e-06, + "loss": 1.3521, + "step": 5495 + }, + { + "epoch": 0.58, + "learning_rate": 9.080746705799971e-06, + "loss": 1.3314, + "step": 5496 + }, + { + "epoch": 0.58, + "learning_rate": 9.077102015221457e-06, + "loss": 1.3119, + "step": 5497 + }, + { + "epoch": 0.58, + "learning_rate": 9.073457448287557e-06, + "loss": 1.2895, + "step": 5498 + }, + { + "epoch": 0.58, + "learning_rate": 9.069813005486554e-06, + "loss": 1.3155, + "step": 5499 + }, + { + "epoch": 0.58, + "learning_rate": 9.066168687306701e-06, + "loss": 1.4048, + "step": 5500 + }, + { + "epoch": 0.58, + "learning_rate": 9.062524494236256e-06, + "loss": 1.3665, + "step": 5501 + }, + { + "epoch": 0.58, + "learning_rate": 9.058880426763442e-06, + "loss": 1.3258, + "step": 5502 + }, + { + "epoch": 0.58, + "learning_rate": 9.05523648537647e-06, + "loss": 1.3078, + "step": 5503 + }, + { + "epoch": 0.58, + "learning_rate": 9.051592670563527e-06, + "loss": 1.361, + "step": 5504 + }, + { + "epoch": 0.58, + "learning_rate": 9.047948982812801e-06, + "loss": 1.3557, + "step": 5505 + }, + { + "epoch": 0.58, + "learning_rate": 9.044305422612453e-06, + "loss": 1.5733, + "step": 5506 + }, + { + "epoch": 0.58, + "learning_rate": 9.040661990450617e-06, + "loss": 1.2835, + "step": 5507 + }, + { + "epoch": 0.58, + "learning_rate": 9.037018686815428e-06, + "loss": 1.311, + "step": 5508 + }, + { + "epoch": 0.58, + "learning_rate": 9.033375512194993e-06, + "loss": 1.3949, + "step": 5509 + }, + { + "epoch": 0.58, + "learning_rate": 9.029732467077405e-06, + "loss": 1.356, + "step": 5510 + }, + { + "epoch": 0.58, + "learning_rate": 9.026089551950727e-06, + "loss": 1.3695, + "step": 5511 + }, + { + "epoch": 0.58, + "learning_rate": 9.022446767303033e-06, + "loss": 1.3325, + "step": 5512 + }, + { + "epoch": 0.58, + "learning_rate": 9.018804113622353e-06, + "loss": 1.401, + "step": 5513 + }, + { + "epoch": 0.58, + "learning_rate": 9.015161591396713e-06, + "loss": 1.3632, + "step": 5514 + }, + { + "epoch": 0.58, + "learning_rate": 9.011519201114108e-06, + "loss": 1.3697, + "step": 5515 + }, + { + "epoch": 0.58, + "learning_rate": 9.007876943262538e-06, + "loss": 1.2604, + "step": 5516 + }, + { + "epoch": 0.58, + "learning_rate": 9.004234818329964e-06, + "loss": 1.3557, + "step": 5517 + }, + { + "epoch": 0.58, + "learning_rate": 9.000592826804342e-06, + "loss": 1.3248, + "step": 5518 + }, + { + "epoch": 0.58, + "learning_rate": 8.996950969173596e-06, + "loss": 1.3237, + "step": 5519 + }, + { + "epoch": 0.58, + "learning_rate": 8.99330924592565e-06, + "loss": 1.339, + "step": 5520 + }, + { + "epoch": 0.58, + "learning_rate": 8.989667657548402e-06, + "loss": 1.3218, + "step": 5521 + }, + { + "epoch": 0.58, + "learning_rate": 8.986026204529728e-06, + "loss": 1.3354, + "step": 5522 + }, + { + "epoch": 0.58, + "learning_rate": 8.982384887357484e-06, + "loss": 1.3011, + "step": 5523 + }, + { + "epoch": 0.58, + "learning_rate": 8.978743706519524e-06, + "loss": 1.3526, + "step": 5524 + }, + { + "epoch": 0.58, + "learning_rate": 8.975102662503666e-06, + "loss": 1.3298, + "step": 5525 + }, + { + "epoch": 0.58, + "learning_rate": 8.971461755797718e-06, + "loss": 1.328, + "step": 5526 + }, + { + "epoch": 0.58, + "learning_rate": 8.967820986889461e-06, + "loss": 1.3705, + "step": 5527 + }, + { + "epoch": 0.58, + "learning_rate": 8.964180356266676e-06, + "loss": 1.3814, + "step": 5528 + }, + { + "epoch": 0.58, + "learning_rate": 8.96053986441711e-06, + "loss": 1.37, + "step": 5529 + }, + { + "epoch": 0.58, + "learning_rate": 8.956899511828489e-06, + "loss": 1.3224, + "step": 5530 + }, + { + "epoch": 0.58, + "learning_rate": 8.953259298988536e-06, + "loss": 1.3416, + "step": 5531 + }, + { + "epoch": 0.58, + "learning_rate": 8.949619226384942e-06, + "loss": 1.4212, + "step": 5532 + }, + { + "epoch": 0.58, + "learning_rate": 8.945979294505383e-06, + "loss": 1.4145, + "step": 5533 + }, + { + "epoch": 0.58, + "learning_rate": 8.942339503837512e-06, + "loss": 1.2179, + "step": 5534 + }, + { + "epoch": 0.58, + "learning_rate": 8.938699854868976e-06, + "loss": 1.3239, + "step": 5535 + }, + { + "epoch": 0.58, + "learning_rate": 8.93506034808739e-06, + "loss": 1.3488, + "step": 5536 + }, + { + "epoch": 0.58, + "learning_rate": 8.931420983980357e-06, + "loss": 1.3283, + "step": 5537 + }, + { + "epoch": 0.58, + "learning_rate": 8.927781763035449e-06, + "loss": 1.3866, + "step": 5538 + }, + { + "epoch": 0.58, + "learning_rate": 8.924142685740239e-06, + "loss": 1.3877, + "step": 5539 + }, + { + "epoch": 0.58, + "learning_rate": 8.920503752582265e-06, + "loss": 1.2511, + "step": 5540 + }, + { + "epoch": 0.58, + "learning_rate": 8.916864964049056e-06, + "loss": 1.3581, + "step": 5541 + }, + { + "epoch": 0.58, + "learning_rate": 8.913226320628104e-06, + "loss": 1.387, + "step": 5542 + }, + { + "epoch": 0.58, + "learning_rate": 8.909587822806905e-06, + "loss": 1.3785, + "step": 5543 + }, + { + "epoch": 0.58, + "learning_rate": 8.905949471072921e-06, + "loss": 1.4302, + "step": 5544 + }, + { + "epoch": 0.58, + "learning_rate": 8.9023112659136e-06, + "loss": 1.439, + "step": 5545 + }, + { + "epoch": 0.58, + "learning_rate": 8.898673207816357e-06, + "loss": 1.3257, + "step": 5546 + }, + { + "epoch": 0.58, + "learning_rate": 8.895035297268611e-06, + "loss": 1.4237, + "step": 5547 + }, + { + "epoch": 0.58, + "learning_rate": 8.891397534757745e-06, + "loss": 1.3141, + "step": 5548 + }, + { + "epoch": 0.58, + "learning_rate": 8.887759920771127e-06, + "loss": 1.3069, + "step": 5549 + }, + { + "epoch": 0.58, + "learning_rate": 8.884122455796095e-06, + "loss": 1.2703, + "step": 5550 + }, + { + "epoch": 0.58, + "learning_rate": 8.880485140319986e-06, + "loss": 1.2929, + "step": 5551 + }, + { + "epoch": 0.58, + "learning_rate": 8.876847974830103e-06, + "loss": 1.3719, + "step": 5552 + }, + { + "epoch": 0.58, + "learning_rate": 8.873210959813731e-06, + "loss": 1.3481, + "step": 5553 + }, + { + "epoch": 0.58, + "learning_rate": 8.869574095758141e-06, + "loss": 1.3609, + "step": 5554 + }, + { + "epoch": 0.58, + "learning_rate": 8.865937383150577e-06, + "loss": 1.3137, + "step": 5555 + }, + { + "epoch": 0.58, + "learning_rate": 8.862300822478265e-06, + "loss": 1.3602, + "step": 5556 + }, + { + "epoch": 0.58, + "learning_rate": 8.858664414228409e-06, + "loss": 1.3142, + "step": 5557 + }, + { + "epoch": 0.58, + "learning_rate": 8.855028158888196e-06, + "loss": 1.288, + "step": 5558 + }, + { + "epoch": 0.58, + "learning_rate": 8.851392056944791e-06, + "loss": 1.3407, + "step": 5559 + }, + { + "epoch": 0.58, + "learning_rate": 8.847756108885342e-06, + "loss": 1.3118, + "step": 5560 + }, + { + "epoch": 0.58, + "learning_rate": 8.84412031519696e-06, + "loss": 1.3646, + "step": 5561 + }, + { + "epoch": 0.58, + "learning_rate": 8.840484676366761e-06, + "loss": 1.3896, + "step": 5562 + }, + { + "epoch": 0.58, + "learning_rate": 8.836849192881822e-06, + "loss": 1.3296, + "step": 5563 + }, + { + "epoch": 0.58, + "learning_rate": 8.833213865229208e-06, + "loss": 1.2918, + "step": 5564 + }, + { + "epoch": 0.58, + "learning_rate": 8.82957869389595e-06, + "loss": 1.4811, + "step": 5565 + }, + { + "epoch": 0.58, + "learning_rate": 8.82594367936908e-06, + "loss": 1.3877, + "step": 5566 + }, + { + "epoch": 0.58, + "learning_rate": 8.822308822135588e-06, + "loss": 1.3716, + "step": 5567 + }, + { + "epoch": 0.58, + "learning_rate": 8.818674122682456e-06, + "loss": 1.3204, + "step": 5568 + }, + { + "epoch": 0.58, + "learning_rate": 8.815039581496634e-06, + "loss": 1.326, + "step": 5569 + }, + { + "epoch": 0.58, + "learning_rate": 8.811405199065066e-06, + "loss": 1.3762, + "step": 5570 + }, + { + "epoch": 0.58, + "learning_rate": 8.807770975874658e-06, + "loss": 1.2944, + "step": 5571 + }, + { + "epoch": 0.58, + "learning_rate": 8.804136912412311e-06, + "loss": 1.3057, + "step": 5572 + }, + { + "epoch": 0.58, + "eval_loss": 1.4187605381011963, + "eval_runtime": 77.5157, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 5572 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 2.4927124935616443e+20, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-5572/training_args.bin b/checkpoint-5572/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-5572/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-6368/config.json b/checkpoint-6368/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-6368/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-6368/generation_config.json b/checkpoint-6368/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-6368/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-6368/model-00001-of-00003.safetensors b/checkpoint-6368/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8fde6a00fdd195f9ecb6f5c6c254933ba0866266 --- /dev/null +++ b/checkpoint-6368/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4762f729403090194d330bedaa8e82939e7bb4acd95bc2942cfc549fd2ab3a26 +size 4943162336 diff --git a/checkpoint-6368/model-00002-of-00003.safetensors b/checkpoint-6368/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7c11cca8ed46ba599183441d9f79b1a2c89c4ea0 --- /dev/null +++ b/checkpoint-6368/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc3b4faed849e332d05d843f6b1c396a1d6008610a4d6118f9c41c6f22ad8e93 +size 4999819336 diff --git a/checkpoint-6368/model-00003-of-00003.safetensors b/checkpoint-6368/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..af93ce8a6bc65cadb1cfb029d203eef7618715aa --- /dev/null +++ b/checkpoint-6368/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c4b0d397d581d7e96859720089e24eedf2dff0b87384a4a1558b448fa8e07b5 +size 4540516344 diff --git a/checkpoint-6368/model.safetensors.index.json b/checkpoint-6368/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-6368/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-6368/optimizer.pt b/checkpoint-6368/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..4923fccc768052200e2d64a64861865115d032f1 --- /dev/null +++ b/checkpoint-6368/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8734da82971ae6cfe309268620e959ef3c7eb48f7811011c16af06c4ffc39b6a +size 14512103560 diff --git a/checkpoint-6368/rng_state_0.pth b/checkpoint-6368/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..4c0e93d1bcf5b5fe0c0bbc69223f1098165b132a --- /dev/null +++ b/checkpoint-6368/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef181294409ae2aaf29fe19d73be43d564a63ce83de6221fc200bc6b51451132 +size 15984 diff --git a/checkpoint-6368/rng_state_1.pth b/checkpoint-6368/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..ec651afaa46e88a496f0a27e4d283c3976c0f713 --- /dev/null +++ b/checkpoint-6368/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9b71e62a06a5a913a01f8788a3587ea4fb39ed8ac02d10a9b3ac00afbf5e941 +size 15984 diff --git a/checkpoint-6368/rng_state_2.pth b/checkpoint-6368/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..76cb79e49eab7e702aba50496102b451599f7590 --- /dev/null +++ b/checkpoint-6368/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84593df49deed8ea6e276d2e568ddbe29f0787275e99e8b328af045062baf0b4 +size 15984 diff --git a/checkpoint-6368/rng_state_3.pth b/checkpoint-6368/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..035102bac42dcd2d49b36c2d55ff4def7f984e58 --- /dev/null +++ b/checkpoint-6368/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a79a5528a33a87f3b0e2630e0ff3e747c0f45dbd9884b7df358f64263a644ed5 +size 15984 diff --git a/checkpoint-6368/rng_state_4.pth b/checkpoint-6368/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..ee909a65021a4c6ad94921b09b5852901232c76a --- /dev/null +++ b/checkpoint-6368/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58423971253a2a3c9345aad38b2cacce29712907c341a776117df5d0d0c3133a +size 15984 diff --git a/checkpoint-6368/rng_state_5.pth b/checkpoint-6368/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..8e4d32e5e6a885ac9f1bbdc45fe895a217125d95 --- /dev/null +++ b/checkpoint-6368/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73271c3b15259d43f4636c021faa8ca99604b323d4ef20329b27264ab2e762f1 +size 15984 diff --git a/checkpoint-6368/rng_state_6.pth b/checkpoint-6368/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..55d3d7c009663fe055a901d32de2f93393b07363 --- /dev/null +++ b/checkpoint-6368/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:623169de882cf16bd4e3d95b1f28f95354331573d66a274969bfd324cc075874 +size 15984 diff --git a/checkpoint-6368/rng_state_7.pth b/checkpoint-6368/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..e47b34c3c1955633727bc7b10cb65fc51b597b43 --- /dev/null +++ b/checkpoint-6368/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5131c69105f507a1d8c319021291bf883bb693f7a4f85e14ca31dac9ac82cf76 +size 15984 diff --git a/checkpoint-6368/scheduler.pt b/checkpoint-6368/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..57fd6bb3624f6d0f2ff78ce493ce73efe1a2d63a --- /dev/null +++ b/checkpoint-6368/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:264108bc19e390cfca20d5e3724455e8b8479ff038829f8ae2a41e804910b893 +size 1064 diff --git a/checkpoint-6368/special_tokens_map.json b/checkpoint-6368/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-6368/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-6368/tokenizer.model b/checkpoint-6368/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-6368/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-6368/tokenizer_config.json b/checkpoint-6368/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-6368/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-6368/trainer_state.json b/checkpoint-6368/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..d52387fde32c80bd103ca93b380511ed01553a25 --- /dev/null +++ b/checkpoint-6368/trainer_state.json @@ -0,0 +1,38484 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.6677852348993288, + "eval_steps": 199, + "global_step": 6368, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + }, + { + "epoch": 0.21, + "learning_rate": 1.928689129323009e-05, + "loss": 1.421, + "step": 1991 + }, + { + "epoch": 0.21, + "learning_rate": 1.928553323396003e-05, + "loss": 1.5625, + "step": 1992 + }, + { + "epoch": 0.21, + "learning_rate": 1.92841739306671e-05, + "loss": 1.5198, + "step": 1993 + }, + { + "epoch": 0.21, + "learning_rate": 1.9282813383533415e-05, + "loss": 1.5116, + "step": 1994 + }, + { + "epoch": 0.21, + "learning_rate": 1.9281451592741247e-05, + "loss": 1.4306, + "step": 1995 + }, + { + "epoch": 0.21, + "learning_rate": 1.9280088558473046e-05, + "loss": 1.5425, + "step": 1996 + }, + { + "epoch": 0.21, + "learning_rate": 1.9278724280911424e-05, + "loss": 1.4972, + "step": 1997 + }, + { + "epoch": 0.21, + "learning_rate": 1.9277358760239156e-05, + "loss": 1.5185, + "step": 1998 + }, + { + "epoch": 0.21, + "learning_rate": 1.9275991996639188e-05, + "loss": 1.5187, + "step": 1999 + }, + { + "epoch": 0.21, + "learning_rate": 1.927462399029463e-05, + "loss": 1.4325, + "step": 2000 + }, + { + "epoch": 0.21, + "learning_rate": 1.9273254741388763e-05, + "loss": 1.4397, + "step": 2001 + }, + { + "epoch": 0.21, + "learning_rate": 1.927188425010503e-05, + "loss": 1.5319, + "step": 2002 + }, + { + "epoch": 0.21, + "learning_rate": 1.9270512516627042e-05, + "loss": 1.5664, + "step": 2003 + }, + { + "epoch": 0.21, + "learning_rate": 1.9269139541138574e-05, + "loss": 1.5227, + "step": 2004 + }, + { + "epoch": 0.21, + "learning_rate": 1.926776532382357e-05, + "loss": 1.5187, + "step": 2005 + }, + { + "epoch": 0.21, + "learning_rate": 1.9266389864866134e-05, + "loss": 1.4029, + "step": 2006 + }, + { + "epoch": 0.21, + "learning_rate": 1.9265013164450557e-05, + "loss": 1.387, + "step": 2007 + }, + { + "epoch": 0.21, + "learning_rate": 1.9263635222761268e-05, + "loss": 1.5047, + "step": 2008 + }, + { + "epoch": 0.21, + "learning_rate": 1.9262256039982882e-05, + "loss": 1.4816, + "step": 2009 + }, + { + "epoch": 0.21, + "learning_rate": 1.9260875616300172e-05, + "loss": 1.4607, + "step": 2010 + }, + { + "epoch": 0.21, + "learning_rate": 1.9259493951898084e-05, + "loss": 1.628, + "step": 2011 + }, + { + "epoch": 0.21, + "learning_rate": 1.9258111046961714e-05, + "loss": 1.4149, + "step": 2012 + }, + { + "epoch": 0.21, + "learning_rate": 1.925672690167635e-05, + "loss": 1.5303, + "step": 2013 + }, + { + "epoch": 0.21, + "learning_rate": 1.925534151622742e-05, + "loss": 1.5198, + "step": 2014 + }, + { + "epoch": 0.21, + "learning_rate": 1.9253954890800535e-05, + "loss": 1.6422, + "step": 2015 + }, + { + "epoch": 0.21, + "learning_rate": 1.925256702558147e-05, + "loss": 1.4738, + "step": 2016 + }, + { + "epoch": 0.21, + "learning_rate": 1.925117792075616e-05, + "loss": 1.4752, + "step": 2017 + }, + { + "epoch": 0.21, + "learning_rate": 1.9249787576510713e-05, + "loss": 1.4547, + "step": 2018 + }, + { + "epoch": 0.21, + "learning_rate": 1.924839599303139e-05, + "loss": 1.4864, + "step": 2019 + }, + { + "epoch": 0.21, + "learning_rate": 1.9247003170504638e-05, + "loss": 1.5037, + "step": 2020 + }, + { + "epoch": 0.21, + "learning_rate": 1.9245609109117053e-05, + "loss": 1.5089, + "step": 2021 + }, + { + "epoch": 0.21, + "learning_rate": 1.924421380905541e-05, + "loss": 1.5616, + "step": 2022 + }, + { + "epoch": 0.21, + "learning_rate": 1.9242817270506634e-05, + "loss": 1.4592, + "step": 2023 + }, + { + "epoch": 0.21, + "learning_rate": 1.9241419493657832e-05, + "loss": 1.5592, + "step": 2024 + }, + { + "epoch": 0.21, + "learning_rate": 1.924002047869627e-05, + "loss": 1.4897, + "step": 2025 + }, + { + "epoch": 0.21, + "learning_rate": 1.9238620225809375e-05, + "loss": 1.4743, + "step": 2026 + }, + { + "epoch": 0.21, + "learning_rate": 1.923721873518475e-05, + "loss": 1.4686, + "step": 2027 + }, + { + "epoch": 0.21, + "learning_rate": 1.923581600701016e-05, + "loss": 1.461, + "step": 2028 + }, + { + "epoch": 0.21, + "learning_rate": 1.9234412041473528e-05, + "loss": 1.6622, + "step": 2029 + }, + { + "epoch": 0.21, + "learning_rate": 1.9233006838762955e-05, + "loss": 1.4707, + "step": 2030 + }, + { + "epoch": 0.21, + "learning_rate": 1.92316003990667e-05, + "loss": 1.5566, + "step": 2031 + }, + { + "epoch": 0.21, + "learning_rate": 1.9230192722573188e-05, + "loss": 1.4881, + "step": 2032 + }, + { + "epoch": 0.21, + "learning_rate": 1.9228783809471015e-05, + "loss": 1.6124, + "step": 2033 + }, + { + "epoch": 0.21, + "learning_rate": 1.9227373659948937e-05, + "loss": 1.3508, + "step": 2034 + }, + { + "epoch": 0.21, + "learning_rate": 1.9225962274195876e-05, + "loss": 1.4418, + "step": 2035 + }, + { + "epoch": 0.21, + "learning_rate": 1.9224549652400927e-05, + "loss": 1.3954, + "step": 2036 + }, + { + "epoch": 0.21, + "learning_rate": 1.922313579475334e-05, + "loss": 1.4798, + "step": 2037 + }, + { + "epoch": 0.21, + "learning_rate": 1.922172070144254e-05, + "loss": 1.4556, + "step": 2038 + }, + { + "epoch": 0.21, + "learning_rate": 1.922030437265811e-05, + "loss": 1.4987, + "step": 2039 + }, + { + "epoch": 0.21, + "learning_rate": 1.9218886808589796e-05, + "loss": 1.4857, + "step": 2040 + }, + { + "epoch": 0.21, + "learning_rate": 1.9217468009427527e-05, + "loss": 1.5289, + "step": 2041 + }, + { + "epoch": 0.21, + "learning_rate": 1.921604797536138e-05, + "loss": 1.5267, + "step": 2042 + }, + { + "epoch": 0.21, + "learning_rate": 1.9214626706581598e-05, + "loss": 1.4655, + "step": 2043 + }, + { + "epoch": 0.21, + "learning_rate": 1.9213204203278602e-05, + "loss": 1.4598, + "step": 2044 + }, + { + "epoch": 0.21, + "learning_rate": 1.9211780465642973e-05, + "loss": 1.4766, + "step": 2045 + }, + { + "epoch": 0.21, + "learning_rate": 1.921035549386545e-05, + "loss": 1.5148, + "step": 2046 + }, + { + "epoch": 0.21, + "learning_rate": 1.9208929288136933e-05, + "loss": 1.5567, + "step": 2047 + }, + { + "epoch": 0.21, + "learning_rate": 1.920750184864852e-05, + "loss": 1.4868, + "step": 2048 + }, + { + "epoch": 0.21, + "learning_rate": 1.920607317559143e-05, + "loss": 1.4752, + "step": 2049 + }, + { + "epoch": 0.21, + "learning_rate": 1.920464326915708e-05, + "loss": 1.4882, + "step": 2050 + }, + { + "epoch": 0.22, + "learning_rate": 1.9203212129537035e-05, + "loss": 1.5933, + "step": 2051 + }, + { + "epoch": 0.22, + "learning_rate": 1.9201779756923037e-05, + "loss": 1.4891, + "step": 2052 + }, + { + "epoch": 0.22, + "learning_rate": 1.9200346151506983e-05, + "loss": 1.4486, + "step": 2053 + }, + { + "epoch": 0.22, + "learning_rate": 1.9198911313480938e-05, + "loss": 1.5091, + "step": 2054 + }, + { + "epoch": 0.22, + "learning_rate": 1.919747524303714e-05, + "loss": 1.4385, + "step": 2055 + }, + { + "epoch": 0.22, + "learning_rate": 1.9196037940367974e-05, + "loss": 1.4104, + "step": 2056 + }, + { + "epoch": 0.22, + "learning_rate": 1.9194599405666015e-05, + "loss": 1.4483, + "step": 2057 + }, + { + "epoch": 0.22, + "learning_rate": 1.9193159639123976e-05, + "loss": 1.4592, + "step": 2058 + }, + { + "epoch": 0.22, + "learning_rate": 1.919171864093476e-05, + "loss": 1.4975, + "step": 2059 + }, + { + "epoch": 0.22, + "learning_rate": 1.9190276411291423e-05, + "loss": 1.4727, + "step": 2060 + }, + { + "epoch": 0.22, + "learning_rate": 1.9188832950387178e-05, + "loss": 1.4791, + "step": 2061 + }, + { + "epoch": 0.22, + "learning_rate": 1.9187388258415423e-05, + "loss": 1.3806, + "step": 2062 + }, + { + "epoch": 0.22, + "learning_rate": 1.9185942335569697e-05, + "loss": 1.4514, + "step": 2063 + }, + { + "epoch": 0.22, + "learning_rate": 1.9184495182043727e-05, + "loss": 1.4389, + "step": 2064 + }, + { + "epoch": 0.22, + "learning_rate": 1.918304679803139e-05, + "loss": 1.5088, + "step": 2065 + }, + { + "epoch": 0.22, + "learning_rate": 1.9181597183726733e-05, + "loss": 1.4665, + "step": 2066 + }, + { + "epoch": 0.22, + "learning_rate": 1.9180146339323966e-05, + "loss": 1.489, + "step": 2067 + }, + { + "epoch": 0.22, + "learning_rate": 1.9178694265017466e-05, + "loss": 1.5215, + "step": 2068 + }, + { + "epoch": 0.22, + "learning_rate": 1.9177240961001775e-05, + "loss": 1.5152, + "step": 2069 + }, + { + "epoch": 0.22, + "learning_rate": 1.9175786427471594e-05, + "loss": 1.4418, + "step": 2070 + }, + { + "epoch": 0.22, + "learning_rate": 1.91743306646218e-05, + "loss": 1.5001, + "step": 2071 + }, + { + "epoch": 0.22, + "learning_rate": 1.9172873672647417e-05, + "loss": 1.4879, + "step": 2072 + }, + { + "epoch": 0.22, + "learning_rate": 1.917141545174366e-05, + "loss": 1.5299, + "step": 2073 + }, + { + "epoch": 0.22, + "learning_rate": 1.9169956002105877e-05, + "loss": 1.4602, + "step": 2074 + }, + { + "epoch": 0.22, + "learning_rate": 1.9168495323929605e-05, + "loss": 1.4921, + "step": 2075 + }, + { + "epoch": 0.22, + "learning_rate": 1.916703341741054e-05, + "loss": 1.4659, + "step": 2076 + }, + { + "epoch": 0.22, + "learning_rate": 1.9165570282744534e-05, + "loss": 1.4707, + "step": 2077 + }, + { + "epoch": 0.22, + "learning_rate": 1.9164105920127613e-05, + "loss": 1.5354, + "step": 2078 + }, + { + "epoch": 0.22, + "learning_rate": 1.9162640329755962e-05, + "loss": 1.526, + "step": 2079 + }, + { + "epoch": 0.22, + "learning_rate": 1.916117351182593e-05, + "loss": 1.6424, + "step": 2080 + }, + { + "epoch": 0.22, + "learning_rate": 1.915970546653404e-05, + "loss": 1.5048, + "step": 2081 + }, + { + "epoch": 0.22, + "learning_rate": 1.915823619407697e-05, + "loss": 1.5344, + "step": 2082 + }, + { + "epoch": 0.22, + "learning_rate": 1.915676569465156e-05, + "loss": 1.4604, + "step": 2083 + }, + { + "epoch": 0.22, + "learning_rate": 1.9155293968454826e-05, + "loss": 1.4929, + "step": 2084 + }, + { + "epoch": 0.22, + "learning_rate": 1.9153821015683937e-05, + "loss": 1.4106, + "step": 2085 + }, + { + "epoch": 0.22, + "learning_rate": 1.915234683653623e-05, + "loss": 1.4146, + "step": 2086 + }, + { + "epoch": 0.22, + "learning_rate": 1.9150871431209207e-05, + "loss": 1.4481, + "step": 2087 + }, + { + "epoch": 0.22, + "learning_rate": 1.914939479990054e-05, + "loss": 1.5206, + "step": 2088 + }, + { + "epoch": 0.22, + "learning_rate": 1.9147916942808054e-05, + "loss": 1.5073, + "step": 2089 + }, + { + "epoch": 0.22, + "learning_rate": 1.9146437860129745e-05, + "loss": 1.5196, + "step": 2090 + }, + { + "epoch": 0.22, + "learning_rate": 1.9144957552063775e-05, + "loss": 1.5389, + "step": 2091 + }, + { + "epoch": 0.22, + "learning_rate": 1.9143476018808463e-05, + "loss": 1.5207, + "step": 2092 + }, + { + "epoch": 0.22, + "learning_rate": 1.9141993260562298e-05, + "loss": 1.3717, + "step": 2093 + }, + { + "epoch": 0.22, + "learning_rate": 1.9140509277523937e-05, + "loss": 1.471, + "step": 2094 + }, + { + "epoch": 0.22, + "learning_rate": 1.9139024069892185e-05, + "loss": 1.4553, + "step": 2095 + }, + { + "epoch": 0.22, + "learning_rate": 1.9137537637866027e-05, + "loss": 1.5311, + "step": 2096 + }, + { + "epoch": 0.22, + "learning_rate": 1.9136049981644614e-05, + "loss": 1.4369, + "step": 2097 + }, + { + "epoch": 0.22, + "learning_rate": 1.913456110142724e-05, + "loss": 1.4528, + "step": 2098 + }, + { + "epoch": 0.22, + "learning_rate": 1.9133070997413384e-05, + "loss": 1.5294, + "step": 2099 + }, + { + "epoch": 0.22, + "learning_rate": 1.9131579669802685e-05, + "loss": 1.4588, + "step": 2100 + }, + { + "epoch": 0.22, + "learning_rate": 1.9130087118794934e-05, + "loss": 1.443, + "step": 2101 + }, + { + "epoch": 0.22, + "learning_rate": 1.9128593344590102e-05, + "loss": 1.4876, + "step": 2102 + }, + { + "epoch": 0.22, + "learning_rate": 1.912709834738831e-05, + "loss": 1.4874, + "step": 2103 + }, + { + "epoch": 0.22, + "learning_rate": 1.9125602127389856e-05, + "loss": 1.4966, + "step": 2104 + }, + { + "epoch": 0.22, + "learning_rate": 1.912410468479519e-05, + "loss": 1.5747, + "step": 2105 + }, + { + "epoch": 0.22, + "learning_rate": 1.9122606019804933e-05, + "loss": 1.4025, + "step": 2106 + }, + { + "epoch": 0.22, + "learning_rate": 1.912110613261987e-05, + "loss": 1.4755, + "step": 2107 + }, + { + "epoch": 0.22, + "learning_rate": 1.911960502344094e-05, + "loss": 1.4739, + "step": 2108 + }, + { + "epoch": 0.22, + "learning_rate": 1.911810269246926e-05, + "loss": 1.4992, + "step": 2109 + }, + { + "epoch": 0.22, + "learning_rate": 1.91165991399061e-05, + "loss": 1.4435, + "step": 2110 + }, + { + "epoch": 0.22, + "learning_rate": 1.91150943659529e-05, + "loss": 1.4918, + "step": 2111 + }, + { + "epoch": 0.22, + "learning_rate": 1.9113588370811258e-05, + "loss": 1.3818, + "step": 2112 + }, + { + "epoch": 0.22, + "learning_rate": 1.911208115468294e-05, + "loss": 1.5105, + "step": 2113 + }, + { + "epoch": 0.22, + "learning_rate": 1.9110572717769878e-05, + "loss": 1.6634, + "step": 2114 + }, + { + "epoch": 0.22, + "learning_rate": 1.9109063060274158e-05, + "loss": 1.5028, + "step": 2115 + }, + { + "epoch": 0.22, + "learning_rate": 1.9107552182398037e-05, + "loss": 1.6657, + "step": 2116 + }, + { + "epoch": 0.22, + "learning_rate": 1.9106040084343935e-05, + "loss": 1.5481, + "step": 2117 + }, + { + "epoch": 0.22, + "learning_rate": 1.910452676631444e-05, + "loss": 1.4505, + "step": 2118 + }, + { + "epoch": 0.22, + "learning_rate": 1.9103012228512284e-05, + "loss": 1.5173, + "step": 2119 + }, + { + "epoch": 0.22, + "learning_rate": 1.9101496471140385e-05, + "loss": 1.3788, + "step": 2120 + }, + { + "epoch": 0.22, + "learning_rate": 1.9099979494401814e-05, + "loss": 1.4649, + "step": 2121 + }, + { + "epoch": 0.22, + "learning_rate": 1.9098461298499805e-05, + "loss": 1.4204, + "step": 2122 + }, + { + "epoch": 0.22, + "learning_rate": 1.9096941883637766e-05, + "loss": 1.4439, + "step": 2123 + }, + { + "epoch": 0.22, + "learning_rate": 1.909542125001925e-05, + "loss": 1.6615, + "step": 2124 + }, + { + "epoch": 0.22, + "learning_rate": 1.9093899397847985e-05, + "loss": 1.4763, + "step": 2125 + }, + { + "epoch": 0.22, + "learning_rate": 1.909237632732786e-05, + "loss": 1.5353, + "step": 2126 + }, + { + "epoch": 0.22, + "learning_rate": 1.909085203866293e-05, + "loss": 1.442, + "step": 2127 + }, + { + "epoch": 0.22, + "learning_rate": 1.9089326532057408e-05, + "loss": 1.4782, + "step": 2128 + }, + { + "epoch": 0.22, + "learning_rate": 1.908779980771567e-05, + "loss": 1.4933, + "step": 2129 + }, + { + "epoch": 0.22, + "learning_rate": 1.9086271865842264e-05, + "loss": 1.5285, + "step": 2130 + }, + { + "epoch": 0.22, + "learning_rate": 1.9084742706641894e-05, + "loss": 1.4736, + "step": 2131 + }, + { + "epoch": 0.22, + "learning_rate": 1.9083212330319427e-05, + "loss": 1.4496, + "step": 2132 + }, + { + "epoch": 0.22, + "learning_rate": 1.908168073707989e-05, + "loss": 1.5099, + "step": 2133 + }, + { + "epoch": 0.22, + "learning_rate": 1.9080147927128483e-05, + "loss": 1.5235, + "step": 2134 + }, + { + "epoch": 0.22, + "learning_rate": 1.9078613900670556e-05, + "loss": 1.4769, + "step": 2135 + }, + { + "epoch": 0.22, + "learning_rate": 1.907707865791164e-05, + "loss": 1.5771, + "step": 2136 + }, + { + "epoch": 0.22, + "learning_rate": 1.907554219905741e-05, + "loss": 1.5116, + "step": 2137 + }, + { + "epoch": 0.22, + "learning_rate": 1.907400452431371e-05, + "loss": 1.5161, + "step": 2138 + }, + { + "epoch": 0.22, + "learning_rate": 1.9072465633886557e-05, + "loss": 1.4356, + "step": 2139 + }, + { + "epoch": 0.22, + "learning_rate": 1.9070925527982117e-05, + "loss": 1.509, + "step": 2140 + }, + { + "epoch": 0.22, + "learning_rate": 1.9069384206806723e-05, + "loss": 1.4681, + "step": 2141 + }, + { + "epoch": 0.22, + "learning_rate": 1.9067841670566883e-05, + "loss": 1.5254, + "step": 2142 + }, + { + "epoch": 0.22, + "learning_rate": 1.9066297919469242e-05, + "loss": 1.4797, + "step": 2143 + }, + { + "epoch": 0.22, + "learning_rate": 1.9064752953720636e-05, + "loss": 1.3996, + "step": 2144 + }, + { + "epoch": 0.22, + "learning_rate": 1.9063206773528042e-05, + "loss": 1.4457, + "step": 2145 + }, + { + "epoch": 0.23, + "learning_rate": 1.9061659379098617e-05, + "loss": 1.5126, + "step": 2146 + }, + { + "epoch": 0.23, + "learning_rate": 1.9060110770639664e-05, + "loss": 1.5925, + "step": 2147 + }, + { + "epoch": 0.23, + "learning_rate": 1.905856094835866e-05, + "loss": 1.5146, + "step": 2148 + }, + { + "epoch": 0.23, + "learning_rate": 1.905700991246324e-05, + "loss": 1.7256, + "step": 2149 + }, + { + "epoch": 0.23, + "learning_rate": 1.90554576631612e-05, + "loss": 1.57, + "step": 2150 + }, + { + "epoch": 0.23, + "learning_rate": 1.905390420066051e-05, + "loss": 1.3722, + "step": 2151 + }, + { + "epoch": 0.23, + "learning_rate": 1.9052349525169292e-05, + "loss": 1.3999, + "step": 2152 + }, + { + "epoch": 0.23, + "learning_rate": 1.9050793636895828e-05, + "loss": 1.586, + "step": 2153 + }, + { + "epoch": 0.23, + "learning_rate": 1.9049236536048567e-05, + "loss": 1.4884, + "step": 2154 + }, + { + "epoch": 0.23, + "learning_rate": 1.9047678222836127e-05, + "loss": 1.5898, + "step": 2155 + }, + { + "epoch": 0.23, + "learning_rate": 1.9046118697467278e-05, + "loss": 1.569, + "step": 2156 + }, + { + "epoch": 0.23, + "learning_rate": 1.904455796015095e-05, + "loss": 1.5592, + "step": 2157 + }, + { + "epoch": 0.23, + "learning_rate": 1.9042996011096253e-05, + "loss": 1.597, + "step": 2158 + }, + { + "epoch": 0.23, + "learning_rate": 1.904143285051244e-05, + "loss": 1.422, + "step": 2159 + }, + { + "epoch": 0.23, + "learning_rate": 1.903986847860894e-05, + "loss": 1.519, + "step": 2160 + }, + { + "epoch": 0.23, + "learning_rate": 1.9038302895595334e-05, + "loss": 1.5197, + "step": 2161 + }, + { + "epoch": 0.23, + "learning_rate": 1.903673610168137e-05, + "loss": 1.4655, + "step": 2162 + }, + { + "epoch": 0.23, + "learning_rate": 1.9035168097076965e-05, + "loss": 1.3909, + "step": 2163 + }, + { + "epoch": 0.23, + "learning_rate": 1.903359888199218e-05, + "loss": 1.4877, + "step": 2164 + }, + { + "epoch": 0.23, + "learning_rate": 1.903202845663726e-05, + "loss": 1.5123, + "step": 2165 + }, + { + "epoch": 0.23, + "learning_rate": 1.9030456821222593e-05, + "loss": 1.4906, + "step": 2166 + }, + { + "epoch": 0.23, + "learning_rate": 1.9028883975958745e-05, + "loss": 1.4574, + "step": 2167 + }, + { + "epoch": 0.23, + "learning_rate": 1.9027309921056435e-05, + "loss": 1.4571, + "step": 2168 + }, + { + "epoch": 0.23, + "learning_rate": 1.902573465672654e-05, + "loss": 1.4281, + "step": 2169 + }, + { + "epoch": 0.23, + "learning_rate": 1.9024158183180116e-05, + "loss": 1.5057, + "step": 2170 + }, + { + "epoch": 0.23, + "learning_rate": 1.902258050062836e-05, + "loss": 1.4514, + "step": 2171 + }, + { + "epoch": 0.23, + "learning_rate": 1.9021001609282646e-05, + "loss": 1.5055, + "step": 2172 + }, + { + "epoch": 0.23, + "learning_rate": 1.9019421509354505e-05, + "loss": 1.4578, + "step": 2173 + }, + { + "epoch": 0.23, + "learning_rate": 1.9017840201055625e-05, + "loss": 1.459, + "step": 2174 + }, + { + "epoch": 0.23, + "learning_rate": 1.9016257684597864e-05, + "loss": 1.5059, + "step": 2175 + }, + { + "epoch": 0.23, + "learning_rate": 1.901467396019324e-05, + "loss": 1.57, + "step": 2176 + }, + { + "epoch": 0.23, + "learning_rate": 1.901308902805393e-05, + "loss": 1.4924, + "step": 2177 + }, + { + "epoch": 0.23, + "learning_rate": 1.9011502888392273e-05, + "loss": 1.4979, + "step": 2178 + }, + { + "epoch": 0.23, + "learning_rate": 1.900991554142077e-05, + "loss": 1.5321, + "step": 2179 + }, + { + "epoch": 0.23, + "learning_rate": 1.9008326987352093e-05, + "loss": 1.493, + "step": 2180 + }, + { + "epoch": 0.23, + "learning_rate": 1.9006737226399056e-05, + "loss": 1.5111, + "step": 2181 + }, + { + "epoch": 0.23, + "learning_rate": 1.900514625877465e-05, + "loss": 1.4154, + "step": 2182 + }, + { + "epoch": 0.23, + "learning_rate": 1.900355408469203e-05, + "loss": 1.4934, + "step": 2183 + }, + { + "epoch": 0.23, + "learning_rate": 1.90019607043645e-05, + "loss": 1.5975, + "step": 2184 + }, + { + "epoch": 0.23, + "learning_rate": 1.9000366118005532e-05, + "loss": 1.3537, + "step": 2185 + }, + { + "epoch": 0.23, + "learning_rate": 1.899877032582876e-05, + "loss": 1.4583, + "step": 2186 + }, + { + "epoch": 0.23, + "learning_rate": 1.8997173328047984e-05, + "loss": 1.4586, + "step": 2187 + }, + { + "epoch": 0.23, + "learning_rate": 1.8995575124877156e-05, + "loss": 1.4774, + "step": 2188 + }, + { + "epoch": 0.23, + "learning_rate": 1.8993975716530394e-05, + "loss": 1.5025, + "step": 2189 + }, + { + "epoch": 0.23, + "eval_loss": 1.5263344049453735, + "eval_runtime": 77.1492, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 2189 + }, + { + "epoch": 0.23, + "learning_rate": 1.899237510322198e-05, + "loss": 1.5438, + "step": 2190 + }, + { + "epoch": 0.23, + "learning_rate": 1.899077328516635e-05, + "loss": 1.5181, + "step": 2191 + }, + { + "epoch": 0.23, + "learning_rate": 1.8989170262578112e-05, + "loss": 1.4454, + "step": 2192 + }, + { + "epoch": 0.23, + "learning_rate": 1.8987566035672028e-05, + "loss": 1.4882, + "step": 2193 + }, + { + "epoch": 0.23, + "learning_rate": 1.8985960604663026e-05, + "loss": 1.5073, + "step": 2194 + }, + { + "epoch": 0.23, + "learning_rate": 1.8984353969766187e-05, + "loss": 1.4478, + "step": 2195 + }, + { + "epoch": 0.23, + "learning_rate": 1.8982746131196763e-05, + "loss": 1.4768, + "step": 2196 + }, + { + "epoch": 0.23, + "learning_rate": 1.8981137089170162e-05, + "loss": 1.5116, + "step": 2197 + }, + { + "epoch": 0.23, + "learning_rate": 1.8979526843901952e-05, + "loss": 1.4202, + "step": 2198 + }, + { + "epoch": 0.23, + "learning_rate": 1.8977915395607867e-05, + "loss": 1.4736, + "step": 2199 + }, + { + "epoch": 0.23, + "learning_rate": 1.89763027445038e-05, + "loss": 1.4489, + "step": 2200 + }, + { + "epoch": 0.23, + "learning_rate": 1.8974688890805804e-05, + "loss": 1.4512, + "step": 2201 + }, + { + "epoch": 0.23, + "learning_rate": 1.897307383473009e-05, + "loss": 1.5091, + "step": 2202 + }, + { + "epoch": 0.23, + "learning_rate": 1.897145757649304e-05, + "loss": 1.5512, + "step": 2203 + }, + { + "epoch": 0.23, + "learning_rate": 1.8969840116311192e-05, + "loss": 1.406, + "step": 2204 + }, + { + "epoch": 0.23, + "learning_rate": 1.896822145440124e-05, + "loss": 1.4531, + "step": 2205 + }, + { + "epoch": 0.23, + "learning_rate": 1.896660159098004e-05, + "loss": 1.4379, + "step": 2206 + }, + { + "epoch": 0.23, + "learning_rate": 1.896498052626462e-05, + "loss": 1.4783, + "step": 2207 + }, + { + "epoch": 0.23, + "learning_rate": 1.896335826047216e-05, + "loss": 1.4801, + "step": 2208 + }, + { + "epoch": 0.23, + "learning_rate": 1.896173479381999e-05, + "loss": 1.4526, + "step": 2209 + }, + { + "epoch": 0.23, + "learning_rate": 1.8960110126525627e-05, + "loss": 1.4952, + "step": 2210 + }, + { + "epoch": 0.23, + "learning_rate": 1.895848425880673e-05, + "loss": 1.5299, + "step": 2211 + }, + { + "epoch": 0.23, + "learning_rate": 1.8956857190881125e-05, + "loss": 1.5274, + "step": 2212 + }, + { + "epoch": 0.23, + "learning_rate": 1.8955228922966792e-05, + "loss": 1.4415, + "step": 2213 + }, + { + "epoch": 0.23, + "learning_rate": 1.8953599455281884e-05, + "loss": 1.5311, + "step": 2214 + }, + { + "epoch": 0.23, + "learning_rate": 1.8951968788044702e-05, + "loss": 1.4972, + "step": 2215 + }, + { + "epoch": 0.23, + "learning_rate": 1.8950336921473715e-05, + "loss": 1.4966, + "step": 2216 + }, + { + "epoch": 0.23, + "learning_rate": 1.8948703855787553e-05, + "loss": 1.4683, + "step": 2217 + }, + { + "epoch": 0.23, + "learning_rate": 1.8947069591205005e-05, + "loss": 1.503, + "step": 2218 + }, + { + "epoch": 0.23, + "learning_rate": 1.8945434127945014e-05, + "loss": 1.4902, + "step": 2219 + }, + { + "epoch": 0.23, + "learning_rate": 1.8943797466226702e-05, + "loss": 1.4835, + "step": 2220 + }, + { + "epoch": 0.23, + "learning_rate": 1.8942159606269332e-05, + "loss": 1.535, + "step": 2221 + }, + { + "epoch": 0.23, + "learning_rate": 1.8940520548292332e-05, + "loss": 1.491, + "step": 2222 + }, + { + "epoch": 0.23, + "learning_rate": 1.89388802925153e-05, + "loss": 1.5157, + "step": 2223 + }, + { + "epoch": 0.23, + "learning_rate": 1.8937238839157987e-05, + "loss": 1.4779, + "step": 2224 + }, + { + "epoch": 0.23, + "learning_rate": 1.8935596188440302e-05, + "loss": 1.4902, + "step": 2225 + }, + { + "epoch": 0.23, + "learning_rate": 1.8933952340582323e-05, + "loss": 1.4988, + "step": 2226 + }, + { + "epoch": 0.23, + "learning_rate": 1.893230729580428e-05, + "loss": 1.4568, + "step": 2227 + }, + { + "epoch": 0.23, + "learning_rate": 1.8930661054326567e-05, + "loss": 1.5163, + "step": 2228 + }, + { + "epoch": 0.23, + "learning_rate": 1.892901361636974e-05, + "loss": 1.4472, + "step": 2229 + }, + { + "epoch": 0.23, + "learning_rate": 1.892736498215451e-05, + "loss": 1.4658, + "step": 2230 + }, + { + "epoch": 0.23, + "learning_rate": 1.8925715151901754e-05, + "loss": 1.4281, + "step": 2231 + }, + { + "epoch": 0.23, + "learning_rate": 1.892406412583251e-05, + "loss": 1.415, + "step": 2232 + }, + { + "epoch": 0.23, + "learning_rate": 1.8922411904167966e-05, + "loss": 1.464, + "step": 2233 + }, + { + "epoch": 0.23, + "learning_rate": 1.892075848712948e-05, + "loss": 1.5014, + "step": 2234 + }, + { + "epoch": 0.23, + "learning_rate": 1.8919103874938568e-05, + "loss": 1.4397, + "step": 2235 + }, + { + "epoch": 0.23, + "learning_rate": 1.891744806781691e-05, + "loss": 1.5508, + "step": 2236 + }, + { + "epoch": 0.23, + "learning_rate": 1.8915791065986335e-05, + "loss": 1.4749, + "step": 2237 + }, + { + "epoch": 0.23, + "learning_rate": 1.891413286966884e-05, + "loss": 1.4538, + "step": 2238 + }, + { + "epoch": 0.23, + "learning_rate": 1.891247347908658e-05, + "loss": 1.4405, + "step": 2239 + }, + { + "epoch": 0.23, + "learning_rate": 1.8910812894461878e-05, + "loss": 1.3562, + "step": 2240 + }, + { + "epoch": 0.24, + "learning_rate": 1.89091511160172e-05, + "loss": 1.4811, + "step": 2241 + }, + { + "epoch": 0.24, + "learning_rate": 1.8907488143975186e-05, + "loss": 1.4286, + "step": 2242 + }, + { + "epoch": 0.24, + "learning_rate": 1.890582397855863e-05, + "loss": 1.4493, + "step": 2243 + }, + { + "epoch": 0.24, + "learning_rate": 1.890415861999049e-05, + "loss": 1.5639, + "step": 2244 + }, + { + "epoch": 0.24, + "learning_rate": 1.890249206849388e-05, + "loss": 1.6375, + "step": 2245 + }, + { + "epoch": 0.24, + "learning_rate": 1.890082432429208e-05, + "loss": 1.4982, + "step": 2246 + }, + { + "epoch": 0.24, + "learning_rate": 1.889915538760851e-05, + "loss": 1.492, + "step": 2247 + }, + { + "epoch": 0.24, + "learning_rate": 1.8897485258666778e-05, + "loss": 1.4294, + "step": 2248 + }, + { + "epoch": 0.24, + "learning_rate": 1.8895813937690638e-05, + "loss": 1.4617, + "step": 2249 + }, + { + "epoch": 0.24, + "learning_rate": 1.8894141424904e-05, + "loss": 1.4763, + "step": 2250 + }, + { + "epoch": 0.24, + "learning_rate": 1.8892467720530937e-05, + "loss": 1.3989, + "step": 2251 + }, + { + "epoch": 0.24, + "learning_rate": 1.8890792824795687e-05, + "loss": 1.4803, + "step": 2252 + }, + { + "epoch": 0.24, + "learning_rate": 1.8889116737922638e-05, + "loss": 1.4734, + "step": 2253 + }, + { + "epoch": 0.24, + "learning_rate": 1.8887439460136342e-05, + "loss": 1.5069, + "step": 2254 + }, + { + "epoch": 0.24, + "learning_rate": 1.8885760991661514e-05, + "loss": 1.5565, + "step": 2255 + }, + { + "epoch": 0.24, + "learning_rate": 1.8884081332723028e-05, + "loss": 1.4707, + "step": 2256 + }, + { + "epoch": 0.24, + "learning_rate": 1.8882400483545913e-05, + "loss": 1.5077, + "step": 2257 + }, + { + "epoch": 0.24, + "learning_rate": 1.888071844435536e-05, + "loss": 1.5075, + "step": 2258 + }, + { + "epoch": 0.24, + "learning_rate": 1.8879035215376717e-05, + "loss": 1.5185, + "step": 2259 + }, + { + "epoch": 0.24, + "learning_rate": 1.887735079683549e-05, + "loss": 1.6266, + "step": 2260 + }, + { + "epoch": 0.24, + "learning_rate": 1.8875665188957354e-05, + "loss": 1.5013, + "step": 2261 + }, + { + "epoch": 0.24, + "learning_rate": 1.887397839196814e-05, + "loss": 1.4362, + "step": 2262 + }, + { + "epoch": 0.24, + "learning_rate": 1.8872290406093827e-05, + "loss": 1.4718, + "step": 2263 + }, + { + "epoch": 0.24, + "learning_rate": 1.8870601231560567e-05, + "loss": 1.5202, + "step": 2264 + }, + { + "epoch": 0.24, + "learning_rate": 1.8868910868594664e-05, + "loss": 1.5168, + "step": 2265 + }, + { + "epoch": 0.24, + "learning_rate": 1.8867219317422588e-05, + "loss": 1.5142, + "step": 2266 + }, + { + "epoch": 0.24, + "learning_rate": 1.8865526578270954e-05, + "loss": 1.4885, + "step": 2267 + }, + { + "epoch": 0.24, + "learning_rate": 1.8863832651366552e-05, + "loss": 1.5441, + "step": 2268 + }, + { + "epoch": 0.24, + "learning_rate": 1.8862137536936328e-05, + "loss": 1.4647, + "step": 2269 + }, + { + "epoch": 0.24, + "learning_rate": 1.8860441235207374e-05, + "loss": 1.5352, + "step": 2270 + }, + { + "epoch": 0.24, + "learning_rate": 1.8858743746406958e-05, + "loss": 1.4568, + "step": 2271 + }, + { + "epoch": 0.24, + "learning_rate": 1.8857045070762497e-05, + "loss": 1.4865, + "step": 2272 + }, + { + "epoch": 0.24, + "learning_rate": 1.8855345208501573e-05, + "loss": 1.4637, + "step": 2273 + }, + { + "epoch": 0.24, + "learning_rate": 1.8853644159851918e-05, + "loss": 1.4348, + "step": 2274 + }, + { + "epoch": 0.24, + "learning_rate": 1.8851941925041436e-05, + "loss": 1.4413, + "step": 2275 + }, + { + "epoch": 0.24, + "learning_rate": 1.8850238504298177e-05, + "loss": 1.4434, + "step": 2276 + }, + { + "epoch": 0.24, + "learning_rate": 1.884853389785036e-05, + "loss": 1.4822, + "step": 2277 + }, + { + "epoch": 0.24, + "learning_rate": 1.8846828105926356e-05, + "loss": 1.4632, + "step": 2278 + }, + { + "epoch": 0.24, + "learning_rate": 1.8845121128754698e-05, + "loss": 1.48, + "step": 2279 + }, + { + "epoch": 0.24, + "learning_rate": 1.8843412966564078e-05, + "loss": 1.4518, + "step": 2280 + }, + { + "epoch": 0.24, + "learning_rate": 1.884170361958334e-05, + "loss": 1.4334, + "step": 2281 + }, + { + "epoch": 0.24, + "learning_rate": 1.8839993088041502e-05, + "loss": 1.5131, + "step": 2282 + }, + { + "epoch": 0.24, + "learning_rate": 1.8838281372167724e-05, + "loss": 1.508, + "step": 2283 + }, + { + "epoch": 0.24, + "learning_rate": 1.8836568472191335e-05, + "loss": 1.4086, + "step": 2284 + }, + { + "epoch": 0.24, + "learning_rate": 1.883485438834182e-05, + "loss": 1.5021, + "step": 2285 + }, + { + "epoch": 0.24, + "learning_rate": 1.8833139120848817e-05, + "loss": 1.5083, + "step": 2286 + }, + { + "epoch": 0.24, + "learning_rate": 1.8831422669942137e-05, + "loss": 1.4162, + "step": 2287 + }, + { + "epoch": 0.24, + "learning_rate": 1.8829705035851734e-05, + "loss": 1.5494, + "step": 2288 + }, + { + "epoch": 0.24, + "learning_rate": 1.8827986218807724e-05, + "loss": 1.425, + "step": 2289 + }, + { + "epoch": 0.24, + "learning_rate": 1.8826266219040396e-05, + "loss": 1.5215, + "step": 2290 + }, + { + "epoch": 0.24, + "learning_rate": 1.8824545036780172e-05, + "loss": 1.5577, + "step": 2291 + }, + { + "epoch": 0.24, + "learning_rate": 1.8822822672257655e-05, + "loss": 1.4923, + "step": 2292 + }, + { + "epoch": 0.24, + "learning_rate": 1.8821099125703595e-05, + "loss": 1.4648, + "step": 2293 + }, + { + "epoch": 0.24, + "learning_rate": 1.8819374397348902e-05, + "loss": 1.471, + "step": 2294 + }, + { + "epoch": 0.24, + "learning_rate": 1.8817648487424648e-05, + "loss": 1.5658, + "step": 2295 + }, + { + "epoch": 0.24, + "learning_rate": 1.8815921396162058e-05, + "loss": 1.5348, + "step": 2296 + }, + { + "epoch": 0.24, + "learning_rate": 1.8814193123792518e-05, + "loss": 1.4081, + "step": 2297 + }, + { + "epoch": 0.24, + "learning_rate": 1.881246367054757e-05, + "loss": 1.4762, + "step": 2298 + }, + { + "epoch": 0.24, + "learning_rate": 1.8810733036658925e-05, + "loss": 1.4399, + "step": 2299 + }, + { + "epoch": 0.24, + "learning_rate": 1.8809001222358432e-05, + "loss": 1.4763, + "step": 2300 + }, + { + "epoch": 0.24, + "learning_rate": 1.880726822787812e-05, + "loss": 1.4874, + "step": 2301 + }, + { + "epoch": 0.24, + "learning_rate": 1.880553405345016e-05, + "loss": 1.4951, + "step": 2302 + }, + { + "epoch": 0.24, + "learning_rate": 1.8803798699306887e-05, + "loss": 1.4697, + "step": 2303 + }, + { + "epoch": 0.24, + "learning_rate": 1.880206216568079e-05, + "loss": 1.481, + "step": 2304 + }, + { + "epoch": 0.24, + "learning_rate": 1.880032445280453e-05, + "loss": 1.4485, + "step": 2305 + }, + { + "epoch": 0.24, + "learning_rate": 1.879858556091091e-05, + "loss": 1.4749, + "step": 2306 + }, + { + "epoch": 0.24, + "learning_rate": 1.8796845490232894e-05, + "loss": 1.5605, + "step": 2307 + }, + { + "epoch": 0.24, + "learning_rate": 1.879510424100361e-05, + "loss": 1.4835, + "step": 2308 + }, + { + "epoch": 0.24, + "learning_rate": 1.8793361813456346e-05, + "loss": 1.4344, + "step": 2309 + }, + { + "epoch": 0.24, + "learning_rate": 1.8791618207824532e-05, + "loss": 1.4571, + "step": 2310 + }, + { + "epoch": 0.24, + "learning_rate": 1.8789873424341772e-05, + "loss": 1.482, + "step": 2311 + }, + { + "epoch": 0.24, + "learning_rate": 1.8788127463241822e-05, + "loss": 1.4736, + "step": 2312 + }, + { + "epoch": 0.24, + "learning_rate": 1.8786380324758597e-05, + "loss": 1.4807, + "step": 2313 + }, + { + "epoch": 0.24, + "learning_rate": 1.8784632009126167e-05, + "loss": 1.4418, + "step": 2314 + }, + { + "epoch": 0.24, + "learning_rate": 1.878288251657876e-05, + "loss": 1.5248, + "step": 2315 + }, + { + "epoch": 0.24, + "learning_rate": 1.8781131847350768e-05, + "loss": 1.483, + "step": 2316 + }, + { + "epoch": 0.24, + "learning_rate": 1.877938000167673e-05, + "loss": 1.5474, + "step": 2317 + }, + { + "epoch": 0.24, + "learning_rate": 1.8777626979791347e-05, + "loss": 1.4671, + "step": 2318 + }, + { + "epoch": 0.24, + "learning_rate": 1.877587278192949e-05, + "loss": 1.3049, + "step": 2319 + }, + { + "epoch": 0.24, + "learning_rate": 1.877411740832616e-05, + "loss": 1.483, + "step": 2320 + }, + { + "epoch": 0.24, + "learning_rate": 1.877236085921655e-05, + "loss": 1.508, + "step": 2321 + }, + { + "epoch": 0.24, + "learning_rate": 1.8770603134835978e-05, + "loss": 1.4854, + "step": 2322 + }, + { + "epoch": 0.24, + "learning_rate": 1.8768844235419942e-05, + "loss": 1.4808, + "step": 2323 + }, + { + "epoch": 0.24, + "learning_rate": 1.8767084161204087e-05, + "loss": 1.5352, + "step": 2324 + }, + { + "epoch": 0.24, + "learning_rate": 1.8765322912424214e-05, + "loss": 1.5628, + "step": 2325 + }, + { + "epoch": 0.24, + "learning_rate": 1.8763560489316292e-05, + "loss": 1.494, + "step": 2326 + }, + { + "epoch": 0.24, + "learning_rate": 1.876179689211643e-05, + "loss": 1.509, + "step": 2327 + }, + { + "epoch": 0.24, + "learning_rate": 1.8760032121060918e-05, + "loss": 1.5021, + "step": 2328 + }, + { + "epoch": 0.24, + "learning_rate": 1.875826617638618e-05, + "loss": 1.4179, + "step": 2329 + }, + { + "epoch": 0.24, + "learning_rate": 1.8756499058328813e-05, + "loss": 1.4302, + "step": 2330 + }, + { + "epoch": 0.24, + "learning_rate": 1.8754730767125564e-05, + "loss": 1.4959, + "step": 2331 + }, + { + "epoch": 0.24, + "learning_rate": 1.8752961303013336e-05, + "loss": 1.4423, + "step": 2332 + }, + { + "epoch": 0.24, + "learning_rate": 1.8751190666229194e-05, + "loss": 1.4564, + "step": 2333 + }, + { + "epoch": 0.24, + "learning_rate": 1.8749418857010358e-05, + "loss": 1.4775, + "step": 2334 + }, + { + "epoch": 0.24, + "learning_rate": 1.8747645875594203e-05, + "loss": 1.4182, + "step": 2335 + }, + { + "epoch": 0.24, + "learning_rate": 1.8745871722218265e-05, + "loss": 1.3957, + "step": 2336 + }, + { + "epoch": 0.25, + "learning_rate": 1.8744096397120235e-05, + "loss": 1.4633, + "step": 2337 + }, + { + "epoch": 0.25, + "learning_rate": 1.874231990053796e-05, + "loss": 1.5512, + "step": 2338 + }, + { + "epoch": 0.25, + "learning_rate": 1.8740542232709444e-05, + "loss": 1.3461, + "step": 2339 + }, + { + "epoch": 0.25, + "learning_rate": 1.8738763393872848e-05, + "loss": 1.4754, + "step": 2340 + }, + { + "epoch": 0.25, + "learning_rate": 1.8736983384266495e-05, + "loss": 1.5448, + "step": 2341 + }, + { + "epoch": 0.25, + "learning_rate": 1.8735202204128854e-05, + "loss": 1.4491, + "step": 2342 + }, + { + "epoch": 0.25, + "learning_rate": 1.8733419853698566e-05, + "loss": 1.457, + "step": 2343 + }, + { + "epoch": 0.25, + "learning_rate": 1.8731636333214414e-05, + "loss": 1.4314, + "step": 2344 + }, + { + "epoch": 0.25, + "learning_rate": 1.8729851642915345e-05, + "loss": 1.3979, + "step": 2345 + }, + { + "epoch": 0.25, + "learning_rate": 1.8728065783040464e-05, + "loss": 1.4146, + "step": 2346 + }, + { + "epoch": 0.25, + "learning_rate": 1.8726278753829027e-05, + "loss": 1.4361, + "step": 2347 + }, + { + "epoch": 0.25, + "learning_rate": 1.872449055552045e-05, + "loss": 1.4989, + "step": 2348 + }, + { + "epoch": 0.25, + "learning_rate": 1.872270118835431e-05, + "loss": 1.5062, + "step": 2349 + }, + { + "epoch": 0.25, + "learning_rate": 1.872091065257033e-05, + "loss": 1.4509, + "step": 2350 + }, + { + "epoch": 0.25, + "learning_rate": 1.8719118948408403e-05, + "loss": 1.4631, + "step": 2351 + }, + { + "epoch": 0.25, + "learning_rate": 1.8717326076108566e-05, + "loss": 1.5119, + "step": 2352 + }, + { + "epoch": 0.25, + "learning_rate": 1.8715532035911017e-05, + "loss": 1.6347, + "step": 2353 + }, + { + "epoch": 0.25, + "learning_rate": 1.8713736828056115e-05, + "loss": 1.5526, + "step": 2354 + }, + { + "epoch": 0.25, + "learning_rate": 1.8711940452784368e-05, + "loss": 1.6348, + "step": 2355 + }, + { + "epoch": 0.25, + "learning_rate": 1.871014291033645e-05, + "loss": 1.5183, + "step": 2356 + }, + { + "epoch": 0.25, + "learning_rate": 1.8708344200953182e-05, + "loss": 1.458, + "step": 2357 + }, + { + "epoch": 0.25, + "learning_rate": 1.8706544324875545e-05, + "loss": 1.524, + "step": 2358 + }, + { + "epoch": 0.25, + "learning_rate": 1.8704743282344672e-05, + "loss": 1.4479, + "step": 2359 + }, + { + "epoch": 0.25, + "learning_rate": 1.870294107360186e-05, + "loss": 1.5408, + "step": 2360 + }, + { + "epoch": 0.25, + "learning_rate": 1.8701137698888563e-05, + "loss": 1.5007, + "step": 2361 + }, + { + "epoch": 0.25, + "learning_rate": 1.8699333158446382e-05, + "loss": 1.5132, + "step": 2362 + }, + { + "epoch": 0.25, + "learning_rate": 1.869752745251708e-05, + "loss": 1.4263, + "step": 2363 + }, + { + "epoch": 0.25, + "learning_rate": 1.8695720581342574e-05, + "loss": 1.422, + "step": 2364 + }, + { + "epoch": 0.25, + "learning_rate": 1.869391254516494e-05, + "loss": 1.4411, + "step": 2365 + }, + { + "epoch": 0.25, + "learning_rate": 1.8692103344226406e-05, + "loss": 1.4594, + "step": 2366 + }, + { + "epoch": 0.25, + "learning_rate": 1.8690292978769364e-05, + "loss": 1.4992, + "step": 2367 + }, + { + "epoch": 0.25, + "learning_rate": 1.868848144903635e-05, + "loss": 1.4822, + "step": 2368 + }, + { + "epoch": 0.25, + "learning_rate": 1.8686668755270064e-05, + "loss": 1.5402, + "step": 2369 + }, + { + "epoch": 0.25, + "learning_rate": 1.8684854897713363e-05, + "loss": 1.5268, + "step": 2370 + }, + { + "epoch": 0.25, + "learning_rate": 1.8683039876609258e-05, + "loss": 1.5587, + "step": 2371 + }, + { + "epoch": 0.25, + "learning_rate": 1.868122369220091e-05, + "loss": 1.4214, + "step": 2372 + }, + { + "epoch": 0.25, + "learning_rate": 1.8679406344731645e-05, + "loss": 1.5089, + "step": 2373 + }, + { + "epoch": 0.25, + "learning_rate": 1.867758783444494e-05, + "loss": 1.5067, + "step": 2374 + }, + { + "epoch": 0.25, + "learning_rate": 1.8675768161584427e-05, + "loss": 2.0616, + "step": 2375 + }, + { + "epoch": 0.25, + "learning_rate": 1.8673947326393903e-05, + "loss": 1.5617, + "step": 2376 + }, + { + "epoch": 0.25, + "learning_rate": 1.86721253291173e-05, + "loss": 1.4422, + "step": 2377 + }, + { + "epoch": 0.25, + "learning_rate": 1.867030216999873e-05, + "loss": 1.4727, + "step": 2378 + }, + { + "epoch": 0.25, + "learning_rate": 1.8668477849282443e-05, + "loss": 1.4152, + "step": 2379 + }, + { + "epoch": 0.25, + "learning_rate": 1.8666652367212856e-05, + "loss": 1.4376, + "step": 2380 + }, + { + "epoch": 0.25, + "learning_rate": 1.8664825724034534e-05, + "loss": 1.393, + "step": 2381 + }, + { + "epoch": 0.25, + "learning_rate": 1.8662997919992197e-05, + "loss": 1.4864, + "step": 2382 + }, + { + "epoch": 0.25, + "learning_rate": 1.866116895533073e-05, + "loss": 1.4261, + "step": 2383 + }, + { + "epoch": 0.25, + "learning_rate": 1.8659338830295163e-05, + "loss": 1.4555, + "step": 2384 + }, + { + "epoch": 0.25, + "learning_rate": 1.8657507545130687e-05, + "loss": 1.4939, + "step": 2385 + }, + { + "epoch": 0.25, + "learning_rate": 1.865567510008265e-05, + "loss": 1.4123, + "step": 2386 + }, + { + "epoch": 0.25, + "learning_rate": 1.8653841495396546e-05, + "loss": 1.4459, + "step": 2387 + }, + { + "epoch": 0.25, + "learning_rate": 1.8652006731318038e-05, + "loss": 1.396, + "step": 2388 + }, + { + "epoch": 0.25, + "eval_loss": 1.5139706134796143, + "eval_runtime": 77.2904, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 2388 + }, + { + "epoch": 0.25, + "learning_rate": 1.8650170808092936e-05, + "loss": 1.4666, + "step": 2389 + }, + { + "epoch": 0.25, + "learning_rate": 1.86483337259672e-05, + "loss": 1.5154, + "step": 2390 + }, + { + "epoch": 0.25, + "learning_rate": 1.864649548518696e-05, + "loss": 1.5163, + "step": 2391 + }, + { + "epoch": 0.25, + "learning_rate": 1.864465608599849e-05, + "loss": 1.4734, + "step": 2392 + }, + { + "epoch": 0.25, + "learning_rate": 1.864281552864822e-05, + "loss": 1.5217, + "step": 2393 + }, + { + "epoch": 0.25, + "learning_rate": 1.8640973813382737e-05, + "loss": 1.4694, + "step": 2394 + }, + { + "epoch": 0.25, + "learning_rate": 1.863913094044879e-05, + "loss": 1.4761, + "step": 2395 + }, + { + "epoch": 0.25, + "learning_rate": 1.863728691009327e-05, + "loss": 1.4766, + "step": 2396 + }, + { + "epoch": 0.25, + "learning_rate": 1.863544172256323e-05, + "loss": 1.5695, + "step": 2397 + }, + { + "epoch": 0.25, + "learning_rate": 1.8633595378105882e-05, + "loss": 1.5079, + "step": 2398 + }, + { + "epoch": 0.25, + "learning_rate": 1.8631747876968584e-05, + "loss": 1.4154, + "step": 2399 + }, + { + "epoch": 0.25, + "learning_rate": 1.862989921939886e-05, + "loss": 1.4488, + "step": 2400 + }, + { + "epoch": 0.25, + "learning_rate": 1.8628049405644376e-05, + "loss": 1.4279, + "step": 2401 + }, + { + "epoch": 0.25, + "learning_rate": 1.8626198435952966e-05, + "loss": 1.4896, + "step": 2402 + }, + { + "epoch": 0.25, + "learning_rate": 1.8624346310572602e-05, + "loss": 1.4315, + "step": 2403 + }, + { + "epoch": 0.25, + "learning_rate": 1.862249302975143e-05, + "loss": 1.4919, + "step": 2404 + }, + { + "epoch": 0.25, + "learning_rate": 1.8620638593737743e-05, + "loss": 1.4561, + "step": 2405 + }, + { + "epoch": 0.25, + "learning_rate": 1.8618783002779985e-05, + "loss": 1.4622, + "step": 2406 + }, + { + "epoch": 0.25, + "learning_rate": 1.8616926257126754e-05, + "loss": 1.4917, + "step": 2407 + }, + { + "epoch": 0.25, + "learning_rate": 1.861506835702681e-05, + "loss": 1.4962, + "step": 2408 + }, + { + "epoch": 0.25, + "learning_rate": 1.861320930272906e-05, + "loss": 1.4164, + "step": 2409 + }, + { + "epoch": 0.25, + "learning_rate": 1.8611349094482578e-05, + "loss": 1.4889, + "step": 2410 + }, + { + "epoch": 0.25, + "learning_rate": 1.8609487732536576e-05, + "loss": 1.543, + "step": 2411 + }, + { + "epoch": 0.25, + "learning_rate": 1.8607625217140433e-05, + "loss": 1.5417, + "step": 2412 + }, + { + "epoch": 0.25, + "learning_rate": 1.8605761548543674e-05, + "loss": 1.5304, + "step": 2413 + }, + { + "epoch": 0.25, + "learning_rate": 1.860389672699599e-05, + "loss": 1.4725, + "step": 2414 + }, + { + "epoch": 0.25, + "learning_rate": 1.860203075274721e-05, + "loss": 1.4745, + "step": 2415 + }, + { + "epoch": 0.25, + "learning_rate": 1.8600163626047334e-05, + "loss": 1.4656, + "step": 2416 + }, + { + "epoch": 0.25, + "learning_rate": 1.8598295347146503e-05, + "loss": 1.5287, + "step": 2417 + }, + { + "epoch": 0.25, + "learning_rate": 1.8596425916295023e-05, + "loss": 1.5024, + "step": 2418 + }, + { + "epoch": 0.25, + "learning_rate": 1.8594555333743348e-05, + "loss": 1.4527, + "step": 2419 + }, + { + "epoch": 0.25, + "learning_rate": 1.859268359974209e-05, + "loss": 1.4897, + "step": 2420 + }, + { + "epoch": 0.25, + "learning_rate": 1.859081071454201e-05, + "loss": 1.3554, + "step": 2421 + }, + { + "epoch": 0.25, + "learning_rate": 1.858893667839403e-05, + "loss": 1.4004, + "step": 2422 + }, + { + "epoch": 0.25, + "learning_rate": 1.858706149154922e-05, + "loss": 1.5582, + "step": 2423 + }, + { + "epoch": 0.25, + "learning_rate": 1.8585185154258803e-05, + "loss": 1.505, + "step": 2424 + }, + { + "epoch": 0.25, + "learning_rate": 1.858330766677417e-05, + "loss": 1.5043, + "step": 2425 + }, + { + "epoch": 0.25, + "learning_rate": 1.858142902934685e-05, + "loss": 1.439, + "step": 2426 + }, + { + "epoch": 0.25, + "learning_rate": 1.857954924222853e-05, + "loss": 1.4927, + "step": 2427 + }, + { + "epoch": 0.25, + "learning_rate": 1.8577668305671056e-05, + "loss": 1.5395, + "step": 2428 + }, + { + "epoch": 0.25, + "learning_rate": 1.8575786219926427e-05, + "loss": 1.4737, + "step": 2429 + }, + { + "epoch": 0.25, + "learning_rate": 1.8573902985246794e-05, + "loss": 1.6151, + "step": 2430 + }, + { + "epoch": 0.25, + "learning_rate": 1.857201860188446e-05, + "loss": 1.4313, + "step": 2431 + }, + { + "epoch": 0.26, + "learning_rate": 1.857013307009188e-05, + "loss": 1.4509, + "step": 2432 + }, + { + "epoch": 0.26, + "learning_rate": 1.8568246390121673e-05, + "loss": 1.3998, + "step": 2433 + }, + { + "epoch": 0.26, + "learning_rate": 1.8566358562226603e-05, + "loss": 1.5268, + "step": 2434 + }, + { + "epoch": 0.26, + "learning_rate": 1.8564469586659593e-05, + "loss": 1.4369, + "step": 2435 + }, + { + "epoch": 0.26, + "learning_rate": 1.8562579463673713e-05, + "loss": 1.4759, + "step": 2436 + }, + { + "epoch": 0.26, + "learning_rate": 1.8560688193522197e-05, + "loss": 1.4092, + "step": 2437 + }, + { + "epoch": 0.26, + "learning_rate": 1.855879577645842e-05, + "loss": 1.43, + "step": 2438 + }, + { + "epoch": 0.26, + "learning_rate": 1.855690221273592e-05, + "loss": 1.5143, + "step": 2439 + }, + { + "epoch": 0.26, + "learning_rate": 1.8555007502608385e-05, + "loss": 1.5482, + "step": 2440 + }, + { + "epoch": 0.26, + "learning_rate": 1.855311164632966e-05, + "loss": 1.4406, + "step": 2441 + }, + { + "epoch": 0.26, + "learning_rate": 1.8551214644153738e-05, + "loss": 1.4551, + "step": 2442 + }, + { + "epoch": 0.26, + "learning_rate": 1.8549316496334774e-05, + "loss": 1.4663, + "step": 2443 + }, + { + "epoch": 0.26, + "learning_rate": 1.8547417203127064e-05, + "loss": 1.4732, + "step": 2444 + }, + { + "epoch": 0.26, + "learning_rate": 1.8545516764785067e-05, + "loss": 1.5378, + "step": 2445 + }, + { + "epoch": 0.26, + "learning_rate": 1.8543615181563397e-05, + "loss": 1.4448, + "step": 2446 + }, + { + "epoch": 0.26, + "learning_rate": 1.854171245371681e-05, + "loss": 1.2861, + "step": 2447 + }, + { + "epoch": 0.26, + "learning_rate": 1.8539808581500228e-05, + "loss": 1.4405, + "step": 2448 + }, + { + "epoch": 0.26, + "learning_rate": 1.8537903565168716e-05, + "loss": 1.4876, + "step": 2449 + }, + { + "epoch": 0.26, + "learning_rate": 1.8535997404977506e-05, + "loss": 1.4119, + "step": 2450 + }, + { + "epoch": 0.26, + "learning_rate": 1.8534090101181967e-05, + "loss": 1.4451, + "step": 2451 + }, + { + "epoch": 0.26, + "learning_rate": 1.8532181654037632e-05, + "loss": 1.4035, + "step": 2452 + }, + { + "epoch": 0.26, + "learning_rate": 1.853027206380018e-05, + "loss": 1.4624, + "step": 2453 + }, + { + "epoch": 0.26, + "learning_rate": 1.852836133072545e-05, + "loss": 1.4935, + "step": 2454 + }, + { + "epoch": 0.26, + "learning_rate": 1.8526449455069434e-05, + "loss": 1.4834, + "step": 2455 + }, + { + "epoch": 0.26, + "learning_rate": 1.8524536437088266e-05, + "loss": 1.498, + "step": 2456 + }, + { + "epoch": 0.26, + "learning_rate": 1.8522622277038247e-05, + "loss": 1.3417, + "step": 2457 + }, + { + "epoch": 0.26, + "learning_rate": 1.852070697517583e-05, + "loss": 1.4455, + "step": 2458 + }, + { + "epoch": 0.26, + "learning_rate": 1.8518790531757607e-05, + "loss": 1.4119, + "step": 2459 + }, + { + "epoch": 0.26, + "learning_rate": 1.8516872947040337e-05, + "loss": 1.558, + "step": 2460 + }, + { + "epoch": 0.26, + "learning_rate": 1.8514954221280926e-05, + "loss": 1.4862, + "step": 2461 + }, + { + "epoch": 0.26, + "learning_rate": 1.8513034354736433e-05, + "loss": 1.6806, + "step": 2462 + }, + { + "epoch": 0.26, + "learning_rate": 1.8511113347664072e-05, + "loss": 1.438, + "step": 2463 + }, + { + "epoch": 0.26, + "learning_rate": 1.850919120032121e-05, + "loss": 1.4975, + "step": 2464 + }, + { + "epoch": 0.26, + "learning_rate": 1.850726791296536e-05, + "loss": 1.4409, + "step": 2465 + }, + { + "epoch": 0.26, + "learning_rate": 1.85053434858542e-05, + "loss": 1.4769, + "step": 2466 + }, + { + "epoch": 0.26, + "learning_rate": 1.8503417919245548e-05, + "loss": 1.5823, + "step": 2467 + }, + { + "epoch": 0.26, + "learning_rate": 1.8501491213397386e-05, + "loss": 1.4045, + "step": 2468 + }, + { + "epoch": 0.26, + "learning_rate": 1.8499563368567837e-05, + "loss": 1.4828, + "step": 2469 + }, + { + "epoch": 0.26, + "learning_rate": 1.849763438501519e-05, + "loss": 1.4684, + "step": 2470 + }, + { + "epoch": 0.26, + "learning_rate": 1.8495704262997873e-05, + "loss": 1.4577, + "step": 2471 + }, + { + "epoch": 0.26, + "learning_rate": 1.8493773002774475e-05, + "loss": 1.4759, + "step": 2472 + }, + { + "epoch": 0.26, + "learning_rate": 1.8491840604603736e-05, + "loss": 1.4259, + "step": 2473 + }, + { + "epoch": 0.26, + "learning_rate": 1.8489907068744543e-05, + "loss": 1.4717, + "step": 2474 + }, + { + "epoch": 0.26, + "learning_rate": 1.848797239545595e-05, + "loss": 1.4247, + "step": 2475 + }, + { + "epoch": 0.26, + "learning_rate": 1.8486036584997143e-05, + "loss": 1.4954, + "step": 2476 + }, + { + "epoch": 0.26, + "learning_rate": 1.8484099637627472e-05, + "loss": 1.4926, + "step": 2477 + }, + { + "epoch": 0.26, + "learning_rate": 1.8482161553606447e-05, + "loss": 1.487, + "step": 2478 + }, + { + "epoch": 0.26, + "learning_rate": 1.8480222333193715e-05, + "loss": 1.4553, + "step": 2479 + }, + { + "epoch": 0.26, + "learning_rate": 1.847828197664908e-05, + "loss": 1.4862, + "step": 2480 + }, + { + "epoch": 0.26, + "learning_rate": 1.8476340484232508e-05, + "loss": 1.4867, + "step": 2481 + }, + { + "epoch": 0.26, + "learning_rate": 1.8474397856204097e-05, + "loss": 1.4736, + "step": 2482 + }, + { + "epoch": 0.26, + "learning_rate": 1.8472454092824122e-05, + "loss": 1.4254, + "step": 2483 + }, + { + "epoch": 0.26, + "learning_rate": 1.8470509194352987e-05, + "loss": 1.4455, + "step": 2484 + }, + { + "epoch": 0.26, + "learning_rate": 1.8468563161051263e-05, + "loss": 1.4402, + "step": 2485 + }, + { + "epoch": 0.26, + "learning_rate": 1.846661599317967e-05, + "loss": 1.4611, + "step": 2486 + }, + { + "epoch": 0.26, + "learning_rate": 1.8464667690999073e-05, + "loss": 1.4814, + "step": 2487 + }, + { + "epoch": 0.26, + "learning_rate": 1.8462718254770503e-05, + "loss": 1.4559, + "step": 2488 + }, + { + "epoch": 0.26, + "learning_rate": 1.8460767684755127e-05, + "loss": 1.4667, + "step": 2489 + }, + { + "epoch": 0.26, + "learning_rate": 1.8458815981214274e-05, + "loss": 1.4427, + "step": 2490 + }, + { + "epoch": 0.26, + "learning_rate": 1.845686314440942e-05, + "loss": 1.4055, + "step": 2491 + }, + { + "epoch": 0.26, + "learning_rate": 1.8454909174602198e-05, + "loss": 1.5563, + "step": 2492 + }, + { + "epoch": 0.26, + "learning_rate": 1.845295407205439e-05, + "loss": 1.4631, + "step": 2493 + }, + { + "epoch": 0.26, + "learning_rate": 1.8450997837027925e-05, + "loss": 1.4887, + "step": 2494 + }, + { + "epoch": 0.26, + "learning_rate": 1.8449040469784895e-05, + "loss": 1.5212, + "step": 2495 + }, + { + "epoch": 0.26, + "learning_rate": 1.844708197058753e-05, + "loss": 1.5582, + "step": 2496 + }, + { + "epoch": 0.26, + "learning_rate": 1.844512233969822e-05, + "loss": 1.4599, + "step": 2497 + }, + { + "epoch": 0.26, + "learning_rate": 1.844316157737951e-05, + "loss": 1.4546, + "step": 2498 + }, + { + "epoch": 0.26, + "learning_rate": 1.844119968389409e-05, + "loss": 1.4631, + "step": 2499 + }, + { + "epoch": 0.26, + "learning_rate": 1.84392366595048e-05, + "loss": 1.4817, + "step": 2500 + }, + { + "epoch": 0.26, + "learning_rate": 1.8437272504474636e-05, + "loss": 1.4214, + "step": 2501 + }, + { + "epoch": 0.26, + "learning_rate": 1.8435307219066744e-05, + "loss": 1.471, + "step": 2502 + }, + { + "epoch": 0.26, + "learning_rate": 1.8433340803544424e-05, + "loss": 1.4693, + "step": 2503 + }, + { + "epoch": 0.26, + "learning_rate": 1.8431373258171127e-05, + "loss": 1.6297, + "step": 2504 + }, + { + "epoch": 0.26, + "learning_rate": 1.842940458321045e-05, + "loss": 1.5916, + "step": 2505 + }, + { + "epoch": 0.26, + "learning_rate": 1.842743477892614e-05, + "loss": 1.4754, + "step": 2506 + }, + { + "epoch": 0.26, + "learning_rate": 1.842546384558211e-05, + "loss": 1.4828, + "step": 2507 + }, + { + "epoch": 0.26, + "learning_rate": 1.842349178344241e-05, + "loss": 1.4239, + "step": 2508 + }, + { + "epoch": 0.26, + "learning_rate": 1.8421518592771243e-05, + "loss": 1.5028, + "step": 2509 + }, + { + "epoch": 0.26, + "learning_rate": 1.841954427383297e-05, + "loss": 1.4848, + "step": 2510 + }, + { + "epoch": 0.26, + "learning_rate": 1.8417568826892097e-05, + "loss": 1.4617, + "step": 2511 + }, + { + "epoch": 0.26, + "learning_rate": 1.8415592252213284e-05, + "loss": 1.4266, + "step": 2512 + }, + { + "epoch": 0.26, + "learning_rate": 1.8413614550061344e-05, + "loss": 1.4321, + "step": 2513 + }, + { + "epoch": 0.26, + "learning_rate": 1.841163572070123e-05, + "loss": 1.4693, + "step": 2514 + }, + { + "epoch": 0.26, + "learning_rate": 1.840965576439806e-05, + "loss": 1.4257, + "step": 2515 + }, + { + "epoch": 0.26, + "learning_rate": 1.84076746814171e-05, + "loss": 1.4488, + "step": 2516 + }, + { + "epoch": 0.26, + "learning_rate": 1.840569247202376e-05, + "loss": 1.5348, + "step": 2517 + }, + { + "epoch": 0.26, + "learning_rate": 1.8403709136483604e-05, + "loss": 1.477, + "step": 2518 + }, + { + "epoch": 0.26, + "learning_rate": 1.840172467506235e-05, + "loss": 1.443, + "step": 2519 + }, + { + "epoch": 0.26, + "learning_rate": 1.839973908802587e-05, + "loss": 1.4772, + "step": 2520 + }, + { + "epoch": 0.26, + "learning_rate": 1.839775237564017e-05, + "loss": 1.4443, + "step": 2521 + }, + { + "epoch": 0.26, + "learning_rate": 1.839576453817143e-05, + "loss": 1.4063, + "step": 2522 + }, + { + "epoch": 0.26, + "learning_rate": 1.8393775575885963e-05, + "loss": 1.5178, + "step": 2523 + }, + { + "epoch": 0.26, + "learning_rate": 1.8391785489050235e-05, + "loss": 1.4337, + "step": 2524 + }, + { + "epoch": 0.26, + "learning_rate": 1.8389794277930875e-05, + "loss": 1.4512, + "step": 2525 + }, + { + "epoch": 0.26, + "learning_rate": 1.838780194279465e-05, + "loss": 1.5578, + "step": 2526 + }, + { + "epoch": 0.26, + "learning_rate": 1.8385808483908484e-05, + "loss": 1.4606, + "step": 2527 + }, + { + "epoch": 0.27, + "learning_rate": 1.8383813901539444e-05, + "loss": 1.4957, + "step": 2528 + }, + { + "epoch": 0.27, + "learning_rate": 1.838181819595476e-05, + "loss": 1.4914, + "step": 2529 + }, + { + "epoch": 0.27, + "learning_rate": 1.8379821367421802e-05, + "loss": 1.4785, + "step": 2530 + }, + { + "epoch": 0.27, + "learning_rate": 1.837782341620809e-05, + "loss": 1.4052, + "step": 2531 + }, + { + "epoch": 0.27, + "learning_rate": 1.8375824342581303e-05, + "loss": 1.4807, + "step": 2532 + }, + { + "epoch": 0.27, + "learning_rate": 1.8373824146809264e-05, + "loss": 1.4313, + "step": 2533 + }, + { + "epoch": 0.27, + "learning_rate": 1.8371822829159945e-05, + "loss": 1.4374, + "step": 2534 + }, + { + "epoch": 0.27, + "learning_rate": 1.836982038990148e-05, + "loss": 1.4482, + "step": 2535 + }, + { + "epoch": 0.27, + "learning_rate": 1.8367816829302133e-05, + "loss": 1.5231, + "step": 2536 + }, + { + "epoch": 0.27, + "learning_rate": 1.8365812147630337e-05, + "loss": 1.4101, + "step": 2537 + }, + { + "epoch": 0.27, + "learning_rate": 1.8363806345154666e-05, + "loss": 1.4372, + "step": 2538 + }, + { + "epoch": 0.27, + "learning_rate": 1.8361799422143845e-05, + "loss": 1.4808, + "step": 2539 + }, + { + "epoch": 0.27, + "learning_rate": 1.835979137886675e-05, + "loss": 1.3515, + "step": 2540 + }, + { + "epoch": 0.27, + "learning_rate": 1.8357782215592412e-05, + "loss": 1.5284, + "step": 2541 + }, + { + "epoch": 0.27, + "learning_rate": 1.835577193259e-05, + "loss": 1.4222, + "step": 2542 + }, + { + "epoch": 0.27, + "learning_rate": 1.8353760530128846e-05, + "loss": 1.4522, + "step": 2543 + }, + { + "epoch": 0.27, + "learning_rate": 1.835174800847842e-05, + "loss": 1.4487, + "step": 2544 + }, + { + "epoch": 0.27, + "learning_rate": 1.8349734367908355e-05, + "loss": 1.3688, + "step": 2545 + }, + { + "epoch": 0.27, + "learning_rate": 1.8347719608688422e-05, + "loss": 1.483, + "step": 2546 + }, + { + "epoch": 0.27, + "learning_rate": 1.8345703731088554e-05, + "loss": 1.4733, + "step": 2547 + }, + { + "epoch": 0.27, + "learning_rate": 1.8343686735378816e-05, + "loss": 1.4594, + "step": 2548 + }, + { + "epoch": 0.27, + "learning_rate": 1.834166862182944e-05, + "loss": 1.4648, + "step": 2549 + }, + { + "epoch": 0.27, + "learning_rate": 1.8339649390710807e-05, + "loss": 1.5249, + "step": 2550 + }, + { + "epoch": 0.27, + "learning_rate": 1.8337629042293434e-05, + "loss": 1.4744, + "step": 2551 + }, + { + "epoch": 0.27, + "learning_rate": 1.8335607576847994e-05, + "loss": 1.5094, + "step": 2552 + }, + { + "epoch": 0.27, + "learning_rate": 1.8333584994645318e-05, + "loss": 1.5122, + "step": 2553 + }, + { + "epoch": 0.27, + "learning_rate": 1.8331561295956374e-05, + "loss": 1.537, + "step": 2554 + }, + { + "epoch": 0.27, + "learning_rate": 1.832953648105229e-05, + "loss": 1.4691, + "step": 2555 + }, + { + "epoch": 0.27, + "learning_rate": 1.8327510550204343e-05, + "loss": 1.4969, + "step": 2556 + }, + { + "epoch": 0.27, + "learning_rate": 1.8325483503683944e-05, + "loss": 1.4596, + "step": 2557 + }, + { + "epoch": 0.27, + "learning_rate": 1.8323455341762675e-05, + "loss": 1.435, + "step": 2558 + }, + { + "epoch": 0.27, + "learning_rate": 1.8321426064712255e-05, + "loss": 1.4883, + "step": 2559 + }, + { + "epoch": 0.27, + "learning_rate": 1.8319395672804554e-05, + "loss": 1.3758, + "step": 2560 + }, + { + "epoch": 0.27, + "learning_rate": 1.8317364166311592e-05, + "loss": 1.4352, + "step": 2561 + }, + { + "epoch": 0.27, + "learning_rate": 1.831533154550554e-05, + "loss": 1.5072, + "step": 2562 + }, + { + "epoch": 0.27, + "learning_rate": 1.8313297810658718e-05, + "loss": 1.4476, + "step": 2563 + }, + { + "epoch": 0.27, + "learning_rate": 1.831126296204359e-05, + "loss": 1.507, + "step": 2564 + }, + { + "epoch": 0.27, + "learning_rate": 1.8309226999932777e-05, + "loss": 1.4677, + "step": 2565 + }, + { + "epoch": 0.27, + "learning_rate": 1.8307189924599044e-05, + "loss": 1.4537, + "step": 2566 + }, + { + "epoch": 0.27, + "learning_rate": 1.8305151736315307e-05, + "loss": 1.4584, + "step": 2567 + }, + { + "epoch": 0.27, + "learning_rate": 1.8303112435354634e-05, + "loss": 1.4944, + "step": 2568 + }, + { + "epoch": 0.27, + "learning_rate": 1.8301072021990232e-05, + "loss": 1.4379, + "step": 2569 + }, + { + "epoch": 0.27, + "learning_rate": 1.8299030496495475e-05, + "loss": 1.539, + "step": 2570 + }, + { + "epoch": 0.27, + "learning_rate": 1.829698785914386e-05, + "loss": 1.4421, + "step": 2571 + }, + { + "epoch": 0.27, + "learning_rate": 1.8294944110209063e-05, + "loss": 1.4693, + "step": 2572 + }, + { + "epoch": 0.27, + "learning_rate": 1.8292899249964887e-05, + "loss": 1.3239, + "step": 2573 + }, + { + "epoch": 0.27, + "learning_rate": 1.8290853278685284e-05, + "loss": 1.472, + "step": 2574 + }, + { + "epoch": 0.27, + "learning_rate": 1.8288806196644374e-05, + "loss": 1.536, + "step": 2575 + }, + { + "epoch": 0.27, + "learning_rate": 1.8286758004116405e-05, + "loss": 1.4644, + "step": 2576 + }, + { + "epoch": 0.27, + "learning_rate": 1.8284708701375783e-05, + "loss": 1.4537, + "step": 2577 + }, + { + "epoch": 0.27, + "learning_rate": 1.8282658288697067e-05, + "loss": 1.4359, + "step": 2578 + }, + { + "epoch": 0.27, + "learning_rate": 1.8280606766354955e-05, + "loss": 1.4842, + "step": 2579 + }, + { + "epoch": 0.27, + "learning_rate": 1.8278554134624302e-05, + "loss": 1.4664, + "step": 2580 + }, + { + "epoch": 0.27, + "learning_rate": 1.8276500393780105e-05, + "loss": 1.4632, + "step": 2581 + }, + { + "epoch": 0.27, + "learning_rate": 1.827444554409751e-05, + "loss": 1.4996, + "step": 2582 + }, + { + "epoch": 0.27, + "learning_rate": 1.827238958585182e-05, + "loss": 1.3399, + "step": 2583 + }, + { + "epoch": 0.27, + "learning_rate": 1.8270332519318476e-05, + "loss": 1.3928, + "step": 2584 + }, + { + "epoch": 0.27, + "learning_rate": 1.8268274344773074e-05, + "loss": 1.4993, + "step": 2585 + }, + { + "epoch": 0.27, + "learning_rate": 1.8266215062491356e-05, + "loss": 1.5398, + "step": 2586 + }, + { + "epoch": 0.27, + "learning_rate": 1.826415467274921e-05, + "loss": 1.4353, + "step": 2587 + }, + { + "epoch": 0.27, + "eval_loss": 1.5104212760925293, + "eval_runtime": 77.3448, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2587 + }, + { + "epoch": 0.27, + "learning_rate": 1.8262093175822685e-05, + "loss": 1.4889, + "step": 2588 + }, + { + "epoch": 0.27, + "learning_rate": 1.826003057198796e-05, + "loss": 1.4912, + "step": 2589 + }, + { + "epoch": 0.27, + "learning_rate": 1.825796686152137e-05, + "loss": 1.4884, + "step": 2590 + }, + { + "epoch": 0.27, + "learning_rate": 1.8255902044699404e-05, + "loss": 1.478, + "step": 2591 + }, + { + "epoch": 0.27, + "learning_rate": 1.8253836121798692e-05, + "loss": 1.6549, + "step": 2592 + }, + { + "epoch": 0.27, + "learning_rate": 1.8251769093096018e-05, + "loss": 1.5146, + "step": 2593 + }, + { + "epoch": 0.27, + "learning_rate": 1.8249700958868306e-05, + "loss": 1.4797, + "step": 2594 + }, + { + "epoch": 0.27, + "learning_rate": 1.8247631719392634e-05, + "loss": 1.4655, + "step": 2595 + }, + { + "epoch": 0.27, + "learning_rate": 1.824556137494623e-05, + "loss": 1.4517, + "step": 2596 + }, + { + "epoch": 0.27, + "learning_rate": 1.8243489925806458e-05, + "loss": 1.4936, + "step": 2597 + }, + { + "epoch": 0.27, + "learning_rate": 1.8241417372250852e-05, + "loss": 1.4614, + "step": 2598 + }, + { + "epoch": 0.27, + "learning_rate": 1.8239343714557073e-05, + "loss": 1.4475, + "step": 2599 + }, + { + "epoch": 0.27, + "learning_rate": 1.8237268953002937e-05, + "loss": 1.5435, + "step": 2600 + }, + { + "epoch": 0.27, + "learning_rate": 1.8235193087866413e-05, + "loss": 1.4616, + "step": 2601 + }, + { + "epoch": 0.27, + "learning_rate": 1.8233116119425612e-05, + "loss": 1.4578, + "step": 2602 + }, + { + "epoch": 0.27, + "learning_rate": 1.8231038047958795e-05, + "loss": 1.434, + "step": 2603 + }, + { + "epoch": 0.27, + "learning_rate": 1.8228958873744368e-05, + "loss": 1.5335, + "step": 2604 + }, + { + "epoch": 0.27, + "learning_rate": 1.8226878597060887e-05, + "loss": 1.415, + "step": 2605 + }, + { + "epoch": 0.27, + "learning_rate": 1.8224797218187058e-05, + "loss": 1.6165, + "step": 2606 + }, + { + "epoch": 0.27, + "learning_rate": 1.822271473740173e-05, + "loss": 1.372, + "step": 2607 + }, + { + "epoch": 0.27, + "learning_rate": 1.8220631154983907e-05, + "loss": 1.4855, + "step": 2608 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218546471212727e-05, + "loss": 1.4093, + "step": 2609 + }, + { + "epoch": 0.27, + "learning_rate": 1.821646068636749e-05, + "loss": 1.4852, + "step": 2610 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214373800727637e-05, + "loss": 1.6959, + "step": 2611 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212285814572755e-05, + "loss": 1.3874, + "step": 2612 + }, + { + "epoch": 0.27, + "learning_rate": 1.821019672818258e-05, + "loss": 1.4425, + "step": 2613 + }, + { + "epoch": 0.27, + "learning_rate": 1.8208106541837e-05, + "loss": 1.6097, + "step": 2614 + }, + { + "epoch": 0.27, + "learning_rate": 1.8206015255816045e-05, + "loss": 1.5675, + "step": 2615 + }, + { + "epoch": 0.27, + "learning_rate": 1.820392287039989e-05, + "loss": 1.4039, + "step": 2616 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201829385868866e-05, + "loss": 1.4872, + "step": 2617 + }, + { + "epoch": 0.27, + "learning_rate": 1.819973480250344e-05, + "loss": 1.4645, + "step": 2618 + }, + { + "epoch": 0.27, + "learning_rate": 1.8197639120584237e-05, + "loss": 1.4923, + "step": 2619 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195542340392025e-05, + "loss": 1.4294, + "step": 2620 + }, + { + "epoch": 0.27, + "learning_rate": 1.8193444462207717e-05, + "loss": 1.4315, + "step": 2621 + }, + { + "epoch": 0.27, + "learning_rate": 1.8191345486312372e-05, + "loss": 1.3972, + "step": 2622 + }, + { + "epoch": 0.28, + "learning_rate": 1.8189245412987205e-05, + "loss": 1.462, + "step": 2623 + }, + { + "epoch": 0.28, + "learning_rate": 1.8187144242513567e-05, + "loss": 1.4738, + "step": 2624 + }, + { + "epoch": 0.28, + "learning_rate": 1.818504197517296e-05, + "loss": 1.4935, + "step": 2625 + }, + { + "epoch": 0.28, + "learning_rate": 1.8182938611247038e-05, + "loss": 1.4231, + "step": 2626 + }, + { + "epoch": 0.28, + "learning_rate": 1.81808341510176e-05, + "loss": 1.4031, + "step": 2627 + }, + { + "epoch": 0.28, + "learning_rate": 1.817872859476658e-05, + "loss": 1.5822, + "step": 2628 + }, + { + "epoch": 0.28, + "learning_rate": 1.8176621942776075e-05, + "loss": 1.432, + "step": 2629 + }, + { + "epoch": 0.28, + "learning_rate": 1.8174514195328324e-05, + "loss": 1.5565, + "step": 2630 + }, + { + "epoch": 0.28, + "learning_rate": 1.8172405352705704e-05, + "loss": 1.4895, + "step": 2631 + }, + { + "epoch": 0.28, + "learning_rate": 1.8170295415190754e-05, + "loss": 1.4032, + "step": 2632 + }, + { + "epoch": 0.28, + "learning_rate": 1.8168184383066144e-05, + "loss": 1.4253, + "step": 2633 + }, + { + "epoch": 0.28, + "learning_rate": 1.8166072256614702e-05, + "loss": 1.5162, + "step": 2634 + }, + { + "epoch": 0.28, + "learning_rate": 1.81639590361194e-05, + "loss": 1.4609, + "step": 2635 + }, + { + "epoch": 0.28, + "learning_rate": 1.816184472186335e-05, + "loss": 1.4351, + "step": 2636 + }, + { + "epoch": 0.28, + "learning_rate": 1.8159729314129823e-05, + "loss": 1.4738, + "step": 2637 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157612813202224e-05, + "loss": 1.5986, + "step": 2638 + }, + { + "epoch": 0.28, + "learning_rate": 1.815549521936411e-05, + "loss": 1.4633, + "step": 2639 + }, + { + "epoch": 0.28, + "learning_rate": 1.8153376532899184e-05, + "loss": 1.4404, + "step": 2640 + }, + { + "epoch": 0.28, + "learning_rate": 1.81512567540913e-05, + "loss": 1.4256, + "step": 2641 + }, + { + "epoch": 0.28, + "learning_rate": 1.814913588322445e-05, + "loss": 1.4054, + "step": 2642 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147013920582773e-05, + "loss": 1.4134, + "step": 2643 + }, + { + "epoch": 0.28, + "learning_rate": 1.8144890866450567e-05, + "loss": 1.4098, + "step": 2644 + }, + { + "epoch": 0.28, + "learning_rate": 1.814276672111226e-05, + "loss": 1.4593, + "step": 2645 + }, + { + "epoch": 0.28, + "learning_rate": 1.814064148485243e-05, + "loss": 1.4679, + "step": 2646 + }, + { + "epoch": 0.28, + "learning_rate": 1.8138515157955812e-05, + "loss": 1.5234, + "step": 2647 + }, + { + "epoch": 0.28, + "learning_rate": 1.8136387740707272e-05, + "loss": 1.4568, + "step": 2648 + }, + { + "epoch": 0.28, + "learning_rate": 1.8134259233391836e-05, + "loss": 1.5057, + "step": 2649 + }, + { + "epoch": 0.28, + "learning_rate": 1.8132129636294665e-05, + "loss": 1.3643, + "step": 2650 + }, + { + "epoch": 0.28, + "learning_rate": 1.812999894970107e-05, + "loss": 1.4766, + "step": 2651 + }, + { + "epoch": 0.28, + "learning_rate": 1.812786717389651e-05, + "loss": 1.5701, + "step": 2652 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125734309166587e-05, + "loss": 1.5341, + "step": 2653 + }, + { + "epoch": 0.28, + "learning_rate": 1.812360035579705e-05, + "loss": 1.3596, + "step": 2654 + }, + { + "epoch": 0.28, + "learning_rate": 1.8121465314073793e-05, + "loss": 1.4847, + "step": 2655 + }, + { + "epoch": 0.28, + "learning_rate": 1.811932918428286e-05, + "loss": 1.4664, + "step": 2656 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117191966710438e-05, + "loss": 1.4673, + "step": 2657 + }, + { + "epoch": 0.28, + "learning_rate": 1.8115053661642856e-05, + "loss": 1.4712, + "step": 2658 + }, + { + "epoch": 0.28, + "learning_rate": 1.811291426936659e-05, + "loss": 1.4458, + "step": 2659 + }, + { + "epoch": 0.28, + "learning_rate": 1.811077379016827e-05, + "loss": 1.4667, + "step": 2660 + }, + { + "epoch": 0.28, + "learning_rate": 1.810863222433466e-05, + "loss": 1.4695, + "step": 2661 + }, + { + "epoch": 0.28, + "learning_rate": 1.8106489572152677e-05, + "loss": 1.5263, + "step": 2662 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104345833909376e-05, + "loss": 1.4148, + "step": 2663 + }, + { + "epoch": 0.28, + "learning_rate": 1.8102201009891976e-05, + "loss": 1.3955, + "step": 2664 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100055100387814e-05, + "loss": 1.6056, + "step": 2665 + }, + { + "epoch": 0.28, + "learning_rate": 1.8097908105684396e-05, + "loss": 1.5394, + "step": 2666 + }, + { + "epoch": 0.28, + "learning_rate": 1.809576002606936e-05, + "loss": 1.479, + "step": 2667 + }, + { + "epoch": 0.28, + "learning_rate": 1.8093610861830494e-05, + "loss": 1.4492, + "step": 2668 + }, + { + "epoch": 0.28, + "learning_rate": 1.8091460613255728e-05, + "loss": 1.4172, + "step": 2669 + }, + { + "epoch": 0.28, + "learning_rate": 1.808930928063315e-05, + "loss": 1.4498, + "step": 2670 + }, + { + "epoch": 0.28, + "learning_rate": 1.808715686425097e-05, + "loss": 1.6203, + "step": 2671 + }, + { + "epoch": 0.28, + "learning_rate": 1.8085003364397567e-05, + "loss": 1.435, + "step": 2672 + }, + { + "epoch": 0.28, + "learning_rate": 1.808284878136145e-05, + "loss": 1.4489, + "step": 2673 + }, + { + "epoch": 0.28, + "learning_rate": 1.8080693115431277e-05, + "loss": 1.4416, + "step": 2674 + }, + { + "epoch": 0.28, + "learning_rate": 1.8078536366895853e-05, + "loss": 1.422, + "step": 2675 + }, + { + "epoch": 0.28, + "learning_rate": 1.8076378536044128e-05, + "loss": 1.4039, + "step": 2676 + }, + { + "epoch": 0.28, + "learning_rate": 1.8074219623165195e-05, + "loss": 1.4705, + "step": 2677 + }, + { + "epoch": 0.28, + "learning_rate": 1.807205962854829e-05, + "loss": 1.5031, + "step": 2678 + }, + { + "epoch": 0.28, + "learning_rate": 1.8069898552482806e-05, + "loss": 1.4812, + "step": 2679 + }, + { + "epoch": 0.28, + "learning_rate": 1.806773639525826e-05, + "loss": 1.4129, + "step": 2680 + }, + { + "epoch": 0.28, + "learning_rate": 1.8065573157164332e-05, + "loss": 1.4559, + "step": 2681 + }, + { + "epoch": 0.28, + "learning_rate": 1.806340883849084e-05, + "loss": 1.3878, + "step": 2682 + }, + { + "epoch": 0.28, + "learning_rate": 1.8061243439527744e-05, + "loss": 1.4752, + "step": 2683 + }, + { + "epoch": 0.28, + "learning_rate": 1.8059076960565156e-05, + "loss": 1.4089, + "step": 2684 + }, + { + "epoch": 0.28, + "learning_rate": 1.8056909401893326e-05, + "loss": 1.4736, + "step": 2685 + }, + { + "epoch": 0.28, + "learning_rate": 1.8054740763802654e-05, + "loss": 1.3796, + "step": 2686 + }, + { + "epoch": 0.28, + "learning_rate": 1.805257104658368e-05, + "loss": 1.4412, + "step": 2687 + }, + { + "epoch": 0.28, + "learning_rate": 1.8050400250527086e-05, + "loss": 1.4639, + "step": 2688 + }, + { + "epoch": 0.28, + "learning_rate": 1.804822837592371e-05, + "loss": 1.4076, + "step": 2689 + }, + { + "epoch": 0.28, + "learning_rate": 1.804605542306452e-05, + "loss": 1.4627, + "step": 2690 + }, + { + "epoch": 0.28, + "learning_rate": 1.8043881392240642e-05, + "loss": 1.5249, + "step": 2691 + }, + { + "epoch": 0.28, + "learning_rate": 1.804170628374334e-05, + "loss": 1.4312, + "step": 2692 + }, + { + "epoch": 0.28, + "learning_rate": 1.803953009786402e-05, + "loss": 1.5676, + "step": 2693 + }, + { + "epoch": 0.28, + "learning_rate": 1.8037352834894233e-05, + "loss": 1.5072, + "step": 2694 + }, + { + "epoch": 0.28, + "learning_rate": 1.803517449512568e-05, + "loss": 1.5662, + "step": 2695 + }, + { + "epoch": 0.28, + "learning_rate": 1.8032995078850207e-05, + "loss": 1.4771, + "step": 2696 + }, + { + "epoch": 0.28, + "learning_rate": 1.803081458635979e-05, + "loss": 1.412, + "step": 2697 + }, + { + "epoch": 0.28, + "learning_rate": 1.8028633017946564e-05, + "loss": 1.497, + "step": 2698 + }, + { + "epoch": 0.28, + "learning_rate": 1.8026450373902804e-05, + "loss": 1.4528, + "step": 2699 + }, + { + "epoch": 0.28, + "learning_rate": 1.802426665452093e-05, + "loss": 1.4785, + "step": 2700 + }, + { + "epoch": 0.28, + "learning_rate": 1.8022081860093493e-05, + "loss": 1.6411, + "step": 2701 + }, + { + "epoch": 0.28, + "learning_rate": 1.8019895990913213e-05, + "loss": 1.4459, + "step": 2702 + }, + { + "epoch": 0.28, + "learning_rate": 1.8017709047272932e-05, + "loss": 1.4418, + "step": 2703 + }, + { + "epoch": 0.28, + "learning_rate": 1.801552102946565e-05, + "loss": 1.4409, + "step": 2704 + }, + { + "epoch": 0.28, + "learning_rate": 1.8013331937784498e-05, + "loss": 1.4651, + "step": 2705 + }, + { + "epoch": 0.28, + "learning_rate": 1.8011141772522766e-05, + "loss": 1.4161, + "step": 2706 + }, + { + "epoch": 0.28, + "learning_rate": 1.8008950533973876e-05, + "loss": 1.458, + "step": 2707 + }, + { + "epoch": 0.28, + "learning_rate": 1.8006758222431398e-05, + "loss": 1.4477, + "step": 2708 + }, + { + "epoch": 0.28, + "learning_rate": 1.800456483818904e-05, + "loss": 1.4433, + "step": 2709 + }, + { + "epoch": 0.28, + "learning_rate": 1.8002370381540672e-05, + "loss": 1.5005, + "step": 2710 + }, + { + "epoch": 0.28, + "learning_rate": 1.8000174852780282e-05, + "loss": 1.4945, + "step": 2711 + }, + { + "epoch": 0.28, + "learning_rate": 1.7997978252202023e-05, + "loss": 1.4298, + "step": 2712 + }, + { + "epoch": 0.28, + "learning_rate": 1.7995780580100177e-05, + "loss": 1.3812, + "step": 2713 + }, + { + "epoch": 0.28, + "learning_rate": 1.799358183676918e-05, + "loss": 1.5559, + "step": 2714 + }, + { + "epoch": 0.28, + "learning_rate": 1.79913820225036e-05, + "loss": 1.4316, + "step": 2715 + }, + { + "epoch": 0.28, + "learning_rate": 1.798918113759817e-05, + "loss": 1.419, + "step": 2716 + }, + { + "epoch": 0.28, + "learning_rate": 1.7986979182347733e-05, + "loss": 1.43, + "step": 2717 + }, + { + "epoch": 0.29, + "learning_rate": 1.798477615704731e-05, + "loss": 1.4964, + "step": 2718 + }, + { + "epoch": 0.29, + "learning_rate": 1.7982572061992044e-05, + "loss": 1.4417, + "step": 2719 + }, + { + "epoch": 0.29, + "learning_rate": 1.7980366897477227e-05, + "loss": 1.4562, + "step": 2720 + }, + { + "epoch": 0.29, + "learning_rate": 1.7978160663798295e-05, + "loss": 1.4386, + "step": 2721 + }, + { + "epoch": 0.29, + "learning_rate": 1.7975953361250824e-05, + "loss": 1.445, + "step": 2722 + }, + { + "epoch": 0.29, + "learning_rate": 1.797374499013054e-05, + "loss": 1.4549, + "step": 2723 + }, + { + "epoch": 0.29, + "learning_rate": 1.7971535550733305e-05, + "loss": 1.5205, + "step": 2724 + }, + { + "epoch": 0.29, + "learning_rate": 1.796932504335513e-05, + "loss": 1.4632, + "step": 2725 + }, + { + "epoch": 0.29, + "learning_rate": 1.796711346829216e-05, + "loss": 1.3767, + "step": 2726 + }, + { + "epoch": 0.29, + "learning_rate": 1.79649008258407e-05, + "loss": 1.4098, + "step": 2727 + }, + { + "epoch": 0.29, + "learning_rate": 1.7962687116297178e-05, + "loss": 1.4675, + "step": 2728 + }, + { + "epoch": 0.29, + "learning_rate": 1.7960472339958176e-05, + "loss": 1.6048, + "step": 2729 + }, + { + "epoch": 0.29, + "learning_rate": 1.7958256497120418e-05, + "loss": 1.5432, + "step": 2730 + }, + { + "epoch": 0.29, + "learning_rate": 1.7956039588080774e-05, + "loss": 1.5453, + "step": 2731 + }, + { + "epoch": 0.29, + "learning_rate": 1.7953821613136246e-05, + "loss": 1.4246, + "step": 2732 + }, + { + "epoch": 0.29, + "learning_rate": 1.7951602572583988e-05, + "loss": 1.3987, + "step": 2733 + }, + { + "epoch": 0.29, + "learning_rate": 1.7949382466721295e-05, + "loss": 1.4943, + "step": 2734 + }, + { + "epoch": 0.29, + "learning_rate": 1.7947161295845606e-05, + "loss": 1.4385, + "step": 2735 + }, + { + "epoch": 0.29, + "learning_rate": 1.7944939060254497e-05, + "loss": 1.4165, + "step": 2736 + }, + { + "epoch": 0.29, + "learning_rate": 1.7942715760245692e-05, + "loss": 1.4004, + "step": 2737 + }, + { + "epoch": 0.29, + "learning_rate": 1.7940491396117063e-05, + "loss": 1.4577, + "step": 2738 + }, + { + "epoch": 0.29, + "learning_rate": 1.7938265968166602e-05, + "loss": 1.4649, + "step": 2739 + }, + { + "epoch": 0.29, + "learning_rate": 1.7936039476692473e-05, + "loss": 1.5273, + "step": 2740 + }, + { + "epoch": 0.29, + "learning_rate": 1.7933811921992962e-05, + "loss": 1.4325, + "step": 2741 + }, + { + "epoch": 0.29, + "learning_rate": 1.793158330436651e-05, + "loss": 1.4388, + "step": 2742 + }, + { + "epoch": 0.29, + "learning_rate": 1.7929353624111687e-05, + "loss": 1.4124, + "step": 2743 + }, + { + "epoch": 0.29, + "learning_rate": 1.7927122881527222e-05, + "loss": 1.5449, + "step": 2744 + }, + { + "epoch": 0.29, + "learning_rate": 1.7924891076911964e-05, + "loss": 1.4728, + "step": 2745 + }, + { + "epoch": 0.29, + "learning_rate": 1.7922658210564932e-05, + "loss": 1.5103, + "step": 2746 + }, + { + "epoch": 0.29, + "learning_rate": 1.792042428278526e-05, + "loss": 1.5975, + "step": 2747 + }, + { + "epoch": 0.29, + "learning_rate": 1.7918189293872247e-05, + "loss": 1.567, + "step": 2748 + }, + { + "epoch": 0.29, + "learning_rate": 1.7915953244125318e-05, + "loss": 1.57, + "step": 2749 + }, + { + "epoch": 0.29, + "learning_rate": 1.791371613384405e-05, + "loss": 1.4372, + "step": 2750 + }, + { + "epoch": 0.29, + "learning_rate": 1.7911477963328155e-05, + "loss": 1.4053, + "step": 2751 + }, + { + "epoch": 0.29, + "learning_rate": 1.7909238732877492e-05, + "loss": 1.3782, + "step": 2752 + }, + { + "epoch": 0.29, + "learning_rate": 1.790699844279206e-05, + "loss": 1.4401, + "step": 2753 + }, + { + "epoch": 0.29, + "learning_rate": 1.7904757093372e-05, + "loss": 1.3749, + "step": 2754 + }, + { + "epoch": 0.29, + "learning_rate": 1.79025146849176e-05, + "loss": 1.4909, + "step": 2755 + }, + { + "epoch": 0.29, + "learning_rate": 1.7900271217729273e-05, + "loss": 1.4103, + "step": 2756 + }, + { + "epoch": 0.29, + "learning_rate": 1.7898026692107597e-05, + "loss": 1.4986, + "step": 2757 + }, + { + "epoch": 0.29, + "learning_rate": 1.7895781108353278e-05, + "loss": 1.5449, + "step": 2758 + }, + { + "epoch": 0.29, + "learning_rate": 1.789353446676717e-05, + "loss": 1.5583, + "step": 2759 + }, + { + "epoch": 0.29, + "learning_rate": 1.7891286767650254e-05, + "loss": 1.5342, + "step": 2760 + }, + { + "epoch": 0.29, + "learning_rate": 1.7889038011303673e-05, + "loss": 1.4233, + "step": 2761 + }, + { + "epoch": 0.29, + "learning_rate": 1.7886788198028707e-05, + "loss": 1.3433, + "step": 2762 + }, + { + "epoch": 0.29, + "learning_rate": 1.788453732812676e-05, + "loss": 1.4451, + "step": 2763 + }, + { + "epoch": 0.29, + "learning_rate": 1.78822854018994e-05, + "loss": 1.4506, + "step": 2764 + }, + { + "epoch": 0.29, + "learning_rate": 1.7880032419648324e-05, + "loss": 1.4386, + "step": 2765 + }, + { + "epoch": 0.29, + "learning_rate": 1.7877778381675374e-05, + "loss": 1.4512, + "step": 2766 + }, + { + "epoch": 0.29, + "learning_rate": 1.7875523288282535e-05, + "loss": 1.4319, + "step": 2767 + }, + { + "epoch": 0.29, + "learning_rate": 1.7873267139771932e-05, + "loss": 1.4753, + "step": 2768 + }, + { + "epoch": 0.29, + "learning_rate": 1.787100993644583e-05, + "loss": 1.4044, + "step": 2769 + }, + { + "epoch": 0.29, + "learning_rate": 1.786875167860663e-05, + "loss": 1.4382, + "step": 2770 + }, + { + "epoch": 0.29, + "learning_rate": 1.786649236655689e-05, + "loss": 1.3977, + "step": 2771 + }, + { + "epoch": 0.29, + "learning_rate": 1.7864232000599298e-05, + "loss": 1.4473, + "step": 2772 + }, + { + "epoch": 0.29, + "learning_rate": 1.7861970581036678e-05, + "loss": 1.4666, + "step": 2773 + }, + { + "epoch": 0.29, + "learning_rate": 1.785970810817201e-05, + "loss": 1.5299, + "step": 2774 + }, + { + "epoch": 0.29, + "learning_rate": 1.7857444582308402e-05, + "loss": 1.3974, + "step": 2775 + }, + { + "epoch": 0.29, + "learning_rate": 1.7855180003749114e-05, + "loss": 1.4603, + "step": 2776 + }, + { + "epoch": 0.29, + "learning_rate": 1.7852914372797535e-05, + "loss": 1.463, + "step": 2777 + }, + { + "epoch": 0.29, + "learning_rate": 1.7850647689757205e-05, + "loss": 1.5317, + "step": 2778 + }, + { + "epoch": 0.29, + "learning_rate": 1.78483799549318e-05, + "loss": 1.4669, + "step": 2779 + }, + { + "epoch": 0.29, + "learning_rate": 1.784611116862514e-05, + "loss": 1.5293, + "step": 2780 + }, + { + "epoch": 0.29, + "learning_rate": 1.7843841331141177e-05, + "loss": 1.5802, + "step": 2781 + }, + { + "epoch": 0.29, + "learning_rate": 1.7841570442784024e-05, + "loss": 1.4486, + "step": 2782 + }, + { + "epoch": 0.29, + "learning_rate": 1.7839298503857913e-05, + "loss": 1.4674, + "step": 2783 + }, + { + "epoch": 0.29, + "learning_rate": 1.7837025514667224e-05, + "loss": 1.4662, + "step": 2784 + }, + { + "epoch": 0.29, + "learning_rate": 1.7834751475516484e-05, + "loss": 1.3555, + "step": 2785 + }, + { + "epoch": 0.29, + "learning_rate": 1.783247638671035e-05, + "loss": 1.4307, + "step": 2786 + }, + { + "epoch": 0.29, + "eval_loss": 1.500258445739746, + "eval_runtime": 77.406, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 2786 + }, + { + "epoch": 0.29, + "learning_rate": 1.7830200248553633e-05, + "loss": 1.4596, + "step": 2787 + }, + { + "epoch": 0.29, + "learning_rate": 1.7827923061351273e-05, + "loss": 1.6118, + "step": 2788 + }, + { + "epoch": 0.29, + "learning_rate": 1.7825644825408353e-05, + "loss": 1.4782, + "step": 2789 + }, + { + "epoch": 0.29, + "learning_rate": 1.78233655410301e-05, + "loss": 1.4681, + "step": 2790 + }, + { + "epoch": 0.29, + "learning_rate": 1.782108520852188e-05, + "loss": 1.6281, + "step": 2791 + }, + { + "epoch": 0.29, + "learning_rate": 1.78188038281892e-05, + "loss": 1.4446, + "step": 2792 + }, + { + "epoch": 0.29, + "learning_rate": 1.7816521400337704e-05, + "loss": 1.479, + "step": 2793 + }, + { + "epoch": 0.29, + "learning_rate": 1.7814237925273178e-05, + "loss": 1.5457, + "step": 2794 + }, + { + "epoch": 0.29, + "learning_rate": 1.7811953403301547e-05, + "loss": 1.3928, + "step": 2795 + }, + { + "epoch": 0.29, + "learning_rate": 1.780966783472889e-05, + "loss": 1.4321, + "step": 2796 + }, + { + "epoch": 0.29, + "learning_rate": 1.78073812198614e-05, + "loss": 1.5734, + "step": 2797 + }, + { + "epoch": 0.29, + "learning_rate": 1.7805093559005432e-05, + "loss": 1.4356, + "step": 2798 + }, + { + "epoch": 0.29, + "learning_rate": 1.7802804852467473e-05, + "loss": 1.4656, + "step": 2799 + }, + { + "epoch": 0.29, + "learning_rate": 1.780051510055415e-05, + "loss": 1.4052, + "step": 2800 + }, + { + "epoch": 0.29, + "learning_rate": 1.7798224303572228e-05, + "loss": 1.4758, + "step": 2801 + }, + { + "epoch": 0.29, + "learning_rate": 1.7795932461828622e-05, + "loss": 1.4326, + "step": 2802 + }, + { + "epoch": 0.29, + "learning_rate": 1.7793639575630376e-05, + "loss": 1.3409, + "step": 2803 + }, + { + "epoch": 0.29, + "learning_rate": 1.7791345645284678e-05, + "loss": 1.4175, + "step": 2804 + }, + { + "epoch": 0.29, + "learning_rate": 1.7789050671098853e-05, + "loss": 1.383, + "step": 2805 + }, + { + "epoch": 0.29, + "learning_rate": 1.7786754653380373e-05, + "loss": 1.5162, + "step": 2806 + }, + { + "epoch": 0.29, + "learning_rate": 1.7784457592436847e-05, + "loss": 1.4899, + "step": 2807 + }, + { + "epoch": 0.29, + "learning_rate": 1.7782159488576016e-05, + "loss": 1.4874, + "step": 2808 + }, + { + "epoch": 0.29, + "learning_rate": 1.777986034210577e-05, + "loss": 1.4363, + "step": 2809 + }, + { + "epoch": 0.29, + "learning_rate": 1.7777560153334134e-05, + "loss": 1.4223, + "step": 2810 + }, + { + "epoch": 0.29, + "learning_rate": 1.7775258922569273e-05, + "loss": 1.4792, + "step": 2811 + }, + { + "epoch": 0.29, + "learning_rate": 1.77729566501195e-05, + "loss": 1.4475, + "step": 2812 + }, + { + "epoch": 0.29, + "learning_rate": 1.7770653336293253e-05, + "loss": 1.5157, + "step": 2813 + }, + { + "epoch": 0.3, + "learning_rate": 1.776834898139912e-05, + "loss": 1.389, + "step": 2814 + }, + { + "epoch": 0.3, + "learning_rate": 1.7766043585745824e-05, + "loss": 1.4358, + "step": 2815 + }, + { + "epoch": 0.3, + "learning_rate": 1.776373714964223e-05, + "loss": 1.4297, + "step": 2816 + }, + { + "epoch": 0.3, + "learning_rate": 1.7761429673397344e-05, + "loss": 1.4102, + "step": 2817 + }, + { + "epoch": 0.3, + "learning_rate": 1.77591211573203e-05, + "loss": 1.4572, + "step": 2818 + }, + { + "epoch": 0.3, + "learning_rate": 1.775681160172039e-05, + "loss": 1.448, + "step": 2819 + }, + { + "epoch": 0.3, + "learning_rate": 1.7754501006907025e-05, + "loss": 1.4426, + "step": 2820 + }, + { + "epoch": 0.3, + "learning_rate": 1.7752189373189773e-05, + "loss": 1.4566, + "step": 2821 + }, + { + "epoch": 0.3, + "learning_rate": 1.7749876700878332e-05, + "loss": 1.4267, + "step": 2822 + }, + { + "epoch": 0.3, + "learning_rate": 1.7747562990282538e-05, + "loss": 1.3951, + "step": 2823 + }, + { + "epoch": 0.3, + "learning_rate": 1.7745248241712373e-05, + "loss": 1.4668, + "step": 2824 + }, + { + "epoch": 0.3, + "learning_rate": 1.774293245547795e-05, + "loss": 1.4924, + "step": 2825 + }, + { + "epoch": 0.3, + "learning_rate": 1.7740615631889525e-05, + "loss": 1.5258, + "step": 2826 + }, + { + "epoch": 0.3, + "learning_rate": 1.7738297771257496e-05, + "loss": 1.4323, + "step": 2827 + }, + { + "epoch": 0.3, + "learning_rate": 1.7735978873892393e-05, + "loss": 1.439, + "step": 2828 + }, + { + "epoch": 0.3, + "learning_rate": 1.773365894010489e-05, + "loss": 1.5658, + "step": 2829 + }, + { + "epoch": 0.3, + "learning_rate": 1.77313379702058e-05, + "loss": 1.4607, + "step": 2830 + }, + { + "epoch": 0.3, + "learning_rate": 1.7729015964506073e-05, + "loss": 1.5544, + "step": 2831 + }, + { + "epoch": 0.3, + "learning_rate": 1.7726692923316798e-05, + "loss": 1.4232, + "step": 2832 + }, + { + "epoch": 0.3, + "learning_rate": 1.77243688469492e-05, + "loss": 1.415, + "step": 2833 + }, + { + "epoch": 0.3, + "learning_rate": 1.772204373571465e-05, + "loss": 1.4658, + "step": 2834 + }, + { + "epoch": 0.3, + "learning_rate": 1.7719717589924647e-05, + "loss": 1.4678, + "step": 2835 + }, + { + "epoch": 0.3, + "learning_rate": 1.771739040989084e-05, + "loss": 1.3021, + "step": 2836 + }, + { + "epoch": 0.3, + "learning_rate": 1.771506219592501e-05, + "loss": 1.4045, + "step": 2837 + }, + { + "epoch": 0.3, + "learning_rate": 1.7712732948339085e-05, + "loss": 1.4593, + "step": 2838 + }, + { + "epoch": 0.3, + "learning_rate": 1.7710402667445108e-05, + "loss": 1.4175, + "step": 2839 + }, + { + "epoch": 0.3, + "learning_rate": 1.770807135355529e-05, + "loss": 1.3939, + "step": 2840 + }, + { + "epoch": 0.3, + "learning_rate": 1.7705739006981963e-05, + "loss": 1.6089, + "step": 2841 + }, + { + "epoch": 0.3, + "learning_rate": 1.77034056280376e-05, + "loss": 1.3952, + "step": 2842 + }, + { + "epoch": 0.3, + "learning_rate": 1.7701071217034818e-05, + "loss": 1.5086, + "step": 2843 + }, + { + "epoch": 0.3, + "learning_rate": 1.7698735774286362e-05, + "loss": 1.4706, + "step": 2844 + }, + { + "epoch": 0.3, + "learning_rate": 1.7696399300105128e-05, + "loss": 1.4286, + "step": 2845 + }, + { + "epoch": 0.3, + "learning_rate": 1.7694061794804137e-05, + "loss": 1.4418, + "step": 2846 + }, + { + "epoch": 0.3, + "learning_rate": 1.7691723258696562e-05, + "loss": 1.516, + "step": 2847 + }, + { + "epoch": 0.3, + "learning_rate": 1.76893836920957e-05, + "loss": 1.4354, + "step": 2848 + }, + { + "epoch": 0.3, + "learning_rate": 1.7687043095314998e-05, + "loss": 1.7503, + "step": 2849 + }, + { + "epoch": 0.3, + "learning_rate": 1.7684701468668032e-05, + "loss": 1.5985, + "step": 2850 + }, + { + "epoch": 0.3, + "learning_rate": 1.768235881246852e-05, + "loss": 1.442, + "step": 2851 + }, + { + "epoch": 0.3, + "learning_rate": 1.7680015127030322e-05, + "loss": 1.4924, + "step": 2852 + }, + { + "epoch": 0.3, + "learning_rate": 1.7677670412667425e-05, + "loss": 1.4461, + "step": 2853 + }, + { + "epoch": 0.3, + "learning_rate": 1.7675324669693968e-05, + "loss": 1.3823, + "step": 2854 + }, + { + "epoch": 0.3, + "learning_rate": 1.767297789842421e-05, + "loss": 1.452, + "step": 2855 + }, + { + "epoch": 0.3, + "learning_rate": 1.767063009917257e-05, + "loss": 1.46, + "step": 2856 + }, + { + "epoch": 0.3, + "learning_rate": 1.7668281272253587e-05, + "loss": 1.4129, + "step": 2857 + }, + { + "epoch": 0.3, + "learning_rate": 1.766593141798194e-05, + "loss": 1.4057, + "step": 2858 + }, + { + "epoch": 0.3, + "learning_rate": 1.7663580536672456e-05, + "loss": 1.5162, + "step": 2859 + }, + { + "epoch": 0.3, + "learning_rate": 1.7661228628640087e-05, + "loss": 1.5177, + "step": 2860 + }, + { + "epoch": 0.3, + "learning_rate": 1.7658875694199933e-05, + "loss": 1.4548, + "step": 2861 + }, + { + "epoch": 0.3, + "learning_rate": 1.7656521733667223e-05, + "loss": 1.4511, + "step": 2862 + }, + { + "epoch": 0.3, + "learning_rate": 1.765416674735733e-05, + "loss": 1.4778, + "step": 2863 + }, + { + "epoch": 0.3, + "learning_rate": 1.765181073558576e-05, + "loss": 1.3935, + "step": 2864 + }, + { + "epoch": 0.3, + "learning_rate": 1.7649453698668156e-05, + "loss": 1.4659, + "step": 2865 + }, + { + "epoch": 0.3, + "learning_rate": 1.7647095636920305e-05, + "loss": 1.7042, + "step": 2866 + }, + { + "epoch": 0.3, + "learning_rate": 1.7644736550658124e-05, + "loss": 1.7957, + "step": 2867 + }, + { + "epoch": 0.3, + "learning_rate": 1.764237644019767e-05, + "loss": 1.5139, + "step": 2868 + }, + { + "epoch": 0.3, + "learning_rate": 1.764001530585514e-05, + "loss": 1.4117, + "step": 2869 + }, + { + "epoch": 0.3, + "learning_rate": 1.7637653147946858e-05, + "loss": 1.4837, + "step": 2870 + }, + { + "epoch": 0.3, + "learning_rate": 1.7635289966789298e-05, + "loss": 1.4379, + "step": 2871 + }, + { + "epoch": 0.3, + "learning_rate": 1.7632925762699068e-05, + "loss": 1.4491, + "step": 2872 + }, + { + "epoch": 0.3, + "learning_rate": 1.7630560535992905e-05, + "loss": 1.4006, + "step": 2873 + }, + { + "epoch": 0.3, + "learning_rate": 1.7628194286987694e-05, + "loss": 1.5484, + "step": 2874 + }, + { + "epoch": 0.3, + "learning_rate": 1.7625827016000446e-05, + "loss": 1.4926, + "step": 2875 + }, + { + "epoch": 0.3, + "learning_rate": 1.762345872334832e-05, + "loss": 1.3909, + "step": 2876 + }, + { + "epoch": 0.3, + "learning_rate": 1.76210894093486e-05, + "loss": 1.405, + "step": 2877 + }, + { + "epoch": 0.3, + "learning_rate": 1.7618719074318718e-05, + "loss": 1.4736, + "step": 2878 + }, + { + "epoch": 0.3, + "learning_rate": 1.7616347718576238e-05, + "loss": 1.4445, + "step": 2879 + }, + { + "epoch": 0.3, + "learning_rate": 1.761397534243886e-05, + "loss": 1.4878, + "step": 2880 + }, + { + "epoch": 0.3, + "learning_rate": 1.7611601946224417e-05, + "loss": 1.4414, + "step": 2881 + }, + { + "epoch": 0.3, + "learning_rate": 1.760922753025089e-05, + "loss": 1.5657, + "step": 2882 + }, + { + "epoch": 0.3, + "learning_rate": 1.7606852094836385e-05, + "loss": 1.5008, + "step": 2883 + }, + { + "epoch": 0.3, + "learning_rate": 1.7604475640299153e-05, + "loss": 1.4922, + "step": 2884 + }, + { + "epoch": 0.3, + "learning_rate": 1.7602098166957577e-05, + "loss": 1.7451, + "step": 2885 + }, + { + "epoch": 0.3, + "learning_rate": 1.759971967513017e-05, + "loss": 1.7077, + "step": 2886 + }, + { + "epoch": 0.3, + "learning_rate": 1.75973401651356e-05, + "loss": 1.3986, + "step": 2887 + }, + { + "epoch": 0.3, + "learning_rate": 1.7594959637292656e-05, + "loss": 1.3966, + "step": 2888 + }, + { + "epoch": 0.3, + "learning_rate": 1.7592578091920264e-05, + "loss": 1.4086, + "step": 2889 + }, + { + "epoch": 0.3, + "learning_rate": 1.7590195529337495e-05, + "loss": 1.4481, + "step": 2890 + }, + { + "epoch": 0.3, + "learning_rate": 1.7587811949863548e-05, + "loss": 1.3974, + "step": 2891 + }, + { + "epoch": 0.3, + "learning_rate": 1.7585427353817758e-05, + "loss": 1.5013, + "step": 2892 + }, + { + "epoch": 0.3, + "learning_rate": 1.7583041741519608e-05, + "loss": 1.5454, + "step": 2893 + }, + { + "epoch": 0.3, + "learning_rate": 1.7580655113288708e-05, + "loss": 1.5033, + "step": 2894 + }, + { + "epoch": 0.3, + "learning_rate": 1.7578267469444793e-05, + "loss": 1.4332, + "step": 2895 + }, + { + "epoch": 0.3, + "learning_rate": 1.757587881030776e-05, + "loss": 1.4667, + "step": 2896 + }, + { + "epoch": 0.3, + "learning_rate": 1.7573489136197623e-05, + "loss": 1.4314, + "step": 2897 + }, + { + "epoch": 0.3, + "learning_rate": 1.7571098447434532e-05, + "loss": 1.4514, + "step": 2898 + }, + { + "epoch": 0.3, + "learning_rate": 1.7568706744338784e-05, + "loss": 1.4872, + "step": 2899 + }, + { + "epoch": 0.3, + "learning_rate": 1.7566314027230808e-05, + "loss": 1.4841, + "step": 2900 + }, + { + "epoch": 0.3, + "learning_rate": 1.7563920296431158e-05, + "loss": 1.3964, + "step": 2901 + }, + { + "epoch": 0.3, + "learning_rate": 1.7561525552260538e-05, + "loss": 1.4932, + "step": 2902 + }, + { + "epoch": 0.3, + "learning_rate": 1.755912979503978e-05, + "loss": 1.4153, + "step": 2903 + }, + { + "epoch": 0.3, + "learning_rate": 1.755673302508986e-05, + "loss": 1.4939, + "step": 2904 + }, + { + "epoch": 0.3, + "learning_rate": 1.755433524273187e-05, + "loss": 1.4437, + "step": 2905 + }, + { + "epoch": 0.3, + "learning_rate": 1.7551936448287067e-05, + "loss": 1.486, + "step": 2906 + }, + { + "epoch": 0.3, + "learning_rate": 1.754953664207682e-05, + "loss": 1.4362, + "step": 2907 + }, + { + "epoch": 0.3, + "learning_rate": 1.7547135824422635e-05, + "loss": 1.4954, + "step": 2908 + }, + { + "epoch": 0.31, + "learning_rate": 1.7544733995646174e-05, + "loss": 1.4552, + "step": 2909 + }, + { + "epoch": 0.31, + "learning_rate": 1.7542331156069213e-05, + "loss": 1.4654, + "step": 2910 + }, + { + "epoch": 0.31, + "learning_rate": 1.753992730601367e-05, + "loss": 1.4531, + "step": 2911 + }, + { + "epoch": 0.31, + "learning_rate": 1.75375224458016e-05, + "loss": 1.4949, + "step": 2912 + }, + { + "epoch": 0.31, + "learning_rate": 1.753511657575519e-05, + "loss": 1.3998, + "step": 2913 + }, + { + "epoch": 0.31, + "learning_rate": 1.753270969619677e-05, + "loss": 1.3904, + "step": 2914 + }, + { + "epoch": 0.31, + "learning_rate": 1.7530301807448794e-05, + "loss": 1.481, + "step": 2915 + }, + { + "epoch": 0.31, + "learning_rate": 1.7527892909833864e-05, + "loss": 1.4301, + "step": 2916 + }, + { + "epoch": 0.31, + "learning_rate": 1.7525483003674707e-05, + "loss": 1.4377, + "step": 2917 + }, + { + "epoch": 0.31, + "learning_rate": 1.7523072089294188e-05, + "loss": 1.5077, + "step": 2918 + }, + { + "epoch": 0.31, + "learning_rate": 1.752066016701531e-05, + "loss": 1.3802, + "step": 2919 + }, + { + "epoch": 0.31, + "learning_rate": 1.7518247237161205e-05, + "loss": 1.3991, + "step": 2920 + }, + { + "epoch": 0.31, + "learning_rate": 1.7515833300055146e-05, + "loss": 1.4283, + "step": 2921 + }, + { + "epoch": 0.31, + "learning_rate": 1.7513418356020535e-05, + "loss": 1.3688, + "step": 2922 + }, + { + "epoch": 0.31, + "learning_rate": 1.751100240538092e-05, + "loss": 1.4336, + "step": 2923 + }, + { + "epoch": 0.31, + "learning_rate": 1.7508585448459967e-05, + "loss": 1.4302, + "step": 2924 + }, + { + "epoch": 0.31, + "learning_rate": 1.7506167485581493e-05, + "loss": 1.4293, + "step": 2925 + }, + { + "epoch": 0.31, + "learning_rate": 1.750374851706944e-05, + "loss": 1.4262, + "step": 2926 + }, + { + "epoch": 0.31, + "learning_rate": 1.7501328543247892e-05, + "loss": 1.4128, + "step": 2927 + }, + { + "epoch": 0.31, + "learning_rate": 1.7498907564441054e-05, + "loss": 1.4258, + "step": 2928 + }, + { + "epoch": 0.31, + "learning_rate": 1.749648558097328e-05, + "loss": 1.4904, + "step": 2929 + }, + { + "epoch": 0.31, + "learning_rate": 1.749406259316906e-05, + "loss": 1.4628, + "step": 2930 + }, + { + "epoch": 0.31, + "learning_rate": 1.7491638601353004e-05, + "loss": 1.4908, + "step": 2931 + }, + { + "epoch": 0.31, + "learning_rate": 1.7489213605849867e-05, + "loss": 1.4563, + "step": 2932 + }, + { + "epoch": 0.31, + "learning_rate": 1.7486787606984533e-05, + "loss": 1.5006, + "step": 2933 + }, + { + "epoch": 0.31, + "learning_rate": 1.748436060508203e-05, + "loss": 1.424, + "step": 2934 + }, + { + "epoch": 0.31, + "learning_rate": 1.7481932600467508e-05, + "loss": 1.4136, + "step": 2935 + }, + { + "epoch": 0.31, + "learning_rate": 1.747950359346626e-05, + "loss": 1.3835, + "step": 2936 + }, + { + "epoch": 0.31, + "learning_rate": 1.747707358440371e-05, + "loss": 1.5284, + "step": 2937 + }, + { + "epoch": 0.31, + "learning_rate": 1.7474642573605418e-05, + "loss": 1.4592, + "step": 2938 + }, + { + "epoch": 0.31, + "learning_rate": 1.7472210561397075e-05, + "loss": 1.5483, + "step": 2939 + }, + { + "epoch": 0.31, + "learning_rate": 1.746977754810451e-05, + "loss": 1.521, + "step": 2940 + }, + { + "epoch": 0.31, + "learning_rate": 1.7467343534053683e-05, + "loss": 1.4276, + "step": 2941 + }, + { + "epoch": 0.31, + "learning_rate": 1.746490851957069e-05, + "loss": 1.4302, + "step": 2942 + }, + { + "epoch": 0.31, + "learning_rate": 1.746247250498176e-05, + "loss": 1.4439, + "step": 2943 + }, + { + "epoch": 0.31, + "learning_rate": 1.7460035490613255e-05, + "loss": 1.4991, + "step": 2944 + }, + { + "epoch": 0.31, + "learning_rate": 1.7457597476791674e-05, + "loss": 1.4188, + "step": 2945 + }, + { + "epoch": 0.31, + "learning_rate": 1.7455158463843648e-05, + "loss": 1.4685, + "step": 2946 + }, + { + "epoch": 0.31, + "learning_rate": 1.745271845209594e-05, + "loss": 1.3811, + "step": 2947 + }, + { + "epoch": 0.31, + "learning_rate": 1.7450277441875454e-05, + "loss": 1.4869, + "step": 2948 + }, + { + "epoch": 0.31, + "learning_rate": 1.7447835433509218e-05, + "loss": 1.5001, + "step": 2949 + }, + { + "epoch": 0.31, + "learning_rate": 1.74453924273244e-05, + "loss": 1.4757, + "step": 2950 + }, + { + "epoch": 0.31, + "learning_rate": 1.74429484236483e-05, + "loss": 1.5072, + "step": 2951 + }, + { + "epoch": 0.31, + "learning_rate": 1.744050342280835e-05, + "loss": 1.4242, + "step": 2952 + }, + { + "epoch": 0.31, + "learning_rate": 1.743805742513212e-05, + "loss": 1.4462, + "step": 2953 + }, + { + "epoch": 0.31, + "learning_rate": 1.743561043094731e-05, + "loss": 1.6815, + "step": 2954 + }, + { + "epoch": 0.31, + "learning_rate": 1.7433162440581755e-05, + "loss": 1.427, + "step": 2955 + }, + { + "epoch": 0.31, + "learning_rate": 1.7430713454363423e-05, + "loss": 1.2933, + "step": 2956 + }, + { + "epoch": 0.31, + "learning_rate": 1.742826347262041e-05, + "loss": 1.4247, + "step": 2957 + }, + { + "epoch": 0.31, + "learning_rate": 1.7425812495680955e-05, + "loss": 1.399, + "step": 2958 + }, + { + "epoch": 0.31, + "learning_rate": 1.742336052387343e-05, + "loss": 1.4818, + "step": 2959 + }, + { + "epoch": 0.31, + "learning_rate": 1.742090755752633e-05, + "loss": 1.3839, + "step": 2960 + }, + { + "epoch": 0.31, + "learning_rate": 1.741845359696829e-05, + "loss": 1.4669, + "step": 2961 + }, + { + "epoch": 0.31, + "learning_rate": 1.741599864252808e-05, + "loss": 1.468, + "step": 2962 + }, + { + "epoch": 0.31, + "learning_rate": 1.74135426945346e-05, + "loss": 1.4135, + "step": 2963 + }, + { + "epoch": 0.31, + "learning_rate": 1.7411085753316882e-05, + "loss": 1.5899, + "step": 2964 + }, + { + "epoch": 0.31, + "learning_rate": 1.74086278192041e-05, + "loss": 1.6115, + "step": 2965 + }, + { + "epoch": 0.31, + "learning_rate": 1.740616889252554e-05, + "loss": 1.3988, + "step": 2966 + }, + { + "epoch": 0.31, + "learning_rate": 1.740370897361065e-05, + "loss": 1.5001, + "step": 2967 + }, + { + "epoch": 0.31, + "learning_rate": 1.740124806278899e-05, + "loss": 1.459, + "step": 2968 + }, + { + "epoch": 0.31, + "learning_rate": 1.7398786160390258e-05, + "loss": 1.4489, + "step": 2969 + }, + { + "epoch": 0.31, + "learning_rate": 1.7396323266744283e-05, + "loss": 1.4397, + "step": 2970 + }, + { + "epoch": 0.31, + "learning_rate": 1.7393859382181033e-05, + "loss": 1.4687, + "step": 2971 + }, + { + "epoch": 0.31, + "learning_rate": 1.7391394507030606e-05, + "loss": 1.4495, + "step": 2972 + }, + { + "epoch": 0.31, + "learning_rate": 1.738892864162323e-05, + "loss": 1.4745, + "step": 2973 + }, + { + "epoch": 0.31, + "learning_rate": 1.7386461786289274e-05, + "loss": 1.3943, + "step": 2974 + }, + { + "epoch": 0.31, + "learning_rate": 1.738399394135922e-05, + "loss": 1.4595, + "step": 2975 + }, + { + "epoch": 0.31, + "learning_rate": 1.738152510716371e-05, + "loss": 1.4023, + "step": 2976 + }, + { + "epoch": 0.31, + "learning_rate": 1.7379055284033493e-05, + "loss": 1.3938, + "step": 2977 + }, + { + "epoch": 0.31, + "learning_rate": 1.7376584472299468e-05, + "loss": 1.4576, + "step": 2978 + }, + { + "epoch": 0.31, + "learning_rate": 1.737411267229266e-05, + "loss": 1.424, + "step": 2979 + }, + { + "epoch": 0.31, + "learning_rate": 1.7371639884344225e-05, + "loss": 1.4224, + "step": 2980 + }, + { + "epoch": 0.31, + "learning_rate": 1.736916610878545e-05, + "loss": 1.4228, + "step": 2981 + }, + { + "epoch": 0.31, + "learning_rate": 1.7366691345947768e-05, + "loss": 1.5021, + "step": 2982 + }, + { + "epoch": 0.31, + "learning_rate": 1.736421559616272e-05, + "loss": 1.3589, + "step": 2983 + }, + { + "epoch": 0.31, + "learning_rate": 1.7361738859762007e-05, + "loss": 1.4748, + "step": 2984 + }, + { + "epoch": 0.31, + "learning_rate": 1.735926113707743e-05, + "loss": 1.3974, + "step": 2985 + }, + { + "epoch": 0.31, + "eval_loss": 1.4849082231521606, + "eval_runtime": 77.3271, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2985 + }, + { + "epoch": 0.31, + "learning_rate": 1.735678242844096e-05, + "loss": 1.392, + "step": 2986 + }, + { + "epoch": 0.31, + "learning_rate": 1.735430273418467e-05, + "loss": 1.4277, + "step": 2987 + }, + { + "epoch": 0.31, + "learning_rate": 1.735182205464077e-05, + "loss": 1.4216, + "step": 2988 + }, + { + "epoch": 0.31, + "learning_rate": 1.7349340390141617e-05, + "loss": 1.4546, + "step": 2989 + }, + { + "epoch": 0.31, + "learning_rate": 1.734685774101969e-05, + "loss": 1.4264, + "step": 2990 + }, + { + "epoch": 0.31, + "learning_rate": 1.7344374107607593e-05, + "loss": 1.4307, + "step": 2991 + }, + { + "epoch": 0.31, + "learning_rate": 1.7341889490238076e-05, + "loss": 1.4266, + "step": 2992 + }, + { + "epoch": 0.31, + "learning_rate": 1.7339403889244008e-05, + "loss": 1.4486, + "step": 2993 + }, + { + "epoch": 0.31, + "learning_rate": 1.7336917304958403e-05, + "loss": 1.4345, + "step": 2994 + }, + { + "epoch": 0.31, + "learning_rate": 1.7334429737714395e-05, + "loss": 1.476, + "step": 2995 + }, + { + "epoch": 0.31, + "learning_rate": 1.7331941187845248e-05, + "loss": 1.5148, + "step": 2996 + }, + { + "epoch": 0.31, + "learning_rate": 1.7329451655684372e-05, + "loss": 1.4026, + "step": 2997 + }, + { + "epoch": 0.31, + "learning_rate": 1.7326961141565303e-05, + "loss": 1.3935, + "step": 2998 + }, + { + "epoch": 0.31, + "learning_rate": 1.73244696458217e-05, + "loss": 1.4483, + "step": 2999 + }, + { + "epoch": 0.31, + "learning_rate": 1.7321977168787356e-05, + "loss": 1.5197, + "step": 3000 + }, + { + "epoch": 0.31, + "learning_rate": 1.7319483710796208e-05, + "loss": 1.4648, + "step": 3001 + }, + { + "epoch": 0.31, + "learning_rate": 1.7316989272182308e-05, + "loss": 1.4171, + "step": 3002 + }, + { + "epoch": 0.31, + "learning_rate": 1.731449385327985e-05, + "loss": 1.4541, + "step": 3003 + }, + { + "epoch": 0.32, + "learning_rate": 1.731199745442316e-05, + "loss": 1.4605, + "step": 3004 + }, + { + "epoch": 0.32, + "learning_rate": 1.7309500075946683e-05, + "loss": 1.5122, + "step": 3005 + }, + { + "epoch": 0.32, + "learning_rate": 1.7307001718185007e-05, + "loss": 1.5243, + "step": 3006 + }, + { + "epoch": 0.32, + "learning_rate": 1.7304502381472844e-05, + "loss": 1.4997, + "step": 3007 + }, + { + "epoch": 0.32, + "learning_rate": 1.730200206614505e-05, + "loss": 1.4891, + "step": 3008 + }, + { + "epoch": 0.32, + "learning_rate": 1.72995007725366e-05, + "loss": 1.4376, + "step": 3009 + }, + { + "epoch": 0.32, + "learning_rate": 1.7296998500982595e-05, + "loss": 1.4403, + "step": 3010 + }, + { + "epoch": 0.32, + "learning_rate": 1.7294495251818285e-05, + "loss": 1.5153, + "step": 3011 + }, + { + "epoch": 0.32, + "learning_rate": 1.729199102537904e-05, + "loss": 1.4996, + "step": 3012 + }, + { + "epoch": 0.32, + "learning_rate": 1.7289485822000356e-05, + "loss": 1.5302, + "step": 3013 + }, + { + "epoch": 0.32, + "learning_rate": 1.7286979642017867e-05, + "loss": 1.5641, + "step": 3014 + }, + { + "epoch": 0.32, + "learning_rate": 1.728447248576734e-05, + "loss": 1.438, + "step": 3015 + }, + { + "epoch": 0.32, + "learning_rate": 1.7281964353584674e-05, + "loss": 1.4796, + "step": 3016 + }, + { + "epoch": 0.32, + "learning_rate": 1.727945524580588e-05, + "loss": 1.4413, + "step": 3017 + }, + { + "epoch": 0.32, + "learning_rate": 1.727694516276713e-05, + "loss": 1.3966, + "step": 3018 + }, + { + "epoch": 0.32, + "learning_rate": 1.72744341048047e-05, + "loss": 1.5267, + "step": 3019 + }, + { + "epoch": 0.32, + "learning_rate": 1.727192207225501e-05, + "loss": 1.4284, + "step": 3020 + }, + { + "epoch": 0.32, + "learning_rate": 1.726940906545461e-05, + "loss": 1.5137, + "step": 3021 + }, + { + "epoch": 0.32, + "learning_rate": 1.7266895084740173e-05, + "loss": 1.3966, + "step": 3022 + }, + { + "epoch": 0.32, + "learning_rate": 1.7264380130448514e-05, + "loss": 1.4156, + "step": 3023 + }, + { + "epoch": 0.32, + "learning_rate": 1.726186420291657e-05, + "loss": 1.4644, + "step": 3024 + }, + { + "epoch": 0.32, + "learning_rate": 1.725934730248141e-05, + "loss": 1.4768, + "step": 3025 + }, + { + "epoch": 0.32, + "learning_rate": 1.7256829429480233e-05, + "loss": 1.4428, + "step": 3026 + }, + { + "epoch": 0.32, + "learning_rate": 1.7254310584250373e-05, + "loss": 1.4495, + "step": 3027 + }, + { + "epoch": 0.32, + "learning_rate": 1.725179076712929e-05, + "loss": 1.3867, + "step": 3028 + }, + { + "epoch": 0.32, + "learning_rate": 1.7249269978454567e-05, + "loss": 1.5011, + "step": 3029 + }, + { + "epoch": 0.32, + "learning_rate": 1.7246748218563937e-05, + "loss": 1.3916, + "step": 3030 + }, + { + "epoch": 0.32, + "learning_rate": 1.7244225487795238e-05, + "loss": 1.4984, + "step": 3031 + }, + { + "epoch": 0.32, + "learning_rate": 1.7241701786486464e-05, + "loss": 1.5776, + "step": 3032 + }, + { + "epoch": 0.32, + "learning_rate": 1.7239177114975717e-05, + "loss": 1.5018, + "step": 3033 + }, + { + "epoch": 0.32, + "learning_rate": 1.7236651473601244e-05, + "loss": 1.5042, + "step": 3034 + }, + { + "epoch": 0.32, + "learning_rate": 1.723412486270141e-05, + "loss": 1.4636, + "step": 3035 + }, + { + "epoch": 0.32, + "learning_rate": 1.723159728261472e-05, + "loss": 1.5612, + "step": 3036 + }, + { + "epoch": 0.32, + "learning_rate": 1.7229068733679803e-05, + "loss": 1.4399, + "step": 3037 + }, + { + "epoch": 0.32, + "learning_rate": 1.7226539216235424e-05, + "loss": 1.5635, + "step": 3038 + }, + { + "epoch": 0.32, + "learning_rate": 1.7224008730620468e-05, + "loss": 1.4329, + "step": 3039 + }, + { + "epoch": 0.32, + "learning_rate": 1.7221477277173956e-05, + "loss": 1.4886, + "step": 3040 + }, + { + "epoch": 0.32, + "learning_rate": 1.721894485623504e-05, + "loss": 1.4741, + "step": 3041 + }, + { + "epoch": 0.32, + "learning_rate": 1.7216411468143e-05, + "loss": 1.4678, + "step": 3042 + }, + { + "epoch": 0.32, + "learning_rate": 1.721387711323724e-05, + "loss": 1.4758, + "step": 3043 + }, + { + "epoch": 0.32, + "learning_rate": 1.72113417918573e-05, + "loss": 1.441, + "step": 3044 + }, + { + "epoch": 0.32, + "learning_rate": 1.7208805504342855e-05, + "loss": 1.4328, + "step": 3045 + }, + { + "epoch": 0.32, + "learning_rate": 1.720626825103369e-05, + "loss": 1.4254, + "step": 3046 + }, + { + "epoch": 0.32, + "learning_rate": 1.7203730032269744e-05, + "loss": 1.4462, + "step": 3047 + }, + { + "epoch": 0.32, + "learning_rate": 1.7201190848391066e-05, + "loss": 1.4826, + "step": 3048 + }, + { + "epoch": 0.32, + "learning_rate": 1.719865069973784e-05, + "loss": 1.4215, + "step": 3049 + }, + { + "epoch": 0.32, + "learning_rate": 1.7196109586650385e-05, + "loss": 1.4291, + "step": 3050 + }, + { + "epoch": 0.32, + "learning_rate": 1.7193567509469146e-05, + "loss": 1.5005, + "step": 3051 + }, + { + "epoch": 0.32, + "learning_rate": 1.719102446853469e-05, + "loss": 1.4216, + "step": 3052 + }, + { + "epoch": 0.32, + "learning_rate": 1.7188480464187725e-05, + "loss": 1.4349, + "step": 3053 + }, + { + "epoch": 0.32, + "learning_rate": 1.718593549676908e-05, + "loss": 1.4784, + "step": 3054 + }, + { + "epoch": 0.32, + "learning_rate": 1.7183389566619714e-05, + "loss": 1.4325, + "step": 3055 + }, + { + "epoch": 0.32, + "learning_rate": 1.7180842674080717e-05, + "loss": 1.5387, + "step": 3056 + }, + { + "epoch": 0.32, + "learning_rate": 1.717829481949331e-05, + "loss": 1.655, + "step": 3057 + }, + { + "epoch": 0.32, + "learning_rate": 1.717574600319883e-05, + "loss": 1.4623, + "step": 3058 + }, + { + "epoch": 0.32, + "learning_rate": 1.7173196225538768e-05, + "loss": 1.4646, + "step": 3059 + }, + { + "epoch": 0.32, + "learning_rate": 1.717064548685472e-05, + "loss": 1.4641, + "step": 3060 + }, + { + "epoch": 0.32, + "learning_rate": 1.7168093787488418e-05, + "loss": 1.4033, + "step": 3061 + }, + { + "epoch": 0.32, + "learning_rate": 1.7165541127781726e-05, + "loss": 1.4085, + "step": 3062 + }, + { + "epoch": 0.32, + "learning_rate": 1.716298750807664e-05, + "loss": 1.387, + "step": 3063 + }, + { + "epoch": 0.32, + "learning_rate": 1.7160432928715272e-05, + "loss": 1.4197, + "step": 3064 + }, + { + "epoch": 0.32, + "learning_rate": 1.7157877390039872e-05, + "loss": 1.4883, + "step": 3065 + }, + { + "epoch": 0.32, + "learning_rate": 1.7155320892392818e-05, + "loss": 1.4865, + "step": 3066 + }, + { + "epoch": 0.32, + "learning_rate": 1.715276343611662e-05, + "loss": 1.4532, + "step": 3067 + }, + { + "epoch": 0.32, + "learning_rate": 1.71502050215539e-05, + "loss": 1.3991, + "step": 3068 + }, + { + "epoch": 0.32, + "learning_rate": 1.7147645649047424e-05, + "loss": 1.4318, + "step": 3069 + }, + { + "epoch": 0.32, + "learning_rate": 1.714508531894009e-05, + "loss": 1.3616, + "step": 3070 + }, + { + "epoch": 0.32, + "learning_rate": 1.7142524031574904e-05, + "loss": 1.4481, + "step": 3071 + }, + { + "epoch": 0.32, + "learning_rate": 1.7139961787295022e-05, + "loss": 1.3897, + "step": 3072 + }, + { + "epoch": 0.32, + "learning_rate": 1.7137398586443716e-05, + "loss": 1.3128, + "step": 3073 + }, + { + "epoch": 0.32, + "learning_rate": 1.713483442936439e-05, + "loss": 1.4481, + "step": 3074 + }, + { + "epoch": 0.32, + "learning_rate": 1.713226931640057e-05, + "loss": 1.5374, + "step": 3075 + }, + { + "epoch": 0.32, + "learning_rate": 1.7129703247895923e-05, + "loss": 1.4247, + "step": 3076 + }, + { + "epoch": 0.32, + "learning_rate": 1.712713622419423e-05, + "loss": 1.4098, + "step": 3077 + }, + { + "epoch": 0.32, + "learning_rate": 1.7124568245639414e-05, + "loss": 1.4558, + "step": 3078 + }, + { + "epoch": 0.32, + "learning_rate": 1.7121999312575507e-05, + "loss": 1.4484, + "step": 3079 + }, + { + "epoch": 0.32, + "learning_rate": 1.711942942534669e-05, + "loss": 1.4236, + "step": 3080 + }, + { + "epoch": 0.32, + "learning_rate": 1.7116858584297253e-05, + "loss": 1.613, + "step": 3081 + }, + { + "epoch": 0.32, + "learning_rate": 1.711428678977163e-05, + "loss": 1.4503, + "step": 3082 + }, + { + "epoch": 0.32, + "learning_rate": 1.7111714042114376e-05, + "loss": 1.4072, + "step": 3083 + }, + { + "epoch": 0.32, + "learning_rate": 1.7109140341670168e-05, + "loss": 1.5999, + "step": 3084 + }, + { + "epoch": 0.32, + "learning_rate": 1.7106565688783815e-05, + "loss": 1.4129, + "step": 3085 + }, + { + "epoch": 0.32, + "learning_rate": 1.710399008380026e-05, + "loss": 1.3973, + "step": 3086 + }, + { + "epoch": 0.32, + "learning_rate": 1.710141352706456e-05, + "loss": 1.4292, + "step": 3087 + }, + { + "epoch": 0.32, + "learning_rate": 1.709883601892192e-05, + "loss": 1.4372, + "step": 3088 + }, + { + "epoch": 0.32, + "learning_rate": 1.7096257559717647e-05, + "loss": 1.4924, + "step": 3089 + }, + { + "epoch": 0.32, + "learning_rate": 1.7093678149797196e-05, + "loss": 1.4222, + "step": 3090 + }, + { + "epoch": 0.32, + "learning_rate": 1.7091097789506137e-05, + "loss": 1.4797, + "step": 3091 + }, + { + "epoch": 0.32, + "learning_rate": 1.7088516479190175e-05, + "loss": 1.4738, + "step": 3092 + }, + { + "epoch": 0.32, + "learning_rate": 1.708593421919514e-05, + "loss": 1.5371, + "step": 3093 + }, + { + "epoch": 0.32, + "learning_rate": 1.7083351009866988e-05, + "loss": 1.3802, + "step": 3094 + }, + { + "epoch": 0.32, + "learning_rate": 1.7080766851551795e-05, + "loss": 1.4292, + "step": 3095 + }, + { + "epoch": 0.32, + "learning_rate": 1.707818174459578e-05, + "loss": 1.4478, + "step": 3096 + }, + { + "epoch": 0.32, + "learning_rate": 1.7075595689345285e-05, + "loss": 1.4619, + "step": 3097 + }, + { + "epoch": 0.32, + "learning_rate": 1.7073008686146763e-05, + "loss": 1.4603, + "step": 3098 + }, + { + "epoch": 0.32, + "learning_rate": 1.7070420735346815e-05, + "loss": 1.4548, + "step": 3099 + }, + { + "epoch": 0.33, + "learning_rate": 1.7067831837292157e-05, + "loss": 1.3638, + "step": 3100 + }, + { + "epoch": 0.33, + "learning_rate": 1.7065241992329634e-05, + "loss": 1.4284, + "step": 3101 + }, + { + "epoch": 0.33, + "learning_rate": 1.7062651200806217e-05, + "loss": 1.386, + "step": 3102 + }, + { + "epoch": 0.33, + "learning_rate": 1.7060059463069013e-05, + "loss": 1.5483, + "step": 3103 + }, + { + "epoch": 0.33, + "learning_rate": 1.705746677946524e-05, + "loss": 1.4963, + "step": 3104 + }, + { + "epoch": 0.33, + "learning_rate": 1.7054873150342257e-05, + "loss": 1.4539, + "step": 3105 + }, + { + "epoch": 0.33, + "learning_rate": 1.705227857604754e-05, + "loss": 1.4361, + "step": 3106 + }, + { + "epoch": 0.33, + "learning_rate": 1.7049683056928695e-05, + "loss": 1.3735, + "step": 3107 + }, + { + "epoch": 0.33, + "learning_rate": 1.7047086593333454e-05, + "loss": 1.4324, + "step": 3108 + }, + { + "epoch": 0.33, + "learning_rate": 1.7044489185609685e-05, + "loss": 1.5037, + "step": 3109 + }, + { + "epoch": 0.33, + "learning_rate": 1.704189083410536e-05, + "loss": 1.3913, + "step": 3110 + }, + { + "epoch": 0.33, + "learning_rate": 1.7039291539168604e-05, + "loss": 1.3233, + "step": 3111 + }, + { + "epoch": 0.33, + "learning_rate": 1.703669130114765e-05, + "loss": 1.4897, + "step": 3112 + }, + { + "epoch": 0.33, + "learning_rate": 1.7034090120390862e-05, + "loss": 1.4843, + "step": 3113 + }, + { + "epoch": 0.33, + "learning_rate": 1.7031487997246735e-05, + "loss": 1.3674, + "step": 3114 + }, + { + "epoch": 0.33, + "learning_rate": 1.7028884932063883e-05, + "loss": 1.4475, + "step": 3115 + }, + { + "epoch": 0.33, + "learning_rate": 1.702628092519105e-05, + "loss": 1.4134, + "step": 3116 + }, + { + "epoch": 0.33, + "learning_rate": 1.7023675976977108e-05, + "loss": 1.4484, + "step": 3117 + }, + { + "epoch": 0.33, + "learning_rate": 1.702107008777106e-05, + "loss": 1.407, + "step": 3118 + }, + { + "epoch": 0.33, + "learning_rate": 1.7018463257922005e-05, + "loss": 1.5443, + "step": 3119 + }, + { + "epoch": 0.33, + "learning_rate": 1.701585548777922e-05, + "loss": 1.4548, + "step": 3120 + }, + { + "epoch": 0.33, + "learning_rate": 1.7013246777692063e-05, + "loss": 1.4252, + "step": 3121 + }, + { + "epoch": 0.33, + "learning_rate": 1.7010637128010037e-05, + "loss": 1.3748, + "step": 3122 + }, + { + "epoch": 0.33, + "learning_rate": 1.7008026539082767e-05, + "loss": 1.3804, + "step": 3123 + }, + { + "epoch": 0.33, + "learning_rate": 1.7005415011260008e-05, + "loss": 1.4203, + "step": 3124 + }, + { + "epoch": 0.33, + "learning_rate": 1.7002802544891634e-05, + "loss": 1.4195, + "step": 3125 + }, + { + "epoch": 0.33, + "learning_rate": 1.700018914032765e-05, + "loss": 1.4188, + "step": 3126 + }, + { + "epoch": 0.33, + "learning_rate": 1.699757479791819e-05, + "loss": 1.3884, + "step": 3127 + }, + { + "epoch": 0.33, + "learning_rate": 1.6994959518013502e-05, + "loss": 1.4111, + "step": 3128 + }, + { + "epoch": 0.33, + "learning_rate": 1.6992343300963963e-05, + "loss": 1.5452, + "step": 3129 + }, + { + "epoch": 0.33, + "learning_rate": 1.6989726147120087e-05, + "loss": 1.4097, + "step": 3130 + }, + { + "epoch": 0.33, + "learning_rate": 1.6987108056832506e-05, + "loss": 1.481, + "step": 3131 + }, + { + "epoch": 0.33, + "learning_rate": 1.6984489030451973e-05, + "loss": 1.4505, + "step": 3132 + }, + { + "epoch": 0.33, + "learning_rate": 1.6981869068329368e-05, + "loss": 1.4281, + "step": 3133 + }, + { + "epoch": 0.33, + "learning_rate": 1.69792481708157e-05, + "loss": 1.4555, + "step": 3134 + }, + { + "epoch": 0.33, + "learning_rate": 1.6976626338262103e-05, + "loss": 1.4525, + "step": 3135 + }, + { + "epoch": 0.33, + "learning_rate": 1.6974003571019837e-05, + "loss": 1.3765, + "step": 3136 + }, + { + "epoch": 0.33, + "learning_rate": 1.6971379869440286e-05, + "loss": 1.3998, + "step": 3137 + }, + { + "epoch": 0.33, + "learning_rate": 1.696875523387495e-05, + "loss": 1.5103, + "step": 3138 + }, + { + "epoch": 0.33, + "learning_rate": 1.6966129664675474e-05, + "loss": 1.427, + "step": 3139 + }, + { + "epoch": 0.33, + "learning_rate": 1.6963503162193612e-05, + "loss": 1.4362, + "step": 3140 + }, + { + "epoch": 0.33, + "learning_rate": 1.6960875726781246e-05, + "loss": 1.4073, + "step": 3141 + }, + { + "epoch": 0.33, + "learning_rate": 1.6958247358790388e-05, + "loss": 1.4014, + "step": 3142 + }, + { + "epoch": 0.33, + "learning_rate": 1.6955618058573165e-05, + "loss": 1.4244, + "step": 3143 + }, + { + "epoch": 0.33, + "learning_rate": 1.6952987826481847e-05, + "loss": 1.47, + "step": 3144 + }, + { + "epoch": 0.33, + "learning_rate": 1.6950356662868814e-05, + "loss": 1.5112, + "step": 3145 + }, + { + "epoch": 0.33, + "learning_rate": 1.6947724568086562e-05, + "loss": 1.3398, + "step": 3146 + }, + { + "epoch": 0.33, + "learning_rate": 1.694509154248774e-05, + "loss": 1.4584, + "step": 3147 + }, + { + "epoch": 0.33, + "learning_rate": 1.69424575864251e-05, + "loss": 1.4383, + "step": 3148 + }, + { + "epoch": 0.33, + "learning_rate": 1.6939822700251523e-05, + "loss": 1.3869, + "step": 3149 + }, + { + "epoch": 0.33, + "learning_rate": 1.6937186884320015e-05, + "loss": 1.4453, + "step": 3150 + }, + { + "epoch": 0.33, + "learning_rate": 1.6934550138983713e-05, + "loss": 1.3355, + "step": 3151 + }, + { + "epoch": 0.33, + "learning_rate": 1.6931912464595866e-05, + "loss": 1.5573, + "step": 3152 + }, + { + "epoch": 0.33, + "learning_rate": 1.6929273861509865e-05, + "loss": 1.439, + "step": 3153 + }, + { + "epoch": 0.33, + "learning_rate": 1.6926634330079203e-05, + "loss": 1.6079, + "step": 3154 + }, + { + "epoch": 0.33, + "learning_rate": 1.692399387065752e-05, + "loss": 1.6973, + "step": 3155 + }, + { + "epoch": 0.33, + "learning_rate": 1.692135248359856e-05, + "loss": 1.3769, + "step": 3156 + }, + { + "epoch": 0.33, + "learning_rate": 1.6918710169256206e-05, + "loss": 1.4454, + "step": 3157 + }, + { + "epoch": 0.33, + "learning_rate": 1.691606692798446e-05, + "loss": 1.4495, + "step": 3158 + }, + { + "epoch": 0.33, + "learning_rate": 1.691342276013745e-05, + "loss": 1.4292, + "step": 3159 + }, + { + "epoch": 0.33, + "learning_rate": 1.691077766606942e-05, + "loss": 1.4405, + "step": 3160 + }, + { + "epoch": 0.33, + "learning_rate": 1.6908131646134757e-05, + "loss": 1.3683, + "step": 3161 + }, + { + "epoch": 0.33, + "learning_rate": 1.690548470068795e-05, + "loss": 1.4731, + "step": 3162 + }, + { + "epoch": 0.33, + "learning_rate": 1.690283683008362e-05, + "loss": 1.4323, + "step": 3163 + }, + { + "epoch": 0.33, + "learning_rate": 1.6900188034676518e-05, + "loss": 1.5133, + "step": 3164 + }, + { + "epoch": 0.33, + "learning_rate": 1.6897538314821516e-05, + "loss": 1.5529, + "step": 3165 + }, + { + "epoch": 0.33, + "learning_rate": 1.6894887670873605e-05, + "loss": 1.4427, + "step": 3166 + }, + { + "epoch": 0.33, + "learning_rate": 1.6892236103187904e-05, + "loss": 1.4344, + "step": 3167 + }, + { + "epoch": 0.33, + "learning_rate": 1.6889583612119657e-05, + "loss": 1.4291, + "step": 3168 + }, + { + "epoch": 0.33, + "learning_rate": 1.6886930198024226e-05, + "loss": 1.4683, + "step": 3169 + }, + { + "epoch": 0.33, + "learning_rate": 1.6884275861257106e-05, + "loss": 1.4442, + "step": 3170 + }, + { + "epoch": 0.33, + "learning_rate": 1.6881620602173905e-05, + "loss": 1.4509, + "step": 3171 + }, + { + "epoch": 0.33, + "learning_rate": 1.6878964421130362e-05, + "loss": 1.5113, + "step": 3172 + }, + { + "epoch": 0.33, + "learning_rate": 1.6876307318482334e-05, + "loss": 1.4261, + "step": 3173 + }, + { + "epoch": 0.33, + "learning_rate": 1.6873649294585805e-05, + "loss": 1.445, + "step": 3174 + }, + { + "epoch": 0.33, + "learning_rate": 1.6870990349796886e-05, + "loss": 1.4603, + "step": 3175 + }, + { + "epoch": 0.33, + "learning_rate": 1.68683304844718e-05, + "loss": 1.41, + "step": 3176 + }, + { + "epoch": 0.33, + "learning_rate": 1.686566969896691e-05, + "loss": 1.4018, + "step": 3177 + }, + { + "epoch": 0.33, + "learning_rate": 1.6863007993638687e-05, + "loss": 1.422, + "step": 3178 + }, + { + "epoch": 0.33, + "learning_rate": 1.6860345368843727e-05, + "loss": 1.4412, + "step": 3179 + }, + { + "epoch": 0.33, + "learning_rate": 1.6857681824938768e-05, + "loss": 1.5411, + "step": 3180 + }, + { + "epoch": 0.33, + "learning_rate": 1.685501736228064e-05, + "loss": 1.4416, + "step": 3181 + }, + { + "epoch": 0.33, + "learning_rate": 1.685235198122632e-05, + "loss": 1.5113, + "step": 3182 + }, + { + "epoch": 0.33, + "learning_rate": 1.6849685682132903e-05, + "loss": 1.423, + "step": 3183 + }, + { + "epoch": 0.33, + "learning_rate": 1.68470184653576e-05, + "loss": 1.404, + "step": 3184 + }, + { + "epoch": 0.33, + "eval_loss": 1.4771089553833008, + "eval_runtime": 77.4034, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3184 + }, + { + "epoch": 0.33, + "learning_rate": 1.6844350331257747e-05, + "loss": 1.4624, + "step": 3185 + }, + { + "epoch": 0.33, + "learning_rate": 1.6841681280190814e-05, + "loss": 1.4306, + "step": 3186 + }, + { + "epoch": 0.33, + "learning_rate": 1.683901131251438e-05, + "loss": 1.42, + "step": 3187 + }, + { + "epoch": 0.33, + "learning_rate": 1.6836340428586155e-05, + "loss": 1.4787, + "step": 3188 + }, + { + "epoch": 0.33, + "learning_rate": 1.6833668628763965e-05, + "loss": 1.3485, + "step": 3189 + }, + { + "epoch": 0.33, + "learning_rate": 1.683099591340576e-05, + "loss": 1.3674, + "step": 3190 + }, + { + "epoch": 0.33, + "learning_rate": 1.6828322282869627e-05, + "loss": 1.5187, + "step": 3191 + }, + { + "epoch": 0.33, + "learning_rate": 1.682564773751375e-05, + "loss": 1.4847, + "step": 3192 + }, + { + "epoch": 0.33, + "learning_rate": 1.682297227769646e-05, + "loss": 1.4815, + "step": 3193 + }, + { + "epoch": 0.33, + "learning_rate": 1.682029590377619e-05, + "loss": 1.4281, + "step": 3194 + }, + { + "epoch": 0.34, + "learning_rate": 1.6817618616111517e-05, + "loss": 1.4734, + "step": 3195 + }, + { + "epoch": 0.34, + "learning_rate": 1.681494041506112e-05, + "loss": 1.4861, + "step": 3196 + }, + { + "epoch": 0.34, + "learning_rate": 1.6812261300983808e-05, + "loss": 1.4372, + "step": 3197 + }, + { + "epoch": 0.34, + "learning_rate": 1.680958127423852e-05, + "loss": 1.4396, + "step": 3198 + }, + { + "epoch": 0.34, + "learning_rate": 1.680690033518431e-05, + "loss": 1.4225, + "step": 3199 + }, + { + "epoch": 0.34, + "learning_rate": 1.6804218484180347e-05, + "loss": 1.4925, + "step": 3200 + }, + { + "epoch": 0.34, + "learning_rate": 1.6801535721585942e-05, + "loss": 1.4306, + "step": 3201 + }, + { + "epoch": 0.34, + "learning_rate": 1.6798852047760506e-05, + "loss": 1.4298, + "step": 3202 + }, + { + "epoch": 0.34, + "learning_rate": 1.6796167463063588e-05, + "loss": 1.4725, + "step": 3203 + }, + { + "epoch": 0.34, + "learning_rate": 1.679348196785485e-05, + "loss": 1.4648, + "step": 3204 + }, + { + "epoch": 0.34, + "learning_rate": 1.6790795562494087e-05, + "loss": 1.4152, + "step": 3205 + }, + { + "epoch": 0.34, + "learning_rate": 1.6788108247341198e-05, + "loss": 1.4637, + "step": 3206 + }, + { + "epoch": 0.34, + "learning_rate": 1.6785420022756216e-05, + "loss": 1.4077, + "step": 3207 + }, + { + "epoch": 0.34, + "learning_rate": 1.67827308890993e-05, + "loss": 1.4585, + "step": 3208 + }, + { + "epoch": 0.34, + "learning_rate": 1.678004084673072e-05, + "loss": 1.3747, + "step": 3209 + }, + { + "epoch": 0.34, + "learning_rate": 1.6777349896010876e-05, + "loss": 1.4264, + "step": 3210 + }, + { + "epoch": 0.34, + "learning_rate": 1.677465803730028e-05, + "loss": 1.4178, + "step": 3211 + }, + { + "epoch": 0.34, + "learning_rate": 1.6771965270959584e-05, + "loss": 1.3876, + "step": 3212 + }, + { + "epoch": 0.34, + "learning_rate": 1.6769271597349538e-05, + "loss": 1.4658, + "step": 3213 + }, + { + "epoch": 0.34, + "learning_rate": 1.6766577016831026e-05, + "loss": 1.3968, + "step": 3214 + }, + { + "epoch": 0.34, + "learning_rate": 1.676388152976506e-05, + "loss": 1.5015, + "step": 3215 + }, + { + "epoch": 0.34, + "learning_rate": 1.6761185136512756e-05, + "loss": 1.4121, + "step": 3216 + }, + { + "epoch": 0.34, + "learning_rate": 1.675848783743537e-05, + "loss": 1.4146, + "step": 3217 + }, + { + "epoch": 0.34, + "learning_rate": 1.675578963289427e-05, + "loss": 1.4113, + "step": 3218 + }, + { + "epoch": 0.34, + "learning_rate": 1.6753090523250937e-05, + "loss": 1.4048, + "step": 3219 + }, + { + "epoch": 0.34, + "learning_rate": 1.6750390508866994e-05, + "loss": 1.4959, + "step": 3220 + }, + { + "epoch": 0.34, + "learning_rate": 1.6747689590104167e-05, + "loss": 1.4445, + "step": 3221 + }, + { + "epoch": 0.34, + "learning_rate": 1.6744987767324312e-05, + "loss": 1.4611, + "step": 3222 + }, + { + "epoch": 0.34, + "learning_rate": 1.67422850408894e-05, + "loss": 1.4141, + "step": 3223 + }, + { + "epoch": 0.34, + "learning_rate": 1.6739581411161535e-05, + "loss": 1.4218, + "step": 3224 + }, + { + "epoch": 0.34, + "learning_rate": 1.6736876878502925e-05, + "loss": 1.4266, + "step": 3225 + }, + { + "epoch": 0.34, + "learning_rate": 1.6734171443275913e-05, + "loss": 1.4941, + "step": 3226 + }, + { + "epoch": 0.34, + "learning_rate": 1.6731465105842955e-05, + "loss": 1.4294, + "step": 3227 + }, + { + "epoch": 0.34, + "learning_rate": 1.6728757866566635e-05, + "loss": 1.4189, + "step": 3228 + }, + { + "epoch": 0.34, + "learning_rate": 1.6726049725809647e-05, + "loss": 1.4713, + "step": 3229 + }, + { + "epoch": 0.34, + "learning_rate": 1.6723340683934818e-05, + "loss": 1.4203, + "step": 3230 + }, + { + "epoch": 0.34, + "learning_rate": 1.6720630741305088e-05, + "loss": 1.4112, + "step": 3231 + }, + { + "epoch": 0.34, + "learning_rate": 1.6717919898283523e-05, + "loss": 1.3811, + "step": 3232 + }, + { + "epoch": 0.34, + "learning_rate": 1.6715208155233296e-05, + "loss": 1.4242, + "step": 3233 + }, + { + "epoch": 0.34, + "learning_rate": 1.6712495512517725e-05, + "loss": 1.4207, + "step": 3234 + }, + { + "epoch": 0.34, + "learning_rate": 1.6709781970500222e-05, + "loss": 1.4888, + "step": 3235 + }, + { + "epoch": 0.34, + "learning_rate": 1.670706752954434e-05, + "loss": 1.4501, + "step": 3236 + }, + { + "epoch": 0.34, + "learning_rate": 1.670435219001374e-05, + "loss": 1.4367, + "step": 3237 + }, + { + "epoch": 0.34, + "learning_rate": 1.6701635952272212e-05, + "loss": 1.3959, + "step": 3238 + }, + { + "epoch": 0.34, + "learning_rate": 1.6698918816683655e-05, + "loss": 1.4257, + "step": 3239 + }, + { + "epoch": 0.34, + "learning_rate": 1.6696200783612102e-05, + "loss": 1.4718, + "step": 3240 + }, + { + "epoch": 0.34, + "learning_rate": 1.6693481853421697e-05, + "loss": 1.5899, + "step": 3241 + }, + { + "epoch": 0.34, + "learning_rate": 1.6690762026476707e-05, + "loss": 1.418, + "step": 3242 + }, + { + "epoch": 0.34, + "learning_rate": 1.668804130314152e-05, + "loss": 1.4076, + "step": 3243 + }, + { + "epoch": 0.34, + "learning_rate": 1.6685319683780645e-05, + "loss": 1.4571, + "step": 3244 + }, + { + "epoch": 0.34, + "learning_rate": 1.66825971687587e-05, + "loss": 1.4066, + "step": 3245 + }, + { + "epoch": 0.34, + "learning_rate": 1.6679873758440442e-05, + "loss": 1.4639, + "step": 3246 + }, + { + "epoch": 0.34, + "learning_rate": 1.6677149453190732e-05, + "loss": 1.453, + "step": 3247 + }, + { + "epoch": 0.34, + "learning_rate": 1.6674424253374558e-05, + "loss": 1.4262, + "step": 3248 + }, + { + "epoch": 0.34, + "learning_rate": 1.667169815935703e-05, + "loss": 1.3687, + "step": 3249 + }, + { + "epoch": 0.34, + "learning_rate": 1.6668971171503372e-05, + "loss": 1.5557, + "step": 3250 + }, + { + "epoch": 0.34, + "learning_rate": 1.6666243290178933e-05, + "loss": 1.4639, + "step": 3251 + }, + { + "epoch": 0.34, + "learning_rate": 1.6663514515749172e-05, + "loss": 1.4334, + "step": 3252 + }, + { + "epoch": 0.34, + "learning_rate": 1.6660784848579685e-05, + "loss": 1.3523, + "step": 3253 + }, + { + "epoch": 0.34, + "learning_rate": 1.6658054289036166e-05, + "loss": 1.3738, + "step": 3254 + }, + { + "epoch": 0.34, + "learning_rate": 1.665532283748445e-05, + "loss": 1.4159, + "step": 3255 + }, + { + "epoch": 0.34, + "learning_rate": 1.6652590494290474e-05, + "loss": 1.3609, + "step": 3256 + }, + { + "epoch": 0.34, + "learning_rate": 1.6649857259820303e-05, + "loss": 1.4449, + "step": 3257 + }, + { + "epoch": 0.34, + "learning_rate": 1.6647123134440126e-05, + "loss": 1.424, + "step": 3258 + }, + { + "epoch": 0.34, + "learning_rate": 1.664438811851624e-05, + "loss": 1.4737, + "step": 3259 + }, + { + "epoch": 0.34, + "learning_rate": 1.6641652212415066e-05, + "loss": 1.2717, + "step": 3260 + }, + { + "epoch": 0.34, + "learning_rate": 1.663891541650315e-05, + "loss": 1.4845, + "step": 3261 + }, + { + "epoch": 0.34, + "learning_rate": 1.663617773114715e-05, + "loss": 1.4115, + "step": 3262 + }, + { + "epoch": 0.34, + "learning_rate": 1.663343915671384e-05, + "loss": 1.4237, + "step": 3263 + }, + { + "epoch": 0.34, + "learning_rate": 1.6630699693570127e-05, + "loss": 1.4209, + "step": 3264 + }, + { + "epoch": 0.34, + "learning_rate": 1.6627959342083026e-05, + "loss": 1.506, + "step": 3265 + }, + { + "epoch": 0.34, + "learning_rate": 1.6625218102619672e-05, + "loss": 1.4466, + "step": 3266 + }, + { + "epoch": 0.34, + "learning_rate": 1.6622475975547324e-05, + "loss": 1.4129, + "step": 3267 + }, + { + "epoch": 0.34, + "learning_rate": 1.661973296123335e-05, + "loss": 1.4152, + "step": 3268 + }, + { + "epoch": 0.34, + "learning_rate": 1.661698906004525e-05, + "loss": 1.43, + "step": 3269 + }, + { + "epoch": 0.34, + "learning_rate": 1.661424427235064e-05, + "loss": 1.4701, + "step": 3270 + }, + { + "epoch": 0.34, + "learning_rate": 1.6611498598517238e-05, + "loss": 1.4598, + "step": 3271 + }, + { + "epoch": 0.34, + "learning_rate": 1.66087520389129e-05, + "loss": 1.4795, + "step": 3272 + }, + { + "epoch": 0.34, + "learning_rate": 1.6606004593905595e-05, + "loss": 1.5264, + "step": 3273 + }, + { + "epoch": 0.34, + "learning_rate": 1.6603256263863415e-05, + "loss": 1.4412, + "step": 3274 + }, + { + "epoch": 0.34, + "learning_rate": 1.6600507049154556e-05, + "loss": 1.45, + "step": 3275 + }, + { + "epoch": 0.34, + "learning_rate": 1.659775695014735e-05, + "loss": 1.4985, + "step": 3276 + }, + { + "epoch": 0.34, + "learning_rate": 1.659500596721024e-05, + "loss": 1.496, + "step": 3277 + }, + { + "epoch": 0.34, + "learning_rate": 1.6592254100711775e-05, + "loss": 1.4386, + "step": 3278 + }, + { + "epoch": 0.34, + "learning_rate": 1.658950135102065e-05, + "loss": 1.4073, + "step": 3279 + }, + { + "epoch": 0.34, + "learning_rate": 1.658674771850565e-05, + "loss": 1.3912, + "step": 3280 + }, + { + "epoch": 0.34, + "learning_rate": 1.6583993203535702e-05, + "loss": 1.3628, + "step": 3281 + }, + { + "epoch": 0.34, + "learning_rate": 1.658123780647983e-05, + "loss": 1.6089, + "step": 3282 + }, + { + "epoch": 0.34, + "learning_rate": 1.6578481527707196e-05, + "loss": 1.2367, + "step": 3283 + }, + { + "epoch": 0.34, + "learning_rate": 1.657572436758706e-05, + "loss": 1.4058, + "step": 3284 + }, + { + "epoch": 0.34, + "learning_rate": 1.6572966326488825e-05, + "loss": 1.4067, + "step": 3285 + }, + { + "epoch": 0.34, + "learning_rate": 1.657020740478198e-05, + "loss": 1.4187, + "step": 3286 + }, + { + "epoch": 0.34, + "learning_rate": 1.6567447602836166e-05, + "loss": 1.4599, + "step": 3287 + }, + { + "epoch": 0.34, + "learning_rate": 1.6564686921021115e-05, + "loss": 1.432, + "step": 3288 + }, + { + "epoch": 0.34, + "learning_rate": 1.6561925359706693e-05, + "loss": 1.3941, + "step": 3289 + }, + { + "epoch": 0.35, + "learning_rate": 1.6559162919262874e-05, + "loss": 1.3644, + "step": 3290 + }, + { + "epoch": 0.35, + "learning_rate": 1.6556399600059756e-05, + "loss": 1.4628, + "step": 3291 + }, + { + "epoch": 0.35, + "learning_rate": 1.6553635402467555e-05, + "loss": 1.4355, + "step": 3292 + }, + { + "epoch": 0.35, + "learning_rate": 1.6550870326856596e-05, + "loss": 1.4627, + "step": 3293 + }, + { + "epoch": 0.35, + "learning_rate": 1.6548104373597335e-05, + "loss": 1.442, + "step": 3294 + }, + { + "epoch": 0.35, + "learning_rate": 1.6545337543060338e-05, + "loss": 1.3991, + "step": 3295 + }, + { + "epoch": 0.35, + "learning_rate": 1.6542569835616283e-05, + "loss": 1.4193, + "step": 3296 + }, + { + "epoch": 0.35, + "learning_rate": 1.6539801251635982e-05, + "loss": 1.4792, + "step": 3297 + }, + { + "epoch": 0.35, + "learning_rate": 1.653703179149034e-05, + "loss": 1.4735, + "step": 3298 + }, + { + "epoch": 0.35, + "learning_rate": 1.6534261455550408e-05, + "loss": 1.451, + "step": 3299 + }, + { + "epoch": 0.35, + "learning_rate": 1.653149024418733e-05, + "loss": 1.3975, + "step": 3300 + }, + { + "epoch": 0.35, + "learning_rate": 1.652871815777238e-05, + "loss": 1.4843, + "step": 3301 + }, + { + "epoch": 0.35, + "learning_rate": 1.6525945196676948e-05, + "loss": 1.4782, + "step": 3302 + }, + { + "epoch": 0.35, + "learning_rate": 1.652317136127254e-05, + "loss": 1.3865, + "step": 3303 + }, + { + "epoch": 0.35, + "learning_rate": 1.6520396651930777e-05, + "loss": 1.4359, + "step": 3304 + }, + { + "epoch": 0.35, + "learning_rate": 1.6517621069023397e-05, + "loss": 1.4289, + "step": 3305 + }, + { + "epoch": 0.35, + "learning_rate": 1.651484461292226e-05, + "loss": 1.3526, + "step": 3306 + }, + { + "epoch": 0.35, + "learning_rate": 1.6512067283999336e-05, + "loss": 1.3671, + "step": 3307 + }, + { + "epoch": 0.35, + "learning_rate": 1.650928908262672e-05, + "loss": 1.6041, + "step": 3308 + }, + { + "epoch": 0.35, + "learning_rate": 1.650651000917662e-05, + "loss": 1.4322, + "step": 3309 + }, + { + "epoch": 0.35, + "learning_rate": 1.6503730064021354e-05, + "loss": 1.3992, + "step": 3310 + }, + { + "epoch": 0.35, + "learning_rate": 1.650094924753337e-05, + "loss": 1.4928, + "step": 3311 + }, + { + "epoch": 0.35, + "learning_rate": 1.6498167560085222e-05, + "loss": 1.4075, + "step": 3312 + }, + { + "epoch": 0.35, + "learning_rate": 1.6495385002049583e-05, + "loss": 1.4535, + "step": 3313 + }, + { + "epoch": 0.35, + "learning_rate": 1.6492601573799253e-05, + "loss": 1.4221, + "step": 3314 + }, + { + "epoch": 0.35, + "learning_rate": 1.6489817275707133e-05, + "loss": 1.3688, + "step": 3315 + }, + { + "epoch": 0.35, + "learning_rate": 1.6487032108146243e-05, + "loss": 1.3889, + "step": 3316 + }, + { + "epoch": 0.35, + "learning_rate": 1.6484246071489733e-05, + "loss": 1.3942, + "step": 3317 + }, + { + "epoch": 0.35, + "learning_rate": 1.6481459166110858e-05, + "loss": 1.4004, + "step": 3318 + }, + { + "epoch": 0.35, + "learning_rate": 1.647867139238299e-05, + "loss": 1.7308, + "step": 3319 + }, + { + "epoch": 0.35, + "learning_rate": 1.6475882750679622e-05, + "loss": 1.5001, + "step": 3320 + }, + { + "epoch": 0.35, + "learning_rate": 1.647309324137435e-05, + "loss": 1.4325, + "step": 3321 + }, + { + "epoch": 0.35, + "learning_rate": 1.6470302864840913e-05, + "loss": 1.4494, + "step": 3322 + }, + { + "epoch": 0.35, + "learning_rate": 1.6467511621453136e-05, + "loss": 1.4418, + "step": 3323 + }, + { + "epoch": 0.35, + "learning_rate": 1.646471951158498e-05, + "loss": 1.4046, + "step": 3324 + }, + { + "epoch": 0.35, + "learning_rate": 1.6461926535610517e-05, + "loss": 1.5031, + "step": 3325 + }, + { + "epoch": 0.35, + "learning_rate": 1.645913269390393e-05, + "loss": 1.4813, + "step": 3326 + }, + { + "epoch": 0.35, + "learning_rate": 1.6456337986839525e-05, + "loss": 1.3842, + "step": 3327 + }, + { + "epoch": 0.35, + "learning_rate": 1.645354241479172e-05, + "loss": 1.4539, + "step": 3328 + }, + { + "epoch": 0.35, + "learning_rate": 1.6450745978135048e-05, + "loss": 1.4503, + "step": 3329 + }, + { + "epoch": 0.35, + "learning_rate": 1.6447948677244163e-05, + "loss": 1.3741, + "step": 3330 + }, + { + "epoch": 0.35, + "learning_rate": 1.6445150512493832e-05, + "loss": 1.425, + "step": 3331 + }, + { + "epoch": 0.35, + "learning_rate": 1.644235148425893e-05, + "loss": 1.4277, + "step": 3332 + }, + { + "epoch": 0.35, + "learning_rate": 1.6439551592914464e-05, + "loss": 1.4918, + "step": 3333 + }, + { + "epoch": 0.35, + "learning_rate": 1.6436750838835543e-05, + "loss": 1.3364, + "step": 3334 + }, + { + "epoch": 0.35, + "learning_rate": 1.6433949222397397e-05, + "loss": 1.4741, + "step": 3335 + }, + { + "epoch": 0.35, + "learning_rate": 1.643114674397537e-05, + "loss": 1.3867, + "step": 3336 + }, + { + "epoch": 0.35, + "learning_rate": 1.642834340394492e-05, + "loss": 1.3817, + "step": 3337 + }, + { + "epoch": 0.35, + "learning_rate": 1.6425539202681625e-05, + "loss": 1.4308, + "step": 3338 + }, + { + "epoch": 0.35, + "learning_rate": 1.6422734140561178e-05, + "loss": 1.4401, + "step": 3339 + }, + { + "epoch": 0.35, + "learning_rate": 1.641992821795938e-05, + "loss": 1.4338, + "step": 3340 + }, + { + "epoch": 0.35, + "learning_rate": 1.641712143525216e-05, + "loss": 1.3804, + "step": 3341 + }, + { + "epoch": 0.35, + "learning_rate": 1.6414313792815546e-05, + "loss": 1.371, + "step": 3342 + }, + { + "epoch": 0.35, + "learning_rate": 1.6411505291025695e-05, + "loss": 1.4102, + "step": 3343 + }, + { + "epoch": 0.35, + "learning_rate": 1.6408695930258875e-05, + "loss": 1.4433, + "step": 3344 + }, + { + "epoch": 0.35, + "learning_rate": 1.6405885710891467e-05, + "loss": 1.3895, + "step": 3345 + }, + { + "epoch": 0.35, + "learning_rate": 1.6403074633299966e-05, + "loss": 1.4321, + "step": 3346 + }, + { + "epoch": 0.35, + "learning_rate": 1.640026269786098e-05, + "loss": 1.4207, + "step": 3347 + }, + { + "epoch": 0.35, + "learning_rate": 1.639744990495125e-05, + "loss": 1.3758, + "step": 3348 + }, + { + "epoch": 0.35, + "learning_rate": 1.6394636254947612e-05, + "loss": 1.4203, + "step": 3349 + }, + { + "epoch": 0.35, + "learning_rate": 1.6391821748227013e-05, + "loss": 1.4596, + "step": 3350 + }, + { + "epoch": 0.35, + "learning_rate": 1.6389006385166537e-05, + "loss": 1.4344, + "step": 3351 + }, + { + "epoch": 0.35, + "learning_rate": 1.6386190166143366e-05, + "loss": 1.4048, + "step": 3352 + }, + { + "epoch": 0.35, + "learning_rate": 1.6383373091534798e-05, + "loss": 1.4348, + "step": 3353 + }, + { + "epoch": 0.35, + "learning_rate": 1.638055516171825e-05, + "loss": 1.4972, + "step": 3354 + }, + { + "epoch": 0.35, + "learning_rate": 1.6377736377071258e-05, + "loss": 1.4685, + "step": 3355 + }, + { + "epoch": 0.35, + "learning_rate": 1.637491673797146e-05, + "loss": 1.4093, + "step": 3356 + }, + { + "epoch": 0.35, + "learning_rate": 1.6372096244796616e-05, + "loss": 1.4452, + "step": 3357 + }, + { + "epoch": 0.35, + "learning_rate": 1.63692748979246e-05, + "loss": 1.4458, + "step": 3358 + }, + { + "epoch": 0.35, + "learning_rate": 1.6366452697733404e-05, + "loss": 1.4187, + "step": 3359 + }, + { + "epoch": 0.35, + "learning_rate": 1.6363629644601126e-05, + "loss": 1.4052, + "step": 3360 + }, + { + "epoch": 0.35, + "learning_rate": 1.6360805738905984e-05, + "loss": 1.439, + "step": 3361 + }, + { + "epoch": 0.35, + "learning_rate": 1.635798098102631e-05, + "loss": 1.4131, + "step": 3362 + }, + { + "epoch": 0.35, + "learning_rate": 1.6355155371340544e-05, + "loss": 1.4391, + "step": 3363 + }, + { + "epoch": 0.35, + "learning_rate": 1.6352328910227252e-05, + "loss": 1.4318, + "step": 3364 + }, + { + "epoch": 0.35, + "learning_rate": 1.63495015980651e-05, + "loss": 1.5112, + "step": 3365 + }, + { + "epoch": 0.35, + "learning_rate": 1.6346673435232884e-05, + "loss": 1.4688, + "step": 3366 + }, + { + "epoch": 0.35, + "learning_rate": 1.6343844422109496e-05, + "loss": 1.3807, + "step": 3367 + }, + { + "epoch": 0.35, + "learning_rate": 1.634101455907396e-05, + "loss": 1.4083, + "step": 3368 + }, + { + "epoch": 0.35, + "learning_rate": 1.6338183846505394e-05, + "loss": 1.3566, + "step": 3369 + }, + { + "epoch": 0.35, + "learning_rate": 1.633535228478305e-05, + "loss": 1.4287, + "step": 3370 + }, + { + "epoch": 0.35, + "learning_rate": 1.6332519874286285e-05, + "loss": 1.3494, + "step": 3371 + }, + { + "epoch": 0.35, + "learning_rate": 1.6329686615394558e-05, + "loss": 1.3813, + "step": 3372 + }, + { + "epoch": 0.35, + "learning_rate": 1.6326852508487468e-05, + "loss": 1.4241, + "step": 3373 + }, + { + "epoch": 0.35, + "learning_rate": 1.63240175539447e-05, + "loss": 1.424, + "step": 3374 + }, + { + "epoch": 0.35, + "learning_rate": 1.632118175214607e-05, + "loss": 1.4212, + "step": 3375 + }, + { + "epoch": 0.35, + "learning_rate": 1.6318345103471504e-05, + "loss": 1.4671, + "step": 3376 + }, + { + "epoch": 0.35, + "learning_rate": 1.6315507608301044e-05, + "loss": 1.4593, + "step": 3377 + }, + { + "epoch": 0.35, + "learning_rate": 1.631266926701483e-05, + "loss": 1.7816, + "step": 3378 + }, + { + "epoch": 0.35, + "learning_rate": 1.6309830079993134e-05, + "loss": 1.5134, + "step": 3379 + }, + { + "epoch": 0.35, + "learning_rate": 1.6306990047616334e-05, + "loss": 0.8933, + "step": 3380 + }, + { + "epoch": 0.35, + "learning_rate": 1.630414917026492e-05, + "loss": 1.1033, + "step": 3381 + }, + { + "epoch": 0.35, + "learning_rate": 1.6301307448319497e-05, + "loss": 1.3494, + "step": 3382 + }, + { + "epoch": 0.35, + "learning_rate": 1.6298464882160784e-05, + "loss": 1.4299, + "step": 3383 + }, + { + "epoch": 0.35, + "eval_loss": 1.482450008392334, + "eval_runtime": 77.3737, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3383 + }, + { + "epoch": 0.35, + "learning_rate": 1.629562147216961e-05, + "loss": 1.3971, + "step": 3384 + }, + { + "epoch": 0.35, + "learning_rate": 1.6292777218726917e-05, + "loss": 1.3706, + "step": 3385 + }, + { + "epoch": 0.36, + "learning_rate": 1.6289932122213765e-05, + "loss": 1.4524, + "step": 3386 + }, + { + "epoch": 0.36, + "learning_rate": 1.6287086183011328e-05, + "loss": 1.4595, + "step": 3387 + }, + { + "epoch": 0.36, + "learning_rate": 1.628423940150088e-05, + "loss": 1.492, + "step": 3388 + }, + { + "epoch": 0.36, + "learning_rate": 1.628139177806382e-05, + "loss": 1.5576, + "step": 3389 + }, + { + "epoch": 0.36, + "learning_rate": 1.6278543313081657e-05, + "loss": 1.4615, + "step": 3390 + }, + { + "epoch": 0.36, + "learning_rate": 1.6275694006936015e-05, + "loss": 1.3456, + "step": 3391 + }, + { + "epoch": 0.36, + "learning_rate": 1.627284386000862e-05, + "loss": 1.4254, + "step": 3392 + }, + { + "epoch": 0.36, + "learning_rate": 1.6269992872681325e-05, + "loss": 1.433, + "step": 3393 + }, + { + "epoch": 0.36, + "learning_rate": 1.626714104533609e-05, + "loss": 1.5291, + "step": 3394 + }, + { + "epoch": 0.36, + "learning_rate": 1.626428837835498e-05, + "loss": 1.4502, + "step": 3395 + }, + { + "epoch": 0.36, + "learning_rate": 1.626143487212019e-05, + "loss": 1.3756, + "step": 3396 + }, + { + "epoch": 0.36, + "learning_rate": 1.6258580527014002e-05, + "loss": 1.414, + "step": 3397 + }, + { + "epoch": 0.36, + "learning_rate": 1.6255725343418835e-05, + "loss": 1.6289, + "step": 3398 + }, + { + "epoch": 0.36, + "learning_rate": 1.6252869321717208e-05, + "loss": 1.4862, + "step": 3399 + }, + { + "epoch": 0.36, + "learning_rate": 1.6250012462291756e-05, + "loss": 1.4213, + "step": 3400 + }, + { + "epoch": 0.36, + "learning_rate": 1.6247154765525217e-05, + "loss": 1.524, + "step": 3401 + }, + { + "epoch": 0.36, + "learning_rate": 1.624429623180046e-05, + "loss": 1.6013, + "step": 3402 + }, + { + "epoch": 0.36, + "learning_rate": 1.624143686150045e-05, + "loss": 1.4557, + "step": 3403 + }, + { + "epoch": 0.36, + "learning_rate": 1.6238576655008266e-05, + "loss": 1.3831, + "step": 3404 + }, + { + "epoch": 0.36, + "learning_rate": 1.6235715612707105e-05, + "loss": 1.4008, + "step": 3405 + }, + { + "epoch": 0.36, + "learning_rate": 1.623285373498028e-05, + "loss": 1.4848, + "step": 3406 + }, + { + "epoch": 0.36, + "learning_rate": 1.6229991022211197e-05, + "loss": 1.4459, + "step": 3407 + }, + { + "epoch": 0.36, + "learning_rate": 1.6227127474783393e-05, + "loss": 1.4334, + "step": 3408 + }, + { + "epoch": 0.36, + "learning_rate": 1.6224263093080507e-05, + "loss": 1.4123, + "step": 3409 + }, + { + "epoch": 0.36, + "learning_rate": 1.6221397877486294e-05, + "loss": 1.3691, + "step": 3410 + }, + { + "epoch": 0.36, + "learning_rate": 1.6218531828384618e-05, + "loss": 1.4128, + "step": 3411 + }, + { + "epoch": 0.36, + "learning_rate": 1.6215664946159457e-05, + "loss": 1.3642, + "step": 3412 + }, + { + "epoch": 0.36, + "learning_rate": 1.6212797231194902e-05, + "loss": 1.4311, + "step": 3413 + }, + { + "epoch": 0.36, + "learning_rate": 1.6209928683875152e-05, + "loss": 1.4695, + "step": 3414 + }, + { + "epoch": 0.36, + "learning_rate": 1.6207059304584514e-05, + "loss": 1.3871, + "step": 3415 + }, + { + "epoch": 0.36, + "learning_rate": 1.6204189093707414e-05, + "loss": 1.4219, + "step": 3416 + }, + { + "epoch": 0.36, + "learning_rate": 1.620131805162839e-05, + "loss": 1.6199, + "step": 3417 + }, + { + "epoch": 0.36, + "learning_rate": 1.619844617873208e-05, + "loss": 1.4433, + "step": 3418 + }, + { + "epoch": 0.36, + "learning_rate": 1.619557347540325e-05, + "loss": 1.4773, + "step": 3419 + }, + { + "epoch": 0.36, + "learning_rate": 1.6192699942026763e-05, + "loss": 1.4551, + "step": 3420 + }, + { + "epoch": 0.36, + "learning_rate": 1.6189825578987603e-05, + "loss": 1.4903, + "step": 3421 + }, + { + "epoch": 0.36, + "learning_rate": 1.6186950386670855e-05, + "loss": 1.473, + "step": 3422 + }, + { + "epoch": 0.36, + "learning_rate": 1.6184074365461722e-05, + "loss": 1.4082, + "step": 3423 + }, + { + "epoch": 0.36, + "learning_rate": 1.6181197515745523e-05, + "loss": 1.4746, + "step": 3424 + }, + { + "epoch": 0.36, + "learning_rate": 1.6178319837907674e-05, + "loss": 1.449, + "step": 3425 + }, + { + "epoch": 0.36, + "learning_rate": 1.6175441332333715e-05, + "loss": 1.377, + "step": 3426 + }, + { + "epoch": 0.36, + "learning_rate": 1.617256199940929e-05, + "loss": 1.2364, + "step": 3427 + }, + { + "epoch": 0.36, + "learning_rate": 1.6169681839520155e-05, + "loss": 1.4437, + "step": 3428 + }, + { + "epoch": 0.36, + "learning_rate": 1.616680085305218e-05, + "loss": 1.4726, + "step": 3429 + }, + { + "epoch": 0.36, + "learning_rate": 1.616391904039134e-05, + "loss": 1.4824, + "step": 3430 + }, + { + "epoch": 0.36, + "learning_rate": 1.616103640192373e-05, + "loss": 1.4052, + "step": 3431 + }, + { + "epoch": 0.36, + "learning_rate": 1.6158152938035537e-05, + "loss": 1.4131, + "step": 3432 + }, + { + "epoch": 0.36, + "learning_rate": 1.6155268649113084e-05, + "loss": 1.4267, + "step": 3433 + }, + { + "epoch": 0.36, + "learning_rate": 1.6152383535542786e-05, + "loss": 1.3735, + "step": 3434 + }, + { + "epoch": 0.36, + "learning_rate": 1.6149497597711175e-05, + "loss": 1.4249, + "step": 3435 + }, + { + "epoch": 0.36, + "learning_rate": 1.614661083600489e-05, + "loss": 1.4312, + "step": 3436 + }, + { + "epoch": 0.36, + "learning_rate": 1.6143723250810686e-05, + "loss": 1.4831, + "step": 3437 + }, + { + "epoch": 0.36, + "learning_rate": 1.6140834842515425e-05, + "loss": 1.4183, + "step": 3438 + }, + { + "epoch": 0.36, + "learning_rate": 1.6137945611506078e-05, + "loss": 1.3908, + "step": 3439 + }, + { + "epoch": 0.36, + "learning_rate": 1.613505555816973e-05, + "loss": 1.425, + "step": 3440 + }, + { + "epoch": 0.36, + "learning_rate": 1.613216468289357e-05, + "loss": 1.3589, + "step": 3441 + }, + { + "epoch": 0.36, + "learning_rate": 1.6129272986064903e-05, + "loss": 1.4272, + "step": 3442 + }, + { + "epoch": 0.36, + "learning_rate": 1.6126380468071142e-05, + "loss": 1.4337, + "step": 3443 + }, + { + "epoch": 0.36, + "learning_rate": 1.6123487129299817e-05, + "loss": 1.3872, + "step": 3444 + }, + { + "epoch": 0.36, + "learning_rate": 1.612059297013855e-05, + "loss": 1.374, + "step": 3445 + }, + { + "epoch": 0.36, + "learning_rate": 1.611769799097509e-05, + "loss": 1.314, + "step": 3446 + }, + { + "epoch": 0.36, + "learning_rate": 1.6114802192197284e-05, + "loss": 1.3951, + "step": 3447 + }, + { + "epoch": 0.36, + "learning_rate": 1.6111905574193102e-05, + "loss": 1.4732, + "step": 3448 + }, + { + "epoch": 0.36, + "learning_rate": 1.6109008137350614e-05, + "loss": 1.3575, + "step": 3449 + }, + { + "epoch": 0.36, + "learning_rate": 1.6106109882058e-05, + "loss": 1.4606, + "step": 3450 + }, + { + "epoch": 0.36, + "learning_rate": 1.6103210808703554e-05, + "loss": 1.4357, + "step": 3451 + }, + { + "epoch": 0.36, + "learning_rate": 1.6100310917675678e-05, + "loss": 0.8456, + "step": 3452 + }, + { + "epoch": 0.36, + "learning_rate": 1.609741020936288e-05, + "loss": 1.07, + "step": 3453 + }, + { + "epoch": 0.36, + "learning_rate": 1.6094508684153782e-05, + "loss": 1.4435, + "step": 3454 + }, + { + "epoch": 0.36, + "learning_rate": 1.609160634243711e-05, + "loss": 1.3696, + "step": 3455 + }, + { + "epoch": 0.36, + "learning_rate": 1.6088703184601712e-05, + "loss": 1.4012, + "step": 3456 + }, + { + "epoch": 0.36, + "learning_rate": 1.608579921103653e-05, + "loss": 1.5212, + "step": 3457 + }, + { + "epoch": 0.36, + "learning_rate": 1.608289442213062e-05, + "loss": 1.4339, + "step": 3458 + }, + { + "epoch": 0.36, + "learning_rate": 1.607998881827316e-05, + "loss": 1.4901, + "step": 3459 + }, + { + "epoch": 0.36, + "learning_rate": 1.6077082399853412e-05, + "loss": 1.4822, + "step": 3460 + }, + { + "epoch": 0.36, + "learning_rate": 1.607417516726077e-05, + "loss": 1.3696, + "step": 3461 + }, + { + "epoch": 0.36, + "learning_rate": 1.6071267120884727e-05, + "loss": 1.4434, + "step": 3462 + }, + { + "epoch": 0.36, + "learning_rate": 1.6068358261114886e-05, + "loss": 1.3916, + "step": 3463 + }, + { + "epoch": 0.36, + "learning_rate": 1.606544858834096e-05, + "loss": 1.422, + "step": 3464 + }, + { + "epoch": 0.36, + "learning_rate": 1.6062538102952763e-05, + "loss": 1.367, + "step": 3465 + }, + { + "epoch": 0.36, + "learning_rate": 1.605962680534024e-05, + "loss": 1.3788, + "step": 3466 + }, + { + "epoch": 0.36, + "learning_rate": 1.605671469589342e-05, + "loss": 1.4366, + "step": 3467 + }, + { + "epoch": 0.36, + "learning_rate": 1.6053801775002453e-05, + "loss": 1.4027, + "step": 3468 + }, + { + "epoch": 0.36, + "learning_rate": 1.6050888043057595e-05, + "loss": 1.4386, + "step": 3469 + }, + { + "epoch": 0.36, + "learning_rate": 1.6047973500449212e-05, + "loss": 1.4675, + "step": 3470 + }, + { + "epoch": 0.36, + "learning_rate": 1.6045058147567778e-05, + "loss": 1.6936, + "step": 3471 + }, + { + "epoch": 0.36, + "learning_rate": 1.6042141984803875e-05, + "loss": 1.4858, + "step": 3472 + }, + { + "epoch": 0.36, + "learning_rate": 1.6039225012548196e-05, + "loss": 1.5004, + "step": 3473 + }, + { + "epoch": 0.36, + "learning_rate": 1.6036307231191534e-05, + "loss": 1.4969, + "step": 3474 + }, + { + "epoch": 0.36, + "learning_rate": 1.6033388641124803e-05, + "loss": 1.4027, + "step": 3475 + }, + { + "epoch": 0.36, + "learning_rate": 1.6030469242739016e-05, + "loss": 1.4741, + "step": 3476 + }, + { + "epoch": 0.36, + "learning_rate": 1.60275490364253e-05, + "loss": 1.3887, + "step": 3477 + }, + { + "epoch": 0.36, + "learning_rate": 1.602462802257488e-05, + "loss": 1.6735, + "step": 3478 + }, + { + "epoch": 0.36, + "learning_rate": 1.602170620157911e-05, + "loss": 1.4997, + "step": 3479 + }, + { + "epoch": 0.36, + "learning_rate": 1.601878357382943e-05, + "loss": 1.3973, + "step": 3480 + }, + { + "epoch": 0.37, + "learning_rate": 1.6015860139717398e-05, + "loss": 1.416, + "step": 3481 + }, + { + "epoch": 0.37, + "learning_rate": 1.6012935899634682e-05, + "loss": 1.4102, + "step": 3482 + }, + { + "epoch": 0.37, + "learning_rate": 1.601001085397305e-05, + "loss": 1.4248, + "step": 3483 + }, + { + "epoch": 0.37, + "learning_rate": 1.6007085003124386e-05, + "loss": 1.3909, + "step": 3484 + }, + { + "epoch": 0.37, + "learning_rate": 1.600415834748068e-05, + "loss": 1.4029, + "step": 3485 + }, + { + "epoch": 0.37, + "learning_rate": 1.6001230887434024e-05, + "loss": 1.4219, + "step": 3486 + }, + { + "epoch": 0.37, + "learning_rate": 1.5998302623376633e-05, + "loss": 1.4008, + "step": 3487 + }, + { + "epoch": 0.37, + "learning_rate": 1.5995373555700806e-05, + "loss": 1.5163, + "step": 3488 + }, + { + "epoch": 0.37, + "learning_rate": 1.599244368479897e-05, + "loss": 1.4541, + "step": 3489 + }, + { + "epoch": 0.37, + "learning_rate": 1.598951301106365e-05, + "loss": 1.4454, + "step": 3490 + }, + { + "epoch": 0.37, + "learning_rate": 1.598658153488748e-05, + "loss": 1.1014, + "step": 3491 + }, + { + "epoch": 0.37, + "learning_rate": 1.598364925666321e-05, + "loss": 1.407, + "step": 3492 + }, + { + "epoch": 0.37, + "learning_rate": 1.5980716176783682e-05, + "loss": 1.5046, + "step": 3493 + }, + { + "epoch": 0.37, + "learning_rate": 1.5977782295641857e-05, + "loss": 1.4265, + "step": 3494 + }, + { + "epoch": 0.37, + "learning_rate": 1.5974847613630796e-05, + "loss": 1.46, + "step": 3495 + }, + { + "epoch": 0.37, + "learning_rate": 1.5971912131143677e-05, + "loss": 1.3996, + "step": 3496 + }, + { + "epoch": 0.37, + "learning_rate": 1.5968975848573772e-05, + "loss": 1.4719, + "step": 3497 + }, + { + "epoch": 0.37, + "learning_rate": 1.596603876631447e-05, + "loss": 1.43, + "step": 3498 + }, + { + "epoch": 0.37, + "learning_rate": 1.596310088475927e-05, + "loss": 1.4109, + "step": 3499 + }, + { + "epoch": 0.37, + "learning_rate": 1.5960162204301768e-05, + "loss": 1.3612, + "step": 3500 + }, + { + "epoch": 0.37, + "learning_rate": 1.5957222725335672e-05, + "loss": 1.5045, + "step": 3501 + }, + { + "epoch": 0.37, + "learning_rate": 1.5954282448254794e-05, + "loss": 1.5323, + "step": 3502 + }, + { + "epoch": 0.37, + "learning_rate": 1.595134137345306e-05, + "loss": 1.4518, + "step": 3503 + }, + { + "epoch": 0.37, + "learning_rate": 1.5948399501324495e-05, + "loss": 1.6131, + "step": 3504 + }, + { + "epoch": 0.37, + "learning_rate": 1.594545683226324e-05, + "loss": 1.5076, + "step": 3505 + }, + { + "epoch": 0.37, + "learning_rate": 1.594251336666353e-05, + "loss": 1.482, + "step": 3506 + }, + { + "epoch": 0.37, + "learning_rate": 1.5939569104919716e-05, + "loss": 1.4429, + "step": 3507 + }, + { + "epoch": 0.37, + "learning_rate": 1.5936624047426254e-05, + "loss": 1.4662, + "step": 3508 + }, + { + "epoch": 0.37, + "learning_rate": 1.5933678194577708e-05, + "loss": 1.425, + "step": 3509 + }, + { + "epoch": 0.37, + "learning_rate": 1.5930731546768744e-05, + "loss": 1.4312, + "step": 3510 + }, + { + "epoch": 0.37, + "learning_rate": 1.592778410439414e-05, + "loss": 1.4336, + "step": 3511 + }, + { + "epoch": 0.37, + "learning_rate": 1.5924835867848775e-05, + "loss": 1.4197, + "step": 3512 + }, + { + "epoch": 0.37, + "learning_rate": 1.5921886837527638e-05, + "loss": 1.4456, + "step": 3513 + }, + { + "epoch": 0.37, + "learning_rate": 1.5918937013825823e-05, + "loss": 1.4394, + "step": 3514 + }, + { + "epoch": 0.37, + "learning_rate": 1.5915986397138526e-05, + "loss": 1.3606, + "step": 3515 + }, + { + "epoch": 0.37, + "learning_rate": 1.591303498786106e-05, + "loss": 1.4382, + "step": 3516 + }, + { + "epoch": 0.37, + "learning_rate": 1.591008278638884e-05, + "loss": 1.4185, + "step": 3517 + }, + { + "epoch": 0.37, + "learning_rate": 1.5907129793117374e-05, + "loss": 1.6692, + "step": 3518 + }, + { + "epoch": 0.37, + "learning_rate": 1.59041760084423e-05, + "loss": 1.501, + "step": 3519 + }, + { + "epoch": 0.37, + "learning_rate": 1.5901221432759345e-05, + "loss": 1.5753, + "step": 3520 + }, + { + "epoch": 0.37, + "learning_rate": 1.589826606646434e-05, + "loss": 1.4795, + "step": 3521 + }, + { + "epoch": 0.37, + "learning_rate": 1.5895309909953236e-05, + "loss": 1.4379, + "step": 3522 + }, + { + "epoch": 0.37, + "learning_rate": 1.5892352963622078e-05, + "loss": 1.3426, + "step": 3523 + }, + { + "epoch": 0.37, + "learning_rate": 1.5889395227867025e-05, + "loss": 1.4048, + "step": 3524 + }, + { + "epoch": 0.37, + "learning_rate": 1.5886436703084332e-05, + "loss": 1.4303, + "step": 3525 + }, + { + "epoch": 0.37, + "learning_rate": 1.5883477389670367e-05, + "loss": 1.3684, + "step": 3526 + }, + { + "epoch": 0.37, + "learning_rate": 1.5880517288021602e-05, + "loss": 1.3701, + "step": 3527 + }, + { + "epoch": 0.37, + "learning_rate": 1.587755639853462e-05, + "loss": 1.4308, + "step": 3528 + }, + { + "epoch": 0.37, + "learning_rate": 1.5874594721606096e-05, + "loss": 1.3981, + "step": 3529 + }, + { + "epoch": 0.37, + "learning_rate": 1.5871632257632823e-05, + "loss": 1.5906, + "step": 3530 + }, + { + "epoch": 0.37, + "learning_rate": 1.5868669007011696e-05, + "loss": 1.4642, + "step": 3531 + }, + { + "epoch": 0.37, + "learning_rate": 1.586570497013971e-05, + "loss": 1.411, + "step": 3532 + }, + { + "epoch": 0.37, + "learning_rate": 1.586274014741397e-05, + "loss": 1.3942, + "step": 3533 + }, + { + "epoch": 0.37, + "learning_rate": 1.5859774539231693e-05, + "loss": 1.3952, + "step": 3534 + }, + { + "epoch": 0.37, + "learning_rate": 1.585680814599019e-05, + "loss": 1.4009, + "step": 3535 + }, + { + "epoch": 0.37, + "learning_rate": 1.585384096808688e-05, + "loss": 1.3238, + "step": 3536 + }, + { + "epoch": 0.37, + "learning_rate": 1.585087300591929e-05, + "loss": 1.346, + "step": 3537 + }, + { + "epoch": 0.37, + "learning_rate": 1.584790425988505e-05, + "loss": 1.3739, + "step": 3538 + }, + { + "epoch": 0.37, + "learning_rate": 1.5844934730381895e-05, + "loss": 1.4264, + "step": 3539 + }, + { + "epoch": 0.37, + "learning_rate": 1.5841964417807668e-05, + "loss": 1.4675, + "step": 3540 + }, + { + "epoch": 0.37, + "learning_rate": 1.5838993322560314e-05, + "loss": 1.3337, + "step": 3541 + }, + { + "epoch": 0.37, + "learning_rate": 1.5836021445037883e-05, + "loss": 1.4052, + "step": 3542 + }, + { + "epoch": 0.37, + "learning_rate": 1.583304878563853e-05, + "loss": 1.4311, + "step": 3543 + }, + { + "epoch": 0.37, + "learning_rate": 1.5830075344760513e-05, + "loss": 1.386, + "step": 3544 + }, + { + "epoch": 0.37, + "learning_rate": 1.58271011228022e-05, + "loss": 1.387, + "step": 3545 + }, + { + "epoch": 0.37, + "learning_rate": 1.582412612016206e-05, + "loss": 1.3601, + "step": 3546 + }, + { + "epoch": 0.37, + "learning_rate": 1.5821150337238663e-05, + "loss": 1.5111, + "step": 3547 + }, + { + "epoch": 0.37, + "learning_rate": 1.5818173774430697e-05, + "loss": 1.471, + "step": 3548 + }, + { + "epoch": 0.37, + "learning_rate": 1.581519643213693e-05, + "loss": 1.4442, + "step": 3549 + }, + { + "epoch": 0.37, + "learning_rate": 1.5812218310756263e-05, + "loss": 1.467, + "step": 3550 + }, + { + "epoch": 0.37, + "learning_rate": 1.5809239410687683e-05, + "loss": 1.3731, + "step": 3551 + }, + { + "epoch": 0.37, + "learning_rate": 1.5806259732330286e-05, + "loss": 1.4072, + "step": 3552 + }, + { + "epoch": 0.37, + "learning_rate": 1.5803279276083268e-05, + "loss": 1.3636, + "step": 3553 + }, + { + "epoch": 0.37, + "learning_rate": 1.5800298042345938e-05, + "loss": 1.3915, + "step": 3554 + }, + { + "epoch": 0.37, + "learning_rate": 1.5797316031517705e-05, + "loss": 1.5038, + "step": 3555 + }, + { + "epoch": 0.37, + "learning_rate": 1.5794333243998082e-05, + "loss": 1.4455, + "step": 3556 + }, + { + "epoch": 0.37, + "learning_rate": 1.5791349680186684e-05, + "loss": 1.5062, + "step": 3557 + }, + { + "epoch": 0.37, + "learning_rate": 1.5788365340483234e-05, + "loss": 1.3899, + "step": 3558 + }, + { + "epoch": 0.37, + "learning_rate": 1.5785380225287554e-05, + "loss": 1.4946, + "step": 3559 + }, + { + "epoch": 0.37, + "learning_rate": 1.5782394334999572e-05, + "loss": 1.3859, + "step": 3560 + }, + { + "epoch": 0.37, + "learning_rate": 1.577940767001933e-05, + "loss": 1.541, + "step": 3561 + }, + { + "epoch": 0.37, + "learning_rate": 1.5776420230746952e-05, + "loss": 1.4952, + "step": 3562 + }, + { + "epoch": 0.37, + "learning_rate": 1.5773432017582684e-05, + "loss": 1.6055, + "step": 3563 + }, + { + "epoch": 0.37, + "learning_rate": 1.577044303092687e-05, + "loss": 1.4661, + "step": 3564 + }, + { + "epoch": 0.37, + "learning_rate": 1.576745327117996e-05, + "loss": 1.4082, + "step": 3565 + }, + { + "epoch": 0.37, + "learning_rate": 1.5764462738742493e-05, + "loss": 1.4005, + "step": 3566 + }, + { + "epoch": 0.37, + "learning_rate": 1.5761471434015137e-05, + "loss": 1.3959, + "step": 3567 + }, + { + "epoch": 0.37, + "learning_rate": 1.5758479357398645e-05, + "loss": 1.4567, + "step": 3568 + }, + { + "epoch": 0.37, + "learning_rate": 1.575548650929388e-05, + "loss": 1.3791, + "step": 3569 + }, + { + "epoch": 0.37, + "learning_rate": 1.57524928901018e-05, + "loss": 1.4428, + "step": 3570 + }, + { + "epoch": 0.37, + "learning_rate": 1.5749498500223486e-05, + "loss": 1.3864, + "step": 3571 + }, + { + "epoch": 0.37, + "learning_rate": 1.5746503340060097e-05, + "loss": 1.4019, + "step": 3572 + }, + { + "epoch": 0.37, + "learning_rate": 1.574350741001291e-05, + "loss": 1.5436, + "step": 3573 + }, + { + "epoch": 0.37, + "learning_rate": 1.5740510710483308e-05, + "loss": 1.4637, + "step": 3574 + }, + { + "epoch": 0.37, + "learning_rate": 1.5737513241872767e-05, + "loss": 1.5097, + "step": 3575 + }, + { + "epoch": 0.38, + "learning_rate": 1.5734515004582873e-05, + "loss": 1.5143, + "step": 3576 + }, + { + "epoch": 0.38, + "learning_rate": 1.5731515999015315e-05, + "loss": 1.3926, + "step": 3577 + }, + { + "epoch": 0.38, + "learning_rate": 1.5728516225571874e-05, + "loss": 1.4242, + "step": 3578 + }, + { + "epoch": 0.38, + "learning_rate": 1.5725515684654453e-05, + "loss": 1.4429, + "step": 3579 + }, + { + "epoch": 0.38, + "learning_rate": 1.572251437666504e-05, + "loss": 1.4638, + "step": 3580 + }, + { + "epoch": 0.38, + "learning_rate": 1.5719512302005735e-05, + "loss": 1.3381, + "step": 3581 + }, + { + "epoch": 0.38, + "learning_rate": 1.571650946107874e-05, + "loss": 1.4342, + "step": 3582 + }, + { + "epoch": 0.38, + "eval_loss": 1.4705015420913696, + "eval_runtime": 77.3664, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3582 + }, + { + "epoch": 0.38, + "learning_rate": 1.571350585428636e-05, + "loss": 1.3991, + "step": 3583 + }, + { + "epoch": 0.38, + "learning_rate": 1.5710501482030998e-05, + "loss": 1.4274, + "step": 3584 + }, + { + "epoch": 0.38, + "learning_rate": 1.5707496344715166e-05, + "loss": 1.438, + "step": 3585 + }, + { + "epoch": 0.38, + "learning_rate": 1.570449044274147e-05, + "loss": 1.4453, + "step": 3586 + }, + { + "epoch": 0.38, + "learning_rate": 1.570148377651263e-05, + "loss": 1.4022, + "step": 3587 + }, + { + "epoch": 0.38, + "learning_rate": 1.5698476346431454e-05, + "loss": 1.4312, + "step": 3588 + }, + { + "epoch": 0.38, + "learning_rate": 1.569546815290087e-05, + "loss": 1.4329, + "step": 3589 + }, + { + "epoch": 0.38, + "learning_rate": 1.569245919632389e-05, + "loss": 1.4036, + "step": 3590 + }, + { + "epoch": 0.38, + "learning_rate": 1.5689449477103644e-05, + "loss": 1.412, + "step": 3591 + }, + { + "epoch": 0.38, + "learning_rate": 1.5686438995643353e-05, + "loss": 1.4492, + "step": 3592 + }, + { + "epoch": 0.38, + "learning_rate": 1.5683427752346343e-05, + "loss": 1.4555, + "step": 3593 + }, + { + "epoch": 0.38, + "learning_rate": 1.5680415747616047e-05, + "loss": 1.5594, + "step": 3594 + }, + { + "epoch": 0.38, + "learning_rate": 1.5677402981855993e-05, + "loss": 1.4813, + "step": 3595 + }, + { + "epoch": 0.38, + "learning_rate": 1.567438945546982e-05, + "loss": 1.5919, + "step": 3596 + }, + { + "epoch": 0.38, + "learning_rate": 1.5671375168861255e-05, + "loss": 1.4235, + "step": 3597 + }, + { + "epoch": 0.38, + "learning_rate": 1.5668360122434135e-05, + "loss": 1.441, + "step": 3598 + }, + { + "epoch": 0.38, + "learning_rate": 1.566534431659241e-05, + "loss": 1.5847, + "step": 3599 + }, + { + "epoch": 0.38, + "learning_rate": 1.566232775174011e-05, + "loss": 1.6123, + "step": 3600 + }, + { + "epoch": 0.38, + "learning_rate": 1.5659310428281374e-05, + "loss": 1.4916, + "step": 3601 + }, + { + "epoch": 0.38, + "learning_rate": 1.5656292346620457e-05, + "loss": 1.4603, + "step": 3602 + }, + { + "epoch": 0.38, + "learning_rate": 1.56532735071617e-05, + "loss": 1.4423, + "step": 3603 + }, + { + "epoch": 0.38, + "learning_rate": 1.5650253910309547e-05, + "loss": 1.4814, + "step": 3604 + }, + { + "epoch": 0.38, + "learning_rate": 1.5647233556468552e-05, + "loss": 1.4015, + "step": 3605 + }, + { + "epoch": 0.38, + "learning_rate": 1.564421244604336e-05, + "loss": 1.3798, + "step": 3606 + }, + { + "epoch": 0.38, + "learning_rate": 1.5641190579438723e-05, + "loss": 1.4259, + "step": 3607 + }, + { + "epoch": 0.38, + "learning_rate": 1.5638167957059493e-05, + "loss": 1.3493, + "step": 3608 + }, + { + "epoch": 0.38, + "learning_rate": 1.5635144579310626e-05, + "loss": 1.3433, + "step": 3609 + }, + { + "epoch": 0.38, + "learning_rate": 1.5632120446597177e-05, + "loss": 1.4661, + "step": 3610 + }, + { + "epoch": 0.38, + "learning_rate": 1.5629095559324297e-05, + "loss": 1.4205, + "step": 3611 + }, + { + "epoch": 0.38, + "learning_rate": 1.562606991789725e-05, + "loss": 1.3976, + "step": 3612 + }, + { + "epoch": 0.38, + "learning_rate": 1.5623043522721393e-05, + "loss": 1.4261, + "step": 3613 + }, + { + "epoch": 0.38, + "learning_rate": 1.562001637420218e-05, + "loss": 1.4358, + "step": 3614 + }, + { + "epoch": 0.38, + "learning_rate": 1.5616988472745175e-05, + "loss": 1.437, + "step": 3615 + }, + { + "epoch": 0.38, + "learning_rate": 1.561395981875604e-05, + "loss": 1.3735, + "step": 3616 + }, + { + "epoch": 0.38, + "learning_rate": 1.5610930412640532e-05, + "loss": 1.4357, + "step": 3617 + }, + { + "epoch": 0.38, + "learning_rate": 1.560790025480452e-05, + "loss": 1.4003, + "step": 3618 + }, + { + "epoch": 0.38, + "learning_rate": 1.5604869345653965e-05, + "loss": 1.4127, + "step": 3619 + }, + { + "epoch": 0.38, + "learning_rate": 1.5601837685594927e-05, + "loss": 1.4666, + "step": 3620 + }, + { + "epoch": 0.38, + "learning_rate": 1.5598805275033574e-05, + "loss": 1.4106, + "step": 3621 + }, + { + "epoch": 0.38, + "learning_rate": 1.5595772114376174e-05, + "loss": 1.3857, + "step": 3622 + }, + { + "epoch": 0.38, + "learning_rate": 1.5592738204029086e-05, + "loss": 1.4704, + "step": 3623 + }, + { + "epoch": 0.38, + "learning_rate": 1.558970354439878e-05, + "loss": 1.4649, + "step": 3624 + }, + { + "epoch": 0.38, + "learning_rate": 1.5586668135891824e-05, + "loss": 1.4812, + "step": 3625 + }, + { + "epoch": 0.38, + "learning_rate": 1.5583631978914882e-05, + "loss": 1.3507, + "step": 3626 + }, + { + "epoch": 0.38, + "learning_rate": 1.5580595073874718e-05, + "loss": 1.3762, + "step": 3627 + }, + { + "epoch": 0.38, + "learning_rate": 1.557755742117821e-05, + "loss": 1.4169, + "step": 3628 + }, + { + "epoch": 0.38, + "learning_rate": 1.557451902123231e-05, + "loss": 1.4098, + "step": 3629 + }, + { + "epoch": 0.38, + "learning_rate": 1.55714798744441e-05, + "loss": 1.5526, + "step": 3630 + }, + { + "epoch": 0.38, + "learning_rate": 1.556843998122074e-05, + "loss": 1.4414, + "step": 3631 + }, + { + "epoch": 0.38, + "learning_rate": 1.5565399341969497e-05, + "loss": 1.4134, + "step": 3632 + }, + { + "epoch": 0.38, + "learning_rate": 1.556235795709774e-05, + "loss": 1.4718, + "step": 3633 + }, + { + "epoch": 0.38, + "learning_rate": 1.5559315827012937e-05, + "loss": 1.412, + "step": 3634 + }, + { + "epoch": 0.38, + "learning_rate": 1.5556272952122657e-05, + "loss": 1.4119, + "step": 3635 + }, + { + "epoch": 0.38, + "learning_rate": 1.5553229332834564e-05, + "loss": 1.3999, + "step": 3636 + }, + { + "epoch": 0.38, + "learning_rate": 1.5550184969556428e-05, + "loss": 1.4626, + "step": 3637 + }, + { + "epoch": 0.38, + "learning_rate": 1.5547139862696113e-05, + "loss": 1.3811, + "step": 3638 + }, + { + "epoch": 0.38, + "learning_rate": 1.5544094012661583e-05, + "loss": 1.4053, + "step": 3639 + }, + { + "epoch": 0.38, + "learning_rate": 1.5541047419860907e-05, + "loss": 1.4059, + "step": 3640 + }, + { + "epoch": 0.38, + "learning_rate": 1.553800008470225e-05, + "loss": 1.4717, + "step": 3641 + }, + { + "epoch": 0.38, + "learning_rate": 1.553495200759388e-05, + "loss": 1.399, + "step": 3642 + }, + { + "epoch": 0.38, + "learning_rate": 1.5531903188944154e-05, + "loss": 1.4143, + "step": 3643 + }, + { + "epoch": 0.38, + "learning_rate": 1.5528853629161536e-05, + "loss": 1.4414, + "step": 3644 + }, + { + "epoch": 0.38, + "learning_rate": 1.5525803328654592e-05, + "loss": 1.4206, + "step": 3645 + }, + { + "epoch": 0.38, + "learning_rate": 1.5522752287831982e-05, + "loss": 1.3869, + "step": 3646 + }, + { + "epoch": 0.38, + "learning_rate": 1.551970050710247e-05, + "loss": 1.5434, + "step": 3647 + }, + { + "epoch": 0.38, + "learning_rate": 1.5516647986874914e-05, + "loss": 1.4574, + "step": 3648 + }, + { + "epoch": 0.38, + "learning_rate": 1.5513594727558273e-05, + "loss": 1.4353, + "step": 3649 + }, + { + "epoch": 0.38, + "learning_rate": 1.5510540729561606e-05, + "loss": 1.4122, + "step": 3650 + }, + { + "epoch": 0.38, + "learning_rate": 1.550748599329407e-05, + "loss": 1.4077, + "step": 3651 + }, + { + "epoch": 0.38, + "learning_rate": 1.550443051916492e-05, + "loss": 1.4433, + "step": 3652 + }, + { + "epoch": 0.38, + "learning_rate": 1.5501374307583514e-05, + "loss": 1.54, + "step": 3653 + }, + { + "epoch": 0.38, + "learning_rate": 1.5498317358959302e-05, + "loss": 1.4522, + "step": 3654 + }, + { + "epoch": 0.38, + "learning_rate": 1.5495259673701842e-05, + "loss": 1.4175, + "step": 3655 + }, + { + "epoch": 0.38, + "learning_rate": 1.5492201252220777e-05, + "loss": 1.4637, + "step": 3656 + }, + { + "epoch": 0.38, + "learning_rate": 1.5489142094925863e-05, + "loss": 1.4701, + "step": 3657 + }, + { + "epoch": 0.38, + "learning_rate": 1.548608220222695e-05, + "loss": 1.4095, + "step": 3658 + }, + { + "epoch": 0.38, + "learning_rate": 1.548302157453398e-05, + "loss": 1.3903, + "step": 3659 + }, + { + "epoch": 0.38, + "learning_rate": 1.5479960212257002e-05, + "loss": 1.4062, + "step": 3660 + }, + { + "epoch": 0.38, + "learning_rate": 1.5476898115806157e-05, + "loss": 1.4706, + "step": 3661 + }, + { + "epoch": 0.38, + "learning_rate": 1.547383528559169e-05, + "loss": 1.4423, + "step": 3662 + }, + { + "epoch": 0.38, + "learning_rate": 1.547077172202394e-05, + "loss": 1.4418, + "step": 3663 + }, + { + "epoch": 0.38, + "learning_rate": 1.5467707425513347e-05, + "loss": 1.4553, + "step": 3664 + }, + { + "epoch": 0.38, + "learning_rate": 1.5464642396470443e-05, + "loss": 1.435, + "step": 3665 + }, + { + "epoch": 0.38, + "learning_rate": 1.5461576635305873e-05, + "loss": 1.4105, + "step": 3666 + }, + { + "epoch": 0.38, + "learning_rate": 1.5458510142430364e-05, + "loss": 1.4118, + "step": 3667 + }, + { + "epoch": 0.38, + "learning_rate": 1.5455442918254746e-05, + "loss": 1.4096, + "step": 3668 + }, + { + "epoch": 0.38, + "learning_rate": 1.545237496318995e-05, + "loss": 1.4248, + "step": 3669 + }, + { + "epoch": 0.38, + "learning_rate": 1.5449306277647003e-05, + "loss": 1.4591, + "step": 3670 + }, + { + "epoch": 0.38, + "learning_rate": 1.544623686203703e-05, + "loss": 1.4764, + "step": 3671 + }, + { + "epoch": 0.39, + "learning_rate": 1.5443166716771255e-05, + "loss": 1.4329, + "step": 3672 + }, + { + "epoch": 0.39, + "learning_rate": 1.5440095842260995e-05, + "loss": 1.4023, + "step": 3673 + }, + { + "epoch": 0.39, + "learning_rate": 1.5437024238917674e-05, + "loss": 1.3802, + "step": 3674 + }, + { + "epoch": 0.39, + "learning_rate": 1.5433951907152806e-05, + "loss": 1.4627, + "step": 3675 + }, + { + "epoch": 0.39, + "learning_rate": 1.5430878847378e-05, + "loss": 1.5164, + "step": 3676 + }, + { + "epoch": 0.39, + "learning_rate": 1.542780506000497e-05, + "loss": 1.3546, + "step": 3677 + }, + { + "epoch": 0.39, + "learning_rate": 1.542473054544553e-05, + "loss": 1.4415, + "step": 3678 + }, + { + "epoch": 0.39, + "learning_rate": 1.5421655304111573e-05, + "loss": 1.4093, + "step": 3679 + }, + { + "epoch": 0.39, + "learning_rate": 1.5418579336415114e-05, + "loss": 1.3943, + "step": 3680 + }, + { + "epoch": 0.39, + "learning_rate": 1.5415502642768252e-05, + "loss": 1.3659, + "step": 3681 + }, + { + "epoch": 0.39, + "learning_rate": 1.541242522358318e-05, + "loss": 1.4322, + "step": 3682 + }, + { + "epoch": 0.39, + "learning_rate": 1.5409347079272198e-05, + "loss": 1.4064, + "step": 3683 + }, + { + "epoch": 0.39, + "learning_rate": 1.5406268210247693e-05, + "loss": 1.4031, + "step": 3684 + }, + { + "epoch": 0.39, + "learning_rate": 1.540318861692216e-05, + "loss": 1.3449, + "step": 3685 + }, + { + "epoch": 0.39, + "learning_rate": 1.5400108299708182e-05, + "loss": 1.5536, + "step": 3686 + }, + { + "epoch": 0.39, + "learning_rate": 1.5397027259018442e-05, + "loss": 1.4106, + "step": 3687 + }, + { + "epoch": 0.39, + "learning_rate": 1.5393945495265722e-05, + "loss": 1.4309, + "step": 3688 + }, + { + "epoch": 0.39, + "learning_rate": 1.53908630088629e-05, + "loss": 1.3765, + "step": 3689 + }, + { + "epoch": 0.39, + "learning_rate": 1.5387779800222947e-05, + "loss": 1.3809, + "step": 3690 + }, + { + "epoch": 0.39, + "learning_rate": 1.5384695869758938e-05, + "loss": 1.4758, + "step": 3691 + }, + { + "epoch": 0.39, + "learning_rate": 1.5381611217884032e-05, + "loss": 1.4249, + "step": 3692 + }, + { + "epoch": 0.39, + "learning_rate": 1.5378525845011503e-05, + "loss": 1.4133, + "step": 3693 + }, + { + "epoch": 0.39, + "learning_rate": 1.5375439751554708e-05, + "loss": 1.418, + "step": 3694 + }, + { + "epoch": 0.39, + "learning_rate": 1.53723529379271e-05, + "loss": 1.441, + "step": 3695 + }, + { + "epoch": 0.39, + "learning_rate": 1.536926540454224e-05, + "loss": 1.3919, + "step": 3696 + }, + { + "epoch": 0.39, + "learning_rate": 1.5366177151813775e-05, + "loss": 1.3722, + "step": 3697 + }, + { + "epoch": 0.39, + "learning_rate": 1.536308818015545e-05, + "loss": 1.4727, + "step": 3698 + }, + { + "epoch": 0.39, + "learning_rate": 1.535999848998111e-05, + "loss": 1.442, + "step": 3699 + }, + { + "epoch": 0.39, + "learning_rate": 1.535690808170469e-05, + "loss": 1.3884, + "step": 3700 + }, + { + "epoch": 0.39, + "learning_rate": 1.535381695574023e-05, + "loss": 1.3226, + "step": 3701 + }, + { + "epoch": 0.39, + "learning_rate": 1.535072511250186e-05, + "loss": 1.4403, + "step": 3702 + }, + { + "epoch": 0.39, + "learning_rate": 1.5347632552403808e-05, + "loss": 1.4144, + "step": 3703 + }, + { + "epoch": 0.39, + "learning_rate": 1.5344539275860395e-05, + "loss": 1.3514, + "step": 3704 + }, + { + "epoch": 0.39, + "learning_rate": 1.5341445283286044e-05, + "loss": 1.519, + "step": 3705 + }, + { + "epoch": 0.39, + "learning_rate": 1.5338350575095268e-05, + "loss": 1.4251, + "step": 3706 + }, + { + "epoch": 0.39, + "learning_rate": 1.5335255151702685e-05, + "loss": 1.392, + "step": 3707 + }, + { + "epoch": 0.39, + "learning_rate": 1.533215901352299e-05, + "loss": 1.3838, + "step": 3708 + }, + { + "epoch": 0.39, + "learning_rate": 1.532906216097099e-05, + "loss": 1.444, + "step": 3709 + }, + { + "epoch": 0.39, + "learning_rate": 1.5325964594461594e-05, + "loss": 1.3459, + "step": 3710 + }, + { + "epoch": 0.39, + "learning_rate": 1.5322866314409783e-05, + "loss": 1.4155, + "step": 3711 + }, + { + "epoch": 0.39, + "learning_rate": 1.5319767321230657e-05, + "loss": 1.4057, + "step": 3712 + }, + { + "epoch": 0.39, + "learning_rate": 1.5316667615339392e-05, + "loss": 1.382, + "step": 3713 + }, + { + "epoch": 0.39, + "learning_rate": 1.5313567197151277e-05, + "loss": 1.3634, + "step": 3714 + }, + { + "epoch": 0.39, + "learning_rate": 1.5310466067081688e-05, + "loss": 1.3434, + "step": 3715 + }, + { + "epoch": 0.39, + "learning_rate": 1.530736422554609e-05, + "loss": 1.4553, + "step": 3716 + }, + { + "epoch": 0.39, + "learning_rate": 1.5304261672960055e-05, + "loss": 1.4193, + "step": 3717 + }, + { + "epoch": 0.39, + "learning_rate": 1.5301158409739242e-05, + "loss": 1.3955, + "step": 3718 + }, + { + "epoch": 0.39, + "learning_rate": 1.5298054436299413e-05, + "loss": 1.4592, + "step": 3719 + }, + { + "epoch": 0.39, + "learning_rate": 1.529494975305642e-05, + "loss": 1.738, + "step": 3720 + }, + { + "epoch": 0.39, + "learning_rate": 1.529184436042621e-05, + "loss": 1.438, + "step": 3721 + }, + { + "epoch": 0.39, + "learning_rate": 1.528873825882482e-05, + "loss": 1.3445, + "step": 3722 + }, + { + "epoch": 0.39, + "learning_rate": 1.5285631448668395e-05, + "loss": 1.4168, + "step": 3723 + }, + { + "epoch": 0.39, + "learning_rate": 1.528252393037317e-05, + "loss": 1.4088, + "step": 3724 + }, + { + "epoch": 0.39, + "learning_rate": 1.5279415704355468e-05, + "loss": 1.4484, + "step": 3725 + }, + { + "epoch": 0.39, + "learning_rate": 1.5276306771031708e-05, + "loss": 1.4706, + "step": 3726 + }, + { + "epoch": 0.39, + "learning_rate": 1.527319713081841e-05, + "loss": 1.3466, + "step": 3727 + }, + { + "epoch": 0.39, + "learning_rate": 1.5270086784132196e-05, + "loss": 1.427, + "step": 3728 + }, + { + "epoch": 0.39, + "learning_rate": 1.5266975731389754e-05, + "loss": 1.4596, + "step": 3729 + }, + { + "epoch": 0.39, + "learning_rate": 1.52638639730079e-05, + "loss": 1.405, + "step": 3730 + }, + { + "epoch": 0.39, + "learning_rate": 1.5260751509403518e-05, + "loss": 1.4572, + "step": 3731 + }, + { + "epoch": 0.39, + "learning_rate": 1.5257638340993608e-05, + "loss": 1.3827, + "step": 3732 + }, + { + "epoch": 0.39, + "learning_rate": 1.5254524468195251e-05, + "loss": 1.3712, + "step": 3733 + }, + { + "epoch": 0.39, + "learning_rate": 1.5251409891425626e-05, + "loss": 1.4541, + "step": 3734 + }, + { + "epoch": 0.39, + "learning_rate": 1.5248294611102006e-05, + "loss": 1.5279, + "step": 3735 + }, + { + "epoch": 0.39, + "learning_rate": 1.5245178627641759e-05, + "loss": 1.3722, + "step": 3736 + }, + { + "epoch": 0.39, + "learning_rate": 1.5242061941462348e-05, + "loss": 1.5158, + "step": 3737 + }, + { + "epoch": 0.39, + "learning_rate": 1.523894455298132e-05, + "loss": 1.4274, + "step": 3738 + }, + { + "epoch": 0.39, + "learning_rate": 1.5235826462616338e-05, + "loss": 1.4543, + "step": 3739 + }, + { + "epoch": 0.39, + "learning_rate": 1.5232707670785144e-05, + "loss": 1.5011, + "step": 3740 + }, + { + "epoch": 0.39, + "learning_rate": 1.5229588177905568e-05, + "loss": 1.24, + "step": 3741 + }, + { + "epoch": 0.39, + "learning_rate": 1.5226467984395544e-05, + "loss": 1.4253, + "step": 3742 + }, + { + "epoch": 0.39, + "learning_rate": 1.5223347090673102e-05, + "loss": 1.3736, + "step": 3743 + }, + { + "epoch": 0.39, + "learning_rate": 1.522022549715636e-05, + "loss": 1.4587, + "step": 3744 + }, + { + "epoch": 0.39, + "learning_rate": 1.521710320426353e-05, + "loss": 1.5024, + "step": 3745 + }, + { + "epoch": 0.39, + "learning_rate": 1.521398021241292e-05, + "loss": 1.427, + "step": 3746 + }, + { + "epoch": 0.39, + "learning_rate": 1.5210856522022929e-05, + "loss": 1.3387, + "step": 3747 + }, + { + "epoch": 0.39, + "learning_rate": 1.5207732133512055e-05, + "loss": 1.3819, + "step": 3748 + }, + { + "epoch": 0.39, + "learning_rate": 1.5204607047298883e-05, + "loss": 1.4571, + "step": 3749 + }, + { + "epoch": 0.39, + "learning_rate": 1.5201481263802094e-05, + "loss": 1.3592, + "step": 3750 + }, + { + "epoch": 0.39, + "learning_rate": 1.5198354783440464e-05, + "loss": 1.3912, + "step": 3751 + }, + { + "epoch": 0.39, + "learning_rate": 1.519522760663286e-05, + "loss": 1.4986, + "step": 3752 + }, + { + "epoch": 0.39, + "learning_rate": 1.5192099733798243e-05, + "loss": 1.4106, + "step": 3753 + }, + { + "epoch": 0.39, + "learning_rate": 1.5188971165355667e-05, + "loss": 1.4145, + "step": 3754 + }, + { + "epoch": 0.39, + "learning_rate": 1.5185841901724282e-05, + "loss": 1.3915, + "step": 3755 + }, + { + "epoch": 0.39, + "learning_rate": 1.5182711943323329e-05, + "loss": 1.4014, + "step": 3756 + }, + { + "epoch": 0.39, + "learning_rate": 1.5179581290572141e-05, + "loss": 1.3651, + "step": 3757 + }, + { + "epoch": 0.39, + "learning_rate": 1.5176449943890147e-05, + "loss": 1.3653, + "step": 3758 + }, + { + "epoch": 0.39, + "learning_rate": 1.5173317903696862e-05, + "loss": 1.4486, + "step": 3759 + }, + { + "epoch": 0.39, + "learning_rate": 1.5170185170411906e-05, + "loss": 1.4459, + "step": 3760 + }, + { + "epoch": 0.39, + "learning_rate": 1.5167051744454977e-05, + "loss": 1.4215, + "step": 3761 + }, + { + "epoch": 0.39, + "learning_rate": 1.5163917626245877e-05, + "loss": 1.4379, + "step": 3762 + }, + { + "epoch": 0.39, + "learning_rate": 1.51607828162045e-05, + "loss": 1.4147, + "step": 3763 + }, + { + "epoch": 0.39, + "learning_rate": 1.5157647314750827e-05, + "loss": 1.4011, + "step": 3764 + }, + { + "epoch": 0.39, + "learning_rate": 1.5154511122304936e-05, + "loss": 1.4309, + "step": 3765 + }, + { + "epoch": 0.39, + "learning_rate": 1.5151374239286993e-05, + "loss": 1.4382, + "step": 3766 + }, + { + "epoch": 0.4, + "learning_rate": 1.5148236666117266e-05, + "loss": 1.405, + "step": 3767 + }, + { + "epoch": 0.4, + "learning_rate": 1.5145098403216104e-05, + "loss": 1.4223, + "step": 3768 + }, + { + "epoch": 0.4, + "learning_rate": 1.5141959451003951e-05, + "loss": 1.4084, + "step": 3769 + }, + { + "epoch": 0.4, + "learning_rate": 1.5138819809901356e-05, + "loss": 1.4063, + "step": 3770 + }, + { + "epoch": 0.4, + "learning_rate": 1.513567948032894e-05, + "loss": 1.3299, + "step": 3771 + }, + { + "epoch": 0.4, + "learning_rate": 1.5132538462707431e-05, + "loss": 1.3901, + "step": 3772 + }, + { + "epoch": 0.4, + "learning_rate": 1.5129396757457646e-05, + "loss": 1.4249, + "step": 3773 + }, + { + "epoch": 0.4, + "learning_rate": 1.512625436500049e-05, + "loss": 1.4087, + "step": 3774 + }, + { + "epoch": 0.4, + "learning_rate": 1.5123111285756964e-05, + "loss": 1.3521, + "step": 3775 + }, + { + "epoch": 0.4, + "learning_rate": 1.5119967520148163e-05, + "loss": 1.4097, + "step": 3776 + }, + { + "epoch": 0.4, + "learning_rate": 1.5116823068595261e-05, + "loss": 1.4871, + "step": 3777 + }, + { + "epoch": 0.4, + "learning_rate": 1.5113677931519543e-05, + "loss": 1.44, + "step": 3778 + }, + { + "epoch": 0.4, + "learning_rate": 1.5110532109342377e-05, + "loss": 1.4518, + "step": 3779 + }, + { + "epoch": 0.4, + "learning_rate": 1.5107385602485214e-05, + "loss": 1.3961, + "step": 3780 + }, + { + "epoch": 0.4, + "learning_rate": 1.5104238411369614e-05, + "loss": 1.4341, + "step": 3781 + }, + { + "epoch": 0.4, + "eval_loss": 1.4642821550369263, + "eval_runtime": 77.3595, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 3781 + }, + { + "epoch": 0.4, + "learning_rate": 1.5101090536417218e-05, + "loss": 1.403, + "step": 3782 + }, + { + "epoch": 0.4, + "learning_rate": 1.5097941978049754e-05, + "loss": 1.4103, + "step": 3783 + }, + { + "epoch": 0.4, + "learning_rate": 1.5094792736689052e-05, + "loss": 1.3478, + "step": 3784 + }, + { + "epoch": 0.4, + "learning_rate": 1.5091642812757035e-05, + "loss": 1.4134, + "step": 3785 + }, + { + "epoch": 0.4, + "learning_rate": 1.5088492206675701e-05, + "loss": 1.4134, + "step": 3786 + }, + { + "epoch": 0.4, + "learning_rate": 1.5085340918867162e-05, + "loss": 1.1494, + "step": 3787 + }, + { + "epoch": 0.4, + "learning_rate": 1.5082188949753598e-05, + "loss": 1.2385, + "step": 3788 + }, + { + "epoch": 0.4, + "learning_rate": 1.5079036299757299e-05, + "loss": 1.4258, + "step": 3789 + }, + { + "epoch": 0.4, + "learning_rate": 1.5075882969300639e-05, + "loss": 1.3781, + "step": 3790 + }, + { + "epoch": 0.4, + "learning_rate": 1.507272895880608e-05, + "loss": 1.5096, + "step": 3791 + }, + { + "epoch": 0.4, + "learning_rate": 1.5069574268696179e-05, + "loss": 1.366, + "step": 3792 + }, + { + "epoch": 0.4, + "learning_rate": 1.5066418899393584e-05, + "loss": 1.3792, + "step": 3793 + }, + { + "epoch": 0.4, + "learning_rate": 1.506326285132104e-05, + "loss": 1.4987, + "step": 3794 + }, + { + "epoch": 0.4, + "learning_rate": 1.5060106124901364e-05, + "loss": 1.445, + "step": 3795 + }, + { + "epoch": 0.4, + "learning_rate": 1.5056948720557482e-05, + "loss": 1.5071, + "step": 3796 + }, + { + "epoch": 0.4, + "learning_rate": 1.505379063871241e-05, + "loss": 1.4029, + "step": 3797 + }, + { + "epoch": 0.4, + "learning_rate": 1.5050631879789244e-05, + "loss": 1.5263, + "step": 3798 + }, + { + "epoch": 0.4, + "learning_rate": 1.5047472444211175e-05, + "loss": 1.3906, + "step": 3799 + }, + { + "epoch": 0.4, + "learning_rate": 1.5044312332401494e-05, + "loss": 1.7352, + "step": 3800 + }, + { + "epoch": 0.4, + "learning_rate": 1.5041151544783565e-05, + "loss": 1.3946, + "step": 3801 + }, + { + "epoch": 0.4, + "learning_rate": 1.5037990081780862e-05, + "loss": 1.3592, + "step": 3802 + }, + { + "epoch": 0.4, + "learning_rate": 1.503482794381693e-05, + "loss": 1.3991, + "step": 3803 + }, + { + "epoch": 0.4, + "learning_rate": 1.5031665131315423e-05, + "loss": 1.4271, + "step": 3804 + }, + { + "epoch": 0.4, + "learning_rate": 1.502850164470007e-05, + "loss": 1.4305, + "step": 3805 + }, + { + "epoch": 0.4, + "learning_rate": 1.5025337484394701e-05, + "loss": 1.4116, + "step": 3806 + }, + { + "epoch": 0.4, + "learning_rate": 1.5022172650823232e-05, + "loss": 1.4242, + "step": 3807 + }, + { + "epoch": 0.4, + "learning_rate": 1.5019007144409667e-05, + "loss": 1.4427, + "step": 3808 + }, + { + "epoch": 0.4, + "learning_rate": 1.5015840965578106e-05, + "loss": 1.3705, + "step": 3809 + }, + { + "epoch": 0.4, + "learning_rate": 1.5012674114752732e-05, + "loss": 1.4498, + "step": 3810 + }, + { + "epoch": 0.4, + "learning_rate": 1.5009506592357822e-05, + "loss": 1.489, + "step": 3811 + }, + { + "epoch": 0.4, + "learning_rate": 1.5006338398817746e-05, + "loss": 1.4801, + "step": 3812 + }, + { + "epoch": 0.4, + "learning_rate": 1.5003169534556956e-05, + "loss": 1.3468, + "step": 3813 + }, + { + "epoch": 0.4, + "learning_rate": 1.5000000000000002e-05, + "loss": 1.4211, + "step": 3814 + }, + { + "epoch": 0.4, + "learning_rate": 1.4996829795571518e-05, + "loss": 1.4683, + "step": 3815 + }, + { + "epoch": 0.4, + "learning_rate": 1.499365892169623e-05, + "loss": 1.4441, + "step": 3816 + }, + { + "epoch": 0.4, + "learning_rate": 1.4990487378798958e-05, + "loss": 1.4368, + "step": 3817 + }, + { + "epoch": 0.4, + "learning_rate": 1.4987315167304602e-05, + "loss": 1.4097, + "step": 3818 + }, + { + "epoch": 0.4, + "learning_rate": 1.4984142287638155e-05, + "loss": 1.4238, + "step": 3819 + }, + { + "epoch": 0.4, + "learning_rate": 1.4980968740224708e-05, + "loss": 1.497, + "step": 3820 + }, + { + "epoch": 0.4, + "learning_rate": 1.4977794525489433e-05, + "loss": 1.3989, + "step": 3821 + }, + { + "epoch": 0.4, + "learning_rate": 1.4974619643857588e-05, + "loss": 1.4415, + "step": 3822 + }, + { + "epoch": 0.4, + "learning_rate": 1.4971444095754533e-05, + "loss": 1.3931, + "step": 3823 + }, + { + "epoch": 0.4, + "learning_rate": 1.4968267881605705e-05, + "loss": 1.3426, + "step": 3824 + }, + { + "epoch": 0.4, + "learning_rate": 1.4965091001836636e-05, + "loss": 1.644, + "step": 3825 + }, + { + "epoch": 0.4, + "learning_rate": 1.4961913456872945e-05, + "loss": 1.3903, + "step": 3826 + }, + { + "epoch": 0.4, + "learning_rate": 1.4958735247140345e-05, + "loss": 1.3764, + "step": 3827 + }, + { + "epoch": 0.4, + "learning_rate": 1.4955556373064632e-05, + "loss": 1.5484, + "step": 3828 + }, + { + "epoch": 0.4, + "learning_rate": 1.4952376835071696e-05, + "loss": 1.5696, + "step": 3829 + }, + { + "epoch": 0.4, + "learning_rate": 1.4949196633587509e-05, + "loss": 1.3844, + "step": 3830 + }, + { + "epoch": 0.4, + "learning_rate": 1.494601576903814e-05, + "loss": 1.3868, + "step": 3831 + }, + { + "epoch": 0.4, + "learning_rate": 1.4942834241849741e-05, + "loss": 1.4229, + "step": 3832 + }, + { + "epoch": 0.4, + "learning_rate": 1.4939652052448557e-05, + "loss": 1.4062, + "step": 3833 + }, + { + "epoch": 0.4, + "learning_rate": 1.4936469201260915e-05, + "loss": 1.3955, + "step": 3834 + }, + { + "epoch": 0.4, + "learning_rate": 1.4933285688713239e-05, + "loss": 1.3959, + "step": 3835 + }, + { + "epoch": 0.4, + "learning_rate": 1.4930101515232038e-05, + "loss": 1.4652, + "step": 3836 + }, + { + "epoch": 0.4, + "learning_rate": 1.4926916681243913e-05, + "loss": 1.5253, + "step": 3837 + }, + { + "epoch": 0.4, + "learning_rate": 1.4923731187175539e-05, + "loss": 1.4694, + "step": 3838 + }, + { + "epoch": 0.4, + "learning_rate": 1.4920545033453702e-05, + "loss": 1.3859, + "step": 3839 + }, + { + "epoch": 0.4, + "learning_rate": 1.4917358220505259e-05, + "loss": 1.4157, + "step": 3840 + }, + { + "epoch": 0.4, + "learning_rate": 1.4914170748757159e-05, + "loss": 1.4491, + "step": 3841 + }, + { + "epoch": 0.4, + "learning_rate": 1.4910982618636445e-05, + "loss": 1.4464, + "step": 3842 + }, + { + "epoch": 0.4, + "learning_rate": 1.4907793830570246e-05, + "loss": 1.3771, + "step": 3843 + }, + { + "epoch": 0.4, + "learning_rate": 1.4904604384985775e-05, + "loss": 1.3673, + "step": 3844 + }, + { + "epoch": 0.4, + "learning_rate": 1.4901414282310334e-05, + "loss": 1.4429, + "step": 3845 + }, + { + "epoch": 0.4, + "learning_rate": 1.4898223522971318e-05, + "loss": 1.4905, + "step": 3846 + }, + { + "epoch": 0.4, + "learning_rate": 1.4895032107396205e-05, + "loss": 1.4039, + "step": 3847 + }, + { + "epoch": 0.4, + "learning_rate": 1.4891840036012566e-05, + "loss": 1.4082, + "step": 3848 + }, + { + "epoch": 0.4, + "learning_rate": 1.4888647309248052e-05, + "loss": 1.3643, + "step": 3849 + }, + { + "epoch": 0.4, + "learning_rate": 1.4885453927530408e-05, + "loss": 1.3116, + "step": 3850 + }, + { + "epoch": 0.4, + "learning_rate": 1.4882259891287467e-05, + "loss": 1.4278, + "step": 3851 + }, + { + "epoch": 0.4, + "learning_rate": 1.4879065200947148e-05, + "loss": 1.3712, + "step": 3852 + }, + { + "epoch": 0.4, + "learning_rate": 1.4875869856937449e-05, + "loss": 1.387, + "step": 3853 + }, + { + "epoch": 0.4, + "learning_rate": 1.4872673859686475e-05, + "loss": 1.5053, + "step": 3854 + }, + { + "epoch": 0.4, + "learning_rate": 1.4869477209622404e-05, + "loss": 1.4427, + "step": 3855 + }, + { + "epoch": 0.4, + "learning_rate": 1.4866279907173502e-05, + "loss": 1.3404, + "step": 3856 + }, + { + "epoch": 0.4, + "learning_rate": 1.4863081952768126e-05, + "loss": 1.3126, + "step": 3857 + }, + { + "epoch": 0.4, + "learning_rate": 1.4859883346834725e-05, + "loss": 1.4588, + "step": 3858 + }, + { + "epoch": 0.4, + "learning_rate": 1.4856684089801822e-05, + "loss": 1.408, + "step": 3859 + }, + { + "epoch": 0.4, + "learning_rate": 1.4853484182098044e-05, + "loss": 1.4356, + "step": 3860 + }, + { + "epoch": 0.4, + "learning_rate": 1.4850283624152088e-05, + "loss": 1.3768, + "step": 3861 + }, + { + "epoch": 0.4, + "learning_rate": 1.4847082416392753e-05, + "loss": 1.4563, + "step": 3862 + }, + { + "epoch": 0.41, + "learning_rate": 1.4843880559248915e-05, + "loss": 1.3648, + "step": 3863 + }, + { + "epoch": 0.41, + "learning_rate": 1.4840678053149542e-05, + "loss": 1.4146, + "step": 3864 + }, + { + "epoch": 0.41, + "learning_rate": 1.4837474898523686e-05, + "loss": 1.4423, + "step": 3865 + }, + { + "epoch": 0.41, + "learning_rate": 1.4834271095800487e-05, + "loss": 1.3351, + "step": 3866 + }, + { + "epoch": 0.41, + "learning_rate": 1.4831066645409178e-05, + "loss": 1.4534, + "step": 3867 + }, + { + "epoch": 0.41, + "learning_rate": 1.4827861547779066e-05, + "loss": 1.4763, + "step": 3868 + }, + { + "epoch": 0.41, + "learning_rate": 1.4824655803339553e-05, + "loss": 1.4019, + "step": 3869 + }, + { + "epoch": 0.41, + "learning_rate": 1.4821449412520132e-05, + "loss": 1.4223, + "step": 3870 + }, + { + "epoch": 0.41, + "learning_rate": 1.4818242375750371e-05, + "loss": 1.4065, + "step": 3871 + }, + { + "epoch": 0.41, + "learning_rate": 1.481503469345993e-05, + "loss": 1.587, + "step": 3872 + }, + { + "epoch": 0.41, + "learning_rate": 1.4811826366078562e-05, + "loss": 1.3746, + "step": 3873 + }, + { + "epoch": 0.41, + "learning_rate": 1.4808617394036096e-05, + "loss": 1.3425, + "step": 3874 + }, + { + "epoch": 0.41, + "learning_rate": 1.480540777776245e-05, + "loss": 0.6637, + "step": 3875 + }, + { + "epoch": 0.41, + "learning_rate": 1.4802197517687634e-05, + "loss": 1.3366, + "step": 3876 + }, + { + "epoch": 0.41, + "learning_rate": 1.479898661424174e-05, + "loss": 1.4033, + "step": 3877 + }, + { + "epoch": 0.41, + "learning_rate": 1.4795775067854947e-05, + "loss": 1.4005, + "step": 3878 + }, + { + "epoch": 0.41, + "learning_rate": 1.4792562878957516e-05, + "loss": 1.3651, + "step": 3879 + }, + { + "epoch": 0.41, + "learning_rate": 1.47893500479798e-05, + "loss": 1.4185, + "step": 3880 + }, + { + "epoch": 0.41, + "learning_rate": 1.4786136575352236e-05, + "loss": 1.4394, + "step": 3881 + }, + { + "epoch": 0.41, + "learning_rate": 1.478292246150535e-05, + "loss": 1.7243, + "step": 3882 + }, + { + "epoch": 0.41, + "learning_rate": 1.4779707706869744e-05, + "loss": 1.3574, + "step": 3883 + }, + { + "epoch": 0.41, + "learning_rate": 1.4776492311876116e-05, + "loss": 1.4031, + "step": 3884 + }, + { + "epoch": 0.41, + "learning_rate": 1.4773276276955248e-05, + "loss": 1.4351, + "step": 3885 + }, + { + "epoch": 0.41, + "learning_rate": 1.4770059602538002e-05, + "loss": 1.3922, + "step": 3886 + }, + { + "epoch": 0.41, + "learning_rate": 1.4766842289055333e-05, + "loss": 1.3374, + "step": 3887 + }, + { + "epoch": 0.41, + "learning_rate": 1.4763624336938278e-05, + "loss": 1.428, + "step": 3888 + }, + { + "epoch": 0.41, + "learning_rate": 1.476040574661796e-05, + "loss": 1.6087, + "step": 3889 + }, + { + "epoch": 0.41, + "learning_rate": 1.4757186518525586e-05, + "loss": 1.4054, + "step": 3890 + }, + { + "epoch": 0.41, + "learning_rate": 1.4753966653092447e-05, + "loss": 1.2595, + "step": 3891 + }, + { + "epoch": 0.41, + "learning_rate": 1.475074615074993e-05, + "loss": 1.4052, + "step": 3892 + }, + { + "epoch": 0.41, + "learning_rate": 1.4747525011929492e-05, + "loss": 1.4296, + "step": 3893 + }, + { + "epoch": 0.41, + "learning_rate": 1.4744303237062689e-05, + "loss": 1.3718, + "step": 3894 + }, + { + "epoch": 0.41, + "learning_rate": 1.4741080826581151e-05, + "loss": 1.4498, + "step": 3895 + }, + { + "epoch": 0.41, + "learning_rate": 1.4737857780916602e-05, + "loss": 1.4029, + "step": 3896 + }, + { + "epoch": 0.41, + "learning_rate": 1.4734634100500846e-05, + "loss": 1.4136, + "step": 3897 + }, + { + "epoch": 0.41, + "learning_rate": 1.4731409785765774e-05, + "loss": 1.348, + "step": 3898 + }, + { + "epoch": 0.41, + "learning_rate": 1.4728184837143355e-05, + "loss": 1.3407, + "step": 3899 + }, + { + "epoch": 0.41, + "learning_rate": 1.472495925506566e-05, + "loss": 1.3737, + "step": 3900 + }, + { + "epoch": 0.41, + "learning_rate": 1.4721733039964826e-05, + "loss": 2.2305, + "step": 3901 + }, + { + "epoch": 0.41, + "learning_rate": 1.4718506192273087e-05, + "loss": 1.4506, + "step": 3902 + }, + { + "epoch": 0.41, + "learning_rate": 1.4715278712422754e-05, + "loss": 1.3657, + "step": 3903 + }, + { + "epoch": 0.41, + "learning_rate": 1.471205060084623e-05, + "loss": 1.4644, + "step": 3904 + }, + { + "epoch": 0.41, + "learning_rate": 1.4708821857976001e-05, + "loss": 1.4823, + "step": 3905 + }, + { + "epoch": 0.41, + "learning_rate": 1.4705592484244628e-05, + "loss": 1.3392, + "step": 3906 + }, + { + "epoch": 0.41, + "learning_rate": 1.4702362480084769e-05, + "loss": 1.3302, + "step": 3907 + }, + { + "epoch": 0.41, + "learning_rate": 1.4699131845929163e-05, + "loss": 1.8952, + "step": 3908 + }, + { + "epoch": 0.41, + "learning_rate": 1.469590058221063e-05, + "loss": 1.4982, + "step": 3909 + }, + { + "epoch": 0.41, + "learning_rate": 1.4692668689362074e-05, + "loss": 1.407, + "step": 3910 + }, + { + "epoch": 0.41, + "learning_rate": 1.4689436167816489e-05, + "loss": 1.3911, + "step": 3911 + }, + { + "epoch": 0.41, + "learning_rate": 1.4686203018006948e-05, + "loss": 1.3421, + "step": 3912 + }, + { + "epoch": 0.41, + "learning_rate": 1.4682969240366612e-05, + "loss": 1.4627, + "step": 3913 + }, + { + "epoch": 0.41, + "learning_rate": 1.4679734835328718e-05, + "loss": 1.394, + "step": 3914 + }, + { + "epoch": 0.41, + "learning_rate": 1.4676499803326603e-05, + "loss": 1.4484, + "step": 3915 + }, + { + "epoch": 0.41, + "learning_rate": 1.4673264144793673e-05, + "loss": 1.4665, + "step": 3916 + }, + { + "epoch": 0.41, + "learning_rate": 1.4670027860163422e-05, + "loss": 1.3191, + "step": 3917 + }, + { + "epoch": 0.41, + "learning_rate": 1.466679094986943e-05, + "loss": 1.4748, + "step": 3918 + }, + { + "epoch": 0.41, + "learning_rate": 1.4663553414345361e-05, + "loss": 1.2467, + "step": 3919 + }, + { + "epoch": 0.41, + "learning_rate": 1.466031525402496e-05, + "loss": 1.4279, + "step": 3920 + }, + { + "epoch": 0.41, + "learning_rate": 1.4657076469342059e-05, + "loss": 1.3822, + "step": 3921 + }, + { + "epoch": 0.41, + "learning_rate": 1.4653837060730566e-05, + "loss": 1.3659, + "step": 3922 + }, + { + "epoch": 0.41, + "learning_rate": 1.465059702862449e-05, + "loss": 1.3663, + "step": 3923 + }, + { + "epoch": 0.41, + "learning_rate": 1.4647356373457902e-05, + "loss": 1.4371, + "step": 3924 + }, + { + "epoch": 0.41, + "learning_rate": 1.4644115095664972e-05, + "loss": 1.3473, + "step": 3925 + }, + { + "epoch": 0.41, + "learning_rate": 1.4640873195679944e-05, + "loss": 1.4797, + "step": 3926 + }, + { + "epoch": 0.41, + "learning_rate": 1.463763067393715e-05, + "loss": 1.3973, + "step": 3927 + }, + { + "epoch": 0.41, + "learning_rate": 1.4634387530871008e-05, + "loss": 1.3899, + "step": 3928 + }, + { + "epoch": 0.41, + "learning_rate": 1.4631143766916015e-05, + "loss": 1.3828, + "step": 3929 + }, + { + "epoch": 0.41, + "learning_rate": 1.4627899382506745e-05, + "loss": 1.4569, + "step": 3930 + }, + { + "epoch": 0.41, + "learning_rate": 1.4624654378077872e-05, + "loss": 1.4011, + "step": 3931 + }, + { + "epoch": 0.41, + "learning_rate": 1.462140875406414e-05, + "loss": 1.3859, + "step": 3932 + }, + { + "epoch": 0.41, + "learning_rate": 1.4618162510900376e-05, + "loss": 1.4518, + "step": 3933 + }, + { + "epoch": 0.41, + "learning_rate": 1.4614915649021493e-05, + "loss": 1.4399, + "step": 3934 + }, + { + "epoch": 0.41, + "learning_rate": 1.4611668168862495e-05, + "loss": 1.4034, + "step": 3935 + }, + { + "epoch": 0.41, + "learning_rate": 1.4608420070858452e-05, + "loss": 1.3919, + "step": 3936 + }, + { + "epoch": 0.41, + "learning_rate": 1.4605171355444528e-05, + "loss": 1.391, + "step": 3937 + }, + { + "epoch": 0.41, + "learning_rate": 1.460192202305597e-05, + "loss": 1.3717, + "step": 3938 + }, + { + "epoch": 0.41, + "learning_rate": 1.4598672074128103e-05, + "loss": 1.4351, + "step": 3939 + }, + { + "epoch": 0.41, + "learning_rate": 1.4595421509096339e-05, + "loss": 1.4202, + "step": 3940 + }, + { + "epoch": 0.41, + "learning_rate": 1.4592170328396165e-05, + "loss": 1.3559, + "step": 3941 + }, + { + "epoch": 0.41, + "learning_rate": 1.458891853246316e-05, + "loss": 1.5878, + "step": 3942 + }, + { + "epoch": 0.41, + "learning_rate": 1.4585666121732982e-05, + "loss": 1.3818, + "step": 3943 + }, + { + "epoch": 0.41, + "learning_rate": 1.4582413096641369e-05, + "loss": 1.4009, + "step": 3944 + }, + { + "epoch": 0.41, + "learning_rate": 1.457915945762414e-05, + "loss": 1.3937, + "step": 3945 + }, + { + "epoch": 0.41, + "learning_rate": 1.4575905205117203e-05, + "loss": 1.381, + "step": 3946 + }, + { + "epoch": 0.41, + "learning_rate": 1.457265033955654e-05, + "loss": 1.3844, + "step": 3947 + }, + { + "epoch": 0.41, + "learning_rate": 1.4569394861378226e-05, + "loss": 1.4059, + "step": 3948 + }, + { + "epoch": 0.41, + "learning_rate": 1.4566138771018403e-05, + "loss": 1.3698, + "step": 3949 + }, + { + "epoch": 0.41, + "learning_rate": 1.4562882068913311e-05, + "loss": 1.4253, + "step": 3950 + }, + { + "epoch": 0.41, + "learning_rate": 1.455962475549926e-05, + "loss": 1.4284, + "step": 3951 + }, + { + "epoch": 0.41, + "learning_rate": 1.4556366831212647e-05, + "loss": 1.4279, + "step": 3952 + }, + { + "epoch": 0.41, + "learning_rate": 1.4553108296489951e-05, + "loss": 1.3072, + "step": 3953 + }, + { + "epoch": 0.41, + "learning_rate": 1.4549849151767731e-05, + "loss": 1.4175, + "step": 3954 + }, + { + "epoch": 0.41, + "learning_rate": 1.4546589397482632e-05, + "loss": 1.5042, + "step": 3955 + }, + { + "epoch": 0.41, + "learning_rate": 1.4543329034071371e-05, + "loss": 1.4363, + "step": 3956 + }, + { + "epoch": 0.41, + "learning_rate": 1.454006806197076e-05, + "loss": 1.4111, + "step": 3957 + }, + { + "epoch": 0.42, + "learning_rate": 1.453680648161768e-05, + "loss": 1.3817, + "step": 3958 + }, + { + "epoch": 0.42, + "learning_rate": 1.45335442934491e-05, + "loss": 1.4689, + "step": 3959 + }, + { + "epoch": 0.42, + "learning_rate": 1.4530281497902072e-05, + "loss": 1.4164, + "step": 3960 + }, + { + "epoch": 0.42, + "learning_rate": 1.4527018095413726e-05, + "loss": 1.3943, + "step": 3961 + }, + { + "epoch": 0.42, + "learning_rate": 1.4523754086421271e-05, + "loss": 1.3851, + "step": 3962 + }, + { + "epoch": 0.42, + "learning_rate": 1.4520489471362003e-05, + "loss": 1.3907, + "step": 3963 + }, + { + "epoch": 0.42, + "learning_rate": 1.4517224250673297e-05, + "loss": 1.2877, + "step": 3964 + }, + { + "epoch": 0.42, + "learning_rate": 1.4513958424792605e-05, + "loss": 1.4696, + "step": 3965 + }, + { + "epoch": 0.42, + "learning_rate": 1.4510691994157471e-05, + "loss": 1.3785, + "step": 3966 + }, + { + "epoch": 0.42, + "learning_rate": 1.4507424959205505e-05, + "loss": 1.3652, + "step": 3967 + }, + { + "epoch": 0.42, + "learning_rate": 1.4504157320374408e-05, + "loss": 1.4198, + "step": 3968 + }, + { + "epoch": 0.42, + "learning_rate": 1.4500889078101962e-05, + "loss": 1.3476, + "step": 3969 + }, + { + "epoch": 0.42, + "learning_rate": 1.4497620232826028e-05, + "loss": 1.4356, + "step": 3970 + }, + { + "epoch": 0.42, + "learning_rate": 1.4494350784984543e-05, + "loss": 1.4993, + "step": 3971 + }, + { + "epoch": 0.42, + "learning_rate": 1.4491080735015533e-05, + "loss": 1.4022, + "step": 3972 + }, + { + "epoch": 0.42, + "learning_rate": 1.44878100833571e-05, + "loss": 1.4074, + "step": 3973 + }, + { + "epoch": 0.42, + "learning_rate": 1.4484538830447423e-05, + "loss": 1.412, + "step": 3974 + }, + { + "epoch": 0.42, + "learning_rate": 1.4481266976724772e-05, + "loss": 1.3872, + "step": 3975 + }, + { + "epoch": 0.42, + "learning_rate": 1.4477994522627485e-05, + "loss": 1.4575, + "step": 3976 + }, + { + "epoch": 0.42, + "learning_rate": 1.4474721468593995e-05, + "loss": 1.3768, + "step": 3977 + }, + { + "epoch": 0.42, + "learning_rate": 1.44714478150628e-05, + "loss": 1.4173, + "step": 3978 + }, + { + "epoch": 0.42, + "learning_rate": 1.4468173562472489e-05, + "loss": 1.3896, + "step": 3979 + }, + { + "epoch": 0.42, + "learning_rate": 1.4464898711261725e-05, + "loss": 1.4535, + "step": 3980 + }, + { + "epoch": 0.42, + "eval_loss": 1.4580057859420776, + "eval_runtime": 77.4537, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 3980 + }, + { + "epoch": 0.42, + "learning_rate": 1.4461623261869258e-05, + "loss": 1.4046, + "step": 3981 + }, + { + "epoch": 0.42, + "learning_rate": 1.445834721473391e-05, + "loss": 1.37, + "step": 3982 + }, + { + "epoch": 0.42, + "learning_rate": 1.4455070570294588e-05, + "loss": 1.4566, + "step": 3983 + }, + { + "epoch": 0.42, + "learning_rate": 1.445179332899028e-05, + "loss": 1.4513, + "step": 3984 + }, + { + "epoch": 0.42, + "learning_rate": 1.4448515491260051e-05, + "loss": 1.3893, + "step": 3985 + }, + { + "epoch": 0.42, + "learning_rate": 1.4445237057543047e-05, + "loss": 1.3955, + "step": 3986 + }, + { + "epoch": 0.42, + "learning_rate": 1.4441958028278493e-05, + "loss": 1.4861, + "step": 3987 + }, + { + "epoch": 0.42, + "learning_rate": 1.4438678403905697e-05, + "loss": 1.4601, + "step": 3988 + }, + { + "epoch": 0.42, + "learning_rate": 1.4435398184864043e-05, + "loss": 1.398, + "step": 3989 + }, + { + "epoch": 0.42, + "learning_rate": 1.4432117371592995e-05, + "loss": 1.4392, + "step": 3990 + }, + { + "epoch": 0.42, + "learning_rate": 1.4428835964532098e-05, + "loss": 1.3772, + "step": 3991 + }, + { + "epoch": 0.42, + "learning_rate": 1.4425553964120979e-05, + "loss": 1.4241, + "step": 3992 + }, + { + "epoch": 0.42, + "learning_rate": 1.4422271370799338e-05, + "loss": 1.3237, + "step": 3993 + }, + { + "epoch": 0.42, + "learning_rate": 1.4418988185006964e-05, + "loss": 1.3813, + "step": 3994 + }, + { + "epoch": 0.42, + "learning_rate": 1.4415704407183709e-05, + "loss": 1.6139, + "step": 3995 + }, + { + "epoch": 0.42, + "learning_rate": 1.4412420037769525e-05, + "loss": 1.4431, + "step": 3996 + }, + { + "epoch": 0.42, + "learning_rate": 1.440913507720443e-05, + "loss": 1.3862, + "step": 3997 + }, + { + "epoch": 0.42, + "learning_rate": 1.4405849525928523e-05, + "loss": 1.3895, + "step": 3998 + }, + { + "epoch": 0.42, + "learning_rate": 1.4402563384381981e-05, + "loss": 1.4068, + "step": 3999 + }, + { + "epoch": 0.42, + "learning_rate": 1.4399276653005072e-05, + "loss": 1.4501, + "step": 4000 + }, + { + "epoch": 0.42, + "learning_rate": 1.4395989332238124e-05, + "loss": 1.3165, + "step": 4001 + }, + { + "epoch": 0.42, + "learning_rate": 1.4392701422521555e-05, + "loss": 1.3783, + "step": 4002 + }, + { + "epoch": 0.42, + "learning_rate": 1.4389412924295865e-05, + "loss": 1.343, + "step": 4003 + }, + { + "epoch": 0.42, + "learning_rate": 1.4386123838001625e-05, + "loss": 1.3456, + "step": 4004 + }, + { + "epoch": 0.42, + "learning_rate": 1.4382834164079486e-05, + "loss": 1.3689, + "step": 4005 + }, + { + "epoch": 0.42, + "learning_rate": 1.4379543902970183e-05, + "loss": 1.3789, + "step": 4006 + }, + { + "epoch": 0.42, + "learning_rate": 1.4376253055114528e-05, + "loss": 1.4912, + "step": 4007 + }, + { + "epoch": 0.42, + "learning_rate": 1.4372961620953407e-05, + "loss": 1.3692, + "step": 4008 + }, + { + "epoch": 0.42, + "learning_rate": 1.436966960092779e-05, + "loss": 1.4901, + "step": 4009 + }, + { + "epoch": 0.42, + "learning_rate": 1.4366376995478717e-05, + "loss": 1.4431, + "step": 4010 + }, + { + "epoch": 0.42, + "learning_rate": 1.436308380504732e-05, + "loss": 1.4626, + "step": 4011 + }, + { + "epoch": 0.42, + "learning_rate": 1.4359790030074798e-05, + "loss": 1.4241, + "step": 4012 + }, + { + "epoch": 0.42, + "learning_rate": 1.4356495671002435e-05, + "loss": 1.3834, + "step": 4013 + }, + { + "epoch": 0.42, + "learning_rate": 1.4353200728271586e-05, + "loss": 1.3626, + "step": 4014 + }, + { + "epoch": 0.42, + "learning_rate": 1.4349905202323692e-05, + "loss": 1.3557, + "step": 4015 + }, + { + "epoch": 0.42, + "learning_rate": 1.434660909360027e-05, + "loss": 1.4077, + "step": 4016 + }, + { + "epoch": 0.42, + "learning_rate": 1.4343312402542911e-05, + "loss": 1.4337, + "step": 4017 + }, + { + "epoch": 0.42, + "learning_rate": 1.4340015129593286e-05, + "loss": 1.419, + "step": 4018 + }, + { + "epoch": 0.42, + "learning_rate": 1.4336717275193148e-05, + "loss": 1.3768, + "step": 4019 + }, + { + "epoch": 0.42, + "learning_rate": 1.4333418839784326e-05, + "loss": 1.383, + "step": 4020 + }, + { + "epoch": 0.42, + "learning_rate": 1.4330119823808719e-05, + "loss": 1.3951, + "step": 4021 + }, + { + "epoch": 0.42, + "learning_rate": 1.4326820227708316e-05, + "loss": 1.3985, + "step": 4022 + }, + { + "epoch": 0.42, + "learning_rate": 1.4323520051925177e-05, + "loss": 1.356, + "step": 4023 + }, + { + "epoch": 0.42, + "learning_rate": 1.4320219296901439e-05, + "loss": 1.5017, + "step": 4024 + }, + { + "epoch": 0.42, + "learning_rate": 1.4316917963079322e-05, + "loss": 1.3594, + "step": 4025 + }, + { + "epoch": 0.42, + "learning_rate": 1.4313616050901114e-05, + "loss": 1.6028, + "step": 4026 + }, + { + "epoch": 0.42, + "learning_rate": 1.4310313560809193e-05, + "loss": 1.4132, + "step": 4027 + }, + { + "epoch": 0.42, + "learning_rate": 1.4307010493246006e-05, + "loss": 1.2969, + "step": 4028 + }, + { + "epoch": 0.42, + "learning_rate": 1.4303706848654073e-05, + "loss": 1.5224, + "step": 4029 + }, + { + "epoch": 0.42, + "learning_rate": 1.4300402627476007e-05, + "loss": 1.3386, + "step": 4030 + }, + { + "epoch": 0.42, + "learning_rate": 1.429709783015448e-05, + "loss": 1.3554, + "step": 4031 + }, + { + "epoch": 0.42, + "learning_rate": 1.4293792457132259e-05, + "loss": 1.3386, + "step": 4032 + }, + { + "epoch": 0.42, + "learning_rate": 1.429048650885217e-05, + "loss": 1.4613, + "step": 4033 + }, + { + "epoch": 0.42, + "learning_rate": 1.4287179985757132e-05, + "loss": 1.3632, + "step": 4034 + }, + { + "epoch": 0.42, + "learning_rate": 1.428387288829013e-05, + "loss": 1.3835, + "step": 4035 + }, + { + "epoch": 0.42, + "learning_rate": 1.4280565216894234e-05, + "loss": 1.3711, + "step": 4036 + }, + { + "epoch": 0.42, + "learning_rate": 1.4277256972012582e-05, + "loss": 1.3385, + "step": 4037 + }, + { + "epoch": 0.42, + "learning_rate": 1.4273948154088395e-05, + "loss": 1.4607, + "step": 4038 + }, + { + "epoch": 0.42, + "learning_rate": 1.4270638763564973e-05, + "loss": 1.4042, + "step": 4039 + }, + { + "epoch": 0.42, + "learning_rate": 1.4267328800885687e-05, + "loss": 1.4006, + "step": 4040 + }, + { + "epoch": 0.42, + "learning_rate": 1.4264018266493987e-05, + "loss": 1.386, + "step": 4041 + }, + { + "epoch": 0.42, + "learning_rate": 1.4260707160833401e-05, + "loss": 1.3487, + "step": 4042 + }, + { + "epoch": 0.42, + "learning_rate": 1.4257395484347529e-05, + "loss": 1.4199, + "step": 4043 + }, + { + "epoch": 0.42, + "learning_rate": 1.4254083237480054e-05, + "loss": 1.3236, + "step": 4044 + }, + { + "epoch": 0.42, + "learning_rate": 1.4250770420674726e-05, + "loss": 1.4056, + "step": 4045 + }, + { + "epoch": 0.42, + "learning_rate": 1.4247457034375387e-05, + "loss": 1.4391, + "step": 4046 + }, + { + "epoch": 0.42, + "learning_rate": 1.4244143079025938e-05, + "loss": 1.3935, + "step": 4047 + }, + { + "epoch": 0.42, + "learning_rate": 1.4240828555070368e-05, + "loss": 1.3623, + "step": 4048 + }, + { + "epoch": 0.42, + "learning_rate": 1.4237513462952733e-05, + "loss": 1.3254, + "step": 4049 + }, + { + "epoch": 0.42, + "learning_rate": 1.4234197803117174e-05, + "loss": 1.4217, + "step": 4050 + }, + { + "epoch": 0.42, + "learning_rate": 1.4230881576007904e-05, + "loss": 1.435, + "step": 4051 + }, + { + "epoch": 0.42, + "learning_rate": 1.422756478206921e-05, + "loss": 1.3687, + "step": 4052 + }, + { + "epoch": 0.43, + "learning_rate": 1.4224247421745464e-05, + "loss": 1.3965, + "step": 4053 + }, + { + "epoch": 0.43, + "learning_rate": 1.4220929495481097e-05, + "loss": 1.4159, + "step": 4054 + }, + { + "epoch": 0.43, + "learning_rate": 1.4217611003720632e-05, + "loss": 1.3632, + "step": 4055 + }, + { + "epoch": 0.43, + "learning_rate": 1.4214291946908661e-05, + "loss": 1.403, + "step": 4056 + }, + { + "epoch": 0.43, + "learning_rate": 1.4210972325489854e-05, + "loss": 1.4093, + "step": 4057 + }, + { + "epoch": 0.43, + "learning_rate": 1.4207652139908952e-05, + "loss": 1.4551, + "step": 4058 + }, + { + "epoch": 0.43, + "learning_rate": 1.4204331390610775e-05, + "loss": 1.4162, + "step": 4059 + }, + { + "epoch": 0.43, + "learning_rate": 1.4201010078040216e-05, + "loss": 1.4492, + "step": 4060 + }, + { + "epoch": 0.43, + "learning_rate": 1.419768820264225e-05, + "loss": 1.4449, + "step": 4061 + }, + { + "epoch": 0.43, + "learning_rate": 1.4194365764861922e-05, + "loss": 1.3382, + "step": 4062 + }, + { + "epoch": 0.43, + "learning_rate": 1.419104276514435e-05, + "loss": 1.3899, + "step": 4063 + }, + { + "epoch": 0.43, + "learning_rate": 1.4187719203934734e-05, + "loss": 1.3513, + "step": 4064 + }, + { + "epoch": 0.43, + "learning_rate": 1.4184395081678344e-05, + "loss": 1.3954, + "step": 4065 + }, + { + "epoch": 0.43, + "learning_rate": 1.4181070398820528e-05, + "loss": 1.442, + "step": 4066 + }, + { + "epoch": 0.43, + "learning_rate": 1.4177745155806708e-05, + "loss": 1.3907, + "step": 4067 + }, + { + "epoch": 0.43, + "learning_rate": 1.417441935308238e-05, + "loss": 1.3757, + "step": 4068 + }, + { + "epoch": 0.43, + "learning_rate": 1.4171092991093118e-05, + "loss": 1.3507, + "step": 4069 + }, + { + "epoch": 0.43, + "learning_rate": 1.4167766070284568e-05, + "loss": 1.4136, + "step": 4070 + }, + { + "epoch": 0.43, + "learning_rate": 1.4164438591102452e-05, + "loss": 1.3835, + "step": 4071 + }, + { + "epoch": 0.43, + "learning_rate": 1.4161110553992565e-05, + "loss": 1.4981, + "step": 4072 + }, + { + "epoch": 0.43, + "learning_rate": 1.415778195940078e-05, + "loss": 1.4387, + "step": 4073 + }, + { + "epoch": 0.43, + "learning_rate": 1.4154452807773047e-05, + "loss": 1.333, + "step": 4074 + }, + { + "epoch": 0.43, + "learning_rate": 1.4151123099555377e-05, + "loss": 1.3558, + "step": 4075 + }, + { + "epoch": 0.43, + "learning_rate": 1.4147792835193875e-05, + "loss": 1.4655, + "step": 4076 + }, + { + "epoch": 0.43, + "learning_rate": 1.4144462015134708e-05, + "loss": 1.4402, + "step": 4077 + }, + { + "epoch": 0.43, + "learning_rate": 1.4141130639824119e-05, + "loss": 1.4227, + "step": 4078 + }, + { + "epoch": 0.43, + "learning_rate": 1.4137798709708423e-05, + "loss": 1.4039, + "step": 4079 + }, + { + "epoch": 0.43, + "learning_rate": 1.4134466225234023e-05, + "loss": 1.3593, + "step": 4080 + }, + { + "epoch": 0.43, + "learning_rate": 1.4131133186847377e-05, + "loss": 1.372, + "step": 4081 + }, + { + "epoch": 0.43, + "learning_rate": 1.412779959499503e-05, + "loss": 1.4487, + "step": 4082 + }, + { + "epoch": 0.43, + "learning_rate": 1.4124465450123599e-05, + "loss": 1.3972, + "step": 4083 + }, + { + "epoch": 0.43, + "learning_rate": 1.4121130752679772e-05, + "loss": 1.3768, + "step": 4084 + }, + { + "epoch": 0.43, + "learning_rate": 1.4117795503110313e-05, + "loss": 1.3827, + "step": 4085 + }, + { + "epoch": 0.43, + "learning_rate": 1.4114459701862062e-05, + "loss": 1.3922, + "step": 4086 + }, + { + "epoch": 0.43, + "learning_rate": 1.4111123349381925e-05, + "loss": 1.3736, + "step": 4087 + }, + { + "epoch": 0.43, + "learning_rate": 1.4107786446116894e-05, + "loss": 1.4338, + "step": 4088 + }, + { + "epoch": 0.43, + "learning_rate": 1.4104448992514023e-05, + "loss": 1.347, + "step": 4089 + }, + { + "epoch": 0.43, + "learning_rate": 1.410111098902045e-05, + "loss": 1.3915, + "step": 4090 + }, + { + "epoch": 0.43, + "learning_rate": 1.4097772436083377e-05, + "loss": 1.3656, + "step": 4091 + }, + { + "epoch": 0.43, + "learning_rate": 1.4094433334150087e-05, + "loss": 1.3461, + "step": 4092 + }, + { + "epoch": 0.43, + "learning_rate": 1.4091093683667934e-05, + "loss": 1.7345, + "step": 4093 + }, + { + "epoch": 0.43, + "learning_rate": 1.4087753485084343e-05, + "loss": 1.6204, + "step": 4094 + }, + { + "epoch": 0.43, + "learning_rate": 1.4084412738846816e-05, + "loss": 1.4074, + "step": 4095 + }, + { + "epoch": 0.43, + "learning_rate": 1.408107144540293e-05, + "loss": 1.3776, + "step": 4096 + }, + { + "epoch": 0.43, + "learning_rate": 1.407772960520033e-05, + "loss": 1.4079, + "step": 4097 + }, + { + "epoch": 0.43, + "learning_rate": 1.4074387218686734e-05, + "loss": 1.4254, + "step": 4098 + }, + { + "epoch": 0.43, + "learning_rate": 1.407104428630994e-05, + "loss": 1.38, + "step": 4099 + }, + { + "epoch": 0.43, + "learning_rate": 1.4067700808517815e-05, + "loss": 1.4175, + "step": 4100 + }, + { + "epoch": 0.43, + "learning_rate": 1.4064356785758298e-05, + "loss": 1.4085, + "step": 4101 + }, + { + "epoch": 0.43, + "learning_rate": 1.4061012218479397e-05, + "loss": 1.4529, + "step": 4102 + }, + { + "epoch": 0.43, + "learning_rate": 1.405766710712921e-05, + "loss": 1.4836, + "step": 4103 + }, + { + "epoch": 0.43, + "learning_rate": 1.4054321452155885e-05, + "loss": 1.3915, + "step": 4104 + }, + { + "epoch": 0.43, + "learning_rate": 1.4050975254007659e-05, + "loss": 1.3044, + "step": 4105 + }, + { + "epoch": 0.43, + "learning_rate": 1.4047628513132835e-05, + "loss": 1.373, + "step": 4106 + }, + { + "epoch": 0.43, + "learning_rate": 1.4044281229979793e-05, + "loss": 1.4266, + "step": 4107 + }, + { + "epoch": 0.43, + "learning_rate": 1.4040933404996977e-05, + "loss": 1.3898, + "step": 4108 + }, + { + "epoch": 0.43, + "learning_rate": 1.4037585038632915e-05, + "loss": 0.9326, + "step": 4109 + }, + { + "epoch": 0.43, + "learning_rate": 1.40342361313362e-05, + "loss": 1.0831, + "step": 4110 + }, + { + "epoch": 0.43, + "learning_rate": 1.40308866835555e-05, + "loss": 1.3898, + "step": 4111 + }, + { + "epoch": 0.43, + "learning_rate": 1.4027536695739554e-05, + "loss": 1.5058, + "step": 4112 + }, + { + "epoch": 0.43, + "learning_rate": 1.4024186168337175e-05, + "loss": 1.3635, + "step": 4113 + }, + { + "epoch": 0.43, + "learning_rate": 1.4020835101797248e-05, + "loss": 1.3871, + "step": 4114 + }, + { + "epoch": 0.43, + "learning_rate": 1.401748349656873e-05, + "loss": 1.3478, + "step": 4115 + }, + { + "epoch": 0.43, + "learning_rate": 1.4014131353100648e-05, + "loss": 1.3356, + "step": 4116 + }, + { + "epoch": 0.43, + "learning_rate": 1.4010778671842107e-05, + "loss": 1.3954, + "step": 4117 + }, + { + "epoch": 0.43, + "learning_rate": 1.4007425453242274e-05, + "loss": 1.3307, + "step": 4118 + }, + { + "epoch": 0.43, + "learning_rate": 1.4004071697750398e-05, + "loss": 1.4508, + "step": 4119 + }, + { + "epoch": 0.43, + "learning_rate": 1.4000717405815799e-05, + "loss": 1.3752, + "step": 4120 + }, + { + "epoch": 0.43, + "learning_rate": 1.399736257788786e-05, + "loss": 1.3654, + "step": 4121 + }, + { + "epoch": 0.43, + "learning_rate": 1.3994007214416046e-05, + "loss": 1.4505, + "step": 4122 + }, + { + "epoch": 0.43, + "learning_rate": 1.3990651315849886e-05, + "loss": 1.4307, + "step": 4123 + }, + { + "epoch": 0.43, + "learning_rate": 1.398729488263899e-05, + "loss": 1.4481, + "step": 4124 + }, + { + "epoch": 0.43, + "learning_rate": 1.3983937915233026e-05, + "loss": 1.4755, + "step": 4125 + }, + { + "epoch": 0.43, + "learning_rate": 1.3980580414081746e-05, + "loss": 1.3402, + "step": 4126 + }, + { + "epoch": 0.43, + "learning_rate": 1.3977222379634969e-05, + "loss": 1.3636, + "step": 4127 + }, + { + "epoch": 0.43, + "learning_rate": 1.3973863812342585e-05, + "loss": 1.4165, + "step": 4128 + }, + { + "epoch": 0.43, + "learning_rate": 1.3970504712654554e-05, + "loss": 1.3832, + "step": 4129 + }, + { + "epoch": 0.43, + "learning_rate": 1.3967145081020912e-05, + "loss": 1.4236, + "step": 4130 + }, + { + "epoch": 0.43, + "learning_rate": 1.396378491789176e-05, + "loss": 1.5022, + "step": 4131 + }, + { + "epoch": 0.43, + "learning_rate": 1.3960424223717276e-05, + "loss": 1.3806, + "step": 4132 + }, + { + "epoch": 0.43, + "learning_rate": 1.3957062998947707e-05, + "loss": 1.3649, + "step": 4133 + }, + { + "epoch": 0.43, + "learning_rate": 1.3953701244033368e-05, + "loss": 1.3787, + "step": 4134 + }, + { + "epoch": 0.43, + "learning_rate": 1.395033895942465e-05, + "loss": 1.3551, + "step": 4135 + }, + { + "epoch": 0.43, + "learning_rate": 1.394697614557201e-05, + "loss": 1.3881, + "step": 4136 + }, + { + "epoch": 0.43, + "learning_rate": 1.3943612802925983e-05, + "loss": 1.4848, + "step": 4137 + }, + { + "epoch": 0.43, + "learning_rate": 1.3940248931937169e-05, + "loss": 1.425, + "step": 4138 + }, + { + "epoch": 0.43, + "learning_rate": 1.3936884533056238e-05, + "loss": 1.4054, + "step": 4139 + }, + { + "epoch": 0.43, + "learning_rate": 1.3933519606733934e-05, + "loss": 1.4028, + "step": 4140 + }, + { + "epoch": 0.43, + "learning_rate": 1.3930154153421072e-05, + "loss": 1.4439, + "step": 4141 + }, + { + "epoch": 0.43, + "learning_rate": 1.3926788173568536e-05, + "loss": 1.4482, + "step": 4142 + }, + { + "epoch": 0.43, + "learning_rate": 1.392342166762728e-05, + "loss": 1.393, + "step": 4143 + }, + { + "epoch": 0.43, + "learning_rate": 1.3920054636048328e-05, + "loss": 1.4097, + "step": 4144 + }, + { + "epoch": 0.43, + "learning_rate": 1.391668707928278e-05, + "loss": 1.5142, + "step": 4145 + }, + { + "epoch": 0.43, + "learning_rate": 1.3913318997781797e-05, + "loss": 1.4118, + "step": 4146 + }, + { + "epoch": 0.43, + "learning_rate": 1.390995039199662e-05, + "loss": 1.4067, + "step": 4147 + }, + { + "epoch": 0.43, + "learning_rate": 1.3906581262378552e-05, + "loss": 1.5214, + "step": 4148 + }, + { + "epoch": 0.44, + "learning_rate": 1.3903211609378971e-05, + "loss": 1.3618, + "step": 4149 + }, + { + "epoch": 0.44, + "learning_rate": 1.3899841433449327e-05, + "loss": 1.338, + "step": 4150 + }, + { + "epoch": 0.44, + "learning_rate": 1.3896470735041132e-05, + "loss": 1.3901, + "step": 4151 + }, + { + "epoch": 0.44, + "learning_rate": 1.3893099514605971e-05, + "loss": 1.4502, + "step": 4152 + }, + { + "epoch": 0.44, + "learning_rate": 1.388972777259551e-05, + "loss": 1.4141, + "step": 4153 + }, + { + "epoch": 0.44, + "learning_rate": 1.3886355509461471e-05, + "loss": 1.3876, + "step": 4154 + }, + { + "epoch": 0.44, + "learning_rate": 1.388298272565565e-05, + "loss": 1.4275, + "step": 4155 + }, + { + "epoch": 0.44, + "learning_rate": 1.3879609421629909e-05, + "loss": 1.3559, + "step": 4156 + }, + { + "epoch": 0.44, + "learning_rate": 1.3876235597836195e-05, + "loss": 1.416, + "step": 4157 + }, + { + "epoch": 0.44, + "learning_rate": 1.3872861254726506e-05, + "loss": 1.437, + "step": 4158 + }, + { + "epoch": 0.44, + "learning_rate": 1.3869486392752918e-05, + "loss": 1.3794, + "step": 4159 + }, + { + "epoch": 0.44, + "learning_rate": 1.3866111012367577e-05, + "loss": 1.4094, + "step": 4160 + }, + { + "epoch": 0.44, + "learning_rate": 1.3862735114022694e-05, + "loss": 1.3957, + "step": 4161 + }, + { + "epoch": 0.44, + "learning_rate": 1.3859358698170559e-05, + "loss": 1.3582, + "step": 4162 + }, + { + "epoch": 0.44, + "learning_rate": 1.3855981765263523e-05, + "loss": 1.4159, + "step": 4163 + }, + { + "epoch": 0.44, + "learning_rate": 1.3852604315754e-05, + "loss": 1.3498, + "step": 4164 + }, + { + "epoch": 0.44, + "learning_rate": 1.3849226350094491e-05, + "loss": 1.3951, + "step": 4165 + }, + { + "epoch": 0.44, + "learning_rate": 1.3845847868737559e-05, + "loss": 1.4087, + "step": 4166 + }, + { + "epoch": 0.44, + "learning_rate": 1.3842468872135821e-05, + "loss": 1.4318, + "step": 4167 + }, + { + "epoch": 0.44, + "learning_rate": 1.3839089360741989e-05, + "loss": 1.4174, + "step": 4168 + }, + { + "epoch": 0.44, + "learning_rate": 1.3835709335008822e-05, + "loss": 1.4499, + "step": 4169 + }, + { + "epoch": 0.44, + "learning_rate": 1.383232879538916e-05, + "loss": 1.3554, + "step": 4170 + }, + { + "epoch": 0.44, + "learning_rate": 1.3828947742335905e-05, + "loss": 1.3873, + "step": 4171 + }, + { + "epoch": 0.44, + "learning_rate": 1.382556617630204e-05, + "loss": 1.3804, + "step": 4172 + }, + { + "epoch": 0.44, + "learning_rate": 1.3822184097740598e-05, + "loss": 1.3856, + "step": 4173 + }, + { + "epoch": 0.44, + "learning_rate": 1.3818801507104697e-05, + "loss": 1.3901, + "step": 4174 + }, + { + "epoch": 0.44, + "learning_rate": 1.381541840484751e-05, + "loss": 1.3714, + "step": 4175 + }, + { + "epoch": 0.44, + "learning_rate": 1.3812034791422297e-05, + "loss": 1.4945, + "step": 4176 + }, + { + "epoch": 0.44, + "learning_rate": 1.3808650667282368e-05, + "loss": 1.429, + "step": 4177 + }, + { + "epoch": 0.44, + "learning_rate": 1.3805266032881108e-05, + "loss": 1.3903, + "step": 4178 + }, + { + "epoch": 0.44, + "learning_rate": 1.3801880888671972e-05, + "loss": 1.4799, + "step": 4179 + }, + { + "epoch": 0.44, + "eval_loss": 1.4521424770355225, + "eval_runtime": 77.3596, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 4179 + }, + { + "epoch": 0.44, + "learning_rate": 1.3798495235108484e-05, + "loss": 1.3912, + "step": 4180 + }, + { + "epoch": 0.44, + "learning_rate": 1.3795109072644235e-05, + "loss": 1.5837, + "step": 4181 + }, + { + "epoch": 0.44, + "learning_rate": 1.379172240173288e-05, + "loss": 1.4255, + "step": 4182 + }, + { + "epoch": 0.44, + "learning_rate": 1.3788335222828148e-05, + "loss": 1.4666, + "step": 4183 + }, + { + "epoch": 0.44, + "learning_rate": 1.3784947536383837e-05, + "loss": 1.3964, + "step": 4184 + }, + { + "epoch": 0.44, + "learning_rate": 1.3781559342853807e-05, + "loss": 1.336, + "step": 4185 + }, + { + "epoch": 0.44, + "learning_rate": 1.3778170642691986e-05, + "loss": 1.4352, + "step": 4186 + }, + { + "epoch": 0.44, + "learning_rate": 1.377478143635238e-05, + "loss": 1.3262, + "step": 4187 + }, + { + "epoch": 0.44, + "learning_rate": 1.3771391724289047e-05, + "loss": 1.3969, + "step": 4188 + }, + { + "epoch": 0.44, + "learning_rate": 1.376800150695613e-05, + "loss": 1.4211, + "step": 4189 + }, + { + "epoch": 0.44, + "learning_rate": 1.3764610784807824e-05, + "loss": 1.4338, + "step": 4190 + }, + { + "epoch": 0.44, + "learning_rate": 1.3761219558298403e-05, + "loss": 1.3815, + "step": 4191 + }, + { + "epoch": 0.44, + "learning_rate": 1.3757827827882203e-05, + "loss": 1.3805, + "step": 4192 + }, + { + "epoch": 0.44, + "learning_rate": 1.3754435594013627e-05, + "loss": 1.4071, + "step": 4193 + }, + { + "epoch": 0.44, + "learning_rate": 1.3751042857147145e-05, + "loss": 1.343, + "step": 4194 + }, + { + "epoch": 0.44, + "learning_rate": 1.3747649617737304e-05, + "loss": 1.4129, + "step": 4195 + }, + { + "epoch": 0.44, + "learning_rate": 1.3744255876238708e-05, + "loss": 1.3939, + "step": 4196 + }, + { + "epoch": 0.44, + "learning_rate": 1.3740861633106029e-05, + "loss": 1.3963, + "step": 4197 + }, + { + "epoch": 0.44, + "learning_rate": 1.3737466888794008e-05, + "loss": 1.5181, + "step": 4198 + }, + { + "epoch": 0.44, + "learning_rate": 1.3734071643757456e-05, + "loss": 1.4397, + "step": 4199 + }, + { + "epoch": 0.44, + "learning_rate": 1.373067589845125e-05, + "loss": 1.6293, + "step": 4200 + }, + { + "epoch": 0.44, + "learning_rate": 1.3727279653330328e-05, + "loss": 1.3498, + "step": 4201 + }, + { + "epoch": 0.44, + "learning_rate": 1.37238829088497e-05, + "loss": 1.4509, + "step": 4202 + }, + { + "epoch": 0.44, + "learning_rate": 1.3720485665464446e-05, + "loss": 1.4477, + "step": 4203 + }, + { + "epoch": 0.44, + "learning_rate": 1.3717087923629709e-05, + "loss": 1.4399, + "step": 4204 + }, + { + "epoch": 0.44, + "learning_rate": 1.3713689683800695e-05, + "loss": 1.4417, + "step": 4205 + }, + { + "epoch": 0.44, + "learning_rate": 1.3710290946432685e-05, + "loss": 1.3957, + "step": 4206 + }, + { + "epoch": 0.44, + "learning_rate": 1.3706891711981021e-05, + "loss": 1.4476, + "step": 4207 + }, + { + "epoch": 0.44, + "learning_rate": 1.3703491980901113e-05, + "loss": 1.3894, + "step": 4208 + }, + { + "epoch": 0.44, + "learning_rate": 1.3700091753648437e-05, + "loss": 1.4745, + "step": 4209 + }, + { + "epoch": 0.44, + "learning_rate": 1.369669103067854e-05, + "loss": 1.4038, + "step": 4210 + }, + { + "epoch": 0.44, + "learning_rate": 1.3693289812447023e-05, + "loss": 1.4151, + "step": 4211 + }, + { + "epoch": 0.44, + "learning_rate": 1.3689888099409572e-05, + "loss": 1.4214, + "step": 4212 + }, + { + "epoch": 0.44, + "learning_rate": 1.368648589202192e-05, + "loss": 1.4287, + "step": 4213 + }, + { + "epoch": 0.44, + "learning_rate": 1.3683083190739883e-05, + "loss": 1.345, + "step": 4214 + }, + { + "epoch": 0.44, + "learning_rate": 1.367967999601933e-05, + "loss": 1.3022, + "step": 4215 + }, + { + "epoch": 0.44, + "learning_rate": 1.3676276308316207e-05, + "loss": 1.3971, + "step": 4216 + }, + { + "epoch": 0.44, + "learning_rate": 1.3672872128086514e-05, + "loss": 1.3335, + "step": 4217 + }, + { + "epoch": 0.44, + "learning_rate": 1.366946745578633e-05, + "loss": 1.3988, + "step": 4218 + }, + { + "epoch": 0.44, + "learning_rate": 1.366606229187179e-05, + "loss": 1.4508, + "step": 4219 + }, + { + "epoch": 0.44, + "learning_rate": 1.3662656636799099e-05, + "loss": 1.3814, + "step": 4220 + }, + { + "epoch": 0.44, + "learning_rate": 1.3659250491024527e-05, + "loss": 1.4128, + "step": 4221 + }, + { + "epoch": 0.44, + "learning_rate": 1.3655843855004411e-05, + "loss": 1.3893, + "step": 4222 + }, + { + "epoch": 0.44, + "learning_rate": 1.3652436729195154e-05, + "loss": 1.2551, + "step": 4223 + }, + { + "epoch": 0.44, + "learning_rate": 1.3649029114053219e-05, + "loss": 1.4386, + "step": 4224 + }, + { + "epoch": 0.44, + "learning_rate": 1.364562101003514e-05, + "loss": 1.4028, + "step": 4225 + }, + { + "epoch": 0.44, + "learning_rate": 1.364221241759752e-05, + "loss": 1.4351, + "step": 4226 + }, + { + "epoch": 0.44, + "learning_rate": 1.363880333719702e-05, + "loss": 1.3941, + "step": 4227 + }, + { + "epoch": 0.44, + "learning_rate": 1.3635393769290368e-05, + "loss": 1.3879, + "step": 4228 + }, + { + "epoch": 0.44, + "learning_rate": 1.3631983714334358e-05, + "loss": 1.3773, + "step": 4229 + }, + { + "epoch": 0.44, + "learning_rate": 1.3628573172785853e-05, + "loss": 1.3679, + "step": 4230 + }, + { + "epoch": 0.44, + "learning_rate": 1.3625162145101776e-05, + "loss": 1.3705, + "step": 4231 + }, + { + "epoch": 0.44, + "learning_rate": 1.3621750631739114e-05, + "loss": 1.8157, + "step": 4232 + }, + { + "epoch": 0.44, + "learning_rate": 1.3618338633154928e-05, + "loss": 1.4056, + "step": 4233 + }, + { + "epoch": 0.44, + "learning_rate": 1.3614926149806334e-05, + "loss": 1.3716, + "step": 4234 + }, + { + "epoch": 0.44, + "learning_rate": 1.3611513182150523e-05, + "loss": 1.3766, + "step": 4235 + }, + { + "epoch": 0.44, + "learning_rate": 1.3608099730644733e-05, + "loss": 1.41, + "step": 4236 + }, + { + "epoch": 0.44, + "learning_rate": 1.3604685795746291e-05, + "loss": 1.421, + "step": 4237 + }, + { + "epoch": 0.44, + "learning_rate": 1.360127137791257e-05, + "loss": 1.3679, + "step": 4238 + }, + { + "epoch": 0.44, + "learning_rate": 1.3597856477601018e-05, + "loss": 1.4615, + "step": 4239 + }, + { + "epoch": 0.44, + "learning_rate": 1.359444109526914e-05, + "loss": 1.3418, + "step": 4240 + }, + { + "epoch": 0.44, + "learning_rate": 1.3591025231374513e-05, + "loss": 1.3631, + "step": 4241 + }, + { + "epoch": 0.44, + "learning_rate": 1.3587608886374772e-05, + "loss": 1.3802, + "step": 4242 + }, + { + "epoch": 0.44, + "learning_rate": 1.3584192060727622e-05, + "loss": 1.4156, + "step": 4243 + }, + { + "epoch": 0.45, + "learning_rate": 1.3580774754890827e-05, + "loss": 1.4161, + "step": 4244 + }, + { + "epoch": 0.45, + "learning_rate": 1.3577356969322222e-05, + "loss": 1.3535, + "step": 4245 + }, + { + "epoch": 0.45, + "learning_rate": 1.3573938704479699e-05, + "loss": 1.3859, + "step": 4246 + }, + { + "epoch": 0.45, + "learning_rate": 1.357051996082122e-05, + "loss": 1.3595, + "step": 4247 + }, + { + "epoch": 0.45, + "learning_rate": 1.3567100738804806e-05, + "loss": 1.4191, + "step": 4248 + }, + { + "epoch": 0.45, + "learning_rate": 1.3563681038888548e-05, + "loss": 1.4186, + "step": 4249 + }, + { + "epoch": 0.45, + "learning_rate": 1.3560260861530596e-05, + "loss": 1.43, + "step": 4250 + }, + { + "epoch": 0.45, + "learning_rate": 1.3556840207189168e-05, + "loss": 1.4139, + "step": 4251 + }, + { + "epoch": 0.45, + "learning_rate": 1.3553419076322539e-05, + "loss": 1.4005, + "step": 4252 + }, + { + "epoch": 0.45, + "learning_rate": 1.3549997469389058e-05, + "loss": 1.3468, + "step": 4253 + }, + { + "epoch": 0.45, + "learning_rate": 1.3546575386847132e-05, + "loss": 1.3756, + "step": 4254 + }, + { + "epoch": 0.45, + "learning_rate": 1.3543152829155226e-05, + "loss": 1.4063, + "step": 4255 + }, + { + "epoch": 0.45, + "learning_rate": 1.3539729796771884e-05, + "loss": 1.4666, + "step": 4256 + }, + { + "epoch": 0.45, + "learning_rate": 1.3536306290155694e-05, + "loss": 1.4212, + "step": 4257 + }, + { + "epoch": 0.45, + "learning_rate": 1.3532882309765332e-05, + "loss": 1.4883, + "step": 4258 + }, + { + "epoch": 0.45, + "learning_rate": 1.3529457856059507e-05, + "loss": 1.6641, + "step": 4259 + }, + { + "epoch": 0.45, + "learning_rate": 1.3526032929497022e-05, + "loss": 1.3659, + "step": 4260 + }, + { + "epoch": 0.45, + "learning_rate": 1.3522607530536717e-05, + "loss": 1.5945, + "step": 4261 + }, + { + "epoch": 0.45, + "learning_rate": 1.351918165963752e-05, + "loss": 1.3643, + "step": 4262 + }, + { + "epoch": 0.45, + "learning_rate": 1.3515755317258397e-05, + "loss": 1.3442, + "step": 4263 + }, + { + "epoch": 0.45, + "learning_rate": 1.3512328503858398e-05, + "loss": 1.3982, + "step": 4264 + }, + { + "epoch": 0.45, + "learning_rate": 1.3508901219896624e-05, + "loss": 1.4985, + "step": 4265 + }, + { + "epoch": 0.45, + "learning_rate": 1.350547346583225e-05, + "loss": 1.3319, + "step": 4266 + }, + { + "epoch": 0.45, + "learning_rate": 1.3502045242124497e-05, + "loss": 1.3961, + "step": 4267 + }, + { + "epoch": 0.45, + "learning_rate": 1.3498616549232665e-05, + "loss": 1.4565, + "step": 4268 + }, + { + "epoch": 0.45, + "learning_rate": 1.349518738761611e-05, + "loss": 1.375, + "step": 4269 + }, + { + "epoch": 0.45, + "learning_rate": 1.3491757757734254e-05, + "loss": 1.3005, + "step": 4270 + }, + { + "epoch": 0.45, + "learning_rate": 1.348832766004657e-05, + "loss": 1.3185, + "step": 4271 + }, + { + "epoch": 0.45, + "learning_rate": 1.3484897095012613e-05, + "loss": 1.4449, + "step": 4272 + }, + { + "epoch": 0.45, + "learning_rate": 1.3481466063091988e-05, + "loss": 1.3587, + "step": 4273 + }, + { + "epoch": 0.45, + "learning_rate": 1.3478034564744362e-05, + "loss": 1.3844, + "step": 4274 + }, + { + "epoch": 0.45, + "learning_rate": 1.3474602600429468e-05, + "loss": 1.4471, + "step": 4275 + }, + { + "epoch": 0.45, + "learning_rate": 1.3471170170607105e-05, + "loss": 1.4686, + "step": 4276 + }, + { + "epoch": 0.45, + "learning_rate": 1.3467737275737127e-05, + "loss": 1.312, + "step": 4277 + }, + { + "epoch": 0.45, + "learning_rate": 1.3464303916279453e-05, + "loss": 1.407, + "step": 4278 + }, + { + "epoch": 0.45, + "learning_rate": 1.346087009269407e-05, + "loss": 1.364, + "step": 4279 + }, + { + "epoch": 0.45, + "learning_rate": 1.3457435805441016e-05, + "loss": 1.4103, + "step": 4280 + }, + { + "epoch": 0.45, + "learning_rate": 1.3454001054980403e-05, + "loss": 1.4243, + "step": 4281 + }, + { + "epoch": 0.45, + "learning_rate": 1.3450565841772392e-05, + "loss": 1.3879, + "step": 4282 + }, + { + "epoch": 0.45, + "learning_rate": 1.344713016627722e-05, + "loss": 1.4688, + "step": 4283 + }, + { + "epoch": 0.45, + "learning_rate": 1.3443694028955176e-05, + "loss": 1.3983, + "step": 4284 + }, + { + "epoch": 0.45, + "learning_rate": 1.344025743026662e-05, + "loss": 1.4316, + "step": 4285 + }, + { + "epoch": 0.45, + "learning_rate": 1.3436820370671956e-05, + "loss": 1.3643, + "step": 4286 + }, + { + "epoch": 0.45, + "learning_rate": 1.3433382850631673e-05, + "loss": 1.4566, + "step": 4287 + }, + { + "epoch": 0.45, + "learning_rate": 1.3429944870606301e-05, + "loss": 1.1263, + "step": 4288 + }, + { + "epoch": 0.45, + "learning_rate": 1.3426506431056452e-05, + "loss": 1.2463, + "step": 4289 + }, + { + "epoch": 0.45, + "learning_rate": 1.342306753244278e-05, + "loss": 1.4753, + "step": 4290 + }, + { + "epoch": 0.45, + "learning_rate": 1.3419628175226012e-05, + "loss": 1.3789, + "step": 4291 + }, + { + "epoch": 0.45, + "learning_rate": 1.3416188359866932e-05, + "loss": 1.3906, + "step": 4292 + }, + { + "epoch": 0.45, + "learning_rate": 1.3412748086826389e-05, + "loss": 1.3995, + "step": 4293 + }, + { + "epoch": 0.45, + "learning_rate": 1.3409307356565288e-05, + "loss": 1.4906, + "step": 4294 + }, + { + "epoch": 0.45, + "learning_rate": 1.3405866169544602e-05, + "loss": 1.3951, + "step": 4295 + }, + { + "epoch": 0.45, + "learning_rate": 1.3402424526225359e-05, + "loss": 1.3753, + "step": 4296 + }, + { + "epoch": 0.45, + "learning_rate": 1.3398982427068654e-05, + "loss": 1.3686, + "step": 4297 + }, + { + "epoch": 0.45, + "learning_rate": 1.3395539872535636e-05, + "loss": 1.3612, + "step": 4298 + }, + { + "epoch": 0.45, + "learning_rate": 1.3392096863087522e-05, + "loss": 1.4043, + "step": 4299 + }, + { + "epoch": 0.45, + "learning_rate": 1.3388653399185585e-05, + "loss": 1.4068, + "step": 4300 + }, + { + "epoch": 0.45, + "learning_rate": 1.338520948129116e-05, + "loss": 1.4066, + "step": 4301 + }, + { + "epoch": 0.45, + "learning_rate": 1.3381765109865646e-05, + "loss": 1.4944, + "step": 4302 + }, + { + "epoch": 0.45, + "learning_rate": 1.3378320285370496e-05, + "loss": 1.3575, + "step": 4303 + }, + { + "epoch": 0.45, + "learning_rate": 1.3374875008267236e-05, + "loss": 1.3807, + "step": 4304 + }, + { + "epoch": 0.45, + "learning_rate": 1.3371429279017437e-05, + "loss": 1.4389, + "step": 4305 + }, + { + "epoch": 0.45, + "learning_rate": 1.3367983098082739e-05, + "loss": 1.4858, + "step": 4306 + }, + { + "epoch": 0.45, + "learning_rate": 1.3364536465924844e-05, + "loss": 1.3282, + "step": 4307 + }, + { + "epoch": 0.45, + "learning_rate": 1.3361089383005515e-05, + "loss": 1.4306, + "step": 4308 + }, + { + "epoch": 0.45, + "learning_rate": 1.3357641849786566e-05, + "loss": 1.3892, + "step": 4309 + }, + { + "epoch": 0.45, + "learning_rate": 1.3354193866729883e-05, + "loss": 1.3621, + "step": 4310 + }, + { + "epoch": 0.45, + "learning_rate": 1.3350745434297401e-05, + "loss": 1.3476, + "step": 4311 + }, + { + "epoch": 0.45, + "learning_rate": 1.334729655295113e-05, + "loss": 1.4477, + "step": 4312 + }, + { + "epoch": 0.45, + "learning_rate": 1.3343847223153123e-05, + "loss": 1.3585, + "step": 4313 + }, + { + "epoch": 0.45, + "learning_rate": 1.334039744536551e-05, + "loss": 1.3616, + "step": 4314 + }, + { + "epoch": 0.45, + "learning_rate": 1.3336947220050462e-05, + "loss": 1.3579, + "step": 4315 + }, + { + "epoch": 0.45, + "learning_rate": 1.3333496547670232e-05, + "loss": 1.3557, + "step": 4316 + }, + { + "epoch": 0.45, + "learning_rate": 1.3330045428687113e-05, + "loss": 1.4443, + "step": 4317 + }, + { + "epoch": 0.45, + "learning_rate": 1.332659386356347e-05, + "loss": 1.3621, + "step": 4318 + }, + { + "epoch": 0.45, + "learning_rate": 1.3323141852761726e-05, + "loss": 1.3295, + "step": 4319 + }, + { + "epoch": 0.45, + "learning_rate": 1.3319689396744358e-05, + "loss": 1.4187, + "step": 4320 + }, + { + "epoch": 0.45, + "learning_rate": 1.3316236495973905e-05, + "loss": 1.335, + "step": 4321 + }, + { + "epoch": 0.45, + "learning_rate": 1.331278315091297e-05, + "loss": 1.4382, + "step": 4322 + }, + { + "epoch": 0.45, + "learning_rate": 1.3309329362024212e-05, + "loss": 1.4244, + "step": 4323 + }, + { + "epoch": 0.45, + "learning_rate": 1.3305875129770351e-05, + "loss": 1.488, + "step": 4324 + }, + { + "epoch": 0.45, + "learning_rate": 1.3302420454614165e-05, + "loss": 1.3369, + "step": 4325 + }, + { + "epoch": 0.45, + "learning_rate": 1.3298965337018487e-05, + "loss": 1.3648, + "step": 4326 + }, + { + "epoch": 0.45, + "learning_rate": 1.3295509777446226e-05, + "loss": 1.3924, + "step": 4327 + }, + { + "epoch": 0.45, + "learning_rate": 1.3292053776360324e-05, + "loss": 1.3789, + "step": 4328 + }, + { + "epoch": 0.45, + "learning_rate": 1.3288597334223802e-05, + "loss": 1.3902, + "step": 4329 + }, + { + "epoch": 0.45, + "learning_rate": 1.3285140451499735e-05, + "loss": 1.4057, + "step": 4330 + }, + { + "epoch": 0.45, + "learning_rate": 1.328168312865126e-05, + "loss": 1.4536, + "step": 4331 + }, + { + "epoch": 0.45, + "learning_rate": 1.3278225366141565e-05, + "loss": 1.3075, + "step": 4332 + }, + { + "epoch": 0.45, + "learning_rate": 1.3274767164433901e-05, + "loss": 1.4579, + "step": 4333 + }, + { + "epoch": 0.45, + "learning_rate": 1.3271308523991579e-05, + "loss": 1.3906, + "step": 4334 + }, + { + "epoch": 0.45, + "learning_rate": 1.326784944527797e-05, + "loss": 1.3992, + "step": 4335 + }, + { + "epoch": 0.45, + "learning_rate": 1.3264389928756498e-05, + "loss": 1.4001, + "step": 4336 + }, + { + "epoch": 0.45, + "learning_rate": 1.3260929974890653e-05, + "loss": 1.2948, + "step": 4337 + }, + { + "epoch": 0.45, + "learning_rate": 1.3257469584143976e-05, + "loss": 1.4041, + "step": 4338 + }, + { + "epoch": 0.46, + "learning_rate": 1.3254008756980076e-05, + "loss": 1.5035, + "step": 4339 + }, + { + "epoch": 0.46, + "learning_rate": 1.3250547493862609e-05, + "loss": 1.4867, + "step": 4340 + }, + { + "epoch": 0.46, + "learning_rate": 1.3247085795255302e-05, + "loss": 1.3612, + "step": 4341 + }, + { + "epoch": 0.46, + "learning_rate": 1.3243623661621925e-05, + "loss": 1.4193, + "step": 4342 + }, + { + "epoch": 0.46, + "learning_rate": 1.3240161093426322e-05, + "loss": 1.3596, + "step": 4343 + }, + { + "epoch": 0.46, + "learning_rate": 1.3236698091132383e-05, + "loss": 1.4448, + "step": 4344 + }, + { + "epoch": 0.46, + "learning_rate": 1.3233234655204066e-05, + "loss": 1.3924, + "step": 4345 + }, + { + "epoch": 0.46, + "learning_rate": 1.322977078610538e-05, + "loss": 1.3552, + "step": 4346 + }, + { + "epoch": 0.46, + "learning_rate": 1.3226306484300395e-05, + "loss": 1.3949, + "step": 4347 + }, + { + "epoch": 0.46, + "learning_rate": 1.322284175025324e-05, + "loss": 1.399, + "step": 4348 + }, + { + "epoch": 0.46, + "learning_rate": 1.3219376584428094e-05, + "loss": 1.4755, + "step": 4349 + }, + { + "epoch": 0.46, + "learning_rate": 1.3215910987289212e-05, + "loss": 1.3877, + "step": 4350 + }, + { + "epoch": 0.46, + "learning_rate": 1.3212444959300882e-05, + "loss": 1.3916, + "step": 4351 + }, + { + "epoch": 0.46, + "learning_rate": 1.3208978500927472e-05, + "loss": 1.3462, + "step": 4352 + }, + { + "epoch": 0.46, + "learning_rate": 1.3205511612633392e-05, + "loss": 1.3834, + "step": 4353 + }, + { + "epoch": 0.46, + "learning_rate": 1.3202044294883123e-05, + "loss": 1.3843, + "step": 4354 + }, + { + "epoch": 0.46, + "learning_rate": 1.3198576548141189e-05, + "loss": 1.2439, + "step": 4355 + }, + { + "epoch": 0.46, + "learning_rate": 1.3195108372872181e-05, + "loss": 1.4106, + "step": 4356 + }, + { + "epoch": 0.46, + "learning_rate": 1.3191639769540746e-05, + "loss": 1.4417, + "step": 4357 + }, + { + "epoch": 0.46, + "learning_rate": 1.3188170738611596e-05, + "loss": 1.4393, + "step": 4358 + }, + { + "epoch": 0.46, + "learning_rate": 1.3184701280549476e-05, + "loss": 1.4616, + "step": 4359 + }, + { + "epoch": 0.46, + "learning_rate": 1.3181231395819218e-05, + "loss": 1.3215, + "step": 4360 + }, + { + "epoch": 0.46, + "learning_rate": 1.3177761084885689e-05, + "loss": 1.368, + "step": 4361 + }, + { + "epoch": 0.46, + "learning_rate": 1.317429034821383e-05, + "loss": 1.3247, + "step": 4362 + }, + { + "epoch": 0.46, + "learning_rate": 1.3170819186268618e-05, + "loss": 1.4512, + "step": 4363 + }, + { + "epoch": 0.46, + "learning_rate": 1.3167347599515111e-05, + "loss": 1.3129, + "step": 4364 + }, + { + "epoch": 0.46, + "learning_rate": 1.3163875588418404e-05, + "loss": 1.3934, + "step": 4365 + }, + { + "epoch": 0.46, + "learning_rate": 1.3160403153443666e-05, + "loss": 1.4518, + "step": 4366 + }, + { + "epoch": 0.46, + "learning_rate": 1.3156930295056105e-05, + "loss": 1.3959, + "step": 4367 + }, + { + "epoch": 0.46, + "learning_rate": 1.3153457013721e-05, + "loss": 1.3475, + "step": 4368 + }, + { + "epoch": 0.46, + "learning_rate": 1.3149983309903687e-05, + "loss": 1.4102, + "step": 4369 + }, + { + "epoch": 0.46, + "learning_rate": 1.3146509184069538e-05, + "loss": 1.3674, + "step": 4370 + }, + { + "epoch": 0.46, + "learning_rate": 1.314303463668401e-05, + "loss": 1.3739, + "step": 4371 + }, + { + "epoch": 0.46, + "learning_rate": 1.3139559668212596e-05, + "loss": 1.4249, + "step": 4372 + }, + { + "epoch": 0.46, + "learning_rate": 1.3136084279120857e-05, + "loss": 1.4473, + "step": 4373 + }, + { + "epoch": 0.46, + "learning_rate": 1.3132608469874404e-05, + "loss": 1.4443, + "step": 4374 + }, + { + "epoch": 0.46, + "learning_rate": 1.3129132240938905e-05, + "loss": 1.3534, + "step": 4375 + }, + { + "epoch": 0.46, + "learning_rate": 1.3125655592780083e-05, + "loss": 1.5663, + "step": 4376 + }, + { + "epoch": 0.46, + "learning_rate": 1.3122178525863727e-05, + "loss": 1.3465, + "step": 4377 + }, + { + "epoch": 0.46, + "learning_rate": 1.3118701040655669e-05, + "loss": 1.35, + "step": 4378 + }, + { + "epoch": 0.46, + "eval_loss": 1.447788953781128, + "eval_runtime": 77.4473, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4378 + }, + { + "epoch": 0.46, + "learning_rate": 1.3115223137621804e-05, + "loss": 1.343, + "step": 4379 + }, + { + "epoch": 0.46, + "learning_rate": 1.3111744817228078e-05, + "loss": 1.4227, + "step": 4380 + }, + { + "epoch": 0.46, + "learning_rate": 1.3108266079940508e-05, + "loss": 1.3982, + "step": 4381 + }, + { + "epoch": 0.46, + "learning_rate": 1.3104786926225141e-05, + "loss": 1.4211, + "step": 4382 + }, + { + "epoch": 0.46, + "learning_rate": 1.3101307356548103e-05, + "loss": 1.382, + "step": 4383 + }, + { + "epoch": 0.46, + "learning_rate": 1.3097827371375562e-05, + "loss": 1.4637, + "step": 4384 + }, + { + "epoch": 0.46, + "learning_rate": 1.3094346971173754e-05, + "loss": 1.4572, + "step": 4385 + }, + { + "epoch": 0.46, + "learning_rate": 1.3090866156408956e-05, + "loss": 1.5113, + "step": 4386 + }, + { + "epoch": 0.46, + "learning_rate": 1.3087384927547512e-05, + "loss": 1.2197, + "step": 4387 + }, + { + "epoch": 0.46, + "learning_rate": 1.3083903285055813e-05, + "loss": 1.3861, + "step": 4388 + }, + { + "epoch": 0.46, + "learning_rate": 1.3080421229400315e-05, + "loss": 1.4754, + "step": 4389 + }, + { + "epoch": 0.46, + "learning_rate": 1.307693876104752e-05, + "loss": 1.3588, + "step": 4390 + }, + { + "epoch": 0.46, + "learning_rate": 1.3073455880463987e-05, + "loss": 1.3995, + "step": 4391 + }, + { + "epoch": 0.46, + "learning_rate": 1.3069972588116341e-05, + "loss": 1.354, + "step": 4392 + }, + { + "epoch": 0.46, + "learning_rate": 1.3066488884471244e-05, + "loss": 1.3378, + "step": 4393 + }, + { + "epoch": 0.46, + "learning_rate": 1.306300476999543e-05, + "loss": 1.5951, + "step": 4394 + }, + { + "epoch": 0.46, + "learning_rate": 1.305952024515568e-05, + "loss": 1.3661, + "step": 4395 + }, + { + "epoch": 0.46, + "learning_rate": 1.3056035310418826e-05, + "loss": 1.4066, + "step": 4396 + }, + { + "epoch": 0.46, + "learning_rate": 1.3052549966251764e-05, + "loss": 1.3687, + "step": 4397 + }, + { + "epoch": 0.46, + "learning_rate": 1.3049064213121438e-05, + "loss": 1.4573, + "step": 4398 + }, + { + "epoch": 0.46, + "learning_rate": 1.3045578051494852e-05, + "loss": 1.3519, + "step": 4399 + }, + { + "epoch": 0.46, + "learning_rate": 1.3042091481839063e-05, + "loss": 1.2803, + "step": 4400 + }, + { + "epoch": 0.46, + "learning_rate": 1.3038604504621173e-05, + "loss": 1.4014, + "step": 4401 + }, + { + "epoch": 0.46, + "learning_rate": 1.3035117120308358e-05, + "loss": 1.4534, + "step": 4402 + }, + { + "epoch": 0.46, + "learning_rate": 1.3031629329367832e-05, + "loss": 1.4747, + "step": 4403 + }, + { + "epoch": 0.46, + "learning_rate": 1.3028141132266877e-05, + "loss": 1.374, + "step": 4404 + }, + { + "epoch": 0.46, + "learning_rate": 1.3024652529472807e-05, + "loss": 1.4328, + "step": 4405 + }, + { + "epoch": 0.46, + "learning_rate": 1.302116352145302e-05, + "loss": 1.468, + "step": 4406 + }, + { + "epoch": 0.46, + "learning_rate": 1.3017674108674942e-05, + "loss": 1.2947, + "step": 4407 + }, + { + "epoch": 0.46, + "learning_rate": 1.3014184291606077e-05, + "loss": 1.3682, + "step": 4408 + }, + { + "epoch": 0.46, + "learning_rate": 1.3010694070713959e-05, + "loss": 1.3651, + "step": 4409 + }, + { + "epoch": 0.46, + "learning_rate": 1.3007203446466194e-05, + "loss": 1.418, + "step": 4410 + }, + { + "epoch": 0.46, + "learning_rate": 1.3003712419330433e-05, + "loss": 1.416, + "step": 4411 + }, + { + "epoch": 0.46, + "learning_rate": 1.300022098977439e-05, + "loss": 1.2979, + "step": 4412 + }, + { + "epoch": 0.46, + "learning_rate": 1.2996729158265819e-05, + "loss": 1.3868, + "step": 4413 + }, + { + "epoch": 0.46, + "learning_rate": 1.2993236925272542e-05, + "loss": 1.3102, + "step": 4414 + }, + { + "epoch": 0.46, + "learning_rate": 1.2989744291262422e-05, + "loss": 1.3506, + "step": 4415 + }, + { + "epoch": 0.46, + "learning_rate": 1.2986251256703388e-05, + "loss": 1.4018, + "step": 4416 + }, + { + "epoch": 0.46, + "learning_rate": 1.2982757822063417e-05, + "loss": 1.4081, + "step": 4417 + }, + { + "epoch": 0.46, + "learning_rate": 1.2979263987810533e-05, + "loss": 1.3592, + "step": 4418 + }, + { + "epoch": 0.46, + "learning_rate": 1.297576975441283e-05, + "loss": 1.4287, + "step": 4419 + }, + { + "epoch": 0.46, + "learning_rate": 1.2972275122338433e-05, + "loss": 1.4099, + "step": 4420 + }, + { + "epoch": 0.46, + "learning_rate": 1.2968780092055546e-05, + "loss": 1.4005, + "step": 4421 + }, + { + "epoch": 0.46, + "learning_rate": 1.2965284664032401e-05, + "loss": 1.365, + "step": 4422 + }, + { + "epoch": 0.46, + "learning_rate": 1.2961788838737309e-05, + "loss": 1.3588, + "step": 4423 + }, + { + "epoch": 0.46, + "learning_rate": 1.2958292616638606e-05, + "loss": 1.3702, + "step": 4424 + }, + { + "epoch": 0.46, + "learning_rate": 1.2954795998204708e-05, + "loss": 1.3487, + "step": 4425 + }, + { + "epoch": 0.46, + "learning_rate": 1.2951298983904063e-05, + "loss": 1.4395, + "step": 4426 + }, + { + "epoch": 0.46, + "learning_rate": 1.2947801574205193e-05, + "loss": 1.3523, + "step": 4427 + }, + { + "epoch": 0.46, + "learning_rate": 1.2944303769576645e-05, + "loss": 1.3125, + "step": 4428 + }, + { + "epoch": 0.46, + "learning_rate": 1.2940805570487048e-05, + "loss": 1.5476, + "step": 4429 + }, + { + "epoch": 0.46, + "learning_rate": 1.2937306977405062e-05, + "loss": 1.4076, + "step": 4430 + }, + { + "epoch": 0.46, + "learning_rate": 1.2933807990799418e-05, + "loss": 1.3007, + "step": 4431 + }, + { + "epoch": 0.46, + "learning_rate": 1.293030861113888e-05, + "loss": 1.3566, + "step": 4432 + }, + { + "epoch": 0.46, + "learning_rate": 1.2926808838892285e-05, + "loss": 1.3907, + "step": 4433 + }, + { + "epoch": 0.46, + "learning_rate": 1.2923308674528501e-05, + "loss": 1.379, + "step": 4434 + }, + { + "epoch": 0.47, + "learning_rate": 1.2919808118516475e-05, + "loss": 1.4319, + "step": 4435 + }, + { + "epoch": 0.47, + "learning_rate": 1.2916307171325176e-05, + "loss": 1.3392, + "step": 4436 + }, + { + "epoch": 0.47, + "learning_rate": 1.291280583342365e-05, + "loss": 1.401, + "step": 4437 + }, + { + "epoch": 0.47, + "learning_rate": 1.2909304105280984e-05, + "loss": 1.3939, + "step": 4438 + }, + { + "epoch": 0.47, + "learning_rate": 1.2905801987366322e-05, + "loss": 1.4676, + "step": 4439 + }, + { + "epoch": 0.47, + "learning_rate": 1.2902299480148855e-05, + "loss": 1.3957, + "step": 4440 + }, + { + "epoch": 0.47, + "learning_rate": 1.2898796584097828e-05, + "loss": 1.3587, + "step": 4441 + }, + { + "epoch": 0.47, + "learning_rate": 1.2895293299682545e-05, + "loss": 1.5809, + "step": 4442 + }, + { + "epoch": 0.47, + "learning_rate": 1.289178962737235e-05, + "loss": 1.3436, + "step": 4443 + }, + { + "epoch": 0.47, + "learning_rate": 1.2888285567636647e-05, + "loss": 1.4535, + "step": 4444 + }, + { + "epoch": 0.47, + "learning_rate": 1.2884781120944889e-05, + "loss": 1.3377, + "step": 4445 + }, + { + "epoch": 0.47, + "learning_rate": 1.2881276287766587e-05, + "loss": 0.8221, + "step": 4446 + }, + { + "epoch": 0.47, + "learning_rate": 1.2877771068571288e-05, + "loss": 0.7259, + "step": 4447 + }, + { + "epoch": 0.47, + "learning_rate": 1.2874265463828612e-05, + "loss": 0.8279, + "step": 4448 + }, + { + "epoch": 0.47, + "learning_rate": 1.2870759474008213e-05, + "loss": 1.3523, + "step": 4449 + }, + { + "epoch": 0.47, + "learning_rate": 1.2867253099579808e-05, + "loss": 1.3658, + "step": 4450 + }, + { + "epoch": 0.47, + "learning_rate": 1.2863746341013158e-05, + "loss": 1.4112, + "step": 4451 + }, + { + "epoch": 0.47, + "learning_rate": 1.2860239198778085e-05, + "loss": 1.389, + "step": 4452 + }, + { + "epoch": 0.47, + "learning_rate": 1.2856731673344442e-05, + "loss": 1.4066, + "step": 4453 + }, + { + "epoch": 0.47, + "learning_rate": 1.2853223765182165e-05, + "loss": 1.3267, + "step": 4454 + }, + { + "epoch": 0.47, + "learning_rate": 1.2849715474761209e-05, + "loss": 1.3381, + "step": 4455 + }, + { + "epoch": 0.47, + "learning_rate": 1.2846206802551602e-05, + "loss": 1.2882, + "step": 4456 + }, + { + "epoch": 0.47, + "learning_rate": 1.2842697749023414e-05, + "loss": 1.3199, + "step": 4457 + }, + { + "epoch": 0.47, + "learning_rate": 1.2839188314646771e-05, + "loss": 1.3896, + "step": 4458 + }, + { + "epoch": 0.47, + "learning_rate": 1.2835678499891842e-05, + "loss": 1.3186, + "step": 4459 + }, + { + "epoch": 0.47, + "learning_rate": 1.283216830522885e-05, + "loss": 1.3466, + "step": 4460 + }, + { + "epoch": 0.47, + "learning_rate": 1.2828657731128083e-05, + "loss": 1.4678, + "step": 4461 + }, + { + "epoch": 0.47, + "learning_rate": 1.2825146778059857e-05, + "loss": 1.4408, + "step": 4462 + }, + { + "epoch": 0.47, + "learning_rate": 1.2821635446494553e-05, + "loss": 1.3672, + "step": 4463 + }, + { + "epoch": 0.47, + "learning_rate": 1.2818123736902597e-05, + "loss": 1.3836, + "step": 4464 + }, + { + "epoch": 0.47, + "learning_rate": 1.2814611649754472e-05, + "loss": 1.3493, + "step": 4465 + }, + { + "epoch": 0.47, + "learning_rate": 1.2811099185520704e-05, + "loss": 1.3584, + "step": 4466 + }, + { + "epoch": 0.47, + "learning_rate": 1.2807586344671875e-05, + "loss": 1.3551, + "step": 4467 + }, + { + "epoch": 0.47, + "learning_rate": 1.2804073127678612e-05, + "loss": 1.3254, + "step": 4468 + }, + { + "epoch": 0.47, + "learning_rate": 1.28005595350116e-05, + "loss": 1.3405, + "step": 4469 + }, + { + "epoch": 0.47, + "learning_rate": 1.2797045567141568e-05, + "loss": 1.3432, + "step": 4470 + }, + { + "epoch": 0.47, + "learning_rate": 1.2793531224539297e-05, + "loss": 1.4347, + "step": 4471 + }, + { + "epoch": 0.47, + "learning_rate": 1.279001650767562e-05, + "loss": 1.3304, + "step": 4472 + }, + { + "epoch": 0.47, + "learning_rate": 1.278650141702142e-05, + "loss": 1.3244, + "step": 4473 + }, + { + "epoch": 0.47, + "learning_rate": 1.2782985953047625e-05, + "loss": 1.3756, + "step": 4474 + }, + { + "epoch": 0.47, + "learning_rate": 1.2779470116225219e-05, + "loss": 1.5468, + "step": 4475 + }, + { + "epoch": 0.47, + "learning_rate": 1.2775953907025232e-05, + "loss": 1.4316, + "step": 4476 + }, + { + "epoch": 0.47, + "learning_rate": 1.2772437325918752e-05, + "loss": 1.3724, + "step": 4477 + }, + { + "epoch": 0.47, + "learning_rate": 1.27689203733769e-05, + "loss": 1.4458, + "step": 4478 + }, + { + "epoch": 0.47, + "learning_rate": 1.2765403049870865e-05, + "loss": 1.3622, + "step": 4479 + }, + { + "epoch": 0.47, + "learning_rate": 1.2761885355871875e-05, + "loss": 1.3875, + "step": 4480 + }, + { + "epoch": 0.47, + "learning_rate": 1.2758367291851217e-05, + "loss": 1.3577, + "step": 4481 + }, + { + "epoch": 0.47, + "learning_rate": 1.2754848858280211e-05, + "loss": 1.4256, + "step": 4482 + }, + { + "epoch": 0.47, + "learning_rate": 1.2751330055630242e-05, + "loss": 1.3771, + "step": 4483 + }, + { + "epoch": 0.47, + "learning_rate": 1.274781088437274e-05, + "loss": 1.357, + "step": 4484 + }, + { + "epoch": 0.47, + "learning_rate": 1.274429134497918e-05, + "loss": 1.3634, + "step": 4485 + }, + { + "epoch": 0.47, + "learning_rate": 1.2740771437921096e-05, + "loss": 1.3661, + "step": 4486 + }, + { + "epoch": 0.47, + "learning_rate": 1.2737251163670057e-05, + "loss": 1.3819, + "step": 4487 + }, + { + "epoch": 0.47, + "learning_rate": 1.2733730522697696e-05, + "loss": 1.4491, + "step": 4488 + }, + { + "epoch": 0.47, + "learning_rate": 1.2730209515475687e-05, + "loss": 1.3857, + "step": 4489 + }, + { + "epoch": 0.47, + "learning_rate": 1.2726688142475751e-05, + "loss": 1.3837, + "step": 4490 + }, + { + "epoch": 0.47, + "learning_rate": 1.2723166404169663e-05, + "loss": 1.3755, + "step": 4491 + }, + { + "epoch": 0.47, + "learning_rate": 1.271964430102925e-05, + "loss": 1.3767, + "step": 4492 + }, + { + "epoch": 0.47, + "learning_rate": 1.2716121833526376e-05, + "loss": 1.4416, + "step": 4493 + }, + { + "epoch": 0.47, + "learning_rate": 1.2712599002132966e-05, + "loss": 1.5573, + "step": 4494 + }, + { + "epoch": 0.47, + "learning_rate": 1.2709075807320988e-05, + "loss": 1.365, + "step": 4495 + }, + { + "epoch": 0.47, + "learning_rate": 1.270555224956246e-05, + "loss": 1.3862, + "step": 4496 + }, + { + "epoch": 0.47, + "learning_rate": 1.2702028329329445e-05, + "loss": 1.3003, + "step": 4497 + }, + { + "epoch": 0.47, + "learning_rate": 1.2698504047094064e-05, + "loss": 1.3806, + "step": 4498 + }, + { + "epoch": 0.47, + "learning_rate": 1.269497940332847e-05, + "loss": 1.5425, + "step": 4499 + }, + { + "epoch": 0.47, + "learning_rate": 1.269145439850489e-05, + "loss": 1.3541, + "step": 4500 + }, + { + "epoch": 0.47, + "learning_rate": 1.268792903309557e-05, + "loss": 1.4337, + "step": 4501 + }, + { + "epoch": 0.47, + "learning_rate": 1.2684403307572825e-05, + "loss": 1.4004, + "step": 4502 + }, + { + "epoch": 0.47, + "learning_rate": 1.268087722240901e-05, + "loss": 1.9453, + "step": 4503 + }, + { + "epoch": 0.47, + "learning_rate": 1.2677350778076532e-05, + "loss": 1.3907, + "step": 4504 + }, + { + "epoch": 0.47, + "learning_rate": 1.2673823975047839e-05, + "loss": 1.4993, + "step": 4505 + }, + { + "epoch": 0.47, + "learning_rate": 1.2670296813795432e-05, + "loss": 1.4386, + "step": 4506 + }, + { + "epoch": 0.47, + "learning_rate": 1.266676929479187e-05, + "loss": 1.4944, + "step": 4507 + }, + { + "epoch": 0.47, + "learning_rate": 1.266324141850974e-05, + "loss": 1.4311, + "step": 4508 + }, + { + "epoch": 0.47, + "learning_rate": 1.265971318542169e-05, + "loss": 1.3607, + "step": 4509 + }, + { + "epoch": 0.47, + "learning_rate": 1.2656184596000412e-05, + "loss": 1.4007, + "step": 4510 + }, + { + "epoch": 0.47, + "learning_rate": 1.2652655650718645e-05, + "loss": 1.4561, + "step": 4511 + }, + { + "epoch": 0.47, + "learning_rate": 1.2649126350049181e-05, + "loss": 1.4321, + "step": 4512 + }, + { + "epoch": 0.47, + "learning_rate": 1.2645596694464851e-05, + "loss": 1.2856, + "step": 4513 + }, + { + "epoch": 0.47, + "learning_rate": 1.2642066684438543e-05, + "loss": 1.3979, + "step": 4514 + }, + { + "epoch": 0.47, + "learning_rate": 1.2638536320443184e-05, + "loss": 1.4977, + "step": 4515 + }, + { + "epoch": 0.47, + "learning_rate": 1.2635005602951752e-05, + "loss": 1.377, + "step": 4516 + }, + { + "epoch": 0.47, + "learning_rate": 1.2631474532437275e-05, + "loss": 1.4266, + "step": 4517 + }, + { + "epoch": 0.47, + "learning_rate": 1.2627943109372822e-05, + "loss": 1.409, + "step": 4518 + }, + { + "epoch": 0.47, + "learning_rate": 1.2624411334231519e-05, + "loss": 1.3374, + "step": 4519 + }, + { + "epoch": 0.47, + "learning_rate": 1.2620879207486525e-05, + "loss": 1.3765, + "step": 4520 + }, + { + "epoch": 0.47, + "learning_rate": 1.2617346729611061e-05, + "loss": 1.3805, + "step": 4521 + }, + { + "epoch": 0.47, + "learning_rate": 1.2613813901078384e-05, + "loss": 1.3326, + "step": 4522 + }, + { + "epoch": 0.47, + "learning_rate": 1.2610280722361807e-05, + "loss": 1.3909, + "step": 4523 + }, + { + "epoch": 0.47, + "learning_rate": 1.260674719393468e-05, + "loss": 1.3815, + "step": 4524 + }, + { + "epoch": 0.47, + "learning_rate": 1.2603213316270409e-05, + "loss": 1.5589, + "step": 4525 + }, + { + "epoch": 0.47, + "learning_rate": 1.2599679089842437e-05, + "loss": 1.4416, + "step": 4526 + }, + { + "epoch": 0.47, + "learning_rate": 1.259614451512427e-05, + "loss": 1.3529, + "step": 4527 + }, + { + "epoch": 0.47, + "learning_rate": 1.2592609592589437e-05, + "loss": 1.3135, + "step": 4528 + }, + { + "epoch": 0.47, + "learning_rate": 1.2589074322711535e-05, + "loss": 1.4177, + "step": 4529 + }, + { + "epoch": 0.48, + "learning_rate": 1.25855387059642e-05, + "loss": 1.353, + "step": 4530 + }, + { + "epoch": 0.48, + "learning_rate": 1.2582002742821111e-05, + "loss": 1.431, + "step": 4531 + }, + { + "epoch": 0.48, + "learning_rate": 1.2578466433755998e-05, + "loss": 1.3803, + "step": 4532 + }, + { + "epoch": 0.48, + "learning_rate": 1.257492977924263e-05, + "loss": 1.3774, + "step": 4533 + }, + { + "epoch": 0.48, + "learning_rate": 1.2571392779754836e-05, + "loss": 1.4339, + "step": 4534 + }, + { + "epoch": 0.48, + "learning_rate": 1.256785543576648e-05, + "loss": 1.4097, + "step": 4535 + }, + { + "epoch": 0.48, + "learning_rate": 1.2564317747751473e-05, + "loss": 1.4223, + "step": 4536 + }, + { + "epoch": 0.48, + "learning_rate": 1.2560779716183775e-05, + "loss": 1.5148, + "step": 4537 + }, + { + "epoch": 0.48, + "learning_rate": 1.2557241341537394e-05, + "loss": 1.3547, + "step": 4538 + }, + { + "epoch": 0.48, + "learning_rate": 1.255370262428638e-05, + "loss": 1.393, + "step": 4539 + }, + { + "epoch": 0.48, + "learning_rate": 1.2550163564904829e-05, + "loss": 1.3312, + "step": 4540 + }, + { + "epoch": 0.48, + "learning_rate": 1.2546624163866882e-05, + "loss": 1.4193, + "step": 4541 + }, + { + "epoch": 0.48, + "learning_rate": 1.2543084421646735e-05, + "loss": 1.4161, + "step": 4542 + }, + { + "epoch": 0.48, + "learning_rate": 1.2539544338718614e-05, + "loss": 1.4224, + "step": 4543 + }, + { + "epoch": 0.48, + "learning_rate": 1.2536003915556805e-05, + "loss": 1.3484, + "step": 4544 + }, + { + "epoch": 0.48, + "learning_rate": 1.253246315263563e-05, + "loss": 1.4492, + "step": 4545 + }, + { + "epoch": 0.48, + "learning_rate": 1.2528922050429467e-05, + "loss": 1.3549, + "step": 4546 + }, + { + "epoch": 0.48, + "learning_rate": 1.252538060941272e-05, + "loss": 1.45, + "step": 4547 + }, + { + "epoch": 0.48, + "learning_rate": 1.2521838830059865e-05, + "loss": 1.3499, + "step": 4548 + }, + { + "epoch": 0.48, + "learning_rate": 1.2518296712845399e-05, + "loss": 1.3786, + "step": 4549 + }, + { + "epoch": 0.48, + "learning_rate": 1.2514754258243884e-05, + "loss": 1.3394, + "step": 4550 + }, + { + "epoch": 0.48, + "learning_rate": 1.2511211466729909e-05, + "loss": 1.2849, + "step": 4551 + }, + { + "epoch": 0.48, + "learning_rate": 1.250766833877812e-05, + "loss": 1.374, + "step": 4552 + }, + { + "epoch": 0.48, + "learning_rate": 1.2504124874863211e-05, + "loss": 1.3084, + "step": 4553 + }, + { + "epoch": 0.48, + "learning_rate": 1.2500581075459905e-05, + "loss": 1.3348, + "step": 4554 + }, + { + "epoch": 0.48, + "learning_rate": 1.249703694104299e-05, + "loss": 1.3797, + "step": 4555 + }, + { + "epoch": 0.48, + "learning_rate": 1.2493492472087279e-05, + "loss": 1.3371, + "step": 4556 + }, + { + "epoch": 0.48, + "learning_rate": 1.248994766906765e-05, + "loss": 1.3974, + "step": 4557 + }, + { + "epoch": 0.48, + "learning_rate": 1.2486402532459007e-05, + "loss": 1.388, + "step": 4558 + }, + { + "epoch": 0.48, + "learning_rate": 1.2482857062736313e-05, + "loss": 1.3619, + "step": 4559 + }, + { + "epoch": 0.48, + "learning_rate": 1.2479311260374565e-05, + "loss": 1.4123, + "step": 4560 + }, + { + "epoch": 0.48, + "learning_rate": 1.2475765125848814e-05, + "loss": 1.5485, + "step": 4561 + }, + { + "epoch": 0.48, + "learning_rate": 1.247221865963415e-05, + "loss": 1.4965, + "step": 4562 + }, + { + "epoch": 0.48, + "learning_rate": 1.2468671862205705e-05, + "loss": 1.4352, + "step": 4563 + }, + { + "epoch": 0.48, + "learning_rate": 1.246512473403866e-05, + "loss": 1.3935, + "step": 4564 + }, + { + "epoch": 0.48, + "learning_rate": 1.2461577275608243e-05, + "loss": 1.3798, + "step": 4565 + }, + { + "epoch": 0.48, + "learning_rate": 1.2458029487389718e-05, + "loss": 1.4039, + "step": 4566 + }, + { + "epoch": 0.48, + "learning_rate": 1.2454481369858397e-05, + "loss": 1.3723, + "step": 4567 + }, + { + "epoch": 0.48, + "learning_rate": 1.245093292348964e-05, + "loss": 1.3713, + "step": 4568 + }, + { + "epoch": 0.48, + "learning_rate": 1.2447384148758847e-05, + "loss": 1.4083, + "step": 4569 + }, + { + "epoch": 0.48, + "learning_rate": 1.244383504614146e-05, + "loss": 1.2811, + "step": 4570 + }, + { + "epoch": 0.48, + "learning_rate": 1.2440285616112968e-05, + "loss": 1.3509, + "step": 4571 + }, + { + "epoch": 0.48, + "learning_rate": 1.2436735859148905e-05, + "loss": 1.3481, + "step": 4572 + }, + { + "epoch": 0.48, + "learning_rate": 1.2433185775724847e-05, + "loss": 1.4168, + "step": 4573 + }, + { + "epoch": 0.48, + "learning_rate": 1.2429635366316418e-05, + "loss": 1.3671, + "step": 4574 + }, + { + "epoch": 0.48, + "learning_rate": 1.2426084631399271e-05, + "loss": 1.6514, + "step": 4575 + }, + { + "epoch": 0.48, + "learning_rate": 1.2422533571449123e-05, + "loss": 1.3564, + "step": 4576 + }, + { + "epoch": 0.48, + "learning_rate": 1.2418982186941721e-05, + "loss": 1.4586, + "step": 4577 + }, + { + "epoch": 0.48, + "eval_loss": 1.4425245523452759, + "eval_runtime": 77.3853, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 4577 + }, + { + "epoch": 0.48, + "learning_rate": 1.2415430478352858e-05, + "loss": 1.3922, + "step": 4578 + }, + { + "epoch": 0.48, + "learning_rate": 1.2411878446158374e-05, + "loss": 1.3903, + "step": 4579 + }, + { + "epoch": 0.48, + "learning_rate": 1.240832609083415e-05, + "loss": 1.3537, + "step": 4580 + }, + { + "epoch": 0.48, + "learning_rate": 1.2404773412856113e-05, + "loss": 1.356, + "step": 4581 + }, + { + "epoch": 0.48, + "learning_rate": 1.2401220412700223e-05, + "loss": 1.4483, + "step": 4582 + }, + { + "epoch": 0.48, + "learning_rate": 1.2397667090842496e-05, + "loss": 1.3926, + "step": 4583 + }, + { + "epoch": 0.48, + "learning_rate": 1.2394113447758986e-05, + "loss": 1.4816, + "step": 4584 + }, + { + "epoch": 0.48, + "learning_rate": 1.2390559483925788e-05, + "loss": 1.3742, + "step": 4585 + }, + { + "epoch": 0.48, + "learning_rate": 1.2387005199819044e-05, + "loss": 1.4476, + "step": 4586 + }, + { + "epoch": 0.48, + "learning_rate": 1.2383450595914932e-05, + "loss": 1.4029, + "step": 4587 + }, + { + "epoch": 0.48, + "learning_rate": 1.2379895672689683e-05, + "loss": 1.4797, + "step": 4588 + }, + { + "epoch": 0.48, + "learning_rate": 1.2376340430619565e-05, + "loss": 1.3366, + "step": 4589 + }, + { + "epoch": 0.48, + "learning_rate": 1.2372784870180885e-05, + "loss": 1.4226, + "step": 4590 + }, + { + "epoch": 0.48, + "learning_rate": 1.2369228991849997e-05, + "loss": 1.3668, + "step": 4591 + }, + { + "epoch": 0.48, + "learning_rate": 1.2365672796103305e-05, + "loss": 1.4932, + "step": 4592 + }, + { + "epoch": 0.48, + "learning_rate": 1.236211628341724e-05, + "loss": 1.4088, + "step": 4593 + }, + { + "epoch": 0.48, + "learning_rate": 1.2358559454268284e-05, + "loss": 1.3616, + "step": 4594 + }, + { + "epoch": 0.48, + "learning_rate": 1.2355002309132961e-05, + "loss": 1.4345, + "step": 4595 + }, + { + "epoch": 0.48, + "learning_rate": 1.2351444848487844e-05, + "loss": 1.4025, + "step": 4596 + }, + { + "epoch": 0.48, + "learning_rate": 1.2347887072809533e-05, + "loss": 1.3895, + "step": 4597 + }, + { + "epoch": 0.48, + "learning_rate": 1.2344328982574678e-05, + "loss": 1.3326, + "step": 4598 + }, + { + "epoch": 0.48, + "learning_rate": 1.234077057825998e-05, + "loss": 1.4249, + "step": 4599 + }, + { + "epoch": 0.48, + "learning_rate": 1.2337211860342167e-05, + "loss": 1.3649, + "step": 4600 + }, + { + "epoch": 0.48, + "learning_rate": 1.2333652829298016e-05, + "loss": 1.3831, + "step": 4601 + }, + { + "epoch": 0.48, + "learning_rate": 1.2330093485604346e-05, + "loss": 1.3748, + "step": 4602 + }, + { + "epoch": 0.48, + "learning_rate": 1.2326533829738022e-05, + "loss": 1.386, + "step": 4603 + }, + { + "epoch": 0.48, + "learning_rate": 1.2322973862175941e-05, + "loss": 1.3923, + "step": 4604 + }, + { + "epoch": 0.48, + "learning_rate": 1.2319413583395052e-05, + "loss": 1.3638, + "step": 4605 + }, + { + "epoch": 0.48, + "learning_rate": 1.2315852993872335e-05, + "loss": 1.3476, + "step": 4606 + }, + { + "epoch": 0.48, + "learning_rate": 1.2312292094084824e-05, + "loss": 1.3581, + "step": 4607 + }, + { + "epoch": 0.48, + "learning_rate": 1.2308730884509583e-05, + "loss": 1.3554, + "step": 4608 + }, + { + "epoch": 0.48, + "learning_rate": 1.2305169365623724e-05, + "loss": 1.3676, + "step": 4609 + }, + { + "epoch": 0.48, + "learning_rate": 1.2301607537904399e-05, + "loss": 1.24, + "step": 4610 + }, + { + "epoch": 0.48, + "learning_rate": 1.2298045401828803e-05, + "loss": 1.3295, + "step": 4611 + }, + { + "epoch": 0.48, + "learning_rate": 1.2294482957874169e-05, + "loss": 1.5684, + "step": 4612 + }, + { + "epoch": 0.48, + "learning_rate": 1.2290920206517774e-05, + "loss": 1.3403, + "step": 4613 + }, + { + "epoch": 0.48, + "learning_rate": 1.2287357148236933e-05, + "loss": 1.349, + "step": 4614 + }, + { + "epoch": 0.48, + "learning_rate": 1.2283793783509008e-05, + "loss": 1.4261, + "step": 4615 + }, + { + "epoch": 0.48, + "learning_rate": 1.2280230112811395e-05, + "loss": 1.322, + "step": 4616 + }, + { + "epoch": 0.48, + "learning_rate": 1.2276666136621538e-05, + "loss": 1.3399, + "step": 4617 + }, + { + "epoch": 0.48, + "learning_rate": 1.2273101855416912e-05, + "loss": 1.3878, + "step": 4618 + }, + { + "epoch": 0.48, + "learning_rate": 1.2269537269675044e-05, + "loss": 1.4733, + "step": 4619 + }, + { + "epoch": 0.48, + "learning_rate": 1.2265972379873497e-05, + "loss": 1.419, + "step": 4620 + }, + { + "epoch": 0.48, + "learning_rate": 1.226240718648987e-05, + "loss": 1.3918, + "step": 4621 + }, + { + "epoch": 0.48, + "learning_rate": 1.2258841690001815e-05, + "loss": 1.3398, + "step": 4622 + }, + { + "epoch": 0.48, + "learning_rate": 1.225527589088701e-05, + "loss": 1.4091, + "step": 4623 + }, + { + "epoch": 0.48, + "learning_rate": 1.2251709789623185e-05, + "loss": 1.3291, + "step": 4624 + }, + { + "epoch": 0.49, + "learning_rate": 1.2248143386688101e-05, + "loss": 1.4288, + "step": 4625 + }, + { + "epoch": 0.49, + "learning_rate": 1.224457668255957e-05, + "loss": 1.2942, + "step": 4626 + }, + { + "epoch": 0.49, + "learning_rate": 1.2241009677715437e-05, + "loss": 1.4014, + "step": 4627 + }, + { + "epoch": 0.49, + "learning_rate": 1.2237442372633586e-05, + "loss": 1.3823, + "step": 4628 + }, + { + "epoch": 0.49, + "learning_rate": 1.2233874767791945e-05, + "loss": 1.3556, + "step": 4629 + }, + { + "epoch": 0.49, + "learning_rate": 1.2230306863668485e-05, + "loss": 1.411, + "step": 4630 + }, + { + "epoch": 0.49, + "learning_rate": 1.2226738660741212e-05, + "loss": 1.4347, + "step": 4631 + }, + { + "epoch": 0.49, + "learning_rate": 1.2223170159488169e-05, + "loss": 1.3095, + "step": 4632 + }, + { + "epoch": 0.49, + "learning_rate": 1.221960136038745e-05, + "loss": 1.4272, + "step": 4633 + }, + { + "epoch": 0.49, + "learning_rate": 1.221603226391718e-05, + "loss": 1.367, + "step": 4634 + }, + { + "epoch": 0.49, + "learning_rate": 1.2212462870555523e-05, + "loss": 1.3357, + "step": 4635 + }, + { + "epoch": 0.49, + "learning_rate": 1.220889318078069e-05, + "loss": 1.3634, + "step": 4636 + }, + { + "epoch": 0.49, + "learning_rate": 1.2205323195070927e-05, + "loss": 1.4143, + "step": 4637 + }, + { + "epoch": 0.49, + "learning_rate": 1.2201752913904519e-05, + "loss": 1.4865, + "step": 4638 + }, + { + "epoch": 0.49, + "learning_rate": 1.2198182337759794e-05, + "loss": 1.451, + "step": 4639 + }, + { + "epoch": 0.49, + "learning_rate": 1.2194611467115116e-05, + "loss": 1.3953, + "step": 4640 + }, + { + "epoch": 0.49, + "learning_rate": 1.2191040302448887e-05, + "loss": 1.4099, + "step": 4641 + }, + { + "epoch": 0.49, + "learning_rate": 1.2187468844239559e-05, + "loss": 1.3338, + "step": 4642 + }, + { + "epoch": 0.49, + "learning_rate": 1.2183897092965609e-05, + "loss": 1.4392, + "step": 4643 + }, + { + "epoch": 0.49, + "learning_rate": 1.2180325049105559e-05, + "loss": 1.3196, + "step": 4644 + }, + { + "epoch": 0.49, + "learning_rate": 1.2176752713137977e-05, + "loss": 1.3727, + "step": 4645 + }, + { + "epoch": 0.49, + "learning_rate": 1.2173180085541464e-05, + "loss": 1.3118, + "step": 4646 + }, + { + "epoch": 0.49, + "learning_rate": 1.2169607166794655e-05, + "loss": 1.3695, + "step": 4647 + }, + { + "epoch": 0.49, + "learning_rate": 1.2166033957376231e-05, + "loss": 1.3568, + "step": 4648 + }, + { + "epoch": 0.49, + "learning_rate": 1.216246045776491e-05, + "loss": 1.3492, + "step": 4649 + }, + { + "epoch": 0.49, + "learning_rate": 1.2158886668439455e-05, + "loss": 1.3445, + "step": 4650 + }, + { + "epoch": 0.49, + "learning_rate": 1.2155312589878654e-05, + "loss": 1.3756, + "step": 4651 + }, + { + "epoch": 0.49, + "learning_rate": 1.2151738222561344e-05, + "loss": 1.3681, + "step": 4652 + }, + { + "epoch": 0.49, + "learning_rate": 1.2148163566966403e-05, + "loss": 1.4345, + "step": 4653 + }, + { + "epoch": 0.49, + "learning_rate": 1.2144588623572738e-05, + "loss": 1.5102, + "step": 4654 + }, + { + "epoch": 0.49, + "learning_rate": 1.2141013392859297e-05, + "loss": 1.3531, + "step": 4655 + }, + { + "epoch": 0.49, + "learning_rate": 1.2137437875305075e-05, + "loss": 1.3824, + "step": 4656 + }, + { + "epoch": 0.49, + "learning_rate": 1.2133862071389099e-05, + "loss": 1.4227, + "step": 4657 + }, + { + "epoch": 0.49, + "learning_rate": 1.2130285981590433e-05, + "loss": 1.3479, + "step": 4658 + }, + { + "epoch": 0.49, + "learning_rate": 1.2126709606388181e-05, + "loss": 1.381, + "step": 4659 + }, + { + "epoch": 0.49, + "learning_rate": 1.2123132946261485e-05, + "loss": 1.3847, + "step": 4660 + }, + { + "epoch": 0.49, + "learning_rate": 1.2119556001689527e-05, + "loss": 1.3549, + "step": 4661 + }, + { + "epoch": 0.49, + "learning_rate": 1.2115978773151527e-05, + "loss": 1.3754, + "step": 4662 + }, + { + "epoch": 0.49, + "learning_rate": 1.2112401261126736e-05, + "loss": 1.3329, + "step": 4663 + }, + { + "epoch": 0.49, + "learning_rate": 1.2108823466094453e-05, + "loss": 1.4228, + "step": 4664 + }, + { + "epoch": 0.49, + "learning_rate": 1.2105245388534013e-05, + "loss": 1.4138, + "step": 4665 + }, + { + "epoch": 0.49, + "learning_rate": 1.2101667028924782e-05, + "loss": 1.3538, + "step": 4666 + }, + { + "epoch": 0.49, + "learning_rate": 1.2098088387746168e-05, + "loss": 1.4848, + "step": 4667 + }, + { + "epoch": 0.49, + "learning_rate": 1.2094509465477619e-05, + "loss": 1.5719, + "step": 4668 + }, + { + "epoch": 0.49, + "learning_rate": 1.209093026259862e-05, + "loss": 1.3863, + "step": 4669 + }, + { + "epoch": 0.49, + "learning_rate": 1.2087350779588691e-05, + "loss": 1.4425, + "step": 4670 + }, + { + "epoch": 0.49, + "learning_rate": 1.2083771016927386e-05, + "loss": 1.3655, + "step": 4671 + }, + { + "epoch": 0.49, + "learning_rate": 1.208019097509431e-05, + "loss": 1.3629, + "step": 4672 + }, + { + "epoch": 0.49, + "learning_rate": 1.2076610654569092e-05, + "loss": 1.3849, + "step": 4673 + }, + { + "epoch": 0.49, + "learning_rate": 1.20730300558314e-05, + "loss": 1.3763, + "step": 4674 + }, + { + "epoch": 0.49, + "learning_rate": 1.2069449179360945e-05, + "loss": 1.5316, + "step": 4675 + }, + { + "epoch": 0.49, + "learning_rate": 1.2065868025637476e-05, + "loss": 1.2873, + "step": 4676 + }, + { + "epoch": 0.49, + "learning_rate": 1.2062286595140773e-05, + "loss": 1.3642, + "step": 4677 + }, + { + "epoch": 0.49, + "learning_rate": 1.2058704888350652e-05, + "loss": 1.3782, + "step": 4678 + }, + { + "epoch": 0.49, + "learning_rate": 1.2055122905746972e-05, + "loss": 1.4597, + "step": 4679 + }, + { + "epoch": 0.49, + "learning_rate": 1.205154064780963e-05, + "loss": 1.3952, + "step": 4680 + }, + { + "epoch": 0.49, + "learning_rate": 1.2047958115018554e-05, + "loss": 1.4012, + "step": 4681 + }, + { + "epoch": 0.49, + "learning_rate": 1.204437530785371e-05, + "loss": 1.3432, + "step": 4682 + }, + { + "epoch": 0.49, + "learning_rate": 1.2040792226795101e-05, + "loss": 1.4111, + "step": 4683 + }, + { + "epoch": 0.49, + "learning_rate": 1.2037208872322773e-05, + "loss": 1.4357, + "step": 4684 + }, + { + "epoch": 0.49, + "learning_rate": 1.2033625244916803e-05, + "loss": 1.3908, + "step": 4685 + }, + { + "epoch": 0.49, + "learning_rate": 1.2030041345057298e-05, + "loss": 1.3804, + "step": 4686 + }, + { + "epoch": 0.49, + "learning_rate": 1.2026457173224412e-05, + "loss": 1.4523, + "step": 4687 + }, + { + "epoch": 0.49, + "learning_rate": 1.2022872729898336e-05, + "loss": 1.4266, + "step": 4688 + }, + { + "epoch": 0.49, + "learning_rate": 1.201928801555929e-05, + "loss": 1.3345, + "step": 4689 + }, + { + "epoch": 0.49, + "learning_rate": 1.2015703030687532e-05, + "loss": 1.1714, + "step": 4690 + }, + { + "epoch": 0.49, + "learning_rate": 1.2012117775763361e-05, + "loss": 1.3899, + "step": 4691 + }, + { + "epoch": 0.49, + "learning_rate": 1.2008532251267109e-05, + "loss": 1.43, + "step": 4692 + }, + { + "epoch": 0.49, + "learning_rate": 1.2004946457679144e-05, + "loss": 1.4302, + "step": 4693 + }, + { + "epoch": 0.49, + "learning_rate": 1.2001360395479865e-05, + "loss": 1.3452, + "step": 4694 + }, + { + "epoch": 0.49, + "learning_rate": 1.1997774065149716e-05, + "loss": 1.3383, + "step": 4695 + }, + { + "epoch": 0.49, + "learning_rate": 1.1994187467169176e-05, + "loss": 1.3677, + "step": 4696 + }, + { + "epoch": 0.49, + "learning_rate": 1.1990600602018755e-05, + "loss": 1.4486, + "step": 4697 + }, + { + "epoch": 0.49, + "learning_rate": 1.1987013470178998e-05, + "loss": 1.4059, + "step": 4698 + }, + { + "epoch": 0.49, + "learning_rate": 1.198342607213049e-05, + "loss": 1.3558, + "step": 4699 + }, + { + "epoch": 0.49, + "learning_rate": 1.1979838408353854e-05, + "loss": 1.3931, + "step": 4700 + }, + { + "epoch": 0.49, + "learning_rate": 1.197625047932974e-05, + "loss": 1.5409, + "step": 4701 + }, + { + "epoch": 0.49, + "learning_rate": 1.197266228553884e-05, + "loss": 1.4878, + "step": 4702 + }, + { + "epoch": 0.49, + "learning_rate": 1.196907382746188e-05, + "loss": 1.3581, + "step": 4703 + }, + { + "epoch": 0.49, + "learning_rate": 1.1965485105579621e-05, + "loss": 1.3617, + "step": 4704 + }, + { + "epoch": 0.49, + "learning_rate": 1.1961896120372857e-05, + "loss": 1.399, + "step": 4705 + }, + { + "epoch": 0.49, + "learning_rate": 1.1958306872322425e-05, + "loss": 1.3861, + "step": 4706 + }, + { + "epoch": 0.49, + "learning_rate": 1.1954717361909186e-05, + "loss": 1.4719, + "step": 4707 + }, + { + "epoch": 0.49, + "learning_rate": 1.195112758961405e-05, + "loss": 1.393, + "step": 4708 + }, + { + "epoch": 0.49, + "learning_rate": 1.1947537555917947e-05, + "loss": 1.4252, + "step": 4709 + }, + { + "epoch": 0.49, + "learning_rate": 1.194394726130185e-05, + "loss": 1.4187, + "step": 4710 + }, + { + "epoch": 0.49, + "learning_rate": 1.1940356706246772e-05, + "loss": 1.4822, + "step": 4711 + }, + { + "epoch": 0.49, + "learning_rate": 1.193676589123375e-05, + "loss": 1.4259, + "step": 4712 + }, + { + "epoch": 0.49, + "learning_rate": 1.1933174816743857e-05, + "loss": 1.4226, + "step": 4713 + }, + { + "epoch": 0.49, + "learning_rate": 1.1929583483258216e-05, + "loss": 1.3701, + "step": 4714 + }, + { + "epoch": 0.49, + "learning_rate": 1.1925991891257967e-05, + "loss": 1.406, + "step": 4715 + }, + { + "epoch": 0.49, + "learning_rate": 1.1922400041224288e-05, + "loss": 1.4593, + "step": 4716 + }, + { + "epoch": 0.49, + "learning_rate": 1.1918807933638401e-05, + "loss": 1.3443, + "step": 4717 + }, + { + "epoch": 0.49, + "learning_rate": 1.1915215568981552e-05, + "loss": 1.3523, + "step": 4718 + }, + { + "epoch": 0.49, + "learning_rate": 1.1911622947735027e-05, + "loss": 1.3175, + "step": 4719 + }, + { + "epoch": 0.49, + "learning_rate": 1.1908030070380143e-05, + "loss": 1.3974, + "step": 4720 + }, + { + "epoch": 0.5, + "learning_rate": 1.1904436937398257e-05, + "loss": 1.386, + "step": 4721 + }, + { + "epoch": 0.5, + "learning_rate": 1.1900843549270753e-05, + "loss": 1.3684, + "step": 4722 + }, + { + "epoch": 0.5, + "learning_rate": 1.1897249906479054e-05, + "loss": 1.383, + "step": 4723 + }, + { + "epoch": 0.5, + "learning_rate": 1.1893656009504617e-05, + "loss": 1.38, + "step": 4724 + }, + { + "epoch": 0.5, + "learning_rate": 1.1890061858828928e-05, + "loss": 1.3844, + "step": 4725 + }, + { + "epoch": 0.5, + "learning_rate": 1.1886467454933515e-05, + "loss": 1.3252, + "step": 4726 + }, + { + "epoch": 0.5, + "learning_rate": 1.1882872798299934e-05, + "loss": 1.3434, + "step": 4727 + }, + { + "epoch": 0.5, + "learning_rate": 1.1879277889409779e-05, + "loss": 1.4115, + "step": 4728 + }, + { + "epoch": 0.5, + "learning_rate": 1.1875682728744669e-05, + "loss": 1.1911, + "step": 4729 + }, + { + "epoch": 0.5, + "learning_rate": 1.1872087316786272e-05, + "loss": 1.2794, + "step": 4730 + }, + { + "epoch": 0.5, + "learning_rate": 1.1868491654016274e-05, + "loss": 1.3961, + "step": 4731 + }, + { + "epoch": 0.5, + "learning_rate": 1.1864895740916404e-05, + "loss": 1.4965, + "step": 4732 + }, + { + "epoch": 0.5, + "learning_rate": 1.1861299577968419e-05, + "loss": 1.3932, + "step": 4733 + }, + { + "epoch": 0.5, + "learning_rate": 1.185770316565412e-05, + "loss": 1.3926, + "step": 4734 + }, + { + "epoch": 0.5, + "learning_rate": 1.1854106504455327e-05, + "loss": 1.3964, + "step": 4735 + }, + { + "epoch": 0.5, + "learning_rate": 1.1850509594853901e-05, + "loss": 1.3666, + "step": 4736 + }, + { + "epoch": 0.5, + "learning_rate": 1.1846912437331736e-05, + "loss": 1.4364, + "step": 4737 + }, + { + "epoch": 0.5, + "learning_rate": 1.1843315032370762e-05, + "loss": 1.3537, + "step": 4738 + }, + { + "epoch": 0.5, + "learning_rate": 1.1839717380452935e-05, + "loss": 1.4083, + "step": 4739 + }, + { + "epoch": 0.5, + "learning_rate": 1.1836119482060247e-05, + "loss": 1.3881, + "step": 4740 + }, + { + "epoch": 0.5, + "learning_rate": 1.1832521337674727e-05, + "loss": 1.4127, + "step": 4741 + }, + { + "epoch": 0.5, + "learning_rate": 1.1828922947778436e-05, + "loss": 1.3433, + "step": 4742 + }, + { + "epoch": 0.5, + "learning_rate": 1.1825324312853461e-05, + "loss": 1.486, + "step": 4743 + }, + { + "epoch": 0.5, + "learning_rate": 1.1821725433381925e-05, + "loss": 1.335, + "step": 4744 + }, + { + "epoch": 0.5, + "learning_rate": 1.1818126309845993e-05, + "loss": 1.3827, + "step": 4745 + }, + { + "epoch": 0.5, + "learning_rate": 1.181452694272785e-05, + "loss": 1.3146, + "step": 4746 + }, + { + "epoch": 0.5, + "learning_rate": 1.1810927332509717e-05, + "loss": 1.3543, + "step": 4747 + }, + { + "epoch": 0.5, + "learning_rate": 1.1807327479673852e-05, + "loss": 1.3544, + "step": 4748 + }, + { + "epoch": 0.5, + "learning_rate": 1.1803727384702543e-05, + "loss": 1.3677, + "step": 4749 + }, + { + "epoch": 0.5, + "learning_rate": 1.1800127048078111e-05, + "loss": 1.3842, + "step": 4750 + }, + { + "epoch": 0.5, + "learning_rate": 1.1796526470282907e-05, + "loss": 1.3495, + "step": 4751 + }, + { + "epoch": 0.5, + "learning_rate": 1.1792925651799314e-05, + "loss": 1.481, + "step": 4752 + }, + { + "epoch": 0.5, + "learning_rate": 1.1789324593109754e-05, + "loss": 1.3482, + "step": 4753 + }, + { + "epoch": 0.5, + "learning_rate": 1.1785723294696673e-05, + "loss": 1.2805, + "step": 4754 + }, + { + "epoch": 0.5, + "learning_rate": 1.1782121757042555e-05, + "loss": 1.3458, + "step": 4755 + }, + { + "epoch": 0.5, + "learning_rate": 1.1778519980629907e-05, + "loss": 1.3937, + "step": 4756 + }, + { + "epoch": 0.5, + "learning_rate": 1.1774917965941284e-05, + "loss": 1.3873, + "step": 4757 + }, + { + "epoch": 0.5, + "learning_rate": 1.1771315713459258e-05, + "loss": 1.3512, + "step": 4758 + }, + { + "epoch": 0.5, + "learning_rate": 1.1767713223666436e-05, + "loss": 1.4465, + "step": 4759 + }, + { + "epoch": 0.5, + "learning_rate": 1.1764110497045463e-05, + "loss": 1.4233, + "step": 4760 + }, + { + "epoch": 0.5, + "learning_rate": 1.1760507534079011e-05, + "loss": 1.4818, + "step": 4761 + }, + { + "epoch": 0.5, + "learning_rate": 1.1756904335249786e-05, + "loss": 1.2933, + "step": 4762 + }, + { + "epoch": 0.5, + "learning_rate": 1.1753300901040518e-05, + "loss": 1.3524, + "step": 4763 + }, + { + "epoch": 0.5, + "learning_rate": 1.1749697231933981e-05, + "loss": 1.4909, + "step": 4764 + }, + { + "epoch": 0.5, + "learning_rate": 1.1746093328412975e-05, + "loss": 1.2912, + "step": 4765 + }, + { + "epoch": 0.5, + "learning_rate": 1.1742489190960325e-05, + "loss": 1.3372, + "step": 4766 + }, + { + "epoch": 0.5, + "learning_rate": 1.1738884820058893e-05, + "loss": 1.3036, + "step": 4767 + }, + { + "epoch": 0.5, + "learning_rate": 1.1735280216191578e-05, + "loss": 1.3189, + "step": 4768 + }, + { + "epoch": 0.5, + "learning_rate": 1.1731675379841298e-05, + "loss": 1.4146, + "step": 4769 + }, + { + "epoch": 0.5, + "learning_rate": 1.1728070311491013e-05, + "loss": 1.3309, + "step": 4770 + }, + { + "epoch": 0.5, + "learning_rate": 1.1724465011623705e-05, + "loss": 1.3427, + "step": 4771 + }, + { + "epoch": 0.5, + "learning_rate": 1.1720859480722395e-05, + "loss": 1.4033, + "step": 4772 + }, + { + "epoch": 0.5, + "learning_rate": 1.1717253719270135e-05, + "loss": 1.3832, + "step": 4773 + }, + { + "epoch": 0.5, + "learning_rate": 1.1713647727749994e-05, + "loss": 1.4074, + "step": 4774 + }, + { + "epoch": 0.5, + "learning_rate": 1.1710041506645092e-05, + "loss": 1.3579, + "step": 4775 + }, + { + "epoch": 0.5, + "learning_rate": 1.1706435056438564e-05, + "loss": 1.3685, + "step": 4776 + }, + { + "epoch": 0.5, + "eval_loss": 1.436767816543579, + "eval_runtime": 77.4332, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4776 + }, + { + "epoch": 0.5, + "learning_rate": 1.1702828377613584e-05, + "loss": 1.5843, + "step": 4777 + }, + { + "epoch": 0.5, + "learning_rate": 1.1699221470653355e-05, + "loss": 1.4168, + "step": 4778 + }, + { + "epoch": 0.5, + "learning_rate": 1.1695614336041108e-05, + "loss": 1.3515, + "step": 4779 + }, + { + "epoch": 0.5, + "learning_rate": 1.169200697426011e-05, + "loss": 1.3214, + "step": 4780 + }, + { + "epoch": 0.5, + "learning_rate": 1.1688399385793652e-05, + "loss": 1.3728, + "step": 4781 + }, + { + "epoch": 0.5, + "learning_rate": 1.1684791571125054e-05, + "loss": 1.3759, + "step": 4782 + }, + { + "epoch": 0.5, + "learning_rate": 1.1681183530737678e-05, + "loss": 1.4955, + "step": 4783 + }, + { + "epoch": 0.5, + "learning_rate": 1.1677575265114904e-05, + "loss": 1.4284, + "step": 4784 + }, + { + "epoch": 0.5, + "learning_rate": 1.1673966774740151e-05, + "loss": 1.3725, + "step": 4785 + }, + { + "epoch": 0.5, + "learning_rate": 1.1670358060096858e-05, + "loss": 1.3612, + "step": 4786 + }, + { + "epoch": 0.5, + "learning_rate": 1.1666749121668506e-05, + "loss": 1.3021, + "step": 4787 + }, + { + "epoch": 0.5, + "learning_rate": 1.1663139959938597e-05, + "loss": 1.4399, + "step": 4788 + }, + { + "epoch": 0.5, + "learning_rate": 1.1659530575390668e-05, + "loss": 1.3511, + "step": 4789 + }, + { + "epoch": 0.5, + "learning_rate": 1.1655920968508276e-05, + "loss": 1.4211, + "step": 4790 + }, + { + "epoch": 0.5, + "learning_rate": 1.1652311139775028e-05, + "loss": 1.343, + "step": 4791 + }, + { + "epoch": 0.5, + "learning_rate": 1.1648701089674541e-05, + "loss": 1.3838, + "step": 4792 + }, + { + "epoch": 0.5, + "learning_rate": 1.164509081869047e-05, + "loss": 1.342, + "step": 4793 + }, + { + "epoch": 0.5, + "learning_rate": 1.1641480327306494e-05, + "loss": 1.3831, + "step": 4794 + }, + { + "epoch": 0.5, + "learning_rate": 1.1637869616006335e-05, + "loss": 1.4102, + "step": 4795 + }, + { + "epoch": 0.5, + "learning_rate": 1.1634258685273732e-05, + "loss": 1.4184, + "step": 4796 + }, + { + "epoch": 0.5, + "learning_rate": 1.1630647535592455e-05, + "loss": 1.3974, + "step": 4797 + }, + { + "epoch": 0.5, + "learning_rate": 1.1627036167446302e-05, + "loss": 1.251, + "step": 4798 + }, + { + "epoch": 0.5, + "learning_rate": 1.1623424581319113e-05, + "loss": 1.3485, + "step": 4799 + }, + { + "epoch": 0.5, + "learning_rate": 1.1619812777694742e-05, + "loss": 1.3544, + "step": 4800 + }, + { + "epoch": 0.5, + "learning_rate": 1.1616200757057076e-05, + "loss": 1.3772, + "step": 4801 + }, + { + "epoch": 0.5, + "learning_rate": 1.1612588519890038e-05, + "loss": 1.3082, + "step": 4802 + }, + { + "epoch": 0.5, + "learning_rate": 1.160897606667757e-05, + "loss": 1.3634, + "step": 4803 + }, + { + "epoch": 0.5, + "learning_rate": 1.1605363397903655e-05, + "loss": 1.3682, + "step": 4804 + }, + { + "epoch": 0.5, + "learning_rate": 1.1601750514052288e-05, + "loss": 1.3258, + "step": 4805 + }, + { + "epoch": 0.5, + "learning_rate": 1.1598137415607511e-05, + "loss": 1.279, + "step": 4806 + }, + { + "epoch": 0.5, + "learning_rate": 1.1594524103053382e-05, + "loss": 1.3759, + "step": 4807 + }, + { + "epoch": 0.5, + "learning_rate": 1.1590910576873995e-05, + "loss": 1.5404, + "step": 4808 + }, + { + "epoch": 0.5, + "learning_rate": 1.1587296837553463e-05, + "loss": 1.4949, + "step": 4809 + }, + { + "epoch": 0.5, + "learning_rate": 1.1583682885575943e-05, + "loss": 1.3501, + "step": 4810 + }, + { + "epoch": 0.5, + "learning_rate": 1.1580068721425608e-05, + "loss": 1.3898, + "step": 4811 + }, + { + "epoch": 0.5, + "learning_rate": 1.157645434558666e-05, + "loss": 1.3265, + "step": 4812 + }, + { + "epoch": 0.5, + "learning_rate": 1.1572839758543338e-05, + "loss": 1.3454, + "step": 4813 + }, + { + "epoch": 0.5, + "learning_rate": 1.1569224960779899e-05, + "loss": 1.4065, + "step": 4814 + }, + { + "epoch": 0.5, + "learning_rate": 1.156560995278064e-05, + "loss": 1.4932, + "step": 4815 + }, + { + "epoch": 0.51, + "learning_rate": 1.156199473502987e-05, + "loss": 1.4224, + "step": 4816 + }, + { + "epoch": 0.51, + "learning_rate": 1.1558379308011937e-05, + "loss": 1.3884, + "step": 4817 + }, + { + "epoch": 0.51, + "learning_rate": 1.1554763672211222e-05, + "loss": 1.3355, + "step": 4818 + }, + { + "epoch": 0.51, + "learning_rate": 1.1551147828112124e-05, + "loss": 1.4281, + "step": 4819 + }, + { + "epoch": 0.51, + "learning_rate": 1.1547531776199072e-05, + "loss": 1.3148, + "step": 4820 + }, + { + "epoch": 0.51, + "learning_rate": 1.1543915516956523e-05, + "loss": 1.3255, + "step": 4821 + }, + { + "epoch": 0.51, + "learning_rate": 1.1540299050868966e-05, + "loss": 1.3361, + "step": 4822 + }, + { + "epoch": 0.51, + "learning_rate": 1.1536682378420912e-05, + "loss": 1.3377, + "step": 4823 + }, + { + "epoch": 0.51, + "learning_rate": 1.1533065500096901e-05, + "loss": 1.4205, + "step": 4824 + }, + { + "epoch": 0.51, + "learning_rate": 1.1529448416381505e-05, + "loss": 1.4193, + "step": 4825 + }, + { + "epoch": 0.51, + "learning_rate": 1.1525831127759322e-05, + "loss": 1.37, + "step": 4826 + }, + { + "epoch": 0.51, + "learning_rate": 1.1522213634714971e-05, + "loss": 1.3642, + "step": 4827 + }, + { + "epoch": 0.51, + "learning_rate": 1.1518595937733103e-05, + "loss": 1.4834, + "step": 4828 + }, + { + "epoch": 0.51, + "learning_rate": 1.1514978037298402e-05, + "loss": 1.2864, + "step": 4829 + }, + { + "epoch": 0.51, + "learning_rate": 1.1511359933895567e-05, + "loss": 1.3468, + "step": 4830 + }, + { + "epoch": 0.51, + "learning_rate": 1.1507741628009337e-05, + "loss": 1.328, + "step": 4831 + }, + { + "epoch": 0.51, + "learning_rate": 1.1504123120124466e-05, + "loss": 1.3489, + "step": 4832 + }, + { + "epoch": 0.51, + "learning_rate": 1.1500504410725746e-05, + "loss": 1.4031, + "step": 4833 + }, + { + "epoch": 0.51, + "learning_rate": 1.149688550029799e-05, + "loss": 1.3482, + "step": 4834 + }, + { + "epoch": 0.51, + "learning_rate": 1.1493266389326037e-05, + "loss": 1.3674, + "step": 4835 + }, + { + "epoch": 0.51, + "learning_rate": 1.1489647078294753e-05, + "loss": 1.2895, + "step": 4836 + }, + { + "epoch": 0.51, + "learning_rate": 1.148602756768904e-05, + "loss": 1.4071, + "step": 4837 + }, + { + "epoch": 0.51, + "learning_rate": 1.1482407857993814e-05, + "loss": 1.5218, + "step": 4838 + }, + { + "epoch": 0.51, + "learning_rate": 1.1478787949694024e-05, + "loss": 1.4577, + "step": 4839 + }, + { + "epoch": 0.51, + "learning_rate": 1.1475167843274643e-05, + "loss": 1.3817, + "step": 4840 + }, + { + "epoch": 0.51, + "learning_rate": 1.1471547539220678e-05, + "loss": 1.3072, + "step": 4841 + }, + { + "epoch": 0.51, + "learning_rate": 1.146792703801715e-05, + "loss": 1.3737, + "step": 4842 + }, + { + "epoch": 0.51, + "learning_rate": 1.1464306340149119e-05, + "loss": 1.4001, + "step": 4843 + }, + { + "epoch": 0.51, + "learning_rate": 1.1460685446101658e-05, + "loss": 1.3963, + "step": 4844 + }, + { + "epoch": 0.51, + "learning_rate": 1.1457064356359882e-05, + "loss": 1.4061, + "step": 4845 + }, + { + "epoch": 0.51, + "learning_rate": 1.145344307140892e-05, + "loss": 1.4211, + "step": 4846 + }, + { + "epoch": 0.51, + "learning_rate": 1.144982159173393e-05, + "loss": 1.3197, + "step": 4847 + }, + { + "epoch": 0.51, + "learning_rate": 1.14461999178201e-05, + "loss": 1.3549, + "step": 4848 + }, + { + "epoch": 0.51, + "learning_rate": 1.1442578050152639e-05, + "loss": 1.3889, + "step": 4849 + }, + { + "epoch": 0.51, + "learning_rate": 1.1438955989216787e-05, + "loss": 1.3847, + "step": 4850 + }, + { + "epoch": 0.51, + "learning_rate": 1.1435333735497803e-05, + "loss": 1.3586, + "step": 4851 + }, + { + "epoch": 0.51, + "learning_rate": 1.1431711289480978e-05, + "loss": 1.503, + "step": 4852 + }, + { + "epoch": 0.51, + "learning_rate": 1.1428088651651627e-05, + "loss": 1.3654, + "step": 4853 + }, + { + "epoch": 0.51, + "learning_rate": 1.1424465822495092e-05, + "loss": 1.3741, + "step": 4854 + }, + { + "epoch": 0.51, + "learning_rate": 1.1420842802496737e-05, + "loss": 1.5437, + "step": 4855 + }, + { + "epoch": 0.51, + "learning_rate": 1.1417219592141953e-05, + "loss": 1.2179, + "step": 4856 + }, + { + "epoch": 0.51, + "learning_rate": 1.1413596191916159e-05, + "loss": 1.3939, + "step": 4857 + }, + { + "epoch": 0.51, + "learning_rate": 1.1409972602304796e-05, + "loss": 1.3383, + "step": 4858 + }, + { + "epoch": 0.51, + "learning_rate": 1.140634882379333e-05, + "loss": 1.3664, + "step": 4859 + }, + { + "epoch": 0.51, + "learning_rate": 1.1402724856867258e-05, + "loss": 1.4002, + "step": 4860 + }, + { + "epoch": 0.51, + "learning_rate": 1.1399100702012098e-05, + "loss": 1.2975, + "step": 4861 + }, + { + "epoch": 0.51, + "learning_rate": 1.1395476359713394e-05, + "loss": 1.3564, + "step": 4862 + }, + { + "epoch": 0.51, + "learning_rate": 1.1391851830456708e-05, + "loss": 1.3574, + "step": 4863 + }, + { + "epoch": 0.51, + "learning_rate": 1.1388227114727644e-05, + "loss": 1.3407, + "step": 4864 + }, + { + "epoch": 0.51, + "learning_rate": 1.1384602213011815e-05, + "loss": 1.3603, + "step": 4865 + }, + { + "epoch": 0.51, + "learning_rate": 1.1380977125794866e-05, + "loss": 1.3465, + "step": 4866 + }, + { + "epoch": 0.51, + "learning_rate": 1.1377351853562461e-05, + "loss": 1.3744, + "step": 4867 + }, + { + "epoch": 0.51, + "learning_rate": 1.1373726396800304e-05, + "loss": 1.3248, + "step": 4868 + }, + { + "epoch": 0.51, + "learning_rate": 1.1370100755994102e-05, + "loss": 1.3352, + "step": 4869 + }, + { + "epoch": 0.51, + "learning_rate": 1.1366474931629603e-05, + "loss": 1.3299, + "step": 4870 + }, + { + "epoch": 0.51, + "learning_rate": 1.1362848924192575e-05, + "loss": 1.344, + "step": 4871 + }, + { + "epoch": 0.51, + "learning_rate": 1.1359222734168809e-05, + "loss": 1.3209, + "step": 4872 + }, + { + "epoch": 0.51, + "learning_rate": 1.135559636204412e-05, + "loss": 1.3927, + "step": 4873 + }, + { + "epoch": 0.51, + "learning_rate": 1.1351969808304349e-05, + "loss": 1.3717, + "step": 4874 + }, + { + "epoch": 0.51, + "learning_rate": 1.1348343073435362e-05, + "loss": 1.3813, + "step": 4875 + }, + { + "epoch": 0.51, + "learning_rate": 1.1344716157923046e-05, + "loss": 1.236, + "step": 4876 + }, + { + "epoch": 0.51, + "learning_rate": 1.1341089062253319e-05, + "loss": 1.2591, + "step": 4877 + }, + { + "epoch": 0.51, + "learning_rate": 1.1337461786912112e-05, + "loss": 1.3211, + "step": 4878 + }, + { + "epoch": 0.51, + "learning_rate": 1.1333834332385394e-05, + "loss": 1.4534, + "step": 4879 + }, + { + "epoch": 0.51, + "learning_rate": 1.1330206699159145e-05, + "loss": 1.346, + "step": 4880 + }, + { + "epoch": 0.51, + "learning_rate": 1.132657888771938e-05, + "loss": 1.3952, + "step": 4881 + }, + { + "epoch": 0.51, + "learning_rate": 1.1322950898552125e-05, + "loss": 1.3008, + "step": 4882 + }, + { + "epoch": 0.51, + "learning_rate": 1.1319322732143445e-05, + "loss": 1.3201, + "step": 4883 + }, + { + "epoch": 0.51, + "learning_rate": 1.1315694388979416e-05, + "loss": 1.3761, + "step": 4884 + }, + { + "epoch": 0.51, + "learning_rate": 1.1312065869546147e-05, + "loss": 1.343, + "step": 4885 + }, + { + "epoch": 0.51, + "learning_rate": 1.1308437174329761e-05, + "loss": 1.3741, + "step": 4886 + }, + { + "epoch": 0.51, + "learning_rate": 1.1304808303816413e-05, + "loss": 1.402, + "step": 4887 + }, + { + "epoch": 0.51, + "learning_rate": 1.130117925849228e-05, + "loss": 1.3834, + "step": 4888 + }, + { + "epoch": 0.51, + "learning_rate": 1.1297550038843559e-05, + "loss": 1.3342, + "step": 4889 + }, + { + "epoch": 0.51, + "learning_rate": 1.1293920645356471e-05, + "loss": 1.3207, + "step": 4890 + }, + { + "epoch": 0.51, + "learning_rate": 1.1290291078517264e-05, + "loss": 1.4274, + "step": 4891 + }, + { + "epoch": 0.51, + "learning_rate": 1.1286661338812203e-05, + "loss": 1.328, + "step": 4892 + }, + { + "epoch": 0.51, + "learning_rate": 1.1283031426727584e-05, + "loss": 1.3823, + "step": 4893 + }, + { + "epoch": 0.51, + "learning_rate": 1.127940134274972e-05, + "loss": 1.3612, + "step": 4894 + }, + { + "epoch": 0.51, + "learning_rate": 1.127577108736495e-05, + "loss": 1.375, + "step": 4895 + }, + { + "epoch": 0.51, + "learning_rate": 1.1272140661059636e-05, + "loss": 1.3531, + "step": 4896 + }, + { + "epoch": 0.51, + "learning_rate": 1.1268510064320155e-05, + "loss": 1.3636, + "step": 4897 + }, + { + "epoch": 0.51, + "learning_rate": 1.1264879297632923e-05, + "loss": 1.3524, + "step": 4898 + }, + { + "epoch": 0.51, + "learning_rate": 1.1261248361484363e-05, + "loss": 1.3865, + "step": 4899 + }, + { + "epoch": 0.51, + "learning_rate": 1.125761725636093e-05, + "loss": 1.4069, + "step": 4900 + }, + { + "epoch": 0.51, + "learning_rate": 1.1253985982749098e-05, + "loss": 1.4643, + "step": 4901 + }, + { + "epoch": 0.51, + "learning_rate": 1.1250354541135364e-05, + "loss": 1.4506, + "step": 4902 + }, + { + "epoch": 0.51, + "learning_rate": 1.124672293200625e-05, + "loss": 1.3857, + "step": 4903 + }, + { + "epoch": 0.51, + "learning_rate": 1.1243091155848295e-05, + "loss": 1.3554, + "step": 4904 + }, + { + "epoch": 0.51, + "learning_rate": 1.1239459213148065e-05, + "loss": 1.4071, + "step": 4905 + }, + { + "epoch": 0.51, + "learning_rate": 1.1235827104392148e-05, + "loss": 1.3981, + "step": 4906 + }, + { + "epoch": 0.51, + "learning_rate": 1.1232194830067153e-05, + "loss": 1.4913, + "step": 4907 + }, + { + "epoch": 0.51, + "learning_rate": 1.1228562390659712e-05, + "loss": 1.3343, + "step": 4908 + }, + { + "epoch": 0.51, + "learning_rate": 1.1224929786656474e-05, + "loss": 1.3832, + "step": 4909 + }, + { + "epoch": 0.51, + "learning_rate": 1.122129701854412e-05, + "loss": 1.367, + "step": 4910 + }, + { + "epoch": 0.51, + "learning_rate": 1.1217664086809345e-05, + "loss": 1.4108, + "step": 4911 + }, + { + "epoch": 0.52, + "learning_rate": 1.1214030991938872e-05, + "loss": 1.3981, + "step": 4912 + }, + { + "epoch": 0.52, + "learning_rate": 1.1210397734419436e-05, + "loss": 1.5266, + "step": 4913 + }, + { + "epoch": 0.52, + "learning_rate": 1.1206764314737806e-05, + "loss": 1.337, + "step": 4914 + }, + { + "epoch": 0.52, + "learning_rate": 1.1203130733380765e-05, + "loss": 1.3784, + "step": 4915 + }, + { + "epoch": 0.52, + "learning_rate": 1.1199496990835117e-05, + "loss": 1.3048, + "step": 4916 + }, + { + "epoch": 0.52, + "learning_rate": 1.1195863087587692e-05, + "loss": 1.2977, + "step": 4917 + }, + { + "epoch": 0.52, + "learning_rate": 1.1192229024125344e-05, + "loss": 1.3304, + "step": 4918 + }, + { + "epoch": 0.52, + "learning_rate": 1.1188594800934938e-05, + "loss": 1.4102, + "step": 4919 + }, + { + "epoch": 0.52, + "learning_rate": 1.1184960418503366e-05, + "loss": 1.3932, + "step": 4920 + }, + { + "epoch": 0.52, + "learning_rate": 1.1181325877317547e-05, + "loss": 1.4985, + "step": 4921 + }, + { + "epoch": 0.52, + "learning_rate": 1.1177691177864415e-05, + "loss": 1.4596, + "step": 4922 + }, + { + "epoch": 0.52, + "learning_rate": 1.1174056320630924e-05, + "loss": 1.3559, + "step": 4923 + }, + { + "epoch": 0.52, + "learning_rate": 1.117042130610405e-05, + "loss": 1.4128, + "step": 4924 + }, + { + "epoch": 0.52, + "learning_rate": 1.1166786134770795e-05, + "loss": 1.3343, + "step": 4925 + }, + { + "epoch": 0.52, + "learning_rate": 1.116315080711818e-05, + "loss": 1.332, + "step": 4926 + }, + { + "epoch": 0.52, + "learning_rate": 1.115951532363324e-05, + "loss": 1.3616, + "step": 4927 + }, + { + "epoch": 0.52, + "learning_rate": 1.1155879684803041e-05, + "loss": 1.4074, + "step": 4928 + }, + { + "epoch": 0.52, + "learning_rate": 1.1152243891114665e-05, + "loss": 1.303, + "step": 4929 + }, + { + "epoch": 0.52, + "learning_rate": 1.1148607943055212e-05, + "loss": 1.4799, + "step": 4930 + }, + { + "epoch": 0.52, + "learning_rate": 1.1144971841111807e-05, + "loss": 1.3881, + "step": 4931 + }, + { + "epoch": 0.52, + "learning_rate": 1.1141335585771593e-05, + "loss": 1.338, + "step": 4932 + }, + { + "epoch": 0.52, + "learning_rate": 1.1137699177521738e-05, + "loss": 1.3289, + "step": 4933 + }, + { + "epoch": 0.52, + "learning_rate": 1.1134062616849426e-05, + "loss": 1.377, + "step": 4934 + }, + { + "epoch": 0.52, + "learning_rate": 1.1130425904241862e-05, + "loss": 1.3596, + "step": 4935 + }, + { + "epoch": 0.52, + "learning_rate": 1.112678904018627e-05, + "loss": 1.4264, + "step": 4936 + }, + { + "epoch": 0.52, + "learning_rate": 1.1123152025169898e-05, + "loss": 1.3526, + "step": 4937 + }, + { + "epoch": 0.52, + "learning_rate": 1.1119514859680016e-05, + "loss": 1.3271, + "step": 4938 + }, + { + "epoch": 0.52, + "learning_rate": 1.1115877544203905e-05, + "loss": 1.3907, + "step": 4939 + }, + { + "epoch": 0.52, + "learning_rate": 1.1112240079228878e-05, + "loss": 1.3415, + "step": 4940 + }, + { + "epoch": 0.52, + "learning_rate": 1.1108602465242258e-05, + "loss": 1.3875, + "step": 4941 + }, + { + "epoch": 0.52, + "learning_rate": 1.110496470273139e-05, + "loss": 1.3964, + "step": 4942 + }, + { + "epoch": 0.52, + "learning_rate": 1.1101326792183645e-05, + "loss": 1.3448, + "step": 4943 + }, + { + "epoch": 0.52, + "learning_rate": 1.1097688734086407e-05, + "loss": 1.3522, + "step": 4944 + }, + { + "epoch": 0.52, + "learning_rate": 1.1094050528927082e-05, + "loss": 1.2742, + "step": 4945 + }, + { + "epoch": 0.52, + "learning_rate": 1.1090412177193097e-05, + "loss": 1.417, + "step": 4946 + }, + { + "epoch": 0.52, + "learning_rate": 1.1086773679371898e-05, + "loss": 1.3993, + "step": 4947 + }, + { + "epoch": 0.52, + "learning_rate": 1.108313503595095e-05, + "loss": 1.3783, + "step": 4948 + }, + { + "epoch": 0.52, + "learning_rate": 1.1079496247417736e-05, + "loss": 1.3975, + "step": 4949 + }, + { + "epoch": 0.52, + "learning_rate": 1.1075857314259763e-05, + "loss": 1.4256, + "step": 4950 + }, + { + "epoch": 0.52, + "learning_rate": 1.1072218236964551e-05, + "loss": 1.3547, + "step": 4951 + }, + { + "epoch": 0.52, + "learning_rate": 1.106857901601965e-05, + "loss": 1.4243, + "step": 4952 + }, + { + "epoch": 0.52, + "learning_rate": 1.1064939651912612e-05, + "loss": 1.4259, + "step": 4953 + }, + { + "epoch": 0.52, + "learning_rate": 1.1061300145131027e-05, + "loss": 1.4323, + "step": 4954 + }, + { + "epoch": 0.52, + "learning_rate": 1.1057660496162488e-05, + "loss": 1.3608, + "step": 4955 + }, + { + "epoch": 0.52, + "learning_rate": 1.1054020705494622e-05, + "loss": 1.3703, + "step": 4956 + }, + { + "epoch": 0.52, + "learning_rate": 1.105038077361506e-05, + "loss": 1.3953, + "step": 4957 + }, + { + "epoch": 0.52, + "learning_rate": 1.1046740701011467e-05, + "loss": 1.392, + "step": 4958 + }, + { + "epoch": 0.52, + "learning_rate": 1.1043100488171513e-05, + "loss": 1.4101, + "step": 4959 + }, + { + "epoch": 0.52, + "learning_rate": 1.1039460135582894e-05, + "loss": 1.5432, + "step": 4960 + }, + { + "epoch": 0.52, + "learning_rate": 1.1035819643733326e-05, + "loss": 1.3822, + "step": 4961 + }, + { + "epoch": 0.52, + "learning_rate": 1.103217901311054e-05, + "loss": 1.3816, + "step": 4962 + }, + { + "epoch": 0.52, + "learning_rate": 1.1028538244202287e-05, + "loss": 1.3137, + "step": 4963 + }, + { + "epoch": 0.52, + "learning_rate": 1.102489733749634e-05, + "loss": 1.3791, + "step": 4964 + }, + { + "epoch": 0.52, + "learning_rate": 1.102125629348048e-05, + "loss": 1.3751, + "step": 4965 + }, + { + "epoch": 0.52, + "learning_rate": 1.1017615112642518e-05, + "loss": 1.3287, + "step": 4966 + }, + { + "epoch": 0.52, + "learning_rate": 1.1013973795470277e-05, + "loss": 1.3187, + "step": 4967 + }, + { + "epoch": 0.52, + "learning_rate": 1.1010332342451602e-05, + "loss": 1.3174, + "step": 4968 + }, + { + "epoch": 0.52, + "learning_rate": 1.1006690754074351e-05, + "loss": 1.3544, + "step": 4969 + }, + { + "epoch": 0.52, + "learning_rate": 1.1003049030826404e-05, + "loss": 1.3789, + "step": 4970 + }, + { + "epoch": 0.52, + "learning_rate": 1.0999407173195662e-05, + "loss": 1.4561, + "step": 4971 + }, + { + "epoch": 0.52, + "learning_rate": 1.0995765181670039e-05, + "loss": 1.3963, + "step": 4972 + }, + { + "epoch": 0.52, + "learning_rate": 1.0992123056737464e-05, + "loss": 1.3519, + "step": 4973 + }, + { + "epoch": 0.52, + "learning_rate": 1.0988480798885892e-05, + "loss": 1.3945, + "step": 4974 + }, + { + "epoch": 0.52, + "learning_rate": 1.0984838408603294e-05, + "loss": 1.4572, + "step": 4975 + }, + { + "epoch": 0.52, + "eval_loss": 1.4313459396362305, + "eval_runtime": 77.4808, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 4975 + }, + { + "epoch": 0.52, + "learning_rate": 1.0981195886377652e-05, + "loss": 1.3493, + "step": 4976 + }, + { + "epoch": 0.52, + "learning_rate": 1.0977553232696972e-05, + "loss": 1.3734, + "step": 4977 + }, + { + "epoch": 0.52, + "learning_rate": 1.0973910448049273e-05, + "loss": 1.3484, + "step": 4978 + }, + { + "epoch": 0.52, + "learning_rate": 1.09702675329226e-05, + "loss": 1.4288, + "step": 4979 + }, + { + "epoch": 0.52, + "learning_rate": 1.096662448780501e-05, + "loss": 1.3748, + "step": 4980 + }, + { + "epoch": 0.52, + "learning_rate": 1.0962981313184575e-05, + "loss": 1.3485, + "step": 4981 + }, + { + "epoch": 0.52, + "learning_rate": 1.0959338009549383e-05, + "loss": 1.3606, + "step": 4982 + }, + { + "epoch": 0.52, + "learning_rate": 1.095569457738755e-05, + "loss": 1.3963, + "step": 4983 + }, + { + "epoch": 0.52, + "learning_rate": 1.09520510171872e-05, + "loss": 1.2986, + "step": 4984 + }, + { + "epoch": 0.52, + "learning_rate": 1.0948407329436474e-05, + "loss": 1.3505, + "step": 4985 + }, + { + "epoch": 0.52, + "learning_rate": 1.0944763514623535e-05, + "loss": 1.4649, + "step": 4986 + }, + { + "epoch": 0.52, + "learning_rate": 1.0941119573236564e-05, + "loss": 1.4743, + "step": 4987 + }, + { + "epoch": 0.52, + "learning_rate": 1.0937475505763745e-05, + "loss": 1.3934, + "step": 4988 + }, + { + "epoch": 0.52, + "learning_rate": 1.09338313126933e-05, + "loss": 1.4225, + "step": 4989 + }, + { + "epoch": 0.52, + "learning_rate": 1.0930186994513453e-05, + "loss": 1.3626, + "step": 4990 + }, + { + "epoch": 0.52, + "learning_rate": 1.0926542551712446e-05, + "loss": 1.3614, + "step": 4991 + }, + { + "epoch": 0.52, + "learning_rate": 1.0922897984778546e-05, + "loss": 1.3766, + "step": 4992 + }, + { + "epoch": 0.52, + "learning_rate": 1.0919253294200027e-05, + "loss": 1.3295, + "step": 4993 + }, + { + "epoch": 0.52, + "learning_rate": 1.091560848046519e-05, + "loss": 1.3802, + "step": 4994 + }, + { + "epoch": 0.52, + "learning_rate": 1.091196354406234e-05, + "loss": 1.2976, + "step": 4995 + }, + { + "epoch": 0.52, + "learning_rate": 1.090831848547981e-05, + "loss": 1.3928, + "step": 4996 + }, + { + "epoch": 0.52, + "learning_rate": 1.0904673305205937e-05, + "loss": 1.3717, + "step": 4997 + }, + { + "epoch": 0.52, + "learning_rate": 1.0901028003729089e-05, + "loss": 1.3164, + "step": 4998 + }, + { + "epoch": 0.52, + "learning_rate": 1.0897382581537638e-05, + "loss": 1.3462, + "step": 4999 + }, + { + "epoch": 0.52, + "learning_rate": 1.0893737039119981e-05, + "loss": 1.3643, + "step": 5000 + }, + { + "epoch": 0.52, + "learning_rate": 1.089009137696452e-05, + "loss": 1.3452, + "step": 5001 + }, + { + "epoch": 0.52, + "learning_rate": 1.0886445595559686e-05, + "loss": 1.358, + "step": 5002 + }, + { + "epoch": 0.52, + "learning_rate": 1.0882799695393922e-05, + "loss": 1.4569, + "step": 5003 + }, + { + "epoch": 0.52, + "learning_rate": 1.0879153676955681e-05, + "loss": 1.2832, + "step": 5004 + }, + { + "epoch": 0.52, + "learning_rate": 1.0875507540733435e-05, + "loss": 1.4089, + "step": 5005 + }, + { + "epoch": 0.52, + "learning_rate": 1.087186128721567e-05, + "loss": 1.3178, + "step": 5006 + }, + { + "epoch": 0.53, + "learning_rate": 1.0868214916890902e-05, + "loss": 1.4883, + "step": 5007 + }, + { + "epoch": 0.53, + "learning_rate": 1.0864568430247638e-05, + "loss": 1.3991, + "step": 5008 + }, + { + "epoch": 0.53, + "learning_rate": 1.0860921827774422e-05, + "loss": 1.4507, + "step": 5009 + }, + { + "epoch": 0.53, + "learning_rate": 1.08572751099598e-05, + "loss": 1.3578, + "step": 5010 + }, + { + "epoch": 0.53, + "learning_rate": 1.0853628277292341e-05, + "loss": 1.4231, + "step": 5011 + }, + { + "epoch": 0.53, + "learning_rate": 1.0849981330260624e-05, + "loss": 1.4835, + "step": 5012 + }, + { + "epoch": 0.53, + "learning_rate": 1.084633426935325e-05, + "loss": 1.4511, + "step": 5013 + }, + { + "epoch": 0.53, + "learning_rate": 1.084268709505883e-05, + "loss": 1.3889, + "step": 5014 + }, + { + "epoch": 0.53, + "learning_rate": 1.0839039807865992e-05, + "loss": 1.355, + "step": 5015 + }, + { + "epoch": 0.53, + "learning_rate": 1.0835392408263375e-05, + "loss": 1.4829, + "step": 5016 + }, + { + "epoch": 0.53, + "learning_rate": 1.0831744896739643e-05, + "loss": 1.3019, + "step": 5017 + }, + { + "epoch": 0.53, + "learning_rate": 1.0828097273783465e-05, + "loss": 1.3418, + "step": 5018 + }, + { + "epoch": 0.53, + "learning_rate": 1.082444953988353e-05, + "loss": 1.4276, + "step": 5019 + }, + { + "epoch": 0.53, + "learning_rate": 1.0820801695528537e-05, + "loss": 1.2816, + "step": 5020 + }, + { + "epoch": 0.53, + "learning_rate": 1.081715374120721e-05, + "loss": 1.5144, + "step": 5021 + }, + { + "epoch": 0.53, + "learning_rate": 1.0813505677408278e-05, + "loss": 1.4063, + "step": 5022 + }, + { + "epoch": 0.53, + "learning_rate": 1.0809857504620487e-05, + "loss": 1.4011, + "step": 5023 + }, + { + "epoch": 0.53, + "learning_rate": 1.0806209223332598e-05, + "loss": 1.373, + "step": 5024 + }, + { + "epoch": 0.53, + "learning_rate": 1.0802560834033388e-05, + "loss": 1.6259, + "step": 5025 + }, + { + "epoch": 0.53, + "learning_rate": 1.0798912337211648e-05, + "loss": 1.4487, + "step": 5026 + }, + { + "epoch": 0.53, + "learning_rate": 1.0795263733356184e-05, + "loss": 1.3056, + "step": 5027 + }, + { + "epoch": 0.53, + "learning_rate": 1.079161502295581e-05, + "loss": 1.2871, + "step": 5028 + }, + { + "epoch": 0.53, + "learning_rate": 1.0787966206499363e-05, + "loss": 1.413, + "step": 5029 + }, + { + "epoch": 0.53, + "learning_rate": 1.0784317284475694e-05, + "loss": 1.3682, + "step": 5030 + }, + { + "epoch": 0.53, + "learning_rate": 1.0780668257373659e-05, + "loss": 1.493, + "step": 5031 + }, + { + "epoch": 0.53, + "learning_rate": 1.0777019125682136e-05, + "loss": 1.6823, + "step": 5032 + }, + { + "epoch": 0.53, + "learning_rate": 1.0773369889890015e-05, + "loss": 1.358, + "step": 5033 + }, + { + "epoch": 0.53, + "learning_rate": 1.07697205504862e-05, + "loss": 1.3532, + "step": 5034 + }, + { + "epoch": 0.53, + "learning_rate": 1.0766071107959608e-05, + "loss": 1.3432, + "step": 5035 + }, + { + "epoch": 0.53, + "learning_rate": 1.0762421562799173e-05, + "loss": 1.3575, + "step": 5036 + }, + { + "epoch": 0.53, + "learning_rate": 1.0758771915493838e-05, + "loss": 1.0924, + "step": 5037 + }, + { + "epoch": 0.53, + "learning_rate": 1.075512216653256e-05, + "loss": 0.7405, + "step": 5038 + }, + { + "epoch": 0.53, + "learning_rate": 1.0751472316404315e-05, + "loss": 0.7134, + "step": 5039 + }, + { + "epoch": 0.53, + "learning_rate": 1.0747822365598088e-05, + "loss": 1.0904, + "step": 5040 + }, + { + "epoch": 0.53, + "learning_rate": 1.0744172314602881e-05, + "loss": 1.4353, + "step": 5041 + }, + { + "epoch": 0.53, + "learning_rate": 1.0740522163907702e-05, + "loss": 1.361, + "step": 5042 + }, + { + "epoch": 0.53, + "learning_rate": 1.073687191400158e-05, + "loss": 1.4024, + "step": 5043 + }, + { + "epoch": 0.53, + "learning_rate": 1.0733221565373557e-05, + "loss": 1.328, + "step": 5044 + }, + { + "epoch": 0.53, + "learning_rate": 1.0729571118512683e-05, + "loss": 1.3309, + "step": 5045 + }, + { + "epoch": 0.53, + "learning_rate": 1.0725920573908024e-05, + "loss": 1.3819, + "step": 5046 + }, + { + "epoch": 0.53, + "learning_rate": 1.0722269932048659e-05, + "loss": 1.3467, + "step": 5047 + }, + { + "epoch": 0.53, + "learning_rate": 1.0718619193423683e-05, + "loss": 1.3036, + "step": 5048 + }, + { + "epoch": 0.53, + "learning_rate": 1.07149683585222e-05, + "loss": 1.3297, + "step": 5049 + }, + { + "epoch": 0.53, + "learning_rate": 1.0711317427833328e-05, + "loss": 1.3439, + "step": 5050 + }, + { + "epoch": 0.53, + "learning_rate": 1.0707666401846192e-05, + "loss": 1.4167, + "step": 5051 + }, + { + "epoch": 0.53, + "learning_rate": 1.0704015281049944e-05, + "loss": 1.4217, + "step": 5052 + }, + { + "epoch": 0.53, + "learning_rate": 1.070036406593374e-05, + "loss": 1.3394, + "step": 5053 + }, + { + "epoch": 0.53, + "learning_rate": 1.0696712756986745e-05, + "loss": 1.3242, + "step": 5054 + }, + { + "epoch": 0.53, + "learning_rate": 1.0693061354698143e-05, + "loss": 1.3957, + "step": 5055 + }, + { + "epoch": 0.53, + "learning_rate": 1.0689409859557123e-05, + "loss": 1.37, + "step": 5056 + }, + { + "epoch": 0.53, + "learning_rate": 1.0685758272052902e-05, + "loss": 1.4524, + "step": 5057 + }, + { + "epoch": 0.53, + "learning_rate": 1.0682106592674688e-05, + "loss": 1.528, + "step": 5058 + }, + { + "epoch": 0.53, + "learning_rate": 1.0678454821911719e-05, + "loss": 1.3613, + "step": 5059 + }, + { + "epoch": 0.53, + "learning_rate": 1.0674802960253234e-05, + "loss": 1.308, + "step": 5060 + }, + { + "epoch": 0.53, + "learning_rate": 1.0671151008188494e-05, + "loss": 1.3343, + "step": 5061 + }, + { + "epoch": 0.53, + "learning_rate": 1.066749896620676e-05, + "loss": 1.365, + "step": 5062 + }, + { + "epoch": 0.53, + "learning_rate": 1.0663846834797316e-05, + "loss": 1.4077, + "step": 5063 + }, + { + "epoch": 0.53, + "learning_rate": 1.0660194614449455e-05, + "loss": 1.324, + "step": 5064 + }, + { + "epoch": 0.53, + "learning_rate": 1.0656542305652478e-05, + "loss": 1.3623, + "step": 5065 + }, + { + "epoch": 0.53, + "learning_rate": 1.0652889908895701e-05, + "loss": 1.4079, + "step": 5066 + }, + { + "epoch": 0.53, + "learning_rate": 1.0649237424668451e-05, + "loss": 1.3089, + "step": 5067 + }, + { + "epoch": 0.53, + "learning_rate": 1.0645584853460069e-05, + "loss": 1.3967, + "step": 5068 + }, + { + "epoch": 0.53, + "learning_rate": 1.0641932195759905e-05, + "loss": 1.3639, + "step": 5069 + }, + { + "epoch": 0.53, + "learning_rate": 1.0638279452057319e-05, + "loss": 1.5919, + "step": 5070 + }, + { + "epoch": 0.53, + "learning_rate": 1.0634626622841686e-05, + "loss": 1.3348, + "step": 5071 + }, + { + "epoch": 0.53, + "learning_rate": 1.0630973708602395e-05, + "loss": 1.3146, + "step": 5072 + }, + { + "epoch": 0.53, + "learning_rate": 1.0627320709828836e-05, + "loss": 1.3375, + "step": 5073 + }, + { + "epoch": 0.53, + "learning_rate": 1.062366762701042e-05, + "loss": 1.3908, + "step": 5074 + }, + { + "epoch": 0.53, + "learning_rate": 1.0620014460636568e-05, + "loss": 1.3726, + "step": 5075 + }, + { + "epoch": 0.53, + "learning_rate": 1.061636121119671e-05, + "loss": 1.2348, + "step": 5076 + }, + { + "epoch": 0.53, + "learning_rate": 1.0612707879180284e-05, + "loss": 1.2957, + "step": 5077 + }, + { + "epoch": 0.53, + "learning_rate": 1.0609054465076749e-05, + "loss": 1.4202, + "step": 5078 + }, + { + "epoch": 0.53, + "learning_rate": 1.060540096937556e-05, + "loss": 1.5809, + "step": 5079 + }, + { + "epoch": 0.53, + "learning_rate": 1.0601747392566202e-05, + "loss": 1.3741, + "step": 5080 + }, + { + "epoch": 0.53, + "learning_rate": 1.059809373513815e-05, + "loss": 1.3537, + "step": 5081 + }, + { + "epoch": 0.53, + "learning_rate": 1.0594439997580907e-05, + "loss": 1.332, + "step": 5082 + }, + { + "epoch": 0.53, + "learning_rate": 1.0590786180383981e-05, + "loss": 1.3267, + "step": 5083 + }, + { + "epoch": 0.53, + "learning_rate": 1.0587132284036883e-05, + "loss": 1.3552, + "step": 5084 + }, + { + "epoch": 0.53, + "learning_rate": 1.0583478309029143e-05, + "loss": 1.2837, + "step": 5085 + }, + { + "epoch": 0.53, + "learning_rate": 1.0579824255850304e-05, + "loss": 1.4311, + "step": 5086 + }, + { + "epoch": 0.53, + "learning_rate": 1.0576170124989915e-05, + "loss": 1.4394, + "step": 5087 + }, + { + "epoch": 0.53, + "learning_rate": 1.0572515916937531e-05, + "loss": 1.3185, + "step": 5088 + }, + { + "epoch": 0.53, + "learning_rate": 1.0568861632182723e-05, + "loss": 1.4212, + "step": 5089 + }, + { + "epoch": 0.53, + "learning_rate": 1.0565207271215075e-05, + "loss": 1.0951, + "step": 5090 + }, + { + "epoch": 0.53, + "learning_rate": 1.0561552834524176e-05, + "loss": 1.4174, + "step": 5091 + }, + { + "epoch": 0.53, + "learning_rate": 1.0557898322599624e-05, + "loss": 1.3349, + "step": 5092 + }, + { + "epoch": 0.53, + "learning_rate": 1.0554243735931031e-05, + "loss": 1.399, + "step": 5093 + }, + { + "epoch": 0.53, + "learning_rate": 1.055058907500802e-05, + "loss": 1.4016, + "step": 5094 + }, + { + "epoch": 0.53, + "learning_rate": 1.0546934340320219e-05, + "loss": 1.3227, + "step": 5095 + }, + { + "epoch": 0.53, + "learning_rate": 1.0543279532357269e-05, + "loss": 1.4017, + "step": 5096 + }, + { + "epoch": 0.53, + "learning_rate": 1.053962465160882e-05, + "loss": 1.3937, + "step": 5097 + }, + { + "epoch": 0.53, + "learning_rate": 1.0535969698564532e-05, + "loss": 1.2405, + "step": 5098 + }, + { + "epoch": 0.53, + "learning_rate": 1.0532314673714081e-05, + "loss": 1.2939, + "step": 5099 + }, + { + "epoch": 0.53, + "learning_rate": 1.0528659577547136e-05, + "loss": 1.4165, + "step": 5100 + }, + { + "epoch": 0.53, + "learning_rate": 1.0525004410553394e-05, + "loss": 1.309, + "step": 5101 + }, + { + "epoch": 0.54, + "learning_rate": 1.0521349173222549e-05, + "loss": 1.4078, + "step": 5102 + }, + { + "epoch": 0.54, + "learning_rate": 1.0517693866044312e-05, + "loss": 1.4026, + "step": 5103 + }, + { + "epoch": 0.54, + "learning_rate": 1.0514038489508396e-05, + "loss": 1.3098, + "step": 5104 + }, + { + "epoch": 0.54, + "learning_rate": 1.0510383044104533e-05, + "loss": 1.2886, + "step": 5105 + }, + { + "epoch": 0.54, + "learning_rate": 1.0506727530322454e-05, + "loss": 1.3114, + "step": 5106 + }, + { + "epoch": 0.54, + "learning_rate": 1.0503071948651908e-05, + "loss": 1.2823, + "step": 5107 + }, + { + "epoch": 0.54, + "learning_rate": 1.0499416299582643e-05, + "loss": 1.4654, + "step": 5108 + }, + { + "epoch": 0.54, + "learning_rate": 1.0495760583604431e-05, + "loss": 1.4043, + "step": 5109 + }, + { + "epoch": 0.54, + "learning_rate": 1.0492104801207035e-05, + "loss": 1.3113, + "step": 5110 + }, + { + "epoch": 0.54, + "learning_rate": 1.0488448952880243e-05, + "loss": 1.3285, + "step": 5111 + }, + { + "epoch": 0.54, + "learning_rate": 1.048479303911384e-05, + "loss": 1.3918, + "step": 5112 + }, + { + "epoch": 0.54, + "learning_rate": 1.0481137060397623e-05, + "loss": 1.346, + "step": 5113 + }, + { + "epoch": 0.54, + "learning_rate": 1.0477481017221407e-05, + "loss": 1.3777, + "step": 5114 + }, + { + "epoch": 0.54, + "learning_rate": 1.0473824910075003e-05, + "loss": 1.3494, + "step": 5115 + }, + { + "epoch": 0.54, + "learning_rate": 1.0470168739448232e-05, + "loss": 1.4173, + "step": 5116 + }, + { + "epoch": 0.54, + "learning_rate": 1.0466512505830932e-05, + "loss": 1.4313, + "step": 5117 + }, + { + "epoch": 0.54, + "learning_rate": 1.0462856209712944e-05, + "loss": 1.335, + "step": 5118 + }, + { + "epoch": 0.54, + "learning_rate": 1.0459199851584117e-05, + "loss": 1.37, + "step": 5119 + }, + { + "epoch": 0.54, + "learning_rate": 1.0455543431934307e-05, + "loss": 1.3504, + "step": 5120 + }, + { + "epoch": 0.54, + "learning_rate": 1.0451886951253381e-05, + "loss": 1.4148, + "step": 5121 + }, + { + "epoch": 0.54, + "learning_rate": 1.0448230410031218e-05, + "loss": 1.3974, + "step": 5122 + }, + { + "epoch": 0.54, + "learning_rate": 1.0444573808757694e-05, + "loss": 1.3644, + "step": 5123 + }, + { + "epoch": 0.54, + "learning_rate": 1.0440917147922705e-05, + "loss": 1.4024, + "step": 5124 + }, + { + "epoch": 0.54, + "learning_rate": 1.0437260428016143e-05, + "loss": 1.3925, + "step": 5125 + }, + { + "epoch": 0.54, + "learning_rate": 1.0433603649527923e-05, + "loss": 1.2907, + "step": 5126 + }, + { + "epoch": 0.54, + "learning_rate": 1.0429946812947953e-05, + "loss": 1.3453, + "step": 5127 + }, + { + "epoch": 0.54, + "learning_rate": 1.0426289918766157e-05, + "loss": 1.3856, + "step": 5128 + }, + { + "epoch": 0.54, + "learning_rate": 1.0422632967472465e-05, + "loss": 1.3309, + "step": 5129 + }, + { + "epoch": 0.54, + "learning_rate": 1.0418975959556819e-05, + "loss": 1.3757, + "step": 5130 + }, + { + "epoch": 0.54, + "learning_rate": 1.0415318895509152e-05, + "loss": 1.406, + "step": 5131 + }, + { + "epoch": 0.54, + "learning_rate": 1.041166177581943e-05, + "loss": 1.3265, + "step": 5132 + }, + { + "epoch": 0.54, + "learning_rate": 1.0408004600977606e-05, + "loss": 1.3377, + "step": 5133 + }, + { + "epoch": 0.54, + "learning_rate": 1.040434737147365e-05, + "loss": 1.3647, + "step": 5134 + }, + { + "epoch": 0.54, + "learning_rate": 1.0400690087797531e-05, + "loss": 1.3262, + "step": 5135 + }, + { + "epoch": 0.54, + "learning_rate": 1.039703275043924e-05, + "loss": 1.3924, + "step": 5136 + }, + { + "epoch": 0.54, + "learning_rate": 1.039337535988876e-05, + "loss": 1.3018, + "step": 5137 + }, + { + "epoch": 0.54, + "learning_rate": 1.038971791663609e-05, + "loss": 1.385, + "step": 5138 + }, + { + "epoch": 0.54, + "learning_rate": 1.0386060421171232e-05, + "loss": 1.3435, + "step": 5139 + }, + { + "epoch": 0.54, + "learning_rate": 1.0382402873984197e-05, + "loss": 1.4023, + "step": 5140 + }, + { + "epoch": 0.54, + "learning_rate": 1.0378745275565003e-05, + "loss": 1.369, + "step": 5141 + }, + { + "epoch": 0.54, + "learning_rate": 1.0375087626403675e-05, + "loss": 1.3199, + "step": 5142 + }, + { + "epoch": 0.54, + "learning_rate": 1.037142992699024e-05, + "loss": 1.4247, + "step": 5143 + }, + { + "epoch": 0.54, + "learning_rate": 1.0367772177814736e-05, + "loss": 1.4015, + "step": 5144 + }, + { + "epoch": 0.54, + "learning_rate": 1.0364114379367217e-05, + "loss": 1.3519, + "step": 5145 + }, + { + "epoch": 0.54, + "learning_rate": 1.0360456532137722e-05, + "loss": 1.3478, + "step": 5146 + }, + { + "epoch": 0.54, + "learning_rate": 1.0356798636616314e-05, + "loss": 1.4876, + "step": 5147 + }, + { + "epoch": 0.54, + "learning_rate": 1.0353140693293056e-05, + "loss": 1.6481, + "step": 5148 + }, + { + "epoch": 0.54, + "learning_rate": 1.034948270265802e-05, + "loss": 1.3851, + "step": 5149 + }, + { + "epoch": 0.54, + "learning_rate": 1.0345824665201281e-05, + "loss": 1.4037, + "step": 5150 + }, + { + "epoch": 0.54, + "learning_rate": 1.0342166581412923e-05, + "loss": 1.3138, + "step": 5151 + }, + { + "epoch": 0.54, + "learning_rate": 1.0338508451783032e-05, + "loss": 1.3536, + "step": 5152 + }, + { + "epoch": 0.54, + "learning_rate": 1.0334850276801712e-05, + "loss": 1.3244, + "step": 5153 + }, + { + "epoch": 0.54, + "learning_rate": 1.0331192056959052e-05, + "loss": 1.3677, + "step": 5154 + }, + { + "epoch": 0.54, + "learning_rate": 1.032753379274517e-05, + "loss": 1.3439, + "step": 5155 + }, + { + "epoch": 0.54, + "learning_rate": 1.0323875484650171e-05, + "loss": 1.365, + "step": 5156 + }, + { + "epoch": 0.54, + "learning_rate": 1.0320217133164186e-05, + "loss": 1.3838, + "step": 5157 + }, + { + "epoch": 0.54, + "learning_rate": 1.0316558738777328e-05, + "loss": 1.3312, + "step": 5158 + }, + { + "epoch": 0.54, + "learning_rate": 1.0312900301979733e-05, + "loss": 1.369, + "step": 5159 + }, + { + "epoch": 0.54, + "learning_rate": 1.030924182326154e-05, + "loss": 1.2712, + "step": 5160 + }, + { + "epoch": 0.54, + "learning_rate": 1.0305583303112887e-05, + "loss": 1.3141, + "step": 5161 + }, + { + "epoch": 0.54, + "learning_rate": 1.030192474202392e-05, + "loss": 1.3708, + "step": 5162 + }, + { + "epoch": 0.54, + "learning_rate": 1.0298266140484798e-05, + "loss": 1.3724, + "step": 5163 + }, + { + "epoch": 0.54, + "learning_rate": 1.0294607498985678e-05, + "loss": 1.3208, + "step": 5164 + }, + { + "epoch": 0.54, + "learning_rate": 1.0290948818016722e-05, + "loss": 1.3379, + "step": 5165 + }, + { + "epoch": 0.54, + "learning_rate": 1.0287290098068099e-05, + "loss": 1.3236, + "step": 5166 + }, + { + "epoch": 0.54, + "learning_rate": 1.0283631339629982e-05, + "loss": 1.3437, + "step": 5167 + }, + { + "epoch": 0.54, + "learning_rate": 1.0279972543192561e-05, + "loss": 1.3381, + "step": 5168 + }, + { + "epoch": 0.54, + "learning_rate": 1.0276313709246007e-05, + "loss": 1.4287, + "step": 5169 + }, + { + "epoch": 0.54, + "learning_rate": 1.0272654838280515e-05, + "loss": 1.3587, + "step": 5170 + }, + { + "epoch": 0.54, + "learning_rate": 1.0268995930786283e-05, + "loss": 1.2982, + "step": 5171 + }, + { + "epoch": 0.54, + "learning_rate": 1.0265336987253509e-05, + "loss": 1.3416, + "step": 5172 + }, + { + "epoch": 0.54, + "learning_rate": 1.0261678008172393e-05, + "loss": 1.3827, + "step": 5173 + }, + { + "epoch": 0.54, + "learning_rate": 1.025801899403315e-05, + "loss": 1.3293, + "step": 5174 + }, + { + "epoch": 0.54, + "eval_loss": 1.4264723062515259, + "eval_runtime": 77.4376, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 5174 + }, + { + "epoch": 0.54, + "learning_rate": 1.0254359945325987e-05, + "loss": 1.3811, + "step": 5175 + }, + { + "epoch": 0.54, + "learning_rate": 1.0250700862541135e-05, + "loss": 1.3423, + "step": 5176 + }, + { + "epoch": 0.54, + "learning_rate": 1.02470417461688e-05, + "loss": 1.3641, + "step": 5177 + }, + { + "epoch": 0.54, + "learning_rate": 1.0243382596699226e-05, + "loss": 1.3211, + "step": 5178 + }, + { + "epoch": 0.54, + "learning_rate": 1.023972341462263e-05, + "loss": 1.4008, + "step": 5179 + }, + { + "epoch": 0.54, + "learning_rate": 1.0236064200429263e-05, + "loss": 1.404, + "step": 5180 + }, + { + "epoch": 0.54, + "learning_rate": 1.0232404954609353e-05, + "loss": 1.3359, + "step": 5181 + }, + { + "epoch": 0.54, + "learning_rate": 1.0228745677653155e-05, + "loss": 1.4069, + "step": 5182 + }, + { + "epoch": 0.54, + "learning_rate": 1.0225086370050914e-05, + "loss": 1.3343, + "step": 5183 + }, + { + "epoch": 0.54, + "learning_rate": 1.0221427032292881e-05, + "loss": 1.3109, + "step": 5184 + }, + { + "epoch": 0.54, + "learning_rate": 1.0217767664869312e-05, + "loss": 1.3611, + "step": 5185 + }, + { + "epoch": 0.54, + "learning_rate": 1.0214108268270476e-05, + "loss": 1.4072, + "step": 5186 + }, + { + "epoch": 0.54, + "learning_rate": 1.0210448842986631e-05, + "loss": 1.3602, + "step": 5187 + }, + { + "epoch": 0.54, + "learning_rate": 1.0206789389508047e-05, + "loss": 1.413, + "step": 5188 + }, + { + "epoch": 0.54, + "learning_rate": 1.0203129908325e-05, + "loss": 1.3209, + "step": 5189 + }, + { + "epoch": 0.54, + "learning_rate": 1.0199470399927764e-05, + "loss": 1.3714, + "step": 5190 + }, + { + "epoch": 0.54, + "learning_rate": 1.0195810864806623e-05, + "loss": 1.3556, + "step": 5191 + }, + { + "epoch": 0.54, + "learning_rate": 1.0192151303451852e-05, + "loss": 1.4116, + "step": 5192 + }, + { + "epoch": 0.54, + "learning_rate": 1.0188491716353745e-05, + "loss": 1.4102, + "step": 5193 + }, + { + "epoch": 0.54, + "learning_rate": 1.0184832104002592e-05, + "loss": 1.4849, + "step": 5194 + }, + { + "epoch": 0.54, + "learning_rate": 1.0181172466888689e-05, + "loss": 1.5395, + "step": 5195 + }, + { + "epoch": 0.54, + "learning_rate": 1.0177512805502325e-05, + "loss": 1.3627, + "step": 5196 + }, + { + "epoch": 0.54, + "learning_rate": 1.017385312033381e-05, + "loss": 1.4152, + "step": 5197 + }, + { + "epoch": 0.55, + "learning_rate": 1.0170193411873442e-05, + "loss": 1.3641, + "step": 5198 + }, + { + "epoch": 0.55, + "learning_rate": 1.0166533680611533e-05, + "loss": 1.3074, + "step": 5199 + }, + { + "epoch": 0.55, + "learning_rate": 1.0162873927038386e-05, + "loss": 1.35, + "step": 5200 + }, + { + "epoch": 0.55, + "learning_rate": 1.015921415164432e-05, + "loss": 1.3551, + "step": 5201 + }, + { + "epoch": 0.55, + "learning_rate": 1.0155554354919643e-05, + "loss": 1.3421, + "step": 5202 + }, + { + "epoch": 0.55, + "learning_rate": 1.0151894537354687e-05, + "loss": 1.4132, + "step": 5203 + }, + { + "epoch": 0.55, + "learning_rate": 1.0148234699439764e-05, + "loss": 1.351, + "step": 5204 + }, + { + "epoch": 0.55, + "learning_rate": 1.0144574841665198e-05, + "loss": 1.3745, + "step": 5205 + }, + { + "epoch": 0.55, + "learning_rate": 1.0140914964521316e-05, + "loss": 1.3151, + "step": 5206 + }, + { + "epoch": 0.55, + "learning_rate": 1.0137255068498456e-05, + "loss": 1.4903, + "step": 5207 + }, + { + "epoch": 0.55, + "learning_rate": 1.0133595154086937e-05, + "loss": 1.3945, + "step": 5208 + }, + { + "epoch": 0.55, + "learning_rate": 1.0129935221777104e-05, + "loss": 1.3924, + "step": 5209 + }, + { + "epoch": 0.55, + "learning_rate": 1.0126275272059286e-05, + "loss": 1.4191, + "step": 5210 + }, + { + "epoch": 0.55, + "learning_rate": 1.012261530542383e-05, + "loss": 1.3408, + "step": 5211 + }, + { + "epoch": 0.55, + "learning_rate": 1.0118955322361071e-05, + "loss": 1.3582, + "step": 5212 + }, + { + "epoch": 0.55, + "learning_rate": 1.0115295323361354e-05, + "loss": 1.3703, + "step": 5213 + }, + { + "epoch": 0.55, + "learning_rate": 1.011163530891503e-05, + "loss": 1.4181, + "step": 5214 + }, + { + "epoch": 0.55, + "learning_rate": 1.0107975279512442e-05, + "loss": 1.5019, + "step": 5215 + }, + { + "epoch": 0.55, + "learning_rate": 1.010431523564394e-05, + "loss": 1.3151, + "step": 5216 + }, + { + "epoch": 0.55, + "learning_rate": 1.0100655177799874e-05, + "loss": 1.4036, + "step": 5217 + }, + { + "epoch": 0.55, + "learning_rate": 1.0096995106470606e-05, + "loss": 1.3584, + "step": 5218 + }, + { + "epoch": 0.55, + "learning_rate": 1.0093335022146482e-05, + "loss": 1.3618, + "step": 5219 + }, + { + "epoch": 0.55, + "learning_rate": 1.0089674925317865e-05, + "loss": 1.3295, + "step": 5220 + }, + { + "epoch": 0.55, + "learning_rate": 1.0086014816475108e-05, + "loss": 1.3968, + "step": 5221 + }, + { + "epoch": 0.55, + "learning_rate": 1.0082354696108586e-05, + "loss": 1.2847, + "step": 5222 + }, + { + "epoch": 0.55, + "learning_rate": 1.007869456470864e-05, + "loss": 1.4461, + "step": 5223 + }, + { + "epoch": 0.55, + "learning_rate": 1.007503442276565e-05, + "loss": 1.3813, + "step": 5224 + }, + { + "epoch": 0.55, + "learning_rate": 1.007137427076997e-05, + "loss": 1.3833, + "step": 5225 + }, + { + "epoch": 0.55, + "learning_rate": 1.006771410921198e-05, + "loss": 1.4024, + "step": 5226 + }, + { + "epoch": 0.55, + "learning_rate": 1.0064053938582032e-05, + "loss": 1.3357, + "step": 5227 + }, + { + "epoch": 0.55, + "learning_rate": 1.0060393759370506e-05, + "loss": 1.35, + "step": 5228 + }, + { + "epoch": 0.55, + "learning_rate": 1.0056733572067765e-05, + "loss": 1.3512, + "step": 5229 + }, + { + "epoch": 0.55, + "learning_rate": 1.0053073377164186e-05, + "loss": 1.3852, + "step": 5230 + }, + { + "epoch": 0.55, + "learning_rate": 1.0049413175150135e-05, + "loss": 1.3502, + "step": 5231 + }, + { + "epoch": 0.55, + "learning_rate": 1.004575296651599e-05, + "loss": 1.4637, + "step": 5232 + }, + { + "epoch": 0.55, + "learning_rate": 1.0042092751752123e-05, + "loss": 1.3877, + "step": 5233 + }, + { + "epoch": 0.55, + "learning_rate": 1.0038432531348909e-05, + "loss": 1.3804, + "step": 5234 + }, + { + "epoch": 0.55, + "learning_rate": 1.0034772305796723e-05, + "loss": 1.3613, + "step": 5235 + }, + { + "epoch": 0.55, + "learning_rate": 1.003111207558594e-05, + "loss": 1.3218, + "step": 5236 + }, + { + "epoch": 0.55, + "learning_rate": 1.0027451841206944e-05, + "loss": 1.3554, + "step": 5237 + }, + { + "epoch": 0.55, + "learning_rate": 1.0023791603150099e-05, + "loss": 1.372, + "step": 5238 + }, + { + "epoch": 0.55, + "learning_rate": 1.0020131361905793e-05, + "loss": 1.3544, + "step": 5239 + }, + { + "epoch": 0.55, + "learning_rate": 1.0016471117964404e-05, + "loss": 1.3472, + "step": 5240 + }, + { + "epoch": 0.55, + "learning_rate": 1.001281087181631e-05, + "loss": 1.4247, + "step": 5241 + }, + { + "epoch": 0.55, + "learning_rate": 1.0009150623951883e-05, + "loss": 1.2685, + "step": 5242 + }, + { + "epoch": 0.55, + "learning_rate": 1.000549037486151e-05, + "loss": 1.4036, + "step": 5243 + }, + { + "epoch": 0.55, + "learning_rate": 1.0001830125035565e-05, + "loss": 1.3602, + "step": 5244 + }, + { + "epoch": 0.55, + "learning_rate": 9.998169874964437e-06, + "loss": 1.3784, + "step": 5245 + }, + { + "epoch": 0.55, + "learning_rate": 9.994509625138496e-06, + "loss": 1.3389, + "step": 5246 + }, + { + "epoch": 0.55, + "learning_rate": 9.990849376048119e-06, + "loss": 1.4561, + "step": 5247 + }, + { + "epoch": 0.55, + "learning_rate": 9.987189128183695e-06, + "loss": 1.3876, + "step": 5248 + }, + { + "epoch": 0.55, + "learning_rate": 9.9835288820356e-06, + "loss": 1.3362, + "step": 5249 + }, + { + "epoch": 0.55, + "learning_rate": 9.97986863809421e-06, + "loss": 1.3449, + "step": 5250 + }, + { + "epoch": 0.55, + "learning_rate": 9.9762083968499e-06, + "loss": 1.3521, + "step": 5251 + }, + { + "epoch": 0.55, + "learning_rate": 9.972548158793061e-06, + "loss": 1.4452, + "step": 5252 + }, + { + "epoch": 0.55, + "learning_rate": 9.968887924414062e-06, + "loss": 1.4126, + "step": 5253 + }, + { + "epoch": 0.55, + "learning_rate": 9.965227694203282e-06, + "loss": 1.3054, + "step": 5254 + }, + { + "epoch": 0.55, + "learning_rate": 9.961567468651093e-06, + "loss": 1.3771, + "step": 5255 + }, + { + "epoch": 0.55, + "learning_rate": 9.957907248247878e-06, + "loss": 1.3566, + "step": 5256 + }, + { + "epoch": 0.55, + "learning_rate": 9.954247033484014e-06, + "loss": 1.4765, + "step": 5257 + }, + { + "epoch": 0.55, + "learning_rate": 9.950586824849865e-06, + "loss": 1.4749, + "step": 5258 + }, + { + "epoch": 0.55, + "learning_rate": 9.946926622835815e-06, + "loss": 1.3679, + "step": 5259 + }, + { + "epoch": 0.55, + "learning_rate": 9.943266427932238e-06, + "loss": 1.2671, + "step": 5260 + }, + { + "epoch": 0.55, + "learning_rate": 9.9396062406295e-06, + "loss": 1.3485, + "step": 5261 + }, + { + "epoch": 0.55, + "learning_rate": 9.935946061417968e-06, + "loss": 1.3136, + "step": 5262 + }, + { + "epoch": 0.55, + "learning_rate": 9.932285890788024e-06, + "loss": 1.3954, + "step": 5263 + }, + { + "epoch": 0.55, + "learning_rate": 9.928625729230031e-06, + "loss": 1.428, + "step": 5264 + }, + { + "epoch": 0.55, + "learning_rate": 9.924965577234356e-06, + "loss": 1.4144, + "step": 5265 + }, + { + "epoch": 0.55, + "learning_rate": 9.92130543529136e-06, + "loss": 1.3361, + "step": 5266 + }, + { + "epoch": 0.55, + "learning_rate": 9.91764530389142e-06, + "loss": 1.4503, + "step": 5267 + }, + { + "epoch": 0.55, + "learning_rate": 9.913985183524893e-06, + "loss": 1.3431, + "step": 5268 + }, + { + "epoch": 0.55, + "learning_rate": 9.91032507468214e-06, + "loss": 1.3206, + "step": 5269 + }, + { + "epoch": 0.55, + "learning_rate": 9.906664977853518e-06, + "loss": 1.4568, + "step": 5270 + }, + { + "epoch": 0.55, + "learning_rate": 9.903004893529397e-06, + "loss": 1.3591, + "step": 5271 + }, + { + "epoch": 0.55, + "learning_rate": 9.899344822200127e-06, + "loss": 1.3382, + "step": 5272 + }, + { + "epoch": 0.55, + "learning_rate": 9.895684764356066e-06, + "loss": 1.3008, + "step": 5273 + }, + { + "epoch": 0.55, + "learning_rate": 9.89202472048756e-06, + "loss": 1.316, + "step": 5274 + }, + { + "epoch": 0.55, + "learning_rate": 9.888364691084971e-06, + "loss": 1.4246, + "step": 5275 + }, + { + "epoch": 0.55, + "learning_rate": 9.88470467663865e-06, + "loss": 1.3615, + "step": 5276 + }, + { + "epoch": 0.55, + "learning_rate": 9.881044677638934e-06, + "loss": 1.3418, + "step": 5277 + }, + { + "epoch": 0.55, + "learning_rate": 9.877384694576172e-06, + "loss": 1.249, + "step": 5278 + }, + { + "epoch": 0.55, + "learning_rate": 9.873724727940715e-06, + "loss": 1.2779, + "step": 5279 + }, + { + "epoch": 0.55, + "learning_rate": 9.870064778222903e-06, + "loss": 1.3529, + "step": 5280 + }, + { + "epoch": 0.55, + "learning_rate": 9.866404845913065e-06, + "loss": 1.3204, + "step": 5281 + }, + { + "epoch": 0.55, + "learning_rate": 9.862744931501548e-06, + "loss": 1.3537, + "step": 5282 + }, + { + "epoch": 0.55, + "learning_rate": 9.859085035478687e-06, + "loss": 1.3681, + "step": 5283 + }, + { + "epoch": 0.55, + "learning_rate": 9.855425158334809e-06, + "loss": 1.3983, + "step": 5284 + }, + { + "epoch": 0.55, + "learning_rate": 9.851765300560238e-06, + "loss": 1.401, + "step": 5285 + }, + { + "epoch": 0.55, + "learning_rate": 9.848105462645315e-06, + "loss": 1.3073, + "step": 5286 + }, + { + "epoch": 0.55, + "learning_rate": 9.844445645080358e-06, + "loss": 1.3162, + "step": 5287 + }, + { + "epoch": 0.55, + "learning_rate": 9.840785848355685e-06, + "loss": 1.3345, + "step": 5288 + }, + { + "epoch": 0.55, + "learning_rate": 9.837126072961616e-06, + "loss": 1.4241, + "step": 5289 + }, + { + "epoch": 0.55, + "learning_rate": 9.83346631938847e-06, + "loss": 1.3339, + "step": 5290 + }, + { + "epoch": 0.55, + "learning_rate": 9.829806588126561e-06, + "loss": 1.3507, + "step": 5291 + }, + { + "epoch": 0.55, + "learning_rate": 9.826146879666196e-06, + "loss": 1.2806, + "step": 5292 + }, + { + "epoch": 0.56, + "learning_rate": 9.822487194497675e-06, + "loss": 1.3952, + "step": 5293 + }, + { + "epoch": 0.56, + "learning_rate": 9.818827533111314e-06, + "loss": 1.3319, + "step": 5294 + }, + { + "epoch": 0.56, + "learning_rate": 9.81516789599741e-06, + "loss": 1.351, + "step": 5295 + }, + { + "epoch": 0.56, + "learning_rate": 9.811508283646258e-06, + "loss": 1.4076, + "step": 5296 + }, + { + "epoch": 0.56, + "learning_rate": 9.80784869654815e-06, + "loss": 1.3271, + "step": 5297 + }, + { + "epoch": 0.56, + "learning_rate": 9.80418913519338e-06, + "loss": 1.4059, + "step": 5298 + }, + { + "epoch": 0.56, + "learning_rate": 9.80052960007224e-06, + "loss": 1.4146, + "step": 5299 + }, + { + "epoch": 0.56, + "learning_rate": 9.796870091675005e-06, + "loss": 1.3454, + "step": 5300 + }, + { + "epoch": 0.56, + "learning_rate": 9.793210610491953e-06, + "loss": 1.4376, + "step": 5301 + }, + { + "epoch": 0.56, + "learning_rate": 9.789551157013372e-06, + "loss": 1.3437, + "step": 5302 + }, + { + "epoch": 0.56, + "learning_rate": 9.78589173172953e-06, + "loss": 1.3073, + "step": 5303 + }, + { + "epoch": 0.56, + "learning_rate": 9.782232335130688e-06, + "loss": 1.2989, + "step": 5304 + }, + { + "epoch": 0.56, + "learning_rate": 9.778572967707122e-06, + "loss": 1.4028, + "step": 5305 + }, + { + "epoch": 0.56, + "learning_rate": 9.77491362994909e-06, + "loss": 1.3096, + "step": 5306 + }, + { + "epoch": 0.56, + "learning_rate": 9.77125432234685e-06, + "loss": 1.3719, + "step": 5307 + }, + { + "epoch": 0.56, + "learning_rate": 9.767595045390647e-06, + "loss": 1.3271, + "step": 5308 + }, + { + "epoch": 0.56, + "learning_rate": 9.763935799570739e-06, + "loss": 1.3693, + "step": 5309 + }, + { + "epoch": 0.56, + "learning_rate": 9.760276585377371e-06, + "loss": 1.3586, + "step": 5310 + }, + { + "epoch": 0.56, + "learning_rate": 9.756617403300781e-06, + "loss": 1.3423, + "step": 5311 + }, + { + "epoch": 0.56, + "learning_rate": 9.7529582538312e-06, + "loss": 1.388, + "step": 5312 + }, + { + "epoch": 0.56, + "learning_rate": 9.74929913745887e-06, + "loss": 1.3594, + "step": 5313 + }, + { + "epoch": 0.56, + "learning_rate": 9.745640054674015e-06, + "loss": 1.2831, + "step": 5314 + }, + { + "epoch": 0.56, + "learning_rate": 9.741981005966856e-06, + "loss": 1.4207, + "step": 5315 + }, + { + "epoch": 0.56, + "learning_rate": 9.738321991827609e-06, + "loss": 1.2807, + "step": 5316 + }, + { + "epoch": 0.56, + "learning_rate": 9.734663012746493e-06, + "loss": 1.3396, + "step": 5317 + }, + { + "epoch": 0.56, + "learning_rate": 9.731004069213722e-06, + "loss": 1.3666, + "step": 5318 + }, + { + "epoch": 0.56, + "learning_rate": 9.72734516171949e-06, + "loss": 1.3466, + "step": 5319 + }, + { + "epoch": 0.56, + "learning_rate": 9.723686290753995e-06, + "loss": 1.4478, + "step": 5320 + }, + { + "epoch": 0.56, + "learning_rate": 9.720027456807442e-06, + "loss": 1.316, + "step": 5321 + }, + { + "epoch": 0.56, + "learning_rate": 9.71636866037002e-06, + "loss": 1.3762, + "step": 5322 + }, + { + "epoch": 0.56, + "learning_rate": 9.712709901931906e-06, + "loss": 1.4156, + "step": 5323 + }, + { + "epoch": 0.56, + "learning_rate": 9.70905118198328e-06, + "loss": 1.2452, + "step": 5324 + }, + { + "epoch": 0.56, + "learning_rate": 9.705392501014325e-06, + "loss": 1.3771, + "step": 5325 + }, + { + "epoch": 0.56, + "learning_rate": 9.701733859515205e-06, + "loss": 1.3433, + "step": 5326 + }, + { + "epoch": 0.56, + "learning_rate": 9.698075257976079e-06, + "loss": 1.3702, + "step": 5327 + }, + { + "epoch": 0.56, + "learning_rate": 9.694416696887115e-06, + "loss": 1.295, + "step": 5328 + }, + { + "epoch": 0.56, + "learning_rate": 9.690758176738463e-06, + "loss": 1.3462, + "step": 5329 + }, + { + "epoch": 0.56, + "learning_rate": 9.68709969802027e-06, + "loss": 1.5304, + "step": 5330 + }, + { + "epoch": 0.56, + "learning_rate": 9.683441261222672e-06, + "loss": 1.3518, + "step": 5331 + }, + { + "epoch": 0.56, + "learning_rate": 9.679782866835816e-06, + "loss": 1.3778, + "step": 5332 + }, + { + "epoch": 0.56, + "learning_rate": 9.67612451534983e-06, + "loss": 1.3731, + "step": 5333 + }, + { + "epoch": 0.56, + "learning_rate": 9.672466207254837e-06, + "loss": 1.3315, + "step": 5334 + }, + { + "epoch": 0.56, + "learning_rate": 9.66880794304095e-06, + "loss": 1.3105, + "step": 5335 + }, + { + "epoch": 0.56, + "learning_rate": 9.665149723198293e-06, + "loss": 1.3903, + "step": 5336 + }, + { + "epoch": 0.56, + "learning_rate": 9.661491548216972e-06, + "loss": 1.3554, + "step": 5337 + }, + { + "epoch": 0.56, + "learning_rate": 9.657833418587084e-06, + "loss": 1.3231, + "step": 5338 + }, + { + "epoch": 0.56, + "learning_rate": 9.65417533479872e-06, + "loss": 1.352, + "step": 5339 + }, + { + "epoch": 0.56, + "learning_rate": 9.650517297341983e-06, + "loss": 1.3957, + "step": 5340 + }, + { + "epoch": 0.56, + "learning_rate": 9.646859306706948e-06, + "loss": 1.3938, + "step": 5341 + }, + { + "epoch": 0.56, + "learning_rate": 9.643201363383693e-06, + "loss": 1.3038, + "step": 5342 + }, + { + "epoch": 0.56, + "learning_rate": 9.63954346786228e-06, + "loss": 1.2973, + "step": 5343 + }, + { + "epoch": 0.56, + "learning_rate": 9.635885620632786e-06, + "loss": 1.379, + "step": 5344 + }, + { + "epoch": 0.56, + "learning_rate": 9.632227822185266e-06, + "loss": 1.5377, + "step": 5345 + }, + { + "epoch": 0.56, + "learning_rate": 9.628570073009767e-06, + "loss": 1.4573, + "step": 5346 + }, + { + "epoch": 0.56, + "learning_rate": 9.624912373596329e-06, + "loss": 1.3394, + "step": 5347 + }, + { + "epoch": 0.56, + "learning_rate": 9.621254724434999e-06, + "loss": 1.4157, + "step": 5348 + }, + { + "epoch": 0.56, + "learning_rate": 9.617597126015808e-06, + "loss": 1.3526, + "step": 5349 + }, + { + "epoch": 0.56, + "learning_rate": 9.61393957882877e-06, + "loss": 1.3795, + "step": 5350 + }, + { + "epoch": 0.56, + "learning_rate": 9.610282083363913e-06, + "loss": 1.3765, + "step": 5351 + }, + { + "epoch": 0.56, + "learning_rate": 9.606624640111243e-06, + "loss": 1.3512, + "step": 5352 + }, + { + "epoch": 0.56, + "learning_rate": 9.602967249560766e-06, + "loss": 1.3298, + "step": 5353 + }, + { + "epoch": 0.56, + "learning_rate": 9.599309912202469e-06, + "loss": 1.3093, + "step": 5354 + }, + { + "epoch": 0.56, + "learning_rate": 9.595652628526354e-06, + "loss": 1.3353, + "step": 5355 + }, + { + "epoch": 0.56, + "learning_rate": 9.591995399022397e-06, + "loss": 1.3081, + "step": 5356 + }, + { + "epoch": 0.56, + "learning_rate": 9.588338224180576e-06, + "loss": 1.343, + "step": 5357 + }, + { + "epoch": 0.56, + "learning_rate": 9.584681104490848e-06, + "loss": 1.3275, + "step": 5358 + }, + { + "epoch": 0.56, + "learning_rate": 9.581024040443185e-06, + "loss": 1.3399, + "step": 5359 + }, + { + "epoch": 0.56, + "learning_rate": 9.577367032527538e-06, + "loss": 1.3181, + "step": 5360 + }, + { + "epoch": 0.56, + "learning_rate": 9.573710081233846e-06, + "loss": 1.3531, + "step": 5361 + }, + { + "epoch": 0.56, + "learning_rate": 9.570053187052049e-06, + "loss": 1.4056, + "step": 5362 + }, + { + "epoch": 0.56, + "learning_rate": 9.566396350472079e-06, + "loss": 1.3303, + "step": 5363 + }, + { + "epoch": 0.56, + "learning_rate": 9.56273957198386e-06, + "loss": 1.3506, + "step": 5364 + }, + { + "epoch": 0.56, + "learning_rate": 9.559082852077302e-06, + "loss": 1.4588, + "step": 5365 + }, + { + "epoch": 0.56, + "learning_rate": 9.555426191242307e-06, + "loss": 1.3434, + "step": 5366 + }, + { + "epoch": 0.56, + "learning_rate": 9.551769589968784e-06, + "loss": 1.3508, + "step": 5367 + }, + { + "epoch": 0.56, + "learning_rate": 9.548113048746622e-06, + "loss": 1.3701, + "step": 5368 + }, + { + "epoch": 0.56, + "learning_rate": 9.544456568065698e-06, + "loss": 1.3664, + "step": 5369 + }, + { + "epoch": 0.56, + "learning_rate": 9.540800148415885e-06, + "loss": 1.6697, + "step": 5370 + }, + { + "epoch": 0.56, + "learning_rate": 9.537143790287057e-06, + "loss": 1.5298, + "step": 5371 + }, + { + "epoch": 0.56, + "learning_rate": 9.533487494169073e-06, + "loss": 1.3884, + "step": 5372 + }, + { + "epoch": 0.56, + "learning_rate": 9.52983126055177e-06, + "loss": 1.403, + "step": 5373 + }, + { + "epoch": 0.56, + "eval_loss": 1.4240995645523071, + "eval_runtime": 77.4615, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 5373 + }, + { + "epoch": 0.56, + "learning_rate": 9.526175089925e-06, + "loss": 1.3141, + "step": 5374 + }, + { + "epoch": 0.56, + "learning_rate": 9.522518982778596e-06, + "loss": 1.3733, + "step": 5375 + }, + { + "epoch": 0.56, + "learning_rate": 9.51886293960238e-06, + "loss": 1.3095, + "step": 5376 + }, + { + "epoch": 0.56, + "learning_rate": 9.515206960886162e-06, + "loss": 1.3713, + "step": 5377 + }, + { + "epoch": 0.56, + "learning_rate": 9.51155104711976e-06, + "loss": 1.3585, + "step": 5378 + }, + { + "epoch": 0.56, + "learning_rate": 9.507895198792967e-06, + "loss": 1.3473, + "step": 5379 + }, + { + "epoch": 0.56, + "learning_rate": 9.504239416395576e-06, + "loss": 1.3282, + "step": 5380 + }, + { + "epoch": 0.56, + "learning_rate": 9.500583700417357e-06, + "loss": 1.3655, + "step": 5381 + }, + { + "epoch": 0.56, + "learning_rate": 9.496928051348095e-06, + "loss": 1.4512, + "step": 5382 + }, + { + "epoch": 0.56, + "learning_rate": 9.49327246967755e-06, + "loss": 1.4071, + "step": 5383 + }, + { + "epoch": 0.56, + "learning_rate": 9.489616955895472e-06, + "loss": 1.3703, + "step": 5384 + }, + { + "epoch": 0.56, + "learning_rate": 9.485961510491604e-06, + "loss": 1.3358, + "step": 5385 + }, + { + "epoch": 0.56, + "learning_rate": 9.482306133955691e-06, + "loss": 1.3505, + "step": 5386 + }, + { + "epoch": 0.56, + "learning_rate": 9.478650826777457e-06, + "loss": 1.2578, + "step": 5387 + }, + { + "epoch": 0.57, + "learning_rate": 9.474995589446612e-06, + "loss": 1.4298, + "step": 5388 + }, + { + "epoch": 0.57, + "learning_rate": 9.471340422452864e-06, + "loss": 1.4044, + "step": 5389 + }, + { + "epoch": 0.57, + "learning_rate": 9.467685326285922e-06, + "loss": 1.3524, + "step": 5390 + }, + { + "epoch": 0.57, + "learning_rate": 9.46403030143547e-06, + "loss": 1.3017, + "step": 5391 + }, + { + "epoch": 0.57, + "learning_rate": 9.460375348391185e-06, + "loss": 1.3361, + "step": 5392 + }, + { + "epoch": 0.57, + "learning_rate": 9.456720467642733e-06, + "loss": 1.3182, + "step": 5393 + }, + { + "epoch": 0.57, + "learning_rate": 9.453065659679785e-06, + "loss": 1.3869, + "step": 5394 + }, + { + "epoch": 0.57, + "learning_rate": 9.449410924991986e-06, + "loss": 1.3161, + "step": 5395 + }, + { + "epoch": 0.57, + "learning_rate": 9.44575626406897e-06, + "loss": 1.3, + "step": 5396 + }, + { + "epoch": 0.57, + "learning_rate": 9.442101677400378e-06, + "loss": 1.5103, + "step": 5397 + }, + { + "epoch": 0.57, + "learning_rate": 9.438447165475828e-06, + "loss": 1.3511, + "step": 5398 + }, + { + "epoch": 0.57, + "learning_rate": 9.43479272878493e-06, + "loss": 1.3461, + "step": 5399 + }, + { + "epoch": 0.57, + "learning_rate": 9.431138367817277e-06, + "loss": 1.2657, + "step": 5400 + }, + { + "epoch": 0.57, + "learning_rate": 9.427484083062472e-06, + "loss": 1.3736, + "step": 5401 + }, + { + "epoch": 0.57, + "learning_rate": 9.423829875010089e-06, + "loss": 1.3476, + "step": 5402 + }, + { + "epoch": 0.57, + "learning_rate": 9.4201757441497e-06, + "loss": 1.3495, + "step": 5403 + }, + { + "epoch": 0.57, + "learning_rate": 9.416521690970857e-06, + "loss": 1.387, + "step": 5404 + }, + { + "epoch": 0.57, + "learning_rate": 9.41286771596312e-06, + "loss": 1.2829, + "step": 5405 + }, + { + "epoch": 0.57, + "learning_rate": 9.409213819616022e-06, + "loss": 1.3544, + "step": 5406 + }, + { + "epoch": 0.57, + "learning_rate": 9.405560002419098e-06, + "loss": 1.3202, + "step": 5407 + }, + { + "epoch": 0.57, + "learning_rate": 9.40190626486185e-06, + "loss": 1.3034, + "step": 5408 + }, + { + "epoch": 0.57, + "learning_rate": 9.398252607433801e-06, + "loss": 1.3223, + "step": 5409 + }, + { + "epoch": 0.57, + "learning_rate": 9.394599030624443e-06, + "loss": 1.3327, + "step": 5410 + }, + { + "epoch": 0.57, + "learning_rate": 9.390945534923258e-06, + "loss": 1.3248, + "step": 5411 + }, + { + "epoch": 0.57, + "learning_rate": 9.387292120819716e-06, + "loss": 1.3084, + "step": 5412 + }, + { + "epoch": 0.57, + "learning_rate": 9.383638788803291e-06, + "loss": 1.344, + "step": 5413 + }, + { + "epoch": 0.57, + "learning_rate": 9.379985539363436e-06, + "loss": 1.3354, + "step": 5414 + }, + { + "epoch": 0.57, + "learning_rate": 9.376332372989586e-06, + "loss": 1.3291, + "step": 5415 + }, + { + "epoch": 0.57, + "learning_rate": 9.372679290171167e-06, + "loss": 1.3468, + "step": 5416 + }, + { + "epoch": 0.57, + "learning_rate": 9.36902629139761e-06, + "loss": 1.3481, + "step": 5417 + }, + { + "epoch": 0.57, + "learning_rate": 9.36537337715832e-06, + "loss": 1.3309, + "step": 5418 + }, + { + "epoch": 0.57, + "learning_rate": 9.361720547942683e-06, + "loss": 1.362, + "step": 5419 + }, + { + "epoch": 0.57, + "learning_rate": 9.358067804240098e-06, + "loss": 1.3647, + "step": 5420 + }, + { + "epoch": 0.57, + "learning_rate": 9.354415146539933e-06, + "loss": 1.4511, + "step": 5421 + }, + { + "epoch": 0.57, + "learning_rate": 9.350762575331554e-06, + "loss": 1.3379, + "step": 5422 + }, + { + "epoch": 0.57, + "learning_rate": 9.3471100911043e-06, + "loss": 1.5468, + "step": 5423 + }, + { + "epoch": 0.57, + "learning_rate": 9.343457694347524e-06, + "loss": 1.4259, + "step": 5424 + }, + { + "epoch": 0.57, + "learning_rate": 9.339805385550548e-06, + "loss": 1.3816, + "step": 5425 + }, + { + "epoch": 0.57, + "learning_rate": 9.336153165202689e-06, + "loss": 1.3627, + "step": 5426 + }, + { + "epoch": 0.57, + "learning_rate": 9.332501033793242e-06, + "loss": 1.3338, + "step": 5427 + }, + { + "epoch": 0.57, + "learning_rate": 9.328848991811509e-06, + "loss": 1.2946, + "step": 5428 + }, + { + "epoch": 0.57, + "learning_rate": 9.325197039746769e-06, + "loss": 1.3405, + "step": 5429 + }, + { + "epoch": 0.57, + "learning_rate": 9.321545178088288e-06, + "loss": 1.3549, + "step": 5430 + }, + { + "epoch": 0.57, + "learning_rate": 9.317893407325314e-06, + "loss": 1.3225, + "step": 5431 + }, + { + "epoch": 0.57, + "learning_rate": 9.314241727947101e-06, + "loss": 1.3457, + "step": 5432 + }, + { + "epoch": 0.57, + "learning_rate": 9.310590140442878e-06, + "loss": 1.311, + "step": 5433 + }, + { + "epoch": 0.57, + "learning_rate": 9.306938645301862e-06, + "loss": 1.3615, + "step": 5434 + }, + { + "epoch": 0.57, + "learning_rate": 9.303287243013255e-06, + "loss": 1.3495, + "step": 5435 + }, + { + "epoch": 0.57, + "learning_rate": 9.29963593406626e-06, + "loss": 1.3899, + "step": 5436 + }, + { + "epoch": 0.57, + "learning_rate": 9.295984718950058e-06, + "loss": 1.3189, + "step": 5437 + }, + { + "epoch": 0.57, + "learning_rate": 9.292333598153813e-06, + "loss": 1.4199, + "step": 5438 + }, + { + "epoch": 0.57, + "learning_rate": 9.288682572166677e-06, + "loss": 1.4751, + "step": 5439 + }, + { + "epoch": 0.57, + "learning_rate": 9.285031641477804e-06, + "loss": 1.3435, + "step": 5440 + }, + { + "epoch": 0.57, + "learning_rate": 9.281380806576322e-06, + "loss": 1.2954, + "step": 5441 + }, + { + "epoch": 0.57, + "learning_rate": 9.277730067951341e-06, + "loss": 1.3414, + "step": 5442 + }, + { + "epoch": 0.57, + "learning_rate": 9.274079426091978e-06, + "loss": 1.3642, + "step": 5443 + }, + { + "epoch": 0.57, + "learning_rate": 9.27042888148732e-06, + "loss": 1.3651, + "step": 5444 + }, + { + "epoch": 0.57, + "learning_rate": 9.266778434626448e-06, + "loss": 1.3995, + "step": 5445 + }, + { + "epoch": 0.57, + "learning_rate": 9.263128085998421e-06, + "loss": 1.2692, + "step": 5446 + }, + { + "epoch": 0.57, + "learning_rate": 9.2594778360923e-06, + "loss": 1.4355, + "step": 5447 + }, + { + "epoch": 0.57, + "learning_rate": 9.255827685397124e-06, + "loss": 1.4262, + "step": 5448 + }, + { + "epoch": 0.57, + "learning_rate": 9.252177634401917e-06, + "loss": 1.3372, + "step": 5449 + }, + { + "epoch": 0.57, + "learning_rate": 9.248527683595685e-06, + "loss": 1.4603, + "step": 5450 + }, + { + "epoch": 0.57, + "learning_rate": 9.24487783346744e-06, + "loss": 1.446, + "step": 5451 + }, + { + "epoch": 0.57, + "learning_rate": 9.241228084506167e-06, + "loss": 1.4088, + "step": 5452 + }, + { + "epoch": 0.57, + "learning_rate": 9.237578437200832e-06, + "loss": 1.3074, + "step": 5453 + }, + { + "epoch": 0.57, + "learning_rate": 9.233928892040392e-06, + "loss": 1.4347, + "step": 5454 + }, + { + "epoch": 0.57, + "learning_rate": 9.230279449513802e-06, + "loss": 1.2982, + "step": 5455 + }, + { + "epoch": 0.57, + "learning_rate": 9.226630110109988e-06, + "loss": 1.2928, + "step": 5456 + }, + { + "epoch": 0.57, + "learning_rate": 9.222980874317869e-06, + "loss": 1.2849, + "step": 5457 + }, + { + "epoch": 0.57, + "learning_rate": 9.219331742626343e-06, + "loss": 1.3137, + "step": 5458 + }, + { + "epoch": 0.57, + "learning_rate": 9.215682715524309e-06, + "loss": 1.3523, + "step": 5459 + }, + { + "epoch": 0.57, + "learning_rate": 9.21203379350064e-06, + "loss": 1.381, + "step": 5460 + }, + { + "epoch": 0.57, + "learning_rate": 9.208384977044191e-06, + "loss": 1.286, + "step": 5461 + }, + { + "epoch": 0.57, + "learning_rate": 9.204736266643819e-06, + "loss": 1.3467, + "step": 5462 + }, + { + "epoch": 0.57, + "learning_rate": 9.201087662788353e-06, + "loss": 1.3582, + "step": 5463 + }, + { + "epoch": 0.57, + "learning_rate": 9.197439165966617e-06, + "loss": 1.3912, + "step": 5464 + }, + { + "epoch": 0.57, + "learning_rate": 9.193790776667402e-06, + "loss": 1.3144, + "step": 5465 + }, + { + "epoch": 0.57, + "learning_rate": 9.190142495379515e-06, + "loss": 1.3403, + "step": 5466 + }, + { + "epoch": 0.57, + "learning_rate": 9.186494322591725e-06, + "loss": 1.3253, + "step": 5467 + }, + { + "epoch": 0.57, + "learning_rate": 9.182846258792794e-06, + "loss": 1.2908, + "step": 5468 + }, + { + "epoch": 0.57, + "learning_rate": 9.179198304471463e-06, + "loss": 1.3486, + "step": 5469 + }, + { + "epoch": 0.57, + "learning_rate": 9.175550460116473e-06, + "loss": 1.3915, + "step": 5470 + }, + { + "epoch": 0.57, + "learning_rate": 9.171902726216538e-06, + "loss": 1.3441, + "step": 5471 + }, + { + "epoch": 0.57, + "learning_rate": 9.168255103260362e-06, + "loss": 1.3196, + "step": 5472 + }, + { + "epoch": 0.57, + "learning_rate": 9.164607591736627e-06, + "loss": 1.3279, + "step": 5473 + }, + { + "epoch": 0.57, + "learning_rate": 9.160960192134011e-06, + "loss": 1.2643, + "step": 5474 + }, + { + "epoch": 0.57, + "learning_rate": 9.157312904941174e-06, + "loss": 1.3327, + "step": 5475 + }, + { + "epoch": 0.57, + "learning_rate": 9.153665730646756e-06, + "loss": 1.4016, + "step": 5476 + }, + { + "epoch": 0.57, + "learning_rate": 9.150018669739378e-06, + "loss": 1.3614, + "step": 5477 + }, + { + "epoch": 0.57, + "learning_rate": 9.146371722707662e-06, + "loss": 1.3469, + "step": 5478 + }, + { + "epoch": 0.57, + "learning_rate": 9.142724890040204e-06, + "loss": 1.3625, + "step": 5479 + }, + { + "epoch": 0.57, + "learning_rate": 9.139078172225585e-06, + "loss": 1.3879, + "step": 5480 + }, + { + "epoch": 0.57, + "learning_rate": 9.135431569752362e-06, + "loss": 1.3738, + "step": 5481 + }, + { + "epoch": 0.57, + "learning_rate": 9.131785083109101e-06, + "loss": 1.3507, + "step": 5482 + }, + { + "epoch": 0.57, + "learning_rate": 9.128138712784331e-06, + "loss": 1.3681, + "step": 5483 + }, + { + "epoch": 0.58, + "learning_rate": 9.124492459266567e-06, + "loss": 1.332, + "step": 5484 + }, + { + "epoch": 0.58, + "learning_rate": 9.12084632304432e-06, + "loss": 1.4746, + "step": 5485 + }, + { + "epoch": 0.58, + "learning_rate": 9.11720030460608e-06, + "loss": 1.2775, + "step": 5486 + }, + { + "epoch": 0.58, + "learning_rate": 9.113554404440317e-06, + "loss": 1.2567, + "step": 5487 + }, + { + "epoch": 0.58, + "learning_rate": 9.10990862303548e-06, + "loss": 1.3935, + "step": 5488 + }, + { + "epoch": 0.58, + "learning_rate": 9.106262960880024e-06, + "loss": 1.3544, + "step": 5489 + }, + { + "epoch": 0.58, + "learning_rate": 9.102617418462365e-06, + "loss": 1.4023, + "step": 5490 + }, + { + "epoch": 0.58, + "learning_rate": 9.098971996270918e-06, + "loss": 1.3759, + "step": 5491 + }, + { + "epoch": 0.58, + "learning_rate": 9.095326694794064e-06, + "loss": 1.4165, + "step": 5492 + }, + { + "epoch": 0.58, + "learning_rate": 9.091681514520194e-06, + "loss": 1.3189, + "step": 5493 + }, + { + "epoch": 0.58, + "learning_rate": 9.088036455937663e-06, + "loss": 1.3135, + "step": 5494 + }, + { + "epoch": 0.58, + "learning_rate": 9.084391519534815e-06, + "loss": 1.3521, + "step": 5495 + }, + { + "epoch": 0.58, + "learning_rate": 9.080746705799971e-06, + "loss": 1.3314, + "step": 5496 + }, + { + "epoch": 0.58, + "learning_rate": 9.077102015221457e-06, + "loss": 1.3119, + "step": 5497 + }, + { + "epoch": 0.58, + "learning_rate": 9.073457448287557e-06, + "loss": 1.2895, + "step": 5498 + }, + { + "epoch": 0.58, + "learning_rate": 9.069813005486554e-06, + "loss": 1.3155, + "step": 5499 + }, + { + "epoch": 0.58, + "learning_rate": 9.066168687306701e-06, + "loss": 1.4048, + "step": 5500 + }, + { + "epoch": 0.58, + "learning_rate": 9.062524494236256e-06, + "loss": 1.3665, + "step": 5501 + }, + { + "epoch": 0.58, + "learning_rate": 9.058880426763442e-06, + "loss": 1.3258, + "step": 5502 + }, + { + "epoch": 0.58, + "learning_rate": 9.05523648537647e-06, + "loss": 1.3078, + "step": 5503 + }, + { + "epoch": 0.58, + "learning_rate": 9.051592670563527e-06, + "loss": 1.361, + "step": 5504 + }, + { + "epoch": 0.58, + "learning_rate": 9.047948982812801e-06, + "loss": 1.3557, + "step": 5505 + }, + { + "epoch": 0.58, + "learning_rate": 9.044305422612453e-06, + "loss": 1.5733, + "step": 5506 + }, + { + "epoch": 0.58, + "learning_rate": 9.040661990450617e-06, + "loss": 1.2835, + "step": 5507 + }, + { + "epoch": 0.58, + "learning_rate": 9.037018686815428e-06, + "loss": 1.311, + "step": 5508 + }, + { + "epoch": 0.58, + "learning_rate": 9.033375512194993e-06, + "loss": 1.3949, + "step": 5509 + }, + { + "epoch": 0.58, + "learning_rate": 9.029732467077405e-06, + "loss": 1.356, + "step": 5510 + }, + { + "epoch": 0.58, + "learning_rate": 9.026089551950727e-06, + "loss": 1.3695, + "step": 5511 + }, + { + "epoch": 0.58, + "learning_rate": 9.022446767303033e-06, + "loss": 1.3325, + "step": 5512 + }, + { + "epoch": 0.58, + "learning_rate": 9.018804113622353e-06, + "loss": 1.401, + "step": 5513 + }, + { + "epoch": 0.58, + "learning_rate": 9.015161591396713e-06, + "loss": 1.3632, + "step": 5514 + }, + { + "epoch": 0.58, + "learning_rate": 9.011519201114108e-06, + "loss": 1.3697, + "step": 5515 + }, + { + "epoch": 0.58, + "learning_rate": 9.007876943262538e-06, + "loss": 1.2604, + "step": 5516 + }, + { + "epoch": 0.58, + "learning_rate": 9.004234818329964e-06, + "loss": 1.3557, + "step": 5517 + }, + { + "epoch": 0.58, + "learning_rate": 9.000592826804342e-06, + "loss": 1.3248, + "step": 5518 + }, + { + "epoch": 0.58, + "learning_rate": 8.996950969173596e-06, + "loss": 1.3237, + "step": 5519 + }, + { + "epoch": 0.58, + "learning_rate": 8.99330924592565e-06, + "loss": 1.339, + "step": 5520 + }, + { + "epoch": 0.58, + "learning_rate": 8.989667657548402e-06, + "loss": 1.3218, + "step": 5521 + }, + { + "epoch": 0.58, + "learning_rate": 8.986026204529728e-06, + "loss": 1.3354, + "step": 5522 + }, + { + "epoch": 0.58, + "learning_rate": 8.982384887357484e-06, + "loss": 1.3011, + "step": 5523 + }, + { + "epoch": 0.58, + "learning_rate": 8.978743706519524e-06, + "loss": 1.3526, + "step": 5524 + }, + { + "epoch": 0.58, + "learning_rate": 8.975102662503666e-06, + "loss": 1.3298, + "step": 5525 + }, + { + "epoch": 0.58, + "learning_rate": 8.971461755797718e-06, + "loss": 1.328, + "step": 5526 + }, + { + "epoch": 0.58, + "learning_rate": 8.967820986889461e-06, + "loss": 1.3705, + "step": 5527 + }, + { + "epoch": 0.58, + "learning_rate": 8.964180356266676e-06, + "loss": 1.3814, + "step": 5528 + }, + { + "epoch": 0.58, + "learning_rate": 8.96053986441711e-06, + "loss": 1.37, + "step": 5529 + }, + { + "epoch": 0.58, + "learning_rate": 8.956899511828489e-06, + "loss": 1.3224, + "step": 5530 + }, + { + "epoch": 0.58, + "learning_rate": 8.953259298988536e-06, + "loss": 1.3416, + "step": 5531 + }, + { + "epoch": 0.58, + "learning_rate": 8.949619226384942e-06, + "loss": 1.4212, + "step": 5532 + }, + { + "epoch": 0.58, + "learning_rate": 8.945979294505383e-06, + "loss": 1.4145, + "step": 5533 + }, + { + "epoch": 0.58, + "learning_rate": 8.942339503837512e-06, + "loss": 1.2179, + "step": 5534 + }, + { + "epoch": 0.58, + "learning_rate": 8.938699854868976e-06, + "loss": 1.3239, + "step": 5535 + }, + { + "epoch": 0.58, + "learning_rate": 8.93506034808739e-06, + "loss": 1.3488, + "step": 5536 + }, + { + "epoch": 0.58, + "learning_rate": 8.931420983980357e-06, + "loss": 1.3283, + "step": 5537 + }, + { + "epoch": 0.58, + "learning_rate": 8.927781763035449e-06, + "loss": 1.3866, + "step": 5538 + }, + { + "epoch": 0.58, + "learning_rate": 8.924142685740239e-06, + "loss": 1.3877, + "step": 5539 + }, + { + "epoch": 0.58, + "learning_rate": 8.920503752582265e-06, + "loss": 1.2511, + "step": 5540 + }, + { + "epoch": 0.58, + "learning_rate": 8.916864964049056e-06, + "loss": 1.3581, + "step": 5541 + }, + { + "epoch": 0.58, + "learning_rate": 8.913226320628104e-06, + "loss": 1.387, + "step": 5542 + }, + { + "epoch": 0.58, + "learning_rate": 8.909587822806905e-06, + "loss": 1.3785, + "step": 5543 + }, + { + "epoch": 0.58, + "learning_rate": 8.905949471072921e-06, + "loss": 1.4302, + "step": 5544 + }, + { + "epoch": 0.58, + "learning_rate": 8.9023112659136e-06, + "loss": 1.439, + "step": 5545 + }, + { + "epoch": 0.58, + "learning_rate": 8.898673207816357e-06, + "loss": 1.3257, + "step": 5546 + }, + { + "epoch": 0.58, + "learning_rate": 8.895035297268611e-06, + "loss": 1.4237, + "step": 5547 + }, + { + "epoch": 0.58, + "learning_rate": 8.891397534757745e-06, + "loss": 1.3141, + "step": 5548 + }, + { + "epoch": 0.58, + "learning_rate": 8.887759920771127e-06, + "loss": 1.3069, + "step": 5549 + }, + { + "epoch": 0.58, + "learning_rate": 8.884122455796095e-06, + "loss": 1.2703, + "step": 5550 + }, + { + "epoch": 0.58, + "learning_rate": 8.880485140319986e-06, + "loss": 1.2929, + "step": 5551 + }, + { + "epoch": 0.58, + "learning_rate": 8.876847974830103e-06, + "loss": 1.3719, + "step": 5552 + }, + { + "epoch": 0.58, + "learning_rate": 8.873210959813731e-06, + "loss": 1.3481, + "step": 5553 + }, + { + "epoch": 0.58, + "learning_rate": 8.869574095758141e-06, + "loss": 1.3609, + "step": 5554 + }, + { + "epoch": 0.58, + "learning_rate": 8.865937383150577e-06, + "loss": 1.3137, + "step": 5555 + }, + { + "epoch": 0.58, + "learning_rate": 8.862300822478265e-06, + "loss": 1.3602, + "step": 5556 + }, + { + "epoch": 0.58, + "learning_rate": 8.858664414228409e-06, + "loss": 1.3142, + "step": 5557 + }, + { + "epoch": 0.58, + "learning_rate": 8.855028158888196e-06, + "loss": 1.288, + "step": 5558 + }, + { + "epoch": 0.58, + "learning_rate": 8.851392056944791e-06, + "loss": 1.3407, + "step": 5559 + }, + { + "epoch": 0.58, + "learning_rate": 8.847756108885342e-06, + "loss": 1.3118, + "step": 5560 + }, + { + "epoch": 0.58, + "learning_rate": 8.84412031519696e-06, + "loss": 1.3646, + "step": 5561 + }, + { + "epoch": 0.58, + "learning_rate": 8.840484676366761e-06, + "loss": 1.3896, + "step": 5562 + }, + { + "epoch": 0.58, + "learning_rate": 8.836849192881822e-06, + "loss": 1.3296, + "step": 5563 + }, + { + "epoch": 0.58, + "learning_rate": 8.833213865229208e-06, + "loss": 1.2918, + "step": 5564 + }, + { + "epoch": 0.58, + "learning_rate": 8.82957869389595e-06, + "loss": 1.4811, + "step": 5565 + }, + { + "epoch": 0.58, + "learning_rate": 8.82594367936908e-06, + "loss": 1.3877, + "step": 5566 + }, + { + "epoch": 0.58, + "learning_rate": 8.822308822135588e-06, + "loss": 1.3716, + "step": 5567 + }, + { + "epoch": 0.58, + "learning_rate": 8.818674122682456e-06, + "loss": 1.3204, + "step": 5568 + }, + { + "epoch": 0.58, + "learning_rate": 8.815039581496634e-06, + "loss": 1.326, + "step": 5569 + }, + { + "epoch": 0.58, + "learning_rate": 8.811405199065066e-06, + "loss": 1.3762, + "step": 5570 + }, + { + "epoch": 0.58, + "learning_rate": 8.807770975874658e-06, + "loss": 1.2944, + "step": 5571 + }, + { + "epoch": 0.58, + "learning_rate": 8.804136912412311e-06, + "loss": 1.3057, + "step": 5572 + }, + { + "epoch": 0.58, + "eval_loss": 1.4187605381011963, + "eval_runtime": 77.5157, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 5572 + }, + { + "epoch": 0.58, + "learning_rate": 8.800503009164884e-06, + "loss": 1.4144, + "step": 5573 + }, + { + "epoch": 0.58, + "learning_rate": 8.796869266619238e-06, + "loss": 1.2218, + "step": 5574 + }, + { + "epoch": 0.58, + "learning_rate": 8.793235685262197e-06, + "loss": 1.4445, + "step": 5575 + }, + { + "epoch": 0.58, + "learning_rate": 8.789602265580565e-06, + "loss": 1.3761, + "step": 5576 + }, + { + "epoch": 0.58, + "learning_rate": 8.78596900806113e-06, + "loss": 1.3762, + "step": 5577 + }, + { + "epoch": 0.58, + "learning_rate": 8.782335913190657e-06, + "loss": 1.3506, + "step": 5578 + }, + { + "epoch": 0.59, + "learning_rate": 8.778702981455883e-06, + "loss": 1.4183, + "step": 5579 + }, + { + "epoch": 0.59, + "learning_rate": 8.775070213343528e-06, + "loss": 1.3123, + "step": 5580 + }, + { + "epoch": 0.59, + "learning_rate": 8.771437609340291e-06, + "loss": 1.3168, + "step": 5581 + }, + { + "epoch": 0.59, + "learning_rate": 8.76780516993285e-06, + "loss": 1.3939, + "step": 5582 + }, + { + "epoch": 0.59, + "learning_rate": 8.764172895607856e-06, + "loss": 1.3317, + "step": 5583 + }, + { + "epoch": 0.59, + "learning_rate": 8.760540786851937e-06, + "loss": 1.3094, + "step": 5584 + }, + { + "epoch": 0.59, + "learning_rate": 8.756908844151708e-06, + "loss": 1.2853, + "step": 5585 + }, + { + "epoch": 0.59, + "learning_rate": 8.753277067993752e-06, + "loss": 1.2625, + "step": 5586 + }, + { + "epoch": 0.59, + "learning_rate": 8.74964545886464e-06, + "loss": 1.4246, + "step": 5587 + }, + { + "epoch": 0.59, + "learning_rate": 8.746014017250904e-06, + "loss": 1.2891, + "step": 5588 + }, + { + "epoch": 0.59, + "learning_rate": 8.742382743639071e-06, + "loss": 1.3135, + "step": 5589 + }, + { + "epoch": 0.59, + "learning_rate": 8.738751638515639e-06, + "loss": 1.3021, + "step": 5590 + }, + { + "epoch": 0.59, + "learning_rate": 8.735120702367082e-06, + "loss": 1.3398, + "step": 5591 + }, + { + "epoch": 0.59, + "learning_rate": 8.731489935679845e-06, + "loss": 1.4173, + "step": 5592 + }, + { + "epoch": 0.59, + "learning_rate": 8.727859338940367e-06, + "loss": 1.4129, + "step": 5593 + }, + { + "epoch": 0.59, + "learning_rate": 8.724228912635053e-06, + "loss": 1.3807, + "step": 5594 + }, + { + "epoch": 0.59, + "learning_rate": 8.720598657250284e-06, + "loss": 1.2962, + "step": 5595 + }, + { + "epoch": 0.59, + "learning_rate": 8.716968573272416e-06, + "loss": 1.3784, + "step": 5596 + }, + { + "epoch": 0.59, + "learning_rate": 8.713338661187799e-06, + "loss": 1.3751, + "step": 5597 + }, + { + "epoch": 0.59, + "learning_rate": 8.70970892148274e-06, + "loss": 1.3122, + "step": 5598 + }, + { + "epoch": 0.59, + "learning_rate": 8.70607935464353e-06, + "loss": 1.4174, + "step": 5599 + }, + { + "epoch": 0.59, + "learning_rate": 8.702449961156445e-06, + "loss": 1.3275, + "step": 5600 + }, + { + "epoch": 0.59, + "learning_rate": 8.698820741507723e-06, + "loss": 1.33, + "step": 5601 + }, + { + "epoch": 0.59, + "learning_rate": 8.695191696183589e-06, + "loss": 1.4075, + "step": 5602 + }, + { + "epoch": 0.59, + "learning_rate": 8.69156282567024e-06, + "loss": 1.3778, + "step": 5603 + }, + { + "epoch": 0.59, + "learning_rate": 8.687934130453857e-06, + "loss": 1.3222, + "step": 5604 + }, + { + "epoch": 0.59, + "learning_rate": 8.684305611020587e-06, + "loss": 1.3443, + "step": 5605 + }, + { + "epoch": 0.59, + "learning_rate": 8.680677267856558e-06, + "loss": 1.3167, + "step": 5606 + }, + { + "epoch": 0.59, + "learning_rate": 8.677049101447877e-06, + "loss": 1.3209, + "step": 5607 + }, + { + "epoch": 0.59, + "learning_rate": 8.673421112280624e-06, + "loss": 1.3125, + "step": 5608 + }, + { + "epoch": 0.59, + "learning_rate": 8.669793300840857e-06, + "loss": 1.375, + "step": 5609 + }, + { + "epoch": 0.59, + "learning_rate": 8.666165667614612e-06, + "loss": 1.3627, + "step": 5610 + }, + { + "epoch": 0.59, + "learning_rate": 8.662538213087888e-06, + "loss": 1.3064, + "step": 5611 + }, + { + "epoch": 0.59, + "learning_rate": 8.658910937746685e-06, + "loss": 1.4251, + "step": 5612 + }, + { + "epoch": 0.59, + "learning_rate": 8.655283842076956e-06, + "loss": 1.3011, + "step": 5613 + }, + { + "epoch": 0.59, + "learning_rate": 8.651656926564645e-06, + "loss": 1.3299, + "step": 5614 + }, + { + "epoch": 0.59, + "learning_rate": 8.648030191695653e-06, + "loss": 1.3448, + "step": 5615 + }, + { + "epoch": 0.59, + "learning_rate": 8.644403637955883e-06, + "loss": 1.4048, + "step": 5616 + }, + { + "epoch": 0.59, + "learning_rate": 8.640777265831195e-06, + "loss": 1.336, + "step": 5617 + }, + { + "epoch": 0.59, + "learning_rate": 8.63715107580743e-06, + "loss": 1.4959, + "step": 5618 + }, + { + "epoch": 0.59, + "learning_rate": 8.633525068370397e-06, + "loss": 1.3822, + "step": 5619 + }, + { + "epoch": 0.59, + "learning_rate": 8.6298992440059e-06, + "loss": 1.282, + "step": 5620 + }, + { + "epoch": 0.59, + "learning_rate": 8.626273603199699e-06, + "loss": 1.1873, + "step": 5621 + }, + { + "epoch": 0.59, + "learning_rate": 8.622648146437538e-06, + "loss": 1.3706, + "step": 5622 + }, + { + "epoch": 0.59, + "learning_rate": 8.619022874205138e-06, + "loss": 1.2709, + "step": 5623 + }, + { + "epoch": 0.59, + "learning_rate": 8.615397786988188e-06, + "loss": 1.3608, + "step": 5624 + }, + { + "epoch": 0.59, + "learning_rate": 8.61177288527236e-06, + "loss": 1.3821, + "step": 5625 + }, + { + "epoch": 0.59, + "learning_rate": 8.608148169543292e-06, + "loss": 1.327, + "step": 5626 + }, + { + "epoch": 0.59, + "learning_rate": 8.604523640286611e-06, + "loss": 1.3544, + "step": 5627 + }, + { + "epoch": 0.59, + "learning_rate": 8.600899297987905e-06, + "loss": 1.3269, + "step": 5628 + }, + { + "epoch": 0.59, + "learning_rate": 8.597275143132745e-06, + "loss": 1.3142, + "step": 5629 + }, + { + "epoch": 0.59, + "learning_rate": 8.593651176206671e-06, + "loss": 1.3878, + "step": 5630 + }, + { + "epoch": 0.59, + "learning_rate": 8.59002739769521e-06, + "loss": 1.3386, + "step": 5631 + }, + { + "epoch": 0.59, + "learning_rate": 8.586403808083846e-06, + "loss": 1.3484, + "step": 5632 + }, + { + "epoch": 0.59, + "learning_rate": 8.582780407858052e-06, + "loss": 1.3676, + "step": 5633 + }, + { + "epoch": 0.59, + "learning_rate": 8.579157197503265e-06, + "loss": 1.3753, + "step": 5634 + }, + { + "epoch": 0.59, + "learning_rate": 8.57553417750491e-06, + "loss": 1.4058, + "step": 5635 + }, + { + "epoch": 0.59, + "learning_rate": 8.571911348348375e-06, + "loss": 1.4434, + "step": 5636 + }, + { + "epoch": 0.59, + "learning_rate": 8.568288710519027e-06, + "loss": 1.3398, + "step": 5637 + }, + { + "epoch": 0.59, + "learning_rate": 8.564666264502199e-06, + "loss": 1.3294, + "step": 5638 + }, + { + "epoch": 0.59, + "learning_rate": 8.561044010783216e-06, + "loss": 1.3165, + "step": 5639 + }, + { + "epoch": 0.59, + "learning_rate": 8.557421949847363e-06, + "loss": 1.3437, + "step": 5640 + }, + { + "epoch": 0.59, + "learning_rate": 8.553800082179905e-06, + "loss": 1.3473, + "step": 5641 + }, + { + "epoch": 0.59, + "learning_rate": 8.55017840826607e-06, + "loss": 1.3378, + "step": 5642 + }, + { + "epoch": 0.59, + "learning_rate": 8.546556928591082e-06, + "loss": 1.3357, + "step": 5643 + }, + { + "epoch": 0.59, + "learning_rate": 8.54293564364012e-06, + "loss": 1.3435, + "step": 5644 + }, + { + "epoch": 0.59, + "learning_rate": 8.53931455389834e-06, + "loss": 1.3335, + "step": 5645 + }, + { + "epoch": 0.59, + "learning_rate": 8.535693659850885e-06, + "loss": 1.2917, + "step": 5646 + }, + { + "epoch": 0.59, + "learning_rate": 8.532072961982851e-06, + "loss": 1.3785, + "step": 5647 + }, + { + "epoch": 0.59, + "learning_rate": 8.528452460779327e-06, + "loss": 1.3634, + "step": 5648 + }, + { + "epoch": 0.59, + "learning_rate": 8.524832156725359e-06, + "loss": 1.3541, + "step": 5649 + }, + { + "epoch": 0.59, + "learning_rate": 8.521212050305978e-06, + "loss": 1.335, + "step": 5650 + }, + { + "epoch": 0.59, + "learning_rate": 8.51759214200619e-06, + "loss": 1.3011, + "step": 5651 + }, + { + "epoch": 0.59, + "learning_rate": 8.513972432310965e-06, + "loss": 1.3982, + "step": 5652 + }, + { + "epoch": 0.59, + "learning_rate": 8.510352921705247e-06, + "loss": 1.3217, + "step": 5653 + }, + { + "epoch": 0.59, + "learning_rate": 8.506733610673968e-06, + "loss": 1.3275, + "step": 5654 + }, + { + "epoch": 0.59, + "learning_rate": 8.503114499702015e-06, + "loss": 1.3335, + "step": 5655 + }, + { + "epoch": 0.59, + "learning_rate": 8.499495589274257e-06, + "loss": 1.3567, + "step": 5656 + }, + { + "epoch": 0.59, + "learning_rate": 8.495876879875536e-06, + "loss": 1.348, + "step": 5657 + }, + { + "epoch": 0.59, + "learning_rate": 8.492258371990667e-06, + "loss": 1.3991, + "step": 5658 + }, + { + "epoch": 0.59, + "learning_rate": 8.488640066104435e-06, + "loss": 1.3528, + "step": 5659 + }, + { + "epoch": 0.59, + "learning_rate": 8.485021962701603e-06, + "loss": 1.3275, + "step": 5660 + }, + { + "epoch": 0.59, + "learning_rate": 8.481404062266897e-06, + "loss": 1.3605, + "step": 5661 + }, + { + "epoch": 0.59, + "learning_rate": 8.477786365285032e-06, + "loss": 1.3288, + "step": 5662 + }, + { + "epoch": 0.59, + "learning_rate": 8.474168872240682e-06, + "loss": 1.3274, + "step": 5663 + }, + { + "epoch": 0.59, + "learning_rate": 8.470551583618498e-06, + "loss": 1.273, + "step": 5664 + }, + { + "epoch": 0.59, + "learning_rate": 8.4669344999031e-06, + "loss": 1.3142, + "step": 5665 + }, + { + "epoch": 0.59, + "learning_rate": 8.463317621579091e-06, + "loss": 1.2912, + "step": 5666 + }, + { + "epoch": 0.59, + "learning_rate": 8.459700949131037e-06, + "loss": 1.3162, + "step": 5667 + }, + { + "epoch": 0.59, + "learning_rate": 8.456084483043479e-06, + "loss": 1.3377, + "step": 5668 + }, + { + "epoch": 0.59, + "learning_rate": 8.452468223800931e-06, + "loss": 1.3545, + "step": 5669 + }, + { + "epoch": 0.59, + "learning_rate": 8.448852171887878e-06, + "loss": 1.4052, + "step": 5670 + }, + { + "epoch": 0.59, + "learning_rate": 8.44523632778878e-06, + "loss": 1.3389, + "step": 5671 + }, + { + "epoch": 0.59, + "learning_rate": 8.441620691988063e-06, + "loss": 1.3801, + "step": 5672 + }, + { + "epoch": 0.59, + "learning_rate": 8.438005264970134e-06, + "loss": 1.2978, + "step": 5673 + }, + { + "epoch": 0.6, + "learning_rate": 8.434390047219366e-06, + "loss": 1.437, + "step": 5674 + }, + { + "epoch": 0.6, + "learning_rate": 8.430775039220103e-06, + "loss": 1.3602, + "step": 5675 + }, + { + "epoch": 0.6, + "learning_rate": 8.427160241456664e-06, + "loss": 1.4971, + "step": 5676 + }, + { + "epoch": 0.6, + "learning_rate": 8.423545654413342e-06, + "loss": 1.2765, + "step": 5677 + }, + { + "epoch": 0.6, + "learning_rate": 8.419931278574397e-06, + "loss": 1.4346, + "step": 5678 + }, + { + "epoch": 0.6, + "learning_rate": 8.416317114424059e-06, + "loss": 1.366, + "step": 5679 + }, + { + "epoch": 0.6, + "learning_rate": 8.412703162446536e-06, + "loss": 1.3776, + "step": 5680 + }, + { + "epoch": 0.6, + "learning_rate": 8.409089423126009e-06, + "loss": 1.2516, + "step": 5681 + }, + { + "epoch": 0.6, + "learning_rate": 8.405475896946621e-06, + "loss": 1.4257, + "step": 5682 + }, + { + "epoch": 0.6, + "learning_rate": 8.401862584392492e-06, + "loss": 1.3523, + "step": 5683 + }, + { + "epoch": 0.6, + "learning_rate": 8.398249485947712e-06, + "loss": 1.3791, + "step": 5684 + }, + { + "epoch": 0.6, + "learning_rate": 8.394636602096348e-06, + "loss": 1.3574, + "step": 5685 + }, + { + "epoch": 0.6, + "learning_rate": 8.39102393332243e-06, + "loss": 1.4748, + "step": 5686 + }, + { + "epoch": 0.6, + "learning_rate": 8.387411480109967e-06, + "loss": 1.3693, + "step": 5687 + }, + { + "epoch": 0.6, + "learning_rate": 8.383799242942925e-06, + "loss": 1.3643, + "step": 5688 + }, + { + "epoch": 0.6, + "learning_rate": 8.38018722230526e-06, + "loss": 1.3446, + "step": 5689 + }, + { + "epoch": 0.6, + "learning_rate": 8.37657541868089e-06, + "loss": 1.3552, + "step": 5690 + }, + { + "epoch": 0.6, + "learning_rate": 8.372963832553698e-06, + "loss": 1.3636, + "step": 5691 + }, + { + "epoch": 0.6, + "learning_rate": 8.36935246440755e-06, + "loss": 1.3398, + "step": 5692 + }, + { + "epoch": 0.6, + "learning_rate": 8.365741314726273e-06, + "loss": 1.3336, + "step": 5693 + }, + { + "epoch": 0.6, + "learning_rate": 8.362130383993667e-06, + "loss": 1.3023, + "step": 5694 + }, + { + "epoch": 0.6, + "learning_rate": 8.358519672693506e-06, + "loss": 1.3591, + "step": 5695 + }, + { + "epoch": 0.6, + "learning_rate": 8.354909181309533e-06, + "loss": 1.3113, + "step": 5696 + }, + { + "epoch": 0.6, + "learning_rate": 8.351298910325462e-06, + "loss": 1.3747, + "step": 5697 + }, + { + "epoch": 0.6, + "learning_rate": 8.347688860224976e-06, + "loss": 1.3555, + "step": 5698 + }, + { + "epoch": 0.6, + "learning_rate": 8.344079031491722e-06, + "loss": 1.2947, + "step": 5699 + }, + { + "epoch": 0.6, + "learning_rate": 8.340469424609337e-06, + "loss": 1.4099, + "step": 5700 + }, + { + "epoch": 0.6, + "learning_rate": 8.336860040061404e-06, + "loss": 1.3263, + "step": 5701 + }, + { + "epoch": 0.6, + "learning_rate": 8.333250878331498e-06, + "loss": 1.372, + "step": 5702 + }, + { + "epoch": 0.6, + "learning_rate": 8.329641939903142e-06, + "loss": 1.3523, + "step": 5703 + }, + { + "epoch": 0.6, + "learning_rate": 8.32603322525985e-06, + "loss": 1.3451, + "step": 5704 + }, + { + "epoch": 0.6, + "learning_rate": 8.322424734885098e-06, + "loss": 1.3296, + "step": 5705 + }, + { + "epoch": 0.6, + "learning_rate": 8.318816469262325e-06, + "loss": 1.449, + "step": 5706 + }, + { + "epoch": 0.6, + "learning_rate": 8.315208428874946e-06, + "loss": 1.3611, + "step": 5707 + }, + { + "epoch": 0.6, + "learning_rate": 8.311600614206352e-06, + "loss": 1.3849, + "step": 5708 + }, + { + "epoch": 0.6, + "learning_rate": 8.307993025739893e-06, + "loss": 1.3968, + "step": 5709 + }, + { + "epoch": 0.6, + "learning_rate": 8.304385663958895e-06, + "loss": 1.4428, + "step": 5710 + }, + { + "epoch": 0.6, + "learning_rate": 8.300778529346647e-06, + "loss": 1.3095, + "step": 5711 + }, + { + "epoch": 0.6, + "learning_rate": 8.297171622386418e-06, + "loss": 1.3135, + "step": 5712 + }, + { + "epoch": 0.6, + "learning_rate": 8.293564943561438e-06, + "loss": 1.3069, + "step": 5713 + }, + { + "epoch": 0.6, + "learning_rate": 8.28995849335491e-06, + "loss": 1.3736, + "step": 5714 + }, + { + "epoch": 0.6, + "learning_rate": 8.286352272250007e-06, + "loss": 1.343, + "step": 5715 + }, + { + "epoch": 0.6, + "learning_rate": 8.28274628072987e-06, + "loss": 1.2929, + "step": 5716 + }, + { + "epoch": 0.6, + "learning_rate": 8.279140519277607e-06, + "loss": 1.3356, + "step": 5717 + }, + { + "epoch": 0.6, + "learning_rate": 8.275534988376295e-06, + "loss": 1.2683, + "step": 5718 + }, + { + "epoch": 0.6, + "learning_rate": 8.27192968850899e-06, + "loss": 1.3738, + "step": 5719 + }, + { + "epoch": 0.6, + "learning_rate": 8.268324620158704e-06, + "loss": 1.3369, + "step": 5720 + }, + { + "epoch": 0.6, + "learning_rate": 8.264719783808425e-06, + "loss": 1.3684, + "step": 5721 + }, + { + "epoch": 0.6, + "learning_rate": 8.261115179941108e-06, + "loss": 1.4081, + "step": 5722 + }, + { + "epoch": 0.6, + "learning_rate": 8.257510809039678e-06, + "loss": 1.2504, + "step": 5723 + }, + { + "epoch": 0.6, + "learning_rate": 8.253906671587029e-06, + "loss": 1.417, + "step": 5724 + }, + { + "epoch": 0.6, + "learning_rate": 8.25030276806602e-06, + "loss": 1.3631, + "step": 5725 + }, + { + "epoch": 0.6, + "learning_rate": 8.246699098959483e-06, + "loss": 1.499, + "step": 5726 + }, + { + "epoch": 0.6, + "learning_rate": 8.243095664750217e-06, + "loss": 1.3656, + "step": 5727 + }, + { + "epoch": 0.6, + "learning_rate": 8.239492465920992e-06, + "loss": 1.3563, + "step": 5728 + }, + { + "epoch": 0.6, + "learning_rate": 8.23588950295454e-06, + "loss": 1.3554, + "step": 5729 + }, + { + "epoch": 0.6, + "learning_rate": 8.232286776333566e-06, + "loss": 1.2705, + "step": 5730 + }, + { + "epoch": 0.6, + "learning_rate": 8.228684286540747e-06, + "loss": 1.3792, + "step": 5731 + }, + { + "epoch": 0.6, + "learning_rate": 8.22508203405872e-06, + "loss": 1.3301, + "step": 5732 + }, + { + "epoch": 0.6, + "learning_rate": 8.221480019370095e-06, + "loss": 1.36, + "step": 5733 + }, + { + "epoch": 0.6, + "learning_rate": 8.217878242957448e-06, + "loss": 1.4406, + "step": 5734 + }, + { + "epoch": 0.6, + "learning_rate": 8.214276705303328e-06, + "loss": 1.2886, + "step": 5735 + }, + { + "epoch": 0.6, + "learning_rate": 8.210675406890248e-06, + "loss": 1.3072, + "step": 5736 + }, + { + "epoch": 0.6, + "learning_rate": 8.207074348200686e-06, + "loss": 1.3734, + "step": 5737 + }, + { + "epoch": 0.6, + "learning_rate": 8.203473529717095e-06, + "loss": 1.3893, + "step": 5738 + }, + { + "epoch": 0.6, + "learning_rate": 8.199872951921892e-06, + "loss": 1.3427, + "step": 5739 + }, + { + "epoch": 0.6, + "learning_rate": 8.196272615297459e-06, + "loss": 1.3125, + "step": 5740 + }, + { + "epoch": 0.6, + "learning_rate": 8.19267252032615e-06, + "loss": 1.3079, + "step": 5741 + }, + { + "epoch": 0.6, + "learning_rate": 8.189072667490285e-06, + "loss": 1.2971, + "step": 5742 + }, + { + "epoch": 0.6, + "learning_rate": 8.185473057272154e-06, + "loss": 1.3003, + "step": 5743 + }, + { + "epoch": 0.6, + "learning_rate": 8.18187369015401e-06, + "loss": 1.3002, + "step": 5744 + }, + { + "epoch": 0.6, + "learning_rate": 8.178274566618075e-06, + "loss": 1.2852, + "step": 5745 + }, + { + "epoch": 0.6, + "learning_rate": 8.174675687146542e-06, + "loss": 1.2807, + "step": 5746 + }, + { + "epoch": 0.6, + "learning_rate": 8.171077052221567e-06, + "loss": 1.2983, + "step": 5747 + }, + { + "epoch": 0.6, + "learning_rate": 8.167478662325274e-06, + "loss": 1.3002, + "step": 5748 + }, + { + "epoch": 0.6, + "learning_rate": 8.163880517939753e-06, + "loss": 1.2575, + "step": 5749 + }, + { + "epoch": 0.6, + "learning_rate": 8.160282619547068e-06, + "loss": 1.2627, + "step": 5750 + }, + { + "epoch": 0.6, + "learning_rate": 8.156684967629242e-06, + "loss": 1.2549, + "step": 5751 + }, + { + "epoch": 0.6, + "learning_rate": 8.153087562668265e-06, + "loss": 1.2595, + "step": 5752 + }, + { + "epoch": 0.6, + "learning_rate": 8.1494904051461e-06, + "loss": 1.2788, + "step": 5753 + }, + { + "epoch": 0.6, + "learning_rate": 8.145893495544676e-06, + "loss": 1.3028, + "step": 5754 + }, + { + "epoch": 0.6, + "learning_rate": 8.142296834345883e-06, + "loss": 1.3019, + "step": 5755 + }, + { + "epoch": 0.6, + "learning_rate": 8.138700422031583e-06, + "loss": 1.2998, + "step": 5756 + }, + { + "epoch": 0.6, + "learning_rate": 8.135104259083598e-06, + "loss": 1.3298, + "step": 5757 + }, + { + "epoch": 0.6, + "learning_rate": 8.13150834598373e-06, + "loss": 1.2681, + "step": 5758 + }, + { + "epoch": 0.6, + "learning_rate": 8.127912683213733e-06, + "loss": 1.2987, + "step": 5759 + }, + { + "epoch": 0.6, + "learning_rate": 8.124317271255331e-06, + "loss": 1.3181, + "step": 5760 + }, + { + "epoch": 0.6, + "learning_rate": 8.120722110590224e-06, + "loss": 1.423, + "step": 5761 + }, + { + "epoch": 0.6, + "learning_rate": 8.117127201700067e-06, + "loss": 1.5029, + "step": 5762 + }, + { + "epoch": 0.6, + "learning_rate": 8.113532545066488e-06, + "loss": 1.3016, + "step": 5763 + }, + { + "epoch": 0.6, + "learning_rate": 8.109938141171074e-06, + "loss": 1.3906, + "step": 5764 + }, + { + "epoch": 0.6, + "learning_rate": 8.106343990495387e-06, + "loss": 1.3363, + "step": 5765 + }, + { + "epoch": 0.6, + "learning_rate": 8.10275009352095e-06, + "loss": 1.314, + "step": 5766 + }, + { + "epoch": 0.6, + "learning_rate": 8.09915645072925e-06, + "loss": 1.3484, + "step": 5767 + }, + { + "epoch": 0.6, + "learning_rate": 8.095563062601745e-06, + "loss": 1.3757, + "step": 5768 + }, + { + "epoch": 0.6, + "learning_rate": 8.091969929619859e-06, + "loss": 1.3068, + "step": 5769 + }, + { + "epoch": 0.61, + "learning_rate": 8.088377052264976e-06, + "loss": 1.3486, + "step": 5770 + }, + { + "epoch": 0.61, + "learning_rate": 8.08478443101845e-06, + "loss": 1.244, + "step": 5771 + }, + { + "epoch": 0.61, + "eval_loss": 1.4178493022918701, + "eval_runtime": 77.6086, + "eval_samples_per_second": 1.662, + "eval_steps_per_second": 0.116, + "step": 5771 + }, + { + "epoch": 0.61, + "learning_rate": 8.0811920663616e-06, + "loss": 1.3325, + "step": 5772 + }, + { + "epoch": 0.61, + "learning_rate": 8.077599958775713e-06, + "loss": 1.336, + "step": 5773 + }, + { + "epoch": 0.61, + "learning_rate": 8.074008108742037e-06, + "loss": 1.3167, + "step": 5774 + }, + { + "epoch": 0.61, + "learning_rate": 8.070416516741786e-06, + "loss": 1.3166, + "step": 5775 + }, + { + "epoch": 0.61, + "learning_rate": 8.066825183256141e-06, + "loss": 1.3377, + "step": 5776 + }, + { + "epoch": 0.61, + "learning_rate": 8.063234108766253e-06, + "loss": 1.3704, + "step": 5777 + }, + { + "epoch": 0.61, + "learning_rate": 8.059643293753233e-06, + "loss": 1.3596, + "step": 5778 + }, + { + "epoch": 0.61, + "learning_rate": 8.056052738698153e-06, + "loss": 1.4477, + "step": 5779 + }, + { + "epoch": 0.61, + "learning_rate": 8.052462444082055e-06, + "loss": 1.338, + "step": 5780 + }, + { + "epoch": 0.61, + "learning_rate": 8.048872410385952e-06, + "loss": 1.2714, + "step": 5781 + }, + { + "epoch": 0.61, + "learning_rate": 8.045282638090815e-06, + "loss": 0.9642, + "step": 5782 + }, + { + "epoch": 0.61, + "learning_rate": 8.041693127677576e-06, + "loss": 0.8702, + "step": 5783 + }, + { + "epoch": 0.61, + "learning_rate": 8.038103879627144e-06, + "loss": 0.8986, + "step": 5784 + }, + { + "epoch": 0.61, + "learning_rate": 8.034514894420382e-06, + "loss": 0.804, + "step": 5785 + }, + { + "epoch": 0.61, + "learning_rate": 8.030926172538122e-06, + "loss": 0.7958, + "step": 5786 + }, + { + "epoch": 0.61, + "learning_rate": 8.02733771446116e-06, + "loss": 0.7608, + "step": 5787 + }, + { + "epoch": 0.61, + "learning_rate": 8.023749520670261e-06, + "loss": 0.7792, + "step": 5788 + }, + { + "epoch": 0.61, + "learning_rate": 8.020161591646147e-06, + "loss": 0.7293, + "step": 5789 + }, + { + "epoch": 0.61, + "learning_rate": 8.016573927869511e-06, + "loss": 1.1287, + "step": 5790 + }, + { + "epoch": 0.61, + "learning_rate": 8.012986529821004e-06, + "loss": 1.3344, + "step": 5791 + }, + { + "epoch": 0.61, + "learning_rate": 8.009399397981248e-06, + "loss": 1.4415, + "step": 5792 + }, + { + "epoch": 0.61, + "learning_rate": 8.005812532830826e-06, + "loss": 1.4265, + "step": 5793 + }, + { + "epoch": 0.61, + "learning_rate": 8.002225934850287e-06, + "loss": 1.3429, + "step": 5794 + }, + { + "epoch": 0.61, + "learning_rate": 7.998639604520137e-06, + "loss": 1.3653, + "step": 5795 + }, + { + "epoch": 0.61, + "learning_rate": 7.995053542320861e-06, + "loss": 1.486, + "step": 5796 + }, + { + "epoch": 0.61, + "learning_rate": 7.991467748732894e-06, + "loss": 1.3389, + "step": 5797 + }, + { + "epoch": 0.61, + "learning_rate": 7.98788222423664e-06, + "loss": 1.3206, + "step": 5798 + }, + { + "epoch": 0.61, + "learning_rate": 7.984296969312468e-06, + "loss": 1.3121, + "step": 5799 + }, + { + "epoch": 0.61, + "learning_rate": 7.980711984440712e-06, + "loss": 1.3512, + "step": 5800 + }, + { + "epoch": 0.61, + "learning_rate": 7.977127270101665e-06, + "loss": 1.3291, + "step": 5801 + }, + { + "epoch": 0.61, + "learning_rate": 7.97354282677559e-06, + "loss": 1.3948, + "step": 5802 + }, + { + "epoch": 0.61, + "learning_rate": 7.969958654942704e-06, + "loss": 1.3076, + "step": 5803 + }, + { + "epoch": 0.61, + "learning_rate": 7.966374755083202e-06, + "loss": 1.3838, + "step": 5804 + }, + { + "epoch": 0.61, + "learning_rate": 7.962791127677228e-06, + "loss": 1.4205, + "step": 5805 + }, + { + "epoch": 0.61, + "learning_rate": 7.959207773204899e-06, + "loss": 1.3635, + "step": 5806 + }, + { + "epoch": 0.61, + "learning_rate": 7.955624692146293e-06, + "loss": 1.3299, + "step": 5807 + }, + { + "epoch": 0.61, + "learning_rate": 7.95204188498145e-06, + "loss": 1.4435, + "step": 5808 + }, + { + "epoch": 0.61, + "learning_rate": 7.948459352190372e-06, + "loss": 1.4335, + "step": 5809 + }, + { + "epoch": 0.61, + "learning_rate": 7.944877094253027e-06, + "loss": 1.3391, + "step": 5810 + }, + { + "epoch": 0.61, + "learning_rate": 7.94129511164935e-06, + "loss": 1.2852, + "step": 5811 + }, + { + "epoch": 0.61, + "learning_rate": 7.93771340485923e-06, + "loss": 1.3174, + "step": 5812 + }, + { + "epoch": 0.61, + "learning_rate": 7.934131974362527e-06, + "loss": 1.3415, + "step": 5813 + }, + { + "epoch": 0.61, + "learning_rate": 7.930550820639055e-06, + "loss": 1.2764, + "step": 5814 + }, + { + "epoch": 0.61, + "learning_rate": 7.926969944168603e-06, + "loss": 1.2978, + "step": 5815 + }, + { + "epoch": 0.61, + "learning_rate": 7.923389345430911e-06, + "loss": 1.3046, + "step": 5816 + }, + { + "epoch": 0.61, + "learning_rate": 7.919809024905694e-06, + "loss": 1.3484, + "step": 5817 + }, + { + "epoch": 0.61, + "learning_rate": 7.916228983072614e-06, + "loss": 1.3207, + "step": 5818 + }, + { + "epoch": 0.61, + "learning_rate": 7.912649220411312e-06, + "loss": 1.4289, + "step": 5819 + }, + { + "epoch": 0.61, + "learning_rate": 7.909069737401382e-06, + "loss": 1.4359, + "step": 5820 + }, + { + "epoch": 0.61, + "learning_rate": 7.905490534522384e-06, + "loss": 1.3316, + "step": 5821 + }, + { + "epoch": 0.61, + "learning_rate": 7.901911612253834e-06, + "loss": 1.3112, + "step": 5822 + }, + { + "epoch": 0.61, + "learning_rate": 7.898332971075221e-06, + "loss": 1.3318, + "step": 5823 + }, + { + "epoch": 0.61, + "learning_rate": 7.894754611465992e-06, + "loss": 1.4373, + "step": 5824 + }, + { + "epoch": 0.61, + "learning_rate": 7.891176533905549e-06, + "loss": 1.2938, + "step": 5825 + }, + { + "epoch": 0.61, + "learning_rate": 7.887598738873266e-06, + "loss": 1.3471, + "step": 5826 + }, + { + "epoch": 0.61, + "learning_rate": 7.884021226848478e-06, + "loss": 1.2999, + "step": 5827 + }, + { + "epoch": 0.61, + "learning_rate": 7.880443998310475e-06, + "loss": 1.35, + "step": 5828 + }, + { + "epoch": 0.61, + "learning_rate": 7.876867053738517e-06, + "loss": 1.3307, + "step": 5829 + }, + { + "epoch": 0.61, + "learning_rate": 7.87329039361182e-06, + "loss": 1.393, + "step": 5830 + }, + { + "epoch": 0.61, + "learning_rate": 7.869714018409568e-06, + "loss": 1.2933, + "step": 5831 + }, + { + "epoch": 0.61, + "learning_rate": 7.866137928610903e-06, + "loss": 1.319, + "step": 5832 + }, + { + "epoch": 0.61, + "learning_rate": 7.862562124694925e-06, + "loss": 1.3088, + "step": 5833 + }, + { + "epoch": 0.61, + "learning_rate": 7.858986607140705e-06, + "loss": 1.2941, + "step": 5834 + }, + { + "epoch": 0.61, + "learning_rate": 7.855411376427267e-06, + "loss": 1.3214, + "step": 5835 + }, + { + "epoch": 0.61, + "learning_rate": 7.851836433033602e-06, + "loss": 1.2991, + "step": 5836 + }, + { + "epoch": 0.61, + "learning_rate": 7.848261777438656e-06, + "loss": 1.3117, + "step": 5837 + }, + { + "epoch": 0.61, + "learning_rate": 7.844687410121348e-06, + "loss": 1.2905, + "step": 5838 + }, + { + "epoch": 0.61, + "learning_rate": 7.841113331560548e-06, + "loss": 1.3688, + "step": 5839 + }, + { + "epoch": 0.61, + "learning_rate": 7.837539542235091e-06, + "loss": 1.3987, + "step": 5840 + }, + { + "epoch": 0.61, + "learning_rate": 7.83396604262377e-06, + "loss": 1.2693, + "step": 5841 + }, + { + "epoch": 0.61, + "learning_rate": 7.830392833205348e-06, + "loss": 1.3205, + "step": 5842 + }, + { + "epoch": 0.61, + "learning_rate": 7.826819914458538e-06, + "loss": 1.3325, + "step": 5843 + }, + { + "epoch": 0.61, + "learning_rate": 7.823247286862024e-06, + "loss": 1.3451, + "step": 5844 + }, + { + "epoch": 0.61, + "learning_rate": 7.81967495089444e-06, + "loss": 1.3484, + "step": 5845 + }, + { + "epoch": 0.61, + "learning_rate": 7.816102907034395e-06, + "loss": 1.4949, + "step": 5846 + }, + { + "epoch": 0.61, + "learning_rate": 7.812531155760445e-06, + "loss": 1.4293, + "step": 5847 + }, + { + "epoch": 0.61, + "learning_rate": 7.808959697551113e-06, + "loss": 1.4314, + "step": 5848 + }, + { + "epoch": 0.61, + "learning_rate": 7.805388532884887e-06, + "loss": 1.3188, + "step": 5849 + }, + { + "epoch": 0.61, + "learning_rate": 7.80181766224021e-06, + "loss": 1.4396, + "step": 5850 + }, + { + "epoch": 0.61, + "learning_rate": 7.798247086095484e-06, + "loss": 1.3448, + "step": 5851 + }, + { + "epoch": 0.61, + "learning_rate": 7.794676804929075e-06, + "loss": 1.3591, + "step": 5852 + }, + { + "epoch": 0.61, + "learning_rate": 7.791106819219311e-06, + "loss": 1.3108, + "step": 5853 + }, + { + "epoch": 0.61, + "learning_rate": 7.78753712944448e-06, + "loss": 1.3773, + "step": 5854 + }, + { + "epoch": 0.61, + "learning_rate": 7.783967736082824e-06, + "loss": 1.3313, + "step": 5855 + }, + { + "epoch": 0.61, + "learning_rate": 7.780398639612551e-06, + "loss": 1.3635, + "step": 5856 + }, + { + "epoch": 0.61, + "learning_rate": 7.776829840511833e-06, + "loss": 1.3225, + "step": 5857 + }, + { + "epoch": 0.61, + "learning_rate": 7.773261339258792e-06, + "loss": 1.3142, + "step": 5858 + }, + { + "epoch": 0.61, + "learning_rate": 7.769693136331519e-06, + "loss": 1.3337, + "step": 5859 + }, + { + "epoch": 0.61, + "learning_rate": 7.766125232208057e-06, + "loss": 1.5289, + "step": 5860 + }, + { + "epoch": 0.61, + "learning_rate": 7.762557627366418e-06, + "loss": 1.573, + "step": 5861 + }, + { + "epoch": 0.61, + "learning_rate": 7.758990322284568e-06, + "loss": 1.322, + "step": 5862 + }, + { + "epoch": 0.61, + "learning_rate": 7.755423317440432e-06, + "loss": 1.3281, + "step": 5863 + }, + { + "epoch": 0.61, + "learning_rate": 7.751856613311899e-06, + "loss": 1.3405, + "step": 5864 + }, + { + "epoch": 0.62, + "learning_rate": 7.748290210376817e-06, + "loss": 1.3083, + "step": 5865 + }, + { + "epoch": 0.62, + "learning_rate": 7.744724109112991e-06, + "loss": 1.3587, + "step": 5866 + }, + { + "epoch": 0.62, + "learning_rate": 7.741158309998188e-06, + "loss": 1.3204, + "step": 5867 + }, + { + "epoch": 0.62, + "learning_rate": 7.73759281351013e-06, + "loss": 1.343, + "step": 5868 + }, + { + "epoch": 0.62, + "learning_rate": 7.734027620126507e-06, + "loss": 1.2874, + "step": 5869 + }, + { + "epoch": 0.62, + "learning_rate": 7.73046273032496e-06, + "loss": 1.3306, + "step": 5870 + }, + { + "epoch": 0.62, + "learning_rate": 7.72689814458309e-06, + "loss": 1.3958, + "step": 5871 + }, + { + "epoch": 0.62, + "learning_rate": 7.723333863378465e-06, + "loss": 1.3135, + "step": 5872 + }, + { + "epoch": 0.62, + "learning_rate": 7.719769887188608e-06, + "loss": 1.3241, + "step": 5873 + }, + { + "epoch": 0.62, + "learning_rate": 7.716206216490995e-06, + "loss": 1.3487, + "step": 5874 + }, + { + "epoch": 0.62, + "learning_rate": 7.712642851763067e-06, + "loss": 1.0263, + "step": 5875 + }, + { + "epoch": 0.62, + "learning_rate": 7.709079793482228e-06, + "loss": 1.4238, + "step": 5876 + }, + { + "epoch": 0.62, + "learning_rate": 7.705517042125833e-06, + "loss": 1.3284, + "step": 5877 + }, + { + "epoch": 0.62, + "learning_rate": 7.701954598171199e-06, + "loss": 1.2965, + "step": 5878 + }, + { + "epoch": 0.62, + "learning_rate": 7.698392462095601e-06, + "loss": 1.3578, + "step": 5879 + }, + { + "epoch": 0.62, + "learning_rate": 7.694830634376278e-06, + "loss": 1.3711, + "step": 5880 + }, + { + "epoch": 0.62, + "learning_rate": 7.69126911549042e-06, + "loss": 1.3274, + "step": 5881 + }, + { + "epoch": 0.62, + "learning_rate": 7.687707905915181e-06, + "loss": 1.4208, + "step": 5882 + }, + { + "epoch": 0.62, + "learning_rate": 7.684147006127665e-06, + "loss": 1.3478, + "step": 5883 + }, + { + "epoch": 0.62, + "learning_rate": 7.68058641660495e-06, + "loss": 1.2997, + "step": 5884 + }, + { + "epoch": 0.62, + "learning_rate": 7.67702613782406e-06, + "loss": 1.2981, + "step": 5885 + }, + { + "epoch": 0.62, + "learning_rate": 7.67346617026198e-06, + "loss": 1.3834, + "step": 5886 + }, + { + "epoch": 0.62, + "learning_rate": 7.669906514395654e-06, + "loss": 1.3585, + "step": 5887 + }, + { + "epoch": 0.62, + "learning_rate": 7.666347170701986e-06, + "loss": 1.3282, + "step": 5888 + }, + { + "epoch": 0.62, + "learning_rate": 7.662788139657838e-06, + "loss": 1.3397, + "step": 5889 + }, + { + "epoch": 0.62, + "learning_rate": 7.659229421740024e-06, + "loss": 1.3367, + "step": 5890 + }, + { + "epoch": 0.62, + "learning_rate": 7.655671017425322e-06, + "loss": 1.3497, + "step": 5891 + }, + { + "epoch": 0.62, + "learning_rate": 7.65211292719047e-06, + "loss": 1.3661, + "step": 5892 + }, + { + "epoch": 0.62, + "learning_rate": 7.64855515151216e-06, + "loss": 1.2793, + "step": 5893 + }, + { + "epoch": 0.62, + "learning_rate": 7.644997690867037e-06, + "loss": 1.3288, + "step": 5894 + }, + { + "epoch": 0.62, + "learning_rate": 7.641440545731717e-06, + "loss": 1.3877, + "step": 5895 + }, + { + "epoch": 0.62, + "learning_rate": 7.637883716582764e-06, + "loss": 1.4467, + "step": 5896 + }, + { + "epoch": 0.62, + "learning_rate": 7.634327203896698e-06, + "loss": 1.304, + "step": 5897 + }, + { + "epoch": 0.62, + "learning_rate": 7.630771008150002e-06, + "loss": 1.374, + "step": 5898 + }, + { + "epoch": 0.62, + "learning_rate": 7.627215129819118e-06, + "loss": 1.3893, + "step": 5899 + }, + { + "epoch": 0.62, + "learning_rate": 7.623659569380439e-06, + "loss": 1.325, + "step": 5900 + }, + { + "epoch": 0.62, + "learning_rate": 7.620104327310319e-06, + "loss": 1.2495, + "step": 5901 + }, + { + "epoch": 0.62, + "learning_rate": 7.616549404085068e-06, + "loss": 1.4034, + "step": 5902 + }, + { + "epoch": 0.62, + "learning_rate": 7.61299480018096e-06, + "loss": 1.2758, + "step": 5903 + }, + { + "epoch": 0.62, + "learning_rate": 7.609440516074215e-06, + "loss": 1.4203, + "step": 5904 + }, + { + "epoch": 0.62, + "learning_rate": 7.605886552241017e-06, + "loss": 1.3162, + "step": 5905 + }, + { + "epoch": 0.62, + "learning_rate": 7.602332909157505e-06, + "loss": 1.3368, + "step": 5906 + }, + { + "epoch": 0.62, + "learning_rate": 7.598779587299778e-06, + "loss": 1.314, + "step": 5907 + }, + { + "epoch": 0.62, + "learning_rate": 7.59522658714389e-06, + "loss": 1.3332, + "step": 5908 + }, + { + "epoch": 0.62, + "learning_rate": 7.5916739091658505e-06, + "loss": 1.3513, + "step": 5909 + }, + { + "epoch": 0.62, + "learning_rate": 7.5881215538416255e-06, + "loss": 1.3767, + "step": 5910 + }, + { + "epoch": 0.62, + "learning_rate": 7.5845695216471426e-06, + "loss": 1.3651, + "step": 5911 + }, + { + "epoch": 0.62, + "learning_rate": 7.581017813058283e-06, + "loss": 1.2676, + "step": 5912 + }, + { + "epoch": 0.62, + "learning_rate": 7.57746642855088e-06, + "loss": 1.3509, + "step": 5913 + }, + { + "epoch": 0.62, + "learning_rate": 7.5739153686007305e-06, + "loss": 1.2854, + "step": 5914 + }, + { + "epoch": 0.62, + "learning_rate": 7.570364633683586e-06, + "loss": 1.4041, + "step": 5915 + }, + { + "epoch": 0.62, + "learning_rate": 7.5668142242751545e-06, + "loss": 1.3218, + "step": 5916 + }, + { + "epoch": 0.62, + "learning_rate": 7.563264140851095e-06, + "loss": 1.398, + "step": 5917 + }, + { + "epoch": 0.62, + "learning_rate": 7.559714383887033e-06, + "loss": 1.3495, + "step": 5918 + }, + { + "epoch": 0.62, + "learning_rate": 7.556164953858543e-06, + "loss": 1.365, + "step": 5919 + }, + { + "epoch": 0.62, + "learning_rate": 7.552615851241157e-06, + "loss": 1.4611, + "step": 5920 + }, + { + "epoch": 0.62, + "learning_rate": 7.549067076510361e-06, + "loss": 1.4031, + "step": 5921 + }, + { + "epoch": 0.62, + "learning_rate": 7.545518630141605e-06, + "loss": 1.2745, + "step": 5922 + }, + { + "epoch": 0.62, + "learning_rate": 7.541970512610286e-06, + "loss": 1.3435, + "step": 5923 + }, + { + "epoch": 0.62, + "learning_rate": 7.538422724391761e-06, + "loss": 1.3433, + "step": 5924 + }, + { + "epoch": 0.62, + "learning_rate": 7.534875265961341e-06, + "loss": 1.3605, + "step": 5925 + }, + { + "epoch": 0.62, + "learning_rate": 7.5313281377942985e-06, + "loss": 1.3896, + "step": 5926 + }, + { + "epoch": 0.62, + "learning_rate": 7.527781340365854e-06, + "loss": 1.3922, + "step": 5927 + }, + { + "epoch": 0.62, + "learning_rate": 7.524234874151189e-06, + "loss": 1.3305, + "step": 5928 + }, + { + "epoch": 0.62, + "learning_rate": 7.520688739625436e-06, + "loss": 1.3117, + "step": 5929 + }, + { + "epoch": 0.62, + "learning_rate": 7.51714293726369e-06, + "loss": 1.3581, + "step": 5930 + }, + { + "epoch": 0.62, + "learning_rate": 7.5135974675409955e-06, + "loss": 1.3973, + "step": 5931 + }, + { + "epoch": 0.62, + "learning_rate": 7.510052330932354e-06, + "loss": 1.3499, + "step": 5932 + }, + { + "epoch": 0.62, + "learning_rate": 7.506507527912721e-06, + "loss": 1.3068, + "step": 5933 + }, + { + "epoch": 0.62, + "learning_rate": 7.502963058957014e-06, + "loss": 1.3689, + "step": 5934 + }, + { + "epoch": 0.62, + "learning_rate": 7.499418924540096e-06, + "loss": 1.3356, + "step": 5935 + }, + { + "epoch": 0.62, + "learning_rate": 7.495875125136793e-06, + "loss": 1.2593, + "step": 5936 + }, + { + "epoch": 0.62, + "learning_rate": 7.492331661221881e-06, + "loss": 1.272, + "step": 5937 + }, + { + "epoch": 0.62, + "learning_rate": 7.488788533270093e-06, + "loss": 1.3552, + "step": 5938 + }, + { + "epoch": 0.62, + "learning_rate": 7.485245741756121e-06, + "loss": 1.3425, + "step": 5939 + }, + { + "epoch": 0.62, + "learning_rate": 7.481703287154602e-06, + "loss": 1.3694, + "step": 5940 + }, + { + "epoch": 0.62, + "learning_rate": 7.478161169940139e-06, + "loss": 1.3281, + "step": 5941 + }, + { + "epoch": 0.62, + "learning_rate": 7.4746193905872825e-06, + "loss": 1.3109, + "step": 5942 + }, + { + "epoch": 0.62, + "learning_rate": 7.47107794957054e-06, + "loss": 1.5121, + "step": 5943 + }, + { + "epoch": 0.62, + "learning_rate": 7.467536847364372e-06, + "loss": 1.4472, + "step": 5944 + }, + { + "epoch": 0.62, + "learning_rate": 7.463996084443198e-06, + "loss": 1.4615, + "step": 5945 + }, + { + "epoch": 0.62, + "learning_rate": 7.460455661281389e-06, + "loss": 1.3764, + "step": 5946 + }, + { + "epoch": 0.62, + "learning_rate": 7.45691557835327e-06, + "loss": 1.3091, + "step": 5947 + }, + { + "epoch": 0.62, + "learning_rate": 7.4533758361331185e-06, + "loss": 1.1841, + "step": 5948 + }, + { + "epoch": 0.62, + "learning_rate": 7.449836435095175e-06, + "loss": 1.3345, + "step": 5949 + }, + { + "epoch": 0.62, + "learning_rate": 7.446297375713622e-06, + "loss": 1.3573, + "step": 5950 + }, + { + "epoch": 0.62, + "learning_rate": 7.442758658462608e-06, + "loss": 1.3161, + "step": 5951 + }, + { + "epoch": 0.62, + "learning_rate": 7.4392202838162245e-06, + "loss": 1.3089, + "step": 5952 + }, + { + "epoch": 0.62, + "learning_rate": 7.435682252248528e-06, + "loss": 1.3069, + "step": 5953 + }, + { + "epoch": 0.62, + "learning_rate": 7.4321445642335234e-06, + "loss": 1.2969, + "step": 5954 + }, + { + "epoch": 0.62, + "learning_rate": 7.428607220245165e-06, + "loss": 1.4706, + "step": 5955 + }, + { + "epoch": 0.62, + "learning_rate": 7.42507022075737e-06, + "loss": 1.3028, + "step": 5956 + }, + { + "epoch": 0.62, + "learning_rate": 7.421533566244006e-06, + "loss": 1.2786, + "step": 5957 + }, + { + "epoch": 0.62, + "learning_rate": 7.417997257178893e-06, + "loss": 1.3534, + "step": 5958 + }, + { + "epoch": 0.62, + "learning_rate": 7.414461294035804e-06, + "loss": 1.2829, + "step": 5959 + }, + { + "epoch": 0.62, + "learning_rate": 7.410925677288467e-06, + "loss": 1.3626, + "step": 5960 + }, + { + "epoch": 0.63, + "learning_rate": 7.407390407410566e-06, + "loss": 1.4531, + "step": 5961 + }, + { + "epoch": 0.63, + "learning_rate": 7.4038554848757375e-06, + "loss": 1.3549, + "step": 5962 + }, + { + "epoch": 0.63, + "learning_rate": 7.400320910157563e-06, + "loss": 1.3407, + "step": 5963 + }, + { + "epoch": 0.63, + "learning_rate": 7.396786683729595e-06, + "loss": 1.2736, + "step": 5964 + }, + { + "epoch": 0.63, + "learning_rate": 7.393252806065323e-06, + "loss": 1.3377, + "step": 5965 + }, + { + "epoch": 0.63, + "learning_rate": 7.389719277638196e-06, + "loss": 1.3479, + "step": 5966 + }, + { + "epoch": 0.63, + "learning_rate": 7.3861860989216175e-06, + "loss": 1.3605, + "step": 5967 + }, + { + "epoch": 0.63, + "learning_rate": 7.382653270388942e-06, + "loss": 1.3175, + "step": 5968 + }, + { + "epoch": 0.63, + "learning_rate": 7.379120792513477e-06, + "loss": 1.3072, + "step": 5969 + }, + { + "epoch": 0.63, + "learning_rate": 7.375588665768485e-06, + "loss": 1.3224, + "step": 5970 + }, + { + "epoch": 0.63, + "eval_loss": 1.4110088348388672, + "eval_runtime": 77.5326, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 5970 + }, + { + "epoch": 0.63, + "learning_rate": 7.37205689062718e-06, + "loss": 1.3491, + "step": 5971 + }, + { + "epoch": 0.63, + "learning_rate": 7.368525467562728e-06, + "loss": 1.3289, + "step": 5972 + }, + { + "epoch": 0.63, + "learning_rate": 7.364994397048251e-06, + "loss": 1.3362, + "step": 5973 + }, + { + "epoch": 0.63, + "learning_rate": 7.36146367955682e-06, + "loss": 1.3754, + "step": 5974 + }, + { + "epoch": 0.63, + "learning_rate": 7.3579333155614585e-06, + "loss": 1.3159, + "step": 5975 + }, + { + "epoch": 0.63, + "learning_rate": 7.354403305535149e-06, + "loss": 1.4366, + "step": 5976 + }, + { + "epoch": 0.63, + "learning_rate": 7.350873649950822e-06, + "loss": 1.3243, + "step": 5977 + }, + { + "epoch": 0.63, + "learning_rate": 7.347344349281358e-06, + "loss": 1.2911, + "step": 5978 + }, + { + "epoch": 0.63, + "learning_rate": 7.34381540399959e-06, + "loss": 1.338, + "step": 5979 + }, + { + "epoch": 0.63, + "learning_rate": 7.340286814578312e-06, + "loss": 1.3241, + "step": 5980 + }, + { + "epoch": 0.63, + "learning_rate": 7.336758581490263e-06, + "loss": 1.3427, + "step": 5981 + }, + { + "epoch": 0.63, + "learning_rate": 7.333230705208134e-06, + "loss": 1.3328, + "step": 5982 + }, + { + "epoch": 0.63, + "learning_rate": 7.3297031862045676e-06, + "loss": 1.2857, + "step": 5983 + }, + { + "epoch": 0.63, + "learning_rate": 7.3261760249521655e-06, + "loss": 1.9065, + "step": 5984 + }, + { + "epoch": 0.63, + "learning_rate": 7.322649221923473e-06, + "loss": 1.3797, + "step": 5985 + }, + { + "epoch": 0.63, + "learning_rate": 7.3191227775909925e-06, + "loss": 1.2343, + "step": 5986 + }, + { + "epoch": 0.63, + "learning_rate": 7.315596692427178e-06, + "loss": 1.3479, + "step": 5987 + }, + { + "epoch": 0.63, + "learning_rate": 7.312070966904432e-06, + "loss": 1.3226, + "step": 5988 + }, + { + "epoch": 0.63, + "learning_rate": 7.308545601495114e-06, + "loss": 1.3329, + "step": 5989 + }, + { + "epoch": 0.63, + "learning_rate": 7.305020596671528e-06, + "loss": 1.3285, + "step": 5990 + }, + { + "epoch": 0.63, + "learning_rate": 7.301495952905939e-06, + "loss": 1.3635, + "step": 5991 + }, + { + "epoch": 0.63, + "learning_rate": 7.297971670670556e-06, + "loss": 1.3343, + "step": 5992 + }, + { + "epoch": 0.63, + "learning_rate": 7.294447750437543e-06, + "loss": 1.3943, + "step": 5993 + }, + { + "epoch": 0.63, + "learning_rate": 7.290924192679014e-06, + "loss": 1.4601, + "step": 5994 + }, + { + "epoch": 0.63, + "learning_rate": 7.287400997867036e-06, + "loss": 1.3813, + "step": 5995 + }, + { + "epoch": 0.63, + "learning_rate": 7.2838781664736266e-06, + "loss": 1.3505, + "step": 5996 + }, + { + "epoch": 0.63, + "learning_rate": 7.2803556989707555e-06, + "loss": 1.3062, + "step": 5997 + }, + { + "epoch": 0.63, + "learning_rate": 7.276833595830338e-06, + "loss": 1.4504, + "step": 5998 + }, + { + "epoch": 0.63, + "learning_rate": 7.273311857524252e-06, + "loss": 1.4935, + "step": 5999 + }, + { + "epoch": 0.63, + "learning_rate": 7.269790484524317e-06, + "loss": 1.296, + "step": 6000 + }, + { + "epoch": 0.63, + "learning_rate": 7.266269477302308e-06, + "loss": 1.3469, + "step": 6001 + }, + { + "epoch": 0.63, + "learning_rate": 7.262748836329944e-06, + "loss": 1.3586, + "step": 6002 + }, + { + "epoch": 0.63, + "learning_rate": 7.259228562078908e-06, + "loss": 1.3643, + "step": 6003 + }, + { + "epoch": 0.63, + "learning_rate": 7.255708655020821e-06, + "loss": 1.3096, + "step": 6004 + }, + { + "epoch": 0.63, + "learning_rate": 7.252189115627264e-06, + "loss": 1.3163, + "step": 6005 + }, + { + "epoch": 0.63, + "learning_rate": 7.2486699443697595e-06, + "loss": 1.3526, + "step": 6006 + }, + { + "epoch": 0.63, + "learning_rate": 7.245151141719793e-06, + "loss": 1.401, + "step": 6007 + }, + { + "epoch": 0.63, + "learning_rate": 7.241632708148788e-06, + "loss": 1.2651, + "step": 6008 + }, + { + "epoch": 0.63, + "learning_rate": 7.238114644128124e-06, + "loss": 1.348, + "step": 6009 + }, + { + "epoch": 0.63, + "learning_rate": 7.234596950129137e-06, + "loss": 1.6934, + "step": 6010 + }, + { + "epoch": 0.63, + "learning_rate": 7.231079626623103e-06, + "loss": 1.3382, + "step": 6011 + }, + { + "epoch": 0.63, + "learning_rate": 7.227562674081254e-06, + "loss": 1.2925, + "step": 6012 + }, + { + "epoch": 0.63, + "learning_rate": 7.22404609297477e-06, + "loss": 1.3365, + "step": 6013 + }, + { + "epoch": 0.63, + "learning_rate": 7.220529883774785e-06, + "loss": 1.3169, + "step": 6014 + }, + { + "epoch": 0.63, + "learning_rate": 7.217014046952379e-06, + "loss": 1.319, + "step": 6015 + }, + { + "epoch": 0.63, + "learning_rate": 7.2134985829785846e-06, + "loss": 1.4049, + "step": 6016 + }, + { + "epoch": 0.63, + "learning_rate": 7.209983492324382e-06, + "loss": 1.2947, + "step": 6017 + }, + { + "epoch": 0.63, + "learning_rate": 7.206468775460704e-06, + "loss": 1.2854, + "step": 6018 + }, + { + "epoch": 0.63, + "learning_rate": 7.202954432858436e-06, + "loss": 1.3381, + "step": 6019 + }, + { + "epoch": 0.63, + "learning_rate": 7.199440464988403e-06, + "loss": 1.3912, + "step": 6020 + }, + { + "epoch": 0.63, + "learning_rate": 7.195926872321391e-06, + "loss": 1.384, + "step": 6021 + }, + { + "epoch": 0.63, + "learning_rate": 7.192413655328129e-06, + "loss": 1.2909, + "step": 6022 + }, + { + "epoch": 0.63, + "learning_rate": 7.188900814479299e-06, + "loss": 1.2951, + "step": 6023 + }, + { + "epoch": 0.63, + "learning_rate": 7.185388350245532e-06, + "loss": 1.2655, + "step": 6024 + }, + { + "epoch": 0.63, + "learning_rate": 7.1818762630974035e-06, + "loss": 1.3288, + "step": 6025 + }, + { + "epoch": 0.63, + "learning_rate": 7.17836455350545e-06, + "loss": 1.2873, + "step": 6026 + }, + { + "epoch": 0.63, + "learning_rate": 7.174853221940146e-06, + "loss": 1.3027, + "step": 6027 + }, + { + "epoch": 0.63, + "learning_rate": 7.17134226887192e-06, + "loss": 1.3273, + "step": 6028 + }, + { + "epoch": 0.63, + "learning_rate": 7.167831694771149e-06, + "loss": 1.3096, + "step": 6029 + }, + { + "epoch": 0.63, + "learning_rate": 7.1643215001081625e-06, + "loss": 1.2904, + "step": 6030 + }, + { + "epoch": 0.63, + "learning_rate": 7.160811685353234e-06, + "loss": 1.2977, + "step": 6031 + }, + { + "epoch": 0.63, + "learning_rate": 7.157302250976588e-06, + "loss": 1.3281, + "step": 6032 + }, + { + "epoch": 0.63, + "learning_rate": 7.1537931974483996e-06, + "loss": 1.3831, + "step": 6033 + }, + { + "epoch": 0.63, + "learning_rate": 7.150284525238794e-06, + "loss": 1.3173, + "step": 6034 + }, + { + "epoch": 0.63, + "learning_rate": 7.146776234817841e-06, + "loss": 1.4148, + "step": 6035 + }, + { + "epoch": 0.63, + "learning_rate": 7.143268326655557e-06, + "loss": 1.3381, + "step": 6036 + }, + { + "epoch": 0.63, + "learning_rate": 7.13976080122192e-06, + "loss": 1.3221, + "step": 6037 + }, + { + "epoch": 0.63, + "learning_rate": 7.136253658986843e-06, + "loss": 1.4373, + "step": 6038 + }, + { + "epoch": 0.63, + "learning_rate": 7.132746900420195e-06, + "loss": 1.3758, + "step": 6039 + }, + { + "epoch": 0.63, + "learning_rate": 7.129240525991788e-06, + "loss": 1.3964, + "step": 6040 + }, + { + "epoch": 0.63, + "learning_rate": 7.125734536171391e-06, + "loss": 1.3136, + "step": 6041 + }, + { + "epoch": 0.63, + "learning_rate": 7.122228931428715e-06, + "loss": 1.2195, + "step": 6042 + }, + { + "epoch": 0.63, + "learning_rate": 7.11872371223342e-06, + "loss": 1.3842, + "step": 6043 + }, + { + "epoch": 0.63, + "learning_rate": 7.115218879055113e-06, + "loss": 1.3369, + "step": 6044 + }, + { + "epoch": 0.63, + "learning_rate": 7.111714432363356e-06, + "loss": 1.2704, + "step": 6045 + }, + { + "epoch": 0.63, + "learning_rate": 7.108210372627653e-06, + "loss": 1.307, + "step": 6046 + }, + { + "epoch": 0.63, + "learning_rate": 7.104706700317459e-06, + "loss": 1.3024, + "step": 6047 + }, + { + "epoch": 0.63, + "learning_rate": 7.1012034159021715e-06, + "loss": 1.4157, + "step": 6048 + }, + { + "epoch": 0.63, + "learning_rate": 7.0977005198511475e-06, + "loss": 1.2314, + "step": 6049 + }, + { + "epoch": 0.63, + "learning_rate": 7.09419801263368e-06, + "loss": 1.4304, + "step": 6050 + }, + { + "epoch": 0.63, + "learning_rate": 7.090695894719019e-06, + "loss": 1.3085, + "step": 6051 + }, + { + "epoch": 0.63, + "learning_rate": 7.0871941665763525e-06, + "loss": 1.367, + "step": 6052 + }, + { + "epoch": 0.63, + "learning_rate": 7.083692828674827e-06, + "loss": 1.2913, + "step": 6053 + }, + { + "epoch": 0.63, + "learning_rate": 7.080191881483531e-06, + "loss": 1.3751, + "step": 6054 + }, + { + "epoch": 0.63, + "learning_rate": 7.0766913254714985e-06, + "loss": 1.3178, + "step": 6055 + }, + { + "epoch": 0.64, + "learning_rate": 7.07319116110772e-06, + "loss": 1.3182, + "step": 6056 + }, + { + "epoch": 0.64, + "learning_rate": 7.069691388861122e-06, + "loss": 1.373, + "step": 6057 + }, + { + "epoch": 0.64, + "learning_rate": 7.066192009200588e-06, + "loss": 1.3235, + "step": 6058 + }, + { + "epoch": 0.64, + "learning_rate": 7.0626930225949395e-06, + "loss": 1.3765, + "step": 6059 + }, + { + "epoch": 0.64, + "learning_rate": 7.0591944295129565e-06, + "loss": 1.4408, + "step": 6060 + }, + { + "epoch": 0.64, + "learning_rate": 7.055696230423359e-06, + "loss": 1.3271, + "step": 6061 + }, + { + "epoch": 0.64, + "learning_rate": 7.052198425794814e-06, + "loss": 1.2194, + "step": 6062 + }, + { + "epoch": 0.64, + "learning_rate": 7.048701016095938e-06, + "loss": 1.3707, + "step": 6063 + }, + { + "epoch": 0.64, + "learning_rate": 7.045204001795296e-06, + "loss": 1.3878, + "step": 6064 + }, + { + "epoch": 0.64, + "learning_rate": 7.041707383361396e-06, + "loss": 1.3674, + "step": 6065 + }, + { + "epoch": 0.64, + "learning_rate": 7.038211161262697e-06, + "loss": 1.4525, + "step": 6066 + }, + { + "epoch": 0.64, + "learning_rate": 7.034715335967599e-06, + "loss": 1.3801, + "step": 6067 + }, + { + "epoch": 0.64, + "learning_rate": 7.031219907944458e-06, + "loss": 1.4855, + "step": 6068 + }, + { + "epoch": 0.64, + "learning_rate": 7.027724877661568e-06, + "loss": 1.3659, + "step": 6069 + }, + { + "epoch": 0.64, + "learning_rate": 7.024230245587176e-06, + "loss": 1.3649, + "step": 6070 + }, + { + "epoch": 0.64, + "learning_rate": 7.020736012189467e-06, + "loss": 1.2629, + "step": 6071 + }, + { + "epoch": 0.64, + "learning_rate": 7.017242177936586e-06, + "loss": 1.2474, + "step": 6072 + }, + { + "epoch": 0.64, + "learning_rate": 7.013748743296614e-06, + "loss": 1.45, + "step": 6073 + }, + { + "epoch": 0.64, + "learning_rate": 7.010255708737581e-06, + "loss": 1.3624, + "step": 6074 + }, + { + "epoch": 0.64, + "learning_rate": 7.006763074727461e-06, + "loss": 0.9335, + "step": 6075 + }, + { + "epoch": 0.64, + "learning_rate": 7.0032708417341835e-06, + "loss": 0.6376, + "step": 6076 + }, + { + "epoch": 0.64, + "learning_rate": 6.999779010225613e-06, + "loss": 0.7882, + "step": 6077 + }, + { + "epoch": 0.64, + "learning_rate": 6.996287580669567e-06, + "loss": 1.3001, + "step": 6078 + }, + { + "epoch": 0.64, + "learning_rate": 6.9927965535338085e-06, + "loss": 1.323, + "step": 6079 + }, + { + "epoch": 0.64, + "learning_rate": 6.989305929286043e-06, + "loss": 1.3478, + "step": 6080 + }, + { + "epoch": 0.64, + "learning_rate": 6.985815708393928e-06, + "loss": 1.319, + "step": 6081 + }, + { + "epoch": 0.64, + "learning_rate": 6.9823258913250566e-06, + "loss": 1.3458, + "step": 6082 + }, + { + "epoch": 0.64, + "learning_rate": 6.978836478546985e-06, + "loss": 1.2481, + "step": 6083 + }, + { + "epoch": 0.64, + "learning_rate": 6.975347470527195e-06, + "loss": 1.4051, + "step": 6084 + }, + { + "epoch": 0.64, + "learning_rate": 6.97185886773313e-06, + "loss": 1.3705, + "step": 6085 + }, + { + "epoch": 0.64, + "learning_rate": 6.9683706706321676e-06, + "loss": 1.3415, + "step": 6086 + }, + { + "epoch": 0.64, + "learning_rate": 6.964882879691643e-06, + "loss": 1.3462, + "step": 6087 + }, + { + "epoch": 0.64, + "learning_rate": 6.961395495378829e-06, + "loss": 1.2974, + "step": 6088 + }, + { + "epoch": 0.64, + "learning_rate": 6.957908518160943e-06, + "loss": 1.3353, + "step": 6089 + }, + { + "epoch": 0.64, + "learning_rate": 6.95442194850515e-06, + "loss": 1.3073, + "step": 6090 + }, + { + "epoch": 0.64, + "learning_rate": 6.9509357868785636e-06, + "loss": 1.352, + "step": 6091 + }, + { + "epoch": 0.64, + "learning_rate": 6.9474500337482396e-06, + "loss": 1.2771, + "step": 6092 + }, + { + "epoch": 0.64, + "learning_rate": 6.943964689581177e-06, + "loss": 1.2925, + "step": 6093 + }, + { + "epoch": 0.64, + "learning_rate": 6.940479754844322e-06, + "loss": 1.2967, + "step": 6094 + }, + { + "epoch": 0.64, + "learning_rate": 6.93699523000457e-06, + "loss": 1.5839, + "step": 6095 + }, + { + "epoch": 0.64, + "learning_rate": 6.933511115528757e-06, + "loss": 1.3051, + "step": 6096 + }, + { + "epoch": 0.64, + "learning_rate": 6.930027411883664e-06, + "loss": 1.5344, + "step": 6097 + }, + { + "epoch": 0.64, + "learning_rate": 6.926544119536014e-06, + "loss": 1.3938, + "step": 6098 + }, + { + "epoch": 0.64, + "learning_rate": 6.923061238952484e-06, + "loss": 1.3504, + "step": 6099 + }, + { + "epoch": 0.64, + "learning_rate": 6.919578770599689e-06, + "loss": 1.3618, + "step": 6100 + }, + { + "epoch": 0.64, + "learning_rate": 6.916096714944187e-06, + "loss": 1.3811, + "step": 6101 + }, + { + "epoch": 0.64, + "learning_rate": 6.912615072452491e-06, + "loss": 1.2673, + "step": 6102 + }, + { + "epoch": 0.64, + "learning_rate": 6.909133843591046e-06, + "loss": 1.3661, + "step": 6103 + }, + { + "epoch": 0.64, + "learning_rate": 6.905653028826249e-06, + "loss": 1.3811, + "step": 6104 + }, + { + "epoch": 0.64, + "learning_rate": 6.902172628624437e-06, + "loss": 1.3399, + "step": 6105 + }, + { + "epoch": 0.64, + "learning_rate": 6.8986926434519e-06, + "loss": 1.281, + "step": 6106 + }, + { + "epoch": 0.64, + "learning_rate": 6.895213073774862e-06, + "loss": 1.3053, + "step": 6107 + }, + { + "epoch": 0.64, + "learning_rate": 6.891733920059498e-06, + "loss": 1.4573, + "step": 6108 + }, + { + "epoch": 0.64, + "learning_rate": 6.8882551827719215e-06, + "loss": 1.355, + "step": 6109 + }, + { + "epoch": 0.64, + "learning_rate": 6.8847768623782e-06, + "loss": 1.3304, + "step": 6110 + }, + { + "epoch": 0.64, + "learning_rate": 6.881298959344335e-06, + "loss": 1.4039, + "step": 6111 + }, + { + "epoch": 0.64, + "learning_rate": 6.877821474136277e-06, + "loss": 1.381, + "step": 6112 + }, + { + "epoch": 0.64, + "learning_rate": 6.874344407219917e-06, + "loss": 1.3503, + "step": 6113 + }, + { + "epoch": 0.64, + "learning_rate": 6.870867759061099e-06, + "loss": 1.2679, + "step": 6114 + }, + { + "epoch": 0.64, + "learning_rate": 6.8673915301256e-06, + "loss": 1.3286, + "step": 6115 + }, + { + "epoch": 0.64, + "learning_rate": 6.863915720879146e-06, + "loss": 1.3528, + "step": 6116 + }, + { + "epoch": 0.64, + "learning_rate": 6.8604403317874055e-06, + "loss": 1.3502, + "step": 6117 + }, + { + "epoch": 0.64, + "learning_rate": 6.856965363315993e-06, + "loss": 1.3507, + "step": 6118 + }, + { + "epoch": 0.64, + "learning_rate": 6.853490815930464e-06, + "loss": 1.2153, + "step": 6119 + }, + { + "epoch": 0.64, + "learning_rate": 6.850016690096319e-06, + "loss": 1.2435, + "step": 6120 + }, + { + "epoch": 0.64, + "learning_rate": 6.846542986279e-06, + "loss": 1.3418, + "step": 6121 + }, + { + "epoch": 0.64, + "learning_rate": 6.843069704943896e-06, + "loss": 1.371, + "step": 6122 + }, + { + "epoch": 0.64, + "learning_rate": 6.8395968465563375e-06, + "loss": 1.1737, + "step": 6123 + }, + { + "epoch": 0.64, + "learning_rate": 6.836124411581598e-06, + "loss": 1.3402, + "step": 6124 + }, + { + "epoch": 0.64, + "learning_rate": 6.8326524004848924e-06, + "loss": 1.3482, + "step": 6125 + }, + { + "epoch": 0.64, + "learning_rate": 6.8291808137313845e-06, + "loss": 1.4585, + "step": 6126 + }, + { + "epoch": 0.64, + "learning_rate": 6.825709651786176e-06, + "loss": 1.2848, + "step": 6127 + }, + { + "epoch": 0.64, + "learning_rate": 6.822238915114312e-06, + "loss": 1.2932, + "step": 6128 + }, + { + "epoch": 0.64, + "learning_rate": 6.818768604180785e-06, + "loss": 1.3124, + "step": 6129 + }, + { + "epoch": 0.64, + "learning_rate": 6.815298719450525e-06, + "loss": 1.2843, + "step": 6130 + }, + { + "epoch": 0.64, + "learning_rate": 6.811829261388409e-06, + "loss": 1.3024, + "step": 6131 + }, + { + "epoch": 0.64, + "learning_rate": 6.808360230459252e-06, + "loss": 1.3612, + "step": 6132 + }, + { + "epoch": 0.64, + "learning_rate": 6.804891627127821e-06, + "loss": 1.3005, + "step": 6133 + }, + { + "epoch": 0.64, + "learning_rate": 6.8014234518588154e-06, + "loss": 1.2614, + "step": 6134 + }, + { + "epoch": 0.64, + "learning_rate": 6.7979557051168835e-06, + "loss": 1.3717, + "step": 6135 + }, + { + "epoch": 0.64, + "learning_rate": 6.794488387366609e-06, + "loss": 1.3873, + "step": 6136 + }, + { + "epoch": 0.64, + "learning_rate": 6.791021499072532e-06, + "loss": 1.2955, + "step": 6137 + }, + { + "epoch": 0.64, + "learning_rate": 6.787555040699121e-06, + "loss": 1.4217, + "step": 6138 + }, + { + "epoch": 0.64, + "learning_rate": 6.784089012710793e-06, + "loss": 1.3805, + "step": 6139 + }, + { + "epoch": 0.64, + "learning_rate": 6.7806234155719055e-06, + "loss": 1.3982, + "step": 6140 + }, + { + "epoch": 0.64, + "learning_rate": 6.7771582497467635e-06, + "loss": 1.4, + "step": 6141 + }, + { + "epoch": 0.64, + "learning_rate": 6.773693515699607e-06, + "loss": 1.439, + "step": 6142 + }, + { + "epoch": 0.64, + "learning_rate": 6.7702292138946235e-06, + "loss": 1.3672, + "step": 6143 + }, + { + "epoch": 0.64, + "learning_rate": 6.7667653447959355e-06, + "loss": 1.2901, + "step": 6144 + }, + { + "epoch": 0.64, + "learning_rate": 6.763301908867619e-06, + "loss": 1.2873, + "step": 6145 + }, + { + "epoch": 0.64, + "learning_rate": 6.759838906573684e-06, + "loss": 1.3582, + "step": 6146 + }, + { + "epoch": 0.64, + "learning_rate": 6.756376338378077e-06, + "loss": 1.3562, + "step": 6147 + }, + { + "epoch": 0.64, + "learning_rate": 6.7529142047447025e-06, + "loss": 1.3091, + "step": 6148 + }, + { + "epoch": 0.64, + "learning_rate": 6.749452506137393e-06, + "loss": 1.4269, + "step": 6149 + }, + { + "epoch": 0.64, + "learning_rate": 6.745991243019927e-06, + "loss": 1.4184, + "step": 6150 + }, + { + "epoch": 0.65, + "learning_rate": 6.7425304158560235e-06, + "loss": 1.4201, + "step": 6151 + }, + { + "epoch": 0.65, + "learning_rate": 6.739070025109349e-06, + "loss": 1.3222, + "step": 6152 + }, + { + "epoch": 0.65, + "learning_rate": 6.7356100712435035e-06, + "loss": 1.3262, + "step": 6153 + }, + { + "epoch": 0.65, + "learning_rate": 6.732150554722034e-06, + "loss": 1.4408, + "step": 6154 + }, + { + "epoch": 0.65, + "learning_rate": 6.728691476008422e-06, + "loss": 1.3441, + "step": 6155 + }, + { + "epoch": 0.65, + "learning_rate": 6.725232835566102e-06, + "loss": 1.3316, + "step": 6156 + }, + { + "epoch": 0.65, + "learning_rate": 6.721774633858438e-06, + "loss": 1.3326, + "step": 6157 + }, + { + "epoch": 0.65, + "learning_rate": 6.7183168713487425e-06, + "loss": 1.3105, + "step": 6158 + }, + { + "epoch": 0.65, + "learning_rate": 6.714859548500265e-06, + "loss": 1.3144, + "step": 6159 + }, + { + "epoch": 0.65, + "learning_rate": 6.7114026657762e-06, + "loss": 1.3472, + "step": 6160 + }, + { + "epoch": 0.65, + "learning_rate": 6.707946223639681e-06, + "loss": 1.3811, + "step": 6161 + }, + { + "epoch": 0.65, + "learning_rate": 6.704490222553781e-06, + "loss": 1.2783, + "step": 6162 + }, + { + "epoch": 0.65, + "learning_rate": 6.701034662981513e-06, + "loss": 1.273, + "step": 6163 + }, + { + "epoch": 0.65, + "learning_rate": 6.697579545385839e-06, + "loss": 1.3522, + "step": 6164 + }, + { + "epoch": 0.65, + "learning_rate": 6.6941248702296524e-06, + "loss": 1.3861, + "step": 6165 + }, + { + "epoch": 0.65, + "learning_rate": 6.6906706379757915e-06, + "loss": 1.3098, + "step": 6166 + }, + { + "epoch": 0.65, + "learning_rate": 6.687216849087032e-06, + "loss": 1.3734, + "step": 6167 + }, + { + "epoch": 0.65, + "learning_rate": 6.6837635040261e-06, + "loss": 1.2289, + "step": 6168 + }, + { + "epoch": 0.65, + "learning_rate": 6.680310603255648e-06, + "loss": 1.3238, + "step": 6169 + }, + { + "epoch": 0.65, + "eval_loss": 1.40826416015625, + "eval_runtime": 77.483, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 6169 + }, + { + "epoch": 0.65, + "learning_rate": 6.676858147238277e-06, + "loss": 1.4317, + "step": 6170 + }, + { + "epoch": 0.65, + "learning_rate": 6.673406136436531e-06, + "loss": 1.3363, + "step": 6171 + }, + { + "epoch": 0.65, + "learning_rate": 6.669954571312889e-06, + "loss": 1.3377, + "step": 6172 + }, + { + "epoch": 0.65, + "learning_rate": 6.666503452329771e-06, + "loss": 1.3382, + "step": 6173 + }, + { + "epoch": 0.65, + "learning_rate": 6.663052779949538e-06, + "loss": 1.3028, + "step": 6174 + }, + { + "epoch": 0.65, + "learning_rate": 6.659602554634494e-06, + "loss": 1.3098, + "step": 6175 + }, + { + "epoch": 0.65, + "learning_rate": 6.656152776846879e-06, + "loss": 1.328, + "step": 6176 + }, + { + "epoch": 0.65, + "learning_rate": 6.652703447048874e-06, + "loss": 1.3014, + "step": 6177 + }, + { + "epoch": 0.65, + "learning_rate": 6.6492545657026e-06, + "loss": 1.2522, + "step": 6178 + }, + { + "epoch": 0.65, + "learning_rate": 6.645806133270121e-06, + "loss": 1.6113, + "step": 6179 + }, + { + "epoch": 0.65, + "learning_rate": 6.642358150213437e-06, + "loss": 1.3431, + "step": 6180 + }, + { + "epoch": 0.65, + "learning_rate": 6.638910616994489e-06, + "loss": 1.2725, + "step": 6181 + }, + { + "epoch": 0.65, + "learning_rate": 6.635463534075156e-06, + "loss": 1.3022, + "step": 6182 + }, + { + "epoch": 0.65, + "learning_rate": 6.632016901917262e-06, + "loss": 1.3496, + "step": 6183 + }, + { + "epoch": 0.65, + "learning_rate": 6.628570720982567e-06, + "loss": 1.2871, + "step": 6184 + }, + { + "epoch": 0.65, + "learning_rate": 6.625124991732767e-06, + "loss": 1.4449, + "step": 6185 + }, + { + "epoch": 0.65, + "learning_rate": 6.621679714629504e-06, + "loss": 1.4395, + "step": 6186 + }, + { + "epoch": 0.65, + "learning_rate": 6.618234890134356e-06, + "loss": 1.4088, + "step": 6187 + }, + { + "epoch": 0.65, + "learning_rate": 6.614790518708843e-06, + "loss": 1.371, + "step": 6188 + }, + { + "epoch": 0.65, + "learning_rate": 6.611346600814419e-06, + "loss": 1.28, + "step": 6189 + }, + { + "epoch": 0.65, + "learning_rate": 6.607903136912482e-06, + "loss": 1.3502, + "step": 6190 + }, + { + "epoch": 0.65, + "learning_rate": 6.604460127464367e-06, + "loss": 1.3398, + "step": 6191 + }, + { + "epoch": 0.65, + "learning_rate": 6.60101757293135e-06, + "loss": 1.4762, + "step": 6192 + }, + { + "epoch": 0.65, + "learning_rate": 6.5975754737746426e-06, + "loss": 1.2981, + "step": 6193 + }, + { + "epoch": 0.65, + "learning_rate": 6.594133830455401e-06, + "loss": 1.3728, + "step": 6194 + }, + { + "epoch": 0.65, + "learning_rate": 6.590692643434715e-06, + "loss": 1.3551, + "step": 6195 + }, + { + "epoch": 0.65, + "learning_rate": 6.5872519131736155e-06, + "loss": 1.3031, + "step": 6196 + }, + { + "epoch": 0.65, + "learning_rate": 6.583811640133071e-06, + "loss": 1.3231, + "step": 6197 + }, + { + "epoch": 0.65, + "learning_rate": 6.5803718247739924e-06, + "loss": 1.2752, + "step": 6198 + }, + { + "epoch": 0.65, + "learning_rate": 6.576932467557223e-06, + "loss": 1.3482, + "step": 6199 + }, + { + "epoch": 0.65, + "learning_rate": 6.573493568943552e-06, + "loss": 1.2612, + "step": 6200 + }, + { + "epoch": 0.65, + "learning_rate": 6.570055129393698e-06, + "loss": 1.6302, + "step": 6201 + }, + { + "epoch": 0.65, + "learning_rate": 6.566617149368331e-06, + "loss": 1.303, + "step": 6202 + }, + { + "epoch": 0.65, + "learning_rate": 6.563179629328047e-06, + "loss": 1.3405, + "step": 6203 + }, + { + "epoch": 0.65, + "learning_rate": 6.559742569733385e-06, + "loss": 1.2816, + "step": 6204 + }, + { + "epoch": 0.65, + "learning_rate": 6.556305971044824e-06, + "loss": 1.3834, + "step": 6205 + }, + { + "epoch": 0.65, + "learning_rate": 6.552869833722781e-06, + "loss": 1.3414, + "step": 6206 + }, + { + "epoch": 0.65, + "learning_rate": 6.5494341582276096e-06, + "loss": 1.3278, + "step": 6207 + }, + { + "epoch": 0.65, + "learning_rate": 6.5459989450196024e-06, + "loss": 1.3577, + "step": 6208 + }, + { + "epoch": 0.65, + "learning_rate": 6.542564194558986e-06, + "loss": 1.3104, + "step": 6209 + }, + { + "epoch": 0.65, + "learning_rate": 6.539129907305933e-06, + "loss": 1.3068, + "step": 6210 + }, + { + "epoch": 0.65, + "learning_rate": 6.53569608372055e-06, + "loss": 1.3769, + "step": 6211 + }, + { + "epoch": 0.65, + "learning_rate": 6.5322627242628775e-06, + "loss": 1.2855, + "step": 6212 + }, + { + "epoch": 0.65, + "learning_rate": 6.528829829392898e-06, + "loss": 1.4129, + "step": 6213 + }, + { + "epoch": 0.65, + "learning_rate": 6.525397399570534e-06, + "loss": 1.3631, + "step": 6214 + }, + { + "epoch": 0.65, + "learning_rate": 6.5219654352556435e-06, + "loss": 1.295, + "step": 6215 + }, + { + "epoch": 0.65, + "learning_rate": 6.518533936908016e-06, + "loss": 1.439, + "step": 6216 + }, + { + "epoch": 0.65, + "learning_rate": 6.515102904987389e-06, + "loss": 1.3148, + "step": 6217 + }, + { + "epoch": 0.65, + "learning_rate": 6.511672339953432e-06, + "loss": 1.3898, + "step": 6218 + }, + { + "epoch": 0.65, + "learning_rate": 6.508242242265752e-06, + "loss": 1.3222, + "step": 6219 + }, + { + "epoch": 0.65, + "learning_rate": 6.504812612383891e-06, + "loss": 1.324, + "step": 6220 + }, + { + "epoch": 0.65, + "learning_rate": 6.501383450767336e-06, + "loss": 1.951, + "step": 6221 + }, + { + "epoch": 0.65, + "learning_rate": 6.4979547578755055e-06, + "loss": 1.2878, + "step": 6222 + }, + { + "epoch": 0.65, + "learning_rate": 6.494526534167754e-06, + "loss": 1.3553, + "step": 6223 + }, + { + "epoch": 0.65, + "learning_rate": 6.491098780103375e-06, + "loss": 1.3898, + "step": 6224 + }, + { + "epoch": 0.65, + "learning_rate": 6.487671496141606e-06, + "loss": 1.4333, + "step": 6225 + }, + { + "epoch": 0.65, + "learning_rate": 6.484244682741606e-06, + "loss": 1.4461, + "step": 6226 + }, + { + "epoch": 0.65, + "learning_rate": 6.480818340362487e-06, + "loss": 1.3461, + "step": 6227 + }, + { + "epoch": 0.65, + "learning_rate": 6.4773924694632835e-06, + "loss": 1.3442, + "step": 6228 + }, + { + "epoch": 0.65, + "learning_rate": 6.473967070502982e-06, + "loss": 1.2692, + "step": 6229 + }, + { + "epoch": 0.65, + "learning_rate": 6.470542143940495e-06, + "loss": 1.446, + "step": 6230 + }, + { + "epoch": 0.65, + "learning_rate": 6.467117690234675e-06, + "loss": 1.3597, + "step": 6231 + }, + { + "epoch": 0.65, + "learning_rate": 6.463693709844305e-06, + "loss": 1.3226, + "step": 6232 + }, + { + "epoch": 0.65, + "learning_rate": 6.46027020322812e-06, + "loss": 1.2702, + "step": 6233 + }, + { + "epoch": 0.65, + "learning_rate": 6.456847170844775e-06, + "loss": 1.2554, + "step": 6234 + }, + { + "epoch": 0.65, + "learning_rate": 6.453424613152872e-06, + "loss": 1.2896, + "step": 6235 + }, + { + "epoch": 0.65, + "learning_rate": 6.450002530610943e-06, + "loss": 1.3148, + "step": 6236 + }, + { + "epoch": 0.65, + "learning_rate": 6.4465809236774635e-06, + "loss": 1.3589, + "step": 6237 + }, + { + "epoch": 0.65, + "learning_rate": 6.443159792810838e-06, + "loss": 1.2938, + "step": 6238 + }, + { + "epoch": 0.65, + "learning_rate": 6.439739138469406e-06, + "loss": 1.366, + "step": 6239 + }, + { + "epoch": 0.65, + "learning_rate": 6.436318961111455e-06, + "loss": 1.4772, + "step": 6240 + }, + { + "epoch": 0.65, + "learning_rate": 6.4328992611951975e-06, + "loss": 1.3131, + "step": 6241 + }, + { + "epoch": 0.65, + "learning_rate": 6.429480039178786e-06, + "loss": 1.2382, + "step": 6242 + }, + { + "epoch": 0.65, + "learning_rate": 6.426061295520304e-06, + "loss": 1.3394, + "step": 6243 + }, + { + "epoch": 0.65, + "learning_rate": 6.422643030677782e-06, + "loss": 1.321, + "step": 6244 + }, + { + "epoch": 0.65, + "learning_rate": 6.419225245109175e-06, + "loss": 1.3478, + "step": 6245 + }, + { + "epoch": 0.65, + "learning_rate": 6.415807939272383e-06, + "loss": 1.3249, + "step": 6246 + }, + { + "epoch": 0.66, + "learning_rate": 6.412391113625231e-06, + "loss": 1.3602, + "step": 6247 + }, + { + "epoch": 0.66, + "learning_rate": 6.408974768625491e-06, + "loss": 1.2799, + "step": 6248 + }, + { + "epoch": 0.66, + "learning_rate": 6.405558904730863e-06, + "loss": 1.3911, + "step": 6249 + }, + { + "epoch": 0.66, + "learning_rate": 6.402143522398987e-06, + "loss": 1.3185, + "step": 6250 + }, + { + "epoch": 0.66, + "learning_rate": 6.398728622087431e-06, + "loss": 1.3198, + "step": 6251 + }, + { + "epoch": 0.66, + "learning_rate": 6.395314204253711e-06, + "loss": 1.361, + "step": 6252 + }, + { + "epoch": 0.66, + "learning_rate": 6.391900269355269e-06, + "loss": 1.3285, + "step": 6253 + }, + { + "epoch": 0.66, + "learning_rate": 6.388486817849484e-06, + "loss": 1.3097, + "step": 6254 + }, + { + "epoch": 0.66, + "learning_rate": 6.385073850193667e-06, + "loss": 1.3057, + "step": 6255 + }, + { + "epoch": 0.66, + "learning_rate": 6.381661366845075e-06, + "loss": 1.4733, + "step": 6256 + }, + { + "epoch": 0.66, + "learning_rate": 6.378249368260889e-06, + "loss": 1.3571, + "step": 6257 + }, + { + "epoch": 0.66, + "learning_rate": 6.374837854898228e-06, + "loss": 1.3278, + "step": 6258 + }, + { + "epoch": 0.66, + "learning_rate": 6.37142682721415e-06, + "loss": 1.3035, + "step": 6259 + }, + { + "epoch": 0.66, + "learning_rate": 6.368016285665645e-06, + "loss": 1.397, + "step": 6260 + }, + { + "epoch": 0.66, + "learning_rate": 6.3646062307096365e-06, + "loss": 1.353, + "step": 6261 + }, + { + "epoch": 0.66, + "learning_rate": 6.361196662802982e-06, + "loss": 1.3534, + "step": 6262 + }, + { + "epoch": 0.66, + "learning_rate": 6.357787582402482e-06, + "loss": 1.3132, + "step": 6263 + }, + { + "epoch": 0.66, + "learning_rate": 6.3543789899648624e-06, + "loss": 1.3551, + "step": 6264 + }, + { + "epoch": 0.66, + "learning_rate": 6.3509708859467855e-06, + "loss": 1.4205, + "step": 6265 + }, + { + "epoch": 0.66, + "learning_rate": 6.347563270804851e-06, + "loss": 1.341, + "step": 6266 + }, + { + "epoch": 0.66, + "learning_rate": 6.344156144995593e-06, + "loss": 1.5188, + "step": 6267 + }, + { + "epoch": 0.66, + "learning_rate": 6.340749508975477e-06, + "loss": 1.4404, + "step": 6268 + }, + { + "epoch": 0.66, + "learning_rate": 6.337343363200905e-06, + "loss": 1.3026, + "step": 6269 + }, + { + "epoch": 0.66, + "learning_rate": 6.3339377081282124e-06, + "loss": 1.3315, + "step": 6270 + }, + { + "epoch": 0.66, + "learning_rate": 6.3305325442136735e-06, + "loss": 1.2503, + "step": 6271 + }, + { + "epoch": 0.66, + "learning_rate": 6.3271278719134885e-06, + "loss": 1.1776, + "step": 6272 + }, + { + "epoch": 0.66, + "learning_rate": 6.323723691683798e-06, + "loss": 1.3033, + "step": 6273 + }, + { + "epoch": 0.66, + "learning_rate": 6.320320003980671e-06, + "loss": 1.3838, + "step": 6274 + }, + { + "epoch": 0.66, + "learning_rate": 6.3169168092601195e-06, + "loss": 1.3691, + "step": 6275 + }, + { + "epoch": 0.66, + "learning_rate": 6.313514107978083e-06, + "loss": 1.3665, + "step": 6276 + }, + { + "epoch": 0.66, + "learning_rate": 6.310111900590432e-06, + "loss": 1.358, + "step": 6277 + }, + { + "epoch": 0.66, + "learning_rate": 6.306710187552978e-06, + "loss": 1.1708, + "step": 6278 + }, + { + "epoch": 0.66, + "learning_rate": 6.303308969321464e-06, + "loss": 1.331, + "step": 6279 + }, + { + "epoch": 0.66, + "learning_rate": 6.299908246351566e-06, + "loss": 1.3914, + "step": 6280 + }, + { + "epoch": 0.66, + "learning_rate": 6.2965080190988896e-06, + "loss": 1.3183, + "step": 6281 + }, + { + "epoch": 0.66, + "learning_rate": 6.293108288018981e-06, + "loss": 1.2969, + "step": 6282 + }, + { + "epoch": 0.66, + "learning_rate": 6.289709053567318e-06, + "loss": 1.2892, + "step": 6283 + }, + { + "epoch": 0.66, + "learning_rate": 6.2863103161993085e-06, + "loss": 1.3517, + "step": 6284 + }, + { + "epoch": 0.66, + "learning_rate": 6.282912076370295e-06, + "loss": 1.3329, + "step": 6285 + }, + { + "epoch": 0.66, + "learning_rate": 6.279514334535557e-06, + "loss": 1.3396, + "step": 6286 + }, + { + "epoch": 0.66, + "learning_rate": 6.276117091150304e-06, + "loss": 1.3878, + "step": 6287 + }, + { + "epoch": 0.66, + "learning_rate": 6.272720346669677e-06, + "loss": 1.2608, + "step": 6288 + }, + { + "epoch": 0.66, + "learning_rate": 6.269324101548754e-06, + "loss": 1.3605, + "step": 6289 + }, + { + "epoch": 0.66, + "learning_rate": 6.265928356242546e-06, + "loss": 1.2682, + "step": 6290 + }, + { + "epoch": 0.66, + "learning_rate": 6.262533111205995e-06, + "loss": 1.3426, + "step": 6291 + }, + { + "epoch": 0.66, + "learning_rate": 6.259138366893975e-06, + "loss": 1.2987, + "step": 6292 + }, + { + "epoch": 0.66, + "learning_rate": 6.255744123761295e-06, + "loss": 1.3521, + "step": 6293 + }, + { + "epoch": 0.66, + "learning_rate": 6.252350382262697e-06, + "loss": 1.2816, + "step": 6294 + }, + { + "epoch": 0.66, + "learning_rate": 6.248957142852856e-06, + "loss": 1.3884, + "step": 6295 + }, + { + "epoch": 0.66, + "learning_rate": 6.2455644059863795e-06, + "loss": 1.3545, + "step": 6296 + }, + { + "epoch": 0.66, + "learning_rate": 6.2421721721178015e-06, + "loss": 1.3636, + "step": 6297 + }, + { + "epoch": 0.66, + "learning_rate": 6.238780441701601e-06, + "loss": 1.3584, + "step": 6298 + }, + { + "epoch": 0.66, + "learning_rate": 6.235389215192179e-06, + "loss": 1.3459, + "step": 6299 + }, + { + "epoch": 0.66, + "learning_rate": 6.231998493043875e-06, + "loss": 1.4654, + "step": 6300 + }, + { + "epoch": 0.66, + "learning_rate": 6.228608275710954e-06, + "loss": 1.3628, + "step": 6301 + }, + { + "epoch": 0.66, + "learning_rate": 6.225218563647623e-06, + "loss": 1.3278, + "step": 6302 + }, + { + "epoch": 0.66, + "learning_rate": 6.221829357308016e-06, + "loss": 1.395, + "step": 6303 + }, + { + "epoch": 0.66, + "learning_rate": 6.218440657146196e-06, + "loss": 1.3481, + "step": 6304 + }, + { + "epoch": 0.66, + "learning_rate": 6.215052463616165e-06, + "loss": 1.309, + "step": 6305 + }, + { + "epoch": 0.66, + "learning_rate": 6.211664777171853e-06, + "loss": 1.275, + "step": 6306 + }, + { + "epoch": 0.66, + "learning_rate": 6.208277598267123e-06, + "loss": 1.4885, + "step": 6307 + }, + { + "epoch": 0.66, + "learning_rate": 6.2048909273557686e-06, + "loss": 1.3334, + "step": 6308 + }, + { + "epoch": 0.66, + "learning_rate": 6.201504764891518e-06, + "loss": 1.3399, + "step": 6309 + }, + { + "epoch": 0.66, + "learning_rate": 6.198119111328032e-06, + "loss": 1.3163, + "step": 6310 + }, + { + "epoch": 0.66, + "learning_rate": 6.1947339671188966e-06, + "loss": 1.2746, + "step": 6311 + }, + { + "epoch": 0.66, + "learning_rate": 6.191349332717635e-06, + "loss": 1.2984, + "step": 6312 + }, + { + "epoch": 0.66, + "learning_rate": 6.187965208577705e-06, + "loss": 1.2295, + "step": 6313 + }, + { + "epoch": 0.66, + "learning_rate": 6.18458159515249e-06, + "loss": 1.3424, + "step": 6314 + }, + { + "epoch": 0.66, + "learning_rate": 6.181198492895308e-06, + "loss": 1.3108, + "step": 6315 + }, + { + "epoch": 0.66, + "learning_rate": 6.1778159022594045e-06, + "loss": 1.4895, + "step": 6316 + }, + { + "epoch": 0.66, + "learning_rate": 6.174433823697964e-06, + "loss": 1.3247, + "step": 6317 + }, + { + "epoch": 0.66, + "learning_rate": 6.171052257664097e-06, + "loss": 1.3659, + "step": 6318 + }, + { + "epoch": 0.66, + "learning_rate": 6.167671204610844e-06, + "loss": 1.3889, + "step": 6319 + }, + { + "epoch": 0.66, + "learning_rate": 6.1642906649911815e-06, + "loss": 1.3946, + "step": 6320 + }, + { + "epoch": 0.66, + "learning_rate": 6.1609106392580155e-06, + "loss": 1.3685, + "step": 6321 + }, + { + "epoch": 0.66, + "learning_rate": 6.157531127864181e-06, + "loss": 1.2584, + "step": 6322 + }, + { + "epoch": 0.66, + "learning_rate": 6.154152131262448e-06, + "loss": 1.3263, + "step": 6323 + }, + { + "epoch": 0.66, + "learning_rate": 6.15077364990551e-06, + "loss": 1.3336, + "step": 6324 + }, + { + "epoch": 0.66, + "learning_rate": 6.147395684246003e-06, + "loss": 1.2513, + "step": 6325 + }, + { + "epoch": 0.66, + "learning_rate": 6.144018234736484e-06, + "loss": 1.3715, + "step": 6326 + }, + { + "epoch": 0.66, + "learning_rate": 6.140641301829444e-06, + "loss": 1.3464, + "step": 6327 + }, + { + "epoch": 0.66, + "learning_rate": 6.1372648859773075e-06, + "loss": 1.4374, + "step": 6328 + }, + { + "epoch": 0.66, + "learning_rate": 6.1338889876324285e-06, + "loss": 1.3903, + "step": 6329 + }, + { + "epoch": 0.66, + "learning_rate": 6.130513607247087e-06, + "loss": 1.3715, + "step": 6330 + }, + { + "epoch": 0.66, + "learning_rate": 6.127138745273497e-06, + "loss": 1.3196, + "step": 6331 + }, + { + "epoch": 0.66, + "learning_rate": 6.123764402163808e-06, + "loss": 1.3013, + "step": 6332 + }, + { + "epoch": 0.66, + "learning_rate": 6.120390578370093e-06, + "loss": 1.2751, + "step": 6333 + }, + { + "epoch": 0.66, + "learning_rate": 6.117017274344356e-06, + "loss": 1.2258, + "step": 6334 + }, + { + "epoch": 0.66, + "learning_rate": 6.113644490538533e-06, + "loss": 1.2982, + "step": 6335 + }, + { + "epoch": 0.66, + "learning_rate": 6.110272227404492e-06, + "loss": 1.3124, + "step": 6336 + }, + { + "epoch": 0.66, + "learning_rate": 6.10690048539403e-06, + "loss": 1.2451, + "step": 6337 + }, + { + "epoch": 0.66, + "learning_rate": 6.103529264958874e-06, + "loss": 1.3896, + "step": 6338 + }, + { + "epoch": 0.66, + "learning_rate": 6.100158566550677e-06, + "loss": 1.46, + "step": 6339 + }, + { + "epoch": 0.66, + "learning_rate": 6.096788390621031e-06, + "loss": 1.2965, + "step": 6340 + }, + { + "epoch": 0.66, + "learning_rate": 6.093418737621452e-06, + "loss": 1.2969, + "step": 6341 + }, + { + "epoch": 0.67, + "learning_rate": 6.0900496080033836e-06, + "loss": 1.3988, + "step": 6342 + }, + { + "epoch": 0.67, + "learning_rate": 6.086681002218204e-06, + "loss": 1.351, + "step": 6343 + }, + { + "epoch": 0.67, + "learning_rate": 6.083312920717224e-06, + "loss": 1.3447, + "step": 6344 + }, + { + "epoch": 0.67, + "learning_rate": 6.079945363951674e-06, + "loss": 1.3361, + "step": 6345 + }, + { + "epoch": 0.67, + "learning_rate": 6.076578332372724e-06, + "loss": 1.3688, + "step": 6346 + }, + { + "epoch": 0.67, + "learning_rate": 6.073211826431467e-06, + "loss": 1.2831, + "step": 6347 + }, + { + "epoch": 0.67, + "learning_rate": 6.069845846578931e-06, + "loss": 1.369, + "step": 6348 + }, + { + "epoch": 0.67, + "learning_rate": 6.06648039326607e-06, + "loss": 1.3247, + "step": 6349 + }, + { + "epoch": 0.67, + "learning_rate": 6.063115466943765e-06, + "loss": 1.288, + "step": 6350 + }, + { + "epoch": 0.67, + "learning_rate": 6.0597510680628345e-06, + "loss": 1.0733, + "step": 6351 + }, + { + "epoch": 0.67, + "learning_rate": 6.056387197074021e-06, + "loss": 1.3386, + "step": 6352 + }, + { + "epoch": 0.67, + "learning_rate": 6.053023854427993e-06, + "loss": 1.3682, + "step": 6353 + }, + { + "epoch": 0.67, + "learning_rate": 6.049661040575353e-06, + "loss": 1.5669, + "step": 6354 + }, + { + "epoch": 0.67, + "learning_rate": 6.0462987559666355e-06, + "loss": 1.3432, + "step": 6355 + }, + { + "epoch": 0.67, + "learning_rate": 6.042937001052298e-06, + "loss": 1.327, + "step": 6356 + }, + { + "epoch": 0.67, + "learning_rate": 6.039575776282728e-06, + "loss": 1.3101, + "step": 6357 + }, + { + "epoch": 0.67, + "learning_rate": 6.0362150821082425e-06, + "loss": 1.3239, + "step": 6358 + }, + { + "epoch": 0.67, + "learning_rate": 6.032854918979092e-06, + "loss": 1.435, + "step": 6359 + }, + { + "epoch": 0.67, + "learning_rate": 6.029495287345448e-06, + "loss": 1.3503, + "step": 6360 + }, + { + "epoch": 0.67, + "learning_rate": 6.0261361876574186e-06, + "loss": 1.3356, + "step": 6361 + }, + { + "epoch": 0.67, + "learning_rate": 6.022777620365032e-06, + "loss": 1.3301, + "step": 6362 + }, + { + "epoch": 0.67, + "learning_rate": 6.019419585918255e-06, + "loss": 1.3925, + "step": 6363 + }, + { + "epoch": 0.67, + "learning_rate": 6.016062084766978e-06, + "loss": 1.3794, + "step": 6364 + }, + { + "epoch": 0.67, + "learning_rate": 6.0127051173610155e-06, + "loss": 1.5496, + "step": 6365 + }, + { + "epoch": 0.67, + "learning_rate": 6.009348684150116e-06, + "loss": 1.3227, + "step": 6366 + }, + { + "epoch": 0.67, + "learning_rate": 6.005992785583958e-06, + "loss": 1.3474, + "step": 6367 + }, + { + "epoch": 0.67, + "learning_rate": 6.002637422112143e-06, + "loss": 1.3262, + "step": 6368 + }, + { + "epoch": 0.67, + "eval_loss": 1.4049769639968872, + "eval_runtime": 77.5156, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 6368 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 2.848814278356165e+20, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-6368/training_args.bin b/checkpoint-6368/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-6368/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-6766/config.json b/checkpoint-6766/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-6766/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-6766/generation_config.json b/checkpoint-6766/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-6766/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-6766/model-00001-of-00003.safetensors b/checkpoint-6766/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a873ba55a8cd6cdc4f85617faad165a615a72ded --- /dev/null +++ b/checkpoint-6766/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ab24c556659581bc2827f608d54e16b543fea7d9494449102ed48be6729c8b0 +size 4943162336 diff --git a/checkpoint-6766/model-00002-of-00003.safetensors b/checkpoint-6766/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a3df958487b90423fff02df1c5d1db88ae631468 --- /dev/null +++ b/checkpoint-6766/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:064c97115a76f02feccbf17594a9a9118253d2b61e8cf994cf51ec1a85caa5bf +size 4999819336 diff --git a/checkpoint-6766/model-00003-of-00003.safetensors b/checkpoint-6766/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cdf6b8ced5559607bc3b92bfd3b897f1a5b53dc7 --- /dev/null +++ b/checkpoint-6766/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80b69fa80aac490d2f518186b244d1122dde62c55d5e4227280ff003b45eace9 +size 4540516344 diff --git a/checkpoint-6766/model.safetensors.index.json b/checkpoint-6766/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-6766/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-6766/optimizer.pt b/checkpoint-6766/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..35490fbde20ea6a6c803330fd9cf09a63b5dd968 --- /dev/null +++ b/checkpoint-6766/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a646510841879a806c2b7d7722dc740d8e71775d9d82acd48351f20eb752b69d +size 14512103560 diff --git a/checkpoint-6766/rng_state_0.pth b/checkpoint-6766/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..0c0cccfa162b72c46a44728bf0725751241eeb04 --- /dev/null +++ b/checkpoint-6766/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d1b60bd962578c6df448ff9bffaa43feb5e54aedaf9cae94905f14757674a12 +size 15984 diff --git a/checkpoint-6766/rng_state_1.pth b/checkpoint-6766/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..3677422dad394aaf42f95beb66a67a15d5b4d6f7 --- /dev/null +++ b/checkpoint-6766/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b56e2be1fca03476156f81cdebe2928ae5ea36ce36bd657c07c65b9e922e888e +size 15984 diff --git a/checkpoint-6766/rng_state_2.pth b/checkpoint-6766/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..d56ae4a95ca52e4308afad5a83345bcde479dd43 --- /dev/null +++ b/checkpoint-6766/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9b21d2dbbef4cf2374f031d3c80f8b8cf65e623ca7aeda94b6c76989be73707 +size 15984 diff --git a/checkpoint-6766/rng_state_3.pth b/checkpoint-6766/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..2b0e4a620d90fdce1b4ad43f146906f651159a5f --- /dev/null +++ b/checkpoint-6766/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c13bd5136ffb0e0727dc2a7fe0456a835e252f719c644dd756e79403fd927564 +size 15984 diff --git a/checkpoint-6766/rng_state_4.pth b/checkpoint-6766/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..fe3c6d9ea99d4f61ec786be822c01b6c839456f6 --- /dev/null +++ b/checkpoint-6766/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1069d1b33ee07aa139751257be025ec891c0652567ee48cff6ae8d24bd4d477 +size 15984 diff --git a/checkpoint-6766/rng_state_5.pth b/checkpoint-6766/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..8d0fc0db9cd11f5f88bf2bd5625009505d71c8d0 --- /dev/null +++ b/checkpoint-6766/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1b13f33402b97d40f0d79df0b6e002a622d08ae40299e9b39a673e309987335 +size 15984 diff --git a/checkpoint-6766/rng_state_6.pth b/checkpoint-6766/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..cd810d84ab47ff1899fefbcc9742c36f574fafb0 --- /dev/null +++ b/checkpoint-6766/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:093110db25b828d0cec4c8553fbfa5db539889bd21e9f26140eac36a4ab8960a +size 15984 diff --git a/checkpoint-6766/rng_state_7.pth b/checkpoint-6766/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..26026b3472bf151f42b7c6115934e9ad5b627269 --- /dev/null +++ b/checkpoint-6766/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8538a1af7df3f4d1501f7c9411219e24a24ddbb136d69f28fa67c202a2ea26fc +size 15984 diff --git a/checkpoint-6766/scheduler.pt b/checkpoint-6766/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..6c07ea045d87eaaa9416fb25280242f22804fa8e --- /dev/null +++ b/checkpoint-6766/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebb1bff0245de7b301e6605f84744c08153e09d86df24edda76e7d6c78ce098b +size 1064 diff --git a/checkpoint-6766/special_tokens_map.json b/checkpoint-6766/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-6766/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-6766/tokenizer.model b/checkpoint-6766/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-6766/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-6766/tokenizer_config.json b/checkpoint-6766/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-6766/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-6766/trainer_state.json b/checkpoint-6766/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..e25a1f4d88eb82a02fa556c392568858b266c580 --- /dev/null +++ b/checkpoint-6766/trainer_state.json @@ -0,0 +1,40888 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.7095218120805369, + "eval_steps": 199, + "global_step": 6766, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + }, + { + "epoch": 0.21, + "learning_rate": 1.928689129323009e-05, + "loss": 1.421, + "step": 1991 + }, + { + "epoch": 0.21, + "learning_rate": 1.928553323396003e-05, + "loss": 1.5625, + "step": 1992 + }, + { + "epoch": 0.21, + "learning_rate": 1.92841739306671e-05, + "loss": 1.5198, + "step": 1993 + }, + { + "epoch": 0.21, + "learning_rate": 1.9282813383533415e-05, + "loss": 1.5116, + "step": 1994 + }, + { + "epoch": 0.21, + "learning_rate": 1.9281451592741247e-05, + "loss": 1.4306, + "step": 1995 + }, + { + "epoch": 0.21, + "learning_rate": 1.9280088558473046e-05, + "loss": 1.5425, + "step": 1996 + }, + { + "epoch": 0.21, + "learning_rate": 1.9278724280911424e-05, + "loss": 1.4972, + "step": 1997 + }, + { + "epoch": 0.21, + "learning_rate": 1.9277358760239156e-05, + "loss": 1.5185, + "step": 1998 + }, + { + "epoch": 0.21, + "learning_rate": 1.9275991996639188e-05, + "loss": 1.5187, + "step": 1999 + }, + { + "epoch": 0.21, + "learning_rate": 1.927462399029463e-05, + "loss": 1.4325, + "step": 2000 + }, + { + "epoch": 0.21, + "learning_rate": 1.9273254741388763e-05, + "loss": 1.4397, + "step": 2001 + }, + { + "epoch": 0.21, + "learning_rate": 1.927188425010503e-05, + "loss": 1.5319, + "step": 2002 + }, + { + "epoch": 0.21, + "learning_rate": 1.9270512516627042e-05, + "loss": 1.5664, + "step": 2003 + }, + { + "epoch": 0.21, + "learning_rate": 1.9269139541138574e-05, + "loss": 1.5227, + "step": 2004 + }, + { + "epoch": 0.21, + "learning_rate": 1.926776532382357e-05, + "loss": 1.5187, + "step": 2005 + }, + { + "epoch": 0.21, + "learning_rate": 1.9266389864866134e-05, + "loss": 1.4029, + "step": 2006 + }, + { + "epoch": 0.21, + "learning_rate": 1.9265013164450557e-05, + "loss": 1.387, + "step": 2007 + }, + { + "epoch": 0.21, + "learning_rate": 1.9263635222761268e-05, + "loss": 1.5047, + "step": 2008 + }, + { + "epoch": 0.21, + "learning_rate": 1.9262256039982882e-05, + "loss": 1.4816, + "step": 2009 + }, + { + "epoch": 0.21, + "learning_rate": 1.9260875616300172e-05, + "loss": 1.4607, + "step": 2010 + }, + { + "epoch": 0.21, + "learning_rate": 1.9259493951898084e-05, + "loss": 1.628, + "step": 2011 + }, + { + "epoch": 0.21, + "learning_rate": 1.9258111046961714e-05, + "loss": 1.4149, + "step": 2012 + }, + { + "epoch": 0.21, + "learning_rate": 1.925672690167635e-05, + "loss": 1.5303, + "step": 2013 + }, + { + "epoch": 0.21, + "learning_rate": 1.925534151622742e-05, + "loss": 1.5198, + "step": 2014 + }, + { + "epoch": 0.21, + "learning_rate": 1.9253954890800535e-05, + "loss": 1.6422, + "step": 2015 + }, + { + "epoch": 0.21, + "learning_rate": 1.925256702558147e-05, + "loss": 1.4738, + "step": 2016 + }, + { + "epoch": 0.21, + "learning_rate": 1.925117792075616e-05, + "loss": 1.4752, + "step": 2017 + }, + { + "epoch": 0.21, + "learning_rate": 1.9249787576510713e-05, + "loss": 1.4547, + "step": 2018 + }, + { + "epoch": 0.21, + "learning_rate": 1.924839599303139e-05, + "loss": 1.4864, + "step": 2019 + }, + { + "epoch": 0.21, + "learning_rate": 1.9247003170504638e-05, + "loss": 1.5037, + "step": 2020 + }, + { + "epoch": 0.21, + "learning_rate": 1.9245609109117053e-05, + "loss": 1.5089, + "step": 2021 + }, + { + "epoch": 0.21, + "learning_rate": 1.924421380905541e-05, + "loss": 1.5616, + "step": 2022 + }, + { + "epoch": 0.21, + "learning_rate": 1.9242817270506634e-05, + "loss": 1.4592, + "step": 2023 + }, + { + "epoch": 0.21, + "learning_rate": 1.9241419493657832e-05, + "loss": 1.5592, + "step": 2024 + }, + { + "epoch": 0.21, + "learning_rate": 1.924002047869627e-05, + "loss": 1.4897, + "step": 2025 + }, + { + "epoch": 0.21, + "learning_rate": 1.9238620225809375e-05, + "loss": 1.4743, + "step": 2026 + }, + { + "epoch": 0.21, + "learning_rate": 1.923721873518475e-05, + "loss": 1.4686, + "step": 2027 + }, + { + "epoch": 0.21, + "learning_rate": 1.923581600701016e-05, + "loss": 1.461, + "step": 2028 + }, + { + "epoch": 0.21, + "learning_rate": 1.9234412041473528e-05, + "loss": 1.6622, + "step": 2029 + }, + { + "epoch": 0.21, + "learning_rate": 1.9233006838762955e-05, + "loss": 1.4707, + "step": 2030 + }, + { + "epoch": 0.21, + "learning_rate": 1.92316003990667e-05, + "loss": 1.5566, + "step": 2031 + }, + { + "epoch": 0.21, + "learning_rate": 1.9230192722573188e-05, + "loss": 1.4881, + "step": 2032 + }, + { + "epoch": 0.21, + "learning_rate": 1.9228783809471015e-05, + "loss": 1.6124, + "step": 2033 + }, + { + "epoch": 0.21, + "learning_rate": 1.9227373659948937e-05, + "loss": 1.3508, + "step": 2034 + }, + { + "epoch": 0.21, + "learning_rate": 1.9225962274195876e-05, + "loss": 1.4418, + "step": 2035 + }, + { + "epoch": 0.21, + "learning_rate": 1.9224549652400927e-05, + "loss": 1.3954, + "step": 2036 + }, + { + "epoch": 0.21, + "learning_rate": 1.922313579475334e-05, + "loss": 1.4798, + "step": 2037 + }, + { + "epoch": 0.21, + "learning_rate": 1.922172070144254e-05, + "loss": 1.4556, + "step": 2038 + }, + { + "epoch": 0.21, + "learning_rate": 1.922030437265811e-05, + "loss": 1.4987, + "step": 2039 + }, + { + "epoch": 0.21, + "learning_rate": 1.9218886808589796e-05, + "loss": 1.4857, + "step": 2040 + }, + { + "epoch": 0.21, + "learning_rate": 1.9217468009427527e-05, + "loss": 1.5289, + "step": 2041 + }, + { + "epoch": 0.21, + "learning_rate": 1.921604797536138e-05, + "loss": 1.5267, + "step": 2042 + }, + { + "epoch": 0.21, + "learning_rate": 1.9214626706581598e-05, + "loss": 1.4655, + "step": 2043 + }, + { + "epoch": 0.21, + "learning_rate": 1.9213204203278602e-05, + "loss": 1.4598, + "step": 2044 + }, + { + "epoch": 0.21, + "learning_rate": 1.9211780465642973e-05, + "loss": 1.4766, + "step": 2045 + }, + { + "epoch": 0.21, + "learning_rate": 1.921035549386545e-05, + "loss": 1.5148, + "step": 2046 + }, + { + "epoch": 0.21, + "learning_rate": 1.9208929288136933e-05, + "loss": 1.5567, + "step": 2047 + }, + { + "epoch": 0.21, + "learning_rate": 1.920750184864852e-05, + "loss": 1.4868, + "step": 2048 + }, + { + "epoch": 0.21, + "learning_rate": 1.920607317559143e-05, + "loss": 1.4752, + "step": 2049 + }, + { + "epoch": 0.21, + "learning_rate": 1.920464326915708e-05, + "loss": 1.4882, + "step": 2050 + }, + { + "epoch": 0.22, + "learning_rate": 1.9203212129537035e-05, + "loss": 1.5933, + "step": 2051 + }, + { + "epoch": 0.22, + "learning_rate": 1.9201779756923037e-05, + "loss": 1.4891, + "step": 2052 + }, + { + "epoch": 0.22, + "learning_rate": 1.9200346151506983e-05, + "loss": 1.4486, + "step": 2053 + }, + { + "epoch": 0.22, + "learning_rate": 1.9198911313480938e-05, + "loss": 1.5091, + "step": 2054 + }, + { + "epoch": 0.22, + "learning_rate": 1.919747524303714e-05, + "loss": 1.4385, + "step": 2055 + }, + { + "epoch": 0.22, + "learning_rate": 1.9196037940367974e-05, + "loss": 1.4104, + "step": 2056 + }, + { + "epoch": 0.22, + "learning_rate": 1.9194599405666015e-05, + "loss": 1.4483, + "step": 2057 + }, + { + "epoch": 0.22, + "learning_rate": 1.9193159639123976e-05, + "loss": 1.4592, + "step": 2058 + }, + { + "epoch": 0.22, + "learning_rate": 1.919171864093476e-05, + "loss": 1.4975, + "step": 2059 + }, + { + "epoch": 0.22, + "learning_rate": 1.9190276411291423e-05, + "loss": 1.4727, + "step": 2060 + }, + { + "epoch": 0.22, + "learning_rate": 1.9188832950387178e-05, + "loss": 1.4791, + "step": 2061 + }, + { + "epoch": 0.22, + "learning_rate": 1.9187388258415423e-05, + "loss": 1.3806, + "step": 2062 + }, + { + "epoch": 0.22, + "learning_rate": 1.9185942335569697e-05, + "loss": 1.4514, + "step": 2063 + }, + { + "epoch": 0.22, + "learning_rate": 1.9184495182043727e-05, + "loss": 1.4389, + "step": 2064 + }, + { + "epoch": 0.22, + "learning_rate": 1.918304679803139e-05, + "loss": 1.5088, + "step": 2065 + }, + { + "epoch": 0.22, + "learning_rate": 1.9181597183726733e-05, + "loss": 1.4665, + "step": 2066 + }, + { + "epoch": 0.22, + "learning_rate": 1.9180146339323966e-05, + "loss": 1.489, + "step": 2067 + }, + { + "epoch": 0.22, + "learning_rate": 1.9178694265017466e-05, + "loss": 1.5215, + "step": 2068 + }, + { + "epoch": 0.22, + "learning_rate": 1.9177240961001775e-05, + "loss": 1.5152, + "step": 2069 + }, + { + "epoch": 0.22, + "learning_rate": 1.9175786427471594e-05, + "loss": 1.4418, + "step": 2070 + }, + { + "epoch": 0.22, + "learning_rate": 1.91743306646218e-05, + "loss": 1.5001, + "step": 2071 + }, + { + "epoch": 0.22, + "learning_rate": 1.9172873672647417e-05, + "loss": 1.4879, + "step": 2072 + }, + { + "epoch": 0.22, + "learning_rate": 1.917141545174366e-05, + "loss": 1.5299, + "step": 2073 + }, + { + "epoch": 0.22, + "learning_rate": 1.9169956002105877e-05, + "loss": 1.4602, + "step": 2074 + }, + { + "epoch": 0.22, + "learning_rate": 1.9168495323929605e-05, + "loss": 1.4921, + "step": 2075 + }, + { + "epoch": 0.22, + "learning_rate": 1.916703341741054e-05, + "loss": 1.4659, + "step": 2076 + }, + { + "epoch": 0.22, + "learning_rate": 1.9165570282744534e-05, + "loss": 1.4707, + "step": 2077 + }, + { + "epoch": 0.22, + "learning_rate": 1.9164105920127613e-05, + "loss": 1.5354, + "step": 2078 + }, + { + "epoch": 0.22, + "learning_rate": 1.9162640329755962e-05, + "loss": 1.526, + "step": 2079 + }, + { + "epoch": 0.22, + "learning_rate": 1.916117351182593e-05, + "loss": 1.6424, + "step": 2080 + }, + { + "epoch": 0.22, + "learning_rate": 1.915970546653404e-05, + "loss": 1.5048, + "step": 2081 + }, + { + "epoch": 0.22, + "learning_rate": 1.915823619407697e-05, + "loss": 1.5344, + "step": 2082 + }, + { + "epoch": 0.22, + "learning_rate": 1.915676569465156e-05, + "loss": 1.4604, + "step": 2083 + }, + { + "epoch": 0.22, + "learning_rate": 1.9155293968454826e-05, + "loss": 1.4929, + "step": 2084 + }, + { + "epoch": 0.22, + "learning_rate": 1.9153821015683937e-05, + "loss": 1.4106, + "step": 2085 + }, + { + "epoch": 0.22, + "learning_rate": 1.915234683653623e-05, + "loss": 1.4146, + "step": 2086 + }, + { + "epoch": 0.22, + "learning_rate": 1.9150871431209207e-05, + "loss": 1.4481, + "step": 2087 + }, + { + "epoch": 0.22, + "learning_rate": 1.914939479990054e-05, + "loss": 1.5206, + "step": 2088 + }, + { + "epoch": 0.22, + "learning_rate": 1.9147916942808054e-05, + "loss": 1.5073, + "step": 2089 + }, + { + "epoch": 0.22, + "learning_rate": 1.9146437860129745e-05, + "loss": 1.5196, + "step": 2090 + }, + { + "epoch": 0.22, + "learning_rate": 1.9144957552063775e-05, + "loss": 1.5389, + "step": 2091 + }, + { + "epoch": 0.22, + "learning_rate": 1.9143476018808463e-05, + "loss": 1.5207, + "step": 2092 + }, + { + "epoch": 0.22, + "learning_rate": 1.9141993260562298e-05, + "loss": 1.3717, + "step": 2093 + }, + { + "epoch": 0.22, + "learning_rate": 1.9140509277523937e-05, + "loss": 1.471, + "step": 2094 + }, + { + "epoch": 0.22, + "learning_rate": 1.9139024069892185e-05, + "loss": 1.4553, + "step": 2095 + }, + { + "epoch": 0.22, + "learning_rate": 1.9137537637866027e-05, + "loss": 1.5311, + "step": 2096 + }, + { + "epoch": 0.22, + "learning_rate": 1.9136049981644614e-05, + "loss": 1.4369, + "step": 2097 + }, + { + "epoch": 0.22, + "learning_rate": 1.913456110142724e-05, + "loss": 1.4528, + "step": 2098 + }, + { + "epoch": 0.22, + "learning_rate": 1.9133070997413384e-05, + "loss": 1.5294, + "step": 2099 + }, + { + "epoch": 0.22, + "learning_rate": 1.9131579669802685e-05, + "loss": 1.4588, + "step": 2100 + }, + { + "epoch": 0.22, + "learning_rate": 1.9130087118794934e-05, + "loss": 1.443, + "step": 2101 + }, + { + "epoch": 0.22, + "learning_rate": 1.9128593344590102e-05, + "loss": 1.4876, + "step": 2102 + }, + { + "epoch": 0.22, + "learning_rate": 1.912709834738831e-05, + "loss": 1.4874, + "step": 2103 + }, + { + "epoch": 0.22, + "learning_rate": 1.9125602127389856e-05, + "loss": 1.4966, + "step": 2104 + }, + { + "epoch": 0.22, + "learning_rate": 1.912410468479519e-05, + "loss": 1.5747, + "step": 2105 + }, + { + "epoch": 0.22, + "learning_rate": 1.9122606019804933e-05, + "loss": 1.4025, + "step": 2106 + }, + { + "epoch": 0.22, + "learning_rate": 1.912110613261987e-05, + "loss": 1.4755, + "step": 2107 + }, + { + "epoch": 0.22, + "learning_rate": 1.911960502344094e-05, + "loss": 1.4739, + "step": 2108 + }, + { + "epoch": 0.22, + "learning_rate": 1.911810269246926e-05, + "loss": 1.4992, + "step": 2109 + }, + { + "epoch": 0.22, + "learning_rate": 1.91165991399061e-05, + "loss": 1.4435, + "step": 2110 + }, + { + "epoch": 0.22, + "learning_rate": 1.91150943659529e-05, + "loss": 1.4918, + "step": 2111 + }, + { + "epoch": 0.22, + "learning_rate": 1.9113588370811258e-05, + "loss": 1.3818, + "step": 2112 + }, + { + "epoch": 0.22, + "learning_rate": 1.911208115468294e-05, + "loss": 1.5105, + "step": 2113 + }, + { + "epoch": 0.22, + "learning_rate": 1.9110572717769878e-05, + "loss": 1.6634, + "step": 2114 + }, + { + "epoch": 0.22, + "learning_rate": 1.9109063060274158e-05, + "loss": 1.5028, + "step": 2115 + }, + { + "epoch": 0.22, + "learning_rate": 1.9107552182398037e-05, + "loss": 1.6657, + "step": 2116 + }, + { + "epoch": 0.22, + "learning_rate": 1.9106040084343935e-05, + "loss": 1.5481, + "step": 2117 + }, + { + "epoch": 0.22, + "learning_rate": 1.910452676631444e-05, + "loss": 1.4505, + "step": 2118 + }, + { + "epoch": 0.22, + "learning_rate": 1.9103012228512284e-05, + "loss": 1.5173, + "step": 2119 + }, + { + "epoch": 0.22, + "learning_rate": 1.9101496471140385e-05, + "loss": 1.3788, + "step": 2120 + }, + { + "epoch": 0.22, + "learning_rate": 1.9099979494401814e-05, + "loss": 1.4649, + "step": 2121 + }, + { + "epoch": 0.22, + "learning_rate": 1.9098461298499805e-05, + "loss": 1.4204, + "step": 2122 + }, + { + "epoch": 0.22, + "learning_rate": 1.9096941883637766e-05, + "loss": 1.4439, + "step": 2123 + }, + { + "epoch": 0.22, + "learning_rate": 1.909542125001925e-05, + "loss": 1.6615, + "step": 2124 + }, + { + "epoch": 0.22, + "learning_rate": 1.9093899397847985e-05, + "loss": 1.4763, + "step": 2125 + }, + { + "epoch": 0.22, + "learning_rate": 1.909237632732786e-05, + "loss": 1.5353, + "step": 2126 + }, + { + "epoch": 0.22, + "learning_rate": 1.909085203866293e-05, + "loss": 1.442, + "step": 2127 + }, + { + "epoch": 0.22, + "learning_rate": 1.9089326532057408e-05, + "loss": 1.4782, + "step": 2128 + }, + { + "epoch": 0.22, + "learning_rate": 1.908779980771567e-05, + "loss": 1.4933, + "step": 2129 + }, + { + "epoch": 0.22, + "learning_rate": 1.9086271865842264e-05, + "loss": 1.5285, + "step": 2130 + }, + { + "epoch": 0.22, + "learning_rate": 1.9084742706641894e-05, + "loss": 1.4736, + "step": 2131 + }, + { + "epoch": 0.22, + "learning_rate": 1.9083212330319427e-05, + "loss": 1.4496, + "step": 2132 + }, + { + "epoch": 0.22, + "learning_rate": 1.908168073707989e-05, + "loss": 1.5099, + "step": 2133 + }, + { + "epoch": 0.22, + "learning_rate": 1.9080147927128483e-05, + "loss": 1.5235, + "step": 2134 + }, + { + "epoch": 0.22, + "learning_rate": 1.9078613900670556e-05, + "loss": 1.4769, + "step": 2135 + }, + { + "epoch": 0.22, + "learning_rate": 1.907707865791164e-05, + "loss": 1.5771, + "step": 2136 + }, + { + "epoch": 0.22, + "learning_rate": 1.907554219905741e-05, + "loss": 1.5116, + "step": 2137 + }, + { + "epoch": 0.22, + "learning_rate": 1.907400452431371e-05, + "loss": 1.5161, + "step": 2138 + }, + { + "epoch": 0.22, + "learning_rate": 1.9072465633886557e-05, + "loss": 1.4356, + "step": 2139 + }, + { + "epoch": 0.22, + "learning_rate": 1.9070925527982117e-05, + "loss": 1.509, + "step": 2140 + }, + { + "epoch": 0.22, + "learning_rate": 1.9069384206806723e-05, + "loss": 1.4681, + "step": 2141 + }, + { + "epoch": 0.22, + "learning_rate": 1.9067841670566883e-05, + "loss": 1.5254, + "step": 2142 + }, + { + "epoch": 0.22, + "learning_rate": 1.9066297919469242e-05, + "loss": 1.4797, + "step": 2143 + }, + { + "epoch": 0.22, + "learning_rate": 1.9064752953720636e-05, + "loss": 1.3996, + "step": 2144 + }, + { + "epoch": 0.22, + "learning_rate": 1.9063206773528042e-05, + "loss": 1.4457, + "step": 2145 + }, + { + "epoch": 0.23, + "learning_rate": 1.9061659379098617e-05, + "loss": 1.5126, + "step": 2146 + }, + { + "epoch": 0.23, + "learning_rate": 1.9060110770639664e-05, + "loss": 1.5925, + "step": 2147 + }, + { + "epoch": 0.23, + "learning_rate": 1.905856094835866e-05, + "loss": 1.5146, + "step": 2148 + }, + { + "epoch": 0.23, + "learning_rate": 1.905700991246324e-05, + "loss": 1.7256, + "step": 2149 + }, + { + "epoch": 0.23, + "learning_rate": 1.90554576631612e-05, + "loss": 1.57, + "step": 2150 + }, + { + "epoch": 0.23, + "learning_rate": 1.905390420066051e-05, + "loss": 1.3722, + "step": 2151 + }, + { + "epoch": 0.23, + "learning_rate": 1.9052349525169292e-05, + "loss": 1.3999, + "step": 2152 + }, + { + "epoch": 0.23, + "learning_rate": 1.9050793636895828e-05, + "loss": 1.586, + "step": 2153 + }, + { + "epoch": 0.23, + "learning_rate": 1.9049236536048567e-05, + "loss": 1.4884, + "step": 2154 + }, + { + "epoch": 0.23, + "learning_rate": 1.9047678222836127e-05, + "loss": 1.5898, + "step": 2155 + }, + { + "epoch": 0.23, + "learning_rate": 1.9046118697467278e-05, + "loss": 1.569, + "step": 2156 + }, + { + "epoch": 0.23, + "learning_rate": 1.904455796015095e-05, + "loss": 1.5592, + "step": 2157 + }, + { + "epoch": 0.23, + "learning_rate": 1.9042996011096253e-05, + "loss": 1.597, + "step": 2158 + }, + { + "epoch": 0.23, + "learning_rate": 1.904143285051244e-05, + "loss": 1.422, + "step": 2159 + }, + { + "epoch": 0.23, + "learning_rate": 1.903986847860894e-05, + "loss": 1.519, + "step": 2160 + }, + { + "epoch": 0.23, + "learning_rate": 1.9038302895595334e-05, + "loss": 1.5197, + "step": 2161 + }, + { + "epoch": 0.23, + "learning_rate": 1.903673610168137e-05, + "loss": 1.4655, + "step": 2162 + }, + { + "epoch": 0.23, + "learning_rate": 1.9035168097076965e-05, + "loss": 1.3909, + "step": 2163 + }, + { + "epoch": 0.23, + "learning_rate": 1.903359888199218e-05, + "loss": 1.4877, + "step": 2164 + }, + { + "epoch": 0.23, + "learning_rate": 1.903202845663726e-05, + "loss": 1.5123, + "step": 2165 + }, + { + "epoch": 0.23, + "learning_rate": 1.9030456821222593e-05, + "loss": 1.4906, + "step": 2166 + }, + { + "epoch": 0.23, + "learning_rate": 1.9028883975958745e-05, + "loss": 1.4574, + "step": 2167 + }, + { + "epoch": 0.23, + "learning_rate": 1.9027309921056435e-05, + "loss": 1.4571, + "step": 2168 + }, + { + "epoch": 0.23, + "learning_rate": 1.902573465672654e-05, + "loss": 1.4281, + "step": 2169 + }, + { + "epoch": 0.23, + "learning_rate": 1.9024158183180116e-05, + "loss": 1.5057, + "step": 2170 + }, + { + "epoch": 0.23, + "learning_rate": 1.902258050062836e-05, + "loss": 1.4514, + "step": 2171 + }, + { + "epoch": 0.23, + "learning_rate": 1.9021001609282646e-05, + "loss": 1.5055, + "step": 2172 + }, + { + "epoch": 0.23, + "learning_rate": 1.9019421509354505e-05, + "loss": 1.4578, + "step": 2173 + }, + { + "epoch": 0.23, + "learning_rate": 1.9017840201055625e-05, + "loss": 1.459, + "step": 2174 + }, + { + "epoch": 0.23, + "learning_rate": 1.9016257684597864e-05, + "loss": 1.5059, + "step": 2175 + }, + { + "epoch": 0.23, + "learning_rate": 1.901467396019324e-05, + "loss": 1.57, + "step": 2176 + }, + { + "epoch": 0.23, + "learning_rate": 1.901308902805393e-05, + "loss": 1.4924, + "step": 2177 + }, + { + "epoch": 0.23, + "learning_rate": 1.9011502888392273e-05, + "loss": 1.4979, + "step": 2178 + }, + { + "epoch": 0.23, + "learning_rate": 1.900991554142077e-05, + "loss": 1.5321, + "step": 2179 + }, + { + "epoch": 0.23, + "learning_rate": 1.9008326987352093e-05, + "loss": 1.493, + "step": 2180 + }, + { + "epoch": 0.23, + "learning_rate": 1.9006737226399056e-05, + "loss": 1.5111, + "step": 2181 + }, + { + "epoch": 0.23, + "learning_rate": 1.900514625877465e-05, + "loss": 1.4154, + "step": 2182 + }, + { + "epoch": 0.23, + "learning_rate": 1.900355408469203e-05, + "loss": 1.4934, + "step": 2183 + }, + { + "epoch": 0.23, + "learning_rate": 1.90019607043645e-05, + "loss": 1.5975, + "step": 2184 + }, + { + "epoch": 0.23, + "learning_rate": 1.9000366118005532e-05, + "loss": 1.3537, + "step": 2185 + }, + { + "epoch": 0.23, + "learning_rate": 1.899877032582876e-05, + "loss": 1.4583, + "step": 2186 + }, + { + "epoch": 0.23, + "learning_rate": 1.8997173328047984e-05, + "loss": 1.4586, + "step": 2187 + }, + { + "epoch": 0.23, + "learning_rate": 1.8995575124877156e-05, + "loss": 1.4774, + "step": 2188 + }, + { + "epoch": 0.23, + "learning_rate": 1.8993975716530394e-05, + "loss": 1.5025, + "step": 2189 + }, + { + "epoch": 0.23, + "eval_loss": 1.5263344049453735, + "eval_runtime": 77.1492, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 2189 + }, + { + "epoch": 0.23, + "learning_rate": 1.899237510322198e-05, + "loss": 1.5438, + "step": 2190 + }, + { + "epoch": 0.23, + "learning_rate": 1.899077328516635e-05, + "loss": 1.5181, + "step": 2191 + }, + { + "epoch": 0.23, + "learning_rate": 1.8989170262578112e-05, + "loss": 1.4454, + "step": 2192 + }, + { + "epoch": 0.23, + "learning_rate": 1.8987566035672028e-05, + "loss": 1.4882, + "step": 2193 + }, + { + "epoch": 0.23, + "learning_rate": 1.8985960604663026e-05, + "loss": 1.5073, + "step": 2194 + }, + { + "epoch": 0.23, + "learning_rate": 1.8984353969766187e-05, + "loss": 1.4478, + "step": 2195 + }, + { + "epoch": 0.23, + "learning_rate": 1.8982746131196763e-05, + "loss": 1.4768, + "step": 2196 + }, + { + "epoch": 0.23, + "learning_rate": 1.8981137089170162e-05, + "loss": 1.5116, + "step": 2197 + }, + { + "epoch": 0.23, + "learning_rate": 1.8979526843901952e-05, + "loss": 1.4202, + "step": 2198 + }, + { + "epoch": 0.23, + "learning_rate": 1.8977915395607867e-05, + "loss": 1.4736, + "step": 2199 + }, + { + "epoch": 0.23, + "learning_rate": 1.89763027445038e-05, + "loss": 1.4489, + "step": 2200 + }, + { + "epoch": 0.23, + "learning_rate": 1.8974688890805804e-05, + "loss": 1.4512, + "step": 2201 + }, + { + "epoch": 0.23, + "learning_rate": 1.897307383473009e-05, + "loss": 1.5091, + "step": 2202 + }, + { + "epoch": 0.23, + "learning_rate": 1.897145757649304e-05, + "loss": 1.5512, + "step": 2203 + }, + { + "epoch": 0.23, + "learning_rate": 1.8969840116311192e-05, + "loss": 1.406, + "step": 2204 + }, + { + "epoch": 0.23, + "learning_rate": 1.896822145440124e-05, + "loss": 1.4531, + "step": 2205 + }, + { + "epoch": 0.23, + "learning_rate": 1.896660159098004e-05, + "loss": 1.4379, + "step": 2206 + }, + { + "epoch": 0.23, + "learning_rate": 1.896498052626462e-05, + "loss": 1.4783, + "step": 2207 + }, + { + "epoch": 0.23, + "learning_rate": 1.896335826047216e-05, + "loss": 1.4801, + "step": 2208 + }, + { + "epoch": 0.23, + "learning_rate": 1.896173479381999e-05, + "loss": 1.4526, + "step": 2209 + }, + { + "epoch": 0.23, + "learning_rate": 1.8960110126525627e-05, + "loss": 1.4952, + "step": 2210 + }, + { + "epoch": 0.23, + "learning_rate": 1.895848425880673e-05, + "loss": 1.5299, + "step": 2211 + }, + { + "epoch": 0.23, + "learning_rate": 1.8956857190881125e-05, + "loss": 1.5274, + "step": 2212 + }, + { + "epoch": 0.23, + "learning_rate": 1.8955228922966792e-05, + "loss": 1.4415, + "step": 2213 + }, + { + "epoch": 0.23, + "learning_rate": 1.8953599455281884e-05, + "loss": 1.5311, + "step": 2214 + }, + { + "epoch": 0.23, + "learning_rate": 1.8951968788044702e-05, + "loss": 1.4972, + "step": 2215 + }, + { + "epoch": 0.23, + "learning_rate": 1.8950336921473715e-05, + "loss": 1.4966, + "step": 2216 + }, + { + "epoch": 0.23, + "learning_rate": 1.8948703855787553e-05, + "loss": 1.4683, + "step": 2217 + }, + { + "epoch": 0.23, + "learning_rate": 1.8947069591205005e-05, + "loss": 1.503, + "step": 2218 + }, + { + "epoch": 0.23, + "learning_rate": 1.8945434127945014e-05, + "loss": 1.4902, + "step": 2219 + }, + { + "epoch": 0.23, + "learning_rate": 1.8943797466226702e-05, + "loss": 1.4835, + "step": 2220 + }, + { + "epoch": 0.23, + "learning_rate": 1.8942159606269332e-05, + "loss": 1.535, + "step": 2221 + }, + { + "epoch": 0.23, + "learning_rate": 1.8940520548292332e-05, + "loss": 1.491, + "step": 2222 + }, + { + "epoch": 0.23, + "learning_rate": 1.89388802925153e-05, + "loss": 1.5157, + "step": 2223 + }, + { + "epoch": 0.23, + "learning_rate": 1.8937238839157987e-05, + "loss": 1.4779, + "step": 2224 + }, + { + "epoch": 0.23, + "learning_rate": 1.8935596188440302e-05, + "loss": 1.4902, + "step": 2225 + }, + { + "epoch": 0.23, + "learning_rate": 1.8933952340582323e-05, + "loss": 1.4988, + "step": 2226 + }, + { + "epoch": 0.23, + "learning_rate": 1.893230729580428e-05, + "loss": 1.4568, + "step": 2227 + }, + { + "epoch": 0.23, + "learning_rate": 1.8930661054326567e-05, + "loss": 1.5163, + "step": 2228 + }, + { + "epoch": 0.23, + "learning_rate": 1.892901361636974e-05, + "loss": 1.4472, + "step": 2229 + }, + { + "epoch": 0.23, + "learning_rate": 1.892736498215451e-05, + "loss": 1.4658, + "step": 2230 + }, + { + "epoch": 0.23, + "learning_rate": 1.8925715151901754e-05, + "loss": 1.4281, + "step": 2231 + }, + { + "epoch": 0.23, + "learning_rate": 1.892406412583251e-05, + "loss": 1.415, + "step": 2232 + }, + { + "epoch": 0.23, + "learning_rate": 1.8922411904167966e-05, + "loss": 1.464, + "step": 2233 + }, + { + "epoch": 0.23, + "learning_rate": 1.892075848712948e-05, + "loss": 1.5014, + "step": 2234 + }, + { + "epoch": 0.23, + "learning_rate": 1.8919103874938568e-05, + "loss": 1.4397, + "step": 2235 + }, + { + "epoch": 0.23, + "learning_rate": 1.891744806781691e-05, + "loss": 1.5508, + "step": 2236 + }, + { + "epoch": 0.23, + "learning_rate": 1.8915791065986335e-05, + "loss": 1.4749, + "step": 2237 + }, + { + "epoch": 0.23, + "learning_rate": 1.891413286966884e-05, + "loss": 1.4538, + "step": 2238 + }, + { + "epoch": 0.23, + "learning_rate": 1.891247347908658e-05, + "loss": 1.4405, + "step": 2239 + }, + { + "epoch": 0.23, + "learning_rate": 1.8910812894461878e-05, + "loss": 1.3562, + "step": 2240 + }, + { + "epoch": 0.24, + "learning_rate": 1.89091511160172e-05, + "loss": 1.4811, + "step": 2241 + }, + { + "epoch": 0.24, + "learning_rate": 1.8907488143975186e-05, + "loss": 1.4286, + "step": 2242 + }, + { + "epoch": 0.24, + "learning_rate": 1.890582397855863e-05, + "loss": 1.4493, + "step": 2243 + }, + { + "epoch": 0.24, + "learning_rate": 1.890415861999049e-05, + "loss": 1.5639, + "step": 2244 + }, + { + "epoch": 0.24, + "learning_rate": 1.890249206849388e-05, + "loss": 1.6375, + "step": 2245 + }, + { + "epoch": 0.24, + "learning_rate": 1.890082432429208e-05, + "loss": 1.4982, + "step": 2246 + }, + { + "epoch": 0.24, + "learning_rate": 1.889915538760851e-05, + "loss": 1.492, + "step": 2247 + }, + { + "epoch": 0.24, + "learning_rate": 1.8897485258666778e-05, + "loss": 1.4294, + "step": 2248 + }, + { + "epoch": 0.24, + "learning_rate": 1.8895813937690638e-05, + "loss": 1.4617, + "step": 2249 + }, + { + "epoch": 0.24, + "learning_rate": 1.8894141424904e-05, + "loss": 1.4763, + "step": 2250 + }, + { + "epoch": 0.24, + "learning_rate": 1.8892467720530937e-05, + "loss": 1.3989, + "step": 2251 + }, + { + "epoch": 0.24, + "learning_rate": 1.8890792824795687e-05, + "loss": 1.4803, + "step": 2252 + }, + { + "epoch": 0.24, + "learning_rate": 1.8889116737922638e-05, + "loss": 1.4734, + "step": 2253 + }, + { + "epoch": 0.24, + "learning_rate": 1.8887439460136342e-05, + "loss": 1.5069, + "step": 2254 + }, + { + "epoch": 0.24, + "learning_rate": 1.8885760991661514e-05, + "loss": 1.5565, + "step": 2255 + }, + { + "epoch": 0.24, + "learning_rate": 1.8884081332723028e-05, + "loss": 1.4707, + "step": 2256 + }, + { + "epoch": 0.24, + "learning_rate": 1.8882400483545913e-05, + "loss": 1.5077, + "step": 2257 + }, + { + "epoch": 0.24, + "learning_rate": 1.888071844435536e-05, + "loss": 1.5075, + "step": 2258 + }, + { + "epoch": 0.24, + "learning_rate": 1.8879035215376717e-05, + "loss": 1.5185, + "step": 2259 + }, + { + "epoch": 0.24, + "learning_rate": 1.887735079683549e-05, + "loss": 1.6266, + "step": 2260 + }, + { + "epoch": 0.24, + "learning_rate": 1.8875665188957354e-05, + "loss": 1.5013, + "step": 2261 + }, + { + "epoch": 0.24, + "learning_rate": 1.887397839196814e-05, + "loss": 1.4362, + "step": 2262 + }, + { + "epoch": 0.24, + "learning_rate": 1.8872290406093827e-05, + "loss": 1.4718, + "step": 2263 + }, + { + "epoch": 0.24, + "learning_rate": 1.8870601231560567e-05, + "loss": 1.5202, + "step": 2264 + }, + { + "epoch": 0.24, + "learning_rate": 1.8868910868594664e-05, + "loss": 1.5168, + "step": 2265 + }, + { + "epoch": 0.24, + "learning_rate": 1.8867219317422588e-05, + "loss": 1.5142, + "step": 2266 + }, + { + "epoch": 0.24, + "learning_rate": 1.8865526578270954e-05, + "loss": 1.4885, + "step": 2267 + }, + { + "epoch": 0.24, + "learning_rate": 1.8863832651366552e-05, + "loss": 1.5441, + "step": 2268 + }, + { + "epoch": 0.24, + "learning_rate": 1.8862137536936328e-05, + "loss": 1.4647, + "step": 2269 + }, + { + "epoch": 0.24, + "learning_rate": 1.8860441235207374e-05, + "loss": 1.5352, + "step": 2270 + }, + { + "epoch": 0.24, + "learning_rate": 1.8858743746406958e-05, + "loss": 1.4568, + "step": 2271 + }, + { + "epoch": 0.24, + "learning_rate": 1.8857045070762497e-05, + "loss": 1.4865, + "step": 2272 + }, + { + "epoch": 0.24, + "learning_rate": 1.8855345208501573e-05, + "loss": 1.4637, + "step": 2273 + }, + { + "epoch": 0.24, + "learning_rate": 1.8853644159851918e-05, + "loss": 1.4348, + "step": 2274 + }, + { + "epoch": 0.24, + "learning_rate": 1.8851941925041436e-05, + "loss": 1.4413, + "step": 2275 + }, + { + "epoch": 0.24, + "learning_rate": 1.8850238504298177e-05, + "loss": 1.4434, + "step": 2276 + }, + { + "epoch": 0.24, + "learning_rate": 1.884853389785036e-05, + "loss": 1.4822, + "step": 2277 + }, + { + "epoch": 0.24, + "learning_rate": 1.8846828105926356e-05, + "loss": 1.4632, + "step": 2278 + }, + { + "epoch": 0.24, + "learning_rate": 1.8845121128754698e-05, + "loss": 1.48, + "step": 2279 + }, + { + "epoch": 0.24, + "learning_rate": 1.8843412966564078e-05, + "loss": 1.4518, + "step": 2280 + }, + { + "epoch": 0.24, + "learning_rate": 1.884170361958334e-05, + "loss": 1.4334, + "step": 2281 + }, + { + "epoch": 0.24, + "learning_rate": 1.8839993088041502e-05, + "loss": 1.5131, + "step": 2282 + }, + { + "epoch": 0.24, + "learning_rate": 1.8838281372167724e-05, + "loss": 1.508, + "step": 2283 + }, + { + "epoch": 0.24, + "learning_rate": 1.8836568472191335e-05, + "loss": 1.4086, + "step": 2284 + }, + { + "epoch": 0.24, + "learning_rate": 1.883485438834182e-05, + "loss": 1.5021, + "step": 2285 + }, + { + "epoch": 0.24, + "learning_rate": 1.8833139120848817e-05, + "loss": 1.5083, + "step": 2286 + }, + { + "epoch": 0.24, + "learning_rate": 1.8831422669942137e-05, + "loss": 1.4162, + "step": 2287 + }, + { + "epoch": 0.24, + "learning_rate": 1.8829705035851734e-05, + "loss": 1.5494, + "step": 2288 + }, + { + "epoch": 0.24, + "learning_rate": 1.8827986218807724e-05, + "loss": 1.425, + "step": 2289 + }, + { + "epoch": 0.24, + "learning_rate": 1.8826266219040396e-05, + "loss": 1.5215, + "step": 2290 + }, + { + "epoch": 0.24, + "learning_rate": 1.8824545036780172e-05, + "loss": 1.5577, + "step": 2291 + }, + { + "epoch": 0.24, + "learning_rate": 1.8822822672257655e-05, + "loss": 1.4923, + "step": 2292 + }, + { + "epoch": 0.24, + "learning_rate": 1.8821099125703595e-05, + "loss": 1.4648, + "step": 2293 + }, + { + "epoch": 0.24, + "learning_rate": 1.8819374397348902e-05, + "loss": 1.471, + "step": 2294 + }, + { + "epoch": 0.24, + "learning_rate": 1.8817648487424648e-05, + "loss": 1.5658, + "step": 2295 + }, + { + "epoch": 0.24, + "learning_rate": 1.8815921396162058e-05, + "loss": 1.5348, + "step": 2296 + }, + { + "epoch": 0.24, + "learning_rate": 1.8814193123792518e-05, + "loss": 1.4081, + "step": 2297 + }, + { + "epoch": 0.24, + "learning_rate": 1.881246367054757e-05, + "loss": 1.4762, + "step": 2298 + }, + { + "epoch": 0.24, + "learning_rate": 1.8810733036658925e-05, + "loss": 1.4399, + "step": 2299 + }, + { + "epoch": 0.24, + "learning_rate": 1.8809001222358432e-05, + "loss": 1.4763, + "step": 2300 + }, + { + "epoch": 0.24, + "learning_rate": 1.880726822787812e-05, + "loss": 1.4874, + "step": 2301 + }, + { + "epoch": 0.24, + "learning_rate": 1.880553405345016e-05, + "loss": 1.4951, + "step": 2302 + }, + { + "epoch": 0.24, + "learning_rate": 1.8803798699306887e-05, + "loss": 1.4697, + "step": 2303 + }, + { + "epoch": 0.24, + "learning_rate": 1.880206216568079e-05, + "loss": 1.481, + "step": 2304 + }, + { + "epoch": 0.24, + "learning_rate": 1.880032445280453e-05, + "loss": 1.4485, + "step": 2305 + }, + { + "epoch": 0.24, + "learning_rate": 1.879858556091091e-05, + "loss": 1.4749, + "step": 2306 + }, + { + "epoch": 0.24, + "learning_rate": 1.8796845490232894e-05, + "loss": 1.5605, + "step": 2307 + }, + { + "epoch": 0.24, + "learning_rate": 1.879510424100361e-05, + "loss": 1.4835, + "step": 2308 + }, + { + "epoch": 0.24, + "learning_rate": 1.8793361813456346e-05, + "loss": 1.4344, + "step": 2309 + }, + { + "epoch": 0.24, + "learning_rate": 1.8791618207824532e-05, + "loss": 1.4571, + "step": 2310 + }, + { + "epoch": 0.24, + "learning_rate": 1.8789873424341772e-05, + "loss": 1.482, + "step": 2311 + }, + { + "epoch": 0.24, + "learning_rate": 1.8788127463241822e-05, + "loss": 1.4736, + "step": 2312 + }, + { + "epoch": 0.24, + "learning_rate": 1.8786380324758597e-05, + "loss": 1.4807, + "step": 2313 + }, + { + "epoch": 0.24, + "learning_rate": 1.8784632009126167e-05, + "loss": 1.4418, + "step": 2314 + }, + { + "epoch": 0.24, + "learning_rate": 1.878288251657876e-05, + "loss": 1.5248, + "step": 2315 + }, + { + "epoch": 0.24, + "learning_rate": 1.8781131847350768e-05, + "loss": 1.483, + "step": 2316 + }, + { + "epoch": 0.24, + "learning_rate": 1.877938000167673e-05, + "loss": 1.5474, + "step": 2317 + }, + { + "epoch": 0.24, + "learning_rate": 1.8777626979791347e-05, + "loss": 1.4671, + "step": 2318 + }, + { + "epoch": 0.24, + "learning_rate": 1.877587278192949e-05, + "loss": 1.3049, + "step": 2319 + }, + { + "epoch": 0.24, + "learning_rate": 1.877411740832616e-05, + "loss": 1.483, + "step": 2320 + }, + { + "epoch": 0.24, + "learning_rate": 1.877236085921655e-05, + "loss": 1.508, + "step": 2321 + }, + { + "epoch": 0.24, + "learning_rate": 1.8770603134835978e-05, + "loss": 1.4854, + "step": 2322 + }, + { + "epoch": 0.24, + "learning_rate": 1.8768844235419942e-05, + "loss": 1.4808, + "step": 2323 + }, + { + "epoch": 0.24, + "learning_rate": 1.8767084161204087e-05, + "loss": 1.5352, + "step": 2324 + }, + { + "epoch": 0.24, + "learning_rate": 1.8765322912424214e-05, + "loss": 1.5628, + "step": 2325 + }, + { + "epoch": 0.24, + "learning_rate": 1.8763560489316292e-05, + "loss": 1.494, + "step": 2326 + }, + { + "epoch": 0.24, + "learning_rate": 1.876179689211643e-05, + "loss": 1.509, + "step": 2327 + }, + { + "epoch": 0.24, + "learning_rate": 1.8760032121060918e-05, + "loss": 1.5021, + "step": 2328 + }, + { + "epoch": 0.24, + "learning_rate": 1.875826617638618e-05, + "loss": 1.4179, + "step": 2329 + }, + { + "epoch": 0.24, + "learning_rate": 1.8756499058328813e-05, + "loss": 1.4302, + "step": 2330 + }, + { + "epoch": 0.24, + "learning_rate": 1.8754730767125564e-05, + "loss": 1.4959, + "step": 2331 + }, + { + "epoch": 0.24, + "learning_rate": 1.8752961303013336e-05, + "loss": 1.4423, + "step": 2332 + }, + { + "epoch": 0.24, + "learning_rate": 1.8751190666229194e-05, + "loss": 1.4564, + "step": 2333 + }, + { + "epoch": 0.24, + "learning_rate": 1.8749418857010358e-05, + "loss": 1.4775, + "step": 2334 + }, + { + "epoch": 0.24, + "learning_rate": 1.8747645875594203e-05, + "loss": 1.4182, + "step": 2335 + }, + { + "epoch": 0.24, + "learning_rate": 1.8745871722218265e-05, + "loss": 1.3957, + "step": 2336 + }, + { + "epoch": 0.25, + "learning_rate": 1.8744096397120235e-05, + "loss": 1.4633, + "step": 2337 + }, + { + "epoch": 0.25, + "learning_rate": 1.874231990053796e-05, + "loss": 1.5512, + "step": 2338 + }, + { + "epoch": 0.25, + "learning_rate": 1.8740542232709444e-05, + "loss": 1.3461, + "step": 2339 + }, + { + "epoch": 0.25, + "learning_rate": 1.8738763393872848e-05, + "loss": 1.4754, + "step": 2340 + }, + { + "epoch": 0.25, + "learning_rate": 1.8736983384266495e-05, + "loss": 1.5448, + "step": 2341 + }, + { + "epoch": 0.25, + "learning_rate": 1.8735202204128854e-05, + "loss": 1.4491, + "step": 2342 + }, + { + "epoch": 0.25, + "learning_rate": 1.8733419853698566e-05, + "loss": 1.457, + "step": 2343 + }, + { + "epoch": 0.25, + "learning_rate": 1.8731636333214414e-05, + "loss": 1.4314, + "step": 2344 + }, + { + "epoch": 0.25, + "learning_rate": 1.8729851642915345e-05, + "loss": 1.3979, + "step": 2345 + }, + { + "epoch": 0.25, + "learning_rate": 1.8728065783040464e-05, + "loss": 1.4146, + "step": 2346 + }, + { + "epoch": 0.25, + "learning_rate": 1.8726278753829027e-05, + "loss": 1.4361, + "step": 2347 + }, + { + "epoch": 0.25, + "learning_rate": 1.872449055552045e-05, + "loss": 1.4989, + "step": 2348 + }, + { + "epoch": 0.25, + "learning_rate": 1.872270118835431e-05, + "loss": 1.5062, + "step": 2349 + }, + { + "epoch": 0.25, + "learning_rate": 1.872091065257033e-05, + "loss": 1.4509, + "step": 2350 + }, + { + "epoch": 0.25, + "learning_rate": 1.8719118948408403e-05, + "loss": 1.4631, + "step": 2351 + }, + { + "epoch": 0.25, + "learning_rate": 1.8717326076108566e-05, + "loss": 1.5119, + "step": 2352 + }, + { + "epoch": 0.25, + "learning_rate": 1.8715532035911017e-05, + "loss": 1.6347, + "step": 2353 + }, + { + "epoch": 0.25, + "learning_rate": 1.8713736828056115e-05, + "loss": 1.5526, + "step": 2354 + }, + { + "epoch": 0.25, + "learning_rate": 1.8711940452784368e-05, + "loss": 1.6348, + "step": 2355 + }, + { + "epoch": 0.25, + "learning_rate": 1.871014291033645e-05, + "loss": 1.5183, + "step": 2356 + }, + { + "epoch": 0.25, + "learning_rate": 1.8708344200953182e-05, + "loss": 1.458, + "step": 2357 + }, + { + "epoch": 0.25, + "learning_rate": 1.8706544324875545e-05, + "loss": 1.524, + "step": 2358 + }, + { + "epoch": 0.25, + "learning_rate": 1.8704743282344672e-05, + "loss": 1.4479, + "step": 2359 + }, + { + "epoch": 0.25, + "learning_rate": 1.870294107360186e-05, + "loss": 1.5408, + "step": 2360 + }, + { + "epoch": 0.25, + "learning_rate": 1.8701137698888563e-05, + "loss": 1.5007, + "step": 2361 + }, + { + "epoch": 0.25, + "learning_rate": 1.8699333158446382e-05, + "loss": 1.5132, + "step": 2362 + }, + { + "epoch": 0.25, + "learning_rate": 1.869752745251708e-05, + "loss": 1.4263, + "step": 2363 + }, + { + "epoch": 0.25, + "learning_rate": 1.8695720581342574e-05, + "loss": 1.422, + "step": 2364 + }, + { + "epoch": 0.25, + "learning_rate": 1.869391254516494e-05, + "loss": 1.4411, + "step": 2365 + }, + { + "epoch": 0.25, + "learning_rate": 1.8692103344226406e-05, + "loss": 1.4594, + "step": 2366 + }, + { + "epoch": 0.25, + "learning_rate": 1.8690292978769364e-05, + "loss": 1.4992, + "step": 2367 + }, + { + "epoch": 0.25, + "learning_rate": 1.868848144903635e-05, + "loss": 1.4822, + "step": 2368 + }, + { + "epoch": 0.25, + "learning_rate": 1.8686668755270064e-05, + "loss": 1.5402, + "step": 2369 + }, + { + "epoch": 0.25, + "learning_rate": 1.8684854897713363e-05, + "loss": 1.5268, + "step": 2370 + }, + { + "epoch": 0.25, + "learning_rate": 1.8683039876609258e-05, + "loss": 1.5587, + "step": 2371 + }, + { + "epoch": 0.25, + "learning_rate": 1.868122369220091e-05, + "loss": 1.4214, + "step": 2372 + }, + { + "epoch": 0.25, + "learning_rate": 1.8679406344731645e-05, + "loss": 1.5089, + "step": 2373 + }, + { + "epoch": 0.25, + "learning_rate": 1.867758783444494e-05, + "loss": 1.5067, + "step": 2374 + }, + { + "epoch": 0.25, + "learning_rate": 1.8675768161584427e-05, + "loss": 2.0616, + "step": 2375 + }, + { + "epoch": 0.25, + "learning_rate": 1.8673947326393903e-05, + "loss": 1.5617, + "step": 2376 + }, + { + "epoch": 0.25, + "learning_rate": 1.86721253291173e-05, + "loss": 1.4422, + "step": 2377 + }, + { + "epoch": 0.25, + "learning_rate": 1.867030216999873e-05, + "loss": 1.4727, + "step": 2378 + }, + { + "epoch": 0.25, + "learning_rate": 1.8668477849282443e-05, + "loss": 1.4152, + "step": 2379 + }, + { + "epoch": 0.25, + "learning_rate": 1.8666652367212856e-05, + "loss": 1.4376, + "step": 2380 + }, + { + "epoch": 0.25, + "learning_rate": 1.8664825724034534e-05, + "loss": 1.393, + "step": 2381 + }, + { + "epoch": 0.25, + "learning_rate": 1.8662997919992197e-05, + "loss": 1.4864, + "step": 2382 + }, + { + "epoch": 0.25, + "learning_rate": 1.866116895533073e-05, + "loss": 1.4261, + "step": 2383 + }, + { + "epoch": 0.25, + "learning_rate": 1.8659338830295163e-05, + "loss": 1.4555, + "step": 2384 + }, + { + "epoch": 0.25, + "learning_rate": 1.8657507545130687e-05, + "loss": 1.4939, + "step": 2385 + }, + { + "epoch": 0.25, + "learning_rate": 1.865567510008265e-05, + "loss": 1.4123, + "step": 2386 + }, + { + "epoch": 0.25, + "learning_rate": 1.8653841495396546e-05, + "loss": 1.4459, + "step": 2387 + }, + { + "epoch": 0.25, + "learning_rate": 1.8652006731318038e-05, + "loss": 1.396, + "step": 2388 + }, + { + "epoch": 0.25, + "eval_loss": 1.5139706134796143, + "eval_runtime": 77.2904, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 2388 + }, + { + "epoch": 0.25, + "learning_rate": 1.8650170808092936e-05, + "loss": 1.4666, + "step": 2389 + }, + { + "epoch": 0.25, + "learning_rate": 1.86483337259672e-05, + "loss": 1.5154, + "step": 2390 + }, + { + "epoch": 0.25, + "learning_rate": 1.864649548518696e-05, + "loss": 1.5163, + "step": 2391 + }, + { + "epoch": 0.25, + "learning_rate": 1.864465608599849e-05, + "loss": 1.4734, + "step": 2392 + }, + { + "epoch": 0.25, + "learning_rate": 1.864281552864822e-05, + "loss": 1.5217, + "step": 2393 + }, + { + "epoch": 0.25, + "learning_rate": 1.8640973813382737e-05, + "loss": 1.4694, + "step": 2394 + }, + { + "epoch": 0.25, + "learning_rate": 1.863913094044879e-05, + "loss": 1.4761, + "step": 2395 + }, + { + "epoch": 0.25, + "learning_rate": 1.863728691009327e-05, + "loss": 1.4766, + "step": 2396 + }, + { + "epoch": 0.25, + "learning_rate": 1.863544172256323e-05, + "loss": 1.5695, + "step": 2397 + }, + { + "epoch": 0.25, + "learning_rate": 1.8633595378105882e-05, + "loss": 1.5079, + "step": 2398 + }, + { + "epoch": 0.25, + "learning_rate": 1.8631747876968584e-05, + "loss": 1.4154, + "step": 2399 + }, + { + "epoch": 0.25, + "learning_rate": 1.862989921939886e-05, + "loss": 1.4488, + "step": 2400 + }, + { + "epoch": 0.25, + "learning_rate": 1.8628049405644376e-05, + "loss": 1.4279, + "step": 2401 + }, + { + "epoch": 0.25, + "learning_rate": 1.8626198435952966e-05, + "loss": 1.4896, + "step": 2402 + }, + { + "epoch": 0.25, + "learning_rate": 1.8624346310572602e-05, + "loss": 1.4315, + "step": 2403 + }, + { + "epoch": 0.25, + "learning_rate": 1.862249302975143e-05, + "loss": 1.4919, + "step": 2404 + }, + { + "epoch": 0.25, + "learning_rate": 1.8620638593737743e-05, + "loss": 1.4561, + "step": 2405 + }, + { + "epoch": 0.25, + "learning_rate": 1.8618783002779985e-05, + "loss": 1.4622, + "step": 2406 + }, + { + "epoch": 0.25, + "learning_rate": 1.8616926257126754e-05, + "loss": 1.4917, + "step": 2407 + }, + { + "epoch": 0.25, + "learning_rate": 1.861506835702681e-05, + "loss": 1.4962, + "step": 2408 + }, + { + "epoch": 0.25, + "learning_rate": 1.861320930272906e-05, + "loss": 1.4164, + "step": 2409 + }, + { + "epoch": 0.25, + "learning_rate": 1.8611349094482578e-05, + "loss": 1.4889, + "step": 2410 + }, + { + "epoch": 0.25, + "learning_rate": 1.8609487732536576e-05, + "loss": 1.543, + "step": 2411 + }, + { + "epoch": 0.25, + "learning_rate": 1.8607625217140433e-05, + "loss": 1.5417, + "step": 2412 + }, + { + "epoch": 0.25, + "learning_rate": 1.8605761548543674e-05, + "loss": 1.5304, + "step": 2413 + }, + { + "epoch": 0.25, + "learning_rate": 1.860389672699599e-05, + "loss": 1.4725, + "step": 2414 + }, + { + "epoch": 0.25, + "learning_rate": 1.860203075274721e-05, + "loss": 1.4745, + "step": 2415 + }, + { + "epoch": 0.25, + "learning_rate": 1.8600163626047334e-05, + "loss": 1.4656, + "step": 2416 + }, + { + "epoch": 0.25, + "learning_rate": 1.8598295347146503e-05, + "loss": 1.5287, + "step": 2417 + }, + { + "epoch": 0.25, + "learning_rate": 1.8596425916295023e-05, + "loss": 1.5024, + "step": 2418 + }, + { + "epoch": 0.25, + "learning_rate": 1.8594555333743348e-05, + "loss": 1.4527, + "step": 2419 + }, + { + "epoch": 0.25, + "learning_rate": 1.859268359974209e-05, + "loss": 1.4897, + "step": 2420 + }, + { + "epoch": 0.25, + "learning_rate": 1.859081071454201e-05, + "loss": 1.3554, + "step": 2421 + }, + { + "epoch": 0.25, + "learning_rate": 1.858893667839403e-05, + "loss": 1.4004, + "step": 2422 + }, + { + "epoch": 0.25, + "learning_rate": 1.858706149154922e-05, + "loss": 1.5582, + "step": 2423 + }, + { + "epoch": 0.25, + "learning_rate": 1.8585185154258803e-05, + "loss": 1.505, + "step": 2424 + }, + { + "epoch": 0.25, + "learning_rate": 1.858330766677417e-05, + "loss": 1.5043, + "step": 2425 + }, + { + "epoch": 0.25, + "learning_rate": 1.858142902934685e-05, + "loss": 1.439, + "step": 2426 + }, + { + "epoch": 0.25, + "learning_rate": 1.857954924222853e-05, + "loss": 1.4927, + "step": 2427 + }, + { + "epoch": 0.25, + "learning_rate": 1.8577668305671056e-05, + "loss": 1.5395, + "step": 2428 + }, + { + "epoch": 0.25, + "learning_rate": 1.8575786219926427e-05, + "loss": 1.4737, + "step": 2429 + }, + { + "epoch": 0.25, + "learning_rate": 1.8573902985246794e-05, + "loss": 1.6151, + "step": 2430 + }, + { + "epoch": 0.25, + "learning_rate": 1.857201860188446e-05, + "loss": 1.4313, + "step": 2431 + }, + { + "epoch": 0.26, + "learning_rate": 1.857013307009188e-05, + "loss": 1.4509, + "step": 2432 + }, + { + "epoch": 0.26, + "learning_rate": 1.8568246390121673e-05, + "loss": 1.3998, + "step": 2433 + }, + { + "epoch": 0.26, + "learning_rate": 1.8566358562226603e-05, + "loss": 1.5268, + "step": 2434 + }, + { + "epoch": 0.26, + "learning_rate": 1.8564469586659593e-05, + "loss": 1.4369, + "step": 2435 + }, + { + "epoch": 0.26, + "learning_rate": 1.8562579463673713e-05, + "loss": 1.4759, + "step": 2436 + }, + { + "epoch": 0.26, + "learning_rate": 1.8560688193522197e-05, + "loss": 1.4092, + "step": 2437 + }, + { + "epoch": 0.26, + "learning_rate": 1.855879577645842e-05, + "loss": 1.43, + "step": 2438 + }, + { + "epoch": 0.26, + "learning_rate": 1.855690221273592e-05, + "loss": 1.5143, + "step": 2439 + }, + { + "epoch": 0.26, + "learning_rate": 1.8555007502608385e-05, + "loss": 1.5482, + "step": 2440 + }, + { + "epoch": 0.26, + "learning_rate": 1.855311164632966e-05, + "loss": 1.4406, + "step": 2441 + }, + { + "epoch": 0.26, + "learning_rate": 1.8551214644153738e-05, + "loss": 1.4551, + "step": 2442 + }, + { + "epoch": 0.26, + "learning_rate": 1.8549316496334774e-05, + "loss": 1.4663, + "step": 2443 + }, + { + "epoch": 0.26, + "learning_rate": 1.8547417203127064e-05, + "loss": 1.4732, + "step": 2444 + }, + { + "epoch": 0.26, + "learning_rate": 1.8545516764785067e-05, + "loss": 1.5378, + "step": 2445 + }, + { + "epoch": 0.26, + "learning_rate": 1.8543615181563397e-05, + "loss": 1.4448, + "step": 2446 + }, + { + "epoch": 0.26, + "learning_rate": 1.854171245371681e-05, + "loss": 1.2861, + "step": 2447 + }, + { + "epoch": 0.26, + "learning_rate": 1.8539808581500228e-05, + "loss": 1.4405, + "step": 2448 + }, + { + "epoch": 0.26, + "learning_rate": 1.8537903565168716e-05, + "loss": 1.4876, + "step": 2449 + }, + { + "epoch": 0.26, + "learning_rate": 1.8535997404977506e-05, + "loss": 1.4119, + "step": 2450 + }, + { + "epoch": 0.26, + "learning_rate": 1.8534090101181967e-05, + "loss": 1.4451, + "step": 2451 + }, + { + "epoch": 0.26, + "learning_rate": 1.8532181654037632e-05, + "loss": 1.4035, + "step": 2452 + }, + { + "epoch": 0.26, + "learning_rate": 1.853027206380018e-05, + "loss": 1.4624, + "step": 2453 + }, + { + "epoch": 0.26, + "learning_rate": 1.852836133072545e-05, + "loss": 1.4935, + "step": 2454 + }, + { + "epoch": 0.26, + "learning_rate": 1.8526449455069434e-05, + "loss": 1.4834, + "step": 2455 + }, + { + "epoch": 0.26, + "learning_rate": 1.8524536437088266e-05, + "loss": 1.498, + "step": 2456 + }, + { + "epoch": 0.26, + "learning_rate": 1.8522622277038247e-05, + "loss": 1.3417, + "step": 2457 + }, + { + "epoch": 0.26, + "learning_rate": 1.852070697517583e-05, + "loss": 1.4455, + "step": 2458 + }, + { + "epoch": 0.26, + "learning_rate": 1.8518790531757607e-05, + "loss": 1.4119, + "step": 2459 + }, + { + "epoch": 0.26, + "learning_rate": 1.8516872947040337e-05, + "loss": 1.558, + "step": 2460 + }, + { + "epoch": 0.26, + "learning_rate": 1.8514954221280926e-05, + "loss": 1.4862, + "step": 2461 + }, + { + "epoch": 0.26, + "learning_rate": 1.8513034354736433e-05, + "loss": 1.6806, + "step": 2462 + }, + { + "epoch": 0.26, + "learning_rate": 1.8511113347664072e-05, + "loss": 1.438, + "step": 2463 + }, + { + "epoch": 0.26, + "learning_rate": 1.850919120032121e-05, + "loss": 1.4975, + "step": 2464 + }, + { + "epoch": 0.26, + "learning_rate": 1.850726791296536e-05, + "loss": 1.4409, + "step": 2465 + }, + { + "epoch": 0.26, + "learning_rate": 1.85053434858542e-05, + "loss": 1.4769, + "step": 2466 + }, + { + "epoch": 0.26, + "learning_rate": 1.8503417919245548e-05, + "loss": 1.5823, + "step": 2467 + }, + { + "epoch": 0.26, + "learning_rate": 1.8501491213397386e-05, + "loss": 1.4045, + "step": 2468 + }, + { + "epoch": 0.26, + "learning_rate": 1.8499563368567837e-05, + "loss": 1.4828, + "step": 2469 + }, + { + "epoch": 0.26, + "learning_rate": 1.849763438501519e-05, + "loss": 1.4684, + "step": 2470 + }, + { + "epoch": 0.26, + "learning_rate": 1.8495704262997873e-05, + "loss": 1.4577, + "step": 2471 + }, + { + "epoch": 0.26, + "learning_rate": 1.8493773002774475e-05, + "loss": 1.4759, + "step": 2472 + }, + { + "epoch": 0.26, + "learning_rate": 1.8491840604603736e-05, + "loss": 1.4259, + "step": 2473 + }, + { + "epoch": 0.26, + "learning_rate": 1.8489907068744543e-05, + "loss": 1.4717, + "step": 2474 + }, + { + "epoch": 0.26, + "learning_rate": 1.848797239545595e-05, + "loss": 1.4247, + "step": 2475 + }, + { + "epoch": 0.26, + "learning_rate": 1.8486036584997143e-05, + "loss": 1.4954, + "step": 2476 + }, + { + "epoch": 0.26, + "learning_rate": 1.8484099637627472e-05, + "loss": 1.4926, + "step": 2477 + }, + { + "epoch": 0.26, + "learning_rate": 1.8482161553606447e-05, + "loss": 1.487, + "step": 2478 + }, + { + "epoch": 0.26, + "learning_rate": 1.8480222333193715e-05, + "loss": 1.4553, + "step": 2479 + }, + { + "epoch": 0.26, + "learning_rate": 1.847828197664908e-05, + "loss": 1.4862, + "step": 2480 + }, + { + "epoch": 0.26, + "learning_rate": 1.8476340484232508e-05, + "loss": 1.4867, + "step": 2481 + }, + { + "epoch": 0.26, + "learning_rate": 1.8474397856204097e-05, + "loss": 1.4736, + "step": 2482 + }, + { + "epoch": 0.26, + "learning_rate": 1.8472454092824122e-05, + "loss": 1.4254, + "step": 2483 + }, + { + "epoch": 0.26, + "learning_rate": 1.8470509194352987e-05, + "loss": 1.4455, + "step": 2484 + }, + { + "epoch": 0.26, + "learning_rate": 1.8468563161051263e-05, + "loss": 1.4402, + "step": 2485 + }, + { + "epoch": 0.26, + "learning_rate": 1.846661599317967e-05, + "loss": 1.4611, + "step": 2486 + }, + { + "epoch": 0.26, + "learning_rate": 1.8464667690999073e-05, + "loss": 1.4814, + "step": 2487 + }, + { + "epoch": 0.26, + "learning_rate": 1.8462718254770503e-05, + "loss": 1.4559, + "step": 2488 + }, + { + "epoch": 0.26, + "learning_rate": 1.8460767684755127e-05, + "loss": 1.4667, + "step": 2489 + }, + { + "epoch": 0.26, + "learning_rate": 1.8458815981214274e-05, + "loss": 1.4427, + "step": 2490 + }, + { + "epoch": 0.26, + "learning_rate": 1.845686314440942e-05, + "loss": 1.4055, + "step": 2491 + }, + { + "epoch": 0.26, + "learning_rate": 1.8454909174602198e-05, + "loss": 1.5563, + "step": 2492 + }, + { + "epoch": 0.26, + "learning_rate": 1.845295407205439e-05, + "loss": 1.4631, + "step": 2493 + }, + { + "epoch": 0.26, + "learning_rate": 1.8450997837027925e-05, + "loss": 1.4887, + "step": 2494 + }, + { + "epoch": 0.26, + "learning_rate": 1.8449040469784895e-05, + "loss": 1.5212, + "step": 2495 + }, + { + "epoch": 0.26, + "learning_rate": 1.844708197058753e-05, + "loss": 1.5582, + "step": 2496 + }, + { + "epoch": 0.26, + "learning_rate": 1.844512233969822e-05, + "loss": 1.4599, + "step": 2497 + }, + { + "epoch": 0.26, + "learning_rate": 1.844316157737951e-05, + "loss": 1.4546, + "step": 2498 + }, + { + "epoch": 0.26, + "learning_rate": 1.844119968389409e-05, + "loss": 1.4631, + "step": 2499 + }, + { + "epoch": 0.26, + "learning_rate": 1.84392366595048e-05, + "loss": 1.4817, + "step": 2500 + }, + { + "epoch": 0.26, + "learning_rate": 1.8437272504474636e-05, + "loss": 1.4214, + "step": 2501 + }, + { + "epoch": 0.26, + "learning_rate": 1.8435307219066744e-05, + "loss": 1.471, + "step": 2502 + }, + { + "epoch": 0.26, + "learning_rate": 1.8433340803544424e-05, + "loss": 1.4693, + "step": 2503 + }, + { + "epoch": 0.26, + "learning_rate": 1.8431373258171127e-05, + "loss": 1.6297, + "step": 2504 + }, + { + "epoch": 0.26, + "learning_rate": 1.842940458321045e-05, + "loss": 1.5916, + "step": 2505 + }, + { + "epoch": 0.26, + "learning_rate": 1.842743477892614e-05, + "loss": 1.4754, + "step": 2506 + }, + { + "epoch": 0.26, + "learning_rate": 1.842546384558211e-05, + "loss": 1.4828, + "step": 2507 + }, + { + "epoch": 0.26, + "learning_rate": 1.842349178344241e-05, + "loss": 1.4239, + "step": 2508 + }, + { + "epoch": 0.26, + "learning_rate": 1.8421518592771243e-05, + "loss": 1.5028, + "step": 2509 + }, + { + "epoch": 0.26, + "learning_rate": 1.841954427383297e-05, + "loss": 1.4848, + "step": 2510 + }, + { + "epoch": 0.26, + "learning_rate": 1.8417568826892097e-05, + "loss": 1.4617, + "step": 2511 + }, + { + "epoch": 0.26, + "learning_rate": 1.8415592252213284e-05, + "loss": 1.4266, + "step": 2512 + }, + { + "epoch": 0.26, + "learning_rate": 1.8413614550061344e-05, + "loss": 1.4321, + "step": 2513 + }, + { + "epoch": 0.26, + "learning_rate": 1.841163572070123e-05, + "loss": 1.4693, + "step": 2514 + }, + { + "epoch": 0.26, + "learning_rate": 1.840965576439806e-05, + "loss": 1.4257, + "step": 2515 + }, + { + "epoch": 0.26, + "learning_rate": 1.84076746814171e-05, + "loss": 1.4488, + "step": 2516 + }, + { + "epoch": 0.26, + "learning_rate": 1.840569247202376e-05, + "loss": 1.5348, + "step": 2517 + }, + { + "epoch": 0.26, + "learning_rate": 1.8403709136483604e-05, + "loss": 1.477, + "step": 2518 + }, + { + "epoch": 0.26, + "learning_rate": 1.840172467506235e-05, + "loss": 1.443, + "step": 2519 + }, + { + "epoch": 0.26, + "learning_rate": 1.839973908802587e-05, + "loss": 1.4772, + "step": 2520 + }, + { + "epoch": 0.26, + "learning_rate": 1.839775237564017e-05, + "loss": 1.4443, + "step": 2521 + }, + { + "epoch": 0.26, + "learning_rate": 1.839576453817143e-05, + "loss": 1.4063, + "step": 2522 + }, + { + "epoch": 0.26, + "learning_rate": 1.8393775575885963e-05, + "loss": 1.5178, + "step": 2523 + }, + { + "epoch": 0.26, + "learning_rate": 1.8391785489050235e-05, + "loss": 1.4337, + "step": 2524 + }, + { + "epoch": 0.26, + "learning_rate": 1.8389794277930875e-05, + "loss": 1.4512, + "step": 2525 + }, + { + "epoch": 0.26, + "learning_rate": 1.838780194279465e-05, + "loss": 1.5578, + "step": 2526 + }, + { + "epoch": 0.26, + "learning_rate": 1.8385808483908484e-05, + "loss": 1.4606, + "step": 2527 + }, + { + "epoch": 0.27, + "learning_rate": 1.8383813901539444e-05, + "loss": 1.4957, + "step": 2528 + }, + { + "epoch": 0.27, + "learning_rate": 1.838181819595476e-05, + "loss": 1.4914, + "step": 2529 + }, + { + "epoch": 0.27, + "learning_rate": 1.8379821367421802e-05, + "loss": 1.4785, + "step": 2530 + }, + { + "epoch": 0.27, + "learning_rate": 1.837782341620809e-05, + "loss": 1.4052, + "step": 2531 + }, + { + "epoch": 0.27, + "learning_rate": 1.8375824342581303e-05, + "loss": 1.4807, + "step": 2532 + }, + { + "epoch": 0.27, + "learning_rate": 1.8373824146809264e-05, + "loss": 1.4313, + "step": 2533 + }, + { + "epoch": 0.27, + "learning_rate": 1.8371822829159945e-05, + "loss": 1.4374, + "step": 2534 + }, + { + "epoch": 0.27, + "learning_rate": 1.836982038990148e-05, + "loss": 1.4482, + "step": 2535 + }, + { + "epoch": 0.27, + "learning_rate": 1.8367816829302133e-05, + "loss": 1.5231, + "step": 2536 + }, + { + "epoch": 0.27, + "learning_rate": 1.8365812147630337e-05, + "loss": 1.4101, + "step": 2537 + }, + { + "epoch": 0.27, + "learning_rate": 1.8363806345154666e-05, + "loss": 1.4372, + "step": 2538 + }, + { + "epoch": 0.27, + "learning_rate": 1.8361799422143845e-05, + "loss": 1.4808, + "step": 2539 + }, + { + "epoch": 0.27, + "learning_rate": 1.835979137886675e-05, + "loss": 1.3515, + "step": 2540 + }, + { + "epoch": 0.27, + "learning_rate": 1.8357782215592412e-05, + "loss": 1.5284, + "step": 2541 + }, + { + "epoch": 0.27, + "learning_rate": 1.835577193259e-05, + "loss": 1.4222, + "step": 2542 + }, + { + "epoch": 0.27, + "learning_rate": 1.8353760530128846e-05, + "loss": 1.4522, + "step": 2543 + }, + { + "epoch": 0.27, + "learning_rate": 1.835174800847842e-05, + "loss": 1.4487, + "step": 2544 + }, + { + "epoch": 0.27, + "learning_rate": 1.8349734367908355e-05, + "loss": 1.3688, + "step": 2545 + }, + { + "epoch": 0.27, + "learning_rate": 1.8347719608688422e-05, + "loss": 1.483, + "step": 2546 + }, + { + "epoch": 0.27, + "learning_rate": 1.8345703731088554e-05, + "loss": 1.4733, + "step": 2547 + }, + { + "epoch": 0.27, + "learning_rate": 1.8343686735378816e-05, + "loss": 1.4594, + "step": 2548 + }, + { + "epoch": 0.27, + "learning_rate": 1.834166862182944e-05, + "loss": 1.4648, + "step": 2549 + }, + { + "epoch": 0.27, + "learning_rate": 1.8339649390710807e-05, + "loss": 1.5249, + "step": 2550 + }, + { + "epoch": 0.27, + "learning_rate": 1.8337629042293434e-05, + "loss": 1.4744, + "step": 2551 + }, + { + "epoch": 0.27, + "learning_rate": 1.8335607576847994e-05, + "loss": 1.5094, + "step": 2552 + }, + { + "epoch": 0.27, + "learning_rate": 1.8333584994645318e-05, + "loss": 1.5122, + "step": 2553 + }, + { + "epoch": 0.27, + "learning_rate": 1.8331561295956374e-05, + "loss": 1.537, + "step": 2554 + }, + { + "epoch": 0.27, + "learning_rate": 1.832953648105229e-05, + "loss": 1.4691, + "step": 2555 + }, + { + "epoch": 0.27, + "learning_rate": 1.8327510550204343e-05, + "loss": 1.4969, + "step": 2556 + }, + { + "epoch": 0.27, + "learning_rate": 1.8325483503683944e-05, + "loss": 1.4596, + "step": 2557 + }, + { + "epoch": 0.27, + "learning_rate": 1.8323455341762675e-05, + "loss": 1.435, + "step": 2558 + }, + { + "epoch": 0.27, + "learning_rate": 1.8321426064712255e-05, + "loss": 1.4883, + "step": 2559 + }, + { + "epoch": 0.27, + "learning_rate": 1.8319395672804554e-05, + "loss": 1.3758, + "step": 2560 + }, + { + "epoch": 0.27, + "learning_rate": 1.8317364166311592e-05, + "loss": 1.4352, + "step": 2561 + }, + { + "epoch": 0.27, + "learning_rate": 1.831533154550554e-05, + "loss": 1.5072, + "step": 2562 + }, + { + "epoch": 0.27, + "learning_rate": 1.8313297810658718e-05, + "loss": 1.4476, + "step": 2563 + }, + { + "epoch": 0.27, + "learning_rate": 1.831126296204359e-05, + "loss": 1.507, + "step": 2564 + }, + { + "epoch": 0.27, + "learning_rate": 1.8309226999932777e-05, + "loss": 1.4677, + "step": 2565 + }, + { + "epoch": 0.27, + "learning_rate": 1.8307189924599044e-05, + "loss": 1.4537, + "step": 2566 + }, + { + "epoch": 0.27, + "learning_rate": 1.8305151736315307e-05, + "loss": 1.4584, + "step": 2567 + }, + { + "epoch": 0.27, + "learning_rate": 1.8303112435354634e-05, + "loss": 1.4944, + "step": 2568 + }, + { + "epoch": 0.27, + "learning_rate": 1.8301072021990232e-05, + "loss": 1.4379, + "step": 2569 + }, + { + "epoch": 0.27, + "learning_rate": 1.8299030496495475e-05, + "loss": 1.539, + "step": 2570 + }, + { + "epoch": 0.27, + "learning_rate": 1.829698785914386e-05, + "loss": 1.4421, + "step": 2571 + }, + { + "epoch": 0.27, + "learning_rate": 1.8294944110209063e-05, + "loss": 1.4693, + "step": 2572 + }, + { + "epoch": 0.27, + "learning_rate": 1.8292899249964887e-05, + "loss": 1.3239, + "step": 2573 + }, + { + "epoch": 0.27, + "learning_rate": 1.8290853278685284e-05, + "loss": 1.472, + "step": 2574 + }, + { + "epoch": 0.27, + "learning_rate": 1.8288806196644374e-05, + "loss": 1.536, + "step": 2575 + }, + { + "epoch": 0.27, + "learning_rate": 1.8286758004116405e-05, + "loss": 1.4644, + "step": 2576 + }, + { + "epoch": 0.27, + "learning_rate": 1.8284708701375783e-05, + "loss": 1.4537, + "step": 2577 + }, + { + "epoch": 0.27, + "learning_rate": 1.8282658288697067e-05, + "loss": 1.4359, + "step": 2578 + }, + { + "epoch": 0.27, + "learning_rate": 1.8280606766354955e-05, + "loss": 1.4842, + "step": 2579 + }, + { + "epoch": 0.27, + "learning_rate": 1.8278554134624302e-05, + "loss": 1.4664, + "step": 2580 + }, + { + "epoch": 0.27, + "learning_rate": 1.8276500393780105e-05, + "loss": 1.4632, + "step": 2581 + }, + { + "epoch": 0.27, + "learning_rate": 1.827444554409751e-05, + "loss": 1.4996, + "step": 2582 + }, + { + "epoch": 0.27, + "learning_rate": 1.827238958585182e-05, + "loss": 1.3399, + "step": 2583 + }, + { + "epoch": 0.27, + "learning_rate": 1.8270332519318476e-05, + "loss": 1.3928, + "step": 2584 + }, + { + "epoch": 0.27, + "learning_rate": 1.8268274344773074e-05, + "loss": 1.4993, + "step": 2585 + }, + { + "epoch": 0.27, + "learning_rate": 1.8266215062491356e-05, + "loss": 1.5398, + "step": 2586 + }, + { + "epoch": 0.27, + "learning_rate": 1.826415467274921e-05, + "loss": 1.4353, + "step": 2587 + }, + { + "epoch": 0.27, + "eval_loss": 1.5104212760925293, + "eval_runtime": 77.3448, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2587 + }, + { + "epoch": 0.27, + "learning_rate": 1.8262093175822685e-05, + "loss": 1.4889, + "step": 2588 + }, + { + "epoch": 0.27, + "learning_rate": 1.826003057198796e-05, + "loss": 1.4912, + "step": 2589 + }, + { + "epoch": 0.27, + "learning_rate": 1.825796686152137e-05, + "loss": 1.4884, + "step": 2590 + }, + { + "epoch": 0.27, + "learning_rate": 1.8255902044699404e-05, + "loss": 1.478, + "step": 2591 + }, + { + "epoch": 0.27, + "learning_rate": 1.8253836121798692e-05, + "loss": 1.6549, + "step": 2592 + }, + { + "epoch": 0.27, + "learning_rate": 1.8251769093096018e-05, + "loss": 1.5146, + "step": 2593 + }, + { + "epoch": 0.27, + "learning_rate": 1.8249700958868306e-05, + "loss": 1.4797, + "step": 2594 + }, + { + "epoch": 0.27, + "learning_rate": 1.8247631719392634e-05, + "loss": 1.4655, + "step": 2595 + }, + { + "epoch": 0.27, + "learning_rate": 1.824556137494623e-05, + "loss": 1.4517, + "step": 2596 + }, + { + "epoch": 0.27, + "learning_rate": 1.8243489925806458e-05, + "loss": 1.4936, + "step": 2597 + }, + { + "epoch": 0.27, + "learning_rate": 1.8241417372250852e-05, + "loss": 1.4614, + "step": 2598 + }, + { + "epoch": 0.27, + "learning_rate": 1.8239343714557073e-05, + "loss": 1.4475, + "step": 2599 + }, + { + "epoch": 0.27, + "learning_rate": 1.8237268953002937e-05, + "loss": 1.5435, + "step": 2600 + }, + { + "epoch": 0.27, + "learning_rate": 1.8235193087866413e-05, + "loss": 1.4616, + "step": 2601 + }, + { + "epoch": 0.27, + "learning_rate": 1.8233116119425612e-05, + "loss": 1.4578, + "step": 2602 + }, + { + "epoch": 0.27, + "learning_rate": 1.8231038047958795e-05, + "loss": 1.434, + "step": 2603 + }, + { + "epoch": 0.27, + "learning_rate": 1.8228958873744368e-05, + "loss": 1.5335, + "step": 2604 + }, + { + "epoch": 0.27, + "learning_rate": 1.8226878597060887e-05, + "loss": 1.415, + "step": 2605 + }, + { + "epoch": 0.27, + "learning_rate": 1.8224797218187058e-05, + "loss": 1.6165, + "step": 2606 + }, + { + "epoch": 0.27, + "learning_rate": 1.822271473740173e-05, + "loss": 1.372, + "step": 2607 + }, + { + "epoch": 0.27, + "learning_rate": 1.8220631154983907e-05, + "loss": 1.4855, + "step": 2608 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218546471212727e-05, + "loss": 1.4093, + "step": 2609 + }, + { + "epoch": 0.27, + "learning_rate": 1.821646068636749e-05, + "loss": 1.4852, + "step": 2610 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214373800727637e-05, + "loss": 1.6959, + "step": 2611 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212285814572755e-05, + "loss": 1.3874, + "step": 2612 + }, + { + "epoch": 0.27, + "learning_rate": 1.821019672818258e-05, + "loss": 1.4425, + "step": 2613 + }, + { + "epoch": 0.27, + "learning_rate": 1.8208106541837e-05, + "loss": 1.6097, + "step": 2614 + }, + { + "epoch": 0.27, + "learning_rate": 1.8206015255816045e-05, + "loss": 1.5675, + "step": 2615 + }, + { + "epoch": 0.27, + "learning_rate": 1.820392287039989e-05, + "loss": 1.4039, + "step": 2616 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201829385868866e-05, + "loss": 1.4872, + "step": 2617 + }, + { + "epoch": 0.27, + "learning_rate": 1.819973480250344e-05, + "loss": 1.4645, + "step": 2618 + }, + { + "epoch": 0.27, + "learning_rate": 1.8197639120584237e-05, + "loss": 1.4923, + "step": 2619 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195542340392025e-05, + "loss": 1.4294, + "step": 2620 + }, + { + "epoch": 0.27, + "learning_rate": 1.8193444462207717e-05, + "loss": 1.4315, + "step": 2621 + }, + { + "epoch": 0.27, + "learning_rate": 1.8191345486312372e-05, + "loss": 1.3972, + "step": 2622 + }, + { + "epoch": 0.28, + "learning_rate": 1.8189245412987205e-05, + "loss": 1.462, + "step": 2623 + }, + { + "epoch": 0.28, + "learning_rate": 1.8187144242513567e-05, + "loss": 1.4738, + "step": 2624 + }, + { + "epoch": 0.28, + "learning_rate": 1.818504197517296e-05, + "loss": 1.4935, + "step": 2625 + }, + { + "epoch": 0.28, + "learning_rate": 1.8182938611247038e-05, + "loss": 1.4231, + "step": 2626 + }, + { + "epoch": 0.28, + "learning_rate": 1.81808341510176e-05, + "loss": 1.4031, + "step": 2627 + }, + { + "epoch": 0.28, + "learning_rate": 1.817872859476658e-05, + "loss": 1.5822, + "step": 2628 + }, + { + "epoch": 0.28, + "learning_rate": 1.8176621942776075e-05, + "loss": 1.432, + "step": 2629 + }, + { + "epoch": 0.28, + "learning_rate": 1.8174514195328324e-05, + "loss": 1.5565, + "step": 2630 + }, + { + "epoch": 0.28, + "learning_rate": 1.8172405352705704e-05, + "loss": 1.4895, + "step": 2631 + }, + { + "epoch": 0.28, + "learning_rate": 1.8170295415190754e-05, + "loss": 1.4032, + "step": 2632 + }, + { + "epoch": 0.28, + "learning_rate": 1.8168184383066144e-05, + "loss": 1.4253, + "step": 2633 + }, + { + "epoch": 0.28, + "learning_rate": 1.8166072256614702e-05, + "loss": 1.5162, + "step": 2634 + }, + { + "epoch": 0.28, + "learning_rate": 1.81639590361194e-05, + "loss": 1.4609, + "step": 2635 + }, + { + "epoch": 0.28, + "learning_rate": 1.816184472186335e-05, + "loss": 1.4351, + "step": 2636 + }, + { + "epoch": 0.28, + "learning_rate": 1.8159729314129823e-05, + "loss": 1.4738, + "step": 2637 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157612813202224e-05, + "loss": 1.5986, + "step": 2638 + }, + { + "epoch": 0.28, + "learning_rate": 1.815549521936411e-05, + "loss": 1.4633, + "step": 2639 + }, + { + "epoch": 0.28, + "learning_rate": 1.8153376532899184e-05, + "loss": 1.4404, + "step": 2640 + }, + { + "epoch": 0.28, + "learning_rate": 1.81512567540913e-05, + "loss": 1.4256, + "step": 2641 + }, + { + "epoch": 0.28, + "learning_rate": 1.814913588322445e-05, + "loss": 1.4054, + "step": 2642 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147013920582773e-05, + "loss": 1.4134, + "step": 2643 + }, + { + "epoch": 0.28, + "learning_rate": 1.8144890866450567e-05, + "loss": 1.4098, + "step": 2644 + }, + { + "epoch": 0.28, + "learning_rate": 1.814276672111226e-05, + "loss": 1.4593, + "step": 2645 + }, + { + "epoch": 0.28, + "learning_rate": 1.814064148485243e-05, + "loss": 1.4679, + "step": 2646 + }, + { + "epoch": 0.28, + "learning_rate": 1.8138515157955812e-05, + "loss": 1.5234, + "step": 2647 + }, + { + "epoch": 0.28, + "learning_rate": 1.8136387740707272e-05, + "loss": 1.4568, + "step": 2648 + }, + { + "epoch": 0.28, + "learning_rate": 1.8134259233391836e-05, + "loss": 1.5057, + "step": 2649 + }, + { + "epoch": 0.28, + "learning_rate": 1.8132129636294665e-05, + "loss": 1.3643, + "step": 2650 + }, + { + "epoch": 0.28, + "learning_rate": 1.812999894970107e-05, + "loss": 1.4766, + "step": 2651 + }, + { + "epoch": 0.28, + "learning_rate": 1.812786717389651e-05, + "loss": 1.5701, + "step": 2652 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125734309166587e-05, + "loss": 1.5341, + "step": 2653 + }, + { + "epoch": 0.28, + "learning_rate": 1.812360035579705e-05, + "loss": 1.3596, + "step": 2654 + }, + { + "epoch": 0.28, + "learning_rate": 1.8121465314073793e-05, + "loss": 1.4847, + "step": 2655 + }, + { + "epoch": 0.28, + "learning_rate": 1.811932918428286e-05, + "loss": 1.4664, + "step": 2656 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117191966710438e-05, + "loss": 1.4673, + "step": 2657 + }, + { + "epoch": 0.28, + "learning_rate": 1.8115053661642856e-05, + "loss": 1.4712, + "step": 2658 + }, + { + "epoch": 0.28, + "learning_rate": 1.811291426936659e-05, + "loss": 1.4458, + "step": 2659 + }, + { + "epoch": 0.28, + "learning_rate": 1.811077379016827e-05, + "loss": 1.4667, + "step": 2660 + }, + { + "epoch": 0.28, + "learning_rate": 1.810863222433466e-05, + "loss": 1.4695, + "step": 2661 + }, + { + "epoch": 0.28, + "learning_rate": 1.8106489572152677e-05, + "loss": 1.5263, + "step": 2662 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104345833909376e-05, + "loss": 1.4148, + "step": 2663 + }, + { + "epoch": 0.28, + "learning_rate": 1.8102201009891976e-05, + "loss": 1.3955, + "step": 2664 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100055100387814e-05, + "loss": 1.6056, + "step": 2665 + }, + { + "epoch": 0.28, + "learning_rate": 1.8097908105684396e-05, + "loss": 1.5394, + "step": 2666 + }, + { + "epoch": 0.28, + "learning_rate": 1.809576002606936e-05, + "loss": 1.479, + "step": 2667 + }, + { + "epoch": 0.28, + "learning_rate": 1.8093610861830494e-05, + "loss": 1.4492, + "step": 2668 + }, + { + "epoch": 0.28, + "learning_rate": 1.8091460613255728e-05, + "loss": 1.4172, + "step": 2669 + }, + { + "epoch": 0.28, + "learning_rate": 1.808930928063315e-05, + "loss": 1.4498, + "step": 2670 + }, + { + "epoch": 0.28, + "learning_rate": 1.808715686425097e-05, + "loss": 1.6203, + "step": 2671 + }, + { + "epoch": 0.28, + "learning_rate": 1.8085003364397567e-05, + "loss": 1.435, + "step": 2672 + }, + { + "epoch": 0.28, + "learning_rate": 1.808284878136145e-05, + "loss": 1.4489, + "step": 2673 + }, + { + "epoch": 0.28, + "learning_rate": 1.8080693115431277e-05, + "loss": 1.4416, + "step": 2674 + }, + { + "epoch": 0.28, + "learning_rate": 1.8078536366895853e-05, + "loss": 1.422, + "step": 2675 + }, + { + "epoch": 0.28, + "learning_rate": 1.8076378536044128e-05, + "loss": 1.4039, + "step": 2676 + }, + { + "epoch": 0.28, + "learning_rate": 1.8074219623165195e-05, + "loss": 1.4705, + "step": 2677 + }, + { + "epoch": 0.28, + "learning_rate": 1.807205962854829e-05, + "loss": 1.5031, + "step": 2678 + }, + { + "epoch": 0.28, + "learning_rate": 1.8069898552482806e-05, + "loss": 1.4812, + "step": 2679 + }, + { + "epoch": 0.28, + "learning_rate": 1.806773639525826e-05, + "loss": 1.4129, + "step": 2680 + }, + { + "epoch": 0.28, + "learning_rate": 1.8065573157164332e-05, + "loss": 1.4559, + "step": 2681 + }, + { + "epoch": 0.28, + "learning_rate": 1.806340883849084e-05, + "loss": 1.3878, + "step": 2682 + }, + { + "epoch": 0.28, + "learning_rate": 1.8061243439527744e-05, + "loss": 1.4752, + "step": 2683 + }, + { + "epoch": 0.28, + "learning_rate": 1.8059076960565156e-05, + "loss": 1.4089, + "step": 2684 + }, + { + "epoch": 0.28, + "learning_rate": 1.8056909401893326e-05, + "loss": 1.4736, + "step": 2685 + }, + { + "epoch": 0.28, + "learning_rate": 1.8054740763802654e-05, + "loss": 1.3796, + "step": 2686 + }, + { + "epoch": 0.28, + "learning_rate": 1.805257104658368e-05, + "loss": 1.4412, + "step": 2687 + }, + { + "epoch": 0.28, + "learning_rate": 1.8050400250527086e-05, + "loss": 1.4639, + "step": 2688 + }, + { + "epoch": 0.28, + "learning_rate": 1.804822837592371e-05, + "loss": 1.4076, + "step": 2689 + }, + { + "epoch": 0.28, + "learning_rate": 1.804605542306452e-05, + "loss": 1.4627, + "step": 2690 + }, + { + "epoch": 0.28, + "learning_rate": 1.8043881392240642e-05, + "loss": 1.5249, + "step": 2691 + }, + { + "epoch": 0.28, + "learning_rate": 1.804170628374334e-05, + "loss": 1.4312, + "step": 2692 + }, + { + "epoch": 0.28, + "learning_rate": 1.803953009786402e-05, + "loss": 1.5676, + "step": 2693 + }, + { + "epoch": 0.28, + "learning_rate": 1.8037352834894233e-05, + "loss": 1.5072, + "step": 2694 + }, + { + "epoch": 0.28, + "learning_rate": 1.803517449512568e-05, + "loss": 1.5662, + "step": 2695 + }, + { + "epoch": 0.28, + "learning_rate": 1.8032995078850207e-05, + "loss": 1.4771, + "step": 2696 + }, + { + "epoch": 0.28, + "learning_rate": 1.803081458635979e-05, + "loss": 1.412, + "step": 2697 + }, + { + "epoch": 0.28, + "learning_rate": 1.8028633017946564e-05, + "loss": 1.497, + "step": 2698 + }, + { + "epoch": 0.28, + "learning_rate": 1.8026450373902804e-05, + "loss": 1.4528, + "step": 2699 + }, + { + "epoch": 0.28, + "learning_rate": 1.802426665452093e-05, + "loss": 1.4785, + "step": 2700 + }, + { + "epoch": 0.28, + "learning_rate": 1.8022081860093493e-05, + "loss": 1.6411, + "step": 2701 + }, + { + "epoch": 0.28, + "learning_rate": 1.8019895990913213e-05, + "loss": 1.4459, + "step": 2702 + }, + { + "epoch": 0.28, + "learning_rate": 1.8017709047272932e-05, + "loss": 1.4418, + "step": 2703 + }, + { + "epoch": 0.28, + "learning_rate": 1.801552102946565e-05, + "loss": 1.4409, + "step": 2704 + }, + { + "epoch": 0.28, + "learning_rate": 1.8013331937784498e-05, + "loss": 1.4651, + "step": 2705 + }, + { + "epoch": 0.28, + "learning_rate": 1.8011141772522766e-05, + "loss": 1.4161, + "step": 2706 + }, + { + "epoch": 0.28, + "learning_rate": 1.8008950533973876e-05, + "loss": 1.458, + "step": 2707 + }, + { + "epoch": 0.28, + "learning_rate": 1.8006758222431398e-05, + "loss": 1.4477, + "step": 2708 + }, + { + "epoch": 0.28, + "learning_rate": 1.800456483818904e-05, + "loss": 1.4433, + "step": 2709 + }, + { + "epoch": 0.28, + "learning_rate": 1.8002370381540672e-05, + "loss": 1.5005, + "step": 2710 + }, + { + "epoch": 0.28, + "learning_rate": 1.8000174852780282e-05, + "loss": 1.4945, + "step": 2711 + }, + { + "epoch": 0.28, + "learning_rate": 1.7997978252202023e-05, + "loss": 1.4298, + "step": 2712 + }, + { + "epoch": 0.28, + "learning_rate": 1.7995780580100177e-05, + "loss": 1.3812, + "step": 2713 + }, + { + "epoch": 0.28, + "learning_rate": 1.799358183676918e-05, + "loss": 1.5559, + "step": 2714 + }, + { + "epoch": 0.28, + "learning_rate": 1.79913820225036e-05, + "loss": 1.4316, + "step": 2715 + }, + { + "epoch": 0.28, + "learning_rate": 1.798918113759817e-05, + "loss": 1.419, + "step": 2716 + }, + { + "epoch": 0.28, + "learning_rate": 1.7986979182347733e-05, + "loss": 1.43, + "step": 2717 + }, + { + "epoch": 0.29, + "learning_rate": 1.798477615704731e-05, + "loss": 1.4964, + "step": 2718 + }, + { + "epoch": 0.29, + "learning_rate": 1.7982572061992044e-05, + "loss": 1.4417, + "step": 2719 + }, + { + "epoch": 0.29, + "learning_rate": 1.7980366897477227e-05, + "loss": 1.4562, + "step": 2720 + }, + { + "epoch": 0.29, + "learning_rate": 1.7978160663798295e-05, + "loss": 1.4386, + "step": 2721 + }, + { + "epoch": 0.29, + "learning_rate": 1.7975953361250824e-05, + "loss": 1.445, + "step": 2722 + }, + { + "epoch": 0.29, + "learning_rate": 1.797374499013054e-05, + "loss": 1.4549, + "step": 2723 + }, + { + "epoch": 0.29, + "learning_rate": 1.7971535550733305e-05, + "loss": 1.5205, + "step": 2724 + }, + { + "epoch": 0.29, + "learning_rate": 1.796932504335513e-05, + "loss": 1.4632, + "step": 2725 + }, + { + "epoch": 0.29, + "learning_rate": 1.796711346829216e-05, + "loss": 1.3767, + "step": 2726 + }, + { + "epoch": 0.29, + "learning_rate": 1.79649008258407e-05, + "loss": 1.4098, + "step": 2727 + }, + { + "epoch": 0.29, + "learning_rate": 1.7962687116297178e-05, + "loss": 1.4675, + "step": 2728 + }, + { + "epoch": 0.29, + "learning_rate": 1.7960472339958176e-05, + "loss": 1.6048, + "step": 2729 + }, + { + "epoch": 0.29, + "learning_rate": 1.7958256497120418e-05, + "loss": 1.5432, + "step": 2730 + }, + { + "epoch": 0.29, + "learning_rate": 1.7956039588080774e-05, + "loss": 1.5453, + "step": 2731 + }, + { + "epoch": 0.29, + "learning_rate": 1.7953821613136246e-05, + "loss": 1.4246, + "step": 2732 + }, + { + "epoch": 0.29, + "learning_rate": 1.7951602572583988e-05, + "loss": 1.3987, + "step": 2733 + }, + { + "epoch": 0.29, + "learning_rate": 1.7949382466721295e-05, + "loss": 1.4943, + "step": 2734 + }, + { + "epoch": 0.29, + "learning_rate": 1.7947161295845606e-05, + "loss": 1.4385, + "step": 2735 + }, + { + "epoch": 0.29, + "learning_rate": 1.7944939060254497e-05, + "loss": 1.4165, + "step": 2736 + }, + { + "epoch": 0.29, + "learning_rate": 1.7942715760245692e-05, + "loss": 1.4004, + "step": 2737 + }, + { + "epoch": 0.29, + "learning_rate": 1.7940491396117063e-05, + "loss": 1.4577, + "step": 2738 + }, + { + "epoch": 0.29, + "learning_rate": 1.7938265968166602e-05, + "loss": 1.4649, + "step": 2739 + }, + { + "epoch": 0.29, + "learning_rate": 1.7936039476692473e-05, + "loss": 1.5273, + "step": 2740 + }, + { + "epoch": 0.29, + "learning_rate": 1.7933811921992962e-05, + "loss": 1.4325, + "step": 2741 + }, + { + "epoch": 0.29, + "learning_rate": 1.793158330436651e-05, + "loss": 1.4388, + "step": 2742 + }, + { + "epoch": 0.29, + "learning_rate": 1.7929353624111687e-05, + "loss": 1.4124, + "step": 2743 + }, + { + "epoch": 0.29, + "learning_rate": 1.7927122881527222e-05, + "loss": 1.5449, + "step": 2744 + }, + { + "epoch": 0.29, + "learning_rate": 1.7924891076911964e-05, + "loss": 1.4728, + "step": 2745 + }, + { + "epoch": 0.29, + "learning_rate": 1.7922658210564932e-05, + "loss": 1.5103, + "step": 2746 + }, + { + "epoch": 0.29, + "learning_rate": 1.792042428278526e-05, + "loss": 1.5975, + "step": 2747 + }, + { + "epoch": 0.29, + "learning_rate": 1.7918189293872247e-05, + "loss": 1.567, + "step": 2748 + }, + { + "epoch": 0.29, + "learning_rate": 1.7915953244125318e-05, + "loss": 1.57, + "step": 2749 + }, + { + "epoch": 0.29, + "learning_rate": 1.791371613384405e-05, + "loss": 1.4372, + "step": 2750 + }, + { + "epoch": 0.29, + "learning_rate": 1.7911477963328155e-05, + "loss": 1.4053, + "step": 2751 + }, + { + "epoch": 0.29, + "learning_rate": 1.7909238732877492e-05, + "loss": 1.3782, + "step": 2752 + }, + { + "epoch": 0.29, + "learning_rate": 1.790699844279206e-05, + "loss": 1.4401, + "step": 2753 + }, + { + "epoch": 0.29, + "learning_rate": 1.7904757093372e-05, + "loss": 1.3749, + "step": 2754 + }, + { + "epoch": 0.29, + "learning_rate": 1.79025146849176e-05, + "loss": 1.4909, + "step": 2755 + }, + { + "epoch": 0.29, + "learning_rate": 1.7900271217729273e-05, + "loss": 1.4103, + "step": 2756 + }, + { + "epoch": 0.29, + "learning_rate": 1.7898026692107597e-05, + "loss": 1.4986, + "step": 2757 + }, + { + "epoch": 0.29, + "learning_rate": 1.7895781108353278e-05, + "loss": 1.5449, + "step": 2758 + }, + { + "epoch": 0.29, + "learning_rate": 1.789353446676717e-05, + "loss": 1.5583, + "step": 2759 + }, + { + "epoch": 0.29, + "learning_rate": 1.7891286767650254e-05, + "loss": 1.5342, + "step": 2760 + }, + { + "epoch": 0.29, + "learning_rate": 1.7889038011303673e-05, + "loss": 1.4233, + "step": 2761 + }, + { + "epoch": 0.29, + "learning_rate": 1.7886788198028707e-05, + "loss": 1.3433, + "step": 2762 + }, + { + "epoch": 0.29, + "learning_rate": 1.788453732812676e-05, + "loss": 1.4451, + "step": 2763 + }, + { + "epoch": 0.29, + "learning_rate": 1.78822854018994e-05, + "loss": 1.4506, + "step": 2764 + }, + { + "epoch": 0.29, + "learning_rate": 1.7880032419648324e-05, + "loss": 1.4386, + "step": 2765 + }, + { + "epoch": 0.29, + "learning_rate": 1.7877778381675374e-05, + "loss": 1.4512, + "step": 2766 + }, + { + "epoch": 0.29, + "learning_rate": 1.7875523288282535e-05, + "loss": 1.4319, + "step": 2767 + }, + { + "epoch": 0.29, + "learning_rate": 1.7873267139771932e-05, + "loss": 1.4753, + "step": 2768 + }, + { + "epoch": 0.29, + "learning_rate": 1.787100993644583e-05, + "loss": 1.4044, + "step": 2769 + }, + { + "epoch": 0.29, + "learning_rate": 1.786875167860663e-05, + "loss": 1.4382, + "step": 2770 + }, + { + "epoch": 0.29, + "learning_rate": 1.786649236655689e-05, + "loss": 1.3977, + "step": 2771 + }, + { + "epoch": 0.29, + "learning_rate": 1.7864232000599298e-05, + "loss": 1.4473, + "step": 2772 + }, + { + "epoch": 0.29, + "learning_rate": 1.7861970581036678e-05, + "loss": 1.4666, + "step": 2773 + }, + { + "epoch": 0.29, + "learning_rate": 1.785970810817201e-05, + "loss": 1.5299, + "step": 2774 + }, + { + "epoch": 0.29, + "learning_rate": 1.7857444582308402e-05, + "loss": 1.3974, + "step": 2775 + }, + { + "epoch": 0.29, + "learning_rate": 1.7855180003749114e-05, + "loss": 1.4603, + "step": 2776 + }, + { + "epoch": 0.29, + "learning_rate": 1.7852914372797535e-05, + "loss": 1.463, + "step": 2777 + }, + { + "epoch": 0.29, + "learning_rate": 1.7850647689757205e-05, + "loss": 1.5317, + "step": 2778 + }, + { + "epoch": 0.29, + "learning_rate": 1.78483799549318e-05, + "loss": 1.4669, + "step": 2779 + }, + { + "epoch": 0.29, + "learning_rate": 1.784611116862514e-05, + "loss": 1.5293, + "step": 2780 + }, + { + "epoch": 0.29, + "learning_rate": 1.7843841331141177e-05, + "loss": 1.5802, + "step": 2781 + }, + { + "epoch": 0.29, + "learning_rate": 1.7841570442784024e-05, + "loss": 1.4486, + "step": 2782 + }, + { + "epoch": 0.29, + "learning_rate": 1.7839298503857913e-05, + "loss": 1.4674, + "step": 2783 + }, + { + "epoch": 0.29, + "learning_rate": 1.7837025514667224e-05, + "loss": 1.4662, + "step": 2784 + }, + { + "epoch": 0.29, + "learning_rate": 1.7834751475516484e-05, + "loss": 1.3555, + "step": 2785 + }, + { + "epoch": 0.29, + "learning_rate": 1.783247638671035e-05, + "loss": 1.4307, + "step": 2786 + }, + { + "epoch": 0.29, + "eval_loss": 1.500258445739746, + "eval_runtime": 77.406, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 2786 + }, + { + "epoch": 0.29, + "learning_rate": 1.7830200248553633e-05, + "loss": 1.4596, + "step": 2787 + }, + { + "epoch": 0.29, + "learning_rate": 1.7827923061351273e-05, + "loss": 1.6118, + "step": 2788 + }, + { + "epoch": 0.29, + "learning_rate": 1.7825644825408353e-05, + "loss": 1.4782, + "step": 2789 + }, + { + "epoch": 0.29, + "learning_rate": 1.78233655410301e-05, + "loss": 1.4681, + "step": 2790 + }, + { + "epoch": 0.29, + "learning_rate": 1.782108520852188e-05, + "loss": 1.6281, + "step": 2791 + }, + { + "epoch": 0.29, + "learning_rate": 1.78188038281892e-05, + "loss": 1.4446, + "step": 2792 + }, + { + "epoch": 0.29, + "learning_rate": 1.7816521400337704e-05, + "loss": 1.479, + "step": 2793 + }, + { + "epoch": 0.29, + "learning_rate": 1.7814237925273178e-05, + "loss": 1.5457, + "step": 2794 + }, + { + "epoch": 0.29, + "learning_rate": 1.7811953403301547e-05, + "loss": 1.3928, + "step": 2795 + }, + { + "epoch": 0.29, + "learning_rate": 1.780966783472889e-05, + "loss": 1.4321, + "step": 2796 + }, + { + "epoch": 0.29, + "learning_rate": 1.78073812198614e-05, + "loss": 1.5734, + "step": 2797 + }, + { + "epoch": 0.29, + "learning_rate": 1.7805093559005432e-05, + "loss": 1.4356, + "step": 2798 + }, + { + "epoch": 0.29, + "learning_rate": 1.7802804852467473e-05, + "loss": 1.4656, + "step": 2799 + }, + { + "epoch": 0.29, + "learning_rate": 1.780051510055415e-05, + "loss": 1.4052, + "step": 2800 + }, + { + "epoch": 0.29, + "learning_rate": 1.7798224303572228e-05, + "loss": 1.4758, + "step": 2801 + }, + { + "epoch": 0.29, + "learning_rate": 1.7795932461828622e-05, + "loss": 1.4326, + "step": 2802 + }, + { + "epoch": 0.29, + "learning_rate": 1.7793639575630376e-05, + "loss": 1.3409, + "step": 2803 + }, + { + "epoch": 0.29, + "learning_rate": 1.7791345645284678e-05, + "loss": 1.4175, + "step": 2804 + }, + { + "epoch": 0.29, + "learning_rate": 1.7789050671098853e-05, + "loss": 1.383, + "step": 2805 + }, + { + "epoch": 0.29, + "learning_rate": 1.7786754653380373e-05, + "loss": 1.5162, + "step": 2806 + }, + { + "epoch": 0.29, + "learning_rate": 1.7784457592436847e-05, + "loss": 1.4899, + "step": 2807 + }, + { + "epoch": 0.29, + "learning_rate": 1.7782159488576016e-05, + "loss": 1.4874, + "step": 2808 + }, + { + "epoch": 0.29, + "learning_rate": 1.777986034210577e-05, + "loss": 1.4363, + "step": 2809 + }, + { + "epoch": 0.29, + "learning_rate": 1.7777560153334134e-05, + "loss": 1.4223, + "step": 2810 + }, + { + "epoch": 0.29, + "learning_rate": 1.7775258922569273e-05, + "loss": 1.4792, + "step": 2811 + }, + { + "epoch": 0.29, + "learning_rate": 1.77729566501195e-05, + "loss": 1.4475, + "step": 2812 + }, + { + "epoch": 0.29, + "learning_rate": 1.7770653336293253e-05, + "loss": 1.5157, + "step": 2813 + }, + { + "epoch": 0.3, + "learning_rate": 1.776834898139912e-05, + "loss": 1.389, + "step": 2814 + }, + { + "epoch": 0.3, + "learning_rate": 1.7766043585745824e-05, + "loss": 1.4358, + "step": 2815 + }, + { + "epoch": 0.3, + "learning_rate": 1.776373714964223e-05, + "loss": 1.4297, + "step": 2816 + }, + { + "epoch": 0.3, + "learning_rate": 1.7761429673397344e-05, + "loss": 1.4102, + "step": 2817 + }, + { + "epoch": 0.3, + "learning_rate": 1.77591211573203e-05, + "loss": 1.4572, + "step": 2818 + }, + { + "epoch": 0.3, + "learning_rate": 1.775681160172039e-05, + "loss": 1.448, + "step": 2819 + }, + { + "epoch": 0.3, + "learning_rate": 1.7754501006907025e-05, + "loss": 1.4426, + "step": 2820 + }, + { + "epoch": 0.3, + "learning_rate": 1.7752189373189773e-05, + "loss": 1.4566, + "step": 2821 + }, + { + "epoch": 0.3, + "learning_rate": 1.7749876700878332e-05, + "loss": 1.4267, + "step": 2822 + }, + { + "epoch": 0.3, + "learning_rate": 1.7747562990282538e-05, + "loss": 1.3951, + "step": 2823 + }, + { + "epoch": 0.3, + "learning_rate": 1.7745248241712373e-05, + "loss": 1.4668, + "step": 2824 + }, + { + "epoch": 0.3, + "learning_rate": 1.774293245547795e-05, + "loss": 1.4924, + "step": 2825 + }, + { + "epoch": 0.3, + "learning_rate": 1.7740615631889525e-05, + "loss": 1.5258, + "step": 2826 + }, + { + "epoch": 0.3, + "learning_rate": 1.7738297771257496e-05, + "loss": 1.4323, + "step": 2827 + }, + { + "epoch": 0.3, + "learning_rate": 1.7735978873892393e-05, + "loss": 1.439, + "step": 2828 + }, + { + "epoch": 0.3, + "learning_rate": 1.773365894010489e-05, + "loss": 1.5658, + "step": 2829 + }, + { + "epoch": 0.3, + "learning_rate": 1.77313379702058e-05, + "loss": 1.4607, + "step": 2830 + }, + { + "epoch": 0.3, + "learning_rate": 1.7729015964506073e-05, + "loss": 1.5544, + "step": 2831 + }, + { + "epoch": 0.3, + "learning_rate": 1.7726692923316798e-05, + "loss": 1.4232, + "step": 2832 + }, + { + "epoch": 0.3, + "learning_rate": 1.77243688469492e-05, + "loss": 1.415, + "step": 2833 + }, + { + "epoch": 0.3, + "learning_rate": 1.772204373571465e-05, + "loss": 1.4658, + "step": 2834 + }, + { + "epoch": 0.3, + "learning_rate": 1.7719717589924647e-05, + "loss": 1.4678, + "step": 2835 + }, + { + "epoch": 0.3, + "learning_rate": 1.771739040989084e-05, + "loss": 1.3021, + "step": 2836 + }, + { + "epoch": 0.3, + "learning_rate": 1.771506219592501e-05, + "loss": 1.4045, + "step": 2837 + }, + { + "epoch": 0.3, + "learning_rate": 1.7712732948339085e-05, + "loss": 1.4593, + "step": 2838 + }, + { + "epoch": 0.3, + "learning_rate": 1.7710402667445108e-05, + "loss": 1.4175, + "step": 2839 + }, + { + "epoch": 0.3, + "learning_rate": 1.770807135355529e-05, + "loss": 1.3939, + "step": 2840 + }, + { + "epoch": 0.3, + "learning_rate": 1.7705739006981963e-05, + "loss": 1.6089, + "step": 2841 + }, + { + "epoch": 0.3, + "learning_rate": 1.77034056280376e-05, + "loss": 1.3952, + "step": 2842 + }, + { + "epoch": 0.3, + "learning_rate": 1.7701071217034818e-05, + "loss": 1.5086, + "step": 2843 + }, + { + "epoch": 0.3, + "learning_rate": 1.7698735774286362e-05, + "loss": 1.4706, + "step": 2844 + }, + { + "epoch": 0.3, + "learning_rate": 1.7696399300105128e-05, + "loss": 1.4286, + "step": 2845 + }, + { + "epoch": 0.3, + "learning_rate": 1.7694061794804137e-05, + "loss": 1.4418, + "step": 2846 + }, + { + "epoch": 0.3, + "learning_rate": 1.7691723258696562e-05, + "loss": 1.516, + "step": 2847 + }, + { + "epoch": 0.3, + "learning_rate": 1.76893836920957e-05, + "loss": 1.4354, + "step": 2848 + }, + { + "epoch": 0.3, + "learning_rate": 1.7687043095314998e-05, + "loss": 1.7503, + "step": 2849 + }, + { + "epoch": 0.3, + "learning_rate": 1.7684701468668032e-05, + "loss": 1.5985, + "step": 2850 + }, + { + "epoch": 0.3, + "learning_rate": 1.768235881246852e-05, + "loss": 1.442, + "step": 2851 + }, + { + "epoch": 0.3, + "learning_rate": 1.7680015127030322e-05, + "loss": 1.4924, + "step": 2852 + }, + { + "epoch": 0.3, + "learning_rate": 1.7677670412667425e-05, + "loss": 1.4461, + "step": 2853 + }, + { + "epoch": 0.3, + "learning_rate": 1.7675324669693968e-05, + "loss": 1.3823, + "step": 2854 + }, + { + "epoch": 0.3, + "learning_rate": 1.767297789842421e-05, + "loss": 1.452, + "step": 2855 + }, + { + "epoch": 0.3, + "learning_rate": 1.767063009917257e-05, + "loss": 1.46, + "step": 2856 + }, + { + "epoch": 0.3, + "learning_rate": 1.7668281272253587e-05, + "loss": 1.4129, + "step": 2857 + }, + { + "epoch": 0.3, + "learning_rate": 1.766593141798194e-05, + "loss": 1.4057, + "step": 2858 + }, + { + "epoch": 0.3, + "learning_rate": 1.7663580536672456e-05, + "loss": 1.5162, + "step": 2859 + }, + { + "epoch": 0.3, + "learning_rate": 1.7661228628640087e-05, + "loss": 1.5177, + "step": 2860 + }, + { + "epoch": 0.3, + "learning_rate": 1.7658875694199933e-05, + "loss": 1.4548, + "step": 2861 + }, + { + "epoch": 0.3, + "learning_rate": 1.7656521733667223e-05, + "loss": 1.4511, + "step": 2862 + }, + { + "epoch": 0.3, + "learning_rate": 1.765416674735733e-05, + "loss": 1.4778, + "step": 2863 + }, + { + "epoch": 0.3, + "learning_rate": 1.765181073558576e-05, + "loss": 1.3935, + "step": 2864 + }, + { + "epoch": 0.3, + "learning_rate": 1.7649453698668156e-05, + "loss": 1.4659, + "step": 2865 + }, + { + "epoch": 0.3, + "learning_rate": 1.7647095636920305e-05, + "loss": 1.7042, + "step": 2866 + }, + { + "epoch": 0.3, + "learning_rate": 1.7644736550658124e-05, + "loss": 1.7957, + "step": 2867 + }, + { + "epoch": 0.3, + "learning_rate": 1.764237644019767e-05, + "loss": 1.5139, + "step": 2868 + }, + { + "epoch": 0.3, + "learning_rate": 1.764001530585514e-05, + "loss": 1.4117, + "step": 2869 + }, + { + "epoch": 0.3, + "learning_rate": 1.7637653147946858e-05, + "loss": 1.4837, + "step": 2870 + }, + { + "epoch": 0.3, + "learning_rate": 1.7635289966789298e-05, + "loss": 1.4379, + "step": 2871 + }, + { + "epoch": 0.3, + "learning_rate": 1.7632925762699068e-05, + "loss": 1.4491, + "step": 2872 + }, + { + "epoch": 0.3, + "learning_rate": 1.7630560535992905e-05, + "loss": 1.4006, + "step": 2873 + }, + { + "epoch": 0.3, + "learning_rate": 1.7628194286987694e-05, + "loss": 1.5484, + "step": 2874 + }, + { + "epoch": 0.3, + "learning_rate": 1.7625827016000446e-05, + "loss": 1.4926, + "step": 2875 + }, + { + "epoch": 0.3, + "learning_rate": 1.762345872334832e-05, + "loss": 1.3909, + "step": 2876 + }, + { + "epoch": 0.3, + "learning_rate": 1.76210894093486e-05, + "loss": 1.405, + "step": 2877 + }, + { + "epoch": 0.3, + "learning_rate": 1.7618719074318718e-05, + "loss": 1.4736, + "step": 2878 + }, + { + "epoch": 0.3, + "learning_rate": 1.7616347718576238e-05, + "loss": 1.4445, + "step": 2879 + }, + { + "epoch": 0.3, + "learning_rate": 1.761397534243886e-05, + "loss": 1.4878, + "step": 2880 + }, + { + "epoch": 0.3, + "learning_rate": 1.7611601946224417e-05, + "loss": 1.4414, + "step": 2881 + }, + { + "epoch": 0.3, + "learning_rate": 1.760922753025089e-05, + "loss": 1.5657, + "step": 2882 + }, + { + "epoch": 0.3, + "learning_rate": 1.7606852094836385e-05, + "loss": 1.5008, + "step": 2883 + }, + { + "epoch": 0.3, + "learning_rate": 1.7604475640299153e-05, + "loss": 1.4922, + "step": 2884 + }, + { + "epoch": 0.3, + "learning_rate": 1.7602098166957577e-05, + "loss": 1.7451, + "step": 2885 + }, + { + "epoch": 0.3, + "learning_rate": 1.759971967513017e-05, + "loss": 1.7077, + "step": 2886 + }, + { + "epoch": 0.3, + "learning_rate": 1.75973401651356e-05, + "loss": 1.3986, + "step": 2887 + }, + { + "epoch": 0.3, + "learning_rate": 1.7594959637292656e-05, + "loss": 1.3966, + "step": 2888 + }, + { + "epoch": 0.3, + "learning_rate": 1.7592578091920264e-05, + "loss": 1.4086, + "step": 2889 + }, + { + "epoch": 0.3, + "learning_rate": 1.7590195529337495e-05, + "loss": 1.4481, + "step": 2890 + }, + { + "epoch": 0.3, + "learning_rate": 1.7587811949863548e-05, + "loss": 1.3974, + "step": 2891 + }, + { + "epoch": 0.3, + "learning_rate": 1.7585427353817758e-05, + "loss": 1.5013, + "step": 2892 + }, + { + "epoch": 0.3, + "learning_rate": 1.7583041741519608e-05, + "loss": 1.5454, + "step": 2893 + }, + { + "epoch": 0.3, + "learning_rate": 1.7580655113288708e-05, + "loss": 1.5033, + "step": 2894 + }, + { + "epoch": 0.3, + "learning_rate": 1.7578267469444793e-05, + "loss": 1.4332, + "step": 2895 + }, + { + "epoch": 0.3, + "learning_rate": 1.757587881030776e-05, + "loss": 1.4667, + "step": 2896 + }, + { + "epoch": 0.3, + "learning_rate": 1.7573489136197623e-05, + "loss": 1.4314, + "step": 2897 + }, + { + "epoch": 0.3, + "learning_rate": 1.7571098447434532e-05, + "loss": 1.4514, + "step": 2898 + }, + { + "epoch": 0.3, + "learning_rate": 1.7568706744338784e-05, + "loss": 1.4872, + "step": 2899 + }, + { + "epoch": 0.3, + "learning_rate": 1.7566314027230808e-05, + "loss": 1.4841, + "step": 2900 + }, + { + "epoch": 0.3, + "learning_rate": 1.7563920296431158e-05, + "loss": 1.3964, + "step": 2901 + }, + { + "epoch": 0.3, + "learning_rate": 1.7561525552260538e-05, + "loss": 1.4932, + "step": 2902 + }, + { + "epoch": 0.3, + "learning_rate": 1.755912979503978e-05, + "loss": 1.4153, + "step": 2903 + }, + { + "epoch": 0.3, + "learning_rate": 1.755673302508986e-05, + "loss": 1.4939, + "step": 2904 + }, + { + "epoch": 0.3, + "learning_rate": 1.755433524273187e-05, + "loss": 1.4437, + "step": 2905 + }, + { + "epoch": 0.3, + "learning_rate": 1.7551936448287067e-05, + "loss": 1.486, + "step": 2906 + }, + { + "epoch": 0.3, + "learning_rate": 1.754953664207682e-05, + "loss": 1.4362, + "step": 2907 + }, + { + "epoch": 0.3, + "learning_rate": 1.7547135824422635e-05, + "loss": 1.4954, + "step": 2908 + }, + { + "epoch": 0.31, + "learning_rate": 1.7544733995646174e-05, + "loss": 1.4552, + "step": 2909 + }, + { + "epoch": 0.31, + "learning_rate": 1.7542331156069213e-05, + "loss": 1.4654, + "step": 2910 + }, + { + "epoch": 0.31, + "learning_rate": 1.753992730601367e-05, + "loss": 1.4531, + "step": 2911 + }, + { + "epoch": 0.31, + "learning_rate": 1.75375224458016e-05, + "loss": 1.4949, + "step": 2912 + }, + { + "epoch": 0.31, + "learning_rate": 1.753511657575519e-05, + "loss": 1.3998, + "step": 2913 + }, + { + "epoch": 0.31, + "learning_rate": 1.753270969619677e-05, + "loss": 1.3904, + "step": 2914 + }, + { + "epoch": 0.31, + "learning_rate": 1.7530301807448794e-05, + "loss": 1.481, + "step": 2915 + }, + { + "epoch": 0.31, + "learning_rate": 1.7527892909833864e-05, + "loss": 1.4301, + "step": 2916 + }, + { + "epoch": 0.31, + "learning_rate": 1.7525483003674707e-05, + "loss": 1.4377, + "step": 2917 + }, + { + "epoch": 0.31, + "learning_rate": 1.7523072089294188e-05, + "loss": 1.5077, + "step": 2918 + }, + { + "epoch": 0.31, + "learning_rate": 1.752066016701531e-05, + "loss": 1.3802, + "step": 2919 + }, + { + "epoch": 0.31, + "learning_rate": 1.7518247237161205e-05, + "loss": 1.3991, + "step": 2920 + }, + { + "epoch": 0.31, + "learning_rate": 1.7515833300055146e-05, + "loss": 1.4283, + "step": 2921 + }, + { + "epoch": 0.31, + "learning_rate": 1.7513418356020535e-05, + "loss": 1.3688, + "step": 2922 + }, + { + "epoch": 0.31, + "learning_rate": 1.751100240538092e-05, + "loss": 1.4336, + "step": 2923 + }, + { + "epoch": 0.31, + "learning_rate": 1.7508585448459967e-05, + "loss": 1.4302, + "step": 2924 + }, + { + "epoch": 0.31, + "learning_rate": 1.7506167485581493e-05, + "loss": 1.4293, + "step": 2925 + }, + { + "epoch": 0.31, + "learning_rate": 1.750374851706944e-05, + "loss": 1.4262, + "step": 2926 + }, + { + "epoch": 0.31, + "learning_rate": 1.7501328543247892e-05, + "loss": 1.4128, + "step": 2927 + }, + { + "epoch": 0.31, + "learning_rate": 1.7498907564441054e-05, + "loss": 1.4258, + "step": 2928 + }, + { + "epoch": 0.31, + "learning_rate": 1.749648558097328e-05, + "loss": 1.4904, + "step": 2929 + }, + { + "epoch": 0.31, + "learning_rate": 1.749406259316906e-05, + "loss": 1.4628, + "step": 2930 + }, + { + "epoch": 0.31, + "learning_rate": 1.7491638601353004e-05, + "loss": 1.4908, + "step": 2931 + }, + { + "epoch": 0.31, + "learning_rate": 1.7489213605849867e-05, + "loss": 1.4563, + "step": 2932 + }, + { + "epoch": 0.31, + "learning_rate": 1.7486787606984533e-05, + "loss": 1.5006, + "step": 2933 + }, + { + "epoch": 0.31, + "learning_rate": 1.748436060508203e-05, + "loss": 1.424, + "step": 2934 + }, + { + "epoch": 0.31, + "learning_rate": 1.7481932600467508e-05, + "loss": 1.4136, + "step": 2935 + }, + { + "epoch": 0.31, + "learning_rate": 1.747950359346626e-05, + "loss": 1.3835, + "step": 2936 + }, + { + "epoch": 0.31, + "learning_rate": 1.747707358440371e-05, + "loss": 1.5284, + "step": 2937 + }, + { + "epoch": 0.31, + "learning_rate": 1.7474642573605418e-05, + "loss": 1.4592, + "step": 2938 + }, + { + "epoch": 0.31, + "learning_rate": 1.7472210561397075e-05, + "loss": 1.5483, + "step": 2939 + }, + { + "epoch": 0.31, + "learning_rate": 1.746977754810451e-05, + "loss": 1.521, + "step": 2940 + }, + { + "epoch": 0.31, + "learning_rate": 1.7467343534053683e-05, + "loss": 1.4276, + "step": 2941 + }, + { + "epoch": 0.31, + "learning_rate": 1.746490851957069e-05, + "loss": 1.4302, + "step": 2942 + }, + { + "epoch": 0.31, + "learning_rate": 1.746247250498176e-05, + "loss": 1.4439, + "step": 2943 + }, + { + "epoch": 0.31, + "learning_rate": 1.7460035490613255e-05, + "loss": 1.4991, + "step": 2944 + }, + { + "epoch": 0.31, + "learning_rate": 1.7457597476791674e-05, + "loss": 1.4188, + "step": 2945 + }, + { + "epoch": 0.31, + "learning_rate": 1.7455158463843648e-05, + "loss": 1.4685, + "step": 2946 + }, + { + "epoch": 0.31, + "learning_rate": 1.745271845209594e-05, + "loss": 1.3811, + "step": 2947 + }, + { + "epoch": 0.31, + "learning_rate": 1.7450277441875454e-05, + "loss": 1.4869, + "step": 2948 + }, + { + "epoch": 0.31, + "learning_rate": 1.7447835433509218e-05, + "loss": 1.5001, + "step": 2949 + }, + { + "epoch": 0.31, + "learning_rate": 1.74453924273244e-05, + "loss": 1.4757, + "step": 2950 + }, + { + "epoch": 0.31, + "learning_rate": 1.74429484236483e-05, + "loss": 1.5072, + "step": 2951 + }, + { + "epoch": 0.31, + "learning_rate": 1.744050342280835e-05, + "loss": 1.4242, + "step": 2952 + }, + { + "epoch": 0.31, + "learning_rate": 1.743805742513212e-05, + "loss": 1.4462, + "step": 2953 + }, + { + "epoch": 0.31, + "learning_rate": 1.743561043094731e-05, + "loss": 1.6815, + "step": 2954 + }, + { + "epoch": 0.31, + "learning_rate": 1.7433162440581755e-05, + "loss": 1.427, + "step": 2955 + }, + { + "epoch": 0.31, + "learning_rate": 1.7430713454363423e-05, + "loss": 1.2933, + "step": 2956 + }, + { + "epoch": 0.31, + "learning_rate": 1.742826347262041e-05, + "loss": 1.4247, + "step": 2957 + }, + { + "epoch": 0.31, + "learning_rate": 1.7425812495680955e-05, + "loss": 1.399, + "step": 2958 + }, + { + "epoch": 0.31, + "learning_rate": 1.742336052387343e-05, + "loss": 1.4818, + "step": 2959 + }, + { + "epoch": 0.31, + "learning_rate": 1.742090755752633e-05, + "loss": 1.3839, + "step": 2960 + }, + { + "epoch": 0.31, + "learning_rate": 1.741845359696829e-05, + "loss": 1.4669, + "step": 2961 + }, + { + "epoch": 0.31, + "learning_rate": 1.741599864252808e-05, + "loss": 1.468, + "step": 2962 + }, + { + "epoch": 0.31, + "learning_rate": 1.74135426945346e-05, + "loss": 1.4135, + "step": 2963 + }, + { + "epoch": 0.31, + "learning_rate": 1.7411085753316882e-05, + "loss": 1.5899, + "step": 2964 + }, + { + "epoch": 0.31, + "learning_rate": 1.74086278192041e-05, + "loss": 1.6115, + "step": 2965 + }, + { + "epoch": 0.31, + "learning_rate": 1.740616889252554e-05, + "loss": 1.3988, + "step": 2966 + }, + { + "epoch": 0.31, + "learning_rate": 1.740370897361065e-05, + "loss": 1.5001, + "step": 2967 + }, + { + "epoch": 0.31, + "learning_rate": 1.740124806278899e-05, + "loss": 1.459, + "step": 2968 + }, + { + "epoch": 0.31, + "learning_rate": 1.7398786160390258e-05, + "loss": 1.4489, + "step": 2969 + }, + { + "epoch": 0.31, + "learning_rate": 1.7396323266744283e-05, + "loss": 1.4397, + "step": 2970 + }, + { + "epoch": 0.31, + "learning_rate": 1.7393859382181033e-05, + "loss": 1.4687, + "step": 2971 + }, + { + "epoch": 0.31, + "learning_rate": 1.7391394507030606e-05, + "loss": 1.4495, + "step": 2972 + }, + { + "epoch": 0.31, + "learning_rate": 1.738892864162323e-05, + "loss": 1.4745, + "step": 2973 + }, + { + "epoch": 0.31, + "learning_rate": 1.7386461786289274e-05, + "loss": 1.3943, + "step": 2974 + }, + { + "epoch": 0.31, + "learning_rate": 1.738399394135922e-05, + "loss": 1.4595, + "step": 2975 + }, + { + "epoch": 0.31, + "learning_rate": 1.738152510716371e-05, + "loss": 1.4023, + "step": 2976 + }, + { + "epoch": 0.31, + "learning_rate": 1.7379055284033493e-05, + "loss": 1.3938, + "step": 2977 + }, + { + "epoch": 0.31, + "learning_rate": 1.7376584472299468e-05, + "loss": 1.4576, + "step": 2978 + }, + { + "epoch": 0.31, + "learning_rate": 1.737411267229266e-05, + "loss": 1.424, + "step": 2979 + }, + { + "epoch": 0.31, + "learning_rate": 1.7371639884344225e-05, + "loss": 1.4224, + "step": 2980 + }, + { + "epoch": 0.31, + "learning_rate": 1.736916610878545e-05, + "loss": 1.4228, + "step": 2981 + }, + { + "epoch": 0.31, + "learning_rate": 1.7366691345947768e-05, + "loss": 1.5021, + "step": 2982 + }, + { + "epoch": 0.31, + "learning_rate": 1.736421559616272e-05, + "loss": 1.3589, + "step": 2983 + }, + { + "epoch": 0.31, + "learning_rate": 1.7361738859762007e-05, + "loss": 1.4748, + "step": 2984 + }, + { + "epoch": 0.31, + "learning_rate": 1.735926113707743e-05, + "loss": 1.3974, + "step": 2985 + }, + { + "epoch": 0.31, + "eval_loss": 1.4849082231521606, + "eval_runtime": 77.3271, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2985 + }, + { + "epoch": 0.31, + "learning_rate": 1.735678242844096e-05, + "loss": 1.392, + "step": 2986 + }, + { + "epoch": 0.31, + "learning_rate": 1.735430273418467e-05, + "loss": 1.4277, + "step": 2987 + }, + { + "epoch": 0.31, + "learning_rate": 1.735182205464077e-05, + "loss": 1.4216, + "step": 2988 + }, + { + "epoch": 0.31, + "learning_rate": 1.7349340390141617e-05, + "loss": 1.4546, + "step": 2989 + }, + { + "epoch": 0.31, + "learning_rate": 1.734685774101969e-05, + "loss": 1.4264, + "step": 2990 + }, + { + "epoch": 0.31, + "learning_rate": 1.7344374107607593e-05, + "loss": 1.4307, + "step": 2991 + }, + { + "epoch": 0.31, + "learning_rate": 1.7341889490238076e-05, + "loss": 1.4266, + "step": 2992 + }, + { + "epoch": 0.31, + "learning_rate": 1.7339403889244008e-05, + "loss": 1.4486, + "step": 2993 + }, + { + "epoch": 0.31, + "learning_rate": 1.7336917304958403e-05, + "loss": 1.4345, + "step": 2994 + }, + { + "epoch": 0.31, + "learning_rate": 1.7334429737714395e-05, + "loss": 1.476, + "step": 2995 + }, + { + "epoch": 0.31, + "learning_rate": 1.7331941187845248e-05, + "loss": 1.5148, + "step": 2996 + }, + { + "epoch": 0.31, + "learning_rate": 1.7329451655684372e-05, + "loss": 1.4026, + "step": 2997 + }, + { + "epoch": 0.31, + "learning_rate": 1.7326961141565303e-05, + "loss": 1.3935, + "step": 2998 + }, + { + "epoch": 0.31, + "learning_rate": 1.73244696458217e-05, + "loss": 1.4483, + "step": 2999 + }, + { + "epoch": 0.31, + "learning_rate": 1.7321977168787356e-05, + "loss": 1.5197, + "step": 3000 + }, + { + "epoch": 0.31, + "learning_rate": 1.7319483710796208e-05, + "loss": 1.4648, + "step": 3001 + }, + { + "epoch": 0.31, + "learning_rate": 1.7316989272182308e-05, + "loss": 1.4171, + "step": 3002 + }, + { + "epoch": 0.31, + "learning_rate": 1.731449385327985e-05, + "loss": 1.4541, + "step": 3003 + }, + { + "epoch": 0.32, + "learning_rate": 1.731199745442316e-05, + "loss": 1.4605, + "step": 3004 + }, + { + "epoch": 0.32, + "learning_rate": 1.7309500075946683e-05, + "loss": 1.5122, + "step": 3005 + }, + { + "epoch": 0.32, + "learning_rate": 1.7307001718185007e-05, + "loss": 1.5243, + "step": 3006 + }, + { + "epoch": 0.32, + "learning_rate": 1.7304502381472844e-05, + "loss": 1.4997, + "step": 3007 + }, + { + "epoch": 0.32, + "learning_rate": 1.730200206614505e-05, + "loss": 1.4891, + "step": 3008 + }, + { + "epoch": 0.32, + "learning_rate": 1.72995007725366e-05, + "loss": 1.4376, + "step": 3009 + }, + { + "epoch": 0.32, + "learning_rate": 1.7296998500982595e-05, + "loss": 1.4403, + "step": 3010 + }, + { + "epoch": 0.32, + "learning_rate": 1.7294495251818285e-05, + "loss": 1.5153, + "step": 3011 + }, + { + "epoch": 0.32, + "learning_rate": 1.729199102537904e-05, + "loss": 1.4996, + "step": 3012 + }, + { + "epoch": 0.32, + "learning_rate": 1.7289485822000356e-05, + "loss": 1.5302, + "step": 3013 + }, + { + "epoch": 0.32, + "learning_rate": 1.7286979642017867e-05, + "loss": 1.5641, + "step": 3014 + }, + { + "epoch": 0.32, + "learning_rate": 1.728447248576734e-05, + "loss": 1.438, + "step": 3015 + }, + { + "epoch": 0.32, + "learning_rate": 1.7281964353584674e-05, + "loss": 1.4796, + "step": 3016 + }, + { + "epoch": 0.32, + "learning_rate": 1.727945524580588e-05, + "loss": 1.4413, + "step": 3017 + }, + { + "epoch": 0.32, + "learning_rate": 1.727694516276713e-05, + "loss": 1.3966, + "step": 3018 + }, + { + "epoch": 0.32, + "learning_rate": 1.72744341048047e-05, + "loss": 1.5267, + "step": 3019 + }, + { + "epoch": 0.32, + "learning_rate": 1.727192207225501e-05, + "loss": 1.4284, + "step": 3020 + }, + { + "epoch": 0.32, + "learning_rate": 1.726940906545461e-05, + "loss": 1.5137, + "step": 3021 + }, + { + "epoch": 0.32, + "learning_rate": 1.7266895084740173e-05, + "loss": 1.3966, + "step": 3022 + }, + { + "epoch": 0.32, + "learning_rate": 1.7264380130448514e-05, + "loss": 1.4156, + "step": 3023 + }, + { + "epoch": 0.32, + "learning_rate": 1.726186420291657e-05, + "loss": 1.4644, + "step": 3024 + }, + { + "epoch": 0.32, + "learning_rate": 1.725934730248141e-05, + "loss": 1.4768, + "step": 3025 + }, + { + "epoch": 0.32, + "learning_rate": 1.7256829429480233e-05, + "loss": 1.4428, + "step": 3026 + }, + { + "epoch": 0.32, + "learning_rate": 1.7254310584250373e-05, + "loss": 1.4495, + "step": 3027 + }, + { + "epoch": 0.32, + "learning_rate": 1.725179076712929e-05, + "loss": 1.3867, + "step": 3028 + }, + { + "epoch": 0.32, + "learning_rate": 1.7249269978454567e-05, + "loss": 1.5011, + "step": 3029 + }, + { + "epoch": 0.32, + "learning_rate": 1.7246748218563937e-05, + "loss": 1.3916, + "step": 3030 + }, + { + "epoch": 0.32, + "learning_rate": 1.7244225487795238e-05, + "loss": 1.4984, + "step": 3031 + }, + { + "epoch": 0.32, + "learning_rate": 1.7241701786486464e-05, + "loss": 1.5776, + "step": 3032 + }, + { + "epoch": 0.32, + "learning_rate": 1.7239177114975717e-05, + "loss": 1.5018, + "step": 3033 + }, + { + "epoch": 0.32, + "learning_rate": 1.7236651473601244e-05, + "loss": 1.5042, + "step": 3034 + }, + { + "epoch": 0.32, + "learning_rate": 1.723412486270141e-05, + "loss": 1.4636, + "step": 3035 + }, + { + "epoch": 0.32, + "learning_rate": 1.723159728261472e-05, + "loss": 1.5612, + "step": 3036 + }, + { + "epoch": 0.32, + "learning_rate": 1.7229068733679803e-05, + "loss": 1.4399, + "step": 3037 + }, + { + "epoch": 0.32, + "learning_rate": 1.7226539216235424e-05, + "loss": 1.5635, + "step": 3038 + }, + { + "epoch": 0.32, + "learning_rate": 1.7224008730620468e-05, + "loss": 1.4329, + "step": 3039 + }, + { + "epoch": 0.32, + "learning_rate": 1.7221477277173956e-05, + "loss": 1.4886, + "step": 3040 + }, + { + "epoch": 0.32, + "learning_rate": 1.721894485623504e-05, + "loss": 1.4741, + "step": 3041 + }, + { + "epoch": 0.32, + "learning_rate": 1.7216411468143e-05, + "loss": 1.4678, + "step": 3042 + }, + { + "epoch": 0.32, + "learning_rate": 1.721387711323724e-05, + "loss": 1.4758, + "step": 3043 + }, + { + "epoch": 0.32, + "learning_rate": 1.72113417918573e-05, + "loss": 1.441, + "step": 3044 + }, + { + "epoch": 0.32, + "learning_rate": 1.7208805504342855e-05, + "loss": 1.4328, + "step": 3045 + }, + { + "epoch": 0.32, + "learning_rate": 1.720626825103369e-05, + "loss": 1.4254, + "step": 3046 + }, + { + "epoch": 0.32, + "learning_rate": 1.7203730032269744e-05, + "loss": 1.4462, + "step": 3047 + }, + { + "epoch": 0.32, + "learning_rate": 1.7201190848391066e-05, + "loss": 1.4826, + "step": 3048 + }, + { + "epoch": 0.32, + "learning_rate": 1.719865069973784e-05, + "loss": 1.4215, + "step": 3049 + }, + { + "epoch": 0.32, + "learning_rate": 1.7196109586650385e-05, + "loss": 1.4291, + "step": 3050 + }, + { + "epoch": 0.32, + "learning_rate": 1.7193567509469146e-05, + "loss": 1.5005, + "step": 3051 + }, + { + "epoch": 0.32, + "learning_rate": 1.719102446853469e-05, + "loss": 1.4216, + "step": 3052 + }, + { + "epoch": 0.32, + "learning_rate": 1.7188480464187725e-05, + "loss": 1.4349, + "step": 3053 + }, + { + "epoch": 0.32, + "learning_rate": 1.718593549676908e-05, + "loss": 1.4784, + "step": 3054 + }, + { + "epoch": 0.32, + "learning_rate": 1.7183389566619714e-05, + "loss": 1.4325, + "step": 3055 + }, + { + "epoch": 0.32, + "learning_rate": 1.7180842674080717e-05, + "loss": 1.5387, + "step": 3056 + }, + { + "epoch": 0.32, + "learning_rate": 1.717829481949331e-05, + "loss": 1.655, + "step": 3057 + }, + { + "epoch": 0.32, + "learning_rate": 1.717574600319883e-05, + "loss": 1.4623, + "step": 3058 + }, + { + "epoch": 0.32, + "learning_rate": 1.7173196225538768e-05, + "loss": 1.4646, + "step": 3059 + }, + { + "epoch": 0.32, + "learning_rate": 1.717064548685472e-05, + "loss": 1.4641, + "step": 3060 + }, + { + "epoch": 0.32, + "learning_rate": 1.7168093787488418e-05, + "loss": 1.4033, + "step": 3061 + }, + { + "epoch": 0.32, + "learning_rate": 1.7165541127781726e-05, + "loss": 1.4085, + "step": 3062 + }, + { + "epoch": 0.32, + "learning_rate": 1.716298750807664e-05, + "loss": 1.387, + "step": 3063 + }, + { + "epoch": 0.32, + "learning_rate": 1.7160432928715272e-05, + "loss": 1.4197, + "step": 3064 + }, + { + "epoch": 0.32, + "learning_rate": 1.7157877390039872e-05, + "loss": 1.4883, + "step": 3065 + }, + { + "epoch": 0.32, + "learning_rate": 1.7155320892392818e-05, + "loss": 1.4865, + "step": 3066 + }, + { + "epoch": 0.32, + "learning_rate": 1.715276343611662e-05, + "loss": 1.4532, + "step": 3067 + }, + { + "epoch": 0.32, + "learning_rate": 1.71502050215539e-05, + "loss": 1.3991, + "step": 3068 + }, + { + "epoch": 0.32, + "learning_rate": 1.7147645649047424e-05, + "loss": 1.4318, + "step": 3069 + }, + { + "epoch": 0.32, + "learning_rate": 1.714508531894009e-05, + "loss": 1.3616, + "step": 3070 + }, + { + "epoch": 0.32, + "learning_rate": 1.7142524031574904e-05, + "loss": 1.4481, + "step": 3071 + }, + { + "epoch": 0.32, + "learning_rate": 1.7139961787295022e-05, + "loss": 1.3897, + "step": 3072 + }, + { + "epoch": 0.32, + "learning_rate": 1.7137398586443716e-05, + "loss": 1.3128, + "step": 3073 + }, + { + "epoch": 0.32, + "learning_rate": 1.713483442936439e-05, + "loss": 1.4481, + "step": 3074 + }, + { + "epoch": 0.32, + "learning_rate": 1.713226931640057e-05, + "loss": 1.5374, + "step": 3075 + }, + { + "epoch": 0.32, + "learning_rate": 1.7129703247895923e-05, + "loss": 1.4247, + "step": 3076 + }, + { + "epoch": 0.32, + "learning_rate": 1.712713622419423e-05, + "loss": 1.4098, + "step": 3077 + }, + { + "epoch": 0.32, + "learning_rate": 1.7124568245639414e-05, + "loss": 1.4558, + "step": 3078 + }, + { + "epoch": 0.32, + "learning_rate": 1.7121999312575507e-05, + "loss": 1.4484, + "step": 3079 + }, + { + "epoch": 0.32, + "learning_rate": 1.711942942534669e-05, + "loss": 1.4236, + "step": 3080 + }, + { + "epoch": 0.32, + "learning_rate": 1.7116858584297253e-05, + "loss": 1.613, + "step": 3081 + }, + { + "epoch": 0.32, + "learning_rate": 1.711428678977163e-05, + "loss": 1.4503, + "step": 3082 + }, + { + "epoch": 0.32, + "learning_rate": 1.7111714042114376e-05, + "loss": 1.4072, + "step": 3083 + }, + { + "epoch": 0.32, + "learning_rate": 1.7109140341670168e-05, + "loss": 1.5999, + "step": 3084 + }, + { + "epoch": 0.32, + "learning_rate": 1.7106565688783815e-05, + "loss": 1.4129, + "step": 3085 + }, + { + "epoch": 0.32, + "learning_rate": 1.710399008380026e-05, + "loss": 1.3973, + "step": 3086 + }, + { + "epoch": 0.32, + "learning_rate": 1.710141352706456e-05, + "loss": 1.4292, + "step": 3087 + }, + { + "epoch": 0.32, + "learning_rate": 1.709883601892192e-05, + "loss": 1.4372, + "step": 3088 + }, + { + "epoch": 0.32, + "learning_rate": 1.7096257559717647e-05, + "loss": 1.4924, + "step": 3089 + }, + { + "epoch": 0.32, + "learning_rate": 1.7093678149797196e-05, + "loss": 1.4222, + "step": 3090 + }, + { + "epoch": 0.32, + "learning_rate": 1.7091097789506137e-05, + "loss": 1.4797, + "step": 3091 + }, + { + "epoch": 0.32, + "learning_rate": 1.7088516479190175e-05, + "loss": 1.4738, + "step": 3092 + }, + { + "epoch": 0.32, + "learning_rate": 1.708593421919514e-05, + "loss": 1.5371, + "step": 3093 + }, + { + "epoch": 0.32, + "learning_rate": 1.7083351009866988e-05, + "loss": 1.3802, + "step": 3094 + }, + { + "epoch": 0.32, + "learning_rate": 1.7080766851551795e-05, + "loss": 1.4292, + "step": 3095 + }, + { + "epoch": 0.32, + "learning_rate": 1.707818174459578e-05, + "loss": 1.4478, + "step": 3096 + }, + { + "epoch": 0.32, + "learning_rate": 1.7075595689345285e-05, + "loss": 1.4619, + "step": 3097 + }, + { + "epoch": 0.32, + "learning_rate": 1.7073008686146763e-05, + "loss": 1.4603, + "step": 3098 + }, + { + "epoch": 0.32, + "learning_rate": 1.7070420735346815e-05, + "loss": 1.4548, + "step": 3099 + }, + { + "epoch": 0.33, + "learning_rate": 1.7067831837292157e-05, + "loss": 1.3638, + "step": 3100 + }, + { + "epoch": 0.33, + "learning_rate": 1.7065241992329634e-05, + "loss": 1.4284, + "step": 3101 + }, + { + "epoch": 0.33, + "learning_rate": 1.7062651200806217e-05, + "loss": 1.386, + "step": 3102 + }, + { + "epoch": 0.33, + "learning_rate": 1.7060059463069013e-05, + "loss": 1.5483, + "step": 3103 + }, + { + "epoch": 0.33, + "learning_rate": 1.705746677946524e-05, + "loss": 1.4963, + "step": 3104 + }, + { + "epoch": 0.33, + "learning_rate": 1.7054873150342257e-05, + "loss": 1.4539, + "step": 3105 + }, + { + "epoch": 0.33, + "learning_rate": 1.705227857604754e-05, + "loss": 1.4361, + "step": 3106 + }, + { + "epoch": 0.33, + "learning_rate": 1.7049683056928695e-05, + "loss": 1.3735, + "step": 3107 + }, + { + "epoch": 0.33, + "learning_rate": 1.7047086593333454e-05, + "loss": 1.4324, + "step": 3108 + }, + { + "epoch": 0.33, + "learning_rate": 1.7044489185609685e-05, + "loss": 1.5037, + "step": 3109 + }, + { + "epoch": 0.33, + "learning_rate": 1.704189083410536e-05, + "loss": 1.3913, + "step": 3110 + }, + { + "epoch": 0.33, + "learning_rate": 1.7039291539168604e-05, + "loss": 1.3233, + "step": 3111 + }, + { + "epoch": 0.33, + "learning_rate": 1.703669130114765e-05, + "loss": 1.4897, + "step": 3112 + }, + { + "epoch": 0.33, + "learning_rate": 1.7034090120390862e-05, + "loss": 1.4843, + "step": 3113 + }, + { + "epoch": 0.33, + "learning_rate": 1.7031487997246735e-05, + "loss": 1.3674, + "step": 3114 + }, + { + "epoch": 0.33, + "learning_rate": 1.7028884932063883e-05, + "loss": 1.4475, + "step": 3115 + }, + { + "epoch": 0.33, + "learning_rate": 1.702628092519105e-05, + "loss": 1.4134, + "step": 3116 + }, + { + "epoch": 0.33, + "learning_rate": 1.7023675976977108e-05, + "loss": 1.4484, + "step": 3117 + }, + { + "epoch": 0.33, + "learning_rate": 1.702107008777106e-05, + "loss": 1.407, + "step": 3118 + }, + { + "epoch": 0.33, + "learning_rate": 1.7018463257922005e-05, + "loss": 1.5443, + "step": 3119 + }, + { + "epoch": 0.33, + "learning_rate": 1.701585548777922e-05, + "loss": 1.4548, + "step": 3120 + }, + { + "epoch": 0.33, + "learning_rate": 1.7013246777692063e-05, + "loss": 1.4252, + "step": 3121 + }, + { + "epoch": 0.33, + "learning_rate": 1.7010637128010037e-05, + "loss": 1.3748, + "step": 3122 + }, + { + "epoch": 0.33, + "learning_rate": 1.7008026539082767e-05, + "loss": 1.3804, + "step": 3123 + }, + { + "epoch": 0.33, + "learning_rate": 1.7005415011260008e-05, + "loss": 1.4203, + "step": 3124 + }, + { + "epoch": 0.33, + "learning_rate": 1.7002802544891634e-05, + "loss": 1.4195, + "step": 3125 + }, + { + "epoch": 0.33, + "learning_rate": 1.700018914032765e-05, + "loss": 1.4188, + "step": 3126 + }, + { + "epoch": 0.33, + "learning_rate": 1.699757479791819e-05, + "loss": 1.3884, + "step": 3127 + }, + { + "epoch": 0.33, + "learning_rate": 1.6994959518013502e-05, + "loss": 1.4111, + "step": 3128 + }, + { + "epoch": 0.33, + "learning_rate": 1.6992343300963963e-05, + "loss": 1.5452, + "step": 3129 + }, + { + "epoch": 0.33, + "learning_rate": 1.6989726147120087e-05, + "loss": 1.4097, + "step": 3130 + }, + { + "epoch": 0.33, + "learning_rate": 1.6987108056832506e-05, + "loss": 1.481, + "step": 3131 + }, + { + "epoch": 0.33, + "learning_rate": 1.6984489030451973e-05, + "loss": 1.4505, + "step": 3132 + }, + { + "epoch": 0.33, + "learning_rate": 1.6981869068329368e-05, + "loss": 1.4281, + "step": 3133 + }, + { + "epoch": 0.33, + "learning_rate": 1.69792481708157e-05, + "loss": 1.4555, + "step": 3134 + }, + { + "epoch": 0.33, + "learning_rate": 1.6976626338262103e-05, + "loss": 1.4525, + "step": 3135 + }, + { + "epoch": 0.33, + "learning_rate": 1.6974003571019837e-05, + "loss": 1.3765, + "step": 3136 + }, + { + "epoch": 0.33, + "learning_rate": 1.6971379869440286e-05, + "loss": 1.3998, + "step": 3137 + }, + { + "epoch": 0.33, + "learning_rate": 1.696875523387495e-05, + "loss": 1.5103, + "step": 3138 + }, + { + "epoch": 0.33, + "learning_rate": 1.6966129664675474e-05, + "loss": 1.427, + "step": 3139 + }, + { + "epoch": 0.33, + "learning_rate": 1.6963503162193612e-05, + "loss": 1.4362, + "step": 3140 + }, + { + "epoch": 0.33, + "learning_rate": 1.6960875726781246e-05, + "loss": 1.4073, + "step": 3141 + }, + { + "epoch": 0.33, + "learning_rate": 1.6958247358790388e-05, + "loss": 1.4014, + "step": 3142 + }, + { + "epoch": 0.33, + "learning_rate": 1.6955618058573165e-05, + "loss": 1.4244, + "step": 3143 + }, + { + "epoch": 0.33, + "learning_rate": 1.6952987826481847e-05, + "loss": 1.47, + "step": 3144 + }, + { + "epoch": 0.33, + "learning_rate": 1.6950356662868814e-05, + "loss": 1.5112, + "step": 3145 + }, + { + "epoch": 0.33, + "learning_rate": 1.6947724568086562e-05, + "loss": 1.3398, + "step": 3146 + }, + { + "epoch": 0.33, + "learning_rate": 1.694509154248774e-05, + "loss": 1.4584, + "step": 3147 + }, + { + "epoch": 0.33, + "learning_rate": 1.69424575864251e-05, + "loss": 1.4383, + "step": 3148 + }, + { + "epoch": 0.33, + "learning_rate": 1.6939822700251523e-05, + "loss": 1.3869, + "step": 3149 + }, + { + "epoch": 0.33, + "learning_rate": 1.6937186884320015e-05, + "loss": 1.4453, + "step": 3150 + }, + { + "epoch": 0.33, + "learning_rate": 1.6934550138983713e-05, + "loss": 1.3355, + "step": 3151 + }, + { + "epoch": 0.33, + "learning_rate": 1.6931912464595866e-05, + "loss": 1.5573, + "step": 3152 + }, + { + "epoch": 0.33, + "learning_rate": 1.6929273861509865e-05, + "loss": 1.439, + "step": 3153 + }, + { + "epoch": 0.33, + "learning_rate": 1.6926634330079203e-05, + "loss": 1.6079, + "step": 3154 + }, + { + "epoch": 0.33, + "learning_rate": 1.692399387065752e-05, + "loss": 1.6973, + "step": 3155 + }, + { + "epoch": 0.33, + "learning_rate": 1.692135248359856e-05, + "loss": 1.3769, + "step": 3156 + }, + { + "epoch": 0.33, + "learning_rate": 1.6918710169256206e-05, + "loss": 1.4454, + "step": 3157 + }, + { + "epoch": 0.33, + "learning_rate": 1.691606692798446e-05, + "loss": 1.4495, + "step": 3158 + }, + { + "epoch": 0.33, + "learning_rate": 1.691342276013745e-05, + "loss": 1.4292, + "step": 3159 + }, + { + "epoch": 0.33, + "learning_rate": 1.691077766606942e-05, + "loss": 1.4405, + "step": 3160 + }, + { + "epoch": 0.33, + "learning_rate": 1.6908131646134757e-05, + "loss": 1.3683, + "step": 3161 + }, + { + "epoch": 0.33, + "learning_rate": 1.690548470068795e-05, + "loss": 1.4731, + "step": 3162 + }, + { + "epoch": 0.33, + "learning_rate": 1.690283683008362e-05, + "loss": 1.4323, + "step": 3163 + }, + { + "epoch": 0.33, + "learning_rate": 1.6900188034676518e-05, + "loss": 1.5133, + "step": 3164 + }, + { + "epoch": 0.33, + "learning_rate": 1.6897538314821516e-05, + "loss": 1.5529, + "step": 3165 + }, + { + "epoch": 0.33, + "learning_rate": 1.6894887670873605e-05, + "loss": 1.4427, + "step": 3166 + }, + { + "epoch": 0.33, + "learning_rate": 1.6892236103187904e-05, + "loss": 1.4344, + "step": 3167 + }, + { + "epoch": 0.33, + "learning_rate": 1.6889583612119657e-05, + "loss": 1.4291, + "step": 3168 + }, + { + "epoch": 0.33, + "learning_rate": 1.6886930198024226e-05, + "loss": 1.4683, + "step": 3169 + }, + { + "epoch": 0.33, + "learning_rate": 1.6884275861257106e-05, + "loss": 1.4442, + "step": 3170 + }, + { + "epoch": 0.33, + "learning_rate": 1.6881620602173905e-05, + "loss": 1.4509, + "step": 3171 + }, + { + "epoch": 0.33, + "learning_rate": 1.6878964421130362e-05, + "loss": 1.5113, + "step": 3172 + }, + { + "epoch": 0.33, + "learning_rate": 1.6876307318482334e-05, + "loss": 1.4261, + "step": 3173 + }, + { + "epoch": 0.33, + "learning_rate": 1.6873649294585805e-05, + "loss": 1.445, + "step": 3174 + }, + { + "epoch": 0.33, + "learning_rate": 1.6870990349796886e-05, + "loss": 1.4603, + "step": 3175 + }, + { + "epoch": 0.33, + "learning_rate": 1.68683304844718e-05, + "loss": 1.41, + "step": 3176 + }, + { + "epoch": 0.33, + "learning_rate": 1.686566969896691e-05, + "loss": 1.4018, + "step": 3177 + }, + { + "epoch": 0.33, + "learning_rate": 1.6863007993638687e-05, + "loss": 1.422, + "step": 3178 + }, + { + "epoch": 0.33, + "learning_rate": 1.6860345368843727e-05, + "loss": 1.4412, + "step": 3179 + }, + { + "epoch": 0.33, + "learning_rate": 1.6857681824938768e-05, + "loss": 1.5411, + "step": 3180 + }, + { + "epoch": 0.33, + "learning_rate": 1.685501736228064e-05, + "loss": 1.4416, + "step": 3181 + }, + { + "epoch": 0.33, + "learning_rate": 1.685235198122632e-05, + "loss": 1.5113, + "step": 3182 + }, + { + "epoch": 0.33, + "learning_rate": 1.6849685682132903e-05, + "loss": 1.423, + "step": 3183 + }, + { + "epoch": 0.33, + "learning_rate": 1.68470184653576e-05, + "loss": 1.404, + "step": 3184 + }, + { + "epoch": 0.33, + "eval_loss": 1.4771089553833008, + "eval_runtime": 77.4034, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3184 + }, + { + "epoch": 0.33, + "learning_rate": 1.6844350331257747e-05, + "loss": 1.4624, + "step": 3185 + }, + { + "epoch": 0.33, + "learning_rate": 1.6841681280190814e-05, + "loss": 1.4306, + "step": 3186 + }, + { + "epoch": 0.33, + "learning_rate": 1.683901131251438e-05, + "loss": 1.42, + "step": 3187 + }, + { + "epoch": 0.33, + "learning_rate": 1.6836340428586155e-05, + "loss": 1.4787, + "step": 3188 + }, + { + "epoch": 0.33, + "learning_rate": 1.6833668628763965e-05, + "loss": 1.3485, + "step": 3189 + }, + { + "epoch": 0.33, + "learning_rate": 1.683099591340576e-05, + "loss": 1.3674, + "step": 3190 + }, + { + "epoch": 0.33, + "learning_rate": 1.6828322282869627e-05, + "loss": 1.5187, + "step": 3191 + }, + { + "epoch": 0.33, + "learning_rate": 1.682564773751375e-05, + "loss": 1.4847, + "step": 3192 + }, + { + "epoch": 0.33, + "learning_rate": 1.682297227769646e-05, + "loss": 1.4815, + "step": 3193 + }, + { + "epoch": 0.33, + "learning_rate": 1.682029590377619e-05, + "loss": 1.4281, + "step": 3194 + }, + { + "epoch": 0.34, + "learning_rate": 1.6817618616111517e-05, + "loss": 1.4734, + "step": 3195 + }, + { + "epoch": 0.34, + "learning_rate": 1.681494041506112e-05, + "loss": 1.4861, + "step": 3196 + }, + { + "epoch": 0.34, + "learning_rate": 1.6812261300983808e-05, + "loss": 1.4372, + "step": 3197 + }, + { + "epoch": 0.34, + "learning_rate": 1.680958127423852e-05, + "loss": 1.4396, + "step": 3198 + }, + { + "epoch": 0.34, + "learning_rate": 1.680690033518431e-05, + "loss": 1.4225, + "step": 3199 + }, + { + "epoch": 0.34, + "learning_rate": 1.6804218484180347e-05, + "loss": 1.4925, + "step": 3200 + }, + { + "epoch": 0.34, + "learning_rate": 1.6801535721585942e-05, + "loss": 1.4306, + "step": 3201 + }, + { + "epoch": 0.34, + "learning_rate": 1.6798852047760506e-05, + "loss": 1.4298, + "step": 3202 + }, + { + "epoch": 0.34, + "learning_rate": 1.6796167463063588e-05, + "loss": 1.4725, + "step": 3203 + }, + { + "epoch": 0.34, + "learning_rate": 1.679348196785485e-05, + "loss": 1.4648, + "step": 3204 + }, + { + "epoch": 0.34, + "learning_rate": 1.6790795562494087e-05, + "loss": 1.4152, + "step": 3205 + }, + { + "epoch": 0.34, + "learning_rate": 1.6788108247341198e-05, + "loss": 1.4637, + "step": 3206 + }, + { + "epoch": 0.34, + "learning_rate": 1.6785420022756216e-05, + "loss": 1.4077, + "step": 3207 + }, + { + "epoch": 0.34, + "learning_rate": 1.67827308890993e-05, + "loss": 1.4585, + "step": 3208 + }, + { + "epoch": 0.34, + "learning_rate": 1.678004084673072e-05, + "loss": 1.3747, + "step": 3209 + }, + { + "epoch": 0.34, + "learning_rate": 1.6777349896010876e-05, + "loss": 1.4264, + "step": 3210 + }, + { + "epoch": 0.34, + "learning_rate": 1.677465803730028e-05, + "loss": 1.4178, + "step": 3211 + }, + { + "epoch": 0.34, + "learning_rate": 1.6771965270959584e-05, + "loss": 1.3876, + "step": 3212 + }, + { + "epoch": 0.34, + "learning_rate": 1.6769271597349538e-05, + "loss": 1.4658, + "step": 3213 + }, + { + "epoch": 0.34, + "learning_rate": 1.6766577016831026e-05, + "loss": 1.3968, + "step": 3214 + }, + { + "epoch": 0.34, + "learning_rate": 1.676388152976506e-05, + "loss": 1.5015, + "step": 3215 + }, + { + "epoch": 0.34, + "learning_rate": 1.6761185136512756e-05, + "loss": 1.4121, + "step": 3216 + }, + { + "epoch": 0.34, + "learning_rate": 1.675848783743537e-05, + "loss": 1.4146, + "step": 3217 + }, + { + "epoch": 0.34, + "learning_rate": 1.675578963289427e-05, + "loss": 1.4113, + "step": 3218 + }, + { + "epoch": 0.34, + "learning_rate": 1.6753090523250937e-05, + "loss": 1.4048, + "step": 3219 + }, + { + "epoch": 0.34, + "learning_rate": 1.6750390508866994e-05, + "loss": 1.4959, + "step": 3220 + }, + { + "epoch": 0.34, + "learning_rate": 1.6747689590104167e-05, + "loss": 1.4445, + "step": 3221 + }, + { + "epoch": 0.34, + "learning_rate": 1.6744987767324312e-05, + "loss": 1.4611, + "step": 3222 + }, + { + "epoch": 0.34, + "learning_rate": 1.67422850408894e-05, + "loss": 1.4141, + "step": 3223 + }, + { + "epoch": 0.34, + "learning_rate": 1.6739581411161535e-05, + "loss": 1.4218, + "step": 3224 + }, + { + "epoch": 0.34, + "learning_rate": 1.6736876878502925e-05, + "loss": 1.4266, + "step": 3225 + }, + { + "epoch": 0.34, + "learning_rate": 1.6734171443275913e-05, + "loss": 1.4941, + "step": 3226 + }, + { + "epoch": 0.34, + "learning_rate": 1.6731465105842955e-05, + "loss": 1.4294, + "step": 3227 + }, + { + "epoch": 0.34, + "learning_rate": 1.6728757866566635e-05, + "loss": 1.4189, + "step": 3228 + }, + { + "epoch": 0.34, + "learning_rate": 1.6726049725809647e-05, + "loss": 1.4713, + "step": 3229 + }, + { + "epoch": 0.34, + "learning_rate": 1.6723340683934818e-05, + "loss": 1.4203, + "step": 3230 + }, + { + "epoch": 0.34, + "learning_rate": 1.6720630741305088e-05, + "loss": 1.4112, + "step": 3231 + }, + { + "epoch": 0.34, + "learning_rate": 1.6717919898283523e-05, + "loss": 1.3811, + "step": 3232 + }, + { + "epoch": 0.34, + "learning_rate": 1.6715208155233296e-05, + "loss": 1.4242, + "step": 3233 + }, + { + "epoch": 0.34, + "learning_rate": 1.6712495512517725e-05, + "loss": 1.4207, + "step": 3234 + }, + { + "epoch": 0.34, + "learning_rate": 1.6709781970500222e-05, + "loss": 1.4888, + "step": 3235 + }, + { + "epoch": 0.34, + "learning_rate": 1.670706752954434e-05, + "loss": 1.4501, + "step": 3236 + }, + { + "epoch": 0.34, + "learning_rate": 1.670435219001374e-05, + "loss": 1.4367, + "step": 3237 + }, + { + "epoch": 0.34, + "learning_rate": 1.6701635952272212e-05, + "loss": 1.3959, + "step": 3238 + }, + { + "epoch": 0.34, + "learning_rate": 1.6698918816683655e-05, + "loss": 1.4257, + "step": 3239 + }, + { + "epoch": 0.34, + "learning_rate": 1.6696200783612102e-05, + "loss": 1.4718, + "step": 3240 + }, + { + "epoch": 0.34, + "learning_rate": 1.6693481853421697e-05, + "loss": 1.5899, + "step": 3241 + }, + { + "epoch": 0.34, + "learning_rate": 1.6690762026476707e-05, + "loss": 1.418, + "step": 3242 + }, + { + "epoch": 0.34, + "learning_rate": 1.668804130314152e-05, + "loss": 1.4076, + "step": 3243 + }, + { + "epoch": 0.34, + "learning_rate": 1.6685319683780645e-05, + "loss": 1.4571, + "step": 3244 + }, + { + "epoch": 0.34, + "learning_rate": 1.66825971687587e-05, + "loss": 1.4066, + "step": 3245 + }, + { + "epoch": 0.34, + "learning_rate": 1.6679873758440442e-05, + "loss": 1.4639, + "step": 3246 + }, + { + "epoch": 0.34, + "learning_rate": 1.6677149453190732e-05, + "loss": 1.453, + "step": 3247 + }, + { + "epoch": 0.34, + "learning_rate": 1.6674424253374558e-05, + "loss": 1.4262, + "step": 3248 + }, + { + "epoch": 0.34, + "learning_rate": 1.667169815935703e-05, + "loss": 1.3687, + "step": 3249 + }, + { + "epoch": 0.34, + "learning_rate": 1.6668971171503372e-05, + "loss": 1.5557, + "step": 3250 + }, + { + "epoch": 0.34, + "learning_rate": 1.6666243290178933e-05, + "loss": 1.4639, + "step": 3251 + }, + { + "epoch": 0.34, + "learning_rate": 1.6663514515749172e-05, + "loss": 1.4334, + "step": 3252 + }, + { + "epoch": 0.34, + "learning_rate": 1.6660784848579685e-05, + "loss": 1.3523, + "step": 3253 + }, + { + "epoch": 0.34, + "learning_rate": 1.6658054289036166e-05, + "loss": 1.3738, + "step": 3254 + }, + { + "epoch": 0.34, + "learning_rate": 1.665532283748445e-05, + "loss": 1.4159, + "step": 3255 + }, + { + "epoch": 0.34, + "learning_rate": 1.6652590494290474e-05, + "loss": 1.3609, + "step": 3256 + }, + { + "epoch": 0.34, + "learning_rate": 1.6649857259820303e-05, + "loss": 1.4449, + "step": 3257 + }, + { + "epoch": 0.34, + "learning_rate": 1.6647123134440126e-05, + "loss": 1.424, + "step": 3258 + }, + { + "epoch": 0.34, + "learning_rate": 1.664438811851624e-05, + "loss": 1.4737, + "step": 3259 + }, + { + "epoch": 0.34, + "learning_rate": 1.6641652212415066e-05, + "loss": 1.2717, + "step": 3260 + }, + { + "epoch": 0.34, + "learning_rate": 1.663891541650315e-05, + "loss": 1.4845, + "step": 3261 + }, + { + "epoch": 0.34, + "learning_rate": 1.663617773114715e-05, + "loss": 1.4115, + "step": 3262 + }, + { + "epoch": 0.34, + "learning_rate": 1.663343915671384e-05, + "loss": 1.4237, + "step": 3263 + }, + { + "epoch": 0.34, + "learning_rate": 1.6630699693570127e-05, + "loss": 1.4209, + "step": 3264 + }, + { + "epoch": 0.34, + "learning_rate": 1.6627959342083026e-05, + "loss": 1.506, + "step": 3265 + }, + { + "epoch": 0.34, + "learning_rate": 1.6625218102619672e-05, + "loss": 1.4466, + "step": 3266 + }, + { + "epoch": 0.34, + "learning_rate": 1.6622475975547324e-05, + "loss": 1.4129, + "step": 3267 + }, + { + "epoch": 0.34, + "learning_rate": 1.661973296123335e-05, + "loss": 1.4152, + "step": 3268 + }, + { + "epoch": 0.34, + "learning_rate": 1.661698906004525e-05, + "loss": 1.43, + "step": 3269 + }, + { + "epoch": 0.34, + "learning_rate": 1.661424427235064e-05, + "loss": 1.4701, + "step": 3270 + }, + { + "epoch": 0.34, + "learning_rate": 1.6611498598517238e-05, + "loss": 1.4598, + "step": 3271 + }, + { + "epoch": 0.34, + "learning_rate": 1.66087520389129e-05, + "loss": 1.4795, + "step": 3272 + }, + { + "epoch": 0.34, + "learning_rate": 1.6606004593905595e-05, + "loss": 1.5264, + "step": 3273 + }, + { + "epoch": 0.34, + "learning_rate": 1.6603256263863415e-05, + "loss": 1.4412, + "step": 3274 + }, + { + "epoch": 0.34, + "learning_rate": 1.6600507049154556e-05, + "loss": 1.45, + "step": 3275 + }, + { + "epoch": 0.34, + "learning_rate": 1.659775695014735e-05, + "loss": 1.4985, + "step": 3276 + }, + { + "epoch": 0.34, + "learning_rate": 1.659500596721024e-05, + "loss": 1.496, + "step": 3277 + }, + { + "epoch": 0.34, + "learning_rate": 1.6592254100711775e-05, + "loss": 1.4386, + "step": 3278 + }, + { + "epoch": 0.34, + "learning_rate": 1.658950135102065e-05, + "loss": 1.4073, + "step": 3279 + }, + { + "epoch": 0.34, + "learning_rate": 1.658674771850565e-05, + "loss": 1.3912, + "step": 3280 + }, + { + "epoch": 0.34, + "learning_rate": 1.6583993203535702e-05, + "loss": 1.3628, + "step": 3281 + }, + { + "epoch": 0.34, + "learning_rate": 1.658123780647983e-05, + "loss": 1.6089, + "step": 3282 + }, + { + "epoch": 0.34, + "learning_rate": 1.6578481527707196e-05, + "loss": 1.2367, + "step": 3283 + }, + { + "epoch": 0.34, + "learning_rate": 1.657572436758706e-05, + "loss": 1.4058, + "step": 3284 + }, + { + "epoch": 0.34, + "learning_rate": 1.6572966326488825e-05, + "loss": 1.4067, + "step": 3285 + }, + { + "epoch": 0.34, + "learning_rate": 1.657020740478198e-05, + "loss": 1.4187, + "step": 3286 + }, + { + "epoch": 0.34, + "learning_rate": 1.6567447602836166e-05, + "loss": 1.4599, + "step": 3287 + }, + { + "epoch": 0.34, + "learning_rate": 1.6564686921021115e-05, + "loss": 1.432, + "step": 3288 + }, + { + "epoch": 0.34, + "learning_rate": 1.6561925359706693e-05, + "loss": 1.3941, + "step": 3289 + }, + { + "epoch": 0.35, + "learning_rate": 1.6559162919262874e-05, + "loss": 1.3644, + "step": 3290 + }, + { + "epoch": 0.35, + "learning_rate": 1.6556399600059756e-05, + "loss": 1.4628, + "step": 3291 + }, + { + "epoch": 0.35, + "learning_rate": 1.6553635402467555e-05, + "loss": 1.4355, + "step": 3292 + }, + { + "epoch": 0.35, + "learning_rate": 1.6550870326856596e-05, + "loss": 1.4627, + "step": 3293 + }, + { + "epoch": 0.35, + "learning_rate": 1.6548104373597335e-05, + "loss": 1.442, + "step": 3294 + }, + { + "epoch": 0.35, + "learning_rate": 1.6545337543060338e-05, + "loss": 1.3991, + "step": 3295 + }, + { + "epoch": 0.35, + "learning_rate": 1.6542569835616283e-05, + "loss": 1.4193, + "step": 3296 + }, + { + "epoch": 0.35, + "learning_rate": 1.6539801251635982e-05, + "loss": 1.4792, + "step": 3297 + }, + { + "epoch": 0.35, + "learning_rate": 1.653703179149034e-05, + "loss": 1.4735, + "step": 3298 + }, + { + "epoch": 0.35, + "learning_rate": 1.6534261455550408e-05, + "loss": 1.451, + "step": 3299 + }, + { + "epoch": 0.35, + "learning_rate": 1.653149024418733e-05, + "loss": 1.3975, + "step": 3300 + }, + { + "epoch": 0.35, + "learning_rate": 1.652871815777238e-05, + "loss": 1.4843, + "step": 3301 + }, + { + "epoch": 0.35, + "learning_rate": 1.6525945196676948e-05, + "loss": 1.4782, + "step": 3302 + }, + { + "epoch": 0.35, + "learning_rate": 1.652317136127254e-05, + "loss": 1.3865, + "step": 3303 + }, + { + "epoch": 0.35, + "learning_rate": 1.6520396651930777e-05, + "loss": 1.4359, + "step": 3304 + }, + { + "epoch": 0.35, + "learning_rate": 1.6517621069023397e-05, + "loss": 1.4289, + "step": 3305 + }, + { + "epoch": 0.35, + "learning_rate": 1.651484461292226e-05, + "loss": 1.3526, + "step": 3306 + }, + { + "epoch": 0.35, + "learning_rate": 1.6512067283999336e-05, + "loss": 1.3671, + "step": 3307 + }, + { + "epoch": 0.35, + "learning_rate": 1.650928908262672e-05, + "loss": 1.6041, + "step": 3308 + }, + { + "epoch": 0.35, + "learning_rate": 1.650651000917662e-05, + "loss": 1.4322, + "step": 3309 + }, + { + "epoch": 0.35, + "learning_rate": 1.6503730064021354e-05, + "loss": 1.3992, + "step": 3310 + }, + { + "epoch": 0.35, + "learning_rate": 1.650094924753337e-05, + "loss": 1.4928, + "step": 3311 + }, + { + "epoch": 0.35, + "learning_rate": 1.6498167560085222e-05, + "loss": 1.4075, + "step": 3312 + }, + { + "epoch": 0.35, + "learning_rate": 1.6495385002049583e-05, + "loss": 1.4535, + "step": 3313 + }, + { + "epoch": 0.35, + "learning_rate": 1.6492601573799253e-05, + "loss": 1.4221, + "step": 3314 + }, + { + "epoch": 0.35, + "learning_rate": 1.6489817275707133e-05, + "loss": 1.3688, + "step": 3315 + }, + { + "epoch": 0.35, + "learning_rate": 1.6487032108146243e-05, + "loss": 1.3889, + "step": 3316 + }, + { + "epoch": 0.35, + "learning_rate": 1.6484246071489733e-05, + "loss": 1.3942, + "step": 3317 + }, + { + "epoch": 0.35, + "learning_rate": 1.6481459166110858e-05, + "loss": 1.4004, + "step": 3318 + }, + { + "epoch": 0.35, + "learning_rate": 1.647867139238299e-05, + "loss": 1.7308, + "step": 3319 + }, + { + "epoch": 0.35, + "learning_rate": 1.6475882750679622e-05, + "loss": 1.5001, + "step": 3320 + }, + { + "epoch": 0.35, + "learning_rate": 1.647309324137435e-05, + "loss": 1.4325, + "step": 3321 + }, + { + "epoch": 0.35, + "learning_rate": 1.6470302864840913e-05, + "loss": 1.4494, + "step": 3322 + }, + { + "epoch": 0.35, + "learning_rate": 1.6467511621453136e-05, + "loss": 1.4418, + "step": 3323 + }, + { + "epoch": 0.35, + "learning_rate": 1.646471951158498e-05, + "loss": 1.4046, + "step": 3324 + }, + { + "epoch": 0.35, + "learning_rate": 1.6461926535610517e-05, + "loss": 1.5031, + "step": 3325 + }, + { + "epoch": 0.35, + "learning_rate": 1.645913269390393e-05, + "loss": 1.4813, + "step": 3326 + }, + { + "epoch": 0.35, + "learning_rate": 1.6456337986839525e-05, + "loss": 1.3842, + "step": 3327 + }, + { + "epoch": 0.35, + "learning_rate": 1.645354241479172e-05, + "loss": 1.4539, + "step": 3328 + }, + { + "epoch": 0.35, + "learning_rate": 1.6450745978135048e-05, + "loss": 1.4503, + "step": 3329 + }, + { + "epoch": 0.35, + "learning_rate": 1.6447948677244163e-05, + "loss": 1.3741, + "step": 3330 + }, + { + "epoch": 0.35, + "learning_rate": 1.6445150512493832e-05, + "loss": 1.425, + "step": 3331 + }, + { + "epoch": 0.35, + "learning_rate": 1.644235148425893e-05, + "loss": 1.4277, + "step": 3332 + }, + { + "epoch": 0.35, + "learning_rate": 1.6439551592914464e-05, + "loss": 1.4918, + "step": 3333 + }, + { + "epoch": 0.35, + "learning_rate": 1.6436750838835543e-05, + "loss": 1.3364, + "step": 3334 + }, + { + "epoch": 0.35, + "learning_rate": 1.6433949222397397e-05, + "loss": 1.4741, + "step": 3335 + }, + { + "epoch": 0.35, + "learning_rate": 1.643114674397537e-05, + "loss": 1.3867, + "step": 3336 + }, + { + "epoch": 0.35, + "learning_rate": 1.642834340394492e-05, + "loss": 1.3817, + "step": 3337 + }, + { + "epoch": 0.35, + "learning_rate": 1.6425539202681625e-05, + "loss": 1.4308, + "step": 3338 + }, + { + "epoch": 0.35, + "learning_rate": 1.6422734140561178e-05, + "loss": 1.4401, + "step": 3339 + }, + { + "epoch": 0.35, + "learning_rate": 1.641992821795938e-05, + "loss": 1.4338, + "step": 3340 + }, + { + "epoch": 0.35, + "learning_rate": 1.641712143525216e-05, + "loss": 1.3804, + "step": 3341 + }, + { + "epoch": 0.35, + "learning_rate": 1.6414313792815546e-05, + "loss": 1.371, + "step": 3342 + }, + { + "epoch": 0.35, + "learning_rate": 1.6411505291025695e-05, + "loss": 1.4102, + "step": 3343 + }, + { + "epoch": 0.35, + "learning_rate": 1.6408695930258875e-05, + "loss": 1.4433, + "step": 3344 + }, + { + "epoch": 0.35, + "learning_rate": 1.6405885710891467e-05, + "loss": 1.3895, + "step": 3345 + }, + { + "epoch": 0.35, + "learning_rate": 1.6403074633299966e-05, + "loss": 1.4321, + "step": 3346 + }, + { + "epoch": 0.35, + "learning_rate": 1.640026269786098e-05, + "loss": 1.4207, + "step": 3347 + }, + { + "epoch": 0.35, + "learning_rate": 1.639744990495125e-05, + "loss": 1.3758, + "step": 3348 + }, + { + "epoch": 0.35, + "learning_rate": 1.6394636254947612e-05, + "loss": 1.4203, + "step": 3349 + }, + { + "epoch": 0.35, + "learning_rate": 1.6391821748227013e-05, + "loss": 1.4596, + "step": 3350 + }, + { + "epoch": 0.35, + "learning_rate": 1.6389006385166537e-05, + "loss": 1.4344, + "step": 3351 + }, + { + "epoch": 0.35, + "learning_rate": 1.6386190166143366e-05, + "loss": 1.4048, + "step": 3352 + }, + { + "epoch": 0.35, + "learning_rate": 1.6383373091534798e-05, + "loss": 1.4348, + "step": 3353 + }, + { + "epoch": 0.35, + "learning_rate": 1.638055516171825e-05, + "loss": 1.4972, + "step": 3354 + }, + { + "epoch": 0.35, + "learning_rate": 1.6377736377071258e-05, + "loss": 1.4685, + "step": 3355 + }, + { + "epoch": 0.35, + "learning_rate": 1.637491673797146e-05, + "loss": 1.4093, + "step": 3356 + }, + { + "epoch": 0.35, + "learning_rate": 1.6372096244796616e-05, + "loss": 1.4452, + "step": 3357 + }, + { + "epoch": 0.35, + "learning_rate": 1.63692748979246e-05, + "loss": 1.4458, + "step": 3358 + }, + { + "epoch": 0.35, + "learning_rate": 1.6366452697733404e-05, + "loss": 1.4187, + "step": 3359 + }, + { + "epoch": 0.35, + "learning_rate": 1.6363629644601126e-05, + "loss": 1.4052, + "step": 3360 + }, + { + "epoch": 0.35, + "learning_rate": 1.6360805738905984e-05, + "loss": 1.439, + "step": 3361 + }, + { + "epoch": 0.35, + "learning_rate": 1.635798098102631e-05, + "loss": 1.4131, + "step": 3362 + }, + { + "epoch": 0.35, + "learning_rate": 1.6355155371340544e-05, + "loss": 1.4391, + "step": 3363 + }, + { + "epoch": 0.35, + "learning_rate": 1.6352328910227252e-05, + "loss": 1.4318, + "step": 3364 + }, + { + "epoch": 0.35, + "learning_rate": 1.63495015980651e-05, + "loss": 1.5112, + "step": 3365 + }, + { + "epoch": 0.35, + "learning_rate": 1.6346673435232884e-05, + "loss": 1.4688, + "step": 3366 + }, + { + "epoch": 0.35, + "learning_rate": 1.6343844422109496e-05, + "loss": 1.3807, + "step": 3367 + }, + { + "epoch": 0.35, + "learning_rate": 1.634101455907396e-05, + "loss": 1.4083, + "step": 3368 + }, + { + "epoch": 0.35, + "learning_rate": 1.6338183846505394e-05, + "loss": 1.3566, + "step": 3369 + }, + { + "epoch": 0.35, + "learning_rate": 1.633535228478305e-05, + "loss": 1.4287, + "step": 3370 + }, + { + "epoch": 0.35, + "learning_rate": 1.6332519874286285e-05, + "loss": 1.3494, + "step": 3371 + }, + { + "epoch": 0.35, + "learning_rate": 1.6329686615394558e-05, + "loss": 1.3813, + "step": 3372 + }, + { + "epoch": 0.35, + "learning_rate": 1.6326852508487468e-05, + "loss": 1.4241, + "step": 3373 + }, + { + "epoch": 0.35, + "learning_rate": 1.63240175539447e-05, + "loss": 1.424, + "step": 3374 + }, + { + "epoch": 0.35, + "learning_rate": 1.632118175214607e-05, + "loss": 1.4212, + "step": 3375 + }, + { + "epoch": 0.35, + "learning_rate": 1.6318345103471504e-05, + "loss": 1.4671, + "step": 3376 + }, + { + "epoch": 0.35, + "learning_rate": 1.6315507608301044e-05, + "loss": 1.4593, + "step": 3377 + }, + { + "epoch": 0.35, + "learning_rate": 1.631266926701483e-05, + "loss": 1.7816, + "step": 3378 + }, + { + "epoch": 0.35, + "learning_rate": 1.6309830079993134e-05, + "loss": 1.5134, + "step": 3379 + }, + { + "epoch": 0.35, + "learning_rate": 1.6306990047616334e-05, + "loss": 0.8933, + "step": 3380 + }, + { + "epoch": 0.35, + "learning_rate": 1.630414917026492e-05, + "loss": 1.1033, + "step": 3381 + }, + { + "epoch": 0.35, + "learning_rate": 1.6301307448319497e-05, + "loss": 1.3494, + "step": 3382 + }, + { + "epoch": 0.35, + "learning_rate": 1.6298464882160784e-05, + "loss": 1.4299, + "step": 3383 + }, + { + "epoch": 0.35, + "eval_loss": 1.482450008392334, + "eval_runtime": 77.3737, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3383 + }, + { + "epoch": 0.35, + "learning_rate": 1.629562147216961e-05, + "loss": 1.3971, + "step": 3384 + }, + { + "epoch": 0.35, + "learning_rate": 1.6292777218726917e-05, + "loss": 1.3706, + "step": 3385 + }, + { + "epoch": 0.36, + "learning_rate": 1.6289932122213765e-05, + "loss": 1.4524, + "step": 3386 + }, + { + "epoch": 0.36, + "learning_rate": 1.6287086183011328e-05, + "loss": 1.4595, + "step": 3387 + }, + { + "epoch": 0.36, + "learning_rate": 1.628423940150088e-05, + "loss": 1.492, + "step": 3388 + }, + { + "epoch": 0.36, + "learning_rate": 1.628139177806382e-05, + "loss": 1.5576, + "step": 3389 + }, + { + "epoch": 0.36, + "learning_rate": 1.6278543313081657e-05, + "loss": 1.4615, + "step": 3390 + }, + { + "epoch": 0.36, + "learning_rate": 1.6275694006936015e-05, + "loss": 1.3456, + "step": 3391 + }, + { + "epoch": 0.36, + "learning_rate": 1.627284386000862e-05, + "loss": 1.4254, + "step": 3392 + }, + { + "epoch": 0.36, + "learning_rate": 1.6269992872681325e-05, + "loss": 1.433, + "step": 3393 + }, + { + "epoch": 0.36, + "learning_rate": 1.626714104533609e-05, + "loss": 1.5291, + "step": 3394 + }, + { + "epoch": 0.36, + "learning_rate": 1.626428837835498e-05, + "loss": 1.4502, + "step": 3395 + }, + { + "epoch": 0.36, + "learning_rate": 1.626143487212019e-05, + "loss": 1.3756, + "step": 3396 + }, + { + "epoch": 0.36, + "learning_rate": 1.6258580527014002e-05, + "loss": 1.414, + "step": 3397 + }, + { + "epoch": 0.36, + "learning_rate": 1.6255725343418835e-05, + "loss": 1.6289, + "step": 3398 + }, + { + "epoch": 0.36, + "learning_rate": 1.6252869321717208e-05, + "loss": 1.4862, + "step": 3399 + }, + { + "epoch": 0.36, + "learning_rate": 1.6250012462291756e-05, + "loss": 1.4213, + "step": 3400 + }, + { + "epoch": 0.36, + "learning_rate": 1.6247154765525217e-05, + "loss": 1.524, + "step": 3401 + }, + { + "epoch": 0.36, + "learning_rate": 1.624429623180046e-05, + "loss": 1.6013, + "step": 3402 + }, + { + "epoch": 0.36, + "learning_rate": 1.624143686150045e-05, + "loss": 1.4557, + "step": 3403 + }, + { + "epoch": 0.36, + "learning_rate": 1.6238576655008266e-05, + "loss": 1.3831, + "step": 3404 + }, + { + "epoch": 0.36, + "learning_rate": 1.6235715612707105e-05, + "loss": 1.4008, + "step": 3405 + }, + { + "epoch": 0.36, + "learning_rate": 1.623285373498028e-05, + "loss": 1.4848, + "step": 3406 + }, + { + "epoch": 0.36, + "learning_rate": 1.6229991022211197e-05, + "loss": 1.4459, + "step": 3407 + }, + { + "epoch": 0.36, + "learning_rate": 1.6227127474783393e-05, + "loss": 1.4334, + "step": 3408 + }, + { + "epoch": 0.36, + "learning_rate": 1.6224263093080507e-05, + "loss": 1.4123, + "step": 3409 + }, + { + "epoch": 0.36, + "learning_rate": 1.6221397877486294e-05, + "loss": 1.3691, + "step": 3410 + }, + { + "epoch": 0.36, + "learning_rate": 1.6218531828384618e-05, + "loss": 1.4128, + "step": 3411 + }, + { + "epoch": 0.36, + "learning_rate": 1.6215664946159457e-05, + "loss": 1.3642, + "step": 3412 + }, + { + "epoch": 0.36, + "learning_rate": 1.6212797231194902e-05, + "loss": 1.4311, + "step": 3413 + }, + { + "epoch": 0.36, + "learning_rate": 1.6209928683875152e-05, + "loss": 1.4695, + "step": 3414 + }, + { + "epoch": 0.36, + "learning_rate": 1.6207059304584514e-05, + "loss": 1.3871, + "step": 3415 + }, + { + "epoch": 0.36, + "learning_rate": 1.6204189093707414e-05, + "loss": 1.4219, + "step": 3416 + }, + { + "epoch": 0.36, + "learning_rate": 1.620131805162839e-05, + "loss": 1.6199, + "step": 3417 + }, + { + "epoch": 0.36, + "learning_rate": 1.619844617873208e-05, + "loss": 1.4433, + "step": 3418 + }, + { + "epoch": 0.36, + "learning_rate": 1.619557347540325e-05, + "loss": 1.4773, + "step": 3419 + }, + { + "epoch": 0.36, + "learning_rate": 1.6192699942026763e-05, + "loss": 1.4551, + "step": 3420 + }, + { + "epoch": 0.36, + "learning_rate": 1.6189825578987603e-05, + "loss": 1.4903, + "step": 3421 + }, + { + "epoch": 0.36, + "learning_rate": 1.6186950386670855e-05, + "loss": 1.473, + "step": 3422 + }, + { + "epoch": 0.36, + "learning_rate": 1.6184074365461722e-05, + "loss": 1.4082, + "step": 3423 + }, + { + "epoch": 0.36, + "learning_rate": 1.6181197515745523e-05, + "loss": 1.4746, + "step": 3424 + }, + { + "epoch": 0.36, + "learning_rate": 1.6178319837907674e-05, + "loss": 1.449, + "step": 3425 + }, + { + "epoch": 0.36, + "learning_rate": 1.6175441332333715e-05, + "loss": 1.377, + "step": 3426 + }, + { + "epoch": 0.36, + "learning_rate": 1.617256199940929e-05, + "loss": 1.2364, + "step": 3427 + }, + { + "epoch": 0.36, + "learning_rate": 1.6169681839520155e-05, + "loss": 1.4437, + "step": 3428 + }, + { + "epoch": 0.36, + "learning_rate": 1.616680085305218e-05, + "loss": 1.4726, + "step": 3429 + }, + { + "epoch": 0.36, + "learning_rate": 1.616391904039134e-05, + "loss": 1.4824, + "step": 3430 + }, + { + "epoch": 0.36, + "learning_rate": 1.616103640192373e-05, + "loss": 1.4052, + "step": 3431 + }, + { + "epoch": 0.36, + "learning_rate": 1.6158152938035537e-05, + "loss": 1.4131, + "step": 3432 + }, + { + "epoch": 0.36, + "learning_rate": 1.6155268649113084e-05, + "loss": 1.4267, + "step": 3433 + }, + { + "epoch": 0.36, + "learning_rate": 1.6152383535542786e-05, + "loss": 1.3735, + "step": 3434 + }, + { + "epoch": 0.36, + "learning_rate": 1.6149497597711175e-05, + "loss": 1.4249, + "step": 3435 + }, + { + "epoch": 0.36, + "learning_rate": 1.614661083600489e-05, + "loss": 1.4312, + "step": 3436 + }, + { + "epoch": 0.36, + "learning_rate": 1.6143723250810686e-05, + "loss": 1.4831, + "step": 3437 + }, + { + "epoch": 0.36, + "learning_rate": 1.6140834842515425e-05, + "loss": 1.4183, + "step": 3438 + }, + { + "epoch": 0.36, + "learning_rate": 1.6137945611506078e-05, + "loss": 1.3908, + "step": 3439 + }, + { + "epoch": 0.36, + "learning_rate": 1.613505555816973e-05, + "loss": 1.425, + "step": 3440 + }, + { + "epoch": 0.36, + "learning_rate": 1.613216468289357e-05, + "loss": 1.3589, + "step": 3441 + }, + { + "epoch": 0.36, + "learning_rate": 1.6129272986064903e-05, + "loss": 1.4272, + "step": 3442 + }, + { + "epoch": 0.36, + "learning_rate": 1.6126380468071142e-05, + "loss": 1.4337, + "step": 3443 + }, + { + "epoch": 0.36, + "learning_rate": 1.6123487129299817e-05, + "loss": 1.3872, + "step": 3444 + }, + { + "epoch": 0.36, + "learning_rate": 1.612059297013855e-05, + "loss": 1.374, + "step": 3445 + }, + { + "epoch": 0.36, + "learning_rate": 1.611769799097509e-05, + "loss": 1.314, + "step": 3446 + }, + { + "epoch": 0.36, + "learning_rate": 1.6114802192197284e-05, + "loss": 1.3951, + "step": 3447 + }, + { + "epoch": 0.36, + "learning_rate": 1.6111905574193102e-05, + "loss": 1.4732, + "step": 3448 + }, + { + "epoch": 0.36, + "learning_rate": 1.6109008137350614e-05, + "loss": 1.3575, + "step": 3449 + }, + { + "epoch": 0.36, + "learning_rate": 1.6106109882058e-05, + "loss": 1.4606, + "step": 3450 + }, + { + "epoch": 0.36, + "learning_rate": 1.6103210808703554e-05, + "loss": 1.4357, + "step": 3451 + }, + { + "epoch": 0.36, + "learning_rate": 1.6100310917675678e-05, + "loss": 0.8456, + "step": 3452 + }, + { + "epoch": 0.36, + "learning_rate": 1.609741020936288e-05, + "loss": 1.07, + "step": 3453 + }, + { + "epoch": 0.36, + "learning_rate": 1.6094508684153782e-05, + "loss": 1.4435, + "step": 3454 + }, + { + "epoch": 0.36, + "learning_rate": 1.609160634243711e-05, + "loss": 1.3696, + "step": 3455 + }, + { + "epoch": 0.36, + "learning_rate": 1.6088703184601712e-05, + "loss": 1.4012, + "step": 3456 + }, + { + "epoch": 0.36, + "learning_rate": 1.608579921103653e-05, + "loss": 1.5212, + "step": 3457 + }, + { + "epoch": 0.36, + "learning_rate": 1.608289442213062e-05, + "loss": 1.4339, + "step": 3458 + }, + { + "epoch": 0.36, + "learning_rate": 1.607998881827316e-05, + "loss": 1.4901, + "step": 3459 + }, + { + "epoch": 0.36, + "learning_rate": 1.6077082399853412e-05, + "loss": 1.4822, + "step": 3460 + }, + { + "epoch": 0.36, + "learning_rate": 1.607417516726077e-05, + "loss": 1.3696, + "step": 3461 + }, + { + "epoch": 0.36, + "learning_rate": 1.6071267120884727e-05, + "loss": 1.4434, + "step": 3462 + }, + { + "epoch": 0.36, + "learning_rate": 1.6068358261114886e-05, + "loss": 1.3916, + "step": 3463 + }, + { + "epoch": 0.36, + "learning_rate": 1.606544858834096e-05, + "loss": 1.422, + "step": 3464 + }, + { + "epoch": 0.36, + "learning_rate": 1.6062538102952763e-05, + "loss": 1.367, + "step": 3465 + }, + { + "epoch": 0.36, + "learning_rate": 1.605962680534024e-05, + "loss": 1.3788, + "step": 3466 + }, + { + "epoch": 0.36, + "learning_rate": 1.605671469589342e-05, + "loss": 1.4366, + "step": 3467 + }, + { + "epoch": 0.36, + "learning_rate": 1.6053801775002453e-05, + "loss": 1.4027, + "step": 3468 + }, + { + "epoch": 0.36, + "learning_rate": 1.6050888043057595e-05, + "loss": 1.4386, + "step": 3469 + }, + { + "epoch": 0.36, + "learning_rate": 1.6047973500449212e-05, + "loss": 1.4675, + "step": 3470 + }, + { + "epoch": 0.36, + "learning_rate": 1.6045058147567778e-05, + "loss": 1.6936, + "step": 3471 + }, + { + "epoch": 0.36, + "learning_rate": 1.6042141984803875e-05, + "loss": 1.4858, + "step": 3472 + }, + { + "epoch": 0.36, + "learning_rate": 1.6039225012548196e-05, + "loss": 1.5004, + "step": 3473 + }, + { + "epoch": 0.36, + "learning_rate": 1.6036307231191534e-05, + "loss": 1.4969, + "step": 3474 + }, + { + "epoch": 0.36, + "learning_rate": 1.6033388641124803e-05, + "loss": 1.4027, + "step": 3475 + }, + { + "epoch": 0.36, + "learning_rate": 1.6030469242739016e-05, + "loss": 1.4741, + "step": 3476 + }, + { + "epoch": 0.36, + "learning_rate": 1.60275490364253e-05, + "loss": 1.3887, + "step": 3477 + }, + { + "epoch": 0.36, + "learning_rate": 1.602462802257488e-05, + "loss": 1.6735, + "step": 3478 + }, + { + "epoch": 0.36, + "learning_rate": 1.602170620157911e-05, + "loss": 1.4997, + "step": 3479 + }, + { + "epoch": 0.36, + "learning_rate": 1.601878357382943e-05, + "loss": 1.3973, + "step": 3480 + }, + { + "epoch": 0.37, + "learning_rate": 1.6015860139717398e-05, + "loss": 1.416, + "step": 3481 + }, + { + "epoch": 0.37, + "learning_rate": 1.6012935899634682e-05, + "loss": 1.4102, + "step": 3482 + }, + { + "epoch": 0.37, + "learning_rate": 1.601001085397305e-05, + "loss": 1.4248, + "step": 3483 + }, + { + "epoch": 0.37, + "learning_rate": 1.6007085003124386e-05, + "loss": 1.3909, + "step": 3484 + }, + { + "epoch": 0.37, + "learning_rate": 1.600415834748068e-05, + "loss": 1.4029, + "step": 3485 + }, + { + "epoch": 0.37, + "learning_rate": 1.6001230887434024e-05, + "loss": 1.4219, + "step": 3486 + }, + { + "epoch": 0.37, + "learning_rate": 1.5998302623376633e-05, + "loss": 1.4008, + "step": 3487 + }, + { + "epoch": 0.37, + "learning_rate": 1.5995373555700806e-05, + "loss": 1.5163, + "step": 3488 + }, + { + "epoch": 0.37, + "learning_rate": 1.599244368479897e-05, + "loss": 1.4541, + "step": 3489 + }, + { + "epoch": 0.37, + "learning_rate": 1.598951301106365e-05, + "loss": 1.4454, + "step": 3490 + }, + { + "epoch": 0.37, + "learning_rate": 1.598658153488748e-05, + "loss": 1.1014, + "step": 3491 + }, + { + "epoch": 0.37, + "learning_rate": 1.598364925666321e-05, + "loss": 1.407, + "step": 3492 + }, + { + "epoch": 0.37, + "learning_rate": 1.5980716176783682e-05, + "loss": 1.5046, + "step": 3493 + }, + { + "epoch": 0.37, + "learning_rate": 1.5977782295641857e-05, + "loss": 1.4265, + "step": 3494 + }, + { + "epoch": 0.37, + "learning_rate": 1.5974847613630796e-05, + "loss": 1.46, + "step": 3495 + }, + { + "epoch": 0.37, + "learning_rate": 1.5971912131143677e-05, + "loss": 1.3996, + "step": 3496 + }, + { + "epoch": 0.37, + "learning_rate": 1.5968975848573772e-05, + "loss": 1.4719, + "step": 3497 + }, + { + "epoch": 0.37, + "learning_rate": 1.596603876631447e-05, + "loss": 1.43, + "step": 3498 + }, + { + "epoch": 0.37, + "learning_rate": 1.596310088475927e-05, + "loss": 1.4109, + "step": 3499 + }, + { + "epoch": 0.37, + "learning_rate": 1.5960162204301768e-05, + "loss": 1.3612, + "step": 3500 + }, + { + "epoch": 0.37, + "learning_rate": 1.5957222725335672e-05, + "loss": 1.5045, + "step": 3501 + }, + { + "epoch": 0.37, + "learning_rate": 1.5954282448254794e-05, + "loss": 1.5323, + "step": 3502 + }, + { + "epoch": 0.37, + "learning_rate": 1.595134137345306e-05, + "loss": 1.4518, + "step": 3503 + }, + { + "epoch": 0.37, + "learning_rate": 1.5948399501324495e-05, + "loss": 1.6131, + "step": 3504 + }, + { + "epoch": 0.37, + "learning_rate": 1.594545683226324e-05, + "loss": 1.5076, + "step": 3505 + }, + { + "epoch": 0.37, + "learning_rate": 1.594251336666353e-05, + "loss": 1.482, + "step": 3506 + }, + { + "epoch": 0.37, + "learning_rate": 1.5939569104919716e-05, + "loss": 1.4429, + "step": 3507 + }, + { + "epoch": 0.37, + "learning_rate": 1.5936624047426254e-05, + "loss": 1.4662, + "step": 3508 + }, + { + "epoch": 0.37, + "learning_rate": 1.5933678194577708e-05, + "loss": 1.425, + "step": 3509 + }, + { + "epoch": 0.37, + "learning_rate": 1.5930731546768744e-05, + "loss": 1.4312, + "step": 3510 + }, + { + "epoch": 0.37, + "learning_rate": 1.592778410439414e-05, + "loss": 1.4336, + "step": 3511 + }, + { + "epoch": 0.37, + "learning_rate": 1.5924835867848775e-05, + "loss": 1.4197, + "step": 3512 + }, + { + "epoch": 0.37, + "learning_rate": 1.5921886837527638e-05, + "loss": 1.4456, + "step": 3513 + }, + { + "epoch": 0.37, + "learning_rate": 1.5918937013825823e-05, + "loss": 1.4394, + "step": 3514 + }, + { + "epoch": 0.37, + "learning_rate": 1.5915986397138526e-05, + "loss": 1.3606, + "step": 3515 + }, + { + "epoch": 0.37, + "learning_rate": 1.591303498786106e-05, + "loss": 1.4382, + "step": 3516 + }, + { + "epoch": 0.37, + "learning_rate": 1.591008278638884e-05, + "loss": 1.4185, + "step": 3517 + }, + { + "epoch": 0.37, + "learning_rate": 1.5907129793117374e-05, + "loss": 1.6692, + "step": 3518 + }, + { + "epoch": 0.37, + "learning_rate": 1.59041760084423e-05, + "loss": 1.501, + "step": 3519 + }, + { + "epoch": 0.37, + "learning_rate": 1.5901221432759345e-05, + "loss": 1.5753, + "step": 3520 + }, + { + "epoch": 0.37, + "learning_rate": 1.589826606646434e-05, + "loss": 1.4795, + "step": 3521 + }, + { + "epoch": 0.37, + "learning_rate": 1.5895309909953236e-05, + "loss": 1.4379, + "step": 3522 + }, + { + "epoch": 0.37, + "learning_rate": 1.5892352963622078e-05, + "loss": 1.3426, + "step": 3523 + }, + { + "epoch": 0.37, + "learning_rate": 1.5889395227867025e-05, + "loss": 1.4048, + "step": 3524 + }, + { + "epoch": 0.37, + "learning_rate": 1.5886436703084332e-05, + "loss": 1.4303, + "step": 3525 + }, + { + "epoch": 0.37, + "learning_rate": 1.5883477389670367e-05, + "loss": 1.3684, + "step": 3526 + }, + { + "epoch": 0.37, + "learning_rate": 1.5880517288021602e-05, + "loss": 1.3701, + "step": 3527 + }, + { + "epoch": 0.37, + "learning_rate": 1.587755639853462e-05, + "loss": 1.4308, + "step": 3528 + }, + { + "epoch": 0.37, + "learning_rate": 1.5874594721606096e-05, + "loss": 1.3981, + "step": 3529 + }, + { + "epoch": 0.37, + "learning_rate": 1.5871632257632823e-05, + "loss": 1.5906, + "step": 3530 + }, + { + "epoch": 0.37, + "learning_rate": 1.5868669007011696e-05, + "loss": 1.4642, + "step": 3531 + }, + { + "epoch": 0.37, + "learning_rate": 1.586570497013971e-05, + "loss": 1.411, + "step": 3532 + }, + { + "epoch": 0.37, + "learning_rate": 1.586274014741397e-05, + "loss": 1.3942, + "step": 3533 + }, + { + "epoch": 0.37, + "learning_rate": 1.5859774539231693e-05, + "loss": 1.3952, + "step": 3534 + }, + { + "epoch": 0.37, + "learning_rate": 1.585680814599019e-05, + "loss": 1.4009, + "step": 3535 + }, + { + "epoch": 0.37, + "learning_rate": 1.585384096808688e-05, + "loss": 1.3238, + "step": 3536 + }, + { + "epoch": 0.37, + "learning_rate": 1.585087300591929e-05, + "loss": 1.346, + "step": 3537 + }, + { + "epoch": 0.37, + "learning_rate": 1.584790425988505e-05, + "loss": 1.3739, + "step": 3538 + }, + { + "epoch": 0.37, + "learning_rate": 1.5844934730381895e-05, + "loss": 1.4264, + "step": 3539 + }, + { + "epoch": 0.37, + "learning_rate": 1.5841964417807668e-05, + "loss": 1.4675, + "step": 3540 + }, + { + "epoch": 0.37, + "learning_rate": 1.5838993322560314e-05, + "loss": 1.3337, + "step": 3541 + }, + { + "epoch": 0.37, + "learning_rate": 1.5836021445037883e-05, + "loss": 1.4052, + "step": 3542 + }, + { + "epoch": 0.37, + "learning_rate": 1.583304878563853e-05, + "loss": 1.4311, + "step": 3543 + }, + { + "epoch": 0.37, + "learning_rate": 1.5830075344760513e-05, + "loss": 1.386, + "step": 3544 + }, + { + "epoch": 0.37, + "learning_rate": 1.58271011228022e-05, + "loss": 1.387, + "step": 3545 + }, + { + "epoch": 0.37, + "learning_rate": 1.582412612016206e-05, + "loss": 1.3601, + "step": 3546 + }, + { + "epoch": 0.37, + "learning_rate": 1.5821150337238663e-05, + "loss": 1.5111, + "step": 3547 + }, + { + "epoch": 0.37, + "learning_rate": 1.5818173774430697e-05, + "loss": 1.471, + "step": 3548 + }, + { + "epoch": 0.37, + "learning_rate": 1.581519643213693e-05, + "loss": 1.4442, + "step": 3549 + }, + { + "epoch": 0.37, + "learning_rate": 1.5812218310756263e-05, + "loss": 1.467, + "step": 3550 + }, + { + "epoch": 0.37, + "learning_rate": 1.5809239410687683e-05, + "loss": 1.3731, + "step": 3551 + }, + { + "epoch": 0.37, + "learning_rate": 1.5806259732330286e-05, + "loss": 1.4072, + "step": 3552 + }, + { + "epoch": 0.37, + "learning_rate": 1.5803279276083268e-05, + "loss": 1.3636, + "step": 3553 + }, + { + "epoch": 0.37, + "learning_rate": 1.5800298042345938e-05, + "loss": 1.3915, + "step": 3554 + }, + { + "epoch": 0.37, + "learning_rate": 1.5797316031517705e-05, + "loss": 1.5038, + "step": 3555 + }, + { + "epoch": 0.37, + "learning_rate": 1.5794333243998082e-05, + "loss": 1.4455, + "step": 3556 + }, + { + "epoch": 0.37, + "learning_rate": 1.5791349680186684e-05, + "loss": 1.5062, + "step": 3557 + }, + { + "epoch": 0.37, + "learning_rate": 1.5788365340483234e-05, + "loss": 1.3899, + "step": 3558 + }, + { + "epoch": 0.37, + "learning_rate": 1.5785380225287554e-05, + "loss": 1.4946, + "step": 3559 + }, + { + "epoch": 0.37, + "learning_rate": 1.5782394334999572e-05, + "loss": 1.3859, + "step": 3560 + }, + { + "epoch": 0.37, + "learning_rate": 1.577940767001933e-05, + "loss": 1.541, + "step": 3561 + }, + { + "epoch": 0.37, + "learning_rate": 1.5776420230746952e-05, + "loss": 1.4952, + "step": 3562 + }, + { + "epoch": 0.37, + "learning_rate": 1.5773432017582684e-05, + "loss": 1.6055, + "step": 3563 + }, + { + "epoch": 0.37, + "learning_rate": 1.577044303092687e-05, + "loss": 1.4661, + "step": 3564 + }, + { + "epoch": 0.37, + "learning_rate": 1.576745327117996e-05, + "loss": 1.4082, + "step": 3565 + }, + { + "epoch": 0.37, + "learning_rate": 1.5764462738742493e-05, + "loss": 1.4005, + "step": 3566 + }, + { + "epoch": 0.37, + "learning_rate": 1.5761471434015137e-05, + "loss": 1.3959, + "step": 3567 + }, + { + "epoch": 0.37, + "learning_rate": 1.5758479357398645e-05, + "loss": 1.4567, + "step": 3568 + }, + { + "epoch": 0.37, + "learning_rate": 1.575548650929388e-05, + "loss": 1.3791, + "step": 3569 + }, + { + "epoch": 0.37, + "learning_rate": 1.57524928901018e-05, + "loss": 1.4428, + "step": 3570 + }, + { + "epoch": 0.37, + "learning_rate": 1.5749498500223486e-05, + "loss": 1.3864, + "step": 3571 + }, + { + "epoch": 0.37, + "learning_rate": 1.5746503340060097e-05, + "loss": 1.4019, + "step": 3572 + }, + { + "epoch": 0.37, + "learning_rate": 1.574350741001291e-05, + "loss": 1.5436, + "step": 3573 + }, + { + "epoch": 0.37, + "learning_rate": 1.5740510710483308e-05, + "loss": 1.4637, + "step": 3574 + }, + { + "epoch": 0.37, + "learning_rate": 1.5737513241872767e-05, + "loss": 1.5097, + "step": 3575 + }, + { + "epoch": 0.38, + "learning_rate": 1.5734515004582873e-05, + "loss": 1.5143, + "step": 3576 + }, + { + "epoch": 0.38, + "learning_rate": 1.5731515999015315e-05, + "loss": 1.3926, + "step": 3577 + }, + { + "epoch": 0.38, + "learning_rate": 1.5728516225571874e-05, + "loss": 1.4242, + "step": 3578 + }, + { + "epoch": 0.38, + "learning_rate": 1.5725515684654453e-05, + "loss": 1.4429, + "step": 3579 + }, + { + "epoch": 0.38, + "learning_rate": 1.572251437666504e-05, + "loss": 1.4638, + "step": 3580 + }, + { + "epoch": 0.38, + "learning_rate": 1.5719512302005735e-05, + "loss": 1.3381, + "step": 3581 + }, + { + "epoch": 0.38, + "learning_rate": 1.571650946107874e-05, + "loss": 1.4342, + "step": 3582 + }, + { + "epoch": 0.38, + "eval_loss": 1.4705015420913696, + "eval_runtime": 77.3664, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3582 + }, + { + "epoch": 0.38, + "learning_rate": 1.571350585428636e-05, + "loss": 1.3991, + "step": 3583 + }, + { + "epoch": 0.38, + "learning_rate": 1.5710501482030998e-05, + "loss": 1.4274, + "step": 3584 + }, + { + "epoch": 0.38, + "learning_rate": 1.5707496344715166e-05, + "loss": 1.438, + "step": 3585 + }, + { + "epoch": 0.38, + "learning_rate": 1.570449044274147e-05, + "loss": 1.4453, + "step": 3586 + }, + { + "epoch": 0.38, + "learning_rate": 1.570148377651263e-05, + "loss": 1.4022, + "step": 3587 + }, + { + "epoch": 0.38, + "learning_rate": 1.5698476346431454e-05, + "loss": 1.4312, + "step": 3588 + }, + { + "epoch": 0.38, + "learning_rate": 1.569546815290087e-05, + "loss": 1.4329, + "step": 3589 + }, + { + "epoch": 0.38, + "learning_rate": 1.569245919632389e-05, + "loss": 1.4036, + "step": 3590 + }, + { + "epoch": 0.38, + "learning_rate": 1.5689449477103644e-05, + "loss": 1.412, + "step": 3591 + }, + { + "epoch": 0.38, + "learning_rate": 1.5686438995643353e-05, + "loss": 1.4492, + "step": 3592 + }, + { + "epoch": 0.38, + "learning_rate": 1.5683427752346343e-05, + "loss": 1.4555, + "step": 3593 + }, + { + "epoch": 0.38, + "learning_rate": 1.5680415747616047e-05, + "loss": 1.5594, + "step": 3594 + }, + { + "epoch": 0.38, + "learning_rate": 1.5677402981855993e-05, + "loss": 1.4813, + "step": 3595 + }, + { + "epoch": 0.38, + "learning_rate": 1.567438945546982e-05, + "loss": 1.5919, + "step": 3596 + }, + { + "epoch": 0.38, + "learning_rate": 1.5671375168861255e-05, + "loss": 1.4235, + "step": 3597 + }, + { + "epoch": 0.38, + "learning_rate": 1.5668360122434135e-05, + "loss": 1.441, + "step": 3598 + }, + { + "epoch": 0.38, + "learning_rate": 1.566534431659241e-05, + "loss": 1.5847, + "step": 3599 + }, + { + "epoch": 0.38, + "learning_rate": 1.566232775174011e-05, + "loss": 1.6123, + "step": 3600 + }, + { + "epoch": 0.38, + "learning_rate": 1.5659310428281374e-05, + "loss": 1.4916, + "step": 3601 + }, + { + "epoch": 0.38, + "learning_rate": 1.5656292346620457e-05, + "loss": 1.4603, + "step": 3602 + }, + { + "epoch": 0.38, + "learning_rate": 1.56532735071617e-05, + "loss": 1.4423, + "step": 3603 + }, + { + "epoch": 0.38, + "learning_rate": 1.5650253910309547e-05, + "loss": 1.4814, + "step": 3604 + }, + { + "epoch": 0.38, + "learning_rate": 1.5647233556468552e-05, + "loss": 1.4015, + "step": 3605 + }, + { + "epoch": 0.38, + "learning_rate": 1.564421244604336e-05, + "loss": 1.3798, + "step": 3606 + }, + { + "epoch": 0.38, + "learning_rate": 1.5641190579438723e-05, + "loss": 1.4259, + "step": 3607 + }, + { + "epoch": 0.38, + "learning_rate": 1.5638167957059493e-05, + "loss": 1.3493, + "step": 3608 + }, + { + "epoch": 0.38, + "learning_rate": 1.5635144579310626e-05, + "loss": 1.3433, + "step": 3609 + }, + { + "epoch": 0.38, + "learning_rate": 1.5632120446597177e-05, + "loss": 1.4661, + "step": 3610 + }, + { + "epoch": 0.38, + "learning_rate": 1.5629095559324297e-05, + "loss": 1.4205, + "step": 3611 + }, + { + "epoch": 0.38, + "learning_rate": 1.562606991789725e-05, + "loss": 1.3976, + "step": 3612 + }, + { + "epoch": 0.38, + "learning_rate": 1.5623043522721393e-05, + "loss": 1.4261, + "step": 3613 + }, + { + "epoch": 0.38, + "learning_rate": 1.562001637420218e-05, + "loss": 1.4358, + "step": 3614 + }, + { + "epoch": 0.38, + "learning_rate": 1.5616988472745175e-05, + "loss": 1.437, + "step": 3615 + }, + { + "epoch": 0.38, + "learning_rate": 1.561395981875604e-05, + "loss": 1.3735, + "step": 3616 + }, + { + "epoch": 0.38, + "learning_rate": 1.5610930412640532e-05, + "loss": 1.4357, + "step": 3617 + }, + { + "epoch": 0.38, + "learning_rate": 1.560790025480452e-05, + "loss": 1.4003, + "step": 3618 + }, + { + "epoch": 0.38, + "learning_rate": 1.5604869345653965e-05, + "loss": 1.4127, + "step": 3619 + }, + { + "epoch": 0.38, + "learning_rate": 1.5601837685594927e-05, + "loss": 1.4666, + "step": 3620 + }, + { + "epoch": 0.38, + "learning_rate": 1.5598805275033574e-05, + "loss": 1.4106, + "step": 3621 + }, + { + "epoch": 0.38, + "learning_rate": 1.5595772114376174e-05, + "loss": 1.3857, + "step": 3622 + }, + { + "epoch": 0.38, + "learning_rate": 1.5592738204029086e-05, + "loss": 1.4704, + "step": 3623 + }, + { + "epoch": 0.38, + "learning_rate": 1.558970354439878e-05, + "loss": 1.4649, + "step": 3624 + }, + { + "epoch": 0.38, + "learning_rate": 1.5586668135891824e-05, + "loss": 1.4812, + "step": 3625 + }, + { + "epoch": 0.38, + "learning_rate": 1.5583631978914882e-05, + "loss": 1.3507, + "step": 3626 + }, + { + "epoch": 0.38, + "learning_rate": 1.5580595073874718e-05, + "loss": 1.3762, + "step": 3627 + }, + { + "epoch": 0.38, + "learning_rate": 1.557755742117821e-05, + "loss": 1.4169, + "step": 3628 + }, + { + "epoch": 0.38, + "learning_rate": 1.557451902123231e-05, + "loss": 1.4098, + "step": 3629 + }, + { + "epoch": 0.38, + "learning_rate": 1.55714798744441e-05, + "loss": 1.5526, + "step": 3630 + }, + { + "epoch": 0.38, + "learning_rate": 1.556843998122074e-05, + "loss": 1.4414, + "step": 3631 + }, + { + "epoch": 0.38, + "learning_rate": 1.5565399341969497e-05, + "loss": 1.4134, + "step": 3632 + }, + { + "epoch": 0.38, + "learning_rate": 1.556235795709774e-05, + "loss": 1.4718, + "step": 3633 + }, + { + "epoch": 0.38, + "learning_rate": 1.5559315827012937e-05, + "loss": 1.412, + "step": 3634 + }, + { + "epoch": 0.38, + "learning_rate": 1.5556272952122657e-05, + "loss": 1.4119, + "step": 3635 + }, + { + "epoch": 0.38, + "learning_rate": 1.5553229332834564e-05, + "loss": 1.3999, + "step": 3636 + }, + { + "epoch": 0.38, + "learning_rate": 1.5550184969556428e-05, + "loss": 1.4626, + "step": 3637 + }, + { + "epoch": 0.38, + "learning_rate": 1.5547139862696113e-05, + "loss": 1.3811, + "step": 3638 + }, + { + "epoch": 0.38, + "learning_rate": 1.5544094012661583e-05, + "loss": 1.4053, + "step": 3639 + }, + { + "epoch": 0.38, + "learning_rate": 1.5541047419860907e-05, + "loss": 1.4059, + "step": 3640 + }, + { + "epoch": 0.38, + "learning_rate": 1.553800008470225e-05, + "loss": 1.4717, + "step": 3641 + }, + { + "epoch": 0.38, + "learning_rate": 1.553495200759388e-05, + "loss": 1.399, + "step": 3642 + }, + { + "epoch": 0.38, + "learning_rate": 1.5531903188944154e-05, + "loss": 1.4143, + "step": 3643 + }, + { + "epoch": 0.38, + "learning_rate": 1.5528853629161536e-05, + "loss": 1.4414, + "step": 3644 + }, + { + "epoch": 0.38, + "learning_rate": 1.5525803328654592e-05, + "loss": 1.4206, + "step": 3645 + }, + { + "epoch": 0.38, + "learning_rate": 1.5522752287831982e-05, + "loss": 1.3869, + "step": 3646 + }, + { + "epoch": 0.38, + "learning_rate": 1.551970050710247e-05, + "loss": 1.5434, + "step": 3647 + }, + { + "epoch": 0.38, + "learning_rate": 1.5516647986874914e-05, + "loss": 1.4574, + "step": 3648 + }, + { + "epoch": 0.38, + "learning_rate": 1.5513594727558273e-05, + "loss": 1.4353, + "step": 3649 + }, + { + "epoch": 0.38, + "learning_rate": 1.5510540729561606e-05, + "loss": 1.4122, + "step": 3650 + }, + { + "epoch": 0.38, + "learning_rate": 1.550748599329407e-05, + "loss": 1.4077, + "step": 3651 + }, + { + "epoch": 0.38, + "learning_rate": 1.550443051916492e-05, + "loss": 1.4433, + "step": 3652 + }, + { + "epoch": 0.38, + "learning_rate": 1.5501374307583514e-05, + "loss": 1.54, + "step": 3653 + }, + { + "epoch": 0.38, + "learning_rate": 1.5498317358959302e-05, + "loss": 1.4522, + "step": 3654 + }, + { + "epoch": 0.38, + "learning_rate": 1.5495259673701842e-05, + "loss": 1.4175, + "step": 3655 + }, + { + "epoch": 0.38, + "learning_rate": 1.5492201252220777e-05, + "loss": 1.4637, + "step": 3656 + }, + { + "epoch": 0.38, + "learning_rate": 1.5489142094925863e-05, + "loss": 1.4701, + "step": 3657 + }, + { + "epoch": 0.38, + "learning_rate": 1.548608220222695e-05, + "loss": 1.4095, + "step": 3658 + }, + { + "epoch": 0.38, + "learning_rate": 1.548302157453398e-05, + "loss": 1.3903, + "step": 3659 + }, + { + "epoch": 0.38, + "learning_rate": 1.5479960212257002e-05, + "loss": 1.4062, + "step": 3660 + }, + { + "epoch": 0.38, + "learning_rate": 1.5476898115806157e-05, + "loss": 1.4706, + "step": 3661 + }, + { + "epoch": 0.38, + "learning_rate": 1.547383528559169e-05, + "loss": 1.4423, + "step": 3662 + }, + { + "epoch": 0.38, + "learning_rate": 1.547077172202394e-05, + "loss": 1.4418, + "step": 3663 + }, + { + "epoch": 0.38, + "learning_rate": 1.5467707425513347e-05, + "loss": 1.4553, + "step": 3664 + }, + { + "epoch": 0.38, + "learning_rate": 1.5464642396470443e-05, + "loss": 1.435, + "step": 3665 + }, + { + "epoch": 0.38, + "learning_rate": 1.5461576635305873e-05, + "loss": 1.4105, + "step": 3666 + }, + { + "epoch": 0.38, + "learning_rate": 1.5458510142430364e-05, + "loss": 1.4118, + "step": 3667 + }, + { + "epoch": 0.38, + "learning_rate": 1.5455442918254746e-05, + "loss": 1.4096, + "step": 3668 + }, + { + "epoch": 0.38, + "learning_rate": 1.545237496318995e-05, + "loss": 1.4248, + "step": 3669 + }, + { + "epoch": 0.38, + "learning_rate": 1.5449306277647003e-05, + "loss": 1.4591, + "step": 3670 + }, + { + "epoch": 0.38, + "learning_rate": 1.544623686203703e-05, + "loss": 1.4764, + "step": 3671 + }, + { + "epoch": 0.39, + "learning_rate": 1.5443166716771255e-05, + "loss": 1.4329, + "step": 3672 + }, + { + "epoch": 0.39, + "learning_rate": 1.5440095842260995e-05, + "loss": 1.4023, + "step": 3673 + }, + { + "epoch": 0.39, + "learning_rate": 1.5437024238917674e-05, + "loss": 1.3802, + "step": 3674 + }, + { + "epoch": 0.39, + "learning_rate": 1.5433951907152806e-05, + "loss": 1.4627, + "step": 3675 + }, + { + "epoch": 0.39, + "learning_rate": 1.5430878847378e-05, + "loss": 1.5164, + "step": 3676 + }, + { + "epoch": 0.39, + "learning_rate": 1.542780506000497e-05, + "loss": 1.3546, + "step": 3677 + }, + { + "epoch": 0.39, + "learning_rate": 1.542473054544553e-05, + "loss": 1.4415, + "step": 3678 + }, + { + "epoch": 0.39, + "learning_rate": 1.5421655304111573e-05, + "loss": 1.4093, + "step": 3679 + }, + { + "epoch": 0.39, + "learning_rate": 1.5418579336415114e-05, + "loss": 1.3943, + "step": 3680 + }, + { + "epoch": 0.39, + "learning_rate": 1.5415502642768252e-05, + "loss": 1.3659, + "step": 3681 + }, + { + "epoch": 0.39, + "learning_rate": 1.541242522358318e-05, + "loss": 1.4322, + "step": 3682 + }, + { + "epoch": 0.39, + "learning_rate": 1.5409347079272198e-05, + "loss": 1.4064, + "step": 3683 + }, + { + "epoch": 0.39, + "learning_rate": 1.5406268210247693e-05, + "loss": 1.4031, + "step": 3684 + }, + { + "epoch": 0.39, + "learning_rate": 1.540318861692216e-05, + "loss": 1.3449, + "step": 3685 + }, + { + "epoch": 0.39, + "learning_rate": 1.5400108299708182e-05, + "loss": 1.5536, + "step": 3686 + }, + { + "epoch": 0.39, + "learning_rate": 1.5397027259018442e-05, + "loss": 1.4106, + "step": 3687 + }, + { + "epoch": 0.39, + "learning_rate": 1.5393945495265722e-05, + "loss": 1.4309, + "step": 3688 + }, + { + "epoch": 0.39, + "learning_rate": 1.53908630088629e-05, + "loss": 1.3765, + "step": 3689 + }, + { + "epoch": 0.39, + "learning_rate": 1.5387779800222947e-05, + "loss": 1.3809, + "step": 3690 + }, + { + "epoch": 0.39, + "learning_rate": 1.5384695869758938e-05, + "loss": 1.4758, + "step": 3691 + }, + { + "epoch": 0.39, + "learning_rate": 1.5381611217884032e-05, + "loss": 1.4249, + "step": 3692 + }, + { + "epoch": 0.39, + "learning_rate": 1.5378525845011503e-05, + "loss": 1.4133, + "step": 3693 + }, + { + "epoch": 0.39, + "learning_rate": 1.5375439751554708e-05, + "loss": 1.418, + "step": 3694 + }, + { + "epoch": 0.39, + "learning_rate": 1.53723529379271e-05, + "loss": 1.441, + "step": 3695 + }, + { + "epoch": 0.39, + "learning_rate": 1.536926540454224e-05, + "loss": 1.3919, + "step": 3696 + }, + { + "epoch": 0.39, + "learning_rate": 1.5366177151813775e-05, + "loss": 1.3722, + "step": 3697 + }, + { + "epoch": 0.39, + "learning_rate": 1.536308818015545e-05, + "loss": 1.4727, + "step": 3698 + }, + { + "epoch": 0.39, + "learning_rate": 1.535999848998111e-05, + "loss": 1.442, + "step": 3699 + }, + { + "epoch": 0.39, + "learning_rate": 1.535690808170469e-05, + "loss": 1.3884, + "step": 3700 + }, + { + "epoch": 0.39, + "learning_rate": 1.535381695574023e-05, + "loss": 1.3226, + "step": 3701 + }, + { + "epoch": 0.39, + "learning_rate": 1.535072511250186e-05, + "loss": 1.4403, + "step": 3702 + }, + { + "epoch": 0.39, + "learning_rate": 1.5347632552403808e-05, + "loss": 1.4144, + "step": 3703 + }, + { + "epoch": 0.39, + "learning_rate": 1.5344539275860395e-05, + "loss": 1.3514, + "step": 3704 + }, + { + "epoch": 0.39, + "learning_rate": 1.5341445283286044e-05, + "loss": 1.519, + "step": 3705 + }, + { + "epoch": 0.39, + "learning_rate": 1.5338350575095268e-05, + "loss": 1.4251, + "step": 3706 + }, + { + "epoch": 0.39, + "learning_rate": 1.5335255151702685e-05, + "loss": 1.392, + "step": 3707 + }, + { + "epoch": 0.39, + "learning_rate": 1.533215901352299e-05, + "loss": 1.3838, + "step": 3708 + }, + { + "epoch": 0.39, + "learning_rate": 1.532906216097099e-05, + "loss": 1.444, + "step": 3709 + }, + { + "epoch": 0.39, + "learning_rate": 1.5325964594461594e-05, + "loss": 1.3459, + "step": 3710 + }, + { + "epoch": 0.39, + "learning_rate": 1.5322866314409783e-05, + "loss": 1.4155, + "step": 3711 + }, + { + "epoch": 0.39, + "learning_rate": 1.5319767321230657e-05, + "loss": 1.4057, + "step": 3712 + }, + { + "epoch": 0.39, + "learning_rate": 1.5316667615339392e-05, + "loss": 1.382, + "step": 3713 + }, + { + "epoch": 0.39, + "learning_rate": 1.5313567197151277e-05, + "loss": 1.3634, + "step": 3714 + }, + { + "epoch": 0.39, + "learning_rate": 1.5310466067081688e-05, + "loss": 1.3434, + "step": 3715 + }, + { + "epoch": 0.39, + "learning_rate": 1.530736422554609e-05, + "loss": 1.4553, + "step": 3716 + }, + { + "epoch": 0.39, + "learning_rate": 1.5304261672960055e-05, + "loss": 1.4193, + "step": 3717 + }, + { + "epoch": 0.39, + "learning_rate": 1.5301158409739242e-05, + "loss": 1.3955, + "step": 3718 + }, + { + "epoch": 0.39, + "learning_rate": 1.5298054436299413e-05, + "loss": 1.4592, + "step": 3719 + }, + { + "epoch": 0.39, + "learning_rate": 1.529494975305642e-05, + "loss": 1.738, + "step": 3720 + }, + { + "epoch": 0.39, + "learning_rate": 1.529184436042621e-05, + "loss": 1.438, + "step": 3721 + }, + { + "epoch": 0.39, + "learning_rate": 1.528873825882482e-05, + "loss": 1.3445, + "step": 3722 + }, + { + "epoch": 0.39, + "learning_rate": 1.5285631448668395e-05, + "loss": 1.4168, + "step": 3723 + }, + { + "epoch": 0.39, + "learning_rate": 1.528252393037317e-05, + "loss": 1.4088, + "step": 3724 + }, + { + "epoch": 0.39, + "learning_rate": 1.5279415704355468e-05, + "loss": 1.4484, + "step": 3725 + }, + { + "epoch": 0.39, + "learning_rate": 1.5276306771031708e-05, + "loss": 1.4706, + "step": 3726 + }, + { + "epoch": 0.39, + "learning_rate": 1.527319713081841e-05, + "loss": 1.3466, + "step": 3727 + }, + { + "epoch": 0.39, + "learning_rate": 1.5270086784132196e-05, + "loss": 1.427, + "step": 3728 + }, + { + "epoch": 0.39, + "learning_rate": 1.5266975731389754e-05, + "loss": 1.4596, + "step": 3729 + }, + { + "epoch": 0.39, + "learning_rate": 1.52638639730079e-05, + "loss": 1.405, + "step": 3730 + }, + { + "epoch": 0.39, + "learning_rate": 1.5260751509403518e-05, + "loss": 1.4572, + "step": 3731 + }, + { + "epoch": 0.39, + "learning_rate": 1.5257638340993608e-05, + "loss": 1.3827, + "step": 3732 + }, + { + "epoch": 0.39, + "learning_rate": 1.5254524468195251e-05, + "loss": 1.3712, + "step": 3733 + }, + { + "epoch": 0.39, + "learning_rate": 1.5251409891425626e-05, + "loss": 1.4541, + "step": 3734 + }, + { + "epoch": 0.39, + "learning_rate": 1.5248294611102006e-05, + "loss": 1.5279, + "step": 3735 + }, + { + "epoch": 0.39, + "learning_rate": 1.5245178627641759e-05, + "loss": 1.3722, + "step": 3736 + }, + { + "epoch": 0.39, + "learning_rate": 1.5242061941462348e-05, + "loss": 1.5158, + "step": 3737 + }, + { + "epoch": 0.39, + "learning_rate": 1.523894455298132e-05, + "loss": 1.4274, + "step": 3738 + }, + { + "epoch": 0.39, + "learning_rate": 1.5235826462616338e-05, + "loss": 1.4543, + "step": 3739 + }, + { + "epoch": 0.39, + "learning_rate": 1.5232707670785144e-05, + "loss": 1.5011, + "step": 3740 + }, + { + "epoch": 0.39, + "learning_rate": 1.5229588177905568e-05, + "loss": 1.24, + "step": 3741 + }, + { + "epoch": 0.39, + "learning_rate": 1.5226467984395544e-05, + "loss": 1.4253, + "step": 3742 + }, + { + "epoch": 0.39, + "learning_rate": 1.5223347090673102e-05, + "loss": 1.3736, + "step": 3743 + }, + { + "epoch": 0.39, + "learning_rate": 1.522022549715636e-05, + "loss": 1.4587, + "step": 3744 + }, + { + "epoch": 0.39, + "learning_rate": 1.521710320426353e-05, + "loss": 1.5024, + "step": 3745 + }, + { + "epoch": 0.39, + "learning_rate": 1.521398021241292e-05, + "loss": 1.427, + "step": 3746 + }, + { + "epoch": 0.39, + "learning_rate": 1.5210856522022929e-05, + "loss": 1.3387, + "step": 3747 + }, + { + "epoch": 0.39, + "learning_rate": 1.5207732133512055e-05, + "loss": 1.3819, + "step": 3748 + }, + { + "epoch": 0.39, + "learning_rate": 1.5204607047298883e-05, + "loss": 1.4571, + "step": 3749 + }, + { + "epoch": 0.39, + "learning_rate": 1.5201481263802094e-05, + "loss": 1.3592, + "step": 3750 + }, + { + "epoch": 0.39, + "learning_rate": 1.5198354783440464e-05, + "loss": 1.3912, + "step": 3751 + }, + { + "epoch": 0.39, + "learning_rate": 1.519522760663286e-05, + "loss": 1.4986, + "step": 3752 + }, + { + "epoch": 0.39, + "learning_rate": 1.5192099733798243e-05, + "loss": 1.4106, + "step": 3753 + }, + { + "epoch": 0.39, + "learning_rate": 1.5188971165355667e-05, + "loss": 1.4145, + "step": 3754 + }, + { + "epoch": 0.39, + "learning_rate": 1.5185841901724282e-05, + "loss": 1.3915, + "step": 3755 + }, + { + "epoch": 0.39, + "learning_rate": 1.5182711943323329e-05, + "loss": 1.4014, + "step": 3756 + }, + { + "epoch": 0.39, + "learning_rate": 1.5179581290572141e-05, + "loss": 1.3651, + "step": 3757 + }, + { + "epoch": 0.39, + "learning_rate": 1.5176449943890147e-05, + "loss": 1.3653, + "step": 3758 + }, + { + "epoch": 0.39, + "learning_rate": 1.5173317903696862e-05, + "loss": 1.4486, + "step": 3759 + }, + { + "epoch": 0.39, + "learning_rate": 1.5170185170411906e-05, + "loss": 1.4459, + "step": 3760 + }, + { + "epoch": 0.39, + "learning_rate": 1.5167051744454977e-05, + "loss": 1.4215, + "step": 3761 + }, + { + "epoch": 0.39, + "learning_rate": 1.5163917626245877e-05, + "loss": 1.4379, + "step": 3762 + }, + { + "epoch": 0.39, + "learning_rate": 1.51607828162045e-05, + "loss": 1.4147, + "step": 3763 + }, + { + "epoch": 0.39, + "learning_rate": 1.5157647314750827e-05, + "loss": 1.4011, + "step": 3764 + }, + { + "epoch": 0.39, + "learning_rate": 1.5154511122304936e-05, + "loss": 1.4309, + "step": 3765 + }, + { + "epoch": 0.39, + "learning_rate": 1.5151374239286993e-05, + "loss": 1.4382, + "step": 3766 + }, + { + "epoch": 0.4, + "learning_rate": 1.5148236666117266e-05, + "loss": 1.405, + "step": 3767 + }, + { + "epoch": 0.4, + "learning_rate": 1.5145098403216104e-05, + "loss": 1.4223, + "step": 3768 + }, + { + "epoch": 0.4, + "learning_rate": 1.5141959451003951e-05, + "loss": 1.4084, + "step": 3769 + }, + { + "epoch": 0.4, + "learning_rate": 1.5138819809901356e-05, + "loss": 1.4063, + "step": 3770 + }, + { + "epoch": 0.4, + "learning_rate": 1.513567948032894e-05, + "loss": 1.3299, + "step": 3771 + }, + { + "epoch": 0.4, + "learning_rate": 1.5132538462707431e-05, + "loss": 1.3901, + "step": 3772 + }, + { + "epoch": 0.4, + "learning_rate": 1.5129396757457646e-05, + "loss": 1.4249, + "step": 3773 + }, + { + "epoch": 0.4, + "learning_rate": 1.512625436500049e-05, + "loss": 1.4087, + "step": 3774 + }, + { + "epoch": 0.4, + "learning_rate": 1.5123111285756964e-05, + "loss": 1.3521, + "step": 3775 + }, + { + "epoch": 0.4, + "learning_rate": 1.5119967520148163e-05, + "loss": 1.4097, + "step": 3776 + }, + { + "epoch": 0.4, + "learning_rate": 1.5116823068595261e-05, + "loss": 1.4871, + "step": 3777 + }, + { + "epoch": 0.4, + "learning_rate": 1.5113677931519543e-05, + "loss": 1.44, + "step": 3778 + }, + { + "epoch": 0.4, + "learning_rate": 1.5110532109342377e-05, + "loss": 1.4518, + "step": 3779 + }, + { + "epoch": 0.4, + "learning_rate": 1.5107385602485214e-05, + "loss": 1.3961, + "step": 3780 + }, + { + "epoch": 0.4, + "learning_rate": 1.5104238411369614e-05, + "loss": 1.4341, + "step": 3781 + }, + { + "epoch": 0.4, + "eval_loss": 1.4642821550369263, + "eval_runtime": 77.3595, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 3781 + }, + { + "epoch": 0.4, + "learning_rate": 1.5101090536417218e-05, + "loss": 1.403, + "step": 3782 + }, + { + "epoch": 0.4, + "learning_rate": 1.5097941978049754e-05, + "loss": 1.4103, + "step": 3783 + }, + { + "epoch": 0.4, + "learning_rate": 1.5094792736689052e-05, + "loss": 1.3478, + "step": 3784 + }, + { + "epoch": 0.4, + "learning_rate": 1.5091642812757035e-05, + "loss": 1.4134, + "step": 3785 + }, + { + "epoch": 0.4, + "learning_rate": 1.5088492206675701e-05, + "loss": 1.4134, + "step": 3786 + }, + { + "epoch": 0.4, + "learning_rate": 1.5085340918867162e-05, + "loss": 1.1494, + "step": 3787 + }, + { + "epoch": 0.4, + "learning_rate": 1.5082188949753598e-05, + "loss": 1.2385, + "step": 3788 + }, + { + "epoch": 0.4, + "learning_rate": 1.5079036299757299e-05, + "loss": 1.4258, + "step": 3789 + }, + { + "epoch": 0.4, + "learning_rate": 1.5075882969300639e-05, + "loss": 1.3781, + "step": 3790 + }, + { + "epoch": 0.4, + "learning_rate": 1.507272895880608e-05, + "loss": 1.5096, + "step": 3791 + }, + { + "epoch": 0.4, + "learning_rate": 1.5069574268696179e-05, + "loss": 1.366, + "step": 3792 + }, + { + "epoch": 0.4, + "learning_rate": 1.5066418899393584e-05, + "loss": 1.3792, + "step": 3793 + }, + { + "epoch": 0.4, + "learning_rate": 1.506326285132104e-05, + "loss": 1.4987, + "step": 3794 + }, + { + "epoch": 0.4, + "learning_rate": 1.5060106124901364e-05, + "loss": 1.445, + "step": 3795 + }, + { + "epoch": 0.4, + "learning_rate": 1.5056948720557482e-05, + "loss": 1.5071, + "step": 3796 + }, + { + "epoch": 0.4, + "learning_rate": 1.505379063871241e-05, + "loss": 1.4029, + "step": 3797 + }, + { + "epoch": 0.4, + "learning_rate": 1.5050631879789244e-05, + "loss": 1.5263, + "step": 3798 + }, + { + "epoch": 0.4, + "learning_rate": 1.5047472444211175e-05, + "loss": 1.3906, + "step": 3799 + }, + { + "epoch": 0.4, + "learning_rate": 1.5044312332401494e-05, + "loss": 1.7352, + "step": 3800 + }, + { + "epoch": 0.4, + "learning_rate": 1.5041151544783565e-05, + "loss": 1.3946, + "step": 3801 + }, + { + "epoch": 0.4, + "learning_rate": 1.5037990081780862e-05, + "loss": 1.3592, + "step": 3802 + }, + { + "epoch": 0.4, + "learning_rate": 1.503482794381693e-05, + "loss": 1.3991, + "step": 3803 + }, + { + "epoch": 0.4, + "learning_rate": 1.5031665131315423e-05, + "loss": 1.4271, + "step": 3804 + }, + { + "epoch": 0.4, + "learning_rate": 1.502850164470007e-05, + "loss": 1.4305, + "step": 3805 + }, + { + "epoch": 0.4, + "learning_rate": 1.5025337484394701e-05, + "loss": 1.4116, + "step": 3806 + }, + { + "epoch": 0.4, + "learning_rate": 1.5022172650823232e-05, + "loss": 1.4242, + "step": 3807 + }, + { + "epoch": 0.4, + "learning_rate": 1.5019007144409667e-05, + "loss": 1.4427, + "step": 3808 + }, + { + "epoch": 0.4, + "learning_rate": 1.5015840965578106e-05, + "loss": 1.3705, + "step": 3809 + }, + { + "epoch": 0.4, + "learning_rate": 1.5012674114752732e-05, + "loss": 1.4498, + "step": 3810 + }, + { + "epoch": 0.4, + "learning_rate": 1.5009506592357822e-05, + "loss": 1.489, + "step": 3811 + }, + { + "epoch": 0.4, + "learning_rate": 1.5006338398817746e-05, + "loss": 1.4801, + "step": 3812 + }, + { + "epoch": 0.4, + "learning_rate": 1.5003169534556956e-05, + "loss": 1.3468, + "step": 3813 + }, + { + "epoch": 0.4, + "learning_rate": 1.5000000000000002e-05, + "loss": 1.4211, + "step": 3814 + }, + { + "epoch": 0.4, + "learning_rate": 1.4996829795571518e-05, + "loss": 1.4683, + "step": 3815 + }, + { + "epoch": 0.4, + "learning_rate": 1.499365892169623e-05, + "loss": 1.4441, + "step": 3816 + }, + { + "epoch": 0.4, + "learning_rate": 1.4990487378798958e-05, + "loss": 1.4368, + "step": 3817 + }, + { + "epoch": 0.4, + "learning_rate": 1.4987315167304602e-05, + "loss": 1.4097, + "step": 3818 + }, + { + "epoch": 0.4, + "learning_rate": 1.4984142287638155e-05, + "loss": 1.4238, + "step": 3819 + }, + { + "epoch": 0.4, + "learning_rate": 1.4980968740224708e-05, + "loss": 1.497, + "step": 3820 + }, + { + "epoch": 0.4, + "learning_rate": 1.4977794525489433e-05, + "loss": 1.3989, + "step": 3821 + }, + { + "epoch": 0.4, + "learning_rate": 1.4974619643857588e-05, + "loss": 1.4415, + "step": 3822 + }, + { + "epoch": 0.4, + "learning_rate": 1.4971444095754533e-05, + "loss": 1.3931, + "step": 3823 + }, + { + "epoch": 0.4, + "learning_rate": 1.4968267881605705e-05, + "loss": 1.3426, + "step": 3824 + }, + { + "epoch": 0.4, + "learning_rate": 1.4965091001836636e-05, + "loss": 1.644, + "step": 3825 + }, + { + "epoch": 0.4, + "learning_rate": 1.4961913456872945e-05, + "loss": 1.3903, + "step": 3826 + }, + { + "epoch": 0.4, + "learning_rate": 1.4958735247140345e-05, + "loss": 1.3764, + "step": 3827 + }, + { + "epoch": 0.4, + "learning_rate": 1.4955556373064632e-05, + "loss": 1.5484, + "step": 3828 + }, + { + "epoch": 0.4, + "learning_rate": 1.4952376835071696e-05, + "loss": 1.5696, + "step": 3829 + }, + { + "epoch": 0.4, + "learning_rate": 1.4949196633587509e-05, + "loss": 1.3844, + "step": 3830 + }, + { + "epoch": 0.4, + "learning_rate": 1.494601576903814e-05, + "loss": 1.3868, + "step": 3831 + }, + { + "epoch": 0.4, + "learning_rate": 1.4942834241849741e-05, + "loss": 1.4229, + "step": 3832 + }, + { + "epoch": 0.4, + "learning_rate": 1.4939652052448557e-05, + "loss": 1.4062, + "step": 3833 + }, + { + "epoch": 0.4, + "learning_rate": 1.4936469201260915e-05, + "loss": 1.3955, + "step": 3834 + }, + { + "epoch": 0.4, + "learning_rate": 1.4933285688713239e-05, + "loss": 1.3959, + "step": 3835 + }, + { + "epoch": 0.4, + "learning_rate": 1.4930101515232038e-05, + "loss": 1.4652, + "step": 3836 + }, + { + "epoch": 0.4, + "learning_rate": 1.4926916681243913e-05, + "loss": 1.5253, + "step": 3837 + }, + { + "epoch": 0.4, + "learning_rate": 1.4923731187175539e-05, + "loss": 1.4694, + "step": 3838 + }, + { + "epoch": 0.4, + "learning_rate": 1.4920545033453702e-05, + "loss": 1.3859, + "step": 3839 + }, + { + "epoch": 0.4, + "learning_rate": 1.4917358220505259e-05, + "loss": 1.4157, + "step": 3840 + }, + { + "epoch": 0.4, + "learning_rate": 1.4914170748757159e-05, + "loss": 1.4491, + "step": 3841 + }, + { + "epoch": 0.4, + "learning_rate": 1.4910982618636445e-05, + "loss": 1.4464, + "step": 3842 + }, + { + "epoch": 0.4, + "learning_rate": 1.4907793830570246e-05, + "loss": 1.3771, + "step": 3843 + }, + { + "epoch": 0.4, + "learning_rate": 1.4904604384985775e-05, + "loss": 1.3673, + "step": 3844 + }, + { + "epoch": 0.4, + "learning_rate": 1.4901414282310334e-05, + "loss": 1.4429, + "step": 3845 + }, + { + "epoch": 0.4, + "learning_rate": 1.4898223522971318e-05, + "loss": 1.4905, + "step": 3846 + }, + { + "epoch": 0.4, + "learning_rate": 1.4895032107396205e-05, + "loss": 1.4039, + "step": 3847 + }, + { + "epoch": 0.4, + "learning_rate": 1.4891840036012566e-05, + "loss": 1.4082, + "step": 3848 + }, + { + "epoch": 0.4, + "learning_rate": 1.4888647309248052e-05, + "loss": 1.3643, + "step": 3849 + }, + { + "epoch": 0.4, + "learning_rate": 1.4885453927530408e-05, + "loss": 1.3116, + "step": 3850 + }, + { + "epoch": 0.4, + "learning_rate": 1.4882259891287467e-05, + "loss": 1.4278, + "step": 3851 + }, + { + "epoch": 0.4, + "learning_rate": 1.4879065200947148e-05, + "loss": 1.3712, + "step": 3852 + }, + { + "epoch": 0.4, + "learning_rate": 1.4875869856937449e-05, + "loss": 1.387, + "step": 3853 + }, + { + "epoch": 0.4, + "learning_rate": 1.4872673859686475e-05, + "loss": 1.5053, + "step": 3854 + }, + { + "epoch": 0.4, + "learning_rate": 1.4869477209622404e-05, + "loss": 1.4427, + "step": 3855 + }, + { + "epoch": 0.4, + "learning_rate": 1.4866279907173502e-05, + "loss": 1.3404, + "step": 3856 + }, + { + "epoch": 0.4, + "learning_rate": 1.4863081952768126e-05, + "loss": 1.3126, + "step": 3857 + }, + { + "epoch": 0.4, + "learning_rate": 1.4859883346834725e-05, + "loss": 1.4588, + "step": 3858 + }, + { + "epoch": 0.4, + "learning_rate": 1.4856684089801822e-05, + "loss": 1.408, + "step": 3859 + }, + { + "epoch": 0.4, + "learning_rate": 1.4853484182098044e-05, + "loss": 1.4356, + "step": 3860 + }, + { + "epoch": 0.4, + "learning_rate": 1.4850283624152088e-05, + "loss": 1.3768, + "step": 3861 + }, + { + "epoch": 0.4, + "learning_rate": 1.4847082416392753e-05, + "loss": 1.4563, + "step": 3862 + }, + { + "epoch": 0.41, + "learning_rate": 1.4843880559248915e-05, + "loss": 1.3648, + "step": 3863 + }, + { + "epoch": 0.41, + "learning_rate": 1.4840678053149542e-05, + "loss": 1.4146, + "step": 3864 + }, + { + "epoch": 0.41, + "learning_rate": 1.4837474898523686e-05, + "loss": 1.4423, + "step": 3865 + }, + { + "epoch": 0.41, + "learning_rate": 1.4834271095800487e-05, + "loss": 1.3351, + "step": 3866 + }, + { + "epoch": 0.41, + "learning_rate": 1.4831066645409178e-05, + "loss": 1.4534, + "step": 3867 + }, + { + "epoch": 0.41, + "learning_rate": 1.4827861547779066e-05, + "loss": 1.4763, + "step": 3868 + }, + { + "epoch": 0.41, + "learning_rate": 1.4824655803339553e-05, + "loss": 1.4019, + "step": 3869 + }, + { + "epoch": 0.41, + "learning_rate": 1.4821449412520132e-05, + "loss": 1.4223, + "step": 3870 + }, + { + "epoch": 0.41, + "learning_rate": 1.4818242375750371e-05, + "loss": 1.4065, + "step": 3871 + }, + { + "epoch": 0.41, + "learning_rate": 1.481503469345993e-05, + "loss": 1.587, + "step": 3872 + }, + { + "epoch": 0.41, + "learning_rate": 1.4811826366078562e-05, + "loss": 1.3746, + "step": 3873 + }, + { + "epoch": 0.41, + "learning_rate": 1.4808617394036096e-05, + "loss": 1.3425, + "step": 3874 + }, + { + "epoch": 0.41, + "learning_rate": 1.480540777776245e-05, + "loss": 0.6637, + "step": 3875 + }, + { + "epoch": 0.41, + "learning_rate": 1.4802197517687634e-05, + "loss": 1.3366, + "step": 3876 + }, + { + "epoch": 0.41, + "learning_rate": 1.479898661424174e-05, + "loss": 1.4033, + "step": 3877 + }, + { + "epoch": 0.41, + "learning_rate": 1.4795775067854947e-05, + "loss": 1.4005, + "step": 3878 + }, + { + "epoch": 0.41, + "learning_rate": 1.4792562878957516e-05, + "loss": 1.3651, + "step": 3879 + }, + { + "epoch": 0.41, + "learning_rate": 1.47893500479798e-05, + "loss": 1.4185, + "step": 3880 + }, + { + "epoch": 0.41, + "learning_rate": 1.4786136575352236e-05, + "loss": 1.4394, + "step": 3881 + }, + { + "epoch": 0.41, + "learning_rate": 1.478292246150535e-05, + "loss": 1.7243, + "step": 3882 + }, + { + "epoch": 0.41, + "learning_rate": 1.4779707706869744e-05, + "loss": 1.3574, + "step": 3883 + }, + { + "epoch": 0.41, + "learning_rate": 1.4776492311876116e-05, + "loss": 1.4031, + "step": 3884 + }, + { + "epoch": 0.41, + "learning_rate": 1.4773276276955248e-05, + "loss": 1.4351, + "step": 3885 + }, + { + "epoch": 0.41, + "learning_rate": 1.4770059602538002e-05, + "loss": 1.3922, + "step": 3886 + }, + { + "epoch": 0.41, + "learning_rate": 1.4766842289055333e-05, + "loss": 1.3374, + "step": 3887 + }, + { + "epoch": 0.41, + "learning_rate": 1.4763624336938278e-05, + "loss": 1.428, + "step": 3888 + }, + { + "epoch": 0.41, + "learning_rate": 1.476040574661796e-05, + "loss": 1.6087, + "step": 3889 + }, + { + "epoch": 0.41, + "learning_rate": 1.4757186518525586e-05, + "loss": 1.4054, + "step": 3890 + }, + { + "epoch": 0.41, + "learning_rate": 1.4753966653092447e-05, + "loss": 1.2595, + "step": 3891 + }, + { + "epoch": 0.41, + "learning_rate": 1.475074615074993e-05, + "loss": 1.4052, + "step": 3892 + }, + { + "epoch": 0.41, + "learning_rate": 1.4747525011929492e-05, + "loss": 1.4296, + "step": 3893 + }, + { + "epoch": 0.41, + "learning_rate": 1.4744303237062689e-05, + "loss": 1.3718, + "step": 3894 + }, + { + "epoch": 0.41, + "learning_rate": 1.4741080826581151e-05, + "loss": 1.4498, + "step": 3895 + }, + { + "epoch": 0.41, + "learning_rate": 1.4737857780916602e-05, + "loss": 1.4029, + "step": 3896 + }, + { + "epoch": 0.41, + "learning_rate": 1.4734634100500846e-05, + "loss": 1.4136, + "step": 3897 + }, + { + "epoch": 0.41, + "learning_rate": 1.4731409785765774e-05, + "loss": 1.348, + "step": 3898 + }, + { + "epoch": 0.41, + "learning_rate": 1.4728184837143355e-05, + "loss": 1.3407, + "step": 3899 + }, + { + "epoch": 0.41, + "learning_rate": 1.472495925506566e-05, + "loss": 1.3737, + "step": 3900 + }, + { + "epoch": 0.41, + "learning_rate": 1.4721733039964826e-05, + "loss": 2.2305, + "step": 3901 + }, + { + "epoch": 0.41, + "learning_rate": 1.4718506192273087e-05, + "loss": 1.4506, + "step": 3902 + }, + { + "epoch": 0.41, + "learning_rate": 1.4715278712422754e-05, + "loss": 1.3657, + "step": 3903 + }, + { + "epoch": 0.41, + "learning_rate": 1.471205060084623e-05, + "loss": 1.4644, + "step": 3904 + }, + { + "epoch": 0.41, + "learning_rate": 1.4708821857976001e-05, + "loss": 1.4823, + "step": 3905 + }, + { + "epoch": 0.41, + "learning_rate": 1.4705592484244628e-05, + "loss": 1.3392, + "step": 3906 + }, + { + "epoch": 0.41, + "learning_rate": 1.4702362480084769e-05, + "loss": 1.3302, + "step": 3907 + }, + { + "epoch": 0.41, + "learning_rate": 1.4699131845929163e-05, + "loss": 1.8952, + "step": 3908 + }, + { + "epoch": 0.41, + "learning_rate": 1.469590058221063e-05, + "loss": 1.4982, + "step": 3909 + }, + { + "epoch": 0.41, + "learning_rate": 1.4692668689362074e-05, + "loss": 1.407, + "step": 3910 + }, + { + "epoch": 0.41, + "learning_rate": 1.4689436167816489e-05, + "loss": 1.3911, + "step": 3911 + }, + { + "epoch": 0.41, + "learning_rate": 1.4686203018006948e-05, + "loss": 1.3421, + "step": 3912 + }, + { + "epoch": 0.41, + "learning_rate": 1.4682969240366612e-05, + "loss": 1.4627, + "step": 3913 + }, + { + "epoch": 0.41, + "learning_rate": 1.4679734835328718e-05, + "loss": 1.394, + "step": 3914 + }, + { + "epoch": 0.41, + "learning_rate": 1.4676499803326603e-05, + "loss": 1.4484, + "step": 3915 + }, + { + "epoch": 0.41, + "learning_rate": 1.4673264144793673e-05, + "loss": 1.4665, + "step": 3916 + }, + { + "epoch": 0.41, + "learning_rate": 1.4670027860163422e-05, + "loss": 1.3191, + "step": 3917 + }, + { + "epoch": 0.41, + "learning_rate": 1.466679094986943e-05, + "loss": 1.4748, + "step": 3918 + }, + { + "epoch": 0.41, + "learning_rate": 1.4663553414345361e-05, + "loss": 1.2467, + "step": 3919 + }, + { + "epoch": 0.41, + "learning_rate": 1.466031525402496e-05, + "loss": 1.4279, + "step": 3920 + }, + { + "epoch": 0.41, + "learning_rate": 1.4657076469342059e-05, + "loss": 1.3822, + "step": 3921 + }, + { + "epoch": 0.41, + "learning_rate": 1.4653837060730566e-05, + "loss": 1.3659, + "step": 3922 + }, + { + "epoch": 0.41, + "learning_rate": 1.465059702862449e-05, + "loss": 1.3663, + "step": 3923 + }, + { + "epoch": 0.41, + "learning_rate": 1.4647356373457902e-05, + "loss": 1.4371, + "step": 3924 + }, + { + "epoch": 0.41, + "learning_rate": 1.4644115095664972e-05, + "loss": 1.3473, + "step": 3925 + }, + { + "epoch": 0.41, + "learning_rate": 1.4640873195679944e-05, + "loss": 1.4797, + "step": 3926 + }, + { + "epoch": 0.41, + "learning_rate": 1.463763067393715e-05, + "loss": 1.3973, + "step": 3927 + }, + { + "epoch": 0.41, + "learning_rate": 1.4634387530871008e-05, + "loss": 1.3899, + "step": 3928 + }, + { + "epoch": 0.41, + "learning_rate": 1.4631143766916015e-05, + "loss": 1.3828, + "step": 3929 + }, + { + "epoch": 0.41, + "learning_rate": 1.4627899382506745e-05, + "loss": 1.4569, + "step": 3930 + }, + { + "epoch": 0.41, + "learning_rate": 1.4624654378077872e-05, + "loss": 1.4011, + "step": 3931 + }, + { + "epoch": 0.41, + "learning_rate": 1.462140875406414e-05, + "loss": 1.3859, + "step": 3932 + }, + { + "epoch": 0.41, + "learning_rate": 1.4618162510900376e-05, + "loss": 1.4518, + "step": 3933 + }, + { + "epoch": 0.41, + "learning_rate": 1.4614915649021493e-05, + "loss": 1.4399, + "step": 3934 + }, + { + "epoch": 0.41, + "learning_rate": 1.4611668168862495e-05, + "loss": 1.4034, + "step": 3935 + }, + { + "epoch": 0.41, + "learning_rate": 1.4608420070858452e-05, + "loss": 1.3919, + "step": 3936 + }, + { + "epoch": 0.41, + "learning_rate": 1.4605171355444528e-05, + "loss": 1.391, + "step": 3937 + }, + { + "epoch": 0.41, + "learning_rate": 1.460192202305597e-05, + "loss": 1.3717, + "step": 3938 + }, + { + "epoch": 0.41, + "learning_rate": 1.4598672074128103e-05, + "loss": 1.4351, + "step": 3939 + }, + { + "epoch": 0.41, + "learning_rate": 1.4595421509096339e-05, + "loss": 1.4202, + "step": 3940 + }, + { + "epoch": 0.41, + "learning_rate": 1.4592170328396165e-05, + "loss": 1.3559, + "step": 3941 + }, + { + "epoch": 0.41, + "learning_rate": 1.458891853246316e-05, + "loss": 1.5878, + "step": 3942 + }, + { + "epoch": 0.41, + "learning_rate": 1.4585666121732982e-05, + "loss": 1.3818, + "step": 3943 + }, + { + "epoch": 0.41, + "learning_rate": 1.4582413096641369e-05, + "loss": 1.4009, + "step": 3944 + }, + { + "epoch": 0.41, + "learning_rate": 1.457915945762414e-05, + "loss": 1.3937, + "step": 3945 + }, + { + "epoch": 0.41, + "learning_rate": 1.4575905205117203e-05, + "loss": 1.381, + "step": 3946 + }, + { + "epoch": 0.41, + "learning_rate": 1.457265033955654e-05, + "loss": 1.3844, + "step": 3947 + }, + { + "epoch": 0.41, + "learning_rate": 1.4569394861378226e-05, + "loss": 1.4059, + "step": 3948 + }, + { + "epoch": 0.41, + "learning_rate": 1.4566138771018403e-05, + "loss": 1.3698, + "step": 3949 + }, + { + "epoch": 0.41, + "learning_rate": 1.4562882068913311e-05, + "loss": 1.4253, + "step": 3950 + }, + { + "epoch": 0.41, + "learning_rate": 1.455962475549926e-05, + "loss": 1.4284, + "step": 3951 + }, + { + "epoch": 0.41, + "learning_rate": 1.4556366831212647e-05, + "loss": 1.4279, + "step": 3952 + }, + { + "epoch": 0.41, + "learning_rate": 1.4553108296489951e-05, + "loss": 1.3072, + "step": 3953 + }, + { + "epoch": 0.41, + "learning_rate": 1.4549849151767731e-05, + "loss": 1.4175, + "step": 3954 + }, + { + "epoch": 0.41, + "learning_rate": 1.4546589397482632e-05, + "loss": 1.5042, + "step": 3955 + }, + { + "epoch": 0.41, + "learning_rate": 1.4543329034071371e-05, + "loss": 1.4363, + "step": 3956 + }, + { + "epoch": 0.41, + "learning_rate": 1.454006806197076e-05, + "loss": 1.4111, + "step": 3957 + }, + { + "epoch": 0.42, + "learning_rate": 1.453680648161768e-05, + "loss": 1.3817, + "step": 3958 + }, + { + "epoch": 0.42, + "learning_rate": 1.45335442934491e-05, + "loss": 1.4689, + "step": 3959 + }, + { + "epoch": 0.42, + "learning_rate": 1.4530281497902072e-05, + "loss": 1.4164, + "step": 3960 + }, + { + "epoch": 0.42, + "learning_rate": 1.4527018095413726e-05, + "loss": 1.3943, + "step": 3961 + }, + { + "epoch": 0.42, + "learning_rate": 1.4523754086421271e-05, + "loss": 1.3851, + "step": 3962 + }, + { + "epoch": 0.42, + "learning_rate": 1.4520489471362003e-05, + "loss": 1.3907, + "step": 3963 + }, + { + "epoch": 0.42, + "learning_rate": 1.4517224250673297e-05, + "loss": 1.2877, + "step": 3964 + }, + { + "epoch": 0.42, + "learning_rate": 1.4513958424792605e-05, + "loss": 1.4696, + "step": 3965 + }, + { + "epoch": 0.42, + "learning_rate": 1.4510691994157471e-05, + "loss": 1.3785, + "step": 3966 + }, + { + "epoch": 0.42, + "learning_rate": 1.4507424959205505e-05, + "loss": 1.3652, + "step": 3967 + }, + { + "epoch": 0.42, + "learning_rate": 1.4504157320374408e-05, + "loss": 1.4198, + "step": 3968 + }, + { + "epoch": 0.42, + "learning_rate": 1.4500889078101962e-05, + "loss": 1.3476, + "step": 3969 + }, + { + "epoch": 0.42, + "learning_rate": 1.4497620232826028e-05, + "loss": 1.4356, + "step": 3970 + }, + { + "epoch": 0.42, + "learning_rate": 1.4494350784984543e-05, + "loss": 1.4993, + "step": 3971 + }, + { + "epoch": 0.42, + "learning_rate": 1.4491080735015533e-05, + "loss": 1.4022, + "step": 3972 + }, + { + "epoch": 0.42, + "learning_rate": 1.44878100833571e-05, + "loss": 1.4074, + "step": 3973 + }, + { + "epoch": 0.42, + "learning_rate": 1.4484538830447423e-05, + "loss": 1.412, + "step": 3974 + }, + { + "epoch": 0.42, + "learning_rate": 1.4481266976724772e-05, + "loss": 1.3872, + "step": 3975 + }, + { + "epoch": 0.42, + "learning_rate": 1.4477994522627485e-05, + "loss": 1.4575, + "step": 3976 + }, + { + "epoch": 0.42, + "learning_rate": 1.4474721468593995e-05, + "loss": 1.3768, + "step": 3977 + }, + { + "epoch": 0.42, + "learning_rate": 1.44714478150628e-05, + "loss": 1.4173, + "step": 3978 + }, + { + "epoch": 0.42, + "learning_rate": 1.4468173562472489e-05, + "loss": 1.3896, + "step": 3979 + }, + { + "epoch": 0.42, + "learning_rate": 1.4464898711261725e-05, + "loss": 1.4535, + "step": 3980 + }, + { + "epoch": 0.42, + "eval_loss": 1.4580057859420776, + "eval_runtime": 77.4537, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 3980 + }, + { + "epoch": 0.42, + "learning_rate": 1.4461623261869258e-05, + "loss": 1.4046, + "step": 3981 + }, + { + "epoch": 0.42, + "learning_rate": 1.445834721473391e-05, + "loss": 1.37, + "step": 3982 + }, + { + "epoch": 0.42, + "learning_rate": 1.4455070570294588e-05, + "loss": 1.4566, + "step": 3983 + }, + { + "epoch": 0.42, + "learning_rate": 1.445179332899028e-05, + "loss": 1.4513, + "step": 3984 + }, + { + "epoch": 0.42, + "learning_rate": 1.4448515491260051e-05, + "loss": 1.3893, + "step": 3985 + }, + { + "epoch": 0.42, + "learning_rate": 1.4445237057543047e-05, + "loss": 1.3955, + "step": 3986 + }, + { + "epoch": 0.42, + "learning_rate": 1.4441958028278493e-05, + "loss": 1.4861, + "step": 3987 + }, + { + "epoch": 0.42, + "learning_rate": 1.4438678403905697e-05, + "loss": 1.4601, + "step": 3988 + }, + { + "epoch": 0.42, + "learning_rate": 1.4435398184864043e-05, + "loss": 1.398, + "step": 3989 + }, + { + "epoch": 0.42, + "learning_rate": 1.4432117371592995e-05, + "loss": 1.4392, + "step": 3990 + }, + { + "epoch": 0.42, + "learning_rate": 1.4428835964532098e-05, + "loss": 1.3772, + "step": 3991 + }, + { + "epoch": 0.42, + "learning_rate": 1.4425553964120979e-05, + "loss": 1.4241, + "step": 3992 + }, + { + "epoch": 0.42, + "learning_rate": 1.4422271370799338e-05, + "loss": 1.3237, + "step": 3993 + }, + { + "epoch": 0.42, + "learning_rate": 1.4418988185006964e-05, + "loss": 1.3813, + "step": 3994 + }, + { + "epoch": 0.42, + "learning_rate": 1.4415704407183709e-05, + "loss": 1.6139, + "step": 3995 + }, + { + "epoch": 0.42, + "learning_rate": 1.4412420037769525e-05, + "loss": 1.4431, + "step": 3996 + }, + { + "epoch": 0.42, + "learning_rate": 1.440913507720443e-05, + "loss": 1.3862, + "step": 3997 + }, + { + "epoch": 0.42, + "learning_rate": 1.4405849525928523e-05, + "loss": 1.3895, + "step": 3998 + }, + { + "epoch": 0.42, + "learning_rate": 1.4402563384381981e-05, + "loss": 1.4068, + "step": 3999 + }, + { + "epoch": 0.42, + "learning_rate": 1.4399276653005072e-05, + "loss": 1.4501, + "step": 4000 + }, + { + "epoch": 0.42, + "learning_rate": 1.4395989332238124e-05, + "loss": 1.3165, + "step": 4001 + }, + { + "epoch": 0.42, + "learning_rate": 1.4392701422521555e-05, + "loss": 1.3783, + "step": 4002 + }, + { + "epoch": 0.42, + "learning_rate": 1.4389412924295865e-05, + "loss": 1.343, + "step": 4003 + }, + { + "epoch": 0.42, + "learning_rate": 1.4386123838001625e-05, + "loss": 1.3456, + "step": 4004 + }, + { + "epoch": 0.42, + "learning_rate": 1.4382834164079486e-05, + "loss": 1.3689, + "step": 4005 + }, + { + "epoch": 0.42, + "learning_rate": 1.4379543902970183e-05, + "loss": 1.3789, + "step": 4006 + }, + { + "epoch": 0.42, + "learning_rate": 1.4376253055114528e-05, + "loss": 1.4912, + "step": 4007 + }, + { + "epoch": 0.42, + "learning_rate": 1.4372961620953407e-05, + "loss": 1.3692, + "step": 4008 + }, + { + "epoch": 0.42, + "learning_rate": 1.436966960092779e-05, + "loss": 1.4901, + "step": 4009 + }, + { + "epoch": 0.42, + "learning_rate": 1.4366376995478717e-05, + "loss": 1.4431, + "step": 4010 + }, + { + "epoch": 0.42, + "learning_rate": 1.436308380504732e-05, + "loss": 1.4626, + "step": 4011 + }, + { + "epoch": 0.42, + "learning_rate": 1.4359790030074798e-05, + "loss": 1.4241, + "step": 4012 + }, + { + "epoch": 0.42, + "learning_rate": 1.4356495671002435e-05, + "loss": 1.3834, + "step": 4013 + }, + { + "epoch": 0.42, + "learning_rate": 1.4353200728271586e-05, + "loss": 1.3626, + "step": 4014 + }, + { + "epoch": 0.42, + "learning_rate": 1.4349905202323692e-05, + "loss": 1.3557, + "step": 4015 + }, + { + "epoch": 0.42, + "learning_rate": 1.434660909360027e-05, + "loss": 1.4077, + "step": 4016 + }, + { + "epoch": 0.42, + "learning_rate": 1.4343312402542911e-05, + "loss": 1.4337, + "step": 4017 + }, + { + "epoch": 0.42, + "learning_rate": 1.4340015129593286e-05, + "loss": 1.419, + "step": 4018 + }, + { + "epoch": 0.42, + "learning_rate": 1.4336717275193148e-05, + "loss": 1.3768, + "step": 4019 + }, + { + "epoch": 0.42, + "learning_rate": 1.4333418839784326e-05, + "loss": 1.383, + "step": 4020 + }, + { + "epoch": 0.42, + "learning_rate": 1.4330119823808719e-05, + "loss": 1.3951, + "step": 4021 + }, + { + "epoch": 0.42, + "learning_rate": 1.4326820227708316e-05, + "loss": 1.3985, + "step": 4022 + }, + { + "epoch": 0.42, + "learning_rate": 1.4323520051925177e-05, + "loss": 1.356, + "step": 4023 + }, + { + "epoch": 0.42, + "learning_rate": 1.4320219296901439e-05, + "loss": 1.5017, + "step": 4024 + }, + { + "epoch": 0.42, + "learning_rate": 1.4316917963079322e-05, + "loss": 1.3594, + "step": 4025 + }, + { + "epoch": 0.42, + "learning_rate": 1.4313616050901114e-05, + "loss": 1.6028, + "step": 4026 + }, + { + "epoch": 0.42, + "learning_rate": 1.4310313560809193e-05, + "loss": 1.4132, + "step": 4027 + }, + { + "epoch": 0.42, + "learning_rate": 1.4307010493246006e-05, + "loss": 1.2969, + "step": 4028 + }, + { + "epoch": 0.42, + "learning_rate": 1.4303706848654073e-05, + "loss": 1.5224, + "step": 4029 + }, + { + "epoch": 0.42, + "learning_rate": 1.4300402627476007e-05, + "loss": 1.3386, + "step": 4030 + }, + { + "epoch": 0.42, + "learning_rate": 1.429709783015448e-05, + "loss": 1.3554, + "step": 4031 + }, + { + "epoch": 0.42, + "learning_rate": 1.4293792457132259e-05, + "loss": 1.3386, + "step": 4032 + }, + { + "epoch": 0.42, + "learning_rate": 1.429048650885217e-05, + "loss": 1.4613, + "step": 4033 + }, + { + "epoch": 0.42, + "learning_rate": 1.4287179985757132e-05, + "loss": 1.3632, + "step": 4034 + }, + { + "epoch": 0.42, + "learning_rate": 1.428387288829013e-05, + "loss": 1.3835, + "step": 4035 + }, + { + "epoch": 0.42, + "learning_rate": 1.4280565216894234e-05, + "loss": 1.3711, + "step": 4036 + }, + { + "epoch": 0.42, + "learning_rate": 1.4277256972012582e-05, + "loss": 1.3385, + "step": 4037 + }, + { + "epoch": 0.42, + "learning_rate": 1.4273948154088395e-05, + "loss": 1.4607, + "step": 4038 + }, + { + "epoch": 0.42, + "learning_rate": 1.4270638763564973e-05, + "loss": 1.4042, + "step": 4039 + }, + { + "epoch": 0.42, + "learning_rate": 1.4267328800885687e-05, + "loss": 1.4006, + "step": 4040 + }, + { + "epoch": 0.42, + "learning_rate": 1.4264018266493987e-05, + "loss": 1.386, + "step": 4041 + }, + { + "epoch": 0.42, + "learning_rate": 1.4260707160833401e-05, + "loss": 1.3487, + "step": 4042 + }, + { + "epoch": 0.42, + "learning_rate": 1.4257395484347529e-05, + "loss": 1.4199, + "step": 4043 + }, + { + "epoch": 0.42, + "learning_rate": 1.4254083237480054e-05, + "loss": 1.3236, + "step": 4044 + }, + { + "epoch": 0.42, + "learning_rate": 1.4250770420674726e-05, + "loss": 1.4056, + "step": 4045 + }, + { + "epoch": 0.42, + "learning_rate": 1.4247457034375387e-05, + "loss": 1.4391, + "step": 4046 + }, + { + "epoch": 0.42, + "learning_rate": 1.4244143079025938e-05, + "loss": 1.3935, + "step": 4047 + }, + { + "epoch": 0.42, + "learning_rate": 1.4240828555070368e-05, + "loss": 1.3623, + "step": 4048 + }, + { + "epoch": 0.42, + "learning_rate": 1.4237513462952733e-05, + "loss": 1.3254, + "step": 4049 + }, + { + "epoch": 0.42, + "learning_rate": 1.4234197803117174e-05, + "loss": 1.4217, + "step": 4050 + }, + { + "epoch": 0.42, + "learning_rate": 1.4230881576007904e-05, + "loss": 1.435, + "step": 4051 + }, + { + "epoch": 0.42, + "learning_rate": 1.422756478206921e-05, + "loss": 1.3687, + "step": 4052 + }, + { + "epoch": 0.43, + "learning_rate": 1.4224247421745464e-05, + "loss": 1.3965, + "step": 4053 + }, + { + "epoch": 0.43, + "learning_rate": 1.4220929495481097e-05, + "loss": 1.4159, + "step": 4054 + }, + { + "epoch": 0.43, + "learning_rate": 1.4217611003720632e-05, + "loss": 1.3632, + "step": 4055 + }, + { + "epoch": 0.43, + "learning_rate": 1.4214291946908661e-05, + "loss": 1.403, + "step": 4056 + }, + { + "epoch": 0.43, + "learning_rate": 1.4210972325489854e-05, + "loss": 1.4093, + "step": 4057 + }, + { + "epoch": 0.43, + "learning_rate": 1.4207652139908952e-05, + "loss": 1.4551, + "step": 4058 + }, + { + "epoch": 0.43, + "learning_rate": 1.4204331390610775e-05, + "loss": 1.4162, + "step": 4059 + }, + { + "epoch": 0.43, + "learning_rate": 1.4201010078040216e-05, + "loss": 1.4492, + "step": 4060 + }, + { + "epoch": 0.43, + "learning_rate": 1.419768820264225e-05, + "loss": 1.4449, + "step": 4061 + }, + { + "epoch": 0.43, + "learning_rate": 1.4194365764861922e-05, + "loss": 1.3382, + "step": 4062 + }, + { + "epoch": 0.43, + "learning_rate": 1.419104276514435e-05, + "loss": 1.3899, + "step": 4063 + }, + { + "epoch": 0.43, + "learning_rate": 1.4187719203934734e-05, + "loss": 1.3513, + "step": 4064 + }, + { + "epoch": 0.43, + "learning_rate": 1.4184395081678344e-05, + "loss": 1.3954, + "step": 4065 + }, + { + "epoch": 0.43, + "learning_rate": 1.4181070398820528e-05, + "loss": 1.442, + "step": 4066 + }, + { + "epoch": 0.43, + "learning_rate": 1.4177745155806708e-05, + "loss": 1.3907, + "step": 4067 + }, + { + "epoch": 0.43, + "learning_rate": 1.417441935308238e-05, + "loss": 1.3757, + "step": 4068 + }, + { + "epoch": 0.43, + "learning_rate": 1.4171092991093118e-05, + "loss": 1.3507, + "step": 4069 + }, + { + "epoch": 0.43, + "learning_rate": 1.4167766070284568e-05, + "loss": 1.4136, + "step": 4070 + }, + { + "epoch": 0.43, + "learning_rate": 1.4164438591102452e-05, + "loss": 1.3835, + "step": 4071 + }, + { + "epoch": 0.43, + "learning_rate": 1.4161110553992565e-05, + "loss": 1.4981, + "step": 4072 + }, + { + "epoch": 0.43, + "learning_rate": 1.415778195940078e-05, + "loss": 1.4387, + "step": 4073 + }, + { + "epoch": 0.43, + "learning_rate": 1.4154452807773047e-05, + "loss": 1.333, + "step": 4074 + }, + { + "epoch": 0.43, + "learning_rate": 1.4151123099555377e-05, + "loss": 1.3558, + "step": 4075 + }, + { + "epoch": 0.43, + "learning_rate": 1.4147792835193875e-05, + "loss": 1.4655, + "step": 4076 + }, + { + "epoch": 0.43, + "learning_rate": 1.4144462015134708e-05, + "loss": 1.4402, + "step": 4077 + }, + { + "epoch": 0.43, + "learning_rate": 1.4141130639824119e-05, + "loss": 1.4227, + "step": 4078 + }, + { + "epoch": 0.43, + "learning_rate": 1.4137798709708423e-05, + "loss": 1.4039, + "step": 4079 + }, + { + "epoch": 0.43, + "learning_rate": 1.4134466225234023e-05, + "loss": 1.3593, + "step": 4080 + }, + { + "epoch": 0.43, + "learning_rate": 1.4131133186847377e-05, + "loss": 1.372, + "step": 4081 + }, + { + "epoch": 0.43, + "learning_rate": 1.412779959499503e-05, + "loss": 1.4487, + "step": 4082 + }, + { + "epoch": 0.43, + "learning_rate": 1.4124465450123599e-05, + "loss": 1.3972, + "step": 4083 + }, + { + "epoch": 0.43, + "learning_rate": 1.4121130752679772e-05, + "loss": 1.3768, + "step": 4084 + }, + { + "epoch": 0.43, + "learning_rate": 1.4117795503110313e-05, + "loss": 1.3827, + "step": 4085 + }, + { + "epoch": 0.43, + "learning_rate": 1.4114459701862062e-05, + "loss": 1.3922, + "step": 4086 + }, + { + "epoch": 0.43, + "learning_rate": 1.4111123349381925e-05, + "loss": 1.3736, + "step": 4087 + }, + { + "epoch": 0.43, + "learning_rate": 1.4107786446116894e-05, + "loss": 1.4338, + "step": 4088 + }, + { + "epoch": 0.43, + "learning_rate": 1.4104448992514023e-05, + "loss": 1.347, + "step": 4089 + }, + { + "epoch": 0.43, + "learning_rate": 1.410111098902045e-05, + "loss": 1.3915, + "step": 4090 + }, + { + "epoch": 0.43, + "learning_rate": 1.4097772436083377e-05, + "loss": 1.3656, + "step": 4091 + }, + { + "epoch": 0.43, + "learning_rate": 1.4094433334150087e-05, + "loss": 1.3461, + "step": 4092 + }, + { + "epoch": 0.43, + "learning_rate": 1.4091093683667934e-05, + "loss": 1.7345, + "step": 4093 + }, + { + "epoch": 0.43, + "learning_rate": 1.4087753485084343e-05, + "loss": 1.6204, + "step": 4094 + }, + { + "epoch": 0.43, + "learning_rate": 1.4084412738846816e-05, + "loss": 1.4074, + "step": 4095 + }, + { + "epoch": 0.43, + "learning_rate": 1.408107144540293e-05, + "loss": 1.3776, + "step": 4096 + }, + { + "epoch": 0.43, + "learning_rate": 1.407772960520033e-05, + "loss": 1.4079, + "step": 4097 + }, + { + "epoch": 0.43, + "learning_rate": 1.4074387218686734e-05, + "loss": 1.4254, + "step": 4098 + }, + { + "epoch": 0.43, + "learning_rate": 1.407104428630994e-05, + "loss": 1.38, + "step": 4099 + }, + { + "epoch": 0.43, + "learning_rate": 1.4067700808517815e-05, + "loss": 1.4175, + "step": 4100 + }, + { + "epoch": 0.43, + "learning_rate": 1.4064356785758298e-05, + "loss": 1.4085, + "step": 4101 + }, + { + "epoch": 0.43, + "learning_rate": 1.4061012218479397e-05, + "loss": 1.4529, + "step": 4102 + }, + { + "epoch": 0.43, + "learning_rate": 1.405766710712921e-05, + "loss": 1.4836, + "step": 4103 + }, + { + "epoch": 0.43, + "learning_rate": 1.4054321452155885e-05, + "loss": 1.3915, + "step": 4104 + }, + { + "epoch": 0.43, + "learning_rate": 1.4050975254007659e-05, + "loss": 1.3044, + "step": 4105 + }, + { + "epoch": 0.43, + "learning_rate": 1.4047628513132835e-05, + "loss": 1.373, + "step": 4106 + }, + { + "epoch": 0.43, + "learning_rate": 1.4044281229979793e-05, + "loss": 1.4266, + "step": 4107 + }, + { + "epoch": 0.43, + "learning_rate": 1.4040933404996977e-05, + "loss": 1.3898, + "step": 4108 + }, + { + "epoch": 0.43, + "learning_rate": 1.4037585038632915e-05, + "loss": 0.9326, + "step": 4109 + }, + { + "epoch": 0.43, + "learning_rate": 1.40342361313362e-05, + "loss": 1.0831, + "step": 4110 + }, + { + "epoch": 0.43, + "learning_rate": 1.40308866835555e-05, + "loss": 1.3898, + "step": 4111 + }, + { + "epoch": 0.43, + "learning_rate": 1.4027536695739554e-05, + "loss": 1.5058, + "step": 4112 + }, + { + "epoch": 0.43, + "learning_rate": 1.4024186168337175e-05, + "loss": 1.3635, + "step": 4113 + }, + { + "epoch": 0.43, + "learning_rate": 1.4020835101797248e-05, + "loss": 1.3871, + "step": 4114 + }, + { + "epoch": 0.43, + "learning_rate": 1.401748349656873e-05, + "loss": 1.3478, + "step": 4115 + }, + { + "epoch": 0.43, + "learning_rate": 1.4014131353100648e-05, + "loss": 1.3356, + "step": 4116 + }, + { + "epoch": 0.43, + "learning_rate": 1.4010778671842107e-05, + "loss": 1.3954, + "step": 4117 + }, + { + "epoch": 0.43, + "learning_rate": 1.4007425453242274e-05, + "loss": 1.3307, + "step": 4118 + }, + { + "epoch": 0.43, + "learning_rate": 1.4004071697750398e-05, + "loss": 1.4508, + "step": 4119 + }, + { + "epoch": 0.43, + "learning_rate": 1.4000717405815799e-05, + "loss": 1.3752, + "step": 4120 + }, + { + "epoch": 0.43, + "learning_rate": 1.399736257788786e-05, + "loss": 1.3654, + "step": 4121 + }, + { + "epoch": 0.43, + "learning_rate": 1.3994007214416046e-05, + "loss": 1.4505, + "step": 4122 + }, + { + "epoch": 0.43, + "learning_rate": 1.3990651315849886e-05, + "loss": 1.4307, + "step": 4123 + }, + { + "epoch": 0.43, + "learning_rate": 1.398729488263899e-05, + "loss": 1.4481, + "step": 4124 + }, + { + "epoch": 0.43, + "learning_rate": 1.3983937915233026e-05, + "loss": 1.4755, + "step": 4125 + }, + { + "epoch": 0.43, + "learning_rate": 1.3980580414081746e-05, + "loss": 1.3402, + "step": 4126 + }, + { + "epoch": 0.43, + "learning_rate": 1.3977222379634969e-05, + "loss": 1.3636, + "step": 4127 + }, + { + "epoch": 0.43, + "learning_rate": 1.3973863812342585e-05, + "loss": 1.4165, + "step": 4128 + }, + { + "epoch": 0.43, + "learning_rate": 1.3970504712654554e-05, + "loss": 1.3832, + "step": 4129 + }, + { + "epoch": 0.43, + "learning_rate": 1.3967145081020912e-05, + "loss": 1.4236, + "step": 4130 + }, + { + "epoch": 0.43, + "learning_rate": 1.396378491789176e-05, + "loss": 1.5022, + "step": 4131 + }, + { + "epoch": 0.43, + "learning_rate": 1.3960424223717276e-05, + "loss": 1.3806, + "step": 4132 + }, + { + "epoch": 0.43, + "learning_rate": 1.3957062998947707e-05, + "loss": 1.3649, + "step": 4133 + }, + { + "epoch": 0.43, + "learning_rate": 1.3953701244033368e-05, + "loss": 1.3787, + "step": 4134 + }, + { + "epoch": 0.43, + "learning_rate": 1.395033895942465e-05, + "loss": 1.3551, + "step": 4135 + }, + { + "epoch": 0.43, + "learning_rate": 1.394697614557201e-05, + "loss": 1.3881, + "step": 4136 + }, + { + "epoch": 0.43, + "learning_rate": 1.3943612802925983e-05, + "loss": 1.4848, + "step": 4137 + }, + { + "epoch": 0.43, + "learning_rate": 1.3940248931937169e-05, + "loss": 1.425, + "step": 4138 + }, + { + "epoch": 0.43, + "learning_rate": 1.3936884533056238e-05, + "loss": 1.4054, + "step": 4139 + }, + { + "epoch": 0.43, + "learning_rate": 1.3933519606733934e-05, + "loss": 1.4028, + "step": 4140 + }, + { + "epoch": 0.43, + "learning_rate": 1.3930154153421072e-05, + "loss": 1.4439, + "step": 4141 + }, + { + "epoch": 0.43, + "learning_rate": 1.3926788173568536e-05, + "loss": 1.4482, + "step": 4142 + }, + { + "epoch": 0.43, + "learning_rate": 1.392342166762728e-05, + "loss": 1.393, + "step": 4143 + }, + { + "epoch": 0.43, + "learning_rate": 1.3920054636048328e-05, + "loss": 1.4097, + "step": 4144 + }, + { + "epoch": 0.43, + "learning_rate": 1.391668707928278e-05, + "loss": 1.5142, + "step": 4145 + }, + { + "epoch": 0.43, + "learning_rate": 1.3913318997781797e-05, + "loss": 1.4118, + "step": 4146 + }, + { + "epoch": 0.43, + "learning_rate": 1.390995039199662e-05, + "loss": 1.4067, + "step": 4147 + }, + { + "epoch": 0.43, + "learning_rate": 1.3906581262378552e-05, + "loss": 1.5214, + "step": 4148 + }, + { + "epoch": 0.44, + "learning_rate": 1.3903211609378971e-05, + "loss": 1.3618, + "step": 4149 + }, + { + "epoch": 0.44, + "learning_rate": 1.3899841433449327e-05, + "loss": 1.338, + "step": 4150 + }, + { + "epoch": 0.44, + "learning_rate": 1.3896470735041132e-05, + "loss": 1.3901, + "step": 4151 + }, + { + "epoch": 0.44, + "learning_rate": 1.3893099514605971e-05, + "loss": 1.4502, + "step": 4152 + }, + { + "epoch": 0.44, + "learning_rate": 1.388972777259551e-05, + "loss": 1.4141, + "step": 4153 + }, + { + "epoch": 0.44, + "learning_rate": 1.3886355509461471e-05, + "loss": 1.3876, + "step": 4154 + }, + { + "epoch": 0.44, + "learning_rate": 1.388298272565565e-05, + "loss": 1.4275, + "step": 4155 + }, + { + "epoch": 0.44, + "learning_rate": 1.3879609421629909e-05, + "loss": 1.3559, + "step": 4156 + }, + { + "epoch": 0.44, + "learning_rate": 1.3876235597836195e-05, + "loss": 1.416, + "step": 4157 + }, + { + "epoch": 0.44, + "learning_rate": 1.3872861254726506e-05, + "loss": 1.437, + "step": 4158 + }, + { + "epoch": 0.44, + "learning_rate": 1.3869486392752918e-05, + "loss": 1.3794, + "step": 4159 + }, + { + "epoch": 0.44, + "learning_rate": 1.3866111012367577e-05, + "loss": 1.4094, + "step": 4160 + }, + { + "epoch": 0.44, + "learning_rate": 1.3862735114022694e-05, + "loss": 1.3957, + "step": 4161 + }, + { + "epoch": 0.44, + "learning_rate": 1.3859358698170559e-05, + "loss": 1.3582, + "step": 4162 + }, + { + "epoch": 0.44, + "learning_rate": 1.3855981765263523e-05, + "loss": 1.4159, + "step": 4163 + }, + { + "epoch": 0.44, + "learning_rate": 1.3852604315754e-05, + "loss": 1.3498, + "step": 4164 + }, + { + "epoch": 0.44, + "learning_rate": 1.3849226350094491e-05, + "loss": 1.3951, + "step": 4165 + }, + { + "epoch": 0.44, + "learning_rate": 1.3845847868737559e-05, + "loss": 1.4087, + "step": 4166 + }, + { + "epoch": 0.44, + "learning_rate": 1.3842468872135821e-05, + "loss": 1.4318, + "step": 4167 + }, + { + "epoch": 0.44, + "learning_rate": 1.3839089360741989e-05, + "loss": 1.4174, + "step": 4168 + }, + { + "epoch": 0.44, + "learning_rate": 1.3835709335008822e-05, + "loss": 1.4499, + "step": 4169 + }, + { + "epoch": 0.44, + "learning_rate": 1.383232879538916e-05, + "loss": 1.3554, + "step": 4170 + }, + { + "epoch": 0.44, + "learning_rate": 1.3828947742335905e-05, + "loss": 1.3873, + "step": 4171 + }, + { + "epoch": 0.44, + "learning_rate": 1.382556617630204e-05, + "loss": 1.3804, + "step": 4172 + }, + { + "epoch": 0.44, + "learning_rate": 1.3822184097740598e-05, + "loss": 1.3856, + "step": 4173 + }, + { + "epoch": 0.44, + "learning_rate": 1.3818801507104697e-05, + "loss": 1.3901, + "step": 4174 + }, + { + "epoch": 0.44, + "learning_rate": 1.381541840484751e-05, + "loss": 1.3714, + "step": 4175 + }, + { + "epoch": 0.44, + "learning_rate": 1.3812034791422297e-05, + "loss": 1.4945, + "step": 4176 + }, + { + "epoch": 0.44, + "learning_rate": 1.3808650667282368e-05, + "loss": 1.429, + "step": 4177 + }, + { + "epoch": 0.44, + "learning_rate": 1.3805266032881108e-05, + "loss": 1.3903, + "step": 4178 + }, + { + "epoch": 0.44, + "learning_rate": 1.3801880888671972e-05, + "loss": 1.4799, + "step": 4179 + }, + { + "epoch": 0.44, + "eval_loss": 1.4521424770355225, + "eval_runtime": 77.3596, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 4179 + }, + { + "epoch": 0.44, + "learning_rate": 1.3798495235108484e-05, + "loss": 1.3912, + "step": 4180 + }, + { + "epoch": 0.44, + "learning_rate": 1.3795109072644235e-05, + "loss": 1.5837, + "step": 4181 + }, + { + "epoch": 0.44, + "learning_rate": 1.379172240173288e-05, + "loss": 1.4255, + "step": 4182 + }, + { + "epoch": 0.44, + "learning_rate": 1.3788335222828148e-05, + "loss": 1.4666, + "step": 4183 + }, + { + "epoch": 0.44, + "learning_rate": 1.3784947536383837e-05, + "loss": 1.3964, + "step": 4184 + }, + { + "epoch": 0.44, + "learning_rate": 1.3781559342853807e-05, + "loss": 1.336, + "step": 4185 + }, + { + "epoch": 0.44, + "learning_rate": 1.3778170642691986e-05, + "loss": 1.4352, + "step": 4186 + }, + { + "epoch": 0.44, + "learning_rate": 1.377478143635238e-05, + "loss": 1.3262, + "step": 4187 + }, + { + "epoch": 0.44, + "learning_rate": 1.3771391724289047e-05, + "loss": 1.3969, + "step": 4188 + }, + { + "epoch": 0.44, + "learning_rate": 1.376800150695613e-05, + "loss": 1.4211, + "step": 4189 + }, + { + "epoch": 0.44, + "learning_rate": 1.3764610784807824e-05, + "loss": 1.4338, + "step": 4190 + }, + { + "epoch": 0.44, + "learning_rate": 1.3761219558298403e-05, + "loss": 1.3815, + "step": 4191 + }, + { + "epoch": 0.44, + "learning_rate": 1.3757827827882203e-05, + "loss": 1.3805, + "step": 4192 + }, + { + "epoch": 0.44, + "learning_rate": 1.3754435594013627e-05, + "loss": 1.4071, + "step": 4193 + }, + { + "epoch": 0.44, + "learning_rate": 1.3751042857147145e-05, + "loss": 1.343, + "step": 4194 + }, + { + "epoch": 0.44, + "learning_rate": 1.3747649617737304e-05, + "loss": 1.4129, + "step": 4195 + }, + { + "epoch": 0.44, + "learning_rate": 1.3744255876238708e-05, + "loss": 1.3939, + "step": 4196 + }, + { + "epoch": 0.44, + "learning_rate": 1.3740861633106029e-05, + "loss": 1.3963, + "step": 4197 + }, + { + "epoch": 0.44, + "learning_rate": 1.3737466888794008e-05, + "loss": 1.5181, + "step": 4198 + }, + { + "epoch": 0.44, + "learning_rate": 1.3734071643757456e-05, + "loss": 1.4397, + "step": 4199 + }, + { + "epoch": 0.44, + "learning_rate": 1.373067589845125e-05, + "loss": 1.6293, + "step": 4200 + }, + { + "epoch": 0.44, + "learning_rate": 1.3727279653330328e-05, + "loss": 1.3498, + "step": 4201 + }, + { + "epoch": 0.44, + "learning_rate": 1.37238829088497e-05, + "loss": 1.4509, + "step": 4202 + }, + { + "epoch": 0.44, + "learning_rate": 1.3720485665464446e-05, + "loss": 1.4477, + "step": 4203 + }, + { + "epoch": 0.44, + "learning_rate": 1.3717087923629709e-05, + "loss": 1.4399, + "step": 4204 + }, + { + "epoch": 0.44, + "learning_rate": 1.3713689683800695e-05, + "loss": 1.4417, + "step": 4205 + }, + { + "epoch": 0.44, + "learning_rate": 1.3710290946432685e-05, + "loss": 1.3957, + "step": 4206 + }, + { + "epoch": 0.44, + "learning_rate": 1.3706891711981021e-05, + "loss": 1.4476, + "step": 4207 + }, + { + "epoch": 0.44, + "learning_rate": 1.3703491980901113e-05, + "loss": 1.3894, + "step": 4208 + }, + { + "epoch": 0.44, + "learning_rate": 1.3700091753648437e-05, + "loss": 1.4745, + "step": 4209 + }, + { + "epoch": 0.44, + "learning_rate": 1.369669103067854e-05, + "loss": 1.4038, + "step": 4210 + }, + { + "epoch": 0.44, + "learning_rate": 1.3693289812447023e-05, + "loss": 1.4151, + "step": 4211 + }, + { + "epoch": 0.44, + "learning_rate": 1.3689888099409572e-05, + "loss": 1.4214, + "step": 4212 + }, + { + "epoch": 0.44, + "learning_rate": 1.368648589202192e-05, + "loss": 1.4287, + "step": 4213 + }, + { + "epoch": 0.44, + "learning_rate": 1.3683083190739883e-05, + "loss": 1.345, + "step": 4214 + }, + { + "epoch": 0.44, + "learning_rate": 1.367967999601933e-05, + "loss": 1.3022, + "step": 4215 + }, + { + "epoch": 0.44, + "learning_rate": 1.3676276308316207e-05, + "loss": 1.3971, + "step": 4216 + }, + { + "epoch": 0.44, + "learning_rate": 1.3672872128086514e-05, + "loss": 1.3335, + "step": 4217 + }, + { + "epoch": 0.44, + "learning_rate": 1.366946745578633e-05, + "loss": 1.3988, + "step": 4218 + }, + { + "epoch": 0.44, + "learning_rate": 1.366606229187179e-05, + "loss": 1.4508, + "step": 4219 + }, + { + "epoch": 0.44, + "learning_rate": 1.3662656636799099e-05, + "loss": 1.3814, + "step": 4220 + }, + { + "epoch": 0.44, + "learning_rate": 1.3659250491024527e-05, + "loss": 1.4128, + "step": 4221 + }, + { + "epoch": 0.44, + "learning_rate": 1.3655843855004411e-05, + "loss": 1.3893, + "step": 4222 + }, + { + "epoch": 0.44, + "learning_rate": 1.3652436729195154e-05, + "loss": 1.2551, + "step": 4223 + }, + { + "epoch": 0.44, + "learning_rate": 1.3649029114053219e-05, + "loss": 1.4386, + "step": 4224 + }, + { + "epoch": 0.44, + "learning_rate": 1.364562101003514e-05, + "loss": 1.4028, + "step": 4225 + }, + { + "epoch": 0.44, + "learning_rate": 1.364221241759752e-05, + "loss": 1.4351, + "step": 4226 + }, + { + "epoch": 0.44, + "learning_rate": 1.363880333719702e-05, + "loss": 1.3941, + "step": 4227 + }, + { + "epoch": 0.44, + "learning_rate": 1.3635393769290368e-05, + "loss": 1.3879, + "step": 4228 + }, + { + "epoch": 0.44, + "learning_rate": 1.3631983714334358e-05, + "loss": 1.3773, + "step": 4229 + }, + { + "epoch": 0.44, + "learning_rate": 1.3628573172785853e-05, + "loss": 1.3679, + "step": 4230 + }, + { + "epoch": 0.44, + "learning_rate": 1.3625162145101776e-05, + "loss": 1.3705, + "step": 4231 + }, + { + "epoch": 0.44, + "learning_rate": 1.3621750631739114e-05, + "loss": 1.8157, + "step": 4232 + }, + { + "epoch": 0.44, + "learning_rate": 1.3618338633154928e-05, + "loss": 1.4056, + "step": 4233 + }, + { + "epoch": 0.44, + "learning_rate": 1.3614926149806334e-05, + "loss": 1.3716, + "step": 4234 + }, + { + "epoch": 0.44, + "learning_rate": 1.3611513182150523e-05, + "loss": 1.3766, + "step": 4235 + }, + { + "epoch": 0.44, + "learning_rate": 1.3608099730644733e-05, + "loss": 1.41, + "step": 4236 + }, + { + "epoch": 0.44, + "learning_rate": 1.3604685795746291e-05, + "loss": 1.421, + "step": 4237 + }, + { + "epoch": 0.44, + "learning_rate": 1.360127137791257e-05, + "loss": 1.3679, + "step": 4238 + }, + { + "epoch": 0.44, + "learning_rate": 1.3597856477601018e-05, + "loss": 1.4615, + "step": 4239 + }, + { + "epoch": 0.44, + "learning_rate": 1.359444109526914e-05, + "loss": 1.3418, + "step": 4240 + }, + { + "epoch": 0.44, + "learning_rate": 1.3591025231374513e-05, + "loss": 1.3631, + "step": 4241 + }, + { + "epoch": 0.44, + "learning_rate": 1.3587608886374772e-05, + "loss": 1.3802, + "step": 4242 + }, + { + "epoch": 0.44, + "learning_rate": 1.3584192060727622e-05, + "loss": 1.4156, + "step": 4243 + }, + { + "epoch": 0.45, + "learning_rate": 1.3580774754890827e-05, + "loss": 1.4161, + "step": 4244 + }, + { + "epoch": 0.45, + "learning_rate": 1.3577356969322222e-05, + "loss": 1.3535, + "step": 4245 + }, + { + "epoch": 0.45, + "learning_rate": 1.3573938704479699e-05, + "loss": 1.3859, + "step": 4246 + }, + { + "epoch": 0.45, + "learning_rate": 1.357051996082122e-05, + "loss": 1.3595, + "step": 4247 + }, + { + "epoch": 0.45, + "learning_rate": 1.3567100738804806e-05, + "loss": 1.4191, + "step": 4248 + }, + { + "epoch": 0.45, + "learning_rate": 1.3563681038888548e-05, + "loss": 1.4186, + "step": 4249 + }, + { + "epoch": 0.45, + "learning_rate": 1.3560260861530596e-05, + "loss": 1.43, + "step": 4250 + }, + { + "epoch": 0.45, + "learning_rate": 1.3556840207189168e-05, + "loss": 1.4139, + "step": 4251 + }, + { + "epoch": 0.45, + "learning_rate": 1.3553419076322539e-05, + "loss": 1.4005, + "step": 4252 + }, + { + "epoch": 0.45, + "learning_rate": 1.3549997469389058e-05, + "loss": 1.3468, + "step": 4253 + }, + { + "epoch": 0.45, + "learning_rate": 1.3546575386847132e-05, + "loss": 1.3756, + "step": 4254 + }, + { + "epoch": 0.45, + "learning_rate": 1.3543152829155226e-05, + "loss": 1.4063, + "step": 4255 + }, + { + "epoch": 0.45, + "learning_rate": 1.3539729796771884e-05, + "loss": 1.4666, + "step": 4256 + }, + { + "epoch": 0.45, + "learning_rate": 1.3536306290155694e-05, + "loss": 1.4212, + "step": 4257 + }, + { + "epoch": 0.45, + "learning_rate": 1.3532882309765332e-05, + "loss": 1.4883, + "step": 4258 + }, + { + "epoch": 0.45, + "learning_rate": 1.3529457856059507e-05, + "loss": 1.6641, + "step": 4259 + }, + { + "epoch": 0.45, + "learning_rate": 1.3526032929497022e-05, + "loss": 1.3659, + "step": 4260 + }, + { + "epoch": 0.45, + "learning_rate": 1.3522607530536717e-05, + "loss": 1.5945, + "step": 4261 + }, + { + "epoch": 0.45, + "learning_rate": 1.351918165963752e-05, + "loss": 1.3643, + "step": 4262 + }, + { + "epoch": 0.45, + "learning_rate": 1.3515755317258397e-05, + "loss": 1.3442, + "step": 4263 + }, + { + "epoch": 0.45, + "learning_rate": 1.3512328503858398e-05, + "loss": 1.3982, + "step": 4264 + }, + { + "epoch": 0.45, + "learning_rate": 1.3508901219896624e-05, + "loss": 1.4985, + "step": 4265 + }, + { + "epoch": 0.45, + "learning_rate": 1.350547346583225e-05, + "loss": 1.3319, + "step": 4266 + }, + { + "epoch": 0.45, + "learning_rate": 1.3502045242124497e-05, + "loss": 1.3961, + "step": 4267 + }, + { + "epoch": 0.45, + "learning_rate": 1.3498616549232665e-05, + "loss": 1.4565, + "step": 4268 + }, + { + "epoch": 0.45, + "learning_rate": 1.349518738761611e-05, + "loss": 1.375, + "step": 4269 + }, + { + "epoch": 0.45, + "learning_rate": 1.3491757757734254e-05, + "loss": 1.3005, + "step": 4270 + }, + { + "epoch": 0.45, + "learning_rate": 1.348832766004657e-05, + "loss": 1.3185, + "step": 4271 + }, + { + "epoch": 0.45, + "learning_rate": 1.3484897095012613e-05, + "loss": 1.4449, + "step": 4272 + }, + { + "epoch": 0.45, + "learning_rate": 1.3481466063091988e-05, + "loss": 1.3587, + "step": 4273 + }, + { + "epoch": 0.45, + "learning_rate": 1.3478034564744362e-05, + "loss": 1.3844, + "step": 4274 + }, + { + "epoch": 0.45, + "learning_rate": 1.3474602600429468e-05, + "loss": 1.4471, + "step": 4275 + }, + { + "epoch": 0.45, + "learning_rate": 1.3471170170607105e-05, + "loss": 1.4686, + "step": 4276 + }, + { + "epoch": 0.45, + "learning_rate": 1.3467737275737127e-05, + "loss": 1.312, + "step": 4277 + }, + { + "epoch": 0.45, + "learning_rate": 1.3464303916279453e-05, + "loss": 1.407, + "step": 4278 + }, + { + "epoch": 0.45, + "learning_rate": 1.346087009269407e-05, + "loss": 1.364, + "step": 4279 + }, + { + "epoch": 0.45, + "learning_rate": 1.3457435805441016e-05, + "loss": 1.4103, + "step": 4280 + }, + { + "epoch": 0.45, + "learning_rate": 1.3454001054980403e-05, + "loss": 1.4243, + "step": 4281 + }, + { + "epoch": 0.45, + "learning_rate": 1.3450565841772392e-05, + "loss": 1.3879, + "step": 4282 + }, + { + "epoch": 0.45, + "learning_rate": 1.344713016627722e-05, + "loss": 1.4688, + "step": 4283 + }, + { + "epoch": 0.45, + "learning_rate": 1.3443694028955176e-05, + "loss": 1.3983, + "step": 4284 + }, + { + "epoch": 0.45, + "learning_rate": 1.344025743026662e-05, + "loss": 1.4316, + "step": 4285 + }, + { + "epoch": 0.45, + "learning_rate": 1.3436820370671956e-05, + "loss": 1.3643, + "step": 4286 + }, + { + "epoch": 0.45, + "learning_rate": 1.3433382850631673e-05, + "loss": 1.4566, + "step": 4287 + }, + { + "epoch": 0.45, + "learning_rate": 1.3429944870606301e-05, + "loss": 1.1263, + "step": 4288 + }, + { + "epoch": 0.45, + "learning_rate": 1.3426506431056452e-05, + "loss": 1.2463, + "step": 4289 + }, + { + "epoch": 0.45, + "learning_rate": 1.342306753244278e-05, + "loss": 1.4753, + "step": 4290 + }, + { + "epoch": 0.45, + "learning_rate": 1.3419628175226012e-05, + "loss": 1.3789, + "step": 4291 + }, + { + "epoch": 0.45, + "learning_rate": 1.3416188359866932e-05, + "loss": 1.3906, + "step": 4292 + }, + { + "epoch": 0.45, + "learning_rate": 1.3412748086826389e-05, + "loss": 1.3995, + "step": 4293 + }, + { + "epoch": 0.45, + "learning_rate": 1.3409307356565288e-05, + "loss": 1.4906, + "step": 4294 + }, + { + "epoch": 0.45, + "learning_rate": 1.3405866169544602e-05, + "loss": 1.3951, + "step": 4295 + }, + { + "epoch": 0.45, + "learning_rate": 1.3402424526225359e-05, + "loss": 1.3753, + "step": 4296 + }, + { + "epoch": 0.45, + "learning_rate": 1.3398982427068654e-05, + "loss": 1.3686, + "step": 4297 + }, + { + "epoch": 0.45, + "learning_rate": 1.3395539872535636e-05, + "loss": 1.3612, + "step": 4298 + }, + { + "epoch": 0.45, + "learning_rate": 1.3392096863087522e-05, + "loss": 1.4043, + "step": 4299 + }, + { + "epoch": 0.45, + "learning_rate": 1.3388653399185585e-05, + "loss": 1.4068, + "step": 4300 + }, + { + "epoch": 0.45, + "learning_rate": 1.338520948129116e-05, + "loss": 1.4066, + "step": 4301 + }, + { + "epoch": 0.45, + "learning_rate": 1.3381765109865646e-05, + "loss": 1.4944, + "step": 4302 + }, + { + "epoch": 0.45, + "learning_rate": 1.3378320285370496e-05, + "loss": 1.3575, + "step": 4303 + }, + { + "epoch": 0.45, + "learning_rate": 1.3374875008267236e-05, + "loss": 1.3807, + "step": 4304 + }, + { + "epoch": 0.45, + "learning_rate": 1.3371429279017437e-05, + "loss": 1.4389, + "step": 4305 + }, + { + "epoch": 0.45, + "learning_rate": 1.3367983098082739e-05, + "loss": 1.4858, + "step": 4306 + }, + { + "epoch": 0.45, + "learning_rate": 1.3364536465924844e-05, + "loss": 1.3282, + "step": 4307 + }, + { + "epoch": 0.45, + "learning_rate": 1.3361089383005515e-05, + "loss": 1.4306, + "step": 4308 + }, + { + "epoch": 0.45, + "learning_rate": 1.3357641849786566e-05, + "loss": 1.3892, + "step": 4309 + }, + { + "epoch": 0.45, + "learning_rate": 1.3354193866729883e-05, + "loss": 1.3621, + "step": 4310 + }, + { + "epoch": 0.45, + "learning_rate": 1.3350745434297401e-05, + "loss": 1.3476, + "step": 4311 + }, + { + "epoch": 0.45, + "learning_rate": 1.334729655295113e-05, + "loss": 1.4477, + "step": 4312 + }, + { + "epoch": 0.45, + "learning_rate": 1.3343847223153123e-05, + "loss": 1.3585, + "step": 4313 + }, + { + "epoch": 0.45, + "learning_rate": 1.334039744536551e-05, + "loss": 1.3616, + "step": 4314 + }, + { + "epoch": 0.45, + "learning_rate": 1.3336947220050462e-05, + "loss": 1.3579, + "step": 4315 + }, + { + "epoch": 0.45, + "learning_rate": 1.3333496547670232e-05, + "loss": 1.3557, + "step": 4316 + }, + { + "epoch": 0.45, + "learning_rate": 1.3330045428687113e-05, + "loss": 1.4443, + "step": 4317 + }, + { + "epoch": 0.45, + "learning_rate": 1.332659386356347e-05, + "loss": 1.3621, + "step": 4318 + }, + { + "epoch": 0.45, + "learning_rate": 1.3323141852761726e-05, + "loss": 1.3295, + "step": 4319 + }, + { + "epoch": 0.45, + "learning_rate": 1.3319689396744358e-05, + "loss": 1.4187, + "step": 4320 + }, + { + "epoch": 0.45, + "learning_rate": 1.3316236495973905e-05, + "loss": 1.335, + "step": 4321 + }, + { + "epoch": 0.45, + "learning_rate": 1.331278315091297e-05, + "loss": 1.4382, + "step": 4322 + }, + { + "epoch": 0.45, + "learning_rate": 1.3309329362024212e-05, + "loss": 1.4244, + "step": 4323 + }, + { + "epoch": 0.45, + "learning_rate": 1.3305875129770351e-05, + "loss": 1.488, + "step": 4324 + }, + { + "epoch": 0.45, + "learning_rate": 1.3302420454614165e-05, + "loss": 1.3369, + "step": 4325 + }, + { + "epoch": 0.45, + "learning_rate": 1.3298965337018487e-05, + "loss": 1.3648, + "step": 4326 + }, + { + "epoch": 0.45, + "learning_rate": 1.3295509777446226e-05, + "loss": 1.3924, + "step": 4327 + }, + { + "epoch": 0.45, + "learning_rate": 1.3292053776360324e-05, + "loss": 1.3789, + "step": 4328 + }, + { + "epoch": 0.45, + "learning_rate": 1.3288597334223802e-05, + "loss": 1.3902, + "step": 4329 + }, + { + "epoch": 0.45, + "learning_rate": 1.3285140451499735e-05, + "loss": 1.4057, + "step": 4330 + }, + { + "epoch": 0.45, + "learning_rate": 1.328168312865126e-05, + "loss": 1.4536, + "step": 4331 + }, + { + "epoch": 0.45, + "learning_rate": 1.3278225366141565e-05, + "loss": 1.3075, + "step": 4332 + }, + { + "epoch": 0.45, + "learning_rate": 1.3274767164433901e-05, + "loss": 1.4579, + "step": 4333 + }, + { + "epoch": 0.45, + "learning_rate": 1.3271308523991579e-05, + "loss": 1.3906, + "step": 4334 + }, + { + "epoch": 0.45, + "learning_rate": 1.326784944527797e-05, + "loss": 1.3992, + "step": 4335 + }, + { + "epoch": 0.45, + "learning_rate": 1.3264389928756498e-05, + "loss": 1.4001, + "step": 4336 + }, + { + "epoch": 0.45, + "learning_rate": 1.3260929974890653e-05, + "loss": 1.2948, + "step": 4337 + }, + { + "epoch": 0.45, + "learning_rate": 1.3257469584143976e-05, + "loss": 1.4041, + "step": 4338 + }, + { + "epoch": 0.46, + "learning_rate": 1.3254008756980076e-05, + "loss": 1.5035, + "step": 4339 + }, + { + "epoch": 0.46, + "learning_rate": 1.3250547493862609e-05, + "loss": 1.4867, + "step": 4340 + }, + { + "epoch": 0.46, + "learning_rate": 1.3247085795255302e-05, + "loss": 1.3612, + "step": 4341 + }, + { + "epoch": 0.46, + "learning_rate": 1.3243623661621925e-05, + "loss": 1.4193, + "step": 4342 + }, + { + "epoch": 0.46, + "learning_rate": 1.3240161093426322e-05, + "loss": 1.3596, + "step": 4343 + }, + { + "epoch": 0.46, + "learning_rate": 1.3236698091132383e-05, + "loss": 1.4448, + "step": 4344 + }, + { + "epoch": 0.46, + "learning_rate": 1.3233234655204066e-05, + "loss": 1.3924, + "step": 4345 + }, + { + "epoch": 0.46, + "learning_rate": 1.322977078610538e-05, + "loss": 1.3552, + "step": 4346 + }, + { + "epoch": 0.46, + "learning_rate": 1.3226306484300395e-05, + "loss": 1.3949, + "step": 4347 + }, + { + "epoch": 0.46, + "learning_rate": 1.322284175025324e-05, + "loss": 1.399, + "step": 4348 + }, + { + "epoch": 0.46, + "learning_rate": 1.3219376584428094e-05, + "loss": 1.4755, + "step": 4349 + }, + { + "epoch": 0.46, + "learning_rate": 1.3215910987289212e-05, + "loss": 1.3877, + "step": 4350 + }, + { + "epoch": 0.46, + "learning_rate": 1.3212444959300882e-05, + "loss": 1.3916, + "step": 4351 + }, + { + "epoch": 0.46, + "learning_rate": 1.3208978500927472e-05, + "loss": 1.3462, + "step": 4352 + }, + { + "epoch": 0.46, + "learning_rate": 1.3205511612633392e-05, + "loss": 1.3834, + "step": 4353 + }, + { + "epoch": 0.46, + "learning_rate": 1.3202044294883123e-05, + "loss": 1.3843, + "step": 4354 + }, + { + "epoch": 0.46, + "learning_rate": 1.3198576548141189e-05, + "loss": 1.2439, + "step": 4355 + }, + { + "epoch": 0.46, + "learning_rate": 1.3195108372872181e-05, + "loss": 1.4106, + "step": 4356 + }, + { + "epoch": 0.46, + "learning_rate": 1.3191639769540746e-05, + "loss": 1.4417, + "step": 4357 + }, + { + "epoch": 0.46, + "learning_rate": 1.3188170738611596e-05, + "loss": 1.4393, + "step": 4358 + }, + { + "epoch": 0.46, + "learning_rate": 1.3184701280549476e-05, + "loss": 1.4616, + "step": 4359 + }, + { + "epoch": 0.46, + "learning_rate": 1.3181231395819218e-05, + "loss": 1.3215, + "step": 4360 + }, + { + "epoch": 0.46, + "learning_rate": 1.3177761084885689e-05, + "loss": 1.368, + "step": 4361 + }, + { + "epoch": 0.46, + "learning_rate": 1.317429034821383e-05, + "loss": 1.3247, + "step": 4362 + }, + { + "epoch": 0.46, + "learning_rate": 1.3170819186268618e-05, + "loss": 1.4512, + "step": 4363 + }, + { + "epoch": 0.46, + "learning_rate": 1.3167347599515111e-05, + "loss": 1.3129, + "step": 4364 + }, + { + "epoch": 0.46, + "learning_rate": 1.3163875588418404e-05, + "loss": 1.3934, + "step": 4365 + }, + { + "epoch": 0.46, + "learning_rate": 1.3160403153443666e-05, + "loss": 1.4518, + "step": 4366 + }, + { + "epoch": 0.46, + "learning_rate": 1.3156930295056105e-05, + "loss": 1.3959, + "step": 4367 + }, + { + "epoch": 0.46, + "learning_rate": 1.3153457013721e-05, + "loss": 1.3475, + "step": 4368 + }, + { + "epoch": 0.46, + "learning_rate": 1.3149983309903687e-05, + "loss": 1.4102, + "step": 4369 + }, + { + "epoch": 0.46, + "learning_rate": 1.3146509184069538e-05, + "loss": 1.3674, + "step": 4370 + }, + { + "epoch": 0.46, + "learning_rate": 1.314303463668401e-05, + "loss": 1.3739, + "step": 4371 + }, + { + "epoch": 0.46, + "learning_rate": 1.3139559668212596e-05, + "loss": 1.4249, + "step": 4372 + }, + { + "epoch": 0.46, + "learning_rate": 1.3136084279120857e-05, + "loss": 1.4473, + "step": 4373 + }, + { + "epoch": 0.46, + "learning_rate": 1.3132608469874404e-05, + "loss": 1.4443, + "step": 4374 + }, + { + "epoch": 0.46, + "learning_rate": 1.3129132240938905e-05, + "loss": 1.3534, + "step": 4375 + }, + { + "epoch": 0.46, + "learning_rate": 1.3125655592780083e-05, + "loss": 1.5663, + "step": 4376 + }, + { + "epoch": 0.46, + "learning_rate": 1.3122178525863727e-05, + "loss": 1.3465, + "step": 4377 + }, + { + "epoch": 0.46, + "learning_rate": 1.3118701040655669e-05, + "loss": 1.35, + "step": 4378 + }, + { + "epoch": 0.46, + "eval_loss": 1.447788953781128, + "eval_runtime": 77.4473, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4378 + }, + { + "epoch": 0.46, + "learning_rate": 1.3115223137621804e-05, + "loss": 1.343, + "step": 4379 + }, + { + "epoch": 0.46, + "learning_rate": 1.3111744817228078e-05, + "loss": 1.4227, + "step": 4380 + }, + { + "epoch": 0.46, + "learning_rate": 1.3108266079940508e-05, + "loss": 1.3982, + "step": 4381 + }, + { + "epoch": 0.46, + "learning_rate": 1.3104786926225141e-05, + "loss": 1.4211, + "step": 4382 + }, + { + "epoch": 0.46, + "learning_rate": 1.3101307356548103e-05, + "loss": 1.382, + "step": 4383 + }, + { + "epoch": 0.46, + "learning_rate": 1.3097827371375562e-05, + "loss": 1.4637, + "step": 4384 + }, + { + "epoch": 0.46, + "learning_rate": 1.3094346971173754e-05, + "loss": 1.4572, + "step": 4385 + }, + { + "epoch": 0.46, + "learning_rate": 1.3090866156408956e-05, + "loss": 1.5113, + "step": 4386 + }, + { + "epoch": 0.46, + "learning_rate": 1.3087384927547512e-05, + "loss": 1.2197, + "step": 4387 + }, + { + "epoch": 0.46, + "learning_rate": 1.3083903285055813e-05, + "loss": 1.3861, + "step": 4388 + }, + { + "epoch": 0.46, + "learning_rate": 1.3080421229400315e-05, + "loss": 1.4754, + "step": 4389 + }, + { + "epoch": 0.46, + "learning_rate": 1.307693876104752e-05, + "loss": 1.3588, + "step": 4390 + }, + { + "epoch": 0.46, + "learning_rate": 1.3073455880463987e-05, + "loss": 1.3995, + "step": 4391 + }, + { + "epoch": 0.46, + "learning_rate": 1.3069972588116341e-05, + "loss": 1.354, + "step": 4392 + }, + { + "epoch": 0.46, + "learning_rate": 1.3066488884471244e-05, + "loss": 1.3378, + "step": 4393 + }, + { + "epoch": 0.46, + "learning_rate": 1.306300476999543e-05, + "loss": 1.5951, + "step": 4394 + }, + { + "epoch": 0.46, + "learning_rate": 1.305952024515568e-05, + "loss": 1.3661, + "step": 4395 + }, + { + "epoch": 0.46, + "learning_rate": 1.3056035310418826e-05, + "loss": 1.4066, + "step": 4396 + }, + { + "epoch": 0.46, + "learning_rate": 1.3052549966251764e-05, + "loss": 1.3687, + "step": 4397 + }, + { + "epoch": 0.46, + "learning_rate": 1.3049064213121438e-05, + "loss": 1.4573, + "step": 4398 + }, + { + "epoch": 0.46, + "learning_rate": 1.3045578051494852e-05, + "loss": 1.3519, + "step": 4399 + }, + { + "epoch": 0.46, + "learning_rate": 1.3042091481839063e-05, + "loss": 1.2803, + "step": 4400 + }, + { + "epoch": 0.46, + "learning_rate": 1.3038604504621173e-05, + "loss": 1.4014, + "step": 4401 + }, + { + "epoch": 0.46, + "learning_rate": 1.3035117120308358e-05, + "loss": 1.4534, + "step": 4402 + }, + { + "epoch": 0.46, + "learning_rate": 1.3031629329367832e-05, + "loss": 1.4747, + "step": 4403 + }, + { + "epoch": 0.46, + "learning_rate": 1.3028141132266877e-05, + "loss": 1.374, + "step": 4404 + }, + { + "epoch": 0.46, + "learning_rate": 1.3024652529472807e-05, + "loss": 1.4328, + "step": 4405 + }, + { + "epoch": 0.46, + "learning_rate": 1.302116352145302e-05, + "loss": 1.468, + "step": 4406 + }, + { + "epoch": 0.46, + "learning_rate": 1.3017674108674942e-05, + "loss": 1.2947, + "step": 4407 + }, + { + "epoch": 0.46, + "learning_rate": 1.3014184291606077e-05, + "loss": 1.3682, + "step": 4408 + }, + { + "epoch": 0.46, + "learning_rate": 1.3010694070713959e-05, + "loss": 1.3651, + "step": 4409 + }, + { + "epoch": 0.46, + "learning_rate": 1.3007203446466194e-05, + "loss": 1.418, + "step": 4410 + }, + { + "epoch": 0.46, + "learning_rate": 1.3003712419330433e-05, + "loss": 1.416, + "step": 4411 + }, + { + "epoch": 0.46, + "learning_rate": 1.300022098977439e-05, + "loss": 1.2979, + "step": 4412 + }, + { + "epoch": 0.46, + "learning_rate": 1.2996729158265819e-05, + "loss": 1.3868, + "step": 4413 + }, + { + "epoch": 0.46, + "learning_rate": 1.2993236925272542e-05, + "loss": 1.3102, + "step": 4414 + }, + { + "epoch": 0.46, + "learning_rate": 1.2989744291262422e-05, + "loss": 1.3506, + "step": 4415 + }, + { + "epoch": 0.46, + "learning_rate": 1.2986251256703388e-05, + "loss": 1.4018, + "step": 4416 + }, + { + "epoch": 0.46, + "learning_rate": 1.2982757822063417e-05, + "loss": 1.4081, + "step": 4417 + }, + { + "epoch": 0.46, + "learning_rate": 1.2979263987810533e-05, + "loss": 1.3592, + "step": 4418 + }, + { + "epoch": 0.46, + "learning_rate": 1.297576975441283e-05, + "loss": 1.4287, + "step": 4419 + }, + { + "epoch": 0.46, + "learning_rate": 1.2972275122338433e-05, + "loss": 1.4099, + "step": 4420 + }, + { + "epoch": 0.46, + "learning_rate": 1.2968780092055546e-05, + "loss": 1.4005, + "step": 4421 + }, + { + "epoch": 0.46, + "learning_rate": 1.2965284664032401e-05, + "loss": 1.365, + "step": 4422 + }, + { + "epoch": 0.46, + "learning_rate": 1.2961788838737309e-05, + "loss": 1.3588, + "step": 4423 + }, + { + "epoch": 0.46, + "learning_rate": 1.2958292616638606e-05, + "loss": 1.3702, + "step": 4424 + }, + { + "epoch": 0.46, + "learning_rate": 1.2954795998204708e-05, + "loss": 1.3487, + "step": 4425 + }, + { + "epoch": 0.46, + "learning_rate": 1.2951298983904063e-05, + "loss": 1.4395, + "step": 4426 + }, + { + "epoch": 0.46, + "learning_rate": 1.2947801574205193e-05, + "loss": 1.3523, + "step": 4427 + }, + { + "epoch": 0.46, + "learning_rate": 1.2944303769576645e-05, + "loss": 1.3125, + "step": 4428 + }, + { + "epoch": 0.46, + "learning_rate": 1.2940805570487048e-05, + "loss": 1.5476, + "step": 4429 + }, + { + "epoch": 0.46, + "learning_rate": 1.2937306977405062e-05, + "loss": 1.4076, + "step": 4430 + }, + { + "epoch": 0.46, + "learning_rate": 1.2933807990799418e-05, + "loss": 1.3007, + "step": 4431 + }, + { + "epoch": 0.46, + "learning_rate": 1.293030861113888e-05, + "loss": 1.3566, + "step": 4432 + }, + { + "epoch": 0.46, + "learning_rate": 1.2926808838892285e-05, + "loss": 1.3907, + "step": 4433 + }, + { + "epoch": 0.46, + "learning_rate": 1.2923308674528501e-05, + "loss": 1.379, + "step": 4434 + }, + { + "epoch": 0.47, + "learning_rate": 1.2919808118516475e-05, + "loss": 1.4319, + "step": 4435 + }, + { + "epoch": 0.47, + "learning_rate": 1.2916307171325176e-05, + "loss": 1.3392, + "step": 4436 + }, + { + "epoch": 0.47, + "learning_rate": 1.291280583342365e-05, + "loss": 1.401, + "step": 4437 + }, + { + "epoch": 0.47, + "learning_rate": 1.2909304105280984e-05, + "loss": 1.3939, + "step": 4438 + }, + { + "epoch": 0.47, + "learning_rate": 1.2905801987366322e-05, + "loss": 1.4676, + "step": 4439 + }, + { + "epoch": 0.47, + "learning_rate": 1.2902299480148855e-05, + "loss": 1.3957, + "step": 4440 + }, + { + "epoch": 0.47, + "learning_rate": 1.2898796584097828e-05, + "loss": 1.3587, + "step": 4441 + }, + { + "epoch": 0.47, + "learning_rate": 1.2895293299682545e-05, + "loss": 1.5809, + "step": 4442 + }, + { + "epoch": 0.47, + "learning_rate": 1.289178962737235e-05, + "loss": 1.3436, + "step": 4443 + }, + { + "epoch": 0.47, + "learning_rate": 1.2888285567636647e-05, + "loss": 1.4535, + "step": 4444 + }, + { + "epoch": 0.47, + "learning_rate": 1.2884781120944889e-05, + "loss": 1.3377, + "step": 4445 + }, + { + "epoch": 0.47, + "learning_rate": 1.2881276287766587e-05, + "loss": 0.8221, + "step": 4446 + }, + { + "epoch": 0.47, + "learning_rate": 1.2877771068571288e-05, + "loss": 0.7259, + "step": 4447 + }, + { + "epoch": 0.47, + "learning_rate": 1.2874265463828612e-05, + "loss": 0.8279, + "step": 4448 + }, + { + "epoch": 0.47, + "learning_rate": 1.2870759474008213e-05, + "loss": 1.3523, + "step": 4449 + }, + { + "epoch": 0.47, + "learning_rate": 1.2867253099579808e-05, + "loss": 1.3658, + "step": 4450 + }, + { + "epoch": 0.47, + "learning_rate": 1.2863746341013158e-05, + "loss": 1.4112, + "step": 4451 + }, + { + "epoch": 0.47, + "learning_rate": 1.2860239198778085e-05, + "loss": 1.389, + "step": 4452 + }, + { + "epoch": 0.47, + "learning_rate": 1.2856731673344442e-05, + "loss": 1.4066, + "step": 4453 + }, + { + "epoch": 0.47, + "learning_rate": 1.2853223765182165e-05, + "loss": 1.3267, + "step": 4454 + }, + { + "epoch": 0.47, + "learning_rate": 1.2849715474761209e-05, + "loss": 1.3381, + "step": 4455 + }, + { + "epoch": 0.47, + "learning_rate": 1.2846206802551602e-05, + "loss": 1.2882, + "step": 4456 + }, + { + "epoch": 0.47, + "learning_rate": 1.2842697749023414e-05, + "loss": 1.3199, + "step": 4457 + }, + { + "epoch": 0.47, + "learning_rate": 1.2839188314646771e-05, + "loss": 1.3896, + "step": 4458 + }, + { + "epoch": 0.47, + "learning_rate": 1.2835678499891842e-05, + "loss": 1.3186, + "step": 4459 + }, + { + "epoch": 0.47, + "learning_rate": 1.283216830522885e-05, + "loss": 1.3466, + "step": 4460 + }, + { + "epoch": 0.47, + "learning_rate": 1.2828657731128083e-05, + "loss": 1.4678, + "step": 4461 + }, + { + "epoch": 0.47, + "learning_rate": 1.2825146778059857e-05, + "loss": 1.4408, + "step": 4462 + }, + { + "epoch": 0.47, + "learning_rate": 1.2821635446494553e-05, + "loss": 1.3672, + "step": 4463 + }, + { + "epoch": 0.47, + "learning_rate": 1.2818123736902597e-05, + "loss": 1.3836, + "step": 4464 + }, + { + "epoch": 0.47, + "learning_rate": 1.2814611649754472e-05, + "loss": 1.3493, + "step": 4465 + }, + { + "epoch": 0.47, + "learning_rate": 1.2811099185520704e-05, + "loss": 1.3584, + "step": 4466 + }, + { + "epoch": 0.47, + "learning_rate": 1.2807586344671875e-05, + "loss": 1.3551, + "step": 4467 + }, + { + "epoch": 0.47, + "learning_rate": 1.2804073127678612e-05, + "loss": 1.3254, + "step": 4468 + }, + { + "epoch": 0.47, + "learning_rate": 1.28005595350116e-05, + "loss": 1.3405, + "step": 4469 + }, + { + "epoch": 0.47, + "learning_rate": 1.2797045567141568e-05, + "loss": 1.3432, + "step": 4470 + }, + { + "epoch": 0.47, + "learning_rate": 1.2793531224539297e-05, + "loss": 1.4347, + "step": 4471 + }, + { + "epoch": 0.47, + "learning_rate": 1.279001650767562e-05, + "loss": 1.3304, + "step": 4472 + }, + { + "epoch": 0.47, + "learning_rate": 1.278650141702142e-05, + "loss": 1.3244, + "step": 4473 + }, + { + "epoch": 0.47, + "learning_rate": 1.2782985953047625e-05, + "loss": 1.3756, + "step": 4474 + }, + { + "epoch": 0.47, + "learning_rate": 1.2779470116225219e-05, + "loss": 1.5468, + "step": 4475 + }, + { + "epoch": 0.47, + "learning_rate": 1.2775953907025232e-05, + "loss": 1.4316, + "step": 4476 + }, + { + "epoch": 0.47, + "learning_rate": 1.2772437325918752e-05, + "loss": 1.3724, + "step": 4477 + }, + { + "epoch": 0.47, + "learning_rate": 1.27689203733769e-05, + "loss": 1.4458, + "step": 4478 + }, + { + "epoch": 0.47, + "learning_rate": 1.2765403049870865e-05, + "loss": 1.3622, + "step": 4479 + }, + { + "epoch": 0.47, + "learning_rate": 1.2761885355871875e-05, + "loss": 1.3875, + "step": 4480 + }, + { + "epoch": 0.47, + "learning_rate": 1.2758367291851217e-05, + "loss": 1.3577, + "step": 4481 + }, + { + "epoch": 0.47, + "learning_rate": 1.2754848858280211e-05, + "loss": 1.4256, + "step": 4482 + }, + { + "epoch": 0.47, + "learning_rate": 1.2751330055630242e-05, + "loss": 1.3771, + "step": 4483 + }, + { + "epoch": 0.47, + "learning_rate": 1.274781088437274e-05, + "loss": 1.357, + "step": 4484 + }, + { + "epoch": 0.47, + "learning_rate": 1.274429134497918e-05, + "loss": 1.3634, + "step": 4485 + }, + { + "epoch": 0.47, + "learning_rate": 1.2740771437921096e-05, + "loss": 1.3661, + "step": 4486 + }, + { + "epoch": 0.47, + "learning_rate": 1.2737251163670057e-05, + "loss": 1.3819, + "step": 4487 + }, + { + "epoch": 0.47, + "learning_rate": 1.2733730522697696e-05, + "loss": 1.4491, + "step": 4488 + }, + { + "epoch": 0.47, + "learning_rate": 1.2730209515475687e-05, + "loss": 1.3857, + "step": 4489 + }, + { + "epoch": 0.47, + "learning_rate": 1.2726688142475751e-05, + "loss": 1.3837, + "step": 4490 + }, + { + "epoch": 0.47, + "learning_rate": 1.2723166404169663e-05, + "loss": 1.3755, + "step": 4491 + }, + { + "epoch": 0.47, + "learning_rate": 1.271964430102925e-05, + "loss": 1.3767, + "step": 4492 + }, + { + "epoch": 0.47, + "learning_rate": 1.2716121833526376e-05, + "loss": 1.4416, + "step": 4493 + }, + { + "epoch": 0.47, + "learning_rate": 1.2712599002132966e-05, + "loss": 1.5573, + "step": 4494 + }, + { + "epoch": 0.47, + "learning_rate": 1.2709075807320988e-05, + "loss": 1.365, + "step": 4495 + }, + { + "epoch": 0.47, + "learning_rate": 1.270555224956246e-05, + "loss": 1.3862, + "step": 4496 + }, + { + "epoch": 0.47, + "learning_rate": 1.2702028329329445e-05, + "loss": 1.3003, + "step": 4497 + }, + { + "epoch": 0.47, + "learning_rate": 1.2698504047094064e-05, + "loss": 1.3806, + "step": 4498 + }, + { + "epoch": 0.47, + "learning_rate": 1.269497940332847e-05, + "loss": 1.5425, + "step": 4499 + }, + { + "epoch": 0.47, + "learning_rate": 1.269145439850489e-05, + "loss": 1.3541, + "step": 4500 + }, + { + "epoch": 0.47, + "learning_rate": 1.268792903309557e-05, + "loss": 1.4337, + "step": 4501 + }, + { + "epoch": 0.47, + "learning_rate": 1.2684403307572825e-05, + "loss": 1.4004, + "step": 4502 + }, + { + "epoch": 0.47, + "learning_rate": 1.268087722240901e-05, + "loss": 1.9453, + "step": 4503 + }, + { + "epoch": 0.47, + "learning_rate": 1.2677350778076532e-05, + "loss": 1.3907, + "step": 4504 + }, + { + "epoch": 0.47, + "learning_rate": 1.2673823975047839e-05, + "loss": 1.4993, + "step": 4505 + }, + { + "epoch": 0.47, + "learning_rate": 1.2670296813795432e-05, + "loss": 1.4386, + "step": 4506 + }, + { + "epoch": 0.47, + "learning_rate": 1.266676929479187e-05, + "loss": 1.4944, + "step": 4507 + }, + { + "epoch": 0.47, + "learning_rate": 1.266324141850974e-05, + "loss": 1.4311, + "step": 4508 + }, + { + "epoch": 0.47, + "learning_rate": 1.265971318542169e-05, + "loss": 1.3607, + "step": 4509 + }, + { + "epoch": 0.47, + "learning_rate": 1.2656184596000412e-05, + "loss": 1.4007, + "step": 4510 + }, + { + "epoch": 0.47, + "learning_rate": 1.2652655650718645e-05, + "loss": 1.4561, + "step": 4511 + }, + { + "epoch": 0.47, + "learning_rate": 1.2649126350049181e-05, + "loss": 1.4321, + "step": 4512 + }, + { + "epoch": 0.47, + "learning_rate": 1.2645596694464851e-05, + "loss": 1.2856, + "step": 4513 + }, + { + "epoch": 0.47, + "learning_rate": 1.2642066684438543e-05, + "loss": 1.3979, + "step": 4514 + }, + { + "epoch": 0.47, + "learning_rate": 1.2638536320443184e-05, + "loss": 1.4977, + "step": 4515 + }, + { + "epoch": 0.47, + "learning_rate": 1.2635005602951752e-05, + "loss": 1.377, + "step": 4516 + }, + { + "epoch": 0.47, + "learning_rate": 1.2631474532437275e-05, + "loss": 1.4266, + "step": 4517 + }, + { + "epoch": 0.47, + "learning_rate": 1.2627943109372822e-05, + "loss": 1.409, + "step": 4518 + }, + { + "epoch": 0.47, + "learning_rate": 1.2624411334231519e-05, + "loss": 1.3374, + "step": 4519 + }, + { + "epoch": 0.47, + "learning_rate": 1.2620879207486525e-05, + "loss": 1.3765, + "step": 4520 + }, + { + "epoch": 0.47, + "learning_rate": 1.2617346729611061e-05, + "loss": 1.3805, + "step": 4521 + }, + { + "epoch": 0.47, + "learning_rate": 1.2613813901078384e-05, + "loss": 1.3326, + "step": 4522 + }, + { + "epoch": 0.47, + "learning_rate": 1.2610280722361807e-05, + "loss": 1.3909, + "step": 4523 + }, + { + "epoch": 0.47, + "learning_rate": 1.260674719393468e-05, + "loss": 1.3815, + "step": 4524 + }, + { + "epoch": 0.47, + "learning_rate": 1.2603213316270409e-05, + "loss": 1.5589, + "step": 4525 + }, + { + "epoch": 0.47, + "learning_rate": 1.2599679089842437e-05, + "loss": 1.4416, + "step": 4526 + }, + { + "epoch": 0.47, + "learning_rate": 1.259614451512427e-05, + "loss": 1.3529, + "step": 4527 + }, + { + "epoch": 0.47, + "learning_rate": 1.2592609592589437e-05, + "loss": 1.3135, + "step": 4528 + }, + { + "epoch": 0.47, + "learning_rate": 1.2589074322711535e-05, + "loss": 1.4177, + "step": 4529 + }, + { + "epoch": 0.48, + "learning_rate": 1.25855387059642e-05, + "loss": 1.353, + "step": 4530 + }, + { + "epoch": 0.48, + "learning_rate": 1.2582002742821111e-05, + "loss": 1.431, + "step": 4531 + }, + { + "epoch": 0.48, + "learning_rate": 1.2578466433755998e-05, + "loss": 1.3803, + "step": 4532 + }, + { + "epoch": 0.48, + "learning_rate": 1.257492977924263e-05, + "loss": 1.3774, + "step": 4533 + }, + { + "epoch": 0.48, + "learning_rate": 1.2571392779754836e-05, + "loss": 1.4339, + "step": 4534 + }, + { + "epoch": 0.48, + "learning_rate": 1.256785543576648e-05, + "loss": 1.4097, + "step": 4535 + }, + { + "epoch": 0.48, + "learning_rate": 1.2564317747751473e-05, + "loss": 1.4223, + "step": 4536 + }, + { + "epoch": 0.48, + "learning_rate": 1.2560779716183775e-05, + "loss": 1.5148, + "step": 4537 + }, + { + "epoch": 0.48, + "learning_rate": 1.2557241341537394e-05, + "loss": 1.3547, + "step": 4538 + }, + { + "epoch": 0.48, + "learning_rate": 1.255370262428638e-05, + "loss": 1.393, + "step": 4539 + }, + { + "epoch": 0.48, + "learning_rate": 1.2550163564904829e-05, + "loss": 1.3312, + "step": 4540 + }, + { + "epoch": 0.48, + "learning_rate": 1.2546624163866882e-05, + "loss": 1.4193, + "step": 4541 + }, + { + "epoch": 0.48, + "learning_rate": 1.2543084421646735e-05, + "loss": 1.4161, + "step": 4542 + }, + { + "epoch": 0.48, + "learning_rate": 1.2539544338718614e-05, + "loss": 1.4224, + "step": 4543 + }, + { + "epoch": 0.48, + "learning_rate": 1.2536003915556805e-05, + "loss": 1.3484, + "step": 4544 + }, + { + "epoch": 0.48, + "learning_rate": 1.253246315263563e-05, + "loss": 1.4492, + "step": 4545 + }, + { + "epoch": 0.48, + "learning_rate": 1.2528922050429467e-05, + "loss": 1.3549, + "step": 4546 + }, + { + "epoch": 0.48, + "learning_rate": 1.252538060941272e-05, + "loss": 1.45, + "step": 4547 + }, + { + "epoch": 0.48, + "learning_rate": 1.2521838830059865e-05, + "loss": 1.3499, + "step": 4548 + }, + { + "epoch": 0.48, + "learning_rate": 1.2518296712845399e-05, + "loss": 1.3786, + "step": 4549 + }, + { + "epoch": 0.48, + "learning_rate": 1.2514754258243884e-05, + "loss": 1.3394, + "step": 4550 + }, + { + "epoch": 0.48, + "learning_rate": 1.2511211466729909e-05, + "loss": 1.2849, + "step": 4551 + }, + { + "epoch": 0.48, + "learning_rate": 1.250766833877812e-05, + "loss": 1.374, + "step": 4552 + }, + { + "epoch": 0.48, + "learning_rate": 1.2504124874863211e-05, + "loss": 1.3084, + "step": 4553 + }, + { + "epoch": 0.48, + "learning_rate": 1.2500581075459905e-05, + "loss": 1.3348, + "step": 4554 + }, + { + "epoch": 0.48, + "learning_rate": 1.249703694104299e-05, + "loss": 1.3797, + "step": 4555 + }, + { + "epoch": 0.48, + "learning_rate": 1.2493492472087279e-05, + "loss": 1.3371, + "step": 4556 + }, + { + "epoch": 0.48, + "learning_rate": 1.248994766906765e-05, + "loss": 1.3974, + "step": 4557 + }, + { + "epoch": 0.48, + "learning_rate": 1.2486402532459007e-05, + "loss": 1.388, + "step": 4558 + }, + { + "epoch": 0.48, + "learning_rate": 1.2482857062736313e-05, + "loss": 1.3619, + "step": 4559 + }, + { + "epoch": 0.48, + "learning_rate": 1.2479311260374565e-05, + "loss": 1.4123, + "step": 4560 + }, + { + "epoch": 0.48, + "learning_rate": 1.2475765125848814e-05, + "loss": 1.5485, + "step": 4561 + }, + { + "epoch": 0.48, + "learning_rate": 1.247221865963415e-05, + "loss": 1.4965, + "step": 4562 + }, + { + "epoch": 0.48, + "learning_rate": 1.2468671862205705e-05, + "loss": 1.4352, + "step": 4563 + }, + { + "epoch": 0.48, + "learning_rate": 1.246512473403866e-05, + "loss": 1.3935, + "step": 4564 + }, + { + "epoch": 0.48, + "learning_rate": 1.2461577275608243e-05, + "loss": 1.3798, + "step": 4565 + }, + { + "epoch": 0.48, + "learning_rate": 1.2458029487389718e-05, + "loss": 1.4039, + "step": 4566 + }, + { + "epoch": 0.48, + "learning_rate": 1.2454481369858397e-05, + "loss": 1.3723, + "step": 4567 + }, + { + "epoch": 0.48, + "learning_rate": 1.245093292348964e-05, + "loss": 1.3713, + "step": 4568 + }, + { + "epoch": 0.48, + "learning_rate": 1.2447384148758847e-05, + "loss": 1.4083, + "step": 4569 + }, + { + "epoch": 0.48, + "learning_rate": 1.244383504614146e-05, + "loss": 1.2811, + "step": 4570 + }, + { + "epoch": 0.48, + "learning_rate": 1.2440285616112968e-05, + "loss": 1.3509, + "step": 4571 + }, + { + "epoch": 0.48, + "learning_rate": 1.2436735859148905e-05, + "loss": 1.3481, + "step": 4572 + }, + { + "epoch": 0.48, + "learning_rate": 1.2433185775724847e-05, + "loss": 1.4168, + "step": 4573 + }, + { + "epoch": 0.48, + "learning_rate": 1.2429635366316418e-05, + "loss": 1.3671, + "step": 4574 + }, + { + "epoch": 0.48, + "learning_rate": 1.2426084631399271e-05, + "loss": 1.6514, + "step": 4575 + }, + { + "epoch": 0.48, + "learning_rate": 1.2422533571449123e-05, + "loss": 1.3564, + "step": 4576 + }, + { + "epoch": 0.48, + "learning_rate": 1.2418982186941721e-05, + "loss": 1.4586, + "step": 4577 + }, + { + "epoch": 0.48, + "eval_loss": 1.4425245523452759, + "eval_runtime": 77.3853, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 4577 + }, + { + "epoch": 0.48, + "learning_rate": 1.2415430478352858e-05, + "loss": 1.3922, + "step": 4578 + }, + { + "epoch": 0.48, + "learning_rate": 1.2411878446158374e-05, + "loss": 1.3903, + "step": 4579 + }, + { + "epoch": 0.48, + "learning_rate": 1.240832609083415e-05, + "loss": 1.3537, + "step": 4580 + }, + { + "epoch": 0.48, + "learning_rate": 1.2404773412856113e-05, + "loss": 1.356, + "step": 4581 + }, + { + "epoch": 0.48, + "learning_rate": 1.2401220412700223e-05, + "loss": 1.4483, + "step": 4582 + }, + { + "epoch": 0.48, + "learning_rate": 1.2397667090842496e-05, + "loss": 1.3926, + "step": 4583 + }, + { + "epoch": 0.48, + "learning_rate": 1.2394113447758986e-05, + "loss": 1.4816, + "step": 4584 + }, + { + "epoch": 0.48, + "learning_rate": 1.2390559483925788e-05, + "loss": 1.3742, + "step": 4585 + }, + { + "epoch": 0.48, + "learning_rate": 1.2387005199819044e-05, + "loss": 1.4476, + "step": 4586 + }, + { + "epoch": 0.48, + "learning_rate": 1.2383450595914932e-05, + "loss": 1.4029, + "step": 4587 + }, + { + "epoch": 0.48, + "learning_rate": 1.2379895672689683e-05, + "loss": 1.4797, + "step": 4588 + }, + { + "epoch": 0.48, + "learning_rate": 1.2376340430619565e-05, + "loss": 1.3366, + "step": 4589 + }, + { + "epoch": 0.48, + "learning_rate": 1.2372784870180885e-05, + "loss": 1.4226, + "step": 4590 + }, + { + "epoch": 0.48, + "learning_rate": 1.2369228991849997e-05, + "loss": 1.3668, + "step": 4591 + }, + { + "epoch": 0.48, + "learning_rate": 1.2365672796103305e-05, + "loss": 1.4932, + "step": 4592 + }, + { + "epoch": 0.48, + "learning_rate": 1.236211628341724e-05, + "loss": 1.4088, + "step": 4593 + }, + { + "epoch": 0.48, + "learning_rate": 1.2358559454268284e-05, + "loss": 1.3616, + "step": 4594 + }, + { + "epoch": 0.48, + "learning_rate": 1.2355002309132961e-05, + "loss": 1.4345, + "step": 4595 + }, + { + "epoch": 0.48, + "learning_rate": 1.2351444848487844e-05, + "loss": 1.4025, + "step": 4596 + }, + { + "epoch": 0.48, + "learning_rate": 1.2347887072809533e-05, + "loss": 1.3895, + "step": 4597 + }, + { + "epoch": 0.48, + "learning_rate": 1.2344328982574678e-05, + "loss": 1.3326, + "step": 4598 + }, + { + "epoch": 0.48, + "learning_rate": 1.234077057825998e-05, + "loss": 1.4249, + "step": 4599 + }, + { + "epoch": 0.48, + "learning_rate": 1.2337211860342167e-05, + "loss": 1.3649, + "step": 4600 + }, + { + "epoch": 0.48, + "learning_rate": 1.2333652829298016e-05, + "loss": 1.3831, + "step": 4601 + }, + { + "epoch": 0.48, + "learning_rate": 1.2330093485604346e-05, + "loss": 1.3748, + "step": 4602 + }, + { + "epoch": 0.48, + "learning_rate": 1.2326533829738022e-05, + "loss": 1.386, + "step": 4603 + }, + { + "epoch": 0.48, + "learning_rate": 1.2322973862175941e-05, + "loss": 1.3923, + "step": 4604 + }, + { + "epoch": 0.48, + "learning_rate": 1.2319413583395052e-05, + "loss": 1.3638, + "step": 4605 + }, + { + "epoch": 0.48, + "learning_rate": 1.2315852993872335e-05, + "loss": 1.3476, + "step": 4606 + }, + { + "epoch": 0.48, + "learning_rate": 1.2312292094084824e-05, + "loss": 1.3581, + "step": 4607 + }, + { + "epoch": 0.48, + "learning_rate": 1.2308730884509583e-05, + "loss": 1.3554, + "step": 4608 + }, + { + "epoch": 0.48, + "learning_rate": 1.2305169365623724e-05, + "loss": 1.3676, + "step": 4609 + }, + { + "epoch": 0.48, + "learning_rate": 1.2301607537904399e-05, + "loss": 1.24, + "step": 4610 + }, + { + "epoch": 0.48, + "learning_rate": 1.2298045401828803e-05, + "loss": 1.3295, + "step": 4611 + }, + { + "epoch": 0.48, + "learning_rate": 1.2294482957874169e-05, + "loss": 1.5684, + "step": 4612 + }, + { + "epoch": 0.48, + "learning_rate": 1.2290920206517774e-05, + "loss": 1.3403, + "step": 4613 + }, + { + "epoch": 0.48, + "learning_rate": 1.2287357148236933e-05, + "loss": 1.349, + "step": 4614 + }, + { + "epoch": 0.48, + "learning_rate": 1.2283793783509008e-05, + "loss": 1.4261, + "step": 4615 + }, + { + "epoch": 0.48, + "learning_rate": 1.2280230112811395e-05, + "loss": 1.322, + "step": 4616 + }, + { + "epoch": 0.48, + "learning_rate": 1.2276666136621538e-05, + "loss": 1.3399, + "step": 4617 + }, + { + "epoch": 0.48, + "learning_rate": 1.2273101855416912e-05, + "loss": 1.3878, + "step": 4618 + }, + { + "epoch": 0.48, + "learning_rate": 1.2269537269675044e-05, + "loss": 1.4733, + "step": 4619 + }, + { + "epoch": 0.48, + "learning_rate": 1.2265972379873497e-05, + "loss": 1.419, + "step": 4620 + }, + { + "epoch": 0.48, + "learning_rate": 1.226240718648987e-05, + "loss": 1.3918, + "step": 4621 + }, + { + "epoch": 0.48, + "learning_rate": 1.2258841690001815e-05, + "loss": 1.3398, + "step": 4622 + }, + { + "epoch": 0.48, + "learning_rate": 1.225527589088701e-05, + "loss": 1.4091, + "step": 4623 + }, + { + "epoch": 0.48, + "learning_rate": 1.2251709789623185e-05, + "loss": 1.3291, + "step": 4624 + }, + { + "epoch": 0.49, + "learning_rate": 1.2248143386688101e-05, + "loss": 1.4288, + "step": 4625 + }, + { + "epoch": 0.49, + "learning_rate": 1.224457668255957e-05, + "loss": 1.2942, + "step": 4626 + }, + { + "epoch": 0.49, + "learning_rate": 1.2241009677715437e-05, + "loss": 1.4014, + "step": 4627 + }, + { + "epoch": 0.49, + "learning_rate": 1.2237442372633586e-05, + "loss": 1.3823, + "step": 4628 + }, + { + "epoch": 0.49, + "learning_rate": 1.2233874767791945e-05, + "loss": 1.3556, + "step": 4629 + }, + { + "epoch": 0.49, + "learning_rate": 1.2230306863668485e-05, + "loss": 1.411, + "step": 4630 + }, + { + "epoch": 0.49, + "learning_rate": 1.2226738660741212e-05, + "loss": 1.4347, + "step": 4631 + }, + { + "epoch": 0.49, + "learning_rate": 1.2223170159488169e-05, + "loss": 1.3095, + "step": 4632 + }, + { + "epoch": 0.49, + "learning_rate": 1.221960136038745e-05, + "loss": 1.4272, + "step": 4633 + }, + { + "epoch": 0.49, + "learning_rate": 1.221603226391718e-05, + "loss": 1.367, + "step": 4634 + }, + { + "epoch": 0.49, + "learning_rate": 1.2212462870555523e-05, + "loss": 1.3357, + "step": 4635 + }, + { + "epoch": 0.49, + "learning_rate": 1.220889318078069e-05, + "loss": 1.3634, + "step": 4636 + }, + { + "epoch": 0.49, + "learning_rate": 1.2205323195070927e-05, + "loss": 1.4143, + "step": 4637 + }, + { + "epoch": 0.49, + "learning_rate": 1.2201752913904519e-05, + "loss": 1.4865, + "step": 4638 + }, + { + "epoch": 0.49, + "learning_rate": 1.2198182337759794e-05, + "loss": 1.451, + "step": 4639 + }, + { + "epoch": 0.49, + "learning_rate": 1.2194611467115116e-05, + "loss": 1.3953, + "step": 4640 + }, + { + "epoch": 0.49, + "learning_rate": 1.2191040302448887e-05, + "loss": 1.4099, + "step": 4641 + }, + { + "epoch": 0.49, + "learning_rate": 1.2187468844239559e-05, + "loss": 1.3338, + "step": 4642 + }, + { + "epoch": 0.49, + "learning_rate": 1.2183897092965609e-05, + "loss": 1.4392, + "step": 4643 + }, + { + "epoch": 0.49, + "learning_rate": 1.2180325049105559e-05, + "loss": 1.3196, + "step": 4644 + }, + { + "epoch": 0.49, + "learning_rate": 1.2176752713137977e-05, + "loss": 1.3727, + "step": 4645 + }, + { + "epoch": 0.49, + "learning_rate": 1.2173180085541464e-05, + "loss": 1.3118, + "step": 4646 + }, + { + "epoch": 0.49, + "learning_rate": 1.2169607166794655e-05, + "loss": 1.3695, + "step": 4647 + }, + { + "epoch": 0.49, + "learning_rate": 1.2166033957376231e-05, + "loss": 1.3568, + "step": 4648 + }, + { + "epoch": 0.49, + "learning_rate": 1.216246045776491e-05, + "loss": 1.3492, + "step": 4649 + }, + { + "epoch": 0.49, + "learning_rate": 1.2158886668439455e-05, + "loss": 1.3445, + "step": 4650 + }, + { + "epoch": 0.49, + "learning_rate": 1.2155312589878654e-05, + "loss": 1.3756, + "step": 4651 + }, + { + "epoch": 0.49, + "learning_rate": 1.2151738222561344e-05, + "loss": 1.3681, + "step": 4652 + }, + { + "epoch": 0.49, + "learning_rate": 1.2148163566966403e-05, + "loss": 1.4345, + "step": 4653 + }, + { + "epoch": 0.49, + "learning_rate": 1.2144588623572738e-05, + "loss": 1.5102, + "step": 4654 + }, + { + "epoch": 0.49, + "learning_rate": 1.2141013392859297e-05, + "loss": 1.3531, + "step": 4655 + }, + { + "epoch": 0.49, + "learning_rate": 1.2137437875305075e-05, + "loss": 1.3824, + "step": 4656 + }, + { + "epoch": 0.49, + "learning_rate": 1.2133862071389099e-05, + "loss": 1.4227, + "step": 4657 + }, + { + "epoch": 0.49, + "learning_rate": 1.2130285981590433e-05, + "loss": 1.3479, + "step": 4658 + }, + { + "epoch": 0.49, + "learning_rate": 1.2126709606388181e-05, + "loss": 1.381, + "step": 4659 + }, + { + "epoch": 0.49, + "learning_rate": 1.2123132946261485e-05, + "loss": 1.3847, + "step": 4660 + }, + { + "epoch": 0.49, + "learning_rate": 1.2119556001689527e-05, + "loss": 1.3549, + "step": 4661 + }, + { + "epoch": 0.49, + "learning_rate": 1.2115978773151527e-05, + "loss": 1.3754, + "step": 4662 + }, + { + "epoch": 0.49, + "learning_rate": 1.2112401261126736e-05, + "loss": 1.3329, + "step": 4663 + }, + { + "epoch": 0.49, + "learning_rate": 1.2108823466094453e-05, + "loss": 1.4228, + "step": 4664 + }, + { + "epoch": 0.49, + "learning_rate": 1.2105245388534013e-05, + "loss": 1.4138, + "step": 4665 + }, + { + "epoch": 0.49, + "learning_rate": 1.2101667028924782e-05, + "loss": 1.3538, + "step": 4666 + }, + { + "epoch": 0.49, + "learning_rate": 1.2098088387746168e-05, + "loss": 1.4848, + "step": 4667 + }, + { + "epoch": 0.49, + "learning_rate": 1.2094509465477619e-05, + "loss": 1.5719, + "step": 4668 + }, + { + "epoch": 0.49, + "learning_rate": 1.209093026259862e-05, + "loss": 1.3863, + "step": 4669 + }, + { + "epoch": 0.49, + "learning_rate": 1.2087350779588691e-05, + "loss": 1.4425, + "step": 4670 + }, + { + "epoch": 0.49, + "learning_rate": 1.2083771016927386e-05, + "loss": 1.3655, + "step": 4671 + }, + { + "epoch": 0.49, + "learning_rate": 1.208019097509431e-05, + "loss": 1.3629, + "step": 4672 + }, + { + "epoch": 0.49, + "learning_rate": 1.2076610654569092e-05, + "loss": 1.3849, + "step": 4673 + }, + { + "epoch": 0.49, + "learning_rate": 1.20730300558314e-05, + "loss": 1.3763, + "step": 4674 + }, + { + "epoch": 0.49, + "learning_rate": 1.2069449179360945e-05, + "loss": 1.5316, + "step": 4675 + }, + { + "epoch": 0.49, + "learning_rate": 1.2065868025637476e-05, + "loss": 1.2873, + "step": 4676 + }, + { + "epoch": 0.49, + "learning_rate": 1.2062286595140773e-05, + "loss": 1.3642, + "step": 4677 + }, + { + "epoch": 0.49, + "learning_rate": 1.2058704888350652e-05, + "loss": 1.3782, + "step": 4678 + }, + { + "epoch": 0.49, + "learning_rate": 1.2055122905746972e-05, + "loss": 1.4597, + "step": 4679 + }, + { + "epoch": 0.49, + "learning_rate": 1.205154064780963e-05, + "loss": 1.3952, + "step": 4680 + }, + { + "epoch": 0.49, + "learning_rate": 1.2047958115018554e-05, + "loss": 1.4012, + "step": 4681 + }, + { + "epoch": 0.49, + "learning_rate": 1.204437530785371e-05, + "loss": 1.3432, + "step": 4682 + }, + { + "epoch": 0.49, + "learning_rate": 1.2040792226795101e-05, + "loss": 1.4111, + "step": 4683 + }, + { + "epoch": 0.49, + "learning_rate": 1.2037208872322773e-05, + "loss": 1.4357, + "step": 4684 + }, + { + "epoch": 0.49, + "learning_rate": 1.2033625244916803e-05, + "loss": 1.3908, + "step": 4685 + }, + { + "epoch": 0.49, + "learning_rate": 1.2030041345057298e-05, + "loss": 1.3804, + "step": 4686 + }, + { + "epoch": 0.49, + "learning_rate": 1.2026457173224412e-05, + "loss": 1.4523, + "step": 4687 + }, + { + "epoch": 0.49, + "learning_rate": 1.2022872729898336e-05, + "loss": 1.4266, + "step": 4688 + }, + { + "epoch": 0.49, + "learning_rate": 1.201928801555929e-05, + "loss": 1.3345, + "step": 4689 + }, + { + "epoch": 0.49, + "learning_rate": 1.2015703030687532e-05, + "loss": 1.1714, + "step": 4690 + }, + { + "epoch": 0.49, + "learning_rate": 1.2012117775763361e-05, + "loss": 1.3899, + "step": 4691 + }, + { + "epoch": 0.49, + "learning_rate": 1.2008532251267109e-05, + "loss": 1.43, + "step": 4692 + }, + { + "epoch": 0.49, + "learning_rate": 1.2004946457679144e-05, + "loss": 1.4302, + "step": 4693 + }, + { + "epoch": 0.49, + "learning_rate": 1.2001360395479865e-05, + "loss": 1.3452, + "step": 4694 + }, + { + "epoch": 0.49, + "learning_rate": 1.1997774065149716e-05, + "loss": 1.3383, + "step": 4695 + }, + { + "epoch": 0.49, + "learning_rate": 1.1994187467169176e-05, + "loss": 1.3677, + "step": 4696 + }, + { + "epoch": 0.49, + "learning_rate": 1.1990600602018755e-05, + "loss": 1.4486, + "step": 4697 + }, + { + "epoch": 0.49, + "learning_rate": 1.1987013470178998e-05, + "loss": 1.4059, + "step": 4698 + }, + { + "epoch": 0.49, + "learning_rate": 1.198342607213049e-05, + "loss": 1.3558, + "step": 4699 + }, + { + "epoch": 0.49, + "learning_rate": 1.1979838408353854e-05, + "loss": 1.3931, + "step": 4700 + }, + { + "epoch": 0.49, + "learning_rate": 1.197625047932974e-05, + "loss": 1.5409, + "step": 4701 + }, + { + "epoch": 0.49, + "learning_rate": 1.197266228553884e-05, + "loss": 1.4878, + "step": 4702 + }, + { + "epoch": 0.49, + "learning_rate": 1.196907382746188e-05, + "loss": 1.3581, + "step": 4703 + }, + { + "epoch": 0.49, + "learning_rate": 1.1965485105579621e-05, + "loss": 1.3617, + "step": 4704 + }, + { + "epoch": 0.49, + "learning_rate": 1.1961896120372857e-05, + "loss": 1.399, + "step": 4705 + }, + { + "epoch": 0.49, + "learning_rate": 1.1958306872322425e-05, + "loss": 1.3861, + "step": 4706 + }, + { + "epoch": 0.49, + "learning_rate": 1.1954717361909186e-05, + "loss": 1.4719, + "step": 4707 + }, + { + "epoch": 0.49, + "learning_rate": 1.195112758961405e-05, + "loss": 1.393, + "step": 4708 + }, + { + "epoch": 0.49, + "learning_rate": 1.1947537555917947e-05, + "loss": 1.4252, + "step": 4709 + }, + { + "epoch": 0.49, + "learning_rate": 1.194394726130185e-05, + "loss": 1.4187, + "step": 4710 + }, + { + "epoch": 0.49, + "learning_rate": 1.1940356706246772e-05, + "loss": 1.4822, + "step": 4711 + }, + { + "epoch": 0.49, + "learning_rate": 1.193676589123375e-05, + "loss": 1.4259, + "step": 4712 + }, + { + "epoch": 0.49, + "learning_rate": 1.1933174816743857e-05, + "loss": 1.4226, + "step": 4713 + }, + { + "epoch": 0.49, + "learning_rate": 1.1929583483258216e-05, + "loss": 1.3701, + "step": 4714 + }, + { + "epoch": 0.49, + "learning_rate": 1.1925991891257967e-05, + "loss": 1.406, + "step": 4715 + }, + { + "epoch": 0.49, + "learning_rate": 1.1922400041224288e-05, + "loss": 1.4593, + "step": 4716 + }, + { + "epoch": 0.49, + "learning_rate": 1.1918807933638401e-05, + "loss": 1.3443, + "step": 4717 + }, + { + "epoch": 0.49, + "learning_rate": 1.1915215568981552e-05, + "loss": 1.3523, + "step": 4718 + }, + { + "epoch": 0.49, + "learning_rate": 1.1911622947735027e-05, + "loss": 1.3175, + "step": 4719 + }, + { + "epoch": 0.49, + "learning_rate": 1.1908030070380143e-05, + "loss": 1.3974, + "step": 4720 + }, + { + "epoch": 0.5, + "learning_rate": 1.1904436937398257e-05, + "loss": 1.386, + "step": 4721 + }, + { + "epoch": 0.5, + "learning_rate": 1.1900843549270753e-05, + "loss": 1.3684, + "step": 4722 + }, + { + "epoch": 0.5, + "learning_rate": 1.1897249906479054e-05, + "loss": 1.383, + "step": 4723 + }, + { + "epoch": 0.5, + "learning_rate": 1.1893656009504617e-05, + "loss": 1.38, + "step": 4724 + }, + { + "epoch": 0.5, + "learning_rate": 1.1890061858828928e-05, + "loss": 1.3844, + "step": 4725 + }, + { + "epoch": 0.5, + "learning_rate": 1.1886467454933515e-05, + "loss": 1.3252, + "step": 4726 + }, + { + "epoch": 0.5, + "learning_rate": 1.1882872798299934e-05, + "loss": 1.3434, + "step": 4727 + }, + { + "epoch": 0.5, + "learning_rate": 1.1879277889409779e-05, + "loss": 1.4115, + "step": 4728 + }, + { + "epoch": 0.5, + "learning_rate": 1.1875682728744669e-05, + "loss": 1.1911, + "step": 4729 + }, + { + "epoch": 0.5, + "learning_rate": 1.1872087316786272e-05, + "loss": 1.2794, + "step": 4730 + }, + { + "epoch": 0.5, + "learning_rate": 1.1868491654016274e-05, + "loss": 1.3961, + "step": 4731 + }, + { + "epoch": 0.5, + "learning_rate": 1.1864895740916404e-05, + "loss": 1.4965, + "step": 4732 + }, + { + "epoch": 0.5, + "learning_rate": 1.1861299577968419e-05, + "loss": 1.3932, + "step": 4733 + }, + { + "epoch": 0.5, + "learning_rate": 1.185770316565412e-05, + "loss": 1.3926, + "step": 4734 + }, + { + "epoch": 0.5, + "learning_rate": 1.1854106504455327e-05, + "loss": 1.3964, + "step": 4735 + }, + { + "epoch": 0.5, + "learning_rate": 1.1850509594853901e-05, + "loss": 1.3666, + "step": 4736 + }, + { + "epoch": 0.5, + "learning_rate": 1.1846912437331736e-05, + "loss": 1.4364, + "step": 4737 + }, + { + "epoch": 0.5, + "learning_rate": 1.1843315032370762e-05, + "loss": 1.3537, + "step": 4738 + }, + { + "epoch": 0.5, + "learning_rate": 1.1839717380452935e-05, + "loss": 1.4083, + "step": 4739 + }, + { + "epoch": 0.5, + "learning_rate": 1.1836119482060247e-05, + "loss": 1.3881, + "step": 4740 + }, + { + "epoch": 0.5, + "learning_rate": 1.1832521337674727e-05, + "loss": 1.4127, + "step": 4741 + }, + { + "epoch": 0.5, + "learning_rate": 1.1828922947778436e-05, + "loss": 1.3433, + "step": 4742 + }, + { + "epoch": 0.5, + "learning_rate": 1.1825324312853461e-05, + "loss": 1.486, + "step": 4743 + }, + { + "epoch": 0.5, + "learning_rate": 1.1821725433381925e-05, + "loss": 1.335, + "step": 4744 + }, + { + "epoch": 0.5, + "learning_rate": 1.1818126309845993e-05, + "loss": 1.3827, + "step": 4745 + }, + { + "epoch": 0.5, + "learning_rate": 1.181452694272785e-05, + "loss": 1.3146, + "step": 4746 + }, + { + "epoch": 0.5, + "learning_rate": 1.1810927332509717e-05, + "loss": 1.3543, + "step": 4747 + }, + { + "epoch": 0.5, + "learning_rate": 1.1807327479673852e-05, + "loss": 1.3544, + "step": 4748 + }, + { + "epoch": 0.5, + "learning_rate": 1.1803727384702543e-05, + "loss": 1.3677, + "step": 4749 + }, + { + "epoch": 0.5, + "learning_rate": 1.1800127048078111e-05, + "loss": 1.3842, + "step": 4750 + }, + { + "epoch": 0.5, + "learning_rate": 1.1796526470282907e-05, + "loss": 1.3495, + "step": 4751 + }, + { + "epoch": 0.5, + "learning_rate": 1.1792925651799314e-05, + "loss": 1.481, + "step": 4752 + }, + { + "epoch": 0.5, + "learning_rate": 1.1789324593109754e-05, + "loss": 1.3482, + "step": 4753 + }, + { + "epoch": 0.5, + "learning_rate": 1.1785723294696673e-05, + "loss": 1.2805, + "step": 4754 + }, + { + "epoch": 0.5, + "learning_rate": 1.1782121757042555e-05, + "loss": 1.3458, + "step": 4755 + }, + { + "epoch": 0.5, + "learning_rate": 1.1778519980629907e-05, + "loss": 1.3937, + "step": 4756 + }, + { + "epoch": 0.5, + "learning_rate": 1.1774917965941284e-05, + "loss": 1.3873, + "step": 4757 + }, + { + "epoch": 0.5, + "learning_rate": 1.1771315713459258e-05, + "loss": 1.3512, + "step": 4758 + }, + { + "epoch": 0.5, + "learning_rate": 1.1767713223666436e-05, + "loss": 1.4465, + "step": 4759 + }, + { + "epoch": 0.5, + "learning_rate": 1.1764110497045463e-05, + "loss": 1.4233, + "step": 4760 + }, + { + "epoch": 0.5, + "learning_rate": 1.1760507534079011e-05, + "loss": 1.4818, + "step": 4761 + }, + { + "epoch": 0.5, + "learning_rate": 1.1756904335249786e-05, + "loss": 1.2933, + "step": 4762 + }, + { + "epoch": 0.5, + "learning_rate": 1.1753300901040518e-05, + "loss": 1.3524, + "step": 4763 + }, + { + "epoch": 0.5, + "learning_rate": 1.1749697231933981e-05, + "loss": 1.4909, + "step": 4764 + }, + { + "epoch": 0.5, + "learning_rate": 1.1746093328412975e-05, + "loss": 1.2912, + "step": 4765 + }, + { + "epoch": 0.5, + "learning_rate": 1.1742489190960325e-05, + "loss": 1.3372, + "step": 4766 + }, + { + "epoch": 0.5, + "learning_rate": 1.1738884820058893e-05, + "loss": 1.3036, + "step": 4767 + }, + { + "epoch": 0.5, + "learning_rate": 1.1735280216191578e-05, + "loss": 1.3189, + "step": 4768 + }, + { + "epoch": 0.5, + "learning_rate": 1.1731675379841298e-05, + "loss": 1.4146, + "step": 4769 + }, + { + "epoch": 0.5, + "learning_rate": 1.1728070311491013e-05, + "loss": 1.3309, + "step": 4770 + }, + { + "epoch": 0.5, + "learning_rate": 1.1724465011623705e-05, + "loss": 1.3427, + "step": 4771 + }, + { + "epoch": 0.5, + "learning_rate": 1.1720859480722395e-05, + "loss": 1.4033, + "step": 4772 + }, + { + "epoch": 0.5, + "learning_rate": 1.1717253719270135e-05, + "loss": 1.3832, + "step": 4773 + }, + { + "epoch": 0.5, + "learning_rate": 1.1713647727749994e-05, + "loss": 1.4074, + "step": 4774 + }, + { + "epoch": 0.5, + "learning_rate": 1.1710041506645092e-05, + "loss": 1.3579, + "step": 4775 + }, + { + "epoch": 0.5, + "learning_rate": 1.1706435056438564e-05, + "loss": 1.3685, + "step": 4776 + }, + { + "epoch": 0.5, + "eval_loss": 1.436767816543579, + "eval_runtime": 77.4332, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4776 + }, + { + "epoch": 0.5, + "learning_rate": 1.1702828377613584e-05, + "loss": 1.5843, + "step": 4777 + }, + { + "epoch": 0.5, + "learning_rate": 1.1699221470653355e-05, + "loss": 1.4168, + "step": 4778 + }, + { + "epoch": 0.5, + "learning_rate": 1.1695614336041108e-05, + "loss": 1.3515, + "step": 4779 + }, + { + "epoch": 0.5, + "learning_rate": 1.169200697426011e-05, + "loss": 1.3214, + "step": 4780 + }, + { + "epoch": 0.5, + "learning_rate": 1.1688399385793652e-05, + "loss": 1.3728, + "step": 4781 + }, + { + "epoch": 0.5, + "learning_rate": 1.1684791571125054e-05, + "loss": 1.3759, + "step": 4782 + }, + { + "epoch": 0.5, + "learning_rate": 1.1681183530737678e-05, + "loss": 1.4955, + "step": 4783 + }, + { + "epoch": 0.5, + "learning_rate": 1.1677575265114904e-05, + "loss": 1.4284, + "step": 4784 + }, + { + "epoch": 0.5, + "learning_rate": 1.1673966774740151e-05, + "loss": 1.3725, + "step": 4785 + }, + { + "epoch": 0.5, + "learning_rate": 1.1670358060096858e-05, + "loss": 1.3612, + "step": 4786 + }, + { + "epoch": 0.5, + "learning_rate": 1.1666749121668506e-05, + "loss": 1.3021, + "step": 4787 + }, + { + "epoch": 0.5, + "learning_rate": 1.1663139959938597e-05, + "loss": 1.4399, + "step": 4788 + }, + { + "epoch": 0.5, + "learning_rate": 1.1659530575390668e-05, + "loss": 1.3511, + "step": 4789 + }, + { + "epoch": 0.5, + "learning_rate": 1.1655920968508276e-05, + "loss": 1.4211, + "step": 4790 + }, + { + "epoch": 0.5, + "learning_rate": 1.1652311139775028e-05, + "loss": 1.343, + "step": 4791 + }, + { + "epoch": 0.5, + "learning_rate": 1.1648701089674541e-05, + "loss": 1.3838, + "step": 4792 + }, + { + "epoch": 0.5, + "learning_rate": 1.164509081869047e-05, + "loss": 1.342, + "step": 4793 + }, + { + "epoch": 0.5, + "learning_rate": 1.1641480327306494e-05, + "loss": 1.3831, + "step": 4794 + }, + { + "epoch": 0.5, + "learning_rate": 1.1637869616006335e-05, + "loss": 1.4102, + "step": 4795 + }, + { + "epoch": 0.5, + "learning_rate": 1.1634258685273732e-05, + "loss": 1.4184, + "step": 4796 + }, + { + "epoch": 0.5, + "learning_rate": 1.1630647535592455e-05, + "loss": 1.3974, + "step": 4797 + }, + { + "epoch": 0.5, + "learning_rate": 1.1627036167446302e-05, + "loss": 1.251, + "step": 4798 + }, + { + "epoch": 0.5, + "learning_rate": 1.1623424581319113e-05, + "loss": 1.3485, + "step": 4799 + }, + { + "epoch": 0.5, + "learning_rate": 1.1619812777694742e-05, + "loss": 1.3544, + "step": 4800 + }, + { + "epoch": 0.5, + "learning_rate": 1.1616200757057076e-05, + "loss": 1.3772, + "step": 4801 + }, + { + "epoch": 0.5, + "learning_rate": 1.1612588519890038e-05, + "loss": 1.3082, + "step": 4802 + }, + { + "epoch": 0.5, + "learning_rate": 1.160897606667757e-05, + "loss": 1.3634, + "step": 4803 + }, + { + "epoch": 0.5, + "learning_rate": 1.1605363397903655e-05, + "loss": 1.3682, + "step": 4804 + }, + { + "epoch": 0.5, + "learning_rate": 1.1601750514052288e-05, + "loss": 1.3258, + "step": 4805 + }, + { + "epoch": 0.5, + "learning_rate": 1.1598137415607511e-05, + "loss": 1.279, + "step": 4806 + }, + { + "epoch": 0.5, + "learning_rate": 1.1594524103053382e-05, + "loss": 1.3759, + "step": 4807 + }, + { + "epoch": 0.5, + "learning_rate": 1.1590910576873995e-05, + "loss": 1.5404, + "step": 4808 + }, + { + "epoch": 0.5, + "learning_rate": 1.1587296837553463e-05, + "loss": 1.4949, + "step": 4809 + }, + { + "epoch": 0.5, + "learning_rate": 1.1583682885575943e-05, + "loss": 1.3501, + "step": 4810 + }, + { + "epoch": 0.5, + "learning_rate": 1.1580068721425608e-05, + "loss": 1.3898, + "step": 4811 + }, + { + "epoch": 0.5, + "learning_rate": 1.157645434558666e-05, + "loss": 1.3265, + "step": 4812 + }, + { + "epoch": 0.5, + "learning_rate": 1.1572839758543338e-05, + "loss": 1.3454, + "step": 4813 + }, + { + "epoch": 0.5, + "learning_rate": 1.1569224960779899e-05, + "loss": 1.4065, + "step": 4814 + }, + { + "epoch": 0.5, + "learning_rate": 1.156560995278064e-05, + "loss": 1.4932, + "step": 4815 + }, + { + "epoch": 0.51, + "learning_rate": 1.156199473502987e-05, + "loss": 1.4224, + "step": 4816 + }, + { + "epoch": 0.51, + "learning_rate": 1.1558379308011937e-05, + "loss": 1.3884, + "step": 4817 + }, + { + "epoch": 0.51, + "learning_rate": 1.1554763672211222e-05, + "loss": 1.3355, + "step": 4818 + }, + { + "epoch": 0.51, + "learning_rate": 1.1551147828112124e-05, + "loss": 1.4281, + "step": 4819 + }, + { + "epoch": 0.51, + "learning_rate": 1.1547531776199072e-05, + "loss": 1.3148, + "step": 4820 + }, + { + "epoch": 0.51, + "learning_rate": 1.1543915516956523e-05, + "loss": 1.3255, + "step": 4821 + }, + { + "epoch": 0.51, + "learning_rate": 1.1540299050868966e-05, + "loss": 1.3361, + "step": 4822 + }, + { + "epoch": 0.51, + "learning_rate": 1.1536682378420912e-05, + "loss": 1.3377, + "step": 4823 + }, + { + "epoch": 0.51, + "learning_rate": 1.1533065500096901e-05, + "loss": 1.4205, + "step": 4824 + }, + { + "epoch": 0.51, + "learning_rate": 1.1529448416381505e-05, + "loss": 1.4193, + "step": 4825 + }, + { + "epoch": 0.51, + "learning_rate": 1.1525831127759322e-05, + "loss": 1.37, + "step": 4826 + }, + { + "epoch": 0.51, + "learning_rate": 1.1522213634714971e-05, + "loss": 1.3642, + "step": 4827 + }, + { + "epoch": 0.51, + "learning_rate": 1.1518595937733103e-05, + "loss": 1.4834, + "step": 4828 + }, + { + "epoch": 0.51, + "learning_rate": 1.1514978037298402e-05, + "loss": 1.2864, + "step": 4829 + }, + { + "epoch": 0.51, + "learning_rate": 1.1511359933895567e-05, + "loss": 1.3468, + "step": 4830 + }, + { + "epoch": 0.51, + "learning_rate": 1.1507741628009337e-05, + "loss": 1.328, + "step": 4831 + }, + { + "epoch": 0.51, + "learning_rate": 1.1504123120124466e-05, + "loss": 1.3489, + "step": 4832 + }, + { + "epoch": 0.51, + "learning_rate": 1.1500504410725746e-05, + "loss": 1.4031, + "step": 4833 + }, + { + "epoch": 0.51, + "learning_rate": 1.149688550029799e-05, + "loss": 1.3482, + "step": 4834 + }, + { + "epoch": 0.51, + "learning_rate": 1.1493266389326037e-05, + "loss": 1.3674, + "step": 4835 + }, + { + "epoch": 0.51, + "learning_rate": 1.1489647078294753e-05, + "loss": 1.2895, + "step": 4836 + }, + { + "epoch": 0.51, + "learning_rate": 1.148602756768904e-05, + "loss": 1.4071, + "step": 4837 + }, + { + "epoch": 0.51, + "learning_rate": 1.1482407857993814e-05, + "loss": 1.5218, + "step": 4838 + }, + { + "epoch": 0.51, + "learning_rate": 1.1478787949694024e-05, + "loss": 1.4577, + "step": 4839 + }, + { + "epoch": 0.51, + "learning_rate": 1.1475167843274643e-05, + "loss": 1.3817, + "step": 4840 + }, + { + "epoch": 0.51, + "learning_rate": 1.1471547539220678e-05, + "loss": 1.3072, + "step": 4841 + }, + { + "epoch": 0.51, + "learning_rate": 1.146792703801715e-05, + "loss": 1.3737, + "step": 4842 + }, + { + "epoch": 0.51, + "learning_rate": 1.1464306340149119e-05, + "loss": 1.4001, + "step": 4843 + }, + { + "epoch": 0.51, + "learning_rate": 1.1460685446101658e-05, + "loss": 1.3963, + "step": 4844 + }, + { + "epoch": 0.51, + "learning_rate": 1.1457064356359882e-05, + "loss": 1.4061, + "step": 4845 + }, + { + "epoch": 0.51, + "learning_rate": 1.145344307140892e-05, + "loss": 1.4211, + "step": 4846 + }, + { + "epoch": 0.51, + "learning_rate": 1.144982159173393e-05, + "loss": 1.3197, + "step": 4847 + }, + { + "epoch": 0.51, + "learning_rate": 1.14461999178201e-05, + "loss": 1.3549, + "step": 4848 + }, + { + "epoch": 0.51, + "learning_rate": 1.1442578050152639e-05, + "loss": 1.3889, + "step": 4849 + }, + { + "epoch": 0.51, + "learning_rate": 1.1438955989216787e-05, + "loss": 1.3847, + "step": 4850 + }, + { + "epoch": 0.51, + "learning_rate": 1.1435333735497803e-05, + "loss": 1.3586, + "step": 4851 + }, + { + "epoch": 0.51, + "learning_rate": 1.1431711289480978e-05, + "loss": 1.503, + "step": 4852 + }, + { + "epoch": 0.51, + "learning_rate": 1.1428088651651627e-05, + "loss": 1.3654, + "step": 4853 + }, + { + "epoch": 0.51, + "learning_rate": 1.1424465822495092e-05, + "loss": 1.3741, + "step": 4854 + }, + { + "epoch": 0.51, + "learning_rate": 1.1420842802496737e-05, + "loss": 1.5437, + "step": 4855 + }, + { + "epoch": 0.51, + "learning_rate": 1.1417219592141953e-05, + "loss": 1.2179, + "step": 4856 + }, + { + "epoch": 0.51, + "learning_rate": 1.1413596191916159e-05, + "loss": 1.3939, + "step": 4857 + }, + { + "epoch": 0.51, + "learning_rate": 1.1409972602304796e-05, + "loss": 1.3383, + "step": 4858 + }, + { + "epoch": 0.51, + "learning_rate": 1.140634882379333e-05, + "loss": 1.3664, + "step": 4859 + }, + { + "epoch": 0.51, + "learning_rate": 1.1402724856867258e-05, + "loss": 1.4002, + "step": 4860 + }, + { + "epoch": 0.51, + "learning_rate": 1.1399100702012098e-05, + "loss": 1.2975, + "step": 4861 + }, + { + "epoch": 0.51, + "learning_rate": 1.1395476359713394e-05, + "loss": 1.3564, + "step": 4862 + }, + { + "epoch": 0.51, + "learning_rate": 1.1391851830456708e-05, + "loss": 1.3574, + "step": 4863 + }, + { + "epoch": 0.51, + "learning_rate": 1.1388227114727644e-05, + "loss": 1.3407, + "step": 4864 + }, + { + "epoch": 0.51, + "learning_rate": 1.1384602213011815e-05, + "loss": 1.3603, + "step": 4865 + }, + { + "epoch": 0.51, + "learning_rate": 1.1380977125794866e-05, + "loss": 1.3465, + "step": 4866 + }, + { + "epoch": 0.51, + "learning_rate": 1.1377351853562461e-05, + "loss": 1.3744, + "step": 4867 + }, + { + "epoch": 0.51, + "learning_rate": 1.1373726396800304e-05, + "loss": 1.3248, + "step": 4868 + }, + { + "epoch": 0.51, + "learning_rate": 1.1370100755994102e-05, + "loss": 1.3352, + "step": 4869 + }, + { + "epoch": 0.51, + "learning_rate": 1.1366474931629603e-05, + "loss": 1.3299, + "step": 4870 + }, + { + "epoch": 0.51, + "learning_rate": 1.1362848924192575e-05, + "loss": 1.344, + "step": 4871 + }, + { + "epoch": 0.51, + "learning_rate": 1.1359222734168809e-05, + "loss": 1.3209, + "step": 4872 + }, + { + "epoch": 0.51, + "learning_rate": 1.135559636204412e-05, + "loss": 1.3927, + "step": 4873 + }, + { + "epoch": 0.51, + "learning_rate": 1.1351969808304349e-05, + "loss": 1.3717, + "step": 4874 + }, + { + "epoch": 0.51, + "learning_rate": 1.1348343073435362e-05, + "loss": 1.3813, + "step": 4875 + }, + { + "epoch": 0.51, + "learning_rate": 1.1344716157923046e-05, + "loss": 1.236, + "step": 4876 + }, + { + "epoch": 0.51, + "learning_rate": 1.1341089062253319e-05, + "loss": 1.2591, + "step": 4877 + }, + { + "epoch": 0.51, + "learning_rate": 1.1337461786912112e-05, + "loss": 1.3211, + "step": 4878 + }, + { + "epoch": 0.51, + "learning_rate": 1.1333834332385394e-05, + "loss": 1.4534, + "step": 4879 + }, + { + "epoch": 0.51, + "learning_rate": 1.1330206699159145e-05, + "loss": 1.346, + "step": 4880 + }, + { + "epoch": 0.51, + "learning_rate": 1.132657888771938e-05, + "loss": 1.3952, + "step": 4881 + }, + { + "epoch": 0.51, + "learning_rate": 1.1322950898552125e-05, + "loss": 1.3008, + "step": 4882 + }, + { + "epoch": 0.51, + "learning_rate": 1.1319322732143445e-05, + "loss": 1.3201, + "step": 4883 + }, + { + "epoch": 0.51, + "learning_rate": 1.1315694388979416e-05, + "loss": 1.3761, + "step": 4884 + }, + { + "epoch": 0.51, + "learning_rate": 1.1312065869546147e-05, + "loss": 1.343, + "step": 4885 + }, + { + "epoch": 0.51, + "learning_rate": 1.1308437174329761e-05, + "loss": 1.3741, + "step": 4886 + }, + { + "epoch": 0.51, + "learning_rate": 1.1304808303816413e-05, + "loss": 1.402, + "step": 4887 + }, + { + "epoch": 0.51, + "learning_rate": 1.130117925849228e-05, + "loss": 1.3834, + "step": 4888 + }, + { + "epoch": 0.51, + "learning_rate": 1.1297550038843559e-05, + "loss": 1.3342, + "step": 4889 + }, + { + "epoch": 0.51, + "learning_rate": 1.1293920645356471e-05, + "loss": 1.3207, + "step": 4890 + }, + { + "epoch": 0.51, + "learning_rate": 1.1290291078517264e-05, + "loss": 1.4274, + "step": 4891 + }, + { + "epoch": 0.51, + "learning_rate": 1.1286661338812203e-05, + "loss": 1.328, + "step": 4892 + }, + { + "epoch": 0.51, + "learning_rate": 1.1283031426727584e-05, + "loss": 1.3823, + "step": 4893 + }, + { + "epoch": 0.51, + "learning_rate": 1.127940134274972e-05, + "loss": 1.3612, + "step": 4894 + }, + { + "epoch": 0.51, + "learning_rate": 1.127577108736495e-05, + "loss": 1.375, + "step": 4895 + }, + { + "epoch": 0.51, + "learning_rate": 1.1272140661059636e-05, + "loss": 1.3531, + "step": 4896 + }, + { + "epoch": 0.51, + "learning_rate": 1.1268510064320155e-05, + "loss": 1.3636, + "step": 4897 + }, + { + "epoch": 0.51, + "learning_rate": 1.1264879297632923e-05, + "loss": 1.3524, + "step": 4898 + }, + { + "epoch": 0.51, + "learning_rate": 1.1261248361484363e-05, + "loss": 1.3865, + "step": 4899 + }, + { + "epoch": 0.51, + "learning_rate": 1.125761725636093e-05, + "loss": 1.4069, + "step": 4900 + }, + { + "epoch": 0.51, + "learning_rate": 1.1253985982749098e-05, + "loss": 1.4643, + "step": 4901 + }, + { + "epoch": 0.51, + "learning_rate": 1.1250354541135364e-05, + "loss": 1.4506, + "step": 4902 + }, + { + "epoch": 0.51, + "learning_rate": 1.124672293200625e-05, + "loss": 1.3857, + "step": 4903 + }, + { + "epoch": 0.51, + "learning_rate": 1.1243091155848295e-05, + "loss": 1.3554, + "step": 4904 + }, + { + "epoch": 0.51, + "learning_rate": 1.1239459213148065e-05, + "loss": 1.4071, + "step": 4905 + }, + { + "epoch": 0.51, + "learning_rate": 1.1235827104392148e-05, + "loss": 1.3981, + "step": 4906 + }, + { + "epoch": 0.51, + "learning_rate": 1.1232194830067153e-05, + "loss": 1.4913, + "step": 4907 + }, + { + "epoch": 0.51, + "learning_rate": 1.1228562390659712e-05, + "loss": 1.3343, + "step": 4908 + }, + { + "epoch": 0.51, + "learning_rate": 1.1224929786656474e-05, + "loss": 1.3832, + "step": 4909 + }, + { + "epoch": 0.51, + "learning_rate": 1.122129701854412e-05, + "loss": 1.367, + "step": 4910 + }, + { + "epoch": 0.51, + "learning_rate": 1.1217664086809345e-05, + "loss": 1.4108, + "step": 4911 + }, + { + "epoch": 0.52, + "learning_rate": 1.1214030991938872e-05, + "loss": 1.3981, + "step": 4912 + }, + { + "epoch": 0.52, + "learning_rate": 1.1210397734419436e-05, + "loss": 1.5266, + "step": 4913 + }, + { + "epoch": 0.52, + "learning_rate": 1.1206764314737806e-05, + "loss": 1.337, + "step": 4914 + }, + { + "epoch": 0.52, + "learning_rate": 1.1203130733380765e-05, + "loss": 1.3784, + "step": 4915 + }, + { + "epoch": 0.52, + "learning_rate": 1.1199496990835117e-05, + "loss": 1.3048, + "step": 4916 + }, + { + "epoch": 0.52, + "learning_rate": 1.1195863087587692e-05, + "loss": 1.2977, + "step": 4917 + }, + { + "epoch": 0.52, + "learning_rate": 1.1192229024125344e-05, + "loss": 1.3304, + "step": 4918 + }, + { + "epoch": 0.52, + "learning_rate": 1.1188594800934938e-05, + "loss": 1.4102, + "step": 4919 + }, + { + "epoch": 0.52, + "learning_rate": 1.1184960418503366e-05, + "loss": 1.3932, + "step": 4920 + }, + { + "epoch": 0.52, + "learning_rate": 1.1181325877317547e-05, + "loss": 1.4985, + "step": 4921 + }, + { + "epoch": 0.52, + "learning_rate": 1.1177691177864415e-05, + "loss": 1.4596, + "step": 4922 + }, + { + "epoch": 0.52, + "learning_rate": 1.1174056320630924e-05, + "loss": 1.3559, + "step": 4923 + }, + { + "epoch": 0.52, + "learning_rate": 1.117042130610405e-05, + "loss": 1.4128, + "step": 4924 + }, + { + "epoch": 0.52, + "learning_rate": 1.1166786134770795e-05, + "loss": 1.3343, + "step": 4925 + }, + { + "epoch": 0.52, + "learning_rate": 1.116315080711818e-05, + "loss": 1.332, + "step": 4926 + }, + { + "epoch": 0.52, + "learning_rate": 1.115951532363324e-05, + "loss": 1.3616, + "step": 4927 + }, + { + "epoch": 0.52, + "learning_rate": 1.1155879684803041e-05, + "loss": 1.4074, + "step": 4928 + }, + { + "epoch": 0.52, + "learning_rate": 1.1152243891114665e-05, + "loss": 1.303, + "step": 4929 + }, + { + "epoch": 0.52, + "learning_rate": 1.1148607943055212e-05, + "loss": 1.4799, + "step": 4930 + }, + { + "epoch": 0.52, + "learning_rate": 1.1144971841111807e-05, + "loss": 1.3881, + "step": 4931 + }, + { + "epoch": 0.52, + "learning_rate": 1.1141335585771593e-05, + "loss": 1.338, + "step": 4932 + }, + { + "epoch": 0.52, + "learning_rate": 1.1137699177521738e-05, + "loss": 1.3289, + "step": 4933 + }, + { + "epoch": 0.52, + "learning_rate": 1.1134062616849426e-05, + "loss": 1.377, + "step": 4934 + }, + { + "epoch": 0.52, + "learning_rate": 1.1130425904241862e-05, + "loss": 1.3596, + "step": 4935 + }, + { + "epoch": 0.52, + "learning_rate": 1.112678904018627e-05, + "loss": 1.4264, + "step": 4936 + }, + { + "epoch": 0.52, + "learning_rate": 1.1123152025169898e-05, + "loss": 1.3526, + "step": 4937 + }, + { + "epoch": 0.52, + "learning_rate": 1.1119514859680016e-05, + "loss": 1.3271, + "step": 4938 + }, + { + "epoch": 0.52, + "learning_rate": 1.1115877544203905e-05, + "loss": 1.3907, + "step": 4939 + }, + { + "epoch": 0.52, + "learning_rate": 1.1112240079228878e-05, + "loss": 1.3415, + "step": 4940 + }, + { + "epoch": 0.52, + "learning_rate": 1.1108602465242258e-05, + "loss": 1.3875, + "step": 4941 + }, + { + "epoch": 0.52, + "learning_rate": 1.110496470273139e-05, + "loss": 1.3964, + "step": 4942 + }, + { + "epoch": 0.52, + "learning_rate": 1.1101326792183645e-05, + "loss": 1.3448, + "step": 4943 + }, + { + "epoch": 0.52, + "learning_rate": 1.1097688734086407e-05, + "loss": 1.3522, + "step": 4944 + }, + { + "epoch": 0.52, + "learning_rate": 1.1094050528927082e-05, + "loss": 1.2742, + "step": 4945 + }, + { + "epoch": 0.52, + "learning_rate": 1.1090412177193097e-05, + "loss": 1.417, + "step": 4946 + }, + { + "epoch": 0.52, + "learning_rate": 1.1086773679371898e-05, + "loss": 1.3993, + "step": 4947 + }, + { + "epoch": 0.52, + "learning_rate": 1.108313503595095e-05, + "loss": 1.3783, + "step": 4948 + }, + { + "epoch": 0.52, + "learning_rate": 1.1079496247417736e-05, + "loss": 1.3975, + "step": 4949 + }, + { + "epoch": 0.52, + "learning_rate": 1.1075857314259763e-05, + "loss": 1.4256, + "step": 4950 + }, + { + "epoch": 0.52, + "learning_rate": 1.1072218236964551e-05, + "loss": 1.3547, + "step": 4951 + }, + { + "epoch": 0.52, + "learning_rate": 1.106857901601965e-05, + "loss": 1.4243, + "step": 4952 + }, + { + "epoch": 0.52, + "learning_rate": 1.1064939651912612e-05, + "loss": 1.4259, + "step": 4953 + }, + { + "epoch": 0.52, + "learning_rate": 1.1061300145131027e-05, + "loss": 1.4323, + "step": 4954 + }, + { + "epoch": 0.52, + "learning_rate": 1.1057660496162488e-05, + "loss": 1.3608, + "step": 4955 + }, + { + "epoch": 0.52, + "learning_rate": 1.1054020705494622e-05, + "loss": 1.3703, + "step": 4956 + }, + { + "epoch": 0.52, + "learning_rate": 1.105038077361506e-05, + "loss": 1.3953, + "step": 4957 + }, + { + "epoch": 0.52, + "learning_rate": 1.1046740701011467e-05, + "loss": 1.392, + "step": 4958 + }, + { + "epoch": 0.52, + "learning_rate": 1.1043100488171513e-05, + "loss": 1.4101, + "step": 4959 + }, + { + "epoch": 0.52, + "learning_rate": 1.1039460135582894e-05, + "loss": 1.5432, + "step": 4960 + }, + { + "epoch": 0.52, + "learning_rate": 1.1035819643733326e-05, + "loss": 1.3822, + "step": 4961 + }, + { + "epoch": 0.52, + "learning_rate": 1.103217901311054e-05, + "loss": 1.3816, + "step": 4962 + }, + { + "epoch": 0.52, + "learning_rate": 1.1028538244202287e-05, + "loss": 1.3137, + "step": 4963 + }, + { + "epoch": 0.52, + "learning_rate": 1.102489733749634e-05, + "loss": 1.3791, + "step": 4964 + }, + { + "epoch": 0.52, + "learning_rate": 1.102125629348048e-05, + "loss": 1.3751, + "step": 4965 + }, + { + "epoch": 0.52, + "learning_rate": 1.1017615112642518e-05, + "loss": 1.3287, + "step": 4966 + }, + { + "epoch": 0.52, + "learning_rate": 1.1013973795470277e-05, + "loss": 1.3187, + "step": 4967 + }, + { + "epoch": 0.52, + "learning_rate": 1.1010332342451602e-05, + "loss": 1.3174, + "step": 4968 + }, + { + "epoch": 0.52, + "learning_rate": 1.1006690754074351e-05, + "loss": 1.3544, + "step": 4969 + }, + { + "epoch": 0.52, + "learning_rate": 1.1003049030826404e-05, + "loss": 1.3789, + "step": 4970 + }, + { + "epoch": 0.52, + "learning_rate": 1.0999407173195662e-05, + "loss": 1.4561, + "step": 4971 + }, + { + "epoch": 0.52, + "learning_rate": 1.0995765181670039e-05, + "loss": 1.3963, + "step": 4972 + }, + { + "epoch": 0.52, + "learning_rate": 1.0992123056737464e-05, + "loss": 1.3519, + "step": 4973 + }, + { + "epoch": 0.52, + "learning_rate": 1.0988480798885892e-05, + "loss": 1.3945, + "step": 4974 + }, + { + "epoch": 0.52, + "learning_rate": 1.0984838408603294e-05, + "loss": 1.4572, + "step": 4975 + }, + { + "epoch": 0.52, + "eval_loss": 1.4313459396362305, + "eval_runtime": 77.4808, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 4975 + }, + { + "epoch": 0.52, + "learning_rate": 1.0981195886377652e-05, + "loss": 1.3493, + "step": 4976 + }, + { + "epoch": 0.52, + "learning_rate": 1.0977553232696972e-05, + "loss": 1.3734, + "step": 4977 + }, + { + "epoch": 0.52, + "learning_rate": 1.0973910448049273e-05, + "loss": 1.3484, + "step": 4978 + }, + { + "epoch": 0.52, + "learning_rate": 1.09702675329226e-05, + "loss": 1.4288, + "step": 4979 + }, + { + "epoch": 0.52, + "learning_rate": 1.096662448780501e-05, + "loss": 1.3748, + "step": 4980 + }, + { + "epoch": 0.52, + "learning_rate": 1.0962981313184575e-05, + "loss": 1.3485, + "step": 4981 + }, + { + "epoch": 0.52, + "learning_rate": 1.0959338009549383e-05, + "loss": 1.3606, + "step": 4982 + }, + { + "epoch": 0.52, + "learning_rate": 1.095569457738755e-05, + "loss": 1.3963, + "step": 4983 + }, + { + "epoch": 0.52, + "learning_rate": 1.09520510171872e-05, + "loss": 1.2986, + "step": 4984 + }, + { + "epoch": 0.52, + "learning_rate": 1.0948407329436474e-05, + "loss": 1.3505, + "step": 4985 + }, + { + "epoch": 0.52, + "learning_rate": 1.0944763514623535e-05, + "loss": 1.4649, + "step": 4986 + }, + { + "epoch": 0.52, + "learning_rate": 1.0941119573236564e-05, + "loss": 1.4743, + "step": 4987 + }, + { + "epoch": 0.52, + "learning_rate": 1.0937475505763745e-05, + "loss": 1.3934, + "step": 4988 + }, + { + "epoch": 0.52, + "learning_rate": 1.09338313126933e-05, + "loss": 1.4225, + "step": 4989 + }, + { + "epoch": 0.52, + "learning_rate": 1.0930186994513453e-05, + "loss": 1.3626, + "step": 4990 + }, + { + "epoch": 0.52, + "learning_rate": 1.0926542551712446e-05, + "loss": 1.3614, + "step": 4991 + }, + { + "epoch": 0.52, + "learning_rate": 1.0922897984778546e-05, + "loss": 1.3766, + "step": 4992 + }, + { + "epoch": 0.52, + "learning_rate": 1.0919253294200027e-05, + "loss": 1.3295, + "step": 4993 + }, + { + "epoch": 0.52, + "learning_rate": 1.091560848046519e-05, + "loss": 1.3802, + "step": 4994 + }, + { + "epoch": 0.52, + "learning_rate": 1.091196354406234e-05, + "loss": 1.2976, + "step": 4995 + }, + { + "epoch": 0.52, + "learning_rate": 1.090831848547981e-05, + "loss": 1.3928, + "step": 4996 + }, + { + "epoch": 0.52, + "learning_rate": 1.0904673305205937e-05, + "loss": 1.3717, + "step": 4997 + }, + { + "epoch": 0.52, + "learning_rate": 1.0901028003729089e-05, + "loss": 1.3164, + "step": 4998 + }, + { + "epoch": 0.52, + "learning_rate": 1.0897382581537638e-05, + "loss": 1.3462, + "step": 4999 + }, + { + "epoch": 0.52, + "learning_rate": 1.0893737039119981e-05, + "loss": 1.3643, + "step": 5000 + }, + { + "epoch": 0.52, + "learning_rate": 1.089009137696452e-05, + "loss": 1.3452, + "step": 5001 + }, + { + "epoch": 0.52, + "learning_rate": 1.0886445595559686e-05, + "loss": 1.358, + "step": 5002 + }, + { + "epoch": 0.52, + "learning_rate": 1.0882799695393922e-05, + "loss": 1.4569, + "step": 5003 + }, + { + "epoch": 0.52, + "learning_rate": 1.0879153676955681e-05, + "loss": 1.2832, + "step": 5004 + }, + { + "epoch": 0.52, + "learning_rate": 1.0875507540733435e-05, + "loss": 1.4089, + "step": 5005 + }, + { + "epoch": 0.52, + "learning_rate": 1.087186128721567e-05, + "loss": 1.3178, + "step": 5006 + }, + { + "epoch": 0.53, + "learning_rate": 1.0868214916890902e-05, + "loss": 1.4883, + "step": 5007 + }, + { + "epoch": 0.53, + "learning_rate": 1.0864568430247638e-05, + "loss": 1.3991, + "step": 5008 + }, + { + "epoch": 0.53, + "learning_rate": 1.0860921827774422e-05, + "loss": 1.4507, + "step": 5009 + }, + { + "epoch": 0.53, + "learning_rate": 1.08572751099598e-05, + "loss": 1.3578, + "step": 5010 + }, + { + "epoch": 0.53, + "learning_rate": 1.0853628277292341e-05, + "loss": 1.4231, + "step": 5011 + }, + { + "epoch": 0.53, + "learning_rate": 1.0849981330260624e-05, + "loss": 1.4835, + "step": 5012 + }, + { + "epoch": 0.53, + "learning_rate": 1.084633426935325e-05, + "loss": 1.4511, + "step": 5013 + }, + { + "epoch": 0.53, + "learning_rate": 1.084268709505883e-05, + "loss": 1.3889, + "step": 5014 + }, + { + "epoch": 0.53, + "learning_rate": 1.0839039807865992e-05, + "loss": 1.355, + "step": 5015 + }, + { + "epoch": 0.53, + "learning_rate": 1.0835392408263375e-05, + "loss": 1.4829, + "step": 5016 + }, + { + "epoch": 0.53, + "learning_rate": 1.0831744896739643e-05, + "loss": 1.3019, + "step": 5017 + }, + { + "epoch": 0.53, + "learning_rate": 1.0828097273783465e-05, + "loss": 1.3418, + "step": 5018 + }, + { + "epoch": 0.53, + "learning_rate": 1.082444953988353e-05, + "loss": 1.4276, + "step": 5019 + }, + { + "epoch": 0.53, + "learning_rate": 1.0820801695528537e-05, + "loss": 1.2816, + "step": 5020 + }, + { + "epoch": 0.53, + "learning_rate": 1.081715374120721e-05, + "loss": 1.5144, + "step": 5021 + }, + { + "epoch": 0.53, + "learning_rate": 1.0813505677408278e-05, + "loss": 1.4063, + "step": 5022 + }, + { + "epoch": 0.53, + "learning_rate": 1.0809857504620487e-05, + "loss": 1.4011, + "step": 5023 + }, + { + "epoch": 0.53, + "learning_rate": 1.0806209223332598e-05, + "loss": 1.373, + "step": 5024 + }, + { + "epoch": 0.53, + "learning_rate": 1.0802560834033388e-05, + "loss": 1.6259, + "step": 5025 + }, + { + "epoch": 0.53, + "learning_rate": 1.0798912337211648e-05, + "loss": 1.4487, + "step": 5026 + }, + { + "epoch": 0.53, + "learning_rate": 1.0795263733356184e-05, + "loss": 1.3056, + "step": 5027 + }, + { + "epoch": 0.53, + "learning_rate": 1.079161502295581e-05, + "loss": 1.2871, + "step": 5028 + }, + { + "epoch": 0.53, + "learning_rate": 1.0787966206499363e-05, + "loss": 1.413, + "step": 5029 + }, + { + "epoch": 0.53, + "learning_rate": 1.0784317284475694e-05, + "loss": 1.3682, + "step": 5030 + }, + { + "epoch": 0.53, + "learning_rate": 1.0780668257373659e-05, + "loss": 1.493, + "step": 5031 + }, + { + "epoch": 0.53, + "learning_rate": 1.0777019125682136e-05, + "loss": 1.6823, + "step": 5032 + }, + { + "epoch": 0.53, + "learning_rate": 1.0773369889890015e-05, + "loss": 1.358, + "step": 5033 + }, + { + "epoch": 0.53, + "learning_rate": 1.07697205504862e-05, + "loss": 1.3532, + "step": 5034 + }, + { + "epoch": 0.53, + "learning_rate": 1.0766071107959608e-05, + "loss": 1.3432, + "step": 5035 + }, + { + "epoch": 0.53, + "learning_rate": 1.0762421562799173e-05, + "loss": 1.3575, + "step": 5036 + }, + { + "epoch": 0.53, + "learning_rate": 1.0758771915493838e-05, + "loss": 1.0924, + "step": 5037 + }, + { + "epoch": 0.53, + "learning_rate": 1.075512216653256e-05, + "loss": 0.7405, + "step": 5038 + }, + { + "epoch": 0.53, + "learning_rate": 1.0751472316404315e-05, + "loss": 0.7134, + "step": 5039 + }, + { + "epoch": 0.53, + "learning_rate": 1.0747822365598088e-05, + "loss": 1.0904, + "step": 5040 + }, + { + "epoch": 0.53, + "learning_rate": 1.0744172314602881e-05, + "loss": 1.4353, + "step": 5041 + }, + { + "epoch": 0.53, + "learning_rate": 1.0740522163907702e-05, + "loss": 1.361, + "step": 5042 + }, + { + "epoch": 0.53, + "learning_rate": 1.073687191400158e-05, + "loss": 1.4024, + "step": 5043 + }, + { + "epoch": 0.53, + "learning_rate": 1.0733221565373557e-05, + "loss": 1.328, + "step": 5044 + }, + { + "epoch": 0.53, + "learning_rate": 1.0729571118512683e-05, + "loss": 1.3309, + "step": 5045 + }, + { + "epoch": 0.53, + "learning_rate": 1.0725920573908024e-05, + "loss": 1.3819, + "step": 5046 + }, + { + "epoch": 0.53, + "learning_rate": 1.0722269932048659e-05, + "loss": 1.3467, + "step": 5047 + }, + { + "epoch": 0.53, + "learning_rate": 1.0718619193423683e-05, + "loss": 1.3036, + "step": 5048 + }, + { + "epoch": 0.53, + "learning_rate": 1.07149683585222e-05, + "loss": 1.3297, + "step": 5049 + }, + { + "epoch": 0.53, + "learning_rate": 1.0711317427833328e-05, + "loss": 1.3439, + "step": 5050 + }, + { + "epoch": 0.53, + "learning_rate": 1.0707666401846192e-05, + "loss": 1.4167, + "step": 5051 + }, + { + "epoch": 0.53, + "learning_rate": 1.0704015281049944e-05, + "loss": 1.4217, + "step": 5052 + }, + { + "epoch": 0.53, + "learning_rate": 1.070036406593374e-05, + "loss": 1.3394, + "step": 5053 + }, + { + "epoch": 0.53, + "learning_rate": 1.0696712756986745e-05, + "loss": 1.3242, + "step": 5054 + }, + { + "epoch": 0.53, + "learning_rate": 1.0693061354698143e-05, + "loss": 1.3957, + "step": 5055 + }, + { + "epoch": 0.53, + "learning_rate": 1.0689409859557123e-05, + "loss": 1.37, + "step": 5056 + }, + { + "epoch": 0.53, + "learning_rate": 1.0685758272052902e-05, + "loss": 1.4524, + "step": 5057 + }, + { + "epoch": 0.53, + "learning_rate": 1.0682106592674688e-05, + "loss": 1.528, + "step": 5058 + }, + { + "epoch": 0.53, + "learning_rate": 1.0678454821911719e-05, + "loss": 1.3613, + "step": 5059 + }, + { + "epoch": 0.53, + "learning_rate": 1.0674802960253234e-05, + "loss": 1.308, + "step": 5060 + }, + { + "epoch": 0.53, + "learning_rate": 1.0671151008188494e-05, + "loss": 1.3343, + "step": 5061 + }, + { + "epoch": 0.53, + "learning_rate": 1.066749896620676e-05, + "loss": 1.365, + "step": 5062 + }, + { + "epoch": 0.53, + "learning_rate": 1.0663846834797316e-05, + "loss": 1.4077, + "step": 5063 + }, + { + "epoch": 0.53, + "learning_rate": 1.0660194614449455e-05, + "loss": 1.324, + "step": 5064 + }, + { + "epoch": 0.53, + "learning_rate": 1.0656542305652478e-05, + "loss": 1.3623, + "step": 5065 + }, + { + "epoch": 0.53, + "learning_rate": 1.0652889908895701e-05, + "loss": 1.4079, + "step": 5066 + }, + { + "epoch": 0.53, + "learning_rate": 1.0649237424668451e-05, + "loss": 1.3089, + "step": 5067 + }, + { + "epoch": 0.53, + "learning_rate": 1.0645584853460069e-05, + "loss": 1.3967, + "step": 5068 + }, + { + "epoch": 0.53, + "learning_rate": 1.0641932195759905e-05, + "loss": 1.3639, + "step": 5069 + }, + { + "epoch": 0.53, + "learning_rate": 1.0638279452057319e-05, + "loss": 1.5919, + "step": 5070 + }, + { + "epoch": 0.53, + "learning_rate": 1.0634626622841686e-05, + "loss": 1.3348, + "step": 5071 + }, + { + "epoch": 0.53, + "learning_rate": 1.0630973708602395e-05, + "loss": 1.3146, + "step": 5072 + }, + { + "epoch": 0.53, + "learning_rate": 1.0627320709828836e-05, + "loss": 1.3375, + "step": 5073 + }, + { + "epoch": 0.53, + "learning_rate": 1.062366762701042e-05, + "loss": 1.3908, + "step": 5074 + }, + { + "epoch": 0.53, + "learning_rate": 1.0620014460636568e-05, + "loss": 1.3726, + "step": 5075 + }, + { + "epoch": 0.53, + "learning_rate": 1.061636121119671e-05, + "loss": 1.2348, + "step": 5076 + }, + { + "epoch": 0.53, + "learning_rate": 1.0612707879180284e-05, + "loss": 1.2957, + "step": 5077 + }, + { + "epoch": 0.53, + "learning_rate": 1.0609054465076749e-05, + "loss": 1.4202, + "step": 5078 + }, + { + "epoch": 0.53, + "learning_rate": 1.060540096937556e-05, + "loss": 1.5809, + "step": 5079 + }, + { + "epoch": 0.53, + "learning_rate": 1.0601747392566202e-05, + "loss": 1.3741, + "step": 5080 + }, + { + "epoch": 0.53, + "learning_rate": 1.059809373513815e-05, + "loss": 1.3537, + "step": 5081 + }, + { + "epoch": 0.53, + "learning_rate": 1.0594439997580907e-05, + "loss": 1.332, + "step": 5082 + }, + { + "epoch": 0.53, + "learning_rate": 1.0590786180383981e-05, + "loss": 1.3267, + "step": 5083 + }, + { + "epoch": 0.53, + "learning_rate": 1.0587132284036883e-05, + "loss": 1.3552, + "step": 5084 + }, + { + "epoch": 0.53, + "learning_rate": 1.0583478309029143e-05, + "loss": 1.2837, + "step": 5085 + }, + { + "epoch": 0.53, + "learning_rate": 1.0579824255850304e-05, + "loss": 1.4311, + "step": 5086 + }, + { + "epoch": 0.53, + "learning_rate": 1.0576170124989915e-05, + "loss": 1.4394, + "step": 5087 + }, + { + "epoch": 0.53, + "learning_rate": 1.0572515916937531e-05, + "loss": 1.3185, + "step": 5088 + }, + { + "epoch": 0.53, + "learning_rate": 1.0568861632182723e-05, + "loss": 1.4212, + "step": 5089 + }, + { + "epoch": 0.53, + "learning_rate": 1.0565207271215075e-05, + "loss": 1.0951, + "step": 5090 + }, + { + "epoch": 0.53, + "learning_rate": 1.0561552834524176e-05, + "loss": 1.4174, + "step": 5091 + }, + { + "epoch": 0.53, + "learning_rate": 1.0557898322599624e-05, + "loss": 1.3349, + "step": 5092 + }, + { + "epoch": 0.53, + "learning_rate": 1.0554243735931031e-05, + "loss": 1.399, + "step": 5093 + }, + { + "epoch": 0.53, + "learning_rate": 1.055058907500802e-05, + "loss": 1.4016, + "step": 5094 + }, + { + "epoch": 0.53, + "learning_rate": 1.0546934340320219e-05, + "loss": 1.3227, + "step": 5095 + }, + { + "epoch": 0.53, + "learning_rate": 1.0543279532357269e-05, + "loss": 1.4017, + "step": 5096 + }, + { + "epoch": 0.53, + "learning_rate": 1.053962465160882e-05, + "loss": 1.3937, + "step": 5097 + }, + { + "epoch": 0.53, + "learning_rate": 1.0535969698564532e-05, + "loss": 1.2405, + "step": 5098 + }, + { + "epoch": 0.53, + "learning_rate": 1.0532314673714081e-05, + "loss": 1.2939, + "step": 5099 + }, + { + "epoch": 0.53, + "learning_rate": 1.0528659577547136e-05, + "loss": 1.4165, + "step": 5100 + }, + { + "epoch": 0.53, + "learning_rate": 1.0525004410553394e-05, + "loss": 1.309, + "step": 5101 + }, + { + "epoch": 0.54, + "learning_rate": 1.0521349173222549e-05, + "loss": 1.4078, + "step": 5102 + }, + { + "epoch": 0.54, + "learning_rate": 1.0517693866044312e-05, + "loss": 1.4026, + "step": 5103 + }, + { + "epoch": 0.54, + "learning_rate": 1.0514038489508396e-05, + "loss": 1.3098, + "step": 5104 + }, + { + "epoch": 0.54, + "learning_rate": 1.0510383044104533e-05, + "loss": 1.2886, + "step": 5105 + }, + { + "epoch": 0.54, + "learning_rate": 1.0506727530322454e-05, + "loss": 1.3114, + "step": 5106 + }, + { + "epoch": 0.54, + "learning_rate": 1.0503071948651908e-05, + "loss": 1.2823, + "step": 5107 + }, + { + "epoch": 0.54, + "learning_rate": 1.0499416299582643e-05, + "loss": 1.4654, + "step": 5108 + }, + { + "epoch": 0.54, + "learning_rate": 1.0495760583604431e-05, + "loss": 1.4043, + "step": 5109 + }, + { + "epoch": 0.54, + "learning_rate": 1.0492104801207035e-05, + "loss": 1.3113, + "step": 5110 + }, + { + "epoch": 0.54, + "learning_rate": 1.0488448952880243e-05, + "loss": 1.3285, + "step": 5111 + }, + { + "epoch": 0.54, + "learning_rate": 1.048479303911384e-05, + "loss": 1.3918, + "step": 5112 + }, + { + "epoch": 0.54, + "learning_rate": 1.0481137060397623e-05, + "loss": 1.346, + "step": 5113 + }, + { + "epoch": 0.54, + "learning_rate": 1.0477481017221407e-05, + "loss": 1.3777, + "step": 5114 + }, + { + "epoch": 0.54, + "learning_rate": 1.0473824910075003e-05, + "loss": 1.3494, + "step": 5115 + }, + { + "epoch": 0.54, + "learning_rate": 1.0470168739448232e-05, + "loss": 1.4173, + "step": 5116 + }, + { + "epoch": 0.54, + "learning_rate": 1.0466512505830932e-05, + "loss": 1.4313, + "step": 5117 + }, + { + "epoch": 0.54, + "learning_rate": 1.0462856209712944e-05, + "loss": 1.335, + "step": 5118 + }, + { + "epoch": 0.54, + "learning_rate": 1.0459199851584117e-05, + "loss": 1.37, + "step": 5119 + }, + { + "epoch": 0.54, + "learning_rate": 1.0455543431934307e-05, + "loss": 1.3504, + "step": 5120 + }, + { + "epoch": 0.54, + "learning_rate": 1.0451886951253381e-05, + "loss": 1.4148, + "step": 5121 + }, + { + "epoch": 0.54, + "learning_rate": 1.0448230410031218e-05, + "loss": 1.3974, + "step": 5122 + }, + { + "epoch": 0.54, + "learning_rate": 1.0444573808757694e-05, + "loss": 1.3644, + "step": 5123 + }, + { + "epoch": 0.54, + "learning_rate": 1.0440917147922705e-05, + "loss": 1.4024, + "step": 5124 + }, + { + "epoch": 0.54, + "learning_rate": 1.0437260428016143e-05, + "loss": 1.3925, + "step": 5125 + }, + { + "epoch": 0.54, + "learning_rate": 1.0433603649527923e-05, + "loss": 1.2907, + "step": 5126 + }, + { + "epoch": 0.54, + "learning_rate": 1.0429946812947953e-05, + "loss": 1.3453, + "step": 5127 + }, + { + "epoch": 0.54, + "learning_rate": 1.0426289918766157e-05, + "loss": 1.3856, + "step": 5128 + }, + { + "epoch": 0.54, + "learning_rate": 1.0422632967472465e-05, + "loss": 1.3309, + "step": 5129 + }, + { + "epoch": 0.54, + "learning_rate": 1.0418975959556819e-05, + "loss": 1.3757, + "step": 5130 + }, + { + "epoch": 0.54, + "learning_rate": 1.0415318895509152e-05, + "loss": 1.406, + "step": 5131 + }, + { + "epoch": 0.54, + "learning_rate": 1.041166177581943e-05, + "loss": 1.3265, + "step": 5132 + }, + { + "epoch": 0.54, + "learning_rate": 1.0408004600977606e-05, + "loss": 1.3377, + "step": 5133 + }, + { + "epoch": 0.54, + "learning_rate": 1.040434737147365e-05, + "loss": 1.3647, + "step": 5134 + }, + { + "epoch": 0.54, + "learning_rate": 1.0400690087797531e-05, + "loss": 1.3262, + "step": 5135 + }, + { + "epoch": 0.54, + "learning_rate": 1.039703275043924e-05, + "loss": 1.3924, + "step": 5136 + }, + { + "epoch": 0.54, + "learning_rate": 1.039337535988876e-05, + "loss": 1.3018, + "step": 5137 + }, + { + "epoch": 0.54, + "learning_rate": 1.038971791663609e-05, + "loss": 1.385, + "step": 5138 + }, + { + "epoch": 0.54, + "learning_rate": 1.0386060421171232e-05, + "loss": 1.3435, + "step": 5139 + }, + { + "epoch": 0.54, + "learning_rate": 1.0382402873984197e-05, + "loss": 1.4023, + "step": 5140 + }, + { + "epoch": 0.54, + "learning_rate": 1.0378745275565003e-05, + "loss": 1.369, + "step": 5141 + }, + { + "epoch": 0.54, + "learning_rate": 1.0375087626403675e-05, + "loss": 1.3199, + "step": 5142 + }, + { + "epoch": 0.54, + "learning_rate": 1.037142992699024e-05, + "loss": 1.4247, + "step": 5143 + }, + { + "epoch": 0.54, + "learning_rate": 1.0367772177814736e-05, + "loss": 1.4015, + "step": 5144 + }, + { + "epoch": 0.54, + "learning_rate": 1.0364114379367217e-05, + "loss": 1.3519, + "step": 5145 + }, + { + "epoch": 0.54, + "learning_rate": 1.0360456532137722e-05, + "loss": 1.3478, + "step": 5146 + }, + { + "epoch": 0.54, + "learning_rate": 1.0356798636616314e-05, + "loss": 1.4876, + "step": 5147 + }, + { + "epoch": 0.54, + "learning_rate": 1.0353140693293056e-05, + "loss": 1.6481, + "step": 5148 + }, + { + "epoch": 0.54, + "learning_rate": 1.034948270265802e-05, + "loss": 1.3851, + "step": 5149 + }, + { + "epoch": 0.54, + "learning_rate": 1.0345824665201281e-05, + "loss": 1.4037, + "step": 5150 + }, + { + "epoch": 0.54, + "learning_rate": 1.0342166581412923e-05, + "loss": 1.3138, + "step": 5151 + }, + { + "epoch": 0.54, + "learning_rate": 1.0338508451783032e-05, + "loss": 1.3536, + "step": 5152 + }, + { + "epoch": 0.54, + "learning_rate": 1.0334850276801712e-05, + "loss": 1.3244, + "step": 5153 + }, + { + "epoch": 0.54, + "learning_rate": 1.0331192056959052e-05, + "loss": 1.3677, + "step": 5154 + }, + { + "epoch": 0.54, + "learning_rate": 1.032753379274517e-05, + "loss": 1.3439, + "step": 5155 + }, + { + "epoch": 0.54, + "learning_rate": 1.0323875484650171e-05, + "loss": 1.365, + "step": 5156 + }, + { + "epoch": 0.54, + "learning_rate": 1.0320217133164186e-05, + "loss": 1.3838, + "step": 5157 + }, + { + "epoch": 0.54, + "learning_rate": 1.0316558738777328e-05, + "loss": 1.3312, + "step": 5158 + }, + { + "epoch": 0.54, + "learning_rate": 1.0312900301979733e-05, + "loss": 1.369, + "step": 5159 + }, + { + "epoch": 0.54, + "learning_rate": 1.030924182326154e-05, + "loss": 1.2712, + "step": 5160 + }, + { + "epoch": 0.54, + "learning_rate": 1.0305583303112887e-05, + "loss": 1.3141, + "step": 5161 + }, + { + "epoch": 0.54, + "learning_rate": 1.030192474202392e-05, + "loss": 1.3708, + "step": 5162 + }, + { + "epoch": 0.54, + "learning_rate": 1.0298266140484798e-05, + "loss": 1.3724, + "step": 5163 + }, + { + "epoch": 0.54, + "learning_rate": 1.0294607498985678e-05, + "loss": 1.3208, + "step": 5164 + }, + { + "epoch": 0.54, + "learning_rate": 1.0290948818016722e-05, + "loss": 1.3379, + "step": 5165 + }, + { + "epoch": 0.54, + "learning_rate": 1.0287290098068099e-05, + "loss": 1.3236, + "step": 5166 + }, + { + "epoch": 0.54, + "learning_rate": 1.0283631339629982e-05, + "loss": 1.3437, + "step": 5167 + }, + { + "epoch": 0.54, + "learning_rate": 1.0279972543192561e-05, + "loss": 1.3381, + "step": 5168 + }, + { + "epoch": 0.54, + "learning_rate": 1.0276313709246007e-05, + "loss": 1.4287, + "step": 5169 + }, + { + "epoch": 0.54, + "learning_rate": 1.0272654838280515e-05, + "loss": 1.3587, + "step": 5170 + }, + { + "epoch": 0.54, + "learning_rate": 1.0268995930786283e-05, + "loss": 1.2982, + "step": 5171 + }, + { + "epoch": 0.54, + "learning_rate": 1.0265336987253509e-05, + "loss": 1.3416, + "step": 5172 + }, + { + "epoch": 0.54, + "learning_rate": 1.0261678008172393e-05, + "loss": 1.3827, + "step": 5173 + }, + { + "epoch": 0.54, + "learning_rate": 1.025801899403315e-05, + "loss": 1.3293, + "step": 5174 + }, + { + "epoch": 0.54, + "eval_loss": 1.4264723062515259, + "eval_runtime": 77.4376, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 5174 + }, + { + "epoch": 0.54, + "learning_rate": 1.0254359945325987e-05, + "loss": 1.3811, + "step": 5175 + }, + { + "epoch": 0.54, + "learning_rate": 1.0250700862541135e-05, + "loss": 1.3423, + "step": 5176 + }, + { + "epoch": 0.54, + "learning_rate": 1.02470417461688e-05, + "loss": 1.3641, + "step": 5177 + }, + { + "epoch": 0.54, + "learning_rate": 1.0243382596699226e-05, + "loss": 1.3211, + "step": 5178 + }, + { + "epoch": 0.54, + "learning_rate": 1.023972341462263e-05, + "loss": 1.4008, + "step": 5179 + }, + { + "epoch": 0.54, + "learning_rate": 1.0236064200429263e-05, + "loss": 1.404, + "step": 5180 + }, + { + "epoch": 0.54, + "learning_rate": 1.0232404954609353e-05, + "loss": 1.3359, + "step": 5181 + }, + { + "epoch": 0.54, + "learning_rate": 1.0228745677653155e-05, + "loss": 1.4069, + "step": 5182 + }, + { + "epoch": 0.54, + "learning_rate": 1.0225086370050914e-05, + "loss": 1.3343, + "step": 5183 + }, + { + "epoch": 0.54, + "learning_rate": 1.0221427032292881e-05, + "loss": 1.3109, + "step": 5184 + }, + { + "epoch": 0.54, + "learning_rate": 1.0217767664869312e-05, + "loss": 1.3611, + "step": 5185 + }, + { + "epoch": 0.54, + "learning_rate": 1.0214108268270476e-05, + "loss": 1.4072, + "step": 5186 + }, + { + "epoch": 0.54, + "learning_rate": 1.0210448842986631e-05, + "loss": 1.3602, + "step": 5187 + }, + { + "epoch": 0.54, + "learning_rate": 1.0206789389508047e-05, + "loss": 1.413, + "step": 5188 + }, + { + "epoch": 0.54, + "learning_rate": 1.0203129908325e-05, + "loss": 1.3209, + "step": 5189 + }, + { + "epoch": 0.54, + "learning_rate": 1.0199470399927764e-05, + "loss": 1.3714, + "step": 5190 + }, + { + "epoch": 0.54, + "learning_rate": 1.0195810864806623e-05, + "loss": 1.3556, + "step": 5191 + }, + { + "epoch": 0.54, + "learning_rate": 1.0192151303451852e-05, + "loss": 1.4116, + "step": 5192 + }, + { + "epoch": 0.54, + "learning_rate": 1.0188491716353745e-05, + "loss": 1.4102, + "step": 5193 + }, + { + "epoch": 0.54, + "learning_rate": 1.0184832104002592e-05, + "loss": 1.4849, + "step": 5194 + }, + { + "epoch": 0.54, + "learning_rate": 1.0181172466888689e-05, + "loss": 1.5395, + "step": 5195 + }, + { + "epoch": 0.54, + "learning_rate": 1.0177512805502325e-05, + "loss": 1.3627, + "step": 5196 + }, + { + "epoch": 0.54, + "learning_rate": 1.017385312033381e-05, + "loss": 1.4152, + "step": 5197 + }, + { + "epoch": 0.55, + "learning_rate": 1.0170193411873442e-05, + "loss": 1.3641, + "step": 5198 + }, + { + "epoch": 0.55, + "learning_rate": 1.0166533680611533e-05, + "loss": 1.3074, + "step": 5199 + }, + { + "epoch": 0.55, + "learning_rate": 1.0162873927038386e-05, + "loss": 1.35, + "step": 5200 + }, + { + "epoch": 0.55, + "learning_rate": 1.015921415164432e-05, + "loss": 1.3551, + "step": 5201 + }, + { + "epoch": 0.55, + "learning_rate": 1.0155554354919643e-05, + "loss": 1.3421, + "step": 5202 + }, + { + "epoch": 0.55, + "learning_rate": 1.0151894537354687e-05, + "loss": 1.4132, + "step": 5203 + }, + { + "epoch": 0.55, + "learning_rate": 1.0148234699439764e-05, + "loss": 1.351, + "step": 5204 + }, + { + "epoch": 0.55, + "learning_rate": 1.0144574841665198e-05, + "loss": 1.3745, + "step": 5205 + }, + { + "epoch": 0.55, + "learning_rate": 1.0140914964521316e-05, + "loss": 1.3151, + "step": 5206 + }, + { + "epoch": 0.55, + "learning_rate": 1.0137255068498456e-05, + "loss": 1.4903, + "step": 5207 + }, + { + "epoch": 0.55, + "learning_rate": 1.0133595154086937e-05, + "loss": 1.3945, + "step": 5208 + }, + { + "epoch": 0.55, + "learning_rate": 1.0129935221777104e-05, + "loss": 1.3924, + "step": 5209 + }, + { + "epoch": 0.55, + "learning_rate": 1.0126275272059286e-05, + "loss": 1.4191, + "step": 5210 + }, + { + "epoch": 0.55, + "learning_rate": 1.012261530542383e-05, + "loss": 1.3408, + "step": 5211 + }, + { + "epoch": 0.55, + "learning_rate": 1.0118955322361071e-05, + "loss": 1.3582, + "step": 5212 + }, + { + "epoch": 0.55, + "learning_rate": 1.0115295323361354e-05, + "loss": 1.3703, + "step": 5213 + }, + { + "epoch": 0.55, + "learning_rate": 1.011163530891503e-05, + "loss": 1.4181, + "step": 5214 + }, + { + "epoch": 0.55, + "learning_rate": 1.0107975279512442e-05, + "loss": 1.5019, + "step": 5215 + }, + { + "epoch": 0.55, + "learning_rate": 1.010431523564394e-05, + "loss": 1.3151, + "step": 5216 + }, + { + "epoch": 0.55, + "learning_rate": 1.0100655177799874e-05, + "loss": 1.4036, + "step": 5217 + }, + { + "epoch": 0.55, + "learning_rate": 1.0096995106470606e-05, + "loss": 1.3584, + "step": 5218 + }, + { + "epoch": 0.55, + "learning_rate": 1.0093335022146482e-05, + "loss": 1.3618, + "step": 5219 + }, + { + "epoch": 0.55, + "learning_rate": 1.0089674925317865e-05, + "loss": 1.3295, + "step": 5220 + }, + { + "epoch": 0.55, + "learning_rate": 1.0086014816475108e-05, + "loss": 1.3968, + "step": 5221 + }, + { + "epoch": 0.55, + "learning_rate": 1.0082354696108586e-05, + "loss": 1.2847, + "step": 5222 + }, + { + "epoch": 0.55, + "learning_rate": 1.007869456470864e-05, + "loss": 1.4461, + "step": 5223 + }, + { + "epoch": 0.55, + "learning_rate": 1.007503442276565e-05, + "loss": 1.3813, + "step": 5224 + }, + { + "epoch": 0.55, + "learning_rate": 1.007137427076997e-05, + "loss": 1.3833, + "step": 5225 + }, + { + "epoch": 0.55, + "learning_rate": 1.006771410921198e-05, + "loss": 1.4024, + "step": 5226 + }, + { + "epoch": 0.55, + "learning_rate": 1.0064053938582032e-05, + "loss": 1.3357, + "step": 5227 + }, + { + "epoch": 0.55, + "learning_rate": 1.0060393759370506e-05, + "loss": 1.35, + "step": 5228 + }, + { + "epoch": 0.55, + "learning_rate": 1.0056733572067765e-05, + "loss": 1.3512, + "step": 5229 + }, + { + "epoch": 0.55, + "learning_rate": 1.0053073377164186e-05, + "loss": 1.3852, + "step": 5230 + }, + { + "epoch": 0.55, + "learning_rate": 1.0049413175150135e-05, + "loss": 1.3502, + "step": 5231 + }, + { + "epoch": 0.55, + "learning_rate": 1.004575296651599e-05, + "loss": 1.4637, + "step": 5232 + }, + { + "epoch": 0.55, + "learning_rate": 1.0042092751752123e-05, + "loss": 1.3877, + "step": 5233 + }, + { + "epoch": 0.55, + "learning_rate": 1.0038432531348909e-05, + "loss": 1.3804, + "step": 5234 + }, + { + "epoch": 0.55, + "learning_rate": 1.0034772305796723e-05, + "loss": 1.3613, + "step": 5235 + }, + { + "epoch": 0.55, + "learning_rate": 1.003111207558594e-05, + "loss": 1.3218, + "step": 5236 + }, + { + "epoch": 0.55, + "learning_rate": 1.0027451841206944e-05, + "loss": 1.3554, + "step": 5237 + }, + { + "epoch": 0.55, + "learning_rate": 1.0023791603150099e-05, + "loss": 1.372, + "step": 5238 + }, + { + "epoch": 0.55, + "learning_rate": 1.0020131361905793e-05, + "loss": 1.3544, + "step": 5239 + }, + { + "epoch": 0.55, + "learning_rate": 1.0016471117964404e-05, + "loss": 1.3472, + "step": 5240 + }, + { + "epoch": 0.55, + "learning_rate": 1.001281087181631e-05, + "loss": 1.4247, + "step": 5241 + }, + { + "epoch": 0.55, + "learning_rate": 1.0009150623951883e-05, + "loss": 1.2685, + "step": 5242 + }, + { + "epoch": 0.55, + "learning_rate": 1.000549037486151e-05, + "loss": 1.4036, + "step": 5243 + }, + { + "epoch": 0.55, + "learning_rate": 1.0001830125035565e-05, + "loss": 1.3602, + "step": 5244 + }, + { + "epoch": 0.55, + "learning_rate": 9.998169874964437e-06, + "loss": 1.3784, + "step": 5245 + }, + { + "epoch": 0.55, + "learning_rate": 9.994509625138496e-06, + "loss": 1.3389, + "step": 5246 + }, + { + "epoch": 0.55, + "learning_rate": 9.990849376048119e-06, + "loss": 1.4561, + "step": 5247 + }, + { + "epoch": 0.55, + "learning_rate": 9.987189128183695e-06, + "loss": 1.3876, + "step": 5248 + }, + { + "epoch": 0.55, + "learning_rate": 9.9835288820356e-06, + "loss": 1.3362, + "step": 5249 + }, + { + "epoch": 0.55, + "learning_rate": 9.97986863809421e-06, + "loss": 1.3449, + "step": 5250 + }, + { + "epoch": 0.55, + "learning_rate": 9.9762083968499e-06, + "loss": 1.3521, + "step": 5251 + }, + { + "epoch": 0.55, + "learning_rate": 9.972548158793061e-06, + "loss": 1.4452, + "step": 5252 + }, + { + "epoch": 0.55, + "learning_rate": 9.968887924414062e-06, + "loss": 1.4126, + "step": 5253 + }, + { + "epoch": 0.55, + "learning_rate": 9.965227694203282e-06, + "loss": 1.3054, + "step": 5254 + }, + { + "epoch": 0.55, + "learning_rate": 9.961567468651093e-06, + "loss": 1.3771, + "step": 5255 + }, + { + "epoch": 0.55, + "learning_rate": 9.957907248247878e-06, + "loss": 1.3566, + "step": 5256 + }, + { + "epoch": 0.55, + "learning_rate": 9.954247033484014e-06, + "loss": 1.4765, + "step": 5257 + }, + { + "epoch": 0.55, + "learning_rate": 9.950586824849865e-06, + "loss": 1.4749, + "step": 5258 + }, + { + "epoch": 0.55, + "learning_rate": 9.946926622835815e-06, + "loss": 1.3679, + "step": 5259 + }, + { + "epoch": 0.55, + "learning_rate": 9.943266427932238e-06, + "loss": 1.2671, + "step": 5260 + }, + { + "epoch": 0.55, + "learning_rate": 9.9396062406295e-06, + "loss": 1.3485, + "step": 5261 + }, + { + "epoch": 0.55, + "learning_rate": 9.935946061417968e-06, + "loss": 1.3136, + "step": 5262 + }, + { + "epoch": 0.55, + "learning_rate": 9.932285890788024e-06, + "loss": 1.3954, + "step": 5263 + }, + { + "epoch": 0.55, + "learning_rate": 9.928625729230031e-06, + "loss": 1.428, + "step": 5264 + }, + { + "epoch": 0.55, + "learning_rate": 9.924965577234356e-06, + "loss": 1.4144, + "step": 5265 + }, + { + "epoch": 0.55, + "learning_rate": 9.92130543529136e-06, + "loss": 1.3361, + "step": 5266 + }, + { + "epoch": 0.55, + "learning_rate": 9.91764530389142e-06, + "loss": 1.4503, + "step": 5267 + }, + { + "epoch": 0.55, + "learning_rate": 9.913985183524893e-06, + "loss": 1.3431, + "step": 5268 + }, + { + "epoch": 0.55, + "learning_rate": 9.91032507468214e-06, + "loss": 1.3206, + "step": 5269 + }, + { + "epoch": 0.55, + "learning_rate": 9.906664977853518e-06, + "loss": 1.4568, + "step": 5270 + }, + { + "epoch": 0.55, + "learning_rate": 9.903004893529397e-06, + "loss": 1.3591, + "step": 5271 + }, + { + "epoch": 0.55, + "learning_rate": 9.899344822200127e-06, + "loss": 1.3382, + "step": 5272 + }, + { + "epoch": 0.55, + "learning_rate": 9.895684764356066e-06, + "loss": 1.3008, + "step": 5273 + }, + { + "epoch": 0.55, + "learning_rate": 9.89202472048756e-06, + "loss": 1.316, + "step": 5274 + }, + { + "epoch": 0.55, + "learning_rate": 9.888364691084971e-06, + "loss": 1.4246, + "step": 5275 + }, + { + "epoch": 0.55, + "learning_rate": 9.88470467663865e-06, + "loss": 1.3615, + "step": 5276 + }, + { + "epoch": 0.55, + "learning_rate": 9.881044677638934e-06, + "loss": 1.3418, + "step": 5277 + }, + { + "epoch": 0.55, + "learning_rate": 9.877384694576172e-06, + "loss": 1.249, + "step": 5278 + }, + { + "epoch": 0.55, + "learning_rate": 9.873724727940715e-06, + "loss": 1.2779, + "step": 5279 + }, + { + "epoch": 0.55, + "learning_rate": 9.870064778222903e-06, + "loss": 1.3529, + "step": 5280 + }, + { + "epoch": 0.55, + "learning_rate": 9.866404845913065e-06, + "loss": 1.3204, + "step": 5281 + }, + { + "epoch": 0.55, + "learning_rate": 9.862744931501548e-06, + "loss": 1.3537, + "step": 5282 + }, + { + "epoch": 0.55, + "learning_rate": 9.859085035478687e-06, + "loss": 1.3681, + "step": 5283 + }, + { + "epoch": 0.55, + "learning_rate": 9.855425158334809e-06, + "loss": 1.3983, + "step": 5284 + }, + { + "epoch": 0.55, + "learning_rate": 9.851765300560238e-06, + "loss": 1.401, + "step": 5285 + }, + { + "epoch": 0.55, + "learning_rate": 9.848105462645315e-06, + "loss": 1.3073, + "step": 5286 + }, + { + "epoch": 0.55, + "learning_rate": 9.844445645080358e-06, + "loss": 1.3162, + "step": 5287 + }, + { + "epoch": 0.55, + "learning_rate": 9.840785848355685e-06, + "loss": 1.3345, + "step": 5288 + }, + { + "epoch": 0.55, + "learning_rate": 9.837126072961616e-06, + "loss": 1.4241, + "step": 5289 + }, + { + "epoch": 0.55, + "learning_rate": 9.83346631938847e-06, + "loss": 1.3339, + "step": 5290 + }, + { + "epoch": 0.55, + "learning_rate": 9.829806588126561e-06, + "loss": 1.3507, + "step": 5291 + }, + { + "epoch": 0.55, + "learning_rate": 9.826146879666196e-06, + "loss": 1.2806, + "step": 5292 + }, + { + "epoch": 0.56, + "learning_rate": 9.822487194497675e-06, + "loss": 1.3952, + "step": 5293 + }, + { + "epoch": 0.56, + "learning_rate": 9.818827533111314e-06, + "loss": 1.3319, + "step": 5294 + }, + { + "epoch": 0.56, + "learning_rate": 9.81516789599741e-06, + "loss": 1.351, + "step": 5295 + }, + { + "epoch": 0.56, + "learning_rate": 9.811508283646258e-06, + "loss": 1.4076, + "step": 5296 + }, + { + "epoch": 0.56, + "learning_rate": 9.80784869654815e-06, + "loss": 1.3271, + "step": 5297 + }, + { + "epoch": 0.56, + "learning_rate": 9.80418913519338e-06, + "loss": 1.4059, + "step": 5298 + }, + { + "epoch": 0.56, + "learning_rate": 9.80052960007224e-06, + "loss": 1.4146, + "step": 5299 + }, + { + "epoch": 0.56, + "learning_rate": 9.796870091675005e-06, + "loss": 1.3454, + "step": 5300 + }, + { + "epoch": 0.56, + "learning_rate": 9.793210610491953e-06, + "loss": 1.4376, + "step": 5301 + }, + { + "epoch": 0.56, + "learning_rate": 9.789551157013372e-06, + "loss": 1.3437, + "step": 5302 + }, + { + "epoch": 0.56, + "learning_rate": 9.78589173172953e-06, + "loss": 1.3073, + "step": 5303 + }, + { + "epoch": 0.56, + "learning_rate": 9.782232335130688e-06, + "loss": 1.2989, + "step": 5304 + }, + { + "epoch": 0.56, + "learning_rate": 9.778572967707122e-06, + "loss": 1.4028, + "step": 5305 + }, + { + "epoch": 0.56, + "learning_rate": 9.77491362994909e-06, + "loss": 1.3096, + "step": 5306 + }, + { + "epoch": 0.56, + "learning_rate": 9.77125432234685e-06, + "loss": 1.3719, + "step": 5307 + }, + { + "epoch": 0.56, + "learning_rate": 9.767595045390647e-06, + "loss": 1.3271, + "step": 5308 + }, + { + "epoch": 0.56, + "learning_rate": 9.763935799570739e-06, + "loss": 1.3693, + "step": 5309 + }, + { + "epoch": 0.56, + "learning_rate": 9.760276585377371e-06, + "loss": 1.3586, + "step": 5310 + }, + { + "epoch": 0.56, + "learning_rate": 9.756617403300781e-06, + "loss": 1.3423, + "step": 5311 + }, + { + "epoch": 0.56, + "learning_rate": 9.7529582538312e-06, + "loss": 1.388, + "step": 5312 + }, + { + "epoch": 0.56, + "learning_rate": 9.74929913745887e-06, + "loss": 1.3594, + "step": 5313 + }, + { + "epoch": 0.56, + "learning_rate": 9.745640054674015e-06, + "loss": 1.2831, + "step": 5314 + }, + { + "epoch": 0.56, + "learning_rate": 9.741981005966856e-06, + "loss": 1.4207, + "step": 5315 + }, + { + "epoch": 0.56, + "learning_rate": 9.738321991827609e-06, + "loss": 1.2807, + "step": 5316 + }, + { + "epoch": 0.56, + "learning_rate": 9.734663012746493e-06, + "loss": 1.3396, + "step": 5317 + }, + { + "epoch": 0.56, + "learning_rate": 9.731004069213722e-06, + "loss": 1.3666, + "step": 5318 + }, + { + "epoch": 0.56, + "learning_rate": 9.72734516171949e-06, + "loss": 1.3466, + "step": 5319 + }, + { + "epoch": 0.56, + "learning_rate": 9.723686290753995e-06, + "loss": 1.4478, + "step": 5320 + }, + { + "epoch": 0.56, + "learning_rate": 9.720027456807442e-06, + "loss": 1.316, + "step": 5321 + }, + { + "epoch": 0.56, + "learning_rate": 9.71636866037002e-06, + "loss": 1.3762, + "step": 5322 + }, + { + "epoch": 0.56, + "learning_rate": 9.712709901931906e-06, + "loss": 1.4156, + "step": 5323 + }, + { + "epoch": 0.56, + "learning_rate": 9.70905118198328e-06, + "loss": 1.2452, + "step": 5324 + }, + { + "epoch": 0.56, + "learning_rate": 9.705392501014325e-06, + "loss": 1.3771, + "step": 5325 + }, + { + "epoch": 0.56, + "learning_rate": 9.701733859515205e-06, + "loss": 1.3433, + "step": 5326 + }, + { + "epoch": 0.56, + "learning_rate": 9.698075257976079e-06, + "loss": 1.3702, + "step": 5327 + }, + { + "epoch": 0.56, + "learning_rate": 9.694416696887115e-06, + "loss": 1.295, + "step": 5328 + }, + { + "epoch": 0.56, + "learning_rate": 9.690758176738463e-06, + "loss": 1.3462, + "step": 5329 + }, + { + "epoch": 0.56, + "learning_rate": 9.68709969802027e-06, + "loss": 1.5304, + "step": 5330 + }, + { + "epoch": 0.56, + "learning_rate": 9.683441261222672e-06, + "loss": 1.3518, + "step": 5331 + }, + { + "epoch": 0.56, + "learning_rate": 9.679782866835816e-06, + "loss": 1.3778, + "step": 5332 + }, + { + "epoch": 0.56, + "learning_rate": 9.67612451534983e-06, + "loss": 1.3731, + "step": 5333 + }, + { + "epoch": 0.56, + "learning_rate": 9.672466207254837e-06, + "loss": 1.3315, + "step": 5334 + }, + { + "epoch": 0.56, + "learning_rate": 9.66880794304095e-06, + "loss": 1.3105, + "step": 5335 + }, + { + "epoch": 0.56, + "learning_rate": 9.665149723198293e-06, + "loss": 1.3903, + "step": 5336 + }, + { + "epoch": 0.56, + "learning_rate": 9.661491548216972e-06, + "loss": 1.3554, + "step": 5337 + }, + { + "epoch": 0.56, + "learning_rate": 9.657833418587084e-06, + "loss": 1.3231, + "step": 5338 + }, + { + "epoch": 0.56, + "learning_rate": 9.65417533479872e-06, + "loss": 1.352, + "step": 5339 + }, + { + "epoch": 0.56, + "learning_rate": 9.650517297341983e-06, + "loss": 1.3957, + "step": 5340 + }, + { + "epoch": 0.56, + "learning_rate": 9.646859306706948e-06, + "loss": 1.3938, + "step": 5341 + }, + { + "epoch": 0.56, + "learning_rate": 9.643201363383693e-06, + "loss": 1.3038, + "step": 5342 + }, + { + "epoch": 0.56, + "learning_rate": 9.63954346786228e-06, + "loss": 1.2973, + "step": 5343 + }, + { + "epoch": 0.56, + "learning_rate": 9.635885620632786e-06, + "loss": 1.379, + "step": 5344 + }, + { + "epoch": 0.56, + "learning_rate": 9.632227822185266e-06, + "loss": 1.5377, + "step": 5345 + }, + { + "epoch": 0.56, + "learning_rate": 9.628570073009767e-06, + "loss": 1.4573, + "step": 5346 + }, + { + "epoch": 0.56, + "learning_rate": 9.624912373596329e-06, + "loss": 1.3394, + "step": 5347 + }, + { + "epoch": 0.56, + "learning_rate": 9.621254724434999e-06, + "loss": 1.4157, + "step": 5348 + }, + { + "epoch": 0.56, + "learning_rate": 9.617597126015808e-06, + "loss": 1.3526, + "step": 5349 + }, + { + "epoch": 0.56, + "learning_rate": 9.61393957882877e-06, + "loss": 1.3795, + "step": 5350 + }, + { + "epoch": 0.56, + "learning_rate": 9.610282083363913e-06, + "loss": 1.3765, + "step": 5351 + }, + { + "epoch": 0.56, + "learning_rate": 9.606624640111243e-06, + "loss": 1.3512, + "step": 5352 + }, + { + "epoch": 0.56, + "learning_rate": 9.602967249560766e-06, + "loss": 1.3298, + "step": 5353 + }, + { + "epoch": 0.56, + "learning_rate": 9.599309912202469e-06, + "loss": 1.3093, + "step": 5354 + }, + { + "epoch": 0.56, + "learning_rate": 9.595652628526354e-06, + "loss": 1.3353, + "step": 5355 + }, + { + "epoch": 0.56, + "learning_rate": 9.591995399022397e-06, + "loss": 1.3081, + "step": 5356 + }, + { + "epoch": 0.56, + "learning_rate": 9.588338224180576e-06, + "loss": 1.343, + "step": 5357 + }, + { + "epoch": 0.56, + "learning_rate": 9.584681104490848e-06, + "loss": 1.3275, + "step": 5358 + }, + { + "epoch": 0.56, + "learning_rate": 9.581024040443185e-06, + "loss": 1.3399, + "step": 5359 + }, + { + "epoch": 0.56, + "learning_rate": 9.577367032527538e-06, + "loss": 1.3181, + "step": 5360 + }, + { + "epoch": 0.56, + "learning_rate": 9.573710081233846e-06, + "loss": 1.3531, + "step": 5361 + }, + { + "epoch": 0.56, + "learning_rate": 9.570053187052049e-06, + "loss": 1.4056, + "step": 5362 + }, + { + "epoch": 0.56, + "learning_rate": 9.566396350472079e-06, + "loss": 1.3303, + "step": 5363 + }, + { + "epoch": 0.56, + "learning_rate": 9.56273957198386e-06, + "loss": 1.3506, + "step": 5364 + }, + { + "epoch": 0.56, + "learning_rate": 9.559082852077302e-06, + "loss": 1.4588, + "step": 5365 + }, + { + "epoch": 0.56, + "learning_rate": 9.555426191242307e-06, + "loss": 1.3434, + "step": 5366 + }, + { + "epoch": 0.56, + "learning_rate": 9.551769589968784e-06, + "loss": 1.3508, + "step": 5367 + }, + { + "epoch": 0.56, + "learning_rate": 9.548113048746622e-06, + "loss": 1.3701, + "step": 5368 + }, + { + "epoch": 0.56, + "learning_rate": 9.544456568065698e-06, + "loss": 1.3664, + "step": 5369 + }, + { + "epoch": 0.56, + "learning_rate": 9.540800148415885e-06, + "loss": 1.6697, + "step": 5370 + }, + { + "epoch": 0.56, + "learning_rate": 9.537143790287057e-06, + "loss": 1.5298, + "step": 5371 + }, + { + "epoch": 0.56, + "learning_rate": 9.533487494169073e-06, + "loss": 1.3884, + "step": 5372 + }, + { + "epoch": 0.56, + "learning_rate": 9.52983126055177e-06, + "loss": 1.403, + "step": 5373 + }, + { + "epoch": 0.56, + "eval_loss": 1.4240995645523071, + "eval_runtime": 77.4615, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 5373 + }, + { + "epoch": 0.56, + "learning_rate": 9.526175089925e-06, + "loss": 1.3141, + "step": 5374 + }, + { + "epoch": 0.56, + "learning_rate": 9.522518982778596e-06, + "loss": 1.3733, + "step": 5375 + }, + { + "epoch": 0.56, + "learning_rate": 9.51886293960238e-06, + "loss": 1.3095, + "step": 5376 + }, + { + "epoch": 0.56, + "learning_rate": 9.515206960886162e-06, + "loss": 1.3713, + "step": 5377 + }, + { + "epoch": 0.56, + "learning_rate": 9.51155104711976e-06, + "loss": 1.3585, + "step": 5378 + }, + { + "epoch": 0.56, + "learning_rate": 9.507895198792967e-06, + "loss": 1.3473, + "step": 5379 + }, + { + "epoch": 0.56, + "learning_rate": 9.504239416395576e-06, + "loss": 1.3282, + "step": 5380 + }, + { + "epoch": 0.56, + "learning_rate": 9.500583700417357e-06, + "loss": 1.3655, + "step": 5381 + }, + { + "epoch": 0.56, + "learning_rate": 9.496928051348095e-06, + "loss": 1.4512, + "step": 5382 + }, + { + "epoch": 0.56, + "learning_rate": 9.49327246967755e-06, + "loss": 1.4071, + "step": 5383 + }, + { + "epoch": 0.56, + "learning_rate": 9.489616955895472e-06, + "loss": 1.3703, + "step": 5384 + }, + { + "epoch": 0.56, + "learning_rate": 9.485961510491604e-06, + "loss": 1.3358, + "step": 5385 + }, + { + "epoch": 0.56, + "learning_rate": 9.482306133955691e-06, + "loss": 1.3505, + "step": 5386 + }, + { + "epoch": 0.56, + "learning_rate": 9.478650826777457e-06, + "loss": 1.2578, + "step": 5387 + }, + { + "epoch": 0.57, + "learning_rate": 9.474995589446612e-06, + "loss": 1.4298, + "step": 5388 + }, + { + "epoch": 0.57, + "learning_rate": 9.471340422452864e-06, + "loss": 1.4044, + "step": 5389 + }, + { + "epoch": 0.57, + "learning_rate": 9.467685326285922e-06, + "loss": 1.3524, + "step": 5390 + }, + { + "epoch": 0.57, + "learning_rate": 9.46403030143547e-06, + "loss": 1.3017, + "step": 5391 + }, + { + "epoch": 0.57, + "learning_rate": 9.460375348391185e-06, + "loss": 1.3361, + "step": 5392 + }, + { + "epoch": 0.57, + "learning_rate": 9.456720467642733e-06, + "loss": 1.3182, + "step": 5393 + }, + { + "epoch": 0.57, + "learning_rate": 9.453065659679785e-06, + "loss": 1.3869, + "step": 5394 + }, + { + "epoch": 0.57, + "learning_rate": 9.449410924991986e-06, + "loss": 1.3161, + "step": 5395 + }, + { + "epoch": 0.57, + "learning_rate": 9.44575626406897e-06, + "loss": 1.3, + "step": 5396 + }, + { + "epoch": 0.57, + "learning_rate": 9.442101677400378e-06, + "loss": 1.5103, + "step": 5397 + }, + { + "epoch": 0.57, + "learning_rate": 9.438447165475828e-06, + "loss": 1.3511, + "step": 5398 + }, + { + "epoch": 0.57, + "learning_rate": 9.43479272878493e-06, + "loss": 1.3461, + "step": 5399 + }, + { + "epoch": 0.57, + "learning_rate": 9.431138367817277e-06, + "loss": 1.2657, + "step": 5400 + }, + { + "epoch": 0.57, + "learning_rate": 9.427484083062472e-06, + "loss": 1.3736, + "step": 5401 + }, + { + "epoch": 0.57, + "learning_rate": 9.423829875010089e-06, + "loss": 1.3476, + "step": 5402 + }, + { + "epoch": 0.57, + "learning_rate": 9.4201757441497e-06, + "loss": 1.3495, + "step": 5403 + }, + { + "epoch": 0.57, + "learning_rate": 9.416521690970857e-06, + "loss": 1.387, + "step": 5404 + }, + { + "epoch": 0.57, + "learning_rate": 9.41286771596312e-06, + "loss": 1.2829, + "step": 5405 + }, + { + "epoch": 0.57, + "learning_rate": 9.409213819616022e-06, + "loss": 1.3544, + "step": 5406 + }, + { + "epoch": 0.57, + "learning_rate": 9.405560002419098e-06, + "loss": 1.3202, + "step": 5407 + }, + { + "epoch": 0.57, + "learning_rate": 9.40190626486185e-06, + "loss": 1.3034, + "step": 5408 + }, + { + "epoch": 0.57, + "learning_rate": 9.398252607433801e-06, + "loss": 1.3223, + "step": 5409 + }, + { + "epoch": 0.57, + "learning_rate": 9.394599030624443e-06, + "loss": 1.3327, + "step": 5410 + }, + { + "epoch": 0.57, + "learning_rate": 9.390945534923258e-06, + "loss": 1.3248, + "step": 5411 + }, + { + "epoch": 0.57, + "learning_rate": 9.387292120819716e-06, + "loss": 1.3084, + "step": 5412 + }, + { + "epoch": 0.57, + "learning_rate": 9.383638788803291e-06, + "loss": 1.344, + "step": 5413 + }, + { + "epoch": 0.57, + "learning_rate": 9.379985539363436e-06, + "loss": 1.3354, + "step": 5414 + }, + { + "epoch": 0.57, + "learning_rate": 9.376332372989586e-06, + "loss": 1.3291, + "step": 5415 + }, + { + "epoch": 0.57, + "learning_rate": 9.372679290171167e-06, + "loss": 1.3468, + "step": 5416 + }, + { + "epoch": 0.57, + "learning_rate": 9.36902629139761e-06, + "loss": 1.3481, + "step": 5417 + }, + { + "epoch": 0.57, + "learning_rate": 9.36537337715832e-06, + "loss": 1.3309, + "step": 5418 + }, + { + "epoch": 0.57, + "learning_rate": 9.361720547942683e-06, + "loss": 1.362, + "step": 5419 + }, + { + "epoch": 0.57, + "learning_rate": 9.358067804240098e-06, + "loss": 1.3647, + "step": 5420 + }, + { + "epoch": 0.57, + "learning_rate": 9.354415146539933e-06, + "loss": 1.4511, + "step": 5421 + }, + { + "epoch": 0.57, + "learning_rate": 9.350762575331554e-06, + "loss": 1.3379, + "step": 5422 + }, + { + "epoch": 0.57, + "learning_rate": 9.3471100911043e-06, + "loss": 1.5468, + "step": 5423 + }, + { + "epoch": 0.57, + "learning_rate": 9.343457694347524e-06, + "loss": 1.4259, + "step": 5424 + }, + { + "epoch": 0.57, + "learning_rate": 9.339805385550548e-06, + "loss": 1.3816, + "step": 5425 + }, + { + "epoch": 0.57, + "learning_rate": 9.336153165202689e-06, + "loss": 1.3627, + "step": 5426 + }, + { + "epoch": 0.57, + "learning_rate": 9.332501033793242e-06, + "loss": 1.3338, + "step": 5427 + }, + { + "epoch": 0.57, + "learning_rate": 9.328848991811509e-06, + "loss": 1.2946, + "step": 5428 + }, + { + "epoch": 0.57, + "learning_rate": 9.325197039746769e-06, + "loss": 1.3405, + "step": 5429 + }, + { + "epoch": 0.57, + "learning_rate": 9.321545178088288e-06, + "loss": 1.3549, + "step": 5430 + }, + { + "epoch": 0.57, + "learning_rate": 9.317893407325314e-06, + "loss": 1.3225, + "step": 5431 + }, + { + "epoch": 0.57, + "learning_rate": 9.314241727947101e-06, + "loss": 1.3457, + "step": 5432 + }, + { + "epoch": 0.57, + "learning_rate": 9.310590140442878e-06, + "loss": 1.311, + "step": 5433 + }, + { + "epoch": 0.57, + "learning_rate": 9.306938645301862e-06, + "loss": 1.3615, + "step": 5434 + }, + { + "epoch": 0.57, + "learning_rate": 9.303287243013255e-06, + "loss": 1.3495, + "step": 5435 + }, + { + "epoch": 0.57, + "learning_rate": 9.29963593406626e-06, + "loss": 1.3899, + "step": 5436 + }, + { + "epoch": 0.57, + "learning_rate": 9.295984718950058e-06, + "loss": 1.3189, + "step": 5437 + }, + { + "epoch": 0.57, + "learning_rate": 9.292333598153813e-06, + "loss": 1.4199, + "step": 5438 + }, + { + "epoch": 0.57, + "learning_rate": 9.288682572166677e-06, + "loss": 1.4751, + "step": 5439 + }, + { + "epoch": 0.57, + "learning_rate": 9.285031641477804e-06, + "loss": 1.3435, + "step": 5440 + }, + { + "epoch": 0.57, + "learning_rate": 9.281380806576322e-06, + "loss": 1.2954, + "step": 5441 + }, + { + "epoch": 0.57, + "learning_rate": 9.277730067951341e-06, + "loss": 1.3414, + "step": 5442 + }, + { + "epoch": 0.57, + "learning_rate": 9.274079426091978e-06, + "loss": 1.3642, + "step": 5443 + }, + { + "epoch": 0.57, + "learning_rate": 9.27042888148732e-06, + "loss": 1.3651, + "step": 5444 + }, + { + "epoch": 0.57, + "learning_rate": 9.266778434626448e-06, + "loss": 1.3995, + "step": 5445 + }, + { + "epoch": 0.57, + "learning_rate": 9.263128085998421e-06, + "loss": 1.2692, + "step": 5446 + }, + { + "epoch": 0.57, + "learning_rate": 9.2594778360923e-06, + "loss": 1.4355, + "step": 5447 + }, + { + "epoch": 0.57, + "learning_rate": 9.255827685397124e-06, + "loss": 1.4262, + "step": 5448 + }, + { + "epoch": 0.57, + "learning_rate": 9.252177634401917e-06, + "loss": 1.3372, + "step": 5449 + }, + { + "epoch": 0.57, + "learning_rate": 9.248527683595685e-06, + "loss": 1.4603, + "step": 5450 + }, + { + "epoch": 0.57, + "learning_rate": 9.24487783346744e-06, + "loss": 1.446, + "step": 5451 + }, + { + "epoch": 0.57, + "learning_rate": 9.241228084506167e-06, + "loss": 1.4088, + "step": 5452 + }, + { + "epoch": 0.57, + "learning_rate": 9.237578437200832e-06, + "loss": 1.3074, + "step": 5453 + }, + { + "epoch": 0.57, + "learning_rate": 9.233928892040392e-06, + "loss": 1.4347, + "step": 5454 + }, + { + "epoch": 0.57, + "learning_rate": 9.230279449513802e-06, + "loss": 1.2982, + "step": 5455 + }, + { + "epoch": 0.57, + "learning_rate": 9.226630110109988e-06, + "loss": 1.2928, + "step": 5456 + }, + { + "epoch": 0.57, + "learning_rate": 9.222980874317869e-06, + "loss": 1.2849, + "step": 5457 + }, + { + "epoch": 0.57, + "learning_rate": 9.219331742626343e-06, + "loss": 1.3137, + "step": 5458 + }, + { + "epoch": 0.57, + "learning_rate": 9.215682715524309e-06, + "loss": 1.3523, + "step": 5459 + }, + { + "epoch": 0.57, + "learning_rate": 9.21203379350064e-06, + "loss": 1.381, + "step": 5460 + }, + { + "epoch": 0.57, + "learning_rate": 9.208384977044191e-06, + "loss": 1.286, + "step": 5461 + }, + { + "epoch": 0.57, + "learning_rate": 9.204736266643819e-06, + "loss": 1.3467, + "step": 5462 + }, + { + "epoch": 0.57, + "learning_rate": 9.201087662788353e-06, + "loss": 1.3582, + "step": 5463 + }, + { + "epoch": 0.57, + "learning_rate": 9.197439165966617e-06, + "loss": 1.3912, + "step": 5464 + }, + { + "epoch": 0.57, + "learning_rate": 9.193790776667402e-06, + "loss": 1.3144, + "step": 5465 + }, + { + "epoch": 0.57, + "learning_rate": 9.190142495379515e-06, + "loss": 1.3403, + "step": 5466 + }, + { + "epoch": 0.57, + "learning_rate": 9.186494322591725e-06, + "loss": 1.3253, + "step": 5467 + }, + { + "epoch": 0.57, + "learning_rate": 9.182846258792794e-06, + "loss": 1.2908, + "step": 5468 + }, + { + "epoch": 0.57, + "learning_rate": 9.179198304471463e-06, + "loss": 1.3486, + "step": 5469 + }, + { + "epoch": 0.57, + "learning_rate": 9.175550460116473e-06, + "loss": 1.3915, + "step": 5470 + }, + { + "epoch": 0.57, + "learning_rate": 9.171902726216538e-06, + "loss": 1.3441, + "step": 5471 + }, + { + "epoch": 0.57, + "learning_rate": 9.168255103260362e-06, + "loss": 1.3196, + "step": 5472 + }, + { + "epoch": 0.57, + "learning_rate": 9.164607591736627e-06, + "loss": 1.3279, + "step": 5473 + }, + { + "epoch": 0.57, + "learning_rate": 9.160960192134011e-06, + "loss": 1.2643, + "step": 5474 + }, + { + "epoch": 0.57, + "learning_rate": 9.157312904941174e-06, + "loss": 1.3327, + "step": 5475 + }, + { + "epoch": 0.57, + "learning_rate": 9.153665730646756e-06, + "loss": 1.4016, + "step": 5476 + }, + { + "epoch": 0.57, + "learning_rate": 9.150018669739378e-06, + "loss": 1.3614, + "step": 5477 + }, + { + "epoch": 0.57, + "learning_rate": 9.146371722707662e-06, + "loss": 1.3469, + "step": 5478 + }, + { + "epoch": 0.57, + "learning_rate": 9.142724890040204e-06, + "loss": 1.3625, + "step": 5479 + }, + { + "epoch": 0.57, + "learning_rate": 9.139078172225585e-06, + "loss": 1.3879, + "step": 5480 + }, + { + "epoch": 0.57, + "learning_rate": 9.135431569752362e-06, + "loss": 1.3738, + "step": 5481 + }, + { + "epoch": 0.57, + "learning_rate": 9.131785083109101e-06, + "loss": 1.3507, + "step": 5482 + }, + { + "epoch": 0.57, + "learning_rate": 9.128138712784331e-06, + "loss": 1.3681, + "step": 5483 + }, + { + "epoch": 0.58, + "learning_rate": 9.124492459266567e-06, + "loss": 1.332, + "step": 5484 + }, + { + "epoch": 0.58, + "learning_rate": 9.12084632304432e-06, + "loss": 1.4746, + "step": 5485 + }, + { + "epoch": 0.58, + "learning_rate": 9.11720030460608e-06, + "loss": 1.2775, + "step": 5486 + }, + { + "epoch": 0.58, + "learning_rate": 9.113554404440317e-06, + "loss": 1.2567, + "step": 5487 + }, + { + "epoch": 0.58, + "learning_rate": 9.10990862303548e-06, + "loss": 1.3935, + "step": 5488 + }, + { + "epoch": 0.58, + "learning_rate": 9.106262960880024e-06, + "loss": 1.3544, + "step": 5489 + }, + { + "epoch": 0.58, + "learning_rate": 9.102617418462365e-06, + "loss": 1.4023, + "step": 5490 + }, + { + "epoch": 0.58, + "learning_rate": 9.098971996270918e-06, + "loss": 1.3759, + "step": 5491 + }, + { + "epoch": 0.58, + "learning_rate": 9.095326694794064e-06, + "loss": 1.4165, + "step": 5492 + }, + { + "epoch": 0.58, + "learning_rate": 9.091681514520194e-06, + "loss": 1.3189, + "step": 5493 + }, + { + "epoch": 0.58, + "learning_rate": 9.088036455937663e-06, + "loss": 1.3135, + "step": 5494 + }, + { + "epoch": 0.58, + "learning_rate": 9.084391519534815e-06, + "loss": 1.3521, + "step": 5495 + }, + { + "epoch": 0.58, + "learning_rate": 9.080746705799971e-06, + "loss": 1.3314, + "step": 5496 + }, + { + "epoch": 0.58, + "learning_rate": 9.077102015221457e-06, + "loss": 1.3119, + "step": 5497 + }, + { + "epoch": 0.58, + "learning_rate": 9.073457448287557e-06, + "loss": 1.2895, + "step": 5498 + }, + { + "epoch": 0.58, + "learning_rate": 9.069813005486554e-06, + "loss": 1.3155, + "step": 5499 + }, + { + "epoch": 0.58, + "learning_rate": 9.066168687306701e-06, + "loss": 1.4048, + "step": 5500 + }, + { + "epoch": 0.58, + "learning_rate": 9.062524494236256e-06, + "loss": 1.3665, + "step": 5501 + }, + { + "epoch": 0.58, + "learning_rate": 9.058880426763442e-06, + "loss": 1.3258, + "step": 5502 + }, + { + "epoch": 0.58, + "learning_rate": 9.05523648537647e-06, + "loss": 1.3078, + "step": 5503 + }, + { + "epoch": 0.58, + "learning_rate": 9.051592670563527e-06, + "loss": 1.361, + "step": 5504 + }, + { + "epoch": 0.58, + "learning_rate": 9.047948982812801e-06, + "loss": 1.3557, + "step": 5505 + }, + { + "epoch": 0.58, + "learning_rate": 9.044305422612453e-06, + "loss": 1.5733, + "step": 5506 + }, + { + "epoch": 0.58, + "learning_rate": 9.040661990450617e-06, + "loss": 1.2835, + "step": 5507 + }, + { + "epoch": 0.58, + "learning_rate": 9.037018686815428e-06, + "loss": 1.311, + "step": 5508 + }, + { + "epoch": 0.58, + "learning_rate": 9.033375512194993e-06, + "loss": 1.3949, + "step": 5509 + }, + { + "epoch": 0.58, + "learning_rate": 9.029732467077405e-06, + "loss": 1.356, + "step": 5510 + }, + { + "epoch": 0.58, + "learning_rate": 9.026089551950727e-06, + "loss": 1.3695, + "step": 5511 + }, + { + "epoch": 0.58, + "learning_rate": 9.022446767303033e-06, + "loss": 1.3325, + "step": 5512 + }, + { + "epoch": 0.58, + "learning_rate": 9.018804113622353e-06, + "loss": 1.401, + "step": 5513 + }, + { + "epoch": 0.58, + "learning_rate": 9.015161591396713e-06, + "loss": 1.3632, + "step": 5514 + }, + { + "epoch": 0.58, + "learning_rate": 9.011519201114108e-06, + "loss": 1.3697, + "step": 5515 + }, + { + "epoch": 0.58, + "learning_rate": 9.007876943262538e-06, + "loss": 1.2604, + "step": 5516 + }, + { + "epoch": 0.58, + "learning_rate": 9.004234818329964e-06, + "loss": 1.3557, + "step": 5517 + }, + { + "epoch": 0.58, + "learning_rate": 9.000592826804342e-06, + "loss": 1.3248, + "step": 5518 + }, + { + "epoch": 0.58, + "learning_rate": 8.996950969173596e-06, + "loss": 1.3237, + "step": 5519 + }, + { + "epoch": 0.58, + "learning_rate": 8.99330924592565e-06, + "loss": 1.339, + "step": 5520 + }, + { + "epoch": 0.58, + "learning_rate": 8.989667657548402e-06, + "loss": 1.3218, + "step": 5521 + }, + { + "epoch": 0.58, + "learning_rate": 8.986026204529728e-06, + "loss": 1.3354, + "step": 5522 + }, + { + "epoch": 0.58, + "learning_rate": 8.982384887357484e-06, + "loss": 1.3011, + "step": 5523 + }, + { + "epoch": 0.58, + "learning_rate": 8.978743706519524e-06, + "loss": 1.3526, + "step": 5524 + }, + { + "epoch": 0.58, + "learning_rate": 8.975102662503666e-06, + "loss": 1.3298, + "step": 5525 + }, + { + "epoch": 0.58, + "learning_rate": 8.971461755797718e-06, + "loss": 1.328, + "step": 5526 + }, + { + "epoch": 0.58, + "learning_rate": 8.967820986889461e-06, + "loss": 1.3705, + "step": 5527 + }, + { + "epoch": 0.58, + "learning_rate": 8.964180356266676e-06, + "loss": 1.3814, + "step": 5528 + }, + { + "epoch": 0.58, + "learning_rate": 8.96053986441711e-06, + "loss": 1.37, + "step": 5529 + }, + { + "epoch": 0.58, + "learning_rate": 8.956899511828489e-06, + "loss": 1.3224, + "step": 5530 + }, + { + "epoch": 0.58, + "learning_rate": 8.953259298988536e-06, + "loss": 1.3416, + "step": 5531 + }, + { + "epoch": 0.58, + "learning_rate": 8.949619226384942e-06, + "loss": 1.4212, + "step": 5532 + }, + { + "epoch": 0.58, + "learning_rate": 8.945979294505383e-06, + "loss": 1.4145, + "step": 5533 + }, + { + "epoch": 0.58, + "learning_rate": 8.942339503837512e-06, + "loss": 1.2179, + "step": 5534 + }, + { + "epoch": 0.58, + "learning_rate": 8.938699854868976e-06, + "loss": 1.3239, + "step": 5535 + }, + { + "epoch": 0.58, + "learning_rate": 8.93506034808739e-06, + "loss": 1.3488, + "step": 5536 + }, + { + "epoch": 0.58, + "learning_rate": 8.931420983980357e-06, + "loss": 1.3283, + "step": 5537 + }, + { + "epoch": 0.58, + "learning_rate": 8.927781763035449e-06, + "loss": 1.3866, + "step": 5538 + }, + { + "epoch": 0.58, + "learning_rate": 8.924142685740239e-06, + "loss": 1.3877, + "step": 5539 + }, + { + "epoch": 0.58, + "learning_rate": 8.920503752582265e-06, + "loss": 1.2511, + "step": 5540 + }, + { + "epoch": 0.58, + "learning_rate": 8.916864964049056e-06, + "loss": 1.3581, + "step": 5541 + }, + { + "epoch": 0.58, + "learning_rate": 8.913226320628104e-06, + "loss": 1.387, + "step": 5542 + }, + { + "epoch": 0.58, + "learning_rate": 8.909587822806905e-06, + "loss": 1.3785, + "step": 5543 + }, + { + "epoch": 0.58, + "learning_rate": 8.905949471072921e-06, + "loss": 1.4302, + "step": 5544 + }, + { + "epoch": 0.58, + "learning_rate": 8.9023112659136e-06, + "loss": 1.439, + "step": 5545 + }, + { + "epoch": 0.58, + "learning_rate": 8.898673207816357e-06, + "loss": 1.3257, + "step": 5546 + }, + { + "epoch": 0.58, + "learning_rate": 8.895035297268611e-06, + "loss": 1.4237, + "step": 5547 + }, + { + "epoch": 0.58, + "learning_rate": 8.891397534757745e-06, + "loss": 1.3141, + "step": 5548 + }, + { + "epoch": 0.58, + "learning_rate": 8.887759920771127e-06, + "loss": 1.3069, + "step": 5549 + }, + { + "epoch": 0.58, + "learning_rate": 8.884122455796095e-06, + "loss": 1.2703, + "step": 5550 + }, + { + "epoch": 0.58, + "learning_rate": 8.880485140319986e-06, + "loss": 1.2929, + "step": 5551 + }, + { + "epoch": 0.58, + "learning_rate": 8.876847974830103e-06, + "loss": 1.3719, + "step": 5552 + }, + { + "epoch": 0.58, + "learning_rate": 8.873210959813731e-06, + "loss": 1.3481, + "step": 5553 + }, + { + "epoch": 0.58, + "learning_rate": 8.869574095758141e-06, + "loss": 1.3609, + "step": 5554 + }, + { + "epoch": 0.58, + "learning_rate": 8.865937383150577e-06, + "loss": 1.3137, + "step": 5555 + }, + { + "epoch": 0.58, + "learning_rate": 8.862300822478265e-06, + "loss": 1.3602, + "step": 5556 + }, + { + "epoch": 0.58, + "learning_rate": 8.858664414228409e-06, + "loss": 1.3142, + "step": 5557 + }, + { + "epoch": 0.58, + "learning_rate": 8.855028158888196e-06, + "loss": 1.288, + "step": 5558 + }, + { + "epoch": 0.58, + "learning_rate": 8.851392056944791e-06, + "loss": 1.3407, + "step": 5559 + }, + { + "epoch": 0.58, + "learning_rate": 8.847756108885342e-06, + "loss": 1.3118, + "step": 5560 + }, + { + "epoch": 0.58, + "learning_rate": 8.84412031519696e-06, + "loss": 1.3646, + "step": 5561 + }, + { + "epoch": 0.58, + "learning_rate": 8.840484676366761e-06, + "loss": 1.3896, + "step": 5562 + }, + { + "epoch": 0.58, + "learning_rate": 8.836849192881822e-06, + "loss": 1.3296, + "step": 5563 + }, + { + "epoch": 0.58, + "learning_rate": 8.833213865229208e-06, + "loss": 1.2918, + "step": 5564 + }, + { + "epoch": 0.58, + "learning_rate": 8.82957869389595e-06, + "loss": 1.4811, + "step": 5565 + }, + { + "epoch": 0.58, + "learning_rate": 8.82594367936908e-06, + "loss": 1.3877, + "step": 5566 + }, + { + "epoch": 0.58, + "learning_rate": 8.822308822135588e-06, + "loss": 1.3716, + "step": 5567 + }, + { + "epoch": 0.58, + "learning_rate": 8.818674122682456e-06, + "loss": 1.3204, + "step": 5568 + }, + { + "epoch": 0.58, + "learning_rate": 8.815039581496634e-06, + "loss": 1.326, + "step": 5569 + }, + { + "epoch": 0.58, + "learning_rate": 8.811405199065066e-06, + "loss": 1.3762, + "step": 5570 + }, + { + "epoch": 0.58, + "learning_rate": 8.807770975874658e-06, + "loss": 1.2944, + "step": 5571 + }, + { + "epoch": 0.58, + "learning_rate": 8.804136912412311e-06, + "loss": 1.3057, + "step": 5572 + }, + { + "epoch": 0.58, + "eval_loss": 1.4187605381011963, + "eval_runtime": 77.5157, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 5572 + }, + { + "epoch": 0.58, + "learning_rate": 8.800503009164884e-06, + "loss": 1.4144, + "step": 5573 + }, + { + "epoch": 0.58, + "learning_rate": 8.796869266619238e-06, + "loss": 1.2218, + "step": 5574 + }, + { + "epoch": 0.58, + "learning_rate": 8.793235685262197e-06, + "loss": 1.4445, + "step": 5575 + }, + { + "epoch": 0.58, + "learning_rate": 8.789602265580565e-06, + "loss": 1.3761, + "step": 5576 + }, + { + "epoch": 0.58, + "learning_rate": 8.78596900806113e-06, + "loss": 1.3762, + "step": 5577 + }, + { + "epoch": 0.58, + "learning_rate": 8.782335913190657e-06, + "loss": 1.3506, + "step": 5578 + }, + { + "epoch": 0.59, + "learning_rate": 8.778702981455883e-06, + "loss": 1.4183, + "step": 5579 + }, + { + "epoch": 0.59, + "learning_rate": 8.775070213343528e-06, + "loss": 1.3123, + "step": 5580 + }, + { + "epoch": 0.59, + "learning_rate": 8.771437609340291e-06, + "loss": 1.3168, + "step": 5581 + }, + { + "epoch": 0.59, + "learning_rate": 8.76780516993285e-06, + "loss": 1.3939, + "step": 5582 + }, + { + "epoch": 0.59, + "learning_rate": 8.764172895607856e-06, + "loss": 1.3317, + "step": 5583 + }, + { + "epoch": 0.59, + "learning_rate": 8.760540786851937e-06, + "loss": 1.3094, + "step": 5584 + }, + { + "epoch": 0.59, + "learning_rate": 8.756908844151708e-06, + "loss": 1.2853, + "step": 5585 + }, + { + "epoch": 0.59, + "learning_rate": 8.753277067993752e-06, + "loss": 1.2625, + "step": 5586 + }, + { + "epoch": 0.59, + "learning_rate": 8.74964545886464e-06, + "loss": 1.4246, + "step": 5587 + }, + { + "epoch": 0.59, + "learning_rate": 8.746014017250904e-06, + "loss": 1.2891, + "step": 5588 + }, + { + "epoch": 0.59, + "learning_rate": 8.742382743639071e-06, + "loss": 1.3135, + "step": 5589 + }, + { + "epoch": 0.59, + "learning_rate": 8.738751638515639e-06, + "loss": 1.3021, + "step": 5590 + }, + { + "epoch": 0.59, + "learning_rate": 8.735120702367082e-06, + "loss": 1.3398, + "step": 5591 + }, + { + "epoch": 0.59, + "learning_rate": 8.731489935679845e-06, + "loss": 1.4173, + "step": 5592 + }, + { + "epoch": 0.59, + "learning_rate": 8.727859338940367e-06, + "loss": 1.4129, + "step": 5593 + }, + { + "epoch": 0.59, + "learning_rate": 8.724228912635053e-06, + "loss": 1.3807, + "step": 5594 + }, + { + "epoch": 0.59, + "learning_rate": 8.720598657250284e-06, + "loss": 1.2962, + "step": 5595 + }, + { + "epoch": 0.59, + "learning_rate": 8.716968573272416e-06, + "loss": 1.3784, + "step": 5596 + }, + { + "epoch": 0.59, + "learning_rate": 8.713338661187799e-06, + "loss": 1.3751, + "step": 5597 + }, + { + "epoch": 0.59, + "learning_rate": 8.70970892148274e-06, + "loss": 1.3122, + "step": 5598 + }, + { + "epoch": 0.59, + "learning_rate": 8.70607935464353e-06, + "loss": 1.4174, + "step": 5599 + }, + { + "epoch": 0.59, + "learning_rate": 8.702449961156445e-06, + "loss": 1.3275, + "step": 5600 + }, + { + "epoch": 0.59, + "learning_rate": 8.698820741507723e-06, + "loss": 1.33, + "step": 5601 + }, + { + "epoch": 0.59, + "learning_rate": 8.695191696183589e-06, + "loss": 1.4075, + "step": 5602 + }, + { + "epoch": 0.59, + "learning_rate": 8.69156282567024e-06, + "loss": 1.3778, + "step": 5603 + }, + { + "epoch": 0.59, + "learning_rate": 8.687934130453857e-06, + "loss": 1.3222, + "step": 5604 + }, + { + "epoch": 0.59, + "learning_rate": 8.684305611020587e-06, + "loss": 1.3443, + "step": 5605 + }, + { + "epoch": 0.59, + "learning_rate": 8.680677267856558e-06, + "loss": 1.3167, + "step": 5606 + }, + { + "epoch": 0.59, + "learning_rate": 8.677049101447877e-06, + "loss": 1.3209, + "step": 5607 + }, + { + "epoch": 0.59, + "learning_rate": 8.673421112280624e-06, + "loss": 1.3125, + "step": 5608 + }, + { + "epoch": 0.59, + "learning_rate": 8.669793300840857e-06, + "loss": 1.375, + "step": 5609 + }, + { + "epoch": 0.59, + "learning_rate": 8.666165667614612e-06, + "loss": 1.3627, + "step": 5610 + }, + { + "epoch": 0.59, + "learning_rate": 8.662538213087888e-06, + "loss": 1.3064, + "step": 5611 + }, + { + "epoch": 0.59, + "learning_rate": 8.658910937746685e-06, + "loss": 1.4251, + "step": 5612 + }, + { + "epoch": 0.59, + "learning_rate": 8.655283842076956e-06, + "loss": 1.3011, + "step": 5613 + }, + { + "epoch": 0.59, + "learning_rate": 8.651656926564645e-06, + "loss": 1.3299, + "step": 5614 + }, + { + "epoch": 0.59, + "learning_rate": 8.648030191695653e-06, + "loss": 1.3448, + "step": 5615 + }, + { + "epoch": 0.59, + "learning_rate": 8.644403637955883e-06, + "loss": 1.4048, + "step": 5616 + }, + { + "epoch": 0.59, + "learning_rate": 8.640777265831195e-06, + "loss": 1.336, + "step": 5617 + }, + { + "epoch": 0.59, + "learning_rate": 8.63715107580743e-06, + "loss": 1.4959, + "step": 5618 + }, + { + "epoch": 0.59, + "learning_rate": 8.633525068370397e-06, + "loss": 1.3822, + "step": 5619 + }, + { + "epoch": 0.59, + "learning_rate": 8.6298992440059e-06, + "loss": 1.282, + "step": 5620 + }, + { + "epoch": 0.59, + "learning_rate": 8.626273603199699e-06, + "loss": 1.1873, + "step": 5621 + }, + { + "epoch": 0.59, + "learning_rate": 8.622648146437538e-06, + "loss": 1.3706, + "step": 5622 + }, + { + "epoch": 0.59, + "learning_rate": 8.619022874205138e-06, + "loss": 1.2709, + "step": 5623 + }, + { + "epoch": 0.59, + "learning_rate": 8.615397786988188e-06, + "loss": 1.3608, + "step": 5624 + }, + { + "epoch": 0.59, + "learning_rate": 8.61177288527236e-06, + "loss": 1.3821, + "step": 5625 + }, + { + "epoch": 0.59, + "learning_rate": 8.608148169543292e-06, + "loss": 1.327, + "step": 5626 + }, + { + "epoch": 0.59, + "learning_rate": 8.604523640286611e-06, + "loss": 1.3544, + "step": 5627 + }, + { + "epoch": 0.59, + "learning_rate": 8.600899297987905e-06, + "loss": 1.3269, + "step": 5628 + }, + { + "epoch": 0.59, + "learning_rate": 8.597275143132745e-06, + "loss": 1.3142, + "step": 5629 + }, + { + "epoch": 0.59, + "learning_rate": 8.593651176206671e-06, + "loss": 1.3878, + "step": 5630 + }, + { + "epoch": 0.59, + "learning_rate": 8.59002739769521e-06, + "loss": 1.3386, + "step": 5631 + }, + { + "epoch": 0.59, + "learning_rate": 8.586403808083846e-06, + "loss": 1.3484, + "step": 5632 + }, + { + "epoch": 0.59, + "learning_rate": 8.582780407858052e-06, + "loss": 1.3676, + "step": 5633 + }, + { + "epoch": 0.59, + "learning_rate": 8.579157197503265e-06, + "loss": 1.3753, + "step": 5634 + }, + { + "epoch": 0.59, + "learning_rate": 8.57553417750491e-06, + "loss": 1.4058, + "step": 5635 + }, + { + "epoch": 0.59, + "learning_rate": 8.571911348348375e-06, + "loss": 1.4434, + "step": 5636 + }, + { + "epoch": 0.59, + "learning_rate": 8.568288710519027e-06, + "loss": 1.3398, + "step": 5637 + }, + { + "epoch": 0.59, + "learning_rate": 8.564666264502199e-06, + "loss": 1.3294, + "step": 5638 + }, + { + "epoch": 0.59, + "learning_rate": 8.561044010783216e-06, + "loss": 1.3165, + "step": 5639 + }, + { + "epoch": 0.59, + "learning_rate": 8.557421949847363e-06, + "loss": 1.3437, + "step": 5640 + }, + { + "epoch": 0.59, + "learning_rate": 8.553800082179905e-06, + "loss": 1.3473, + "step": 5641 + }, + { + "epoch": 0.59, + "learning_rate": 8.55017840826607e-06, + "loss": 1.3378, + "step": 5642 + }, + { + "epoch": 0.59, + "learning_rate": 8.546556928591082e-06, + "loss": 1.3357, + "step": 5643 + }, + { + "epoch": 0.59, + "learning_rate": 8.54293564364012e-06, + "loss": 1.3435, + "step": 5644 + }, + { + "epoch": 0.59, + "learning_rate": 8.53931455389834e-06, + "loss": 1.3335, + "step": 5645 + }, + { + "epoch": 0.59, + "learning_rate": 8.535693659850885e-06, + "loss": 1.2917, + "step": 5646 + }, + { + "epoch": 0.59, + "learning_rate": 8.532072961982851e-06, + "loss": 1.3785, + "step": 5647 + }, + { + "epoch": 0.59, + "learning_rate": 8.528452460779327e-06, + "loss": 1.3634, + "step": 5648 + }, + { + "epoch": 0.59, + "learning_rate": 8.524832156725359e-06, + "loss": 1.3541, + "step": 5649 + }, + { + "epoch": 0.59, + "learning_rate": 8.521212050305978e-06, + "loss": 1.335, + "step": 5650 + }, + { + "epoch": 0.59, + "learning_rate": 8.51759214200619e-06, + "loss": 1.3011, + "step": 5651 + }, + { + "epoch": 0.59, + "learning_rate": 8.513972432310965e-06, + "loss": 1.3982, + "step": 5652 + }, + { + "epoch": 0.59, + "learning_rate": 8.510352921705247e-06, + "loss": 1.3217, + "step": 5653 + }, + { + "epoch": 0.59, + "learning_rate": 8.506733610673968e-06, + "loss": 1.3275, + "step": 5654 + }, + { + "epoch": 0.59, + "learning_rate": 8.503114499702015e-06, + "loss": 1.3335, + "step": 5655 + }, + { + "epoch": 0.59, + "learning_rate": 8.499495589274257e-06, + "loss": 1.3567, + "step": 5656 + }, + { + "epoch": 0.59, + "learning_rate": 8.495876879875536e-06, + "loss": 1.348, + "step": 5657 + }, + { + "epoch": 0.59, + "learning_rate": 8.492258371990667e-06, + "loss": 1.3991, + "step": 5658 + }, + { + "epoch": 0.59, + "learning_rate": 8.488640066104435e-06, + "loss": 1.3528, + "step": 5659 + }, + { + "epoch": 0.59, + "learning_rate": 8.485021962701603e-06, + "loss": 1.3275, + "step": 5660 + }, + { + "epoch": 0.59, + "learning_rate": 8.481404062266897e-06, + "loss": 1.3605, + "step": 5661 + }, + { + "epoch": 0.59, + "learning_rate": 8.477786365285032e-06, + "loss": 1.3288, + "step": 5662 + }, + { + "epoch": 0.59, + "learning_rate": 8.474168872240682e-06, + "loss": 1.3274, + "step": 5663 + }, + { + "epoch": 0.59, + "learning_rate": 8.470551583618498e-06, + "loss": 1.273, + "step": 5664 + }, + { + "epoch": 0.59, + "learning_rate": 8.4669344999031e-06, + "loss": 1.3142, + "step": 5665 + }, + { + "epoch": 0.59, + "learning_rate": 8.463317621579091e-06, + "loss": 1.2912, + "step": 5666 + }, + { + "epoch": 0.59, + "learning_rate": 8.459700949131037e-06, + "loss": 1.3162, + "step": 5667 + }, + { + "epoch": 0.59, + "learning_rate": 8.456084483043479e-06, + "loss": 1.3377, + "step": 5668 + }, + { + "epoch": 0.59, + "learning_rate": 8.452468223800931e-06, + "loss": 1.3545, + "step": 5669 + }, + { + "epoch": 0.59, + "learning_rate": 8.448852171887878e-06, + "loss": 1.4052, + "step": 5670 + }, + { + "epoch": 0.59, + "learning_rate": 8.44523632778878e-06, + "loss": 1.3389, + "step": 5671 + }, + { + "epoch": 0.59, + "learning_rate": 8.441620691988063e-06, + "loss": 1.3801, + "step": 5672 + }, + { + "epoch": 0.59, + "learning_rate": 8.438005264970134e-06, + "loss": 1.2978, + "step": 5673 + }, + { + "epoch": 0.6, + "learning_rate": 8.434390047219366e-06, + "loss": 1.437, + "step": 5674 + }, + { + "epoch": 0.6, + "learning_rate": 8.430775039220103e-06, + "loss": 1.3602, + "step": 5675 + }, + { + "epoch": 0.6, + "learning_rate": 8.427160241456664e-06, + "loss": 1.4971, + "step": 5676 + }, + { + "epoch": 0.6, + "learning_rate": 8.423545654413342e-06, + "loss": 1.2765, + "step": 5677 + }, + { + "epoch": 0.6, + "learning_rate": 8.419931278574397e-06, + "loss": 1.4346, + "step": 5678 + }, + { + "epoch": 0.6, + "learning_rate": 8.416317114424059e-06, + "loss": 1.366, + "step": 5679 + }, + { + "epoch": 0.6, + "learning_rate": 8.412703162446536e-06, + "loss": 1.3776, + "step": 5680 + }, + { + "epoch": 0.6, + "learning_rate": 8.409089423126009e-06, + "loss": 1.2516, + "step": 5681 + }, + { + "epoch": 0.6, + "learning_rate": 8.405475896946621e-06, + "loss": 1.4257, + "step": 5682 + }, + { + "epoch": 0.6, + "learning_rate": 8.401862584392492e-06, + "loss": 1.3523, + "step": 5683 + }, + { + "epoch": 0.6, + "learning_rate": 8.398249485947712e-06, + "loss": 1.3791, + "step": 5684 + }, + { + "epoch": 0.6, + "learning_rate": 8.394636602096348e-06, + "loss": 1.3574, + "step": 5685 + }, + { + "epoch": 0.6, + "learning_rate": 8.39102393332243e-06, + "loss": 1.4748, + "step": 5686 + }, + { + "epoch": 0.6, + "learning_rate": 8.387411480109967e-06, + "loss": 1.3693, + "step": 5687 + }, + { + "epoch": 0.6, + "learning_rate": 8.383799242942925e-06, + "loss": 1.3643, + "step": 5688 + }, + { + "epoch": 0.6, + "learning_rate": 8.38018722230526e-06, + "loss": 1.3446, + "step": 5689 + }, + { + "epoch": 0.6, + "learning_rate": 8.37657541868089e-06, + "loss": 1.3552, + "step": 5690 + }, + { + "epoch": 0.6, + "learning_rate": 8.372963832553698e-06, + "loss": 1.3636, + "step": 5691 + }, + { + "epoch": 0.6, + "learning_rate": 8.36935246440755e-06, + "loss": 1.3398, + "step": 5692 + }, + { + "epoch": 0.6, + "learning_rate": 8.365741314726273e-06, + "loss": 1.3336, + "step": 5693 + }, + { + "epoch": 0.6, + "learning_rate": 8.362130383993667e-06, + "loss": 1.3023, + "step": 5694 + }, + { + "epoch": 0.6, + "learning_rate": 8.358519672693506e-06, + "loss": 1.3591, + "step": 5695 + }, + { + "epoch": 0.6, + "learning_rate": 8.354909181309533e-06, + "loss": 1.3113, + "step": 5696 + }, + { + "epoch": 0.6, + "learning_rate": 8.351298910325462e-06, + "loss": 1.3747, + "step": 5697 + }, + { + "epoch": 0.6, + "learning_rate": 8.347688860224976e-06, + "loss": 1.3555, + "step": 5698 + }, + { + "epoch": 0.6, + "learning_rate": 8.344079031491722e-06, + "loss": 1.2947, + "step": 5699 + }, + { + "epoch": 0.6, + "learning_rate": 8.340469424609337e-06, + "loss": 1.4099, + "step": 5700 + }, + { + "epoch": 0.6, + "learning_rate": 8.336860040061404e-06, + "loss": 1.3263, + "step": 5701 + }, + { + "epoch": 0.6, + "learning_rate": 8.333250878331498e-06, + "loss": 1.372, + "step": 5702 + }, + { + "epoch": 0.6, + "learning_rate": 8.329641939903142e-06, + "loss": 1.3523, + "step": 5703 + }, + { + "epoch": 0.6, + "learning_rate": 8.32603322525985e-06, + "loss": 1.3451, + "step": 5704 + }, + { + "epoch": 0.6, + "learning_rate": 8.322424734885098e-06, + "loss": 1.3296, + "step": 5705 + }, + { + "epoch": 0.6, + "learning_rate": 8.318816469262325e-06, + "loss": 1.449, + "step": 5706 + }, + { + "epoch": 0.6, + "learning_rate": 8.315208428874946e-06, + "loss": 1.3611, + "step": 5707 + }, + { + "epoch": 0.6, + "learning_rate": 8.311600614206352e-06, + "loss": 1.3849, + "step": 5708 + }, + { + "epoch": 0.6, + "learning_rate": 8.307993025739893e-06, + "loss": 1.3968, + "step": 5709 + }, + { + "epoch": 0.6, + "learning_rate": 8.304385663958895e-06, + "loss": 1.4428, + "step": 5710 + }, + { + "epoch": 0.6, + "learning_rate": 8.300778529346647e-06, + "loss": 1.3095, + "step": 5711 + }, + { + "epoch": 0.6, + "learning_rate": 8.297171622386418e-06, + "loss": 1.3135, + "step": 5712 + }, + { + "epoch": 0.6, + "learning_rate": 8.293564943561438e-06, + "loss": 1.3069, + "step": 5713 + }, + { + "epoch": 0.6, + "learning_rate": 8.28995849335491e-06, + "loss": 1.3736, + "step": 5714 + }, + { + "epoch": 0.6, + "learning_rate": 8.286352272250007e-06, + "loss": 1.343, + "step": 5715 + }, + { + "epoch": 0.6, + "learning_rate": 8.28274628072987e-06, + "loss": 1.2929, + "step": 5716 + }, + { + "epoch": 0.6, + "learning_rate": 8.279140519277607e-06, + "loss": 1.3356, + "step": 5717 + }, + { + "epoch": 0.6, + "learning_rate": 8.275534988376295e-06, + "loss": 1.2683, + "step": 5718 + }, + { + "epoch": 0.6, + "learning_rate": 8.27192968850899e-06, + "loss": 1.3738, + "step": 5719 + }, + { + "epoch": 0.6, + "learning_rate": 8.268324620158704e-06, + "loss": 1.3369, + "step": 5720 + }, + { + "epoch": 0.6, + "learning_rate": 8.264719783808425e-06, + "loss": 1.3684, + "step": 5721 + }, + { + "epoch": 0.6, + "learning_rate": 8.261115179941108e-06, + "loss": 1.4081, + "step": 5722 + }, + { + "epoch": 0.6, + "learning_rate": 8.257510809039678e-06, + "loss": 1.2504, + "step": 5723 + }, + { + "epoch": 0.6, + "learning_rate": 8.253906671587029e-06, + "loss": 1.417, + "step": 5724 + }, + { + "epoch": 0.6, + "learning_rate": 8.25030276806602e-06, + "loss": 1.3631, + "step": 5725 + }, + { + "epoch": 0.6, + "learning_rate": 8.246699098959483e-06, + "loss": 1.499, + "step": 5726 + }, + { + "epoch": 0.6, + "learning_rate": 8.243095664750217e-06, + "loss": 1.3656, + "step": 5727 + }, + { + "epoch": 0.6, + "learning_rate": 8.239492465920992e-06, + "loss": 1.3563, + "step": 5728 + }, + { + "epoch": 0.6, + "learning_rate": 8.23588950295454e-06, + "loss": 1.3554, + "step": 5729 + }, + { + "epoch": 0.6, + "learning_rate": 8.232286776333566e-06, + "loss": 1.2705, + "step": 5730 + }, + { + "epoch": 0.6, + "learning_rate": 8.228684286540747e-06, + "loss": 1.3792, + "step": 5731 + }, + { + "epoch": 0.6, + "learning_rate": 8.22508203405872e-06, + "loss": 1.3301, + "step": 5732 + }, + { + "epoch": 0.6, + "learning_rate": 8.221480019370095e-06, + "loss": 1.36, + "step": 5733 + }, + { + "epoch": 0.6, + "learning_rate": 8.217878242957448e-06, + "loss": 1.4406, + "step": 5734 + }, + { + "epoch": 0.6, + "learning_rate": 8.214276705303328e-06, + "loss": 1.2886, + "step": 5735 + }, + { + "epoch": 0.6, + "learning_rate": 8.210675406890248e-06, + "loss": 1.3072, + "step": 5736 + }, + { + "epoch": 0.6, + "learning_rate": 8.207074348200686e-06, + "loss": 1.3734, + "step": 5737 + }, + { + "epoch": 0.6, + "learning_rate": 8.203473529717095e-06, + "loss": 1.3893, + "step": 5738 + }, + { + "epoch": 0.6, + "learning_rate": 8.199872951921892e-06, + "loss": 1.3427, + "step": 5739 + }, + { + "epoch": 0.6, + "learning_rate": 8.196272615297459e-06, + "loss": 1.3125, + "step": 5740 + }, + { + "epoch": 0.6, + "learning_rate": 8.19267252032615e-06, + "loss": 1.3079, + "step": 5741 + }, + { + "epoch": 0.6, + "learning_rate": 8.189072667490285e-06, + "loss": 1.2971, + "step": 5742 + }, + { + "epoch": 0.6, + "learning_rate": 8.185473057272154e-06, + "loss": 1.3003, + "step": 5743 + }, + { + "epoch": 0.6, + "learning_rate": 8.18187369015401e-06, + "loss": 1.3002, + "step": 5744 + }, + { + "epoch": 0.6, + "learning_rate": 8.178274566618075e-06, + "loss": 1.2852, + "step": 5745 + }, + { + "epoch": 0.6, + "learning_rate": 8.174675687146542e-06, + "loss": 1.2807, + "step": 5746 + }, + { + "epoch": 0.6, + "learning_rate": 8.171077052221567e-06, + "loss": 1.2983, + "step": 5747 + }, + { + "epoch": 0.6, + "learning_rate": 8.167478662325274e-06, + "loss": 1.3002, + "step": 5748 + }, + { + "epoch": 0.6, + "learning_rate": 8.163880517939753e-06, + "loss": 1.2575, + "step": 5749 + }, + { + "epoch": 0.6, + "learning_rate": 8.160282619547068e-06, + "loss": 1.2627, + "step": 5750 + }, + { + "epoch": 0.6, + "learning_rate": 8.156684967629242e-06, + "loss": 1.2549, + "step": 5751 + }, + { + "epoch": 0.6, + "learning_rate": 8.153087562668265e-06, + "loss": 1.2595, + "step": 5752 + }, + { + "epoch": 0.6, + "learning_rate": 8.1494904051461e-06, + "loss": 1.2788, + "step": 5753 + }, + { + "epoch": 0.6, + "learning_rate": 8.145893495544676e-06, + "loss": 1.3028, + "step": 5754 + }, + { + "epoch": 0.6, + "learning_rate": 8.142296834345883e-06, + "loss": 1.3019, + "step": 5755 + }, + { + "epoch": 0.6, + "learning_rate": 8.138700422031583e-06, + "loss": 1.2998, + "step": 5756 + }, + { + "epoch": 0.6, + "learning_rate": 8.135104259083598e-06, + "loss": 1.3298, + "step": 5757 + }, + { + "epoch": 0.6, + "learning_rate": 8.13150834598373e-06, + "loss": 1.2681, + "step": 5758 + }, + { + "epoch": 0.6, + "learning_rate": 8.127912683213733e-06, + "loss": 1.2987, + "step": 5759 + }, + { + "epoch": 0.6, + "learning_rate": 8.124317271255331e-06, + "loss": 1.3181, + "step": 5760 + }, + { + "epoch": 0.6, + "learning_rate": 8.120722110590224e-06, + "loss": 1.423, + "step": 5761 + }, + { + "epoch": 0.6, + "learning_rate": 8.117127201700067e-06, + "loss": 1.5029, + "step": 5762 + }, + { + "epoch": 0.6, + "learning_rate": 8.113532545066488e-06, + "loss": 1.3016, + "step": 5763 + }, + { + "epoch": 0.6, + "learning_rate": 8.109938141171074e-06, + "loss": 1.3906, + "step": 5764 + }, + { + "epoch": 0.6, + "learning_rate": 8.106343990495387e-06, + "loss": 1.3363, + "step": 5765 + }, + { + "epoch": 0.6, + "learning_rate": 8.10275009352095e-06, + "loss": 1.314, + "step": 5766 + }, + { + "epoch": 0.6, + "learning_rate": 8.09915645072925e-06, + "loss": 1.3484, + "step": 5767 + }, + { + "epoch": 0.6, + "learning_rate": 8.095563062601745e-06, + "loss": 1.3757, + "step": 5768 + }, + { + "epoch": 0.6, + "learning_rate": 8.091969929619859e-06, + "loss": 1.3068, + "step": 5769 + }, + { + "epoch": 0.61, + "learning_rate": 8.088377052264976e-06, + "loss": 1.3486, + "step": 5770 + }, + { + "epoch": 0.61, + "learning_rate": 8.08478443101845e-06, + "loss": 1.244, + "step": 5771 + }, + { + "epoch": 0.61, + "eval_loss": 1.4178493022918701, + "eval_runtime": 77.6086, + "eval_samples_per_second": 1.662, + "eval_steps_per_second": 0.116, + "step": 5771 + }, + { + "epoch": 0.61, + "learning_rate": 8.0811920663616e-06, + "loss": 1.3325, + "step": 5772 + }, + { + "epoch": 0.61, + "learning_rate": 8.077599958775713e-06, + "loss": 1.336, + "step": 5773 + }, + { + "epoch": 0.61, + "learning_rate": 8.074008108742037e-06, + "loss": 1.3167, + "step": 5774 + }, + { + "epoch": 0.61, + "learning_rate": 8.070416516741786e-06, + "loss": 1.3166, + "step": 5775 + }, + { + "epoch": 0.61, + "learning_rate": 8.066825183256141e-06, + "loss": 1.3377, + "step": 5776 + }, + { + "epoch": 0.61, + "learning_rate": 8.063234108766253e-06, + "loss": 1.3704, + "step": 5777 + }, + { + "epoch": 0.61, + "learning_rate": 8.059643293753233e-06, + "loss": 1.3596, + "step": 5778 + }, + { + "epoch": 0.61, + "learning_rate": 8.056052738698153e-06, + "loss": 1.4477, + "step": 5779 + }, + { + "epoch": 0.61, + "learning_rate": 8.052462444082055e-06, + "loss": 1.338, + "step": 5780 + }, + { + "epoch": 0.61, + "learning_rate": 8.048872410385952e-06, + "loss": 1.2714, + "step": 5781 + }, + { + "epoch": 0.61, + "learning_rate": 8.045282638090815e-06, + "loss": 0.9642, + "step": 5782 + }, + { + "epoch": 0.61, + "learning_rate": 8.041693127677576e-06, + "loss": 0.8702, + "step": 5783 + }, + { + "epoch": 0.61, + "learning_rate": 8.038103879627144e-06, + "loss": 0.8986, + "step": 5784 + }, + { + "epoch": 0.61, + "learning_rate": 8.034514894420382e-06, + "loss": 0.804, + "step": 5785 + }, + { + "epoch": 0.61, + "learning_rate": 8.030926172538122e-06, + "loss": 0.7958, + "step": 5786 + }, + { + "epoch": 0.61, + "learning_rate": 8.02733771446116e-06, + "loss": 0.7608, + "step": 5787 + }, + { + "epoch": 0.61, + "learning_rate": 8.023749520670261e-06, + "loss": 0.7792, + "step": 5788 + }, + { + "epoch": 0.61, + "learning_rate": 8.020161591646147e-06, + "loss": 0.7293, + "step": 5789 + }, + { + "epoch": 0.61, + "learning_rate": 8.016573927869511e-06, + "loss": 1.1287, + "step": 5790 + }, + { + "epoch": 0.61, + "learning_rate": 8.012986529821004e-06, + "loss": 1.3344, + "step": 5791 + }, + { + "epoch": 0.61, + "learning_rate": 8.009399397981248e-06, + "loss": 1.4415, + "step": 5792 + }, + { + "epoch": 0.61, + "learning_rate": 8.005812532830826e-06, + "loss": 1.4265, + "step": 5793 + }, + { + "epoch": 0.61, + "learning_rate": 8.002225934850287e-06, + "loss": 1.3429, + "step": 5794 + }, + { + "epoch": 0.61, + "learning_rate": 7.998639604520137e-06, + "loss": 1.3653, + "step": 5795 + }, + { + "epoch": 0.61, + "learning_rate": 7.995053542320861e-06, + "loss": 1.486, + "step": 5796 + }, + { + "epoch": 0.61, + "learning_rate": 7.991467748732894e-06, + "loss": 1.3389, + "step": 5797 + }, + { + "epoch": 0.61, + "learning_rate": 7.98788222423664e-06, + "loss": 1.3206, + "step": 5798 + }, + { + "epoch": 0.61, + "learning_rate": 7.984296969312468e-06, + "loss": 1.3121, + "step": 5799 + }, + { + "epoch": 0.61, + "learning_rate": 7.980711984440712e-06, + "loss": 1.3512, + "step": 5800 + }, + { + "epoch": 0.61, + "learning_rate": 7.977127270101665e-06, + "loss": 1.3291, + "step": 5801 + }, + { + "epoch": 0.61, + "learning_rate": 7.97354282677559e-06, + "loss": 1.3948, + "step": 5802 + }, + { + "epoch": 0.61, + "learning_rate": 7.969958654942704e-06, + "loss": 1.3076, + "step": 5803 + }, + { + "epoch": 0.61, + "learning_rate": 7.966374755083202e-06, + "loss": 1.3838, + "step": 5804 + }, + { + "epoch": 0.61, + "learning_rate": 7.962791127677228e-06, + "loss": 1.4205, + "step": 5805 + }, + { + "epoch": 0.61, + "learning_rate": 7.959207773204899e-06, + "loss": 1.3635, + "step": 5806 + }, + { + "epoch": 0.61, + "learning_rate": 7.955624692146293e-06, + "loss": 1.3299, + "step": 5807 + }, + { + "epoch": 0.61, + "learning_rate": 7.95204188498145e-06, + "loss": 1.4435, + "step": 5808 + }, + { + "epoch": 0.61, + "learning_rate": 7.948459352190372e-06, + "loss": 1.4335, + "step": 5809 + }, + { + "epoch": 0.61, + "learning_rate": 7.944877094253027e-06, + "loss": 1.3391, + "step": 5810 + }, + { + "epoch": 0.61, + "learning_rate": 7.94129511164935e-06, + "loss": 1.2852, + "step": 5811 + }, + { + "epoch": 0.61, + "learning_rate": 7.93771340485923e-06, + "loss": 1.3174, + "step": 5812 + }, + { + "epoch": 0.61, + "learning_rate": 7.934131974362527e-06, + "loss": 1.3415, + "step": 5813 + }, + { + "epoch": 0.61, + "learning_rate": 7.930550820639055e-06, + "loss": 1.2764, + "step": 5814 + }, + { + "epoch": 0.61, + "learning_rate": 7.926969944168603e-06, + "loss": 1.2978, + "step": 5815 + }, + { + "epoch": 0.61, + "learning_rate": 7.923389345430911e-06, + "loss": 1.3046, + "step": 5816 + }, + { + "epoch": 0.61, + "learning_rate": 7.919809024905694e-06, + "loss": 1.3484, + "step": 5817 + }, + { + "epoch": 0.61, + "learning_rate": 7.916228983072614e-06, + "loss": 1.3207, + "step": 5818 + }, + { + "epoch": 0.61, + "learning_rate": 7.912649220411312e-06, + "loss": 1.4289, + "step": 5819 + }, + { + "epoch": 0.61, + "learning_rate": 7.909069737401382e-06, + "loss": 1.4359, + "step": 5820 + }, + { + "epoch": 0.61, + "learning_rate": 7.905490534522384e-06, + "loss": 1.3316, + "step": 5821 + }, + { + "epoch": 0.61, + "learning_rate": 7.901911612253834e-06, + "loss": 1.3112, + "step": 5822 + }, + { + "epoch": 0.61, + "learning_rate": 7.898332971075221e-06, + "loss": 1.3318, + "step": 5823 + }, + { + "epoch": 0.61, + "learning_rate": 7.894754611465992e-06, + "loss": 1.4373, + "step": 5824 + }, + { + "epoch": 0.61, + "learning_rate": 7.891176533905549e-06, + "loss": 1.2938, + "step": 5825 + }, + { + "epoch": 0.61, + "learning_rate": 7.887598738873266e-06, + "loss": 1.3471, + "step": 5826 + }, + { + "epoch": 0.61, + "learning_rate": 7.884021226848478e-06, + "loss": 1.2999, + "step": 5827 + }, + { + "epoch": 0.61, + "learning_rate": 7.880443998310475e-06, + "loss": 1.35, + "step": 5828 + }, + { + "epoch": 0.61, + "learning_rate": 7.876867053738517e-06, + "loss": 1.3307, + "step": 5829 + }, + { + "epoch": 0.61, + "learning_rate": 7.87329039361182e-06, + "loss": 1.393, + "step": 5830 + }, + { + "epoch": 0.61, + "learning_rate": 7.869714018409568e-06, + "loss": 1.2933, + "step": 5831 + }, + { + "epoch": 0.61, + "learning_rate": 7.866137928610903e-06, + "loss": 1.319, + "step": 5832 + }, + { + "epoch": 0.61, + "learning_rate": 7.862562124694925e-06, + "loss": 1.3088, + "step": 5833 + }, + { + "epoch": 0.61, + "learning_rate": 7.858986607140705e-06, + "loss": 1.2941, + "step": 5834 + }, + { + "epoch": 0.61, + "learning_rate": 7.855411376427267e-06, + "loss": 1.3214, + "step": 5835 + }, + { + "epoch": 0.61, + "learning_rate": 7.851836433033602e-06, + "loss": 1.2991, + "step": 5836 + }, + { + "epoch": 0.61, + "learning_rate": 7.848261777438656e-06, + "loss": 1.3117, + "step": 5837 + }, + { + "epoch": 0.61, + "learning_rate": 7.844687410121348e-06, + "loss": 1.2905, + "step": 5838 + }, + { + "epoch": 0.61, + "learning_rate": 7.841113331560548e-06, + "loss": 1.3688, + "step": 5839 + }, + { + "epoch": 0.61, + "learning_rate": 7.837539542235091e-06, + "loss": 1.3987, + "step": 5840 + }, + { + "epoch": 0.61, + "learning_rate": 7.83396604262377e-06, + "loss": 1.2693, + "step": 5841 + }, + { + "epoch": 0.61, + "learning_rate": 7.830392833205348e-06, + "loss": 1.3205, + "step": 5842 + }, + { + "epoch": 0.61, + "learning_rate": 7.826819914458538e-06, + "loss": 1.3325, + "step": 5843 + }, + { + "epoch": 0.61, + "learning_rate": 7.823247286862024e-06, + "loss": 1.3451, + "step": 5844 + }, + { + "epoch": 0.61, + "learning_rate": 7.81967495089444e-06, + "loss": 1.3484, + "step": 5845 + }, + { + "epoch": 0.61, + "learning_rate": 7.816102907034395e-06, + "loss": 1.4949, + "step": 5846 + }, + { + "epoch": 0.61, + "learning_rate": 7.812531155760445e-06, + "loss": 1.4293, + "step": 5847 + }, + { + "epoch": 0.61, + "learning_rate": 7.808959697551113e-06, + "loss": 1.4314, + "step": 5848 + }, + { + "epoch": 0.61, + "learning_rate": 7.805388532884887e-06, + "loss": 1.3188, + "step": 5849 + }, + { + "epoch": 0.61, + "learning_rate": 7.80181766224021e-06, + "loss": 1.4396, + "step": 5850 + }, + { + "epoch": 0.61, + "learning_rate": 7.798247086095484e-06, + "loss": 1.3448, + "step": 5851 + }, + { + "epoch": 0.61, + "learning_rate": 7.794676804929075e-06, + "loss": 1.3591, + "step": 5852 + }, + { + "epoch": 0.61, + "learning_rate": 7.791106819219311e-06, + "loss": 1.3108, + "step": 5853 + }, + { + "epoch": 0.61, + "learning_rate": 7.78753712944448e-06, + "loss": 1.3773, + "step": 5854 + }, + { + "epoch": 0.61, + "learning_rate": 7.783967736082824e-06, + "loss": 1.3313, + "step": 5855 + }, + { + "epoch": 0.61, + "learning_rate": 7.780398639612551e-06, + "loss": 1.3635, + "step": 5856 + }, + { + "epoch": 0.61, + "learning_rate": 7.776829840511833e-06, + "loss": 1.3225, + "step": 5857 + }, + { + "epoch": 0.61, + "learning_rate": 7.773261339258792e-06, + "loss": 1.3142, + "step": 5858 + }, + { + "epoch": 0.61, + "learning_rate": 7.769693136331519e-06, + "loss": 1.3337, + "step": 5859 + }, + { + "epoch": 0.61, + "learning_rate": 7.766125232208057e-06, + "loss": 1.5289, + "step": 5860 + }, + { + "epoch": 0.61, + "learning_rate": 7.762557627366418e-06, + "loss": 1.573, + "step": 5861 + }, + { + "epoch": 0.61, + "learning_rate": 7.758990322284568e-06, + "loss": 1.322, + "step": 5862 + }, + { + "epoch": 0.61, + "learning_rate": 7.755423317440432e-06, + "loss": 1.3281, + "step": 5863 + }, + { + "epoch": 0.61, + "learning_rate": 7.751856613311899e-06, + "loss": 1.3405, + "step": 5864 + }, + { + "epoch": 0.62, + "learning_rate": 7.748290210376817e-06, + "loss": 1.3083, + "step": 5865 + }, + { + "epoch": 0.62, + "learning_rate": 7.744724109112991e-06, + "loss": 1.3587, + "step": 5866 + }, + { + "epoch": 0.62, + "learning_rate": 7.741158309998188e-06, + "loss": 1.3204, + "step": 5867 + }, + { + "epoch": 0.62, + "learning_rate": 7.73759281351013e-06, + "loss": 1.343, + "step": 5868 + }, + { + "epoch": 0.62, + "learning_rate": 7.734027620126507e-06, + "loss": 1.2874, + "step": 5869 + }, + { + "epoch": 0.62, + "learning_rate": 7.73046273032496e-06, + "loss": 1.3306, + "step": 5870 + }, + { + "epoch": 0.62, + "learning_rate": 7.72689814458309e-06, + "loss": 1.3958, + "step": 5871 + }, + { + "epoch": 0.62, + "learning_rate": 7.723333863378465e-06, + "loss": 1.3135, + "step": 5872 + }, + { + "epoch": 0.62, + "learning_rate": 7.719769887188608e-06, + "loss": 1.3241, + "step": 5873 + }, + { + "epoch": 0.62, + "learning_rate": 7.716206216490995e-06, + "loss": 1.3487, + "step": 5874 + }, + { + "epoch": 0.62, + "learning_rate": 7.712642851763067e-06, + "loss": 1.0263, + "step": 5875 + }, + { + "epoch": 0.62, + "learning_rate": 7.709079793482228e-06, + "loss": 1.4238, + "step": 5876 + }, + { + "epoch": 0.62, + "learning_rate": 7.705517042125833e-06, + "loss": 1.3284, + "step": 5877 + }, + { + "epoch": 0.62, + "learning_rate": 7.701954598171199e-06, + "loss": 1.2965, + "step": 5878 + }, + { + "epoch": 0.62, + "learning_rate": 7.698392462095601e-06, + "loss": 1.3578, + "step": 5879 + }, + { + "epoch": 0.62, + "learning_rate": 7.694830634376278e-06, + "loss": 1.3711, + "step": 5880 + }, + { + "epoch": 0.62, + "learning_rate": 7.69126911549042e-06, + "loss": 1.3274, + "step": 5881 + }, + { + "epoch": 0.62, + "learning_rate": 7.687707905915181e-06, + "loss": 1.4208, + "step": 5882 + }, + { + "epoch": 0.62, + "learning_rate": 7.684147006127665e-06, + "loss": 1.3478, + "step": 5883 + }, + { + "epoch": 0.62, + "learning_rate": 7.68058641660495e-06, + "loss": 1.2997, + "step": 5884 + }, + { + "epoch": 0.62, + "learning_rate": 7.67702613782406e-06, + "loss": 1.2981, + "step": 5885 + }, + { + "epoch": 0.62, + "learning_rate": 7.67346617026198e-06, + "loss": 1.3834, + "step": 5886 + }, + { + "epoch": 0.62, + "learning_rate": 7.669906514395654e-06, + "loss": 1.3585, + "step": 5887 + }, + { + "epoch": 0.62, + "learning_rate": 7.666347170701986e-06, + "loss": 1.3282, + "step": 5888 + }, + { + "epoch": 0.62, + "learning_rate": 7.662788139657838e-06, + "loss": 1.3397, + "step": 5889 + }, + { + "epoch": 0.62, + "learning_rate": 7.659229421740024e-06, + "loss": 1.3367, + "step": 5890 + }, + { + "epoch": 0.62, + "learning_rate": 7.655671017425322e-06, + "loss": 1.3497, + "step": 5891 + }, + { + "epoch": 0.62, + "learning_rate": 7.65211292719047e-06, + "loss": 1.3661, + "step": 5892 + }, + { + "epoch": 0.62, + "learning_rate": 7.64855515151216e-06, + "loss": 1.2793, + "step": 5893 + }, + { + "epoch": 0.62, + "learning_rate": 7.644997690867037e-06, + "loss": 1.3288, + "step": 5894 + }, + { + "epoch": 0.62, + "learning_rate": 7.641440545731717e-06, + "loss": 1.3877, + "step": 5895 + }, + { + "epoch": 0.62, + "learning_rate": 7.637883716582764e-06, + "loss": 1.4467, + "step": 5896 + }, + { + "epoch": 0.62, + "learning_rate": 7.634327203896698e-06, + "loss": 1.304, + "step": 5897 + }, + { + "epoch": 0.62, + "learning_rate": 7.630771008150002e-06, + "loss": 1.374, + "step": 5898 + }, + { + "epoch": 0.62, + "learning_rate": 7.627215129819118e-06, + "loss": 1.3893, + "step": 5899 + }, + { + "epoch": 0.62, + "learning_rate": 7.623659569380439e-06, + "loss": 1.325, + "step": 5900 + }, + { + "epoch": 0.62, + "learning_rate": 7.620104327310319e-06, + "loss": 1.2495, + "step": 5901 + }, + { + "epoch": 0.62, + "learning_rate": 7.616549404085068e-06, + "loss": 1.4034, + "step": 5902 + }, + { + "epoch": 0.62, + "learning_rate": 7.61299480018096e-06, + "loss": 1.2758, + "step": 5903 + }, + { + "epoch": 0.62, + "learning_rate": 7.609440516074215e-06, + "loss": 1.4203, + "step": 5904 + }, + { + "epoch": 0.62, + "learning_rate": 7.605886552241017e-06, + "loss": 1.3162, + "step": 5905 + }, + { + "epoch": 0.62, + "learning_rate": 7.602332909157505e-06, + "loss": 1.3368, + "step": 5906 + }, + { + "epoch": 0.62, + "learning_rate": 7.598779587299778e-06, + "loss": 1.314, + "step": 5907 + }, + { + "epoch": 0.62, + "learning_rate": 7.59522658714389e-06, + "loss": 1.3332, + "step": 5908 + }, + { + "epoch": 0.62, + "learning_rate": 7.5916739091658505e-06, + "loss": 1.3513, + "step": 5909 + }, + { + "epoch": 0.62, + "learning_rate": 7.5881215538416255e-06, + "loss": 1.3767, + "step": 5910 + }, + { + "epoch": 0.62, + "learning_rate": 7.5845695216471426e-06, + "loss": 1.3651, + "step": 5911 + }, + { + "epoch": 0.62, + "learning_rate": 7.581017813058283e-06, + "loss": 1.2676, + "step": 5912 + }, + { + "epoch": 0.62, + "learning_rate": 7.57746642855088e-06, + "loss": 1.3509, + "step": 5913 + }, + { + "epoch": 0.62, + "learning_rate": 7.5739153686007305e-06, + "loss": 1.2854, + "step": 5914 + }, + { + "epoch": 0.62, + "learning_rate": 7.570364633683586e-06, + "loss": 1.4041, + "step": 5915 + }, + { + "epoch": 0.62, + "learning_rate": 7.5668142242751545e-06, + "loss": 1.3218, + "step": 5916 + }, + { + "epoch": 0.62, + "learning_rate": 7.563264140851095e-06, + "loss": 1.398, + "step": 5917 + }, + { + "epoch": 0.62, + "learning_rate": 7.559714383887033e-06, + "loss": 1.3495, + "step": 5918 + }, + { + "epoch": 0.62, + "learning_rate": 7.556164953858543e-06, + "loss": 1.365, + "step": 5919 + }, + { + "epoch": 0.62, + "learning_rate": 7.552615851241157e-06, + "loss": 1.4611, + "step": 5920 + }, + { + "epoch": 0.62, + "learning_rate": 7.549067076510361e-06, + "loss": 1.4031, + "step": 5921 + }, + { + "epoch": 0.62, + "learning_rate": 7.545518630141605e-06, + "loss": 1.2745, + "step": 5922 + }, + { + "epoch": 0.62, + "learning_rate": 7.541970512610286e-06, + "loss": 1.3435, + "step": 5923 + }, + { + "epoch": 0.62, + "learning_rate": 7.538422724391761e-06, + "loss": 1.3433, + "step": 5924 + }, + { + "epoch": 0.62, + "learning_rate": 7.534875265961341e-06, + "loss": 1.3605, + "step": 5925 + }, + { + "epoch": 0.62, + "learning_rate": 7.5313281377942985e-06, + "loss": 1.3896, + "step": 5926 + }, + { + "epoch": 0.62, + "learning_rate": 7.527781340365854e-06, + "loss": 1.3922, + "step": 5927 + }, + { + "epoch": 0.62, + "learning_rate": 7.524234874151189e-06, + "loss": 1.3305, + "step": 5928 + }, + { + "epoch": 0.62, + "learning_rate": 7.520688739625436e-06, + "loss": 1.3117, + "step": 5929 + }, + { + "epoch": 0.62, + "learning_rate": 7.51714293726369e-06, + "loss": 1.3581, + "step": 5930 + }, + { + "epoch": 0.62, + "learning_rate": 7.5135974675409955e-06, + "loss": 1.3973, + "step": 5931 + }, + { + "epoch": 0.62, + "learning_rate": 7.510052330932354e-06, + "loss": 1.3499, + "step": 5932 + }, + { + "epoch": 0.62, + "learning_rate": 7.506507527912721e-06, + "loss": 1.3068, + "step": 5933 + }, + { + "epoch": 0.62, + "learning_rate": 7.502963058957014e-06, + "loss": 1.3689, + "step": 5934 + }, + { + "epoch": 0.62, + "learning_rate": 7.499418924540096e-06, + "loss": 1.3356, + "step": 5935 + }, + { + "epoch": 0.62, + "learning_rate": 7.495875125136793e-06, + "loss": 1.2593, + "step": 5936 + }, + { + "epoch": 0.62, + "learning_rate": 7.492331661221881e-06, + "loss": 1.272, + "step": 5937 + }, + { + "epoch": 0.62, + "learning_rate": 7.488788533270093e-06, + "loss": 1.3552, + "step": 5938 + }, + { + "epoch": 0.62, + "learning_rate": 7.485245741756121e-06, + "loss": 1.3425, + "step": 5939 + }, + { + "epoch": 0.62, + "learning_rate": 7.481703287154602e-06, + "loss": 1.3694, + "step": 5940 + }, + { + "epoch": 0.62, + "learning_rate": 7.478161169940139e-06, + "loss": 1.3281, + "step": 5941 + }, + { + "epoch": 0.62, + "learning_rate": 7.4746193905872825e-06, + "loss": 1.3109, + "step": 5942 + }, + { + "epoch": 0.62, + "learning_rate": 7.47107794957054e-06, + "loss": 1.5121, + "step": 5943 + }, + { + "epoch": 0.62, + "learning_rate": 7.467536847364372e-06, + "loss": 1.4472, + "step": 5944 + }, + { + "epoch": 0.62, + "learning_rate": 7.463996084443198e-06, + "loss": 1.4615, + "step": 5945 + }, + { + "epoch": 0.62, + "learning_rate": 7.460455661281389e-06, + "loss": 1.3764, + "step": 5946 + }, + { + "epoch": 0.62, + "learning_rate": 7.45691557835327e-06, + "loss": 1.3091, + "step": 5947 + }, + { + "epoch": 0.62, + "learning_rate": 7.4533758361331185e-06, + "loss": 1.1841, + "step": 5948 + }, + { + "epoch": 0.62, + "learning_rate": 7.449836435095175e-06, + "loss": 1.3345, + "step": 5949 + }, + { + "epoch": 0.62, + "learning_rate": 7.446297375713622e-06, + "loss": 1.3573, + "step": 5950 + }, + { + "epoch": 0.62, + "learning_rate": 7.442758658462608e-06, + "loss": 1.3161, + "step": 5951 + }, + { + "epoch": 0.62, + "learning_rate": 7.4392202838162245e-06, + "loss": 1.3089, + "step": 5952 + }, + { + "epoch": 0.62, + "learning_rate": 7.435682252248528e-06, + "loss": 1.3069, + "step": 5953 + }, + { + "epoch": 0.62, + "learning_rate": 7.4321445642335234e-06, + "loss": 1.2969, + "step": 5954 + }, + { + "epoch": 0.62, + "learning_rate": 7.428607220245165e-06, + "loss": 1.4706, + "step": 5955 + }, + { + "epoch": 0.62, + "learning_rate": 7.42507022075737e-06, + "loss": 1.3028, + "step": 5956 + }, + { + "epoch": 0.62, + "learning_rate": 7.421533566244006e-06, + "loss": 1.2786, + "step": 5957 + }, + { + "epoch": 0.62, + "learning_rate": 7.417997257178893e-06, + "loss": 1.3534, + "step": 5958 + }, + { + "epoch": 0.62, + "learning_rate": 7.414461294035804e-06, + "loss": 1.2829, + "step": 5959 + }, + { + "epoch": 0.62, + "learning_rate": 7.410925677288467e-06, + "loss": 1.3626, + "step": 5960 + }, + { + "epoch": 0.63, + "learning_rate": 7.407390407410566e-06, + "loss": 1.4531, + "step": 5961 + }, + { + "epoch": 0.63, + "learning_rate": 7.4038554848757375e-06, + "loss": 1.3549, + "step": 5962 + }, + { + "epoch": 0.63, + "learning_rate": 7.400320910157563e-06, + "loss": 1.3407, + "step": 5963 + }, + { + "epoch": 0.63, + "learning_rate": 7.396786683729595e-06, + "loss": 1.2736, + "step": 5964 + }, + { + "epoch": 0.63, + "learning_rate": 7.393252806065323e-06, + "loss": 1.3377, + "step": 5965 + }, + { + "epoch": 0.63, + "learning_rate": 7.389719277638196e-06, + "loss": 1.3479, + "step": 5966 + }, + { + "epoch": 0.63, + "learning_rate": 7.3861860989216175e-06, + "loss": 1.3605, + "step": 5967 + }, + { + "epoch": 0.63, + "learning_rate": 7.382653270388942e-06, + "loss": 1.3175, + "step": 5968 + }, + { + "epoch": 0.63, + "learning_rate": 7.379120792513477e-06, + "loss": 1.3072, + "step": 5969 + }, + { + "epoch": 0.63, + "learning_rate": 7.375588665768485e-06, + "loss": 1.3224, + "step": 5970 + }, + { + "epoch": 0.63, + "eval_loss": 1.4110088348388672, + "eval_runtime": 77.5326, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 5970 + }, + { + "epoch": 0.63, + "learning_rate": 7.37205689062718e-06, + "loss": 1.3491, + "step": 5971 + }, + { + "epoch": 0.63, + "learning_rate": 7.368525467562728e-06, + "loss": 1.3289, + "step": 5972 + }, + { + "epoch": 0.63, + "learning_rate": 7.364994397048251e-06, + "loss": 1.3362, + "step": 5973 + }, + { + "epoch": 0.63, + "learning_rate": 7.36146367955682e-06, + "loss": 1.3754, + "step": 5974 + }, + { + "epoch": 0.63, + "learning_rate": 7.3579333155614585e-06, + "loss": 1.3159, + "step": 5975 + }, + { + "epoch": 0.63, + "learning_rate": 7.354403305535149e-06, + "loss": 1.4366, + "step": 5976 + }, + { + "epoch": 0.63, + "learning_rate": 7.350873649950822e-06, + "loss": 1.3243, + "step": 5977 + }, + { + "epoch": 0.63, + "learning_rate": 7.347344349281358e-06, + "loss": 1.2911, + "step": 5978 + }, + { + "epoch": 0.63, + "learning_rate": 7.34381540399959e-06, + "loss": 1.338, + "step": 5979 + }, + { + "epoch": 0.63, + "learning_rate": 7.340286814578312e-06, + "loss": 1.3241, + "step": 5980 + }, + { + "epoch": 0.63, + "learning_rate": 7.336758581490263e-06, + "loss": 1.3427, + "step": 5981 + }, + { + "epoch": 0.63, + "learning_rate": 7.333230705208134e-06, + "loss": 1.3328, + "step": 5982 + }, + { + "epoch": 0.63, + "learning_rate": 7.3297031862045676e-06, + "loss": 1.2857, + "step": 5983 + }, + { + "epoch": 0.63, + "learning_rate": 7.3261760249521655e-06, + "loss": 1.9065, + "step": 5984 + }, + { + "epoch": 0.63, + "learning_rate": 7.322649221923473e-06, + "loss": 1.3797, + "step": 5985 + }, + { + "epoch": 0.63, + "learning_rate": 7.3191227775909925e-06, + "loss": 1.2343, + "step": 5986 + }, + { + "epoch": 0.63, + "learning_rate": 7.315596692427178e-06, + "loss": 1.3479, + "step": 5987 + }, + { + "epoch": 0.63, + "learning_rate": 7.312070966904432e-06, + "loss": 1.3226, + "step": 5988 + }, + { + "epoch": 0.63, + "learning_rate": 7.308545601495114e-06, + "loss": 1.3329, + "step": 5989 + }, + { + "epoch": 0.63, + "learning_rate": 7.305020596671528e-06, + "loss": 1.3285, + "step": 5990 + }, + { + "epoch": 0.63, + "learning_rate": 7.301495952905939e-06, + "loss": 1.3635, + "step": 5991 + }, + { + "epoch": 0.63, + "learning_rate": 7.297971670670556e-06, + "loss": 1.3343, + "step": 5992 + }, + { + "epoch": 0.63, + "learning_rate": 7.294447750437543e-06, + "loss": 1.3943, + "step": 5993 + }, + { + "epoch": 0.63, + "learning_rate": 7.290924192679014e-06, + "loss": 1.4601, + "step": 5994 + }, + { + "epoch": 0.63, + "learning_rate": 7.287400997867036e-06, + "loss": 1.3813, + "step": 5995 + }, + { + "epoch": 0.63, + "learning_rate": 7.2838781664736266e-06, + "loss": 1.3505, + "step": 5996 + }, + { + "epoch": 0.63, + "learning_rate": 7.2803556989707555e-06, + "loss": 1.3062, + "step": 5997 + }, + { + "epoch": 0.63, + "learning_rate": 7.276833595830338e-06, + "loss": 1.4504, + "step": 5998 + }, + { + "epoch": 0.63, + "learning_rate": 7.273311857524252e-06, + "loss": 1.4935, + "step": 5999 + }, + { + "epoch": 0.63, + "learning_rate": 7.269790484524317e-06, + "loss": 1.296, + "step": 6000 + }, + { + "epoch": 0.63, + "learning_rate": 7.266269477302308e-06, + "loss": 1.3469, + "step": 6001 + }, + { + "epoch": 0.63, + "learning_rate": 7.262748836329944e-06, + "loss": 1.3586, + "step": 6002 + }, + { + "epoch": 0.63, + "learning_rate": 7.259228562078908e-06, + "loss": 1.3643, + "step": 6003 + }, + { + "epoch": 0.63, + "learning_rate": 7.255708655020821e-06, + "loss": 1.3096, + "step": 6004 + }, + { + "epoch": 0.63, + "learning_rate": 7.252189115627264e-06, + "loss": 1.3163, + "step": 6005 + }, + { + "epoch": 0.63, + "learning_rate": 7.2486699443697595e-06, + "loss": 1.3526, + "step": 6006 + }, + { + "epoch": 0.63, + "learning_rate": 7.245151141719793e-06, + "loss": 1.401, + "step": 6007 + }, + { + "epoch": 0.63, + "learning_rate": 7.241632708148788e-06, + "loss": 1.2651, + "step": 6008 + }, + { + "epoch": 0.63, + "learning_rate": 7.238114644128124e-06, + "loss": 1.348, + "step": 6009 + }, + { + "epoch": 0.63, + "learning_rate": 7.234596950129137e-06, + "loss": 1.6934, + "step": 6010 + }, + { + "epoch": 0.63, + "learning_rate": 7.231079626623103e-06, + "loss": 1.3382, + "step": 6011 + }, + { + "epoch": 0.63, + "learning_rate": 7.227562674081254e-06, + "loss": 1.2925, + "step": 6012 + }, + { + "epoch": 0.63, + "learning_rate": 7.22404609297477e-06, + "loss": 1.3365, + "step": 6013 + }, + { + "epoch": 0.63, + "learning_rate": 7.220529883774785e-06, + "loss": 1.3169, + "step": 6014 + }, + { + "epoch": 0.63, + "learning_rate": 7.217014046952379e-06, + "loss": 1.319, + "step": 6015 + }, + { + "epoch": 0.63, + "learning_rate": 7.2134985829785846e-06, + "loss": 1.4049, + "step": 6016 + }, + { + "epoch": 0.63, + "learning_rate": 7.209983492324382e-06, + "loss": 1.2947, + "step": 6017 + }, + { + "epoch": 0.63, + "learning_rate": 7.206468775460704e-06, + "loss": 1.2854, + "step": 6018 + }, + { + "epoch": 0.63, + "learning_rate": 7.202954432858436e-06, + "loss": 1.3381, + "step": 6019 + }, + { + "epoch": 0.63, + "learning_rate": 7.199440464988403e-06, + "loss": 1.3912, + "step": 6020 + }, + { + "epoch": 0.63, + "learning_rate": 7.195926872321391e-06, + "loss": 1.384, + "step": 6021 + }, + { + "epoch": 0.63, + "learning_rate": 7.192413655328129e-06, + "loss": 1.2909, + "step": 6022 + }, + { + "epoch": 0.63, + "learning_rate": 7.188900814479299e-06, + "loss": 1.2951, + "step": 6023 + }, + { + "epoch": 0.63, + "learning_rate": 7.185388350245532e-06, + "loss": 1.2655, + "step": 6024 + }, + { + "epoch": 0.63, + "learning_rate": 7.1818762630974035e-06, + "loss": 1.3288, + "step": 6025 + }, + { + "epoch": 0.63, + "learning_rate": 7.17836455350545e-06, + "loss": 1.2873, + "step": 6026 + }, + { + "epoch": 0.63, + "learning_rate": 7.174853221940146e-06, + "loss": 1.3027, + "step": 6027 + }, + { + "epoch": 0.63, + "learning_rate": 7.17134226887192e-06, + "loss": 1.3273, + "step": 6028 + }, + { + "epoch": 0.63, + "learning_rate": 7.167831694771149e-06, + "loss": 1.3096, + "step": 6029 + }, + { + "epoch": 0.63, + "learning_rate": 7.1643215001081625e-06, + "loss": 1.2904, + "step": 6030 + }, + { + "epoch": 0.63, + "learning_rate": 7.160811685353234e-06, + "loss": 1.2977, + "step": 6031 + }, + { + "epoch": 0.63, + "learning_rate": 7.157302250976588e-06, + "loss": 1.3281, + "step": 6032 + }, + { + "epoch": 0.63, + "learning_rate": 7.1537931974483996e-06, + "loss": 1.3831, + "step": 6033 + }, + { + "epoch": 0.63, + "learning_rate": 7.150284525238794e-06, + "loss": 1.3173, + "step": 6034 + }, + { + "epoch": 0.63, + "learning_rate": 7.146776234817841e-06, + "loss": 1.4148, + "step": 6035 + }, + { + "epoch": 0.63, + "learning_rate": 7.143268326655557e-06, + "loss": 1.3381, + "step": 6036 + }, + { + "epoch": 0.63, + "learning_rate": 7.13976080122192e-06, + "loss": 1.3221, + "step": 6037 + }, + { + "epoch": 0.63, + "learning_rate": 7.136253658986843e-06, + "loss": 1.4373, + "step": 6038 + }, + { + "epoch": 0.63, + "learning_rate": 7.132746900420195e-06, + "loss": 1.3758, + "step": 6039 + }, + { + "epoch": 0.63, + "learning_rate": 7.129240525991788e-06, + "loss": 1.3964, + "step": 6040 + }, + { + "epoch": 0.63, + "learning_rate": 7.125734536171391e-06, + "loss": 1.3136, + "step": 6041 + }, + { + "epoch": 0.63, + "learning_rate": 7.122228931428715e-06, + "loss": 1.2195, + "step": 6042 + }, + { + "epoch": 0.63, + "learning_rate": 7.11872371223342e-06, + "loss": 1.3842, + "step": 6043 + }, + { + "epoch": 0.63, + "learning_rate": 7.115218879055113e-06, + "loss": 1.3369, + "step": 6044 + }, + { + "epoch": 0.63, + "learning_rate": 7.111714432363356e-06, + "loss": 1.2704, + "step": 6045 + }, + { + "epoch": 0.63, + "learning_rate": 7.108210372627653e-06, + "loss": 1.307, + "step": 6046 + }, + { + "epoch": 0.63, + "learning_rate": 7.104706700317459e-06, + "loss": 1.3024, + "step": 6047 + }, + { + "epoch": 0.63, + "learning_rate": 7.1012034159021715e-06, + "loss": 1.4157, + "step": 6048 + }, + { + "epoch": 0.63, + "learning_rate": 7.0977005198511475e-06, + "loss": 1.2314, + "step": 6049 + }, + { + "epoch": 0.63, + "learning_rate": 7.09419801263368e-06, + "loss": 1.4304, + "step": 6050 + }, + { + "epoch": 0.63, + "learning_rate": 7.090695894719019e-06, + "loss": 1.3085, + "step": 6051 + }, + { + "epoch": 0.63, + "learning_rate": 7.0871941665763525e-06, + "loss": 1.367, + "step": 6052 + }, + { + "epoch": 0.63, + "learning_rate": 7.083692828674827e-06, + "loss": 1.2913, + "step": 6053 + }, + { + "epoch": 0.63, + "learning_rate": 7.080191881483531e-06, + "loss": 1.3751, + "step": 6054 + }, + { + "epoch": 0.63, + "learning_rate": 7.0766913254714985e-06, + "loss": 1.3178, + "step": 6055 + }, + { + "epoch": 0.64, + "learning_rate": 7.07319116110772e-06, + "loss": 1.3182, + "step": 6056 + }, + { + "epoch": 0.64, + "learning_rate": 7.069691388861122e-06, + "loss": 1.373, + "step": 6057 + }, + { + "epoch": 0.64, + "learning_rate": 7.066192009200588e-06, + "loss": 1.3235, + "step": 6058 + }, + { + "epoch": 0.64, + "learning_rate": 7.0626930225949395e-06, + "loss": 1.3765, + "step": 6059 + }, + { + "epoch": 0.64, + "learning_rate": 7.0591944295129565e-06, + "loss": 1.4408, + "step": 6060 + }, + { + "epoch": 0.64, + "learning_rate": 7.055696230423359e-06, + "loss": 1.3271, + "step": 6061 + }, + { + "epoch": 0.64, + "learning_rate": 7.052198425794814e-06, + "loss": 1.2194, + "step": 6062 + }, + { + "epoch": 0.64, + "learning_rate": 7.048701016095938e-06, + "loss": 1.3707, + "step": 6063 + }, + { + "epoch": 0.64, + "learning_rate": 7.045204001795296e-06, + "loss": 1.3878, + "step": 6064 + }, + { + "epoch": 0.64, + "learning_rate": 7.041707383361396e-06, + "loss": 1.3674, + "step": 6065 + }, + { + "epoch": 0.64, + "learning_rate": 7.038211161262697e-06, + "loss": 1.4525, + "step": 6066 + }, + { + "epoch": 0.64, + "learning_rate": 7.034715335967599e-06, + "loss": 1.3801, + "step": 6067 + }, + { + "epoch": 0.64, + "learning_rate": 7.031219907944458e-06, + "loss": 1.4855, + "step": 6068 + }, + { + "epoch": 0.64, + "learning_rate": 7.027724877661568e-06, + "loss": 1.3659, + "step": 6069 + }, + { + "epoch": 0.64, + "learning_rate": 7.024230245587176e-06, + "loss": 1.3649, + "step": 6070 + }, + { + "epoch": 0.64, + "learning_rate": 7.020736012189467e-06, + "loss": 1.2629, + "step": 6071 + }, + { + "epoch": 0.64, + "learning_rate": 7.017242177936586e-06, + "loss": 1.2474, + "step": 6072 + }, + { + "epoch": 0.64, + "learning_rate": 7.013748743296614e-06, + "loss": 1.45, + "step": 6073 + }, + { + "epoch": 0.64, + "learning_rate": 7.010255708737581e-06, + "loss": 1.3624, + "step": 6074 + }, + { + "epoch": 0.64, + "learning_rate": 7.006763074727461e-06, + "loss": 0.9335, + "step": 6075 + }, + { + "epoch": 0.64, + "learning_rate": 7.0032708417341835e-06, + "loss": 0.6376, + "step": 6076 + }, + { + "epoch": 0.64, + "learning_rate": 6.999779010225613e-06, + "loss": 0.7882, + "step": 6077 + }, + { + "epoch": 0.64, + "learning_rate": 6.996287580669567e-06, + "loss": 1.3001, + "step": 6078 + }, + { + "epoch": 0.64, + "learning_rate": 6.9927965535338085e-06, + "loss": 1.323, + "step": 6079 + }, + { + "epoch": 0.64, + "learning_rate": 6.989305929286043e-06, + "loss": 1.3478, + "step": 6080 + }, + { + "epoch": 0.64, + "learning_rate": 6.985815708393928e-06, + "loss": 1.319, + "step": 6081 + }, + { + "epoch": 0.64, + "learning_rate": 6.9823258913250566e-06, + "loss": 1.3458, + "step": 6082 + }, + { + "epoch": 0.64, + "learning_rate": 6.978836478546985e-06, + "loss": 1.2481, + "step": 6083 + }, + { + "epoch": 0.64, + "learning_rate": 6.975347470527195e-06, + "loss": 1.4051, + "step": 6084 + }, + { + "epoch": 0.64, + "learning_rate": 6.97185886773313e-06, + "loss": 1.3705, + "step": 6085 + }, + { + "epoch": 0.64, + "learning_rate": 6.9683706706321676e-06, + "loss": 1.3415, + "step": 6086 + }, + { + "epoch": 0.64, + "learning_rate": 6.964882879691643e-06, + "loss": 1.3462, + "step": 6087 + }, + { + "epoch": 0.64, + "learning_rate": 6.961395495378829e-06, + "loss": 1.2974, + "step": 6088 + }, + { + "epoch": 0.64, + "learning_rate": 6.957908518160943e-06, + "loss": 1.3353, + "step": 6089 + }, + { + "epoch": 0.64, + "learning_rate": 6.95442194850515e-06, + "loss": 1.3073, + "step": 6090 + }, + { + "epoch": 0.64, + "learning_rate": 6.9509357868785636e-06, + "loss": 1.352, + "step": 6091 + }, + { + "epoch": 0.64, + "learning_rate": 6.9474500337482396e-06, + "loss": 1.2771, + "step": 6092 + }, + { + "epoch": 0.64, + "learning_rate": 6.943964689581177e-06, + "loss": 1.2925, + "step": 6093 + }, + { + "epoch": 0.64, + "learning_rate": 6.940479754844322e-06, + "loss": 1.2967, + "step": 6094 + }, + { + "epoch": 0.64, + "learning_rate": 6.93699523000457e-06, + "loss": 1.5839, + "step": 6095 + }, + { + "epoch": 0.64, + "learning_rate": 6.933511115528757e-06, + "loss": 1.3051, + "step": 6096 + }, + { + "epoch": 0.64, + "learning_rate": 6.930027411883664e-06, + "loss": 1.5344, + "step": 6097 + }, + { + "epoch": 0.64, + "learning_rate": 6.926544119536014e-06, + "loss": 1.3938, + "step": 6098 + }, + { + "epoch": 0.64, + "learning_rate": 6.923061238952484e-06, + "loss": 1.3504, + "step": 6099 + }, + { + "epoch": 0.64, + "learning_rate": 6.919578770599689e-06, + "loss": 1.3618, + "step": 6100 + }, + { + "epoch": 0.64, + "learning_rate": 6.916096714944187e-06, + "loss": 1.3811, + "step": 6101 + }, + { + "epoch": 0.64, + "learning_rate": 6.912615072452491e-06, + "loss": 1.2673, + "step": 6102 + }, + { + "epoch": 0.64, + "learning_rate": 6.909133843591046e-06, + "loss": 1.3661, + "step": 6103 + }, + { + "epoch": 0.64, + "learning_rate": 6.905653028826249e-06, + "loss": 1.3811, + "step": 6104 + }, + { + "epoch": 0.64, + "learning_rate": 6.902172628624437e-06, + "loss": 1.3399, + "step": 6105 + }, + { + "epoch": 0.64, + "learning_rate": 6.8986926434519e-06, + "loss": 1.281, + "step": 6106 + }, + { + "epoch": 0.64, + "learning_rate": 6.895213073774862e-06, + "loss": 1.3053, + "step": 6107 + }, + { + "epoch": 0.64, + "learning_rate": 6.891733920059498e-06, + "loss": 1.4573, + "step": 6108 + }, + { + "epoch": 0.64, + "learning_rate": 6.8882551827719215e-06, + "loss": 1.355, + "step": 6109 + }, + { + "epoch": 0.64, + "learning_rate": 6.8847768623782e-06, + "loss": 1.3304, + "step": 6110 + }, + { + "epoch": 0.64, + "learning_rate": 6.881298959344335e-06, + "loss": 1.4039, + "step": 6111 + }, + { + "epoch": 0.64, + "learning_rate": 6.877821474136277e-06, + "loss": 1.381, + "step": 6112 + }, + { + "epoch": 0.64, + "learning_rate": 6.874344407219917e-06, + "loss": 1.3503, + "step": 6113 + }, + { + "epoch": 0.64, + "learning_rate": 6.870867759061099e-06, + "loss": 1.2679, + "step": 6114 + }, + { + "epoch": 0.64, + "learning_rate": 6.8673915301256e-06, + "loss": 1.3286, + "step": 6115 + }, + { + "epoch": 0.64, + "learning_rate": 6.863915720879146e-06, + "loss": 1.3528, + "step": 6116 + }, + { + "epoch": 0.64, + "learning_rate": 6.8604403317874055e-06, + "loss": 1.3502, + "step": 6117 + }, + { + "epoch": 0.64, + "learning_rate": 6.856965363315993e-06, + "loss": 1.3507, + "step": 6118 + }, + { + "epoch": 0.64, + "learning_rate": 6.853490815930464e-06, + "loss": 1.2153, + "step": 6119 + }, + { + "epoch": 0.64, + "learning_rate": 6.850016690096319e-06, + "loss": 1.2435, + "step": 6120 + }, + { + "epoch": 0.64, + "learning_rate": 6.846542986279e-06, + "loss": 1.3418, + "step": 6121 + }, + { + "epoch": 0.64, + "learning_rate": 6.843069704943896e-06, + "loss": 1.371, + "step": 6122 + }, + { + "epoch": 0.64, + "learning_rate": 6.8395968465563375e-06, + "loss": 1.1737, + "step": 6123 + }, + { + "epoch": 0.64, + "learning_rate": 6.836124411581598e-06, + "loss": 1.3402, + "step": 6124 + }, + { + "epoch": 0.64, + "learning_rate": 6.8326524004848924e-06, + "loss": 1.3482, + "step": 6125 + }, + { + "epoch": 0.64, + "learning_rate": 6.8291808137313845e-06, + "loss": 1.4585, + "step": 6126 + }, + { + "epoch": 0.64, + "learning_rate": 6.825709651786176e-06, + "loss": 1.2848, + "step": 6127 + }, + { + "epoch": 0.64, + "learning_rate": 6.822238915114312e-06, + "loss": 1.2932, + "step": 6128 + }, + { + "epoch": 0.64, + "learning_rate": 6.818768604180785e-06, + "loss": 1.3124, + "step": 6129 + }, + { + "epoch": 0.64, + "learning_rate": 6.815298719450525e-06, + "loss": 1.2843, + "step": 6130 + }, + { + "epoch": 0.64, + "learning_rate": 6.811829261388409e-06, + "loss": 1.3024, + "step": 6131 + }, + { + "epoch": 0.64, + "learning_rate": 6.808360230459252e-06, + "loss": 1.3612, + "step": 6132 + }, + { + "epoch": 0.64, + "learning_rate": 6.804891627127821e-06, + "loss": 1.3005, + "step": 6133 + }, + { + "epoch": 0.64, + "learning_rate": 6.8014234518588154e-06, + "loss": 1.2614, + "step": 6134 + }, + { + "epoch": 0.64, + "learning_rate": 6.7979557051168835e-06, + "loss": 1.3717, + "step": 6135 + }, + { + "epoch": 0.64, + "learning_rate": 6.794488387366609e-06, + "loss": 1.3873, + "step": 6136 + }, + { + "epoch": 0.64, + "learning_rate": 6.791021499072532e-06, + "loss": 1.2955, + "step": 6137 + }, + { + "epoch": 0.64, + "learning_rate": 6.787555040699121e-06, + "loss": 1.4217, + "step": 6138 + }, + { + "epoch": 0.64, + "learning_rate": 6.784089012710793e-06, + "loss": 1.3805, + "step": 6139 + }, + { + "epoch": 0.64, + "learning_rate": 6.7806234155719055e-06, + "loss": 1.3982, + "step": 6140 + }, + { + "epoch": 0.64, + "learning_rate": 6.7771582497467635e-06, + "loss": 1.4, + "step": 6141 + }, + { + "epoch": 0.64, + "learning_rate": 6.773693515699607e-06, + "loss": 1.439, + "step": 6142 + }, + { + "epoch": 0.64, + "learning_rate": 6.7702292138946235e-06, + "loss": 1.3672, + "step": 6143 + }, + { + "epoch": 0.64, + "learning_rate": 6.7667653447959355e-06, + "loss": 1.2901, + "step": 6144 + }, + { + "epoch": 0.64, + "learning_rate": 6.763301908867619e-06, + "loss": 1.2873, + "step": 6145 + }, + { + "epoch": 0.64, + "learning_rate": 6.759838906573684e-06, + "loss": 1.3582, + "step": 6146 + }, + { + "epoch": 0.64, + "learning_rate": 6.756376338378077e-06, + "loss": 1.3562, + "step": 6147 + }, + { + "epoch": 0.64, + "learning_rate": 6.7529142047447025e-06, + "loss": 1.3091, + "step": 6148 + }, + { + "epoch": 0.64, + "learning_rate": 6.749452506137393e-06, + "loss": 1.4269, + "step": 6149 + }, + { + "epoch": 0.64, + "learning_rate": 6.745991243019927e-06, + "loss": 1.4184, + "step": 6150 + }, + { + "epoch": 0.65, + "learning_rate": 6.7425304158560235e-06, + "loss": 1.4201, + "step": 6151 + }, + { + "epoch": 0.65, + "learning_rate": 6.739070025109349e-06, + "loss": 1.3222, + "step": 6152 + }, + { + "epoch": 0.65, + "learning_rate": 6.7356100712435035e-06, + "loss": 1.3262, + "step": 6153 + }, + { + "epoch": 0.65, + "learning_rate": 6.732150554722034e-06, + "loss": 1.4408, + "step": 6154 + }, + { + "epoch": 0.65, + "learning_rate": 6.728691476008422e-06, + "loss": 1.3441, + "step": 6155 + }, + { + "epoch": 0.65, + "learning_rate": 6.725232835566102e-06, + "loss": 1.3316, + "step": 6156 + }, + { + "epoch": 0.65, + "learning_rate": 6.721774633858438e-06, + "loss": 1.3326, + "step": 6157 + }, + { + "epoch": 0.65, + "learning_rate": 6.7183168713487425e-06, + "loss": 1.3105, + "step": 6158 + }, + { + "epoch": 0.65, + "learning_rate": 6.714859548500265e-06, + "loss": 1.3144, + "step": 6159 + }, + { + "epoch": 0.65, + "learning_rate": 6.7114026657762e-06, + "loss": 1.3472, + "step": 6160 + }, + { + "epoch": 0.65, + "learning_rate": 6.707946223639681e-06, + "loss": 1.3811, + "step": 6161 + }, + { + "epoch": 0.65, + "learning_rate": 6.704490222553781e-06, + "loss": 1.2783, + "step": 6162 + }, + { + "epoch": 0.65, + "learning_rate": 6.701034662981513e-06, + "loss": 1.273, + "step": 6163 + }, + { + "epoch": 0.65, + "learning_rate": 6.697579545385839e-06, + "loss": 1.3522, + "step": 6164 + }, + { + "epoch": 0.65, + "learning_rate": 6.6941248702296524e-06, + "loss": 1.3861, + "step": 6165 + }, + { + "epoch": 0.65, + "learning_rate": 6.6906706379757915e-06, + "loss": 1.3098, + "step": 6166 + }, + { + "epoch": 0.65, + "learning_rate": 6.687216849087032e-06, + "loss": 1.3734, + "step": 6167 + }, + { + "epoch": 0.65, + "learning_rate": 6.6837635040261e-06, + "loss": 1.2289, + "step": 6168 + }, + { + "epoch": 0.65, + "learning_rate": 6.680310603255648e-06, + "loss": 1.3238, + "step": 6169 + }, + { + "epoch": 0.65, + "eval_loss": 1.40826416015625, + "eval_runtime": 77.483, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 6169 + }, + { + "epoch": 0.65, + "learning_rate": 6.676858147238277e-06, + "loss": 1.4317, + "step": 6170 + }, + { + "epoch": 0.65, + "learning_rate": 6.673406136436531e-06, + "loss": 1.3363, + "step": 6171 + }, + { + "epoch": 0.65, + "learning_rate": 6.669954571312889e-06, + "loss": 1.3377, + "step": 6172 + }, + { + "epoch": 0.65, + "learning_rate": 6.666503452329771e-06, + "loss": 1.3382, + "step": 6173 + }, + { + "epoch": 0.65, + "learning_rate": 6.663052779949538e-06, + "loss": 1.3028, + "step": 6174 + }, + { + "epoch": 0.65, + "learning_rate": 6.659602554634494e-06, + "loss": 1.3098, + "step": 6175 + }, + { + "epoch": 0.65, + "learning_rate": 6.656152776846879e-06, + "loss": 1.328, + "step": 6176 + }, + { + "epoch": 0.65, + "learning_rate": 6.652703447048874e-06, + "loss": 1.3014, + "step": 6177 + }, + { + "epoch": 0.65, + "learning_rate": 6.6492545657026e-06, + "loss": 1.2522, + "step": 6178 + }, + { + "epoch": 0.65, + "learning_rate": 6.645806133270121e-06, + "loss": 1.6113, + "step": 6179 + }, + { + "epoch": 0.65, + "learning_rate": 6.642358150213437e-06, + "loss": 1.3431, + "step": 6180 + }, + { + "epoch": 0.65, + "learning_rate": 6.638910616994489e-06, + "loss": 1.2725, + "step": 6181 + }, + { + "epoch": 0.65, + "learning_rate": 6.635463534075156e-06, + "loss": 1.3022, + "step": 6182 + }, + { + "epoch": 0.65, + "learning_rate": 6.632016901917262e-06, + "loss": 1.3496, + "step": 6183 + }, + { + "epoch": 0.65, + "learning_rate": 6.628570720982567e-06, + "loss": 1.2871, + "step": 6184 + }, + { + "epoch": 0.65, + "learning_rate": 6.625124991732767e-06, + "loss": 1.4449, + "step": 6185 + }, + { + "epoch": 0.65, + "learning_rate": 6.621679714629504e-06, + "loss": 1.4395, + "step": 6186 + }, + { + "epoch": 0.65, + "learning_rate": 6.618234890134356e-06, + "loss": 1.4088, + "step": 6187 + }, + { + "epoch": 0.65, + "learning_rate": 6.614790518708843e-06, + "loss": 1.371, + "step": 6188 + }, + { + "epoch": 0.65, + "learning_rate": 6.611346600814419e-06, + "loss": 1.28, + "step": 6189 + }, + { + "epoch": 0.65, + "learning_rate": 6.607903136912482e-06, + "loss": 1.3502, + "step": 6190 + }, + { + "epoch": 0.65, + "learning_rate": 6.604460127464367e-06, + "loss": 1.3398, + "step": 6191 + }, + { + "epoch": 0.65, + "learning_rate": 6.60101757293135e-06, + "loss": 1.4762, + "step": 6192 + }, + { + "epoch": 0.65, + "learning_rate": 6.5975754737746426e-06, + "loss": 1.2981, + "step": 6193 + }, + { + "epoch": 0.65, + "learning_rate": 6.594133830455401e-06, + "loss": 1.3728, + "step": 6194 + }, + { + "epoch": 0.65, + "learning_rate": 6.590692643434715e-06, + "loss": 1.3551, + "step": 6195 + }, + { + "epoch": 0.65, + "learning_rate": 6.5872519131736155e-06, + "loss": 1.3031, + "step": 6196 + }, + { + "epoch": 0.65, + "learning_rate": 6.583811640133071e-06, + "loss": 1.3231, + "step": 6197 + }, + { + "epoch": 0.65, + "learning_rate": 6.5803718247739924e-06, + "loss": 1.2752, + "step": 6198 + }, + { + "epoch": 0.65, + "learning_rate": 6.576932467557223e-06, + "loss": 1.3482, + "step": 6199 + }, + { + "epoch": 0.65, + "learning_rate": 6.573493568943552e-06, + "loss": 1.2612, + "step": 6200 + }, + { + "epoch": 0.65, + "learning_rate": 6.570055129393698e-06, + "loss": 1.6302, + "step": 6201 + }, + { + "epoch": 0.65, + "learning_rate": 6.566617149368331e-06, + "loss": 1.303, + "step": 6202 + }, + { + "epoch": 0.65, + "learning_rate": 6.563179629328047e-06, + "loss": 1.3405, + "step": 6203 + }, + { + "epoch": 0.65, + "learning_rate": 6.559742569733385e-06, + "loss": 1.2816, + "step": 6204 + }, + { + "epoch": 0.65, + "learning_rate": 6.556305971044824e-06, + "loss": 1.3834, + "step": 6205 + }, + { + "epoch": 0.65, + "learning_rate": 6.552869833722781e-06, + "loss": 1.3414, + "step": 6206 + }, + { + "epoch": 0.65, + "learning_rate": 6.5494341582276096e-06, + "loss": 1.3278, + "step": 6207 + }, + { + "epoch": 0.65, + "learning_rate": 6.5459989450196024e-06, + "loss": 1.3577, + "step": 6208 + }, + { + "epoch": 0.65, + "learning_rate": 6.542564194558986e-06, + "loss": 1.3104, + "step": 6209 + }, + { + "epoch": 0.65, + "learning_rate": 6.539129907305933e-06, + "loss": 1.3068, + "step": 6210 + }, + { + "epoch": 0.65, + "learning_rate": 6.53569608372055e-06, + "loss": 1.3769, + "step": 6211 + }, + { + "epoch": 0.65, + "learning_rate": 6.5322627242628775e-06, + "loss": 1.2855, + "step": 6212 + }, + { + "epoch": 0.65, + "learning_rate": 6.528829829392898e-06, + "loss": 1.4129, + "step": 6213 + }, + { + "epoch": 0.65, + "learning_rate": 6.525397399570534e-06, + "loss": 1.3631, + "step": 6214 + }, + { + "epoch": 0.65, + "learning_rate": 6.5219654352556435e-06, + "loss": 1.295, + "step": 6215 + }, + { + "epoch": 0.65, + "learning_rate": 6.518533936908016e-06, + "loss": 1.439, + "step": 6216 + }, + { + "epoch": 0.65, + "learning_rate": 6.515102904987389e-06, + "loss": 1.3148, + "step": 6217 + }, + { + "epoch": 0.65, + "learning_rate": 6.511672339953432e-06, + "loss": 1.3898, + "step": 6218 + }, + { + "epoch": 0.65, + "learning_rate": 6.508242242265752e-06, + "loss": 1.3222, + "step": 6219 + }, + { + "epoch": 0.65, + "learning_rate": 6.504812612383891e-06, + "loss": 1.324, + "step": 6220 + }, + { + "epoch": 0.65, + "learning_rate": 6.501383450767336e-06, + "loss": 1.951, + "step": 6221 + }, + { + "epoch": 0.65, + "learning_rate": 6.4979547578755055e-06, + "loss": 1.2878, + "step": 6222 + }, + { + "epoch": 0.65, + "learning_rate": 6.494526534167754e-06, + "loss": 1.3553, + "step": 6223 + }, + { + "epoch": 0.65, + "learning_rate": 6.491098780103375e-06, + "loss": 1.3898, + "step": 6224 + }, + { + "epoch": 0.65, + "learning_rate": 6.487671496141606e-06, + "loss": 1.4333, + "step": 6225 + }, + { + "epoch": 0.65, + "learning_rate": 6.484244682741606e-06, + "loss": 1.4461, + "step": 6226 + }, + { + "epoch": 0.65, + "learning_rate": 6.480818340362487e-06, + "loss": 1.3461, + "step": 6227 + }, + { + "epoch": 0.65, + "learning_rate": 6.4773924694632835e-06, + "loss": 1.3442, + "step": 6228 + }, + { + "epoch": 0.65, + "learning_rate": 6.473967070502982e-06, + "loss": 1.2692, + "step": 6229 + }, + { + "epoch": 0.65, + "learning_rate": 6.470542143940495e-06, + "loss": 1.446, + "step": 6230 + }, + { + "epoch": 0.65, + "learning_rate": 6.467117690234675e-06, + "loss": 1.3597, + "step": 6231 + }, + { + "epoch": 0.65, + "learning_rate": 6.463693709844305e-06, + "loss": 1.3226, + "step": 6232 + }, + { + "epoch": 0.65, + "learning_rate": 6.46027020322812e-06, + "loss": 1.2702, + "step": 6233 + }, + { + "epoch": 0.65, + "learning_rate": 6.456847170844775e-06, + "loss": 1.2554, + "step": 6234 + }, + { + "epoch": 0.65, + "learning_rate": 6.453424613152872e-06, + "loss": 1.2896, + "step": 6235 + }, + { + "epoch": 0.65, + "learning_rate": 6.450002530610943e-06, + "loss": 1.3148, + "step": 6236 + }, + { + "epoch": 0.65, + "learning_rate": 6.4465809236774635e-06, + "loss": 1.3589, + "step": 6237 + }, + { + "epoch": 0.65, + "learning_rate": 6.443159792810838e-06, + "loss": 1.2938, + "step": 6238 + }, + { + "epoch": 0.65, + "learning_rate": 6.439739138469406e-06, + "loss": 1.366, + "step": 6239 + }, + { + "epoch": 0.65, + "learning_rate": 6.436318961111455e-06, + "loss": 1.4772, + "step": 6240 + }, + { + "epoch": 0.65, + "learning_rate": 6.4328992611951975e-06, + "loss": 1.3131, + "step": 6241 + }, + { + "epoch": 0.65, + "learning_rate": 6.429480039178786e-06, + "loss": 1.2382, + "step": 6242 + }, + { + "epoch": 0.65, + "learning_rate": 6.426061295520304e-06, + "loss": 1.3394, + "step": 6243 + }, + { + "epoch": 0.65, + "learning_rate": 6.422643030677782e-06, + "loss": 1.321, + "step": 6244 + }, + { + "epoch": 0.65, + "learning_rate": 6.419225245109175e-06, + "loss": 1.3478, + "step": 6245 + }, + { + "epoch": 0.65, + "learning_rate": 6.415807939272383e-06, + "loss": 1.3249, + "step": 6246 + }, + { + "epoch": 0.66, + "learning_rate": 6.412391113625231e-06, + "loss": 1.3602, + "step": 6247 + }, + { + "epoch": 0.66, + "learning_rate": 6.408974768625491e-06, + "loss": 1.2799, + "step": 6248 + }, + { + "epoch": 0.66, + "learning_rate": 6.405558904730863e-06, + "loss": 1.3911, + "step": 6249 + }, + { + "epoch": 0.66, + "learning_rate": 6.402143522398987e-06, + "loss": 1.3185, + "step": 6250 + }, + { + "epoch": 0.66, + "learning_rate": 6.398728622087431e-06, + "loss": 1.3198, + "step": 6251 + }, + { + "epoch": 0.66, + "learning_rate": 6.395314204253711e-06, + "loss": 1.361, + "step": 6252 + }, + { + "epoch": 0.66, + "learning_rate": 6.391900269355269e-06, + "loss": 1.3285, + "step": 6253 + }, + { + "epoch": 0.66, + "learning_rate": 6.388486817849484e-06, + "loss": 1.3097, + "step": 6254 + }, + { + "epoch": 0.66, + "learning_rate": 6.385073850193667e-06, + "loss": 1.3057, + "step": 6255 + }, + { + "epoch": 0.66, + "learning_rate": 6.381661366845075e-06, + "loss": 1.4733, + "step": 6256 + }, + { + "epoch": 0.66, + "learning_rate": 6.378249368260889e-06, + "loss": 1.3571, + "step": 6257 + }, + { + "epoch": 0.66, + "learning_rate": 6.374837854898228e-06, + "loss": 1.3278, + "step": 6258 + }, + { + "epoch": 0.66, + "learning_rate": 6.37142682721415e-06, + "loss": 1.3035, + "step": 6259 + }, + { + "epoch": 0.66, + "learning_rate": 6.368016285665645e-06, + "loss": 1.397, + "step": 6260 + }, + { + "epoch": 0.66, + "learning_rate": 6.3646062307096365e-06, + "loss": 1.353, + "step": 6261 + }, + { + "epoch": 0.66, + "learning_rate": 6.361196662802982e-06, + "loss": 1.3534, + "step": 6262 + }, + { + "epoch": 0.66, + "learning_rate": 6.357787582402482e-06, + "loss": 1.3132, + "step": 6263 + }, + { + "epoch": 0.66, + "learning_rate": 6.3543789899648624e-06, + "loss": 1.3551, + "step": 6264 + }, + { + "epoch": 0.66, + "learning_rate": 6.3509708859467855e-06, + "loss": 1.4205, + "step": 6265 + }, + { + "epoch": 0.66, + "learning_rate": 6.347563270804851e-06, + "loss": 1.341, + "step": 6266 + }, + { + "epoch": 0.66, + "learning_rate": 6.344156144995593e-06, + "loss": 1.5188, + "step": 6267 + }, + { + "epoch": 0.66, + "learning_rate": 6.340749508975477e-06, + "loss": 1.4404, + "step": 6268 + }, + { + "epoch": 0.66, + "learning_rate": 6.337343363200905e-06, + "loss": 1.3026, + "step": 6269 + }, + { + "epoch": 0.66, + "learning_rate": 6.3339377081282124e-06, + "loss": 1.3315, + "step": 6270 + }, + { + "epoch": 0.66, + "learning_rate": 6.3305325442136735e-06, + "loss": 1.2503, + "step": 6271 + }, + { + "epoch": 0.66, + "learning_rate": 6.3271278719134885e-06, + "loss": 1.1776, + "step": 6272 + }, + { + "epoch": 0.66, + "learning_rate": 6.323723691683798e-06, + "loss": 1.3033, + "step": 6273 + }, + { + "epoch": 0.66, + "learning_rate": 6.320320003980671e-06, + "loss": 1.3838, + "step": 6274 + }, + { + "epoch": 0.66, + "learning_rate": 6.3169168092601195e-06, + "loss": 1.3691, + "step": 6275 + }, + { + "epoch": 0.66, + "learning_rate": 6.313514107978083e-06, + "loss": 1.3665, + "step": 6276 + }, + { + "epoch": 0.66, + "learning_rate": 6.310111900590432e-06, + "loss": 1.358, + "step": 6277 + }, + { + "epoch": 0.66, + "learning_rate": 6.306710187552978e-06, + "loss": 1.1708, + "step": 6278 + }, + { + "epoch": 0.66, + "learning_rate": 6.303308969321464e-06, + "loss": 1.331, + "step": 6279 + }, + { + "epoch": 0.66, + "learning_rate": 6.299908246351566e-06, + "loss": 1.3914, + "step": 6280 + }, + { + "epoch": 0.66, + "learning_rate": 6.2965080190988896e-06, + "loss": 1.3183, + "step": 6281 + }, + { + "epoch": 0.66, + "learning_rate": 6.293108288018981e-06, + "loss": 1.2969, + "step": 6282 + }, + { + "epoch": 0.66, + "learning_rate": 6.289709053567318e-06, + "loss": 1.2892, + "step": 6283 + }, + { + "epoch": 0.66, + "learning_rate": 6.2863103161993085e-06, + "loss": 1.3517, + "step": 6284 + }, + { + "epoch": 0.66, + "learning_rate": 6.282912076370295e-06, + "loss": 1.3329, + "step": 6285 + }, + { + "epoch": 0.66, + "learning_rate": 6.279514334535557e-06, + "loss": 1.3396, + "step": 6286 + }, + { + "epoch": 0.66, + "learning_rate": 6.276117091150304e-06, + "loss": 1.3878, + "step": 6287 + }, + { + "epoch": 0.66, + "learning_rate": 6.272720346669677e-06, + "loss": 1.2608, + "step": 6288 + }, + { + "epoch": 0.66, + "learning_rate": 6.269324101548754e-06, + "loss": 1.3605, + "step": 6289 + }, + { + "epoch": 0.66, + "learning_rate": 6.265928356242546e-06, + "loss": 1.2682, + "step": 6290 + }, + { + "epoch": 0.66, + "learning_rate": 6.262533111205995e-06, + "loss": 1.3426, + "step": 6291 + }, + { + "epoch": 0.66, + "learning_rate": 6.259138366893975e-06, + "loss": 1.2987, + "step": 6292 + }, + { + "epoch": 0.66, + "learning_rate": 6.255744123761295e-06, + "loss": 1.3521, + "step": 6293 + }, + { + "epoch": 0.66, + "learning_rate": 6.252350382262697e-06, + "loss": 1.2816, + "step": 6294 + }, + { + "epoch": 0.66, + "learning_rate": 6.248957142852856e-06, + "loss": 1.3884, + "step": 6295 + }, + { + "epoch": 0.66, + "learning_rate": 6.2455644059863795e-06, + "loss": 1.3545, + "step": 6296 + }, + { + "epoch": 0.66, + "learning_rate": 6.2421721721178015e-06, + "loss": 1.3636, + "step": 6297 + }, + { + "epoch": 0.66, + "learning_rate": 6.238780441701601e-06, + "loss": 1.3584, + "step": 6298 + }, + { + "epoch": 0.66, + "learning_rate": 6.235389215192179e-06, + "loss": 1.3459, + "step": 6299 + }, + { + "epoch": 0.66, + "learning_rate": 6.231998493043875e-06, + "loss": 1.4654, + "step": 6300 + }, + { + "epoch": 0.66, + "learning_rate": 6.228608275710954e-06, + "loss": 1.3628, + "step": 6301 + }, + { + "epoch": 0.66, + "learning_rate": 6.225218563647623e-06, + "loss": 1.3278, + "step": 6302 + }, + { + "epoch": 0.66, + "learning_rate": 6.221829357308016e-06, + "loss": 1.395, + "step": 6303 + }, + { + "epoch": 0.66, + "learning_rate": 6.218440657146196e-06, + "loss": 1.3481, + "step": 6304 + }, + { + "epoch": 0.66, + "learning_rate": 6.215052463616165e-06, + "loss": 1.309, + "step": 6305 + }, + { + "epoch": 0.66, + "learning_rate": 6.211664777171853e-06, + "loss": 1.275, + "step": 6306 + }, + { + "epoch": 0.66, + "learning_rate": 6.208277598267123e-06, + "loss": 1.4885, + "step": 6307 + }, + { + "epoch": 0.66, + "learning_rate": 6.2048909273557686e-06, + "loss": 1.3334, + "step": 6308 + }, + { + "epoch": 0.66, + "learning_rate": 6.201504764891518e-06, + "loss": 1.3399, + "step": 6309 + }, + { + "epoch": 0.66, + "learning_rate": 6.198119111328032e-06, + "loss": 1.3163, + "step": 6310 + }, + { + "epoch": 0.66, + "learning_rate": 6.1947339671188966e-06, + "loss": 1.2746, + "step": 6311 + }, + { + "epoch": 0.66, + "learning_rate": 6.191349332717635e-06, + "loss": 1.2984, + "step": 6312 + }, + { + "epoch": 0.66, + "learning_rate": 6.187965208577705e-06, + "loss": 1.2295, + "step": 6313 + }, + { + "epoch": 0.66, + "learning_rate": 6.18458159515249e-06, + "loss": 1.3424, + "step": 6314 + }, + { + "epoch": 0.66, + "learning_rate": 6.181198492895308e-06, + "loss": 1.3108, + "step": 6315 + }, + { + "epoch": 0.66, + "learning_rate": 6.1778159022594045e-06, + "loss": 1.4895, + "step": 6316 + }, + { + "epoch": 0.66, + "learning_rate": 6.174433823697964e-06, + "loss": 1.3247, + "step": 6317 + }, + { + "epoch": 0.66, + "learning_rate": 6.171052257664097e-06, + "loss": 1.3659, + "step": 6318 + }, + { + "epoch": 0.66, + "learning_rate": 6.167671204610844e-06, + "loss": 1.3889, + "step": 6319 + }, + { + "epoch": 0.66, + "learning_rate": 6.1642906649911815e-06, + "loss": 1.3946, + "step": 6320 + }, + { + "epoch": 0.66, + "learning_rate": 6.1609106392580155e-06, + "loss": 1.3685, + "step": 6321 + }, + { + "epoch": 0.66, + "learning_rate": 6.157531127864181e-06, + "loss": 1.2584, + "step": 6322 + }, + { + "epoch": 0.66, + "learning_rate": 6.154152131262448e-06, + "loss": 1.3263, + "step": 6323 + }, + { + "epoch": 0.66, + "learning_rate": 6.15077364990551e-06, + "loss": 1.3336, + "step": 6324 + }, + { + "epoch": 0.66, + "learning_rate": 6.147395684246003e-06, + "loss": 1.2513, + "step": 6325 + }, + { + "epoch": 0.66, + "learning_rate": 6.144018234736484e-06, + "loss": 1.3715, + "step": 6326 + }, + { + "epoch": 0.66, + "learning_rate": 6.140641301829444e-06, + "loss": 1.3464, + "step": 6327 + }, + { + "epoch": 0.66, + "learning_rate": 6.1372648859773075e-06, + "loss": 1.4374, + "step": 6328 + }, + { + "epoch": 0.66, + "learning_rate": 6.1338889876324285e-06, + "loss": 1.3903, + "step": 6329 + }, + { + "epoch": 0.66, + "learning_rate": 6.130513607247087e-06, + "loss": 1.3715, + "step": 6330 + }, + { + "epoch": 0.66, + "learning_rate": 6.127138745273497e-06, + "loss": 1.3196, + "step": 6331 + }, + { + "epoch": 0.66, + "learning_rate": 6.123764402163808e-06, + "loss": 1.3013, + "step": 6332 + }, + { + "epoch": 0.66, + "learning_rate": 6.120390578370093e-06, + "loss": 1.2751, + "step": 6333 + }, + { + "epoch": 0.66, + "learning_rate": 6.117017274344356e-06, + "loss": 1.2258, + "step": 6334 + }, + { + "epoch": 0.66, + "learning_rate": 6.113644490538533e-06, + "loss": 1.2982, + "step": 6335 + }, + { + "epoch": 0.66, + "learning_rate": 6.110272227404492e-06, + "loss": 1.3124, + "step": 6336 + }, + { + "epoch": 0.66, + "learning_rate": 6.10690048539403e-06, + "loss": 1.2451, + "step": 6337 + }, + { + "epoch": 0.66, + "learning_rate": 6.103529264958874e-06, + "loss": 1.3896, + "step": 6338 + }, + { + "epoch": 0.66, + "learning_rate": 6.100158566550677e-06, + "loss": 1.46, + "step": 6339 + }, + { + "epoch": 0.66, + "learning_rate": 6.096788390621031e-06, + "loss": 1.2965, + "step": 6340 + }, + { + "epoch": 0.66, + "learning_rate": 6.093418737621452e-06, + "loss": 1.2969, + "step": 6341 + }, + { + "epoch": 0.67, + "learning_rate": 6.0900496080033836e-06, + "loss": 1.3988, + "step": 6342 + }, + { + "epoch": 0.67, + "learning_rate": 6.086681002218204e-06, + "loss": 1.351, + "step": 6343 + }, + { + "epoch": 0.67, + "learning_rate": 6.083312920717224e-06, + "loss": 1.3447, + "step": 6344 + }, + { + "epoch": 0.67, + "learning_rate": 6.079945363951674e-06, + "loss": 1.3361, + "step": 6345 + }, + { + "epoch": 0.67, + "learning_rate": 6.076578332372724e-06, + "loss": 1.3688, + "step": 6346 + }, + { + "epoch": 0.67, + "learning_rate": 6.073211826431467e-06, + "loss": 1.2831, + "step": 6347 + }, + { + "epoch": 0.67, + "learning_rate": 6.069845846578931e-06, + "loss": 1.369, + "step": 6348 + }, + { + "epoch": 0.67, + "learning_rate": 6.06648039326607e-06, + "loss": 1.3247, + "step": 6349 + }, + { + "epoch": 0.67, + "learning_rate": 6.063115466943765e-06, + "loss": 1.288, + "step": 6350 + }, + { + "epoch": 0.67, + "learning_rate": 6.0597510680628345e-06, + "loss": 1.0733, + "step": 6351 + }, + { + "epoch": 0.67, + "learning_rate": 6.056387197074021e-06, + "loss": 1.3386, + "step": 6352 + }, + { + "epoch": 0.67, + "learning_rate": 6.053023854427993e-06, + "loss": 1.3682, + "step": 6353 + }, + { + "epoch": 0.67, + "learning_rate": 6.049661040575353e-06, + "loss": 1.5669, + "step": 6354 + }, + { + "epoch": 0.67, + "learning_rate": 6.0462987559666355e-06, + "loss": 1.3432, + "step": 6355 + }, + { + "epoch": 0.67, + "learning_rate": 6.042937001052298e-06, + "loss": 1.327, + "step": 6356 + }, + { + "epoch": 0.67, + "learning_rate": 6.039575776282728e-06, + "loss": 1.3101, + "step": 6357 + }, + { + "epoch": 0.67, + "learning_rate": 6.0362150821082425e-06, + "loss": 1.3239, + "step": 6358 + }, + { + "epoch": 0.67, + "learning_rate": 6.032854918979092e-06, + "loss": 1.435, + "step": 6359 + }, + { + "epoch": 0.67, + "learning_rate": 6.029495287345448e-06, + "loss": 1.3503, + "step": 6360 + }, + { + "epoch": 0.67, + "learning_rate": 6.0261361876574186e-06, + "loss": 1.3356, + "step": 6361 + }, + { + "epoch": 0.67, + "learning_rate": 6.022777620365032e-06, + "loss": 1.3301, + "step": 6362 + }, + { + "epoch": 0.67, + "learning_rate": 6.019419585918255e-06, + "loss": 1.3925, + "step": 6363 + }, + { + "epoch": 0.67, + "learning_rate": 6.016062084766978e-06, + "loss": 1.3794, + "step": 6364 + }, + { + "epoch": 0.67, + "learning_rate": 6.0127051173610155e-06, + "loss": 1.5496, + "step": 6365 + }, + { + "epoch": 0.67, + "learning_rate": 6.009348684150116e-06, + "loss": 1.3227, + "step": 6366 + }, + { + "epoch": 0.67, + "learning_rate": 6.005992785583958e-06, + "loss": 1.3474, + "step": 6367 + }, + { + "epoch": 0.67, + "learning_rate": 6.002637422112143e-06, + "loss": 1.3262, + "step": 6368 + }, + { + "epoch": 0.67, + "eval_loss": 1.4049769639968872, + "eval_runtime": 77.5156, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 6368 + }, + { + "epoch": 0.67, + "learning_rate": 5.999282594184206e-06, + "loss": 1.3083, + "step": 6369 + }, + { + "epoch": 0.67, + "learning_rate": 5.995928302249603e-06, + "loss": 1.323, + "step": 6370 + }, + { + "epoch": 0.67, + "learning_rate": 5.99257454675773e-06, + "loss": 1.3101, + "step": 6371 + }, + { + "epoch": 0.67, + "learning_rate": 5.989221328157899e-06, + "loss": 1.4546, + "step": 6372 + }, + { + "epoch": 0.67, + "learning_rate": 5.985868646899355e-06, + "loss": 1.3315, + "step": 6373 + }, + { + "epoch": 0.67, + "learning_rate": 5.982516503431273e-06, + "loss": 1.3768, + "step": 6374 + }, + { + "epoch": 0.67, + "learning_rate": 5.979164898202755e-06, + "loss": 1.332, + "step": 6375 + }, + { + "epoch": 0.67, + "learning_rate": 5.975813831662829e-06, + "loss": 1.3154, + "step": 6376 + }, + { + "epoch": 0.67, + "learning_rate": 5.972463304260448e-06, + "loss": 1.3636, + "step": 6377 + }, + { + "epoch": 0.67, + "learning_rate": 5.969113316444504e-06, + "loss": 1.3553, + "step": 6378 + }, + { + "epoch": 0.67, + "learning_rate": 5.965763868663803e-06, + "loss": 1.3805, + "step": 6379 + }, + { + "epoch": 0.67, + "learning_rate": 5.962414961367089e-06, + "loss": 1.3096, + "step": 6380 + }, + { + "epoch": 0.67, + "learning_rate": 5.959066595003025e-06, + "loss": 1.326, + "step": 6381 + }, + { + "epoch": 0.67, + "learning_rate": 5.955718770020212e-06, + "loss": 1.3021, + "step": 6382 + }, + { + "epoch": 0.67, + "learning_rate": 5.952371486867168e-06, + "loss": 1.35, + "step": 6383 + }, + { + "epoch": 0.67, + "learning_rate": 5.949024745992344e-06, + "loss": 1.6749, + "step": 6384 + }, + { + "epoch": 0.67, + "learning_rate": 5.945678547844117e-06, + "loss": 1.4931, + "step": 6385 + }, + { + "epoch": 0.67, + "learning_rate": 5.942332892870793e-06, + "loss": 1.284, + "step": 6386 + }, + { + "epoch": 0.67, + "learning_rate": 5.938987781520604e-06, + "loss": 1.3296, + "step": 6387 + }, + { + "epoch": 0.67, + "learning_rate": 5.9356432142417074e-06, + "loss": 1.4837, + "step": 6388 + }, + { + "epoch": 0.67, + "learning_rate": 5.932299191482188e-06, + "loss": 1.3114, + "step": 6389 + }, + { + "epoch": 0.67, + "learning_rate": 5.928955713690063e-06, + "loss": 1.3328, + "step": 6390 + }, + { + "epoch": 0.67, + "learning_rate": 5.92561278131327e-06, + "loss": 1.3163, + "step": 6391 + }, + { + "epoch": 0.67, + "learning_rate": 5.922270394799676e-06, + "loss": 1.3068, + "step": 6392 + }, + { + "epoch": 0.67, + "learning_rate": 5.918928554597073e-06, + "loss": 1.292, + "step": 6393 + }, + { + "epoch": 0.67, + "learning_rate": 5.915587261153186e-06, + "loss": 1.3359, + "step": 6394 + }, + { + "epoch": 0.67, + "learning_rate": 5.912246514915662e-06, + "loss": 1.4109, + "step": 6395 + }, + { + "epoch": 0.67, + "learning_rate": 5.908906316332071e-06, + "loss": 1.3083, + "step": 6396 + }, + { + "epoch": 0.67, + "learning_rate": 5.905566665849917e-06, + "loss": 1.2973, + "step": 6397 + }, + { + "epoch": 0.67, + "learning_rate": 5.902227563916627e-06, + "loss": 1.4159, + "step": 6398 + }, + { + "epoch": 0.67, + "learning_rate": 5.898889010979556e-06, + "loss": 1.287, + "step": 6399 + }, + { + "epoch": 0.67, + "learning_rate": 5.89555100748598e-06, + "loss": 1.2865, + "step": 6400 + }, + { + "epoch": 0.67, + "learning_rate": 5.89221355388311e-06, + "loss": 1.3137, + "step": 6401 + }, + { + "epoch": 0.67, + "learning_rate": 5.8888766506180785e-06, + "loss": 1.2751, + "step": 6402 + }, + { + "epoch": 0.67, + "learning_rate": 5.885540298137944e-06, + "loss": 1.3687, + "step": 6403 + }, + { + "epoch": 0.67, + "learning_rate": 5.882204496889688e-06, + "loss": 1.2941, + "step": 6404 + }, + { + "epoch": 0.67, + "learning_rate": 5.878869247320231e-06, + "loss": 1.2926, + "step": 6405 + }, + { + "epoch": 0.67, + "learning_rate": 5.875534549876404e-06, + "loss": 1.2675, + "step": 6406 + }, + { + "epoch": 0.67, + "learning_rate": 5.872200405004973e-06, + "loss": 1.2806, + "step": 6407 + }, + { + "epoch": 0.67, + "learning_rate": 5.868866813152625e-06, + "loss": 1.3438, + "step": 6408 + }, + { + "epoch": 0.67, + "learning_rate": 5.865533774765981e-06, + "loss": 1.2947, + "step": 6409 + }, + { + "epoch": 0.67, + "learning_rate": 5.862201290291578e-06, + "loss": 1.3643, + "step": 6410 + }, + { + "epoch": 0.67, + "learning_rate": 5.858869360175887e-06, + "loss": 1.2579, + "step": 6411 + }, + { + "epoch": 0.67, + "learning_rate": 5.855537984865296e-06, + "loss": 1.3479, + "step": 6412 + }, + { + "epoch": 0.67, + "learning_rate": 5.852207164806127e-06, + "loss": 1.3239, + "step": 6413 + }, + { + "epoch": 0.67, + "learning_rate": 5.848876900444626e-06, + "loss": 1.2644, + "step": 6414 + }, + { + "epoch": 0.67, + "learning_rate": 5.845547192226959e-06, + "loss": 1.3279, + "step": 6415 + }, + { + "epoch": 0.67, + "learning_rate": 5.8422180405992216e-06, + "loss": 1.5202, + "step": 6416 + }, + { + "epoch": 0.67, + "learning_rate": 5.838889446007439e-06, + "loss": 1.5714, + "step": 6417 + }, + { + "epoch": 0.67, + "learning_rate": 5.835561408897552e-06, + "loss": 1.2592, + "step": 6418 + }, + { + "epoch": 0.67, + "learning_rate": 5.832233929715434e-06, + "loss": 1.3407, + "step": 6419 + }, + { + "epoch": 0.67, + "learning_rate": 5.828907008906882e-06, + "loss": 1.3555, + "step": 6420 + }, + { + "epoch": 0.67, + "learning_rate": 5.825580646917622e-06, + "loss": 1.2602, + "step": 6421 + }, + { + "epoch": 0.67, + "learning_rate": 5.822254844193293e-06, + "loss": 1.2672, + "step": 6422 + }, + { + "epoch": 0.67, + "learning_rate": 5.818929601179472e-06, + "loss": 1.3361, + "step": 6423 + }, + { + "epoch": 0.67, + "learning_rate": 5.8156049183216575e-06, + "loss": 1.49, + "step": 6424 + }, + { + "epoch": 0.67, + "learning_rate": 5.812280796065269e-06, + "loss": 1.306, + "step": 6425 + }, + { + "epoch": 0.67, + "learning_rate": 5.808957234855654e-06, + "loss": 1.3167, + "step": 6426 + }, + { + "epoch": 0.67, + "learning_rate": 5.805634235138082e-06, + "loss": 1.3103, + "step": 6427 + }, + { + "epoch": 0.67, + "learning_rate": 5.802311797357752e-06, + "loss": 1.2992, + "step": 6428 + }, + { + "epoch": 0.67, + "learning_rate": 5.7989899219597875e-06, + "loss": 1.3269, + "step": 6429 + }, + { + "epoch": 0.67, + "learning_rate": 5.795668609389233e-06, + "loss": 1.3393, + "step": 6430 + }, + { + "epoch": 0.67, + "learning_rate": 5.79234786009105e-06, + "loss": 1.2633, + "step": 6431 + }, + { + "epoch": 0.67, + "learning_rate": 5.7890276745101495e-06, + "loss": 1.2758, + "step": 6432 + }, + { + "epoch": 0.67, + "learning_rate": 5.785708053091339e-06, + "loss": 1.3294, + "step": 6433 + }, + { + "epoch": 0.67, + "learning_rate": 5.782388996279371e-06, + "loss": 1.3657, + "step": 6434 + }, + { + "epoch": 0.67, + "learning_rate": 5.779070504518905e-06, + "loss": 1.3353, + "step": 6435 + }, + { + "epoch": 0.67, + "learning_rate": 5.775752578254539e-06, + "loss": 1.2741, + "step": 6436 + }, + { + "epoch": 0.68, + "learning_rate": 5.772435217930792e-06, + "loss": 1.2979, + "step": 6437 + }, + { + "epoch": 0.68, + "learning_rate": 5.7691184239921026e-06, + "loss": 1.366, + "step": 6438 + }, + { + "epoch": 0.68, + "learning_rate": 5.765802196882828e-06, + "loss": 1.2873, + "step": 6439 + }, + { + "epoch": 0.68, + "learning_rate": 5.762486537047271e-06, + "loss": 1.2865, + "step": 6440 + }, + { + "epoch": 0.68, + "learning_rate": 5.7591714449296365e-06, + "loss": 1.3887, + "step": 6441 + }, + { + "epoch": 0.68, + "learning_rate": 5.755856920974063e-06, + "loss": 1.127, + "step": 6442 + }, + { + "epoch": 0.68, + "learning_rate": 5.752542965624617e-06, + "loss": 1.4331, + "step": 6443 + }, + { + "epoch": 0.68, + "learning_rate": 5.749229579325274e-06, + "loss": 1.3199, + "step": 6444 + }, + { + "epoch": 0.68, + "learning_rate": 5.745916762519952e-06, + "loss": 1.2719, + "step": 6445 + }, + { + "epoch": 0.68, + "learning_rate": 5.742604515652475e-06, + "loss": 1.2991, + "step": 6446 + }, + { + "epoch": 0.68, + "learning_rate": 5.7392928391666014e-06, + "loss": 1.2164, + "step": 6447 + }, + { + "epoch": 0.68, + "learning_rate": 5.735981733506016e-06, + "loss": 1.3636, + "step": 6448 + }, + { + "epoch": 0.68, + "learning_rate": 5.732671199114314e-06, + "loss": 1.3486, + "step": 6449 + }, + { + "epoch": 0.68, + "learning_rate": 5.729361236435027e-06, + "loss": 1.3378, + "step": 6450 + }, + { + "epoch": 0.68, + "learning_rate": 5.726051845911606e-06, + "loss": 1.3521, + "step": 6451 + }, + { + "epoch": 0.68, + "learning_rate": 5.722743027987421e-06, + "loss": 1.4295, + "step": 6452 + }, + { + "epoch": 0.68, + "learning_rate": 5.719434783105772e-06, + "loss": 1.2625, + "step": 6453 + }, + { + "epoch": 0.68, + "learning_rate": 5.716127111709873e-06, + "loss": 1.2944, + "step": 6454 + }, + { + "epoch": 0.68, + "learning_rate": 5.7128200142428695e-06, + "loss": 1.3655, + "step": 6455 + }, + { + "epoch": 0.68, + "learning_rate": 5.7095134911478336e-06, + "loss": 1.3115, + "step": 6456 + }, + { + "epoch": 0.68, + "learning_rate": 5.706207542867747e-06, + "loss": 1.3391, + "step": 6457 + }, + { + "epoch": 0.68, + "learning_rate": 5.702902169845519e-06, + "loss": 1.3911, + "step": 6458 + }, + { + "epoch": 0.68, + "learning_rate": 5.699597372523997e-06, + "loss": 1.2936, + "step": 6459 + }, + { + "epoch": 0.68, + "learning_rate": 5.696293151345928e-06, + "loss": 1.379, + "step": 6460 + }, + { + "epoch": 0.68, + "learning_rate": 5.692989506754e-06, + "loss": 1.4083, + "step": 6461 + }, + { + "epoch": 0.68, + "learning_rate": 5.689686439190809e-06, + "loss": 1.2645, + "step": 6462 + }, + { + "epoch": 0.68, + "learning_rate": 5.686383949098886e-06, + "loss": 1.3207, + "step": 6463 + }, + { + "epoch": 0.68, + "learning_rate": 5.683082036920682e-06, + "loss": 1.4293, + "step": 6464 + }, + { + "epoch": 0.68, + "learning_rate": 5.679780703098563e-06, + "loss": 1.3018, + "step": 6465 + }, + { + "epoch": 0.68, + "learning_rate": 5.676479948074825e-06, + "loss": 1.3568, + "step": 6466 + }, + { + "epoch": 0.68, + "learning_rate": 5.673179772291687e-06, + "loss": 1.3252, + "step": 6467 + }, + { + "epoch": 0.68, + "learning_rate": 5.669880176191283e-06, + "loss": 1.2674, + "step": 6468 + }, + { + "epoch": 0.68, + "learning_rate": 5.666581160215676e-06, + "loss": 1.3774, + "step": 6469 + }, + { + "epoch": 0.68, + "learning_rate": 5.663282724806855e-06, + "loss": 1.3013, + "step": 6470 + }, + { + "epoch": 0.68, + "learning_rate": 5.659984870406715e-06, + "loss": 1.3354, + "step": 6471 + }, + { + "epoch": 0.68, + "learning_rate": 5.656687597457093e-06, + "loss": 1.273, + "step": 6472 + }, + { + "epoch": 0.68, + "learning_rate": 5.653390906399732e-06, + "loss": 1.3041, + "step": 6473 + }, + { + "epoch": 0.68, + "learning_rate": 5.650094797676308e-06, + "loss": 1.3521, + "step": 6474 + }, + { + "epoch": 0.68, + "learning_rate": 5.646799271728417e-06, + "loss": 1.3751, + "step": 6475 + }, + { + "epoch": 0.68, + "learning_rate": 5.643504328997571e-06, + "loss": 1.2882, + "step": 6476 + }, + { + "epoch": 0.68, + "learning_rate": 5.640209969925202e-06, + "loss": 1.2625, + "step": 6477 + }, + { + "epoch": 0.68, + "learning_rate": 5.636916194952683e-06, + "loss": 1.3648, + "step": 6478 + }, + { + "epoch": 0.68, + "learning_rate": 5.633623004521285e-06, + "loss": 1.3115, + "step": 6479 + }, + { + "epoch": 0.68, + "learning_rate": 5.6303303990722154e-06, + "loss": 1.2755, + "step": 6480 + }, + { + "epoch": 0.68, + "learning_rate": 5.627038379046595e-06, + "loss": 1.4546, + "step": 6481 + }, + { + "epoch": 0.68, + "learning_rate": 5.623746944885473e-06, + "loss": 1.3717, + "step": 6482 + }, + { + "epoch": 0.68, + "learning_rate": 5.620456097029818e-06, + "loss": 1.3188, + "step": 6483 + }, + { + "epoch": 0.68, + "learning_rate": 5.61716583592052e-06, + "loss": 1.3166, + "step": 6484 + }, + { + "epoch": 0.68, + "learning_rate": 5.613876161998377e-06, + "loss": 1.3413, + "step": 6485 + }, + { + "epoch": 0.68, + "learning_rate": 5.610587075704139e-06, + "loss": 1.395, + "step": 6486 + }, + { + "epoch": 0.68, + "learning_rate": 5.6072985774784465e-06, + "loss": 1.2914, + "step": 6487 + }, + { + "epoch": 0.68, + "learning_rate": 5.604010667761876e-06, + "loss": 1.3118, + "step": 6488 + }, + { + "epoch": 0.68, + "learning_rate": 5.600723346994932e-06, + "loss": 1.3599, + "step": 6489 + }, + { + "epoch": 0.68, + "learning_rate": 5.597436615618017e-06, + "loss": 1.2862, + "step": 6490 + }, + { + "epoch": 0.68, + "learning_rate": 5.594150474071481e-06, + "loss": 1.3585, + "step": 6491 + }, + { + "epoch": 0.68, + "learning_rate": 5.590864922795573e-06, + "loss": 1.3449, + "step": 6492 + }, + { + "epoch": 0.68, + "learning_rate": 5.587579962230475e-06, + "loss": 1.2787, + "step": 6493 + }, + { + "epoch": 0.68, + "learning_rate": 5.5842955928162934e-06, + "loss": 1.3755, + "step": 6494 + }, + { + "epoch": 0.68, + "learning_rate": 5.5810118149930406e-06, + "loss": 1.2858, + "step": 6495 + }, + { + "epoch": 0.68, + "learning_rate": 5.577728629200662e-06, + "loss": 1.4214, + "step": 6496 + }, + { + "epoch": 0.68, + "learning_rate": 5.574446035879024e-06, + "loss": 1.5007, + "step": 6497 + }, + { + "epoch": 0.68, + "learning_rate": 5.571164035467903e-06, + "loss": 1.2952, + "step": 6498 + }, + { + "epoch": 0.68, + "learning_rate": 5.56788262840701e-06, + "loss": 1.267, + "step": 6499 + }, + { + "epoch": 0.68, + "learning_rate": 5.564601815135962e-06, + "loss": 1.3168, + "step": 6500 + }, + { + "epoch": 0.68, + "learning_rate": 5.561321596094305e-06, + "loss": 1.2992, + "step": 6501 + }, + { + "epoch": 0.68, + "learning_rate": 5.558041971721511e-06, + "loss": 1.4237, + "step": 6502 + }, + { + "epoch": 0.68, + "learning_rate": 5.554762942456959e-06, + "loss": 1.3865, + "step": 6503 + }, + { + "epoch": 0.68, + "learning_rate": 5.5514845087399505e-06, + "loss": 1.2875, + "step": 6504 + }, + { + "epoch": 0.68, + "learning_rate": 5.548206671009724e-06, + "loss": 1.3011, + "step": 6505 + }, + { + "epoch": 0.68, + "learning_rate": 5.544929429705415e-06, + "loss": 1.3425, + "step": 6506 + }, + { + "epoch": 0.68, + "learning_rate": 5.541652785266095e-06, + "loss": 1.4265, + "step": 6507 + }, + { + "epoch": 0.68, + "learning_rate": 5.538376738130747e-06, + "loss": 1.2877, + "step": 6508 + }, + { + "epoch": 0.68, + "learning_rate": 5.535101288738276e-06, + "loss": 1.3652, + "step": 6509 + }, + { + "epoch": 0.68, + "learning_rate": 5.5318264375275145e-06, + "loss": 1.2997, + "step": 6510 + }, + { + "epoch": 0.68, + "learning_rate": 5.528552184937201e-06, + "loss": 1.3223, + "step": 6511 + }, + { + "epoch": 0.68, + "learning_rate": 5.525278531406006e-06, + "loss": 1.2897, + "step": 6512 + }, + { + "epoch": 0.68, + "learning_rate": 5.522005477372516e-06, + "loss": 1.3554, + "step": 6513 + }, + { + "epoch": 0.68, + "learning_rate": 5.51873302327523e-06, + "loss": 1.3233, + "step": 6514 + }, + { + "epoch": 0.68, + "learning_rate": 5.515461169552576e-06, + "loss": 1.3536, + "step": 6515 + }, + { + "epoch": 0.68, + "learning_rate": 5.5121899166429046e-06, + "loss": 1.3485, + "step": 6516 + }, + { + "epoch": 0.68, + "learning_rate": 5.508919264984468e-06, + "loss": 1.3264, + "step": 6517 + }, + { + "epoch": 0.68, + "learning_rate": 5.505649215015461e-06, + "loss": 1.4498, + "step": 6518 + }, + { + "epoch": 0.68, + "learning_rate": 5.5023797671739755e-06, + "loss": 1.4468, + "step": 6519 + }, + { + "epoch": 0.68, + "learning_rate": 5.499110921898038e-06, + "loss": 1.2659, + "step": 6520 + }, + { + "epoch": 0.68, + "learning_rate": 5.4958426796255934e-06, + "loss": 1.318, + "step": 6521 + }, + { + "epoch": 0.68, + "learning_rate": 5.492575040794498e-06, + "loss": 1.3167, + "step": 6522 + }, + { + "epoch": 0.68, + "learning_rate": 5.48930800584253e-06, + "loss": 1.3453, + "step": 6523 + }, + { + "epoch": 0.68, + "learning_rate": 5.486041575207397e-06, + "loss": 1.2557, + "step": 6524 + }, + { + "epoch": 0.68, + "learning_rate": 5.482775749326705e-06, + "loss": 1.3235, + "step": 6525 + }, + { + "epoch": 0.68, + "learning_rate": 5.479510528638001e-06, + "loss": 1.3119, + "step": 6526 + }, + { + "epoch": 0.68, + "learning_rate": 5.476245913578733e-06, + "loss": 1.4639, + "step": 6527 + }, + { + "epoch": 0.68, + "learning_rate": 5.472981904586277e-06, + "loss": 1.3233, + "step": 6528 + }, + { + "epoch": 0.68, + "learning_rate": 5.469718502097931e-06, + "loss": 1.2722, + "step": 6529 + }, + { + "epoch": 0.68, + "learning_rate": 5.466455706550906e-06, + "loss": 1.4428, + "step": 6530 + }, + { + "epoch": 0.68, + "learning_rate": 5.463193518382321e-06, + "loss": 1.5695, + "step": 6531 + }, + { + "epoch": 0.68, + "learning_rate": 5.4599319380292434e-06, + "loss": 1.3161, + "step": 6532 + }, + { + "epoch": 0.69, + "learning_rate": 5.4566709659286296e-06, + "loss": 1.3513, + "step": 6533 + }, + { + "epoch": 0.69, + "learning_rate": 5.453410602517368e-06, + "loss": 1.2716, + "step": 6534 + }, + { + "epoch": 0.69, + "learning_rate": 5.45015084823227e-06, + "loss": 1.4467, + "step": 6535 + }, + { + "epoch": 0.69, + "learning_rate": 5.44689170351005e-06, + "loss": 1.4082, + "step": 6536 + }, + { + "epoch": 0.69, + "learning_rate": 5.443633168787357e-06, + "loss": 1.303, + "step": 6537 + }, + { + "epoch": 0.69, + "learning_rate": 5.440375244500743e-06, + "loss": 1.2765, + "step": 6538 + }, + { + "epoch": 0.69, + "learning_rate": 5.43711793108669e-06, + "loss": 1.6814, + "step": 6539 + }, + { + "epoch": 0.69, + "learning_rate": 5.4338612289816e-06, + "loss": 1.3899, + "step": 6540 + }, + { + "epoch": 0.69, + "learning_rate": 5.430605138621778e-06, + "loss": 1.201, + "step": 6541 + }, + { + "epoch": 0.69, + "learning_rate": 5.42734966044346e-06, + "loss": 1.3214, + "step": 6542 + }, + { + "epoch": 0.69, + "learning_rate": 5.424094794882801e-06, + "loss": 1.2676, + "step": 6543 + }, + { + "epoch": 0.69, + "learning_rate": 5.420840542375862e-06, + "loss": 1.3006, + "step": 6544 + }, + { + "epoch": 0.69, + "learning_rate": 5.4175869033586355e-06, + "loss": 1.32, + "step": 6545 + }, + { + "epoch": 0.69, + "learning_rate": 5.41433387826702e-06, + "loss": 1.3347, + "step": 6546 + }, + { + "epoch": 0.69, + "learning_rate": 5.41108146753684e-06, + "loss": 1.3983, + "step": 6547 + }, + { + "epoch": 0.69, + "learning_rate": 5.407829671603838e-06, + "loss": 1.3756, + "step": 6548 + }, + { + "epoch": 0.69, + "learning_rate": 5.404578490903664e-06, + "loss": 1.3444, + "step": 6549 + }, + { + "epoch": 0.69, + "learning_rate": 5.4013279258718974e-06, + "loss": 1.3369, + "step": 6550 + }, + { + "epoch": 0.69, + "learning_rate": 5.398077976944034e-06, + "loss": 1.2995, + "step": 6551 + }, + { + "epoch": 0.69, + "learning_rate": 5.394828644555475e-06, + "loss": 1.3305, + "step": 6552 + }, + { + "epoch": 0.69, + "learning_rate": 5.391579929141554e-06, + "loss": 1.3743, + "step": 6553 + }, + { + "epoch": 0.69, + "learning_rate": 5.3883318311375095e-06, + "loss": 1.2829, + "step": 6554 + }, + { + "epoch": 0.69, + "learning_rate": 5.3850843509785065e-06, + "loss": 1.379, + "step": 6555 + }, + { + "epoch": 0.69, + "learning_rate": 5.3818374890996295e-06, + "loss": 1.3236, + "step": 6556 + }, + { + "epoch": 0.69, + "learning_rate": 5.378591245935865e-06, + "loss": 1.3469, + "step": 6557 + }, + { + "epoch": 0.69, + "learning_rate": 5.375345621922129e-06, + "loss": 1.3318, + "step": 6558 + }, + { + "epoch": 0.69, + "learning_rate": 5.3721006174932576e-06, + "loss": 1.3395, + "step": 6559 + }, + { + "epoch": 0.69, + "learning_rate": 5.36885623308399e-06, + "loss": 1.4148, + "step": 6560 + }, + { + "epoch": 0.69, + "learning_rate": 5.365612469128993e-06, + "loss": 1.3007, + "step": 6561 + }, + { + "epoch": 0.69, + "learning_rate": 5.362369326062853e-06, + "loss": 1.4365, + "step": 6562 + }, + { + "epoch": 0.69, + "learning_rate": 5.3591268043200585e-06, + "loss": 1.4269, + "step": 6563 + }, + { + "epoch": 0.69, + "learning_rate": 5.355884904335034e-06, + "loss": 1.2619, + "step": 6564 + }, + { + "epoch": 0.69, + "learning_rate": 5.3526436265421e-06, + "loss": 1.2678, + "step": 6565 + }, + { + "epoch": 0.69, + "learning_rate": 5.34940297137551e-06, + "loss": 1.2541, + "step": 6566 + }, + { + "epoch": 0.69, + "learning_rate": 5.3461629392694345e-06, + "loss": 1.3237, + "step": 6567 + }, + { + "epoch": 0.69, + "eval_loss": 1.402653694152832, + "eval_runtime": 77.5033, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 6567 + }, + { + "epoch": 0.69, + "learning_rate": 5.342923530657944e-06, + "loss": 1.357, + "step": 6568 + }, + { + "epoch": 0.69, + "learning_rate": 5.33968474597504e-06, + "loss": 1.3561, + "step": 6569 + }, + { + "epoch": 0.69, + "learning_rate": 5.336446585654642e-06, + "loss": 1.2969, + "step": 6570 + }, + { + "epoch": 0.69, + "learning_rate": 5.33320905013057e-06, + "loss": 1.2922, + "step": 6571 + }, + { + "epoch": 0.69, + "learning_rate": 5.329972139836581e-06, + "loss": 1.3581, + "step": 6572 + }, + { + "epoch": 0.69, + "learning_rate": 5.326735855206328e-06, + "loss": 1.2926, + "step": 6573 + }, + { + "epoch": 0.69, + "learning_rate": 5.3235001966733965e-06, + "loss": 1.3933, + "step": 6574 + }, + { + "epoch": 0.69, + "learning_rate": 5.320265164671283e-06, + "loss": 1.4009, + "step": 6575 + }, + { + "epoch": 0.69, + "learning_rate": 5.3170307596333955e-06, + "loss": 1.4051, + "step": 6576 + }, + { + "epoch": 0.69, + "learning_rate": 5.313796981993054e-06, + "loss": 1.3448, + "step": 6577 + }, + { + "epoch": 0.69, + "learning_rate": 5.310563832183515e-06, + "loss": 1.3141, + "step": 6578 + }, + { + "epoch": 0.69, + "learning_rate": 5.307331310637929e-06, + "loss": 1.3658, + "step": 6579 + }, + { + "epoch": 0.69, + "learning_rate": 5.3040994177893725e-06, + "loss": 1.2881, + "step": 6580 + }, + { + "epoch": 0.69, + "learning_rate": 5.30086815407084e-06, + "loss": 1.3051, + "step": 6581 + }, + { + "epoch": 0.69, + "learning_rate": 5.297637519915231e-06, + "loss": 1.3353, + "step": 6582 + }, + { + "epoch": 0.69, + "learning_rate": 5.2944075157553754e-06, + "loss": 1.3997, + "step": 6583 + }, + { + "epoch": 0.69, + "learning_rate": 5.291178142024002e-06, + "loss": 1.3094, + "step": 6584 + }, + { + "epoch": 0.69, + "learning_rate": 5.287949399153769e-06, + "loss": 1.3384, + "step": 6585 + }, + { + "epoch": 0.69, + "learning_rate": 5.284721287577248e-06, + "loss": 1.3183, + "step": 6586 + }, + { + "epoch": 0.69, + "learning_rate": 5.281493807726916e-06, + "loss": 1.4433, + "step": 6587 + }, + { + "epoch": 0.69, + "learning_rate": 5.278266960035174e-06, + "loss": 1.3103, + "step": 6588 + }, + { + "epoch": 0.69, + "learning_rate": 5.275040744934343e-06, + "loss": 1.3478, + "step": 6589 + }, + { + "epoch": 0.69, + "learning_rate": 5.271815162856645e-06, + "loss": 1.2713, + "step": 6590 + }, + { + "epoch": 0.69, + "learning_rate": 5.268590214234233e-06, + "loss": 1.3697, + "step": 6591 + }, + { + "epoch": 0.69, + "learning_rate": 5.265365899499156e-06, + "loss": 1.6169, + "step": 6592 + }, + { + "epoch": 0.69, + "learning_rate": 5.262142219083398e-06, + "loss": 1.2988, + "step": 6593 + }, + { + "epoch": 0.69, + "learning_rate": 5.258919173418851e-06, + "loss": 1.515, + "step": 6594 + }, + { + "epoch": 0.69, + "learning_rate": 5.2556967629373125e-06, + "loss": 1.3704, + "step": 6595 + }, + { + "epoch": 0.69, + "learning_rate": 5.2524749880705075e-06, + "loss": 1.2404, + "step": 6596 + }, + { + "epoch": 0.69, + "learning_rate": 5.249253849250073e-06, + "loss": 1.2799, + "step": 6597 + }, + { + "epoch": 0.69, + "learning_rate": 5.246033346907553e-06, + "loss": 1.2876, + "step": 6598 + }, + { + "epoch": 0.69, + "learning_rate": 5.24281348147442e-06, + "loss": 1.3058, + "step": 6599 + }, + { + "epoch": 0.69, + "learning_rate": 5.239594253382043e-06, + "loss": 1.3347, + "step": 6600 + }, + { + "epoch": 0.69, + "learning_rate": 5.236375663061722e-06, + "loss": 1.3323, + "step": 6601 + }, + { + "epoch": 0.69, + "learning_rate": 5.23315771094467e-06, + "loss": 1.3254, + "step": 6602 + }, + { + "epoch": 0.69, + "learning_rate": 5.229940397461999e-06, + "loss": 1.3462, + "step": 6603 + }, + { + "epoch": 0.69, + "learning_rate": 5.226723723044753e-06, + "loss": 1.2901, + "step": 6604 + }, + { + "epoch": 0.69, + "learning_rate": 5.223507688123887e-06, + "loss": 1.3079, + "step": 6605 + }, + { + "epoch": 0.69, + "learning_rate": 5.220292293130258e-06, + "loss": 1.4282, + "step": 6606 + }, + { + "epoch": 0.69, + "learning_rate": 5.217077538494651e-06, + "loss": 1.3197, + "step": 6607 + }, + { + "epoch": 0.69, + "learning_rate": 5.213863424647765e-06, + "loss": 1.3581, + "step": 6608 + }, + { + "epoch": 0.69, + "learning_rate": 5.2106499520202005e-06, + "loss": 1.3322, + "step": 6609 + }, + { + "epoch": 0.69, + "learning_rate": 5.207437121042488e-06, + "loss": 1.3368, + "step": 6610 + }, + { + "epoch": 0.69, + "learning_rate": 5.204224932145056e-06, + "loss": 1.2771, + "step": 6611 + }, + { + "epoch": 0.69, + "learning_rate": 5.20101338575826e-06, + "loss": 1.2852, + "step": 6612 + }, + { + "epoch": 0.69, + "learning_rate": 5.197802482312369e-06, + "loss": 1.3733, + "step": 6613 + }, + { + "epoch": 0.69, + "learning_rate": 5.194592222237551e-06, + "loss": 1.3719, + "step": 6614 + }, + { + "epoch": 0.69, + "learning_rate": 5.191382605963906e-06, + "loss": 1.3658, + "step": 6615 + }, + { + "epoch": 0.69, + "learning_rate": 5.1881736339214415e-06, + "loss": 1.3261, + "step": 6616 + }, + { + "epoch": 0.69, + "learning_rate": 5.18496530654007e-06, + "loss": 1.3057, + "step": 6617 + }, + { + "epoch": 0.69, + "learning_rate": 5.181757624249635e-06, + "loss": 1.2665, + "step": 6618 + }, + { + "epoch": 0.69, + "learning_rate": 5.1785505874798716e-06, + "loss": 1.2839, + "step": 6619 + }, + { + "epoch": 0.69, + "learning_rate": 5.175344196660447e-06, + "loss": 1.3131, + "step": 6620 + }, + { + "epoch": 0.69, + "learning_rate": 5.1721384522209385e-06, + "loss": 1.3217, + "step": 6621 + }, + { + "epoch": 0.69, + "learning_rate": 5.168933354590825e-06, + "loss": 1.3306, + "step": 6622 + }, + { + "epoch": 0.69, + "learning_rate": 5.165728904199512e-06, + "loss": 1.3197, + "step": 6623 + }, + { + "epoch": 0.69, + "learning_rate": 5.1625251014763176e-06, + "loss": 1.3035, + "step": 6624 + }, + { + "epoch": 0.69, + "learning_rate": 5.1593219468504605e-06, + "loss": 1.2927, + "step": 6625 + }, + { + "epoch": 0.69, + "learning_rate": 5.156119440751086e-06, + "loss": 1.3333, + "step": 6626 + }, + { + "epoch": 0.69, + "learning_rate": 5.152917583607251e-06, + "loss": 1.3181, + "step": 6627 + }, + { + "epoch": 0.7, + "learning_rate": 5.149716375847913e-06, + "loss": 1.347, + "step": 6628 + }, + { + "epoch": 0.7, + "learning_rate": 5.14651581790196e-06, + "loss": 1.347, + "step": 6629 + }, + { + "epoch": 0.7, + "learning_rate": 5.143315910198179e-06, + "loss": 1.2892, + "step": 6630 + }, + { + "epoch": 0.7, + "learning_rate": 5.140116653165277e-06, + "loss": 1.2996, + "step": 6631 + }, + { + "epoch": 0.7, + "learning_rate": 5.136918047231876e-06, + "loss": 1.2802, + "step": 6632 + }, + { + "epoch": 0.7, + "learning_rate": 5.133720092826501e-06, + "loss": 1.2766, + "step": 6633 + }, + { + "epoch": 0.7, + "learning_rate": 5.130522790377598e-06, + "loss": 1.5365, + "step": 6634 + }, + { + "epoch": 0.7, + "learning_rate": 5.127326140313528e-06, + "loss": 1.4848, + "step": 6635 + }, + { + "epoch": 0.7, + "learning_rate": 5.124130143062551e-06, + "loss": 1.3712, + "step": 6636 + }, + { + "epoch": 0.7, + "learning_rate": 5.120934799052859e-06, + "loss": 1.3094, + "step": 6637 + }, + { + "epoch": 0.7, + "learning_rate": 5.1177401087125355e-06, + "loss": 1.272, + "step": 6638 + }, + { + "epoch": 0.7, + "learning_rate": 5.114546072469593e-06, + "loss": 1.2856, + "step": 6639 + }, + { + "epoch": 0.7, + "learning_rate": 5.111352690751952e-06, + "loss": 1.2886, + "step": 6640 + }, + { + "epoch": 0.7, + "learning_rate": 5.108159963987436e-06, + "loss": 1.277, + "step": 6641 + }, + { + "epoch": 0.7, + "learning_rate": 5.104967892603794e-06, + "loss": 1.3392, + "step": 6642 + }, + { + "epoch": 0.7, + "learning_rate": 5.101776477028684e-06, + "loss": 1.3036, + "step": 6643 + }, + { + "epoch": 0.7, + "learning_rate": 5.098585717689667e-06, + "loss": 1.4116, + "step": 6644 + }, + { + "epoch": 0.7, + "learning_rate": 5.095395615014226e-06, + "loss": 1.3437, + "step": 6645 + }, + { + "epoch": 0.7, + "learning_rate": 5.0922061694297565e-06, + "loss": 1.2608, + "step": 6646 + }, + { + "epoch": 0.7, + "learning_rate": 5.089017381363554e-06, + "loss": 1.2959, + "step": 6647 + }, + { + "epoch": 0.7, + "learning_rate": 5.085829251242844e-06, + "loss": 1.3508, + "step": 6648 + }, + { + "epoch": 0.7, + "learning_rate": 5.0826417794947455e-06, + "loss": 1.34, + "step": 6649 + }, + { + "epoch": 0.7, + "learning_rate": 5.0794549665463e-06, + "loss": 1.3092, + "step": 6650 + }, + { + "epoch": 0.7, + "learning_rate": 5.076268812824463e-06, + "loss": 1.3417, + "step": 6651 + }, + { + "epoch": 0.7, + "learning_rate": 5.073083318756092e-06, + "loss": 1.3424, + "step": 6652 + }, + { + "epoch": 0.7, + "learning_rate": 5.069898484767961e-06, + "loss": 1.3296, + "step": 6653 + }, + { + "epoch": 0.7, + "learning_rate": 5.066714311286762e-06, + "loss": 1.2852, + "step": 6654 + }, + { + "epoch": 0.7, + "learning_rate": 5.063530798739087e-06, + "loss": 1.3462, + "step": 6655 + }, + { + "epoch": 0.7, + "learning_rate": 5.06034794755145e-06, + "loss": 1.3615, + "step": 6656 + }, + { + "epoch": 0.7, + "learning_rate": 5.057165758150262e-06, + "loss": 1.245, + "step": 6657 + }, + { + "epoch": 0.7, + "learning_rate": 5.053984230961862e-06, + "loss": 1.201, + "step": 6658 + }, + { + "epoch": 0.7, + "learning_rate": 5.050803366412494e-06, + "loss": 1.331, + "step": 6659 + }, + { + "epoch": 0.7, + "learning_rate": 5.047623164928306e-06, + "loss": 1.3034, + "step": 6660 + }, + { + "epoch": 0.7, + "learning_rate": 5.044443626935367e-06, + "loss": 1.2822, + "step": 6661 + }, + { + "epoch": 0.7, + "learning_rate": 5.041264752859657e-06, + "loss": 1.2576, + "step": 6662 + }, + { + "epoch": 0.7, + "learning_rate": 5.038086543127055e-06, + "loss": 1.3198, + "step": 6663 + }, + { + "epoch": 0.7, + "learning_rate": 5.034908998163368e-06, + "loss": 1.2892, + "step": 6664 + }, + { + "epoch": 0.7, + "learning_rate": 5.031732118394299e-06, + "loss": 1.3004, + "step": 6665 + }, + { + "epoch": 0.7, + "learning_rate": 5.028555904245469e-06, + "loss": 1.3178, + "step": 6666 + }, + { + "epoch": 0.7, + "learning_rate": 5.0253803561424156e-06, + "loss": 1.3014, + "step": 6667 + }, + { + "epoch": 0.7, + "learning_rate": 5.022205474510571e-06, + "loss": 1.3151, + "step": 6668 + }, + { + "epoch": 0.7, + "learning_rate": 5.019031259775292e-06, + "loss": 1.3551, + "step": 6669 + }, + { + "epoch": 0.7, + "learning_rate": 5.015857712361847e-06, + "loss": 1.4188, + "step": 6670 + }, + { + "epoch": 0.7, + "learning_rate": 5.0126848326954025e-06, + "loss": 1.2743, + "step": 6671 + }, + { + "epoch": 0.7, + "learning_rate": 5.009512621201043e-06, + "loss": 1.3528, + "step": 6672 + }, + { + "epoch": 0.7, + "learning_rate": 5.006341078303771e-06, + "loss": 1.309, + "step": 6673 + }, + { + "epoch": 0.7, + "learning_rate": 5.003170204428483e-06, + "loss": 1.3353, + "step": 6674 + }, + { + "epoch": 0.7, + "learning_rate": 5.000000000000003e-06, + "loss": 1.2753, + "step": 6675 + }, + { + "epoch": 0.7, + "learning_rate": 4.9968304654430465e-06, + "loss": 1.3907, + "step": 6676 + }, + { + "epoch": 0.7, + "learning_rate": 4.993661601182256e-06, + "loss": 1.2876, + "step": 6677 + }, + { + "epoch": 0.7, + "learning_rate": 4.990493407642181e-06, + "loss": 1.2534, + "step": 6678 + }, + { + "epoch": 0.7, + "learning_rate": 4.98732588524727e-06, + "loss": 1.3352, + "step": 6679 + }, + { + "epoch": 0.7, + "learning_rate": 4.984159034421895e-06, + "loss": 1.3302, + "step": 6680 + }, + { + "epoch": 0.7, + "learning_rate": 4.980992855590336e-06, + "loss": 1.3783, + "step": 6681 + }, + { + "epoch": 0.7, + "learning_rate": 4.977827349176769e-06, + "loss": 1.2848, + "step": 6682 + }, + { + "epoch": 0.7, + "learning_rate": 4.974662515605302e-06, + "loss": 1.3269, + "step": 6683 + }, + { + "epoch": 0.7, + "learning_rate": 4.971498355299932e-06, + "loss": 1.3662, + "step": 6684 + }, + { + "epoch": 0.7, + "learning_rate": 4.968334868684579e-06, + "loss": 1.2508, + "step": 6685 + }, + { + "epoch": 0.7, + "learning_rate": 4.965172056183073e-06, + "loss": 1.3872, + "step": 6686 + }, + { + "epoch": 0.7, + "learning_rate": 4.962009918219142e-06, + "loss": 1.3008, + "step": 6687 + }, + { + "epoch": 0.7, + "learning_rate": 4.958848455216434e-06, + "loss": 1.2058, + "step": 6688 + }, + { + "epoch": 0.7, + "learning_rate": 4.95568766759851e-06, + "loss": 1.3127, + "step": 6689 + }, + { + "epoch": 0.7, + "learning_rate": 4.952527555788825e-06, + "loss": 1.2985, + "step": 6690 + }, + { + "epoch": 0.7, + "learning_rate": 4.949368120210757e-06, + "loss": 1.333, + "step": 6691 + }, + { + "epoch": 0.7, + "learning_rate": 4.946209361287593e-06, + "loss": 1.2945, + "step": 6692 + }, + { + "epoch": 0.7, + "learning_rate": 4.943051279442516e-06, + "loss": 1.262, + "step": 6693 + }, + { + "epoch": 0.7, + "learning_rate": 4.93989387509864e-06, + "loss": 1.6155, + "step": 6694 + }, + { + "epoch": 0.7, + "learning_rate": 4.936737148678965e-06, + "loss": 1.2838, + "step": 6695 + }, + { + "epoch": 0.7, + "learning_rate": 4.933581100606415e-06, + "loss": 1.3778, + "step": 6696 + }, + { + "epoch": 0.7, + "learning_rate": 4.930425731303824e-06, + "loss": 1.3624, + "step": 6697 + }, + { + "epoch": 0.7, + "learning_rate": 4.927271041193923e-06, + "loss": 1.2641, + "step": 6698 + }, + { + "epoch": 0.7, + "learning_rate": 4.924117030699362e-06, + "loss": 1.3314, + "step": 6699 + }, + { + "epoch": 0.7, + "learning_rate": 4.920963700242704e-06, + "loss": 1.328, + "step": 6700 + }, + { + "epoch": 0.7, + "learning_rate": 4.917811050246404e-06, + "loss": 1.3128, + "step": 6701 + }, + { + "epoch": 0.7, + "learning_rate": 4.914659081132843e-06, + "loss": 1.3877, + "step": 6702 + }, + { + "epoch": 0.7, + "learning_rate": 4.911507793324299e-06, + "loss": 1.3114, + "step": 6703 + }, + { + "epoch": 0.7, + "learning_rate": 4.908357187242967e-06, + "loss": 1.3592, + "step": 6704 + }, + { + "epoch": 0.7, + "learning_rate": 4.905207263310948e-06, + "loss": 1.329, + "step": 6705 + }, + { + "epoch": 0.7, + "learning_rate": 4.902058021950247e-06, + "loss": 1.2558, + "step": 6706 + }, + { + "epoch": 0.7, + "learning_rate": 4.898909463582784e-06, + "loss": 1.2489, + "step": 6707 + }, + { + "epoch": 0.7, + "learning_rate": 4.895761588630388e-06, + "loss": 1.2817, + "step": 6708 + }, + { + "epoch": 0.7, + "learning_rate": 4.892614397514785e-06, + "loss": 1.1606, + "step": 6709 + }, + { + "epoch": 0.7, + "learning_rate": 4.889467890657628e-06, + "loss": 1.2878, + "step": 6710 + }, + { + "epoch": 0.7, + "learning_rate": 4.886322068480458e-06, + "loss": 1.2747, + "step": 6711 + }, + { + "epoch": 0.7, + "learning_rate": 4.88317693140474e-06, + "loss": 1.3662, + "step": 6712 + }, + { + "epoch": 0.7, + "learning_rate": 4.880032479851844e-06, + "loss": 1.3009, + "step": 6713 + }, + { + "epoch": 0.7, + "learning_rate": 4.8768887142430385e-06, + "loss": 1.3157, + "step": 6714 + }, + { + "epoch": 0.7, + "learning_rate": 4.873745634999511e-06, + "loss": 1.4461, + "step": 6715 + }, + { + "epoch": 0.7, + "learning_rate": 4.870603242542358e-06, + "loss": 1.3818, + "step": 6716 + }, + { + "epoch": 0.7, + "learning_rate": 4.86746153729257e-06, + "loss": 1.3361, + "step": 6717 + }, + { + "epoch": 0.7, + "learning_rate": 4.864320519671061e-06, + "loss": 1.3147, + "step": 6718 + }, + { + "epoch": 0.7, + "learning_rate": 4.8611801900986485e-06, + "loss": 1.3773, + "step": 6719 + }, + { + "epoch": 0.7, + "learning_rate": 4.858040548996049e-06, + "loss": 1.3091, + "step": 6720 + }, + { + "epoch": 0.7, + "learning_rate": 4.854901596783902e-06, + "loss": 1.3314, + "step": 6721 + }, + { + "epoch": 0.7, + "learning_rate": 4.851763333882738e-06, + "loss": 1.3082, + "step": 6722 + }, + { + "epoch": 0.71, + "learning_rate": 4.848625760713007e-06, + "loss": 1.2687, + "step": 6723 + }, + { + "epoch": 0.71, + "learning_rate": 4.845488877695068e-06, + "loss": 1.3378, + "step": 6724 + }, + { + "epoch": 0.71, + "learning_rate": 4.842352685249174e-06, + "loss": 1.3516, + "step": 6725 + }, + { + "epoch": 0.71, + "learning_rate": 4.839217183795501e-06, + "loss": 1.4083, + "step": 6726 + }, + { + "epoch": 0.71, + "learning_rate": 4.836082373754124e-06, + "loss": 1.3073, + "step": 6727 + }, + { + "epoch": 0.71, + "learning_rate": 4.832948255545024e-06, + "loss": 1.2948, + "step": 6728 + }, + { + "epoch": 0.71, + "learning_rate": 4.829814829588099e-06, + "loss": 1.3323, + "step": 6729 + }, + { + "epoch": 0.71, + "learning_rate": 4.826682096303139e-06, + "loss": 1.3101, + "step": 6730 + }, + { + "epoch": 0.71, + "learning_rate": 4.823550056109853e-06, + "loss": 1.3323, + "step": 6731 + }, + { + "epoch": 0.71, + "learning_rate": 4.8204187094278605e-06, + "loss": 1.3862, + "step": 6732 + }, + { + "epoch": 0.71, + "learning_rate": 4.817288056676671e-06, + "loss": 1.3112, + "step": 6733 + }, + { + "epoch": 0.71, + "learning_rate": 4.8141580982757175e-06, + "loss": 1.297, + "step": 6734 + }, + { + "epoch": 0.71, + "learning_rate": 4.811028834644336e-06, + "loss": 1.2604, + "step": 6735 + }, + { + "epoch": 0.71, + "learning_rate": 4.807900266201761e-06, + "loss": 1.343, + "step": 6736 + }, + { + "epoch": 0.71, + "learning_rate": 4.804772393367142e-06, + "loss": 1.3254, + "step": 6737 + }, + { + "epoch": 0.71, + "learning_rate": 4.80164521655954e-06, + "loss": 1.2688, + "step": 6738 + }, + { + "epoch": 0.71, + "learning_rate": 4.798518736197909e-06, + "loss": 1.2693, + "step": 6739 + }, + { + "epoch": 0.71, + "learning_rate": 4.795392952701122e-06, + "loss": 1.4536, + "step": 6740 + }, + { + "epoch": 0.71, + "learning_rate": 4.7922678664879485e-06, + "loss": 1.3811, + "step": 6741 + }, + { + "epoch": 0.71, + "learning_rate": 4.789143477977072e-06, + "loss": 1.2584, + "step": 6742 + }, + { + "epoch": 0.71, + "learning_rate": 4.786019787587084e-06, + "loss": 1.2584, + "step": 6743 + }, + { + "epoch": 0.71, + "learning_rate": 4.782896795736472e-06, + "loss": 1.2005, + "step": 6744 + }, + { + "epoch": 0.71, + "learning_rate": 4.779774502843642e-06, + "loss": 1.335, + "step": 6745 + }, + { + "epoch": 0.71, + "learning_rate": 4.776652909326901e-06, + "loss": 1.3675, + "step": 6746 + }, + { + "epoch": 0.71, + "learning_rate": 4.773532015604457e-06, + "loss": 1.3794, + "step": 6747 + }, + { + "epoch": 0.71, + "learning_rate": 4.770411822094437e-06, + "loss": 1.3629, + "step": 6748 + }, + { + "epoch": 0.71, + "learning_rate": 4.76729232921486e-06, + "loss": 1.0805, + "step": 6749 + }, + { + "epoch": 0.71, + "learning_rate": 4.76417353738366e-06, + "loss": 1.2874, + "step": 6750 + }, + { + "epoch": 0.71, + "learning_rate": 4.761055447018681e-06, + "loss": 1.428, + "step": 6751 + }, + { + "epoch": 0.71, + "learning_rate": 4.757938058537656e-06, + "loss": 1.2935, + "step": 6752 + }, + { + "epoch": 0.71, + "learning_rate": 4.754821372358242e-06, + "loss": 1.4202, + "step": 6753 + }, + { + "epoch": 0.71, + "learning_rate": 4.751705388897997e-06, + "loss": 1.3109, + "step": 6754 + }, + { + "epoch": 0.71, + "learning_rate": 4.7485901085743754e-06, + "loss": 1.3319, + "step": 6755 + }, + { + "epoch": 0.71, + "learning_rate": 4.745475531804753e-06, + "loss": 1.3246, + "step": 6756 + }, + { + "epoch": 0.71, + "learning_rate": 4.742361659006395e-06, + "loss": 1.3407, + "step": 6757 + }, + { + "epoch": 0.71, + "learning_rate": 4.739248490596483e-06, + "loss": 1.2953, + "step": 6758 + }, + { + "epoch": 0.71, + "learning_rate": 4.736136026992107e-06, + "loss": 1.3214, + "step": 6759 + }, + { + "epoch": 0.71, + "learning_rate": 4.733024268610249e-06, + "loss": 1.4112, + "step": 6760 + }, + { + "epoch": 0.71, + "learning_rate": 4.7299132158678085e-06, + "loss": 1.2981, + "step": 6761 + }, + { + "epoch": 0.71, + "learning_rate": 4.726802869181591e-06, + "loss": 1.2975, + "step": 6762 + }, + { + "epoch": 0.71, + "learning_rate": 4.723693228968293e-06, + "loss": 1.3047, + "step": 6763 + }, + { + "epoch": 0.71, + "learning_rate": 4.720584295644533e-06, + "loss": 1.3906, + "step": 6764 + }, + { + "epoch": 0.71, + "learning_rate": 4.717476069626832e-06, + "loss": 1.2523, + "step": 6765 + }, + { + "epoch": 0.71, + "learning_rate": 4.7143685513316025e-06, + "loss": 1.0453, + "step": 6766 + }, + { + "epoch": 0.71, + "eval_loss": 1.4004828929901123, + "eval_runtime": 77.565, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 6766 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 3.026865170753425e+20, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-6766/training_args.bin b/checkpoint-6766/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-6766/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-7164/config.json b/checkpoint-7164/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-7164/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-7164/generation_config.json b/checkpoint-7164/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-7164/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-7164/model-00001-of-00003.safetensors b/checkpoint-7164/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a9855513ac0f205789c12fadedf2c0eb52686765 --- /dev/null +++ b/checkpoint-7164/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a41f642884136fcfb1a0a66c630757e5c80867879978672066434f3a2ee21eb +size 4943162336 diff --git a/checkpoint-7164/model-00002-of-00003.safetensors b/checkpoint-7164/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c8812251da6d2bb194c9c06c403dbb5860b7c2e6 --- /dev/null +++ b/checkpoint-7164/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d3c918f6cbad73592d09c270744251f07b0e49aef77f888569f35de4df10bcc +size 4999819336 diff --git a/checkpoint-7164/model-00003-of-00003.safetensors b/checkpoint-7164/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..274b11134a550090d4bb69a93298571549f91ecb --- /dev/null +++ b/checkpoint-7164/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35551b09597d5aa4da125fa44a43411e1e71b149d21886a3059ab387bb053df9 +size 4540516344 diff --git a/checkpoint-7164/model.safetensors.index.json b/checkpoint-7164/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-7164/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-7164/optimizer.pt b/checkpoint-7164/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..6dc06e99d4784b722cd534339f0e5b667966380d --- /dev/null +++ b/checkpoint-7164/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53cedf7072aa0654f6161732637da79df39f502ff776b1ad8f999eee6eae0ffd +size 14512103560 diff --git a/checkpoint-7164/rng_state_0.pth b/checkpoint-7164/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..48805b5599278dd552bddcd18f947e16f5522c23 --- /dev/null +++ b/checkpoint-7164/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0f6dc27d8e532a9e4354013fb9dd1b5ed776ca79da6a3e2d04c55281e12481c +size 15984 diff --git a/checkpoint-7164/rng_state_1.pth b/checkpoint-7164/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..7728f1e9fd8d218b289786b7cd05833205a0590d --- /dev/null +++ b/checkpoint-7164/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d840369a9e712f4552e4fd2d3f0fde8861bf70d10b54a380994a50099c232df6 +size 15984 diff --git a/checkpoint-7164/rng_state_2.pth b/checkpoint-7164/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..441ccd4e29eb7c5bf36a628aa1e1172adfabd482 --- /dev/null +++ b/checkpoint-7164/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:897f62f8043d5aac7f7bc25fa9a2a07f500e202fb44c6adc3b72b83b082aa23f +size 15984 diff --git a/checkpoint-7164/rng_state_3.pth b/checkpoint-7164/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..0ce7a81f7c55d08f37063b135f2c1e2525208350 --- /dev/null +++ b/checkpoint-7164/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5e5cd1e8e15c12664a44791ffdd6dbecee58bc963503c3d06e5efca20c81e13 +size 15984 diff --git a/checkpoint-7164/rng_state_4.pth b/checkpoint-7164/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..666e4213ee79a69260413cc3c1f2d82336681835 --- /dev/null +++ b/checkpoint-7164/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:973a443afb789959dfbf08e4b4880a2a1384bb4aa580405c4f781cfcf7adc998 +size 15984 diff --git a/checkpoint-7164/rng_state_5.pth b/checkpoint-7164/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..14e7205bce21fd52c9614a21b82e1e2e01198b56 --- /dev/null +++ b/checkpoint-7164/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7f9ee0e3e265a9534f0c9fbe800f0802a53c2ac30ab81ee8eb3ed7e3929a657 +size 15984 diff --git a/checkpoint-7164/rng_state_6.pth b/checkpoint-7164/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..8ca8ce7505e82983cbda380245c7ec172560546e --- /dev/null +++ b/checkpoint-7164/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d47e20102aeeea653c50df3e72e52ab77ff6def5ea960ff20cd0d00e27a11edc +size 15984 diff --git a/checkpoint-7164/rng_state_7.pth b/checkpoint-7164/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..9e331e9743d91be5285df4293866cf1d08717cac --- /dev/null +++ b/checkpoint-7164/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e579ef16e5c6a82777d7151af5acf6fbdd8038ab889a9f6c1bb0f0ef0e51a55b +size 15984 diff --git a/checkpoint-7164/scheduler.pt b/checkpoint-7164/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..1775514abdac30c2e7dfd4a44435dcb7b1aeeb74 --- /dev/null +++ b/checkpoint-7164/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3de2ec0481df31ccea02efda2a484102e98ab9b7ab0d65194f84ac4fa7eb0db +size 1064 diff --git a/checkpoint-7164/special_tokens_map.json b/checkpoint-7164/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-7164/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-7164/tokenizer.model b/checkpoint-7164/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-7164/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-7164/tokenizer_config.json b/checkpoint-7164/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-7164/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-7164/trainer_state.json b/checkpoint-7164/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..161342b202ea0be4bd5b8a6bdd839fe9cadedef4 --- /dev/null +++ b/checkpoint-7164/trainer_state.json @@ -0,0 +1,43292 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.7512583892617449, + "eval_steps": 199, + "global_step": 7164, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + }, + { + "epoch": 0.21, + "learning_rate": 1.928689129323009e-05, + "loss": 1.421, + "step": 1991 + }, + { + "epoch": 0.21, + "learning_rate": 1.928553323396003e-05, + "loss": 1.5625, + "step": 1992 + }, + { + "epoch": 0.21, + "learning_rate": 1.92841739306671e-05, + "loss": 1.5198, + "step": 1993 + }, + { + "epoch": 0.21, + "learning_rate": 1.9282813383533415e-05, + "loss": 1.5116, + "step": 1994 + }, + { + "epoch": 0.21, + "learning_rate": 1.9281451592741247e-05, + "loss": 1.4306, + "step": 1995 + }, + { + "epoch": 0.21, + "learning_rate": 1.9280088558473046e-05, + "loss": 1.5425, + "step": 1996 + }, + { + "epoch": 0.21, + "learning_rate": 1.9278724280911424e-05, + "loss": 1.4972, + "step": 1997 + }, + { + "epoch": 0.21, + "learning_rate": 1.9277358760239156e-05, + "loss": 1.5185, + "step": 1998 + }, + { + "epoch": 0.21, + "learning_rate": 1.9275991996639188e-05, + "loss": 1.5187, + "step": 1999 + }, + { + "epoch": 0.21, + "learning_rate": 1.927462399029463e-05, + "loss": 1.4325, + "step": 2000 + }, + { + "epoch": 0.21, + "learning_rate": 1.9273254741388763e-05, + "loss": 1.4397, + "step": 2001 + }, + { + "epoch": 0.21, + "learning_rate": 1.927188425010503e-05, + "loss": 1.5319, + "step": 2002 + }, + { + "epoch": 0.21, + "learning_rate": 1.9270512516627042e-05, + "loss": 1.5664, + "step": 2003 + }, + { + "epoch": 0.21, + "learning_rate": 1.9269139541138574e-05, + "loss": 1.5227, + "step": 2004 + }, + { + "epoch": 0.21, + "learning_rate": 1.926776532382357e-05, + "loss": 1.5187, + "step": 2005 + }, + { + "epoch": 0.21, + "learning_rate": 1.9266389864866134e-05, + "loss": 1.4029, + "step": 2006 + }, + { + "epoch": 0.21, + "learning_rate": 1.9265013164450557e-05, + "loss": 1.387, + "step": 2007 + }, + { + "epoch": 0.21, + "learning_rate": 1.9263635222761268e-05, + "loss": 1.5047, + "step": 2008 + }, + { + "epoch": 0.21, + "learning_rate": 1.9262256039982882e-05, + "loss": 1.4816, + "step": 2009 + }, + { + "epoch": 0.21, + "learning_rate": 1.9260875616300172e-05, + "loss": 1.4607, + "step": 2010 + }, + { + "epoch": 0.21, + "learning_rate": 1.9259493951898084e-05, + "loss": 1.628, + "step": 2011 + }, + { + "epoch": 0.21, + "learning_rate": 1.9258111046961714e-05, + "loss": 1.4149, + "step": 2012 + }, + { + "epoch": 0.21, + "learning_rate": 1.925672690167635e-05, + "loss": 1.5303, + "step": 2013 + }, + { + "epoch": 0.21, + "learning_rate": 1.925534151622742e-05, + "loss": 1.5198, + "step": 2014 + }, + { + "epoch": 0.21, + "learning_rate": 1.9253954890800535e-05, + "loss": 1.6422, + "step": 2015 + }, + { + "epoch": 0.21, + "learning_rate": 1.925256702558147e-05, + "loss": 1.4738, + "step": 2016 + }, + { + "epoch": 0.21, + "learning_rate": 1.925117792075616e-05, + "loss": 1.4752, + "step": 2017 + }, + { + "epoch": 0.21, + "learning_rate": 1.9249787576510713e-05, + "loss": 1.4547, + "step": 2018 + }, + { + "epoch": 0.21, + "learning_rate": 1.924839599303139e-05, + "loss": 1.4864, + "step": 2019 + }, + { + "epoch": 0.21, + "learning_rate": 1.9247003170504638e-05, + "loss": 1.5037, + "step": 2020 + }, + { + "epoch": 0.21, + "learning_rate": 1.9245609109117053e-05, + "loss": 1.5089, + "step": 2021 + }, + { + "epoch": 0.21, + "learning_rate": 1.924421380905541e-05, + "loss": 1.5616, + "step": 2022 + }, + { + "epoch": 0.21, + "learning_rate": 1.9242817270506634e-05, + "loss": 1.4592, + "step": 2023 + }, + { + "epoch": 0.21, + "learning_rate": 1.9241419493657832e-05, + "loss": 1.5592, + "step": 2024 + }, + { + "epoch": 0.21, + "learning_rate": 1.924002047869627e-05, + "loss": 1.4897, + "step": 2025 + }, + { + "epoch": 0.21, + "learning_rate": 1.9238620225809375e-05, + "loss": 1.4743, + "step": 2026 + }, + { + "epoch": 0.21, + "learning_rate": 1.923721873518475e-05, + "loss": 1.4686, + "step": 2027 + }, + { + "epoch": 0.21, + "learning_rate": 1.923581600701016e-05, + "loss": 1.461, + "step": 2028 + }, + { + "epoch": 0.21, + "learning_rate": 1.9234412041473528e-05, + "loss": 1.6622, + "step": 2029 + }, + { + "epoch": 0.21, + "learning_rate": 1.9233006838762955e-05, + "loss": 1.4707, + "step": 2030 + }, + { + "epoch": 0.21, + "learning_rate": 1.92316003990667e-05, + "loss": 1.5566, + "step": 2031 + }, + { + "epoch": 0.21, + "learning_rate": 1.9230192722573188e-05, + "loss": 1.4881, + "step": 2032 + }, + { + "epoch": 0.21, + "learning_rate": 1.9228783809471015e-05, + "loss": 1.6124, + "step": 2033 + }, + { + "epoch": 0.21, + "learning_rate": 1.9227373659948937e-05, + "loss": 1.3508, + "step": 2034 + }, + { + "epoch": 0.21, + "learning_rate": 1.9225962274195876e-05, + "loss": 1.4418, + "step": 2035 + }, + { + "epoch": 0.21, + "learning_rate": 1.9224549652400927e-05, + "loss": 1.3954, + "step": 2036 + }, + { + "epoch": 0.21, + "learning_rate": 1.922313579475334e-05, + "loss": 1.4798, + "step": 2037 + }, + { + "epoch": 0.21, + "learning_rate": 1.922172070144254e-05, + "loss": 1.4556, + "step": 2038 + }, + { + "epoch": 0.21, + "learning_rate": 1.922030437265811e-05, + "loss": 1.4987, + "step": 2039 + }, + { + "epoch": 0.21, + "learning_rate": 1.9218886808589796e-05, + "loss": 1.4857, + "step": 2040 + }, + { + "epoch": 0.21, + "learning_rate": 1.9217468009427527e-05, + "loss": 1.5289, + "step": 2041 + }, + { + "epoch": 0.21, + "learning_rate": 1.921604797536138e-05, + "loss": 1.5267, + "step": 2042 + }, + { + "epoch": 0.21, + "learning_rate": 1.9214626706581598e-05, + "loss": 1.4655, + "step": 2043 + }, + { + "epoch": 0.21, + "learning_rate": 1.9213204203278602e-05, + "loss": 1.4598, + "step": 2044 + }, + { + "epoch": 0.21, + "learning_rate": 1.9211780465642973e-05, + "loss": 1.4766, + "step": 2045 + }, + { + "epoch": 0.21, + "learning_rate": 1.921035549386545e-05, + "loss": 1.5148, + "step": 2046 + }, + { + "epoch": 0.21, + "learning_rate": 1.9208929288136933e-05, + "loss": 1.5567, + "step": 2047 + }, + { + "epoch": 0.21, + "learning_rate": 1.920750184864852e-05, + "loss": 1.4868, + "step": 2048 + }, + { + "epoch": 0.21, + "learning_rate": 1.920607317559143e-05, + "loss": 1.4752, + "step": 2049 + }, + { + "epoch": 0.21, + "learning_rate": 1.920464326915708e-05, + "loss": 1.4882, + "step": 2050 + }, + { + "epoch": 0.22, + "learning_rate": 1.9203212129537035e-05, + "loss": 1.5933, + "step": 2051 + }, + { + "epoch": 0.22, + "learning_rate": 1.9201779756923037e-05, + "loss": 1.4891, + "step": 2052 + }, + { + "epoch": 0.22, + "learning_rate": 1.9200346151506983e-05, + "loss": 1.4486, + "step": 2053 + }, + { + "epoch": 0.22, + "learning_rate": 1.9198911313480938e-05, + "loss": 1.5091, + "step": 2054 + }, + { + "epoch": 0.22, + "learning_rate": 1.919747524303714e-05, + "loss": 1.4385, + "step": 2055 + }, + { + "epoch": 0.22, + "learning_rate": 1.9196037940367974e-05, + "loss": 1.4104, + "step": 2056 + }, + { + "epoch": 0.22, + "learning_rate": 1.9194599405666015e-05, + "loss": 1.4483, + "step": 2057 + }, + { + "epoch": 0.22, + "learning_rate": 1.9193159639123976e-05, + "loss": 1.4592, + "step": 2058 + }, + { + "epoch": 0.22, + "learning_rate": 1.919171864093476e-05, + "loss": 1.4975, + "step": 2059 + }, + { + "epoch": 0.22, + "learning_rate": 1.9190276411291423e-05, + "loss": 1.4727, + "step": 2060 + }, + { + "epoch": 0.22, + "learning_rate": 1.9188832950387178e-05, + "loss": 1.4791, + "step": 2061 + }, + { + "epoch": 0.22, + "learning_rate": 1.9187388258415423e-05, + "loss": 1.3806, + "step": 2062 + }, + { + "epoch": 0.22, + "learning_rate": 1.9185942335569697e-05, + "loss": 1.4514, + "step": 2063 + }, + { + "epoch": 0.22, + "learning_rate": 1.9184495182043727e-05, + "loss": 1.4389, + "step": 2064 + }, + { + "epoch": 0.22, + "learning_rate": 1.918304679803139e-05, + "loss": 1.5088, + "step": 2065 + }, + { + "epoch": 0.22, + "learning_rate": 1.9181597183726733e-05, + "loss": 1.4665, + "step": 2066 + }, + { + "epoch": 0.22, + "learning_rate": 1.9180146339323966e-05, + "loss": 1.489, + "step": 2067 + }, + { + "epoch": 0.22, + "learning_rate": 1.9178694265017466e-05, + "loss": 1.5215, + "step": 2068 + }, + { + "epoch": 0.22, + "learning_rate": 1.9177240961001775e-05, + "loss": 1.5152, + "step": 2069 + }, + { + "epoch": 0.22, + "learning_rate": 1.9175786427471594e-05, + "loss": 1.4418, + "step": 2070 + }, + { + "epoch": 0.22, + "learning_rate": 1.91743306646218e-05, + "loss": 1.5001, + "step": 2071 + }, + { + "epoch": 0.22, + "learning_rate": 1.9172873672647417e-05, + "loss": 1.4879, + "step": 2072 + }, + { + "epoch": 0.22, + "learning_rate": 1.917141545174366e-05, + "loss": 1.5299, + "step": 2073 + }, + { + "epoch": 0.22, + "learning_rate": 1.9169956002105877e-05, + "loss": 1.4602, + "step": 2074 + }, + { + "epoch": 0.22, + "learning_rate": 1.9168495323929605e-05, + "loss": 1.4921, + "step": 2075 + }, + { + "epoch": 0.22, + "learning_rate": 1.916703341741054e-05, + "loss": 1.4659, + "step": 2076 + }, + { + "epoch": 0.22, + "learning_rate": 1.9165570282744534e-05, + "loss": 1.4707, + "step": 2077 + }, + { + "epoch": 0.22, + "learning_rate": 1.9164105920127613e-05, + "loss": 1.5354, + "step": 2078 + }, + { + "epoch": 0.22, + "learning_rate": 1.9162640329755962e-05, + "loss": 1.526, + "step": 2079 + }, + { + "epoch": 0.22, + "learning_rate": 1.916117351182593e-05, + "loss": 1.6424, + "step": 2080 + }, + { + "epoch": 0.22, + "learning_rate": 1.915970546653404e-05, + "loss": 1.5048, + "step": 2081 + }, + { + "epoch": 0.22, + "learning_rate": 1.915823619407697e-05, + "loss": 1.5344, + "step": 2082 + }, + { + "epoch": 0.22, + "learning_rate": 1.915676569465156e-05, + "loss": 1.4604, + "step": 2083 + }, + { + "epoch": 0.22, + "learning_rate": 1.9155293968454826e-05, + "loss": 1.4929, + "step": 2084 + }, + { + "epoch": 0.22, + "learning_rate": 1.9153821015683937e-05, + "loss": 1.4106, + "step": 2085 + }, + { + "epoch": 0.22, + "learning_rate": 1.915234683653623e-05, + "loss": 1.4146, + "step": 2086 + }, + { + "epoch": 0.22, + "learning_rate": 1.9150871431209207e-05, + "loss": 1.4481, + "step": 2087 + }, + { + "epoch": 0.22, + "learning_rate": 1.914939479990054e-05, + "loss": 1.5206, + "step": 2088 + }, + { + "epoch": 0.22, + "learning_rate": 1.9147916942808054e-05, + "loss": 1.5073, + "step": 2089 + }, + { + "epoch": 0.22, + "learning_rate": 1.9146437860129745e-05, + "loss": 1.5196, + "step": 2090 + }, + { + "epoch": 0.22, + "learning_rate": 1.9144957552063775e-05, + "loss": 1.5389, + "step": 2091 + }, + { + "epoch": 0.22, + "learning_rate": 1.9143476018808463e-05, + "loss": 1.5207, + "step": 2092 + }, + { + "epoch": 0.22, + "learning_rate": 1.9141993260562298e-05, + "loss": 1.3717, + "step": 2093 + }, + { + "epoch": 0.22, + "learning_rate": 1.9140509277523937e-05, + "loss": 1.471, + "step": 2094 + }, + { + "epoch": 0.22, + "learning_rate": 1.9139024069892185e-05, + "loss": 1.4553, + "step": 2095 + }, + { + "epoch": 0.22, + "learning_rate": 1.9137537637866027e-05, + "loss": 1.5311, + "step": 2096 + }, + { + "epoch": 0.22, + "learning_rate": 1.9136049981644614e-05, + "loss": 1.4369, + "step": 2097 + }, + { + "epoch": 0.22, + "learning_rate": 1.913456110142724e-05, + "loss": 1.4528, + "step": 2098 + }, + { + "epoch": 0.22, + "learning_rate": 1.9133070997413384e-05, + "loss": 1.5294, + "step": 2099 + }, + { + "epoch": 0.22, + "learning_rate": 1.9131579669802685e-05, + "loss": 1.4588, + "step": 2100 + }, + { + "epoch": 0.22, + "learning_rate": 1.9130087118794934e-05, + "loss": 1.443, + "step": 2101 + }, + { + "epoch": 0.22, + "learning_rate": 1.9128593344590102e-05, + "loss": 1.4876, + "step": 2102 + }, + { + "epoch": 0.22, + "learning_rate": 1.912709834738831e-05, + "loss": 1.4874, + "step": 2103 + }, + { + "epoch": 0.22, + "learning_rate": 1.9125602127389856e-05, + "loss": 1.4966, + "step": 2104 + }, + { + "epoch": 0.22, + "learning_rate": 1.912410468479519e-05, + "loss": 1.5747, + "step": 2105 + }, + { + "epoch": 0.22, + "learning_rate": 1.9122606019804933e-05, + "loss": 1.4025, + "step": 2106 + }, + { + "epoch": 0.22, + "learning_rate": 1.912110613261987e-05, + "loss": 1.4755, + "step": 2107 + }, + { + "epoch": 0.22, + "learning_rate": 1.911960502344094e-05, + "loss": 1.4739, + "step": 2108 + }, + { + "epoch": 0.22, + "learning_rate": 1.911810269246926e-05, + "loss": 1.4992, + "step": 2109 + }, + { + "epoch": 0.22, + "learning_rate": 1.91165991399061e-05, + "loss": 1.4435, + "step": 2110 + }, + { + "epoch": 0.22, + "learning_rate": 1.91150943659529e-05, + "loss": 1.4918, + "step": 2111 + }, + { + "epoch": 0.22, + "learning_rate": 1.9113588370811258e-05, + "loss": 1.3818, + "step": 2112 + }, + { + "epoch": 0.22, + "learning_rate": 1.911208115468294e-05, + "loss": 1.5105, + "step": 2113 + }, + { + "epoch": 0.22, + "learning_rate": 1.9110572717769878e-05, + "loss": 1.6634, + "step": 2114 + }, + { + "epoch": 0.22, + "learning_rate": 1.9109063060274158e-05, + "loss": 1.5028, + "step": 2115 + }, + { + "epoch": 0.22, + "learning_rate": 1.9107552182398037e-05, + "loss": 1.6657, + "step": 2116 + }, + { + "epoch": 0.22, + "learning_rate": 1.9106040084343935e-05, + "loss": 1.5481, + "step": 2117 + }, + { + "epoch": 0.22, + "learning_rate": 1.910452676631444e-05, + "loss": 1.4505, + "step": 2118 + }, + { + "epoch": 0.22, + "learning_rate": 1.9103012228512284e-05, + "loss": 1.5173, + "step": 2119 + }, + { + "epoch": 0.22, + "learning_rate": 1.9101496471140385e-05, + "loss": 1.3788, + "step": 2120 + }, + { + "epoch": 0.22, + "learning_rate": 1.9099979494401814e-05, + "loss": 1.4649, + "step": 2121 + }, + { + "epoch": 0.22, + "learning_rate": 1.9098461298499805e-05, + "loss": 1.4204, + "step": 2122 + }, + { + "epoch": 0.22, + "learning_rate": 1.9096941883637766e-05, + "loss": 1.4439, + "step": 2123 + }, + { + "epoch": 0.22, + "learning_rate": 1.909542125001925e-05, + "loss": 1.6615, + "step": 2124 + }, + { + "epoch": 0.22, + "learning_rate": 1.9093899397847985e-05, + "loss": 1.4763, + "step": 2125 + }, + { + "epoch": 0.22, + "learning_rate": 1.909237632732786e-05, + "loss": 1.5353, + "step": 2126 + }, + { + "epoch": 0.22, + "learning_rate": 1.909085203866293e-05, + "loss": 1.442, + "step": 2127 + }, + { + "epoch": 0.22, + "learning_rate": 1.9089326532057408e-05, + "loss": 1.4782, + "step": 2128 + }, + { + "epoch": 0.22, + "learning_rate": 1.908779980771567e-05, + "loss": 1.4933, + "step": 2129 + }, + { + "epoch": 0.22, + "learning_rate": 1.9086271865842264e-05, + "loss": 1.5285, + "step": 2130 + }, + { + "epoch": 0.22, + "learning_rate": 1.9084742706641894e-05, + "loss": 1.4736, + "step": 2131 + }, + { + "epoch": 0.22, + "learning_rate": 1.9083212330319427e-05, + "loss": 1.4496, + "step": 2132 + }, + { + "epoch": 0.22, + "learning_rate": 1.908168073707989e-05, + "loss": 1.5099, + "step": 2133 + }, + { + "epoch": 0.22, + "learning_rate": 1.9080147927128483e-05, + "loss": 1.5235, + "step": 2134 + }, + { + "epoch": 0.22, + "learning_rate": 1.9078613900670556e-05, + "loss": 1.4769, + "step": 2135 + }, + { + "epoch": 0.22, + "learning_rate": 1.907707865791164e-05, + "loss": 1.5771, + "step": 2136 + }, + { + "epoch": 0.22, + "learning_rate": 1.907554219905741e-05, + "loss": 1.5116, + "step": 2137 + }, + { + "epoch": 0.22, + "learning_rate": 1.907400452431371e-05, + "loss": 1.5161, + "step": 2138 + }, + { + "epoch": 0.22, + "learning_rate": 1.9072465633886557e-05, + "loss": 1.4356, + "step": 2139 + }, + { + "epoch": 0.22, + "learning_rate": 1.9070925527982117e-05, + "loss": 1.509, + "step": 2140 + }, + { + "epoch": 0.22, + "learning_rate": 1.9069384206806723e-05, + "loss": 1.4681, + "step": 2141 + }, + { + "epoch": 0.22, + "learning_rate": 1.9067841670566883e-05, + "loss": 1.5254, + "step": 2142 + }, + { + "epoch": 0.22, + "learning_rate": 1.9066297919469242e-05, + "loss": 1.4797, + "step": 2143 + }, + { + "epoch": 0.22, + "learning_rate": 1.9064752953720636e-05, + "loss": 1.3996, + "step": 2144 + }, + { + "epoch": 0.22, + "learning_rate": 1.9063206773528042e-05, + "loss": 1.4457, + "step": 2145 + }, + { + "epoch": 0.23, + "learning_rate": 1.9061659379098617e-05, + "loss": 1.5126, + "step": 2146 + }, + { + "epoch": 0.23, + "learning_rate": 1.9060110770639664e-05, + "loss": 1.5925, + "step": 2147 + }, + { + "epoch": 0.23, + "learning_rate": 1.905856094835866e-05, + "loss": 1.5146, + "step": 2148 + }, + { + "epoch": 0.23, + "learning_rate": 1.905700991246324e-05, + "loss": 1.7256, + "step": 2149 + }, + { + "epoch": 0.23, + "learning_rate": 1.90554576631612e-05, + "loss": 1.57, + "step": 2150 + }, + { + "epoch": 0.23, + "learning_rate": 1.905390420066051e-05, + "loss": 1.3722, + "step": 2151 + }, + { + "epoch": 0.23, + "learning_rate": 1.9052349525169292e-05, + "loss": 1.3999, + "step": 2152 + }, + { + "epoch": 0.23, + "learning_rate": 1.9050793636895828e-05, + "loss": 1.586, + "step": 2153 + }, + { + "epoch": 0.23, + "learning_rate": 1.9049236536048567e-05, + "loss": 1.4884, + "step": 2154 + }, + { + "epoch": 0.23, + "learning_rate": 1.9047678222836127e-05, + "loss": 1.5898, + "step": 2155 + }, + { + "epoch": 0.23, + "learning_rate": 1.9046118697467278e-05, + "loss": 1.569, + "step": 2156 + }, + { + "epoch": 0.23, + "learning_rate": 1.904455796015095e-05, + "loss": 1.5592, + "step": 2157 + }, + { + "epoch": 0.23, + "learning_rate": 1.9042996011096253e-05, + "loss": 1.597, + "step": 2158 + }, + { + "epoch": 0.23, + "learning_rate": 1.904143285051244e-05, + "loss": 1.422, + "step": 2159 + }, + { + "epoch": 0.23, + "learning_rate": 1.903986847860894e-05, + "loss": 1.519, + "step": 2160 + }, + { + "epoch": 0.23, + "learning_rate": 1.9038302895595334e-05, + "loss": 1.5197, + "step": 2161 + }, + { + "epoch": 0.23, + "learning_rate": 1.903673610168137e-05, + "loss": 1.4655, + "step": 2162 + }, + { + "epoch": 0.23, + "learning_rate": 1.9035168097076965e-05, + "loss": 1.3909, + "step": 2163 + }, + { + "epoch": 0.23, + "learning_rate": 1.903359888199218e-05, + "loss": 1.4877, + "step": 2164 + }, + { + "epoch": 0.23, + "learning_rate": 1.903202845663726e-05, + "loss": 1.5123, + "step": 2165 + }, + { + "epoch": 0.23, + "learning_rate": 1.9030456821222593e-05, + "loss": 1.4906, + "step": 2166 + }, + { + "epoch": 0.23, + "learning_rate": 1.9028883975958745e-05, + "loss": 1.4574, + "step": 2167 + }, + { + "epoch": 0.23, + "learning_rate": 1.9027309921056435e-05, + "loss": 1.4571, + "step": 2168 + }, + { + "epoch": 0.23, + "learning_rate": 1.902573465672654e-05, + "loss": 1.4281, + "step": 2169 + }, + { + "epoch": 0.23, + "learning_rate": 1.9024158183180116e-05, + "loss": 1.5057, + "step": 2170 + }, + { + "epoch": 0.23, + "learning_rate": 1.902258050062836e-05, + "loss": 1.4514, + "step": 2171 + }, + { + "epoch": 0.23, + "learning_rate": 1.9021001609282646e-05, + "loss": 1.5055, + "step": 2172 + }, + { + "epoch": 0.23, + "learning_rate": 1.9019421509354505e-05, + "loss": 1.4578, + "step": 2173 + }, + { + "epoch": 0.23, + "learning_rate": 1.9017840201055625e-05, + "loss": 1.459, + "step": 2174 + }, + { + "epoch": 0.23, + "learning_rate": 1.9016257684597864e-05, + "loss": 1.5059, + "step": 2175 + }, + { + "epoch": 0.23, + "learning_rate": 1.901467396019324e-05, + "loss": 1.57, + "step": 2176 + }, + { + "epoch": 0.23, + "learning_rate": 1.901308902805393e-05, + "loss": 1.4924, + "step": 2177 + }, + { + "epoch": 0.23, + "learning_rate": 1.9011502888392273e-05, + "loss": 1.4979, + "step": 2178 + }, + { + "epoch": 0.23, + "learning_rate": 1.900991554142077e-05, + "loss": 1.5321, + "step": 2179 + }, + { + "epoch": 0.23, + "learning_rate": 1.9008326987352093e-05, + "loss": 1.493, + "step": 2180 + }, + { + "epoch": 0.23, + "learning_rate": 1.9006737226399056e-05, + "loss": 1.5111, + "step": 2181 + }, + { + "epoch": 0.23, + "learning_rate": 1.900514625877465e-05, + "loss": 1.4154, + "step": 2182 + }, + { + "epoch": 0.23, + "learning_rate": 1.900355408469203e-05, + "loss": 1.4934, + "step": 2183 + }, + { + "epoch": 0.23, + "learning_rate": 1.90019607043645e-05, + "loss": 1.5975, + "step": 2184 + }, + { + "epoch": 0.23, + "learning_rate": 1.9000366118005532e-05, + "loss": 1.3537, + "step": 2185 + }, + { + "epoch": 0.23, + "learning_rate": 1.899877032582876e-05, + "loss": 1.4583, + "step": 2186 + }, + { + "epoch": 0.23, + "learning_rate": 1.8997173328047984e-05, + "loss": 1.4586, + "step": 2187 + }, + { + "epoch": 0.23, + "learning_rate": 1.8995575124877156e-05, + "loss": 1.4774, + "step": 2188 + }, + { + "epoch": 0.23, + "learning_rate": 1.8993975716530394e-05, + "loss": 1.5025, + "step": 2189 + }, + { + "epoch": 0.23, + "eval_loss": 1.5263344049453735, + "eval_runtime": 77.1492, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 2189 + }, + { + "epoch": 0.23, + "learning_rate": 1.899237510322198e-05, + "loss": 1.5438, + "step": 2190 + }, + { + "epoch": 0.23, + "learning_rate": 1.899077328516635e-05, + "loss": 1.5181, + "step": 2191 + }, + { + "epoch": 0.23, + "learning_rate": 1.8989170262578112e-05, + "loss": 1.4454, + "step": 2192 + }, + { + "epoch": 0.23, + "learning_rate": 1.8987566035672028e-05, + "loss": 1.4882, + "step": 2193 + }, + { + "epoch": 0.23, + "learning_rate": 1.8985960604663026e-05, + "loss": 1.5073, + "step": 2194 + }, + { + "epoch": 0.23, + "learning_rate": 1.8984353969766187e-05, + "loss": 1.4478, + "step": 2195 + }, + { + "epoch": 0.23, + "learning_rate": 1.8982746131196763e-05, + "loss": 1.4768, + "step": 2196 + }, + { + "epoch": 0.23, + "learning_rate": 1.8981137089170162e-05, + "loss": 1.5116, + "step": 2197 + }, + { + "epoch": 0.23, + "learning_rate": 1.8979526843901952e-05, + "loss": 1.4202, + "step": 2198 + }, + { + "epoch": 0.23, + "learning_rate": 1.8977915395607867e-05, + "loss": 1.4736, + "step": 2199 + }, + { + "epoch": 0.23, + "learning_rate": 1.89763027445038e-05, + "loss": 1.4489, + "step": 2200 + }, + { + "epoch": 0.23, + "learning_rate": 1.8974688890805804e-05, + "loss": 1.4512, + "step": 2201 + }, + { + "epoch": 0.23, + "learning_rate": 1.897307383473009e-05, + "loss": 1.5091, + "step": 2202 + }, + { + "epoch": 0.23, + "learning_rate": 1.897145757649304e-05, + "loss": 1.5512, + "step": 2203 + }, + { + "epoch": 0.23, + "learning_rate": 1.8969840116311192e-05, + "loss": 1.406, + "step": 2204 + }, + { + "epoch": 0.23, + "learning_rate": 1.896822145440124e-05, + "loss": 1.4531, + "step": 2205 + }, + { + "epoch": 0.23, + "learning_rate": 1.896660159098004e-05, + "loss": 1.4379, + "step": 2206 + }, + { + "epoch": 0.23, + "learning_rate": 1.896498052626462e-05, + "loss": 1.4783, + "step": 2207 + }, + { + "epoch": 0.23, + "learning_rate": 1.896335826047216e-05, + "loss": 1.4801, + "step": 2208 + }, + { + "epoch": 0.23, + "learning_rate": 1.896173479381999e-05, + "loss": 1.4526, + "step": 2209 + }, + { + "epoch": 0.23, + "learning_rate": 1.8960110126525627e-05, + "loss": 1.4952, + "step": 2210 + }, + { + "epoch": 0.23, + "learning_rate": 1.895848425880673e-05, + "loss": 1.5299, + "step": 2211 + }, + { + "epoch": 0.23, + "learning_rate": 1.8956857190881125e-05, + "loss": 1.5274, + "step": 2212 + }, + { + "epoch": 0.23, + "learning_rate": 1.8955228922966792e-05, + "loss": 1.4415, + "step": 2213 + }, + { + "epoch": 0.23, + "learning_rate": 1.8953599455281884e-05, + "loss": 1.5311, + "step": 2214 + }, + { + "epoch": 0.23, + "learning_rate": 1.8951968788044702e-05, + "loss": 1.4972, + "step": 2215 + }, + { + "epoch": 0.23, + "learning_rate": 1.8950336921473715e-05, + "loss": 1.4966, + "step": 2216 + }, + { + "epoch": 0.23, + "learning_rate": 1.8948703855787553e-05, + "loss": 1.4683, + "step": 2217 + }, + { + "epoch": 0.23, + "learning_rate": 1.8947069591205005e-05, + "loss": 1.503, + "step": 2218 + }, + { + "epoch": 0.23, + "learning_rate": 1.8945434127945014e-05, + "loss": 1.4902, + "step": 2219 + }, + { + "epoch": 0.23, + "learning_rate": 1.8943797466226702e-05, + "loss": 1.4835, + "step": 2220 + }, + { + "epoch": 0.23, + "learning_rate": 1.8942159606269332e-05, + "loss": 1.535, + "step": 2221 + }, + { + "epoch": 0.23, + "learning_rate": 1.8940520548292332e-05, + "loss": 1.491, + "step": 2222 + }, + { + "epoch": 0.23, + "learning_rate": 1.89388802925153e-05, + "loss": 1.5157, + "step": 2223 + }, + { + "epoch": 0.23, + "learning_rate": 1.8937238839157987e-05, + "loss": 1.4779, + "step": 2224 + }, + { + "epoch": 0.23, + "learning_rate": 1.8935596188440302e-05, + "loss": 1.4902, + "step": 2225 + }, + { + "epoch": 0.23, + "learning_rate": 1.8933952340582323e-05, + "loss": 1.4988, + "step": 2226 + }, + { + "epoch": 0.23, + "learning_rate": 1.893230729580428e-05, + "loss": 1.4568, + "step": 2227 + }, + { + "epoch": 0.23, + "learning_rate": 1.8930661054326567e-05, + "loss": 1.5163, + "step": 2228 + }, + { + "epoch": 0.23, + "learning_rate": 1.892901361636974e-05, + "loss": 1.4472, + "step": 2229 + }, + { + "epoch": 0.23, + "learning_rate": 1.892736498215451e-05, + "loss": 1.4658, + "step": 2230 + }, + { + "epoch": 0.23, + "learning_rate": 1.8925715151901754e-05, + "loss": 1.4281, + "step": 2231 + }, + { + "epoch": 0.23, + "learning_rate": 1.892406412583251e-05, + "loss": 1.415, + "step": 2232 + }, + { + "epoch": 0.23, + "learning_rate": 1.8922411904167966e-05, + "loss": 1.464, + "step": 2233 + }, + { + "epoch": 0.23, + "learning_rate": 1.892075848712948e-05, + "loss": 1.5014, + "step": 2234 + }, + { + "epoch": 0.23, + "learning_rate": 1.8919103874938568e-05, + "loss": 1.4397, + "step": 2235 + }, + { + "epoch": 0.23, + "learning_rate": 1.891744806781691e-05, + "loss": 1.5508, + "step": 2236 + }, + { + "epoch": 0.23, + "learning_rate": 1.8915791065986335e-05, + "loss": 1.4749, + "step": 2237 + }, + { + "epoch": 0.23, + "learning_rate": 1.891413286966884e-05, + "loss": 1.4538, + "step": 2238 + }, + { + "epoch": 0.23, + "learning_rate": 1.891247347908658e-05, + "loss": 1.4405, + "step": 2239 + }, + { + "epoch": 0.23, + "learning_rate": 1.8910812894461878e-05, + "loss": 1.3562, + "step": 2240 + }, + { + "epoch": 0.24, + "learning_rate": 1.89091511160172e-05, + "loss": 1.4811, + "step": 2241 + }, + { + "epoch": 0.24, + "learning_rate": 1.8907488143975186e-05, + "loss": 1.4286, + "step": 2242 + }, + { + "epoch": 0.24, + "learning_rate": 1.890582397855863e-05, + "loss": 1.4493, + "step": 2243 + }, + { + "epoch": 0.24, + "learning_rate": 1.890415861999049e-05, + "loss": 1.5639, + "step": 2244 + }, + { + "epoch": 0.24, + "learning_rate": 1.890249206849388e-05, + "loss": 1.6375, + "step": 2245 + }, + { + "epoch": 0.24, + "learning_rate": 1.890082432429208e-05, + "loss": 1.4982, + "step": 2246 + }, + { + "epoch": 0.24, + "learning_rate": 1.889915538760851e-05, + "loss": 1.492, + "step": 2247 + }, + { + "epoch": 0.24, + "learning_rate": 1.8897485258666778e-05, + "loss": 1.4294, + "step": 2248 + }, + { + "epoch": 0.24, + "learning_rate": 1.8895813937690638e-05, + "loss": 1.4617, + "step": 2249 + }, + { + "epoch": 0.24, + "learning_rate": 1.8894141424904e-05, + "loss": 1.4763, + "step": 2250 + }, + { + "epoch": 0.24, + "learning_rate": 1.8892467720530937e-05, + "loss": 1.3989, + "step": 2251 + }, + { + "epoch": 0.24, + "learning_rate": 1.8890792824795687e-05, + "loss": 1.4803, + "step": 2252 + }, + { + "epoch": 0.24, + "learning_rate": 1.8889116737922638e-05, + "loss": 1.4734, + "step": 2253 + }, + { + "epoch": 0.24, + "learning_rate": 1.8887439460136342e-05, + "loss": 1.5069, + "step": 2254 + }, + { + "epoch": 0.24, + "learning_rate": 1.8885760991661514e-05, + "loss": 1.5565, + "step": 2255 + }, + { + "epoch": 0.24, + "learning_rate": 1.8884081332723028e-05, + "loss": 1.4707, + "step": 2256 + }, + { + "epoch": 0.24, + "learning_rate": 1.8882400483545913e-05, + "loss": 1.5077, + "step": 2257 + }, + { + "epoch": 0.24, + "learning_rate": 1.888071844435536e-05, + "loss": 1.5075, + "step": 2258 + }, + { + "epoch": 0.24, + "learning_rate": 1.8879035215376717e-05, + "loss": 1.5185, + "step": 2259 + }, + { + "epoch": 0.24, + "learning_rate": 1.887735079683549e-05, + "loss": 1.6266, + "step": 2260 + }, + { + "epoch": 0.24, + "learning_rate": 1.8875665188957354e-05, + "loss": 1.5013, + "step": 2261 + }, + { + "epoch": 0.24, + "learning_rate": 1.887397839196814e-05, + "loss": 1.4362, + "step": 2262 + }, + { + "epoch": 0.24, + "learning_rate": 1.8872290406093827e-05, + "loss": 1.4718, + "step": 2263 + }, + { + "epoch": 0.24, + "learning_rate": 1.8870601231560567e-05, + "loss": 1.5202, + "step": 2264 + }, + { + "epoch": 0.24, + "learning_rate": 1.8868910868594664e-05, + "loss": 1.5168, + "step": 2265 + }, + { + "epoch": 0.24, + "learning_rate": 1.8867219317422588e-05, + "loss": 1.5142, + "step": 2266 + }, + { + "epoch": 0.24, + "learning_rate": 1.8865526578270954e-05, + "loss": 1.4885, + "step": 2267 + }, + { + "epoch": 0.24, + "learning_rate": 1.8863832651366552e-05, + "loss": 1.5441, + "step": 2268 + }, + { + "epoch": 0.24, + "learning_rate": 1.8862137536936328e-05, + "loss": 1.4647, + "step": 2269 + }, + { + "epoch": 0.24, + "learning_rate": 1.8860441235207374e-05, + "loss": 1.5352, + "step": 2270 + }, + { + "epoch": 0.24, + "learning_rate": 1.8858743746406958e-05, + "loss": 1.4568, + "step": 2271 + }, + { + "epoch": 0.24, + "learning_rate": 1.8857045070762497e-05, + "loss": 1.4865, + "step": 2272 + }, + { + "epoch": 0.24, + "learning_rate": 1.8855345208501573e-05, + "loss": 1.4637, + "step": 2273 + }, + { + "epoch": 0.24, + "learning_rate": 1.8853644159851918e-05, + "loss": 1.4348, + "step": 2274 + }, + { + "epoch": 0.24, + "learning_rate": 1.8851941925041436e-05, + "loss": 1.4413, + "step": 2275 + }, + { + "epoch": 0.24, + "learning_rate": 1.8850238504298177e-05, + "loss": 1.4434, + "step": 2276 + }, + { + "epoch": 0.24, + "learning_rate": 1.884853389785036e-05, + "loss": 1.4822, + "step": 2277 + }, + { + "epoch": 0.24, + "learning_rate": 1.8846828105926356e-05, + "loss": 1.4632, + "step": 2278 + }, + { + "epoch": 0.24, + "learning_rate": 1.8845121128754698e-05, + "loss": 1.48, + "step": 2279 + }, + { + "epoch": 0.24, + "learning_rate": 1.8843412966564078e-05, + "loss": 1.4518, + "step": 2280 + }, + { + "epoch": 0.24, + "learning_rate": 1.884170361958334e-05, + "loss": 1.4334, + "step": 2281 + }, + { + "epoch": 0.24, + "learning_rate": 1.8839993088041502e-05, + "loss": 1.5131, + "step": 2282 + }, + { + "epoch": 0.24, + "learning_rate": 1.8838281372167724e-05, + "loss": 1.508, + "step": 2283 + }, + { + "epoch": 0.24, + "learning_rate": 1.8836568472191335e-05, + "loss": 1.4086, + "step": 2284 + }, + { + "epoch": 0.24, + "learning_rate": 1.883485438834182e-05, + "loss": 1.5021, + "step": 2285 + }, + { + "epoch": 0.24, + "learning_rate": 1.8833139120848817e-05, + "loss": 1.5083, + "step": 2286 + }, + { + "epoch": 0.24, + "learning_rate": 1.8831422669942137e-05, + "loss": 1.4162, + "step": 2287 + }, + { + "epoch": 0.24, + "learning_rate": 1.8829705035851734e-05, + "loss": 1.5494, + "step": 2288 + }, + { + "epoch": 0.24, + "learning_rate": 1.8827986218807724e-05, + "loss": 1.425, + "step": 2289 + }, + { + "epoch": 0.24, + "learning_rate": 1.8826266219040396e-05, + "loss": 1.5215, + "step": 2290 + }, + { + "epoch": 0.24, + "learning_rate": 1.8824545036780172e-05, + "loss": 1.5577, + "step": 2291 + }, + { + "epoch": 0.24, + "learning_rate": 1.8822822672257655e-05, + "loss": 1.4923, + "step": 2292 + }, + { + "epoch": 0.24, + "learning_rate": 1.8821099125703595e-05, + "loss": 1.4648, + "step": 2293 + }, + { + "epoch": 0.24, + "learning_rate": 1.8819374397348902e-05, + "loss": 1.471, + "step": 2294 + }, + { + "epoch": 0.24, + "learning_rate": 1.8817648487424648e-05, + "loss": 1.5658, + "step": 2295 + }, + { + "epoch": 0.24, + "learning_rate": 1.8815921396162058e-05, + "loss": 1.5348, + "step": 2296 + }, + { + "epoch": 0.24, + "learning_rate": 1.8814193123792518e-05, + "loss": 1.4081, + "step": 2297 + }, + { + "epoch": 0.24, + "learning_rate": 1.881246367054757e-05, + "loss": 1.4762, + "step": 2298 + }, + { + "epoch": 0.24, + "learning_rate": 1.8810733036658925e-05, + "loss": 1.4399, + "step": 2299 + }, + { + "epoch": 0.24, + "learning_rate": 1.8809001222358432e-05, + "loss": 1.4763, + "step": 2300 + }, + { + "epoch": 0.24, + "learning_rate": 1.880726822787812e-05, + "loss": 1.4874, + "step": 2301 + }, + { + "epoch": 0.24, + "learning_rate": 1.880553405345016e-05, + "loss": 1.4951, + "step": 2302 + }, + { + "epoch": 0.24, + "learning_rate": 1.8803798699306887e-05, + "loss": 1.4697, + "step": 2303 + }, + { + "epoch": 0.24, + "learning_rate": 1.880206216568079e-05, + "loss": 1.481, + "step": 2304 + }, + { + "epoch": 0.24, + "learning_rate": 1.880032445280453e-05, + "loss": 1.4485, + "step": 2305 + }, + { + "epoch": 0.24, + "learning_rate": 1.879858556091091e-05, + "loss": 1.4749, + "step": 2306 + }, + { + "epoch": 0.24, + "learning_rate": 1.8796845490232894e-05, + "loss": 1.5605, + "step": 2307 + }, + { + "epoch": 0.24, + "learning_rate": 1.879510424100361e-05, + "loss": 1.4835, + "step": 2308 + }, + { + "epoch": 0.24, + "learning_rate": 1.8793361813456346e-05, + "loss": 1.4344, + "step": 2309 + }, + { + "epoch": 0.24, + "learning_rate": 1.8791618207824532e-05, + "loss": 1.4571, + "step": 2310 + }, + { + "epoch": 0.24, + "learning_rate": 1.8789873424341772e-05, + "loss": 1.482, + "step": 2311 + }, + { + "epoch": 0.24, + "learning_rate": 1.8788127463241822e-05, + "loss": 1.4736, + "step": 2312 + }, + { + "epoch": 0.24, + "learning_rate": 1.8786380324758597e-05, + "loss": 1.4807, + "step": 2313 + }, + { + "epoch": 0.24, + "learning_rate": 1.8784632009126167e-05, + "loss": 1.4418, + "step": 2314 + }, + { + "epoch": 0.24, + "learning_rate": 1.878288251657876e-05, + "loss": 1.5248, + "step": 2315 + }, + { + "epoch": 0.24, + "learning_rate": 1.8781131847350768e-05, + "loss": 1.483, + "step": 2316 + }, + { + "epoch": 0.24, + "learning_rate": 1.877938000167673e-05, + "loss": 1.5474, + "step": 2317 + }, + { + "epoch": 0.24, + "learning_rate": 1.8777626979791347e-05, + "loss": 1.4671, + "step": 2318 + }, + { + "epoch": 0.24, + "learning_rate": 1.877587278192949e-05, + "loss": 1.3049, + "step": 2319 + }, + { + "epoch": 0.24, + "learning_rate": 1.877411740832616e-05, + "loss": 1.483, + "step": 2320 + }, + { + "epoch": 0.24, + "learning_rate": 1.877236085921655e-05, + "loss": 1.508, + "step": 2321 + }, + { + "epoch": 0.24, + "learning_rate": 1.8770603134835978e-05, + "loss": 1.4854, + "step": 2322 + }, + { + "epoch": 0.24, + "learning_rate": 1.8768844235419942e-05, + "loss": 1.4808, + "step": 2323 + }, + { + "epoch": 0.24, + "learning_rate": 1.8767084161204087e-05, + "loss": 1.5352, + "step": 2324 + }, + { + "epoch": 0.24, + "learning_rate": 1.8765322912424214e-05, + "loss": 1.5628, + "step": 2325 + }, + { + "epoch": 0.24, + "learning_rate": 1.8763560489316292e-05, + "loss": 1.494, + "step": 2326 + }, + { + "epoch": 0.24, + "learning_rate": 1.876179689211643e-05, + "loss": 1.509, + "step": 2327 + }, + { + "epoch": 0.24, + "learning_rate": 1.8760032121060918e-05, + "loss": 1.5021, + "step": 2328 + }, + { + "epoch": 0.24, + "learning_rate": 1.875826617638618e-05, + "loss": 1.4179, + "step": 2329 + }, + { + "epoch": 0.24, + "learning_rate": 1.8756499058328813e-05, + "loss": 1.4302, + "step": 2330 + }, + { + "epoch": 0.24, + "learning_rate": 1.8754730767125564e-05, + "loss": 1.4959, + "step": 2331 + }, + { + "epoch": 0.24, + "learning_rate": 1.8752961303013336e-05, + "loss": 1.4423, + "step": 2332 + }, + { + "epoch": 0.24, + "learning_rate": 1.8751190666229194e-05, + "loss": 1.4564, + "step": 2333 + }, + { + "epoch": 0.24, + "learning_rate": 1.8749418857010358e-05, + "loss": 1.4775, + "step": 2334 + }, + { + "epoch": 0.24, + "learning_rate": 1.8747645875594203e-05, + "loss": 1.4182, + "step": 2335 + }, + { + "epoch": 0.24, + "learning_rate": 1.8745871722218265e-05, + "loss": 1.3957, + "step": 2336 + }, + { + "epoch": 0.25, + "learning_rate": 1.8744096397120235e-05, + "loss": 1.4633, + "step": 2337 + }, + { + "epoch": 0.25, + "learning_rate": 1.874231990053796e-05, + "loss": 1.5512, + "step": 2338 + }, + { + "epoch": 0.25, + "learning_rate": 1.8740542232709444e-05, + "loss": 1.3461, + "step": 2339 + }, + { + "epoch": 0.25, + "learning_rate": 1.8738763393872848e-05, + "loss": 1.4754, + "step": 2340 + }, + { + "epoch": 0.25, + "learning_rate": 1.8736983384266495e-05, + "loss": 1.5448, + "step": 2341 + }, + { + "epoch": 0.25, + "learning_rate": 1.8735202204128854e-05, + "loss": 1.4491, + "step": 2342 + }, + { + "epoch": 0.25, + "learning_rate": 1.8733419853698566e-05, + "loss": 1.457, + "step": 2343 + }, + { + "epoch": 0.25, + "learning_rate": 1.8731636333214414e-05, + "loss": 1.4314, + "step": 2344 + }, + { + "epoch": 0.25, + "learning_rate": 1.8729851642915345e-05, + "loss": 1.3979, + "step": 2345 + }, + { + "epoch": 0.25, + "learning_rate": 1.8728065783040464e-05, + "loss": 1.4146, + "step": 2346 + }, + { + "epoch": 0.25, + "learning_rate": 1.8726278753829027e-05, + "loss": 1.4361, + "step": 2347 + }, + { + "epoch": 0.25, + "learning_rate": 1.872449055552045e-05, + "loss": 1.4989, + "step": 2348 + }, + { + "epoch": 0.25, + "learning_rate": 1.872270118835431e-05, + "loss": 1.5062, + "step": 2349 + }, + { + "epoch": 0.25, + "learning_rate": 1.872091065257033e-05, + "loss": 1.4509, + "step": 2350 + }, + { + "epoch": 0.25, + "learning_rate": 1.8719118948408403e-05, + "loss": 1.4631, + "step": 2351 + }, + { + "epoch": 0.25, + "learning_rate": 1.8717326076108566e-05, + "loss": 1.5119, + "step": 2352 + }, + { + "epoch": 0.25, + "learning_rate": 1.8715532035911017e-05, + "loss": 1.6347, + "step": 2353 + }, + { + "epoch": 0.25, + "learning_rate": 1.8713736828056115e-05, + "loss": 1.5526, + "step": 2354 + }, + { + "epoch": 0.25, + "learning_rate": 1.8711940452784368e-05, + "loss": 1.6348, + "step": 2355 + }, + { + "epoch": 0.25, + "learning_rate": 1.871014291033645e-05, + "loss": 1.5183, + "step": 2356 + }, + { + "epoch": 0.25, + "learning_rate": 1.8708344200953182e-05, + "loss": 1.458, + "step": 2357 + }, + { + "epoch": 0.25, + "learning_rate": 1.8706544324875545e-05, + "loss": 1.524, + "step": 2358 + }, + { + "epoch": 0.25, + "learning_rate": 1.8704743282344672e-05, + "loss": 1.4479, + "step": 2359 + }, + { + "epoch": 0.25, + "learning_rate": 1.870294107360186e-05, + "loss": 1.5408, + "step": 2360 + }, + { + "epoch": 0.25, + "learning_rate": 1.8701137698888563e-05, + "loss": 1.5007, + "step": 2361 + }, + { + "epoch": 0.25, + "learning_rate": 1.8699333158446382e-05, + "loss": 1.5132, + "step": 2362 + }, + { + "epoch": 0.25, + "learning_rate": 1.869752745251708e-05, + "loss": 1.4263, + "step": 2363 + }, + { + "epoch": 0.25, + "learning_rate": 1.8695720581342574e-05, + "loss": 1.422, + "step": 2364 + }, + { + "epoch": 0.25, + "learning_rate": 1.869391254516494e-05, + "loss": 1.4411, + "step": 2365 + }, + { + "epoch": 0.25, + "learning_rate": 1.8692103344226406e-05, + "loss": 1.4594, + "step": 2366 + }, + { + "epoch": 0.25, + "learning_rate": 1.8690292978769364e-05, + "loss": 1.4992, + "step": 2367 + }, + { + "epoch": 0.25, + "learning_rate": 1.868848144903635e-05, + "loss": 1.4822, + "step": 2368 + }, + { + "epoch": 0.25, + "learning_rate": 1.8686668755270064e-05, + "loss": 1.5402, + "step": 2369 + }, + { + "epoch": 0.25, + "learning_rate": 1.8684854897713363e-05, + "loss": 1.5268, + "step": 2370 + }, + { + "epoch": 0.25, + "learning_rate": 1.8683039876609258e-05, + "loss": 1.5587, + "step": 2371 + }, + { + "epoch": 0.25, + "learning_rate": 1.868122369220091e-05, + "loss": 1.4214, + "step": 2372 + }, + { + "epoch": 0.25, + "learning_rate": 1.8679406344731645e-05, + "loss": 1.5089, + "step": 2373 + }, + { + "epoch": 0.25, + "learning_rate": 1.867758783444494e-05, + "loss": 1.5067, + "step": 2374 + }, + { + "epoch": 0.25, + "learning_rate": 1.8675768161584427e-05, + "loss": 2.0616, + "step": 2375 + }, + { + "epoch": 0.25, + "learning_rate": 1.8673947326393903e-05, + "loss": 1.5617, + "step": 2376 + }, + { + "epoch": 0.25, + "learning_rate": 1.86721253291173e-05, + "loss": 1.4422, + "step": 2377 + }, + { + "epoch": 0.25, + "learning_rate": 1.867030216999873e-05, + "loss": 1.4727, + "step": 2378 + }, + { + "epoch": 0.25, + "learning_rate": 1.8668477849282443e-05, + "loss": 1.4152, + "step": 2379 + }, + { + "epoch": 0.25, + "learning_rate": 1.8666652367212856e-05, + "loss": 1.4376, + "step": 2380 + }, + { + "epoch": 0.25, + "learning_rate": 1.8664825724034534e-05, + "loss": 1.393, + "step": 2381 + }, + { + "epoch": 0.25, + "learning_rate": 1.8662997919992197e-05, + "loss": 1.4864, + "step": 2382 + }, + { + "epoch": 0.25, + "learning_rate": 1.866116895533073e-05, + "loss": 1.4261, + "step": 2383 + }, + { + "epoch": 0.25, + "learning_rate": 1.8659338830295163e-05, + "loss": 1.4555, + "step": 2384 + }, + { + "epoch": 0.25, + "learning_rate": 1.8657507545130687e-05, + "loss": 1.4939, + "step": 2385 + }, + { + "epoch": 0.25, + "learning_rate": 1.865567510008265e-05, + "loss": 1.4123, + "step": 2386 + }, + { + "epoch": 0.25, + "learning_rate": 1.8653841495396546e-05, + "loss": 1.4459, + "step": 2387 + }, + { + "epoch": 0.25, + "learning_rate": 1.8652006731318038e-05, + "loss": 1.396, + "step": 2388 + }, + { + "epoch": 0.25, + "eval_loss": 1.5139706134796143, + "eval_runtime": 77.2904, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 2388 + }, + { + "epoch": 0.25, + "learning_rate": 1.8650170808092936e-05, + "loss": 1.4666, + "step": 2389 + }, + { + "epoch": 0.25, + "learning_rate": 1.86483337259672e-05, + "loss": 1.5154, + "step": 2390 + }, + { + "epoch": 0.25, + "learning_rate": 1.864649548518696e-05, + "loss": 1.5163, + "step": 2391 + }, + { + "epoch": 0.25, + "learning_rate": 1.864465608599849e-05, + "loss": 1.4734, + "step": 2392 + }, + { + "epoch": 0.25, + "learning_rate": 1.864281552864822e-05, + "loss": 1.5217, + "step": 2393 + }, + { + "epoch": 0.25, + "learning_rate": 1.8640973813382737e-05, + "loss": 1.4694, + "step": 2394 + }, + { + "epoch": 0.25, + "learning_rate": 1.863913094044879e-05, + "loss": 1.4761, + "step": 2395 + }, + { + "epoch": 0.25, + "learning_rate": 1.863728691009327e-05, + "loss": 1.4766, + "step": 2396 + }, + { + "epoch": 0.25, + "learning_rate": 1.863544172256323e-05, + "loss": 1.5695, + "step": 2397 + }, + { + "epoch": 0.25, + "learning_rate": 1.8633595378105882e-05, + "loss": 1.5079, + "step": 2398 + }, + { + "epoch": 0.25, + "learning_rate": 1.8631747876968584e-05, + "loss": 1.4154, + "step": 2399 + }, + { + "epoch": 0.25, + "learning_rate": 1.862989921939886e-05, + "loss": 1.4488, + "step": 2400 + }, + { + "epoch": 0.25, + "learning_rate": 1.8628049405644376e-05, + "loss": 1.4279, + "step": 2401 + }, + { + "epoch": 0.25, + "learning_rate": 1.8626198435952966e-05, + "loss": 1.4896, + "step": 2402 + }, + { + "epoch": 0.25, + "learning_rate": 1.8624346310572602e-05, + "loss": 1.4315, + "step": 2403 + }, + { + "epoch": 0.25, + "learning_rate": 1.862249302975143e-05, + "loss": 1.4919, + "step": 2404 + }, + { + "epoch": 0.25, + "learning_rate": 1.8620638593737743e-05, + "loss": 1.4561, + "step": 2405 + }, + { + "epoch": 0.25, + "learning_rate": 1.8618783002779985e-05, + "loss": 1.4622, + "step": 2406 + }, + { + "epoch": 0.25, + "learning_rate": 1.8616926257126754e-05, + "loss": 1.4917, + "step": 2407 + }, + { + "epoch": 0.25, + "learning_rate": 1.861506835702681e-05, + "loss": 1.4962, + "step": 2408 + }, + { + "epoch": 0.25, + "learning_rate": 1.861320930272906e-05, + "loss": 1.4164, + "step": 2409 + }, + { + "epoch": 0.25, + "learning_rate": 1.8611349094482578e-05, + "loss": 1.4889, + "step": 2410 + }, + { + "epoch": 0.25, + "learning_rate": 1.8609487732536576e-05, + "loss": 1.543, + "step": 2411 + }, + { + "epoch": 0.25, + "learning_rate": 1.8607625217140433e-05, + "loss": 1.5417, + "step": 2412 + }, + { + "epoch": 0.25, + "learning_rate": 1.8605761548543674e-05, + "loss": 1.5304, + "step": 2413 + }, + { + "epoch": 0.25, + "learning_rate": 1.860389672699599e-05, + "loss": 1.4725, + "step": 2414 + }, + { + "epoch": 0.25, + "learning_rate": 1.860203075274721e-05, + "loss": 1.4745, + "step": 2415 + }, + { + "epoch": 0.25, + "learning_rate": 1.8600163626047334e-05, + "loss": 1.4656, + "step": 2416 + }, + { + "epoch": 0.25, + "learning_rate": 1.8598295347146503e-05, + "loss": 1.5287, + "step": 2417 + }, + { + "epoch": 0.25, + "learning_rate": 1.8596425916295023e-05, + "loss": 1.5024, + "step": 2418 + }, + { + "epoch": 0.25, + "learning_rate": 1.8594555333743348e-05, + "loss": 1.4527, + "step": 2419 + }, + { + "epoch": 0.25, + "learning_rate": 1.859268359974209e-05, + "loss": 1.4897, + "step": 2420 + }, + { + "epoch": 0.25, + "learning_rate": 1.859081071454201e-05, + "loss": 1.3554, + "step": 2421 + }, + { + "epoch": 0.25, + "learning_rate": 1.858893667839403e-05, + "loss": 1.4004, + "step": 2422 + }, + { + "epoch": 0.25, + "learning_rate": 1.858706149154922e-05, + "loss": 1.5582, + "step": 2423 + }, + { + "epoch": 0.25, + "learning_rate": 1.8585185154258803e-05, + "loss": 1.505, + "step": 2424 + }, + { + "epoch": 0.25, + "learning_rate": 1.858330766677417e-05, + "loss": 1.5043, + "step": 2425 + }, + { + "epoch": 0.25, + "learning_rate": 1.858142902934685e-05, + "loss": 1.439, + "step": 2426 + }, + { + "epoch": 0.25, + "learning_rate": 1.857954924222853e-05, + "loss": 1.4927, + "step": 2427 + }, + { + "epoch": 0.25, + "learning_rate": 1.8577668305671056e-05, + "loss": 1.5395, + "step": 2428 + }, + { + "epoch": 0.25, + "learning_rate": 1.8575786219926427e-05, + "loss": 1.4737, + "step": 2429 + }, + { + "epoch": 0.25, + "learning_rate": 1.8573902985246794e-05, + "loss": 1.6151, + "step": 2430 + }, + { + "epoch": 0.25, + "learning_rate": 1.857201860188446e-05, + "loss": 1.4313, + "step": 2431 + }, + { + "epoch": 0.26, + "learning_rate": 1.857013307009188e-05, + "loss": 1.4509, + "step": 2432 + }, + { + "epoch": 0.26, + "learning_rate": 1.8568246390121673e-05, + "loss": 1.3998, + "step": 2433 + }, + { + "epoch": 0.26, + "learning_rate": 1.8566358562226603e-05, + "loss": 1.5268, + "step": 2434 + }, + { + "epoch": 0.26, + "learning_rate": 1.8564469586659593e-05, + "loss": 1.4369, + "step": 2435 + }, + { + "epoch": 0.26, + "learning_rate": 1.8562579463673713e-05, + "loss": 1.4759, + "step": 2436 + }, + { + "epoch": 0.26, + "learning_rate": 1.8560688193522197e-05, + "loss": 1.4092, + "step": 2437 + }, + { + "epoch": 0.26, + "learning_rate": 1.855879577645842e-05, + "loss": 1.43, + "step": 2438 + }, + { + "epoch": 0.26, + "learning_rate": 1.855690221273592e-05, + "loss": 1.5143, + "step": 2439 + }, + { + "epoch": 0.26, + "learning_rate": 1.8555007502608385e-05, + "loss": 1.5482, + "step": 2440 + }, + { + "epoch": 0.26, + "learning_rate": 1.855311164632966e-05, + "loss": 1.4406, + "step": 2441 + }, + { + "epoch": 0.26, + "learning_rate": 1.8551214644153738e-05, + "loss": 1.4551, + "step": 2442 + }, + { + "epoch": 0.26, + "learning_rate": 1.8549316496334774e-05, + "loss": 1.4663, + "step": 2443 + }, + { + "epoch": 0.26, + "learning_rate": 1.8547417203127064e-05, + "loss": 1.4732, + "step": 2444 + }, + { + "epoch": 0.26, + "learning_rate": 1.8545516764785067e-05, + "loss": 1.5378, + "step": 2445 + }, + { + "epoch": 0.26, + "learning_rate": 1.8543615181563397e-05, + "loss": 1.4448, + "step": 2446 + }, + { + "epoch": 0.26, + "learning_rate": 1.854171245371681e-05, + "loss": 1.2861, + "step": 2447 + }, + { + "epoch": 0.26, + "learning_rate": 1.8539808581500228e-05, + "loss": 1.4405, + "step": 2448 + }, + { + "epoch": 0.26, + "learning_rate": 1.8537903565168716e-05, + "loss": 1.4876, + "step": 2449 + }, + { + "epoch": 0.26, + "learning_rate": 1.8535997404977506e-05, + "loss": 1.4119, + "step": 2450 + }, + { + "epoch": 0.26, + "learning_rate": 1.8534090101181967e-05, + "loss": 1.4451, + "step": 2451 + }, + { + "epoch": 0.26, + "learning_rate": 1.8532181654037632e-05, + "loss": 1.4035, + "step": 2452 + }, + { + "epoch": 0.26, + "learning_rate": 1.853027206380018e-05, + "loss": 1.4624, + "step": 2453 + }, + { + "epoch": 0.26, + "learning_rate": 1.852836133072545e-05, + "loss": 1.4935, + "step": 2454 + }, + { + "epoch": 0.26, + "learning_rate": 1.8526449455069434e-05, + "loss": 1.4834, + "step": 2455 + }, + { + "epoch": 0.26, + "learning_rate": 1.8524536437088266e-05, + "loss": 1.498, + "step": 2456 + }, + { + "epoch": 0.26, + "learning_rate": 1.8522622277038247e-05, + "loss": 1.3417, + "step": 2457 + }, + { + "epoch": 0.26, + "learning_rate": 1.852070697517583e-05, + "loss": 1.4455, + "step": 2458 + }, + { + "epoch": 0.26, + "learning_rate": 1.8518790531757607e-05, + "loss": 1.4119, + "step": 2459 + }, + { + "epoch": 0.26, + "learning_rate": 1.8516872947040337e-05, + "loss": 1.558, + "step": 2460 + }, + { + "epoch": 0.26, + "learning_rate": 1.8514954221280926e-05, + "loss": 1.4862, + "step": 2461 + }, + { + "epoch": 0.26, + "learning_rate": 1.8513034354736433e-05, + "loss": 1.6806, + "step": 2462 + }, + { + "epoch": 0.26, + "learning_rate": 1.8511113347664072e-05, + "loss": 1.438, + "step": 2463 + }, + { + "epoch": 0.26, + "learning_rate": 1.850919120032121e-05, + "loss": 1.4975, + "step": 2464 + }, + { + "epoch": 0.26, + "learning_rate": 1.850726791296536e-05, + "loss": 1.4409, + "step": 2465 + }, + { + "epoch": 0.26, + "learning_rate": 1.85053434858542e-05, + "loss": 1.4769, + "step": 2466 + }, + { + "epoch": 0.26, + "learning_rate": 1.8503417919245548e-05, + "loss": 1.5823, + "step": 2467 + }, + { + "epoch": 0.26, + "learning_rate": 1.8501491213397386e-05, + "loss": 1.4045, + "step": 2468 + }, + { + "epoch": 0.26, + "learning_rate": 1.8499563368567837e-05, + "loss": 1.4828, + "step": 2469 + }, + { + "epoch": 0.26, + "learning_rate": 1.849763438501519e-05, + "loss": 1.4684, + "step": 2470 + }, + { + "epoch": 0.26, + "learning_rate": 1.8495704262997873e-05, + "loss": 1.4577, + "step": 2471 + }, + { + "epoch": 0.26, + "learning_rate": 1.8493773002774475e-05, + "loss": 1.4759, + "step": 2472 + }, + { + "epoch": 0.26, + "learning_rate": 1.8491840604603736e-05, + "loss": 1.4259, + "step": 2473 + }, + { + "epoch": 0.26, + "learning_rate": 1.8489907068744543e-05, + "loss": 1.4717, + "step": 2474 + }, + { + "epoch": 0.26, + "learning_rate": 1.848797239545595e-05, + "loss": 1.4247, + "step": 2475 + }, + { + "epoch": 0.26, + "learning_rate": 1.8486036584997143e-05, + "loss": 1.4954, + "step": 2476 + }, + { + "epoch": 0.26, + "learning_rate": 1.8484099637627472e-05, + "loss": 1.4926, + "step": 2477 + }, + { + "epoch": 0.26, + "learning_rate": 1.8482161553606447e-05, + "loss": 1.487, + "step": 2478 + }, + { + "epoch": 0.26, + "learning_rate": 1.8480222333193715e-05, + "loss": 1.4553, + "step": 2479 + }, + { + "epoch": 0.26, + "learning_rate": 1.847828197664908e-05, + "loss": 1.4862, + "step": 2480 + }, + { + "epoch": 0.26, + "learning_rate": 1.8476340484232508e-05, + "loss": 1.4867, + "step": 2481 + }, + { + "epoch": 0.26, + "learning_rate": 1.8474397856204097e-05, + "loss": 1.4736, + "step": 2482 + }, + { + "epoch": 0.26, + "learning_rate": 1.8472454092824122e-05, + "loss": 1.4254, + "step": 2483 + }, + { + "epoch": 0.26, + "learning_rate": 1.8470509194352987e-05, + "loss": 1.4455, + "step": 2484 + }, + { + "epoch": 0.26, + "learning_rate": 1.8468563161051263e-05, + "loss": 1.4402, + "step": 2485 + }, + { + "epoch": 0.26, + "learning_rate": 1.846661599317967e-05, + "loss": 1.4611, + "step": 2486 + }, + { + "epoch": 0.26, + "learning_rate": 1.8464667690999073e-05, + "loss": 1.4814, + "step": 2487 + }, + { + "epoch": 0.26, + "learning_rate": 1.8462718254770503e-05, + "loss": 1.4559, + "step": 2488 + }, + { + "epoch": 0.26, + "learning_rate": 1.8460767684755127e-05, + "loss": 1.4667, + "step": 2489 + }, + { + "epoch": 0.26, + "learning_rate": 1.8458815981214274e-05, + "loss": 1.4427, + "step": 2490 + }, + { + "epoch": 0.26, + "learning_rate": 1.845686314440942e-05, + "loss": 1.4055, + "step": 2491 + }, + { + "epoch": 0.26, + "learning_rate": 1.8454909174602198e-05, + "loss": 1.5563, + "step": 2492 + }, + { + "epoch": 0.26, + "learning_rate": 1.845295407205439e-05, + "loss": 1.4631, + "step": 2493 + }, + { + "epoch": 0.26, + "learning_rate": 1.8450997837027925e-05, + "loss": 1.4887, + "step": 2494 + }, + { + "epoch": 0.26, + "learning_rate": 1.8449040469784895e-05, + "loss": 1.5212, + "step": 2495 + }, + { + "epoch": 0.26, + "learning_rate": 1.844708197058753e-05, + "loss": 1.5582, + "step": 2496 + }, + { + "epoch": 0.26, + "learning_rate": 1.844512233969822e-05, + "loss": 1.4599, + "step": 2497 + }, + { + "epoch": 0.26, + "learning_rate": 1.844316157737951e-05, + "loss": 1.4546, + "step": 2498 + }, + { + "epoch": 0.26, + "learning_rate": 1.844119968389409e-05, + "loss": 1.4631, + "step": 2499 + }, + { + "epoch": 0.26, + "learning_rate": 1.84392366595048e-05, + "loss": 1.4817, + "step": 2500 + }, + { + "epoch": 0.26, + "learning_rate": 1.8437272504474636e-05, + "loss": 1.4214, + "step": 2501 + }, + { + "epoch": 0.26, + "learning_rate": 1.8435307219066744e-05, + "loss": 1.471, + "step": 2502 + }, + { + "epoch": 0.26, + "learning_rate": 1.8433340803544424e-05, + "loss": 1.4693, + "step": 2503 + }, + { + "epoch": 0.26, + "learning_rate": 1.8431373258171127e-05, + "loss": 1.6297, + "step": 2504 + }, + { + "epoch": 0.26, + "learning_rate": 1.842940458321045e-05, + "loss": 1.5916, + "step": 2505 + }, + { + "epoch": 0.26, + "learning_rate": 1.842743477892614e-05, + "loss": 1.4754, + "step": 2506 + }, + { + "epoch": 0.26, + "learning_rate": 1.842546384558211e-05, + "loss": 1.4828, + "step": 2507 + }, + { + "epoch": 0.26, + "learning_rate": 1.842349178344241e-05, + "loss": 1.4239, + "step": 2508 + }, + { + "epoch": 0.26, + "learning_rate": 1.8421518592771243e-05, + "loss": 1.5028, + "step": 2509 + }, + { + "epoch": 0.26, + "learning_rate": 1.841954427383297e-05, + "loss": 1.4848, + "step": 2510 + }, + { + "epoch": 0.26, + "learning_rate": 1.8417568826892097e-05, + "loss": 1.4617, + "step": 2511 + }, + { + "epoch": 0.26, + "learning_rate": 1.8415592252213284e-05, + "loss": 1.4266, + "step": 2512 + }, + { + "epoch": 0.26, + "learning_rate": 1.8413614550061344e-05, + "loss": 1.4321, + "step": 2513 + }, + { + "epoch": 0.26, + "learning_rate": 1.841163572070123e-05, + "loss": 1.4693, + "step": 2514 + }, + { + "epoch": 0.26, + "learning_rate": 1.840965576439806e-05, + "loss": 1.4257, + "step": 2515 + }, + { + "epoch": 0.26, + "learning_rate": 1.84076746814171e-05, + "loss": 1.4488, + "step": 2516 + }, + { + "epoch": 0.26, + "learning_rate": 1.840569247202376e-05, + "loss": 1.5348, + "step": 2517 + }, + { + "epoch": 0.26, + "learning_rate": 1.8403709136483604e-05, + "loss": 1.477, + "step": 2518 + }, + { + "epoch": 0.26, + "learning_rate": 1.840172467506235e-05, + "loss": 1.443, + "step": 2519 + }, + { + "epoch": 0.26, + "learning_rate": 1.839973908802587e-05, + "loss": 1.4772, + "step": 2520 + }, + { + "epoch": 0.26, + "learning_rate": 1.839775237564017e-05, + "loss": 1.4443, + "step": 2521 + }, + { + "epoch": 0.26, + "learning_rate": 1.839576453817143e-05, + "loss": 1.4063, + "step": 2522 + }, + { + "epoch": 0.26, + "learning_rate": 1.8393775575885963e-05, + "loss": 1.5178, + "step": 2523 + }, + { + "epoch": 0.26, + "learning_rate": 1.8391785489050235e-05, + "loss": 1.4337, + "step": 2524 + }, + { + "epoch": 0.26, + "learning_rate": 1.8389794277930875e-05, + "loss": 1.4512, + "step": 2525 + }, + { + "epoch": 0.26, + "learning_rate": 1.838780194279465e-05, + "loss": 1.5578, + "step": 2526 + }, + { + "epoch": 0.26, + "learning_rate": 1.8385808483908484e-05, + "loss": 1.4606, + "step": 2527 + }, + { + "epoch": 0.27, + "learning_rate": 1.8383813901539444e-05, + "loss": 1.4957, + "step": 2528 + }, + { + "epoch": 0.27, + "learning_rate": 1.838181819595476e-05, + "loss": 1.4914, + "step": 2529 + }, + { + "epoch": 0.27, + "learning_rate": 1.8379821367421802e-05, + "loss": 1.4785, + "step": 2530 + }, + { + "epoch": 0.27, + "learning_rate": 1.837782341620809e-05, + "loss": 1.4052, + "step": 2531 + }, + { + "epoch": 0.27, + "learning_rate": 1.8375824342581303e-05, + "loss": 1.4807, + "step": 2532 + }, + { + "epoch": 0.27, + "learning_rate": 1.8373824146809264e-05, + "loss": 1.4313, + "step": 2533 + }, + { + "epoch": 0.27, + "learning_rate": 1.8371822829159945e-05, + "loss": 1.4374, + "step": 2534 + }, + { + "epoch": 0.27, + "learning_rate": 1.836982038990148e-05, + "loss": 1.4482, + "step": 2535 + }, + { + "epoch": 0.27, + "learning_rate": 1.8367816829302133e-05, + "loss": 1.5231, + "step": 2536 + }, + { + "epoch": 0.27, + "learning_rate": 1.8365812147630337e-05, + "loss": 1.4101, + "step": 2537 + }, + { + "epoch": 0.27, + "learning_rate": 1.8363806345154666e-05, + "loss": 1.4372, + "step": 2538 + }, + { + "epoch": 0.27, + "learning_rate": 1.8361799422143845e-05, + "loss": 1.4808, + "step": 2539 + }, + { + "epoch": 0.27, + "learning_rate": 1.835979137886675e-05, + "loss": 1.3515, + "step": 2540 + }, + { + "epoch": 0.27, + "learning_rate": 1.8357782215592412e-05, + "loss": 1.5284, + "step": 2541 + }, + { + "epoch": 0.27, + "learning_rate": 1.835577193259e-05, + "loss": 1.4222, + "step": 2542 + }, + { + "epoch": 0.27, + "learning_rate": 1.8353760530128846e-05, + "loss": 1.4522, + "step": 2543 + }, + { + "epoch": 0.27, + "learning_rate": 1.835174800847842e-05, + "loss": 1.4487, + "step": 2544 + }, + { + "epoch": 0.27, + "learning_rate": 1.8349734367908355e-05, + "loss": 1.3688, + "step": 2545 + }, + { + "epoch": 0.27, + "learning_rate": 1.8347719608688422e-05, + "loss": 1.483, + "step": 2546 + }, + { + "epoch": 0.27, + "learning_rate": 1.8345703731088554e-05, + "loss": 1.4733, + "step": 2547 + }, + { + "epoch": 0.27, + "learning_rate": 1.8343686735378816e-05, + "loss": 1.4594, + "step": 2548 + }, + { + "epoch": 0.27, + "learning_rate": 1.834166862182944e-05, + "loss": 1.4648, + "step": 2549 + }, + { + "epoch": 0.27, + "learning_rate": 1.8339649390710807e-05, + "loss": 1.5249, + "step": 2550 + }, + { + "epoch": 0.27, + "learning_rate": 1.8337629042293434e-05, + "loss": 1.4744, + "step": 2551 + }, + { + "epoch": 0.27, + "learning_rate": 1.8335607576847994e-05, + "loss": 1.5094, + "step": 2552 + }, + { + "epoch": 0.27, + "learning_rate": 1.8333584994645318e-05, + "loss": 1.5122, + "step": 2553 + }, + { + "epoch": 0.27, + "learning_rate": 1.8331561295956374e-05, + "loss": 1.537, + "step": 2554 + }, + { + "epoch": 0.27, + "learning_rate": 1.832953648105229e-05, + "loss": 1.4691, + "step": 2555 + }, + { + "epoch": 0.27, + "learning_rate": 1.8327510550204343e-05, + "loss": 1.4969, + "step": 2556 + }, + { + "epoch": 0.27, + "learning_rate": 1.8325483503683944e-05, + "loss": 1.4596, + "step": 2557 + }, + { + "epoch": 0.27, + "learning_rate": 1.8323455341762675e-05, + "loss": 1.435, + "step": 2558 + }, + { + "epoch": 0.27, + "learning_rate": 1.8321426064712255e-05, + "loss": 1.4883, + "step": 2559 + }, + { + "epoch": 0.27, + "learning_rate": 1.8319395672804554e-05, + "loss": 1.3758, + "step": 2560 + }, + { + "epoch": 0.27, + "learning_rate": 1.8317364166311592e-05, + "loss": 1.4352, + "step": 2561 + }, + { + "epoch": 0.27, + "learning_rate": 1.831533154550554e-05, + "loss": 1.5072, + "step": 2562 + }, + { + "epoch": 0.27, + "learning_rate": 1.8313297810658718e-05, + "loss": 1.4476, + "step": 2563 + }, + { + "epoch": 0.27, + "learning_rate": 1.831126296204359e-05, + "loss": 1.507, + "step": 2564 + }, + { + "epoch": 0.27, + "learning_rate": 1.8309226999932777e-05, + "loss": 1.4677, + "step": 2565 + }, + { + "epoch": 0.27, + "learning_rate": 1.8307189924599044e-05, + "loss": 1.4537, + "step": 2566 + }, + { + "epoch": 0.27, + "learning_rate": 1.8305151736315307e-05, + "loss": 1.4584, + "step": 2567 + }, + { + "epoch": 0.27, + "learning_rate": 1.8303112435354634e-05, + "loss": 1.4944, + "step": 2568 + }, + { + "epoch": 0.27, + "learning_rate": 1.8301072021990232e-05, + "loss": 1.4379, + "step": 2569 + }, + { + "epoch": 0.27, + "learning_rate": 1.8299030496495475e-05, + "loss": 1.539, + "step": 2570 + }, + { + "epoch": 0.27, + "learning_rate": 1.829698785914386e-05, + "loss": 1.4421, + "step": 2571 + }, + { + "epoch": 0.27, + "learning_rate": 1.8294944110209063e-05, + "loss": 1.4693, + "step": 2572 + }, + { + "epoch": 0.27, + "learning_rate": 1.8292899249964887e-05, + "loss": 1.3239, + "step": 2573 + }, + { + "epoch": 0.27, + "learning_rate": 1.8290853278685284e-05, + "loss": 1.472, + "step": 2574 + }, + { + "epoch": 0.27, + "learning_rate": 1.8288806196644374e-05, + "loss": 1.536, + "step": 2575 + }, + { + "epoch": 0.27, + "learning_rate": 1.8286758004116405e-05, + "loss": 1.4644, + "step": 2576 + }, + { + "epoch": 0.27, + "learning_rate": 1.8284708701375783e-05, + "loss": 1.4537, + "step": 2577 + }, + { + "epoch": 0.27, + "learning_rate": 1.8282658288697067e-05, + "loss": 1.4359, + "step": 2578 + }, + { + "epoch": 0.27, + "learning_rate": 1.8280606766354955e-05, + "loss": 1.4842, + "step": 2579 + }, + { + "epoch": 0.27, + "learning_rate": 1.8278554134624302e-05, + "loss": 1.4664, + "step": 2580 + }, + { + "epoch": 0.27, + "learning_rate": 1.8276500393780105e-05, + "loss": 1.4632, + "step": 2581 + }, + { + "epoch": 0.27, + "learning_rate": 1.827444554409751e-05, + "loss": 1.4996, + "step": 2582 + }, + { + "epoch": 0.27, + "learning_rate": 1.827238958585182e-05, + "loss": 1.3399, + "step": 2583 + }, + { + "epoch": 0.27, + "learning_rate": 1.8270332519318476e-05, + "loss": 1.3928, + "step": 2584 + }, + { + "epoch": 0.27, + "learning_rate": 1.8268274344773074e-05, + "loss": 1.4993, + "step": 2585 + }, + { + "epoch": 0.27, + "learning_rate": 1.8266215062491356e-05, + "loss": 1.5398, + "step": 2586 + }, + { + "epoch": 0.27, + "learning_rate": 1.826415467274921e-05, + "loss": 1.4353, + "step": 2587 + }, + { + "epoch": 0.27, + "eval_loss": 1.5104212760925293, + "eval_runtime": 77.3448, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2587 + }, + { + "epoch": 0.27, + "learning_rate": 1.8262093175822685e-05, + "loss": 1.4889, + "step": 2588 + }, + { + "epoch": 0.27, + "learning_rate": 1.826003057198796e-05, + "loss": 1.4912, + "step": 2589 + }, + { + "epoch": 0.27, + "learning_rate": 1.825796686152137e-05, + "loss": 1.4884, + "step": 2590 + }, + { + "epoch": 0.27, + "learning_rate": 1.8255902044699404e-05, + "loss": 1.478, + "step": 2591 + }, + { + "epoch": 0.27, + "learning_rate": 1.8253836121798692e-05, + "loss": 1.6549, + "step": 2592 + }, + { + "epoch": 0.27, + "learning_rate": 1.8251769093096018e-05, + "loss": 1.5146, + "step": 2593 + }, + { + "epoch": 0.27, + "learning_rate": 1.8249700958868306e-05, + "loss": 1.4797, + "step": 2594 + }, + { + "epoch": 0.27, + "learning_rate": 1.8247631719392634e-05, + "loss": 1.4655, + "step": 2595 + }, + { + "epoch": 0.27, + "learning_rate": 1.824556137494623e-05, + "loss": 1.4517, + "step": 2596 + }, + { + "epoch": 0.27, + "learning_rate": 1.8243489925806458e-05, + "loss": 1.4936, + "step": 2597 + }, + { + "epoch": 0.27, + "learning_rate": 1.8241417372250852e-05, + "loss": 1.4614, + "step": 2598 + }, + { + "epoch": 0.27, + "learning_rate": 1.8239343714557073e-05, + "loss": 1.4475, + "step": 2599 + }, + { + "epoch": 0.27, + "learning_rate": 1.8237268953002937e-05, + "loss": 1.5435, + "step": 2600 + }, + { + "epoch": 0.27, + "learning_rate": 1.8235193087866413e-05, + "loss": 1.4616, + "step": 2601 + }, + { + "epoch": 0.27, + "learning_rate": 1.8233116119425612e-05, + "loss": 1.4578, + "step": 2602 + }, + { + "epoch": 0.27, + "learning_rate": 1.8231038047958795e-05, + "loss": 1.434, + "step": 2603 + }, + { + "epoch": 0.27, + "learning_rate": 1.8228958873744368e-05, + "loss": 1.5335, + "step": 2604 + }, + { + "epoch": 0.27, + "learning_rate": 1.8226878597060887e-05, + "loss": 1.415, + "step": 2605 + }, + { + "epoch": 0.27, + "learning_rate": 1.8224797218187058e-05, + "loss": 1.6165, + "step": 2606 + }, + { + "epoch": 0.27, + "learning_rate": 1.822271473740173e-05, + "loss": 1.372, + "step": 2607 + }, + { + "epoch": 0.27, + "learning_rate": 1.8220631154983907e-05, + "loss": 1.4855, + "step": 2608 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218546471212727e-05, + "loss": 1.4093, + "step": 2609 + }, + { + "epoch": 0.27, + "learning_rate": 1.821646068636749e-05, + "loss": 1.4852, + "step": 2610 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214373800727637e-05, + "loss": 1.6959, + "step": 2611 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212285814572755e-05, + "loss": 1.3874, + "step": 2612 + }, + { + "epoch": 0.27, + "learning_rate": 1.821019672818258e-05, + "loss": 1.4425, + "step": 2613 + }, + { + "epoch": 0.27, + "learning_rate": 1.8208106541837e-05, + "loss": 1.6097, + "step": 2614 + }, + { + "epoch": 0.27, + "learning_rate": 1.8206015255816045e-05, + "loss": 1.5675, + "step": 2615 + }, + { + "epoch": 0.27, + "learning_rate": 1.820392287039989e-05, + "loss": 1.4039, + "step": 2616 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201829385868866e-05, + "loss": 1.4872, + "step": 2617 + }, + { + "epoch": 0.27, + "learning_rate": 1.819973480250344e-05, + "loss": 1.4645, + "step": 2618 + }, + { + "epoch": 0.27, + "learning_rate": 1.8197639120584237e-05, + "loss": 1.4923, + "step": 2619 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195542340392025e-05, + "loss": 1.4294, + "step": 2620 + }, + { + "epoch": 0.27, + "learning_rate": 1.8193444462207717e-05, + "loss": 1.4315, + "step": 2621 + }, + { + "epoch": 0.27, + "learning_rate": 1.8191345486312372e-05, + "loss": 1.3972, + "step": 2622 + }, + { + "epoch": 0.28, + "learning_rate": 1.8189245412987205e-05, + "loss": 1.462, + "step": 2623 + }, + { + "epoch": 0.28, + "learning_rate": 1.8187144242513567e-05, + "loss": 1.4738, + "step": 2624 + }, + { + "epoch": 0.28, + "learning_rate": 1.818504197517296e-05, + "loss": 1.4935, + "step": 2625 + }, + { + "epoch": 0.28, + "learning_rate": 1.8182938611247038e-05, + "loss": 1.4231, + "step": 2626 + }, + { + "epoch": 0.28, + "learning_rate": 1.81808341510176e-05, + "loss": 1.4031, + "step": 2627 + }, + { + "epoch": 0.28, + "learning_rate": 1.817872859476658e-05, + "loss": 1.5822, + "step": 2628 + }, + { + "epoch": 0.28, + "learning_rate": 1.8176621942776075e-05, + "loss": 1.432, + "step": 2629 + }, + { + "epoch": 0.28, + "learning_rate": 1.8174514195328324e-05, + "loss": 1.5565, + "step": 2630 + }, + { + "epoch": 0.28, + "learning_rate": 1.8172405352705704e-05, + "loss": 1.4895, + "step": 2631 + }, + { + "epoch": 0.28, + "learning_rate": 1.8170295415190754e-05, + "loss": 1.4032, + "step": 2632 + }, + { + "epoch": 0.28, + "learning_rate": 1.8168184383066144e-05, + "loss": 1.4253, + "step": 2633 + }, + { + "epoch": 0.28, + "learning_rate": 1.8166072256614702e-05, + "loss": 1.5162, + "step": 2634 + }, + { + "epoch": 0.28, + "learning_rate": 1.81639590361194e-05, + "loss": 1.4609, + "step": 2635 + }, + { + "epoch": 0.28, + "learning_rate": 1.816184472186335e-05, + "loss": 1.4351, + "step": 2636 + }, + { + "epoch": 0.28, + "learning_rate": 1.8159729314129823e-05, + "loss": 1.4738, + "step": 2637 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157612813202224e-05, + "loss": 1.5986, + "step": 2638 + }, + { + "epoch": 0.28, + "learning_rate": 1.815549521936411e-05, + "loss": 1.4633, + "step": 2639 + }, + { + "epoch": 0.28, + "learning_rate": 1.8153376532899184e-05, + "loss": 1.4404, + "step": 2640 + }, + { + "epoch": 0.28, + "learning_rate": 1.81512567540913e-05, + "loss": 1.4256, + "step": 2641 + }, + { + "epoch": 0.28, + "learning_rate": 1.814913588322445e-05, + "loss": 1.4054, + "step": 2642 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147013920582773e-05, + "loss": 1.4134, + "step": 2643 + }, + { + "epoch": 0.28, + "learning_rate": 1.8144890866450567e-05, + "loss": 1.4098, + "step": 2644 + }, + { + "epoch": 0.28, + "learning_rate": 1.814276672111226e-05, + "loss": 1.4593, + "step": 2645 + }, + { + "epoch": 0.28, + "learning_rate": 1.814064148485243e-05, + "loss": 1.4679, + "step": 2646 + }, + { + "epoch": 0.28, + "learning_rate": 1.8138515157955812e-05, + "loss": 1.5234, + "step": 2647 + }, + { + "epoch": 0.28, + "learning_rate": 1.8136387740707272e-05, + "loss": 1.4568, + "step": 2648 + }, + { + "epoch": 0.28, + "learning_rate": 1.8134259233391836e-05, + "loss": 1.5057, + "step": 2649 + }, + { + "epoch": 0.28, + "learning_rate": 1.8132129636294665e-05, + "loss": 1.3643, + "step": 2650 + }, + { + "epoch": 0.28, + "learning_rate": 1.812999894970107e-05, + "loss": 1.4766, + "step": 2651 + }, + { + "epoch": 0.28, + "learning_rate": 1.812786717389651e-05, + "loss": 1.5701, + "step": 2652 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125734309166587e-05, + "loss": 1.5341, + "step": 2653 + }, + { + "epoch": 0.28, + "learning_rate": 1.812360035579705e-05, + "loss": 1.3596, + "step": 2654 + }, + { + "epoch": 0.28, + "learning_rate": 1.8121465314073793e-05, + "loss": 1.4847, + "step": 2655 + }, + { + "epoch": 0.28, + "learning_rate": 1.811932918428286e-05, + "loss": 1.4664, + "step": 2656 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117191966710438e-05, + "loss": 1.4673, + "step": 2657 + }, + { + "epoch": 0.28, + "learning_rate": 1.8115053661642856e-05, + "loss": 1.4712, + "step": 2658 + }, + { + "epoch": 0.28, + "learning_rate": 1.811291426936659e-05, + "loss": 1.4458, + "step": 2659 + }, + { + "epoch": 0.28, + "learning_rate": 1.811077379016827e-05, + "loss": 1.4667, + "step": 2660 + }, + { + "epoch": 0.28, + "learning_rate": 1.810863222433466e-05, + "loss": 1.4695, + "step": 2661 + }, + { + "epoch": 0.28, + "learning_rate": 1.8106489572152677e-05, + "loss": 1.5263, + "step": 2662 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104345833909376e-05, + "loss": 1.4148, + "step": 2663 + }, + { + "epoch": 0.28, + "learning_rate": 1.8102201009891976e-05, + "loss": 1.3955, + "step": 2664 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100055100387814e-05, + "loss": 1.6056, + "step": 2665 + }, + { + "epoch": 0.28, + "learning_rate": 1.8097908105684396e-05, + "loss": 1.5394, + "step": 2666 + }, + { + "epoch": 0.28, + "learning_rate": 1.809576002606936e-05, + "loss": 1.479, + "step": 2667 + }, + { + "epoch": 0.28, + "learning_rate": 1.8093610861830494e-05, + "loss": 1.4492, + "step": 2668 + }, + { + "epoch": 0.28, + "learning_rate": 1.8091460613255728e-05, + "loss": 1.4172, + "step": 2669 + }, + { + "epoch": 0.28, + "learning_rate": 1.808930928063315e-05, + "loss": 1.4498, + "step": 2670 + }, + { + "epoch": 0.28, + "learning_rate": 1.808715686425097e-05, + "loss": 1.6203, + "step": 2671 + }, + { + "epoch": 0.28, + "learning_rate": 1.8085003364397567e-05, + "loss": 1.435, + "step": 2672 + }, + { + "epoch": 0.28, + "learning_rate": 1.808284878136145e-05, + "loss": 1.4489, + "step": 2673 + }, + { + "epoch": 0.28, + "learning_rate": 1.8080693115431277e-05, + "loss": 1.4416, + "step": 2674 + }, + { + "epoch": 0.28, + "learning_rate": 1.8078536366895853e-05, + "loss": 1.422, + "step": 2675 + }, + { + "epoch": 0.28, + "learning_rate": 1.8076378536044128e-05, + "loss": 1.4039, + "step": 2676 + }, + { + "epoch": 0.28, + "learning_rate": 1.8074219623165195e-05, + "loss": 1.4705, + "step": 2677 + }, + { + "epoch": 0.28, + "learning_rate": 1.807205962854829e-05, + "loss": 1.5031, + "step": 2678 + }, + { + "epoch": 0.28, + "learning_rate": 1.8069898552482806e-05, + "loss": 1.4812, + "step": 2679 + }, + { + "epoch": 0.28, + "learning_rate": 1.806773639525826e-05, + "loss": 1.4129, + "step": 2680 + }, + { + "epoch": 0.28, + "learning_rate": 1.8065573157164332e-05, + "loss": 1.4559, + "step": 2681 + }, + { + "epoch": 0.28, + "learning_rate": 1.806340883849084e-05, + "loss": 1.3878, + "step": 2682 + }, + { + "epoch": 0.28, + "learning_rate": 1.8061243439527744e-05, + "loss": 1.4752, + "step": 2683 + }, + { + "epoch": 0.28, + "learning_rate": 1.8059076960565156e-05, + "loss": 1.4089, + "step": 2684 + }, + { + "epoch": 0.28, + "learning_rate": 1.8056909401893326e-05, + "loss": 1.4736, + "step": 2685 + }, + { + "epoch": 0.28, + "learning_rate": 1.8054740763802654e-05, + "loss": 1.3796, + "step": 2686 + }, + { + "epoch": 0.28, + "learning_rate": 1.805257104658368e-05, + "loss": 1.4412, + "step": 2687 + }, + { + "epoch": 0.28, + "learning_rate": 1.8050400250527086e-05, + "loss": 1.4639, + "step": 2688 + }, + { + "epoch": 0.28, + "learning_rate": 1.804822837592371e-05, + "loss": 1.4076, + "step": 2689 + }, + { + "epoch": 0.28, + "learning_rate": 1.804605542306452e-05, + "loss": 1.4627, + "step": 2690 + }, + { + "epoch": 0.28, + "learning_rate": 1.8043881392240642e-05, + "loss": 1.5249, + "step": 2691 + }, + { + "epoch": 0.28, + "learning_rate": 1.804170628374334e-05, + "loss": 1.4312, + "step": 2692 + }, + { + "epoch": 0.28, + "learning_rate": 1.803953009786402e-05, + "loss": 1.5676, + "step": 2693 + }, + { + "epoch": 0.28, + "learning_rate": 1.8037352834894233e-05, + "loss": 1.5072, + "step": 2694 + }, + { + "epoch": 0.28, + "learning_rate": 1.803517449512568e-05, + "loss": 1.5662, + "step": 2695 + }, + { + "epoch": 0.28, + "learning_rate": 1.8032995078850207e-05, + "loss": 1.4771, + "step": 2696 + }, + { + "epoch": 0.28, + "learning_rate": 1.803081458635979e-05, + "loss": 1.412, + "step": 2697 + }, + { + "epoch": 0.28, + "learning_rate": 1.8028633017946564e-05, + "loss": 1.497, + "step": 2698 + }, + { + "epoch": 0.28, + "learning_rate": 1.8026450373902804e-05, + "loss": 1.4528, + "step": 2699 + }, + { + "epoch": 0.28, + "learning_rate": 1.802426665452093e-05, + "loss": 1.4785, + "step": 2700 + }, + { + "epoch": 0.28, + "learning_rate": 1.8022081860093493e-05, + "loss": 1.6411, + "step": 2701 + }, + { + "epoch": 0.28, + "learning_rate": 1.8019895990913213e-05, + "loss": 1.4459, + "step": 2702 + }, + { + "epoch": 0.28, + "learning_rate": 1.8017709047272932e-05, + "loss": 1.4418, + "step": 2703 + }, + { + "epoch": 0.28, + "learning_rate": 1.801552102946565e-05, + "loss": 1.4409, + "step": 2704 + }, + { + "epoch": 0.28, + "learning_rate": 1.8013331937784498e-05, + "loss": 1.4651, + "step": 2705 + }, + { + "epoch": 0.28, + "learning_rate": 1.8011141772522766e-05, + "loss": 1.4161, + "step": 2706 + }, + { + "epoch": 0.28, + "learning_rate": 1.8008950533973876e-05, + "loss": 1.458, + "step": 2707 + }, + { + "epoch": 0.28, + "learning_rate": 1.8006758222431398e-05, + "loss": 1.4477, + "step": 2708 + }, + { + "epoch": 0.28, + "learning_rate": 1.800456483818904e-05, + "loss": 1.4433, + "step": 2709 + }, + { + "epoch": 0.28, + "learning_rate": 1.8002370381540672e-05, + "loss": 1.5005, + "step": 2710 + }, + { + "epoch": 0.28, + "learning_rate": 1.8000174852780282e-05, + "loss": 1.4945, + "step": 2711 + }, + { + "epoch": 0.28, + "learning_rate": 1.7997978252202023e-05, + "loss": 1.4298, + "step": 2712 + }, + { + "epoch": 0.28, + "learning_rate": 1.7995780580100177e-05, + "loss": 1.3812, + "step": 2713 + }, + { + "epoch": 0.28, + "learning_rate": 1.799358183676918e-05, + "loss": 1.5559, + "step": 2714 + }, + { + "epoch": 0.28, + "learning_rate": 1.79913820225036e-05, + "loss": 1.4316, + "step": 2715 + }, + { + "epoch": 0.28, + "learning_rate": 1.798918113759817e-05, + "loss": 1.419, + "step": 2716 + }, + { + "epoch": 0.28, + "learning_rate": 1.7986979182347733e-05, + "loss": 1.43, + "step": 2717 + }, + { + "epoch": 0.29, + "learning_rate": 1.798477615704731e-05, + "loss": 1.4964, + "step": 2718 + }, + { + "epoch": 0.29, + "learning_rate": 1.7982572061992044e-05, + "loss": 1.4417, + "step": 2719 + }, + { + "epoch": 0.29, + "learning_rate": 1.7980366897477227e-05, + "loss": 1.4562, + "step": 2720 + }, + { + "epoch": 0.29, + "learning_rate": 1.7978160663798295e-05, + "loss": 1.4386, + "step": 2721 + }, + { + "epoch": 0.29, + "learning_rate": 1.7975953361250824e-05, + "loss": 1.445, + "step": 2722 + }, + { + "epoch": 0.29, + "learning_rate": 1.797374499013054e-05, + "loss": 1.4549, + "step": 2723 + }, + { + "epoch": 0.29, + "learning_rate": 1.7971535550733305e-05, + "loss": 1.5205, + "step": 2724 + }, + { + "epoch": 0.29, + "learning_rate": 1.796932504335513e-05, + "loss": 1.4632, + "step": 2725 + }, + { + "epoch": 0.29, + "learning_rate": 1.796711346829216e-05, + "loss": 1.3767, + "step": 2726 + }, + { + "epoch": 0.29, + "learning_rate": 1.79649008258407e-05, + "loss": 1.4098, + "step": 2727 + }, + { + "epoch": 0.29, + "learning_rate": 1.7962687116297178e-05, + "loss": 1.4675, + "step": 2728 + }, + { + "epoch": 0.29, + "learning_rate": 1.7960472339958176e-05, + "loss": 1.6048, + "step": 2729 + }, + { + "epoch": 0.29, + "learning_rate": 1.7958256497120418e-05, + "loss": 1.5432, + "step": 2730 + }, + { + "epoch": 0.29, + "learning_rate": 1.7956039588080774e-05, + "loss": 1.5453, + "step": 2731 + }, + { + "epoch": 0.29, + "learning_rate": 1.7953821613136246e-05, + "loss": 1.4246, + "step": 2732 + }, + { + "epoch": 0.29, + "learning_rate": 1.7951602572583988e-05, + "loss": 1.3987, + "step": 2733 + }, + { + "epoch": 0.29, + "learning_rate": 1.7949382466721295e-05, + "loss": 1.4943, + "step": 2734 + }, + { + "epoch": 0.29, + "learning_rate": 1.7947161295845606e-05, + "loss": 1.4385, + "step": 2735 + }, + { + "epoch": 0.29, + "learning_rate": 1.7944939060254497e-05, + "loss": 1.4165, + "step": 2736 + }, + { + "epoch": 0.29, + "learning_rate": 1.7942715760245692e-05, + "loss": 1.4004, + "step": 2737 + }, + { + "epoch": 0.29, + "learning_rate": 1.7940491396117063e-05, + "loss": 1.4577, + "step": 2738 + }, + { + "epoch": 0.29, + "learning_rate": 1.7938265968166602e-05, + "loss": 1.4649, + "step": 2739 + }, + { + "epoch": 0.29, + "learning_rate": 1.7936039476692473e-05, + "loss": 1.5273, + "step": 2740 + }, + { + "epoch": 0.29, + "learning_rate": 1.7933811921992962e-05, + "loss": 1.4325, + "step": 2741 + }, + { + "epoch": 0.29, + "learning_rate": 1.793158330436651e-05, + "loss": 1.4388, + "step": 2742 + }, + { + "epoch": 0.29, + "learning_rate": 1.7929353624111687e-05, + "loss": 1.4124, + "step": 2743 + }, + { + "epoch": 0.29, + "learning_rate": 1.7927122881527222e-05, + "loss": 1.5449, + "step": 2744 + }, + { + "epoch": 0.29, + "learning_rate": 1.7924891076911964e-05, + "loss": 1.4728, + "step": 2745 + }, + { + "epoch": 0.29, + "learning_rate": 1.7922658210564932e-05, + "loss": 1.5103, + "step": 2746 + }, + { + "epoch": 0.29, + "learning_rate": 1.792042428278526e-05, + "loss": 1.5975, + "step": 2747 + }, + { + "epoch": 0.29, + "learning_rate": 1.7918189293872247e-05, + "loss": 1.567, + "step": 2748 + }, + { + "epoch": 0.29, + "learning_rate": 1.7915953244125318e-05, + "loss": 1.57, + "step": 2749 + }, + { + "epoch": 0.29, + "learning_rate": 1.791371613384405e-05, + "loss": 1.4372, + "step": 2750 + }, + { + "epoch": 0.29, + "learning_rate": 1.7911477963328155e-05, + "loss": 1.4053, + "step": 2751 + }, + { + "epoch": 0.29, + "learning_rate": 1.7909238732877492e-05, + "loss": 1.3782, + "step": 2752 + }, + { + "epoch": 0.29, + "learning_rate": 1.790699844279206e-05, + "loss": 1.4401, + "step": 2753 + }, + { + "epoch": 0.29, + "learning_rate": 1.7904757093372e-05, + "loss": 1.3749, + "step": 2754 + }, + { + "epoch": 0.29, + "learning_rate": 1.79025146849176e-05, + "loss": 1.4909, + "step": 2755 + }, + { + "epoch": 0.29, + "learning_rate": 1.7900271217729273e-05, + "loss": 1.4103, + "step": 2756 + }, + { + "epoch": 0.29, + "learning_rate": 1.7898026692107597e-05, + "loss": 1.4986, + "step": 2757 + }, + { + "epoch": 0.29, + "learning_rate": 1.7895781108353278e-05, + "loss": 1.5449, + "step": 2758 + }, + { + "epoch": 0.29, + "learning_rate": 1.789353446676717e-05, + "loss": 1.5583, + "step": 2759 + }, + { + "epoch": 0.29, + "learning_rate": 1.7891286767650254e-05, + "loss": 1.5342, + "step": 2760 + }, + { + "epoch": 0.29, + "learning_rate": 1.7889038011303673e-05, + "loss": 1.4233, + "step": 2761 + }, + { + "epoch": 0.29, + "learning_rate": 1.7886788198028707e-05, + "loss": 1.3433, + "step": 2762 + }, + { + "epoch": 0.29, + "learning_rate": 1.788453732812676e-05, + "loss": 1.4451, + "step": 2763 + }, + { + "epoch": 0.29, + "learning_rate": 1.78822854018994e-05, + "loss": 1.4506, + "step": 2764 + }, + { + "epoch": 0.29, + "learning_rate": 1.7880032419648324e-05, + "loss": 1.4386, + "step": 2765 + }, + { + "epoch": 0.29, + "learning_rate": 1.7877778381675374e-05, + "loss": 1.4512, + "step": 2766 + }, + { + "epoch": 0.29, + "learning_rate": 1.7875523288282535e-05, + "loss": 1.4319, + "step": 2767 + }, + { + "epoch": 0.29, + "learning_rate": 1.7873267139771932e-05, + "loss": 1.4753, + "step": 2768 + }, + { + "epoch": 0.29, + "learning_rate": 1.787100993644583e-05, + "loss": 1.4044, + "step": 2769 + }, + { + "epoch": 0.29, + "learning_rate": 1.786875167860663e-05, + "loss": 1.4382, + "step": 2770 + }, + { + "epoch": 0.29, + "learning_rate": 1.786649236655689e-05, + "loss": 1.3977, + "step": 2771 + }, + { + "epoch": 0.29, + "learning_rate": 1.7864232000599298e-05, + "loss": 1.4473, + "step": 2772 + }, + { + "epoch": 0.29, + "learning_rate": 1.7861970581036678e-05, + "loss": 1.4666, + "step": 2773 + }, + { + "epoch": 0.29, + "learning_rate": 1.785970810817201e-05, + "loss": 1.5299, + "step": 2774 + }, + { + "epoch": 0.29, + "learning_rate": 1.7857444582308402e-05, + "loss": 1.3974, + "step": 2775 + }, + { + "epoch": 0.29, + "learning_rate": 1.7855180003749114e-05, + "loss": 1.4603, + "step": 2776 + }, + { + "epoch": 0.29, + "learning_rate": 1.7852914372797535e-05, + "loss": 1.463, + "step": 2777 + }, + { + "epoch": 0.29, + "learning_rate": 1.7850647689757205e-05, + "loss": 1.5317, + "step": 2778 + }, + { + "epoch": 0.29, + "learning_rate": 1.78483799549318e-05, + "loss": 1.4669, + "step": 2779 + }, + { + "epoch": 0.29, + "learning_rate": 1.784611116862514e-05, + "loss": 1.5293, + "step": 2780 + }, + { + "epoch": 0.29, + "learning_rate": 1.7843841331141177e-05, + "loss": 1.5802, + "step": 2781 + }, + { + "epoch": 0.29, + "learning_rate": 1.7841570442784024e-05, + "loss": 1.4486, + "step": 2782 + }, + { + "epoch": 0.29, + "learning_rate": 1.7839298503857913e-05, + "loss": 1.4674, + "step": 2783 + }, + { + "epoch": 0.29, + "learning_rate": 1.7837025514667224e-05, + "loss": 1.4662, + "step": 2784 + }, + { + "epoch": 0.29, + "learning_rate": 1.7834751475516484e-05, + "loss": 1.3555, + "step": 2785 + }, + { + "epoch": 0.29, + "learning_rate": 1.783247638671035e-05, + "loss": 1.4307, + "step": 2786 + }, + { + "epoch": 0.29, + "eval_loss": 1.500258445739746, + "eval_runtime": 77.406, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 2786 + }, + { + "epoch": 0.29, + "learning_rate": 1.7830200248553633e-05, + "loss": 1.4596, + "step": 2787 + }, + { + "epoch": 0.29, + "learning_rate": 1.7827923061351273e-05, + "loss": 1.6118, + "step": 2788 + }, + { + "epoch": 0.29, + "learning_rate": 1.7825644825408353e-05, + "loss": 1.4782, + "step": 2789 + }, + { + "epoch": 0.29, + "learning_rate": 1.78233655410301e-05, + "loss": 1.4681, + "step": 2790 + }, + { + "epoch": 0.29, + "learning_rate": 1.782108520852188e-05, + "loss": 1.6281, + "step": 2791 + }, + { + "epoch": 0.29, + "learning_rate": 1.78188038281892e-05, + "loss": 1.4446, + "step": 2792 + }, + { + "epoch": 0.29, + "learning_rate": 1.7816521400337704e-05, + "loss": 1.479, + "step": 2793 + }, + { + "epoch": 0.29, + "learning_rate": 1.7814237925273178e-05, + "loss": 1.5457, + "step": 2794 + }, + { + "epoch": 0.29, + "learning_rate": 1.7811953403301547e-05, + "loss": 1.3928, + "step": 2795 + }, + { + "epoch": 0.29, + "learning_rate": 1.780966783472889e-05, + "loss": 1.4321, + "step": 2796 + }, + { + "epoch": 0.29, + "learning_rate": 1.78073812198614e-05, + "loss": 1.5734, + "step": 2797 + }, + { + "epoch": 0.29, + "learning_rate": 1.7805093559005432e-05, + "loss": 1.4356, + "step": 2798 + }, + { + "epoch": 0.29, + "learning_rate": 1.7802804852467473e-05, + "loss": 1.4656, + "step": 2799 + }, + { + "epoch": 0.29, + "learning_rate": 1.780051510055415e-05, + "loss": 1.4052, + "step": 2800 + }, + { + "epoch": 0.29, + "learning_rate": 1.7798224303572228e-05, + "loss": 1.4758, + "step": 2801 + }, + { + "epoch": 0.29, + "learning_rate": 1.7795932461828622e-05, + "loss": 1.4326, + "step": 2802 + }, + { + "epoch": 0.29, + "learning_rate": 1.7793639575630376e-05, + "loss": 1.3409, + "step": 2803 + }, + { + "epoch": 0.29, + "learning_rate": 1.7791345645284678e-05, + "loss": 1.4175, + "step": 2804 + }, + { + "epoch": 0.29, + "learning_rate": 1.7789050671098853e-05, + "loss": 1.383, + "step": 2805 + }, + { + "epoch": 0.29, + "learning_rate": 1.7786754653380373e-05, + "loss": 1.5162, + "step": 2806 + }, + { + "epoch": 0.29, + "learning_rate": 1.7784457592436847e-05, + "loss": 1.4899, + "step": 2807 + }, + { + "epoch": 0.29, + "learning_rate": 1.7782159488576016e-05, + "loss": 1.4874, + "step": 2808 + }, + { + "epoch": 0.29, + "learning_rate": 1.777986034210577e-05, + "loss": 1.4363, + "step": 2809 + }, + { + "epoch": 0.29, + "learning_rate": 1.7777560153334134e-05, + "loss": 1.4223, + "step": 2810 + }, + { + "epoch": 0.29, + "learning_rate": 1.7775258922569273e-05, + "loss": 1.4792, + "step": 2811 + }, + { + "epoch": 0.29, + "learning_rate": 1.77729566501195e-05, + "loss": 1.4475, + "step": 2812 + }, + { + "epoch": 0.29, + "learning_rate": 1.7770653336293253e-05, + "loss": 1.5157, + "step": 2813 + }, + { + "epoch": 0.3, + "learning_rate": 1.776834898139912e-05, + "loss": 1.389, + "step": 2814 + }, + { + "epoch": 0.3, + "learning_rate": 1.7766043585745824e-05, + "loss": 1.4358, + "step": 2815 + }, + { + "epoch": 0.3, + "learning_rate": 1.776373714964223e-05, + "loss": 1.4297, + "step": 2816 + }, + { + "epoch": 0.3, + "learning_rate": 1.7761429673397344e-05, + "loss": 1.4102, + "step": 2817 + }, + { + "epoch": 0.3, + "learning_rate": 1.77591211573203e-05, + "loss": 1.4572, + "step": 2818 + }, + { + "epoch": 0.3, + "learning_rate": 1.775681160172039e-05, + "loss": 1.448, + "step": 2819 + }, + { + "epoch": 0.3, + "learning_rate": 1.7754501006907025e-05, + "loss": 1.4426, + "step": 2820 + }, + { + "epoch": 0.3, + "learning_rate": 1.7752189373189773e-05, + "loss": 1.4566, + "step": 2821 + }, + { + "epoch": 0.3, + "learning_rate": 1.7749876700878332e-05, + "loss": 1.4267, + "step": 2822 + }, + { + "epoch": 0.3, + "learning_rate": 1.7747562990282538e-05, + "loss": 1.3951, + "step": 2823 + }, + { + "epoch": 0.3, + "learning_rate": 1.7745248241712373e-05, + "loss": 1.4668, + "step": 2824 + }, + { + "epoch": 0.3, + "learning_rate": 1.774293245547795e-05, + "loss": 1.4924, + "step": 2825 + }, + { + "epoch": 0.3, + "learning_rate": 1.7740615631889525e-05, + "loss": 1.5258, + "step": 2826 + }, + { + "epoch": 0.3, + "learning_rate": 1.7738297771257496e-05, + "loss": 1.4323, + "step": 2827 + }, + { + "epoch": 0.3, + "learning_rate": 1.7735978873892393e-05, + "loss": 1.439, + "step": 2828 + }, + { + "epoch": 0.3, + "learning_rate": 1.773365894010489e-05, + "loss": 1.5658, + "step": 2829 + }, + { + "epoch": 0.3, + "learning_rate": 1.77313379702058e-05, + "loss": 1.4607, + "step": 2830 + }, + { + "epoch": 0.3, + "learning_rate": 1.7729015964506073e-05, + "loss": 1.5544, + "step": 2831 + }, + { + "epoch": 0.3, + "learning_rate": 1.7726692923316798e-05, + "loss": 1.4232, + "step": 2832 + }, + { + "epoch": 0.3, + "learning_rate": 1.77243688469492e-05, + "loss": 1.415, + "step": 2833 + }, + { + "epoch": 0.3, + "learning_rate": 1.772204373571465e-05, + "loss": 1.4658, + "step": 2834 + }, + { + "epoch": 0.3, + "learning_rate": 1.7719717589924647e-05, + "loss": 1.4678, + "step": 2835 + }, + { + "epoch": 0.3, + "learning_rate": 1.771739040989084e-05, + "loss": 1.3021, + "step": 2836 + }, + { + "epoch": 0.3, + "learning_rate": 1.771506219592501e-05, + "loss": 1.4045, + "step": 2837 + }, + { + "epoch": 0.3, + "learning_rate": 1.7712732948339085e-05, + "loss": 1.4593, + "step": 2838 + }, + { + "epoch": 0.3, + "learning_rate": 1.7710402667445108e-05, + "loss": 1.4175, + "step": 2839 + }, + { + "epoch": 0.3, + "learning_rate": 1.770807135355529e-05, + "loss": 1.3939, + "step": 2840 + }, + { + "epoch": 0.3, + "learning_rate": 1.7705739006981963e-05, + "loss": 1.6089, + "step": 2841 + }, + { + "epoch": 0.3, + "learning_rate": 1.77034056280376e-05, + "loss": 1.3952, + "step": 2842 + }, + { + "epoch": 0.3, + "learning_rate": 1.7701071217034818e-05, + "loss": 1.5086, + "step": 2843 + }, + { + "epoch": 0.3, + "learning_rate": 1.7698735774286362e-05, + "loss": 1.4706, + "step": 2844 + }, + { + "epoch": 0.3, + "learning_rate": 1.7696399300105128e-05, + "loss": 1.4286, + "step": 2845 + }, + { + "epoch": 0.3, + "learning_rate": 1.7694061794804137e-05, + "loss": 1.4418, + "step": 2846 + }, + { + "epoch": 0.3, + "learning_rate": 1.7691723258696562e-05, + "loss": 1.516, + "step": 2847 + }, + { + "epoch": 0.3, + "learning_rate": 1.76893836920957e-05, + "loss": 1.4354, + "step": 2848 + }, + { + "epoch": 0.3, + "learning_rate": 1.7687043095314998e-05, + "loss": 1.7503, + "step": 2849 + }, + { + "epoch": 0.3, + "learning_rate": 1.7684701468668032e-05, + "loss": 1.5985, + "step": 2850 + }, + { + "epoch": 0.3, + "learning_rate": 1.768235881246852e-05, + "loss": 1.442, + "step": 2851 + }, + { + "epoch": 0.3, + "learning_rate": 1.7680015127030322e-05, + "loss": 1.4924, + "step": 2852 + }, + { + "epoch": 0.3, + "learning_rate": 1.7677670412667425e-05, + "loss": 1.4461, + "step": 2853 + }, + { + "epoch": 0.3, + "learning_rate": 1.7675324669693968e-05, + "loss": 1.3823, + "step": 2854 + }, + { + "epoch": 0.3, + "learning_rate": 1.767297789842421e-05, + "loss": 1.452, + "step": 2855 + }, + { + "epoch": 0.3, + "learning_rate": 1.767063009917257e-05, + "loss": 1.46, + "step": 2856 + }, + { + "epoch": 0.3, + "learning_rate": 1.7668281272253587e-05, + "loss": 1.4129, + "step": 2857 + }, + { + "epoch": 0.3, + "learning_rate": 1.766593141798194e-05, + "loss": 1.4057, + "step": 2858 + }, + { + "epoch": 0.3, + "learning_rate": 1.7663580536672456e-05, + "loss": 1.5162, + "step": 2859 + }, + { + "epoch": 0.3, + "learning_rate": 1.7661228628640087e-05, + "loss": 1.5177, + "step": 2860 + }, + { + "epoch": 0.3, + "learning_rate": 1.7658875694199933e-05, + "loss": 1.4548, + "step": 2861 + }, + { + "epoch": 0.3, + "learning_rate": 1.7656521733667223e-05, + "loss": 1.4511, + "step": 2862 + }, + { + "epoch": 0.3, + "learning_rate": 1.765416674735733e-05, + "loss": 1.4778, + "step": 2863 + }, + { + "epoch": 0.3, + "learning_rate": 1.765181073558576e-05, + "loss": 1.3935, + "step": 2864 + }, + { + "epoch": 0.3, + "learning_rate": 1.7649453698668156e-05, + "loss": 1.4659, + "step": 2865 + }, + { + "epoch": 0.3, + "learning_rate": 1.7647095636920305e-05, + "loss": 1.7042, + "step": 2866 + }, + { + "epoch": 0.3, + "learning_rate": 1.7644736550658124e-05, + "loss": 1.7957, + "step": 2867 + }, + { + "epoch": 0.3, + "learning_rate": 1.764237644019767e-05, + "loss": 1.5139, + "step": 2868 + }, + { + "epoch": 0.3, + "learning_rate": 1.764001530585514e-05, + "loss": 1.4117, + "step": 2869 + }, + { + "epoch": 0.3, + "learning_rate": 1.7637653147946858e-05, + "loss": 1.4837, + "step": 2870 + }, + { + "epoch": 0.3, + "learning_rate": 1.7635289966789298e-05, + "loss": 1.4379, + "step": 2871 + }, + { + "epoch": 0.3, + "learning_rate": 1.7632925762699068e-05, + "loss": 1.4491, + "step": 2872 + }, + { + "epoch": 0.3, + "learning_rate": 1.7630560535992905e-05, + "loss": 1.4006, + "step": 2873 + }, + { + "epoch": 0.3, + "learning_rate": 1.7628194286987694e-05, + "loss": 1.5484, + "step": 2874 + }, + { + "epoch": 0.3, + "learning_rate": 1.7625827016000446e-05, + "loss": 1.4926, + "step": 2875 + }, + { + "epoch": 0.3, + "learning_rate": 1.762345872334832e-05, + "loss": 1.3909, + "step": 2876 + }, + { + "epoch": 0.3, + "learning_rate": 1.76210894093486e-05, + "loss": 1.405, + "step": 2877 + }, + { + "epoch": 0.3, + "learning_rate": 1.7618719074318718e-05, + "loss": 1.4736, + "step": 2878 + }, + { + "epoch": 0.3, + "learning_rate": 1.7616347718576238e-05, + "loss": 1.4445, + "step": 2879 + }, + { + "epoch": 0.3, + "learning_rate": 1.761397534243886e-05, + "loss": 1.4878, + "step": 2880 + }, + { + "epoch": 0.3, + "learning_rate": 1.7611601946224417e-05, + "loss": 1.4414, + "step": 2881 + }, + { + "epoch": 0.3, + "learning_rate": 1.760922753025089e-05, + "loss": 1.5657, + "step": 2882 + }, + { + "epoch": 0.3, + "learning_rate": 1.7606852094836385e-05, + "loss": 1.5008, + "step": 2883 + }, + { + "epoch": 0.3, + "learning_rate": 1.7604475640299153e-05, + "loss": 1.4922, + "step": 2884 + }, + { + "epoch": 0.3, + "learning_rate": 1.7602098166957577e-05, + "loss": 1.7451, + "step": 2885 + }, + { + "epoch": 0.3, + "learning_rate": 1.759971967513017e-05, + "loss": 1.7077, + "step": 2886 + }, + { + "epoch": 0.3, + "learning_rate": 1.75973401651356e-05, + "loss": 1.3986, + "step": 2887 + }, + { + "epoch": 0.3, + "learning_rate": 1.7594959637292656e-05, + "loss": 1.3966, + "step": 2888 + }, + { + "epoch": 0.3, + "learning_rate": 1.7592578091920264e-05, + "loss": 1.4086, + "step": 2889 + }, + { + "epoch": 0.3, + "learning_rate": 1.7590195529337495e-05, + "loss": 1.4481, + "step": 2890 + }, + { + "epoch": 0.3, + "learning_rate": 1.7587811949863548e-05, + "loss": 1.3974, + "step": 2891 + }, + { + "epoch": 0.3, + "learning_rate": 1.7585427353817758e-05, + "loss": 1.5013, + "step": 2892 + }, + { + "epoch": 0.3, + "learning_rate": 1.7583041741519608e-05, + "loss": 1.5454, + "step": 2893 + }, + { + "epoch": 0.3, + "learning_rate": 1.7580655113288708e-05, + "loss": 1.5033, + "step": 2894 + }, + { + "epoch": 0.3, + "learning_rate": 1.7578267469444793e-05, + "loss": 1.4332, + "step": 2895 + }, + { + "epoch": 0.3, + "learning_rate": 1.757587881030776e-05, + "loss": 1.4667, + "step": 2896 + }, + { + "epoch": 0.3, + "learning_rate": 1.7573489136197623e-05, + "loss": 1.4314, + "step": 2897 + }, + { + "epoch": 0.3, + "learning_rate": 1.7571098447434532e-05, + "loss": 1.4514, + "step": 2898 + }, + { + "epoch": 0.3, + "learning_rate": 1.7568706744338784e-05, + "loss": 1.4872, + "step": 2899 + }, + { + "epoch": 0.3, + "learning_rate": 1.7566314027230808e-05, + "loss": 1.4841, + "step": 2900 + }, + { + "epoch": 0.3, + "learning_rate": 1.7563920296431158e-05, + "loss": 1.3964, + "step": 2901 + }, + { + "epoch": 0.3, + "learning_rate": 1.7561525552260538e-05, + "loss": 1.4932, + "step": 2902 + }, + { + "epoch": 0.3, + "learning_rate": 1.755912979503978e-05, + "loss": 1.4153, + "step": 2903 + }, + { + "epoch": 0.3, + "learning_rate": 1.755673302508986e-05, + "loss": 1.4939, + "step": 2904 + }, + { + "epoch": 0.3, + "learning_rate": 1.755433524273187e-05, + "loss": 1.4437, + "step": 2905 + }, + { + "epoch": 0.3, + "learning_rate": 1.7551936448287067e-05, + "loss": 1.486, + "step": 2906 + }, + { + "epoch": 0.3, + "learning_rate": 1.754953664207682e-05, + "loss": 1.4362, + "step": 2907 + }, + { + "epoch": 0.3, + "learning_rate": 1.7547135824422635e-05, + "loss": 1.4954, + "step": 2908 + }, + { + "epoch": 0.31, + "learning_rate": 1.7544733995646174e-05, + "loss": 1.4552, + "step": 2909 + }, + { + "epoch": 0.31, + "learning_rate": 1.7542331156069213e-05, + "loss": 1.4654, + "step": 2910 + }, + { + "epoch": 0.31, + "learning_rate": 1.753992730601367e-05, + "loss": 1.4531, + "step": 2911 + }, + { + "epoch": 0.31, + "learning_rate": 1.75375224458016e-05, + "loss": 1.4949, + "step": 2912 + }, + { + "epoch": 0.31, + "learning_rate": 1.753511657575519e-05, + "loss": 1.3998, + "step": 2913 + }, + { + "epoch": 0.31, + "learning_rate": 1.753270969619677e-05, + "loss": 1.3904, + "step": 2914 + }, + { + "epoch": 0.31, + "learning_rate": 1.7530301807448794e-05, + "loss": 1.481, + "step": 2915 + }, + { + "epoch": 0.31, + "learning_rate": 1.7527892909833864e-05, + "loss": 1.4301, + "step": 2916 + }, + { + "epoch": 0.31, + "learning_rate": 1.7525483003674707e-05, + "loss": 1.4377, + "step": 2917 + }, + { + "epoch": 0.31, + "learning_rate": 1.7523072089294188e-05, + "loss": 1.5077, + "step": 2918 + }, + { + "epoch": 0.31, + "learning_rate": 1.752066016701531e-05, + "loss": 1.3802, + "step": 2919 + }, + { + "epoch": 0.31, + "learning_rate": 1.7518247237161205e-05, + "loss": 1.3991, + "step": 2920 + }, + { + "epoch": 0.31, + "learning_rate": 1.7515833300055146e-05, + "loss": 1.4283, + "step": 2921 + }, + { + "epoch": 0.31, + "learning_rate": 1.7513418356020535e-05, + "loss": 1.3688, + "step": 2922 + }, + { + "epoch": 0.31, + "learning_rate": 1.751100240538092e-05, + "loss": 1.4336, + "step": 2923 + }, + { + "epoch": 0.31, + "learning_rate": 1.7508585448459967e-05, + "loss": 1.4302, + "step": 2924 + }, + { + "epoch": 0.31, + "learning_rate": 1.7506167485581493e-05, + "loss": 1.4293, + "step": 2925 + }, + { + "epoch": 0.31, + "learning_rate": 1.750374851706944e-05, + "loss": 1.4262, + "step": 2926 + }, + { + "epoch": 0.31, + "learning_rate": 1.7501328543247892e-05, + "loss": 1.4128, + "step": 2927 + }, + { + "epoch": 0.31, + "learning_rate": 1.7498907564441054e-05, + "loss": 1.4258, + "step": 2928 + }, + { + "epoch": 0.31, + "learning_rate": 1.749648558097328e-05, + "loss": 1.4904, + "step": 2929 + }, + { + "epoch": 0.31, + "learning_rate": 1.749406259316906e-05, + "loss": 1.4628, + "step": 2930 + }, + { + "epoch": 0.31, + "learning_rate": 1.7491638601353004e-05, + "loss": 1.4908, + "step": 2931 + }, + { + "epoch": 0.31, + "learning_rate": 1.7489213605849867e-05, + "loss": 1.4563, + "step": 2932 + }, + { + "epoch": 0.31, + "learning_rate": 1.7486787606984533e-05, + "loss": 1.5006, + "step": 2933 + }, + { + "epoch": 0.31, + "learning_rate": 1.748436060508203e-05, + "loss": 1.424, + "step": 2934 + }, + { + "epoch": 0.31, + "learning_rate": 1.7481932600467508e-05, + "loss": 1.4136, + "step": 2935 + }, + { + "epoch": 0.31, + "learning_rate": 1.747950359346626e-05, + "loss": 1.3835, + "step": 2936 + }, + { + "epoch": 0.31, + "learning_rate": 1.747707358440371e-05, + "loss": 1.5284, + "step": 2937 + }, + { + "epoch": 0.31, + "learning_rate": 1.7474642573605418e-05, + "loss": 1.4592, + "step": 2938 + }, + { + "epoch": 0.31, + "learning_rate": 1.7472210561397075e-05, + "loss": 1.5483, + "step": 2939 + }, + { + "epoch": 0.31, + "learning_rate": 1.746977754810451e-05, + "loss": 1.521, + "step": 2940 + }, + { + "epoch": 0.31, + "learning_rate": 1.7467343534053683e-05, + "loss": 1.4276, + "step": 2941 + }, + { + "epoch": 0.31, + "learning_rate": 1.746490851957069e-05, + "loss": 1.4302, + "step": 2942 + }, + { + "epoch": 0.31, + "learning_rate": 1.746247250498176e-05, + "loss": 1.4439, + "step": 2943 + }, + { + "epoch": 0.31, + "learning_rate": 1.7460035490613255e-05, + "loss": 1.4991, + "step": 2944 + }, + { + "epoch": 0.31, + "learning_rate": 1.7457597476791674e-05, + "loss": 1.4188, + "step": 2945 + }, + { + "epoch": 0.31, + "learning_rate": 1.7455158463843648e-05, + "loss": 1.4685, + "step": 2946 + }, + { + "epoch": 0.31, + "learning_rate": 1.745271845209594e-05, + "loss": 1.3811, + "step": 2947 + }, + { + "epoch": 0.31, + "learning_rate": 1.7450277441875454e-05, + "loss": 1.4869, + "step": 2948 + }, + { + "epoch": 0.31, + "learning_rate": 1.7447835433509218e-05, + "loss": 1.5001, + "step": 2949 + }, + { + "epoch": 0.31, + "learning_rate": 1.74453924273244e-05, + "loss": 1.4757, + "step": 2950 + }, + { + "epoch": 0.31, + "learning_rate": 1.74429484236483e-05, + "loss": 1.5072, + "step": 2951 + }, + { + "epoch": 0.31, + "learning_rate": 1.744050342280835e-05, + "loss": 1.4242, + "step": 2952 + }, + { + "epoch": 0.31, + "learning_rate": 1.743805742513212e-05, + "loss": 1.4462, + "step": 2953 + }, + { + "epoch": 0.31, + "learning_rate": 1.743561043094731e-05, + "loss": 1.6815, + "step": 2954 + }, + { + "epoch": 0.31, + "learning_rate": 1.7433162440581755e-05, + "loss": 1.427, + "step": 2955 + }, + { + "epoch": 0.31, + "learning_rate": 1.7430713454363423e-05, + "loss": 1.2933, + "step": 2956 + }, + { + "epoch": 0.31, + "learning_rate": 1.742826347262041e-05, + "loss": 1.4247, + "step": 2957 + }, + { + "epoch": 0.31, + "learning_rate": 1.7425812495680955e-05, + "loss": 1.399, + "step": 2958 + }, + { + "epoch": 0.31, + "learning_rate": 1.742336052387343e-05, + "loss": 1.4818, + "step": 2959 + }, + { + "epoch": 0.31, + "learning_rate": 1.742090755752633e-05, + "loss": 1.3839, + "step": 2960 + }, + { + "epoch": 0.31, + "learning_rate": 1.741845359696829e-05, + "loss": 1.4669, + "step": 2961 + }, + { + "epoch": 0.31, + "learning_rate": 1.741599864252808e-05, + "loss": 1.468, + "step": 2962 + }, + { + "epoch": 0.31, + "learning_rate": 1.74135426945346e-05, + "loss": 1.4135, + "step": 2963 + }, + { + "epoch": 0.31, + "learning_rate": 1.7411085753316882e-05, + "loss": 1.5899, + "step": 2964 + }, + { + "epoch": 0.31, + "learning_rate": 1.74086278192041e-05, + "loss": 1.6115, + "step": 2965 + }, + { + "epoch": 0.31, + "learning_rate": 1.740616889252554e-05, + "loss": 1.3988, + "step": 2966 + }, + { + "epoch": 0.31, + "learning_rate": 1.740370897361065e-05, + "loss": 1.5001, + "step": 2967 + }, + { + "epoch": 0.31, + "learning_rate": 1.740124806278899e-05, + "loss": 1.459, + "step": 2968 + }, + { + "epoch": 0.31, + "learning_rate": 1.7398786160390258e-05, + "loss": 1.4489, + "step": 2969 + }, + { + "epoch": 0.31, + "learning_rate": 1.7396323266744283e-05, + "loss": 1.4397, + "step": 2970 + }, + { + "epoch": 0.31, + "learning_rate": 1.7393859382181033e-05, + "loss": 1.4687, + "step": 2971 + }, + { + "epoch": 0.31, + "learning_rate": 1.7391394507030606e-05, + "loss": 1.4495, + "step": 2972 + }, + { + "epoch": 0.31, + "learning_rate": 1.738892864162323e-05, + "loss": 1.4745, + "step": 2973 + }, + { + "epoch": 0.31, + "learning_rate": 1.7386461786289274e-05, + "loss": 1.3943, + "step": 2974 + }, + { + "epoch": 0.31, + "learning_rate": 1.738399394135922e-05, + "loss": 1.4595, + "step": 2975 + }, + { + "epoch": 0.31, + "learning_rate": 1.738152510716371e-05, + "loss": 1.4023, + "step": 2976 + }, + { + "epoch": 0.31, + "learning_rate": 1.7379055284033493e-05, + "loss": 1.3938, + "step": 2977 + }, + { + "epoch": 0.31, + "learning_rate": 1.7376584472299468e-05, + "loss": 1.4576, + "step": 2978 + }, + { + "epoch": 0.31, + "learning_rate": 1.737411267229266e-05, + "loss": 1.424, + "step": 2979 + }, + { + "epoch": 0.31, + "learning_rate": 1.7371639884344225e-05, + "loss": 1.4224, + "step": 2980 + }, + { + "epoch": 0.31, + "learning_rate": 1.736916610878545e-05, + "loss": 1.4228, + "step": 2981 + }, + { + "epoch": 0.31, + "learning_rate": 1.7366691345947768e-05, + "loss": 1.5021, + "step": 2982 + }, + { + "epoch": 0.31, + "learning_rate": 1.736421559616272e-05, + "loss": 1.3589, + "step": 2983 + }, + { + "epoch": 0.31, + "learning_rate": 1.7361738859762007e-05, + "loss": 1.4748, + "step": 2984 + }, + { + "epoch": 0.31, + "learning_rate": 1.735926113707743e-05, + "loss": 1.3974, + "step": 2985 + }, + { + "epoch": 0.31, + "eval_loss": 1.4849082231521606, + "eval_runtime": 77.3271, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2985 + }, + { + "epoch": 0.31, + "learning_rate": 1.735678242844096e-05, + "loss": 1.392, + "step": 2986 + }, + { + "epoch": 0.31, + "learning_rate": 1.735430273418467e-05, + "loss": 1.4277, + "step": 2987 + }, + { + "epoch": 0.31, + "learning_rate": 1.735182205464077e-05, + "loss": 1.4216, + "step": 2988 + }, + { + "epoch": 0.31, + "learning_rate": 1.7349340390141617e-05, + "loss": 1.4546, + "step": 2989 + }, + { + "epoch": 0.31, + "learning_rate": 1.734685774101969e-05, + "loss": 1.4264, + "step": 2990 + }, + { + "epoch": 0.31, + "learning_rate": 1.7344374107607593e-05, + "loss": 1.4307, + "step": 2991 + }, + { + "epoch": 0.31, + "learning_rate": 1.7341889490238076e-05, + "loss": 1.4266, + "step": 2992 + }, + { + "epoch": 0.31, + "learning_rate": 1.7339403889244008e-05, + "loss": 1.4486, + "step": 2993 + }, + { + "epoch": 0.31, + "learning_rate": 1.7336917304958403e-05, + "loss": 1.4345, + "step": 2994 + }, + { + "epoch": 0.31, + "learning_rate": 1.7334429737714395e-05, + "loss": 1.476, + "step": 2995 + }, + { + "epoch": 0.31, + "learning_rate": 1.7331941187845248e-05, + "loss": 1.5148, + "step": 2996 + }, + { + "epoch": 0.31, + "learning_rate": 1.7329451655684372e-05, + "loss": 1.4026, + "step": 2997 + }, + { + "epoch": 0.31, + "learning_rate": 1.7326961141565303e-05, + "loss": 1.3935, + "step": 2998 + }, + { + "epoch": 0.31, + "learning_rate": 1.73244696458217e-05, + "loss": 1.4483, + "step": 2999 + }, + { + "epoch": 0.31, + "learning_rate": 1.7321977168787356e-05, + "loss": 1.5197, + "step": 3000 + }, + { + "epoch": 0.31, + "learning_rate": 1.7319483710796208e-05, + "loss": 1.4648, + "step": 3001 + }, + { + "epoch": 0.31, + "learning_rate": 1.7316989272182308e-05, + "loss": 1.4171, + "step": 3002 + }, + { + "epoch": 0.31, + "learning_rate": 1.731449385327985e-05, + "loss": 1.4541, + "step": 3003 + }, + { + "epoch": 0.32, + "learning_rate": 1.731199745442316e-05, + "loss": 1.4605, + "step": 3004 + }, + { + "epoch": 0.32, + "learning_rate": 1.7309500075946683e-05, + "loss": 1.5122, + "step": 3005 + }, + { + "epoch": 0.32, + "learning_rate": 1.7307001718185007e-05, + "loss": 1.5243, + "step": 3006 + }, + { + "epoch": 0.32, + "learning_rate": 1.7304502381472844e-05, + "loss": 1.4997, + "step": 3007 + }, + { + "epoch": 0.32, + "learning_rate": 1.730200206614505e-05, + "loss": 1.4891, + "step": 3008 + }, + { + "epoch": 0.32, + "learning_rate": 1.72995007725366e-05, + "loss": 1.4376, + "step": 3009 + }, + { + "epoch": 0.32, + "learning_rate": 1.7296998500982595e-05, + "loss": 1.4403, + "step": 3010 + }, + { + "epoch": 0.32, + "learning_rate": 1.7294495251818285e-05, + "loss": 1.5153, + "step": 3011 + }, + { + "epoch": 0.32, + "learning_rate": 1.729199102537904e-05, + "loss": 1.4996, + "step": 3012 + }, + { + "epoch": 0.32, + "learning_rate": 1.7289485822000356e-05, + "loss": 1.5302, + "step": 3013 + }, + { + "epoch": 0.32, + "learning_rate": 1.7286979642017867e-05, + "loss": 1.5641, + "step": 3014 + }, + { + "epoch": 0.32, + "learning_rate": 1.728447248576734e-05, + "loss": 1.438, + "step": 3015 + }, + { + "epoch": 0.32, + "learning_rate": 1.7281964353584674e-05, + "loss": 1.4796, + "step": 3016 + }, + { + "epoch": 0.32, + "learning_rate": 1.727945524580588e-05, + "loss": 1.4413, + "step": 3017 + }, + { + "epoch": 0.32, + "learning_rate": 1.727694516276713e-05, + "loss": 1.3966, + "step": 3018 + }, + { + "epoch": 0.32, + "learning_rate": 1.72744341048047e-05, + "loss": 1.5267, + "step": 3019 + }, + { + "epoch": 0.32, + "learning_rate": 1.727192207225501e-05, + "loss": 1.4284, + "step": 3020 + }, + { + "epoch": 0.32, + "learning_rate": 1.726940906545461e-05, + "loss": 1.5137, + "step": 3021 + }, + { + "epoch": 0.32, + "learning_rate": 1.7266895084740173e-05, + "loss": 1.3966, + "step": 3022 + }, + { + "epoch": 0.32, + "learning_rate": 1.7264380130448514e-05, + "loss": 1.4156, + "step": 3023 + }, + { + "epoch": 0.32, + "learning_rate": 1.726186420291657e-05, + "loss": 1.4644, + "step": 3024 + }, + { + "epoch": 0.32, + "learning_rate": 1.725934730248141e-05, + "loss": 1.4768, + "step": 3025 + }, + { + "epoch": 0.32, + "learning_rate": 1.7256829429480233e-05, + "loss": 1.4428, + "step": 3026 + }, + { + "epoch": 0.32, + "learning_rate": 1.7254310584250373e-05, + "loss": 1.4495, + "step": 3027 + }, + { + "epoch": 0.32, + "learning_rate": 1.725179076712929e-05, + "loss": 1.3867, + "step": 3028 + }, + { + "epoch": 0.32, + "learning_rate": 1.7249269978454567e-05, + "loss": 1.5011, + "step": 3029 + }, + { + "epoch": 0.32, + "learning_rate": 1.7246748218563937e-05, + "loss": 1.3916, + "step": 3030 + }, + { + "epoch": 0.32, + "learning_rate": 1.7244225487795238e-05, + "loss": 1.4984, + "step": 3031 + }, + { + "epoch": 0.32, + "learning_rate": 1.7241701786486464e-05, + "loss": 1.5776, + "step": 3032 + }, + { + "epoch": 0.32, + "learning_rate": 1.7239177114975717e-05, + "loss": 1.5018, + "step": 3033 + }, + { + "epoch": 0.32, + "learning_rate": 1.7236651473601244e-05, + "loss": 1.5042, + "step": 3034 + }, + { + "epoch": 0.32, + "learning_rate": 1.723412486270141e-05, + "loss": 1.4636, + "step": 3035 + }, + { + "epoch": 0.32, + "learning_rate": 1.723159728261472e-05, + "loss": 1.5612, + "step": 3036 + }, + { + "epoch": 0.32, + "learning_rate": 1.7229068733679803e-05, + "loss": 1.4399, + "step": 3037 + }, + { + "epoch": 0.32, + "learning_rate": 1.7226539216235424e-05, + "loss": 1.5635, + "step": 3038 + }, + { + "epoch": 0.32, + "learning_rate": 1.7224008730620468e-05, + "loss": 1.4329, + "step": 3039 + }, + { + "epoch": 0.32, + "learning_rate": 1.7221477277173956e-05, + "loss": 1.4886, + "step": 3040 + }, + { + "epoch": 0.32, + "learning_rate": 1.721894485623504e-05, + "loss": 1.4741, + "step": 3041 + }, + { + "epoch": 0.32, + "learning_rate": 1.7216411468143e-05, + "loss": 1.4678, + "step": 3042 + }, + { + "epoch": 0.32, + "learning_rate": 1.721387711323724e-05, + "loss": 1.4758, + "step": 3043 + }, + { + "epoch": 0.32, + "learning_rate": 1.72113417918573e-05, + "loss": 1.441, + "step": 3044 + }, + { + "epoch": 0.32, + "learning_rate": 1.7208805504342855e-05, + "loss": 1.4328, + "step": 3045 + }, + { + "epoch": 0.32, + "learning_rate": 1.720626825103369e-05, + "loss": 1.4254, + "step": 3046 + }, + { + "epoch": 0.32, + "learning_rate": 1.7203730032269744e-05, + "loss": 1.4462, + "step": 3047 + }, + { + "epoch": 0.32, + "learning_rate": 1.7201190848391066e-05, + "loss": 1.4826, + "step": 3048 + }, + { + "epoch": 0.32, + "learning_rate": 1.719865069973784e-05, + "loss": 1.4215, + "step": 3049 + }, + { + "epoch": 0.32, + "learning_rate": 1.7196109586650385e-05, + "loss": 1.4291, + "step": 3050 + }, + { + "epoch": 0.32, + "learning_rate": 1.7193567509469146e-05, + "loss": 1.5005, + "step": 3051 + }, + { + "epoch": 0.32, + "learning_rate": 1.719102446853469e-05, + "loss": 1.4216, + "step": 3052 + }, + { + "epoch": 0.32, + "learning_rate": 1.7188480464187725e-05, + "loss": 1.4349, + "step": 3053 + }, + { + "epoch": 0.32, + "learning_rate": 1.718593549676908e-05, + "loss": 1.4784, + "step": 3054 + }, + { + "epoch": 0.32, + "learning_rate": 1.7183389566619714e-05, + "loss": 1.4325, + "step": 3055 + }, + { + "epoch": 0.32, + "learning_rate": 1.7180842674080717e-05, + "loss": 1.5387, + "step": 3056 + }, + { + "epoch": 0.32, + "learning_rate": 1.717829481949331e-05, + "loss": 1.655, + "step": 3057 + }, + { + "epoch": 0.32, + "learning_rate": 1.717574600319883e-05, + "loss": 1.4623, + "step": 3058 + }, + { + "epoch": 0.32, + "learning_rate": 1.7173196225538768e-05, + "loss": 1.4646, + "step": 3059 + }, + { + "epoch": 0.32, + "learning_rate": 1.717064548685472e-05, + "loss": 1.4641, + "step": 3060 + }, + { + "epoch": 0.32, + "learning_rate": 1.7168093787488418e-05, + "loss": 1.4033, + "step": 3061 + }, + { + "epoch": 0.32, + "learning_rate": 1.7165541127781726e-05, + "loss": 1.4085, + "step": 3062 + }, + { + "epoch": 0.32, + "learning_rate": 1.716298750807664e-05, + "loss": 1.387, + "step": 3063 + }, + { + "epoch": 0.32, + "learning_rate": 1.7160432928715272e-05, + "loss": 1.4197, + "step": 3064 + }, + { + "epoch": 0.32, + "learning_rate": 1.7157877390039872e-05, + "loss": 1.4883, + "step": 3065 + }, + { + "epoch": 0.32, + "learning_rate": 1.7155320892392818e-05, + "loss": 1.4865, + "step": 3066 + }, + { + "epoch": 0.32, + "learning_rate": 1.715276343611662e-05, + "loss": 1.4532, + "step": 3067 + }, + { + "epoch": 0.32, + "learning_rate": 1.71502050215539e-05, + "loss": 1.3991, + "step": 3068 + }, + { + "epoch": 0.32, + "learning_rate": 1.7147645649047424e-05, + "loss": 1.4318, + "step": 3069 + }, + { + "epoch": 0.32, + "learning_rate": 1.714508531894009e-05, + "loss": 1.3616, + "step": 3070 + }, + { + "epoch": 0.32, + "learning_rate": 1.7142524031574904e-05, + "loss": 1.4481, + "step": 3071 + }, + { + "epoch": 0.32, + "learning_rate": 1.7139961787295022e-05, + "loss": 1.3897, + "step": 3072 + }, + { + "epoch": 0.32, + "learning_rate": 1.7137398586443716e-05, + "loss": 1.3128, + "step": 3073 + }, + { + "epoch": 0.32, + "learning_rate": 1.713483442936439e-05, + "loss": 1.4481, + "step": 3074 + }, + { + "epoch": 0.32, + "learning_rate": 1.713226931640057e-05, + "loss": 1.5374, + "step": 3075 + }, + { + "epoch": 0.32, + "learning_rate": 1.7129703247895923e-05, + "loss": 1.4247, + "step": 3076 + }, + { + "epoch": 0.32, + "learning_rate": 1.712713622419423e-05, + "loss": 1.4098, + "step": 3077 + }, + { + "epoch": 0.32, + "learning_rate": 1.7124568245639414e-05, + "loss": 1.4558, + "step": 3078 + }, + { + "epoch": 0.32, + "learning_rate": 1.7121999312575507e-05, + "loss": 1.4484, + "step": 3079 + }, + { + "epoch": 0.32, + "learning_rate": 1.711942942534669e-05, + "loss": 1.4236, + "step": 3080 + }, + { + "epoch": 0.32, + "learning_rate": 1.7116858584297253e-05, + "loss": 1.613, + "step": 3081 + }, + { + "epoch": 0.32, + "learning_rate": 1.711428678977163e-05, + "loss": 1.4503, + "step": 3082 + }, + { + "epoch": 0.32, + "learning_rate": 1.7111714042114376e-05, + "loss": 1.4072, + "step": 3083 + }, + { + "epoch": 0.32, + "learning_rate": 1.7109140341670168e-05, + "loss": 1.5999, + "step": 3084 + }, + { + "epoch": 0.32, + "learning_rate": 1.7106565688783815e-05, + "loss": 1.4129, + "step": 3085 + }, + { + "epoch": 0.32, + "learning_rate": 1.710399008380026e-05, + "loss": 1.3973, + "step": 3086 + }, + { + "epoch": 0.32, + "learning_rate": 1.710141352706456e-05, + "loss": 1.4292, + "step": 3087 + }, + { + "epoch": 0.32, + "learning_rate": 1.709883601892192e-05, + "loss": 1.4372, + "step": 3088 + }, + { + "epoch": 0.32, + "learning_rate": 1.7096257559717647e-05, + "loss": 1.4924, + "step": 3089 + }, + { + "epoch": 0.32, + "learning_rate": 1.7093678149797196e-05, + "loss": 1.4222, + "step": 3090 + }, + { + "epoch": 0.32, + "learning_rate": 1.7091097789506137e-05, + "loss": 1.4797, + "step": 3091 + }, + { + "epoch": 0.32, + "learning_rate": 1.7088516479190175e-05, + "loss": 1.4738, + "step": 3092 + }, + { + "epoch": 0.32, + "learning_rate": 1.708593421919514e-05, + "loss": 1.5371, + "step": 3093 + }, + { + "epoch": 0.32, + "learning_rate": 1.7083351009866988e-05, + "loss": 1.3802, + "step": 3094 + }, + { + "epoch": 0.32, + "learning_rate": 1.7080766851551795e-05, + "loss": 1.4292, + "step": 3095 + }, + { + "epoch": 0.32, + "learning_rate": 1.707818174459578e-05, + "loss": 1.4478, + "step": 3096 + }, + { + "epoch": 0.32, + "learning_rate": 1.7075595689345285e-05, + "loss": 1.4619, + "step": 3097 + }, + { + "epoch": 0.32, + "learning_rate": 1.7073008686146763e-05, + "loss": 1.4603, + "step": 3098 + }, + { + "epoch": 0.32, + "learning_rate": 1.7070420735346815e-05, + "loss": 1.4548, + "step": 3099 + }, + { + "epoch": 0.33, + "learning_rate": 1.7067831837292157e-05, + "loss": 1.3638, + "step": 3100 + }, + { + "epoch": 0.33, + "learning_rate": 1.7065241992329634e-05, + "loss": 1.4284, + "step": 3101 + }, + { + "epoch": 0.33, + "learning_rate": 1.7062651200806217e-05, + "loss": 1.386, + "step": 3102 + }, + { + "epoch": 0.33, + "learning_rate": 1.7060059463069013e-05, + "loss": 1.5483, + "step": 3103 + }, + { + "epoch": 0.33, + "learning_rate": 1.705746677946524e-05, + "loss": 1.4963, + "step": 3104 + }, + { + "epoch": 0.33, + "learning_rate": 1.7054873150342257e-05, + "loss": 1.4539, + "step": 3105 + }, + { + "epoch": 0.33, + "learning_rate": 1.705227857604754e-05, + "loss": 1.4361, + "step": 3106 + }, + { + "epoch": 0.33, + "learning_rate": 1.7049683056928695e-05, + "loss": 1.3735, + "step": 3107 + }, + { + "epoch": 0.33, + "learning_rate": 1.7047086593333454e-05, + "loss": 1.4324, + "step": 3108 + }, + { + "epoch": 0.33, + "learning_rate": 1.7044489185609685e-05, + "loss": 1.5037, + "step": 3109 + }, + { + "epoch": 0.33, + "learning_rate": 1.704189083410536e-05, + "loss": 1.3913, + "step": 3110 + }, + { + "epoch": 0.33, + "learning_rate": 1.7039291539168604e-05, + "loss": 1.3233, + "step": 3111 + }, + { + "epoch": 0.33, + "learning_rate": 1.703669130114765e-05, + "loss": 1.4897, + "step": 3112 + }, + { + "epoch": 0.33, + "learning_rate": 1.7034090120390862e-05, + "loss": 1.4843, + "step": 3113 + }, + { + "epoch": 0.33, + "learning_rate": 1.7031487997246735e-05, + "loss": 1.3674, + "step": 3114 + }, + { + "epoch": 0.33, + "learning_rate": 1.7028884932063883e-05, + "loss": 1.4475, + "step": 3115 + }, + { + "epoch": 0.33, + "learning_rate": 1.702628092519105e-05, + "loss": 1.4134, + "step": 3116 + }, + { + "epoch": 0.33, + "learning_rate": 1.7023675976977108e-05, + "loss": 1.4484, + "step": 3117 + }, + { + "epoch": 0.33, + "learning_rate": 1.702107008777106e-05, + "loss": 1.407, + "step": 3118 + }, + { + "epoch": 0.33, + "learning_rate": 1.7018463257922005e-05, + "loss": 1.5443, + "step": 3119 + }, + { + "epoch": 0.33, + "learning_rate": 1.701585548777922e-05, + "loss": 1.4548, + "step": 3120 + }, + { + "epoch": 0.33, + "learning_rate": 1.7013246777692063e-05, + "loss": 1.4252, + "step": 3121 + }, + { + "epoch": 0.33, + "learning_rate": 1.7010637128010037e-05, + "loss": 1.3748, + "step": 3122 + }, + { + "epoch": 0.33, + "learning_rate": 1.7008026539082767e-05, + "loss": 1.3804, + "step": 3123 + }, + { + "epoch": 0.33, + "learning_rate": 1.7005415011260008e-05, + "loss": 1.4203, + "step": 3124 + }, + { + "epoch": 0.33, + "learning_rate": 1.7002802544891634e-05, + "loss": 1.4195, + "step": 3125 + }, + { + "epoch": 0.33, + "learning_rate": 1.700018914032765e-05, + "loss": 1.4188, + "step": 3126 + }, + { + "epoch": 0.33, + "learning_rate": 1.699757479791819e-05, + "loss": 1.3884, + "step": 3127 + }, + { + "epoch": 0.33, + "learning_rate": 1.6994959518013502e-05, + "loss": 1.4111, + "step": 3128 + }, + { + "epoch": 0.33, + "learning_rate": 1.6992343300963963e-05, + "loss": 1.5452, + "step": 3129 + }, + { + "epoch": 0.33, + "learning_rate": 1.6989726147120087e-05, + "loss": 1.4097, + "step": 3130 + }, + { + "epoch": 0.33, + "learning_rate": 1.6987108056832506e-05, + "loss": 1.481, + "step": 3131 + }, + { + "epoch": 0.33, + "learning_rate": 1.6984489030451973e-05, + "loss": 1.4505, + "step": 3132 + }, + { + "epoch": 0.33, + "learning_rate": 1.6981869068329368e-05, + "loss": 1.4281, + "step": 3133 + }, + { + "epoch": 0.33, + "learning_rate": 1.69792481708157e-05, + "loss": 1.4555, + "step": 3134 + }, + { + "epoch": 0.33, + "learning_rate": 1.6976626338262103e-05, + "loss": 1.4525, + "step": 3135 + }, + { + "epoch": 0.33, + "learning_rate": 1.6974003571019837e-05, + "loss": 1.3765, + "step": 3136 + }, + { + "epoch": 0.33, + "learning_rate": 1.6971379869440286e-05, + "loss": 1.3998, + "step": 3137 + }, + { + "epoch": 0.33, + "learning_rate": 1.696875523387495e-05, + "loss": 1.5103, + "step": 3138 + }, + { + "epoch": 0.33, + "learning_rate": 1.6966129664675474e-05, + "loss": 1.427, + "step": 3139 + }, + { + "epoch": 0.33, + "learning_rate": 1.6963503162193612e-05, + "loss": 1.4362, + "step": 3140 + }, + { + "epoch": 0.33, + "learning_rate": 1.6960875726781246e-05, + "loss": 1.4073, + "step": 3141 + }, + { + "epoch": 0.33, + "learning_rate": 1.6958247358790388e-05, + "loss": 1.4014, + "step": 3142 + }, + { + "epoch": 0.33, + "learning_rate": 1.6955618058573165e-05, + "loss": 1.4244, + "step": 3143 + }, + { + "epoch": 0.33, + "learning_rate": 1.6952987826481847e-05, + "loss": 1.47, + "step": 3144 + }, + { + "epoch": 0.33, + "learning_rate": 1.6950356662868814e-05, + "loss": 1.5112, + "step": 3145 + }, + { + "epoch": 0.33, + "learning_rate": 1.6947724568086562e-05, + "loss": 1.3398, + "step": 3146 + }, + { + "epoch": 0.33, + "learning_rate": 1.694509154248774e-05, + "loss": 1.4584, + "step": 3147 + }, + { + "epoch": 0.33, + "learning_rate": 1.69424575864251e-05, + "loss": 1.4383, + "step": 3148 + }, + { + "epoch": 0.33, + "learning_rate": 1.6939822700251523e-05, + "loss": 1.3869, + "step": 3149 + }, + { + "epoch": 0.33, + "learning_rate": 1.6937186884320015e-05, + "loss": 1.4453, + "step": 3150 + }, + { + "epoch": 0.33, + "learning_rate": 1.6934550138983713e-05, + "loss": 1.3355, + "step": 3151 + }, + { + "epoch": 0.33, + "learning_rate": 1.6931912464595866e-05, + "loss": 1.5573, + "step": 3152 + }, + { + "epoch": 0.33, + "learning_rate": 1.6929273861509865e-05, + "loss": 1.439, + "step": 3153 + }, + { + "epoch": 0.33, + "learning_rate": 1.6926634330079203e-05, + "loss": 1.6079, + "step": 3154 + }, + { + "epoch": 0.33, + "learning_rate": 1.692399387065752e-05, + "loss": 1.6973, + "step": 3155 + }, + { + "epoch": 0.33, + "learning_rate": 1.692135248359856e-05, + "loss": 1.3769, + "step": 3156 + }, + { + "epoch": 0.33, + "learning_rate": 1.6918710169256206e-05, + "loss": 1.4454, + "step": 3157 + }, + { + "epoch": 0.33, + "learning_rate": 1.691606692798446e-05, + "loss": 1.4495, + "step": 3158 + }, + { + "epoch": 0.33, + "learning_rate": 1.691342276013745e-05, + "loss": 1.4292, + "step": 3159 + }, + { + "epoch": 0.33, + "learning_rate": 1.691077766606942e-05, + "loss": 1.4405, + "step": 3160 + }, + { + "epoch": 0.33, + "learning_rate": 1.6908131646134757e-05, + "loss": 1.3683, + "step": 3161 + }, + { + "epoch": 0.33, + "learning_rate": 1.690548470068795e-05, + "loss": 1.4731, + "step": 3162 + }, + { + "epoch": 0.33, + "learning_rate": 1.690283683008362e-05, + "loss": 1.4323, + "step": 3163 + }, + { + "epoch": 0.33, + "learning_rate": 1.6900188034676518e-05, + "loss": 1.5133, + "step": 3164 + }, + { + "epoch": 0.33, + "learning_rate": 1.6897538314821516e-05, + "loss": 1.5529, + "step": 3165 + }, + { + "epoch": 0.33, + "learning_rate": 1.6894887670873605e-05, + "loss": 1.4427, + "step": 3166 + }, + { + "epoch": 0.33, + "learning_rate": 1.6892236103187904e-05, + "loss": 1.4344, + "step": 3167 + }, + { + "epoch": 0.33, + "learning_rate": 1.6889583612119657e-05, + "loss": 1.4291, + "step": 3168 + }, + { + "epoch": 0.33, + "learning_rate": 1.6886930198024226e-05, + "loss": 1.4683, + "step": 3169 + }, + { + "epoch": 0.33, + "learning_rate": 1.6884275861257106e-05, + "loss": 1.4442, + "step": 3170 + }, + { + "epoch": 0.33, + "learning_rate": 1.6881620602173905e-05, + "loss": 1.4509, + "step": 3171 + }, + { + "epoch": 0.33, + "learning_rate": 1.6878964421130362e-05, + "loss": 1.5113, + "step": 3172 + }, + { + "epoch": 0.33, + "learning_rate": 1.6876307318482334e-05, + "loss": 1.4261, + "step": 3173 + }, + { + "epoch": 0.33, + "learning_rate": 1.6873649294585805e-05, + "loss": 1.445, + "step": 3174 + }, + { + "epoch": 0.33, + "learning_rate": 1.6870990349796886e-05, + "loss": 1.4603, + "step": 3175 + }, + { + "epoch": 0.33, + "learning_rate": 1.68683304844718e-05, + "loss": 1.41, + "step": 3176 + }, + { + "epoch": 0.33, + "learning_rate": 1.686566969896691e-05, + "loss": 1.4018, + "step": 3177 + }, + { + "epoch": 0.33, + "learning_rate": 1.6863007993638687e-05, + "loss": 1.422, + "step": 3178 + }, + { + "epoch": 0.33, + "learning_rate": 1.6860345368843727e-05, + "loss": 1.4412, + "step": 3179 + }, + { + "epoch": 0.33, + "learning_rate": 1.6857681824938768e-05, + "loss": 1.5411, + "step": 3180 + }, + { + "epoch": 0.33, + "learning_rate": 1.685501736228064e-05, + "loss": 1.4416, + "step": 3181 + }, + { + "epoch": 0.33, + "learning_rate": 1.685235198122632e-05, + "loss": 1.5113, + "step": 3182 + }, + { + "epoch": 0.33, + "learning_rate": 1.6849685682132903e-05, + "loss": 1.423, + "step": 3183 + }, + { + "epoch": 0.33, + "learning_rate": 1.68470184653576e-05, + "loss": 1.404, + "step": 3184 + }, + { + "epoch": 0.33, + "eval_loss": 1.4771089553833008, + "eval_runtime": 77.4034, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3184 + }, + { + "epoch": 0.33, + "learning_rate": 1.6844350331257747e-05, + "loss": 1.4624, + "step": 3185 + }, + { + "epoch": 0.33, + "learning_rate": 1.6841681280190814e-05, + "loss": 1.4306, + "step": 3186 + }, + { + "epoch": 0.33, + "learning_rate": 1.683901131251438e-05, + "loss": 1.42, + "step": 3187 + }, + { + "epoch": 0.33, + "learning_rate": 1.6836340428586155e-05, + "loss": 1.4787, + "step": 3188 + }, + { + "epoch": 0.33, + "learning_rate": 1.6833668628763965e-05, + "loss": 1.3485, + "step": 3189 + }, + { + "epoch": 0.33, + "learning_rate": 1.683099591340576e-05, + "loss": 1.3674, + "step": 3190 + }, + { + "epoch": 0.33, + "learning_rate": 1.6828322282869627e-05, + "loss": 1.5187, + "step": 3191 + }, + { + "epoch": 0.33, + "learning_rate": 1.682564773751375e-05, + "loss": 1.4847, + "step": 3192 + }, + { + "epoch": 0.33, + "learning_rate": 1.682297227769646e-05, + "loss": 1.4815, + "step": 3193 + }, + { + "epoch": 0.33, + "learning_rate": 1.682029590377619e-05, + "loss": 1.4281, + "step": 3194 + }, + { + "epoch": 0.34, + "learning_rate": 1.6817618616111517e-05, + "loss": 1.4734, + "step": 3195 + }, + { + "epoch": 0.34, + "learning_rate": 1.681494041506112e-05, + "loss": 1.4861, + "step": 3196 + }, + { + "epoch": 0.34, + "learning_rate": 1.6812261300983808e-05, + "loss": 1.4372, + "step": 3197 + }, + { + "epoch": 0.34, + "learning_rate": 1.680958127423852e-05, + "loss": 1.4396, + "step": 3198 + }, + { + "epoch": 0.34, + "learning_rate": 1.680690033518431e-05, + "loss": 1.4225, + "step": 3199 + }, + { + "epoch": 0.34, + "learning_rate": 1.6804218484180347e-05, + "loss": 1.4925, + "step": 3200 + }, + { + "epoch": 0.34, + "learning_rate": 1.6801535721585942e-05, + "loss": 1.4306, + "step": 3201 + }, + { + "epoch": 0.34, + "learning_rate": 1.6798852047760506e-05, + "loss": 1.4298, + "step": 3202 + }, + { + "epoch": 0.34, + "learning_rate": 1.6796167463063588e-05, + "loss": 1.4725, + "step": 3203 + }, + { + "epoch": 0.34, + "learning_rate": 1.679348196785485e-05, + "loss": 1.4648, + "step": 3204 + }, + { + "epoch": 0.34, + "learning_rate": 1.6790795562494087e-05, + "loss": 1.4152, + "step": 3205 + }, + { + "epoch": 0.34, + "learning_rate": 1.6788108247341198e-05, + "loss": 1.4637, + "step": 3206 + }, + { + "epoch": 0.34, + "learning_rate": 1.6785420022756216e-05, + "loss": 1.4077, + "step": 3207 + }, + { + "epoch": 0.34, + "learning_rate": 1.67827308890993e-05, + "loss": 1.4585, + "step": 3208 + }, + { + "epoch": 0.34, + "learning_rate": 1.678004084673072e-05, + "loss": 1.3747, + "step": 3209 + }, + { + "epoch": 0.34, + "learning_rate": 1.6777349896010876e-05, + "loss": 1.4264, + "step": 3210 + }, + { + "epoch": 0.34, + "learning_rate": 1.677465803730028e-05, + "loss": 1.4178, + "step": 3211 + }, + { + "epoch": 0.34, + "learning_rate": 1.6771965270959584e-05, + "loss": 1.3876, + "step": 3212 + }, + { + "epoch": 0.34, + "learning_rate": 1.6769271597349538e-05, + "loss": 1.4658, + "step": 3213 + }, + { + "epoch": 0.34, + "learning_rate": 1.6766577016831026e-05, + "loss": 1.3968, + "step": 3214 + }, + { + "epoch": 0.34, + "learning_rate": 1.676388152976506e-05, + "loss": 1.5015, + "step": 3215 + }, + { + "epoch": 0.34, + "learning_rate": 1.6761185136512756e-05, + "loss": 1.4121, + "step": 3216 + }, + { + "epoch": 0.34, + "learning_rate": 1.675848783743537e-05, + "loss": 1.4146, + "step": 3217 + }, + { + "epoch": 0.34, + "learning_rate": 1.675578963289427e-05, + "loss": 1.4113, + "step": 3218 + }, + { + "epoch": 0.34, + "learning_rate": 1.6753090523250937e-05, + "loss": 1.4048, + "step": 3219 + }, + { + "epoch": 0.34, + "learning_rate": 1.6750390508866994e-05, + "loss": 1.4959, + "step": 3220 + }, + { + "epoch": 0.34, + "learning_rate": 1.6747689590104167e-05, + "loss": 1.4445, + "step": 3221 + }, + { + "epoch": 0.34, + "learning_rate": 1.6744987767324312e-05, + "loss": 1.4611, + "step": 3222 + }, + { + "epoch": 0.34, + "learning_rate": 1.67422850408894e-05, + "loss": 1.4141, + "step": 3223 + }, + { + "epoch": 0.34, + "learning_rate": 1.6739581411161535e-05, + "loss": 1.4218, + "step": 3224 + }, + { + "epoch": 0.34, + "learning_rate": 1.6736876878502925e-05, + "loss": 1.4266, + "step": 3225 + }, + { + "epoch": 0.34, + "learning_rate": 1.6734171443275913e-05, + "loss": 1.4941, + "step": 3226 + }, + { + "epoch": 0.34, + "learning_rate": 1.6731465105842955e-05, + "loss": 1.4294, + "step": 3227 + }, + { + "epoch": 0.34, + "learning_rate": 1.6728757866566635e-05, + "loss": 1.4189, + "step": 3228 + }, + { + "epoch": 0.34, + "learning_rate": 1.6726049725809647e-05, + "loss": 1.4713, + "step": 3229 + }, + { + "epoch": 0.34, + "learning_rate": 1.6723340683934818e-05, + "loss": 1.4203, + "step": 3230 + }, + { + "epoch": 0.34, + "learning_rate": 1.6720630741305088e-05, + "loss": 1.4112, + "step": 3231 + }, + { + "epoch": 0.34, + "learning_rate": 1.6717919898283523e-05, + "loss": 1.3811, + "step": 3232 + }, + { + "epoch": 0.34, + "learning_rate": 1.6715208155233296e-05, + "loss": 1.4242, + "step": 3233 + }, + { + "epoch": 0.34, + "learning_rate": 1.6712495512517725e-05, + "loss": 1.4207, + "step": 3234 + }, + { + "epoch": 0.34, + "learning_rate": 1.6709781970500222e-05, + "loss": 1.4888, + "step": 3235 + }, + { + "epoch": 0.34, + "learning_rate": 1.670706752954434e-05, + "loss": 1.4501, + "step": 3236 + }, + { + "epoch": 0.34, + "learning_rate": 1.670435219001374e-05, + "loss": 1.4367, + "step": 3237 + }, + { + "epoch": 0.34, + "learning_rate": 1.6701635952272212e-05, + "loss": 1.3959, + "step": 3238 + }, + { + "epoch": 0.34, + "learning_rate": 1.6698918816683655e-05, + "loss": 1.4257, + "step": 3239 + }, + { + "epoch": 0.34, + "learning_rate": 1.6696200783612102e-05, + "loss": 1.4718, + "step": 3240 + }, + { + "epoch": 0.34, + "learning_rate": 1.6693481853421697e-05, + "loss": 1.5899, + "step": 3241 + }, + { + "epoch": 0.34, + "learning_rate": 1.6690762026476707e-05, + "loss": 1.418, + "step": 3242 + }, + { + "epoch": 0.34, + "learning_rate": 1.668804130314152e-05, + "loss": 1.4076, + "step": 3243 + }, + { + "epoch": 0.34, + "learning_rate": 1.6685319683780645e-05, + "loss": 1.4571, + "step": 3244 + }, + { + "epoch": 0.34, + "learning_rate": 1.66825971687587e-05, + "loss": 1.4066, + "step": 3245 + }, + { + "epoch": 0.34, + "learning_rate": 1.6679873758440442e-05, + "loss": 1.4639, + "step": 3246 + }, + { + "epoch": 0.34, + "learning_rate": 1.6677149453190732e-05, + "loss": 1.453, + "step": 3247 + }, + { + "epoch": 0.34, + "learning_rate": 1.6674424253374558e-05, + "loss": 1.4262, + "step": 3248 + }, + { + "epoch": 0.34, + "learning_rate": 1.667169815935703e-05, + "loss": 1.3687, + "step": 3249 + }, + { + "epoch": 0.34, + "learning_rate": 1.6668971171503372e-05, + "loss": 1.5557, + "step": 3250 + }, + { + "epoch": 0.34, + "learning_rate": 1.6666243290178933e-05, + "loss": 1.4639, + "step": 3251 + }, + { + "epoch": 0.34, + "learning_rate": 1.6663514515749172e-05, + "loss": 1.4334, + "step": 3252 + }, + { + "epoch": 0.34, + "learning_rate": 1.6660784848579685e-05, + "loss": 1.3523, + "step": 3253 + }, + { + "epoch": 0.34, + "learning_rate": 1.6658054289036166e-05, + "loss": 1.3738, + "step": 3254 + }, + { + "epoch": 0.34, + "learning_rate": 1.665532283748445e-05, + "loss": 1.4159, + "step": 3255 + }, + { + "epoch": 0.34, + "learning_rate": 1.6652590494290474e-05, + "loss": 1.3609, + "step": 3256 + }, + { + "epoch": 0.34, + "learning_rate": 1.6649857259820303e-05, + "loss": 1.4449, + "step": 3257 + }, + { + "epoch": 0.34, + "learning_rate": 1.6647123134440126e-05, + "loss": 1.424, + "step": 3258 + }, + { + "epoch": 0.34, + "learning_rate": 1.664438811851624e-05, + "loss": 1.4737, + "step": 3259 + }, + { + "epoch": 0.34, + "learning_rate": 1.6641652212415066e-05, + "loss": 1.2717, + "step": 3260 + }, + { + "epoch": 0.34, + "learning_rate": 1.663891541650315e-05, + "loss": 1.4845, + "step": 3261 + }, + { + "epoch": 0.34, + "learning_rate": 1.663617773114715e-05, + "loss": 1.4115, + "step": 3262 + }, + { + "epoch": 0.34, + "learning_rate": 1.663343915671384e-05, + "loss": 1.4237, + "step": 3263 + }, + { + "epoch": 0.34, + "learning_rate": 1.6630699693570127e-05, + "loss": 1.4209, + "step": 3264 + }, + { + "epoch": 0.34, + "learning_rate": 1.6627959342083026e-05, + "loss": 1.506, + "step": 3265 + }, + { + "epoch": 0.34, + "learning_rate": 1.6625218102619672e-05, + "loss": 1.4466, + "step": 3266 + }, + { + "epoch": 0.34, + "learning_rate": 1.6622475975547324e-05, + "loss": 1.4129, + "step": 3267 + }, + { + "epoch": 0.34, + "learning_rate": 1.661973296123335e-05, + "loss": 1.4152, + "step": 3268 + }, + { + "epoch": 0.34, + "learning_rate": 1.661698906004525e-05, + "loss": 1.43, + "step": 3269 + }, + { + "epoch": 0.34, + "learning_rate": 1.661424427235064e-05, + "loss": 1.4701, + "step": 3270 + }, + { + "epoch": 0.34, + "learning_rate": 1.6611498598517238e-05, + "loss": 1.4598, + "step": 3271 + }, + { + "epoch": 0.34, + "learning_rate": 1.66087520389129e-05, + "loss": 1.4795, + "step": 3272 + }, + { + "epoch": 0.34, + "learning_rate": 1.6606004593905595e-05, + "loss": 1.5264, + "step": 3273 + }, + { + "epoch": 0.34, + "learning_rate": 1.6603256263863415e-05, + "loss": 1.4412, + "step": 3274 + }, + { + "epoch": 0.34, + "learning_rate": 1.6600507049154556e-05, + "loss": 1.45, + "step": 3275 + }, + { + "epoch": 0.34, + "learning_rate": 1.659775695014735e-05, + "loss": 1.4985, + "step": 3276 + }, + { + "epoch": 0.34, + "learning_rate": 1.659500596721024e-05, + "loss": 1.496, + "step": 3277 + }, + { + "epoch": 0.34, + "learning_rate": 1.6592254100711775e-05, + "loss": 1.4386, + "step": 3278 + }, + { + "epoch": 0.34, + "learning_rate": 1.658950135102065e-05, + "loss": 1.4073, + "step": 3279 + }, + { + "epoch": 0.34, + "learning_rate": 1.658674771850565e-05, + "loss": 1.3912, + "step": 3280 + }, + { + "epoch": 0.34, + "learning_rate": 1.6583993203535702e-05, + "loss": 1.3628, + "step": 3281 + }, + { + "epoch": 0.34, + "learning_rate": 1.658123780647983e-05, + "loss": 1.6089, + "step": 3282 + }, + { + "epoch": 0.34, + "learning_rate": 1.6578481527707196e-05, + "loss": 1.2367, + "step": 3283 + }, + { + "epoch": 0.34, + "learning_rate": 1.657572436758706e-05, + "loss": 1.4058, + "step": 3284 + }, + { + "epoch": 0.34, + "learning_rate": 1.6572966326488825e-05, + "loss": 1.4067, + "step": 3285 + }, + { + "epoch": 0.34, + "learning_rate": 1.657020740478198e-05, + "loss": 1.4187, + "step": 3286 + }, + { + "epoch": 0.34, + "learning_rate": 1.6567447602836166e-05, + "loss": 1.4599, + "step": 3287 + }, + { + "epoch": 0.34, + "learning_rate": 1.6564686921021115e-05, + "loss": 1.432, + "step": 3288 + }, + { + "epoch": 0.34, + "learning_rate": 1.6561925359706693e-05, + "loss": 1.3941, + "step": 3289 + }, + { + "epoch": 0.35, + "learning_rate": 1.6559162919262874e-05, + "loss": 1.3644, + "step": 3290 + }, + { + "epoch": 0.35, + "learning_rate": 1.6556399600059756e-05, + "loss": 1.4628, + "step": 3291 + }, + { + "epoch": 0.35, + "learning_rate": 1.6553635402467555e-05, + "loss": 1.4355, + "step": 3292 + }, + { + "epoch": 0.35, + "learning_rate": 1.6550870326856596e-05, + "loss": 1.4627, + "step": 3293 + }, + { + "epoch": 0.35, + "learning_rate": 1.6548104373597335e-05, + "loss": 1.442, + "step": 3294 + }, + { + "epoch": 0.35, + "learning_rate": 1.6545337543060338e-05, + "loss": 1.3991, + "step": 3295 + }, + { + "epoch": 0.35, + "learning_rate": 1.6542569835616283e-05, + "loss": 1.4193, + "step": 3296 + }, + { + "epoch": 0.35, + "learning_rate": 1.6539801251635982e-05, + "loss": 1.4792, + "step": 3297 + }, + { + "epoch": 0.35, + "learning_rate": 1.653703179149034e-05, + "loss": 1.4735, + "step": 3298 + }, + { + "epoch": 0.35, + "learning_rate": 1.6534261455550408e-05, + "loss": 1.451, + "step": 3299 + }, + { + "epoch": 0.35, + "learning_rate": 1.653149024418733e-05, + "loss": 1.3975, + "step": 3300 + }, + { + "epoch": 0.35, + "learning_rate": 1.652871815777238e-05, + "loss": 1.4843, + "step": 3301 + }, + { + "epoch": 0.35, + "learning_rate": 1.6525945196676948e-05, + "loss": 1.4782, + "step": 3302 + }, + { + "epoch": 0.35, + "learning_rate": 1.652317136127254e-05, + "loss": 1.3865, + "step": 3303 + }, + { + "epoch": 0.35, + "learning_rate": 1.6520396651930777e-05, + "loss": 1.4359, + "step": 3304 + }, + { + "epoch": 0.35, + "learning_rate": 1.6517621069023397e-05, + "loss": 1.4289, + "step": 3305 + }, + { + "epoch": 0.35, + "learning_rate": 1.651484461292226e-05, + "loss": 1.3526, + "step": 3306 + }, + { + "epoch": 0.35, + "learning_rate": 1.6512067283999336e-05, + "loss": 1.3671, + "step": 3307 + }, + { + "epoch": 0.35, + "learning_rate": 1.650928908262672e-05, + "loss": 1.6041, + "step": 3308 + }, + { + "epoch": 0.35, + "learning_rate": 1.650651000917662e-05, + "loss": 1.4322, + "step": 3309 + }, + { + "epoch": 0.35, + "learning_rate": 1.6503730064021354e-05, + "loss": 1.3992, + "step": 3310 + }, + { + "epoch": 0.35, + "learning_rate": 1.650094924753337e-05, + "loss": 1.4928, + "step": 3311 + }, + { + "epoch": 0.35, + "learning_rate": 1.6498167560085222e-05, + "loss": 1.4075, + "step": 3312 + }, + { + "epoch": 0.35, + "learning_rate": 1.6495385002049583e-05, + "loss": 1.4535, + "step": 3313 + }, + { + "epoch": 0.35, + "learning_rate": 1.6492601573799253e-05, + "loss": 1.4221, + "step": 3314 + }, + { + "epoch": 0.35, + "learning_rate": 1.6489817275707133e-05, + "loss": 1.3688, + "step": 3315 + }, + { + "epoch": 0.35, + "learning_rate": 1.6487032108146243e-05, + "loss": 1.3889, + "step": 3316 + }, + { + "epoch": 0.35, + "learning_rate": 1.6484246071489733e-05, + "loss": 1.3942, + "step": 3317 + }, + { + "epoch": 0.35, + "learning_rate": 1.6481459166110858e-05, + "loss": 1.4004, + "step": 3318 + }, + { + "epoch": 0.35, + "learning_rate": 1.647867139238299e-05, + "loss": 1.7308, + "step": 3319 + }, + { + "epoch": 0.35, + "learning_rate": 1.6475882750679622e-05, + "loss": 1.5001, + "step": 3320 + }, + { + "epoch": 0.35, + "learning_rate": 1.647309324137435e-05, + "loss": 1.4325, + "step": 3321 + }, + { + "epoch": 0.35, + "learning_rate": 1.6470302864840913e-05, + "loss": 1.4494, + "step": 3322 + }, + { + "epoch": 0.35, + "learning_rate": 1.6467511621453136e-05, + "loss": 1.4418, + "step": 3323 + }, + { + "epoch": 0.35, + "learning_rate": 1.646471951158498e-05, + "loss": 1.4046, + "step": 3324 + }, + { + "epoch": 0.35, + "learning_rate": 1.6461926535610517e-05, + "loss": 1.5031, + "step": 3325 + }, + { + "epoch": 0.35, + "learning_rate": 1.645913269390393e-05, + "loss": 1.4813, + "step": 3326 + }, + { + "epoch": 0.35, + "learning_rate": 1.6456337986839525e-05, + "loss": 1.3842, + "step": 3327 + }, + { + "epoch": 0.35, + "learning_rate": 1.645354241479172e-05, + "loss": 1.4539, + "step": 3328 + }, + { + "epoch": 0.35, + "learning_rate": 1.6450745978135048e-05, + "loss": 1.4503, + "step": 3329 + }, + { + "epoch": 0.35, + "learning_rate": 1.6447948677244163e-05, + "loss": 1.3741, + "step": 3330 + }, + { + "epoch": 0.35, + "learning_rate": 1.6445150512493832e-05, + "loss": 1.425, + "step": 3331 + }, + { + "epoch": 0.35, + "learning_rate": 1.644235148425893e-05, + "loss": 1.4277, + "step": 3332 + }, + { + "epoch": 0.35, + "learning_rate": 1.6439551592914464e-05, + "loss": 1.4918, + "step": 3333 + }, + { + "epoch": 0.35, + "learning_rate": 1.6436750838835543e-05, + "loss": 1.3364, + "step": 3334 + }, + { + "epoch": 0.35, + "learning_rate": 1.6433949222397397e-05, + "loss": 1.4741, + "step": 3335 + }, + { + "epoch": 0.35, + "learning_rate": 1.643114674397537e-05, + "loss": 1.3867, + "step": 3336 + }, + { + "epoch": 0.35, + "learning_rate": 1.642834340394492e-05, + "loss": 1.3817, + "step": 3337 + }, + { + "epoch": 0.35, + "learning_rate": 1.6425539202681625e-05, + "loss": 1.4308, + "step": 3338 + }, + { + "epoch": 0.35, + "learning_rate": 1.6422734140561178e-05, + "loss": 1.4401, + "step": 3339 + }, + { + "epoch": 0.35, + "learning_rate": 1.641992821795938e-05, + "loss": 1.4338, + "step": 3340 + }, + { + "epoch": 0.35, + "learning_rate": 1.641712143525216e-05, + "loss": 1.3804, + "step": 3341 + }, + { + "epoch": 0.35, + "learning_rate": 1.6414313792815546e-05, + "loss": 1.371, + "step": 3342 + }, + { + "epoch": 0.35, + "learning_rate": 1.6411505291025695e-05, + "loss": 1.4102, + "step": 3343 + }, + { + "epoch": 0.35, + "learning_rate": 1.6408695930258875e-05, + "loss": 1.4433, + "step": 3344 + }, + { + "epoch": 0.35, + "learning_rate": 1.6405885710891467e-05, + "loss": 1.3895, + "step": 3345 + }, + { + "epoch": 0.35, + "learning_rate": 1.6403074633299966e-05, + "loss": 1.4321, + "step": 3346 + }, + { + "epoch": 0.35, + "learning_rate": 1.640026269786098e-05, + "loss": 1.4207, + "step": 3347 + }, + { + "epoch": 0.35, + "learning_rate": 1.639744990495125e-05, + "loss": 1.3758, + "step": 3348 + }, + { + "epoch": 0.35, + "learning_rate": 1.6394636254947612e-05, + "loss": 1.4203, + "step": 3349 + }, + { + "epoch": 0.35, + "learning_rate": 1.6391821748227013e-05, + "loss": 1.4596, + "step": 3350 + }, + { + "epoch": 0.35, + "learning_rate": 1.6389006385166537e-05, + "loss": 1.4344, + "step": 3351 + }, + { + "epoch": 0.35, + "learning_rate": 1.6386190166143366e-05, + "loss": 1.4048, + "step": 3352 + }, + { + "epoch": 0.35, + "learning_rate": 1.6383373091534798e-05, + "loss": 1.4348, + "step": 3353 + }, + { + "epoch": 0.35, + "learning_rate": 1.638055516171825e-05, + "loss": 1.4972, + "step": 3354 + }, + { + "epoch": 0.35, + "learning_rate": 1.6377736377071258e-05, + "loss": 1.4685, + "step": 3355 + }, + { + "epoch": 0.35, + "learning_rate": 1.637491673797146e-05, + "loss": 1.4093, + "step": 3356 + }, + { + "epoch": 0.35, + "learning_rate": 1.6372096244796616e-05, + "loss": 1.4452, + "step": 3357 + }, + { + "epoch": 0.35, + "learning_rate": 1.63692748979246e-05, + "loss": 1.4458, + "step": 3358 + }, + { + "epoch": 0.35, + "learning_rate": 1.6366452697733404e-05, + "loss": 1.4187, + "step": 3359 + }, + { + "epoch": 0.35, + "learning_rate": 1.6363629644601126e-05, + "loss": 1.4052, + "step": 3360 + }, + { + "epoch": 0.35, + "learning_rate": 1.6360805738905984e-05, + "loss": 1.439, + "step": 3361 + }, + { + "epoch": 0.35, + "learning_rate": 1.635798098102631e-05, + "loss": 1.4131, + "step": 3362 + }, + { + "epoch": 0.35, + "learning_rate": 1.6355155371340544e-05, + "loss": 1.4391, + "step": 3363 + }, + { + "epoch": 0.35, + "learning_rate": 1.6352328910227252e-05, + "loss": 1.4318, + "step": 3364 + }, + { + "epoch": 0.35, + "learning_rate": 1.63495015980651e-05, + "loss": 1.5112, + "step": 3365 + }, + { + "epoch": 0.35, + "learning_rate": 1.6346673435232884e-05, + "loss": 1.4688, + "step": 3366 + }, + { + "epoch": 0.35, + "learning_rate": 1.6343844422109496e-05, + "loss": 1.3807, + "step": 3367 + }, + { + "epoch": 0.35, + "learning_rate": 1.634101455907396e-05, + "loss": 1.4083, + "step": 3368 + }, + { + "epoch": 0.35, + "learning_rate": 1.6338183846505394e-05, + "loss": 1.3566, + "step": 3369 + }, + { + "epoch": 0.35, + "learning_rate": 1.633535228478305e-05, + "loss": 1.4287, + "step": 3370 + }, + { + "epoch": 0.35, + "learning_rate": 1.6332519874286285e-05, + "loss": 1.3494, + "step": 3371 + }, + { + "epoch": 0.35, + "learning_rate": 1.6329686615394558e-05, + "loss": 1.3813, + "step": 3372 + }, + { + "epoch": 0.35, + "learning_rate": 1.6326852508487468e-05, + "loss": 1.4241, + "step": 3373 + }, + { + "epoch": 0.35, + "learning_rate": 1.63240175539447e-05, + "loss": 1.424, + "step": 3374 + }, + { + "epoch": 0.35, + "learning_rate": 1.632118175214607e-05, + "loss": 1.4212, + "step": 3375 + }, + { + "epoch": 0.35, + "learning_rate": 1.6318345103471504e-05, + "loss": 1.4671, + "step": 3376 + }, + { + "epoch": 0.35, + "learning_rate": 1.6315507608301044e-05, + "loss": 1.4593, + "step": 3377 + }, + { + "epoch": 0.35, + "learning_rate": 1.631266926701483e-05, + "loss": 1.7816, + "step": 3378 + }, + { + "epoch": 0.35, + "learning_rate": 1.6309830079993134e-05, + "loss": 1.5134, + "step": 3379 + }, + { + "epoch": 0.35, + "learning_rate": 1.6306990047616334e-05, + "loss": 0.8933, + "step": 3380 + }, + { + "epoch": 0.35, + "learning_rate": 1.630414917026492e-05, + "loss": 1.1033, + "step": 3381 + }, + { + "epoch": 0.35, + "learning_rate": 1.6301307448319497e-05, + "loss": 1.3494, + "step": 3382 + }, + { + "epoch": 0.35, + "learning_rate": 1.6298464882160784e-05, + "loss": 1.4299, + "step": 3383 + }, + { + "epoch": 0.35, + "eval_loss": 1.482450008392334, + "eval_runtime": 77.3737, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3383 + }, + { + "epoch": 0.35, + "learning_rate": 1.629562147216961e-05, + "loss": 1.3971, + "step": 3384 + }, + { + "epoch": 0.35, + "learning_rate": 1.6292777218726917e-05, + "loss": 1.3706, + "step": 3385 + }, + { + "epoch": 0.36, + "learning_rate": 1.6289932122213765e-05, + "loss": 1.4524, + "step": 3386 + }, + { + "epoch": 0.36, + "learning_rate": 1.6287086183011328e-05, + "loss": 1.4595, + "step": 3387 + }, + { + "epoch": 0.36, + "learning_rate": 1.628423940150088e-05, + "loss": 1.492, + "step": 3388 + }, + { + "epoch": 0.36, + "learning_rate": 1.628139177806382e-05, + "loss": 1.5576, + "step": 3389 + }, + { + "epoch": 0.36, + "learning_rate": 1.6278543313081657e-05, + "loss": 1.4615, + "step": 3390 + }, + { + "epoch": 0.36, + "learning_rate": 1.6275694006936015e-05, + "loss": 1.3456, + "step": 3391 + }, + { + "epoch": 0.36, + "learning_rate": 1.627284386000862e-05, + "loss": 1.4254, + "step": 3392 + }, + { + "epoch": 0.36, + "learning_rate": 1.6269992872681325e-05, + "loss": 1.433, + "step": 3393 + }, + { + "epoch": 0.36, + "learning_rate": 1.626714104533609e-05, + "loss": 1.5291, + "step": 3394 + }, + { + "epoch": 0.36, + "learning_rate": 1.626428837835498e-05, + "loss": 1.4502, + "step": 3395 + }, + { + "epoch": 0.36, + "learning_rate": 1.626143487212019e-05, + "loss": 1.3756, + "step": 3396 + }, + { + "epoch": 0.36, + "learning_rate": 1.6258580527014002e-05, + "loss": 1.414, + "step": 3397 + }, + { + "epoch": 0.36, + "learning_rate": 1.6255725343418835e-05, + "loss": 1.6289, + "step": 3398 + }, + { + "epoch": 0.36, + "learning_rate": 1.6252869321717208e-05, + "loss": 1.4862, + "step": 3399 + }, + { + "epoch": 0.36, + "learning_rate": 1.6250012462291756e-05, + "loss": 1.4213, + "step": 3400 + }, + { + "epoch": 0.36, + "learning_rate": 1.6247154765525217e-05, + "loss": 1.524, + "step": 3401 + }, + { + "epoch": 0.36, + "learning_rate": 1.624429623180046e-05, + "loss": 1.6013, + "step": 3402 + }, + { + "epoch": 0.36, + "learning_rate": 1.624143686150045e-05, + "loss": 1.4557, + "step": 3403 + }, + { + "epoch": 0.36, + "learning_rate": 1.6238576655008266e-05, + "loss": 1.3831, + "step": 3404 + }, + { + "epoch": 0.36, + "learning_rate": 1.6235715612707105e-05, + "loss": 1.4008, + "step": 3405 + }, + { + "epoch": 0.36, + "learning_rate": 1.623285373498028e-05, + "loss": 1.4848, + "step": 3406 + }, + { + "epoch": 0.36, + "learning_rate": 1.6229991022211197e-05, + "loss": 1.4459, + "step": 3407 + }, + { + "epoch": 0.36, + "learning_rate": 1.6227127474783393e-05, + "loss": 1.4334, + "step": 3408 + }, + { + "epoch": 0.36, + "learning_rate": 1.6224263093080507e-05, + "loss": 1.4123, + "step": 3409 + }, + { + "epoch": 0.36, + "learning_rate": 1.6221397877486294e-05, + "loss": 1.3691, + "step": 3410 + }, + { + "epoch": 0.36, + "learning_rate": 1.6218531828384618e-05, + "loss": 1.4128, + "step": 3411 + }, + { + "epoch": 0.36, + "learning_rate": 1.6215664946159457e-05, + "loss": 1.3642, + "step": 3412 + }, + { + "epoch": 0.36, + "learning_rate": 1.6212797231194902e-05, + "loss": 1.4311, + "step": 3413 + }, + { + "epoch": 0.36, + "learning_rate": 1.6209928683875152e-05, + "loss": 1.4695, + "step": 3414 + }, + { + "epoch": 0.36, + "learning_rate": 1.6207059304584514e-05, + "loss": 1.3871, + "step": 3415 + }, + { + "epoch": 0.36, + "learning_rate": 1.6204189093707414e-05, + "loss": 1.4219, + "step": 3416 + }, + { + "epoch": 0.36, + "learning_rate": 1.620131805162839e-05, + "loss": 1.6199, + "step": 3417 + }, + { + "epoch": 0.36, + "learning_rate": 1.619844617873208e-05, + "loss": 1.4433, + "step": 3418 + }, + { + "epoch": 0.36, + "learning_rate": 1.619557347540325e-05, + "loss": 1.4773, + "step": 3419 + }, + { + "epoch": 0.36, + "learning_rate": 1.6192699942026763e-05, + "loss": 1.4551, + "step": 3420 + }, + { + "epoch": 0.36, + "learning_rate": 1.6189825578987603e-05, + "loss": 1.4903, + "step": 3421 + }, + { + "epoch": 0.36, + "learning_rate": 1.6186950386670855e-05, + "loss": 1.473, + "step": 3422 + }, + { + "epoch": 0.36, + "learning_rate": 1.6184074365461722e-05, + "loss": 1.4082, + "step": 3423 + }, + { + "epoch": 0.36, + "learning_rate": 1.6181197515745523e-05, + "loss": 1.4746, + "step": 3424 + }, + { + "epoch": 0.36, + "learning_rate": 1.6178319837907674e-05, + "loss": 1.449, + "step": 3425 + }, + { + "epoch": 0.36, + "learning_rate": 1.6175441332333715e-05, + "loss": 1.377, + "step": 3426 + }, + { + "epoch": 0.36, + "learning_rate": 1.617256199940929e-05, + "loss": 1.2364, + "step": 3427 + }, + { + "epoch": 0.36, + "learning_rate": 1.6169681839520155e-05, + "loss": 1.4437, + "step": 3428 + }, + { + "epoch": 0.36, + "learning_rate": 1.616680085305218e-05, + "loss": 1.4726, + "step": 3429 + }, + { + "epoch": 0.36, + "learning_rate": 1.616391904039134e-05, + "loss": 1.4824, + "step": 3430 + }, + { + "epoch": 0.36, + "learning_rate": 1.616103640192373e-05, + "loss": 1.4052, + "step": 3431 + }, + { + "epoch": 0.36, + "learning_rate": 1.6158152938035537e-05, + "loss": 1.4131, + "step": 3432 + }, + { + "epoch": 0.36, + "learning_rate": 1.6155268649113084e-05, + "loss": 1.4267, + "step": 3433 + }, + { + "epoch": 0.36, + "learning_rate": 1.6152383535542786e-05, + "loss": 1.3735, + "step": 3434 + }, + { + "epoch": 0.36, + "learning_rate": 1.6149497597711175e-05, + "loss": 1.4249, + "step": 3435 + }, + { + "epoch": 0.36, + "learning_rate": 1.614661083600489e-05, + "loss": 1.4312, + "step": 3436 + }, + { + "epoch": 0.36, + "learning_rate": 1.6143723250810686e-05, + "loss": 1.4831, + "step": 3437 + }, + { + "epoch": 0.36, + "learning_rate": 1.6140834842515425e-05, + "loss": 1.4183, + "step": 3438 + }, + { + "epoch": 0.36, + "learning_rate": 1.6137945611506078e-05, + "loss": 1.3908, + "step": 3439 + }, + { + "epoch": 0.36, + "learning_rate": 1.613505555816973e-05, + "loss": 1.425, + "step": 3440 + }, + { + "epoch": 0.36, + "learning_rate": 1.613216468289357e-05, + "loss": 1.3589, + "step": 3441 + }, + { + "epoch": 0.36, + "learning_rate": 1.6129272986064903e-05, + "loss": 1.4272, + "step": 3442 + }, + { + "epoch": 0.36, + "learning_rate": 1.6126380468071142e-05, + "loss": 1.4337, + "step": 3443 + }, + { + "epoch": 0.36, + "learning_rate": 1.6123487129299817e-05, + "loss": 1.3872, + "step": 3444 + }, + { + "epoch": 0.36, + "learning_rate": 1.612059297013855e-05, + "loss": 1.374, + "step": 3445 + }, + { + "epoch": 0.36, + "learning_rate": 1.611769799097509e-05, + "loss": 1.314, + "step": 3446 + }, + { + "epoch": 0.36, + "learning_rate": 1.6114802192197284e-05, + "loss": 1.3951, + "step": 3447 + }, + { + "epoch": 0.36, + "learning_rate": 1.6111905574193102e-05, + "loss": 1.4732, + "step": 3448 + }, + { + "epoch": 0.36, + "learning_rate": 1.6109008137350614e-05, + "loss": 1.3575, + "step": 3449 + }, + { + "epoch": 0.36, + "learning_rate": 1.6106109882058e-05, + "loss": 1.4606, + "step": 3450 + }, + { + "epoch": 0.36, + "learning_rate": 1.6103210808703554e-05, + "loss": 1.4357, + "step": 3451 + }, + { + "epoch": 0.36, + "learning_rate": 1.6100310917675678e-05, + "loss": 0.8456, + "step": 3452 + }, + { + "epoch": 0.36, + "learning_rate": 1.609741020936288e-05, + "loss": 1.07, + "step": 3453 + }, + { + "epoch": 0.36, + "learning_rate": 1.6094508684153782e-05, + "loss": 1.4435, + "step": 3454 + }, + { + "epoch": 0.36, + "learning_rate": 1.609160634243711e-05, + "loss": 1.3696, + "step": 3455 + }, + { + "epoch": 0.36, + "learning_rate": 1.6088703184601712e-05, + "loss": 1.4012, + "step": 3456 + }, + { + "epoch": 0.36, + "learning_rate": 1.608579921103653e-05, + "loss": 1.5212, + "step": 3457 + }, + { + "epoch": 0.36, + "learning_rate": 1.608289442213062e-05, + "loss": 1.4339, + "step": 3458 + }, + { + "epoch": 0.36, + "learning_rate": 1.607998881827316e-05, + "loss": 1.4901, + "step": 3459 + }, + { + "epoch": 0.36, + "learning_rate": 1.6077082399853412e-05, + "loss": 1.4822, + "step": 3460 + }, + { + "epoch": 0.36, + "learning_rate": 1.607417516726077e-05, + "loss": 1.3696, + "step": 3461 + }, + { + "epoch": 0.36, + "learning_rate": 1.6071267120884727e-05, + "loss": 1.4434, + "step": 3462 + }, + { + "epoch": 0.36, + "learning_rate": 1.6068358261114886e-05, + "loss": 1.3916, + "step": 3463 + }, + { + "epoch": 0.36, + "learning_rate": 1.606544858834096e-05, + "loss": 1.422, + "step": 3464 + }, + { + "epoch": 0.36, + "learning_rate": 1.6062538102952763e-05, + "loss": 1.367, + "step": 3465 + }, + { + "epoch": 0.36, + "learning_rate": 1.605962680534024e-05, + "loss": 1.3788, + "step": 3466 + }, + { + "epoch": 0.36, + "learning_rate": 1.605671469589342e-05, + "loss": 1.4366, + "step": 3467 + }, + { + "epoch": 0.36, + "learning_rate": 1.6053801775002453e-05, + "loss": 1.4027, + "step": 3468 + }, + { + "epoch": 0.36, + "learning_rate": 1.6050888043057595e-05, + "loss": 1.4386, + "step": 3469 + }, + { + "epoch": 0.36, + "learning_rate": 1.6047973500449212e-05, + "loss": 1.4675, + "step": 3470 + }, + { + "epoch": 0.36, + "learning_rate": 1.6045058147567778e-05, + "loss": 1.6936, + "step": 3471 + }, + { + "epoch": 0.36, + "learning_rate": 1.6042141984803875e-05, + "loss": 1.4858, + "step": 3472 + }, + { + "epoch": 0.36, + "learning_rate": 1.6039225012548196e-05, + "loss": 1.5004, + "step": 3473 + }, + { + "epoch": 0.36, + "learning_rate": 1.6036307231191534e-05, + "loss": 1.4969, + "step": 3474 + }, + { + "epoch": 0.36, + "learning_rate": 1.6033388641124803e-05, + "loss": 1.4027, + "step": 3475 + }, + { + "epoch": 0.36, + "learning_rate": 1.6030469242739016e-05, + "loss": 1.4741, + "step": 3476 + }, + { + "epoch": 0.36, + "learning_rate": 1.60275490364253e-05, + "loss": 1.3887, + "step": 3477 + }, + { + "epoch": 0.36, + "learning_rate": 1.602462802257488e-05, + "loss": 1.6735, + "step": 3478 + }, + { + "epoch": 0.36, + "learning_rate": 1.602170620157911e-05, + "loss": 1.4997, + "step": 3479 + }, + { + "epoch": 0.36, + "learning_rate": 1.601878357382943e-05, + "loss": 1.3973, + "step": 3480 + }, + { + "epoch": 0.37, + "learning_rate": 1.6015860139717398e-05, + "loss": 1.416, + "step": 3481 + }, + { + "epoch": 0.37, + "learning_rate": 1.6012935899634682e-05, + "loss": 1.4102, + "step": 3482 + }, + { + "epoch": 0.37, + "learning_rate": 1.601001085397305e-05, + "loss": 1.4248, + "step": 3483 + }, + { + "epoch": 0.37, + "learning_rate": 1.6007085003124386e-05, + "loss": 1.3909, + "step": 3484 + }, + { + "epoch": 0.37, + "learning_rate": 1.600415834748068e-05, + "loss": 1.4029, + "step": 3485 + }, + { + "epoch": 0.37, + "learning_rate": 1.6001230887434024e-05, + "loss": 1.4219, + "step": 3486 + }, + { + "epoch": 0.37, + "learning_rate": 1.5998302623376633e-05, + "loss": 1.4008, + "step": 3487 + }, + { + "epoch": 0.37, + "learning_rate": 1.5995373555700806e-05, + "loss": 1.5163, + "step": 3488 + }, + { + "epoch": 0.37, + "learning_rate": 1.599244368479897e-05, + "loss": 1.4541, + "step": 3489 + }, + { + "epoch": 0.37, + "learning_rate": 1.598951301106365e-05, + "loss": 1.4454, + "step": 3490 + }, + { + "epoch": 0.37, + "learning_rate": 1.598658153488748e-05, + "loss": 1.1014, + "step": 3491 + }, + { + "epoch": 0.37, + "learning_rate": 1.598364925666321e-05, + "loss": 1.407, + "step": 3492 + }, + { + "epoch": 0.37, + "learning_rate": 1.5980716176783682e-05, + "loss": 1.5046, + "step": 3493 + }, + { + "epoch": 0.37, + "learning_rate": 1.5977782295641857e-05, + "loss": 1.4265, + "step": 3494 + }, + { + "epoch": 0.37, + "learning_rate": 1.5974847613630796e-05, + "loss": 1.46, + "step": 3495 + }, + { + "epoch": 0.37, + "learning_rate": 1.5971912131143677e-05, + "loss": 1.3996, + "step": 3496 + }, + { + "epoch": 0.37, + "learning_rate": 1.5968975848573772e-05, + "loss": 1.4719, + "step": 3497 + }, + { + "epoch": 0.37, + "learning_rate": 1.596603876631447e-05, + "loss": 1.43, + "step": 3498 + }, + { + "epoch": 0.37, + "learning_rate": 1.596310088475927e-05, + "loss": 1.4109, + "step": 3499 + }, + { + "epoch": 0.37, + "learning_rate": 1.5960162204301768e-05, + "loss": 1.3612, + "step": 3500 + }, + { + "epoch": 0.37, + "learning_rate": 1.5957222725335672e-05, + "loss": 1.5045, + "step": 3501 + }, + { + "epoch": 0.37, + "learning_rate": 1.5954282448254794e-05, + "loss": 1.5323, + "step": 3502 + }, + { + "epoch": 0.37, + "learning_rate": 1.595134137345306e-05, + "loss": 1.4518, + "step": 3503 + }, + { + "epoch": 0.37, + "learning_rate": 1.5948399501324495e-05, + "loss": 1.6131, + "step": 3504 + }, + { + "epoch": 0.37, + "learning_rate": 1.594545683226324e-05, + "loss": 1.5076, + "step": 3505 + }, + { + "epoch": 0.37, + "learning_rate": 1.594251336666353e-05, + "loss": 1.482, + "step": 3506 + }, + { + "epoch": 0.37, + "learning_rate": 1.5939569104919716e-05, + "loss": 1.4429, + "step": 3507 + }, + { + "epoch": 0.37, + "learning_rate": 1.5936624047426254e-05, + "loss": 1.4662, + "step": 3508 + }, + { + "epoch": 0.37, + "learning_rate": 1.5933678194577708e-05, + "loss": 1.425, + "step": 3509 + }, + { + "epoch": 0.37, + "learning_rate": 1.5930731546768744e-05, + "loss": 1.4312, + "step": 3510 + }, + { + "epoch": 0.37, + "learning_rate": 1.592778410439414e-05, + "loss": 1.4336, + "step": 3511 + }, + { + "epoch": 0.37, + "learning_rate": 1.5924835867848775e-05, + "loss": 1.4197, + "step": 3512 + }, + { + "epoch": 0.37, + "learning_rate": 1.5921886837527638e-05, + "loss": 1.4456, + "step": 3513 + }, + { + "epoch": 0.37, + "learning_rate": 1.5918937013825823e-05, + "loss": 1.4394, + "step": 3514 + }, + { + "epoch": 0.37, + "learning_rate": 1.5915986397138526e-05, + "loss": 1.3606, + "step": 3515 + }, + { + "epoch": 0.37, + "learning_rate": 1.591303498786106e-05, + "loss": 1.4382, + "step": 3516 + }, + { + "epoch": 0.37, + "learning_rate": 1.591008278638884e-05, + "loss": 1.4185, + "step": 3517 + }, + { + "epoch": 0.37, + "learning_rate": 1.5907129793117374e-05, + "loss": 1.6692, + "step": 3518 + }, + { + "epoch": 0.37, + "learning_rate": 1.59041760084423e-05, + "loss": 1.501, + "step": 3519 + }, + { + "epoch": 0.37, + "learning_rate": 1.5901221432759345e-05, + "loss": 1.5753, + "step": 3520 + }, + { + "epoch": 0.37, + "learning_rate": 1.589826606646434e-05, + "loss": 1.4795, + "step": 3521 + }, + { + "epoch": 0.37, + "learning_rate": 1.5895309909953236e-05, + "loss": 1.4379, + "step": 3522 + }, + { + "epoch": 0.37, + "learning_rate": 1.5892352963622078e-05, + "loss": 1.3426, + "step": 3523 + }, + { + "epoch": 0.37, + "learning_rate": 1.5889395227867025e-05, + "loss": 1.4048, + "step": 3524 + }, + { + "epoch": 0.37, + "learning_rate": 1.5886436703084332e-05, + "loss": 1.4303, + "step": 3525 + }, + { + "epoch": 0.37, + "learning_rate": 1.5883477389670367e-05, + "loss": 1.3684, + "step": 3526 + }, + { + "epoch": 0.37, + "learning_rate": 1.5880517288021602e-05, + "loss": 1.3701, + "step": 3527 + }, + { + "epoch": 0.37, + "learning_rate": 1.587755639853462e-05, + "loss": 1.4308, + "step": 3528 + }, + { + "epoch": 0.37, + "learning_rate": 1.5874594721606096e-05, + "loss": 1.3981, + "step": 3529 + }, + { + "epoch": 0.37, + "learning_rate": 1.5871632257632823e-05, + "loss": 1.5906, + "step": 3530 + }, + { + "epoch": 0.37, + "learning_rate": 1.5868669007011696e-05, + "loss": 1.4642, + "step": 3531 + }, + { + "epoch": 0.37, + "learning_rate": 1.586570497013971e-05, + "loss": 1.411, + "step": 3532 + }, + { + "epoch": 0.37, + "learning_rate": 1.586274014741397e-05, + "loss": 1.3942, + "step": 3533 + }, + { + "epoch": 0.37, + "learning_rate": 1.5859774539231693e-05, + "loss": 1.3952, + "step": 3534 + }, + { + "epoch": 0.37, + "learning_rate": 1.585680814599019e-05, + "loss": 1.4009, + "step": 3535 + }, + { + "epoch": 0.37, + "learning_rate": 1.585384096808688e-05, + "loss": 1.3238, + "step": 3536 + }, + { + "epoch": 0.37, + "learning_rate": 1.585087300591929e-05, + "loss": 1.346, + "step": 3537 + }, + { + "epoch": 0.37, + "learning_rate": 1.584790425988505e-05, + "loss": 1.3739, + "step": 3538 + }, + { + "epoch": 0.37, + "learning_rate": 1.5844934730381895e-05, + "loss": 1.4264, + "step": 3539 + }, + { + "epoch": 0.37, + "learning_rate": 1.5841964417807668e-05, + "loss": 1.4675, + "step": 3540 + }, + { + "epoch": 0.37, + "learning_rate": 1.5838993322560314e-05, + "loss": 1.3337, + "step": 3541 + }, + { + "epoch": 0.37, + "learning_rate": 1.5836021445037883e-05, + "loss": 1.4052, + "step": 3542 + }, + { + "epoch": 0.37, + "learning_rate": 1.583304878563853e-05, + "loss": 1.4311, + "step": 3543 + }, + { + "epoch": 0.37, + "learning_rate": 1.5830075344760513e-05, + "loss": 1.386, + "step": 3544 + }, + { + "epoch": 0.37, + "learning_rate": 1.58271011228022e-05, + "loss": 1.387, + "step": 3545 + }, + { + "epoch": 0.37, + "learning_rate": 1.582412612016206e-05, + "loss": 1.3601, + "step": 3546 + }, + { + "epoch": 0.37, + "learning_rate": 1.5821150337238663e-05, + "loss": 1.5111, + "step": 3547 + }, + { + "epoch": 0.37, + "learning_rate": 1.5818173774430697e-05, + "loss": 1.471, + "step": 3548 + }, + { + "epoch": 0.37, + "learning_rate": 1.581519643213693e-05, + "loss": 1.4442, + "step": 3549 + }, + { + "epoch": 0.37, + "learning_rate": 1.5812218310756263e-05, + "loss": 1.467, + "step": 3550 + }, + { + "epoch": 0.37, + "learning_rate": 1.5809239410687683e-05, + "loss": 1.3731, + "step": 3551 + }, + { + "epoch": 0.37, + "learning_rate": 1.5806259732330286e-05, + "loss": 1.4072, + "step": 3552 + }, + { + "epoch": 0.37, + "learning_rate": 1.5803279276083268e-05, + "loss": 1.3636, + "step": 3553 + }, + { + "epoch": 0.37, + "learning_rate": 1.5800298042345938e-05, + "loss": 1.3915, + "step": 3554 + }, + { + "epoch": 0.37, + "learning_rate": 1.5797316031517705e-05, + "loss": 1.5038, + "step": 3555 + }, + { + "epoch": 0.37, + "learning_rate": 1.5794333243998082e-05, + "loss": 1.4455, + "step": 3556 + }, + { + "epoch": 0.37, + "learning_rate": 1.5791349680186684e-05, + "loss": 1.5062, + "step": 3557 + }, + { + "epoch": 0.37, + "learning_rate": 1.5788365340483234e-05, + "loss": 1.3899, + "step": 3558 + }, + { + "epoch": 0.37, + "learning_rate": 1.5785380225287554e-05, + "loss": 1.4946, + "step": 3559 + }, + { + "epoch": 0.37, + "learning_rate": 1.5782394334999572e-05, + "loss": 1.3859, + "step": 3560 + }, + { + "epoch": 0.37, + "learning_rate": 1.577940767001933e-05, + "loss": 1.541, + "step": 3561 + }, + { + "epoch": 0.37, + "learning_rate": 1.5776420230746952e-05, + "loss": 1.4952, + "step": 3562 + }, + { + "epoch": 0.37, + "learning_rate": 1.5773432017582684e-05, + "loss": 1.6055, + "step": 3563 + }, + { + "epoch": 0.37, + "learning_rate": 1.577044303092687e-05, + "loss": 1.4661, + "step": 3564 + }, + { + "epoch": 0.37, + "learning_rate": 1.576745327117996e-05, + "loss": 1.4082, + "step": 3565 + }, + { + "epoch": 0.37, + "learning_rate": 1.5764462738742493e-05, + "loss": 1.4005, + "step": 3566 + }, + { + "epoch": 0.37, + "learning_rate": 1.5761471434015137e-05, + "loss": 1.3959, + "step": 3567 + }, + { + "epoch": 0.37, + "learning_rate": 1.5758479357398645e-05, + "loss": 1.4567, + "step": 3568 + }, + { + "epoch": 0.37, + "learning_rate": 1.575548650929388e-05, + "loss": 1.3791, + "step": 3569 + }, + { + "epoch": 0.37, + "learning_rate": 1.57524928901018e-05, + "loss": 1.4428, + "step": 3570 + }, + { + "epoch": 0.37, + "learning_rate": 1.5749498500223486e-05, + "loss": 1.3864, + "step": 3571 + }, + { + "epoch": 0.37, + "learning_rate": 1.5746503340060097e-05, + "loss": 1.4019, + "step": 3572 + }, + { + "epoch": 0.37, + "learning_rate": 1.574350741001291e-05, + "loss": 1.5436, + "step": 3573 + }, + { + "epoch": 0.37, + "learning_rate": 1.5740510710483308e-05, + "loss": 1.4637, + "step": 3574 + }, + { + "epoch": 0.37, + "learning_rate": 1.5737513241872767e-05, + "loss": 1.5097, + "step": 3575 + }, + { + "epoch": 0.38, + "learning_rate": 1.5734515004582873e-05, + "loss": 1.5143, + "step": 3576 + }, + { + "epoch": 0.38, + "learning_rate": 1.5731515999015315e-05, + "loss": 1.3926, + "step": 3577 + }, + { + "epoch": 0.38, + "learning_rate": 1.5728516225571874e-05, + "loss": 1.4242, + "step": 3578 + }, + { + "epoch": 0.38, + "learning_rate": 1.5725515684654453e-05, + "loss": 1.4429, + "step": 3579 + }, + { + "epoch": 0.38, + "learning_rate": 1.572251437666504e-05, + "loss": 1.4638, + "step": 3580 + }, + { + "epoch": 0.38, + "learning_rate": 1.5719512302005735e-05, + "loss": 1.3381, + "step": 3581 + }, + { + "epoch": 0.38, + "learning_rate": 1.571650946107874e-05, + "loss": 1.4342, + "step": 3582 + }, + { + "epoch": 0.38, + "eval_loss": 1.4705015420913696, + "eval_runtime": 77.3664, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3582 + }, + { + "epoch": 0.38, + "learning_rate": 1.571350585428636e-05, + "loss": 1.3991, + "step": 3583 + }, + { + "epoch": 0.38, + "learning_rate": 1.5710501482030998e-05, + "loss": 1.4274, + "step": 3584 + }, + { + "epoch": 0.38, + "learning_rate": 1.5707496344715166e-05, + "loss": 1.438, + "step": 3585 + }, + { + "epoch": 0.38, + "learning_rate": 1.570449044274147e-05, + "loss": 1.4453, + "step": 3586 + }, + { + "epoch": 0.38, + "learning_rate": 1.570148377651263e-05, + "loss": 1.4022, + "step": 3587 + }, + { + "epoch": 0.38, + "learning_rate": 1.5698476346431454e-05, + "loss": 1.4312, + "step": 3588 + }, + { + "epoch": 0.38, + "learning_rate": 1.569546815290087e-05, + "loss": 1.4329, + "step": 3589 + }, + { + "epoch": 0.38, + "learning_rate": 1.569245919632389e-05, + "loss": 1.4036, + "step": 3590 + }, + { + "epoch": 0.38, + "learning_rate": 1.5689449477103644e-05, + "loss": 1.412, + "step": 3591 + }, + { + "epoch": 0.38, + "learning_rate": 1.5686438995643353e-05, + "loss": 1.4492, + "step": 3592 + }, + { + "epoch": 0.38, + "learning_rate": 1.5683427752346343e-05, + "loss": 1.4555, + "step": 3593 + }, + { + "epoch": 0.38, + "learning_rate": 1.5680415747616047e-05, + "loss": 1.5594, + "step": 3594 + }, + { + "epoch": 0.38, + "learning_rate": 1.5677402981855993e-05, + "loss": 1.4813, + "step": 3595 + }, + { + "epoch": 0.38, + "learning_rate": 1.567438945546982e-05, + "loss": 1.5919, + "step": 3596 + }, + { + "epoch": 0.38, + "learning_rate": 1.5671375168861255e-05, + "loss": 1.4235, + "step": 3597 + }, + { + "epoch": 0.38, + "learning_rate": 1.5668360122434135e-05, + "loss": 1.441, + "step": 3598 + }, + { + "epoch": 0.38, + "learning_rate": 1.566534431659241e-05, + "loss": 1.5847, + "step": 3599 + }, + { + "epoch": 0.38, + "learning_rate": 1.566232775174011e-05, + "loss": 1.6123, + "step": 3600 + }, + { + "epoch": 0.38, + "learning_rate": 1.5659310428281374e-05, + "loss": 1.4916, + "step": 3601 + }, + { + "epoch": 0.38, + "learning_rate": 1.5656292346620457e-05, + "loss": 1.4603, + "step": 3602 + }, + { + "epoch": 0.38, + "learning_rate": 1.56532735071617e-05, + "loss": 1.4423, + "step": 3603 + }, + { + "epoch": 0.38, + "learning_rate": 1.5650253910309547e-05, + "loss": 1.4814, + "step": 3604 + }, + { + "epoch": 0.38, + "learning_rate": 1.5647233556468552e-05, + "loss": 1.4015, + "step": 3605 + }, + { + "epoch": 0.38, + "learning_rate": 1.564421244604336e-05, + "loss": 1.3798, + "step": 3606 + }, + { + "epoch": 0.38, + "learning_rate": 1.5641190579438723e-05, + "loss": 1.4259, + "step": 3607 + }, + { + "epoch": 0.38, + "learning_rate": 1.5638167957059493e-05, + "loss": 1.3493, + "step": 3608 + }, + { + "epoch": 0.38, + "learning_rate": 1.5635144579310626e-05, + "loss": 1.3433, + "step": 3609 + }, + { + "epoch": 0.38, + "learning_rate": 1.5632120446597177e-05, + "loss": 1.4661, + "step": 3610 + }, + { + "epoch": 0.38, + "learning_rate": 1.5629095559324297e-05, + "loss": 1.4205, + "step": 3611 + }, + { + "epoch": 0.38, + "learning_rate": 1.562606991789725e-05, + "loss": 1.3976, + "step": 3612 + }, + { + "epoch": 0.38, + "learning_rate": 1.5623043522721393e-05, + "loss": 1.4261, + "step": 3613 + }, + { + "epoch": 0.38, + "learning_rate": 1.562001637420218e-05, + "loss": 1.4358, + "step": 3614 + }, + { + "epoch": 0.38, + "learning_rate": 1.5616988472745175e-05, + "loss": 1.437, + "step": 3615 + }, + { + "epoch": 0.38, + "learning_rate": 1.561395981875604e-05, + "loss": 1.3735, + "step": 3616 + }, + { + "epoch": 0.38, + "learning_rate": 1.5610930412640532e-05, + "loss": 1.4357, + "step": 3617 + }, + { + "epoch": 0.38, + "learning_rate": 1.560790025480452e-05, + "loss": 1.4003, + "step": 3618 + }, + { + "epoch": 0.38, + "learning_rate": 1.5604869345653965e-05, + "loss": 1.4127, + "step": 3619 + }, + { + "epoch": 0.38, + "learning_rate": 1.5601837685594927e-05, + "loss": 1.4666, + "step": 3620 + }, + { + "epoch": 0.38, + "learning_rate": 1.5598805275033574e-05, + "loss": 1.4106, + "step": 3621 + }, + { + "epoch": 0.38, + "learning_rate": 1.5595772114376174e-05, + "loss": 1.3857, + "step": 3622 + }, + { + "epoch": 0.38, + "learning_rate": 1.5592738204029086e-05, + "loss": 1.4704, + "step": 3623 + }, + { + "epoch": 0.38, + "learning_rate": 1.558970354439878e-05, + "loss": 1.4649, + "step": 3624 + }, + { + "epoch": 0.38, + "learning_rate": 1.5586668135891824e-05, + "loss": 1.4812, + "step": 3625 + }, + { + "epoch": 0.38, + "learning_rate": 1.5583631978914882e-05, + "loss": 1.3507, + "step": 3626 + }, + { + "epoch": 0.38, + "learning_rate": 1.5580595073874718e-05, + "loss": 1.3762, + "step": 3627 + }, + { + "epoch": 0.38, + "learning_rate": 1.557755742117821e-05, + "loss": 1.4169, + "step": 3628 + }, + { + "epoch": 0.38, + "learning_rate": 1.557451902123231e-05, + "loss": 1.4098, + "step": 3629 + }, + { + "epoch": 0.38, + "learning_rate": 1.55714798744441e-05, + "loss": 1.5526, + "step": 3630 + }, + { + "epoch": 0.38, + "learning_rate": 1.556843998122074e-05, + "loss": 1.4414, + "step": 3631 + }, + { + "epoch": 0.38, + "learning_rate": 1.5565399341969497e-05, + "loss": 1.4134, + "step": 3632 + }, + { + "epoch": 0.38, + "learning_rate": 1.556235795709774e-05, + "loss": 1.4718, + "step": 3633 + }, + { + "epoch": 0.38, + "learning_rate": 1.5559315827012937e-05, + "loss": 1.412, + "step": 3634 + }, + { + "epoch": 0.38, + "learning_rate": 1.5556272952122657e-05, + "loss": 1.4119, + "step": 3635 + }, + { + "epoch": 0.38, + "learning_rate": 1.5553229332834564e-05, + "loss": 1.3999, + "step": 3636 + }, + { + "epoch": 0.38, + "learning_rate": 1.5550184969556428e-05, + "loss": 1.4626, + "step": 3637 + }, + { + "epoch": 0.38, + "learning_rate": 1.5547139862696113e-05, + "loss": 1.3811, + "step": 3638 + }, + { + "epoch": 0.38, + "learning_rate": 1.5544094012661583e-05, + "loss": 1.4053, + "step": 3639 + }, + { + "epoch": 0.38, + "learning_rate": 1.5541047419860907e-05, + "loss": 1.4059, + "step": 3640 + }, + { + "epoch": 0.38, + "learning_rate": 1.553800008470225e-05, + "loss": 1.4717, + "step": 3641 + }, + { + "epoch": 0.38, + "learning_rate": 1.553495200759388e-05, + "loss": 1.399, + "step": 3642 + }, + { + "epoch": 0.38, + "learning_rate": 1.5531903188944154e-05, + "loss": 1.4143, + "step": 3643 + }, + { + "epoch": 0.38, + "learning_rate": 1.5528853629161536e-05, + "loss": 1.4414, + "step": 3644 + }, + { + "epoch": 0.38, + "learning_rate": 1.5525803328654592e-05, + "loss": 1.4206, + "step": 3645 + }, + { + "epoch": 0.38, + "learning_rate": 1.5522752287831982e-05, + "loss": 1.3869, + "step": 3646 + }, + { + "epoch": 0.38, + "learning_rate": 1.551970050710247e-05, + "loss": 1.5434, + "step": 3647 + }, + { + "epoch": 0.38, + "learning_rate": 1.5516647986874914e-05, + "loss": 1.4574, + "step": 3648 + }, + { + "epoch": 0.38, + "learning_rate": 1.5513594727558273e-05, + "loss": 1.4353, + "step": 3649 + }, + { + "epoch": 0.38, + "learning_rate": 1.5510540729561606e-05, + "loss": 1.4122, + "step": 3650 + }, + { + "epoch": 0.38, + "learning_rate": 1.550748599329407e-05, + "loss": 1.4077, + "step": 3651 + }, + { + "epoch": 0.38, + "learning_rate": 1.550443051916492e-05, + "loss": 1.4433, + "step": 3652 + }, + { + "epoch": 0.38, + "learning_rate": 1.5501374307583514e-05, + "loss": 1.54, + "step": 3653 + }, + { + "epoch": 0.38, + "learning_rate": 1.5498317358959302e-05, + "loss": 1.4522, + "step": 3654 + }, + { + "epoch": 0.38, + "learning_rate": 1.5495259673701842e-05, + "loss": 1.4175, + "step": 3655 + }, + { + "epoch": 0.38, + "learning_rate": 1.5492201252220777e-05, + "loss": 1.4637, + "step": 3656 + }, + { + "epoch": 0.38, + "learning_rate": 1.5489142094925863e-05, + "loss": 1.4701, + "step": 3657 + }, + { + "epoch": 0.38, + "learning_rate": 1.548608220222695e-05, + "loss": 1.4095, + "step": 3658 + }, + { + "epoch": 0.38, + "learning_rate": 1.548302157453398e-05, + "loss": 1.3903, + "step": 3659 + }, + { + "epoch": 0.38, + "learning_rate": 1.5479960212257002e-05, + "loss": 1.4062, + "step": 3660 + }, + { + "epoch": 0.38, + "learning_rate": 1.5476898115806157e-05, + "loss": 1.4706, + "step": 3661 + }, + { + "epoch": 0.38, + "learning_rate": 1.547383528559169e-05, + "loss": 1.4423, + "step": 3662 + }, + { + "epoch": 0.38, + "learning_rate": 1.547077172202394e-05, + "loss": 1.4418, + "step": 3663 + }, + { + "epoch": 0.38, + "learning_rate": 1.5467707425513347e-05, + "loss": 1.4553, + "step": 3664 + }, + { + "epoch": 0.38, + "learning_rate": 1.5464642396470443e-05, + "loss": 1.435, + "step": 3665 + }, + { + "epoch": 0.38, + "learning_rate": 1.5461576635305873e-05, + "loss": 1.4105, + "step": 3666 + }, + { + "epoch": 0.38, + "learning_rate": 1.5458510142430364e-05, + "loss": 1.4118, + "step": 3667 + }, + { + "epoch": 0.38, + "learning_rate": 1.5455442918254746e-05, + "loss": 1.4096, + "step": 3668 + }, + { + "epoch": 0.38, + "learning_rate": 1.545237496318995e-05, + "loss": 1.4248, + "step": 3669 + }, + { + "epoch": 0.38, + "learning_rate": 1.5449306277647003e-05, + "loss": 1.4591, + "step": 3670 + }, + { + "epoch": 0.38, + "learning_rate": 1.544623686203703e-05, + "loss": 1.4764, + "step": 3671 + }, + { + "epoch": 0.39, + "learning_rate": 1.5443166716771255e-05, + "loss": 1.4329, + "step": 3672 + }, + { + "epoch": 0.39, + "learning_rate": 1.5440095842260995e-05, + "loss": 1.4023, + "step": 3673 + }, + { + "epoch": 0.39, + "learning_rate": 1.5437024238917674e-05, + "loss": 1.3802, + "step": 3674 + }, + { + "epoch": 0.39, + "learning_rate": 1.5433951907152806e-05, + "loss": 1.4627, + "step": 3675 + }, + { + "epoch": 0.39, + "learning_rate": 1.5430878847378e-05, + "loss": 1.5164, + "step": 3676 + }, + { + "epoch": 0.39, + "learning_rate": 1.542780506000497e-05, + "loss": 1.3546, + "step": 3677 + }, + { + "epoch": 0.39, + "learning_rate": 1.542473054544553e-05, + "loss": 1.4415, + "step": 3678 + }, + { + "epoch": 0.39, + "learning_rate": 1.5421655304111573e-05, + "loss": 1.4093, + "step": 3679 + }, + { + "epoch": 0.39, + "learning_rate": 1.5418579336415114e-05, + "loss": 1.3943, + "step": 3680 + }, + { + "epoch": 0.39, + "learning_rate": 1.5415502642768252e-05, + "loss": 1.3659, + "step": 3681 + }, + { + "epoch": 0.39, + "learning_rate": 1.541242522358318e-05, + "loss": 1.4322, + "step": 3682 + }, + { + "epoch": 0.39, + "learning_rate": 1.5409347079272198e-05, + "loss": 1.4064, + "step": 3683 + }, + { + "epoch": 0.39, + "learning_rate": 1.5406268210247693e-05, + "loss": 1.4031, + "step": 3684 + }, + { + "epoch": 0.39, + "learning_rate": 1.540318861692216e-05, + "loss": 1.3449, + "step": 3685 + }, + { + "epoch": 0.39, + "learning_rate": 1.5400108299708182e-05, + "loss": 1.5536, + "step": 3686 + }, + { + "epoch": 0.39, + "learning_rate": 1.5397027259018442e-05, + "loss": 1.4106, + "step": 3687 + }, + { + "epoch": 0.39, + "learning_rate": 1.5393945495265722e-05, + "loss": 1.4309, + "step": 3688 + }, + { + "epoch": 0.39, + "learning_rate": 1.53908630088629e-05, + "loss": 1.3765, + "step": 3689 + }, + { + "epoch": 0.39, + "learning_rate": 1.5387779800222947e-05, + "loss": 1.3809, + "step": 3690 + }, + { + "epoch": 0.39, + "learning_rate": 1.5384695869758938e-05, + "loss": 1.4758, + "step": 3691 + }, + { + "epoch": 0.39, + "learning_rate": 1.5381611217884032e-05, + "loss": 1.4249, + "step": 3692 + }, + { + "epoch": 0.39, + "learning_rate": 1.5378525845011503e-05, + "loss": 1.4133, + "step": 3693 + }, + { + "epoch": 0.39, + "learning_rate": 1.5375439751554708e-05, + "loss": 1.418, + "step": 3694 + }, + { + "epoch": 0.39, + "learning_rate": 1.53723529379271e-05, + "loss": 1.441, + "step": 3695 + }, + { + "epoch": 0.39, + "learning_rate": 1.536926540454224e-05, + "loss": 1.3919, + "step": 3696 + }, + { + "epoch": 0.39, + "learning_rate": 1.5366177151813775e-05, + "loss": 1.3722, + "step": 3697 + }, + { + "epoch": 0.39, + "learning_rate": 1.536308818015545e-05, + "loss": 1.4727, + "step": 3698 + }, + { + "epoch": 0.39, + "learning_rate": 1.535999848998111e-05, + "loss": 1.442, + "step": 3699 + }, + { + "epoch": 0.39, + "learning_rate": 1.535690808170469e-05, + "loss": 1.3884, + "step": 3700 + }, + { + "epoch": 0.39, + "learning_rate": 1.535381695574023e-05, + "loss": 1.3226, + "step": 3701 + }, + { + "epoch": 0.39, + "learning_rate": 1.535072511250186e-05, + "loss": 1.4403, + "step": 3702 + }, + { + "epoch": 0.39, + "learning_rate": 1.5347632552403808e-05, + "loss": 1.4144, + "step": 3703 + }, + { + "epoch": 0.39, + "learning_rate": 1.5344539275860395e-05, + "loss": 1.3514, + "step": 3704 + }, + { + "epoch": 0.39, + "learning_rate": 1.5341445283286044e-05, + "loss": 1.519, + "step": 3705 + }, + { + "epoch": 0.39, + "learning_rate": 1.5338350575095268e-05, + "loss": 1.4251, + "step": 3706 + }, + { + "epoch": 0.39, + "learning_rate": 1.5335255151702685e-05, + "loss": 1.392, + "step": 3707 + }, + { + "epoch": 0.39, + "learning_rate": 1.533215901352299e-05, + "loss": 1.3838, + "step": 3708 + }, + { + "epoch": 0.39, + "learning_rate": 1.532906216097099e-05, + "loss": 1.444, + "step": 3709 + }, + { + "epoch": 0.39, + "learning_rate": 1.5325964594461594e-05, + "loss": 1.3459, + "step": 3710 + }, + { + "epoch": 0.39, + "learning_rate": 1.5322866314409783e-05, + "loss": 1.4155, + "step": 3711 + }, + { + "epoch": 0.39, + "learning_rate": 1.5319767321230657e-05, + "loss": 1.4057, + "step": 3712 + }, + { + "epoch": 0.39, + "learning_rate": 1.5316667615339392e-05, + "loss": 1.382, + "step": 3713 + }, + { + "epoch": 0.39, + "learning_rate": 1.5313567197151277e-05, + "loss": 1.3634, + "step": 3714 + }, + { + "epoch": 0.39, + "learning_rate": 1.5310466067081688e-05, + "loss": 1.3434, + "step": 3715 + }, + { + "epoch": 0.39, + "learning_rate": 1.530736422554609e-05, + "loss": 1.4553, + "step": 3716 + }, + { + "epoch": 0.39, + "learning_rate": 1.5304261672960055e-05, + "loss": 1.4193, + "step": 3717 + }, + { + "epoch": 0.39, + "learning_rate": 1.5301158409739242e-05, + "loss": 1.3955, + "step": 3718 + }, + { + "epoch": 0.39, + "learning_rate": 1.5298054436299413e-05, + "loss": 1.4592, + "step": 3719 + }, + { + "epoch": 0.39, + "learning_rate": 1.529494975305642e-05, + "loss": 1.738, + "step": 3720 + }, + { + "epoch": 0.39, + "learning_rate": 1.529184436042621e-05, + "loss": 1.438, + "step": 3721 + }, + { + "epoch": 0.39, + "learning_rate": 1.528873825882482e-05, + "loss": 1.3445, + "step": 3722 + }, + { + "epoch": 0.39, + "learning_rate": 1.5285631448668395e-05, + "loss": 1.4168, + "step": 3723 + }, + { + "epoch": 0.39, + "learning_rate": 1.528252393037317e-05, + "loss": 1.4088, + "step": 3724 + }, + { + "epoch": 0.39, + "learning_rate": 1.5279415704355468e-05, + "loss": 1.4484, + "step": 3725 + }, + { + "epoch": 0.39, + "learning_rate": 1.5276306771031708e-05, + "loss": 1.4706, + "step": 3726 + }, + { + "epoch": 0.39, + "learning_rate": 1.527319713081841e-05, + "loss": 1.3466, + "step": 3727 + }, + { + "epoch": 0.39, + "learning_rate": 1.5270086784132196e-05, + "loss": 1.427, + "step": 3728 + }, + { + "epoch": 0.39, + "learning_rate": 1.5266975731389754e-05, + "loss": 1.4596, + "step": 3729 + }, + { + "epoch": 0.39, + "learning_rate": 1.52638639730079e-05, + "loss": 1.405, + "step": 3730 + }, + { + "epoch": 0.39, + "learning_rate": 1.5260751509403518e-05, + "loss": 1.4572, + "step": 3731 + }, + { + "epoch": 0.39, + "learning_rate": 1.5257638340993608e-05, + "loss": 1.3827, + "step": 3732 + }, + { + "epoch": 0.39, + "learning_rate": 1.5254524468195251e-05, + "loss": 1.3712, + "step": 3733 + }, + { + "epoch": 0.39, + "learning_rate": 1.5251409891425626e-05, + "loss": 1.4541, + "step": 3734 + }, + { + "epoch": 0.39, + "learning_rate": 1.5248294611102006e-05, + "loss": 1.5279, + "step": 3735 + }, + { + "epoch": 0.39, + "learning_rate": 1.5245178627641759e-05, + "loss": 1.3722, + "step": 3736 + }, + { + "epoch": 0.39, + "learning_rate": 1.5242061941462348e-05, + "loss": 1.5158, + "step": 3737 + }, + { + "epoch": 0.39, + "learning_rate": 1.523894455298132e-05, + "loss": 1.4274, + "step": 3738 + }, + { + "epoch": 0.39, + "learning_rate": 1.5235826462616338e-05, + "loss": 1.4543, + "step": 3739 + }, + { + "epoch": 0.39, + "learning_rate": 1.5232707670785144e-05, + "loss": 1.5011, + "step": 3740 + }, + { + "epoch": 0.39, + "learning_rate": 1.5229588177905568e-05, + "loss": 1.24, + "step": 3741 + }, + { + "epoch": 0.39, + "learning_rate": 1.5226467984395544e-05, + "loss": 1.4253, + "step": 3742 + }, + { + "epoch": 0.39, + "learning_rate": 1.5223347090673102e-05, + "loss": 1.3736, + "step": 3743 + }, + { + "epoch": 0.39, + "learning_rate": 1.522022549715636e-05, + "loss": 1.4587, + "step": 3744 + }, + { + "epoch": 0.39, + "learning_rate": 1.521710320426353e-05, + "loss": 1.5024, + "step": 3745 + }, + { + "epoch": 0.39, + "learning_rate": 1.521398021241292e-05, + "loss": 1.427, + "step": 3746 + }, + { + "epoch": 0.39, + "learning_rate": 1.5210856522022929e-05, + "loss": 1.3387, + "step": 3747 + }, + { + "epoch": 0.39, + "learning_rate": 1.5207732133512055e-05, + "loss": 1.3819, + "step": 3748 + }, + { + "epoch": 0.39, + "learning_rate": 1.5204607047298883e-05, + "loss": 1.4571, + "step": 3749 + }, + { + "epoch": 0.39, + "learning_rate": 1.5201481263802094e-05, + "loss": 1.3592, + "step": 3750 + }, + { + "epoch": 0.39, + "learning_rate": 1.5198354783440464e-05, + "loss": 1.3912, + "step": 3751 + }, + { + "epoch": 0.39, + "learning_rate": 1.519522760663286e-05, + "loss": 1.4986, + "step": 3752 + }, + { + "epoch": 0.39, + "learning_rate": 1.5192099733798243e-05, + "loss": 1.4106, + "step": 3753 + }, + { + "epoch": 0.39, + "learning_rate": 1.5188971165355667e-05, + "loss": 1.4145, + "step": 3754 + }, + { + "epoch": 0.39, + "learning_rate": 1.5185841901724282e-05, + "loss": 1.3915, + "step": 3755 + }, + { + "epoch": 0.39, + "learning_rate": 1.5182711943323329e-05, + "loss": 1.4014, + "step": 3756 + }, + { + "epoch": 0.39, + "learning_rate": 1.5179581290572141e-05, + "loss": 1.3651, + "step": 3757 + }, + { + "epoch": 0.39, + "learning_rate": 1.5176449943890147e-05, + "loss": 1.3653, + "step": 3758 + }, + { + "epoch": 0.39, + "learning_rate": 1.5173317903696862e-05, + "loss": 1.4486, + "step": 3759 + }, + { + "epoch": 0.39, + "learning_rate": 1.5170185170411906e-05, + "loss": 1.4459, + "step": 3760 + }, + { + "epoch": 0.39, + "learning_rate": 1.5167051744454977e-05, + "loss": 1.4215, + "step": 3761 + }, + { + "epoch": 0.39, + "learning_rate": 1.5163917626245877e-05, + "loss": 1.4379, + "step": 3762 + }, + { + "epoch": 0.39, + "learning_rate": 1.51607828162045e-05, + "loss": 1.4147, + "step": 3763 + }, + { + "epoch": 0.39, + "learning_rate": 1.5157647314750827e-05, + "loss": 1.4011, + "step": 3764 + }, + { + "epoch": 0.39, + "learning_rate": 1.5154511122304936e-05, + "loss": 1.4309, + "step": 3765 + }, + { + "epoch": 0.39, + "learning_rate": 1.5151374239286993e-05, + "loss": 1.4382, + "step": 3766 + }, + { + "epoch": 0.4, + "learning_rate": 1.5148236666117266e-05, + "loss": 1.405, + "step": 3767 + }, + { + "epoch": 0.4, + "learning_rate": 1.5145098403216104e-05, + "loss": 1.4223, + "step": 3768 + }, + { + "epoch": 0.4, + "learning_rate": 1.5141959451003951e-05, + "loss": 1.4084, + "step": 3769 + }, + { + "epoch": 0.4, + "learning_rate": 1.5138819809901356e-05, + "loss": 1.4063, + "step": 3770 + }, + { + "epoch": 0.4, + "learning_rate": 1.513567948032894e-05, + "loss": 1.3299, + "step": 3771 + }, + { + "epoch": 0.4, + "learning_rate": 1.5132538462707431e-05, + "loss": 1.3901, + "step": 3772 + }, + { + "epoch": 0.4, + "learning_rate": 1.5129396757457646e-05, + "loss": 1.4249, + "step": 3773 + }, + { + "epoch": 0.4, + "learning_rate": 1.512625436500049e-05, + "loss": 1.4087, + "step": 3774 + }, + { + "epoch": 0.4, + "learning_rate": 1.5123111285756964e-05, + "loss": 1.3521, + "step": 3775 + }, + { + "epoch": 0.4, + "learning_rate": 1.5119967520148163e-05, + "loss": 1.4097, + "step": 3776 + }, + { + "epoch": 0.4, + "learning_rate": 1.5116823068595261e-05, + "loss": 1.4871, + "step": 3777 + }, + { + "epoch": 0.4, + "learning_rate": 1.5113677931519543e-05, + "loss": 1.44, + "step": 3778 + }, + { + "epoch": 0.4, + "learning_rate": 1.5110532109342377e-05, + "loss": 1.4518, + "step": 3779 + }, + { + "epoch": 0.4, + "learning_rate": 1.5107385602485214e-05, + "loss": 1.3961, + "step": 3780 + }, + { + "epoch": 0.4, + "learning_rate": 1.5104238411369614e-05, + "loss": 1.4341, + "step": 3781 + }, + { + "epoch": 0.4, + "eval_loss": 1.4642821550369263, + "eval_runtime": 77.3595, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 3781 + }, + { + "epoch": 0.4, + "learning_rate": 1.5101090536417218e-05, + "loss": 1.403, + "step": 3782 + }, + { + "epoch": 0.4, + "learning_rate": 1.5097941978049754e-05, + "loss": 1.4103, + "step": 3783 + }, + { + "epoch": 0.4, + "learning_rate": 1.5094792736689052e-05, + "loss": 1.3478, + "step": 3784 + }, + { + "epoch": 0.4, + "learning_rate": 1.5091642812757035e-05, + "loss": 1.4134, + "step": 3785 + }, + { + "epoch": 0.4, + "learning_rate": 1.5088492206675701e-05, + "loss": 1.4134, + "step": 3786 + }, + { + "epoch": 0.4, + "learning_rate": 1.5085340918867162e-05, + "loss": 1.1494, + "step": 3787 + }, + { + "epoch": 0.4, + "learning_rate": 1.5082188949753598e-05, + "loss": 1.2385, + "step": 3788 + }, + { + "epoch": 0.4, + "learning_rate": 1.5079036299757299e-05, + "loss": 1.4258, + "step": 3789 + }, + { + "epoch": 0.4, + "learning_rate": 1.5075882969300639e-05, + "loss": 1.3781, + "step": 3790 + }, + { + "epoch": 0.4, + "learning_rate": 1.507272895880608e-05, + "loss": 1.5096, + "step": 3791 + }, + { + "epoch": 0.4, + "learning_rate": 1.5069574268696179e-05, + "loss": 1.366, + "step": 3792 + }, + { + "epoch": 0.4, + "learning_rate": 1.5066418899393584e-05, + "loss": 1.3792, + "step": 3793 + }, + { + "epoch": 0.4, + "learning_rate": 1.506326285132104e-05, + "loss": 1.4987, + "step": 3794 + }, + { + "epoch": 0.4, + "learning_rate": 1.5060106124901364e-05, + "loss": 1.445, + "step": 3795 + }, + { + "epoch": 0.4, + "learning_rate": 1.5056948720557482e-05, + "loss": 1.5071, + "step": 3796 + }, + { + "epoch": 0.4, + "learning_rate": 1.505379063871241e-05, + "loss": 1.4029, + "step": 3797 + }, + { + "epoch": 0.4, + "learning_rate": 1.5050631879789244e-05, + "loss": 1.5263, + "step": 3798 + }, + { + "epoch": 0.4, + "learning_rate": 1.5047472444211175e-05, + "loss": 1.3906, + "step": 3799 + }, + { + "epoch": 0.4, + "learning_rate": 1.5044312332401494e-05, + "loss": 1.7352, + "step": 3800 + }, + { + "epoch": 0.4, + "learning_rate": 1.5041151544783565e-05, + "loss": 1.3946, + "step": 3801 + }, + { + "epoch": 0.4, + "learning_rate": 1.5037990081780862e-05, + "loss": 1.3592, + "step": 3802 + }, + { + "epoch": 0.4, + "learning_rate": 1.503482794381693e-05, + "loss": 1.3991, + "step": 3803 + }, + { + "epoch": 0.4, + "learning_rate": 1.5031665131315423e-05, + "loss": 1.4271, + "step": 3804 + }, + { + "epoch": 0.4, + "learning_rate": 1.502850164470007e-05, + "loss": 1.4305, + "step": 3805 + }, + { + "epoch": 0.4, + "learning_rate": 1.5025337484394701e-05, + "loss": 1.4116, + "step": 3806 + }, + { + "epoch": 0.4, + "learning_rate": 1.5022172650823232e-05, + "loss": 1.4242, + "step": 3807 + }, + { + "epoch": 0.4, + "learning_rate": 1.5019007144409667e-05, + "loss": 1.4427, + "step": 3808 + }, + { + "epoch": 0.4, + "learning_rate": 1.5015840965578106e-05, + "loss": 1.3705, + "step": 3809 + }, + { + "epoch": 0.4, + "learning_rate": 1.5012674114752732e-05, + "loss": 1.4498, + "step": 3810 + }, + { + "epoch": 0.4, + "learning_rate": 1.5009506592357822e-05, + "loss": 1.489, + "step": 3811 + }, + { + "epoch": 0.4, + "learning_rate": 1.5006338398817746e-05, + "loss": 1.4801, + "step": 3812 + }, + { + "epoch": 0.4, + "learning_rate": 1.5003169534556956e-05, + "loss": 1.3468, + "step": 3813 + }, + { + "epoch": 0.4, + "learning_rate": 1.5000000000000002e-05, + "loss": 1.4211, + "step": 3814 + }, + { + "epoch": 0.4, + "learning_rate": 1.4996829795571518e-05, + "loss": 1.4683, + "step": 3815 + }, + { + "epoch": 0.4, + "learning_rate": 1.499365892169623e-05, + "loss": 1.4441, + "step": 3816 + }, + { + "epoch": 0.4, + "learning_rate": 1.4990487378798958e-05, + "loss": 1.4368, + "step": 3817 + }, + { + "epoch": 0.4, + "learning_rate": 1.4987315167304602e-05, + "loss": 1.4097, + "step": 3818 + }, + { + "epoch": 0.4, + "learning_rate": 1.4984142287638155e-05, + "loss": 1.4238, + "step": 3819 + }, + { + "epoch": 0.4, + "learning_rate": 1.4980968740224708e-05, + "loss": 1.497, + "step": 3820 + }, + { + "epoch": 0.4, + "learning_rate": 1.4977794525489433e-05, + "loss": 1.3989, + "step": 3821 + }, + { + "epoch": 0.4, + "learning_rate": 1.4974619643857588e-05, + "loss": 1.4415, + "step": 3822 + }, + { + "epoch": 0.4, + "learning_rate": 1.4971444095754533e-05, + "loss": 1.3931, + "step": 3823 + }, + { + "epoch": 0.4, + "learning_rate": 1.4968267881605705e-05, + "loss": 1.3426, + "step": 3824 + }, + { + "epoch": 0.4, + "learning_rate": 1.4965091001836636e-05, + "loss": 1.644, + "step": 3825 + }, + { + "epoch": 0.4, + "learning_rate": 1.4961913456872945e-05, + "loss": 1.3903, + "step": 3826 + }, + { + "epoch": 0.4, + "learning_rate": 1.4958735247140345e-05, + "loss": 1.3764, + "step": 3827 + }, + { + "epoch": 0.4, + "learning_rate": 1.4955556373064632e-05, + "loss": 1.5484, + "step": 3828 + }, + { + "epoch": 0.4, + "learning_rate": 1.4952376835071696e-05, + "loss": 1.5696, + "step": 3829 + }, + { + "epoch": 0.4, + "learning_rate": 1.4949196633587509e-05, + "loss": 1.3844, + "step": 3830 + }, + { + "epoch": 0.4, + "learning_rate": 1.494601576903814e-05, + "loss": 1.3868, + "step": 3831 + }, + { + "epoch": 0.4, + "learning_rate": 1.4942834241849741e-05, + "loss": 1.4229, + "step": 3832 + }, + { + "epoch": 0.4, + "learning_rate": 1.4939652052448557e-05, + "loss": 1.4062, + "step": 3833 + }, + { + "epoch": 0.4, + "learning_rate": 1.4936469201260915e-05, + "loss": 1.3955, + "step": 3834 + }, + { + "epoch": 0.4, + "learning_rate": 1.4933285688713239e-05, + "loss": 1.3959, + "step": 3835 + }, + { + "epoch": 0.4, + "learning_rate": 1.4930101515232038e-05, + "loss": 1.4652, + "step": 3836 + }, + { + "epoch": 0.4, + "learning_rate": 1.4926916681243913e-05, + "loss": 1.5253, + "step": 3837 + }, + { + "epoch": 0.4, + "learning_rate": 1.4923731187175539e-05, + "loss": 1.4694, + "step": 3838 + }, + { + "epoch": 0.4, + "learning_rate": 1.4920545033453702e-05, + "loss": 1.3859, + "step": 3839 + }, + { + "epoch": 0.4, + "learning_rate": 1.4917358220505259e-05, + "loss": 1.4157, + "step": 3840 + }, + { + "epoch": 0.4, + "learning_rate": 1.4914170748757159e-05, + "loss": 1.4491, + "step": 3841 + }, + { + "epoch": 0.4, + "learning_rate": 1.4910982618636445e-05, + "loss": 1.4464, + "step": 3842 + }, + { + "epoch": 0.4, + "learning_rate": 1.4907793830570246e-05, + "loss": 1.3771, + "step": 3843 + }, + { + "epoch": 0.4, + "learning_rate": 1.4904604384985775e-05, + "loss": 1.3673, + "step": 3844 + }, + { + "epoch": 0.4, + "learning_rate": 1.4901414282310334e-05, + "loss": 1.4429, + "step": 3845 + }, + { + "epoch": 0.4, + "learning_rate": 1.4898223522971318e-05, + "loss": 1.4905, + "step": 3846 + }, + { + "epoch": 0.4, + "learning_rate": 1.4895032107396205e-05, + "loss": 1.4039, + "step": 3847 + }, + { + "epoch": 0.4, + "learning_rate": 1.4891840036012566e-05, + "loss": 1.4082, + "step": 3848 + }, + { + "epoch": 0.4, + "learning_rate": 1.4888647309248052e-05, + "loss": 1.3643, + "step": 3849 + }, + { + "epoch": 0.4, + "learning_rate": 1.4885453927530408e-05, + "loss": 1.3116, + "step": 3850 + }, + { + "epoch": 0.4, + "learning_rate": 1.4882259891287467e-05, + "loss": 1.4278, + "step": 3851 + }, + { + "epoch": 0.4, + "learning_rate": 1.4879065200947148e-05, + "loss": 1.3712, + "step": 3852 + }, + { + "epoch": 0.4, + "learning_rate": 1.4875869856937449e-05, + "loss": 1.387, + "step": 3853 + }, + { + "epoch": 0.4, + "learning_rate": 1.4872673859686475e-05, + "loss": 1.5053, + "step": 3854 + }, + { + "epoch": 0.4, + "learning_rate": 1.4869477209622404e-05, + "loss": 1.4427, + "step": 3855 + }, + { + "epoch": 0.4, + "learning_rate": 1.4866279907173502e-05, + "loss": 1.3404, + "step": 3856 + }, + { + "epoch": 0.4, + "learning_rate": 1.4863081952768126e-05, + "loss": 1.3126, + "step": 3857 + }, + { + "epoch": 0.4, + "learning_rate": 1.4859883346834725e-05, + "loss": 1.4588, + "step": 3858 + }, + { + "epoch": 0.4, + "learning_rate": 1.4856684089801822e-05, + "loss": 1.408, + "step": 3859 + }, + { + "epoch": 0.4, + "learning_rate": 1.4853484182098044e-05, + "loss": 1.4356, + "step": 3860 + }, + { + "epoch": 0.4, + "learning_rate": 1.4850283624152088e-05, + "loss": 1.3768, + "step": 3861 + }, + { + "epoch": 0.4, + "learning_rate": 1.4847082416392753e-05, + "loss": 1.4563, + "step": 3862 + }, + { + "epoch": 0.41, + "learning_rate": 1.4843880559248915e-05, + "loss": 1.3648, + "step": 3863 + }, + { + "epoch": 0.41, + "learning_rate": 1.4840678053149542e-05, + "loss": 1.4146, + "step": 3864 + }, + { + "epoch": 0.41, + "learning_rate": 1.4837474898523686e-05, + "loss": 1.4423, + "step": 3865 + }, + { + "epoch": 0.41, + "learning_rate": 1.4834271095800487e-05, + "loss": 1.3351, + "step": 3866 + }, + { + "epoch": 0.41, + "learning_rate": 1.4831066645409178e-05, + "loss": 1.4534, + "step": 3867 + }, + { + "epoch": 0.41, + "learning_rate": 1.4827861547779066e-05, + "loss": 1.4763, + "step": 3868 + }, + { + "epoch": 0.41, + "learning_rate": 1.4824655803339553e-05, + "loss": 1.4019, + "step": 3869 + }, + { + "epoch": 0.41, + "learning_rate": 1.4821449412520132e-05, + "loss": 1.4223, + "step": 3870 + }, + { + "epoch": 0.41, + "learning_rate": 1.4818242375750371e-05, + "loss": 1.4065, + "step": 3871 + }, + { + "epoch": 0.41, + "learning_rate": 1.481503469345993e-05, + "loss": 1.587, + "step": 3872 + }, + { + "epoch": 0.41, + "learning_rate": 1.4811826366078562e-05, + "loss": 1.3746, + "step": 3873 + }, + { + "epoch": 0.41, + "learning_rate": 1.4808617394036096e-05, + "loss": 1.3425, + "step": 3874 + }, + { + "epoch": 0.41, + "learning_rate": 1.480540777776245e-05, + "loss": 0.6637, + "step": 3875 + }, + { + "epoch": 0.41, + "learning_rate": 1.4802197517687634e-05, + "loss": 1.3366, + "step": 3876 + }, + { + "epoch": 0.41, + "learning_rate": 1.479898661424174e-05, + "loss": 1.4033, + "step": 3877 + }, + { + "epoch": 0.41, + "learning_rate": 1.4795775067854947e-05, + "loss": 1.4005, + "step": 3878 + }, + { + "epoch": 0.41, + "learning_rate": 1.4792562878957516e-05, + "loss": 1.3651, + "step": 3879 + }, + { + "epoch": 0.41, + "learning_rate": 1.47893500479798e-05, + "loss": 1.4185, + "step": 3880 + }, + { + "epoch": 0.41, + "learning_rate": 1.4786136575352236e-05, + "loss": 1.4394, + "step": 3881 + }, + { + "epoch": 0.41, + "learning_rate": 1.478292246150535e-05, + "loss": 1.7243, + "step": 3882 + }, + { + "epoch": 0.41, + "learning_rate": 1.4779707706869744e-05, + "loss": 1.3574, + "step": 3883 + }, + { + "epoch": 0.41, + "learning_rate": 1.4776492311876116e-05, + "loss": 1.4031, + "step": 3884 + }, + { + "epoch": 0.41, + "learning_rate": 1.4773276276955248e-05, + "loss": 1.4351, + "step": 3885 + }, + { + "epoch": 0.41, + "learning_rate": 1.4770059602538002e-05, + "loss": 1.3922, + "step": 3886 + }, + { + "epoch": 0.41, + "learning_rate": 1.4766842289055333e-05, + "loss": 1.3374, + "step": 3887 + }, + { + "epoch": 0.41, + "learning_rate": 1.4763624336938278e-05, + "loss": 1.428, + "step": 3888 + }, + { + "epoch": 0.41, + "learning_rate": 1.476040574661796e-05, + "loss": 1.6087, + "step": 3889 + }, + { + "epoch": 0.41, + "learning_rate": 1.4757186518525586e-05, + "loss": 1.4054, + "step": 3890 + }, + { + "epoch": 0.41, + "learning_rate": 1.4753966653092447e-05, + "loss": 1.2595, + "step": 3891 + }, + { + "epoch": 0.41, + "learning_rate": 1.475074615074993e-05, + "loss": 1.4052, + "step": 3892 + }, + { + "epoch": 0.41, + "learning_rate": 1.4747525011929492e-05, + "loss": 1.4296, + "step": 3893 + }, + { + "epoch": 0.41, + "learning_rate": 1.4744303237062689e-05, + "loss": 1.3718, + "step": 3894 + }, + { + "epoch": 0.41, + "learning_rate": 1.4741080826581151e-05, + "loss": 1.4498, + "step": 3895 + }, + { + "epoch": 0.41, + "learning_rate": 1.4737857780916602e-05, + "loss": 1.4029, + "step": 3896 + }, + { + "epoch": 0.41, + "learning_rate": 1.4734634100500846e-05, + "loss": 1.4136, + "step": 3897 + }, + { + "epoch": 0.41, + "learning_rate": 1.4731409785765774e-05, + "loss": 1.348, + "step": 3898 + }, + { + "epoch": 0.41, + "learning_rate": 1.4728184837143355e-05, + "loss": 1.3407, + "step": 3899 + }, + { + "epoch": 0.41, + "learning_rate": 1.472495925506566e-05, + "loss": 1.3737, + "step": 3900 + }, + { + "epoch": 0.41, + "learning_rate": 1.4721733039964826e-05, + "loss": 2.2305, + "step": 3901 + }, + { + "epoch": 0.41, + "learning_rate": 1.4718506192273087e-05, + "loss": 1.4506, + "step": 3902 + }, + { + "epoch": 0.41, + "learning_rate": 1.4715278712422754e-05, + "loss": 1.3657, + "step": 3903 + }, + { + "epoch": 0.41, + "learning_rate": 1.471205060084623e-05, + "loss": 1.4644, + "step": 3904 + }, + { + "epoch": 0.41, + "learning_rate": 1.4708821857976001e-05, + "loss": 1.4823, + "step": 3905 + }, + { + "epoch": 0.41, + "learning_rate": 1.4705592484244628e-05, + "loss": 1.3392, + "step": 3906 + }, + { + "epoch": 0.41, + "learning_rate": 1.4702362480084769e-05, + "loss": 1.3302, + "step": 3907 + }, + { + "epoch": 0.41, + "learning_rate": 1.4699131845929163e-05, + "loss": 1.8952, + "step": 3908 + }, + { + "epoch": 0.41, + "learning_rate": 1.469590058221063e-05, + "loss": 1.4982, + "step": 3909 + }, + { + "epoch": 0.41, + "learning_rate": 1.4692668689362074e-05, + "loss": 1.407, + "step": 3910 + }, + { + "epoch": 0.41, + "learning_rate": 1.4689436167816489e-05, + "loss": 1.3911, + "step": 3911 + }, + { + "epoch": 0.41, + "learning_rate": 1.4686203018006948e-05, + "loss": 1.3421, + "step": 3912 + }, + { + "epoch": 0.41, + "learning_rate": 1.4682969240366612e-05, + "loss": 1.4627, + "step": 3913 + }, + { + "epoch": 0.41, + "learning_rate": 1.4679734835328718e-05, + "loss": 1.394, + "step": 3914 + }, + { + "epoch": 0.41, + "learning_rate": 1.4676499803326603e-05, + "loss": 1.4484, + "step": 3915 + }, + { + "epoch": 0.41, + "learning_rate": 1.4673264144793673e-05, + "loss": 1.4665, + "step": 3916 + }, + { + "epoch": 0.41, + "learning_rate": 1.4670027860163422e-05, + "loss": 1.3191, + "step": 3917 + }, + { + "epoch": 0.41, + "learning_rate": 1.466679094986943e-05, + "loss": 1.4748, + "step": 3918 + }, + { + "epoch": 0.41, + "learning_rate": 1.4663553414345361e-05, + "loss": 1.2467, + "step": 3919 + }, + { + "epoch": 0.41, + "learning_rate": 1.466031525402496e-05, + "loss": 1.4279, + "step": 3920 + }, + { + "epoch": 0.41, + "learning_rate": 1.4657076469342059e-05, + "loss": 1.3822, + "step": 3921 + }, + { + "epoch": 0.41, + "learning_rate": 1.4653837060730566e-05, + "loss": 1.3659, + "step": 3922 + }, + { + "epoch": 0.41, + "learning_rate": 1.465059702862449e-05, + "loss": 1.3663, + "step": 3923 + }, + { + "epoch": 0.41, + "learning_rate": 1.4647356373457902e-05, + "loss": 1.4371, + "step": 3924 + }, + { + "epoch": 0.41, + "learning_rate": 1.4644115095664972e-05, + "loss": 1.3473, + "step": 3925 + }, + { + "epoch": 0.41, + "learning_rate": 1.4640873195679944e-05, + "loss": 1.4797, + "step": 3926 + }, + { + "epoch": 0.41, + "learning_rate": 1.463763067393715e-05, + "loss": 1.3973, + "step": 3927 + }, + { + "epoch": 0.41, + "learning_rate": 1.4634387530871008e-05, + "loss": 1.3899, + "step": 3928 + }, + { + "epoch": 0.41, + "learning_rate": 1.4631143766916015e-05, + "loss": 1.3828, + "step": 3929 + }, + { + "epoch": 0.41, + "learning_rate": 1.4627899382506745e-05, + "loss": 1.4569, + "step": 3930 + }, + { + "epoch": 0.41, + "learning_rate": 1.4624654378077872e-05, + "loss": 1.4011, + "step": 3931 + }, + { + "epoch": 0.41, + "learning_rate": 1.462140875406414e-05, + "loss": 1.3859, + "step": 3932 + }, + { + "epoch": 0.41, + "learning_rate": 1.4618162510900376e-05, + "loss": 1.4518, + "step": 3933 + }, + { + "epoch": 0.41, + "learning_rate": 1.4614915649021493e-05, + "loss": 1.4399, + "step": 3934 + }, + { + "epoch": 0.41, + "learning_rate": 1.4611668168862495e-05, + "loss": 1.4034, + "step": 3935 + }, + { + "epoch": 0.41, + "learning_rate": 1.4608420070858452e-05, + "loss": 1.3919, + "step": 3936 + }, + { + "epoch": 0.41, + "learning_rate": 1.4605171355444528e-05, + "loss": 1.391, + "step": 3937 + }, + { + "epoch": 0.41, + "learning_rate": 1.460192202305597e-05, + "loss": 1.3717, + "step": 3938 + }, + { + "epoch": 0.41, + "learning_rate": 1.4598672074128103e-05, + "loss": 1.4351, + "step": 3939 + }, + { + "epoch": 0.41, + "learning_rate": 1.4595421509096339e-05, + "loss": 1.4202, + "step": 3940 + }, + { + "epoch": 0.41, + "learning_rate": 1.4592170328396165e-05, + "loss": 1.3559, + "step": 3941 + }, + { + "epoch": 0.41, + "learning_rate": 1.458891853246316e-05, + "loss": 1.5878, + "step": 3942 + }, + { + "epoch": 0.41, + "learning_rate": 1.4585666121732982e-05, + "loss": 1.3818, + "step": 3943 + }, + { + "epoch": 0.41, + "learning_rate": 1.4582413096641369e-05, + "loss": 1.4009, + "step": 3944 + }, + { + "epoch": 0.41, + "learning_rate": 1.457915945762414e-05, + "loss": 1.3937, + "step": 3945 + }, + { + "epoch": 0.41, + "learning_rate": 1.4575905205117203e-05, + "loss": 1.381, + "step": 3946 + }, + { + "epoch": 0.41, + "learning_rate": 1.457265033955654e-05, + "loss": 1.3844, + "step": 3947 + }, + { + "epoch": 0.41, + "learning_rate": 1.4569394861378226e-05, + "loss": 1.4059, + "step": 3948 + }, + { + "epoch": 0.41, + "learning_rate": 1.4566138771018403e-05, + "loss": 1.3698, + "step": 3949 + }, + { + "epoch": 0.41, + "learning_rate": 1.4562882068913311e-05, + "loss": 1.4253, + "step": 3950 + }, + { + "epoch": 0.41, + "learning_rate": 1.455962475549926e-05, + "loss": 1.4284, + "step": 3951 + }, + { + "epoch": 0.41, + "learning_rate": 1.4556366831212647e-05, + "loss": 1.4279, + "step": 3952 + }, + { + "epoch": 0.41, + "learning_rate": 1.4553108296489951e-05, + "loss": 1.3072, + "step": 3953 + }, + { + "epoch": 0.41, + "learning_rate": 1.4549849151767731e-05, + "loss": 1.4175, + "step": 3954 + }, + { + "epoch": 0.41, + "learning_rate": 1.4546589397482632e-05, + "loss": 1.5042, + "step": 3955 + }, + { + "epoch": 0.41, + "learning_rate": 1.4543329034071371e-05, + "loss": 1.4363, + "step": 3956 + }, + { + "epoch": 0.41, + "learning_rate": 1.454006806197076e-05, + "loss": 1.4111, + "step": 3957 + }, + { + "epoch": 0.42, + "learning_rate": 1.453680648161768e-05, + "loss": 1.3817, + "step": 3958 + }, + { + "epoch": 0.42, + "learning_rate": 1.45335442934491e-05, + "loss": 1.4689, + "step": 3959 + }, + { + "epoch": 0.42, + "learning_rate": 1.4530281497902072e-05, + "loss": 1.4164, + "step": 3960 + }, + { + "epoch": 0.42, + "learning_rate": 1.4527018095413726e-05, + "loss": 1.3943, + "step": 3961 + }, + { + "epoch": 0.42, + "learning_rate": 1.4523754086421271e-05, + "loss": 1.3851, + "step": 3962 + }, + { + "epoch": 0.42, + "learning_rate": 1.4520489471362003e-05, + "loss": 1.3907, + "step": 3963 + }, + { + "epoch": 0.42, + "learning_rate": 1.4517224250673297e-05, + "loss": 1.2877, + "step": 3964 + }, + { + "epoch": 0.42, + "learning_rate": 1.4513958424792605e-05, + "loss": 1.4696, + "step": 3965 + }, + { + "epoch": 0.42, + "learning_rate": 1.4510691994157471e-05, + "loss": 1.3785, + "step": 3966 + }, + { + "epoch": 0.42, + "learning_rate": 1.4507424959205505e-05, + "loss": 1.3652, + "step": 3967 + }, + { + "epoch": 0.42, + "learning_rate": 1.4504157320374408e-05, + "loss": 1.4198, + "step": 3968 + }, + { + "epoch": 0.42, + "learning_rate": 1.4500889078101962e-05, + "loss": 1.3476, + "step": 3969 + }, + { + "epoch": 0.42, + "learning_rate": 1.4497620232826028e-05, + "loss": 1.4356, + "step": 3970 + }, + { + "epoch": 0.42, + "learning_rate": 1.4494350784984543e-05, + "loss": 1.4993, + "step": 3971 + }, + { + "epoch": 0.42, + "learning_rate": 1.4491080735015533e-05, + "loss": 1.4022, + "step": 3972 + }, + { + "epoch": 0.42, + "learning_rate": 1.44878100833571e-05, + "loss": 1.4074, + "step": 3973 + }, + { + "epoch": 0.42, + "learning_rate": 1.4484538830447423e-05, + "loss": 1.412, + "step": 3974 + }, + { + "epoch": 0.42, + "learning_rate": 1.4481266976724772e-05, + "loss": 1.3872, + "step": 3975 + }, + { + "epoch": 0.42, + "learning_rate": 1.4477994522627485e-05, + "loss": 1.4575, + "step": 3976 + }, + { + "epoch": 0.42, + "learning_rate": 1.4474721468593995e-05, + "loss": 1.3768, + "step": 3977 + }, + { + "epoch": 0.42, + "learning_rate": 1.44714478150628e-05, + "loss": 1.4173, + "step": 3978 + }, + { + "epoch": 0.42, + "learning_rate": 1.4468173562472489e-05, + "loss": 1.3896, + "step": 3979 + }, + { + "epoch": 0.42, + "learning_rate": 1.4464898711261725e-05, + "loss": 1.4535, + "step": 3980 + }, + { + "epoch": 0.42, + "eval_loss": 1.4580057859420776, + "eval_runtime": 77.4537, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 3980 + }, + { + "epoch": 0.42, + "learning_rate": 1.4461623261869258e-05, + "loss": 1.4046, + "step": 3981 + }, + { + "epoch": 0.42, + "learning_rate": 1.445834721473391e-05, + "loss": 1.37, + "step": 3982 + }, + { + "epoch": 0.42, + "learning_rate": 1.4455070570294588e-05, + "loss": 1.4566, + "step": 3983 + }, + { + "epoch": 0.42, + "learning_rate": 1.445179332899028e-05, + "loss": 1.4513, + "step": 3984 + }, + { + "epoch": 0.42, + "learning_rate": 1.4448515491260051e-05, + "loss": 1.3893, + "step": 3985 + }, + { + "epoch": 0.42, + "learning_rate": 1.4445237057543047e-05, + "loss": 1.3955, + "step": 3986 + }, + { + "epoch": 0.42, + "learning_rate": 1.4441958028278493e-05, + "loss": 1.4861, + "step": 3987 + }, + { + "epoch": 0.42, + "learning_rate": 1.4438678403905697e-05, + "loss": 1.4601, + "step": 3988 + }, + { + "epoch": 0.42, + "learning_rate": 1.4435398184864043e-05, + "loss": 1.398, + "step": 3989 + }, + { + "epoch": 0.42, + "learning_rate": 1.4432117371592995e-05, + "loss": 1.4392, + "step": 3990 + }, + { + "epoch": 0.42, + "learning_rate": 1.4428835964532098e-05, + "loss": 1.3772, + "step": 3991 + }, + { + "epoch": 0.42, + "learning_rate": 1.4425553964120979e-05, + "loss": 1.4241, + "step": 3992 + }, + { + "epoch": 0.42, + "learning_rate": 1.4422271370799338e-05, + "loss": 1.3237, + "step": 3993 + }, + { + "epoch": 0.42, + "learning_rate": 1.4418988185006964e-05, + "loss": 1.3813, + "step": 3994 + }, + { + "epoch": 0.42, + "learning_rate": 1.4415704407183709e-05, + "loss": 1.6139, + "step": 3995 + }, + { + "epoch": 0.42, + "learning_rate": 1.4412420037769525e-05, + "loss": 1.4431, + "step": 3996 + }, + { + "epoch": 0.42, + "learning_rate": 1.440913507720443e-05, + "loss": 1.3862, + "step": 3997 + }, + { + "epoch": 0.42, + "learning_rate": 1.4405849525928523e-05, + "loss": 1.3895, + "step": 3998 + }, + { + "epoch": 0.42, + "learning_rate": 1.4402563384381981e-05, + "loss": 1.4068, + "step": 3999 + }, + { + "epoch": 0.42, + "learning_rate": 1.4399276653005072e-05, + "loss": 1.4501, + "step": 4000 + }, + { + "epoch": 0.42, + "learning_rate": 1.4395989332238124e-05, + "loss": 1.3165, + "step": 4001 + }, + { + "epoch": 0.42, + "learning_rate": 1.4392701422521555e-05, + "loss": 1.3783, + "step": 4002 + }, + { + "epoch": 0.42, + "learning_rate": 1.4389412924295865e-05, + "loss": 1.343, + "step": 4003 + }, + { + "epoch": 0.42, + "learning_rate": 1.4386123838001625e-05, + "loss": 1.3456, + "step": 4004 + }, + { + "epoch": 0.42, + "learning_rate": 1.4382834164079486e-05, + "loss": 1.3689, + "step": 4005 + }, + { + "epoch": 0.42, + "learning_rate": 1.4379543902970183e-05, + "loss": 1.3789, + "step": 4006 + }, + { + "epoch": 0.42, + "learning_rate": 1.4376253055114528e-05, + "loss": 1.4912, + "step": 4007 + }, + { + "epoch": 0.42, + "learning_rate": 1.4372961620953407e-05, + "loss": 1.3692, + "step": 4008 + }, + { + "epoch": 0.42, + "learning_rate": 1.436966960092779e-05, + "loss": 1.4901, + "step": 4009 + }, + { + "epoch": 0.42, + "learning_rate": 1.4366376995478717e-05, + "loss": 1.4431, + "step": 4010 + }, + { + "epoch": 0.42, + "learning_rate": 1.436308380504732e-05, + "loss": 1.4626, + "step": 4011 + }, + { + "epoch": 0.42, + "learning_rate": 1.4359790030074798e-05, + "loss": 1.4241, + "step": 4012 + }, + { + "epoch": 0.42, + "learning_rate": 1.4356495671002435e-05, + "loss": 1.3834, + "step": 4013 + }, + { + "epoch": 0.42, + "learning_rate": 1.4353200728271586e-05, + "loss": 1.3626, + "step": 4014 + }, + { + "epoch": 0.42, + "learning_rate": 1.4349905202323692e-05, + "loss": 1.3557, + "step": 4015 + }, + { + "epoch": 0.42, + "learning_rate": 1.434660909360027e-05, + "loss": 1.4077, + "step": 4016 + }, + { + "epoch": 0.42, + "learning_rate": 1.4343312402542911e-05, + "loss": 1.4337, + "step": 4017 + }, + { + "epoch": 0.42, + "learning_rate": 1.4340015129593286e-05, + "loss": 1.419, + "step": 4018 + }, + { + "epoch": 0.42, + "learning_rate": 1.4336717275193148e-05, + "loss": 1.3768, + "step": 4019 + }, + { + "epoch": 0.42, + "learning_rate": 1.4333418839784326e-05, + "loss": 1.383, + "step": 4020 + }, + { + "epoch": 0.42, + "learning_rate": 1.4330119823808719e-05, + "loss": 1.3951, + "step": 4021 + }, + { + "epoch": 0.42, + "learning_rate": 1.4326820227708316e-05, + "loss": 1.3985, + "step": 4022 + }, + { + "epoch": 0.42, + "learning_rate": 1.4323520051925177e-05, + "loss": 1.356, + "step": 4023 + }, + { + "epoch": 0.42, + "learning_rate": 1.4320219296901439e-05, + "loss": 1.5017, + "step": 4024 + }, + { + "epoch": 0.42, + "learning_rate": 1.4316917963079322e-05, + "loss": 1.3594, + "step": 4025 + }, + { + "epoch": 0.42, + "learning_rate": 1.4313616050901114e-05, + "loss": 1.6028, + "step": 4026 + }, + { + "epoch": 0.42, + "learning_rate": 1.4310313560809193e-05, + "loss": 1.4132, + "step": 4027 + }, + { + "epoch": 0.42, + "learning_rate": 1.4307010493246006e-05, + "loss": 1.2969, + "step": 4028 + }, + { + "epoch": 0.42, + "learning_rate": 1.4303706848654073e-05, + "loss": 1.5224, + "step": 4029 + }, + { + "epoch": 0.42, + "learning_rate": 1.4300402627476007e-05, + "loss": 1.3386, + "step": 4030 + }, + { + "epoch": 0.42, + "learning_rate": 1.429709783015448e-05, + "loss": 1.3554, + "step": 4031 + }, + { + "epoch": 0.42, + "learning_rate": 1.4293792457132259e-05, + "loss": 1.3386, + "step": 4032 + }, + { + "epoch": 0.42, + "learning_rate": 1.429048650885217e-05, + "loss": 1.4613, + "step": 4033 + }, + { + "epoch": 0.42, + "learning_rate": 1.4287179985757132e-05, + "loss": 1.3632, + "step": 4034 + }, + { + "epoch": 0.42, + "learning_rate": 1.428387288829013e-05, + "loss": 1.3835, + "step": 4035 + }, + { + "epoch": 0.42, + "learning_rate": 1.4280565216894234e-05, + "loss": 1.3711, + "step": 4036 + }, + { + "epoch": 0.42, + "learning_rate": 1.4277256972012582e-05, + "loss": 1.3385, + "step": 4037 + }, + { + "epoch": 0.42, + "learning_rate": 1.4273948154088395e-05, + "loss": 1.4607, + "step": 4038 + }, + { + "epoch": 0.42, + "learning_rate": 1.4270638763564973e-05, + "loss": 1.4042, + "step": 4039 + }, + { + "epoch": 0.42, + "learning_rate": 1.4267328800885687e-05, + "loss": 1.4006, + "step": 4040 + }, + { + "epoch": 0.42, + "learning_rate": 1.4264018266493987e-05, + "loss": 1.386, + "step": 4041 + }, + { + "epoch": 0.42, + "learning_rate": 1.4260707160833401e-05, + "loss": 1.3487, + "step": 4042 + }, + { + "epoch": 0.42, + "learning_rate": 1.4257395484347529e-05, + "loss": 1.4199, + "step": 4043 + }, + { + "epoch": 0.42, + "learning_rate": 1.4254083237480054e-05, + "loss": 1.3236, + "step": 4044 + }, + { + "epoch": 0.42, + "learning_rate": 1.4250770420674726e-05, + "loss": 1.4056, + "step": 4045 + }, + { + "epoch": 0.42, + "learning_rate": 1.4247457034375387e-05, + "loss": 1.4391, + "step": 4046 + }, + { + "epoch": 0.42, + "learning_rate": 1.4244143079025938e-05, + "loss": 1.3935, + "step": 4047 + }, + { + "epoch": 0.42, + "learning_rate": 1.4240828555070368e-05, + "loss": 1.3623, + "step": 4048 + }, + { + "epoch": 0.42, + "learning_rate": 1.4237513462952733e-05, + "loss": 1.3254, + "step": 4049 + }, + { + "epoch": 0.42, + "learning_rate": 1.4234197803117174e-05, + "loss": 1.4217, + "step": 4050 + }, + { + "epoch": 0.42, + "learning_rate": 1.4230881576007904e-05, + "loss": 1.435, + "step": 4051 + }, + { + "epoch": 0.42, + "learning_rate": 1.422756478206921e-05, + "loss": 1.3687, + "step": 4052 + }, + { + "epoch": 0.43, + "learning_rate": 1.4224247421745464e-05, + "loss": 1.3965, + "step": 4053 + }, + { + "epoch": 0.43, + "learning_rate": 1.4220929495481097e-05, + "loss": 1.4159, + "step": 4054 + }, + { + "epoch": 0.43, + "learning_rate": 1.4217611003720632e-05, + "loss": 1.3632, + "step": 4055 + }, + { + "epoch": 0.43, + "learning_rate": 1.4214291946908661e-05, + "loss": 1.403, + "step": 4056 + }, + { + "epoch": 0.43, + "learning_rate": 1.4210972325489854e-05, + "loss": 1.4093, + "step": 4057 + }, + { + "epoch": 0.43, + "learning_rate": 1.4207652139908952e-05, + "loss": 1.4551, + "step": 4058 + }, + { + "epoch": 0.43, + "learning_rate": 1.4204331390610775e-05, + "loss": 1.4162, + "step": 4059 + }, + { + "epoch": 0.43, + "learning_rate": 1.4201010078040216e-05, + "loss": 1.4492, + "step": 4060 + }, + { + "epoch": 0.43, + "learning_rate": 1.419768820264225e-05, + "loss": 1.4449, + "step": 4061 + }, + { + "epoch": 0.43, + "learning_rate": 1.4194365764861922e-05, + "loss": 1.3382, + "step": 4062 + }, + { + "epoch": 0.43, + "learning_rate": 1.419104276514435e-05, + "loss": 1.3899, + "step": 4063 + }, + { + "epoch": 0.43, + "learning_rate": 1.4187719203934734e-05, + "loss": 1.3513, + "step": 4064 + }, + { + "epoch": 0.43, + "learning_rate": 1.4184395081678344e-05, + "loss": 1.3954, + "step": 4065 + }, + { + "epoch": 0.43, + "learning_rate": 1.4181070398820528e-05, + "loss": 1.442, + "step": 4066 + }, + { + "epoch": 0.43, + "learning_rate": 1.4177745155806708e-05, + "loss": 1.3907, + "step": 4067 + }, + { + "epoch": 0.43, + "learning_rate": 1.417441935308238e-05, + "loss": 1.3757, + "step": 4068 + }, + { + "epoch": 0.43, + "learning_rate": 1.4171092991093118e-05, + "loss": 1.3507, + "step": 4069 + }, + { + "epoch": 0.43, + "learning_rate": 1.4167766070284568e-05, + "loss": 1.4136, + "step": 4070 + }, + { + "epoch": 0.43, + "learning_rate": 1.4164438591102452e-05, + "loss": 1.3835, + "step": 4071 + }, + { + "epoch": 0.43, + "learning_rate": 1.4161110553992565e-05, + "loss": 1.4981, + "step": 4072 + }, + { + "epoch": 0.43, + "learning_rate": 1.415778195940078e-05, + "loss": 1.4387, + "step": 4073 + }, + { + "epoch": 0.43, + "learning_rate": 1.4154452807773047e-05, + "loss": 1.333, + "step": 4074 + }, + { + "epoch": 0.43, + "learning_rate": 1.4151123099555377e-05, + "loss": 1.3558, + "step": 4075 + }, + { + "epoch": 0.43, + "learning_rate": 1.4147792835193875e-05, + "loss": 1.4655, + "step": 4076 + }, + { + "epoch": 0.43, + "learning_rate": 1.4144462015134708e-05, + "loss": 1.4402, + "step": 4077 + }, + { + "epoch": 0.43, + "learning_rate": 1.4141130639824119e-05, + "loss": 1.4227, + "step": 4078 + }, + { + "epoch": 0.43, + "learning_rate": 1.4137798709708423e-05, + "loss": 1.4039, + "step": 4079 + }, + { + "epoch": 0.43, + "learning_rate": 1.4134466225234023e-05, + "loss": 1.3593, + "step": 4080 + }, + { + "epoch": 0.43, + "learning_rate": 1.4131133186847377e-05, + "loss": 1.372, + "step": 4081 + }, + { + "epoch": 0.43, + "learning_rate": 1.412779959499503e-05, + "loss": 1.4487, + "step": 4082 + }, + { + "epoch": 0.43, + "learning_rate": 1.4124465450123599e-05, + "loss": 1.3972, + "step": 4083 + }, + { + "epoch": 0.43, + "learning_rate": 1.4121130752679772e-05, + "loss": 1.3768, + "step": 4084 + }, + { + "epoch": 0.43, + "learning_rate": 1.4117795503110313e-05, + "loss": 1.3827, + "step": 4085 + }, + { + "epoch": 0.43, + "learning_rate": 1.4114459701862062e-05, + "loss": 1.3922, + "step": 4086 + }, + { + "epoch": 0.43, + "learning_rate": 1.4111123349381925e-05, + "loss": 1.3736, + "step": 4087 + }, + { + "epoch": 0.43, + "learning_rate": 1.4107786446116894e-05, + "loss": 1.4338, + "step": 4088 + }, + { + "epoch": 0.43, + "learning_rate": 1.4104448992514023e-05, + "loss": 1.347, + "step": 4089 + }, + { + "epoch": 0.43, + "learning_rate": 1.410111098902045e-05, + "loss": 1.3915, + "step": 4090 + }, + { + "epoch": 0.43, + "learning_rate": 1.4097772436083377e-05, + "loss": 1.3656, + "step": 4091 + }, + { + "epoch": 0.43, + "learning_rate": 1.4094433334150087e-05, + "loss": 1.3461, + "step": 4092 + }, + { + "epoch": 0.43, + "learning_rate": 1.4091093683667934e-05, + "loss": 1.7345, + "step": 4093 + }, + { + "epoch": 0.43, + "learning_rate": 1.4087753485084343e-05, + "loss": 1.6204, + "step": 4094 + }, + { + "epoch": 0.43, + "learning_rate": 1.4084412738846816e-05, + "loss": 1.4074, + "step": 4095 + }, + { + "epoch": 0.43, + "learning_rate": 1.408107144540293e-05, + "loss": 1.3776, + "step": 4096 + }, + { + "epoch": 0.43, + "learning_rate": 1.407772960520033e-05, + "loss": 1.4079, + "step": 4097 + }, + { + "epoch": 0.43, + "learning_rate": 1.4074387218686734e-05, + "loss": 1.4254, + "step": 4098 + }, + { + "epoch": 0.43, + "learning_rate": 1.407104428630994e-05, + "loss": 1.38, + "step": 4099 + }, + { + "epoch": 0.43, + "learning_rate": 1.4067700808517815e-05, + "loss": 1.4175, + "step": 4100 + }, + { + "epoch": 0.43, + "learning_rate": 1.4064356785758298e-05, + "loss": 1.4085, + "step": 4101 + }, + { + "epoch": 0.43, + "learning_rate": 1.4061012218479397e-05, + "loss": 1.4529, + "step": 4102 + }, + { + "epoch": 0.43, + "learning_rate": 1.405766710712921e-05, + "loss": 1.4836, + "step": 4103 + }, + { + "epoch": 0.43, + "learning_rate": 1.4054321452155885e-05, + "loss": 1.3915, + "step": 4104 + }, + { + "epoch": 0.43, + "learning_rate": 1.4050975254007659e-05, + "loss": 1.3044, + "step": 4105 + }, + { + "epoch": 0.43, + "learning_rate": 1.4047628513132835e-05, + "loss": 1.373, + "step": 4106 + }, + { + "epoch": 0.43, + "learning_rate": 1.4044281229979793e-05, + "loss": 1.4266, + "step": 4107 + }, + { + "epoch": 0.43, + "learning_rate": 1.4040933404996977e-05, + "loss": 1.3898, + "step": 4108 + }, + { + "epoch": 0.43, + "learning_rate": 1.4037585038632915e-05, + "loss": 0.9326, + "step": 4109 + }, + { + "epoch": 0.43, + "learning_rate": 1.40342361313362e-05, + "loss": 1.0831, + "step": 4110 + }, + { + "epoch": 0.43, + "learning_rate": 1.40308866835555e-05, + "loss": 1.3898, + "step": 4111 + }, + { + "epoch": 0.43, + "learning_rate": 1.4027536695739554e-05, + "loss": 1.5058, + "step": 4112 + }, + { + "epoch": 0.43, + "learning_rate": 1.4024186168337175e-05, + "loss": 1.3635, + "step": 4113 + }, + { + "epoch": 0.43, + "learning_rate": 1.4020835101797248e-05, + "loss": 1.3871, + "step": 4114 + }, + { + "epoch": 0.43, + "learning_rate": 1.401748349656873e-05, + "loss": 1.3478, + "step": 4115 + }, + { + "epoch": 0.43, + "learning_rate": 1.4014131353100648e-05, + "loss": 1.3356, + "step": 4116 + }, + { + "epoch": 0.43, + "learning_rate": 1.4010778671842107e-05, + "loss": 1.3954, + "step": 4117 + }, + { + "epoch": 0.43, + "learning_rate": 1.4007425453242274e-05, + "loss": 1.3307, + "step": 4118 + }, + { + "epoch": 0.43, + "learning_rate": 1.4004071697750398e-05, + "loss": 1.4508, + "step": 4119 + }, + { + "epoch": 0.43, + "learning_rate": 1.4000717405815799e-05, + "loss": 1.3752, + "step": 4120 + }, + { + "epoch": 0.43, + "learning_rate": 1.399736257788786e-05, + "loss": 1.3654, + "step": 4121 + }, + { + "epoch": 0.43, + "learning_rate": 1.3994007214416046e-05, + "loss": 1.4505, + "step": 4122 + }, + { + "epoch": 0.43, + "learning_rate": 1.3990651315849886e-05, + "loss": 1.4307, + "step": 4123 + }, + { + "epoch": 0.43, + "learning_rate": 1.398729488263899e-05, + "loss": 1.4481, + "step": 4124 + }, + { + "epoch": 0.43, + "learning_rate": 1.3983937915233026e-05, + "loss": 1.4755, + "step": 4125 + }, + { + "epoch": 0.43, + "learning_rate": 1.3980580414081746e-05, + "loss": 1.3402, + "step": 4126 + }, + { + "epoch": 0.43, + "learning_rate": 1.3977222379634969e-05, + "loss": 1.3636, + "step": 4127 + }, + { + "epoch": 0.43, + "learning_rate": 1.3973863812342585e-05, + "loss": 1.4165, + "step": 4128 + }, + { + "epoch": 0.43, + "learning_rate": 1.3970504712654554e-05, + "loss": 1.3832, + "step": 4129 + }, + { + "epoch": 0.43, + "learning_rate": 1.3967145081020912e-05, + "loss": 1.4236, + "step": 4130 + }, + { + "epoch": 0.43, + "learning_rate": 1.396378491789176e-05, + "loss": 1.5022, + "step": 4131 + }, + { + "epoch": 0.43, + "learning_rate": 1.3960424223717276e-05, + "loss": 1.3806, + "step": 4132 + }, + { + "epoch": 0.43, + "learning_rate": 1.3957062998947707e-05, + "loss": 1.3649, + "step": 4133 + }, + { + "epoch": 0.43, + "learning_rate": 1.3953701244033368e-05, + "loss": 1.3787, + "step": 4134 + }, + { + "epoch": 0.43, + "learning_rate": 1.395033895942465e-05, + "loss": 1.3551, + "step": 4135 + }, + { + "epoch": 0.43, + "learning_rate": 1.394697614557201e-05, + "loss": 1.3881, + "step": 4136 + }, + { + "epoch": 0.43, + "learning_rate": 1.3943612802925983e-05, + "loss": 1.4848, + "step": 4137 + }, + { + "epoch": 0.43, + "learning_rate": 1.3940248931937169e-05, + "loss": 1.425, + "step": 4138 + }, + { + "epoch": 0.43, + "learning_rate": 1.3936884533056238e-05, + "loss": 1.4054, + "step": 4139 + }, + { + "epoch": 0.43, + "learning_rate": 1.3933519606733934e-05, + "loss": 1.4028, + "step": 4140 + }, + { + "epoch": 0.43, + "learning_rate": 1.3930154153421072e-05, + "loss": 1.4439, + "step": 4141 + }, + { + "epoch": 0.43, + "learning_rate": 1.3926788173568536e-05, + "loss": 1.4482, + "step": 4142 + }, + { + "epoch": 0.43, + "learning_rate": 1.392342166762728e-05, + "loss": 1.393, + "step": 4143 + }, + { + "epoch": 0.43, + "learning_rate": 1.3920054636048328e-05, + "loss": 1.4097, + "step": 4144 + }, + { + "epoch": 0.43, + "learning_rate": 1.391668707928278e-05, + "loss": 1.5142, + "step": 4145 + }, + { + "epoch": 0.43, + "learning_rate": 1.3913318997781797e-05, + "loss": 1.4118, + "step": 4146 + }, + { + "epoch": 0.43, + "learning_rate": 1.390995039199662e-05, + "loss": 1.4067, + "step": 4147 + }, + { + "epoch": 0.43, + "learning_rate": 1.3906581262378552e-05, + "loss": 1.5214, + "step": 4148 + }, + { + "epoch": 0.44, + "learning_rate": 1.3903211609378971e-05, + "loss": 1.3618, + "step": 4149 + }, + { + "epoch": 0.44, + "learning_rate": 1.3899841433449327e-05, + "loss": 1.338, + "step": 4150 + }, + { + "epoch": 0.44, + "learning_rate": 1.3896470735041132e-05, + "loss": 1.3901, + "step": 4151 + }, + { + "epoch": 0.44, + "learning_rate": 1.3893099514605971e-05, + "loss": 1.4502, + "step": 4152 + }, + { + "epoch": 0.44, + "learning_rate": 1.388972777259551e-05, + "loss": 1.4141, + "step": 4153 + }, + { + "epoch": 0.44, + "learning_rate": 1.3886355509461471e-05, + "loss": 1.3876, + "step": 4154 + }, + { + "epoch": 0.44, + "learning_rate": 1.388298272565565e-05, + "loss": 1.4275, + "step": 4155 + }, + { + "epoch": 0.44, + "learning_rate": 1.3879609421629909e-05, + "loss": 1.3559, + "step": 4156 + }, + { + "epoch": 0.44, + "learning_rate": 1.3876235597836195e-05, + "loss": 1.416, + "step": 4157 + }, + { + "epoch": 0.44, + "learning_rate": 1.3872861254726506e-05, + "loss": 1.437, + "step": 4158 + }, + { + "epoch": 0.44, + "learning_rate": 1.3869486392752918e-05, + "loss": 1.3794, + "step": 4159 + }, + { + "epoch": 0.44, + "learning_rate": 1.3866111012367577e-05, + "loss": 1.4094, + "step": 4160 + }, + { + "epoch": 0.44, + "learning_rate": 1.3862735114022694e-05, + "loss": 1.3957, + "step": 4161 + }, + { + "epoch": 0.44, + "learning_rate": 1.3859358698170559e-05, + "loss": 1.3582, + "step": 4162 + }, + { + "epoch": 0.44, + "learning_rate": 1.3855981765263523e-05, + "loss": 1.4159, + "step": 4163 + }, + { + "epoch": 0.44, + "learning_rate": 1.3852604315754e-05, + "loss": 1.3498, + "step": 4164 + }, + { + "epoch": 0.44, + "learning_rate": 1.3849226350094491e-05, + "loss": 1.3951, + "step": 4165 + }, + { + "epoch": 0.44, + "learning_rate": 1.3845847868737559e-05, + "loss": 1.4087, + "step": 4166 + }, + { + "epoch": 0.44, + "learning_rate": 1.3842468872135821e-05, + "loss": 1.4318, + "step": 4167 + }, + { + "epoch": 0.44, + "learning_rate": 1.3839089360741989e-05, + "loss": 1.4174, + "step": 4168 + }, + { + "epoch": 0.44, + "learning_rate": 1.3835709335008822e-05, + "loss": 1.4499, + "step": 4169 + }, + { + "epoch": 0.44, + "learning_rate": 1.383232879538916e-05, + "loss": 1.3554, + "step": 4170 + }, + { + "epoch": 0.44, + "learning_rate": 1.3828947742335905e-05, + "loss": 1.3873, + "step": 4171 + }, + { + "epoch": 0.44, + "learning_rate": 1.382556617630204e-05, + "loss": 1.3804, + "step": 4172 + }, + { + "epoch": 0.44, + "learning_rate": 1.3822184097740598e-05, + "loss": 1.3856, + "step": 4173 + }, + { + "epoch": 0.44, + "learning_rate": 1.3818801507104697e-05, + "loss": 1.3901, + "step": 4174 + }, + { + "epoch": 0.44, + "learning_rate": 1.381541840484751e-05, + "loss": 1.3714, + "step": 4175 + }, + { + "epoch": 0.44, + "learning_rate": 1.3812034791422297e-05, + "loss": 1.4945, + "step": 4176 + }, + { + "epoch": 0.44, + "learning_rate": 1.3808650667282368e-05, + "loss": 1.429, + "step": 4177 + }, + { + "epoch": 0.44, + "learning_rate": 1.3805266032881108e-05, + "loss": 1.3903, + "step": 4178 + }, + { + "epoch": 0.44, + "learning_rate": 1.3801880888671972e-05, + "loss": 1.4799, + "step": 4179 + }, + { + "epoch": 0.44, + "eval_loss": 1.4521424770355225, + "eval_runtime": 77.3596, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 4179 + }, + { + "epoch": 0.44, + "learning_rate": 1.3798495235108484e-05, + "loss": 1.3912, + "step": 4180 + }, + { + "epoch": 0.44, + "learning_rate": 1.3795109072644235e-05, + "loss": 1.5837, + "step": 4181 + }, + { + "epoch": 0.44, + "learning_rate": 1.379172240173288e-05, + "loss": 1.4255, + "step": 4182 + }, + { + "epoch": 0.44, + "learning_rate": 1.3788335222828148e-05, + "loss": 1.4666, + "step": 4183 + }, + { + "epoch": 0.44, + "learning_rate": 1.3784947536383837e-05, + "loss": 1.3964, + "step": 4184 + }, + { + "epoch": 0.44, + "learning_rate": 1.3781559342853807e-05, + "loss": 1.336, + "step": 4185 + }, + { + "epoch": 0.44, + "learning_rate": 1.3778170642691986e-05, + "loss": 1.4352, + "step": 4186 + }, + { + "epoch": 0.44, + "learning_rate": 1.377478143635238e-05, + "loss": 1.3262, + "step": 4187 + }, + { + "epoch": 0.44, + "learning_rate": 1.3771391724289047e-05, + "loss": 1.3969, + "step": 4188 + }, + { + "epoch": 0.44, + "learning_rate": 1.376800150695613e-05, + "loss": 1.4211, + "step": 4189 + }, + { + "epoch": 0.44, + "learning_rate": 1.3764610784807824e-05, + "loss": 1.4338, + "step": 4190 + }, + { + "epoch": 0.44, + "learning_rate": 1.3761219558298403e-05, + "loss": 1.3815, + "step": 4191 + }, + { + "epoch": 0.44, + "learning_rate": 1.3757827827882203e-05, + "loss": 1.3805, + "step": 4192 + }, + { + "epoch": 0.44, + "learning_rate": 1.3754435594013627e-05, + "loss": 1.4071, + "step": 4193 + }, + { + "epoch": 0.44, + "learning_rate": 1.3751042857147145e-05, + "loss": 1.343, + "step": 4194 + }, + { + "epoch": 0.44, + "learning_rate": 1.3747649617737304e-05, + "loss": 1.4129, + "step": 4195 + }, + { + "epoch": 0.44, + "learning_rate": 1.3744255876238708e-05, + "loss": 1.3939, + "step": 4196 + }, + { + "epoch": 0.44, + "learning_rate": 1.3740861633106029e-05, + "loss": 1.3963, + "step": 4197 + }, + { + "epoch": 0.44, + "learning_rate": 1.3737466888794008e-05, + "loss": 1.5181, + "step": 4198 + }, + { + "epoch": 0.44, + "learning_rate": 1.3734071643757456e-05, + "loss": 1.4397, + "step": 4199 + }, + { + "epoch": 0.44, + "learning_rate": 1.373067589845125e-05, + "loss": 1.6293, + "step": 4200 + }, + { + "epoch": 0.44, + "learning_rate": 1.3727279653330328e-05, + "loss": 1.3498, + "step": 4201 + }, + { + "epoch": 0.44, + "learning_rate": 1.37238829088497e-05, + "loss": 1.4509, + "step": 4202 + }, + { + "epoch": 0.44, + "learning_rate": 1.3720485665464446e-05, + "loss": 1.4477, + "step": 4203 + }, + { + "epoch": 0.44, + "learning_rate": 1.3717087923629709e-05, + "loss": 1.4399, + "step": 4204 + }, + { + "epoch": 0.44, + "learning_rate": 1.3713689683800695e-05, + "loss": 1.4417, + "step": 4205 + }, + { + "epoch": 0.44, + "learning_rate": 1.3710290946432685e-05, + "loss": 1.3957, + "step": 4206 + }, + { + "epoch": 0.44, + "learning_rate": 1.3706891711981021e-05, + "loss": 1.4476, + "step": 4207 + }, + { + "epoch": 0.44, + "learning_rate": 1.3703491980901113e-05, + "loss": 1.3894, + "step": 4208 + }, + { + "epoch": 0.44, + "learning_rate": 1.3700091753648437e-05, + "loss": 1.4745, + "step": 4209 + }, + { + "epoch": 0.44, + "learning_rate": 1.369669103067854e-05, + "loss": 1.4038, + "step": 4210 + }, + { + "epoch": 0.44, + "learning_rate": 1.3693289812447023e-05, + "loss": 1.4151, + "step": 4211 + }, + { + "epoch": 0.44, + "learning_rate": 1.3689888099409572e-05, + "loss": 1.4214, + "step": 4212 + }, + { + "epoch": 0.44, + "learning_rate": 1.368648589202192e-05, + "loss": 1.4287, + "step": 4213 + }, + { + "epoch": 0.44, + "learning_rate": 1.3683083190739883e-05, + "loss": 1.345, + "step": 4214 + }, + { + "epoch": 0.44, + "learning_rate": 1.367967999601933e-05, + "loss": 1.3022, + "step": 4215 + }, + { + "epoch": 0.44, + "learning_rate": 1.3676276308316207e-05, + "loss": 1.3971, + "step": 4216 + }, + { + "epoch": 0.44, + "learning_rate": 1.3672872128086514e-05, + "loss": 1.3335, + "step": 4217 + }, + { + "epoch": 0.44, + "learning_rate": 1.366946745578633e-05, + "loss": 1.3988, + "step": 4218 + }, + { + "epoch": 0.44, + "learning_rate": 1.366606229187179e-05, + "loss": 1.4508, + "step": 4219 + }, + { + "epoch": 0.44, + "learning_rate": 1.3662656636799099e-05, + "loss": 1.3814, + "step": 4220 + }, + { + "epoch": 0.44, + "learning_rate": 1.3659250491024527e-05, + "loss": 1.4128, + "step": 4221 + }, + { + "epoch": 0.44, + "learning_rate": 1.3655843855004411e-05, + "loss": 1.3893, + "step": 4222 + }, + { + "epoch": 0.44, + "learning_rate": 1.3652436729195154e-05, + "loss": 1.2551, + "step": 4223 + }, + { + "epoch": 0.44, + "learning_rate": 1.3649029114053219e-05, + "loss": 1.4386, + "step": 4224 + }, + { + "epoch": 0.44, + "learning_rate": 1.364562101003514e-05, + "loss": 1.4028, + "step": 4225 + }, + { + "epoch": 0.44, + "learning_rate": 1.364221241759752e-05, + "loss": 1.4351, + "step": 4226 + }, + { + "epoch": 0.44, + "learning_rate": 1.363880333719702e-05, + "loss": 1.3941, + "step": 4227 + }, + { + "epoch": 0.44, + "learning_rate": 1.3635393769290368e-05, + "loss": 1.3879, + "step": 4228 + }, + { + "epoch": 0.44, + "learning_rate": 1.3631983714334358e-05, + "loss": 1.3773, + "step": 4229 + }, + { + "epoch": 0.44, + "learning_rate": 1.3628573172785853e-05, + "loss": 1.3679, + "step": 4230 + }, + { + "epoch": 0.44, + "learning_rate": 1.3625162145101776e-05, + "loss": 1.3705, + "step": 4231 + }, + { + "epoch": 0.44, + "learning_rate": 1.3621750631739114e-05, + "loss": 1.8157, + "step": 4232 + }, + { + "epoch": 0.44, + "learning_rate": 1.3618338633154928e-05, + "loss": 1.4056, + "step": 4233 + }, + { + "epoch": 0.44, + "learning_rate": 1.3614926149806334e-05, + "loss": 1.3716, + "step": 4234 + }, + { + "epoch": 0.44, + "learning_rate": 1.3611513182150523e-05, + "loss": 1.3766, + "step": 4235 + }, + { + "epoch": 0.44, + "learning_rate": 1.3608099730644733e-05, + "loss": 1.41, + "step": 4236 + }, + { + "epoch": 0.44, + "learning_rate": 1.3604685795746291e-05, + "loss": 1.421, + "step": 4237 + }, + { + "epoch": 0.44, + "learning_rate": 1.360127137791257e-05, + "loss": 1.3679, + "step": 4238 + }, + { + "epoch": 0.44, + "learning_rate": 1.3597856477601018e-05, + "loss": 1.4615, + "step": 4239 + }, + { + "epoch": 0.44, + "learning_rate": 1.359444109526914e-05, + "loss": 1.3418, + "step": 4240 + }, + { + "epoch": 0.44, + "learning_rate": 1.3591025231374513e-05, + "loss": 1.3631, + "step": 4241 + }, + { + "epoch": 0.44, + "learning_rate": 1.3587608886374772e-05, + "loss": 1.3802, + "step": 4242 + }, + { + "epoch": 0.44, + "learning_rate": 1.3584192060727622e-05, + "loss": 1.4156, + "step": 4243 + }, + { + "epoch": 0.45, + "learning_rate": 1.3580774754890827e-05, + "loss": 1.4161, + "step": 4244 + }, + { + "epoch": 0.45, + "learning_rate": 1.3577356969322222e-05, + "loss": 1.3535, + "step": 4245 + }, + { + "epoch": 0.45, + "learning_rate": 1.3573938704479699e-05, + "loss": 1.3859, + "step": 4246 + }, + { + "epoch": 0.45, + "learning_rate": 1.357051996082122e-05, + "loss": 1.3595, + "step": 4247 + }, + { + "epoch": 0.45, + "learning_rate": 1.3567100738804806e-05, + "loss": 1.4191, + "step": 4248 + }, + { + "epoch": 0.45, + "learning_rate": 1.3563681038888548e-05, + "loss": 1.4186, + "step": 4249 + }, + { + "epoch": 0.45, + "learning_rate": 1.3560260861530596e-05, + "loss": 1.43, + "step": 4250 + }, + { + "epoch": 0.45, + "learning_rate": 1.3556840207189168e-05, + "loss": 1.4139, + "step": 4251 + }, + { + "epoch": 0.45, + "learning_rate": 1.3553419076322539e-05, + "loss": 1.4005, + "step": 4252 + }, + { + "epoch": 0.45, + "learning_rate": 1.3549997469389058e-05, + "loss": 1.3468, + "step": 4253 + }, + { + "epoch": 0.45, + "learning_rate": 1.3546575386847132e-05, + "loss": 1.3756, + "step": 4254 + }, + { + "epoch": 0.45, + "learning_rate": 1.3543152829155226e-05, + "loss": 1.4063, + "step": 4255 + }, + { + "epoch": 0.45, + "learning_rate": 1.3539729796771884e-05, + "loss": 1.4666, + "step": 4256 + }, + { + "epoch": 0.45, + "learning_rate": 1.3536306290155694e-05, + "loss": 1.4212, + "step": 4257 + }, + { + "epoch": 0.45, + "learning_rate": 1.3532882309765332e-05, + "loss": 1.4883, + "step": 4258 + }, + { + "epoch": 0.45, + "learning_rate": 1.3529457856059507e-05, + "loss": 1.6641, + "step": 4259 + }, + { + "epoch": 0.45, + "learning_rate": 1.3526032929497022e-05, + "loss": 1.3659, + "step": 4260 + }, + { + "epoch": 0.45, + "learning_rate": 1.3522607530536717e-05, + "loss": 1.5945, + "step": 4261 + }, + { + "epoch": 0.45, + "learning_rate": 1.351918165963752e-05, + "loss": 1.3643, + "step": 4262 + }, + { + "epoch": 0.45, + "learning_rate": 1.3515755317258397e-05, + "loss": 1.3442, + "step": 4263 + }, + { + "epoch": 0.45, + "learning_rate": 1.3512328503858398e-05, + "loss": 1.3982, + "step": 4264 + }, + { + "epoch": 0.45, + "learning_rate": 1.3508901219896624e-05, + "loss": 1.4985, + "step": 4265 + }, + { + "epoch": 0.45, + "learning_rate": 1.350547346583225e-05, + "loss": 1.3319, + "step": 4266 + }, + { + "epoch": 0.45, + "learning_rate": 1.3502045242124497e-05, + "loss": 1.3961, + "step": 4267 + }, + { + "epoch": 0.45, + "learning_rate": 1.3498616549232665e-05, + "loss": 1.4565, + "step": 4268 + }, + { + "epoch": 0.45, + "learning_rate": 1.349518738761611e-05, + "loss": 1.375, + "step": 4269 + }, + { + "epoch": 0.45, + "learning_rate": 1.3491757757734254e-05, + "loss": 1.3005, + "step": 4270 + }, + { + "epoch": 0.45, + "learning_rate": 1.348832766004657e-05, + "loss": 1.3185, + "step": 4271 + }, + { + "epoch": 0.45, + "learning_rate": 1.3484897095012613e-05, + "loss": 1.4449, + "step": 4272 + }, + { + "epoch": 0.45, + "learning_rate": 1.3481466063091988e-05, + "loss": 1.3587, + "step": 4273 + }, + { + "epoch": 0.45, + "learning_rate": 1.3478034564744362e-05, + "loss": 1.3844, + "step": 4274 + }, + { + "epoch": 0.45, + "learning_rate": 1.3474602600429468e-05, + "loss": 1.4471, + "step": 4275 + }, + { + "epoch": 0.45, + "learning_rate": 1.3471170170607105e-05, + "loss": 1.4686, + "step": 4276 + }, + { + "epoch": 0.45, + "learning_rate": 1.3467737275737127e-05, + "loss": 1.312, + "step": 4277 + }, + { + "epoch": 0.45, + "learning_rate": 1.3464303916279453e-05, + "loss": 1.407, + "step": 4278 + }, + { + "epoch": 0.45, + "learning_rate": 1.346087009269407e-05, + "loss": 1.364, + "step": 4279 + }, + { + "epoch": 0.45, + "learning_rate": 1.3457435805441016e-05, + "loss": 1.4103, + "step": 4280 + }, + { + "epoch": 0.45, + "learning_rate": 1.3454001054980403e-05, + "loss": 1.4243, + "step": 4281 + }, + { + "epoch": 0.45, + "learning_rate": 1.3450565841772392e-05, + "loss": 1.3879, + "step": 4282 + }, + { + "epoch": 0.45, + "learning_rate": 1.344713016627722e-05, + "loss": 1.4688, + "step": 4283 + }, + { + "epoch": 0.45, + "learning_rate": 1.3443694028955176e-05, + "loss": 1.3983, + "step": 4284 + }, + { + "epoch": 0.45, + "learning_rate": 1.344025743026662e-05, + "loss": 1.4316, + "step": 4285 + }, + { + "epoch": 0.45, + "learning_rate": 1.3436820370671956e-05, + "loss": 1.3643, + "step": 4286 + }, + { + "epoch": 0.45, + "learning_rate": 1.3433382850631673e-05, + "loss": 1.4566, + "step": 4287 + }, + { + "epoch": 0.45, + "learning_rate": 1.3429944870606301e-05, + "loss": 1.1263, + "step": 4288 + }, + { + "epoch": 0.45, + "learning_rate": 1.3426506431056452e-05, + "loss": 1.2463, + "step": 4289 + }, + { + "epoch": 0.45, + "learning_rate": 1.342306753244278e-05, + "loss": 1.4753, + "step": 4290 + }, + { + "epoch": 0.45, + "learning_rate": 1.3419628175226012e-05, + "loss": 1.3789, + "step": 4291 + }, + { + "epoch": 0.45, + "learning_rate": 1.3416188359866932e-05, + "loss": 1.3906, + "step": 4292 + }, + { + "epoch": 0.45, + "learning_rate": 1.3412748086826389e-05, + "loss": 1.3995, + "step": 4293 + }, + { + "epoch": 0.45, + "learning_rate": 1.3409307356565288e-05, + "loss": 1.4906, + "step": 4294 + }, + { + "epoch": 0.45, + "learning_rate": 1.3405866169544602e-05, + "loss": 1.3951, + "step": 4295 + }, + { + "epoch": 0.45, + "learning_rate": 1.3402424526225359e-05, + "loss": 1.3753, + "step": 4296 + }, + { + "epoch": 0.45, + "learning_rate": 1.3398982427068654e-05, + "loss": 1.3686, + "step": 4297 + }, + { + "epoch": 0.45, + "learning_rate": 1.3395539872535636e-05, + "loss": 1.3612, + "step": 4298 + }, + { + "epoch": 0.45, + "learning_rate": 1.3392096863087522e-05, + "loss": 1.4043, + "step": 4299 + }, + { + "epoch": 0.45, + "learning_rate": 1.3388653399185585e-05, + "loss": 1.4068, + "step": 4300 + }, + { + "epoch": 0.45, + "learning_rate": 1.338520948129116e-05, + "loss": 1.4066, + "step": 4301 + }, + { + "epoch": 0.45, + "learning_rate": 1.3381765109865646e-05, + "loss": 1.4944, + "step": 4302 + }, + { + "epoch": 0.45, + "learning_rate": 1.3378320285370496e-05, + "loss": 1.3575, + "step": 4303 + }, + { + "epoch": 0.45, + "learning_rate": 1.3374875008267236e-05, + "loss": 1.3807, + "step": 4304 + }, + { + "epoch": 0.45, + "learning_rate": 1.3371429279017437e-05, + "loss": 1.4389, + "step": 4305 + }, + { + "epoch": 0.45, + "learning_rate": 1.3367983098082739e-05, + "loss": 1.4858, + "step": 4306 + }, + { + "epoch": 0.45, + "learning_rate": 1.3364536465924844e-05, + "loss": 1.3282, + "step": 4307 + }, + { + "epoch": 0.45, + "learning_rate": 1.3361089383005515e-05, + "loss": 1.4306, + "step": 4308 + }, + { + "epoch": 0.45, + "learning_rate": 1.3357641849786566e-05, + "loss": 1.3892, + "step": 4309 + }, + { + "epoch": 0.45, + "learning_rate": 1.3354193866729883e-05, + "loss": 1.3621, + "step": 4310 + }, + { + "epoch": 0.45, + "learning_rate": 1.3350745434297401e-05, + "loss": 1.3476, + "step": 4311 + }, + { + "epoch": 0.45, + "learning_rate": 1.334729655295113e-05, + "loss": 1.4477, + "step": 4312 + }, + { + "epoch": 0.45, + "learning_rate": 1.3343847223153123e-05, + "loss": 1.3585, + "step": 4313 + }, + { + "epoch": 0.45, + "learning_rate": 1.334039744536551e-05, + "loss": 1.3616, + "step": 4314 + }, + { + "epoch": 0.45, + "learning_rate": 1.3336947220050462e-05, + "loss": 1.3579, + "step": 4315 + }, + { + "epoch": 0.45, + "learning_rate": 1.3333496547670232e-05, + "loss": 1.3557, + "step": 4316 + }, + { + "epoch": 0.45, + "learning_rate": 1.3330045428687113e-05, + "loss": 1.4443, + "step": 4317 + }, + { + "epoch": 0.45, + "learning_rate": 1.332659386356347e-05, + "loss": 1.3621, + "step": 4318 + }, + { + "epoch": 0.45, + "learning_rate": 1.3323141852761726e-05, + "loss": 1.3295, + "step": 4319 + }, + { + "epoch": 0.45, + "learning_rate": 1.3319689396744358e-05, + "loss": 1.4187, + "step": 4320 + }, + { + "epoch": 0.45, + "learning_rate": 1.3316236495973905e-05, + "loss": 1.335, + "step": 4321 + }, + { + "epoch": 0.45, + "learning_rate": 1.331278315091297e-05, + "loss": 1.4382, + "step": 4322 + }, + { + "epoch": 0.45, + "learning_rate": 1.3309329362024212e-05, + "loss": 1.4244, + "step": 4323 + }, + { + "epoch": 0.45, + "learning_rate": 1.3305875129770351e-05, + "loss": 1.488, + "step": 4324 + }, + { + "epoch": 0.45, + "learning_rate": 1.3302420454614165e-05, + "loss": 1.3369, + "step": 4325 + }, + { + "epoch": 0.45, + "learning_rate": 1.3298965337018487e-05, + "loss": 1.3648, + "step": 4326 + }, + { + "epoch": 0.45, + "learning_rate": 1.3295509777446226e-05, + "loss": 1.3924, + "step": 4327 + }, + { + "epoch": 0.45, + "learning_rate": 1.3292053776360324e-05, + "loss": 1.3789, + "step": 4328 + }, + { + "epoch": 0.45, + "learning_rate": 1.3288597334223802e-05, + "loss": 1.3902, + "step": 4329 + }, + { + "epoch": 0.45, + "learning_rate": 1.3285140451499735e-05, + "loss": 1.4057, + "step": 4330 + }, + { + "epoch": 0.45, + "learning_rate": 1.328168312865126e-05, + "loss": 1.4536, + "step": 4331 + }, + { + "epoch": 0.45, + "learning_rate": 1.3278225366141565e-05, + "loss": 1.3075, + "step": 4332 + }, + { + "epoch": 0.45, + "learning_rate": 1.3274767164433901e-05, + "loss": 1.4579, + "step": 4333 + }, + { + "epoch": 0.45, + "learning_rate": 1.3271308523991579e-05, + "loss": 1.3906, + "step": 4334 + }, + { + "epoch": 0.45, + "learning_rate": 1.326784944527797e-05, + "loss": 1.3992, + "step": 4335 + }, + { + "epoch": 0.45, + "learning_rate": 1.3264389928756498e-05, + "loss": 1.4001, + "step": 4336 + }, + { + "epoch": 0.45, + "learning_rate": 1.3260929974890653e-05, + "loss": 1.2948, + "step": 4337 + }, + { + "epoch": 0.45, + "learning_rate": 1.3257469584143976e-05, + "loss": 1.4041, + "step": 4338 + }, + { + "epoch": 0.46, + "learning_rate": 1.3254008756980076e-05, + "loss": 1.5035, + "step": 4339 + }, + { + "epoch": 0.46, + "learning_rate": 1.3250547493862609e-05, + "loss": 1.4867, + "step": 4340 + }, + { + "epoch": 0.46, + "learning_rate": 1.3247085795255302e-05, + "loss": 1.3612, + "step": 4341 + }, + { + "epoch": 0.46, + "learning_rate": 1.3243623661621925e-05, + "loss": 1.4193, + "step": 4342 + }, + { + "epoch": 0.46, + "learning_rate": 1.3240161093426322e-05, + "loss": 1.3596, + "step": 4343 + }, + { + "epoch": 0.46, + "learning_rate": 1.3236698091132383e-05, + "loss": 1.4448, + "step": 4344 + }, + { + "epoch": 0.46, + "learning_rate": 1.3233234655204066e-05, + "loss": 1.3924, + "step": 4345 + }, + { + "epoch": 0.46, + "learning_rate": 1.322977078610538e-05, + "loss": 1.3552, + "step": 4346 + }, + { + "epoch": 0.46, + "learning_rate": 1.3226306484300395e-05, + "loss": 1.3949, + "step": 4347 + }, + { + "epoch": 0.46, + "learning_rate": 1.322284175025324e-05, + "loss": 1.399, + "step": 4348 + }, + { + "epoch": 0.46, + "learning_rate": 1.3219376584428094e-05, + "loss": 1.4755, + "step": 4349 + }, + { + "epoch": 0.46, + "learning_rate": 1.3215910987289212e-05, + "loss": 1.3877, + "step": 4350 + }, + { + "epoch": 0.46, + "learning_rate": 1.3212444959300882e-05, + "loss": 1.3916, + "step": 4351 + }, + { + "epoch": 0.46, + "learning_rate": 1.3208978500927472e-05, + "loss": 1.3462, + "step": 4352 + }, + { + "epoch": 0.46, + "learning_rate": 1.3205511612633392e-05, + "loss": 1.3834, + "step": 4353 + }, + { + "epoch": 0.46, + "learning_rate": 1.3202044294883123e-05, + "loss": 1.3843, + "step": 4354 + }, + { + "epoch": 0.46, + "learning_rate": 1.3198576548141189e-05, + "loss": 1.2439, + "step": 4355 + }, + { + "epoch": 0.46, + "learning_rate": 1.3195108372872181e-05, + "loss": 1.4106, + "step": 4356 + }, + { + "epoch": 0.46, + "learning_rate": 1.3191639769540746e-05, + "loss": 1.4417, + "step": 4357 + }, + { + "epoch": 0.46, + "learning_rate": 1.3188170738611596e-05, + "loss": 1.4393, + "step": 4358 + }, + { + "epoch": 0.46, + "learning_rate": 1.3184701280549476e-05, + "loss": 1.4616, + "step": 4359 + }, + { + "epoch": 0.46, + "learning_rate": 1.3181231395819218e-05, + "loss": 1.3215, + "step": 4360 + }, + { + "epoch": 0.46, + "learning_rate": 1.3177761084885689e-05, + "loss": 1.368, + "step": 4361 + }, + { + "epoch": 0.46, + "learning_rate": 1.317429034821383e-05, + "loss": 1.3247, + "step": 4362 + }, + { + "epoch": 0.46, + "learning_rate": 1.3170819186268618e-05, + "loss": 1.4512, + "step": 4363 + }, + { + "epoch": 0.46, + "learning_rate": 1.3167347599515111e-05, + "loss": 1.3129, + "step": 4364 + }, + { + "epoch": 0.46, + "learning_rate": 1.3163875588418404e-05, + "loss": 1.3934, + "step": 4365 + }, + { + "epoch": 0.46, + "learning_rate": 1.3160403153443666e-05, + "loss": 1.4518, + "step": 4366 + }, + { + "epoch": 0.46, + "learning_rate": 1.3156930295056105e-05, + "loss": 1.3959, + "step": 4367 + }, + { + "epoch": 0.46, + "learning_rate": 1.3153457013721e-05, + "loss": 1.3475, + "step": 4368 + }, + { + "epoch": 0.46, + "learning_rate": 1.3149983309903687e-05, + "loss": 1.4102, + "step": 4369 + }, + { + "epoch": 0.46, + "learning_rate": 1.3146509184069538e-05, + "loss": 1.3674, + "step": 4370 + }, + { + "epoch": 0.46, + "learning_rate": 1.314303463668401e-05, + "loss": 1.3739, + "step": 4371 + }, + { + "epoch": 0.46, + "learning_rate": 1.3139559668212596e-05, + "loss": 1.4249, + "step": 4372 + }, + { + "epoch": 0.46, + "learning_rate": 1.3136084279120857e-05, + "loss": 1.4473, + "step": 4373 + }, + { + "epoch": 0.46, + "learning_rate": 1.3132608469874404e-05, + "loss": 1.4443, + "step": 4374 + }, + { + "epoch": 0.46, + "learning_rate": 1.3129132240938905e-05, + "loss": 1.3534, + "step": 4375 + }, + { + "epoch": 0.46, + "learning_rate": 1.3125655592780083e-05, + "loss": 1.5663, + "step": 4376 + }, + { + "epoch": 0.46, + "learning_rate": 1.3122178525863727e-05, + "loss": 1.3465, + "step": 4377 + }, + { + "epoch": 0.46, + "learning_rate": 1.3118701040655669e-05, + "loss": 1.35, + "step": 4378 + }, + { + "epoch": 0.46, + "eval_loss": 1.447788953781128, + "eval_runtime": 77.4473, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4378 + }, + { + "epoch": 0.46, + "learning_rate": 1.3115223137621804e-05, + "loss": 1.343, + "step": 4379 + }, + { + "epoch": 0.46, + "learning_rate": 1.3111744817228078e-05, + "loss": 1.4227, + "step": 4380 + }, + { + "epoch": 0.46, + "learning_rate": 1.3108266079940508e-05, + "loss": 1.3982, + "step": 4381 + }, + { + "epoch": 0.46, + "learning_rate": 1.3104786926225141e-05, + "loss": 1.4211, + "step": 4382 + }, + { + "epoch": 0.46, + "learning_rate": 1.3101307356548103e-05, + "loss": 1.382, + "step": 4383 + }, + { + "epoch": 0.46, + "learning_rate": 1.3097827371375562e-05, + "loss": 1.4637, + "step": 4384 + }, + { + "epoch": 0.46, + "learning_rate": 1.3094346971173754e-05, + "loss": 1.4572, + "step": 4385 + }, + { + "epoch": 0.46, + "learning_rate": 1.3090866156408956e-05, + "loss": 1.5113, + "step": 4386 + }, + { + "epoch": 0.46, + "learning_rate": 1.3087384927547512e-05, + "loss": 1.2197, + "step": 4387 + }, + { + "epoch": 0.46, + "learning_rate": 1.3083903285055813e-05, + "loss": 1.3861, + "step": 4388 + }, + { + "epoch": 0.46, + "learning_rate": 1.3080421229400315e-05, + "loss": 1.4754, + "step": 4389 + }, + { + "epoch": 0.46, + "learning_rate": 1.307693876104752e-05, + "loss": 1.3588, + "step": 4390 + }, + { + "epoch": 0.46, + "learning_rate": 1.3073455880463987e-05, + "loss": 1.3995, + "step": 4391 + }, + { + "epoch": 0.46, + "learning_rate": 1.3069972588116341e-05, + "loss": 1.354, + "step": 4392 + }, + { + "epoch": 0.46, + "learning_rate": 1.3066488884471244e-05, + "loss": 1.3378, + "step": 4393 + }, + { + "epoch": 0.46, + "learning_rate": 1.306300476999543e-05, + "loss": 1.5951, + "step": 4394 + }, + { + "epoch": 0.46, + "learning_rate": 1.305952024515568e-05, + "loss": 1.3661, + "step": 4395 + }, + { + "epoch": 0.46, + "learning_rate": 1.3056035310418826e-05, + "loss": 1.4066, + "step": 4396 + }, + { + "epoch": 0.46, + "learning_rate": 1.3052549966251764e-05, + "loss": 1.3687, + "step": 4397 + }, + { + "epoch": 0.46, + "learning_rate": 1.3049064213121438e-05, + "loss": 1.4573, + "step": 4398 + }, + { + "epoch": 0.46, + "learning_rate": 1.3045578051494852e-05, + "loss": 1.3519, + "step": 4399 + }, + { + "epoch": 0.46, + "learning_rate": 1.3042091481839063e-05, + "loss": 1.2803, + "step": 4400 + }, + { + "epoch": 0.46, + "learning_rate": 1.3038604504621173e-05, + "loss": 1.4014, + "step": 4401 + }, + { + "epoch": 0.46, + "learning_rate": 1.3035117120308358e-05, + "loss": 1.4534, + "step": 4402 + }, + { + "epoch": 0.46, + "learning_rate": 1.3031629329367832e-05, + "loss": 1.4747, + "step": 4403 + }, + { + "epoch": 0.46, + "learning_rate": 1.3028141132266877e-05, + "loss": 1.374, + "step": 4404 + }, + { + "epoch": 0.46, + "learning_rate": 1.3024652529472807e-05, + "loss": 1.4328, + "step": 4405 + }, + { + "epoch": 0.46, + "learning_rate": 1.302116352145302e-05, + "loss": 1.468, + "step": 4406 + }, + { + "epoch": 0.46, + "learning_rate": 1.3017674108674942e-05, + "loss": 1.2947, + "step": 4407 + }, + { + "epoch": 0.46, + "learning_rate": 1.3014184291606077e-05, + "loss": 1.3682, + "step": 4408 + }, + { + "epoch": 0.46, + "learning_rate": 1.3010694070713959e-05, + "loss": 1.3651, + "step": 4409 + }, + { + "epoch": 0.46, + "learning_rate": 1.3007203446466194e-05, + "loss": 1.418, + "step": 4410 + }, + { + "epoch": 0.46, + "learning_rate": 1.3003712419330433e-05, + "loss": 1.416, + "step": 4411 + }, + { + "epoch": 0.46, + "learning_rate": 1.300022098977439e-05, + "loss": 1.2979, + "step": 4412 + }, + { + "epoch": 0.46, + "learning_rate": 1.2996729158265819e-05, + "loss": 1.3868, + "step": 4413 + }, + { + "epoch": 0.46, + "learning_rate": 1.2993236925272542e-05, + "loss": 1.3102, + "step": 4414 + }, + { + "epoch": 0.46, + "learning_rate": 1.2989744291262422e-05, + "loss": 1.3506, + "step": 4415 + }, + { + "epoch": 0.46, + "learning_rate": 1.2986251256703388e-05, + "loss": 1.4018, + "step": 4416 + }, + { + "epoch": 0.46, + "learning_rate": 1.2982757822063417e-05, + "loss": 1.4081, + "step": 4417 + }, + { + "epoch": 0.46, + "learning_rate": 1.2979263987810533e-05, + "loss": 1.3592, + "step": 4418 + }, + { + "epoch": 0.46, + "learning_rate": 1.297576975441283e-05, + "loss": 1.4287, + "step": 4419 + }, + { + "epoch": 0.46, + "learning_rate": 1.2972275122338433e-05, + "loss": 1.4099, + "step": 4420 + }, + { + "epoch": 0.46, + "learning_rate": 1.2968780092055546e-05, + "loss": 1.4005, + "step": 4421 + }, + { + "epoch": 0.46, + "learning_rate": 1.2965284664032401e-05, + "loss": 1.365, + "step": 4422 + }, + { + "epoch": 0.46, + "learning_rate": 1.2961788838737309e-05, + "loss": 1.3588, + "step": 4423 + }, + { + "epoch": 0.46, + "learning_rate": 1.2958292616638606e-05, + "loss": 1.3702, + "step": 4424 + }, + { + "epoch": 0.46, + "learning_rate": 1.2954795998204708e-05, + "loss": 1.3487, + "step": 4425 + }, + { + "epoch": 0.46, + "learning_rate": 1.2951298983904063e-05, + "loss": 1.4395, + "step": 4426 + }, + { + "epoch": 0.46, + "learning_rate": 1.2947801574205193e-05, + "loss": 1.3523, + "step": 4427 + }, + { + "epoch": 0.46, + "learning_rate": 1.2944303769576645e-05, + "loss": 1.3125, + "step": 4428 + }, + { + "epoch": 0.46, + "learning_rate": 1.2940805570487048e-05, + "loss": 1.5476, + "step": 4429 + }, + { + "epoch": 0.46, + "learning_rate": 1.2937306977405062e-05, + "loss": 1.4076, + "step": 4430 + }, + { + "epoch": 0.46, + "learning_rate": 1.2933807990799418e-05, + "loss": 1.3007, + "step": 4431 + }, + { + "epoch": 0.46, + "learning_rate": 1.293030861113888e-05, + "loss": 1.3566, + "step": 4432 + }, + { + "epoch": 0.46, + "learning_rate": 1.2926808838892285e-05, + "loss": 1.3907, + "step": 4433 + }, + { + "epoch": 0.46, + "learning_rate": 1.2923308674528501e-05, + "loss": 1.379, + "step": 4434 + }, + { + "epoch": 0.47, + "learning_rate": 1.2919808118516475e-05, + "loss": 1.4319, + "step": 4435 + }, + { + "epoch": 0.47, + "learning_rate": 1.2916307171325176e-05, + "loss": 1.3392, + "step": 4436 + }, + { + "epoch": 0.47, + "learning_rate": 1.291280583342365e-05, + "loss": 1.401, + "step": 4437 + }, + { + "epoch": 0.47, + "learning_rate": 1.2909304105280984e-05, + "loss": 1.3939, + "step": 4438 + }, + { + "epoch": 0.47, + "learning_rate": 1.2905801987366322e-05, + "loss": 1.4676, + "step": 4439 + }, + { + "epoch": 0.47, + "learning_rate": 1.2902299480148855e-05, + "loss": 1.3957, + "step": 4440 + }, + { + "epoch": 0.47, + "learning_rate": 1.2898796584097828e-05, + "loss": 1.3587, + "step": 4441 + }, + { + "epoch": 0.47, + "learning_rate": 1.2895293299682545e-05, + "loss": 1.5809, + "step": 4442 + }, + { + "epoch": 0.47, + "learning_rate": 1.289178962737235e-05, + "loss": 1.3436, + "step": 4443 + }, + { + "epoch": 0.47, + "learning_rate": 1.2888285567636647e-05, + "loss": 1.4535, + "step": 4444 + }, + { + "epoch": 0.47, + "learning_rate": 1.2884781120944889e-05, + "loss": 1.3377, + "step": 4445 + }, + { + "epoch": 0.47, + "learning_rate": 1.2881276287766587e-05, + "loss": 0.8221, + "step": 4446 + }, + { + "epoch": 0.47, + "learning_rate": 1.2877771068571288e-05, + "loss": 0.7259, + "step": 4447 + }, + { + "epoch": 0.47, + "learning_rate": 1.2874265463828612e-05, + "loss": 0.8279, + "step": 4448 + }, + { + "epoch": 0.47, + "learning_rate": 1.2870759474008213e-05, + "loss": 1.3523, + "step": 4449 + }, + { + "epoch": 0.47, + "learning_rate": 1.2867253099579808e-05, + "loss": 1.3658, + "step": 4450 + }, + { + "epoch": 0.47, + "learning_rate": 1.2863746341013158e-05, + "loss": 1.4112, + "step": 4451 + }, + { + "epoch": 0.47, + "learning_rate": 1.2860239198778085e-05, + "loss": 1.389, + "step": 4452 + }, + { + "epoch": 0.47, + "learning_rate": 1.2856731673344442e-05, + "loss": 1.4066, + "step": 4453 + }, + { + "epoch": 0.47, + "learning_rate": 1.2853223765182165e-05, + "loss": 1.3267, + "step": 4454 + }, + { + "epoch": 0.47, + "learning_rate": 1.2849715474761209e-05, + "loss": 1.3381, + "step": 4455 + }, + { + "epoch": 0.47, + "learning_rate": 1.2846206802551602e-05, + "loss": 1.2882, + "step": 4456 + }, + { + "epoch": 0.47, + "learning_rate": 1.2842697749023414e-05, + "loss": 1.3199, + "step": 4457 + }, + { + "epoch": 0.47, + "learning_rate": 1.2839188314646771e-05, + "loss": 1.3896, + "step": 4458 + }, + { + "epoch": 0.47, + "learning_rate": 1.2835678499891842e-05, + "loss": 1.3186, + "step": 4459 + }, + { + "epoch": 0.47, + "learning_rate": 1.283216830522885e-05, + "loss": 1.3466, + "step": 4460 + }, + { + "epoch": 0.47, + "learning_rate": 1.2828657731128083e-05, + "loss": 1.4678, + "step": 4461 + }, + { + "epoch": 0.47, + "learning_rate": 1.2825146778059857e-05, + "loss": 1.4408, + "step": 4462 + }, + { + "epoch": 0.47, + "learning_rate": 1.2821635446494553e-05, + "loss": 1.3672, + "step": 4463 + }, + { + "epoch": 0.47, + "learning_rate": 1.2818123736902597e-05, + "loss": 1.3836, + "step": 4464 + }, + { + "epoch": 0.47, + "learning_rate": 1.2814611649754472e-05, + "loss": 1.3493, + "step": 4465 + }, + { + "epoch": 0.47, + "learning_rate": 1.2811099185520704e-05, + "loss": 1.3584, + "step": 4466 + }, + { + "epoch": 0.47, + "learning_rate": 1.2807586344671875e-05, + "loss": 1.3551, + "step": 4467 + }, + { + "epoch": 0.47, + "learning_rate": 1.2804073127678612e-05, + "loss": 1.3254, + "step": 4468 + }, + { + "epoch": 0.47, + "learning_rate": 1.28005595350116e-05, + "loss": 1.3405, + "step": 4469 + }, + { + "epoch": 0.47, + "learning_rate": 1.2797045567141568e-05, + "loss": 1.3432, + "step": 4470 + }, + { + "epoch": 0.47, + "learning_rate": 1.2793531224539297e-05, + "loss": 1.4347, + "step": 4471 + }, + { + "epoch": 0.47, + "learning_rate": 1.279001650767562e-05, + "loss": 1.3304, + "step": 4472 + }, + { + "epoch": 0.47, + "learning_rate": 1.278650141702142e-05, + "loss": 1.3244, + "step": 4473 + }, + { + "epoch": 0.47, + "learning_rate": 1.2782985953047625e-05, + "loss": 1.3756, + "step": 4474 + }, + { + "epoch": 0.47, + "learning_rate": 1.2779470116225219e-05, + "loss": 1.5468, + "step": 4475 + }, + { + "epoch": 0.47, + "learning_rate": 1.2775953907025232e-05, + "loss": 1.4316, + "step": 4476 + }, + { + "epoch": 0.47, + "learning_rate": 1.2772437325918752e-05, + "loss": 1.3724, + "step": 4477 + }, + { + "epoch": 0.47, + "learning_rate": 1.27689203733769e-05, + "loss": 1.4458, + "step": 4478 + }, + { + "epoch": 0.47, + "learning_rate": 1.2765403049870865e-05, + "loss": 1.3622, + "step": 4479 + }, + { + "epoch": 0.47, + "learning_rate": 1.2761885355871875e-05, + "loss": 1.3875, + "step": 4480 + }, + { + "epoch": 0.47, + "learning_rate": 1.2758367291851217e-05, + "loss": 1.3577, + "step": 4481 + }, + { + "epoch": 0.47, + "learning_rate": 1.2754848858280211e-05, + "loss": 1.4256, + "step": 4482 + }, + { + "epoch": 0.47, + "learning_rate": 1.2751330055630242e-05, + "loss": 1.3771, + "step": 4483 + }, + { + "epoch": 0.47, + "learning_rate": 1.274781088437274e-05, + "loss": 1.357, + "step": 4484 + }, + { + "epoch": 0.47, + "learning_rate": 1.274429134497918e-05, + "loss": 1.3634, + "step": 4485 + }, + { + "epoch": 0.47, + "learning_rate": 1.2740771437921096e-05, + "loss": 1.3661, + "step": 4486 + }, + { + "epoch": 0.47, + "learning_rate": 1.2737251163670057e-05, + "loss": 1.3819, + "step": 4487 + }, + { + "epoch": 0.47, + "learning_rate": 1.2733730522697696e-05, + "loss": 1.4491, + "step": 4488 + }, + { + "epoch": 0.47, + "learning_rate": 1.2730209515475687e-05, + "loss": 1.3857, + "step": 4489 + }, + { + "epoch": 0.47, + "learning_rate": 1.2726688142475751e-05, + "loss": 1.3837, + "step": 4490 + }, + { + "epoch": 0.47, + "learning_rate": 1.2723166404169663e-05, + "loss": 1.3755, + "step": 4491 + }, + { + "epoch": 0.47, + "learning_rate": 1.271964430102925e-05, + "loss": 1.3767, + "step": 4492 + }, + { + "epoch": 0.47, + "learning_rate": 1.2716121833526376e-05, + "loss": 1.4416, + "step": 4493 + }, + { + "epoch": 0.47, + "learning_rate": 1.2712599002132966e-05, + "loss": 1.5573, + "step": 4494 + }, + { + "epoch": 0.47, + "learning_rate": 1.2709075807320988e-05, + "loss": 1.365, + "step": 4495 + }, + { + "epoch": 0.47, + "learning_rate": 1.270555224956246e-05, + "loss": 1.3862, + "step": 4496 + }, + { + "epoch": 0.47, + "learning_rate": 1.2702028329329445e-05, + "loss": 1.3003, + "step": 4497 + }, + { + "epoch": 0.47, + "learning_rate": 1.2698504047094064e-05, + "loss": 1.3806, + "step": 4498 + }, + { + "epoch": 0.47, + "learning_rate": 1.269497940332847e-05, + "loss": 1.5425, + "step": 4499 + }, + { + "epoch": 0.47, + "learning_rate": 1.269145439850489e-05, + "loss": 1.3541, + "step": 4500 + }, + { + "epoch": 0.47, + "learning_rate": 1.268792903309557e-05, + "loss": 1.4337, + "step": 4501 + }, + { + "epoch": 0.47, + "learning_rate": 1.2684403307572825e-05, + "loss": 1.4004, + "step": 4502 + }, + { + "epoch": 0.47, + "learning_rate": 1.268087722240901e-05, + "loss": 1.9453, + "step": 4503 + }, + { + "epoch": 0.47, + "learning_rate": 1.2677350778076532e-05, + "loss": 1.3907, + "step": 4504 + }, + { + "epoch": 0.47, + "learning_rate": 1.2673823975047839e-05, + "loss": 1.4993, + "step": 4505 + }, + { + "epoch": 0.47, + "learning_rate": 1.2670296813795432e-05, + "loss": 1.4386, + "step": 4506 + }, + { + "epoch": 0.47, + "learning_rate": 1.266676929479187e-05, + "loss": 1.4944, + "step": 4507 + }, + { + "epoch": 0.47, + "learning_rate": 1.266324141850974e-05, + "loss": 1.4311, + "step": 4508 + }, + { + "epoch": 0.47, + "learning_rate": 1.265971318542169e-05, + "loss": 1.3607, + "step": 4509 + }, + { + "epoch": 0.47, + "learning_rate": 1.2656184596000412e-05, + "loss": 1.4007, + "step": 4510 + }, + { + "epoch": 0.47, + "learning_rate": 1.2652655650718645e-05, + "loss": 1.4561, + "step": 4511 + }, + { + "epoch": 0.47, + "learning_rate": 1.2649126350049181e-05, + "loss": 1.4321, + "step": 4512 + }, + { + "epoch": 0.47, + "learning_rate": 1.2645596694464851e-05, + "loss": 1.2856, + "step": 4513 + }, + { + "epoch": 0.47, + "learning_rate": 1.2642066684438543e-05, + "loss": 1.3979, + "step": 4514 + }, + { + "epoch": 0.47, + "learning_rate": 1.2638536320443184e-05, + "loss": 1.4977, + "step": 4515 + }, + { + "epoch": 0.47, + "learning_rate": 1.2635005602951752e-05, + "loss": 1.377, + "step": 4516 + }, + { + "epoch": 0.47, + "learning_rate": 1.2631474532437275e-05, + "loss": 1.4266, + "step": 4517 + }, + { + "epoch": 0.47, + "learning_rate": 1.2627943109372822e-05, + "loss": 1.409, + "step": 4518 + }, + { + "epoch": 0.47, + "learning_rate": 1.2624411334231519e-05, + "loss": 1.3374, + "step": 4519 + }, + { + "epoch": 0.47, + "learning_rate": 1.2620879207486525e-05, + "loss": 1.3765, + "step": 4520 + }, + { + "epoch": 0.47, + "learning_rate": 1.2617346729611061e-05, + "loss": 1.3805, + "step": 4521 + }, + { + "epoch": 0.47, + "learning_rate": 1.2613813901078384e-05, + "loss": 1.3326, + "step": 4522 + }, + { + "epoch": 0.47, + "learning_rate": 1.2610280722361807e-05, + "loss": 1.3909, + "step": 4523 + }, + { + "epoch": 0.47, + "learning_rate": 1.260674719393468e-05, + "loss": 1.3815, + "step": 4524 + }, + { + "epoch": 0.47, + "learning_rate": 1.2603213316270409e-05, + "loss": 1.5589, + "step": 4525 + }, + { + "epoch": 0.47, + "learning_rate": 1.2599679089842437e-05, + "loss": 1.4416, + "step": 4526 + }, + { + "epoch": 0.47, + "learning_rate": 1.259614451512427e-05, + "loss": 1.3529, + "step": 4527 + }, + { + "epoch": 0.47, + "learning_rate": 1.2592609592589437e-05, + "loss": 1.3135, + "step": 4528 + }, + { + "epoch": 0.47, + "learning_rate": 1.2589074322711535e-05, + "loss": 1.4177, + "step": 4529 + }, + { + "epoch": 0.48, + "learning_rate": 1.25855387059642e-05, + "loss": 1.353, + "step": 4530 + }, + { + "epoch": 0.48, + "learning_rate": 1.2582002742821111e-05, + "loss": 1.431, + "step": 4531 + }, + { + "epoch": 0.48, + "learning_rate": 1.2578466433755998e-05, + "loss": 1.3803, + "step": 4532 + }, + { + "epoch": 0.48, + "learning_rate": 1.257492977924263e-05, + "loss": 1.3774, + "step": 4533 + }, + { + "epoch": 0.48, + "learning_rate": 1.2571392779754836e-05, + "loss": 1.4339, + "step": 4534 + }, + { + "epoch": 0.48, + "learning_rate": 1.256785543576648e-05, + "loss": 1.4097, + "step": 4535 + }, + { + "epoch": 0.48, + "learning_rate": 1.2564317747751473e-05, + "loss": 1.4223, + "step": 4536 + }, + { + "epoch": 0.48, + "learning_rate": 1.2560779716183775e-05, + "loss": 1.5148, + "step": 4537 + }, + { + "epoch": 0.48, + "learning_rate": 1.2557241341537394e-05, + "loss": 1.3547, + "step": 4538 + }, + { + "epoch": 0.48, + "learning_rate": 1.255370262428638e-05, + "loss": 1.393, + "step": 4539 + }, + { + "epoch": 0.48, + "learning_rate": 1.2550163564904829e-05, + "loss": 1.3312, + "step": 4540 + }, + { + "epoch": 0.48, + "learning_rate": 1.2546624163866882e-05, + "loss": 1.4193, + "step": 4541 + }, + { + "epoch": 0.48, + "learning_rate": 1.2543084421646735e-05, + "loss": 1.4161, + "step": 4542 + }, + { + "epoch": 0.48, + "learning_rate": 1.2539544338718614e-05, + "loss": 1.4224, + "step": 4543 + }, + { + "epoch": 0.48, + "learning_rate": 1.2536003915556805e-05, + "loss": 1.3484, + "step": 4544 + }, + { + "epoch": 0.48, + "learning_rate": 1.253246315263563e-05, + "loss": 1.4492, + "step": 4545 + }, + { + "epoch": 0.48, + "learning_rate": 1.2528922050429467e-05, + "loss": 1.3549, + "step": 4546 + }, + { + "epoch": 0.48, + "learning_rate": 1.252538060941272e-05, + "loss": 1.45, + "step": 4547 + }, + { + "epoch": 0.48, + "learning_rate": 1.2521838830059865e-05, + "loss": 1.3499, + "step": 4548 + }, + { + "epoch": 0.48, + "learning_rate": 1.2518296712845399e-05, + "loss": 1.3786, + "step": 4549 + }, + { + "epoch": 0.48, + "learning_rate": 1.2514754258243884e-05, + "loss": 1.3394, + "step": 4550 + }, + { + "epoch": 0.48, + "learning_rate": 1.2511211466729909e-05, + "loss": 1.2849, + "step": 4551 + }, + { + "epoch": 0.48, + "learning_rate": 1.250766833877812e-05, + "loss": 1.374, + "step": 4552 + }, + { + "epoch": 0.48, + "learning_rate": 1.2504124874863211e-05, + "loss": 1.3084, + "step": 4553 + }, + { + "epoch": 0.48, + "learning_rate": 1.2500581075459905e-05, + "loss": 1.3348, + "step": 4554 + }, + { + "epoch": 0.48, + "learning_rate": 1.249703694104299e-05, + "loss": 1.3797, + "step": 4555 + }, + { + "epoch": 0.48, + "learning_rate": 1.2493492472087279e-05, + "loss": 1.3371, + "step": 4556 + }, + { + "epoch": 0.48, + "learning_rate": 1.248994766906765e-05, + "loss": 1.3974, + "step": 4557 + }, + { + "epoch": 0.48, + "learning_rate": 1.2486402532459007e-05, + "loss": 1.388, + "step": 4558 + }, + { + "epoch": 0.48, + "learning_rate": 1.2482857062736313e-05, + "loss": 1.3619, + "step": 4559 + }, + { + "epoch": 0.48, + "learning_rate": 1.2479311260374565e-05, + "loss": 1.4123, + "step": 4560 + }, + { + "epoch": 0.48, + "learning_rate": 1.2475765125848814e-05, + "loss": 1.5485, + "step": 4561 + }, + { + "epoch": 0.48, + "learning_rate": 1.247221865963415e-05, + "loss": 1.4965, + "step": 4562 + }, + { + "epoch": 0.48, + "learning_rate": 1.2468671862205705e-05, + "loss": 1.4352, + "step": 4563 + }, + { + "epoch": 0.48, + "learning_rate": 1.246512473403866e-05, + "loss": 1.3935, + "step": 4564 + }, + { + "epoch": 0.48, + "learning_rate": 1.2461577275608243e-05, + "loss": 1.3798, + "step": 4565 + }, + { + "epoch": 0.48, + "learning_rate": 1.2458029487389718e-05, + "loss": 1.4039, + "step": 4566 + }, + { + "epoch": 0.48, + "learning_rate": 1.2454481369858397e-05, + "loss": 1.3723, + "step": 4567 + }, + { + "epoch": 0.48, + "learning_rate": 1.245093292348964e-05, + "loss": 1.3713, + "step": 4568 + }, + { + "epoch": 0.48, + "learning_rate": 1.2447384148758847e-05, + "loss": 1.4083, + "step": 4569 + }, + { + "epoch": 0.48, + "learning_rate": 1.244383504614146e-05, + "loss": 1.2811, + "step": 4570 + }, + { + "epoch": 0.48, + "learning_rate": 1.2440285616112968e-05, + "loss": 1.3509, + "step": 4571 + }, + { + "epoch": 0.48, + "learning_rate": 1.2436735859148905e-05, + "loss": 1.3481, + "step": 4572 + }, + { + "epoch": 0.48, + "learning_rate": 1.2433185775724847e-05, + "loss": 1.4168, + "step": 4573 + }, + { + "epoch": 0.48, + "learning_rate": 1.2429635366316418e-05, + "loss": 1.3671, + "step": 4574 + }, + { + "epoch": 0.48, + "learning_rate": 1.2426084631399271e-05, + "loss": 1.6514, + "step": 4575 + }, + { + "epoch": 0.48, + "learning_rate": 1.2422533571449123e-05, + "loss": 1.3564, + "step": 4576 + }, + { + "epoch": 0.48, + "learning_rate": 1.2418982186941721e-05, + "loss": 1.4586, + "step": 4577 + }, + { + "epoch": 0.48, + "eval_loss": 1.4425245523452759, + "eval_runtime": 77.3853, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 4577 + }, + { + "epoch": 0.48, + "learning_rate": 1.2415430478352858e-05, + "loss": 1.3922, + "step": 4578 + }, + { + "epoch": 0.48, + "learning_rate": 1.2411878446158374e-05, + "loss": 1.3903, + "step": 4579 + }, + { + "epoch": 0.48, + "learning_rate": 1.240832609083415e-05, + "loss": 1.3537, + "step": 4580 + }, + { + "epoch": 0.48, + "learning_rate": 1.2404773412856113e-05, + "loss": 1.356, + "step": 4581 + }, + { + "epoch": 0.48, + "learning_rate": 1.2401220412700223e-05, + "loss": 1.4483, + "step": 4582 + }, + { + "epoch": 0.48, + "learning_rate": 1.2397667090842496e-05, + "loss": 1.3926, + "step": 4583 + }, + { + "epoch": 0.48, + "learning_rate": 1.2394113447758986e-05, + "loss": 1.4816, + "step": 4584 + }, + { + "epoch": 0.48, + "learning_rate": 1.2390559483925788e-05, + "loss": 1.3742, + "step": 4585 + }, + { + "epoch": 0.48, + "learning_rate": 1.2387005199819044e-05, + "loss": 1.4476, + "step": 4586 + }, + { + "epoch": 0.48, + "learning_rate": 1.2383450595914932e-05, + "loss": 1.4029, + "step": 4587 + }, + { + "epoch": 0.48, + "learning_rate": 1.2379895672689683e-05, + "loss": 1.4797, + "step": 4588 + }, + { + "epoch": 0.48, + "learning_rate": 1.2376340430619565e-05, + "loss": 1.3366, + "step": 4589 + }, + { + "epoch": 0.48, + "learning_rate": 1.2372784870180885e-05, + "loss": 1.4226, + "step": 4590 + }, + { + "epoch": 0.48, + "learning_rate": 1.2369228991849997e-05, + "loss": 1.3668, + "step": 4591 + }, + { + "epoch": 0.48, + "learning_rate": 1.2365672796103305e-05, + "loss": 1.4932, + "step": 4592 + }, + { + "epoch": 0.48, + "learning_rate": 1.236211628341724e-05, + "loss": 1.4088, + "step": 4593 + }, + { + "epoch": 0.48, + "learning_rate": 1.2358559454268284e-05, + "loss": 1.3616, + "step": 4594 + }, + { + "epoch": 0.48, + "learning_rate": 1.2355002309132961e-05, + "loss": 1.4345, + "step": 4595 + }, + { + "epoch": 0.48, + "learning_rate": 1.2351444848487844e-05, + "loss": 1.4025, + "step": 4596 + }, + { + "epoch": 0.48, + "learning_rate": 1.2347887072809533e-05, + "loss": 1.3895, + "step": 4597 + }, + { + "epoch": 0.48, + "learning_rate": 1.2344328982574678e-05, + "loss": 1.3326, + "step": 4598 + }, + { + "epoch": 0.48, + "learning_rate": 1.234077057825998e-05, + "loss": 1.4249, + "step": 4599 + }, + { + "epoch": 0.48, + "learning_rate": 1.2337211860342167e-05, + "loss": 1.3649, + "step": 4600 + }, + { + "epoch": 0.48, + "learning_rate": 1.2333652829298016e-05, + "loss": 1.3831, + "step": 4601 + }, + { + "epoch": 0.48, + "learning_rate": 1.2330093485604346e-05, + "loss": 1.3748, + "step": 4602 + }, + { + "epoch": 0.48, + "learning_rate": 1.2326533829738022e-05, + "loss": 1.386, + "step": 4603 + }, + { + "epoch": 0.48, + "learning_rate": 1.2322973862175941e-05, + "loss": 1.3923, + "step": 4604 + }, + { + "epoch": 0.48, + "learning_rate": 1.2319413583395052e-05, + "loss": 1.3638, + "step": 4605 + }, + { + "epoch": 0.48, + "learning_rate": 1.2315852993872335e-05, + "loss": 1.3476, + "step": 4606 + }, + { + "epoch": 0.48, + "learning_rate": 1.2312292094084824e-05, + "loss": 1.3581, + "step": 4607 + }, + { + "epoch": 0.48, + "learning_rate": 1.2308730884509583e-05, + "loss": 1.3554, + "step": 4608 + }, + { + "epoch": 0.48, + "learning_rate": 1.2305169365623724e-05, + "loss": 1.3676, + "step": 4609 + }, + { + "epoch": 0.48, + "learning_rate": 1.2301607537904399e-05, + "loss": 1.24, + "step": 4610 + }, + { + "epoch": 0.48, + "learning_rate": 1.2298045401828803e-05, + "loss": 1.3295, + "step": 4611 + }, + { + "epoch": 0.48, + "learning_rate": 1.2294482957874169e-05, + "loss": 1.5684, + "step": 4612 + }, + { + "epoch": 0.48, + "learning_rate": 1.2290920206517774e-05, + "loss": 1.3403, + "step": 4613 + }, + { + "epoch": 0.48, + "learning_rate": 1.2287357148236933e-05, + "loss": 1.349, + "step": 4614 + }, + { + "epoch": 0.48, + "learning_rate": 1.2283793783509008e-05, + "loss": 1.4261, + "step": 4615 + }, + { + "epoch": 0.48, + "learning_rate": 1.2280230112811395e-05, + "loss": 1.322, + "step": 4616 + }, + { + "epoch": 0.48, + "learning_rate": 1.2276666136621538e-05, + "loss": 1.3399, + "step": 4617 + }, + { + "epoch": 0.48, + "learning_rate": 1.2273101855416912e-05, + "loss": 1.3878, + "step": 4618 + }, + { + "epoch": 0.48, + "learning_rate": 1.2269537269675044e-05, + "loss": 1.4733, + "step": 4619 + }, + { + "epoch": 0.48, + "learning_rate": 1.2265972379873497e-05, + "loss": 1.419, + "step": 4620 + }, + { + "epoch": 0.48, + "learning_rate": 1.226240718648987e-05, + "loss": 1.3918, + "step": 4621 + }, + { + "epoch": 0.48, + "learning_rate": 1.2258841690001815e-05, + "loss": 1.3398, + "step": 4622 + }, + { + "epoch": 0.48, + "learning_rate": 1.225527589088701e-05, + "loss": 1.4091, + "step": 4623 + }, + { + "epoch": 0.48, + "learning_rate": 1.2251709789623185e-05, + "loss": 1.3291, + "step": 4624 + }, + { + "epoch": 0.49, + "learning_rate": 1.2248143386688101e-05, + "loss": 1.4288, + "step": 4625 + }, + { + "epoch": 0.49, + "learning_rate": 1.224457668255957e-05, + "loss": 1.2942, + "step": 4626 + }, + { + "epoch": 0.49, + "learning_rate": 1.2241009677715437e-05, + "loss": 1.4014, + "step": 4627 + }, + { + "epoch": 0.49, + "learning_rate": 1.2237442372633586e-05, + "loss": 1.3823, + "step": 4628 + }, + { + "epoch": 0.49, + "learning_rate": 1.2233874767791945e-05, + "loss": 1.3556, + "step": 4629 + }, + { + "epoch": 0.49, + "learning_rate": 1.2230306863668485e-05, + "loss": 1.411, + "step": 4630 + }, + { + "epoch": 0.49, + "learning_rate": 1.2226738660741212e-05, + "loss": 1.4347, + "step": 4631 + }, + { + "epoch": 0.49, + "learning_rate": 1.2223170159488169e-05, + "loss": 1.3095, + "step": 4632 + }, + { + "epoch": 0.49, + "learning_rate": 1.221960136038745e-05, + "loss": 1.4272, + "step": 4633 + }, + { + "epoch": 0.49, + "learning_rate": 1.221603226391718e-05, + "loss": 1.367, + "step": 4634 + }, + { + "epoch": 0.49, + "learning_rate": 1.2212462870555523e-05, + "loss": 1.3357, + "step": 4635 + }, + { + "epoch": 0.49, + "learning_rate": 1.220889318078069e-05, + "loss": 1.3634, + "step": 4636 + }, + { + "epoch": 0.49, + "learning_rate": 1.2205323195070927e-05, + "loss": 1.4143, + "step": 4637 + }, + { + "epoch": 0.49, + "learning_rate": 1.2201752913904519e-05, + "loss": 1.4865, + "step": 4638 + }, + { + "epoch": 0.49, + "learning_rate": 1.2198182337759794e-05, + "loss": 1.451, + "step": 4639 + }, + { + "epoch": 0.49, + "learning_rate": 1.2194611467115116e-05, + "loss": 1.3953, + "step": 4640 + }, + { + "epoch": 0.49, + "learning_rate": 1.2191040302448887e-05, + "loss": 1.4099, + "step": 4641 + }, + { + "epoch": 0.49, + "learning_rate": 1.2187468844239559e-05, + "loss": 1.3338, + "step": 4642 + }, + { + "epoch": 0.49, + "learning_rate": 1.2183897092965609e-05, + "loss": 1.4392, + "step": 4643 + }, + { + "epoch": 0.49, + "learning_rate": 1.2180325049105559e-05, + "loss": 1.3196, + "step": 4644 + }, + { + "epoch": 0.49, + "learning_rate": 1.2176752713137977e-05, + "loss": 1.3727, + "step": 4645 + }, + { + "epoch": 0.49, + "learning_rate": 1.2173180085541464e-05, + "loss": 1.3118, + "step": 4646 + }, + { + "epoch": 0.49, + "learning_rate": 1.2169607166794655e-05, + "loss": 1.3695, + "step": 4647 + }, + { + "epoch": 0.49, + "learning_rate": 1.2166033957376231e-05, + "loss": 1.3568, + "step": 4648 + }, + { + "epoch": 0.49, + "learning_rate": 1.216246045776491e-05, + "loss": 1.3492, + "step": 4649 + }, + { + "epoch": 0.49, + "learning_rate": 1.2158886668439455e-05, + "loss": 1.3445, + "step": 4650 + }, + { + "epoch": 0.49, + "learning_rate": 1.2155312589878654e-05, + "loss": 1.3756, + "step": 4651 + }, + { + "epoch": 0.49, + "learning_rate": 1.2151738222561344e-05, + "loss": 1.3681, + "step": 4652 + }, + { + "epoch": 0.49, + "learning_rate": 1.2148163566966403e-05, + "loss": 1.4345, + "step": 4653 + }, + { + "epoch": 0.49, + "learning_rate": 1.2144588623572738e-05, + "loss": 1.5102, + "step": 4654 + }, + { + "epoch": 0.49, + "learning_rate": 1.2141013392859297e-05, + "loss": 1.3531, + "step": 4655 + }, + { + "epoch": 0.49, + "learning_rate": 1.2137437875305075e-05, + "loss": 1.3824, + "step": 4656 + }, + { + "epoch": 0.49, + "learning_rate": 1.2133862071389099e-05, + "loss": 1.4227, + "step": 4657 + }, + { + "epoch": 0.49, + "learning_rate": 1.2130285981590433e-05, + "loss": 1.3479, + "step": 4658 + }, + { + "epoch": 0.49, + "learning_rate": 1.2126709606388181e-05, + "loss": 1.381, + "step": 4659 + }, + { + "epoch": 0.49, + "learning_rate": 1.2123132946261485e-05, + "loss": 1.3847, + "step": 4660 + }, + { + "epoch": 0.49, + "learning_rate": 1.2119556001689527e-05, + "loss": 1.3549, + "step": 4661 + }, + { + "epoch": 0.49, + "learning_rate": 1.2115978773151527e-05, + "loss": 1.3754, + "step": 4662 + }, + { + "epoch": 0.49, + "learning_rate": 1.2112401261126736e-05, + "loss": 1.3329, + "step": 4663 + }, + { + "epoch": 0.49, + "learning_rate": 1.2108823466094453e-05, + "loss": 1.4228, + "step": 4664 + }, + { + "epoch": 0.49, + "learning_rate": 1.2105245388534013e-05, + "loss": 1.4138, + "step": 4665 + }, + { + "epoch": 0.49, + "learning_rate": 1.2101667028924782e-05, + "loss": 1.3538, + "step": 4666 + }, + { + "epoch": 0.49, + "learning_rate": 1.2098088387746168e-05, + "loss": 1.4848, + "step": 4667 + }, + { + "epoch": 0.49, + "learning_rate": 1.2094509465477619e-05, + "loss": 1.5719, + "step": 4668 + }, + { + "epoch": 0.49, + "learning_rate": 1.209093026259862e-05, + "loss": 1.3863, + "step": 4669 + }, + { + "epoch": 0.49, + "learning_rate": 1.2087350779588691e-05, + "loss": 1.4425, + "step": 4670 + }, + { + "epoch": 0.49, + "learning_rate": 1.2083771016927386e-05, + "loss": 1.3655, + "step": 4671 + }, + { + "epoch": 0.49, + "learning_rate": 1.208019097509431e-05, + "loss": 1.3629, + "step": 4672 + }, + { + "epoch": 0.49, + "learning_rate": 1.2076610654569092e-05, + "loss": 1.3849, + "step": 4673 + }, + { + "epoch": 0.49, + "learning_rate": 1.20730300558314e-05, + "loss": 1.3763, + "step": 4674 + }, + { + "epoch": 0.49, + "learning_rate": 1.2069449179360945e-05, + "loss": 1.5316, + "step": 4675 + }, + { + "epoch": 0.49, + "learning_rate": 1.2065868025637476e-05, + "loss": 1.2873, + "step": 4676 + }, + { + "epoch": 0.49, + "learning_rate": 1.2062286595140773e-05, + "loss": 1.3642, + "step": 4677 + }, + { + "epoch": 0.49, + "learning_rate": 1.2058704888350652e-05, + "loss": 1.3782, + "step": 4678 + }, + { + "epoch": 0.49, + "learning_rate": 1.2055122905746972e-05, + "loss": 1.4597, + "step": 4679 + }, + { + "epoch": 0.49, + "learning_rate": 1.205154064780963e-05, + "loss": 1.3952, + "step": 4680 + }, + { + "epoch": 0.49, + "learning_rate": 1.2047958115018554e-05, + "loss": 1.4012, + "step": 4681 + }, + { + "epoch": 0.49, + "learning_rate": 1.204437530785371e-05, + "loss": 1.3432, + "step": 4682 + }, + { + "epoch": 0.49, + "learning_rate": 1.2040792226795101e-05, + "loss": 1.4111, + "step": 4683 + }, + { + "epoch": 0.49, + "learning_rate": 1.2037208872322773e-05, + "loss": 1.4357, + "step": 4684 + }, + { + "epoch": 0.49, + "learning_rate": 1.2033625244916803e-05, + "loss": 1.3908, + "step": 4685 + }, + { + "epoch": 0.49, + "learning_rate": 1.2030041345057298e-05, + "loss": 1.3804, + "step": 4686 + }, + { + "epoch": 0.49, + "learning_rate": 1.2026457173224412e-05, + "loss": 1.4523, + "step": 4687 + }, + { + "epoch": 0.49, + "learning_rate": 1.2022872729898336e-05, + "loss": 1.4266, + "step": 4688 + }, + { + "epoch": 0.49, + "learning_rate": 1.201928801555929e-05, + "loss": 1.3345, + "step": 4689 + }, + { + "epoch": 0.49, + "learning_rate": 1.2015703030687532e-05, + "loss": 1.1714, + "step": 4690 + }, + { + "epoch": 0.49, + "learning_rate": 1.2012117775763361e-05, + "loss": 1.3899, + "step": 4691 + }, + { + "epoch": 0.49, + "learning_rate": 1.2008532251267109e-05, + "loss": 1.43, + "step": 4692 + }, + { + "epoch": 0.49, + "learning_rate": 1.2004946457679144e-05, + "loss": 1.4302, + "step": 4693 + }, + { + "epoch": 0.49, + "learning_rate": 1.2001360395479865e-05, + "loss": 1.3452, + "step": 4694 + }, + { + "epoch": 0.49, + "learning_rate": 1.1997774065149716e-05, + "loss": 1.3383, + "step": 4695 + }, + { + "epoch": 0.49, + "learning_rate": 1.1994187467169176e-05, + "loss": 1.3677, + "step": 4696 + }, + { + "epoch": 0.49, + "learning_rate": 1.1990600602018755e-05, + "loss": 1.4486, + "step": 4697 + }, + { + "epoch": 0.49, + "learning_rate": 1.1987013470178998e-05, + "loss": 1.4059, + "step": 4698 + }, + { + "epoch": 0.49, + "learning_rate": 1.198342607213049e-05, + "loss": 1.3558, + "step": 4699 + }, + { + "epoch": 0.49, + "learning_rate": 1.1979838408353854e-05, + "loss": 1.3931, + "step": 4700 + }, + { + "epoch": 0.49, + "learning_rate": 1.197625047932974e-05, + "loss": 1.5409, + "step": 4701 + }, + { + "epoch": 0.49, + "learning_rate": 1.197266228553884e-05, + "loss": 1.4878, + "step": 4702 + }, + { + "epoch": 0.49, + "learning_rate": 1.196907382746188e-05, + "loss": 1.3581, + "step": 4703 + }, + { + "epoch": 0.49, + "learning_rate": 1.1965485105579621e-05, + "loss": 1.3617, + "step": 4704 + }, + { + "epoch": 0.49, + "learning_rate": 1.1961896120372857e-05, + "loss": 1.399, + "step": 4705 + }, + { + "epoch": 0.49, + "learning_rate": 1.1958306872322425e-05, + "loss": 1.3861, + "step": 4706 + }, + { + "epoch": 0.49, + "learning_rate": 1.1954717361909186e-05, + "loss": 1.4719, + "step": 4707 + }, + { + "epoch": 0.49, + "learning_rate": 1.195112758961405e-05, + "loss": 1.393, + "step": 4708 + }, + { + "epoch": 0.49, + "learning_rate": 1.1947537555917947e-05, + "loss": 1.4252, + "step": 4709 + }, + { + "epoch": 0.49, + "learning_rate": 1.194394726130185e-05, + "loss": 1.4187, + "step": 4710 + }, + { + "epoch": 0.49, + "learning_rate": 1.1940356706246772e-05, + "loss": 1.4822, + "step": 4711 + }, + { + "epoch": 0.49, + "learning_rate": 1.193676589123375e-05, + "loss": 1.4259, + "step": 4712 + }, + { + "epoch": 0.49, + "learning_rate": 1.1933174816743857e-05, + "loss": 1.4226, + "step": 4713 + }, + { + "epoch": 0.49, + "learning_rate": 1.1929583483258216e-05, + "loss": 1.3701, + "step": 4714 + }, + { + "epoch": 0.49, + "learning_rate": 1.1925991891257967e-05, + "loss": 1.406, + "step": 4715 + }, + { + "epoch": 0.49, + "learning_rate": 1.1922400041224288e-05, + "loss": 1.4593, + "step": 4716 + }, + { + "epoch": 0.49, + "learning_rate": 1.1918807933638401e-05, + "loss": 1.3443, + "step": 4717 + }, + { + "epoch": 0.49, + "learning_rate": 1.1915215568981552e-05, + "loss": 1.3523, + "step": 4718 + }, + { + "epoch": 0.49, + "learning_rate": 1.1911622947735027e-05, + "loss": 1.3175, + "step": 4719 + }, + { + "epoch": 0.49, + "learning_rate": 1.1908030070380143e-05, + "loss": 1.3974, + "step": 4720 + }, + { + "epoch": 0.5, + "learning_rate": 1.1904436937398257e-05, + "loss": 1.386, + "step": 4721 + }, + { + "epoch": 0.5, + "learning_rate": 1.1900843549270753e-05, + "loss": 1.3684, + "step": 4722 + }, + { + "epoch": 0.5, + "learning_rate": 1.1897249906479054e-05, + "loss": 1.383, + "step": 4723 + }, + { + "epoch": 0.5, + "learning_rate": 1.1893656009504617e-05, + "loss": 1.38, + "step": 4724 + }, + { + "epoch": 0.5, + "learning_rate": 1.1890061858828928e-05, + "loss": 1.3844, + "step": 4725 + }, + { + "epoch": 0.5, + "learning_rate": 1.1886467454933515e-05, + "loss": 1.3252, + "step": 4726 + }, + { + "epoch": 0.5, + "learning_rate": 1.1882872798299934e-05, + "loss": 1.3434, + "step": 4727 + }, + { + "epoch": 0.5, + "learning_rate": 1.1879277889409779e-05, + "loss": 1.4115, + "step": 4728 + }, + { + "epoch": 0.5, + "learning_rate": 1.1875682728744669e-05, + "loss": 1.1911, + "step": 4729 + }, + { + "epoch": 0.5, + "learning_rate": 1.1872087316786272e-05, + "loss": 1.2794, + "step": 4730 + }, + { + "epoch": 0.5, + "learning_rate": 1.1868491654016274e-05, + "loss": 1.3961, + "step": 4731 + }, + { + "epoch": 0.5, + "learning_rate": 1.1864895740916404e-05, + "loss": 1.4965, + "step": 4732 + }, + { + "epoch": 0.5, + "learning_rate": 1.1861299577968419e-05, + "loss": 1.3932, + "step": 4733 + }, + { + "epoch": 0.5, + "learning_rate": 1.185770316565412e-05, + "loss": 1.3926, + "step": 4734 + }, + { + "epoch": 0.5, + "learning_rate": 1.1854106504455327e-05, + "loss": 1.3964, + "step": 4735 + }, + { + "epoch": 0.5, + "learning_rate": 1.1850509594853901e-05, + "loss": 1.3666, + "step": 4736 + }, + { + "epoch": 0.5, + "learning_rate": 1.1846912437331736e-05, + "loss": 1.4364, + "step": 4737 + }, + { + "epoch": 0.5, + "learning_rate": 1.1843315032370762e-05, + "loss": 1.3537, + "step": 4738 + }, + { + "epoch": 0.5, + "learning_rate": 1.1839717380452935e-05, + "loss": 1.4083, + "step": 4739 + }, + { + "epoch": 0.5, + "learning_rate": 1.1836119482060247e-05, + "loss": 1.3881, + "step": 4740 + }, + { + "epoch": 0.5, + "learning_rate": 1.1832521337674727e-05, + "loss": 1.4127, + "step": 4741 + }, + { + "epoch": 0.5, + "learning_rate": 1.1828922947778436e-05, + "loss": 1.3433, + "step": 4742 + }, + { + "epoch": 0.5, + "learning_rate": 1.1825324312853461e-05, + "loss": 1.486, + "step": 4743 + }, + { + "epoch": 0.5, + "learning_rate": 1.1821725433381925e-05, + "loss": 1.335, + "step": 4744 + }, + { + "epoch": 0.5, + "learning_rate": 1.1818126309845993e-05, + "loss": 1.3827, + "step": 4745 + }, + { + "epoch": 0.5, + "learning_rate": 1.181452694272785e-05, + "loss": 1.3146, + "step": 4746 + }, + { + "epoch": 0.5, + "learning_rate": 1.1810927332509717e-05, + "loss": 1.3543, + "step": 4747 + }, + { + "epoch": 0.5, + "learning_rate": 1.1807327479673852e-05, + "loss": 1.3544, + "step": 4748 + }, + { + "epoch": 0.5, + "learning_rate": 1.1803727384702543e-05, + "loss": 1.3677, + "step": 4749 + }, + { + "epoch": 0.5, + "learning_rate": 1.1800127048078111e-05, + "loss": 1.3842, + "step": 4750 + }, + { + "epoch": 0.5, + "learning_rate": 1.1796526470282907e-05, + "loss": 1.3495, + "step": 4751 + }, + { + "epoch": 0.5, + "learning_rate": 1.1792925651799314e-05, + "loss": 1.481, + "step": 4752 + }, + { + "epoch": 0.5, + "learning_rate": 1.1789324593109754e-05, + "loss": 1.3482, + "step": 4753 + }, + { + "epoch": 0.5, + "learning_rate": 1.1785723294696673e-05, + "loss": 1.2805, + "step": 4754 + }, + { + "epoch": 0.5, + "learning_rate": 1.1782121757042555e-05, + "loss": 1.3458, + "step": 4755 + }, + { + "epoch": 0.5, + "learning_rate": 1.1778519980629907e-05, + "loss": 1.3937, + "step": 4756 + }, + { + "epoch": 0.5, + "learning_rate": 1.1774917965941284e-05, + "loss": 1.3873, + "step": 4757 + }, + { + "epoch": 0.5, + "learning_rate": 1.1771315713459258e-05, + "loss": 1.3512, + "step": 4758 + }, + { + "epoch": 0.5, + "learning_rate": 1.1767713223666436e-05, + "loss": 1.4465, + "step": 4759 + }, + { + "epoch": 0.5, + "learning_rate": 1.1764110497045463e-05, + "loss": 1.4233, + "step": 4760 + }, + { + "epoch": 0.5, + "learning_rate": 1.1760507534079011e-05, + "loss": 1.4818, + "step": 4761 + }, + { + "epoch": 0.5, + "learning_rate": 1.1756904335249786e-05, + "loss": 1.2933, + "step": 4762 + }, + { + "epoch": 0.5, + "learning_rate": 1.1753300901040518e-05, + "loss": 1.3524, + "step": 4763 + }, + { + "epoch": 0.5, + "learning_rate": 1.1749697231933981e-05, + "loss": 1.4909, + "step": 4764 + }, + { + "epoch": 0.5, + "learning_rate": 1.1746093328412975e-05, + "loss": 1.2912, + "step": 4765 + }, + { + "epoch": 0.5, + "learning_rate": 1.1742489190960325e-05, + "loss": 1.3372, + "step": 4766 + }, + { + "epoch": 0.5, + "learning_rate": 1.1738884820058893e-05, + "loss": 1.3036, + "step": 4767 + }, + { + "epoch": 0.5, + "learning_rate": 1.1735280216191578e-05, + "loss": 1.3189, + "step": 4768 + }, + { + "epoch": 0.5, + "learning_rate": 1.1731675379841298e-05, + "loss": 1.4146, + "step": 4769 + }, + { + "epoch": 0.5, + "learning_rate": 1.1728070311491013e-05, + "loss": 1.3309, + "step": 4770 + }, + { + "epoch": 0.5, + "learning_rate": 1.1724465011623705e-05, + "loss": 1.3427, + "step": 4771 + }, + { + "epoch": 0.5, + "learning_rate": 1.1720859480722395e-05, + "loss": 1.4033, + "step": 4772 + }, + { + "epoch": 0.5, + "learning_rate": 1.1717253719270135e-05, + "loss": 1.3832, + "step": 4773 + }, + { + "epoch": 0.5, + "learning_rate": 1.1713647727749994e-05, + "loss": 1.4074, + "step": 4774 + }, + { + "epoch": 0.5, + "learning_rate": 1.1710041506645092e-05, + "loss": 1.3579, + "step": 4775 + }, + { + "epoch": 0.5, + "learning_rate": 1.1706435056438564e-05, + "loss": 1.3685, + "step": 4776 + }, + { + "epoch": 0.5, + "eval_loss": 1.436767816543579, + "eval_runtime": 77.4332, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4776 + }, + { + "epoch": 0.5, + "learning_rate": 1.1702828377613584e-05, + "loss": 1.5843, + "step": 4777 + }, + { + "epoch": 0.5, + "learning_rate": 1.1699221470653355e-05, + "loss": 1.4168, + "step": 4778 + }, + { + "epoch": 0.5, + "learning_rate": 1.1695614336041108e-05, + "loss": 1.3515, + "step": 4779 + }, + { + "epoch": 0.5, + "learning_rate": 1.169200697426011e-05, + "loss": 1.3214, + "step": 4780 + }, + { + "epoch": 0.5, + "learning_rate": 1.1688399385793652e-05, + "loss": 1.3728, + "step": 4781 + }, + { + "epoch": 0.5, + "learning_rate": 1.1684791571125054e-05, + "loss": 1.3759, + "step": 4782 + }, + { + "epoch": 0.5, + "learning_rate": 1.1681183530737678e-05, + "loss": 1.4955, + "step": 4783 + }, + { + "epoch": 0.5, + "learning_rate": 1.1677575265114904e-05, + "loss": 1.4284, + "step": 4784 + }, + { + "epoch": 0.5, + "learning_rate": 1.1673966774740151e-05, + "loss": 1.3725, + "step": 4785 + }, + { + "epoch": 0.5, + "learning_rate": 1.1670358060096858e-05, + "loss": 1.3612, + "step": 4786 + }, + { + "epoch": 0.5, + "learning_rate": 1.1666749121668506e-05, + "loss": 1.3021, + "step": 4787 + }, + { + "epoch": 0.5, + "learning_rate": 1.1663139959938597e-05, + "loss": 1.4399, + "step": 4788 + }, + { + "epoch": 0.5, + "learning_rate": 1.1659530575390668e-05, + "loss": 1.3511, + "step": 4789 + }, + { + "epoch": 0.5, + "learning_rate": 1.1655920968508276e-05, + "loss": 1.4211, + "step": 4790 + }, + { + "epoch": 0.5, + "learning_rate": 1.1652311139775028e-05, + "loss": 1.343, + "step": 4791 + }, + { + "epoch": 0.5, + "learning_rate": 1.1648701089674541e-05, + "loss": 1.3838, + "step": 4792 + }, + { + "epoch": 0.5, + "learning_rate": 1.164509081869047e-05, + "loss": 1.342, + "step": 4793 + }, + { + "epoch": 0.5, + "learning_rate": 1.1641480327306494e-05, + "loss": 1.3831, + "step": 4794 + }, + { + "epoch": 0.5, + "learning_rate": 1.1637869616006335e-05, + "loss": 1.4102, + "step": 4795 + }, + { + "epoch": 0.5, + "learning_rate": 1.1634258685273732e-05, + "loss": 1.4184, + "step": 4796 + }, + { + "epoch": 0.5, + "learning_rate": 1.1630647535592455e-05, + "loss": 1.3974, + "step": 4797 + }, + { + "epoch": 0.5, + "learning_rate": 1.1627036167446302e-05, + "loss": 1.251, + "step": 4798 + }, + { + "epoch": 0.5, + "learning_rate": 1.1623424581319113e-05, + "loss": 1.3485, + "step": 4799 + }, + { + "epoch": 0.5, + "learning_rate": 1.1619812777694742e-05, + "loss": 1.3544, + "step": 4800 + }, + { + "epoch": 0.5, + "learning_rate": 1.1616200757057076e-05, + "loss": 1.3772, + "step": 4801 + }, + { + "epoch": 0.5, + "learning_rate": 1.1612588519890038e-05, + "loss": 1.3082, + "step": 4802 + }, + { + "epoch": 0.5, + "learning_rate": 1.160897606667757e-05, + "loss": 1.3634, + "step": 4803 + }, + { + "epoch": 0.5, + "learning_rate": 1.1605363397903655e-05, + "loss": 1.3682, + "step": 4804 + }, + { + "epoch": 0.5, + "learning_rate": 1.1601750514052288e-05, + "loss": 1.3258, + "step": 4805 + }, + { + "epoch": 0.5, + "learning_rate": 1.1598137415607511e-05, + "loss": 1.279, + "step": 4806 + }, + { + "epoch": 0.5, + "learning_rate": 1.1594524103053382e-05, + "loss": 1.3759, + "step": 4807 + }, + { + "epoch": 0.5, + "learning_rate": 1.1590910576873995e-05, + "loss": 1.5404, + "step": 4808 + }, + { + "epoch": 0.5, + "learning_rate": 1.1587296837553463e-05, + "loss": 1.4949, + "step": 4809 + }, + { + "epoch": 0.5, + "learning_rate": 1.1583682885575943e-05, + "loss": 1.3501, + "step": 4810 + }, + { + "epoch": 0.5, + "learning_rate": 1.1580068721425608e-05, + "loss": 1.3898, + "step": 4811 + }, + { + "epoch": 0.5, + "learning_rate": 1.157645434558666e-05, + "loss": 1.3265, + "step": 4812 + }, + { + "epoch": 0.5, + "learning_rate": 1.1572839758543338e-05, + "loss": 1.3454, + "step": 4813 + }, + { + "epoch": 0.5, + "learning_rate": 1.1569224960779899e-05, + "loss": 1.4065, + "step": 4814 + }, + { + "epoch": 0.5, + "learning_rate": 1.156560995278064e-05, + "loss": 1.4932, + "step": 4815 + }, + { + "epoch": 0.51, + "learning_rate": 1.156199473502987e-05, + "loss": 1.4224, + "step": 4816 + }, + { + "epoch": 0.51, + "learning_rate": 1.1558379308011937e-05, + "loss": 1.3884, + "step": 4817 + }, + { + "epoch": 0.51, + "learning_rate": 1.1554763672211222e-05, + "loss": 1.3355, + "step": 4818 + }, + { + "epoch": 0.51, + "learning_rate": 1.1551147828112124e-05, + "loss": 1.4281, + "step": 4819 + }, + { + "epoch": 0.51, + "learning_rate": 1.1547531776199072e-05, + "loss": 1.3148, + "step": 4820 + }, + { + "epoch": 0.51, + "learning_rate": 1.1543915516956523e-05, + "loss": 1.3255, + "step": 4821 + }, + { + "epoch": 0.51, + "learning_rate": 1.1540299050868966e-05, + "loss": 1.3361, + "step": 4822 + }, + { + "epoch": 0.51, + "learning_rate": 1.1536682378420912e-05, + "loss": 1.3377, + "step": 4823 + }, + { + "epoch": 0.51, + "learning_rate": 1.1533065500096901e-05, + "loss": 1.4205, + "step": 4824 + }, + { + "epoch": 0.51, + "learning_rate": 1.1529448416381505e-05, + "loss": 1.4193, + "step": 4825 + }, + { + "epoch": 0.51, + "learning_rate": 1.1525831127759322e-05, + "loss": 1.37, + "step": 4826 + }, + { + "epoch": 0.51, + "learning_rate": 1.1522213634714971e-05, + "loss": 1.3642, + "step": 4827 + }, + { + "epoch": 0.51, + "learning_rate": 1.1518595937733103e-05, + "loss": 1.4834, + "step": 4828 + }, + { + "epoch": 0.51, + "learning_rate": 1.1514978037298402e-05, + "loss": 1.2864, + "step": 4829 + }, + { + "epoch": 0.51, + "learning_rate": 1.1511359933895567e-05, + "loss": 1.3468, + "step": 4830 + }, + { + "epoch": 0.51, + "learning_rate": 1.1507741628009337e-05, + "loss": 1.328, + "step": 4831 + }, + { + "epoch": 0.51, + "learning_rate": 1.1504123120124466e-05, + "loss": 1.3489, + "step": 4832 + }, + { + "epoch": 0.51, + "learning_rate": 1.1500504410725746e-05, + "loss": 1.4031, + "step": 4833 + }, + { + "epoch": 0.51, + "learning_rate": 1.149688550029799e-05, + "loss": 1.3482, + "step": 4834 + }, + { + "epoch": 0.51, + "learning_rate": 1.1493266389326037e-05, + "loss": 1.3674, + "step": 4835 + }, + { + "epoch": 0.51, + "learning_rate": 1.1489647078294753e-05, + "loss": 1.2895, + "step": 4836 + }, + { + "epoch": 0.51, + "learning_rate": 1.148602756768904e-05, + "loss": 1.4071, + "step": 4837 + }, + { + "epoch": 0.51, + "learning_rate": 1.1482407857993814e-05, + "loss": 1.5218, + "step": 4838 + }, + { + "epoch": 0.51, + "learning_rate": 1.1478787949694024e-05, + "loss": 1.4577, + "step": 4839 + }, + { + "epoch": 0.51, + "learning_rate": 1.1475167843274643e-05, + "loss": 1.3817, + "step": 4840 + }, + { + "epoch": 0.51, + "learning_rate": 1.1471547539220678e-05, + "loss": 1.3072, + "step": 4841 + }, + { + "epoch": 0.51, + "learning_rate": 1.146792703801715e-05, + "loss": 1.3737, + "step": 4842 + }, + { + "epoch": 0.51, + "learning_rate": 1.1464306340149119e-05, + "loss": 1.4001, + "step": 4843 + }, + { + "epoch": 0.51, + "learning_rate": 1.1460685446101658e-05, + "loss": 1.3963, + "step": 4844 + }, + { + "epoch": 0.51, + "learning_rate": 1.1457064356359882e-05, + "loss": 1.4061, + "step": 4845 + }, + { + "epoch": 0.51, + "learning_rate": 1.145344307140892e-05, + "loss": 1.4211, + "step": 4846 + }, + { + "epoch": 0.51, + "learning_rate": 1.144982159173393e-05, + "loss": 1.3197, + "step": 4847 + }, + { + "epoch": 0.51, + "learning_rate": 1.14461999178201e-05, + "loss": 1.3549, + "step": 4848 + }, + { + "epoch": 0.51, + "learning_rate": 1.1442578050152639e-05, + "loss": 1.3889, + "step": 4849 + }, + { + "epoch": 0.51, + "learning_rate": 1.1438955989216787e-05, + "loss": 1.3847, + "step": 4850 + }, + { + "epoch": 0.51, + "learning_rate": 1.1435333735497803e-05, + "loss": 1.3586, + "step": 4851 + }, + { + "epoch": 0.51, + "learning_rate": 1.1431711289480978e-05, + "loss": 1.503, + "step": 4852 + }, + { + "epoch": 0.51, + "learning_rate": 1.1428088651651627e-05, + "loss": 1.3654, + "step": 4853 + }, + { + "epoch": 0.51, + "learning_rate": 1.1424465822495092e-05, + "loss": 1.3741, + "step": 4854 + }, + { + "epoch": 0.51, + "learning_rate": 1.1420842802496737e-05, + "loss": 1.5437, + "step": 4855 + }, + { + "epoch": 0.51, + "learning_rate": 1.1417219592141953e-05, + "loss": 1.2179, + "step": 4856 + }, + { + "epoch": 0.51, + "learning_rate": 1.1413596191916159e-05, + "loss": 1.3939, + "step": 4857 + }, + { + "epoch": 0.51, + "learning_rate": 1.1409972602304796e-05, + "loss": 1.3383, + "step": 4858 + }, + { + "epoch": 0.51, + "learning_rate": 1.140634882379333e-05, + "loss": 1.3664, + "step": 4859 + }, + { + "epoch": 0.51, + "learning_rate": 1.1402724856867258e-05, + "loss": 1.4002, + "step": 4860 + }, + { + "epoch": 0.51, + "learning_rate": 1.1399100702012098e-05, + "loss": 1.2975, + "step": 4861 + }, + { + "epoch": 0.51, + "learning_rate": 1.1395476359713394e-05, + "loss": 1.3564, + "step": 4862 + }, + { + "epoch": 0.51, + "learning_rate": 1.1391851830456708e-05, + "loss": 1.3574, + "step": 4863 + }, + { + "epoch": 0.51, + "learning_rate": 1.1388227114727644e-05, + "loss": 1.3407, + "step": 4864 + }, + { + "epoch": 0.51, + "learning_rate": 1.1384602213011815e-05, + "loss": 1.3603, + "step": 4865 + }, + { + "epoch": 0.51, + "learning_rate": 1.1380977125794866e-05, + "loss": 1.3465, + "step": 4866 + }, + { + "epoch": 0.51, + "learning_rate": 1.1377351853562461e-05, + "loss": 1.3744, + "step": 4867 + }, + { + "epoch": 0.51, + "learning_rate": 1.1373726396800304e-05, + "loss": 1.3248, + "step": 4868 + }, + { + "epoch": 0.51, + "learning_rate": 1.1370100755994102e-05, + "loss": 1.3352, + "step": 4869 + }, + { + "epoch": 0.51, + "learning_rate": 1.1366474931629603e-05, + "loss": 1.3299, + "step": 4870 + }, + { + "epoch": 0.51, + "learning_rate": 1.1362848924192575e-05, + "loss": 1.344, + "step": 4871 + }, + { + "epoch": 0.51, + "learning_rate": 1.1359222734168809e-05, + "loss": 1.3209, + "step": 4872 + }, + { + "epoch": 0.51, + "learning_rate": 1.135559636204412e-05, + "loss": 1.3927, + "step": 4873 + }, + { + "epoch": 0.51, + "learning_rate": 1.1351969808304349e-05, + "loss": 1.3717, + "step": 4874 + }, + { + "epoch": 0.51, + "learning_rate": 1.1348343073435362e-05, + "loss": 1.3813, + "step": 4875 + }, + { + "epoch": 0.51, + "learning_rate": 1.1344716157923046e-05, + "loss": 1.236, + "step": 4876 + }, + { + "epoch": 0.51, + "learning_rate": 1.1341089062253319e-05, + "loss": 1.2591, + "step": 4877 + }, + { + "epoch": 0.51, + "learning_rate": 1.1337461786912112e-05, + "loss": 1.3211, + "step": 4878 + }, + { + "epoch": 0.51, + "learning_rate": 1.1333834332385394e-05, + "loss": 1.4534, + "step": 4879 + }, + { + "epoch": 0.51, + "learning_rate": 1.1330206699159145e-05, + "loss": 1.346, + "step": 4880 + }, + { + "epoch": 0.51, + "learning_rate": 1.132657888771938e-05, + "loss": 1.3952, + "step": 4881 + }, + { + "epoch": 0.51, + "learning_rate": 1.1322950898552125e-05, + "loss": 1.3008, + "step": 4882 + }, + { + "epoch": 0.51, + "learning_rate": 1.1319322732143445e-05, + "loss": 1.3201, + "step": 4883 + }, + { + "epoch": 0.51, + "learning_rate": 1.1315694388979416e-05, + "loss": 1.3761, + "step": 4884 + }, + { + "epoch": 0.51, + "learning_rate": 1.1312065869546147e-05, + "loss": 1.343, + "step": 4885 + }, + { + "epoch": 0.51, + "learning_rate": 1.1308437174329761e-05, + "loss": 1.3741, + "step": 4886 + }, + { + "epoch": 0.51, + "learning_rate": 1.1304808303816413e-05, + "loss": 1.402, + "step": 4887 + }, + { + "epoch": 0.51, + "learning_rate": 1.130117925849228e-05, + "loss": 1.3834, + "step": 4888 + }, + { + "epoch": 0.51, + "learning_rate": 1.1297550038843559e-05, + "loss": 1.3342, + "step": 4889 + }, + { + "epoch": 0.51, + "learning_rate": 1.1293920645356471e-05, + "loss": 1.3207, + "step": 4890 + }, + { + "epoch": 0.51, + "learning_rate": 1.1290291078517264e-05, + "loss": 1.4274, + "step": 4891 + }, + { + "epoch": 0.51, + "learning_rate": 1.1286661338812203e-05, + "loss": 1.328, + "step": 4892 + }, + { + "epoch": 0.51, + "learning_rate": 1.1283031426727584e-05, + "loss": 1.3823, + "step": 4893 + }, + { + "epoch": 0.51, + "learning_rate": 1.127940134274972e-05, + "loss": 1.3612, + "step": 4894 + }, + { + "epoch": 0.51, + "learning_rate": 1.127577108736495e-05, + "loss": 1.375, + "step": 4895 + }, + { + "epoch": 0.51, + "learning_rate": 1.1272140661059636e-05, + "loss": 1.3531, + "step": 4896 + }, + { + "epoch": 0.51, + "learning_rate": 1.1268510064320155e-05, + "loss": 1.3636, + "step": 4897 + }, + { + "epoch": 0.51, + "learning_rate": 1.1264879297632923e-05, + "loss": 1.3524, + "step": 4898 + }, + { + "epoch": 0.51, + "learning_rate": 1.1261248361484363e-05, + "loss": 1.3865, + "step": 4899 + }, + { + "epoch": 0.51, + "learning_rate": 1.125761725636093e-05, + "loss": 1.4069, + "step": 4900 + }, + { + "epoch": 0.51, + "learning_rate": 1.1253985982749098e-05, + "loss": 1.4643, + "step": 4901 + }, + { + "epoch": 0.51, + "learning_rate": 1.1250354541135364e-05, + "loss": 1.4506, + "step": 4902 + }, + { + "epoch": 0.51, + "learning_rate": 1.124672293200625e-05, + "loss": 1.3857, + "step": 4903 + }, + { + "epoch": 0.51, + "learning_rate": 1.1243091155848295e-05, + "loss": 1.3554, + "step": 4904 + }, + { + "epoch": 0.51, + "learning_rate": 1.1239459213148065e-05, + "loss": 1.4071, + "step": 4905 + }, + { + "epoch": 0.51, + "learning_rate": 1.1235827104392148e-05, + "loss": 1.3981, + "step": 4906 + }, + { + "epoch": 0.51, + "learning_rate": 1.1232194830067153e-05, + "loss": 1.4913, + "step": 4907 + }, + { + "epoch": 0.51, + "learning_rate": 1.1228562390659712e-05, + "loss": 1.3343, + "step": 4908 + }, + { + "epoch": 0.51, + "learning_rate": 1.1224929786656474e-05, + "loss": 1.3832, + "step": 4909 + }, + { + "epoch": 0.51, + "learning_rate": 1.122129701854412e-05, + "loss": 1.367, + "step": 4910 + }, + { + "epoch": 0.51, + "learning_rate": 1.1217664086809345e-05, + "loss": 1.4108, + "step": 4911 + }, + { + "epoch": 0.52, + "learning_rate": 1.1214030991938872e-05, + "loss": 1.3981, + "step": 4912 + }, + { + "epoch": 0.52, + "learning_rate": 1.1210397734419436e-05, + "loss": 1.5266, + "step": 4913 + }, + { + "epoch": 0.52, + "learning_rate": 1.1206764314737806e-05, + "loss": 1.337, + "step": 4914 + }, + { + "epoch": 0.52, + "learning_rate": 1.1203130733380765e-05, + "loss": 1.3784, + "step": 4915 + }, + { + "epoch": 0.52, + "learning_rate": 1.1199496990835117e-05, + "loss": 1.3048, + "step": 4916 + }, + { + "epoch": 0.52, + "learning_rate": 1.1195863087587692e-05, + "loss": 1.2977, + "step": 4917 + }, + { + "epoch": 0.52, + "learning_rate": 1.1192229024125344e-05, + "loss": 1.3304, + "step": 4918 + }, + { + "epoch": 0.52, + "learning_rate": 1.1188594800934938e-05, + "loss": 1.4102, + "step": 4919 + }, + { + "epoch": 0.52, + "learning_rate": 1.1184960418503366e-05, + "loss": 1.3932, + "step": 4920 + }, + { + "epoch": 0.52, + "learning_rate": 1.1181325877317547e-05, + "loss": 1.4985, + "step": 4921 + }, + { + "epoch": 0.52, + "learning_rate": 1.1177691177864415e-05, + "loss": 1.4596, + "step": 4922 + }, + { + "epoch": 0.52, + "learning_rate": 1.1174056320630924e-05, + "loss": 1.3559, + "step": 4923 + }, + { + "epoch": 0.52, + "learning_rate": 1.117042130610405e-05, + "loss": 1.4128, + "step": 4924 + }, + { + "epoch": 0.52, + "learning_rate": 1.1166786134770795e-05, + "loss": 1.3343, + "step": 4925 + }, + { + "epoch": 0.52, + "learning_rate": 1.116315080711818e-05, + "loss": 1.332, + "step": 4926 + }, + { + "epoch": 0.52, + "learning_rate": 1.115951532363324e-05, + "loss": 1.3616, + "step": 4927 + }, + { + "epoch": 0.52, + "learning_rate": 1.1155879684803041e-05, + "loss": 1.4074, + "step": 4928 + }, + { + "epoch": 0.52, + "learning_rate": 1.1152243891114665e-05, + "loss": 1.303, + "step": 4929 + }, + { + "epoch": 0.52, + "learning_rate": 1.1148607943055212e-05, + "loss": 1.4799, + "step": 4930 + }, + { + "epoch": 0.52, + "learning_rate": 1.1144971841111807e-05, + "loss": 1.3881, + "step": 4931 + }, + { + "epoch": 0.52, + "learning_rate": 1.1141335585771593e-05, + "loss": 1.338, + "step": 4932 + }, + { + "epoch": 0.52, + "learning_rate": 1.1137699177521738e-05, + "loss": 1.3289, + "step": 4933 + }, + { + "epoch": 0.52, + "learning_rate": 1.1134062616849426e-05, + "loss": 1.377, + "step": 4934 + }, + { + "epoch": 0.52, + "learning_rate": 1.1130425904241862e-05, + "loss": 1.3596, + "step": 4935 + }, + { + "epoch": 0.52, + "learning_rate": 1.112678904018627e-05, + "loss": 1.4264, + "step": 4936 + }, + { + "epoch": 0.52, + "learning_rate": 1.1123152025169898e-05, + "loss": 1.3526, + "step": 4937 + }, + { + "epoch": 0.52, + "learning_rate": 1.1119514859680016e-05, + "loss": 1.3271, + "step": 4938 + }, + { + "epoch": 0.52, + "learning_rate": 1.1115877544203905e-05, + "loss": 1.3907, + "step": 4939 + }, + { + "epoch": 0.52, + "learning_rate": 1.1112240079228878e-05, + "loss": 1.3415, + "step": 4940 + }, + { + "epoch": 0.52, + "learning_rate": 1.1108602465242258e-05, + "loss": 1.3875, + "step": 4941 + }, + { + "epoch": 0.52, + "learning_rate": 1.110496470273139e-05, + "loss": 1.3964, + "step": 4942 + }, + { + "epoch": 0.52, + "learning_rate": 1.1101326792183645e-05, + "loss": 1.3448, + "step": 4943 + }, + { + "epoch": 0.52, + "learning_rate": 1.1097688734086407e-05, + "loss": 1.3522, + "step": 4944 + }, + { + "epoch": 0.52, + "learning_rate": 1.1094050528927082e-05, + "loss": 1.2742, + "step": 4945 + }, + { + "epoch": 0.52, + "learning_rate": 1.1090412177193097e-05, + "loss": 1.417, + "step": 4946 + }, + { + "epoch": 0.52, + "learning_rate": 1.1086773679371898e-05, + "loss": 1.3993, + "step": 4947 + }, + { + "epoch": 0.52, + "learning_rate": 1.108313503595095e-05, + "loss": 1.3783, + "step": 4948 + }, + { + "epoch": 0.52, + "learning_rate": 1.1079496247417736e-05, + "loss": 1.3975, + "step": 4949 + }, + { + "epoch": 0.52, + "learning_rate": 1.1075857314259763e-05, + "loss": 1.4256, + "step": 4950 + }, + { + "epoch": 0.52, + "learning_rate": 1.1072218236964551e-05, + "loss": 1.3547, + "step": 4951 + }, + { + "epoch": 0.52, + "learning_rate": 1.106857901601965e-05, + "loss": 1.4243, + "step": 4952 + }, + { + "epoch": 0.52, + "learning_rate": 1.1064939651912612e-05, + "loss": 1.4259, + "step": 4953 + }, + { + "epoch": 0.52, + "learning_rate": 1.1061300145131027e-05, + "loss": 1.4323, + "step": 4954 + }, + { + "epoch": 0.52, + "learning_rate": 1.1057660496162488e-05, + "loss": 1.3608, + "step": 4955 + }, + { + "epoch": 0.52, + "learning_rate": 1.1054020705494622e-05, + "loss": 1.3703, + "step": 4956 + }, + { + "epoch": 0.52, + "learning_rate": 1.105038077361506e-05, + "loss": 1.3953, + "step": 4957 + }, + { + "epoch": 0.52, + "learning_rate": 1.1046740701011467e-05, + "loss": 1.392, + "step": 4958 + }, + { + "epoch": 0.52, + "learning_rate": 1.1043100488171513e-05, + "loss": 1.4101, + "step": 4959 + }, + { + "epoch": 0.52, + "learning_rate": 1.1039460135582894e-05, + "loss": 1.5432, + "step": 4960 + }, + { + "epoch": 0.52, + "learning_rate": 1.1035819643733326e-05, + "loss": 1.3822, + "step": 4961 + }, + { + "epoch": 0.52, + "learning_rate": 1.103217901311054e-05, + "loss": 1.3816, + "step": 4962 + }, + { + "epoch": 0.52, + "learning_rate": 1.1028538244202287e-05, + "loss": 1.3137, + "step": 4963 + }, + { + "epoch": 0.52, + "learning_rate": 1.102489733749634e-05, + "loss": 1.3791, + "step": 4964 + }, + { + "epoch": 0.52, + "learning_rate": 1.102125629348048e-05, + "loss": 1.3751, + "step": 4965 + }, + { + "epoch": 0.52, + "learning_rate": 1.1017615112642518e-05, + "loss": 1.3287, + "step": 4966 + }, + { + "epoch": 0.52, + "learning_rate": 1.1013973795470277e-05, + "loss": 1.3187, + "step": 4967 + }, + { + "epoch": 0.52, + "learning_rate": 1.1010332342451602e-05, + "loss": 1.3174, + "step": 4968 + }, + { + "epoch": 0.52, + "learning_rate": 1.1006690754074351e-05, + "loss": 1.3544, + "step": 4969 + }, + { + "epoch": 0.52, + "learning_rate": 1.1003049030826404e-05, + "loss": 1.3789, + "step": 4970 + }, + { + "epoch": 0.52, + "learning_rate": 1.0999407173195662e-05, + "loss": 1.4561, + "step": 4971 + }, + { + "epoch": 0.52, + "learning_rate": 1.0995765181670039e-05, + "loss": 1.3963, + "step": 4972 + }, + { + "epoch": 0.52, + "learning_rate": 1.0992123056737464e-05, + "loss": 1.3519, + "step": 4973 + }, + { + "epoch": 0.52, + "learning_rate": 1.0988480798885892e-05, + "loss": 1.3945, + "step": 4974 + }, + { + "epoch": 0.52, + "learning_rate": 1.0984838408603294e-05, + "loss": 1.4572, + "step": 4975 + }, + { + "epoch": 0.52, + "eval_loss": 1.4313459396362305, + "eval_runtime": 77.4808, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 4975 + }, + { + "epoch": 0.52, + "learning_rate": 1.0981195886377652e-05, + "loss": 1.3493, + "step": 4976 + }, + { + "epoch": 0.52, + "learning_rate": 1.0977553232696972e-05, + "loss": 1.3734, + "step": 4977 + }, + { + "epoch": 0.52, + "learning_rate": 1.0973910448049273e-05, + "loss": 1.3484, + "step": 4978 + }, + { + "epoch": 0.52, + "learning_rate": 1.09702675329226e-05, + "loss": 1.4288, + "step": 4979 + }, + { + "epoch": 0.52, + "learning_rate": 1.096662448780501e-05, + "loss": 1.3748, + "step": 4980 + }, + { + "epoch": 0.52, + "learning_rate": 1.0962981313184575e-05, + "loss": 1.3485, + "step": 4981 + }, + { + "epoch": 0.52, + "learning_rate": 1.0959338009549383e-05, + "loss": 1.3606, + "step": 4982 + }, + { + "epoch": 0.52, + "learning_rate": 1.095569457738755e-05, + "loss": 1.3963, + "step": 4983 + }, + { + "epoch": 0.52, + "learning_rate": 1.09520510171872e-05, + "loss": 1.2986, + "step": 4984 + }, + { + "epoch": 0.52, + "learning_rate": 1.0948407329436474e-05, + "loss": 1.3505, + "step": 4985 + }, + { + "epoch": 0.52, + "learning_rate": 1.0944763514623535e-05, + "loss": 1.4649, + "step": 4986 + }, + { + "epoch": 0.52, + "learning_rate": 1.0941119573236564e-05, + "loss": 1.4743, + "step": 4987 + }, + { + "epoch": 0.52, + "learning_rate": 1.0937475505763745e-05, + "loss": 1.3934, + "step": 4988 + }, + { + "epoch": 0.52, + "learning_rate": 1.09338313126933e-05, + "loss": 1.4225, + "step": 4989 + }, + { + "epoch": 0.52, + "learning_rate": 1.0930186994513453e-05, + "loss": 1.3626, + "step": 4990 + }, + { + "epoch": 0.52, + "learning_rate": 1.0926542551712446e-05, + "loss": 1.3614, + "step": 4991 + }, + { + "epoch": 0.52, + "learning_rate": 1.0922897984778546e-05, + "loss": 1.3766, + "step": 4992 + }, + { + "epoch": 0.52, + "learning_rate": 1.0919253294200027e-05, + "loss": 1.3295, + "step": 4993 + }, + { + "epoch": 0.52, + "learning_rate": 1.091560848046519e-05, + "loss": 1.3802, + "step": 4994 + }, + { + "epoch": 0.52, + "learning_rate": 1.091196354406234e-05, + "loss": 1.2976, + "step": 4995 + }, + { + "epoch": 0.52, + "learning_rate": 1.090831848547981e-05, + "loss": 1.3928, + "step": 4996 + }, + { + "epoch": 0.52, + "learning_rate": 1.0904673305205937e-05, + "loss": 1.3717, + "step": 4997 + }, + { + "epoch": 0.52, + "learning_rate": 1.0901028003729089e-05, + "loss": 1.3164, + "step": 4998 + }, + { + "epoch": 0.52, + "learning_rate": 1.0897382581537638e-05, + "loss": 1.3462, + "step": 4999 + }, + { + "epoch": 0.52, + "learning_rate": 1.0893737039119981e-05, + "loss": 1.3643, + "step": 5000 + }, + { + "epoch": 0.52, + "learning_rate": 1.089009137696452e-05, + "loss": 1.3452, + "step": 5001 + }, + { + "epoch": 0.52, + "learning_rate": 1.0886445595559686e-05, + "loss": 1.358, + "step": 5002 + }, + { + "epoch": 0.52, + "learning_rate": 1.0882799695393922e-05, + "loss": 1.4569, + "step": 5003 + }, + { + "epoch": 0.52, + "learning_rate": 1.0879153676955681e-05, + "loss": 1.2832, + "step": 5004 + }, + { + "epoch": 0.52, + "learning_rate": 1.0875507540733435e-05, + "loss": 1.4089, + "step": 5005 + }, + { + "epoch": 0.52, + "learning_rate": 1.087186128721567e-05, + "loss": 1.3178, + "step": 5006 + }, + { + "epoch": 0.53, + "learning_rate": 1.0868214916890902e-05, + "loss": 1.4883, + "step": 5007 + }, + { + "epoch": 0.53, + "learning_rate": 1.0864568430247638e-05, + "loss": 1.3991, + "step": 5008 + }, + { + "epoch": 0.53, + "learning_rate": 1.0860921827774422e-05, + "loss": 1.4507, + "step": 5009 + }, + { + "epoch": 0.53, + "learning_rate": 1.08572751099598e-05, + "loss": 1.3578, + "step": 5010 + }, + { + "epoch": 0.53, + "learning_rate": 1.0853628277292341e-05, + "loss": 1.4231, + "step": 5011 + }, + { + "epoch": 0.53, + "learning_rate": 1.0849981330260624e-05, + "loss": 1.4835, + "step": 5012 + }, + { + "epoch": 0.53, + "learning_rate": 1.084633426935325e-05, + "loss": 1.4511, + "step": 5013 + }, + { + "epoch": 0.53, + "learning_rate": 1.084268709505883e-05, + "loss": 1.3889, + "step": 5014 + }, + { + "epoch": 0.53, + "learning_rate": 1.0839039807865992e-05, + "loss": 1.355, + "step": 5015 + }, + { + "epoch": 0.53, + "learning_rate": 1.0835392408263375e-05, + "loss": 1.4829, + "step": 5016 + }, + { + "epoch": 0.53, + "learning_rate": 1.0831744896739643e-05, + "loss": 1.3019, + "step": 5017 + }, + { + "epoch": 0.53, + "learning_rate": 1.0828097273783465e-05, + "loss": 1.3418, + "step": 5018 + }, + { + "epoch": 0.53, + "learning_rate": 1.082444953988353e-05, + "loss": 1.4276, + "step": 5019 + }, + { + "epoch": 0.53, + "learning_rate": 1.0820801695528537e-05, + "loss": 1.2816, + "step": 5020 + }, + { + "epoch": 0.53, + "learning_rate": 1.081715374120721e-05, + "loss": 1.5144, + "step": 5021 + }, + { + "epoch": 0.53, + "learning_rate": 1.0813505677408278e-05, + "loss": 1.4063, + "step": 5022 + }, + { + "epoch": 0.53, + "learning_rate": 1.0809857504620487e-05, + "loss": 1.4011, + "step": 5023 + }, + { + "epoch": 0.53, + "learning_rate": 1.0806209223332598e-05, + "loss": 1.373, + "step": 5024 + }, + { + "epoch": 0.53, + "learning_rate": 1.0802560834033388e-05, + "loss": 1.6259, + "step": 5025 + }, + { + "epoch": 0.53, + "learning_rate": 1.0798912337211648e-05, + "loss": 1.4487, + "step": 5026 + }, + { + "epoch": 0.53, + "learning_rate": 1.0795263733356184e-05, + "loss": 1.3056, + "step": 5027 + }, + { + "epoch": 0.53, + "learning_rate": 1.079161502295581e-05, + "loss": 1.2871, + "step": 5028 + }, + { + "epoch": 0.53, + "learning_rate": 1.0787966206499363e-05, + "loss": 1.413, + "step": 5029 + }, + { + "epoch": 0.53, + "learning_rate": 1.0784317284475694e-05, + "loss": 1.3682, + "step": 5030 + }, + { + "epoch": 0.53, + "learning_rate": 1.0780668257373659e-05, + "loss": 1.493, + "step": 5031 + }, + { + "epoch": 0.53, + "learning_rate": 1.0777019125682136e-05, + "loss": 1.6823, + "step": 5032 + }, + { + "epoch": 0.53, + "learning_rate": 1.0773369889890015e-05, + "loss": 1.358, + "step": 5033 + }, + { + "epoch": 0.53, + "learning_rate": 1.07697205504862e-05, + "loss": 1.3532, + "step": 5034 + }, + { + "epoch": 0.53, + "learning_rate": 1.0766071107959608e-05, + "loss": 1.3432, + "step": 5035 + }, + { + "epoch": 0.53, + "learning_rate": 1.0762421562799173e-05, + "loss": 1.3575, + "step": 5036 + }, + { + "epoch": 0.53, + "learning_rate": 1.0758771915493838e-05, + "loss": 1.0924, + "step": 5037 + }, + { + "epoch": 0.53, + "learning_rate": 1.075512216653256e-05, + "loss": 0.7405, + "step": 5038 + }, + { + "epoch": 0.53, + "learning_rate": 1.0751472316404315e-05, + "loss": 0.7134, + "step": 5039 + }, + { + "epoch": 0.53, + "learning_rate": 1.0747822365598088e-05, + "loss": 1.0904, + "step": 5040 + }, + { + "epoch": 0.53, + "learning_rate": 1.0744172314602881e-05, + "loss": 1.4353, + "step": 5041 + }, + { + "epoch": 0.53, + "learning_rate": 1.0740522163907702e-05, + "loss": 1.361, + "step": 5042 + }, + { + "epoch": 0.53, + "learning_rate": 1.073687191400158e-05, + "loss": 1.4024, + "step": 5043 + }, + { + "epoch": 0.53, + "learning_rate": 1.0733221565373557e-05, + "loss": 1.328, + "step": 5044 + }, + { + "epoch": 0.53, + "learning_rate": 1.0729571118512683e-05, + "loss": 1.3309, + "step": 5045 + }, + { + "epoch": 0.53, + "learning_rate": 1.0725920573908024e-05, + "loss": 1.3819, + "step": 5046 + }, + { + "epoch": 0.53, + "learning_rate": 1.0722269932048659e-05, + "loss": 1.3467, + "step": 5047 + }, + { + "epoch": 0.53, + "learning_rate": 1.0718619193423683e-05, + "loss": 1.3036, + "step": 5048 + }, + { + "epoch": 0.53, + "learning_rate": 1.07149683585222e-05, + "loss": 1.3297, + "step": 5049 + }, + { + "epoch": 0.53, + "learning_rate": 1.0711317427833328e-05, + "loss": 1.3439, + "step": 5050 + }, + { + "epoch": 0.53, + "learning_rate": 1.0707666401846192e-05, + "loss": 1.4167, + "step": 5051 + }, + { + "epoch": 0.53, + "learning_rate": 1.0704015281049944e-05, + "loss": 1.4217, + "step": 5052 + }, + { + "epoch": 0.53, + "learning_rate": 1.070036406593374e-05, + "loss": 1.3394, + "step": 5053 + }, + { + "epoch": 0.53, + "learning_rate": 1.0696712756986745e-05, + "loss": 1.3242, + "step": 5054 + }, + { + "epoch": 0.53, + "learning_rate": 1.0693061354698143e-05, + "loss": 1.3957, + "step": 5055 + }, + { + "epoch": 0.53, + "learning_rate": 1.0689409859557123e-05, + "loss": 1.37, + "step": 5056 + }, + { + "epoch": 0.53, + "learning_rate": 1.0685758272052902e-05, + "loss": 1.4524, + "step": 5057 + }, + { + "epoch": 0.53, + "learning_rate": 1.0682106592674688e-05, + "loss": 1.528, + "step": 5058 + }, + { + "epoch": 0.53, + "learning_rate": 1.0678454821911719e-05, + "loss": 1.3613, + "step": 5059 + }, + { + "epoch": 0.53, + "learning_rate": 1.0674802960253234e-05, + "loss": 1.308, + "step": 5060 + }, + { + "epoch": 0.53, + "learning_rate": 1.0671151008188494e-05, + "loss": 1.3343, + "step": 5061 + }, + { + "epoch": 0.53, + "learning_rate": 1.066749896620676e-05, + "loss": 1.365, + "step": 5062 + }, + { + "epoch": 0.53, + "learning_rate": 1.0663846834797316e-05, + "loss": 1.4077, + "step": 5063 + }, + { + "epoch": 0.53, + "learning_rate": 1.0660194614449455e-05, + "loss": 1.324, + "step": 5064 + }, + { + "epoch": 0.53, + "learning_rate": 1.0656542305652478e-05, + "loss": 1.3623, + "step": 5065 + }, + { + "epoch": 0.53, + "learning_rate": 1.0652889908895701e-05, + "loss": 1.4079, + "step": 5066 + }, + { + "epoch": 0.53, + "learning_rate": 1.0649237424668451e-05, + "loss": 1.3089, + "step": 5067 + }, + { + "epoch": 0.53, + "learning_rate": 1.0645584853460069e-05, + "loss": 1.3967, + "step": 5068 + }, + { + "epoch": 0.53, + "learning_rate": 1.0641932195759905e-05, + "loss": 1.3639, + "step": 5069 + }, + { + "epoch": 0.53, + "learning_rate": 1.0638279452057319e-05, + "loss": 1.5919, + "step": 5070 + }, + { + "epoch": 0.53, + "learning_rate": 1.0634626622841686e-05, + "loss": 1.3348, + "step": 5071 + }, + { + "epoch": 0.53, + "learning_rate": 1.0630973708602395e-05, + "loss": 1.3146, + "step": 5072 + }, + { + "epoch": 0.53, + "learning_rate": 1.0627320709828836e-05, + "loss": 1.3375, + "step": 5073 + }, + { + "epoch": 0.53, + "learning_rate": 1.062366762701042e-05, + "loss": 1.3908, + "step": 5074 + }, + { + "epoch": 0.53, + "learning_rate": 1.0620014460636568e-05, + "loss": 1.3726, + "step": 5075 + }, + { + "epoch": 0.53, + "learning_rate": 1.061636121119671e-05, + "loss": 1.2348, + "step": 5076 + }, + { + "epoch": 0.53, + "learning_rate": 1.0612707879180284e-05, + "loss": 1.2957, + "step": 5077 + }, + { + "epoch": 0.53, + "learning_rate": 1.0609054465076749e-05, + "loss": 1.4202, + "step": 5078 + }, + { + "epoch": 0.53, + "learning_rate": 1.060540096937556e-05, + "loss": 1.5809, + "step": 5079 + }, + { + "epoch": 0.53, + "learning_rate": 1.0601747392566202e-05, + "loss": 1.3741, + "step": 5080 + }, + { + "epoch": 0.53, + "learning_rate": 1.059809373513815e-05, + "loss": 1.3537, + "step": 5081 + }, + { + "epoch": 0.53, + "learning_rate": 1.0594439997580907e-05, + "loss": 1.332, + "step": 5082 + }, + { + "epoch": 0.53, + "learning_rate": 1.0590786180383981e-05, + "loss": 1.3267, + "step": 5083 + }, + { + "epoch": 0.53, + "learning_rate": 1.0587132284036883e-05, + "loss": 1.3552, + "step": 5084 + }, + { + "epoch": 0.53, + "learning_rate": 1.0583478309029143e-05, + "loss": 1.2837, + "step": 5085 + }, + { + "epoch": 0.53, + "learning_rate": 1.0579824255850304e-05, + "loss": 1.4311, + "step": 5086 + }, + { + "epoch": 0.53, + "learning_rate": 1.0576170124989915e-05, + "loss": 1.4394, + "step": 5087 + }, + { + "epoch": 0.53, + "learning_rate": 1.0572515916937531e-05, + "loss": 1.3185, + "step": 5088 + }, + { + "epoch": 0.53, + "learning_rate": 1.0568861632182723e-05, + "loss": 1.4212, + "step": 5089 + }, + { + "epoch": 0.53, + "learning_rate": 1.0565207271215075e-05, + "loss": 1.0951, + "step": 5090 + }, + { + "epoch": 0.53, + "learning_rate": 1.0561552834524176e-05, + "loss": 1.4174, + "step": 5091 + }, + { + "epoch": 0.53, + "learning_rate": 1.0557898322599624e-05, + "loss": 1.3349, + "step": 5092 + }, + { + "epoch": 0.53, + "learning_rate": 1.0554243735931031e-05, + "loss": 1.399, + "step": 5093 + }, + { + "epoch": 0.53, + "learning_rate": 1.055058907500802e-05, + "loss": 1.4016, + "step": 5094 + }, + { + "epoch": 0.53, + "learning_rate": 1.0546934340320219e-05, + "loss": 1.3227, + "step": 5095 + }, + { + "epoch": 0.53, + "learning_rate": 1.0543279532357269e-05, + "loss": 1.4017, + "step": 5096 + }, + { + "epoch": 0.53, + "learning_rate": 1.053962465160882e-05, + "loss": 1.3937, + "step": 5097 + }, + { + "epoch": 0.53, + "learning_rate": 1.0535969698564532e-05, + "loss": 1.2405, + "step": 5098 + }, + { + "epoch": 0.53, + "learning_rate": 1.0532314673714081e-05, + "loss": 1.2939, + "step": 5099 + }, + { + "epoch": 0.53, + "learning_rate": 1.0528659577547136e-05, + "loss": 1.4165, + "step": 5100 + }, + { + "epoch": 0.53, + "learning_rate": 1.0525004410553394e-05, + "loss": 1.309, + "step": 5101 + }, + { + "epoch": 0.54, + "learning_rate": 1.0521349173222549e-05, + "loss": 1.4078, + "step": 5102 + }, + { + "epoch": 0.54, + "learning_rate": 1.0517693866044312e-05, + "loss": 1.4026, + "step": 5103 + }, + { + "epoch": 0.54, + "learning_rate": 1.0514038489508396e-05, + "loss": 1.3098, + "step": 5104 + }, + { + "epoch": 0.54, + "learning_rate": 1.0510383044104533e-05, + "loss": 1.2886, + "step": 5105 + }, + { + "epoch": 0.54, + "learning_rate": 1.0506727530322454e-05, + "loss": 1.3114, + "step": 5106 + }, + { + "epoch": 0.54, + "learning_rate": 1.0503071948651908e-05, + "loss": 1.2823, + "step": 5107 + }, + { + "epoch": 0.54, + "learning_rate": 1.0499416299582643e-05, + "loss": 1.4654, + "step": 5108 + }, + { + "epoch": 0.54, + "learning_rate": 1.0495760583604431e-05, + "loss": 1.4043, + "step": 5109 + }, + { + "epoch": 0.54, + "learning_rate": 1.0492104801207035e-05, + "loss": 1.3113, + "step": 5110 + }, + { + "epoch": 0.54, + "learning_rate": 1.0488448952880243e-05, + "loss": 1.3285, + "step": 5111 + }, + { + "epoch": 0.54, + "learning_rate": 1.048479303911384e-05, + "loss": 1.3918, + "step": 5112 + }, + { + "epoch": 0.54, + "learning_rate": 1.0481137060397623e-05, + "loss": 1.346, + "step": 5113 + }, + { + "epoch": 0.54, + "learning_rate": 1.0477481017221407e-05, + "loss": 1.3777, + "step": 5114 + }, + { + "epoch": 0.54, + "learning_rate": 1.0473824910075003e-05, + "loss": 1.3494, + "step": 5115 + }, + { + "epoch": 0.54, + "learning_rate": 1.0470168739448232e-05, + "loss": 1.4173, + "step": 5116 + }, + { + "epoch": 0.54, + "learning_rate": 1.0466512505830932e-05, + "loss": 1.4313, + "step": 5117 + }, + { + "epoch": 0.54, + "learning_rate": 1.0462856209712944e-05, + "loss": 1.335, + "step": 5118 + }, + { + "epoch": 0.54, + "learning_rate": 1.0459199851584117e-05, + "loss": 1.37, + "step": 5119 + }, + { + "epoch": 0.54, + "learning_rate": 1.0455543431934307e-05, + "loss": 1.3504, + "step": 5120 + }, + { + "epoch": 0.54, + "learning_rate": 1.0451886951253381e-05, + "loss": 1.4148, + "step": 5121 + }, + { + "epoch": 0.54, + "learning_rate": 1.0448230410031218e-05, + "loss": 1.3974, + "step": 5122 + }, + { + "epoch": 0.54, + "learning_rate": 1.0444573808757694e-05, + "loss": 1.3644, + "step": 5123 + }, + { + "epoch": 0.54, + "learning_rate": 1.0440917147922705e-05, + "loss": 1.4024, + "step": 5124 + }, + { + "epoch": 0.54, + "learning_rate": 1.0437260428016143e-05, + "loss": 1.3925, + "step": 5125 + }, + { + "epoch": 0.54, + "learning_rate": 1.0433603649527923e-05, + "loss": 1.2907, + "step": 5126 + }, + { + "epoch": 0.54, + "learning_rate": 1.0429946812947953e-05, + "loss": 1.3453, + "step": 5127 + }, + { + "epoch": 0.54, + "learning_rate": 1.0426289918766157e-05, + "loss": 1.3856, + "step": 5128 + }, + { + "epoch": 0.54, + "learning_rate": 1.0422632967472465e-05, + "loss": 1.3309, + "step": 5129 + }, + { + "epoch": 0.54, + "learning_rate": 1.0418975959556819e-05, + "loss": 1.3757, + "step": 5130 + }, + { + "epoch": 0.54, + "learning_rate": 1.0415318895509152e-05, + "loss": 1.406, + "step": 5131 + }, + { + "epoch": 0.54, + "learning_rate": 1.041166177581943e-05, + "loss": 1.3265, + "step": 5132 + }, + { + "epoch": 0.54, + "learning_rate": 1.0408004600977606e-05, + "loss": 1.3377, + "step": 5133 + }, + { + "epoch": 0.54, + "learning_rate": 1.040434737147365e-05, + "loss": 1.3647, + "step": 5134 + }, + { + "epoch": 0.54, + "learning_rate": 1.0400690087797531e-05, + "loss": 1.3262, + "step": 5135 + }, + { + "epoch": 0.54, + "learning_rate": 1.039703275043924e-05, + "loss": 1.3924, + "step": 5136 + }, + { + "epoch": 0.54, + "learning_rate": 1.039337535988876e-05, + "loss": 1.3018, + "step": 5137 + }, + { + "epoch": 0.54, + "learning_rate": 1.038971791663609e-05, + "loss": 1.385, + "step": 5138 + }, + { + "epoch": 0.54, + "learning_rate": 1.0386060421171232e-05, + "loss": 1.3435, + "step": 5139 + }, + { + "epoch": 0.54, + "learning_rate": 1.0382402873984197e-05, + "loss": 1.4023, + "step": 5140 + }, + { + "epoch": 0.54, + "learning_rate": 1.0378745275565003e-05, + "loss": 1.369, + "step": 5141 + }, + { + "epoch": 0.54, + "learning_rate": 1.0375087626403675e-05, + "loss": 1.3199, + "step": 5142 + }, + { + "epoch": 0.54, + "learning_rate": 1.037142992699024e-05, + "loss": 1.4247, + "step": 5143 + }, + { + "epoch": 0.54, + "learning_rate": 1.0367772177814736e-05, + "loss": 1.4015, + "step": 5144 + }, + { + "epoch": 0.54, + "learning_rate": 1.0364114379367217e-05, + "loss": 1.3519, + "step": 5145 + }, + { + "epoch": 0.54, + "learning_rate": 1.0360456532137722e-05, + "loss": 1.3478, + "step": 5146 + }, + { + "epoch": 0.54, + "learning_rate": 1.0356798636616314e-05, + "loss": 1.4876, + "step": 5147 + }, + { + "epoch": 0.54, + "learning_rate": 1.0353140693293056e-05, + "loss": 1.6481, + "step": 5148 + }, + { + "epoch": 0.54, + "learning_rate": 1.034948270265802e-05, + "loss": 1.3851, + "step": 5149 + }, + { + "epoch": 0.54, + "learning_rate": 1.0345824665201281e-05, + "loss": 1.4037, + "step": 5150 + }, + { + "epoch": 0.54, + "learning_rate": 1.0342166581412923e-05, + "loss": 1.3138, + "step": 5151 + }, + { + "epoch": 0.54, + "learning_rate": 1.0338508451783032e-05, + "loss": 1.3536, + "step": 5152 + }, + { + "epoch": 0.54, + "learning_rate": 1.0334850276801712e-05, + "loss": 1.3244, + "step": 5153 + }, + { + "epoch": 0.54, + "learning_rate": 1.0331192056959052e-05, + "loss": 1.3677, + "step": 5154 + }, + { + "epoch": 0.54, + "learning_rate": 1.032753379274517e-05, + "loss": 1.3439, + "step": 5155 + }, + { + "epoch": 0.54, + "learning_rate": 1.0323875484650171e-05, + "loss": 1.365, + "step": 5156 + }, + { + "epoch": 0.54, + "learning_rate": 1.0320217133164186e-05, + "loss": 1.3838, + "step": 5157 + }, + { + "epoch": 0.54, + "learning_rate": 1.0316558738777328e-05, + "loss": 1.3312, + "step": 5158 + }, + { + "epoch": 0.54, + "learning_rate": 1.0312900301979733e-05, + "loss": 1.369, + "step": 5159 + }, + { + "epoch": 0.54, + "learning_rate": 1.030924182326154e-05, + "loss": 1.2712, + "step": 5160 + }, + { + "epoch": 0.54, + "learning_rate": 1.0305583303112887e-05, + "loss": 1.3141, + "step": 5161 + }, + { + "epoch": 0.54, + "learning_rate": 1.030192474202392e-05, + "loss": 1.3708, + "step": 5162 + }, + { + "epoch": 0.54, + "learning_rate": 1.0298266140484798e-05, + "loss": 1.3724, + "step": 5163 + }, + { + "epoch": 0.54, + "learning_rate": 1.0294607498985678e-05, + "loss": 1.3208, + "step": 5164 + }, + { + "epoch": 0.54, + "learning_rate": 1.0290948818016722e-05, + "loss": 1.3379, + "step": 5165 + }, + { + "epoch": 0.54, + "learning_rate": 1.0287290098068099e-05, + "loss": 1.3236, + "step": 5166 + }, + { + "epoch": 0.54, + "learning_rate": 1.0283631339629982e-05, + "loss": 1.3437, + "step": 5167 + }, + { + "epoch": 0.54, + "learning_rate": 1.0279972543192561e-05, + "loss": 1.3381, + "step": 5168 + }, + { + "epoch": 0.54, + "learning_rate": 1.0276313709246007e-05, + "loss": 1.4287, + "step": 5169 + }, + { + "epoch": 0.54, + "learning_rate": 1.0272654838280515e-05, + "loss": 1.3587, + "step": 5170 + }, + { + "epoch": 0.54, + "learning_rate": 1.0268995930786283e-05, + "loss": 1.2982, + "step": 5171 + }, + { + "epoch": 0.54, + "learning_rate": 1.0265336987253509e-05, + "loss": 1.3416, + "step": 5172 + }, + { + "epoch": 0.54, + "learning_rate": 1.0261678008172393e-05, + "loss": 1.3827, + "step": 5173 + }, + { + "epoch": 0.54, + "learning_rate": 1.025801899403315e-05, + "loss": 1.3293, + "step": 5174 + }, + { + "epoch": 0.54, + "eval_loss": 1.4264723062515259, + "eval_runtime": 77.4376, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 5174 + }, + { + "epoch": 0.54, + "learning_rate": 1.0254359945325987e-05, + "loss": 1.3811, + "step": 5175 + }, + { + "epoch": 0.54, + "learning_rate": 1.0250700862541135e-05, + "loss": 1.3423, + "step": 5176 + }, + { + "epoch": 0.54, + "learning_rate": 1.02470417461688e-05, + "loss": 1.3641, + "step": 5177 + }, + { + "epoch": 0.54, + "learning_rate": 1.0243382596699226e-05, + "loss": 1.3211, + "step": 5178 + }, + { + "epoch": 0.54, + "learning_rate": 1.023972341462263e-05, + "loss": 1.4008, + "step": 5179 + }, + { + "epoch": 0.54, + "learning_rate": 1.0236064200429263e-05, + "loss": 1.404, + "step": 5180 + }, + { + "epoch": 0.54, + "learning_rate": 1.0232404954609353e-05, + "loss": 1.3359, + "step": 5181 + }, + { + "epoch": 0.54, + "learning_rate": 1.0228745677653155e-05, + "loss": 1.4069, + "step": 5182 + }, + { + "epoch": 0.54, + "learning_rate": 1.0225086370050914e-05, + "loss": 1.3343, + "step": 5183 + }, + { + "epoch": 0.54, + "learning_rate": 1.0221427032292881e-05, + "loss": 1.3109, + "step": 5184 + }, + { + "epoch": 0.54, + "learning_rate": 1.0217767664869312e-05, + "loss": 1.3611, + "step": 5185 + }, + { + "epoch": 0.54, + "learning_rate": 1.0214108268270476e-05, + "loss": 1.4072, + "step": 5186 + }, + { + "epoch": 0.54, + "learning_rate": 1.0210448842986631e-05, + "loss": 1.3602, + "step": 5187 + }, + { + "epoch": 0.54, + "learning_rate": 1.0206789389508047e-05, + "loss": 1.413, + "step": 5188 + }, + { + "epoch": 0.54, + "learning_rate": 1.0203129908325e-05, + "loss": 1.3209, + "step": 5189 + }, + { + "epoch": 0.54, + "learning_rate": 1.0199470399927764e-05, + "loss": 1.3714, + "step": 5190 + }, + { + "epoch": 0.54, + "learning_rate": 1.0195810864806623e-05, + "loss": 1.3556, + "step": 5191 + }, + { + "epoch": 0.54, + "learning_rate": 1.0192151303451852e-05, + "loss": 1.4116, + "step": 5192 + }, + { + "epoch": 0.54, + "learning_rate": 1.0188491716353745e-05, + "loss": 1.4102, + "step": 5193 + }, + { + "epoch": 0.54, + "learning_rate": 1.0184832104002592e-05, + "loss": 1.4849, + "step": 5194 + }, + { + "epoch": 0.54, + "learning_rate": 1.0181172466888689e-05, + "loss": 1.5395, + "step": 5195 + }, + { + "epoch": 0.54, + "learning_rate": 1.0177512805502325e-05, + "loss": 1.3627, + "step": 5196 + }, + { + "epoch": 0.54, + "learning_rate": 1.017385312033381e-05, + "loss": 1.4152, + "step": 5197 + }, + { + "epoch": 0.55, + "learning_rate": 1.0170193411873442e-05, + "loss": 1.3641, + "step": 5198 + }, + { + "epoch": 0.55, + "learning_rate": 1.0166533680611533e-05, + "loss": 1.3074, + "step": 5199 + }, + { + "epoch": 0.55, + "learning_rate": 1.0162873927038386e-05, + "loss": 1.35, + "step": 5200 + }, + { + "epoch": 0.55, + "learning_rate": 1.015921415164432e-05, + "loss": 1.3551, + "step": 5201 + }, + { + "epoch": 0.55, + "learning_rate": 1.0155554354919643e-05, + "loss": 1.3421, + "step": 5202 + }, + { + "epoch": 0.55, + "learning_rate": 1.0151894537354687e-05, + "loss": 1.4132, + "step": 5203 + }, + { + "epoch": 0.55, + "learning_rate": 1.0148234699439764e-05, + "loss": 1.351, + "step": 5204 + }, + { + "epoch": 0.55, + "learning_rate": 1.0144574841665198e-05, + "loss": 1.3745, + "step": 5205 + }, + { + "epoch": 0.55, + "learning_rate": 1.0140914964521316e-05, + "loss": 1.3151, + "step": 5206 + }, + { + "epoch": 0.55, + "learning_rate": 1.0137255068498456e-05, + "loss": 1.4903, + "step": 5207 + }, + { + "epoch": 0.55, + "learning_rate": 1.0133595154086937e-05, + "loss": 1.3945, + "step": 5208 + }, + { + "epoch": 0.55, + "learning_rate": 1.0129935221777104e-05, + "loss": 1.3924, + "step": 5209 + }, + { + "epoch": 0.55, + "learning_rate": 1.0126275272059286e-05, + "loss": 1.4191, + "step": 5210 + }, + { + "epoch": 0.55, + "learning_rate": 1.012261530542383e-05, + "loss": 1.3408, + "step": 5211 + }, + { + "epoch": 0.55, + "learning_rate": 1.0118955322361071e-05, + "loss": 1.3582, + "step": 5212 + }, + { + "epoch": 0.55, + "learning_rate": 1.0115295323361354e-05, + "loss": 1.3703, + "step": 5213 + }, + { + "epoch": 0.55, + "learning_rate": 1.011163530891503e-05, + "loss": 1.4181, + "step": 5214 + }, + { + "epoch": 0.55, + "learning_rate": 1.0107975279512442e-05, + "loss": 1.5019, + "step": 5215 + }, + { + "epoch": 0.55, + "learning_rate": 1.010431523564394e-05, + "loss": 1.3151, + "step": 5216 + }, + { + "epoch": 0.55, + "learning_rate": 1.0100655177799874e-05, + "loss": 1.4036, + "step": 5217 + }, + { + "epoch": 0.55, + "learning_rate": 1.0096995106470606e-05, + "loss": 1.3584, + "step": 5218 + }, + { + "epoch": 0.55, + "learning_rate": 1.0093335022146482e-05, + "loss": 1.3618, + "step": 5219 + }, + { + "epoch": 0.55, + "learning_rate": 1.0089674925317865e-05, + "loss": 1.3295, + "step": 5220 + }, + { + "epoch": 0.55, + "learning_rate": 1.0086014816475108e-05, + "loss": 1.3968, + "step": 5221 + }, + { + "epoch": 0.55, + "learning_rate": 1.0082354696108586e-05, + "loss": 1.2847, + "step": 5222 + }, + { + "epoch": 0.55, + "learning_rate": 1.007869456470864e-05, + "loss": 1.4461, + "step": 5223 + }, + { + "epoch": 0.55, + "learning_rate": 1.007503442276565e-05, + "loss": 1.3813, + "step": 5224 + }, + { + "epoch": 0.55, + "learning_rate": 1.007137427076997e-05, + "loss": 1.3833, + "step": 5225 + }, + { + "epoch": 0.55, + "learning_rate": 1.006771410921198e-05, + "loss": 1.4024, + "step": 5226 + }, + { + "epoch": 0.55, + "learning_rate": 1.0064053938582032e-05, + "loss": 1.3357, + "step": 5227 + }, + { + "epoch": 0.55, + "learning_rate": 1.0060393759370506e-05, + "loss": 1.35, + "step": 5228 + }, + { + "epoch": 0.55, + "learning_rate": 1.0056733572067765e-05, + "loss": 1.3512, + "step": 5229 + }, + { + "epoch": 0.55, + "learning_rate": 1.0053073377164186e-05, + "loss": 1.3852, + "step": 5230 + }, + { + "epoch": 0.55, + "learning_rate": 1.0049413175150135e-05, + "loss": 1.3502, + "step": 5231 + }, + { + "epoch": 0.55, + "learning_rate": 1.004575296651599e-05, + "loss": 1.4637, + "step": 5232 + }, + { + "epoch": 0.55, + "learning_rate": 1.0042092751752123e-05, + "loss": 1.3877, + "step": 5233 + }, + { + "epoch": 0.55, + "learning_rate": 1.0038432531348909e-05, + "loss": 1.3804, + "step": 5234 + }, + { + "epoch": 0.55, + "learning_rate": 1.0034772305796723e-05, + "loss": 1.3613, + "step": 5235 + }, + { + "epoch": 0.55, + "learning_rate": 1.003111207558594e-05, + "loss": 1.3218, + "step": 5236 + }, + { + "epoch": 0.55, + "learning_rate": 1.0027451841206944e-05, + "loss": 1.3554, + "step": 5237 + }, + { + "epoch": 0.55, + "learning_rate": 1.0023791603150099e-05, + "loss": 1.372, + "step": 5238 + }, + { + "epoch": 0.55, + "learning_rate": 1.0020131361905793e-05, + "loss": 1.3544, + "step": 5239 + }, + { + "epoch": 0.55, + "learning_rate": 1.0016471117964404e-05, + "loss": 1.3472, + "step": 5240 + }, + { + "epoch": 0.55, + "learning_rate": 1.001281087181631e-05, + "loss": 1.4247, + "step": 5241 + }, + { + "epoch": 0.55, + "learning_rate": 1.0009150623951883e-05, + "loss": 1.2685, + "step": 5242 + }, + { + "epoch": 0.55, + "learning_rate": 1.000549037486151e-05, + "loss": 1.4036, + "step": 5243 + }, + { + "epoch": 0.55, + "learning_rate": 1.0001830125035565e-05, + "loss": 1.3602, + "step": 5244 + }, + { + "epoch": 0.55, + "learning_rate": 9.998169874964437e-06, + "loss": 1.3784, + "step": 5245 + }, + { + "epoch": 0.55, + "learning_rate": 9.994509625138496e-06, + "loss": 1.3389, + "step": 5246 + }, + { + "epoch": 0.55, + "learning_rate": 9.990849376048119e-06, + "loss": 1.4561, + "step": 5247 + }, + { + "epoch": 0.55, + "learning_rate": 9.987189128183695e-06, + "loss": 1.3876, + "step": 5248 + }, + { + "epoch": 0.55, + "learning_rate": 9.9835288820356e-06, + "loss": 1.3362, + "step": 5249 + }, + { + "epoch": 0.55, + "learning_rate": 9.97986863809421e-06, + "loss": 1.3449, + "step": 5250 + }, + { + "epoch": 0.55, + "learning_rate": 9.9762083968499e-06, + "loss": 1.3521, + "step": 5251 + }, + { + "epoch": 0.55, + "learning_rate": 9.972548158793061e-06, + "loss": 1.4452, + "step": 5252 + }, + { + "epoch": 0.55, + "learning_rate": 9.968887924414062e-06, + "loss": 1.4126, + "step": 5253 + }, + { + "epoch": 0.55, + "learning_rate": 9.965227694203282e-06, + "loss": 1.3054, + "step": 5254 + }, + { + "epoch": 0.55, + "learning_rate": 9.961567468651093e-06, + "loss": 1.3771, + "step": 5255 + }, + { + "epoch": 0.55, + "learning_rate": 9.957907248247878e-06, + "loss": 1.3566, + "step": 5256 + }, + { + "epoch": 0.55, + "learning_rate": 9.954247033484014e-06, + "loss": 1.4765, + "step": 5257 + }, + { + "epoch": 0.55, + "learning_rate": 9.950586824849865e-06, + "loss": 1.4749, + "step": 5258 + }, + { + "epoch": 0.55, + "learning_rate": 9.946926622835815e-06, + "loss": 1.3679, + "step": 5259 + }, + { + "epoch": 0.55, + "learning_rate": 9.943266427932238e-06, + "loss": 1.2671, + "step": 5260 + }, + { + "epoch": 0.55, + "learning_rate": 9.9396062406295e-06, + "loss": 1.3485, + "step": 5261 + }, + { + "epoch": 0.55, + "learning_rate": 9.935946061417968e-06, + "loss": 1.3136, + "step": 5262 + }, + { + "epoch": 0.55, + "learning_rate": 9.932285890788024e-06, + "loss": 1.3954, + "step": 5263 + }, + { + "epoch": 0.55, + "learning_rate": 9.928625729230031e-06, + "loss": 1.428, + "step": 5264 + }, + { + "epoch": 0.55, + "learning_rate": 9.924965577234356e-06, + "loss": 1.4144, + "step": 5265 + }, + { + "epoch": 0.55, + "learning_rate": 9.92130543529136e-06, + "loss": 1.3361, + "step": 5266 + }, + { + "epoch": 0.55, + "learning_rate": 9.91764530389142e-06, + "loss": 1.4503, + "step": 5267 + }, + { + "epoch": 0.55, + "learning_rate": 9.913985183524893e-06, + "loss": 1.3431, + "step": 5268 + }, + { + "epoch": 0.55, + "learning_rate": 9.91032507468214e-06, + "loss": 1.3206, + "step": 5269 + }, + { + "epoch": 0.55, + "learning_rate": 9.906664977853518e-06, + "loss": 1.4568, + "step": 5270 + }, + { + "epoch": 0.55, + "learning_rate": 9.903004893529397e-06, + "loss": 1.3591, + "step": 5271 + }, + { + "epoch": 0.55, + "learning_rate": 9.899344822200127e-06, + "loss": 1.3382, + "step": 5272 + }, + { + "epoch": 0.55, + "learning_rate": 9.895684764356066e-06, + "loss": 1.3008, + "step": 5273 + }, + { + "epoch": 0.55, + "learning_rate": 9.89202472048756e-06, + "loss": 1.316, + "step": 5274 + }, + { + "epoch": 0.55, + "learning_rate": 9.888364691084971e-06, + "loss": 1.4246, + "step": 5275 + }, + { + "epoch": 0.55, + "learning_rate": 9.88470467663865e-06, + "loss": 1.3615, + "step": 5276 + }, + { + "epoch": 0.55, + "learning_rate": 9.881044677638934e-06, + "loss": 1.3418, + "step": 5277 + }, + { + "epoch": 0.55, + "learning_rate": 9.877384694576172e-06, + "loss": 1.249, + "step": 5278 + }, + { + "epoch": 0.55, + "learning_rate": 9.873724727940715e-06, + "loss": 1.2779, + "step": 5279 + }, + { + "epoch": 0.55, + "learning_rate": 9.870064778222903e-06, + "loss": 1.3529, + "step": 5280 + }, + { + "epoch": 0.55, + "learning_rate": 9.866404845913065e-06, + "loss": 1.3204, + "step": 5281 + }, + { + "epoch": 0.55, + "learning_rate": 9.862744931501548e-06, + "loss": 1.3537, + "step": 5282 + }, + { + "epoch": 0.55, + "learning_rate": 9.859085035478687e-06, + "loss": 1.3681, + "step": 5283 + }, + { + "epoch": 0.55, + "learning_rate": 9.855425158334809e-06, + "loss": 1.3983, + "step": 5284 + }, + { + "epoch": 0.55, + "learning_rate": 9.851765300560238e-06, + "loss": 1.401, + "step": 5285 + }, + { + "epoch": 0.55, + "learning_rate": 9.848105462645315e-06, + "loss": 1.3073, + "step": 5286 + }, + { + "epoch": 0.55, + "learning_rate": 9.844445645080358e-06, + "loss": 1.3162, + "step": 5287 + }, + { + "epoch": 0.55, + "learning_rate": 9.840785848355685e-06, + "loss": 1.3345, + "step": 5288 + }, + { + "epoch": 0.55, + "learning_rate": 9.837126072961616e-06, + "loss": 1.4241, + "step": 5289 + }, + { + "epoch": 0.55, + "learning_rate": 9.83346631938847e-06, + "loss": 1.3339, + "step": 5290 + }, + { + "epoch": 0.55, + "learning_rate": 9.829806588126561e-06, + "loss": 1.3507, + "step": 5291 + }, + { + "epoch": 0.55, + "learning_rate": 9.826146879666196e-06, + "loss": 1.2806, + "step": 5292 + }, + { + "epoch": 0.56, + "learning_rate": 9.822487194497675e-06, + "loss": 1.3952, + "step": 5293 + }, + { + "epoch": 0.56, + "learning_rate": 9.818827533111314e-06, + "loss": 1.3319, + "step": 5294 + }, + { + "epoch": 0.56, + "learning_rate": 9.81516789599741e-06, + "loss": 1.351, + "step": 5295 + }, + { + "epoch": 0.56, + "learning_rate": 9.811508283646258e-06, + "loss": 1.4076, + "step": 5296 + }, + { + "epoch": 0.56, + "learning_rate": 9.80784869654815e-06, + "loss": 1.3271, + "step": 5297 + }, + { + "epoch": 0.56, + "learning_rate": 9.80418913519338e-06, + "loss": 1.4059, + "step": 5298 + }, + { + "epoch": 0.56, + "learning_rate": 9.80052960007224e-06, + "loss": 1.4146, + "step": 5299 + }, + { + "epoch": 0.56, + "learning_rate": 9.796870091675005e-06, + "loss": 1.3454, + "step": 5300 + }, + { + "epoch": 0.56, + "learning_rate": 9.793210610491953e-06, + "loss": 1.4376, + "step": 5301 + }, + { + "epoch": 0.56, + "learning_rate": 9.789551157013372e-06, + "loss": 1.3437, + "step": 5302 + }, + { + "epoch": 0.56, + "learning_rate": 9.78589173172953e-06, + "loss": 1.3073, + "step": 5303 + }, + { + "epoch": 0.56, + "learning_rate": 9.782232335130688e-06, + "loss": 1.2989, + "step": 5304 + }, + { + "epoch": 0.56, + "learning_rate": 9.778572967707122e-06, + "loss": 1.4028, + "step": 5305 + }, + { + "epoch": 0.56, + "learning_rate": 9.77491362994909e-06, + "loss": 1.3096, + "step": 5306 + }, + { + "epoch": 0.56, + "learning_rate": 9.77125432234685e-06, + "loss": 1.3719, + "step": 5307 + }, + { + "epoch": 0.56, + "learning_rate": 9.767595045390647e-06, + "loss": 1.3271, + "step": 5308 + }, + { + "epoch": 0.56, + "learning_rate": 9.763935799570739e-06, + "loss": 1.3693, + "step": 5309 + }, + { + "epoch": 0.56, + "learning_rate": 9.760276585377371e-06, + "loss": 1.3586, + "step": 5310 + }, + { + "epoch": 0.56, + "learning_rate": 9.756617403300781e-06, + "loss": 1.3423, + "step": 5311 + }, + { + "epoch": 0.56, + "learning_rate": 9.7529582538312e-06, + "loss": 1.388, + "step": 5312 + }, + { + "epoch": 0.56, + "learning_rate": 9.74929913745887e-06, + "loss": 1.3594, + "step": 5313 + }, + { + "epoch": 0.56, + "learning_rate": 9.745640054674015e-06, + "loss": 1.2831, + "step": 5314 + }, + { + "epoch": 0.56, + "learning_rate": 9.741981005966856e-06, + "loss": 1.4207, + "step": 5315 + }, + { + "epoch": 0.56, + "learning_rate": 9.738321991827609e-06, + "loss": 1.2807, + "step": 5316 + }, + { + "epoch": 0.56, + "learning_rate": 9.734663012746493e-06, + "loss": 1.3396, + "step": 5317 + }, + { + "epoch": 0.56, + "learning_rate": 9.731004069213722e-06, + "loss": 1.3666, + "step": 5318 + }, + { + "epoch": 0.56, + "learning_rate": 9.72734516171949e-06, + "loss": 1.3466, + "step": 5319 + }, + { + "epoch": 0.56, + "learning_rate": 9.723686290753995e-06, + "loss": 1.4478, + "step": 5320 + }, + { + "epoch": 0.56, + "learning_rate": 9.720027456807442e-06, + "loss": 1.316, + "step": 5321 + }, + { + "epoch": 0.56, + "learning_rate": 9.71636866037002e-06, + "loss": 1.3762, + "step": 5322 + }, + { + "epoch": 0.56, + "learning_rate": 9.712709901931906e-06, + "loss": 1.4156, + "step": 5323 + }, + { + "epoch": 0.56, + "learning_rate": 9.70905118198328e-06, + "loss": 1.2452, + "step": 5324 + }, + { + "epoch": 0.56, + "learning_rate": 9.705392501014325e-06, + "loss": 1.3771, + "step": 5325 + }, + { + "epoch": 0.56, + "learning_rate": 9.701733859515205e-06, + "loss": 1.3433, + "step": 5326 + }, + { + "epoch": 0.56, + "learning_rate": 9.698075257976079e-06, + "loss": 1.3702, + "step": 5327 + }, + { + "epoch": 0.56, + "learning_rate": 9.694416696887115e-06, + "loss": 1.295, + "step": 5328 + }, + { + "epoch": 0.56, + "learning_rate": 9.690758176738463e-06, + "loss": 1.3462, + "step": 5329 + }, + { + "epoch": 0.56, + "learning_rate": 9.68709969802027e-06, + "loss": 1.5304, + "step": 5330 + }, + { + "epoch": 0.56, + "learning_rate": 9.683441261222672e-06, + "loss": 1.3518, + "step": 5331 + }, + { + "epoch": 0.56, + "learning_rate": 9.679782866835816e-06, + "loss": 1.3778, + "step": 5332 + }, + { + "epoch": 0.56, + "learning_rate": 9.67612451534983e-06, + "loss": 1.3731, + "step": 5333 + }, + { + "epoch": 0.56, + "learning_rate": 9.672466207254837e-06, + "loss": 1.3315, + "step": 5334 + }, + { + "epoch": 0.56, + "learning_rate": 9.66880794304095e-06, + "loss": 1.3105, + "step": 5335 + }, + { + "epoch": 0.56, + "learning_rate": 9.665149723198293e-06, + "loss": 1.3903, + "step": 5336 + }, + { + "epoch": 0.56, + "learning_rate": 9.661491548216972e-06, + "loss": 1.3554, + "step": 5337 + }, + { + "epoch": 0.56, + "learning_rate": 9.657833418587084e-06, + "loss": 1.3231, + "step": 5338 + }, + { + "epoch": 0.56, + "learning_rate": 9.65417533479872e-06, + "loss": 1.352, + "step": 5339 + }, + { + "epoch": 0.56, + "learning_rate": 9.650517297341983e-06, + "loss": 1.3957, + "step": 5340 + }, + { + "epoch": 0.56, + "learning_rate": 9.646859306706948e-06, + "loss": 1.3938, + "step": 5341 + }, + { + "epoch": 0.56, + "learning_rate": 9.643201363383693e-06, + "loss": 1.3038, + "step": 5342 + }, + { + "epoch": 0.56, + "learning_rate": 9.63954346786228e-06, + "loss": 1.2973, + "step": 5343 + }, + { + "epoch": 0.56, + "learning_rate": 9.635885620632786e-06, + "loss": 1.379, + "step": 5344 + }, + { + "epoch": 0.56, + "learning_rate": 9.632227822185266e-06, + "loss": 1.5377, + "step": 5345 + }, + { + "epoch": 0.56, + "learning_rate": 9.628570073009767e-06, + "loss": 1.4573, + "step": 5346 + }, + { + "epoch": 0.56, + "learning_rate": 9.624912373596329e-06, + "loss": 1.3394, + "step": 5347 + }, + { + "epoch": 0.56, + "learning_rate": 9.621254724434999e-06, + "loss": 1.4157, + "step": 5348 + }, + { + "epoch": 0.56, + "learning_rate": 9.617597126015808e-06, + "loss": 1.3526, + "step": 5349 + }, + { + "epoch": 0.56, + "learning_rate": 9.61393957882877e-06, + "loss": 1.3795, + "step": 5350 + }, + { + "epoch": 0.56, + "learning_rate": 9.610282083363913e-06, + "loss": 1.3765, + "step": 5351 + }, + { + "epoch": 0.56, + "learning_rate": 9.606624640111243e-06, + "loss": 1.3512, + "step": 5352 + }, + { + "epoch": 0.56, + "learning_rate": 9.602967249560766e-06, + "loss": 1.3298, + "step": 5353 + }, + { + "epoch": 0.56, + "learning_rate": 9.599309912202469e-06, + "loss": 1.3093, + "step": 5354 + }, + { + "epoch": 0.56, + "learning_rate": 9.595652628526354e-06, + "loss": 1.3353, + "step": 5355 + }, + { + "epoch": 0.56, + "learning_rate": 9.591995399022397e-06, + "loss": 1.3081, + "step": 5356 + }, + { + "epoch": 0.56, + "learning_rate": 9.588338224180576e-06, + "loss": 1.343, + "step": 5357 + }, + { + "epoch": 0.56, + "learning_rate": 9.584681104490848e-06, + "loss": 1.3275, + "step": 5358 + }, + { + "epoch": 0.56, + "learning_rate": 9.581024040443185e-06, + "loss": 1.3399, + "step": 5359 + }, + { + "epoch": 0.56, + "learning_rate": 9.577367032527538e-06, + "loss": 1.3181, + "step": 5360 + }, + { + "epoch": 0.56, + "learning_rate": 9.573710081233846e-06, + "loss": 1.3531, + "step": 5361 + }, + { + "epoch": 0.56, + "learning_rate": 9.570053187052049e-06, + "loss": 1.4056, + "step": 5362 + }, + { + "epoch": 0.56, + "learning_rate": 9.566396350472079e-06, + "loss": 1.3303, + "step": 5363 + }, + { + "epoch": 0.56, + "learning_rate": 9.56273957198386e-06, + "loss": 1.3506, + "step": 5364 + }, + { + "epoch": 0.56, + "learning_rate": 9.559082852077302e-06, + "loss": 1.4588, + "step": 5365 + }, + { + "epoch": 0.56, + "learning_rate": 9.555426191242307e-06, + "loss": 1.3434, + "step": 5366 + }, + { + "epoch": 0.56, + "learning_rate": 9.551769589968784e-06, + "loss": 1.3508, + "step": 5367 + }, + { + "epoch": 0.56, + "learning_rate": 9.548113048746622e-06, + "loss": 1.3701, + "step": 5368 + }, + { + "epoch": 0.56, + "learning_rate": 9.544456568065698e-06, + "loss": 1.3664, + "step": 5369 + }, + { + "epoch": 0.56, + "learning_rate": 9.540800148415885e-06, + "loss": 1.6697, + "step": 5370 + }, + { + "epoch": 0.56, + "learning_rate": 9.537143790287057e-06, + "loss": 1.5298, + "step": 5371 + }, + { + "epoch": 0.56, + "learning_rate": 9.533487494169073e-06, + "loss": 1.3884, + "step": 5372 + }, + { + "epoch": 0.56, + "learning_rate": 9.52983126055177e-06, + "loss": 1.403, + "step": 5373 + }, + { + "epoch": 0.56, + "eval_loss": 1.4240995645523071, + "eval_runtime": 77.4615, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 5373 + }, + { + "epoch": 0.56, + "learning_rate": 9.526175089925e-06, + "loss": 1.3141, + "step": 5374 + }, + { + "epoch": 0.56, + "learning_rate": 9.522518982778596e-06, + "loss": 1.3733, + "step": 5375 + }, + { + "epoch": 0.56, + "learning_rate": 9.51886293960238e-06, + "loss": 1.3095, + "step": 5376 + }, + { + "epoch": 0.56, + "learning_rate": 9.515206960886162e-06, + "loss": 1.3713, + "step": 5377 + }, + { + "epoch": 0.56, + "learning_rate": 9.51155104711976e-06, + "loss": 1.3585, + "step": 5378 + }, + { + "epoch": 0.56, + "learning_rate": 9.507895198792967e-06, + "loss": 1.3473, + "step": 5379 + }, + { + "epoch": 0.56, + "learning_rate": 9.504239416395576e-06, + "loss": 1.3282, + "step": 5380 + }, + { + "epoch": 0.56, + "learning_rate": 9.500583700417357e-06, + "loss": 1.3655, + "step": 5381 + }, + { + "epoch": 0.56, + "learning_rate": 9.496928051348095e-06, + "loss": 1.4512, + "step": 5382 + }, + { + "epoch": 0.56, + "learning_rate": 9.49327246967755e-06, + "loss": 1.4071, + "step": 5383 + }, + { + "epoch": 0.56, + "learning_rate": 9.489616955895472e-06, + "loss": 1.3703, + "step": 5384 + }, + { + "epoch": 0.56, + "learning_rate": 9.485961510491604e-06, + "loss": 1.3358, + "step": 5385 + }, + { + "epoch": 0.56, + "learning_rate": 9.482306133955691e-06, + "loss": 1.3505, + "step": 5386 + }, + { + "epoch": 0.56, + "learning_rate": 9.478650826777457e-06, + "loss": 1.2578, + "step": 5387 + }, + { + "epoch": 0.57, + "learning_rate": 9.474995589446612e-06, + "loss": 1.4298, + "step": 5388 + }, + { + "epoch": 0.57, + "learning_rate": 9.471340422452864e-06, + "loss": 1.4044, + "step": 5389 + }, + { + "epoch": 0.57, + "learning_rate": 9.467685326285922e-06, + "loss": 1.3524, + "step": 5390 + }, + { + "epoch": 0.57, + "learning_rate": 9.46403030143547e-06, + "loss": 1.3017, + "step": 5391 + }, + { + "epoch": 0.57, + "learning_rate": 9.460375348391185e-06, + "loss": 1.3361, + "step": 5392 + }, + { + "epoch": 0.57, + "learning_rate": 9.456720467642733e-06, + "loss": 1.3182, + "step": 5393 + }, + { + "epoch": 0.57, + "learning_rate": 9.453065659679785e-06, + "loss": 1.3869, + "step": 5394 + }, + { + "epoch": 0.57, + "learning_rate": 9.449410924991986e-06, + "loss": 1.3161, + "step": 5395 + }, + { + "epoch": 0.57, + "learning_rate": 9.44575626406897e-06, + "loss": 1.3, + "step": 5396 + }, + { + "epoch": 0.57, + "learning_rate": 9.442101677400378e-06, + "loss": 1.5103, + "step": 5397 + }, + { + "epoch": 0.57, + "learning_rate": 9.438447165475828e-06, + "loss": 1.3511, + "step": 5398 + }, + { + "epoch": 0.57, + "learning_rate": 9.43479272878493e-06, + "loss": 1.3461, + "step": 5399 + }, + { + "epoch": 0.57, + "learning_rate": 9.431138367817277e-06, + "loss": 1.2657, + "step": 5400 + }, + { + "epoch": 0.57, + "learning_rate": 9.427484083062472e-06, + "loss": 1.3736, + "step": 5401 + }, + { + "epoch": 0.57, + "learning_rate": 9.423829875010089e-06, + "loss": 1.3476, + "step": 5402 + }, + { + "epoch": 0.57, + "learning_rate": 9.4201757441497e-06, + "loss": 1.3495, + "step": 5403 + }, + { + "epoch": 0.57, + "learning_rate": 9.416521690970857e-06, + "loss": 1.387, + "step": 5404 + }, + { + "epoch": 0.57, + "learning_rate": 9.41286771596312e-06, + "loss": 1.2829, + "step": 5405 + }, + { + "epoch": 0.57, + "learning_rate": 9.409213819616022e-06, + "loss": 1.3544, + "step": 5406 + }, + { + "epoch": 0.57, + "learning_rate": 9.405560002419098e-06, + "loss": 1.3202, + "step": 5407 + }, + { + "epoch": 0.57, + "learning_rate": 9.40190626486185e-06, + "loss": 1.3034, + "step": 5408 + }, + { + "epoch": 0.57, + "learning_rate": 9.398252607433801e-06, + "loss": 1.3223, + "step": 5409 + }, + { + "epoch": 0.57, + "learning_rate": 9.394599030624443e-06, + "loss": 1.3327, + "step": 5410 + }, + { + "epoch": 0.57, + "learning_rate": 9.390945534923258e-06, + "loss": 1.3248, + "step": 5411 + }, + { + "epoch": 0.57, + "learning_rate": 9.387292120819716e-06, + "loss": 1.3084, + "step": 5412 + }, + { + "epoch": 0.57, + "learning_rate": 9.383638788803291e-06, + "loss": 1.344, + "step": 5413 + }, + { + "epoch": 0.57, + "learning_rate": 9.379985539363436e-06, + "loss": 1.3354, + "step": 5414 + }, + { + "epoch": 0.57, + "learning_rate": 9.376332372989586e-06, + "loss": 1.3291, + "step": 5415 + }, + { + "epoch": 0.57, + "learning_rate": 9.372679290171167e-06, + "loss": 1.3468, + "step": 5416 + }, + { + "epoch": 0.57, + "learning_rate": 9.36902629139761e-06, + "loss": 1.3481, + "step": 5417 + }, + { + "epoch": 0.57, + "learning_rate": 9.36537337715832e-06, + "loss": 1.3309, + "step": 5418 + }, + { + "epoch": 0.57, + "learning_rate": 9.361720547942683e-06, + "loss": 1.362, + "step": 5419 + }, + { + "epoch": 0.57, + "learning_rate": 9.358067804240098e-06, + "loss": 1.3647, + "step": 5420 + }, + { + "epoch": 0.57, + "learning_rate": 9.354415146539933e-06, + "loss": 1.4511, + "step": 5421 + }, + { + "epoch": 0.57, + "learning_rate": 9.350762575331554e-06, + "loss": 1.3379, + "step": 5422 + }, + { + "epoch": 0.57, + "learning_rate": 9.3471100911043e-06, + "loss": 1.5468, + "step": 5423 + }, + { + "epoch": 0.57, + "learning_rate": 9.343457694347524e-06, + "loss": 1.4259, + "step": 5424 + }, + { + "epoch": 0.57, + "learning_rate": 9.339805385550548e-06, + "loss": 1.3816, + "step": 5425 + }, + { + "epoch": 0.57, + "learning_rate": 9.336153165202689e-06, + "loss": 1.3627, + "step": 5426 + }, + { + "epoch": 0.57, + "learning_rate": 9.332501033793242e-06, + "loss": 1.3338, + "step": 5427 + }, + { + "epoch": 0.57, + "learning_rate": 9.328848991811509e-06, + "loss": 1.2946, + "step": 5428 + }, + { + "epoch": 0.57, + "learning_rate": 9.325197039746769e-06, + "loss": 1.3405, + "step": 5429 + }, + { + "epoch": 0.57, + "learning_rate": 9.321545178088288e-06, + "loss": 1.3549, + "step": 5430 + }, + { + "epoch": 0.57, + "learning_rate": 9.317893407325314e-06, + "loss": 1.3225, + "step": 5431 + }, + { + "epoch": 0.57, + "learning_rate": 9.314241727947101e-06, + "loss": 1.3457, + "step": 5432 + }, + { + "epoch": 0.57, + "learning_rate": 9.310590140442878e-06, + "loss": 1.311, + "step": 5433 + }, + { + "epoch": 0.57, + "learning_rate": 9.306938645301862e-06, + "loss": 1.3615, + "step": 5434 + }, + { + "epoch": 0.57, + "learning_rate": 9.303287243013255e-06, + "loss": 1.3495, + "step": 5435 + }, + { + "epoch": 0.57, + "learning_rate": 9.29963593406626e-06, + "loss": 1.3899, + "step": 5436 + }, + { + "epoch": 0.57, + "learning_rate": 9.295984718950058e-06, + "loss": 1.3189, + "step": 5437 + }, + { + "epoch": 0.57, + "learning_rate": 9.292333598153813e-06, + "loss": 1.4199, + "step": 5438 + }, + { + "epoch": 0.57, + "learning_rate": 9.288682572166677e-06, + "loss": 1.4751, + "step": 5439 + }, + { + "epoch": 0.57, + "learning_rate": 9.285031641477804e-06, + "loss": 1.3435, + "step": 5440 + }, + { + "epoch": 0.57, + "learning_rate": 9.281380806576322e-06, + "loss": 1.2954, + "step": 5441 + }, + { + "epoch": 0.57, + "learning_rate": 9.277730067951341e-06, + "loss": 1.3414, + "step": 5442 + }, + { + "epoch": 0.57, + "learning_rate": 9.274079426091978e-06, + "loss": 1.3642, + "step": 5443 + }, + { + "epoch": 0.57, + "learning_rate": 9.27042888148732e-06, + "loss": 1.3651, + "step": 5444 + }, + { + "epoch": 0.57, + "learning_rate": 9.266778434626448e-06, + "loss": 1.3995, + "step": 5445 + }, + { + "epoch": 0.57, + "learning_rate": 9.263128085998421e-06, + "loss": 1.2692, + "step": 5446 + }, + { + "epoch": 0.57, + "learning_rate": 9.2594778360923e-06, + "loss": 1.4355, + "step": 5447 + }, + { + "epoch": 0.57, + "learning_rate": 9.255827685397124e-06, + "loss": 1.4262, + "step": 5448 + }, + { + "epoch": 0.57, + "learning_rate": 9.252177634401917e-06, + "loss": 1.3372, + "step": 5449 + }, + { + "epoch": 0.57, + "learning_rate": 9.248527683595685e-06, + "loss": 1.4603, + "step": 5450 + }, + { + "epoch": 0.57, + "learning_rate": 9.24487783346744e-06, + "loss": 1.446, + "step": 5451 + }, + { + "epoch": 0.57, + "learning_rate": 9.241228084506167e-06, + "loss": 1.4088, + "step": 5452 + }, + { + "epoch": 0.57, + "learning_rate": 9.237578437200832e-06, + "loss": 1.3074, + "step": 5453 + }, + { + "epoch": 0.57, + "learning_rate": 9.233928892040392e-06, + "loss": 1.4347, + "step": 5454 + }, + { + "epoch": 0.57, + "learning_rate": 9.230279449513802e-06, + "loss": 1.2982, + "step": 5455 + }, + { + "epoch": 0.57, + "learning_rate": 9.226630110109988e-06, + "loss": 1.2928, + "step": 5456 + }, + { + "epoch": 0.57, + "learning_rate": 9.222980874317869e-06, + "loss": 1.2849, + "step": 5457 + }, + { + "epoch": 0.57, + "learning_rate": 9.219331742626343e-06, + "loss": 1.3137, + "step": 5458 + }, + { + "epoch": 0.57, + "learning_rate": 9.215682715524309e-06, + "loss": 1.3523, + "step": 5459 + }, + { + "epoch": 0.57, + "learning_rate": 9.21203379350064e-06, + "loss": 1.381, + "step": 5460 + }, + { + "epoch": 0.57, + "learning_rate": 9.208384977044191e-06, + "loss": 1.286, + "step": 5461 + }, + { + "epoch": 0.57, + "learning_rate": 9.204736266643819e-06, + "loss": 1.3467, + "step": 5462 + }, + { + "epoch": 0.57, + "learning_rate": 9.201087662788353e-06, + "loss": 1.3582, + "step": 5463 + }, + { + "epoch": 0.57, + "learning_rate": 9.197439165966617e-06, + "loss": 1.3912, + "step": 5464 + }, + { + "epoch": 0.57, + "learning_rate": 9.193790776667402e-06, + "loss": 1.3144, + "step": 5465 + }, + { + "epoch": 0.57, + "learning_rate": 9.190142495379515e-06, + "loss": 1.3403, + "step": 5466 + }, + { + "epoch": 0.57, + "learning_rate": 9.186494322591725e-06, + "loss": 1.3253, + "step": 5467 + }, + { + "epoch": 0.57, + "learning_rate": 9.182846258792794e-06, + "loss": 1.2908, + "step": 5468 + }, + { + "epoch": 0.57, + "learning_rate": 9.179198304471463e-06, + "loss": 1.3486, + "step": 5469 + }, + { + "epoch": 0.57, + "learning_rate": 9.175550460116473e-06, + "loss": 1.3915, + "step": 5470 + }, + { + "epoch": 0.57, + "learning_rate": 9.171902726216538e-06, + "loss": 1.3441, + "step": 5471 + }, + { + "epoch": 0.57, + "learning_rate": 9.168255103260362e-06, + "loss": 1.3196, + "step": 5472 + }, + { + "epoch": 0.57, + "learning_rate": 9.164607591736627e-06, + "loss": 1.3279, + "step": 5473 + }, + { + "epoch": 0.57, + "learning_rate": 9.160960192134011e-06, + "loss": 1.2643, + "step": 5474 + }, + { + "epoch": 0.57, + "learning_rate": 9.157312904941174e-06, + "loss": 1.3327, + "step": 5475 + }, + { + "epoch": 0.57, + "learning_rate": 9.153665730646756e-06, + "loss": 1.4016, + "step": 5476 + }, + { + "epoch": 0.57, + "learning_rate": 9.150018669739378e-06, + "loss": 1.3614, + "step": 5477 + }, + { + "epoch": 0.57, + "learning_rate": 9.146371722707662e-06, + "loss": 1.3469, + "step": 5478 + }, + { + "epoch": 0.57, + "learning_rate": 9.142724890040204e-06, + "loss": 1.3625, + "step": 5479 + }, + { + "epoch": 0.57, + "learning_rate": 9.139078172225585e-06, + "loss": 1.3879, + "step": 5480 + }, + { + "epoch": 0.57, + "learning_rate": 9.135431569752362e-06, + "loss": 1.3738, + "step": 5481 + }, + { + "epoch": 0.57, + "learning_rate": 9.131785083109101e-06, + "loss": 1.3507, + "step": 5482 + }, + { + "epoch": 0.57, + "learning_rate": 9.128138712784331e-06, + "loss": 1.3681, + "step": 5483 + }, + { + "epoch": 0.58, + "learning_rate": 9.124492459266567e-06, + "loss": 1.332, + "step": 5484 + }, + { + "epoch": 0.58, + "learning_rate": 9.12084632304432e-06, + "loss": 1.4746, + "step": 5485 + }, + { + "epoch": 0.58, + "learning_rate": 9.11720030460608e-06, + "loss": 1.2775, + "step": 5486 + }, + { + "epoch": 0.58, + "learning_rate": 9.113554404440317e-06, + "loss": 1.2567, + "step": 5487 + }, + { + "epoch": 0.58, + "learning_rate": 9.10990862303548e-06, + "loss": 1.3935, + "step": 5488 + }, + { + "epoch": 0.58, + "learning_rate": 9.106262960880024e-06, + "loss": 1.3544, + "step": 5489 + }, + { + "epoch": 0.58, + "learning_rate": 9.102617418462365e-06, + "loss": 1.4023, + "step": 5490 + }, + { + "epoch": 0.58, + "learning_rate": 9.098971996270918e-06, + "loss": 1.3759, + "step": 5491 + }, + { + "epoch": 0.58, + "learning_rate": 9.095326694794064e-06, + "loss": 1.4165, + "step": 5492 + }, + { + "epoch": 0.58, + "learning_rate": 9.091681514520194e-06, + "loss": 1.3189, + "step": 5493 + }, + { + "epoch": 0.58, + "learning_rate": 9.088036455937663e-06, + "loss": 1.3135, + "step": 5494 + }, + { + "epoch": 0.58, + "learning_rate": 9.084391519534815e-06, + "loss": 1.3521, + "step": 5495 + }, + { + "epoch": 0.58, + "learning_rate": 9.080746705799971e-06, + "loss": 1.3314, + "step": 5496 + }, + { + "epoch": 0.58, + "learning_rate": 9.077102015221457e-06, + "loss": 1.3119, + "step": 5497 + }, + { + "epoch": 0.58, + "learning_rate": 9.073457448287557e-06, + "loss": 1.2895, + "step": 5498 + }, + { + "epoch": 0.58, + "learning_rate": 9.069813005486554e-06, + "loss": 1.3155, + "step": 5499 + }, + { + "epoch": 0.58, + "learning_rate": 9.066168687306701e-06, + "loss": 1.4048, + "step": 5500 + }, + { + "epoch": 0.58, + "learning_rate": 9.062524494236256e-06, + "loss": 1.3665, + "step": 5501 + }, + { + "epoch": 0.58, + "learning_rate": 9.058880426763442e-06, + "loss": 1.3258, + "step": 5502 + }, + { + "epoch": 0.58, + "learning_rate": 9.05523648537647e-06, + "loss": 1.3078, + "step": 5503 + }, + { + "epoch": 0.58, + "learning_rate": 9.051592670563527e-06, + "loss": 1.361, + "step": 5504 + }, + { + "epoch": 0.58, + "learning_rate": 9.047948982812801e-06, + "loss": 1.3557, + "step": 5505 + }, + { + "epoch": 0.58, + "learning_rate": 9.044305422612453e-06, + "loss": 1.5733, + "step": 5506 + }, + { + "epoch": 0.58, + "learning_rate": 9.040661990450617e-06, + "loss": 1.2835, + "step": 5507 + }, + { + "epoch": 0.58, + "learning_rate": 9.037018686815428e-06, + "loss": 1.311, + "step": 5508 + }, + { + "epoch": 0.58, + "learning_rate": 9.033375512194993e-06, + "loss": 1.3949, + "step": 5509 + }, + { + "epoch": 0.58, + "learning_rate": 9.029732467077405e-06, + "loss": 1.356, + "step": 5510 + }, + { + "epoch": 0.58, + "learning_rate": 9.026089551950727e-06, + "loss": 1.3695, + "step": 5511 + }, + { + "epoch": 0.58, + "learning_rate": 9.022446767303033e-06, + "loss": 1.3325, + "step": 5512 + }, + { + "epoch": 0.58, + "learning_rate": 9.018804113622353e-06, + "loss": 1.401, + "step": 5513 + }, + { + "epoch": 0.58, + "learning_rate": 9.015161591396713e-06, + "loss": 1.3632, + "step": 5514 + }, + { + "epoch": 0.58, + "learning_rate": 9.011519201114108e-06, + "loss": 1.3697, + "step": 5515 + }, + { + "epoch": 0.58, + "learning_rate": 9.007876943262538e-06, + "loss": 1.2604, + "step": 5516 + }, + { + "epoch": 0.58, + "learning_rate": 9.004234818329964e-06, + "loss": 1.3557, + "step": 5517 + }, + { + "epoch": 0.58, + "learning_rate": 9.000592826804342e-06, + "loss": 1.3248, + "step": 5518 + }, + { + "epoch": 0.58, + "learning_rate": 8.996950969173596e-06, + "loss": 1.3237, + "step": 5519 + }, + { + "epoch": 0.58, + "learning_rate": 8.99330924592565e-06, + "loss": 1.339, + "step": 5520 + }, + { + "epoch": 0.58, + "learning_rate": 8.989667657548402e-06, + "loss": 1.3218, + "step": 5521 + }, + { + "epoch": 0.58, + "learning_rate": 8.986026204529728e-06, + "loss": 1.3354, + "step": 5522 + }, + { + "epoch": 0.58, + "learning_rate": 8.982384887357484e-06, + "loss": 1.3011, + "step": 5523 + }, + { + "epoch": 0.58, + "learning_rate": 8.978743706519524e-06, + "loss": 1.3526, + "step": 5524 + }, + { + "epoch": 0.58, + "learning_rate": 8.975102662503666e-06, + "loss": 1.3298, + "step": 5525 + }, + { + "epoch": 0.58, + "learning_rate": 8.971461755797718e-06, + "loss": 1.328, + "step": 5526 + }, + { + "epoch": 0.58, + "learning_rate": 8.967820986889461e-06, + "loss": 1.3705, + "step": 5527 + }, + { + "epoch": 0.58, + "learning_rate": 8.964180356266676e-06, + "loss": 1.3814, + "step": 5528 + }, + { + "epoch": 0.58, + "learning_rate": 8.96053986441711e-06, + "loss": 1.37, + "step": 5529 + }, + { + "epoch": 0.58, + "learning_rate": 8.956899511828489e-06, + "loss": 1.3224, + "step": 5530 + }, + { + "epoch": 0.58, + "learning_rate": 8.953259298988536e-06, + "loss": 1.3416, + "step": 5531 + }, + { + "epoch": 0.58, + "learning_rate": 8.949619226384942e-06, + "loss": 1.4212, + "step": 5532 + }, + { + "epoch": 0.58, + "learning_rate": 8.945979294505383e-06, + "loss": 1.4145, + "step": 5533 + }, + { + "epoch": 0.58, + "learning_rate": 8.942339503837512e-06, + "loss": 1.2179, + "step": 5534 + }, + { + "epoch": 0.58, + "learning_rate": 8.938699854868976e-06, + "loss": 1.3239, + "step": 5535 + }, + { + "epoch": 0.58, + "learning_rate": 8.93506034808739e-06, + "loss": 1.3488, + "step": 5536 + }, + { + "epoch": 0.58, + "learning_rate": 8.931420983980357e-06, + "loss": 1.3283, + "step": 5537 + }, + { + "epoch": 0.58, + "learning_rate": 8.927781763035449e-06, + "loss": 1.3866, + "step": 5538 + }, + { + "epoch": 0.58, + "learning_rate": 8.924142685740239e-06, + "loss": 1.3877, + "step": 5539 + }, + { + "epoch": 0.58, + "learning_rate": 8.920503752582265e-06, + "loss": 1.2511, + "step": 5540 + }, + { + "epoch": 0.58, + "learning_rate": 8.916864964049056e-06, + "loss": 1.3581, + "step": 5541 + }, + { + "epoch": 0.58, + "learning_rate": 8.913226320628104e-06, + "loss": 1.387, + "step": 5542 + }, + { + "epoch": 0.58, + "learning_rate": 8.909587822806905e-06, + "loss": 1.3785, + "step": 5543 + }, + { + "epoch": 0.58, + "learning_rate": 8.905949471072921e-06, + "loss": 1.4302, + "step": 5544 + }, + { + "epoch": 0.58, + "learning_rate": 8.9023112659136e-06, + "loss": 1.439, + "step": 5545 + }, + { + "epoch": 0.58, + "learning_rate": 8.898673207816357e-06, + "loss": 1.3257, + "step": 5546 + }, + { + "epoch": 0.58, + "learning_rate": 8.895035297268611e-06, + "loss": 1.4237, + "step": 5547 + }, + { + "epoch": 0.58, + "learning_rate": 8.891397534757745e-06, + "loss": 1.3141, + "step": 5548 + }, + { + "epoch": 0.58, + "learning_rate": 8.887759920771127e-06, + "loss": 1.3069, + "step": 5549 + }, + { + "epoch": 0.58, + "learning_rate": 8.884122455796095e-06, + "loss": 1.2703, + "step": 5550 + }, + { + "epoch": 0.58, + "learning_rate": 8.880485140319986e-06, + "loss": 1.2929, + "step": 5551 + }, + { + "epoch": 0.58, + "learning_rate": 8.876847974830103e-06, + "loss": 1.3719, + "step": 5552 + }, + { + "epoch": 0.58, + "learning_rate": 8.873210959813731e-06, + "loss": 1.3481, + "step": 5553 + }, + { + "epoch": 0.58, + "learning_rate": 8.869574095758141e-06, + "loss": 1.3609, + "step": 5554 + }, + { + "epoch": 0.58, + "learning_rate": 8.865937383150577e-06, + "loss": 1.3137, + "step": 5555 + }, + { + "epoch": 0.58, + "learning_rate": 8.862300822478265e-06, + "loss": 1.3602, + "step": 5556 + }, + { + "epoch": 0.58, + "learning_rate": 8.858664414228409e-06, + "loss": 1.3142, + "step": 5557 + }, + { + "epoch": 0.58, + "learning_rate": 8.855028158888196e-06, + "loss": 1.288, + "step": 5558 + }, + { + "epoch": 0.58, + "learning_rate": 8.851392056944791e-06, + "loss": 1.3407, + "step": 5559 + }, + { + "epoch": 0.58, + "learning_rate": 8.847756108885342e-06, + "loss": 1.3118, + "step": 5560 + }, + { + "epoch": 0.58, + "learning_rate": 8.84412031519696e-06, + "loss": 1.3646, + "step": 5561 + }, + { + "epoch": 0.58, + "learning_rate": 8.840484676366761e-06, + "loss": 1.3896, + "step": 5562 + }, + { + "epoch": 0.58, + "learning_rate": 8.836849192881822e-06, + "loss": 1.3296, + "step": 5563 + }, + { + "epoch": 0.58, + "learning_rate": 8.833213865229208e-06, + "loss": 1.2918, + "step": 5564 + }, + { + "epoch": 0.58, + "learning_rate": 8.82957869389595e-06, + "loss": 1.4811, + "step": 5565 + }, + { + "epoch": 0.58, + "learning_rate": 8.82594367936908e-06, + "loss": 1.3877, + "step": 5566 + }, + { + "epoch": 0.58, + "learning_rate": 8.822308822135588e-06, + "loss": 1.3716, + "step": 5567 + }, + { + "epoch": 0.58, + "learning_rate": 8.818674122682456e-06, + "loss": 1.3204, + "step": 5568 + }, + { + "epoch": 0.58, + "learning_rate": 8.815039581496634e-06, + "loss": 1.326, + "step": 5569 + }, + { + "epoch": 0.58, + "learning_rate": 8.811405199065066e-06, + "loss": 1.3762, + "step": 5570 + }, + { + "epoch": 0.58, + "learning_rate": 8.807770975874658e-06, + "loss": 1.2944, + "step": 5571 + }, + { + "epoch": 0.58, + "learning_rate": 8.804136912412311e-06, + "loss": 1.3057, + "step": 5572 + }, + { + "epoch": 0.58, + "eval_loss": 1.4187605381011963, + "eval_runtime": 77.5157, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 5572 + }, + { + "epoch": 0.58, + "learning_rate": 8.800503009164884e-06, + "loss": 1.4144, + "step": 5573 + }, + { + "epoch": 0.58, + "learning_rate": 8.796869266619238e-06, + "loss": 1.2218, + "step": 5574 + }, + { + "epoch": 0.58, + "learning_rate": 8.793235685262197e-06, + "loss": 1.4445, + "step": 5575 + }, + { + "epoch": 0.58, + "learning_rate": 8.789602265580565e-06, + "loss": 1.3761, + "step": 5576 + }, + { + "epoch": 0.58, + "learning_rate": 8.78596900806113e-06, + "loss": 1.3762, + "step": 5577 + }, + { + "epoch": 0.58, + "learning_rate": 8.782335913190657e-06, + "loss": 1.3506, + "step": 5578 + }, + { + "epoch": 0.59, + "learning_rate": 8.778702981455883e-06, + "loss": 1.4183, + "step": 5579 + }, + { + "epoch": 0.59, + "learning_rate": 8.775070213343528e-06, + "loss": 1.3123, + "step": 5580 + }, + { + "epoch": 0.59, + "learning_rate": 8.771437609340291e-06, + "loss": 1.3168, + "step": 5581 + }, + { + "epoch": 0.59, + "learning_rate": 8.76780516993285e-06, + "loss": 1.3939, + "step": 5582 + }, + { + "epoch": 0.59, + "learning_rate": 8.764172895607856e-06, + "loss": 1.3317, + "step": 5583 + }, + { + "epoch": 0.59, + "learning_rate": 8.760540786851937e-06, + "loss": 1.3094, + "step": 5584 + }, + { + "epoch": 0.59, + "learning_rate": 8.756908844151708e-06, + "loss": 1.2853, + "step": 5585 + }, + { + "epoch": 0.59, + "learning_rate": 8.753277067993752e-06, + "loss": 1.2625, + "step": 5586 + }, + { + "epoch": 0.59, + "learning_rate": 8.74964545886464e-06, + "loss": 1.4246, + "step": 5587 + }, + { + "epoch": 0.59, + "learning_rate": 8.746014017250904e-06, + "loss": 1.2891, + "step": 5588 + }, + { + "epoch": 0.59, + "learning_rate": 8.742382743639071e-06, + "loss": 1.3135, + "step": 5589 + }, + { + "epoch": 0.59, + "learning_rate": 8.738751638515639e-06, + "loss": 1.3021, + "step": 5590 + }, + { + "epoch": 0.59, + "learning_rate": 8.735120702367082e-06, + "loss": 1.3398, + "step": 5591 + }, + { + "epoch": 0.59, + "learning_rate": 8.731489935679845e-06, + "loss": 1.4173, + "step": 5592 + }, + { + "epoch": 0.59, + "learning_rate": 8.727859338940367e-06, + "loss": 1.4129, + "step": 5593 + }, + { + "epoch": 0.59, + "learning_rate": 8.724228912635053e-06, + "loss": 1.3807, + "step": 5594 + }, + { + "epoch": 0.59, + "learning_rate": 8.720598657250284e-06, + "loss": 1.2962, + "step": 5595 + }, + { + "epoch": 0.59, + "learning_rate": 8.716968573272416e-06, + "loss": 1.3784, + "step": 5596 + }, + { + "epoch": 0.59, + "learning_rate": 8.713338661187799e-06, + "loss": 1.3751, + "step": 5597 + }, + { + "epoch": 0.59, + "learning_rate": 8.70970892148274e-06, + "loss": 1.3122, + "step": 5598 + }, + { + "epoch": 0.59, + "learning_rate": 8.70607935464353e-06, + "loss": 1.4174, + "step": 5599 + }, + { + "epoch": 0.59, + "learning_rate": 8.702449961156445e-06, + "loss": 1.3275, + "step": 5600 + }, + { + "epoch": 0.59, + "learning_rate": 8.698820741507723e-06, + "loss": 1.33, + "step": 5601 + }, + { + "epoch": 0.59, + "learning_rate": 8.695191696183589e-06, + "loss": 1.4075, + "step": 5602 + }, + { + "epoch": 0.59, + "learning_rate": 8.69156282567024e-06, + "loss": 1.3778, + "step": 5603 + }, + { + "epoch": 0.59, + "learning_rate": 8.687934130453857e-06, + "loss": 1.3222, + "step": 5604 + }, + { + "epoch": 0.59, + "learning_rate": 8.684305611020587e-06, + "loss": 1.3443, + "step": 5605 + }, + { + "epoch": 0.59, + "learning_rate": 8.680677267856558e-06, + "loss": 1.3167, + "step": 5606 + }, + { + "epoch": 0.59, + "learning_rate": 8.677049101447877e-06, + "loss": 1.3209, + "step": 5607 + }, + { + "epoch": 0.59, + "learning_rate": 8.673421112280624e-06, + "loss": 1.3125, + "step": 5608 + }, + { + "epoch": 0.59, + "learning_rate": 8.669793300840857e-06, + "loss": 1.375, + "step": 5609 + }, + { + "epoch": 0.59, + "learning_rate": 8.666165667614612e-06, + "loss": 1.3627, + "step": 5610 + }, + { + "epoch": 0.59, + "learning_rate": 8.662538213087888e-06, + "loss": 1.3064, + "step": 5611 + }, + { + "epoch": 0.59, + "learning_rate": 8.658910937746685e-06, + "loss": 1.4251, + "step": 5612 + }, + { + "epoch": 0.59, + "learning_rate": 8.655283842076956e-06, + "loss": 1.3011, + "step": 5613 + }, + { + "epoch": 0.59, + "learning_rate": 8.651656926564645e-06, + "loss": 1.3299, + "step": 5614 + }, + { + "epoch": 0.59, + "learning_rate": 8.648030191695653e-06, + "loss": 1.3448, + "step": 5615 + }, + { + "epoch": 0.59, + "learning_rate": 8.644403637955883e-06, + "loss": 1.4048, + "step": 5616 + }, + { + "epoch": 0.59, + "learning_rate": 8.640777265831195e-06, + "loss": 1.336, + "step": 5617 + }, + { + "epoch": 0.59, + "learning_rate": 8.63715107580743e-06, + "loss": 1.4959, + "step": 5618 + }, + { + "epoch": 0.59, + "learning_rate": 8.633525068370397e-06, + "loss": 1.3822, + "step": 5619 + }, + { + "epoch": 0.59, + "learning_rate": 8.6298992440059e-06, + "loss": 1.282, + "step": 5620 + }, + { + "epoch": 0.59, + "learning_rate": 8.626273603199699e-06, + "loss": 1.1873, + "step": 5621 + }, + { + "epoch": 0.59, + "learning_rate": 8.622648146437538e-06, + "loss": 1.3706, + "step": 5622 + }, + { + "epoch": 0.59, + "learning_rate": 8.619022874205138e-06, + "loss": 1.2709, + "step": 5623 + }, + { + "epoch": 0.59, + "learning_rate": 8.615397786988188e-06, + "loss": 1.3608, + "step": 5624 + }, + { + "epoch": 0.59, + "learning_rate": 8.61177288527236e-06, + "loss": 1.3821, + "step": 5625 + }, + { + "epoch": 0.59, + "learning_rate": 8.608148169543292e-06, + "loss": 1.327, + "step": 5626 + }, + { + "epoch": 0.59, + "learning_rate": 8.604523640286611e-06, + "loss": 1.3544, + "step": 5627 + }, + { + "epoch": 0.59, + "learning_rate": 8.600899297987905e-06, + "loss": 1.3269, + "step": 5628 + }, + { + "epoch": 0.59, + "learning_rate": 8.597275143132745e-06, + "loss": 1.3142, + "step": 5629 + }, + { + "epoch": 0.59, + "learning_rate": 8.593651176206671e-06, + "loss": 1.3878, + "step": 5630 + }, + { + "epoch": 0.59, + "learning_rate": 8.59002739769521e-06, + "loss": 1.3386, + "step": 5631 + }, + { + "epoch": 0.59, + "learning_rate": 8.586403808083846e-06, + "loss": 1.3484, + "step": 5632 + }, + { + "epoch": 0.59, + "learning_rate": 8.582780407858052e-06, + "loss": 1.3676, + "step": 5633 + }, + { + "epoch": 0.59, + "learning_rate": 8.579157197503265e-06, + "loss": 1.3753, + "step": 5634 + }, + { + "epoch": 0.59, + "learning_rate": 8.57553417750491e-06, + "loss": 1.4058, + "step": 5635 + }, + { + "epoch": 0.59, + "learning_rate": 8.571911348348375e-06, + "loss": 1.4434, + "step": 5636 + }, + { + "epoch": 0.59, + "learning_rate": 8.568288710519027e-06, + "loss": 1.3398, + "step": 5637 + }, + { + "epoch": 0.59, + "learning_rate": 8.564666264502199e-06, + "loss": 1.3294, + "step": 5638 + }, + { + "epoch": 0.59, + "learning_rate": 8.561044010783216e-06, + "loss": 1.3165, + "step": 5639 + }, + { + "epoch": 0.59, + "learning_rate": 8.557421949847363e-06, + "loss": 1.3437, + "step": 5640 + }, + { + "epoch": 0.59, + "learning_rate": 8.553800082179905e-06, + "loss": 1.3473, + "step": 5641 + }, + { + "epoch": 0.59, + "learning_rate": 8.55017840826607e-06, + "loss": 1.3378, + "step": 5642 + }, + { + "epoch": 0.59, + "learning_rate": 8.546556928591082e-06, + "loss": 1.3357, + "step": 5643 + }, + { + "epoch": 0.59, + "learning_rate": 8.54293564364012e-06, + "loss": 1.3435, + "step": 5644 + }, + { + "epoch": 0.59, + "learning_rate": 8.53931455389834e-06, + "loss": 1.3335, + "step": 5645 + }, + { + "epoch": 0.59, + "learning_rate": 8.535693659850885e-06, + "loss": 1.2917, + "step": 5646 + }, + { + "epoch": 0.59, + "learning_rate": 8.532072961982851e-06, + "loss": 1.3785, + "step": 5647 + }, + { + "epoch": 0.59, + "learning_rate": 8.528452460779327e-06, + "loss": 1.3634, + "step": 5648 + }, + { + "epoch": 0.59, + "learning_rate": 8.524832156725359e-06, + "loss": 1.3541, + "step": 5649 + }, + { + "epoch": 0.59, + "learning_rate": 8.521212050305978e-06, + "loss": 1.335, + "step": 5650 + }, + { + "epoch": 0.59, + "learning_rate": 8.51759214200619e-06, + "loss": 1.3011, + "step": 5651 + }, + { + "epoch": 0.59, + "learning_rate": 8.513972432310965e-06, + "loss": 1.3982, + "step": 5652 + }, + { + "epoch": 0.59, + "learning_rate": 8.510352921705247e-06, + "loss": 1.3217, + "step": 5653 + }, + { + "epoch": 0.59, + "learning_rate": 8.506733610673968e-06, + "loss": 1.3275, + "step": 5654 + }, + { + "epoch": 0.59, + "learning_rate": 8.503114499702015e-06, + "loss": 1.3335, + "step": 5655 + }, + { + "epoch": 0.59, + "learning_rate": 8.499495589274257e-06, + "loss": 1.3567, + "step": 5656 + }, + { + "epoch": 0.59, + "learning_rate": 8.495876879875536e-06, + "loss": 1.348, + "step": 5657 + }, + { + "epoch": 0.59, + "learning_rate": 8.492258371990667e-06, + "loss": 1.3991, + "step": 5658 + }, + { + "epoch": 0.59, + "learning_rate": 8.488640066104435e-06, + "loss": 1.3528, + "step": 5659 + }, + { + "epoch": 0.59, + "learning_rate": 8.485021962701603e-06, + "loss": 1.3275, + "step": 5660 + }, + { + "epoch": 0.59, + "learning_rate": 8.481404062266897e-06, + "loss": 1.3605, + "step": 5661 + }, + { + "epoch": 0.59, + "learning_rate": 8.477786365285032e-06, + "loss": 1.3288, + "step": 5662 + }, + { + "epoch": 0.59, + "learning_rate": 8.474168872240682e-06, + "loss": 1.3274, + "step": 5663 + }, + { + "epoch": 0.59, + "learning_rate": 8.470551583618498e-06, + "loss": 1.273, + "step": 5664 + }, + { + "epoch": 0.59, + "learning_rate": 8.4669344999031e-06, + "loss": 1.3142, + "step": 5665 + }, + { + "epoch": 0.59, + "learning_rate": 8.463317621579091e-06, + "loss": 1.2912, + "step": 5666 + }, + { + "epoch": 0.59, + "learning_rate": 8.459700949131037e-06, + "loss": 1.3162, + "step": 5667 + }, + { + "epoch": 0.59, + "learning_rate": 8.456084483043479e-06, + "loss": 1.3377, + "step": 5668 + }, + { + "epoch": 0.59, + "learning_rate": 8.452468223800931e-06, + "loss": 1.3545, + "step": 5669 + }, + { + "epoch": 0.59, + "learning_rate": 8.448852171887878e-06, + "loss": 1.4052, + "step": 5670 + }, + { + "epoch": 0.59, + "learning_rate": 8.44523632778878e-06, + "loss": 1.3389, + "step": 5671 + }, + { + "epoch": 0.59, + "learning_rate": 8.441620691988063e-06, + "loss": 1.3801, + "step": 5672 + }, + { + "epoch": 0.59, + "learning_rate": 8.438005264970134e-06, + "loss": 1.2978, + "step": 5673 + }, + { + "epoch": 0.6, + "learning_rate": 8.434390047219366e-06, + "loss": 1.437, + "step": 5674 + }, + { + "epoch": 0.6, + "learning_rate": 8.430775039220103e-06, + "loss": 1.3602, + "step": 5675 + }, + { + "epoch": 0.6, + "learning_rate": 8.427160241456664e-06, + "loss": 1.4971, + "step": 5676 + }, + { + "epoch": 0.6, + "learning_rate": 8.423545654413342e-06, + "loss": 1.2765, + "step": 5677 + }, + { + "epoch": 0.6, + "learning_rate": 8.419931278574397e-06, + "loss": 1.4346, + "step": 5678 + }, + { + "epoch": 0.6, + "learning_rate": 8.416317114424059e-06, + "loss": 1.366, + "step": 5679 + }, + { + "epoch": 0.6, + "learning_rate": 8.412703162446536e-06, + "loss": 1.3776, + "step": 5680 + }, + { + "epoch": 0.6, + "learning_rate": 8.409089423126009e-06, + "loss": 1.2516, + "step": 5681 + }, + { + "epoch": 0.6, + "learning_rate": 8.405475896946621e-06, + "loss": 1.4257, + "step": 5682 + }, + { + "epoch": 0.6, + "learning_rate": 8.401862584392492e-06, + "loss": 1.3523, + "step": 5683 + }, + { + "epoch": 0.6, + "learning_rate": 8.398249485947712e-06, + "loss": 1.3791, + "step": 5684 + }, + { + "epoch": 0.6, + "learning_rate": 8.394636602096348e-06, + "loss": 1.3574, + "step": 5685 + }, + { + "epoch": 0.6, + "learning_rate": 8.39102393332243e-06, + "loss": 1.4748, + "step": 5686 + }, + { + "epoch": 0.6, + "learning_rate": 8.387411480109967e-06, + "loss": 1.3693, + "step": 5687 + }, + { + "epoch": 0.6, + "learning_rate": 8.383799242942925e-06, + "loss": 1.3643, + "step": 5688 + }, + { + "epoch": 0.6, + "learning_rate": 8.38018722230526e-06, + "loss": 1.3446, + "step": 5689 + }, + { + "epoch": 0.6, + "learning_rate": 8.37657541868089e-06, + "loss": 1.3552, + "step": 5690 + }, + { + "epoch": 0.6, + "learning_rate": 8.372963832553698e-06, + "loss": 1.3636, + "step": 5691 + }, + { + "epoch": 0.6, + "learning_rate": 8.36935246440755e-06, + "loss": 1.3398, + "step": 5692 + }, + { + "epoch": 0.6, + "learning_rate": 8.365741314726273e-06, + "loss": 1.3336, + "step": 5693 + }, + { + "epoch": 0.6, + "learning_rate": 8.362130383993667e-06, + "loss": 1.3023, + "step": 5694 + }, + { + "epoch": 0.6, + "learning_rate": 8.358519672693506e-06, + "loss": 1.3591, + "step": 5695 + }, + { + "epoch": 0.6, + "learning_rate": 8.354909181309533e-06, + "loss": 1.3113, + "step": 5696 + }, + { + "epoch": 0.6, + "learning_rate": 8.351298910325462e-06, + "loss": 1.3747, + "step": 5697 + }, + { + "epoch": 0.6, + "learning_rate": 8.347688860224976e-06, + "loss": 1.3555, + "step": 5698 + }, + { + "epoch": 0.6, + "learning_rate": 8.344079031491722e-06, + "loss": 1.2947, + "step": 5699 + }, + { + "epoch": 0.6, + "learning_rate": 8.340469424609337e-06, + "loss": 1.4099, + "step": 5700 + }, + { + "epoch": 0.6, + "learning_rate": 8.336860040061404e-06, + "loss": 1.3263, + "step": 5701 + }, + { + "epoch": 0.6, + "learning_rate": 8.333250878331498e-06, + "loss": 1.372, + "step": 5702 + }, + { + "epoch": 0.6, + "learning_rate": 8.329641939903142e-06, + "loss": 1.3523, + "step": 5703 + }, + { + "epoch": 0.6, + "learning_rate": 8.32603322525985e-06, + "loss": 1.3451, + "step": 5704 + }, + { + "epoch": 0.6, + "learning_rate": 8.322424734885098e-06, + "loss": 1.3296, + "step": 5705 + }, + { + "epoch": 0.6, + "learning_rate": 8.318816469262325e-06, + "loss": 1.449, + "step": 5706 + }, + { + "epoch": 0.6, + "learning_rate": 8.315208428874946e-06, + "loss": 1.3611, + "step": 5707 + }, + { + "epoch": 0.6, + "learning_rate": 8.311600614206352e-06, + "loss": 1.3849, + "step": 5708 + }, + { + "epoch": 0.6, + "learning_rate": 8.307993025739893e-06, + "loss": 1.3968, + "step": 5709 + }, + { + "epoch": 0.6, + "learning_rate": 8.304385663958895e-06, + "loss": 1.4428, + "step": 5710 + }, + { + "epoch": 0.6, + "learning_rate": 8.300778529346647e-06, + "loss": 1.3095, + "step": 5711 + }, + { + "epoch": 0.6, + "learning_rate": 8.297171622386418e-06, + "loss": 1.3135, + "step": 5712 + }, + { + "epoch": 0.6, + "learning_rate": 8.293564943561438e-06, + "loss": 1.3069, + "step": 5713 + }, + { + "epoch": 0.6, + "learning_rate": 8.28995849335491e-06, + "loss": 1.3736, + "step": 5714 + }, + { + "epoch": 0.6, + "learning_rate": 8.286352272250007e-06, + "loss": 1.343, + "step": 5715 + }, + { + "epoch": 0.6, + "learning_rate": 8.28274628072987e-06, + "loss": 1.2929, + "step": 5716 + }, + { + "epoch": 0.6, + "learning_rate": 8.279140519277607e-06, + "loss": 1.3356, + "step": 5717 + }, + { + "epoch": 0.6, + "learning_rate": 8.275534988376295e-06, + "loss": 1.2683, + "step": 5718 + }, + { + "epoch": 0.6, + "learning_rate": 8.27192968850899e-06, + "loss": 1.3738, + "step": 5719 + }, + { + "epoch": 0.6, + "learning_rate": 8.268324620158704e-06, + "loss": 1.3369, + "step": 5720 + }, + { + "epoch": 0.6, + "learning_rate": 8.264719783808425e-06, + "loss": 1.3684, + "step": 5721 + }, + { + "epoch": 0.6, + "learning_rate": 8.261115179941108e-06, + "loss": 1.4081, + "step": 5722 + }, + { + "epoch": 0.6, + "learning_rate": 8.257510809039678e-06, + "loss": 1.2504, + "step": 5723 + }, + { + "epoch": 0.6, + "learning_rate": 8.253906671587029e-06, + "loss": 1.417, + "step": 5724 + }, + { + "epoch": 0.6, + "learning_rate": 8.25030276806602e-06, + "loss": 1.3631, + "step": 5725 + }, + { + "epoch": 0.6, + "learning_rate": 8.246699098959483e-06, + "loss": 1.499, + "step": 5726 + }, + { + "epoch": 0.6, + "learning_rate": 8.243095664750217e-06, + "loss": 1.3656, + "step": 5727 + }, + { + "epoch": 0.6, + "learning_rate": 8.239492465920992e-06, + "loss": 1.3563, + "step": 5728 + }, + { + "epoch": 0.6, + "learning_rate": 8.23588950295454e-06, + "loss": 1.3554, + "step": 5729 + }, + { + "epoch": 0.6, + "learning_rate": 8.232286776333566e-06, + "loss": 1.2705, + "step": 5730 + }, + { + "epoch": 0.6, + "learning_rate": 8.228684286540747e-06, + "loss": 1.3792, + "step": 5731 + }, + { + "epoch": 0.6, + "learning_rate": 8.22508203405872e-06, + "loss": 1.3301, + "step": 5732 + }, + { + "epoch": 0.6, + "learning_rate": 8.221480019370095e-06, + "loss": 1.36, + "step": 5733 + }, + { + "epoch": 0.6, + "learning_rate": 8.217878242957448e-06, + "loss": 1.4406, + "step": 5734 + }, + { + "epoch": 0.6, + "learning_rate": 8.214276705303328e-06, + "loss": 1.2886, + "step": 5735 + }, + { + "epoch": 0.6, + "learning_rate": 8.210675406890248e-06, + "loss": 1.3072, + "step": 5736 + }, + { + "epoch": 0.6, + "learning_rate": 8.207074348200686e-06, + "loss": 1.3734, + "step": 5737 + }, + { + "epoch": 0.6, + "learning_rate": 8.203473529717095e-06, + "loss": 1.3893, + "step": 5738 + }, + { + "epoch": 0.6, + "learning_rate": 8.199872951921892e-06, + "loss": 1.3427, + "step": 5739 + }, + { + "epoch": 0.6, + "learning_rate": 8.196272615297459e-06, + "loss": 1.3125, + "step": 5740 + }, + { + "epoch": 0.6, + "learning_rate": 8.19267252032615e-06, + "loss": 1.3079, + "step": 5741 + }, + { + "epoch": 0.6, + "learning_rate": 8.189072667490285e-06, + "loss": 1.2971, + "step": 5742 + }, + { + "epoch": 0.6, + "learning_rate": 8.185473057272154e-06, + "loss": 1.3003, + "step": 5743 + }, + { + "epoch": 0.6, + "learning_rate": 8.18187369015401e-06, + "loss": 1.3002, + "step": 5744 + }, + { + "epoch": 0.6, + "learning_rate": 8.178274566618075e-06, + "loss": 1.2852, + "step": 5745 + }, + { + "epoch": 0.6, + "learning_rate": 8.174675687146542e-06, + "loss": 1.2807, + "step": 5746 + }, + { + "epoch": 0.6, + "learning_rate": 8.171077052221567e-06, + "loss": 1.2983, + "step": 5747 + }, + { + "epoch": 0.6, + "learning_rate": 8.167478662325274e-06, + "loss": 1.3002, + "step": 5748 + }, + { + "epoch": 0.6, + "learning_rate": 8.163880517939753e-06, + "loss": 1.2575, + "step": 5749 + }, + { + "epoch": 0.6, + "learning_rate": 8.160282619547068e-06, + "loss": 1.2627, + "step": 5750 + }, + { + "epoch": 0.6, + "learning_rate": 8.156684967629242e-06, + "loss": 1.2549, + "step": 5751 + }, + { + "epoch": 0.6, + "learning_rate": 8.153087562668265e-06, + "loss": 1.2595, + "step": 5752 + }, + { + "epoch": 0.6, + "learning_rate": 8.1494904051461e-06, + "loss": 1.2788, + "step": 5753 + }, + { + "epoch": 0.6, + "learning_rate": 8.145893495544676e-06, + "loss": 1.3028, + "step": 5754 + }, + { + "epoch": 0.6, + "learning_rate": 8.142296834345883e-06, + "loss": 1.3019, + "step": 5755 + }, + { + "epoch": 0.6, + "learning_rate": 8.138700422031583e-06, + "loss": 1.2998, + "step": 5756 + }, + { + "epoch": 0.6, + "learning_rate": 8.135104259083598e-06, + "loss": 1.3298, + "step": 5757 + }, + { + "epoch": 0.6, + "learning_rate": 8.13150834598373e-06, + "loss": 1.2681, + "step": 5758 + }, + { + "epoch": 0.6, + "learning_rate": 8.127912683213733e-06, + "loss": 1.2987, + "step": 5759 + }, + { + "epoch": 0.6, + "learning_rate": 8.124317271255331e-06, + "loss": 1.3181, + "step": 5760 + }, + { + "epoch": 0.6, + "learning_rate": 8.120722110590224e-06, + "loss": 1.423, + "step": 5761 + }, + { + "epoch": 0.6, + "learning_rate": 8.117127201700067e-06, + "loss": 1.5029, + "step": 5762 + }, + { + "epoch": 0.6, + "learning_rate": 8.113532545066488e-06, + "loss": 1.3016, + "step": 5763 + }, + { + "epoch": 0.6, + "learning_rate": 8.109938141171074e-06, + "loss": 1.3906, + "step": 5764 + }, + { + "epoch": 0.6, + "learning_rate": 8.106343990495387e-06, + "loss": 1.3363, + "step": 5765 + }, + { + "epoch": 0.6, + "learning_rate": 8.10275009352095e-06, + "loss": 1.314, + "step": 5766 + }, + { + "epoch": 0.6, + "learning_rate": 8.09915645072925e-06, + "loss": 1.3484, + "step": 5767 + }, + { + "epoch": 0.6, + "learning_rate": 8.095563062601745e-06, + "loss": 1.3757, + "step": 5768 + }, + { + "epoch": 0.6, + "learning_rate": 8.091969929619859e-06, + "loss": 1.3068, + "step": 5769 + }, + { + "epoch": 0.61, + "learning_rate": 8.088377052264976e-06, + "loss": 1.3486, + "step": 5770 + }, + { + "epoch": 0.61, + "learning_rate": 8.08478443101845e-06, + "loss": 1.244, + "step": 5771 + }, + { + "epoch": 0.61, + "eval_loss": 1.4178493022918701, + "eval_runtime": 77.6086, + "eval_samples_per_second": 1.662, + "eval_steps_per_second": 0.116, + "step": 5771 + }, + { + "epoch": 0.61, + "learning_rate": 8.0811920663616e-06, + "loss": 1.3325, + "step": 5772 + }, + { + "epoch": 0.61, + "learning_rate": 8.077599958775713e-06, + "loss": 1.336, + "step": 5773 + }, + { + "epoch": 0.61, + "learning_rate": 8.074008108742037e-06, + "loss": 1.3167, + "step": 5774 + }, + { + "epoch": 0.61, + "learning_rate": 8.070416516741786e-06, + "loss": 1.3166, + "step": 5775 + }, + { + "epoch": 0.61, + "learning_rate": 8.066825183256141e-06, + "loss": 1.3377, + "step": 5776 + }, + { + "epoch": 0.61, + "learning_rate": 8.063234108766253e-06, + "loss": 1.3704, + "step": 5777 + }, + { + "epoch": 0.61, + "learning_rate": 8.059643293753233e-06, + "loss": 1.3596, + "step": 5778 + }, + { + "epoch": 0.61, + "learning_rate": 8.056052738698153e-06, + "loss": 1.4477, + "step": 5779 + }, + { + "epoch": 0.61, + "learning_rate": 8.052462444082055e-06, + "loss": 1.338, + "step": 5780 + }, + { + "epoch": 0.61, + "learning_rate": 8.048872410385952e-06, + "loss": 1.2714, + "step": 5781 + }, + { + "epoch": 0.61, + "learning_rate": 8.045282638090815e-06, + "loss": 0.9642, + "step": 5782 + }, + { + "epoch": 0.61, + "learning_rate": 8.041693127677576e-06, + "loss": 0.8702, + "step": 5783 + }, + { + "epoch": 0.61, + "learning_rate": 8.038103879627144e-06, + "loss": 0.8986, + "step": 5784 + }, + { + "epoch": 0.61, + "learning_rate": 8.034514894420382e-06, + "loss": 0.804, + "step": 5785 + }, + { + "epoch": 0.61, + "learning_rate": 8.030926172538122e-06, + "loss": 0.7958, + "step": 5786 + }, + { + "epoch": 0.61, + "learning_rate": 8.02733771446116e-06, + "loss": 0.7608, + "step": 5787 + }, + { + "epoch": 0.61, + "learning_rate": 8.023749520670261e-06, + "loss": 0.7792, + "step": 5788 + }, + { + "epoch": 0.61, + "learning_rate": 8.020161591646147e-06, + "loss": 0.7293, + "step": 5789 + }, + { + "epoch": 0.61, + "learning_rate": 8.016573927869511e-06, + "loss": 1.1287, + "step": 5790 + }, + { + "epoch": 0.61, + "learning_rate": 8.012986529821004e-06, + "loss": 1.3344, + "step": 5791 + }, + { + "epoch": 0.61, + "learning_rate": 8.009399397981248e-06, + "loss": 1.4415, + "step": 5792 + }, + { + "epoch": 0.61, + "learning_rate": 8.005812532830826e-06, + "loss": 1.4265, + "step": 5793 + }, + { + "epoch": 0.61, + "learning_rate": 8.002225934850287e-06, + "loss": 1.3429, + "step": 5794 + }, + { + "epoch": 0.61, + "learning_rate": 7.998639604520137e-06, + "loss": 1.3653, + "step": 5795 + }, + { + "epoch": 0.61, + "learning_rate": 7.995053542320861e-06, + "loss": 1.486, + "step": 5796 + }, + { + "epoch": 0.61, + "learning_rate": 7.991467748732894e-06, + "loss": 1.3389, + "step": 5797 + }, + { + "epoch": 0.61, + "learning_rate": 7.98788222423664e-06, + "loss": 1.3206, + "step": 5798 + }, + { + "epoch": 0.61, + "learning_rate": 7.984296969312468e-06, + "loss": 1.3121, + "step": 5799 + }, + { + "epoch": 0.61, + "learning_rate": 7.980711984440712e-06, + "loss": 1.3512, + "step": 5800 + }, + { + "epoch": 0.61, + "learning_rate": 7.977127270101665e-06, + "loss": 1.3291, + "step": 5801 + }, + { + "epoch": 0.61, + "learning_rate": 7.97354282677559e-06, + "loss": 1.3948, + "step": 5802 + }, + { + "epoch": 0.61, + "learning_rate": 7.969958654942704e-06, + "loss": 1.3076, + "step": 5803 + }, + { + "epoch": 0.61, + "learning_rate": 7.966374755083202e-06, + "loss": 1.3838, + "step": 5804 + }, + { + "epoch": 0.61, + "learning_rate": 7.962791127677228e-06, + "loss": 1.4205, + "step": 5805 + }, + { + "epoch": 0.61, + "learning_rate": 7.959207773204899e-06, + "loss": 1.3635, + "step": 5806 + }, + { + "epoch": 0.61, + "learning_rate": 7.955624692146293e-06, + "loss": 1.3299, + "step": 5807 + }, + { + "epoch": 0.61, + "learning_rate": 7.95204188498145e-06, + "loss": 1.4435, + "step": 5808 + }, + { + "epoch": 0.61, + "learning_rate": 7.948459352190372e-06, + "loss": 1.4335, + "step": 5809 + }, + { + "epoch": 0.61, + "learning_rate": 7.944877094253027e-06, + "loss": 1.3391, + "step": 5810 + }, + { + "epoch": 0.61, + "learning_rate": 7.94129511164935e-06, + "loss": 1.2852, + "step": 5811 + }, + { + "epoch": 0.61, + "learning_rate": 7.93771340485923e-06, + "loss": 1.3174, + "step": 5812 + }, + { + "epoch": 0.61, + "learning_rate": 7.934131974362527e-06, + "loss": 1.3415, + "step": 5813 + }, + { + "epoch": 0.61, + "learning_rate": 7.930550820639055e-06, + "loss": 1.2764, + "step": 5814 + }, + { + "epoch": 0.61, + "learning_rate": 7.926969944168603e-06, + "loss": 1.2978, + "step": 5815 + }, + { + "epoch": 0.61, + "learning_rate": 7.923389345430911e-06, + "loss": 1.3046, + "step": 5816 + }, + { + "epoch": 0.61, + "learning_rate": 7.919809024905694e-06, + "loss": 1.3484, + "step": 5817 + }, + { + "epoch": 0.61, + "learning_rate": 7.916228983072614e-06, + "loss": 1.3207, + "step": 5818 + }, + { + "epoch": 0.61, + "learning_rate": 7.912649220411312e-06, + "loss": 1.4289, + "step": 5819 + }, + { + "epoch": 0.61, + "learning_rate": 7.909069737401382e-06, + "loss": 1.4359, + "step": 5820 + }, + { + "epoch": 0.61, + "learning_rate": 7.905490534522384e-06, + "loss": 1.3316, + "step": 5821 + }, + { + "epoch": 0.61, + "learning_rate": 7.901911612253834e-06, + "loss": 1.3112, + "step": 5822 + }, + { + "epoch": 0.61, + "learning_rate": 7.898332971075221e-06, + "loss": 1.3318, + "step": 5823 + }, + { + "epoch": 0.61, + "learning_rate": 7.894754611465992e-06, + "loss": 1.4373, + "step": 5824 + }, + { + "epoch": 0.61, + "learning_rate": 7.891176533905549e-06, + "loss": 1.2938, + "step": 5825 + }, + { + "epoch": 0.61, + "learning_rate": 7.887598738873266e-06, + "loss": 1.3471, + "step": 5826 + }, + { + "epoch": 0.61, + "learning_rate": 7.884021226848478e-06, + "loss": 1.2999, + "step": 5827 + }, + { + "epoch": 0.61, + "learning_rate": 7.880443998310475e-06, + "loss": 1.35, + "step": 5828 + }, + { + "epoch": 0.61, + "learning_rate": 7.876867053738517e-06, + "loss": 1.3307, + "step": 5829 + }, + { + "epoch": 0.61, + "learning_rate": 7.87329039361182e-06, + "loss": 1.393, + "step": 5830 + }, + { + "epoch": 0.61, + "learning_rate": 7.869714018409568e-06, + "loss": 1.2933, + "step": 5831 + }, + { + "epoch": 0.61, + "learning_rate": 7.866137928610903e-06, + "loss": 1.319, + "step": 5832 + }, + { + "epoch": 0.61, + "learning_rate": 7.862562124694925e-06, + "loss": 1.3088, + "step": 5833 + }, + { + "epoch": 0.61, + "learning_rate": 7.858986607140705e-06, + "loss": 1.2941, + "step": 5834 + }, + { + "epoch": 0.61, + "learning_rate": 7.855411376427267e-06, + "loss": 1.3214, + "step": 5835 + }, + { + "epoch": 0.61, + "learning_rate": 7.851836433033602e-06, + "loss": 1.2991, + "step": 5836 + }, + { + "epoch": 0.61, + "learning_rate": 7.848261777438656e-06, + "loss": 1.3117, + "step": 5837 + }, + { + "epoch": 0.61, + "learning_rate": 7.844687410121348e-06, + "loss": 1.2905, + "step": 5838 + }, + { + "epoch": 0.61, + "learning_rate": 7.841113331560548e-06, + "loss": 1.3688, + "step": 5839 + }, + { + "epoch": 0.61, + "learning_rate": 7.837539542235091e-06, + "loss": 1.3987, + "step": 5840 + }, + { + "epoch": 0.61, + "learning_rate": 7.83396604262377e-06, + "loss": 1.2693, + "step": 5841 + }, + { + "epoch": 0.61, + "learning_rate": 7.830392833205348e-06, + "loss": 1.3205, + "step": 5842 + }, + { + "epoch": 0.61, + "learning_rate": 7.826819914458538e-06, + "loss": 1.3325, + "step": 5843 + }, + { + "epoch": 0.61, + "learning_rate": 7.823247286862024e-06, + "loss": 1.3451, + "step": 5844 + }, + { + "epoch": 0.61, + "learning_rate": 7.81967495089444e-06, + "loss": 1.3484, + "step": 5845 + }, + { + "epoch": 0.61, + "learning_rate": 7.816102907034395e-06, + "loss": 1.4949, + "step": 5846 + }, + { + "epoch": 0.61, + "learning_rate": 7.812531155760445e-06, + "loss": 1.4293, + "step": 5847 + }, + { + "epoch": 0.61, + "learning_rate": 7.808959697551113e-06, + "loss": 1.4314, + "step": 5848 + }, + { + "epoch": 0.61, + "learning_rate": 7.805388532884887e-06, + "loss": 1.3188, + "step": 5849 + }, + { + "epoch": 0.61, + "learning_rate": 7.80181766224021e-06, + "loss": 1.4396, + "step": 5850 + }, + { + "epoch": 0.61, + "learning_rate": 7.798247086095484e-06, + "loss": 1.3448, + "step": 5851 + }, + { + "epoch": 0.61, + "learning_rate": 7.794676804929075e-06, + "loss": 1.3591, + "step": 5852 + }, + { + "epoch": 0.61, + "learning_rate": 7.791106819219311e-06, + "loss": 1.3108, + "step": 5853 + }, + { + "epoch": 0.61, + "learning_rate": 7.78753712944448e-06, + "loss": 1.3773, + "step": 5854 + }, + { + "epoch": 0.61, + "learning_rate": 7.783967736082824e-06, + "loss": 1.3313, + "step": 5855 + }, + { + "epoch": 0.61, + "learning_rate": 7.780398639612551e-06, + "loss": 1.3635, + "step": 5856 + }, + { + "epoch": 0.61, + "learning_rate": 7.776829840511833e-06, + "loss": 1.3225, + "step": 5857 + }, + { + "epoch": 0.61, + "learning_rate": 7.773261339258792e-06, + "loss": 1.3142, + "step": 5858 + }, + { + "epoch": 0.61, + "learning_rate": 7.769693136331519e-06, + "loss": 1.3337, + "step": 5859 + }, + { + "epoch": 0.61, + "learning_rate": 7.766125232208057e-06, + "loss": 1.5289, + "step": 5860 + }, + { + "epoch": 0.61, + "learning_rate": 7.762557627366418e-06, + "loss": 1.573, + "step": 5861 + }, + { + "epoch": 0.61, + "learning_rate": 7.758990322284568e-06, + "loss": 1.322, + "step": 5862 + }, + { + "epoch": 0.61, + "learning_rate": 7.755423317440432e-06, + "loss": 1.3281, + "step": 5863 + }, + { + "epoch": 0.61, + "learning_rate": 7.751856613311899e-06, + "loss": 1.3405, + "step": 5864 + }, + { + "epoch": 0.62, + "learning_rate": 7.748290210376817e-06, + "loss": 1.3083, + "step": 5865 + }, + { + "epoch": 0.62, + "learning_rate": 7.744724109112991e-06, + "loss": 1.3587, + "step": 5866 + }, + { + "epoch": 0.62, + "learning_rate": 7.741158309998188e-06, + "loss": 1.3204, + "step": 5867 + }, + { + "epoch": 0.62, + "learning_rate": 7.73759281351013e-06, + "loss": 1.343, + "step": 5868 + }, + { + "epoch": 0.62, + "learning_rate": 7.734027620126507e-06, + "loss": 1.2874, + "step": 5869 + }, + { + "epoch": 0.62, + "learning_rate": 7.73046273032496e-06, + "loss": 1.3306, + "step": 5870 + }, + { + "epoch": 0.62, + "learning_rate": 7.72689814458309e-06, + "loss": 1.3958, + "step": 5871 + }, + { + "epoch": 0.62, + "learning_rate": 7.723333863378465e-06, + "loss": 1.3135, + "step": 5872 + }, + { + "epoch": 0.62, + "learning_rate": 7.719769887188608e-06, + "loss": 1.3241, + "step": 5873 + }, + { + "epoch": 0.62, + "learning_rate": 7.716206216490995e-06, + "loss": 1.3487, + "step": 5874 + }, + { + "epoch": 0.62, + "learning_rate": 7.712642851763067e-06, + "loss": 1.0263, + "step": 5875 + }, + { + "epoch": 0.62, + "learning_rate": 7.709079793482228e-06, + "loss": 1.4238, + "step": 5876 + }, + { + "epoch": 0.62, + "learning_rate": 7.705517042125833e-06, + "loss": 1.3284, + "step": 5877 + }, + { + "epoch": 0.62, + "learning_rate": 7.701954598171199e-06, + "loss": 1.2965, + "step": 5878 + }, + { + "epoch": 0.62, + "learning_rate": 7.698392462095601e-06, + "loss": 1.3578, + "step": 5879 + }, + { + "epoch": 0.62, + "learning_rate": 7.694830634376278e-06, + "loss": 1.3711, + "step": 5880 + }, + { + "epoch": 0.62, + "learning_rate": 7.69126911549042e-06, + "loss": 1.3274, + "step": 5881 + }, + { + "epoch": 0.62, + "learning_rate": 7.687707905915181e-06, + "loss": 1.4208, + "step": 5882 + }, + { + "epoch": 0.62, + "learning_rate": 7.684147006127665e-06, + "loss": 1.3478, + "step": 5883 + }, + { + "epoch": 0.62, + "learning_rate": 7.68058641660495e-06, + "loss": 1.2997, + "step": 5884 + }, + { + "epoch": 0.62, + "learning_rate": 7.67702613782406e-06, + "loss": 1.2981, + "step": 5885 + }, + { + "epoch": 0.62, + "learning_rate": 7.67346617026198e-06, + "loss": 1.3834, + "step": 5886 + }, + { + "epoch": 0.62, + "learning_rate": 7.669906514395654e-06, + "loss": 1.3585, + "step": 5887 + }, + { + "epoch": 0.62, + "learning_rate": 7.666347170701986e-06, + "loss": 1.3282, + "step": 5888 + }, + { + "epoch": 0.62, + "learning_rate": 7.662788139657838e-06, + "loss": 1.3397, + "step": 5889 + }, + { + "epoch": 0.62, + "learning_rate": 7.659229421740024e-06, + "loss": 1.3367, + "step": 5890 + }, + { + "epoch": 0.62, + "learning_rate": 7.655671017425322e-06, + "loss": 1.3497, + "step": 5891 + }, + { + "epoch": 0.62, + "learning_rate": 7.65211292719047e-06, + "loss": 1.3661, + "step": 5892 + }, + { + "epoch": 0.62, + "learning_rate": 7.64855515151216e-06, + "loss": 1.2793, + "step": 5893 + }, + { + "epoch": 0.62, + "learning_rate": 7.644997690867037e-06, + "loss": 1.3288, + "step": 5894 + }, + { + "epoch": 0.62, + "learning_rate": 7.641440545731717e-06, + "loss": 1.3877, + "step": 5895 + }, + { + "epoch": 0.62, + "learning_rate": 7.637883716582764e-06, + "loss": 1.4467, + "step": 5896 + }, + { + "epoch": 0.62, + "learning_rate": 7.634327203896698e-06, + "loss": 1.304, + "step": 5897 + }, + { + "epoch": 0.62, + "learning_rate": 7.630771008150002e-06, + "loss": 1.374, + "step": 5898 + }, + { + "epoch": 0.62, + "learning_rate": 7.627215129819118e-06, + "loss": 1.3893, + "step": 5899 + }, + { + "epoch": 0.62, + "learning_rate": 7.623659569380439e-06, + "loss": 1.325, + "step": 5900 + }, + { + "epoch": 0.62, + "learning_rate": 7.620104327310319e-06, + "loss": 1.2495, + "step": 5901 + }, + { + "epoch": 0.62, + "learning_rate": 7.616549404085068e-06, + "loss": 1.4034, + "step": 5902 + }, + { + "epoch": 0.62, + "learning_rate": 7.61299480018096e-06, + "loss": 1.2758, + "step": 5903 + }, + { + "epoch": 0.62, + "learning_rate": 7.609440516074215e-06, + "loss": 1.4203, + "step": 5904 + }, + { + "epoch": 0.62, + "learning_rate": 7.605886552241017e-06, + "loss": 1.3162, + "step": 5905 + }, + { + "epoch": 0.62, + "learning_rate": 7.602332909157505e-06, + "loss": 1.3368, + "step": 5906 + }, + { + "epoch": 0.62, + "learning_rate": 7.598779587299778e-06, + "loss": 1.314, + "step": 5907 + }, + { + "epoch": 0.62, + "learning_rate": 7.59522658714389e-06, + "loss": 1.3332, + "step": 5908 + }, + { + "epoch": 0.62, + "learning_rate": 7.5916739091658505e-06, + "loss": 1.3513, + "step": 5909 + }, + { + "epoch": 0.62, + "learning_rate": 7.5881215538416255e-06, + "loss": 1.3767, + "step": 5910 + }, + { + "epoch": 0.62, + "learning_rate": 7.5845695216471426e-06, + "loss": 1.3651, + "step": 5911 + }, + { + "epoch": 0.62, + "learning_rate": 7.581017813058283e-06, + "loss": 1.2676, + "step": 5912 + }, + { + "epoch": 0.62, + "learning_rate": 7.57746642855088e-06, + "loss": 1.3509, + "step": 5913 + }, + { + "epoch": 0.62, + "learning_rate": 7.5739153686007305e-06, + "loss": 1.2854, + "step": 5914 + }, + { + "epoch": 0.62, + "learning_rate": 7.570364633683586e-06, + "loss": 1.4041, + "step": 5915 + }, + { + "epoch": 0.62, + "learning_rate": 7.5668142242751545e-06, + "loss": 1.3218, + "step": 5916 + }, + { + "epoch": 0.62, + "learning_rate": 7.563264140851095e-06, + "loss": 1.398, + "step": 5917 + }, + { + "epoch": 0.62, + "learning_rate": 7.559714383887033e-06, + "loss": 1.3495, + "step": 5918 + }, + { + "epoch": 0.62, + "learning_rate": 7.556164953858543e-06, + "loss": 1.365, + "step": 5919 + }, + { + "epoch": 0.62, + "learning_rate": 7.552615851241157e-06, + "loss": 1.4611, + "step": 5920 + }, + { + "epoch": 0.62, + "learning_rate": 7.549067076510361e-06, + "loss": 1.4031, + "step": 5921 + }, + { + "epoch": 0.62, + "learning_rate": 7.545518630141605e-06, + "loss": 1.2745, + "step": 5922 + }, + { + "epoch": 0.62, + "learning_rate": 7.541970512610286e-06, + "loss": 1.3435, + "step": 5923 + }, + { + "epoch": 0.62, + "learning_rate": 7.538422724391761e-06, + "loss": 1.3433, + "step": 5924 + }, + { + "epoch": 0.62, + "learning_rate": 7.534875265961341e-06, + "loss": 1.3605, + "step": 5925 + }, + { + "epoch": 0.62, + "learning_rate": 7.5313281377942985e-06, + "loss": 1.3896, + "step": 5926 + }, + { + "epoch": 0.62, + "learning_rate": 7.527781340365854e-06, + "loss": 1.3922, + "step": 5927 + }, + { + "epoch": 0.62, + "learning_rate": 7.524234874151189e-06, + "loss": 1.3305, + "step": 5928 + }, + { + "epoch": 0.62, + "learning_rate": 7.520688739625436e-06, + "loss": 1.3117, + "step": 5929 + }, + { + "epoch": 0.62, + "learning_rate": 7.51714293726369e-06, + "loss": 1.3581, + "step": 5930 + }, + { + "epoch": 0.62, + "learning_rate": 7.5135974675409955e-06, + "loss": 1.3973, + "step": 5931 + }, + { + "epoch": 0.62, + "learning_rate": 7.510052330932354e-06, + "loss": 1.3499, + "step": 5932 + }, + { + "epoch": 0.62, + "learning_rate": 7.506507527912721e-06, + "loss": 1.3068, + "step": 5933 + }, + { + "epoch": 0.62, + "learning_rate": 7.502963058957014e-06, + "loss": 1.3689, + "step": 5934 + }, + { + "epoch": 0.62, + "learning_rate": 7.499418924540096e-06, + "loss": 1.3356, + "step": 5935 + }, + { + "epoch": 0.62, + "learning_rate": 7.495875125136793e-06, + "loss": 1.2593, + "step": 5936 + }, + { + "epoch": 0.62, + "learning_rate": 7.492331661221881e-06, + "loss": 1.272, + "step": 5937 + }, + { + "epoch": 0.62, + "learning_rate": 7.488788533270093e-06, + "loss": 1.3552, + "step": 5938 + }, + { + "epoch": 0.62, + "learning_rate": 7.485245741756121e-06, + "loss": 1.3425, + "step": 5939 + }, + { + "epoch": 0.62, + "learning_rate": 7.481703287154602e-06, + "loss": 1.3694, + "step": 5940 + }, + { + "epoch": 0.62, + "learning_rate": 7.478161169940139e-06, + "loss": 1.3281, + "step": 5941 + }, + { + "epoch": 0.62, + "learning_rate": 7.4746193905872825e-06, + "loss": 1.3109, + "step": 5942 + }, + { + "epoch": 0.62, + "learning_rate": 7.47107794957054e-06, + "loss": 1.5121, + "step": 5943 + }, + { + "epoch": 0.62, + "learning_rate": 7.467536847364372e-06, + "loss": 1.4472, + "step": 5944 + }, + { + "epoch": 0.62, + "learning_rate": 7.463996084443198e-06, + "loss": 1.4615, + "step": 5945 + }, + { + "epoch": 0.62, + "learning_rate": 7.460455661281389e-06, + "loss": 1.3764, + "step": 5946 + }, + { + "epoch": 0.62, + "learning_rate": 7.45691557835327e-06, + "loss": 1.3091, + "step": 5947 + }, + { + "epoch": 0.62, + "learning_rate": 7.4533758361331185e-06, + "loss": 1.1841, + "step": 5948 + }, + { + "epoch": 0.62, + "learning_rate": 7.449836435095175e-06, + "loss": 1.3345, + "step": 5949 + }, + { + "epoch": 0.62, + "learning_rate": 7.446297375713622e-06, + "loss": 1.3573, + "step": 5950 + }, + { + "epoch": 0.62, + "learning_rate": 7.442758658462608e-06, + "loss": 1.3161, + "step": 5951 + }, + { + "epoch": 0.62, + "learning_rate": 7.4392202838162245e-06, + "loss": 1.3089, + "step": 5952 + }, + { + "epoch": 0.62, + "learning_rate": 7.435682252248528e-06, + "loss": 1.3069, + "step": 5953 + }, + { + "epoch": 0.62, + "learning_rate": 7.4321445642335234e-06, + "loss": 1.2969, + "step": 5954 + }, + { + "epoch": 0.62, + "learning_rate": 7.428607220245165e-06, + "loss": 1.4706, + "step": 5955 + }, + { + "epoch": 0.62, + "learning_rate": 7.42507022075737e-06, + "loss": 1.3028, + "step": 5956 + }, + { + "epoch": 0.62, + "learning_rate": 7.421533566244006e-06, + "loss": 1.2786, + "step": 5957 + }, + { + "epoch": 0.62, + "learning_rate": 7.417997257178893e-06, + "loss": 1.3534, + "step": 5958 + }, + { + "epoch": 0.62, + "learning_rate": 7.414461294035804e-06, + "loss": 1.2829, + "step": 5959 + }, + { + "epoch": 0.62, + "learning_rate": 7.410925677288467e-06, + "loss": 1.3626, + "step": 5960 + }, + { + "epoch": 0.63, + "learning_rate": 7.407390407410566e-06, + "loss": 1.4531, + "step": 5961 + }, + { + "epoch": 0.63, + "learning_rate": 7.4038554848757375e-06, + "loss": 1.3549, + "step": 5962 + }, + { + "epoch": 0.63, + "learning_rate": 7.400320910157563e-06, + "loss": 1.3407, + "step": 5963 + }, + { + "epoch": 0.63, + "learning_rate": 7.396786683729595e-06, + "loss": 1.2736, + "step": 5964 + }, + { + "epoch": 0.63, + "learning_rate": 7.393252806065323e-06, + "loss": 1.3377, + "step": 5965 + }, + { + "epoch": 0.63, + "learning_rate": 7.389719277638196e-06, + "loss": 1.3479, + "step": 5966 + }, + { + "epoch": 0.63, + "learning_rate": 7.3861860989216175e-06, + "loss": 1.3605, + "step": 5967 + }, + { + "epoch": 0.63, + "learning_rate": 7.382653270388942e-06, + "loss": 1.3175, + "step": 5968 + }, + { + "epoch": 0.63, + "learning_rate": 7.379120792513477e-06, + "loss": 1.3072, + "step": 5969 + }, + { + "epoch": 0.63, + "learning_rate": 7.375588665768485e-06, + "loss": 1.3224, + "step": 5970 + }, + { + "epoch": 0.63, + "eval_loss": 1.4110088348388672, + "eval_runtime": 77.5326, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 5970 + }, + { + "epoch": 0.63, + "learning_rate": 7.37205689062718e-06, + "loss": 1.3491, + "step": 5971 + }, + { + "epoch": 0.63, + "learning_rate": 7.368525467562728e-06, + "loss": 1.3289, + "step": 5972 + }, + { + "epoch": 0.63, + "learning_rate": 7.364994397048251e-06, + "loss": 1.3362, + "step": 5973 + }, + { + "epoch": 0.63, + "learning_rate": 7.36146367955682e-06, + "loss": 1.3754, + "step": 5974 + }, + { + "epoch": 0.63, + "learning_rate": 7.3579333155614585e-06, + "loss": 1.3159, + "step": 5975 + }, + { + "epoch": 0.63, + "learning_rate": 7.354403305535149e-06, + "loss": 1.4366, + "step": 5976 + }, + { + "epoch": 0.63, + "learning_rate": 7.350873649950822e-06, + "loss": 1.3243, + "step": 5977 + }, + { + "epoch": 0.63, + "learning_rate": 7.347344349281358e-06, + "loss": 1.2911, + "step": 5978 + }, + { + "epoch": 0.63, + "learning_rate": 7.34381540399959e-06, + "loss": 1.338, + "step": 5979 + }, + { + "epoch": 0.63, + "learning_rate": 7.340286814578312e-06, + "loss": 1.3241, + "step": 5980 + }, + { + "epoch": 0.63, + "learning_rate": 7.336758581490263e-06, + "loss": 1.3427, + "step": 5981 + }, + { + "epoch": 0.63, + "learning_rate": 7.333230705208134e-06, + "loss": 1.3328, + "step": 5982 + }, + { + "epoch": 0.63, + "learning_rate": 7.3297031862045676e-06, + "loss": 1.2857, + "step": 5983 + }, + { + "epoch": 0.63, + "learning_rate": 7.3261760249521655e-06, + "loss": 1.9065, + "step": 5984 + }, + { + "epoch": 0.63, + "learning_rate": 7.322649221923473e-06, + "loss": 1.3797, + "step": 5985 + }, + { + "epoch": 0.63, + "learning_rate": 7.3191227775909925e-06, + "loss": 1.2343, + "step": 5986 + }, + { + "epoch": 0.63, + "learning_rate": 7.315596692427178e-06, + "loss": 1.3479, + "step": 5987 + }, + { + "epoch": 0.63, + "learning_rate": 7.312070966904432e-06, + "loss": 1.3226, + "step": 5988 + }, + { + "epoch": 0.63, + "learning_rate": 7.308545601495114e-06, + "loss": 1.3329, + "step": 5989 + }, + { + "epoch": 0.63, + "learning_rate": 7.305020596671528e-06, + "loss": 1.3285, + "step": 5990 + }, + { + "epoch": 0.63, + "learning_rate": 7.301495952905939e-06, + "loss": 1.3635, + "step": 5991 + }, + { + "epoch": 0.63, + "learning_rate": 7.297971670670556e-06, + "loss": 1.3343, + "step": 5992 + }, + { + "epoch": 0.63, + "learning_rate": 7.294447750437543e-06, + "loss": 1.3943, + "step": 5993 + }, + { + "epoch": 0.63, + "learning_rate": 7.290924192679014e-06, + "loss": 1.4601, + "step": 5994 + }, + { + "epoch": 0.63, + "learning_rate": 7.287400997867036e-06, + "loss": 1.3813, + "step": 5995 + }, + { + "epoch": 0.63, + "learning_rate": 7.2838781664736266e-06, + "loss": 1.3505, + "step": 5996 + }, + { + "epoch": 0.63, + "learning_rate": 7.2803556989707555e-06, + "loss": 1.3062, + "step": 5997 + }, + { + "epoch": 0.63, + "learning_rate": 7.276833595830338e-06, + "loss": 1.4504, + "step": 5998 + }, + { + "epoch": 0.63, + "learning_rate": 7.273311857524252e-06, + "loss": 1.4935, + "step": 5999 + }, + { + "epoch": 0.63, + "learning_rate": 7.269790484524317e-06, + "loss": 1.296, + "step": 6000 + }, + { + "epoch": 0.63, + "learning_rate": 7.266269477302308e-06, + "loss": 1.3469, + "step": 6001 + }, + { + "epoch": 0.63, + "learning_rate": 7.262748836329944e-06, + "loss": 1.3586, + "step": 6002 + }, + { + "epoch": 0.63, + "learning_rate": 7.259228562078908e-06, + "loss": 1.3643, + "step": 6003 + }, + { + "epoch": 0.63, + "learning_rate": 7.255708655020821e-06, + "loss": 1.3096, + "step": 6004 + }, + { + "epoch": 0.63, + "learning_rate": 7.252189115627264e-06, + "loss": 1.3163, + "step": 6005 + }, + { + "epoch": 0.63, + "learning_rate": 7.2486699443697595e-06, + "loss": 1.3526, + "step": 6006 + }, + { + "epoch": 0.63, + "learning_rate": 7.245151141719793e-06, + "loss": 1.401, + "step": 6007 + }, + { + "epoch": 0.63, + "learning_rate": 7.241632708148788e-06, + "loss": 1.2651, + "step": 6008 + }, + { + "epoch": 0.63, + "learning_rate": 7.238114644128124e-06, + "loss": 1.348, + "step": 6009 + }, + { + "epoch": 0.63, + "learning_rate": 7.234596950129137e-06, + "loss": 1.6934, + "step": 6010 + }, + { + "epoch": 0.63, + "learning_rate": 7.231079626623103e-06, + "loss": 1.3382, + "step": 6011 + }, + { + "epoch": 0.63, + "learning_rate": 7.227562674081254e-06, + "loss": 1.2925, + "step": 6012 + }, + { + "epoch": 0.63, + "learning_rate": 7.22404609297477e-06, + "loss": 1.3365, + "step": 6013 + }, + { + "epoch": 0.63, + "learning_rate": 7.220529883774785e-06, + "loss": 1.3169, + "step": 6014 + }, + { + "epoch": 0.63, + "learning_rate": 7.217014046952379e-06, + "loss": 1.319, + "step": 6015 + }, + { + "epoch": 0.63, + "learning_rate": 7.2134985829785846e-06, + "loss": 1.4049, + "step": 6016 + }, + { + "epoch": 0.63, + "learning_rate": 7.209983492324382e-06, + "loss": 1.2947, + "step": 6017 + }, + { + "epoch": 0.63, + "learning_rate": 7.206468775460704e-06, + "loss": 1.2854, + "step": 6018 + }, + { + "epoch": 0.63, + "learning_rate": 7.202954432858436e-06, + "loss": 1.3381, + "step": 6019 + }, + { + "epoch": 0.63, + "learning_rate": 7.199440464988403e-06, + "loss": 1.3912, + "step": 6020 + }, + { + "epoch": 0.63, + "learning_rate": 7.195926872321391e-06, + "loss": 1.384, + "step": 6021 + }, + { + "epoch": 0.63, + "learning_rate": 7.192413655328129e-06, + "loss": 1.2909, + "step": 6022 + }, + { + "epoch": 0.63, + "learning_rate": 7.188900814479299e-06, + "loss": 1.2951, + "step": 6023 + }, + { + "epoch": 0.63, + "learning_rate": 7.185388350245532e-06, + "loss": 1.2655, + "step": 6024 + }, + { + "epoch": 0.63, + "learning_rate": 7.1818762630974035e-06, + "loss": 1.3288, + "step": 6025 + }, + { + "epoch": 0.63, + "learning_rate": 7.17836455350545e-06, + "loss": 1.2873, + "step": 6026 + }, + { + "epoch": 0.63, + "learning_rate": 7.174853221940146e-06, + "loss": 1.3027, + "step": 6027 + }, + { + "epoch": 0.63, + "learning_rate": 7.17134226887192e-06, + "loss": 1.3273, + "step": 6028 + }, + { + "epoch": 0.63, + "learning_rate": 7.167831694771149e-06, + "loss": 1.3096, + "step": 6029 + }, + { + "epoch": 0.63, + "learning_rate": 7.1643215001081625e-06, + "loss": 1.2904, + "step": 6030 + }, + { + "epoch": 0.63, + "learning_rate": 7.160811685353234e-06, + "loss": 1.2977, + "step": 6031 + }, + { + "epoch": 0.63, + "learning_rate": 7.157302250976588e-06, + "loss": 1.3281, + "step": 6032 + }, + { + "epoch": 0.63, + "learning_rate": 7.1537931974483996e-06, + "loss": 1.3831, + "step": 6033 + }, + { + "epoch": 0.63, + "learning_rate": 7.150284525238794e-06, + "loss": 1.3173, + "step": 6034 + }, + { + "epoch": 0.63, + "learning_rate": 7.146776234817841e-06, + "loss": 1.4148, + "step": 6035 + }, + { + "epoch": 0.63, + "learning_rate": 7.143268326655557e-06, + "loss": 1.3381, + "step": 6036 + }, + { + "epoch": 0.63, + "learning_rate": 7.13976080122192e-06, + "loss": 1.3221, + "step": 6037 + }, + { + "epoch": 0.63, + "learning_rate": 7.136253658986843e-06, + "loss": 1.4373, + "step": 6038 + }, + { + "epoch": 0.63, + "learning_rate": 7.132746900420195e-06, + "loss": 1.3758, + "step": 6039 + }, + { + "epoch": 0.63, + "learning_rate": 7.129240525991788e-06, + "loss": 1.3964, + "step": 6040 + }, + { + "epoch": 0.63, + "learning_rate": 7.125734536171391e-06, + "loss": 1.3136, + "step": 6041 + }, + { + "epoch": 0.63, + "learning_rate": 7.122228931428715e-06, + "loss": 1.2195, + "step": 6042 + }, + { + "epoch": 0.63, + "learning_rate": 7.11872371223342e-06, + "loss": 1.3842, + "step": 6043 + }, + { + "epoch": 0.63, + "learning_rate": 7.115218879055113e-06, + "loss": 1.3369, + "step": 6044 + }, + { + "epoch": 0.63, + "learning_rate": 7.111714432363356e-06, + "loss": 1.2704, + "step": 6045 + }, + { + "epoch": 0.63, + "learning_rate": 7.108210372627653e-06, + "loss": 1.307, + "step": 6046 + }, + { + "epoch": 0.63, + "learning_rate": 7.104706700317459e-06, + "loss": 1.3024, + "step": 6047 + }, + { + "epoch": 0.63, + "learning_rate": 7.1012034159021715e-06, + "loss": 1.4157, + "step": 6048 + }, + { + "epoch": 0.63, + "learning_rate": 7.0977005198511475e-06, + "loss": 1.2314, + "step": 6049 + }, + { + "epoch": 0.63, + "learning_rate": 7.09419801263368e-06, + "loss": 1.4304, + "step": 6050 + }, + { + "epoch": 0.63, + "learning_rate": 7.090695894719019e-06, + "loss": 1.3085, + "step": 6051 + }, + { + "epoch": 0.63, + "learning_rate": 7.0871941665763525e-06, + "loss": 1.367, + "step": 6052 + }, + { + "epoch": 0.63, + "learning_rate": 7.083692828674827e-06, + "loss": 1.2913, + "step": 6053 + }, + { + "epoch": 0.63, + "learning_rate": 7.080191881483531e-06, + "loss": 1.3751, + "step": 6054 + }, + { + "epoch": 0.63, + "learning_rate": 7.0766913254714985e-06, + "loss": 1.3178, + "step": 6055 + }, + { + "epoch": 0.64, + "learning_rate": 7.07319116110772e-06, + "loss": 1.3182, + "step": 6056 + }, + { + "epoch": 0.64, + "learning_rate": 7.069691388861122e-06, + "loss": 1.373, + "step": 6057 + }, + { + "epoch": 0.64, + "learning_rate": 7.066192009200588e-06, + "loss": 1.3235, + "step": 6058 + }, + { + "epoch": 0.64, + "learning_rate": 7.0626930225949395e-06, + "loss": 1.3765, + "step": 6059 + }, + { + "epoch": 0.64, + "learning_rate": 7.0591944295129565e-06, + "loss": 1.4408, + "step": 6060 + }, + { + "epoch": 0.64, + "learning_rate": 7.055696230423359e-06, + "loss": 1.3271, + "step": 6061 + }, + { + "epoch": 0.64, + "learning_rate": 7.052198425794814e-06, + "loss": 1.2194, + "step": 6062 + }, + { + "epoch": 0.64, + "learning_rate": 7.048701016095938e-06, + "loss": 1.3707, + "step": 6063 + }, + { + "epoch": 0.64, + "learning_rate": 7.045204001795296e-06, + "loss": 1.3878, + "step": 6064 + }, + { + "epoch": 0.64, + "learning_rate": 7.041707383361396e-06, + "loss": 1.3674, + "step": 6065 + }, + { + "epoch": 0.64, + "learning_rate": 7.038211161262697e-06, + "loss": 1.4525, + "step": 6066 + }, + { + "epoch": 0.64, + "learning_rate": 7.034715335967599e-06, + "loss": 1.3801, + "step": 6067 + }, + { + "epoch": 0.64, + "learning_rate": 7.031219907944458e-06, + "loss": 1.4855, + "step": 6068 + }, + { + "epoch": 0.64, + "learning_rate": 7.027724877661568e-06, + "loss": 1.3659, + "step": 6069 + }, + { + "epoch": 0.64, + "learning_rate": 7.024230245587176e-06, + "loss": 1.3649, + "step": 6070 + }, + { + "epoch": 0.64, + "learning_rate": 7.020736012189467e-06, + "loss": 1.2629, + "step": 6071 + }, + { + "epoch": 0.64, + "learning_rate": 7.017242177936586e-06, + "loss": 1.2474, + "step": 6072 + }, + { + "epoch": 0.64, + "learning_rate": 7.013748743296614e-06, + "loss": 1.45, + "step": 6073 + }, + { + "epoch": 0.64, + "learning_rate": 7.010255708737581e-06, + "loss": 1.3624, + "step": 6074 + }, + { + "epoch": 0.64, + "learning_rate": 7.006763074727461e-06, + "loss": 0.9335, + "step": 6075 + }, + { + "epoch": 0.64, + "learning_rate": 7.0032708417341835e-06, + "loss": 0.6376, + "step": 6076 + }, + { + "epoch": 0.64, + "learning_rate": 6.999779010225613e-06, + "loss": 0.7882, + "step": 6077 + }, + { + "epoch": 0.64, + "learning_rate": 6.996287580669567e-06, + "loss": 1.3001, + "step": 6078 + }, + { + "epoch": 0.64, + "learning_rate": 6.9927965535338085e-06, + "loss": 1.323, + "step": 6079 + }, + { + "epoch": 0.64, + "learning_rate": 6.989305929286043e-06, + "loss": 1.3478, + "step": 6080 + }, + { + "epoch": 0.64, + "learning_rate": 6.985815708393928e-06, + "loss": 1.319, + "step": 6081 + }, + { + "epoch": 0.64, + "learning_rate": 6.9823258913250566e-06, + "loss": 1.3458, + "step": 6082 + }, + { + "epoch": 0.64, + "learning_rate": 6.978836478546985e-06, + "loss": 1.2481, + "step": 6083 + }, + { + "epoch": 0.64, + "learning_rate": 6.975347470527195e-06, + "loss": 1.4051, + "step": 6084 + }, + { + "epoch": 0.64, + "learning_rate": 6.97185886773313e-06, + "loss": 1.3705, + "step": 6085 + }, + { + "epoch": 0.64, + "learning_rate": 6.9683706706321676e-06, + "loss": 1.3415, + "step": 6086 + }, + { + "epoch": 0.64, + "learning_rate": 6.964882879691643e-06, + "loss": 1.3462, + "step": 6087 + }, + { + "epoch": 0.64, + "learning_rate": 6.961395495378829e-06, + "loss": 1.2974, + "step": 6088 + }, + { + "epoch": 0.64, + "learning_rate": 6.957908518160943e-06, + "loss": 1.3353, + "step": 6089 + }, + { + "epoch": 0.64, + "learning_rate": 6.95442194850515e-06, + "loss": 1.3073, + "step": 6090 + }, + { + "epoch": 0.64, + "learning_rate": 6.9509357868785636e-06, + "loss": 1.352, + "step": 6091 + }, + { + "epoch": 0.64, + "learning_rate": 6.9474500337482396e-06, + "loss": 1.2771, + "step": 6092 + }, + { + "epoch": 0.64, + "learning_rate": 6.943964689581177e-06, + "loss": 1.2925, + "step": 6093 + }, + { + "epoch": 0.64, + "learning_rate": 6.940479754844322e-06, + "loss": 1.2967, + "step": 6094 + }, + { + "epoch": 0.64, + "learning_rate": 6.93699523000457e-06, + "loss": 1.5839, + "step": 6095 + }, + { + "epoch": 0.64, + "learning_rate": 6.933511115528757e-06, + "loss": 1.3051, + "step": 6096 + }, + { + "epoch": 0.64, + "learning_rate": 6.930027411883664e-06, + "loss": 1.5344, + "step": 6097 + }, + { + "epoch": 0.64, + "learning_rate": 6.926544119536014e-06, + "loss": 1.3938, + "step": 6098 + }, + { + "epoch": 0.64, + "learning_rate": 6.923061238952484e-06, + "loss": 1.3504, + "step": 6099 + }, + { + "epoch": 0.64, + "learning_rate": 6.919578770599689e-06, + "loss": 1.3618, + "step": 6100 + }, + { + "epoch": 0.64, + "learning_rate": 6.916096714944187e-06, + "loss": 1.3811, + "step": 6101 + }, + { + "epoch": 0.64, + "learning_rate": 6.912615072452491e-06, + "loss": 1.2673, + "step": 6102 + }, + { + "epoch": 0.64, + "learning_rate": 6.909133843591046e-06, + "loss": 1.3661, + "step": 6103 + }, + { + "epoch": 0.64, + "learning_rate": 6.905653028826249e-06, + "loss": 1.3811, + "step": 6104 + }, + { + "epoch": 0.64, + "learning_rate": 6.902172628624437e-06, + "loss": 1.3399, + "step": 6105 + }, + { + "epoch": 0.64, + "learning_rate": 6.8986926434519e-06, + "loss": 1.281, + "step": 6106 + }, + { + "epoch": 0.64, + "learning_rate": 6.895213073774862e-06, + "loss": 1.3053, + "step": 6107 + }, + { + "epoch": 0.64, + "learning_rate": 6.891733920059498e-06, + "loss": 1.4573, + "step": 6108 + }, + { + "epoch": 0.64, + "learning_rate": 6.8882551827719215e-06, + "loss": 1.355, + "step": 6109 + }, + { + "epoch": 0.64, + "learning_rate": 6.8847768623782e-06, + "loss": 1.3304, + "step": 6110 + }, + { + "epoch": 0.64, + "learning_rate": 6.881298959344335e-06, + "loss": 1.4039, + "step": 6111 + }, + { + "epoch": 0.64, + "learning_rate": 6.877821474136277e-06, + "loss": 1.381, + "step": 6112 + }, + { + "epoch": 0.64, + "learning_rate": 6.874344407219917e-06, + "loss": 1.3503, + "step": 6113 + }, + { + "epoch": 0.64, + "learning_rate": 6.870867759061099e-06, + "loss": 1.2679, + "step": 6114 + }, + { + "epoch": 0.64, + "learning_rate": 6.8673915301256e-06, + "loss": 1.3286, + "step": 6115 + }, + { + "epoch": 0.64, + "learning_rate": 6.863915720879146e-06, + "loss": 1.3528, + "step": 6116 + }, + { + "epoch": 0.64, + "learning_rate": 6.8604403317874055e-06, + "loss": 1.3502, + "step": 6117 + }, + { + "epoch": 0.64, + "learning_rate": 6.856965363315993e-06, + "loss": 1.3507, + "step": 6118 + }, + { + "epoch": 0.64, + "learning_rate": 6.853490815930464e-06, + "loss": 1.2153, + "step": 6119 + }, + { + "epoch": 0.64, + "learning_rate": 6.850016690096319e-06, + "loss": 1.2435, + "step": 6120 + }, + { + "epoch": 0.64, + "learning_rate": 6.846542986279e-06, + "loss": 1.3418, + "step": 6121 + }, + { + "epoch": 0.64, + "learning_rate": 6.843069704943896e-06, + "loss": 1.371, + "step": 6122 + }, + { + "epoch": 0.64, + "learning_rate": 6.8395968465563375e-06, + "loss": 1.1737, + "step": 6123 + }, + { + "epoch": 0.64, + "learning_rate": 6.836124411581598e-06, + "loss": 1.3402, + "step": 6124 + }, + { + "epoch": 0.64, + "learning_rate": 6.8326524004848924e-06, + "loss": 1.3482, + "step": 6125 + }, + { + "epoch": 0.64, + "learning_rate": 6.8291808137313845e-06, + "loss": 1.4585, + "step": 6126 + }, + { + "epoch": 0.64, + "learning_rate": 6.825709651786176e-06, + "loss": 1.2848, + "step": 6127 + }, + { + "epoch": 0.64, + "learning_rate": 6.822238915114312e-06, + "loss": 1.2932, + "step": 6128 + }, + { + "epoch": 0.64, + "learning_rate": 6.818768604180785e-06, + "loss": 1.3124, + "step": 6129 + }, + { + "epoch": 0.64, + "learning_rate": 6.815298719450525e-06, + "loss": 1.2843, + "step": 6130 + }, + { + "epoch": 0.64, + "learning_rate": 6.811829261388409e-06, + "loss": 1.3024, + "step": 6131 + }, + { + "epoch": 0.64, + "learning_rate": 6.808360230459252e-06, + "loss": 1.3612, + "step": 6132 + }, + { + "epoch": 0.64, + "learning_rate": 6.804891627127821e-06, + "loss": 1.3005, + "step": 6133 + }, + { + "epoch": 0.64, + "learning_rate": 6.8014234518588154e-06, + "loss": 1.2614, + "step": 6134 + }, + { + "epoch": 0.64, + "learning_rate": 6.7979557051168835e-06, + "loss": 1.3717, + "step": 6135 + }, + { + "epoch": 0.64, + "learning_rate": 6.794488387366609e-06, + "loss": 1.3873, + "step": 6136 + }, + { + "epoch": 0.64, + "learning_rate": 6.791021499072532e-06, + "loss": 1.2955, + "step": 6137 + }, + { + "epoch": 0.64, + "learning_rate": 6.787555040699121e-06, + "loss": 1.4217, + "step": 6138 + }, + { + "epoch": 0.64, + "learning_rate": 6.784089012710793e-06, + "loss": 1.3805, + "step": 6139 + }, + { + "epoch": 0.64, + "learning_rate": 6.7806234155719055e-06, + "loss": 1.3982, + "step": 6140 + }, + { + "epoch": 0.64, + "learning_rate": 6.7771582497467635e-06, + "loss": 1.4, + "step": 6141 + }, + { + "epoch": 0.64, + "learning_rate": 6.773693515699607e-06, + "loss": 1.439, + "step": 6142 + }, + { + "epoch": 0.64, + "learning_rate": 6.7702292138946235e-06, + "loss": 1.3672, + "step": 6143 + }, + { + "epoch": 0.64, + "learning_rate": 6.7667653447959355e-06, + "loss": 1.2901, + "step": 6144 + }, + { + "epoch": 0.64, + "learning_rate": 6.763301908867619e-06, + "loss": 1.2873, + "step": 6145 + }, + { + "epoch": 0.64, + "learning_rate": 6.759838906573684e-06, + "loss": 1.3582, + "step": 6146 + }, + { + "epoch": 0.64, + "learning_rate": 6.756376338378077e-06, + "loss": 1.3562, + "step": 6147 + }, + { + "epoch": 0.64, + "learning_rate": 6.7529142047447025e-06, + "loss": 1.3091, + "step": 6148 + }, + { + "epoch": 0.64, + "learning_rate": 6.749452506137393e-06, + "loss": 1.4269, + "step": 6149 + }, + { + "epoch": 0.64, + "learning_rate": 6.745991243019927e-06, + "loss": 1.4184, + "step": 6150 + }, + { + "epoch": 0.65, + "learning_rate": 6.7425304158560235e-06, + "loss": 1.4201, + "step": 6151 + }, + { + "epoch": 0.65, + "learning_rate": 6.739070025109349e-06, + "loss": 1.3222, + "step": 6152 + }, + { + "epoch": 0.65, + "learning_rate": 6.7356100712435035e-06, + "loss": 1.3262, + "step": 6153 + }, + { + "epoch": 0.65, + "learning_rate": 6.732150554722034e-06, + "loss": 1.4408, + "step": 6154 + }, + { + "epoch": 0.65, + "learning_rate": 6.728691476008422e-06, + "loss": 1.3441, + "step": 6155 + }, + { + "epoch": 0.65, + "learning_rate": 6.725232835566102e-06, + "loss": 1.3316, + "step": 6156 + }, + { + "epoch": 0.65, + "learning_rate": 6.721774633858438e-06, + "loss": 1.3326, + "step": 6157 + }, + { + "epoch": 0.65, + "learning_rate": 6.7183168713487425e-06, + "loss": 1.3105, + "step": 6158 + }, + { + "epoch": 0.65, + "learning_rate": 6.714859548500265e-06, + "loss": 1.3144, + "step": 6159 + }, + { + "epoch": 0.65, + "learning_rate": 6.7114026657762e-06, + "loss": 1.3472, + "step": 6160 + }, + { + "epoch": 0.65, + "learning_rate": 6.707946223639681e-06, + "loss": 1.3811, + "step": 6161 + }, + { + "epoch": 0.65, + "learning_rate": 6.704490222553781e-06, + "loss": 1.2783, + "step": 6162 + }, + { + "epoch": 0.65, + "learning_rate": 6.701034662981513e-06, + "loss": 1.273, + "step": 6163 + }, + { + "epoch": 0.65, + "learning_rate": 6.697579545385839e-06, + "loss": 1.3522, + "step": 6164 + }, + { + "epoch": 0.65, + "learning_rate": 6.6941248702296524e-06, + "loss": 1.3861, + "step": 6165 + }, + { + "epoch": 0.65, + "learning_rate": 6.6906706379757915e-06, + "loss": 1.3098, + "step": 6166 + }, + { + "epoch": 0.65, + "learning_rate": 6.687216849087032e-06, + "loss": 1.3734, + "step": 6167 + }, + { + "epoch": 0.65, + "learning_rate": 6.6837635040261e-06, + "loss": 1.2289, + "step": 6168 + }, + { + "epoch": 0.65, + "learning_rate": 6.680310603255648e-06, + "loss": 1.3238, + "step": 6169 + }, + { + "epoch": 0.65, + "eval_loss": 1.40826416015625, + "eval_runtime": 77.483, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 6169 + }, + { + "epoch": 0.65, + "learning_rate": 6.676858147238277e-06, + "loss": 1.4317, + "step": 6170 + }, + { + "epoch": 0.65, + "learning_rate": 6.673406136436531e-06, + "loss": 1.3363, + "step": 6171 + }, + { + "epoch": 0.65, + "learning_rate": 6.669954571312889e-06, + "loss": 1.3377, + "step": 6172 + }, + { + "epoch": 0.65, + "learning_rate": 6.666503452329771e-06, + "loss": 1.3382, + "step": 6173 + }, + { + "epoch": 0.65, + "learning_rate": 6.663052779949538e-06, + "loss": 1.3028, + "step": 6174 + }, + { + "epoch": 0.65, + "learning_rate": 6.659602554634494e-06, + "loss": 1.3098, + "step": 6175 + }, + { + "epoch": 0.65, + "learning_rate": 6.656152776846879e-06, + "loss": 1.328, + "step": 6176 + }, + { + "epoch": 0.65, + "learning_rate": 6.652703447048874e-06, + "loss": 1.3014, + "step": 6177 + }, + { + "epoch": 0.65, + "learning_rate": 6.6492545657026e-06, + "loss": 1.2522, + "step": 6178 + }, + { + "epoch": 0.65, + "learning_rate": 6.645806133270121e-06, + "loss": 1.6113, + "step": 6179 + }, + { + "epoch": 0.65, + "learning_rate": 6.642358150213437e-06, + "loss": 1.3431, + "step": 6180 + }, + { + "epoch": 0.65, + "learning_rate": 6.638910616994489e-06, + "loss": 1.2725, + "step": 6181 + }, + { + "epoch": 0.65, + "learning_rate": 6.635463534075156e-06, + "loss": 1.3022, + "step": 6182 + }, + { + "epoch": 0.65, + "learning_rate": 6.632016901917262e-06, + "loss": 1.3496, + "step": 6183 + }, + { + "epoch": 0.65, + "learning_rate": 6.628570720982567e-06, + "loss": 1.2871, + "step": 6184 + }, + { + "epoch": 0.65, + "learning_rate": 6.625124991732767e-06, + "loss": 1.4449, + "step": 6185 + }, + { + "epoch": 0.65, + "learning_rate": 6.621679714629504e-06, + "loss": 1.4395, + "step": 6186 + }, + { + "epoch": 0.65, + "learning_rate": 6.618234890134356e-06, + "loss": 1.4088, + "step": 6187 + }, + { + "epoch": 0.65, + "learning_rate": 6.614790518708843e-06, + "loss": 1.371, + "step": 6188 + }, + { + "epoch": 0.65, + "learning_rate": 6.611346600814419e-06, + "loss": 1.28, + "step": 6189 + }, + { + "epoch": 0.65, + "learning_rate": 6.607903136912482e-06, + "loss": 1.3502, + "step": 6190 + }, + { + "epoch": 0.65, + "learning_rate": 6.604460127464367e-06, + "loss": 1.3398, + "step": 6191 + }, + { + "epoch": 0.65, + "learning_rate": 6.60101757293135e-06, + "loss": 1.4762, + "step": 6192 + }, + { + "epoch": 0.65, + "learning_rate": 6.5975754737746426e-06, + "loss": 1.2981, + "step": 6193 + }, + { + "epoch": 0.65, + "learning_rate": 6.594133830455401e-06, + "loss": 1.3728, + "step": 6194 + }, + { + "epoch": 0.65, + "learning_rate": 6.590692643434715e-06, + "loss": 1.3551, + "step": 6195 + }, + { + "epoch": 0.65, + "learning_rate": 6.5872519131736155e-06, + "loss": 1.3031, + "step": 6196 + }, + { + "epoch": 0.65, + "learning_rate": 6.583811640133071e-06, + "loss": 1.3231, + "step": 6197 + }, + { + "epoch": 0.65, + "learning_rate": 6.5803718247739924e-06, + "loss": 1.2752, + "step": 6198 + }, + { + "epoch": 0.65, + "learning_rate": 6.576932467557223e-06, + "loss": 1.3482, + "step": 6199 + }, + { + "epoch": 0.65, + "learning_rate": 6.573493568943552e-06, + "loss": 1.2612, + "step": 6200 + }, + { + "epoch": 0.65, + "learning_rate": 6.570055129393698e-06, + "loss": 1.6302, + "step": 6201 + }, + { + "epoch": 0.65, + "learning_rate": 6.566617149368331e-06, + "loss": 1.303, + "step": 6202 + }, + { + "epoch": 0.65, + "learning_rate": 6.563179629328047e-06, + "loss": 1.3405, + "step": 6203 + }, + { + "epoch": 0.65, + "learning_rate": 6.559742569733385e-06, + "loss": 1.2816, + "step": 6204 + }, + { + "epoch": 0.65, + "learning_rate": 6.556305971044824e-06, + "loss": 1.3834, + "step": 6205 + }, + { + "epoch": 0.65, + "learning_rate": 6.552869833722781e-06, + "loss": 1.3414, + "step": 6206 + }, + { + "epoch": 0.65, + "learning_rate": 6.5494341582276096e-06, + "loss": 1.3278, + "step": 6207 + }, + { + "epoch": 0.65, + "learning_rate": 6.5459989450196024e-06, + "loss": 1.3577, + "step": 6208 + }, + { + "epoch": 0.65, + "learning_rate": 6.542564194558986e-06, + "loss": 1.3104, + "step": 6209 + }, + { + "epoch": 0.65, + "learning_rate": 6.539129907305933e-06, + "loss": 1.3068, + "step": 6210 + }, + { + "epoch": 0.65, + "learning_rate": 6.53569608372055e-06, + "loss": 1.3769, + "step": 6211 + }, + { + "epoch": 0.65, + "learning_rate": 6.5322627242628775e-06, + "loss": 1.2855, + "step": 6212 + }, + { + "epoch": 0.65, + "learning_rate": 6.528829829392898e-06, + "loss": 1.4129, + "step": 6213 + }, + { + "epoch": 0.65, + "learning_rate": 6.525397399570534e-06, + "loss": 1.3631, + "step": 6214 + }, + { + "epoch": 0.65, + "learning_rate": 6.5219654352556435e-06, + "loss": 1.295, + "step": 6215 + }, + { + "epoch": 0.65, + "learning_rate": 6.518533936908016e-06, + "loss": 1.439, + "step": 6216 + }, + { + "epoch": 0.65, + "learning_rate": 6.515102904987389e-06, + "loss": 1.3148, + "step": 6217 + }, + { + "epoch": 0.65, + "learning_rate": 6.511672339953432e-06, + "loss": 1.3898, + "step": 6218 + }, + { + "epoch": 0.65, + "learning_rate": 6.508242242265752e-06, + "loss": 1.3222, + "step": 6219 + }, + { + "epoch": 0.65, + "learning_rate": 6.504812612383891e-06, + "loss": 1.324, + "step": 6220 + }, + { + "epoch": 0.65, + "learning_rate": 6.501383450767336e-06, + "loss": 1.951, + "step": 6221 + }, + { + "epoch": 0.65, + "learning_rate": 6.4979547578755055e-06, + "loss": 1.2878, + "step": 6222 + }, + { + "epoch": 0.65, + "learning_rate": 6.494526534167754e-06, + "loss": 1.3553, + "step": 6223 + }, + { + "epoch": 0.65, + "learning_rate": 6.491098780103375e-06, + "loss": 1.3898, + "step": 6224 + }, + { + "epoch": 0.65, + "learning_rate": 6.487671496141606e-06, + "loss": 1.4333, + "step": 6225 + }, + { + "epoch": 0.65, + "learning_rate": 6.484244682741606e-06, + "loss": 1.4461, + "step": 6226 + }, + { + "epoch": 0.65, + "learning_rate": 6.480818340362487e-06, + "loss": 1.3461, + "step": 6227 + }, + { + "epoch": 0.65, + "learning_rate": 6.4773924694632835e-06, + "loss": 1.3442, + "step": 6228 + }, + { + "epoch": 0.65, + "learning_rate": 6.473967070502982e-06, + "loss": 1.2692, + "step": 6229 + }, + { + "epoch": 0.65, + "learning_rate": 6.470542143940495e-06, + "loss": 1.446, + "step": 6230 + }, + { + "epoch": 0.65, + "learning_rate": 6.467117690234675e-06, + "loss": 1.3597, + "step": 6231 + }, + { + "epoch": 0.65, + "learning_rate": 6.463693709844305e-06, + "loss": 1.3226, + "step": 6232 + }, + { + "epoch": 0.65, + "learning_rate": 6.46027020322812e-06, + "loss": 1.2702, + "step": 6233 + }, + { + "epoch": 0.65, + "learning_rate": 6.456847170844775e-06, + "loss": 1.2554, + "step": 6234 + }, + { + "epoch": 0.65, + "learning_rate": 6.453424613152872e-06, + "loss": 1.2896, + "step": 6235 + }, + { + "epoch": 0.65, + "learning_rate": 6.450002530610943e-06, + "loss": 1.3148, + "step": 6236 + }, + { + "epoch": 0.65, + "learning_rate": 6.4465809236774635e-06, + "loss": 1.3589, + "step": 6237 + }, + { + "epoch": 0.65, + "learning_rate": 6.443159792810838e-06, + "loss": 1.2938, + "step": 6238 + }, + { + "epoch": 0.65, + "learning_rate": 6.439739138469406e-06, + "loss": 1.366, + "step": 6239 + }, + { + "epoch": 0.65, + "learning_rate": 6.436318961111455e-06, + "loss": 1.4772, + "step": 6240 + }, + { + "epoch": 0.65, + "learning_rate": 6.4328992611951975e-06, + "loss": 1.3131, + "step": 6241 + }, + { + "epoch": 0.65, + "learning_rate": 6.429480039178786e-06, + "loss": 1.2382, + "step": 6242 + }, + { + "epoch": 0.65, + "learning_rate": 6.426061295520304e-06, + "loss": 1.3394, + "step": 6243 + }, + { + "epoch": 0.65, + "learning_rate": 6.422643030677782e-06, + "loss": 1.321, + "step": 6244 + }, + { + "epoch": 0.65, + "learning_rate": 6.419225245109175e-06, + "loss": 1.3478, + "step": 6245 + }, + { + "epoch": 0.65, + "learning_rate": 6.415807939272383e-06, + "loss": 1.3249, + "step": 6246 + }, + { + "epoch": 0.66, + "learning_rate": 6.412391113625231e-06, + "loss": 1.3602, + "step": 6247 + }, + { + "epoch": 0.66, + "learning_rate": 6.408974768625491e-06, + "loss": 1.2799, + "step": 6248 + }, + { + "epoch": 0.66, + "learning_rate": 6.405558904730863e-06, + "loss": 1.3911, + "step": 6249 + }, + { + "epoch": 0.66, + "learning_rate": 6.402143522398987e-06, + "loss": 1.3185, + "step": 6250 + }, + { + "epoch": 0.66, + "learning_rate": 6.398728622087431e-06, + "loss": 1.3198, + "step": 6251 + }, + { + "epoch": 0.66, + "learning_rate": 6.395314204253711e-06, + "loss": 1.361, + "step": 6252 + }, + { + "epoch": 0.66, + "learning_rate": 6.391900269355269e-06, + "loss": 1.3285, + "step": 6253 + }, + { + "epoch": 0.66, + "learning_rate": 6.388486817849484e-06, + "loss": 1.3097, + "step": 6254 + }, + { + "epoch": 0.66, + "learning_rate": 6.385073850193667e-06, + "loss": 1.3057, + "step": 6255 + }, + { + "epoch": 0.66, + "learning_rate": 6.381661366845075e-06, + "loss": 1.4733, + "step": 6256 + }, + { + "epoch": 0.66, + "learning_rate": 6.378249368260889e-06, + "loss": 1.3571, + "step": 6257 + }, + { + "epoch": 0.66, + "learning_rate": 6.374837854898228e-06, + "loss": 1.3278, + "step": 6258 + }, + { + "epoch": 0.66, + "learning_rate": 6.37142682721415e-06, + "loss": 1.3035, + "step": 6259 + }, + { + "epoch": 0.66, + "learning_rate": 6.368016285665645e-06, + "loss": 1.397, + "step": 6260 + }, + { + "epoch": 0.66, + "learning_rate": 6.3646062307096365e-06, + "loss": 1.353, + "step": 6261 + }, + { + "epoch": 0.66, + "learning_rate": 6.361196662802982e-06, + "loss": 1.3534, + "step": 6262 + }, + { + "epoch": 0.66, + "learning_rate": 6.357787582402482e-06, + "loss": 1.3132, + "step": 6263 + }, + { + "epoch": 0.66, + "learning_rate": 6.3543789899648624e-06, + "loss": 1.3551, + "step": 6264 + }, + { + "epoch": 0.66, + "learning_rate": 6.3509708859467855e-06, + "loss": 1.4205, + "step": 6265 + }, + { + "epoch": 0.66, + "learning_rate": 6.347563270804851e-06, + "loss": 1.341, + "step": 6266 + }, + { + "epoch": 0.66, + "learning_rate": 6.344156144995593e-06, + "loss": 1.5188, + "step": 6267 + }, + { + "epoch": 0.66, + "learning_rate": 6.340749508975477e-06, + "loss": 1.4404, + "step": 6268 + }, + { + "epoch": 0.66, + "learning_rate": 6.337343363200905e-06, + "loss": 1.3026, + "step": 6269 + }, + { + "epoch": 0.66, + "learning_rate": 6.3339377081282124e-06, + "loss": 1.3315, + "step": 6270 + }, + { + "epoch": 0.66, + "learning_rate": 6.3305325442136735e-06, + "loss": 1.2503, + "step": 6271 + }, + { + "epoch": 0.66, + "learning_rate": 6.3271278719134885e-06, + "loss": 1.1776, + "step": 6272 + }, + { + "epoch": 0.66, + "learning_rate": 6.323723691683798e-06, + "loss": 1.3033, + "step": 6273 + }, + { + "epoch": 0.66, + "learning_rate": 6.320320003980671e-06, + "loss": 1.3838, + "step": 6274 + }, + { + "epoch": 0.66, + "learning_rate": 6.3169168092601195e-06, + "loss": 1.3691, + "step": 6275 + }, + { + "epoch": 0.66, + "learning_rate": 6.313514107978083e-06, + "loss": 1.3665, + "step": 6276 + }, + { + "epoch": 0.66, + "learning_rate": 6.310111900590432e-06, + "loss": 1.358, + "step": 6277 + }, + { + "epoch": 0.66, + "learning_rate": 6.306710187552978e-06, + "loss": 1.1708, + "step": 6278 + }, + { + "epoch": 0.66, + "learning_rate": 6.303308969321464e-06, + "loss": 1.331, + "step": 6279 + }, + { + "epoch": 0.66, + "learning_rate": 6.299908246351566e-06, + "loss": 1.3914, + "step": 6280 + }, + { + "epoch": 0.66, + "learning_rate": 6.2965080190988896e-06, + "loss": 1.3183, + "step": 6281 + }, + { + "epoch": 0.66, + "learning_rate": 6.293108288018981e-06, + "loss": 1.2969, + "step": 6282 + }, + { + "epoch": 0.66, + "learning_rate": 6.289709053567318e-06, + "loss": 1.2892, + "step": 6283 + }, + { + "epoch": 0.66, + "learning_rate": 6.2863103161993085e-06, + "loss": 1.3517, + "step": 6284 + }, + { + "epoch": 0.66, + "learning_rate": 6.282912076370295e-06, + "loss": 1.3329, + "step": 6285 + }, + { + "epoch": 0.66, + "learning_rate": 6.279514334535557e-06, + "loss": 1.3396, + "step": 6286 + }, + { + "epoch": 0.66, + "learning_rate": 6.276117091150304e-06, + "loss": 1.3878, + "step": 6287 + }, + { + "epoch": 0.66, + "learning_rate": 6.272720346669677e-06, + "loss": 1.2608, + "step": 6288 + }, + { + "epoch": 0.66, + "learning_rate": 6.269324101548754e-06, + "loss": 1.3605, + "step": 6289 + }, + { + "epoch": 0.66, + "learning_rate": 6.265928356242546e-06, + "loss": 1.2682, + "step": 6290 + }, + { + "epoch": 0.66, + "learning_rate": 6.262533111205995e-06, + "loss": 1.3426, + "step": 6291 + }, + { + "epoch": 0.66, + "learning_rate": 6.259138366893975e-06, + "loss": 1.2987, + "step": 6292 + }, + { + "epoch": 0.66, + "learning_rate": 6.255744123761295e-06, + "loss": 1.3521, + "step": 6293 + }, + { + "epoch": 0.66, + "learning_rate": 6.252350382262697e-06, + "loss": 1.2816, + "step": 6294 + }, + { + "epoch": 0.66, + "learning_rate": 6.248957142852856e-06, + "loss": 1.3884, + "step": 6295 + }, + { + "epoch": 0.66, + "learning_rate": 6.2455644059863795e-06, + "loss": 1.3545, + "step": 6296 + }, + { + "epoch": 0.66, + "learning_rate": 6.2421721721178015e-06, + "loss": 1.3636, + "step": 6297 + }, + { + "epoch": 0.66, + "learning_rate": 6.238780441701601e-06, + "loss": 1.3584, + "step": 6298 + }, + { + "epoch": 0.66, + "learning_rate": 6.235389215192179e-06, + "loss": 1.3459, + "step": 6299 + }, + { + "epoch": 0.66, + "learning_rate": 6.231998493043875e-06, + "loss": 1.4654, + "step": 6300 + }, + { + "epoch": 0.66, + "learning_rate": 6.228608275710954e-06, + "loss": 1.3628, + "step": 6301 + }, + { + "epoch": 0.66, + "learning_rate": 6.225218563647623e-06, + "loss": 1.3278, + "step": 6302 + }, + { + "epoch": 0.66, + "learning_rate": 6.221829357308016e-06, + "loss": 1.395, + "step": 6303 + }, + { + "epoch": 0.66, + "learning_rate": 6.218440657146196e-06, + "loss": 1.3481, + "step": 6304 + }, + { + "epoch": 0.66, + "learning_rate": 6.215052463616165e-06, + "loss": 1.309, + "step": 6305 + }, + { + "epoch": 0.66, + "learning_rate": 6.211664777171853e-06, + "loss": 1.275, + "step": 6306 + }, + { + "epoch": 0.66, + "learning_rate": 6.208277598267123e-06, + "loss": 1.4885, + "step": 6307 + }, + { + "epoch": 0.66, + "learning_rate": 6.2048909273557686e-06, + "loss": 1.3334, + "step": 6308 + }, + { + "epoch": 0.66, + "learning_rate": 6.201504764891518e-06, + "loss": 1.3399, + "step": 6309 + }, + { + "epoch": 0.66, + "learning_rate": 6.198119111328032e-06, + "loss": 1.3163, + "step": 6310 + }, + { + "epoch": 0.66, + "learning_rate": 6.1947339671188966e-06, + "loss": 1.2746, + "step": 6311 + }, + { + "epoch": 0.66, + "learning_rate": 6.191349332717635e-06, + "loss": 1.2984, + "step": 6312 + }, + { + "epoch": 0.66, + "learning_rate": 6.187965208577705e-06, + "loss": 1.2295, + "step": 6313 + }, + { + "epoch": 0.66, + "learning_rate": 6.18458159515249e-06, + "loss": 1.3424, + "step": 6314 + }, + { + "epoch": 0.66, + "learning_rate": 6.181198492895308e-06, + "loss": 1.3108, + "step": 6315 + }, + { + "epoch": 0.66, + "learning_rate": 6.1778159022594045e-06, + "loss": 1.4895, + "step": 6316 + }, + { + "epoch": 0.66, + "learning_rate": 6.174433823697964e-06, + "loss": 1.3247, + "step": 6317 + }, + { + "epoch": 0.66, + "learning_rate": 6.171052257664097e-06, + "loss": 1.3659, + "step": 6318 + }, + { + "epoch": 0.66, + "learning_rate": 6.167671204610844e-06, + "loss": 1.3889, + "step": 6319 + }, + { + "epoch": 0.66, + "learning_rate": 6.1642906649911815e-06, + "loss": 1.3946, + "step": 6320 + }, + { + "epoch": 0.66, + "learning_rate": 6.1609106392580155e-06, + "loss": 1.3685, + "step": 6321 + }, + { + "epoch": 0.66, + "learning_rate": 6.157531127864181e-06, + "loss": 1.2584, + "step": 6322 + }, + { + "epoch": 0.66, + "learning_rate": 6.154152131262448e-06, + "loss": 1.3263, + "step": 6323 + }, + { + "epoch": 0.66, + "learning_rate": 6.15077364990551e-06, + "loss": 1.3336, + "step": 6324 + }, + { + "epoch": 0.66, + "learning_rate": 6.147395684246003e-06, + "loss": 1.2513, + "step": 6325 + }, + { + "epoch": 0.66, + "learning_rate": 6.144018234736484e-06, + "loss": 1.3715, + "step": 6326 + }, + { + "epoch": 0.66, + "learning_rate": 6.140641301829444e-06, + "loss": 1.3464, + "step": 6327 + }, + { + "epoch": 0.66, + "learning_rate": 6.1372648859773075e-06, + "loss": 1.4374, + "step": 6328 + }, + { + "epoch": 0.66, + "learning_rate": 6.1338889876324285e-06, + "loss": 1.3903, + "step": 6329 + }, + { + "epoch": 0.66, + "learning_rate": 6.130513607247087e-06, + "loss": 1.3715, + "step": 6330 + }, + { + "epoch": 0.66, + "learning_rate": 6.127138745273497e-06, + "loss": 1.3196, + "step": 6331 + }, + { + "epoch": 0.66, + "learning_rate": 6.123764402163808e-06, + "loss": 1.3013, + "step": 6332 + }, + { + "epoch": 0.66, + "learning_rate": 6.120390578370093e-06, + "loss": 1.2751, + "step": 6333 + }, + { + "epoch": 0.66, + "learning_rate": 6.117017274344356e-06, + "loss": 1.2258, + "step": 6334 + }, + { + "epoch": 0.66, + "learning_rate": 6.113644490538533e-06, + "loss": 1.2982, + "step": 6335 + }, + { + "epoch": 0.66, + "learning_rate": 6.110272227404492e-06, + "loss": 1.3124, + "step": 6336 + }, + { + "epoch": 0.66, + "learning_rate": 6.10690048539403e-06, + "loss": 1.2451, + "step": 6337 + }, + { + "epoch": 0.66, + "learning_rate": 6.103529264958874e-06, + "loss": 1.3896, + "step": 6338 + }, + { + "epoch": 0.66, + "learning_rate": 6.100158566550677e-06, + "loss": 1.46, + "step": 6339 + }, + { + "epoch": 0.66, + "learning_rate": 6.096788390621031e-06, + "loss": 1.2965, + "step": 6340 + }, + { + "epoch": 0.66, + "learning_rate": 6.093418737621452e-06, + "loss": 1.2969, + "step": 6341 + }, + { + "epoch": 0.67, + "learning_rate": 6.0900496080033836e-06, + "loss": 1.3988, + "step": 6342 + }, + { + "epoch": 0.67, + "learning_rate": 6.086681002218204e-06, + "loss": 1.351, + "step": 6343 + }, + { + "epoch": 0.67, + "learning_rate": 6.083312920717224e-06, + "loss": 1.3447, + "step": 6344 + }, + { + "epoch": 0.67, + "learning_rate": 6.079945363951674e-06, + "loss": 1.3361, + "step": 6345 + }, + { + "epoch": 0.67, + "learning_rate": 6.076578332372724e-06, + "loss": 1.3688, + "step": 6346 + }, + { + "epoch": 0.67, + "learning_rate": 6.073211826431467e-06, + "loss": 1.2831, + "step": 6347 + }, + { + "epoch": 0.67, + "learning_rate": 6.069845846578931e-06, + "loss": 1.369, + "step": 6348 + }, + { + "epoch": 0.67, + "learning_rate": 6.06648039326607e-06, + "loss": 1.3247, + "step": 6349 + }, + { + "epoch": 0.67, + "learning_rate": 6.063115466943765e-06, + "loss": 1.288, + "step": 6350 + }, + { + "epoch": 0.67, + "learning_rate": 6.0597510680628345e-06, + "loss": 1.0733, + "step": 6351 + }, + { + "epoch": 0.67, + "learning_rate": 6.056387197074021e-06, + "loss": 1.3386, + "step": 6352 + }, + { + "epoch": 0.67, + "learning_rate": 6.053023854427993e-06, + "loss": 1.3682, + "step": 6353 + }, + { + "epoch": 0.67, + "learning_rate": 6.049661040575353e-06, + "loss": 1.5669, + "step": 6354 + }, + { + "epoch": 0.67, + "learning_rate": 6.0462987559666355e-06, + "loss": 1.3432, + "step": 6355 + }, + { + "epoch": 0.67, + "learning_rate": 6.042937001052298e-06, + "loss": 1.327, + "step": 6356 + }, + { + "epoch": 0.67, + "learning_rate": 6.039575776282728e-06, + "loss": 1.3101, + "step": 6357 + }, + { + "epoch": 0.67, + "learning_rate": 6.0362150821082425e-06, + "loss": 1.3239, + "step": 6358 + }, + { + "epoch": 0.67, + "learning_rate": 6.032854918979092e-06, + "loss": 1.435, + "step": 6359 + }, + { + "epoch": 0.67, + "learning_rate": 6.029495287345448e-06, + "loss": 1.3503, + "step": 6360 + }, + { + "epoch": 0.67, + "learning_rate": 6.0261361876574186e-06, + "loss": 1.3356, + "step": 6361 + }, + { + "epoch": 0.67, + "learning_rate": 6.022777620365032e-06, + "loss": 1.3301, + "step": 6362 + }, + { + "epoch": 0.67, + "learning_rate": 6.019419585918255e-06, + "loss": 1.3925, + "step": 6363 + }, + { + "epoch": 0.67, + "learning_rate": 6.016062084766978e-06, + "loss": 1.3794, + "step": 6364 + }, + { + "epoch": 0.67, + "learning_rate": 6.0127051173610155e-06, + "loss": 1.5496, + "step": 6365 + }, + { + "epoch": 0.67, + "learning_rate": 6.009348684150116e-06, + "loss": 1.3227, + "step": 6366 + }, + { + "epoch": 0.67, + "learning_rate": 6.005992785583958e-06, + "loss": 1.3474, + "step": 6367 + }, + { + "epoch": 0.67, + "learning_rate": 6.002637422112143e-06, + "loss": 1.3262, + "step": 6368 + }, + { + "epoch": 0.67, + "eval_loss": 1.4049769639968872, + "eval_runtime": 77.5156, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 6368 + }, + { + "epoch": 0.67, + "learning_rate": 5.999282594184206e-06, + "loss": 1.3083, + "step": 6369 + }, + { + "epoch": 0.67, + "learning_rate": 5.995928302249603e-06, + "loss": 1.323, + "step": 6370 + }, + { + "epoch": 0.67, + "learning_rate": 5.99257454675773e-06, + "loss": 1.3101, + "step": 6371 + }, + { + "epoch": 0.67, + "learning_rate": 5.989221328157899e-06, + "loss": 1.4546, + "step": 6372 + }, + { + "epoch": 0.67, + "learning_rate": 5.985868646899355e-06, + "loss": 1.3315, + "step": 6373 + }, + { + "epoch": 0.67, + "learning_rate": 5.982516503431273e-06, + "loss": 1.3768, + "step": 6374 + }, + { + "epoch": 0.67, + "learning_rate": 5.979164898202755e-06, + "loss": 1.332, + "step": 6375 + }, + { + "epoch": 0.67, + "learning_rate": 5.975813831662829e-06, + "loss": 1.3154, + "step": 6376 + }, + { + "epoch": 0.67, + "learning_rate": 5.972463304260448e-06, + "loss": 1.3636, + "step": 6377 + }, + { + "epoch": 0.67, + "learning_rate": 5.969113316444504e-06, + "loss": 1.3553, + "step": 6378 + }, + { + "epoch": 0.67, + "learning_rate": 5.965763868663803e-06, + "loss": 1.3805, + "step": 6379 + }, + { + "epoch": 0.67, + "learning_rate": 5.962414961367089e-06, + "loss": 1.3096, + "step": 6380 + }, + { + "epoch": 0.67, + "learning_rate": 5.959066595003025e-06, + "loss": 1.326, + "step": 6381 + }, + { + "epoch": 0.67, + "learning_rate": 5.955718770020212e-06, + "loss": 1.3021, + "step": 6382 + }, + { + "epoch": 0.67, + "learning_rate": 5.952371486867168e-06, + "loss": 1.35, + "step": 6383 + }, + { + "epoch": 0.67, + "learning_rate": 5.949024745992344e-06, + "loss": 1.6749, + "step": 6384 + }, + { + "epoch": 0.67, + "learning_rate": 5.945678547844117e-06, + "loss": 1.4931, + "step": 6385 + }, + { + "epoch": 0.67, + "learning_rate": 5.942332892870793e-06, + "loss": 1.284, + "step": 6386 + }, + { + "epoch": 0.67, + "learning_rate": 5.938987781520604e-06, + "loss": 1.3296, + "step": 6387 + }, + { + "epoch": 0.67, + "learning_rate": 5.9356432142417074e-06, + "loss": 1.4837, + "step": 6388 + }, + { + "epoch": 0.67, + "learning_rate": 5.932299191482188e-06, + "loss": 1.3114, + "step": 6389 + }, + { + "epoch": 0.67, + "learning_rate": 5.928955713690063e-06, + "loss": 1.3328, + "step": 6390 + }, + { + "epoch": 0.67, + "learning_rate": 5.92561278131327e-06, + "loss": 1.3163, + "step": 6391 + }, + { + "epoch": 0.67, + "learning_rate": 5.922270394799676e-06, + "loss": 1.3068, + "step": 6392 + }, + { + "epoch": 0.67, + "learning_rate": 5.918928554597073e-06, + "loss": 1.292, + "step": 6393 + }, + { + "epoch": 0.67, + "learning_rate": 5.915587261153186e-06, + "loss": 1.3359, + "step": 6394 + }, + { + "epoch": 0.67, + "learning_rate": 5.912246514915662e-06, + "loss": 1.4109, + "step": 6395 + }, + { + "epoch": 0.67, + "learning_rate": 5.908906316332071e-06, + "loss": 1.3083, + "step": 6396 + }, + { + "epoch": 0.67, + "learning_rate": 5.905566665849917e-06, + "loss": 1.2973, + "step": 6397 + }, + { + "epoch": 0.67, + "learning_rate": 5.902227563916627e-06, + "loss": 1.4159, + "step": 6398 + }, + { + "epoch": 0.67, + "learning_rate": 5.898889010979556e-06, + "loss": 1.287, + "step": 6399 + }, + { + "epoch": 0.67, + "learning_rate": 5.89555100748598e-06, + "loss": 1.2865, + "step": 6400 + }, + { + "epoch": 0.67, + "learning_rate": 5.89221355388311e-06, + "loss": 1.3137, + "step": 6401 + }, + { + "epoch": 0.67, + "learning_rate": 5.8888766506180785e-06, + "loss": 1.2751, + "step": 6402 + }, + { + "epoch": 0.67, + "learning_rate": 5.885540298137944e-06, + "loss": 1.3687, + "step": 6403 + }, + { + "epoch": 0.67, + "learning_rate": 5.882204496889688e-06, + "loss": 1.2941, + "step": 6404 + }, + { + "epoch": 0.67, + "learning_rate": 5.878869247320231e-06, + "loss": 1.2926, + "step": 6405 + }, + { + "epoch": 0.67, + "learning_rate": 5.875534549876404e-06, + "loss": 1.2675, + "step": 6406 + }, + { + "epoch": 0.67, + "learning_rate": 5.872200405004973e-06, + "loss": 1.2806, + "step": 6407 + }, + { + "epoch": 0.67, + "learning_rate": 5.868866813152625e-06, + "loss": 1.3438, + "step": 6408 + }, + { + "epoch": 0.67, + "learning_rate": 5.865533774765981e-06, + "loss": 1.2947, + "step": 6409 + }, + { + "epoch": 0.67, + "learning_rate": 5.862201290291578e-06, + "loss": 1.3643, + "step": 6410 + }, + { + "epoch": 0.67, + "learning_rate": 5.858869360175887e-06, + "loss": 1.2579, + "step": 6411 + }, + { + "epoch": 0.67, + "learning_rate": 5.855537984865296e-06, + "loss": 1.3479, + "step": 6412 + }, + { + "epoch": 0.67, + "learning_rate": 5.852207164806127e-06, + "loss": 1.3239, + "step": 6413 + }, + { + "epoch": 0.67, + "learning_rate": 5.848876900444626e-06, + "loss": 1.2644, + "step": 6414 + }, + { + "epoch": 0.67, + "learning_rate": 5.845547192226959e-06, + "loss": 1.3279, + "step": 6415 + }, + { + "epoch": 0.67, + "learning_rate": 5.8422180405992216e-06, + "loss": 1.5202, + "step": 6416 + }, + { + "epoch": 0.67, + "learning_rate": 5.838889446007439e-06, + "loss": 1.5714, + "step": 6417 + }, + { + "epoch": 0.67, + "learning_rate": 5.835561408897552e-06, + "loss": 1.2592, + "step": 6418 + }, + { + "epoch": 0.67, + "learning_rate": 5.832233929715434e-06, + "loss": 1.3407, + "step": 6419 + }, + { + "epoch": 0.67, + "learning_rate": 5.828907008906882e-06, + "loss": 1.3555, + "step": 6420 + }, + { + "epoch": 0.67, + "learning_rate": 5.825580646917622e-06, + "loss": 1.2602, + "step": 6421 + }, + { + "epoch": 0.67, + "learning_rate": 5.822254844193293e-06, + "loss": 1.2672, + "step": 6422 + }, + { + "epoch": 0.67, + "learning_rate": 5.818929601179472e-06, + "loss": 1.3361, + "step": 6423 + }, + { + "epoch": 0.67, + "learning_rate": 5.8156049183216575e-06, + "loss": 1.49, + "step": 6424 + }, + { + "epoch": 0.67, + "learning_rate": 5.812280796065269e-06, + "loss": 1.306, + "step": 6425 + }, + { + "epoch": 0.67, + "learning_rate": 5.808957234855654e-06, + "loss": 1.3167, + "step": 6426 + }, + { + "epoch": 0.67, + "learning_rate": 5.805634235138082e-06, + "loss": 1.3103, + "step": 6427 + }, + { + "epoch": 0.67, + "learning_rate": 5.802311797357752e-06, + "loss": 1.2992, + "step": 6428 + }, + { + "epoch": 0.67, + "learning_rate": 5.7989899219597875e-06, + "loss": 1.3269, + "step": 6429 + }, + { + "epoch": 0.67, + "learning_rate": 5.795668609389233e-06, + "loss": 1.3393, + "step": 6430 + }, + { + "epoch": 0.67, + "learning_rate": 5.79234786009105e-06, + "loss": 1.2633, + "step": 6431 + }, + { + "epoch": 0.67, + "learning_rate": 5.7890276745101495e-06, + "loss": 1.2758, + "step": 6432 + }, + { + "epoch": 0.67, + "learning_rate": 5.785708053091339e-06, + "loss": 1.3294, + "step": 6433 + }, + { + "epoch": 0.67, + "learning_rate": 5.782388996279371e-06, + "loss": 1.3657, + "step": 6434 + }, + { + "epoch": 0.67, + "learning_rate": 5.779070504518905e-06, + "loss": 1.3353, + "step": 6435 + }, + { + "epoch": 0.67, + "learning_rate": 5.775752578254539e-06, + "loss": 1.2741, + "step": 6436 + }, + { + "epoch": 0.68, + "learning_rate": 5.772435217930792e-06, + "loss": 1.2979, + "step": 6437 + }, + { + "epoch": 0.68, + "learning_rate": 5.7691184239921026e-06, + "loss": 1.366, + "step": 6438 + }, + { + "epoch": 0.68, + "learning_rate": 5.765802196882828e-06, + "loss": 1.2873, + "step": 6439 + }, + { + "epoch": 0.68, + "learning_rate": 5.762486537047271e-06, + "loss": 1.2865, + "step": 6440 + }, + { + "epoch": 0.68, + "learning_rate": 5.7591714449296365e-06, + "loss": 1.3887, + "step": 6441 + }, + { + "epoch": 0.68, + "learning_rate": 5.755856920974063e-06, + "loss": 1.127, + "step": 6442 + }, + { + "epoch": 0.68, + "learning_rate": 5.752542965624617e-06, + "loss": 1.4331, + "step": 6443 + }, + { + "epoch": 0.68, + "learning_rate": 5.749229579325274e-06, + "loss": 1.3199, + "step": 6444 + }, + { + "epoch": 0.68, + "learning_rate": 5.745916762519952e-06, + "loss": 1.2719, + "step": 6445 + }, + { + "epoch": 0.68, + "learning_rate": 5.742604515652475e-06, + "loss": 1.2991, + "step": 6446 + }, + { + "epoch": 0.68, + "learning_rate": 5.7392928391666014e-06, + "loss": 1.2164, + "step": 6447 + }, + { + "epoch": 0.68, + "learning_rate": 5.735981733506016e-06, + "loss": 1.3636, + "step": 6448 + }, + { + "epoch": 0.68, + "learning_rate": 5.732671199114314e-06, + "loss": 1.3486, + "step": 6449 + }, + { + "epoch": 0.68, + "learning_rate": 5.729361236435027e-06, + "loss": 1.3378, + "step": 6450 + }, + { + "epoch": 0.68, + "learning_rate": 5.726051845911606e-06, + "loss": 1.3521, + "step": 6451 + }, + { + "epoch": 0.68, + "learning_rate": 5.722743027987421e-06, + "loss": 1.4295, + "step": 6452 + }, + { + "epoch": 0.68, + "learning_rate": 5.719434783105772e-06, + "loss": 1.2625, + "step": 6453 + }, + { + "epoch": 0.68, + "learning_rate": 5.716127111709873e-06, + "loss": 1.2944, + "step": 6454 + }, + { + "epoch": 0.68, + "learning_rate": 5.7128200142428695e-06, + "loss": 1.3655, + "step": 6455 + }, + { + "epoch": 0.68, + "learning_rate": 5.7095134911478336e-06, + "loss": 1.3115, + "step": 6456 + }, + { + "epoch": 0.68, + "learning_rate": 5.706207542867747e-06, + "loss": 1.3391, + "step": 6457 + }, + { + "epoch": 0.68, + "learning_rate": 5.702902169845519e-06, + "loss": 1.3911, + "step": 6458 + }, + { + "epoch": 0.68, + "learning_rate": 5.699597372523997e-06, + "loss": 1.2936, + "step": 6459 + }, + { + "epoch": 0.68, + "learning_rate": 5.696293151345928e-06, + "loss": 1.379, + "step": 6460 + }, + { + "epoch": 0.68, + "learning_rate": 5.692989506754e-06, + "loss": 1.4083, + "step": 6461 + }, + { + "epoch": 0.68, + "learning_rate": 5.689686439190809e-06, + "loss": 1.2645, + "step": 6462 + }, + { + "epoch": 0.68, + "learning_rate": 5.686383949098886e-06, + "loss": 1.3207, + "step": 6463 + }, + { + "epoch": 0.68, + "learning_rate": 5.683082036920682e-06, + "loss": 1.4293, + "step": 6464 + }, + { + "epoch": 0.68, + "learning_rate": 5.679780703098563e-06, + "loss": 1.3018, + "step": 6465 + }, + { + "epoch": 0.68, + "learning_rate": 5.676479948074825e-06, + "loss": 1.3568, + "step": 6466 + }, + { + "epoch": 0.68, + "learning_rate": 5.673179772291687e-06, + "loss": 1.3252, + "step": 6467 + }, + { + "epoch": 0.68, + "learning_rate": 5.669880176191283e-06, + "loss": 1.2674, + "step": 6468 + }, + { + "epoch": 0.68, + "learning_rate": 5.666581160215676e-06, + "loss": 1.3774, + "step": 6469 + }, + { + "epoch": 0.68, + "learning_rate": 5.663282724806855e-06, + "loss": 1.3013, + "step": 6470 + }, + { + "epoch": 0.68, + "learning_rate": 5.659984870406715e-06, + "loss": 1.3354, + "step": 6471 + }, + { + "epoch": 0.68, + "learning_rate": 5.656687597457093e-06, + "loss": 1.273, + "step": 6472 + }, + { + "epoch": 0.68, + "learning_rate": 5.653390906399732e-06, + "loss": 1.3041, + "step": 6473 + }, + { + "epoch": 0.68, + "learning_rate": 5.650094797676308e-06, + "loss": 1.3521, + "step": 6474 + }, + { + "epoch": 0.68, + "learning_rate": 5.646799271728417e-06, + "loss": 1.3751, + "step": 6475 + }, + { + "epoch": 0.68, + "learning_rate": 5.643504328997571e-06, + "loss": 1.2882, + "step": 6476 + }, + { + "epoch": 0.68, + "learning_rate": 5.640209969925202e-06, + "loss": 1.2625, + "step": 6477 + }, + { + "epoch": 0.68, + "learning_rate": 5.636916194952683e-06, + "loss": 1.3648, + "step": 6478 + }, + { + "epoch": 0.68, + "learning_rate": 5.633623004521285e-06, + "loss": 1.3115, + "step": 6479 + }, + { + "epoch": 0.68, + "learning_rate": 5.6303303990722154e-06, + "loss": 1.2755, + "step": 6480 + }, + { + "epoch": 0.68, + "learning_rate": 5.627038379046595e-06, + "loss": 1.4546, + "step": 6481 + }, + { + "epoch": 0.68, + "learning_rate": 5.623746944885473e-06, + "loss": 1.3717, + "step": 6482 + }, + { + "epoch": 0.68, + "learning_rate": 5.620456097029818e-06, + "loss": 1.3188, + "step": 6483 + }, + { + "epoch": 0.68, + "learning_rate": 5.61716583592052e-06, + "loss": 1.3166, + "step": 6484 + }, + { + "epoch": 0.68, + "learning_rate": 5.613876161998377e-06, + "loss": 1.3413, + "step": 6485 + }, + { + "epoch": 0.68, + "learning_rate": 5.610587075704139e-06, + "loss": 1.395, + "step": 6486 + }, + { + "epoch": 0.68, + "learning_rate": 5.6072985774784465e-06, + "loss": 1.2914, + "step": 6487 + }, + { + "epoch": 0.68, + "learning_rate": 5.604010667761876e-06, + "loss": 1.3118, + "step": 6488 + }, + { + "epoch": 0.68, + "learning_rate": 5.600723346994932e-06, + "loss": 1.3599, + "step": 6489 + }, + { + "epoch": 0.68, + "learning_rate": 5.597436615618017e-06, + "loss": 1.2862, + "step": 6490 + }, + { + "epoch": 0.68, + "learning_rate": 5.594150474071481e-06, + "loss": 1.3585, + "step": 6491 + }, + { + "epoch": 0.68, + "learning_rate": 5.590864922795573e-06, + "loss": 1.3449, + "step": 6492 + }, + { + "epoch": 0.68, + "learning_rate": 5.587579962230475e-06, + "loss": 1.2787, + "step": 6493 + }, + { + "epoch": 0.68, + "learning_rate": 5.5842955928162934e-06, + "loss": 1.3755, + "step": 6494 + }, + { + "epoch": 0.68, + "learning_rate": 5.5810118149930406e-06, + "loss": 1.2858, + "step": 6495 + }, + { + "epoch": 0.68, + "learning_rate": 5.577728629200662e-06, + "loss": 1.4214, + "step": 6496 + }, + { + "epoch": 0.68, + "learning_rate": 5.574446035879024e-06, + "loss": 1.5007, + "step": 6497 + }, + { + "epoch": 0.68, + "learning_rate": 5.571164035467903e-06, + "loss": 1.2952, + "step": 6498 + }, + { + "epoch": 0.68, + "learning_rate": 5.56788262840701e-06, + "loss": 1.267, + "step": 6499 + }, + { + "epoch": 0.68, + "learning_rate": 5.564601815135962e-06, + "loss": 1.3168, + "step": 6500 + }, + { + "epoch": 0.68, + "learning_rate": 5.561321596094305e-06, + "loss": 1.2992, + "step": 6501 + }, + { + "epoch": 0.68, + "learning_rate": 5.558041971721511e-06, + "loss": 1.4237, + "step": 6502 + }, + { + "epoch": 0.68, + "learning_rate": 5.554762942456959e-06, + "loss": 1.3865, + "step": 6503 + }, + { + "epoch": 0.68, + "learning_rate": 5.5514845087399505e-06, + "loss": 1.2875, + "step": 6504 + }, + { + "epoch": 0.68, + "learning_rate": 5.548206671009724e-06, + "loss": 1.3011, + "step": 6505 + }, + { + "epoch": 0.68, + "learning_rate": 5.544929429705415e-06, + "loss": 1.3425, + "step": 6506 + }, + { + "epoch": 0.68, + "learning_rate": 5.541652785266095e-06, + "loss": 1.4265, + "step": 6507 + }, + { + "epoch": 0.68, + "learning_rate": 5.538376738130747e-06, + "loss": 1.2877, + "step": 6508 + }, + { + "epoch": 0.68, + "learning_rate": 5.535101288738276e-06, + "loss": 1.3652, + "step": 6509 + }, + { + "epoch": 0.68, + "learning_rate": 5.5318264375275145e-06, + "loss": 1.2997, + "step": 6510 + }, + { + "epoch": 0.68, + "learning_rate": 5.528552184937201e-06, + "loss": 1.3223, + "step": 6511 + }, + { + "epoch": 0.68, + "learning_rate": 5.525278531406006e-06, + "loss": 1.2897, + "step": 6512 + }, + { + "epoch": 0.68, + "learning_rate": 5.522005477372516e-06, + "loss": 1.3554, + "step": 6513 + }, + { + "epoch": 0.68, + "learning_rate": 5.51873302327523e-06, + "loss": 1.3233, + "step": 6514 + }, + { + "epoch": 0.68, + "learning_rate": 5.515461169552576e-06, + "loss": 1.3536, + "step": 6515 + }, + { + "epoch": 0.68, + "learning_rate": 5.5121899166429046e-06, + "loss": 1.3485, + "step": 6516 + }, + { + "epoch": 0.68, + "learning_rate": 5.508919264984468e-06, + "loss": 1.3264, + "step": 6517 + }, + { + "epoch": 0.68, + "learning_rate": 5.505649215015461e-06, + "loss": 1.4498, + "step": 6518 + }, + { + "epoch": 0.68, + "learning_rate": 5.5023797671739755e-06, + "loss": 1.4468, + "step": 6519 + }, + { + "epoch": 0.68, + "learning_rate": 5.499110921898038e-06, + "loss": 1.2659, + "step": 6520 + }, + { + "epoch": 0.68, + "learning_rate": 5.4958426796255934e-06, + "loss": 1.318, + "step": 6521 + }, + { + "epoch": 0.68, + "learning_rate": 5.492575040794498e-06, + "loss": 1.3167, + "step": 6522 + }, + { + "epoch": 0.68, + "learning_rate": 5.48930800584253e-06, + "loss": 1.3453, + "step": 6523 + }, + { + "epoch": 0.68, + "learning_rate": 5.486041575207397e-06, + "loss": 1.2557, + "step": 6524 + }, + { + "epoch": 0.68, + "learning_rate": 5.482775749326705e-06, + "loss": 1.3235, + "step": 6525 + }, + { + "epoch": 0.68, + "learning_rate": 5.479510528638001e-06, + "loss": 1.3119, + "step": 6526 + }, + { + "epoch": 0.68, + "learning_rate": 5.476245913578733e-06, + "loss": 1.4639, + "step": 6527 + }, + { + "epoch": 0.68, + "learning_rate": 5.472981904586277e-06, + "loss": 1.3233, + "step": 6528 + }, + { + "epoch": 0.68, + "learning_rate": 5.469718502097931e-06, + "loss": 1.2722, + "step": 6529 + }, + { + "epoch": 0.68, + "learning_rate": 5.466455706550906e-06, + "loss": 1.4428, + "step": 6530 + }, + { + "epoch": 0.68, + "learning_rate": 5.463193518382321e-06, + "loss": 1.5695, + "step": 6531 + }, + { + "epoch": 0.68, + "learning_rate": 5.4599319380292434e-06, + "loss": 1.3161, + "step": 6532 + }, + { + "epoch": 0.69, + "learning_rate": 5.4566709659286296e-06, + "loss": 1.3513, + "step": 6533 + }, + { + "epoch": 0.69, + "learning_rate": 5.453410602517368e-06, + "loss": 1.2716, + "step": 6534 + }, + { + "epoch": 0.69, + "learning_rate": 5.45015084823227e-06, + "loss": 1.4467, + "step": 6535 + }, + { + "epoch": 0.69, + "learning_rate": 5.44689170351005e-06, + "loss": 1.4082, + "step": 6536 + }, + { + "epoch": 0.69, + "learning_rate": 5.443633168787357e-06, + "loss": 1.303, + "step": 6537 + }, + { + "epoch": 0.69, + "learning_rate": 5.440375244500743e-06, + "loss": 1.2765, + "step": 6538 + }, + { + "epoch": 0.69, + "learning_rate": 5.43711793108669e-06, + "loss": 1.6814, + "step": 6539 + }, + { + "epoch": 0.69, + "learning_rate": 5.4338612289816e-06, + "loss": 1.3899, + "step": 6540 + }, + { + "epoch": 0.69, + "learning_rate": 5.430605138621778e-06, + "loss": 1.201, + "step": 6541 + }, + { + "epoch": 0.69, + "learning_rate": 5.42734966044346e-06, + "loss": 1.3214, + "step": 6542 + }, + { + "epoch": 0.69, + "learning_rate": 5.424094794882801e-06, + "loss": 1.2676, + "step": 6543 + }, + { + "epoch": 0.69, + "learning_rate": 5.420840542375862e-06, + "loss": 1.3006, + "step": 6544 + }, + { + "epoch": 0.69, + "learning_rate": 5.4175869033586355e-06, + "loss": 1.32, + "step": 6545 + }, + { + "epoch": 0.69, + "learning_rate": 5.41433387826702e-06, + "loss": 1.3347, + "step": 6546 + }, + { + "epoch": 0.69, + "learning_rate": 5.41108146753684e-06, + "loss": 1.3983, + "step": 6547 + }, + { + "epoch": 0.69, + "learning_rate": 5.407829671603838e-06, + "loss": 1.3756, + "step": 6548 + }, + { + "epoch": 0.69, + "learning_rate": 5.404578490903664e-06, + "loss": 1.3444, + "step": 6549 + }, + { + "epoch": 0.69, + "learning_rate": 5.4013279258718974e-06, + "loss": 1.3369, + "step": 6550 + }, + { + "epoch": 0.69, + "learning_rate": 5.398077976944034e-06, + "loss": 1.2995, + "step": 6551 + }, + { + "epoch": 0.69, + "learning_rate": 5.394828644555475e-06, + "loss": 1.3305, + "step": 6552 + }, + { + "epoch": 0.69, + "learning_rate": 5.391579929141554e-06, + "loss": 1.3743, + "step": 6553 + }, + { + "epoch": 0.69, + "learning_rate": 5.3883318311375095e-06, + "loss": 1.2829, + "step": 6554 + }, + { + "epoch": 0.69, + "learning_rate": 5.3850843509785065e-06, + "loss": 1.379, + "step": 6555 + }, + { + "epoch": 0.69, + "learning_rate": 5.3818374890996295e-06, + "loss": 1.3236, + "step": 6556 + }, + { + "epoch": 0.69, + "learning_rate": 5.378591245935865e-06, + "loss": 1.3469, + "step": 6557 + }, + { + "epoch": 0.69, + "learning_rate": 5.375345621922129e-06, + "loss": 1.3318, + "step": 6558 + }, + { + "epoch": 0.69, + "learning_rate": 5.3721006174932576e-06, + "loss": 1.3395, + "step": 6559 + }, + { + "epoch": 0.69, + "learning_rate": 5.36885623308399e-06, + "loss": 1.4148, + "step": 6560 + }, + { + "epoch": 0.69, + "learning_rate": 5.365612469128993e-06, + "loss": 1.3007, + "step": 6561 + }, + { + "epoch": 0.69, + "learning_rate": 5.362369326062853e-06, + "loss": 1.4365, + "step": 6562 + }, + { + "epoch": 0.69, + "learning_rate": 5.3591268043200585e-06, + "loss": 1.4269, + "step": 6563 + }, + { + "epoch": 0.69, + "learning_rate": 5.355884904335034e-06, + "loss": 1.2619, + "step": 6564 + }, + { + "epoch": 0.69, + "learning_rate": 5.3526436265421e-06, + "loss": 1.2678, + "step": 6565 + }, + { + "epoch": 0.69, + "learning_rate": 5.34940297137551e-06, + "loss": 1.2541, + "step": 6566 + }, + { + "epoch": 0.69, + "learning_rate": 5.3461629392694345e-06, + "loss": 1.3237, + "step": 6567 + }, + { + "epoch": 0.69, + "eval_loss": 1.402653694152832, + "eval_runtime": 77.5033, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 6567 + }, + { + "epoch": 0.69, + "learning_rate": 5.342923530657944e-06, + "loss": 1.357, + "step": 6568 + }, + { + "epoch": 0.69, + "learning_rate": 5.33968474597504e-06, + "loss": 1.3561, + "step": 6569 + }, + { + "epoch": 0.69, + "learning_rate": 5.336446585654642e-06, + "loss": 1.2969, + "step": 6570 + }, + { + "epoch": 0.69, + "learning_rate": 5.33320905013057e-06, + "loss": 1.2922, + "step": 6571 + }, + { + "epoch": 0.69, + "learning_rate": 5.329972139836581e-06, + "loss": 1.3581, + "step": 6572 + }, + { + "epoch": 0.69, + "learning_rate": 5.326735855206328e-06, + "loss": 1.2926, + "step": 6573 + }, + { + "epoch": 0.69, + "learning_rate": 5.3235001966733965e-06, + "loss": 1.3933, + "step": 6574 + }, + { + "epoch": 0.69, + "learning_rate": 5.320265164671283e-06, + "loss": 1.4009, + "step": 6575 + }, + { + "epoch": 0.69, + "learning_rate": 5.3170307596333955e-06, + "loss": 1.4051, + "step": 6576 + }, + { + "epoch": 0.69, + "learning_rate": 5.313796981993054e-06, + "loss": 1.3448, + "step": 6577 + }, + { + "epoch": 0.69, + "learning_rate": 5.310563832183515e-06, + "loss": 1.3141, + "step": 6578 + }, + { + "epoch": 0.69, + "learning_rate": 5.307331310637929e-06, + "loss": 1.3658, + "step": 6579 + }, + { + "epoch": 0.69, + "learning_rate": 5.3040994177893725e-06, + "loss": 1.2881, + "step": 6580 + }, + { + "epoch": 0.69, + "learning_rate": 5.30086815407084e-06, + "loss": 1.3051, + "step": 6581 + }, + { + "epoch": 0.69, + "learning_rate": 5.297637519915231e-06, + "loss": 1.3353, + "step": 6582 + }, + { + "epoch": 0.69, + "learning_rate": 5.2944075157553754e-06, + "loss": 1.3997, + "step": 6583 + }, + { + "epoch": 0.69, + "learning_rate": 5.291178142024002e-06, + "loss": 1.3094, + "step": 6584 + }, + { + "epoch": 0.69, + "learning_rate": 5.287949399153769e-06, + "loss": 1.3384, + "step": 6585 + }, + { + "epoch": 0.69, + "learning_rate": 5.284721287577248e-06, + "loss": 1.3183, + "step": 6586 + }, + { + "epoch": 0.69, + "learning_rate": 5.281493807726916e-06, + "loss": 1.4433, + "step": 6587 + }, + { + "epoch": 0.69, + "learning_rate": 5.278266960035174e-06, + "loss": 1.3103, + "step": 6588 + }, + { + "epoch": 0.69, + "learning_rate": 5.275040744934343e-06, + "loss": 1.3478, + "step": 6589 + }, + { + "epoch": 0.69, + "learning_rate": 5.271815162856645e-06, + "loss": 1.2713, + "step": 6590 + }, + { + "epoch": 0.69, + "learning_rate": 5.268590214234233e-06, + "loss": 1.3697, + "step": 6591 + }, + { + "epoch": 0.69, + "learning_rate": 5.265365899499156e-06, + "loss": 1.6169, + "step": 6592 + }, + { + "epoch": 0.69, + "learning_rate": 5.262142219083398e-06, + "loss": 1.2988, + "step": 6593 + }, + { + "epoch": 0.69, + "learning_rate": 5.258919173418851e-06, + "loss": 1.515, + "step": 6594 + }, + { + "epoch": 0.69, + "learning_rate": 5.2556967629373125e-06, + "loss": 1.3704, + "step": 6595 + }, + { + "epoch": 0.69, + "learning_rate": 5.2524749880705075e-06, + "loss": 1.2404, + "step": 6596 + }, + { + "epoch": 0.69, + "learning_rate": 5.249253849250073e-06, + "loss": 1.2799, + "step": 6597 + }, + { + "epoch": 0.69, + "learning_rate": 5.246033346907553e-06, + "loss": 1.2876, + "step": 6598 + }, + { + "epoch": 0.69, + "learning_rate": 5.24281348147442e-06, + "loss": 1.3058, + "step": 6599 + }, + { + "epoch": 0.69, + "learning_rate": 5.239594253382043e-06, + "loss": 1.3347, + "step": 6600 + }, + { + "epoch": 0.69, + "learning_rate": 5.236375663061722e-06, + "loss": 1.3323, + "step": 6601 + }, + { + "epoch": 0.69, + "learning_rate": 5.23315771094467e-06, + "loss": 1.3254, + "step": 6602 + }, + { + "epoch": 0.69, + "learning_rate": 5.229940397461999e-06, + "loss": 1.3462, + "step": 6603 + }, + { + "epoch": 0.69, + "learning_rate": 5.226723723044753e-06, + "loss": 1.2901, + "step": 6604 + }, + { + "epoch": 0.69, + "learning_rate": 5.223507688123887e-06, + "loss": 1.3079, + "step": 6605 + }, + { + "epoch": 0.69, + "learning_rate": 5.220292293130258e-06, + "loss": 1.4282, + "step": 6606 + }, + { + "epoch": 0.69, + "learning_rate": 5.217077538494651e-06, + "loss": 1.3197, + "step": 6607 + }, + { + "epoch": 0.69, + "learning_rate": 5.213863424647765e-06, + "loss": 1.3581, + "step": 6608 + }, + { + "epoch": 0.69, + "learning_rate": 5.2106499520202005e-06, + "loss": 1.3322, + "step": 6609 + }, + { + "epoch": 0.69, + "learning_rate": 5.207437121042488e-06, + "loss": 1.3368, + "step": 6610 + }, + { + "epoch": 0.69, + "learning_rate": 5.204224932145056e-06, + "loss": 1.2771, + "step": 6611 + }, + { + "epoch": 0.69, + "learning_rate": 5.20101338575826e-06, + "loss": 1.2852, + "step": 6612 + }, + { + "epoch": 0.69, + "learning_rate": 5.197802482312369e-06, + "loss": 1.3733, + "step": 6613 + }, + { + "epoch": 0.69, + "learning_rate": 5.194592222237551e-06, + "loss": 1.3719, + "step": 6614 + }, + { + "epoch": 0.69, + "learning_rate": 5.191382605963906e-06, + "loss": 1.3658, + "step": 6615 + }, + { + "epoch": 0.69, + "learning_rate": 5.1881736339214415e-06, + "loss": 1.3261, + "step": 6616 + }, + { + "epoch": 0.69, + "learning_rate": 5.18496530654007e-06, + "loss": 1.3057, + "step": 6617 + }, + { + "epoch": 0.69, + "learning_rate": 5.181757624249635e-06, + "loss": 1.2665, + "step": 6618 + }, + { + "epoch": 0.69, + "learning_rate": 5.1785505874798716e-06, + "loss": 1.2839, + "step": 6619 + }, + { + "epoch": 0.69, + "learning_rate": 5.175344196660447e-06, + "loss": 1.3131, + "step": 6620 + }, + { + "epoch": 0.69, + "learning_rate": 5.1721384522209385e-06, + "loss": 1.3217, + "step": 6621 + }, + { + "epoch": 0.69, + "learning_rate": 5.168933354590825e-06, + "loss": 1.3306, + "step": 6622 + }, + { + "epoch": 0.69, + "learning_rate": 5.165728904199512e-06, + "loss": 1.3197, + "step": 6623 + }, + { + "epoch": 0.69, + "learning_rate": 5.1625251014763176e-06, + "loss": 1.3035, + "step": 6624 + }, + { + "epoch": 0.69, + "learning_rate": 5.1593219468504605e-06, + "loss": 1.2927, + "step": 6625 + }, + { + "epoch": 0.69, + "learning_rate": 5.156119440751086e-06, + "loss": 1.3333, + "step": 6626 + }, + { + "epoch": 0.69, + "learning_rate": 5.152917583607251e-06, + "loss": 1.3181, + "step": 6627 + }, + { + "epoch": 0.7, + "learning_rate": 5.149716375847913e-06, + "loss": 1.347, + "step": 6628 + }, + { + "epoch": 0.7, + "learning_rate": 5.14651581790196e-06, + "loss": 1.347, + "step": 6629 + }, + { + "epoch": 0.7, + "learning_rate": 5.143315910198179e-06, + "loss": 1.2892, + "step": 6630 + }, + { + "epoch": 0.7, + "learning_rate": 5.140116653165277e-06, + "loss": 1.2996, + "step": 6631 + }, + { + "epoch": 0.7, + "learning_rate": 5.136918047231876e-06, + "loss": 1.2802, + "step": 6632 + }, + { + "epoch": 0.7, + "learning_rate": 5.133720092826501e-06, + "loss": 1.2766, + "step": 6633 + }, + { + "epoch": 0.7, + "learning_rate": 5.130522790377598e-06, + "loss": 1.5365, + "step": 6634 + }, + { + "epoch": 0.7, + "learning_rate": 5.127326140313528e-06, + "loss": 1.4848, + "step": 6635 + }, + { + "epoch": 0.7, + "learning_rate": 5.124130143062551e-06, + "loss": 1.3712, + "step": 6636 + }, + { + "epoch": 0.7, + "learning_rate": 5.120934799052859e-06, + "loss": 1.3094, + "step": 6637 + }, + { + "epoch": 0.7, + "learning_rate": 5.1177401087125355e-06, + "loss": 1.272, + "step": 6638 + }, + { + "epoch": 0.7, + "learning_rate": 5.114546072469593e-06, + "loss": 1.2856, + "step": 6639 + }, + { + "epoch": 0.7, + "learning_rate": 5.111352690751952e-06, + "loss": 1.2886, + "step": 6640 + }, + { + "epoch": 0.7, + "learning_rate": 5.108159963987436e-06, + "loss": 1.277, + "step": 6641 + }, + { + "epoch": 0.7, + "learning_rate": 5.104967892603794e-06, + "loss": 1.3392, + "step": 6642 + }, + { + "epoch": 0.7, + "learning_rate": 5.101776477028684e-06, + "loss": 1.3036, + "step": 6643 + }, + { + "epoch": 0.7, + "learning_rate": 5.098585717689667e-06, + "loss": 1.4116, + "step": 6644 + }, + { + "epoch": 0.7, + "learning_rate": 5.095395615014226e-06, + "loss": 1.3437, + "step": 6645 + }, + { + "epoch": 0.7, + "learning_rate": 5.0922061694297565e-06, + "loss": 1.2608, + "step": 6646 + }, + { + "epoch": 0.7, + "learning_rate": 5.089017381363554e-06, + "loss": 1.2959, + "step": 6647 + }, + { + "epoch": 0.7, + "learning_rate": 5.085829251242844e-06, + "loss": 1.3508, + "step": 6648 + }, + { + "epoch": 0.7, + "learning_rate": 5.0826417794947455e-06, + "loss": 1.34, + "step": 6649 + }, + { + "epoch": 0.7, + "learning_rate": 5.0794549665463e-06, + "loss": 1.3092, + "step": 6650 + }, + { + "epoch": 0.7, + "learning_rate": 5.076268812824463e-06, + "loss": 1.3417, + "step": 6651 + }, + { + "epoch": 0.7, + "learning_rate": 5.073083318756092e-06, + "loss": 1.3424, + "step": 6652 + }, + { + "epoch": 0.7, + "learning_rate": 5.069898484767961e-06, + "loss": 1.3296, + "step": 6653 + }, + { + "epoch": 0.7, + "learning_rate": 5.066714311286762e-06, + "loss": 1.2852, + "step": 6654 + }, + { + "epoch": 0.7, + "learning_rate": 5.063530798739087e-06, + "loss": 1.3462, + "step": 6655 + }, + { + "epoch": 0.7, + "learning_rate": 5.06034794755145e-06, + "loss": 1.3615, + "step": 6656 + }, + { + "epoch": 0.7, + "learning_rate": 5.057165758150262e-06, + "loss": 1.245, + "step": 6657 + }, + { + "epoch": 0.7, + "learning_rate": 5.053984230961862e-06, + "loss": 1.201, + "step": 6658 + }, + { + "epoch": 0.7, + "learning_rate": 5.050803366412494e-06, + "loss": 1.331, + "step": 6659 + }, + { + "epoch": 0.7, + "learning_rate": 5.047623164928306e-06, + "loss": 1.3034, + "step": 6660 + }, + { + "epoch": 0.7, + "learning_rate": 5.044443626935367e-06, + "loss": 1.2822, + "step": 6661 + }, + { + "epoch": 0.7, + "learning_rate": 5.041264752859657e-06, + "loss": 1.2576, + "step": 6662 + }, + { + "epoch": 0.7, + "learning_rate": 5.038086543127055e-06, + "loss": 1.3198, + "step": 6663 + }, + { + "epoch": 0.7, + "learning_rate": 5.034908998163368e-06, + "loss": 1.2892, + "step": 6664 + }, + { + "epoch": 0.7, + "learning_rate": 5.031732118394299e-06, + "loss": 1.3004, + "step": 6665 + }, + { + "epoch": 0.7, + "learning_rate": 5.028555904245469e-06, + "loss": 1.3178, + "step": 6666 + }, + { + "epoch": 0.7, + "learning_rate": 5.0253803561424156e-06, + "loss": 1.3014, + "step": 6667 + }, + { + "epoch": 0.7, + "learning_rate": 5.022205474510571e-06, + "loss": 1.3151, + "step": 6668 + }, + { + "epoch": 0.7, + "learning_rate": 5.019031259775292e-06, + "loss": 1.3551, + "step": 6669 + }, + { + "epoch": 0.7, + "learning_rate": 5.015857712361847e-06, + "loss": 1.4188, + "step": 6670 + }, + { + "epoch": 0.7, + "learning_rate": 5.0126848326954025e-06, + "loss": 1.2743, + "step": 6671 + }, + { + "epoch": 0.7, + "learning_rate": 5.009512621201043e-06, + "loss": 1.3528, + "step": 6672 + }, + { + "epoch": 0.7, + "learning_rate": 5.006341078303771e-06, + "loss": 1.309, + "step": 6673 + }, + { + "epoch": 0.7, + "learning_rate": 5.003170204428483e-06, + "loss": 1.3353, + "step": 6674 + }, + { + "epoch": 0.7, + "learning_rate": 5.000000000000003e-06, + "loss": 1.2753, + "step": 6675 + }, + { + "epoch": 0.7, + "learning_rate": 4.9968304654430465e-06, + "loss": 1.3907, + "step": 6676 + }, + { + "epoch": 0.7, + "learning_rate": 4.993661601182256e-06, + "loss": 1.2876, + "step": 6677 + }, + { + "epoch": 0.7, + "learning_rate": 4.990493407642181e-06, + "loss": 1.2534, + "step": 6678 + }, + { + "epoch": 0.7, + "learning_rate": 4.98732588524727e-06, + "loss": 1.3352, + "step": 6679 + }, + { + "epoch": 0.7, + "learning_rate": 4.984159034421895e-06, + "loss": 1.3302, + "step": 6680 + }, + { + "epoch": 0.7, + "learning_rate": 4.980992855590336e-06, + "loss": 1.3783, + "step": 6681 + }, + { + "epoch": 0.7, + "learning_rate": 4.977827349176769e-06, + "loss": 1.2848, + "step": 6682 + }, + { + "epoch": 0.7, + "learning_rate": 4.974662515605302e-06, + "loss": 1.3269, + "step": 6683 + }, + { + "epoch": 0.7, + "learning_rate": 4.971498355299932e-06, + "loss": 1.3662, + "step": 6684 + }, + { + "epoch": 0.7, + "learning_rate": 4.968334868684579e-06, + "loss": 1.2508, + "step": 6685 + }, + { + "epoch": 0.7, + "learning_rate": 4.965172056183073e-06, + "loss": 1.3872, + "step": 6686 + }, + { + "epoch": 0.7, + "learning_rate": 4.962009918219142e-06, + "loss": 1.3008, + "step": 6687 + }, + { + "epoch": 0.7, + "learning_rate": 4.958848455216434e-06, + "loss": 1.2058, + "step": 6688 + }, + { + "epoch": 0.7, + "learning_rate": 4.95568766759851e-06, + "loss": 1.3127, + "step": 6689 + }, + { + "epoch": 0.7, + "learning_rate": 4.952527555788825e-06, + "loss": 1.2985, + "step": 6690 + }, + { + "epoch": 0.7, + "learning_rate": 4.949368120210757e-06, + "loss": 1.333, + "step": 6691 + }, + { + "epoch": 0.7, + "learning_rate": 4.946209361287593e-06, + "loss": 1.2945, + "step": 6692 + }, + { + "epoch": 0.7, + "learning_rate": 4.943051279442516e-06, + "loss": 1.262, + "step": 6693 + }, + { + "epoch": 0.7, + "learning_rate": 4.93989387509864e-06, + "loss": 1.6155, + "step": 6694 + }, + { + "epoch": 0.7, + "learning_rate": 4.936737148678965e-06, + "loss": 1.2838, + "step": 6695 + }, + { + "epoch": 0.7, + "learning_rate": 4.933581100606415e-06, + "loss": 1.3778, + "step": 6696 + }, + { + "epoch": 0.7, + "learning_rate": 4.930425731303824e-06, + "loss": 1.3624, + "step": 6697 + }, + { + "epoch": 0.7, + "learning_rate": 4.927271041193923e-06, + "loss": 1.2641, + "step": 6698 + }, + { + "epoch": 0.7, + "learning_rate": 4.924117030699362e-06, + "loss": 1.3314, + "step": 6699 + }, + { + "epoch": 0.7, + "learning_rate": 4.920963700242704e-06, + "loss": 1.328, + "step": 6700 + }, + { + "epoch": 0.7, + "learning_rate": 4.917811050246404e-06, + "loss": 1.3128, + "step": 6701 + }, + { + "epoch": 0.7, + "learning_rate": 4.914659081132843e-06, + "loss": 1.3877, + "step": 6702 + }, + { + "epoch": 0.7, + "learning_rate": 4.911507793324299e-06, + "loss": 1.3114, + "step": 6703 + }, + { + "epoch": 0.7, + "learning_rate": 4.908357187242967e-06, + "loss": 1.3592, + "step": 6704 + }, + { + "epoch": 0.7, + "learning_rate": 4.905207263310948e-06, + "loss": 1.329, + "step": 6705 + }, + { + "epoch": 0.7, + "learning_rate": 4.902058021950247e-06, + "loss": 1.2558, + "step": 6706 + }, + { + "epoch": 0.7, + "learning_rate": 4.898909463582784e-06, + "loss": 1.2489, + "step": 6707 + }, + { + "epoch": 0.7, + "learning_rate": 4.895761588630388e-06, + "loss": 1.2817, + "step": 6708 + }, + { + "epoch": 0.7, + "learning_rate": 4.892614397514785e-06, + "loss": 1.1606, + "step": 6709 + }, + { + "epoch": 0.7, + "learning_rate": 4.889467890657628e-06, + "loss": 1.2878, + "step": 6710 + }, + { + "epoch": 0.7, + "learning_rate": 4.886322068480458e-06, + "loss": 1.2747, + "step": 6711 + }, + { + "epoch": 0.7, + "learning_rate": 4.88317693140474e-06, + "loss": 1.3662, + "step": 6712 + }, + { + "epoch": 0.7, + "learning_rate": 4.880032479851844e-06, + "loss": 1.3009, + "step": 6713 + }, + { + "epoch": 0.7, + "learning_rate": 4.8768887142430385e-06, + "loss": 1.3157, + "step": 6714 + }, + { + "epoch": 0.7, + "learning_rate": 4.873745634999511e-06, + "loss": 1.4461, + "step": 6715 + }, + { + "epoch": 0.7, + "learning_rate": 4.870603242542358e-06, + "loss": 1.3818, + "step": 6716 + }, + { + "epoch": 0.7, + "learning_rate": 4.86746153729257e-06, + "loss": 1.3361, + "step": 6717 + }, + { + "epoch": 0.7, + "learning_rate": 4.864320519671061e-06, + "loss": 1.3147, + "step": 6718 + }, + { + "epoch": 0.7, + "learning_rate": 4.8611801900986485e-06, + "loss": 1.3773, + "step": 6719 + }, + { + "epoch": 0.7, + "learning_rate": 4.858040548996049e-06, + "loss": 1.3091, + "step": 6720 + }, + { + "epoch": 0.7, + "learning_rate": 4.854901596783902e-06, + "loss": 1.3314, + "step": 6721 + }, + { + "epoch": 0.7, + "learning_rate": 4.851763333882738e-06, + "loss": 1.3082, + "step": 6722 + }, + { + "epoch": 0.71, + "learning_rate": 4.848625760713007e-06, + "loss": 1.2687, + "step": 6723 + }, + { + "epoch": 0.71, + "learning_rate": 4.845488877695068e-06, + "loss": 1.3378, + "step": 6724 + }, + { + "epoch": 0.71, + "learning_rate": 4.842352685249174e-06, + "loss": 1.3516, + "step": 6725 + }, + { + "epoch": 0.71, + "learning_rate": 4.839217183795501e-06, + "loss": 1.4083, + "step": 6726 + }, + { + "epoch": 0.71, + "learning_rate": 4.836082373754124e-06, + "loss": 1.3073, + "step": 6727 + }, + { + "epoch": 0.71, + "learning_rate": 4.832948255545024e-06, + "loss": 1.2948, + "step": 6728 + }, + { + "epoch": 0.71, + "learning_rate": 4.829814829588099e-06, + "loss": 1.3323, + "step": 6729 + }, + { + "epoch": 0.71, + "learning_rate": 4.826682096303139e-06, + "loss": 1.3101, + "step": 6730 + }, + { + "epoch": 0.71, + "learning_rate": 4.823550056109853e-06, + "loss": 1.3323, + "step": 6731 + }, + { + "epoch": 0.71, + "learning_rate": 4.8204187094278605e-06, + "loss": 1.3862, + "step": 6732 + }, + { + "epoch": 0.71, + "learning_rate": 4.817288056676671e-06, + "loss": 1.3112, + "step": 6733 + }, + { + "epoch": 0.71, + "learning_rate": 4.8141580982757175e-06, + "loss": 1.297, + "step": 6734 + }, + { + "epoch": 0.71, + "learning_rate": 4.811028834644336e-06, + "loss": 1.2604, + "step": 6735 + }, + { + "epoch": 0.71, + "learning_rate": 4.807900266201761e-06, + "loss": 1.343, + "step": 6736 + }, + { + "epoch": 0.71, + "learning_rate": 4.804772393367142e-06, + "loss": 1.3254, + "step": 6737 + }, + { + "epoch": 0.71, + "learning_rate": 4.80164521655954e-06, + "loss": 1.2688, + "step": 6738 + }, + { + "epoch": 0.71, + "learning_rate": 4.798518736197909e-06, + "loss": 1.2693, + "step": 6739 + }, + { + "epoch": 0.71, + "learning_rate": 4.795392952701122e-06, + "loss": 1.4536, + "step": 6740 + }, + { + "epoch": 0.71, + "learning_rate": 4.7922678664879485e-06, + "loss": 1.3811, + "step": 6741 + }, + { + "epoch": 0.71, + "learning_rate": 4.789143477977072e-06, + "loss": 1.2584, + "step": 6742 + }, + { + "epoch": 0.71, + "learning_rate": 4.786019787587084e-06, + "loss": 1.2584, + "step": 6743 + }, + { + "epoch": 0.71, + "learning_rate": 4.782896795736472e-06, + "loss": 1.2005, + "step": 6744 + }, + { + "epoch": 0.71, + "learning_rate": 4.779774502843642e-06, + "loss": 1.335, + "step": 6745 + }, + { + "epoch": 0.71, + "learning_rate": 4.776652909326901e-06, + "loss": 1.3675, + "step": 6746 + }, + { + "epoch": 0.71, + "learning_rate": 4.773532015604457e-06, + "loss": 1.3794, + "step": 6747 + }, + { + "epoch": 0.71, + "learning_rate": 4.770411822094437e-06, + "loss": 1.3629, + "step": 6748 + }, + { + "epoch": 0.71, + "learning_rate": 4.76729232921486e-06, + "loss": 1.0805, + "step": 6749 + }, + { + "epoch": 0.71, + "learning_rate": 4.76417353738366e-06, + "loss": 1.2874, + "step": 6750 + }, + { + "epoch": 0.71, + "learning_rate": 4.761055447018681e-06, + "loss": 1.428, + "step": 6751 + }, + { + "epoch": 0.71, + "learning_rate": 4.757938058537656e-06, + "loss": 1.2935, + "step": 6752 + }, + { + "epoch": 0.71, + "learning_rate": 4.754821372358242e-06, + "loss": 1.4202, + "step": 6753 + }, + { + "epoch": 0.71, + "learning_rate": 4.751705388897997e-06, + "loss": 1.3109, + "step": 6754 + }, + { + "epoch": 0.71, + "learning_rate": 4.7485901085743754e-06, + "loss": 1.3319, + "step": 6755 + }, + { + "epoch": 0.71, + "learning_rate": 4.745475531804753e-06, + "loss": 1.3246, + "step": 6756 + }, + { + "epoch": 0.71, + "learning_rate": 4.742361659006395e-06, + "loss": 1.3407, + "step": 6757 + }, + { + "epoch": 0.71, + "learning_rate": 4.739248490596483e-06, + "loss": 1.2953, + "step": 6758 + }, + { + "epoch": 0.71, + "learning_rate": 4.736136026992107e-06, + "loss": 1.3214, + "step": 6759 + }, + { + "epoch": 0.71, + "learning_rate": 4.733024268610249e-06, + "loss": 1.4112, + "step": 6760 + }, + { + "epoch": 0.71, + "learning_rate": 4.7299132158678085e-06, + "loss": 1.2981, + "step": 6761 + }, + { + "epoch": 0.71, + "learning_rate": 4.726802869181591e-06, + "loss": 1.2975, + "step": 6762 + }, + { + "epoch": 0.71, + "learning_rate": 4.723693228968293e-06, + "loss": 1.3047, + "step": 6763 + }, + { + "epoch": 0.71, + "learning_rate": 4.720584295644533e-06, + "loss": 1.3906, + "step": 6764 + }, + { + "epoch": 0.71, + "learning_rate": 4.717476069626832e-06, + "loss": 1.2523, + "step": 6765 + }, + { + "epoch": 0.71, + "learning_rate": 4.7143685513316025e-06, + "loss": 1.0453, + "step": 6766 + }, + { + "epoch": 0.71, + "eval_loss": 1.4004828929901123, + "eval_runtime": 77.565, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 6766 + }, + { + "epoch": 0.71, + "learning_rate": 4.711261741175182e-06, + "loss": 1.1339, + "step": 6767 + }, + { + "epoch": 0.71, + "learning_rate": 4.7081556395737935e-06, + "loss": 1.2401, + "step": 6768 + }, + { + "epoch": 0.71, + "learning_rate": 4.705050246943581e-06, + "loss": 1.3009, + "step": 6769 + }, + { + "epoch": 0.71, + "learning_rate": 4.7019455637005895e-06, + "loss": 1.3106, + "step": 6770 + }, + { + "epoch": 0.71, + "learning_rate": 4.698841590260758e-06, + "loss": 1.3021, + "step": 6771 + }, + { + "epoch": 0.71, + "learning_rate": 4.695738327039947e-06, + "loss": 1.3147, + "step": 6772 + }, + { + "epoch": 0.71, + "learning_rate": 4.692635774453914e-06, + "loss": 1.238, + "step": 6773 + }, + { + "epoch": 0.71, + "learning_rate": 4.6895339329183154e-06, + "loss": 1.3876, + "step": 6774 + }, + { + "epoch": 0.71, + "learning_rate": 4.686432802848726e-06, + "loss": 1.3012, + "step": 6775 + }, + { + "epoch": 0.71, + "learning_rate": 4.68333238466061e-06, + "loss": 1.1421, + "step": 6776 + }, + { + "epoch": 0.71, + "learning_rate": 4.6802326787693455e-06, + "loss": 1.2838, + "step": 6777 + }, + { + "epoch": 0.71, + "learning_rate": 4.677133685590219e-06, + "loss": 1.3725, + "step": 6778 + }, + { + "epoch": 0.71, + "learning_rate": 4.674035405538409e-06, + "loss": 1.3093, + "step": 6779 + }, + { + "epoch": 0.71, + "learning_rate": 4.6709378390290085e-06, + "loss": 1.2785, + "step": 6780 + }, + { + "epoch": 0.71, + "learning_rate": 4.667840986477015e-06, + "loss": 1.2513, + "step": 6781 + }, + { + "epoch": 0.71, + "learning_rate": 4.66474484829732e-06, + "loss": 1.2903, + "step": 6782 + }, + { + "epoch": 0.71, + "learning_rate": 4.661649424904732e-06, + "loss": 1.4217, + "step": 6783 + }, + { + "epoch": 0.71, + "learning_rate": 4.658554716713959e-06, + "loss": 1.337, + "step": 6784 + }, + { + "epoch": 0.71, + "learning_rate": 4.655460724139605e-06, + "loss": 1.2978, + "step": 6785 + }, + { + "epoch": 0.71, + "learning_rate": 4.652367447596197e-06, + "loss": 1.3036, + "step": 6786 + }, + { + "epoch": 0.71, + "learning_rate": 4.6492748874981415e-06, + "loss": 1.2889, + "step": 6787 + }, + { + "epoch": 0.71, + "learning_rate": 4.646183044259771e-06, + "loss": 1.3046, + "step": 6788 + }, + { + "epoch": 0.71, + "learning_rate": 4.643091918295312e-06, + "loss": 1.3483, + "step": 6789 + }, + { + "epoch": 0.71, + "learning_rate": 4.640001510018893e-06, + "loss": 1.3862, + "step": 6790 + }, + { + "epoch": 0.71, + "learning_rate": 4.6369118198445505e-06, + "loss": 1.2483, + "step": 6791 + }, + { + "epoch": 0.71, + "learning_rate": 4.633822848186228e-06, + "loss": 1.2669, + "step": 6792 + }, + { + "epoch": 0.71, + "learning_rate": 4.63073459545776e-06, + "loss": 1.3535, + "step": 6793 + }, + { + "epoch": 0.71, + "learning_rate": 4.627647062072902e-06, + "loss": 1.2742, + "step": 6794 + }, + { + "epoch": 0.71, + "learning_rate": 4.624560248445295e-06, + "loss": 1.3429, + "step": 6795 + }, + { + "epoch": 0.71, + "learning_rate": 4.621474154988498e-06, + "loss": 1.3548, + "step": 6796 + }, + { + "epoch": 0.71, + "learning_rate": 4.61838878211597e-06, + "loss": 1.2722, + "step": 6797 + }, + { + "epoch": 0.71, + "learning_rate": 4.6153041302410665e-06, + "loss": 1.3357, + "step": 6798 + }, + { + "epoch": 0.71, + "learning_rate": 4.612220199777053e-06, + "loss": 1.2494, + "step": 6799 + }, + { + "epoch": 0.71, + "learning_rate": 4.609136991137103e-06, + "loss": 1.2792, + "step": 6800 + }, + { + "epoch": 0.71, + "learning_rate": 4.60605450473428e-06, + "loss": 1.2892, + "step": 6801 + }, + { + "epoch": 0.71, + "learning_rate": 4.602972740981562e-06, + "loss": 1.316, + "step": 6802 + }, + { + "epoch": 0.71, + "learning_rate": 4.599891700291822e-06, + "loss": 1.3017, + "step": 6803 + }, + { + "epoch": 0.71, + "learning_rate": 4.5968113830778416e-06, + "loss": 1.3133, + "step": 6804 + }, + { + "epoch": 0.71, + "learning_rate": 4.593731789752311e-06, + "loss": 1.3768, + "step": 6805 + }, + { + "epoch": 0.71, + "learning_rate": 4.590652920727806e-06, + "loss": 1.3259, + "step": 6806 + }, + { + "epoch": 0.71, + "learning_rate": 4.5875747764168214e-06, + "loss": 1.328, + "step": 6807 + }, + { + "epoch": 0.71, + "learning_rate": 4.584497357231752e-06, + "loss": 1.2924, + "step": 6808 + }, + { + "epoch": 0.71, + "learning_rate": 4.581420663584886e-06, + "loss": 1.3347, + "step": 6809 + }, + { + "epoch": 0.71, + "learning_rate": 4.578344695888427e-06, + "loss": 1.3042, + "step": 6810 + }, + { + "epoch": 0.71, + "learning_rate": 4.575269454554477e-06, + "loss": 1.3121, + "step": 6811 + }, + { + "epoch": 0.71, + "learning_rate": 4.572194939995031e-06, + "loss": 1.3471, + "step": 6812 + }, + { + "epoch": 0.71, + "learning_rate": 4.569121152622005e-06, + "loss": 1.4279, + "step": 6813 + }, + { + "epoch": 0.71, + "learning_rate": 4.5660480928471985e-06, + "loss": 1.2902, + "step": 6814 + }, + { + "epoch": 0.71, + "learning_rate": 4.562975761082326e-06, + "loss": 1.0803, + "step": 6815 + }, + { + "epoch": 0.71, + "learning_rate": 4.5599041577390065e-06, + "loss": 1.008, + "step": 6816 + }, + { + "epoch": 0.71, + "learning_rate": 4.556833283228748e-06, + "loss": 1.168, + "step": 6817 + }, + { + "epoch": 0.71, + "learning_rate": 4.553763137962971e-06, + "loss": 1.3092, + "step": 6818 + }, + { + "epoch": 0.72, + "learning_rate": 4.550693722353001e-06, + "loss": 1.364, + "step": 6819 + }, + { + "epoch": 0.72, + "learning_rate": 4.547625036810052e-06, + "loss": 1.3079, + "step": 6820 + }, + { + "epoch": 0.72, + "learning_rate": 4.544557081745259e-06, + "loss": 1.2639, + "step": 6821 + }, + { + "epoch": 0.72, + "learning_rate": 4.541489857569639e-06, + "loss": 1.3586, + "step": 6822 + }, + { + "epoch": 0.72, + "learning_rate": 4.5384233646941275e-06, + "loss": 1.4261, + "step": 6823 + }, + { + "epoch": 0.72, + "learning_rate": 4.535357603529558e-06, + "loss": 1.428, + "step": 6824 + }, + { + "epoch": 0.72, + "learning_rate": 4.532292574486656e-06, + "loss": 1.2541, + "step": 6825 + }, + { + "epoch": 0.72, + "learning_rate": 4.529228277976061e-06, + "loss": 1.2761, + "step": 6826 + }, + { + "epoch": 0.72, + "learning_rate": 4.526164714408314e-06, + "loss": 1.3439, + "step": 6827 + }, + { + "epoch": 0.72, + "learning_rate": 4.523101884193845e-06, + "loss": 1.3585, + "step": 6828 + }, + { + "epoch": 0.72, + "learning_rate": 4.520039787742999e-06, + "loss": 1.4035, + "step": 6829 + }, + { + "epoch": 0.72, + "learning_rate": 4.516978425466023e-06, + "loss": 1.3328, + "step": 6830 + }, + { + "epoch": 0.72, + "learning_rate": 4.5139177977730516e-06, + "loss": 1.2931, + "step": 6831 + }, + { + "epoch": 0.72, + "learning_rate": 4.5108579050741395e-06, + "loss": 1.2515, + "step": 6832 + }, + { + "epoch": 0.72, + "learning_rate": 4.507798747779226e-06, + "loss": 1.3178, + "step": 6833 + }, + { + "epoch": 0.72, + "learning_rate": 4.504740326298163e-06, + "loss": 1.3037, + "step": 6834 + }, + { + "epoch": 0.72, + "learning_rate": 4.501682641040702e-06, + "loss": 1.14, + "step": 6835 + }, + { + "epoch": 0.72, + "learning_rate": 4.4986256924164895e-06, + "loss": 1.2801, + "step": 6836 + }, + { + "epoch": 0.72, + "learning_rate": 4.495569480835081e-06, + "loss": 1.3195, + "step": 6837 + }, + { + "epoch": 0.72, + "learning_rate": 4.492514006705935e-06, + "loss": 1.2949, + "step": 6838 + }, + { + "epoch": 0.72, + "learning_rate": 4.489459270438397e-06, + "loss": 1.3297, + "step": 6839 + }, + { + "epoch": 0.72, + "learning_rate": 4.4864052724417315e-06, + "loss": 1.2127, + "step": 6840 + }, + { + "epoch": 0.72, + "learning_rate": 4.4833520131250894e-06, + "loss": 1.3124, + "step": 6841 + }, + { + "epoch": 0.72, + "learning_rate": 4.480299492897532e-06, + "loss": 1.3056, + "step": 6842 + }, + { + "epoch": 0.72, + "learning_rate": 4.477247712168021e-06, + "loss": 1.2853, + "step": 6843 + }, + { + "epoch": 0.72, + "learning_rate": 4.474196671345411e-06, + "loss": 1.2531, + "step": 6844 + }, + { + "epoch": 0.72, + "learning_rate": 4.471146370838466e-06, + "loss": 1.2712, + "step": 6845 + }, + { + "epoch": 0.72, + "learning_rate": 4.468096811055852e-06, + "loss": 1.3443, + "step": 6846 + }, + { + "epoch": 0.72, + "learning_rate": 4.465047992406124e-06, + "loss": 1.2692, + "step": 6847 + }, + { + "epoch": 0.72, + "learning_rate": 4.461999915297752e-06, + "loss": 1.3937, + "step": 6848 + }, + { + "epoch": 0.72, + "learning_rate": 4.458952580139094e-06, + "loss": 1.2743, + "step": 6849 + }, + { + "epoch": 0.72, + "learning_rate": 4.455905987338418e-06, + "loss": 1.3949, + "step": 6850 + }, + { + "epoch": 0.72, + "learning_rate": 4.452860137303892e-06, + "loss": 1.2578, + "step": 6851 + }, + { + "epoch": 0.72, + "learning_rate": 4.449815030443575e-06, + "loss": 1.3199, + "step": 6852 + }, + { + "epoch": 0.72, + "learning_rate": 4.4467706671654365e-06, + "loss": 1.3199, + "step": 6853 + }, + { + "epoch": 0.72, + "learning_rate": 4.4437270478773464e-06, + "loss": 1.3098, + "step": 6854 + }, + { + "epoch": 0.72, + "learning_rate": 4.440684172987064e-06, + "loss": 1.2888, + "step": 6855 + }, + { + "epoch": 0.72, + "learning_rate": 4.4376420429022615e-06, + "loss": 1.646, + "step": 6856 + }, + { + "epoch": 0.72, + "learning_rate": 4.434600658030508e-06, + "loss": 1.3573, + "step": 6857 + }, + { + "epoch": 0.72, + "learning_rate": 4.431560018779264e-06, + "loss": 1.3748, + "step": 6858 + }, + { + "epoch": 0.72, + "learning_rate": 4.428520125555906e-06, + "loss": 1.358, + "step": 6859 + }, + { + "epoch": 0.72, + "learning_rate": 4.425480978767692e-06, + "loss": 1.2707, + "step": 6860 + }, + { + "epoch": 0.72, + "learning_rate": 4.422442578821795e-06, + "loss": 1.4066, + "step": 6861 + }, + { + "epoch": 0.72, + "learning_rate": 4.4194049261252845e-06, + "loss": 1.3725, + "step": 6862 + }, + { + "epoch": 0.72, + "learning_rate": 4.416368021085122e-06, + "loss": 1.2392, + "step": 6863 + }, + { + "epoch": 0.72, + "learning_rate": 4.413331864108178e-06, + "loss": 1.2917, + "step": 6864 + }, + { + "epoch": 0.72, + "learning_rate": 4.410296455601223e-06, + "loss": 1.2685, + "step": 6865 + }, + { + "epoch": 0.72, + "learning_rate": 4.407261795970916e-06, + "loss": 1.265, + "step": 6866 + }, + { + "epoch": 0.72, + "learning_rate": 4.404227885623832e-06, + "loss": 1.3838, + "step": 6867 + }, + { + "epoch": 0.72, + "learning_rate": 4.4011947249664276e-06, + "loss": 1.3496, + "step": 6868 + }, + { + "epoch": 0.72, + "learning_rate": 4.398162314405075e-06, + "loss": 1.3007, + "step": 6869 + }, + { + "epoch": 0.72, + "learning_rate": 4.39513065434604e-06, + "loss": 1.2934, + "step": 6870 + }, + { + "epoch": 0.72, + "learning_rate": 4.392099745195483e-06, + "loss": 1.559, + "step": 6871 + }, + { + "epoch": 0.72, + "learning_rate": 4.389069587359468e-06, + "loss": 1.346, + "step": 6872 + }, + { + "epoch": 0.72, + "learning_rate": 4.386040181243965e-06, + "loss": 1.2433, + "step": 6873 + }, + { + "epoch": 0.72, + "learning_rate": 4.3830115272548275e-06, + "loss": 1.2938, + "step": 6874 + }, + { + "epoch": 0.72, + "learning_rate": 4.379983625797821e-06, + "loss": 1.3463, + "step": 6875 + }, + { + "epoch": 0.72, + "learning_rate": 4.376956477278612e-06, + "loss": 1.2832, + "step": 6876 + }, + { + "epoch": 0.72, + "learning_rate": 4.37393008210275e-06, + "loss": 1.3693, + "step": 6877 + }, + { + "epoch": 0.72, + "learning_rate": 4.370904440675705e-06, + "loss": 1.2652, + "step": 6878 + }, + { + "epoch": 0.72, + "learning_rate": 4.367879553402826e-06, + "loss": 1.3217, + "step": 6879 + }, + { + "epoch": 0.72, + "learning_rate": 4.364855420689375e-06, + "loss": 1.3519, + "step": 6880 + }, + { + "epoch": 0.72, + "learning_rate": 4.36183204294051e-06, + "loss": 1.3131, + "step": 6881 + }, + { + "epoch": 0.72, + "learning_rate": 4.35880942056128e-06, + "loss": 1.4334, + "step": 6882 + }, + { + "epoch": 0.72, + "learning_rate": 4.3557875539566415e-06, + "loss": 1.259, + "step": 6883 + }, + { + "epoch": 0.72, + "learning_rate": 4.352766443531451e-06, + "loss": 1.2841, + "step": 6884 + }, + { + "epoch": 0.72, + "learning_rate": 4.349746089690453e-06, + "loss": 1.35, + "step": 6885 + }, + { + "epoch": 0.72, + "learning_rate": 4.346726492838304e-06, + "loss": 1.3623, + "step": 6886 + }, + { + "epoch": 0.72, + "learning_rate": 4.343707653379544e-06, + "loss": 1.3729, + "step": 6887 + }, + { + "epoch": 0.72, + "learning_rate": 4.340689571718626e-06, + "loss": 1.2992, + "step": 6888 + }, + { + "epoch": 0.72, + "learning_rate": 4.337672248259898e-06, + "loss": 1.3484, + "step": 6889 + }, + { + "epoch": 0.72, + "learning_rate": 4.334655683407594e-06, + "loss": 1.3347, + "step": 6890 + }, + { + "epoch": 0.72, + "learning_rate": 4.331639877565865e-06, + "loss": 1.2986, + "step": 6891 + }, + { + "epoch": 0.72, + "learning_rate": 4.328624831138751e-06, + "loss": 1.3217, + "step": 6892 + }, + { + "epoch": 0.72, + "learning_rate": 4.325610544530184e-06, + "loss": 1.2834, + "step": 6893 + }, + { + "epoch": 0.72, + "learning_rate": 4.32259701814401e-06, + "loss": 1.3474, + "step": 6894 + }, + { + "epoch": 0.72, + "learning_rate": 4.319584252383956e-06, + "loss": 1.2871, + "step": 6895 + }, + { + "epoch": 0.72, + "learning_rate": 4.316572247653659e-06, + "loss": 1.3534, + "step": 6896 + }, + { + "epoch": 0.72, + "learning_rate": 4.313561004356653e-06, + "loss": 1.4421, + "step": 6897 + }, + { + "epoch": 0.72, + "learning_rate": 4.310550522896359e-06, + "loss": 1.3091, + "step": 6898 + }, + { + "epoch": 0.72, + "learning_rate": 4.30754080367611e-06, + "loss": 1.2565, + "step": 6899 + }, + { + "epoch": 0.72, + "learning_rate": 4.304531847099135e-06, + "loss": 1.5767, + "step": 6900 + }, + { + "epoch": 0.72, + "learning_rate": 4.3015236535685475e-06, + "loss": 1.4257, + "step": 6901 + }, + { + "epoch": 0.72, + "learning_rate": 4.298516223487373e-06, + "loss": 1.362, + "step": 6902 + }, + { + "epoch": 0.72, + "learning_rate": 4.2955095572585336e-06, + "loss": 1.3475, + "step": 6903 + }, + { + "epoch": 0.72, + "learning_rate": 4.292503655284838e-06, + "loss": 1.3223, + "step": 6904 + }, + { + "epoch": 0.72, + "learning_rate": 4.289498517969006e-06, + "loss": 1.3142, + "step": 6905 + }, + { + "epoch": 0.72, + "learning_rate": 4.286494145713644e-06, + "loss": 1.3124, + "step": 6906 + }, + { + "epoch": 0.72, + "learning_rate": 4.283490538921261e-06, + "loss": 1.3636, + "step": 6907 + }, + { + "epoch": 0.72, + "learning_rate": 4.280487697994269e-06, + "loss": 1.347, + "step": 6908 + }, + { + "epoch": 0.72, + "learning_rate": 4.277485623334964e-06, + "loss": 1.2986, + "step": 6909 + }, + { + "epoch": 0.72, + "learning_rate": 4.27448431534555e-06, + "loss": 1.3058, + "step": 6910 + }, + { + "epoch": 0.72, + "learning_rate": 4.271483774428128e-06, + "loss": 1.7858, + "step": 6911 + }, + { + "epoch": 0.72, + "learning_rate": 4.268484000984689e-06, + "loss": 1.3529, + "step": 6912 + }, + { + "epoch": 0.72, + "learning_rate": 4.26548499541713e-06, + "loss": 1.3215, + "step": 6913 + }, + { + "epoch": 0.73, + "learning_rate": 4.262486758127234e-06, + "loss": 1.2914, + "step": 6914 + }, + { + "epoch": 0.73, + "learning_rate": 4.259489289516693e-06, + "loss": 1.4562, + "step": 6915 + }, + { + "epoch": 0.73, + "learning_rate": 4.256492589987092e-06, + "loss": 1.2548, + "step": 6916 + }, + { + "epoch": 0.73, + "learning_rate": 4.253496659939907e-06, + "loss": 1.3047, + "step": 6917 + }, + { + "epoch": 0.73, + "learning_rate": 4.250501499776516e-06, + "loss": 1.4184, + "step": 6918 + }, + { + "epoch": 0.73, + "learning_rate": 4.2475071098982e-06, + "loss": 1.3519, + "step": 6919 + }, + { + "epoch": 0.73, + "learning_rate": 4.2445134907061224e-06, + "loss": 1.3274, + "step": 6920 + }, + { + "epoch": 0.73, + "learning_rate": 4.2415206426013545e-06, + "loss": 1.389, + "step": 6921 + }, + { + "epoch": 0.73, + "learning_rate": 4.238528565984865e-06, + "loss": 1.2929, + "step": 6922 + }, + { + "epoch": 0.73, + "learning_rate": 4.235537261257507e-06, + "loss": 1.3883, + "step": 6923 + }, + { + "epoch": 0.73, + "learning_rate": 4.232546728820047e-06, + "loss": 1.3395, + "step": 6924 + }, + { + "epoch": 0.73, + "learning_rate": 4.229556969073133e-06, + "loss": 1.3534, + "step": 6925 + }, + { + "epoch": 0.73, + "learning_rate": 4.226567982417317e-06, + "loss": 1.4218, + "step": 6926 + }, + { + "epoch": 0.73, + "learning_rate": 4.223579769253052e-06, + "loss": 1.3737, + "step": 6927 + }, + { + "epoch": 0.73, + "learning_rate": 4.220592329980674e-06, + "loss": 1.4805, + "step": 6928 + }, + { + "epoch": 0.73, + "learning_rate": 4.217605665000426e-06, + "loss": 1.2409, + "step": 6929 + }, + { + "epoch": 0.73, + "learning_rate": 4.21461977471245e-06, + "loss": 1.3375, + "step": 6930 + }, + { + "epoch": 0.73, + "learning_rate": 4.211634659516769e-06, + "loss": 1.3535, + "step": 6931 + }, + { + "epoch": 0.73, + "learning_rate": 4.20865031981332e-06, + "loss": 1.2723, + "step": 6932 + }, + { + "epoch": 0.73, + "learning_rate": 4.2056667560019206e-06, + "loss": 1.342, + "step": 6933 + }, + { + "epoch": 0.73, + "learning_rate": 4.202683968482296e-06, + "loss": 1.4075, + "step": 6934 + }, + { + "epoch": 0.73, + "learning_rate": 4.199701957654065e-06, + "loss": 1.3003, + "step": 6935 + }, + { + "epoch": 0.73, + "learning_rate": 4.196720723916735e-06, + "loss": 1.3098, + "step": 6936 + }, + { + "epoch": 0.73, + "learning_rate": 4.193740267669718e-06, + "loss": 1.2386, + "step": 6937 + }, + { + "epoch": 0.73, + "learning_rate": 4.19076058931232e-06, + "loss": 1.3271, + "step": 6938 + }, + { + "epoch": 0.73, + "learning_rate": 4.187781689243737e-06, + "loss": 1.4604, + "step": 6939 + }, + { + "epoch": 0.73, + "learning_rate": 4.184803567863072e-06, + "loss": 1.3496, + "step": 6940 + }, + { + "epoch": 0.73, + "learning_rate": 4.181826225569308e-06, + "loss": 1.3056, + "step": 6941 + }, + { + "epoch": 0.73, + "learning_rate": 4.1788496627613366e-06, + "loss": 1.2886, + "step": 6942 + }, + { + "epoch": 0.73, + "learning_rate": 4.175873879837944e-06, + "loss": 1.282, + "step": 6943 + }, + { + "epoch": 0.73, + "learning_rate": 4.172898877197802e-06, + "loss": 1.2984, + "step": 6944 + }, + { + "epoch": 0.73, + "learning_rate": 4.169924655239488e-06, + "loss": 1.2909, + "step": 6945 + }, + { + "epoch": 0.73, + "learning_rate": 4.166951214361474e-06, + "loss": 1.4015, + "step": 6946 + }, + { + "epoch": 0.73, + "learning_rate": 4.16397855496212e-06, + "loss": 1.3772, + "step": 6947 + }, + { + "epoch": 0.73, + "learning_rate": 4.161006677439687e-06, + "loss": 1.3089, + "step": 6948 + }, + { + "epoch": 0.73, + "learning_rate": 4.1580355821923344e-06, + "loss": 1.3599, + "step": 6949 + }, + { + "epoch": 0.73, + "learning_rate": 4.155065269618107e-06, + "loss": 1.2886, + "step": 6950 + }, + { + "epoch": 0.73, + "learning_rate": 4.152095740114955e-06, + "loss": 1.3071, + "step": 6951 + }, + { + "epoch": 0.73, + "learning_rate": 4.149126994080715e-06, + "loss": 1.3332, + "step": 6952 + }, + { + "epoch": 0.73, + "learning_rate": 4.146159031913123e-06, + "loss": 1.3835, + "step": 6953 + }, + { + "epoch": 0.73, + "learning_rate": 4.1431918540098144e-06, + "loss": 1.3399, + "step": 6954 + }, + { + "epoch": 0.73, + "learning_rate": 4.140225460768309e-06, + "loss": 1.2906, + "step": 6955 + }, + { + "epoch": 0.73, + "learning_rate": 4.137259852586029e-06, + "loss": 1.295, + "step": 6956 + }, + { + "epoch": 0.73, + "learning_rate": 4.134295029860295e-06, + "loss": 1.3371, + "step": 6957 + }, + { + "epoch": 0.73, + "learning_rate": 4.131330992988308e-06, + "loss": 1.4441, + "step": 6958 + }, + { + "epoch": 0.73, + "learning_rate": 4.1283677423671805e-06, + "loss": 1.3257, + "step": 6959 + }, + { + "epoch": 0.73, + "learning_rate": 4.125405278393907e-06, + "loss": 1.3958, + "step": 6960 + }, + { + "epoch": 0.73, + "learning_rate": 4.1224436014653826e-06, + "loss": 1.2856, + "step": 6961 + }, + { + "epoch": 0.73, + "learning_rate": 4.1194827119784e-06, + "loss": 1.2943, + "step": 6962 + }, + { + "epoch": 0.73, + "learning_rate": 4.116522610329636e-06, + "loss": 1.2691, + "step": 6963 + }, + { + "epoch": 0.73, + "learning_rate": 4.11356329691567e-06, + "loss": 1.293, + "step": 6964 + }, + { + "epoch": 0.73, + "learning_rate": 4.11060477213298e-06, + "loss": 1.3136, + "step": 6965 + }, + { + "epoch": 0.73, + "eval_loss": 1.399178147315979, + "eval_runtime": 77.5864, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 6965 + }, + { + "epoch": 0.73, + "learning_rate": 4.1076470363779235e-06, + "loss": 1.2833, + "step": 6966 + }, + { + "epoch": 0.73, + "learning_rate": 4.104690090046765e-06, + "loss": 1.3177, + "step": 6967 + }, + { + "epoch": 0.73, + "learning_rate": 4.101733933535663e-06, + "loss": 1.2623, + "step": 6968 + }, + { + "epoch": 0.73, + "learning_rate": 4.0987785672406585e-06, + "loss": 1.2814, + "step": 6969 + }, + { + "epoch": 0.73, + "learning_rate": 4.0958239915577036e-06, + "loss": 1.3823, + "step": 6970 + }, + { + "epoch": 0.73, + "learning_rate": 4.092870206882627e-06, + "loss": 1.2926, + "step": 6971 + }, + { + "epoch": 0.73, + "learning_rate": 4.089917213611164e-06, + "loss": 1.3324, + "step": 6972 + }, + { + "epoch": 0.73, + "learning_rate": 4.086965012138943e-06, + "loss": 1.3521, + "step": 6973 + }, + { + "epoch": 0.73, + "learning_rate": 4.084013602861476e-06, + "loss": 1.4828, + "step": 6974 + }, + { + "epoch": 0.73, + "learning_rate": 4.0810629861741804e-06, + "loss": 1.3187, + "step": 6975 + }, + { + "epoch": 0.73, + "learning_rate": 4.078113162472366e-06, + "loss": 1.3478, + "step": 6976 + }, + { + "epoch": 0.73, + "learning_rate": 4.075164132151227e-06, + "loss": 1.4256, + "step": 6977 + }, + { + "epoch": 0.73, + "learning_rate": 4.0722158956058635e-06, + "loss": 1.2815, + "step": 6978 + }, + { + "epoch": 0.73, + "learning_rate": 4.069268453231257e-06, + "loss": 1.3031, + "step": 6979 + }, + { + "epoch": 0.73, + "learning_rate": 4.066321805422292e-06, + "loss": 1.2983, + "step": 6980 + }, + { + "epoch": 0.73, + "learning_rate": 4.063375952573748e-06, + "loss": 1.3595, + "step": 6981 + }, + { + "epoch": 0.73, + "learning_rate": 4.060430895080286e-06, + "loss": 1.3119, + "step": 6982 + }, + { + "epoch": 0.73, + "learning_rate": 4.057486633336472e-06, + "loss": 1.328, + "step": 6983 + }, + { + "epoch": 0.73, + "learning_rate": 4.054543167736766e-06, + "loss": 1.232, + "step": 6984 + }, + { + "epoch": 0.73, + "learning_rate": 4.0516004986755064e-06, + "loss": 1.3288, + "step": 6985 + }, + { + "epoch": 0.73, + "learning_rate": 4.048658626546945e-06, + "loss": 1.2916, + "step": 6986 + }, + { + "epoch": 0.73, + "learning_rate": 4.045717551745209e-06, + "loss": 1.2411, + "step": 6987 + }, + { + "epoch": 0.73, + "learning_rate": 4.042777274664331e-06, + "loss": 1.3256, + "step": 6988 + }, + { + "epoch": 0.73, + "learning_rate": 4.039837795698237e-06, + "loss": 1.3455, + "step": 6989 + }, + { + "epoch": 0.73, + "learning_rate": 4.036899115240732e-06, + "loss": 1.3303, + "step": 6990 + }, + { + "epoch": 0.73, + "learning_rate": 4.033961233685529e-06, + "loss": 1.2805, + "step": 6991 + }, + { + "epoch": 0.73, + "learning_rate": 4.031024151426233e-06, + "loss": 1.3958, + "step": 6992 + }, + { + "epoch": 0.73, + "learning_rate": 4.0280878688563275e-06, + "loss": 1.2853, + "step": 6993 + }, + { + "epoch": 0.73, + "learning_rate": 4.0251523863692054e-06, + "loss": 1.2433, + "step": 6994 + }, + { + "epoch": 0.73, + "learning_rate": 4.022217704358148e-06, + "loss": 1.2644, + "step": 6995 + }, + { + "epoch": 0.73, + "learning_rate": 4.0192838232163204e-06, + "loss": 1.3218, + "step": 6996 + }, + { + "epoch": 0.73, + "learning_rate": 4.016350743336795e-06, + "loss": 1.2973, + "step": 6997 + }, + { + "epoch": 0.73, + "learning_rate": 4.013418465112521e-06, + "loss": 1.3209, + "step": 6998 + }, + { + "epoch": 0.73, + "learning_rate": 4.010486988936353e-06, + "loss": 1.2855, + "step": 6999 + }, + { + "epoch": 0.73, + "learning_rate": 4.007556315201035e-06, + "loss": 1.2381, + "step": 7000 + }, + { + "epoch": 0.73, + "learning_rate": 4.004626444299198e-06, + "loss": 1.3558, + "step": 7001 + }, + { + "epoch": 0.73, + "learning_rate": 4.001697376623371e-06, + "loss": 1.3139, + "step": 7002 + }, + { + "epoch": 0.73, + "learning_rate": 3.998769112565978e-06, + "loss": 1.3582, + "step": 7003 + }, + { + "epoch": 0.73, + "learning_rate": 3.9958416525193225e-06, + "loss": 1.2684, + "step": 7004 + }, + { + "epoch": 0.73, + "learning_rate": 3.992914996875618e-06, + "loss": 1.2915, + "step": 7005 + }, + { + "epoch": 0.73, + "learning_rate": 3.9899891460269536e-06, + "loss": 1.3205, + "step": 7006 + }, + { + "epoch": 0.73, + "learning_rate": 3.987064100365321e-06, + "loss": 1.2966, + "step": 7007 + }, + { + "epoch": 0.73, + "learning_rate": 3.984139860282606e-06, + "loss": 1.2691, + "step": 7008 + }, + { + "epoch": 0.74, + "learning_rate": 3.981216426170572e-06, + "loss": 1.3421, + "step": 7009 + }, + { + "epoch": 0.74, + "learning_rate": 3.97829379842089e-06, + "loss": 1.3034, + "step": 7010 + }, + { + "epoch": 0.74, + "learning_rate": 3.9753719774251195e-06, + "loss": 1.2863, + "step": 7011 + }, + { + "epoch": 0.74, + "learning_rate": 3.972450963574703e-06, + "loss": 1.3812, + "step": 7012 + }, + { + "epoch": 0.74, + "learning_rate": 3.969530757260986e-06, + "loss": 1.334, + "step": 7013 + }, + { + "epoch": 0.74, + "learning_rate": 3.966611358875201e-06, + "loss": 1.3289, + "step": 7014 + }, + { + "epoch": 0.74, + "learning_rate": 3.963692768808468e-06, + "loss": 1.395, + "step": 7015 + }, + { + "epoch": 0.74, + "learning_rate": 3.960774987451811e-06, + "loss": 1.3298, + "step": 7016 + }, + { + "epoch": 0.74, + "learning_rate": 3.957858015196128e-06, + "loss": 1.3304, + "step": 7017 + }, + { + "epoch": 0.74, + "learning_rate": 3.954941852432224e-06, + "loss": 1.301, + "step": 7018 + }, + { + "epoch": 0.74, + "learning_rate": 3.952026499550791e-06, + "loss": 1.3568, + "step": 7019 + }, + { + "epoch": 0.74, + "learning_rate": 3.949111956942406e-06, + "loss": 1.4464, + "step": 7020 + }, + { + "epoch": 0.74, + "learning_rate": 3.946198224997548e-06, + "loss": 1.4417, + "step": 7021 + }, + { + "epoch": 0.74, + "learning_rate": 3.943285304106583e-06, + "loss": 1.3979, + "step": 7022 + }, + { + "epoch": 0.74, + "learning_rate": 3.940373194659761e-06, + "loss": 1.2943, + "step": 7023 + }, + { + "epoch": 0.74, + "learning_rate": 3.937461897047239e-06, + "loss": 1.2571, + "step": 7024 + }, + { + "epoch": 0.74, + "learning_rate": 3.9345514116590454e-06, + "loss": 1.3433, + "step": 7025 + }, + { + "epoch": 0.74, + "learning_rate": 3.931641738885117e-06, + "loss": 1.4203, + "step": 7026 + }, + { + "epoch": 0.74, + "learning_rate": 3.9287328791152775e-06, + "loss": 1.3657, + "step": 7027 + }, + { + "epoch": 0.74, + "learning_rate": 3.925824832739234e-06, + "loss": 1.3954, + "step": 7028 + }, + { + "epoch": 0.74, + "learning_rate": 3.92291760014659e-06, + "loss": 1.2847, + "step": 7029 + }, + { + "epoch": 0.74, + "learning_rate": 3.920011181726846e-06, + "loss": 1.2776, + "step": 7030 + }, + { + "epoch": 0.74, + "learning_rate": 3.91710557786938e-06, + "loss": 1.3391, + "step": 7031 + }, + { + "epoch": 0.74, + "learning_rate": 3.914200788963472e-06, + "loss": 1.2935, + "step": 7032 + }, + { + "epoch": 0.74, + "learning_rate": 3.911296815398291e-06, + "loss": 1.3775, + "step": 7033 + }, + { + "epoch": 0.74, + "learning_rate": 3.90839365756289e-06, + "loss": 1.3652, + "step": 7034 + }, + { + "epoch": 0.74, + "learning_rate": 3.905491315846224e-06, + "loss": 1.2902, + "step": 7035 + }, + { + "epoch": 0.74, + "learning_rate": 3.902589790637125e-06, + "loss": 1.2859, + "step": 7036 + }, + { + "epoch": 0.74, + "learning_rate": 3.899689082324325e-06, + "loss": 1.4019, + "step": 7037 + }, + { + "epoch": 0.74, + "learning_rate": 3.89678919129645e-06, + "loss": 1.299, + "step": 7038 + }, + { + "epoch": 0.74, + "learning_rate": 3.893890117942003e-06, + "loss": 1.275, + "step": 7039 + }, + { + "epoch": 0.74, + "learning_rate": 3.890991862649388e-06, + "loss": 1.2593, + "step": 7040 + }, + { + "epoch": 0.74, + "learning_rate": 3.888094425806902e-06, + "loss": 1.2932, + "step": 7041 + }, + { + "epoch": 0.74, + "learning_rate": 3.885197807802719e-06, + "loss": 1.3038, + "step": 7042 + }, + { + "epoch": 0.74, + "learning_rate": 3.882302009024917e-06, + "loss": 1.285, + "step": 7043 + }, + { + "epoch": 0.74, + "learning_rate": 3.879407029861455e-06, + "loss": 1.4116, + "step": 7044 + }, + { + "epoch": 0.74, + "learning_rate": 3.876512870700187e-06, + "loss": 1.3823, + "step": 7045 + }, + { + "epoch": 0.74, + "learning_rate": 3.873619531928858e-06, + "loss": 1.2803, + "step": 7046 + }, + { + "epoch": 0.74, + "learning_rate": 3.870727013935099e-06, + "loss": 1.3287, + "step": 7047 + }, + { + "epoch": 0.74, + "learning_rate": 3.867835317106432e-06, + "loss": 1.3919, + "step": 7048 + }, + { + "epoch": 0.74, + "learning_rate": 3.864944441830275e-06, + "loss": 1.3967, + "step": 7049 + }, + { + "epoch": 0.74, + "learning_rate": 3.862054388493924e-06, + "loss": 1.2749, + "step": 7050 + }, + { + "epoch": 0.74, + "learning_rate": 3.85916515748458e-06, + "loss": 1.3408, + "step": 7051 + }, + { + "epoch": 0.74, + "learning_rate": 3.856276749189317e-06, + "loss": 1.3143, + "step": 7052 + }, + { + "epoch": 0.74, + "learning_rate": 3.853389163995111e-06, + "loss": 1.3661, + "step": 7053 + }, + { + "epoch": 0.74, + "learning_rate": 3.8505024022888305e-06, + "loss": 1.3094, + "step": 7054 + }, + { + "epoch": 0.74, + "learning_rate": 3.847616464457216e-06, + "loss": 1.2736, + "step": 7055 + }, + { + "epoch": 0.74, + "learning_rate": 3.844731350886917e-06, + "loss": 1.3628, + "step": 7056 + }, + { + "epoch": 0.74, + "learning_rate": 3.841847061964465e-06, + "loss": 1.2706, + "step": 7057 + }, + { + "epoch": 0.74, + "learning_rate": 3.838963598076275e-06, + "loss": 1.2566, + "step": 7058 + }, + { + "epoch": 0.74, + "learning_rate": 3.83608095960866e-06, + "loss": 1.2415, + "step": 7059 + }, + { + "epoch": 0.74, + "learning_rate": 3.833199146947823e-06, + "loss": 1.2748, + "step": 7060 + }, + { + "epoch": 0.74, + "learning_rate": 3.830318160479847e-06, + "loss": 1.4672, + "step": 7061 + }, + { + "epoch": 0.74, + "learning_rate": 3.827438000590714e-06, + "loss": 1.2907, + "step": 7062 + }, + { + "epoch": 0.74, + "learning_rate": 3.824558667666288e-06, + "loss": 1.3477, + "step": 7063 + }, + { + "epoch": 0.74, + "learning_rate": 3.821680162092328e-06, + "loss": 1.1135, + "step": 7064 + }, + { + "epoch": 0.74, + "learning_rate": 3.8188024842544825e-06, + "loss": 1.3724, + "step": 7065 + }, + { + "epoch": 0.74, + "learning_rate": 3.81592563453828e-06, + "loss": 1.3854, + "step": 7066 + }, + { + "epoch": 0.74, + "learning_rate": 3.8130496133291473e-06, + "loss": 1.3074, + "step": 7067 + }, + { + "epoch": 0.74, + "learning_rate": 3.8101744210124012e-06, + "loss": 1.4434, + "step": 7068 + }, + { + "epoch": 0.74, + "learning_rate": 3.807300057973238e-06, + "loss": 1.2754, + "step": 7069 + }, + { + "epoch": 0.74, + "learning_rate": 3.804426524596754e-06, + "loss": 1.3654, + "step": 7070 + }, + { + "epoch": 0.74, + "learning_rate": 3.8015538212679214e-06, + "loss": 1.2616, + "step": 7071 + }, + { + "epoch": 0.74, + "learning_rate": 3.798681948371613e-06, + "loss": 1.2939, + "step": 7072 + }, + { + "epoch": 0.74, + "learning_rate": 3.7958109062925894e-06, + "loss": 1.2787, + "step": 7073 + }, + { + "epoch": 0.74, + "learning_rate": 3.792940695415489e-06, + "loss": 1.2953, + "step": 7074 + }, + { + "epoch": 0.74, + "learning_rate": 3.7900713161248515e-06, + "loss": 1.2714, + "step": 7075 + }, + { + "epoch": 0.74, + "learning_rate": 3.7872027688051004e-06, + "loss": 1.3085, + "step": 7076 + }, + { + "epoch": 0.74, + "learning_rate": 3.7843350538405433e-06, + "loss": 1.311, + "step": 7077 + }, + { + "epoch": 0.74, + "learning_rate": 3.781468171615382e-06, + "loss": 1.3367, + "step": 7078 + }, + { + "epoch": 0.74, + "learning_rate": 3.7786021225137102e-06, + "loss": 1.2768, + "step": 7079 + }, + { + "epoch": 0.74, + "learning_rate": 3.775736906919496e-06, + "loss": 1.2828, + "step": 7080 + }, + { + "epoch": 0.74, + "learning_rate": 3.772872525216613e-06, + "loss": 1.3682, + "step": 7081 + }, + { + "epoch": 0.74, + "learning_rate": 3.7700089777888072e-06, + "loss": 1.3906, + "step": 7082 + }, + { + "epoch": 0.74, + "learning_rate": 3.767146265019723e-06, + "loss": 1.2712, + "step": 7083 + }, + { + "epoch": 0.74, + "learning_rate": 3.764284387292896e-06, + "loss": 1.3405, + "step": 7084 + }, + { + "epoch": 0.74, + "learning_rate": 3.761423344991736e-06, + "loss": 1.3941, + "step": 7085 + }, + { + "epoch": 0.74, + "learning_rate": 3.7585631384995523e-06, + "loss": 1.3463, + "step": 7086 + }, + { + "epoch": 0.74, + "learning_rate": 3.7557037681995423e-06, + "loss": 1.2771, + "step": 7087 + }, + { + "epoch": 0.74, + "learning_rate": 3.7528452344747834e-06, + "loss": 1.2706, + "step": 7088 + }, + { + "epoch": 0.74, + "learning_rate": 3.7499875377082497e-06, + "loss": 1.2672, + "step": 7089 + }, + { + "epoch": 0.74, + "learning_rate": 3.7471306782827944e-06, + "loss": 1.2638, + "step": 7090 + }, + { + "epoch": 0.74, + "learning_rate": 3.744274656581166e-06, + "loss": 1.3417, + "step": 7091 + }, + { + "epoch": 0.74, + "learning_rate": 3.7414194729860008e-06, + "loss": 1.278, + "step": 7092 + }, + { + "epoch": 0.74, + "learning_rate": 3.738565127879814e-06, + "loss": 1.2753, + "step": 7093 + }, + { + "epoch": 0.74, + "learning_rate": 3.7357116216450183e-06, + "loss": 1.2989, + "step": 7094 + }, + { + "epoch": 0.74, + "learning_rate": 3.7328589546639127e-06, + "loss": 1.263, + "step": 7095 + }, + { + "epoch": 0.74, + "learning_rate": 3.7300071273186745e-06, + "loss": 1.3534, + "step": 7096 + }, + { + "epoch": 0.74, + "learning_rate": 3.7271561399913825e-06, + "loss": 1.2565, + "step": 7097 + }, + { + "epoch": 0.74, + "learning_rate": 3.724305993063989e-06, + "loss": 1.3233, + "step": 7098 + }, + { + "epoch": 0.74, + "learning_rate": 3.7214566869183443e-06, + "loss": 1.3179, + "step": 7099 + }, + { + "epoch": 0.74, + "learning_rate": 3.718608221936184e-06, + "loss": 1.2749, + "step": 7100 + }, + { + "epoch": 0.74, + "learning_rate": 3.715760598499124e-06, + "loss": 1.3106, + "step": 7101 + }, + { + "epoch": 0.74, + "learning_rate": 3.712913816988675e-06, + "loss": 1.3115, + "step": 7102 + }, + { + "epoch": 0.74, + "learning_rate": 3.7100678777862364e-06, + "loss": 1.2798, + "step": 7103 + }, + { + "epoch": 0.74, + "learning_rate": 3.7072227812730853e-06, + "loss": 1.3964, + "step": 7104 + }, + { + "epoch": 0.75, + "learning_rate": 3.7043785278303923e-06, + "loss": 1.4034, + "step": 7105 + }, + { + "epoch": 0.75, + "learning_rate": 3.70153511783922e-06, + "loss": 1.3244, + "step": 7106 + }, + { + "epoch": 0.75, + "learning_rate": 3.698692551680505e-06, + "loss": 1.3283, + "step": 7107 + }, + { + "epoch": 0.75, + "learning_rate": 3.6958508297350847e-06, + "loss": 1.3567, + "step": 7108 + }, + { + "epoch": 0.75, + "learning_rate": 3.6930099523836692e-06, + "loss": 1.3178, + "step": 7109 + }, + { + "epoch": 0.75, + "learning_rate": 3.6901699200068673e-06, + "loss": 1.2697, + "step": 7110 + }, + { + "epoch": 0.75, + "learning_rate": 3.687330732985175e-06, + "loss": 1.2501, + "step": 7111 + }, + { + "epoch": 0.75, + "learning_rate": 3.6844923916989607e-06, + "loss": 1.2772, + "step": 7112 + }, + { + "epoch": 0.75, + "learning_rate": 3.681654896528495e-06, + "loss": 1.2845, + "step": 7113 + }, + { + "epoch": 0.75, + "learning_rate": 3.6788182478539312e-06, + "loss": 1.3151, + "step": 7114 + }, + { + "epoch": 0.75, + "learning_rate": 3.6759824460553016e-06, + "loss": 1.4925, + "step": 7115 + }, + { + "epoch": 0.75, + "learning_rate": 3.673147491512539e-06, + "loss": 1.2892, + "step": 7116 + }, + { + "epoch": 0.75, + "learning_rate": 3.670313384605444e-06, + "loss": 1.2906, + "step": 7117 + }, + { + "epoch": 0.75, + "learning_rate": 3.6674801257137195e-06, + "loss": 1.3927, + "step": 7118 + }, + { + "epoch": 0.75, + "learning_rate": 3.6646477152169522e-06, + "loss": 1.4001, + "step": 7119 + }, + { + "epoch": 0.75, + "learning_rate": 3.6618161534946074e-06, + "loss": 1.3363, + "step": 7120 + }, + { + "epoch": 0.75, + "learning_rate": 3.658985440926044e-06, + "loss": 1.3297, + "step": 7121 + }, + { + "epoch": 0.75, + "learning_rate": 3.656155577890507e-06, + "loss": 1.3029, + "step": 7122 + }, + { + "epoch": 0.75, + "learning_rate": 3.653326564767119e-06, + "loss": 1.3452, + "step": 7123 + }, + { + "epoch": 0.75, + "learning_rate": 3.6504984019348987e-06, + "loss": 1.3246, + "step": 7124 + }, + { + "epoch": 0.75, + "learning_rate": 3.647671089772752e-06, + "loss": 1.3285, + "step": 7125 + }, + { + "epoch": 0.75, + "learning_rate": 3.6448446286594574e-06, + "loss": 1.3127, + "step": 7126 + }, + { + "epoch": 0.75, + "learning_rate": 3.6420190189736946e-06, + "loss": 1.3224, + "step": 7127 + }, + { + "epoch": 0.75, + "learning_rate": 3.6391942610940178e-06, + "loss": 1.3086, + "step": 7128 + }, + { + "epoch": 0.75, + "learning_rate": 3.6363703553988748e-06, + "loss": 1.3741, + "step": 7129 + }, + { + "epoch": 0.75, + "learning_rate": 3.633547302266599e-06, + "loss": 1.3192, + "step": 7130 + }, + { + "epoch": 0.75, + "learning_rate": 3.6307251020754e-06, + "loss": 1.3032, + "step": 7131 + }, + { + "epoch": 0.75, + "learning_rate": 3.6279037552033847e-06, + "loss": 1.2642, + "step": 7132 + }, + { + "epoch": 0.75, + "learning_rate": 3.6250832620285436e-06, + "loss": 1.3948, + "step": 7133 + }, + { + "epoch": 0.75, + "learning_rate": 3.6222636229287445e-06, + "loss": 1.3542, + "step": 7134 + }, + { + "epoch": 0.75, + "learning_rate": 3.6194448382817526e-06, + "loss": 1.3028, + "step": 7135 + }, + { + "epoch": 0.75, + "learning_rate": 3.616626908465205e-06, + "loss": 1.3017, + "step": 7136 + }, + { + "epoch": 0.75, + "learning_rate": 3.613809833856636e-06, + "loss": 1.3072, + "step": 7137 + }, + { + "epoch": 0.75, + "learning_rate": 3.6109936148334666e-06, + "loss": 1.3065, + "step": 7138 + }, + { + "epoch": 0.75, + "learning_rate": 3.608178251772988e-06, + "loss": 1.4268, + "step": 7139 + }, + { + "epoch": 0.75, + "learning_rate": 3.6053637450523914e-06, + "loss": 1.301, + "step": 7140 + }, + { + "epoch": 0.75, + "learning_rate": 3.6025500950487514e-06, + "loss": 1.2873, + "step": 7141 + }, + { + "epoch": 0.75, + "learning_rate": 3.599737302139018e-06, + "loss": 1.2831, + "step": 7142 + }, + { + "epoch": 0.75, + "learning_rate": 3.5969253667000403e-06, + "loss": 1.5125, + "step": 7143 + }, + { + "epoch": 0.75, + "learning_rate": 3.594114289108538e-06, + "loss": 1.3643, + "step": 7144 + }, + { + "epoch": 0.75, + "learning_rate": 3.5913040697411272e-06, + "loss": 1.3157, + "step": 7145 + }, + { + "epoch": 0.75, + "learning_rate": 3.5884947089743084e-06, + "loss": 1.2687, + "step": 7146 + }, + { + "epoch": 0.75, + "learning_rate": 3.585686207184458e-06, + "loss": 1.3227, + "step": 7147 + }, + { + "epoch": 0.75, + "learning_rate": 3.5828785647478435e-06, + "loss": 1.2745, + "step": 7148 + }, + { + "epoch": 0.75, + "learning_rate": 3.5800717820406226e-06, + "loss": 1.332, + "step": 7149 + }, + { + "epoch": 0.75, + "learning_rate": 3.5772658594388253e-06, + "loss": 1.2863, + "step": 7150 + }, + { + "epoch": 0.75, + "learning_rate": 3.5744607973183766e-06, + "loss": 1.3791, + "step": 7151 + }, + { + "epoch": 0.75, + "learning_rate": 3.5716565960550844e-06, + "loss": 1.2781, + "step": 7152 + }, + { + "epoch": 0.75, + "learning_rate": 3.5688532560246348e-06, + "loss": 1.252, + "step": 7153 + }, + { + "epoch": 0.75, + "learning_rate": 3.5660507776026086e-06, + "loss": 1.3158, + "step": 7154 + }, + { + "epoch": 0.75, + "learning_rate": 3.5632491611644603e-06, + "loss": 1.3241, + "step": 7155 + }, + { + "epoch": 0.75, + "learning_rate": 3.5604484070855382e-06, + "loss": 1.2572, + "step": 7156 + }, + { + "epoch": 0.75, + "learning_rate": 3.5576485157410733e-06, + "loss": 1.3734, + "step": 7157 + }, + { + "epoch": 0.75, + "learning_rate": 3.5548494875061724e-06, + "loss": 1.3253, + "step": 7158 + }, + { + "epoch": 0.75, + "learning_rate": 3.5520513227558385e-06, + "loss": 1.2659, + "step": 7159 + }, + { + "epoch": 0.75, + "learning_rate": 3.5492540218649553e-06, + "loss": 1.3149, + "step": 7160 + }, + { + "epoch": 0.75, + "learning_rate": 3.546457585208283e-06, + "loss": 1.3413, + "step": 7161 + }, + { + "epoch": 0.75, + "learning_rate": 3.5436620131604803e-06, + "loss": 1.2846, + "step": 7162 + }, + { + "epoch": 0.75, + "learning_rate": 3.540867306096073e-06, + "loss": 1.3239, + "step": 7163 + }, + { + "epoch": 0.75, + "learning_rate": 3.5380734643894856e-06, + "loss": 1.3137, + "step": 7164 + }, + { + "epoch": 0.75, + "eval_loss": 1.397520899772644, + "eval_runtime": 77.542, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 7164 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 3.2049160631506856e+20, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-7164/training_args.bin b/checkpoint-7164/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-7164/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-7562/config.json b/checkpoint-7562/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-7562/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-7562/generation_config.json b/checkpoint-7562/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-7562/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-7562/model-00001-of-00003.safetensors b/checkpoint-7562/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a0b0c88d0c7977da02be572c5ce261c7414e9bfe --- /dev/null +++ b/checkpoint-7562/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c02e1994e10f6584d461d7270133a332ab7dfea10e26673b58b293329daddb2b +size 4943162336 diff --git a/checkpoint-7562/model-00002-of-00003.safetensors b/checkpoint-7562/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3e8eff920e5fe817671bb62e5d06f6f8d5a7198c --- /dev/null +++ b/checkpoint-7562/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ae433d2385655541e3b6605b265ce8dd5f0b29c5388a01ffcd8a6f1e2d44b83 +size 4999819336 diff --git a/checkpoint-7562/model-00003-of-00003.safetensors b/checkpoint-7562/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1deb33e4ed221118b496ece15453b0ca496f1075 --- /dev/null +++ b/checkpoint-7562/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfaa4ddd98132be6377ed647f498a00be0abf283963104842c77987df42f9675 +size 4540516344 diff --git a/checkpoint-7562/model.safetensors.index.json b/checkpoint-7562/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-7562/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-7562/optimizer.pt b/checkpoint-7562/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..1fb4951bba2a0b9af114fd22f919998080db5e18 --- /dev/null +++ b/checkpoint-7562/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7059955577e84933d20d905c786a3712d6b754c5e036b2a61bca491ff1f117c8 +size 14512103560 diff --git a/checkpoint-7562/rng_state_0.pth b/checkpoint-7562/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..46068b4fc6097787f30523e11417e4a113e27883 --- /dev/null +++ b/checkpoint-7562/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e335f544caa857d11abf9cb09880353f64949e255a62dc5453b96847c561f0ac +size 15984 diff --git a/checkpoint-7562/rng_state_1.pth b/checkpoint-7562/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..d7092c9972e785c5da458db9d5c880beb4a856a4 --- /dev/null +++ b/checkpoint-7562/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3386b1e39d8e02e3e871adae85560cf234b867a3c992efc33f75936ee1f2d78 +size 15984 diff --git a/checkpoint-7562/rng_state_2.pth b/checkpoint-7562/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..0d0a6dfe5bbf8e662bf730780e5625c728c22e57 --- /dev/null +++ b/checkpoint-7562/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9cdc3bc69c0cdbf403bd33fe473b728c8b289a359ceccbc0a9aa47bbd9d17b5 +size 15984 diff --git a/checkpoint-7562/rng_state_3.pth b/checkpoint-7562/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..07ac7a01796476c31aa6677bacad25014b7db7be --- /dev/null +++ b/checkpoint-7562/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8633ec6c78fdc9b764706dc4a108d9778e4be03084ed075204c83816bfb0b594 +size 15984 diff --git a/checkpoint-7562/rng_state_4.pth b/checkpoint-7562/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..af1d7f32e3fa47e3a752b3424eaf61f874cc24e8 --- /dev/null +++ b/checkpoint-7562/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e266d26e5111e7ee3fd6b754955dcc6e942824318775a3d91f136d08aff277d +size 15984 diff --git a/checkpoint-7562/rng_state_5.pth b/checkpoint-7562/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..ca7527b667b3034830e3778a78144bca02c84c22 --- /dev/null +++ b/checkpoint-7562/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:506ce4f9f78a95adeea3bdf6fd3c37022550c880c097f9a5097be36b0a685ef8 +size 15984 diff --git a/checkpoint-7562/rng_state_6.pth b/checkpoint-7562/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..dcb4c32ab693b0c78c5fda872ffd70bac0a8a060 --- /dev/null +++ b/checkpoint-7562/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:475cd26f1278f1ce58936112317402ff5ce4e15a7fad5d733299e542617bb52b +size 15984 diff --git a/checkpoint-7562/rng_state_7.pth b/checkpoint-7562/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..270ddd9c5010cfa53de5af14705d684b31aa6551 --- /dev/null +++ b/checkpoint-7562/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cf3ddb2fd167ef380ad3ca8a0fa303c8e0476c4aab0f31bb9a6945306d21e50 +size 15984 diff --git a/checkpoint-7562/scheduler.pt b/checkpoint-7562/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..7175f39cdd2fbf103f291ac17a4d94839656d443 --- /dev/null +++ b/checkpoint-7562/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3550d28f05d7714f44ce839e73f0cb70ccafe0a25110da5d2a4ff0dec4091c4 +size 1064 diff --git a/checkpoint-7562/special_tokens_map.json b/checkpoint-7562/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-7562/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-7562/tokenizer.model b/checkpoint-7562/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-7562/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-7562/tokenizer_config.json b/checkpoint-7562/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-7562/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-7562/trainer_state.json b/checkpoint-7562/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..04a77f434b4b8254a44fb0ac2516cb56411b1c3f --- /dev/null +++ b/checkpoint-7562/trainer_state.json @@ -0,0 +1,45696 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.792994966442953, + "eval_steps": 199, + "global_step": 7562, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + }, + { + "epoch": 0.21, + "learning_rate": 1.928689129323009e-05, + "loss": 1.421, + "step": 1991 + }, + { + "epoch": 0.21, + "learning_rate": 1.928553323396003e-05, + "loss": 1.5625, + "step": 1992 + }, + { + "epoch": 0.21, + "learning_rate": 1.92841739306671e-05, + "loss": 1.5198, + "step": 1993 + }, + { + "epoch": 0.21, + "learning_rate": 1.9282813383533415e-05, + "loss": 1.5116, + "step": 1994 + }, + { + "epoch": 0.21, + "learning_rate": 1.9281451592741247e-05, + "loss": 1.4306, + "step": 1995 + }, + { + "epoch": 0.21, + "learning_rate": 1.9280088558473046e-05, + "loss": 1.5425, + "step": 1996 + }, + { + "epoch": 0.21, + "learning_rate": 1.9278724280911424e-05, + "loss": 1.4972, + "step": 1997 + }, + { + "epoch": 0.21, + "learning_rate": 1.9277358760239156e-05, + "loss": 1.5185, + "step": 1998 + }, + { + "epoch": 0.21, + "learning_rate": 1.9275991996639188e-05, + "loss": 1.5187, + "step": 1999 + }, + { + "epoch": 0.21, + "learning_rate": 1.927462399029463e-05, + "loss": 1.4325, + "step": 2000 + }, + { + "epoch": 0.21, + "learning_rate": 1.9273254741388763e-05, + "loss": 1.4397, + "step": 2001 + }, + { + "epoch": 0.21, + "learning_rate": 1.927188425010503e-05, + "loss": 1.5319, + "step": 2002 + }, + { + "epoch": 0.21, + "learning_rate": 1.9270512516627042e-05, + "loss": 1.5664, + "step": 2003 + }, + { + "epoch": 0.21, + "learning_rate": 1.9269139541138574e-05, + "loss": 1.5227, + "step": 2004 + }, + { + "epoch": 0.21, + "learning_rate": 1.926776532382357e-05, + "loss": 1.5187, + "step": 2005 + }, + { + "epoch": 0.21, + "learning_rate": 1.9266389864866134e-05, + "loss": 1.4029, + "step": 2006 + }, + { + "epoch": 0.21, + "learning_rate": 1.9265013164450557e-05, + "loss": 1.387, + "step": 2007 + }, + { + "epoch": 0.21, + "learning_rate": 1.9263635222761268e-05, + "loss": 1.5047, + "step": 2008 + }, + { + "epoch": 0.21, + "learning_rate": 1.9262256039982882e-05, + "loss": 1.4816, + "step": 2009 + }, + { + "epoch": 0.21, + "learning_rate": 1.9260875616300172e-05, + "loss": 1.4607, + "step": 2010 + }, + { + "epoch": 0.21, + "learning_rate": 1.9259493951898084e-05, + "loss": 1.628, + "step": 2011 + }, + { + "epoch": 0.21, + "learning_rate": 1.9258111046961714e-05, + "loss": 1.4149, + "step": 2012 + }, + { + "epoch": 0.21, + "learning_rate": 1.925672690167635e-05, + "loss": 1.5303, + "step": 2013 + }, + { + "epoch": 0.21, + "learning_rate": 1.925534151622742e-05, + "loss": 1.5198, + "step": 2014 + }, + { + "epoch": 0.21, + "learning_rate": 1.9253954890800535e-05, + "loss": 1.6422, + "step": 2015 + }, + { + "epoch": 0.21, + "learning_rate": 1.925256702558147e-05, + "loss": 1.4738, + "step": 2016 + }, + { + "epoch": 0.21, + "learning_rate": 1.925117792075616e-05, + "loss": 1.4752, + "step": 2017 + }, + { + "epoch": 0.21, + "learning_rate": 1.9249787576510713e-05, + "loss": 1.4547, + "step": 2018 + }, + { + "epoch": 0.21, + "learning_rate": 1.924839599303139e-05, + "loss": 1.4864, + "step": 2019 + }, + { + "epoch": 0.21, + "learning_rate": 1.9247003170504638e-05, + "loss": 1.5037, + "step": 2020 + }, + { + "epoch": 0.21, + "learning_rate": 1.9245609109117053e-05, + "loss": 1.5089, + "step": 2021 + }, + { + "epoch": 0.21, + "learning_rate": 1.924421380905541e-05, + "loss": 1.5616, + "step": 2022 + }, + { + "epoch": 0.21, + "learning_rate": 1.9242817270506634e-05, + "loss": 1.4592, + "step": 2023 + }, + { + "epoch": 0.21, + "learning_rate": 1.9241419493657832e-05, + "loss": 1.5592, + "step": 2024 + }, + { + "epoch": 0.21, + "learning_rate": 1.924002047869627e-05, + "loss": 1.4897, + "step": 2025 + }, + { + "epoch": 0.21, + "learning_rate": 1.9238620225809375e-05, + "loss": 1.4743, + "step": 2026 + }, + { + "epoch": 0.21, + "learning_rate": 1.923721873518475e-05, + "loss": 1.4686, + "step": 2027 + }, + { + "epoch": 0.21, + "learning_rate": 1.923581600701016e-05, + "loss": 1.461, + "step": 2028 + }, + { + "epoch": 0.21, + "learning_rate": 1.9234412041473528e-05, + "loss": 1.6622, + "step": 2029 + }, + { + "epoch": 0.21, + "learning_rate": 1.9233006838762955e-05, + "loss": 1.4707, + "step": 2030 + }, + { + "epoch": 0.21, + "learning_rate": 1.92316003990667e-05, + "loss": 1.5566, + "step": 2031 + }, + { + "epoch": 0.21, + "learning_rate": 1.9230192722573188e-05, + "loss": 1.4881, + "step": 2032 + }, + { + "epoch": 0.21, + "learning_rate": 1.9228783809471015e-05, + "loss": 1.6124, + "step": 2033 + }, + { + "epoch": 0.21, + "learning_rate": 1.9227373659948937e-05, + "loss": 1.3508, + "step": 2034 + }, + { + "epoch": 0.21, + "learning_rate": 1.9225962274195876e-05, + "loss": 1.4418, + "step": 2035 + }, + { + "epoch": 0.21, + "learning_rate": 1.9224549652400927e-05, + "loss": 1.3954, + "step": 2036 + }, + { + "epoch": 0.21, + "learning_rate": 1.922313579475334e-05, + "loss": 1.4798, + "step": 2037 + }, + { + "epoch": 0.21, + "learning_rate": 1.922172070144254e-05, + "loss": 1.4556, + "step": 2038 + }, + { + "epoch": 0.21, + "learning_rate": 1.922030437265811e-05, + "loss": 1.4987, + "step": 2039 + }, + { + "epoch": 0.21, + "learning_rate": 1.9218886808589796e-05, + "loss": 1.4857, + "step": 2040 + }, + { + "epoch": 0.21, + "learning_rate": 1.9217468009427527e-05, + "loss": 1.5289, + "step": 2041 + }, + { + "epoch": 0.21, + "learning_rate": 1.921604797536138e-05, + "loss": 1.5267, + "step": 2042 + }, + { + "epoch": 0.21, + "learning_rate": 1.9214626706581598e-05, + "loss": 1.4655, + "step": 2043 + }, + { + "epoch": 0.21, + "learning_rate": 1.9213204203278602e-05, + "loss": 1.4598, + "step": 2044 + }, + { + "epoch": 0.21, + "learning_rate": 1.9211780465642973e-05, + "loss": 1.4766, + "step": 2045 + }, + { + "epoch": 0.21, + "learning_rate": 1.921035549386545e-05, + "loss": 1.5148, + "step": 2046 + }, + { + "epoch": 0.21, + "learning_rate": 1.9208929288136933e-05, + "loss": 1.5567, + "step": 2047 + }, + { + "epoch": 0.21, + "learning_rate": 1.920750184864852e-05, + "loss": 1.4868, + "step": 2048 + }, + { + "epoch": 0.21, + "learning_rate": 1.920607317559143e-05, + "loss": 1.4752, + "step": 2049 + }, + { + "epoch": 0.21, + "learning_rate": 1.920464326915708e-05, + "loss": 1.4882, + "step": 2050 + }, + { + "epoch": 0.22, + "learning_rate": 1.9203212129537035e-05, + "loss": 1.5933, + "step": 2051 + }, + { + "epoch": 0.22, + "learning_rate": 1.9201779756923037e-05, + "loss": 1.4891, + "step": 2052 + }, + { + "epoch": 0.22, + "learning_rate": 1.9200346151506983e-05, + "loss": 1.4486, + "step": 2053 + }, + { + "epoch": 0.22, + "learning_rate": 1.9198911313480938e-05, + "loss": 1.5091, + "step": 2054 + }, + { + "epoch": 0.22, + "learning_rate": 1.919747524303714e-05, + "loss": 1.4385, + "step": 2055 + }, + { + "epoch": 0.22, + "learning_rate": 1.9196037940367974e-05, + "loss": 1.4104, + "step": 2056 + }, + { + "epoch": 0.22, + "learning_rate": 1.9194599405666015e-05, + "loss": 1.4483, + "step": 2057 + }, + { + "epoch": 0.22, + "learning_rate": 1.9193159639123976e-05, + "loss": 1.4592, + "step": 2058 + }, + { + "epoch": 0.22, + "learning_rate": 1.919171864093476e-05, + "loss": 1.4975, + "step": 2059 + }, + { + "epoch": 0.22, + "learning_rate": 1.9190276411291423e-05, + "loss": 1.4727, + "step": 2060 + }, + { + "epoch": 0.22, + "learning_rate": 1.9188832950387178e-05, + "loss": 1.4791, + "step": 2061 + }, + { + "epoch": 0.22, + "learning_rate": 1.9187388258415423e-05, + "loss": 1.3806, + "step": 2062 + }, + { + "epoch": 0.22, + "learning_rate": 1.9185942335569697e-05, + "loss": 1.4514, + "step": 2063 + }, + { + "epoch": 0.22, + "learning_rate": 1.9184495182043727e-05, + "loss": 1.4389, + "step": 2064 + }, + { + "epoch": 0.22, + "learning_rate": 1.918304679803139e-05, + "loss": 1.5088, + "step": 2065 + }, + { + "epoch": 0.22, + "learning_rate": 1.9181597183726733e-05, + "loss": 1.4665, + "step": 2066 + }, + { + "epoch": 0.22, + "learning_rate": 1.9180146339323966e-05, + "loss": 1.489, + "step": 2067 + }, + { + "epoch": 0.22, + "learning_rate": 1.9178694265017466e-05, + "loss": 1.5215, + "step": 2068 + }, + { + "epoch": 0.22, + "learning_rate": 1.9177240961001775e-05, + "loss": 1.5152, + "step": 2069 + }, + { + "epoch": 0.22, + "learning_rate": 1.9175786427471594e-05, + "loss": 1.4418, + "step": 2070 + }, + { + "epoch": 0.22, + "learning_rate": 1.91743306646218e-05, + "loss": 1.5001, + "step": 2071 + }, + { + "epoch": 0.22, + "learning_rate": 1.9172873672647417e-05, + "loss": 1.4879, + "step": 2072 + }, + { + "epoch": 0.22, + "learning_rate": 1.917141545174366e-05, + "loss": 1.5299, + "step": 2073 + }, + { + "epoch": 0.22, + "learning_rate": 1.9169956002105877e-05, + "loss": 1.4602, + "step": 2074 + }, + { + "epoch": 0.22, + "learning_rate": 1.9168495323929605e-05, + "loss": 1.4921, + "step": 2075 + }, + { + "epoch": 0.22, + "learning_rate": 1.916703341741054e-05, + "loss": 1.4659, + "step": 2076 + }, + { + "epoch": 0.22, + "learning_rate": 1.9165570282744534e-05, + "loss": 1.4707, + "step": 2077 + }, + { + "epoch": 0.22, + "learning_rate": 1.9164105920127613e-05, + "loss": 1.5354, + "step": 2078 + }, + { + "epoch": 0.22, + "learning_rate": 1.9162640329755962e-05, + "loss": 1.526, + "step": 2079 + }, + { + "epoch": 0.22, + "learning_rate": 1.916117351182593e-05, + "loss": 1.6424, + "step": 2080 + }, + { + "epoch": 0.22, + "learning_rate": 1.915970546653404e-05, + "loss": 1.5048, + "step": 2081 + }, + { + "epoch": 0.22, + "learning_rate": 1.915823619407697e-05, + "loss": 1.5344, + "step": 2082 + }, + { + "epoch": 0.22, + "learning_rate": 1.915676569465156e-05, + "loss": 1.4604, + "step": 2083 + }, + { + "epoch": 0.22, + "learning_rate": 1.9155293968454826e-05, + "loss": 1.4929, + "step": 2084 + }, + { + "epoch": 0.22, + "learning_rate": 1.9153821015683937e-05, + "loss": 1.4106, + "step": 2085 + }, + { + "epoch": 0.22, + "learning_rate": 1.915234683653623e-05, + "loss": 1.4146, + "step": 2086 + }, + { + "epoch": 0.22, + "learning_rate": 1.9150871431209207e-05, + "loss": 1.4481, + "step": 2087 + }, + { + "epoch": 0.22, + "learning_rate": 1.914939479990054e-05, + "loss": 1.5206, + "step": 2088 + }, + { + "epoch": 0.22, + "learning_rate": 1.9147916942808054e-05, + "loss": 1.5073, + "step": 2089 + }, + { + "epoch": 0.22, + "learning_rate": 1.9146437860129745e-05, + "loss": 1.5196, + "step": 2090 + }, + { + "epoch": 0.22, + "learning_rate": 1.9144957552063775e-05, + "loss": 1.5389, + "step": 2091 + }, + { + "epoch": 0.22, + "learning_rate": 1.9143476018808463e-05, + "loss": 1.5207, + "step": 2092 + }, + { + "epoch": 0.22, + "learning_rate": 1.9141993260562298e-05, + "loss": 1.3717, + "step": 2093 + }, + { + "epoch": 0.22, + "learning_rate": 1.9140509277523937e-05, + "loss": 1.471, + "step": 2094 + }, + { + "epoch": 0.22, + "learning_rate": 1.9139024069892185e-05, + "loss": 1.4553, + "step": 2095 + }, + { + "epoch": 0.22, + "learning_rate": 1.9137537637866027e-05, + "loss": 1.5311, + "step": 2096 + }, + { + "epoch": 0.22, + "learning_rate": 1.9136049981644614e-05, + "loss": 1.4369, + "step": 2097 + }, + { + "epoch": 0.22, + "learning_rate": 1.913456110142724e-05, + "loss": 1.4528, + "step": 2098 + }, + { + "epoch": 0.22, + "learning_rate": 1.9133070997413384e-05, + "loss": 1.5294, + "step": 2099 + }, + { + "epoch": 0.22, + "learning_rate": 1.9131579669802685e-05, + "loss": 1.4588, + "step": 2100 + }, + { + "epoch": 0.22, + "learning_rate": 1.9130087118794934e-05, + "loss": 1.443, + "step": 2101 + }, + { + "epoch": 0.22, + "learning_rate": 1.9128593344590102e-05, + "loss": 1.4876, + "step": 2102 + }, + { + "epoch": 0.22, + "learning_rate": 1.912709834738831e-05, + "loss": 1.4874, + "step": 2103 + }, + { + "epoch": 0.22, + "learning_rate": 1.9125602127389856e-05, + "loss": 1.4966, + "step": 2104 + }, + { + "epoch": 0.22, + "learning_rate": 1.912410468479519e-05, + "loss": 1.5747, + "step": 2105 + }, + { + "epoch": 0.22, + "learning_rate": 1.9122606019804933e-05, + "loss": 1.4025, + "step": 2106 + }, + { + "epoch": 0.22, + "learning_rate": 1.912110613261987e-05, + "loss": 1.4755, + "step": 2107 + }, + { + "epoch": 0.22, + "learning_rate": 1.911960502344094e-05, + "loss": 1.4739, + "step": 2108 + }, + { + "epoch": 0.22, + "learning_rate": 1.911810269246926e-05, + "loss": 1.4992, + "step": 2109 + }, + { + "epoch": 0.22, + "learning_rate": 1.91165991399061e-05, + "loss": 1.4435, + "step": 2110 + }, + { + "epoch": 0.22, + "learning_rate": 1.91150943659529e-05, + "loss": 1.4918, + "step": 2111 + }, + { + "epoch": 0.22, + "learning_rate": 1.9113588370811258e-05, + "loss": 1.3818, + "step": 2112 + }, + { + "epoch": 0.22, + "learning_rate": 1.911208115468294e-05, + "loss": 1.5105, + "step": 2113 + }, + { + "epoch": 0.22, + "learning_rate": 1.9110572717769878e-05, + "loss": 1.6634, + "step": 2114 + }, + { + "epoch": 0.22, + "learning_rate": 1.9109063060274158e-05, + "loss": 1.5028, + "step": 2115 + }, + { + "epoch": 0.22, + "learning_rate": 1.9107552182398037e-05, + "loss": 1.6657, + "step": 2116 + }, + { + "epoch": 0.22, + "learning_rate": 1.9106040084343935e-05, + "loss": 1.5481, + "step": 2117 + }, + { + "epoch": 0.22, + "learning_rate": 1.910452676631444e-05, + "loss": 1.4505, + "step": 2118 + }, + { + "epoch": 0.22, + "learning_rate": 1.9103012228512284e-05, + "loss": 1.5173, + "step": 2119 + }, + { + "epoch": 0.22, + "learning_rate": 1.9101496471140385e-05, + "loss": 1.3788, + "step": 2120 + }, + { + "epoch": 0.22, + "learning_rate": 1.9099979494401814e-05, + "loss": 1.4649, + "step": 2121 + }, + { + "epoch": 0.22, + "learning_rate": 1.9098461298499805e-05, + "loss": 1.4204, + "step": 2122 + }, + { + "epoch": 0.22, + "learning_rate": 1.9096941883637766e-05, + "loss": 1.4439, + "step": 2123 + }, + { + "epoch": 0.22, + "learning_rate": 1.909542125001925e-05, + "loss": 1.6615, + "step": 2124 + }, + { + "epoch": 0.22, + "learning_rate": 1.9093899397847985e-05, + "loss": 1.4763, + "step": 2125 + }, + { + "epoch": 0.22, + "learning_rate": 1.909237632732786e-05, + "loss": 1.5353, + "step": 2126 + }, + { + "epoch": 0.22, + "learning_rate": 1.909085203866293e-05, + "loss": 1.442, + "step": 2127 + }, + { + "epoch": 0.22, + "learning_rate": 1.9089326532057408e-05, + "loss": 1.4782, + "step": 2128 + }, + { + "epoch": 0.22, + "learning_rate": 1.908779980771567e-05, + "loss": 1.4933, + "step": 2129 + }, + { + "epoch": 0.22, + "learning_rate": 1.9086271865842264e-05, + "loss": 1.5285, + "step": 2130 + }, + { + "epoch": 0.22, + "learning_rate": 1.9084742706641894e-05, + "loss": 1.4736, + "step": 2131 + }, + { + "epoch": 0.22, + "learning_rate": 1.9083212330319427e-05, + "loss": 1.4496, + "step": 2132 + }, + { + "epoch": 0.22, + "learning_rate": 1.908168073707989e-05, + "loss": 1.5099, + "step": 2133 + }, + { + "epoch": 0.22, + "learning_rate": 1.9080147927128483e-05, + "loss": 1.5235, + "step": 2134 + }, + { + "epoch": 0.22, + "learning_rate": 1.9078613900670556e-05, + "loss": 1.4769, + "step": 2135 + }, + { + "epoch": 0.22, + "learning_rate": 1.907707865791164e-05, + "loss": 1.5771, + "step": 2136 + }, + { + "epoch": 0.22, + "learning_rate": 1.907554219905741e-05, + "loss": 1.5116, + "step": 2137 + }, + { + "epoch": 0.22, + "learning_rate": 1.907400452431371e-05, + "loss": 1.5161, + "step": 2138 + }, + { + "epoch": 0.22, + "learning_rate": 1.9072465633886557e-05, + "loss": 1.4356, + "step": 2139 + }, + { + "epoch": 0.22, + "learning_rate": 1.9070925527982117e-05, + "loss": 1.509, + "step": 2140 + }, + { + "epoch": 0.22, + "learning_rate": 1.9069384206806723e-05, + "loss": 1.4681, + "step": 2141 + }, + { + "epoch": 0.22, + "learning_rate": 1.9067841670566883e-05, + "loss": 1.5254, + "step": 2142 + }, + { + "epoch": 0.22, + "learning_rate": 1.9066297919469242e-05, + "loss": 1.4797, + "step": 2143 + }, + { + "epoch": 0.22, + "learning_rate": 1.9064752953720636e-05, + "loss": 1.3996, + "step": 2144 + }, + { + "epoch": 0.22, + "learning_rate": 1.9063206773528042e-05, + "loss": 1.4457, + "step": 2145 + }, + { + "epoch": 0.23, + "learning_rate": 1.9061659379098617e-05, + "loss": 1.5126, + "step": 2146 + }, + { + "epoch": 0.23, + "learning_rate": 1.9060110770639664e-05, + "loss": 1.5925, + "step": 2147 + }, + { + "epoch": 0.23, + "learning_rate": 1.905856094835866e-05, + "loss": 1.5146, + "step": 2148 + }, + { + "epoch": 0.23, + "learning_rate": 1.905700991246324e-05, + "loss": 1.7256, + "step": 2149 + }, + { + "epoch": 0.23, + "learning_rate": 1.90554576631612e-05, + "loss": 1.57, + "step": 2150 + }, + { + "epoch": 0.23, + "learning_rate": 1.905390420066051e-05, + "loss": 1.3722, + "step": 2151 + }, + { + "epoch": 0.23, + "learning_rate": 1.9052349525169292e-05, + "loss": 1.3999, + "step": 2152 + }, + { + "epoch": 0.23, + "learning_rate": 1.9050793636895828e-05, + "loss": 1.586, + "step": 2153 + }, + { + "epoch": 0.23, + "learning_rate": 1.9049236536048567e-05, + "loss": 1.4884, + "step": 2154 + }, + { + "epoch": 0.23, + "learning_rate": 1.9047678222836127e-05, + "loss": 1.5898, + "step": 2155 + }, + { + "epoch": 0.23, + "learning_rate": 1.9046118697467278e-05, + "loss": 1.569, + "step": 2156 + }, + { + "epoch": 0.23, + "learning_rate": 1.904455796015095e-05, + "loss": 1.5592, + "step": 2157 + }, + { + "epoch": 0.23, + "learning_rate": 1.9042996011096253e-05, + "loss": 1.597, + "step": 2158 + }, + { + "epoch": 0.23, + "learning_rate": 1.904143285051244e-05, + "loss": 1.422, + "step": 2159 + }, + { + "epoch": 0.23, + "learning_rate": 1.903986847860894e-05, + "loss": 1.519, + "step": 2160 + }, + { + "epoch": 0.23, + "learning_rate": 1.9038302895595334e-05, + "loss": 1.5197, + "step": 2161 + }, + { + "epoch": 0.23, + "learning_rate": 1.903673610168137e-05, + "loss": 1.4655, + "step": 2162 + }, + { + "epoch": 0.23, + "learning_rate": 1.9035168097076965e-05, + "loss": 1.3909, + "step": 2163 + }, + { + "epoch": 0.23, + "learning_rate": 1.903359888199218e-05, + "loss": 1.4877, + "step": 2164 + }, + { + "epoch": 0.23, + "learning_rate": 1.903202845663726e-05, + "loss": 1.5123, + "step": 2165 + }, + { + "epoch": 0.23, + "learning_rate": 1.9030456821222593e-05, + "loss": 1.4906, + "step": 2166 + }, + { + "epoch": 0.23, + "learning_rate": 1.9028883975958745e-05, + "loss": 1.4574, + "step": 2167 + }, + { + "epoch": 0.23, + "learning_rate": 1.9027309921056435e-05, + "loss": 1.4571, + "step": 2168 + }, + { + "epoch": 0.23, + "learning_rate": 1.902573465672654e-05, + "loss": 1.4281, + "step": 2169 + }, + { + "epoch": 0.23, + "learning_rate": 1.9024158183180116e-05, + "loss": 1.5057, + "step": 2170 + }, + { + "epoch": 0.23, + "learning_rate": 1.902258050062836e-05, + "loss": 1.4514, + "step": 2171 + }, + { + "epoch": 0.23, + "learning_rate": 1.9021001609282646e-05, + "loss": 1.5055, + "step": 2172 + }, + { + "epoch": 0.23, + "learning_rate": 1.9019421509354505e-05, + "loss": 1.4578, + "step": 2173 + }, + { + "epoch": 0.23, + "learning_rate": 1.9017840201055625e-05, + "loss": 1.459, + "step": 2174 + }, + { + "epoch": 0.23, + "learning_rate": 1.9016257684597864e-05, + "loss": 1.5059, + "step": 2175 + }, + { + "epoch": 0.23, + "learning_rate": 1.901467396019324e-05, + "loss": 1.57, + "step": 2176 + }, + { + "epoch": 0.23, + "learning_rate": 1.901308902805393e-05, + "loss": 1.4924, + "step": 2177 + }, + { + "epoch": 0.23, + "learning_rate": 1.9011502888392273e-05, + "loss": 1.4979, + "step": 2178 + }, + { + "epoch": 0.23, + "learning_rate": 1.900991554142077e-05, + "loss": 1.5321, + "step": 2179 + }, + { + "epoch": 0.23, + "learning_rate": 1.9008326987352093e-05, + "loss": 1.493, + "step": 2180 + }, + { + "epoch": 0.23, + "learning_rate": 1.9006737226399056e-05, + "loss": 1.5111, + "step": 2181 + }, + { + "epoch": 0.23, + "learning_rate": 1.900514625877465e-05, + "loss": 1.4154, + "step": 2182 + }, + { + "epoch": 0.23, + "learning_rate": 1.900355408469203e-05, + "loss": 1.4934, + "step": 2183 + }, + { + "epoch": 0.23, + "learning_rate": 1.90019607043645e-05, + "loss": 1.5975, + "step": 2184 + }, + { + "epoch": 0.23, + "learning_rate": 1.9000366118005532e-05, + "loss": 1.3537, + "step": 2185 + }, + { + "epoch": 0.23, + "learning_rate": 1.899877032582876e-05, + "loss": 1.4583, + "step": 2186 + }, + { + "epoch": 0.23, + "learning_rate": 1.8997173328047984e-05, + "loss": 1.4586, + "step": 2187 + }, + { + "epoch": 0.23, + "learning_rate": 1.8995575124877156e-05, + "loss": 1.4774, + "step": 2188 + }, + { + "epoch": 0.23, + "learning_rate": 1.8993975716530394e-05, + "loss": 1.5025, + "step": 2189 + }, + { + "epoch": 0.23, + "eval_loss": 1.5263344049453735, + "eval_runtime": 77.1492, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 2189 + }, + { + "epoch": 0.23, + "learning_rate": 1.899237510322198e-05, + "loss": 1.5438, + "step": 2190 + }, + { + "epoch": 0.23, + "learning_rate": 1.899077328516635e-05, + "loss": 1.5181, + "step": 2191 + }, + { + "epoch": 0.23, + "learning_rate": 1.8989170262578112e-05, + "loss": 1.4454, + "step": 2192 + }, + { + "epoch": 0.23, + "learning_rate": 1.8987566035672028e-05, + "loss": 1.4882, + "step": 2193 + }, + { + "epoch": 0.23, + "learning_rate": 1.8985960604663026e-05, + "loss": 1.5073, + "step": 2194 + }, + { + "epoch": 0.23, + "learning_rate": 1.8984353969766187e-05, + "loss": 1.4478, + "step": 2195 + }, + { + "epoch": 0.23, + "learning_rate": 1.8982746131196763e-05, + "loss": 1.4768, + "step": 2196 + }, + { + "epoch": 0.23, + "learning_rate": 1.8981137089170162e-05, + "loss": 1.5116, + "step": 2197 + }, + { + "epoch": 0.23, + "learning_rate": 1.8979526843901952e-05, + "loss": 1.4202, + "step": 2198 + }, + { + "epoch": 0.23, + "learning_rate": 1.8977915395607867e-05, + "loss": 1.4736, + "step": 2199 + }, + { + "epoch": 0.23, + "learning_rate": 1.89763027445038e-05, + "loss": 1.4489, + "step": 2200 + }, + { + "epoch": 0.23, + "learning_rate": 1.8974688890805804e-05, + "loss": 1.4512, + "step": 2201 + }, + { + "epoch": 0.23, + "learning_rate": 1.897307383473009e-05, + "loss": 1.5091, + "step": 2202 + }, + { + "epoch": 0.23, + "learning_rate": 1.897145757649304e-05, + "loss": 1.5512, + "step": 2203 + }, + { + "epoch": 0.23, + "learning_rate": 1.8969840116311192e-05, + "loss": 1.406, + "step": 2204 + }, + { + "epoch": 0.23, + "learning_rate": 1.896822145440124e-05, + "loss": 1.4531, + "step": 2205 + }, + { + "epoch": 0.23, + "learning_rate": 1.896660159098004e-05, + "loss": 1.4379, + "step": 2206 + }, + { + "epoch": 0.23, + "learning_rate": 1.896498052626462e-05, + "loss": 1.4783, + "step": 2207 + }, + { + "epoch": 0.23, + "learning_rate": 1.896335826047216e-05, + "loss": 1.4801, + "step": 2208 + }, + { + "epoch": 0.23, + "learning_rate": 1.896173479381999e-05, + "loss": 1.4526, + "step": 2209 + }, + { + "epoch": 0.23, + "learning_rate": 1.8960110126525627e-05, + "loss": 1.4952, + "step": 2210 + }, + { + "epoch": 0.23, + "learning_rate": 1.895848425880673e-05, + "loss": 1.5299, + "step": 2211 + }, + { + "epoch": 0.23, + "learning_rate": 1.8956857190881125e-05, + "loss": 1.5274, + "step": 2212 + }, + { + "epoch": 0.23, + "learning_rate": 1.8955228922966792e-05, + "loss": 1.4415, + "step": 2213 + }, + { + "epoch": 0.23, + "learning_rate": 1.8953599455281884e-05, + "loss": 1.5311, + "step": 2214 + }, + { + "epoch": 0.23, + "learning_rate": 1.8951968788044702e-05, + "loss": 1.4972, + "step": 2215 + }, + { + "epoch": 0.23, + "learning_rate": 1.8950336921473715e-05, + "loss": 1.4966, + "step": 2216 + }, + { + "epoch": 0.23, + "learning_rate": 1.8948703855787553e-05, + "loss": 1.4683, + "step": 2217 + }, + { + "epoch": 0.23, + "learning_rate": 1.8947069591205005e-05, + "loss": 1.503, + "step": 2218 + }, + { + "epoch": 0.23, + "learning_rate": 1.8945434127945014e-05, + "loss": 1.4902, + "step": 2219 + }, + { + "epoch": 0.23, + "learning_rate": 1.8943797466226702e-05, + "loss": 1.4835, + "step": 2220 + }, + { + "epoch": 0.23, + "learning_rate": 1.8942159606269332e-05, + "loss": 1.535, + "step": 2221 + }, + { + "epoch": 0.23, + "learning_rate": 1.8940520548292332e-05, + "loss": 1.491, + "step": 2222 + }, + { + "epoch": 0.23, + "learning_rate": 1.89388802925153e-05, + "loss": 1.5157, + "step": 2223 + }, + { + "epoch": 0.23, + "learning_rate": 1.8937238839157987e-05, + "loss": 1.4779, + "step": 2224 + }, + { + "epoch": 0.23, + "learning_rate": 1.8935596188440302e-05, + "loss": 1.4902, + "step": 2225 + }, + { + "epoch": 0.23, + "learning_rate": 1.8933952340582323e-05, + "loss": 1.4988, + "step": 2226 + }, + { + "epoch": 0.23, + "learning_rate": 1.893230729580428e-05, + "loss": 1.4568, + "step": 2227 + }, + { + "epoch": 0.23, + "learning_rate": 1.8930661054326567e-05, + "loss": 1.5163, + "step": 2228 + }, + { + "epoch": 0.23, + "learning_rate": 1.892901361636974e-05, + "loss": 1.4472, + "step": 2229 + }, + { + "epoch": 0.23, + "learning_rate": 1.892736498215451e-05, + "loss": 1.4658, + "step": 2230 + }, + { + "epoch": 0.23, + "learning_rate": 1.8925715151901754e-05, + "loss": 1.4281, + "step": 2231 + }, + { + "epoch": 0.23, + "learning_rate": 1.892406412583251e-05, + "loss": 1.415, + "step": 2232 + }, + { + "epoch": 0.23, + "learning_rate": 1.8922411904167966e-05, + "loss": 1.464, + "step": 2233 + }, + { + "epoch": 0.23, + "learning_rate": 1.892075848712948e-05, + "loss": 1.5014, + "step": 2234 + }, + { + "epoch": 0.23, + "learning_rate": 1.8919103874938568e-05, + "loss": 1.4397, + "step": 2235 + }, + { + "epoch": 0.23, + "learning_rate": 1.891744806781691e-05, + "loss": 1.5508, + "step": 2236 + }, + { + "epoch": 0.23, + "learning_rate": 1.8915791065986335e-05, + "loss": 1.4749, + "step": 2237 + }, + { + "epoch": 0.23, + "learning_rate": 1.891413286966884e-05, + "loss": 1.4538, + "step": 2238 + }, + { + "epoch": 0.23, + "learning_rate": 1.891247347908658e-05, + "loss": 1.4405, + "step": 2239 + }, + { + "epoch": 0.23, + "learning_rate": 1.8910812894461878e-05, + "loss": 1.3562, + "step": 2240 + }, + { + "epoch": 0.24, + "learning_rate": 1.89091511160172e-05, + "loss": 1.4811, + "step": 2241 + }, + { + "epoch": 0.24, + "learning_rate": 1.8907488143975186e-05, + "loss": 1.4286, + "step": 2242 + }, + { + "epoch": 0.24, + "learning_rate": 1.890582397855863e-05, + "loss": 1.4493, + "step": 2243 + }, + { + "epoch": 0.24, + "learning_rate": 1.890415861999049e-05, + "loss": 1.5639, + "step": 2244 + }, + { + "epoch": 0.24, + "learning_rate": 1.890249206849388e-05, + "loss": 1.6375, + "step": 2245 + }, + { + "epoch": 0.24, + "learning_rate": 1.890082432429208e-05, + "loss": 1.4982, + "step": 2246 + }, + { + "epoch": 0.24, + "learning_rate": 1.889915538760851e-05, + "loss": 1.492, + "step": 2247 + }, + { + "epoch": 0.24, + "learning_rate": 1.8897485258666778e-05, + "loss": 1.4294, + "step": 2248 + }, + { + "epoch": 0.24, + "learning_rate": 1.8895813937690638e-05, + "loss": 1.4617, + "step": 2249 + }, + { + "epoch": 0.24, + "learning_rate": 1.8894141424904e-05, + "loss": 1.4763, + "step": 2250 + }, + { + "epoch": 0.24, + "learning_rate": 1.8892467720530937e-05, + "loss": 1.3989, + "step": 2251 + }, + { + "epoch": 0.24, + "learning_rate": 1.8890792824795687e-05, + "loss": 1.4803, + "step": 2252 + }, + { + "epoch": 0.24, + "learning_rate": 1.8889116737922638e-05, + "loss": 1.4734, + "step": 2253 + }, + { + "epoch": 0.24, + "learning_rate": 1.8887439460136342e-05, + "loss": 1.5069, + "step": 2254 + }, + { + "epoch": 0.24, + "learning_rate": 1.8885760991661514e-05, + "loss": 1.5565, + "step": 2255 + }, + { + "epoch": 0.24, + "learning_rate": 1.8884081332723028e-05, + "loss": 1.4707, + "step": 2256 + }, + { + "epoch": 0.24, + "learning_rate": 1.8882400483545913e-05, + "loss": 1.5077, + "step": 2257 + }, + { + "epoch": 0.24, + "learning_rate": 1.888071844435536e-05, + "loss": 1.5075, + "step": 2258 + }, + { + "epoch": 0.24, + "learning_rate": 1.8879035215376717e-05, + "loss": 1.5185, + "step": 2259 + }, + { + "epoch": 0.24, + "learning_rate": 1.887735079683549e-05, + "loss": 1.6266, + "step": 2260 + }, + { + "epoch": 0.24, + "learning_rate": 1.8875665188957354e-05, + "loss": 1.5013, + "step": 2261 + }, + { + "epoch": 0.24, + "learning_rate": 1.887397839196814e-05, + "loss": 1.4362, + "step": 2262 + }, + { + "epoch": 0.24, + "learning_rate": 1.8872290406093827e-05, + "loss": 1.4718, + "step": 2263 + }, + { + "epoch": 0.24, + "learning_rate": 1.8870601231560567e-05, + "loss": 1.5202, + "step": 2264 + }, + { + "epoch": 0.24, + "learning_rate": 1.8868910868594664e-05, + "loss": 1.5168, + "step": 2265 + }, + { + "epoch": 0.24, + "learning_rate": 1.8867219317422588e-05, + "loss": 1.5142, + "step": 2266 + }, + { + "epoch": 0.24, + "learning_rate": 1.8865526578270954e-05, + "loss": 1.4885, + "step": 2267 + }, + { + "epoch": 0.24, + "learning_rate": 1.8863832651366552e-05, + "loss": 1.5441, + "step": 2268 + }, + { + "epoch": 0.24, + "learning_rate": 1.8862137536936328e-05, + "loss": 1.4647, + "step": 2269 + }, + { + "epoch": 0.24, + "learning_rate": 1.8860441235207374e-05, + "loss": 1.5352, + "step": 2270 + }, + { + "epoch": 0.24, + "learning_rate": 1.8858743746406958e-05, + "loss": 1.4568, + "step": 2271 + }, + { + "epoch": 0.24, + "learning_rate": 1.8857045070762497e-05, + "loss": 1.4865, + "step": 2272 + }, + { + "epoch": 0.24, + "learning_rate": 1.8855345208501573e-05, + "loss": 1.4637, + "step": 2273 + }, + { + "epoch": 0.24, + "learning_rate": 1.8853644159851918e-05, + "loss": 1.4348, + "step": 2274 + }, + { + "epoch": 0.24, + "learning_rate": 1.8851941925041436e-05, + "loss": 1.4413, + "step": 2275 + }, + { + "epoch": 0.24, + "learning_rate": 1.8850238504298177e-05, + "loss": 1.4434, + "step": 2276 + }, + { + "epoch": 0.24, + "learning_rate": 1.884853389785036e-05, + "loss": 1.4822, + "step": 2277 + }, + { + "epoch": 0.24, + "learning_rate": 1.8846828105926356e-05, + "loss": 1.4632, + "step": 2278 + }, + { + "epoch": 0.24, + "learning_rate": 1.8845121128754698e-05, + "loss": 1.48, + "step": 2279 + }, + { + "epoch": 0.24, + "learning_rate": 1.8843412966564078e-05, + "loss": 1.4518, + "step": 2280 + }, + { + "epoch": 0.24, + "learning_rate": 1.884170361958334e-05, + "loss": 1.4334, + "step": 2281 + }, + { + "epoch": 0.24, + "learning_rate": 1.8839993088041502e-05, + "loss": 1.5131, + "step": 2282 + }, + { + "epoch": 0.24, + "learning_rate": 1.8838281372167724e-05, + "loss": 1.508, + "step": 2283 + }, + { + "epoch": 0.24, + "learning_rate": 1.8836568472191335e-05, + "loss": 1.4086, + "step": 2284 + }, + { + "epoch": 0.24, + "learning_rate": 1.883485438834182e-05, + "loss": 1.5021, + "step": 2285 + }, + { + "epoch": 0.24, + "learning_rate": 1.8833139120848817e-05, + "loss": 1.5083, + "step": 2286 + }, + { + "epoch": 0.24, + "learning_rate": 1.8831422669942137e-05, + "loss": 1.4162, + "step": 2287 + }, + { + "epoch": 0.24, + "learning_rate": 1.8829705035851734e-05, + "loss": 1.5494, + "step": 2288 + }, + { + "epoch": 0.24, + "learning_rate": 1.8827986218807724e-05, + "loss": 1.425, + "step": 2289 + }, + { + "epoch": 0.24, + "learning_rate": 1.8826266219040396e-05, + "loss": 1.5215, + "step": 2290 + }, + { + "epoch": 0.24, + "learning_rate": 1.8824545036780172e-05, + "loss": 1.5577, + "step": 2291 + }, + { + "epoch": 0.24, + "learning_rate": 1.8822822672257655e-05, + "loss": 1.4923, + "step": 2292 + }, + { + "epoch": 0.24, + "learning_rate": 1.8821099125703595e-05, + "loss": 1.4648, + "step": 2293 + }, + { + "epoch": 0.24, + "learning_rate": 1.8819374397348902e-05, + "loss": 1.471, + "step": 2294 + }, + { + "epoch": 0.24, + "learning_rate": 1.8817648487424648e-05, + "loss": 1.5658, + "step": 2295 + }, + { + "epoch": 0.24, + "learning_rate": 1.8815921396162058e-05, + "loss": 1.5348, + "step": 2296 + }, + { + "epoch": 0.24, + "learning_rate": 1.8814193123792518e-05, + "loss": 1.4081, + "step": 2297 + }, + { + "epoch": 0.24, + "learning_rate": 1.881246367054757e-05, + "loss": 1.4762, + "step": 2298 + }, + { + "epoch": 0.24, + "learning_rate": 1.8810733036658925e-05, + "loss": 1.4399, + "step": 2299 + }, + { + "epoch": 0.24, + "learning_rate": 1.8809001222358432e-05, + "loss": 1.4763, + "step": 2300 + }, + { + "epoch": 0.24, + "learning_rate": 1.880726822787812e-05, + "loss": 1.4874, + "step": 2301 + }, + { + "epoch": 0.24, + "learning_rate": 1.880553405345016e-05, + "loss": 1.4951, + "step": 2302 + }, + { + "epoch": 0.24, + "learning_rate": 1.8803798699306887e-05, + "loss": 1.4697, + "step": 2303 + }, + { + "epoch": 0.24, + "learning_rate": 1.880206216568079e-05, + "loss": 1.481, + "step": 2304 + }, + { + "epoch": 0.24, + "learning_rate": 1.880032445280453e-05, + "loss": 1.4485, + "step": 2305 + }, + { + "epoch": 0.24, + "learning_rate": 1.879858556091091e-05, + "loss": 1.4749, + "step": 2306 + }, + { + "epoch": 0.24, + "learning_rate": 1.8796845490232894e-05, + "loss": 1.5605, + "step": 2307 + }, + { + "epoch": 0.24, + "learning_rate": 1.879510424100361e-05, + "loss": 1.4835, + "step": 2308 + }, + { + "epoch": 0.24, + "learning_rate": 1.8793361813456346e-05, + "loss": 1.4344, + "step": 2309 + }, + { + "epoch": 0.24, + "learning_rate": 1.8791618207824532e-05, + "loss": 1.4571, + "step": 2310 + }, + { + "epoch": 0.24, + "learning_rate": 1.8789873424341772e-05, + "loss": 1.482, + "step": 2311 + }, + { + "epoch": 0.24, + "learning_rate": 1.8788127463241822e-05, + "loss": 1.4736, + "step": 2312 + }, + { + "epoch": 0.24, + "learning_rate": 1.8786380324758597e-05, + "loss": 1.4807, + "step": 2313 + }, + { + "epoch": 0.24, + "learning_rate": 1.8784632009126167e-05, + "loss": 1.4418, + "step": 2314 + }, + { + "epoch": 0.24, + "learning_rate": 1.878288251657876e-05, + "loss": 1.5248, + "step": 2315 + }, + { + "epoch": 0.24, + "learning_rate": 1.8781131847350768e-05, + "loss": 1.483, + "step": 2316 + }, + { + "epoch": 0.24, + "learning_rate": 1.877938000167673e-05, + "loss": 1.5474, + "step": 2317 + }, + { + "epoch": 0.24, + "learning_rate": 1.8777626979791347e-05, + "loss": 1.4671, + "step": 2318 + }, + { + "epoch": 0.24, + "learning_rate": 1.877587278192949e-05, + "loss": 1.3049, + "step": 2319 + }, + { + "epoch": 0.24, + "learning_rate": 1.877411740832616e-05, + "loss": 1.483, + "step": 2320 + }, + { + "epoch": 0.24, + "learning_rate": 1.877236085921655e-05, + "loss": 1.508, + "step": 2321 + }, + { + "epoch": 0.24, + "learning_rate": 1.8770603134835978e-05, + "loss": 1.4854, + "step": 2322 + }, + { + "epoch": 0.24, + "learning_rate": 1.8768844235419942e-05, + "loss": 1.4808, + "step": 2323 + }, + { + "epoch": 0.24, + "learning_rate": 1.8767084161204087e-05, + "loss": 1.5352, + "step": 2324 + }, + { + "epoch": 0.24, + "learning_rate": 1.8765322912424214e-05, + "loss": 1.5628, + "step": 2325 + }, + { + "epoch": 0.24, + "learning_rate": 1.8763560489316292e-05, + "loss": 1.494, + "step": 2326 + }, + { + "epoch": 0.24, + "learning_rate": 1.876179689211643e-05, + "loss": 1.509, + "step": 2327 + }, + { + "epoch": 0.24, + "learning_rate": 1.8760032121060918e-05, + "loss": 1.5021, + "step": 2328 + }, + { + "epoch": 0.24, + "learning_rate": 1.875826617638618e-05, + "loss": 1.4179, + "step": 2329 + }, + { + "epoch": 0.24, + "learning_rate": 1.8756499058328813e-05, + "loss": 1.4302, + "step": 2330 + }, + { + "epoch": 0.24, + "learning_rate": 1.8754730767125564e-05, + "loss": 1.4959, + "step": 2331 + }, + { + "epoch": 0.24, + "learning_rate": 1.8752961303013336e-05, + "loss": 1.4423, + "step": 2332 + }, + { + "epoch": 0.24, + "learning_rate": 1.8751190666229194e-05, + "loss": 1.4564, + "step": 2333 + }, + { + "epoch": 0.24, + "learning_rate": 1.8749418857010358e-05, + "loss": 1.4775, + "step": 2334 + }, + { + "epoch": 0.24, + "learning_rate": 1.8747645875594203e-05, + "loss": 1.4182, + "step": 2335 + }, + { + "epoch": 0.24, + "learning_rate": 1.8745871722218265e-05, + "loss": 1.3957, + "step": 2336 + }, + { + "epoch": 0.25, + "learning_rate": 1.8744096397120235e-05, + "loss": 1.4633, + "step": 2337 + }, + { + "epoch": 0.25, + "learning_rate": 1.874231990053796e-05, + "loss": 1.5512, + "step": 2338 + }, + { + "epoch": 0.25, + "learning_rate": 1.8740542232709444e-05, + "loss": 1.3461, + "step": 2339 + }, + { + "epoch": 0.25, + "learning_rate": 1.8738763393872848e-05, + "loss": 1.4754, + "step": 2340 + }, + { + "epoch": 0.25, + "learning_rate": 1.8736983384266495e-05, + "loss": 1.5448, + "step": 2341 + }, + { + "epoch": 0.25, + "learning_rate": 1.8735202204128854e-05, + "loss": 1.4491, + "step": 2342 + }, + { + "epoch": 0.25, + "learning_rate": 1.8733419853698566e-05, + "loss": 1.457, + "step": 2343 + }, + { + "epoch": 0.25, + "learning_rate": 1.8731636333214414e-05, + "loss": 1.4314, + "step": 2344 + }, + { + "epoch": 0.25, + "learning_rate": 1.8729851642915345e-05, + "loss": 1.3979, + "step": 2345 + }, + { + "epoch": 0.25, + "learning_rate": 1.8728065783040464e-05, + "loss": 1.4146, + "step": 2346 + }, + { + "epoch": 0.25, + "learning_rate": 1.8726278753829027e-05, + "loss": 1.4361, + "step": 2347 + }, + { + "epoch": 0.25, + "learning_rate": 1.872449055552045e-05, + "loss": 1.4989, + "step": 2348 + }, + { + "epoch": 0.25, + "learning_rate": 1.872270118835431e-05, + "loss": 1.5062, + "step": 2349 + }, + { + "epoch": 0.25, + "learning_rate": 1.872091065257033e-05, + "loss": 1.4509, + "step": 2350 + }, + { + "epoch": 0.25, + "learning_rate": 1.8719118948408403e-05, + "loss": 1.4631, + "step": 2351 + }, + { + "epoch": 0.25, + "learning_rate": 1.8717326076108566e-05, + "loss": 1.5119, + "step": 2352 + }, + { + "epoch": 0.25, + "learning_rate": 1.8715532035911017e-05, + "loss": 1.6347, + "step": 2353 + }, + { + "epoch": 0.25, + "learning_rate": 1.8713736828056115e-05, + "loss": 1.5526, + "step": 2354 + }, + { + "epoch": 0.25, + "learning_rate": 1.8711940452784368e-05, + "loss": 1.6348, + "step": 2355 + }, + { + "epoch": 0.25, + "learning_rate": 1.871014291033645e-05, + "loss": 1.5183, + "step": 2356 + }, + { + "epoch": 0.25, + "learning_rate": 1.8708344200953182e-05, + "loss": 1.458, + "step": 2357 + }, + { + "epoch": 0.25, + "learning_rate": 1.8706544324875545e-05, + "loss": 1.524, + "step": 2358 + }, + { + "epoch": 0.25, + "learning_rate": 1.8704743282344672e-05, + "loss": 1.4479, + "step": 2359 + }, + { + "epoch": 0.25, + "learning_rate": 1.870294107360186e-05, + "loss": 1.5408, + "step": 2360 + }, + { + "epoch": 0.25, + "learning_rate": 1.8701137698888563e-05, + "loss": 1.5007, + "step": 2361 + }, + { + "epoch": 0.25, + "learning_rate": 1.8699333158446382e-05, + "loss": 1.5132, + "step": 2362 + }, + { + "epoch": 0.25, + "learning_rate": 1.869752745251708e-05, + "loss": 1.4263, + "step": 2363 + }, + { + "epoch": 0.25, + "learning_rate": 1.8695720581342574e-05, + "loss": 1.422, + "step": 2364 + }, + { + "epoch": 0.25, + "learning_rate": 1.869391254516494e-05, + "loss": 1.4411, + "step": 2365 + }, + { + "epoch": 0.25, + "learning_rate": 1.8692103344226406e-05, + "loss": 1.4594, + "step": 2366 + }, + { + "epoch": 0.25, + "learning_rate": 1.8690292978769364e-05, + "loss": 1.4992, + "step": 2367 + }, + { + "epoch": 0.25, + "learning_rate": 1.868848144903635e-05, + "loss": 1.4822, + "step": 2368 + }, + { + "epoch": 0.25, + "learning_rate": 1.8686668755270064e-05, + "loss": 1.5402, + "step": 2369 + }, + { + "epoch": 0.25, + "learning_rate": 1.8684854897713363e-05, + "loss": 1.5268, + "step": 2370 + }, + { + "epoch": 0.25, + "learning_rate": 1.8683039876609258e-05, + "loss": 1.5587, + "step": 2371 + }, + { + "epoch": 0.25, + "learning_rate": 1.868122369220091e-05, + "loss": 1.4214, + "step": 2372 + }, + { + "epoch": 0.25, + "learning_rate": 1.8679406344731645e-05, + "loss": 1.5089, + "step": 2373 + }, + { + "epoch": 0.25, + "learning_rate": 1.867758783444494e-05, + "loss": 1.5067, + "step": 2374 + }, + { + "epoch": 0.25, + "learning_rate": 1.8675768161584427e-05, + "loss": 2.0616, + "step": 2375 + }, + { + "epoch": 0.25, + "learning_rate": 1.8673947326393903e-05, + "loss": 1.5617, + "step": 2376 + }, + { + "epoch": 0.25, + "learning_rate": 1.86721253291173e-05, + "loss": 1.4422, + "step": 2377 + }, + { + "epoch": 0.25, + "learning_rate": 1.867030216999873e-05, + "loss": 1.4727, + "step": 2378 + }, + { + "epoch": 0.25, + "learning_rate": 1.8668477849282443e-05, + "loss": 1.4152, + "step": 2379 + }, + { + "epoch": 0.25, + "learning_rate": 1.8666652367212856e-05, + "loss": 1.4376, + "step": 2380 + }, + { + "epoch": 0.25, + "learning_rate": 1.8664825724034534e-05, + "loss": 1.393, + "step": 2381 + }, + { + "epoch": 0.25, + "learning_rate": 1.8662997919992197e-05, + "loss": 1.4864, + "step": 2382 + }, + { + "epoch": 0.25, + "learning_rate": 1.866116895533073e-05, + "loss": 1.4261, + "step": 2383 + }, + { + "epoch": 0.25, + "learning_rate": 1.8659338830295163e-05, + "loss": 1.4555, + "step": 2384 + }, + { + "epoch": 0.25, + "learning_rate": 1.8657507545130687e-05, + "loss": 1.4939, + "step": 2385 + }, + { + "epoch": 0.25, + "learning_rate": 1.865567510008265e-05, + "loss": 1.4123, + "step": 2386 + }, + { + "epoch": 0.25, + "learning_rate": 1.8653841495396546e-05, + "loss": 1.4459, + "step": 2387 + }, + { + "epoch": 0.25, + "learning_rate": 1.8652006731318038e-05, + "loss": 1.396, + "step": 2388 + }, + { + "epoch": 0.25, + "eval_loss": 1.5139706134796143, + "eval_runtime": 77.2904, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 2388 + }, + { + "epoch": 0.25, + "learning_rate": 1.8650170808092936e-05, + "loss": 1.4666, + "step": 2389 + }, + { + "epoch": 0.25, + "learning_rate": 1.86483337259672e-05, + "loss": 1.5154, + "step": 2390 + }, + { + "epoch": 0.25, + "learning_rate": 1.864649548518696e-05, + "loss": 1.5163, + "step": 2391 + }, + { + "epoch": 0.25, + "learning_rate": 1.864465608599849e-05, + "loss": 1.4734, + "step": 2392 + }, + { + "epoch": 0.25, + "learning_rate": 1.864281552864822e-05, + "loss": 1.5217, + "step": 2393 + }, + { + "epoch": 0.25, + "learning_rate": 1.8640973813382737e-05, + "loss": 1.4694, + "step": 2394 + }, + { + "epoch": 0.25, + "learning_rate": 1.863913094044879e-05, + "loss": 1.4761, + "step": 2395 + }, + { + "epoch": 0.25, + "learning_rate": 1.863728691009327e-05, + "loss": 1.4766, + "step": 2396 + }, + { + "epoch": 0.25, + "learning_rate": 1.863544172256323e-05, + "loss": 1.5695, + "step": 2397 + }, + { + "epoch": 0.25, + "learning_rate": 1.8633595378105882e-05, + "loss": 1.5079, + "step": 2398 + }, + { + "epoch": 0.25, + "learning_rate": 1.8631747876968584e-05, + "loss": 1.4154, + "step": 2399 + }, + { + "epoch": 0.25, + "learning_rate": 1.862989921939886e-05, + "loss": 1.4488, + "step": 2400 + }, + { + "epoch": 0.25, + "learning_rate": 1.8628049405644376e-05, + "loss": 1.4279, + "step": 2401 + }, + { + "epoch": 0.25, + "learning_rate": 1.8626198435952966e-05, + "loss": 1.4896, + "step": 2402 + }, + { + "epoch": 0.25, + "learning_rate": 1.8624346310572602e-05, + "loss": 1.4315, + "step": 2403 + }, + { + "epoch": 0.25, + "learning_rate": 1.862249302975143e-05, + "loss": 1.4919, + "step": 2404 + }, + { + "epoch": 0.25, + "learning_rate": 1.8620638593737743e-05, + "loss": 1.4561, + "step": 2405 + }, + { + "epoch": 0.25, + "learning_rate": 1.8618783002779985e-05, + "loss": 1.4622, + "step": 2406 + }, + { + "epoch": 0.25, + "learning_rate": 1.8616926257126754e-05, + "loss": 1.4917, + "step": 2407 + }, + { + "epoch": 0.25, + "learning_rate": 1.861506835702681e-05, + "loss": 1.4962, + "step": 2408 + }, + { + "epoch": 0.25, + "learning_rate": 1.861320930272906e-05, + "loss": 1.4164, + "step": 2409 + }, + { + "epoch": 0.25, + "learning_rate": 1.8611349094482578e-05, + "loss": 1.4889, + "step": 2410 + }, + { + "epoch": 0.25, + "learning_rate": 1.8609487732536576e-05, + "loss": 1.543, + "step": 2411 + }, + { + "epoch": 0.25, + "learning_rate": 1.8607625217140433e-05, + "loss": 1.5417, + "step": 2412 + }, + { + "epoch": 0.25, + "learning_rate": 1.8605761548543674e-05, + "loss": 1.5304, + "step": 2413 + }, + { + "epoch": 0.25, + "learning_rate": 1.860389672699599e-05, + "loss": 1.4725, + "step": 2414 + }, + { + "epoch": 0.25, + "learning_rate": 1.860203075274721e-05, + "loss": 1.4745, + "step": 2415 + }, + { + "epoch": 0.25, + "learning_rate": 1.8600163626047334e-05, + "loss": 1.4656, + "step": 2416 + }, + { + "epoch": 0.25, + "learning_rate": 1.8598295347146503e-05, + "loss": 1.5287, + "step": 2417 + }, + { + "epoch": 0.25, + "learning_rate": 1.8596425916295023e-05, + "loss": 1.5024, + "step": 2418 + }, + { + "epoch": 0.25, + "learning_rate": 1.8594555333743348e-05, + "loss": 1.4527, + "step": 2419 + }, + { + "epoch": 0.25, + "learning_rate": 1.859268359974209e-05, + "loss": 1.4897, + "step": 2420 + }, + { + "epoch": 0.25, + "learning_rate": 1.859081071454201e-05, + "loss": 1.3554, + "step": 2421 + }, + { + "epoch": 0.25, + "learning_rate": 1.858893667839403e-05, + "loss": 1.4004, + "step": 2422 + }, + { + "epoch": 0.25, + "learning_rate": 1.858706149154922e-05, + "loss": 1.5582, + "step": 2423 + }, + { + "epoch": 0.25, + "learning_rate": 1.8585185154258803e-05, + "loss": 1.505, + "step": 2424 + }, + { + "epoch": 0.25, + "learning_rate": 1.858330766677417e-05, + "loss": 1.5043, + "step": 2425 + }, + { + "epoch": 0.25, + "learning_rate": 1.858142902934685e-05, + "loss": 1.439, + "step": 2426 + }, + { + "epoch": 0.25, + "learning_rate": 1.857954924222853e-05, + "loss": 1.4927, + "step": 2427 + }, + { + "epoch": 0.25, + "learning_rate": 1.8577668305671056e-05, + "loss": 1.5395, + "step": 2428 + }, + { + "epoch": 0.25, + "learning_rate": 1.8575786219926427e-05, + "loss": 1.4737, + "step": 2429 + }, + { + "epoch": 0.25, + "learning_rate": 1.8573902985246794e-05, + "loss": 1.6151, + "step": 2430 + }, + { + "epoch": 0.25, + "learning_rate": 1.857201860188446e-05, + "loss": 1.4313, + "step": 2431 + }, + { + "epoch": 0.26, + "learning_rate": 1.857013307009188e-05, + "loss": 1.4509, + "step": 2432 + }, + { + "epoch": 0.26, + "learning_rate": 1.8568246390121673e-05, + "loss": 1.3998, + "step": 2433 + }, + { + "epoch": 0.26, + "learning_rate": 1.8566358562226603e-05, + "loss": 1.5268, + "step": 2434 + }, + { + "epoch": 0.26, + "learning_rate": 1.8564469586659593e-05, + "loss": 1.4369, + "step": 2435 + }, + { + "epoch": 0.26, + "learning_rate": 1.8562579463673713e-05, + "loss": 1.4759, + "step": 2436 + }, + { + "epoch": 0.26, + "learning_rate": 1.8560688193522197e-05, + "loss": 1.4092, + "step": 2437 + }, + { + "epoch": 0.26, + "learning_rate": 1.855879577645842e-05, + "loss": 1.43, + "step": 2438 + }, + { + "epoch": 0.26, + "learning_rate": 1.855690221273592e-05, + "loss": 1.5143, + "step": 2439 + }, + { + "epoch": 0.26, + "learning_rate": 1.8555007502608385e-05, + "loss": 1.5482, + "step": 2440 + }, + { + "epoch": 0.26, + "learning_rate": 1.855311164632966e-05, + "loss": 1.4406, + "step": 2441 + }, + { + "epoch": 0.26, + "learning_rate": 1.8551214644153738e-05, + "loss": 1.4551, + "step": 2442 + }, + { + "epoch": 0.26, + "learning_rate": 1.8549316496334774e-05, + "loss": 1.4663, + "step": 2443 + }, + { + "epoch": 0.26, + "learning_rate": 1.8547417203127064e-05, + "loss": 1.4732, + "step": 2444 + }, + { + "epoch": 0.26, + "learning_rate": 1.8545516764785067e-05, + "loss": 1.5378, + "step": 2445 + }, + { + "epoch": 0.26, + "learning_rate": 1.8543615181563397e-05, + "loss": 1.4448, + "step": 2446 + }, + { + "epoch": 0.26, + "learning_rate": 1.854171245371681e-05, + "loss": 1.2861, + "step": 2447 + }, + { + "epoch": 0.26, + "learning_rate": 1.8539808581500228e-05, + "loss": 1.4405, + "step": 2448 + }, + { + "epoch": 0.26, + "learning_rate": 1.8537903565168716e-05, + "loss": 1.4876, + "step": 2449 + }, + { + "epoch": 0.26, + "learning_rate": 1.8535997404977506e-05, + "loss": 1.4119, + "step": 2450 + }, + { + "epoch": 0.26, + "learning_rate": 1.8534090101181967e-05, + "loss": 1.4451, + "step": 2451 + }, + { + "epoch": 0.26, + "learning_rate": 1.8532181654037632e-05, + "loss": 1.4035, + "step": 2452 + }, + { + "epoch": 0.26, + "learning_rate": 1.853027206380018e-05, + "loss": 1.4624, + "step": 2453 + }, + { + "epoch": 0.26, + "learning_rate": 1.852836133072545e-05, + "loss": 1.4935, + "step": 2454 + }, + { + "epoch": 0.26, + "learning_rate": 1.8526449455069434e-05, + "loss": 1.4834, + "step": 2455 + }, + { + "epoch": 0.26, + "learning_rate": 1.8524536437088266e-05, + "loss": 1.498, + "step": 2456 + }, + { + "epoch": 0.26, + "learning_rate": 1.8522622277038247e-05, + "loss": 1.3417, + "step": 2457 + }, + { + "epoch": 0.26, + "learning_rate": 1.852070697517583e-05, + "loss": 1.4455, + "step": 2458 + }, + { + "epoch": 0.26, + "learning_rate": 1.8518790531757607e-05, + "loss": 1.4119, + "step": 2459 + }, + { + "epoch": 0.26, + "learning_rate": 1.8516872947040337e-05, + "loss": 1.558, + "step": 2460 + }, + { + "epoch": 0.26, + "learning_rate": 1.8514954221280926e-05, + "loss": 1.4862, + "step": 2461 + }, + { + "epoch": 0.26, + "learning_rate": 1.8513034354736433e-05, + "loss": 1.6806, + "step": 2462 + }, + { + "epoch": 0.26, + "learning_rate": 1.8511113347664072e-05, + "loss": 1.438, + "step": 2463 + }, + { + "epoch": 0.26, + "learning_rate": 1.850919120032121e-05, + "loss": 1.4975, + "step": 2464 + }, + { + "epoch": 0.26, + "learning_rate": 1.850726791296536e-05, + "loss": 1.4409, + "step": 2465 + }, + { + "epoch": 0.26, + "learning_rate": 1.85053434858542e-05, + "loss": 1.4769, + "step": 2466 + }, + { + "epoch": 0.26, + "learning_rate": 1.8503417919245548e-05, + "loss": 1.5823, + "step": 2467 + }, + { + "epoch": 0.26, + "learning_rate": 1.8501491213397386e-05, + "loss": 1.4045, + "step": 2468 + }, + { + "epoch": 0.26, + "learning_rate": 1.8499563368567837e-05, + "loss": 1.4828, + "step": 2469 + }, + { + "epoch": 0.26, + "learning_rate": 1.849763438501519e-05, + "loss": 1.4684, + "step": 2470 + }, + { + "epoch": 0.26, + "learning_rate": 1.8495704262997873e-05, + "loss": 1.4577, + "step": 2471 + }, + { + "epoch": 0.26, + "learning_rate": 1.8493773002774475e-05, + "loss": 1.4759, + "step": 2472 + }, + { + "epoch": 0.26, + "learning_rate": 1.8491840604603736e-05, + "loss": 1.4259, + "step": 2473 + }, + { + "epoch": 0.26, + "learning_rate": 1.8489907068744543e-05, + "loss": 1.4717, + "step": 2474 + }, + { + "epoch": 0.26, + "learning_rate": 1.848797239545595e-05, + "loss": 1.4247, + "step": 2475 + }, + { + "epoch": 0.26, + "learning_rate": 1.8486036584997143e-05, + "loss": 1.4954, + "step": 2476 + }, + { + "epoch": 0.26, + "learning_rate": 1.8484099637627472e-05, + "loss": 1.4926, + "step": 2477 + }, + { + "epoch": 0.26, + "learning_rate": 1.8482161553606447e-05, + "loss": 1.487, + "step": 2478 + }, + { + "epoch": 0.26, + "learning_rate": 1.8480222333193715e-05, + "loss": 1.4553, + "step": 2479 + }, + { + "epoch": 0.26, + "learning_rate": 1.847828197664908e-05, + "loss": 1.4862, + "step": 2480 + }, + { + "epoch": 0.26, + "learning_rate": 1.8476340484232508e-05, + "loss": 1.4867, + "step": 2481 + }, + { + "epoch": 0.26, + "learning_rate": 1.8474397856204097e-05, + "loss": 1.4736, + "step": 2482 + }, + { + "epoch": 0.26, + "learning_rate": 1.8472454092824122e-05, + "loss": 1.4254, + "step": 2483 + }, + { + "epoch": 0.26, + "learning_rate": 1.8470509194352987e-05, + "loss": 1.4455, + "step": 2484 + }, + { + "epoch": 0.26, + "learning_rate": 1.8468563161051263e-05, + "loss": 1.4402, + "step": 2485 + }, + { + "epoch": 0.26, + "learning_rate": 1.846661599317967e-05, + "loss": 1.4611, + "step": 2486 + }, + { + "epoch": 0.26, + "learning_rate": 1.8464667690999073e-05, + "loss": 1.4814, + "step": 2487 + }, + { + "epoch": 0.26, + "learning_rate": 1.8462718254770503e-05, + "loss": 1.4559, + "step": 2488 + }, + { + "epoch": 0.26, + "learning_rate": 1.8460767684755127e-05, + "loss": 1.4667, + "step": 2489 + }, + { + "epoch": 0.26, + "learning_rate": 1.8458815981214274e-05, + "loss": 1.4427, + "step": 2490 + }, + { + "epoch": 0.26, + "learning_rate": 1.845686314440942e-05, + "loss": 1.4055, + "step": 2491 + }, + { + "epoch": 0.26, + "learning_rate": 1.8454909174602198e-05, + "loss": 1.5563, + "step": 2492 + }, + { + "epoch": 0.26, + "learning_rate": 1.845295407205439e-05, + "loss": 1.4631, + "step": 2493 + }, + { + "epoch": 0.26, + "learning_rate": 1.8450997837027925e-05, + "loss": 1.4887, + "step": 2494 + }, + { + "epoch": 0.26, + "learning_rate": 1.8449040469784895e-05, + "loss": 1.5212, + "step": 2495 + }, + { + "epoch": 0.26, + "learning_rate": 1.844708197058753e-05, + "loss": 1.5582, + "step": 2496 + }, + { + "epoch": 0.26, + "learning_rate": 1.844512233969822e-05, + "loss": 1.4599, + "step": 2497 + }, + { + "epoch": 0.26, + "learning_rate": 1.844316157737951e-05, + "loss": 1.4546, + "step": 2498 + }, + { + "epoch": 0.26, + "learning_rate": 1.844119968389409e-05, + "loss": 1.4631, + "step": 2499 + }, + { + "epoch": 0.26, + "learning_rate": 1.84392366595048e-05, + "loss": 1.4817, + "step": 2500 + }, + { + "epoch": 0.26, + "learning_rate": 1.8437272504474636e-05, + "loss": 1.4214, + "step": 2501 + }, + { + "epoch": 0.26, + "learning_rate": 1.8435307219066744e-05, + "loss": 1.471, + "step": 2502 + }, + { + "epoch": 0.26, + "learning_rate": 1.8433340803544424e-05, + "loss": 1.4693, + "step": 2503 + }, + { + "epoch": 0.26, + "learning_rate": 1.8431373258171127e-05, + "loss": 1.6297, + "step": 2504 + }, + { + "epoch": 0.26, + "learning_rate": 1.842940458321045e-05, + "loss": 1.5916, + "step": 2505 + }, + { + "epoch": 0.26, + "learning_rate": 1.842743477892614e-05, + "loss": 1.4754, + "step": 2506 + }, + { + "epoch": 0.26, + "learning_rate": 1.842546384558211e-05, + "loss": 1.4828, + "step": 2507 + }, + { + "epoch": 0.26, + "learning_rate": 1.842349178344241e-05, + "loss": 1.4239, + "step": 2508 + }, + { + "epoch": 0.26, + "learning_rate": 1.8421518592771243e-05, + "loss": 1.5028, + "step": 2509 + }, + { + "epoch": 0.26, + "learning_rate": 1.841954427383297e-05, + "loss": 1.4848, + "step": 2510 + }, + { + "epoch": 0.26, + "learning_rate": 1.8417568826892097e-05, + "loss": 1.4617, + "step": 2511 + }, + { + "epoch": 0.26, + "learning_rate": 1.8415592252213284e-05, + "loss": 1.4266, + "step": 2512 + }, + { + "epoch": 0.26, + "learning_rate": 1.8413614550061344e-05, + "loss": 1.4321, + "step": 2513 + }, + { + "epoch": 0.26, + "learning_rate": 1.841163572070123e-05, + "loss": 1.4693, + "step": 2514 + }, + { + "epoch": 0.26, + "learning_rate": 1.840965576439806e-05, + "loss": 1.4257, + "step": 2515 + }, + { + "epoch": 0.26, + "learning_rate": 1.84076746814171e-05, + "loss": 1.4488, + "step": 2516 + }, + { + "epoch": 0.26, + "learning_rate": 1.840569247202376e-05, + "loss": 1.5348, + "step": 2517 + }, + { + "epoch": 0.26, + "learning_rate": 1.8403709136483604e-05, + "loss": 1.477, + "step": 2518 + }, + { + "epoch": 0.26, + "learning_rate": 1.840172467506235e-05, + "loss": 1.443, + "step": 2519 + }, + { + "epoch": 0.26, + "learning_rate": 1.839973908802587e-05, + "loss": 1.4772, + "step": 2520 + }, + { + "epoch": 0.26, + "learning_rate": 1.839775237564017e-05, + "loss": 1.4443, + "step": 2521 + }, + { + "epoch": 0.26, + "learning_rate": 1.839576453817143e-05, + "loss": 1.4063, + "step": 2522 + }, + { + "epoch": 0.26, + "learning_rate": 1.8393775575885963e-05, + "loss": 1.5178, + "step": 2523 + }, + { + "epoch": 0.26, + "learning_rate": 1.8391785489050235e-05, + "loss": 1.4337, + "step": 2524 + }, + { + "epoch": 0.26, + "learning_rate": 1.8389794277930875e-05, + "loss": 1.4512, + "step": 2525 + }, + { + "epoch": 0.26, + "learning_rate": 1.838780194279465e-05, + "loss": 1.5578, + "step": 2526 + }, + { + "epoch": 0.26, + "learning_rate": 1.8385808483908484e-05, + "loss": 1.4606, + "step": 2527 + }, + { + "epoch": 0.27, + "learning_rate": 1.8383813901539444e-05, + "loss": 1.4957, + "step": 2528 + }, + { + "epoch": 0.27, + "learning_rate": 1.838181819595476e-05, + "loss": 1.4914, + "step": 2529 + }, + { + "epoch": 0.27, + "learning_rate": 1.8379821367421802e-05, + "loss": 1.4785, + "step": 2530 + }, + { + "epoch": 0.27, + "learning_rate": 1.837782341620809e-05, + "loss": 1.4052, + "step": 2531 + }, + { + "epoch": 0.27, + "learning_rate": 1.8375824342581303e-05, + "loss": 1.4807, + "step": 2532 + }, + { + "epoch": 0.27, + "learning_rate": 1.8373824146809264e-05, + "loss": 1.4313, + "step": 2533 + }, + { + "epoch": 0.27, + "learning_rate": 1.8371822829159945e-05, + "loss": 1.4374, + "step": 2534 + }, + { + "epoch": 0.27, + "learning_rate": 1.836982038990148e-05, + "loss": 1.4482, + "step": 2535 + }, + { + "epoch": 0.27, + "learning_rate": 1.8367816829302133e-05, + "loss": 1.5231, + "step": 2536 + }, + { + "epoch": 0.27, + "learning_rate": 1.8365812147630337e-05, + "loss": 1.4101, + "step": 2537 + }, + { + "epoch": 0.27, + "learning_rate": 1.8363806345154666e-05, + "loss": 1.4372, + "step": 2538 + }, + { + "epoch": 0.27, + "learning_rate": 1.8361799422143845e-05, + "loss": 1.4808, + "step": 2539 + }, + { + "epoch": 0.27, + "learning_rate": 1.835979137886675e-05, + "loss": 1.3515, + "step": 2540 + }, + { + "epoch": 0.27, + "learning_rate": 1.8357782215592412e-05, + "loss": 1.5284, + "step": 2541 + }, + { + "epoch": 0.27, + "learning_rate": 1.835577193259e-05, + "loss": 1.4222, + "step": 2542 + }, + { + "epoch": 0.27, + "learning_rate": 1.8353760530128846e-05, + "loss": 1.4522, + "step": 2543 + }, + { + "epoch": 0.27, + "learning_rate": 1.835174800847842e-05, + "loss": 1.4487, + "step": 2544 + }, + { + "epoch": 0.27, + "learning_rate": 1.8349734367908355e-05, + "loss": 1.3688, + "step": 2545 + }, + { + "epoch": 0.27, + "learning_rate": 1.8347719608688422e-05, + "loss": 1.483, + "step": 2546 + }, + { + "epoch": 0.27, + "learning_rate": 1.8345703731088554e-05, + "loss": 1.4733, + "step": 2547 + }, + { + "epoch": 0.27, + "learning_rate": 1.8343686735378816e-05, + "loss": 1.4594, + "step": 2548 + }, + { + "epoch": 0.27, + "learning_rate": 1.834166862182944e-05, + "loss": 1.4648, + "step": 2549 + }, + { + "epoch": 0.27, + "learning_rate": 1.8339649390710807e-05, + "loss": 1.5249, + "step": 2550 + }, + { + "epoch": 0.27, + "learning_rate": 1.8337629042293434e-05, + "loss": 1.4744, + "step": 2551 + }, + { + "epoch": 0.27, + "learning_rate": 1.8335607576847994e-05, + "loss": 1.5094, + "step": 2552 + }, + { + "epoch": 0.27, + "learning_rate": 1.8333584994645318e-05, + "loss": 1.5122, + "step": 2553 + }, + { + "epoch": 0.27, + "learning_rate": 1.8331561295956374e-05, + "loss": 1.537, + "step": 2554 + }, + { + "epoch": 0.27, + "learning_rate": 1.832953648105229e-05, + "loss": 1.4691, + "step": 2555 + }, + { + "epoch": 0.27, + "learning_rate": 1.8327510550204343e-05, + "loss": 1.4969, + "step": 2556 + }, + { + "epoch": 0.27, + "learning_rate": 1.8325483503683944e-05, + "loss": 1.4596, + "step": 2557 + }, + { + "epoch": 0.27, + "learning_rate": 1.8323455341762675e-05, + "loss": 1.435, + "step": 2558 + }, + { + "epoch": 0.27, + "learning_rate": 1.8321426064712255e-05, + "loss": 1.4883, + "step": 2559 + }, + { + "epoch": 0.27, + "learning_rate": 1.8319395672804554e-05, + "loss": 1.3758, + "step": 2560 + }, + { + "epoch": 0.27, + "learning_rate": 1.8317364166311592e-05, + "loss": 1.4352, + "step": 2561 + }, + { + "epoch": 0.27, + "learning_rate": 1.831533154550554e-05, + "loss": 1.5072, + "step": 2562 + }, + { + "epoch": 0.27, + "learning_rate": 1.8313297810658718e-05, + "loss": 1.4476, + "step": 2563 + }, + { + "epoch": 0.27, + "learning_rate": 1.831126296204359e-05, + "loss": 1.507, + "step": 2564 + }, + { + "epoch": 0.27, + "learning_rate": 1.8309226999932777e-05, + "loss": 1.4677, + "step": 2565 + }, + { + "epoch": 0.27, + "learning_rate": 1.8307189924599044e-05, + "loss": 1.4537, + "step": 2566 + }, + { + "epoch": 0.27, + "learning_rate": 1.8305151736315307e-05, + "loss": 1.4584, + "step": 2567 + }, + { + "epoch": 0.27, + "learning_rate": 1.8303112435354634e-05, + "loss": 1.4944, + "step": 2568 + }, + { + "epoch": 0.27, + "learning_rate": 1.8301072021990232e-05, + "loss": 1.4379, + "step": 2569 + }, + { + "epoch": 0.27, + "learning_rate": 1.8299030496495475e-05, + "loss": 1.539, + "step": 2570 + }, + { + "epoch": 0.27, + "learning_rate": 1.829698785914386e-05, + "loss": 1.4421, + "step": 2571 + }, + { + "epoch": 0.27, + "learning_rate": 1.8294944110209063e-05, + "loss": 1.4693, + "step": 2572 + }, + { + "epoch": 0.27, + "learning_rate": 1.8292899249964887e-05, + "loss": 1.3239, + "step": 2573 + }, + { + "epoch": 0.27, + "learning_rate": 1.8290853278685284e-05, + "loss": 1.472, + "step": 2574 + }, + { + "epoch": 0.27, + "learning_rate": 1.8288806196644374e-05, + "loss": 1.536, + "step": 2575 + }, + { + "epoch": 0.27, + "learning_rate": 1.8286758004116405e-05, + "loss": 1.4644, + "step": 2576 + }, + { + "epoch": 0.27, + "learning_rate": 1.8284708701375783e-05, + "loss": 1.4537, + "step": 2577 + }, + { + "epoch": 0.27, + "learning_rate": 1.8282658288697067e-05, + "loss": 1.4359, + "step": 2578 + }, + { + "epoch": 0.27, + "learning_rate": 1.8280606766354955e-05, + "loss": 1.4842, + "step": 2579 + }, + { + "epoch": 0.27, + "learning_rate": 1.8278554134624302e-05, + "loss": 1.4664, + "step": 2580 + }, + { + "epoch": 0.27, + "learning_rate": 1.8276500393780105e-05, + "loss": 1.4632, + "step": 2581 + }, + { + "epoch": 0.27, + "learning_rate": 1.827444554409751e-05, + "loss": 1.4996, + "step": 2582 + }, + { + "epoch": 0.27, + "learning_rate": 1.827238958585182e-05, + "loss": 1.3399, + "step": 2583 + }, + { + "epoch": 0.27, + "learning_rate": 1.8270332519318476e-05, + "loss": 1.3928, + "step": 2584 + }, + { + "epoch": 0.27, + "learning_rate": 1.8268274344773074e-05, + "loss": 1.4993, + "step": 2585 + }, + { + "epoch": 0.27, + "learning_rate": 1.8266215062491356e-05, + "loss": 1.5398, + "step": 2586 + }, + { + "epoch": 0.27, + "learning_rate": 1.826415467274921e-05, + "loss": 1.4353, + "step": 2587 + }, + { + "epoch": 0.27, + "eval_loss": 1.5104212760925293, + "eval_runtime": 77.3448, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2587 + }, + { + "epoch": 0.27, + "learning_rate": 1.8262093175822685e-05, + "loss": 1.4889, + "step": 2588 + }, + { + "epoch": 0.27, + "learning_rate": 1.826003057198796e-05, + "loss": 1.4912, + "step": 2589 + }, + { + "epoch": 0.27, + "learning_rate": 1.825796686152137e-05, + "loss": 1.4884, + "step": 2590 + }, + { + "epoch": 0.27, + "learning_rate": 1.8255902044699404e-05, + "loss": 1.478, + "step": 2591 + }, + { + "epoch": 0.27, + "learning_rate": 1.8253836121798692e-05, + "loss": 1.6549, + "step": 2592 + }, + { + "epoch": 0.27, + "learning_rate": 1.8251769093096018e-05, + "loss": 1.5146, + "step": 2593 + }, + { + "epoch": 0.27, + "learning_rate": 1.8249700958868306e-05, + "loss": 1.4797, + "step": 2594 + }, + { + "epoch": 0.27, + "learning_rate": 1.8247631719392634e-05, + "loss": 1.4655, + "step": 2595 + }, + { + "epoch": 0.27, + "learning_rate": 1.824556137494623e-05, + "loss": 1.4517, + "step": 2596 + }, + { + "epoch": 0.27, + "learning_rate": 1.8243489925806458e-05, + "loss": 1.4936, + "step": 2597 + }, + { + "epoch": 0.27, + "learning_rate": 1.8241417372250852e-05, + "loss": 1.4614, + "step": 2598 + }, + { + "epoch": 0.27, + "learning_rate": 1.8239343714557073e-05, + "loss": 1.4475, + "step": 2599 + }, + { + "epoch": 0.27, + "learning_rate": 1.8237268953002937e-05, + "loss": 1.5435, + "step": 2600 + }, + { + "epoch": 0.27, + "learning_rate": 1.8235193087866413e-05, + "loss": 1.4616, + "step": 2601 + }, + { + "epoch": 0.27, + "learning_rate": 1.8233116119425612e-05, + "loss": 1.4578, + "step": 2602 + }, + { + "epoch": 0.27, + "learning_rate": 1.8231038047958795e-05, + "loss": 1.434, + "step": 2603 + }, + { + "epoch": 0.27, + "learning_rate": 1.8228958873744368e-05, + "loss": 1.5335, + "step": 2604 + }, + { + "epoch": 0.27, + "learning_rate": 1.8226878597060887e-05, + "loss": 1.415, + "step": 2605 + }, + { + "epoch": 0.27, + "learning_rate": 1.8224797218187058e-05, + "loss": 1.6165, + "step": 2606 + }, + { + "epoch": 0.27, + "learning_rate": 1.822271473740173e-05, + "loss": 1.372, + "step": 2607 + }, + { + "epoch": 0.27, + "learning_rate": 1.8220631154983907e-05, + "loss": 1.4855, + "step": 2608 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218546471212727e-05, + "loss": 1.4093, + "step": 2609 + }, + { + "epoch": 0.27, + "learning_rate": 1.821646068636749e-05, + "loss": 1.4852, + "step": 2610 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214373800727637e-05, + "loss": 1.6959, + "step": 2611 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212285814572755e-05, + "loss": 1.3874, + "step": 2612 + }, + { + "epoch": 0.27, + "learning_rate": 1.821019672818258e-05, + "loss": 1.4425, + "step": 2613 + }, + { + "epoch": 0.27, + "learning_rate": 1.8208106541837e-05, + "loss": 1.6097, + "step": 2614 + }, + { + "epoch": 0.27, + "learning_rate": 1.8206015255816045e-05, + "loss": 1.5675, + "step": 2615 + }, + { + "epoch": 0.27, + "learning_rate": 1.820392287039989e-05, + "loss": 1.4039, + "step": 2616 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201829385868866e-05, + "loss": 1.4872, + "step": 2617 + }, + { + "epoch": 0.27, + "learning_rate": 1.819973480250344e-05, + "loss": 1.4645, + "step": 2618 + }, + { + "epoch": 0.27, + "learning_rate": 1.8197639120584237e-05, + "loss": 1.4923, + "step": 2619 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195542340392025e-05, + "loss": 1.4294, + "step": 2620 + }, + { + "epoch": 0.27, + "learning_rate": 1.8193444462207717e-05, + "loss": 1.4315, + "step": 2621 + }, + { + "epoch": 0.27, + "learning_rate": 1.8191345486312372e-05, + "loss": 1.3972, + "step": 2622 + }, + { + "epoch": 0.28, + "learning_rate": 1.8189245412987205e-05, + "loss": 1.462, + "step": 2623 + }, + { + "epoch": 0.28, + "learning_rate": 1.8187144242513567e-05, + "loss": 1.4738, + "step": 2624 + }, + { + "epoch": 0.28, + "learning_rate": 1.818504197517296e-05, + "loss": 1.4935, + "step": 2625 + }, + { + "epoch": 0.28, + "learning_rate": 1.8182938611247038e-05, + "loss": 1.4231, + "step": 2626 + }, + { + "epoch": 0.28, + "learning_rate": 1.81808341510176e-05, + "loss": 1.4031, + "step": 2627 + }, + { + "epoch": 0.28, + "learning_rate": 1.817872859476658e-05, + "loss": 1.5822, + "step": 2628 + }, + { + "epoch": 0.28, + "learning_rate": 1.8176621942776075e-05, + "loss": 1.432, + "step": 2629 + }, + { + "epoch": 0.28, + "learning_rate": 1.8174514195328324e-05, + "loss": 1.5565, + "step": 2630 + }, + { + "epoch": 0.28, + "learning_rate": 1.8172405352705704e-05, + "loss": 1.4895, + "step": 2631 + }, + { + "epoch": 0.28, + "learning_rate": 1.8170295415190754e-05, + "loss": 1.4032, + "step": 2632 + }, + { + "epoch": 0.28, + "learning_rate": 1.8168184383066144e-05, + "loss": 1.4253, + "step": 2633 + }, + { + "epoch": 0.28, + "learning_rate": 1.8166072256614702e-05, + "loss": 1.5162, + "step": 2634 + }, + { + "epoch": 0.28, + "learning_rate": 1.81639590361194e-05, + "loss": 1.4609, + "step": 2635 + }, + { + "epoch": 0.28, + "learning_rate": 1.816184472186335e-05, + "loss": 1.4351, + "step": 2636 + }, + { + "epoch": 0.28, + "learning_rate": 1.8159729314129823e-05, + "loss": 1.4738, + "step": 2637 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157612813202224e-05, + "loss": 1.5986, + "step": 2638 + }, + { + "epoch": 0.28, + "learning_rate": 1.815549521936411e-05, + "loss": 1.4633, + "step": 2639 + }, + { + "epoch": 0.28, + "learning_rate": 1.8153376532899184e-05, + "loss": 1.4404, + "step": 2640 + }, + { + "epoch": 0.28, + "learning_rate": 1.81512567540913e-05, + "loss": 1.4256, + "step": 2641 + }, + { + "epoch": 0.28, + "learning_rate": 1.814913588322445e-05, + "loss": 1.4054, + "step": 2642 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147013920582773e-05, + "loss": 1.4134, + "step": 2643 + }, + { + "epoch": 0.28, + "learning_rate": 1.8144890866450567e-05, + "loss": 1.4098, + "step": 2644 + }, + { + "epoch": 0.28, + "learning_rate": 1.814276672111226e-05, + "loss": 1.4593, + "step": 2645 + }, + { + "epoch": 0.28, + "learning_rate": 1.814064148485243e-05, + "loss": 1.4679, + "step": 2646 + }, + { + "epoch": 0.28, + "learning_rate": 1.8138515157955812e-05, + "loss": 1.5234, + "step": 2647 + }, + { + "epoch": 0.28, + "learning_rate": 1.8136387740707272e-05, + "loss": 1.4568, + "step": 2648 + }, + { + "epoch": 0.28, + "learning_rate": 1.8134259233391836e-05, + "loss": 1.5057, + "step": 2649 + }, + { + "epoch": 0.28, + "learning_rate": 1.8132129636294665e-05, + "loss": 1.3643, + "step": 2650 + }, + { + "epoch": 0.28, + "learning_rate": 1.812999894970107e-05, + "loss": 1.4766, + "step": 2651 + }, + { + "epoch": 0.28, + "learning_rate": 1.812786717389651e-05, + "loss": 1.5701, + "step": 2652 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125734309166587e-05, + "loss": 1.5341, + "step": 2653 + }, + { + "epoch": 0.28, + "learning_rate": 1.812360035579705e-05, + "loss": 1.3596, + "step": 2654 + }, + { + "epoch": 0.28, + "learning_rate": 1.8121465314073793e-05, + "loss": 1.4847, + "step": 2655 + }, + { + "epoch": 0.28, + "learning_rate": 1.811932918428286e-05, + "loss": 1.4664, + "step": 2656 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117191966710438e-05, + "loss": 1.4673, + "step": 2657 + }, + { + "epoch": 0.28, + "learning_rate": 1.8115053661642856e-05, + "loss": 1.4712, + "step": 2658 + }, + { + "epoch": 0.28, + "learning_rate": 1.811291426936659e-05, + "loss": 1.4458, + "step": 2659 + }, + { + "epoch": 0.28, + "learning_rate": 1.811077379016827e-05, + "loss": 1.4667, + "step": 2660 + }, + { + "epoch": 0.28, + "learning_rate": 1.810863222433466e-05, + "loss": 1.4695, + "step": 2661 + }, + { + "epoch": 0.28, + "learning_rate": 1.8106489572152677e-05, + "loss": 1.5263, + "step": 2662 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104345833909376e-05, + "loss": 1.4148, + "step": 2663 + }, + { + "epoch": 0.28, + "learning_rate": 1.8102201009891976e-05, + "loss": 1.3955, + "step": 2664 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100055100387814e-05, + "loss": 1.6056, + "step": 2665 + }, + { + "epoch": 0.28, + "learning_rate": 1.8097908105684396e-05, + "loss": 1.5394, + "step": 2666 + }, + { + "epoch": 0.28, + "learning_rate": 1.809576002606936e-05, + "loss": 1.479, + "step": 2667 + }, + { + "epoch": 0.28, + "learning_rate": 1.8093610861830494e-05, + "loss": 1.4492, + "step": 2668 + }, + { + "epoch": 0.28, + "learning_rate": 1.8091460613255728e-05, + "loss": 1.4172, + "step": 2669 + }, + { + "epoch": 0.28, + "learning_rate": 1.808930928063315e-05, + "loss": 1.4498, + "step": 2670 + }, + { + "epoch": 0.28, + "learning_rate": 1.808715686425097e-05, + "loss": 1.6203, + "step": 2671 + }, + { + "epoch": 0.28, + "learning_rate": 1.8085003364397567e-05, + "loss": 1.435, + "step": 2672 + }, + { + "epoch": 0.28, + "learning_rate": 1.808284878136145e-05, + "loss": 1.4489, + "step": 2673 + }, + { + "epoch": 0.28, + "learning_rate": 1.8080693115431277e-05, + "loss": 1.4416, + "step": 2674 + }, + { + "epoch": 0.28, + "learning_rate": 1.8078536366895853e-05, + "loss": 1.422, + "step": 2675 + }, + { + "epoch": 0.28, + "learning_rate": 1.8076378536044128e-05, + "loss": 1.4039, + "step": 2676 + }, + { + "epoch": 0.28, + "learning_rate": 1.8074219623165195e-05, + "loss": 1.4705, + "step": 2677 + }, + { + "epoch": 0.28, + "learning_rate": 1.807205962854829e-05, + "loss": 1.5031, + "step": 2678 + }, + { + "epoch": 0.28, + "learning_rate": 1.8069898552482806e-05, + "loss": 1.4812, + "step": 2679 + }, + { + "epoch": 0.28, + "learning_rate": 1.806773639525826e-05, + "loss": 1.4129, + "step": 2680 + }, + { + "epoch": 0.28, + "learning_rate": 1.8065573157164332e-05, + "loss": 1.4559, + "step": 2681 + }, + { + "epoch": 0.28, + "learning_rate": 1.806340883849084e-05, + "loss": 1.3878, + "step": 2682 + }, + { + "epoch": 0.28, + "learning_rate": 1.8061243439527744e-05, + "loss": 1.4752, + "step": 2683 + }, + { + "epoch": 0.28, + "learning_rate": 1.8059076960565156e-05, + "loss": 1.4089, + "step": 2684 + }, + { + "epoch": 0.28, + "learning_rate": 1.8056909401893326e-05, + "loss": 1.4736, + "step": 2685 + }, + { + "epoch": 0.28, + "learning_rate": 1.8054740763802654e-05, + "loss": 1.3796, + "step": 2686 + }, + { + "epoch": 0.28, + "learning_rate": 1.805257104658368e-05, + "loss": 1.4412, + "step": 2687 + }, + { + "epoch": 0.28, + "learning_rate": 1.8050400250527086e-05, + "loss": 1.4639, + "step": 2688 + }, + { + "epoch": 0.28, + "learning_rate": 1.804822837592371e-05, + "loss": 1.4076, + "step": 2689 + }, + { + "epoch": 0.28, + "learning_rate": 1.804605542306452e-05, + "loss": 1.4627, + "step": 2690 + }, + { + "epoch": 0.28, + "learning_rate": 1.8043881392240642e-05, + "loss": 1.5249, + "step": 2691 + }, + { + "epoch": 0.28, + "learning_rate": 1.804170628374334e-05, + "loss": 1.4312, + "step": 2692 + }, + { + "epoch": 0.28, + "learning_rate": 1.803953009786402e-05, + "loss": 1.5676, + "step": 2693 + }, + { + "epoch": 0.28, + "learning_rate": 1.8037352834894233e-05, + "loss": 1.5072, + "step": 2694 + }, + { + "epoch": 0.28, + "learning_rate": 1.803517449512568e-05, + "loss": 1.5662, + "step": 2695 + }, + { + "epoch": 0.28, + "learning_rate": 1.8032995078850207e-05, + "loss": 1.4771, + "step": 2696 + }, + { + "epoch": 0.28, + "learning_rate": 1.803081458635979e-05, + "loss": 1.412, + "step": 2697 + }, + { + "epoch": 0.28, + "learning_rate": 1.8028633017946564e-05, + "loss": 1.497, + "step": 2698 + }, + { + "epoch": 0.28, + "learning_rate": 1.8026450373902804e-05, + "loss": 1.4528, + "step": 2699 + }, + { + "epoch": 0.28, + "learning_rate": 1.802426665452093e-05, + "loss": 1.4785, + "step": 2700 + }, + { + "epoch": 0.28, + "learning_rate": 1.8022081860093493e-05, + "loss": 1.6411, + "step": 2701 + }, + { + "epoch": 0.28, + "learning_rate": 1.8019895990913213e-05, + "loss": 1.4459, + "step": 2702 + }, + { + "epoch": 0.28, + "learning_rate": 1.8017709047272932e-05, + "loss": 1.4418, + "step": 2703 + }, + { + "epoch": 0.28, + "learning_rate": 1.801552102946565e-05, + "loss": 1.4409, + "step": 2704 + }, + { + "epoch": 0.28, + "learning_rate": 1.8013331937784498e-05, + "loss": 1.4651, + "step": 2705 + }, + { + "epoch": 0.28, + "learning_rate": 1.8011141772522766e-05, + "loss": 1.4161, + "step": 2706 + }, + { + "epoch": 0.28, + "learning_rate": 1.8008950533973876e-05, + "loss": 1.458, + "step": 2707 + }, + { + "epoch": 0.28, + "learning_rate": 1.8006758222431398e-05, + "loss": 1.4477, + "step": 2708 + }, + { + "epoch": 0.28, + "learning_rate": 1.800456483818904e-05, + "loss": 1.4433, + "step": 2709 + }, + { + "epoch": 0.28, + "learning_rate": 1.8002370381540672e-05, + "loss": 1.5005, + "step": 2710 + }, + { + "epoch": 0.28, + "learning_rate": 1.8000174852780282e-05, + "loss": 1.4945, + "step": 2711 + }, + { + "epoch": 0.28, + "learning_rate": 1.7997978252202023e-05, + "loss": 1.4298, + "step": 2712 + }, + { + "epoch": 0.28, + "learning_rate": 1.7995780580100177e-05, + "loss": 1.3812, + "step": 2713 + }, + { + "epoch": 0.28, + "learning_rate": 1.799358183676918e-05, + "loss": 1.5559, + "step": 2714 + }, + { + "epoch": 0.28, + "learning_rate": 1.79913820225036e-05, + "loss": 1.4316, + "step": 2715 + }, + { + "epoch": 0.28, + "learning_rate": 1.798918113759817e-05, + "loss": 1.419, + "step": 2716 + }, + { + "epoch": 0.28, + "learning_rate": 1.7986979182347733e-05, + "loss": 1.43, + "step": 2717 + }, + { + "epoch": 0.29, + "learning_rate": 1.798477615704731e-05, + "loss": 1.4964, + "step": 2718 + }, + { + "epoch": 0.29, + "learning_rate": 1.7982572061992044e-05, + "loss": 1.4417, + "step": 2719 + }, + { + "epoch": 0.29, + "learning_rate": 1.7980366897477227e-05, + "loss": 1.4562, + "step": 2720 + }, + { + "epoch": 0.29, + "learning_rate": 1.7978160663798295e-05, + "loss": 1.4386, + "step": 2721 + }, + { + "epoch": 0.29, + "learning_rate": 1.7975953361250824e-05, + "loss": 1.445, + "step": 2722 + }, + { + "epoch": 0.29, + "learning_rate": 1.797374499013054e-05, + "loss": 1.4549, + "step": 2723 + }, + { + "epoch": 0.29, + "learning_rate": 1.7971535550733305e-05, + "loss": 1.5205, + "step": 2724 + }, + { + "epoch": 0.29, + "learning_rate": 1.796932504335513e-05, + "loss": 1.4632, + "step": 2725 + }, + { + "epoch": 0.29, + "learning_rate": 1.796711346829216e-05, + "loss": 1.3767, + "step": 2726 + }, + { + "epoch": 0.29, + "learning_rate": 1.79649008258407e-05, + "loss": 1.4098, + "step": 2727 + }, + { + "epoch": 0.29, + "learning_rate": 1.7962687116297178e-05, + "loss": 1.4675, + "step": 2728 + }, + { + "epoch": 0.29, + "learning_rate": 1.7960472339958176e-05, + "loss": 1.6048, + "step": 2729 + }, + { + "epoch": 0.29, + "learning_rate": 1.7958256497120418e-05, + "loss": 1.5432, + "step": 2730 + }, + { + "epoch": 0.29, + "learning_rate": 1.7956039588080774e-05, + "loss": 1.5453, + "step": 2731 + }, + { + "epoch": 0.29, + "learning_rate": 1.7953821613136246e-05, + "loss": 1.4246, + "step": 2732 + }, + { + "epoch": 0.29, + "learning_rate": 1.7951602572583988e-05, + "loss": 1.3987, + "step": 2733 + }, + { + "epoch": 0.29, + "learning_rate": 1.7949382466721295e-05, + "loss": 1.4943, + "step": 2734 + }, + { + "epoch": 0.29, + "learning_rate": 1.7947161295845606e-05, + "loss": 1.4385, + "step": 2735 + }, + { + "epoch": 0.29, + "learning_rate": 1.7944939060254497e-05, + "loss": 1.4165, + "step": 2736 + }, + { + "epoch": 0.29, + "learning_rate": 1.7942715760245692e-05, + "loss": 1.4004, + "step": 2737 + }, + { + "epoch": 0.29, + "learning_rate": 1.7940491396117063e-05, + "loss": 1.4577, + "step": 2738 + }, + { + "epoch": 0.29, + "learning_rate": 1.7938265968166602e-05, + "loss": 1.4649, + "step": 2739 + }, + { + "epoch": 0.29, + "learning_rate": 1.7936039476692473e-05, + "loss": 1.5273, + "step": 2740 + }, + { + "epoch": 0.29, + "learning_rate": 1.7933811921992962e-05, + "loss": 1.4325, + "step": 2741 + }, + { + "epoch": 0.29, + "learning_rate": 1.793158330436651e-05, + "loss": 1.4388, + "step": 2742 + }, + { + "epoch": 0.29, + "learning_rate": 1.7929353624111687e-05, + "loss": 1.4124, + "step": 2743 + }, + { + "epoch": 0.29, + "learning_rate": 1.7927122881527222e-05, + "loss": 1.5449, + "step": 2744 + }, + { + "epoch": 0.29, + "learning_rate": 1.7924891076911964e-05, + "loss": 1.4728, + "step": 2745 + }, + { + "epoch": 0.29, + "learning_rate": 1.7922658210564932e-05, + "loss": 1.5103, + "step": 2746 + }, + { + "epoch": 0.29, + "learning_rate": 1.792042428278526e-05, + "loss": 1.5975, + "step": 2747 + }, + { + "epoch": 0.29, + "learning_rate": 1.7918189293872247e-05, + "loss": 1.567, + "step": 2748 + }, + { + "epoch": 0.29, + "learning_rate": 1.7915953244125318e-05, + "loss": 1.57, + "step": 2749 + }, + { + "epoch": 0.29, + "learning_rate": 1.791371613384405e-05, + "loss": 1.4372, + "step": 2750 + }, + { + "epoch": 0.29, + "learning_rate": 1.7911477963328155e-05, + "loss": 1.4053, + "step": 2751 + }, + { + "epoch": 0.29, + "learning_rate": 1.7909238732877492e-05, + "loss": 1.3782, + "step": 2752 + }, + { + "epoch": 0.29, + "learning_rate": 1.790699844279206e-05, + "loss": 1.4401, + "step": 2753 + }, + { + "epoch": 0.29, + "learning_rate": 1.7904757093372e-05, + "loss": 1.3749, + "step": 2754 + }, + { + "epoch": 0.29, + "learning_rate": 1.79025146849176e-05, + "loss": 1.4909, + "step": 2755 + }, + { + "epoch": 0.29, + "learning_rate": 1.7900271217729273e-05, + "loss": 1.4103, + "step": 2756 + }, + { + "epoch": 0.29, + "learning_rate": 1.7898026692107597e-05, + "loss": 1.4986, + "step": 2757 + }, + { + "epoch": 0.29, + "learning_rate": 1.7895781108353278e-05, + "loss": 1.5449, + "step": 2758 + }, + { + "epoch": 0.29, + "learning_rate": 1.789353446676717e-05, + "loss": 1.5583, + "step": 2759 + }, + { + "epoch": 0.29, + "learning_rate": 1.7891286767650254e-05, + "loss": 1.5342, + "step": 2760 + }, + { + "epoch": 0.29, + "learning_rate": 1.7889038011303673e-05, + "loss": 1.4233, + "step": 2761 + }, + { + "epoch": 0.29, + "learning_rate": 1.7886788198028707e-05, + "loss": 1.3433, + "step": 2762 + }, + { + "epoch": 0.29, + "learning_rate": 1.788453732812676e-05, + "loss": 1.4451, + "step": 2763 + }, + { + "epoch": 0.29, + "learning_rate": 1.78822854018994e-05, + "loss": 1.4506, + "step": 2764 + }, + { + "epoch": 0.29, + "learning_rate": 1.7880032419648324e-05, + "loss": 1.4386, + "step": 2765 + }, + { + "epoch": 0.29, + "learning_rate": 1.7877778381675374e-05, + "loss": 1.4512, + "step": 2766 + }, + { + "epoch": 0.29, + "learning_rate": 1.7875523288282535e-05, + "loss": 1.4319, + "step": 2767 + }, + { + "epoch": 0.29, + "learning_rate": 1.7873267139771932e-05, + "loss": 1.4753, + "step": 2768 + }, + { + "epoch": 0.29, + "learning_rate": 1.787100993644583e-05, + "loss": 1.4044, + "step": 2769 + }, + { + "epoch": 0.29, + "learning_rate": 1.786875167860663e-05, + "loss": 1.4382, + "step": 2770 + }, + { + "epoch": 0.29, + "learning_rate": 1.786649236655689e-05, + "loss": 1.3977, + "step": 2771 + }, + { + "epoch": 0.29, + "learning_rate": 1.7864232000599298e-05, + "loss": 1.4473, + "step": 2772 + }, + { + "epoch": 0.29, + "learning_rate": 1.7861970581036678e-05, + "loss": 1.4666, + "step": 2773 + }, + { + "epoch": 0.29, + "learning_rate": 1.785970810817201e-05, + "loss": 1.5299, + "step": 2774 + }, + { + "epoch": 0.29, + "learning_rate": 1.7857444582308402e-05, + "loss": 1.3974, + "step": 2775 + }, + { + "epoch": 0.29, + "learning_rate": 1.7855180003749114e-05, + "loss": 1.4603, + "step": 2776 + }, + { + "epoch": 0.29, + "learning_rate": 1.7852914372797535e-05, + "loss": 1.463, + "step": 2777 + }, + { + "epoch": 0.29, + "learning_rate": 1.7850647689757205e-05, + "loss": 1.5317, + "step": 2778 + }, + { + "epoch": 0.29, + "learning_rate": 1.78483799549318e-05, + "loss": 1.4669, + "step": 2779 + }, + { + "epoch": 0.29, + "learning_rate": 1.784611116862514e-05, + "loss": 1.5293, + "step": 2780 + }, + { + "epoch": 0.29, + "learning_rate": 1.7843841331141177e-05, + "loss": 1.5802, + "step": 2781 + }, + { + "epoch": 0.29, + "learning_rate": 1.7841570442784024e-05, + "loss": 1.4486, + "step": 2782 + }, + { + "epoch": 0.29, + "learning_rate": 1.7839298503857913e-05, + "loss": 1.4674, + "step": 2783 + }, + { + "epoch": 0.29, + "learning_rate": 1.7837025514667224e-05, + "loss": 1.4662, + "step": 2784 + }, + { + "epoch": 0.29, + "learning_rate": 1.7834751475516484e-05, + "loss": 1.3555, + "step": 2785 + }, + { + "epoch": 0.29, + "learning_rate": 1.783247638671035e-05, + "loss": 1.4307, + "step": 2786 + }, + { + "epoch": 0.29, + "eval_loss": 1.500258445739746, + "eval_runtime": 77.406, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 2786 + }, + { + "epoch": 0.29, + "learning_rate": 1.7830200248553633e-05, + "loss": 1.4596, + "step": 2787 + }, + { + "epoch": 0.29, + "learning_rate": 1.7827923061351273e-05, + "loss": 1.6118, + "step": 2788 + }, + { + "epoch": 0.29, + "learning_rate": 1.7825644825408353e-05, + "loss": 1.4782, + "step": 2789 + }, + { + "epoch": 0.29, + "learning_rate": 1.78233655410301e-05, + "loss": 1.4681, + "step": 2790 + }, + { + "epoch": 0.29, + "learning_rate": 1.782108520852188e-05, + "loss": 1.6281, + "step": 2791 + }, + { + "epoch": 0.29, + "learning_rate": 1.78188038281892e-05, + "loss": 1.4446, + "step": 2792 + }, + { + "epoch": 0.29, + "learning_rate": 1.7816521400337704e-05, + "loss": 1.479, + "step": 2793 + }, + { + "epoch": 0.29, + "learning_rate": 1.7814237925273178e-05, + "loss": 1.5457, + "step": 2794 + }, + { + "epoch": 0.29, + "learning_rate": 1.7811953403301547e-05, + "loss": 1.3928, + "step": 2795 + }, + { + "epoch": 0.29, + "learning_rate": 1.780966783472889e-05, + "loss": 1.4321, + "step": 2796 + }, + { + "epoch": 0.29, + "learning_rate": 1.78073812198614e-05, + "loss": 1.5734, + "step": 2797 + }, + { + "epoch": 0.29, + "learning_rate": 1.7805093559005432e-05, + "loss": 1.4356, + "step": 2798 + }, + { + "epoch": 0.29, + "learning_rate": 1.7802804852467473e-05, + "loss": 1.4656, + "step": 2799 + }, + { + "epoch": 0.29, + "learning_rate": 1.780051510055415e-05, + "loss": 1.4052, + "step": 2800 + }, + { + "epoch": 0.29, + "learning_rate": 1.7798224303572228e-05, + "loss": 1.4758, + "step": 2801 + }, + { + "epoch": 0.29, + "learning_rate": 1.7795932461828622e-05, + "loss": 1.4326, + "step": 2802 + }, + { + "epoch": 0.29, + "learning_rate": 1.7793639575630376e-05, + "loss": 1.3409, + "step": 2803 + }, + { + "epoch": 0.29, + "learning_rate": 1.7791345645284678e-05, + "loss": 1.4175, + "step": 2804 + }, + { + "epoch": 0.29, + "learning_rate": 1.7789050671098853e-05, + "loss": 1.383, + "step": 2805 + }, + { + "epoch": 0.29, + "learning_rate": 1.7786754653380373e-05, + "loss": 1.5162, + "step": 2806 + }, + { + "epoch": 0.29, + "learning_rate": 1.7784457592436847e-05, + "loss": 1.4899, + "step": 2807 + }, + { + "epoch": 0.29, + "learning_rate": 1.7782159488576016e-05, + "loss": 1.4874, + "step": 2808 + }, + { + "epoch": 0.29, + "learning_rate": 1.777986034210577e-05, + "loss": 1.4363, + "step": 2809 + }, + { + "epoch": 0.29, + "learning_rate": 1.7777560153334134e-05, + "loss": 1.4223, + "step": 2810 + }, + { + "epoch": 0.29, + "learning_rate": 1.7775258922569273e-05, + "loss": 1.4792, + "step": 2811 + }, + { + "epoch": 0.29, + "learning_rate": 1.77729566501195e-05, + "loss": 1.4475, + "step": 2812 + }, + { + "epoch": 0.29, + "learning_rate": 1.7770653336293253e-05, + "loss": 1.5157, + "step": 2813 + }, + { + "epoch": 0.3, + "learning_rate": 1.776834898139912e-05, + "loss": 1.389, + "step": 2814 + }, + { + "epoch": 0.3, + "learning_rate": 1.7766043585745824e-05, + "loss": 1.4358, + "step": 2815 + }, + { + "epoch": 0.3, + "learning_rate": 1.776373714964223e-05, + "loss": 1.4297, + "step": 2816 + }, + { + "epoch": 0.3, + "learning_rate": 1.7761429673397344e-05, + "loss": 1.4102, + "step": 2817 + }, + { + "epoch": 0.3, + "learning_rate": 1.77591211573203e-05, + "loss": 1.4572, + "step": 2818 + }, + { + "epoch": 0.3, + "learning_rate": 1.775681160172039e-05, + "loss": 1.448, + "step": 2819 + }, + { + "epoch": 0.3, + "learning_rate": 1.7754501006907025e-05, + "loss": 1.4426, + "step": 2820 + }, + { + "epoch": 0.3, + "learning_rate": 1.7752189373189773e-05, + "loss": 1.4566, + "step": 2821 + }, + { + "epoch": 0.3, + "learning_rate": 1.7749876700878332e-05, + "loss": 1.4267, + "step": 2822 + }, + { + "epoch": 0.3, + "learning_rate": 1.7747562990282538e-05, + "loss": 1.3951, + "step": 2823 + }, + { + "epoch": 0.3, + "learning_rate": 1.7745248241712373e-05, + "loss": 1.4668, + "step": 2824 + }, + { + "epoch": 0.3, + "learning_rate": 1.774293245547795e-05, + "loss": 1.4924, + "step": 2825 + }, + { + "epoch": 0.3, + "learning_rate": 1.7740615631889525e-05, + "loss": 1.5258, + "step": 2826 + }, + { + "epoch": 0.3, + "learning_rate": 1.7738297771257496e-05, + "loss": 1.4323, + "step": 2827 + }, + { + "epoch": 0.3, + "learning_rate": 1.7735978873892393e-05, + "loss": 1.439, + "step": 2828 + }, + { + "epoch": 0.3, + "learning_rate": 1.773365894010489e-05, + "loss": 1.5658, + "step": 2829 + }, + { + "epoch": 0.3, + "learning_rate": 1.77313379702058e-05, + "loss": 1.4607, + "step": 2830 + }, + { + "epoch": 0.3, + "learning_rate": 1.7729015964506073e-05, + "loss": 1.5544, + "step": 2831 + }, + { + "epoch": 0.3, + "learning_rate": 1.7726692923316798e-05, + "loss": 1.4232, + "step": 2832 + }, + { + "epoch": 0.3, + "learning_rate": 1.77243688469492e-05, + "loss": 1.415, + "step": 2833 + }, + { + "epoch": 0.3, + "learning_rate": 1.772204373571465e-05, + "loss": 1.4658, + "step": 2834 + }, + { + "epoch": 0.3, + "learning_rate": 1.7719717589924647e-05, + "loss": 1.4678, + "step": 2835 + }, + { + "epoch": 0.3, + "learning_rate": 1.771739040989084e-05, + "loss": 1.3021, + "step": 2836 + }, + { + "epoch": 0.3, + "learning_rate": 1.771506219592501e-05, + "loss": 1.4045, + "step": 2837 + }, + { + "epoch": 0.3, + "learning_rate": 1.7712732948339085e-05, + "loss": 1.4593, + "step": 2838 + }, + { + "epoch": 0.3, + "learning_rate": 1.7710402667445108e-05, + "loss": 1.4175, + "step": 2839 + }, + { + "epoch": 0.3, + "learning_rate": 1.770807135355529e-05, + "loss": 1.3939, + "step": 2840 + }, + { + "epoch": 0.3, + "learning_rate": 1.7705739006981963e-05, + "loss": 1.6089, + "step": 2841 + }, + { + "epoch": 0.3, + "learning_rate": 1.77034056280376e-05, + "loss": 1.3952, + "step": 2842 + }, + { + "epoch": 0.3, + "learning_rate": 1.7701071217034818e-05, + "loss": 1.5086, + "step": 2843 + }, + { + "epoch": 0.3, + "learning_rate": 1.7698735774286362e-05, + "loss": 1.4706, + "step": 2844 + }, + { + "epoch": 0.3, + "learning_rate": 1.7696399300105128e-05, + "loss": 1.4286, + "step": 2845 + }, + { + "epoch": 0.3, + "learning_rate": 1.7694061794804137e-05, + "loss": 1.4418, + "step": 2846 + }, + { + "epoch": 0.3, + "learning_rate": 1.7691723258696562e-05, + "loss": 1.516, + "step": 2847 + }, + { + "epoch": 0.3, + "learning_rate": 1.76893836920957e-05, + "loss": 1.4354, + "step": 2848 + }, + { + "epoch": 0.3, + "learning_rate": 1.7687043095314998e-05, + "loss": 1.7503, + "step": 2849 + }, + { + "epoch": 0.3, + "learning_rate": 1.7684701468668032e-05, + "loss": 1.5985, + "step": 2850 + }, + { + "epoch": 0.3, + "learning_rate": 1.768235881246852e-05, + "loss": 1.442, + "step": 2851 + }, + { + "epoch": 0.3, + "learning_rate": 1.7680015127030322e-05, + "loss": 1.4924, + "step": 2852 + }, + { + "epoch": 0.3, + "learning_rate": 1.7677670412667425e-05, + "loss": 1.4461, + "step": 2853 + }, + { + "epoch": 0.3, + "learning_rate": 1.7675324669693968e-05, + "loss": 1.3823, + "step": 2854 + }, + { + "epoch": 0.3, + "learning_rate": 1.767297789842421e-05, + "loss": 1.452, + "step": 2855 + }, + { + "epoch": 0.3, + "learning_rate": 1.767063009917257e-05, + "loss": 1.46, + "step": 2856 + }, + { + "epoch": 0.3, + "learning_rate": 1.7668281272253587e-05, + "loss": 1.4129, + "step": 2857 + }, + { + "epoch": 0.3, + "learning_rate": 1.766593141798194e-05, + "loss": 1.4057, + "step": 2858 + }, + { + "epoch": 0.3, + "learning_rate": 1.7663580536672456e-05, + "loss": 1.5162, + "step": 2859 + }, + { + "epoch": 0.3, + "learning_rate": 1.7661228628640087e-05, + "loss": 1.5177, + "step": 2860 + }, + { + "epoch": 0.3, + "learning_rate": 1.7658875694199933e-05, + "loss": 1.4548, + "step": 2861 + }, + { + "epoch": 0.3, + "learning_rate": 1.7656521733667223e-05, + "loss": 1.4511, + "step": 2862 + }, + { + "epoch": 0.3, + "learning_rate": 1.765416674735733e-05, + "loss": 1.4778, + "step": 2863 + }, + { + "epoch": 0.3, + "learning_rate": 1.765181073558576e-05, + "loss": 1.3935, + "step": 2864 + }, + { + "epoch": 0.3, + "learning_rate": 1.7649453698668156e-05, + "loss": 1.4659, + "step": 2865 + }, + { + "epoch": 0.3, + "learning_rate": 1.7647095636920305e-05, + "loss": 1.7042, + "step": 2866 + }, + { + "epoch": 0.3, + "learning_rate": 1.7644736550658124e-05, + "loss": 1.7957, + "step": 2867 + }, + { + "epoch": 0.3, + "learning_rate": 1.764237644019767e-05, + "loss": 1.5139, + "step": 2868 + }, + { + "epoch": 0.3, + "learning_rate": 1.764001530585514e-05, + "loss": 1.4117, + "step": 2869 + }, + { + "epoch": 0.3, + "learning_rate": 1.7637653147946858e-05, + "loss": 1.4837, + "step": 2870 + }, + { + "epoch": 0.3, + "learning_rate": 1.7635289966789298e-05, + "loss": 1.4379, + "step": 2871 + }, + { + "epoch": 0.3, + "learning_rate": 1.7632925762699068e-05, + "loss": 1.4491, + "step": 2872 + }, + { + "epoch": 0.3, + "learning_rate": 1.7630560535992905e-05, + "loss": 1.4006, + "step": 2873 + }, + { + "epoch": 0.3, + "learning_rate": 1.7628194286987694e-05, + "loss": 1.5484, + "step": 2874 + }, + { + "epoch": 0.3, + "learning_rate": 1.7625827016000446e-05, + "loss": 1.4926, + "step": 2875 + }, + { + "epoch": 0.3, + "learning_rate": 1.762345872334832e-05, + "loss": 1.3909, + "step": 2876 + }, + { + "epoch": 0.3, + "learning_rate": 1.76210894093486e-05, + "loss": 1.405, + "step": 2877 + }, + { + "epoch": 0.3, + "learning_rate": 1.7618719074318718e-05, + "loss": 1.4736, + "step": 2878 + }, + { + "epoch": 0.3, + "learning_rate": 1.7616347718576238e-05, + "loss": 1.4445, + "step": 2879 + }, + { + "epoch": 0.3, + "learning_rate": 1.761397534243886e-05, + "loss": 1.4878, + "step": 2880 + }, + { + "epoch": 0.3, + "learning_rate": 1.7611601946224417e-05, + "loss": 1.4414, + "step": 2881 + }, + { + "epoch": 0.3, + "learning_rate": 1.760922753025089e-05, + "loss": 1.5657, + "step": 2882 + }, + { + "epoch": 0.3, + "learning_rate": 1.7606852094836385e-05, + "loss": 1.5008, + "step": 2883 + }, + { + "epoch": 0.3, + "learning_rate": 1.7604475640299153e-05, + "loss": 1.4922, + "step": 2884 + }, + { + "epoch": 0.3, + "learning_rate": 1.7602098166957577e-05, + "loss": 1.7451, + "step": 2885 + }, + { + "epoch": 0.3, + "learning_rate": 1.759971967513017e-05, + "loss": 1.7077, + "step": 2886 + }, + { + "epoch": 0.3, + "learning_rate": 1.75973401651356e-05, + "loss": 1.3986, + "step": 2887 + }, + { + "epoch": 0.3, + "learning_rate": 1.7594959637292656e-05, + "loss": 1.3966, + "step": 2888 + }, + { + "epoch": 0.3, + "learning_rate": 1.7592578091920264e-05, + "loss": 1.4086, + "step": 2889 + }, + { + "epoch": 0.3, + "learning_rate": 1.7590195529337495e-05, + "loss": 1.4481, + "step": 2890 + }, + { + "epoch": 0.3, + "learning_rate": 1.7587811949863548e-05, + "loss": 1.3974, + "step": 2891 + }, + { + "epoch": 0.3, + "learning_rate": 1.7585427353817758e-05, + "loss": 1.5013, + "step": 2892 + }, + { + "epoch": 0.3, + "learning_rate": 1.7583041741519608e-05, + "loss": 1.5454, + "step": 2893 + }, + { + "epoch": 0.3, + "learning_rate": 1.7580655113288708e-05, + "loss": 1.5033, + "step": 2894 + }, + { + "epoch": 0.3, + "learning_rate": 1.7578267469444793e-05, + "loss": 1.4332, + "step": 2895 + }, + { + "epoch": 0.3, + "learning_rate": 1.757587881030776e-05, + "loss": 1.4667, + "step": 2896 + }, + { + "epoch": 0.3, + "learning_rate": 1.7573489136197623e-05, + "loss": 1.4314, + "step": 2897 + }, + { + "epoch": 0.3, + "learning_rate": 1.7571098447434532e-05, + "loss": 1.4514, + "step": 2898 + }, + { + "epoch": 0.3, + "learning_rate": 1.7568706744338784e-05, + "loss": 1.4872, + "step": 2899 + }, + { + "epoch": 0.3, + "learning_rate": 1.7566314027230808e-05, + "loss": 1.4841, + "step": 2900 + }, + { + "epoch": 0.3, + "learning_rate": 1.7563920296431158e-05, + "loss": 1.3964, + "step": 2901 + }, + { + "epoch": 0.3, + "learning_rate": 1.7561525552260538e-05, + "loss": 1.4932, + "step": 2902 + }, + { + "epoch": 0.3, + "learning_rate": 1.755912979503978e-05, + "loss": 1.4153, + "step": 2903 + }, + { + "epoch": 0.3, + "learning_rate": 1.755673302508986e-05, + "loss": 1.4939, + "step": 2904 + }, + { + "epoch": 0.3, + "learning_rate": 1.755433524273187e-05, + "loss": 1.4437, + "step": 2905 + }, + { + "epoch": 0.3, + "learning_rate": 1.7551936448287067e-05, + "loss": 1.486, + "step": 2906 + }, + { + "epoch": 0.3, + "learning_rate": 1.754953664207682e-05, + "loss": 1.4362, + "step": 2907 + }, + { + "epoch": 0.3, + "learning_rate": 1.7547135824422635e-05, + "loss": 1.4954, + "step": 2908 + }, + { + "epoch": 0.31, + "learning_rate": 1.7544733995646174e-05, + "loss": 1.4552, + "step": 2909 + }, + { + "epoch": 0.31, + "learning_rate": 1.7542331156069213e-05, + "loss": 1.4654, + "step": 2910 + }, + { + "epoch": 0.31, + "learning_rate": 1.753992730601367e-05, + "loss": 1.4531, + "step": 2911 + }, + { + "epoch": 0.31, + "learning_rate": 1.75375224458016e-05, + "loss": 1.4949, + "step": 2912 + }, + { + "epoch": 0.31, + "learning_rate": 1.753511657575519e-05, + "loss": 1.3998, + "step": 2913 + }, + { + "epoch": 0.31, + "learning_rate": 1.753270969619677e-05, + "loss": 1.3904, + "step": 2914 + }, + { + "epoch": 0.31, + "learning_rate": 1.7530301807448794e-05, + "loss": 1.481, + "step": 2915 + }, + { + "epoch": 0.31, + "learning_rate": 1.7527892909833864e-05, + "loss": 1.4301, + "step": 2916 + }, + { + "epoch": 0.31, + "learning_rate": 1.7525483003674707e-05, + "loss": 1.4377, + "step": 2917 + }, + { + "epoch": 0.31, + "learning_rate": 1.7523072089294188e-05, + "loss": 1.5077, + "step": 2918 + }, + { + "epoch": 0.31, + "learning_rate": 1.752066016701531e-05, + "loss": 1.3802, + "step": 2919 + }, + { + "epoch": 0.31, + "learning_rate": 1.7518247237161205e-05, + "loss": 1.3991, + "step": 2920 + }, + { + "epoch": 0.31, + "learning_rate": 1.7515833300055146e-05, + "loss": 1.4283, + "step": 2921 + }, + { + "epoch": 0.31, + "learning_rate": 1.7513418356020535e-05, + "loss": 1.3688, + "step": 2922 + }, + { + "epoch": 0.31, + "learning_rate": 1.751100240538092e-05, + "loss": 1.4336, + "step": 2923 + }, + { + "epoch": 0.31, + "learning_rate": 1.7508585448459967e-05, + "loss": 1.4302, + "step": 2924 + }, + { + "epoch": 0.31, + "learning_rate": 1.7506167485581493e-05, + "loss": 1.4293, + "step": 2925 + }, + { + "epoch": 0.31, + "learning_rate": 1.750374851706944e-05, + "loss": 1.4262, + "step": 2926 + }, + { + "epoch": 0.31, + "learning_rate": 1.7501328543247892e-05, + "loss": 1.4128, + "step": 2927 + }, + { + "epoch": 0.31, + "learning_rate": 1.7498907564441054e-05, + "loss": 1.4258, + "step": 2928 + }, + { + "epoch": 0.31, + "learning_rate": 1.749648558097328e-05, + "loss": 1.4904, + "step": 2929 + }, + { + "epoch": 0.31, + "learning_rate": 1.749406259316906e-05, + "loss": 1.4628, + "step": 2930 + }, + { + "epoch": 0.31, + "learning_rate": 1.7491638601353004e-05, + "loss": 1.4908, + "step": 2931 + }, + { + "epoch": 0.31, + "learning_rate": 1.7489213605849867e-05, + "loss": 1.4563, + "step": 2932 + }, + { + "epoch": 0.31, + "learning_rate": 1.7486787606984533e-05, + "loss": 1.5006, + "step": 2933 + }, + { + "epoch": 0.31, + "learning_rate": 1.748436060508203e-05, + "loss": 1.424, + "step": 2934 + }, + { + "epoch": 0.31, + "learning_rate": 1.7481932600467508e-05, + "loss": 1.4136, + "step": 2935 + }, + { + "epoch": 0.31, + "learning_rate": 1.747950359346626e-05, + "loss": 1.3835, + "step": 2936 + }, + { + "epoch": 0.31, + "learning_rate": 1.747707358440371e-05, + "loss": 1.5284, + "step": 2937 + }, + { + "epoch": 0.31, + "learning_rate": 1.7474642573605418e-05, + "loss": 1.4592, + "step": 2938 + }, + { + "epoch": 0.31, + "learning_rate": 1.7472210561397075e-05, + "loss": 1.5483, + "step": 2939 + }, + { + "epoch": 0.31, + "learning_rate": 1.746977754810451e-05, + "loss": 1.521, + "step": 2940 + }, + { + "epoch": 0.31, + "learning_rate": 1.7467343534053683e-05, + "loss": 1.4276, + "step": 2941 + }, + { + "epoch": 0.31, + "learning_rate": 1.746490851957069e-05, + "loss": 1.4302, + "step": 2942 + }, + { + "epoch": 0.31, + "learning_rate": 1.746247250498176e-05, + "loss": 1.4439, + "step": 2943 + }, + { + "epoch": 0.31, + "learning_rate": 1.7460035490613255e-05, + "loss": 1.4991, + "step": 2944 + }, + { + "epoch": 0.31, + "learning_rate": 1.7457597476791674e-05, + "loss": 1.4188, + "step": 2945 + }, + { + "epoch": 0.31, + "learning_rate": 1.7455158463843648e-05, + "loss": 1.4685, + "step": 2946 + }, + { + "epoch": 0.31, + "learning_rate": 1.745271845209594e-05, + "loss": 1.3811, + "step": 2947 + }, + { + "epoch": 0.31, + "learning_rate": 1.7450277441875454e-05, + "loss": 1.4869, + "step": 2948 + }, + { + "epoch": 0.31, + "learning_rate": 1.7447835433509218e-05, + "loss": 1.5001, + "step": 2949 + }, + { + "epoch": 0.31, + "learning_rate": 1.74453924273244e-05, + "loss": 1.4757, + "step": 2950 + }, + { + "epoch": 0.31, + "learning_rate": 1.74429484236483e-05, + "loss": 1.5072, + "step": 2951 + }, + { + "epoch": 0.31, + "learning_rate": 1.744050342280835e-05, + "loss": 1.4242, + "step": 2952 + }, + { + "epoch": 0.31, + "learning_rate": 1.743805742513212e-05, + "loss": 1.4462, + "step": 2953 + }, + { + "epoch": 0.31, + "learning_rate": 1.743561043094731e-05, + "loss": 1.6815, + "step": 2954 + }, + { + "epoch": 0.31, + "learning_rate": 1.7433162440581755e-05, + "loss": 1.427, + "step": 2955 + }, + { + "epoch": 0.31, + "learning_rate": 1.7430713454363423e-05, + "loss": 1.2933, + "step": 2956 + }, + { + "epoch": 0.31, + "learning_rate": 1.742826347262041e-05, + "loss": 1.4247, + "step": 2957 + }, + { + "epoch": 0.31, + "learning_rate": 1.7425812495680955e-05, + "loss": 1.399, + "step": 2958 + }, + { + "epoch": 0.31, + "learning_rate": 1.742336052387343e-05, + "loss": 1.4818, + "step": 2959 + }, + { + "epoch": 0.31, + "learning_rate": 1.742090755752633e-05, + "loss": 1.3839, + "step": 2960 + }, + { + "epoch": 0.31, + "learning_rate": 1.741845359696829e-05, + "loss": 1.4669, + "step": 2961 + }, + { + "epoch": 0.31, + "learning_rate": 1.741599864252808e-05, + "loss": 1.468, + "step": 2962 + }, + { + "epoch": 0.31, + "learning_rate": 1.74135426945346e-05, + "loss": 1.4135, + "step": 2963 + }, + { + "epoch": 0.31, + "learning_rate": 1.7411085753316882e-05, + "loss": 1.5899, + "step": 2964 + }, + { + "epoch": 0.31, + "learning_rate": 1.74086278192041e-05, + "loss": 1.6115, + "step": 2965 + }, + { + "epoch": 0.31, + "learning_rate": 1.740616889252554e-05, + "loss": 1.3988, + "step": 2966 + }, + { + "epoch": 0.31, + "learning_rate": 1.740370897361065e-05, + "loss": 1.5001, + "step": 2967 + }, + { + "epoch": 0.31, + "learning_rate": 1.740124806278899e-05, + "loss": 1.459, + "step": 2968 + }, + { + "epoch": 0.31, + "learning_rate": 1.7398786160390258e-05, + "loss": 1.4489, + "step": 2969 + }, + { + "epoch": 0.31, + "learning_rate": 1.7396323266744283e-05, + "loss": 1.4397, + "step": 2970 + }, + { + "epoch": 0.31, + "learning_rate": 1.7393859382181033e-05, + "loss": 1.4687, + "step": 2971 + }, + { + "epoch": 0.31, + "learning_rate": 1.7391394507030606e-05, + "loss": 1.4495, + "step": 2972 + }, + { + "epoch": 0.31, + "learning_rate": 1.738892864162323e-05, + "loss": 1.4745, + "step": 2973 + }, + { + "epoch": 0.31, + "learning_rate": 1.7386461786289274e-05, + "loss": 1.3943, + "step": 2974 + }, + { + "epoch": 0.31, + "learning_rate": 1.738399394135922e-05, + "loss": 1.4595, + "step": 2975 + }, + { + "epoch": 0.31, + "learning_rate": 1.738152510716371e-05, + "loss": 1.4023, + "step": 2976 + }, + { + "epoch": 0.31, + "learning_rate": 1.7379055284033493e-05, + "loss": 1.3938, + "step": 2977 + }, + { + "epoch": 0.31, + "learning_rate": 1.7376584472299468e-05, + "loss": 1.4576, + "step": 2978 + }, + { + "epoch": 0.31, + "learning_rate": 1.737411267229266e-05, + "loss": 1.424, + "step": 2979 + }, + { + "epoch": 0.31, + "learning_rate": 1.7371639884344225e-05, + "loss": 1.4224, + "step": 2980 + }, + { + "epoch": 0.31, + "learning_rate": 1.736916610878545e-05, + "loss": 1.4228, + "step": 2981 + }, + { + "epoch": 0.31, + "learning_rate": 1.7366691345947768e-05, + "loss": 1.5021, + "step": 2982 + }, + { + "epoch": 0.31, + "learning_rate": 1.736421559616272e-05, + "loss": 1.3589, + "step": 2983 + }, + { + "epoch": 0.31, + "learning_rate": 1.7361738859762007e-05, + "loss": 1.4748, + "step": 2984 + }, + { + "epoch": 0.31, + "learning_rate": 1.735926113707743e-05, + "loss": 1.3974, + "step": 2985 + }, + { + "epoch": 0.31, + "eval_loss": 1.4849082231521606, + "eval_runtime": 77.3271, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2985 + }, + { + "epoch": 0.31, + "learning_rate": 1.735678242844096e-05, + "loss": 1.392, + "step": 2986 + }, + { + "epoch": 0.31, + "learning_rate": 1.735430273418467e-05, + "loss": 1.4277, + "step": 2987 + }, + { + "epoch": 0.31, + "learning_rate": 1.735182205464077e-05, + "loss": 1.4216, + "step": 2988 + }, + { + "epoch": 0.31, + "learning_rate": 1.7349340390141617e-05, + "loss": 1.4546, + "step": 2989 + }, + { + "epoch": 0.31, + "learning_rate": 1.734685774101969e-05, + "loss": 1.4264, + "step": 2990 + }, + { + "epoch": 0.31, + "learning_rate": 1.7344374107607593e-05, + "loss": 1.4307, + "step": 2991 + }, + { + "epoch": 0.31, + "learning_rate": 1.7341889490238076e-05, + "loss": 1.4266, + "step": 2992 + }, + { + "epoch": 0.31, + "learning_rate": 1.7339403889244008e-05, + "loss": 1.4486, + "step": 2993 + }, + { + "epoch": 0.31, + "learning_rate": 1.7336917304958403e-05, + "loss": 1.4345, + "step": 2994 + }, + { + "epoch": 0.31, + "learning_rate": 1.7334429737714395e-05, + "loss": 1.476, + "step": 2995 + }, + { + "epoch": 0.31, + "learning_rate": 1.7331941187845248e-05, + "loss": 1.5148, + "step": 2996 + }, + { + "epoch": 0.31, + "learning_rate": 1.7329451655684372e-05, + "loss": 1.4026, + "step": 2997 + }, + { + "epoch": 0.31, + "learning_rate": 1.7326961141565303e-05, + "loss": 1.3935, + "step": 2998 + }, + { + "epoch": 0.31, + "learning_rate": 1.73244696458217e-05, + "loss": 1.4483, + "step": 2999 + }, + { + "epoch": 0.31, + "learning_rate": 1.7321977168787356e-05, + "loss": 1.5197, + "step": 3000 + }, + { + "epoch": 0.31, + "learning_rate": 1.7319483710796208e-05, + "loss": 1.4648, + "step": 3001 + }, + { + "epoch": 0.31, + "learning_rate": 1.7316989272182308e-05, + "loss": 1.4171, + "step": 3002 + }, + { + "epoch": 0.31, + "learning_rate": 1.731449385327985e-05, + "loss": 1.4541, + "step": 3003 + }, + { + "epoch": 0.32, + "learning_rate": 1.731199745442316e-05, + "loss": 1.4605, + "step": 3004 + }, + { + "epoch": 0.32, + "learning_rate": 1.7309500075946683e-05, + "loss": 1.5122, + "step": 3005 + }, + { + "epoch": 0.32, + "learning_rate": 1.7307001718185007e-05, + "loss": 1.5243, + "step": 3006 + }, + { + "epoch": 0.32, + "learning_rate": 1.7304502381472844e-05, + "loss": 1.4997, + "step": 3007 + }, + { + "epoch": 0.32, + "learning_rate": 1.730200206614505e-05, + "loss": 1.4891, + "step": 3008 + }, + { + "epoch": 0.32, + "learning_rate": 1.72995007725366e-05, + "loss": 1.4376, + "step": 3009 + }, + { + "epoch": 0.32, + "learning_rate": 1.7296998500982595e-05, + "loss": 1.4403, + "step": 3010 + }, + { + "epoch": 0.32, + "learning_rate": 1.7294495251818285e-05, + "loss": 1.5153, + "step": 3011 + }, + { + "epoch": 0.32, + "learning_rate": 1.729199102537904e-05, + "loss": 1.4996, + "step": 3012 + }, + { + "epoch": 0.32, + "learning_rate": 1.7289485822000356e-05, + "loss": 1.5302, + "step": 3013 + }, + { + "epoch": 0.32, + "learning_rate": 1.7286979642017867e-05, + "loss": 1.5641, + "step": 3014 + }, + { + "epoch": 0.32, + "learning_rate": 1.728447248576734e-05, + "loss": 1.438, + "step": 3015 + }, + { + "epoch": 0.32, + "learning_rate": 1.7281964353584674e-05, + "loss": 1.4796, + "step": 3016 + }, + { + "epoch": 0.32, + "learning_rate": 1.727945524580588e-05, + "loss": 1.4413, + "step": 3017 + }, + { + "epoch": 0.32, + "learning_rate": 1.727694516276713e-05, + "loss": 1.3966, + "step": 3018 + }, + { + "epoch": 0.32, + "learning_rate": 1.72744341048047e-05, + "loss": 1.5267, + "step": 3019 + }, + { + "epoch": 0.32, + "learning_rate": 1.727192207225501e-05, + "loss": 1.4284, + "step": 3020 + }, + { + "epoch": 0.32, + "learning_rate": 1.726940906545461e-05, + "loss": 1.5137, + "step": 3021 + }, + { + "epoch": 0.32, + "learning_rate": 1.7266895084740173e-05, + "loss": 1.3966, + "step": 3022 + }, + { + "epoch": 0.32, + "learning_rate": 1.7264380130448514e-05, + "loss": 1.4156, + "step": 3023 + }, + { + "epoch": 0.32, + "learning_rate": 1.726186420291657e-05, + "loss": 1.4644, + "step": 3024 + }, + { + "epoch": 0.32, + "learning_rate": 1.725934730248141e-05, + "loss": 1.4768, + "step": 3025 + }, + { + "epoch": 0.32, + "learning_rate": 1.7256829429480233e-05, + "loss": 1.4428, + "step": 3026 + }, + { + "epoch": 0.32, + "learning_rate": 1.7254310584250373e-05, + "loss": 1.4495, + "step": 3027 + }, + { + "epoch": 0.32, + "learning_rate": 1.725179076712929e-05, + "loss": 1.3867, + "step": 3028 + }, + { + "epoch": 0.32, + "learning_rate": 1.7249269978454567e-05, + "loss": 1.5011, + "step": 3029 + }, + { + "epoch": 0.32, + "learning_rate": 1.7246748218563937e-05, + "loss": 1.3916, + "step": 3030 + }, + { + "epoch": 0.32, + "learning_rate": 1.7244225487795238e-05, + "loss": 1.4984, + "step": 3031 + }, + { + "epoch": 0.32, + "learning_rate": 1.7241701786486464e-05, + "loss": 1.5776, + "step": 3032 + }, + { + "epoch": 0.32, + "learning_rate": 1.7239177114975717e-05, + "loss": 1.5018, + "step": 3033 + }, + { + "epoch": 0.32, + "learning_rate": 1.7236651473601244e-05, + "loss": 1.5042, + "step": 3034 + }, + { + "epoch": 0.32, + "learning_rate": 1.723412486270141e-05, + "loss": 1.4636, + "step": 3035 + }, + { + "epoch": 0.32, + "learning_rate": 1.723159728261472e-05, + "loss": 1.5612, + "step": 3036 + }, + { + "epoch": 0.32, + "learning_rate": 1.7229068733679803e-05, + "loss": 1.4399, + "step": 3037 + }, + { + "epoch": 0.32, + "learning_rate": 1.7226539216235424e-05, + "loss": 1.5635, + "step": 3038 + }, + { + "epoch": 0.32, + "learning_rate": 1.7224008730620468e-05, + "loss": 1.4329, + "step": 3039 + }, + { + "epoch": 0.32, + "learning_rate": 1.7221477277173956e-05, + "loss": 1.4886, + "step": 3040 + }, + { + "epoch": 0.32, + "learning_rate": 1.721894485623504e-05, + "loss": 1.4741, + "step": 3041 + }, + { + "epoch": 0.32, + "learning_rate": 1.7216411468143e-05, + "loss": 1.4678, + "step": 3042 + }, + { + "epoch": 0.32, + "learning_rate": 1.721387711323724e-05, + "loss": 1.4758, + "step": 3043 + }, + { + "epoch": 0.32, + "learning_rate": 1.72113417918573e-05, + "loss": 1.441, + "step": 3044 + }, + { + "epoch": 0.32, + "learning_rate": 1.7208805504342855e-05, + "loss": 1.4328, + "step": 3045 + }, + { + "epoch": 0.32, + "learning_rate": 1.720626825103369e-05, + "loss": 1.4254, + "step": 3046 + }, + { + "epoch": 0.32, + "learning_rate": 1.7203730032269744e-05, + "loss": 1.4462, + "step": 3047 + }, + { + "epoch": 0.32, + "learning_rate": 1.7201190848391066e-05, + "loss": 1.4826, + "step": 3048 + }, + { + "epoch": 0.32, + "learning_rate": 1.719865069973784e-05, + "loss": 1.4215, + "step": 3049 + }, + { + "epoch": 0.32, + "learning_rate": 1.7196109586650385e-05, + "loss": 1.4291, + "step": 3050 + }, + { + "epoch": 0.32, + "learning_rate": 1.7193567509469146e-05, + "loss": 1.5005, + "step": 3051 + }, + { + "epoch": 0.32, + "learning_rate": 1.719102446853469e-05, + "loss": 1.4216, + "step": 3052 + }, + { + "epoch": 0.32, + "learning_rate": 1.7188480464187725e-05, + "loss": 1.4349, + "step": 3053 + }, + { + "epoch": 0.32, + "learning_rate": 1.718593549676908e-05, + "loss": 1.4784, + "step": 3054 + }, + { + "epoch": 0.32, + "learning_rate": 1.7183389566619714e-05, + "loss": 1.4325, + "step": 3055 + }, + { + "epoch": 0.32, + "learning_rate": 1.7180842674080717e-05, + "loss": 1.5387, + "step": 3056 + }, + { + "epoch": 0.32, + "learning_rate": 1.717829481949331e-05, + "loss": 1.655, + "step": 3057 + }, + { + "epoch": 0.32, + "learning_rate": 1.717574600319883e-05, + "loss": 1.4623, + "step": 3058 + }, + { + "epoch": 0.32, + "learning_rate": 1.7173196225538768e-05, + "loss": 1.4646, + "step": 3059 + }, + { + "epoch": 0.32, + "learning_rate": 1.717064548685472e-05, + "loss": 1.4641, + "step": 3060 + }, + { + "epoch": 0.32, + "learning_rate": 1.7168093787488418e-05, + "loss": 1.4033, + "step": 3061 + }, + { + "epoch": 0.32, + "learning_rate": 1.7165541127781726e-05, + "loss": 1.4085, + "step": 3062 + }, + { + "epoch": 0.32, + "learning_rate": 1.716298750807664e-05, + "loss": 1.387, + "step": 3063 + }, + { + "epoch": 0.32, + "learning_rate": 1.7160432928715272e-05, + "loss": 1.4197, + "step": 3064 + }, + { + "epoch": 0.32, + "learning_rate": 1.7157877390039872e-05, + "loss": 1.4883, + "step": 3065 + }, + { + "epoch": 0.32, + "learning_rate": 1.7155320892392818e-05, + "loss": 1.4865, + "step": 3066 + }, + { + "epoch": 0.32, + "learning_rate": 1.715276343611662e-05, + "loss": 1.4532, + "step": 3067 + }, + { + "epoch": 0.32, + "learning_rate": 1.71502050215539e-05, + "loss": 1.3991, + "step": 3068 + }, + { + "epoch": 0.32, + "learning_rate": 1.7147645649047424e-05, + "loss": 1.4318, + "step": 3069 + }, + { + "epoch": 0.32, + "learning_rate": 1.714508531894009e-05, + "loss": 1.3616, + "step": 3070 + }, + { + "epoch": 0.32, + "learning_rate": 1.7142524031574904e-05, + "loss": 1.4481, + "step": 3071 + }, + { + "epoch": 0.32, + "learning_rate": 1.7139961787295022e-05, + "loss": 1.3897, + "step": 3072 + }, + { + "epoch": 0.32, + "learning_rate": 1.7137398586443716e-05, + "loss": 1.3128, + "step": 3073 + }, + { + "epoch": 0.32, + "learning_rate": 1.713483442936439e-05, + "loss": 1.4481, + "step": 3074 + }, + { + "epoch": 0.32, + "learning_rate": 1.713226931640057e-05, + "loss": 1.5374, + "step": 3075 + }, + { + "epoch": 0.32, + "learning_rate": 1.7129703247895923e-05, + "loss": 1.4247, + "step": 3076 + }, + { + "epoch": 0.32, + "learning_rate": 1.712713622419423e-05, + "loss": 1.4098, + "step": 3077 + }, + { + "epoch": 0.32, + "learning_rate": 1.7124568245639414e-05, + "loss": 1.4558, + "step": 3078 + }, + { + "epoch": 0.32, + "learning_rate": 1.7121999312575507e-05, + "loss": 1.4484, + "step": 3079 + }, + { + "epoch": 0.32, + "learning_rate": 1.711942942534669e-05, + "loss": 1.4236, + "step": 3080 + }, + { + "epoch": 0.32, + "learning_rate": 1.7116858584297253e-05, + "loss": 1.613, + "step": 3081 + }, + { + "epoch": 0.32, + "learning_rate": 1.711428678977163e-05, + "loss": 1.4503, + "step": 3082 + }, + { + "epoch": 0.32, + "learning_rate": 1.7111714042114376e-05, + "loss": 1.4072, + "step": 3083 + }, + { + "epoch": 0.32, + "learning_rate": 1.7109140341670168e-05, + "loss": 1.5999, + "step": 3084 + }, + { + "epoch": 0.32, + "learning_rate": 1.7106565688783815e-05, + "loss": 1.4129, + "step": 3085 + }, + { + "epoch": 0.32, + "learning_rate": 1.710399008380026e-05, + "loss": 1.3973, + "step": 3086 + }, + { + "epoch": 0.32, + "learning_rate": 1.710141352706456e-05, + "loss": 1.4292, + "step": 3087 + }, + { + "epoch": 0.32, + "learning_rate": 1.709883601892192e-05, + "loss": 1.4372, + "step": 3088 + }, + { + "epoch": 0.32, + "learning_rate": 1.7096257559717647e-05, + "loss": 1.4924, + "step": 3089 + }, + { + "epoch": 0.32, + "learning_rate": 1.7093678149797196e-05, + "loss": 1.4222, + "step": 3090 + }, + { + "epoch": 0.32, + "learning_rate": 1.7091097789506137e-05, + "loss": 1.4797, + "step": 3091 + }, + { + "epoch": 0.32, + "learning_rate": 1.7088516479190175e-05, + "loss": 1.4738, + "step": 3092 + }, + { + "epoch": 0.32, + "learning_rate": 1.708593421919514e-05, + "loss": 1.5371, + "step": 3093 + }, + { + "epoch": 0.32, + "learning_rate": 1.7083351009866988e-05, + "loss": 1.3802, + "step": 3094 + }, + { + "epoch": 0.32, + "learning_rate": 1.7080766851551795e-05, + "loss": 1.4292, + "step": 3095 + }, + { + "epoch": 0.32, + "learning_rate": 1.707818174459578e-05, + "loss": 1.4478, + "step": 3096 + }, + { + "epoch": 0.32, + "learning_rate": 1.7075595689345285e-05, + "loss": 1.4619, + "step": 3097 + }, + { + "epoch": 0.32, + "learning_rate": 1.7073008686146763e-05, + "loss": 1.4603, + "step": 3098 + }, + { + "epoch": 0.32, + "learning_rate": 1.7070420735346815e-05, + "loss": 1.4548, + "step": 3099 + }, + { + "epoch": 0.33, + "learning_rate": 1.7067831837292157e-05, + "loss": 1.3638, + "step": 3100 + }, + { + "epoch": 0.33, + "learning_rate": 1.7065241992329634e-05, + "loss": 1.4284, + "step": 3101 + }, + { + "epoch": 0.33, + "learning_rate": 1.7062651200806217e-05, + "loss": 1.386, + "step": 3102 + }, + { + "epoch": 0.33, + "learning_rate": 1.7060059463069013e-05, + "loss": 1.5483, + "step": 3103 + }, + { + "epoch": 0.33, + "learning_rate": 1.705746677946524e-05, + "loss": 1.4963, + "step": 3104 + }, + { + "epoch": 0.33, + "learning_rate": 1.7054873150342257e-05, + "loss": 1.4539, + "step": 3105 + }, + { + "epoch": 0.33, + "learning_rate": 1.705227857604754e-05, + "loss": 1.4361, + "step": 3106 + }, + { + "epoch": 0.33, + "learning_rate": 1.7049683056928695e-05, + "loss": 1.3735, + "step": 3107 + }, + { + "epoch": 0.33, + "learning_rate": 1.7047086593333454e-05, + "loss": 1.4324, + "step": 3108 + }, + { + "epoch": 0.33, + "learning_rate": 1.7044489185609685e-05, + "loss": 1.5037, + "step": 3109 + }, + { + "epoch": 0.33, + "learning_rate": 1.704189083410536e-05, + "loss": 1.3913, + "step": 3110 + }, + { + "epoch": 0.33, + "learning_rate": 1.7039291539168604e-05, + "loss": 1.3233, + "step": 3111 + }, + { + "epoch": 0.33, + "learning_rate": 1.703669130114765e-05, + "loss": 1.4897, + "step": 3112 + }, + { + "epoch": 0.33, + "learning_rate": 1.7034090120390862e-05, + "loss": 1.4843, + "step": 3113 + }, + { + "epoch": 0.33, + "learning_rate": 1.7031487997246735e-05, + "loss": 1.3674, + "step": 3114 + }, + { + "epoch": 0.33, + "learning_rate": 1.7028884932063883e-05, + "loss": 1.4475, + "step": 3115 + }, + { + "epoch": 0.33, + "learning_rate": 1.702628092519105e-05, + "loss": 1.4134, + "step": 3116 + }, + { + "epoch": 0.33, + "learning_rate": 1.7023675976977108e-05, + "loss": 1.4484, + "step": 3117 + }, + { + "epoch": 0.33, + "learning_rate": 1.702107008777106e-05, + "loss": 1.407, + "step": 3118 + }, + { + "epoch": 0.33, + "learning_rate": 1.7018463257922005e-05, + "loss": 1.5443, + "step": 3119 + }, + { + "epoch": 0.33, + "learning_rate": 1.701585548777922e-05, + "loss": 1.4548, + "step": 3120 + }, + { + "epoch": 0.33, + "learning_rate": 1.7013246777692063e-05, + "loss": 1.4252, + "step": 3121 + }, + { + "epoch": 0.33, + "learning_rate": 1.7010637128010037e-05, + "loss": 1.3748, + "step": 3122 + }, + { + "epoch": 0.33, + "learning_rate": 1.7008026539082767e-05, + "loss": 1.3804, + "step": 3123 + }, + { + "epoch": 0.33, + "learning_rate": 1.7005415011260008e-05, + "loss": 1.4203, + "step": 3124 + }, + { + "epoch": 0.33, + "learning_rate": 1.7002802544891634e-05, + "loss": 1.4195, + "step": 3125 + }, + { + "epoch": 0.33, + "learning_rate": 1.700018914032765e-05, + "loss": 1.4188, + "step": 3126 + }, + { + "epoch": 0.33, + "learning_rate": 1.699757479791819e-05, + "loss": 1.3884, + "step": 3127 + }, + { + "epoch": 0.33, + "learning_rate": 1.6994959518013502e-05, + "loss": 1.4111, + "step": 3128 + }, + { + "epoch": 0.33, + "learning_rate": 1.6992343300963963e-05, + "loss": 1.5452, + "step": 3129 + }, + { + "epoch": 0.33, + "learning_rate": 1.6989726147120087e-05, + "loss": 1.4097, + "step": 3130 + }, + { + "epoch": 0.33, + "learning_rate": 1.6987108056832506e-05, + "loss": 1.481, + "step": 3131 + }, + { + "epoch": 0.33, + "learning_rate": 1.6984489030451973e-05, + "loss": 1.4505, + "step": 3132 + }, + { + "epoch": 0.33, + "learning_rate": 1.6981869068329368e-05, + "loss": 1.4281, + "step": 3133 + }, + { + "epoch": 0.33, + "learning_rate": 1.69792481708157e-05, + "loss": 1.4555, + "step": 3134 + }, + { + "epoch": 0.33, + "learning_rate": 1.6976626338262103e-05, + "loss": 1.4525, + "step": 3135 + }, + { + "epoch": 0.33, + "learning_rate": 1.6974003571019837e-05, + "loss": 1.3765, + "step": 3136 + }, + { + "epoch": 0.33, + "learning_rate": 1.6971379869440286e-05, + "loss": 1.3998, + "step": 3137 + }, + { + "epoch": 0.33, + "learning_rate": 1.696875523387495e-05, + "loss": 1.5103, + "step": 3138 + }, + { + "epoch": 0.33, + "learning_rate": 1.6966129664675474e-05, + "loss": 1.427, + "step": 3139 + }, + { + "epoch": 0.33, + "learning_rate": 1.6963503162193612e-05, + "loss": 1.4362, + "step": 3140 + }, + { + "epoch": 0.33, + "learning_rate": 1.6960875726781246e-05, + "loss": 1.4073, + "step": 3141 + }, + { + "epoch": 0.33, + "learning_rate": 1.6958247358790388e-05, + "loss": 1.4014, + "step": 3142 + }, + { + "epoch": 0.33, + "learning_rate": 1.6955618058573165e-05, + "loss": 1.4244, + "step": 3143 + }, + { + "epoch": 0.33, + "learning_rate": 1.6952987826481847e-05, + "loss": 1.47, + "step": 3144 + }, + { + "epoch": 0.33, + "learning_rate": 1.6950356662868814e-05, + "loss": 1.5112, + "step": 3145 + }, + { + "epoch": 0.33, + "learning_rate": 1.6947724568086562e-05, + "loss": 1.3398, + "step": 3146 + }, + { + "epoch": 0.33, + "learning_rate": 1.694509154248774e-05, + "loss": 1.4584, + "step": 3147 + }, + { + "epoch": 0.33, + "learning_rate": 1.69424575864251e-05, + "loss": 1.4383, + "step": 3148 + }, + { + "epoch": 0.33, + "learning_rate": 1.6939822700251523e-05, + "loss": 1.3869, + "step": 3149 + }, + { + "epoch": 0.33, + "learning_rate": 1.6937186884320015e-05, + "loss": 1.4453, + "step": 3150 + }, + { + "epoch": 0.33, + "learning_rate": 1.6934550138983713e-05, + "loss": 1.3355, + "step": 3151 + }, + { + "epoch": 0.33, + "learning_rate": 1.6931912464595866e-05, + "loss": 1.5573, + "step": 3152 + }, + { + "epoch": 0.33, + "learning_rate": 1.6929273861509865e-05, + "loss": 1.439, + "step": 3153 + }, + { + "epoch": 0.33, + "learning_rate": 1.6926634330079203e-05, + "loss": 1.6079, + "step": 3154 + }, + { + "epoch": 0.33, + "learning_rate": 1.692399387065752e-05, + "loss": 1.6973, + "step": 3155 + }, + { + "epoch": 0.33, + "learning_rate": 1.692135248359856e-05, + "loss": 1.3769, + "step": 3156 + }, + { + "epoch": 0.33, + "learning_rate": 1.6918710169256206e-05, + "loss": 1.4454, + "step": 3157 + }, + { + "epoch": 0.33, + "learning_rate": 1.691606692798446e-05, + "loss": 1.4495, + "step": 3158 + }, + { + "epoch": 0.33, + "learning_rate": 1.691342276013745e-05, + "loss": 1.4292, + "step": 3159 + }, + { + "epoch": 0.33, + "learning_rate": 1.691077766606942e-05, + "loss": 1.4405, + "step": 3160 + }, + { + "epoch": 0.33, + "learning_rate": 1.6908131646134757e-05, + "loss": 1.3683, + "step": 3161 + }, + { + "epoch": 0.33, + "learning_rate": 1.690548470068795e-05, + "loss": 1.4731, + "step": 3162 + }, + { + "epoch": 0.33, + "learning_rate": 1.690283683008362e-05, + "loss": 1.4323, + "step": 3163 + }, + { + "epoch": 0.33, + "learning_rate": 1.6900188034676518e-05, + "loss": 1.5133, + "step": 3164 + }, + { + "epoch": 0.33, + "learning_rate": 1.6897538314821516e-05, + "loss": 1.5529, + "step": 3165 + }, + { + "epoch": 0.33, + "learning_rate": 1.6894887670873605e-05, + "loss": 1.4427, + "step": 3166 + }, + { + "epoch": 0.33, + "learning_rate": 1.6892236103187904e-05, + "loss": 1.4344, + "step": 3167 + }, + { + "epoch": 0.33, + "learning_rate": 1.6889583612119657e-05, + "loss": 1.4291, + "step": 3168 + }, + { + "epoch": 0.33, + "learning_rate": 1.6886930198024226e-05, + "loss": 1.4683, + "step": 3169 + }, + { + "epoch": 0.33, + "learning_rate": 1.6884275861257106e-05, + "loss": 1.4442, + "step": 3170 + }, + { + "epoch": 0.33, + "learning_rate": 1.6881620602173905e-05, + "loss": 1.4509, + "step": 3171 + }, + { + "epoch": 0.33, + "learning_rate": 1.6878964421130362e-05, + "loss": 1.5113, + "step": 3172 + }, + { + "epoch": 0.33, + "learning_rate": 1.6876307318482334e-05, + "loss": 1.4261, + "step": 3173 + }, + { + "epoch": 0.33, + "learning_rate": 1.6873649294585805e-05, + "loss": 1.445, + "step": 3174 + }, + { + "epoch": 0.33, + "learning_rate": 1.6870990349796886e-05, + "loss": 1.4603, + "step": 3175 + }, + { + "epoch": 0.33, + "learning_rate": 1.68683304844718e-05, + "loss": 1.41, + "step": 3176 + }, + { + "epoch": 0.33, + "learning_rate": 1.686566969896691e-05, + "loss": 1.4018, + "step": 3177 + }, + { + "epoch": 0.33, + "learning_rate": 1.6863007993638687e-05, + "loss": 1.422, + "step": 3178 + }, + { + "epoch": 0.33, + "learning_rate": 1.6860345368843727e-05, + "loss": 1.4412, + "step": 3179 + }, + { + "epoch": 0.33, + "learning_rate": 1.6857681824938768e-05, + "loss": 1.5411, + "step": 3180 + }, + { + "epoch": 0.33, + "learning_rate": 1.685501736228064e-05, + "loss": 1.4416, + "step": 3181 + }, + { + "epoch": 0.33, + "learning_rate": 1.685235198122632e-05, + "loss": 1.5113, + "step": 3182 + }, + { + "epoch": 0.33, + "learning_rate": 1.6849685682132903e-05, + "loss": 1.423, + "step": 3183 + }, + { + "epoch": 0.33, + "learning_rate": 1.68470184653576e-05, + "loss": 1.404, + "step": 3184 + }, + { + "epoch": 0.33, + "eval_loss": 1.4771089553833008, + "eval_runtime": 77.4034, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3184 + }, + { + "epoch": 0.33, + "learning_rate": 1.6844350331257747e-05, + "loss": 1.4624, + "step": 3185 + }, + { + "epoch": 0.33, + "learning_rate": 1.6841681280190814e-05, + "loss": 1.4306, + "step": 3186 + }, + { + "epoch": 0.33, + "learning_rate": 1.683901131251438e-05, + "loss": 1.42, + "step": 3187 + }, + { + "epoch": 0.33, + "learning_rate": 1.6836340428586155e-05, + "loss": 1.4787, + "step": 3188 + }, + { + "epoch": 0.33, + "learning_rate": 1.6833668628763965e-05, + "loss": 1.3485, + "step": 3189 + }, + { + "epoch": 0.33, + "learning_rate": 1.683099591340576e-05, + "loss": 1.3674, + "step": 3190 + }, + { + "epoch": 0.33, + "learning_rate": 1.6828322282869627e-05, + "loss": 1.5187, + "step": 3191 + }, + { + "epoch": 0.33, + "learning_rate": 1.682564773751375e-05, + "loss": 1.4847, + "step": 3192 + }, + { + "epoch": 0.33, + "learning_rate": 1.682297227769646e-05, + "loss": 1.4815, + "step": 3193 + }, + { + "epoch": 0.33, + "learning_rate": 1.682029590377619e-05, + "loss": 1.4281, + "step": 3194 + }, + { + "epoch": 0.34, + "learning_rate": 1.6817618616111517e-05, + "loss": 1.4734, + "step": 3195 + }, + { + "epoch": 0.34, + "learning_rate": 1.681494041506112e-05, + "loss": 1.4861, + "step": 3196 + }, + { + "epoch": 0.34, + "learning_rate": 1.6812261300983808e-05, + "loss": 1.4372, + "step": 3197 + }, + { + "epoch": 0.34, + "learning_rate": 1.680958127423852e-05, + "loss": 1.4396, + "step": 3198 + }, + { + "epoch": 0.34, + "learning_rate": 1.680690033518431e-05, + "loss": 1.4225, + "step": 3199 + }, + { + "epoch": 0.34, + "learning_rate": 1.6804218484180347e-05, + "loss": 1.4925, + "step": 3200 + }, + { + "epoch": 0.34, + "learning_rate": 1.6801535721585942e-05, + "loss": 1.4306, + "step": 3201 + }, + { + "epoch": 0.34, + "learning_rate": 1.6798852047760506e-05, + "loss": 1.4298, + "step": 3202 + }, + { + "epoch": 0.34, + "learning_rate": 1.6796167463063588e-05, + "loss": 1.4725, + "step": 3203 + }, + { + "epoch": 0.34, + "learning_rate": 1.679348196785485e-05, + "loss": 1.4648, + "step": 3204 + }, + { + "epoch": 0.34, + "learning_rate": 1.6790795562494087e-05, + "loss": 1.4152, + "step": 3205 + }, + { + "epoch": 0.34, + "learning_rate": 1.6788108247341198e-05, + "loss": 1.4637, + "step": 3206 + }, + { + "epoch": 0.34, + "learning_rate": 1.6785420022756216e-05, + "loss": 1.4077, + "step": 3207 + }, + { + "epoch": 0.34, + "learning_rate": 1.67827308890993e-05, + "loss": 1.4585, + "step": 3208 + }, + { + "epoch": 0.34, + "learning_rate": 1.678004084673072e-05, + "loss": 1.3747, + "step": 3209 + }, + { + "epoch": 0.34, + "learning_rate": 1.6777349896010876e-05, + "loss": 1.4264, + "step": 3210 + }, + { + "epoch": 0.34, + "learning_rate": 1.677465803730028e-05, + "loss": 1.4178, + "step": 3211 + }, + { + "epoch": 0.34, + "learning_rate": 1.6771965270959584e-05, + "loss": 1.3876, + "step": 3212 + }, + { + "epoch": 0.34, + "learning_rate": 1.6769271597349538e-05, + "loss": 1.4658, + "step": 3213 + }, + { + "epoch": 0.34, + "learning_rate": 1.6766577016831026e-05, + "loss": 1.3968, + "step": 3214 + }, + { + "epoch": 0.34, + "learning_rate": 1.676388152976506e-05, + "loss": 1.5015, + "step": 3215 + }, + { + "epoch": 0.34, + "learning_rate": 1.6761185136512756e-05, + "loss": 1.4121, + "step": 3216 + }, + { + "epoch": 0.34, + "learning_rate": 1.675848783743537e-05, + "loss": 1.4146, + "step": 3217 + }, + { + "epoch": 0.34, + "learning_rate": 1.675578963289427e-05, + "loss": 1.4113, + "step": 3218 + }, + { + "epoch": 0.34, + "learning_rate": 1.6753090523250937e-05, + "loss": 1.4048, + "step": 3219 + }, + { + "epoch": 0.34, + "learning_rate": 1.6750390508866994e-05, + "loss": 1.4959, + "step": 3220 + }, + { + "epoch": 0.34, + "learning_rate": 1.6747689590104167e-05, + "loss": 1.4445, + "step": 3221 + }, + { + "epoch": 0.34, + "learning_rate": 1.6744987767324312e-05, + "loss": 1.4611, + "step": 3222 + }, + { + "epoch": 0.34, + "learning_rate": 1.67422850408894e-05, + "loss": 1.4141, + "step": 3223 + }, + { + "epoch": 0.34, + "learning_rate": 1.6739581411161535e-05, + "loss": 1.4218, + "step": 3224 + }, + { + "epoch": 0.34, + "learning_rate": 1.6736876878502925e-05, + "loss": 1.4266, + "step": 3225 + }, + { + "epoch": 0.34, + "learning_rate": 1.6734171443275913e-05, + "loss": 1.4941, + "step": 3226 + }, + { + "epoch": 0.34, + "learning_rate": 1.6731465105842955e-05, + "loss": 1.4294, + "step": 3227 + }, + { + "epoch": 0.34, + "learning_rate": 1.6728757866566635e-05, + "loss": 1.4189, + "step": 3228 + }, + { + "epoch": 0.34, + "learning_rate": 1.6726049725809647e-05, + "loss": 1.4713, + "step": 3229 + }, + { + "epoch": 0.34, + "learning_rate": 1.6723340683934818e-05, + "loss": 1.4203, + "step": 3230 + }, + { + "epoch": 0.34, + "learning_rate": 1.6720630741305088e-05, + "loss": 1.4112, + "step": 3231 + }, + { + "epoch": 0.34, + "learning_rate": 1.6717919898283523e-05, + "loss": 1.3811, + "step": 3232 + }, + { + "epoch": 0.34, + "learning_rate": 1.6715208155233296e-05, + "loss": 1.4242, + "step": 3233 + }, + { + "epoch": 0.34, + "learning_rate": 1.6712495512517725e-05, + "loss": 1.4207, + "step": 3234 + }, + { + "epoch": 0.34, + "learning_rate": 1.6709781970500222e-05, + "loss": 1.4888, + "step": 3235 + }, + { + "epoch": 0.34, + "learning_rate": 1.670706752954434e-05, + "loss": 1.4501, + "step": 3236 + }, + { + "epoch": 0.34, + "learning_rate": 1.670435219001374e-05, + "loss": 1.4367, + "step": 3237 + }, + { + "epoch": 0.34, + "learning_rate": 1.6701635952272212e-05, + "loss": 1.3959, + "step": 3238 + }, + { + "epoch": 0.34, + "learning_rate": 1.6698918816683655e-05, + "loss": 1.4257, + "step": 3239 + }, + { + "epoch": 0.34, + "learning_rate": 1.6696200783612102e-05, + "loss": 1.4718, + "step": 3240 + }, + { + "epoch": 0.34, + "learning_rate": 1.6693481853421697e-05, + "loss": 1.5899, + "step": 3241 + }, + { + "epoch": 0.34, + "learning_rate": 1.6690762026476707e-05, + "loss": 1.418, + "step": 3242 + }, + { + "epoch": 0.34, + "learning_rate": 1.668804130314152e-05, + "loss": 1.4076, + "step": 3243 + }, + { + "epoch": 0.34, + "learning_rate": 1.6685319683780645e-05, + "loss": 1.4571, + "step": 3244 + }, + { + "epoch": 0.34, + "learning_rate": 1.66825971687587e-05, + "loss": 1.4066, + "step": 3245 + }, + { + "epoch": 0.34, + "learning_rate": 1.6679873758440442e-05, + "loss": 1.4639, + "step": 3246 + }, + { + "epoch": 0.34, + "learning_rate": 1.6677149453190732e-05, + "loss": 1.453, + "step": 3247 + }, + { + "epoch": 0.34, + "learning_rate": 1.6674424253374558e-05, + "loss": 1.4262, + "step": 3248 + }, + { + "epoch": 0.34, + "learning_rate": 1.667169815935703e-05, + "loss": 1.3687, + "step": 3249 + }, + { + "epoch": 0.34, + "learning_rate": 1.6668971171503372e-05, + "loss": 1.5557, + "step": 3250 + }, + { + "epoch": 0.34, + "learning_rate": 1.6666243290178933e-05, + "loss": 1.4639, + "step": 3251 + }, + { + "epoch": 0.34, + "learning_rate": 1.6663514515749172e-05, + "loss": 1.4334, + "step": 3252 + }, + { + "epoch": 0.34, + "learning_rate": 1.6660784848579685e-05, + "loss": 1.3523, + "step": 3253 + }, + { + "epoch": 0.34, + "learning_rate": 1.6658054289036166e-05, + "loss": 1.3738, + "step": 3254 + }, + { + "epoch": 0.34, + "learning_rate": 1.665532283748445e-05, + "loss": 1.4159, + "step": 3255 + }, + { + "epoch": 0.34, + "learning_rate": 1.6652590494290474e-05, + "loss": 1.3609, + "step": 3256 + }, + { + "epoch": 0.34, + "learning_rate": 1.6649857259820303e-05, + "loss": 1.4449, + "step": 3257 + }, + { + "epoch": 0.34, + "learning_rate": 1.6647123134440126e-05, + "loss": 1.424, + "step": 3258 + }, + { + "epoch": 0.34, + "learning_rate": 1.664438811851624e-05, + "loss": 1.4737, + "step": 3259 + }, + { + "epoch": 0.34, + "learning_rate": 1.6641652212415066e-05, + "loss": 1.2717, + "step": 3260 + }, + { + "epoch": 0.34, + "learning_rate": 1.663891541650315e-05, + "loss": 1.4845, + "step": 3261 + }, + { + "epoch": 0.34, + "learning_rate": 1.663617773114715e-05, + "loss": 1.4115, + "step": 3262 + }, + { + "epoch": 0.34, + "learning_rate": 1.663343915671384e-05, + "loss": 1.4237, + "step": 3263 + }, + { + "epoch": 0.34, + "learning_rate": 1.6630699693570127e-05, + "loss": 1.4209, + "step": 3264 + }, + { + "epoch": 0.34, + "learning_rate": 1.6627959342083026e-05, + "loss": 1.506, + "step": 3265 + }, + { + "epoch": 0.34, + "learning_rate": 1.6625218102619672e-05, + "loss": 1.4466, + "step": 3266 + }, + { + "epoch": 0.34, + "learning_rate": 1.6622475975547324e-05, + "loss": 1.4129, + "step": 3267 + }, + { + "epoch": 0.34, + "learning_rate": 1.661973296123335e-05, + "loss": 1.4152, + "step": 3268 + }, + { + "epoch": 0.34, + "learning_rate": 1.661698906004525e-05, + "loss": 1.43, + "step": 3269 + }, + { + "epoch": 0.34, + "learning_rate": 1.661424427235064e-05, + "loss": 1.4701, + "step": 3270 + }, + { + "epoch": 0.34, + "learning_rate": 1.6611498598517238e-05, + "loss": 1.4598, + "step": 3271 + }, + { + "epoch": 0.34, + "learning_rate": 1.66087520389129e-05, + "loss": 1.4795, + "step": 3272 + }, + { + "epoch": 0.34, + "learning_rate": 1.6606004593905595e-05, + "loss": 1.5264, + "step": 3273 + }, + { + "epoch": 0.34, + "learning_rate": 1.6603256263863415e-05, + "loss": 1.4412, + "step": 3274 + }, + { + "epoch": 0.34, + "learning_rate": 1.6600507049154556e-05, + "loss": 1.45, + "step": 3275 + }, + { + "epoch": 0.34, + "learning_rate": 1.659775695014735e-05, + "loss": 1.4985, + "step": 3276 + }, + { + "epoch": 0.34, + "learning_rate": 1.659500596721024e-05, + "loss": 1.496, + "step": 3277 + }, + { + "epoch": 0.34, + "learning_rate": 1.6592254100711775e-05, + "loss": 1.4386, + "step": 3278 + }, + { + "epoch": 0.34, + "learning_rate": 1.658950135102065e-05, + "loss": 1.4073, + "step": 3279 + }, + { + "epoch": 0.34, + "learning_rate": 1.658674771850565e-05, + "loss": 1.3912, + "step": 3280 + }, + { + "epoch": 0.34, + "learning_rate": 1.6583993203535702e-05, + "loss": 1.3628, + "step": 3281 + }, + { + "epoch": 0.34, + "learning_rate": 1.658123780647983e-05, + "loss": 1.6089, + "step": 3282 + }, + { + "epoch": 0.34, + "learning_rate": 1.6578481527707196e-05, + "loss": 1.2367, + "step": 3283 + }, + { + "epoch": 0.34, + "learning_rate": 1.657572436758706e-05, + "loss": 1.4058, + "step": 3284 + }, + { + "epoch": 0.34, + "learning_rate": 1.6572966326488825e-05, + "loss": 1.4067, + "step": 3285 + }, + { + "epoch": 0.34, + "learning_rate": 1.657020740478198e-05, + "loss": 1.4187, + "step": 3286 + }, + { + "epoch": 0.34, + "learning_rate": 1.6567447602836166e-05, + "loss": 1.4599, + "step": 3287 + }, + { + "epoch": 0.34, + "learning_rate": 1.6564686921021115e-05, + "loss": 1.432, + "step": 3288 + }, + { + "epoch": 0.34, + "learning_rate": 1.6561925359706693e-05, + "loss": 1.3941, + "step": 3289 + }, + { + "epoch": 0.35, + "learning_rate": 1.6559162919262874e-05, + "loss": 1.3644, + "step": 3290 + }, + { + "epoch": 0.35, + "learning_rate": 1.6556399600059756e-05, + "loss": 1.4628, + "step": 3291 + }, + { + "epoch": 0.35, + "learning_rate": 1.6553635402467555e-05, + "loss": 1.4355, + "step": 3292 + }, + { + "epoch": 0.35, + "learning_rate": 1.6550870326856596e-05, + "loss": 1.4627, + "step": 3293 + }, + { + "epoch": 0.35, + "learning_rate": 1.6548104373597335e-05, + "loss": 1.442, + "step": 3294 + }, + { + "epoch": 0.35, + "learning_rate": 1.6545337543060338e-05, + "loss": 1.3991, + "step": 3295 + }, + { + "epoch": 0.35, + "learning_rate": 1.6542569835616283e-05, + "loss": 1.4193, + "step": 3296 + }, + { + "epoch": 0.35, + "learning_rate": 1.6539801251635982e-05, + "loss": 1.4792, + "step": 3297 + }, + { + "epoch": 0.35, + "learning_rate": 1.653703179149034e-05, + "loss": 1.4735, + "step": 3298 + }, + { + "epoch": 0.35, + "learning_rate": 1.6534261455550408e-05, + "loss": 1.451, + "step": 3299 + }, + { + "epoch": 0.35, + "learning_rate": 1.653149024418733e-05, + "loss": 1.3975, + "step": 3300 + }, + { + "epoch": 0.35, + "learning_rate": 1.652871815777238e-05, + "loss": 1.4843, + "step": 3301 + }, + { + "epoch": 0.35, + "learning_rate": 1.6525945196676948e-05, + "loss": 1.4782, + "step": 3302 + }, + { + "epoch": 0.35, + "learning_rate": 1.652317136127254e-05, + "loss": 1.3865, + "step": 3303 + }, + { + "epoch": 0.35, + "learning_rate": 1.6520396651930777e-05, + "loss": 1.4359, + "step": 3304 + }, + { + "epoch": 0.35, + "learning_rate": 1.6517621069023397e-05, + "loss": 1.4289, + "step": 3305 + }, + { + "epoch": 0.35, + "learning_rate": 1.651484461292226e-05, + "loss": 1.3526, + "step": 3306 + }, + { + "epoch": 0.35, + "learning_rate": 1.6512067283999336e-05, + "loss": 1.3671, + "step": 3307 + }, + { + "epoch": 0.35, + "learning_rate": 1.650928908262672e-05, + "loss": 1.6041, + "step": 3308 + }, + { + "epoch": 0.35, + "learning_rate": 1.650651000917662e-05, + "loss": 1.4322, + "step": 3309 + }, + { + "epoch": 0.35, + "learning_rate": 1.6503730064021354e-05, + "loss": 1.3992, + "step": 3310 + }, + { + "epoch": 0.35, + "learning_rate": 1.650094924753337e-05, + "loss": 1.4928, + "step": 3311 + }, + { + "epoch": 0.35, + "learning_rate": 1.6498167560085222e-05, + "loss": 1.4075, + "step": 3312 + }, + { + "epoch": 0.35, + "learning_rate": 1.6495385002049583e-05, + "loss": 1.4535, + "step": 3313 + }, + { + "epoch": 0.35, + "learning_rate": 1.6492601573799253e-05, + "loss": 1.4221, + "step": 3314 + }, + { + "epoch": 0.35, + "learning_rate": 1.6489817275707133e-05, + "loss": 1.3688, + "step": 3315 + }, + { + "epoch": 0.35, + "learning_rate": 1.6487032108146243e-05, + "loss": 1.3889, + "step": 3316 + }, + { + "epoch": 0.35, + "learning_rate": 1.6484246071489733e-05, + "loss": 1.3942, + "step": 3317 + }, + { + "epoch": 0.35, + "learning_rate": 1.6481459166110858e-05, + "loss": 1.4004, + "step": 3318 + }, + { + "epoch": 0.35, + "learning_rate": 1.647867139238299e-05, + "loss": 1.7308, + "step": 3319 + }, + { + "epoch": 0.35, + "learning_rate": 1.6475882750679622e-05, + "loss": 1.5001, + "step": 3320 + }, + { + "epoch": 0.35, + "learning_rate": 1.647309324137435e-05, + "loss": 1.4325, + "step": 3321 + }, + { + "epoch": 0.35, + "learning_rate": 1.6470302864840913e-05, + "loss": 1.4494, + "step": 3322 + }, + { + "epoch": 0.35, + "learning_rate": 1.6467511621453136e-05, + "loss": 1.4418, + "step": 3323 + }, + { + "epoch": 0.35, + "learning_rate": 1.646471951158498e-05, + "loss": 1.4046, + "step": 3324 + }, + { + "epoch": 0.35, + "learning_rate": 1.6461926535610517e-05, + "loss": 1.5031, + "step": 3325 + }, + { + "epoch": 0.35, + "learning_rate": 1.645913269390393e-05, + "loss": 1.4813, + "step": 3326 + }, + { + "epoch": 0.35, + "learning_rate": 1.6456337986839525e-05, + "loss": 1.3842, + "step": 3327 + }, + { + "epoch": 0.35, + "learning_rate": 1.645354241479172e-05, + "loss": 1.4539, + "step": 3328 + }, + { + "epoch": 0.35, + "learning_rate": 1.6450745978135048e-05, + "loss": 1.4503, + "step": 3329 + }, + { + "epoch": 0.35, + "learning_rate": 1.6447948677244163e-05, + "loss": 1.3741, + "step": 3330 + }, + { + "epoch": 0.35, + "learning_rate": 1.6445150512493832e-05, + "loss": 1.425, + "step": 3331 + }, + { + "epoch": 0.35, + "learning_rate": 1.644235148425893e-05, + "loss": 1.4277, + "step": 3332 + }, + { + "epoch": 0.35, + "learning_rate": 1.6439551592914464e-05, + "loss": 1.4918, + "step": 3333 + }, + { + "epoch": 0.35, + "learning_rate": 1.6436750838835543e-05, + "loss": 1.3364, + "step": 3334 + }, + { + "epoch": 0.35, + "learning_rate": 1.6433949222397397e-05, + "loss": 1.4741, + "step": 3335 + }, + { + "epoch": 0.35, + "learning_rate": 1.643114674397537e-05, + "loss": 1.3867, + "step": 3336 + }, + { + "epoch": 0.35, + "learning_rate": 1.642834340394492e-05, + "loss": 1.3817, + "step": 3337 + }, + { + "epoch": 0.35, + "learning_rate": 1.6425539202681625e-05, + "loss": 1.4308, + "step": 3338 + }, + { + "epoch": 0.35, + "learning_rate": 1.6422734140561178e-05, + "loss": 1.4401, + "step": 3339 + }, + { + "epoch": 0.35, + "learning_rate": 1.641992821795938e-05, + "loss": 1.4338, + "step": 3340 + }, + { + "epoch": 0.35, + "learning_rate": 1.641712143525216e-05, + "loss": 1.3804, + "step": 3341 + }, + { + "epoch": 0.35, + "learning_rate": 1.6414313792815546e-05, + "loss": 1.371, + "step": 3342 + }, + { + "epoch": 0.35, + "learning_rate": 1.6411505291025695e-05, + "loss": 1.4102, + "step": 3343 + }, + { + "epoch": 0.35, + "learning_rate": 1.6408695930258875e-05, + "loss": 1.4433, + "step": 3344 + }, + { + "epoch": 0.35, + "learning_rate": 1.6405885710891467e-05, + "loss": 1.3895, + "step": 3345 + }, + { + "epoch": 0.35, + "learning_rate": 1.6403074633299966e-05, + "loss": 1.4321, + "step": 3346 + }, + { + "epoch": 0.35, + "learning_rate": 1.640026269786098e-05, + "loss": 1.4207, + "step": 3347 + }, + { + "epoch": 0.35, + "learning_rate": 1.639744990495125e-05, + "loss": 1.3758, + "step": 3348 + }, + { + "epoch": 0.35, + "learning_rate": 1.6394636254947612e-05, + "loss": 1.4203, + "step": 3349 + }, + { + "epoch": 0.35, + "learning_rate": 1.6391821748227013e-05, + "loss": 1.4596, + "step": 3350 + }, + { + "epoch": 0.35, + "learning_rate": 1.6389006385166537e-05, + "loss": 1.4344, + "step": 3351 + }, + { + "epoch": 0.35, + "learning_rate": 1.6386190166143366e-05, + "loss": 1.4048, + "step": 3352 + }, + { + "epoch": 0.35, + "learning_rate": 1.6383373091534798e-05, + "loss": 1.4348, + "step": 3353 + }, + { + "epoch": 0.35, + "learning_rate": 1.638055516171825e-05, + "loss": 1.4972, + "step": 3354 + }, + { + "epoch": 0.35, + "learning_rate": 1.6377736377071258e-05, + "loss": 1.4685, + "step": 3355 + }, + { + "epoch": 0.35, + "learning_rate": 1.637491673797146e-05, + "loss": 1.4093, + "step": 3356 + }, + { + "epoch": 0.35, + "learning_rate": 1.6372096244796616e-05, + "loss": 1.4452, + "step": 3357 + }, + { + "epoch": 0.35, + "learning_rate": 1.63692748979246e-05, + "loss": 1.4458, + "step": 3358 + }, + { + "epoch": 0.35, + "learning_rate": 1.6366452697733404e-05, + "loss": 1.4187, + "step": 3359 + }, + { + "epoch": 0.35, + "learning_rate": 1.6363629644601126e-05, + "loss": 1.4052, + "step": 3360 + }, + { + "epoch": 0.35, + "learning_rate": 1.6360805738905984e-05, + "loss": 1.439, + "step": 3361 + }, + { + "epoch": 0.35, + "learning_rate": 1.635798098102631e-05, + "loss": 1.4131, + "step": 3362 + }, + { + "epoch": 0.35, + "learning_rate": 1.6355155371340544e-05, + "loss": 1.4391, + "step": 3363 + }, + { + "epoch": 0.35, + "learning_rate": 1.6352328910227252e-05, + "loss": 1.4318, + "step": 3364 + }, + { + "epoch": 0.35, + "learning_rate": 1.63495015980651e-05, + "loss": 1.5112, + "step": 3365 + }, + { + "epoch": 0.35, + "learning_rate": 1.6346673435232884e-05, + "loss": 1.4688, + "step": 3366 + }, + { + "epoch": 0.35, + "learning_rate": 1.6343844422109496e-05, + "loss": 1.3807, + "step": 3367 + }, + { + "epoch": 0.35, + "learning_rate": 1.634101455907396e-05, + "loss": 1.4083, + "step": 3368 + }, + { + "epoch": 0.35, + "learning_rate": 1.6338183846505394e-05, + "loss": 1.3566, + "step": 3369 + }, + { + "epoch": 0.35, + "learning_rate": 1.633535228478305e-05, + "loss": 1.4287, + "step": 3370 + }, + { + "epoch": 0.35, + "learning_rate": 1.6332519874286285e-05, + "loss": 1.3494, + "step": 3371 + }, + { + "epoch": 0.35, + "learning_rate": 1.6329686615394558e-05, + "loss": 1.3813, + "step": 3372 + }, + { + "epoch": 0.35, + "learning_rate": 1.6326852508487468e-05, + "loss": 1.4241, + "step": 3373 + }, + { + "epoch": 0.35, + "learning_rate": 1.63240175539447e-05, + "loss": 1.424, + "step": 3374 + }, + { + "epoch": 0.35, + "learning_rate": 1.632118175214607e-05, + "loss": 1.4212, + "step": 3375 + }, + { + "epoch": 0.35, + "learning_rate": 1.6318345103471504e-05, + "loss": 1.4671, + "step": 3376 + }, + { + "epoch": 0.35, + "learning_rate": 1.6315507608301044e-05, + "loss": 1.4593, + "step": 3377 + }, + { + "epoch": 0.35, + "learning_rate": 1.631266926701483e-05, + "loss": 1.7816, + "step": 3378 + }, + { + "epoch": 0.35, + "learning_rate": 1.6309830079993134e-05, + "loss": 1.5134, + "step": 3379 + }, + { + "epoch": 0.35, + "learning_rate": 1.6306990047616334e-05, + "loss": 0.8933, + "step": 3380 + }, + { + "epoch": 0.35, + "learning_rate": 1.630414917026492e-05, + "loss": 1.1033, + "step": 3381 + }, + { + "epoch": 0.35, + "learning_rate": 1.6301307448319497e-05, + "loss": 1.3494, + "step": 3382 + }, + { + "epoch": 0.35, + "learning_rate": 1.6298464882160784e-05, + "loss": 1.4299, + "step": 3383 + }, + { + "epoch": 0.35, + "eval_loss": 1.482450008392334, + "eval_runtime": 77.3737, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3383 + }, + { + "epoch": 0.35, + "learning_rate": 1.629562147216961e-05, + "loss": 1.3971, + "step": 3384 + }, + { + "epoch": 0.35, + "learning_rate": 1.6292777218726917e-05, + "loss": 1.3706, + "step": 3385 + }, + { + "epoch": 0.36, + "learning_rate": 1.6289932122213765e-05, + "loss": 1.4524, + "step": 3386 + }, + { + "epoch": 0.36, + "learning_rate": 1.6287086183011328e-05, + "loss": 1.4595, + "step": 3387 + }, + { + "epoch": 0.36, + "learning_rate": 1.628423940150088e-05, + "loss": 1.492, + "step": 3388 + }, + { + "epoch": 0.36, + "learning_rate": 1.628139177806382e-05, + "loss": 1.5576, + "step": 3389 + }, + { + "epoch": 0.36, + "learning_rate": 1.6278543313081657e-05, + "loss": 1.4615, + "step": 3390 + }, + { + "epoch": 0.36, + "learning_rate": 1.6275694006936015e-05, + "loss": 1.3456, + "step": 3391 + }, + { + "epoch": 0.36, + "learning_rate": 1.627284386000862e-05, + "loss": 1.4254, + "step": 3392 + }, + { + "epoch": 0.36, + "learning_rate": 1.6269992872681325e-05, + "loss": 1.433, + "step": 3393 + }, + { + "epoch": 0.36, + "learning_rate": 1.626714104533609e-05, + "loss": 1.5291, + "step": 3394 + }, + { + "epoch": 0.36, + "learning_rate": 1.626428837835498e-05, + "loss": 1.4502, + "step": 3395 + }, + { + "epoch": 0.36, + "learning_rate": 1.626143487212019e-05, + "loss": 1.3756, + "step": 3396 + }, + { + "epoch": 0.36, + "learning_rate": 1.6258580527014002e-05, + "loss": 1.414, + "step": 3397 + }, + { + "epoch": 0.36, + "learning_rate": 1.6255725343418835e-05, + "loss": 1.6289, + "step": 3398 + }, + { + "epoch": 0.36, + "learning_rate": 1.6252869321717208e-05, + "loss": 1.4862, + "step": 3399 + }, + { + "epoch": 0.36, + "learning_rate": 1.6250012462291756e-05, + "loss": 1.4213, + "step": 3400 + }, + { + "epoch": 0.36, + "learning_rate": 1.6247154765525217e-05, + "loss": 1.524, + "step": 3401 + }, + { + "epoch": 0.36, + "learning_rate": 1.624429623180046e-05, + "loss": 1.6013, + "step": 3402 + }, + { + "epoch": 0.36, + "learning_rate": 1.624143686150045e-05, + "loss": 1.4557, + "step": 3403 + }, + { + "epoch": 0.36, + "learning_rate": 1.6238576655008266e-05, + "loss": 1.3831, + "step": 3404 + }, + { + "epoch": 0.36, + "learning_rate": 1.6235715612707105e-05, + "loss": 1.4008, + "step": 3405 + }, + { + "epoch": 0.36, + "learning_rate": 1.623285373498028e-05, + "loss": 1.4848, + "step": 3406 + }, + { + "epoch": 0.36, + "learning_rate": 1.6229991022211197e-05, + "loss": 1.4459, + "step": 3407 + }, + { + "epoch": 0.36, + "learning_rate": 1.6227127474783393e-05, + "loss": 1.4334, + "step": 3408 + }, + { + "epoch": 0.36, + "learning_rate": 1.6224263093080507e-05, + "loss": 1.4123, + "step": 3409 + }, + { + "epoch": 0.36, + "learning_rate": 1.6221397877486294e-05, + "loss": 1.3691, + "step": 3410 + }, + { + "epoch": 0.36, + "learning_rate": 1.6218531828384618e-05, + "loss": 1.4128, + "step": 3411 + }, + { + "epoch": 0.36, + "learning_rate": 1.6215664946159457e-05, + "loss": 1.3642, + "step": 3412 + }, + { + "epoch": 0.36, + "learning_rate": 1.6212797231194902e-05, + "loss": 1.4311, + "step": 3413 + }, + { + "epoch": 0.36, + "learning_rate": 1.6209928683875152e-05, + "loss": 1.4695, + "step": 3414 + }, + { + "epoch": 0.36, + "learning_rate": 1.6207059304584514e-05, + "loss": 1.3871, + "step": 3415 + }, + { + "epoch": 0.36, + "learning_rate": 1.6204189093707414e-05, + "loss": 1.4219, + "step": 3416 + }, + { + "epoch": 0.36, + "learning_rate": 1.620131805162839e-05, + "loss": 1.6199, + "step": 3417 + }, + { + "epoch": 0.36, + "learning_rate": 1.619844617873208e-05, + "loss": 1.4433, + "step": 3418 + }, + { + "epoch": 0.36, + "learning_rate": 1.619557347540325e-05, + "loss": 1.4773, + "step": 3419 + }, + { + "epoch": 0.36, + "learning_rate": 1.6192699942026763e-05, + "loss": 1.4551, + "step": 3420 + }, + { + "epoch": 0.36, + "learning_rate": 1.6189825578987603e-05, + "loss": 1.4903, + "step": 3421 + }, + { + "epoch": 0.36, + "learning_rate": 1.6186950386670855e-05, + "loss": 1.473, + "step": 3422 + }, + { + "epoch": 0.36, + "learning_rate": 1.6184074365461722e-05, + "loss": 1.4082, + "step": 3423 + }, + { + "epoch": 0.36, + "learning_rate": 1.6181197515745523e-05, + "loss": 1.4746, + "step": 3424 + }, + { + "epoch": 0.36, + "learning_rate": 1.6178319837907674e-05, + "loss": 1.449, + "step": 3425 + }, + { + "epoch": 0.36, + "learning_rate": 1.6175441332333715e-05, + "loss": 1.377, + "step": 3426 + }, + { + "epoch": 0.36, + "learning_rate": 1.617256199940929e-05, + "loss": 1.2364, + "step": 3427 + }, + { + "epoch": 0.36, + "learning_rate": 1.6169681839520155e-05, + "loss": 1.4437, + "step": 3428 + }, + { + "epoch": 0.36, + "learning_rate": 1.616680085305218e-05, + "loss": 1.4726, + "step": 3429 + }, + { + "epoch": 0.36, + "learning_rate": 1.616391904039134e-05, + "loss": 1.4824, + "step": 3430 + }, + { + "epoch": 0.36, + "learning_rate": 1.616103640192373e-05, + "loss": 1.4052, + "step": 3431 + }, + { + "epoch": 0.36, + "learning_rate": 1.6158152938035537e-05, + "loss": 1.4131, + "step": 3432 + }, + { + "epoch": 0.36, + "learning_rate": 1.6155268649113084e-05, + "loss": 1.4267, + "step": 3433 + }, + { + "epoch": 0.36, + "learning_rate": 1.6152383535542786e-05, + "loss": 1.3735, + "step": 3434 + }, + { + "epoch": 0.36, + "learning_rate": 1.6149497597711175e-05, + "loss": 1.4249, + "step": 3435 + }, + { + "epoch": 0.36, + "learning_rate": 1.614661083600489e-05, + "loss": 1.4312, + "step": 3436 + }, + { + "epoch": 0.36, + "learning_rate": 1.6143723250810686e-05, + "loss": 1.4831, + "step": 3437 + }, + { + "epoch": 0.36, + "learning_rate": 1.6140834842515425e-05, + "loss": 1.4183, + "step": 3438 + }, + { + "epoch": 0.36, + "learning_rate": 1.6137945611506078e-05, + "loss": 1.3908, + "step": 3439 + }, + { + "epoch": 0.36, + "learning_rate": 1.613505555816973e-05, + "loss": 1.425, + "step": 3440 + }, + { + "epoch": 0.36, + "learning_rate": 1.613216468289357e-05, + "loss": 1.3589, + "step": 3441 + }, + { + "epoch": 0.36, + "learning_rate": 1.6129272986064903e-05, + "loss": 1.4272, + "step": 3442 + }, + { + "epoch": 0.36, + "learning_rate": 1.6126380468071142e-05, + "loss": 1.4337, + "step": 3443 + }, + { + "epoch": 0.36, + "learning_rate": 1.6123487129299817e-05, + "loss": 1.3872, + "step": 3444 + }, + { + "epoch": 0.36, + "learning_rate": 1.612059297013855e-05, + "loss": 1.374, + "step": 3445 + }, + { + "epoch": 0.36, + "learning_rate": 1.611769799097509e-05, + "loss": 1.314, + "step": 3446 + }, + { + "epoch": 0.36, + "learning_rate": 1.6114802192197284e-05, + "loss": 1.3951, + "step": 3447 + }, + { + "epoch": 0.36, + "learning_rate": 1.6111905574193102e-05, + "loss": 1.4732, + "step": 3448 + }, + { + "epoch": 0.36, + "learning_rate": 1.6109008137350614e-05, + "loss": 1.3575, + "step": 3449 + }, + { + "epoch": 0.36, + "learning_rate": 1.6106109882058e-05, + "loss": 1.4606, + "step": 3450 + }, + { + "epoch": 0.36, + "learning_rate": 1.6103210808703554e-05, + "loss": 1.4357, + "step": 3451 + }, + { + "epoch": 0.36, + "learning_rate": 1.6100310917675678e-05, + "loss": 0.8456, + "step": 3452 + }, + { + "epoch": 0.36, + "learning_rate": 1.609741020936288e-05, + "loss": 1.07, + "step": 3453 + }, + { + "epoch": 0.36, + "learning_rate": 1.6094508684153782e-05, + "loss": 1.4435, + "step": 3454 + }, + { + "epoch": 0.36, + "learning_rate": 1.609160634243711e-05, + "loss": 1.3696, + "step": 3455 + }, + { + "epoch": 0.36, + "learning_rate": 1.6088703184601712e-05, + "loss": 1.4012, + "step": 3456 + }, + { + "epoch": 0.36, + "learning_rate": 1.608579921103653e-05, + "loss": 1.5212, + "step": 3457 + }, + { + "epoch": 0.36, + "learning_rate": 1.608289442213062e-05, + "loss": 1.4339, + "step": 3458 + }, + { + "epoch": 0.36, + "learning_rate": 1.607998881827316e-05, + "loss": 1.4901, + "step": 3459 + }, + { + "epoch": 0.36, + "learning_rate": 1.6077082399853412e-05, + "loss": 1.4822, + "step": 3460 + }, + { + "epoch": 0.36, + "learning_rate": 1.607417516726077e-05, + "loss": 1.3696, + "step": 3461 + }, + { + "epoch": 0.36, + "learning_rate": 1.6071267120884727e-05, + "loss": 1.4434, + "step": 3462 + }, + { + "epoch": 0.36, + "learning_rate": 1.6068358261114886e-05, + "loss": 1.3916, + "step": 3463 + }, + { + "epoch": 0.36, + "learning_rate": 1.606544858834096e-05, + "loss": 1.422, + "step": 3464 + }, + { + "epoch": 0.36, + "learning_rate": 1.6062538102952763e-05, + "loss": 1.367, + "step": 3465 + }, + { + "epoch": 0.36, + "learning_rate": 1.605962680534024e-05, + "loss": 1.3788, + "step": 3466 + }, + { + "epoch": 0.36, + "learning_rate": 1.605671469589342e-05, + "loss": 1.4366, + "step": 3467 + }, + { + "epoch": 0.36, + "learning_rate": 1.6053801775002453e-05, + "loss": 1.4027, + "step": 3468 + }, + { + "epoch": 0.36, + "learning_rate": 1.6050888043057595e-05, + "loss": 1.4386, + "step": 3469 + }, + { + "epoch": 0.36, + "learning_rate": 1.6047973500449212e-05, + "loss": 1.4675, + "step": 3470 + }, + { + "epoch": 0.36, + "learning_rate": 1.6045058147567778e-05, + "loss": 1.6936, + "step": 3471 + }, + { + "epoch": 0.36, + "learning_rate": 1.6042141984803875e-05, + "loss": 1.4858, + "step": 3472 + }, + { + "epoch": 0.36, + "learning_rate": 1.6039225012548196e-05, + "loss": 1.5004, + "step": 3473 + }, + { + "epoch": 0.36, + "learning_rate": 1.6036307231191534e-05, + "loss": 1.4969, + "step": 3474 + }, + { + "epoch": 0.36, + "learning_rate": 1.6033388641124803e-05, + "loss": 1.4027, + "step": 3475 + }, + { + "epoch": 0.36, + "learning_rate": 1.6030469242739016e-05, + "loss": 1.4741, + "step": 3476 + }, + { + "epoch": 0.36, + "learning_rate": 1.60275490364253e-05, + "loss": 1.3887, + "step": 3477 + }, + { + "epoch": 0.36, + "learning_rate": 1.602462802257488e-05, + "loss": 1.6735, + "step": 3478 + }, + { + "epoch": 0.36, + "learning_rate": 1.602170620157911e-05, + "loss": 1.4997, + "step": 3479 + }, + { + "epoch": 0.36, + "learning_rate": 1.601878357382943e-05, + "loss": 1.3973, + "step": 3480 + }, + { + "epoch": 0.37, + "learning_rate": 1.6015860139717398e-05, + "loss": 1.416, + "step": 3481 + }, + { + "epoch": 0.37, + "learning_rate": 1.6012935899634682e-05, + "loss": 1.4102, + "step": 3482 + }, + { + "epoch": 0.37, + "learning_rate": 1.601001085397305e-05, + "loss": 1.4248, + "step": 3483 + }, + { + "epoch": 0.37, + "learning_rate": 1.6007085003124386e-05, + "loss": 1.3909, + "step": 3484 + }, + { + "epoch": 0.37, + "learning_rate": 1.600415834748068e-05, + "loss": 1.4029, + "step": 3485 + }, + { + "epoch": 0.37, + "learning_rate": 1.6001230887434024e-05, + "loss": 1.4219, + "step": 3486 + }, + { + "epoch": 0.37, + "learning_rate": 1.5998302623376633e-05, + "loss": 1.4008, + "step": 3487 + }, + { + "epoch": 0.37, + "learning_rate": 1.5995373555700806e-05, + "loss": 1.5163, + "step": 3488 + }, + { + "epoch": 0.37, + "learning_rate": 1.599244368479897e-05, + "loss": 1.4541, + "step": 3489 + }, + { + "epoch": 0.37, + "learning_rate": 1.598951301106365e-05, + "loss": 1.4454, + "step": 3490 + }, + { + "epoch": 0.37, + "learning_rate": 1.598658153488748e-05, + "loss": 1.1014, + "step": 3491 + }, + { + "epoch": 0.37, + "learning_rate": 1.598364925666321e-05, + "loss": 1.407, + "step": 3492 + }, + { + "epoch": 0.37, + "learning_rate": 1.5980716176783682e-05, + "loss": 1.5046, + "step": 3493 + }, + { + "epoch": 0.37, + "learning_rate": 1.5977782295641857e-05, + "loss": 1.4265, + "step": 3494 + }, + { + "epoch": 0.37, + "learning_rate": 1.5974847613630796e-05, + "loss": 1.46, + "step": 3495 + }, + { + "epoch": 0.37, + "learning_rate": 1.5971912131143677e-05, + "loss": 1.3996, + "step": 3496 + }, + { + "epoch": 0.37, + "learning_rate": 1.5968975848573772e-05, + "loss": 1.4719, + "step": 3497 + }, + { + "epoch": 0.37, + "learning_rate": 1.596603876631447e-05, + "loss": 1.43, + "step": 3498 + }, + { + "epoch": 0.37, + "learning_rate": 1.596310088475927e-05, + "loss": 1.4109, + "step": 3499 + }, + { + "epoch": 0.37, + "learning_rate": 1.5960162204301768e-05, + "loss": 1.3612, + "step": 3500 + }, + { + "epoch": 0.37, + "learning_rate": 1.5957222725335672e-05, + "loss": 1.5045, + "step": 3501 + }, + { + "epoch": 0.37, + "learning_rate": 1.5954282448254794e-05, + "loss": 1.5323, + "step": 3502 + }, + { + "epoch": 0.37, + "learning_rate": 1.595134137345306e-05, + "loss": 1.4518, + "step": 3503 + }, + { + "epoch": 0.37, + "learning_rate": 1.5948399501324495e-05, + "loss": 1.6131, + "step": 3504 + }, + { + "epoch": 0.37, + "learning_rate": 1.594545683226324e-05, + "loss": 1.5076, + "step": 3505 + }, + { + "epoch": 0.37, + "learning_rate": 1.594251336666353e-05, + "loss": 1.482, + "step": 3506 + }, + { + "epoch": 0.37, + "learning_rate": 1.5939569104919716e-05, + "loss": 1.4429, + "step": 3507 + }, + { + "epoch": 0.37, + "learning_rate": 1.5936624047426254e-05, + "loss": 1.4662, + "step": 3508 + }, + { + "epoch": 0.37, + "learning_rate": 1.5933678194577708e-05, + "loss": 1.425, + "step": 3509 + }, + { + "epoch": 0.37, + "learning_rate": 1.5930731546768744e-05, + "loss": 1.4312, + "step": 3510 + }, + { + "epoch": 0.37, + "learning_rate": 1.592778410439414e-05, + "loss": 1.4336, + "step": 3511 + }, + { + "epoch": 0.37, + "learning_rate": 1.5924835867848775e-05, + "loss": 1.4197, + "step": 3512 + }, + { + "epoch": 0.37, + "learning_rate": 1.5921886837527638e-05, + "loss": 1.4456, + "step": 3513 + }, + { + "epoch": 0.37, + "learning_rate": 1.5918937013825823e-05, + "loss": 1.4394, + "step": 3514 + }, + { + "epoch": 0.37, + "learning_rate": 1.5915986397138526e-05, + "loss": 1.3606, + "step": 3515 + }, + { + "epoch": 0.37, + "learning_rate": 1.591303498786106e-05, + "loss": 1.4382, + "step": 3516 + }, + { + "epoch": 0.37, + "learning_rate": 1.591008278638884e-05, + "loss": 1.4185, + "step": 3517 + }, + { + "epoch": 0.37, + "learning_rate": 1.5907129793117374e-05, + "loss": 1.6692, + "step": 3518 + }, + { + "epoch": 0.37, + "learning_rate": 1.59041760084423e-05, + "loss": 1.501, + "step": 3519 + }, + { + "epoch": 0.37, + "learning_rate": 1.5901221432759345e-05, + "loss": 1.5753, + "step": 3520 + }, + { + "epoch": 0.37, + "learning_rate": 1.589826606646434e-05, + "loss": 1.4795, + "step": 3521 + }, + { + "epoch": 0.37, + "learning_rate": 1.5895309909953236e-05, + "loss": 1.4379, + "step": 3522 + }, + { + "epoch": 0.37, + "learning_rate": 1.5892352963622078e-05, + "loss": 1.3426, + "step": 3523 + }, + { + "epoch": 0.37, + "learning_rate": 1.5889395227867025e-05, + "loss": 1.4048, + "step": 3524 + }, + { + "epoch": 0.37, + "learning_rate": 1.5886436703084332e-05, + "loss": 1.4303, + "step": 3525 + }, + { + "epoch": 0.37, + "learning_rate": 1.5883477389670367e-05, + "loss": 1.3684, + "step": 3526 + }, + { + "epoch": 0.37, + "learning_rate": 1.5880517288021602e-05, + "loss": 1.3701, + "step": 3527 + }, + { + "epoch": 0.37, + "learning_rate": 1.587755639853462e-05, + "loss": 1.4308, + "step": 3528 + }, + { + "epoch": 0.37, + "learning_rate": 1.5874594721606096e-05, + "loss": 1.3981, + "step": 3529 + }, + { + "epoch": 0.37, + "learning_rate": 1.5871632257632823e-05, + "loss": 1.5906, + "step": 3530 + }, + { + "epoch": 0.37, + "learning_rate": 1.5868669007011696e-05, + "loss": 1.4642, + "step": 3531 + }, + { + "epoch": 0.37, + "learning_rate": 1.586570497013971e-05, + "loss": 1.411, + "step": 3532 + }, + { + "epoch": 0.37, + "learning_rate": 1.586274014741397e-05, + "loss": 1.3942, + "step": 3533 + }, + { + "epoch": 0.37, + "learning_rate": 1.5859774539231693e-05, + "loss": 1.3952, + "step": 3534 + }, + { + "epoch": 0.37, + "learning_rate": 1.585680814599019e-05, + "loss": 1.4009, + "step": 3535 + }, + { + "epoch": 0.37, + "learning_rate": 1.585384096808688e-05, + "loss": 1.3238, + "step": 3536 + }, + { + "epoch": 0.37, + "learning_rate": 1.585087300591929e-05, + "loss": 1.346, + "step": 3537 + }, + { + "epoch": 0.37, + "learning_rate": 1.584790425988505e-05, + "loss": 1.3739, + "step": 3538 + }, + { + "epoch": 0.37, + "learning_rate": 1.5844934730381895e-05, + "loss": 1.4264, + "step": 3539 + }, + { + "epoch": 0.37, + "learning_rate": 1.5841964417807668e-05, + "loss": 1.4675, + "step": 3540 + }, + { + "epoch": 0.37, + "learning_rate": 1.5838993322560314e-05, + "loss": 1.3337, + "step": 3541 + }, + { + "epoch": 0.37, + "learning_rate": 1.5836021445037883e-05, + "loss": 1.4052, + "step": 3542 + }, + { + "epoch": 0.37, + "learning_rate": 1.583304878563853e-05, + "loss": 1.4311, + "step": 3543 + }, + { + "epoch": 0.37, + "learning_rate": 1.5830075344760513e-05, + "loss": 1.386, + "step": 3544 + }, + { + "epoch": 0.37, + "learning_rate": 1.58271011228022e-05, + "loss": 1.387, + "step": 3545 + }, + { + "epoch": 0.37, + "learning_rate": 1.582412612016206e-05, + "loss": 1.3601, + "step": 3546 + }, + { + "epoch": 0.37, + "learning_rate": 1.5821150337238663e-05, + "loss": 1.5111, + "step": 3547 + }, + { + "epoch": 0.37, + "learning_rate": 1.5818173774430697e-05, + "loss": 1.471, + "step": 3548 + }, + { + "epoch": 0.37, + "learning_rate": 1.581519643213693e-05, + "loss": 1.4442, + "step": 3549 + }, + { + "epoch": 0.37, + "learning_rate": 1.5812218310756263e-05, + "loss": 1.467, + "step": 3550 + }, + { + "epoch": 0.37, + "learning_rate": 1.5809239410687683e-05, + "loss": 1.3731, + "step": 3551 + }, + { + "epoch": 0.37, + "learning_rate": 1.5806259732330286e-05, + "loss": 1.4072, + "step": 3552 + }, + { + "epoch": 0.37, + "learning_rate": 1.5803279276083268e-05, + "loss": 1.3636, + "step": 3553 + }, + { + "epoch": 0.37, + "learning_rate": 1.5800298042345938e-05, + "loss": 1.3915, + "step": 3554 + }, + { + "epoch": 0.37, + "learning_rate": 1.5797316031517705e-05, + "loss": 1.5038, + "step": 3555 + }, + { + "epoch": 0.37, + "learning_rate": 1.5794333243998082e-05, + "loss": 1.4455, + "step": 3556 + }, + { + "epoch": 0.37, + "learning_rate": 1.5791349680186684e-05, + "loss": 1.5062, + "step": 3557 + }, + { + "epoch": 0.37, + "learning_rate": 1.5788365340483234e-05, + "loss": 1.3899, + "step": 3558 + }, + { + "epoch": 0.37, + "learning_rate": 1.5785380225287554e-05, + "loss": 1.4946, + "step": 3559 + }, + { + "epoch": 0.37, + "learning_rate": 1.5782394334999572e-05, + "loss": 1.3859, + "step": 3560 + }, + { + "epoch": 0.37, + "learning_rate": 1.577940767001933e-05, + "loss": 1.541, + "step": 3561 + }, + { + "epoch": 0.37, + "learning_rate": 1.5776420230746952e-05, + "loss": 1.4952, + "step": 3562 + }, + { + "epoch": 0.37, + "learning_rate": 1.5773432017582684e-05, + "loss": 1.6055, + "step": 3563 + }, + { + "epoch": 0.37, + "learning_rate": 1.577044303092687e-05, + "loss": 1.4661, + "step": 3564 + }, + { + "epoch": 0.37, + "learning_rate": 1.576745327117996e-05, + "loss": 1.4082, + "step": 3565 + }, + { + "epoch": 0.37, + "learning_rate": 1.5764462738742493e-05, + "loss": 1.4005, + "step": 3566 + }, + { + "epoch": 0.37, + "learning_rate": 1.5761471434015137e-05, + "loss": 1.3959, + "step": 3567 + }, + { + "epoch": 0.37, + "learning_rate": 1.5758479357398645e-05, + "loss": 1.4567, + "step": 3568 + }, + { + "epoch": 0.37, + "learning_rate": 1.575548650929388e-05, + "loss": 1.3791, + "step": 3569 + }, + { + "epoch": 0.37, + "learning_rate": 1.57524928901018e-05, + "loss": 1.4428, + "step": 3570 + }, + { + "epoch": 0.37, + "learning_rate": 1.5749498500223486e-05, + "loss": 1.3864, + "step": 3571 + }, + { + "epoch": 0.37, + "learning_rate": 1.5746503340060097e-05, + "loss": 1.4019, + "step": 3572 + }, + { + "epoch": 0.37, + "learning_rate": 1.574350741001291e-05, + "loss": 1.5436, + "step": 3573 + }, + { + "epoch": 0.37, + "learning_rate": 1.5740510710483308e-05, + "loss": 1.4637, + "step": 3574 + }, + { + "epoch": 0.37, + "learning_rate": 1.5737513241872767e-05, + "loss": 1.5097, + "step": 3575 + }, + { + "epoch": 0.38, + "learning_rate": 1.5734515004582873e-05, + "loss": 1.5143, + "step": 3576 + }, + { + "epoch": 0.38, + "learning_rate": 1.5731515999015315e-05, + "loss": 1.3926, + "step": 3577 + }, + { + "epoch": 0.38, + "learning_rate": 1.5728516225571874e-05, + "loss": 1.4242, + "step": 3578 + }, + { + "epoch": 0.38, + "learning_rate": 1.5725515684654453e-05, + "loss": 1.4429, + "step": 3579 + }, + { + "epoch": 0.38, + "learning_rate": 1.572251437666504e-05, + "loss": 1.4638, + "step": 3580 + }, + { + "epoch": 0.38, + "learning_rate": 1.5719512302005735e-05, + "loss": 1.3381, + "step": 3581 + }, + { + "epoch": 0.38, + "learning_rate": 1.571650946107874e-05, + "loss": 1.4342, + "step": 3582 + }, + { + "epoch": 0.38, + "eval_loss": 1.4705015420913696, + "eval_runtime": 77.3664, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3582 + }, + { + "epoch": 0.38, + "learning_rate": 1.571350585428636e-05, + "loss": 1.3991, + "step": 3583 + }, + { + "epoch": 0.38, + "learning_rate": 1.5710501482030998e-05, + "loss": 1.4274, + "step": 3584 + }, + { + "epoch": 0.38, + "learning_rate": 1.5707496344715166e-05, + "loss": 1.438, + "step": 3585 + }, + { + "epoch": 0.38, + "learning_rate": 1.570449044274147e-05, + "loss": 1.4453, + "step": 3586 + }, + { + "epoch": 0.38, + "learning_rate": 1.570148377651263e-05, + "loss": 1.4022, + "step": 3587 + }, + { + "epoch": 0.38, + "learning_rate": 1.5698476346431454e-05, + "loss": 1.4312, + "step": 3588 + }, + { + "epoch": 0.38, + "learning_rate": 1.569546815290087e-05, + "loss": 1.4329, + "step": 3589 + }, + { + "epoch": 0.38, + "learning_rate": 1.569245919632389e-05, + "loss": 1.4036, + "step": 3590 + }, + { + "epoch": 0.38, + "learning_rate": 1.5689449477103644e-05, + "loss": 1.412, + "step": 3591 + }, + { + "epoch": 0.38, + "learning_rate": 1.5686438995643353e-05, + "loss": 1.4492, + "step": 3592 + }, + { + "epoch": 0.38, + "learning_rate": 1.5683427752346343e-05, + "loss": 1.4555, + "step": 3593 + }, + { + "epoch": 0.38, + "learning_rate": 1.5680415747616047e-05, + "loss": 1.5594, + "step": 3594 + }, + { + "epoch": 0.38, + "learning_rate": 1.5677402981855993e-05, + "loss": 1.4813, + "step": 3595 + }, + { + "epoch": 0.38, + "learning_rate": 1.567438945546982e-05, + "loss": 1.5919, + "step": 3596 + }, + { + "epoch": 0.38, + "learning_rate": 1.5671375168861255e-05, + "loss": 1.4235, + "step": 3597 + }, + { + "epoch": 0.38, + "learning_rate": 1.5668360122434135e-05, + "loss": 1.441, + "step": 3598 + }, + { + "epoch": 0.38, + "learning_rate": 1.566534431659241e-05, + "loss": 1.5847, + "step": 3599 + }, + { + "epoch": 0.38, + "learning_rate": 1.566232775174011e-05, + "loss": 1.6123, + "step": 3600 + }, + { + "epoch": 0.38, + "learning_rate": 1.5659310428281374e-05, + "loss": 1.4916, + "step": 3601 + }, + { + "epoch": 0.38, + "learning_rate": 1.5656292346620457e-05, + "loss": 1.4603, + "step": 3602 + }, + { + "epoch": 0.38, + "learning_rate": 1.56532735071617e-05, + "loss": 1.4423, + "step": 3603 + }, + { + "epoch": 0.38, + "learning_rate": 1.5650253910309547e-05, + "loss": 1.4814, + "step": 3604 + }, + { + "epoch": 0.38, + "learning_rate": 1.5647233556468552e-05, + "loss": 1.4015, + "step": 3605 + }, + { + "epoch": 0.38, + "learning_rate": 1.564421244604336e-05, + "loss": 1.3798, + "step": 3606 + }, + { + "epoch": 0.38, + "learning_rate": 1.5641190579438723e-05, + "loss": 1.4259, + "step": 3607 + }, + { + "epoch": 0.38, + "learning_rate": 1.5638167957059493e-05, + "loss": 1.3493, + "step": 3608 + }, + { + "epoch": 0.38, + "learning_rate": 1.5635144579310626e-05, + "loss": 1.3433, + "step": 3609 + }, + { + "epoch": 0.38, + "learning_rate": 1.5632120446597177e-05, + "loss": 1.4661, + "step": 3610 + }, + { + "epoch": 0.38, + "learning_rate": 1.5629095559324297e-05, + "loss": 1.4205, + "step": 3611 + }, + { + "epoch": 0.38, + "learning_rate": 1.562606991789725e-05, + "loss": 1.3976, + "step": 3612 + }, + { + "epoch": 0.38, + "learning_rate": 1.5623043522721393e-05, + "loss": 1.4261, + "step": 3613 + }, + { + "epoch": 0.38, + "learning_rate": 1.562001637420218e-05, + "loss": 1.4358, + "step": 3614 + }, + { + "epoch": 0.38, + "learning_rate": 1.5616988472745175e-05, + "loss": 1.437, + "step": 3615 + }, + { + "epoch": 0.38, + "learning_rate": 1.561395981875604e-05, + "loss": 1.3735, + "step": 3616 + }, + { + "epoch": 0.38, + "learning_rate": 1.5610930412640532e-05, + "loss": 1.4357, + "step": 3617 + }, + { + "epoch": 0.38, + "learning_rate": 1.560790025480452e-05, + "loss": 1.4003, + "step": 3618 + }, + { + "epoch": 0.38, + "learning_rate": 1.5604869345653965e-05, + "loss": 1.4127, + "step": 3619 + }, + { + "epoch": 0.38, + "learning_rate": 1.5601837685594927e-05, + "loss": 1.4666, + "step": 3620 + }, + { + "epoch": 0.38, + "learning_rate": 1.5598805275033574e-05, + "loss": 1.4106, + "step": 3621 + }, + { + "epoch": 0.38, + "learning_rate": 1.5595772114376174e-05, + "loss": 1.3857, + "step": 3622 + }, + { + "epoch": 0.38, + "learning_rate": 1.5592738204029086e-05, + "loss": 1.4704, + "step": 3623 + }, + { + "epoch": 0.38, + "learning_rate": 1.558970354439878e-05, + "loss": 1.4649, + "step": 3624 + }, + { + "epoch": 0.38, + "learning_rate": 1.5586668135891824e-05, + "loss": 1.4812, + "step": 3625 + }, + { + "epoch": 0.38, + "learning_rate": 1.5583631978914882e-05, + "loss": 1.3507, + "step": 3626 + }, + { + "epoch": 0.38, + "learning_rate": 1.5580595073874718e-05, + "loss": 1.3762, + "step": 3627 + }, + { + "epoch": 0.38, + "learning_rate": 1.557755742117821e-05, + "loss": 1.4169, + "step": 3628 + }, + { + "epoch": 0.38, + "learning_rate": 1.557451902123231e-05, + "loss": 1.4098, + "step": 3629 + }, + { + "epoch": 0.38, + "learning_rate": 1.55714798744441e-05, + "loss": 1.5526, + "step": 3630 + }, + { + "epoch": 0.38, + "learning_rate": 1.556843998122074e-05, + "loss": 1.4414, + "step": 3631 + }, + { + "epoch": 0.38, + "learning_rate": 1.5565399341969497e-05, + "loss": 1.4134, + "step": 3632 + }, + { + "epoch": 0.38, + "learning_rate": 1.556235795709774e-05, + "loss": 1.4718, + "step": 3633 + }, + { + "epoch": 0.38, + "learning_rate": 1.5559315827012937e-05, + "loss": 1.412, + "step": 3634 + }, + { + "epoch": 0.38, + "learning_rate": 1.5556272952122657e-05, + "loss": 1.4119, + "step": 3635 + }, + { + "epoch": 0.38, + "learning_rate": 1.5553229332834564e-05, + "loss": 1.3999, + "step": 3636 + }, + { + "epoch": 0.38, + "learning_rate": 1.5550184969556428e-05, + "loss": 1.4626, + "step": 3637 + }, + { + "epoch": 0.38, + "learning_rate": 1.5547139862696113e-05, + "loss": 1.3811, + "step": 3638 + }, + { + "epoch": 0.38, + "learning_rate": 1.5544094012661583e-05, + "loss": 1.4053, + "step": 3639 + }, + { + "epoch": 0.38, + "learning_rate": 1.5541047419860907e-05, + "loss": 1.4059, + "step": 3640 + }, + { + "epoch": 0.38, + "learning_rate": 1.553800008470225e-05, + "loss": 1.4717, + "step": 3641 + }, + { + "epoch": 0.38, + "learning_rate": 1.553495200759388e-05, + "loss": 1.399, + "step": 3642 + }, + { + "epoch": 0.38, + "learning_rate": 1.5531903188944154e-05, + "loss": 1.4143, + "step": 3643 + }, + { + "epoch": 0.38, + "learning_rate": 1.5528853629161536e-05, + "loss": 1.4414, + "step": 3644 + }, + { + "epoch": 0.38, + "learning_rate": 1.5525803328654592e-05, + "loss": 1.4206, + "step": 3645 + }, + { + "epoch": 0.38, + "learning_rate": 1.5522752287831982e-05, + "loss": 1.3869, + "step": 3646 + }, + { + "epoch": 0.38, + "learning_rate": 1.551970050710247e-05, + "loss": 1.5434, + "step": 3647 + }, + { + "epoch": 0.38, + "learning_rate": 1.5516647986874914e-05, + "loss": 1.4574, + "step": 3648 + }, + { + "epoch": 0.38, + "learning_rate": 1.5513594727558273e-05, + "loss": 1.4353, + "step": 3649 + }, + { + "epoch": 0.38, + "learning_rate": 1.5510540729561606e-05, + "loss": 1.4122, + "step": 3650 + }, + { + "epoch": 0.38, + "learning_rate": 1.550748599329407e-05, + "loss": 1.4077, + "step": 3651 + }, + { + "epoch": 0.38, + "learning_rate": 1.550443051916492e-05, + "loss": 1.4433, + "step": 3652 + }, + { + "epoch": 0.38, + "learning_rate": 1.5501374307583514e-05, + "loss": 1.54, + "step": 3653 + }, + { + "epoch": 0.38, + "learning_rate": 1.5498317358959302e-05, + "loss": 1.4522, + "step": 3654 + }, + { + "epoch": 0.38, + "learning_rate": 1.5495259673701842e-05, + "loss": 1.4175, + "step": 3655 + }, + { + "epoch": 0.38, + "learning_rate": 1.5492201252220777e-05, + "loss": 1.4637, + "step": 3656 + }, + { + "epoch": 0.38, + "learning_rate": 1.5489142094925863e-05, + "loss": 1.4701, + "step": 3657 + }, + { + "epoch": 0.38, + "learning_rate": 1.548608220222695e-05, + "loss": 1.4095, + "step": 3658 + }, + { + "epoch": 0.38, + "learning_rate": 1.548302157453398e-05, + "loss": 1.3903, + "step": 3659 + }, + { + "epoch": 0.38, + "learning_rate": 1.5479960212257002e-05, + "loss": 1.4062, + "step": 3660 + }, + { + "epoch": 0.38, + "learning_rate": 1.5476898115806157e-05, + "loss": 1.4706, + "step": 3661 + }, + { + "epoch": 0.38, + "learning_rate": 1.547383528559169e-05, + "loss": 1.4423, + "step": 3662 + }, + { + "epoch": 0.38, + "learning_rate": 1.547077172202394e-05, + "loss": 1.4418, + "step": 3663 + }, + { + "epoch": 0.38, + "learning_rate": 1.5467707425513347e-05, + "loss": 1.4553, + "step": 3664 + }, + { + "epoch": 0.38, + "learning_rate": 1.5464642396470443e-05, + "loss": 1.435, + "step": 3665 + }, + { + "epoch": 0.38, + "learning_rate": 1.5461576635305873e-05, + "loss": 1.4105, + "step": 3666 + }, + { + "epoch": 0.38, + "learning_rate": 1.5458510142430364e-05, + "loss": 1.4118, + "step": 3667 + }, + { + "epoch": 0.38, + "learning_rate": 1.5455442918254746e-05, + "loss": 1.4096, + "step": 3668 + }, + { + "epoch": 0.38, + "learning_rate": 1.545237496318995e-05, + "loss": 1.4248, + "step": 3669 + }, + { + "epoch": 0.38, + "learning_rate": 1.5449306277647003e-05, + "loss": 1.4591, + "step": 3670 + }, + { + "epoch": 0.38, + "learning_rate": 1.544623686203703e-05, + "loss": 1.4764, + "step": 3671 + }, + { + "epoch": 0.39, + "learning_rate": 1.5443166716771255e-05, + "loss": 1.4329, + "step": 3672 + }, + { + "epoch": 0.39, + "learning_rate": 1.5440095842260995e-05, + "loss": 1.4023, + "step": 3673 + }, + { + "epoch": 0.39, + "learning_rate": 1.5437024238917674e-05, + "loss": 1.3802, + "step": 3674 + }, + { + "epoch": 0.39, + "learning_rate": 1.5433951907152806e-05, + "loss": 1.4627, + "step": 3675 + }, + { + "epoch": 0.39, + "learning_rate": 1.5430878847378e-05, + "loss": 1.5164, + "step": 3676 + }, + { + "epoch": 0.39, + "learning_rate": 1.542780506000497e-05, + "loss": 1.3546, + "step": 3677 + }, + { + "epoch": 0.39, + "learning_rate": 1.542473054544553e-05, + "loss": 1.4415, + "step": 3678 + }, + { + "epoch": 0.39, + "learning_rate": 1.5421655304111573e-05, + "loss": 1.4093, + "step": 3679 + }, + { + "epoch": 0.39, + "learning_rate": 1.5418579336415114e-05, + "loss": 1.3943, + "step": 3680 + }, + { + "epoch": 0.39, + "learning_rate": 1.5415502642768252e-05, + "loss": 1.3659, + "step": 3681 + }, + { + "epoch": 0.39, + "learning_rate": 1.541242522358318e-05, + "loss": 1.4322, + "step": 3682 + }, + { + "epoch": 0.39, + "learning_rate": 1.5409347079272198e-05, + "loss": 1.4064, + "step": 3683 + }, + { + "epoch": 0.39, + "learning_rate": 1.5406268210247693e-05, + "loss": 1.4031, + "step": 3684 + }, + { + "epoch": 0.39, + "learning_rate": 1.540318861692216e-05, + "loss": 1.3449, + "step": 3685 + }, + { + "epoch": 0.39, + "learning_rate": 1.5400108299708182e-05, + "loss": 1.5536, + "step": 3686 + }, + { + "epoch": 0.39, + "learning_rate": 1.5397027259018442e-05, + "loss": 1.4106, + "step": 3687 + }, + { + "epoch": 0.39, + "learning_rate": 1.5393945495265722e-05, + "loss": 1.4309, + "step": 3688 + }, + { + "epoch": 0.39, + "learning_rate": 1.53908630088629e-05, + "loss": 1.3765, + "step": 3689 + }, + { + "epoch": 0.39, + "learning_rate": 1.5387779800222947e-05, + "loss": 1.3809, + "step": 3690 + }, + { + "epoch": 0.39, + "learning_rate": 1.5384695869758938e-05, + "loss": 1.4758, + "step": 3691 + }, + { + "epoch": 0.39, + "learning_rate": 1.5381611217884032e-05, + "loss": 1.4249, + "step": 3692 + }, + { + "epoch": 0.39, + "learning_rate": 1.5378525845011503e-05, + "loss": 1.4133, + "step": 3693 + }, + { + "epoch": 0.39, + "learning_rate": 1.5375439751554708e-05, + "loss": 1.418, + "step": 3694 + }, + { + "epoch": 0.39, + "learning_rate": 1.53723529379271e-05, + "loss": 1.441, + "step": 3695 + }, + { + "epoch": 0.39, + "learning_rate": 1.536926540454224e-05, + "loss": 1.3919, + "step": 3696 + }, + { + "epoch": 0.39, + "learning_rate": 1.5366177151813775e-05, + "loss": 1.3722, + "step": 3697 + }, + { + "epoch": 0.39, + "learning_rate": 1.536308818015545e-05, + "loss": 1.4727, + "step": 3698 + }, + { + "epoch": 0.39, + "learning_rate": 1.535999848998111e-05, + "loss": 1.442, + "step": 3699 + }, + { + "epoch": 0.39, + "learning_rate": 1.535690808170469e-05, + "loss": 1.3884, + "step": 3700 + }, + { + "epoch": 0.39, + "learning_rate": 1.535381695574023e-05, + "loss": 1.3226, + "step": 3701 + }, + { + "epoch": 0.39, + "learning_rate": 1.535072511250186e-05, + "loss": 1.4403, + "step": 3702 + }, + { + "epoch": 0.39, + "learning_rate": 1.5347632552403808e-05, + "loss": 1.4144, + "step": 3703 + }, + { + "epoch": 0.39, + "learning_rate": 1.5344539275860395e-05, + "loss": 1.3514, + "step": 3704 + }, + { + "epoch": 0.39, + "learning_rate": 1.5341445283286044e-05, + "loss": 1.519, + "step": 3705 + }, + { + "epoch": 0.39, + "learning_rate": 1.5338350575095268e-05, + "loss": 1.4251, + "step": 3706 + }, + { + "epoch": 0.39, + "learning_rate": 1.5335255151702685e-05, + "loss": 1.392, + "step": 3707 + }, + { + "epoch": 0.39, + "learning_rate": 1.533215901352299e-05, + "loss": 1.3838, + "step": 3708 + }, + { + "epoch": 0.39, + "learning_rate": 1.532906216097099e-05, + "loss": 1.444, + "step": 3709 + }, + { + "epoch": 0.39, + "learning_rate": 1.5325964594461594e-05, + "loss": 1.3459, + "step": 3710 + }, + { + "epoch": 0.39, + "learning_rate": 1.5322866314409783e-05, + "loss": 1.4155, + "step": 3711 + }, + { + "epoch": 0.39, + "learning_rate": 1.5319767321230657e-05, + "loss": 1.4057, + "step": 3712 + }, + { + "epoch": 0.39, + "learning_rate": 1.5316667615339392e-05, + "loss": 1.382, + "step": 3713 + }, + { + "epoch": 0.39, + "learning_rate": 1.5313567197151277e-05, + "loss": 1.3634, + "step": 3714 + }, + { + "epoch": 0.39, + "learning_rate": 1.5310466067081688e-05, + "loss": 1.3434, + "step": 3715 + }, + { + "epoch": 0.39, + "learning_rate": 1.530736422554609e-05, + "loss": 1.4553, + "step": 3716 + }, + { + "epoch": 0.39, + "learning_rate": 1.5304261672960055e-05, + "loss": 1.4193, + "step": 3717 + }, + { + "epoch": 0.39, + "learning_rate": 1.5301158409739242e-05, + "loss": 1.3955, + "step": 3718 + }, + { + "epoch": 0.39, + "learning_rate": 1.5298054436299413e-05, + "loss": 1.4592, + "step": 3719 + }, + { + "epoch": 0.39, + "learning_rate": 1.529494975305642e-05, + "loss": 1.738, + "step": 3720 + }, + { + "epoch": 0.39, + "learning_rate": 1.529184436042621e-05, + "loss": 1.438, + "step": 3721 + }, + { + "epoch": 0.39, + "learning_rate": 1.528873825882482e-05, + "loss": 1.3445, + "step": 3722 + }, + { + "epoch": 0.39, + "learning_rate": 1.5285631448668395e-05, + "loss": 1.4168, + "step": 3723 + }, + { + "epoch": 0.39, + "learning_rate": 1.528252393037317e-05, + "loss": 1.4088, + "step": 3724 + }, + { + "epoch": 0.39, + "learning_rate": 1.5279415704355468e-05, + "loss": 1.4484, + "step": 3725 + }, + { + "epoch": 0.39, + "learning_rate": 1.5276306771031708e-05, + "loss": 1.4706, + "step": 3726 + }, + { + "epoch": 0.39, + "learning_rate": 1.527319713081841e-05, + "loss": 1.3466, + "step": 3727 + }, + { + "epoch": 0.39, + "learning_rate": 1.5270086784132196e-05, + "loss": 1.427, + "step": 3728 + }, + { + "epoch": 0.39, + "learning_rate": 1.5266975731389754e-05, + "loss": 1.4596, + "step": 3729 + }, + { + "epoch": 0.39, + "learning_rate": 1.52638639730079e-05, + "loss": 1.405, + "step": 3730 + }, + { + "epoch": 0.39, + "learning_rate": 1.5260751509403518e-05, + "loss": 1.4572, + "step": 3731 + }, + { + "epoch": 0.39, + "learning_rate": 1.5257638340993608e-05, + "loss": 1.3827, + "step": 3732 + }, + { + "epoch": 0.39, + "learning_rate": 1.5254524468195251e-05, + "loss": 1.3712, + "step": 3733 + }, + { + "epoch": 0.39, + "learning_rate": 1.5251409891425626e-05, + "loss": 1.4541, + "step": 3734 + }, + { + "epoch": 0.39, + "learning_rate": 1.5248294611102006e-05, + "loss": 1.5279, + "step": 3735 + }, + { + "epoch": 0.39, + "learning_rate": 1.5245178627641759e-05, + "loss": 1.3722, + "step": 3736 + }, + { + "epoch": 0.39, + "learning_rate": 1.5242061941462348e-05, + "loss": 1.5158, + "step": 3737 + }, + { + "epoch": 0.39, + "learning_rate": 1.523894455298132e-05, + "loss": 1.4274, + "step": 3738 + }, + { + "epoch": 0.39, + "learning_rate": 1.5235826462616338e-05, + "loss": 1.4543, + "step": 3739 + }, + { + "epoch": 0.39, + "learning_rate": 1.5232707670785144e-05, + "loss": 1.5011, + "step": 3740 + }, + { + "epoch": 0.39, + "learning_rate": 1.5229588177905568e-05, + "loss": 1.24, + "step": 3741 + }, + { + "epoch": 0.39, + "learning_rate": 1.5226467984395544e-05, + "loss": 1.4253, + "step": 3742 + }, + { + "epoch": 0.39, + "learning_rate": 1.5223347090673102e-05, + "loss": 1.3736, + "step": 3743 + }, + { + "epoch": 0.39, + "learning_rate": 1.522022549715636e-05, + "loss": 1.4587, + "step": 3744 + }, + { + "epoch": 0.39, + "learning_rate": 1.521710320426353e-05, + "loss": 1.5024, + "step": 3745 + }, + { + "epoch": 0.39, + "learning_rate": 1.521398021241292e-05, + "loss": 1.427, + "step": 3746 + }, + { + "epoch": 0.39, + "learning_rate": 1.5210856522022929e-05, + "loss": 1.3387, + "step": 3747 + }, + { + "epoch": 0.39, + "learning_rate": 1.5207732133512055e-05, + "loss": 1.3819, + "step": 3748 + }, + { + "epoch": 0.39, + "learning_rate": 1.5204607047298883e-05, + "loss": 1.4571, + "step": 3749 + }, + { + "epoch": 0.39, + "learning_rate": 1.5201481263802094e-05, + "loss": 1.3592, + "step": 3750 + }, + { + "epoch": 0.39, + "learning_rate": 1.5198354783440464e-05, + "loss": 1.3912, + "step": 3751 + }, + { + "epoch": 0.39, + "learning_rate": 1.519522760663286e-05, + "loss": 1.4986, + "step": 3752 + }, + { + "epoch": 0.39, + "learning_rate": 1.5192099733798243e-05, + "loss": 1.4106, + "step": 3753 + }, + { + "epoch": 0.39, + "learning_rate": 1.5188971165355667e-05, + "loss": 1.4145, + "step": 3754 + }, + { + "epoch": 0.39, + "learning_rate": 1.5185841901724282e-05, + "loss": 1.3915, + "step": 3755 + }, + { + "epoch": 0.39, + "learning_rate": 1.5182711943323329e-05, + "loss": 1.4014, + "step": 3756 + }, + { + "epoch": 0.39, + "learning_rate": 1.5179581290572141e-05, + "loss": 1.3651, + "step": 3757 + }, + { + "epoch": 0.39, + "learning_rate": 1.5176449943890147e-05, + "loss": 1.3653, + "step": 3758 + }, + { + "epoch": 0.39, + "learning_rate": 1.5173317903696862e-05, + "loss": 1.4486, + "step": 3759 + }, + { + "epoch": 0.39, + "learning_rate": 1.5170185170411906e-05, + "loss": 1.4459, + "step": 3760 + }, + { + "epoch": 0.39, + "learning_rate": 1.5167051744454977e-05, + "loss": 1.4215, + "step": 3761 + }, + { + "epoch": 0.39, + "learning_rate": 1.5163917626245877e-05, + "loss": 1.4379, + "step": 3762 + }, + { + "epoch": 0.39, + "learning_rate": 1.51607828162045e-05, + "loss": 1.4147, + "step": 3763 + }, + { + "epoch": 0.39, + "learning_rate": 1.5157647314750827e-05, + "loss": 1.4011, + "step": 3764 + }, + { + "epoch": 0.39, + "learning_rate": 1.5154511122304936e-05, + "loss": 1.4309, + "step": 3765 + }, + { + "epoch": 0.39, + "learning_rate": 1.5151374239286993e-05, + "loss": 1.4382, + "step": 3766 + }, + { + "epoch": 0.4, + "learning_rate": 1.5148236666117266e-05, + "loss": 1.405, + "step": 3767 + }, + { + "epoch": 0.4, + "learning_rate": 1.5145098403216104e-05, + "loss": 1.4223, + "step": 3768 + }, + { + "epoch": 0.4, + "learning_rate": 1.5141959451003951e-05, + "loss": 1.4084, + "step": 3769 + }, + { + "epoch": 0.4, + "learning_rate": 1.5138819809901356e-05, + "loss": 1.4063, + "step": 3770 + }, + { + "epoch": 0.4, + "learning_rate": 1.513567948032894e-05, + "loss": 1.3299, + "step": 3771 + }, + { + "epoch": 0.4, + "learning_rate": 1.5132538462707431e-05, + "loss": 1.3901, + "step": 3772 + }, + { + "epoch": 0.4, + "learning_rate": 1.5129396757457646e-05, + "loss": 1.4249, + "step": 3773 + }, + { + "epoch": 0.4, + "learning_rate": 1.512625436500049e-05, + "loss": 1.4087, + "step": 3774 + }, + { + "epoch": 0.4, + "learning_rate": 1.5123111285756964e-05, + "loss": 1.3521, + "step": 3775 + }, + { + "epoch": 0.4, + "learning_rate": 1.5119967520148163e-05, + "loss": 1.4097, + "step": 3776 + }, + { + "epoch": 0.4, + "learning_rate": 1.5116823068595261e-05, + "loss": 1.4871, + "step": 3777 + }, + { + "epoch": 0.4, + "learning_rate": 1.5113677931519543e-05, + "loss": 1.44, + "step": 3778 + }, + { + "epoch": 0.4, + "learning_rate": 1.5110532109342377e-05, + "loss": 1.4518, + "step": 3779 + }, + { + "epoch": 0.4, + "learning_rate": 1.5107385602485214e-05, + "loss": 1.3961, + "step": 3780 + }, + { + "epoch": 0.4, + "learning_rate": 1.5104238411369614e-05, + "loss": 1.4341, + "step": 3781 + }, + { + "epoch": 0.4, + "eval_loss": 1.4642821550369263, + "eval_runtime": 77.3595, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 3781 + }, + { + "epoch": 0.4, + "learning_rate": 1.5101090536417218e-05, + "loss": 1.403, + "step": 3782 + }, + { + "epoch": 0.4, + "learning_rate": 1.5097941978049754e-05, + "loss": 1.4103, + "step": 3783 + }, + { + "epoch": 0.4, + "learning_rate": 1.5094792736689052e-05, + "loss": 1.3478, + "step": 3784 + }, + { + "epoch": 0.4, + "learning_rate": 1.5091642812757035e-05, + "loss": 1.4134, + "step": 3785 + }, + { + "epoch": 0.4, + "learning_rate": 1.5088492206675701e-05, + "loss": 1.4134, + "step": 3786 + }, + { + "epoch": 0.4, + "learning_rate": 1.5085340918867162e-05, + "loss": 1.1494, + "step": 3787 + }, + { + "epoch": 0.4, + "learning_rate": 1.5082188949753598e-05, + "loss": 1.2385, + "step": 3788 + }, + { + "epoch": 0.4, + "learning_rate": 1.5079036299757299e-05, + "loss": 1.4258, + "step": 3789 + }, + { + "epoch": 0.4, + "learning_rate": 1.5075882969300639e-05, + "loss": 1.3781, + "step": 3790 + }, + { + "epoch": 0.4, + "learning_rate": 1.507272895880608e-05, + "loss": 1.5096, + "step": 3791 + }, + { + "epoch": 0.4, + "learning_rate": 1.5069574268696179e-05, + "loss": 1.366, + "step": 3792 + }, + { + "epoch": 0.4, + "learning_rate": 1.5066418899393584e-05, + "loss": 1.3792, + "step": 3793 + }, + { + "epoch": 0.4, + "learning_rate": 1.506326285132104e-05, + "loss": 1.4987, + "step": 3794 + }, + { + "epoch": 0.4, + "learning_rate": 1.5060106124901364e-05, + "loss": 1.445, + "step": 3795 + }, + { + "epoch": 0.4, + "learning_rate": 1.5056948720557482e-05, + "loss": 1.5071, + "step": 3796 + }, + { + "epoch": 0.4, + "learning_rate": 1.505379063871241e-05, + "loss": 1.4029, + "step": 3797 + }, + { + "epoch": 0.4, + "learning_rate": 1.5050631879789244e-05, + "loss": 1.5263, + "step": 3798 + }, + { + "epoch": 0.4, + "learning_rate": 1.5047472444211175e-05, + "loss": 1.3906, + "step": 3799 + }, + { + "epoch": 0.4, + "learning_rate": 1.5044312332401494e-05, + "loss": 1.7352, + "step": 3800 + }, + { + "epoch": 0.4, + "learning_rate": 1.5041151544783565e-05, + "loss": 1.3946, + "step": 3801 + }, + { + "epoch": 0.4, + "learning_rate": 1.5037990081780862e-05, + "loss": 1.3592, + "step": 3802 + }, + { + "epoch": 0.4, + "learning_rate": 1.503482794381693e-05, + "loss": 1.3991, + "step": 3803 + }, + { + "epoch": 0.4, + "learning_rate": 1.5031665131315423e-05, + "loss": 1.4271, + "step": 3804 + }, + { + "epoch": 0.4, + "learning_rate": 1.502850164470007e-05, + "loss": 1.4305, + "step": 3805 + }, + { + "epoch": 0.4, + "learning_rate": 1.5025337484394701e-05, + "loss": 1.4116, + "step": 3806 + }, + { + "epoch": 0.4, + "learning_rate": 1.5022172650823232e-05, + "loss": 1.4242, + "step": 3807 + }, + { + "epoch": 0.4, + "learning_rate": 1.5019007144409667e-05, + "loss": 1.4427, + "step": 3808 + }, + { + "epoch": 0.4, + "learning_rate": 1.5015840965578106e-05, + "loss": 1.3705, + "step": 3809 + }, + { + "epoch": 0.4, + "learning_rate": 1.5012674114752732e-05, + "loss": 1.4498, + "step": 3810 + }, + { + "epoch": 0.4, + "learning_rate": 1.5009506592357822e-05, + "loss": 1.489, + "step": 3811 + }, + { + "epoch": 0.4, + "learning_rate": 1.5006338398817746e-05, + "loss": 1.4801, + "step": 3812 + }, + { + "epoch": 0.4, + "learning_rate": 1.5003169534556956e-05, + "loss": 1.3468, + "step": 3813 + }, + { + "epoch": 0.4, + "learning_rate": 1.5000000000000002e-05, + "loss": 1.4211, + "step": 3814 + }, + { + "epoch": 0.4, + "learning_rate": 1.4996829795571518e-05, + "loss": 1.4683, + "step": 3815 + }, + { + "epoch": 0.4, + "learning_rate": 1.499365892169623e-05, + "loss": 1.4441, + "step": 3816 + }, + { + "epoch": 0.4, + "learning_rate": 1.4990487378798958e-05, + "loss": 1.4368, + "step": 3817 + }, + { + "epoch": 0.4, + "learning_rate": 1.4987315167304602e-05, + "loss": 1.4097, + "step": 3818 + }, + { + "epoch": 0.4, + "learning_rate": 1.4984142287638155e-05, + "loss": 1.4238, + "step": 3819 + }, + { + "epoch": 0.4, + "learning_rate": 1.4980968740224708e-05, + "loss": 1.497, + "step": 3820 + }, + { + "epoch": 0.4, + "learning_rate": 1.4977794525489433e-05, + "loss": 1.3989, + "step": 3821 + }, + { + "epoch": 0.4, + "learning_rate": 1.4974619643857588e-05, + "loss": 1.4415, + "step": 3822 + }, + { + "epoch": 0.4, + "learning_rate": 1.4971444095754533e-05, + "loss": 1.3931, + "step": 3823 + }, + { + "epoch": 0.4, + "learning_rate": 1.4968267881605705e-05, + "loss": 1.3426, + "step": 3824 + }, + { + "epoch": 0.4, + "learning_rate": 1.4965091001836636e-05, + "loss": 1.644, + "step": 3825 + }, + { + "epoch": 0.4, + "learning_rate": 1.4961913456872945e-05, + "loss": 1.3903, + "step": 3826 + }, + { + "epoch": 0.4, + "learning_rate": 1.4958735247140345e-05, + "loss": 1.3764, + "step": 3827 + }, + { + "epoch": 0.4, + "learning_rate": 1.4955556373064632e-05, + "loss": 1.5484, + "step": 3828 + }, + { + "epoch": 0.4, + "learning_rate": 1.4952376835071696e-05, + "loss": 1.5696, + "step": 3829 + }, + { + "epoch": 0.4, + "learning_rate": 1.4949196633587509e-05, + "loss": 1.3844, + "step": 3830 + }, + { + "epoch": 0.4, + "learning_rate": 1.494601576903814e-05, + "loss": 1.3868, + "step": 3831 + }, + { + "epoch": 0.4, + "learning_rate": 1.4942834241849741e-05, + "loss": 1.4229, + "step": 3832 + }, + { + "epoch": 0.4, + "learning_rate": 1.4939652052448557e-05, + "loss": 1.4062, + "step": 3833 + }, + { + "epoch": 0.4, + "learning_rate": 1.4936469201260915e-05, + "loss": 1.3955, + "step": 3834 + }, + { + "epoch": 0.4, + "learning_rate": 1.4933285688713239e-05, + "loss": 1.3959, + "step": 3835 + }, + { + "epoch": 0.4, + "learning_rate": 1.4930101515232038e-05, + "loss": 1.4652, + "step": 3836 + }, + { + "epoch": 0.4, + "learning_rate": 1.4926916681243913e-05, + "loss": 1.5253, + "step": 3837 + }, + { + "epoch": 0.4, + "learning_rate": 1.4923731187175539e-05, + "loss": 1.4694, + "step": 3838 + }, + { + "epoch": 0.4, + "learning_rate": 1.4920545033453702e-05, + "loss": 1.3859, + "step": 3839 + }, + { + "epoch": 0.4, + "learning_rate": 1.4917358220505259e-05, + "loss": 1.4157, + "step": 3840 + }, + { + "epoch": 0.4, + "learning_rate": 1.4914170748757159e-05, + "loss": 1.4491, + "step": 3841 + }, + { + "epoch": 0.4, + "learning_rate": 1.4910982618636445e-05, + "loss": 1.4464, + "step": 3842 + }, + { + "epoch": 0.4, + "learning_rate": 1.4907793830570246e-05, + "loss": 1.3771, + "step": 3843 + }, + { + "epoch": 0.4, + "learning_rate": 1.4904604384985775e-05, + "loss": 1.3673, + "step": 3844 + }, + { + "epoch": 0.4, + "learning_rate": 1.4901414282310334e-05, + "loss": 1.4429, + "step": 3845 + }, + { + "epoch": 0.4, + "learning_rate": 1.4898223522971318e-05, + "loss": 1.4905, + "step": 3846 + }, + { + "epoch": 0.4, + "learning_rate": 1.4895032107396205e-05, + "loss": 1.4039, + "step": 3847 + }, + { + "epoch": 0.4, + "learning_rate": 1.4891840036012566e-05, + "loss": 1.4082, + "step": 3848 + }, + { + "epoch": 0.4, + "learning_rate": 1.4888647309248052e-05, + "loss": 1.3643, + "step": 3849 + }, + { + "epoch": 0.4, + "learning_rate": 1.4885453927530408e-05, + "loss": 1.3116, + "step": 3850 + }, + { + "epoch": 0.4, + "learning_rate": 1.4882259891287467e-05, + "loss": 1.4278, + "step": 3851 + }, + { + "epoch": 0.4, + "learning_rate": 1.4879065200947148e-05, + "loss": 1.3712, + "step": 3852 + }, + { + "epoch": 0.4, + "learning_rate": 1.4875869856937449e-05, + "loss": 1.387, + "step": 3853 + }, + { + "epoch": 0.4, + "learning_rate": 1.4872673859686475e-05, + "loss": 1.5053, + "step": 3854 + }, + { + "epoch": 0.4, + "learning_rate": 1.4869477209622404e-05, + "loss": 1.4427, + "step": 3855 + }, + { + "epoch": 0.4, + "learning_rate": 1.4866279907173502e-05, + "loss": 1.3404, + "step": 3856 + }, + { + "epoch": 0.4, + "learning_rate": 1.4863081952768126e-05, + "loss": 1.3126, + "step": 3857 + }, + { + "epoch": 0.4, + "learning_rate": 1.4859883346834725e-05, + "loss": 1.4588, + "step": 3858 + }, + { + "epoch": 0.4, + "learning_rate": 1.4856684089801822e-05, + "loss": 1.408, + "step": 3859 + }, + { + "epoch": 0.4, + "learning_rate": 1.4853484182098044e-05, + "loss": 1.4356, + "step": 3860 + }, + { + "epoch": 0.4, + "learning_rate": 1.4850283624152088e-05, + "loss": 1.3768, + "step": 3861 + }, + { + "epoch": 0.4, + "learning_rate": 1.4847082416392753e-05, + "loss": 1.4563, + "step": 3862 + }, + { + "epoch": 0.41, + "learning_rate": 1.4843880559248915e-05, + "loss": 1.3648, + "step": 3863 + }, + { + "epoch": 0.41, + "learning_rate": 1.4840678053149542e-05, + "loss": 1.4146, + "step": 3864 + }, + { + "epoch": 0.41, + "learning_rate": 1.4837474898523686e-05, + "loss": 1.4423, + "step": 3865 + }, + { + "epoch": 0.41, + "learning_rate": 1.4834271095800487e-05, + "loss": 1.3351, + "step": 3866 + }, + { + "epoch": 0.41, + "learning_rate": 1.4831066645409178e-05, + "loss": 1.4534, + "step": 3867 + }, + { + "epoch": 0.41, + "learning_rate": 1.4827861547779066e-05, + "loss": 1.4763, + "step": 3868 + }, + { + "epoch": 0.41, + "learning_rate": 1.4824655803339553e-05, + "loss": 1.4019, + "step": 3869 + }, + { + "epoch": 0.41, + "learning_rate": 1.4821449412520132e-05, + "loss": 1.4223, + "step": 3870 + }, + { + "epoch": 0.41, + "learning_rate": 1.4818242375750371e-05, + "loss": 1.4065, + "step": 3871 + }, + { + "epoch": 0.41, + "learning_rate": 1.481503469345993e-05, + "loss": 1.587, + "step": 3872 + }, + { + "epoch": 0.41, + "learning_rate": 1.4811826366078562e-05, + "loss": 1.3746, + "step": 3873 + }, + { + "epoch": 0.41, + "learning_rate": 1.4808617394036096e-05, + "loss": 1.3425, + "step": 3874 + }, + { + "epoch": 0.41, + "learning_rate": 1.480540777776245e-05, + "loss": 0.6637, + "step": 3875 + }, + { + "epoch": 0.41, + "learning_rate": 1.4802197517687634e-05, + "loss": 1.3366, + "step": 3876 + }, + { + "epoch": 0.41, + "learning_rate": 1.479898661424174e-05, + "loss": 1.4033, + "step": 3877 + }, + { + "epoch": 0.41, + "learning_rate": 1.4795775067854947e-05, + "loss": 1.4005, + "step": 3878 + }, + { + "epoch": 0.41, + "learning_rate": 1.4792562878957516e-05, + "loss": 1.3651, + "step": 3879 + }, + { + "epoch": 0.41, + "learning_rate": 1.47893500479798e-05, + "loss": 1.4185, + "step": 3880 + }, + { + "epoch": 0.41, + "learning_rate": 1.4786136575352236e-05, + "loss": 1.4394, + "step": 3881 + }, + { + "epoch": 0.41, + "learning_rate": 1.478292246150535e-05, + "loss": 1.7243, + "step": 3882 + }, + { + "epoch": 0.41, + "learning_rate": 1.4779707706869744e-05, + "loss": 1.3574, + "step": 3883 + }, + { + "epoch": 0.41, + "learning_rate": 1.4776492311876116e-05, + "loss": 1.4031, + "step": 3884 + }, + { + "epoch": 0.41, + "learning_rate": 1.4773276276955248e-05, + "loss": 1.4351, + "step": 3885 + }, + { + "epoch": 0.41, + "learning_rate": 1.4770059602538002e-05, + "loss": 1.3922, + "step": 3886 + }, + { + "epoch": 0.41, + "learning_rate": 1.4766842289055333e-05, + "loss": 1.3374, + "step": 3887 + }, + { + "epoch": 0.41, + "learning_rate": 1.4763624336938278e-05, + "loss": 1.428, + "step": 3888 + }, + { + "epoch": 0.41, + "learning_rate": 1.476040574661796e-05, + "loss": 1.6087, + "step": 3889 + }, + { + "epoch": 0.41, + "learning_rate": 1.4757186518525586e-05, + "loss": 1.4054, + "step": 3890 + }, + { + "epoch": 0.41, + "learning_rate": 1.4753966653092447e-05, + "loss": 1.2595, + "step": 3891 + }, + { + "epoch": 0.41, + "learning_rate": 1.475074615074993e-05, + "loss": 1.4052, + "step": 3892 + }, + { + "epoch": 0.41, + "learning_rate": 1.4747525011929492e-05, + "loss": 1.4296, + "step": 3893 + }, + { + "epoch": 0.41, + "learning_rate": 1.4744303237062689e-05, + "loss": 1.3718, + "step": 3894 + }, + { + "epoch": 0.41, + "learning_rate": 1.4741080826581151e-05, + "loss": 1.4498, + "step": 3895 + }, + { + "epoch": 0.41, + "learning_rate": 1.4737857780916602e-05, + "loss": 1.4029, + "step": 3896 + }, + { + "epoch": 0.41, + "learning_rate": 1.4734634100500846e-05, + "loss": 1.4136, + "step": 3897 + }, + { + "epoch": 0.41, + "learning_rate": 1.4731409785765774e-05, + "loss": 1.348, + "step": 3898 + }, + { + "epoch": 0.41, + "learning_rate": 1.4728184837143355e-05, + "loss": 1.3407, + "step": 3899 + }, + { + "epoch": 0.41, + "learning_rate": 1.472495925506566e-05, + "loss": 1.3737, + "step": 3900 + }, + { + "epoch": 0.41, + "learning_rate": 1.4721733039964826e-05, + "loss": 2.2305, + "step": 3901 + }, + { + "epoch": 0.41, + "learning_rate": 1.4718506192273087e-05, + "loss": 1.4506, + "step": 3902 + }, + { + "epoch": 0.41, + "learning_rate": 1.4715278712422754e-05, + "loss": 1.3657, + "step": 3903 + }, + { + "epoch": 0.41, + "learning_rate": 1.471205060084623e-05, + "loss": 1.4644, + "step": 3904 + }, + { + "epoch": 0.41, + "learning_rate": 1.4708821857976001e-05, + "loss": 1.4823, + "step": 3905 + }, + { + "epoch": 0.41, + "learning_rate": 1.4705592484244628e-05, + "loss": 1.3392, + "step": 3906 + }, + { + "epoch": 0.41, + "learning_rate": 1.4702362480084769e-05, + "loss": 1.3302, + "step": 3907 + }, + { + "epoch": 0.41, + "learning_rate": 1.4699131845929163e-05, + "loss": 1.8952, + "step": 3908 + }, + { + "epoch": 0.41, + "learning_rate": 1.469590058221063e-05, + "loss": 1.4982, + "step": 3909 + }, + { + "epoch": 0.41, + "learning_rate": 1.4692668689362074e-05, + "loss": 1.407, + "step": 3910 + }, + { + "epoch": 0.41, + "learning_rate": 1.4689436167816489e-05, + "loss": 1.3911, + "step": 3911 + }, + { + "epoch": 0.41, + "learning_rate": 1.4686203018006948e-05, + "loss": 1.3421, + "step": 3912 + }, + { + "epoch": 0.41, + "learning_rate": 1.4682969240366612e-05, + "loss": 1.4627, + "step": 3913 + }, + { + "epoch": 0.41, + "learning_rate": 1.4679734835328718e-05, + "loss": 1.394, + "step": 3914 + }, + { + "epoch": 0.41, + "learning_rate": 1.4676499803326603e-05, + "loss": 1.4484, + "step": 3915 + }, + { + "epoch": 0.41, + "learning_rate": 1.4673264144793673e-05, + "loss": 1.4665, + "step": 3916 + }, + { + "epoch": 0.41, + "learning_rate": 1.4670027860163422e-05, + "loss": 1.3191, + "step": 3917 + }, + { + "epoch": 0.41, + "learning_rate": 1.466679094986943e-05, + "loss": 1.4748, + "step": 3918 + }, + { + "epoch": 0.41, + "learning_rate": 1.4663553414345361e-05, + "loss": 1.2467, + "step": 3919 + }, + { + "epoch": 0.41, + "learning_rate": 1.466031525402496e-05, + "loss": 1.4279, + "step": 3920 + }, + { + "epoch": 0.41, + "learning_rate": 1.4657076469342059e-05, + "loss": 1.3822, + "step": 3921 + }, + { + "epoch": 0.41, + "learning_rate": 1.4653837060730566e-05, + "loss": 1.3659, + "step": 3922 + }, + { + "epoch": 0.41, + "learning_rate": 1.465059702862449e-05, + "loss": 1.3663, + "step": 3923 + }, + { + "epoch": 0.41, + "learning_rate": 1.4647356373457902e-05, + "loss": 1.4371, + "step": 3924 + }, + { + "epoch": 0.41, + "learning_rate": 1.4644115095664972e-05, + "loss": 1.3473, + "step": 3925 + }, + { + "epoch": 0.41, + "learning_rate": 1.4640873195679944e-05, + "loss": 1.4797, + "step": 3926 + }, + { + "epoch": 0.41, + "learning_rate": 1.463763067393715e-05, + "loss": 1.3973, + "step": 3927 + }, + { + "epoch": 0.41, + "learning_rate": 1.4634387530871008e-05, + "loss": 1.3899, + "step": 3928 + }, + { + "epoch": 0.41, + "learning_rate": 1.4631143766916015e-05, + "loss": 1.3828, + "step": 3929 + }, + { + "epoch": 0.41, + "learning_rate": 1.4627899382506745e-05, + "loss": 1.4569, + "step": 3930 + }, + { + "epoch": 0.41, + "learning_rate": 1.4624654378077872e-05, + "loss": 1.4011, + "step": 3931 + }, + { + "epoch": 0.41, + "learning_rate": 1.462140875406414e-05, + "loss": 1.3859, + "step": 3932 + }, + { + "epoch": 0.41, + "learning_rate": 1.4618162510900376e-05, + "loss": 1.4518, + "step": 3933 + }, + { + "epoch": 0.41, + "learning_rate": 1.4614915649021493e-05, + "loss": 1.4399, + "step": 3934 + }, + { + "epoch": 0.41, + "learning_rate": 1.4611668168862495e-05, + "loss": 1.4034, + "step": 3935 + }, + { + "epoch": 0.41, + "learning_rate": 1.4608420070858452e-05, + "loss": 1.3919, + "step": 3936 + }, + { + "epoch": 0.41, + "learning_rate": 1.4605171355444528e-05, + "loss": 1.391, + "step": 3937 + }, + { + "epoch": 0.41, + "learning_rate": 1.460192202305597e-05, + "loss": 1.3717, + "step": 3938 + }, + { + "epoch": 0.41, + "learning_rate": 1.4598672074128103e-05, + "loss": 1.4351, + "step": 3939 + }, + { + "epoch": 0.41, + "learning_rate": 1.4595421509096339e-05, + "loss": 1.4202, + "step": 3940 + }, + { + "epoch": 0.41, + "learning_rate": 1.4592170328396165e-05, + "loss": 1.3559, + "step": 3941 + }, + { + "epoch": 0.41, + "learning_rate": 1.458891853246316e-05, + "loss": 1.5878, + "step": 3942 + }, + { + "epoch": 0.41, + "learning_rate": 1.4585666121732982e-05, + "loss": 1.3818, + "step": 3943 + }, + { + "epoch": 0.41, + "learning_rate": 1.4582413096641369e-05, + "loss": 1.4009, + "step": 3944 + }, + { + "epoch": 0.41, + "learning_rate": 1.457915945762414e-05, + "loss": 1.3937, + "step": 3945 + }, + { + "epoch": 0.41, + "learning_rate": 1.4575905205117203e-05, + "loss": 1.381, + "step": 3946 + }, + { + "epoch": 0.41, + "learning_rate": 1.457265033955654e-05, + "loss": 1.3844, + "step": 3947 + }, + { + "epoch": 0.41, + "learning_rate": 1.4569394861378226e-05, + "loss": 1.4059, + "step": 3948 + }, + { + "epoch": 0.41, + "learning_rate": 1.4566138771018403e-05, + "loss": 1.3698, + "step": 3949 + }, + { + "epoch": 0.41, + "learning_rate": 1.4562882068913311e-05, + "loss": 1.4253, + "step": 3950 + }, + { + "epoch": 0.41, + "learning_rate": 1.455962475549926e-05, + "loss": 1.4284, + "step": 3951 + }, + { + "epoch": 0.41, + "learning_rate": 1.4556366831212647e-05, + "loss": 1.4279, + "step": 3952 + }, + { + "epoch": 0.41, + "learning_rate": 1.4553108296489951e-05, + "loss": 1.3072, + "step": 3953 + }, + { + "epoch": 0.41, + "learning_rate": 1.4549849151767731e-05, + "loss": 1.4175, + "step": 3954 + }, + { + "epoch": 0.41, + "learning_rate": 1.4546589397482632e-05, + "loss": 1.5042, + "step": 3955 + }, + { + "epoch": 0.41, + "learning_rate": 1.4543329034071371e-05, + "loss": 1.4363, + "step": 3956 + }, + { + "epoch": 0.41, + "learning_rate": 1.454006806197076e-05, + "loss": 1.4111, + "step": 3957 + }, + { + "epoch": 0.42, + "learning_rate": 1.453680648161768e-05, + "loss": 1.3817, + "step": 3958 + }, + { + "epoch": 0.42, + "learning_rate": 1.45335442934491e-05, + "loss": 1.4689, + "step": 3959 + }, + { + "epoch": 0.42, + "learning_rate": 1.4530281497902072e-05, + "loss": 1.4164, + "step": 3960 + }, + { + "epoch": 0.42, + "learning_rate": 1.4527018095413726e-05, + "loss": 1.3943, + "step": 3961 + }, + { + "epoch": 0.42, + "learning_rate": 1.4523754086421271e-05, + "loss": 1.3851, + "step": 3962 + }, + { + "epoch": 0.42, + "learning_rate": 1.4520489471362003e-05, + "loss": 1.3907, + "step": 3963 + }, + { + "epoch": 0.42, + "learning_rate": 1.4517224250673297e-05, + "loss": 1.2877, + "step": 3964 + }, + { + "epoch": 0.42, + "learning_rate": 1.4513958424792605e-05, + "loss": 1.4696, + "step": 3965 + }, + { + "epoch": 0.42, + "learning_rate": 1.4510691994157471e-05, + "loss": 1.3785, + "step": 3966 + }, + { + "epoch": 0.42, + "learning_rate": 1.4507424959205505e-05, + "loss": 1.3652, + "step": 3967 + }, + { + "epoch": 0.42, + "learning_rate": 1.4504157320374408e-05, + "loss": 1.4198, + "step": 3968 + }, + { + "epoch": 0.42, + "learning_rate": 1.4500889078101962e-05, + "loss": 1.3476, + "step": 3969 + }, + { + "epoch": 0.42, + "learning_rate": 1.4497620232826028e-05, + "loss": 1.4356, + "step": 3970 + }, + { + "epoch": 0.42, + "learning_rate": 1.4494350784984543e-05, + "loss": 1.4993, + "step": 3971 + }, + { + "epoch": 0.42, + "learning_rate": 1.4491080735015533e-05, + "loss": 1.4022, + "step": 3972 + }, + { + "epoch": 0.42, + "learning_rate": 1.44878100833571e-05, + "loss": 1.4074, + "step": 3973 + }, + { + "epoch": 0.42, + "learning_rate": 1.4484538830447423e-05, + "loss": 1.412, + "step": 3974 + }, + { + "epoch": 0.42, + "learning_rate": 1.4481266976724772e-05, + "loss": 1.3872, + "step": 3975 + }, + { + "epoch": 0.42, + "learning_rate": 1.4477994522627485e-05, + "loss": 1.4575, + "step": 3976 + }, + { + "epoch": 0.42, + "learning_rate": 1.4474721468593995e-05, + "loss": 1.3768, + "step": 3977 + }, + { + "epoch": 0.42, + "learning_rate": 1.44714478150628e-05, + "loss": 1.4173, + "step": 3978 + }, + { + "epoch": 0.42, + "learning_rate": 1.4468173562472489e-05, + "loss": 1.3896, + "step": 3979 + }, + { + "epoch": 0.42, + "learning_rate": 1.4464898711261725e-05, + "loss": 1.4535, + "step": 3980 + }, + { + "epoch": 0.42, + "eval_loss": 1.4580057859420776, + "eval_runtime": 77.4537, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 3980 + }, + { + "epoch": 0.42, + "learning_rate": 1.4461623261869258e-05, + "loss": 1.4046, + "step": 3981 + }, + { + "epoch": 0.42, + "learning_rate": 1.445834721473391e-05, + "loss": 1.37, + "step": 3982 + }, + { + "epoch": 0.42, + "learning_rate": 1.4455070570294588e-05, + "loss": 1.4566, + "step": 3983 + }, + { + "epoch": 0.42, + "learning_rate": 1.445179332899028e-05, + "loss": 1.4513, + "step": 3984 + }, + { + "epoch": 0.42, + "learning_rate": 1.4448515491260051e-05, + "loss": 1.3893, + "step": 3985 + }, + { + "epoch": 0.42, + "learning_rate": 1.4445237057543047e-05, + "loss": 1.3955, + "step": 3986 + }, + { + "epoch": 0.42, + "learning_rate": 1.4441958028278493e-05, + "loss": 1.4861, + "step": 3987 + }, + { + "epoch": 0.42, + "learning_rate": 1.4438678403905697e-05, + "loss": 1.4601, + "step": 3988 + }, + { + "epoch": 0.42, + "learning_rate": 1.4435398184864043e-05, + "loss": 1.398, + "step": 3989 + }, + { + "epoch": 0.42, + "learning_rate": 1.4432117371592995e-05, + "loss": 1.4392, + "step": 3990 + }, + { + "epoch": 0.42, + "learning_rate": 1.4428835964532098e-05, + "loss": 1.3772, + "step": 3991 + }, + { + "epoch": 0.42, + "learning_rate": 1.4425553964120979e-05, + "loss": 1.4241, + "step": 3992 + }, + { + "epoch": 0.42, + "learning_rate": 1.4422271370799338e-05, + "loss": 1.3237, + "step": 3993 + }, + { + "epoch": 0.42, + "learning_rate": 1.4418988185006964e-05, + "loss": 1.3813, + "step": 3994 + }, + { + "epoch": 0.42, + "learning_rate": 1.4415704407183709e-05, + "loss": 1.6139, + "step": 3995 + }, + { + "epoch": 0.42, + "learning_rate": 1.4412420037769525e-05, + "loss": 1.4431, + "step": 3996 + }, + { + "epoch": 0.42, + "learning_rate": 1.440913507720443e-05, + "loss": 1.3862, + "step": 3997 + }, + { + "epoch": 0.42, + "learning_rate": 1.4405849525928523e-05, + "loss": 1.3895, + "step": 3998 + }, + { + "epoch": 0.42, + "learning_rate": 1.4402563384381981e-05, + "loss": 1.4068, + "step": 3999 + }, + { + "epoch": 0.42, + "learning_rate": 1.4399276653005072e-05, + "loss": 1.4501, + "step": 4000 + }, + { + "epoch": 0.42, + "learning_rate": 1.4395989332238124e-05, + "loss": 1.3165, + "step": 4001 + }, + { + "epoch": 0.42, + "learning_rate": 1.4392701422521555e-05, + "loss": 1.3783, + "step": 4002 + }, + { + "epoch": 0.42, + "learning_rate": 1.4389412924295865e-05, + "loss": 1.343, + "step": 4003 + }, + { + "epoch": 0.42, + "learning_rate": 1.4386123838001625e-05, + "loss": 1.3456, + "step": 4004 + }, + { + "epoch": 0.42, + "learning_rate": 1.4382834164079486e-05, + "loss": 1.3689, + "step": 4005 + }, + { + "epoch": 0.42, + "learning_rate": 1.4379543902970183e-05, + "loss": 1.3789, + "step": 4006 + }, + { + "epoch": 0.42, + "learning_rate": 1.4376253055114528e-05, + "loss": 1.4912, + "step": 4007 + }, + { + "epoch": 0.42, + "learning_rate": 1.4372961620953407e-05, + "loss": 1.3692, + "step": 4008 + }, + { + "epoch": 0.42, + "learning_rate": 1.436966960092779e-05, + "loss": 1.4901, + "step": 4009 + }, + { + "epoch": 0.42, + "learning_rate": 1.4366376995478717e-05, + "loss": 1.4431, + "step": 4010 + }, + { + "epoch": 0.42, + "learning_rate": 1.436308380504732e-05, + "loss": 1.4626, + "step": 4011 + }, + { + "epoch": 0.42, + "learning_rate": 1.4359790030074798e-05, + "loss": 1.4241, + "step": 4012 + }, + { + "epoch": 0.42, + "learning_rate": 1.4356495671002435e-05, + "loss": 1.3834, + "step": 4013 + }, + { + "epoch": 0.42, + "learning_rate": 1.4353200728271586e-05, + "loss": 1.3626, + "step": 4014 + }, + { + "epoch": 0.42, + "learning_rate": 1.4349905202323692e-05, + "loss": 1.3557, + "step": 4015 + }, + { + "epoch": 0.42, + "learning_rate": 1.434660909360027e-05, + "loss": 1.4077, + "step": 4016 + }, + { + "epoch": 0.42, + "learning_rate": 1.4343312402542911e-05, + "loss": 1.4337, + "step": 4017 + }, + { + "epoch": 0.42, + "learning_rate": 1.4340015129593286e-05, + "loss": 1.419, + "step": 4018 + }, + { + "epoch": 0.42, + "learning_rate": 1.4336717275193148e-05, + "loss": 1.3768, + "step": 4019 + }, + { + "epoch": 0.42, + "learning_rate": 1.4333418839784326e-05, + "loss": 1.383, + "step": 4020 + }, + { + "epoch": 0.42, + "learning_rate": 1.4330119823808719e-05, + "loss": 1.3951, + "step": 4021 + }, + { + "epoch": 0.42, + "learning_rate": 1.4326820227708316e-05, + "loss": 1.3985, + "step": 4022 + }, + { + "epoch": 0.42, + "learning_rate": 1.4323520051925177e-05, + "loss": 1.356, + "step": 4023 + }, + { + "epoch": 0.42, + "learning_rate": 1.4320219296901439e-05, + "loss": 1.5017, + "step": 4024 + }, + { + "epoch": 0.42, + "learning_rate": 1.4316917963079322e-05, + "loss": 1.3594, + "step": 4025 + }, + { + "epoch": 0.42, + "learning_rate": 1.4313616050901114e-05, + "loss": 1.6028, + "step": 4026 + }, + { + "epoch": 0.42, + "learning_rate": 1.4310313560809193e-05, + "loss": 1.4132, + "step": 4027 + }, + { + "epoch": 0.42, + "learning_rate": 1.4307010493246006e-05, + "loss": 1.2969, + "step": 4028 + }, + { + "epoch": 0.42, + "learning_rate": 1.4303706848654073e-05, + "loss": 1.5224, + "step": 4029 + }, + { + "epoch": 0.42, + "learning_rate": 1.4300402627476007e-05, + "loss": 1.3386, + "step": 4030 + }, + { + "epoch": 0.42, + "learning_rate": 1.429709783015448e-05, + "loss": 1.3554, + "step": 4031 + }, + { + "epoch": 0.42, + "learning_rate": 1.4293792457132259e-05, + "loss": 1.3386, + "step": 4032 + }, + { + "epoch": 0.42, + "learning_rate": 1.429048650885217e-05, + "loss": 1.4613, + "step": 4033 + }, + { + "epoch": 0.42, + "learning_rate": 1.4287179985757132e-05, + "loss": 1.3632, + "step": 4034 + }, + { + "epoch": 0.42, + "learning_rate": 1.428387288829013e-05, + "loss": 1.3835, + "step": 4035 + }, + { + "epoch": 0.42, + "learning_rate": 1.4280565216894234e-05, + "loss": 1.3711, + "step": 4036 + }, + { + "epoch": 0.42, + "learning_rate": 1.4277256972012582e-05, + "loss": 1.3385, + "step": 4037 + }, + { + "epoch": 0.42, + "learning_rate": 1.4273948154088395e-05, + "loss": 1.4607, + "step": 4038 + }, + { + "epoch": 0.42, + "learning_rate": 1.4270638763564973e-05, + "loss": 1.4042, + "step": 4039 + }, + { + "epoch": 0.42, + "learning_rate": 1.4267328800885687e-05, + "loss": 1.4006, + "step": 4040 + }, + { + "epoch": 0.42, + "learning_rate": 1.4264018266493987e-05, + "loss": 1.386, + "step": 4041 + }, + { + "epoch": 0.42, + "learning_rate": 1.4260707160833401e-05, + "loss": 1.3487, + "step": 4042 + }, + { + "epoch": 0.42, + "learning_rate": 1.4257395484347529e-05, + "loss": 1.4199, + "step": 4043 + }, + { + "epoch": 0.42, + "learning_rate": 1.4254083237480054e-05, + "loss": 1.3236, + "step": 4044 + }, + { + "epoch": 0.42, + "learning_rate": 1.4250770420674726e-05, + "loss": 1.4056, + "step": 4045 + }, + { + "epoch": 0.42, + "learning_rate": 1.4247457034375387e-05, + "loss": 1.4391, + "step": 4046 + }, + { + "epoch": 0.42, + "learning_rate": 1.4244143079025938e-05, + "loss": 1.3935, + "step": 4047 + }, + { + "epoch": 0.42, + "learning_rate": 1.4240828555070368e-05, + "loss": 1.3623, + "step": 4048 + }, + { + "epoch": 0.42, + "learning_rate": 1.4237513462952733e-05, + "loss": 1.3254, + "step": 4049 + }, + { + "epoch": 0.42, + "learning_rate": 1.4234197803117174e-05, + "loss": 1.4217, + "step": 4050 + }, + { + "epoch": 0.42, + "learning_rate": 1.4230881576007904e-05, + "loss": 1.435, + "step": 4051 + }, + { + "epoch": 0.42, + "learning_rate": 1.422756478206921e-05, + "loss": 1.3687, + "step": 4052 + }, + { + "epoch": 0.43, + "learning_rate": 1.4224247421745464e-05, + "loss": 1.3965, + "step": 4053 + }, + { + "epoch": 0.43, + "learning_rate": 1.4220929495481097e-05, + "loss": 1.4159, + "step": 4054 + }, + { + "epoch": 0.43, + "learning_rate": 1.4217611003720632e-05, + "loss": 1.3632, + "step": 4055 + }, + { + "epoch": 0.43, + "learning_rate": 1.4214291946908661e-05, + "loss": 1.403, + "step": 4056 + }, + { + "epoch": 0.43, + "learning_rate": 1.4210972325489854e-05, + "loss": 1.4093, + "step": 4057 + }, + { + "epoch": 0.43, + "learning_rate": 1.4207652139908952e-05, + "loss": 1.4551, + "step": 4058 + }, + { + "epoch": 0.43, + "learning_rate": 1.4204331390610775e-05, + "loss": 1.4162, + "step": 4059 + }, + { + "epoch": 0.43, + "learning_rate": 1.4201010078040216e-05, + "loss": 1.4492, + "step": 4060 + }, + { + "epoch": 0.43, + "learning_rate": 1.419768820264225e-05, + "loss": 1.4449, + "step": 4061 + }, + { + "epoch": 0.43, + "learning_rate": 1.4194365764861922e-05, + "loss": 1.3382, + "step": 4062 + }, + { + "epoch": 0.43, + "learning_rate": 1.419104276514435e-05, + "loss": 1.3899, + "step": 4063 + }, + { + "epoch": 0.43, + "learning_rate": 1.4187719203934734e-05, + "loss": 1.3513, + "step": 4064 + }, + { + "epoch": 0.43, + "learning_rate": 1.4184395081678344e-05, + "loss": 1.3954, + "step": 4065 + }, + { + "epoch": 0.43, + "learning_rate": 1.4181070398820528e-05, + "loss": 1.442, + "step": 4066 + }, + { + "epoch": 0.43, + "learning_rate": 1.4177745155806708e-05, + "loss": 1.3907, + "step": 4067 + }, + { + "epoch": 0.43, + "learning_rate": 1.417441935308238e-05, + "loss": 1.3757, + "step": 4068 + }, + { + "epoch": 0.43, + "learning_rate": 1.4171092991093118e-05, + "loss": 1.3507, + "step": 4069 + }, + { + "epoch": 0.43, + "learning_rate": 1.4167766070284568e-05, + "loss": 1.4136, + "step": 4070 + }, + { + "epoch": 0.43, + "learning_rate": 1.4164438591102452e-05, + "loss": 1.3835, + "step": 4071 + }, + { + "epoch": 0.43, + "learning_rate": 1.4161110553992565e-05, + "loss": 1.4981, + "step": 4072 + }, + { + "epoch": 0.43, + "learning_rate": 1.415778195940078e-05, + "loss": 1.4387, + "step": 4073 + }, + { + "epoch": 0.43, + "learning_rate": 1.4154452807773047e-05, + "loss": 1.333, + "step": 4074 + }, + { + "epoch": 0.43, + "learning_rate": 1.4151123099555377e-05, + "loss": 1.3558, + "step": 4075 + }, + { + "epoch": 0.43, + "learning_rate": 1.4147792835193875e-05, + "loss": 1.4655, + "step": 4076 + }, + { + "epoch": 0.43, + "learning_rate": 1.4144462015134708e-05, + "loss": 1.4402, + "step": 4077 + }, + { + "epoch": 0.43, + "learning_rate": 1.4141130639824119e-05, + "loss": 1.4227, + "step": 4078 + }, + { + "epoch": 0.43, + "learning_rate": 1.4137798709708423e-05, + "loss": 1.4039, + "step": 4079 + }, + { + "epoch": 0.43, + "learning_rate": 1.4134466225234023e-05, + "loss": 1.3593, + "step": 4080 + }, + { + "epoch": 0.43, + "learning_rate": 1.4131133186847377e-05, + "loss": 1.372, + "step": 4081 + }, + { + "epoch": 0.43, + "learning_rate": 1.412779959499503e-05, + "loss": 1.4487, + "step": 4082 + }, + { + "epoch": 0.43, + "learning_rate": 1.4124465450123599e-05, + "loss": 1.3972, + "step": 4083 + }, + { + "epoch": 0.43, + "learning_rate": 1.4121130752679772e-05, + "loss": 1.3768, + "step": 4084 + }, + { + "epoch": 0.43, + "learning_rate": 1.4117795503110313e-05, + "loss": 1.3827, + "step": 4085 + }, + { + "epoch": 0.43, + "learning_rate": 1.4114459701862062e-05, + "loss": 1.3922, + "step": 4086 + }, + { + "epoch": 0.43, + "learning_rate": 1.4111123349381925e-05, + "loss": 1.3736, + "step": 4087 + }, + { + "epoch": 0.43, + "learning_rate": 1.4107786446116894e-05, + "loss": 1.4338, + "step": 4088 + }, + { + "epoch": 0.43, + "learning_rate": 1.4104448992514023e-05, + "loss": 1.347, + "step": 4089 + }, + { + "epoch": 0.43, + "learning_rate": 1.410111098902045e-05, + "loss": 1.3915, + "step": 4090 + }, + { + "epoch": 0.43, + "learning_rate": 1.4097772436083377e-05, + "loss": 1.3656, + "step": 4091 + }, + { + "epoch": 0.43, + "learning_rate": 1.4094433334150087e-05, + "loss": 1.3461, + "step": 4092 + }, + { + "epoch": 0.43, + "learning_rate": 1.4091093683667934e-05, + "loss": 1.7345, + "step": 4093 + }, + { + "epoch": 0.43, + "learning_rate": 1.4087753485084343e-05, + "loss": 1.6204, + "step": 4094 + }, + { + "epoch": 0.43, + "learning_rate": 1.4084412738846816e-05, + "loss": 1.4074, + "step": 4095 + }, + { + "epoch": 0.43, + "learning_rate": 1.408107144540293e-05, + "loss": 1.3776, + "step": 4096 + }, + { + "epoch": 0.43, + "learning_rate": 1.407772960520033e-05, + "loss": 1.4079, + "step": 4097 + }, + { + "epoch": 0.43, + "learning_rate": 1.4074387218686734e-05, + "loss": 1.4254, + "step": 4098 + }, + { + "epoch": 0.43, + "learning_rate": 1.407104428630994e-05, + "loss": 1.38, + "step": 4099 + }, + { + "epoch": 0.43, + "learning_rate": 1.4067700808517815e-05, + "loss": 1.4175, + "step": 4100 + }, + { + "epoch": 0.43, + "learning_rate": 1.4064356785758298e-05, + "loss": 1.4085, + "step": 4101 + }, + { + "epoch": 0.43, + "learning_rate": 1.4061012218479397e-05, + "loss": 1.4529, + "step": 4102 + }, + { + "epoch": 0.43, + "learning_rate": 1.405766710712921e-05, + "loss": 1.4836, + "step": 4103 + }, + { + "epoch": 0.43, + "learning_rate": 1.4054321452155885e-05, + "loss": 1.3915, + "step": 4104 + }, + { + "epoch": 0.43, + "learning_rate": 1.4050975254007659e-05, + "loss": 1.3044, + "step": 4105 + }, + { + "epoch": 0.43, + "learning_rate": 1.4047628513132835e-05, + "loss": 1.373, + "step": 4106 + }, + { + "epoch": 0.43, + "learning_rate": 1.4044281229979793e-05, + "loss": 1.4266, + "step": 4107 + }, + { + "epoch": 0.43, + "learning_rate": 1.4040933404996977e-05, + "loss": 1.3898, + "step": 4108 + }, + { + "epoch": 0.43, + "learning_rate": 1.4037585038632915e-05, + "loss": 0.9326, + "step": 4109 + }, + { + "epoch": 0.43, + "learning_rate": 1.40342361313362e-05, + "loss": 1.0831, + "step": 4110 + }, + { + "epoch": 0.43, + "learning_rate": 1.40308866835555e-05, + "loss": 1.3898, + "step": 4111 + }, + { + "epoch": 0.43, + "learning_rate": 1.4027536695739554e-05, + "loss": 1.5058, + "step": 4112 + }, + { + "epoch": 0.43, + "learning_rate": 1.4024186168337175e-05, + "loss": 1.3635, + "step": 4113 + }, + { + "epoch": 0.43, + "learning_rate": 1.4020835101797248e-05, + "loss": 1.3871, + "step": 4114 + }, + { + "epoch": 0.43, + "learning_rate": 1.401748349656873e-05, + "loss": 1.3478, + "step": 4115 + }, + { + "epoch": 0.43, + "learning_rate": 1.4014131353100648e-05, + "loss": 1.3356, + "step": 4116 + }, + { + "epoch": 0.43, + "learning_rate": 1.4010778671842107e-05, + "loss": 1.3954, + "step": 4117 + }, + { + "epoch": 0.43, + "learning_rate": 1.4007425453242274e-05, + "loss": 1.3307, + "step": 4118 + }, + { + "epoch": 0.43, + "learning_rate": 1.4004071697750398e-05, + "loss": 1.4508, + "step": 4119 + }, + { + "epoch": 0.43, + "learning_rate": 1.4000717405815799e-05, + "loss": 1.3752, + "step": 4120 + }, + { + "epoch": 0.43, + "learning_rate": 1.399736257788786e-05, + "loss": 1.3654, + "step": 4121 + }, + { + "epoch": 0.43, + "learning_rate": 1.3994007214416046e-05, + "loss": 1.4505, + "step": 4122 + }, + { + "epoch": 0.43, + "learning_rate": 1.3990651315849886e-05, + "loss": 1.4307, + "step": 4123 + }, + { + "epoch": 0.43, + "learning_rate": 1.398729488263899e-05, + "loss": 1.4481, + "step": 4124 + }, + { + "epoch": 0.43, + "learning_rate": 1.3983937915233026e-05, + "loss": 1.4755, + "step": 4125 + }, + { + "epoch": 0.43, + "learning_rate": 1.3980580414081746e-05, + "loss": 1.3402, + "step": 4126 + }, + { + "epoch": 0.43, + "learning_rate": 1.3977222379634969e-05, + "loss": 1.3636, + "step": 4127 + }, + { + "epoch": 0.43, + "learning_rate": 1.3973863812342585e-05, + "loss": 1.4165, + "step": 4128 + }, + { + "epoch": 0.43, + "learning_rate": 1.3970504712654554e-05, + "loss": 1.3832, + "step": 4129 + }, + { + "epoch": 0.43, + "learning_rate": 1.3967145081020912e-05, + "loss": 1.4236, + "step": 4130 + }, + { + "epoch": 0.43, + "learning_rate": 1.396378491789176e-05, + "loss": 1.5022, + "step": 4131 + }, + { + "epoch": 0.43, + "learning_rate": 1.3960424223717276e-05, + "loss": 1.3806, + "step": 4132 + }, + { + "epoch": 0.43, + "learning_rate": 1.3957062998947707e-05, + "loss": 1.3649, + "step": 4133 + }, + { + "epoch": 0.43, + "learning_rate": 1.3953701244033368e-05, + "loss": 1.3787, + "step": 4134 + }, + { + "epoch": 0.43, + "learning_rate": 1.395033895942465e-05, + "loss": 1.3551, + "step": 4135 + }, + { + "epoch": 0.43, + "learning_rate": 1.394697614557201e-05, + "loss": 1.3881, + "step": 4136 + }, + { + "epoch": 0.43, + "learning_rate": 1.3943612802925983e-05, + "loss": 1.4848, + "step": 4137 + }, + { + "epoch": 0.43, + "learning_rate": 1.3940248931937169e-05, + "loss": 1.425, + "step": 4138 + }, + { + "epoch": 0.43, + "learning_rate": 1.3936884533056238e-05, + "loss": 1.4054, + "step": 4139 + }, + { + "epoch": 0.43, + "learning_rate": 1.3933519606733934e-05, + "loss": 1.4028, + "step": 4140 + }, + { + "epoch": 0.43, + "learning_rate": 1.3930154153421072e-05, + "loss": 1.4439, + "step": 4141 + }, + { + "epoch": 0.43, + "learning_rate": 1.3926788173568536e-05, + "loss": 1.4482, + "step": 4142 + }, + { + "epoch": 0.43, + "learning_rate": 1.392342166762728e-05, + "loss": 1.393, + "step": 4143 + }, + { + "epoch": 0.43, + "learning_rate": 1.3920054636048328e-05, + "loss": 1.4097, + "step": 4144 + }, + { + "epoch": 0.43, + "learning_rate": 1.391668707928278e-05, + "loss": 1.5142, + "step": 4145 + }, + { + "epoch": 0.43, + "learning_rate": 1.3913318997781797e-05, + "loss": 1.4118, + "step": 4146 + }, + { + "epoch": 0.43, + "learning_rate": 1.390995039199662e-05, + "loss": 1.4067, + "step": 4147 + }, + { + "epoch": 0.43, + "learning_rate": 1.3906581262378552e-05, + "loss": 1.5214, + "step": 4148 + }, + { + "epoch": 0.44, + "learning_rate": 1.3903211609378971e-05, + "loss": 1.3618, + "step": 4149 + }, + { + "epoch": 0.44, + "learning_rate": 1.3899841433449327e-05, + "loss": 1.338, + "step": 4150 + }, + { + "epoch": 0.44, + "learning_rate": 1.3896470735041132e-05, + "loss": 1.3901, + "step": 4151 + }, + { + "epoch": 0.44, + "learning_rate": 1.3893099514605971e-05, + "loss": 1.4502, + "step": 4152 + }, + { + "epoch": 0.44, + "learning_rate": 1.388972777259551e-05, + "loss": 1.4141, + "step": 4153 + }, + { + "epoch": 0.44, + "learning_rate": 1.3886355509461471e-05, + "loss": 1.3876, + "step": 4154 + }, + { + "epoch": 0.44, + "learning_rate": 1.388298272565565e-05, + "loss": 1.4275, + "step": 4155 + }, + { + "epoch": 0.44, + "learning_rate": 1.3879609421629909e-05, + "loss": 1.3559, + "step": 4156 + }, + { + "epoch": 0.44, + "learning_rate": 1.3876235597836195e-05, + "loss": 1.416, + "step": 4157 + }, + { + "epoch": 0.44, + "learning_rate": 1.3872861254726506e-05, + "loss": 1.437, + "step": 4158 + }, + { + "epoch": 0.44, + "learning_rate": 1.3869486392752918e-05, + "loss": 1.3794, + "step": 4159 + }, + { + "epoch": 0.44, + "learning_rate": 1.3866111012367577e-05, + "loss": 1.4094, + "step": 4160 + }, + { + "epoch": 0.44, + "learning_rate": 1.3862735114022694e-05, + "loss": 1.3957, + "step": 4161 + }, + { + "epoch": 0.44, + "learning_rate": 1.3859358698170559e-05, + "loss": 1.3582, + "step": 4162 + }, + { + "epoch": 0.44, + "learning_rate": 1.3855981765263523e-05, + "loss": 1.4159, + "step": 4163 + }, + { + "epoch": 0.44, + "learning_rate": 1.3852604315754e-05, + "loss": 1.3498, + "step": 4164 + }, + { + "epoch": 0.44, + "learning_rate": 1.3849226350094491e-05, + "loss": 1.3951, + "step": 4165 + }, + { + "epoch": 0.44, + "learning_rate": 1.3845847868737559e-05, + "loss": 1.4087, + "step": 4166 + }, + { + "epoch": 0.44, + "learning_rate": 1.3842468872135821e-05, + "loss": 1.4318, + "step": 4167 + }, + { + "epoch": 0.44, + "learning_rate": 1.3839089360741989e-05, + "loss": 1.4174, + "step": 4168 + }, + { + "epoch": 0.44, + "learning_rate": 1.3835709335008822e-05, + "loss": 1.4499, + "step": 4169 + }, + { + "epoch": 0.44, + "learning_rate": 1.383232879538916e-05, + "loss": 1.3554, + "step": 4170 + }, + { + "epoch": 0.44, + "learning_rate": 1.3828947742335905e-05, + "loss": 1.3873, + "step": 4171 + }, + { + "epoch": 0.44, + "learning_rate": 1.382556617630204e-05, + "loss": 1.3804, + "step": 4172 + }, + { + "epoch": 0.44, + "learning_rate": 1.3822184097740598e-05, + "loss": 1.3856, + "step": 4173 + }, + { + "epoch": 0.44, + "learning_rate": 1.3818801507104697e-05, + "loss": 1.3901, + "step": 4174 + }, + { + "epoch": 0.44, + "learning_rate": 1.381541840484751e-05, + "loss": 1.3714, + "step": 4175 + }, + { + "epoch": 0.44, + "learning_rate": 1.3812034791422297e-05, + "loss": 1.4945, + "step": 4176 + }, + { + "epoch": 0.44, + "learning_rate": 1.3808650667282368e-05, + "loss": 1.429, + "step": 4177 + }, + { + "epoch": 0.44, + "learning_rate": 1.3805266032881108e-05, + "loss": 1.3903, + "step": 4178 + }, + { + "epoch": 0.44, + "learning_rate": 1.3801880888671972e-05, + "loss": 1.4799, + "step": 4179 + }, + { + "epoch": 0.44, + "eval_loss": 1.4521424770355225, + "eval_runtime": 77.3596, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 4179 + }, + { + "epoch": 0.44, + "learning_rate": 1.3798495235108484e-05, + "loss": 1.3912, + "step": 4180 + }, + { + "epoch": 0.44, + "learning_rate": 1.3795109072644235e-05, + "loss": 1.5837, + "step": 4181 + }, + { + "epoch": 0.44, + "learning_rate": 1.379172240173288e-05, + "loss": 1.4255, + "step": 4182 + }, + { + "epoch": 0.44, + "learning_rate": 1.3788335222828148e-05, + "loss": 1.4666, + "step": 4183 + }, + { + "epoch": 0.44, + "learning_rate": 1.3784947536383837e-05, + "loss": 1.3964, + "step": 4184 + }, + { + "epoch": 0.44, + "learning_rate": 1.3781559342853807e-05, + "loss": 1.336, + "step": 4185 + }, + { + "epoch": 0.44, + "learning_rate": 1.3778170642691986e-05, + "loss": 1.4352, + "step": 4186 + }, + { + "epoch": 0.44, + "learning_rate": 1.377478143635238e-05, + "loss": 1.3262, + "step": 4187 + }, + { + "epoch": 0.44, + "learning_rate": 1.3771391724289047e-05, + "loss": 1.3969, + "step": 4188 + }, + { + "epoch": 0.44, + "learning_rate": 1.376800150695613e-05, + "loss": 1.4211, + "step": 4189 + }, + { + "epoch": 0.44, + "learning_rate": 1.3764610784807824e-05, + "loss": 1.4338, + "step": 4190 + }, + { + "epoch": 0.44, + "learning_rate": 1.3761219558298403e-05, + "loss": 1.3815, + "step": 4191 + }, + { + "epoch": 0.44, + "learning_rate": 1.3757827827882203e-05, + "loss": 1.3805, + "step": 4192 + }, + { + "epoch": 0.44, + "learning_rate": 1.3754435594013627e-05, + "loss": 1.4071, + "step": 4193 + }, + { + "epoch": 0.44, + "learning_rate": 1.3751042857147145e-05, + "loss": 1.343, + "step": 4194 + }, + { + "epoch": 0.44, + "learning_rate": 1.3747649617737304e-05, + "loss": 1.4129, + "step": 4195 + }, + { + "epoch": 0.44, + "learning_rate": 1.3744255876238708e-05, + "loss": 1.3939, + "step": 4196 + }, + { + "epoch": 0.44, + "learning_rate": 1.3740861633106029e-05, + "loss": 1.3963, + "step": 4197 + }, + { + "epoch": 0.44, + "learning_rate": 1.3737466888794008e-05, + "loss": 1.5181, + "step": 4198 + }, + { + "epoch": 0.44, + "learning_rate": 1.3734071643757456e-05, + "loss": 1.4397, + "step": 4199 + }, + { + "epoch": 0.44, + "learning_rate": 1.373067589845125e-05, + "loss": 1.6293, + "step": 4200 + }, + { + "epoch": 0.44, + "learning_rate": 1.3727279653330328e-05, + "loss": 1.3498, + "step": 4201 + }, + { + "epoch": 0.44, + "learning_rate": 1.37238829088497e-05, + "loss": 1.4509, + "step": 4202 + }, + { + "epoch": 0.44, + "learning_rate": 1.3720485665464446e-05, + "loss": 1.4477, + "step": 4203 + }, + { + "epoch": 0.44, + "learning_rate": 1.3717087923629709e-05, + "loss": 1.4399, + "step": 4204 + }, + { + "epoch": 0.44, + "learning_rate": 1.3713689683800695e-05, + "loss": 1.4417, + "step": 4205 + }, + { + "epoch": 0.44, + "learning_rate": 1.3710290946432685e-05, + "loss": 1.3957, + "step": 4206 + }, + { + "epoch": 0.44, + "learning_rate": 1.3706891711981021e-05, + "loss": 1.4476, + "step": 4207 + }, + { + "epoch": 0.44, + "learning_rate": 1.3703491980901113e-05, + "loss": 1.3894, + "step": 4208 + }, + { + "epoch": 0.44, + "learning_rate": 1.3700091753648437e-05, + "loss": 1.4745, + "step": 4209 + }, + { + "epoch": 0.44, + "learning_rate": 1.369669103067854e-05, + "loss": 1.4038, + "step": 4210 + }, + { + "epoch": 0.44, + "learning_rate": 1.3693289812447023e-05, + "loss": 1.4151, + "step": 4211 + }, + { + "epoch": 0.44, + "learning_rate": 1.3689888099409572e-05, + "loss": 1.4214, + "step": 4212 + }, + { + "epoch": 0.44, + "learning_rate": 1.368648589202192e-05, + "loss": 1.4287, + "step": 4213 + }, + { + "epoch": 0.44, + "learning_rate": 1.3683083190739883e-05, + "loss": 1.345, + "step": 4214 + }, + { + "epoch": 0.44, + "learning_rate": 1.367967999601933e-05, + "loss": 1.3022, + "step": 4215 + }, + { + "epoch": 0.44, + "learning_rate": 1.3676276308316207e-05, + "loss": 1.3971, + "step": 4216 + }, + { + "epoch": 0.44, + "learning_rate": 1.3672872128086514e-05, + "loss": 1.3335, + "step": 4217 + }, + { + "epoch": 0.44, + "learning_rate": 1.366946745578633e-05, + "loss": 1.3988, + "step": 4218 + }, + { + "epoch": 0.44, + "learning_rate": 1.366606229187179e-05, + "loss": 1.4508, + "step": 4219 + }, + { + "epoch": 0.44, + "learning_rate": 1.3662656636799099e-05, + "loss": 1.3814, + "step": 4220 + }, + { + "epoch": 0.44, + "learning_rate": 1.3659250491024527e-05, + "loss": 1.4128, + "step": 4221 + }, + { + "epoch": 0.44, + "learning_rate": 1.3655843855004411e-05, + "loss": 1.3893, + "step": 4222 + }, + { + "epoch": 0.44, + "learning_rate": 1.3652436729195154e-05, + "loss": 1.2551, + "step": 4223 + }, + { + "epoch": 0.44, + "learning_rate": 1.3649029114053219e-05, + "loss": 1.4386, + "step": 4224 + }, + { + "epoch": 0.44, + "learning_rate": 1.364562101003514e-05, + "loss": 1.4028, + "step": 4225 + }, + { + "epoch": 0.44, + "learning_rate": 1.364221241759752e-05, + "loss": 1.4351, + "step": 4226 + }, + { + "epoch": 0.44, + "learning_rate": 1.363880333719702e-05, + "loss": 1.3941, + "step": 4227 + }, + { + "epoch": 0.44, + "learning_rate": 1.3635393769290368e-05, + "loss": 1.3879, + "step": 4228 + }, + { + "epoch": 0.44, + "learning_rate": 1.3631983714334358e-05, + "loss": 1.3773, + "step": 4229 + }, + { + "epoch": 0.44, + "learning_rate": 1.3628573172785853e-05, + "loss": 1.3679, + "step": 4230 + }, + { + "epoch": 0.44, + "learning_rate": 1.3625162145101776e-05, + "loss": 1.3705, + "step": 4231 + }, + { + "epoch": 0.44, + "learning_rate": 1.3621750631739114e-05, + "loss": 1.8157, + "step": 4232 + }, + { + "epoch": 0.44, + "learning_rate": 1.3618338633154928e-05, + "loss": 1.4056, + "step": 4233 + }, + { + "epoch": 0.44, + "learning_rate": 1.3614926149806334e-05, + "loss": 1.3716, + "step": 4234 + }, + { + "epoch": 0.44, + "learning_rate": 1.3611513182150523e-05, + "loss": 1.3766, + "step": 4235 + }, + { + "epoch": 0.44, + "learning_rate": 1.3608099730644733e-05, + "loss": 1.41, + "step": 4236 + }, + { + "epoch": 0.44, + "learning_rate": 1.3604685795746291e-05, + "loss": 1.421, + "step": 4237 + }, + { + "epoch": 0.44, + "learning_rate": 1.360127137791257e-05, + "loss": 1.3679, + "step": 4238 + }, + { + "epoch": 0.44, + "learning_rate": 1.3597856477601018e-05, + "loss": 1.4615, + "step": 4239 + }, + { + "epoch": 0.44, + "learning_rate": 1.359444109526914e-05, + "loss": 1.3418, + "step": 4240 + }, + { + "epoch": 0.44, + "learning_rate": 1.3591025231374513e-05, + "loss": 1.3631, + "step": 4241 + }, + { + "epoch": 0.44, + "learning_rate": 1.3587608886374772e-05, + "loss": 1.3802, + "step": 4242 + }, + { + "epoch": 0.44, + "learning_rate": 1.3584192060727622e-05, + "loss": 1.4156, + "step": 4243 + }, + { + "epoch": 0.45, + "learning_rate": 1.3580774754890827e-05, + "loss": 1.4161, + "step": 4244 + }, + { + "epoch": 0.45, + "learning_rate": 1.3577356969322222e-05, + "loss": 1.3535, + "step": 4245 + }, + { + "epoch": 0.45, + "learning_rate": 1.3573938704479699e-05, + "loss": 1.3859, + "step": 4246 + }, + { + "epoch": 0.45, + "learning_rate": 1.357051996082122e-05, + "loss": 1.3595, + "step": 4247 + }, + { + "epoch": 0.45, + "learning_rate": 1.3567100738804806e-05, + "loss": 1.4191, + "step": 4248 + }, + { + "epoch": 0.45, + "learning_rate": 1.3563681038888548e-05, + "loss": 1.4186, + "step": 4249 + }, + { + "epoch": 0.45, + "learning_rate": 1.3560260861530596e-05, + "loss": 1.43, + "step": 4250 + }, + { + "epoch": 0.45, + "learning_rate": 1.3556840207189168e-05, + "loss": 1.4139, + "step": 4251 + }, + { + "epoch": 0.45, + "learning_rate": 1.3553419076322539e-05, + "loss": 1.4005, + "step": 4252 + }, + { + "epoch": 0.45, + "learning_rate": 1.3549997469389058e-05, + "loss": 1.3468, + "step": 4253 + }, + { + "epoch": 0.45, + "learning_rate": 1.3546575386847132e-05, + "loss": 1.3756, + "step": 4254 + }, + { + "epoch": 0.45, + "learning_rate": 1.3543152829155226e-05, + "loss": 1.4063, + "step": 4255 + }, + { + "epoch": 0.45, + "learning_rate": 1.3539729796771884e-05, + "loss": 1.4666, + "step": 4256 + }, + { + "epoch": 0.45, + "learning_rate": 1.3536306290155694e-05, + "loss": 1.4212, + "step": 4257 + }, + { + "epoch": 0.45, + "learning_rate": 1.3532882309765332e-05, + "loss": 1.4883, + "step": 4258 + }, + { + "epoch": 0.45, + "learning_rate": 1.3529457856059507e-05, + "loss": 1.6641, + "step": 4259 + }, + { + "epoch": 0.45, + "learning_rate": 1.3526032929497022e-05, + "loss": 1.3659, + "step": 4260 + }, + { + "epoch": 0.45, + "learning_rate": 1.3522607530536717e-05, + "loss": 1.5945, + "step": 4261 + }, + { + "epoch": 0.45, + "learning_rate": 1.351918165963752e-05, + "loss": 1.3643, + "step": 4262 + }, + { + "epoch": 0.45, + "learning_rate": 1.3515755317258397e-05, + "loss": 1.3442, + "step": 4263 + }, + { + "epoch": 0.45, + "learning_rate": 1.3512328503858398e-05, + "loss": 1.3982, + "step": 4264 + }, + { + "epoch": 0.45, + "learning_rate": 1.3508901219896624e-05, + "loss": 1.4985, + "step": 4265 + }, + { + "epoch": 0.45, + "learning_rate": 1.350547346583225e-05, + "loss": 1.3319, + "step": 4266 + }, + { + "epoch": 0.45, + "learning_rate": 1.3502045242124497e-05, + "loss": 1.3961, + "step": 4267 + }, + { + "epoch": 0.45, + "learning_rate": 1.3498616549232665e-05, + "loss": 1.4565, + "step": 4268 + }, + { + "epoch": 0.45, + "learning_rate": 1.349518738761611e-05, + "loss": 1.375, + "step": 4269 + }, + { + "epoch": 0.45, + "learning_rate": 1.3491757757734254e-05, + "loss": 1.3005, + "step": 4270 + }, + { + "epoch": 0.45, + "learning_rate": 1.348832766004657e-05, + "loss": 1.3185, + "step": 4271 + }, + { + "epoch": 0.45, + "learning_rate": 1.3484897095012613e-05, + "loss": 1.4449, + "step": 4272 + }, + { + "epoch": 0.45, + "learning_rate": 1.3481466063091988e-05, + "loss": 1.3587, + "step": 4273 + }, + { + "epoch": 0.45, + "learning_rate": 1.3478034564744362e-05, + "loss": 1.3844, + "step": 4274 + }, + { + "epoch": 0.45, + "learning_rate": 1.3474602600429468e-05, + "loss": 1.4471, + "step": 4275 + }, + { + "epoch": 0.45, + "learning_rate": 1.3471170170607105e-05, + "loss": 1.4686, + "step": 4276 + }, + { + "epoch": 0.45, + "learning_rate": 1.3467737275737127e-05, + "loss": 1.312, + "step": 4277 + }, + { + "epoch": 0.45, + "learning_rate": 1.3464303916279453e-05, + "loss": 1.407, + "step": 4278 + }, + { + "epoch": 0.45, + "learning_rate": 1.346087009269407e-05, + "loss": 1.364, + "step": 4279 + }, + { + "epoch": 0.45, + "learning_rate": 1.3457435805441016e-05, + "loss": 1.4103, + "step": 4280 + }, + { + "epoch": 0.45, + "learning_rate": 1.3454001054980403e-05, + "loss": 1.4243, + "step": 4281 + }, + { + "epoch": 0.45, + "learning_rate": 1.3450565841772392e-05, + "loss": 1.3879, + "step": 4282 + }, + { + "epoch": 0.45, + "learning_rate": 1.344713016627722e-05, + "loss": 1.4688, + "step": 4283 + }, + { + "epoch": 0.45, + "learning_rate": 1.3443694028955176e-05, + "loss": 1.3983, + "step": 4284 + }, + { + "epoch": 0.45, + "learning_rate": 1.344025743026662e-05, + "loss": 1.4316, + "step": 4285 + }, + { + "epoch": 0.45, + "learning_rate": 1.3436820370671956e-05, + "loss": 1.3643, + "step": 4286 + }, + { + "epoch": 0.45, + "learning_rate": 1.3433382850631673e-05, + "loss": 1.4566, + "step": 4287 + }, + { + "epoch": 0.45, + "learning_rate": 1.3429944870606301e-05, + "loss": 1.1263, + "step": 4288 + }, + { + "epoch": 0.45, + "learning_rate": 1.3426506431056452e-05, + "loss": 1.2463, + "step": 4289 + }, + { + "epoch": 0.45, + "learning_rate": 1.342306753244278e-05, + "loss": 1.4753, + "step": 4290 + }, + { + "epoch": 0.45, + "learning_rate": 1.3419628175226012e-05, + "loss": 1.3789, + "step": 4291 + }, + { + "epoch": 0.45, + "learning_rate": 1.3416188359866932e-05, + "loss": 1.3906, + "step": 4292 + }, + { + "epoch": 0.45, + "learning_rate": 1.3412748086826389e-05, + "loss": 1.3995, + "step": 4293 + }, + { + "epoch": 0.45, + "learning_rate": 1.3409307356565288e-05, + "loss": 1.4906, + "step": 4294 + }, + { + "epoch": 0.45, + "learning_rate": 1.3405866169544602e-05, + "loss": 1.3951, + "step": 4295 + }, + { + "epoch": 0.45, + "learning_rate": 1.3402424526225359e-05, + "loss": 1.3753, + "step": 4296 + }, + { + "epoch": 0.45, + "learning_rate": 1.3398982427068654e-05, + "loss": 1.3686, + "step": 4297 + }, + { + "epoch": 0.45, + "learning_rate": 1.3395539872535636e-05, + "loss": 1.3612, + "step": 4298 + }, + { + "epoch": 0.45, + "learning_rate": 1.3392096863087522e-05, + "loss": 1.4043, + "step": 4299 + }, + { + "epoch": 0.45, + "learning_rate": 1.3388653399185585e-05, + "loss": 1.4068, + "step": 4300 + }, + { + "epoch": 0.45, + "learning_rate": 1.338520948129116e-05, + "loss": 1.4066, + "step": 4301 + }, + { + "epoch": 0.45, + "learning_rate": 1.3381765109865646e-05, + "loss": 1.4944, + "step": 4302 + }, + { + "epoch": 0.45, + "learning_rate": 1.3378320285370496e-05, + "loss": 1.3575, + "step": 4303 + }, + { + "epoch": 0.45, + "learning_rate": 1.3374875008267236e-05, + "loss": 1.3807, + "step": 4304 + }, + { + "epoch": 0.45, + "learning_rate": 1.3371429279017437e-05, + "loss": 1.4389, + "step": 4305 + }, + { + "epoch": 0.45, + "learning_rate": 1.3367983098082739e-05, + "loss": 1.4858, + "step": 4306 + }, + { + "epoch": 0.45, + "learning_rate": 1.3364536465924844e-05, + "loss": 1.3282, + "step": 4307 + }, + { + "epoch": 0.45, + "learning_rate": 1.3361089383005515e-05, + "loss": 1.4306, + "step": 4308 + }, + { + "epoch": 0.45, + "learning_rate": 1.3357641849786566e-05, + "loss": 1.3892, + "step": 4309 + }, + { + "epoch": 0.45, + "learning_rate": 1.3354193866729883e-05, + "loss": 1.3621, + "step": 4310 + }, + { + "epoch": 0.45, + "learning_rate": 1.3350745434297401e-05, + "loss": 1.3476, + "step": 4311 + }, + { + "epoch": 0.45, + "learning_rate": 1.334729655295113e-05, + "loss": 1.4477, + "step": 4312 + }, + { + "epoch": 0.45, + "learning_rate": 1.3343847223153123e-05, + "loss": 1.3585, + "step": 4313 + }, + { + "epoch": 0.45, + "learning_rate": 1.334039744536551e-05, + "loss": 1.3616, + "step": 4314 + }, + { + "epoch": 0.45, + "learning_rate": 1.3336947220050462e-05, + "loss": 1.3579, + "step": 4315 + }, + { + "epoch": 0.45, + "learning_rate": 1.3333496547670232e-05, + "loss": 1.3557, + "step": 4316 + }, + { + "epoch": 0.45, + "learning_rate": 1.3330045428687113e-05, + "loss": 1.4443, + "step": 4317 + }, + { + "epoch": 0.45, + "learning_rate": 1.332659386356347e-05, + "loss": 1.3621, + "step": 4318 + }, + { + "epoch": 0.45, + "learning_rate": 1.3323141852761726e-05, + "loss": 1.3295, + "step": 4319 + }, + { + "epoch": 0.45, + "learning_rate": 1.3319689396744358e-05, + "loss": 1.4187, + "step": 4320 + }, + { + "epoch": 0.45, + "learning_rate": 1.3316236495973905e-05, + "loss": 1.335, + "step": 4321 + }, + { + "epoch": 0.45, + "learning_rate": 1.331278315091297e-05, + "loss": 1.4382, + "step": 4322 + }, + { + "epoch": 0.45, + "learning_rate": 1.3309329362024212e-05, + "loss": 1.4244, + "step": 4323 + }, + { + "epoch": 0.45, + "learning_rate": 1.3305875129770351e-05, + "loss": 1.488, + "step": 4324 + }, + { + "epoch": 0.45, + "learning_rate": 1.3302420454614165e-05, + "loss": 1.3369, + "step": 4325 + }, + { + "epoch": 0.45, + "learning_rate": 1.3298965337018487e-05, + "loss": 1.3648, + "step": 4326 + }, + { + "epoch": 0.45, + "learning_rate": 1.3295509777446226e-05, + "loss": 1.3924, + "step": 4327 + }, + { + "epoch": 0.45, + "learning_rate": 1.3292053776360324e-05, + "loss": 1.3789, + "step": 4328 + }, + { + "epoch": 0.45, + "learning_rate": 1.3288597334223802e-05, + "loss": 1.3902, + "step": 4329 + }, + { + "epoch": 0.45, + "learning_rate": 1.3285140451499735e-05, + "loss": 1.4057, + "step": 4330 + }, + { + "epoch": 0.45, + "learning_rate": 1.328168312865126e-05, + "loss": 1.4536, + "step": 4331 + }, + { + "epoch": 0.45, + "learning_rate": 1.3278225366141565e-05, + "loss": 1.3075, + "step": 4332 + }, + { + "epoch": 0.45, + "learning_rate": 1.3274767164433901e-05, + "loss": 1.4579, + "step": 4333 + }, + { + "epoch": 0.45, + "learning_rate": 1.3271308523991579e-05, + "loss": 1.3906, + "step": 4334 + }, + { + "epoch": 0.45, + "learning_rate": 1.326784944527797e-05, + "loss": 1.3992, + "step": 4335 + }, + { + "epoch": 0.45, + "learning_rate": 1.3264389928756498e-05, + "loss": 1.4001, + "step": 4336 + }, + { + "epoch": 0.45, + "learning_rate": 1.3260929974890653e-05, + "loss": 1.2948, + "step": 4337 + }, + { + "epoch": 0.45, + "learning_rate": 1.3257469584143976e-05, + "loss": 1.4041, + "step": 4338 + }, + { + "epoch": 0.46, + "learning_rate": 1.3254008756980076e-05, + "loss": 1.5035, + "step": 4339 + }, + { + "epoch": 0.46, + "learning_rate": 1.3250547493862609e-05, + "loss": 1.4867, + "step": 4340 + }, + { + "epoch": 0.46, + "learning_rate": 1.3247085795255302e-05, + "loss": 1.3612, + "step": 4341 + }, + { + "epoch": 0.46, + "learning_rate": 1.3243623661621925e-05, + "loss": 1.4193, + "step": 4342 + }, + { + "epoch": 0.46, + "learning_rate": 1.3240161093426322e-05, + "loss": 1.3596, + "step": 4343 + }, + { + "epoch": 0.46, + "learning_rate": 1.3236698091132383e-05, + "loss": 1.4448, + "step": 4344 + }, + { + "epoch": 0.46, + "learning_rate": 1.3233234655204066e-05, + "loss": 1.3924, + "step": 4345 + }, + { + "epoch": 0.46, + "learning_rate": 1.322977078610538e-05, + "loss": 1.3552, + "step": 4346 + }, + { + "epoch": 0.46, + "learning_rate": 1.3226306484300395e-05, + "loss": 1.3949, + "step": 4347 + }, + { + "epoch": 0.46, + "learning_rate": 1.322284175025324e-05, + "loss": 1.399, + "step": 4348 + }, + { + "epoch": 0.46, + "learning_rate": 1.3219376584428094e-05, + "loss": 1.4755, + "step": 4349 + }, + { + "epoch": 0.46, + "learning_rate": 1.3215910987289212e-05, + "loss": 1.3877, + "step": 4350 + }, + { + "epoch": 0.46, + "learning_rate": 1.3212444959300882e-05, + "loss": 1.3916, + "step": 4351 + }, + { + "epoch": 0.46, + "learning_rate": 1.3208978500927472e-05, + "loss": 1.3462, + "step": 4352 + }, + { + "epoch": 0.46, + "learning_rate": 1.3205511612633392e-05, + "loss": 1.3834, + "step": 4353 + }, + { + "epoch": 0.46, + "learning_rate": 1.3202044294883123e-05, + "loss": 1.3843, + "step": 4354 + }, + { + "epoch": 0.46, + "learning_rate": 1.3198576548141189e-05, + "loss": 1.2439, + "step": 4355 + }, + { + "epoch": 0.46, + "learning_rate": 1.3195108372872181e-05, + "loss": 1.4106, + "step": 4356 + }, + { + "epoch": 0.46, + "learning_rate": 1.3191639769540746e-05, + "loss": 1.4417, + "step": 4357 + }, + { + "epoch": 0.46, + "learning_rate": 1.3188170738611596e-05, + "loss": 1.4393, + "step": 4358 + }, + { + "epoch": 0.46, + "learning_rate": 1.3184701280549476e-05, + "loss": 1.4616, + "step": 4359 + }, + { + "epoch": 0.46, + "learning_rate": 1.3181231395819218e-05, + "loss": 1.3215, + "step": 4360 + }, + { + "epoch": 0.46, + "learning_rate": 1.3177761084885689e-05, + "loss": 1.368, + "step": 4361 + }, + { + "epoch": 0.46, + "learning_rate": 1.317429034821383e-05, + "loss": 1.3247, + "step": 4362 + }, + { + "epoch": 0.46, + "learning_rate": 1.3170819186268618e-05, + "loss": 1.4512, + "step": 4363 + }, + { + "epoch": 0.46, + "learning_rate": 1.3167347599515111e-05, + "loss": 1.3129, + "step": 4364 + }, + { + "epoch": 0.46, + "learning_rate": 1.3163875588418404e-05, + "loss": 1.3934, + "step": 4365 + }, + { + "epoch": 0.46, + "learning_rate": 1.3160403153443666e-05, + "loss": 1.4518, + "step": 4366 + }, + { + "epoch": 0.46, + "learning_rate": 1.3156930295056105e-05, + "loss": 1.3959, + "step": 4367 + }, + { + "epoch": 0.46, + "learning_rate": 1.3153457013721e-05, + "loss": 1.3475, + "step": 4368 + }, + { + "epoch": 0.46, + "learning_rate": 1.3149983309903687e-05, + "loss": 1.4102, + "step": 4369 + }, + { + "epoch": 0.46, + "learning_rate": 1.3146509184069538e-05, + "loss": 1.3674, + "step": 4370 + }, + { + "epoch": 0.46, + "learning_rate": 1.314303463668401e-05, + "loss": 1.3739, + "step": 4371 + }, + { + "epoch": 0.46, + "learning_rate": 1.3139559668212596e-05, + "loss": 1.4249, + "step": 4372 + }, + { + "epoch": 0.46, + "learning_rate": 1.3136084279120857e-05, + "loss": 1.4473, + "step": 4373 + }, + { + "epoch": 0.46, + "learning_rate": 1.3132608469874404e-05, + "loss": 1.4443, + "step": 4374 + }, + { + "epoch": 0.46, + "learning_rate": 1.3129132240938905e-05, + "loss": 1.3534, + "step": 4375 + }, + { + "epoch": 0.46, + "learning_rate": 1.3125655592780083e-05, + "loss": 1.5663, + "step": 4376 + }, + { + "epoch": 0.46, + "learning_rate": 1.3122178525863727e-05, + "loss": 1.3465, + "step": 4377 + }, + { + "epoch": 0.46, + "learning_rate": 1.3118701040655669e-05, + "loss": 1.35, + "step": 4378 + }, + { + "epoch": 0.46, + "eval_loss": 1.447788953781128, + "eval_runtime": 77.4473, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4378 + }, + { + "epoch": 0.46, + "learning_rate": 1.3115223137621804e-05, + "loss": 1.343, + "step": 4379 + }, + { + "epoch": 0.46, + "learning_rate": 1.3111744817228078e-05, + "loss": 1.4227, + "step": 4380 + }, + { + "epoch": 0.46, + "learning_rate": 1.3108266079940508e-05, + "loss": 1.3982, + "step": 4381 + }, + { + "epoch": 0.46, + "learning_rate": 1.3104786926225141e-05, + "loss": 1.4211, + "step": 4382 + }, + { + "epoch": 0.46, + "learning_rate": 1.3101307356548103e-05, + "loss": 1.382, + "step": 4383 + }, + { + "epoch": 0.46, + "learning_rate": 1.3097827371375562e-05, + "loss": 1.4637, + "step": 4384 + }, + { + "epoch": 0.46, + "learning_rate": 1.3094346971173754e-05, + "loss": 1.4572, + "step": 4385 + }, + { + "epoch": 0.46, + "learning_rate": 1.3090866156408956e-05, + "loss": 1.5113, + "step": 4386 + }, + { + "epoch": 0.46, + "learning_rate": 1.3087384927547512e-05, + "loss": 1.2197, + "step": 4387 + }, + { + "epoch": 0.46, + "learning_rate": 1.3083903285055813e-05, + "loss": 1.3861, + "step": 4388 + }, + { + "epoch": 0.46, + "learning_rate": 1.3080421229400315e-05, + "loss": 1.4754, + "step": 4389 + }, + { + "epoch": 0.46, + "learning_rate": 1.307693876104752e-05, + "loss": 1.3588, + "step": 4390 + }, + { + "epoch": 0.46, + "learning_rate": 1.3073455880463987e-05, + "loss": 1.3995, + "step": 4391 + }, + { + "epoch": 0.46, + "learning_rate": 1.3069972588116341e-05, + "loss": 1.354, + "step": 4392 + }, + { + "epoch": 0.46, + "learning_rate": 1.3066488884471244e-05, + "loss": 1.3378, + "step": 4393 + }, + { + "epoch": 0.46, + "learning_rate": 1.306300476999543e-05, + "loss": 1.5951, + "step": 4394 + }, + { + "epoch": 0.46, + "learning_rate": 1.305952024515568e-05, + "loss": 1.3661, + "step": 4395 + }, + { + "epoch": 0.46, + "learning_rate": 1.3056035310418826e-05, + "loss": 1.4066, + "step": 4396 + }, + { + "epoch": 0.46, + "learning_rate": 1.3052549966251764e-05, + "loss": 1.3687, + "step": 4397 + }, + { + "epoch": 0.46, + "learning_rate": 1.3049064213121438e-05, + "loss": 1.4573, + "step": 4398 + }, + { + "epoch": 0.46, + "learning_rate": 1.3045578051494852e-05, + "loss": 1.3519, + "step": 4399 + }, + { + "epoch": 0.46, + "learning_rate": 1.3042091481839063e-05, + "loss": 1.2803, + "step": 4400 + }, + { + "epoch": 0.46, + "learning_rate": 1.3038604504621173e-05, + "loss": 1.4014, + "step": 4401 + }, + { + "epoch": 0.46, + "learning_rate": 1.3035117120308358e-05, + "loss": 1.4534, + "step": 4402 + }, + { + "epoch": 0.46, + "learning_rate": 1.3031629329367832e-05, + "loss": 1.4747, + "step": 4403 + }, + { + "epoch": 0.46, + "learning_rate": 1.3028141132266877e-05, + "loss": 1.374, + "step": 4404 + }, + { + "epoch": 0.46, + "learning_rate": 1.3024652529472807e-05, + "loss": 1.4328, + "step": 4405 + }, + { + "epoch": 0.46, + "learning_rate": 1.302116352145302e-05, + "loss": 1.468, + "step": 4406 + }, + { + "epoch": 0.46, + "learning_rate": 1.3017674108674942e-05, + "loss": 1.2947, + "step": 4407 + }, + { + "epoch": 0.46, + "learning_rate": 1.3014184291606077e-05, + "loss": 1.3682, + "step": 4408 + }, + { + "epoch": 0.46, + "learning_rate": 1.3010694070713959e-05, + "loss": 1.3651, + "step": 4409 + }, + { + "epoch": 0.46, + "learning_rate": 1.3007203446466194e-05, + "loss": 1.418, + "step": 4410 + }, + { + "epoch": 0.46, + "learning_rate": 1.3003712419330433e-05, + "loss": 1.416, + "step": 4411 + }, + { + "epoch": 0.46, + "learning_rate": 1.300022098977439e-05, + "loss": 1.2979, + "step": 4412 + }, + { + "epoch": 0.46, + "learning_rate": 1.2996729158265819e-05, + "loss": 1.3868, + "step": 4413 + }, + { + "epoch": 0.46, + "learning_rate": 1.2993236925272542e-05, + "loss": 1.3102, + "step": 4414 + }, + { + "epoch": 0.46, + "learning_rate": 1.2989744291262422e-05, + "loss": 1.3506, + "step": 4415 + }, + { + "epoch": 0.46, + "learning_rate": 1.2986251256703388e-05, + "loss": 1.4018, + "step": 4416 + }, + { + "epoch": 0.46, + "learning_rate": 1.2982757822063417e-05, + "loss": 1.4081, + "step": 4417 + }, + { + "epoch": 0.46, + "learning_rate": 1.2979263987810533e-05, + "loss": 1.3592, + "step": 4418 + }, + { + "epoch": 0.46, + "learning_rate": 1.297576975441283e-05, + "loss": 1.4287, + "step": 4419 + }, + { + "epoch": 0.46, + "learning_rate": 1.2972275122338433e-05, + "loss": 1.4099, + "step": 4420 + }, + { + "epoch": 0.46, + "learning_rate": 1.2968780092055546e-05, + "loss": 1.4005, + "step": 4421 + }, + { + "epoch": 0.46, + "learning_rate": 1.2965284664032401e-05, + "loss": 1.365, + "step": 4422 + }, + { + "epoch": 0.46, + "learning_rate": 1.2961788838737309e-05, + "loss": 1.3588, + "step": 4423 + }, + { + "epoch": 0.46, + "learning_rate": 1.2958292616638606e-05, + "loss": 1.3702, + "step": 4424 + }, + { + "epoch": 0.46, + "learning_rate": 1.2954795998204708e-05, + "loss": 1.3487, + "step": 4425 + }, + { + "epoch": 0.46, + "learning_rate": 1.2951298983904063e-05, + "loss": 1.4395, + "step": 4426 + }, + { + "epoch": 0.46, + "learning_rate": 1.2947801574205193e-05, + "loss": 1.3523, + "step": 4427 + }, + { + "epoch": 0.46, + "learning_rate": 1.2944303769576645e-05, + "loss": 1.3125, + "step": 4428 + }, + { + "epoch": 0.46, + "learning_rate": 1.2940805570487048e-05, + "loss": 1.5476, + "step": 4429 + }, + { + "epoch": 0.46, + "learning_rate": 1.2937306977405062e-05, + "loss": 1.4076, + "step": 4430 + }, + { + "epoch": 0.46, + "learning_rate": 1.2933807990799418e-05, + "loss": 1.3007, + "step": 4431 + }, + { + "epoch": 0.46, + "learning_rate": 1.293030861113888e-05, + "loss": 1.3566, + "step": 4432 + }, + { + "epoch": 0.46, + "learning_rate": 1.2926808838892285e-05, + "loss": 1.3907, + "step": 4433 + }, + { + "epoch": 0.46, + "learning_rate": 1.2923308674528501e-05, + "loss": 1.379, + "step": 4434 + }, + { + "epoch": 0.47, + "learning_rate": 1.2919808118516475e-05, + "loss": 1.4319, + "step": 4435 + }, + { + "epoch": 0.47, + "learning_rate": 1.2916307171325176e-05, + "loss": 1.3392, + "step": 4436 + }, + { + "epoch": 0.47, + "learning_rate": 1.291280583342365e-05, + "loss": 1.401, + "step": 4437 + }, + { + "epoch": 0.47, + "learning_rate": 1.2909304105280984e-05, + "loss": 1.3939, + "step": 4438 + }, + { + "epoch": 0.47, + "learning_rate": 1.2905801987366322e-05, + "loss": 1.4676, + "step": 4439 + }, + { + "epoch": 0.47, + "learning_rate": 1.2902299480148855e-05, + "loss": 1.3957, + "step": 4440 + }, + { + "epoch": 0.47, + "learning_rate": 1.2898796584097828e-05, + "loss": 1.3587, + "step": 4441 + }, + { + "epoch": 0.47, + "learning_rate": 1.2895293299682545e-05, + "loss": 1.5809, + "step": 4442 + }, + { + "epoch": 0.47, + "learning_rate": 1.289178962737235e-05, + "loss": 1.3436, + "step": 4443 + }, + { + "epoch": 0.47, + "learning_rate": 1.2888285567636647e-05, + "loss": 1.4535, + "step": 4444 + }, + { + "epoch": 0.47, + "learning_rate": 1.2884781120944889e-05, + "loss": 1.3377, + "step": 4445 + }, + { + "epoch": 0.47, + "learning_rate": 1.2881276287766587e-05, + "loss": 0.8221, + "step": 4446 + }, + { + "epoch": 0.47, + "learning_rate": 1.2877771068571288e-05, + "loss": 0.7259, + "step": 4447 + }, + { + "epoch": 0.47, + "learning_rate": 1.2874265463828612e-05, + "loss": 0.8279, + "step": 4448 + }, + { + "epoch": 0.47, + "learning_rate": 1.2870759474008213e-05, + "loss": 1.3523, + "step": 4449 + }, + { + "epoch": 0.47, + "learning_rate": 1.2867253099579808e-05, + "loss": 1.3658, + "step": 4450 + }, + { + "epoch": 0.47, + "learning_rate": 1.2863746341013158e-05, + "loss": 1.4112, + "step": 4451 + }, + { + "epoch": 0.47, + "learning_rate": 1.2860239198778085e-05, + "loss": 1.389, + "step": 4452 + }, + { + "epoch": 0.47, + "learning_rate": 1.2856731673344442e-05, + "loss": 1.4066, + "step": 4453 + }, + { + "epoch": 0.47, + "learning_rate": 1.2853223765182165e-05, + "loss": 1.3267, + "step": 4454 + }, + { + "epoch": 0.47, + "learning_rate": 1.2849715474761209e-05, + "loss": 1.3381, + "step": 4455 + }, + { + "epoch": 0.47, + "learning_rate": 1.2846206802551602e-05, + "loss": 1.2882, + "step": 4456 + }, + { + "epoch": 0.47, + "learning_rate": 1.2842697749023414e-05, + "loss": 1.3199, + "step": 4457 + }, + { + "epoch": 0.47, + "learning_rate": 1.2839188314646771e-05, + "loss": 1.3896, + "step": 4458 + }, + { + "epoch": 0.47, + "learning_rate": 1.2835678499891842e-05, + "loss": 1.3186, + "step": 4459 + }, + { + "epoch": 0.47, + "learning_rate": 1.283216830522885e-05, + "loss": 1.3466, + "step": 4460 + }, + { + "epoch": 0.47, + "learning_rate": 1.2828657731128083e-05, + "loss": 1.4678, + "step": 4461 + }, + { + "epoch": 0.47, + "learning_rate": 1.2825146778059857e-05, + "loss": 1.4408, + "step": 4462 + }, + { + "epoch": 0.47, + "learning_rate": 1.2821635446494553e-05, + "loss": 1.3672, + "step": 4463 + }, + { + "epoch": 0.47, + "learning_rate": 1.2818123736902597e-05, + "loss": 1.3836, + "step": 4464 + }, + { + "epoch": 0.47, + "learning_rate": 1.2814611649754472e-05, + "loss": 1.3493, + "step": 4465 + }, + { + "epoch": 0.47, + "learning_rate": 1.2811099185520704e-05, + "loss": 1.3584, + "step": 4466 + }, + { + "epoch": 0.47, + "learning_rate": 1.2807586344671875e-05, + "loss": 1.3551, + "step": 4467 + }, + { + "epoch": 0.47, + "learning_rate": 1.2804073127678612e-05, + "loss": 1.3254, + "step": 4468 + }, + { + "epoch": 0.47, + "learning_rate": 1.28005595350116e-05, + "loss": 1.3405, + "step": 4469 + }, + { + "epoch": 0.47, + "learning_rate": 1.2797045567141568e-05, + "loss": 1.3432, + "step": 4470 + }, + { + "epoch": 0.47, + "learning_rate": 1.2793531224539297e-05, + "loss": 1.4347, + "step": 4471 + }, + { + "epoch": 0.47, + "learning_rate": 1.279001650767562e-05, + "loss": 1.3304, + "step": 4472 + }, + { + "epoch": 0.47, + "learning_rate": 1.278650141702142e-05, + "loss": 1.3244, + "step": 4473 + }, + { + "epoch": 0.47, + "learning_rate": 1.2782985953047625e-05, + "loss": 1.3756, + "step": 4474 + }, + { + "epoch": 0.47, + "learning_rate": 1.2779470116225219e-05, + "loss": 1.5468, + "step": 4475 + }, + { + "epoch": 0.47, + "learning_rate": 1.2775953907025232e-05, + "loss": 1.4316, + "step": 4476 + }, + { + "epoch": 0.47, + "learning_rate": 1.2772437325918752e-05, + "loss": 1.3724, + "step": 4477 + }, + { + "epoch": 0.47, + "learning_rate": 1.27689203733769e-05, + "loss": 1.4458, + "step": 4478 + }, + { + "epoch": 0.47, + "learning_rate": 1.2765403049870865e-05, + "loss": 1.3622, + "step": 4479 + }, + { + "epoch": 0.47, + "learning_rate": 1.2761885355871875e-05, + "loss": 1.3875, + "step": 4480 + }, + { + "epoch": 0.47, + "learning_rate": 1.2758367291851217e-05, + "loss": 1.3577, + "step": 4481 + }, + { + "epoch": 0.47, + "learning_rate": 1.2754848858280211e-05, + "loss": 1.4256, + "step": 4482 + }, + { + "epoch": 0.47, + "learning_rate": 1.2751330055630242e-05, + "loss": 1.3771, + "step": 4483 + }, + { + "epoch": 0.47, + "learning_rate": 1.274781088437274e-05, + "loss": 1.357, + "step": 4484 + }, + { + "epoch": 0.47, + "learning_rate": 1.274429134497918e-05, + "loss": 1.3634, + "step": 4485 + }, + { + "epoch": 0.47, + "learning_rate": 1.2740771437921096e-05, + "loss": 1.3661, + "step": 4486 + }, + { + "epoch": 0.47, + "learning_rate": 1.2737251163670057e-05, + "loss": 1.3819, + "step": 4487 + }, + { + "epoch": 0.47, + "learning_rate": 1.2733730522697696e-05, + "loss": 1.4491, + "step": 4488 + }, + { + "epoch": 0.47, + "learning_rate": 1.2730209515475687e-05, + "loss": 1.3857, + "step": 4489 + }, + { + "epoch": 0.47, + "learning_rate": 1.2726688142475751e-05, + "loss": 1.3837, + "step": 4490 + }, + { + "epoch": 0.47, + "learning_rate": 1.2723166404169663e-05, + "loss": 1.3755, + "step": 4491 + }, + { + "epoch": 0.47, + "learning_rate": 1.271964430102925e-05, + "loss": 1.3767, + "step": 4492 + }, + { + "epoch": 0.47, + "learning_rate": 1.2716121833526376e-05, + "loss": 1.4416, + "step": 4493 + }, + { + "epoch": 0.47, + "learning_rate": 1.2712599002132966e-05, + "loss": 1.5573, + "step": 4494 + }, + { + "epoch": 0.47, + "learning_rate": 1.2709075807320988e-05, + "loss": 1.365, + "step": 4495 + }, + { + "epoch": 0.47, + "learning_rate": 1.270555224956246e-05, + "loss": 1.3862, + "step": 4496 + }, + { + "epoch": 0.47, + "learning_rate": 1.2702028329329445e-05, + "loss": 1.3003, + "step": 4497 + }, + { + "epoch": 0.47, + "learning_rate": 1.2698504047094064e-05, + "loss": 1.3806, + "step": 4498 + }, + { + "epoch": 0.47, + "learning_rate": 1.269497940332847e-05, + "loss": 1.5425, + "step": 4499 + }, + { + "epoch": 0.47, + "learning_rate": 1.269145439850489e-05, + "loss": 1.3541, + "step": 4500 + }, + { + "epoch": 0.47, + "learning_rate": 1.268792903309557e-05, + "loss": 1.4337, + "step": 4501 + }, + { + "epoch": 0.47, + "learning_rate": 1.2684403307572825e-05, + "loss": 1.4004, + "step": 4502 + }, + { + "epoch": 0.47, + "learning_rate": 1.268087722240901e-05, + "loss": 1.9453, + "step": 4503 + }, + { + "epoch": 0.47, + "learning_rate": 1.2677350778076532e-05, + "loss": 1.3907, + "step": 4504 + }, + { + "epoch": 0.47, + "learning_rate": 1.2673823975047839e-05, + "loss": 1.4993, + "step": 4505 + }, + { + "epoch": 0.47, + "learning_rate": 1.2670296813795432e-05, + "loss": 1.4386, + "step": 4506 + }, + { + "epoch": 0.47, + "learning_rate": 1.266676929479187e-05, + "loss": 1.4944, + "step": 4507 + }, + { + "epoch": 0.47, + "learning_rate": 1.266324141850974e-05, + "loss": 1.4311, + "step": 4508 + }, + { + "epoch": 0.47, + "learning_rate": 1.265971318542169e-05, + "loss": 1.3607, + "step": 4509 + }, + { + "epoch": 0.47, + "learning_rate": 1.2656184596000412e-05, + "loss": 1.4007, + "step": 4510 + }, + { + "epoch": 0.47, + "learning_rate": 1.2652655650718645e-05, + "loss": 1.4561, + "step": 4511 + }, + { + "epoch": 0.47, + "learning_rate": 1.2649126350049181e-05, + "loss": 1.4321, + "step": 4512 + }, + { + "epoch": 0.47, + "learning_rate": 1.2645596694464851e-05, + "loss": 1.2856, + "step": 4513 + }, + { + "epoch": 0.47, + "learning_rate": 1.2642066684438543e-05, + "loss": 1.3979, + "step": 4514 + }, + { + "epoch": 0.47, + "learning_rate": 1.2638536320443184e-05, + "loss": 1.4977, + "step": 4515 + }, + { + "epoch": 0.47, + "learning_rate": 1.2635005602951752e-05, + "loss": 1.377, + "step": 4516 + }, + { + "epoch": 0.47, + "learning_rate": 1.2631474532437275e-05, + "loss": 1.4266, + "step": 4517 + }, + { + "epoch": 0.47, + "learning_rate": 1.2627943109372822e-05, + "loss": 1.409, + "step": 4518 + }, + { + "epoch": 0.47, + "learning_rate": 1.2624411334231519e-05, + "loss": 1.3374, + "step": 4519 + }, + { + "epoch": 0.47, + "learning_rate": 1.2620879207486525e-05, + "loss": 1.3765, + "step": 4520 + }, + { + "epoch": 0.47, + "learning_rate": 1.2617346729611061e-05, + "loss": 1.3805, + "step": 4521 + }, + { + "epoch": 0.47, + "learning_rate": 1.2613813901078384e-05, + "loss": 1.3326, + "step": 4522 + }, + { + "epoch": 0.47, + "learning_rate": 1.2610280722361807e-05, + "loss": 1.3909, + "step": 4523 + }, + { + "epoch": 0.47, + "learning_rate": 1.260674719393468e-05, + "loss": 1.3815, + "step": 4524 + }, + { + "epoch": 0.47, + "learning_rate": 1.2603213316270409e-05, + "loss": 1.5589, + "step": 4525 + }, + { + "epoch": 0.47, + "learning_rate": 1.2599679089842437e-05, + "loss": 1.4416, + "step": 4526 + }, + { + "epoch": 0.47, + "learning_rate": 1.259614451512427e-05, + "loss": 1.3529, + "step": 4527 + }, + { + "epoch": 0.47, + "learning_rate": 1.2592609592589437e-05, + "loss": 1.3135, + "step": 4528 + }, + { + "epoch": 0.47, + "learning_rate": 1.2589074322711535e-05, + "loss": 1.4177, + "step": 4529 + }, + { + "epoch": 0.48, + "learning_rate": 1.25855387059642e-05, + "loss": 1.353, + "step": 4530 + }, + { + "epoch": 0.48, + "learning_rate": 1.2582002742821111e-05, + "loss": 1.431, + "step": 4531 + }, + { + "epoch": 0.48, + "learning_rate": 1.2578466433755998e-05, + "loss": 1.3803, + "step": 4532 + }, + { + "epoch": 0.48, + "learning_rate": 1.257492977924263e-05, + "loss": 1.3774, + "step": 4533 + }, + { + "epoch": 0.48, + "learning_rate": 1.2571392779754836e-05, + "loss": 1.4339, + "step": 4534 + }, + { + "epoch": 0.48, + "learning_rate": 1.256785543576648e-05, + "loss": 1.4097, + "step": 4535 + }, + { + "epoch": 0.48, + "learning_rate": 1.2564317747751473e-05, + "loss": 1.4223, + "step": 4536 + }, + { + "epoch": 0.48, + "learning_rate": 1.2560779716183775e-05, + "loss": 1.5148, + "step": 4537 + }, + { + "epoch": 0.48, + "learning_rate": 1.2557241341537394e-05, + "loss": 1.3547, + "step": 4538 + }, + { + "epoch": 0.48, + "learning_rate": 1.255370262428638e-05, + "loss": 1.393, + "step": 4539 + }, + { + "epoch": 0.48, + "learning_rate": 1.2550163564904829e-05, + "loss": 1.3312, + "step": 4540 + }, + { + "epoch": 0.48, + "learning_rate": 1.2546624163866882e-05, + "loss": 1.4193, + "step": 4541 + }, + { + "epoch": 0.48, + "learning_rate": 1.2543084421646735e-05, + "loss": 1.4161, + "step": 4542 + }, + { + "epoch": 0.48, + "learning_rate": 1.2539544338718614e-05, + "loss": 1.4224, + "step": 4543 + }, + { + "epoch": 0.48, + "learning_rate": 1.2536003915556805e-05, + "loss": 1.3484, + "step": 4544 + }, + { + "epoch": 0.48, + "learning_rate": 1.253246315263563e-05, + "loss": 1.4492, + "step": 4545 + }, + { + "epoch": 0.48, + "learning_rate": 1.2528922050429467e-05, + "loss": 1.3549, + "step": 4546 + }, + { + "epoch": 0.48, + "learning_rate": 1.252538060941272e-05, + "loss": 1.45, + "step": 4547 + }, + { + "epoch": 0.48, + "learning_rate": 1.2521838830059865e-05, + "loss": 1.3499, + "step": 4548 + }, + { + "epoch": 0.48, + "learning_rate": 1.2518296712845399e-05, + "loss": 1.3786, + "step": 4549 + }, + { + "epoch": 0.48, + "learning_rate": 1.2514754258243884e-05, + "loss": 1.3394, + "step": 4550 + }, + { + "epoch": 0.48, + "learning_rate": 1.2511211466729909e-05, + "loss": 1.2849, + "step": 4551 + }, + { + "epoch": 0.48, + "learning_rate": 1.250766833877812e-05, + "loss": 1.374, + "step": 4552 + }, + { + "epoch": 0.48, + "learning_rate": 1.2504124874863211e-05, + "loss": 1.3084, + "step": 4553 + }, + { + "epoch": 0.48, + "learning_rate": 1.2500581075459905e-05, + "loss": 1.3348, + "step": 4554 + }, + { + "epoch": 0.48, + "learning_rate": 1.249703694104299e-05, + "loss": 1.3797, + "step": 4555 + }, + { + "epoch": 0.48, + "learning_rate": 1.2493492472087279e-05, + "loss": 1.3371, + "step": 4556 + }, + { + "epoch": 0.48, + "learning_rate": 1.248994766906765e-05, + "loss": 1.3974, + "step": 4557 + }, + { + "epoch": 0.48, + "learning_rate": 1.2486402532459007e-05, + "loss": 1.388, + "step": 4558 + }, + { + "epoch": 0.48, + "learning_rate": 1.2482857062736313e-05, + "loss": 1.3619, + "step": 4559 + }, + { + "epoch": 0.48, + "learning_rate": 1.2479311260374565e-05, + "loss": 1.4123, + "step": 4560 + }, + { + "epoch": 0.48, + "learning_rate": 1.2475765125848814e-05, + "loss": 1.5485, + "step": 4561 + }, + { + "epoch": 0.48, + "learning_rate": 1.247221865963415e-05, + "loss": 1.4965, + "step": 4562 + }, + { + "epoch": 0.48, + "learning_rate": 1.2468671862205705e-05, + "loss": 1.4352, + "step": 4563 + }, + { + "epoch": 0.48, + "learning_rate": 1.246512473403866e-05, + "loss": 1.3935, + "step": 4564 + }, + { + "epoch": 0.48, + "learning_rate": 1.2461577275608243e-05, + "loss": 1.3798, + "step": 4565 + }, + { + "epoch": 0.48, + "learning_rate": 1.2458029487389718e-05, + "loss": 1.4039, + "step": 4566 + }, + { + "epoch": 0.48, + "learning_rate": 1.2454481369858397e-05, + "loss": 1.3723, + "step": 4567 + }, + { + "epoch": 0.48, + "learning_rate": 1.245093292348964e-05, + "loss": 1.3713, + "step": 4568 + }, + { + "epoch": 0.48, + "learning_rate": 1.2447384148758847e-05, + "loss": 1.4083, + "step": 4569 + }, + { + "epoch": 0.48, + "learning_rate": 1.244383504614146e-05, + "loss": 1.2811, + "step": 4570 + }, + { + "epoch": 0.48, + "learning_rate": 1.2440285616112968e-05, + "loss": 1.3509, + "step": 4571 + }, + { + "epoch": 0.48, + "learning_rate": 1.2436735859148905e-05, + "loss": 1.3481, + "step": 4572 + }, + { + "epoch": 0.48, + "learning_rate": 1.2433185775724847e-05, + "loss": 1.4168, + "step": 4573 + }, + { + "epoch": 0.48, + "learning_rate": 1.2429635366316418e-05, + "loss": 1.3671, + "step": 4574 + }, + { + "epoch": 0.48, + "learning_rate": 1.2426084631399271e-05, + "loss": 1.6514, + "step": 4575 + }, + { + "epoch": 0.48, + "learning_rate": 1.2422533571449123e-05, + "loss": 1.3564, + "step": 4576 + }, + { + "epoch": 0.48, + "learning_rate": 1.2418982186941721e-05, + "loss": 1.4586, + "step": 4577 + }, + { + "epoch": 0.48, + "eval_loss": 1.4425245523452759, + "eval_runtime": 77.3853, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 4577 + }, + { + "epoch": 0.48, + "learning_rate": 1.2415430478352858e-05, + "loss": 1.3922, + "step": 4578 + }, + { + "epoch": 0.48, + "learning_rate": 1.2411878446158374e-05, + "loss": 1.3903, + "step": 4579 + }, + { + "epoch": 0.48, + "learning_rate": 1.240832609083415e-05, + "loss": 1.3537, + "step": 4580 + }, + { + "epoch": 0.48, + "learning_rate": 1.2404773412856113e-05, + "loss": 1.356, + "step": 4581 + }, + { + "epoch": 0.48, + "learning_rate": 1.2401220412700223e-05, + "loss": 1.4483, + "step": 4582 + }, + { + "epoch": 0.48, + "learning_rate": 1.2397667090842496e-05, + "loss": 1.3926, + "step": 4583 + }, + { + "epoch": 0.48, + "learning_rate": 1.2394113447758986e-05, + "loss": 1.4816, + "step": 4584 + }, + { + "epoch": 0.48, + "learning_rate": 1.2390559483925788e-05, + "loss": 1.3742, + "step": 4585 + }, + { + "epoch": 0.48, + "learning_rate": 1.2387005199819044e-05, + "loss": 1.4476, + "step": 4586 + }, + { + "epoch": 0.48, + "learning_rate": 1.2383450595914932e-05, + "loss": 1.4029, + "step": 4587 + }, + { + "epoch": 0.48, + "learning_rate": 1.2379895672689683e-05, + "loss": 1.4797, + "step": 4588 + }, + { + "epoch": 0.48, + "learning_rate": 1.2376340430619565e-05, + "loss": 1.3366, + "step": 4589 + }, + { + "epoch": 0.48, + "learning_rate": 1.2372784870180885e-05, + "loss": 1.4226, + "step": 4590 + }, + { + "epoch": 0.48, + "learning_rate": 1.2369228991849997e-05, + "loss": 1.3668, + "step": 4591 + }, + { + "epoch": 0.48, + "learning_rate": 1.2365672796103305e-05, + "loss": 1.4932, + "step": 4592 + }, + { + "epoch": 0.48, + "learning_rate": 1.236211628341724e-05, + "loss": 1.4088, + "step": 4593 + }, + { + "epoch": 0.48, + "learning_rate": 1.2358559454268284e-05, + "loss": 1.3616, + "step": 4594 + }, + { + "epoch": 0.48, + "learning_rate": 1.2355002309132961e-05, + "loss": 1.4345, + "step": 4595 + }, + { + "epoch": 0.48, + "learning_rate": 1.2351444848487844e-05, + "loss": 1.4025, + "step": 4596 + }, + { + "epoch": 0.48, + "learning_rate": 1.2347887072809533e-05, + "loss": 1.3895, + "step": 4597 + }, + { + "epoch": 0.48, + "learning_rate": 1.2344328982574678e-05, + "loss": 1.3326, + "step": 4598 + }, + { + "epoch": 0.48, + "learning_rate": 1.234077057825998e-05, + "loss": 1.4249, + "step": 4599 + }, + { + "epoch": 0.48, + "learning_rate": 1.2337211860342167e-05, + "loss": 1.3649, + "step": 4600 + }, + { + "epoch": 0.48, + "learning_rate": 1.2333652829298016e-05, + "loss": 1.3831, + "step": 4601 + }, + { + "epoch": 0.48, + "learning_rate": 1.2330093485604346e-05, + "loss": 1.3748, + "step": 4602 + }, + { + "epoch": 0.48, + "learning_rate": 1.2326533829738022e-05, + "loss": 1.386, + "step": 4603 + }, + { + "epoch": 0.48, + "learning_rate": 1.2322973862175941e-05, + "loss": 1.3923, + "step": 4604 + }, + { + "epoch": 0.48, + "learning_rate": 1.2319413583395052e-05, + "loss": 1.3638, + "step": 4605 + }, + { + "epoch": 0.48, + "learning_rate": 1.2315852993872335e-05, + "loss": 1.3476, + "step": 4606 + }, + { + "epoch": 0.48, + "learning_rate": 1.2312292094084824e-05, + "loss": 1.3581, + "step": 4607 + }, + { + "epoch": 0.48, + "learning_rate": 1.2308730884509583e-05, + "loss": 1.3554, + "step": 4608 + }, + { + "epoch": 0.48, + "learning_rate": 1.2305169365623724e-05, + "loss": 1.3676, + "step": 4609 + }, + { + "epoch": 0.48, + "learning_rate": 1.2301607537904399e-05, + "loss": 1.24, + "step": 4610 + }, + { + "epoch": 0.48, + "learning_rate": 1.2298045401828803e-05, + "loss": 1.3295, + "step": 4611 + }, + { + "epoch": 0.48, + "learning_rate": 1.2294482957874169e-05, + "loss": 1.5684, + "step": 4612 + }, + { + "epoch": 0.48, + "learning_rate": 1.2290920206517774e-05, + "loss": 1.3403, + "step": 4613 + }, + { + "epoch": 0.48, + "learning_rate": 1.2287357148236933e-05, + "loss": 1.349, + "step": 4614 + }, + { + "epoch": 0.48, + "learning_rate": 1.2283793783509008e-05, + "loss": 1.4261, + "step": 4615 + }, + { + "epoch": 0.48, + "learning_rate": 1.2280230112811395e-05, + "loss": 1.322, + "step": 4616 + }, + { + "epoch": 0.48, + "learning_rate": 1.2276666136621538e-05, + "loss": 1.3399, + "step": 4617 + }, + { + "epoch": 0.48, + "learning_rate": 1.2273101855416912e-05, + "loss": 1.3878, + "step": 4618 + }, + { + "epoch": 0.48, + "learning_rate": 1.2269537269675044e-05, + "loss": 1.4733, + "step": 4619 + }, + { + "epoch": 0.48, + "learning_rate": 1.2265972379873497e-05, + "loss": 1.419, + "step": 4620 + }, + { + "epoch": 0.48, + "learning_rate": 1.226240718648987e-05, + "loss": 1.3918, + "step": 4621 + }, + { + "epoch": 0.48, + "learning_rate": 1.2258841690001815e-05, + "loss": 1.3398, + "step": 4622 + }, + { + "epoch": 0.48, + "learning_rate": 1.225527589088701e-05, + "loss": 1.4091, + "step": 4623 + }, + { + "epoch": 0.48, + "learning_rate": 1.2251709789623185e-05, + "loss": 1.3291, + "step": 4624 + }, + { + "epoch": 0.49, + "learning_rate": 1.2248143386688101e-05, + "loss": 1.4288, + "step": 4625 + }, + { + "epoch": 0.49, + "learning_rate": 1.224457668255957e-05, + "loss": 1.2942, + "step": 4626 + }, + { + "epoch": 0.49, + "learning_rate": 1.2241009677715437e-05, + "loss": 1.4014, + "step": 4627 + }, + { + "epoch": 0.49, + "learning_rate": 1.2237442372633586e-05, + "loss": 1.3823, + "step": 4628 + }, + { + "epoch": 0.49, + "learning_rate": 1.2233874767791945e-05, + "loss": 1.3556, + "step": 4629 + }, + { + "epoch": 0.49, + "learning_rate": 1.2230306863668485e-05, + "loss": 1.411, + "step": 4630 + }, + { + "epoch": 0.49, + "learning_rate": 1.2226738660741212e-05, + "loss": 1.4347, + "step": 4631 + }, + { + "epoch": 0.49, + "learning_rate": 1.2223170159488169e-05, + "loss": 1.3095, + "step": 4632 + }, + { + "epoch": 0.49, + "learning_rate": 1.221960136038745e-05, + "loss": 1.4272, + "step": 4633 + }, + { + "epoch": 0.49, + "learning_rate": 1.221603226391718e-05, + "loss": 1.367, + "step": 4634 + }, + { + "epoch": 0.49, + "learning_rate": 1.2212462870555523e-05, + "loss": 1.3357, + "step": 4635 + }, + { + "epoch": 0.49, + "learning_rate": 1.220889318078069e-05, + "loss": 1.3634, + "step": 4636 + }, + { + "epoch": 0.49, + "learning_rate": 1.2205323195070927e-05, + "loss": 1.4143, + "step": 4637 + }, + { + "epoch": 0.49, + "learning_rate": 1.2201752913904519e-05, + "loss": 1.4865, + "step": 4638 + }, + { + "epoch": 0.49, + "learning_rate": 1.2198182337759794e-05, + "loss": 1.451, + "step": 4639 + }, + { + "epoch": 0.49, + "learning_rate": 1.2194611467115116e-05, + "loss": 1.3953, + "step": 4640 + }, + { + "epoch": 0.49, + "learning_rate": 1.2191040302448887e-05, + "loss": 1.4099, + "step": 4641 + }, + { + "epoch": 0.49, + "learning_rate": 1.2187468844239559e-05, + "loss": 1.3338, + "step": 4642 + }, + { + "epoch": 0.49, + "learning_rate": 1.2183897092965609e-05, + "loss": 1.4392, + "step": 4643 + }, + { + "epoch": 0.49, + "learning_rate": 1.2180325049105559e-05, + "loss": 1.3196, + "step": 4644 + }, + { + "epoch": 0.49, + "learning_rate": 1.2176752713137977e-05, + "loss": 1.3727, + "step": 4645 + }, + { + "epoch": 0.49, + "learning_rate": 1.2173180085541464e-05, + "loss": 1.3118, + "step": 4646 + }, + { + "epoch": 0.49, + "learning_rate": 1.2169607166794655e-05, + "loss": 1.3695, + "step": 4647 + }, + { + "epoch": 0.49, + "learning_rate": 1.2166033957376231e-05, + "loss": 1.3568, + "step": 4648 + }, + { + "epoch": 0.49, + "learning_rate": 1.216246045776491e-05, + "loss": 1.3492, + "step": 4649 + }, + { + "epoch": 0.49, + "learning_rate": 1.2158886668439455e-05, + "loss": 1.3445, + "step": 4650 + }, + { + "epoch": 0.49, + "learning_rate": 1.2155312589878654e-05, + "loss": 1.3756, + "step": 4651 + }, + { + "epoch": 0.49, + "learning_rate": 1.2151738222561344e-05, + "loss": 1.3681, + "step": 4652 + }, + { + "epoch": 0.49, + "learning_rate": 1.2148163566966403e-05, + "loss": 1.4345, + "step": 4653 + }, + { + "epoch": 0.49, + "learning_rate": 1.2144588623572738e-05, + "loss": 1.5102, + "step": 4654 + }, + { + "epoch": 0.49, + "learning_rate": 1.2141013392859297e-05, + "loss": 1.3531, + "step": 4655 + }, + { + "epoch": 0.49, + "learning_rate": 1.2137437875305075e-05, + "loss": 1.3824, + "step": 4656 + }, + { + "epoch": 0.49, + "learning_rate": 1.2133862071389099e-05, + "loss": 1.4227, + "step": 4657 + }, + { + "epoch": 0.49, + "learning_rate": 1.2130285981590433e-05, + "loss": 1.3479, + "step": 4658 + }, + { + "epoch": 0.49, + "learning_rate": 1.2126709606388181e-05, + "loss": 1.381, + "step": 4659 + }, + { + "epoch": 0.49, + "learning_rate": 1.2123132946261485e-05, + "loss": 1.3847, + "step": 4660 + }, + { + "epoch": 0.49, + "learning_rate": 1.2119556001689527e-05, + "loss": 1.3549, + "step": 4661 + }, + { + "epoch": 0.49, + "learning_rate": 1.2115978773151527e-05, + "loss": 1.3754, + "step": 4662 + }, + { + "epoch": 0.49, + "learning_rate": 1.2112401261126736e-05, + "loss": 1.3329, + "step": 4663 + }, + { + "epoch": 0.49, + "learning_rate": 1.2108823466094453e-05, + "loss": 1.4228, + "step": 4664 + }, + { + "epoch": 0.49, + "learning_rate": 1.2105245388534013e-05, + "loss": 1.4138, + "step": 4665 + }, + { + "epoch": 0.49, + "learning_rate": 1.2101667028924782e-05, + "loss": 1.3538, + "step": 4666 + }, + { + "epoch": 0.49, + "learning_rate": 1.2098088387746168e-05, + "loss": 1.4848, + "step": 4667 + }, + { + "epoch": 0.49, + "learning_rate": 1.2094509465477619e-05, + "loss": 1.5719, + "step": 4668 + }, + { + "epoch": 0.49, + "learning_rate": 1.209093026259862e-05, + "loss": 1.3863, + "step": 4669 + }, + { + "epoch": 0.49, + "learning_rate": 1.2087350779588691e-05, + "loss": 1.4425, + "step": 4670 + }, + { + "epoch": 0.49, + "learning_rate": 1.2083771016927386e-05, + "loss": 1.3655, + "step": 4671 + }, + { + "epoch": 0.49, + "learning_rate": 1.208019097509431e-05, + "loss": 1.3629, + "step": 4672 + }, + { + "epoch": 0.49, + "learning_rate": 1.2076610654569092e-05, + "loss": 1.3849, + "step": 4673 + }, + { + "epoch": 0.49, + "learning_rate": 1.20730300558314e-05, + "loss": 1.3763, + "step": 4674 + }, + { + "epoch": 0.49, + "learning_rate": 1.2069449179360945e-05, + "loss": 1.5316, + "step": 4675 + }, + { + "epoch": 0.49, + "learning_rate": 1.2065868025637476e-05, + "loss": 1.2873, + "step": 4676 + }, + { + "epoch": 0.49, + "learning_rate": 1.2062286595140773e-05, + "loss": 1.3642, + "step": 4677 + }, + { + "epoch": 0.49, + "learning_rate": 1.2058704888350652e-05, + "loss": 1.3782, + "step": 4678 + }, + { + "epoch": 0.49, + "learning_rate": 1.2055122905746972e-05, + "loss": 1.4597, + "step": 4679 + }, + { + "epoch": 0.49, + "learning_rate": 1.205154064780963e-05, + "loss": 1.3952, + "step": 4680 + }, + { + "epoch": 0.49, + "learning_rate": 1.2047958115018554e-05, + "loss": 1.4012, + "step": 4681 + }, + { + "epoch": 0.49, + "learning_rate": 1.204437530785371e-05, + "loss": 1.3432, + "step": 4682 + }, + { + "epoch": 0.49, + "learning_rate": 1.2040792226795101e-05, + "loss": 1.4111, + "step": 4683 + }, + { + "epoch": 0.49, + "learning_rate": 1.2037208872322773e-05, + "loss": 1.4357, + "step": 4684 + }, + { + "epoch": 0.49, + "learning_rate": 1.2033625244916803e-05, + "loss": 1.3908, + "step": 4685 + }, + { + "epoch": 0.49, + "learning_rate": 1.2030041345057298e-05, + "loss": 1.3804, + "step": 4686 + }, + { + "epoch": 0.49, + "learning_rate": 1.2026457173224412e-05, + "loss": 1.4523, + "step": 4687 + }, + { + "epoch": 0.49, + "learning_rate": 1.2022872729898336e-05, + "loss": 1.4266, + "step": 4688 + }, + { + "epoch": 0.49, + "learning_rate": 1.201928801555929e-05, + "loss": 1.3345, + "step": 4689 + }, + { + "epoch": 0.49, + "learning_rate": 1.2015703030687532e-05, + "loss": 1.1714, + "step": 4690 + }, + { + "epoch": 0.49, + "learning_rate": 1.2012117775763361e-05, + "loss": 1.3899, + "step": 4691 + }, + { + "epoch": 0.49, + "learning_rate": 1.2008532251267109e-05, + "loss": 1.43, + "step": 4692 + }, + { + "epoch": 0.49, + "learning_rate": 1.2004946457679144e-05, + "loss": 1.4302, + "step": 4693 + }, + { + "epoch": 0.49, + "learning_rate": 1.2001360395479865e-05, + "loss": 1.3452, + "step": 4694 + }, + { + "epoch": 0.49, + "learning_rate": 1.1997774065149716e-05, + "loss": 1.3383, + "step": 4695 + }, + { + "epoch": 0.49, + "learning_rate": 1.1994187467169176e-05, + "loss": 1.3677, + "step": 4696 + }, + { + "epoch": 0.49, + "learning_rate": 1.1990600602018755e-05, + "loss": 1.4486, + "step": 4697 + }, + { + "epoch": 0.49, + "learning_rate": 1.1987013470178998e-05, + "loss": 1.4059, + "step": 4698 + }, + { + "epoch": 0.49, + "learning_rate": 1.198342607213049e-05, + "loss": 1.3558, + "step": 4699 + }, + { + "epoch": 0.49, + "learning_rate": 1.1979838408353854e-05, + "loss": 1.3931, + "step": 4700 + }, + { + "epoch": 0.49, + "learning_rate": 1.197625047932974e-05, + "loss": 1.5409, + "step": 4701 + }, + { + "epoch": 0.49, + "learning_rate": 1.197266228553884e-05, + "loss": 1.4878, + "step": 4702 + }, + { + "epoch": 0.49, + "learning_rate": 1.196907382746188e-05, + "loss": 1.3581, + "step": 4703 + }, + { + "epoch": 0.49, + "learning_rate": 1.1965485105579621e-05, + "loss": 1.3617, + "step": 4704 + }, + { + "epoch": 0.49, + "learning_rate": 1.1961896120372857e-05, + "loss": 1.399, + "step": 4705 + }, + { + "epoch": 0.49, + "learning_rate": 1.1958306872322425e-05, + "loss": 1.3861, + "step": 4706 + }, + { + "epoch": 0.49, + "learning_rate": 1.1954717361909186e-05, + "loss": 1.4719, + "step": 4707 + }, + { + "epoch": 0.49, + "learning_rate": 1.195112758961405e-05, + "loss": 1.393, + "step": 4708 + }, + { + "epoch": 0.49, + "learning_rate": 1.1947537555917947e-05, + "loss": 1.4252, + "step": 4709 + }, + { + "epoch": 0.49, + "learning_rate": 1.194394726130185e-05, + "loss": 1.4187, + "step": 4710 + }, + { + "epoch": 0.49, + "learning_rate": 1.1940356706246772e-05, + "loss": 1.4822, + "step": 4711 + }, + { + "epoch": 0.49, + "learning_rate": 1.193676589123375e-05, + "loss": 1.4259, + "step": 4712 + }, + { + "epoch": 0.49, + "learning_rate": 1.1933174816743857e-05, + "loss": 1.4226, + "step": 4713 + }, + { + "epoch": 0.49, + "learning_rate": 1.1929583483258216e-05, + "loss": 1.3701, + "step": 4714 + }, + { + "epoch": 0.49, + "learning_rate": 1.1925991891257967e-05, + "loss": 1.406, + "step": 4715 + }, + { + "epoch": 0.49, + "learning_rate": 1.1922400041224288e-05, + "loss": 1.4593, + "step": 4716 + }, + { + "epoch": 0.49, + "learning_rate": 1.1918807933638401e-05, + "loss": 1.3443, + "step": 4717 + }, + { + "epoch": 0.49, + "learning_rate": 1.1915215568981552e-05, + "loss": 1.3523, + "step": 4718 + }, + { + "epoch": 0.49, + "learning_rate": 1.1911622947735027e-05, + "loss": 1.3175, + "step": 4719 + }, + { + "epoch": 0.49, + "learning_rate": 1.1908030070380143e-05, + "loss": 1.3974, + "step": 4720 + }, + { + "epoch": 0.5, + "learning_rate": 1.1904436937398257e-05, + "loss": 1.386, + "step": 4721 + }, + { + "epoch": 0.5, + "learning_rate": 1.1900843549270753e-05, + "loss": 1.3684, + "step": 4722 + }, + { + "epoch": 0.5, + "learning_rate": 1.1897249906479054e-05, + "loss": 1.383, + "step": 4723 + }, + { + "epoch": 0.5, + "learning_rate": 1.1893656009504617e-05, + "loss": 1.38, + "step": 4724 + }, + { + "epoch": 0.5, + "learning_rate": 1.1890061858828928e-05, + "loss": 1.3844, + "step": 4725 + }, + { + "epoch": 0.5, + "learning_rate": 1.1886467454933515e-05, + "loss": 1.3252, + "step": 4726 + }, + { + "epoch": 0.5, + "learning_rate": 1.1882872798299934e-05, + "loss": 1.3434, + "step": 4727 + }, + { + "epoch": 0.5, + "learning_rate": 1.1879277889409779e-05, + "loss": 1.4115, + "step": 4728 + }, + { + "epoch": 0.5, + "learning_rate": 1.1875682728744669e-05, + "loss": 1.1911, + "step": 4729 + }, + { + "epoch": 0.5, + "learning_rate": 1.1872087316786272e-05, + "loss": 1.2794, + "step": 4730 + }, + { + "epoch": 0.5, + "learning_rate": 1.1868491654016274e-05, + "loss": 1.3961, + "step": 4731 + }, + { + "epoch": 0.5, + "learning_rate": 1.1864895740916404e-05, + "loss": 1.4965, + "step": 4732 + }, + { + "epoch": 0.5, + "learning_rate": 1.1861299577968419e-05, + "loss": 1.3932, + "step": 4733 + }, + { + "epoch": 0.5, + "learning_rate": 1.185770316565412e-05, + "loss": 1.3926, + "step": 4734 + }, + { + "epoch": 0.5, + "learning_rate": 1.1854106504455327e-05, + "loss": 1.3964, + "step": 4735 + }, + { + "epoch": 0.5, + "learning_rate": 1.1850509594853901e-05, + "loss": 1.3666, + "step": 4736 + }, + { + "epoch": 0.5, + "learning_rate": 1.1846912437331736e-05, + "loss": 1.4364, + "step": 4737 + }, + { + "epoch": 0.5, + "learning_rate": 1.1843315032370762e-05, + "loss": 1.3537, + "step": 4738 + }, + { + "epoch": 0.5, + "learning_rate": 1.1839717380452935e-05, + "loss": 1.4083, + "step": 4739 + }, + { + "epoch": 0.5, + "learning_rate": 1.1836119482060247e-05, + "loss": 1.3881, + "step": 4740 + }, + { + "epoch": 0.5, + "learning_rate": 1.1832521337674727e-05, + "loss": 1.4127, + "step": 4741 + }, + { + "epoch": 0.5, + "learning_rate": 1.1828922947778436e-05, + "loss": 1.3433, + "step": 4742 + }, + { + "epoch": 0.5, + "learning_rate": 1.1825324312853461e-05, + "loss": 1.486, + "step": 4743 + }, + { + "epoch": 0.5, + "learning_rate": 1.1821725433381925e-05, + "loss": 1.335, + "step": 4744 + }, + { + "epoch": 0.5, + "learning_rate": 1.1818126309845993e-05, + "loss": 1.3827, + "step": 4745 + }, + { + "epoch": 0.5, + "learning_rate": 1.181452694272785e-05, + "loss": 1.3146, + "step": 4746 + }, + { + "epoch": 0.5, + "learning_rate": 1.1810927332509717e-05, + "loss": 1.3543, + "step": 4747 + }, + { + "epoch": 0.5, + "learning_rate": 1.1807327479673852e-05, + "loss": 1.3544, + "step": 4748 + }, + { + "epoch": 0.5, + "learning_rate": 1.1803727384702543e-05, + "loss": 1.3677, + "step": 4749 + }, + { + "epoch": 0.5, + "learning_rate": 1.1800127048078111e-05, + "loss": 1.3842, + "step": 4750 + }, + { + "epoch": 0.5, + "learning_rate": 1.1796526470282907e-05, + "loss": 1.3495, + "step": 4751 + }, + { + "epoch": 0.5, + "learning_rate": 1.1792925651799314e-05, + "loss": 1.481, + "step": 4752 + }, + { + "epoch": 0.5, + "learning_rate": 1.1789324593109754e-05, + "loss": 1.3482, + "step": 4753 + }, + { + "epoch": 0.5, + "learning_rate": 1.1785723294696673e-05, + "loss": 1.2805, + "step": 4754 + }, + { + "epoch": 0.5, + "learning_rate": 1.1782121757042555e-05, + "loss": 1.3458, + "step": 4755 + }, + { + "epoch": 0.5, + "learning_rate": 1.1778519980629907e-05, + "loss": 1.3937, + "step": 4756 + }, + { + "epoch": 0.5, + "learning_rate": 1.1774917965941284e-05, + "loss": 1.3873, + "step": 4757 + }, + { + "epoch": 0.5, + "learning_rate": 1.1771315713459258e-05, + "loss": 1.3512, + "step": 4758 + }, + { + "epoch": 0.5, + "learning_rate": 1.1767713223666436e-05, + "loss": 1.4465, + "step": 4759 + }, + { + "epoch": 0.5, + "learning_rate": 1.1764110497045463e-05, + "loss": 1.4233, + "step": 4760 + }, + { + "epoch": 0.5, + "learning_rate": 1.1760507534079011e-05, + "loss": 1.4818, + "step": 4761 + }, + { + "epoch": 0.5, + "learning_rate": 1.1756904335249786e-05, + "loss": 1.2933, + "step": 4762 + }, + { + "epoch": 0.5, + "learning_rate": 1.1753300901040518e-05, + "loss": 1.3524, + "step": 4763 + }, + { + "epoch": 0.5, + "learning_rate": 1.1749697231933981e-05, + "loss": 1.4909, + "step": 4764 + }, + { + "epoch": 0.5, + "learning_rate": 1.1746093328412975e-05, + "loss": 1.2912, + "step": 4765 + }, + { + "epoch": 0.5, + "learning_rate": 1.1742489190960325e-05, + "loss": 1.3372, + "step": 4766 + }, + { + "epoch": 0.5, + "learning_rate": 1.1738884820058893e-05, + "loss": 1.3036, + "step": 4767 + }, + { + "epoch": 0.5, + "learning_rate": 1.1735280216191578e-05, + "loss": 1.3189, + "step": 4768 + }, + { + "epoch": 0.5, + "learning_rate": 1.1731675379841298e-05, + "loss": 1.4146, + "step": 4769 + }, + { + "epoch": 0.5, + "learning_rate": 1.1728070311491013e-05, + "loss": 1.3309, + "step": 4770 + }, + { + "epoch": 0.5, + "learning_rate": 1.1724465011623705e-05, + "loss": 1.3427, + "step": 4771 + }, + { + "epoch": 0.5, + "learning_rate": 1.1720859480722395e-05, + "loss": 1.4033, + "step": 4772 + }, + { + "epoch": 0.5, + "learning_rate": 1.1717253719270135e-05, + "loss": 1.3832, + "step": 4773 + }, + { + "epoch": 0.5, + "learning_rate": 1.1713647727749994e-05, + "loss": 1.4074, + "step": 4774 + }, + { + "epoch": 0.5, + "learning_rate": 1.1710041506645092e-05, + "loss": 1.3579, + "step": 4775 + }, + { + "epoch": 0.5, + "learning_rate": 1.1706435056438564e-05, + "loss": 1.3685, + "step": 4776 + }, + { + "epoch": 0.5, + "eval_loss": 1.436767816543579, + "eval_runtime": 77.4332, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4776 + }, + { + "epoch": 0.5, + "learning_rate": 1.1702828377613584e-05, + "loss": 1.5843, + "step": 4777 + }, + { + "epoch": 0.5, + "learning_rate": 1.1699221470653355e-05, + "loss": 1.4168, + "step": 4778 + }, + { + "epoch": 0.5, + "learning_rate": 1.1695614336041108e-05, + "loss": 1.3515, + "step": 4779 + }, + { + "epoch": 0.5, + "learning_rate": 1.169200697426011e-05, + "loss": 1.3214, + "step": 4780 + }, + { + "epoch": 0.5, + "learning_rate": 1.1688399385793652e-05, + "loss": 1.3728, + "step": 4781 + }, + { + "epoch": 0.5, + "learning_rate": 1.1684791571125054e-05, + "loss": 1.3759, + "step": 4782 + }, + { + "epoch": 0.5, + "learning_rate": 1.1681183530737678e-05, + "loss": 1.4955, + "step": 4783 + }, + { + "epoch": 0.5, + "learning_rate": 1.1677575265114904e-05, + "loss": 1.4284, + "step": 4784 + }, + { + "epoch": 0.5, + "learning_rate": 1.1673966774740151e-05, + "loss": 1.3725, + "step": 4785 + }, + { + "epoch": 0.5, + "learning_rate": 1.1670358060096858e-05, + "loss": 1.3612, + "step": 4786 + }, + { + "epoch": 0.5, + "learning_rate": 1.1666749121668506e-05, + "loss": 1.3021, + "step": 4787 + }, + { + "epoch": 0.5, + "learning_rate": 1.1663139959938597e-05, + "loss": 1.4399, + "step": 4788 + }, + { + "epoch": 0.5, + "learning_rate": 1.1659530575390668e-05, + "loss": 1.3511, + "step": 4789 + }, + { + "epoch": 0.5, + "learning_rate": 1.1655920968508276e-05, + "loss": 1.4211, + "step": 4790 + }, + { + "epoch": 0.5, + "learning_rate": 1.1652311139775028e-05, + "loss": 1.343, + "step": 4791 + }, + { + "epoch": 0.5, + "learning_rate": 1.1648701089674541e-05, + "loss": 1.3838, + "step": 4792 + }, + { + "epoch": 0.5, + "learning_rate": 1.164509081869047e-05, + "loss": 1.342, + "step": 4793 + }, + { + "epoch": 0.5, + "learning_rate": 1.1641480327306494e-05, + "loss": 1.3831, + "step": 4794 + }, + { + "epoch": 0.5, + "learning_rate": 1.1637869616006335e-05, + "loss": 1.4102, + "step": 4795 + }, + { + "epoch": 0.5, + "learning_rate": 1.1634258685273732e-05, + "loss": 1.4184, + "step": 4796 + }, + { + "epoch": 0.5, + "learning_rate": 1.1630647535592455e-05, + "loss": 1.3974, + "step": 4797 + }, + { + "epoch": 0.5, + "learning_rate": 1.1627036167446302e-05, + "loss": 1.251, + "step": 4798 + }, + { + "epoch": 0.5, + "learning_rate": 1.1623424581319113e-05, + "loss": 1.3485, + "step": 4799 + }, + { + "epoch": 0.5, + "learning_rate": 1.1619812777694742e-05, + "loss": 1.3544, + "step": 4800 + }, + { + "epoch": 0.5, + "learning_rate": 1.1616200757057076e-05, + "loss": 1.3772, + "step": 4801 + }, + { + "epoch": 0.5, + "learning_rate": 1.1612588519890038e-05, + "loss": 1.3082, + "step": 4802 + }, + { + "epoch": 0.5, + "learning_rate": 1.160897606667757e-05, + "loss": 1.3634, + "step": 4803 + }, + { + "epoch": 0.5, + "learning_rate": 1.1605363397903655e-05, + "loss": 1.3682, + "step": 4804 + }, + { + "epoch": 0.5, + "learning_rate": 1.1601750514052288e-05, + "loss": 1.3258, + "step": 4805 + }, + { + "epoch": 0.5, + "learning_rate": 1.1598137415607511e-05, + "loss": 1.279, + "step": 4806 + }, + { + "epoch": 0.5, + "learning_rate": 1.1594524103053382e-05, + "loss": 1.3759, + "step": 4807 + }, + { + "epoch": 0.5, + "learning_rate": 1.1590910576873995e-05, + "loss": 1.5404, + "step": 4808 + }, + { + "epoch": 0.5, + "learning_rate": 1.1587296837553463e-05, + "loss": 1.4949, + "step": 4809 + }, + { + "epoch": 0.5, + "learning_rate": 1.1583682885575943e-05, + "loss": 1.3501, + "step": 4810 + }, + { + "epoch": 0.5, + "learning_rate": 1.1580068721425608e-05, + "loss": 1.3898, + "step": 4811 + }, + { + "epoch": 0.5, + "learning_rate": 1.157645434558666e-05, + "loss": 1.3265, + "step": 4812 + }, + { + "epoch": 0.5, + "learning_rate": 1.1572839758543338e-05, + "loss": 1.3454, + "step": 4813 + }, + { + "epoch": 0.5, + "learning_rate": 1.1569224960779899e-05, + "loss": 1.4065, + "step": 4814 + }, + { + "epoch": 0.5, + "learning_rate": 1.156560995278064e-05, + "loss": 1.4932, + "step": 4815 + }, + { + "epoch": 0.51, + "learning_rate": 1.156199473502987e-05, + "loss": 1.4224, + "step": 4816 + }, + { + "epoch": 0.51, + "learning_rate": 1.1558379308011937e-05, + "loss": 1.3884, + "step": 4817 + }, + { + "epoch": 0.51, + "learning_rate": 1.1554763672211222e-05, + "loss": 1.3355, + "step": 4818 + }, + { + "epoch": 0.51, + "learning_rate": 1.1551147828112124e-05, + "loss": 1.4281, + "step": 4819 + }, + { + "epoch": 0.51, + "learning_rate": 1.1547531776199072e-05, + "loss": 1.3148, + "step": 4820 + }, + { + "epoch": 0.51, + "learning_rate": 1.1543915516956523e-05, + "loss": 1.3255, + "step": 4821 + }, + { + "epoch": 0.51, + "learning_rate": 1.1540299050868966e-05, + "loss": 1.3361, + "step": 4822 + }, + { + "epoch": 0.51, + "learning_rate": 1.1536682378420912e-05, + "loss": 1.3377, + "step": 4823 + }, + { + "epoch": 0.51, + "learning_rate": 1.1533065500096901e-05, + "loss": 1.4205, + "step": 4824 + }, + { + "epoch": 0.51, + "learning_rate": 1.1529448416381505e-05, + "loss": 1.4193, + "step": 4825 + }, + { + "epoch": 0.51, + "learning_rate": 1.1525831127759322e-05, + "loss": 1.37, + "step": 4826 + }, + { + "epoch": 0.51, + "learning_rate": 1.1522213634714971e-05, + "loss": 1.3642, + "step": 4827 + }, + { + "epoch": 0.51, + "learning_rate": 1.1518595937733103e-05, + "loss": 1.4834, + "step": 4828 + }, + { + "epoch": 0.51, + "learning_rate": 1.1514978037298402e-05, + "loss": 1.2864, + "step": 4829 + }, + { + "epoch": 0.51, + "learning_rate": 1.1511359933895567e-05, + "loss": 1.3468, + "step": 4830 + }, + { + "epoch": 0.51, + "learning_rate": 1.1507741628009337e-05, + "loss": 1.328, + "step": 4831 + }, + { + "epoch": 0.51, + "learning_rate": 1.1504123120124466e-05, + "loss": 1.3489, + "step": 4832 + }, + { + "epoch": 0.51, + "learning_rate": 1.1500504410725746e-05, + "loss": 1.4031, + "step": 4833 + }, + { + "epoch": 0.51, + "learning_rate": 1.149688550029799e-05, + "loss": 1.3482, + "step": 4834 + }, + { + "epoch": 0.51, + "learning_rate": 1.1493266389326037e-05, + "loss": 1.3674, + "step": 4835 + }, + { + "epoch": 0.51, + "learning_rate": 1.1489647078294753e-05, + "loss": 1.2895, + "step": 4836 + }, + { + "epoch": 0.51, + "learning_rate": 1.148602756768904e-05, + "loss": 1.4071, + "step": 4837 + }, + { + "epoch": 0.51, + "learning_rate": 1.1482407857993814e-05, + "loss": 1.5218, + "step": 4838 + }, + { + "epoch": 0.51, + "learning_rate": 1.1478787949694024e-05, + "loss": 1.4577, + "step": 4839 + }, + { + "epoch": 0.51, + "learning_rate": 1.1475167843274643e-05, + "loss": 1.3817, + "step": 4840 + }, + { + "epoch": 0.51, + "learning_rate": 1.1471547539220678e-05, + "loss": 1.3072, + "step": 4841 + }, + { + "epoch": 0.51, + "learning_rate": 1.146792703801715e-05, + "loss": 1.3737, + "step": 4842 + }, + { + "epoch": 0.51, + "learning_rate": 1.1464306340149119e-05, + "loss": 1.4001, + "step": 4843 + }, + { + "epoch": 0.51, + "learning_rate": 1.1460685446101658e-05, + "loss": 1.3963, + "step": 4844 + }, + { + "epoch": 0.51, + "learning_rate": 1.1457064356359882e-05, + "loss": 1.4061, + "step": 4845 + }, + { + "epoch": 0.51, + "learning_rate": 1.145344307140892e-05, + "loss": 1.4211, + "step": 4846 + }, + { + "epoch": 0.51, + "learning_rate": 1.144982159173393e-05, + "loss": 1.3197, + "step": 4847 + }, + { + "epoch": 0.51, + "learning_rate": 1.14461999178201e-05, + "loss": 1.3549, + "step": 4848 + }, + { + "epoch": 0.51, + "learning_rate": 1.1442578050152639e-05, + "loss": 1.3889, + "step": 4849 + }, + { + "epoch": 0.51, + "learning_rate": 1.1438955989216787e-05, + "loss": 1.3847, + "step": 4850 + }, + { + "epoch": 0.51, + "learning_rate": 1.1435333735497803e-05, + "loss": 1.3586, + "step": 4851 + }, + { + "epoch": 0.51, + "learning_rate": 1.1431711289480978e-05, + "loss": 1.503, + "step": 4852 + }, + { + "epoch": 0.51, + "learning_rate": 1.1428088651651627e-05, + "loss": 1.3654, + "step": 4853 + }, + { + "epoch": 0.51, + "learning_rate": 1.1424465822495092e-05, + "loss": 1.3741, + "step": 4854 + }, + { + "epoch": 0.51, + "learning_rate": 1.1420842802496737e-05, + "loss": 1.5437, + "step": 4855 + }, + { + "epoch": 0.51, + "learning_rate": 1.1417219592141953e-05, + "loss": 1.2179, + "step": 4856 + }, + { + "epoch": 0.51, + "learning_rate": 1.1413596191916159e-05, + "loss": 1.3939, + "step": 4857 + }, + { + "epoch": 0.51, + "learning_rate": 1.1409972602304796e-05, + "loss": 1.3383, + "step": 4858 + }, + { + "epoch": 0.51, + "learning_rate": 1.140634882379333e-05, + "loss": 1.3664, + "step": 4859 + }, + { + "epoch": 0.51, + "learning_rate": 1.1402724856867258e-05, + "loss": 1.4002, + "step": 4860 + }, + { + "epoch": 0.51, + "learning_rate": 1.1399100702012098e-05, + "loss": 1.2975, + "step": 4861 + }, + { + "epoch": 0.51, + "learning_rate": 1.1395476359713394e-05, + "loss": 1.3564, + "step": 4862 + }, + { + "epoch": 0.51, + "learning_rate": 1.1391851830456708e-05, + "loss": 1.3574, + "step": 4863 + }, + { + "epoch": 0.51, + "learning_rate": 1.1388227114727644e-05, + "loss": 1.3407, + "step": 4864 + }, + { + "epoch": 0.51, + "learning_rate": 1.1384602213011815e-05, + "loss": 1.3603, + "step": 4865 + }, + { + "epoch": 0.51, + "learning_rate": 1.1380977125794866e-05, + "loss": 1.3465, + "step": 4866 + }, + { + "epoch": 0.51, + "learning_rate": 1.1377351853562461e-05, + "loss": 1.3744, + "step": 4867 + }, + { + "epoch": 0.51, + "learning_rate": 1.1373726396800304e-05, + "loss": 1.3248, + "step": 4868 + }, + { + "epoch": 0.51, + "learning_rate": 1.1370100755994102e-05, + "loss": 1.3352, + "step": 4869 + }, + { + "epoch": 0.51, + "learning_rate": 1.1366474931629603e-05, + "loss": 1.3299, + "step": 4870 + }, + { + "epoch": 0.51, + "learning_rate": 1.1362848924192575e-05, + "loss": 1.344, + "step": 4871 + }, + { + "epoch": 0.51, + "learning_rate": 1.1359222734168809e-05, + "loss": 1.3209, + "step": 4872 + }, + { + "epoch": 0.51, + "learning_rate": 1.135559636204412e-05, + "loss": 1.3927, + "step": 4873 + }, + { + "epoch": 0.51, + "learning_rate": 1.1351969808304349e-05, + "loss": 1.3717, + "step": 4874 + }, + { + "epoch": 0.51, + "learning_rate": 1.1348343073435362e-05, + "loss": 1.3813, + "step": 4875 + }, + { + "epoch": 0.51, + "learning_rate": 1.1344716157923046e-05, + "loss": 1.236, + "step": 4876 + }, + { + "epoch": 0.51, + "learning_rate": 1.1341089062253319e-05, + "loss": 1.2591, + "step": 4877 + }, + { + "epoch": 0.51, + "learning_rate": 1.1337461786912112e-05, + "loss": 1.3211, + "step": 4878 + }, + { + "epoch": 0.51, + "learning_rate": 1.1333834332385394e-05, + "loss": 1.4534, + "step": 4879 + }, + { + "epoch": 0.51, + "learning_rate": 1.1330206699159145e-05, + "loss": 1.346, + "step": 4880 + }, + { + "epoch": 0.51, + "learning_rate": 1.132657888771938e-05, + "loss": 1.3952, + "step": 4881 + }, + { + "epoch": 0.51, + "learning_rate": 1.1322950898552125e-05, + "loss": 1.3008, + "step": 4882 + }, + { + "epoch": 0.51, + "learning_rate": 1.1319322732143445e-05, + "loss": 1.3201, + "step": 4883 + }, + { + "epoch": 0.51, + "learning_rate": 1.1315694388979416e-05, + "loss": 1.3761, + "step": 4884 + }, + { + "epoch": 0.51, + "learning_rate": 1.1312065869546147e-05, + "loss": 1.343, + "step": 4885 + }, + { + "epoch": 0.51, + "learning_rate": 1.1308437174329761e-05, + "loss": 1.3741, + "step": 4886 + }, + { + "epoch": 0.51, + "learning_rate": 1.1304808303816413e-05, + "loss": 1.402, + "step": 4887 + }, + { + "epoch": 0.51, + "learning_rate": 1.130117925849228e-05, + "loss": 1.3834, + "step": 4888 + }, + { + "epoch": 0.51, + "learning_rate": 1.1297550038843559e-05, + "loss": 1.3342, + "step": 4889 + }, + { + "epoch": 0.51, + "learning_rate": 1.1293920645356471e-05, + "loss": 1.3207, + "step": 4890 + }, + { + "epoch": 0.51, + "learning_rate": 1.1290291078517264e-05, + "loss": 1.4274, + "step": 4891 + }, + { + "epoch": 0.51, + "learning_rate": 1.1286661338812203e-05, + "loss": 1.328, + "step": 4892 + }, + { + "epoch": 0.51, + "learning_rate": 1.1283031426727584e-05, + "loss": 1.3823, + "step": 4893 + }, + { + "epoch": 0.51, + "learning_rate": 1.127940134274972e-05, + "loss": 1.3612, + "step": 4894 + }, + { + "epoch": 0.51, + "learning_rate": 1.127577108736495e-05, + "loss": 1.375, + "step": 4895 + }, + { + "epoch": 0.51, + "learning_rate": 1.1272140661059636e-05, + "loss": 1.3531, + "step": 4896 + }, + { + "epoch": 0.51, + "learning_rate": 1.1268510064320155e-05, + "loss": 1.3636, + "step": 4897 + }, + { + "epoch": 0.51, + "learning_rate": 1.1264879297632923e-05, + "loss": 1.3524, + "step": 4898 + }, + { + "epoch": 0.51, + "learning_rate": 1.1261248361484363e-05, + "loss": 1.3865, + "step": 4899 + }, + { + "epoch": 0.51, + "learning_rate": 1.125761725636093e-05, + "loss": 1.4069, + "step": 4900 + }, + { + "epoch": 0.51, + "learning_rate": 1.1253985982749098e-05, + "loss": 1.4643, + "step": 4901 + }, + { + "epoch": 0.51, + "learning_rate": 1.1250354541135364e-05, + "loss": 1.4506, + "step": 4902 + }, + { + "epoch": 0.51, + "learning_rate": 1.124672293200625e-05, + "loss": 1.3857, + "step": 4903 + }, + { + "epoch": 0.51, + "learning_rate": 1.1243091155848295e-05, + "loss": 1.3554, + "step": 4904 + }, + { + "epoch": 0.51, + "learning_rate": 1.1239459213148065e-05, + "loss": 1.4071, + "step": 4905 + }, + { + "epoch": 0.51, + "learning_rate": 1.1235827104392148e-05, + "loss": 1.3981, + "step": 4906 + }, + { + "epoch": 0.51, + "learning_rate": 1.1232194830067153e-05, + "loss": 1.4913, + "step": 4907 + }, + { + "epoch": 0.51, + "learning_rate": 1.1228562390659712e-05, + "loss": 1.3343, + "step": 4908 + }, + { + "epoch": 0.51, + "learning_rate": 1.1224929786656474e-05, + "loss": 1.3832, + "step": 4909 + }, + { + "epoch": 0.51, + "learning_rate": 1.122129701854412e-05, + "loss": 1.367, + "step": 4910 + }, + { + "epoch": 0.51, + "learning_rate": 1.1217664086809345e-05, + "loss": 1.4108, + "step": 4911 + }, + { + "epoch": 0.52, + "learning_rate": 1.1214030991938872e-05, + "loss": 1.3981, + "step": 4912 + }, + { + "epoch": 0.52, + "learning_rate": 1.1210397734419436e-05, + "loss": 1.5266, + "step": 4913 + }, + { + "epoch": 0.52, + "learning_rate": 1.1206764314737806e-05, + "loss": 1.337, + "step": 4914 + }, + { + "epoch": 0.52, + "learning_rate": 1.1203130733380765e-05, + "loss": 1.3784, + "step": 4915 + }, + { + "epoch": 0.52, + "learning_rate": 1.1199496990835117e-05, + "loss": 1.3048, + "step": 4916 + }, + { + "epoch": 0.52, + "learning_rate": 1.1195863087587692e-05, + "loss": 1.2977, + "step": 4917 + }, + { + "epoch": 0.52, + "learning_rate": 1.1192229024125344e-05, + "loss": 1.3304, + "step": 4918 + }, + { + "epoch": 0.52, + "learning_rate": 1.1188594800934938e-05, + "loss": 1.4102, + "step": 4919 + }, + { + "epoch": 0.52, + "learning_rate": 1.1184960418503366e-05, + "loss": 1.3932, + "step": 4920 + }, + { + "epoch": 0.52, + "learning_rate": 1.1181325877317547e-05, + "loss": 1.4985, + "step": 4921 + }, + { + "epoch": 0.52, + "learning_rate": 1.1177691177864415e-05, + "loss": 1.4596, + "step": 4922 + }, + { + "epoch": 0.52, + "learning_rate": 1.1174056320630924e-05, + "loss": 1.3559, + "step": 4923 + }, + { + "epoch": 0.52, + "learning_rate": 1.117042130610405e-05, + "loss": 1.4128, + "step": 4924 + }, + { + "epoch": 0.52, + "learning_rate": 1.1166786134770795e-05, + "loss": 1.3343, + "step": 4925 + }, + { + "epoch": 0.52, + "learning_rate": 1.116315080711818e-05, + "loss": 1.332, + "step": 4926 + }, + { + "epoch": 0.52, + "learning_rate": 1.115951532363324e-05, + "loss": 1.3616, + "step": 4927 + }, + { + "epoch": 0.52, + "learning_rate": 1.1155879684803041e-05, + "loss": 1.4074, + "step": 4928 + }, + { + "epoch": 0.52, + "learning_rate": 1.1152243891114665e-05, + "loss": 1.303, + "step": 4929 + }, + { + "epoch": 0.52, + "learning_rate": 1.1148607943055212e-05, + "loss": 1.4799, + "step": 4930 + }, + { + "epoch": 0.52, + "learning_rate": 1.1144971841111807e-05, + "loss": 1.3881, + "step": 4931 + }, + { + "epoch": 0.52, + "learning_rate": 1.1141335585771593e-05, + "loss": 1.338, + "step": 4932 + }, + { + "epoch": 0.52, + "learning_rate": 1.1137699177521738e-05, + "loss": 1.3289, + "step": 4933 + }, + { + "epoch": 0.52, + "learning_rate": 1.1134062616849426e-05, + "loss": 1.377, + "step": 4934 + }, + { + "epoch": 0.52, + "learning_rate": 1.1130425904241862e-05, + "loss": 1.3596, + "step": 4935 + }, + { + "epoch": 0.52, + "learning_rate": 1.112678904018627e-05, + "loss": 1.4264, + "step": 4936 + }, + { + "epoch": 0.52, + "learning_rate": 1.1123152025169898e-05, + "loss": 1.3526, + "step": 4937 + }, + { + "epoch": 0.52, + "learning_rate": 1.1119514859680016e-05, + "loss": 1.3271, + "step": 4938 + }, + { + "epoch": 0.52, + "learning_rate": 1.1115877544203905e-05, + "loss": 1.3907, + "step": 4939 + }, + { + "epoch": 0.52, + "learning_rate": 1.1112240079228878e-05, + "loss": 1.3415, + "step": 4940 + }, + { + "epoch": 0.52, + "learning_rate": 1.1108602465242258e-05, + "loss": 1.3875, + "step": 4941 + }, + { + "epoch": 0.52, + "learning_rate": 1.110496470273139e-05, + "loss": 1.3964, + "step": 4942 + }, + { + "epoch": 0.52, + "learning_rate": 1.1101326792183645e-05, + "loss": 1.3448, + "step": 4943 + }, + { + "epoch": 0.52, + "learning_rate": 1.1097688734086407e-05, + "loss": 1.3522, + "step": 4944 + }, + { + "epoch": 0.52, + "learning_rate": 1.1094050528927082e-05, + "loss": 1.2742, + "step": 4945 + }, + { + "epoch": 0.52, + "learning_rate": 1.1090412177193097e-05, + "loss": 1.417, + "step": 4946 + }, + { + "epoch": 0.52, + "learning_rate": 1.1086773679371898e-05, + "loss": 1.3993, + "step": 4947 + }, + { + "epoch": 0.52, + "learning_rate": 1.108313503595095e-05, + "loss": 1.3783, + "step": 4948 + }, + { + "epoch": 0.52, + "learning_rate": 1.1079496247417736e-05, + "loss": 1.3975, + "step": 4949 + }, + { + "epoch": 0.52, + "learning_rate": 1.1075857314259763e-05, + "loss": 1.4256, + "step": 4950 + }, + { + "epoch": 0.52, + "learning_rate": 1.1072218236964551e-05, + "loss": 1.3547, + "step": 4951 + }, + { + "epoch": 0.52, + "learning_rate": 1.106857901601965e-05, + "loss": 1.4243, + "step": 4952 + }, + { + "epoch": 0.52, + "learning_rate": 1.1064939651912612e-05, + "loss": 1.4259, + "step": 4953 + }, + { + "epoch": 0.52, + "learning_rate": 1.1061300145131027e-05, + "loss": 1.4323, + "step": 4954 + }, + { + "epoch": 0.52, + "learning_rate": 1.1057660496162488e-05, + "loss": 1.3608, + "step": 4955 + }, + { + "epoch": 0.52, + "learning_rate": 1.1054020705494622e-05, + "loss": 1.3703, + "step": 4956 + }, + { + "epoch": 0.52, + "learning_rate": 1.105038077361506e-05, + "loss": 1.3953, + "step": 4957 + }, + { + "epoch": 0.52, + "learning_rate": 1.1046740701011467e-05, + "loss": 1.392, + "step": 4958 + }, + { + "epoch": 0.52, + "learning_rate": 1.1043100488171513e-05, + "loss": 1.4101, + "step": 4959 + }, + { + "epoch": 0.52, + "learning_rate": 1.1039460135582894e-05, + "loss": 1.5432, + "step": 4960 + }, + { + "epoch": 0.52, + "learning_rate": 1.1035819643733326e-05, + "loss": 1.3822, + "step": 4961 + }, + { + "epoch": 0.52, + "learning_rate": 1.103217901311054e-05, + "loss": 1.3816, + "step": 4962 + }, + { + "epoch": 0.52, + "learning_rate": 1.1028538244202287e-05, + "loss": 1.3137, + "step": 4963 + }, + { + "epoch": 0.52, + "learning_rate": 1.102489733749634e-05, + "loss": 1.3791, + "step": 4964 + }, + { + "epoch": 0.52, + "learning_rate": 1.102125629348048e-05, + "loss": 1.3751, + "step": 4965 + }, + { + "epoch": 0.52, + "learning_rate": 1.1017615112642518e-05, + "loss": 1.3287, + "step": 4966 + }, + { + "epoch": 0.52, + "learning_rate": 1.1013973795470277e-05, + "loss": 1.3187, + "step": 4967 + }, + { + "epoch": 0.52, + "learning_rate": 1.1010332342451602e-05, + "loss": 1.3174, + "step": 4968 + }, + { + "epoch": 0.52, + "learning_rate": 1.1006690754074351e-05, + "loss": 1.3544, + "step": 4969 + }, + { + "epoch": 0.52, + "learning_rate": 1.1003049030826404e-05, + "loss": 1.3789, + "step": 4970 + }, + { + "epoch": 0.52, + "learning_rate": 1.0999407173195662e-05, + "loss": 1.4561, + "step": 4971 + }, + { + "epoch": 0.52, + "learning_rate": 1.0995765181670039e-05, + "loss": 1.3963, + "step": 4972 + }, + { + "epoch": 0.52, + "learning_rate": 1.0992123056737464e-05, + "loss": 1.3519, + "step": 4973 + }, + { + "epoch": 0.52, + "learning_rate": 1.0988480798885892e-05, + "loss": 1.3945, + "step": 4974 + }, + { + "epoch": 0.52, + "learning_rate": 1.0984838408603294e-05, + "loss": 1.4572, + "step": 4975 + }, + { + "epoch": 0.52, + "eval_loss": 1.4313459396362305, + "eval_runtime": 77.4808, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 4975 + }, + { + "epoch": 0.52, + "learning_rate": 1.0981195886377652e-05, + "loss": 1.3493, + "step": 4976 + }, + { + "epoch": 0.52, + "learning_rate": 1.0977553232696972e-05, + "loss": 1.3734, + "step": 4977 + }, + { + "epoch": 0.52, + "learning_rate": 1.0973910448049273e-05, + "loss": 1.3484, + "step": 4978 + }, + { + "epoch": 0.52, + "learning_rate": 1.09702675329226e-05, + "loss": 1.4288, + "step": 4979 + }, + { + "epoch": 0.52, + "learning_rate": 1.096662448780501e-05, + "loss": 1.3748, + "step": 4980 + }, + { + "epoch": 0.52, + "learning_rate": 1.0962981313184575e-05, + "loss": 1.3485, + "step": 4981 + }, + { + "epoch": 0.52, + "learning_rate": 1.0959338009549383e-05, + "loss": 1.3606, + "step": 4982 + }, + { + "epoch": 0.52, + "learning_rate": 1.095569457738755e-05, + "loss": 1.3963, + "step": 4983 + }, + { + "epoch": 0.52, + "learning_rate": 1.09520510171872e-05, + "loss": 1.2986, + "step": 4984 + }, + { + "epoch": 0.52, + "learning_rate": 1.0948407329436474e-05, + "loss": 1.3505, + "step": 4985 + }, + { + "epoch": 0.52, + "learning_rate": 1.0944763514623535e-05, + "loss": 1.4649, + "step": 4986 + }, + { + "epoch": 0.52, + "learning_rate": 1.0941119573236564e-05, + "loss": 1.4743, + "step": 4987 + }, + { + "epoch": 0.52, + "learning_rate": 1.0937475505763745e-05, + "loss": 1.3934, + "step": 4988 + }, + { + "epoch": 0.52, + "learning_rate": 1.09338313126933e-05, + "loss": 1.4225, + "step": 4989 + }, + { + "epoch": 0.52, + "learning_rate": 1.0930186994513453e-05, + "loss": 1.3626, + "step": 4990 + }, + { + "epoch": 0.52, + "learning_rate": 1.0926542551712446e-05, + "loss": 1.3614, + "step": 4991 + }, + { + "epoch": 0.52, + "learning_rate": 1.0922897984778546e-05, + "loss": 1.3766, + "step": 4992 + }, + { + "epoch": 0.52, + "learning_rate": 1.0919253294200027e-05, + "loss": 1.3295, + "step": 4993 + }, + { + "epoch": 0.52, + "learning_rate": 1.091560848046519e-05, + "loss": 1.3802, + "step": 4994 + }, + { + "epoch": 0.52, + "learning_rate": 1.091196354406234e-05, + "loss": 1.2976, + "step": 4995 + }, + { + "epoch": 0.52, + "learning_rate": 1.090831848547981e-05, + "loss": 1.3928, + "step": 4996 + }, + { + "epoch": 0.52, + "learning_rate": 1.0904673305205937e-05, + "loss": 1.3717, + "step": 4997 + }, + { + "epoch": 0.52, + "learning_rate": 1.0901028003729089e-05, + "loss": 1.3164, + "step": 4998 + }, + { + "epoch": 0.52, + "learning_rate": 1.0897382581537638e-05, + "loss": 1.3462, + "step": 4999 + }, + { + "epoch": 0.52, + "learning_rate": 1.0893737039119981e-05, + "loss": 1.3643, + "step": 5000 + }, + { + "epoch": 0.52, + "learning_rate": 1.089009137696452e-05, + "loss": 1.3452, + "step": 5001 + }, + { + "epoch": 0.52, + "learning_rate": 1.0886445595559686e-05, + "loss": 1.358, + "step": 5002 + }, + { + "epoch": 0.52, + "learning_rate": 1.0882799695393922e-05, + "loss": 1.4569, + "step": 5003 + }, + { + "epoch": 0.52, + "learning_rate": 1.0879153676955681e-05, + "loss": 1.2832, + "step": 5004 + }, + { + "epoch": 0.52, + "learning_rate": 1.0875507540733435e-05, + "loss": 1.4089, + "step": 5005 + }, + { + "epoch": 0.52, + "learning_rate": 1.087186128721567e-05, + "loss": 1.3178, + "step": 5006 + }, + { + "epoch": 0.53, + "learning_rate": 1.0868214916890902e-05, + "loss": 1.4883, + "step": 5007 + }, + { + "epoch": 0.53, + "learning_rate": 1.0864568430247638e-05, + "loss": 1.3991, + "step": 5008 + }, + { + "epoch": 0.53, + "learning_rate": 1.0860921827774422e-05, + "loss": 1.4507, + "step": 5009 + }, + { + "epoch": 0.53, + "learning_rate": 1.08572751099598e-05, + "loss": 1.3578, + "step": 5010 + }, + { + "epoch": 0.53, + "learning_rate": 1.0853628277292341e-05, + "loss": 1.4231, + "step": 5011 + }, + { + "epoch": 0.53, + "learning_rate": 1.0849981330260624e-05, + "loss": 1.4835, + "step": 5012 + }, + { + "epoch": 0.53, + "learning_rate": 1.084633426935325e-05, + "loss": 1.4511, + "step": 5013 + }, + { + "epoch": 0.53, + "learning_rate": 1.084268709505883e-05, + "loss": 1.3889, + "step": 5014 + }, + { + "epoch": 0.53, + "learning_rate": 1.0839039807865992e-05, + "loss": 1.355, + "step": 5015 + }, + { + "epoch": 0.53, + "learning_rate": 1.0835392408263375e-05, + "loss": 1.4829, + "step": 5016 + }, + { + "epoch": 0.53, + "learning_rate": 1.0831744896739643e-05, + "loss": 1.3019, + "step": 5017 + }, + { + "epoch": 0.53, + "learning_rate": 1.0828097273783465e-05, + "loss": 1.3418, + "step": 5018 + }, + { + "epoch": 0.53, + "learning_rate": 1.082444953988353e-05, + "loss": 1.4276, + "step": 5019 + }, + { + "epoch": 0.53, + "learning_rate": 1.0820801695528537e-05, + "loss": 1.2816, + "step": 5020 + }, + { + "epoch": 0.53, + "learning_rate": 1.081715374120721e-05, + "loss": 1.5144, + "step": 5021 + }, + { + "epoch": 0.53, + "learning_rate": 1.0813505677408278e-05, + "loss": 1.4063, + "step": 5022 + }, + { + "epoch": 0.53, + "learning_rate": 1.0809857504620487e-05, + "loss": 1.4011, + "step": 5023 + }, + { + "epoch": 0.53, + "learning_rate": 1.0806209223332598e-05, + "loss": 1.373, + "step": 5024 + }, + { + "epoch": 0.53, + "learning_rate": 1.0802560834033388e-05, + "loss": 1.6259, + "step": 5025 + }, + { + "epoch": 0.53, + "learning_rate": 1.0798912337211648e-05, + "loss": 1.4487, + "step": 5026 + }, + { + "epoch": 0.53, + "learning_rate": 1.0795263733356184e-05, + "loss": 1.3056, + "step": 5027 + }, + { + "epoch": 0.53, + "learning_rate": 1.079161502295581e-05, + "loss": 1.2871, + "step": 5028 + }, + { + "epoch": 0.53, + "learning_rate": 1.0787966206499363e-05, + "loss": 1.413, + "step": 5029 + }, + { + "epoch": 0.53, + "learning_rate": 1.0784317284475694e-05, + "loss": 1.3682, + "step": 5030 + }, + { + "epoch": 0.53, + "learning_rate": 1.0780668257373659e-05, + "loss": 1.493, + "step": 5031 + }, + { + "epoch": 0.53, + "learning_rate": 1.0777019125682136e-05, + "loss": 1.6823, + "step": 5032 + }, + { + "epoch": 0.53, + "learning_rate": 1.0773369889890015e-05, + "loss": 1.358, + "step": 5033 + }, + { + "epoch": 0.53, + "learning_rate": 1.07697205504862e-05, + "loss": 1.3532, + "step": 5034 + }, + { + "epoch": 0.53, + "learning_rate": 1.0766071107959608e-05, + "loss": 1.3432, + "step": 5035 + }, + { + "epoch": 0.53, + "learning_rate": 1.0762421562799173e-05, + "loss": 1.3575, + "step": 5036 + }, + { + "epoch": 0.53, + "learning_rate": 1.0758771915493838e-05, + "loss": 1.0924, + "step": 5037 + }, + { + "epoch": 0.53, + "learning_rate": 1.075512216653256e-05, + "loss": 0.7405, + "step": 5038 + }, + { + "epoch": 0.53, + "learning_rate": 1.0751472316404315e-05, + "loss": 0.7134, + "step": 5039 + }, + { + "epoch": 0.53, + "learning_rate": 1.0747822365598088e-05, + "loss": 1.0904, + "step": 5040 + }, + { + "epoch": 0.53, + "learning_rate": 1.0744172314602881e-05, + "loss": 1.4353, + "step": 5041 + }, + { + "epoch": 0.53, + "learning_rate": 1.0740522163907702e-05, + "loss": 1.361, + "step": 5042 + }, + { + "epoch": 0.53, + "learning_rate": 1.073687191400158e-05, + "loss": 1.4024, + "step": 5043 + }, + { + "epoch": 0.53, + "learning_rate": 1.0733221565373557e-05, + "loss": 1.328, + "step": 5044 + }, + { + "epoch": 0.53, + "learning_rate": 1.0729571118512683e-05, + "loss": 1.3309, + "step": 5045 + }, + { + "epoch": 0.53, + "learning_rate": 1.0725920573908024e-05, + "loss": 1.3819, + "step": 5046 + }, + { + "epoch": 0.53, + "learning_rate": 1.0722269932048659e-05, + "loss": 1.3467, + "step": 5047 + }, + { + "epoch": 0.53, + "learning_rate": 1.0718619193423683e-05, + "loss": 1.3036, + "step": 5048 + }, + { + "epoch": 0.53, + "learning_rate": 1.07149683585222e-05, + "loss": 1.3297, + "step": 5049 + }, + { + "epoch": 0.53, + "learning_rate": 1.0711317427833328e-05, + "loss": 1.3439, + "step": 5050 + }, + { + "epoch": 0.53, + "learning_rate": 1.0707666401846192e-05, + "loss": 1.4167, + "step": 5051 + }, + { + "epoch": 0.53, + "learning_rate": 1.0704015281049944e-05, + "loss": 1.4217, + "step": 5052 + }, + { + "epoch": 0.53, + "learning_rate": 1.070036406593374e-05, + "loss": 1.3394, + "step": 5053 + }, + { + "epoch": 0.53, + "learning_rate": 1.0696712756986745e-05, + "loss": 1.3242, + "step": 5054 + }, + { + "epoch": 0.53, + "learning_rate": 1.0693061354698143e-05, + "loss": 1.3957, + "step": 5055 + }, + { + "epoch": 0.53, + "learning_rate": 1.0689409859557123e-05, + "loss": 1.37, + "step": 5056 + }, + { + "epoch": 0.53, + "learning_rate": 1.0685758272052902e-05, + "loss": 1.4524, + "step": 5057 + }, + { + "epoch": 0.53, + "learning_rate": 1.0682106592674688e-05, + "loss": 1.528, + "step": 5058 + }, + { + "epoch": 0.53, + "learning_rate": 1.0678454821911719e-05, + "loss": 1.3613, + "step": 5059 + }, + { + "epoch": 0.53, + "learning_rate": 1.0674802960253234e-05, + "loss": 1.308, + "step": 5060 + }, + { + "epoch": 0.53, + "learning_rate": 1.0671151008188494e-05, + "loss": 1.3343, + "step": 5061 + }, + { + "epoch": 0.53, + "learning_rate": 1.066749896620676e-05, + "loss": 1.365, + "step": 5062 + }, + { + "epoch": 0.53, + "learning_rate": 1.0663846834797316e-05, + "loss": 1.4077, + "step": 5063 + }, + { + "epoch": 0.53, + "learning_rate": 1.0660194614449455e-05, + "loss": 1.324, + "step": 5064 + }, + { + "epoch": 0.53, + "learning_rate": 1.0656542305652478e-05, + "loss": 1.3623, + "step": 5065 + }, + { + "epoch": 0.53, + "learning_rate": 1.0652889908895701e-05, + "loss": 1.4079, + "step": 5066 + }, + { + "epoch": 0.53, + "learning_rate": 1.0649237424668451e-05, + "loss": 1.3089, + "step": 5067 + }, + { + "epoch": 0.53, + "learning_rate": 1.0645584853460069e-05, + "loss": 1.3967, + "step": 5068 + }, + { + "epoch": 0.53, + "learning_rate": 1.0641932195759905e-05, + "loss": 1.3639, + "step": 5069 + }, + { + "epoch": 0.53, + "learning_rate": 1.0638279452057319e-05, + "loss": 1.5919, + "step": 5070 + }, + { + "epoch": 0.53, + "learning_rate": 1.0634626622841686e-05, + "loss": 1.3348, + "step": 5071 + }, + { + "epoch": 0.53, + "learning_rate": 1.0630973708602395e-05, + "loss": 1.3146, + "step": 5072 + }, + { + "epoch": 0.53, + "learning_rate": 1.0627320709828836e-05, + "loss": 1.3375, + "step": 5073 + }, + { + "epoch": 0.53, + "learning_rate": 1.062366762701042e-05, + "loss": 1.3908, + "step": 5074 + }, + { + "epoch": 0.53, + "learning_rate": 1.0620014460636568e-05, + "loss": 1.3726, + "step": 5075 + }, + { + "epoch": 0.53, + "learning_rate": 1.061636121119671e-05, + "loss": 1.2348, + "step": 5076 + }, + { + "epoch": 0.53, + "learning_rate": 1.0612707879180284e-05, + "loss": 1.2957, + "step": 5077 + }, + { + "epoch": 0.53, + "learning_rate": 1.0609054465076749e-05, + "loss": 1.4202, + "step": 5078 + }, + { + "epoch": 0.53, + "learning_rate": 1.060540096937556e-05, + "loss": 1.5809, + "step": 5079 + }, + { + "epoch": 0.53, + "learning_rate": 1.0601747392566202e-05, + "loss": 1.3741, + "step": 5080 + }, + { + "epoch": 0.53, + "learning_rate": 1.059809373513815e-05, + "loss": 1.3537, + "step": 5081 + }, + { + "epoch": 0.53, + "learning_rate": 1.0594439997580907e-05, + "loss": 1.332, + "step": 5082 + }, + { + "epoch": 0.53, + "learning_rate": 1.0590786180383981e-05, + "loss": 1.3267, + "step": 5083 + }, + { + "epoch": 0.53, + "learning_rate": 1.0587132284036883e-05, + "loss": 1.3552, + "step": 5084 + }, + { + "epoch": 0.53, + "learning_rate": 1.0583478309029143e-05, + "loss": 1.2837, + "step": 5085 + }, + { + "epoch": 0.53, + "learning_rate": 1.0579824255850304e-05, + "loss": 1.4311, + "step": 5086 + }, + { + "epoch": 0.53, + "learning_rate": 1.0576170124989915e-05, + "loss": 1.4394, + "step": 5087 + }, + { + "epoch": 0.53, + "learning_rate": 1.0572515916937531e-05, + "loss": 1.3185, + "step": 5088 + }, + { + "epoch": 0.53, + "learning_rate": 1.0568861632182723e-05, + "loss": 1.4212, + "step": 5089 + }, + { + "epoch": 0.53, + "learning_rate": 1.0565207271215075e-05, + "loss": 1.0951, + "step": 5090 + }, + { + "epoch": 0.53, + "learning_rate": 1.0561552834524176e-05, + "loss": 1.4174, + "step": 5091 + }, + { + "epoch": 0.53, + "learning_rate": 1.0557898322599624e-05, + "loss": 1.3349, + "step": 5092 + }, + { + "epoch": 0.53, + "learning_rate": 1.0554243735931031e-05, + "loss": 1.399, + "step": 5093 + }, + { + "epoch": 0.53, + "learning_rate": 1.055058907500802e-05, + "loss": 1.4016, + "step": 5094 + }, + { + "epoch": 0.53, + "learning_rate": 1.0546934340320219e-05, + "loss": 1.3227, + "step": 5095 + }, + { + "epoch": 0.53, + "learning_rate": 1.0543279532357269e-05, + "loss": 1.4017, + "step": 5096 + }, + { + "epoch": 0.53, + "learning_rate": 1.053962465160882e-05, + "loss": 1.3937, + "step": 5097 + }, + { + "epoch": 0.53, + "learning_rate": 1.0535969698564532e-05, + "loss": 1.2405, + "step": 5098 + }, + { + "epoch": 0.53, + "learning_rate": 1.0532314673714081e-05, + "loss": 1.2939, + "step": 5099 + }, + { + "epoch": 0.53, + "learning_rate": 1.0528659577547136e-05, + "loss": 1.4165, + "step": 5100 + }, + { + "epoch": 0.53, + "learning_rate": 1.0525004410553394e-05, + "loss": 1.309, + "step": 5101 + }, + { + "epoch": 0.54, + "learning_rate": 1.0521349173222549e-05, + "loss": 1.4078, + "step": 5102 + }, + { + "epoch": 0.54, + "learning_rate": 1.0517693866044312e-05, + "loss": 1.4026, + "step": 5103 + }, + { + "epoch": 0.54, + "learning_rate": 1.0514038489508396e-05, + "loss": 1.3098, + "step": 5104 + }, + { + "epoch": 0.54, + "learning_rate": 1.0510383044104533e-05, + "loss": 1.2886, + "step": 5105 + }, + { + "epoch": 0.54, + "learning_rate": 1.0506727530322454e-05, + "loss": 1.3114, + "step": 5106 + }, + { + "epoch": 0.54, + "learning_rate": 1.0503071948651908e-05, + "loss": 1.2823, + "step": 5107 + }, + { + "epoch": 0.54, + "learning_rate": 1.0499416299582643e-05, + "loss": 1.4654, + "step": 5108 + }, + { + "epoch": 0.54, + "learning_rate": 1.0495760583604431e-05, + "loss": 1.4043, + "step": 5109 + }, + { + "epoch": 0.54, + "learning_rate": 1.0492104801207035e-05, + "loss": 1.3113, + "step": 5110 + }, + { + "epoch": 0.54, + "learning_rate": 1.0488448952880243e-05, + "loss": 1.3285, + "step": 5111 + }, + { + "epoch": 0.54, + "learning_rate": 1.048479303911384e-05, + "loss": 1.3918, + "step": 5112 + }, + { + "epoch": 0.54, + "learning_rate": 1.0481137060397623e-05, + "loss": 1.346, + "step": 5113 + }, + { + "epoch": 0.54, + "learning_rate": 1.0477481017221407e-05, + "loss": 1.3777, + "step": 5114 + }, + { + "epoch": 0.54, + "learning_rate": 1.0473824910075003e-05, + "loss": 1.3494, + "step": 5115 + }, + { + "epoch": 0.54, + "learning_rate": 1.0470168739448232e-05, + "loss": 1.4173, + "step": 5116 + }, + { + "epoch": 0.54, + "learning_rate": 1.0466512505830932e-05, + "loss": 1.4313, + "step": 5117 + }, + { + "epoch": 0.54, + "learning_rate": 1.0462856209712944e-05, + "loss": 1.335, + "step": 5118 + }, + { + "epoch": 0.54, + "learning_rate": 1.0459199851584117e-05, + "loss": 1.37, + "step": 5119 + }, + { + "epoch": 0.54, + "learning_rate": 1.0455543431934307e-05, + "loss": 1.3504, + "step": 5120 + }, + { + "epoch": 0.54, + "learning_rate": 1.0451886951253381e-05, + "loss": 1.4148, + "step": 5121 + }, + { + "epoch": 0.54, + "learning_rate": 1.0448230410031218e-05, + "loss": 1.3974, + "step": 5122 + }, + { + "epoch": 0.54, + "learning_rate": 1.0444573808757694e-05, + "loss": 1.3644, + "step": 5123 + }, + { + "epoch": 0.54, + "learning_rate": 1.0440917147922705e-05, + "loss": 1.4024, + "step": 5124 + }, + { + "epoch": 0.54, + "learning_rate": 1.0437260428016143e-05, + "loss": 1.3925, + "step": 5125 + }, + { + "epoch": 0.54, + "learning_rate": 1.0433603649527923e-05, + "loss": 1.2907, + "step": 5126 + }, + { + "epoch": 0.54, + "learning_rate": 1.0429946812947953e-05, + "loss": 1.3453, + "step": 5127 + }, + { + "epoch": 0.54, + "learning_rate": 1.0426289918766157e-05, + "loss": 1.3856, + "step": 5128 + }, + { + "epoch": 0.54, + "learning_rate": 1.0422632967472465e-05, + "loss": 1.3309, + "step": 5129 + }, + { + "epoch": 0.54, + "learning_rate": 1.0418975959556819e-05, + "loss": 1.3757, + "step": 5130 + }, + { + "epoch": 0.54, + "learning_rate": 1.0415318895509152e-05, + "loss": 1.406, + "step": 5131 + }, + { + "epoch": 0.54, + "learning_rate": 1.041166177581943e-05, + "loss": 1.3265, + "step": 5132 + }, + { + "epoch": 0.54, + "learning_rate": 1.0408004600977606e-05, + "loss": 1.3377, + "step": 5133 + }, + { + "epoch": 0.54, + "learning_rate": 1.040434737147365e-05, + "loss": 1.3647, + "step": 5134 + }, + { + "epoch": 0.54, + "learning_rate": 1.0400690087797531e-05, + "loss": 1.3262, + "step": 5135 + }, + { + "epoch": 0.54, + "learning_rate": 1.039703275043924e-05, + "loss": 1.3924, + "step": 5136 + }, + { + "epoch": 0.54, + "learning_rate": 1.039337535988876e-05, + "loss": 1.3018, + "step": 5137 + }, + { + "epoch": 0.54, + "learning_rate": 1.038971791663609e-05, + "loss": 1.385, + "step": 5138 + }, + { + "epoch": 0.54, + "learning_rate": 1.0386060421171232e-05, + "loss": 1.3435, + "step": 5139 + }, + { + "epoch": 0.54, + "learning_rate": 1.0382402873984197e-05, + "loss": 1.4023, + "step": 5140 + }, + { + "epoch": 0.54, + "learning_rate": 1.0378745275565003e-05, + "loss": 1.369, + "step": 5141 + }, + { + "epoch": 0.54, + "learning_rate": 1.0375087626403675e-05, + "loss": 1.3199, + "step": 5142 + }, + { + "epoch": 0.54, + "learning_rate": 1.037142992699024e-05, + "loss": 1.4247, + "step": 5143 + }, + { + "epoch": 0.54, + "learning_rate": 1.0367772177814736e-05, + "loss": 1.4015, + "step": 5144 + }, + { + "epoch": 0.54, + "learning_rate": 1.0364114379367217e-05, + "loss": 1.3519, + "step": 5145 + }, + { + "epoch": 0.54, + "learning_rate": 1.0360456532137722e-05, + "loss": 1.3478, + "step": 5146 + }, + { + "epoch": 0.54, + "learning_rate": 1.0356798636616314e-05, + "loss": 1.4876, + "step": 5147 + }, + { + "epoch": 0.54, + "learning_rate": 1.0353140693293056e-05, + "loss": 1.6481, + "step": 5148 + }, + { + "epoch": 0.54, + "learning_rate": 1.034948270265802e-05, + "loss": 1.3851, + "step": 5149 + }, + { + "epoch": 0.54, + "learning_rate": 1.0345824665201281e-05, + "loss": 1.4037, + "step": 5150 + }, + { + "epoch": 0.54, + "learning_rate": 1.0342166581412923e-05, + "loss": 1.3138, + "step": 5151 + }, + { + "epoch": 0.54, + "learning_rate": 1.0338508451783032e-05, + "loss": 1.3536, + "step": 5152 + }, + { + "epoch": 0.54, + "learning_rate": 1.0334850276801712e-05, + "loss": 1.3244, + "step": 5153 + }, + { + "epoch": 0.54, + "learning_rate": 1.0331192056959052e-05, + "loss": 1.3677, + "step": 5154 + }, + { + "epoch": 0.54, + "learning_rate": 1.032753379274517e-05, + "loss": 1.3439, + "step": 5155 + }, + { + "epoch": 0.54, + "learning_rate": 1.0323875484650171e-05, + "loss": 1.365, + "step": 5156 + }, + { + "epoch": 0.54, + "learning_rate": 1.0320217133164186e-05, + "loss": 1.3838, + "step": 5157 + }, + { + "epoch": 0.54, + "learning_rate": 1.0316558738777328e-05, + "loss": 1.3312, + "step": 5158 + }, + { + "epoch": 0.54, + "learning_rate": 1.0312900301979733e-05, + "loss": 1.369, + "step": 5159 + }, + { + "epoch": 0.54, + "learning_rate": 1.030924182326154e-05, + "loss": 1.2712, + "step": 5160 + }, + { + "epoch": 0.54, + "learning_rate": 1.0305583303112887e-05, + "loss": 1.3141, + "step": 5161 + }, + { + "epoch": 0.54, + "learning_rate": 1.030192474202392e-05, + "loss": 1.3708, + "step": 5162 + }, + { + "epoch": 0.54, + "learning_rate": 1.0298266140484798e-05, + "loss": 1.3724, + "step": 5163 + }, + { + "epoch": 0.54, + "learning_rate": 1.0294607498985678e-05, + "loss": 1.3208, + "step": 5164 + }, + { + "epoch": 0.54, + "learning_rate": 1.0290948818016722e-05, + "loss": 1.3379, + "step": 5165 + }, + { + "epoch": 0.54, + "learning_rate": 1.0287290098068099e-05, + "loss": 1.3236, + "step": 5166 + }, + { + "epoch": 0.54, + "learning_rate": 1.0283631339629982e-05, + "loss": 1.3437, + "step": 5167 + }, + { + "epoch": 0.54, + "learning_rate": 1.0279972543192561e-05, + "loss": 1.3381, + "step": 5168 + }, + { + "epoch": 0.54, + "learning_rate": 1.0276313709246007e-05, + "loss": 1.4287, + "step": 5169 + }, + { + "epoch": 0.54, + "learning_rate": 1.0272654838280515e-05, + "loss": 1.3587, + "step": 5170 + }, + { + "epoch": 0.54, + "learning_rate": 1.0268995930786283e-05, + "loss": 1.2982, + "step": 5171 + }, + { + "epoch": 0.54, + "learning_rate": 1.0265336987253509e-05, + "loss": 1.3416, + "step": 5172 + }, + { + "epoch": 0.54, + "learning_rate": 1.0261678008172393e-05, + "loss": 1.3827, + "step": 5173 + }, + { + "epoch": 0.54, + "learning_rate": 1.025801899403315e-05, + "loss": 1.3293, + "step": 5174 + }, + { + "epoch": 0.54, + "eval_loss": 1.4264723062515259, + "eval_runtime": 77.4376, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 5174 + }, + { + "epoch": 0.54, + "learning_rate": 1.0254359945325987e-05, + "loss": 1.3811, + "step": 5175 + }, + { + "epoch": 0.54, + "learning_rate": 1.0250700862541135e-05, + "loss": 1.3423, + "step": 5176 + }, + { + "epoch": 0.54, + "learning_rate": 1.02470417461688e-05, + "loss": 1.3641, + "step": 5177 + }, + { + "epoch": 0.54, + "learning_rate": 1.0243382596699226e-05, + "loss": 1.3211, + "step": 5178 + }, + { + "epoch": 0.54, + "learning_rate": 1.023972341462263e-05, + "loss": 1.4008, + "step": 5179 + }, + { + "epoch": 0.54, + "learning_rate": 1.0236064200429263e-05, + "loss": 1.404, + "step": 5180 + }, + { + "epoch": 0.54, + "learning_rate": 1.0232404954609353e-05, + "loss": 1.3359, + "step": 5181 + }, + { + "epoch": 0.54, + "learning_rate": 1.0228745677653155e-05, + "loss": 1.4069, + "step": 5182 + }, + { + "epoch": 0.54, + "learning_rate": 1.0225086370050914e-05, + "loss": 1.3343, + "step": 5183 + }, + { + "epoch": 0.54, + "learning_rate": 1.0221427032292881e-05, + "loss": 1.3109, + "step": 5184 + }, + { + "epoch": 0.54, + "learning_rate": 1.0217767664869312e-05, + "loss": 1.3611, + "step": 5185 + }, + { + "epoch": 0.54, + "learning_rate": 1.0214108268270476e-05, + "loss": 1.4072, + "step": 5186 + }, + { + "epoch": 0.54, + "learning_rate": 1.0210448842986631e-05, + "loss": 1.3602, + "step": 5187 + }, + { + "epoch": 0.54, + "learning_rate": 1.0206789389508047e-05, + "loss": 1.413, + "step": 5188 + }, + { + "epoch": 0.54, + "learning_rate": 1.0203129908325e-05, + "loss": 1.3209, + "step": 5189 + }, + { + "epoch": 0.54, + "learning_rate": 1.0199470399927764e-05, + "loss": 1.3714, + "step": 5190 + }, + { + "epoch": 0.54, + "learning_rate": 1.0195810864806623e-05, + "loss": 1.3556, + "step": 5191 + }, + { + "epoch": 0.54, + "learning_rate": 1.0192151303451852e-05, + "loss": 1.4116, + "step": 5192 + }, + { + "epoch": 0.54, + "learning_rate": 1.0188491716353745e-05, + "loss": 1.4102, + "step": 5193 + }, + { + "epoch": 0.54, + "learning_rate": 1.0184832104002592e-05, + "loss": 1.4849, + "step": 5194 + }, + { + "epoch": 0.54, + "learning_rate": 1.0181172466888689e-05, + "loss": 1.5395, + "step": 5195 + }, + { + "epoch": 0.54, + "learning_rate": 1.0177512805502325e-05, + "loss": 1.3627, + "step": 5196 + }, + { + "epoch": 0.54, + "learning_rate": 1.017385312033381e-05, + "loss": 1.4152, + "step": 5197 + }, + { + "epoch": 0.55, + "learning_rate": 1.0170193411873442e-05, + "loss": 1.3641, + "step": 5198 + }, + { + "epoch": 0.55, + "learning_rate": 1.0166533680611533e-05, + "loss": 1.3074, + "step": 5199 + }, + { + "epoch": 0.55, + "learning_rate": 1.0162873927038386e-05, + "loss": 1.35, + "step": 5200 + }, + { + "epoch": 0.55, + "learning_rate": 1.015921415164432e-05, + "loss": 1.3551, + "step": 5201 + }, + { + "epoch": 0.55, + "learning_rate": 1.0155554354919643e-05, + "loss": 1.3421, + "step": 5202 + }, + { + "epoch": 0.55, + "learning_rate": 1.0151894537354687e-05, + "loss": 1.4132, + "step": 5203 + }, + { + "epoch": 0.55, + "learning_rate": 1.0148234699439764e-05, + "loss": 1.351, + "step": 5204 + }, + { + "epoch": 0.55, + "learning_rate": 1.0144574841665198e-05, + "loss": 1.3745, + "step": 5205 + }, + { + "epoch": 0.55, + "learning_rate": 1.0140914964521316e-05, + "loss": 1.3151, + "step": 5206 + }, + { + "epoch": 0.55, + "learning_rate": 1.0137255068498456e-05, + "loss": 1.4903, + "step": 5207 + }, + { + "epoch": 0.55, + "learning_rate": 1.0133595154086937e-05, + "loss": 1.3945, + "step": 5208 + }, + { + "epoch": 0.55, + "learning_rate": 1.0129935221777104e-05, + "loss": 1.3924, + "step": 5209 + }, + { + "epoch": 0.55, + "learning_rate": 1.0126275272059286e-05, + "loss": 1.4191, + "step": 5210 + }, + { + "epoch": 0.55, + "learning_rate": 1.012261530542383e-05, + "loss": 1.3408, + "step": 5211 + }, + { + "epoch": 0.55, + "learning_rate": 1.0118955322361071e-05, + "loss": 1.3582, + "step": 5212 + }, + { + "epoch": 0.55, + "learning_rate": 1.0115295323361354e-05, + "loss": 1.3703, + "step": 5213 + }, + { + "epoch": 0.55, + "learning_rate": 1.011163530891503e-05, + "loss": 1.4181, + "step": 5214 + }, + { + "epoch": 0.55, + "learning_rate": 1.0107975279512442e-05, + "loss": 1.5019, + "step": 5215 + }, + { + "epoch": 0.55, + "learning_rate": 1.010431523564394e-05, + "loss": 1.3151, + "step": 5216 + }, + { + "epoch": 0.55, + "learning_rate": 1.0100655177799874e-05, + "loss": 1.4036, + "step": 5217 + }, + { + "epoch": 0.55, + "learning_rate": 1.0096995106470606e-05, + "loss": 1.3584, + "step": 5218 + }, + { + "epoch": 0.55, + "learning_rate": 1.0093335022146482e-05, + "loss": 1.3618, + "step": 5219 + }, + { + "epoch": 0.55, + "learning_rate": 1.0089674925317865e-05, + "loss": 1.3295, + "step": 5220 + }, + { + "epoch": 0.55, + "learning_rate": 1.0086014816475108e-05, + "loss": 1.3968, + "step": 5221 + }, + { + "epoch": 0.55, + "learning_rate": 1.0082354696108586e-05, + "loss": 1.2847, + "step": 5222 + }, + { + "epoch": 0.55, + "learning_rate": 1.007869456470864e-05, + "loss": 1.4461, + "step": 5223 + }, + { + "epoch": 0.55, + "learning_rate": 1.007503442276565e-05, + "loss": 1.3813, + "step": 5224 + }, + { + "epoch": 0.55, + "learning_rate": 1.007137427076997e-05, + "loss": 1.3833, + "step": 5225 + }, + { + "epoch": 0.55, + "learning_rate": 1.006771410921198e-05, + "loss": 1.4024, + "step": 5226 + }, + { + "epoch": 0.55, + "learning_rate": 1.0064053938582032e-05, + "loss": 1.3357, + "step": 5227 + }, + { + "epoch": 0.55, + "learning_rate": 1.0060393759370506e-05, + "loss": 1.35, + "step": 5228 + }, + { + "epoch": 0.55, + "learning_rate": 1.0056733572067765e-05, + "loss": 1.3512, + "step": 5229 + }, + { + "epoch": 0.55, + "learning_rate": 1.0053073377164186e-05, + "loss": 1.3852, + "step": 5230 + }, + { + "epoch": 0.55, + "learning_rate": 1.0049413175150135e-05, + "loss": 1.3502, + "step": 5231 + }, + { + "epoch": 0.55, + "learning_rate": 1.004575296651599e-05, + "loss": 1.4637, + "step": 5232 + }, + { + "epoch": 0.55, + "learning_rate": 1.0042092751752123e-05, + "loss": 1.3877, + "step": 5233 + }, + { + "epoch": 0.55, + "learning_rate": 1.0038432531348909e-05, + "loss": 1.3804, + "step": 5234 + }, + { + "epoch": 0.55, + "learning_rate": 1.0034772305796723e-05, + "loss": 1.3613, + "step": 5235 + }, + { + "epoch": 0.55, + "learning_rate": 1.003111207558594e-05, + "loss": 1.3218, + "step": 5236 + }, + { + "epoch": 0.55, + "learning_rate": 1.0027451841206944e-05, + "loss": 1.3554, + "step": 5237 + }, + { + "epoch": 0.55, + "learning_rate": 1.0023791603150099e-05, + "loss": 1.372, + "step": 5238 + }, + { + "epoch": 0.55, + "learning_rate": 1.0020131361905793e-05, + "loss": 1.3544, + "step": 5239 + }, + { + "epoch": 0.55, + "learning_rate": 1.0016471117964404e-05, + "loss": 1.3472, + "step": 5240 + }, + { + "epoch": 0.55, + "learning_rate": 1.001281087181631e-05, + "loss": 1.4247, + "step": 5241 + }, + { + "epoch": 0.55, + "learning_rate": 1.0009150623951883e-05, + "loss": 1.2685, + "step": 5242 + }, + { + "epoch": 0.55, + "learning_rate": 1.000549037486151e-05, + "loss": 1.4036, + "step": 5243 + }, + { + "epoch": 0.55, + "learning_rate": 1.0001830125035565e-05, + "loss": 1.3602, + "step": 5244 + }, + { + "epoch": 0.55, + "learning_rate": 9.998169874964437e-06, + "loss": 1.3784, + "step": 5245 + }, + { + "epoch": 0.55, + "learning_rate": 9.994509625138496e-06, + "loss": 1.3389, + "step": 5246 + }, + { + "epoch": 0.55, + "learning_rate": 9.990849376048119e-06, + "loss": 1.4561, + "step": 5247 + }, + { + "epoch": 0.55, + "learning_rate": 9.987189128183695e-06, + "loss": 1.3876, + "step": 5248 + }, + { + "epoch": 0.55, + "learning_rate": 9.9835288820356e-06, + "loss": 1.3362, + "step": 5249 + }, + { + "epoch": 0.55, + "learning_rate": 9.97986863809421e-06, + "loss": 1.3449, + "step": 5250 + }, + { + "epoch": 0.55, + "learning_rate": 9.9762083968499e-06, + "loss": 1.3521, + "step": 5251 + }, + { + "epoch": 0.55, + "learning_rate": 9.972548158793061e-06, + "loss": 1.4452, + "step": 5252 + }, + { + "epoch": 0.55, + "learning_rate": 9.968887924414062e-06, + "loss": 1.4126, + "step": 5253 + }, + { + "epoch": 0.55, + "learning_rate": 9.965227694203282e-06, + "loss": 1.3054, + "step": 5254 + }, + { + "epoch": 0.55, + "learning_rate": 9.961567468651093e-06, + "loss": 1.3771, + "step": 5255 + }, + { + "epoch": 0.55, + "learning_rate": 9.957907248247878e-06, + "loss": 1.3566, + "step": 5256 + }, + { + "epoch": 0.55, + "learning_rate": 9.954247033484014e-06, + "loss": 1.4765, + "step": 5257 + }, + { + "epoch": 0.55, + "learning_rate": 9.950586824849865e-06, + "loss": 1.4749, + "step": 5258 + }, + { + "epoch": 0.55, + "learning_rate": 9.946926622835815e-06, + "loss": 1.3679, + "step": 5259 + }, + { + "epoch": 0.55, + "learning_rate": 9.943266427932238e-06, + "loss": 1.2671, + "step": 5260 + }, + { + "epoch": 0.55, + "learning_rate": 9.9396062406295e-06, + "loss": 1.3485, + "step": 5261 + }, + { + "epoch": 0.55, + "learning_rate": 9.935946061417968e-06, + "loss": 1.3136, + "step": 5262 + }, + { + "epoch": 0.55, + "learning_rate": 9.932285890788024e-06, + "loss": 1.3954, + "step": 5263 + }, + { + "epoch": 0.55, + "learning_rate": 9.928625729230031e-06, + "loss": 1.428, + "step": 5264 + }, + { + "epoch": 0.55, + "learning_rate": 9.924965577234356e-06, + "loss": 1.4144, + "step": 5265 + }, + { + "epoch": 0.55, + "learning_rate": 9.92130543529136e-06, + "loss": 1.3361, + "step": 5266 + }, + { + "epoch": 0.55, + "learning_rate": 9.91764530389142e-06, + "loss": 1.4503, + "step": 5267 + }, + { + "epoch": 0.55, + "learning_rate": 9.913985183524893e-06, + "loss": 1.3431, + "step": 5268 + }, + { + "epoch": 0.55, + "learning_rate": 9.91032507468214e-06, + "loss": 1.3206, + "step": 5269 + }, + { + "epoch": 0.55, + "learning_rate": 9.906664977853518e-06, + "loss": 1.4568, + "step": 5270 + }, + { + "epoch": 0.55, + "learning_rate": 9.903004893529397e-06, + "loss": 1.3591, + "step": 5271 + }, + { + "epoch": 0.55, + "learning_rate": 9.899344822200127e-06, + "loss": 1.3382, + "step": 5272 + }, + { + "epoch": 0.55, + "learning_rate": 9.895684764356066e-06, + "loss": 1.3008, + "step": 5273 + }, + { + "epoch": 0.55, + "learning_rate": 9.89202472048756e-06, + "loss": 1.316, + "step": 5274 + }, + { + "epoch": 0.55, + "learning_rate": 9.888364691084971e-06, + "loss": 1.4246, + "step": 5275 + }, + { + "epoch": 0.55, + "learning_rate": 9.88470467663865e-06, + "loss": 1.3615, + "step": 5276 + }, + { + "epoch": 0.55, + "learning_rate": 9.881044677638934e-06, + "loss": 1.3418, + "step": 5277 + }, + { + "epoch": 0.55, + "learning_rate": 9.877384694576172e-06, + "loss": 1.249, + "step": 5278 + }, + { + "epoch": 0.55, + "learning_rate": 9.873724727940715e-06, + "loss": 1.2779, + "step": 5279 + }, + { + "epoch": 0.55, + "learning_rate": 9.870064778222903e-06, + "loss": 1.3529, + "step": 5280 + }, + { + "epoch": 0.55, + "learning_rate": 9.866404845913065e-06, + "loss": 1.3204, + "step": 5281 + }, + { + "epoch": 0.55, + "learning_rate": 9.862744931501548e-06, + "loss": 1.3537, + "step": 5282 + }, + { + "epoch": 0.55, + "learning_rate": 9.859085035478687e-06, + "loss": 1.3681, + "step": 5283 + }, + { + "epoch": 0.55, + "learning_rate": 9.855425158334809e-06, + "loss": 1.3983, + "step": 5284 + }, + { + "epoch": 0.55, + "learning_rate": 9.851765300560238e-06, + "loss": 1.401, + "step": 5285 + }, + { + "epoch": 0.55, + "learning_rate": 9.848105462645315e-06, + "loss": 1.3073, + "step": 5286 + }, + { + "epoch": 0.55, + "learning_rate": 9.844445645080358e-06, + "loss": 1.3162, + "step": 5287 + }, + { + "epoch": 0.55, + "learning_rate": 9.840785848355685e-06, + "loss": 1.3345, + "step": 5288 + }, + { + "epoch": 0.55, + "learning_rate": 9.837126072961616e-06, + "loss": 1.4241, + "step": 5289 + }, + { + "epoch": 0.55, + "learning_rate": 9.83346631938847e-06, + "loss": 1.3339, + "step": 5290 + }, + { + "epoch": 0.55, + "learning_rate": 9.829806588126561e-06, + "loss": 1.3507, + "step": 5291 + }, + { + "epoch": 0.55, + "learning_rate": 9.826146879666196e-06, + "loss": 1.2806, + "step": 5292 + }, + { + "epoch": 0.56, + "learning_rate": 9.822487194497675e-06, + "loss": 1.3952, + "step": 5293 + }, + { + "epoch": 0.56, + "learning_rate": 9.818827533111314e-06, + "loss": 1.3319, + "step": 5294 + }, + { + "epoch": 0.56, + "learning_rate": 9.81516789599741e-06, + "loss": 1.351, + "step": 5295 + }, + { + "epoch": 0.56, + "learning_rate": 9.811508283646258e-06, + "loss": 1.4076, + "step": 5296 + }, + { + "epoch": 0.56, + "learning_rate": 9.80784869654815e-06, + "loss": 1.3271, + "step": 5297 + }, + { + "epoch": 0.56, + "learning_rate": 9.80418913519338e-06, + "loss": 1.4059, + "step": 5298 + }, + { + "epoch": 0.56, + "learning_rate": 9.80052960007224e-06, + "loss": 1.4146, + "step": 5299 + }, + { + "epoch": 0.56, + "learning_rate": 9.796870091675005e-06, + "loss": 1.3454, + "step": 5300 + }, + { + "epoch": 0.56, + "learning_rate": 9.793210610491953e-06, + "loss": 1.4376, + "step": 5301 + }, + { + "epoch": 0.56, + "learning_rate": 9.789551157013372e-06, + "loss": 1.3437, + "step": 5302 + }, + { + "epoch": 0.56, + "learning_rate": 9.78589173172953e-06, + "loss": 1.3073, + "step": 5303 + }, + { + "epoch": 0.56, + "learning_rate": 9.782232335130688e-06, + "loss": 1.2989, + "step": 5304 + }, + { + "epoch": 0.56, + "learning_rate": 9.778572967707122e-06, + "loss": 1.4028, + "step": 5305 + }, + { + "epoch": 0.56, + "learning_rate": 9.77491362994909e-06, + "loss": 1.3096, + "step": 5306 + }, + { + "epoch": 0.56, + "learning_rate": 9.77125432234685e-06, + "loss": 1.3719, + "step": 5307 + }, + { + "epoch": 0.56, + "learning_rate": 9.767595045390647e-06, + "loss": 1.3271, + "step": 5308 + }, + { + "epoch": 0.56, + "learning_rate": 9.763935799570739e-06, + "loss": 1.3693, + "step": 5309 + }, + { + "epoch": 0.56, + "learning_rate": 9.760276585377371e-06, + "loss": 1.3586, + "step": 5310 + }, + { + "epoch": 0.56, + "learning_rate": 9.756617403300781e-06, + "loss": 1.3423, + "step": 5311 + }, + { + "epoch": 0.56, + "learning_rate": 9.7529582538312e-06, + "loss": 1.388, + "step": 5312 + }, + { + "epoch": 0.56, + "learning_rate": 9.74929913745887e-06, + "loss": 1.3594, + "step": 5313 + }, + { + "epoch": 0.56, + "learning_rate": 9.745640054674015e-06, + "loss": 1.2831, + "step": 5314 + }, + { + "epoch": 0.56, + "learning_rate": 9.741981005966856e-06, + "loss": 1.4207, + "step": 5315 + }, + { + "epoch": 0.56, + "learning_rate": 9.738321991827609e-06, + "loss": 1.2807, + "step": 5316 + }, + { + "epoch": 0.56, + "learning_rate": 9.734663012746493e-06, + "loss": 1.3396, + "step": 5317 + }, + { + "epoch": 0.56, + "learning_rate": 9.731004069213722e-06, + "loss": 1.3666, + "step": 5318 + }, + { + "epoch": 0.56, + "learning_rate": 9.72734516171949e-06, + "loss": 1.3466, + "step": 5319 + }, + { + "epoch": 0.56, + "learning_rate": 9.723686290753995e-06, + "loss": 1.4478, + "step": 5320 + }, + { + "epoch": 0.56, + "learning_rate": 9.720027456807442e-06, + "loss": 1.316, + "step": 5321 + }, + { + "epoch": 0.56, + "learning_rate": 9.71636866037002e-06, + "loss": 1.3762, + "step": 5322 + }, + { + "epoch": 0.56, + "learning_rate": 9.712709901931906e-06, + "loss": 1.4156, + "step": 5323 + }, + { + "epoch": 0.56, + "learning_rate": 9.70905118198328e-06, + "loss": 1.2452, + "step": 5324 + }, + { + "epoch": 0.56, + "learning_rate": 9.705392501014325e-06, + "loss": 1.3771, + "step": 5325 + }, + { + "epoch": 0.56, + "learning_rate": 9.701733859515205e-06, + "loss": 1.3433, + "step": 5326 + }, + { + "epoch": 0.56, + "learning_rate": 9.698075257976079e-06, + "loss": 1.3702, + "step": 5327 + }, + { + "epoch": 0.56, + "learning_rate": 9.694416696887115e-06, + "loss": 1.295, + "step": 5328 + }, + { + "epoch": 0.56, + "learning_rate": 9.690758176738463e-06, + "loss": 1.3462, + "step": 5329 + }, + { + "epoch": 0.56, + "learning_rate": 9.68709969802027e-06, + "loss": 1.5304, + "step": 5330 + }, + { + "epoch": 0.56, + "learning_rate": 9.683441261222672e-06, + "loss": 1.3518, + "step": 5331 + }, + { + "epoch": 0.56, + "learning_rate": 9.679782866835816e-06, + "loss": 1.3778, + "step": 5332 + }, + { + "epoch": 0.56, + "learning_rate": 9.67612451534983e-06, + "loss": 1.3731, + "step": 5333 + }, + { + "epoch": 0.56, + "learning_rate": 9.672466207254837e-06, + "loss": 1.3315, + "step": 5334 + }, + { + "epoch": 0.56, + "learning_rate": 9.66880794304095e-06, + "loss": 1.3105, + "step": 5335 + }, + { + "epoch": 0.56, + "learning_rate": 9.665149723198293e-06, + "loss": 1.3903, + "step": 5336 + }, + { + "epoch": 0.56, + "learning_rate": 9.661491548216972e-06, + "loss": 1.3554, + "step": 5337 + }, + { + "epoch": 0.56, + "learning_rate": 9.657833418587084e-06, + "loss": 1.3231, + "step": 5338 + }, + { + "epoch": 0.56, + "learning_rate": 9.65417533479872e-06, + "loss": 1.352, + "step": 5339 + }, + { + "epoch": 0.56, + "learning_rate": 9.650517297341983e-06, + "loss": 1.3957, + "step": 5340 + }, + { + "epoch": 0.56, + "learning_rate": 9.646859306706948e-06, + "loss": 1.3938, + "step": 5341 + }, + { + "epoch": 0.56, + "learning_rate": 9.643201363383693e-06, + "loss": 1.3038, + "step": 5342 + }, + { + "epoch": 0.56, + "learning_rate": 9.63954346786228e-06, + "loss": 1.2973, + "step": 5343 + }, + { + "epoch": 0.56, + "learning_rate": 9.635885620632786e-06, + "loss": 1.379, + "step": 5344 + }, + { + "epoch": 0.56, + "learning_rate": 9.632227822185266e-06, + "loss": 1.5377, + "step": 5345 + }, + { + "epoch": 0.56, + "learning_rate": 9.628570073009767e-06, + "loss": 1.4573, + "step": 5346 + }, + { + "epoch": 0.56, + "learning_rate": 9.624912373596329e-06, + "loss": 1.3394, + "step": 5347 + }, + { + "epoch": 0.56, + "learning_rate": 9.621254724434999e-06, + "loss": 1.4157, + "step": 5348 + }, + { + "epoch": 0.56, + "learning_rate": 9.617597126015808e-06, + "loss": 1.3526, + "step": 5349 + }, + { + "epoch": 0.56, + "learning_rate": 9.61393957882877e-06, + "loss": 1.3795, + "step": 5350 + }, + { + "epoch": 0.56, + "learning_rate": 9.610282083363913e-06, + "loss": 1.3765, + "step": 5351 + }, + { + "epoch": 0.56, + "learning_rate": 9.606624640111243e-06, + "loss": 1.3512, + "step": 5352 + }, + { + "epoch": 0.56, + "learning_rate": 9.602967249560766e-06, + "loss": 1.3298, + "step": 5353 + }, + { + "epoch": 0.56, + "learning_rate": 9.599309912202469e-06, + "loss": 1.3093, + "step": 5354 + }, + { + "epoch": 0.56, + "learning_rate": 9.595652628526354e-06, + "loss": 1.3353, + "step": 5355 + }, + { + "epoch": 0.56, + "learning_rate": 9.591995399022397e-06, + "loss": 1.3081, + "step": 5356 + }, + { + "epoch": 0.56, + "learning_rate": 9.588338224180576e-06, + "loss": 1.343, + "step": 5357 + }, + { + "epoch": 0.56, + "learning_rate": 9.584681104490848e-06, + "loss": 1.3275, + "step": 5358 + }, + { + "epoch": 0.56, + "learning_rate": 9.581024040443185e-06, + "loss": 1.3399, + "step": 5359 + }, + { + "epoch": 0.56, + "learning_rate": 9.577367032527538e-06, + "loss": 1.3181, + "step": 5360 + }, + { + "epoch": 0.56, + "learning_rate": 9.573710081233846e-06, + "loss": 1.3531, + "step": 5361 + }, + { + "epoch": 0.56, + "learning_rate": 9.570053187052049e-06, + "loss": 1.4056, + "step": 5362 + }, + { + "epoch": 0.56, + "learning_rate": 9.566396350472079e-06, + "loss": 1.3303, + "step": 5363 + }, + { + "epoch": 0.56, + "learning_rate": 9.56273957198386e-06, + "loss": 1.3506, + "step": 5364 + }, + { + "epoch": 0.56, + "learning_rate": 9.559082852077302e-06, + "loss": 1.4588, + "step": 5365 + }, + { + "epoch": 0.56, + "learning_rate": 9.555426191242307e-06, + "loss": 1.3434, + "step": 5366 + }, + { + "epoch": 0.56, + "learning_rate": 9.551769589968784e-06, + "loss": 1.3508, + "step": 5367 + }, + { + "epoch": 0.56, + "learning_rate": 9.548113048746622e-06, + "loss": 1.3701, + "step": 5368 + }, + { + "epoch": 0.56, + "learning_rate": 9.544456568065698e-06, + "loss": 1.3664, + "step": 5369 + }, + { + "epoch": 0.56, + "learning_rate": 9.540800148415885e-06, + "loss": 1.6697, + "step": 5370 + }, + { + "epoch": 0.56, + "learning_rate": 9.537143790287057e-06, + "loss": 1.5298, + "step": 5371 + }, + { + "epoch": 0.56, + "learning_rate": 9.533487494169073e-06, + "loss": 1.3884, + "step": 5372 + }, + { + "epoch": 0.56, + "learning_rate": 9.52983126055177e-06, + "loss": 1.403, + "step": 5373 + }, + { + "epoch": 0.56, + "eval_loss": 1.4240995645523071, + "eval_runtime": 77.4615, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 5373 + }, + { + "epoch": 0.56, + "learning_rate": 9.526175089925e-06, + "loss": 1.3141, + "step": 5374 + }, + { + "epoch": 0.56, + "learning_rate": 9.522518982778596e-06, + "loss": 1.3733, + "step": 5375 + }, + { + "epoch": 0.56, + "learning_rate": 9.51886293960238e-06, + "loss": 1.3095, + "step": 5376 + }, + { + "epoch": 0.56, + "learning_rate": 9.515206960886162e-06, + "loss": 1.3713, + "step": 5377 + }, + { + "epoch": 0.56, + "learning_rate": 9.51155104711976e-06, + "loss": 1.3585, + "step": 5378 + }, + { + "epoch": 0.56, + "learning_rate": 9.507895198792967e-06, + "loss": 1.3473, + "step": 5379 + }, + { + "epoch": 0.56, + "learning_rate": 9.504239416395576e-06, + "loss": 1.3282, + "step": 5380 + }, + { + "epoch": 0.56, + "learning_rate": 9.500583700417357e-06, + "loss": 1.3655, + "step": 5381 + }, + { + "epoch": 0.56, + "learning_rate": 9.496928051348095e-06, + "loss": 1.4512, + "step": 5382 + }, + { + "epoch": 0.56, + "learning_rate": 9.49327246967755e-06, + "loss": 1.4071, + "step": 5383 + }, + { + "epoch": 0.56, + "learning_rate": 9.489616955895472e-06, + "loss": 1.3703, + "step": 5384 + }, + { + "epoch": 0.56, + "learning_rate": 9.485961510491604e-06, + "loss": 1.3358, + "step": 5385 + }, + { + "epoch": 0.56, + "learning_rate": 9.482306133955691e-06, + "loss": 1.3505, + "step": 5386 + }, + { + "epoch": 0.56, + "learning_rate": 9.478650826777457e-06, + "loss": 1.2578, + "step": 5387 + }, + { + "epoch": 0.57, + "learning_rate": 9.474995589446612e-06, + "loss": 1.4298, + "step": 5388 + }, + { + "epoch": 0.57, + "learning_rate": 9.471340422452864e-06, + "loss": 1.4044, + "step": 5389 + }, + { + "epoch": 0.57, + "learning_rate": 9.467685326285922e-06, + "loss": 1.3524, + "step": 5390 + }, + { + "epoch": 0.57, + "learning_rate": 9.46403030143547e-06, + "loss": 1.3017, + "step": 5391 + }, + { + "epoch": 0.57, + "learning_rate": 9.460375348391185e-06, + "loss": 1.3361, + "step": 5392 + }, + { + "epoch": 0.57, + "learning_rate": 9.456720467642733e-06, + "loss": 1.3182, + "step": 5393 + }, + { + "epoch": 0.57, + "learning_rate": 9.453065659679785e-06, + "loss": 1.3869, + "step": 5394 + }, + { + "epoch": 0.57, + "learning_rate": 9.449410924991986e-06, + "loss": 1.3161, + "step": 5395 + }, + { + "epoch": 0.57, + "learning_rate": 9.44575626406897e-06, + "loss": 1.3, + "step": 5396 + }, + { + "epoch": 0.57, + "learning_rate": 9.442101677400378e-06, + "loss": 1.5103, + "step": 5397 + }, + { + "epoch": 0.57, + "learning_rate": 9.438447165475828e-06, + "loss": 1.3511, + "step": 5398 + }, + { + "epoch": 0.57, + "learning_rate": 9.43479272878493e-06, + "loss": 1.3461, + "step": 5399 + }, + { + "epoch": 0.57, + "learning_rate": 9.431138367817277e-06, + "loss": 1.2657, + "step": 5400 + }, + { + "epoch": 0.57, + "learning_rate": 9.427484083062472e-06, + "loss": 1.3736, + "step": 5401 + }, + { + "epoch": 0.57, + "learning_rate": 9.423829875010089e-06, + "loss": 1.3476, + "step": 5402 + }, + { + "epoch": 0.57, + "learning_rate": 9.4201757441497e-06, + "loss": 1.3495, + "step": 5403 + }, + { + "epoch": 0.57, + "learning_rate": 9.416521690970857e-06, + "loss": 1.387, + "step": 5404 + }, + { + "epoch": 0.57, + "learning_rate": 9.41286771596312e-06, + "loss": 1.2829, + "step": 5405 + }, + { + "epoch": 0.57, + "learning_rate": 9.409213819616022e-06, + "loss": 1.3544, + "step": 5406 + }, + { + "epoch": 0.57, + "learning_rate": 9.405560002419098e-06, + "loss": 1.3202, + "step": 5407 + }, + { + "epoch": 0.57, + "learning_rate": 9.40190626486185e-06, + "loss": 1.3034, + "step": 5408 + }, + { + "epoch": 0.57, + "learning_rate": 9.398252607433801e-06, + "loss": 1.3223, + "step": 5409 + }, + { + "epoch": 0.57, + "learning_rate": 9.394599030624443e-06, + "loss": 1.3327, + "step": 5410 + }, + { + "epoch": 0.57, + "learning_rate": 9.390945534923258e-06, + "loss": 1.3248, + "step": 5411 + }, + { + "epoch": 0.57, + "learning_rate": 9.387292120819716e-06, + "loss": 1.3084, + "step": 5412 + }, + { + "epoch": 0.57, + "learning_rate": 9.383638788803291e-06, + "loss": 1.344, + "step": 5413 + }, + { + "epoch": 0.57, + "learning_rate": 9.379985539363436e-06, + "loss": 1.3354, + "step": 5414 + }, + { + "epoch": 0.57, + "learning_rate": 9.376332372989586e-06, + "loss": 1.3291, + "step": 5415 + }, + { + "epoch": 0.57, + "learning_rate": 9.372679290171167e-06, + "loss": 1.3468, + "step": 5416 + }, + { + "epoch": 0.57, + "learning_rate": 9.36902629139761e-06, + "loss": 1.3481, + "step": 5417 + }, + { + "epoch": 0.57, + "learning_rate": 9.36537337715832e-06, + "loss": 1.3309, + "step": 5418 + }, + { + "epoch": 0.57, + "learning_rate": 9.361720547942683e-06, + "loss": 1.362, + "step": 5419 + }, + { + "epoch": 0.57, + "learning_rate": 9.358067804240098e-06, + "loss": 1.3647, + "step": 5420 + }, + { + "epoch": 0.57, + "learning_rate": 9.354415146539933e-06, + "loss": 1.4511, + "step": 5421 + }, + { + "epoch": 0.57, + "learning_rate": 9.350762575331554e-06, + "loss": 1.3379, + "step": 5422 + }, + { + "epoch": 0.57, + "learning_rate": 9.3471100911043e-06, + "loss": 1.5468, + "step": 5423 + }, + { + "epoch": 0.57, + "learning_rate": 9.343457694347524e-06, + "loss": 1.4259, + "step": 5424 + }, + { + "epoch": 0.57, + "learning_rate": 9.339805385550548e-06, + "loss": 1.3816, + "step": 5425 + }, + { + "epoch": 0.57, + "learning_rate": 9.336153165202689e-06, + "loss": 1.3627, + "step": 5426 + }, + { + "epoch": 0.57, + "learning_rate": 9.332501033793242e-06, + "loss": 1.3338, + "step": 5427 + }, + { + "epoch": 0.57, + "learning_rate": 9.328848991811509e-06, + "loss": 1.2946, + "step": 5428 + }, + { + "epoch": 0.57, + "learning_rate": 9.325197039746769e-06, + "loss": 1.3405, + "step": 5429 + }, + { + "epoch": 0.57, + "learning_rate": 9.321545178088288e-06, + "loss": 1.3549, + "step": 5430 + }, + { + "epoch": 0.57, + "learning_rate": 9.317893407325314e-06, + "loss": 1.3225, + "step": 5431 + }, + { + "epoch": 0.57, + "learning_rate": 9.314241727947101e-06, + "loss": 1.3457, + "step": 5432 + }, + { + "epoch": 0.57, + "learning_rate": 9.310590140442878e-06, + "loss": 1.311, + "step": 5433 + }, + { + "epoch": 0.57, + "learning_rate": 9.306938645301862e-06, + "loss": 1.3615, + "step": 5434 + }, + { + "epoch": 0.57, + "learning_rate": 9.303287243013255e-06, + "loss": 1.3495, + "step": 5435 + }, + { + "epoch": 0.57, + "learning_rate": 9.29963593406626e-06, + "loss": 1.3899, + "step": 5436 + }, + { + "epoch": 0.57, + "learning_rate": 9.295984718950058e-06, + "loss": 1.3189, + "step": 5437 + }, + { + "epoch": 0.57, + "learning_rate": 9.292333598153813e-06, + "loss": 1.4199, + "step": 5438 + }, + { + "epoch": 0.57, + "learning_rate": 9.288682572166677e-06, + "loss": 1.4751, + "step": 5439 + }, + { + "epoch": 0.57, + "learning_rate": 9.285031641477804e-06, + "loss": 1.3435, + "step": 5440 + }, + { + "epoch": 0.57, + "learning_rate": 9.281380806576322e-06, + "loss": 1.2954, + "step": 5441 + }, + { + "epoch": 0.57, + "learning_rate": 9.277730067951341e-06, + "loss": 1.3414, + "step": 5442 + }, + { + "epoch": 0.57, + "learning_rate": 9.274079426091978e-06, + "loss": 1.3642, + "step": 5443 + }, + { + "epoch": 0.57, + "learning_rate": 9.27042888148732e-06, + "loss": 1.3651, + "step": 5444 + }, + { + "epoch": 0.57, + "learning_rate": 9.266778434626448e-06, + "loss": 1.3995, + "step": 5445 + }, + { + "epoch": 0.57, + "learning_rate": 9.263128085998421e-06, + "loss": 1.2692, + "step": 5446 + }, + { + "epoch": 0.57, + "learning_rate": 9.2594778360923e-06, + "loss": 1.4355, + "step": 5447 + }, + { + "epoch": 0.57, + "learning_rate": 9.255827685397124e-06, + "loss": 1.4262, + "step": 5448 + }, + { + "epoch": 0.57, + "learning_rate": 9.252177634401917e-06, + "loss": 1.3372, + "step": 5449 + }, + { + "epoch": 0.57, + "learning_rate": 9.248527683595685e-06, + "loss": 1.4603, + "step": 5450 + }, + { + "epoch": 0.57, + "learning_rate": 9.24487783346744e-06, + "loss": 1.446, + "step": 5451 + }, + { + "epoch": 0.57, + "learning_rate": 9.241228084506167e-06, + "loss": 1.4088, + "step": 5452 + }, + { + "epoch": 0.57, + "learning_rate": 9.237578437200832e-06, + "loss": 1.3074, + "step": 5453 + }, + { + "epoch": 0.57, + "learning_rate": 9.233928892040392e-06, + "loss": 1.4347, + "step": 5454 + }, + { + "epoch": 0.57, + "learning_rate": 9.230279449513802e-06, + "loss": 1.2982, + "step": 5455 + }, + { + "epoch": 0.57, + "learning_rate": 9.226630110109988e-06, + "loss": 1.2928, + "step": 5456 + }, + { + "epoch": 0.57, + "learning_rate": 9.222980874317869e-06, + "loss": 1.2849, + "step": 5457 + }, + { + "epoch": 0.57, + "learning_rate": 9.219331742626343e-06, + "loss": 1.3137, + "step": 5458 + }, + { + "epoch": 0.57, + "learning_rate": 9.215682715524309e-06, + "loss": 1.3523, + "step": 5459 + }, + { + "epoch": 0.57, + "learning_rate": 9.21203379350064e-06, + "loss": 1.381, + "step": 5460 + }, + { + "epoch": 0.57, + "learning_rate": 9.208384977044191e-06, + "loss": 1.286, + "step": 5461 + }, + { + "epoch": 0.57, + "learning_rate": 9.204736266643819e-06, + "loss": 1.3467, + "step": 5462 + }, + { + "epoch": 0.57, + "learning_rate": 9.201087662788353e-06, + "loss": 1.3582, + "step": 5463 + }, + { + "epoch": 0.57, + "learning_rate": 9.197439165966617e-06, + "loss": 1.3912, + "step": 5464 + }, + { + "epoch": 0.57, + "learning_rate": 9.193790776667402e-06, + "loss": 1.3144, + "step": 5465 + }, + { + "epoch": 0.57, + "learning_rate": 9.190142495379515e-06, + "loss": 1.3403, + "step": 5466 + }, + { + "epoch": 0.57, + "learning_rate": 9.186494322591725e-06, + "loss": 1.3253, + "step": 5467 + }, + { + "epoch": 0.57, + "learning_rate": 9.182846258792794e-06, + "loss": 1.2908, + "step": 5468 + }, + { + "epoch": 0.57, + "learning_rate": 9.179198304471463e-06, + "loss": 1.3486, + "step": 5469 + }, + { + "epoch": 0.57, + "learning_rate": 9.175550460116473e-06, + "loss": 1.3915, + "step": 5470 + }, + { + "epoch": 0.57, + "learning_rate": 9.171902726216538e-06, + "loss": 1.3441, + "step": 5471 + }, + { + "epoch": 0.57, + "learning_rate": 9.168255103260362e-06, + "loss": 1.3196, + "step": 5472 + }, + { + "epoch": 0.57, + "learning_rate": 9.164607591736627e-06, + "loss": 1.3279, + "step": 5473 + }, + { + "epoch": 0.57, + "learning_rate": 9.160960192134011e-06, + "loss": 1.2643, + "step": 5474 + }, + { + "epoch": 0.57, + "learning_rate": 9.157312904941174e-06, + "loss": 1.3327, + "step": 5475 + }, + { + "epoch": 0.57, + "learning_rate": 9.153665730646756e-06, + "loss": 1.4016, + "step": 5476 + }, + { + "epoch": 0.57, + "learning_rate": 9.150018669739378e-06, + "loss": 1.3614, + "step": 5477 + }, + { + "epoch": 0.57, + "learning_rate": 9.146371722707662e-06, + "loss": 1.3469, + "step": 5478 + }, + { + "epoch": 0.57, + "learning_rate": 9.142724890040204e-06, + "loss": 1.3625, + "step": 5479 + }, + { + "epoch": 0.57, + "learning_rate": 9.139078172225585e-06, + "loss": 1.3879, + "step": 5480 + }, + { + "epoch": 0.57, + "learning_rate": 9.135431569752362e-06, + "loss": 1.3738, + "step": 5481 + }, + { + "epoch": 0.57, + "learning_rate": 9.131785083109101e-06, + "loss": 1.3507, + "step": 5482 + }, + { + "epoch": 0.57, + "learning_rate": 9.128138712784331e-06, + "loss": 1.3681, + "step": 5483 + }, + { + "epoch": 0.58, + "learning_rate": 9.124492459266567e-06, + "loss": 1.332, + "step": 5484 + }, + { + "epoch": 0.58, + "learning_rate": 9.12084632304432e-06, + "loss": 1.4746, + "step": 5485 + }, + { + "epoch": 0.58, + "learning_rate": 9.11720030460608e-06, + "loss": 1.2775, + "step": 5486 + }, + { + "epoch": 0.58, + "learning_rate": 9.113554404440317e-06, + "loss": 1.2567, + "step": 5487 + }, + { + "epoch": 0.58, + "learning_rate": 9.10990862303548e-06, + "loss": 1.3935, + "step": 5488 + }, + { + "epoch": 0.58, + "learning_rate": 9.106262960880024e-06, + "loss": 1.3544, + "step": 5489 + }, + { + "epoch": 0.58, + "learning_rate": 9.102617418462365e-06, + "loss": 1.4023, + "step": 5490 + }, + { + "epoch": 0.58, + "learning_rate": 9.098971996270918e-06, + "loss": 1.3759, + "step": 5491 + }, + { + "epoch": 0.58, + "learning_rate": 9.095326694794064e-06, + "loss": 1.4165, + "step": 5492 + }, + { + "epoch": 0.58, + "learning_rate": 9.091681514520194e-06, + "loss": 1.3189, + "step": 5493 + }, + { + "epoch": 0.58, + "learning_rate": 9.088036455937663e-06, + "loss": 1.3135, + "step": 5494 + }, + { + "epoch": 0.58, + "learning_rate": 9.084391519534815e-06, + "loss": 1.3521, + "step": 5495 + }, + { + "epoch": 0.58, + "learning_rate": 9.080746705799971e-06, + "loss": 1.3314, + "step": 5496 + }, + { + "epoch": 0.58, + "learning_rate": 9.077102015221457e-06, + "loss": 1.3119, + "step": 5497 + }, + { + "epoch": 0.58, + "learning_rate": 9.073457448287557e-06, + "loss": 1.2895, + "step": 5498 + }, + { + "epoch": 0.58, + "learning_rate": 9.069813005486554e-06, + "loss": 1.3155, + "step": 5499 + }, + { + "epoch": 0.58, + "learning_rate": 9.066168687306701e-06, + "loss": 1.4048, + "step": 5500 + }, + { + "epoch": 0.58, + "learning_rate": 9.062524494236256e-06, + "loss": 1.3665, + "step": 5501 + }, + { + "epoch": 0.58, + "learning_rate": 9.058880426763442e-06, + "loss": 1.3258, + "step": 5502 + }, + { + "epoch": 0.58, + "learning_rate": 9.05523648537647e-06, + "loss": 1.3078, + "step": 5503 + }, + { + "epoch": 0.58, + "learning_rate": 9.051592670563527e-06, + "loss": 1.361, + "step": 5504 + }, + { + "epoch": 0.58, + "learning_rate": 9.047948982812801e-06, + "loss": 1.3557, + "step": 5505 + }, + { + "epoch": 0.58, + "learning_rate": 9.044305422612453e-06, + "loss": 1.5733, + "step": 5506 + }, + { + "epoch": 0.58, + "learning_rate": 9.040661990450617e-06, + "loss": 1.2835, + "step": 5507 + }, + { + "epoch": 0.58, + "learning_rate": 9.037018686815428e-06, + "loss": 1.311, + "step": 5508 + }, + { + "epoch": 0.58, + "learning_rate": 9.033375512194993e-06, + "loss": 1.3949, + "step": 5509 + }, + { + "epoch": 0.58, + "learning_rate": 9.029732467077405e-06, + "loss": 1.356, + "step": 5510 + }, + { + "epoch": 0.58, + "learning_rate": 9.026089551950727e-06, + "loss": 1.3695, + "step": 5511 + }, + { + "epoch": 0.58, + "learning_rate": 9.022446767303033e-06, + "loss": 1.3325, + "step": 5512 + }, + { + "epoch": 0.58, + "learning_rate": 9.018804113622353e-06, + "loss": 1.401, + "step": 5513 + }, + { + "epoch": 0.58, + "learning_rate": 9.015161591396713e-06, + "loss": 1.3632, + "step": 5514 + }, + { + "epoch": 0.58, + "learning_rate": 9.011519201114108e-06, + "loss": 1.3697, + "step": 5515 + }, + { + "epoch": 0.58, + "learning_rate": 9.007876943262538e-06, + "loss": 1.2604, + "step": 5516 + }, + { + "epoch": 0.58, + "learning_rate": 9.004234818329964e-06, + "loss": 1.3557, + "step": 5517 + }, + { + "epoch": 0.58, + "learning_rate": 9.000592826804342e-06, + "loss": 1.3248, + "step": 5518 + }, + { + "epoch": 0.58, + "learning_rate": 8.996950969173596e-06, + "loss": 1.3237, + "step": 5519 + }, + { + "epoch": 0.58, + "learning_rate": 8.99330924592565e-06, + "loss": 1.339, + "step": 5520 + }, + { + "epoch": 0.58, + "learning_rate": 8.989667657548402e-06, + "loss": 1.3218, + "step": 5521 + }, + { + "epoch": 0.58, + "learning_rate": 8.986026204529728e-06, + "loss": 1.3354, + "step": 5522 + }, + { + "epoch": 0.58, + "learning_rate": 8.982384887357484e-06, + "loss": 1.3011, + "step": 5523 + }, + { + "epoch": 0.58, + "learning_rate": 8.978743706519524e-06, + "loss": 1.3526, + "step": 5524 + }, + { + "epoch": 0.58, + "learning_rate": 8.975102662503666e-06, + "loss": 1.3298, + "step": 5525 + }, + { + "epoch": 0.58, + "learning_rate": 8.971461755797718e-06, + "loss": 1.328, + "step": 5526 + }, + { + "epoch": 0.58, + "learning_rate": 8.967820986889461e-06, + "loss": 1.3705, + "step": 5527 + }, + { + "epoch": 0.58, + "learning_rate": 8.964180356266676e-06, + "loss": 1.3814, + "step": 5528 + }, + { + "epoch": 0.58, + "learning_rate": 8.96053986441711e-06, + "loss": 1.37, + "step": 5529 + }, + { + "epoch": 0.58, + "learning_rate": 8.956899511828489e-06, + "loss": 1.3224, + "step": 5530 + }, + { + "epoch": 0.58, + "learning_rate": 8.953259298988536e-06, + "loss": 1.3416, + "step": 5531 + }, + { + "epoch": 0.58, + "learning_rate": 8.949619226384942e-06, + "loss": 1.4212, + "step": 5532 + }, + { + "epoch": 0.58, + "learning_rate": 8.945979294505383e-06, + "loss": 1.4145, + "step": 5533 + }, + { + "epoch": 0.58, + "learning_rate": 8.942339503837512e-06, + "loss": 1.2179, + "step": 5534 + }, + { + "epoch": 0.58, + "learning_rate": 8.938699854868976e-06, + "loss": 1.3239, + "step": 5535 + }, + { + "epoch": 0.58, + "learning_rate": 8.93506034808739e-06, + "loss": 1.3488, + "step": 5536 + }, + { + "epoch": 0.58, + "learning_rate": 8.931420983980357e-06, + "loss": 1.3283, + "step": 5537 + }, + { + "epoch": 0.58, + "learning_rate": 8.927781763035449e-06, + "loss": 1.3866, + "step": 5538 + }, + { + "epoch": 0.58, + "learning_rate": 8.924142685740239e-06, + "loss": 1.3877, + "step": 5539 + }, + { + "epoch": 0.58, + "learning_rate": 8.920503752582265e-06, + "loss": 1.2511, + "step": 5540 + }, + { + "epoch": 0.58, + "learning_rate": 8.916864964049056e-06, + "loss": 1.3581, + "step": 5541 + }, + { + "epoch": 0.58, + "learning_rate": 8.913226320628104e-06, + "loss": 1.387, + "step": 5542 + }, + { + "epoch": 0.58, + "learning_rate": 8.909587822806905e-06, + "loss": 1.3785, + "step": 5543 + }, + { + "epoch": 0.58, + "learning_rate": 8.905949471072921e-06, + "loss": 1.4302, + "step": 5544 + }, + { + "epoch": 0.58, + "learning_rate": 8.9023112659136e-06, + "loss": 1.439, + "step": 5545 + }, + { + "epoch": 0.58, + "learning_rate": 8.898673207816357e-06, + "loss": 1.3257, + "step": 5546 + }, + { + "epoch": 0.58, + "learning_rate": 8.895035297268611e-06, + "loss": 1.4237, + "step": 5547 + }, + { + "epoch": 0.58, + "learning_rate": 8.891397534757745e-06, + "loss": 1.3141, + "step": 5548 + }, + { + "epoch": 0.58, + "learning_rate": 8.887759920771127e-06, + "loss": 1.3069, + "step": 5549 + }, + { + "epoch": 0.58, + "learning_rate": 8.884122455796095e-06, + "loss": 1.2703, + "step": 5550 + }, + { + "epoch": 0.58, + "learning_rate": 8.880485140319986e-06, + "loss": 1.2929, + "step": 5551 + }, + { + "epoch": 0.58, + "learning_rate": 8.876847974830103e-06, + "loss": 1.3719, + "step": 5552 + }, + { + "epoch": 0.58, + "learning_rate": 8.873210959813731e-06, + "loss": 1.3481, + "step": 5553 + }, + { + "epoch": 0.58, + "learning_rate": 8.869574095758141e-06, + "loss": 1.3609, + "step": 5554 + }, + { + "epoch": 0.58, + "learning_rate": 8.865937383150577e-06, + "loss": 1.3137, + "step": 5555 + }, + { + "epoch": 0.58, + "learning_rate": 8.862300822478265e-06, + "loss": 1.3602, + "step": 5556 + }, + { + "epoch": 0.58, + "learning_rate": 8.858664414228409e-06, + "loss": 1.3142, + "step": 5557 + }, + { + "epoch": 0.58, + "learning_rate": 8.855028158888196e-06, + "loss": 1.288, + "step": 5558 + }, + { + "epoch": 0.58, + "learning_rate": 8.851392056944791e-06, + "loss": 1.3407, + "step": 5559 + }, + { + "epoch": 0.58, + "learning_rate": 8.847756108885342e-06, + "loss": 1.3118, + "step": 5560 + }, + { + "epoch": 0.58, + "learning_rate": 8.84412031519696e-06, + "loss": 1.3646, + "step": 5561 + }, + { + "epoch": 0.58, + "learning_rate": 8.840484676366761e-06, + "loss": 1.3896, + "step": 5562 + }, + { + "epoch": 0.58, + "learning_rate": 8.836849192881822e-06, + "loss": 1.3296, + "step": 5563 + }, + { + "epoch": 0.58, + "learning_rate": 8.833213865229208e-06, + "loss": 1.2918, + "step": 5564 + }, + { + "epoch": 0.58, + "learning_rate": 8.82957869389595e-06, + "loss": 1.4811, + "step": 5565 + }, + { + "epoch": 0.58, + "learning_rate": 8.82594367936908e-06, + "loss": 1.3877, + "step": 5566 + }, + { + "epoch": 0.58, + "learning_rate": 8.822308822135588e-06, + "loss": 1.3716, + "step": 5567 + }, + { + "epoch": 0.58, + "learning_rate": 8.818674122682456e-06, + "loss": 1.3204, + "step": 5568 + }, + { + "epoch": 0.58, + "learning_rate": 8.815039581496634e-06, + "loss": 1.326, + "step": 5569 + }, + { + "epoch": 0.58, + "learning_rate": 8.811405199065066e-06, + "loss": 1.3762, + "step": 5570 + }, + { + "epoch": 0.58, + "learning_rate": 8.807770975874658e-06, + "loss": 1.2944, + "step": 5571 + }, + { + "epoch": 0.58, + "learning_rate": 8.804136912412311e-06, + "loss": 1.3057, + "step": 5572 + }, + { + "epoch": 0.58, + "eval_loss": 1.4187605381011963, + "eval_runtime": 77.5157, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 5572 + }, + { + "epoch": 0.58, + "learning_rate": 8.800503009164884e-06, + "loss": 1.4144, + "step": 5573 + }, + { + "epoch": 0.58, + "learning_rate": 8.796869266619238e-06, + "loss": 1.2218, + "step": 5574 + }, + { + "epoch": 0.58, + "learning_rate": 8.793235685262197e-06, + "loss": 1.4445, + "step": 5575 + }, + { + "epoch": 0.58, + "learning_rate": 8.789602265580565e-06, + "loss": 1.3761, + "step": 5576 + }, + { + "epoch": 0.58, + "learning_rate": 8.78596900806113e-06, + "loss": 1.3762, + "step": 5577 + }, + { + "epoch": 0.58, + "learning_rate": 8.782335913190657e-06, + "loss": 1.3506, + "step": 5578 + }, + { + "epoch": 0.59, + "learning_rate": 8.778702981455883e-06, + "loss": 1.4183, + "step": 5579 + }, + { + "epoch": 0.59, + "learning_rate": 8.775070213343528e-06, + "loss": 1.3123, + "step": 5580 + }, + { + "epoch": 0.59, + "learning_rate": 8.771437609340291e-06, + "loss": 1.3168, + "step": 5581 + }, + { + "epoch": 0.59, + "learning_rate": 8.76780516993285e-06, + "loss": 1.3939, + "step": 5582 + }, + { + "epoch": 0.59, + "learning_rate": 8.764172895607856e-06, + "loss": 1.3317, + "step": 5583 + }, + { + "epoch": 0.59, + "learning_rate": 8.760540786851937e-06, + "loss": 1.3094, + "step": 5584 + }, + { + "epoch": 0.59, + "learning_rate": 8.756908844151708e-06, + "loss": 1.2853, + "step": 5585 + }, + { + "epoch": 0.59, + "learning_rate": 8.753277067993752e-06, + "loss": 1.2625, + "step": 5586 + }, + { + "epoch": 0.59, + "learning_rate": 8.74964545886464e-06, + "loss": 1.4246, + "step": 5587 + }, + { + "epoch": 0.59, + "learning_rate": 8.746014017250904e-06, + "loss": 1.2891, + "step": 5588 + }, + { + "epoch": 0.59, + "learning_rate": 8.742382743639071e-06, + "loss": 1.3135, + "step": 5589 + }, + { + "epoch": 0.59, + "learning_rate": 8.738751638515639e-06, + "loss": 1.3021, + "step": 5590 + }, + { + "epoch": 0.59, + "learning_rate": 8.735120702367082e-06, + "loss": 1.3398, + "step": 5591 + }, + { + "epoch": 0.59, + "learning_rate": 8.731489935679845e-06, + "loss": 1.4173, + "step": 5592 + }, + { + "epoch": 0.59, + "learning_rate": 8.727859338940367e-06, + "loss": 1.4129, + "step": 5593 + }, + { + "epoch": 0.59, + "learning_rate": 8.724228912635053e-06, + "loss": 1.3807, + "step": 5594 + }, + { + "epoch": 0.59, + "learning_rate": 8.720598657250284e-06, + "loss": 1.2962, + "step": 5595 + }, + { + "epoch": 0.59, + "learning_rate": 8.716968573272416e-06, + "loss": 1.3784, + "step": 5596 + }, + { + "epoch": 0.59, + "learning_rate": 8.713338661187799e-06, + "loss": 1.3751, + "step": 5597 + }, + { + "epoch": 0.59, + "learning_rate": 8.70970892148274e-06, + "loss": 1.3122, + "step": 5598 + }, + { + "epoch": 0.59, + "learning_rate": 8.70607935464353e-06, + "loss": 1.4174, + "step": 5599 + }, + { + "epoch": 0.59, + "learning_rate": 8.702449961156445e-06, + "loss": 1.3275, + "step": 5600 + }, + { + "epoch": 0.59, + "learning_rate": 8.698820741507723e-06, + "loss": 1.33, + "step": 5601 + }, + { + "epoch": 0.59, + "learning_rate": 8.695191696183589e-06, + "loss": 1.4075, + "step": 5602 + }, + { + "epoch": 0.59, + "learning_rate": 8.69156282567024e-06, + "loss": 1.3778, + "step": 5603 + }, + { + "epoch": 0.59, + "learning_rate": 8.687934130453857e-06, + "loss": 1.3222, + "step": 5604 + }, + { + "epoch": 0.59, + "learning_rate": 8.684305611020587e-06, + "loss": 1.3443, + "step": 5605 + }, + { + "epoch": 0.59, + "learning_rate": 8.680677267856558e-06, + "loss": 1.3167, + "step": 5606 + }, + { + "epoch": 0.59, + "learning_rate": 8.677049101447877e-06, + "loss": 1.3209, + "step": 5607 + }, + { + "epoch": 0.59, + "learning_rate": 8.673421112280624e-06, + "loss": 1.3125, + "step": 5608 + }, + { + "epoch": 0.59, + "learning_rate": 8.669793300840857e-06, + "loss": 1.375, + "step": 5609 + }, + { + "epoch": 0.59, + "learning_rate": 8.666165667614612e-06, + "loss": 1.3627, + "step": 5610 + }, + { + "epoch": 0.59, + "learning_rate": 8.662538213087888e-06, + "loss": 1.3064, + "step": 5611 + }, + { + "epoch": 0.59, + "learning_rate": 8.658910937746685e-06, + "loss": 1.4251, + "step": 5612 + }, + { + "epoch": 0.59, + "learning_rate": 8.655283842076956e-06, + "loss": 1.3011, + "step": 5613 + }, + { + "epoch": 0.59, + "learning_rate": 8.651656926564645e-06, + "loss": 1.3299, + "step": 5614 + }, + { + "epoch": 0.59, + "learning_rate": 8.648030191695653e-06, + "loss": 1.3448, + "step": 5615 + }, + { + "epoch": 0.59, + "learning_rate": 8.644403637955883e-06, + "loss": 1.4048, + "step": 5616 + }, + { + "epoch": 0.59, + "learning_rate": 8.640777265831195e-06, + "loss": 1.336, + "step": 5617 + }, + { + "epoch": 0.59, + "learning_rate": 8.63715107580743e-06, + "loss": 1.4959, + "step": 5618 + }, + { + "epoch": 0.59, + "learning_rate": 8.633525068370397e-06, + "loss": 1.3822, + "step": 5619 + }, + { + "epoch": 0.59, + "learning_rate": 8.6298992440059e-06, + "loss": 1.282, + "step": 5620 + }, + { + "epoch": 0.59, + "learning_rate": 8.626273603199699e-06, + "loss": 1.1873, + "step": 5621 + }, + { + "epoch": 0.59, + "learning_rate": 8.622648146437538e-06, + "loss": 1.3706, + "step": 5622 + }, + { + "epoch": 0.59, + "learning_rate": 8.619022874205138e-06, + "loss": 1.2709, + "step": 5623 + }, + { + "epoch": 0.59, + "learning_rate": 8.615397786988188e-06, + "loss": 1.3608, + "step": 5624 + }, + { + "epoch": 0.59, + "learning_rate": 8.61177288527236e-06, + "loss": 1.3821, + "step": 5625 + }, + { + "epoch": 0.59, + "learning_rate": 8.608148169543292e-06, + "loss": 1.327, + "step": 5626 + }, + { + "epoch": 0.59, + "learning_rate": 8.604523640286611e-06, + "loss": 1.3544, + "step": 5627 + }, + { + "epoch": 0.59, + "learning_rate": 8.600899297987905e-06, + "loss": 1.3269, + "step": 5628 + }, + { + "epoch": 0.59, + "learning_rate": 8.597275143132745e-06, + "loss": 1.3142, + "step": 5629 + }, + { + "epoch": 0.59, + "learning_rate": 8.593651176206671e-06, + "loss": 1.3878, + "step": 5630 + }, + { + "epoch": 0.59, + "learning_rate": 8.59002739769521e-06, + "loss": 1.3386, + "step": 5631 + }, + { + "epoch": 0.59, + "learning_rate": 8.586403808083846e-06, + "loss": 1.3484, + "step": 5632 + }, + { + "epoch": 0.59, + "learning_rate": 8.582780407858052e-06, + "loss": 1.3676, + "step": 5633 + }, + { + "epoch": 0.59, + "learning_rate": 8.579157197503265e-06, + "loss": 1.3753, + "step": 5634 + }, + { + "epoch": 0.59, + "learning_rate": 8.57553417750491e-06, + "loss": 1.4058, + "step": 5635 + }, + { + "epoch": 0.59, + "learning_rate": 8.571911348348375e-06, + "loss": 1.4434, + "step": 5636 + }, + { + "epoch": 0.59, + "learning_rate": 8.568288710519027e-06, + "loss": 1.3398, + "step": 5637 + }, + { + "epoch": 0.59, + "learning_rate": 8.564666264502199e-06, + "loss": 1.3294, + "step": 5638 + }, + { + "epoch": 0.59, + "learning_rate": 8.561044010783216e-06, + "loss": 1.3165, + "step": 5639 + }, + { + "epoch": 0.59, + "learning_rate": 8.557421949847363e-06, + "loss": 1.3437, + "step": 5640 + }, + { + "epoch": 0.59, + "learning_rate": 8.553800082179905e-06, + "loss": 1.3473, + "step": 5641 + }, + { + "epoch": 0.59, + "learning_rate": 8.55017840826607e-06, + "loss": 1.3378, + "step": 5642 + }, + { + "epoch": 0.59, + "learning_rate": 8.546556928591082e-06, + "loss": 1.3357, + "step": 5643 + }, + { + "epoch": 0.59, + "learning_rate": 8.54293564364012e-06, + "loss": 1.3435, + "step": 5644 + }, + { + "epoch": 0.59, + "learning_rate": 8.53931455389834e-06, + "loss": 1.3335, + "step": 5645 + }, + { + "epoch": 0.59, + "learning_rate": 8.535693659850885e-06, + "loss": 1.2917, + "step": 5646 + }, + { + "epoch": 0.59, + "learning_rate": 8.532072961982851e-06, + "loss": 1.3785, + "step": 5647 + }, + { + "epoch": 0.59, + "learning_rate": 8.528452460779327e-06, + "loss": 1.3634, + "step": 5648 + }, + { + "epoch": 0.59, + "learning_rate": 8.524832156725359e-06, + "loss": 1.3541, + "step": 5649 + }, + { + "epoch": 0.59, + "learning_rate": 8.521212050305978e-06, + "loss": 1.335, + "step": 5650 + }, + { + "epoch": 0.59, + "learning_rate": 8.51759214200619e-06, + "loss": 1.3011, + "step": 5651 + }, + { + "epoch": 0.59, + "learning_rate": 8.513972432310965e-06, + "loss": 1.3982, + "step": 5652 + }, + { + "epoch": 0.59, + "learning_rate": 8.510352921705247e-06, + "loss": 1.3217, + "step": 5653 + }, + { + "epoch": 0.59, + "learning_rate": 8.506733610673968e-06, + "loss": 1.3275, + "step": 5654 + }, + { + "epoch": 0.59, + "learning_rate": 8.503114499702015e-06, + "loss": 1.3335, + "step": 5655 + }, + { + "epoch": 0.59, + "learning_rate": 8.499495589274257e-06, + "loss": 1.3567, + "step": 5656 + }, + { + "epoch": 0.59, + "learning_rate": 8.495876879875536e-06, + "loss": 1.348, + "step": 5657 + }, + { + "epoch": 0.59, + "learning_rate": 8.492258371990667e-06, + "loss": 1.3991, + "step": 5658 + }, + { + "epoch": 0.59, + "learning_rate": 8.488640066104435e-06, + "loss": 1.3528, + "step": 5659 + }, + { + "epoch": 0.59, + "learning_rate": 8.485021962701603e-06, + "loss": 1.3275, + "step": 5660 + }, + { + "epoch": 0.59, + "learning_rate": 8.481404062266897e-06, + "loss": 1.3605, + "step": 5661 + }, + { + "epoch": 0.59, + "learning_rate": 8.477786365285032e-06, + "loss": 1.3288, + "step": 5662 + }, + { + "epoch": 0.59, + "learning_rate": 8.474168872240682e-06, + "loss": 1.3274, + "step": 5663 + }, + { + "epoch": 0.59, + "learning_rate": 8.470551583618498e-06, + "loss": 1.273, + "step": 5664 + }, + { + "epoch": 0.59, + "learning_rate": 8.4669344999031e-06, + "loss": 1.3142, + "step": 5665 + }, + { + "epoch": 0.59, + "learning_rate": 8.463317621579091e-06, + "loss": 1.2912, + "step": 5666 + }, + { + "epoch": 0.59, + "learning_rate": 8.459700949131037e-06, + "loss": 1.3162, + "step": 5667 + }, + { + "epoch": 0.59, + "learning_rate": 8.456084483043479e-06, + "loss": 1.3377, + "step": 5668 + }, + { + "epoch": 0.59, + "learning_rate": 8.452468223800931e-06, + "loss": 1.3545, + "step": 5669 + }, + { + "epoch": 0.59, + "learning_rate": 8.448852171887878e-06, + "loss": 1.4052, + "step": 5670 + }, + { + "epoch": 0.59, + "learning_rate": 8.44523632778878e-06, + "loss": 1.3389, + "step": 5671 + }, + { + "epoch": 0.59, + "learning_rate": 8.441620691988063e-06, + "loss": 1.3801, + "step": 5672 + }, + { + "epoch": 0.59, + "learning_rate": 8.438005264970134e-06, + "loss": 1.2978, + "step": 5673 + }, + { + "epoch": 0.6, + "learning_rate": 8.434390047219366e-06, + "loss": 1.437, + "step": 5674 + }, + { + "epoch": 0.6, + "learning_rate": 8.430775039220103e-06, + "loss": 1.3602, + "step": 5675 + }, + { + "epoch": 0.6, + "learning_rate": 8.427160241456664e-06, + "loss": 1.4971, + "step": 5676 + }, + { + "epoch": 0.6, + "learning_rate": 8.423545654413342e-06, + "loss": 1.2765, + "step": 5677 + }, + { + "epoch": 0.6, + "learning_rate": 8.419931278574397e-06, + "loss": 1.4346, + "step": 5678 + }, + { + "epoch": 0.6, + "learning_rate": 8.416317114424059e-06, + "loss": 1.366, + "step": 5679 + }, + { + "epoch": 0.6, + "learning_rate": 8.412703162446536e-06, + "loss": 1.3776, + "step": 5680 + }, + { + "epoch": 0.6, + "learning_rate": 8.409089423126009e-06, + "loss": 1.2516, + "step": 5681 + }, + { + "epoch": 0.6, + "learning_rate": 8.405475896946621e-06, + "loss": 1.4257, + "step": 5682 + }, + { + "epoch": 0.6, + "learning_rate": 8.401862584392492e-06, + "loss": 1.3523, + "step": 5683 + }, + { + "epoch": 0.6, + "learning_rate": 8.398249485947712e-06, + "loss": 1.3791, + "step": 5684 + }, + { + "epoch": 0.6, + "learning_rate": 8.394636602096348e-06, + "loss": 1.3574, + "step": 5685 + }, + { + "epoch": 0.6, + "learning_rate": 8.39102393332243e-06, + "loss": 1.4748, + "step": 5686 + }, + { + "epoch": 0.6, + "learning_rate": 8.387411480109967e-06, + "loss": 1.3693, + "step": 5687 + }, + { + "epoch": 0.6, + "learning_rate": 8.383799242942925e-06, + "loss": 1.3643, + "step": 5688 + }, + { + "epoch": 0.6, + "learning_rate": 8.38018722230526e-06, + "loss": 1.3446, + "step": 5689 + }, + { + "epoch": 0.6, + "learning_rate": 8.37657541868089e-06, + "loss": 1.3552, + "step": 5690 + }, + { + "epoch": 0.6, + "learning_rate": 8.372963832553698e-06, + "loss": 1.3636, + "step": 5691 + }, + { + "epoch": 0.6, + "learning_rate": 8.36935246440755e-06, + "loss": 1.3398, + "step": 5692 + }, + { + "epoch": 0.6, + "learning_rate": 8.365741314726273e-06, + "loss": 1.3336, + "step": 5693 + }, + { + "epoch": 0.6, + "learning_rate": 8.362130383993667e-06, + "loss": 1.3023, + "step": 5694 + }, + { + "epoch": 0.6, + "learning_rate": 8.358519672693506e-06, + "loss": 1.3591, + "step": 5695 + }, + { + "epoch": 0.6, + "learning_rate": 8.354909181309533e-06, + "loss": 1.3113, + "step": 5696 + }, + { + "epoch": 0.6, + "learning_rate": 8.351298910325462e-06, + "loss": 1.3747, + "step": 5697 + }, + { + "epoch": 0.6, + "learning_rate": 8.347688860224976e-06, + "loss": 1.3555, + "step": 5698 + }, + { + "epoch": 0.6, + "learning_rate": 8.344079031491722e-06, + "loss": 1.2947, + "step": 5699 + }, + { + "epoch": 0.6, + "learning_rate": 8.340469424609337e-06, + "loss": 1.4099, + "step": 5700 + }, + { + "epoch": 0.6, + "learning_rate": 8.336860040061404e-06, + "loss": 1.3263, + "step": 5701 + }, + { + "epoch": 0.6, + "learning_rate": 8.333250878331498e-06, + "loss": 1.372, + "step": 5702 + }, + { + "epoch": 0.6, + "learning_rate": 8.329641939903142e-06, + "loss": 1.3523, + "step": 5703 + }, + { + "epoch": 0.6, + "learning_rate": 8.32603322525985e-06, + "loss": 1.3451, + "step": 5704 + }, + { + "epoch": 0.6, + "learning_rate": 8.322424734885098e-06, + "loss": 1.3296, + "step": 5705 + }, + { + "epoch": 0.6, + "learning_rate": 8.318816469262325e-06, + "loss": 1.449, + "step": 5706 + }, + { + "epoch": 0.6, + "learning_rate": 8.315208428874946e-06, + "loss": 1.3611, + "step": 5707 + }, + { + "epoch": 0.6, + "learning_rate": 8.311600614206352e-06, + "loss": 1.3849, + "step": 5708 + }, + { + "epoch": 0.6, + "learning_rate": 8.307993025739893e-06, + "loss": 1.3968, + "step": 5709 + }, + { + "epoch": 0.6, + "learning_rate": 8.304385663958895e-06, + "loss": 1.4428, + "step": 5710 + }, + { + "epoch": 0.6, + "learning_rate": 8.300778529346647e-06, + "loss": 1.3095, + "step": 5711 + }, + { + "epoch": 0.6, + "learning_rate": 8.297171622386418e-06, + "loss": 1.3135, + "step": 5712 + }, + { + "epoch": 0.6, + "learning_rate": 8.293564943561438e-06, + "loss": 1.3069, + "step": 5713 + }, + { + "epoch": 0.6, + "learning_rate": 8.28995849335491e-06, + "loss": 1.3736, + "step": 5714 + }, + { + "epoch": 0.6, + "learning_rate": 8.286352272250007e-06, + "loss": 1.343, + "step": 5715 + }, + { + "epoch": 0.6, + "learning_rate": 8.28274628072987e-06, + "loss": 1.2929, + "step": 5716 + }, + { + "epoch": 0.6, + "learning_rate": 8.279140519277607e-06, + "loss": 1.3356, + "step": 5717 + }, + { + "epoch": 0.6, + "learning_rate": 8.275534988376295e-06, + "loss": 1.2683, + "step": 5718 + }, + { + "epoch": 0.6, + "learning_rate": 8.27192968850899e-06, + "loss": 1.3738, + "step": 5719 + }, + { + "epoch": 0.6, + "learning_rate": 8.268324620158704e-06, + "loss": 1.3369, + "step": 5720 + }, + { + "epoch": 0.6, + "learning_rate": 8.264719783808425e-06, + "loss": 1.3684, + "step": 5721 + }, + { + "epoch": 0.6, + "learning_rate": 8.261115179941108e-06, + "loss": 1.4081, + "step": 5722 + }, + { + "epoch": 0.6, + "learning_rate": 8.257510809039678e-06, + "loss": 1.2504, + "step": 5723 + }, + { + "epoch": 0.6, + "learning_rate": 8.253906671587029e-06, + "loss": 1.417, + "step": 5724 + }, + { + "epoch": 0.6, + "learning_rate": 8.25030276806602e-06, + "loss": 1.3631, + "step": 5725 + }, + { + "epoch": 0.6, + "learning_rate": 8.246699098959483e-06, + "loss": 1.499, + "step": 5726 + }, + { + "epoch": 0.6, + "learning_rate": 8.243095664750217e-06, + "loss": 1.3656, + "step": 5727 + }, + { + "epoch": 0.6, + "learning_rate": 8.239492465920992e-06, + "loss": 1.3563, + "step": 5728 + }, + { + "epoch": 0.6, + "learning_rate": 8.23588950295454e-06, + "loss": 1.3554, + "step": 5729 + }, + { + "epoch": 0.6, + "learning_rate": 8.232286776333566e-06, + "loss": 1.2705, + "step": 5730 + }, + { + "epoch": 0.6, + "learning_rate": 8.228684286540747e-06, + "loss": 1.3792, + "step": 5731 + }, + { + "epoch": 0.6, + "learning_rate": 8.22508203405872e-06, + "loss": 1.3301, + "step": 5732 + }, + { + "epoch": 0.6, + "learning_rate": 8.221480019370095e-06, + "loss": 1.36, + "step": 5733 + }, + { + "epoch": 0.6, + "learning_rate": 8.217878242957448e-06, + "loss": 1.4406, + "step": 5734 + }, + { + "epoch": 0.6, + "learning_rate": 8.214276705303328e-06, + "loss": 1.2886, + "step": 5735 + }, + { + "epoch": 0.6, + "learning_rate": 8.210675406890248e-06, + "loss": 1.3072, + "step": 5736 + }, + { + "epoch": 0.6, + "learning_rate": 8.207074348200686e-06, + "loss": 1.3734, + "step": 5737 + }, + { + "epoch": 0.6, + "learning_rate": 8.203473529717095e-06, + "loss": 1.3893, + "step": 5738 + }, + { + "epoch": 0.6, + "learning_rate": 8.199872951921892e-06, + "loss": 1.3427, + "step": 5739 + }, + { + "epoch": 0.6, + "learning_rate": 8.196272615297459e-06, + "loss": 1.3125, + "step": 5740 + }, + { + "epoch": 0.6, + "learning_rate": 8.19267252032615e-06, + "loss": 1.3079, + "step": 5741 + }, + { + "epoch": 0.6, + "learning_rate": 8.189072667490285e-06, + "loss": 1.2971, + "step": 5742 + }, + { + "epoch": 0.6, + "learning_rate": 8.185473057272154e-06, + "loss": 1.3003, + "step": 5743 + }, + { + "epoch": 0.6, + "learning_rate": 8.18187369015401e-06, + "loss": 1.3002, + "step": 5744 + }, + { + "epoch": 0.6, + "learning_rate": 8.178274566618075e-06, + "loss": 1.2852, + "step": 5745 + }, + { + "epoch": 0.6, + "learning_rate": 8.174675687146542e-06, + "loss": 1.2807, + "step": 5746 + }, + { + "epoch": 0.6, + "learning_rate": 8.171077052221567e-06, + "loss": 1.2983, + "step": 5747 + }, + { + "epoch": 0.6, + "learning_rate": 8.167478662325274e-06, + "loss": 1.3002, + "step": 5748 + }, + { + "epoch": 0.6, + "learning_rate": 8.163880517939753e-06, + "loss": 1.2575, + "step": 5749 + }, + { + "epoch": 0.6, + "learning_rate": 8.160282619547068e-06, + "loss": 1.2627, + "step": 5750 + }, + { + "epoch": 0.6, + "learning_rate": 8.156684967629242e-06, + "loss": 1.2549, + "step": 5751 + }, + { + "epoch": 0.6, + "learning_rate": 8.153087562668265e-06, + "loss": 1.2595, + "step": 5752 + }, + { + "epoch": 0.6, + "learning_rate": 8.1494904051461e-06, + "loss": 1.2788, + "step": 5753 + }, + { + "epoch": 0.6, + "learning_rate": 8.145893495544676e-06, + "loss": 1.3028, + "step": 5754 + }, + { + "epoch": 0.6, + "learning_rate": 8.142296834345883e-06, + "loss": 1.3019, + "step": 5755 + }, + { + "epoch": 0.6, + "learning_rate": 8.138700422031583e-06, + "loss": 1.2998, + "step": 5756 + }, + { + "epoch": 0.6, + "learning_rate": 8.135104259083598e-06, + "loss": 1.3298, + "step": 5757 + }, + { + "epoch": 0.6, + "learning_rate": 8.13150834598373e-06, + "loss": 1.2681, + "step": 5758 + }, + { + "epoch": 0.6, + "learning_rate": 8.127912683213733e-06, + "loss": 1.2987, + "step": 5759 + }, + { + "epoch": 0.6, + "learning_rate": 8.124317271255331e-06, + "loss": 1.3181, + "step": 5760 + }, + { + "epoch": 0.6, + "learning_rate": 8.120722110590224e-06, + "loss": 1.423, + "step": 5761 + }, + { + "epoch": 0.6, + "learning_rate": 8.117127201700067e-06, + "loss": 1.5029, + "step": 5762 + }, + { + "epoch": 0.6, + "learning_rate": 8.113532545066488e-06, + "loss": 1.3016, + "step": 5763 + }, + { + "epoch": 0.6, + "learning_rate": 8.109938141171074e-06, + "loss": 1.3906, + "step": 5764 + }, + { + "epoch": 0.6, + "learning_rate": 8.106343990495387e-06, + "loss": 1.3363, + "step": 5765 + }, + { + "epoch": 0.6, + "learning_rate": 8.10275009352095e-06, + "loss": 1.314, + "step": 5766 + }, + { + "epoch": 0.6, + "learning_rate": 8.09915645072925e-06, + "loss": 1.3484, + "step": 5767 + }, + { + "epoch": 0.6, + "learning_rate": 8.095563062601745e-06, + "loss": 1.3757, + "step": 5768 + }, + { + "epoch": 0.6, + "learning_rate": 8.091969929619859e-06, + "loss": 1.3068, + "step": 5769 + }, + { + "epoch": 0.61, + "learning_rate": 8.088377052264976e-06, + "loss": 1.3486, + "step": 5770 + }, + { + "epoch": 0.61, + "learning_rate": 8.08478443101845e-06, + "loss": 1.244, + "step": 5771 + }, + { + "epoch": 0.61, + "eval_loss": 1.4178493022918701, + "eval_runtime": 77.6086, + "eval_samples_per_second": 1.662, + "eval_steps_per_second": 0.116, + "step": 5771 + }, + { + "epoch": 0.61, + "learning_rate": 8.0811920663616e-06, + "loss": 1.3325, + "step": 5772 + }, + { + "epoch": 0.61, + "learning_rate": 8.077599958775713e-06, + "loss": 1.336, + "step": 5773 + }, + { + "epoch": 0.61, + "learning_rate": 8.074008108742037e-06, + "loss": 1.3167, + "step": 5774 + }, + { + "epoch": 0.61, + "learning_rate": 8.070416516741786e-06, + "loss": 1.3166, + "step": 5775 + }, + { + "epoch": 0.61, + "learning_rate": 8.066825183256141e-06, + "loss": 1.3377, + "step": 5776 + }, + { + "epoch": 0.61, + "learning_rate": 8.063234108766253e-06, + "loss": 1.3704, + "step": 5777 + }, + { + "epoch": 0.61, + "learning_rate": 8.059643293753233e-06, + "loss": 1.3596, + "step": 5778 + }, + { + "epoch": 0.61, + "learning_rate": 8.056052738698153e-06, + "loss": 1.4477, + "step": 5779 + }, + { + "epoch": 0.61, + "learning_rate": 8.052462444082055e-06, + "loss": 1.338, + "step": 5780 + }, + { + "epoch": 0.61, + "learning_rate": 8.048872410385952e-06, + "loss": 1.2714, + "step": 5781 + }, + { + "epoch": 0.61, + "learning_rate": 8.045282638090815e-06, + "loss": 0.9642, + "step": 5782 + }, + { + "epoch": 0.61, + "learning_rate": 8.041693127677576e-06, + "loss": 0.8702, + "step": 5783 + }, + { + "epoch": 0.61, + "learning_rate": 8.038103879627144e-06, + "loss": 0.8986, + "step": 5784 + }, + { + "epoch": 0.61, + "learning_rate": 8.034514894420382e-06, + "loss": 0.804, + "step": 5785 + }, + { + "epoch": 0.61, + "learning_rate": 8.030926172538122e-06, + "loss": 0.7958, + "step": 5786 + }, + { + "epoch": 0.61, + "learning_rate": 8.02733771446116e-06, + "loss": 0.7608, + "step": 5787 + }, + { + "epoch": 0.61, + "learning_rate": 8.023749520670261e-06, + "loss": 0.7792, + "step": 5788 + }, + { + "epoch": 0.61, + "learning_rate": 8.020161591646147e-06, + "loss": 0.7293, + "step": 5789 + }, + { + "epoch": 0.61, + "learning_rate": 8.016573927869511e-06, + "loss": 1.1287, + "step": 5790 + }, + { + "epoch": 0.61, + "learning_rate": 8.012986529821004e-06, + "loss": 1.3344, + "step": 5791 + }, + { + "epoch": 0.61, + "learning_rate": 8.009399397981248e-06, + "loss": 1.4415, + "step": 5792 + }, + { + "epoch": 0.61, + "learning_rate": 8.005812532830826e-06, + "loss": 1.4265, + "step": 5793 + }, + { + "epoch": 0.61, + "learning_rate": 8.002225934850287e-06, + "loss": 1.3429, + "step": 5794 + }, + { + "epoch": 0.61, + "learning_rate": 7.998639604520137e-06, + "loss": 1.3653, + "step": 5795 + }, + { + "epoch": 0.61, + "learning_rate": 7.995053542320861e-06, + "loss": 1.486, + "step": 5796 + }, + { + "epoch": 0.61, + "learning_rate": 7.991467748732894e-06, + "loss": 1.3389, + "step": 5797 + }, + { + "epoch": 0.61, + "learning_rate": 7.98788222423664e-06, + "loss": 1.3206, + "step": 5798 + }, + { + "epoch": 0.61, + "learning_rate": 7.984296969312468e-06, + "loss": 1.3121, + "step": 5799 + }, + { + "epoch": 0.61, + "learning_rate": 7.980711984440712e-06, + "loss": 1.3512, + "step": 5800 + }, + { + "epoch": 0.61, + "learning_rate": 7.977127270101665e-06, + "loss": 1.3291, + "step": 5801 + }, + { + "epoch": 0.61, + "learning_rate": 7.97354282677559e-06, + "loss": 1.3948, + "step": 5802 + }, + { + "epoch": 0.61, + "learning_rate": 7.969958654942704e-06, + "loss": 1.3076, + "step": 5803 + }, + { + "epoch": 0.61, + "learning_rate": 7.966374755083202e-06, + "loss": 1.3838, + "step": 5804 + }, + { + "epoch": 0.61, + "learning_rate": 7.962791127677228e-06, + "loss": 1.4205, + "step": 5805 + }, + { + "epoch": 0.61, + "learning_rate": 7.959207773204899e-06, + "loss": 1.3635, + "step": 5806 + }, + { + "epoch": 0.61, + "learning_rate": 7.955624692146293e-06, + "loss": 1.3299, + "step": 5807 + }, + { + "epoch": 0.61, + "learning_rate": 7.95204188498145e-06, + "loss": 1.4435, + "step": 5808 + }, + { + "epoch": 0.61, + "learning_rate": 7.948459352190372e-06, + "loss": 1.4335, + "step": 5809 + }, + { + "epoch": 0.61, + "learning_rate": 7.944877094253027e-06, + "loss": 1.3391, + "step": 5810 + }, + { + "epoch": 0.61, + "learning_rate": 7.94129511164935e-06, + "loss": 1.2852, + "step": 5811 + }, + { + "epoch": 0.61, + "learning_rate": 7.93771340485923e-06, + "loss": 1.3174, + "step": 5812 + }, + { + "epoch": 0.61, + "learning_rate": 7.934131974362527e-06, + "loss": 1.3415, + "step": 5813 + }, + { + "epoch": 0.61, + "learning_rate": 7.930550820639055e-06, + "loss": 1.2764, + "step": 5814 + }, + { + "epoch": 0.61, + "learning_rate": 7.926969944168603e-06, + "loss": 1.2978, + "step": 5815 + }, + { + "epoch": 0.61, + "learning_rate": 7.923389345430911e-06, + "loss": 1.3046, + "step": 5816 + }, + { + "epoch": 0.61, + "learning_rate": 7.919809024905694e-06, + "loss": 1.3484, + "step": 5817 + }, + { + "epoch": 0.61, + "learning_rate": 7.916228983072614e-06, + "loss": 1.3207, + "step": 5818 + }, + { + "epoch": 0.61, + "learning_rate": 7.912649220411312e-06, + "loss": 1.4289, + "step": 5819 + }, + { + "epoch": 0.61, + "learning_rate": 7.909069737401382e-06, + "loss": 1.4359, + "step": 5820 + }, + { + "epoch": 0.61, + "learning_rate": 7.905490534522384e-06, + "loss": 1.3316, + "step": 5821 + }, + { + "epoch": 0.61, + "learning_rate": 7.901911612253834e-06, + "loss": 1.3112, + "step": 5822 + }, + { + "epoch": 0.61, + "learning_rate": 7.898332971075221e-06, + "loss": 1.3318, + "step": 5823 + }, + { + "epoch": 0.61, + "learning_rate": 7.894754611465992e-06, + "loss": 1.4373, + "step": 5824 + }, + { + "epoch": 0.61, + "learning_rate": 7.891176533905549e-06, + "loss": 1.2938, + "step": 5825 + }, + { + "epoch": 0.61, + "learning_rate": 7.887598738873266e-06, + "loss": 1.3471, + "step": 5826 + }, + { + "epoch": 0.61, + "learning_rate": 7.884021226848478e-06, + "loss": 1.2999, + "step": 5827 + }, + { + "epoch": 0.61, + "learning_rate": 7.880443998310475e-06, + "loss": 1.35, + "step": 5828 + }, + { + "epoch": 0.61, + "learning_rate": 7.876867053738517e-06, + "loss": 1.3307, + "step": 5829 + }, + { + "epoch": 0.61, + "learning_rate": 7.87329039361182e-06, + "loss": 1.393, + "step": 5830 + }, + { + "epoch": 0.61, + "learning_rate": 7.869714018409568e-06, + "loss": 1.2933, + "step": 5831 + }, + { + "epoch": 0.61, + "learning_rate": 7.866137928610903e-06, + "loss": 1.319, + "step": 5832 + }, + { + "epoch": 0.61, + "learning_rate": 7.862562124694925e-06, + "loss": 1.3088, + "step": 5833 + }, + { + "epoch": 0.61, + "learning_rate": 7.858986607140705e-06, + "loss": 1.2941, + "step": 5834 + }, + { + "epoch": 0.61, + "learning_rate": 7.855411376427267e-06, + "loss": 1.3214, + "step": 5835 + }, + { + "epoch": 0.61, + "learning_rate": 7.851836433033602e-06, + "loss": 1.2991, + "step": 5836 + }, + { + "epoch": 0.61, + "learning_rate": 7.848261777438656e-06, + "loss": 1.3117, + "step": 5837 + }, + { + "epoch": 0.61, + "learning_rate": 7.844687410121348e-06, + "loss": 1.2905, + "step": 5838 + }, + { + "epoch": 0.61, + "learning_rate": 7.841113331560548e-06, + "loss": 1.3688, + "step": 5839 + }, + { + "epoch": 0.61, + "learning_rate": 7.837539542235091e-06, + "loss": 1.3987, + "step": 5840 + }, + { + "epoch": 0.61, + "learning_rate": 7.83396604262377e-06, + "loss": 1.2693, + "step": 5841 + }, + { + "epoch": 0.61, + "learning_rate": 7.830392833205348e-06, + "loss": 1.3205, + "step": 5842 + }, + { + "epoch": 0.61, + "learning_rate": 7.826819914458538e-06, + "loss": 1.3325, + "step": 5843 + }, + { + "epoch": 0.61, + "learning_rate": 7.823247286862024e-06, + "loss": 1.3451, + "step": 5844 + }, + { + "epoch": 0.61, + "learning_rate": 7.81967495089444e-06, + "loss": 1.3484, + "step": 5845 + }, + { + "epoch": 0.61, + "learning_rate": 7.816102907034395e-06, + "loss": 1.4949, + "step": 5846 + }, + { + "epoch": 0.61, + "learning_rate": 7.812531155760445e-06, + "loss": 1.4293, + "step": 5847 + }, + { + "epoch": 0.61, + "learning_rate": 7.808959697551113e-06, + "loss": 1.4314, + "step": 5848 + }, + { + "epoch": 0.61, + "learning_rate": 7.805388532884887e-06, + "loss": 1.3188, + "step": 5849 + }, + { + "epoch": 0.61, + "learning_rate": 7.80181766224021e-06, + "loss": 1.4396, + "step": 5850 + }, + { + "epoch": 0.61, + "learning_rate": 7.798247086095484e-06, + "loss": 1.3448, + "step": 5851 + }, + { + "epoch": 0.61, + "learning_rate": 7.794676804929075e-06, + "loss": 1.3591, + "step": 5852 + }, + { + "epoch": 0.61, + "learning_rate": 7.791106819219311e-06, + "loss": 1.3108, + "step": 5853 + }, + { + "epoch": 0.61, + "learning_rate": 7.78753712944448e-06, + "loss": 1.3773, + "step": 5854 + }, + { + "epoch": 0.61, + "learning_rate": 7.783967736082824e-06, + "loss": 1.3313, + "step": 5855 + }, + { + "epoch": 0.61, + "learning_rate": 7.780398639612551e-06, + "loss": 1.3635, + "step": 5856 + }, + { + "epoch": 0.61, + "learning_rate": 7.776829840511833e-06, + "loss": 1.3225, + "step": 5857 + }, + { + "epoch": 0.61, + "learning_rate": 7.773261339258792e-06, + "loss": 1.3142, + "step": 5858 + }, + { + "epoch": 0.61, + "learning_rate": 7.769693136331519e-06, + "loss": 1.3337, + "step": 5859 + }, + { + "epoch": 0.61, + "learning_rate": 7.766125232208057e-06, + "loss": 1.5289, + "step": 5860 + }, + { + "epoch": 0.61, + "learning_rate": 7.762557627366418e-06, + "loss": 1.573, + "step": 5861 + }, + { + "epoch": 0.61, + "learning_rate": 7.758990322284568e-06, + "loss": 1.322, + "step": 5862 + }, + { + "epoch": 0.61, + "learning_rate": 7.755423317440432e-06, + "loss": 1.3281, + "step": 5863 + }, + { + "epoch": 0.61, + "learning_rate": 7.751856613311899e-06, + "loss": 1.3405, + "step": 5864 + }, + { + "epoch": 0.62, + "learning_rate": 7.748290210376817e-06, + "loss": 1.3083, + "step": 5865 + }, + { + "epoch": 0.62, + "learning_rate": 7.744724109112991e-06, + "loss": 1.3587, + "step": 5866 + }, + { + "epoch": 0.62, + "learning_rate": 7.741158309998188e-06, + "loss": 1.3204, + "step": 5867 + }, + { + "epoch": 0.62, + "learning_rate": 7.73759281351013e-06, + "loss": 1.343, + "step": 5868 + }, + { + "epoch": 0.62, + "learning_rate": 7.734027620126507e-06, + "loss": 1.2874, + "step": 5869 + }, + { + "epoch": 0.62, + "learning_rate": 7.73046273032496e-06, + "loss": 1.3306, + "step": 5870 + }, + { + "epoch": 0.62, + "learning_rate": 7.72689814458309e-06, + "loss": 1.3958, + "step": 5871 + }, + { + "epoch": 0.62, + "learning_rate": 7.723333863378465e-06, + "loss": 1.3135, + "step": 5872 + }, + { + "epoch": 0.62, + "learning_rate": 7.719769887188608e-06, + "loss": 1.3241, + "step": 5873 + }, + { + "epoch": 0.62, + "learning_rate": 7.716206216490995e-06, + "loss": 1.3487, + "step": 5874 + }, + { + "epoch": 0.62, + "learning_rate": 7.712642851763067e-06, + "loss": 1.0263, + "step": 5875 + }, + { + "epoch": 0.62, + "learning_rate": 7.709079793482228e-06, + "loss": 1.4238, + "step": 5876 + }, + { + "epoch": 0.62, + "learning_rate": 7.705517042125833e-06, + "loss": 1.3284, + "step": 5877 + }, + { + "epoch": 0.62, + "learning_rate": 7.701954598171199e-06, + "loss": 1.2965, + "step": 5878 + }, + { + "epoch": 0.62, + "learning_rate": 7.698392462095601e-06, + "loss": 1.3578, + "step": 5879 + }, + { + "epoch": 0.62, + "learning_rate": 7.694830634376278e-06, + "loss": 1.3711, + "step": 5880 + }, + { + "epoch": 0.62, + "learning_rate": 7.69126911549042e-06, + "loss": 1.3274, + "step": 5881 + }, + { + "epoch": 0.62, + "learning_rate": 7.687707905915181e-06, + "loss": 1.4208, + "step": 5882 + }, + { + "epoch": 0.62, + "learning_rate": 7.684147006127665e-06, + "loss": 1.3478, + "step": 5883 + }, + { + "epoch": 0.62, + "learning_rate": 7.68058641660495e-06, + "loss": 1.2997, + "step": 5884 + }, + { + "epoch": 0.62, + "learning_rate": 7.67702613782406e-06, + "loss": 1.2981, + "step": 5885 + }, + { + "epoch": 0.62, + "learning_rate": 7.67346617026198e-06, + "loss": 1.3834, + "step": 5886 + }, + { + "epoch": 0.62, + "learning_rate": 7.669906514395654e-06, + "loss": 1.3585, + "step": 5887 + }, + { + "epoch": 0.62, + "learning_rate": 7.666347170701986e-06, + "loss": 1.3282, + "step": 5888 + }, + { + "epoch": 0.62, + "learning_rate": 7.662788139657838e-06, + "loss": 1.3397, + "step": 5889 + }, + { + "epoch": 0.62, + "learning_rate": 7.659229421740024e-06, + "loss": 1.3367, + "step": 5890 + }, + { + "epoch": 0.62, + "learning_rate": 7.655671017425322e-06, + "loss": 1.3497, + "step": 5891 + }, + { + "epoch": 0.62, + "learning_rate": 7.65211292719047e-06, + "loss": 1.3661, + "step": 5892 + }, + { + "epoch": 0.62, + "learning_rate": 7.64855515151216e-06, + "loss": 1.2793, + "step": 5893 + }, + { + "epoch": 0.62, + "learning_rate": 7.644997690867037e-06, + "loss": 1.3288, + "step": 5894 + }, + { + "epoch": 0.62, + "learning_rate": 7.641440545731717e-06, + "loss": 1.3877, + "step": 5895 + }, + { + "epoch": 0.62, + "learning_rate": 7.637883716582764e-06, + "loss": 1.4467, + "step": 5896 + }, + { + "epoch": 0.62, + "learning_rate": 7.634327203896698e-06, + "loss": 1.304, + "step": 5897 + }, + { + "epoch": 0.62, + "learning_rate": 7.630771008150002e-06, + "loss": 1.374, + "step": 5898 + }, + { + "epoch": 0.62, + "learning_rate": 7.627215129819118e-06, + "loss": 1.3893, + "step": 5899 + }, + { + "epoch": 0.62, + "learning_rate": 7.623659569380439e-06, + "loss": 1.325, + "step": 5900 + }, + { + "epoch": 0.62, + "learning_rate": 7.620104327310319e-06, + "loss": 1.2495, + "step": 5901 + }, + { + "epoch": 0.62, + "learning_rate": 7.616549404085068e-06, + "loss": 1.4034, + "step": 5902 + }, + { + "epoch": 0.62, + "learning_rate": 7.61299480018096e-06, + "loss": 1.2758, + "step": 5903 + }, + { + "epoch": 0.62, + "learning_rate": 7.609440516074215e-06, + "loss": 1.4203, + "step": 5904 + }, + { + "epoch": 0.62, + "learning_rate": 7.605886552241017e-06, + "loss": 1.3162, + "step": 5905 + }, + { + "epoch": 0.62, + "learning_rate": 7.602332909157505e-06, + "loss": 1.3368, + "step": 5906 + }, + { + "epoch": 0.62, + "learning_rate": 7.598779587299778e-06, + "loss": 1.314, + "step": 5907 + }, + { + "epoch": 0.62, + "learning_rate": 7.59522658714389e-06, + "loss": 1.3332, + "step": 5908 + }, + { + "epoch": 0.62, + "learning_rate": 7.5916739091658505e-06, + "loss": 1.3513, + "step": 5909 + }, + { + "epoch": 0.62, + "learning_rate": 7.5881215538416255e-06, + "loss": 1.3767, + "step": 5910 + }, + { + "epoch": 0.62, + "learning_rate": 7.5845695216471426e-06, + "loss": 1.3651, + "step": 5911 + }, + { + "epoch": 0.62, + "learning_rate": 7.581017813058283e-06, + "loss": 1.2676, + "step": 5912 + }, + { + "epoch": 0.62, + "learning_rate": 7.57746642855088e-06, + "loss": 1.3509, + "step": 5913 + }, + { + "epoch": 0.62, + "learning_rate": 7.5739153686007305e-06, + "loss": 1.2854, + "step": 5914 + }, + { + "epoch": 0.62, + "learning_rate": 7.570364633683586e-06, + "loss": 1.4041, + "step": 5915 + }, + { + "epoch": 0.62, + "learning_rate": 7.5668142242751545e-06, + "loss": 1.3218, + "step": 5916 + }, + { + "epoch": 0.62, + "learning_rate": 7.563264140851095e-06, + "loss": 1.398, + "step": 5917 + }, + { + "epoch": 0.62, + "learning_rate": 7.559714383887033e-06, + "loss": 1.3495, + "step": 5918 + }, + { + "epoch": 0.62, + "learning_rate": 7.556164953858543e-06, + "loss": 1.365, + "step": 5919 + }, + { + "epoch": 0.62, + "learning_rate": 7.552615851241157e-06, + "loss": 1.4611, + "step": 5920 + }, + { + "epoch": 0.62, + "learning_rate": 7.549067076510361e-06, + "loss": 1.4031, + "step": 5921 + }, + { + "epoch": 0.62, + "learning_rate": 7.545518630141605e-06, + "loss": 1.2745, + "step": 5922 + }, + { + "epoch": 0.62, + "learning_rate": 7.541970512610286e-06, + "loss": 1.3435, + "step": 5923 + }, + { + "epoch": 0.62, + "learning_rate": 7.538422724391761e-06, + "loss": 1.3433, + "step": 5924 + }, + { + "epoch": 0.62, + "learning_rate": 7.534875265961341e-06, + "loss": 1.3605, + "step": 5925 + }, + { + "epoch": 0.62, + "learning_rate": 7.5313281377942985e-06, + "loss": 1.3896, + "step": 5926 + }, + { + "epoch": 0.62, + "learning_rate": 7.527781340365854e-06, + "loss": 1.3922, + "step": 5927 + }, + { + "epoch": 0.62, + "learning_rate": 7.524234874151189e-06, + "loss": 1.3305, + "step": 5928 + }, + { + "epoch": 0.62, + "learning_rate": 7.520688739625436e-06, + "loss": 1.3117, + "step": 5929 + }, + { + "epoch": 0.62, + "learning_rate": 7.51714293726369e-06, + "loss": 1.3581, + "step": 5930 + }, + { + "epoch": 0.62, + "learning_rate": 7.5135974675409955e-06, + "loss": 1.3973, + "step": 5931 + }, + { + "epoch": 0.62, + "learning_rate": 7.510052330932354e-06, + "loss": 1.3499, + "step": 5932 + }, + { + "epoch": 0.62, + "learning_rate": 7.506507527912721e-06, + "loss": 1.3068, + "step": 5933 + }, + { + "epoch": 0.62, + "learning_rate": 7.502963058957014e-06, + "loss": 1.3689, + "step": 5934 + }, + { + "epoch": 0.62, + "learning_rate": 7.499418924540096e-06, + "loss": 1.3356, + "step": 5935 + }, + { + "epoch": 0.62, + "learning_rate": 7.495875125136793e-06, + "loss": 1.2593, + "step": 5936 + }, + { + "epoch": 0.62, + "learning_rate": 7.492331661221881e-06, + "loss": 1.272, + "step": 5937 + }, + { + "epoch": 0.62, + "learning_rate": 7.488788533270093e-06, + "loss": 1.3552, + "step": 5938 + }, + { + "epoch": 0.62, + "learning_rate": 7.485245741756121e-06, + "loss": 1.3425, + "step": 5939 + }, + { + "epoch": 0.62, + "learning_rate": 7.481703287154602e-06, + "loss": 1.3694, + "step": 5940 + }, + { + "epoch": 0.62, + "learning_rate": 7.478161169940139e-06, + "loss": 1.3281, + "step": 5941 + }, + { + "epoch": 0.62, + "learning_rate": 7.4746193905872825e-06, + "loss": 1.3109, + "step": 5942 + }, + { + "epoch": 0.62, + "learning_rate": 7.47107794957054e-06, + "loss": 1.5121, + "step": 5943 + }, + { + "epoch": 0.62, + "learning_rate": 7.467536847364372e-06, + "loss": 1.4472, + "step": 5944 + }, + { + "epoch": 0.62, + "learning_rate": 7.463996084443198e-06, + "loss": 1.4615, + "step": 5945 + }, + { + "epoch": 0.62, + "learning_rate": 7.460455661281389e-06, + "loss": 1.3764, + "step": 5946 + }, + { + "epoch": 0.62, + "learning_rate": 7.45691557835327e-06, + "loss": 1.3091, + "step": 5947 + }, + { + "epoch": 0.62, + "learning_rate": 7.4533758361331185e-06, + "loss": 1.1841, + "step": 5948 + }, + { + "epoch": 0.62, + "learning_rate": 7.449836435095175e-06, + "loss": 1.3345, + "step": 5949 + }, + { + "epoch": 0.62, + "learning_rate": 7.446297375713622e-06, + "loss": 1.3573, + "step": 5950 + }, + { + "epoch": 0.62, + "learning_rate": 7.442758658462608e-06, + "loss": 1.3161, + "step": 5951 + }, + { + "epoch": 0.62, + "learning_rate": 7.4392202838162245e-06, + "loss": 1.3089, + "step": 5952 + }, + { + "epoch": 0.62, + "learning_rate": 7.435682252248528e-06, + "loss": 1.3069, + "step": 5953 + }, + { + "epoch": 0.62, + "learning_rate": 7.4321445642335234e-06, + "loss": 1.2969, + "step": 5954 + }, + { + "epoch": 0.62, + "learning_rate": 7.428607220245165e-06, + "loss": 1.4706, + "step": 5955 + }, + { + "epoch": 0.62, + "learning_rate": 7.42507022075737e-06, + "loss": 1.3028, + "step": 5956 + }, + { + "epoch": 0.62, + "learning_rate": 7.421533566244006e-06, + "loss": 1.2786, + "step": 5957 + }, + { + "epoch": 0.62, + "learning_rate": 7.417997257178893e-06, + "loss": 1.3534, + "step": 5958 + }, + { + "epoch": 0.62, + "learning_rate": 7.414461294035804e-06, + "loss": 1.2829, + "step": 5959 + }, + { + "epoch": 0.62, + "learning_rate": 7.410925677288467e-06, + "loss": 1.3626, + "step": 5960 + }, + { + "epoch": 0.63, + "learning_rate": 7.407390407410566e-06, + "loss": 1.4531, + "step": 5961 + }, + { + "epoch": 0.63, + "learning_rate": 7.4038554848757375e-06, + "loss": 1.3549, + "step": 5962 + }, + { + "epoch": 0.63, + "learning_rate": 7.400320910157563e-06, + "loss": 1.3407, + "step": 5963 + }, + { + "epoch": 0.63, + "learning_rate": 7.396786683729595e-06, + "loss": 1.2736, + "step": 5964 + }, + { + "epoch": 0.63, + "learning_rate": 7.393252806065323e-06, + "loss": 1.3377, + "step": 5965 + }, + { + "epoch": 0.63, + "learning_rate": 7.389719277638196e-06, + "loss": 1.3479, + "step": 5966 + }, + { + "epoch": 0.63, + "learning_rate": 7.3861860989216175e-06, + "loss": 1.3605, + "step": 5967 + }, + { + "epoch": 0.63, + "learning_rate": 7.382653270388942e-06, + "loss": 1.3175, + "step": 5968 + }, + { + "epoch": 0.63, + "learning_rate": 7.379120792513477e-06, + "loss": 1.3072, + "step": 5969 + }, + { + "epoch": 0.63, + "learning_rate": 7.375588665768485e-06, + "loss": 1.3224, + "step": 5970 + }, + { + "epoch": 0.63, + "eval_loss": 1.4110088348388672, + "eval_runtime": 77.5326, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 5970 + }, + { + "epoch": 0.63, + "learning_rate": 7.37205689062718e-06, + "loss": 1.3491, + "step": 5971 + }, + { + "epoch": 0.63, + "learning_rate": 7.368525467562728e-06, + "loss": 1.3289, + "step": 5972 + }, + { + "epoch": 0.63, + "learning_rate": 7.364994397048251e-06, + "loss": 1.3362, + "step": 5973 + }, + { + "epoch": 0.63, + "learning_rate": 7.36146367955682e-06, + "loss": 1.3754, + "step": 5974 + }, + { + "epoch": 0.63, + "learning_rate": 7.3579333155614585e-06, + "loss": 1.3159, + "step": 5975 + }, + { + "epoch": 0.63, + "learning_rate": 7.354403305535149e-06, + "loss": 1.4366, + "step": 5976 + }, + { + "epoch": 0.63, + "learning_rate": 7.350873649950822e-06, + "loss": 1.3243, + "step": 5977 + }, + { + "epoch": 0.63, + "learning_rate": 7.347344349281358e-06, + "loss": 1.2911, + "step": 5978 + }, + { + "epoch": 0.63, + "learning_rate": 7.34381540399959e-06, + "loss": 1.338, + "step": 5979 + }, + { + "epoch": 0.63, + "learning_rate": 7.340286814578312e-06, + "loss": 1.3241, + "step": 5980 + }, + { + "epoch": 0.63, + "learning_rate": 7.336758581490263e-06, + "loss": 1.3427, + "step": 5981 + }, + { + "epoch": 0.63, + "learning_rate": 7.333230705208134e-06, + "loss": 1.3328, + "step": 5982 + }, + { + "epoch": 0.63, + "learning_rate": 7.3297031862045676e-06, + "loss": 1.2857, + "step": 5983 + }, + { + "epoch": 0.63, + "learning_rate": 7.3261760249521655e-06, + "loss": 1.9065, + "step": 5984 + }, + { + "epoch": 0.63, + "learning_rate": 7.322649221923473e-06, + "loss": 1.3797, + "step": 5985 + }, + { + "epoch": 0.63, + "learning_rate": 7.3191227775909925e-06, + "loss": 1.2343, + "step": 5986 + }, + { + "epoch": 0.63, + "learning_rate": 7.315596692427178e-06, + "loss": 1.3479, + "step": 5987 + }, + { + "epoch": 0.63, + "learning_rate": 7.312070966904432e-06, + "loss": 1.3226, + "step": 5988 + }, + { + "epoch": 0.63, + "learning_rate": 7.308545601495114e-06, + "loss": 1.3329, + "step": 5989 + }, + { + "epoch": 0.63, + "learning_rate": 7.305020596671528e-06, + "loss": 1.3285, + "step": 5990 + }, + { + "epoch": 0.63, + "learning_rate": 7.301495952905939e-06, + "loss": 1.3635, + "step": 5991 + }, + { + "epoch": 0.63, + "learning_rate": 7.297971670670556e-06, + "loss": 1.3343, + "step": 5992 + }, + { + "epoch": 0.63, + "learning_rate": 7.294447750437543e-06, + "loss": 1.3943, + "step": 5993 + }, + { + "epoch": 0.63, + "learning_rate": 7.290924192679014e-06, + "loss": 1.4601, + "step": 5994 + }, + { + "epoch": 0.63, + "learning_rate": 7.287400997867036e-06, + "loss": 1.3813, + "step": 5995 + }, + { + "epoch": 0.63, + "learning_rate": 7.2838781664736266e-06, + "loss": 1.3505, + "step": 5996 + }, + { + "epoch": 0.63, + "learning_rate": 7.2803556989707555e-06, + "loss": 1.3062, + "step": 5997 + }, + { + "epoch": 0.63, + "learning_rate": 7.276833595830338e-06, + "loss": 1.4504, + "step": 5998 + }, + { + "epoch": 0.63, + "learning_rate": 7.273311857524252e-06, + "loss": 1.4935, + "step": 5999 + }, + { + "epoch": 0.63, + "learning_rate": 7.269790484524317e-06, + "loss": 1.296, + "step": 6000 + }, + { + "epoch": 0.63, + "learning_rate": 7.266269477302308e-06, + "loss": 1.3469, + "step": 6001 + }, + { + "epoch": 0.63, + "learning_rate": 7.262748836329944e-06, + "loss": 1.3586, + "step": 6002 + }, + { + "epoch": 0.63, + "learning_rate": 7.259228562078908e-06, + "loss": 1.3643, + "step": 6003 + }, + { + "epoch": 0.63, + "learning_rate": 7.255708655020821e-06, + "loss": 1.3096, + "step": 6004 + }, + { + "epoch": 0.63, + "learning_rate": 7.252189115627264e-06, + "loss": 1.3163, + "step": 6005 + }, + { + "epoch": 0.63, + "learning_rate": 7.2486699443697595e-06, + "loss": 1.3526, + "step": 6006 + }, + { + "epoch": 0.63, + "learning_rate": 7.245151141719793e-06, + "loss": 1.401, + "step": 6007 + }, + { + "epoch": 0.63, + "learning_rate": 7.241632708148788e-06, + "loss": 1.2651, + "step": 6008 + }, + { + "epoch": 0.63, + "learning_rate": 7.238114644128124e-06, + "loss": 1.348, + "step": 6009 + }, + { + "epoch": 0.63, + "learning_rate": 7.234596950129137e-06, + "loss": 1.6934, + "step": 6010 + }, + { + "epoch": 0.63, + "learning_rate": 7.231079626623103e-06, + "loss": 1.3382, + "step": 6011 + }, + { + "epoch": 0.63, + "learning_rate": 7.227562674081254e-06, + "loss": 1.2925, + "step": 6012 + }, + { + "epoch": 0.63, + "learning_rate": 7.22404609297477e-06, + "loss": 1.3365, + "step": 6013 + }, + { + "epoch": 0.63, + "learning_rate": 7.220529883774785e-06, + "loss": 1.3169, + "step": 6014 + }, + { + "epoch": 0.63, + "learning_rate": 7.217014046952379e-06, + "loss": 1.319, + "step": 6015 + }, + { + "epoch": 0.63, + "learning_rate": 7.2134985829785846e-06, + "loss": 1.4049, + "step": 6016 + }, + { + "epoch": 0.63, + "learning_rate": 7.209983492324382e-06, + "loss": 1.2947, + "step": 6017 + }, + { + "epoch": 0.63, + "learning_rate": 7.206468775460704e-06, + "loss": 1.2854, + "step": 6018 + }, + { + "epoch": 0.63, + "learning_rate": 7.202954432858436e-06, + "loss": 1.3381, + "step": 6019 + }, + { + "epoch": 0.63, + "learning_rate": 7.199440464988403e-06, + "loss": 1.3912, + "step": 6020 + }, + { + "epoch": 0.63, + "learning_rate": 7.195926872321391e-06, + "loss": 1.384, + "step": 6021 + }, + { + "epoch": 0.63, + "learning_rate": 7.192413655328129e-06, + "loss": 1.2909, + "step": 6022 + }, + { + "epoch": 0.63, + "learning_rate": 7.188900814479299e-06, + "loss": 1.2951, + "step": 6023 + }, + { + "epoch": 0.63, + "learning_rate": 7.185388350245532e-06, + "loss": 1.2655, + "step": 6024 + }, + { + "epoch": 0.63, + "learning_rate": 7.1818762630974035e-06, + "loss": 1.3288, + "step": 6025 + }, + { + "epoch": 0.63, + "learning_rate": 7.17836455350545e-06, + "loss": 1.2873, + "step": 6026 + }, + { + "epoch": 0.63, + "learning_rate": 7.174853221940146e-06, + "loss": 1.3027, + "step": 6027 + }, + { + "epoch": 0.63, + "learning_rate": 7.17134226887192e-06, + "loss": 1.3273, + "step": 6028 + }, + { + "epoch": 0.63, + "learning_rate": 7.167831694771149e-06, + "loss": 1.3096, + "step": 6029 + }, + { + "epoch": 0.63, + "learning_rate": 7.1643215001081625e-06, + "loss": 1.2904, + "step": 6030 + }, + { + "epoch": 0.63, + "learning_rate": 7.160811685353234e-06, + "loss": 1.2977, + "step": 6031 + }, + { + "epoch": 0.63, + "learning_rate": 7.157302250976588e-06, + "loss": 1.3281, + "step": 6032 + }, + { + "epoch": 0.63, + "learning_rate": 7.1537931974483996e-06, + "loss": 1.3831, + "step": 6033 + }, + { + "epoch": 0.63, + "learning_rate": 7.150284525238794e-06, + "loss": 1.3173, + "step": 6034 + }, + { + "epoch": 0.63, + "learning_rate": 7.146776234817841e-06, + "loss": 1.4148, + "step": 6035 + }, + { + "epoch": 0.63, + "learning_rate": 7.143268326655557e-06, + "loss": 1.3381, + "step": 6036 + }, + { + "epoch": 0.63, + "learning_rate": 7.13976080122192e-06, + "loss": 1.3221, + "step": 6037 + }, + { + "epoch": 0.63, + "learning_rate": 7.136253658986843e-06, + "loss": 1.4373, + "step": 6038 + }, + { + "epoch": 0.63, + "learning_rate": 7.132746900420195e-06, + "loss": 1.3758, + "step": 6039 + }, + { + "epoch": 0.63, + "learning_rate": 7.129240525991788e-06, + "loss": 1.3964, + "step": 6040 + }, + { + "epoch": 0.63, + "learning_rate": 7.125734536171391e-06, + "loss": 1.3136, + "step": 6041 + }, + { + "epoch": 0.63, + "learning_rate": 7.122228931428715e-06, + "loss": 1.2195, + "step": 6042 + }, + { + "epoch": 0.63, + "learning_rate": 7.11872371223342e-06, + "loss": 1.3842, + "step": 6043 + }, + { + "epoch": 0.63, + "learning_rate": 7.115218879055113e-06, + "loss": 1.3369, + "step": 6044 + }, + { + "epoch": 0.63, + "learning_rate": 7.111714432363356e-06, + "loss": 1.2704, + "step": 6045 + }, + { + "epoch": 0.63, + "learning_rate": 7.108210372627653e-06, + "loss": 1.307, + "step": 6046 + }, + { + "epoch": 0.63, + "learning_rate": 7.104706700317459e-06, + "loss": 1.3024, + "step": 6047 + }, + { + "epoch": 0.63, + "learning_rate": 7.1012034159021715e-06, + "loss": 1.4157, + "step": 6048 + }, + { + "epoch": 0.63, + "learning_rate": 7.0977005198511475e-06, + "loss": 1.2314, + "step": 6049 + }, + { + "epoch": 0.63, + "learning_rate": 7.09419801263368e-06, + "loss": 1.4304, + "step": 6050 + }, + { + "epoch": 0.63, + "learning_rate": 7.090695894719019e-06, + "loss": 1.3085, + "step": 6051 + }, + { + "epoch": 0.63, + "learning_rate": 7.0871941665763525e-06, + "loss": 1.367, + "step": 6052 + }, + { + "epoch": 0.63, + "learning_rate": 7.083692828674827e-06, + "loss": 1.2913, + "step": 6053 + }, + { + "epoch": 0.63, + "learning_rate": 7.080191881483531e-06, + "loss": 1.3751, + "step": 6054 + }, + { + "epoch": 0.63, + "learning_rate": 7.0766913254714985e-06, + "loss": 1.3178, + "step": 6055 + }, + { + "epoch": 0.64, + "learning_rate": 7.07319116110772e-06, + "loss": 1.3182, + "step": 6056 + }, + { + "epoch": 0.64, + "learning_rate": 7.069691388861122e-06, + "loss": 1.373, + "step": 6057 + }, + { + "epoch": 0.64, + "learning_rate": 7.066192009200588e-06, + "loss": 1.3235, + "step": 6058 + }, + { + "epoch": 0.64, + "learning_rate": 7.0626930225949395e-06, + "loss": 1.3765, + "step": 6059 + }, + { + "epoch": 0.64, + "learning_rate": 7.0591944295129565e-06, + "loss": 1.4408, + "step": 6060 + }, + { + "epoch": 0.64, + "learning_rate": 7.055696230423359e-06, + "loss": 1.3271, + "step": 6061 + }, + { + "epoch": 0.64, + "learning_rate": 7.052198425794814e-06, + "loss": 1.2194, + "step": 6062 + }, + { + "epoch": 0.64, + "learning_rate": 7.048701016095938e-06, + "loss": 1.3707, + "step": 6063 + }, + { + "epoch": 0.64, + "learning_rate": 7.045204001795296e-06, + "loss": 1.3878, + "step": 6064 + }, + { + "epoch": 0.64, + "learning_rate": 7.041707383361396e-06, + "loss": 1.3674, + "step": 6065 + }, + { + "epoch": 0.64, + "learning_rate": 7.038211161262697e-06, + "loss": 1.4525, + "step": 6066 + }, + { + "epoch": 0.64, + "learning_rate": 7.034715335967599e-06, + "loss": 1.3801, + "step": 6067 + }, + { + "epoch": 0.64, + "learning_rate": 7.031219907944458e-06, + "loss": 1.4855, + "step": 6068 + }, + { + "epoch": 0.64, + "learning_rate": 7.027724877661568e-06, + "loss": 1.3659, + "step": 6069 + }, + { + "epoch": 0.64, + "learning_rate": 7.024230245587176e-06, + "loss": 1.3649, + "step": 6070 + }, + { + "epoch": 0.64, + "learning_rate": 7.020736012189467e-06, + "loss": 1.2629, + "step": 6071 + }, + { + "epoch": 0.64, + "learning_rate": 7.017242177936586e-06, + "loss": 1.2474, + "step": 6072 + }, + { + "epoch": 0.64, + "learning_rate": 7.013748743296614e-06, + "loss": 1.45, + "step": 6073 + }, + { + "epoch": 0.64, + "learning_rate": 7.010255708737581e-06, + "loss": 1.3624, + "step": 6074 + }, + { + "epoch": 0.64, + "learning_rate": 7.006763074727461e-06, + "loss": 0.9335, + "step": 6075 + }, + { + "epoch": 0.64, + "learning_rate": 7.0032708417341835e-06, + "loss": 0.6376, + "step": 6076 + }, + { + "epoch": 0.64, + "learning_rate": 6.999779010225613e-06, + "loss": 0.7882, + "step": 6077 + }, + { + "epoch": 0.64, + "learning_rate": 6.996287580669567e-06, + "loss": 1.3001, + "step": 6078 + }, + { + "epoch": 0.64, + "learning_rate": 6.9927965535338085e-06, + "loss": 1.323, + "step": 6079 + }, + { + "epoch": 0.64, + "learning_rate": 6.989305929286043e-06, + "loss": 1.3478, + "step": 6080 + }, + { + "epoch": 0.64, + "learning_rate": 6.985815708393928e-06, + "loss": 1.319, + "step": 6081 + }, + { + "epoch": 0.64, + "learning_rate": 6.9823258913250566e-06, + "loss": 1.3458, + "step": 6082 + }, + { + "epoch": 0.64, + "learning_rate": 6.978836478546985e-06, + "loss": 1.2481, + "step": 6083 + }, + { + "epoch": 0.64, + "learning_rate": 6.975347470527195e-06, + "loss": 1.4051, + "step": 6084 + }, + { + "epoch": 0.64, + "learning_rate": 6.97185886773313e-06, + "loss": 1.3705, + "step": 6085 + }, + { + "epoch": 0.64, + "learning_rate": 6.9683706706321676e-06, + "loss": 1.3415, + "step": 6086 + }, + { + "epoch": 0.64, + "learning_rate": 6.964882879691643e-06, + "loss": 1.3462, + "step": 6087 + }, + { + "epoch": 0.64, + "learning_rate": 6.961395495378829e-06, + "loss": 1.2974, + "step": 6088 + }, + { + "epoch": 0.64, + "learning_rate": 6.957908518160943e-06, + "loss": 1.3353, + "step": 6089 + }, + { + "epoch": 0.64, + "learning_rate": 6.95442194850515e-06, + "loss": 1.3073, + "step": 6090 + }, + { + "epoch": 0.64, + "learning_rate": 6.9509357868785636e-06, + "loss": 1.352, + "step": 6091 + }, + { + "epoch": 0.64, + "learning_rate": 6.9474500337482396e-06, + "loss": 1.2771, + "step": 6092 + }, + { + "epoch": 0.64, + "learning_rate": 6.943964689581177e-06, + "loss": 1.2925, + "step": 6093 + }, + { + "epoch": 0.64, + "learning_rate": 6.940479754844322e-06, + "loss": 1.2967, + "step": 6094 + }, + { + "epoch": 0.64, + "learning_rate": 6.93699523000457e-06, + "loss": 1.5839, + "step": 6095 + }, + { + "epoch": 0.64, + "learning_rate": 6.933511115528757e-06, + "loss": 1.3051, + "step": 6096 + }, + { + "epoch": 0.64, + "learning_rate": 6.930027411883664e-06, + "loss": 1.5344, + "step": 6097 + }, + { + "epoch": 0.64, + "learning_rate": 6.926544119536014e-06, + "loss": 1.3938, + "step": 6098 + }, + { + "epoch": 0.64, + "learning_rate": 6.923061238952484e-06, + "loss": 1.3504, + "step": 6099 + }, + { + "epoch": 0.64, + "learning_rate": 6.919578770599689e-06, + "loss": 1.3618, + "step": 6100 + }, + { + "epoch": 0.64, + "learning_rate": 6.916096714944187e-06, + "loss": 1.3811, + "step": 6101 + }, + { + "epoch": 0.64, + "learning_rate": 6.912615072452491e-06, + "loss": 1.2673, + "step": 6102 + }, + { + "epoch": 0.64, + "learning_rate": 6.909133843591046e-06, + "loss": 1.3661, + "step": 6103 + }, + { + "epoch": 0.64, + "learning_rate": 6.905653028826249e-06, + "loss": 1.3811, + "step": 6104 + }, + { + "epoch": 0.64, + "learning_rate": 6.902172628624437e-06, + "loss": 1.3399, + "step": 6105 + }, + { + "epoch": 0.64, + "learning_rate": 6.8986926434519e-06, + "loss": 1.281, + "step": 6106 + }, + { + "epoch": 0.64, + "learning_rate": 6.895213073774862e-06, + "loss": 1.3053, + "step": 6107 + }, + { + "epoch": 0.64, + "learning_rate": 6.891733920059498e-06, + "loss": 1.4573, + "step": 6108 + }, + { + "epoch": 0.64, + "learning_rate": 6.8882551827719215e-06, + "loss": 1.355, + "step": 6109 + }, + { + "epoch": 0.64, + "learning_rate": 6.8847768623782e-06, + "loss": 1.3304, + "step": 6110 + }, + { + "epoch": 0.64, + "learning_rate": 6.881298959344335e-06, + "loss": 1.4039, + "step": 6111 + }, + { + "epoch": 0.64, + "learning_rate": 6.877821474136277e-06, + "loss": 1.381, + "step": 6112 + }, + { + "epoch": 0.64, + "learning_rate": 6.874344407219917e-06, + "loss": 1.3503, + "step": 6113 + }, + { + "epoch": 0.64, + "learning_rate": 6.870867759061099e-06, + "loss": 1.2679, + "step": 6114 + }, + { + "epoch": 0.64, + "learning_rate": 6.8673915301256e-06, + "loss": 1.3286, + "step": 6115 + }, + { + "epoch": 0.64, + "learning_rate": 6.863915720879146e-06, + "loss": 1.3528, + "step": 6116 + }, + { + "epoch": 0.64, + "learning_rate": 6.8604403317874055e-06, + "loss": 1.3502, + "step": 6117 + }, + { + "epoch": 0.64, + "learning_rate": 6.856965363315993e-06, + "loss": 1.3507, + "step": 6118 + }, + { + "epoch": 0.64, + "learning_rate": 6.853490815930464e-06, + "loss": 1.2153, + "step": 6119 + }, + { + "epoch": 0.64, + "learning_rate": 6.850016690096319e-06, + "loss": 1.2435, + "step": 6120 + }, + { + "epoch": 0.64, + "learning_rate": 6.846542986279e-06, + "loss": 1.3418, + "step": 6121 + }, + { + "epoch": 0.64, + "learning_rate": 6.843069704943896e-06, + "loss": 1.371, + "step": 6122 + }, + { + "epoch": 0.64, + "learning_rate": 6.8395968465563375e-06, + "loss": 1.1737, + "step": 6123 + }, + { + "epoch": 0.64, + "learning_rate": 6.836124411581598e-06, + "loss": 1.3402, + "step": 6124 + }, + { + "epoch": 0.64, + "learning_rate": 6.8326524004848924e-06, + "loss": 1.3482, + "step": 6125 + }, + { + "epoch": 0.64, + "learning_rate": 6.8291808137313845e-06, + "loss": 1.4585, + "step": 6126 + }, + { + "epoch": 0.64, + "learning_rate": 6.825709651786176e-06, + "loss": 1.2848, + "step": 6127 + }, + { + "epoch": 0.64, + "learning_rate": 6.822238915114312e-06, + "loss": 1.2932, + "step": 6128 + }, + { + "epoch": 0.64, + "learning_rate": 6.818768604180785e-06, + "loss": 1.3124, + "step": 6129 + }, + { + "epoch": 0.64, + "learning_rate": 6.815298719450525e-06, + "loss": 1.2843, + "step": 6130 + }, + { + "epoch": 0.64, + "learning_rate": 6.811829261388409e-06, + "loss": 1.3024, + "step": 6131 + }, + { + "epoch": 0.64, + "learning_rate": 6.808360230459252e-06, + "loss": 1.3612, + "step": 6132 + }, + { + "epoch": 0.64, + "learning_rate": 6.804891627127821e-06, + "loss": 1.3005, + "step": 6133 + }, + { + "epoch": 0.64, + "learning_rate": 6.8014234518588154e-06, + "loss": 1.2614, + "step": 6134 + }, + { + "epoch": 0.64, + "learning_rate": 6.7979557051168835e-06, + "loss": 1.3717, + "step": 6135 + }, + { + "epoch": 0.64, + "learning_rate": 6.794488387366609e-06, + "loss": 1.3873, + "step": 6136 + }, + { + "epoch": 0.64, + "learning_rate": 6.791021499072532e-06, + "loss": 1.2955, + "step": 6137 + }, + { + "epoch": 0.64, + "learning_rate": 6.787555040699121e-06, + "loss": 1.4217, + "step": 6138 + }, + { + "epoch": 0.64, + "learning_rate": 6.784089012710793e-06, + "loss": 1.3805, + "step": 6139 + }, + { + "epoch": 0.64, + "learning_rate": 6.7806234155719055e-06, + "loss": 1.3982, + "step": 6140 + }, + { + "epoch": 0.64, + "learning_rate": 6.7771582497467635e-06, + "loss": 1.4, + "step": 6141 + }, + { + "epoch": 0.64, + "learning_rate": 6.773693515699607e-06, + "loss": 1.439, + "step": 6142 + }, + { + "epoch": 0.64, + "learning_rate": 6.7702292138946235e-06, + "loss": 1.3672, + "step": 6143 + }, + { + "epoch": 0.64, + "learning_rate": 6.7667653447959355e-06, + "loss": 1.2901, + "step": 6144 + }, + { + "epoch": 0.64, + "learning_rate": 6.763301908867619e-06, + "loss": 1.2873, + "step": 6145 + }, + { + "epoch": 0.64, + "learning_rate": 6.759838906573684e-06, + "loss": 1.3582, + "step": 6146 + }, + { + "epoch": 0.64, + "learning_rate": 6.756376338378077e-06, + "loss": 1.3562, + "step": 6147 + }, + { + "epoch": 0.64, + "learning_rate": 6.7529142047447025e-06, + "loss": 1.3091, + "step": 6148 + }, + { + "epoch": 0.64, + "learning_rate": 6.749452506137393e-06, + "loss": 1.4269, + "step": 6149 + }, + { + "epoch": 0.64, + "learning_rate": 6.745991243019927e-06, + "loss": 1.4184, + "step": 6150 + }, + { + "epoch": 0.65, + "learning_rate": 6.7425304158560235e-06, + "loss": 1.4201, + "step": 6151 + }, + { + "epoch": 0.65, + "learning_rate": 6.739070025109349e-06, + "loss": 1.3222, + "step": 6152 + }, + { + "epoch": 0.65, + "learning_rate": 6.7356100712435035e-06, + "loss": 1.3262, + "step": 6153 + }, + { + "epoch": 0.65, + "learning_rate": 6.732150554722034e-06, + "loss": 1.4408, + "step": 6154 + }, + { + "epoch": 0.65, + "learning_rate": 6.728691476008422e-06, + "loss": 1.3441, + "step": 6155 + }, + { + "epoch": 0.65, + "learning_rate": 6.725232835566102e-06, + "loss": 1.3316, + "step": 6156 + }, + { + "epoch": 0.65, + "learning_rate": 6.721774633858438e-06, + "loss": 1.3326, + "step": 6157 + }, + { + "epoch": 0.65, + "learning_rate": 6.7183168713487425e-06, + "loss": 1.3105, + "step": 6158 + }, + { + "epoch": 0.65, + "learning_rate": 6.714859548500265e-06, + "loss": 1.3144, + "step": 6159 + }, + { + "epoch": 0.65, + "learning_rate": 6.7114026657762e-06, + "loss": 1.3472, + "step": 6160 + }, + { + "epoch": 0.65, + "learning_rate": 6.707946223639681e-06, + "loss": 1.3811, + "step": 6161 + }, + { + "epoch": 0.65, + "learning_rate": 6.704490222553781e-06, + "loss": 1.2783, + "step": 6162 + }, + { + "epoch": 0.65, + "learning_rate": 6.701034662981513e-06, + "loss": 1.273, + "step": 6163 + }, + { + "epoch": 0.65, + "learning_rate": 6.697579545385839e-06, + "loss": 1.3522, + "step": 6164 + }, + { + "epoch": 0.65, + "learning_rate": 6.6941248702296524e-06, + "loss": 1.3861, + "step": 6165 + }, + { + "epoch": 0.65, + "learning_rate": 6.6906706379757915e-06, + "loss": 1.3098, + "step": 6166 + }, + { + "epoch": 0.65, + "learning_rate": 6.687216849087032e-06, + "loss": 1.3734, + "step": 6167 + }, + { + "epoch": 0.65, + "learning_rate": 6.6837635040261e-06, + "loss": 1.2289, + "step": 6168 + }, + { + "epoch": 0.65, + "learning_rate": 6.680310603255648e-06, + "loss": 1.3238, + "step": 6169 + }, + { + "epoch": 0.65, + "eval_loss": 1.40826416015625, + "eval_runtime": 77.483, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 6169 + }, + { + "epoch": 0.65, + "learning_rate": 6.676858147238277e-06, + "loss": 1.4317, + "step": 6170 + }, + { + "epoch": 0.65, + "learning_rate": 6.673406136436531e-06, + "loss": 1.3363, + "step": 6171 + }, + { + "epoch": 0.65, + "learning_rate": 6.669954571312889e-06, + "loss": 1.3377, + "step": 6172 + }, + { + "epoch": 0.65, + "learning_rate": 6.666503452329771e-06, + "loss": 1.3382, + "step": 6173 + }, + { + "epoch": 0.65, + "learning_rate": 6.663052779949538e-06, + "loss": 1.3028, + "step": 6174 + }, + { + "epoch": 0.65, + "learning_rate": 6.659602554634494e-06, + "loss": 1.3098, + "step": 6175 + }, + { + "epoch": 0.65, + "learning_rate": 6.656152776846879e-06, + "loss": 1.328, + "step": 6176 + }, + { + "epoch": 0.65, + "learning_rate": 6.652703447048874e-06, + "loss": 1.3014, + "step": 6177 + }, + { + "epoch": 0.65, + "learning_rate": 6.6492545657026e-06, + "loss": 1.2522, + "step": 6178 + }, + { + "epoch": 0.65, + "learning_rate": 6.645806133270121e-06, + "loss": 1.6113, + "step": 6179 + }, + { + "epoch": 0.65, + "learning_rate": 6.642358150213437e-06, + "loss": 1.3431, + "step": 6180 + }, + { + "epoch": 0.65, + "learning_rate": 6.638910616994489e-06, + "loss": 1.2725, + "step": 6181 + }, + { + "epoch": 0.65, + "learning_rate": 6.635463534075156e-06, + "loss": 1.3022, + "step": 6182 + }, + { + "epoch": 0.65, + "learning_rate": 6.632016901917262e-06, + "loss": 1.3496, + "step": 6183 + }, + { + "epoch": 0.65, + "learning_rate": 6.628570720982567e-06, + "loss": 1.2871, + "step": 6184 + }, + { + "epoch": 0.65, + "learning_rate": 6.625124991732767e-06, + "loss": 1.4449, + "step": 6185 + }, + { + "epoch": 0.65, + "learning_rate": 6.621679714629504e-06, + "loss": 1.4395, + "step": 6186 + }, + { + "epoch": 0.65, + "learning_rate": 6.618234890134356e-06, + "loss": 1.4088, + "step": 6187 + }, + { + "epoch": 0.65, + "learning_rate": 6.614790518708843e-06, + "loss": 1.371, + "step": 6188 + }, + { + "epoch": 0.65, + "learning_rate": 6.611346600814419e-06, + "loss": 1.28, + "step": 6189 + }, + { + "epoch": 0.65, + "learning_rate": 6.607903136912482e-06, + "loss": 1.3502, + "step": 6190 + }, + { + "epoch": 0.65, + "learning_rate": 6.604460127464367e-06, + "loss": 1.3398, + "step": 6191 + }, + { + "epoch": 0.65, + "learning_rate": 6.60101757293135e-06, + "loss": 1.4762, + "step": 6192 + }, + { + "epoch": 0.65, + "learning_rate": 6.5975754737746426e-06, + "loss": 1.2981, + "step": 6193 + }, + { + "epoch": 0.65, + "learning_rate": 6.594133830455401e-06, + "loss": 1.3728, + "step": 6194 + }, + { + "epoch": 0.65, + "learning_rate": 6.590692643434715e-06, + "loss": 1.3551, + "step": 6195 + }, + { + "epoch": 0.65, + "learning_rate": 6.5872519131736155e-06, + "loss": 1.3031, + "step": 6196 + }, + { + "epoch": 0.65, + "learning_rate": 6.583811640133071e-06, + "loss": 1.3231, + "step": 6197 + }, + { + "epoch": 0.65, + "learning_rate": 6.5803718247739924e-06, + "loss": 1.2752, + "step": 6198 + }, + { + "epoch": 0.65, + "learning_rate": 6.576932467557223e-06, + "loss": 1.3482, + "step": 6199 + }, + { + "epoch": 0.65, + "learning_rate": 6.573493568943552e-06, + "loss": 1.2612, + "step": 6200 + }, + { + "epoch": 0.65, + "learning_rate": 6.570055129393698e-06, + "loss": 1.6302, + "step": 6201 + }, + { + "epoch": 0.65, + "learning_rate": 6.566617149368331e-06, + "loss": 1.303, + "step": 6202 + }, + { + "epoch": 0.65, + "learning_rate": 6.563179629328047e-06, + "loss": 1.3405, + "step": 6203 + }, + { + "epoch": 0.65, + "learning_rate": 6.559742569733385e-06, + "loss": 1.2816, + "step": 6204 + }, + { + "epoch": 0.65, + "learning_rate": 6.556305971044824e-06, + "loss": 1.3834, + "step": 6205 + }, + { + "epoch": 0.65, + "learning_rate": 6.552869833722781e-06, + "loss": 1.3414, + "step": 6206 + }, + { + "epoch": 0.65, + "learning_rate": 6.5494341582276096e-06, + "loss": 1.3278, + "step": 6207 + }, + { + "epoch": 0.65, + "learning_rate": 6.5459989450196024e-06, + "loss": 1.3577, + "step": 6208 + }, + { + "epoch": 0.65, + "learning_rate": 6.542564194558986e-06, + "loss": 1.3104, + "step": 6209 + }, + { + "epoch": 0.65, + "learning_rate": 6.539129907305933e-06, + "loss": 1.3068, + "step": 6210 + }, + { + "epoch": 0.65, + "learning_rate": 6.53569608372055e-06, + "loss": 1.3769, + "step": 6211 + }, + { + "epoch": 0.65, + "learning_rate": 6.5322627242628775e-06, + "loss": 1.2855, + "step": 6212 + }, + { + "epoch": 0.65, + "learning_rate": 6.528829829392898e-06, + "loss": 1.4129, + "step": 6213 + }, + { + "epoch": 0.65, + "learning_rate": 6.525397399570534e-06, + "loss": 1.3631, + "step": 6214 + }, + { + "epoch": 0.65, + "learning_rate": 6.5219654352556435e-06, + "loss": 1.295, + "step": 6215 + }, + { + "epoch": 0.65, + "learning_rate": 6.518533936908016e-06, + "loss": 1.439, + "step": 6216 + }, + { + "epoch": 0.65, + "learning_rate": 6.515102904987389e-06, + "loss": 1.3148, + "step": 6217 + }, + { + "epoch": 0.65, + "learning_rate": 6.511672339953432e-06, + "loss": 1.3898, + "step": 6218 + }, + { + "epoch": 0.65, + "learning_rate": 6.508242242265752e-06, + "loss": 1.3222, + "step": 6219 + }, + { + "epoch": 0.65, + "learning_rate": 6.504812612383891e-06, + "loss": 1.324, + "step": 6220 + }, + { + "epoch": 0.65, + "learning_rate": 6.501383450767336e-06, + "loss": 1.951, + "step": 6221 + }, + { + "epoch": 0.65, + "learning_rate": 6.4979547578755055e-06, + "loss": 1.2878, + "step": 6222 + }, + { + "epoch": 0.65, + "learning_rate": 6.494526534167754e-06, + "loss": 1.3553, + "step": 6223 + }, + { + "epoch": 0.65, + "learning_rate": 6.491098780103375e-06, + "loss": 1.3898, + "step": 6224 + }, + { + "epoch": 0.65, + "learning_rate": 6.487671496141606e-06, + "loss": 1.4333, + "step": 6225 + }, + { + "epoch": 0.65, + "learning_rate": 6.484244682741606e-06, + "loss": 1.4461, + "step": 6226 + }, + { + "epoch": 0.65, + "learning_rate": 6.480818340362487e-06, + "loss": 1.3461, + "step": 6227 + }, + { + "epoch": 0.65, + "learning_rate": 6.4773924694632835e-06, + "loss": 1.3442, + "step": 6228 + }, + { + "epoch": 0.65, + "learning_rate": 6.473967070502982e-06, + "loss": 1.2692, + "step": 6229 + }, + { + "epoch": 0.65, + "learning_rate": 6.470542143940495e-06, + "loss": 1.446, + "step": 6230 + }, + { + "epoch": 0.65, + "learning_rate": 6.467117690234675e-06, + "loss": 1.3597, + "step": 6231 + }, + { + "epoch": 0.65, + "learning_rate": 6.463693709844305e-06, + "loss": 1.3226, + "step": 6232 + }, + { + "epoch": 0.65, + "learning_rate": 6.46027020322812e-06, + "loss": 1.2702, + "step": 6233 + }, + { + "epoch": 0.65, + "learning_rate": 6.456847170844775e-06, + "loss": 1.2554, + "step": 6234 + }, + { + "epoch": 0.65, + "learning_rate": 6.453424613152872e-06, + "loss": 1.2896, + "step": 6235 + }, + { + "epoch": 0.65, + "learning_rate": 6.450002530610943e-06, + "loss": 1.3148, + "step": 6236 + }, + { + "epoch": 0.65, + "learning_rate": 6.4465809236774635e-06, + "loss": 1.3589, + "step": 6237 + }, + { + "epoch": 0.65, + "learning_rate": 6.443159792810838e-06, + "loss": 1.2938, + "step": 6238 + }, + { + "epoch": 0.65, + "learning_rate": 6.439739138469406e-06, + "loss": 1.366, + "step": 6239 + }, + { + "epoch": 0.65, + "learning_rate": 6.436318961111455e-06, + "loss": 1.4772, + "step": 6240 + }, + { + "epoch": 0.65, + "learning_rate": 6.4328992611951975e-06, + "loss": 1.3131, + "step": 6241 + }, + { + "epoch": 0.65, + "learning_rate": 6.429480039178786e-06, + "loss": 1.2382, + "step": 6242 + }, + { + "epoch": 0.65, + "learning_rate": 6.426061295520304e-06, + "loss": 1.3394, + "step": 6243 + }, + { + "epoch": 0.65, + "learning_rate": 6.422643030677782e-06, + "loss": 1.321, + "step": 6244 + }, + { + "epoch": 0.65, + "learning_rate": 6.419225245109175e-06, + "loss": 1.3478, + "step": 6245 + }, + { + "epoch": 0.65, + "learning_rate": 6.415807939272383e-06, + "loss": 1.3249, + "step": 6246 + }, + { + "epoch": 0.66, + "learning_rate": 6.412391113625231e-06, + "loss": 1.3602, + "step": 6247 + }, + { + "epoch": 0.66, + "learning_rate": 6.408974768625491e-06, + "loss": 1.2799, + "step": 6248 + }, + { + "epoch": 0.66, + "learning_rate": 6.405558904730863e-06, + "loss": 1.3911, + "step": 6249 + }, + { + "epoch": 0.66, + "learning_rate": 6.402143522398987e-06, + "loss": 1.3185, + "step": 6250 + }, + { + "epoch": 0.66, + "learning_rate": 6.398728622087431e-06, + "loss": 1.3198, + "step": 6251 + }, + { + "epoch": 0.66, + "learning_rate": 6.395314204253711e-06, + "loss": 1.361, + "step": 6252 + }, + { + "epoch": 0.66, + "learning_rate": 6.391900269355269e-06, + "loss": 1.3285, + "step": 6253 + }, + { + "epoch": 0.66, + "learning_rate": 6.388486817849484e-06, + "loss": 1.3097, + "step": 6254 + }, + { + "epoch": 0.66, + "learning_rate": 6.385073850193667e-06, + "loss": 1.3057, + "step": 6255 + }, + { + "epoch": 0.66, + "learning_rate": 6.381661366845075e-06, + "loss": 1.4733, + "step": 6256 + }, + { + "epoch": 0.66, + "learning_rate": 6.378249368260889e-06, + "loss": 1.3571, + "step": 6257 + }, + { + "epoch": 0.66, + "learning_rate": 6.374837854898228e-06, + "loss": 1.3278, + "step": 6258 + }, + { + "epoch": 0.66, + "learning_rate": 6.37142682721415e-06, + "loss": 1.3035, + "step": 6259 + }, + { + "epoch": 0.66, + "learning_rate": 6.368016285665645e-06, + "loss": 1.397, + "step": 6260 + }, + { + "epoch": 0.66, + "learning_rate": 6.3646062307096365e-06, + "loss": 1.353, + "step": 6261 + }, + { + "epoch": 0.66, + "learning_rate": 6.361196662802982e-06, + "loss": 1.3534, + "step": 6262 + }, + { + "epoch": 0.66, + "learning_rate": 6.357787582402482e-06, + "loss": 1.3132, + "step": 6263 + }, + { + "epoch": 0.66, + "learning_rate": 6.3543789899648624e-06, + "loss": 1.3551, + "step": 6264 + }, + { + "epoch": 0.66, + "learning_rate": 6.3509708859467855e-06, + "loss": 1.4205, + "step": 6265 + }, + { + "epoch": 0.66, + "learning_rate": 6.347563270804851e-06, + "loss": 1.341, + "step": 6266 + }, + { + "epoch": 0.66, + "learning_rate": 6.344156144995593e-06, + "loss": 1.5188, + "step": 6267 + }, + { + "epoch": 0.66, + "learning_rate": 6.340749508975477e-06, + "loss": 1.4404, + "step": 6268 + }, + { + "epoch": 0.66, + "learning_rate": 6.337343363200905e-06, + "loss": 1.3026, + "step": 6269 + }, + { + "epoch": 0.66, + "learning_rate": 6.3339377081282124e-06, + "loss": 1.3315, + "step": 6270 + }, + { + "epoch": 0.66, + "learning_rate": 6.3305325442136735e-06, + "loss": 1.2503, + "step": 6271 + }, + { + "epoch": 0.66, + "learning_rate": 6.3271278719134885e-06, + "loss": 1.1776, + "step": 6272 + }, + { + "epoch": 0.66, + "learning_rate": 6.323723691683798e-06, + "loss": 1.3033, + "step": 6273 + }, + { + "epoch": 0.66, + "learning_rate": 6.320320003980671e-06, + "loss": 1.3838, + "step": 6274 + }, + { + "epoch": 0.66, + "learning_rate": 6.3169168092601195e-06, + "loss": 1.3691, + "step": 6275 + }, + { + "epoch": 0.66, + "learning_rate": 6.313514107978083e-06, + "loss": 1.3665, + "step": 6276 + }, + { + "epoch": 0.66, + "learning_rate": 6.310111900590432e-06, + "loss": 1.358, + "step": 6277 + }, + { + "epoch": 0.66, + "learning_rate": 6.306710187552978e-06, + "loss": 1.1708, + "step": 6278 + }, + { + "epoch": 0.66, + "learning_rate": 6.303308969321464e-06, + "loss": 1.331, + "step": 6279 + }, + { + "epoch": 0.66, + "learning_rate": 6.299908246351566e-06, + "loss": 1.3914, + "step": 6280 + }, + { + "epoch": 0.66, + "learning_rate": 6.2965080190988896e-06, + "loss": 1.3183, + "step": 6281 + }, + { + "epoch": 0.66, + "learning_rate": 6.293108288018981e-06, + "loss": 1.2969, + "step": 6282 + }, + { + "epoch": 0.66, + "learning_rate": 6.289709053567318e-06, + "loss": 1.2892, + "step": 6283 + }, + { + "epoch": 0.66, + "learning_rate": 6.2863103161993085e-06, + "loss": 1.3517, + "step": 6284 + }, + { + "epoch": 0.66, + "learning_rate": 6.282912076370295e-06, + "loss": 1.3329, + "step": 6285 + }, + { + "epoch": 0.66, + "learning_rate": 6.279514334535557e-06, + "loss": 1.3396, + "step": 6286 + }, + { + "epoch": 0.66, + "learning_rate": 6.276117091150304e-06, + "loss": 1.3878, + "step": 6287 + }, + { + "epoch": 0.66, + "learning_rate": 6.272720346669677e-06, + "loss": 1.2608, + "step": 6288 + }, + { + "epoch": 0.66, + "learning_rate": 6.269324101548754e-06, + "loss": 1.3605, + "step": 6289 + }, + { + "epoch": 0.66, + "learning_rate": 6.265928356242546e-06, + "loss": 1.2682, + "step": 6290 + }, + { + "epoch": 0.66, + "learning_rate": 6.262533111205995e-06, + "loss": 1.3426, + "step": 6291 + }, + { + "epoch": 0.66, + "learning_rate": 6.259138366893975e-06, + "loss": 1.2987, + "step": 6292 + }, + { + "epoch": 0.66, + "learning_rate": 6.255744123761295e-06, + "loss": 1.3521, + "step": 6293 + }, + { + "epoch": 0.66, + "learning_rate": 6.252350382262697e-06, + "loss": 1.2816, + "step": 6294 + }, + { + "epoch": 0.66, + "learning_rate": 6.248957142852856e-06, + "loss": 1.3884, + "step": 6295 + }, + { + "epoch": 0.66, + "learning_rate": 6.2455644059863795e-06, + "loss": 1.3545, + "step": 6296 + }, + { + "epoch": 0.66, + "learning_rate": 6.2421721721178015e-06, + "loss": 1.3636, + "step": 6297 + }, + { + "epoch": 0.66, + "learning_rate": 6.238780441701601e-06, + "loss": 1.3584, + "step": 6298 + }, + { + "epoch": 0.66, + "learning_rate": 6.235389215192179e-06, + "loss": 1.3459, + "step": 6299 + }, + { + "epoch": 0.66, + "learning_rate": 6.231998493043875e-06, + "loss": 1.4654, + "step": 6300 + }, + { + "epoch": 0.66, + "learning_rate": 6.228608275710954e-06, + "loss": 1.3628, + "step": 6301 + }, + { + "epoch": 0.66, + "learning_rate": 6.225218563647623e-06, + "loss": 1.3278, + "step": 6302 + }, + { + "epoch": 0.66, + "learning_rate": 6.221829357308016e-06, + "loss": 1.395, + "step": 6303 + }, + { + "epoch": 0.66, + "learning_rate": 6.218440657146196e-06, + "loss": 1.3481, + "step": 6304 + }, + { + "epoch": 0.66, + "learning_rate": 6.215052463616165e-06, + "loss": 1.309, + "step": 6305 + }, + { + "epoch": 0.66, + "learning_rate": 6.211664777171853e-06, + "loss": 1.275, + "step": 6306 + }, + { + "epoch": 0.66, + "learning_rate": 6.208277598267123e-06, + "loss": 1.4885, + "step": 6307 + }, + { + "epoch": 0.66, + "learning_rate": 6.2048909273557686e-06, + "loss": 1.3334, + "step": 6308 + }, + { + "epoch": 0.66, + "learning_rate": 6.201504764891518e-06, + "loss": 1.3399, + "step": 6309 + }, + { + "epoch": 0.66, + "learning_rate": 6.198119111328032e-06, + "loss": 1.3163, + "step": 6310 + }, + { + "epoch": 0.66, + "learning_rate": 6.1947339671188966e-06, + "loss": 1.2746, + "step": 6311 + }, + { + "epoch": 0.66, + "learning_rate": 6.191349332717635e-06, + "loss": 1.2984, + "step": 6312 + }, + { + "epoch": 0.66, + "learning_rate": 6.187965208577705e-06, + "loss": 1.2295, + "step": 6313 + }, + { + "epoch": 0.66, + "learning_rate": 6.18458159515249e-06, + "loss": 1.3424, + "step": 6314 + }, + { + "epoch": 0.66, + "learning_rate": 6.181198492895308e-06, + "loss": 1.3108, + "step": 6315 + }, + { + "epoch": 0.66, + "learning_rate": 6.1778159022594045e-06, + "loss": 1.4895, + "step": 6316 + }, + { + "epoch": 0.66, + "learning_rate": 6.174433823697964e-06, + "loss": 1.3247, + "step": 6317 + }, + { + "epoch": 0.66, + "learning_rate": 6.171052257664097e-06, + "loss": 1.3659, + "step": 6318 + }, + { + "epoch": 0.66, + "learning_rate": 6.167671204610844e-06, + "loss": 1.3889, + "step": 6319 + }, + { + "epoch": 0.66, + "learning_rate": 6.1642906649911815e-06, + "loss": 1.3946, + "step": 6320 + }, + { + "epoch": 0.66, + "learning_rate": 6.1609106392580155e-06, + "loss": 1.3685, + "step": 6321 + }, + { + "epoch": 0.66, + "learning_rate": 6.157531127864181e-06, + "loss": 1.2584, + "step": 6322 + }, + { + "epoch": 0.66, + "learning_rate": 6.154152131262448e-06, + "loss": 1.3263, + "step": 6323 + }, + { + "epoch": 0.66, + "learning_rate": 6.15077364990551e-06, + "loss": 1.3336, + "step": 6324 + }, + { + "epoch": 0.66, + "learning_rate": 6.147395684246003e-06, + "loss": 1.2513, + "step": 6325 + }, + { + "epoch": 0.66, + "learning_rate": 6.144018234736484e-06, + "loss": 1.3715, + "step": 6326 + }, + { + "epoch": 0.66, + "learning_rate": 6.140641301829444e-06, + "loss": 1.3464, + "step": 6327 + }, + { + "epoch": 0.66, + "learning_rate": 6.1372648859773075e-06, + "loss": 1.4374, + "step": 6328 + }, + { + "epoch": 0.66, + "learning_rate": 6.1338889876324285e-06, + "loss": 1.3903, + "step": 6329 + }, + { + "epoch": 0.66, + "learning_rate": 6.130513607247087e-06, + "loss": 1.3715, + "step": 6330 + }, + { + "epoch": 0.66, + "learning_rate": 6.127138745273497e-06, + "loss": 1.3196, + "step": 6331 + }, + { + "epoch": 0.66, + "learning_rate": 6.123764402163808e-06, + "loss": 1.3013, + "step": 6332 + }, + { + "epoch": 0.66, + "learning_rate": 6.120390578370093e-06, + "loss": 1.2751, + "step": 6333 + }, + { + "epoch": 0.66, + "learning_rate": 6.117017274344356e-06, + "loss": 1.2258, + "step": 6334 + }, + { + "epoch": 0.66, + "learning_rate": 6.113644490538533e-06, + "loss": 1.2982, + "step": 6335 + }, + { + "epoch": 0.66, + "learning_rate": 6.110272227404492e-06, + "loss": 1.3124, + "step": 6336 + }, + { + "epoch": 0.66, + "learning_rate": 6.10690048539403e-06, + "loss": 1.2451, + "step": 6337 + }, + { + "epoch": 0.66, + "learning_rate": 6.103529264958874e-06, + "loss": 1.3896, + "step": 6338 + }, + { + "epoch": 0.66, + "learning_rate": 6.100158566550677e-06, + "loss": 1.46, + "step": 6339 + }, + { + "epoch": 0.66, + "learning_rate": 6.096788390621031e-06, + "loss": 1.2965, + "step": 6340 + }, + { + "epoch": 0.66, + "learning_rate": 6.093418737621452e-06, + "loss": 1.2969, + "step": 6341 + }, + { + "epoch": 0.67, + "learning_rate": 6.0900496080033836e-06, + "loss": 1.3988, + "step": 6342 + }, + { + "epoch": 0.67, + "learning_rate": 6.086681002218204e-06, + "loss": 1.351, + "step": 6343 + }, + { + "epoch": 0.67, + "learning_rate": 6.083312920717224e-06, + "loss": 1.3447, + "step": 6344 + }, + { + "epoch": 0.67, + "learning_rate": 6.079945363951674e-06, + "loss": 1.3361, + "step": 6345 + }, + { + "epoch": 0.67, + "learning_rate": 6.076578332372724e-06, + "loss": 1.3688, + "step": 6346 + }, + { + "epoch": 0.67, + "learning_rate": 6.073211826431467e-06, + "loss": 1.2831, + "step": 6347 + }, + { + "epoch": 0.67, + "learning_rate": 6.069845846578931e-06, + "loss": 1.369, + "step": 6348 + }, + { + "epoch": 0.67, + "learning_rate": 6.06648039326607e-06, + "loss": 1.3247, + "step": 6349 + }, + { + "epoch": 0.67, + "learning_rate": 6.063115466943765e-06, + "loss": 1.288, + "step": 6350 + }, + { + "epoch": 0.67, + "learning_rate": 6.0597510680628345e-06, + "loss": 1.0733, + "step": 6351 + }, + { + "epoch": 0.67, + "learning_rate": 6.056387197074021e-06, + "loss": 1.3386, + "step": 6352 + }, + { + "epoch": 0.67, + "learning_rate": 6.053023854427993e-06, + "loss": 1.3682, + "step": 6353 + }, + { + "epoch": 0.67, + "learning_rate": 6.049661040575353e-06, + "loss": 1.5669, + "step": 6354 + }, + { + "epoch": 0.67, + "learning_rate": 6.0462987559666355e-06, + "loss": 1.3432, + "step": 6355 + }, + { + "epoch": 0.67, + "learning_rate": 6.042937001052298e-06, + "loss": 1.327, + "step": 6356 + }, + { + "epoch": 0.67, + "learning_rate": 6.039575776282728e-06, + "loss": 1.3101, + "step": 6357 + }, + { + "epoch": 0.67, + "learning_rate": 6.0362150821082425e-06, + "loss": 1.3239, + "step": 6358 + }, + { + "epoch": 0.67, + "learning_rate": 6.032854918979092e-06, + "loss": 1.435, + "step": 6359 + }, + { + "epoch": 0.67, + "learning_rate": 6.029495287345448e-06, + "loss": 1.3503, + "step": 6360 + }, + { + "epoch": 0.67, + "learning_rate": 6.0261361876574186e-06, + "loss": 1.3356, + "step": 6361 + }, + { + "epoch": 0.67, + "learning_rate": 6.022777620365032e-06, + "loss": 1.3301, + "step": 6362 + }, + { + "epoch": 0.67, + "learning_rate": 6.019419585918255e-06, + "loss": 1.3925, + "step": 6363 + }, + { + "epoch": 0.67, + "learning_rate": 6.016062084766978e-06, + "loss": 1.3794, + "step": 6364 + }, + { + "epoch": 0.67, + "learning_rate": 6.0127051173610155e-06, + "loss": 1.5496, + "step": 6365 + }, + { + "epoch": 0.67, + "learning_rate": 6.009348684150116e-06, + "loss": 1.3227, + "step": 6366 + }, + { + "epoch": 0.67, + "learning_rate": 6.005992785583958e-06, + "loss": 1.3474, + "step": 6367 + }, + { + "epoch": 0.67, + "learning_rate": 6.002637422112143e-06, + "loss": 1.3262, + "step": 6368 + }, + { + "epoch": 0.67, + "eval_loss": 1.4049769639968872, + "eval_runtime": 77.5156, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 6368 + }, + { + "epoch": 0.67, + "learning_rate": 5.999282594184206e-06, + "loss": 1.3083, + "step": 6369 + }, + { + "epoch": 0.67, + "learning_rate": 5.995928302249603e-06, + "loss": 1.323, + "step": 6370 + }, + { + "epoch": 0.67, + "learning_rate": 5.99257454675773e-06, + "loss": 1.3101, + "step": 6371 + }, + { + "epoch": 0.67, + "learning_rate": 5.989221328157899e-06, + "loss": 1.4546, + "step": 6372 + }, + { + "epoch": 0.67, + "learning_rate": 5.985868646899355e-06, + "loss": 1.3315, + "step": 6373 + }, + { + "epoch": 0.67, + "learning_rate": 5.982516503431273e-06, + "loss": 1.3768, + "step": 6374 + }, + { + "epoch": 0.67, + "learning_rate": 5.979164898202755e-06, + "loss": 1.332, + "step": 6375 + }, + { + "epoch": 0.67, + "learning_rate": 5.975813831662829e-06, + "loss": 1.3154, + "step": 6376 + }, + { + "epoch": 0.67, + "learning_rate": 5.972463304260448e-06, + "loss": 1.3636, + "step": 6377 + }, + { + "epoch": 0.67, + "learning_rate": 5.969113316444504e-06, + "loss": 1.3553, + "step": 6378 + }, + { + "epoch": 0.67, + "learning_rate": 5.965763868663803e-06, + "loss": 1.3805, + "step": 6379 + }, + { + "epoch": 0.67, + "learning_rate": 5.962414961367089e-06, + "loss": 1.3096, + "step": 6380 + }, + { + "epoch": 0.67, + "learning_rate": 5.959066595003025e-06, + "loss": 1.326, + "step": 6381 + }, + { + "epoch": 0.67, + "learning_rate": 5.955718770020212e-06, + "loss": 1.3021, + "step": 6382 + }, + { + "epoch": 0.67, + "learning_rate": 5.952371486867168e-06, + "loss": 1.35, + "step": 6383 + }, + { + "epoch": 0.67, + "learning_rate": 5.949024745992344e-06, + "loss": 1.6749, + "step": 6384 + }, + { + "epoch": 0.67, + "learning_rate": 5.945678547844117e-06, + "loss": 1.4931, + "step": 6385 + }, + { + "epoch": 0.67, + "learning_rate": 5.942332892870793e-06, + "loss": 1.284, + "step": 6386 + }, + { + "epoch": 0.67, + "learning_rate": 5.938987781520604e-06, + "loss": 1.3296, + "step": 6387 + }, + { + "epoch": 0.67, + "learning_rate": 5.9356432142417074e-06, + "loss": 1.4837, + "step": 6388 + }, + { + "epoch": 0.67, + "learning_rate": 5.932299191482188e-06, + "loss": 1.3114, + "step": 6389 + }, + { + "epoch": 0.67, + "learning_rate": 5.928955713690063e-06, + "loss": 1.3328, + "step": 6390 + }, + { + "epoch": 0.67, + "learning_rate": 5.92561278131327e-06, + "loss": 1.3163, + "step": 6391 + }, + { + "epoch": 0.67, + "learning_rate": 5.922270394799676e-06, + "loss": 1.3068, + "step": 6392 + }, + { + "epoch": 0.67, + "learning_rate": 5.918928554597073e-06, + "loss": 1.292, + "step": 6393 + }, + { + "epoch": 0.67, + "learning_rate": 5.915587261153186e-06, + "loss": 1.3359, + "step": 6394 + }, + { + "epoch": 0.67, + "learning_rate": 5.912246514915662e-06, + "loss": 1.4109, + "step": 6395 + }, + { + "epoch": 0.67, + "learning_rate": 5.908906316332071e-06, + "loss": 1.3083, + "step": 6396 + }, + { + "epoch": 0.67, + "learning_rate": 5.905566665849917e-06, + "loss": 1.2973, + "step": 6397 + }, + { + "epoch": 0.67, + "learning_rate": 5.902227563916627e-06, + "loss": 1.4159, + "step": 6398 + }, + { + "epoch": 0.67, + "learning_rate": 5.898889010979556e-06, + "loss": 1.287, + "step": 6399 + }, + { + "epoch": 0.67, + "learning_rate": 5.89555100748598e-06, + "loss": 1.2865, + "step": 6400 + }, + { + "epoch": 0.67, + "learning_rate": 5.89221355388311e-06, + "loss": 1.3137, + "step": 6401 + }, + { + "epoch": 0.67, + "learning_rate": 5.8888766506180785e-06, + "loss": 1.2751, + "step": 6402 + }, + { + "epoch": 0.67, + "learning_rate": 5.885540298137944e-06, + "loss": 1.3687, + "step": 6403 + }, + { + "epoch": 0.67, + "learning_rate": 5.882204496889688e-06, + "loss": 1.2941, + "step": 6404 + }, + { + "epoch": 0.67, + "learning_rate": 5.878869247320231e-06, + "loss": 1.2926, + "step": 6405 + }, + { + "epoch": 0.67, + "learning_rate": 5.875534549876404e-06, + "loss": 1.2675, + "step": 6406 + }, + { + "epoch": 0.67, + "learning_rate": 5.872200405004973e-06, + "loss": 1.2806, + "step": 6407 + }, + { + "epoch": 0.67, + "learning_rate": 5.868866813152625e-06, + "loss": 1.3438, + "step": 6408 + }, + { + "epoch": 0.67, + "learning_rate": 5.865533774765981e-06, + "loss": 1.2947, + "step": 6409 + }, + { + "epoch": 0.67, + "learning_rate": 5.862201290291578e-06, + "loss": 1.3643, + "step": 6410 + }, + { + "epoch": 0.67, + "learning_rate": 5.858869360175887e-06, + "loss": 1.2579, + "step": 6411 + }, + { + "epoch": 0.67, + "learning_rate": 5.855537984865296e-06, + "loss": 1.3479, + "step": 6412 + }, + { + "epoch": 0.67, + "learning_rate": 5.852207164806127e-06, + "loss": 1.3239, + "step": 6413 + }, + { + "epoch": 0.67, + "learning_rate": 5.848876900444626e-06, + "loss": 1.2644, + "step": 6414 + }, + { + "epoch": 0.67, + "learning_rate": 5.845547192226959e-06, + "loss": 1.3279, + "step": 6415 + }, + { + "epoch": 0.67, + "learning_rate": 5.8422180405992216e-06, + "loss": 1.5202, + "step": 6416 + }, + { + "epoch": 0.67, + "learning_rate": 5.838889446007439e-06, + "loss": 1.5714, + "step": 6417 + }, + { + "epoch": 0.67, + "learning_rate": 5.835561408897552e-06, + "loss": 1.2592, + "step": 6418 + }, + { + "epoch": 0.67, + "learning_rate": 5.832233929715434e-06, + "loss": 1.3407, + "step": 6419 + }, + { + "epoch": 0.67, + "learning_rate": 5.828907008906882e-06, + "loss": 1.3555, + "step": 6420 + }, + { + "epoch": 0.67, + "learning_rate": 5.825580646917622e-06, + "loss": 1.2602, + "step": 6421 + }, + { + "epoch": 0.67, + "learning_rate": 5.822254844193293e-06, + "loss": 1.2672, + "step": 6422 + }, + { + "epoch": 0.67, + "learning_rate": 5.818929601179472e-06, + "loss": 1.3361, + "step": 6423 + }, + { + "epoch": 0.67, + "learning_rate": 5.8156049183216575e-06, + "loss": 1.49, + "step": 6424 + }, + { + "epoch": 0.67, + "learning_rate": 5.812280796065269e-06, + "loss": 1.306, + "step": 6425 + }, + { + "epoch": 0.67, + "learning_rate": 5.808957234855654e-06, + "loss": 1.3167, + "step": 6426 + }, + { + "epoch": 0.67, + "learning_rate": 5.805634235138082e-06, + "loss": 1.3103, + "step": 6427 + }, + { + "epoch": 0.67, + "learning_rate": 5.802311797357752e-06, + "loss": 1.2992, + "step": 6428 + }, + { + "epoch": 0.67, + "learning_rate": 5.7989899219597875e-06, + "loss": 1.3269, + "step": 6429 + }, + { + "epoch": 0.67, + "learning_rate": 5.795668609389233e-06, + "loss": 1.3393, + "step": 6430 + }, + { + "epoch": 0.67, + "learning_rate": 5.79234786009105e-06, + "loss": 1.2633, + "step": 6431 + }, + { + "epoch": 0.67, + "learning_rate": 5.7890276745101495e-06, + "loss": 1.2758, + "step": 6432 + }, + { + "epoch": 0.67, + "learning_rate": 5.785708053091339e-06, + "loss": 1.3294, + "step": 6433 + }, + { + "epoch": 0.67, + "learning_rate": 5.782388996279371e-06, + "loss": 1.3657, + "step": 6434 + }, + { + "epoch": 0.67, + "learning_rate": 5.779070504518905e-06, + "loss": 1.3353, + "step": 6435 + }, + { + "epoch": 0.67, + "learning_rate": 5.775752578254539e-06, + "loss": 1.2741, + "step": 6436 + }, + { + "epoch": 0.68, + "learning_rate": 5.772435217930792e-06, + "loss": 1.2979, + "step": 6437 + }, + { + "epoch": 0.68, + "learning_rate": 5.7691184239921026e-06, + "loss": 1.366, + "step": 6438 + }, + { + "epoch": 0.68, + "learning_rate": 5.765802196882828e-06, + "loss": 1.2873, + "step": 6439 + }, + { + "epoch": 0.68, + "learning_rate": 5.762486537047271e-06, + "loss": 1.2865, + "step": 6440 + }, + { + "epoch": 0.68, + "learning_rate": 5.7591714449296365e-06, + "loss": 1.3887, + "step": 6441 + }, + { + "epoch": 0.68, + "learning_rate": 5.755856920974063e-06, + "loss": 1.127, + "step": 6442 + }, + { + "epoch": 0.68, + "learning_rate": 5.752542965624617e-06, + "loss": 1.4331, + "step": 6443 + }, + { + "epoch": 0.68, + "learning_rate": 5.749229579325274e-06, + "loss": 1.3199, + "step": 6444 + }, + { + "epoch": 0.68, + "learning_rate": 5.745916762519952e-06, + "loss": 1.2719, + "step": 6445 + }, + { + "epoch": 0.68, + "learning_rate": 5.742604515652475e-06, + "loss": 1.2991, + "step": 6446 + }, + { + "epoch": 0.68, + "learning_rate": 5.7392928391666014e-06, + "loss": 1.2164, + "step": 6447 + }, + { + "epoch": 0.68, + "learning_rate": 5.735981733506016e-06, + "loss": 1.3636, + "step": 6448 + }, + { + "epoch": 0.68, + "learning_rate": 5.732671199114314e-06, + "loss": 1.3486, + "step": 6449 + }, + { + "epoch": 0.68, + "learning_rate": 5.729361236435027e-06, + "loss": 1.3378, + "step": 6450 + }, + { + "epoch": 0.68, + "learning_rate": 5.726051845911606e-06, + "loss": 1.3521, + "step": 6451 + }, + { + "epoch": 0.68, + "learning_rate": 5.722743027987421e-06, + "loss": 1.4295, + "step": 6452 + }, + { + "epoch": 0.68, + "learning_rate": 5.719434783105772e-06, + "loss": 1.2625, + "step": 6453 + }, + { + "epoch": 0.68, + "learning_rate": 5.716127111709873e-06, + "loss": 1.2944, + "step": 6454 + }, + { + "epoch": 0.68, + "learning_rate": 5.7128200142428695e-06, + "loss": 1.3655, + "step": 6455 + }, + { + "epoch": 0.68, + "learning_rate": 5.7095134911478336e-06, + "loss": 1.3115, + "step": 6456 + }, + { + "epoch": 0.68, + "learning_rate": 5.706207542867747e-06, + "loss": 1.3391, + "step": 6457 + }, + { + "epoch": 0.68, + "learning_rate": 5.702902169845519e-06, + "loss": 1.3911, + "step": 6458 + }, + { + "epoch": 0.68, + "learning_rate": 5.699597372523997e-06, + "loss": 1.2936, + "step": 6459 + }, + { + "epoch": 0.68, + "learning_rate": 5.696293151345928e-06, + "loss": 1.379, + "step": 6460 + }, + { + "epoch": 0.68, + "learning_rate": 5.692989506754e-06, + "loss": 1.4083, + "step": 6461 + }, + { + "epoch": 0.68, + "learning_rate": 5.689686439190809e-06, + "loss": 1.2645, + "step": 6462 + }, + { + "epoch": 0.68, + "learning_rate": 5.686383949098886e-06, + "loss": 1.3207, + "step": 6463 + }, + { + "epoch": 0.68, + "learning_rate": 5.683082036920682e-06, + "loss": 1.4293, + "step": 6464 + }, + { + "epoch": 0.68, + "learning_rate": 5.679780703098563e-06, + "loss": 1.3018, + "step": 6465 + }, + { + "epoch": 0.68, + "learning_rate": 5.676479948074825e-06, + "loss": 1.3568, + "step": 6466 + }, + { + "epoch": 0.68, + "learning_rate": 5.673179772291687e-06, + "loss": 1.3252, + "step": 6467 + }, + { + "epoch": 0.68, + "learning_rate": 5.669880176191283e-06, + "loss": 1.2674, + "step": 6468 + }, + { + "epoch": 0.68, + "learning_rate": 5.666581160215676e-06, + "loss": 1.3774, + "step": 6469 + }, + { + "epoch": 0.68, + "learning_rate": 5.663282724806855e-06, + "loss": 1.3013, + "step": 6470 + }, + { + "epoch": 0.68, + "learning_rate": 5.659984870406715e-06, + "loss": 1.3354, + "step": 6471 + }, + { + "epoch": 0.68, + "learning_rate": 5.656687597457093e-06, + "loss": 1.273, + "step": 6472 + }, + { + "epoch": 0.68, + "learning_rate": 5.653390906399732e-06, + "loss": 1.3041, + "step": 6473 + }, + { + "epoch": 0.68, + "learning_rate": 5.650094797676308e-06, + "loss": 1.3521, + "step": 6474 + }, + { + "epoch": 0.68, + "learning_rate": 5.646799271728417e-06, + "loss": 1.3751, + "step": 6475 + }, + { + "epoch": 0.68, + "learning_rate": 5.643504328997571e-06, + "loss": 1.2882, + "step": 6476 + }, + { + "epoch": 0.68, + "learning_rate": 5.640209969925202e-06, + "loss": 1.2625, + "step": 6477 + }, + { + "epoch": 0.68, + "learning_rate": 5.636916194952683e-06, + "loss": 1.3648, + "step": 6478 + }, + { + "epoch": 0.68, + "learning_rate": 5.633623004521285e-06, + "loss": 1.3115, + "step": 6479 + }, + { + "epoch": 0.68, + "learning_rate": 5.6303303990722154e-06, + "loss": 1.2755, + "step": 6480 + }, + { + "epoch": 0.68, + "learning_rate": 5.627038379046595e-06, + "loss": 1.4546, + "step": 6481 + }, + { + "epoch": 0.68, + "learning_rate": 5.623746944885473e-06, + "loss": 1.3717, + "step": 6482 + }, + { + "epoch": 0.68, + "learning_rate": 5.620456097029818e-06, + "loss": 1.3188, + "step": 6483 + }, + { + "epoch": 0.68, + "learning_rate": 5.61716583592052e-06, + "loss": 1.3166, + "step": 6484 + }, + { + "epoch": 0.68, + "learning_rate": 5.613876161998377e-06, + "loss": 1.3413, + "step": 6485 + }, + { + "epoch": 0.68, + "learning_rate": 5.610587075704139e-06, + "loss": 1.395, + "step": 6486 + }, + { + "epoch": 0.68, + "learning_rate": 5.6072985774784465e-06, + "loss": 1.2914, + "step": 6487 + }, + { + "epoch": 0.68, + "learning_rate": 5.604010667761876e-06, + "loss": 1.3118, + "step": 6488 + }, + { + "epoch": 0.68, + "learning_rate": 5.600723346994932e-06, + "loss": 1.3599, + "step": 6489 + }, + { + "epoch": 0.68, + "learning_rate": 5.597436615618017e-06, + "loss": 1.2862, + "step": 6490 + }, + { + "epoch": 0.68, + "learning_rate": 5.594150474071481e-06, + "loss": 1.3585, + "step": 6491 + }, + { + "epoch": 0.68, + "learning_rate": 5.590864922795573e-06, + "loss": 1.3449, + "step": 6492 + }, + { + "epoch": 0.68, + "learning_rate": 5.587579962230475e-06, + "loss": 1.2787, + "step": 6493 + }, + { + "epoch": 0.68, + "learning_rate": 5.5842955928162934e-06, + "loss": 1.3755, + "step": 6494 + }, + { + "epoch": 0.68, + "learning_rate": 5.5810118149930406e-06, + "loss": 1.2858, + "step": 6495 + }, + { + "epoch": 0.68, + "learning_rate": 5.577728629200662e-06, + "loss": 1.4214, + "step": 6496 + }, + { + "epoch": 0.68, + "learning_rate": 5.574446035879024e-06, + "loss": 1.5007, + "step": 6497 + }, + { + "epoch": 0.68, + "learning_rate": 5.571164035467903e-06, + "loss": 1.2952, + "step": 6498 + }, + { + "epoch": 0.68, + "learning_rate": 5.56788262840701e-06, + "loss": 1.267, + "step": 6499 + }, + { + "epoch": 0.68, + "learning_rate": 5.564601815135962e-06, + "loss": 1.3168, + "step": 6500 + }, + { + "epoch": 0.68, + "learning_rate": 5.561321596094305e-06, + "loss": 1.2992, + "step": 6501 + }, + { + "epoch": 0.68, + "learning_rate": 5.558041971721511e-06, + "loss": 1.4237, + "step": 6502 + }, + { + "epoch": 0.68, + "learning_rate": 5.554762942456959e-06, + "loss": 1.3865, + "step": 6503 + }, + { + "epoch": 0.68, + "learning_rate": 5.5514845087399505e-06, + "loss": 1.2875, + "step": 6504 + }, + { + "epoch": 0.68, + "learning_rate": 5.548206671009724e-06, + "loss": 1.3011, + "step": 6505 + }, + { + "epoch": 0.68, + "learning_rate": 5.544929429705415e-06, + "loss": 1.3425, + "step": 6506 + }, + { + "epoch": 0.68, + "learning_rate": 5.541652785266095e-06, + "loss": 1.4265, + "step": 6507 + }, + { + "epoch": 0.68, + "learning_rate": 5.538376738130747e-06, + "loss": 1.2877, + "step": 6508 + }, + { + "epoch": 0.68, + "learning_rate": 5.535101288738276e-06, + "loss": 1.3652, + "step": 6509 + }, + { + "epoch": 0.68, + "learning_rate": 5.5318264375275145e-06, + "loss": 1.2997, + "step": 6510 + }, + { + "epoch": 0.68, + "learning_rate": 5.528552184937201e-06, + "loss": 1.3223, + "step": 6511 + }, + { + "epoch": 0.68, + "learning_rate": 5.525278531406006e-06, + "loss": 1.2897, + "step": 6512 + }, + { + "epoch": 0.68, + "learning_rate": 5.522005477372516e-06, + "loss": 1.3554, + "step": 6513 + }, + { + "epoch": 0.68, + "learning_rate": 5.51873302327523e-06, + "loss": 1.3233, + "step": 6514 + }, + { + "epoch": 0.68, + "learning_rate": 5.515461169552576e-06, + "loss": 1.3536, + "step": 6515 + }, + { + "epoch": 0.68, + "learning_rate": 5.5121899166429046e-06, + "loss": 1.3485, + "step": 6516 + }, + { + "epoch": 0.68, + "learning_rate": 5.508919264984468e-06, + "loss": 1.3264, + "step": 6517 + }, + { + "epoch": 0.68, + "learning_rate": 5.505649215015461e-06, + "loss": 1.4498, + "step": 6518 + }, + { + "epoch": 0.68, + "learning_rate": 5.5023797671739755e-06, + "loss": 1.4468, + "step": 6519 + }, + { + "epoch": 0.68, + "learning_rate": 5.499110921898038e-06, + "loss": 1.2659, + "step": 6520 + }, + { + "epoch": 0.68, + "learning_rate": 5.4958426796255934e-06, + "loss": 1.318, + "step": 6521 + }, + { + "epoch": 0.68, + "learning_rate": 5.492575040794498e-06, + "loss": 1.3167, + "step": 6522 + }, + { + "epoch": 0.68, + "learning_rate": 5.48930800584253e-06, + "loss": 1.3453, + "step": 6523 + }, + { + "epoch": 0.68, + "learning_rate": 5.486041575207397e-06, + "loss": 1.2557, + "step": 6524 + }, + { + "epoch": 0.68, + "learning_rate": 5.482775749326705e-06, + "loss": 1.3235, + "step": 6525 + }, + { + "epoch": 0.68, + "learning_rate": 5.479510528638001e-06, + "loss": 1.3119, + "step": 6526 + }, + { + "epoch": 0.68, + "learning_rate": 5.476245913578733e-06, + "loss": 1.4639, + "step": 6527 + }, + { + "epoch": 0.68, + "learning_rate": 5.472981904586277e-06, + "loss": 1.3233, + "step": 6528 + }, + { + "epoch": 0.68, + "learning_rate": 5.469718502097931e-06, + "loss": 1.2722, + "step": 6529 + }, + { + "epoch": 0.68, + "learning_rate": 5.466455706550906e-06, + "loss": 1.4428, + "step": 6530 + }, + { + "epoch": 0.68, + "learning_rate": 5.463193518382321e-06, + "loss": 1.5695, + "step": 6531 + }, + { + "epoch": 0.68, + "learning_rate": 5.4599319380292434e-06, + "loss": 1.3161, + "step": 6532 + }, + { + "epoch": 0.69, + "learning_rate": 5.4566709659286296e-06, + "loss": 1.3513, + "step": 6533 + }, + { + "epoch": 0.69, + "learning_rate": 5.453410602517368e-06, + "loss": 1.2716, + "step": 6534 + }, + { + "epoch": 0.69, + "learning_rate": 5.45015084823227e-06, + "loss": 1.4467, + "step": 6535 + }, + { + "epoch": 0.69, + "learning_rate": 5.44689170351005e-06, + "loss": 1.4082, + "step": 6536 + }, + { + "epoch": 0.69, + "learning_rate": 5.443633168787357e-06, + "loss": 1.303, + "step": 6537 + }, + { + "epoch": 0.69, + "learning_rate": 5.440375244500743e-06, + "loss": 1.2765, + "step": 6538 + }, + { + "epoch": 0.69, + "learning_rate": 5.43711793108669e-06, + "loss": 1.6814, + "step": 6539 + }, + { + "epoch": 0.69, + "learning_rate": 5.4338612289816e-06, + "loss": 1.3899, + "step": 6540 + }, + { + "epoch": 0.69, + "learning_rate": 5.430605138621778e-06, + "loss": 1.201, + "step": 6541 + }, + { + "epoch": 0.69, + "learning_rate": 5.42734966044346e-06, + "loss": 1.3214, + "step": 6542 + }, + { + "epoch": 0.69, + "learning_rate": 5.424094794882801e-06, + "loss": 1.2676, + "step": 6543 + }, + { + "epoch": 0.69, + "learning_rate": 5.420840542375862e-06, + "loss": 1.3006, + "step": 6544 + }, + { + "epoch": 0.69, + "learning_rate": 5.4175869033586355e-06, + "loss": 1.32, + "step": 6545 + }, + { + "epoch": 0.69, + "learning_rate": 5.41433387826702e-06, + "loss": 1.3347, + "step": 6546 + }, + { + "epoch": 0.69, + "learning_rate": 5.41108146753684e-06, + "loss": 1.3983, + "step": 6547 + }, + { + "epoch": 0.69, + "learning_rate": 5.407829671603838e-06, + "loss": 1.3756, + "step": 6548 + }, + { + "epoch": 0.69, + "learning_rate": 5.404578490903664e-06, + "loss": 1.3444, + "step": 6549 + }, + { + "epoch": 0.69, + "learning_rate": 5.4013279258718974e-06, + "loss": 1.3369, + "step": 6550 + }, + { + "epoch": 0.69, + "learning_rate": 5.398077976944034e-06, + "loss": 1.2995, + "step": 6551 + }, + { + "epoch": 0.69, + "learning_rate": 5.394828644555475e-06, + "loss": 1.3305, + "step": 6552 + }, + { + "epoch": 0.69, + "learning_rate": 5.391579929141554e-06, + "loss": 1.3743, + "step": 6553 + }, + { + "epoch": 0.69, + "learning_rate": 5.3883318311375095e-06, + "loss": 1.2829, + "step": 6554 + }, + { + "epoch": 0.69, + "learning_rate": 5.3850843509785065e-06, + "loss": 1.379, + "step": 6555 + }, + { + "epoch": 0.69, + "learning_rate": 5.3818374890996295e-06, + "loss": 1.3236, + "step": 6556 + }, + { + "epoch": 0.69, + "learning_rate": 5.378591245935865e-06, + "loss": 1.3469, + "step": 6557 + }, + { + "epoch": 0.69, + "learning_rate": 5.375345621922129e-06, + "loss": 1.3318, + "step": 6558 + }, + { + "epoch": 0.69, + "learning_rate": 5.3721006174932576e-06, + "loss": 1.3395, + "step": 6559 + }, + { + "epoch": 0.69, + "learning_rate": 5.36885623308399e-06, + "loss": 1.4148, + "step": 6560 + }, + { + "epoch": 0.69, + "learning_rate": 5.365612469128993e-06, + "loss": 1.3007, + "step": 6561 + }, + { + "epoch": 0.69, + "learning_rate": 5.362369326062853e-06, + "loss": 1.4365, + "step": 6562 + }, + { + "epoch": 0.69, + "learning_rate": 5.3591268043200585e-06, + "loss": 1.4269, + "step": 6563 + }, + { + "epoch": 0.69, + "learning_rate": 5.355884904335034e-06, + "loss": 1.2619, + "step": 6564 + }, + { + "epoch": 0.69, + "learning_rate": 5.3526436265421e-06, + "loss": 1.2678, + "step": 6565 + }, + { + "epoch": 0.69, + "learning_rate": 5.34940297137551e-06, + "loss": 1.2541, + "step": 6566 + }, + { + "epoch": 0.69, + "learning_rate": 5.3461629392694345e-06, + "loss": 1.3237, + "step": 6567 + }, + { + "epoch": 0.69, + "eval_loss": 1.402653694152832, + "eval_runtime": 77.5033, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 6567 + }, + { + "epoch": 0.69, + "learning_rate": 5.342923530657944e-06, + "loss": 1.357, + "step": 6568 + }, + { + "epoch": 0.69, + "learning_rate": 5.33968474597504e-06, + "loss": 1.3561, + "step": 6569 + }, + { + "epoch": 0.69, + "learning_rate": 5.336446585654642e-06, + "loss": 1.2969, + "step": 6570 + }, + { + "epoch": 0.69, + "learning_rate": 5.33320905013057e-06, + "loss": 1.2922, + "step": 6571 + }, + { + "epoch": 0.69, + "learning_rate": 5.329972139836581e-06, + "loss": 1.3581, + "step": 6572 + }, + { + "epoch": 0.69, + "learning_rate": 5.326735855206328e-06, + "loss": 1.2926, + "step": 6573 + }, + { + "epoch": 0.69, + "learning_rate": 5.3235001966733965e-06, + "loss": 1.3933, + "step": 6574 + }, + { + "epoch": 0.69, + "learning_rate": 5.320265164671283e-06, + "loss": 1.4009, + "step": 6575 + }, + { + "epoch": 0.69, + "learning_rate": 5.3170307596333955e-06, + "loss": 1.4051, + "step": 6576 + }, + { + "epoch": 0.69, + "learning_rate": 5.313796981993054e-06, + "loss": 1.3448, + "step": 6577 + }, + { + "epoch": 0.69, + "learning_rate": 5.310563832183515e-06, + "loss": 1.3141, + "step": 6578 + }, + { + "epoch": 0.69, + "learning_rate": 5.307331310637929e-06, + "loss": 1.3658, + "step": 6579 + }, + { + "epoch": 0.69, + "learning_rate": 5.3040994177893725e-06, + "loss": 1.2881, + "step": 6580 + }, + { + "epoch": 0.69, + "learning_rate": 5.30086815407084e-06, + "loss": 1.3051, + "step": 6581 + }, + { + "epoch": 0.69, + "learning_rate": 5.297637519915231e-06, + "loss": 1.3353, + "step": 6582 + }, + { + "epoch": 0.69, + "learning_rate": 5.2944075157553754e-06, + "loss": 1.3997, + "step": 6583 + }, + { + "epoch": 0.69, + "learning_rate": 5.291178142024002e-06, + "loss": 1.3094, + "step": 6584 + }, + { + "epoch": 0.69, + "learning_rate": 5.287949399153769e-06, + "loss": 1.3384, + "step": 6585 + }, + { + "epoch": 0.69, + "learning_rate": 5.284721287577248e-06, + "loss": 1.3183, + "step": 6586 + }, + { + "epoch": 0.69, + "learning_rate": 5.281493807726916e-06, + "loss": 1.4433, + "step": 6587 + }, + { + "epoch": 0.69, + "learning_rate": 5.278266960035174e-06, + "loss": 1.3103, + "step": 6588 + }, + { + "epoch": 0.69, + "learning_rate": 5.275040744934343e-06, + "loss": 1.3478, + "step": 6589 + }, + { + "epoch": 0.69, + "learning_rate": 5.271815162856645e-06, + "loss": 1.2713, + "step": 6590 + }, + { + "epoch": 0.69, + "learning_rate": 5.268590214234233e-06, + "loss": 1.3697, + "step": 6591 + }, + { + "epoch": 0.69, + "learning_rate": 5.265365899499156e-06, + "loss": 1.6169, + "step": 6592 + }, + { + "epoch": 0.69, + "learning_rate": 5.262142219083398e-06, + "loss": 1.2988, + "step": 6593 + }, + { + "epoch": 0.69, + "learning_rate": 5.258919173418851e-06, + "loss": 1.515, + "step": 6594 + }, + { + "epoch": 0.69, + "learning_rate": 5.2556967629373125e-06, + "loss": 1.3704, + "step": 6595 + }, + { + "epoch": 0.69, + "learning_rate": 5.2524749880705075e-06, + "loss": 1.2404, + "step": 6596 + }, + { + "epoch": 0.69, + "learning_rate": 5.249253849250073e-06, + "loss": 1.2799, + "step": 6597 + }, + { + "epoch": 0.69, + "learning_rate": 5.246033346907553e-06, + "loss": 1.2876, + "step": 6598 + }, + { + "epoch": 0.69, + "learning_rate": 5.24281348147442e-06, + "loss": 1.3058, + "step": 6599 + }, + { + "epoch": 0.69, + "learning_rate": 5.239594253382043e-06, + "loss": 1.3347, + "step": 6600 + }, + { + "epoch": 0.69, + "learning_rate": 5.236375663061722e-06, + "loss": 1.3323, + "step": 6601 + }, + { + "epoch": 0.69, + "learning_rate": 5.23315771094467e-06, + "loss": 1.3254, + "step": 6602 + }, + { + "epoch": 0.69, + "learning_rate": 5.229940397461999e-06, + "loss": 1.3462, + "step": 6603 + }, + { + "epoch": 0.69, + "learning_rate": 5.226723723044753e-06, + "loss": 1.2901, + "step": 6604 + }, + { + "epoch": 0.69, + "learning_rate": 5.223507688123887e-06, + "loss": 1.3079, + "step": 6605 + }, + { + "epoch": 0.69, + "learning_rate": 5.220292293130258e-06, + "loss": 1.4282, + "step": 6606 + }, + { + "epoch": 0.69, + "learning_rate": 5.217077538494651e-06, + "loss": 1.3197, + "step": 6607 + }, + { + "epoch": 0.69, + "learning_rate": 5.213863424647765e-06, + "loss": 1.3581, + "step": 6608 + }, + { + "epoch": 0.69, + "learning_rate": 5.2106499520202005e-06, + "loss": 1.3322, + "step": 6609 + }, + { + "epoch": 0.69, + "learning_rate": 5.207437121042488e-06, + "loss": 1.3368, + "step": 6610 + }, + { + "epoch": 0.69, + "learning_rate": 5.204224932145056e-06, + "loss": 1.2771, + "step": 6611 + }, + { + "epoch": 0.69, + "learning_rate": 5.20101338575826e-06, + "loss": 1.2852, + "step": 6612 + }, + { + "epoch": 0.69, + "learning_rate": 5.197802482312369e-06, + "loss": 1.3733, + "step": 6613 + }, + { + "epoch": 0.69, + "learning_rate": 5.194592222237551e-06, + "loss": 1.3719, + "step": 6614 + }, + { + "epoch": 0.69, + "learning_rate": 5.191382605963906e-06, + "loss": 1.3658, + "step": 6615 + }, + { + "epoch": 0.69, + "learning_rate": 5.1881736339214415e-06, + "loss": 1.3261, + "step": 6616 + }, + { + "epoch": 0.69, + "learning_rate": 5.18496530654007e-06, + "loss": 1.3057, + "step": 6617 + }, + { + "epoch": 0.69, + "learning_rate": 5.181757624249635e-06, + "loss": 1.2665, + "step": 6618 + }, + { + "epoch": 0.69, + "learning_rate": 5.1785505874798716e-06, + "loss": 1.2839, + "step": 6619 + }, + { + "epoch": 0.69, + "learning_rate": 5.175344196660447e-06, + "loss": 1.3131, + "step": 6620 + }, + { + "epoch": 0.69, + "learning_rate": 5.1721384522209385e-06, + "loss": 1.3217, + "step": 6621 + }, + { + "epoch": 0.69, + "learning_rate": 5.168933354590825e-06, + "loss": 1.3306, + "step": 6622 + }, + { + "epoch": 0.69, + "learning_rate": 5.165728904199512e-06, + "loss": 1.3197, + "step": 6623 + }, + { + "epoch": 0.69, + "learning_rate": 5.1625251014763176e-06, + "loss": 1.3035, + "step": 6624 + }, + { + "epoch": 0.69, + "learning_rate": 5.1593219468504605e-06, + "loss": 1.2927, + "step": 6625 + }, + { + "epoch": 0.69, + "learning_rate": 5.156119440751086e-06, + "loss": 1.3333, + "step": 6626 + }, + { + "epoch": 0.69, + "learning_rate": 5.152917583607251e-06, + "loss": 1.3181, + "step": 6627 + }, + { + "epoch": 0.7, + "learning_rate": 5.149716375847913e-06, + "loss": 1.347, + "step": 6628 + }, + { + "epoch": 0.7, + "learning_rate": 5.14651581790196e-06, + "loss": 1.347, + "step": 6629 + }, + { + "epoch": 0.7, + "learning_rate": 5.143315910198179e-06, + "loss": 1.2892, + "step": 6630 + }, + { + "epoch": 0.7, + "learning_rate": 5.140116653165277e-06, + "loss": 1.2996, + "step": 6631 + }, + { + "epoch": 0.7, + "learning_rate": 5.136918047231876e-06, + "loss": 1.2802, + "step": 6632 + }, + { + "epoch": 0.7, + "learning_rate": 5.133720092826501e-06, + "loss": 1.2766, + "step": 6633 + }, + { + "epoch": 0.7, + "learning_rate": 5.130522790377598e-06, + "loss": 1.5365, + "step": 6634 + }, + { + "epoch": 0.7, + "learning_rate": 5.127326140313528e-06, + "loss": 1.4848, + "step": 6635 + }, + { + "epoch": 0.7, + "learning_rate": 5.124130143062551e-06, + "loss": 1.3712, + "step": 6636 + }, + { + "epoch": 0.7, + "learning_rate": 5.120934799052859e-06, + "loss": 1.3094, + "step": 6637 + }, + { + "epoch": 0.7, + "learning_rate": 5.1177401087125355e-06, + "loss": 1.272, + "step": 6638 + }, + { + "epoch": 0.7, + "learning_rate": 5.114546072469593e-06, + "loss": 1.2856, + "step": 6639 + }, + { + "epoch": 0.7, + "learning_rate": 5.111352690751952e-06, + "loss": 1.2886, + "step": 6640 + }, + { + "epoch": 0.7, + "learning_rate": 5.108159963987436e-06, + "loss": 1.277, + "step": 6641 + }, + { + "epoch": 0.7, + "learning_rate": 5.104967892603794e-06, + "loss": 1.3392, + "step": 6642 + }, + { + "epoch": 0.7, + "learning_rate": 5.101776477028684e-06, + "loss": 1.3036, + "step": 6643 + }, + { + "epoch": 0.7, + "learning_rate": 5.098585717689667e-06, + "loss": 1.4116, + "step": 6644 + }, + { + "epoch": 0.7, + "learning_rate": 5.095395615014226e-06, + "loss": 1.3437, + "step": 6645 + }, + { + "epoch": 0.7, + "learning_rate": 5.0922061694297565e-06, + "loss": 1.2608, + "step": 6646 + }, + { + "epoch": 0.7, + "learning_rate": 5.089017381363554e-06, + "loss": 1.2959, + "step": 6647 + }, + { + "epoch": 0.7, + "learning_rate": 5.085829251242844e-06, + "loss": 1.3508, + "step": 6648 + }, + { + "epoch": 0.7, + "learning_rate": 5.0826417794947455e-06, + "loss": 1.34, + "step": 6649 + }, + { + "epoch": 0.7, + "learning_rate": 5.0794549665463e-06, + "loss": 1.3092, + "step": 6650 + }, + { + "epoch": 0.7, + "learning_rate": 5.076268812824463e-06, + "loss": 1.3417, + "step": 6651 + }, + { + "epoch": 0.7, + "learning_rate": 5.073083318756092e-06, + "loss": 1.3424, + "step": 6652 + }, + { + "epoch": 0.7, + "learning_rate": 5.069898484767961e-06, + "loss": 1.3296, + "step": 6653 + }, + { + "epoch": 0.7, + "learning_rate": 5.066714311286762e-06, + "loss": 1.2852, + "step": 6654 + }, + { + "epoch": 0.7, + "learning_rate": 5.063530798739087e-06, + "loss": 1.3462, + "step": 6655 + }, + { + "epoch": 0.7, + "learning_rate": 5.06034794755145e-06, + "loss": 1.3615, + "step": 6656 + }, + { + "epoch": 0.7, + "learning_rate": 5.057165758150262e-06, + "loss": 1.245, + "step": 6657 + }, + { + "epoch": 0.7, + "learning_rate": 5.053984230961862e-06, + "loss": 1.201, + "step": 6658 + }, + { + "epoch": 0.7, + "learning_rate": 5.050803366412494e-06, + "loss": 1.331, + "step": 6659 + }, + { + "epoch": 0.7, + "learning_rate": 5.047623164928306e-06, + "loss": 1.3034, + "step": 6660 + }, + { + "epoch": 0.7, + "learning_rate": 5.044443626935367e-06, + "loss": 1.2822, + "step": 6661 + }, + { + "epoch": 0.7, + "learning_rate": 5.041264752859657e-06, + "loss": 1.2576, + "step": 6662 + }, + { + "epoch": 0.7, + "learning_rate": 5.038086543127055e-06, + "loss": 1.3198, + "step": 6663 + }, + { + "epoch": 0.7, + "learning_rate": 5.034908998163368e-06, + "loss": 1.2892, + "step": 6664 + }, + { + "epoch": 0.7, + "learning_rate": 5.031732118394299e-06, + "loss": 1.3004, + "step": 6665 + }, + { + "epoch": 0.7, + "learning_rate": 5.028555904245469e-06, + "loss": 1.3178, + "step": 6666 + }, + { + "epoch": 0.7, + "learning_rate": 5.0253803561424156e-06, + "loss": 1.3014, + "step": 6667 + }, + { + "epoch": 0.7, + "learning_rate": 5.022205474510571e-06, + "loss": 1.3151, + "step": 6668 + }, + { + "epoch": 0.7, + "learning_rate": 5.019031259775292e-06, + "loss": 1.3551, + "step": 6669 + }, + { + "epoch": 0.7, + "learning_rate": 5.015857712361847e-06, + "loss": 1.4188, + "step": 6670 + }, + { + "epoch": 0.7, + "learning_rate": 5.0126848326954025e-06, + "loss": 1.2743, + "step": 6671 + }, + { + "epoch": 0.7, + "learning_rate": 5.009512621201043e-06, + "loss": 1.3528, + "step": 6672 + }, + { + "epoch": 0.7, + "learning_rate": 5.006341078303771e-06, + "loss": 1.309, + "step": 6673 + }, + { + "epoch": 0.7, + "learning_rate": 5.003170204428483e-06, + "loss": 1.3353, + "step": 6674 + }, + { + "epoch": 0.7, + "learning_rate": 5.000000000000003e-06, + "loss": 1.2753, + "step": 6675 + }, + { + "epoch": 0.7, + "learning_rate": 4.9968304654430465e-06, + "loss": 1.3907, + "step": 6676 + }, + { + "epoch": 0.7, + "learning_rate": 4.993661601182256e-06, + "loss": 1.2876, + "step": 6677 + }, + { + "epoch": 0.7, + "learning_rate": 4.990493407642181e-06, + "loss": 1.2534, + "step": 6678 + }, + { + "epoch": 0.7, + "learning_rate": 4.98732588524727e-06, + "loss": 1.3352, + "step": 6679 + }, + { + "epoch": 0.7, + "learning_rate": 4.984159034421895e-06, + "loss": 1.3302, + "step": 6680 + }, + { + "epoch": 0.7, + "learning_rate": 4.980992855590336e-06, + "loss": 1.3783, + "step": 6681 + }, + { + "epoch": 0.7, + "learning_rate": 4.977827349176769e-06, + "loss": 1.2848, + "step": 6682 + }, + { + "epoch": 0.7, + "learning_rate": 4.974662515605302e-06, + "loss": 1.3269, + "step": 6683 + }, + { + "epoch": 0.7, + "learning_rate": 4.971498355299932e-06, + "loss": 1.3662, + "step": 6684 + }, + { + "epoch": 0.7, + "learning_rate": 4.968334868684579e-06, + "loss": 1.2508, + "step": 6685 + }, + { + "epoch": 0.7, + "learning_rate": 4.965172056183073e-06, + "loss": 1.3872, + "step": 6686 + }, + { + "epoch": 0.7, + "learning_rate": 4.962009918219142e-06, + "loss": 1.3008, + "step": 6687 + }, + { + "epoch": 0.7, + "learning_rate": 4.958848455216434e-06, + "loss": 1.2058, + "step": 6688 + }, + { + "epoch": 0.7, + "learning_rate": 4.95568766759851e-06, + "loss": 1.3127, + "step": 6689 + }, + { + "epoch": 0.7, + "learning_rate": 4.952527555788825e-06, + "loss": 1.2985, + "step": 6690 + }, + { + "epoch": 0.7, + "learning_rate": 4.949368120210757e-06, + "loss": 1.333, + "step": 6691 + }, + { + "epoch": 0.7, + "learning_rate": 4.946209361287593e-06, + "loss": 1.2945, + "step": 6692 + }, + { + "epoch": 0.7, + "learning_rate": 4.943051279442516e-06, + "loss": 1.262, + "step": 6693 + }, + { + "epoch": 0.7, + "learning_rate": 4.93989387509864e-06, + "loss": 1.6155, + "step": 6694 + }, + { + "epoch": 0.7, + "learning_rate": 4.936737148678965e-06, + "loss": 1.2838, + "step": 6695 + }, + { + "epoch": 0.7, + "learning_rate": 4.933581100606415e-06, + "loss": 1.3778, + "step": 6696 + }, + { + "epoch": 0.7, + "learning_rate": 4.930425731303824e-06, + "loss": 1.3624, + "step": 6697 + }, + { + "epoch": 0.7, + "learning_rate": 4.927271041193923e-06, + "loss": 1.2641, + "step": 6698 + }, + { + "epoch": 0.7, + "learning_rate": 4.924117030699362e-06, + "loss": 1.3314, + "step": 6699 + }, + { + "epoch": 0.7, + "learning_rate": 4.920963700242704e-06, + "loss": 1.328, + "step": 6700 + }, + { + "epoch": 0.7, + "learning_rate": 4.917811050246404e-06, + "loss": 1.3128, + "step": 6701 + }, + { + "epoch": 0.7, + "learning_rate": 4.914659081132843e-06, + "loss": 1.3877, + "step": 6702 + }, + { + "epoch": 0.7, + "learning_rate": 4.911507793324299e-06, + "loss": 1.3114, + "step": 6703 + }, + { + "epoch": 0.7, + "learning_rate": 4.908357187242967e-06, + "loss": 1.3592, + "step": 6704 + }, + { + "epoch": 0.7, + "learning_rate": 4.905207263310948e-06, + "loss": 1.329, + "step": 6705 + }, + { + "epoch": 0.7, + "learning_rate": 4.902058021950247e-06, + "loss": 1.2558, + "step": 6706 + }, + { + "epoch": 0.7, + "learning_rate": 4.898909463582784e-06, + "loss": 1.2489, + "step": 6707 + }, + { + "epoch": 0.7, + "learning_rate": 4.895761588630388e-06, + "loss": 1.2817, + "step": 6708 + }, + { + "epoch": 0.7, + "learning_rate": 4.892614397514785e-06, + "loss": 1.1606, + "step": 6709 + }, + { + "epoch": 0.7, + "learning_rate": 4.889467890657628e-06, + "loss": 1.2878, + "step": 6710 + }, + { + "epoch": 0.7, + "learning_rate": 4.886322068480458e-06, + "loss": 1.2747, + "step": 6711 + }, + { + "epoch": 0.7, + "learning_rate": 4.88317693140474e-06, + "loss": 1.3662, + "step": 6712 + }, + { + "epoch": 0.7, + "learning_rate": 4.880032479851844e-06, + "loss": 1.3009, + "step": 6713 + }, + { + "epoch": 0.7, + "learning_rate": 4.8768887142430385e-06, + "loss": 1.3157, + "step": 6714 + }, + { + "epoch": 0.7, + "learning_rate": 4.873745634999511e-06, + "loss": 1.4461, + "step": 6715 + }, + { + "epoch": 0.7, + "learning_rate": 4.870603242542358e-06, + "loss": 1.3818, + "step": 6716 + }, + { + "epoch": 0.7, + "learning_rate": 4.86746153729257e-06, + "loss": 1.3361, + "step": 6717 + }, + { + "epoch": 0.7, + "learning_rate": 4.864320519671061e-06, + "loss": 1.3147, + "step": 6718 + }, + { + "epoch": 0.7, + "learning_rate": 4.8611801900986485e-06, + "loss": 1.3773, + "step": 6719 + }, + { + "epoch": 0.7, + "learning_rate": 4.858040548996049e-06, + "loss": 1.3091, + "step": 6720 + }, + { + "epoch": 0.7, + "learning_rate": 4.854901596783902e-06, + "loss": 1.3314, + "step": 6721 + }, + { + "epoch": 0.7, + "learning_rate": 4.851763333882738e-06, + "loss": 1.3082, + "step": 6722 + }, + { + "epoch": 0.71, + "learning_rate": 4.848625760713007e-06, + "loss": 1.2687, + "step": 6723 + }, + { + "epoch": 0.71, + "learning_rate": 4.845488877695068e-06, + "loss": 1.3378, + "step": 6724 + }, + { + "epoch": 0.71, + "learning_rate": 4.842352685249174e-06, + "loss": 1.3516, + "step": 6725 + }, + { + "epoch": 0.71, + "learning_rate": 4.839217183795501e-06, + "loss": 1.4083, + "step": 6726 + }, + { + "epoch": 0.71, + "learning_rate": 4.836082373754124e-06, + "loss": 1.3073, + "step": 6727 + }, + { + "epoch": 0.71, + "learning_rate": 4.832948255545024e-06, + "loss": 1.2948, + "step": 6728 + }, + { + "epoch": 0.71, + "learning_rate": 4.829814829588099e-06, + "loss": 1.3323, + "step": 6729 + }, + { + "epoch": 0.71, + "learning_rate": 4.826682096303139e-06, + "loss": 1.3101, + "step": 6730 + }, + { + "epoch": 0.71, + "learning_rate": 4.823550056109853e-06, + "loss": 1.3323, + "step": 6731 + }, + { + "epoch": 0.71, + "learning_rate": 4.8204187094278605e-06, + "loss": 1.3862, + "step": 6732 + }, + { + "epoch": 0.71, + "learning_rate": 4.817288056676671e-06, + "loss": 1.3112, + "step": 6733 + }, + { + "epoch": 0.71, + "learning_rate": 4.8141580982757175e-06, + "loss": 1.297, + "step": 6734 + }, + { + "epoch": 0.71, + "learning_rate": 4.811028834644336e-06, + "loss": 1.2604, + "step": 6735 + }, + { + "epoch": 0.71, + "learning_rate": 4.807900266201761e-06, + "loss": 1.343, + "step": 6736 + }, + { + "epoch": 0.71, + "learning_rate": 4.804772393367142e-06, + "loss": 1.3254, + "step": 6737 + }, + { + "epoch": 0.71, + "learning_rate": 4.80164521655954e-06, + "loss": 1.2688, + "step": 6738 + }, + { + "epoch": 0.71, + "learning_rate": 4.798518736197909e-06, + "loss": 1.2693, + "step": 6739 + }, + { + "epoch": 0.71, + "learning_rate": 4.795392952701122e-06, + "loss": 1.4536, + "step": 6740 + }, + { + "epoch": 0.71, + "learning_rate": 4.7922678664879485e-06, + "loss": 1.3811, + "step": 6741 + }, + { + "epoch": 0.71, + "learning_rate": 4.789143477977072e-06, + "loss": 1.2584, + "step": 6742 + }, + { + "epoch": 0.71, + "learning_rate": 4.786019787587084e-06, + "loss": 1.2584, + "step": 6743 + }, + { + "epoch": 0.71, + "learning_rate": 4.782896795736472e-06, + "loss": 1.2005, + "step": 6744 + }, + { + "epoch": 0.71, + "learning_rate": 4.779774502843642e-06, + "loss": 1.335, + "step": 6745 + }, + { + "epoch": 0.71, + "learning_rate": 4.776652909326901e-06, + "loss": 1.3675, + "step": 6746 + }, + { + "epoch": 0.71, + "learning_rate": 4.773532015604457e-06, + "loss": 1.3794, + "step": 6747 + }, + { + "epoch": 0.71, + "learning_rate": 4.770411822094437e-06, + "loss": 1.3629, + "step": 6748 + }, + { + "epoch": 0.71, + "learning_rate": 4.76729232921486e-06, + "loss": 1.0805, + "step": 6749 + }, + { + "epoch": 0.71, + "learning_rate": 4.76417353738366e-06, + "loss": 1.2874, + "step": 6750 + }, + { + "epoch": 0.71, + "learning_rate": 4.761055447018681e-06, + "loss": 1.428, + "step": 6751 + }, + { + "epoch": 0.71, + "learning_rate": 4.757938058537656e-06, + "loss": 1.2935, + "step": 6752 + }, + { + "epoch": 0.71, + "learning_rate": 4.754821372358242e-06, + "loss": 1.4202, + "step": 6753 + }, + { + "epoch": 0.71, + "learning_rate": 4.751705388897997e-06, + "loss": 1.3109, + "step": 6754 + }, + { + "epoch": 0.71, + "learning_rate": 4.7485901085743754e-06, + "loss": 1.3319, + "step": 6755 + }, + { + "epoch": 0.71, + "learning_rate": 4.745475531804753e-06, + "loss": 1.3246, + "step": 6756 + }, + { + "epoch": 0.71, + "learning_rate": 4.742361659006395e-06, + "loss": 1.3407, + "step": 6757 + }, + { + "epoch": 0.71, + "learning_rate": 4.739248490596483e-06, + "loss": 1.2953, + "step": 6758 + }, + { + "epoch": 0.71, + "learning_rate": 4.736136026992107e-06, + "loss": 1.3214, + "step": 6759 + }, + { + "epoch": 0.71, + "learning_rate": 4.733024268610249e-06, + "loss": 1.4112, + "step": 6760 + }, + { + "epoch": 0.71, + "learning_rate": 4.7299132158678085e-06, + "loss": 1.2981, + "step": 6761 + }, + { + "epoch": 0.71, + "learning_rate": 4.726802869181591e-06, + "loss": 1.2975, + "step": 6762 + }, + { + "epoch": 0.71, + "learning_rate": 4.723693228968293e-06, + "loss": 1.3047, + "step": 6763 + }, + { + "epoch": 0.71, + "learning_rate": 4.720584295644533e-06, + "loss": 1.3906, + "step": 6764 + }, + { + "epoch": 0.71, + "learning_rate": 4.717476069626832e-06, + "loss": 1.2523, + "step": 6765 + }, + { + "epoch": 0.71, + "learning_rate": 4.7143685513316025e-06, + "loss": 1.0453, + "step": 6766 + }, + { + "epoch": 0.71, + "eval_loss": 1.4004828929901123, + "eval_runtime": 77.565, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 6766 + }, + { + "epoch": 0.71, + "learning_rate": 4.711261741175182e-06, + "loss": 1.1339, + "step": 6767 + }, + { + "epoch": 0.71, + "learning_rate": 4.7081556395737935e-06, + "loss": 1.2401, + "step": 6768 + }, + { + "epoch": 0.71, + "learning_rate": 4.705050246943581e-06, + "loss": 1.3009, + "step": 6769 + }, + { + "epoch": 0.71, + "learning_rate": 4.7019455637005895e-06, + "loss": 1.3106, + "step": 6770 + }, + { + "epoch": 0.71, + "learning_rate": 4.698841590260758e-06, + "loss": 1.3021, + "step": 6771 + }, + { + "epoch": 0.71, + "learning_rate": 4.695738327039947e-06, + "loss": 1.3147, + "step": 6772 + }, + { + "epoch": 0.71, + "learning_rate": 4.692635774453914e-06, + "loss": 1.238, + "step": 6773 + }, + { + "epoch": 0.71, + "learning_rate": 4.6895339329183154e-06, + "loss": 1.3876, + "step": 6774 + }, + { + "epoch": 0.71, + "learning_rate": 4.686432802848726e-06, + "loss": 1.3012, + "step": 6775 + }, + { + "epoch": 0.71, + "learning_rate": 4.68333238466061e-06, + "loss": 1.1421, + "step": 6776 + }, + { + "epoch": 0.71, + "learning_rate": 4.6802326787693455e-06, + "loss": 1.2838, + "step": 6777 + }, + { + "epoch": 0.71, + "learning_rate": 4.677133685590219e-06, + "loss": 1.3725, + "step": 6778 + }, + { + "epoch": 0.71, + "learning_rate": 4.674035405538409e-06, + "loss": 1.3093, + "step": 6779 + }, + { + "epoch": 0.71, + "learning_rate": 4.6709378390290085e-06, + "loss": 1.2785, + "step": 6780 + }, + { + "epoch": 0.71, + "learning_rate": 4.667840986477015e-06, + "loss": 1.2513, + "step": 6781 + }, + { + "epoch": 0.71, + "learning_rate": 4.66474484829732e-06, + "loss": 1.2903, + "step": 6782 + }, + { + "epoch": 0.71, + "learning_rate": 4.661649424904732e-06, + "loss": 1.4217, + "step": 6783 + }, + { + "epoch": 0.71, + "learning_rate": 4.658554716713959e-06, + "loss": 1.337, + "step": 6784 + }, + { + "epoch": 0.71, + "learning_rate": 4.655460724139605e-06, + "loss": 1.2978, + "step": 6785 + }, + { + "epoch": 0.71, + "learning_rate": 4.652367447596197e-06, + "loss": 1.3036, + "step": 6786 + }, + { + "epoch": 0.71, + "learning_rate": 4.6492748874981415e-06, + "loss": 1.2889, + "step": 6787 + }, + { + "epoch": 0.71, + "learning_rate": 4.646183044259771e-06, + "loss": 1.3046, + "step": 6788 + }, + { + "epoch": 0.71, + "learning_rate": 4.643091918295312e-06, + "loss": 1.3483, + "step": 6789 + }, + { + "epoch": 0.71, + "learning_rate": 4.640001510018893e-06, + "loss": 1.3862, + "step": 6790 + }, + { + "epoch": 0.71, + "learning_rate": 4.6369118198445505e-06, + "loss": 1.2483, + "step": 6791 + }, + { + "epoch": 0.71, + "learning_rate": 4.633822848186228e-06, + "loss": 1.2669, + "step": 6792 + }, + { + "epoch": 0.71, + "learning_rate": 4.63073459545776e-06, + "loss": 1.3535, + "step": 6793 + }, + { + "epoch": 0.71, + "learning_rate": 4.627647062072902e-06, + "loss": 1.2742, + "step": 6794 + }, + { + "epoch": 0.71, + "learning_rate": 4.624560248445295e-06, + "loss": 1.3429, + "step": 6795 + }, + { + "epoch": 0.71, + "learning_rate": 4.621474154988498e-06, + "loss": 1.3548, + "step": 6796 + }, + { + "epoch": 0.71, + "learning_rate": 4.61838878211597e-06, + "loss": 1.2722, + "step": 6797 + }, + { + "epoch": 0.71, + "learning_rate": 4.6153041302410665e-06, + "loss": 1.3357, + "step": 6798 + }, + { + "epoch": 0.71, + "learning_rate": 4.612220199777053e-06, + "loss": 1.2494, + "step": 6799 + }, + { + "epoch": 0.71, + "learning_rate": 4.609136991137103e-06, + "loss": 1.2792, + "step": 6800 + }, + { + "epoch": 0.71, + "learning_rate": 4.60605450473428e-06, + "loss": 1.2892, + "step": 6801 + }, + { + "epoch": 0.71, + "learning_rate": 4.602972740981562e-06, + "loss": 1.316, + "step": 6802 + }, + { + "epoch": 0.71, + "learning_rate": 4.599891700291822e-06, + "loss": 1.3017, + "step": 6803 + }, + { + "epoch": 0.71, + "learning_rate": 4.5968113830778416e-06, + "loss": 1.3133, + "step": 6804 + }, + { + "epoch": 0.71, + "learning_rate": 4.593731789752311e-06, + "loss": 1.3768, + "step": 6805 + }, + { + "epoch": 0.71, + "learning_rate": 4.590652920727806e-06, + "loss": 1.3259, + "step": 6806 + }, + { + "epoch": 0.71, + "learning_rate": 4.5875747764168214e-06, + "loss": 1.328, + "step": 6807 + }, + { + "epoch": 0.71, + "learning_rate": 4.584497357231752e-06, + "loss": 1.2924, + "step": 6808 + }, + { + "epoch": 0.71, + "learning_rate": 4.581420663584886e-06, + "loss": 1.3347, + "step": 6809 + }, + { + "epoch": 0.71, + "learning_rate": 4.578344695888427e-06, + "loss": 1.3042, + "step": 6810 + }, + { + "epoch": 0.71, + "learning_rate": 4.575269454554477e-06, + "loss": 1.3121, + "step": 6811 + }, + { + "epoch": 0.71, + "learning_rate": 4.572194939995031e-06, + "loss": 1.3471, + "step": 6812 + }, + { + "epoch": 0.71, + "learning_rate": 4.569121152622005e-06, + "loss": 1.4279, + "step": 6813 + }, + { + "epoch": 0.71, + "learning_rate": 4.5660480928471985e-06, + "loss": 1.2902, + "step": 6814 + }, + { + "epoch": 0.71, + "learning_rate": 4.562975761082326e-06, + "loss": 1.0803, + "step": 6815 + }, + { + "epoch": 0.71, + "learning_rate": 4.5599041577390065e-06, + "loss": 1.008, + "step": 6816 + }, + { + "epoch": 0.71, + "learning_rate": 4.556833283228748e-06, + "loss": 1.168, + "step": 6817 + }, + { + "epoch": 0.71, + "learning_rate": 4.553763137962971e-06, + "loss": 1.3092, + "step": 6818 + }, + { + "epoch": 0.72, + "learning_rate": 4.550693722353001e-06, + "loss": 1.364, + "step": 6819 + }, + { + "epoch": 0.72, + "learning_rate": 4.547625036810052e-06, + "loss": 1.3079, + "step": 6820 + }, + { + "epoch": 0.72, + "learning_rate": 4.544557081745259e-06, + "loss": 1.2639, + "step": 6821 + }, + { + "epoch": 0.72, + "learning_rate": 4.541489857569639e-06, + "loss": 1.3586, + "step": 6822 + }, + { + "epoch": 0.72, + "learning_rate": 4.5384233646941275e-06, + "loss": 1.4261, + "step": 6823 + }, + { + "epoch": 0.72, + "learning_rate": 4.535357603529558e-06, + "loss": 1.428, + "step": 6824 + }, + { + "epoch": 0.72, + "learning_rate": 4.532292574486656e-06, + "loss": 1.2541, + "step": 6825 + }, + { + "epoch": 0.72, + "learning_rate": 4.529228277976061e-06, + "loss": 1.2761, + "step": 6826 + }, + { + "epoch": 0.72, + "learning_rate": 4.526164714408314e-06, + "loss": 1.3439, + "step": 6827 + }, + { + "epoch": 0.72, + "learning_rate": 4.523101884193845e-06, + "loss": 1.3585, + "step": 6828 + }, + { + "epoch": 0.72, + "learning_rate": 4.520039787742999e-06, + "loss": 1.4035, + "step": 6829 + }, + { + "epoch": 0.72, + "learning_rate": 4.516978425466023e-06, + "loss": 1.3328, + "step": 6830 + }, + { + "epoch": 0.72, + "learning_rate": 4.5139177977730516e-06, + "loss": 1.2931, + "step": 6831 + }, + { + "epoch": 0.72, + "learning_rate": 4.5108579050741395e-06, + "loss": 1.2515, + "step": 6832 + }, + { + "epoch": 0.72, + "learning_rate": 4.507798747779226e-06, + "loss": 1.3178, + "step": 6833 + }, + { + "epoch": 0.72, + "learning_rate": 4.504740326298163e-06, + "loss": 1.3037, + "step": 6834 + }, + { + "epoch": 0.72, + "learning_rate": 4.501682641040702e-06, + "loss": 1.14, + "step": 6835 + }, + { + "epoch": 0.72, + "learning_rate": 4.4986256924164895e-06, + "loss": 1.2801, + "step": 6836 + }, + { + "epoch": 0.72, + "learning_rate": 4.495569480835081e-06, + "loss": 1.3195, + "step": 6837 + }, + { + "epoch": 0.72, + "learning_rate": 4.492514006705935e-06, + "loss": 1.2949, + "step": 6838 + }, + { + "epoch": 0.72, + "learning_rate": 4.489459270438397e-06, + "loss": 1.3297, + "step": 6839 + }, + { + "epoch": 0.72, + "learning_rate": 4.4864052724417315e-06, + "loss": 1.2127, + "step": 6840 + }, + { + "epoch": 0.72, + "learning_rate": 4.4833520131250894e-06, + "loss": 1.3124, + "step": 6841 + }, + { + "epoch": 0.72, + "learning_rate": 4.480299492897532e-06, + "loss": 1.3056, + "step": 6842 + }, + { + "epoch": 0.72, + "learning_rate": 4.477247712168021e-06, + "loss": 1.2853, + "step": 6843 + }, + { + "epoch": 0.72, + "learning_rate": 4.474196671345411e-06, + "loss": 1.2531, + "step": 6844 + }, + { + "epoch": 0.72, + "learning_rate": 4.471146370838466e-06, + "loss": 1.2712, + "step": 6845 + }, + { + "epoch": 0.72, + "learning_rate": 4.468096811055852e-06, + "loss": 1.3443, + "step": 6846 + }, + { + "epoch": 0.72, + "learning_rate": 4.465047992406124e-06, + "loss": 1.2692, + "step": 6847 + }, + { + "epoch": 0.72, + "learning_rate": 4.461999915297752e-06, + "loss": 1.3937, + "step": 6848 + }, + { + "epoch": 0.72, + "learning_rate": 4.458952580139094e-06, + "loss": 1.2743, + "step": 6849 + }, + { + "epoch": 0.72, + "learning_rate": 4.455905987338418e-06, + "loss": 1.3949, + "step": 6850 + }, + { + "epoch": 0.72, + "learning_rate": 4.452860137303892e-06, + "loss": 1.2578, + "step": 6851 + }, + { + "epoch": 0.72, + "learning_rate": 4.449815030443575e-06, + "loss": 1.3199, + "step": 6852 + }, + { + "epoch": 0.72, + "learning_rate": 4.4467706671654365e-06, + "loss": 1.3199, + "step": 6853 + }, + { + "epoch": 0.72, + "learning_rate": 4.4437270478773464e-06, + "loss": 1.3098, + "step": 6854 + }, + { + "epoch": 0.72, + "learning_rate": 4.440684172987064e-06, + "loss": 1.2888, + "step": 6855 + }, + { + "epoch": 0.72, + "learning_rate": 4.4376420429022615e-06, + "loss": 1.646, + "step": 6856 + }, + { + "epoch": 0.72, + "learning_rate": 4.434600658030508e-06, + "loss": 1.3573, + "step": 6857 + }, + { + "epoch": 0.72, + "learning_rate": 4.431560018779264e-06, + "loss": 1.3748, + "step": 6858 + }, + { + "epoch": 0.72, + "learning_rate": 4.428520125555906e-06, + "loss": 1.358, + "step": 6859 + }, + { + "epoch": 0.72, + "learning_rate": 4.425480978767692e-06, + "loss": 1.2707, + "step": 6860 + }, + { + "epoch": 0.72, + "learning_rate": 4.422442578821795e-06, + "loss": 1.4066, + "step": 6861 + }, + { + "epoch": 0.72, + "learning_rate": 4.4194049261252845e-06, + "loss": 1.3725, + "step": 6862 + }, + { + "epoch": 0.72, + "learning_rate": 4.416368021085122e-06, + "loss": 1.2392, + "step": 6863 + }, + { + "epoch": 0.72, + "learning_rate": 4.413331864108178e-06, + "loss": 1.2917, + "step": 6864 + }, + { + "epoch": 0.72, + "learning_rate": 4.410296455601223e-06, + "loss": 1.2685, + "step": 6865 + }, + { + "epoch": 0.72, + "learning_rate": 4.407261795970916e-06, + "loss": 1.265, + "step": 6866 + }, + { + "epoch": 0.72, + "learning_rate": 4.404227885623832e-06, + "loss": 1.3838, + "step": 6867 + }, + { + "epoch": 0.72, + "learning_rate": 4.4011947249664276e-06, + "loss": 1.3496, + "step": 6868 + }, + { + "epoch": 0.72, + "learning_rate": 4.398162314405075e-06, + "loss": 1.3007, + "step": 6869 + }, + { + "epoch": 0.72, + "learning_rate": 4.39513065434604e-06, + "loss": 1.2934, + "step": 6870 + }, + { + "epoch": 0.72, + "learning_rate": 4.392099745195483e-06, + "loss": 1.559, + "step": 6871 + }, + { + "epoch": 0.72, + "learning_rate": 4.389069587359468e-06, + "loss": 1.346, + "step": 6872 + }, + { + "epoch": 0.72, + "learning_rate": 4.386040181243965e-06, + "loss": 1.2433, + "step": 6873 + }, + { + "epoch": 0.72, + "learning_rate": 4.3830115272548275e-06, + "loss": 1.2938, + "step": 6874 + }, + { + "epoch": 0.72, + "learning_rate": 4.379983625797821e-06, + "loss": 1.3463, + "step": 6875 + }, + { + "epoch": 0.72, + "learning_rate": 4.376956477278612e-06, + "loss": 1.2832, + "step": 6876 + }, + { + "epoch": 0.72, + "learning_rate": 4.37393008210275e-06, + "loss": 1.3693, + "step": 6877 + }, + { + "epoch": 0.72, + "learning_rate": 4.370904440675705e-06, + "loss": 1.2652, + "step": 6878 + }, + { + "epoch": 0.72, + "learning_rate": 4.367879553402826e-06, + "loss": 1.3217, + "step": 6879 + }, + { + "epoch": 0.72, + "learning_rate": 4.364855420689375e-06, + "loss": 1.3519, + "step": 6880 + }, + { + "epoch": 0.72, + "learning_rate": 4.36183204294051e-06, + "loss": 1.3131, + "step": 6881 + }, + { + "epoch": 0.72, + "learning_rate": 4.35880942056128e-06, + "loss": 1.4334, + "step": 6882 + }, + { + "epoch": 0.72, + "learning_rate": 4.3557875539566415e-06, + "loss": 1.259, + "step": 6883 + }, + { + "epoch": 0.72, + "learning_rate": 4.352766443531451e-06, + "loss": 1.2841, + "step": 6884 + }, + { + "epoch": 0.72, + "learning_rate": 4.349746089690453e-06, + "loss": 1.35, + "step": 6885 + }, + { + "epoch": 0.72, + "learning_rate": 4.346726492838304e-06, + "loss": 1.3623, + "step": 6886 + }, + { + "epoch": 0.72, + "learning_rate": 4.343707653379544e-06, + "loss": 1.3729, + "step": 6887 + }, + { + "epoch": 0.72, + "learning_rate": 4.340689571718626e-06, + "loss": 1.2992, + "step": 6888 + }, + { + "epoch": 0.72, + "learning_rate": 4.337672248259898e-06, + "loss": 1.3484, + "step": 6889 + }, + { + "epoch": 0.72, + "learning_rate": 4.334655683407594e-06, + "loss": 1.3347, + "step": 6890 + }, + { + "epoch": 0.72, + "learning_rate": 4.331639877565865e-06, + "loss": 1.2986, + "step": 6891 + }, + { + "epoch": 0.72, + "learning_rate": 4.328624831138751e-06, + "loss": 1.3217, + "step": 6892 + }, + { + "epoch": 0.72, + "learning_rate": 4.325610544530184e-06, + "loss": 1.2834, + "step": 6893 + }, + { + "epoch": 0.72, + "learning_rate": 4.32259701814401e-06, + "loss": 1.3474, + "step": 6894 + }, + { + "epoch": 0.72, + "learning_rate": 4.319584252383956e-06, + "loss": 1.2871, + "step": 6895 + }, + { + "epoch": 0.72, + "learning_rate": 4.316572247653659e-06, + "loss": 1.3534, + "step": 6896 + }, + { + "epoch": 0.72, + "learning_rate": 4.313561004356653e-06, + "loss": 1.4421, + "step": 6897 + }, + { + "epoch": 0.72, + "learning_rate": 4.310550522896359e-06, + "loss": 1.3091, + "step": 6898 + }, + { + "epoch": 0.72, + "learning_rate": 4.30754080367611e-06, + "loss": 1.2565, + "step": 6899 + }, + { + "epoch": 0.72, + "learning_rate": 4.304531847099135e-06, + "loss": 1.5767, + "step": 6900 + }, + { + "epoch": 0.72, + "learning_rate": 4.3015236535685475e-06, + "loss": 1.4257, + "step": 6901 + }, + { + "epoch": 0.72, + "learning_rate": 4.298516223487373e-06, + "loss": 1.362, + "step": 6902 + }, + { + "epoch": 0.72, + "learning_rate": 4.2955095572585336e-06, + "loss": 1.3475, + "step": 6903 + }, + { + "epoch": 0.72, + "learning_rate": 4.292503655284838e-06, + "loss": 1.3223, + "step": 6904 + }, + { + "epoch": 0.72, + "learning_rate": 4.289498517969006e-06, + "loss": 1.3142, + "step": 6905 + }, + { + "epoch": 0.72, + "learning_rate": 4.286494145713644e-06, + "loss": 1.3124, + "step": 6906 + }, + { + "epoch": 0.72, + "learning_rate": 4.283490538921261e-06, + "loss": 1.3636, + "step": 6907 + }, + { + "epoch": 0.72, + "learning_rate": 4.280487697994269e-06, + "loss": 1.347, + "step": 6908 + }, + { + "epoch": 0.72, + "learning_rate": 4.277485623334964e-06, + "loss": 1.2986, + "step": 6909 + }, + { + "epoch": 0.72, + "learning_rate": 4.27448431534555e-06, + "loss": 1.3058, + "step": 6910 + }, + { + "epoch": 0.72, + "learning_rate": 4.271483774428128e-06, + "loss": 1.7858, + "step": 6911 + }, + { + "epoch": 0.72, + "learning_rate": 4.268484000984689e-06, + "loss": 1.3529, + "step": 6912 + }, + { + "epoch": 0.72, + "learning_rate": 4.26548499541713e-06, + "loss": 1.3215, + "step": 6913 + }, + { + "epoch": 0.73, + "learning_rate": 4.262486758127234e-06, + "loss": 1.2914, + "step": 6914 + }, + { + "epoch": 0.73, + "learning_rate": 4.259489289516693e-06, + "loss": 1.4562, + "step": 6915 + }, + { + "epoch": 0.73, + "learning_rate": 4.256492589987092e-06, + "loss": 1.2548, + "step": 6916 + }, + { + "epoch": 0.73, + "learning_rate": 4.253496659939907e-06, + "loss": 1.3047, + "step": 6917 + }, + { + "epoch": 0.73, + "learning_rate": 4.250501499776516e-06, + "loss": 1.4184, + "step": 6918 + }, + { + "epoch": 0.73, + "learning_rate": 4.2475071098982e-06, + "loss": 1.3519, + "step": 6919 + }, + { + "epoch": 0.73, + "learning_rate": 4.2445134907061224e-06, + "loss": 1.3274, + "step": 6920 + }, + { + "epoch": 0.73, + "learning_rate": 4.2415206426013545e-06, + "loss": 1.389, + "step": 6921 + }, + { + "epoch": 0.73, + "learning_rate": 4.238528565984865e-06, + "loss": 1.2929, + "step": 6922 + }, + { + "epoch": 0.73, + "learning_rate": 4.235537261257507e-06, + "loss": 1.3883, + "step": 6923 + }, + { + "epoch": 0.73, + "learning_rate": 4.232546728820047e-06, + "loss": 1.3395, + "step": 6924 + }, + { + "epoch": 0.73, + "learning_rate": 4.229556969073133e-06, + "loss": 1.3534, + "step": 6925 + }, + { + "epoch": 0.73, + "learning_rate": 4.226567982417317e-06, + "loss": 1.4218, + "step": 6926 + }, + { + "epoch": 0.73, + "learning_rate": 4.223579769253052e-06, + "loss": 1.3737, + "step": 6927 + }, + { + "epoch": 0.73, + "learning_rate": 4.220592329980674e-06, + "loss": 1.4805, + "step": 6928 + }, + { + "epoch": 0.73, + "learning_rate": 4.217605665000426e-06, + "loss": 1.2409, + "step": 6929 + }, + { + "epoch": 0.73, + "learning_rate": 4.21461977471245e-06, + "loss": 1.3375, + "step": 6930 + }, + { + "epoch": 0.73, + "learning_rate": 4.211634659516769e-06, + "loss": 1.3535, + "step": 6931 + }, + { + "epoch": 0.73, + "learning_rate": 4.20865031981332e-06, + "loss": 1.2723, + "step": 6932 + }, + { + "epoch": 0.73, + "learning_rate": 4.2056667560019206e-06, + "loss": 1.342, + "step": 6933 + }, + { + "epoch": 0.73, + "learning_rate": 4.202683968482296e-06, + "loss": 1.4075, + "step": 6934 + }, + { + "epoch": 0.73, + "learning_rate": 4.199701957654065e-06, + "loss": 1.3003, + "step": 6935 + }, + { + "epoch": 0.73, + "learning_rate": 4.196720723916735e-06, + "loss": 1.3098, + "step": 6936 + }, + { + "epoch": 0.73, + "learning_rate": 4.193740267669718e-06, + "loss": 1.2386, + "step": 6937 + }, + { + "epoch": 0.73, + "learning_rate": 4.19076058931232e-06, + "loss": 1.3271, + "step": 6938 + }, + { + "epoch": 0.73, + "learning_rate": 4.187781689243737e-06, + "loss": 1.4604, + "step": 6939 + }, + { + "epoch": 0.73, + "learning_rate": 4.184803567863072e-06, + "loss": 1.3496, + "step": 6940 + }, + { + "epoch": 0.73, + "learning_rate": 4.181826225569308e-06, + "loss": 1.3056, + "step": 6941 + }, + { + "epoch": 0.73, + "learning_rate": 4.1788496627613366e-06, + "loss": 1.2886, + "step": 6942 + }, + { + "epoch": 0.73, + "learning_rate": 4.175873879837944e-06, + "loss": 1.282, + "step": 6943 + }, + { + "epoch": 0.73, + "learning_rate": 4.172898877197802e-06, + "loss": 1.2984, + "step": 6944 + }, + { + "epoch": 0.73, + "learning_rate": 4.169924655239488e-06, + "loss": 1.2909, + "step": 6945 + }, + { + "epoch": 0.73, + "learning_rate": 4.166951214361474e-06, + "loss": 1.4015, + "step": 6946 + }, + { + "epoch": 0.73, + "learning_rate": 4.16397855496212e-06, + "loss": 1.3772, + "step": 6947 + }, + { + "epoch": 0.73, + "learning_rate": 4.161006677439687e-06, + "loss": 1.3089, + "step": 6948 + }, + { + "epoch": 0.73, + "learning_rate": 4.1580355821923344e-06, + "loss": 1.3599, + "step": 6949 + }, + { + "epoch": 0.73, + "learning_rate": 4.155065269618107e-06, + "loss": 1.2886, + "step": 6950 + }, + { + "epoch": 0.73, + "learning_rate": 4.152095740114955e-06, + "loss": 1.3071, + "step": 6951 + }, + { + "epoch": 0.73, + "learning_rate": 4.149126994080715e-06, + "loss": 1.3332, + "step": 6952 + }, + { + "epoch": 0.73, + "learning_rate": 4.146159031913123e-06, + "loss": 1.3835, + "step": 6953 + }, + { + "epoch": 0.73, + "learning_rate": 4.1431918540098144e-06, + "loss": 1.3399, + "step": 6954 + }, + { + "epoch": 0.73, + "learning_rate": 4.140225460768309e-06, + "loss": 1.2906, + "step": 6955 + }, + { + "epoch": 0.73, + "learning_rate": 4.137259852586029e-06, + "loss": 1.295, + "step": 6956 + }, + { + "epoch": 0.73, + "learning_rate": 4.134295029860295e-06, + "loss": 1.3371, + "step": 6957 + }, + { + "epoch": 0.73, + "learning_rate": 4.131330992988308e-06, + "loss": 1.4441, + "step": 6958 + }, + { + "epoch": 0.73, + "learning_rate": 4.1283677423671805e-06, + "loss": 1.3257, + "step": 6959 + }, + { + "epoch": 0.73, + "learning_rate": 4.125405278393907e-06, + "loss": 1.3958, + "step": 6960 + }, + { + "epoch": 0.73, + "learning_rate": 4.1224436014653826e-06, + "loss": 1.2856, + "step": 6961 + }, + { + "epoch": 0.73, + "learning_rate": 4.1194827119784e-06, + "loss": 1.2943, + "step": 6962 + }, + { + "epoch": 0.73, + "learning_rate": 4.116522610329636e-06, + "loss": 1.2691, + "step": 6963 + }, + { + "epoch": 0.73, + "learning_rate": 4.11356329691567e-06, + "loss": 1.293, + "step": 6964 + }, + { + "epoch": 0.73, + "learning_rate": 4.11060477213298e-06, + "loss": 1.3136, + "step": 6965 + }, + { + "epoch": 0.73, + "eval_loss": 1.399178147315979, + "eval_runtime": 77.5864, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 6965 + }, + { + "epoch": 0.73, + "learning_rate": 4.1076470363779235e-06, + "loss": 1.2833, + "step": 6966 + }, + { + "epoch": 0.73, + "learning_rate": 4.104690090046765e-06, + "loss": 1.3177, + "step": 6967 + }, + { + "epoch": 0.73, + "learning_rate": 4.101733933535663e-06, + "loss": 1.2623, + "step": 6968 + }, + { + "epoch": 0.73, + "learning_rate": 4.0987785672406585e-06, + "loss": 1.2814, + "step": 6969 + }, + { + "epoch": 0.73, + "learning_rate": 4.0958239915577036e-06, + "loss": 1.3823, + "step": 6970 + }, + { + "epoch": 0.73, + "learning_rate": 4.092870206882627e-06, + "loss": 1.2926, + "step": 6971 + }, + { + "epoch": 0.73, + "learning_rate": 4.089917213611164e-06, + "loss": 1.3324, + "step": 6972 + }, + { + "epoch": 0.73, + "learning_rate": 4.086965012138943e-06, + "loss": 1.3521, + "step": 6973 + }, + { + "epoch": 0.73, + "learning_rate": 4.084013602861476e-06, + "loss": 1.4828, + "step": 6974 + }, + { + "epoch": 0.73, + "learning_rate": 4.0810629861741804e-06, + "loss": 1.3187, + "step": 6975 + }, + { + "epoch": 0.73, + "learning_rate": 4.078113162472366e-06, + "loss": 1.3478, + "step": 6976 + }, + { + "epoch": 0.73, + "learning_rate": 4.075164132151227e-06, + "loss": 1.4256, + "step": 6977 + }, + { + "epoch": 0.73, + "learning_rate": 4.0722158956058635e-06, + "loss": 1.2815, + "step": 6978 + }, + { + "epoch": 0.73, + "learning_rate": 4.069268453231257e-06, + "loss": 1.3031, + "step": 6979 + }, + { + "epoch": 0.73, + "learning_rate": 4.066321805422292e-06, + "loss": 1.2983, + "step": 6980 + }, + { + "epoch": 0.73, + "learning_rate": 4.063375952573748e-06, + "loss": 1.3595, + "step": 6981 + }, + { + "epoch": 0.73, + "learning_rate": 4.060430895080286e-06, + "loss": 1.3119, + "step": 6982 + }, + { + "epoch": 0.73, + "learning_rate": 4.057486633336472e-06, + "loss": 1.328, + "step": 6983 + }, + { + "epoch": 0.73, + "learning_rate": 4.054543167736766e-06, + "loss": 1.232, + "step": 6984 + }, + { + "epoch": 0.73, + "learning_rate": 4.0516004986755064e-06, + "loss": 1.3288, + "step": 6985 + }, + { + "epoch": 0.73, + "learning_rate": 4.048658626546945e-06, + "loss": 1.2916, + "step": 6986 + }, + { + "epoch": 0.73, + "learning_rate": 4.045717551745209e-06, + "loss": 1.2411, + "step": 6987 + }, + { + "epoch": 0.73, + "learning_rate": 4.042777274664331e-06, + "loss": 1.3256, + "step": 6988 + }, + { + "epoch": 0.73, + "learning_rate": 4.039837795698237e-06, + "loss": 1.3455, + "step": 6989 + }, + { + "epoch": 0.73, + "learning_rate": 4.036899115240732e-06, + "loss": 1.3303, + "step": 6990 + }, + { + "epoch": 0.73, + "learning_rate": 4.033961233685529e-06, + "loss": 1.2805, + "step": 6991 + }, + { + "epoch": 0.73, + "learning_rate": 4.031024151426233e-06, + "loss": 1.3958, + "step": 6992 + }, + { + "epoch": 0.73, + "learning_rate": 4.0280878688563275e-06, + "loss": 1.2853, + "step": 6993 + }, + { + "epoch": 0.73, + "learning_rate": 4.0251523863692054e-06, + "loss": 1.2433, + "step": 6994 + }, + { + "epoch": 0.73, + "learning_rate": 4.022217704358148e-06, + "loss": 1.2644, + "step": 6995 + }, + { + "epoch": 0.73, + "learning_rate": 4.0192838232163204e-06, + "loss": 1.3218, + "step": 6996 + }, + { + "epoch": 0.73, + "learning_rate": 4.016350743336795e-06, + "loss": 1.2973, + "step": 6997 + }, + { + "epoch": 0.73, + "learning_rate": 4.013418465112521e-06, + "loss": 1.3209, + "step": 6998 + }, + { + "epoch": 0.73, + "learning_rate": 4.010486988936353e-06, + "loss": 1.2855, + "step": 6999 + }, + { + "epoch": 0.73, + "learning_rate": 4.007556315201035e-06, + "loss": 1.2381, + "step": 7000 + }, + { + "epoch": 0.73, + "learning_rate": 4.004626444299198e-06, + "loss": 1.3558, + "step": 7001 + }, + { + "epoch": 0.73, + "learning_rate": 4.001697376623371e-06, + "loss": 1.3139, + "step": 7002 + }, + { + "epoch": 0.73, + "learning_rate": 3.998769112565978e-06, + "loss": 1.3582, + "step": 7003 + }, + { + "epoch": 0.73, + "learning_rate": 3.9958416525193225e-06, + "loss": 1.2684, + "step": 7004 + }, + { + "epoch": 0.73, + "learning_rate": 3.992914996875618e-06, + "loss": 1.2915, + "step": 7005 + }, + { + "epoch": 0.73, + "learning_rate": 3.9899891460269536e-06, + "loss": 1.3205, + "step": 7006 + }, + { + "epoch": 0.73, + "learning_rate": 3.987064100365321e-06, + "loss": 1.2966, + "step": 7007 + }, + { + "epoch": 0.73, + "learning_rate": 3.984139860282606e-06, + "loss": 1.2691, + "step": 7008 + }, + { + "epoch": 0.74, + "learning_rate": 3.981216426170572e-06, + "loss": 1.3421, + "step": 7009 + }, + { + "epoch": 0.74, + "learning_rate": 3.97829379842089e-06, + "loss": 1.3034, + "step": 7010 + }, + { + "epoch": 0.74, + "learning_rate": 3.9753719774251195e-06, + "loss": 1.2863, + "step": 7011 + }, + { + "epoch": 0.74, + "learning_rate": 3.972450963574703e-06, + "loss": 1.3812, + "step": 7012 + }, + { + "epoch": 0.74, + "learning_rate": 3.969530757260986e-06, + "loss": 1.334, + "step": 7013 + }, + { + "epoch": 0.74, + "learning_rate": 3.966611358875201e-06, + "loss": 1.3289, + "step": 7014 + }, + { + "epoch": 0.74, + "learning_rate": 3.963692768808468e-06, + "loss": 1.395, + "step": 7015 + }, + { + "epoch": 0.74, + "learning_rate": 3.960774987451811e-06, + "loss": 1.3298, + "step": 7016 + }, + { + "epoch": 0.74, + "learning_rate": 3.957858015196128e-06, + "loss": 1.3304, + "step": 7017 + }, + { + "epoch": 0.74, + "learning_rate": 3.954941852432224e-06, + "loss": 1.301, + "step": 7018 + }, + { + "epoch": 0.74, + "learning_rate": 3.952026499550791e-06, + "loss": 1.3568, + "step": 7019 + }, + { + "epoch": 0.74, + "learning_rate": 3.949111956942406e-06, + "loss": 1.4464, + "step": 7020 + }, + { + "epoch": 0.74, + "learning_rate": 3.946198224997548e-06, + "loss": 1.4417, + "step": 7021 + }, + { + "epoch": 0.74, + "learning_rate": 3.943285304106583e-06, + "loss": 1.3979, + "step": 7022 + }, + { + "epoch": 0.74, + "learning_rate": 3.940373194659761e-06, + "loss": 1.2943, + "step": 7023 + }, + { + "epoch": 0.74, + "learning_rate": 3.937461897047239e-06, + "loss": 1.2571, + "step": 7024 + }, + { + "epoch": 0.74, + "learning_rate": 3.9345514116590454e-06, + "loss": 1.3433, + "step": 7025 + }, + { + "epoch": 0.74, + "learning_rate": 3.931641738885117e-06, + "loss": 1.4203, + "step": 7026 + }, + { + "epoch": 0.74, + "learning_rate": 3.9287328791152775e-06, + "loss": 1.3657, + "step": 7027 + }, + { + "epoch": 0.74, + "learning_rate": 3.925824832739234e-06, + "loss": 1.3954, + "step": 7028 + }, + { + "epoch": 0.74, + "learning_rate": 3.92291760014659e-06, + "loss": 1.2847, + "step": 7029 + }, + { + "epoch": 0.74, + "learning_rate": 3.920011181726846e-06, + "loss": 1.2776, + "step": 7030 + }, + { + "epoch": 0.74, + "learning_rate": 3.91710557786938e-06, + "loss": 1.3391, + "step": 7031 + }, + { + "epoch": 0.74, + "learning_rate": 3.914200788963472e-06, + "loss": 1.2935, + "step": 7032 + }, + { + "epoch": 0.74, + "learning_rate": 3.911296815398291e-06, + "loss": 1.3775, + "step": 7033 + }, + { + "epoch": 0.74, + "learning_rate": 3.90839365756289e-06, + "loss": 1.3652, + "step": 7034 + }, + { + "epoch": 0.74, + "learning_rate": 3.905491315846224e-06, + "loss": 1.2902, + "step": 7035 + }, + { + "epoch": 0.74, + "learning_rate": 3.902589790637125e-06, + "loss": 1.2859, + "step": 7036 + }, + { + "epoch": 0.74, + "learning_rate": 3.899689082324325e-06, + "loss": 1.4019, + "step": 7037 + }, + { + "epoch": 0.74, + "learning_rate": 3.89678919129645e-06, + "loss": 1.299, + "step": 7038 + }, + { + "epoch": 0.74, + "learning_rate": 3.893890117942003e-06, + "loss": 1.275, + "step": 7039 + }, + { + "epoch": 0.74, + "learning_rate": 3.890991862649388e-06, + "loss": 1.2593, + "step": 7040 + }, + { + "epoch": 0.74, + "learning_rate": 3.888094425806902e-06, + "loss": 1.2932, + "step": 7041 + }, + { + "epoch": 0.74, + "learning_rate": 3.885197807802719e-06, + "loss": 1.3038, + "step": 7042 + }, + { + "epoch": 0.74, + "learning_rate": 3.882302009024917e-06, + "loss": 1.285, + "step": 7043 + }, + { + "epoch": 0.74, + "learning_rate": 3.879407029861455e-06, + "loss": 1.4116, + "step": 7044 + }, + { + "epoch": 0.74, + "learning_rate": 3.876512870700187e-06, + "loss": 1.3823, + "step": 7045 + }, + { + "epoch": 0.74, + "learning_rate": 3.873619531928858e-06, + "loss": 1.2803, + "step": 7046 + }, + { + "epoch": 0.74, + "learning_rate": 3.870727013935099e-06, + "loss": 1.3287, + "step": 7047 + }, + { + "epoch": 0.74, + "learning_rate": 3.867835317106432e-06, + "loss": 1.3919, + "step": 7048 + }, + { + "epoch": 0.74, + "learning_rate": 3.864944441830275e-06, + "loss": 1.3967, + "step": 7049 + }, + { + "epoch": 0.74, + "learning_rate": 3.862054388493924e-06, + "loss": 1.2749, + "step": 7050 + }, + { + "epoch": 0.74, + "learning_rate": 3.85916515748458e-06, + "loss": 1.3408, + "step": 7051 + }, + { + "epoch": 0.74, + "learning_rate": 3.856276749189317e-06, + "loss": 1.3143, + "step": 7052 + }, + { + "epoch": 0.74, + "learning_rate": 3.853389163995111e-06, + "loss": 1.3661, + "step": 7053 + }, + { + "epoch": 0.74, + "learning_rate": 3.8505024022888305e-06, + "loss": 1.3094, + "step": 7054 + }, + { + "epoch": 0.74, + "learning_rate": 3.847616464457216e-06, + "loss": 1.2736, + "step": 7055 + }, + { + "epoch": 0.74, + "learning_rate": 3.844731350886917e-06, + "loss": 1.3628, + "step": 7056 + }, + { + "epoch": 0.74, + "learning_rate": 3.841847061964465e-06, + "loss": 1.2706, + "step": 7057 + }, + { + "epoch": 0.74, + "learning_rate": 3.838963598076275e-06, + "loss": 1.2566, + "step": 7058 + }, + { + "epoch": 0.74, + "learning_rate": 3.83608095960866e-06, + "loss": 1.2415, + "step": 7059 + }, + { + "epoch": 0.74, + "learning_rate": 3.833199146947823e-06, + "loss": 1.2748, + "step": 7060 + }, + { + "epoch": 0.74, + "learning_rate": 3.830318160479847e-06, + "loss": 1.4672, + "step": 7061 + }, + { + "epoch": 0.74, + "learning_rate": 3.827438000590714e-06, + "loss": 1.2907, + "step": 7062 + }, + { + "epoch": 0.74, + "learning_rate": 3.824558667666288e-06, + "loss": 1.3477, + "step": 7063 + }, + { + "epoch": 0.74, + "learning_rate": 3.821680162092328e-06, + "loss": 1.1135, + "step": 7064 + }, + { + "epoch": 0.74, + "learning_rate": 3.8188024842544825e-06, + "loss": 1.3724, + "step": 7065 + }, + { + "epoch": 0.74, + "learning_rate": 3.81592563453828e-06, + "loss": 1.3854, + "step": 7066 + }, + { + "epoch": 0.74, + "learning_rate": 3.8130496133291473e-06, + "loss": 1.3074, + "step": 7067 + }, + { + "epoch": 0.74, + "learning_rate": 3.8101744210124012e-06, + "loss": 1.4434, + "step": 7068 + }, + { + "epoch": 0.74, + "learning_rate": 3.807300057973238e-06, + "loss": 1.2754, + "step": 7069 + }, + { + "epoch": 0.74, + "learning_rate": 3.804426524596754e-06, + "loss": 1.3654, + "step": 7070 + }, + { + "epoch": 0.74, + "learning_rate": 3.8015538212679214e-06, + "loss": 1.2616, + "step": 7071 + }, + { + "epoch": 0.74, + "learning_rate": 3.798681948371613e-06, + "loss": 1.2939, + "step": 7072 + }, + { + "epoch": 0.74, + "learning_rate": 3.7958109062925894e-06, + "loss": 1.2787, + "step": 7073 + }, + { + "epoch": 0.74, + "learning_rate": 3.792940695415489e-06, + "loss": 1.2953, + "step": 7074 + }, + { + "epoch": 0.74, + "learning_rate": 3.7900713161248515e-06, + "loss": 1.2714, + "step": 7075 + }, + { + "epoch": 0.74, + "learning_rate": 3.7872027688051004e-06, + "loss": 1.3085, + "step": 7076 + }, + { + "epoch": 0.74, + "learning_rate": 3.7843350538405433e-06, + "loss": 1.311, + "step": 7077 + }, + { + "epoch": 0.74, + "learning_rate": 3.781468171615382e-06, + "loss": 1.3367, + "step": 7078 + }, + { + "epoch": 0.74, + "learning_rate": 3.7786021225137102e-06, + "loss": 1.2768, + "step": 7079 + }, + { + "epoch": 0.74, + "learning_rate": 3.775736906919496e-06, + "loss": 1.2828, + "step": 7080 + }, + { + "epoch": 0.74, + "learning_rate": 3.772872525216613e-06, + "loss": 1.3682, + "step": 7081 + }, + { + "epoch": 0.74, + "learning_rate": 3.7700089777888072e-06, + "loss": 1.3906, + "step": 7082 + }, + { + "epoch": 0.74, + "learning_rate": 3.767146265019723e-06, + "loss": 1.2712, + "step": 7083 + }, + { + "epoch": 0.74, + "learning_rate": 3.764284387292896e-06, + "loss": 1.3405, + "step": 7084 + }, + { + "epoch": 0.74, + "learning_rate": 3.761423344991736e-06, + "loss": 1.3941, + "step": 7085 + }, + { + "epoch": 0.74, + "learning_rate": 3.7585631384995523e-06, + "loss": 1.3463, + "step": 7086 + }, + { + "epoch": 0.74, + "learning_rate": 3.7557037681995423e-06, + "loss": 1.2771, + "step": 7087 + }, + { + "epoch": 0.74, + "learning_rate": 3.7528452344747834e-06, + "loss": 1.2706, + "step": 7088 + }, + { + "epoch": 0.74, + "learning_rate": 3.7499875377082497e-06, + "loss": 1.2672, + "step": 7089 + }, + { + "epoch": 0.74, + "learning_rate": 3.7471306782827944e-06, + "loss": 1.2638, + "step": 7090 + }, + { + "epoch": 0.74, + "learning_rate": 3.744274656581166e-06, + "loss": 1.3417, + "step": 7091 + }, + { + "epoch": 0.74, + "learning_rate": 3.7414194729860008e-06, + "loss": 1.278, + "step": 7092 + }, + { + "epoch": 0.74, + "learning_rate": 3.738565127879814e-06, + "loss": 1.2753, + "step": 7093 + }, + { + "epoch": 0.74, + "learning_rate": 3.7357116216450183e-06, + "loss": 1.2989, + "step": 7094 + }, + { + "epoch": 0.74, + "learning_rate": 3.7328589546639127e-06, + "loss": 1.263, + "step": 7095 + }, + { + "epoch": 0.74, + "learning_rate": 3.7300071273186745e-06, + "loss": 1.3534, + "step": 7096 + }, + { + "epoch": 0.74, + "learning_rate": 3.7271561399913825e-06, + "loss": 1.2565, + "step": 7097 + }, + { + "epoch": 0.74, + "learning_rate": 3.724305993063989e-06, + "loss": 1.3233, + "step": 7098 + }, + { + "epoch": 0.74, + "learning_rate": 3.7214566869183443e-06, + "loss": 1.3179, + "step": 7099 + }, + { + "epoch": 0.74, + "learning_rate": 3.718608221936184e-06, + "loss": 1.2749, + "step": 7100 + }, + { + "epoch": 0.74, + "learning_rate": 3.715760598499124e-06, + "loss": 1.3106, + "step": 7101 + }, + { + "epoch": 0.74, + "learning_rate": 3.712913816988675e-06, + "loss": 1.3115, + "step": 7102 + }, + { + "epoch": 0.74, + "learning_rate": 3.7100678777862364e-06, + "loss": 1.2798, + "step": 7103 + }, + { + "epoch": 0.74, + "learning_rate": 3.7072227812730853e-06, + "loss": 1.3964, + "step": 7104 + }, + { + "epoch": 0.75, + "learning_rate": 3.7043785278303923e-06, + "loss": 1.4034, + "step": 7105 + }, + { + "epoch": 0.75, + "learning_rate": 3.70153511783922e-06, + "loss": 1.3244, + "step": 7106 + }, + { + "epoch": 0.75, + "learning_rate": 3.698692551680505e-06, + "loss": 1.3283, + "step": 7107 + }, + { + "epoch": 0.75, + "learning_rate": 3.6958508297350847e-06, + "loss": 1.3567, + "step": 7108 + }, + { + "epoch": 0.75, + "learning_rate": 3.6930099523836692e-06, + "loss": 1.3178, + "step": 7109 + }, + { + "epoch": 0.75, + "learning_rate": 3.6901699200068673e-06, + "loss": 1.2697, + "step": 7110 + }, + { + "epoch": 0.75, + "learning_rate": 3.687330732985175e-06, + "loss": 1.2501, + "step": 7111 + }, + { + "epoch": 0.75, + "learning_rate": 3.6844923916989607e-06, + "loss": 1.2772, + "step": 7112 + }, + { + "epoch": 0.75, + "learning_rate": 3.681654896528495e-06, + "loss": 1.2845, + "step": 7113 + }, + { + "epoch": 0.75, + "learning_rate": 3.6788182478539312e-06, + "loss": 1.3151, + "step": 7114 + }, + { + "epoch": 0.75, + "learning_rate": 3.6759824460553016e-06, + "loss": 1.4925, + "step": 7115 + }, + { + "epoch": 0.75, + "learning_rate": 3.673147491512539e-06, + "loss": 1.2892, + "step": 7116 + }, + { + "epoch": 0.75, + "learning_rate": 3.670313384605444e-06, + "loss": 1.2906, + "step": 7117 + }, + { + "epoch": 0.75, + "learning_rate": 3.6674801257137195e-06, + "loss": 1.3927, + "step": 7118 + }, + { + "epoch": 0.75, + "learning_rate": 3.6646477152169522e-06, + "loss": 1.4001, + "step": 7119 + }, + { + "epoch": 0.75, + "learning_rate": 3.6618161534946074e-06, + "loss": 1.3363, + "step": 7120 + }, + { + "epoch": 0.75, + "learning_rate": 3.658985440926044e-06, + "loss": 1.3297, + "step": 7121 + }, + { + "epoch": 0.75, + "learning_rate": 3.656155577890507e-06, + "loss": 1.3029, + "step": 7122 + }, + { + "epoch": 0.75, + "learning_rate": 3.653326564767119e-06, + "loss": 1.3452, + "step": 7123 + }, + { + "epoch": 0.75, + "learning_rate": 3.6504984019348987e-06, + "loss": 1.3246, + "step": 7124 + }, + { + "epoch": 0.75, + "learning_rate": 3.647671089772752e-06, + "loss": 1.3285, + "step": 7125 + }, + { + "epoch": 0.75, + "learning_rate": 3.6448446286594574e-06, + "loss": 1.3127, + "step": 7126 + }, + { + "epoch": 0.75, + "learning_rate": 3.6420190189736946e-06, + "loss": 1.3224, + "step": 7127 + }, + { + "epoch": 0.75, + "learning_rate": 3.6391942610940178e-06, + "loss": 1.3086, + "step": 7128 + }, + { + "epoch": 0.75, + "learning_rate": 3.6363703553988748e-06, + "loss": 1.3741, + "step": 7129 + }, + { + "epoch": 0.75, + "learning_rate": 3.633547302266599e-06, + "loss": 1.3192, + "step": 7130 + }, + { + "epoch": 0.75, + "learning_rate": 3.6307251020754e-06, + "loss": 1.3032, + "step": 7131 + }, + { + "epoch": 0.75, + "learning_rate": 3.6279037552033847e-06, + "loss": 1.2642, + "step": 7132 + }, + { + "epoch": 0.75, + "learning_rate": 3.6250832620285436e-06, + "loss": 1.3948, + "step": 7133 + }, + { + "epoch": 0.75, + "learning_rate": 3.6222636229287445e-06, + "loss": 1.3542, + "step": 7134 + }, + { + "epoch": 0.75, + "learning_rate": 3.6194448382817526e-06, + "loss": 1.3028, + "step": 7135 + }, + { + "epoch": 0.75, + "learning_rate": 3.616626908465205e-06, + "loss": 1.3017, + "step": 7136 + }, + { + "epoch": 0.75, + "learning_rate": 3.613809833856636e-06, + "loss": 1.3072, + "step": 7137 + }, + { + "epoch": 0.75, + "learning_rate": 3.6109936148334666e-06, + "loss": 1.3065, + "step": 7138 + }, + { + "epoch": 0.75, + "learning_rate": 3.608178251772988e-06, + "loss": 1.4268, + "step": 7139 + }, + { + "epoch": 0.75, + "learning_rate": 3.6053637450523914e-06, + "loss": 1.301, + "step": 7140 + }, + { + "epoch": 0.75, + "learning_rate": 3.6025500950487514e-06, + "loss": 1.2873, + "step": 7141 + }, + { + "epoch": 0.75, + "learning_rate": 3.599737302139018e-06, + "loss": 1.2831, + "step": 7142 + }, + { + "epoch": 0.75, + "learning_rate": 3.5969253667000403e-06, + "loss": 1.5125, + "step": 7143 + }, + { + "epoch": 0.75, + "learning_rate": 3.594114289108538e-06, + "loss": 1.3643, + "step": 7144 + }, + { + "epoch": 0.75, + "learning_rate": 3.5913040697411272e-06, + "loss": 1.3157, + "step": 7145 + }, + { + "epoch": 0.75, + "learning_rate": 3.5884947089743084e-06, + "loss": 1.2687, + "step": 7146 + }, + { + "epoch": 0.75, + "learning_rate": 3.585686207184458e-06, + "loss": 1.3227, + "step": 7147 + }, + { + "epoch": 0.75, + "learning_rate": 3.5828785647478435e-06, + "loss": 1.2745, + "step": 7148 + }, + { + "epoch": 0.75, + "learning_rate": 3.5800717820406226e-06, + "loss": 1.332, + "step": 7149 + }, + { + "epoch": 0.75, + "learning_rate": 3.5772658594388253e-06, + "loss": 1.2863, + "step": 7150 + }, + { + "epoch": 0.75, + "learning_rate": 3.5744607973183766e-06, + "loss": 1.3791, + "step": 7151 + }, + { + "epoch": 0.75, + "learning_rate": 3.5716565960550844e-06, + "loss": 1.2781, + "step": 7152 + }, + { + "epoch": 0.75, + "learning_rate": 3.5688532560246348e-06, + "loss": 1.252, + "step": 7153 + }, + { + "epoch": 0.75, + "learning_rate": 3.5660507776026086e-06, + "loss": 1.3158, + "step": 7154 + }, + { + "epoch": 0.75, + "learning_rate": 3.5632491611644603e-06, + "loss": 1.3241, + "step": 7155 + }, + { + "epoch": 0.75, + "learning_rate": 3.5604484070855382e-06, + "loss": 1.2572, + "step": 7156 + }, + { + "epoch": 0.75, + "learning_rate": 3.5576485157410733e-06, + "loss": 1.3734, + "step": 7157 + }, + { + "epoch": 0.75, + "learning_rate": 3.5548494875061724e-06, + "loss": 1.3253, + "step": 7158 + }, + { + "epoch": 0.75, + "learning_rate": 3.5520513227558385e-06, + "loss": 1.2659, + "step": 7159 + }, + { + "epoch": 0.75, + "learning_rate": 3.5492540218649553e-06, + "loss": 1.3149, + "step": 7160 + }, + { + "epoch": 0.75, + "learning_rate": 3.546457585208283e-06, + "loss": 1.3413, + "step": 7161 + }, + { + "epoch": 0.75, + "learning_rate": 3.5436620131604803e-06, + "loss": 1.2846, + "step": 7162 + }, + { + "epoch": 0.75, + "learning_rate": 3.540867306096073e-06, + "loss": 1.3239, + "step": 7163 + }, + { + "epoch": 0.75, + "learning_rate": 3.5380734643894856e-06, + "loss": 1.3137, + "step": 7164 + }, + { + "epoch": 0.75, + "eval_loss": 1.397520899772644, + "eval_runtime": 77.542, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 7164 + }, + { + "epoch": 0.75, + "learning_rate": 3.535280488415024e-06, + "loss": 1.414, + "step": 7165 + }, + { + "epoch": 0.75, + "learning_rate": 3.5324883785468665e-06, + "loss": 1.2708, + "step": 7166 + }, + { + "epoch": 0.75, + "learning_rate": 3.529697135159089e-06, + "loss": 1.2975, + "step": 7167 + }, + { + "epoch": 0.75, + "learning_rate": 3.526906758625651e-06, + "loss": 1.3723, + "step": 7168 + }, + { + "epoch": 0.75, + "learning_rate": 3.5241172493203822e-06, + "loss": 1.4105, + "step": 7169 + }, + { + "epoch": 0.75, + "learning_rate": 3.5213286076170107e-06, + "loss": 1.2592, + "step": 7170 + }, + { + "epoch": 0.75, + "learning_rate": 3.5185408338891437e-06, + "loss": 1.3361, + "step": 7171 + }, + { + "epoch": 0.75, + "learning_rate": 3.515753928510267e-06, + "loss": 1.2591, + "step": 7172 + }, + { + "epoch": 0.75, + "learning_rate": 3.512967891853759e-06, + "loss": 1.2938, + "step": 7173 + }, + { + "epoch": 0.75, + "learning_rate": 3.510182724292872e-06, + "loss": 1.4116, + "step": 7174 + }, + { + "epoch": 0.75, + "learning_rate": 3.5073984262007486e-06, + "loss": 1.3968, + "step": 7175 + }, + { + "epoch": 0.75, + "learning_rate": 3.5046149979504184e-06, + "loss": 1.31, + "step": 7176 + }, + { + "epoch": 0.75, + "learning_rate": 3.5018324399147817e-06, + "loss": 1.2966, + "step": 7177 + }, + { + "epoch": 0.75, + "learning_rate": 3.4990507524666327e-06, + "loss": 1.3431, + "step": 7178 + }, + { + "epoch": 0.75, + "learning_rate": 3.49626993597865e-06, + "loss": 1.3227, + "step": 7179 + }, + { + "epoch": 0.75, + "learning_rate": 3.4934899908233834e-06, + "loss": 1.201, + "step": 7180 + }, + { + "epoch": 0.75, + "learning_rate": 3.490710917373283e-06, + "loss": 1.3003, + "step": 7181 + }, + { + "epoch": 0.75, + "learning_rate": 3.487932716000666e-06, + "loss": 1.2879, + "step": 7182 + }, + { + "epoch": 0.75, + "learning_rate": 3.485155387077742e-06, + "loss": 1.2742, + "step": 7183 + }, + { + "epoch": 0.75, + "learning_rate": 3.4823789309766065e-06, + "loss": 1.2972, + "step": 7184 + }, + { + "epoch": 0.75, + "learning_rate": 3.479603348069226e-06, + "loss": 1.3763, + "step": 7185 + }, + { + "epoch": 0.75, + "learning_rate": 3.4768286387274597e-06, + "loss": 1.4653, + "step": 7186 + }, + { + "epoch": 0.75, + "learning_rate": 3.4740548033230524e-06, + "loss": 1.3534, + "step": 7187 + }, + { + "epoch": 0.75, + "learning_rate": 3.4712818422276207e-06, + "loss": 1.3917, + "step": 7188 + }, + { + "epoch": 0.75, + "learning_rate": 3.4685097558126733e-06, + "loss": 1.306, + "step": 7189 + }, + { + "epoch": 0.75, + "learning_rate": 3.465738544449596e-06, + "loss": 1.4628, + "step": 7190 + }, + { + "epoch": 0.75, + "learning_rate": 3.4629682085096606e-06, + "loss": 1.3916, + "step": 7191 + }, + { + "epoch": 0.75, + "learning_rate": 3.4601987483640243e-06, + "loss": 1.3348, + "step": 7192 + }, + { + "epoch": 0.75, + "learning_rate": 3.457430164383718e-06, + "loss": 1.4771, + "step": 7193 + }, + { + "epoch": 0.75, + "learning_rate": 3.4546624569396635e-06, + "loss": 1.5004, + "step": 7194 + }, + { + "epoch": 0.75, + "learning_rate": 3.451895626402667e-06, + "loss": 1.279, + "step": 7195 + }, + { + "epoch": 0.75, + "learning_rate": 3.4491296731434053e-06, + "loss": 1.3263, + "step": 7196 + }, + { + "epoch": 0.75, + "learning_rate": 3.4463645975324466e-06, + "loss": 1.2449, + "step": 7197 + }, + { + "epoch": 0.75, + "learning_rate": 3.4436003999402466e-06, + "loss": 1.2743, + "step": 7198 + }, + { + "epoch": 0.75, + "learning_rate": 3.4408370807371283e-06, + "loss": 1.3127, + "step": 7199 + }, + { + "epoch": 0.76, + "learning_rate": 3.438074640293312e-06, + "loss": 1.2996, + "step": 7200 + }, + { + "epoch": 0.76, + "learning_rate": 3.435313078978887e-06, + "loss": 1.3114, + "step": 7201 + }, + { + "epoch": 0.76, + "learning_rate": 3.432552397163835e-06, + "loss": 1.2574, + "step": 7202 + }, + { + "epoch": 0.76, + "learning_rate": 3.42979259521802e-06, + "loss": 1.2605, + "step": 7203 + }, + { + "epoch": 0.76, + "learning_rate": 3.4270336735111785e-06, + "loss": 1.2578, + "step": 7204 + }, + { + "epoch": 0.76, + "learning_rate": 3.424275632412938e-06, + "loss": 1.3297, + "step": 7205 + }, + { + "epoch": 0.76, + "learning_rate": 3.4215184722928073e-06, + "loss": 1.2353, + "step": 7206 + }, + { + "epoch": 0.76, + "learning_rate": 3.4187621935201707e-06, + "loss": 1.288, + "step": 7207 + }, + { + "epoch": 0.76, + "learning_rate": 3.416006796464304e-06, + "loss": 1.2947, + "step": 7208 + }, + { + "epoch": 0.76, + "learning_rate": 3.4132522814943513e-06, + "loss": 1.4208, + "step": 7209 + }, + { + "epoch": 0.76, + "learning_rate": 3.4104986489793534e-06, + "loss": 1.3273, + "step": 7210 + }, + { + "epoch": 0.76, + "learning_rate": 3.4077458992882285e-06, + "loss": 1.274, + "step": 7211 + }, + { + "epoch": 0.76, + "learning_rate": 3.404994032789766e-06, + "loss": 1.2782, + "step": 7212 + }, + { + "epoch": 0.76, + "learning_rate": 3.4022430498526505e-06, + "loss": 1.3513, + "step": 7213 + }, + { + "epoch": 0.76, + "learning_rate": 3.3994929508454455e-06, + "loss": 1.2843, + "step": 7214 + }, + { + "epoch": 0.76, + "learning_rate": 3.3967437361365873e-06, + "loss": 1.2764, + "step": 7215 + }, + { + "epoch": 0.76, + "learning_rate": 3.3939954060944036e-06, + "loss": 1.2786, + "step": 7216 + }, + { + "epoch": 0.76, + "learning_rate": 3.391247961087103e-06, + "loss": 1.2927, + "step": 7217 + }, + { + "epoch": 0.76, + "learning_rate": 3.3885014014827657e-06, + "loss": 1.3735, + "step": 7218 + }, + { + "epoch": 0.76, + "learning_rate": 3.385755727649367e-06, + "loss": 1.3065, + "step": 7219 + }, + { + "epoch": 0.76, + "learning_rate": 3.3830109399547506e-06, + "loss": 1.2463, + "step": 7220 + }, + { + "epoch": 0.76, + "learning_rate": 3.3802670387666492e-06, + "loss": 1.2496, + "step": 7221 + }, + { + "epoch": 0.76, + "learning_rate": 3.3775240244526796e-06, + "loss": 1.2807, + "step": 7222 + }, + { + "epoch": 0.76, + "learning_rate": 3.3747818973803294e-06, + "loss": 1.313, + "step": 7223 + }, + { + "epoch": 0.76, + "learning_rate": 3.372040657916974e-06, + "loss": 1.3557, + "step": 7224 + }, + { + "epoch": 0.76, + "learning_rate": 3.3693003064298744e-06, + "loss": 1.3705, + "step": 7225 + }, + { + "epoch": 0.76, + "learning_rate": 3.366560843286161e-06, + "loss": 1.3763, + "step": 7226 + }, + { + "epoch": 0.76, + "learning_rate": 3.3638222688528565e-06, + "loss": 1.3252, + "step": 7227 + }, + { + "epoch": 0.76, + "learning_rate": 3.361084583496853e-06, + "loss": 1.2635, + "step": 7228 + }, + { + "epoch": 0.76, + "learning_rate": 3.3583477875849346e-06, + "loss": 1.3084, + "step": 7229 + }, + { + "epoch": 0.76, + "learning_rate": 3.3556118814837646e-06, + "loss": 1.3347, + "step": 7230 + }, + { + "epoch": 0.76, + "learning_rate": 3.3528768655598764e-06, + "loss": 1.3937, + "step": 7231 + }, + { + "epoch": 0.76, + "learning_rate": 3.350142740179696e-06, + "loss": 1.3251, + "step": 7232 + }, + { + "epoch": 0.76, + "learning_rate": 3.347409505709529e-06, + "loss": 1.3654, + "step": 7233 + }, + { + "epoch": 0.76, + "learning_rate": 3.344677162515553e-06, + "loss": 1.3864, + "step": 7234 + }, + { + "epoch": 0.76, + "learning_rate": 3.3419457109638377e-06, + "loss": 1.3142, + "step": 7235 + }, + { + "epoch": 0.76, + "learning_rate": 3.3392151514203195e-06, + "loss": 1.3557, + "step": 7236 + }, + { + "epoch": 0.76, + "learning_rate": 3.3364854842508276e-06, + "loss": 1.3093, + "step": 7237 + }, + { + "epoch": 0.76, + "learning_rate": 3.333756709821072e-06, + "loss": 1.3763, + "step": 7238 + }, + { + "epoch": 0.76, + "learning_rate": 3.3310288284966297e-06, + "loss": 1.2943, + "step": 7239 + }, + { + "epoch": 0.76, + "learning_rate": 3.3283018406429703e-06, + "loss": 1.473, + "step": 7240 + }, + { + "epoch": 0.76, + "learning_rate": 3.3255757466254448e-06, + "loss": 1.2501, + "step": 7241 + }, + { + "epoch": 0.76, + "learning_rate": 3.322850546809271e-06, + "loss": 1.2893, + "step": 7242 + }, + { + "epoch": 0.76, + "learning_rate": 3.3201262415595614e-06, + "loss": 1.2995, + "step": 7243 + }, + { + "epoch": 0.76, + "learning_rate": 3.3174028312413044e-06, + "loss": 1.2985, + "step": 7244 + }, + { + "epoch": 0.76, + "learning_rate": 3.31468031621936e-06, + "loss": 1.2868, + "step": 7245 + }, + { + "epoch": 0.76, + "learning_rate": 3.311958696858484e-06, + "loss": 1.2467, + "step": 7246 + }, + { + "epoch": 0.76, + "learning_rate": 3.309237973523295e-06, + "loss": 1.2303, + "step": 7247 + }, + { + "epoch": 0.76, + "learning_rate": 3.3065181465783045e-06, + "loss": 1.3172, + "step": 7248 + }, + { + "epoch": 0.76, + "learning_rate": 3.303799216387902e-06, + "loss": 1.2003, + "step": 7249 + }, + { + "epoch": 0.76, + "learning_rate": 3.3010811833163482e-06, + "loss": 1.2931, + "step": 7250 + }, + { + "epoch": 0.76, + "learning_rate": 3.2983640477277925e-06, + "loss": 1.3135, + "step": 7251 + }, + { + "epoch": 0.76, + "learning_rate": 3.2956478099862644e-06, + "loss": 1.2711, + "step": 7252 + }, + { + "epoch": 0.76, + "learning_rate": 3.292932470455663e-06, + "loss": 1.291, + "step": 7253 + }, + { + "epoch": 0.76, + "learning_rate": 3.2902180294997832e-06, + "loss": 1.2838, + "step": 7254 + }, + { + "epoch": 0.76, + "learning_rate": 3.2875044874822804e-06, + "loss": 1.2381, + "step": 7255 + }, + { + "epoch": 0.76, + "learning_rate": 3.284791844766705e-06, + "loss": 1.2966, + "step": 7256 + }, + { + "epoch": 0.76, + "learning_rate": 3.282080101716484e-06, + "loss": 1.3418, + "step": 7257 + }, + { + "epoch": 0.76, + "learning_rate": 3.2793692586949143e-06, + "loss": 1.3247, + "step": 7258 + }, + { + "epoch": 0.76, + "learning_rate": 3.2766593160651827e-06, + "loss": 1.3462, + "step": 7259 + }, + { + "epoch": 0.76, + "learning_rate": 3.273950274190356e-06, + "loss": 1.3699, + "step": 7260 + }, + { + "epoch": 0.76, + "learning_rate": 3.2712421334333687e-06, + "loss": 1.2863, + "step": 7261 + }, + { + "epoch": 0.76, + "learning_rate": 3.268534894157046e-06, + "loss": 1.3791, + "step": 7262 + }, + { + "epoch": 0.76, + "learning_rate": 3.265828556724092e-06, + "loss": 1.3066, + "step": 7263 + }, + { + "epoch": 0.76, + "learning_rate": 3.2631231214970784e-06, + "loss": 1.319, + "step": 7264 + }, + { + "epoch": 0.76, + "learning_rate": 3.260418588838471e-06, + "loss": 1.2939, + "step": 7265 + }, + { + "epoch": 0.76, + "learning_rate": 3.2577149591106017e-06, + "loss": 1.2568, + "step": 7266 + }, + { + "epoch": 0.76, + "learning_rate": 3.2550122326756905e-06, + "loss": 1.3494, + "step": 7267 + }, + { + "epoch": 0.76, + "learning_rate": 3.252310409895837e-06, + "loss": 1.3001, + "step": 7268 + }, + { + "epoch": 0.76, + "learning_rate": 3.2496094911330087e-06, + "loss": 1.4039, + "step": 7269 + }, + { + "epoch": 0.76, + "learning_rate": 3.246909476749063e-06, + "loss": 1.2904, + "step": 7270 + }, + { + "epoch": 0.76, + "learning_rate": 3.2442103671057358e-06, + "loss": 1.2864, + "step": 7271 + }, + { + "epoch": 0.76, + "learning_rate": 3.241512162564632e-06, + "loss": 1.3195, + "step": 7272 + }, + { + "epoch": 0.76, + "learning_rate": 3.2388148634872473e-06, + "loss": 1.2776, + "step": 7273 + }, + { + "epoch": 0.76, + "learning_rate": 3.2361184702349446e-06, + "loss": 1.3391, + "step": 7274 + }, + { + "epoch": 0.76, + "learning_rate": 3.2334229831689745e-06, + "loss": 1.6897, + "step": 7275 + }, + { + "epoch": 0.76, + "learning_rate": 3.2307284026504673e-06, + "loss": 1.4191, + "step": 7276 + }, + { + "epoch": 0.76, + "learning_rate": 3.228034729040419e-06, + "loss": 1.2671, + "step": 7277 + }, + { + "epoch": 0.76, + "learning_rate": 3.2253419626997172e-06, + "loss": 1.3085, + "step": 7278 + }, + { + "epoch": 0.76, + "learning_rate": 3.2226501039891266e-06, + "loss": 1.4378, + "step": 7279 + }, + { + "epoch": 0.76, + "learning_rate": 3.2199591532692807e-06, + "loss": 1.3044, + "step": 7280 + }, + { + "epoch": 0.76, + "learning_rate": 3.2172691109007036e-06, + "loss": 1.2709, + "step": 7281 + }, + { + "epoch": 0.76, + "learning_rate": 3.214579977243787e-06, + "loss": 1.2394, + "step": 7282 + }, + { + "epoch": 0.76, + "learning_rate": 3.2118917526588055e-06, + "loss": 1.2945, + "step": 7283 + }, + { + "epoch": 0.76, + "learning_rate": 3.2092044375059197e-06, + "loss": 1.4074, + "step": 7284 + }, + { + "epoch": 0.76, + "learning_rate": 3.2065180321451504e-06, + "loss": 1.3769, + "step": 7285 + }, + { + "epoch": 0.76, + "learning_rate": 3.203832536936413e-06, + "loss": 1.2479, + "step": 7286 + }, + { + "epoch": 0.76, + "learning_rate": 3.2011479522394973e-06, + "loss": 1.2623, + "step": 7287 + }, + { + "epoch": 0.76, + "learning_rate": 3.1984642784140616e-06, + "loss": 1.3044, + "step": 7288 + }, + { + "epoch": 0.76, + "learning_rate": 3.1957815158196525e-06, + "loss": 1.321, + "step": 7289 + }, + { + "epoch": 0.76, + "learning_rate": 3.1930996648156953e-06, + "loss": 1.3307, + "step": 7290 + }, + { + "epoch": 0.76, + "learning_rate": 3.1904187257614814e-06, + "loss": 1.3135, + "step": 7291 + }, + { + "epoch": 0.76, + "learning_rate": 3.187738699016195e-06, + "loss": 1.2821, + "step": 7292 + }, + { + "epoch": 0.76, + "learning_rate": 3.1850595849388853e-06, + "loss": 1.3069, + "step": 7293 + }, + { + "epoch": 0.76, + "learning_rate": 3.1823813838884865e-06, + "loss": 1.2952, + "step": 7294 + }, + { + "epoch": 0.76, + "learning_rate": 3.179704096223812e-06, + "loss": 1.3313, + "step": 7295 + }, + { + "epoch": 0.77, + "learning_rate": 3.177027722303544e-06, + "loss": 1.3454, + "step": 7296 + }, + { + "epoch": 0.77, + "learning_rate": 3.1743522624862497e-06, + "loss": 1.2904, + "step": 7297 + }, + { + "epoch": 0.77, + "learning_rate": 3.1716777171303783e-06, + "loss": 1.3213, + "step": 7298 + }, + { + "epoch": 0.77, + "learning_rate": 3.1690040865942396e-06, + "loss": 1.3336, + "step": 7299 + }, + { + "epoch": 0.77, + "learning_rate": 3.1663313712360398e-06, + "loss": 1.3399, + "step": 7300 + }, + { + "epoch": 0.77, + "learning_rate": 3.1636595714138483e-06, + "loss": 1.2871, + "step": 7301 + }, + { + "epoch": 0.77, + "learning_rate": 3.16098868748562e-06, + "loss": 1.312, + "step": 7302 + }, + { + "epoch": 0.77, + "learning_rate": 3.158318719809188e-06, + "loss": 1.3325, + "step": 7303 + }, + { + "epoch": 0.77, + "learning_rate": 3.1556496687422534e-06, + "loss": 1.309, + "step": 7304 + }, + { + "epoch": 0.77, + "learning_rate": 3.152981534642403e-06, + "loss": 1.3186, + "step": 7305 + }, + { + "epoch": 0.77, + "learning_rate": 3.1503143178671016e-06, + "loss": 1.3235, + "step": 7306 + }, + { + "epoch": 0.77, + "learning_rate": 3.1476480187736812e-06, + "loss": 1.3557, + "step": 7307 + }, + { + "epoch": 0.77, + "learning_rate": 3.1449826377193613e-06, + "loss": 1.3206, + "step": 7308 + }, + { + "epoch": 0.77, + "learning_rate": 3.1423181750612375e-06, + "loss": 1.2901, + "step": 7309 + }, + { + "epoch": 0.77, + "learning_rate": 3.1396546311562713e-06, + "loss": 1.3232, + "step": 7310 + }, + { + "epoch": 0.77, + "learning_rate": 3.136992006361318e-06, + "loss": 1.3065, + "step": 7311 + }, + { + "epoch": 0.77, + "learning_rate": 3.1343303010330926e-06, + "loss": 1.273, + "step": 7312 + }, + { + "epoch": 0.77, + "learning_rate": 3.1316695155281997e-06, + "loss": 1.2773, + "step": 7313 + }, + { + "epoch": 0.77, + "learning_rate": 3.12900965020312e-06, + "loss": 1.2959, + "step": 7314 + }, + { + "epoch": 0.77, + "learning_rate": 3.1263507054141975e-06, + "loss": 1.2685, + "step": 7315 + }, + { + "epoch": 0.77, + "learning_rate": 3.1236926815176683e-06, + "loss": 1.3908, + "step": 7316 + }, + { + "epoch": 0.77, + "learning_rate": 3.121035578869643e-06, + "loss": 1.3022, + "step": 7317 + }, + { + "epoch": 0.77, + "learning_rate": 3.1183793978260966e-06, + "loss": 1.3144, + "step": 7318 + }, + { + "epoch": 0.77, + "learning_rate": 3.1157241387428972e-06, + "loss": 1.3142, + "step": 7319 + }, + { + "epoch": 0.77, + "learning_rate": 3.1130698019757743e-06, + "loss": 1.3277, + "step": 7320 + }, + { + "epoch": 0.77, + "learning_rate": 3.110416387880344e-06, + "loss": 1.2973, + "step": 7321 + }, + { + "epoch": 0.77, + "learning_rate": 3.1077638968120984e-06, + "loss": 1.2862, + "step": 7322 + }, + { + "epoch": 0.77, + "learning_rate": 3.1051123291263975e-06, + "loss": 1.5172, + "step": 7323 + }, + { + "epoch": 0.77, + "learning_rate": 3.102461685178486e-06, + "loss": 1.3757, + "step": 7324 + }, + { + "epoch": 0.77, + "learning_rate": 3.099811965323485e-06, + "loss": 1.3082, + "step": 7325 + }, + { + "epoch": 0.77, + "learning_rate": 3.097163169916383e-06, + "loss": 1.3674, + "step": 7326 + }, + { + "epoch": 0.77, + "learning_rate": 3.0945152993120574e-06, + "loss": 1.3168, + "step": 7327 + }, + { + "epoch": 0.77, + "learning_rate": 3.0918683538652474e-06, + "loss": 1.3122, + "step": 7328 + }, + { + "epoch": 0.77, + "learning_rate": 3.089222333930579e-06, + "loss": 1.3437, + "step": 7329 + }, + { + "epoch": 0.77, + "learning_rate": 3.0865772398625548e-06, + "loss": 1.371, + "step": 7330 + }, + { + "epoch": 0.77, + "learning_rate": 3.0839330720155426e-06, + "loss": 1.327, + "step": 7331 + }, + { + "epoch": 0.77, + "learning_rate": 3.0812898307437955e-06, + "loss": 1.3369, + "step": 7332 + }, + { + "epoch": 0.77, + "learning_rate": 3.078647516401444e-06, + "loss": 1.2148, + "step": 7333 + }, + { + "epoch": 0.77, + "learning_rate": 3.0760061293424846e-06, + "loss": 1.3074, + "step": 7334 + }, + { + "epoch": 0.77, + "learning_rate": 3.073365669920797e-06, + "loss": 1.3218, + "step": 7335 + }, + { + "epoch": 0.77, + "learning_rate": 3.070726138490139e-06, + "loss": 1.2974, + "step": 7336 + }, + { + "epoch": 0.77, + "learning_rate": 3.0680875354041327e-06, + "loss": 1.3037, + "step": 7337 + }, + { + "epoch": 0.77, + "learning_rate": 3.065449861016291e-06, + "loss": 1.5706, + "step": 7338 + }, + { + "epoch": 0.77, + "learning_rate": 3.0628131156799857e-06, + "loss": 1.3346, + "step": 7339 + }, + { + "epoch": 0.77, + "learning_rate": 3.0601772997484793e-06, + "loss": 1.6488, + "step": 7340 + }, + { + "epoch": 0.77, + "learning_rate": 3.0575424135749045e-06, + "loss": 1.2929, + "step": 7341 + }, + { + "epoch": 0.77, + "learning_rate": 3.0549084575122625e-06, + "loss": 1.3137, + "step": 7342 + }, + { + "epoch": 0.77, + "learning_rate": 3.0522754319134373e-06, + "loss": 1.3218, + "step": 7343 + }, + { + "epoch": 0.77, + "learning_rate": 3.0496433371311927e-06, + "loss": 1.2805, + "step": 7344 + }, + { + "epoch": 0.77, + "learning_rate": 3.0470121735181544e-06, + "loss": 1.2218, + "step": 7345 + }, + { + "epoch": 0.77, + "learning_rate": 3.0443819414268373e-06, + "loss": 1.381, + "step": 7346 + }, + { + "epoch": 0.77, + "learning_rate": 3.0417526412096164e-06, + "loss": 1.3571, + "step": 7347 + }, + { + "epoch": 0.77, + "learning_rate": 3.0391242732187565e-06, + "loss": 1.3295, + "step": 7348 + }, + { + "epoch": 0.77, + "learning_rate": 3.036496837806393e-06, + "loss": 1.3795, + "step": 7349 + }, + { + "epoch": 0.77, + "learning_rate": 3.033870335324528e-06, + "loss": 1.282, + "step": 7350 + }, + { + "epoch": 0.77, + "learning_rate": 3.03124476612505e-06, + "loss": 1.3428, + "step": 7351 + }, + { + "epoch": 0.77, + "learning_rate": 3.0286201305597194e-06, + "loss": 1.3321, + "step": 7352 + }, + { + "epoch": 0.77, + "learning_rate": 3.0259964289801646e-06, + "loss": 1.4135, + "step": 7353 + }, + { + "epoch": 0.77, + "learning_rate": 3.023373661737897e-06, + "loss": 1.3032, + "step": 7354 + }, + { + "epoch": 0.77, + "learning_rate": 3.0207518291843042e-06, + "loss": 1.2676, + "step": 7355 + }, + { + "epoch": 0.77, + "learning_rate": 3.0181309316706362e-06, + "loss": 1.2902, + "step": 7356 + }, + { + "epoch": 0.77, + "learning_rate": 3.0155109695480333e-06, + "loss": 1.3364, + "step": 7357 + }, + { + "epoch": 0.77, + "learning_rate": 3.0128919431674975e-06, + "loss": 1.3733, + "step": 7358 + }, + { + "epoch": 0.77, + "learning_rate": 3.0102738528799125e-06, + "loss": 1.3114, + "step": 7359 + }, + { + "epoch": 0.77, + "learning_rate": 3.007656699036039e-06, + "loss": 1.3176, + "step": 7360 + }, + { + "epoch": 0.77, + "learning_rate": 3.005040481986503e-06, + "loss": 1.301, + "step": 7361 + }, + { + "epoch": 0.77, + "learning_rate": 3.0024252020818124e-06, + "loss": 1.3281, + "step": 7362 + }, + { + "epoch": 0.77, + "learning_rate": 2.9998108596723508e-06, + "loss": 1.1587, + "step": 7363 + }, + { + "epoch": 0.77, + "eval_loss": 1.3964349031448364, + "eval_runtime": 77.4566, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 7363 + }, + { + "epoch": 0.77, + "learning_rate": 2.9971974551083673e-06, + "loss": 1.3628, + "step": 7364 + }, + { + "epoch": 0.77, + "learning_rate": 2.9945849887399958e-06, + "loss": 1.4178, + "step": 7365 + }, + { + "epoch": 0.77, + "learning_rate": 2.9919734609172356e-06, + "loss": 1.3428, + "step": 7366 + }, + { + "epoch": 0.77, + "learning_rate": 2.989362871989965e-06, + "loss": 1.2675, + "step": 7367 + }, + { + "epoch": 0.77, + "learning_rate": 2.986753222307941e-06, + "loss": 1.3353, + "step": 7368 + }, + { + "epoch": 0.77, + "learning_rate": 2.9841445122207826e-06, + "loss": 1.2842, + "step": 7369 + }, + { + "epoch": 0.77, + "learning_rate": 2.981536742077993e-06, + "loss": 1.2237, + "step": 7370 + }, + { + "epoch": 0.77, + "learning_rate": 2.9789299122289493e-06, + "loss": 1.2554, + "step": 7371 + }, + { + "epoch": 0.77, + "learning_rate": 2.976324023022893e-06, + "loss": 1.3277, + "step": 7372 + }, + { + "epoch": 0.77, + "learning_rate": 2.973719074808954e-06, + "loss": 1.3258, + "step": 7373 + }, + { + "epoch": 0.77, + "learning_rate": 2.971115067936122e-06, + "loss": 1.2757, + "step": 7374 + }, + { + "epoch": 0.77, + "learning_rate": 2.9685120027532687e-06, + "loss": 1.3267, + "step": 7375 + }, + { + "epoch": 0.77, + "learning_rate": 2.9659098796091423e-06, + "loss": 1.3451, + "step": 7376 + }, + { + "epoch": 0.77, + "learning_rate": 2.9633086988523507e-06, + "loss": 1.2742, + "step": 7377 + }, + { + "epoch": 0.77, + "learning_rate": 2.9607084608313972e-06, + "loss": 1.3589, + "step": 7378 + }, + { + "epoch": 0.77, + "learning_rate": 2.9581091658946415e-06, + "loss": 1.2839, + "step": 7379 + }, + { + "epoch": 0.77, + "learning_rate": 2.9555108143903187e-06, + "loss": 1.2883, + "step": 7380 + }, + { + "epoch": 0.77, + "learning_rate": 2.9529134066665453e-06, + "loss": 1.2781, + "step": 7381 + }, + { + "epoch": 0.77, + "learning_rate": 2.9503169430713084e-06, + "loss": 1.3638, + "step": 7382 + }, + { + "epoch": 0.77, + "learning_rate": 2.947721423952463e-06, + "loss": 1.3284, + "step": 7383 + }, + { + "epoch": 0.77, + "learning_rate": 2.945126849657748e-06, + "loss": 1.4043, + "step": 7384 + }, + { + "epoch": 0.77, + "learning_rate": 2.9425332205347624e-06, + "loss": 1.3173, + "step": 7385 + }, + { + "epoch": 0.77, + "learning_rate": 2.9399405369309884e-06, + "loss": 1.2099, + "step": 7386 + }, + { + "epoch": 0.77, + "learning_rate": 2.9373487991937845e-06, + "loss": 1.3062, + "step": 7387 + }, + { + "epoch": 0.77, + "learning_rate": 2.9347580076703695e-06, + "loss": 1.3075, + "step": 7388 + }, + { + "epoch": 0.77, + "learning_rate": 2.932168162707846e-06, + "loss": 1.3129, + "step": 7389 + }, + { + "epoch": 0.77, + "learning_rate": 2.9295792646531882e-06, + "loss": 1.4852, + "step": 7390 + }, + { + "epoch": 0.78, + "learning_rate": 2.926991313853239e-06, + "loss": 1.303, + "step": 7391 + }, + { + "epoch": 0.78, + "learning_rate": 2.9244043106547214e-06, + "loss": 1.2761, + "step": 7392 + }, + { + "epoch": 0.78, + "learning_rate": 2.9218182554042206e-06, + "loss": 1.2693, + "step": 7393 + }, + { + "epoch": 0.78, + "learning_rate": 2.9192331484482074e-06, + "loss": 1.2966, + "step": 7394 + }, + { + "epoch": 0.78, + "learning_rate": 2.9166489901330195e-06, + "loss": 1.3091, + "step": 7395 + }, + { + "epoch": 0.78, + "learning_rate": 2.91406578080486e-06, + "loss": 1.373, + "step": 7396 + }, + { + "epoch": 0.78, + "learning_rate": 2.9114835208098257e-06, + "loss": 1.2369, + "step": 7397 + }, + { + "epoch": 0.78, + "learning_rate": 2.908902210493866e-06, + "loss": 1.6399, + "step": 7398 + }, + { + "epoch": 0.78, + "learning_rate": 2.906321850202806e-06, + "loss": 1.3121, + "step": 7399 + }, + { + "epoch": 0.78, + "learning_rate": 2.903742440282352e-06, + "loss": 1.3401, + "step": 7400 + }, + { + "epoch": 0.78, + "learning_rate": 2.9011639810780833e-06, + "loss": 1.2974, + "step": 7401 + }, + { + "epoch": 0.78, + "learning_rate": 2.8985864729354383e-06, + "loss": 1.2825, + "step": 7402 + }, + { + "epoch": 0.78, + "learning_rate": 2.8960099161997434e-06, + "loss": 1.4901, + "step": 7403 + }, + { + "epoch": 0.78, + "learning_rate": 2.8934343112161867e-06, + "loss": 1.3203, + "step": 7404 + }, + { + "epoch": 0.78, + "learning_rate": 2.8908596583298343e-06, + "loss": 1.2859, + "step": 7405 + }, + { + "epoch": 0.78, + "learning_rate": 2.888285957885628e-06, + "loss": 1.334, + "step": 7406 + }, + { + "epoch": 0.78, + "learning_rate": 2.8857132102283703e-06, + "loss": 1.3358, + "step": 7407 + }, + { + "epoch": 0.78, + "learning_rate": 2.883141415702747e-06, + "loss": 1.2927, + "step": 7408 + }, + { + "epoch": 0.78, + "learning_rate": 2.8805705746533154e-06, + "loss": 1.3846, + "step": 7409 + }, + { + "epoch": 0.78, + "learning_rate": 2.8780006874244947e-06, + "loss": 1.2857, + "step": 7410 + }, + { + "epoch": 0.78, + "learning_rate": 2.8754317543605923e-06, + "loss": 1.3791, + "step": 7411 + }, + { + "epoch": 0.78, + "learning_rate": 2.872863775805772e-06, + "loss": 1.3286, + "step": 7412 + }, + { + "epoch": 0.78, + "learning_rate": 2.870296752104079e-06, + "loss": 1.244, + "step": 7413 + }, + { + "epoch": 0.78, + "learning_rate": 2.8677306835994335e-06, + "loss": 1.3673, + "step": 7414 + }, + { + "epoch": 0.78, + "learning_rate": 2.865165570635615e-06, + "loss": 1.3123, + "step": 7415 + }, + { + "epoch": 0.78, + "learning_rate": 2.862601413556286e-06, + "loss": 1.2867, + "step": 7416 + }, + { + "epoch": 0.78, + "learning_rate": 2.860038212704982e-06, + "loss": 1.3254, + "step": 7417 + }, + { + "epoch": 0.78, + "learning_rate": 2.8574759684250985e-06, + "loss": 1.2298, + "step": 7418 + }, + { + "epoch": 0.78, + "learning_rate": 2.854914681059914e-06, + "loss": 1.3054, + "step": 7419 + }, + { + "epoch": 0.78, + "learning_rate": 2.8523543509525785e-06, + "loss": 1.2984, + "step": 7420 + }, + { + "epoch": 0.78, + "learning_rate": 2.8497949784461043e-06, + "loss": 1.2848, + "step": 7421 + }, + { + "epoch": 0.78, + "learning_rate": 2.847236563883388e-06, + "loss": 1.4184, + "step": 7422 + }, + { + "epoch": 0.78, + "learning_rate": 2.84467910760718e-06, + "loss": 1.3967, + "step": 7423 + }, + { + "epoch": 0.78, + "learning_rate": 2.8421226099601284e-06, + "loss": 1.2847, + "step": 7424 + }, + { + "epoch": 0.78, + "learning_rate": 2.8395670712847322e-06, + "loss": 1.3681, + "step": 7425 + }, + { + "epoch": 0.78, + "learning_rate": 2.837012491923363e-06, + "loss": 1.3114, + "step": 7426 + }, + { + "epoch": 0.78, + "learning_rate": 2.834458872218274e-06, + "loss": 1.3264, + "step": 7427 + }, + { + "epoch": 0.78, + "learning_rate": 2.831906212511586e-06, + "loss": 1.3019, + "step": 7428 + }, + { + "epoch": 0.78, + "learning_rate": 2.829354513145284e-06, + "loss": 1.2619, + "step": 7429 + }, + { + "epoch": 0.78, + "learning_rate": 2.8268037744612362e-06, + "loss": 1.2825, + "step": 7430 + }, + { + "epoch": 0.78, + "learning_rate": 2.824253996801172e-06, + "loss": 1.2942, + "step": 7431 + }, + { + "epoch": 0.78, + "learning_rate": 2.8217051805066953e-06, + "loss": 1.3907, + "step": 7432 + }, + { + "epoch": 0.78, + "learning_rate": 2.8191573259192884e-06, + "loss": 1.2871, + "step": 7433 + }, + { + "epoch": 0.78, + "learning_rate": 2.81661043338029e-06, + "loss": 1.3924, + "step": 7434 + }, + { + "epoch": 0.78, + "learning_rate": 2.814064503230923e-06, + "loss": 1.3649, + "step": 7435 + }, + { + "epoch": 0.78, + "learning_rate": 2.8115195358122795e-06, + "loss": 1.3475, + "step": 7436 + }, + { + "epoch": 0.78, + "learning_rate": 2.808975531465312e-06, + "loss": 1.3736, + "step": 7437 + }, + { + "epoch": 0.78, + "learning_rate": 2.806432490530859e-06, + "loss": 1.2908, + "step": 7438 + }, + { + "epoch": 0.78, + "learning_rate": 2.803890413349618e-06, + "loss": 1.3991, + "step": 7439 + }, + { + "epoch": 0.78, + "learning_rate": 2.8013493002621617e-06, + "loss": 1.2928, + "step": 7440 + }, + { + "epoch": 0.78, + "learning_rate": 2.79880915160894e-06, + "loss": 1.3408, + "step": 7441 + }, + { + "epoch": 0.78, + "learning_rate": 2.7962699677302574e-06, + "loss": 1.3045, + "step": 7442 + }, + { + "epoch": 0.78, + "learning_rate": 2.793731748966311e-06, + "loss": 1.3179, + "step": 7443 + }, + { + "epoch": 0.78, + "learning_rate": 2.791194495657151e-06, + "loss": 1.2709, + "step": 7444 + }, + { + "epoch": 0.78, + "learning_rate": 2.7886582081427014e-06, + "loss": 1.3635, + "step": 7445 + }, + { + "epoch": 0.78, + "learning_rate": 2.786122886762762e-06, + "loss": 1.323, + "step": 7446 + }, + { + "epoch": 0.78, + "learning_rate": 2.7835885318570054e-06, + "loss": 1.2629, + "step": 7447 + }, + { + "epoch": 0.78, + "learning_rate": 2.7810551437649613e-06, + "loss": 1.4308, + "step": 7448 + }, + { + "epoch": 0.78, + "learning_rate": 2.778522722826048e-06, + "loss": 1.3546, + "step": 7449 + }, + { + "epoch": 0.78, + "learning_rate": 2.775991269379532e-06, + "loss": 1.4486, + "step": 7450 + }, + { + "epoch": 0.78, + "learning_rate": 2.773460783764579e-06, + "loss": 1.2845, + "step": 7451 + }, + { + "epoch": 0.78, + "learning_rate": 2.7709312663201993e-06, + "loss": 1.2393, + "step": 7452 + }, + { + "epoch": 0.78, + "learning_rate": 2.7684027173852836e-06, + "loss": 1.2939, + "step": 7453 + }, + { + "epoch": 0.78, + "learning_rate": 2.7658751372985926e-06, + "loss": 1.5802, + "step": 7454 + }, + { + "epoch": 0.78, + "learning_rate": 2.7633485263987627e-06, + "loss": 1.258, + "step": 7455 + }, + { + "epoch": 0.78, + "learning_rate": 2.760822885024286e-06, + "loss": 1.3223, + "step": 7456 + }, + { + "epoch": 0.78, + "learning_rate": 2.7582982135135418e-06, + "loss": 1.277, + "step": 7457 + }, + { + "epoch": 0.78, + "learning_rate": 2.755774512204764e-06, + "loss": 1.3047, + "step": 7458 + }, + { + "epoch": 0.78, + "learning_rate": 2.753251781436068e-06, + "loss": 1.3021, + "step": 7459 + }, + { + "epoch": 0.78, + "learning_rate": 2.750730021545437e-06, + "loss": 1.3321, + "step": 7460 + }, + { + "epoch": 0.78, + "learning_rate": 2.7482092328707154e-06, + "loss": 1.2453, + "step": 7461 + }, + { + "epoch": 0.78, + "learning_rate": 2.7456894157496293e-06, + "loss": 1.2628, + "step": 7462 + }, + { + "epoch": 0.78, + "learning_rate": 2.74317057051977e-06, + "loss": 1.4221, + "step": 7463 + }, + { + "epoch": 0.78, + "learning_rate": 2.740652697518593e-06, + "loss": 1.3034, + "step": 7464 + }, + { + "epoch": 0.78, + "learning_rate": 2.738135797083432e-06, + "loss": 1.2944, + "step": 7465 + }, + { + "epoch": 0.78, + "learning_rate": 2.7356198695514893e-06, + "loss": 1.3434, + "step": 7466 + }, + { + "epoch": 0.78, + "learning_rate": 2.733104915259829e-06, + "loss": 1.3127, + "step": 7467 + }, + { + "epoch": 0.78, + "learning_rate": 2.730590934545396e-06, + "loss": 1.2425, + "step": 7468 + }, + { + "epoch": 0.78, + "learning_rate": 2.7280779277449907e-06, + "loss": 1.4366, + "step": 7469 + }, + { + "epoch": 0.78, + "learning_rate": 2.7255658951953036e-06, + "loss": 1.3024, + "step": 7470 + }, + { + "epoch": 0.78, + "learning_rate": 2.7230548372328745e-06, + "loss": 1.2768, + "step": 7471 + }, + { + "epoch": 0.78, + "learning_rate": 2.720544754194121e-06, + "loss": 1.2453, + "step": 7472 + }, + { + "epoch": 0.78, + "learning_rate": 2.7180356464153303e-06, + "loss": 1.2796, + "step": 7473 + }, + { + "epoch": 0.78, + "learning_rate": 2.715527514232661e-06, + "loss": 1.3181, + "step": 7474 + }, + { + "epoch": 0.78, + "learning_rate": 2.7130203579821344e-06, + "loss": 1.4013, + "step": 7475 + }, + { + "epoch": 0.78, + "learning_rate": 2.710514177999649e-06, + "loss": 1.3365, + "step": 7476 + }, + { + "epoch": 0.78, + "learning_rate": 2.7080089746209614e-06, + "loss": 1.31, + "step": 7477 + }, + { + "epoch": 0.78, + "learning_rate": 2.7055047481817153e-06, + "loss": 1.258, + "step": 7478 + }, + { + "epoch": 0.78, + "learning_rate": 2.7030014990174068e-06, + "loss": 1.2199, + "step": 7479 + }, + { + "epoch": 0.78, + "learning_rate": 2.7004992274634046e-06, + "loss": 1.3007, + "step": 7480 + }, + { + "epoch": 0.78, + "learning_rate": 2.69799793385495e-06, + "loss": 1.2772, + "step": 7481 + }, + { + "epoch": 0.78, + "learning_rate": 2.6954976185271576e-06, + "loss": 1.4021, + "step": 7482 + }, + { + "epoch": 0.78, + "learning_rate": 2.692998281814998e-06, + "loss": 1.3183, + "step": 7483 + }, + { + "epoch": 0.78, + "learning_rate": 2.6904999240533246e-06, + "loss": 1.3412, + "step": 7484 + }, + { + "epoch": 0.78, + "learning_rate": 2.6880025455768465e-06, + "loss": 1.2552, + "step": 7485 + }, + { + "epoch": 0.79, + "learning_rate": 2.6855061467201517e-06, + "loss": 1.2525, + "step": 7486 + }, + { + "epoch": 0.79, + "learning_rate": 2.683010727817695e-06, + "loss": 1.269, + "step": 7487 + }, + { + "epoch": 0.79, + "learning_rate": 2.680516289203793e-06, + "loss": 1.5189, + "step": 7488 + }, + { + "epoch": 0.79, + "learning_rate": 2.6780228312126454e-06, + "loss": 1.2999, + "step": 7489 + }, + { + "epoch": 0.79, + "learning_rate": 2.675530354178306e-06, + "loss": 1.3322, + "step": 7490 + }, + { + "epoch": 0.79, + "learning_rate": 2.6730388584347e-06, + "loss": 1.3918, + "step": 7491 + }, + { + "epoch": 0.79, + "learning_rate": 2.670548344315628e-06, + "loss": 1.4438, + "step": 7492 + }, + { + "epoch": 0.79, + "learning_rate": 2.6680588121547546e-06, + "loss": 1.3393, + "step": 7493 + }, + { + "epoch": 0.79, + "learning_rate": 2.6655702622856105e-06, + "loss": 1.301, + "step": 7494 + }, + { + "epoch": 0.79, + "learning_rate": 2.6630826950416024e-06, + "loss": 1.2463, + "step": 7495 + }, + { + "epoch": 0.79, + "learning_rate": 2.660596110755991e-06, + "loss": 1.2641, + "step": 7496 + }, + { + "epoch": 0.79, + "learning_rate": 2.6581105097619264e-06, + "loss": 1.3824, + "step": 7497 + }, + { + "epoch": 0.79, + "learning_rate": 2.6556258923924104e-06, + "loss": 1.339, + "step": 7498 + }, + { + "epoch": 0.79, + "learning_rate": 2.6531422589803134e-06, + "loss": 1.2653, + "step": 7499 + }, + { + "epoch": 0.79, + "learning_rate": 2.6506596098583826e-06, + "loss": 1.2773, + "step": 7500 + }, + { + "epoch": 0.79, + "learning_rate": 2.648177945359233e-06, + "loss": 1.1829, + "step": 7501 + }, + { + "epoch": 0.79, + "learning_rate": 2.6456972658153358e-06, + "loss": 1.4014, + "step": 7502 + }, + { + "epoch": 0.79, + "learning_rate": 2.6432175715590446e-06, + "loss": 1.3648, + "step": 7503 + }, + { + "epoch": 0.79, + "learning_rate": 2.6407388629225706e-06, + "loss": 1.2731, + "step": 7504 + }, + { + "epoch": 0.79, + "learning_rate": 2.6382611402379988e-06, + "loss": 1.3076, + "step": 7505 + }, + { + "epoch": 0.79, + "learning_rate": 2.6357844038372824e-06, + "loss": 1.2054, + "step": 7506 + }, + { + "epoch": 0.79, + "learning_rate": 2.6333086540522366e-06, + "loss": 1.2579, + "step": 7507 + }, + { + "epoch": 0.79, + "learning_rate": 2.6308338912145493e-06, + "loss": 1.316, + "step": 7508 + }, + { + "epoch": 0.79, + "learning_rate": 2.6283601156557792e-06, + "loss": 1.2957, + "step": 7509 + }, + { + "epoch": 0.79, + "learning_rate": 2.625887327707343e-06, + "loss": 1.3017, + "step": 7510 + }, + { + "epoch": 0.79, + "learning_rate": 2.6234155277005334e-06, + "loss": 1.2591, + "step": 7511 + }, + { + "epoch": 0.79, + "learning_rate": 2.62094471596651e-06, + "loss": 1.3582, + "step": 7512 + }, + { + "epoch": 0.79, + "learning_rate": 2.6184748928362934e-06, + "loss": 1.3026, + "step": 7513 + }, + { + "epoch": 0.79, + "learning_rate": 2.616006058640782e-06, + "loss": 1.3222, + "step": 7514 + }, + { + "epoch": 0.79, + "learning_rate": 2.6135382137107268e-06, + "loss": 1.2785, + "step": 7515 + }, + { + "epoch": 0.79, + "learning_rate": 2.6110713583767687e-06, + "loss": 1.3227, + "step": 7516 + }, + { + "epoch": 0.79, + "learning_rate": 2.608605492969396e-06, + "loss": 1.2695, + "step": 7517 + }, + { + "epoch": 0.79, + "learning_rate": 2.6061406178189684e-06, + "loss": 1.2809, + "step": 7518 + }, + { + "epoch": 0.79, + "learning_rate": 2.6036767332557188e-06, + "loss": 1.2934, + "step": 7519 + }, + { + "epoch": 0.79, + "learning_rate": 2.6012138396097473e-06, + "loss": 1.2484, + "step": 7520 + }, + { + "epoch": 0.79, + "learning_rate": 2.5987519372110125e-06, + "loss": 1.3422, + "step": 7521 + }, + { + "epoch": 0.79, + "learning_rate": 2.596291026389354e-06, + "loss": 1.3008, + "step": 7522 + }, + { + "epoch": 0.79, + "learning_rate": 2.5938311074744582e-06, + "loss": 1.3698, + "step": 7523 + }, + { + "epoch": 0.79, + "learning_rate": 2.5913721807959045e-06, + "loss": 1.3034, + "step": 7524 + }, + { + "epoch": 0.79, + "learning_rate": 2.5889142466831208e-06, + "loss": 1.3011, + "step": 7525 + }, + { + "epoch": 0.79, + "learning_rate": 2.586457305465403e-06, + "loss": 1.3626, + "step": 7526 + }, + { + "epoch": 0.79, + "learning_rate": 2.5840013574719213e-06, + "loss": 1.3018, + "step": 7527 + }, + { + "epoch": 0.79, + "learning_rate": 2.581546403031713e-06, + "loss": 1.3316, + "step": 7528 + }, + { + "epoch": 0.79, + "learning_rate": 2.579092442473673e-06, + "loss": 1.2534, + "step": 7529 + }, + { + "epoch": 0.79, + "learning_rate": 2.5766394761265743e-06, + "loss": 1.2949, + "step": 7530 + }, + { + "epoch": 0.79, + "learning_rate": 2.574187504319046e-06, + "loss": 1.2962, + "step": 7531 + }, + { + "epoch": 0.79, + "learning_rate": 2.5717365273795914e-06, + "loss": 1.2926, + "step": 7532 + }, + { + "epoch": 0.79, + "learning_rate": 2.5692865456365824e-06, + "loss": 1.3136, + "step": 7533 + }, + { + "epoch": 0.79, + "learning_rate": 2.5668375594182447e-06, + "loss": 1.3065, + "step": 7534 + }, + { + "epoch": 0.79, + "learning_rate": 2.564389569052691e-06, + "loss": 1.3631, + "step": 7535 + }, + { + "epoch": 0.79, + "learning_rate": 2.5619425748678827e-06, + "loss": 1.3028, + "step": 7536 + }, + { + "epoch": 0.79, + "learning_rate": 2.5594965771916526e-06, + "loss": 1.3212, + "step": 7537 + }, + { + "epoch": 0.79, + "learning_rate": 2.557051576351702e-06, + "loss": 1.3154, + "step": 7538 + }, + { + "epoch": 0.79, + "learning_rate": 2.554607572675605e-06, + "loss": 1.284, + "step": 7539 + }, + { + "epoch": 0.79, + "learning_rate": 2.5521645664907856e-06, + "loss": 1.3833, + "step": 7540 + }, + { + "epoch": 0.79, + "learning_rate": 2.549722558124551e-06, + "loss": 1.3079, + "step": 7541 + }, + { + "epoch": 0.79, + "learning_rate": 2.54728154790406e-06, + "loss": 1.3104, + "step": 7542 + }, + { + "epoch": 0.79, + "learning_rate": 2.544841536156356e-06, + "loss": 1.2933, + "step": 7543 + }, + { + "epoch": 0.79, + "learning_rate": 2.5424025232083315e-06, + "loss": 1.4103, + "step": 7544 + }, + { + "epoch": 0.79, + "learning_rate": 2.53996450938675e-06, + "loss": 1.3602, + "step": 7545 + }, + { + "epoch": 0.79, + "learning_rate": 2.537527495018244e-06, + "loss": 1.381, + "step": 7546 + }, + { + "epoch": 0.79, + "learning_rate": 2.535091480429315e-06, + "loss": 1.4212, + "step": 7547 + }, + { + "epoch": 0.79, + "learning_rate": 2.5326564659463203e-06, + "loss": 1.3662, + "step": 7548 + }, + { + "epoch": 0.79, + "learning_rate": 2.5302224518954944e-06, + "loss": 1.2896, + "step": 7549 + }, + { + "epoch": 0.79, + "learning_rate": 2.5277894386029246e-06, + "loss": 1.3218, + "step": 7550 + }, + { + "epoch": 0.79, + "learning_rate": 2.5253574263945835e-06, + "loss": 1.337, + "step": 7551 + }, + { + "epoch": 0.79, + "learning_rate": 2.522926415596293e-06, + "loss": 1.3457, + "step": 7552 + }, + { + "epoch": 0.79, + "learning_rate": 2.5204964065337423e-06, + "loss": 1.3227, + "step": 7553 + }, + { + "epoch": 0.79, + "learning_rate": 2.5180673995324933e-06, + "loss": 1.2529, + "step": 7554 + }, + { + "epoch": 0.79, + "learning_rate": 2.5156393949179746e-06, + "loss": 1.3193, + "step": 7555 + }, + { + "epoch": 0.79, + "learning_rate": 2.5132123930154697e-06, + "loss": 1.2719, + "step": 7556 + }, + { + "epoch": 0.79, + "learning_rate": 2.5107863941501363e-06, + "loss": 1.3367, + "step": 7557 + }, + { + "epoch": 0.79, + "learning_rate": 2.508361398647e-06, + "loss": 1.2918, + "step": 7558 + }, + { + "epoch": 0.79, + "learning_rate": 2.505937406830942e-06, + "loss": 1.3458, + "step": 7559 + }, + { + "epoch": 0.79, + "learning_rate": 2.5035144190267215e-06, + "loss": 1.3975, + "step": 7560 + }, + { + "epoch": 0.79, + "learning_rate": 2.5010924355589463e-06, + "loss": 1.3717, + "step": 7561 + }, + { + "epoch": 0.79, + "learning_rate": 2.498671456752112e-06, + "loss": 1.316, + "step": 7562 + }, + { + "epoch": 0.79, + "eval_loss": 1.3956769704818726, + "eval_runtime": 77.5888, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 7562 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 3.382966955547946e+20, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-7562/training_args.bin b/checkpoint-7562/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-7562/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-796/config.json b/checkpoint-796/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-796/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-796/generation_config.json b/checkpoint-796/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-796/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-796/model-00001-of-00003.safetensors b/checkpoint-796/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..18af61a551031e20ab91e79c9f10591c2360565a --- /dev/null +++ b/checkpoint-796/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1830f7ed904f6e1f66f5beca8cb079d1bc1a835620413846407540a08030a708 +size 4943162336 diff --git a/checkpoint-796/model-00002-of-00003.safetensors b/checkpoint-796/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5d2d7722de3763bd2c76f1cb36c6d36dc6931fdc --- /dev/null +++ b/checkpoint-796/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d68952ff91d92c676b2dcaeddcbf22ac2751aee770acc828792f828dd3316fb +size 4999819336 diff --git a/checkpoint-796/model-00003-of-00003.safetensors b/checkpoint-796/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..313f4b06b9d0a23edf8689585179ba76e8ae4eaf --- /dev/null +++ b/checkpoint-796/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dfb42513f0641ca9c631b12d8e8174276a6aeefa90024209b7845c43b0d48b6 +size 4540516344 diff --git a/checkpoint-796/model.safetensors.index.json b/checkpoint-796/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-796/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-796/optimizer.pt b/checkpoint-796/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..3c88aeef634ecb73df015df123d012bb0a2c6113 --- /dev/null +++ b/checkpoint-796/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21904222a056e9368dda8ec72d93d9bce09c30d3319ce1019ff343d0898332d3 +size 14512103560 diff --git a/checkpoint-796/rng_state_0.pth b/checkpoint-796/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..9d31438b0bfd38acb69501aeb325fee7751b84e8 --- /dev/null +++ b/checkpoint-796/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a0ef6f96a48e59aa52c4b471312c2a62378c19acc7ebbae839612b03a7d775a +size 15984 diff --git a/checkpoint-796/rng_state_1.pth b/checkpoint-796/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..6759906b0863c54055155658e8d374770ecfc5f9 --- /dev/null +++ b/checkpoint-796/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab11d533c0fdad46ea8b8e295ba5fdb705e078eeb88cc28f37d82913508766e9 +size 15984 diff --git a/checkpoint-796/rng_state_2.pth b/checkpoint-796/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..784c719c042a2cca1f38818c7e9638aab398c859 --- /dev/null +++ b/checkpoint-796/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:615c168147e3465ce5bfab6da2ff4afc68566ce00ec0f0c6c9fc988038a58d0a +size 15984 diff --git a/checkpoint-796/rng_state_3.pth b/checkpoint-796/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..b32e705bcb6afbb2ab95f5c68c07d0ccc3d457df --- /dev/null +++ b/checkpoint-796/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79f71e8f8674ecaef9f8cdcbf7ac457a8b8ff15b12694ba2a2fffcb4b43f0f08 +size 15984 diff --git a/checkpoint-796/rng_state_4.pth b/checkpoint-796/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..37b97b2d3011e43a6dbac487263b52a0b3a55c83 --- /dev/null +++ b/checkpoint-796/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88cf6d674dab5545c300a55135f08ca935730a3d35e2c419fb0b333f19482c19 +size 15984 diff --git a/checkpoint-796/rng_state_5.pth b/checkpoint-796/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..1acb3d3b1d3de061b997d1dee57e44b465d0630e --- /dev/null +++ b/checkpoint-796/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2754f2cd8824702f027870d93748b3c0491b0ecd30f1e3d8e937116b2be6151f +size 15984 diff --git a/checkpoint-796/rng_state_6.pth b/checkpoint-796/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..7760bbbcd6d3754ac81a5218adb6e0cd8036905b --- /dev/null +++ b/checkpoint-796/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1385124ac55604598f45ea6e2d141f29456647d3e7c10d12ca64ec93d312be8d +size 15984 diff --git a/checkpoint-796/rng_state_7.pth b/checkpoint-796/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..d8c4407057d0cb21c08140413cb320528190a941 --- /dev/null +++ b/checkpoint-796/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:416538efaec7391fa8fe782fb15146b83e5612d9e1961292c34c53e964806873 +size 15984 diff --git a/checkpoint-796/scheduler.pt b/checkpoint-796/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..9dfa531c562ed814b648e637eda1a2808d083e55 --- /dev/null +++ b/checkpoint-796/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:815f613151cb782d855cd963e32cf2b5e0aaf3763fccf572b25d41fcfdfe4747 +size 1064 diff --git a/checkpoint-796/special_tokens_map.json b/checkpoint-796/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-796/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-796/tokenizer.model b/checkpoint-796/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-796/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-796/tokenizer_config.json b/checkpoint-796/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-796/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-796/trainer_state.json b/checkpoint-796/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..5e31a053e4814340d36e7884d496a82ec4b98887 --- /dev/null +++ b/checkpoint-796/trainer_state.json @@ -0,0 +1,4828 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.0834731543624161, + "eval_steps": 199, + "global_step": 796, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 3.561017847945206e+19, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-796/training_args.bin b/checkpoint-796/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-796/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-7960/config.json b/checkpoint-7960/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-7960/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-7960/generation_config.json b/checkpoint-7960/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-7960/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-7960/model-00001-of-00003.safetensors b/checkpoint-7960/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2334d64a7c1b339d4833882dc9398e270b61780f --- /dev/null +++ b/checkpoint-7960/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a4733d0d9a7bf9e6edd5e4e7cada2b79cc30e50d1dffea4bed57557621c8e39 +size 4943162336 diff --git a/checkpoint-7960/model-00002-of-00003.safetensors b/checkpoint-7960/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..08984d4af9e58a2ac5caf2952c10a7a90c803309 --- /dev/null +++ b/checkpoint-7960/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a765bae3c1d88fdfdeca04a85b2ec6031d74a6ca5e3fc97fe9e0c7537348747d +size 4999819336 diff --git a/checkpoint-7960/model-00003-of-00003.safetensors b/checkpoint-7960/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5fb42d9fee9d44caa9d580b1c0952ba003805b1b --- /dev/null +++ b/checkpoint-7960/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62dc559ef0ac1d8d14e6be0b7c406a039a09a6dac29f990eccf12fabcc775935 +size 4540516344 diff --git a/checkpoint-7960/model.safetensors.index.json b/checkpoint-7960/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-7960/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-7960/optimizer.pt b/checkpoint-7960/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..29a5a3adb16e28dba3adb781be972afb71b9867b --- /dev/null +++ b/checkpoint-7960/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fde5d4c1766fe23e87a7739b21969d8bbac5ea732ea6cdd6685ac6de3a8e9c3 +size 14512103560 diff --git a/checkpoint-7960/rng_state_0.pth b/checkpoint-7960/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..5f5fcf560f7a6dff8cfc54889b95cb0d390209d9 --- /dev/null +++ b/checkpoint-7960/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:191ab504c780d43f47feb85a00bed987462419eadeb03ae85bc3876b45a688b3 +size 15984 diff --git a/checkpoint-7960/rng_state_1.pth b/checkpoint-7960/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..1ed660e9f1d471e2521b7ad58f9ff4c70643ad93 --- /dev/null +++ b/checkpoint-7960/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6caeb2193f442ff45b99c7c35ee1bf753c03ebe8e39a497ef453db6e995d4b7 +size 15984 diff --git a/checkpoint-7960/rng_state_2.pth b/checkpoint-7960/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..17ce80fc37b07190d53038968c5b8aa0293b7edd --- /dev/null +++ b/checkpoint-7960/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:002addd749a91af039898d88370c74a969a473a98dfb8ddaf342b5e503b2921c +size 15984 diff --git a/checkpoint-7960/rng_state_3.pth b/checkpoint-7960/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..2764950491635561e6920bd652dcdd7b0485b192 --- /dev/null +++ b/checkpoint-7960/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adce98e8a8832b8c8addc2892384dcb5d18335f037935fdb6ba0392f75ffe061 +size 15984 diff --git a/checkpoint-7960/rng_state_4.pth b/checkpoint-7960/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..439fafb83214d539d6d6e9e3422185c34efab98c --- /dev/null +++ b/checkpoint-7960/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd4bbf9db140cee23977afd5c621035c12b882645bb92c8bd783b233fa18c04b +size 15984 diff --git a/checkpoint-7960/rng_state_5.pth b/checkpoint-7960/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..666910626aae64d826c8c2620212beae54b72d72 --- /dev/null +++ b/checkpoint-7960/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df139d2e5ff9c1833295496cc37a59fe58f95b1406ebac0f98482dc1ffd865b4 +size 15984 diff --git a/checkpoint-7960/rng_state_6.pth b/checkpoint-7960/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..69d6fbbcd8eb5def728f5128045e8e4e45b5943f --- /dev/null +++ b/checkpoint-7960/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebbbdfda7de9d2b05453f6ea651c726119e6ea061c8b6250ab50e17c3243e8a2 +size 15984 diff --git a/checkpoint-7960/rng_state_7.pth b/checkpoint-7960/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..0efc488b255dfde0b57fa8d32fc7086f9d9f2b4e --- /dev/null +++ b/checkpoint-7960/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbf0f2ddf67909a9dbe08e9f44e6d91317cf34e837b11cc8b71fae4f22a8d09a +size 15984 diff --git a/checkpoint-7960/scheduler.pt b/checkpoint-7960/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..884a583cdf3c7b47094629c00a6abe7b43645aee --- /dev/null +++ b/checkpoint-7960/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdeb659295e85038d47b363890e506cc205200985d5bf2a31fd46078356f4019 +size 1064 diff --git a/checkpoint-7960/special_tokens_map.json b/checkpoint-7960/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-7960/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-7960/tokenizer.model b/checkpoint-7960/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-7960/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-7960/tokenizer_config.json b/checkpoint-7960/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-7960/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-7960/trainer_state.json b/checkpoint-7960/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..e25fb3036e707da9f666d9a516d5cacca7734ca1 --- /dev/null +++ b/checkpoint-7960/trainer_state.json @@ -0,0 +1,48100 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.834731543624161, + "eval_steps": 199, + "global_step": 7960, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + }, + { + "epoch": 0.21, + "learning_rate": 1.928689129323009e-05, + "loss": 1.421, + "step": 1991 + }, + { + "epoch": 0.21, + "learning_rate": 1.928553323396003e-05, + "loss": 1.5625, + "step": 1992 + }, + { + "epoch": 0.21, + "learning_rate": 1.92841739306671e-05, + "loss": 1.5198, + "step": 1993 + }, + { + "epoch": 0.21, + "learning_rate": 1.9282813383533415e-05, + "loss": 1.5116, + "step": 1994 + }, + { + "epoch": 0.21, + "learning_rate": 1.9281451592741247e-05, + "loss": 1.4306, + "step": 1995 + }, + { + "epoch": 0.21, + "learning_rate": 1.9280088558473046e-05, + "loss": 1.5425, + "step": 1996 + }, + { + "epoch": 0.21, + "learning_rate": 1.9278724280911424e-05, + "loss": 1.4972, + "step": 1997 + }, + { + "epoch": 0.21, + "learning_rate": 1.9277358760239156e-05, + "loss": 1.5185, + "step": 1998 + }, + { + "epoch": 0.21, + "learning_rate": 1.9275991996639188e-05, + "loss": 1.5187, + "step": 1999 + }, + { + "epoch": 0.21, + "learning_rate": 1.927462399029463e-05, + "loss": 1.4325, + "step": 2000 + }, + { + "epoch": 0.21, + "learning_rate": 1.9273254741388763e-05, + "loss": 1.4397, + "step": 2001 + }, + { + "epoch": 0.21, + "learning_rate": 1.927188425010503e-05, + "loss": 1.5319, + "step": 2002 + }, + { + "epoch": 0.21, + "learning_rate": 1.9270512516627042e-05, + "loss": 1.5664, + "step": 2003 + }, + { + "epoch": 0.21, + "learning_rate": 1.9269139541138574e-05, + "loss": 1.5227, + "step": 2004 + }, + { + "epoch": 0.21, + "learning_rate": 1.926776532382357e-05, + "loss": 1.5187, + "step": 2005 + }, + { + "epoch": 0.21, + "learning_rate": 1.9266389864866134e-05, + "loss": 1.4029, + "step": 2006 + }, + { + "epoch": 0.21, + "learning_rate": 1.9265013164450557e-05, + "loss": 1.387, + "step": 2007 + }, + { + "epoch": 0.21, + "learning_rate": 1.9263635222761268e-05, + "loss": 1.5047, + "step": 2008 + }, + { + "epoch": 0.21, + "learning_rate": 1.9262256039982882e-05, + "loss": 1.4816, + "step": 2009 + }, + { + "epoch": 0.21, + "learning_rate": 1.9260875616300172e-05, + "loss": 1.4607, + "step": 2010 + }, + { + "epoch": 0.21, + "learning_rate": 1.9259493951898084e-05, + "loss": 1.628, + "step": 2011 + }, + { + "epoch": 0.21, + "learning_rate": 1.9258111046961714e-05, + "loss": 1.4149, + "step": 2012 + }, + { + "epoch": 0.21, + "learning_rate": 1.925672690167635e-05, + "loss": 1.5303, + "step": 2013 + }, + { + "epoch": 0.21, + "learning_rate": 1.925534151622742e-05, + "loss": 1.5198, + "step": 2014 + }, + { + "epoch": 0.21, + "learning_rate": 1.9253954890800535e-05, + "loss": 1.6422, + "step": 2015 + }, + { + "epoch": 0.21, + "learning_rate": 1.925256702558147e-05, + "loss": 1.4738, + "step": 2016 + }, + { + "epoch": 0.21, + "learning_rate": 1.925117792075616e-05, + "loss": 1.4752, + "step": 2017 + }, + { + "epoch": 0.21, + "learning_rate": 1.9249787576510713e-05, + "loss": 1.4547, + "step": 2018 + }, + { + "epoch": 0.21, + "learning_rate": 1.924839599303139e-05, + "loss": 1.4864, + "step": 2019 + }, + { + "epoch": 0.21, + "learning_rate": 1.9247003170504638e-05, + "loss": 1.5037, + "step": 2020 + }, + { + "epoch": 0.21, + "learning_rate": 1.9245609109117053e-05, + "loss": 1.5089, + "step": 2021 + }, + { + "epoch": 0.21, + "learning_rate": 1.924421380905541e-05, + "loss": 1.5616, + "step": 2022 + }, + { + "epoch": 0.21, + "learning_rate": 1.9242817270506634e-05, + "loss": 1.4592, + "step": 2023 + }, + { + "epoch": 0.21, + "learning_rate": 1.9241419493657832e-05, + "loss": 1.5592, + "step": 2024 + }, + { + "epoch": 0.21, + "learning_rate": 1.924002047869627e-05, + "loss": 1.4897, + "step": 2025 + }, + { + "epoch": 0.21, + "learning_rate": 1.9238620225809375e-05, + "loss": 1.4743, + "step": 2026 + }, + { + "epoch": 0.21, + "learning_rate": 1.923721873518475e-05, + "loss": 1.4686, + "step": 2027 + }, + { + "epoch": 0.21, + "learning_rate": 1.923581600701016e-05, + "loss": 1.461, + "step": 2028 + }, + { + "epoch": 0.21, + "learning_rate": 1.9234412041473528e-05, + "loss": 1.6622, + "step": 2029 + }, + { + "epoch": 0.21, + "learning_rate": 1.9233006838762955e-05, + "loss": 1.4707, + "step": 2030 + }, + { + "epoch": 0.21, + "learning_rate": 1.92316003990667e-05, + "loss": 1.5566, + "step": 2031 + }, + { + "epoch": 0.21, + "learning_rate": 1.9230192722573188e-05, + "loss": 1.4881, + "step": 2032 + }, + { + "epoch": 0.21, + "learning_rate": 1.9228783809471015e-05, + "loss": 1.6124, + "step": 2033 + }, + { + "epoch": 0.21, + "learning_rate": 1.9227373659948937e-05, + "loss": 1.3508, + "step": 2034 + }, + { + "epoch": 0.21, + "learning_rate": 1.9225962274195876e-05, + "loss": 1.4418, + "step": 2035 + }, + { + "epoch": 0.21, + "learning_rate": 1.9224549652400927e-05, + "loss": 1.3954, + "step": 2036 + }, + { + "epoch": 0.21, + "learning_rate": 1.922313579475334e-05, + "loss": 1.4798, + "step": 2037 + }, + { + "epoch": 0.21, + "learning_rate": 1.922172070144254e-05, + "loss": 1.4556, + "step": 2038 + }, + { + "epoch": 0.21, + "learning_rate": 1.922030437265811e-05, + "loss": 1.4987, + "step": 2039 + }, + { + "epoch": 0.21, + "learning_rate": 1.9218886808589796e-05, + "loss": 1.4857, + "step": 2040 + }, + { + "epoch": 0.21, + "learning_rate": 1.9217468009427527e-05, + "loss": 1.5289, + "step": 2041 + }, + { + "epoch": 0.21, + "learning_rate": 1.921604797536138e-05, + "loss": 1.5267, + "step": 2042 + }, + { + "epoch": 0.21, + "learning_rate": 1.9214626706581598e-05, + "loss": 1.4655, + "step": 2043 + }, + { + "epoch": 0.21, + "learning_rate": 1.9213204203278602e-05, + "loss": 1.4598, + "step": 2044 + }, + { + "epoch": 0.21, + "learning_rate": 1.9211780465642973e-05, + "loss": 1.4766, + "step": 2045 + }, + { + "epoch": 0.21, + "learning_rate": 1.921035549386545e-05, + "loss": 1.5148, + "step": 2046 + }, + { + "epoch": 0.21, + "learning_rate": 1.9208929288136933e-05, + "loss": 1.5567, + "step": 2047 + }, + { + "epoch": 0.21, + "learning_rate": 1.920750184864852e-05, + "loss": 1.4868, + "step": 2048 + }, + { + "epoch": 0.21, + "learning_rate": 1.920607317559143e-05, + "loss": 1.4752, + "step": 2049 + }, + { + "epoch": 0.21, + "learning_rate": 1.920464326915708e-05, + "loss": 1.4882, + "step": 2050 + }, + { + "epoch": 0.22, + "learning_rate": 1.9203212129537035e-05, + "loss": 1.5933, + "step": 2051 + }, + { + "epoch": 0.22, + "learning_rate": 1.9201779756923037e-05, + "loss": 1.4891, + "step": 2052 + }, + { + "epoch": 0.22, + "learning_rate": 1.9200346151506983e-05, + "loss": 1.4486, + "step": 2053 + }, + { + "epoch": 0.22, + "learning_rate": 1.9198911313480938e-05, + "loss": 1.5091, + "step": 2054 + }, + { + "epoch": 0.22, + "learning_rate": 1.919747524303714e-05, + "loss": 1.4385, + "step": 2055 + }, + { + "epoch": 0.22, + "learning_rate": 1.9196037940367974e-05, + "loss": 1.4104, + "step": 2056 + }, + { + "epoch": 0.22, + "learning_rate": 1.9194599405666015e-05, + "loss": 1.4483, + "step": 2057 + }, + { + "epoch": 0.22, + "learning_rate": 1.9193159639123976e-05, + "loss": 1.4592, + "step": 2058 + }, + { + "epoch": 0.22, + "learning_rate": 1.919171864093476e-05, + "loss": 1.4975, + "step": 2059 + }, + { + "epoch": 0.22, + "learning_rate": 1.9190276411291423e-05, + "loss": 1.4727, + "step": 2060 + }, + { + "epoch": 0.22, + "learning_rate": 1.9188832950387178e-05, + "loss": 1.4791, + "step": 2061 + }, + { + "epoch": 0.22, + "learning_rate": 1.9187388258415423e-05, + "loss": 1.3806, + "step": 2062 + }, + { + "epoch": 0.22, + "learning_rate": 1.9185942335569697e-05, + "loss": 1.4514, + "step": 2063 + }, + { + "epoch": 0.22, + "learning_rate": 1.9184495182043727e-05, + "loss": 1.4389, + "step": 2064 + }, + { + "epoch": 0.22, + "learning_rate": 1.918304679803139e-05, + "loss": 1.5088, + "step": 2065 + }, + { + "epoch": 0.22, + "learning_rate": 1.9181597183726733e-05, + "loss": 1.4665, + "step": 2066 + }, + { + "epoch": 0.22, + "learning_rate": 1.9180146339323966e-05, + "loss": 1.489, + "step": 2067 + }, + { + "epoch": 0.22, + "learning_rate": 1.9178694265017466e-05, + "loss": 1.5215, + "step": 2068 + }, + { + "epoch": 0.22, + "learning_rate": 1.9177240961001775e-05, + "loss": 1.5152, + "step": 2069 + }, + { + "epoch": 0.22, + "learning_rate": 1.9175786427471594e-05, + "loss": 1.4418, + "step": 2070 + }, + { + "epoch": 0.22, + "learning_rate": 1.91743306646218e-05, + "loss": 1.5001, + "step": 2071 + }, + { + "epoch": 0.22, + "learning_rate": 1.9172873672647417e-05, + "loss": 1.4879, + "step": 2072 + }, + { + "epoch": 0.22, + "learning_rate": 1.917141545174366e-05, + "loss": 1.5299, + "step": 2073 + }, + { + "epoch": 0.22, + "learning_rate": 1.9169956002105877e-05, + "loss": 1.4602, + "step": 2074 + }, + { + "epoch": 0.22, + "learning_rate": 1.9168495323929605e-05, + "loss": 1.4921, + "step": 2075 + }, + { + "epoch": 0.22, + "learning_rate": 1.916703341741054e-05, + "loss": 1.4659, + "step": 2076 + }, + { + "epoch": 0.22, + "learning_rate": 1.9165570282744534e-05, + "loss": 1.4707, + "step": 2077 + }, + { + "epoch": 0.22, + "learning_rate": 1.9164105920127613e-05, + "loss": 1.5354, + "step": 2078 + }, + { + "epoch": 0.22, + "learning_rate": 1.9162640329755962e-05, + "loss": 1.526, + "step": 2079 + }, + { + "epoch": 0.22, + "learning_rate": 1.916117351182593e-05, + "loss": 1.6424, + "step": 2080 + }, + { + "epoch": 0.22, + "learning_rate": 1.915970546653404e-05, + "loss": 1.5048, + "step": 2081 + }, + { + "epoch": 0.22, + "learning_rate": 1.915823619407697e-05, + "loss": 1.5344, + "step": 2082 + }, + { + "epoch": 0.22, + "learning_rate": 1.915676569465156e-05, + "loss": 1.4604, + "step": 2083 + }, + { + "epoch": 0.22, + "learning_rate": 1.9155293968454826e-05, + "loss": 1.4929, + "step": 2084 + }, + { + "epoch": 0.22, + "learning_rate": 1.9153821015683937e-05, + "loss": 1.4106, + "step": 2085 + }, + { + "epoch": 0.22, + "learning_rate": 1.915234683653623e-05, + "loss": 1.4146, + "step": 2086 + }, + { + "epoch": 0.22, + "learning_rate": 1.9150871431209207e-05, + "loss": 1.4481, + "step": 2087 + }, + { + "epoch": 0.22, + "learning_rate": 1.914939479990054e-05, + "loss": 1.5206, + "step": 2088 + }, + { + "epoch": 0.22, + "learning_rate": 1.9147916942808054e-05, + "loss": 1.5073, + "step": 2089 + }, + { + "epoch": 0.22, + "learning_rate": 1.9146437860129745e-05, + "loss": 1.5196, + "step": 2090 + }, + { + "epoch": 0.22, + "learning_rate": 1.9144957552063775e-05, + "loss": 1.5389, + "step": 2091 + }, + { + "epoch": 0.22, + "learning_rate": 1.9143476018808463e-05, + "loss": 1.5207, + "step": 2092 + }, + { + "epoch": 0.22, + "learning_rate": 1.9141993260562298e-05, + "loss": 1.3717, + "step": 2093 + }, + { + "epoch": 0.22, + "learning_rate": 1.9140509277523937e-05, + "loss": 1.471, + "step": 2094 + }, + { + "epoch": 0.22, + "learning_rate": 1.9139024069892185e-05, + "loss": 1.4553, + "step": 2095 + }, + { + "epoch": 0.22, + "learning_rate": 1.9137537637866027e-05, + "loss": 1.5311, + "step": 2096 + }, + { + "epoch": 0.22, + "learning_rate": 1.9136049981644614e-05, + "loss": 1.4369, + "step": 2097 + }, + { + "epoch": 0.22, + "learning_rate": 1.913456110142724e-05, + "loss": 1.4528, + "step": 2098 + }, + { + "epoch": 0.22, + "learning_rate": 1.9133070997413384e-05, + "loss": 1.5294, + "step": 2099 + }, + { + "epoch": 0.22, + "learning_rate": 1.9131579669802685e-05, + "loss": 1.4588, + "step": 2100 + }, + { + "epoch": 0.22, + "learning_rate": 1.9130087118794934e-05, + "loss": 1.443, + "step": 2101 + }, + { + "epoch": 0.22, + "learning_rate": 1.9128593344590102e-05, + "loss": 1.4876, + "step": 2102 + }, + { + "epoch": 0.22, + "learning_rate": 1.912709834738831e-05, + "loss": 1.4874, + "step": 2103 + }, + { + "epoch": 0.22, + "learning_rate": 1.9125602127389856e-05, + "loss": 1.4966, + "step": 2104 + }, + { + "epoch": 0.22, + "learning_rate": 1.912410468479519e-05, + "loss": 1.5747, + "step": 2105 + }, + { + "epoch": 0.22, + "learning_rate": 1.9122606019804933e-05, + "loss": 1.4025, + "step": 2106 + }, + { + "epoch": 0.22, + "learning_rate": 1.912110613261987e-05, + "loss": 1.4755, + "step": 2107 + }, + { + "epoch": 0.22, + "learning_rate": 1.911960502344094e-05, + "loss": 1.4739, + "step": 2108 + }, + { + "epoch": 0.22, + "learning_rate": 1.911810269246926e-05, + "loss": 1.4992, + "step": 2109 + }, + { + "epoch": 0.22, + "learning_rate": 1.91165991399061e-05, + "loss": 1.4435, + "step": 2110 + }, + { + "epoch": 0.22, + "learning_rate": 1.91150943659529e-05, + "loss": 1.4918, + "step": 2111 + }, + { + "epoch": 0.22, + "learning_rate": 1.9113588370811258e-05, + "loss": 1.3818, + "step": 2112 + }, + { + "epoch": 0.22, + "learning_rate": 1.911208115468294e-05, + "loss": 1.5105, + "step": 2113 + }, + { + "epoch": 0.22, + "learning_rate": 1.9110572717769878e-05, + "loss": 1.6634, + "step": 2114 + }, + { + "epoch": 0.22, + "learning_rate": 1.9109063060274158e-05, + "loss": 1.5028, + "step": 2115 + }, + { + "epoch": 0.22, + "learning_rate": 1.9107552182398037e-05, + "loss": 1.6657, + "step": 2116 + }, + { + "epoch": 0.22, + "learning_rate": 1.9106040084343935e-05, + "loss": 1.5481, + "step": 2117 + }, + { + "epoch": 0.22, + "learning_rate": 1.910452676631444e-05, + "loss": 1.4505, + "step": 2118 + }, + { + "epoch": 0.22, + "learning_rate": 1.9103012228512284e-05, + "loss": 1.5173, + "step": 2119 + }, + { + "epoch": 0.22, + "learning_rate": 1.9101496471140385e-05, + "loss": 1.3788, + "step": 2120 + }, + { + "epoch": 0.22, + "learning_rate": 1.9099979494401814e-05, + "loss": 1.4649, + "step": 2121 + }, + { + "epoch": 0.22, + "learning_rate": 1.9098461298499805e-05, + "loss": 1.4204, + "step": 2122 + }, + { + "epoch": 0.22, + "learning_rate": 1.9096941883637766e-05, + "loss": 1.4439, + "step": 2123 + }, + { + "epoch": 0.22, + "learning_rate": 1.909542125001925e-05, + "loss": 1.6615, + "step": 2124 + }, + { + "epoch": 0.22, + "learning_rate": 1.9093899397847985e-05, + "loss": 1.4763, + "step": 2125 + }, + { + "epoch": 0.22, + "learning_rate": 1.909237632732786e-05, + "loss": 1.5353, + "step": 2126 + }, + { + "epoch": 0.22, + "learning_rate": 1.909085203866293e-05, + "loss": 1.442, + "step": 2127 + }, + { + "epoch": 0.22, + "learning_rate": 1.9089326532057408e-05, + "loss": 1.4782, + "step": 2128 + }, + { + "epoch": 0.22, + "learning_rate": 1.908779980771567e-05, + "loss": 1.4933, + "step": 2129 + }, + { + "epoch": 0.22, + "learning_rate": 1.9086271865842264e-05, + "loss": 1.5285, + "step": 2130 + }, + { + "epoch": 0.22, + "learning_rate": 1.9084742706641894e-05, + "loss": 1.4736, + "step": 2131 + }, + { + "epoch": 0.22, + "learning_rate": 1.9083212330319427e-05, + "loss": 1.4496, + "step": 2132 + }, + { + "epoch": 0.22, + "learning_rate": 1.908168073707989e-05, + "loss": 1.5099, + "step": 2133 + }, + { + "epoch": 0.22, + "learning_rate": 1.9080147927128483e-05, + "loss": 1.5235, + "step": 2134 + }, + { + "epoch": 0.22, + "learning_rate": 1.9078613900670556e-05, + "loss": 1.4769, + "step": 2135 + }, + { + "epoch": 0.22, + "learning_rate": 1.907707865791164e-05, + "loss": 1.5771, + "step": 2136 + }, + { + "epoch": 0.22, + "learning_rate": 1.907554219905741e-05, + "loss": 1.5116, + "step": 2137 + }, + { + "epoch": 0.22, + "learning_rate": 1.907400452431371e-05, + "loss": 1.5161, + "step": 2138 + }, + { + "epoch": 0.22, + "learning_rate": 1.9072465633886557e-05, + "loss": 1.4356, + "step": 2139 + }, + { + "epoch": 0.22, + "learning_rate": 1.9070925527982117e-05, + "loss": 1.509, + "step": 2140 + }, + { + "epoch": 0.22, + "learning_rate": 1.9069384206806723e-05, + "loss": 1.4681, + "step": 2141 + }, + { + "epoch": 0.22, + "learning_rate": 1.9067841670566883e-05, + "loss": 1.5254, + "step": 2142 + }, + { + "epoch": 0.22, + "learning_rate": 1.9066297919469242e-05, + "loss": 1.4797, + "step": 2143 + }, + { + "epoch": 0.22, + "learning_rate": 1.9064752953720636e-05, + "loss": 1.3996, + "step": 2144 + }, + { + "epoch": 0.22, + "learning_rate": 1.9063206773528042e-05, + "loss": 1.4457, + "step": 2145 + }, + { + "epoch": 0.23, + "learning_rate": 1.9061659379098617e-05, + "loss": 1.5126, + "step": 2146 + }, + { + "epoch": 0.23, + "learning_rate": 1.9060110770639664e-05, + "loss": 1.5925, + "step": 2147 + }, + { + "epoch": 0.23, + "learning_rate": 1.905856094835866e-05, + "loss": 1.5146, + "step": 2148 + }, + { + "epoch": 0.23, + "learning_rate": 1.905700991246324e-05, + "loss": 1.7256, + "step": 2149 + }, + { + "epoch": 0.23, + "learning_rate": 1.90554576631612e-05, + "loss": 1.57, + "step": 2150 + }, + { + "epoch": 0.23, + "learning_rate": 1.905390420066051e-05, + "loss": 1.3722, + "step": 2151 + }, + { + "epoch": 0.23, + "learning_rate": 1.9052349525169292e-05, + "loss": 1.3999, + "step": 2152 + }, + { + "epoch": 0.23, + "learning_rate": 1.9050793636895828e-05, + "loss": 1.586, + "step": 2153 + }, + { + "epoch": 0.23, + "learning_rate": 1.9049236536048567e-05, + "loss": 1.4884, + "step": 2154 + }, + { + "epoch": 0.23, + "learning_rate": 1.9047678222836127e-05, + "loss": 1.5898, + "step": 2155 + }, + { + "epoch": 0.23, + "learning_rate": 1.9046118697467278e-05, + "loss": 1.569, + "step": 2156 + }, + { + "epoch": 0.23, + "learning_rate": 1.904455796015095e-05, + "loss": 1.5592, + "step": 2157 + }, + { + "epoch": 0.23, + "learning_rate": 1.9042996011096253e-05, + "loss": 1.597, + "step": 2158 + }, + { + "epoch": 0.23, + "learning_rate": 1.904143285051244e-05, + "loss": 1.422, + "step": 2159 + }, + { + "epoch": 0.23, + "learning_rate": 1.903986847860894e-05, + "loss": 1.519, + "step": 2160 + }, + { + "epoch": 0.23, + "learning_rate": 1.9038302895595334e-05, + "loss": 1.5197, + "step": 2161 + }, + { + "epoch": 0.23, + "learning_rate": 1.903673610168137e-05, + "loss": 1.4655, + "step": 2162 + }, + { + "epoch": 0.23, + "learning_rate": 1.9035168097076965e-05, + "loss": 1.3909, + "step": 2163 + }, + { + "epoch": 0.23, + "learning_rate": 1.903359888199218e-05, + "loss": 1.4877, + "step": 2164 + }, + { + "epoch": 0.23, + "learning_rate": 1.903202845663726e-05, + "loss": 1.5123, + "step": 2165 + }, + { + "epoch": 0.23, + "learning_rate": 1.9030456821222593e-05, + "loss": 1.4906, + "step": 2166 + }, + { + "epoch": 0.23, + "learning_rate": 1.9028883975958745e-05, + "loss": 1.4574, + "step": 2167 + }, + { + "epoch": 0.23, + "learning_rate": 1.9027309921056435e-05, + "loss": 1.4571, + "step": 2168 + }, + { + "epoch": 0.23, + "learning_rate": 1.902573465672654e-05, + "loss": 1.4281, + "step": 2169 + }, + { + "epoch": 0.23, + "learning_rate": 1.9024158183180116e-05, + "loss": 1.5057, + "step": 2170 + }, + { + "epoch": 0.23, + "learning_rate": 1.902258050062836e-05, + "loss": 1.4514, + "step": 2171 + }, + { + "epoch": 0.23, + "learning_rate": 1.9021001609282646e-05, + "loss": 1.5055, + "step": 2172 + }, + { + "epoch": 0.23, + "learning_rate": 1.9019421509354505e-05, + "loss": 1.4578, + "step": 2173 + }, + { + "epoch": 0.23, + "learning_rate": 1.9017840201055625e-05, + "loss": 1.459, + "step": 2174 + }, + { + "epoch": 0.23, + "learning_rate": 1.9016257684597864e-05, + "loss": 1.5059, + "step": 2175 + }, + { + "epoch": 0.23, + "learning_rate": 1.901467396019324e-05, + "loss": 1.57, + "step": 2176 + }, + { + "epoch": 0.23, + "learning_rate": 1.901308902805393e-05, + "loss": 1.4924, + "step": 2177 + }, + { + "epoch": 0.23, + "learning_rate": 1.9011502888392273e-05, + "loss": 1.4979, + "step": 2178 + }, + { + "epoch": 0.23, + "learning_rate": 1.900991554142077e-05, + "loss": 1.5321, + "step": 2179 + }, + { + "epoch": 0.23, + "learning_rate": 1.9008326987352093e-05, + "loss": 1.493, + "step": 2180 + }, + { + "epoch": 0.23, + "learning_rate": 1.9006737226399056e-05, + "loss": 1.5111, + "step": 2181 + }, + { + "epoch": 0.23, + "learning_rate": 1.900514625877465e-05, + "loss": 1.4154, + "step": 2182 + }, + { + "epoch": 0.23, + "learning_rate": 1.900355408469203e-05, + "loss": 1.4934, + "step": 2183 + }, + { + "epoch": 0.23, + "learning_rate": 1.90019607043645e-05, + "loss": 1.5975, + "step": 2184 + }, + { + "epoch": 0.23, + "learning_rate": 1.9000366118005532e-05, + "loss": 1.3537, + "step": 2185 + }, + { + "epoch": 0.23, + "learning_rate": 1.899877032582876e-05, + "loss": 1.4583, + "step": 2186 + }, + { + "epoch": 0.23, + "learning_rate": 1.8997173328047984e-05, + "loss": 1.4586, + "step": 2187 + }, + { + "epoch": 0.23, + "learning_rate": 1.8995575124877156e-05, + "loss": 1.4774, + "step": 2188 + }, + { + "epoch": 0.23, + "learning_rate": 1.8993975716530394e-05, + "loss": 1.5025, + "step": 2189 + }, + { + "epoch": 0.23, + "eval_loss": 1.5263344049453735, + "eval_runtime": 77.1492, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 2189 + }, + { + "epoch": 0.23, + "learning_rate": 1.899237510322198e-05, + "loss": 1.5438, + "step": 2190 + }, + { + "epoch": 0.23, + "learning_rate": 1.899077328516635e-05, + "loss": 1.5181, + "step": 2191 + }, + { + "epoch": 0.23, + "learning_rate": 1.8989170262578112e-05, + "loss": 1.4454, + "step": 2192 + }, + { + "epoch": 0.23, + "learning_rate": 1.8987566035672028e-05, + "loss": 1.4882, + "step": 2193 + }, + { + "epoch": 0.23, + "learning_rate": 1.8985960604663026e-05, + "loss": 1.5073, + "step": 2194 + }, + { + "epoch": 0.23, + "learning_rate": 1.8984353969766187e-05, + "loss": 1.4478, + "step": 2195 + }, + { + "epoch": 0.23, + "learning_rate": 1.8982746131196763e-05, + "loss": 1.4768, + "step": 2196 + }, + { + "epoch": 0.23, + "learning_rate": 1.8981137089170162e-05, + "loss": 1.5116, + "step": 2197 + }, + { + "epoch": 0.23, + "learning_rate": 1.8979526843901952e-05, + "loss": 1.4202, + "step": 2198 + }, + { + "epoch": 0.23, + "learning_rate": 1.8977915395607867e-05, + "loss": 1.4736, + "step": 2199 + }, + { + "epoch": 0.23, + "learning_rate": 1.89763027445038e-05, + "loss": 1.4489, + "step": 2200 + }, + { + "epoch": 0.23, + "learning_rate": 1.8974688890805804e-05, + "loss": 1.4512, + "step": 2201 + }, + { + "epoch": 0.23, + "learning_rate": 1.897307383473009e-05, + "loss": 1.5091, + "step": 2202 + }, + { + "epoch": 0.23, + "learning_rate": 1.897145757649304e-05, + "loss": 1.5512, + "step": 2203 + }, + { + "epoch": 0.23, + "learning_rate": 1.8969840116311192e-05, + "loss": 1.406, + "step": 2204 + }, + { + "epoch": 0.23, + "learning_rate": 1.896822145440124e-05, + "loss": 1.4531, + "step": 2205 + }, + { + "epoch": 0.23, + "learning_rate": 1.896660159098004e-05, + "loss": 1.4379, + "step": 2206 + }, + { + "epoch": 0.23, + "learning_rate": 1.896498052626462e-05, + "loss": 1.4783, + "step": 2207 + }, + { + "epoch": 0.23, + "learning_rate": 1.896335826047216e-05, + "loss": 1.4801, + "step": 2208 + }, + { + "epoch": 0.23, + "learning_rate": 1.896173479381999e-05, + "loss": 1.4526, + "step": 2209 + }, + { + "epoch": 0.23, + "learning_rate": 1.8960110126525627e-05, + "loss": 1.4952, + "step": 2210 + }, + { + "epoch": 0.23, + "learning_rate": 1.895848425880673e-05, + "loss": 1.5299, + "step": 2211 + }, + { + "epoch": 0.23, + "learning_rate": 1.8956857190881125e-05, + "loss": 1.5274, + "step": 2212 + }, + { + "epoch": 0.23, + "learning_rate": 1.8955228922966792e-05, + "loss": 1.4415, + "step": 2213 + }, + { + "epoch": 0.23, + "learning_rate": 1.8953599455281884e-05, + "loss": 1.5311, + "step": 2214 + }, + { + "epoch": 0.23, + "learning_rate": 1.8951968788044702e-05, + "loss": 1.4972, + "step": 2215 + }, + { + "epoch": 0.23, + "learning_rate": 1.8950336921473715e-05, + "loss": 1.4966, + "step": 2216 + }, + { + "epoch": 0.23, + "learning_rate": 1.8948703855787553e-05, + "loss": 1.4683, + "step": 2217 + }, + { + "epoch": 0.23, + "learning_rate": 1.8947069591205005e-05, + "loss": 1.503, + "step": 2218 + }, + { + "epoch": 0.23, + "learning_rate": 1.8945434127945014e-05, + "loss": 1.4902, + "step": 2219 + }, + { + "epoch": 0.23, + "learning_rate": 1.8943797466226702e-05, + "loss": 1.4835, + "step": 2220 + }, + { + "epoch": 0.23, + "learning_rate": 1.8942159606269332e-05, + "loss": 1.535, + "step": 2221 + }, + { + "epoch": 0.23, + "learning_rate": 1.8940520548292332e-05, + "loss": 1.491, + "step": 2222 + }, + { + "epoch": 0.23, + "learning_rate": 1.89388802925153e-05, + "loss": 1.5157, + "step": 2223 + }, + { + "epoch": 0.23, + "learning_rate": 1.8937238839157987e-05, + "loss": 1.4779, + "step": 2224 + }, + { + "epoch": 0.23, + "learning_rate": 1.8935596188440302e-05, + "loss": 1.4902, + "step": 2225 + }, + { + "epoch": 0.23, + "learning_rate": 1.8933952340582323e-05, + "loss": 1.4988, + "step": 2226 + }, + { + "epoch": 0.23, + "learning_rate": 1.893230729580428e-05, + "loss": 1.4568, + "step": 2227 + }, + { + "epoch": 0.23, + "learning_rate": 1.8930661054326567e-05, + "loss": 1.5163, + "step": 2228 + }, + { + "epoch": 0.23, + "learning_rate": 1.892901361636974e-05, + "loss": 1.4472, + "step": 2229 + }, + { + "epoch": 0.23, + "learning_rate": 1.892736498215451e-05, + "loss": 1.4658, + "step": 2230 + }, + { + "epoch": 0.23, + "learning_rate": 1.8925715151901754e-05, + "loss": 1.4281, + "step": 2231 + }, + { + "epoch": 0.23, + "learning_rate": 1.892406412583251e-05, + "loss": 1.415, + "step": 2232 + }, + { + "epoch": 0.23, + "learning_rate": 1.8922411904167966e-05, + "loss": 1.464, + "step": 2233 + }, + { + "epoch": 0.23, + "learning_rate": 1.892075848712948e-05, + "loss": 1.5014, + "step": 2234 + }, + { + "epoch": 0.23, + "learning_rate": 1.8919103874938568e-05, + "loss": 1.4397, + "step": 2235 + }, + { + "epoch": 0.23, + "learning_rate": 1.891744806781691e-05, + "loss": 1.5508, + "step": 2236 + }, + { + "epoch": 0.23, + "learning_rate": 1.8915791065986335e-05, + "loss": 1.4749, + "step": 2237 + }, + { + "epoch": 0.23, + "learning_rate": 1.891413286966884e-05, + "loss": 1.4538, + "step": 2238 + }, + { + "epoch": 0.23, + "learning_rate": 1.891247347908658e-05, + "loss": 1.4405, + "step": 2239 + }, + { + "epoch": 0.23, + "learning_rate": 1.8910812894461878e-05, + "loss": 1.3562, + "step": 2240 + }, + { + "epoch": 0.24, + "learning_rate": 1.89091511160172e-05, + "loss": 1.4811, + "step": 2241 + }, + { + "epoch": 0.24, + "learning_rate": 1.8907488143975186e-05, + "loss": 1.4286, + "step": 2242 + }, + { + "epoch": 0.24, + "learning_rate": 1.890582397855863e-05, + "loss": 1.4493, + "step": 2243 + }, + { + "epoch": 0.24, + "learning_rate": 1.890415861999049e-05, + "loss": 1.5639, + "step": 2244 + }, + { + "epoch": 0.24, + "learning_rate": 1.890249206849388e-05, + "loss": 1.6375, + "step": 2245 + }, + { + "epoch": 0.24, + "learning_rate": 1.890082432429208e-05, + "loss": 1.4982, + "step": 2246 + }, + { + "epoch": 0.24, + "learning_rate": 1.889915538760851e-05, + "loss": 1.492, + "step": 2247 + }, + { + "epoch": 0.24, + "learning_rate": 1.8897485258666778e-05, + "loss": 1.4294, + "step": 2248 + }, + { + "epoch": 0.24, + "learning_rate": 1.8895813937690638e-05, + "loss": 1.4617, + "step": 2249 + }, + { + "epoch": 0.24, + "learning_rate": 1.8894141424904e-05, + "loss": 1.4763, + "step": 2250 + }, + { + "epoch": 0.24, + "learning_rate": 1.8892467720530937e-05, + "loss": 1.3989, + "step": 2251 + }, + { + "epoch": 0.24, + "learning_rate": 1.8890792824795687e-05, + "loss": 1.4803, + "step": 2252 + }, + { + "epoch": 0.24, + "learning_rate": 1.8889116737922638e-05, + "loss": 1.4734, + "step": 2253 + }, + { + "epoch": 0.24, + "learning_rate": 1.8887439460136342e-05, + "loss": 1.5069, + "step": 2254 + }, + { + "epoch": 0.24, + "learning_rate": 1.8885760991661514e-05, + "loss": 1.5565, + "step": 2255 + }, + { + "epoch": 0.24, + "learning_rate": 1.8884081332723028e-05, + "loss": 1.4707, + "step": 2256 + }, + { + "epoch": 0.24, + "learning_rate": 1.8882400483545913e-05, + "loss": 1.5077, + "step": 2257 + }, + { + "epoch": 0.24, + "learning_rate": 1.888071844435536e-05, + "loss": 1.5075, + "step": 2258 + }, + { + "epoch": 0.24, + "learning_rate": 1.8879035215376717e-05, + "loss": 1.5185, + "step": 2259 + }, + { + "epoch": 0.24, + "learning_rate": 1.887735079683549e-05, + "loss": 1.6266, + "step": 2260 + }, + { + "epoch": 0.24, + "learning_rate": 1.8875665188957354e-05, + "loss": 1.5013, + "step": 2261 + }, + { + "epoch": 0.24, + "learning_rate": 1.887397839196814e-05, + "loss": 1.4362, + "step": 2262 + }, + { + "epoch": 0.24, + "learning_rate": 1.8872290406093827e-05, + "loss": 1.4718, + "step": 2263 + }, + { + "epoch": 0.24, + "learning_rate": 1.8870601231560567e-05, + "loss": 1.5202, + "step": 2264 + }, + { + "epoch": 0.24, + "learning_rate": 1.8868910868594664e-05, + "loss": 1.5168, + "step": 2265 + }, + { + "epoch": 0.24, + "learning_rate": 1.8867219317422588e-05, + "loss": 1.5142, + "step": 2266 + }, + { + "epoch": 0.24, + "learning_rate": 1.8865526578270954e-05, + "loss": 1.4885, + "step": 2267 + }, + { + "epoch": 0.24, + "learning_rate": 1.8863832651366552e-05, + "loss": 1.5441, + "step": 2268 + }, + { + "epoch": 0.24, + "learning_rate": 1.8862137536936328e-05, + "loss": 1.4647, + "step": 2269 + }, + { + "epoch": 0.24, + "learning_rate": 1.8860441235207374e-05, + "loss": 1.5352, + "step": 2270 + }, + { + "epoch": 0.24, + "learning_rate": 1.8858743746406958e-05, + "loss": 1.4568, + "step": 2271 + }, + { + "epoch": 0.24, + "learning_rate": 1.8857045070762497e-05, + "loss": 1.4865, + "step": 2272 + }, + { + "epoch": 0.24, + "learning_rate": 1.8855345208501573e-05, + "loss": 1.4637, + "step": 2273 + }, + { + "epoch": 0.24, + "learning_rate": 1.8853644159851918e-05, + "loss": 1.4348, + "step": 2274 + }, + { + "epoch": 0.24, + "learning_rate": 1.8851941925041436e-05, + "loss": 1.4413, + "step": 2275 + }, + { + "epoch": 0.24, + "learning_rate": 1.8850238504298177e-05, + "loss": 1.4434, + "step": 2276 + }, + { + "epoch": 0.24, + "learning_rate": 1.884853389785036e-05, + "loss": 1.4822, + "step": 2277 + }, + { + "epoch": 0.24, + "learning_rate": 1.8846828105926356e-05, + "loss": 1.4632, + "step": 2278 + }, + { + "epoch": 0.24, + "learning_rate": 1.8845121128754698e-05, + "loss": 1.48, + "step": 2279 + }, + { + "epoch": 0.24, + "learning_rate": 1.8843412966564078e-05, + "loss": 1.4518, + "step": 2280 + }, + { + "epoch": 0.24, + "learning_rate": 1.884170361958334e-05, + "loss": 1.4334, + "step": 2281 + }, + { + "epoch": 0.24, + "learning_rate": 1.8839993088041502e-05, + "loss": 1.5131, + "step": 2282 + }, + { + "epoch": 0.24, + "learning_rate": 1.8838281372167724e-05, + "loss": 1.508, + "step": 2283 + }, + { + "epoch": 0.24, + "learning_rate": 1.8836568472191335e-05, + "loss": 1.4086, + "step": 2284 + }, + { + "epoch": 0.24, + "learning_rate": 1.883485438834182e-05, + "loss": 1.5021, + "step": 2285 + }, + { + "epoch": 0.24, + "learning_rate": 1.8833139120848817e-05, + "loss": 1.5083, + "step": 2286 + }, + { + "epoch": 0.24, + "learning_rate": 1.8831422669942137e-05, + "loss": 1.4162, + "step": 2287 + }, + { + "epoch": 0.24, + "learning_rate": 1.8829705035851734e-05, + "loss": 1.5494, + "step": 2288 + }, + { + "epoch": 0.24, + "learning_rate": 1.8827986218807724e-05, + "loss": 1.425, + "step": 2289 + }, + { + "epoch": 0.24, + "learning_rate": 1.8826266219040396e-05, + "loss": 1.5215, + "step": 2290 + }, + { + "epoch": 0.24, + "learning_rate": 1.8824545036780172e-05, + "loss": 1.5577, + "step": 2291 + }, + { + "epoch": 0.24, + "learning_rate": 1.8822822672257655e-05, + "loss": 1.4923, + "step": 2292 + }, + { + "epoch": 0.24, + "learning_rate": 1.8821099125703595e-05, + "loss": 1.4648, + "step": 2293 + }, + { + "epoch": 0.24, + "learning_rate": 1.8819374397348902e-05, + "loss": 1.471, + "step": 2294 + }, + { + "epoch": 0.24, + "learning_rate": 1.8817648487424648e-05, + "loss": 1.5658, + "step": 2295 + }, + { + "epoch": 0.24, + "learning_rate": 1.8815921396162058e-05, + "loss": 1.5348, + "step": 2296 + }, + { + "epoch": 0.24, + "learning_rate": 1.8814193123792518e-05, + "loss": 1.4081, + "step": 2297 + }, + { + "epoch": 0.24, + "learning_rate": 1.881246367054757e-05, + "loss": 1.4762, + "step": 2298 + }, + { + "epoch": 0.24, + "learning_rate": 1.8810733036658925e-05, + "loss": 1.4399, + "step": 2299 + }, + { + "epoch": 0.24, + "learning_rate": 1.8809001222358432e-05, + "loss": 1.4763, + "step": 2300 + }, + { + "epoch": 0.24, + "learning_rate": 1.880726822787812e-05, + "loss": 1.4874, + "step": 2301 + }, + { + "epoch": 0.24, + "learning_rate": 1.880553405345016e-05, + "loss": 1.4951, + "step": 2302 + }, + { + "epoch": 0.24, + "learning_rate": 1.8803798699306887e-05, + "loss": 1.4697, + "step": 2303 + }, + { + "epoch": 0.24, + "learning_rate": 1.880206216568079e-05, + "loss": 1.481, + "step": 2304 + }, + { + "epoch": 0.24, + "learning_rate": 1.880032445280453e-05, + "loss": 1.4485, + "step": 2305 + }, + { + "epoch": 0.24, + "learning_rate": 1.879858556091091e-05, + "loss": 1.4749, + "step": 2306 + }, + { + "epoch": 0.24, + "learning_rate": 1.8796845490232894e-05, + "loss": 1.5605, + "step": 2307 + }, + { + "epoch": 0.24, + "learning_rate": 1.879510424100361e-05, + "loss": 1.4835, + "step": 2308 + }, + { + "epoch": 0.24, + "learning_rate": 1.8793361813456346e-05, + "loss": 1.4344, + "step": 2309 + }, + { + "epoch": 0.24, + "learning_rate": 1.8791618207824532e-05, + "loss": 1.4571, + "step": 2310 + }, + { + "epoch": 0.24, + "learning_rate": 1.8789873424341772e-05, + "loss": 1.482, + "step": 2311 + }, + { + "epoch": 0.24, + "learning_rate": 1.8788127463241822e-05, + "loss": 1.4736, + "step": 2312 + }, + { + "epoch": 0.24, + "learning_rate": 1.8786380324758597e-05, + "loss": 1.4807, + "step": 2313 + }, + { + "epoch": 0.24, + "learning_rate": 1.8784632009126167e-05, + "loss": 1.4418, + "step": 2314 + }, + { + "epoch": 0.24, + "learning_rate": 1.878288251657876e-05, + "loss": 1.5248, + "step": 2315 + }, + { + "epoch": 0.24, + "learning_rate": 1.8781131847350768e-05, + "loss": 1.483, + "step": 2316 + }, + { + "epoch": 0.24, + "learning_rate": 1.877938000167673e-05, + "loss": 1.5474, + "step": 2317 + }, + { + "epoch": 0.24, + "learning_rate": 1.8777626979791347e-05, + "loss": 1.4671, + "step": 2318 + }, + { + "epoch": 0.24, + "learning_rate": 1.877587278192949e-05, + "loss": 1.3049, + "step": 2319 + }, + { + "epoch": 0.24, + "learning_rate": 1.877411740832616e-05, + "loss": 1.483, + "step": 2320 + }, + { + "epoch": 0.24, + "learning_rate": 1.877236085921655e-05, + "loss": 1.508, + "step": 2321 + }, + { + "epoch": 0.24, + "learning_rate": 1.8770603134835978e-05, + "loss": 1.4854, + "step": 2322 + }, + { + "epoch": 0.24, + "learning_rate": 1.8768844235419942e-05, + "loss": 1.4808, + "step": 2323 + }, + { + "epoch": 0.24, + "learning_rate": 1.8767084161204087e-05, + "loss": 1.5352, + "step": 2324 + }, + { + "epoch": 0.24, + "learning_rate": 1.8765322912424214e-05, + "loss": 1.5628, + "step": 2325 + }, + { + "epoch": 0.24, + "learning_rate": 1.8763560489316292e-05, + "loss": 1.494, + "step": 2326 + }, + { + "epoch": 0.24, + "learning_rate": 1.876179689211643e-05, + "loss": 1.509, + "step": 2327 + }, + { + "epoch": 0.24, + "learning_rate": 1.8760032121060918e-05, + "loss": 1.5021, + "step": 2328 + }, + { + "epoch": 0.24, + "learning_rate": 1.875826617638618e-05, + "loss": 1.4179, + "step": 2329 + }, + { + "epoch": 0.24, + "learning_rate": 1.8756499058328813e-05, + "loss": 1.4302, + "step": 2330 + }, + { + "epoch": 0.24, + "learning_rate": 1.8754730767125564e-05, + "loss": 1.4959, + "step": 2331 + }, + { + "epoch": 0.24, + "learning_rate": 1.8752961303013336e-05, + "loss": 1.4423, + "step": 2332 + }, + { + "epoch": 0.24, + "learning_rate": 1.8751190666229194e-05, + "loss": 1.4564, + "step": 2333 + }, + { + "epoch": 0.24, + "learning_rate": 1.8749418857010358e-05, + "loss": 1.4775, + "step": 2334 + }, + { + "epoch": 0.24, + "learning_rate": 1.8747645875594203e-05, + "loss": 1.4182, + "step": 2335 + }, + { + "epoch": 0.24, + "learning_rate": 1.8745871722218265e-05, + "loss": 1.3957, + "step": 2336 + }, + { + "epoch": 0.25, + "learning_rate": 1.8744096397120235e-05, + "loss": 1.4633, + "step": 2337 + }, + { + "epoch": 0.25, + "learning_rate": 1.874231990053796e-05, + "loss": 1.5512, + "step": 2338 + }, + { + "epoch": 0.25, + "learning_rate": 1.8740542232709444e-05, + "loss": 1.3461, + "step": 2339 + }, + { + "epoch": 0.25, + "learning_rate": 1.8738763393872848e-05, + "loss": 1.4754, + "step": 2340 + }, + { + "epoch": 0.25, + "learning_rate": 1.8736983384266495e-05, + "loss": 1.5448, + "step": 2341 + }, + { + "epoch": 0.25, + "learning_rate": 1.8735202204128854e-05, + "loss": 1.4491, + "step": 2342 + }, + { + "epoch": 0.25, + "learning_rate": 1.8733419853698566e-05, + "loss": 1.457, + "step": 2343 + }, + { + "epoch": 0.25, + "learning_rate": 1.8731636333214414e-05, + "loss": 1.4314, + "step": 2344 + }, + { + "epoch": 0.25, + "learning_rate": 1.8729851642915345e-05, + "loss": 1.3979, + "step": 2345 + }, + { + "epoch": 0.25, + "learning_rate": 1.8728065783040464e-05, + "loss": 1.4146, + "step": 2346 + }, + { + "epoch": 0.25, + "learning_rate": 1.8726278753829027e-05, + "loss": 1.4361, + "step": 2347 + }, + { + "epoch": 0.25, + "learning_rate": 1.872449055552045e-05, + "loss": 1.4989, + "step": 2348 + }, + { + "epoch": 0.25, + "learning_rate": 1.872270118835431e-05, + "loss": 1.5062, + "step": 2349 + }, + { + "epoch": 0.25, + "learning_rate": 1.872091065257033e-05, + "loss": 1.4509, + "step": 2350 + }, + { + "epoch": 0.25, + "learning_rate": 1.8719118948408403e-05, + "loss": 1.4631, + "step": 2351 + }, + { + "epoch": 0.25, + "learning_rate": 1.8717326076108566e-05, + "loss": 1.5119, + "step": 2352 + }, + { + "epoch": 0.25, + "learning_rate": 1.8715532035911017e-05, + "loss": 1.6347, + "step": 2353 + }, + { + "epoch": 0.25, + "learning_rate": 1.8713736828056115e-05, + "loss": 1.5526, + "step": 2354 + }, + { + "epoch": 0.25, + "learning_rate": 1.8711940452784368e-05, + "loss": 1.6348, + "step": 2355 + }, + { + "epoch": 0.25, + "learning_rate": 1.871014291033645e-05, + "loss": 1.5183, + "step": 2356 + }, + { + "epoch": 0.25, + "learning_rate": 1.8708344200953182e-05, + "loss": 1.458, + "step": 2357 + }, + { + "epoch": 0.25, + "learning_rate": 1.8706544324875545e-05, + "loss": 1.524, + "step": 2358 + }, + { + "epoch": 0.25, + "learning_rate": 1.8704743282344672e-05, + "loss": 1.4479, + "step": 2359 + }, + { + "epoch": 0.25, + "learning_rate": 1.870294107360186e-05, + "loss": 1.5408, + "step": 2360 + }, + { + "epoch": 0.25, + "learning_rate": 1.8701137698888563e-05, + "loss": 1.5007, + "step": 2361 + }, + { + "epoch": 0.25, + "learning_rate": 1.8699333158446382e-05, + "loss": 1.5132, + "step": 2362 + }, + { + "epoch": 0.25, + "learning_rate": 1.869752745251708e-05, + "loss": 1.4263, + "step": 2363 + }, + { + "epoch": 0.25, + "learning_rate": 1.8695720581342574e-05, + "loss": 1.422, + "step": 2364 + }, + { + "epoch": 0.25, + "learning_rate": 1.869391254516494e-05, + "loss": 1.4411, + "step": 2365 + }, + { + "epoch": 0.25, + "learning_rate": 1.8692103344226406e-05, + "loss": 1.4594, + "step": 2366 + }, + { + "epoch": 0.25, + "learning_rate": 1.8690292978769364e-05, + "loss": 1.4992, + "step": 2367 + }, + { + "epoch": 0.25, + "learning_rate": 1.868848144903635e-05, + "loss": 1.4822, + "step": 2368 + }, + { + "epoch": 0.25, + "learning_rate": 1.8686668755270064e-05, + "loss": 1.5402, + "step": 2369 + }, + { + "epoch": 0.25, + "learning_rate": 1.8684854897713363e-05, + "loss": 1.5268, + "step": 2370 + }, + { + "epoch": 0.25, + "learning_rate": 1.8683039876609258e-05, + "loss": 1.5587, + "step": 2371 + }, + { + "epoch": 0.25, + "learning_rate": 1.868122369220091e-05, + "loss": 1.4214, + "step": 2372 + }, + { + "epoch": 0.25, + "learning_rate": 1.8679406344731645e-05, + "loss": 1.5089, + "step": 2373 + }, + { + "epoch": 0.25, + "learning_rate": 1.867758783444494e-05, + "loss": 1.5067, + "step": 2374 + }, + { + "epoch": 0.25, + "learning_rate": 1.8675768161584427e-05, + "loss": 2.0616, + "step": 2375 + }, + { + "epoch": 0.25, + "learning_rate": 1.8673947326393903e-05, + "loss": 1.5617, + "step": 2376 + }, + { + "epoch": 0.25, + "learning_rate": 1.86721253291173e-05, + "loss": 1.4422, + "step": 2377 + }, + { + "epoch": 0.25, + "learning_rate": 1.867030216999873e-05, + "loss": 1.4727, + "step": 2378 + }, + { + "epoch": 0.25, + "learning_rate": 1.8668477849282443e-05, + "loss": 1.4152, + "step": 2379 + }, + { + "epoch": 0.25, + "learning_rate": 1.8666652367212856e-05, + "loss": 1.4376, + "step": 2380 + }, + { + "epoch": 0.25, + "learning_rate": 1.8664825724034534e-05, + "loss": 1.393, + "step": 2381 + }, + { + "epoch": 0.25, + "learning_rate": 1.8662997919992197e-05, + "loss": 1.4864, + "step": 2382 + }, + { + "epoch": 0.25, + "learning_rate": 1.866116895533073e-05, + "loss": 1.4261, + "step": 2383 + }, + { + "epoch": 0.25, + "learning_rate": 1.8659338830295163e-05, + "loss": 1.4555, + "step": 2384 + }, + { + "epoch": 0.25, + "learning_rate": 1.8657507545130687e-05, + "loss": 1.4939, + "step": 2385 + }, + { + "epoch": 0.25, + "learning_rate": 1.865567510008265e-05, + "loss": 1.4123, + "step": 2386 + }, + { + "epoch": 0.25, + "learning_rate": 1.8653841495396546e-05, + "loss": 1.4459, + "step": 2387 + }, + { + "epoch": 0.25, + "learning_rate": 1.8652006731318038e-05, + "loss": 1.396, + "step": 2388 + }, + { + "epoch": 0.25, + "eval_loss": 1.5139706134796143, + "eval_runtime": 77.2904, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 2388 + }, + { + "epoch": 0.25, + "learning_rate": 1.8650170808092936e-05, + "loss": 1.4666, + "step": 2389 + }, + { + "epoch": 0.25, + "learning_rate": 1.86483337259672e-05, + "loss": 1.5154, + "step": 2390 + }, + { + "epoch": 0.25, + "learning_rate": 1.864649548518696e-05, + "loss": 1.5163, + "step": 2391 + }, + { + "epoch": 0.25, + "learning_rate": 1.864465608599849e-05, + "loss": 1.4734, + "step": 2392 + }, + { + "epoch": 0.25, + "learning_rate": 1.864281552864822e-05, + "loss": 1.5217, + "step": 2393 + }, + { + "epoch": 0.25, + "learning_rate": 1.8640973813382737e-05, + "loss": 1.4694, + "step": 2394 + }, + { + "epoch": 0.25, + "learning_rate": 1.863913094044879e-05, + "loss": 1.4761, + "step": 2395 + }, + { + "epoch": 0.25, + "learning_rate": 1.863728691009327e-05, + "loss": 1.4766, + "step": 2396 + }, + { + "epoch": 0.25, + "learning_rate": 1.863544172256323e-05, + "loss": 1.5695, + "step": 2397 + }, + { + "epoch": 0.25, + "learning_rate": 1.8633595378105882e-05, + "loss": 1.5079, + "step": 2398 + }, + { + "epoch": 0.25, + "learning_rate": 1.8631747876968584e-05, + "loss": 1.4154, + "step": 2399 + }, + { + "epoch": 0.25, + "learning_rate": 1.862989921939886e-05, + "loss": 1.4488, + "step": 2400 + }, + { + "epoch": 0.25, + "learning_rate": 1.8628049405644376e-05, + "loss": 1.4279, + "step": 2401 + }, + { + "epoch": 0.25, + "learning_rate": 1.8626198435952966e-05, + "loss": 1.4896, + "step": 2402 + }, + { + "epoch": 0.25, + "learning_rate": 1.8624346310572602e-05, + "loss": 1.4315, + "step": 2403 + }, + { + "epoch": 0.25, + "learning_rate": 1.862249302975143e-05, + "loss": 1.4919, + "step": 2404 + }, + { + "epoch": 0.25, + "learning_rate": 1.8620638593737743e-05, + "loss": 1.4561, + "step": 2405 + }, + { + "epoch": 0.25, + "learning_rate": 1.8618783002779985e-05, + "loss": 1.4622, + "step": 2406 + }, + { + "epoch": 0.25, + "learning_rate": 1.8616926257126754e-05, + "loss": 1.4917, + "step": 2407 + }, + { + "epoch": 0.25, + "learning_rate": 1.861506835702681e-05, + "loss": 1.4962, + "step": 2408 + }, + { + "epoch": 0.25, + "learning_rate": 1.861320930272906e-05, + "loss": 1.4164, + "step": 2409 + }, + { + "epoch": 0.25, + "learning_rate": 1.8611349094482578e-05, + "loss": 1.4889, + "step": 2410 + }, + { + "epoch": 0.25, + "learning_rate": 1.8609487732536576e-05, + "loss": 1.543, + "step": 2411 + }, + { + "epoch": 0.25, + "learning_rate": 1.8607625217140433e-05, + "loss": 1.5417, + "step": 2412 + }, + { + "epoch": 0.25, + "learning_rate": 1.8605761548543674e-05, + "loss": 1.5304, + "step": 2413 + }, + { + "epoch": 0.25, + "learning_rate": 1.860389672699599e-05, + "loss": 1.4725, + "step": 2414 + }, + { + "epoch": 0.25, + "learning_rate": 1.860203075274721e-05, + "loss": 1.4745, + "step": 2415 + }, + { + "epoch": 0.25, + "learning_rate": 1.8600163626047334e-05, + "loss": 1.4656, + "step": 2416 + }, + { + "epoch": 0.25, + "learning_rate": 1.8598295347146503e-05, + "loss": 1.5287, + "step": 2417 + }, + { + "epoch": 0.25, + "learning_rate": 1.8596425916295023e-05, + "loss": 1.5024, + "step": 2418 + }, + { + "epoch": 0.25, + "learning_rate": 1.8594555333743348e-05, + "loss": 1.4527, + "step": 2419 + }, + { + "epoch": 0.25, + "learning_rate": 1.859268359974209e-05, + "loss": 1.4897, + "step": 2420 + }, + { + "epoch": 0.25, + "learning_rate": 1.859081071454201e-05, + "loss": 1.3554, + "step": 2421 + }, + { + "epoch": 0.25, + "learning_rate": 1.858893667839403e-05, + "loss": 1.4004, + "step": 2422 + }, + { + "epoch": 0.25, + "learning_rate": 1.858706149154922e-05, + "loss": 1.5582, + "step": 2423 + }, + { + "epoch": 0.25, + "learning_rate": 1.8585185154258803e-05, + "loss": 1.505, + "step": 2424 + }, + { + "epoch": 0.25, + "learning_rate": 1.858330766677417e-05, + "loss": 1.5043, + "step": 2425 + }, + { + "epoch": 0.25, + "learning_rate": 1.858142902934685e-05, + "loss": 1.439, + "step": 2426 + }, + { + "epoch": 0.25, + "learning_rate": 1.857954924222853e-05, + "loss": 1.4927, + "step": 2427 + }, + { + "epoch": 0.25, + "learning_rate": 1.8577668305671056e-05, + "loss": 1.5395, + "step": 2428 + }, + { + "epoch": 0.25, + "learning_rate": 1.8575786219926427e-05, + "loss": 1.4737, + "step": 2429 + }, + { + "epoch": 0.25, + "learning_rate": 1.8573902985246794e-05, + "loss": 1.6151, + "step": 2430 + }, + { + "epoch": 0.25, + "learning_rate": 1.857201860188446e-05, + "loss": 1.4313, + "step": 2431 + }, + { + "epoch": 0.26, + "learning_rate": 1.857013307009188e-05, + "loss": 1.4509, + "step": 2432 + }, + { + "epoch": 0.26, + "learning_rate": 1.8568246390121673e-05, + "loss": 1.3998, + "step": 2433 + }, + { + "epoch": 0.26, + "learning_rate": 1.8566358562226603e-05, + "loss": 1.5268, + "step": 2434 + }, + { + "epoch": 0.26, + "learning_rate": 1.8564469586659593e-05, + "loss": 1.4369, + "step": 2435 + }, + { + "epoch": 0.26, + "learning_rate": 1.8562579463673713e-05, + "loss": 1.4759, + "step": 2436 + }, + { + "epoch": 0.26, + "learning_rate": 1.8560688193522197e-05, + "loss": 1.4092, + "step": 2437 + }, + { + "epoch": 0.26, + "learning_rate": 1.855879577645842e-05, + "loss": 1.43, + "step": 2438 + }, + { + "epoch": 0.26, + "learning_rate": 1.855690221273592e-05, + "loss": 1.5143, + "step": 2439 + }, + { + "epoch": 0.26, + "learning_rate": 1.8555007502608385e-05, + "loss": 1.5482, + "step": 2440 + }, + { + "epoch": 0.26, + "learning_rate": 1.855311164632966e-05, + "loss": 1.4406, + "step": 2441 + }, + { + "epoch": 0.26, + "learning_rate": 1.8551214644153738e-05, + "loss": 1.4551, + "step": 2442 + }, + { + "epoch": 0.26, + "learning_rate": 1.8549316496334774e-05, + "loss": 1.4663, + "step": 2443 + }, + { + "epoch": 0.26, + "learning_rate": 1.8547417203127064e-05, + "loss": 1.4732, + "step": 2444 + }, + { + "epoch": 0.26, + "learning_rate": 1.8545516764785067e-05, + "loss": 1.5378, + "step": 2445 + }, + { + "epoch": 0.26, + "learning_rate": 1.8543615181563397e-05, + "loss": 1.4448, + "step": 2446 + }, + { + "epoch": 0.26, + "learning_rate": 1.854171245371681e-05, + "loss": 1.2861, + "step": 2447 + }, + { + "epoch": 0.26, + "learning_rate": 1.8539808581500228e-05, + "loss": 1.4405, + "step": 2448 + }, + { + "epoch": 0.26, + "learning_rate": 1.8537903565168716e-05, + "loss": 1.4876, + "step": 2449 + }, + { + "epoch": 0.26, + "learning_rate": 1.8535997404977506e-05, + "loss": 1.4119, + "step": 2450 + }, + { + "epoch": 0.26, + "learning_rate": 1.8534090101181967e-05, + "loss": 1.4451, + "step": 2451 + }, + { + "epoch": 0.26, + "learning_rate": 1.8532181654037632e-05, + "loss": 1.4035, + "step": 2452 + }, + { + "epoch": 0.26, + "learning_rate": 1.853027206380018e-05, + "loss": 1.4624, + "step": 2453 + }, + { + "epoch": 0.26, + "learning_rate": 1.852836133072545e-05, + "loss": 1.4935, + "step": 2454 + }, + { + "epoch": 0.26, + "learning_rate": 1.8526449455069434e-05, + "loss": 1.4834, + "step": 2455 + }, + { + "epoch": 0.26, + "learning_rate": 1.8524536437088266e-05, + "loss": 1.498, + "step": 2456 + }, + { + "epoch": 0.26, + "learning_rate": 1.8522622277038247e-05, + "loss": 1.3417, + "step": 2457 + }, + { + "epoch": 0.26, + "learning_rate": 1.852070697517583e-05, + "loss": 1.4455, + "step": 2458 + }, + { + "epoch": 0.26, + "learning_rate": 1.8518790531757607e-05, + "loss": 1.4119, + "step": 2459 + }, + { + "epoch": 0.26, + "learning_rate": 1.8516872947040337e-05, + "loss": 1.558, + "step": 2460 + }, + { + "epoch": 0.26, + "learning_rate": 1.8514954221280926e-05, + "loss": 1.4862, + "step": 2461 + }, + { + "epoch": 0.26, + "learning_rate": 1.8513034354736433e-05, + "loss": 1.6806, + "step": 2462 + }, + { + "epoch": 0.26, + "learning_rate": 1.8511113347664072e-05, + "loss": 1.438, + "step": 2463 + }, + { + "epoch": 0.26, + "learning_rate": 1.850919120032121e-05, + "loss": 1.4975, + "step": 2464 + }, + { + "epoch": 0.26, + "learning_rate": 1.850726791296536e-05, + "loss": 1.4409, + "step": 2465 + }, + { + "epoch": 0.26, + "learning_rate": 1.85053434858542e-05, + "loss": 1.4769, + "step": 2466 + }, + { + "epoch": 0.26, + "learning_rate": 1.8503417919245548e-05, + "loss": 1.5823, + "step": 2467 + }, + { + "epoch": 0.26, + "learning_rate": 1.8501491213397386e-05, + "loss": 1.4045, + "step": 2468 + }, + { + "epoch": 0.26, + "learning_rate": 1.8499563368567837e-05, + "loss": 1.4828, + "step": 2469 + }, + { + "epoch": 0.26, + "learning_rate": 1.849763438501519e-05, + "loss": 1.4684, + "step": 2470 + }, + { + "epoch": 0.26, + "learning_rate": 1.8495704262997873e-05, + "loss": 1.4577, + "step": 2471 + }, + { + "epoch": 0.26, + "learning_rate": 1.8493773002774475e-05, + "loss": 1.4759, + "step": 2472 + }, + { + "epoch": 0.26, + "learning_rate": 1.8491840604603736e-05, + "loss": 1.4259, + "step": 2473 + }, + { + "epoch": 0.26, + "learning_rate": 1.8489907068744543e-05, + "loss": 1.4717, + "step": 2474 + }, + { + "epoch": 0.26, + "learning_rate": 1.848797239545595e-05, + "loss": 1.4247, + "step": 2475 + }, + { + "epoch": 0.26, + "learning_rate": 1.8486036584997143e-05, + "loss": 1.4954, + "step": 2476 + }, + { + "epoch": 0.26, + "learning_rate": 1.8484099637627472e-05, + "loss": 1.4926, + "step": 2477 + }, + { + "epoch": 0.26, + "learning_rate": 1.8482161553606447e-05, + "loss": 1.487, + "step": 2478 + }, + { + "epoch": 0.26, + "learning_rate": 1.8480222333193715e-05, + "loss": 1.4553, + "step": 2479 + }, + { + "epoch": 0.26, + "learning_rate": 1.847828197664908e-05, + "loss": 1.4862, + "step": 2480 + }, + { + "epoch": 0.26, + "learning_rate": 1.8476340484232508e-05, + "loss": 1.4867, + "step": 2481 + }, + { + "epoch": 0.26, + "learning_rate": 1.8474397856204097e-05, + "loss": 1.4736, + "step": 2482 + }, + { + "epoch": 0.26, + "learning_rate": 1.8472454092824122e-05, + "loss": 1.4254, + "step": 2483 + }, + { + "epoch": 0.26, + "learning_rate": 1.8470509194352987e-05, + "loss": 1.4455, + "step": 2484 + }, + { + "epoch": 0.26, + "learning_rate": 1.8468563161051263e-05, + "loss": 1.4402, + "step": 2485 + }, + { + "epoch": 0.26, + "learning_rate": 1.846661599317967e-05, + "loss": 1.4611, + "step": 2486 + }, + { + "epoch": 0.26, + "learning_rate": 1.8464667690999073e-05, + "loss": 1.4814, + "step": 2487 + }, + { + "epoch": 0.26, + "learning_rate": 1.8462718254770503e-05, + "loss": 1.4559, + "step": 2488 + }, + { + "epoch": 0.26, + "learning_rate": 1.8460767684755127e-05, + "loss": 1.4667, + "step": 2489 + }, + { + "epoch": 0.26, + "learning_rate": 1.8458815981214274e-05, + "loss": 1.4427, + "step": 2490 + }, + { + "epoch": 0.26, + "learning_rate": 1.845686314440942e-05, + "loss": 1.4055, + "step": 2491 + }, + { + "epoch": 0.26, + "learning_rate": 1.8454909174602198e-05, + "loss": 1.5563, + "step": 2492 + }, + { + "epoch": 0.26, + "learning_rate": 1.845295407205439e-05, + "loss": 1.4631, + "step": 2493 + }, + { + "epoch": 0.26, + "learning_rate": 1.8450997837027925e-05, + "loss": 1.4887, + "step": 2494 + }, + { + "epoch": 0.26, + "learning_rate": 1.8449040469784895e-05, + "loss": 1.5212, + "step": 2495 + }, + { + "epoch": 0.26, + "learning_rate": 1.844708197058753e-05, + "loss": 1.5582, + "step": 2496 + }, + { + "epoch": 0.26, + "learning_rate": 1.844512233969822e-05, + "loss": 1.4599, + "step": 2497 + }, + { + "epoch": 0.26, + "learning_rate": 1.844316157737951e-05, + "loss": 1.4546, + "step": 2498 + }, + { + "epoch": 0.26, + "learning_rate": 1.844119968389409e-05, + "loss": 1.4631, + "step": 2499 + }, + { + "epoch": 0.26, + "learning_rate": 1.84392366595048e-05, + "loss": 1.4817, + "step": 2500 + }, + { + "epoch": 0.26, + "learning_rate": 1.8437272504474636e-05, + "loss": 1.4214, + "step": 2501 + }, + { + "epoch": 0.26, + "learning_rate": 1.8435307219066744e-05, + "loss": 1.471, + "step": 2502 + }, + { + "epoch": 0.26, + "learning_rate": 1.8433340803544424e-05, + "loss": 1.4693, + "step": 2503 + }, + { + "epoch": 0.26, + "learning_rate": 1.8431373258171127e-05, + "loss": 1.6297, + "step": 2504 + }, + { + "epoch": 0.26, + "learning_rate": 1.842940458321045e-05, + "loss": 1.5916, + "step": 2505 + }, + { + "epoch": 0.26, + "learning_rate": 1.842743477892614e-05, + "loss": 1.4754, + "step": 2506 + }, + { + "epoch": 0.26, + "learning_rate": 1.842546384558211e-05, + "loss": 1.4828, + "step": 2507 + }, + { + "epoch": 0.26, + "learning_rate": 1.842349178344241e-05, + "loss": 1.4239, + "step": 2508 + }, + { + "epoch": 0.26, + "learning_rate": 1.8421518592771243e-05, + "loss": 1.5028, + "step": 2509 + }, + { + "epoch": 0.26, + "learning_rate": 1.841954427383297e-05, + "loss": 1.4848, + "step": 2510 + }, + { + "epoch": 0.26, + "learning_rate": 1.8417568826892097e-05, + "loss": 1.4617, + "step": 2511 + }, + { + "epoch": 0.26, + "learning_rate": 1.8415592252213284e-05, + "loss": 1.4266, + "step": 2512 + }, + { + "epoch": 0.26, + "learning_rate": 1.8413614550061344e-05, + "loss": 1.4321, + "step": 2513 + }, + { + "epoch": 0.26, + "learning_rate": 1.841163572070123e-05, + "loss": 1.4693, + "step": 2514 + }, + { + "epoch": 0.26, + "learning_rate": 1.840965576439806e-05, + "loss": 1.4257, + "step": 2515 + }, + { + "epoch": 0.26, + "learning_rate": 1.84076746814171e-05, + "loss": 1.4488, + "step": 2516 + }, + { + "epoch": 0.26, + "learning_rate": 1.840569247202376e-05, + "loss": 1.5348, + "step": 2517 + }, + { + "epoch": 0.26, + "learning_rate": 1.8403709136483604e-05, + "loss": 1.477, + "step": 2518 + }, + { + "epoch": 0.26, + "learning_rate": 1.840172467506235e-05, + "loss": 1.443, + "step": 2519 + }, + { + "epoch": 0.26, + "learning_rate": 1.839973908802587e-05, + "loss": 1.4772, + "step": 2520 + }, + { + "epoch": 0.26, + "learning_rate": 1.839775237564017e-05, + "loss": 1.4443, + "step": 2521 + }, + { + "epoch": 0.26, + "learning_rate": 1.839576453817143e-05, + "loss": 1.4063, + "step": 2522 + }, + { + "epoch": 0.26, + "learning_rate": 1.8393775575885963e-05, + "loss": 1.5178, + "step": 2523 + }, + { + "epoch": 0.26, + "learning_rate": 1.8391785489050235e-05, + "loss": 1.4337, + "step": 2524 + }, + { + "epoch": 0.26, + "learning_rate": 1.8389794277930875e-05, + "loss": 1.4512, + "step": 2525 + }, + { + "epoch": 0.26, + "learning_rate": 1.838780194279465e-05, + "loss": 1.5578, + "step": 2526 + }, + { + "epoch": 0.26, + "learning_rate": 1.8385808483908484e-05, + "loss": 1.4606, + "step": 2527 + }, + { + "epoch": 0.27, + "learning_rate": 1.8383813901539444e-05, + "loss": 1.4957, + "step": 2528 + }, + { + "epoch": 0.27, + "learning_rate": 1.838181819595476e-05, + "loss": 1.4914, + "step": 2529 + }, + { + "epoch": 0.27, + "learning_rate": 1.8379821367421802e-05, + "loss": 1.4785, + "step": 2530 + }, + { + "epoch": 0.27, + "learning_rate": 1.837782341620809e-05, + "loss": 1.4052, + "step": 2531 + }, + { + "epoch": 0.27, + "learning_rate": 1.8375824342581303e-05, + "loss": 1.4807, + "step": 2532 + }, + { + "epoch": 0.27, + "learning_rate": 1.8373824146809264e-05, + "loss": 1.4313, + "step": 2533 + }, + { + "epoch": 0.27, + "learning_rate": 1.8371822829159945e-05, + "loss": 1.4374, + "step": 2534 + }, + { + "epoch": 0.27, + "learning_rate": 1.836982038990148e-05, + "loss": 1.4482, + "step": 2535 + }, + { + "epoch": 0.27, + "learning_rate": 1.8367816829302133e-05, + "loss": 1.5231, + "step": 2536 + }, + { + "epoch": 0.27, + "learning_rate": 1.8365812147630337e-05, + "loss": 1.4101, + "step": 2537 + }, + { + "epoch": 0.27, + "learning_rate": 1.8363806345154666e-05, + "loss": 1.4372, + "step": 2538 + }, + { + "epoch": 0.27, + "learning_rate": 1.8361799422143845e-05, + "loss": 1.4808, + "step": 2539 + }, + { + "epoch": 0.27, + "learning_rate": 1.835979137886675e-05, + "loss": 1.3515, + "step": 2540 + }, + { + "epoch": 0.27, + "learning_rate": 1.8357782215592412e-05, + "loss": 1.5284, + "step": 2541 + }, + { + "epoch": 0.27, + "learning_rate": 1.835577193259e-05, + "loss": 1.4222, + "step": 2542 + }, + { + "epoch": 0.27, + "learning_rate": 1.8353760530128846e-05, + "loss": 1.4522, + "step": 2543 + }, + { + "epoch": 0.27, + "learning_rate": 1.835174800847842e-05, + "loss": 1.4487, + "step": 2544 + }, + { + "epoch": 0.27, + "learning_rate": 1.8349734367908355e-05, + "loss": 1.3688, + "step": 2545 + }, + { + "epoch": 0.27, + "learning_rate": 1.8347719608688422e-05, + "loss": 1.483, + "step": 2546 + }, + { + "epoch": 0.27, + "learning_rate": 1.8345703731088554e-05, + "loss": 1.4733, + "step": 2547 + }, + { + "epoch": 0.27, + "learning_rate": 1.8343686735378816e-05, + "loss": 1.4594, + "step": 2548 + }, + { + "epoch": 0.27, + "learning_rate": 1.834166862182944e-05, + "loss": 1.4648, + "step": 2549 + }, + { + "epoch": 0.27, + "learning_rate": 1.8339649390710807e-05, + "loss": 1.5249, + "step": 2550 + }, + { + "epoch": 0.27, + "learning_rate": 1.8337629042293434e-05, + "loss": 1.4744, + "step": 2551 + }, + { + "epoch": 0.27, + "learning_rate": 1.8335607576847994e-05, + "loss": 1.5094, + "step": 2552 + }, + { + "epoch": 0.27, + "learning_rate": 1.8333584994645318e-05, + "loss": 1.5122, + "step": 2553 + }, + { + "epoch": 0.27, + "learning_rate": 1.8331561295956374e-05, + "loss": 1.537, + "step": 2554 + }, + { + "epoch": 0.27, + "learning_rate": 1.832953648105229e-05, + "loss": 1.4691, + "step": 2555 + }, + { + "epoch": 0.27, + "learning_rate": 1.8327510550204343e-05, + "loss": 1.4969, + "step": 2556 + }, + { + "epoch": 0.27, + "learning_rate": 1.8325483503683944e-05, + "loss": 1.4596, + "step": 2557 + }, + { + "epoch": 0.27, + "learning_rate": 1.8323455341762675e-05, + "loss": 1.435, + "step": 2558 + }, + { + "epoch": 0.27, + "learning_rate": 1.8321426064712255e-05, + "loss": 1.4883, + "step": 2559 + }, + { + "epoch": 0.27, + "learning_rate": 1.8319395672804554e-05, + "loss": 1.3758, + "step": 2560 + }, + { + "epoch": 0.27, + "learning_rate": 1.8317364166311592e-05, + "loss": 1.4352, + "step": 2561 + }, + { + "epoch": 0.27, + "learning_rate": 1.831533154550554e-05, + "loss": 1.5072, + "step": 2562 + }, + { + "epoch": 0.27, + "learning_rate": 1.8313297810658718e-05, + "loss": 1.4476, + "step": 2563 + }, + { + "epoch": 0.27, + "learning_rate": 1.831126296204359e-05, + "loss": 1.507, + "step": 2564 + }, + { + "epoch": 0.27, + "learning_rate": 1.8309226999932777e-05, + "loss": 1.4677, + "step": 2565 + }, + { + "epoch": 0.27, + "learning_rate": 1.8307189924599044e-05, + "loss": 1.4537, + "step": 2566 + }, + { + "epoch": 0.27, + "learning_rate": 1.8305151736315307e-05, + "loss": 1.4584, + "step": 2567 + }, + { + "epoch": 0.27, + "learning_rate": 1.8303112435354634e-05, + "loss": 1.4944, + "step": 2568 + }, + { + "epoch": 0.27, + "learning_rate": 1.8301072021990232e-05, + "loss": 1.4379, + "step": 2569 + }, + { + "epoch": 0.27, + "learning_rate": 1.8299030496495475e-05, + "loss": 1.539, + "step": 2570 + }, + { + "epoch": 0.27, + "learning_rate": 1.829698785914386e-05, + "loss": 1.4421, + "step": 2571 + }, + { + "epoch": 0.27, + "learning_rate": 1.8294944110209063e-05, + "loss": 1.4693, + "step": 2572 + }, + { + "epoch": 0.27, + "learning_rate": 1.8292899249964887e-05, + "loss": 1.3239, + "step": 2573 + }, + { + "epoch": 0.27, + "learning_rate": 1.8290853278685284e-05, + "loss": 1.472, + "step": 2574 + }, + { + "epoch": 0.27, + "learning_rate": 1.8288806196644374e-05, + "loss": 1.536, + "step": 2575 + }, + { + "epoch": 0.27, + "learning_rate": 1.8286758004116405e-05, + "loss": 1.4644, + "step": 2576 + }, + { + "epoch": 0.27, + "learning_rate": 1.8284708701375783e-05, + "loss": 1.4537, + "step": 2577 + }, + { + "epoch": 0.27, + "learning_rate": 1.8282658288697067e-05, + "loss": 1.4359, + "step": 2578 + }, + { + "epoch": 0.27, + "learning_rate": 1.8280606766354955e-05, + "loss": 1.4842, + "step": 2579 + }, + { + "epoch": 0.27, + "learning_rate": 1.8278554134624302e-05, + "loss": 1.4664, + "step": 2580 + }, + { + "epoch": 0.27, + "learning_rate": 1.8276500393780105e-05, + "loss": 1.4632, + "step": 2581 + }, + { + "epoch": 0.27, + "learning_rate": 1.827444554409751e-05, + "loss": 1.4996, + "step": 2582 + }, + { + "epoch": 0.27, + "learning_rate": 1.827238958585182e-05, + "loss": 1.3399, + "step": 2583 + }, + { + "epoch": 0.27, + "learning_rate": 1.8270332519318476e-05, + "loss": 1.3928, + "step": 2584 + }, + { + "epoch": 0.27, + "learning_rate": 1.8268274344773074e-05, + "loss": 1.4993, + "step": 2585 + }, + { + "epoch": 0.27, + "learning_rate": 1.8266215062491356e-05, + "loss": 1.5398, + "step": 2586 + }, + { + "epoch": 0.27, + "learning_rate": 1.826415467274921e-05, + "loss": 1.4353, + "step": 2587 + }, + { + "epoch": 0.27, + "eval_loss": 1.5104212760925293, + "eval_runtime": 77.3448, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2587 + }, + { + "epoch": 0.27, + "learning_rate": 1.8262093175822685e-05, + "loss": 1.4889, + "step": 2588 + }, + { + "epoch": 0.27, + "learning_rate": 1.826003057198796e-05, + "loss": 1.4912, + "step": 2589 + }, + { + "epoch": 0.27, + "learning_rate": 1.825796686152137e-05, + "loss": 1.4884, + "step": 2590 + }, + { + "epoch": 0.27, + "learning_rate": 1.8255902044699404e-05, + "loss": 1.478, + "step": 2591 + }, + { + "epoch": 0.27, + "learning_rate": 1.8253836121798692e-05, + "loss": 1.6549, + "step": 2592 + }, + { + "epoch": 0.27, + "learning_rate": 1.8251769093096018e-05, + "loss": 1.5146, + "step": 2593 + }, + { + "epoch": 0.27, + "learning_rate": 1.8249700958868306e-05, + "loss": 1.4797, + "step": 2594 + }, + { + "epoch": 0.27, + "learning_rate": 1.8247631719392634e-05, + "loss": 1.4655, + "step": 2595 + }, + { + "epoch": 0.27, + "learning_rate": 1.824556137494623e-05, + "loss": 1.4517, + "step": 2596 + }, + { + "epoch": 0.27, + "learning_rate": 1.8243489925806458e-05, + "loss": 1.4936, + "step": 2597 + }, + { + "epoch": 0.27, + "learning_rate": 1.8241417372250852e-05, + "loss": 1.4614, + "step": 2598 + }, + { + "epoch": 0.27, + "learning_rate": 1.8239343714557073e-05, + "loss": 1.4475, + "step": 2599 + }, + { + "epoch": 0.27, + "learning_rate": 1.8237268953002937e-05, + "loss": 1.5435, + "step": 2600 + }, + { + "epoch": 0.27, + "learning_rate": 1.8235193087866413e-05, + "loss": 1.4616, + "step": 2601 + }, + { + "epoch": 0.27, + "learning_rate": 1.8233116119425612e-05, + "loss": 1.4578, + "step": 2602 + }, + { + "epoch": 0.27, + "learning_rate": 1.8231038047958795e-05, + "loss": 1.434, + "step": 2603 + }, + { + "epoch": 0.27, + "learning_rate": 1.8228958873744368e-05, + "loss": 1.5335, + "step": 2604 + }, + { + "epoch": 0.27, + "learning_rate": 1.8226878597060887e-05, + "loss": 1.415, + "step": 2605 + }, + { + "epoch": 0.27, + "learning_rate": 1.8224797218187058e-05, + "loss": 1.6165, + "step": 2606 + }, + { + "epoch": 0.27, + "learning_rate": 1.822271473740173e-05, + "loss": 1.372, + "step": 2607 + }, + { + "epoch": 0.27, + "learning_rate": 1.8220631154983907e-05, + "loss": 1.4855, + "step": 2608 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218546471212727e-05, + "loss": 1.4093, + "step": 2609 + }, + { + "epoch": 0.27, + "learning_rate": 1.821646068636749e-05, + "loss": 1.4852, + "step": 2610 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214373800727637e-05, + "loss": 1.6959, + "step": 2611 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212285814572755e-05, + "loss": 1.3874, + "step": 2612 + }, + { + "epoch": 0.27, + "learning_rate": 1.821019672818258e-05, + "loss": 1.4425, + "step": 2613 + }, + { + "epoch": 0.27, + "learning_rate": 1.8208106541837e-05, + "loss": 1.6097, + "step": 2614 + }, + { + "epoch": 0.27, + "learning_rate": 1.8206015255816045e-05, + "loss": 1.5675, + "step": 2615 + }, + { + "epoch": 0.27, + "learning_rate": 1.820392287039989e-05, + "loss": 1.4039, + "step": 2616 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201829385868866e-05, + "loss": 1.4872, + "step": 2617 + }, + { + "epoch": 0.27, + "learning_rate": 1.819973480250344e-05, + "loss": 1.4645, + "step": 2618 + }, + { + "epoch": 0.27, + "learning_rate": 1.8197639120584237e-05, + "loss": 1.4923, + "step": 2619 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195542340392025e-05, + "loss": 1.4294, + "step": 2620 + }, + { + "epoch": 0.27, + "learning_rate": 1.8193444462207717e-05, + "loss": 1.4315, + "step": 2621 + }, + { + "epoch": 0.27, + "learning_rate": 1.8191345486312372e-05, + "loss": 1.3972, + "step": 2622 + }, + { + "epoch": 0.28, + "learning_rate": 1.8189245412987205e-05, + "loss": 1.462, + "step": 2623 + }, + { + "epoch": 0.28, + "learning_rate": 1.8187144242513567e-05, + "loss": 1.4738, + "step": 2624 + }, + { + "epoch": 0.28, + "learning_rate": 1.818504197517296e-05, + "loss": 1.4935, + "step": 2625 + }, + { + "epoch": 0.28, + "learning_rate": 1.8182938611247038e-05, + "loss": 1.4231, + "step": 2626 + }, + { + "epoch": 0.28, + "learning_rate": 1.81808341510176e-05, + "loss": 1.4031, + "step": 2627 + }, + { + "epoch": 0.28, + "learning_rate": 1.817872859476658e-05, + "loss": 1.5822, + "step": 2628 + }, + { + "epoch": 0.28, + "learning_rate": 1.8176621942776075e-05, + "loss": 1.432, + "step": 2629 + }, + { + "epoch": 0.28, + "learning_rate": 1.8174514195328324e-05, + "loss": 1.5565, + "step": 2630 + }, + { + "epoch": 0.28, + "learning_rate": 1.8172405352705704e-05, + "loss": 1.4895, + "step": 2631 + }, + { + "epoch": 0.28, + "learning_rate": 1.8170295415190754e-05, + "loss": 1.4032, + "step": 2632 + }, + { + "epoch": 0.28, + "learning_rate": 1.8168184383066144e-05, + "loss": 1.4253, + "step": 2633 + }, + { + "epoch": 0.28, + "learning_rate": 1.8166072256614702e-05, + "loss": 1.5162, + "step": 2634 + }, + { + "epoch": 0.28, + "learning_rate": 1.81639590361194e-05, + "loss": 1.4609, + "step": 2635 + }, + { + "epoch": 0.28, + "learning_rate": 1.816184472186335e-05, + "loss": 1.4351, + "step": 2636 + }, + { + "epoch": 0.28, + "learning_rate": 1.8159729314129823e-05, + "loss": 1.4738, + "step": 2637 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157612813202224e-05, + "loss": 1.5986, + "step": 2638 + }, + { + "epoch": 0.28, + "learning_rate": 1.815549521936411e-05, + "loss": 1.4633, + "step": 2639 + }, + { + "epoch": 0.28, + "learning_rate": 1.8153376532899184e-05, + "loss": 1.4404, + "step": 2640 + }, + { + "epoch": 0.28, + "learning_rate": 1.81512567540913e-05, + "loss": 1.4256, + "step": 2641 + }, + { + "epoch": 0.28, + "learning_rate": 1.814913588322445e-05, + "loss": 1.4054, + "step": 2642 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147013920582773e-05, + "loss": 1.4134, + "step": 2643 + }, + { + "epoch": 0.28, + "learning_rate": 1.8144890866450567e-05, + "loss": 1.4098, + "step": 2644 + }, + { + "epoch": 0.28, + "learning_rate": 1.814276672111226e-05, + "loss": 1.4593, + "step": 2645 + }, + { + "epoch": 0.28, + "learning_rate": 1.814064148485243e-05, + "loss": 1.4679, + "step": 2646 + }, + { + "epoch": 0.28, + "learning_rate": 1.8138515157955812e-05, + "loss": 1.5234, + "step": 2647 + }, + { + "epoch": 0.28, + "learning_rate": 1.8136387740707272e-05, + "loss": 1.4568, + "step": 2648 + }, + { + "epoch": 0.28, + "learning_rate": 1.8134259233391836e-05, + "loss": 1.5057, + "step": 2649 + }, + { + "epoch": 0.28, + "learning_rate": 1.8132129636294665e-05, + "loss": 1.3643, + "step": 2650 + }, + { + "epoch": 0.28, + "learning_rate": 1.812999894970107e-05, + "loss": 1.4766, + "step": 2651 + }, + { + "epoch": 0.28, + "learning_rate": 1.812786717389651e-05, + "loss": 1.5701, + "step": 2652 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125734309166587e-05, + "loss": 1.5341, + "step": 2653 + }, + { + "epoch": 0.28, + "learning_rate": 1.812360035579705e-05, + "loss": 1.3596, + "step": 2654 + }, + { + "epoch": 0.28, + "learning_rate": 1.8121465314073793e-05, + "loss": 1.4847, + "step": 2655 + }, + { + "epoch": 0.28, + "learning_rate": 1.811932918428286e-05, + "loss": 1.4664, + "step": 2656 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117191966710438e-05, + "loss": 1.4673, + "step": 2657 + }, + { + "epoch": 0.28, + "learning_rate": 1.8115053661642856e-05, + "loss": 1.4712, + "step": 2658 + }, + { + "epoch": 0.28, + "learning_rate": 1.811291426936659e-05, + "loss": 1.4458, + "step": 2659 + }, + { + "epoch": 0.28, + "learning_rate": 1.811077379016827e-05, + "loss": 1.4667, + "step": 2660 + }, + { + "epoch": 0.28, + "learning_rate": 1.810863222433466e-05, + "loss": 1.4695, + "step": 2661 + }, + { + "epoch": 0.28, + "learning_rate": 1.8106489572152677e-05, + "loss": 1.5263, + "step": 2662 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104345833909376e-05, + "loss": 1.4148, + "step": 2663 + }, + { + "epoch": 0.28, + "learning_rate": 1.8102201009891976e-05, + "loss": 1.3955, + "step": 2664 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100055100387814e-05, + "loss": 1.6056, + "step": 2665 + }, + { + "epoch": 0.28, + "learning_rate": 1.8097908105684396e-05, + "loss": 1.5394, + "step": 2666 + }, + { + "epoch": 0.28, + "learning_rate": 1.809576002606936e-05, + "loss": 1.479, + "step": 2667 + }, + { + "epoch": 0.28, + "learning_rate": 1.8093610861830494e-05, + "loss": 1.4492, + "step": 2668 + }, + { + "epoch": 0.28, + "learning_rate": 1.8091460613255728e-05, + "loss": 1.4172, + "step": 2669 + }, + { + "epoch": 0.28, + "learning_rate": 1.808930928063315e-05, + "loss": 1.4498, + "step": 2670 + }, + { + "epoch": 0.28, + "learning_rate": 1.808715686425097e-05, + "loss": 1.6203, + "step": 2671 + }, + { + "epoch": 0.28, + "learning_rate": 1.8085003364397567e-05, + "loss": 1.435, + "step": 2672 + }, + { + "epoch": 0.28, + "learning_rate": 1.808284878136145e-05, + "loss": 1.4489, + "step": 2673 + }, + { + "epoch": 0.28, + "learning_rate": 1.8080693115431277e-05, + "loss": 1.4416, + "step": 2674 + }, + { + "epoch": 0.28, + "learning_rate": 1.8078536366895853e-05, + "loss": 1.422, + "step": 2675 + }, + { + "epoch": 0.28, + "learning_rate": 1.8076378536044128e-05, + "loss": 1.4039, + "step": 2676 + }, + { + "epoch": 0.28, + "learning_rate": 1.8074219623165195e-05, + "loss": 1.4705, + "step": 2677 + }, + { + "epoch": 0.28, + "learning_rate": 1.807205962854829e-05, + "loss": 1.5031, + "step": 2678 + }, + { + "epoch": 0.28, + "learning_rate": 1.8069898552482806e-05, + "loss": 1.4812, + "step": 2679 + }, + { + "epoch": 0.28, + "learning_rate": 1.806773639525826e-05, + "loss": 1.4129, + "step": 2680 + }, + { + "epoch": 0.28, + "learning_rate": 1.8065573157164332e-05, + "loss": 1.4559, + "step": 2681 + }, + { + "epoch": 0.28, + "learning_rate": 1.806340883849084e-05, + "loss": 1.3878, + "step": 2682 + }, + { + "epoch": 0.28, + "learning_rate": 1.8061243439527744e-05, + "loss": 1.4752, + "step": 2683 + }, + { + "epoch": 0.28, + "learning_rate": 1.8059076960565156e-05, + "loss": 1.4089, + "step": 2684 + }, + { + "epoch": 0.28, + "learning_rate": 1.8056909401893326e-05, + "loss": 1.4736, + "step": 2685 + }, + { + "epoch": 0.28, + "learning_rate": 1.8054740763802654e-05, + "loss": 1.3796, + "step": 2686 + }, + { + "epoch": 0.28, + "learning_rate": 1.805257104658368e-05, + "loss": 1.4412, + "step": 2687 + }, + { + "epoch": 0.28, + "learning_rate": 1.8050400250527086e-05, + "loss": 1.4639, + "step": 2688 + }, + { + "epoch": 0.28, + "learning_rate": 1.804822837592371e-05, + "loss": 1.4076, + "step": 2689 + }, + { + "epoch": 0.28, + "learning_rate": 1.804605542306452e-05, + "loss": 1.4627, + "step": 2690 + }, + { + "epoch": 0.28, + "learning_rate": 1.8043881392240642e-05, + "loss": 1.5249, + "step": 2691 + }, + { + "epoch": 0.28, + "learning_rate": 1.804170628374334e-05, + "loss": 1.4312, + "step": 2692 + }, + { + "epoch": 0.28, + "learning_rate": 1.803953009786402e-05, + "loss": 1.5676, + "step": 2693 + }, + { + "epoch": 0.28, + "learning_rate": 1.8037352834894233e-05, + "loss": 1.5072, + "step": 2694 + }, + { + "epoch": 0.28, + "learning_rate": 1.803517449512568e-05, + "loss": 1.5662, + "step": 2695 + }, + { + "epoch": 0.28, + "learning_rate": 1.8032995078850207e-05, + "loss": 1.4771, + "step": 2696 + }, + { + "epoch": 0.28, + "learning_rate": 1.803081458635979e-05, + "loss": 1.412, + "step": 2697 + }, + { + "epoch": 0.28, + "learning_rate": 1.8028633017946564e-05, + "loss": 1.497, + "step": 2698 + }, + { + "epoch": 0.28, + "learning_rate": 1.8026450373902804e-05, + "loss": 1.4528, + "step": 2699 + }, + { + "epoch": 0.28, + "learning_rate": 1.802426665452093e-05, + "loss": 1.4785, + "step": 2700 + }, + { + "epoch": 0.28, + "learning_rate": 1.8022081860093493e-05, + "loss": 1.6411, + "step": 2701 + }, + { + "epoch": 0.28, + "learning_rate": 1.8019895990913213e-05, + "loss": 1.4459, + "step": 2702 + }, + { + "epoch": 0.28, + "learning_rate": 1.8017709047272932e-05, + "loss": 1.4418, + "step": 2703 + }, + { + "epoch": 0.28, + "learning_rate": 1.801552102946565e-05, + "loss": 1.4409, + "step": 2704 + }, + { + "epoch": 0.28, + "learning_rate": 1.8013331937784498e-05, + "loss": 1.4651, + "step": 2705 + }, + { + "epoch": 0.28, + "learning_rate": 1.8011141772522766e-05, + "loss": 1.4161, + "step": 2706 + }, + { + "epoch": 0.28, + "learning_rate": 1.8008950533973876e-05, + "loss": 1.458, + "step": 2707 + }, + { + "epoch": 0.28, + "learning_rate": 1.8006758222431398e-05, + "loss": 1.4477, + "step": 2708 + }, + { + "epoch": 0.28, + "learning_rate": 1.800456483818904e-05, + "loss": 1.4433, + "step": 2709 + }, + { + "epoch": 0.28, + "learning_rate": 1.8002370381540672e-05, + "loss": 1.5005, + "step": 2710 + }, + { + "epoch": 0.28, + "learning_rate": 1.8000174852780282e-05, + "loss": 1.4945, + "step": 2711 + }, + { + "epoch": 0.28, + "learning_rate": 1.7997978252202023e-05, + "loss": 1.4298, + "step": 2712 + }, + { + "epoch": 0.28, + "learning_rate": 1.7995780580100177e-05, + "loss": 1.3812, + "step": 2713 + }, + { + "epoch": 0.28, + "learning_rate": 1.799358183676918e-05, + "loss": 1.5559, + "step": 2714 + }, + { + "epoch": 0.28, + "learning_rate": 1.79913820225036e-05, + "loss": 1.4316, + "step": 2715 + }, + { + "epoch": 0.28, + "learning_rate": 1.798918113759817e-05, + "loss": 1.419, + "step": 2716 + }, + { + "epoch": 0.28, + "learning_rate": 1.7986979182347733e-05, + "loss": 1.43, + "step": 2717 + }, + { + "epoch": 0.29, + "learning_rate": 1.798477615704731e-05, + "loss": 1.4964, + "step": 2718 + }, + { + "epoch": 0.29, + "learning_rate": 1.7982572061992044e-05, + "loss": 1.4417, + "step": 2719 + }, + { + "epoch": 0.29, + "learning_rate": 1.7980366897477227e-05, + "loss": 1.4562, + "step": 2720 + }, + { + "epoch": 0.29, + "learning_rate": 1.7978160663798295e-05, + "loss": 1.4386, + "step": 2721 + }, + { + "epoch": 0.29, + "learning_rate": 1.7975953361250824e-05, + "loss": 1.445, + "step": 2722 + }, + { + "epoch": 0.29, + "learning_rate": 1.797374499013054e-05, + "loss": 1.4549, + "step": 2723 + }, + { + "epoch": 0.29, + "learning_rate": 1.7971535550733305e-05, + "loss": 1.5205, + "step": 2724 + }, + { + "epoch": 0.29, + "learning_rate": 1.796932504335513e-05, + "loss": 1.4632, + "step": 2725 + }, + { + "epoch": 0.29, + "learning_rate": 1.796711346829216e-05, + "loss": 1.3767, + "step": 2726 + }, + { + "epoch": 0.29, + "learning_rate": 1.79649008258407e-05, + "loss": 1.4098, + "step": 2727 + }, + { + "epoch": 0.29, + "learning_rate": 1.7962687116297178e-05, + "loss": 1.4675, + "step": 2728 + }, + { + "epoch": 0.29, + "learning_rate": 1.7960472339958176e-05, + "loss": 1.6048, + "step": 2729 + }, + { + "epoch": 0.29, + "learning_rate": 1.7958256497120418e-05, + "loss": 1.5432, + "step": 2730 + }, + { + "epoch": 0.29, + "learning_rate": 1.7956039588080774e-05, + "loss": 1.5453, + "step": 2731 + }, + { + "epoch": 0.29, + "learning_rate": 1.7953821613136246e-05, + "loss": 1.4246, + "step": 2732 + }, + { + "epoch": 0.29, + "learning_rate": 1.7951602572583988e-05, + "loss": 1.3987, + "step": 2733 + }, + { + "epoch": 0.29, + "learning_rate": 1.7949382466721295e-05, + "loss": 1.4943, + "step": 2734 + }, + { + "epoch": 0.29, + "learning_rate": 1.7947161295845606e-05, + "loss": 1.4385, + "step": 2735 + }, + { + "epoch": 0.29, + "learning_rate": 1.7944939060254497e-05, + "loss": 1.4165, + "step": 2736 + }, + { + "epoch": 0.29, + "learning_rate": 1.7942715760245692e-05, + "loss": 1.4004, + "step": 2737 + }, + { + "epoch": 0.29, + "learning_rate": 1.7940491396117063e-05, + "loss": 1.4577, + "step": 2738 + }, + { + "epoch": 0.29, + "learning_rate": 1.7938265968166602e-05, + "loss": 1.4649, + "step": 2739 + }, + { + "epoch": 0.29, + "learning_rate": 1.7936039476692473e-05, + "loss": 1.5273, + "step": 2740 + }, + { + "epoch": 0.29, + "learning_rate": 1.7933811921992962e-05, + "loss": 1.4325, + "step": 2741 + }, + { + "epoch": 0.29, + "learning_rate": 1.793158330436651e-05, + "loss": 1.4388, + "step": 2742 + }, + { + "epoch": 0.29, + "learning_rate": 1.7929353624111687e-05, + "loss": 1.4124, + "step": 2743 + }, + { + "epoch": 0.29, + "learning_rate": 1.7927122881527222e-05, + "loss": 1.5449, + "step": 2744 + }, + { + "epoch": 0.29, + "learning_rate": 1.7924891076911964e-05, + "loss": 1.4728, + "step": 2745 + }, + { + "epoch": 0.29, + "learning_rate": 1.7922658210564932e-05, + "loss": 1.5103, + "step": 2746 + }, + { + "epoch": 0.29, + "learning_rate": 1.792042428278526e-05, + "loss": 1.5975, + "step": 2747 + }, + { + "epoch": 0.29, + "learning_rate": 1.7918189293872247e-05, + "loss": 1.567, + "step": 2748 + }, + { + "epoch": 0.29, + "learning_rate": 1.7915953244125318e-05, + "loss": 1.57, + "step": 2749 + }, + { + "epoch": 0.29, + "learning_rate": 1.791371613384405e-05, + "loss": 1.4372, + "step": 2750 + }, + { + "epoch": 0.29, + "learning_rate": 1.7911477963328155e-05, + "loss": 1.4053, + "step": 2751 + }, + { + "epoch": 0.29, + "learning_rate": 1.7909238732877492e-05, + "loss": 1.3782, + "step": 2752 + }, + { + "epoch": 0.29, + "learning_rate": 1.790699844279206e-05, + "loss": 1.4401, + "step": 2753 + }, + { + "epoch": 0.29, + "learning_rate": 1.7904757093372e-05, + "loss": 1.3749, + "step": 2754 + }, + { + "epoch": 0.29, + "learning_rate": 1.79025146849176e-05, + "loss": 1.4909, + "step": 2755 + }, + { + "epoch": 0.29, + "learning_rate": 1.7900271217729273e-05, + "loss": 1.4103, + "step": 2756 + }, + { + "epoch": 0.29, + "learning_rate": 1.7898026692107597e-05, + "loss": 1.4986, + "step": 2757 + }, + { + "epoch": 0.29, + "learning_rate": 1.7895781108353278e-05, + "loss": 1.5449, + "step": 2758 + }, + { + "epoch": 0.29, + "learning_rate": 1.789353446676717e-05, + "loss": 1.5583, + "step": 2759 + }, + { + "epoch": 0.29, + "learning_rate": 1.7891286767650254e-05, + "loss": 1.5342, + "step": 2760 + }, + { + "epoch": 0.29, + "learning_rate": 1.7889038011303673e-05, + "loss": 1.4233, + "step": 2761 + }, + { + "epoch": 0.29, + "learning_rate": 1.7886788198028707e-05, + "loss": 1.3433, + "step": 2762 + }, + { + "epoch": 0.29, + "learning_rate": 1.788453732812676e-05, + "loss": 1.4451, + "step": 2763 + }, + { + "epoch": 0.29, + "learning_rate": 1.78822854018994e-05, + "loss": 1.4506, + "step": 2764 + }, + { + "epoch": 0.29, + "learning_rate": 1.7880032419648324e-05, + "loss": 1.4386, + "step": 2765 + }, + { + "epoch": 0.29, + "learning_rate": 1.7877778381675374e-05, + "loss": 1.4512, + "step": 2766 + }, + { + "epoch": 0.29, + "learning_rate": 1.7875523288282535e-05, + "loss": 1.4319, + "step": 2767 + }, + { + "epoch": 0.29, + "learning_rate": 1.7873267139771932e-05, + "loss": 1.4753, + "step": 2768 + }, + { + "epoch": 0.29, + "learning_rate": 1.787100993644583e-05, + "loss": 1.4044, + "step": 2769 + }, + { + "epoch": 0.29, + "learning_rate": 1.786875167860663e-05, + "loss": 1.4382, + "step": 2770 + }, + { + "epoch": 0.29, + "learning_rate": 1.786649236655689e-05, + "loss": 1.3977, + "step": 2771 + }, + { + "epoch": 0.29, + "learning_rate": 1.7864232000599298e-05, + "loss": 1.4473, + "step": 2772 + }, + { + "epoch": 0.29, + "learning_rate": 1.7861970581036678e-05, + "loss": 1.4666, + "step": 2773 + }, + { + "epoch": 0.29, + "learning_rate": 1.785970810817201e-05, + "loss": 1.5299, + "step": 2774 + }, + { + "epoch": 0.29, + "learning_rate": 1.7857444582308402e-05, + "loss": 1.3974, + "step": 2775 + }, + { + "epoch": 0.29, + "learning_rate": 1.7855180003749114e-05, + "loss": 1.4603, + "step": 2776 + }, + { + "epoch": 0.29, + "learning_rate": 1.7852914372797535e-05, + "loss": 1.463, + "step": 2777 + }, + { + "epoch": 0.29, + "learning_rate": 1.7850647689757205e-05, + "loss": 1.5317, + "step": 2778 + }, + { + "epoch": 0.29, + "learning_rate": 1.78483799549318e-05, + "loss": 1.4669, + "step": 2779 + }, + { + "epoch": 0.29, + "learning_rate": 1.784611116862514e-05, + "loss": 1.5293, + "step": 2780 + }, + { + "epoch": 0.29, + "learning_rate": 1.7843841331141177e-05, + "loss": 1.5802, + "step": 2781 + }, + { + "epoch": 0.29, + "learning_rate": 1.7841570442784024e-05, + "loss": 1.4486, + "step": 2782 + }, + { + "epoch": 0.29, + "learning_rate": 1.7839298503857913e-05, + "loss": 1.4674, + "step": 2783 + }, + { + "epoch": 0.29, + "learning_rate": 1.7837025514667224e-05, + "loss": 1.4662, + "step": 2784 + }, + { + "epoch": 0.29, + "learning_rate": 1.7834751475516484e-05, + "loss": 1.3555, + "step": 2785 + }, + { + "epoch": 0.29, + "learning_rate": 1.783247638671035e-05, + "loss": 1.4307, + "step": 2786 + }, + { + "epoch": 0.29, + "eval_loss": 1.500258445739746, + "eval_runtime": 77.406, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 2786 + }, + { + "epoch": 0.29, + "learning_rate": 1.7830200248553633e-05, + "loss": 1.4596, + "step": 2787 + }, + { + "epoch": 0.29, + "learning_rate": 1.7827923061351273e-05, + "loss": 1.6118, + "step": 2788 + }, + { + "epoch": 0.29, + "learning_rate": 1.7825644825408353e-05, + "loss": 1.4782, + "step": 2789 + }, + { + "epoch": 0.29, + "learning_rate": 1.78233655410301e-05, + "loss": 1.4681, + "step": 2790 + }, + { + "epoch": 0.29, + "learning_rate": 1.782108520852188e-05, + "loss": 1.6281, + "step": 2791 + }, + { + "epoch": 0.29, + "learning_rate": 1.78188038281892e-05, + "loss": 1.4446, + "step": 2792 + }, + { + "epoch": 0.29, + "learning_rate": 1.7816521400337704e-05, + "loss": 1.479, + "step": 2793 + }, + { + "epoch": 0.29, + "learning_rate": 1.7814237925273178e-05, + "loss": 1.5457, + "step": 2794 + }, + { + "epoch": 0.29, + "learning_rate": 1.7811953403301547e-05, + "loss": 1.3928, + "step": 2795 + }, + { + "epoch": 0.29, + "learning_rate": 1.780966783472889e-05, + "loss": 1.4321, + "step": 2796 + }, + { + "epoch": 0.29, + "learning_rate": 1.78073812198614e-05, + "loss": 1.5734, + "step": 2797 + }, + { + "epoch": 0.29, + "learning_rate": 1.7805093559005432e-05, + "loss": 1.4356, + "step": 2798 + }, + { + "epoch": 0.29, + "learning_rate": 1.7802804852467473e-05, + "loss": 1.4656, + "step": 2799 + }, + { + "epoch": 0.29, + "learning_rate": 1.780051510055415e-05, + "loss": 1.4052, + "step": 2800 + }, + { + "epoch": 0.29, + "learning_rate": 1.7798224303572228e-05, + "loss": 1.4758, + "step": 2801 + }, + { + "epoch": 0.29, + "learning_rate": 1.7795932461828622e-05, + "loss": 1.4326, + "step": 2802 + }, + { + "epoch": 0.29, + "learning_rate": 1.7793639575630376e-05, + "loss": 1.3409, + "step": 2803 + }, + { + "epoch": 0.29, + "learning_rate": 1.7791345645284678e-05, + "loss": 1.4175, + "step": 2804 + }, + { + "epoch": 0.29, + "learning_rate": 1.7789050671098853e-05, + "loss": 1.383, + "step": 2805 + }, + { + "epoch": 0.29, + "learning_rate": 1.7786754653380373e-05, + "loss": 1.5162, + "step": 2806 + }, + { + "epoch": 0.29, + "learning_rate": 1.7784457592436847e-05, + "loss": 1.4899, + "step": 2807 + }, + { + "epoch": 0.29, + "learning_rate": 1.7782159488576016e-05, + "loss": 1.4874, + "step": 2808 + }, + { + "epoch": 0.29, + "learning_rate": 1.777986034210577e-05, + "loss": 1.4363, + "step": 2809 + }, + { + "epoch": 0.29, + "learning_rate": 1.7777560153334134e-05, + "loss": 1.4223, + "step": 2810 + }, + { + "epoch": 0.29, + "learning_rate": 1.7775258922569273e-05, + "loss": 1.4792, + "step": 2811 + }, + { + "epoch": 0.29, + "learning_rate": 1.77729566501195e-05, + "loss": 1.4475, + "step": 2812 + }, + { + "epoch": 0.29, + "learning_rate": 1.7770653336293253e-05, + "loss": 1.5157, + "step": 2813 + }, + { + "epoch": 0.3, + "learning_rate": 1.776834898139912e-05, + "loss": 1.389, + "step": 2814 + }, + { + "epoch": 0.3, + "learning_rate": 1.7766043585745824e-05, + "loss": 1.4358, + "step": 2815 + }, + { + "epoch": 0.3, + "learning_rate": 1.776373714964223e-05, + "loss": 1.4297, + "step": 2816 + }, + { + "epoch": 0.3, + "learning_rate": 1.7761429673397344e-05, + "loss": 1.4102, + "step": 2817 + }, + { + "epoch": 0.3, + "learning_rate": 1.77591211573203e-05, + "loss": 1.4572, + "step": 2818 + }, + { + "epoch": 0.3, + "learning_rate": 1.775681160172039e-05, + "loss": 1.448, + "step": 2819 + }, + { + "epoch": 0.3, + "learning_rate": 1.7754501006907025e-05, + "loss": 1.4426, + "step": 2820 + }, + { + "epoch": 0.3, + "learning_rate": 1.7752189373189773e-05, + "loss": 1.4566, + "step": 2821 + }, + { + "epoch": 0.3, + "learning_rate": 1.7749876700878332e-05, + "loss": 1.4267, + "step": 2822 + }, + { + "epoch": 0.3, + "learning_rate": 1.7747562990282538e-05, + "loss": 1.3951, + "step": 2823 + }, + { + "epoch": 0.3, + "learning_rate": 1.7745248241712373e-05, + "loss": 1.4668, + "step": 2824 + }, + { + "epoch": 0.3, + "learning_rate": 1.774293245547795e-05, + "loss": 1.4924, + "step": 2825 + }, + { + "epoch": 0.3, + "learning_rate": 1.7740615631889525e-05, + "loss": 1.5258, + "step": 2826 + }, + { + "epoch": 0.3, + "learning_rate": 1.7738297771257496e-05, + "loss": 1.4323, + "step": 2827 + }, + { + "epoch": 0.3, + "learning_rate": 1.7735978873892393e-05, + "loss": 1.439, + "step": 2828 + }, + { + "epoch": 0.3, + "learning_rate": 1.773365894010489e-05, + "loss": 1.5658, + "step": 2829 + }, + { + "epoch": 0.3, + "learning_rate": 1.77313379702058e-05, + "loss": 1.4607, + "step": 2830 + }, + { + "epoch": 0.3, + "learning_rate": 1.7729015964506073e-05, + "loss": 1.5544, + "step": 2831 + }, + { + "epoch": 0.3, + "learning_rate": 1.7726692923316798e-05, + "loss": 1.4232, + "step": 2832 + }, + { + "epoch": 0.3, + "learning_rate": 1.77243688469492e-05, + "loss": 1.415, + "step": 2833 + }, + { + "epoch": 0.3, + "learning_rate": 1.772204373571465e-05, + "loss": 1.4658, + "step": 2834 + }, + { + "epoch": 0.3, + "learning_rate": 1.7719717589924647e-05, + "loss": 1.4678, + "step": 2835 + }, + { + "epoch": 0.3, + "learning_rate": 1.771739040989084e-05, + "loss": 1.3021, + "step": 2836 + }, + { + "epoch": 0.3, + "learning_rate": 1.771506219592501e-05, + "loss": 1.4045, + "step": 2837 + }, + { + "epoch": 0.3, + "learning_rate": 1.7712732948339085e-05, + "loss": 1.4593, + "step": 2838 + }, + { + "epoch": 0.3, + "learning_rate": 1.7710402667445108e-05, + "loss": 1.4175, + "step": 2839 + }, + { + "epoch": 0.3, + "learning_rate": 1.770807135355529e-05, + "loss": 1.3939, + "step": 2840 + }, + { + "epoch": 0.3, + "learning_rate": 1.7705739006981963e-05, + "loss": 1.6089, + "step": 2841 + }, + { + "epoch": 0.3, + "learning_rate": 1.77034056280376e-05, + "loss": 1.3952, + "step": 2842 + }, + { + "epoch": 0.3, + "learning_rate": 1.7701071217034818e-05, + "loss": 1.5086, + "step": 2843 + }, + { + "epoch": 0.3, + "learning_rate": 1.7698735774286362e-05, + "loss": 1.4706, + "step": 2844 + }, + { + "epoch": 0.3, + "learning_rate": 1.7696399300105128e-05, + "loss": 1.4286, + "step": 2845 + }, + { + "epoch": 0.3, + "learning_rate": 1.7694061794804137e-05, + "loss": 1.4418, + "step": 2846 + }, + { + "epoch": 0.3, + "learning_rate": 1.7691723258696562e-05, + "loss": 1.516, + "step": 2847 + }, + { + "epoch": 0.3, + "learning_rate": 1.76893836920957e-05, + "loss": 1.4354, + "step": 2848 + }, + { + "epoch": 0.3, + "learning_rate": 1.7687043095314998e-05, + "loss": 1.7503, + "step": 2849 + }, + { + "epoch": 0.3, + "learning_rate": 1.7684701468668032e-05, + "loss": 1.5985, + "step": 2850 + }, + { + "epoch": 0.3, + "learning_rate": 1.768235881246852e-05, + "loss": 1.442, + "step": 2851 + }, + { + "epoch": 0.3, + "learning_rate": 1.7680015127030322e-05, + "loss": 1.4924, + "step": 2852 + }, + { + "epoch": 0.3, + "learning_rate": 1.7677670412667425e-05, + "loss": 1.4461, + "step": 2853 + }, + { + "epoch": 0.3, + "learning_rate": 1.7675324669693968e-05, + "loss": 1.3823, + "step": 2854 + }, + { + "epoch": 0.3, + "learning_rate": 1.767297789842421e-05, + "loss": 1.452, + "step": 2855 + }, + { + "epoch": 0.3, + "learning_rate": 1.767063009917257e-05, + "loss": 1.46, + "step": 2856 + }, + { + "epoch": 0.3, + "learning_rate": 1.7668281272253587e-05, + "loss": 1.4129, + "step": 2857 + }, + { + "epoch": 0.3, + "learning_rate": 1.766593141798194e-05, + "loss": 1.4057, + "step": 2858 + }, + { + "epoch": 0.3, + "learning_rate": 1.7663580536672456e-05, + "loss": 1.5162, + "step": 2859 + }, + { + "epoch": 0.3, + "learning_rate": 1.7661228628640087e-05, + "loss": 1.5177, + "step": 2860 + }, + { + "epoch": 0.3, + "learning_rate": 1.7658875694199933e-05, + "loss": 1.4548, + "step": 2861 + }, + { + "epoch": 0.3, + "learning_rate": 1.7656521733667223e-05, + "loss": 1.4511, + "step": 2862 + }, + { + "epoch": 0.3, + "learning_rate": 1.765416674735733e-05, + "loss": 1.4778, + "step": 2863 + }, + { + "epoch": 0.3, + "learning_rate": 1.765181073558576e-05, + "loss": 1.3935, + "step": 2864 + }, + { + "epoch": 0.3, + "learning_rate": 1.7649453698668156e-05, + "loss": 1.4659, + "step": 2865 + }, + { + "epoch": 0.3, + "learning_rate": 1.7647095636920305e-05, + "loss": 1.7042, + "step": 2866 + }, + { + "epoch": 0.3, + "learning_rate": 1.7644736550658124e-05, + "loss": 1.7957, + "step": 2867 + }, + { + "epoch": 0.3, + "learning_rate": 1.764237644019767e-05, + "loss": 1.5139, + "step": 2868 + }, + { + "epoch": 0.3, + "learning_rate": 1.764001530585514e-05, + "loss": 1.4117, + "step": 2869 + }, + { + "epoch": 0.3, + "learning_rate": 1.7637653147946858e-05, + "loss": 1.4837, + "step": 2870 + }, + { + "epoch": 0.3, + "learning_rate": 1.7635289966789298e-05, + "loss": 1.4379, + "step": 2871 + }, + { + "epoch": 0.3, + "learning_rate": 1.7632925762699068e-05, + "loss": 1.4491, + "step": 2872 + }, + { + "epoch": 0.3, + "learning_rate": 1.7630560535992905e-05, + "loss": 1.4006, + "step": 2873 + }, + { + "epoch": 0.3, + "learning_rate": 1.7628194286987694e-05, + "loss": 1.5484, + "step": 2874 + }, + { + "epoch": 0.3, + "learning_rate": 1.7625827016000446e-05, + "loss": 1.4926, + "step": 2875 + }, + { + "epoch": 0.3, + "learning_rate": 1.762345872334832e-05, + "loss": 1.3909, + "step": 2876 + }, + { + "epoch": 0.3, + "learning_rate": 1.76210894093486e-05, + "loss": 1.405, + "step": 2877 + }, + { + "epoch": 0.3, + "learning_rate": 1.7618719074318718e-05, + "loss": 1.4736, + "step": 2878 + }, + { + "epoch": 0.3, + "learning_rate": 1.7616347718576238e-05, + "loss": 1.4445, + "step": 2879 + }, + { + "epoch": 0.3, + "learning_rate": 1.761397534243886e-05, + "loss": 1.4878, + "step": 2880 + }, + { + "epoch": 0.3, + "learning_rate": 1.7611601946224417e-05, + "loss": 1.4414, + "step": 2881 + }, + { + "epoch": 0.3, + "learning_rate": 1.760922753025089e-05, + "loss": 1.5657, + "step": 2882 + }, + { + "epoch": 0.3, + "learning_rate": 1.7606852094836385e-05, + "loss": 1.5008, + "step": 2883 + }, + { + "epoch": 0.3, + "learning_rate": 1.7604475640299153e-05, + "loss": 1.4922, + "step": 2884 + }, + { + "epoch": 0.3, + "learning_rate": 1.7602098166957577e-05, + "loss": 1.7451, + "step": 2885 + }, + { + "epoch": 0.3, + "learning_rate": 1.759971967513017e-05, + "loss": 1.7077, + "step": 2886 + }, + { + "epoch": 0.3, + "learning_rate": 1.75973401651356e-05, + "loss": 1.3986, + "step": 2887 + }, + { + "epoch": 0.3, + "learning_rate": 1.7594959637292656e-05, + "loss": 1.3966, + "step": 2888 + }, + { + "epoch": 0.3, + "learning_rate": 1.7592578091920264e-05, + "loss": 1.4086, + "step": 2889 + }, + { + "epoch": 0.3, + "learning_rate": 1.7590195529337495e-05, + "loss": 1.4481, + "step": 2890 + }, + { + "epoch": 0.3, + "learning_rate": 1.7587811949863548e-05, + "loss": 1.3974, + "step": 2891 + }, + { + "epoch": 0.3, + "learning_rate": 1.7585427353817758e-05, + "loss": 1.5013, + "step": 2892 + }, + { + "epoch": 0.3, + "learning_rate": 1.7583041741519608e-05, + "loss": 1.5454, + "step": 2893 + }, + { + "epoch": 0.3, + "learning_rate": 1.7580655113288708e-05, + "loss": 1.5033, + "step": 2894 + }, + { + "epoch": 0.3, + "learning_rate": 1.7578267469444793e-05, + "loss": 1.4332, + "step": 2895 + }, + { + "epoch": 0.3, + "learning_rate": 1.757587881030776e-05, + "loss": 1.4667, + "step": 2896 + }, + { + "epoch": 0.3, + "learning_rate": 1.7573489136197623e-05, + "loss": 1.4314, + "step": 2897 + }, + { + "epoch": 0.3, + "learning_rate": 1.7571098447434532e-05, + "loss": 1.4514, + "step": 2898 + }, + { + "epoch": 0.3, + "learning_rate": 1.7568706744338784e-05, + "loss": 1.4872, + "step": 2899 + }, + { + "epoch": 0.3, + "learning_rate": 1.7566314027230808e-05, + "loss": 1.4841, + "step": 2900 + }, + { + "epoch": 0.3, + "learning_rate": 1.7563920296431158e-05, + "loss": 1.3964, + "step": 2901 + }, + { + "epoch": 0.3, + "learning_rate": 1.7561525552260538e-05, + "loss": 1.4932, + "step": 2902 + }, + { + "epoch": 0.3, + "learning_rate": 1.755912979503978e-05, + "loss": 1.4153, + "step": 2903 + }, + { + "epoch": 0.3, + "learning_rate": 1.755673302508986e-05, + "loss": 1.4939, + "step": 2904 + }, + { + "epoch": 0.3, + "learning_rate": 1.755433524273187e-05, + "loss": 1.4437, + "step": 2905 + }, + { + "epoch": 0.3, + "learning_rate": 1.7551936448287067e-05, + "loss": 1.486, + "step": 2906 + }, + { + "epoch": 0.3, + "learning_rate": 1.754953664207682e-05, + "loss": 1.4362, + "step": 2907 + }, + { + "epoch": 0.3, + "learning_rate": 1.7547135824422635e-05, + "loss": 1.4954, + "step": 2908 + }, + { + "epoch": 0.31, + "learning_rate": 1.7544733995646174e-05, + "loss": 1.4552, + "step": 2909 + }, + { + "epoch": 0.31, + "learning_rate": 1.7542331156069213e-05, + "loss": 1.4654, + "step": 2910 + }, + { + "epoch": 0.31, + "learning_rate": 1.753992730601367e-05, + "loss": 1.4531, + "step": 2911 + }, + { + "epoch": 0.31, + "learning_rate": 1.75375224458016e-05, + "loss": 1.4949, + "step": 2912 + }, + { + "epoch": 0.31, + "learning_rate": 1.753511657575519e-05, + "loss": 1.3998, + "step": 2913 + }, + { + "epoch": 0.31, + "learning_rate": 1.753270969619677e-05, + "loss": 1.3904, + "step": 2914 + }, + { + "epoch": 0.31, + "learning_rate": 1.7530301807448794e-05, + "loss": 1.481, + "step": 2915 + }, + { + "epoch": 0.31, + "learning_rate": 1.7527892909833864e-05, + "loss": 1.4301, + "step": 2916 + }, + { + "epoch": 0.31, + "learning_rate": 1.7525483003674707e-05, + "loss": 1.4377, + "step": 2917 + }, + { + "epoch": 0.31, + "learning_rate": 1.7523072089294188e-05, + "loss": 1.5077, + "step": 2918 + }, + { + "epoch": 0.31, + "learning_rate": 1.752066016701531e-05, + "loss": 1.3802, + "step": 2919 + }, + { + "epoch": 0.31, + "learning_rate": 1.7518247237161205e-05, + "loss": 1.3991, + "step": 2920 + }, + { + "epoch": 0.31, + "learning_rate": 1.7515833300055146e-05, + "loss": 1.4283, + "step": 2921 + }, + { + "epoch": 0.31, + "learning_rate": 1.7513418356020535e-05, + "loss": 1.3688, + "step": 2922 + }, + { + "epoch": 0.31, + "learning_rate": 1.751100240538092e-05, + "loss": 1.4336, + "step": 2923 + }, + { + "epoch": 0.31, + "learning_rate": 1.7508585448459967e-05, + "loss": 1.4302, + "step": 2924 + }, + { + "epoch": 0.31, + "learning_rate": 1.7506167485581493e-05, + "loss": 1.4293, + "step": 2925 + }, + { + "epoch": 0.31, + "learning_rate": 1.750374851706944e-05, + "loss": 1.4262, + "step": 2926 + }, + { + "epoch": 0.31, + "learning_rate": 1.7501328543247892e-05, + "loss": 1.4128, + "step": 2927 + }, + { + "epoch": 0.31, + "learning_rate": 1.7498907564441054e-05, + "loss": 1.4258, + "step": 2928 + }, + { + "epoch": 0.31, + "learning_rate": 1.749648558097328e-05, + "loss": 1.4904, + "step": 2929 + }, + { + "epoch": 0.31, + "learning_rate": 1.749406259316906e-05, + "loss": 1.4628, + "step": 2930 + }, + { + "epoch": 0.31, + "learning_rate": 1.7491638601353004e-05, + "loss": 1.4908, + "step": 2931 + }, + { + "epoch": 0.31, + "learning_rate": 1.7489213605849867e-05, + "loss": 1.4563, + "step": 2932 + }, + { + "epoch": 0.31, + "learning_rate": 1.7486787606984533e-05, + "loss": 1.5006, + "step": 2933 + }, + { + "epoch": 0.31, + "learning_rate": 1.748436060508203e-05, + "loss": 1.424, + "step": 2934 + }, + { + "epoch": 0.31, + "learning_rate": 1.7481932600467508e-05, + "loss": 1.4136, + "step": 2935 + }, + { + "epoch": 0.31, + "learning_rate": 1.747950359346626e-05, + "loss": 1.3835, + "step": 2936 + }, + { + "epoch": 0.31, + "learning_rate": 1.747707358440371e-05, + "loss": 1.5284, + "step": 2937 + }, + { + "epoch": 0.31, + "learning_rate": 1.7474642573605418e-05, + "loss": 1.4592, + "step": 2938 + }, + { + "epoch": 0.31, + "learning_rate": 1.7472210561397075e-05, + "loss": 1.5483, + "step": 2939 + }, + { + "epoch": 0.31, + "learning_rate": 1.746977754810451e-05, + "loss": 1.521, + "step": 2940 + }, + { + "epoch": 0.31, + "learning_rate": 1.7467343534053683e-05, + "loss": 1.4276, + "step": 2941 + }, + { + "epoch": 0.31, + "learning_rate": 1.746490851957069e-05, + "loss": 1.4302, + "step": 2942 + }, + { + "epoch": 0.31, + "learning_rate": 1.746247250498176e-05, + "loss": 1.4439, + "step": 2943 + }, + { + "epoch": 0.31, + "learning_rate": 1.7460035490613255e-05, + "loss": 1.4991, + "step": 2944 + }, + { + "epoch": 0.31, + "learning_rate": 1.7457597476791674e-05, + "loss": 1.4188, + "step": 2945 + }, + { + "epoch": 0.31, + "learning_rate": 1.7455158463843648e-05, + "loss": 1.4685, + "step": 2946 + }, + { + "epoch": 0.31, + "learning_rate": 1.745271845209594e-05, + "loss": 1.3811, + "step": 2947 + }, + { + "epoch": 0.31, + "learning_rate": 1.7450277441875454e-05, + "loss": 1.4869, + "step": 2948 + }, + { + "epoch": 0.31, + "learning_rate": 1.7447835433509218e-05, + "loss": 1.5001, + "step": 2949 + }, + { + "epoch": 0.31, + "learning_rate": 1.74453924273244e-05, + "loss": 1.4757, + "step": 2950 + }, + { + "epoch": 0.31, + "learning_rate": 1.74429484236483e-05, + "loss": 1.5072, + "step": 2951 + }, + { + "epoch": 0.31, + "learning_rate": 1.744050342280835e-05, + "loss": 1.4242, + "step": 2952 + }, + { + "epoch": 0.31, + "learning_rate": 1.743805742513212e-05, + "loss": 1.4462, + "step": 2953 + }, + { + "epoch": 0.31, + "learning_rate": 1.743561043094731e-05, + "loss": 1.6815, + "step": 2954 + }, + { + "epoch": 0.31, + "learning_rate": 1.7433162440581755e-05, + "loss": 1.427, + "step": 2955 + }, + { + "epoch": 0.31, + "learning_rate": 1.7430713454363423e-05, + "loss": 1.2933, + "step": 2956 + }, + { + "epoch": 0.31, + "learning_rate": 1.742826347262041e-05, + "loss": 1.4247, + "step": 2957 + }, + { + "epoch": 0.31, + "learning_rate": 1.7425812495680955e-05, + "loss": 1.399, + "step": 2958 + }, + { + "epoch": 0.31, + "learning_rate": 1.742336052387343e-05, + "loss": 1.4818, + "step": 2959 + }, + { + "epoch": 0.31, + "learning_rate": 1.742090755752633e-05, + "loss": 1.3839, + "step": 2960 + }, + { + "epoch": 0.31, + "learning_rate": 1.741845359696829e-05, + "loss": 1.4669, + "step": 2961 + }, + { + "epoch": 0.31, + "learning_rate": 1.741599864252808e-05, + "loss": 1.468, + "step": 2962 + }, + { + "epoch": 0.31, + "learning_rate": 1.74135426945346e-05, + "loss": 1.4135, + "step": 2963 + }, + { + "epoch": 0.31, + "learning_rate": 1.7411085753316882e-05, + "loss": 1.5899, + "step": 2964 + }, + { + "epoch": 0.31, + "learning_rate": 1.74086278192041e-05, + "loss": 1.6115, + "step": 2965 + }, + { + "epoch": 0.31, + "learning_rate": 1.740616889252554e-05, + "loss": 1.3988, + "step": 2966 + }, + { + "epoch": 0.31, + "learning_rate": 1.740370897361065e-05, + "loss": 1.5001, + "step": 2967 + }, + { + "epoch": 0.31, + "learning_rate": 1.740124806278899e-05, + "loss": 1.459, + "step": 2968 + }, + { + "epoch": 0.31, + "learning_rate": 1.7398786160390258e-05, + "loss": 1.4489, + "step": 2969 + }, + { + "epoch": 0.31, + "learning_rate": 1.7396323266744283e-05, + "loss": 1.4397, + "step": 2970 + }, + { + "epoch": 0.31, + "learning_rate": 1.7393859382181033e-05, + "loss": 1.4687, + "step": 2971 + }, + { + "epoch": 0.31, + "learning_rate": 1.7391394507030606e-05, + "loss": 1.4495, + "step": 2972 + }, + { + "epoch": 0.31, + "learning_rate": 1.738892864162323e-05, + "loss": 1.4745, + "step": 2973 + }, + { + "epoch": 0.31, + "learning_rate": 1.7386461786289274e-05, + "loss": 1.3943, + "step": 2974 + }, + { + "epoch": 0.31, + "learning_rate": 1.738399394135922e-05, + "loss": 1.4595, + "step": 2975 + }, + { + "epoch": 0.31, + "learning_rate": 1.738152510716371e-05, + "loss": 1.4023, + "step": 2976 + }, + { + "epoch": 0.31, + "learning_rate": 1.7379055284033493e-05, + "loss": 1.3938, + "step": 2977 + }, + { + "epoch": 0.31, + "learning_rate": 1.7376584472299468e-05, + "loss": 1.4576, + "step": 2978 + }, + { + "epoch": 0.31, + "learning_rate": 1.737411267229266e-05, + "loss": 1.424, + "step": 2979 + }, + { + "epoch": 0.31, + "learning_rate": 1.7371639884344225e-05, + "loss": 1.4224, + "step": 2980 + }, + { + "epoch": 0.31, + "learning_rate": 1.736916610878545e-05, + "loss": 1.4228, + "step": 2981 + }, + { + "epoch": 0.31, + "learning_rate": 1.7366691345947768e-05, + "loss": 1.5021, + "step": 2982 + }, + { + "epoch": 0.31, + "learning_rate": 1.736421559616272e-05, + "loss": 1.3589, + "step": 2983 + }, + { + "epoch": 0.31, + "learning_rate": 1.7361738859762007e-05, + "loss": 1.4748, + "step": 2984 + }, + { + "epoch": 0.31, + "learning_rate": 1.735926113707743e-05, + "loss": 1.3974, + "step": 2985 + }, + { + "epoch": 0.31, + "eval_loss": 1.4849082231521606, + "eval_runtime": 77.3271, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2985 + }, + { + "epoch": 0.31, + "learning_rate": 1.735678242844096e-05, + "loss": 1.392, + "step": 2986 + }, + { + "epoch": 0.31, + "learning_rate": 1.735430273418467e-05, + "loss": 1.4277, + "step": 2987 + }, + { + "epoch": 0.31, + "learning_rate": 1.735182205464077e-05, + "loss": 1.4216, + "step": 2988 + }, + { + "epoch": 0.31, + "learning_rate": 1.7349340390141617e-05, + "loss": 1.4546, + "step": 2989 + }, + { + "epoch": 0.31, + "learning_rate": 1.734685774101969e-05, + "loss": 1.4264, + "step": 2990 + }, + { + "epoch": 0.31, + "learning_rate": 1.7344374107607593e-05, + "loss": 1.4307, + "step": 2991 + }, + { + "epoch": 0.31, + "learning_rate": 1.7341889490238076e-05, + "loss": 1.4266, + "step": 2992 + }, + { + "epoch": 0.31, + "learning_rate": 1.7339403889244008e-05, + "loss": 1.4486, + "step": 2993 + }, + { + "epoch": 0.31, + "learning_rate": 1.7336917304958403e-05, + "loss": 1.4345, + "step": 2994 + }, + { + "epoch": 0.31, + "learning_rate": 1.7334429737714395e-05, + "loss": 1.476, + "step": 2995 + }, + { + "epoch": 0.31, + "learning_rate": 1.7331941187845248e-05, + "loss": 1.5148, + "step": 2996 + }, + { + "epoch": 0.31, + "learning_rate": 1.7329451655684372e-05, + "loss": 1.4026, + "step": 2997 + }, + { + "epoch": 0.31, + "learning_rate": 1.7326961141565303e-05, + "loss": 1.3935, + "step": 2998 + }, + { + "epoch": 0.31, + "learning_rate": 1.73244696458217e-05, + "loss": 1.4483, + "step": 2999 + }, + { + "epoch": 0.31, + "learning_rate": 1.7321977168787356e-05, + "loss": 1.5197, + "step": 3000 + }, + { + "epoch": 0.31, + "learning_rate": 1.7319483710796208e-05, + "loss": 1.4648, + "step": 3001 + }, + { + "epoch": 0.31, + "learning_rate": 1.7316989272182308e-05, + "loss": 1.4171, + "step": 3002 + }, + { + "epoch": 0.31, + "learning_rate": 1.731449385327985e-05, + "loss": 1.4541, + "step": 3003 + }, + { + "epoch": 0.32, + "learning_rate": 1.731199745442316e-05, + "loss": 1.4605, + "step": 3004 + }, + { + "epoch": 0.32, + "learning_rate": 1.7309500075946683e-05, + "loss": 1.5122, + "step": 3005 + }, + { + "epoch": 0.32, + "learning_rate": 1.7307001718185007e-05, + "loss": 1.5243, + "step": 3006 + }, + { + "epoch": 0.32, + "learning_rate": 1.7304502381472844e-05, + "loss": 1.4997, + "step": 3007 + }, + { + "epoch": 0.32, + "learning_rate": 1.730200206614505e-05, + "loss": 1.4891, + "step": 3008 + }, + { + "epoch": 0.32, + "learning_rate": 1.72995007725366e-05, + "loss": 1.4376, + "step": 3009 + }, + { + "epoch": 0.32, + "learning_rate": 1.7296998500982595e-05, + "loss": 1.4403, + "step": 3010 + }, + { + "epoch": 0.32, + "learning_rate": 1.7294495251818285e-05, + "loss": 1.5153, + "step": 3011 + }, + { + "epoch": 0.32, + "learning_rate": 1.729199102537904e-05, + "loss": 1.4996, + "step": 3012 + }, + { + "epoch": 0.32, + "learning_rate": 1.7289485822000356e-05, + "loss": 1.5302, + "step": 3013 + }, + { + "epoch": 0.32, + "learning_rate": 1.7286979642017867e-05, + "loss": 1.5641, + "step": 3014 + }, + { + "epoch": 0.32, + "learning_rate": 1.728447248576734e-05, + "loss": 1.438, + "step": 3015 + }, + { + "epoch": 0.32, + "learning_rate": 1.7281964353584674e-05, + "loss": 1.4796, + "step": 3016 + }, + { + "epoch": 0.32, + "learning_rate": 1.727945524580588e-05, + "loss": 1.4413, + "step": 3017 + }, + { + "epoch": 0.32, + "learning_rate": 1.727694516276713e-05, + "loss": 1.3966, + "step": 3018 + }, + { + "epoch": 0.32, + "learning_rate": 1.72744341048047e-05, + "loss": 1.5267, + "step": 3019 + }, + { + "epoch": 0.32, + "learning_rate": 1.727192207225501e-05, + "loss": 1.4284, + "step": 3020 + }, + { + "epoch": 0.32, + "learning_rate": 1.726940906545461e-05, + "loss": 1.5137, + "step": 3021 + }, + { + "epoch": 0.32, + "learning_rate": 1.7266895084740173e-05, + "loss": 1.3966, + "step": 3022 + }, + { + "epoch": 0.32, + "learning_rate": 1.7264380130448514e-05, + "loss": 1.4156, + "step": 3023 + }, + { + "epoch": 0.32, + "learning_rate": 1.726186420291657e-05, + "loss": 1.4644, + "step": 3024 + }, + { + "epoch": 0.32, + "learning_rate": 1.725934730248141e-05, + "loss": 1.4768, + "step": 3025 + }, + { + "epoch": 0.32, + "learning_rate": 1.7256829429480233e-05, + "loss": 1.4428, + "step": 3026 + }, + { + "epoch": 0.32, + "learning_rate": 1.7254310584250373e-05, + "loss": 1.4495, + "step": 3027 + }, + { + "epoch": 0.32, + "learning_rate": 1.725179076712929e-05, + "loss": 1.3867, + "step": 3028 + }, + { + "epoch": 0.32, + "learning_rate": 1.7249269978454567e-05, + "loss": 1.5011, + "step": 3029 + }, + { + "epoch": 0.32, + "learning_rate": 1.7246748218563937e-05, + "loss": 1.3916, + "step": 3030 + }, + { + "epoch": 0.32, + "learning_rate": 1.7244225487795238e-05, + "loss": 1.4984, + "step": 3031 + }, + { + "epoch": 0.32, + "learning_rate": 1.7241701786486464e-05, + "loss": 1.5776, + "step": 3032 + }, + { + "epoch": 0.32, + "learning_rate": 1.7239177114975717e-05, + "loss": 1.5018, + "step": 3033 + }, + { + "epoch": 0.32, + "learning_rate": 1.7236651473601244e-05, + "loss": 1.5042, + "step": 3034 + }, + { + "epoch": 0.32, + "learning_rate": 1.723412486270141e-05, + "loss": 1.4636, + "step": 3035 + }, + { + "epoch": 0.32, + "learning_rate": 1.723159728261472e-05, + "loss": 1.5612, + "step": 3036 + }, + { + "epoch": 0.32, + "learning_rate": 1.7229068733679803e-05, + "loss": 1.4399, + "step": 3037 + }, + { + "epoch": 0.32, + "learning_rate": 1.7226539216235424e-05, + "loss": 1.5635, + "step": 3038 + }, + { + "epoch": 0.32, + "learning_rate": 1.7224008730620468e-05, + "loss": 1.4329, + "step": 3039 + }, + { + "epoch": 0.32, + "learning_rate": 1.7221477277173956e-05, + "loss": 1.4886, + "step": 3040 + }, + { + "epoch": 0.32, + "learning_rate": 1.721894485623504e-05, + "loss": 1.4741, + "step": 3041 + }, + { + "epoch": 0.32, + "learning_rate": 1.7216411468143e-05, + "loss": 1.4678, + "step": 3042 + }, + { + "epoch": 0.32, + "learning_rate": 1.721387711323724e-05, + "loss": 1.4758, + "step": 3043 + }, + { + "epoch": 0.32, + "learning_rate": 1.72113417918573e-05, + "loss": 1.441, + "step": 3044 + }, + { + "epoch": 0.32, + "learning_rate": 1.7208805504342855e-05, + "loss": 1.4328, + "step": 3045 + }, + { + "epoch": 0.32, + "learning_rate": 1.720626825103369e-05, + "loss": 1.4254, + "step": 3046 + }, + { + "epoch": 0.32, + "learning_rate": 1.7203730032269744e-05, + "loss": 1.4462, + "step": 3047 + }, + { + "epoch": 0.32, + "learning_rate": 1.7201190848391066e-05, + "loss": 1.4826, + "step": 3048 + }, + { + "epoch": 0.32, + "learning_rate": 1.719865069973784e-05, + "loss": 1.4215, + "step": 3049 + }, + { + "epoch": 0.32, + "learning_rate": 1.7196109586650385e-05, + "loss": 1.4291, + "step": 3050 + }, + { + "epoch": 0.32, + "learning_rate": 1.7193567509469146e-05, + "loss": 1.5005, + "step": 3051 + }, + { + "epoch": 0.32, + "learning_rate": 1.719102446853469e-05, + "loss": 1.4216, + "step": 3052 + }, + { + "epoch": 0.32, + "learning_rate": 1.7188480464187725e-05, + "loss": 1.4349, + "step": 3053 + }, + { + "epoch": 0.32, + "learning_rate": 1.718593549676908e-05, + "loss": 1.4784, + "step": 3054 + }, + { + "epoch": 0.32, + "learning_rate": 1.7183389566619714e-05, + "loss": 1.4325, + "step": 3055 + }, + { + "epoch": 0.32, + "learning_rate": 1.7180842674080717e-05, + "loss": 1.5387, + "step": 3056 + }, + { + "epoch": 0.32, + "learning_rate": 1.717829481949331e-05, + "loss": 1.655, + "step": 3057 + }, + { + "epoch": 0.32, + "learning_rate": 1.717574600319883e-05, + "loss": 1.4623, + "step": 3058 + }, + { + "epoch": 0.32, + "learning_rate": 1.7173196225538768e-05, + "loss": 1.4646, + "step": 3059 + }, + { + "epoch": 0.32, + "learning_rate": 1.717064548685472e-05, + "loss": 1.4641, + "step": 3060 + }, + { + "epoch": 0.32, + "learning_rate": 1.7168093787488418e-05, + "loss": 1.4033, + "step": 3061 + }, + { + "epoch": 0.32, + "learning_rate": 1.7165541127781726e-05, + "loss": 1.4085, + "step": 3062 + }, + { + "epoch": 0.32, + "learning_rate": 1.716298750807664e-05, + "loss": 1.387, + "step": 3063 + }, + { + "epoch": 0.32, + "learning_rate": 1.7160432928715272e-05, + "loss": 1.4197, + "step": 3064 + }, + { + "epoch": 0.32, + "learning_rate": 1.7157877390039872e-05, + "loss": 1.4883, + "step": 3065 + }, + { + "epoch": 0.32, + "learning_rate": 1.7155320892392818e-05, + "loss": 1.4865, + "step": 3066 + }, + { + "epoch": 0.32, + "learning_rate": 1.715276343611662e-05, + "loss": 1.4532, + "step": 3067 + }, + { + "epoch": 0.32, + "learning_rate": 1.71502050215539e-05, + "loss": 1.3991, + "step": 3068 + }, + { + "epoch": 0.32, + "learning_rate": 1.7147645649047424e-05, + "loss": 1.4318, + "step": 3069 + }, + { + "epoch": 0.32, + "learning_rate": 1.714508531894009e-05, + "loss": 1.3616, + "step": 3070 + }, + { + "epoch": 0.32, + "learning_rate": 1.7142524031574904e-05, + "loss": 1.4481, + "step": 3071 + }, + { + "epoch": 0.32, + "learning_rate": 1.7139961787295022e-05, + "loss": 1.3897, + "step": 3072 + }, + { + "epoch": 0.32, + "learning_rate": 1.7137398586443716e-05, + "loss": 1.3128, + "step": 3073 + }, + { + "epoch": 0.32, + "learning_rate": 1.713483442936439e-05, + "loss": 1.4481, + "step": 3074 + }, + { + "epoch": 0.32, + "learning_rate": 1.713226931640057e-05, + "loss": 1.5374, + "step": 3075 + }, + { + "epoch": 0.32, + "learning_rate": 1.7129703247895923e-05, + "loss": 1.4247, + "step": 3076 + }, + { + "epoch": 0.32, + "learning_rate": 1.712713622419423e-05, + "loss": 1.4098, + "step": 3077 + }, + { + "epoch": 0.32, + "learning_rate": 1.7124568245639414e-05, + "loss": 1.4558, + "step": 3078 + }, + { + "epoch": 0.32, + "learning_rate": 1.7121999312575507e-05, + "loss": 1.4484, + "step": 3079 + }, + { + "epoch": 0.32, + "learning_rate": 1.711942942534669e-05, + "loss": 1.4236, + "step": 3080 + }, + { + "epoch": 0.32, + "learning_rate": 1.7116858584297253e-05, + "loss": 1.613, + "step": 3081 + }, + { + "epoch": 0.32, + "learning_rate": 1.711428678977163e-05, + "loss": 1.4503, + "step": 3082 + }, + { + "epoch": 0.32, + "learning_rate": 1.7111714042114376e-05, + "loss": 1.4072, + "step": 3083 + }, + { + "epoch": 0.32, + "learning_rate": 1.7109140341670168e-05, + "loss": 1.5999, + "step": 3084 + }, + { + "epoch": 0.32, + "learning_rate": 1.7106565688783815e-05, + "loss": 1.4129, + "step": 3085 + }, + { + "epoch": 0.32, + "learning_rate": 1.710399008380026e-05, + "loss": 1.3973, + "step": 3086 + }, + { + "epoch": 0.32, + "learning_rate": 1.710141352706456e-05, + "loss": 1.4292, + "step": 3087 + }, + { + "epoch": 0.32, + "learning_rate": 1.709883601892192e-05, + "loss": 1.4372, + "step": 3088 + }, + { + "epoch": 0.32, + "learning_rate": 1.7096257559717647e-05, + "loss": 1.4924, + "step": 3089 + }, + { + "epoch": 0.32, + "learning_rate": 1.7093678149797196e-05, + "loss": 1.4222, + "step": 3090 + }, + { + "epoch": 0.32, + "learning_rate": 1.7091097789506137e-05, + "loss": 1.4797, + "step": 3091 + }, + { + "epoch": 0.32, + "learning_rate": 1.7088516479190175e-05, + "loss": 1.4738, + "step": 3092 + }, + { + "epoch": 0.32, + "learning_rate": 1.708593421919514e-05, + "loss": 1.5371, + "step": 3093 + }, + { + "epoch": 0.32, + "learning_rate": 1.7083351009866988e-05, + "loss": 1.3802, + "step": 3094 + }, + { + "epoch": 0.32, + "learning_rate": 1.7080766851551795e-05, + "loss": 1.4292, + "step": 3095 + }, + { + "epoch": 0.32, + "learning_rate": 1.707818174459578e-05, + "loss": 1.4478, + "step": 3096 + }, + { + "epoch": 0.32, + "learning_rate": 1.7075595689345285e-05, + "loss": 1.4619, + "step": 3097 + }, + { + "epoch": 0.32, + "learning_rate": 1.7073008686146763e-05, + "loss": 1.4603, + "step": 3098 + }, + { + "epoch": 0.32, + "learning_rate": 1.7070420735346815e-05, + "loss": 1.4548, + "step": 3099 + }, + { + "epoch": 0.33, + "learning_rate": 1.7067831837292157e-05, + "loss": 1.3638, + "step": 3100 + }, + { + "epoch": 0.33, + "learning_rate": 1.7065241992329634e-05, + "loss": 1.4284, + "step": 3101 + }, + { + "epoch": 0.33, + "learning_rate": 1.7062651200806217e-05, + "loss": 1.386, + "step": 3102 + }, + { + "epoch": 0.33, + "learning_rate": 1.7060059463069013e-05, + "loss": 1.5483, + "step": 3103 + }, + { + "epoch": 0.33, + "learning_rate": 1.705746677946524e-05, + "loss": 1.4963, + "step": 3104 + }, + { + "epoch": 0.33, + "learning_rate": 1.7054873150342257e-05, + "loss": 1.4539, + "step": 3105 + }, + { + "epoch": 0.33, + "learning_rate": 1.705227857604754e-05, + "loss": 1.4361, + "step": 3106 + }, + { + "epoch": 0.33, + "learning_rate": 1.7049683056928695e-05, + "loss": 1.3735, + "step": 3107 + }, + { + "epoch": 0.33, + "learning_rate": 1.7047086593333454e-05, + "loss": 1.4324, + "step": 3108 + }, + { + "epoch": 0.33, + "learning_rate": 1.7044489185609685e-05, + "loss": 1.5037, + "step": 3109 + }, + { + "epoch": 0.33, + "learning_rate": 1.704189083410536e-05, + "loss": 1.3913, + "step": 3110 + }, + { + "epoch": 0.33, + "learning_rate": 1.7039291539168604e-05, + "loss": 1.3233, + "step": 3111 + }, + { + "epoch": 0.33, + "learning_rate": 1.703669130114765e-05, + "loss": 1.4897, + "step": 3112 + }, + { + "epoch": 0.33, + "learning_rate": 1.7034090120390862e-05, + "loss": 1.4843, + "step": 3113 + }, + { + "epoch": 0.33, + "learning_rate": 1.7031487997246735e-05, + "loss": 1.3674, + "step": 3114 + }, + { + "epoch": 0.33, + "learning_rate": 1.7028884932063883e-05, + "loss": 1.4475, + "step": 3115 + }, + { + "epoch": 0.33, + "learning_rate": 1.702628092519105e-05, + "loss": 1.4134, + "step": 3116 + }, + { + "epoch": 0.33, + "learning_rate": 1.7023675976977108e-05, + "loss": 1.4484, + "step": 3117 + }, + { + "epoch": 0.33, + "learning_rate": 1.702107008777106e-05, + "loss": 1.407, + "step": 3118 + }, + { + "epoch": 0.33, + "learning_rate": 1.7018463257922005e-05, + "loss": 1.5443, + "step": 3119 + }, + { + "epoch": 0.33, + "learning_rate": 1.701585548777922e-05, + "loss": 1.4548, + "step": 3120 + }, + { + "epoch": 0.33, + "learning_rate": 1.7013246777692063e-05, + "loss": 1.4252, + "step": 3121 + }, + { + "epoch": 0.33, + "learning_rate": 1.7010637128010037e-05, + "loss": 1.3748, + "step": 3122 + }, + { + "epoch": 0.33, + "learning_rate": 1.7008026539082767e-05, + "loss": 1.3804, + "step": 3123 + }, + { + "epoch": 0.33, + "learning_rate": 1.7005415011260008e-05, + "loss": 1.4203, + "step": 3124 + }, + { + "epoch": 0.33, + "learning_rate": 1.7002802544891634e-05, + "loss": 1.4195, + "step": 3125 + }, + { + "epoch": 0.33, + "learning_rate": 1.700018914032765e-05, + "loss": 1.4188, + "step": 3126 + }, + { + "epoch": 0.33, + "learning_rate": 1.699757479791819e-05, + "loss": 1.3884, + "step": 3127 + }, + { + "epoch": 0.33, + "learning_rate": 1.6994959518013502e-05, + "loss": 1.4111, + "step": 3128 + }, + { + "epoch": 0.33, + "learning_rate": 1.6992343300963963e-05, + "loss": 1.5452, + "step": 3129 + }, + { + "epoch": 0.33, + "learning_rate": 1.6989726147120087e-05, + "loss": 1.4097, + "step": 3130 + }, + { + "epoch": 0.33, + "learning_rate": 1.6987108056832506e-05, + "loss": 1.481, + "step": 3131 + }, + { + "epoch": 0.33, + "learning_rate": 1.6984489030451973e-05, + "loss": 1.4505, + "step": 3132 + }, + { + "epoch": 0.33, + "learning_rate": 1.6981869068329368e-05, + "loss": 1.4281, + "step": 3133 + }, + { + "epoch": 0.33, + "learning_rate": 1.69792481708157e-05, + "loss": 1.4555, + "step": 3134 + }, + { + "epoch": 0.33, + "learning_rate": 1.6976626338262103e-05, + "loss": 1.4525, + "step": 3135 + }, + { + "epoch": 0.33, + "learning_rate": 1.6974003571019837e-05, + "loss": 1.3765, + "step": 3136 + }, + { + "epoch": 0.33, + "learning_rate": 1.6971379869440286e-05, + "loss": 1.3998, + "step": 3137 + }, + { + "epoch": 0.33, + "learning_rate": 1.696875523387495e-05, + "loss": 1.5103, + "step": 3138 + }, + { + "epoch": 0.33, + "learning_rate": 1.6966129664675474e-05, + "loss": 1.427, + "step": 3139 + }, + { + "epoch": 0.33, + "learning_rate": 1.6963503162193612e-05, + "loss": 1.4362, + "step": 3140 + }, + { + "epoch": 0.33, + "learning_rate": 1.6960875726781246e-05, + "loss": 1.4073, + "step": 3141 + }, + { + "epoch": 0.33, + "learning_rate": 1.6958247358790388e-05, + "loss": 1.4014, + "step": 3142 + }, + { + "epoch": 0.33, + "learning_rate": 1.6955618058573165e-05, + "loss": 1.4244, + "step": 3143 + }, + { + "epoch": 0.33, + "learning_rate": 1.6952987826481847e-05, + "loss": 1.47, + "step": 3144 + }, + { + "epoch": 0.33, + "learning_rate": 1.6950356662868814e-05, + "loss": 1.5112, + "step": 3145 + }, + { + "epoch": 0.33, + "learning_rate": 1.6947724568086562e-05, + "loss": 1.3398, + "step": 3146 + }, + { + "epoch": 0.33, + "learning_rate": 1.694509154248774e-05, + "loss": 1.4584, + "step": 3147 + }, + { + "epoch": 0.33, + "learning_rate": 1.69424575864251e-05, + "loss": 1.4383, + "step": 3148 + }, + { + "epoch": 0.33, + "learning_rate": 1.6939822700251523e-05, + "loss": 1.3869, + "step": 3149 + }, + { + "epoch": 0.33, + "learning_rate": 1.6937186884320015e-05, + "loss": 1.4453, + "step": 3150 + }, + { + "epoch": 0.33, + "learning_rate": 1.6934550138983713e-05, + "loss": 1.3355, + "step": 3151 + }, + { + "epoch": 0.33, + "learning_rate": 1.6931912464595866e-05, + "loss": 1.5573, + "step": 3152 + }, + { + "epoch": 0.33, + "learning_rate": 1.6929273861509865e-05, + "loss": 1.439, + "step": 3153 + }, + { + "epoch": 0.33, + "learning_rate": 1.6926634330079203e-05, + "loss": 1.6079, + "step": 3154 + }, + { + "epoch": 0.33, + "learning_rate": 1.692399387065752e-05, + "loss": 1.6973, + "step": 3155 + }, + { + "epoch": 0.33, + "learning_rate": 1.692135248359856e-05, + "loss": 1.3769, + "step": 3156 + }, + { + "epoch": 0.33, + "learning_rate": 1.6918710169256206e-05, + "loss": 1.4454, + "step": 3157 + }, + { + "epoch": 0.33, + "learning_rate": 1.691606692798446e-05, + "loss": 1.4495, + "step": 3158 + }, + { + "epoch": 0.33, + "learning_rate": 1.691342276013745e-05, + "loss": 1.4292, + "step": 3159 + }, + { + "epoch": 0.33, + "learning_rate": 1.691077766606942e-05, + "loss": 1.4405, + "step": 3160 + }, + { + "epoch": 0.33, + "learning_rate": 1.6908131646134757e-05, + "loss": 1.3683, + "step": 3161 + }, + { + "epoch": 0.33, + "learning_rate": 1.690548470068795e-05, + "loss": 1.4731, + "step": 3162 + }, + { + "epoch": 0.33, + "learning_rate": 1.690283683008362e-05, + "loss": 1.4323, + "step": 3163 + }, + { + "epoch": 0.33, + "learning_rate": 1.6900188034676518e-05, + "loss": 1.5133, + "step": 3164 + }, + { + "epoch": 0.33, + "learning_rate": 1.6897538314821516e-05, + "loss": 1.5529, + "step": 3165 + }, + { + "epoch": 0.33, + "learning_rate": 1.6894887670873605e-05, + "loss": 1.4427, + "step": 3166 + }, + { + "epoch": 0.33, + "learning_rate": 1.6892236103187904e-05, + "loss": 1.4344, + "step": 3167 + }, + { + "epoch": 0.33, + "learning_rate": 1.6889583612119657e-05, + "loss": 1.4291, + "step": 3168 + }, + { + "epoch": 0.33, + "learning_rate": 1.6886930198024226e-05, + "loss": 1.4683, + "step": 3169 + }, + { + "epoch": 0.33, + "learning_rate": 1.6884275861257106e-05, + "loss": 1.4442, + "step": 3170 + }, + { + "epoch": 0.33, + "learning_rate": 1.6881620602173905e-05, + "loss": 1.4509, + "step": 3171 + }, + { + "epoch": 0.33, + "learning_rate": 1.6878964421130362e-05, + "loss": 1.5113, + "step": 3172 + }, + { + "epoch": 0.33, + "learning_rate": 1.6876307318482334e-05, + "loss": 1.4261, + "step": 3173 + }, + { + "epoch": 0.33, + "learning_rate": 1.6873649294585805e-05, + "loss": 1.445, + "step": 3174 + }, + { + "epoch": 0.33, + "learning_rate": 1.6870990349796886e-05, + "loss": 1.4603, + "step": 3175 + }, + { + "epoch": 0.33, + "learning_rate": 1.68683304844718e-05, + "loss": 1.41, + "step": 3176 + }, + { + "epoch": 0.33, + "learning_rate": 1.686566969896691e-05, + "loss": 1.4018, + "step": 3177 + }, + { + "epoch": 0.33, + "learning_rate": 1.6863007993638687e-05, + "loss": 1.422, + "step": 3178 + }, + { + "epoch": 0.33, + "learning_rate": 1.6860345368843727e-05, + "loss": 1.4412, + "step": 3179 + }, + { + "epoch": 0.33, + "learning_rate": 1.6857681824938768e-05, + "loss": 1.5411, + "step": 3180 + }, + { + "epoch": 0.33, + "learning_rate": 1.685501736228064e-05, + "loss": 1.4416, + "step": 3181 + }, + { + "epoch": 0.33, + "learning_rate": 1.685235198122632e-05, + "loss": 1.5113, + "step": 3182 + }, + { + "epoch": 0.33, + "learning_rate": 1.6849685682132903e-05, + "loss": 1.423, + "step": 3183 + }, + { + "epoch": 0.33, + "learning_rate": 1.68470184653576e-05, + "loss": 1.404, + "step": 3184 + }, + { + "epoch": 0.33, + "eval_loss": 1.4771089553833008, + "eval_runtime": 77.4034, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3184 + }, + { + "epoch": 0.33, + "learning_rate": 1.6844350331257747e-05, + "loss": 1.4624, + "step": 3185 + }, + { + "epoch": 0.33, + "learning_rate": 1.6841681280190814e-05, + "loss": 1.4306, + "step": 3186 + }, + { + "epoch": 0.33, + "learning_rate": 1.683901131251438e-05, + "loss": 1.42, + "step": 3187 + }, + { + "epoch": 0.33, + "learning_rate": 1.6836340428586155e-05, + "loss": 1.4787, + "step": 3188 + }, + { + "epoch": 0.33, + "learning_rate": 1.6833668628763965e-05, + "loss": 1.3485, + "step": 3189 + }, + { + "epoch": 0.33, + "learning_rate": 1.683099591340576e-05, + "loss": 1.3674, + "step": 3190 + }, + { + "epoch": 0.33, + "learning_rate": 1.6828322282869627e-05, + "loss": 1.5187, + "step": 3191 + }, + { + "epoch": 0.33, + "learning_rate": 1.682564773751375e-05, + "loss": 1.4847, + "step": 3192 + }, + { + "epoch": 0.33, + "learning_rate": 1.682297227769646e-05, + "loss": 1.4815, + "step": 3193 + }, + { + "epoch": 0.33, + "learning_rate": 1.682029590377619e-05, + "loss": 1.4281, + "step": 3194 + }, + { + "epoch": 0.34, + "learning_rate": 1.6817618616111517e-05, + "loss": 1.4734, + "step": 3195 + }, + { + "epoch": 0.34, + "learning_rate": 1.681494041506112e-05, + "loss": 1.4861, + "step": 3196 + }, + { + "epoch": 0.34, + "learning_rate": 1.6812261300983808e-05, + "loss": 1.4372, + "step": 3197 + }, + { + "epoch": 0.34, + "learning_rate": 1.680958127423852e-05, + "loss": 1.4396, + "step": 3198 + }, + { + "epoch": 0.34, + "learning_rate": 1.680690033518431e-05, + "loss": 1.4225, + "step": 3199 + }, + { + "epoch": 0.34, + "learning_rate": 1.6804218484180347e-05, + "loss": 1.4925, + "step": 3200 + }, + { + "epoch": 0.34, + "learning_rate": 1.6801535721585942e-05, + "loss": 1.4306, + "step": 3201 + }, + { + "epoch": 0.34, + "learning_rate": 1.6798852047760506e-05, + "loss": 1.4298, + "step": 3202 + }, + { + "epoch": 0.34, + "learning_rate": 1.6796167463063588e-05, + "loss": 1.4725, + "step": 3203 + }, + { + "epoch": 0.34, + "learning_rate": 1.679348196785485e-05, + "loss": 1.4648, + "step": 3204 + }, + { + "epoch": 0.34, + "learning_rate": 1.6790795562494087e-05, + "loss": 1.4152, + "step": 3205 + }, + { + "epoch": 0.34, + "learning_rate": 1.6788108247341198e-05, + "loss": 1.4637, + "step": 3206 + }, + { + "epoch": 0.34, + "learning_rate": 1.6785420022756216e-05, + "loss": 1.4077, + "step": 3207 + }, + { + "epoch": 0.34, + "learning_rate": 1.67827308890993e-05, + "loss": 1.4585, + "step": 3208 + }, + { + "epoch": 0.34, + "learning_rate": 1.678004084673072e-05, + "loss": 1.3747, + "step": 3209 + }, + { + "epoch": 0.34, + "learning_rate": 1.6777349896010876e-05, + "loss": 1.4264, + "step": 3210 + }, + { + "epoch": 0.34, + "learning_rate": 1.677465803730028e-05, + "loss": 1.4178, + "step": 3211 + }, + { + "epoch": 0.34, + "learning_rate": 1.6771965270959584e-05, + "loss": 1.3876, + "step": 3212 + }, + { + "epoch": 0.34, + "learning_rate": 1.6769271597349538e-05, + "loss": 1.4658, + "step": 3213 + }, + { + "epoch": 0.34, + "learning_rate": 1.6766577016831026e-05, + "loss": 1.3968, + "step": 3214 + }, + { + "epoch": 0.34, + "learning_rate": 1.676388152976506e-05, + "loss": 1.5015, + "step": 3215 + }, + { + "epoch": 0.34, + "learning_rate": 1.6761185136512756e-05, + "loss": 1.4121, + "step": 3216 + }, + { + "epoch": 0.34, + "learning_rate": 1.675848783743537e-05, + "loss": 1.4146, + "step": 3217 + }, + { + "epoch": 0.34, + "learning_rate": 1.675578963289427e-05, + "loss": 1.4113, + "step": 3218 + }, + { + "epoch": 0.34, + "learning_rate": 1.6753090523250937e-05, + "loss": 1.4048, + "step": 3219 + }, + { + "epoch": 0.34, + "learning_rate": 1.6750390508866994e-05, + "loss": 1.4959, + "step": 3220 + }, + { + "epoch": 0.34, + "learning_rate": 1.6747689590104167e-05, + "loss": 1.4445, + "step": 3221 + }, + { + "epoch": 0.34, + "learning_rate": 1.6744987767324312e-05, + "loss": 1.4611, + "step": 3222 + }, + { + "epoch": 0.34, + "learning_rate": 1.67422850408894e-05, + "loss": 1.4141, + "step": 3223 + }, + { + "epoch": 0.34, + "learning_rate": 1.6739581411161535e-05, + "loss": 1.4218, + "step": 3224 + }, + { + "epoch": 0.34, + "learning_rate": 1.6736876878502925e-05, + "loss": 1.4266, + "step": 3225 + }, + { + "epoch": 0.34, + "learning_rate": 1.6734171443275913e-05, + "loss": 1.4941, + "step": 3226 + }, + { + "epoch": 0.34, + "learning_rate": 1.6731465105842955e-05, + "loss": 1.4294, + "step": 3227 + }, + { + "epoch": 0.34, + "learning_rate": 1.6728757866566635e-05, + "loss": 1.4189, + "step": 3228 + }, + { + "epoch": 0.34, + "learning_rate": 1.6726049725809647e-05, + "loss": 1.4713, + "step": 3229 + }, + { + "epoch": 0.34, + "learning_rate": 1.6723340683934818e-05, + "loss": 1.4203, + "step": 3230 + }, + { + "epoch": 0.34, + "learning_rate": 1.6720630741305088e-05, + "loss": 1.4112, + "step": 3231 + }, + { + "epoch": 0.34, + "learning_rate": 1.6717919898283523e-05, + "loss": 1.3811, + "step": 3232 + }, + { + "epoch": 0.34, + "learning_rate": 1.6715208155233296e-05, + "loss": 1.4242, + "step": 3233 + }, + { + "epoch": 0.34, + "learning_rate": 1.6712495512517725e-05, + "loss": 1.4207, + "step": 3234 + }, + { + "epoch": 0.34, + "learning_rate": 1.6709781970500222e-05, + "loss": 1.4888, + "step": 3235 + }, + { + "epoch": 0.34, + "learning_rate": 1.670706752954434e-05, + "loss": 1.4501, + "step": 3236 + }, + { + "epoch": 0.34, + "learning_rate": 1.670435219001374e-05, + "loss": 1.4367, + "step": 3237 + }, + { + "epoch": 0.34, + "learning_rate": 1.6701635952272212e-05, + "loss": 1.3959, + "step": 3238 + }, + { + "epoch": 0.34, + "learning_rate": 1.6698918816683655e-05, + "loss": 1.4257, + "step": 3239 + }, + { + "epoch": 0.34, + "learning_rate": 1.6696200783612102e-05, + "loss": 1.4718, + "step": 3240 + }, + { + "epoch": 0.34, + "learning_rate": 1.6693481853421697e-05, + "loss": 1.5899, + "step": 3241 + }, + { + "epoch": 0.34, + "learning_rate": 1.6690762026476707e-05, + "loss": 1.418, + "step": 3242 + }, + { + "epoch": 0.34, + "learning_rate": 1.668804130314152e-05, + "loss": 1.4076, + "step": 3243 + }, + { + "epoch": 0.34, + "learning_rate": 1.6685319683780645e-05, + "loss": 1.4571, + "step": 3244 + }, + { + "epoch": 0.34, + "learning_rate": 1.66825971687587e-05, + "loss": 1.4066, + "step": 3245 + }, + { + "epoch": 0.34, + "learning_rate": 1.6679873758440442e-05, + "loss": 1.4639, + "step": 3246 + }, + { + "epoch": 0.34, + "learning_rate": 1.6677149453190732e-05, + "loss": 1.453, + "step": 3247 + }, + { + "epoch": 0.34, + "learning_rate": 1.6674424253374558e-05, + "loss": 1.4262, + "step": 3248 + }, + { + "epoch": 0.34, + "learning_rate": 1.667169815935703e-05, + "loss": 1.3687, + "step": 3249 + }, + { + "epoch": 0.34, + "learning_rate": 1.6668971171503372e-05, + "loss": 1.5557, + "step": 3250 + }, + { + "epoch": 0.34, + "learning_rate": 1.6666243290178933e-05, + "loss": 1.4639, + "step": 3251 + }, + { + "epoch": 0.34, + "learning_rate": 1.6663514515749172e-05, + "loss": 1.4334, + "step": 3252 + }, + { + "epoch": 0.34, + "learning_rate": 1.6660784848579685e-05, + "loss": 1.3523, + "step": 3253 + }, + { + "epoch": 0.34, + "learning_rate": 1.6658054289036166e-05, + "loss": 1.3738, + "step": 3254 + }, + { + "epoch": 0.34, + "learning_rate": 1.665532283748445e-05, + "loss": 1.4159, + "step": 3255 + }, + { + "epoch": 0.34, + "learning_rate": 1.6652590494290474e-05, + "loss": 1.3609, + "step": 3256 + }, + { + "epoch": 0.34, + "learning_rate": 1.6649857259820303e-05, + "loss": 1.4449, + "step": 3257 + }, + { + "epoch": 0.34, + "learning_rate": 1.6647123134440126e-05, + "loss": 1.424, + "step": 3258 + }, + { + "epoch": 0.34, + "learning_rate": 1.664438811851624e-05, + "loss": 1.4737, + "step": 3259 + }, + { + "epoch": 0.34, + "learning_rate": 1.6641652212415066e-05, + "loss": 1.2717, + "step": 3260 + }, + { + "epoch": 0.34, + "learning_rate": 1.663891541650315e-05, + "loss": 1.4845, + "step": 3261 + }, + { + "epoch": 0.34, + "learning_rate": 1.663617773114715e-05, + "loss": 1.4115, + "step": 3262 + }, + { + "epoch": 0.34, + "learning_rate": 1.663343915671384e-05, + "loss": 1.4237, + "step": 3263 + }, + { + "epoch": 0.34, + "learning_rate": 1.6630699693570127e-05, + "loss": 1.4209, + "step": 3264 + }, + { + "epoch": 0.34, + "learning_rate": 1.6627959342083026e-05, + "loss": 1.506, + "step": 3265 + }, + { + "epoch": 0.34, + "learning_rate": 1.6625218102619672e-05, + "loss": 1.4466, + "step": 3266 + }, + { + "epoch": 0.34, + "learning_rate": 1.6622475975547324e-05, + "loss": 1.4129, + "step": 3267 + }, + { + "epoch": 0.34, + "learning_rate": 1.661973296123335e-05, + "loss": 1.4152, + "step": 3268 + }, + { + "epoch": 0.34, + "learning_rate": 1.661698906004525e-05, + "loss": 1.43, + "step": 3269 + }, + { + "epoch": 0.34, + "learning_rate": 1.661424427235064e-05, + "loss": 1.4701, + "step": 3270 + }, + { + "epoch": 0.34, + "learning_rate": 1.6611498598517238e-05, + "loss": 1.4598, + "step": 3271 + }, + { + "epoch": 0.34, + "learning_rate": 1.66087520389129e-05, + "loss": 1.4795, + "step": 3272 + }, + { + "epoch": 0.34, + "learning_rate": 1.6606004593905595e-05, + "loss": 1.5264, + "step": 3273 + }, + { + "epoch": 0.34, + "learning_rate": 1.6603256263863415e-05, + "loss": 1.4412, + "step": 3274 + }, + { + "epoch": 0.34, + "learning_rate": 1.6600507049154556e-05, + "loss": 1.45, + "step": 3275 + }, + { + "epoch": 0.34, + "learning_rate": 1.659775695014735e-05, + "loss": 1.4985, + "step": 3276 + }, + { + "epoch": 0.34, + "learning_rate": 1.659500596721024e-05, + "loss": 1.496, + "step": 3277 + }, + { + "epoch": 0.34, + "learning_rate": 1.6592254100711775e-05, + "loss": 1.4386, + "step": 3278 + }, + { + "epoch": 0.34, + "learning_rate": 1.658950135102065e-05, + "loss": 1.4073, + "step": 3279 + }, + { + "epoch": 0.34, + "learning_rate": 1.658674771850565e-05, + "loss": 1.3912, + "step": 3280 + }, + { + "epoch": 0.34, + "learning_rate": 1.6583993203535702e-05, + "loss": 1.3628, + "step": 3281 + }, + { + "epoch": 0.34, + "learning_rate": 1.658123780647983e-05, + "loss": 1.6089, + "step": 3282 + }, + { + "epoch": 0.34, + "learning_rate": 1.6578481527707196e-05, + "loss": 1.2367, + "step": 3283 + }, + { + "epoch": 0.34, + "learning_rate": 1.657572436758706e-05, + "loss": 1.4058, + "step": 3284 + }, + { + "epoch": 0.34, + "learning_rate": 1.6572966326488825e-05, + "loss": 1.4067, + "step": 3285 + }, + { + "epoch": 0.34, + "learning_rate": 1.657020740478198e-05, + "loss": 1.4187, + "step": 3286 + }, + { + "epoch": 0.34, + "learning_rate": 1.6567447602836166e-05, + "loss": 1.4599, + "step": 3287 + }, + { + "epoch": 0.34, + "learning_rate": 1.6564686921021115e-05, + "loss": 1.432, + "step": 3288 + }, + { + "epoch": 0.34, + "learning_rate": 1.6561925359706693e-05, + "loss": 1.3941, + "step": 3289 + }, + { + "epoch": 0.35, + "learning_rate": 1.6559162919262874e-05, + "loss": 1.3644, + "step": 3290 + }, + { + "epoch": 0.35, + "learning_rate": 1.6556399600059756e-05, + "loss": 1.4628, + "step": 3291 + }, + { + "epoch": 0.35, + "learning_rate": 1.6553635402467555e-05, + "loss": 1.4355, + "step": 3292 + }, + { + "epoch": 0.35, + "learning_rate": 1.6550870326856596e-05, + "loss": 1.4627, + "step": 3293 + }, + { + "epoch": 0.35, + "learning_rate": 1.6548104373597335e-05, + "loss": 1.442, + "step": 3294 + }, + { + "epoch": 0.35, + "learning_rate": 1.6545337543060338e-05, + "loss": 1.3991, + "step": 3295 + }, + { + "epoch": 0.35, + "learning_rate": 1.6542569835616283e-05, + "loss": 1.4193, + "step": 3296 + }, + { + "epoch": 0.35, + "learning_rate": 1.6539801251635982e-05, + "loss": 1.4792, + "step": 3297 + }, + { + "epoch": 0.35, + "learning_rate": 1.653703179149034e-05, + "loss": 1.4735, + "step": 3298 + }, + { + "epoch": 0.35, + "learning_rate": 1.6534261455550408e-05, + "loss": 1.451, + "step": 3299 + }, + { + "epoch": 0.35, + "learning_rate": 1.653149024418733e-05, + "loss": 1.3975, + "step": 3300 + }, + { + "epoch": 0.35, + "learning_rate": 1.652871815777238e-05, + "loss": 1.4843, + "step": 3301 + }, + { + "epoch": 0.35, + "learning_rate": 1.6525945196676948e-05, + "loss": 1.4782, + "step": 3302 + }, + { + "epoch": 0.35, + "learning_rate": 1.652317136127254e-05, + "loss": 1.3865, + "step": 3303 + }, + { + "epoch": 0.35, + "learning_rate": 1.6520396651930777e-05, + "loss": 1.4359, + "step": 3304 + }, + { + "epoch": 0.35, + "learning_rate": 1.6517621069023397e-05, + "loss": 1.4289, + "step": 3305 + }, + { + "epoch": 0.35, + "learning_rate": 1.651484461292226e-05, + "loss": 1.3526, + "step": 3306 + }, + { + "epoch": 0.35, + "learning_rate": 1.6512067283999336e-05, + "loss": 1.3671, + "step": 3307 + }, + { + "epoch": 0.35, + "learning_rate": 1.650928908262672e-05, + "loss": 1.6041, + "step": 3308 + }, + { + "epoch": 0.35, + "learning_rate": 1.650651000917662e-05, + "loss": 1.4322, + "step": 3309 + }, + { + "epoch": 0.35, + "learning_rate": 1.6503730064021354e-05, + "loss": 1.3992, + "step": 3310 + }, + { + "epoch": 0.35, + "learning_rate": 1.650094924753337e-05, + "loss": 1.4928, + "step": 3311 + }, + { + "epoch": 0.35, + "learning_rate": 1.6498167560085222e-05, + "loss": 1.4075, + "step": 3312 + }, + { + "epoch": 0.35, + "learning_rate": 1.6495385002049583e-05, + "loss": 1.4535, + "step": 3313 + }, + { + "epoch": 0.35, + "learning_rate": 1.6492601573799253e-05, + "loss": 1.4221, + "step": 3314 + }, + { + "epoch": 0.35, + "learning_rate": 1.6489817275707133e-05, + "loss": 1.3688, + "step": 3315 + }, + { + "epoch": 0.35, + "learning_rate": 1.6487032108146243e-05, + "loss": 1.3889, + "step": 3316 + }, + { + "epoch": 0.35, + "learning_rate": 1.6484246071489733e-05, + "loss": 1.3942, + "step": 3317 + }, + { + "epoch": 0.35, + "learning_rate": 1.6481459166110858e-05, + "loss": 1.4004, + "step": 3318 + }, + { + "epoch": 0.35, + "learning_rate": 1.647867139238299e-05, + "loss": 1.7308, + "step": 3319 + }, + { + "epoch": 0.35, + "learning_rate": 1.6475882750679622e-05, + "loss": 1.5001, + "step": 3320 + }, + { + "epoch": 0.35, + "learning_rate": 1.647309324137435e-05, + "loss": 1.4325, + "step": 3321 + }, + { + "epoch": 0.35, + "learning_rate": 1.6470302864840913e-05, + "loss": 1.4494, + "step": 3322 + }, + { + "epoch": 0.35, + "learning_rate": 1.6467511621453136e-05, + "loss": 1.4418, + "step": 3323 + }, + { + "epoch": 0.35, + "learning_rate": 1.646471951158498e-05, + "loss": 1.4046, + "step": 3324 + }, + { + "epoch": 0.35, + "learning_rate": 1.6461926535610517e-05, + "loss": 1.5031, + "step": 3325 + }, + { + "epoch": 0.35, + "learning_rate": 1.645913269390393e-05, + "loss": 1.4813, + "step": 3326 + }, + { + "epoch": 0.35, + "learning_rate": 1.6456337986839525e-05, + "loss": 1.3842, + "step": 3327 + }, + { + "epoch": 0.35, + "learning_rate": 1.645354241479172e-05, + "loss": 1.4539, + "step": 3328 + }, + { + "epoch": 0.35, + "learning_rate": 1.6450745978135048e-05, + "loss": 1.4503, + "step": 3329 + }, + { + "epoch": 0.35, + "learning_rate": 1.6447948677244163e-05, + "loss": 1.3741, + "step": 3330 + }, + { + "epoch": 0.35, + "learning_rate": 1.6445150512493832e-05, + "loss": 1.425, + "step": 3331 + }, + { + "epoch": 0.35, + "learning_rate": 1.644235148425893e-05, + "loss": 1.4277, + "step": 3332 + }, + { + "epoch": 0.35, + "learning_rate": 1.6439551592914464e-05, + "loss": 1.4918, + "step": 3333 + }, + { + "epoch": 0.35, + "learning_rate": 1.6436750838835543e-05, + "loss": 1.3364, + "step": 3334 + }, + { + "epoch": 0.35, + "learning_rate": 1.6433949222397397e-05, + "loss": 1.4741, + "step": 3335 + }, + { + "epoch": 0.35, + "learning_rate": 1.643114674397537e-05, + "loss": 1.3867, + "step": 3336 + }, + { + "epoch": 0.35, + "learning_rate": 1.642834340394492e-05, + "loss": 1.3817, + "step": 3337 + }, + { + "epoch": 0.35, + "learning_rate": 1.6425539202681625e-05, + "loss": 1.4308, + "step": 3338 + }, + { + "epoch": 0.35, + "learning_rate": 1.6422734140561178e-05, + "loss": 1.4401, + "step": 3339 + }, + { + "epoch": 0.35, + "learning_rate": 1.641992821795938e-05, + "loss": 1.4338, + "step": 3340 + }, + { + "epoch": 0.35, + "learning_rate": 1.641712143525216e-05, + "loss": 1.3804, + "step": 3341 + }, + { + "epoch": 0.35, + "learning_rate": 1.6414313792815546e-05, + "loss": 1.371, + "step": 3342 + }, + { + "epoch": 0.35, + "learning_rate": 1.6411505291025695e-05, + "loss": 1.4102, + "step": 3343 + }, + { + "epoch": 0.35, + "learning_rate": 1.6408695930258875e-05, + "loss": 1.4433, + "step": 3344 + }, + { + "epoch": 0.35, + "learning_rate": 1.6405885710891467e-05, + "loss": 1.3895, + "step": 3345 + }, + { + "epoch": 0.35, + "learning_rate": 1.6403074633299966e-05, + "loss": 1.4321, + "step": 3346 + }, + { + "epoch": 0.35, + "learning_rate": 1.640026269786098e-05, + "loss": 1.4207, + "step": 3347 + }, + { + "epoch": 0.35, + "learning_rate": 1.639744990495125e-05, + "loss": 1.3758, + "step": 3348 + }, + { + "epoch": 0.35, + "learning_rate": 1.6394636254947612e-05, + "loss": 1.4203, + "step": 3349 + }, + { + "epoch": 0.35, + "learning_rate": 1.6391821748227013e-05, + "loss": 1.4596, + "step": 3350 + }, + { + "epoch": 0.35, + "learning_rate": 1.6389006385166537e-05, + "loss": 1.4344, + "step": 3351 + }, + { + "epoch": 0.35, + "learning_rate": 1.6386190166143366e-05, + "loss": 1.4048, + "step": 3352 + }, + { + "epoch": 0.35, + "learning_rate": 1.6383373091534798e-05, + "loss": 1.4348, + "step": 3353 + }, + { + "epoch": 0.35, + "learning_rate": 1.638055516171825e-05, + "loss": 1.4972, + "step": 3354 + }, + { + "epoch": 0.35, + "learning_rate": 1.6377736377071258e-05, + "loss": 1.4685, + "step": 3355 + }, + { + "epoch": 0.35, + "learning_rate": 1.637491673797146e-05, + "loss": 1.4093, + "step": 3356 + }, + { + "epoch": 0.35, + "learning_rate": 1.6372096244796616e-05, + "loss": 1.4452, + "step": 3357 + }, + { + "epoch": 0.35, + "learning_rate": 1.63692748979246e-05, + "loss": 1.4458, + "step": 3358 + }, + { + "epoch": 0.35, + "learning_rate": 1.6366452697733404e-05, + "loss": 1.4187, + "step": 3359 + }, + { + "epoch": 0.35, + "learning_rate": 1.6363629644601126e-05, + "loss": 1.4052, + "step": 3360 + }, + { + "epoch": 0.35, + "learning_rate": 1.6360805738905984e-05, + "loss": 1.439, + "step": 3361 + }, + { + "epoch": 0.35, + "learning_rate": 1.635798098102631e-05, + "loss": 1.4131, + "step": 3362 + }, + { + "epoch": 0.35, + "learning_rate": 1.6355155371340544e-05, + "loss": 1.4391, + "step": 3363 + }, + { + "epoch": 0.35, + "learning_rate": 1.6352328910227252e-05, + "loss": 1.4318, + "step": 3364 + }, + { + "epoch": 0.35, + "learning_rate": 1.63495015980651e-05, + "loss": 1.5112, + "step": 3365 + }, + { + "epoch": 0.35, + "learning_rate": 1.6346673435232884e-05, + "loss": 1.4688, + "step": 3366 + }, + { + "epoch": 0.35, + "learning_rate": 1.6343844422109496e-05, + "loss": 1.3807, + "step": 3367 + }, + { + "epoch": 0.35, + "learning_rate": 1.634101455907396e-05, + "loss": 1.4083, + "step": 3368 + }, + { + "epoch": 0.35, + "learning_rate": 1.6338183846505394e-05, + "loss": 1.3566, + "step": 3369 + }, + { + "epoch": 0.35, + "learning_rate": 1.633535228478305e-05, + "loss": 1.4287, + "step": 3370 + }, + { + "epoch": 0.35, + "learning_rate": 1.6332519874286285e-05, + "loss": 1.3494, + "step": 3371 + }, + { + "epoch": 0.35, + "learning_rate": 1.6329686615394558e-05, + "loss": 1.3813, + "step": 3372 + }, + { + "epoch": 0.35, + "learning_rate": 1.6326852508487468e-05, + "loss": 1.4241, + "step": 3373 + }, + { + "epoch": 0.35, + "learning_rate": 1.63240175539447e-05, + "loss": 1.424, + "step": 3374 + }, + { + "epoch": 0.35, + "learning_rate": 1.632118175214607e-05, + "loss": 1.4212, + "step": 3375 + }, + { + "epoch": 0.35, + "learning_rate": 1.6318345103471504e-05, + "loss": 1.4671, + "step": 3376 + }, + { + "epoch": 0.35, + "learning_rate": 1.6315507608301044e-05, + "loss": 1.4593, + "step": 3377 + }, + { + "epoch": 0.35, + "learning_rate": 1.631266926701483e-05, + "loss": 1.7816, + "step": 3378 + }, + { + "epoch": 0.35, + "learning_rate": 1.6309830079993134e-05, + "loss": 1.5134, + "step": 3379 + }, + { + "epoch": 0.35, + "learning_rate": 1.6306990047616334e-05, + "loss": 0.8933, + "step": 3380 + }, + { + "epoch": 0.35, + "learning_rate": 1.630414917026492e-05, + "loss": 1.1033, + "step": 3381 + }, + { + "epoch": 0.35, + "learning_rate": 1.6301307448319497e-05, + "loss": 1.3494, + "step": 3382 + }, + { + "epoch": 0.35, + "learning_rate": 1.6298464882160784e-05, + "loss": 1.4299, + "step": 3383 + }, + { + "epoch": 0.35, + "eval_loss": 1.482450008392334, + "eval_runtime": 77.3737, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3383 + }, + { + "epoch": 0.35, + "learning_rate": 1.629562147216961e-05, + "loss": 1.3971, + "step": 3384 + }, + { + "epoch": 0.35, + "learning_rate": 1.6292777218726917e-05, + "loss": 1.3706, + "step": 3385 + }, + { + "epoch": 0.36, + "learning_rate": 1.6289932122213765e-05, + "loss": 1.4524, + "step": 3386 + }, + { + "epoch": 0.36, + "learning_rate": 1.6287086183011328e-05, + "loss": 1.4595, + "step": 3387 + }, + { + "epoch": 0.36, + "learning_rate": 1.628423940150088e-05, + "loss": 1.492, + "step": 3388 + }, + { + "epoch": 0.36, + "learning_rate": 1.628139177806382e-05, + "loss": 1.5576, + "step": 3389 + }, + { + "epoch": 0.36, + "learning_rate": 1.6278543313081657e-05, + "loss": 1.4615, + "step": 3390 + }, + { + "epoch": 0.36, + "learning_rate": 1.6275694006936015e-05, + "loss": 1.3456, + "step": 3391 + }, + { + "epoch": 0.36, + "learning_rate": 1.627284386000862e-05, + "loss": 1.4254, + "step": 3392 + }, + { + "epoch": 0.36, + "learning_rate": 1.6269992872681325e-05, + "loss": 1.433, + "step": 3393 + }, + { + "epoch": 0.36, + "learning_rate": 1.626714104533609e-05, + "loss": 1.5291, + "step": 3394 + }, + { + "epoch": 0.36, + "learning_rate": 1.626428837835498e-05, + "loss": 1.4502, + "step": 3395 + }, + { + "epoch": 0.36, + "learning_rate": 1.626143487212019e-05, + "loss": 1.3756, + "step": 3396 + }, + { + "epoch": 0.36, + "learning_rate": 1.6258580527014002e-05, + "loss": 1.414, + "step": 3397 + }, + { + "epoch": 0.36, + "learning_rate": 1.6255725343418835e-05, + "loss": 1.6289, + "step": 3398 + }, + { + "epoch": 0.36, + "learning_rate": 1.6252869321717208e-05, + "loss": 1.4862, + "step": 3399 + }, + { + "epoch": 0.36, + "learning_rate": 1.6250012462291756e-05, + "loss": 1.4213, + "step": 3400 + }, + { + "epoch": 0.36, + "learning_rate": 1.6247154765525217e-05, + "loss": 1.524, + "step": 3401 + }, + { + "epoch": 0.36, + "learning_rate": 1.624429623180046e-05, + "loss": 1.6013, + "step": 3402 + }, + { + "epoch": 0.36, + "learning_rate": 1.624143686150045e-05, + "loss": 1.4557, + "step": 3403 + }, + { + "epoch": 0.36, + "learning_rate": 1.6238576655008266e-05, + "loss": 1.3831, + "step": 3404 + }, + { + "epoch": 0.36, + "learning_rate": 1.6235715612707105e-05, + "loss": 1.4008, + "step": 3405 + }, + { + "epoch": 0.36, + "learning_rate": 1.623285373498028e-05, + "loss": 1.4848, + "step": 3406 + }, + { + "epoch": 0.36, + "learning_rate": 1.6229991022211197e-05, + "loss": 1.4459, + "step": 3407 + }, + { + "epoch": 0.36, + "learning_rate": 1.6227127474783393e-05, + "loss": 1.4334, + "step": 3408 + }, + { + "epoch": 0.36, + "learning_rate": 1.6224263093080507e-05, + "loss": 1.4123, + "step": 3409 + }, + { + "epoch": 0.36, + "learning_rate": 1.6221397877486294e-05, + "loss": 1.3691, + "step": 3410 + }, + { + "epoch": 0.36, + "learning_rate": 1.6218531828384618e-05, + "loss": 1.4128, + "step": 3411 + }, + { + "epoch": 0.36, + "learning_rate": 1.6215664946159457e-05, + "loss": 1.3642, + "step": 3412 + }, + { + "epoch": 0.36, + "learning_rate": 1.6212797231194902e-05, + "loss": 1.4311, + "step": 3413 + }, + { + "epoch": 0.36, + "learning_rate": 1.6209928683875152e-05, + "loss": 1.4695, + "step": 3414 + }, + { + "epoch": 0.36, + "learning_rate": 1.6207059304584514e-05, + "loss": 1.3871, + "step": 3415 + }, + { + "epoch": 0.36, + "learning_rate": 1.6204189093707414e-05, + "loss": 1.4219, + "step": 3416 + }, + { + "epoch": 0.36, + "learning_rate": 1.620131805162839e-05, + "loss": 1.6199, + "step": 3417 + }, + { + "epoch": 0.36, + "learning_rate": 1.619844617873208e-05, + "loss": 1.4433, + "step": 3418 + }, + { + "epoch": 0.36, + "learning_rate": 1.619557347540325e-05, + "loss": 1.4773, + "step": 3419 + }, + { + "epoch": 0.36, + "learning_rate": 1.6192699942026763e-05, + "loss": 1.4551, + "step": 3420 + }, + { + "epoch": 0.36, + "learning_rate": 1.6189825578987603e-05, + "loss": 1.4903, + "step": 3421 + }, + { + "epoch": 0.36, + "learning_rate": 1.6186950386670855e-05, + "loss": 1.473, + "step": 3422 + }, + { + "epoch": 0.36, + "learning_rate": 1.6184074365461722e-05, + "loss": 1.4082, + "step": 3423 + }, + { + "epoch": 0.36, + "learning_rate": 1.6181197515745523e-05, + "loss": 1.4746, + "step": 3424 + }, + { + "epoch": 0.36, + "learning_rate": 1.6178319837907674e-05, + "loss": 1.449, + "step": 3425 + }, + { + "epoch": 0.36, + "learning_rate": 1.6175441332333715e-05, + "loss": 1.377, + "step": 3426 + }, + { + "epoch": 0.36, + "learning_rate": 1.617256199940929e-05, + "loss": 1.2364, + "step": 3427 + }, + { + "epoch": 0.36, + "learning_rate": 1.6169681839520155e-05, + "loss": 1.4437, + "step": 3428 + }, + { + "epoch": 0.36, + "learning_rate": 1.616680085305218e-05, + "loss": 1.4726, + "step": 3429 + }, + { + "epoch": 0.36, + "learning_rate": 1.616391904039134e-05, + "loss": 1.4824, + "step": 3430 + }, + { + "epoch": 0.36, + "learning_rate": 1.616103640192373e-05, + "loss": 1.4052, + "step": 3431 + }, + { + "epoch": 0.36, + "learning_rate": 1.6158152938035537e-05, + "loss": 1.4131, + "step": 3432 + }, + { + "epoch": 0.36, + "learning_rate": 1.6155268649113084e-05, + "loss": 1.4267, + "step": 3433 + }, + { + "epoch": 0.36, + "learning_rate": 1.6152383535542786e-05, + "loss": 1.3735, + "step": 3434 + }, + { + "epoch": 0.36, + "learning_rate": 1.6149497597711175e-05, + "loss": 1.4249, + "step": 3435 + }, + { + "epoch": 0.36, + "learning_rate": 1.614661083600489e-05, + "loss": 1.4312, + "step": 3436 + }, + { + "epoch": 0.36, + "learning_rate": 1.6143723250810686e-05, + "loss": 1.4831, + "step": 3437 + }, + { + "epoch": 0.36, + "learning_rate": 1.6140834842515425e-05, + "loss": 1.4183, + "step": 3438 + }, + { + "epoch": 0.36, + "learning_rate": 1.6137945611506078e-05, + "loss": 1.3908, + "step": 3439 + }, + { + "epoch": 0.36, + "learning_rate": 1.613505555816973e-05, + "loss": 1.425, + "step": 3440 + }, + { + "epoch": 0.36, + "learning_rate": 1.613216468289357e-05, + "loss": 1.3589, + "step": 3441 + }, + { + "epoch": 0.36, + "learning_rate": 1.6129272986064903e-05, + "loss": 1.4272, + "step": 3442 + }, + { + "epoch": 0.36, + "learning_rate": 1.6126380468071142e-05, + "loss": 1.4337, + "step": 3443 + }, + { + "epoch": 0.36, + "learning_rate": 1.6123487129299817e-05, + "loss": 1.3872, + "step": 3444 + }, + { + "epoch": 0.36, + "learning_rate": 1.612059297013855e-05, + "loss": 1.374, + "step": 3445 + }, + { + "epoch": 0.36, + "learning_rate": 1.611769799097509e-05, + "loss": 1.314, + "step": 3446 + }, + { + "epoch": 0.36, + "learning_rate": 1.6114802192197284e-05, + "loss": 1.3951, + "step": 3447 + }, + { + "epoch": 0.36, + "learning_rate": 1.6111905574193102e-05, + "loss": 1.4732, + "step": 3448 + }, + { + "epoch": 0.36, + "learning_rate": 1.6109008137350614e-05, + "loss": 1.3575, + "step": 3449 + }, + { + "epoch": 0.36, + "learning_rate": 1.6106109882058e-05, + "loss": 1.4606, + "step": 3450 + }, + { + "epoch": 0.36, + "learning_rate": 1.6103210808703554e-05, + "loss": 1.4357, + "step": 3451 + }, + { + "epoch": 0.36, + "learning_rate": 1.6100310917675678e-05, + "loss": 0.8456, + "step": 3452 + }, + { + "epoch": 0.36, + "learning_rate": 1.609741020936288e-05, + "loss": 1.07, + "step": 3453 + }, + { + "epoch": 0.36, + "learning_rate": 1.6094508684153782e-05, + "loss": 1.4435, + "step": 3454 + }, + { + "epoch": 0.36, + "learning_rate": 1.609160634243711e-05, + "loss": 1.3696, + "step": 3455 + }, + { + "epoch": 0.36, + "learning_rate": 1.6088703184601712e-05, + "loss": 1.4012, + "step": 3456 + }, + { + "epoch": 0.36, + "learning_rate": 1.608579921103653e-05, + "loss": 1.5212, + "step": 3457 + }, + { + "epoch": 0.36, + "learning_rate": 1.608289442213062e-05, + "loss": 1.4339, + "step": 3458 + }, + { + "epoch": 0.36, + "learning_rate": 1.607998881827316e-05, + "loss": 1.4901, + "step": 3459 + }, + { + "epoch": 0.36, + "learning_rate": 1.6077082399853412e-05, + "loss": 1.4822, + "step": 3460 + }, + { + "epoch": 0.36, + "learning_rate": 1.607417516726077e-05, + "loss": 1.3696, + "step": 3461 + }, + { + "epoch": 0.36, + "learning_rate": 1.6071267120884727e-05, + "loss": 1.4434, + "step": 3462 + }, + { + "epoch": 0.36, + "learning_rate": 1.6068358261114886e-05, + "loss": 1.3916, + "step": 3463 + }, + { + "epoch": 0.36, + "learning_rate": 1.606544858834096e-05, + "loss": 1.422, + "step": 3464 + }, + { + "epoch": 0.36, + "learning_rate": 1.6062538102952763e-05, + "loss": 1.367, + "step": 3465 + }, + { + "epoch": 0.36, + "learning_rate": 1.605962680534024e-05, + "loss": 1.3788, + "step": 3466 + }, + { + "epoch": 0.36, + "learning_rate": 1.605671469589342e-05, + "loss": 1.4366, + "step": 3467 + }, + { + "epoch": 0.36, + "learning_rate": 1.6053801775002453e-05, + "loss": 1.4027, + "step": 3468 + }, + { + "epoch": 0.36, + "learning_rate": 1.6050888043057595e-05, + "loss": 1.4386, + "step": 3469 + }, + { + "epoch": 0.36, + "learning_rate": 1.6047973500449212e-05, + "loss": 1.4675, + "step": 3470 + }, + { + "epoch": 0.36, + "learning_rate": 1.6045058147567778e-05, + "loss": 1.6936, + "step": 3471 + }, + { + "epoch": 0.36, + "learning_rate": 1.6042141984803875e-05, + "loss": 1.4858, + "step": 3472 + }, + { + "epoch": 0.36, + "learning_rate": 1.6039225012548196e-05, + "loss": 1.5004, + "step": 3473 + }, + { + "epoch": 0.36, + "learning_rate": 1.6036307231191534e-05, + "loss": 1.4969, + "step": 3474 + }, + { + "epoch": 0.36, + "learning_rate": 1.6033388641124803e-05, + "loss": 1.4027, + "step": 3475 + }, + { + "epoch": 0.36, + "learning_rate": 1.6030469242739016e-05, + "loss": 1.4741, + "step": 3476 + }, + { + "epoch": 0.36, + "learning_rate": 1.60275490364253e-05, + "loss": 1.3887, + "step": 3477 + }, + { + "epoch": 0.36, + "learning_rate": 1.602462802257488e-05, + "loss": 1.6735, + "step": 3478 + }, + { + "epoch": 0.36, + "learning_rate": 1.602170620157911e-05, + "loss": 1.4997, + "step": 3479 + }, + { + "epoch": 0.36, + "learning_rate": 1.601878357382943e-05, + "loss": 1.3973, + "step": 3480 + }, + { + "epoch": 0.37, + "learning_rate": 1.6015860139717398e-05, + "loss": 1.416, + "step": 3481 + }, + { + "epoch": 0.37, + "learning_rate": 1.6012935899634682e-05, + "loss": 1.4102, + "step": 3482 + }, + { + "epoch": 0.37, + "learning_rate": 1.601001085397305e-05, + "loss": 1.4248, + "step": 3483 + }, + { + "epoch": 0.37, + "learning_rate": 1.6007085003124386e-05, + "loss": 1.3909, + "step": 3484 + }, + { + "epoch": 0.37, + "learning_rate": 1.600415834748068e-05, + "loss": 1.4029, + "step": 3485 + }, + { + "epoch": 0.37, + "learning_rate": 1.6001230887434024e-05, + "loss": 1.4219, + "step": 3486 + }, + { + "epoch": 0.37, + "learning_rate": 1.5998302623376633e-05, + "loss": 1.4008, + "step": 3487 + }, + { + "epoch": 0.37, + "learning_rate": 1.5995373555700806e-05, + "loss": 1.5163, + "step": 3488 + }, + { + "epoch": 0.37, + "learning_rate": 1.599244368479897e-05, + "loss": 1.4541, + "step": 3489 + }, + { + "epoch": 0.37, + "learning_rate": 1.598951301106365e-05, + "loss": 1.4454, + "step": 3490 + }, + { + "epoch": 0.37, + "learning_rate": 1.598658153488748e-05, + "loss": 1.1014, + "step": 3491 + }, + { + "epoch": 0.37, + "learning_rate": 1.598364925666321e-05, + "loss": 1.407, + "step": 3492 + }, + { + "epoch": 0.37, + "learning_rate": 1.5980716176783682e-05, + "loss": 1.5046, + "step": 3493 + }, + { + "epoch": 0.37, + "learning_rate": 1.5977782295641857e-05, + "loss": 1.4265, + "step": 3494 + }, + { + "epoch": 0.37, + "learning_rate": 1.5974847613630796e-05, + "loss": 1.46, + "step": 3495 + }, + { + "epoch": 0.37, + "learning_rate": 1.5971912131143677e-05, + "loss": 1.3996, + "step": 3496 + }, + { + "epoch": 0.37, + "learning_rate": 1.5968975848573772e-05, + "loss": 1.4719, + "step": 3497 + }, + { + "epoch": 0.37, + "learning_rate": 1.596603876631447e-05, + "loss": 1.43, + "step": 3498 + }, + { + "epoch": 0.37, + "learning_rate": 1.596310088475927e-05, + "loss": 1.4109, + "step": 3499 + }, + { + "epoch": 0.37, + "learning_rate": 1.5960162204301768e-05, + "loss": 1.3612, + "step": 3500 + }, + { + "epoch": 0.37, + "learning_rate": 1.5957222725335672e-05, + "loss": 1.5045, + "step": 3501 + }, + { + "epoch": 0.37, + "learning_rate": 1.5954282448254794e-05, + "loss": 1.5323, + "step": 3502 + }, + { + "epoch": 0.37, + "learning_rate": 1.595134137345306e-05, + "loss": 1.4518, + "step": 3503 + }, + { + "epoch": 0.37, + "learning_rate": 1.5948399501324495e-05, + "loss": 1.6131, + "step": 3504 + }, + { + "epoch": 0.37, + "learning_rate": 1.594545683226324e-05, + "loss": 1.5076, + "step": 3505 + }, + { + "epoch": 0.37, + "learning_rate": 1.594251336666353e-05, + "loss": 1.482, + "step": 3506 + }, + { + "epoch": 0.37, + "learning_rate": 1.5939569104919716e-05, + "loss": 1.4429, + "step": 3507 + }, + { + "epoch": 0.37, + "learning_rate": 1.5936624047426254e-05, + "loss": 1.4662, + "step": 3508 + }, + { + "epoch": 0.37, + "learning_rate": 1.5933678194577708e-05, + "loss": 1.425, + "step": 3509 + }, + { + "epoch": 0.37, + "learning_rate": 1.5930731546768744e-05, + "loss": 1.4312, + "step": 3510 + }, + { + "epoch": 0.37, + "learning_rate": 1.592778410439414e-05, + "loss": 1.4336, + "step": 3511 + }, + { + "epoch": 0.37, + "learning_rate": 1.5924835867848775e-05, + "loss": 1.4197, + "step": 3512 + }, + { + "epoch": 0.37, + "learning_rate": 1.5921886837527638e-05, + "loss": 1.4456, + "step": 3513 + }, + { + "epoch": 0.37, + "learning_rate": 1.5918937013825823e-05, + "loss": 1.4394, + "step": 3514 + }, + { + "epoch": 0.37, + "learning_rate": 1.5915986397138526e-05, + "loss": 1.3606, + "step": 3515 + }, + { + "epoch": 0.37, + "learning_rate": 1.591303498786106e-05, + "loss": 1.4382, + "step": 3516 + }, + { + "epoch": 0.37, + "learning_rate": 1.591008278638884e-05, + "loss": 1.4185, + "step": 3517 + }, + { + "epoch": 0.37, + "learning_rate": 1.5907129793117374e-05, + "loss": 1.6692, + "step": 3518 + }, + { + "epoch": 0.37, + "learning_rate": 1.59041760084423e-05, + "loss": 1.501, + "step": 3519 + }, + { + "epoch": 0.37, + "learning_rate": 1.5901221432759345e-05, + "loss": 1.5753, + "step": 3520 + }, + { + "epoch": 0.37, + "learning_rate": 1.589826606646434e-05, + "loss": 1.4795, + "step": 3521 + }, + { + "epoch": 0.37, + "learning_rate": 1.5895309909953236e-05, + "loss": 1.4379, + "step": 3522 + }, + { + "epoch": 0.37, + "learning_rate": 1.5892352963622078e-05, + "loss": 1.3426, + "step": 3523 + }, + { + "epoch": 0.37, + "learning_rate": 1.5889395227867025e-05, + "loss": 1.4048, + "step": 3524 + }, + { + "epoch": 0.37, + "learning_rate": 1.5886436703084332e-05, + "loss": 1.4303, + "step": 3525 + }, + { + "epoch": 0.37, + "learning_rate": 1.5883477389670367e-05, + "loss": 1.3684, + "step": 3526 + }, + { + "epoch": 0.37, + "learning_rate": 1.5880517288021602e-05, + "loss": 1.3701, + "step": 3527 + }, + { + "epoch": 0.37, + "learning_rate": 1.587755639853462e-05, + "loss": 1.4308, + "step": 3528 + }, + { + "epoch": 0.37, + "learning_rate": 1.5874594721606096e-05, + "loss": 1.3981, + "step": 3529 + }, + { + "epoch": 0.37, + "learning_rate": 1.5871632257632823e-05, + "loss": 1.5906, + "step": 3530 + }, + { + "epoch": 0.37, + "learning_rate": 1.5868669007011696e-05, + "loss": 1.4642, + "step": 3531 + }, + { + "epoch": 0.37, + "learning_rate": 1.586570497013971e-05, + "loss": 1.411, + "step": 3532 + }, + { + "epoch": 0.37, + "learning_rate": 1.586274014741397e-05, + "loss": 1.3942, + "step": 3533 + }, + { + "epoch": 0.37, + "learning_rate": 1.5859774539231693e-05, + "loss": 1.3952, + "step": 3534 + }, + { + "epoch": 0.37, + "learning_rate": 1.585680814599019e-05, + "loss": 1.4009, + "step": 3535 + }, + { + "epoch": 0.37, + "learning_rate": 1.585384096808688e-05, + "loss": 1.3238, + "step": 3536 + }, + { + "epoch": 0.37, + "learning_rate": 1.585087300591929e-05, + "loss": 1.346, + "step": 3537 + }, + { + "epoch": 0.37, + "learning_rate": 1.584790425988505e-05, + "loss": 1.3739, + "step": 3538 + }, + { + "epoch": 0.37, + "learning_rate": 1.5844934730381895e-05, + "loss": 1.4264, + "step": 3539 + }, + { + "epoch": 0.37, + "learning_rate": 1.5841964417807668e-05, + "loss": 1.4675, + "step": 3540 + }, + { + "epoch": 0.37, + "learning_rate": 1.5838993322560314e-05, + "loss": 1.3337, + "step": 3541 + }, + { + "epoch": 0.37, + "learning_rate": 1.5836021445037883e-05, + "loss": 1.4052, + "step": 3542 + }, + { + "epoch": 0.37, + "learning_rate": 1.583304878563853e-05, + "loss": 1.4311, + "step": 3543 + }, + { + "epoch": 0.37, + "learning_rate": 1.5830075344760513e-05, + "loss": 1.386, + "step": 3544 + }, + { + "epoch": 0.37, + "learning_rate": 1.58271011228022e-05, + "loss": 1.387, + "step": 3545 + }, + { + "epoch": 0.37, + "learning_rate": 1.582412612016206e-05, + "loss": 1.3601, + "step": 3546 + }, + { + "epoch": 0.37, + "learning_rate": 1.5821150337238663e-05, + "loss": 1.5111, + "step": 3547 + }, + { + "epoch": 0.37, + "learning_rate": 1.5818173774430697e-05, + "loss": 1.471, + "step": 3548 + }, + { + "epoch": 0.37, + "learning_rate": 1.581519643213693e-05, + "loss": 1.4442, + "step": 3549 + }, + { + "epoch": 0.37, + "learning_rate": 1.5812218310756263e-05, + "loss": 1.467, + "step": 3550 + }, + { + "epoch": 0.37, + "learning_rate": 1.5809239410687683e-05, + "loss": 1.3731, + "step": 3551 + }, + { + "epoch": 0.37, + "learning_rate": 1.5806259732330286e-05, + "loss": 1.4072, + "step": 3552 + }, + { + "epoch": 0.37, + "learning_rate": 1.5803279276083268e-05, + "loss": 1.3636, + "step": 3553 + }, + { + "epoch": 0.37, + "learning_rate": 1.5800298042345938e-05, + "loss": 1.3915, + "step": 3554 + }, + { + "epoch": 0.37, + "learning_rate": 1.5797316031517705e-05, + "loss": 1.5038, + "step": 3555 + }, + { + "epoch": 0.37, + "learning_rate": 1.5794333243998082e-05, + "loss": 1.4455, + "step": 3556 + }, + { + "epoch": 0.37, + "learning_rate": 1.5791349680186684e-05, + "loss": 1.5062, + "step": 3557 + }, + { + "epoch": 0.37, + "learning_rate": 1.5788365340483234e-05, + "loss": 1.3899, + "step": 3558 + }, + { + "epoch": 0.37, + "learning_rate": 1.5785380225287554e-05, + "loss": 1.4946, + "step": 3559 + }, + { + "epoch": 0.37, + "learning_rate": 1.5782394334999572e-05, + "loss": 1.3859, + "step": 3560 + }, + { + "epoch": 0.37, + "learning_rate": 1.577940767001933e-05, + "loss": 1.541, + "step": 3561 + }, + { + "epoch": 0.37, + "learning_rate": 1.5776420230746952e-05, + "loss": 1.4952, + "step": 3562 + }, + { + "epoch": 0.37, + "learning_rate": 1.5773432017582684e-05, + "loss": 1.6055, + "step": 3563 + }, + { + "epoch": 0.37, + "learning_rate": 1.577044303092687e-05, + "loss": 1.4661, + "step": 3564 + }, + { + "epoch": 0.37, + "learning_rate": 1.576745327117996e-05, + "loss": 1.4082, + "step": 3565 + }, + { + "epoch": 0.37, + "learning_rate": 1.5764462738742493e-05, + "loss": 1.4005, + "step": 3566 + }, + { + "epoch": 0.37, + "learning_rate": 1.5761471434015137e-05, + "loss": 1.3959, + "step": 3567 + }, + { + "epoch": 0.37, + "learning_rate": 1.5758479357398645e-05, + "loss": 1.4567, + "step": 3568 + }, + { + "epoch": 0.37, + "learning_rate": 1.575548650929388e-05, + "loss": 1.3791, + "step": 3569 + }, + { + "epoch": 0.37, + "learning_rate": 1.57524928901018e-05, + "loss": 1.4428, + "step": 3570 + }, + { + "epoch": 0.37, + "learning_rate": 1.5749498500223486e-05, + "loss": 1.3864, + "step": 3571 + }, + { + "epoch": 0.37, + "learning_rate": 1.5746503340060097e-05, + "loss": 1.4019, + "step": 3572 + }, + { + "epoch": 0.37, + "learning_rate": 1.574350741001291e-05, + "loss": 1.5436, + "step": 3573 + }, + { + "epoch": 0.37, + "learning_rate": 1.5740510710483308e-05, + "loss": 1.4637, + "step": 3574 + }, + { + "epoch": 0.37, + "learning_rate": 1.5737513241872767e-05, + "loss": 1.5097, + "step": 3575 + }, + { + "epoch": 0.38, + "learning_rate": 1.5734515004582873e-05, + "loss": 1.5143, + "step": 3576 + }, + { + "epoch": 0.38, + "learning_rate": 1.5731515999015315e-05, + "loss": 1.3926, + "step": 3577 + }, + { + "epoch": 0.38, + "learning_rate": 1.5728516225571874e-05, + "loss": 1.4242, + "step": 3578 + }, + { + "epoch": 0.38, + "learning_rate": 1.5725515684654453e-05, + "loss": 1.4429, + "step": 3579 + }, + { + "epoch": 0.38, + "learning_rate": 1.572251437666504e-05, + "loss": 1.4638, + "step": 3580 + }, + { + "epoch": 0.38, + "learning_rate": 1.5719512302005735e-05, + "loss": 1.3381, + "step": 3581 + }, + { + "epoch": 0.38, + "learning_rate": 1.571650946107874e-05, + "loss": 1.4342, + "step": 3582 + }, + { + "epoch": 0.38, + "eval_loss": 1.4705015420913696, + "eval_runtime": 77.3664, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3582 + }, + { + "epoch": 0.38, + "learning_rate": 1.571350585428636e-05, + "loss": 1.3991, + "step": 3583 + }, + { + "epoch": 0.38, + "learning_rate": 1.5710501482030998e-05, + "loss": 1.4274, + "step": 3584 + }, + { + "epoch": 0.38, + "learning_rate": 1.5707496344715166e-05, + "loss": 1.438, + "step": 3585 + }, + { + "epoch": 0.38, + "learning_rate": 1.570449044274147e-05, + "loss": 1.4453, + "step": 3586 + }, + { + "epoch": 0.38, + "learning_rate": 1.570148377651263e-05, + "loss": 1.4022, + "step": 3587 + }, + { + "epoch": 0.38, + "learning_rate": 1.5698476346431454e-05, + "loss": 1.4312, + "step": 3588 + }, + { + "epoch": 0.38, + "learning_rate": 1.569546815290087e-05, + "loss": 1.4329, + "step": 3589 + }, + { + "epoch": 0.38, + "learning_rate": 1.569245919632389e-05, + "loss": 1.4036, + "step": 3590 + }, + { + "epoch": 0.38, + "learning_rate": 1.5689449477103644e-05, + "loss": 1.412, + "step": 3591 + }, + { + "epoch": 0.38, + "learning_rate": 1.5686438995643353e-05, + "loss": 1.4492, + "step": 3592 + }, + { + "epoch": 0.38, + "learning_rate": 1.5683427752346343e-05, + "loss": 1.4555, + "step": 3593 + }, + { + "epoch": 0.38, + "learning_rate": 1.5680415747616047e-05, + "loss": 1.5594, + "step": 3594 + }, + { + "epoch": 0.38, + "learning_rate": 1.5677402981855993e-05, + "loss": 1.4813, + "step": 3595 + }, + { + "epoch": 0.38, + "learning_rate": 1.567438945546982e-05, + "loss": 1.5919, + "step": 3596 + }, + { + "epoch": 0.38, + "learning_rate": 1.5671375168861255e-05, + "loss": 1.4235, + "step": 3597 + }, + { + "epoch": 0.38, + "learning_rate": 1.5668360122434135e-05, + "loss": 1.441, + "step": 3598 + }, + { + "epoch": 0.38, + "learning_rate": 1.566534431659241e-05, + "loss": 1.5847, + "step": 3599 + }, + { + "epoch": 0.38, + "learning_rate": 1.566232775174011e-05, + "loss": 1.6123, + "step": 3600 + }, + { + "epoch": 0.38, + "learning_rate": 1.5659310428281374e-05, + "loss": 1.4916, + "step": 3601 + }, + { + "epoch": 0.38, + "learning_rate": 1.5656292346620457e-05, + "loss": 1.4603, + "step": 3602 + }, + { + "epoch": 0.38, + "learning_rate": 1.56532735071617e-05, + "loss": 1.4423, + "step": 3603 + }, + { + "epoch": 0.38, + "learning_rate": 1.5650253910309547e-05, + "loss": 1.4814, + "step": 3604 + }, + { + "epoch": 0.38, + "learning_rate": 1.5647233556468552e-05, + "loss": 1.4015, + "step": 3605 + }, + { + "epoch": 0.38, + "learning_rate": 1.564421244604336e-05, + "loss": 1.3798, + "step": 3606 + }, + { + "epoch": 0.38, + "learning_rate": 1.5641190579438723e-05, + "loss": 1.4259, + "step": 3607 + }, + { + "epoch": 0.38, + "learning_rate": 1.5638167957059493e-05, + "loss": 1.3493, + "step": 3608 + }, + { + "epoch": 0.38, + "learning_rate": 1.5635144579310626e-05, + "loss": 1.3433, + "step": 3609 + }, + { + "epoch": 0.38, + "learning_rate": 1.5632120446597177e-05, + "loss": 1.4661, + "step": 3610 + }, + { + "epoch": 0.38, + "learning_rate": 1.5629095559324297e-05, + "loss": 1.4205, + "step": 3611 + }, + { + "epoch": 0.38, + "learning_rate": 1.562606991789725e-05, + "loss": 1.3976, + "step": 3612 + }, + { + "epoch": 0.38, + "learning_rate": 1.5623043522721393e-05, + "loss": 1.4261, + "step": 3613 + }, + { + "epoch": 0.38, + "learning_rate": 1.562001637420218e-05, + "loss": 1.4358, + "step": 3614 + }, + { + "epoch": 0.38, + "learning_rate": 1.5616988472745175e-05, + "loss": 1.437, + "step": 3615 + }, + { + "epoch": 0.38, + "learning_rate": 1.561395981875604e-05, + "loss": 1.3735, + "step": 3616 + }, + { + "epoch": 0.38, + "learning_rate": 1.5610930412640532e-05, + "loss": 1.4357, + "step": 3617 + }, + { + "epoch": 0.38, + "learning_rate": 1.560790025480452e-05, + "loss": 1.4003, + "step": 3618 + }, + { + "epoch": 0.38, + "learning_rate": 1.5604869345653965e-05, + "loss": 1.4127, + "step": 3619 + }, + { + "epoch": 0.38, + "learning_rate": 1.5601837685594927e-05, + "loss": 1.4666, + "step": 3620 + }, + { + "epoch": 0.38, + "learning_rate": 1.5598805275033574e-05, + "loss": 1.4106, + "step": 3621 + }, + { + "epoch": 0.38, + "learning_rate": 1.5595772114376174e-05, + "loss": 1.3857, + "step": 3622 + }, + { + "epoch": 0.38, + "learning_rate": 1.5592738204029086e-05, + "loss": 1.4704, + "step": 3623 + }, + { + "epoch": 0.38, + "learning_rate": 1.558970354439878e-05, + "loss": 1.4649, + "step": 3624 + }, + { + "epoch": 0.38, + "learning_rate": 1.5586668135891824e-05, + "loss": 1.4812, + "step": 3625 + }, + { + "epoch": 0.38, + "learning_rate": 1.5583631978914882e-05, + "loss": 1.3507, + "step": 3626 + }, + { + "epoch": 0.38, + "learning_rate": 1.5580595073874718e-05, + "loss": 1.3762, + "step": 3627 + }, + { + "epoch": 0.38, + "learning_rate": 1.557755742117821e-05, + "loss": 1.4169, + "step": 3628 + }, + { + "epoch": 0.38, + "learning_rate": 1.557451902123231e-05, + "loss": 1.4098, + "step": 3629 + }, + { + "epoch": 0.38, + "learning_rate": 1.55714798744441e-05, + "loss": 1.5526, + "step": 3630 + }, + { + "epoch": 0.38, + "learning_rate": 1.556843998122074e-05, + "loss": 1.4414, + "step": 3631 + }, + { + "epoch": 0.38, + "learning_rate": 1.5565399341969497e-05, + "loss": 1.4134, + "step": 3632 + }, + { + "epoch": 0.38, + "learning_rate": 1.556235795709774e-05, + "loss": 1.4718, + "step": 3633 + }, + { + "epoch": 0.38, + "learning_rate": 1.5559315827012937e-05, + "loss": 1.412, + "step": 3634 + }, + { + "epoch": 0.38, + "learning_rate": 1.5556272952122657e-05, + "loss": 1.4119, + "step": 3635 + }, + { + "epoch": 0.38, + "learning_rate": 1.5553229332834564e-05, + "loss": 1.3999, + "step": 3636 + }, + { + "epoch": 0.38, + "learning_rate": 1.5550184969556428e-05, + "loss": 1.4626, + "step": 3637 + }, + { + "epoch": 0.38, + "learning_rate": 1.5547139862696113e-05, + "loss": 1.3811, + "step": 3638 + }, + { + "epoch": 0.38, + "learning_rate": 1.5544094012661583e-05, + "loss": 1.4053, + "step": 3639 + }, + { + "epoch": 0.38, + "learning_rate": 1.5541047419860907e-05, + "loss": 1.4059, + "step": 3640 + }, + { + "epoch": 0.38, + "learning_rate": 1.553800008470225e-05, + "loss": 1.4717, + "step": 3641 + }, + { + "epoch": 0.38, + "learning_rate": 1.553495200759388e-05, + "loss": 1.399, + "step": 3642 + }, + { + "epoch": 0.38, + "learning_rate": 1.5531903188944154e-05, + "loss": 1.4143, + "step": 3643 + }, + { + "epoch": 0.38, + "learning_rate": 1.5528853629161536e-05, + "loss": 1.4414, + "step": 3644 + }, + { + "epoch": 0.38, + "learning_rate": 1.5525803328654592e-05, + "loss": 1.4206, + "step": 3645 + }, + { + "epoch": 0.38, + "learning_rate": 1.5522752287831982e-05, + "loss": 1.3869, + "step": 3646 + }, + { + "epoch": 0.38, + "learning_rate": 1.551970050710247e-05, + "loss": 1.5434, + "step": 3647 + }, + { + "epoch": 0.38, + "learning_rate": 1.5516647986874914e-05, + "loss": 1.4574, + "step": 3648 + }, + { + "epoch": 0.38, + "learning_rate": 1.5513594727558273e-05, + "loss": 1.4353, + "step": 3649 + }, + { + "epoch": 0.38, + "learning_rate": 1.5510540729561606e-05, + "loss": 1.4122, + "step": 3650 + }, + { + "epoch": 0.38, + "learning_rate": 1.550748599329407e-05, + "loss": 1.4077, + "step": 3651 + }, + { + "epoch": 0.38, + "learning_rate": 1.550443051916492e-05, + "loss": 1.4433, + "step": 3652 + }, + { + "epoch": 0.38, + "learning_rate": 1.5501374307583514e-05, + "loss": 1.54, + "step": 3653 + }, + { + "epoch": 0.38, + "learning_rate": 1.5498317358959302e-05, + "loss": 1.4522, + "step": 3654 + }, + { + "epoch": 0.38, + "learning_rate": 1.5495259673701842e-05, + "loss": 1.4175, + "step": 3655 + }, + { + "epoch": 0.38, + "learning_rate": 1.5492201252220777e-05, + "loss": 1.4637, + "step": 3656 + }, + { + "epoch": 0.38, + "learning_rate": 1.5489142094925863e-05, + "loss": 1.4701, + "step": 3657 + }, + { + "epoch": 0.38, + "learning_rate": 1.548608220222695e-05, + "loss": 1.4095, + "step": 3658 + }, + { + "epoch": 0.38, + "learning_rate": 1.548302157453398e-05, + "loss": 1.3903, + "step": 3659 + }, + { + "epoch": 0.38, + "learning_rate": 1.5479960212257002e-05, + "loss": 1.4062, + "step": 3660 + }, + { + "epoch": 0.38, + "learning_rate": 1.5476898115806157e-05, + "loss": 1.4706, + "step": 3661 + }, + { + "epoch": 0.38, + "learning_rate": 1.547383528559169e-05, + "loss": 1.4423, + "step": 3662 + }, + { + "epoch": 0.38, + "learning_rate": 1.547077172202394e-05, + "loss": 1.4418, + "step": 3663 + }, + { + "epoch": 0.38, + "learning_rate": 1.5467707425513347e-05, + "loss": 1.4553, + "step": 3664 + }, + { + "epoch": 0.38, + "learning_rate": 1.5464642396470443e-05, + "loss": 1.435, + "step": 3665 + }, + { + "epoch": 0.38, + "learning_rate": 1.5461576635305873e-05, + "loss": 1.4105, + "step": 3666 + }, + { + "epoch": 0.38, + "learning_rate": 1.5458510142430364e-05, + "loss": 1.4118, + "step": 3667 + }, + { + "epoch": 0.38, + "learning_rate": 1.5455442918254746e-05, + "loss": 1.4096, + "step": 3668 + }, + { + "epoch": 0.38, + "learning_rate": 1.545237496318995e-05, + "loss": 1.4248, + "step": 3669 + }, + { + "epoch": 0.38, + "learning_rate": 1.5449306277647003e-05, + "loss": 1.4591, + "step": 3670 + }, + { + "epoch": 0.38, + "learning_rate": 1.544623686203703e-05, + "loss": 1.4764, + "step": 3671 + }, + { + "epoch": 0.39, + "learning_rate": 1.5443166716771255e-05, + "loss": 1.4329, + "step": 3672 + }, + { + "epoch": 0.39, + "learning_rate": 1.5440095842260995e-05, + "loss": 1.4023, + "step": 3673 + }, + { + "epoch": 0.39, + "learning_rate": 1.5437024238917674e-05, + "loss": 1.3802, + "step": 3674 + }, + { + "epoch": 0.39, + "learning_rate": 1.5433951907152806e-05, + "loss": 1.4627, + "step": 3675 + }, + { + "epoch": 0.39, + "learning_rate": 1.5430878847378e-05, + "loss": 1.5164, + "step": 3676 + }, + { + "epoch": 0.39, + "learning_rate": 1.542780506000497e-05, + "loss": 1.3546, + "step": 3677 + }, + { + "epoch": 0.39, + "learning_rate": 1.542473054544553e-05, + "loss": 1.4415, + "step": 3678 + }, + { + "epoch": 0.39, + "learning_rate": 1.5421655304111573e-05, + "loss": 1.4093, + "step": 3679 + }, + { + "epoch": 0.39, + "learning_rate": 1.5418579336415114e-05, + "loss": 1.3943, + "step": 3680 + }, + { + "epoch": 0.39, + "learning_rate": 1.5415502642768252e-05, + "loss": 1.3659, + "step": 3681 + }, + { + "epoch": 0.39, + "learning_rate": 1.541242522358318e-05, + "loss": 1.4322, + "step": 3682 + }, + { + "epoch": 0.39, + "learning_rate": 1.5409347079272198e-05, + "loss": 1.4064, + "step": 3683 + }, + { + "epoch": 0.39, + "learning_rate": 1.5406268210247693e-05, + "loss": 1.4031, + "step": 3684 + }, + { + "epoch": 0.39, + "learning_rate": 1.540318861692216e-05, + "loss": 1.3449, + "step": 3685 + }, + { + "epoch": 0.39, + "learning_rate": 1.5400108299708182e-05, + "loss": 1.5536, + "step": 3686 + }, + { + "epoch": 0.39, + "learning_rate": 1.5397027259018442e-05, + "loss": 1.4106, + "step": 3687 + }, + { + "epoch": 0.39, + "learning_rate": 1.5393945495265722e-05, + "loss": 1.4309, + "step": 3688 + }, + { + "epoch": 0.39, + "learning_rate": 1.53908630088629e-05, + "loss": 1.3765, + "step": 3689 + }, + { + "epoch": 0.39, + "learning_rate": 1.5387779800222947e-05, + "loss": 1.3809, + "step": 3690 + }, + { + "epoch": 0.39, + "learning_rate": 1.5384695869758938e-05, + "loss": 1.4758, + "step": 3691 + }, + { + "epoch": 0.39, + "learning_rate": 1.5381611217884032e-05, + "loss": 1.4249, + "step": 3692 + }, + { + "epoch": 0.39, + "learning_rate": 1.5378525845011503e-05, + "loss": 1.4133, + "step": 3693 + }, + { + "epoch": 0.39, + "learning_rate": 1.5375439751554708e-05, + "loss": 1.418, + "step": 3694 + }, + { + "epoch": 0.39, + "learning_rate": 1.53723529379271e-05, + "loss": 1.441, + "step": 3695 + }, + { + "epoch": 0.39, + "learning_rate": 1.536926540454224e-05, + "loss": 1.3919, + "step": 3696 + }, + { + "epoch": 0.39, + "learning_rate": 1.5366177151813775e-05, + "loss": 1.3722, + "step": 3697 + }, + { + "epoch": 0.39, + "learning_rate": 1.536308818015545e-05, + "loss": 1.4727, + "step": 3698 + }, + { + "epoch": 0.39, + "learning_rate": 1.535999848998111e-05, + "loss": 1.442, + "step": 3699 + }, + { + "epoch": 0.39, + "learning_rate": 1.535690808170469e-05, + "loss": 1.3884, + "step": 3700 + }, + { + "epoch": 0.39, + "learning_rate": 1.535381695574023e-05, + "loss": 1.3226, + "step": 3701 + }, + { + "epoch": 0.39, + "learning_rate": 1.535072511250186e-05, + "loss": 1.4403, + "step": 3702 + }, + { + "epoch": 0.39, + "learning_rate": 1.5347632552403808e-05, + "loss": 1.4144, + "step": 3703 + }, + { + "epoch": 0.39, + "learning_rate": 1.5344539275860395e-05, + "loss": 1.3514, + "step": 3704 + }, + { + "epoch": 0.39, + "learning_rate": 1.5341445283286044e-05, + "loss": 1.519, + "step": 3705 + }, + { + "epoch": 0.39, + "learning_rate": 1.5338350575095268e-05, + "loss": 1.4251, + "step": 3706 + }, + { + "epoch": 0.39, + "learning_rate": 1.5335255151702685e-05, + "loss": 1.392, + "step": 3707 + }, + { + "epoch": 0.39, + "learning_rate": 1.533215901352299e-05, + "loss": 1.3838, + "step": 3708 + }, + { + "epoch": 0.39, + "learning_rate": 1.532906216097099e-05, + "loss": 1.444, + "step": 3709 + }, + { + "epoch": 0.39, + "learning_rate": 1.5325964594461594e-05, + "loss": 1.3459, + "step": 3710 + }, + { + "epoch": 0.39, + "learning_rate": 1.5322866314409783e-05, + "loss": 1.4155, + "step": 3711 + }, + { + "epoch": 0.39, + "learning_rate": 1.5319767321230657e-05, + "loss": 1.4057, + "step": 3712 + }, + { + "epoch": 0.39, + "learning_rate": 1.5316667615339392e-05, + "loss": 1.382, + "step": 3713 + }, + { + "epoch": 0.39, + "learning_rate": 1.5313567197151277e-05, + "loss": 1.3634, + "step": 3714 + }, + { + "epoch": 0.39, + "learning_rate": 1.5310466067081688e-05, + "loss": 1.3434, + "step": 3715 + }, + { + "epoch": 0.39, + "learning_rate": 1.530736422554609e-05, + "loss": 1.4553, + "step": 3716 + }, + { + "epoch": 0.39, + "learning_rate": 1.5304261672960055e-05, + "loss": 1.4193, + "step": 3717 + }, + { + "epoch": 0.39, + "learning_rate": 1.5301158409739242e-05, + "loss": 1.3955, + "step": 3718 + }, + { + "epoch": 0.39, + "learning_rate": 1.5298054436299413e-05, + "loss": 1.4592, + "step": 3719 + }, + { + "epoch": 0.39, + "learning_rate": 1.529494975305642e-05, + "loss": 1.738, + "step": 3720 + }, + { + "epoch": 0.39, + "learning_rate": 1.529184436042621e-05, + "loss": 1.438, + "step": 3721 + }, + { + "epoch": 0.39, + "learning_rate": 1.528873825882482e-05, + "loss": 1.3445, + "step": 3722 + }, + { + "epoch": 0.39, + "learning_rate": 1.5285631448668395e-05, + "loss": 1.4168, + "step": 3723 + }, + { + "epoch": 0.39, + "learning_rate": 1.528252393037317e-05, + "loss": 1.4088, + "step": 3724 + }, + { + "epoch": 0.39, + "learning_rate": 1.5279415704355468e-05, + "loss": 1.4484, + "step": 3725 + }, + { + "epoch": 0.39, + "learning_rate": 1.5276306771031708e-05, + "loss": 1.4706, + "step": 3726 + }, + { + "epoch": 0.39, + "learning_rate": 1.527319713081841e-05, + "loss": 1.3466, + "step": 3727 + }, + { + "epoch": 0.39, + "learning_rate": 1.5270086784132196e-05, + "loss": 1.427, + "step": 3728 + }, + { + "epoch": 0.39, + "learning_rate": 1.5266975731389754e-05, + "loss": 1.4596, + "step": 3729 + }, + { + "epoch": 0.39, + "learning_rate": 1.52638639730079e-05, + "loss": 1.405, + "step": 3730 + }, + { + "epoch": 0.39, + "learning_rate": 1.5260751509403518e-05, + "loss": 1.4572, + "step": 3731 + }, + { + "epoch": 0.39, + "learning_rate": 1.5257638340993608e-05, + "loss": 1.3827, + "step": 3732 + }, + { + "epoch": 0.39, + "learning_rate": 1.5254524468195251e-05, + "loss": 1.3712, + "step": 3733 + }, + { + "epoch": 0.39, + "learning_rate": 1.5251409891425626e-05, + "loss": 1.4541, + "step": 3734 + }, + { + "epoch": 0.39, + "learning_rate": 1.5248294611102006e-05, + "loss": 1.5279, + "step": 3735 + }, + { + "epoch": 0.39, + "learning_rate": 1.5245178627641759e-05, + "loss": 1.3722, + "step": 3736 + }, + { + "epoch": 0.39, + "learning_rate": 1.5242061941462348e-05, + "loss": 1.5158, + "step": 3737 + }, + { + "epoch": 0.39, + "learning_rate": 1.523894455298132e-05, + "loss": 1.4274, + "step": 3738 + }, + { + "epoch": 0.39, + "learning_rate": 1.5235826462616338e-05, + "loss": 1.4543, + "step": 3739 + }, + { + "epoch": 0.39, + "learning_rate": 1.5232707670785144e-05, + "loss": 1.5011, + "step": 3740 + }, + { + "epoch": 0.39, + "learning_rate": 1.5229588177905568e-05, + "loss": 1.24, + "step": 3741 + }, + { + "epoch": 0.39, + "learning_rate": 1.5226467984395544e-05, + "loss": 1.4253, + "step": 3742 + }, + { + "epoch": 0.39, + "learning_rate": 1.5223347090673102e-05, + "loss": 1.3736, + "step": 3743 + }, + { + "epoch": 0.39, + "learning_rate": 1.522022549715636e-05, + "loss": 1.4587, + "step": 3744 + }, + { + "epoch": 0.39, + "learning_rate": 1.521710320426353e-05, + "loss": 1.5024, + "step": 3745 + }, + { + "epoch": 0.39, + "learning_rate": 1.521398021241292e-05, + "loss": 1.427, + "step": 3746 + }, + { + "epoch": 0.39, + "learning_rate": 1.5210856522022929e-05, + "loss": 1.3387, + "step": 3747 + }, + { + "epoch": 0.39, + "learning_rate": 1.5207732133512055e-05, + "loss": 1.3819, + "step": 3748 + }, + { + "epoch": 0.39, + "learning_rate": 1.5204607047298883e-05, + "loss": 1.4571, + "step": 3749 + }, + { + "epoch": 0.39, + "learning_rate": 1.5201481263802094e-05, + "loss": 1.3592, + "step": 3750 + }, + { + "epoch": 0.39, + "learning_rate": 1.5198354783440464e-05, + "loss": 1.3912, + "step": 3751 + }, + { + "epoch": 0.39, + "learning_rate": 1.519522760663286e-05, + "loss": 1.4986, + "step": 3752 + }, + { + "epoch": 0.39, + "learning_rate": 1.5192099733798243e-05, + "loss": 1.4106, + "step": 3753 + }, + { + "epoch": 0.39, + "learning_rate": 1.5188971165355667e-05, + "loss": 1.4145, + "step": 3754 + }, + { + "epoch": 0.39, + "learning_rate": 1.5185841901724282e-05, + "loss": 1.3915, + "step": 3755 + }, + { + "epoch": 0.39, + "learning_rate": 1.5182711943323329e-05, + "loss": 1.4014, + "step": 3756 + }, + { + "epoch": 0.39, + "learning_rate": 1.5179581290572141e-05, + "loss": 1.3651, + "step": 3757 + }, + { + "epoch": 0.39, + "learning_rate": 1.5176449943890147e-05, + "loss": 1.3653, + "step": 3758 + }, + { + "epoch": 0.39, + "learning_rate": 1.5173317903696862e-05, + "loss": 1.4486, + "step": 3759 + }, + { + "epoch": 0.39, + "learning_rate": 1.5170185170411906e-05, + "loss": 1.4459, + "step": 3760 + }, + { + "epoch": 0.39, + "learning_rate": 1.5167051744454977e-05, + "loss": 1.4215, + "step": 3761 + }, + { + "epoch": 0.39, + "learning_rate": 1.5163917626245877e-05, + "loss": 1.4379, + "step": 3762 + }, + { + "epoch": 0.39, + "learning_rate": 1.51607828162045e-05, + "loss": 1.4147, + "step": 3763 + }, + { + "epoch": 0.39, + "learning_rate": 1.5157647314750827e-05, + "loss": 1.4011, + "step": 3764 + }, + { + "epoch": 0.39, + "learning_rate": 1.5154511122304936e-05, + "loss": 1.4309, + "step": 3765 + }, + { + "epoch": 0.39, + "learning_rate": 1.5151374239286993e-05, + "loss": 1.4382, + "step": 3766 + }, + { + "epoch": 0.4, + "learning_rate": 1.5148236666117266e-05, + "loss": 1.405, + "step": 3767 + }, + { + "epoch": 0.4, + "learning_rate": 1.5145098403216104e-05, + "loss": 1.4223, + "step": 3768 + }, + { + "epoch": 0.4, + "learning_rate": 1.5141959451003951e-05, + "loss": 1.4084, + "step": 3769 + }, + { + "epoch": 0.4, + "learning_rate": 1.5138819809901356e-05, + "loss": 1.4063, + "step": 3770 + }, + { + "epoch": 0.4, + "learning_rate": 1.513567948032894e-05, + "loss": 1.3299, + "step": 3771 + }, + { + "epoch": 0.4, + "learning_rate": 1.5132538462707431e-05, + "loss": 1.3901, + "step": 3772 + }, + { + "epoch": 0.4, + "learning_rate": 1.5129396757457646e-05, + "loss": 1.4249, + "step": 3773 + }, + { + "epoch": 0.4, + "learning_rate": 1.512625436500049e-05, + "loss": 1.4087, + "step": 3774 + }, + { + "epoch": 0.4, + "learning_rate": 1.5123111285756964e-05, + "loss": 1.3521, + "step": 3775 + }, + { + "epoch": 0.4, + "learning_rate": 1.5119967520148163e-05, + "loss": 1.4097, + "step": 3776 + }, + { + "epoch": 0.4, + "learning_rate": 1.5116823068595261e-05, + "loss": 1.4871, + "step": 3777 + }, + { + "epoch": 0.4, + "learning_rate": 1.5113677931519543e-05, + "loss": 1.44, + "step": 3778 + }, + { + "epoch": 0.4, + "learning_rate": 1.5110532109342377e-05, + "loss": 1.4518, + "step": 3779 + }, + { + "epoch": 0.4, + "learning_rate": 1.5107385602485214e-05, + "loss": 1.3961, + "step": 3780 + }, + { + "epoch": 0.4, + "learning_rate": 1.5104238411369614e-05, + "loss": 1.4341, + "step": 3781 + }, + { + "epoch": 0.4, + "eval_loss": 1.4642821550369263, + "eval_runtime": 77.3595, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 3781 + }, + { + "epoch": 0.4, + "learning_rate": 1.5101090536417218e-05, + "loss": 1.403, + "step": 3782 + }, + { + "epoch": 0.4, + "learning_rate": 1.5097941978049754e-05, + "loss": 1.4103, + "step": 3783 + }, + { + "epoch": 0.4, + "learning_rate": 1.5094792736689052e-05, + "loss": 1.3478, + "step": 3784 + }, + { + "epoch": 0.4, + "learning_rate": 1.5091642812757035e-05, + "loss": 1.4134, + "step": 3785 + }, + { + "epoch": 0.4, + "learning_rate": 1.5088492206675701e-05, + "loss": 1.4134, + "step": 3786 + }, + { + "epoch": 0.4, + "learning_rate": 1.5085340918867162e-05, + "loss": 1.1494, + "step": 3787 + }, + { + "epoch": 0.4, + "learning_rate": 1.5082188949753598e-05, + "loss": 1.2385, + "step": 3788 + }, + { + "epoch": 0.4, + "learning_rate": 1.5079036299757299e-05, + "loss": 1.4258, + "step": 3789 + }, + { + "epoch": 0.4, + "learning_rate": 1.5075882969300639e-05, + "loss": 1.3781, + "step": 3790 + }, + { + "epoch": 0.4, + "learning_rate": 1.507272895880608e-05, + "loss": 1.5096, + "step": 3791 + }, + { + "epoch": 0.4, + "learning_rate": 1.5069574268696179e-05, + "loss": 1.366, + "step": 3792 + }, + { + "epoch": 0.4, + "learning_rate": 1.5066418899393584e-05, + "loss": 1.3792, + "step": 3793 + }, + { + "epoch": 0.4, + "learning_rate": 1.506326285132104e-05, + "loss": 1.4987, + "step": 3794 + }, + { + "epoch": 0.4, + "learning_rate": 1.5060106124901364e-05, + "loss": 1.445, + "step": 3795 + }, + { + "epoch": 0.4, + "learning_rate": 1.5056948720557482e-05, + "loss": 1.5071, + "step": 3796 + }, + { + "epoch": 0.4, + "learning_rate": 1.505379063871241e-05, + "loss": 1.4029, + "step": 3797 + }, + { + "epoch": 0.4, + "learning_rate": 1.5050631879789244e-05, + "loss": 1.5263, + "step": 3798 + }, + { + "epoch": 0.4, + "learning_rate": 1.5047472444211175e-05, + "loss": 1.3906, + "step": 3799 + }, + { + "epoch": 0.4, + "learning_rate": 1.5044312332401494e-05, + "loss": 1.7352, + "step": 3800 + }, + { + "epoch": 0.4, + "learning_rate": 1.5041151544783565e-05, + "loss": 1.3946, + "step": 3801 + }, + { + "epoch": 0.4, + "learning_rate": 1.5037990081780862e-05, + "loss": 1.3592, + "step": 3802 + }, + { + "epoch": 0.4, + "learning_rate": 1.503482794381693e-05, + "loss": 1.3991, + "step": 3803 + }, + { + "epoch": 0.4, + "learning_rate": 1.5031665131315423e-05, + "loss": 1.4271, + "step": 3804 + }, + { + "epoch": 0.4, + "learning_rate": 1.502850164470007e-05, + "loss": 1.4305, + "step": 3805 + }, + { + "epoch": 0.4, + "learning_rate": 1.5025337484394701e-05, + "loss": 1.4116, + "step": 3806 + }, + { + "epoch": 0.4, + "learning_rate": 1.5022172650823232e-05, + "loss": 1.4242, + "step": 3807 + }, + { + "epoch": 0.4, + "learning_rate": 1.5019007144409667e-05, + "loss": 1.4427, + "step": 3808 + }, + { + "epoch": 0.4, + "learning_rate": 1.5015840965578106e-05, + "loss": 1.3705, + "step": 3809 + }, + { + "epoch": 0.4, + "learning_rate": 1.5012674114752732e-05, + "loss": 1.4498, + "step": 3810 + }, + { + "epoch": 0.4, + "learning_rate": 1.5009506592357822e-05, + "loss": 1.489, + "step": 3811 + }, + { + "epoch": 0.4, + "learning_rate": 1.5006338398817746e-05, + "loss": 1.4801, + "step": 3812 + }, + { + "epoch": 0.4, + "learning_rate": 1.5003169534556956e-05, + "loss": 1.3468, + "step": 3813 + }, + { + "epoch": 0.4, + "learning_rate": 1.5000000000000002e-05, + "loss": 1.4211, + "step": 3814 + }, + { + "epoch": 0.4, + "learning_rate": 1.4996829795571518e-05, + "loss": 1.4683, + "step": 3815 + }, + { + "epoch": 0.4, + "learning_rate": 1.499365892169623e-05, + "loss": 1.4441, + "step": 3816 + }, + { + "epoch": 0.4, + "learning_rate": 1.4990487378798958e-05, + "loss": 1.4368, + "step": 3817 + }, + { + "epoch": 0.4, + "learning_rate": 1.4987315167304602e-05, + "loss": 1.4097, + "step": 3818 + }, + { + "epoch": 0.4, + "learning_rate": 1.4984142287638155e-05, + "loss": 1.4238, + "step": 3819 + }, + { + "epoch": 0.4, + "learning_rate": 1.4980968740224708e-05, + "loss": 1.497, + "step": 3820 + }, + { + "epoch": 0.4, + "learning_rate": 1.4977794525489433e-05, + "loss": 1.3989, + "step": 3821 + }, + { + "epoch": 0.4, + "learning_rate": 1.4974619643857588e-05, + "loss": 1.4415, + "step": 3822 + }, + { + "epoch": 0.4, + "learning_rate": 1.4971444095754533e-05, + "loss": 1.3931, + "step": 3823 + }, + { + "epoch": 0.4, + "learning_rate": 1.4968267881605705e-05, + "loss": 1.3426, + "step": 3824 + }, + { + "epoch": 0.4, + "learning_rate": 1.4965091001836636e-05, + "loss": 1.644, + "step": 3825 + }, + { + "epoch": 0.4, + "learning_rate": 1.4961913456872945e-05, + "loss": 1.3903, + "step": 3826 + }, + { + "epoch": 0.4, + "learning_rate": 1.4958735247140345e-05, + "loss": 1.3764, + "step": 3827 + }, + { + "epoch": 0.4, + "learning_rate": 1.4955556373064632e-05, + "loss": 1.5484, + "step": 3828 + }, + { + "epoch": 0.4, + "learning_rate": 1.4952376835071696e-05, + "loss": 1.5696, + "step": 3829 + }, + { + "epoch": 0.4, + "learning_rate": 1.4949196633587509e-05, + "loss": 1.3844, + "step": 3830 + }, + { + "epoch": 0.4, + "learning_rate": 1.494601576903814e-05, + "loss": 1.3868, + "step": 3831 + }, + { + "epoch": 0.4, + "learning_rate": 1.4942834241849741e-05, + "loss": 1.4229, + "step": 3832 + }, + { + "epoch": 0.4, + "learning_rate": 1.4939652052448557e-05, + "loss": 1.4062, + "step": 3833 + }, + { + "epoch": 0.4, + "learning_rate": 1.4936469201260915e-05, + "loss": 1.3955, + "step": 3834 + }, + { + "epoch": 0.4, + "learning_rate": 1.4933285688713239e-05, + "loss": 1.3959, + "step": 3835 + }, + { + "epoch": 0.4, + "learning_rate": 1.4930101515232038e-05, + "loss": 1.4652, + "step": 3836 + }, + { + "epoch": 0.4, + "learning_rate": 1.4926916681243913e-05, + "loss": 1.5253, + "step": 3837 + }, + { + "epoch": 0.4, + "learning_rate": 1.4923731187175539e-05, + "loss": 1.4694, + "step": 3838 + }, + { + "epoch": 0.4, + "learning_rate": 1.4920545033453702e-05, + "loss": 1.3859, + "step": 3839 + }, + { + "epoch": 0.4, + "learning_rate": 1.4917358220505259e-05, + "loss": 1.4157, + "step": 3840 + }, + { + "epoch": 0.4, + "learning_rate": 1.4914170748757159e-05, + "loss": 1.4491, + "step": 3841 + }, + { + "epoch": 0.4, + "learning_rate": 1.4910982618636445e-05, + "loss": 1.4464, + "step": 3842 + }, + { + "epoch": 0.4, + "learning_rate": 1.4907793830570246e-05, + "loss": 1.3771, + "step": 3843 + }, + { + "epoch": 0.4, + "learning_rate": 1.4904604384985775e-05, + "loss": 1.3673, + "step": 3844 + }, + { + "epoch": 0.4, + "learning_rate": 1.4901414282310334e-05, + "loss": 1.4429, + "step": 3845 + }, + { + "epoch": 0.4, + "learning_rate": 1.4898223522971318e-05, + "loss": 1.4905, + "step": 3846 + }, + { + "epoch": 0.4, + "learning_rate": 1.4895032107396205e-05, + "loss": 1.4039, + "step": 3847 + }, + { + "epoch": 0.4, + "learning_rate": 1.4891840036012566e-05, + "loss": 1.4082, + "step": 3848 + }, + { + "epoch": 0.4, + "learning_rate": 1.4888647309248052e-05, + "loss": 1.3643, + "step": 3849 + }, + { + "epoch": 0.4, + "learning_rate": 1.4885453927530408e-05, + "loss": 1.3116, + "step": 3850 + }, + { + "epoch": 0.4, + "learning_rate": 1.4882259891287467e-05, + "loss": 1.4278, + "step": 3851 + }, + { + "epoch": 0.4, + "learning_rate": 1.4879065200947148e-05, + "loss": 1.3712, + "step": 3852 + }, + { + "epoch": 0.4, + "learning_rate": 1.4875869856937449e-05, + "loss": 1.387, + "step": 3853 + }, + { + "epoch": 0.4, + "learning_rate": 1.4872673859686475e-05, + "loss": 1.5053, + "step": 3854 + }, + { + "epoch": 0.4, + "learning_rate": 1.4869477209622404e-05, + "loss": 1.4427, + "step": 3855 + }, + { + "epoch": 0.4, + "learning_rate": 1.4866279907173502e-05, + "loss": 1.3404, + "step": 3856 + }, + { + "epoch": 0.4, + "learning_rate": 1.4863081952768126e-05, + "loss": 1.3126, + "step": 3857 + }, + { + "epoch": 0.4, + "learning_rate": 1.4859883346834725e-05, + "loss": 1.4588, + "step": 3858 + }, + { + "epoch": 0.4, + "learning_rate": 1.4856684089801822e-05, + "loss": 1.408, + "step": 3859 + }, + { + "epoch": 0.4, + "learning_rate": 1.4853484182098044e-05, + "loss": 1.4356, + "step": 3860 + }, + { + "epoch": 0.4, + "learning_rate": 1.4850283624152088e-05, + "loss": 1.3768, + "step": 3861 + }, + { + "epoch": 0.4, + "learning_rate": 1.4847082416392753e-05, + "loss": 1.4563, + "step": 3862 + }, + { + "epoch": 0.41, + "learning_rate": 1.4843880559248915e-05, + "loss": 1.3648, + "step": 3863 + }, + { + "epoch": 0.41, + "learning_rate": 1.4840678053149542e-05, + "loss": 1.4146, + "step": 3864 + }, + { + "epoch": 0.41, + "learning_rate": 1.4837474898523686e-05, + "loss": 1.4423, + "step": 3865 + }, + { + "epoch": 0.41, + "learning_rate": 1.4834271095800487e-05, + "loss": 1.3351, + "step": 3866 + }, + { + "epoch": 0.41, + "learning_rate": 1.4831066645409178e-05, + "loss": 1.4534, + "step": 3867 + }, + { + "epoch": 0.41, + "learning_rate": 1.4827861547779066e-05, + "loss": 1.4763, + "step": 3868 + }, + { + "epoch": 0.41, + "learning_rate": 1.4824655803339553e-05, + "loss": 1.4019, + "step": 3869 + }, + { + "epoch": 0.41, + "learning_rate": 1.4821449412520132e-05, + "loss": 1.4223, + "step": 3870 + }, + { + "epoch": 0.41, + "learning_rate": 1.4818242375750371e-05, + "loss": 1.4065, + "step": 3871 + }, + { + "epoch": 0.41, + "learning_rate": 1.481503469345993e-05, + "loss": 1.587, + "step": 3872 + }, + { + "epoch": 0.41, + "learning_rate": 1.4811826366078562e-05, + "loss": 1.3746, + "step": 3873 + }, + { + "epoch": 0.41, + "learning_rate": 1.4808617394036096e-05, + "loss": 1.3425, + "step": 3874 + }, + { + "epoch": 0.41, + "learning_rate": 1.480540777776245e-05, + "loss": 0.6637, + "step": 3875 + }, + { + "epoch": 0.41, + "learning_rate": 1.4802197517687634e-05, + "loss": 1.3366, + "step": 3876 + }, + { + "epoch": 0.41, + "learning_rate": 1.479898661424174e-05, + "loss": 1.4033, + "step": 3877 + }, + { + "epoch": 0.41, + "learning_rate": 1.4795775067854947e-05, + "loss": 1.4005, + "step": 3878 + }, + { + "epoch": 0.41, + "learning_rate": 1.4792562878957516e-05, + "loss": 1.3651, + "step": 3879 + }, + { + "epoch": 0.41, + "learning_rate": 1.47893500479798e-05, + "loss": 1.4185, + "step": 3880 + }, + { + "epoch": 0.41, + "learning_rate": 1.4786136575352236e-05, + "loss": 1.4394, + "step": 3881 + }, + { + "epoch": 0.41, + "learning_rate": 1.478292246150535e-05, + "loss": 1.7243, + "step": 3882 + }, + { + "epoch": 0.41, + "learning_rate": 1.4779707706869744e-05, + "loss": 1.3574, + "step": 3883 + }, + { + "epoch": 0.41, + "learning_rate": 1.4776492311876116e-05, + "loss": 1.4031, + "step": 3884 + }, + { + "epoch": 0.41, + "learning_rate": 1.4773276276955248e-05, + "loss": 1.4351, + "step": 3885 + }, + { + "epoch": 0.41, + "learning_rate": 1.4770059602538002e-05, + "loss": 1.3922, + "step": 3886 + }, + { + "epoch": 0.41, + "learning_rate": 1.4766842289055333e-05, + "loss": 1.3374, + "step": 3887 + }, + { + "epoch": 0.41, + "learning_rate": 1.4763624336938278e-05, + "loss": 1.428, + "step": 3888 + }, + { + "epoch": 0.41, + "learning_rate": 1.476040574661796e-05, + "loss": 1.6087, + "step": 3889 + }, + { + "epoch": 0.41, + "learning_rate": 1.4757186518525586e-05, + "loss": 1.4054, + "step": 3890 + }, + { + "epoch": 0.41, + "learning_rate": 1.4753966653092447e-05, + "loss": 1.2595, + "step": 3891 + }, + { + "epoch": 0.41, + "learning_rate": 1.475074615074993e-05, + "loss": 1.4052, + "step": 3892 + }, + { + "epoch": 0.41, + "learning_rate": 1.4747525011929492e-05, + "loss": 1.4296, + "step": 3893 + }, + { + "epoch": 0.41, + "learning_rate": 1.4744303237062689e-05, + "loss": 1.3718, + "step": 3894 + }, + { + "epoch": 0.41, + "learning_rate": 1.4741080826581151e-05, + "loss": 1.4498, + "step": 3895 + }, + { + "epoch": 0.41, + "learning_rate": 1.4737857780916602e-05, + "loss": 1.4029, + "step": 3896 + }, + { + "epoch": 0.41, + "learning_rate": 1.4734634100500846e-05, + "loss": 1.4136, + "step": 3897 + }, + { + "epoch": 0.41, + "learning_rate": 1.4731409785765774e-05, + "loss": 1.348, + "step": 3898 + }, + { + "epoch": 0.41, + "learning_rate": 1.4728184837143355e-05, + "loss": 1.3407, + "step": 3899 + }, + { + "epoch": 0.41, + "learning_rate": 1.472495925506566e-05, + "loss": 1.3737, + "step": 3900 + }, + { + "epoch": 0.41, + "learning_rate": 1.4721733039964826e-05, + "loss": 2.2305, + "step": 3901 + }, + { + "epoch": 0.41, + "learning_rate": 1.4718506192273087e-05, + "loss": 1.4506, + "step": 3902 + }, + { + "epoch": 0.41, + "learning_rate": 1.4715278712422754e-05, + "loss": 1.3657, + "step": 3903 + }, + { + "epoch": 0.41, + "learning_rate": 1.471205060084623e-05, + "loss": 1.4644, + "step": 3904 + }, + { + "epoch": 0.41, + "learning_rate": 1.4708821857976001e-05, + "loss": 1.4823, + "step": 3905 + }, + { + "epoch": 0.41, + "learning_rate": 1.4705592484244628e-05, + "loss": 1.3392, + "step": 3906 + }, + { + "epoch": 0.41, + "learning_rate": 1.4702362480084769e-05, + "loss": 1.3302, + "step": 3907 + }, + { + "epoch": 0.41, + "learning_rate": 1.4699131845929163e-05, + "loss": 1.8952, + "step": 3908 + }, + { + "epoch": 0.41, + "learning_rate": 1.469590058221063e-05, + "loss": 1.4982, + "step": 3909 + }, + { + "epoch": 0.41, + "learning_rate": 1.4692668689362074e-05, + "loss": 1.407, + "step": 3910 + }, + { + "epoch": 0.41, + "learning_rate": 1.4689436167816489e-05, + "loss": 1.3911, + "step": 3911 + }, + { + "epoch": 0.41, + "learning_rate": 1.4686203018006948e-05, + "loss": 1.3421, + "step": 3912 + }, + { + "epoch": 0.41, + "learning_rate": 1.4682969240366612e-05, + "loss": 1.4627, + "step": 3913 + }, + { + "epoch": 0.41, + "learning_rate": 1.4679734835328718e-05, + "loss": 1.394, + "step": 3914 + }, + { + "epoch": 0.41, + "learning_rate": 1.4676499803326603e-05, + "loss": 1.4484, + "step": 3915 + }, + { + "epoch": 0.41, + "learning_rate": 1.4673264144793673e-05, + "loss": 1.4665, + "step": 3916 + }, + { + "epoch": 0.41, + "learning_rate": 1.4670027860163422e-05, + "loss": 1.3191, + "step": 3917 + }, + { + "epoch": 0.41, + "learning_rate": 1.466679094986943e-05, + "loss": 1.4748, + "step": 3918 + }, + { + "epoch": 0.41, + "learning_rate": 1.4663553414345361e-05, + "loss": 1.2467, + "step": 3919 + }, + { + "epoch": 0.41, + "learning_rate": 1.466031525402496e-05, + "loss": 1.4279, + "step": 3920 + }, + { + "epoch": 0.41, + "learning_rate": 1.4657076469342059e-05, + "loss": 1.3822, + "step": 3921 + }, + { + "epoch": 0.41, + "learning_rate": 1.4653837060730566e-05, + "loss": 1.3659, + "step": 3922 + }, + { + "epoch": 0.41, + "learning_rate": 1.465059702862449e-05, + "loss": 1.3663, + "step": 3923 + }, + { + "epoch": 0.41, + "learning_rate": 1.4647356373457902e-05, + "loss": 1.4371, + "step": 3924 + }, + { + "epoch": 0.41, + "learning_rate": 1.4644115095664972e-05, + "loss": 1.3473, + "step": 3925 + }, + { + "epoch": 0.41, + "learning_rate": 1.4640873195679944e-05, + "loss": 1.4797, + "step": 3926 + }, + { + "epoch": 0.41, + "learning_rate": 1.463763067393715e-05, + "loss": 1.3973, + "step": 3927 + }, + { + "epoch": 0.41, + "learning_rate": 1.4634387530871008e-05, + "loss": 1.3899, + "step": 3928 + }, + { + "epoch": 0.41, + "learning_rate": 1.4631143766916015e-05, + "loss": 1.3828, + "step": 3929 + }, + { + "epoch": 0.41, + "learning_rate": 1.4627899382506745e-05, + "loss": 1.4569, + "step": 3930 + }, + { + "epoch": 0.41, + "learning_rate": 1.4624654378077872e-05, + "loss": 1.4011, + "step": 3931 + }, + { + "epoch": 0.41, + "learning_rate": 1.462140875406414e-05, + "loss": 1.3859, + "step": 3932 + }, + { + "epoch": 0.41, + "learning_rate": 1.4618162510900376e-05, + "loss": 1.4518, + "step": 3933 + }, + { + "epoch": 0.41, + "learning_rate": 1.4614915649021493e-05, + "loss": 1.4399, + "step": 3934 + }, + { + "epoch": 0.41, + "learning_rate": 1.4611668168862495e-05, + "loss": 1.4034, + "step": 3935 + }, + { + "epoch": 0.41, + "learning_rate": 1.4608420070858452e-05, + "loss": 1.3919, + "step": 3936 + }, + { + "epoch": 0.41, + "learning_rate": 1.4605171355444528e-05, + "loss": 1.391, + "step": 3937 + }, + { + "epoch": 0.41, + "learning_rate": 1.460192202305597e-05, + "loss": 1.3717, + "step": 3938 + }, + { + "epoch": 0.41, + "learning_rate": 1.4598672074128103e-05, + "loss": 1.4351, + "step": 3939 + }, + { + "epoch": 0.41, + "learning_rate": 1.4595421509096339e-05, + "loss": 1.4202, + "step": 3940 + }, + { + "epoch": 0.41, + "learning_rate": 1.4592170328396165e-05, + "loss": 1.3559, + "step": 3941 + }, + { + "epoch": 0.41, + "learning_rate": 1.458891853246316e-05, + "loss": 1.5878, + "step": 3942 + }, + { + "epoch": 0.41, + "learning_rate": 1.4585666121732982e-05, + "loss": 1.3818, + "step": 3943 + }, + { + "epoch": 0.41, + "learning_rate": 1.4582413096641369e-05, + "loss": 1.4009, + "step": 3944 + }, + { + "epoch": 0.41, + "learning_rate": 1.457915945762414e-05, + "loss": 1.3937, + "step": 3945 + }, + { + "epoch": 0.41, + "learning_rate": 1.4575905205117203e-05, + "loss": 1.381, + "step": 3946 + }, + { + "epoch": 0.41, + "learning_rate": 1.457265033955654e-05, + "loss": 1.3844, + "step": 3947 + }, + { + "epoch": 0.41, + "learning_rate": 1.4569394861378226e-05, + "loss": 1.4059, + "step": 3948 + }, + { + "epoch": 0.41, + "learning_rate": 1.4566138771018403e-05, + "loss": 1.3698, + "step": 3949 + }, + { + "epoch": 0.41, + "learning_rate": 1.4562882068913311e-05, + "loss": 1.4253, + "step": 3950 + }, + { + "epoch": 0.41, + "learning_rate": 1.455962475549926e-05, + "loss": 1.4284, + "step": 3951 + }, + { + "epoch": 0.41, + "learning_rate": 1.4556366831212647e-05, + "loss": 1.4279, + "step": 3952 + }, + { + "epoch": 0.41, + "learning_rate": 1.4553108296489951e-05, + "loss": 1.3072, + "step": 3953 + }, + { + "epoch": 0.41, + "learning_rate": 1.4549849151767731e-05, + "loss": 1.4175, + "step": 3954 + }, + { + "epoch": 0.41, + "learning_rate": 1.4546589397482632e-05, + "loss": 1.5042, + "step": 3955 + }, + { + "epoch": 0.41, + "learning_rate": 1.4543329034071371e-05, + "loss": 1.4363, + "step": 3956 + }, + { + "epoch": 0.41, + "learning_rate": 1.454006806197076e-05, + "loss": 1.4111, + "step": 3957 + }, + { + "epoch": 0.42, + "learning_rate": 1.453680648161768e-05, + "loss": 1.3817, + "step": 3958 + }, + { + "epoch": 0.42, + "learning_rate": 1.45335442934491e-05, + "loss": 1.4689, + "step": 3959 + }, + { + "epoch": 0.42, + "learning_rate": 1.4530281497902072e-05, + "loss": 1.4164, + "step": 3960 + }, + { + "epoch": 0.42, + "learning_rate": 1.4527018095413726e-05, + "loss": 1.3943, + "step": 3961 + }, + { + "epoch": 0.42, + "learning_rate": 1.4523754086421271e-05, + "loss": 1.3851, + "step": 3962 + }, + { + "epoch": 0.42, + "learning_rate": 1.4520489471362003e-05, + "loss": 1.3907, + "step": 3963 + }, + { + "epoch": 0.42, + "learning_rate": 1.4517224250673297e-05, + "loss": 1.2877, + "step": 3964 + }, + { + "epoch": 0.42, + "learning_rate": 1.4513958424792605e-05, + "loss": 1.4696, + "step": 3965 + }, + { + "epoch": 0.42, + "learning_rate": 1.4510691994157471e-05, + "loss": 1.3785, + "step": 3966 + }, + { + "epoch": 0.42, + "learning_rate": 1.4507424959205505e-05, + "loss": 1.3652, + "step": 3967 + }, + { + "epoch": 0.42, + "learning_rate": 1.4504157320374408e-05, + "loss": 1.4198, + "step": 3968 + }, + { + "epoch": 0.42, + "learning_rate": 1.4500889078101962e-05, + "loss": 1.3476, + "step": 3969 + }, + { + "epoch": 0.42, + "learning_rate": 1.4497620232826028e-05, + "loss": 1.4356, + "step": 3970 + }, + { + "epoch": 0.42, + "learning_rate": 1.4494350784984543e-05, + "loss": 1.4993, + "step": 3971 + }, + { + "epoch": 0.42, + "learning_rate": 1.4491080735015533e-05, + "loss": 1.4022, + "step": 3972 + }, + { + "epoch": 0.42, + "learning_rate": 1.44878100833571e-05, + "loss": 1.4074, + "step": 3973 + }, + { + "epoch": 0.42, + "learning_rate": 1.4484538830447423e-05, + "loss": 1.412, + "step": 3974 + }, + { + "epoch": 0.42, + "learning_rate": 1.4481266976724772e-05, + "loss": 1.3872, + "step": 3975 + }, + { + "epoch": 0.42, + "learning_rate": 1.4477994522627485e-05, + "loss": 1.4575, + "step": 3976 + }, + { + "epoch": 0.42, + "learning_rate": 1.4474721468593995e-05, + "loss": 1.3768, + "step": 3977 + }, + { + "epoch": 0.42, + "learning_rate": 1.44714478150628e-05, + "loss": 1.4173, + "step": 3978 + }, + { + "epoch": 0.42, + "learning_rate": 1.4468173562472489e-05, + "loss": 1.3896, + "step": 3979 + }, + { + "epoch": 0.42, + "learning_rate": 1.4464898711261725e-05, + "loss": 1.4535, + "step": 3980 + }, + { + "epoch": 0.42, + "eval_loss": 1.4580057859420776, + "eval_runtime": 77.4537, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 3980 + }, + { + "epoch": 0.42, + "learning_rate": 1.4461623261869258e-05, + "loss": 1.4046, + "step": 3981 + }, + { + "epoch": 0.42, + "learning_rate": 1.445834721473391e-05, + "loss": 1.37, + "step": 3982 + }, + { + "epoch": 0.42, + "learning_rate": 1.4455070570294588e-05, + "loss": 1.4566, + "step": 3983 + }, + { + "epoch": 0.42, + "learning_rate": 1.445179332899028e-05, + "loss": 1.4513, + "step": 3984 + }, + { + "epoch": 0.42, + "learning_rate": 1.4448515491260051e-05, + "loss": 1.3893, + "step": 3985 + }, + { + "epoch": 0.42, + "learning_rate": 1.4445237057543047e-05, + "loss": 1.3955, + "step": 3986 + }, + { + "epoch": 0.42, + "learning_rate": 1.4441958028278493e-05, + "loss": 1.4861, + "step": 3987 + }, + { + "epoch": 0.42, + "learning_rate": 1.4438678403905697e-05, + "loss": 1.4601, + "step": 3988 + }, + { + "epoch": 0.42, + "learning_rate": 1.4435398184864043e-05, + "loss": 1.398, + "step": 3989 + }, + { + "epoch": 0.42, + "learning_rate": 1.4432117371592995e-05, + "loss": 1.4392, + "step": 3990 + }, + { + "epoch": 0.42, + "learning_rate": 1.4428835964532098e-05, + "loss": 1.3772, + "step": 3991 + }, + { + "epoch": 0.42, + "learning_rate": 1.4425553964120979e-05, + "loss": 1.4241, + "step": 3992 + }, + { + "epoch": 0.42, + "learning_rate": 1.4422271370799338e-05, + "loss": 1.3237, + "step": 3993 + }, + { + "epoch": 0.42, + "learning_rate": 1.4418988185006964e-05, + "loss": 1.3813, + "step": 3994 + }, + { + "epoch": 0.42, + "learning_rate": 1.4415704407183709e-05, + "loss": 1.6139, + "step": 3995 + }, + { + "epoch": 0.42, + "learning_rate": 1.4412420037769525e-05, + "loss": 1.4431, + "step": 3996 + }, + { + "epoch": 0.42, + "learning_rate": 1.440913507720443e-05, + "loss": 1.3862, + "step": 3997 + }, + { + "epoch": 0.42, + "learning_rate": 1.4405849525928523e-05, + "loss": 1.3895, + "step": 3998 + }, + { + "epoch": 0.42, + "learning_rate": 1.4402563384381981e-05, + "loss": 1.4068, + "step": 3999 + }, + { + "epoch": 0.42, + "learning_rate": 1.4399276653005072e-05, + "loss": 1.4501, + "step": 4000 + }, + { + "epoch": 0.42, + "learning_rate": 1.4395989332238124e-05, + "loss": 1.3165, + "step": 4001 + }, + { + "epoch": 0.42, + "learning_rate": 1.4392701422521555e-05, + "loss": 1.3783, + "step": 4002 + }, + { + "epoch": 0.42, + "learning_rate": 1.4389412924295865e-05, + "loss": 1.343, + "step": 4003 + }, + { + "epoch": 0.42, + "learning_rate": 1.4386123838001625e-05, + "loss": 1.3456, + "step": 4004 + }, + { + "epoch": 0.42, + "learning_rate": 1.4382834164079486e-05, + "loss": 1.3689, + "step": 4005 + }, + { + "epoch": 0.42, + "learning_rate": 1.4379543902970183e-05, + "loss": 1.3789, + "step": 4006 + }, + { + "epoch": 0.42, + "learning_rate": 1.4376253055114528e-05, + "loss": 1.4912, + "step": 4007 + }, + { + "epoch": 0.42, + "learning_rate": 1.4372961620953407e-05, + "loss": 1.3692, + "step": 4008 + }, + { + "epoch": 0.42, + "learning_rate": 1.436966960092779e-05, + "loss": 1.4901, + "step": 4009 + }, + { + "epoch": 0.42, + "learning_rate": 1.4366376995478717e-05, + "loss": 1.4431, + "step": 4010 + }, + { + "epoch": 0.42, + "learning_rate": 1.436308380504732e-05, + "loss": 1.4626, + "step": 4011 + }, + { + "epoch": 0.42, + "learning_rate": 1.4359790030074798e-05, + "loss": 1.4241, + "step": 4012 + }, + { + "epoch": 0.42, + "learning_rate": 1.4356495671002435e-05, + "loss": 1.3834, + "step": 4013 + }, + { + "epoch": 0.42, + "learning_rate": 1.4353200728271586e-05, + "loss": 1.3626, + "step": 4014 + }, + { + "epoch": 0.42, + "learning_rate": 1.4349905202323692e-05, + "loss": 1.3557, + "step": 4015 + }, + { + "epoch": 0.42, + "learning_rate": 1.434660909360027e-05, + "loss": 1.4077, + "step": 4016 + }, + { + "epoch": 0.42, + "learning_rate": 1.4343312402542911e-05, + "loss": 1.4337, + "step": 4017 + }, + { + "epoch": 0.42, + "learning_rate": 1.4340015129593286e-05, + "loss": 1.419, + "step": 4018 + }, + { + "epoch": 0.42, + "learning_rate": 1.4336717275193148e-05, + "loss": 1.3768, + "step": 4019 + }, + { + "epoch": 0.42, + "learning_rate": 1.4333418839784326e-05, + "loss": 1.383, + "step": 4020 + }, + { + "epoch": 0.42, + "learning_rate": 1.4330119823808719e-05, + "loss": 1.3951, + "step": 4021 + }, + { + "epoch": 0.42, + "learning_rate": 1.4326820227708316e-05, + "loss": 1.3985, + "step": 4022 + }, + { + "epoch": 0.42, + "learning_rate": 1.4323520051925177e-05, + "loss": 1.356, + "step": 4023 + }, + { + "epoch": 0.42, + "learning_rate": 1.4320219296901439e-05, + "loss": 1.5017, + "step": 4024 + }, + { + "epoch": 0.42, + "learning_rate": 1.4316917963079322e-05, + "loss": 1.3594, + "step": 4025 + }, + { + "epoch": 0.42, + "learning_rate": 1.4313616050901114e-05, + "loss": 1.6028, + "step": 4026 + }, + { + "epoch": 0.42, + "learning_rate": 1.4310313560809193e-05, + "loss": 1.4132, + "step": 4027 + }, + { + "epoch": 0.42, + "learning_rate": 1.4307010493246006e-05, + "loss": 1.2969, + "step": 4028 + }, + { + "epoch": 0.42, + "learning_rate": 1.4303706848654073e-05, + "loss": 1.5224, + "step": 4029 + }, + { + "epoch": 0.42, + "learning_rate": 1.4300402627476007e-05, + "loss": 1.3386, + "step": 4030 + }, + { + "epoch": 0.42, + "learning_rate": 1.429709783015448e-05, + "loss": 1.3554, + "step": 4031 + }, + { + "epoch": 0.42, + "learning_rate": 1.4293792457132259e-05, + "loss": 1.3386, + "step": 4032 + }, + { + "epoch": 0.42, + "learning_rate": 1.429048650885217e-05, + "loss": 1.4613, + "step": 4033 + }, + { + "epoch": 0.42, + "learning_rate": 1.4287179985757132e-05, + "loss": 1.3632, + "step": 4034 + }, + { + "epoch": 0.42, + "learning_rate": 1.428387288829013e-05, + "loss": 1.3835, + "step": 4035 + }, + { + "epoch": 0.42, + "learning_rate": 1.4280565216894234e-05, + "loss": 1.3711, + "step": 4036 + }, + { + "epoch": 0.42, + "learning_rate": 1.4277256972012582e-05, + "loss": 1.3385, + "step": 4037 + }, + { + "epoch": 0.42, + "learning_rate": 1.4273948154088395e-05, + "loss": 1.4607, + "step": 4038 + }, + { + "epoch": 0.42, + "learning_rate": 1.4270638763564973e-05, + "loss": 1.4042, + "step": 4039 + }, + { + "epoch": 0.42, + "learning_rate": 1.4267328800885687e-05, + "loss": 1.4006, + "step": 4040 + }, + { + "epoch": 0.42, + "learning_rate": 1.4264018266493987e-05, + "loss": 1.386, + "step": 4041 + }, + { + "epoch": 0.42, + "learning_rate": 1.4260707160833401e-05, + "loss": 1.3487, + "step": 4042 + }, + { + "epoch": 0.42, + "learning_rate": 1.4257395484347529e-05, + "loss": 1.4199, + "step": 4043 + }, + { + "epoch": 0.42, + "learning_rate": 1.4254083237480054e-05, + "loss": 1.3236, + "step": 4044 + }, + { + "epoch": 0.42, + "learning_rate": 1.4250770420674726e-05, + "loss": 1.4056, + "step": 4045 + }, + { + "epoch": 0.42, + "learning_rate": 1.4247457034375387e-05, + "loss": 1.4391, + "step": 4046 + }, + { + "epoch": 0.42, + "learning_rate": 1.4244143079025938e-05, + "loss": 1.3935, + "step": 4047 + }, + { + "epoch": 0.42, + "learning_rate": 1.4240828555070368e-05, + "loss": 1.3623, + "step": 4048 + }, + { + "epoch": 0.42, + "learning_rate": 1.4237513462952733e-05, + "loss": 1.3254, + "step": 4049 + }, + { + "epoch": 0.42, + "learning_rate": 1.4234197803117174e-05, + "loss": 1.4217, + "step": 4050 + }, + { + "epoch": 0.42, + "learning_rate": 1.4230881576007904e-05, + "loss": 1.435, + "step": 4051 + }, + { + "epoch": 0.42, + "learning_rate": 1.422756478206921e-05, + "loss": 1.3687, + "step": 4052 + }, + { + "epoch": 0.43, + "learning_rate": 1.4224247421745464e-05, + "loss": 1.3965, + "step": 4053 + }, + { + "epoch": 0.43, + "learning_rate": 1.4220929495481097e-05, + "loss": 1.4159, + "step": 4054 + }, + { + "epoch": 0.43, + "learning_rate": 1.4217611003720632e-05, + "loss": 1.3632, + "step": 4055 + }, + { + "epoch": 0.43, + "learning_rate": 1.4214291946908661e-05, + "loss": 1.403, + "step": 4056 + }, + { + "epoch": 0.43, + "learning_rate": 1.4210972325489854e-05, + "loss": 1.4093, + "step": 4057 + }, + { + "epoch": 0.43, + "learning_rate": 1.4207652139908952e-05, + "loss": 1.4551, + "step": 4058 + }, + { + "epoch": 0.43, + "learning_rate": 1.4204331390610775e-05, + "loss": 1.4162, + "step": 4059 + }, + { + "epoch": 0.43, + "learning_rate": 1.4201010078040216e-05, + "loss": 1.4492, + "step": 4060 + }, + { + "epoch": 0.43, + "learning_rate": 1.419768820264225e-05, + "loss": 1.4449, + "step": 4061 + }, + { + "epoch": 0.43, + "learning_rate": 1.4194365764861922e-05, + "loss": 1.3382, + "step": 4062 + }, + { + "epoch": 0.43, + "learning_rate": 1.419104276514435e-05, + "loss": 1.3899, + "step": 4063 + }, + { + "epoch": 0.43, + "learning_rate": 1.4187719203934734e-05, + "loss": 1.3513, + "step": 4064 + }, + { + "epoch": 0.43, + "learning_rate": 1.4184395081678344e-05, + "loss": 1.3954, + "step": 4065 + }, + { + "epoch": 0.43, + "learning_rate": 1.4181070398820528e-05, + "loss": 1.442, + "step": 4066 + }, + { + "epoch": 0.43, + "learning_rate": 1.4177745155806708e-05, + "loss": 1.3907, + "step": 4067 + }, + { + "epoch": 0.43, + "learning_rate": 1.417441935308238e-05, + "loss": 1.3757, + "step": 4068 + }, + { + "epoch": 0.43, + "learning_rate": 1.4171092991093118e-05, + "loss": 1.3507, + "step": 4069 + }, + { + "epoch": 0.43, + "learning_rate": 1.4167766070284568e-05, + "loss": 1.4136, + "step": 4070 + }, + { + "epoch": 0.43, + "learning_rate": 1.4164438591102452e-05, + "loss": 1.3835, + "step": 4071 + }, + { + "epoch": 0.43, + "learning_rate": 1.4161110553992565e-05, + "loss": 1.4981, + "step": 4072 + }, + { + "epoch": 0.43, + "learning_rate": 1.415778195940078e-05, + "loss": 1.4387, + "step": 4073 + }, + { + "epoch": 0.43, + "learning_rate": 1.4154452807773047e-05, + "loss": 1.333, + "step": 4074 + }, + { + "epoch": 0.43, + "learning_rate": 1.4151123099555377e-05, + "loss": 1.3558, + "step": 4075 + }, + { + "epoch": 0.43, + "learning_rate": 1.4147792835193875e-05, + "loss": 1.4655, + "step": 4076 + }, + { + "epoch": 0.43, + "learning_rate": 1.4144462015134708e-05, + "loss": 1.4402, + "step": 4077 + }, + { + "epoch": 0.43, + "learning_rate": 1.4141130639824119e-05, + "loss": 1.4227, + "step": 4078 + }, + { + "epoch": 0.43, + "learning_rate": 1.4137798709708423e-05, + "loss": 1.4039, + "step": 4079 + }, + { + "epoch": 0.43, + "learning_rate": 1.4134466225234023e-05, + "loss": 1.3593, + "step": 4080 + }, + { + "epoch": 0.43, + "learning_rate": 1.4131133186847377e-05, + "loss": 1.372, + "step": 4081 + }, + { + "epoch": 0.43, + "learning_rate": 1.412779959499503e-05, + "loss": 1.4487, + "step": 4082 + }, + { + "epoch": 0.43, + "learning_rate": 1.4124465450123599e-05, + "loss": 1.3972, + "step": 4083 + }, + { + "epoch": 0.43, + "learning_rate": 1.4121130752679772e-05, + "loss": 1.3768, + "step": 4084 + }, + { + "epoch": 0.43, + "learning_rate": 1.4117795503110313e-05, + "loss": 1.3827, + "step": 4085 + }, + { + "epoch": 0.43, + "learning_rate": 1.4114459701862062e-05, + "loss": 1.3922, + "step": 4086 + }, + { + "epoch": 0.43, + "learning_rate": 1.4111123349381925e-05, + "loss": 1.3736, + "step": 4087 + }, + { + "epoch": 0.43, + "learning_rate": 1.4107786446116894e-05, + "loss": 1.4338, + "step": 4088 + }, + { + "epoch": 0.43, + "learning_rate": 1.4104448992514023e-05, + "loss": 1.347, + "step": 4089 + }, + { + "epoch": 0.43, + "learning_rate": 1.410111098902045e-05, + "loss": 1.3915, + "step": 4090 + }, + { + "epoch": 0.43, + "learning_rate": 1.4097772436083377e-05, + "loss": 1.3656, + "step": 4091 + }, + { + "epoch": 0.43, + "learning_rate": 1.4094433334150087e-05, + "loss": 1.3461, + "step": 4092 + }, + { + "epoch": 0.43, + "learning_rate": 1.4091093683667934e-05, + "loss": 1.7345, + "step": 4093 + }, + { + "epoch": 0.43, + "learning_rate": 1.4087753485084343e-05, + "loss": 1.6204, + "step": 4094 + }, + { + "epoch": 0.43, + "learning_rate": 1.4084412738846816e-05, + "loss": 1.4074, + "step": 4095 + }, + { + "epoch": 0.43, + "learning_rate": 1.408107144540293e-05, + "loss": 1.3776, + "step": 4096 + }, + { + "epoch": 0.43, + "learning_rate": 1.407772960520033e-05, + "loss": 1.4079, + "step": 4097 + }, + { + "epoch": 0.43, + "learning_rate": 1.4074387218686734e-05, + "loss": 1.4254, + "step": 4098 + }, + { + "epoch": 0.43, + "learning_rate": 1.407104428630994e-05, + "loss": 1.38, + "step": 4099 + }, + { + "epoch": 0.43, + "learning_rate": 1.4067700808517815e-05, + "loss": 1.4175, + "step": 4100 + }, + { + "epoch": 0.43, + "learning_rate": 1.4064356785758298e-05, + "loss": 1.4085, + "step": 4101 + }, + { + "epoch": 0.43, + "learning_rate": 1.4061012218479397e-05, + "loss": 1.4529, + "step": 4102 + }, + { + "epoch": 0.43, + "learning_rate": 1.405766710712921e-05, + "loss": 1.4836, + "step": 4103 + }, + { + "epoch": 0.43, + "learning_rate": 1.4054321452155885e-05, + "loss": 1.3915, + "step": 4104 + }, + { + "epoch": 0.43, + "learning_rate": 1.4050975254007659e-05, + "loss": 1.3044, + "step": 4105 + }, + { + "epoch": 0.43, + "learning_rate": 1.4047628513132835e-05, + "loss": 1.373, + "step": 4106 + }, + { + "epoch": 0.43, + "learning_rate": 1.4044281229979793e-05, + "loss": 1.4266, + "step": 4107 + }, + { + "epoch": 0.43, + "learning_rate": 1.4040933404996977e-05, + "loss": 1.3898, + "step": 4108 + }, + { + "epoch": 0.43, + "learning_rate": 1.4037585038632915e-05, + "loss": 0.9326, + "step": 4109 + }, + { + "epoch": 0.43, + "learning_rate": 1.40342361313362e-05, + "loss": 1.0831, + "step": 4110 + }, + { + "epoch": 0.43, + "learning_rate": 1.40308866835555e-05, + "loss": 1.3898, + "step": 4111 + }, + { + "epoch": 0.43, + "learning_rate": 1.4027536695739554e-05, + "loss": 1.5058, + "step": 4112 + }, + { + "epoch": 0.43, + "learning_rate": 1.4024186168337175e-05, + "loss": 1.3635, + "step": 4113 + }, + { + "epoch": 0.43, + "learning_rate": 1.4020835101797248e-05, + "loss": 1.3871, + "step": 4114 + }, + { + "epoch": 0.43, + "learning_rate": 1.401748349656873e-05, + "loss": 1.3478, + "step": 4115 + }, + { + "epoch": 0.43, + "learning_rate": 1.4014131353100648e-05, + "loss": 1.3356, + "step": 4116 + }, + { + "epoch": 0.43, + "learning_rate": 1.4010778671842107e-05, + "loss": 1.3954, + "step": 4117 + }, + { + "epoch": 0.43, + "learning_rate": 1.4007425453242274e-05, + "loss": 1.3307, + "step": 4118 + }, + { + "epoch": 0.43, + "learning_rate": 1.4004071697750398e-05, + "loss": 1.4508, + "step": 4119 + }, + { + "epoch": 0.43, + "learning_rate": 1.4000717405815799e-05, + "loss": 1.3752, + "step": 4120 + }, + { + "epoch": 0.43, + "learning_rate": 1.399736257788786e-05, + "loss": 1.3654, + "step": 4121 + }, + { + "epoch": 0.43, + "learning_rate": 1.3994007214416046e-05, + "loss": 1.4505, + "step": 4122 + }, + { + "epoch": 0.43, + "learning_rate": 1.3990651315849886e-05, + "loss": 1.4307, + "step": 4123 + }, + { + "epoch": 0.43, + "learning_rate": 1.398729488263899e-05, + "loss": 1.4481, + "step": 4124 + }, + { + "epoch": 0.43, + "learning_rate": 1.3983937915233026e-05, + "loss": 1.4755, + "step": 4125 + }, + { + "epoch": 0.43, + "learning_rate": 1.3980580414081746e-05, + "loss": 1.3402, + "step": 4126 + }, + { + "epoch": 0.43, + "learning_rate": 1.3977222379634969e-05, + "loss": 1.3636, + "step": 4127 + }, + { + "epoch": 0.43, + "learning_rate": 1.3973863812342585e-05, + "loss": 1.4165, + "step": 4128 + }, + { + "epoch": 0.43, + "learning_rate": 1.3970504712654554e-05, + "loss": 1.3832, + "step": 4129 + }, + { + "epoch": 0.43, + "learning_rate": 1.3967145081020912e-05, + "loss": 1.4236, + "step": 4130 + }, + { + "epoch": 0.43, + "learning_rate": 1.396378491789176e-05, + "loss": 1.5022, + "step": 4131 + }, + { + "epoch": 0.43, + "learning_rate": 1.3960424223717276e-05, + "loss": 1.3806, + "step": 4132 + }, + { + "epoch": 0.43, + "learning_rate": 1.3957062998947707e-05, + "loss": 1.3649, + "step": 4133 + }, + { + "epoch": 0.43, + "learning_rate": 1.3953701244033368e-05, + "loss": 1.3787, + "step": 4134 + }, + { + "epoch": 0.43, + "learning_rate": 1.395033895942465e-05, + "loss": 1.3551, + "step": 4135 + }, + { + "epoch": 0.43, + "learning_rate": 1.394697614557201e-05, + "loss": 1.3881, + "step": 4136 + }, + { + "epoch": 0.43, + "learning_rate": 1.3943612802925983e-05, + "loss": 1.4848, + "step": 4137 + }, + { + "epoch": 0.43, + "learning_rate": 1.3940248931937169e-05, + "loss": 1.425, + "step": 4138 + }, + { + "epoch": 0.43, + "learning_rate": 1.3936884533056238e-05, + "loss": 1.4054, + "step": 4139 + }, + { + "epoch": 0.43, + "learning_rate": 1.3933519606733934e-05, + "loss": 1.4028, + "step": 4140 + }, + { + "epoch": 0.43, + "learning_rate": 1.3930154153421072e-05, + "loss": 1.4439, + "step": 4141 + }, + { + "epoch": 0.43, + "learning_rate": 1.3926788173568536e-05, + "loss": 1.4482, + "step": 4142 + }, + { + "epoch": 0.43, + "learning_rate": 1.392342166762728e-05, + "loss": 1.393, + "step": 4143 + }, + { + "epoch": 0.43, + "learning_rate": 1.3920054636048328e-05, + "loss": 1.4097, + "step": 4144 + }, + { + "epoch": 0.43, + "learning_rate": 1.391668707928278e-05, + "loss": 1.5142, + "step": 4145 + }, + { + "epoch": 0.43, + "learning_rate": 1.3913318997781797e-05, + "loss": 1.4118, + "step": 4146 + }, + { + "epoch": 0.43, + "learning_rate": 1.390995039199662e-05, + "loss": 1.4067, + "step": 4147 + }, + { + "epoch": 0.43, + "learning_rate": 1.3906581262378552e-05, + "loss": 1.5214, + "step": 4148 + }, + { + "epoch": 0.44, + "learning_rate": 1.3903211609378971e-05, + "loss": 1.3618, + "step": 4149 + }, + { + "epoch": 0.44, + "learning_rate": 1.3899841433449327e-05, + "loss": 1.338, + "step": 4150 + }, + { + "epoch": 0.44, + "learning_rate": 1.3896470735041132e-05, + "loss": 1.3901, + "step": 4151 + }, + { + "epoch": 0.44, + "learning_rate": 1.3893099514605971e-05, + "loss": 1.4502, + "step": 4152 + }, + { + "epoch": 0.44, + "learning_rate": 1.388972777259551e-05, + "loss": 1.4141, + "step": 4153 + }, + { + "epoch": 0.44, + "learning_rate": 1.3886355509461471e-05, + "loss": 1.3876, + "step": 4154 + }, + { + "epoch": 0.44, + "learning_rate": 1.388298272565565e-05, + "loss": 1.4275, + "step": 4155 + }, + { + "epoch": 0.44, + "learning_rate": 1.3879609421629909e-05, + "loss": 1.3559, + "step": 4156 + }, + { + "epoch": 0.44, + "learning_rate": 1.3876235597836195e-05, + "loss": 1.416, + "step": 4157 + }, + { + "epoch": 0.44, + "learning_rate": 1.3872861254726506e-05, + "loss": 1.437, + "step": 4158 + }, + { + "epoch": 0.44, + "learning_rate": 1.3869486392752918e-05, + "loss": 1.3794, + "step": 4159 + }, + { + "epoch": 0.44, + "learning_rate": 1.3866111012367577e-05, + "loss": 1.4094, + "step": 4160 + }, + { + "epoch": 0.44, + "learning_rate": 1.3862735114022694e-05, + "loss": 1.3957, + "step": 4161 + }, + { + "epoch": 0.44, + "learning_rate": 1.3859358698170559e-05, + "loss": 1.3582, + "step": 4162 + }, + { + "epoch": 0.44, + "learning_rate": 1.3855981765263523e-05, + "loss": 1.4159, + "step": 4163 + }, + { + "epoch": 0.44, + "learning_rate": 1.3852604315754e-05, + "loss": 1.3498, + "step": 4164 + }, + { + "epoch": 0.44, + "learning_rate": 1.3849226350094491e-05, + "loss": 1.3951, + "step": 4165 + }, + { + "epoch": 0.44, + "learning_rate": 1.3845847868737559e-05, + "loss": 1.4087, + "step": 4166 + }, + { + "epoch": 0.44, + "learning_rate": 1.3842468872135821e-05, + "loss": 1.4318, + "step": 4167 + }, + { + "epoch": 0.44, + "learning_rate": 1.3839089360741989e-05, + "loss": 1.4174, + "step": 4168 + }, + { + "epoch": 0.44, + "learning_rate": 1.3835709335008822e-05, + "loss": 1.4499, + "step": 4169 + }, + { + "epoch": 0.44, + "learning_rate": 1.383232879538916e-05, + "loss": 1.3554, + "step": 4170 + }, + { + "epoch": 0.44, + "learning_rate": 1.3828947742335905e-05, + "loss": 1.3873, + "step": 4171 + }, + { + "epoch": 0.44, + "learning_rate": 1.382556617630204e-05, + "loss": 1.3804, + "step": 4172 + }, + { + "epoch": 0.44, + "learning_rate": 1.3822184097740598e-05, + "loss": 1.3856, + "step": 4173 + }, + { + "epoch": 0.44, + "learning_rate": 1.3818801507104697e-05, + "loss": 1.3901, + "step": 4174 + }, + { + "epoch": 0.44, + "learning_rate": 1.381541840484751e-05, + "loss": 1.3714, + "step": 4175 + }, + { + "epoch": 0.44, + "learning_rate": 1.3812034791422297e-05, + "loss": 1.4945, + "step": 4176 + }, + { + "epoch": 0.44, + "learning_rate": 1.3808650667282368e-05, + "loss": 1.429, + "step": 4177 + }, + { + "epoch": 0.44, + "learning_rate": 1.3805266032881108e-05, + "loss": 1.3903, + "step": 4178 + }, + { + "epoch": 0.44, + "learning_rate": 1.3801880888671972e-05, + "loss": 1.4799, + "step": 4179 + }, + { + "epoch": 0.44, + "eval_loss": 1.4521424770355225, + "eval_runtime": 77.3596, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 4179 + }, + { + "epoch": 0.44, + "learning_rate": 1.3798495235108484e-05, + "loss": 1.3912, + "step": 4180 + }, + { + "epoch": 0.44, + "learning_rate": 1.3795109072644235e-05, + "loss": 1.5837, + "step": 4181 + }, + { + "epoch": 0.44, + "learning_rate": 1.379172240173288e-05, + "loss": 1.4255, + "step": 4182 + }, + { + "epoch": 0.44, + "learning_rate": 1.3788335222828148e-05, + "loss": 1.4666, + "step": 4183 + }, + { + "epoch": 0.44, + "learning_rate": 1.3784947536383837e-05, + "loss": 1.3964, + "step": 4184 + }, + { + "epoch": 0.44, + "learning_rate": 1.3781559342853807e-05, + "loss": 1.336, + "step": 4185 + }, + { + "epoch": 0.44, + "learning_rate": 1.3778170642691986e-05, + "loss": 1.4352, + "step": 4186 + }, + { + "epoch": 0.44, + "learning_rate": 1.377478143635238e-05, + "loss": 1.3262, + "step": 4187 + }, + { + "epoch": 0.44, + "learning_rate": 1.3771391724289047e-05, + "loss": 1.3969, + "step": 4188 + }, + { + "epoch": 0.44, + "learning_rate": 1.376800150695613e-05, + "loss": 1.4211, + "step": 4189 + }, + { + "epoch": 0.44, + "learning_rate": 1.3764610784807824e-05, + "loss": 1.4338, + "step": 4190 + }, + { + "epoch": 0.44, + "learning_rate": 1.3761219558298403e-05, + "loss": 1.3815, + "step": 4191 + }, + { + "epoch": 0.44, + "learning_rate": 1.3757827827882203e-05, + "loss": 1.3805, + "step": 4192 + }, + { + "epoch": 0.44, + "learning_rate": 1.3754435594013627e-05, + "loss": 1.4071, + "step": 4193 + }, + { + "epoch": 0.44, + "learning_rate": 1.3751042857147145e-05, + "loss": 1.343, + "step": 4194 + }, + { + "epoch": 0.44, + "learning_rate": 1.3747649617737304e-05, + "loss": 1.4129, + "step": 4195 + }, + { + "epoch": 0.44, + "learning_rate": 1.3744255876238708e-05, + "loss": 1.3939, + "step": 4196 + }, + { + "epoch": 0.44, + "learning_rate": 1.3740861633106029e-05, + "loss": 1.3963, + "step": 4197 + }, + { + "epoch": 0.44, + "learning_rate": 1.3737466888794008e-05, + "loss": 1.5181, + "step": 4198 + }, + { + "epoch": 0.44, + "learning_rate": 1.3734071643757456e-05, + "loss": 1.4397, + "step": 4199 + }, + { + "epoch": 0.44, + "learning_rate": 1.373067589845125e-05, + "loss": 1.6293, + "step": 4200 + }, + { + "epoch": 0.44, + "learning_rate": 1.3727279653330328e-05, + "loss": 1.3498, + "step": 4201 + }, + { + "epoch": 0.44, + "learning_rate": 1.37238829088497e-05, + "loss": 1.4509, + "step": 4202 + }, + { + "epoch": 0.44, + "learning_rate": 1.3720485665464446e-05, + "loss": 1.4477, + "step": 4203 + }, + { + "epoch": 0.44, + "learning_rate": 1.3717087923629709e-05, + "loss": 1.4399, + "step": 4204 + }, + { + "epoch": 0.44, + "learning_rate": 1.3713689683800695e-05, + "loss": 1.4417, + "step": 4205 + }, + { + "epoch": 0.44, + "learning_rate": 1.3710290946432685e-05, + "loss": 1.3957, + "step": 4206 + }, + { + "epoch": 0.44, + "learning_rate": 1.3706891711981021e-05, + "loss": 1.4476, + "step": 4207 + }, + { + "epoch": 0.44, + "learning_rate": 1.3703491980901113e-05, + "loss": 1.3894, + "step": 4208 + }, + { + "epoch": 0.44, + "learning_rate": 1.3700091753648437e-05, + "loss": 1.4745, + "step": 4209 + }, + { + "epoch": 0.44, + "learning_rate": 1.369669103067854e-05, + "loss": 1.4038, + "step": 4210 + }, + { + "epoch": 0.44, + "learning_rate": 1.3693289812447023e-05, + "loss": 1.4151, + "step": 4211 + }, + { + "epoch": 0.44, + "learning_rate": 1.3689888099409572e-05, + "loss": 1.4214, + "step": 4212 + }, + { + "epoch": 0.44, + "learning_rate": 1.368648589202192e-05, + "loss": 1.4287, + "step": 4213 + }, + { + "epoch": 0.44, + "learning_rate": 1.3683083190739883e-05, + "loss": 1.345, + "step": 4214 + }, + { + "epoch": 0.44, + "learning_rate": 1.367967999601933e-05, + "loss": 1.3022, + "step": 4215 + }, + { + "epoch": 0.44, + "learning_rate": 1.3676276308316207e-05, + "loss": 1.3971, + "step": 4216 + }, + { + "epoch": 0.44, + "learning_rate": 1.3672872128086514e-05, + "loss": 1.3335, + "step": 4217 + }, + { + "epoch": 0.44, + "learning_rate": 1.366946745578633e-05, + "loss": 1.3988, + "step": 4218 + }, + { + "epoch": 0.44, + "learning_rate": 1.366606229187179e-05, + "loss": 1.4508, + "step": 4219 + }, + { + "epoch": 0.44, + "learning_rate": 1.3662656636799099e-05, + "loss": 1.3814, + "step": 4220 + }, + { + "epoch": 0.44, + "learning_rate": 1.3659250491024527e-05, + "loss": 1.4128, + "step": 4221 + }, + { + "epoch": 0.44, + "learning_rate": 1.3655843855004411e-05, + "loss": 1.3893, + "step": 4222 + }, + { + "epoch": 0.44, + "learning_rate": 1.3652436729195154e-05, + "loss": 1.2551, + "step": 4223 + }, + { + "epoch": 0.44, + "learning_rate": 1.3649029114053219e-05, + "loss": 1.4386, + "step": 4224 + }, + { + "epoch": 0.44, + "learning_rate": 1.364562101003514e-05, + "loss": 1.4028, + "step": 4225 + }, + { + "epoch": 0.44, + "learning_rate": 1.364221241759752e-05, + "loss": 1.4351, + "step": 4226 + }, + { + "epoch": 0.44, + "learning_rate": 1.363880333719702e-05, + "loss": 1.3941, + "step": 4227 + }, + { + "epoch": 0.44, + "learning_rate": 1.3635393769290368e-05, + "loss": 1.3879, + "step": 4228 + }, + { + "epoch": 0.44, + "learning_rate": 1.3631983714334358e-05, + "loss": 1.3773, + "step": 4229 + }, + { + "epoch": 0.44, + "learning_rate": 1.3628573172785853e-05, + "loss": 1.3679, + "step": 4230 + }, + { + "epoch": 0.44, + "learning_rate": 1.3625162145101776e-05, + "loss": 1.3705, + "step": 4231 + }, + { + "epoch": 0.44, + "learning_rate": 1.3621750631739114e-05, + "loss": 1.8157, + "step": 4232 + }, + { + "epoch": 0.44, + "learning_rate": 1.3618338633154928e-05, + "loss": 1.4056, + "step": 4233 + }, + { + "epoch": 0.44, + "learning_rate": 1.3614926149806334e-05, + "loss": 1.3716, + "step": 4234 + }, + { + "epoch": 0.44, + "learning_rate": 1.3611513182150523e-05, + "loss": 1.3766, + "step": 4235 + }, + { + "epoch": 0.44, + "learning_rate": 1.3608099730644733e-05, + "loss": 1.41, + "step": 4236 + }, + { + "epoch": 0.44, + "learning_rate": 1.3604685795746291e-05, + "loss": 1.421, + "step": 4237 + }, + { + "epoch": 0.44, + "learning_rate": 1.360127137791257e-05, + "loss": 1.3679, + "step": 4238 + }, + { + "epoch": 0.44, + "learning_rate": 1.3597856477601018e-05, + "loss": 1.4615, + "step": 4239 + }, + { + "epoch": 0.44, + "learning_rate": 1.359444109526914e-05, + "loss": 1.3418, + "step": 4240 + }, + { + "epoch": 0.44, + "learning_rate": 1.3591025231374513e-05, + "loss": 1.3631, + "step": 4241 + }, + { + "epoch": 0.44, + "learning_rate": 1.3587608886374772e-05, + "loss": 1.3802, + "step": 4242 + }, + { + "epoch": 0.44, + "learning_rate": 1.3584192060727622e-05, + "loss": 1.4156, + "step": 4243 + }, + { + "epoch": 0.45, + "learning_rate": 1.3580774754890827e-05, + "loss": 1.4161, + "step": 4244 + }, + { + "epoch": 0.45, + "learning_rate": 1.3577356969322222e-05, + "loss": 1.3535, + "step": 4245 + }, + { + "epoch": 0.45, + "learning_rate": 1.3573938704479699e-05, + "loss": 1.3859, + "step": 4246 + }, + { + "epoch": 0.45, + "learning_rate": 1.357051996082122e-05, + "loss": 1.3595, + "step": 4247 + }, + { + "epoch": 0.45, + "learning_rate": 1.3567100738804806e-05, + "loss": 1.4191, + "step": 4248 + }, + { + "epoch": 0.45, + "learning_rate": 1.3563681038888548e-05, + "loss": 1.4186, + "step": 4249 + }, + { + "epoch": 0.45, + "learning_rate": 1.3560260861530596e-05, + "loss": 1.43, + "step": 4250 + }, + { + "epoch": 0.45, + "learning_rate": 1.3556840207189168e-05, + "loss": 1.4139, + "step": 4251 + }, + { + "epoch": 0.45, + "learning_rate": 1.3553419076322539e-05, + "loss": 1.4005, + "step": 4252 + }, + { + "epoch": 0.45, + "learning_rate": 1.3549997469389058e-05, + "loss": 1.3468, + "step": 4253 + }, + { + "epoch": 0.45, + "learning_rate": 1.3546575386847132e-05, + "loss": 1.3756, + "step": 4254 + }, + { + "epoch": 0.45, + "learning_rate": 1.3543152829155226e-05, + "loss": 1.4063, + "step": 4255 + }, + { + "epoch": 0.45, + "learning_rate": 1.3539729796771884e-05, + "loss": 1.4666, + "step": 4256 + }, + { + "epoch": 0.45, + "learning_rate": 1.3536306290155694e-05, + "loss": 1.4212, + "step": 4257 + }, + { + "epoch": 0.45, + "learning_rate": 1.3532882309765332e-05, + "loss": 1.4883, + "step": 4258 + }, + { + "epoch": 0.45, + "learning_rate": 1.3529457856059507e-05, + "loss": 1.6641, + "step": 4259 + }, + { + "epoch": 0.45, + "learning_rate": 1.3526032929497022e-05, + "loss": 1.3659, + "step": 4260 + }, + { + "epoch": 0.45, + "learning_rate": 1.3522607530536717e-05, + "loss": 1.5945, + "step": 4261 + }, + { + "epoch": 0.45, + "learning_rate": 1.351918165963752e-05, + "loss": 1.3643, + "step": 4262 + }, + { + "epoch": 0.45, + "learning_rate": 1.3515755317258397e-05, + "loss": 1.3442, + "step": 4263 + }, + { + "epoch": 0.45, + "learning_rate": 1.3512328503858398e-05, + "loss": 1.3982, + "step": 4264 + }, + { + "epoch": 0.45, + "learning_rate": 1.3508901219896624e-05, + "loss": 1.4985, + "step": 4265 + }, + { + "epoch": 0.45, + "learning_rate": 1.350547346583225e-05, + "loss": 1.3319, + "step": 4266 + }, + { + "epoch": 0.45, + "learning_rate": 1.3502045242124497e-05, + "loss": 1.3961, + "step": 4267 + }, + { + "epoch": 0.45, + "learning_rate": 1.3498616549232665e-05, + "loss": 1.4565, + "step": 4268 + }, + { + "epoch": 0.45, + "learning_rate": 1.349518738761611e-05, + "loss": 1.375, + "step": 4269 + }, + { + "epoch": 0.45, + "learning_rate": 1.3491757757734254e-05, + "loss": 1.3005, + "step": 4270 + }, + { + "epoch": 0.45, + "learning_rate": 1.348832766004657e-05, + "loss": 1.3185, + "step": 4271 + }, + { + "epoch": 0.45, + "learning_rate": 1.3484897095012613e-05, + "loss": 1.4449, + "step": 4272 + }, + { + "epoch": 0.45, + "learning_rate": 1.3481466063091988e-05, + "loss": 1.3587, + "step": 4273 + }, + { + "epoch": 0.45, + "learning_rate": 1.3478034564744362e-05, + "loss": 1.3844, + "step": 4274 + }, + { + "epoch": 0.45, + "learning_rate": 1.3474602600429468e-05, + "loss": 1.4471, + "step": 4275 + }, + { + "epoch": 0.45, + "learning_rate": 1.3471170170607105e-05, + "loss": 1.4686, + "step": 4276 + }, + { + "epoch": 0.45, + "learning_rate": 1.3467737275737127e-05, + "loss": 1.312, + "step": 4277 + }, + { + "epoch": 0.45, + "learning_rate": 1.3464303916279453e-05, + "loss": 1.407, + "step": 4278 + }, + { + "epoch": 0.45, + "learning_rate": 1.346087009269407e-05, + "loss": 1.364, + "step": 4279 + }, + { + "epoch": 0.45, + "learning_rate": 1.3457435805441016e-05, + "loss": 1.4103, + "step": 4280 + }, + { + "epoch": 0.45, + "learning_rate": 1.3454001054980403e-05, + "loss": 1.4243, + "step": 4281 + }, + { + "epoch": 0.45, + "learning_rate": 1.3450565841772392e-05, + "loss": 1.3879, + "step": 4282 + }, + { + "epoch": 0.45, + "learning_rate": 1.344713016627722e-05, + "loss": 1.4688, + "step": 4283 + }, + { + "epoch": 0.45, + "learning_rate": 1.3443694028955176e-05, + "loss": 1.3983, + "step": 4284 + }, + { + "epoch": 0.45, + "learning_rate": 1.344025743026662e-05, + "loss": 1.4316, + "step": 4285 + }, + { + "epoch": 0.45, + "learning_rate": 1.3436820370671956e-05, + "loss": 1.3643, + "step": 4286 + }, + { + "epoch": 0.45, + "learning_rate": 1.3433382850631673e-05, + "loss": 1.4566, + "step": 4287 + }, + { + "epoch": 0.45, + "learning_rate": 1.3429944870606301e-05, + "loss": 1.1263, + "step": 4288 + }, + { + "epoch": 0.45, + "learning_rate": 1.3426506431056452e-05, + "loss": 1.2463, + "step": 4289 + }, + { + "epoch": 0.45, + "learning_rate": 1.342306753244278e-05, + "loss": 1.4753, + "step": 4290 + }, + { + "epoch": 0.45, + "learning_rate": 1.3419628175226012e-05, + "loss": 1.3789, + "step": 4291 + }, + { + "epoch": 0.45, + "learning_rate": 1.3416188359866932e-05, + "loss": 1.3906, + "step": 4292 + }, + { + "epoch": 0.45, + "learning_rate": 1.3412748086826389e-05, + "loss": 1.3995, + "step": 4293 + }, + { + "epoch": 0.45, + "learning_rate": 1.3409307356565288e-05, + "loss": 1.4906, + "step": 4294 + }, + { + "epoch": 0.45, + "learning_rate": 1.3405866169544602e-05, + "loss": 1.3951, + "step": 4295 + }, + { + "epoch": 0.45, + "learning_rate": 1.3402424526225359e-05, + "loss": 1.3753, + "step": 4296 + }, + { + "epoch": 0.45, + "learning_rate": 1.3398982427068654e-05, + "loss": 1.3686, + "step": 4297 + }, + { + "epoch": 0.45, + "learning_rate": 1.3395539872535636e-05, + "loss": 1.3612, + "step": 4298 + }, + { + "epoch": 0.45, + "learning_rate": 1.3392096863087522e-05, + "loss": 1.4043, + "step": 4299 + }, + { + "epoch": 0.45, + "learning_rate": 1.3388653399185585e-05, + "loss": 1.4068, + "step": 4300 + }, + { + "epoch": 0.45, + "learning_rate": 1.338520948129116e-05, + "loss": 1.4066, + "step": 4301 + }, + { + "epoch": 0.45, + "learning_rate": 1.3381765109865646e-05, + "loss": 1.4944, + "step": 4302 + }, + { + "epoch": 0.45, + "learning_rate": 1.3378320285370496e-05, + "loss": 1.3575, + "step": 4303 + }, + { + "epoch": 0.45, + "learning_rate": 1.3374875008267236e-05, + "loss": 1.3807, + "step": 4304 + }, + { + "epoch": 0.45, + "learning_rate": 1.3371429279017437e-05, + "loss": 1.4389, + "step": 4305 + }, + { + "epoch": 0.45, + "learning_rate": 1.3367983098082739e-05, + "loss": 1.4858, + "step": 4306 + }, + { + "epoch": 0.45, + "learning_rate": 1.3364536465924844e-05, + "loss": 1.3282, + "step": 4307 + }, + { + "epoch": 0.45, + "learning_rate": 1.3361089383005515e-05, + "loss": 1.4306, + "step": 4308 + }, + { + "epoch": 0.45, + "learning_rate": 1.3357641849786566e-05, + "loss": 1.3892, + "step": 4309 + }, + { + "epoch": 0.45, + "learning_rate": 1.3354193866729883e-05, + "loss": 1.3621, + "step": 4310 + }, + { + "epoch": 0.45, + "learning_rate": 1.3350745434297401e-05, + "loss": 1.3476, + "step": 4311 + }, + { + "epoch": 0.45, + "learning_rate": 1.334729655295113e-05, + "loss": 1.4477, + "step": 4312 + }, + { + "epoch": 0.45, + "learning_rate": 1.3343847223153123e-05, + "loss": 1.3585, + "step": 4313 + }, + { + "epoch": 0.45, + "learning_rate": 1.334039744536551e-05, + "loss": 1.3616, + "step": 4314 + }, + { + "epoch": 0.45, + "learning_rate": 1.3336947220050462e-05, + "loss": 1.3579, + "step": 4315 + }, + { + "epoch": 0.45, + "learning_rate": 1.3333496547670232e-05, + "loss": 1.3557, + "step": 4316 + }, + { + "epoch": 0.45, + "learning_rate": 1.3330045428687113e-05, + "loss": 1.4443, + "step": 4317 + }, + { + "epoch": 0.45, + "learning_rate": 1.332659386356347e-05, + "loss": 1.3621, + "step": 4318 + }, + { + "epoch": 0.45, + "learning_rate": 1.3323141852761726e-05, + "loss": 1.3295, + "step": 4319 + }, + { + "epoch": 0.45, + "learning_rate": 1.3319689396744358e-05, + "loss": 1.4187, + "step": 4320 + }, + { + "epoch": 0.45, + "learning_rate": 1.3316236495973905e-05, + "loss": 1.335, + "step": 4321 + }, + { + "epoch": 0.45, + "learning_rate": 1.331278315091297e-05, + "loss": 1.4382, + "step": 4322 + }, + { + "epoch": 0.45, + "learning_rate": 1.3309329362024212e-05, + "loss": 1.4244, + "step": 4323 + }, + { + "epoch": 0.45, + "learning_rate": 1.3305875129770351e-05, + "loss": 1.488, + "step": 4324 + }, + { + "epoch": 0.45, + "learning_rate": 1.3302420454614165e-05, + "loss": 1.3369, + "step": 4325 + }, + { + "epoch": 0.45, + "learning_rate": 1.3298965337018487e-05, + "loss": 1.3648, + "step": 4326 + }, + { + "epoch": 0.45, + "learning_rate": 1.3295509777446226e-05, + "loss": 1.3924, + "step": 4327 + }, + { + "epoch": 0.45, + "learning_rate": 1.3292053776360324e-05, + "loss": 1.3789, + "step": 4328 + }, + { + "epoch": 0.45, + "learning_rate": 1.3288597334223802e-05, + "loss": 1.3902, + "step": 4329 + }, + { + "epoch": 0.45, + "learning_rate": 1.3285140451499735e-05, + "loss": 1.4057, + "step": 4330 + }, + { + "epoch": 0.45, + "learning_rate": 1.328168312865126e-05, + "loss": 1.4536, + "step": 4331 + }, + { + "epoch": 0.45, + "learning_rate": 1.3278225366141565e-05, + "loss": 1.3075, + "step": 4332 + }, + { + "epoch": 0.45, + "learning_rate": 1.3274767164433901e-05, + "loss": 1.4579, + "step": 4333 + }, + { + "epoch": 0.45, + "learning_rate": 1.3271308523991579e-05, + "loss": 1.3906, + "step": 4334 + }, + { + "epoch": 0.45, + "learning_rate": 1.326784944527797e-05, + "loss": 1.3992, + "step": 4335 + }, + { + "epoch": 0.45, + "learning_rate": 1.3264389928756498e-05, + "loss": 1.4001, + "step": 4336 + }, + { + "epoch": 0.45, + "learning_rate": 1.3260929974890653e-05, + "loss": 1.2948, + "step": 4337 + }, + { + "epoch": 0.45, + "learning_rate": 1.3257469584143976e-05, + "loss": 1.4041, + "step": 4338 + }, + { + "epoch": 0.46, + "learning_rate": 1.3254008756980076e-05, + "loss": 1.5035, + "step": 4339 + }, + { + "epoch": 0.46, + "learning_rate": 1.3250547493862609e-05, + "loss": 1.4867, + "step": 4340 + }, + { + "epoch": 0.46, + "learning_rate": 1.3247085795255302e-05, + "loss": 1.3612, + "step": 4341 + }, + { + "epoch": 0.46, + "learning_rate": 1.3243623661621925e-05, + "loss": 1.4193, + "step": 4342 + }, + { + "epoch": 0.46, + "learning_rate": 1.3240161093426322e-05, + "loss": 1.3596, + "step": 4343 + }, + { + "epoch": 0.46, + "learning_rate": 1.3236698091132383e-05, + "loss": 1.4448, + "step": 4344 + }, + { + "epoch": 0.46, + "learning_rate": 1.3233234655204066e-05, + "loss": 1.3924, + "step": 4345 + }, + { + "epoch": 0.46, + "learning_rate": 1.322977078610538e-05, + "loss": 1.3552, + "step": 4346 + }, + { + "epoch": 0.46, + "learning_rate": 1.3226306484300395e-05, + "loss": 1.3949, + "step": 4347 + }, + { + "epoch": 0.46, + "learning_rate": 1.322284175025324e-05, + "loss": 1.399, + "step": 4348 + }, + { + "epoch": 0.46, + "learning_rate": 1.3219376584428094e-05, + "loss": 1.4755, + "step": 4349 + }, + { + "epoch": 0.46, + "learning_rate": 1.3215910987289212e-05, + "loss": 1.3877, + "step": 4350 + }, + { + "epoch": 0.46, + "learning_rate": 1.3212444959300882e-05, + "loss": 1.3916, + "step": 4351 + }, + { + "epoch": 0.46, + "learning_rate": 1.3208978500927472e-05, + "loss": 1.3462, + "step": 4352 + }, + { + "epoch": 0.46, + "learning_rate": 1.3205511612633392e-05, + "loss": 1.3834, + "step": 4353 + }, + { + "epoch": 0.46, + "learning_rate": 1.3202044294883123e-05, + "loss": 1.3843, + "step": 4354 + }, + { + "epoch": 0.46, + "learning_rate": 1.3198576548141189e-05, + "loss": 1.2439, + "step": 4355 + }, + { + "epoch": 0.46, + "learning_rate": 1.3195108372872181e-05, + "loss": 1.4106, + "step": 4356 + }, + { + "epoch": 0.46, + "learning_rate": 1.3191639769540746e-05, + "loss": 1.4417, + "step": 4357 + }, + { + "epoch": 0.46, + "learning_rate": 1.3188170738611596e-05, + "loss": 1.4393, + "step": 4358 + }, + { + "epoch": 0.46, + "learning_rate": 1.3184701280549476e-05, + "loss": 1.4616, + "step": 4359 + }, + { + "epoch": 0.46, + "learning_rate": 1.3181231395819218e-05, + "loss": 1.3215, + "step": 4360 + }, + { + "epoch": 0.46, + "learning_rate": 1.3177761084885689e-05, + "loss": 1.368, + "step": 4361 + }, + { + "epoch": 0.46, + "learning_rate": 1.317429034821383e-05, + "loss": 1.3247, + "step": 4362 + }, + { + "epoch": 0.46, + "learning_rate": 1.3170819186268618e-05, + "loss": 1.4512, + "step": 4363 + }, + { + "epoch": 0.46, + "learning_rate": 1.3167347599515111e-05, + "loss": 1.3129, + "step": 4364 + }, + { + "epoch": 0.46, + "learning_rate": 1.3163875588418404e-05, + "loss": 1.3934, + "step": 4365 + }, + { + "epoch": 0.46, + "learning_rate": 1.3160403153443666e-05, + "loss": 1.4518, + "step": 4366 + }, + { + "epoch": 0.46, + "learning_rate": 1.3156930295056105e-05, + "loss": 1.3959, + "step": 4367 + }, + { + "epoch": 0.46, + "learning_rate": 1.3153457013721e-05, + "loss": 1.3475, + "step": 4368 + }, + { + "epoch": 0.46, + "learning_rate": 1.3149983309903687e-05, + "loss": 1.4102, + "step": 4369 + }, + { + "epoch": 0.46, + "learning_rate": 1.3146509184069538e-05, + "loss": 1.3674, + "step": 4370 + }, + { + "epoch": 0.46, + "learning_rate": 1.314303463668401e-05, + "loss": 1.3739, + "step": 4371 + }, + { + "epoch": 0.46, + "learning_rate": 1.3139559668212596e-05, + "loss": 1.4249, + "step": 4372 + }, + { + "epoch": 0.46, + "learning_rate": 1.3136084279120857e-05, + "loss": 1.4473, + "step": 4373 + }, + { + "epoch": 0.46, + "learning_rate": 1.3132608469874404e-05, + "loss": 1.4443, + "step": 4374 + }, + { + "epoch": 0.46, + "learning_rate": 1.3129132240938905e-05, + "loss": 1.3534, + "step": 4375 + }, + { + "epoch": 0.46, + "learning_rate": 1.3125655592780083e-05, + "loss": 1.5663, + "step": 4376 + }, + { + "epoch": 0.46, + "learning_rate": 1.3122178525863727e-05, + "loss": 1.3465, + "step": 4377 + }, + { + "epoch": 0.46, + "learning_rate": 1.3118701040655669e-05, + "loss": 1.35, + "step": 4378 + }, + { + "epoch": 0.46, + "eval_loss": 1.447788953781128, + "eval_runtime": 77.4473, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4378 + }, + { + "epoch": 0.46, + "learning_rate": 1.3115223137621804e-05, + "loss": 1.343, + "step": 4379 + }, + { + "epoch": 0.46, + "learning_rate": 1.3111744817228078e-05, + "loss": 1.4227, + "step": 4380 + }, + { + "epoch": 0.46, + "learning_rate": 1.3108266079940508e-05, + "loss": 1.3982, + "step": 4381 + }, + { + "epoch": 0.46, + "learning_rate": 1.3104786926225141e-05, + "loss": 1.4211, + "step": 4382 + }, + { + "epoch": 0.46, + "learning_rate": 1.3101307356548103e-05, + "loss": 1.382, + "step": 4383 + }, + { + "epoch": 0.46, + "learning_rate": 1.3097827371375562e-05, + "loss": 1.4637, + "step": 4384 + }, + { + "epoch": 0.46, + "learning_rate": 1.3094346971173754e-05, + "loss": 1.4572, + "step": 4385 + }, + { + "epoch": 0.46, + "learning_rate": 1.3090866156408956e-05, + "loss": 1.5113, + "step": 4386 + }, + { + "epoch": 0.46, + "learning_rate": 1.3087384927547512e-05, + "loss": 1.2197, + "step": 4387 + }, + { + "epoch": 0.46, + "learning_rate": 1.3083903285055813e-05, + "loss": 1.3861, + "step": 4388 + }, + { + "epoch": 0.46, + "learning_rate": 1.3080421229400315e-05, + "loss": 1.4754, + "step": 4389 + }, + { + "epoch": 0.46, + "learning_rate": 1.307693876104752e-05, + "loss": 1.3588, + "step": 4390 + }, + { + "epoch": 0.46, + "learning_rate": 1.3073455880463987e-05, + "loss": 1.3995, + "step": 4391 + }, + { + "epoch": 0.46, + "learning_rate": 1.3069972588116341e-05, + "loss": 1.354, + "step": 4392 + }, + { + "epoch": 0.46, + "learning_rate": 1.3066488884471244e-05, + "loss": 1.3378, + "step": 4393 + }, + { + "epoch": 0.46, + "learning_rate": 1.306300476999543e-05, + "loss": 1.5951, + "step": 4394 + }, + { + "epoch": 0.46, + "learning_rate": 1.305952024515568e-05, + "loss": 1.3661, + "step": 4395 + }, + { + "epoch": 0.46, + "learning_rate": 1.3056035310418826e-05, + "loss": 1.4066, + "step": 4396 + }, + { + "epoch": 0.46, + "learning_rate": 1.3052549966251764e-05, + "loss": 1.3687, + "step": 4397 + }, + { + "epoch": 0.46, + "learning_rate": 1.3049064213121438e-05, + "loss": 1.4573, + "step": 4398 + }, + { + "epoch": 0.46, + "learning_rate": 1.3045578051494852e-05, + "loss": 1.3519, + "step": 4399 + }, + { + "epoch": 0.46, + "learning_rate": 1.3042091481839063e-05, + "loss": 1.2803, + "step": 4400 + }, + { + "epoch": 0.46, + "learning_rate": 1.3038604504621173e-05, + "loss": 1.4014, + "step": 4401 + }, + { + "epoch": 0.46, + "learning_rate": 1.3035117120308358e-05, + "loss": 1.4534, + "step": 4402 + }, + { + "epoch": 0.46, + "learning_rate": 1.3031629329367832e-05, + "loss": 1.4747, + "step": 4403 + }, + { + "epoch": 0.46, + "learning_rate": 1.3028141132266877e-05, + "loss": 1.374, + "step": 4404 + }, + { + "epoch": 0.46, + "learning_rate": 1.3024652529472807e-05, + "loss": 1.4328, + "step": 4405 + }, + { + "epoch": 0.46, + "learning_rate": 1.302116352145302e-05, + "loss": 1.468, + "step": 4406 + }, + { + "epoch": 0.46, + "learning_rate": 1.3017674108674942e-05, + "loss": 1.2947, + "step": 4407 + }, + { + "epoch": 0.46, + "learning_rate": 1.3014184291606077e-05, + "loss": 1.3682, + "step": 4408 + }, + { + "epoch": 0.46, + "learning_rate": 1.3010694070713959e-05, + "loss": 1.3651, + "step": 4409 + }, + { + "epoch": 0.46, + "learning_rate": 1.3007203446466194e-05, + "loss": 1.418, + "step": 4410 + }, + { + "epoch": 0.46, + "learning_rate": 1.3003712419330433e-05, + "loss": 1.416, + "step": 4411 + }, + { + "epoch": 0.46, + "learning_rate": 1.300022098977439e-05, + "loss": 1.2979, + "step": 4412 + }, + { + "epoch": 0.46, + "learning_rate": 1.2996729158265819e-05, + "loss": 1.3868, + "step": 4413 + }, + { + "epoch": 0.46, + "learning_rate": 1.2993236925272542e-05, + "loss": 1.3102, + "step": 4414 + }, + { + "epoch": 0.46, + "learning_rate": 1.2989744291262422e-05, + "loss": 1.3506, + "step": 4415 + }, + { + "epoch": 0.46, + "learning_rate": 1.2986251256703388e-05, + "loss": 1.4018, + "step": 4416 + }, + { + "epoch": 0.46, + "learning_rate": 1.2982757822063417e-05, + "loss": 1.4081, + "step": 4417 + }, + { + "epoch": 0.46, + "learning_rate": 1.2979263987810533e-05, + "loss": 1.3592, + "step": 4418 + }, + { + "epoch": 0.46, + "learning_rate": 1.297576975441283e-05, + "loss": 1.4287, + "step": 4419 + }, + { + "epoch": 0.46, + "learning_rate": 1.2972275122338433e-05, + "loss": 1.4099, + "step": 4420 + }, + { + "epoch": 0.46, + "learning_rate": 1.2968780092055546e-05, + "loss": 1.4005, + "step": 4421 + }, + { + "epoch": 0.46, + "learning_rate": 1.2965284664032401e-05, + "loss": 1.365, + "step": 4422 + }, + { + "epoch": 0.46, + "learning_rate": 1.2961788838737309e-05, + "loss": 1.3588, + "step": 4423 + }, + { + "epoch": 0.46, + "learning_rate": 1.2958292616638606e-05, + "loss": 1.3702, + "step": 4424 + }, + { + "epoch": 0.46, + "learning_rate": 1.2954795998204708e-05, + "loss": 1.3487, + "step": 4425 + }, + { + "epoch": 0.46, + "learning_rate": 1.2951298983904063e-05, + "loss": 1.4395, + "step": 4426 + }, + { + "epoch": 0.46, + "learning_rate": 1.2947801574205193e-05, + "loss": 1.3523, + "step": 4427 + }, + { + "epoch": 0.46, + "learning_rate": 1.2944303769576645e-05, + "loss": 1.3125, + "step": 4428 + }, + { + "epoch": 0.46, + "learning_rate": 1.2940805570487048e-05, + "loss": 1.5476, + "step": 4429 + }, + { + "epoch": 0.46, + "learning_rate": 1.2937306977405062e-05, + "loss": 1.4076, + "step": 4430 + }, + { + "epoch": 0.46, + "learning_rate": 1.2933807990799418e-05, + "loss": 1.3007, + "step": 4431 + }, + { + "epoch": 0.46, + "learning_rate": 1.293030861113888e-05, + "loss": 1.3566, + "step": 4432 + }, + { + "epoch": 0.46, + "learning_rate": 1.2926808838892285e-05, + "loss": 1.3907, + "step": 4433 + }, + { + "epoch": 0.46, + "learning_rate": 1.2923308674528501e-05, + "loss": 1.379, + "step": 4434 + }, + { + "epoch": 0.47, + "learning_rate": 1.2919808118516475e-05, + "loss": 1.4319, + "step": 4435 + }, + { + "epoch": 0.47, + "learning_rate": 1.2916307171325176e-05, + "loss": 1.3392, + "step": 4436 + }, + { + "epoch": 0.47, + "learning_rate": 1.291280583342365e-05, + "loss": 1.401, + "step": 4437 + }, + { + "epoch": 0.47, + "learning_rate": 1.2909304105280984e-05, + "loss": 1.3939, + "step": 4438 + }, + { + "epoch": 0.47, + "learning_rate": 1.2905801987366322e-05, + "loss": 1.4676, + "step": 4439 + }, + { + "epoch": 0.47, + "learning_rate": 1.2902299480148855e-05, + "loss": 1.3957, + "step": 4440 + }, + { + "epoch": 0.47, + "learning_rate": 1.2898796584097828e-05, + "loss": 1.3587, + "step": 4441 + }, + { + "epoch": 0.47, + "learning_rate": 1.2895293299682545e-05, + "loss": 1.5809, + "step": 4442 + }, + { + "epoch": 0.47, + "learning_rate": 1.289178962737235e-05, + "loss": 1.3436, + "step": 4443 + }, + { + "epoch": 0.47, + "learning_rate": 1.2888285567636647e-05, + "loss": 1.4535, + "step": 4444 + }, + { + "epoch": 0.47, + "learning_rate": 1.2884781120944889e-05, + "loss": 1.3377, + "step": 4445 + }, + { + "epoch": 0.47, + "learning_rate": 1.2881276287766587e-05, + "loss": 0.8221, + "step": 4446 + }, + { + "epoch": 0.47, + "learning_rate": 1.2877771068571288e-05, + "loss": 0.7259, + "step": 4447 + }, + { + "epoch": 0.47, + "learning_rate": 1.2874265463828612e-05, + "loss": 0.8279, + "step": 4448 + }, + { + "epoch": 0.47, + "learning_rate": 1.2870759474008213e-05, + "loss": 1.3523, + "step": 4449 + }, + { + "epoch": 0.47, + "learning_rate": 1.2867253099579808e-05, + "loss": 1.3658, + "step": 4450 + }, + { + "epoch": 0.47, + "learning_rate": 1.2863746341013158e-05, + "loss": 1.4112, + "step": 4451 + }, + { + "epoch": 0.47, + "learning_rate": 1.2860239198778085e-05, + "loss": 1.389, + "step": 4452 + }, + { + "epoch": 0.47, + "learning_rate": 1.2856731673344442e-05, + "loss": 1.4066, + "step": 4453 + }, + { + "epoch": 0.47, + "learning_rate": 1.2853223765182165e-05, + "loss": 1.3267, + "step": 4454 + }, + { + "epoch": 0.47, + "learning_rate": 1.2849715474761209e-05, + "loss": 1.3381, + "step": 4455 + }, + { + "epoch": 0.47, + "learning_rate": 1.2846206802551602e-05, + "loss": 1.2882, + "step": 4456 + }, + { + "epoch": 0.47, + "learning_rate": 1.2842697749023414e-05, + "loss": 1.3199, + "step": 4457 + }, + { + "epoch": 0.47, + "learning_rate": 1.2839188314646771e-05, + "loss": 1.3896, + "step": 4458 + }, + { + "epoch": 0.47, + "learning_rate": 1.2835678499891842e-05, + "loss": 1.3186, + "step": 4459 + }, + { + "epoch": 0.47, + "learning_rate": 1.283216830522885e-05, + "loss": 1.3466, + "step": 4460 + }, + { + "epoch": 0.47, + "learning_rate": 1.2828657731128083e-05, + "loss": 1.4678, + "step": 4461 + }, + { + "epoch": 0.47, + "learning_rate": 1.2825146778059857e-05, + "loss": 1.4408, + "step": 4462 + }, + { + "epoch": 0.47, + "learning_rate": 1.2821635446494553e-05, + "loss": 1.3672, + "step": 4463 + }, + { + "epoch": 0.47, + "learning_rate": 1.2818123736902597e-05, + "loss": 1.3836, + "step": 4464 + }, + { + "epoch": 0.47, + "learning_rate": 1.2814611649754472e-05, + "loss": 1.3493, + "step": 4465 + }, + { + "epoch": 0.47, + "learning_rate": 1.2811099185520704e-05, + "loss": 1.3584, + "step": 4466 + }, + { + "epoch": 0.47, + "learning_rate": 1.2807586344671875e-05, + "loss": 1.3551, + "step": 4467 + }, + { + "epoch": 0.47, + "learning_rate": 1.2804073127678612e-05, + "loss": 1.3254, + "step": 4468 + }, + { + "epoch": 0.47, + "learning_rate": 1.28005595350116e-05, + "loss": 1.3405, + "step": 4469 + }, + { + "epoch": 0.47, + "learning_rate": 1.2797045567141568e-05, + "loss": 1.3432, + "step": 4470 + }, + { + "epoch": 0.47, + "learning_rate": 1.2793531224539297e-05, + "loss": 1.4347, + "step": 4471 + }, + { + "epoch": 0.47, + "learning_rate": 1.279001650767562e-05, + "loss": 1.3304, + "step": 4472 + }, + { + "epoch": 0.47, + "learning_rate": 1.278650141702142e-05, + "loss": 1.3244, + "step": 4473 + }, + { + "epoch": 0.47, + "learning_rate": 1.2782985953047625e-05, + "loss": 1.3756, + "step": 4474 + }, + { + "epoch": 0.47, + "learning_rate": 1.2779470116225219e-05, + "loss": 1.5468, + "step": 4475 + }, + { + "epoch": 0.47, + "learning_rate": 1.2775953907025232e-05, + "loss": 1.4316, + "step": 4476 + }, + { + "epoch": 0.47, + "learning_rate": 1.2772437325918752e-05, + "loss": 1.3724, + "step": 4477 + }, + { + "epoch": 0.47, + "learning_rate": 1.27689203733769e-05, + "loss": 1.4458, + "step": 4478 + }, + { + "epoch": 0.47, + "learning_rate": 1.2765403049870865e-05, + "loss": 1.3622, + "step": 4479 + }, + { + "epoch": 0.47, + "learning_rate": 1.2761885355871875e-05, + "loss": 1.3875, + "step": 4480 + }, + { + "epoch": 0.47, + "learning_rate": 1.2758367291851217e-05, + "loss": 1.3577, + "step": 4481 + }, + { + "epoch": 0.47, + "learning_rate": 1.2754848858280211e-05, + "loss": 1.4256, + "step": 4482 + }, + { + "epoch": 0.47, + "learning_rate": 1.2751330055630242e-05, + "loss": 1.3771, + "step": 4483 + }, + { + "epoch": 0.47, + "learning_rate": 1.274781088437274e-05, + "loss": 1.357, + "step": 4484 + }, + { + "epoch": 0.47, + "learning_rate": 1.274429134497918e-05, + "loss": 1.3634, + "step": 4485 + }, + { + "epoch": 0.47, + "learning_rate": 1.2740771437921096e-05, + "loss": 1.3661, + "step": 4486 + }, + { + "epoch": 0.47, + "learning_rate": 1.2737251163670057e-05, + "loss": 1.3819, + "step": 4487 + }, + { + "epoch": 0.47, + "learning_rate": 1.2733730522697696e-05, + "loss": 1.4491, + "step": 4488 + }, + { + "epoch": 0.47, + "learning_rate": 1.2730209515475687e-05, + "loss": 1.3857, + "step": 4489 + }, + { + "epoch": 0.47, + "learning_rate": 1.2726688142475751e-05, + "loss": 1.3837, + "step": 4490 + }, + { + "epoch": 0.47, + "learning_rate": 1.2723166404169663e-05, + "loss": 1.3755, + "step": 4491 + }, + { + "epoch": 0.47, + "learning_rate": 1.271964430102925e-05, + "loss": 1.3767, + "step": 4492 + }, + { + "epoch": 0.47, + "learning_rate": 1.2716121833526376e-05, + "loss": 1.4416, + "step": 4493 + }, + { + "epoch": 0.47, + "learning_rate": 1.2712599002132966e-05, + "loss": 1.5573, + "step": 4494 + }, + { + "epoch": 0.47, + "learning_rate": 1.2709075807320988e-05, + "loss": 1.365, + "step": 4495 + }, + { + "epoch": 0.47, + "learning_rate": 1.270555224956246e-05, + "loss": 1.3862, + "step": 4496 + }, + { + "epoch": 0.47, + "learning_rate": 1.2702028329329445e-05, + "loss": 1.3003, + "step": 4497 + }, + { + "epoch": 0.47, + "learning_rate": 1.2698504047094064e-05, + "loss": 1.3806, + "step": 4498 + }, + { + "epoch": 0.47, + "learning_rate": 1.269497940332847e-05, + "loss": 1.5425, + "step": 4499 + }, + { + "epoch": 0.47, + "learning_rate": 1.269145439850489e-05, + "loss": 1.3541, + "step": 4500 + }, + { + "epoch": 0.47, + "learning_rate": 1.268792903309557e-05, + "loss": 1.4337, + "step": 4501 + }, + { + "epoch": 0.47, + "learning_rate": 1.2684403307572825e-05, + "loss": 1.4004, + "step": 4502 + }, + { + "epoch": 0.47, + "learning_rate": 1.268087722240901e-05, + "loss": 1.9453, + "step": 4503 + }, + { + "epoch": 0.47, + "learning_rate": 1.2677350778076532e-05, + "loss": 1.3907, + "step": 4504 + }, + { + "epoch": 0.47, + "learning_rate": 1.2673823975047839e-05, + "loss": 1.4993, + "step": 4505 + }, + { + "epoch": 0.47, + "learning_rate": 1.2670296813795432e-05, + "loss": 1.4386, + "step": 4506 + }, + { + "epoch": 0.47, + "learning_rate": 1.266676929479187e-05, + "loss": 1.4944, + "step": 4507 + }, + { + "epoch": 0.47, + "learning_rate": 1.266324141850974e-05, + "loss": 1.4311, + "step": 4508 + }, + { + "epoch": 0.47, + "learning_rate": 1.265971318542169e-05, + "loss": 1.3607, + "step": 4509 + }, + { + "epoch": 0.47, + "learning_rate": 1.2656184596000412e-05, + "loss": 1.4007, + "step": 4510 + }, + { + "epoch": 0.47, + "learning_rate": 1.2652655650718645e-05, + "loss": 1.4561, + "step": 4511 + }, + { + "epoch": 0.47, + "learning_rate": 1.2649126350049181e-05, + "loss": 1.4321, + "step": 4512 + }, + { + "epoch": 0.47, + "learning_rate": 1.2645596694464851e-05, + "loss": 1.2856, + "step": 4513 + }, + { + "epoch": 0.47, + "learning_rate": 1.2642066684438543e-05, + "loss": 1.3979, + "step": 4514 + }, + { + "epoch": 0.47, + "learning_rate": 1.2638536320443184e-05, + "loss": 1.4977, + "step": 4515 + }, + { + "epoch": 0.47, + "learning_rate": 1.2635005602951752e-05, + "loss": 1.377, + "step": 4516 + }, + { + "epoch": 0.47, + "learning_rate": 1.2631474532437275e-05, + "loss": 1.4266, + "step": 4517 + }, + { + "epoch": 0.47, + "learning_rate": 1.2627943109372822e-05, + "loss": 1.409, + "step": 4518 + }, + { + "epoch": 0.47, + "learning_rate": 1.2624411334231519e-05, + "loss": 1.3374, + "step": 4519 + }, + { + "epoch": 0.47, + "learning_rate": 1.2620879207486525e-05, + "loss": 1.3765, + "step": 4520 + }, + { + "epoch": 0.47, + "learning_rate": 1.2617346729611061e-05, + "loss": 1.3805, + "step": 4521 + }, + { + "epoch": 0.47, + "learning_rate": 1.2613813901078384e-05, + "loss": 1.3326, + "step": 4522 + }, + { + "epoch": 0.47, + "learning_rate": 1.2610280722361807e-05, + "loss": 1.3909, + "step": 4523 + }, + { + "epoch": 0.47, + "learning_rate": 1.260674719393468e-05, + "loss": 1.3815, + "step": 4524 + }, + { + "epoch": 0.47, + "learning_rate": 1.2603213316270409e-05, + "loss": 1.5589, + "step": 4525 + }, + { + "epoch": 0.47, + "learning_rate": 1.2599679089842437e-05, + "loss": 1.4416, + "step": 4526 + }, + { + "epoch": 0.47, + "learning_rate": 1.259614451512427e-05, + "loss": 1.3529, + "step": 4527 + }, + { + "epoch": 0.47, + "learning_rate": 1.2592609592589437e-05, + "loss": 1.3135, + "step": 4528 + }, + { + "epoch": 0.47, + "learning_rate": 1.2589074322711535e-05, + "loss": 1.4177, + "step": 4529 + }, + { + "epoch": 0.48, + "learning_rate": 1.25855387059642e-05, + "loss": 1.353, + "step": 4530 + }, + { + "epoch": 0.48, + "learning_rate": 1.2582002742821111e-05, + "loss": 1.431, + "step": 4531 + }, + { + "epoch": 0.48, + "learning_rate": 1.2578466433755998e-05, + "loss": 1.3803, + "step": 4532 + }, + { + "epoch": 0.48, + "learning_rate": 1.257492977924263e-05, + "loss": 1.3774, + "step": 4533 + }, + { + "epoch": 0.48, + "learning_rate": 1.2571392779754836e-05, + "loss": 1.4339, + "step": 4534 + }, + { + "epoch": 0.48, + "learning_rate": 1.256785543576648e-05, + "loss": 1.4097, + "step": 4535 + }, + { + "epoch": 0.48, + "learning_rate": 1.2564317747751473e-05, + "loss": 1.4223, + "step": 4536 + }, + { + "epoch": 0.48, + "learning_rate": 1.2560779716183775e-05, + "loss": 1.5148, + "step": 4537 + }, + { + "epoch": 0.48, + "learning_rate": 1.2557241341537394e-05, + "loss": 1.3547, + "step": 4538 + }, + { + "epoch": 0.48, + "learning_rate": 1.255370262428638e-05, + "loss": 1.393, + "step": 4539 + }, + { + "epoch": 0.48, + "learning_rate": 1.2550163564904829e-05, + "loss": 1.3312, + "step": 4540 + }, + { + "epoch": 0.48, + "learning_rate": 1.2546624163866882e-05, + "loss": 1.4193, + "step": 4541 + }, + { + "epoch": 0.48, + "learning_rate": 1.2543084421646735e-05, + "loss": 1.4161, + "step": 4542 + }, + { + "epoch": 0.48, + "learning_rate": 1.2539544338718614e-05, + "loss": 1.4224, + "step": 4543 + }, + { + "epoch": 0.48, + "learning_rate": 1.2536003915556805e-05, + "loss": 1.3484, + "step": 4544 + }, + { + "epoch": 0.48, + "learning_rate": 1.253246315263563e-05, + "loss": 1.4492, + "step": 4545 + }, + { + "epoch": 0.48, + "learning_rate": 1.2528922050429467e-05, + "loss": 1.3549, + "step": 4546 + }, + { + "epoch": 0.48, + "learning_rate": 1.252538060941272e-05, + "loss": 1.45, + "step": 4547 + }, + { + "epoch": 0.48, + "learning_rate": 1.2521838830059865e-05, + "loss": 1.3499, + "step": 4548 + }, + { + "epoch": 0.48, + "learning_rate": 1.2518296712845399e-05, + "loss": 1.3786, + "step": 4549 + }, + { + "epoch": 0.48, + "learning_rate": 1.2514754258243884e-05, + "loss": 1.3394, + "step": 4550 + }, + { + "epoch": 0.48, + "learning_rate": 1.2511211466729909e-05, + "loss": 1.2849, + "step": 4551 + }, + { + "epoch": 0.48, + "learning_rate": 1.250766833877812e-05, + "loss": 1.374, + "step": 4552 + }, + { + "epoch": 0.48, + "learning_rate": 1.2504124874863211e-05, + "loss": 1.3084, + "step": 4553 + }, + { + "epoch": 0.48, + "learning_rate": 1.2500581075459905e-05, + "loss": 1.3348, + "step": 4554 + }, + { + "epoch": 0.48, + "learning_rate": 1.249703694104299e-05, + "loss": 1.3797, + "step": 4555 + }, + { + "epoch": 0.48, + "learning_rate": 1.2493492472087279e-05, + "loss": 1.3371, + "step": 4556 + }, + { + "epoch": 0.48, + "learning_rate": 1.248994766906765e-05, + "loss": 1.3974, + "step": 4557 + }, + { + "epoch": 0.48, + "learning_rate": 1.2486402532459007e-05, + "loss": 1.388, + "step": 4558 + }, + { + "epoch": 0.48, + "learning_rate": 1.2482857062736313e-05, + "loss": 1.3619, + "step": 4559 + }, + { + "epoch": 0.48, + "learning_rate": 1.2479311260374565e-05, + "loss": 1.4123, + "step": 4560 + }, + { + "epoch": 0.48, + "learning_rate": 1.2475765125848814e-05, + "loss": 1.5485, + "step": 4561 + }, + { + "epoch": 0.48, + "learning_rate": 1.247221865963415e-05, + "loss": 1.4965, + "step": 4562 + }, + { + "epoch": 0.48, + "learning_rate": 1.2468671862205705e-05, + "loss": 1.4352, + "step": 4563 + }, + { + "epoch": 0.48, + "learning_rate": 1.246512473403866e-05, + "loss": 1.3935, + "step": 4564 + }, + { + "epoch": 0.48, + "learning_rate": 1.2461577275608243e-05, + "loss": 1.3798, + "step": 4565 + }, + { + "epoch": 0.48, + "learning_rate": 1.2458029487389718e-05, + "loss": 1.4039, + "step": 4566 + }, + { + "epoch": 0.48, + "learning_rate": 1.2454481369858397e-05, + "loss": 1.3723, + "step": 4567 + }, + { + "epoch": 0.48, + "learning_rate": 1.245093292348964e-05, + "loss": 1.3713, + "step": 4568 + }, + { + "epoch": 0.48, + "learning_rate": 1.2447384148758847e-05, + "loss": 1.4083, + "step": 4569 + }, + { + "epoch": 0.48, + "learning_rate": 1.244383504614146e-05, + "loss": 1.2811, + "step": 4570 + }, + { + "epoch": 0.48, + "learning_rate": 1.2440285616112968e-05, + "loss": 1.3509, + "step": 4571 + }, + { + "epoch": 0.48, + "learning_rate": 1.2436735859148905e-05, + "loss": 1.3481, + "step": 4572 + }, + { + "epoch": 0.48, + "learning_rate": 1.2433185775724847e-05, + "loss": 1.4168, + "step": 4573 + }, + { + "epoch": 0.48, + "learning_rate": 1.2429635366316418e-05, + "loss": 1.3671, + "step": 4574 + }, + { + "epoch": 0.48, + "learning_rate": 1.2426084631399271e-05, + "loss": 1.6514, + "step": 4575 + }, + { + "epoch": 0.48, + "learning_rate": 1.2422533571449123e-05, + "loss": 1.3564, + "step": 4576 + }, + { + "epoch": 0.48, + "learning_rate": 1.2418982186941721e-05, + "loss": 1.4586, + "step": 4577 + }, + { + "epoch": 0.48, + "eval_loss": 1.4425245523452759, + "eval_runtime": 77.3853, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 4577 + }, + { + "epoch": 0.48, + "learning_rate": 1.2415430478352858e-05, + "loss": 1.3922, + "step": 4578 + }, + { + "epoch": 0.48, + "learning_rate": 1.2411878446158374e-05, + "loss": 1.3903, + "step": 4579 + }, + { + "epoch": 0.48, + "learning_rate": 1.240832609083415e-05, + "loss": 1.3537, + "step": 4580 + }, + { + "epoch": 0.48, + "learning_rate": 1.2404773412856113e-05, + "loss": 1.356, + "step": 4581 + }, + { + "epoch": 0.48, + "learning_rate": 1.2401220412700223e-05, + "loss": 1.4483, + "step": 4582 + }, + { + "epoch": 0.48, + "learning_rate": 1.2397667090842496e-05, + "loss": 1.3926, + "step": 4583 + }, + { + "epoch": 0.48, + "learning_rate": 1.2394113447758986e-05, + "loss": 1.4816, + "step": 4584 + }, + { + "epoch": 0.48, + "learning_rate": 1.2390559483925788e-05, + "loss": 1.3742, + "step": 4585 + }, + { + "epoch": 0.48, + "learning_rate": 1.2387005199819044e-05, + "loss": 1.4476, + "step": 4586 + }, + { + "epoch": 0.48, + "learning_rate": 1.2383450595914932e-05, + "loss": 1.4029, + "step": 4587 + }, + { + "epoch": 0.48, + "learning_rate": 1.2379895672689683e-05, + "loss": 1.4797, + "step": 4588 + }, + { + "epoch": 0.48, + "learning_rate": 1.2376340430619565e-05, + "loss": 1.3366, + "step": 4589 + }, + { + "epoch": 0.48, + "learning_rate": 1.2372784870180885e-05, + "loss": 1.4226, + "step": 4590 + }, + { + "epoch": 0.48, + "learning_rate": 1.2369228991849997e-05, + "loss": 1.3668, + "step": 4591 + }, + { + "epoch": 0.48, + "learning_rate": 1.2365672796103305e-05, + "loss": 1.4932, + "step": 4592 + }, + { + "epoch": 0.48, + "learning_rate": 1.236211628341724e-05, + "loss": 1.4088, + "step": 4593 + }, + { + "epoch": 0.48, + "learning_rate": 1.2358559454268284e-05, + "loss": 1.3616, + "step": 4594 + }, + { + "epoch": 0.48, + "learning_rate": 1.2355002309132961e-05, + "loss": 1.4345, + "step": 4595 + }, + { + "epoch": 0.48, + "learning_rate": 1.2351444848487844e-05, + "loss": 1.4025, + "step": 4596 + }, + { + "epoch": 0.48, + "learning_rate": 1.2347887072809533e-05, + "loss": 1.3895, + "step": 4597 + }, + { + "epoch": 0.48, + "learning_rate": 1.2344328982574678e-05, + "loss": 1.3326, + "step": 4598 + }, + { + "epoch": 0.48, + "learning_rate": 1.234077057825998e-05, + "loss": 1.4249, + "step": 4599 + }, + { + "epoch": 0.48, + "learning_rate": 1.2337211860342167e-05, + "loss": 1.3649, + "step": 4600 + }, + { + "epoch": 0.48, + "learning_rate": 1.2333652829298016e-05, + "loss": 1.3831, + "step": 4601 + }, + { + "epoch": 0.48, + "learning_rate": 1.2330093485604346e-05, + "loss": 1.3748, + "step": 4602 + }, + { + "epoch": 0.48, + "learning_rate": 1.2326533829738022e-05, + "loss": 1.386, + "step": 4603 + }, + { + "epoch": 0.48, + "learning_rate": 1.2322973862175941e-05, + "loss": 1.3923, + "step": 4604 + }, + { + "epoch": 0.48, + "learning_rate": 1.2319413583395052e-05, + "loss": 1.3638, + "step": 4605 + }, + { + "epoch": 0.48, + "learning_rate": 1.2315852993872335e-05, + "loss": 1.3476, + "step": 4606 + }, + { + "epoch": 0.48, + "learning_rate": 1.2312292094084824e-05, + "loss": 1.3581, + "step": 4607 + }, + { + "epoch": 0.48, + "learning_rate": 1.2308730884509583e-05, + "loss": 1.3554, + "step": 4608 + }, + { + "epoch": 0.48, + "learning_rate": 1.2305169365623724e-05, + "loss": 1.3676, + "step": 4609 + }, + { + "epoch": 0.48, + "learning_rate": 1.2301607537904399e-05, + "loss": 1.24, + "step": 4610 + }, + { + "epoch": 0.48, + "learning_rate": 1.2298045401828803e-05, + "loss": 1.3295, + "step": 4611 + }, + { + "epoch": 0.48, + "learning_rate": 1.2294482957874169e-05, + "loss": 1.5684, + "step": 4612 + }, + { + "epoch": 0.48, + "learning_rate": 1.2290920206517774e-05, + "loss": 1.3403, + "step": 4613 + }, + { + "epoch": 0.48, + "learning_rate": 1.2287357148236933e-05, + "loss": 1.349, + "step": 4614 + }, + { + "epoch": 0.48, + "learning_rate": 1.2283793783509008e-05, + "loss": 1.4261, + "step": 4615 + }, + { + "epoch": 0.48, + "learning_rate": 1.2280230112811395e-05, + "loss": 1.322, + "step": 4616 + }, + { + "epoch": 0.48, + "learning_rate": 1.2276666136621538e-05, + "loss": 1.3399, + "step": 4617 + }, + { + "epoch": 0.48, + "learning_rate": 1.2273101855416912e-05, + "loss": 1.3878, + "step": 4618 + }, + { + "epoch": 0.48, + "learning_rate": 1.2269537269675044e-05, + "loss": 1.4733, + "step": 4619 + }, + { + "epoch": 0.48, + "learning_rate": 1.2265972379873497e-05, + "loss": 1.419, + "step": 4620 + }, + { + "epoch": 0.48, + "learning_rate": 1.226240718648987e-05, + "loss": 1.3918, + "step": 4621 + }, + { + "epoch": 0.48, + "learning_rate": 1.2258841690001815e-05, + "loss": 1.3398, + "step": 4622 + }, + { + "epoch": 0.48, + "learning_rate": 1.225527589088701e-05, + "loss": 1.4091, + "step": 4623 + }, + { + "epoch": 0.48, + "learning_rate": 1.2251709789623185e-05, + "loss": 1.3291, + "step": 4624 + }, + { + "epoch": 0.49, + "learning_rate": 1.2248143386688101e-05, + "loss": 1.4288, + "step": 4625 + }, + { + "epoch": 0.49, + "learning_rate": 1.224457668255957e-05, + "loss": 1.2942, + "step": 4626 + }, + { + "epoch": 0.49, + "learning_rate": 1.2241009677715437e-05, + "loss": 1.4014, + "step": 4627 + }, + { + "epoch": 0.49, + "learning_rate": 1.2237442372633586e-05, + "loss": 1.3823, + "step": 4628 + }, + { + "epoch": 0.49, + "learning_rate": 1.2233874767791945e-05, + "loss": 1.3556, + "step": 4629 + }, + { + "epoch": 0.49, + "learning_rate": 1.2230306863668485e-05, + "loss": 1.411, + "step": 4630 + }, + { + "epoch": 0.49, + "learning_rate": 1.2226738660741212e-05, + "loss": 1.4347, + "step": 4631 + }, + { + "epoch": 0.49, + "learning_rate": 1.2223170159488169e-05, + "loss": 1.3095, + "step": 4632 + }, + { + "epoch": 0.49, + "learning_rate": 1.221960136038745e-05, + "loss": 1.4272, + "step": 4633 + }, + { + "epoch": 0.49, + "learning_rate": 1.221603226391718e-05, + "loss": 1.367, + "step": 4634 + }, + { + "epoch": 0.49, + "learning_rate": 1.2212462870555523e-05, + "loss": 1.3357, + "step": 4635 + }, + { + "epoch": 0.49, + "learning_rate": 1.220889318078069e-05, + "loss": 1.3634, + "step": 4636 + }, + { + "epoch": 0.49, + "learning_rate": 1.2205323195070927e-05, + "loss": 1.4143, + "step": 4637 + }, + { + "epoch": 0.49, + "learning_rate": 1.2201752913904519e-05, + "loss": 1.4865, + "step": 4638 + }, + { + "epoch": 0.49, + "learning_rate": 1.2198182337759794e-05, + "loss": 1.451, + "step": 4639 + }, + { + "epoch": 0.49, + "learning_rate": 1.2194611467115116e-05, + "loss": 1.3953, + "step": 4640 + }, + { + "epoch": 0.49, + "learning_rate": 1.2191040302448887e-05, + "loss": 1.4099, + "step": 4641 + }, + { + "epoch": 0.49, + "learning_rate": 1.2187468844239559e-05, + "loss": 1.3338, + "step": 4642 + }, + { + "epoch": 0.49, + "learning_rate": 1.2183897092965609e-05, + "loss": 1.4392, + "step": 4643 + }, + { + "epoch": 0.49, + "learning_rate": 1.2180325049105559e-05, + "loss": 1.3196, + "step": 4644 + }, + { + "epoch": 0.49, + "learning_rate": 1.2176752713137977e-05, + "loss": 1.3727, + "step": 4645 + }, + { + "epoch": 0.49, + "learning_rate": 1.2173180085541464e-05, + "loss": 1.3118, + "step": 4646 + }, + { + "epoch": 0.49, + "learning_rate": 1.2169607166794655e-05, + "loss": 1.3695, + "step": 4647 + }, + { + "epoch": 0.49, + "learning_rate": 1.2166033957376231e-05, + "loss": 1.3568, + "step": 4648 + }, + { + "epoch": 0.49, + "learning_rate": 1.216246045776491e-05, + "loss": 1.3492, + "step": 4649 + }, + { + "epoch": 0.49, + "learning_rate": 1.2158886668439455e-05, + "loss": 1.3445, + "step": 4650 + }, + { + "epoch": 0.49, + "learning_rate": 1.2155312589878654e-05, + "loss": 1.3756, + "step": 4651 + }, + { + "epoch": 0.49, + "learning_rate": 1.2151738222561344e-05, + "loss": 1.3681, + "step": 4652 + }, + { + "epoch": 0.49, + "learning_rate": 1.2148163566966403e-05, + "loss": 1.4345, + "step": 4653 + }, + { + "epoch": 0.49, + "learning_rate": 1.2144588623572738e-05, + "loss": 1.5102, + "step": 4654 + }, + { + "epoch": 0.49, + "learning_rate": 1.2141013392859297e-05, + "loss": 1.3531, + "step": 4655 + }, + { + "epoch": 0.49, + "learning_rate": 1.2137437875305075e-05, + "loss": 1.3824, + "step": 4656 + }, + { + "epoch": 0.49, + "learning_rate": 1.2133862071389099e-05, + "loss": 1.4227, + "step": 4657 + }, + { + "epoch": 0.49, + "learning_rate": 1.2130285981590433e-05, + "loss": 1.3479, + "step": 4658 + }, + { + "epoch": 0.49, + "learning_rate": 1.2126709606388181e-05, + "loss": 1.381, + "step": 4659 + }, + { + "epoch": 0.49, + "learning_rate": 1.2123132946261485e-05, + "loss": 1.3847, + "step": 4660 + }, + { + "epoch": 0.49, + "learning_rate": 1.2119556001689527e-05, + "loss": 1.3549, + "step": 4661 + }, + { + "epoch": 0.49, + "learning_rate": 1.2115978773151527e-05, + "loss": 1.3754, + "step": 4662 + }, + { + "epoch": 0.49, + "learning_rate": 1.2112401261126736e-05, + "loss": 1.3329, + "step": 4663 + }, + { + "epoch": 0.49, + "learning_rate": 1.2108823466094453e-05, + "loss": 1.4228, + "step": 4664 + }, + { + "epoch": 0.49, + "learning_rate": 1.2105245388534013e-05, + "loss": 1.4138, + "step": 4665 + }, + { + "epoch": 0.49, + "learning_rate": 1.2101667028924782e-05, + "loss": 1.3538, + "step": 4666 + }, + { + "epoch": 0.49, + "learning_rate": 1.2098088387746168e-05, + "loss": 1.4848, + "step": 4667 + }, + { + "epoch": 0.49, + "learning_rate": 1.2094509465477619e-05, + "loss": 1.5719, + "step": 4668 + }, + { + "epoch": 0.49, + "learning_rate": 1.209093026259862e-05, + "loss": 1.3863, + "step": 4669 + }, + { + "epoch": 0.49, + "learning_rate": 1.2087350779588691e-05, + "loss": 1.4425, + "step": 4670 + }, + { + "epoch": 0.49, + "learning_rate": 1.2083771016927386e-05, + "loss": 1.3655, + "step": 4671 + }, + { + "epoch": 0.49, + "learning_rate": 1.208019097509431e-05, + "loss": 1.3629, + "step": 4672 + }, + { + "epoch": 0.49, + "learning_rate": 1.2076610654569092e-05, + "loss": 1.3849, + "step": 4673 + }, + { + "epoch": 0.49, + "learning_rate": 1.20730300558314e-05, + "loss": 1.3763, + "step": 4674 + }, + { + "epoch": 0.49, + "learning_rate": 1.2069449179360945e-05, + "loss": 1.5316, + "step": 4675 + }, + { + "epoch": 0.49, + "learning_rate": 1.2065868025637476e-05, + "loss": 1.2873, + "step": 4676 + }, + { + "epoch": 0.49, + "learning_rate": 1.2062286595140773e-05, + "loss": 1.3642, + "step": 4677 + }, + { + "epoch": 0.49, + "learning_rate": 1.2058704888350652e-05, + "loss": 1.3782, + "step": 4678 + }, + { + "epoch": 0.49, + "learning_rate": 1.2055122905746972e-05, + "loss": 1.4597, + "step": 4679 + }, + { + "epoch": 0.49, + "learning_rate": 1.205154064780963e-05, + "loss": 1.3952, + "step": 4680 + }, + { + "epoch": 0.49, + "learning_rate": 1.2047958115018554e-05, + "loss": 1.4012, + "step": 4681 + }, + { + "epoch": 0.49, + "learning_rate": 1.204437530785371e-05, + "loss": 1.3432, + "step": 4682 + }, + { + "epoch": 0.49, + "learning_rate": 1.2040792226795101e-05, + "loss": 1.4111, + "step": 4683 + }, + { + "epoch": 0.49, + "learning_rate": 1.2037208872322773e-05, + "loss": 1.4357, + "step": 4684 + }, + { + "epoch": 0.49, + "learning_rate": 1.2033625244916803e-05, + "loss": 1.3908, + "step": 4685 + }, + { + "epoch": 0.49, + "learning_rate": 1.2030041345057298e-05, + "loss": 1.3804, + "step": 4686 + }, + { + "epoch": 0.49, + "learning_rate": 1.2026457173224412e-05, + "loss": 1.4523, + "step": 4687 + }, + { + "epoch": 0.49, + "learning_rate": 1.2022872729898336e-05, + "loss": 1.4266, + "step": 4688 + }, + { + "epoch": 0.49, + "learning_rate": 1.201928801555929e-05, + "loss": 1.3345, + "step": 4689 + }, + { + "epoch": 0.49, + "learning_rate": 1.2015703030687532e-05, + "loss": 1.1714, + "step": 4690 + }, + { + "epoch": 0.49, + "learning_rate": 1.2012117775763361e-05, + "loss": 1.3899, + "step": 4691 + }, + { + "epoch": 0.49, + "learning_rate": 1.2008532251267109e-05, + "loss": 1.43, + "step": 4692 + }, + { + "epoch": 0.49, + "learning_rate": 1.2004946457679144e-05, + "loss": 1.4302, + "step": 4693 + }, + { + "epoch": 0.49, + "learning_rate": 1.2001360395479865e-05, + "loss": 1.3452, + "step": 4694 + }, + { + "epoch": 0.49, + "learning_rate": 1.1997774065149716e-05, + "loss": 1.3383, + "step": 4695 + }, + { + "epoch": 0.49, + "learning_rate": 1.1994187467169176e-05, + "loss": 1.3677, + "step": 4696 + }, + { + "epoch": 0.49, + "learning_rate": 1.1990600602018755e-05, + "loss": 1.4486, + "step": 4697 + }, + { + "epoch": 0.49, + "learning_rate": 1.1987013470178998e-05, + "loss": 1.4059, + "step": 4698 + }, + { + "epoch": 0.49, + "learning_rate": 1.198342607213049e-05, + "loss": 1.3558, + "step": 4699 + }, + { + "epoch": 0.49, + "learning_rate": 1.1979838408353854e-05, + "loss": 1.3931, + "step": 4700 + }, + { + "epoch": 0.49, + "learning_rate": 1.197625047932974e-05, + "loss": 1.5409, + "step": 4701 + }, + { + "epoch": 0.49, + "learning_rate": 1.197266228553884e-05, + "loss": 1.4878, + "step": 4702 + }, + { + "epoch": 0.49, + "learning_rate": 1.196907382746188e-05, + "loss": 1.3581, + "step": 4703 + }, + { + "epoch": 0.49, + "learning_rate": 1.1965485105579621e-05, + "loss": 1.3617, + "step": 4704 + }, + { + "epoch": 0.49, + "learning_rate": 1.1961896120372857e-05, + "loss": 1.399, + "step": 4705 + }, + { + "epoch": 0.49, + "learning_rate": 1.1958306872322425e-05, + "loss": 1.3861, + "step": 4706 + }, + { + "epoch": 0.49, + "learning_rate": 1.1954717361909186e-05, + "loss": 1.4719, + "step": 4707 + }, + { + "epoch": 0.49, + "learning_rate": 1.195112758961405e-05, + "loss": 1.393, + "step": 4708 + }, + { + "epoch": 0.49, + "learning_rate": 1.1947537555917947e-05, + "loss": 1.4252, + "step": 4709 + }, + { + "epoch": 0.49, + "learning_rate": 1.194394726130185e-05, + "loss": 1.4187, + "step": 4710 + }, + { + "epoch": 0.49, + "learning_rate": 1.1940356706246772e-05, + "loss": 1.4822, + "step": 4711 + }, + { + "epoch": 0.49, + "learning_rate": 1.193676589123375e-05, + "loss": 1.4259, + "step": 4712 + }, + { + "epoch": 0.49, + "learning_rate": 1.1933174816743857e-05, + "loss": 1.4226, + "step": 4713 + }, + { + "epoch": 0.49, + "learning_rate": 1.1929583483258216e-05, + "loss": 1.3701, + "step": 4714 + }, + { + "epoch": 0.49, + "learning_rate": 1.1925991891257967e-05, + "loss": 1.406, + "step": 4715 + }, + { + "epoch": 0.49, + "learning_rate": 1.1922400041224288e-05, + "loss": 1.4593, + "step": 4716 + }, + { + "epoch": 0.49, + "learning_rate": 1.1918807933638401e-05, + "loss": 1.3443, + "step": 4717 + }, + { + "epoch": 0.49, + "learning_rate": 1.1915215568981552e-05, + "loss": 1.3523, + "step": 4718 + }, + { + "epoch": 0.49, + "learning_rate": 1.1911622947735027e-05, + "loss": 1.3175, + "step": 4719 + }, + { + "epoch": 0.49, + "learning_rate": 1.1908030070380143e-05, + "loss": 1.3974, + "step": 4720 + }, + { + "epoch": 0.5, + "learning_rate": 1.1904436937398257e-05, + "loss": 1.386, + "step": 4721 + }, + { + "epoch": 0.5, + "learning_rate": 1.1900843549270753e-05, + "loss": 1.3684, + "step": 4722 + }, + { + "epoch": 0.5, + "learning_rate": 1.1897249906479054e-05, + "loss": 1.383, + "step": 4723 + }, + { + "epoch": 0.5, + "learning_rate": 1.1893656009504617e-05, + "loss": 1.38, + "step": 4724 + }, + { + "epoch": 0.5, + "learning_rate": 1.1890061858828928e-05, + "loss": 1.3844, + "step": 4725 + }, + { + "epoch": 0.5, + "learning_rate": 1.1886467454933515e-05, + "loss": 1.3252, + "step": 4726 + }, + { + "epoch": 0.5, + "learning_rate": 1.1882872798299934e-05, + "loss": 1.3434, + "step": 4727 + }, + { + "epoch": 0.5, + "learning_rate": 1.1879277889409779e-05, + "loss": 1.4115, + "step": 4728 + }, + { + "epoch": 0.5, + "learning_rate": 1.1875682728744669e-05, + "loss": 1.1911, + "step": 4729 + }, + { + "epoch": 0.5, + "learning_rate": 1.1872087316786272e-05, + "loss": 1.2794, + "step": 4730 + }, + { + "epoch": 0.5, + "learning_rate": 1.1868491654016274e-05, + "loss": 1.3961, + "step": 4731 + }, + { + "epoch": 0.5, + "learning_rate": 1.1864895740916404e-05, + "loss": 1.4965, + "step": 4732 + }, + { + "epoch": 0.5, + "learning_rate": 1.1861299577968419e-05, + "loss": 1.3932, + "step": 4733 + }, + { + "epoch": 0.5, + "learning_rate": 1.185770316565412e-05, + "loss": 1.3926, + "step": 4734 + }, + { + "epoch": 0.5, + "learning_rate": 1.1854106504455327e-05, + "loss": 1.3964, + "step": 4735 + }, + { + "epoch": 0.5, + "learning_rate": 1.1850509594853901e-05, + "loss": 1.3666, + "step": 4736 + }, + { + "epoch": 0.5, + "learning_rate": 1.1846912437331736e-05, + "loss": 1.4364, + "step": 4737 + }, + { + "epoch": 0.5, + "learning_rate": 1.1843315032370762e-05, + "loss": 1.3537, + "step": 4738 + }, + { + "epoch": 0.5, + "learning_rate": 1.1839717380452935e-05, + "loss": 1.4083, + "step": 4739 + }, + { + "epoch": 0.5, + "learning_rate": 1.1836119482060247e-05, + "loss": 1.3881, + "step": 4740 + }, + { + "epoch": 0.5, + "learning_rate": 1.1832521337674727e-05, + "loss": 1.4127, + "step": 4741 + }, + { + "epoch": 0.5, + "learning_rate": 1.1828922947778436e-05, + "loss": 1.3433, + "step": 4742 + }, + { + "epoch": 0.5, + "learning_rate": 1.1825324312853461e-05, + "loss": 1.486, + "step": 4743 + }, + { + "epoch": 0.5, + "learning_rate": 1.1821725433381925e-05, + "loss": 1.335, + "step": 4744 + }, + { + "epoch": 0.5, + "learning_rate": 1.1818126309845993e-05, + "loss": 1.3827, + "step": 4745 + }, + { + "epoch": 0.5, + "learning_rate": 1.181452694272785e-05, + "loss": 1.3146, + "step": 4746 + }, + { + "epoch": 0.5, + "learning_rate": 1.1810927332509717e-05, + "loss": 1.3543, + "step": 4747 + }, + { + "epoch": 0.5, + "learning_rate": 1.1807327479673852e-05, + "loss": 1.3544, + "step": 4748 + }, + { + "epoch": 0.5, + "learning_rate": 1.1803727384702543e-05, + "loss": 1.3677, + "step": 4749 + }, + { + "epoch": 0.5, + "learning_rate": 1.1800127048078111e-05, + "loss": 1.3842, + "step": 4750 + }, + { + "epoch": 0.5, + "learning_rate": 1.1796526470282907e-05, + "loss": 1.3495, + "step": 4751 + }, + { + "epoch": 0.5, + "learning_rate": 1.1792925651799314e-05, + "loss": 1.481, + "step": 4752 + }, + { + "epoch": 0.5, + "learning_rate": 1.1789324593109754e-05, + "loss": 1.3482, + "step": 4753 + }, + { + "epoch": 0.5, + "learning_rate": 1.1785723294696673e-05, + "loss": 1.2805, + "step": 4754 + }, + { + "epoch": 0.5, + "learning_rate": 1.1782121757042555e-05, + "loss": 1.3458, + "step": 4755 + }, + { + "epoch": 0.5, + "learning_rate": 1.1778519980629907e-05, + "loss": 1.3937, + "step": 4756 + }, + { + "epoch": 0.5, + "learning_rate": 1.1774917965941284e-05, + "loss": 1.3873, + "step": 4757 + }, + { + "epoch": 0.5, + "learning_rate": 1.1771315713459258e-05, + "loss": 1.3512, + "step": 4758 + }, + { + "epoch": 0.5, + "learning_rate": 1.1767713223666436e-05, + "loss": 1.4465, + "step": 4759 + }, + { + "epoch": 0.5, + "learning_rate": 1.1764110497045463e-05, + "loss": 1.4233, + "step": 4760 + }, + { + "epoch": 0.5, + "learning_rate": 1.1760507534079011e-05, + "loss": 1.4818, + "step": 4761 + }, + { + "epoch": 0.5, + "learning_rate": 1.1756904335249786e-05, + "loss": 1.2933, + "step": 4762 + }, + { + "epoch": 0.5, + "learning_rate": 1.1753300901040518e-05, + "loss": 1.3524, + "step": 4763 + }, + { + "epoch": 0.5, + "learning_rate": 1.1749697231933981e-05, + "loss": 1.4909, + "step": 4764 + }, + { + "epoch": 0.5, + "learning_rate": 1.1746093328412975e-05, + "loss": 1.2912, + "step": 4765 + }, + { + "epoch": 0.5, + "learning_rate": 1.1742489190960325e-05, + "loss": 1.3372, + "step": 4766 + }, + { + "epoch": 0.5, + "learning_rate": 1.1738884820058893e-05, + "loss": 1.3036, + "step": 4767 + }, + { + "epoch": 0.5, + "learning_rate": 1.1735280216191578e-05, + "loss": 1.3189, + "step": 4768 + }, + { + "epoch": 0.5, + "learning_rate": 1.1731675379841298e-05, + "loss": 1.4146, + "step": 4769 + }, + { + "epoch": 0.5, + "learning_rate": 1.1728070311491013e-05, + "loss": 1.3309, + "step": 4770 + }, + { + "epoch": 0.5, + "learning_rate": 1.1724465011623705e-05, + "loss": 1.3427, + "step": 4771 + }, + { + "epoch": 0.5, + "learning_rate": 1.1720859480722395e-05, + "loss": 1.4033, + "step": 4772 + }, + { + "epoch": 0.5, + "learning_rate": 1.1717253719270135e-05, + "loss": 1.3832, + "step": 4773 + }, + { + "epoch": 0.5, + "learning_rate": 1.1713647727749994e-05, + "loss": 1.4074, + "step": 4774 + }, + { + "epoch": 0.5, + "learning_rate": 1.1710041506645092e-05, + "loss": 1.3579, + "step": 4775 + }, + { + "epoch": 0.5, + "learning_rate": 1.1706435056438564e-05, + "loss": 1.3685, + "step": 4776 + }, + { + "epoch": 0.5, + "eval_loss": 1.436767816543579, + "eval_runtime": 77.4332, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4776 + }, + { + "epoch": 0.5, + "learning_rate": 1.1702828377613584e-05, + "loss": 1.5843, + "step": 4777 + }, + { + "epoch": 0.5, + "learning_rate": 1.1699221470653355e-05, + "loss": 1.4168, + "step": 4778 + }, + { + "epoch": 0.5, + "learning_rate": 1.1695614336041108e-05, + "loss": 1.3515, + "step": 4779 + }, + { + "epoch": 0.5, + "learning_rate": 1.169200697426011e-05, + "loss": 1.3214, + "step": 4780 + }, + { + "epoch": 0.5, + "learning_rate": 1.1688399385793652e-05, + "loss": 1.3728, + "step": 4781 + }, + { + "epoch": 0.5, + "learning_rate": 1.1684791571125054e-05, + "loss": 1.3759, + "step": 4782 + }, + { + "epoch": 0.5, + "learning_rate": 1.1681183530737678e-05, + "loss": 1.4955, + "step": 4783 + }, + { + "epoch": 0.5, + "learning_rate": 1.1677575265114904e-05, + "loss": 1.4284, + "step": 4784 + }, + { + "epoch": 0.5, + "learning_rate": 1.1673966774740151e-05, + "loss": 1.3725, + "step": 4785 + }, + { + "epoch": 0.5, + "learning_rate": 1.1670358060096858e-05, + "loss": 1.3612, + "step": 4786 + }, + { + "epoch": 0.5, + "learning_rate": 1.1666749121668506e-05, + "loss": 1.3021, + "step": 4787 + }, + { + "epoch": 0.5, + "learning_rate": 1.1663139959938597e-05, + "loss": 1.4399, + "step": 4788 + }, + { + "epoch": 0.5, + "learning_rate": 1.1659530575390668e-05, + "loss": 1.3511, + "step": 4789 + }, + { + "epoch": 0.5, + "learning_rate": 1.1655920968508276e-05, + "loss": 1.4211, + "step": 4790 + }, + { + "epoch": 0.5, + "learning_rate": 1.1652311139775028e-05, + "loss": 1.343, + "step": 4791 + }, + { + "epoch": 0.5, + "learning_rate": 1.1648701089674541e-05, + "loss": 1.3838, + "step": 4792 + }, + { + "epoch": 0.5, + "learning_rate": 1.164509081869047e-05, + "loss": 1.342, + "step": 4793 + }, + { + "epoch": 0.5, + "learning_rate": 1.1641480327306494e-05, + "loss": 1.3831, + "step": 4794 + }, + { + "epoch": 0.5, + "learning_rate": 1.1637869616006335e-05, + "loss": 1.4102, + "step": 4795 + }, + { + "epoch": 0.5, + "learning_rate": 1.1634258685273732e-05, + "loss": 1.4184, + "step": 4796 + }, + { + "epoch": 0.5, + "learning_rate": 1.1630647535592455e-05, + "loss": 1.3974, + "step": 4797 + }, + { + "epoch": 0.5, + "learning_rate": 1.1627036167446302e-05, + "loss": 1.251, + "step": 4798 + }, + { + "epoch": 0.5, + "learning_rate": 1.1623424581319113e-05, + "loss": 1.3485, + "step": 4799 + }, + { + "epoch": 0.5, + "learning_rate": 1.1619812777694742e-05, + "loss": 1.3544, + "step": 4800 + }, + { + "epoch": 0.5, + "learning_rate": 1.1616200757057076e-05, + "loss": 1.3772, + "step": 4801 + }, + { + "epoch": 0.5, + "learning_rate": 1.1612588519890038e-05, + "loss": 1.3082, + "step": 4802 + }, + { + "epoch": 0.5, + "learning_rate": 1.160897606667757e-05, + "loss": 1.3634, + "step": 4803 + }, + { + "epoch": 0.5, + "learning_rate": 1.1605363397903655e-05, + "loss": 1.3682, + "step": 4804 + }, + { + "epoch": 0.5, + "learning_rate": 1.1601750514052288e-05, + "loss": 1.3258, + "step": 4805 + }, + { + "epoch": 0.5, + "learning_rate": 1.1598137415607511e-05, + "loss": 1.279, + "step": 4806 + }, + { + "epoch": 0.5, + "learning_rate": 1.1594524103053382e-05, + "loss": 1.3759, + "step": 4807 + }, + { + "epoch": 0.5, + "learning_rate": 1.1590910576873995e-05, + "loss": 1.5404, + "step": 4808 + }, + { + "epoch": 0.5, + "learning_rate": 1.1587296837553463e-05, + "loss": 1.4949, + "step": 4809 + }, + { + "epoch": 0.5, + "learning_rate": 1.1583682885575943e-05, + "loss": 1.3501, + "step": 4810 + }, + { + "epoch": 0.5, + "learning_rate": 1.1580068721425608e-05, + "loss": 1.3898, + "step": 4811 + }, + { + "epoch": 0.5, + "learning_rate": 1.157645434558666e-05, + "loss": 1.3265, + "step": 4812 + }, + { + "epoch": 0.5, + "learning_rate": 1.1572839758543338e-05, + "loss": 1.3454, + "step": 4813 + }, + { + "epoch": 0.5, + "learning_rate": 1.1569224960779899e-05, + "loss": 1.4065, + "step": 4814 + }, + { + "epoch": 0.5, + "learning_rate": 1.156560995278064e-05, + "loss": 1.4932, + "step": 4815 + }, + { + "epoch": 0.51, + "learning_rate": 1.156199473502987e-05, + "loss": 1.4224, + "step": 4816 + }, + { + "epoch": 0.51, + "learning_rate": 1.1558379308011937e-05, + "loss": 1.3884, + "step": 4817 + }, + { + "epoch": 0.51, + "learning_rate": 1.1554763672211222e-05, + "loss": 1.3355, + "step": 4818 + }, + { + "epoch": 0.51, + "learning_rate": 1.1551147828112124e-05, + "loss": 1.4281, + "step": 4819 + }, + { + "epoch": 0.51, + "learning_rate": 1.1547531776199072e-05, + "loss": 1.3148, + "step": 4820 + }, + { + "epoch": 0.51, + "learning_rate": 1.1543915516956523e-05, + "loss": 1.3255, + "step": 4821 + }, + { + "epoch": 0.51, + "learning_rate": 1.1540299050868966e-05, + "loss": 1.3361, + "step": 4822 + }, + { + "epoch": 0.51, + "learning_rate": 1.1536682378420912e-05, + "loss": 1.3377, + "step": 4823 + }, + { + "epoch": 0.51, + "learning_rate": 1.1533065500096901e-05, + "loss": 1.4205, + "step": 4824 + }, + { + "epoch": 0.51, + "learning_rate": 1.1529448416381505e-05, + "loss": 1.4193, + "step": 4825 + }, + { + "epoch": 0.51, + "learning_rate": 1.1525831127759322e-05, + "loss": 1.37, + "step": 4826 + }, + { + "epoch": 0.51, + "learning_rate": 1.1522213634714971e-05, + "loss": 1.3642, + "step": 4827 + }, + { + "epoch": 0.51, + "learning_rate": 1.1518595937733103e-05, + "loss": 1.4834, + "step": 4828 + }, + { + "epoch": 0.51, + "learning_rate": 1.1514978037298402e-05, + "loss": 1.2864, + "step": 4829 + }, + { + "epoch": 0.51, + "learning_rate": 1.1511359933895567e-05, + "loss": 1.3468, + "step": 4830 + }, + { + "epoch": 0.51, + "learning_rate": 1.1507741628009337e-05, + "loss": 1.328, + "step": 4831 + }, + { + "epoch": 0.51, + "learning_rate": 1.1504123120124466e-05, + "loss": 1.3489, + "step": 4832 + }, + { + "epoch": 0.51, + "learning_rate": 1.1500504410725746e-05, + "loss": 1.4031, + "step": 4833 + }, + { + "epoch": 0.51, + "learning_rate": 1.149688550029799e-05, + "loss": 1.3482, + "step": 4834 + }, + { + "epoch": 0.51, + "learning_rate": 1.1493266389326037e-05, + "loss": 1.3674, + "step": 4835 + }, + { + "epoch": 0.51, + "learning_rate": 1.1489647078294753e-05, + "loss": 1.2895, + "step": 4836 + }, + { + "epoch": 0.51, + "learning_rate": 1.148602756768904e-05, + "loss": 1.4071, + "step": 4837 + }, + { + "epoch": 0.51, + "learning_rate": 1.1482407857993814e-05, + "loss": 1.5218, + "step": 4838 + }, + { + "epoch": 0.51, + "learning_rate": 1.1478787949694024e-05, + "loss": 1.4577, + "step": 4839 + }, + { + "epoch": 0.51, + "learning_rate": 1.1475167843274643e-05, + "loss": 1.3817, + "step": 4840 + }, + { + "epoch": 0.51, + "learning_rate": 1.1471547539220678e-05, + "loss": 1.3072, + "step": 4841 + }, + { + "epoch": 0.51, + "learning_rate": 1.146792703801715e-05, + "loss": 1.3737, + "step": 4842 + }, + { + "epoch": 0.51, + "learning_rate": 1.1464306340149119e-05, + "loss": 1.4001, + "step": 4843 + }, + { + "epoch": 0.51, + "learning_rate": 1.1460685446101658e-05, + "loss": 1.3963, + "step": 4844 + }, + { + "epoch": 0.51, + "learning_rate": 1.1457064356359882e-05, + "loss": 1.4061, + "step": 4845 + }, + { + "epoch": 0.51, + "learning_rate": 1.145344307140892e-05, + "loss": 1.4211, + "step": 4846 + }, + { + "epoch": 0.51, + "learning_rate": 1.144982159173393e-05, + "loss": 1.3197, + "step": 4847 + }, + { + "epoch": 0.51, + "learning_rate": 1.14461999178201e-05, + "loss": 1.3549, + "step": 4848 + }, + { + "epoch": 0.51, + "learning_rate": 1.1442578050152639e-05, + "loss": 1.3889, + "step": 4849 + }, + { + "epoch": 0.51, + "learning_rate": 1.1438955989216787e-05, + "loss": 1.3847, + "step": 4850 + }, + { + "epoch": 0.51, + "learning_rate": 1.1435333735497803e-05, + "loss": 1.3586, + "step": 4851 + }, + { + "epoch": 0.51, + "learning_rate": 1.1431711289480978e-05, + "loss": 1.503, + "step": 4852 + }, + { + "epoch": 0.51, + "learning_rate": 1.1428088651651627e-05, + "loss": 1.3654, + "step": 4853 + }, + { + "epoch": 0.51, + "learning_rate": 1.1424465822495092e-05, + "loss": 1.3741, + "step": 4854 + }, + { + "epoch": 0.51, + "learning_rate": 1.1420842802496737e-05, + "loss": 1.5437, + "step": 4855 + }, + { + "epoch": 0.51, + "learning_rate": 1.1417219592141953e-05, + "loss": 1.2179, + "step": 4856 + }, + { + "epoch": 0.51, + "learning_rate": 1.1413596191916159e-05, + "loss": 1.3939, + "step": 4857 + }, + { + "epoch": 0.51, + "learning_rate": 1.1409972602304796e-05, + "loss": 1.3383, + "step": 4858 + }, + { + "epoch": 0.51, + "learning_rate": 1.140634882379333e-05, + "loss": 1.3664, + "step": 4859 + }, + { + "epoch": 0.51, + "learning_rate": 1.1402724856867258e-05, + "loss": 1.4002, + "step": 4860 + }, + { + "epoch": 0.51, + "learning_rate": 1.1399100702012098e-05, + "loss": 1.2975, + "step": 4861 + }, + { + "epoch": 0.51, + "learning_rate": 1.1395476359713394e-05, + "loss": 1.3564, + "step": 4862 + }, + { + "epoch": 0.51, + "learning_rate": 1.1391851830456708e-05, + "loss": 1.3574, + "step": 4863 + }, + { + "epoch": 0.51, + "learning_rate": 1.1388227114727644e-05, + "loss": 1.3407, + "step": 4864 + }, + { + "epoch": 0.51, + "learning_rate": 1.1384602213011815e-05, + "loss": 1.3603, + "step": 4865 + }, + { + "epoch": 0.51, + "learning_rate": 1.1380977125794866e-05, + "loss": 1.3465, + "step": 4866 + }, + { + "epoch": 0.51, + "learning_rate": 1.1377351853562461e-05, + "loss": 1.3744, + "step": 4867 + }, + { + "epoch": 0.51, + "learning_rate": 1.1373726396800304e-05, + "loss": 1.3248, + "step": 4868 + }, + { + "epoch": 0.51, + "learning_rate": 1.1370100755994102e-05, + "loss": 1.3352, + "step": 4869 + }, + { + "epoch": 0.51, + "learning_rate": 1.1366474931629603e-05, + "loss": 1.3299, + "step": 4870 + }, + { + "epoch": 0.51, + "learning_rate": 1.1362848924192575e-05, + "loss": 1.344, + "step": 4871 + }, + { + "epoch": 0.51, + "learning_rate": 1.1359222734168809e-05, + "loss": 1.3209, + "step": 4872 + }, + { + "epoch": 0.51, + "learning_rate": 1.135559636204412e-05, + "loss": 1.3927, + "step": 4873 + }, + { + "epoch": 0.51, + "learning_rate": 1.1351969808304349e-05, + "loss": 1.3717, + "step": 4874 + }, + { + "epoch": 0.51, + "learning_rate": 1.1348343073435362e-05, + "loss": 1.3813, + "step": 4875 + }, + { + "epoch": 0.51, + "learning_rate": 1.1344716157923046e-05, + "loss": 1.236, + "step": 4876 + }, + { + "epoch": 0.51, + "learning_rate": 1.1341089062253319e-05, + "loss": 1.2591, + "step": 4877 + }, + { + "epoch": 0.51, + "learning_rate": 1.1337461786912112e-05, + "loss": 1.3211, + "step": 4878 + }, + { + "epoch": 0.51, + "learning_rate": 1.1333834332385394e-05, + "loss": 1.4534, + "step": 4879 + }, + { + "epoch": 0.51, + "learning_rate": 1.1330206699159145e-05, + "loss": 1.346, + "step": 4880 + }, + { + "epoch": 0.51, + "learning_rate": 1.132657888771938e-05, + "loss": 1.3952, + "step": 4881 + }, + { + "epoch": 0.51, + "learning_rate": 1.1322950898552125e-05, + "loss": 1.3008, + "step": 4882 + }, + { + "epoch": 0.51, + "learning_rate": 1.1319322732143445e-05, + "loss": 1.3201, + "step": 4883 + }, + { + "epoch": 0.51, + "learning_rate": 1.1315694388979416e-05, + "loss": 1.3761, + "step": 4884 + }, + { + "epoch": 0.51, + "learning_rate": 1.1312065869546147e-05, + "loss": 1.343, + "step": 4885 + }, + { + "epoch": 0.51, + "learning_rate": 1.1308437174329761e-05, + "loss": 1.3741, + "step": 4886 + }, + { + "epoch": 0.51, + "learning_rate": 1.1304808303816413e-05, + "loss": 1.402, + "step": 4887 + }, + { + "epoch": 0.51, + "learning_rate": 1.130117925849228e-05, + "loss": 1.3834, + "step": 4888 + }, + { + "epoch": 0.51, + "learning_rate": 1.1297550038843559e-05, + "loss": 1.3342, + "step": 4889 + }, + { + "epoch": 0.51, + "learning_rate": 1.1293920645356471e-05, + "loss": 1.3207, + "step": 4890 + }, + { + "epoch": 0.51, + "learning_rate": 1.1290291078517264e-05, + "loss": 1.4274, + "step": 4891 + }, + { + "epoch": 0.51, + "learning_rate": 1.1286661338812203e-05, + "loss": 1.328, + "step": 4892 + }, + { + "epoch": 0.51, + "learning_rate": 1.1283031426727584e-05, + "loss": 1.3823, + "step": 4893 + }, + { + "epoch": 0.51, + "learning_rate": 1.127940134274972e-05, + "loss": 1.3612, + "step": 4894 + }, + { + "epoch": 0.51, + "learning_rate": 1.127577108736495e-05, + "loss": 1.375, + "step": 4895 + }, + { + "epoch": 0.51, + "learning_rate": 1.1272140661059636e-05, + "loss": 1.3531, + "step": 4896 + }, + { + "epoch": 0.51, + "learning_rate": 1.1268510064320155e-05, + "loss": 1.3636, + "step": 4897 + }, + { + "epoch": 0.51, + "learning_rate": 1.1264879297632923e-05, + "loss": 1.3524, + "step": 4898 + }, + { + "epoch": 0.51, + "learning_rate": 1.1261248361484363e-05, + "loss": 1.3865, + "step": 4899 + }, + { + "epoch": 0.51, + "learning_rate": 1.125761725636093e-05, + "loss": 1.4069, + "step": 4900 + }, + { + "epoch": 0.51, + "learning_rate": 1.1253985982749098e-05, + "loss": 1.4643, + "step": 4901 + }, + { + "epoch": 0.51, + "learning_rate": 1.1250354541135364e-05, + "loss": 1.4506, + "step": 4902 + }, + { + "epoch": 0.51, + "learning_rate": 1.124672293200625e-05, + "loss": 1.3857, + "step": 4903 + }, + { + "epoch": 0.51, + "learning_rate": 1.1243091155848295e-05, + "loss": 1.3554, + "step": 4904 + }, + { + "epoch": 0.51, + "learning_rate": 1.1239459213148065e-05, + "loss": 1.4071, + "step": 4905 + }, + { + "epoch": 0.51, + "learning_rate": 1.1235827104392148e-05, + "loss": 1.3981, + "step": 4906 + }, + { + "epoch": 0.51, + "learning_rate": 1.1232194830067153e-05, + "loss": 1.4913, + "step": 4907 + }, + { + "epoch": 0.51, + "learning_rate": 1.1228562390659712e-05, + "loss": 1.3343, + "step": 4908 + }, + { + "epoch": 0.51, + "learning_rate": 1.1224929786656474e-05, + "loss": 1.3832, + "step": 4909 + }, + { + "epoch": 0.51, + "learning_rate": 1.122129701854412e-05, + "loss": 1.367, + "step": 4910 + }, + { + "epoch": 0.51, + "learning_rate": 1.1217664086809345e-05, + "loss": 1.4108, + "step": 4911 + }, + { + "epoch": 0.52, + "learning_rate": 1.1214030991938872e-05, + "loss": 1.3981, + "step": 4912 + }, + { + "epoch": 0.52, + "learning_rate": 1.1210397734419436e-05, + "loss": 1.5266, + "step": 4913 + }, + { + "epoch": 0.52, + "learning_rate": 1.1206764314737806e-05, + "loss": 1.337, + "step": 4914 + }, + { + "epoch": 0.52, + "learning_rate": 1.1203130733380765e-05, + "loss": 1.3784, + "step": 4915 + }, + { + "epoch": 0.52, + "learning_rate": 1.1199496990835117e-05, + "loss": 1.3048, + "step": 4916 + }, + { + "epoch": 0.52, + "learning_rate": 1.1195863087587692e-05, + "loss": 1.2977, + "step": 4917 + }, + { + "epoch": 0.52, + "learning_rate": 1.1192229024125344e-05, + "loss": 1.3304, + "step": 4918 + }, + { + "epoch": 0.52, + "learning_rate": 1.1188594800934938e-05, + "loss": 1.4102, + "step": 4919 + }, + { + "epoch": 0.52, + "learning_rate": 1.1184960418503366e-05, + "loss": 1.3932, + "step": 4920 + }, + { + "epoch": 0.52, + "learning_rate": 1.1181325877317547e-05, + "loss": 1.4985, + "step": 4921 + }, + { + "epoch": 0.52, + "learning_rate": 1.1177691177864415e-05, + "loss": 1.4596, + "step": 4922 + }, + { + "epoch": 0.52, + "learning_rate": 1.1174056320630924e-05, + "loss": 1.3559, + "step": 4923 + }, + { + "epoch": 0.52, + "learning_rate": 1.117042130610405e-05, + "loss": 1.4128, + "step": 4924 + }, + { + "epoch": 0.52, + "learning_rate": 1.1166786134770795e-05, + "loss": 1.3343, + "step": 4925 + }, + { + "epoch": 0.52, + "learning_rate": 1.116315080711818e-05, + "loss": 1.332, + "step": 4926 + }, + { + "epoch": 0.52, + "learning_rate": 1.115951532363324e-05, + "loss": 1.3616, + "step": 4927 + }, + { + "epoch": 0.52, + "learning_rate": 1.1155879684803041e-05, + "loss": 1.4074, + "step": 4928 + }, + { + "epoch": 0.52, + "learning_rate": 1.1152243891114665e-05, + "loss": 1.303, + "step": 4929 + }, + { + "epoch": 0.52, + "learning_rate": 1.1148607943055212e-05, + "loss": 1.4799, + "step": 4930 + }, + { + "epoch": 0.52, + "learning_rate": 1.1144971841111807e-05, + "loss": 1.3881, + "step": 4931 + }, + { + "epoch": 0.52, + "learning_rate": 1.1141335585771593e-05, + "loss": 1.338, + "step": 4932 + }, + { + "epoch": 0.52, + "learning_rate": 1.1137699177521738e-05, + "loss": 1.3289, + "step": 4933 + }, + { + "epoch": 0.52, + "learning_rate": 1.1134062616849426e-05, + "loss": 1.377, + "step": 4934 + }, + { + "epoch": 0.52, + "learning_rate": 1.1130425904241862e-05, + "loss": 1.3596, + "step": 4935 + }, + { + "epoch": 0.52, + "learning_rate": 1.112678904018627e-05, + "loss": 1.4264, + "step": 4936 + }, + { + "epoch": 0.52, + "learning_rate": 1.1123152025169898e-05, + "loss": 1.3526, + "step": 4937 + }, + { + "epoch": 0.52, + "learning_rate": 1.1119514859680016e-05, + "loss": 1.3271, + "step": 4938 + }, + { + "epoch": 0.52, + "learning_rate": 1.1115877544203905e-05, + "loss": 1.3907, + "step": 4939 + }, + { + "epoch": 0.52, + "learning_rate": 1.1112240079228878e-05, + "loss": 1.3415, + "step": 4940 + }, + { + "epoch": 0.52, + "learning_rate": 1.1108602465242258e-05, + "loss": 1.3875, + "step": 4941 + }, + { + "epoch": 0.52, + "learning_rate": 1.110496470273139e-05, + "loss": 1.3964, + "step": 4942 + }, + { + "epoch": 0.52, + "learning_rate": 1.1101326792183645e-05, + "loss": 1.3448, + "step": 4943 + }, + { + "epoch": 0.52, + "learning_rate": 1.1097688734086407e-05, + "loss": 1.3522, + "step": 4944 + }, + { + "epoch": 0.52, + "learning_rate": 1.1094050528927082e-05, + "loss": 1.2742, + "step": 4945 + }, + { + "epoch": 0.52, + "learning_rate": 1.1090412177193097e-05, + "loss": 1.417, + "step": 4946 + }, + { + "epoch": 0.52, + "learning_rate": 1.1086773679371898e-05, + "loss": 1.3993, + "step": 4947 + }, + { + "epoch": 0.52, + "learning_rate": 1.108313503595095e-05, + "loss": 1.3783, + "step": 4948 + }, + { + "epoch": 0.52, + "learning_rate": 1.1079496247417736e-05, + "loss": 1.3975, + "step": 4949 + }, + { + "epoch": 0.52, + "learning_rate": 1.1075857314259763e-05, + "loss": 1.4256, + "step": 4950 + }, + { + "epoch": 0.52, + "learning_rate": 1.1072218236964551e-05, + "loss": 1.3547, + "step": 4951 + }, + { + "epoch": 0.52, + "learning_rate": 1.106857901601965e-05, + "loss": 1.4243, + "step": 4952 + }, + { + "epoch": 0.52, + "learning_rate": 1.1064939651912612e-05, + "loss": 1.4259, + "step": 4953 + }, + { + "epoch": 0.52, + "learning_rate": 1.1061300145131027e-05, + "loss": 1.4323, + "step": 4954 + }, + { + "epoch": 0.52, + "learning_rate": 1.1057660496162488e-05, + "loss": 1.3608, + "step": 4955 + }, + { + "epoch": 0.52, + "learning_rate": 1.1054020705494622e-05, + "loss": 1.3703, + "step": 4956 + }, + { + "epoch": 0.52, + "learning_rate": 1.105038077361506e-05, + "loss": 1.3953, + "step": 4957 + }, + { + "epoch": 0.52, + "learning_rate": 1.1046740701011467e-05, + "loss": 1.392, + "step": 4958 + }, + { + "epoch": 0.52, + "learning_rate": 1.1043100488171513e-05, + "loss": 1.4101, + "step": 4959 + }, + { + "epoch": 0.52, + "learning_rate": 1.1039460135582894e-05, + "loss": 1.5432, + "step": 4960 + }, + { + "epoch": 0.52, + "learning_rate": 1.1035819643733326e-05, + "loss": 1.3822, + "step": 4961 + }, + { + "epoch": 0.52, + "learning_rate": 1.103217901311054e-05, + "loss": 1.3816, + "step": 4962 + }, + { + "epoch": 0.52, + "learning_rate": 1.1028538244202287e-05, + "loss": 1.3137, + "step": 4963 + }, + { + "epoch": 0.52, + "learning_rate": 1.102489733749634e-05, + "loss": 1.3791, + "step": 4964 + }, + { + "epoch": 0.52, + "learning_rate": 1.102125629348048e-05, + "loss": 1.3751, + "step": 4965 + }, + { + "epoch": 0.52, + "learning_rate": 1.1017615112642518e-05, + "loss": 1.3287, + "step": 4966 + }, + { + "epoch": 0.52, + "learning_rate": 1.1013973795470277e-05, + "loss": 1.3187, + "step": 4967 + }, + { + "epoch": 0.52, + "learning_rate": 1.1010332342451602e-05, + "loss": 1.3174, + "step": 4968 + }, + { + "epoch": 0.52, + "learning_rate": 1.1006690754074351e-05, + "loss": 1.3544, + "step": 4969 + }, + { + "epoch": 0.52, + "learning_rate": 1.1003049030826404e-05, + "loss": 1.3789, + "step": 4970 + }, + { + "epoch": 0.52, + "learning_rate": 1.0999407173195662e-05, + "loss": 1.4561, + "step": 4971 + }, + { + "epoch": 0.52, + "learning_rate": 1.0995765181670039e-05, + "loss": 1.3963, + "step": 4972 + }, + { + "epoch": 0.52, + "learning_rate": 1.0992123056737464e-05, + "loss": 1.3519, + "step": 4973 + }, + { + "epoch": 0.52, + "learning_rate": 1.0988480798885892e-05, + "loss": 1.3945, + "step": 4974 + }, + { + "epoch": 0.52, + "learning_rate": 1.0984838408603294e-05, + "loss": 1.4572, + "step": 4975 + }, + { + "epoch": 0.52, + "eval_loss": 1.4313459396362305, + "eval_runtime": 77.4808, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 4975 + }, + { + "epoch": 0.52, + "learning_rate": 1.0981195886377652e-05, + "loss": 1.3493, + "step": 4976 + }, + { + "epoch": 0.52, + "learning_rate": 1.0977553232696972e-05, + "loss": 1.3734, + "step": 4977 + }, + { + "epoch": 0.52, + "learning_rate": 1.0973910448049273e-05, + "loss": 1.3484, + "step": 4978 + }, + { + "epoch": 0.52, + "learning_rate": 1.09702675329226e-05, + "loss": 1.4288, + "step": 4979 + }, + { + "epoch": 0.52, + "learning_rate": 1.096662448780501e-05, + "loss": 1.3748, + "step": 4980 + }, + { + "epoch": 0.52, + "learning_rate": 1.0962981313184575e-05, + "loss": 1.3485, + "step": 4981 + }, + { + "epoch": 0.52, + "learning_rate": 1.0959338009549383e-05, + "loss": 1.3606, + "step": 4982 + }, + { + "epoch": 0.52, + "learning_rate": 1.095569457738755e-05, + "loss": 1.3963, + "step": 4983 + }, + { + "epoch": 0.52, + "learning_rate": 1.09520510171872e-05, + "loss": 1.2986, + "step": 4984 + }, + { + "epoch": 0.52, + "learning_rate": 1.0948407329436474e-05, + "loss": 1.3505, + "step": 4985 + }, + { + "epoch": 0.52, + "learning_rate": 1.0944763514623535e-05, + "loss": 1.4649, + "step": 4986 + }, + { + "epoch": 0.52, + "learning_rate": 1.0941119573236564e-05, + "loss": 1.4743, + "step": 4987 + }, + { + "epoch": 0.52, + "learning_rate": 1.0937475505763745e-05, + "loss": 1.3934, + "step": 4988 + }, + { + "epoch": 0.52, + "learning_rate": 1.09338313126933e-05, + "loss": 1.4225, + "step": 4989 + }, + { + "epoch": 0.52, + "learning_rate": 1.0930186994513453e-05, + "loss": 1.3626, + "step": 4990 + }, + { + "epoch": 0.52, + "learning_rate": 1.0926542551712446e-05, + "loss": 1.3614, + "step": 4991 + }, + { + "epoch": 0.52, + "learning_rate": 1.0922897984778546e-05, + "loss": 1.3766, + "step": 4992 + }, + { + "epoch": 0.52, + "learning_rate": 1.0919253294200027e-05, + "loss": 1.3295, + "step": 4993 + }, + { + "epoch": 0.52, + "learning_rate": 1.091560848046519e-05, + "loss": 1.3802, + "step": 4994 + }, + { + "epoch": 0.52, + "learning_rate": 1.091196354406234e-05, + "loss": 1.2976, + "step": 4995 + }, + { + "epoch": 0.52, + "learning_rate": 1.090831848547981e-05, + "loss": 1.3928, + "step": 4996 + }, + { + "epoch": 0.52, + "learning_rate": 1.0904673305205937e-05, + "loss": 1.3717, + "step": 4997 + }, + { + "epoch": 0.52, + "learning_rate": 1.0901028003729089e-05, + "loss": 1.3164, + "step": 4998 + }, + { + "epoch": 0.52, + "learning_rate": 1.0897382581537638e-05, + "loss": 1.3462, + "step": 4999 + }, + { + "epoch": 0.52, + "learning_rate": 1.0893737039119981e-05, + "loss": 1.3643, + "step": 5000 + }, + { + "epoch": 0.52, + "learning_rate": 1.089009137696452e-05, + "loss": 1.3452, + "step": 5001 + }, + { + "epoch": 0.52, + "learning_rate": 1.0886445595559686e-05, + "loss": 1.358, + "step": 5002 + }, + { + "epoch": 0.52, + "learning_rate": 1.0882799695393922e-05, + "loss": 1.4569, + "step": 5003 + }, + { + "epoch": 0.52, + "learning_rate": 1.0879153676955681e-05, + "loss": 1.2832, + "step": 5004 + }, + { + "epoch": 0.52, + "learning_rate": 1.0875507540733435e-05, + "loss": 1.4089, + "step": 5005 + }, + { + "epoch": 0.52, + "learning_rate": 1.087186128721567e-05, + "loss": 1.3178, + "step": 5006 + }, + { + "epoch": 0.53, + "learning_rate": 1.0868214916890902e-05, + "loss": 1.4883, + "step": 5007 + }, + { + "epoch": 0.53, + "learning_rate": 1.0864568430247638e-05, + "loss": 1.3991, + "step": 5008 + }, + { + "epoch": 0.53, + "learning_rate": 1.0860921827774422e-05, + "loss": 1.4507, + "step": 5009 + }, + { + "epoch": 0.53, + "learning_rate": 1.08572751099598e-05, + "loss": 1.3578, + "step": 5010 + }, + { + "epoch": 0.53, + "learning_rate": 1.0853628277292341e-05, + "loss": 1.4231, + "step": 5011 + }, + { + "epoch": 0.53, + "learning_rate": 1.0849981330260624e-05, + "loss": 1.4835, + "step": 5012 + }, + { + "epoch": 0.53, + "learning_rate": 1.084633426935325e-05, + "loss": 1.4511, + "step": 5013 + }, + { + "epoch": 0.53, + "learning_rate": 1.084268709505883e-05, + "loss": 1.3889, + "step": 5014 + }, + { + "epoch": 0.53, + "learning_rate": 1.0839039807865992e-05, + "loss": 1.355, + "step": 5015 + }, + { + "epoch": 0.53, + "learning_rate": 1.0835392408263375e-05, + "loss": 1.4829, + "step": 5016 + }, + { + "epoch": 0.53, + "learning_rate": 1.0831744896739643e-05, + "loss": 1.3019, + "step": 5017 + }, + { + "epoch": 0.53, + "learning_rate": 1.0828097273783465e-05, + "loss": 1.3418, + "step": 5018 + }, + { + "epoch": 0.53, + "learning_rate": 1.082444953988353e-05, + "loss": 1.4276, + "step": 5019 + }, + { + "epoch": 0.53, + "learning_rate": 1.0820801695528537e-05, + "loss": 1.2816, + "step": 5020 + }, + { + "epoch": 0.53, + "learning_rate": 1.081715374120721e-05, + "loss": 1.5144, + "step": 5021 + }, + { + "epoch": 0.53, + "learning_rate": 1.0813505677408278e-05, + "loss": 1.4063, + "step": 5022 + }, + { + "epoch": 0.53, + "learning_rate": 1.0809857504620487e-05, + "loss": 1.4011, + "step": 5023 + }, + { + "epoch": 0.53, + "learning_rate": 1.0806209223332598e-05, + "loss": 1.373, + "step": 5024 + }, + { + "epoch": 0.53, + "learning_rate": 1.0802560834033388e-05, + "loss": 1.6259, + "step": 5025 + }, + { + "epoch": 0.53, + "learning_rate": 1.0798912337211648e-05, + "loss": 1.4487, + "step": 5026 + }, + { + "epoch": 0.53, + "learning_rate": 1.0795263733356184e-05, + "loss": 1.3056, + "step": 5027 + }, + { + "epoch": 0.53, + "learning_rate": 1.079161502295581e-05, + "loss": 1.2871, + "step": 5028 + }, + { + "epoch": 0.53, + "learning_rate": 1.0787966206499363e-05, + "loss": 1.413, + "step": 5029 + }, + { + "epoch": 0.53, + "learning_rate": 1.0784317284475694e-05, + "loss": 1.3682, + "step": 5030 + }, + { + "epoch": 0.53, + "learning_rate": 1.0780668257373659e-05, + "loss": 1.493, + "step": 5031 + }, + { + "epoch": 0.53, + "learning_rate": 1.0777019125682136e-05, + "loss": 1.6823, + "step": 5032 + }, + { + "epoch": 0.53, + "learning_rate": 1.0773369889890015e-05, + "loss": 1.358, + "step": 5033 + }, + { + "epoch": 0.53, + "learning_rate": 1.07697205504862e-05, + "loss": 1.3532, + "step": 5034 + }, + { + "epoch": 0.53, + "learning_rate": 1.0766071107959608e-05, + "loss": 1.3432, + "step": 5035 + }, + { + "epoch": 0.53, + "learning_rate": 1.0762421562799173e-05, + "loss": 1.3575, + "step": 5036 + }, + { + "epoch": 0.53, + "learning_rate": 1.0758771915493838e-05, + "loss": 1.0924, + "step": 5037 + }, + { + "epoch": 0.53, + "learning_rate": 1.075512216653256e-05, + "loss": 0.7405, + "step": 5038 + }, + { + "epoch": 0.53, + "learning_rate": 1.0751472316404315e-05, + "loss": 0.7134, + "step": 5039 + }, + { + "epoch": 0.53, + "learning_rate": 1.0747822365598088e-05, + "loss": 1.0904, + "step": 5040 + }, + { + "epoch": 0.53, + "learning_rate": 1.0744172314602881e-05, + "loss": 1.4353, + "step": 5041 + }, + { + "epoch": 0.53, + "learning_rate": 1.0740522163907702e-05, + "loss": 1.361, + "step": 5042 + }, + { + "epoch": 0.53, + "learning_rate": 1.073687191400158e-05, + "loss": 1.4024, + "step": 5043 + }, + { + "epoch": 0.53, + "learning_rate": 1.0733221565373557e-05, + "loss": 1.328, + "step": 5044 + }, + { + "epoch": 0.53, + "learning_rate": 1.0729571118512683e-05, + "loss": 1.3309, + "step": 5045 + }, + { + "epoch": 0.53, + "learning_rate": 1.0725920573908024e-05, + "loss": 1.3819, + "step": 5046 + }, + { + "epoch": 0.53, + "learning_rate": 1.0722269932048659e-05, + "loss": 1.3467, + "step": 5047 + }, + { + "epoch": 0.53, + "learning_rate": 1.0718619193423683e-05, + "loss": 1.3036, + "step": 5048 + }, + { + "epoch": 0.53, + "learning_rate": 1.07149683585222e-05, + "loss": 1.3297, + "step": 5049 + }, + { + "epoch": 0.53, + "learning_rate": 1.0711317427833328e-05, + "loss": 1.3439, + "step": 5050 + }, + { + "epoch": 0.53, + "learning_rate": 1.0707666401846192e-05, + "loss": 1.4167, + "step": 5051 + }, + { + "epoch": 0.53, + "learning_rate": 1.0704015281049944e-05, + "loss": 1.4217, + "step": 5052 + }, + { + "epoch": 0.53, + "learning_rate": 1.070036406593374e-05, + "loss": 1.3394, + "step": 5053 + }, + { + "epoch": 0.53, + "learning_rate": 1.0696712756986745e-05, + "loss": 1.3242, + "step": 5054 + }, + { + "epoch": 0.53, + "learning_rate": 1.0693061354698143e-05, + "loss": 1.3957, + "step": 5055 + }, + { + "epoch": 0.53, + "learning_rate": 1.0689409859557123e-05, + "loss": 1.37, + "step": 5056 + }, + { + "epoch": 0.53, + "learning_rate": 1.0685758272052902e-05, + "loss": 1.4524, + "step": 5057 + }, + { + "epoch": 0.53, + "learning_rate": 1.0682106592674688e-05, + "loss": 1.528, + "step": 5058 + }, + { + "epoch": 0.53, + "learning_rate": 1.0678454821911719e-05, + "loss": 1.3613, + "step": 5059 + }, + { + "epoch": 0.53, + "learning_rate": 1.0674802960253234e-05, + "loss": 1.308, + "step": 5060 + }, + { + "epoch": 0.53, + "learning_rate": 1.0671151008188494e-05, + "loss": 1.3343, + "step": 5061 + }, + { + "epoch": 0.53, + "learning_rate": 1.066749896620676e-05, + "loss": 1.365, + "step": 5062 + }, + { + "epoch": 0.53, + "learning_rate": 1.0663846834797316e-05, + "loss": 1.4077, + "step": 5063 + }, + { + "epoch": 0.53, + "learning_rate": 1.0660194614449455e-05, + "loss": 1.324, + "step": 5064 + }, + { + "epoch": 0.53, + "learning_rate": 1.0656542305652478e-05, + "loss": 1.3623, + "step": 5065 + }, + { + "epoch": 0.53, + "learning_rate": 1.0652889908895701e-05, + "loss": 1.4079, + "step": 5066 + }, + { + "epoch": 0.53, + "learning_rate": 1.0649237424668451e-05, + "loss": 1.3089, + "step": 5067 + }, + { + "epoch": 0.53, + "learning_rate": 1.0645584853460069e-05, + "loss": 1.3967, + "step": 5068 + }, + { + "epoch": 0.53, + "learning_rate": 1.0641932195759905e-05, + "loss": 1.3639, + "step": 5069 + }, + { + "epoch": 0.53, + "learning_rate": 1.0638279452057319e-05, + "loss": 1.5919, + "step": 5070 + }, + { + "epoch": 0.53, + "learning_rate": 1.0634626622841686e-05, + "loss": 1.3348, + "step": 5071 + }, + { + "epoch": 0.53, + "learning_rate": 1.0630973708602395e-05, + "loss": 1.3146, + "step": 5072 + }, + { + "epoch": 0.53, + "learning_rate": 1.0627320709828836e-05, + "loss": 1.3375, + "step": 5073 + }, + { + "epoch": 0.53, + "learning_rate": 1.062366762701042e-05, + "loss": 1.3908, + "step": 5074 + }, + { + "epoch": 0.53, + "learning_rate": 1.0620014460636568e-05, + "loss": 1.3726, + "step": 5075 + }, + { + "epoch": 0.53, + "learning_rate": 1.061636121119671e-05, + "loss": 1.2348, + "step": 5076 + }, + { + "epoch": 0.53, + "learning_rate": 1.0612707879180284e-05, + "loss": 1.2957, + "step": 5077 + }, + { + "epoch": 0.53, + "learning_rate": 1.0609054465076749e-05, + "loss": 1.4202, + "step": 5078 + }, + { + "epoch": 0.53, + "learning_rate": 1.060540096937556e-05, + "loss": 1.5809, + "step": 5079 + }, + { + "epoch": 0.53, + "learning_rate": 1.0601747392566202e-05, + "loss": 1.3741, + "step": 5080 + }, + { + "epoch": 0.53, + "learning_rate": 1.059809373513815e-05, + "loss": 1.3537, + "step": 5081 + }, + { + "epoch": 0.53, + "learning_rate": 1.0594439997580907e-05, + "loss": 1.332, + "step": 5082 + }, + { + "epoch": 0.53, + "learning_rate": 1.0590786180383981e-05, + "loss": 1.3267, + "step": 5083 + }, + { + "epoch": 0.53, + "learning_rate": 1.0587132284036883e-05, + "loss": 1.3552, + "step": 5084 + }, + { + "epoch": 0.53, + "learning_rate": 1.0583478309029143e-05, + "loss": 1.2837, + "step": 5085 + }, + { + "epoch": 0.53, + "learning_rate": 1.0579824255850304e-05, + "loss": 1.4311, + "step": 5086 + }, + { + "epoch": 0.53, + "learning_rate": 1.0576170124989915e-05, + "loss": 1.4394, + "step": 5087 + }, + { + "epoch": 0.53, + "learning_rate": 1.0572515916937531e-05, + "loss": 1.3185, + "step": 5088 + }, + { + "epoch": 0.53, + "learning_rate": 1.0568861632182723e-05, + "loss": 1.4212, + "step": 5089 + }, + { + "epoch": 0.53, + "learning_rate": 1.0565207271215075e-05, + "loss": 1.0951, + "step": 5090 + }, + { + "epoch": 0.53, + "learning_rate": 1.0561552834524176e-05, + "loss": 1.4174, + "step": 5091 + }, + { + "epoch": 0.53, + "learning_rate": 1.0557898322599624e-05, + "loss": 1.3349, + "step": 5092 + }, + { + "epoch": 0.53, + "learning_rate": 1.0554243735931031e-05, + "loss": 1.399, + "step": 5093 + }, + { + "epoch": 0.53, + "learning_rate": 1.055058907500802e-05, + "loss": 1.4016, + "step": 5094 + }, + { + "epoch": 0.53, + "learning_rate": 1.0546934340320219e-05, + "loss": 1.3227, + "step": 5095 + }, + { + "epoch": 0.53, + "learning_rate": 1.0543279532357269e-05, + "loss": 1.4017, + "step": 5096 + }, + { + "epoch": 0.53, + "learning_rate": 1.053962465160882e-05, + "loss": 1.3937, + "step": 5097 + }, + { + "epoch": 0.53, + "learning_rate": 1.0535969698564532e-05, + "loss": 1.2405, + "step": 5098 + }, + { + "epoch": 0.53, + "learning_rate": 1.0532314673714081e-05, + "loss": 1.2939, + "step": 5099 + }, + { + "epoch": 0.53, + "learning_rate": 1.0528659577547136e-05, + "loss": 1.4165, + "step": 5100 + }, + { + "epoch": 0.53, + "learning_rate": 1.0525004410553394e-05, + "loss": 1.309, + "step": 5101 + }, + { + "epoch": 0.54, + "learning_rate": 1.0521349173222549e-05, + "loss": 1.4078, + "step": 5102 + }, + { + "epoch": 0.54, + "learning_rate": 1.0517693866044312e-05, + "loss": 1.4026, + "step": 5103 + }, + { + "epoch": 0.54, + "learning_rate": 1.0514038489508396e-05, + "loss": 1.3098, + "step": 5104 + }, + { + "epoch": 0.54, + "learning_rate": 1.0510383044104533e-05, + "loss": 1.2886, + "step": 5105 + }, + { + "epoch": 0.54, + "learning_rate": 1.0506727530322454e-05, + "loss": 1.3114, + "step": 5106 + }, + { + "epoch": 0.54, + "learning_rate": 1.0503071948651908e-05, + "loss": 1.2823, + "step": 5107 + }, + { + "epoch": 0.54, + "learning_rate": 1.0499416299582643e-05, + "loss": 1.4654, + "step": 5108 + }, + { + "epoch": 0.54, + "learning_rate": 1.0495760583604431e-05, + "loss": 1.4043, + "step": 5109 + }, + { + "epoch": 0.54, + "learning_rate": 1.0492104801207035e-05, + "loss": 1.3113, + "step": 5110 + }, + { + "epoch": 0.54, + "learning_rate": 1.0488448952880243e-05, + "loss": 1.3285, + "step": 5111 + }, + { + "epoch": 0.54, + "learning_rate": 1.048479303911384e-05, + "loss": 1.3918, + "step": 5112 + }, + { + "epoch": 0.54, + "learning_rate": 1.0481137060397623e-05, + "loss": 1.346, + "step": 5113 + }, + { + "epoch": 0.54, + "learning_rate": 1.0477481017221407e-05, + "loss": 1.3777, + "step": 5114 + }, + { + "epoch": 0.54, + "learning_rate": 1.0473824910075003e-05, + "loss": 1.3494, + "step": 5115 + }, + { + "epoch": 0.54, + "learning_rate": 1.0470168739448232e-05, + "loss": 1.4173, + "step": 5116 + }, + { + "epoch": 0.54, + "learning_rate": 1.0466512505830932e-05, + "loss": 1.4313, + "step": 5117 + }, + { + "epoch": 0.54, + "learning_rate": 1.0462856209712944e-05, + "loss": 1.335, + "step": 5118 + }, + { + "epoch": 0.54, + "learning_rate": 1.0459199851584117e-05, + "loss": 1.37, + "step": 5119 + }, + { + "epoch": 0.54, + "learning_rate": 1.0455543431934307e-05, + "loss": 1.3504, + "step": 5120 + }, + { + "epoch": 0.54, + "learning_rate": 1.0451886951253381e-05, + "loss": 1.4148, + "step": 5121 + }, + { + "epoch": 0.54, + "learning_rate": 1.0448230410031218e-05, + "loss": 1.3974, + "step": 5122 + }, + { + "epoch": 0.54, + "learning_rate": 1.0444573808757694e-05, + "loss": 1.3644, + "step": 5123 + }, + { + "epoch": 0.54, + "learning_rate": 1.0440917147922705e-05, + "loss": 1.4024, + "step": 5124 + }, + { + "epoch": 0.54, + "learning_rate": 1.0437260428016143e-05, + "loss": 1.3925, + "step": 5125 + }, + { + "epoch": 0.54, + "learning_rate": 1.0433603649527923e-05, + "loss": 1.2907, + "step": 5126 + }, + { + "epoch": 0.54, + "learning_rate": 1.0429946812947953e-05, + "loss": 1.3453, + "step": 5127 + }, + { + "epoch": 0.54, + "learning_rate": 1.0426289918766157e-05, + "loss": 1.3856, + "step": 5128 + }, + { + "epoch": 0.54, + "learning_rate": 1.0422632967472465e-05, + "loss": 1.3309, + "step": 5129 + }, + { + "epoch": 0.54, + "learning_rate": 1.0418975959556819e-05, + "loss": 1.3757, + "step": 5130 + }, + { + "epoch": 0.54, + "learning_rate": 1.0415318895509152e-05, + "loss": 1.406, + "step": 5131 + }, + { + "epoch": 0.54, + "learning_rate": 1.041166177581943e-05, + "loss": 1.3265, + "step": 5132 + }, + { + "epoch": 0.54, + "learning_rate": 1.0408004600977606e-05, + "loss": 1.3377, + "step": 5133 + }, + { + "epoch": 0.54, + "learning_rate": 1.040434737147365e-05, + "loss": 1.3647, + "step": 5134 + }, + { + "epoch": 0.54, + "learning_rate": 1.0400690087797531e-05, + "loss": 1.3262, + "step": 5135 + }, + { + "epoch": 0.54, + "learning_rate": 1.039703275043924e-05, + "loss": 1.3924, + "step": 5136 + }, + { + "epoch": 0.54, + "learning_rate": 1.039337535988876e-05, + "loss": 1.3018, + "step": 5137 + }, + { + "epoch": 0.54, + "learning_rate": 1.038971791663609e-05, + "loss": 1.385, + "step": 5138 + }, + { + "epoch": 0.54, + "learning_rate": 1.0386060421171232e-05, + "loss": 1.3435, + "step": 5139 + }, + { + "epoch": 0.54, + "learning_rate": 1.0382402873984197e-05, + "loss": 1.4023, + "step": 5140 + }, + { + "epoch": 0.54, + "learning_rate": 1.0378745275565003e-05, + "loss": 1.369, + "step": 5141 + }, + { + "epoch": 0.54, + "learning_rate": 1.0375087626403675e-05, + "loss": 1.3199, + "step": 5142 + }, + { + "epoch": 0.54, + "learning_rate": 1.037142992699024e-05, + "loss": 1.4247, + "step": 5143 + }, + { + "epoch": 0.54, + "learning_rate": 1.0367772177814736e-05, + "loss": 1.4015, + "step": 5144 + }, + { + "epoch": 0.54, + "learning_rate": 1.0364114379367217e-05, + "loss": 1.3519, + "step": 5145 + }, + { + "epoch": 0.54, + "learning_rate": 1.0360456532137722e-05, + "loss": 1.3478, + "step": 5146 + }, + { + "epoch": 0.54, + "learning_rate": 1.0356798636616314e-05, + "loss": 1.4876, + "step": 5147 + }, + { + "epoch": 0.54, + "learning_rate": 1.0353140693293056e-05, + "loss": 1.6481, + "step": 5148 + }, + { + "epoch": 0.54, + "learning_rate": 1.034948270265802e-05, + "loss": 1.3851, + "step": 5149 + }, + { + "epoch": 0.54, + "learning_rate": 1.0345824665201281e-05, + "loss": 1.4037, + "step": 5150 + }, + { + "epoch": 0.54, + "learning_rate": 1.0342166581412923e-05, + "loss": 1.3138, + "step": 5151 + }, + { + "epoch": 0.54, + "learning_rate": 1.0338508451783032e-05, + "loss": 1.3536, + "step": 5152 + }, + { + "epoch": 0.54, + "learning_rate": 1.0334850276801712e-05, + "loss": 1.3244, + "step": 5153 + }, + { + "epoch": 0.54, + "learning_rate": 1.0331192056959052e-05, + "loss": 1.3677, + "step": 5154 + }, + { + "epoch": 0.54, + "learning_rate": 1.032753379274517e-05, + "loss": 1.3439, + "step": 5155 + }, + { + "epoch": 0.54, + "learning_rate": 1.0323875484650171e-05, + "loss": 1.365, + "step": 5156 + }, + { + "epoch": 0.54, + "learning_rate": 1.0320217133164186e-05, + "loss": 1.3838, + "step": 5157 + }, + { + "epoch": 0.54, + "learning_rate": 1.0316558738777328e-05, + "loss": 1.3312, + "step": 5158 + }, + { + "epoch": 0.54, + "learning_rate": 1.0312900301979733e-05, + "loss": 1.369, + "step": 5159 + }, + { + "epoch": 0.54, + "learning_rate": 1.030924182326154e-05, + "loss": 1.2712, + "step": 5160 + }, + { + "epoch": 0.54, + "learning_rate": 1.0305583303112887e-05, + "loss": 1.3141, + "step": 5161 + }, + { + "epoch": 0.54, + "learning_rate": 1.030192474202392e-05, + "loss": 1.3708, + "step": 5162 + }, + { + "epoch": 0.54, + "learning_rate": 1.0298266140484798e-05, + "loss": 1.3724, + "step": 5163 + }, + { + "epoch": 0.54, + "learning_rate": 1.0294607498985678e-05, + "loss": 1.3208, + "step": 5164 + }, + { + "epoch": 0.54, + "learning_rate": 1.0290948818016722e-05, + "loss": 1.3379, + "step": 5165 + }, + { + "epoch": 0.54, + "learning_rate": 1.0287290098068099e-05, + "loss": 1.3236, + "step": 5166 + }, + { + "epoch": 0.54, + "learning_rate": 1.0283631339629982e-05, + "loss": 1.3437, + "step": 5167 + }, + { + "epoch": 0.54, + "learning_rate": 1.0279972543192561e-05, + "loss": 1.3381, + "step": 5168 + }, + { + "epoch": 0.54, + "learning_rate": 1.0276313709246007e-05, + "loss": 1.4287, + "step": 5169 + }, + { + "epoch": 0.54, + "learning_rate": 1.0272654838280515e-05, + "loss": 1.3587, + "step": 5170 + }, + { + "epoch": 0.54, + "learning_rate": 1.0268995930786283e-05, + "loss": 1.2982, + "step": 5171 + }, + { + "epoch": 0.54, + "learning_rate": 1.0265336987253509e-05, + "loss": 1.3416, + "step": 5172 + }, + { + "epoch": 0.54, + "learning_rate": 1.0261678008172393e-05, + "loss": 1.3827, + "step": 5173 + }, + { + "epoch": 0.54, + "learning_rate": 1.025801899403315e-05, + "loss": 1.3293, + "step": 5174 + }, + { + "epoch": 0.54, + "eval_loss": 1.4264723062515259, + "eval_runtime": 77.4376, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 5174 + }, + { + "epoch": 0.54, + "learning_rate": 1.0254359945325987e-05, + "loss": 1.3811, + "step": 5175 + }, + { + "epoch": 0.54, + "learning_rate": 1.0250700862541135e-05, + "loss": 1.3423, + "step": 5176 + }, + { + "epoch": 0.54, + "learning_rate": 1.02470417461688e-05, + "loss": 1.3641, + "step": 5177 + }, + { + "epoch": 0.54, + "learning_rate": 1.0243382596699226e-05, + "loss": 1.3211, + "step": 5178 + }, + { + "epoch": 0.54, + "learning_rate": 1.023972341462263e-05, + "loss": 1.4008, + "step": 5179 + }, + { + "epoch": 0.54, + "learning_rate": 1.0236064200429263e-05, + "loss": 1.404, + "step": 5180 + }, + { + "epoch": 0.54, + "learning_rate": 1.0232404954609353e-05, + "loss": 1.3359, + "step": 5181 + }, + { + "epoch": 0.54, + "learning_rate": 1.0228745677653155e-05, + "loss": 1.4069, + "step": 5182 + }, + { + "epoch": 0.54, + "learning_rate": 1.0225086370050914e-05, + "loss": 1.3343, + "step": 5183 + }, + { + "epoch": 0.54, + "learning_rate": 1.0221427032292881e-05, + "loss": 1.3109, + "step": 5184 + }, + { + "epoch": 0.54, + "learning_rate": 1.0217767664869312e-05, + "loss": 1.3611, + "step": 5185 + }, + { + "epoch": 0.54, + "learning_rate": 1.0214108268270476e-05, + "loss": 1.4072, + "step": 5186 + }, + { + "epoch": 0.54, + "learning_rate": 1.0210448842986631e-05, + "loss": 1.3602, + "step": 5187 + }, + { + "epoch": 0.54, + "learning_rate": 1.0206789389508047e-05, + "loss": 1.413, + "step": 5188 + }, + { + "epoch": 0.54, + "learning_rate": 1.0203129908325e-05, + "loss": 1.3209, + "step": 5189 + }, + { + "epoch": 0.54, + "learning_rate": 1.0199470399927764e-05, + "loss": 1.3714, + "step": 5190 + }, + { + "epoch": 0.54, + "learning_rate": 1.0195810864806623e-05, + "loss": 1.3556, + "step": 5191 + }, + { + "epoch": 0.54, + "learning_rate": 1.0192151303451852e-05, + "loss": 1.4116, + "step": 5192 + }, + { + "epoch": 0.54, + "learning_rate": 1.0188491716353745e-05, + "loss": 1.4102, + "step": 5193 + }, + { + "epoch": 0.54, + "learning_rate": 1.0184832104002592e-05, + "loss": 1.4849, + "step": 5194 + }, + { + "epoch": 0.54, + "learning_rate": 1.0181172466888689e-05, + "loss": 1.5395, + "step": 5195 + }, + { + "epoch": 0.54, + "learning_rate": 1.0177512805502325e-05, + "loss": 1.3627, + "step": 5196 + }, + { + "epoch": 0.54, + "learning_rate": 1.017385312033381e-05, + "loss": 1.4152, + "step": 5197 + }, + { + "epoch": 0.55, + "learning_rate": 1.0170193411873442e-05, + "loss": 1.3641, + "step": 5198 + }, + { + "epoch": 0.55, + "learning_rate": 1.0166533680611533e-05, + "loss": 1.3074, + "step": 5199 + }, + { + "epoch": 0.55, + "learning_rate": 1.0162873927038386e-05, + "loss": 1.35, + "step": 5200 + }, + { + "epoch": 0.55, + "learning_rate": 1.015921415164432e-05, + "loss": 1.3551, + "step": 5201 + }, + { + "epoch": 0.55, + "learning_rate": 1.0155554354919643e-05, + "loss": 1.3421, + "step": 5202 + }, + { + "epoch": 0.55, + "learning_rate": 1.0151894537354687e-05, + "loss": 1.4132, + "step": 5203 + }, + { + "epoch": 0.55, + "learning_rate": 1.0148234699439764e-05, + "loss": 1.351, + "step": 5204 + }, + { + "epoch": 0.55, + "learning_rate": 1.0144574841665198e-05, + "loss": 1.3745, + "step": 5205 + }, + { + "epoch": 0.55, + "learning_rate": 1.0140914964521316e-05, + "loss": 1.3151, + "step": 5206 + }, + { + "epoch": 0.55, + "learning_rate": 1.0137255068498456e-05, + "loss": 1.4903, + "step": 5207 + }, + { + "epoch": 0.55, + "learning_rate": 1.0133595154086937e-05, + "loss": 1.3945, + "step": 5208 + }, + { + "epoch": 0.55, + "learning_rate": 1.0129935221777104e-05, + "loss": 1.3924, + "step": 5209 + }, + { + "epoch": 0.55, + "learning_rate": 1.0126275272059286e-05, + "loss": 1.4191, + "step": 5210 + }, + { + "epoch": 0.55, + "learning_rate": 1.012261530542383e-05, + "loss": 1.3408, + "step": 5211 + }, + { + "epoch": 0.55, + "learning_rate": 1.0118955322361071e-05, + "loss": 1.3582, + "step": 5212 + }, + { + "epoch": 0.55, + "learning_rate": 1.0115295323361354e-05, + "loss": 1.3703, + "step": 5213 + }, + { + "epoch": 0.55, + "learning_rate": 1.011163530891503e-05, + "loss": 1.4181, + "step": 5214 + }, + { + "epoch": 0.55, + "learning_rate": 1.0107975279512442e-05, + "loss": 1.5019, + "step": 5215 + }, + { + "epoch": 0.55, + "learning_rate": 1.010431523564394e-05, + "loss": 1.3151, + "step": 5216 + }, + { + "epoch": 0.55, + "learning_rate": 1.0100655177799874e-05, + "loss": 1.4036, + "step": 5217 + }, + { + "epoch": 0.55, + "learning_rate": 1.0096995106470606e-05, + "loss": 1.3584, + "step": 5218 + }, + { + "epoch": 0.55, + "learning_rate": 1.0093335022146482e-05, + "loss": 1.3618, + "step": 5219 + }, + { + "epoch": 0.55, + "learning_rate": 1.0089674925317865e-05, + "loss": 1.3295, + "step": 5220 + }, + { + "epoch": 0.55, + "learning_rate": 1.0086014816475108e-05, + "loss": 1.3968, + "step": 5221 + }, + { + "epoch": 0.55, + "learning_rate": 1.0082354696108586e-05, + "loss": 1.2847, + "step": 5222 + }, + { + "epoch": 0.55, + "learning_rate": 1.007869456470864e-05, + "loss": 1.4461, + "step": 5223 + }, + { + "epoch": 0.55, + "learning_rate": 1.007503442276565e-05, + "loss": 1.3813, + "step": 5224 + }, + { + "epoch": 0.55, + "learning_rate": 1.007137427076997e-05, + "loss": 1.3833, + "step": 5225 + }, + { + "epoch": 0.55, + "learning_rate": 1.006771410921198e-05, + "loss": 1.4024, + "step": 5226 + }, + { + "epoch": 0.55, + "learning_rate": 1.0064053938582032e-05, + "loss": 1.3357, + "step": 5227 + }, + { + "epoch": 0.55, + "learning_rate": 1.0060393759370506e-05, + "loss": 1.35, + "step": 5228 + }, + { + "epoch": 0.55, + "learning_rate": 1.0056733572067765e-05, + "loss": 1.3512, + "step": 5229 + }, + { + "epoch": 0.55, + "learning_rate": 1.0053073377164186e-05, + "loss": 1.3852, + "step": 5230 + }, + { + "epoch": 0.55, + "learning_rate": 1.0049413175150135e-05, + "loss": 1.3502, + "step": 5231 + }, + { + "epoch": 0.55, + "learning_rate": 1.004575296651599e-05, + "loss": 1.4637, + "step": 5232 + }, + { + "epoch": 0.55, + "learning_rate": 1.0042092751752123e-05, + "loss": 1.3877, + "step": 5233 + }, + { + "epoch": 0.55, + "learning_rate": 1.0038432531348909e-05, + "loss": 1.3804, + "step": 5234 + }, + { + "epoch": 0.55, + "learning_rate": 1.0034772305796723e-05, + "loss": 1.3613, + "step": 5235 + }, + { + "epoch": 0.55, + "learning_rate": 1.003111207558594e-05, + "loss": 1.3218, + "step": 5236 + }, + { + "epoch": 0.55, + "learning_rate": 1.0027451841206944e-05, + "loss": 1.3554, + "step": 5237 + }, + { + "epoch": 0.55, + "learning_rate": 1.0023791603150099e-05, + "loss": 1.372, + "step": 5238 + }, + { + "epoch": 0.55, + "learning_rate": 1.0020131361905793e-05, + "loss": 1.3544, + "step": 5239 + }, + { + "epoch": 0.55, + "learning_rate": 1.0016471117964404e-05, + "loss": 1.3472, + "step": 5240 + }, + { + "epoch": 0.55, + "learning_rate": 1.001281087181631e-05, + "loss": 1.4247, + "step": 5241 + }, + { + "epoch": 0.55, + "learning_rate": 1.0009150623951883e-05, + "loss": 1.2685, + "step": 5242 + }, + { + "epoch": 0.55, + "learning_rate": 1.000549037486151e-05, + "loss": 1.4036, + "step": 5243 + }, + { + "epoch": 0.55, + "learning_rate": 1.0001830125035565e-05, + "loss": 1.3602, + "step": 5244 + }, + { + "epoch": 0.55, + "learning_rate": 9.998169874964437e-06, + "loss": 1.3784, + "step": 5245 + }, + { + "epoch": 0.55, + "learning_rate": 9.994509625138496e-06, + "loss": 1.3389, + "step": 5246 + }, + { + "epoch": 0.55, + "learning_rate": 9.990849376048119e-06, + "loss": 1.4561, + "step": 5247 + }, + { + "epoch": 0.55, + "learning_rate": 9.987189128183695e-06, + "loss": 1.3876, + "step": 5248 + }, + { + "epoch": 0.55, + "learning_rate": 9.9835288820356e-06, + "loss": 1.3362, + "step": 5249 + }, + { + "epoch": 0.55, + "learning_rate": 9.97986863809421e-06, + "loss": 1.3449, + "step": 5250 + }, + { + "epoch": 0.55, + "learning_rate": 9.9762083968499e-06, + "loss": 1.3521, + "step": 5251 + }, + { + "epoch": 0.55, + "learning_rate": 9.972548158793061e-06, + "loss": 1.4452, + "step": 5252 + }, + { + "epoch": 0.55, + "learning_rate": 9.968887924414062e-06, + "loss": 1.4126, + "step": 5253 + }, + { + "epoch": 0.55, + "learning_rate": 9.965227694203282e-06, + "loss": 1.3054, + "step": 5254 + }, + { + "epoch": 0.55, + "learning_rate": 9.961567468651093e-06, + "loss": 1.3771, + "step": 5255 + }, + { + "epoch": 0.55, + "learning_rate": 9.957907248247878e-06, + "loss": 1.3566, + "step": 5256 + }, + { + "epoch": 0.55, + "learning_rate": 9.954247033484014e-06, + "loss": 1.4765, + "step": 5257 + }, + { + "epoch": 0.55, + "learning_rate": 9.950586824849865e-06, + "loss": 1.4749, + "step": 5258 + }, + { + "epoch": 0.55, + "learning_rate": 9.946926622835815e-06, + "loss": 1.3679, + "step": 5259 + }, + { + "epoch": 0.55, + "learning_rate": 9.943266427932238e-06, + "loss": 1.2671, + "step": 5260 + }, + { + "epoch": 0.55, + "learning_rate": 9.9396062406295e-06, + "loss": 1.3485, + "step": 5261 + }, + { + "epoch": 0.55, + "learning_rate": 9.935946061417968e-06, + "loss": 1.3136, + "step": 5262 + }, + { + "epoch": 0.55, + "learning_rate": 9.932285890788024e-06, + "loss": 1.3954, + "step": 5263 + }, + { + "epoch": 0.55, + "learning_rate": 9.928625729230031e-06, + "loss": 1.428, + "step": 5264 + }, + { + "epoch": 0.55, + "learning_rate": 9.924965577234356e-06, + "loss": 1.4144, + "step": 5265 + }, + { + "epoch": 0.55, + "learning_rate": 9.92130543529136e-06, + "loss": 1.3361, + "step": 5266 + }, + { + "epoch": 0.55, + "learning_rate": 9.91764530389142e-06, + "loss": 1.4503, + "step": 5267 + }, + { + "epoch": 0.55, + "learning_rate": 9.913985183524893e-06, + "loss": 1.3431, + "step": 5268 + }, + { + "epoch": 0.55, + "learning_rate": 9.91032507468214e-06, + "loss": 1.3206, + "step": 5269 + }, + { + "epoch": 0.55, + "learning_rate": 9.906664977853518e-06, + "loss": 1.4568, + "step": 5270 + }, + { + "epoch": 0.55, + "learning_rate": 9.903004893529397e-06, + "loss": 1.3591, + "step": 5271 + }, + { + "epoch": 0.55, + "learning_rate": 9.899344822200127e-06, + "loss": 1.3382, + "step": 5272 + }, + { + "epoch": 0.55, + "learning_rate": 9.895684764356066e-06, + "loss": 1.3008, + "step": 5273 + }, + { + "epoch": 0.55, + "learning_rate": 9.89202472048756e-06, + "loss": 1.316, + "step": 5274 + }, + { + "epoch": 0.55, + "learning_rate": 9.888364691084971e-06, + "loss": 1.4246, + "step": 5275 + }, + { + "epoch": 0.55, + "learning_rate": 9.88470467663865e-06, + "loss": 1.3615, + "step": 5276 + }, + { + "epoch": 0.55, + "learning_rate": 9.881044677638934e-06, + "loss": 1.3418, + "step": 5277 + }, + { + "epoch": 0.55, + "learning_rate": 9.877384694576172e-06, + "loss": 1.249, + "step": 5278 + }, + { + "epoch": 0.55, + "learning_rate": 9.873724727940715e-06, + "loss": 1.2779, + "step": 5279 + }, + { + "epoch": 0.55, + "learning_rate": 9.870064778222903e-06, + "loss": 1.3529, + "step": 5280 + }, + { + "epoch": 0.55, + "learning_rate": 9.866404845913065e-06, + "loss": 1.3204, + "step": 5281 + }, + { + "epoch": 0.55, + "learning_rate": 9.862744931501548e-06, + "loss": 1.3537, + "step": 5282 + }, + { + "epoch": 0.55, + "learning_rate": 9.859085035478687e-06, + "loss": 1.3681, + "step": 5283 + }, + { + "epoch": 0.55, + "learning_rate": 9.855425158334809e-06, + "loss": 1.3983, + "step": 5284 + }, + { + "epoch": 0.55, + "learning_rate": 9.851765300560238e-06, + "loss": 1.401, + "step": 5285 + }, + { + "epoch": 0.55, + "learning_rate": 9.848105462645315e-06, + "loss": 1.3073, + "step": 5286 + }, + { + "epoch": 0.55, + "learning_rate": 9.844445645080358e-06, + "loss": 1.3162, + "step": 5287 + }, + { + "epoch": 0.55, + "learning_rate": 9.840785848355685e-06, + "loss": 1.3345, + "step": 5288 + }, + { + "epoch": 0.55, + "learning_rate": 9.837126072961616e-06, + "loss": 1.4241, + "step": 5289 + }, + { + "epoch": 0.55, + "learning_rate": 9.83346631938847e-06, + "loss": 1.3339, + "step": 5290 + }, + { + "epoch": 0.55, + "learning_rate": 9.829806588126561e-06, + "loss": 1.3507, + "step": 5291 + }, + { + "epoch": 0.55, + "learning_rate": 9.826146879666196e-06, + "loss": 1.2806, + "step": 5292 + }, + { + "epoch": 0.56, + "learning_rate": 9.822487194497675e-06, + "loss": 1.3952, + "step": 5293 + }, + { + "epoch": 0.56, + "learning_rate": 9.818827533111314e-06, + "loss": 1.3319, + "step": 5294 + }, + { + "epoch": 0.56, + "learning_rate": 9.81516789599741e-06, + "loss": 1.351, + "step": 5295 + }, + { + "epoch": 0.56, + "learning_rate": 9.811508283646258e-06, + "loss": 1.4076, + "step": 5296 + }, + { + "epoch": 0.56, + "learning_rate": 9.80784869654815e-06, + "loss": 1.3271, + "step": 5297 + }, + { + "epoch": 0.56, + "learning_rate": 9.80418913519338e-06, + "loss": 1.4059, + "step": 5298 + }, + { + "epoch": 0.56, + "learning_rate": 9.80052960007224e-06, + "loss": 1.4146, + "step": 5299 + }, + { + "epoch": 0.56, + "learning_rate": 9.796870091675005e-06, + "loss": 1.3454, + "step": 5300 + }, + { + "epoch": 0.56, + "learning_rate": 9.793210610491953e-06, + "loss": 1.4376, + "step": 5301 + }, + { + "epoch": 0.56, + "learning_rate": 9.789551157013372e-06, + "loss": 1.3437, + "step": 5302 + }, + { + "epoch": 0.56, + "learning_rate": 9.78589173172953e-06, + "loss": 1.3073, + "step": 5303 + }, + { + "epoch": 0.56, + "learning_rate": 9.782232335130688e-06, + "loss": 1.2989, + "step": 5304 + }, + { + "epoch": 0.56, + "learning_rate": 9.778572967707122e-06, + "loss": 1.4028, + "step": 5305 + }, + { + "epoch": 0.56, + "learning_rate": 9.77491362994909e-06, + "loss": 1.3096, + "step": 5306 + }, + { + "epoch": 0.56, + "learning_rate": 9.77125432234685e-06, + "loss": 1.3719, + "step": 5307 + }, + { + "epoch": 0.56, + "learning_rate": 9.767595045390647e-06, + "loss": 1.3271, + "step": 5308 + }, + { + "epoch": 0.56, + "learning_rate": 9.763935799570739e-06, + "loss": 1.3693, + "step": 5309 + }, + { + "epoch": 0.56, + "learning_rate": 9.760276585377371e-06, + "loss": 1.3586, + "step": 5310 + }, + { + "epoch": 0.56, + "learning_rate": 9.756617403300781e-06, + "loss": 1.3423, + "step": 5311 + }, + { + "epoch": 0.56, + "learning_rate": 9.7529582538312e-06, + "loss": 1.388, + "step": 5312 + }, + { + "epoch": 0.56, + "learning_rate": 9.74929913745887e-06, + "loss": 1.3594, + "step": 5313 + }, + { + "epoch": 0.56, + "learning_rate": 9.745640054674015e-06, + "loss": 1.2831, + "step": 5314 + }, + { + "epoch": 0.56, + "learning_rate": 9.741981005966856e-06, + "loss": 1.4207, + "step": 5315 + }, + { + "epoch": 0.56, + "learning_rate": 9.738321991827609e-06, + "loss": 1.2807, + "step": 5316 + }, + { + "epoch": 0.56, + "learning_rate": 9.734663012746493e-06, + "loss": 1.3396, + "step": 5317 + }, + { + "epoch": 0.56, + "learning_rate": 9.731004069213722e-06, + "loss": 1.3666, + "step": 5318 + }, + { + "epoch": 0.56, + "learning_rate": 9.72734516171949e-06, + "loss": 1.3466, + "step": 5319 + }, + { + "epoch": 0.56, + "learning_rate": 9.723686290753995e-06, + "loss": 1.4478, + "step": 5320 + }, + { + "epoch": 0.56, + "learning_rate": 9.720027456807442e-06, + "loss": 1.316, + "step": 5321 + }, + { + "epoch": 0.56, + "learning_rate": 9.71636866037002e-06, + "loss": 1.3762, + "step": 5322 + }, + { + "epoch": 0.56, + "learning_rate": 9.712709901931906e-06, + "loss": 1.4156, + "step": 5323 + }, + { + "epoch": 0.56, + "learning_rate": 9.70905118198328e-06, + "loss": 1.2452, + "step": 5324 + }, + { + "epoch": 0.56, + "learning_rate": 9.705392501014325e-06, + "loss": 1.3771, + "step": 5325 + }, + { + "epoch": 0.56, + "learning_rate": 9.701733859515205e-06, + "loss": 1.3433, + "step": 5326 + }, + { + "epoch": 0.56, + "learning_rate": 9.698075257976079e-06, + "loss": 1.3702, + "step": 5327 + }, + { + "epoch": 0.56, + "learning_rate": 9.694416696887115e-06, + "loss": 1.295, + "step": 5328 + }, + { + "epoch": 0.56, + "learning_rate": 9.690758176738463e-06, + "loss": 1.3462, + "step": 5329 + }, + { + "epoch": 0.56, + "learning_rate": 9.68709969802027e-06, + "loss": 1.5304, + "step": 5330 + }, + { + "epoch": 0.56, + "learning_rate": 9.683441261222672e-06, + "loss": 1.3518, + "step": 5331 + }, + { + "epoch": 0.56, + "learning_rate": 9.679782866835816e-06, + "loss": 1.3778, + "step": 5332 + }, + { + "epoch": 0.56, + "learning_rate": 9.67612451534983e-06, + "loss": 1.3731, + "step": 5333 + }, + { + "epoch": 0.56, + "learning_rate": 9.672466207254837e-06, + "loss": 1.3315, + "step": 5334 + }, + { + "epoch": 0.56, + "learning_rate": 9.66880794304095e-06, + "loss": 1.3105, + "step": 5335 + }, + { + "epoch": 0.56, + "learning_rate": 9.665149723198293e-06, + "loss": 1.3903, + "step": 5336 + }, + { + "epoch": 0.56, + "learning_rate": 9.661491548216972e-06, + "loss": 1.3554, + "step": 5337 + }, + { + "epoch": 0.56, + "learning_rate": 9.657833418587084e-06, + "loss": 1.3231, + "step": 5338 + }, + { + "epoch": 0.56, + "learning_rate": 9.65417533479872e-06, + "loss": 1.352, + "step": 5339 + }, + { + "epoch": 0.56, + "learning_rate": 9.650517297341983e-06, + "loss": 1.3957, + "step": 5340 + }, + { + "epoch": 0.56, + "learning_rate": 9.646859306706948e-06, + "loss": 1.3938, + "step": 5341 + }, + { + "epoch": 0.56, + "learning_rate": 9.643201363383693e-06, + "loss": 1.3038, + "step": 5342 + }, + { + "epoch": 0.56, + "learning_rate": 9.63954346786228e-06, + "loss": 1.2973, + "step": 5343 + }, + { + "epoch": 0.56, + "learning_rate": 9.635885620632786e-06, + "loss": 1.379, + "step": 5344 + }, + { + "epoch": 0.56, + "learning_rate": 9.632227822185266e-06, + "loss": 1.5377, + "step": 5345 + }, + { + "epoch": 0.56, + "learning_rate": 9.628570073009767e-06, + "loss": 1.4573, + "step": 5346 + }, + { + "epoch": 0.56, + "learning_rate": 9.624912373596329e-06, + "loss": 1.3394, + "step": 5347 + }, + { + "epoch": 0.56, + "learning_rate": 9.621254724434999e-06, + "loss": 1.4157, + "step": 5348 + }, + { + "epoch": 0.56, + "learning_rate": 9.617597126015808e-06, + "loss": 1.3526, + "step": 5349 + }, + { + "epoch": 0.56, + "learning_rate": 9.61393957882877e-06, + "loss": 1.3795, + "step": 5350 + }, + { + "epoch": 0.56, + "learning_rate": 9.610282083363913e-06, + "loss": 1.3765, + "step": 5351 + }, + { + "epoch": 0.56, + "learning_rate": 9.606624640111243e-06, + "loss": 1.3512, + "step": 5352 + }, + { + "epoch": 0.56, + "learning_rate": 9.602967249560766e-06, + "loss": 1.3298, + "step": 5353 + }, + { + "epoch": 0.56, + "learning_rate": 9.599309912202469e-06, + "loss": 1.3093, + "step": 5354 + }, + { + "epoch": 0.56, + "learning_rate": 9.595652628526354e-06, + "loss": 1.3353, + "step": 5355 + }, + { + "epoch": 0.56, + "learning_rate": 9.591995399022397e-06, + "loss": 1.3081, + "step": 5356 + }, + { + "epoch": 0.56, + "learning_rate": 9.588338224180576e-06, + "loss": 1.343, + "step": 5357 + }, + { + "epoch": 0.56, + "learning_rate": 9.584681104490848e-06, + "loss": 1.3275, + "step": 5358 + }, + { + "epoch": 0.56, + "learning_rate": 9.581024040443185e-06, + "loss": 1.3399, + "step": 5359 + }, + { + "epoch": 0.56, + "learning_rate": 9.577367032527538e-06, + "loss": 1.3181, + "step": 5360 + }, + { + "epoch": 0.56, + "learning_rate": 9.573710081233846e-06, + "loss": 1.3531, + "step": 5361 + }, + { + "epoch": 0.56, + "learning_rate": 9.570053187052049e-06, + "loss": 1.4056, + "step": 5362 + }, + { + "epoch": 0.56, + "learning_rate": 9.566396350472079e-06, + "loss": 1.3303, + "step": 5363 + }, + { + "epoch": 0.56, + "learning_rate": 9.56273957198386e-06, + "loss": 1.3506, + "step": 5364 + }, + { + "epoch": 0.56, + "learning_rate": 9.559082852077302e-06, + "loss": 1.4588, + "step": 5365 + }, + { + "epoch": 0.56, + "learning_rate": 9.555426191242307e-06, + "loss": 1.3434, + "step": 5366 + }, + { + "epoch": 0.56, + "learning_rate": 9.551769589968784e-06, + "loss": 1.3508, + "step": 5367 + }, + { + "epoch": 0.56, + "learning_rate": 9.548113048746622e-06, + "loss": 1.3701, + "step": 5368 + }, + { + "epoch": 0.56, + "learning_rate": 9.544456568065698e-06, + "loss": 1.3664, + "step": 5369 + }, + { + "epoch": 0.56, + "learning_rate": 9.540800148415885e-06, + "loss": 1.6697, + "step": 5370 + }, + { + "epoch": 0.56, + "learning_rate": 9.537143790287057e-06, + "loss": 1.5298, + "step": 5371 + }, + { + "epoch": 0.56, + "learning_rate": 9.533487494169073e-06, + "loss": 1.3884, + "step": 5372 + }, + { + "epoch": 0.56, + "learning_rate": 9.52983126055177e-06, + "loss": 1.403, + "step": 5373 + }, + { + "epoch": 0.56, + "eval_loss": 1.4240995645523071, + "eval_runtime": 77.4615, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 5373 + }, + { + "epoch": 0.56, + "learning_rate": 9.526175089925e-06, + "loss": 1.3141, + "step": 5374 + }, + { + "epoch": 0.56, + "learning_rate": 9.522518982778596e-06, + "loss": 1.3733, + "step": 5375 + }, + { + "epoch": 0.56, + "learning_rate": 9.51886293960238e-06, + "loss": 1.3095, + "step": 5376 + }, + { + "epoch": 0.56, + "learning_rate": 9.515206960886162e-06, + "loss": 1.3713, + "step": 5377 + }, + { + "epoch": 0.56, + "learning_rate": 9.51155104711976e-06, + "loss": 1.3585, + "step": 5378 + }, + { + "epoch": 0.56, + "learning_rate": 9.507895198792967e-06, + "loss": 1.3473, + "step": 5379 + }, + { + "epoch": 0.56, + "learning_rate": 9.504239416395576e-06, + "loss": 1.3282, + "step": 5380 + }, + { + "epoch": 0.56, + "learning_rate": 9.500583700417357e-06, + "loss": 1.3655, + "step": 5381 + }, + { + "epoch": 0.56, + "learning_rate": 9.496928051348095e-06, + "loss": 1.4512, + "step": 5382 + }, + { + "epoch": 0.56, + "learning_rate": 9.49327246967755e-06, + "loss": 1.4071, + "step": 5383 + }, + { + "epoch": 0.56, + "learning_rate": 9.489616955895472e-06, + "loss": 1.3703, + "step": 5384 + }, + { + "epoch": 0.56, + "learning_rate": 9.485961510491604e-06, + "loss": 1.3358, + "step": 5385 + }, + { + "epoch": 0.56, + "learning_rate": 9.482306133955691e-06, + "loss": 1.3505, + "step": 5386 + }, + { + "epoch": 0.56, + "learning_rate": 9.478650826777457e-06, + "loss": 1.2578, + "step": 5387 + }, + { + "epoch": 0.57, + "learning_rate": 9.474995589446612e-06, + "loss": 1.4298, + "step": 5388 + }, + { + "epoch": 0.57, + "learning_rate": 9.471340422452864e-06, + "loss": 1.4044, + "step": 5389 + }, + { + "epoch": 0.57, + "learning_rate": 9.467685326285922e-06, + "loss": 1.3524, + "step": 5390 + }, + { + "epoch": 0.57, + "learning_rate": 9.46403030143547e-06, + "loss": 1.3017, + "step": 5391 + }, + { + "epoch": 0.57, + "learning_rate": 9.460375348391185e-06, + "loss": 1.3361, + "step": 5392 + }, + { + "epoch": 0.57, + "learning_rate": 9.456720467642733e-06, + "loss": 1.3182, + "step": 5393 + }, + { + "epoch": 0.57, + "learning_rate": 9.453065659679785e-06, + "loss": 1.3869, + "step": 5394 + }, + { + "epoch": 0.57, + "learning_rate": 9.449410924991986e-06, + "loss": 1.3161, + "step": 5395 + }, + { + "epoch": 0.57, + "learning_rate": 9.44575626406897e-06, + "loss": 1.3, + "step": 5396 + }, + { + "epoch": 0.57, + "learning_rate": 9.442101677400378e-06, + "loss": 1.5103, + "step": 5397 + }, + { + "epoch": 0.57, + "learning_rate": 9.438447165475828e-06, + "loss": 1.3511, + "step": 5398 + }, + { + "epoch": 0.57, + "learning_rate": 9.43479272878493e-06, + "loss": 1.3461, + "step": 5399 + }, + { + "epoch": 0.57, + "learning_rate": 9.431138367817277e-06, + "loss": 1.2657, + "step": 5400 + }, + { + "epoch": 0.57, + "learning_rate": 9.427484083062472e-06, + "loss": 1.3736, + "step": 5401 + }, + { + "epoch": 0.57, + "learning_rate": 9.423829875010089e-06, + "loss": 1.3476, + "step": 5402 + }, + { + "epoch": 0.57, + "learning_rate": 9.4201757441497e-06, + "loss": 1.3495, + "step": 5403 + }, + { + "epoch": 0.57, + "learning_rate": 9.416521690970857e-06, + "loss": 1.387, + "step": 5404 + }, + { + "epoch": 0.57, + "learning_rate": 9.41286771596312e-06, + "loss": 1.2829, + "step": 5405 + }, + { + "epoch": 0.57, + "learning_rate": 9.409213819616022e-06, + "loss": 1.3544, + "step": 5406 + }, + { + "epoch": 0.57, + "learning_rate": 9.405560002419098e-06, + "loss": 1.3202, + "step": 5407 + }, + { + "epoch": 0.57, + "learning_rate": 9.40190626486185e-06, + "loss": 1.3034, + "step": 5408 + }, + { + "epoch": 0.57, + "learning_rate": 9.398252607433801e-06, + "loss": 1.3223, + "step": 5409 + }, + { + "epoch": 0.57, + "learning_rate": 9.394599030624443e-06, + "loss": 1.3327, + "step": 5410 + }, + { + "epoch": 0.57, + "learning_rate": 9.390945534923258e-06, + "loss": 1.3248, + "step": 5411 + }, + { + "epoch": 0.57, + "learning_rate": 9.387292120819716e-06, + "loss": 1.3084, + "step": 5412 + }, + { + "epoch": 0.57, + "learning_rate": 9.383638788803291e-06, + "loss": 1.344, + "step": 5413 + }, + { + "epoch": 0.57, + "learning_rate": 9.379985539363436e-06, + "loss": 1.3354, + "step": 5414 + }, + { + "epoch": 0.57, + "learning_rate": 9.376332372989586e-06, + "loss": 1.3291, + "step": 5415 + }, + { + "epoch": 0.57, + "learning_rate": 9.372679290171167e-06, + "loss": 1.3468, + "step": 5416 + }, + { + "epoch": 0.57, + "learning_rate": 9.36902629139761e-06, + "loss": 1.3481, + "step": 5417 + }, + { + "epoch": 0.57, + "learning_rate": 9.36537337715832e-06, + "loss": 1.3309, + "step": 5418 + }, + { + "epoch": 0.57, + "learning_rate": 9.361720547942683e-06, + "loss": 1.362, + "step": 5419 + }, + { + "epoch": 0.57, + "learning_rate": 9.358067804240098e-06, + "loss": 1.3647, + "step": 5420 + }, + { + "epoch": 0.57, + "learning_rate": 9.354415146539933e-06, + "loss": 1.4511, + "step": 5421 + }, + { + "epoch": 0.57, + "learning_rate": 9.350762575331554e-06, + "loss": 1.3379, + "step": 5422 + }, + { + "epoch": 0.57, + "learning_rate": 9.3471100911043e-06, + "loss": 1.5468, + "step": 5423 + }, + { + "epoch": 0.57, + "learning_rate": 9.343457694347524e-06, + "loss": 1.4259, + "step": 5424 + }, + { + "epoch": 0.57, + "learning_rate": 9.339805385550548e-06, + "loss": 1.3816, + "step": 5425 + }, + { + "epoch": 0.57, + "learning_rate": 9.336153165202689e-06, + "loss": 1.3627, + "step": 5426 + }, + { + "epoch": 0.57, + "learning_rate": 9.332501033793242e-06, + "loss": 1.3338, + "step": 5427 + }, + { + "epoch": 0.57, + "learning_rate": 9.328848991811509e-06, + "loss": 1.2946, + "step": 5428 + }, + { + "epoch": 0.57, + "learning_rate": 9.325197039746769e-06, + "loss": 1.3405, + "step": 5429 + }, + { + "epoch": 0.57, + "learning_rate": 9.321545178088288e-06, + "loss": 1.3549, + "step": 5430 + }, + { + "epoch": 0.57, + "learning_rate": 9.317893407325314e-06, + "loss": 1.3225, + "step": 5431 + }, + { + "epoch": 0.57, + "learning_rate": 9.314241727947101e-06, + "loss": 1.3457, + "step": 5432 + }, + { + "epoch": 0.57, + "learning_rate": 9.310590140442878e-06, + "loss": 1.311, + "step": 5433 + }, + { + "epoch": 0.57, + "learning_rate": 9.306938645301862e-06, + "loss": 1.3615, + "step": 5434 + }, + { + "epoch": 0.57, + "learning_rate": 9.303287243013255e-06, + "loss": 1.3495, + "step": 5435 + }, + { + "epoch": 0.57, + "learning_rate": 9.29963593406626e-06, + "loss": 1.3899, + "step": 5436 + }, + { + "epoch": 0.57, + "learning_rate": 9.295984718950058e-06, + "loss": 1.3189, + "step": 5437 + }, + { + "epoch": 0.57, + "learning_rate": 9.292333598153813e-06, + "loss": 1.4199, + "step": 5438 + }, + { + "epoch": 0.57, + "learning_rate": 9.288682572166677e-06, + "loss": 1.4751, + "step": 5439 + }, + { + "epoch": 0.57, + "learning_rate": 9.285031641477804e-06, + "loss": 1.3435, + "step": 5440 + }, + { + "epoch": 0.57, + "learning_rate": 9.281380806576322e-06, + "loss": 1.2954, + "step": 5441 + }, + { + "epoch": 0.57, + "learning_rate": 9.277730067951341e-06, + "loss": 1.3414, + "step": 5442 + }, + { + "epoch": 0.57, + "learning_rate": 9.274079426091978e-06, + "loss": 1.3642, + "step": 5443 + }, + { + "epoch": 0.57, + "learning_rate": 9.27042888148732e-06, + "loss": 1.3651, + "step": 5444 + }, + { + "epoch": 0.57, + "learning_rate": 9.266778434626448e-06, + "loss": 1.3995, + "step": 5445 + }, + { + "epoch": 0.57, + "learning_rate": 9.263128085998421e-06, + "loss": 1.2692, + "step": 5446 + }, + { + "epoch": 0.57, + "learning_rate": 9.2594778360923e-06, + "loss": 1.4355, + "step": 5447 + }, + { + "epoch": 0.57, + "learning_rate": 9.255827685397124e-06, + "loss": 1.4262, + "step": 5448 + }, + { + "epoch": 0.57, + "learning_rate": 9.252177634401917e-06, + "loss": 1.3372, + "step": 5449 + }, + { + "epoch": 0.57, + "learning_rate": 9.248527683595685e-06, + "loss": 1.4603, + "step": 5450 + }, + { + "epoch": 0.57, + "learning_rate": 9.24487783346744e-06, + "loss": 1.446, + "step": 5451 + }, + { + "epoch": 0.57, + "learning_rate": 9.241228084506167e-06, + "loss": 1.4088, + "step": 5452 + }, + { + "epoch": 0.57, + "learning_rate": 9.237578437200832e-06, + "loss": 1.3074, + "step": 5453 + }, + { + "epoch": 0.57, + "learning_rate": 9.233928892040392e-06, + "loss": 1.4347, + "step": 5454 + }, + { + "epoch": 0.57, + "learning_rate": 9.230279449513802e-06, + "loss": 1.2982, + "step": 5455 + }, + { + "epoch": 0.57, + "learning_rate": 9.226630110109988e-06, + "loss": 1.2928, + "step": 5456 + }, + { + "epoch": 0.57, + "learning_rate": 9.222980874317869e-06, + "loss": 1.2849, + "step": 5457 + }, + { + "epoch": 0.57, + "learning_rate": 9.219331742626343e-06, + "loss": 1.3137, + "step": 5458 + }, + { + "epoch": 0.57, + "learning_rate": 9.215682715524309e-06, + "loss": 1.3523, + "step": 5459 + }, + { + "epoch": 0.57, + "learning_rate": 9.21203379350064e-06, + "loss": 1.381, + "step": 5460 + }, + { + "epoch": 0.57, + "learning_rate": 9.208384977044191e-06, + "loss": 1.286, + "step": 5461 + }, + { + "epoch": 0.57, + "learning_rate": 9.204736266643819e-06, + "loss": 1.3467, + "step": 5462 + }, + { + "epoch": 0.57, + "learning_rate": 9.201087662788353e-06, + "loss": 1.3582, + "step": 5463 + }, + { + "epoch": 0.57, + "learning_rate": 9.197439165966617e-06, + "loss": 1.3912, + "step": 5464 + }, + { + "epoch": 0.57, + "learning_rate": 9.193790776667402e-06, + "loss": 1.3144, + "step": 5465 + }, + { + "epoch": 0.57, + "learning_rate": 9.190142495379515e-06, + "loss": 1.3403, + "step": 5466 + }, + { + "epoch": 0.57, + "learning_rate": 9.186494322591725e-06, + "loss": 1.3253, + "step": 5467 + }, + { + "epoch": 0.57, + "learning_rate": 9.182846258792794e-06, + "loss": 1.2908, + "step": 5468 + }, + { + "epoch": 0.57, + "learning_rate": 9.179198304471463e-06, + "loss": 1.3486, + "step": 5469 + }, + { + "epoch": 0.57, + "learning_rate": 9.175550460116473e-06, + "loss": 1.3915, + "step": 5470 + }, + { + "epoch": 0.57, + "learning_rate": 9.171902726216538e-06, + "loss": 1.3441, + "step": 5471 + }, + { + "epoch": 0.57, + "learning_rate": 9.168255103260362e-06, + "loss": 1.3196, + "step": 5472 + }, + { + "epoch": 0.57, + "learning_rate": 9.164607591736627e-06, + "loss": 1.3279, + "step": 5473 + }, + { + "epoch": 0.57, + "learning_rate": 9.160960192134011e-06, + "loss": 1.2643, + "step": 5474 + }, + { + "epoch": 0.57, + "learning_rate": 9.157312904941174e-06, + "loss": 1.3327, + "step": 5475 + }, + { + "epoch": 0.57, + "learning_rate": 9.153665730646756e-06, + "loss": 1.4016, + "step": 5476 + }, + { + "epoch": 0.57, + "learning_rate": 9.150018669739378e-06, + "loss": 1.3614, + "step": 5477 + }, + { + "epoch": 0.57, + "learning_rate": 9.146371722707662e-06, + "loss": 1.3469, + "step": 5478 + }, + { + "epoch": 0.57, + "learning_rate": 9.142724890040204e-06, + "loss": 1.3625, + "step": 5479 + }, + { + "epoch": 0.57, + "learning_rate": 9.139078172225585e-06, + "loss": 1.3879, + "step": 5480 + }, + { + "epoch": 0.57, + "learning_rate": 9.135431569752362e-06, + "loss": 1.3738, + "step": 5481 + }, + { + "epoch": 0.57, + "learning_rate": 9.131785083109101e-06, + "loss": 1.3507, + "step": 5482 + }, + { + "epoch": 0.57, + "learning_rate": 9.128138712784331e-06, + "loss": 1.3681, + "step": 5483 + }, + { + "epoch": 0.58, + "learning_rate": 9.124492459266567e-06, + "loss": 1.332, + "step": 5484 + }, + { + "epoch": 0.58, + "learning_rate": 9.12084632304432e-06, + "loss": 1.4746, + "step": 5485 + }, + { + "epoch": 0.58, + "learning_rate": 9.11720030460608e-06, + "loss": 1.2775, + "step": 5486 + }, + { + "epoch": 0.58, + "learning_rate": 9.113554404440317e-06, + "loss": 1.2567, + "step": 5487 + }, + { + "epoch": 0.58, + "learning_rate": 9.10990862303548e-06, + "loss": 1.3935, + "step": 5488 + }, + { + "epoch": 0.58, + "learning_rate": 9.106262960880024e-06, + "loss": 1.3544, + "step": 5489 + }, + { + "epoch": 0.58, + "learning_rate": 9.102617418462365e-06, + "loss": 1.4023, + "step": 5490 + }, + { + "epoch": 0.58, + "learning_rate": 9.098971996270918e-06, + "loss": 1.3759, + "step": 5491 + }, + { + "epoch": 0.58, + "learning_rate": 9.095326694794064e-06, + "loss": 1.4165, + "step": 5492 + }, + { + "epoch": 0.58, + "learning_rate": 9.091681514520194e-06, + "loss": 1.3189, + "step": 5493 + }, + { + "epoch": 0.58, + "learning_rate": 9.088036455937663e-06, + "loss": 1.3135, + "step": 5494 + }, + { + "epoch": 0.58, + "learning_rate": 9.084391519534815e-06, + "loss": 1.3521, + "step": 5495 + }, + { + "epoch": 0.58, + "learning_rate": 9.080746705799971e-06, + "loss": 1.3314, + "step": 5496 + }, + { + "epoch": 0.58, + "learning_rate": 9.077102015221457e-06, + "loss": 1.3119, + "step": 5497 + }, + { + "epoch": 0.58, + "learning_rate": 9.073457448287557e-06, + "loss": 1.2895, + "step": 5498 + }, + { + "epoch": 0.58, + "learning_rate": 9.069813005486554e-06, + "loss": 1.3155, + "step": 5499 + }, + { + "epoch": 0.58, + "learning_rate": 9.066168687306701e-06, + "loss": 1.4048, + "step": 5500 + }, + { + "epoch": 0.58, + "learning_rate": 9.062524494236256e-06, + "loss": 1.3665, + "step": 5501 + }, + { + "epoch": 0.58, + "learning_rate": 9.058880426763442e-06, + "loss": 1.3258, + "step": 5502 + }, + { + "epoch": 0.58, + "learning_rate": 9.05523648537647e-06, + "loss": 1.3078, + "step": 5503 + }, + { + "epoch": 0.58, + "learning_rate": 9.051592670563527e-06, + "loss": 1.361, + "step": 5504 + }, + { + "epoch": 0.58, + "learning_rate": 9.047948982812801e-06, + "loss": 1.3557, + "step": 5505 + }, + { + "epoch": 0.58, + "learning_rate": 9.044305422612453e-06, + "loss": 1.5733, + "step": 5506 + }, + { + "epoch": 0.58, + "learning_rate": 9.040661990450617e-06, + "loss": 1.2835, + "step": 5507 + }, + { + "epoch": 0.58, + "learning_rate": 9.037018686815428e-06, + "loss": 1.311, + "step": 5508 + }, + { + "epoch": 0.58, + "learning_rate": 9.033375512194993e-06, + "loss": 1.3949, + "step": 5509 + }, + { + "epoch": 0.58, + "learning_rate": 9.029732467077405e-06, + "loss": 1.356, + "step": 5510 + }, + { + "epoch": 0.58, + "learning_rate": 9.026089551950727e-06, + "loss": 1.3695, + "step": 5511 + }, + { + "epoch": 0.58, + "learning_rate": 9.022446767303033e-06, + "loss": 1.3325, + "step": 5512 + }, + { + "epoch": 0.58, + "learning_rate": 9.018804113622353e-06, + "loss": 1.401, + "step": 5513 + }, + { + "epoch": 0.58, + "learning_rate": 9.015161591396713e-06, + "loss": 1.3632, + "step": 5514 + }, + { + "epoch": 0.58, + "learning_rate": 9.011519201114108e-06, + "loss": 1.3697, + "step": 5515 + }, + { + "epoch": 0.58, + "learning_rate": 9.007876943262538e-06, + "loss": 1.2604, + "step": 5516 + }, + { + "epoch": 0.58, + "learning_rate": 9.004234818329964e-06, + "loss": 1.3557, + "step": 5517 + }, + { + "epoch": 0.58, + "learning_rate": 9.000592826804342e-06, + "loss": 1.3248, + "step": 5518 + }, + { + "epoch": 0.58, + "learning_rate": 8.996950969173596e-06, + "loss": 1.3237, + "step": 5519 + }, + { + "epoch": 0.58, + "learning_rate": 8.99330924592565e-06, + "loss": 1.339, + "step": 5520 + }, + { + "epoch": 0.58, + "learning_rate": 8.989667657548402e-06, + "loss": 1.3218, + "step": 5521 + }, + { + "epoch": 0.58, + "learning_rate": 8.986026204529728e-06, + "loss": 1.3354, + "step": 5522 + }, + { + "epoch": 0.58, + "learning_rate": 8.982384887357484e-06, + "loss": 1.3011, + "step": 5523 + }, + { + "epoch": 0.58, + "learning_rate": 8.978743706519524e-06, + "loss": 1.3526, + "step": 5524 + }, + { + "epoch": 0.58, + "learning_rate": 8.975102662503666e-06, + "loss": 1.3298, + "step": 5525 + }, + { + "epoch": 0.58, + "learning_rate": 8.971461755797718e-06, + "loss": 1.328, + "step": 5526 + }, + { + "epoch": 0.58, + "learning_rate": 8.967820986889461e-06, + "loss": 1.3705, + "step": 5527 + }, + { + "epoch": 0.58, + "learning_rate": 8.964180356266676e-06, + "loss": 1.3814, + "step": 5528 + }, + { + "epoch": 0.58, + "learning_rate": 8.96053986441711e-06, + "loss": 1.37, + "step": 5529 + }, + { + "epoch": 0.58, + "learning_rate": 8.956899511828489e-06, + "loss": 1.3224, + "step": 5530 + }, + { + "epoch": 0.58, + "learning_rate": 8.953259298988536e-06, + "loss": 1.3416, + "step": 5531 + }, + { + "epoch": 0.58, + "learning_rate": 8.949619226384942e-06, + "loss": 1.4212, + "step": 5532 + }, + { + "epoch": 0.58, + "learning_rate": 8.945979294505383e-06, + "loss": 1.4145, + "step": 5533 + }, + { + "epoch": 0.58, + "learning_rate": 8.942339503837512e-06, + "loss": 1.2179, + "step": 5534 + }, + { + "epoch": 0.58, + "learning_rate": 8.938699854868976e-06, + "loss": 1.3239, + "step": 5535 + }, + { + "epoch": 0.58, + "learning_rate": 8.93506034808739e-06, + "loss": 1.3488, + "step": 5536 + }, + { + "epoch": 0.58, + "learning_rate": 8.931420983980357e-06, + "loss": 1.3283, + "step": 5537 + }, + { + "epoch": 0.58, + "learning_rate": 8.927781763035449e-06, + "loss": 1.3866, + "step": 5538 + }, + { + "epoch": 0.58, + "learning_rate": 8.924142685740239e-06, + "loss": 1.3877, + "step": 5539 + }, + { + "epoch": 0.58, + "learning_rate": 8.920503752582265e-06, + "loss": 1.2511, + "step": 5540 + }, + { + "epoch": 0.58, + "learning_rate": 8.916864964049056e-06, + "loss": 1.3581, + "step": 5541 + }, + { + "epoch": 0.58, + "learning_rate": 8.913226320628104e-06, + "loss": 1.387, + "step": 5542 + }, + { + "epoch": 0.58, + "learning_rate": 8.909587822806905e-06, + "loss": 1.3785, + "step": 5543 + }, + { + "epoch": 0.58, + "learning_rate": 8.905949471072921e-06, + "loss": 1.4302, + "step": 5544 + }, + { + "epoch": 0.58, + "learning_rate": 8.9023112659136e-06, + "loss": 1.439, + "step": 5545 + }, + { + "epoch": 0.58, + "learning_rate": 8.898673207816357e-06, + "loss": 1.3257, + "step": 5546 + }, + { + "epoch": 0.58, + "learning_rate": 8.895035297268611e-06, + "loss": 1.4237, + "step": 5547 + }, + { + "epoch": 0.58, + "learning_rate": 8.891397534757745e-06, + "loss": 1.3141, + "step": 5548 + }, + { + "epoch": 0.58, + "learning_rate": 8.887759920771127e-06, + "loss": 1.3069, + "step": 5549 + }, + { + "epoch": 0.58, + "learning_rate": 8.884122455796095e-06, + "loss": 1.2703, + "step": 5550 + }, + { + "epoch": 0.58, + "learning_rate": 8.880485140319986e-06, + "loss": 1.2929, + "step": 5551 + }, + { + "epoch": 0.58, + "learning_rate": 8.876847974830103e-06, + "loss": 1.3719, + "step": 5552 + }, + { + "epoch": 0.58, + "learning_rate": 8.873210959813731e-06, + "loss": 1.3481, + "step": 5553 + }, + { + "epoch": 0.58, + "learning_rate": 8.869574095758141e-06, + "loss": 1.3609, + "step": 5554 + }, + { + "epoch": 0.58, + "learning_rate": 8.865937383150577e-06, + "loss": 1.3137, + "step": 5555 + }, + { + "epoch": 0.58, + "learning_rate": 8.862300822478265e-06, + "loss": 1.3602, + "step": 5556 + }, + { + "epoch": 0.58, + "learning_rate": 8.858664414228409e-06, + "loss": 1.3142, + "step": 5557 + }, + { + "epoch": 0.58, + "learning_rate": 8.855028158888196e-06, + "loss": 1.288, + "step": 5558 + }, + { + "epoch": 0.58, + "learning_rate": 8.851392056944791e-06, + "loss": 1.3407, + "step": 5559 + }, + { + "epoch": 0.58, + "learning_rate": 8.847756108885342e-06, + "loss": 1.3118, + "step": 5560 + }, + { + "epoch": 0.58, + "learning_rate": 8.84412031519696e-06, + "loss": 1.3646, + "step": 5561 + }, + { + "epoch": 0.58, + "learning_rate": 8.840484676366761e-06, + "loss": 1.3896, + "step": 5562 + }, + { + "epoch": 0.58, + "learning_rate": 8.836849192881822e-06, + "loss": 1.3296, + "step": 5563 + }, + { + "epoch": 0.58, + "learning_rate": 8.833213865229208e-06, + "loss": 1.2918, + "step": 5564 + }, + { + "epoch": 0.58, + "learning_rate": 8.82957869389595e-06, + "loss": 1.4811, + "step": 5565 + }, + { + "epoch": 0.58, + "learning_rate": 8.82594367936908e-06, + "loss": 1.3877, + "step": 5566 + }, + { + "epoch": 0.58, + "learning_rate": 8.822308822135588e-06, + "loss": 1.3716, + "step": 5567 + }, + { + "epoch": 0.58, + "learning_rate": 8.818674122682456e-06, + "loss": 1.3204, + "step": 5568 + }, + { + "epoch": 0.58, + "learning_rate": 8.815039581496634e-06, + "loss": 1.326, + "step": 5569 + }, + { + "epoch": 0.58, + "learning_rate": 8.811405199065066e-06, + "loss": 1.3762, + "step": 5570 + }, + { + "epoch": 0.58, + "learning_rate": 8.807770975874658e-06, + "loss": 1.2944, + "step": 5571 + }, + { + "epoch": 0.58, + "learning_rate": 8.804136912412311e-06, + "loss": 1.3057, + "step": 5572 + }, + { + "epoch": 0.58, + "eval_loss": 1.4187605381011963, + "eval_runtime": 77.5157, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 5572 + }, + { + "epoch": 0.58, + "learning_rate": 8.800503009164884e-06, + "loss": 1.4144, + "step": 5573 + }, + { + "epoch": 0.58, + "learning_rate": 8.796869266619238e-06, + "loss": 1.2218, + "step": 5574 + }, + { + "epoch": 0.58, + "learning_rate": 8.793235685262197e-06, + "loss": 1.4445, + "step": 5575 + }, + { + "epoch": 0.58, + "learning_rate": 8.789602265580565e-06, + "loss": 1.3761, + "step": 5576 + }, + { + "epoch": 0.58, + "learning_rate": 8.78596900806113e-06, + "loss": 1.3762, + "step": 5577 + }, + { + "epoch": 0.58, + "learning_rate": 8.782335913190657e-06, + "loss": 1.3506, + "step": 5578 + }, + { + "epoch": 0.59, + "learning_rate": 8.778702981455883e-06, + "loss": 1.4183, + "step": 5579 + }, + { + "epoch": 0.59, + "learning_rate": 8.775070213343528e-06, + "loss": 1.3123, + "step": 5580 + }, + { + "epoch": 0.59, + "learning_rate": 8.771437609340291e-06, + "loss": 1.3168, + "step": 5581 + }, + { + "epoch": 0.59, + "learning_rate": 8.76780516993285e-06, + "loss": 1.3939, + "step": 5582 + }, + { + "epoch": 0.59, + "learning_rate": 8.764172895607856e-06, + "loss": 1.3317, + "step": 5583 + }, + { + "epoch": 0.59, + "learning_rate": 8.760540786851937e-06, + "loss": 1.3094, + "step": 5584 + }, + { + "epoch": 0.59, + "learning_rate": 8.756908844151708e-06, + "loss": 1.2853, + "step": 5585 + }, + { + "epoch": 0.59, + "learning_rate": 8.753277067993752e-06, + "loss": 1.2625, + "step": 5586 + }, + { + "epoch": 0.59, + "learning_rate": 8.74964545886464e-06, + "loss": 1.4246, + "step": 5587 + }, + { + "epoch": 0.59, + "learning_rate": 8.746014017250904e-06, + "loss": 1.2891, + "step": 5588 + }, + { + "epoch": 0.59, + "learning_rate": 8.742382743639071e-06, + "loss": 1.3135, + "step": 5589 + }, + { + "epoch": 0.59, + "learning_rate": 8.738751638515639e-06, + "loss": 1.3021, + "step": 5590 + }, + { + "epoch": 0.59, + "learning_rate": 8.735120702367082e-06, + "loss": 1.3398, + "step": 5591 + }, + { + "epoch": 0.59, + "learning_rate": 8.731489935679845e-06, + "loss": 1.4173, + "step": 5592 + }, + { + "epoch": 0.59, + "learning_rate": 8.727859338940367e-06, + "loss": 1.4129, + "step": 5593 + }, + { + "epoch": 0.59, + "learning_rate": 8.724228912635053e-06, + "loss": 1.3807, + "step": 5594 + }, + { + "epoch": 0.59, + "learning_rate": 8.720598657250284e-06, + "loss": 1.2962, + "step": 5595 + }, + { + "epoch": 0.59, + "learning_rate": 8.716968573272416e-06, + "loss": 1.3784, + "step": 5596 + }, + { + "epoch": 0.59, + "learning_rate": 8.713338661187799e-06, + "loss": 1.3751, + "step": 5597 + }, + { + "epoch": 0.59, + "learning_rate": 8.70970892148274e-06, + "loss": 1.3122, + "step": 5598 + }, + { + "epoch": 0.59, + "learning_rate": 8.70607935464353e-06, + "loss": 1.4174, + "step": 5599 + }, + { + "epoch": 0.59, + "learning_rate": 8.702449961156445e-06, + "loss": 1.3275, + "step": 5600 + }, + { + "epoch": 0.59, + "learning_rate": 8.698820741507723e-06, + "loss": 1.33, + "step": 5601 + }, + { + "epoch": 0.59, + "learning_rate": 8.695191696183589e-06, + "loss": 1.4075, + "step": 5602 + }, + { + "epoch": 0.59, + "learning_rate": 8.69156282567024e-06, + "loss": 1.3778, + "step": 5603 + }, + { + "epoch": 0.59, + "learning_rate": 8.687934130453857e-06, + "loss": 1.3222, + "step": 5604 + }, + { + "epoch": 0.59, + "learning_rate": 8.684305611020587e-06, + "loss": 1.3443, + "step": 5605 + }, + { + "epoch": 0.59, + "learning_rate": 8.680677267856558e-06, + "loss": 1.3167, + "step": 5606 + }, + { + "epoch": 0.59, + "learning_rate": 8.677049101447877e-06, + "loss": 1.3209, + "step": 5607 + }, + { + "epoch": 0.59, + "learning_rate": 8.673421112280624e-06, + "loss": 1.3125, + "step": 5608 + }, + { + "epoch": 0.59, + "learning_rate": 8.669793300840857e-06, + "loss": 1.375, + "step": 5609 + }, + { + "epoch": 0.59, + "learning_rate": 8.666165667614612e-06, + "loss": 1.3627, + "step": 5610 + }, + { + "epoch": 0.59, + "learning_rate": 8.662538213087888e-06, + "loss": 1.3064, + "step": 5611 + }, + { + "epoch": 0.59, + "learning_rate": 8.658910937746685e-06, + "loss": 1.4251, + "step": 5612 + }, + { + "epoch": 0.59, + "learning_rate": 8.655283842076956e-06, + "loss": 1.3011, + "step": 5613 + }, + { + "epoch": 0.59, + "learning_rate": 8.651656926564645e-06, + "loss": 1.3299, + "step": 5614 + }, + { + "epoch": 0.59, + "learning_rate": 8.648030191695653e-06, + "loss": 1.3448, + "step": 5615 + }, + { + "epoch": 0.59, + "learning_rate": 8.644403637955883e-06, + "loss": 1.4048, + "step": 5616 + }, + { + "epoch": 0.59, + "learning_rate": 8.640777265831195e-06, + "loss": 1.336, + "step": 5617 + }, + { + "epoch": 0.59, + "learning_rate": 8.63715107580743e-06, + "loss": 1.4959, + "step": 5618 + }, + { + "epoch": 0.59, + "learning_rate": 8.633525068370397e-06, + "loss": 1.3822, + "step": 5619 + }, + { + "epoch": 0.59, + "learning_rate": 8.6298992440059e-06, + "loss": 1.282, + "step": 5620 + }, + { + "epoch": 0.59, + "learning_rate": 8.626273603199699e-06, + "loss": 1.1873, + "step": 5621 + }, + { + "epoch": 0.59, + "learning_rate": 8.622648146437538e-06, + "loss": 1.3706, + "step": 5622 + }, + { + "epoch": 0.59, + "learning_rate": 8.619022874205138e-06, + "loss": 1.2709, + "step": 5623 + }, + { + "epoch": 0.59, + "learning_rate": 8.615397786988188e-06, + "loss": 1.3608, + "step": 5624 + }, + { + "epoch": 0.59, + "learning_rate": 8.61177288527236e-06, + "loss": 1.3821, + "step": 5625 + }, + { + "epoch": 0.59, + "learning_rate": 8.608148169543292e-06, + "loss": 1.327, + "step": 5626 + }, + { + "epoch": 0.59, + "learning_rate": 8.604523640286611e-06, + "loss": 1.3544, + "step": 5627 + }, + { + "epoch": 0.59, + "learning_rate": 8.600899297987905e-06, + "loss": 1.3269, + "step": 5628 + }, + { + "epoch": 0.59, + "learning_rate": 8.597275143132745e-06, + "loss": 1.3142, + "step": 5629 + }, + { + "epoch": 0.59, + "learning_rate": 8.593651176206671e-06, + "loss": 1.3878, + "step": 5630 + }, + { + "epoch": 0.59, + "learning_rate": 8.59002739769521e-06, + "loss": 1.3386, + "step": 5631 + }, + { + "epoch": 0.59, + "learning_rate": 8.586403808083846e-06, + "loss": 1.3484, + "step": 5632 + }, + { + "epoch": 0.59, + "learning_rate": 8.582780407858052e-06, + "loss": 1.3676, + "step": 5633 + }, + { + "epoch": 0.59, + "learning_rate": 8.579157197503265e-06, + "loss": 1.3753, + "step": 5634 + }, + { + "epoch": 0.59, + "learning_rate": 8.57553417750491e-06, + "loss": 1.4058, + "step": 5635 + }, + { + "epoch": 0.59, + "learning_rate": 8.571911348348375e-06, + "loss": 1.4434, + "step": 5636 + }, + { + "epoch": 0.59, + "learning_rate": 8.568288710519027e-06, + "loss": 1.3398, + "step": 5637 + }, + { + "epoch": 0.59, + "learning_rate": 8.564666264502199e-06, + "loss": 1.3294, + "step": 5638 + }, + { + "epoch": 0.59, + "learning_rate": 8.561044010783216e-06, + "loss": 1.3165, + "step": 5639 + }, + { + "epoch": 0.59, + "learning_rate": 8.557421949847363e-06, + "loss": 1.3437, + "step": 5640 + }, + { + "epoch": 0.59, + "learning_rate": 8.553800082179905e-06, + "loss": 1.3473, + "step": 5641 + }, + { + "epoch": 0.59, + "learning_rate": 8.55017840826607e-06, + "loss": 1.3378, + "step": 5642 + }, + { + "epoch": 0.59, + "learning_rate": 8.546556928591082e-06, + "loss": 1.3357, + "step": 5643 + }, + { + "epoch": 0.59, + "learning_rate": 8.54293564364012e-06, + "loss": 1.3435, + "step": 5644 + }, + { + "epoch": 0.59, + "learning_rate": 8.53931455389834e-06, + "loss": 1.3335, + "step": 5645 + }, + { + "epoch": 0.59, + "learning_rate": 8.535693659850885e-06, + "loss": 1.2917, + "step": 5646 + }, + { + "epoch": 0.59, + "learning_rate": 8.532072961982851e-06, + "loss": 1.3785, + "step": 5647 + }, + { + "epoch": 0.59, + "learning_rate": 8.528452460779327e-06, + "loss": 1.3634, + "step": 5648 + }, + { + "epoch": 0.59, + "learning_rate": 8.524832156725359e-06, + "loss": 1.3541, + "step": 5649 + }, + { + "epoch": 0.59, + "learning_rate": 8.521212050305978e-06, + "loss": 1.335, + "step": 5650 + }, + { + "epoch": 0.59, + "learning_rate": 8.51759214200619e-06, + "loss": 1.3011, + "step": 5651 + }, + { + "epoch": 0.59, + "learning_rate": 8.513972432310965e-06, + "loss": 1.3982, + "step": 5652 + }, + { + "epoch": 0.59, + "learning_rate": 8.510352921705247e-06, + "loss": 1.3217, + "step": 5653 + }, + { + "epoch": 0.59, + "learning_rate": 8.506733610673968e-06, + "loss": 1.3275, + "step": 5654 + }, + { + "epoch": 0.59, + "learning_rate": 8.503114499702015e-06, + "loss": 1.3335, + "step": 5655 + }, + { + "epoch": 0.59, + "learning_rate": 8.499495589274257e-06, + "loss": 1.3567, + "step": 5656 + }, + { + "epoch": 0.59, + "learning_rate": 8.495876879875536e-06, + "loss": 1.348, + "step": 5657 + }, + { + "epoch": 0.59, + "learning_rate": 8.492258371990667e-06, + "loss": 1.3991, + "step": 5658 + }, + { + "epoch": 0.59, + "learning_rate": 8.488640066104435e-06, + "loss": 1.3528, + "step": 5659 + }, + { + "epoch": 0.59, + "learning_rate": 8.485021962701603e-06, + "loss": 1.3275, + "step": 5660 + }, + { + "epoch": 0.59, + "learning_rate": 8.481404062266897e-06, + "loss": 1.3605, + "step": 5661 + }, + { + "epoch": 0.59, + "learning_rate": 8.477786365285032e-06, + "loss": 1.3288, + "step": 5662 + }, + { + "epoch": 0.59, + "learning_rate": 8.474168872240682e-06, + "loss": 1.3274, + "step": 5663 + }, + { + "epoch": 0.59, + "learning_rate": 8.470551583618498e-06, + "loss": 1.273, + "step": 5664 + }, + { + "epoch": 0.59, + "learning_rate": 8.4669344999031e-06, + "loss": 1.3142, + "step": 5665 + }, + { + "epoch": 0.59, + "learning_rate": 8.463317621579091e-06, + "loss": 1.2912, + "step": 5666 + }, + { + "epoch": 0.59, + "learning_rate": 8.459700949131037e-06, + "loss": 1.3162, + "step": 5667 + }, + { + "epoch": 0.59, + "learning_rate": 8.456084483043479e-06, + "loss": 1.3377, + "step": 5668 + }, + { + "epoch": 0.59, + "learning_rate": 8.452468223800931e-06, + "loss": 1.3545, + "step": 5669 + }, + { + "epoch": 0.59, + "learning_rate": 8.448852171887878e-06, + "loss": 1.4052, + "step": 5670 + }, + { + "epoch": 0.59, + "learning_rate": 8.44523632778878e-06, + "loss": 1.3389, + "step": 5671 + }, + { + "epoch": 0.59, + "learning_rate": 8.441620691988063e-06, + "loss": 1.3801, + "step": 5672 + }, + { + "epoch": 0.59, + "learning_rate": 8.438005264970134e-06, + "loss": 1.2978, + "step": 5673 + }, + { + "epoch": 0.6, + "learning_rate": 8.434390047219366e-06, + "loss": 1.437, + "step": 5674 + }, + { + "epoch": 0.6, + "learning_rate": 8.430775039220103e-06, + "loss": 1.3602, + "step": 5675 + }, + { + "epoch": 0.6, + "learning_rate": 8.427160241456664e-06, + "loss": 1.4971, + "step": 5676 + }, + { + "epoch": 0.6, + "learning_rate": 8.423545654413342e-06, + "loss": 1.2765, + "step": 5677 + }, + { + "epoch": 0.6, + "learning_rate": 8.419931278574397e-06, + "loss": 1.4346, + "step": 5678 + }, + { + "epoch": 0.6, + "learning_rate": 8.416317114424059e-06, + "loss": 1.366, + "step": 5679 + }, + { + "epoch": 0.6, + "learning_rate": 8.412703162446536e-06, + "loss": 1.3776, + "step": 5680 + }, + { + "epoch": 0.6, + "learning_rate": 8.409089423126009e-06, + "loss": 1.2516, + "step": 5681 + }, + { + "epoch": 0.6, + "learning_rate": 8.405475896946621e-06, + "loss": 1.4257, + "step": 5682 + }, + { + "epoch": 0.6, + "learning_rate": 8.401862584392492e-06, + "loss": 1.3523, + "step": 5683 + }, + { + "epoch": 0.6, + "learning_rate": 8.398249485947712e-06, + "loss": 1.3791, + "step": 5684 + }, + { + "epoch": 0.6, + "learning_rate": 8.394636602096348e-06, + "loss": 1.3574, + "step": 5685 + }, + { + "epoch": 0.6, + "learning_rate": 8.39102393332243e-06, + "loss": 1.4748, + "step": 5686 + }, + { + "epoch": 0.6, + "learning_rate": 8.387411480109967e-06, + "loss": 1.3693, + "step": 5687 + }, + { + "epoch": 0.6, + "learning_rate": 8.383799242942925e-06, + "loss": 1.3643, + "step": 5688 + }, + { + "epoch": 0.6, + "learning_rate": 8.38018722230526e-06, + "loss": 1.3446, + "step": 5689 + }, + { + "epoch": 0.6, + "learning_rate": 8.37657541868089e-06, + "loss": 1.3552, + "step": 5690 + }, + { + "epoch": 0.6, + "learning_rate": 8.372963832553698e-06, + "loss": 1.3636, + "step": 5691 + }, + { + "epoch": 0.6, + "learning_rate": 8.36935246440755e-06, + "loss": 1.3398, + "step": 5692 + }, + { + "epoch": 0.6, + "learning_rate": 8.365741314726273e-06, + "loss": 1.3336, + "step": 5693 + }, + { + "epoch": 0.6, + "learning_rate": 8.362130383993667e-06, + "loss": 1.3023, + "step": 5694 + }, + { + "epoch": 0.6, + "learning_rate": 8.358519672693506e-06, + "loss": 1.3591, + "step": 5695 + }, + { + "epoch": 0.6, + "learning_rate": 8.354909181309533e-06, + "loss": 1.3113, + "step": 5696 + }, + { + "epoch": 0.6, + "learning_rate": 8.351298910325462e-06, + "loss": 1.3747, + "step": 5697 + }, + { + "epoch": 0.6, + "learning_rate": 8.347688860224976e-06, + "loss": 1.3555, + "step": 5698 + }, + { + "epoch": 0.6, + "learning_rate": 8.344079031491722e-06, + "loss": 1.2947, + "step": 5699 + }, + { + "epoch": 0.6, + "learning_rate": 8.340469424609337e-06, + "loss": 1.4099, + "step": 5700 + }, + { + "epoch": 0.6, + "learning_rate": 8.336860040061404e-06, + "loss": 1.3263, + "step": 5701 + }, + { + "epoch": 0.6, + "learning_rate": 8.333250878331498e-06, + "loss": 1.372, + "step": 5702 + }, + { + "epoch": 0.6, + "learning_rate": 8.329641939903142e-06, + "loss": 1.3523, + "step": 5703 + }, + { + "epoch": 0.6, + "learning_rate": 8.32603322525985e-06, + "loss": 1.3451, + "step": 5704 + }, + { + "epoch": 0.6, + "learning_rate": 8.322424734885098e-06, + "loss": 1.3296, + "step": 5705 + }, + { + "epoch": 0.6, + "learning_rate": 8.318816469262325e-06, + "loss": 1.449, + "step": 5706 + }, + { + "epoch": 0.6, + "learning_rate": 8.315208428874946e-06, + "loss": 1.3611, + "step": 5707 + }, + { + "epoch": 0.6, + "learning_rate": 8.311600614206352e-06, + "loss": 1.3849, + "step": 5708 + }, + { + "epoch": 0.6, + "learning_rate": 8.307993025739893e-06, + "loss": 1.3968, + "step": 5709 + }, + { + "epoch": 0.6, + "learning_rate": 8.304385663958895e-06, + "loss": 1.4428, + "step": 5710 + }, + { + "epoch": 0.6, + "learning_rate": 8.300778529346647e-06, + "loss": 1.3095, + "step": 5711 + }, + { + "epoch": 0.6, + "learning_rate": 8.297171622386418e-06, + "loss": 1.3135, + "step": 5712 + }, + { + "epoch": 0.6, + "learning_rate": 8.293564943561438e-06, + "loss": 1.3069, + "step": 5713 + }, + { + "epoch": 0.6, + "learning_rate": 8.28995849335491e-06, + "loss": 1.3736, + "step": 5714 + }, + { + "epoch": 0.6, + "learning_rate": 8.286352272250007e-06, + "loss": 1.343, + "step": 5715 + }, + { + "epoch": 0.6, + "learning_rate": 8.28274628072987e-06, + "loss": 1.2929, + "step": 5716 + }, + { + "epoch": 0.6, + "learning_rate": 8.279140519277607e-06, + "loss": 1.3356, + "step": 5717 + }, + { + "epoch": 0.6, + "learning_rate": 8.275534988376295e-06, + "loss": 1.2683, + "step": 5718 + }, + { + "epoch": 0.6, + "learning_rate": 8.27192968850899e-06, + "loss": 1.3738, + "step": 5719 + }, + { + "epoch": 0.6, + "learning_rate": 8.268324620158704e-06, + "loss": 1.3369, + "step": 5720 + }, + { + "epoch": 0.6, + "learning_rate": 8.264719783808425e-06, + "loss": 1.3684, + "step": 5721 + }, + { + "epoch": 0.6, + "learning_rate": 8.261115179941108e-06, + "loss": 1.4081, + "step": 5722 + }, + { + "epoch": 0.6, + "learning_rate": 8.257510809039678e-06, + "loss": 1.2504, + "step": 5723 + }, + { + "epoch": 0.6, + "learning_rate": 8.253906671587029e-06, + "loss": 1.417, + "step": 5724 + }, + { + "epoch": 0.6, + "learning_rate": 8.25030276806602e-06, + "loss": 1.3631, + "step": 5725 + }, + { + "epoch": 0.6, + "learning_rate": 8.246699098959483e-06, + "loss": 1.499, + "step": 5726 + }, + { + "epoch": 0.6, + "learning_rate": 8.243095664750217e-06, + "loss": 1.3656, + "step": 5727 + }, + { + "epoch": 0.6, + "learning_rate": 8.239492465920992e-06, + "loss": 1.3563, + "step": 5728 + }, + { + "epoch": 0.6, + "learning_rate": 8.23588950295454e-06, + "loss": 1.3554, + "step": 5729 + }, + { + "epoch": 0.6, + "learning_rate": 8.232286776333566e-06, + "loss": 1.2705, + "step": 5730 + }, + { + "epoch": 0.6, + "learning_rate": 8.228684286540747e-06, + "loss": 1.3792, + "step": 5731 + }, + { + "epoch": 0.6, + "learning_rate": 8.22508203405872e-06, + "loss": 1.3301, + "step": 5732 + }, + { + "epoch": 0.6, + "learning_rate": 8.221480019370095e-06, + "loss": 1.36, + "step": 5733 + }, + { + "epoch": 0.6, + "learning_rate": 8.217878242957448e-06, + "loss": 1.4406, + "step": 5734 + }, + { + "epoch": 0.6, + "learning_rate": 8.214276705303328e-06, + "loss": 1.2886, + "step": 5735 + }, + { + "epoch": 0.6, + "learning_rate": 8.210675406890248e-06, + "loss": 1.3072, + "step": 5736 + }, + { + "epoch": 0.6, + "learning_rate": 8.207074348200686e-06, + "loss": 1.3734, + "step": 5737 + }, + { + "epoch": 0.6, + "learning_rate": 8.203473529717095e-06, + "loss": 1.3893, + "step": 5738 + }, + { + "epoch": 0.6, + "learning_rate": 8.199872951921892e-06, + "loss": 1.3427, + "step": 5739 + }, + { + "epoch": 0.6, + "learning_rate": 8.196272615297459e-06, + "loss": 1.3125, + "step": 5740 + }, + { + "epoch": 0.6, + "learning_rate": 8.19267252032615e-06, + "loss": 1.3079, + "step": 5741 + }, + { + "epoch": 0.6, + "learning_rate": 8.189072667490285e-06, + "loss": 1.2971, + "step": 5742 + }, + { + "epoch": 0.6, + "learning_rate": 8.185473057272154e-06, + "loss": 1.3003, + "step": 5743 + }, + { + "epoch": 0.6, + "learning_rate": 8.18187369015401e-06, + "loss": 1.3002, + "step": 5744 + }, + { + "epoch": 0.6, + "learning_rate": 8.178274566618075e-06, + "loss": 1.2852, + "step": 5745 + }, + { + "epoch": 0.6, + "learning_rate": 8.174675687146542e-06, + "loss": 1.2807, + "step": 5746 + }, + { + "epoch": 0.6, + "learning_rate": 8.171077052221567e-06, + "loss": 1.2983, + "step": 5747 + }, + { + "epoch": 0.6, + "learning_rate": 8.167478662325274e-06, + "loss": 1.3002, + "step": 5748 + }, + { + "epoch": 0.6, + "learning_rate": 8.163880517939753e-06, + "loss": 1.2575, + "step": 5749 + }, + { + "epoch": 0.6, + "learning_rate": 8.160282619547068e-06, + "loss": 1.2627, + "step": 5750 + }, + { + "epoch": 0.6, + "learning_rate": 8.156684967629242e-06, + "loss": 1.2549, + "step": 5751 + }, + { + "epoch": 0.6, + "learning_rate": 8.153087562668265e-06, + "loss": 1.2595, + "step": 5752 + }, + { + "epoch": 0.6, + "learning_rate": 8.1494904051461e-06, + "loss": 1.2788, + "step": 5753 + }, + { + "epoch": 0.6, + "learning_rate": 8.145893495544676e-06, + "loss": 1.3028, + "step": 5754 + }, + { + "epoch": 0.6, + "learning_rate": 8.142296834345883e-06, + "loss": 1.3019, + "step": 5755 + }, + { + "epoch": 0.6, + "learning_rate": 8.138700422031583e-06, + "loss": 1.2998, + "step": 5756 + }, + { + "epoch": 0.6, + "learning_rate": 8.135104259083598e-06, + "loss": 1.3298, + "step": 5757 + }, + { + "epoch": 0.6, + "learning_rate": 8.13150834598373e-06, + "loss": 1.2681, + "step": 5758 + }, + { + "epoch": 0.6, + "learning_rate": 8.127912683213733e-06, + "loss": 1.2987, + "step": 5759 + }, + { + "epoch": 0.6, + "learning_rate": 8.124317271255331e-06, + "loss": 1.3181, + "step": 5760 + }, + { + "epoch": 0.6, + "learning_rate": 8.120722110590224e-06, + "loss": 1.423, + "step": 5761 + }, + { + "epoch": 0.6, + "learning_rate": 8.117127201700067e-06, + "loss": 1.5029, + "step": 5762 + }, + { + "epoch": 0.6, + "learning_rate": 8.113532545066488e-06, + "loss": 1.3016, + "step": 5763 + }, + { + "epoch": 0.6, + "learning_rate": 8.109938141171074e-06, + "loss": 1.3906, + "step": 5764 + }, + { + "epoch": 0.6, + "learning_rate": 8.106343990495387e-06, + "loss": 1.3363, + "step": 5765 + }, + { + "epoch": 0.6, + "learning_rate": 8.10275009352095e-06, + "loss": 1.314, + "step": 5766 + }, + { + "epoch": 0.6, + "learning_rate": 8.09915645072925e-06, + "loss": 1.3484, + "step": 5767 + }, + { + "epoch": 0.6, + "learning_rate": 8.095563062601745e-06, + "loss": 1.3757, + "step": 5768 + }, + { + "epoch": 0.6, + "learning_rate": 8.091969929619859e-06, + "loss": 1.3068, + "step": 5769 + }, + { + "epoch": 0.61, + "learning_rate": 8.088377052264976e-06, + "loss": 1.3486, + "step": 5770 + }, + { + "epoch": 0.61, + "learning_rate": 8.08478443101845e-06, + "loss": 1.244, + "step": 5771 + }, + { + "epoch": 0.61, + "eval_loss": 1.4178493022918701, + "eval_runtime": 77.6086, + "eval_samples_per_second": 1.662, + "eval_steps_per_second": 0.116, + "step": 5771 + }, + { + "epoch": 0.61, + "learning_rate": 8.0811920663616e-06, + "loss": 1.3325, + "step": 5772 + }, + { + "epoch": 0.61, + "learning_rate": 8.077599958775713e-06, + "loss": 1.336, + "step": 5773 + }, + { + "epoch": 0.61, + "learning_rate": 8.074008108742037e-06, + "loss": 1.3167, + "step": 5774 + }, + { + "epoch": 0.61, + "learning_rate": 8.070416516741786e-06, + "loss": 1.3166, + "step": 5775 + }, + { + "epoch": 0.61, + "learning_rate": 8.066825183256141e-06, + "loss": 1.3377, + "step": 5776 + }, + { + "epoch": 0.61, + "learning_rate": 8.063234108766253e-06, + "loss": 1.3704, + "step": 5777 + }, + { + "epoch": 0.61, + "learning_rate": 8.059643293753233e-06, + "loss": 1.3596, + "step": 5778 + }, + { + "epoch": 0.61, + "learning_rate": 8.056052738698153e-06, + "loss": 1.4477, + "step": 5779 + }, + { + "epoch": 0.61, + "learning_rate": 8.052462444082055e-06, + "loss": 1.338, + "step": 5780 + }, + { + "epoch": 0.61, + "learning_rate": 8.048872410385952e-06, + "loss": 1.2714, + "step": 5781 + }, + { + "epoch": 0.61, + "learning_rate": 8.045282638090815e-06, + "loss": 0.9642, + "step": 5782 + }, + { + "epoch": 0.61, + "learning_rate": 8.041693127677576e-06, + "loss": 0.8702, + "step": 5783 + }, + { + "epoch": 0.61, + "learning_rate": 8.038103879627144e-06, + "loss": 0.8986, + "step": 5784 + }, + { + "epoch": 0.61, + "learning_rate": 8.034514894420382e-06, + "loss": 0.804, + "step": 5785 + }, + { + "epoch": 0.61, + "learning_rate": 8.030926172538122e-06, + "loss": 0.7958, + "step": 5786 + }, + { + "epoch": 0.61, + "learning_rate": 8.02733771446116e-06, + "loss": 0.7608, + "step": 5787 + }, + { + "epoch": 0.61, + "learning_rate": 8.023749520670261e-06, + "loss": 0.7792, + "step": 5788 + }, + { + "epoch": 0.61, + "learning_rate": 8.020161591646147e-06, + "loss": 0.7293, + "step": 5789 + }, + { + "epoch": 0.61, + "learning_rate": 8.016573927869511e-06, + "loss": 1.1287, + "step": 5790 + }, + { + "epoch": 0.61, + "learning_rate": 8.012986529821004e-06, + "loss": 1.3344, + "step": 5791 + }, + { + "epoch": 0.61, + "learning_rate": 8.009399397981248e-06, + "loss": 1.4415, + "step": 5792 + }, + { + "epoch": 0.61, + "learning_rate": 8.005812532830826e-06, + "loss": 1.4265, + "step": 5793 + }, + { + "epoch": 0.61, + "learning_rate": 8.002225934850287e-06, + "loss": 1.3429, + "step": 5794 + }, + { + "epoch": 0.61, + "learning_rate": 7.998639604520137e-06, + "loss": 1.3653, + "step": 5795 + }, + { + "epoch": 0.61, + "learning_rate": 7.995053542320861e-06, + "loss": 1.486, + "step": 5796 + }, + { + "epoch": 0.61, + "learning_rate": 7.991467748732894e-06, + "loss": 1.3389, + "step": 5797 + }, + { + "epoch": 0.61, + "learning_rate": 7.98788222423664e-06, + "loss": 1.3206, + "step": 5798 + }, + { + "epoch": 0.61, + "learning_rate": 7.984296969312468e-06, + "loss": 1.3121, + "step": 5799 + }, + { + "epoch": 0.61, + "learning_rate": 7.980711984440712e-06, + "loss": 1.3512, + "step": 5800 + }, + { + "epoch": 0.61, + "learning_rate": 7.977127270101665e-06, + "loss": 1.3291, + "step": 5801 + }, + { + "epoch": 0.61, + "learning_rate": 7.97354282677559e-06, + "loss": 1.3948, + "step": 5802 + }, + { + "epoch": 0.61, + "learning_rate": 7.969958654942704e-06, + "loss": 1.3076, + "step": 5803 + }, + { + "epoch": 0.61, + "learning_rate": 7.966374755083202e-06, + "loss": 1.3838, + "step": 5804 + }, + { + "epoch": 0.61, + "learning_rate": 7.962791127677228e-06, + "loss": 1.4205, + "step": 5805 + }, + { + "epoch": 0.61, + "learning_rate": 7.959207773204899e-06, + "loss": 1.3635, + "step": 5806 + }, + { + "epoch": 0.61, + "learning_rate": 7.955624692146293e-06, + "loss": 1.3299, + "step": 5807 + }, + { + "epoch": 0.61, + "learning_rate": 7.95204188498145e-06, + "loss": 1.4435, + "step": 5808 + }, + { + "epoch": 0.61, + "learning_rate": 7.948459352190372e-06, + "loss": 1.4335, + "step": 5809 + }, + { + "epoch": 0.61, + "learning_rate": 7.944877094253027e-06, + "loss": 1.3391, + "step": 5810 + }, + { + "epoch": 0.61, + "learning_rate": 7.94129511164935e-06, + "loss": 1.2852, + "step": 5811 + }, + { + "epoch": 0.61, + "learning_rate": 7.93771340485923e-06, + "loss": 1.3174, + "step": 5812 + }, + { + "epoch": 0.61, + "learning_rate": 7.934131974362527e-06, + "loss": 1.3415, + "step": 5813 + }, + { + "epoch": 0.61, + "learning_rate": 7.930550820639055e-06, + "loss": 1.2764, + "step": 5814 + }, + { + "epoch": 0.61, + "learning_rate": 7.926969944168603e-06, + "loss": 1.2978, + "step": 5815 + }, + { + "epoch": 0.61, + "learning_rate": 7.923389345430911e-06, + "loss": 1.3046, + "step": 5816 + }, + { + "epoch": 0.61, + "learning_rate": 7.919809024905694e-06, + "loss": 1.3484, + "step": 5817 + }, + { + "epoch": 0.61, + "learning_rate": 7.916228983072614e-06, + "loss": 1.3207, + "step": 5818 + }, + { + "epoch": 0.61, + "learning_rate": 7.912649220411312e-06, + "loss": 1.4289, + "step": 5819 + }, + { + "epoch": 0.61, + "learning_rate": 7.909069737401382e-06, + "loss": 1.4359, + "step": 5820 + }, + { + "epoch": 0.61, + "learning_rate": 7.905490534522384e-06, + "loss": 1.3316, + "step": 5821 + }, + { + "epoch": 0.61, + "learning_rate": 7.901911612253834e-06, + "loss": 1.3112, + "step": 5822 + }, + { + "epoch": 0.61, + "learning_rate": 7.898332971075221e-06, + "loss": 1.3318, + "step": 5823 + }, + { + "epoch": 0.61, + "learning_rate": 7.894754611465992e-06, + "loss": 1.4373, + "step": 5824 + }, + { + "epoch": 0.61, + "learning_rate": 7.891176533905549e-06, + "loss": 1.2938, + "step": 5825 + }, + { + "epoch": 0.61, + "learning_rate": 7.887598738873266e-06, + "loss": 1.3471, + "step": 5826 + }, + { + "epoch": 0.61, + "learning_rate": 7.884021226848478e-06, + "loss": 1.2999, + "step": 5827 + }, + { + "epoch": 0.61, + "learning_rate": 7.880443998310475e-06, + "loss": 1.35, + "step": 5828 + }, + { + "epoch": 0.61, + "learning_rate": 7.876867053738517e-06, + "loss": 1.3307, + "step": 5829 + }, + { + "epoch": 0.61, + "learning_rate": 7.87329039361182e-06, + "loss": 1.393, + "step": 5830 + }, + { + "epoch": 0.61, + "learning_rate": 7.869714018409568e-06, + "loss": 1.2933, + "step": 5831 + }, + { + "epoch": 0.61, + "learning_rate": 7.866137928610903e-06, + "loss": 1.319, + "step": 5832 + }, + { + "epoch": 0.61, + "learning_rate": 7.862562124694925e-06, + "loss": 1.3088, + "step": 5833 + }, + { + "epoch": 0.61, + "learning_rate": 7.858986607140705e-06, + "loss": 1.2941, + "step": 5834 + }, + { + "epoch": 0.61, + "learning_rate": 7.855411376427267e-06, + "loss": 1.3214, + "step": 5835 + }, + { + "epoch": 0.61, + "learning_rate": 7.851836433033602e-06, + "loss": 1.2991, + "step": 5836 + }, + { + "epoch": 0.61, + "learning_rate": 7.848261777438656e-06, + "loss": 1.3117, + "step": 5837 + }, + { + "epoch": 0.61, + "learning_rate": 7.844687410121348e-06, + "loss": 1.2905, + "step": 5838 + }, + { + "epoch": 0.61, + "learning_rate": 7.841113331560548e-06, + "loss": 1.3688, + "step": 5839 + }, + { + "epoch": 0.61, + "learning_rate": 7.837539542235091e-06, + "loss": 1.3987, + "step": 5840 + }, + { + "epoch": 0.61, + "learning_rate": 7.83396604262377e-06, + "loss": 1.2693, + "step": 5841 + }, + { + "epoch": 0.61, + "learning_rate": 7.830392833205348e-06, + "loss": 1.3205, + "step": 5842 + }, + { + "epoch": 0.61, + "learning_rate": 7.826819914458538e-06, + "loss": 1.3325, + "step": 5843 + }, + { + "epoch": 0.61, + "learning_rate": 7.823247286862024e-06, + "loss": 1.3451, + "step": 5844 + }, + { + "epoch": 0.61, + "learning_rate": 7.81967495089444e-06, + "loss": 1.3484, + "step": 5845 + }, + { + "epoch": 0.61, + "learning_rate": 7.816102907034395e-06, + "loss": 1.4949, + "step": 5846 + }, + { + "epoch": 0.61, + "learning_rate": 7.812531155760445e-06, + "loss": 1.4293, + "step": 5847 + }, + { + "epoch": 0.61, + "learning_rate": 7.808959697551113e-06, + "loss": 1.4314, + "step": 5848 + }, + { + "epoch": 0.61, + "learning_rate": 7.805388532884887e-06, + "loss": 1.3188, + "step": 5849 + }, + { + "epoch": 0.61, + "learning_rate": 7.80181766224021e-06, + "loss": 1.4396, + "step": 5850 + }, + { + "epoch": 0.61, + "learning_rate": 7.798247086095484e-06, + "loss": 1.3448, + "step": 5851 + }, + { + "epoch": 0.61, + "learning_rate": 7.794676804929075e-06, + "loss": 1.3591, + "step": 5852 + }, + { + "epoch": 0.61, + "learning_rate": 7.791106819219311e-06, + "loss": 1.3108, + "step": 5853 + }, + { + "epoch": 0.61, + "learning_rate": 7.78753712944448e-06, + "loss": 1.3773, + "step": 5854 + }, + { + "epoch": 0.61, + "learning_rate": 7.783967736082824e-06, + "loss": 1.3313, + "step": 5855 + }, + { + "epoch": 0.61, + "learning_rate": 7.780398639612551e-06, + "loss": 1.3635, + "step": 5856 + }, + { + "epoch": 0.61, + "learning_rate": 7.776829840511833e-06, + "loss": 1.3225, + "step": 5857 + }, + { + "epoch": 0.61, + "learning_rate": 7.773261339258792e-06, + "loss": 1.3142, + "step": 5858 + }, + { + "epoch": 0.61, + "learning_rate": 7.769693136331519e-06, + "loss": 1.3337, + "step": 5859 + }, + { + "epoch": 0.61, + "learning_rate": 7.766125232208057e-06, + "loss": 1.5289, + "step": 5860 + }, + { + "epoch": 0.61, + "learning_rate": 7.762557627366418e-06, + "loss": 1.573, + "step": 5861 + }, + { + "epoch": 0.61, + "learning_rate": 7.758990322284568e-06, + "loss": 1.322, + "step": 5862 + }, + { + "epoch": 0.61, + "learning_rate": 7.755423317440432e-06, + "loss": 1.3281, + "step": 5863 + }, + { + "epoch": 0.61, + "learning_rate": 7.751856613311899e-06, + "loss": 1.3405, + "step": 5864 + }, + { + "epoch": 0.62, + "learning_rate": 7.748290210376817e-06, + "loss": 1.3083, + "step": 5865 + }, + { + "epoch": 0.62, + "learning_rate": 7.744724109112991e-06, + "loss": 1.3587, + "step": 5866 + }, + { + "epoch": 0.62, + "learning_rate": 7.741158309998188e-06, + "loss": 1.3204, + "step": 5867 + }, + { + "epoch": 0.62, + "learning_rate": 7.73759281351013e-06, + "loss": 1.343, + "step": 5868 + }, + { + "epoch": 0.62, + "learning_rate": 7.734027620126507e-06, + "loss": 1.2874, + "step": 5869 + }, + { + "epoch": 0.62, + "learning_rate": 7.73046273032496e-06, + "loss": 1.3306, + "step": 5870 + }, + { + "epoch": 0.62, + "learning_rate": 7.72689814458309e-06, + "loss": 1.3958, + "step": 5871 + }, + { + "epoch": 0.62, + "learning_rate": 7.723333863378465e-06, + "loss": 1.3135, + "step": 5872 + }, + { + "epoch": 0.62, + "learning_rate": 7.719769887188608e-06, + "loss": 1.3241, + "step": 5873 + }, + { + "epoch": 0.62, + "learning_rate": 7.716206216490995e-06, + "loss": 1.3487, + "step": 5874 + }, + { + "epoch": 0.62, + "learning_rate": 7.712642851763067e-06, + "loss": 1.0263, + "step": 5875 + }, + { + "epoch": 0.62, + "learning_rate": 7.709079793482228e-06, + "loss": 1.4238, + "step": 5876 + }, + { + "epoch": 0.62, + "learning_rate": 7.705517042125833e-06, + "loss": 1.3284, + "step": 5877 + }, + { + "epoch": 0.62, + "learning_rate": 7.701954598171199e-06, + "loss": 1.2965, + "step": 5878 + }, + { + "epoch": 0.62, + "learning_rate": 7.698392462095601e-06, + "loss": 1.3578, + "step": 5879 + }, + { + "epoch": 0.62, + "learning_rate": 7.694830634376278e-06, + "loss": 1.3711, + "step": 5880 + }, + { + "epoch": 0.62, + "learning_rate": 7.69126911549042e-06, + "loss": 1.3274, + "step": 5881 + }, + { + "epoch": 0.62, + "learning_rate": 7.687707905915181e-06, + "loss": 1.4208, + "step": 5882 + }, + { + "epoch": 0.62, + "learning_rate": 7.684147006127665e-06, + "loss": 1.3478, + "step": 5883 + }, + { + "epoch": 0.62, + "learning_rate": 7.68058641660495e-06, + "loss": 1.2997, + "step": 5884 + }, + { + "epoch": 0.62, + "learning_rate": 7.67702613782406e-06, + "loss": 1.2981, + "step": 5885 + }, + { + "epoch": 0.62, + "learning_rate": 7.67346617026198e-06, + "loss": 1.3834, + "step": 5886 + }, + { + "epoch": 0.62, + "learning_rate": 7.669906514395654e-06, + "loss": 1.3585, + "step": 5887 + }, + { + "epoch": 0.62, + "learning_rate": 7.666347170701986e-06, + "loss": 1.3282, + "step": 5888 + }, + { + "epoch": 0.62, + "learning_rate": 7.662788139657838e-06, + "loss": 1.3397, + "step": 5889 + }, + { + "epoch": 0.62, + "learning_rate": 7.659229421740024e-06, + "loss": 1.3367, + "step": 5890 + }, + { + "epoch": 0.62, + "learning_rate": 7.655671017425322e-06, + "loss": 1.3497, + "step": 5891 + }, + { + "epoch": 0.62, + "learning_rate": 7.65211292719047e-06, + "loss": 1.3661, + "step": 5892 + }, + { + "epoch": 0.62, + "learning_rate": 7.64855515151216e-06, + "loss": 1.2793, + "step": 5893 + }, + { + "epoch": 0.62, + "learning_rate": 7.644997690867037e-06, + "loss": 1.3288, + "step": 5894 + }, + { + "epoch": 0.62, + "learning_rate": 7.641440545731717e-06, + "loss": 1.3877, + "step": 5895 + }, + { + "epoch": 0.62, + "learning_rate": 7.637883716582764e-06, + "loss": 1.4467, + "step": 5896 + }, + { + "epoch": 0.62, + "learning_rate": 7.634327203896698e-06, + "loss": 1.304, + "step": 5897 + }, + { + "epoch": 0.62, + "learning_rate": 7.630771008150002e-06, + "loss": 1.374, + "step": 5898 + }, + { + "epoch": 0.62, + "learning_rate": 7.627215129819118e-06, + "loss": 1.3893, + "step": 5899 + }, + { + "epoch": 0.62, + "learning_rate": 7.623659569380439e-06, + "loss": 1.325, + "step": 5900 + }, + { + "epoch": 0.62, + "learning_rate": 7.620104327310319e-06, + "loss": 1.2495, + "step": 5901 + }, + { + "epoch": 0.62, + "learning_rate": 7.616549404085068e-06, + "loss": 1.4034, + "step": 5902 + }, + { + "epoch": 0.62, + "learning_rate": 7.61299480018096e-06, + "loss": 1.2758, + "step": 5903 + }, + { + "epoch": 0.62, + "learning_rate": 7.609440516074215e-06, + "loss": 1.4203, + "step": 5904 + }, + { + "epoch": 0.62, + "learning_rate": 7.605886552241017e-06, + "loss": 1.3162, + "step": 5905 + }, + { + "epoch": 0.62, + "learning_rate": 7.602332909157505e-06, + "loss": 1.3368, + "step": 5906 + }, + { + "epoch": 0.62, + "learning_rate": 7.598779587299778e-06, + "loss": 1.314, + "step": 5907 + }, + { + "epoch": 0.62, + "learning_rate": 7.59522658714389e-06, + "loss": 1.3332, + "step": 5908 + }, + { + "epoch": 0.62, + "learning_rate": 7.5916739091658505e-06, + "loss": 1.3513, + "step": 5909 + }, + { + "epoch": 0.62, + "learning_rate": 7.5881215538416255e-06, + "loss": 1.3767, + "step": 5910 + }, + { + "epoch": 0.62, + "learning_rate": 7.5845695216471426e-06, + "loss": 1.3651, + "step": 5911 + }, + { + "epoch": 0.62, + "learning_rate": 7.581017813058283e-06, + "loss": 1.2676, + "step": 5912 + }, + { + "epoch": 0.62, + "learning_rate": 7.57746642855088e-06, + "loss": 1.3509, + "step": 5913 + }, + { + "epoch": 0.62, + "learning_rate": 7.5739153686007305e-06, + "loss": 1.2854, + "step": 5914 + }, + { + "epoch": 0.62, + "learning_rate": 7.570364633683586e-06, + "loss": 1.4041, + "step": 5915 + }, + { + "epoch": 0.62, + "learning_rate": 7.5668142242751545e-06, + "loss": 1.3218, + "step": 5916 + }, + { + "epoch": 0.62, + "learning_rate": 7.563264140851095e-06, + "loss": 1.398, + "step": 5917 + }, + { + "epoch": 0.62, + "learning_rate": 7.559714383887033e-06, + "loss": 1.3495, + "step": 5918 + }, + { + "epoch": 0.62, + "learning_rate": 7.556164953858543e-06, + "loss": 1.365, + "step": 5919 + }, + { + "epoch": 0.62, + "learning_rate": 7.552615851241157e-06, + "loss": 1.4611, + "step": 5920 + }, + { + "epoch": 0.62, + "learning_rate": 7.549067076510361e-06, + "loss": 1.4031, + "step": 5921 + }, + { + "epoch": 0.62, + "learning_rate": 7.545518630141605e-06, + "loss": 1.2745, + "step": 5922 + }, + { + "epoch": 0.62, + "learning_rate": 7.541970512610286e-06, + "loss": 1.3435, + "step": 5923 + }, + { + "epoch": 0.62, + "learning_rate": 7.538422724391761e-06, + "loss": 1.3433, + "step": 5924 + }, + { + "epoch": 0.62, + "learning_rate": 7.534875265961341e-06, + "loss": 1.3605, + "step": 5925 + }, + { + "epoch": 0.62, + "learning_rate": 7.5313281377942985e-06, + "loss": 1.3896, + "step": 5926 + }, + { + "epoch": 0.62, + "learning_rate": 7.527781340365854e-06, + "loss": 1.3922, + "step": 5927 + }, + { + "epoch": 0.62, + "learning_rate": 7.524234874151189e-06, + "loss": 1.3305, + "step": 5928 + }, + { + "epoch": 0.62, + "learning_rate": 7.520688739625436e-06, + "loss": 1.3117, + "step": 5929 + }, + { + "epoch": 0.62, + "learning_rate": 7.51714293726369e-06, + "loss": 1.3581, + "step": 5930 + }, + { + "epoch": 0.62, + "learning_rate": 7.5135974675409955e-06, + "loss": 1.3973, + "step": 5931 + }, + { + "epoch": 0.62, + "learning_rate": 7.510052330932354e-06, + "loss": 1.3499, + "step": 5932 + }, + { + "epoch": 0.62, + "learning_rate": 7.506507527912721e-06, + "loss": 1.3068, + "step": 5933 + }, + { + "epoch": 0.62, + "learning_rate": 7.502963058957014e-06, + "loss": 1.3689, + "step": 5934 + }, + { + "epoch": 0.62, + "learning_rate": 7.499418924540096e-06, + "loss": 1.3356, + "step": 5935 + }, + { + "epoch": 0.62, + "learning_rate": 7.495875125136793e-06, + "loss": 1.2593, + "step": 5936 + }, + { + "epoch": 0.62, + "learning_rate": 7.492331661221881e-06, + "loss": 1.272, + "step": 5937 + }, + { + "epoch": 0.62, + "learning_rate": 7.488788533270093e-06, + "loss": 1.3552, + "step": 5938 + }, + { + "epoch": 0.62, + "learning_rate": 7.485245741756121e-06, + "loss": 1.3425, + "step": 5939 + }, + { + "epoch": 0.62, + "learning_rate": 7.481703287154602e-06, + "loss": 1.3694, + "step": 5940 + }, + { + "epoch": 0.62, + "learning_rate": 7.478161169940139e-06, + "loss": 1.3281, + "step": 5941 + }, + { + "epoch": 0.62, + "learning_rate": 7.4746193905872825e-06, + "loss": 1.3109, + "step": 5942 + }, + { + "epoch": 0.62, + "learning_rate": 7.47107794957054e-06, + "loss": 1.5121, + "step": 5943 + }, + { + "epoch": 0.62, + "learning_rate": 7.467536847364372e-06, + "loss": 1.4472, + "step": 5944 + }, + { + "epoch": 0.62, + "learning_rate": 7.463996084443198e-06, + "loss": 1.4615, + "step": 5945 + }, + { + "epoch": 0.62, + "learning_rate": 7.460455661281389e-06, + "loss": 1.3764, + "step": 5946 + }, + { + "epoch": 0.62, + "learning_rate": 7.45691557835327e-06, + "loss": 1.3091, + "step": 5947 + }, + { + "epoch": 0.62, + "learning_rate": 7.4533758361331185e-06, + "loss": 1.1841, + "step": 5948 + }, + { + "epoch": 0.62, + "learning_rate": 7.449836435095175e-06, + "loss": 1.3345, + "step": 5949 + }, + { + "epoch": 0.62, + "learning_rate": 7.446297375713622e-06, + "loss": 1.3573, + "step": 5950 + }, + { + "epoch": 0.62, + "learning_rate": 7.442758658462608e-06, + "loss": 1.3161, + "step": 5951 + }, + { + "epoch": 0.62, + "learning_rate": 7.4392202838162245e-06, + "loss": 1.3089, + "step": 5952 + }, + { + "epoch": 0.62, + "learning_rate": 7.435682252248528e-06, + "loss": 1.3069, + "step": 5953 + }, + { + "epoch": 0.62, + "learning_rate": 7.4321445642335234e-06, + "loss": 1.2969, + "step": 5954 + }, + { + "epoch": 0.62, + "learning_rate": 7.428607220245165e-06, + "loss": 1.4706, + "step": 5955 + }, + { + "epoch": 0.62, + "learning_rate": 7.42507022075737e-06, + "loss": 1.3028, + "step": 5956 + }, + { + "epoch": 0.62, + "learning_rate": 7.421533566244006e-06, + "loss": 1.2786, + "step": 5957 + }, + { + "epoch": 0.62, + "learning_rate": 7.417997257178893e-06, + "loss": 1.3534, + "step": 5958 + }, + { + "epoch": 0.62, + "learning_rate": 7.414461294035804e-06, + "loss": 1.2829, + "step": 5959 + }, + { + "epoch": 0.62, + "learning_rate": 7.410925677288467e-06, + "loss": 1.3626, + "step": 5960 + }, + { + "epoch": 0.63, + "learning_rate": 7.407390407410566e-06, + "loss": 1.4531, + "step": 5961 + }, + { + "epoch": 0.63, + "learning_rate": 7.4038554848757375e-06, + "loss": 1.3549, + "step": 5962 + }, + { + "epoch": 0.63, + "learning_rate": 7.400320910157563e-06, + "loss": 1.3407, + "step": 5963 + }, + { + "epoch": 0.63, + "learning_rate": 7.396786683729595e-06, + "loss": 1.2736, + "step": 5964 + }, + { + "epoch": 0.63, + "learning_rate": 7.393252806065323e-06, + "loss": 1.3377, + "step": 5965 + }, + { + "epoch": 0.63, + "learning_rate": 7.389719277638196e-06, + "loss": 1.3479, + "step": 5966 + }, + { + "epoch": 0.63, + "learning_rate": 7.3861860989216175e-06, + "loss": 1.3605, + "step": 5967 + }, + { + "epoch": 0.63, + "learning_rate": 7.382653270388942e-06, + "loss": 1.3175, + "step": 5968 + }, + { + "epoch": 0.63, + "learning_rate": 7.379120792513477e-06, + "loss": 1.3072, + "step": 5969 + }, + { + "epoch": 0.63, + "learning_rate": 7.375588665768485e-06, + "loss": 1.3224, + "step": 5970 + }, + { + "epoch": 0.63, + "eval_loss": 1.4110088348388672, + "eval_runtime": 77.5326, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 5970 + }, + { + "epoch": 0.63, + "learning_rate": 7.37205689062718e-06, + "loss": 1.3491, + "step": 5971 + }, + { + "epoch": 0.63, + "learning_rate": 7.368525467562728e-06, + "loss": 1.3289, + "step": 5972 + }, + { + "epoch": 0.63, + "learning_rate": 7.364994397048251e-06, + "loss": 1.3362, + "step": 5973 + }, + { + "epoch": 0.63, + "learning_rate": 7.36146367955682e-06, + "loss": 1.3754, + "step": 5974 + }, + { + "epoch": 0.63, + "learning_rate": 7.3579333155614585e-06, + "loss": 1.3159, + "step": 5975 + }, + { + "epoch": 0.63, + "learning_rate": 7.354403305535149e-06, + "loss": 1.4366, + "step": 5976 + }, + { + "epoch": 0.63, + "learning_rate": 7.350873649950822e-06, + "loss": 1.3243, + "step": 5977 + }, + { + "epoch": 0.63, + "learning_rate": 7.347344349281358e-06, + "loss": 1.2911, + "step": 5978 + }, + { + "epoch": 0.63, + "learning_rate": 7.34381540399959e-06, + "loss": 1.338, + "step": 5979 + }, + { + "epoch": 0.63, + "learning_rate": 7.340286814578312e-06, + "loss": 1.3241, + "step": 5980 + }, + { + "epoch": 0.63, + "learning_rate": 7.336758581490263e-06, + "loss": 1.3427, + "step": 5981 + }, + { + "epoch": 0.63, + "learning_rate": 7.333230705208134e-06, + "loss": 1.3328, + "step": 5982 + }, + { + "epoch": 0.63, + "learning_rate": 7.3297031862045676e-06, + "loss": 1.2857, + "step": 5983 + }, + { + "epoch": 0.63, + "learning_rate": 7.3261760249521655e-06, + "loss": 1.9065, + "step": 5984 + }, + { + "epoch": 0.63, + "learning_rate": 7.322649221923473e-06, + "loss": 1.3797, + "step": 5985 + }, + { + "epoch": 0.63, + "learning_rate": 7.3191227775909925e-06, + "loss": 1.2343, + "step": 5986 + }, + { + "epoch": 0.63, + "learning_rate": 7.315596692427178e-06, + "loss": 1.3479, + "step": 5987 + }, + { + "epoch": 0.63, + "learning_rate": 7.312070966904432e-06, + "loss": 1.3226, + "step": 5988 + }, + { + "epoch": 0.63, + "learning_rate": 7.308545601495114e-06, + "loss": 1.3329, + "step": 5989 + }, + { + "epoch": 0.63, + "learning_rate": 7.305020596671528e-06, + "loss": 1.3285, + "step": 5990 + }, + { + "epoch": 0.63, + "learning_rate": 7.301495952905939e-06, + "loss": 1.3635, + "step": 5991 + }, + { + "epoch": 0.63, + "learning_rate": 7.297971670670556e-06, + "loss": 1.3343, + "step": 5992 + }, + { + "epoch": 0.63, + "learning_rate": 7.294447750437543e-06, + "loss": 1.3943, + "step": 5993 + }, + { + "epoch": 0.63, + "learning_rate": 7.290924192679014e-06, + "loss": 1.4601, + "step": 5994 + }, + { + "epoch": 0.63, + "learning_rate": 7.287400997867036e-06, + "loss": 1.3813, + "step": 5995 + }, + { + "epoch": 0.63, + "learning_rate": 7.2838781664736266e-06, + "loss": 1.3505, + "step": 5996 + }, + { + "epoch": 0.63, + "learning_rate": 7.2803556989707555e-06, + "loss": 1.3062, + "step": 5997 + }, + { + "epoch": 0.63, + "learning_rate": 7.276833595830338e-06, + "loss": 1.4504, + "step": 5998 + }, + { + "epoch": 0.63, + "learning_rate": 7.273311857524252e-06, + "loss": 1.4935, + "step": 5999 + }, + { + "epoch": 0.63, + "learning_rate": 7.269790484524317e-06, + "loss": 1.296, + "step": 6000 + }, + { + "epoch": 0.63, + "learning_rate": 7.266269477302308e-06, + "loss": 1.3469, + "step": 6001 + }, + { + "epoch": 0.63, + "learning_rate": 7.262748836329944e-06, + "loss": 1.3586, + "step": 6002 + }, + { + "epoch": 0.63, + "learning_rate": 7.259228562078908e-06, + "loss": 1.3643, + "step": 6003 + }, + { + "epoch": 0.63, + "learning_rate": 7.255708655020821e-06, + "loss": 1.3096, + "step": 6004 + }, + { + "epoch": 0.63, + "learning_rate": 7.252189115627264e-06, + "loss": 1.3163, + "step": 6005 + }, + { + "epoch": 0.63, + "learning_rate": 7.2486699443697595e-06, + "loss": 1.3526, + "step": 6006 + }, + { + "epoch": 0.63, + "learning_rate": 7.245151141719793e-06, + "loss": 1.401, + "step": 6007 + }, + { + "epoch": 0.63, + "learning_rate": 7.241632708148788e-06, + "loss": 1.2651, + "step": 6008 + }, + { + "epoch": 0.63, + "learning_rate": 7.238114644128124e-06, + "loss": 1.348, + "step": 6009 + }, + { + "epoch": 0.63, + "learning_rate": 7.234596950129137e-06, + "loss": 1.6934, + "step": 6010 + }, + { + "epoch": 0.63, + "learning_rate": 7.231079626623103e-06, + "loss": 1.3382, + "step": 6011 + }, + { + "epoch": 0.63, + "learning_rate": 7.227562674081254e-06, + "loss": 1.2925, + "step": 6012 + }, + { + "epoch": 0.63, + "learning_rate": 7.22404609297477e-06, + "loss": 1.3365, + "step": 6013 + }, + { + "epoch": 0.63, + "learning_rate": 7.220529883774785e-06, + "loss": 1.3169, + "step": 6014 + }, + { + "epoch": 0.63, + "learning_rate": 7.217014046952379e-06, + "loss": 1.319, + "step": 6015 + }, + { + "epoch": 0.63, + "learning_rate": 7.2134985829785846e-06, + "loss": 1.4049, + "step": 6016 + }, + { + "epoch": 0.63, + "learning_rate": 7.209983492324382e-06, + "loss": 1.2947, + "step": 6017 + }, + { + "epoch": 0.63, + "learning_rate": 7.206468775460704e-06, + "loss": 1.2854, + "step": 6018 + }, + { + "epoch": 0.63, + "learning_rate": 7.202954432858436e-06, + "loss": 1.3381, + "step": 6019 + }, + { + "epoch": 0.63, + "learning_rate": 7.199440464988403e-06, + "loss": 1.3912, + "step": 6020 + }, + { + "epoch": 0.63, + "learning_rate": 7.195926872321391e-06, + "loss": 1.384, + "step": 6021 + }, + { + "epoch": 0.63, + "learning_rate": 7.192413655328129e-06, + "loss": 1.2909, + "step": 6022 + }, + { + "epoch": 0.63, + "learning_rate": 7.188900814479299e-06, + "loss": 1.2951, + "step": 6023 + }, + { + "epoch": 0.63, + "learning_rate": 7.185388350245532e-06, + "loss": 1.2655, + "step": 6024 + }, + { + "epoch": 0.63, + "learning_rate": 7.1818762630974035e-06, + "loss": 1.3288, + "step": 6025 + }, + { + "epoch": 0.63, + "learning_rate": 7.17836455350545e-06, + "loss": 1.2873, + "step": 6026 + }, + { + "epoch": 0.63, + "learning_rate": 7.174853221940146e-06, + "loss": 1.3027, + "step": 6027 + }, + { + "epoch": 0.63, + "learning_rate": 7.17134226887192e-06, + "loss": 1.3273, + "step": 6028 + }, + { + "epoch": 0.63, + "learning_rate": 7.167831694771149e-06, + "loss": 1.3096, + "step": 6029 + }, + { + "epoch": 0.63, + "learning_rate": 7.1643215001081625e-06, + "loss": 1.2904, + "step": 6030 + }, + { + "epoch": 0.63, + "learning_rate": 7.160811685353234e-06, + "loss": 1.2977, + "step": 6031 + }, + { + "epoch": 0.63, + "learning_rate": 7.157302250976588e-06, + "loss": 1.3281, + "step": 6032 + }, + { + "epoch": 0.63, + "learning_rate": 7.1537931974483996e-06, + "loss": 1.3831, + "step": 6033 + }, + { + "epoch": 0.63, + "learning_rate": 7.150284525238794e-06, + "loss": 1.3173, + "step": 6034 + }, + { + "epoch": 0.63, + "learning_rate": 7.146776234817841e-06, + "loss": 1.4148, + "step": 6035 + }, + { + "epoch": 0.63, + "learning_rate": 7.143268326655557e-06, + "loss": 1.3381, + "step": 6036 + }, + { + "epoch": 0.63, + "learning_rate": 7.13976080122192e-06, + "loss": 1.3221, + "step": 6037 + }, + { + "epoch": 0.63, + "learning_rate": 7.136253658986843e-06, + "loss": 1.4373, + "step": 6038 + }, + { + "epoch": 0.63, + "learning_rate": 7.132746900420195e-06, + "loss": 1.3758, + "step": 6039 + }, + { + "epoch": 0.63, + "learning_rate": 7.129240525991788e-06, + "loss": 1.3964, + "step": 6040 + }, + { + "epoch": 0.63, + "learning_rate": 7.125734536171391e-06, + "loss": 1.3136, + "step": 6041 + }, + { + "epoch": 0.63, + "learning_rate": 7.122228931428715e-06, + "loss": 1.2195, + "step": 6042 + }, + { + "epoch": 0.63, + "learning_rate": 7.11872371223342e-06, + "loss": 1.3842, + "step": 6043 + }, + { + "epoch": 0.63, + "learning_rate": 7.115218879055113e-06, + "loss": 1.3369, + "step": 6044 + }, + { + "epoch": 0.63, + "learning_rate": 7.111714432363356e-06, + "loss": 1.2704, + "step": 6045 + }, + { + "epoch": 0.63, + "learning_rate": 7.108210372627653e-06, + "loss": 1.307, + "step": 6046 + }, + { + "epoch": 0.63, + "learning_rate": 7.104706700317459e-06, + "loss": 1.3024, + "step": 6047 + }, + { + "epoch": 0.63, + "learning_rate": 7.1012034159021715e-06, + "loss": 1.4157, + "step": 6048 + }, + { + "epoch": 0.63, + "learning_rate": 7.0977005198511475e-06, + "loss": 1.2314, + "step": 6049 + }, + { + "epoch": 0.63, + "learning_rate": 7.09419801263368e-06, + "loss": 1.4304, + "step": 6050 + }, + { + "epoch": 0.63, + "learning_rate": 7.090695894719019e-06, + "loss": 1.3085, + "step": 6051 + }, + { + "epoch": 0.63, + "learning_rate": 7.0871941665763525e-06, + "loss": 1.367, + "step": 6052 + }, + { + "epoch": 0.63, + "learning_rate": 7.083692828674827e-06, + "loss": 1.2913, + "step": 6053 + }, + { + "epoch": 0.63, + "learning_rate": 7.080191881483531e-06, + "loss": 1.3751, + "step": 6054 + }, + { + "epoch": 0.63, + "learning_rate": 7.0766913254714985e-06, + "loss": 1.3178, + "step": 6055 + }, + { + "epoch": 0.64, + "learning_rate": 7.07319116110772e-06, + "loss": 1.3182, + "step": 6056 + }, + { + "epoch": 0.64, + "learning_rate": 7.069691388861122e-06, + "loss": 1.373, + "step": 6057 + }, + { + "epoch": 0.64, + "learning_rate": 7.066192009200588e-06, + "loss": 1.3235, + "step": 6058 + }, + { + "epoch": 0.64, + "learning_rate": 7.0626930225949395e-06, + "loss": 1.3765, + "step": 6059 + }, + { + "epoch": 0.64, + "learning_rate": 7.0591944295129565e-06, + "loss": 1.4408, + "step": 6060 + }, + { + "epoch": 0.64, + "learning_rate": 7.055696230423359e-06, + "loss": 1.3271, + "step": 6061 + }, + { + "epoch": 0.64, + "learning_rate": 7.052198425794814e-06, + "loss": 1.2194, + "step": 6062 + }, + { + "epoch": 0.64, + "learning_rate": 7.048701016095938e-06, + "loss": 1.3707, + "step": 6063 + }, + { + "epoch": 0.64, + "learning_rate": 7.045204001795296e-06, + "loss": 1.3878, + "step": 6064 + }, + { + "epoch": 0.64, + "learning_rate": 7.041707383361396e-06, + "loss": 1.3674, + "step": 6065 + }, + { + "epoch": 0.64, + "learning_rate": 7.038211161262697e-06, + "loss": 1.4525, + "step": 6066 + }, + { + "epoch": 0.64, + "learning_rate": 7.034715335967599e-06, + "loss": 1.3801, + "step": 6067 + }, + { + "epoch": 0.64, + "learning_rate": 7.031219907944458e-06, + "loss": 1.4855, + "step": 6068 + }, + { + "epoch": 0.64, + "learning_rate": 7.027724877661568e-06, + "loss": 1.3659, + "step": 6069 + }, + { + "epoch": 0.64, + "learning_rate": 7.024230245587176e-06, + "loss": 1.3649, + "step": 6070 + }, + { + "epoch": 0.64, + "learning_rate": 7.020736012189467e-06, + "loss": 1.2629, + "step": 6071 + }, + { + "epoch": 0.64, + "learning_rate": 7.017242177936586e-06, + "loss": 1.2474, + "step": 6072 + }, + { + "epoch": 0.64, + "learning_rate": 7.013748743296614e-06, + "loss": 1.45, + "step": 6073 + }, + { + "epoch": 0.64, + "learning_rate": 7.010255708737581e-06, + "loss": 1.3624, + "step": 6074 + }, + { + "epoch": 0.64, + "learning_rate": 7.006763074727461e-06, + "loss": 0.9335, + "step": 6075 + }, + { + "epoch": 0.64, + "learning_rate": 7.0032708417341835e-06, + "loss": 0.6376, + "step": 6076 + }, + { + "epoch": 0.64, + "learning_rate": 6.999779010225613e-06, + "loss": 0.7882, + "step": 6077 + }, + { + "epoch": 0.64, + "learning_rate": 6.996287580669567e-06, + "loss": 1.3001, + "step": 6078 + }, + { + "epoch": 0.64, + "learning_rate": 6.9927965535338085e-06, + "loss": 1.323, + "step": 6079 + }, + { + "epoch": 0.64, + "learning_rate": 6.989305929286043e-06, + "loss": 1.3478, + "step": 6080 + }, + { + "epoch": 0.64, + "learning_rate": 6.985815708393928e-06, + "loss": 1.319, + "step": 6081 + }, + { + "epoch": 0.64, + "learning_rate": 6.9823258913250566e-06, + "loss": 1.3458, + "step": 6082 + }, + { + "epoch": 0.64, + "learning_rate": 6.978836478546985e-06, + "loss": 1.2481, + "step": 6083 + }, + { + "epoch": 0.64, + "learning_rate": 6.975347470527195e-06, + "loss": 1.4051, + "step": 6084 + }, + { + "epoch": 0.64, + "learning_rate": 6.97185886773313e-06, + "loss": 1.3705, + "step": 6085 + }, + { + "epoch": 0.64, + "learning_rate": 6.9683706706321676e-06, + "loss": 1.3415, + "step": 6086 + }, + { + "epoch": 0.64, + "learning_rate": 6.964882879691643e-06, + "loss": 1.3462, + "step": 6087 + }, + { + "epoch": 0.64, + "learning_rate": 6.961395495378829e-06, + "loss": 1.2974, + "step": 6088 + }, + { + "epoch": 0.64, + "learning_rate": 6.957908518160943e-06, + "loss": 1.3353, + "step": 6089 + }, + { + "epoch": 0.64, + "learning_rate": 6.95442194850515e-06, + "loss": 1.3073, + "step": 6090 + }, + { + "epoch": 0.64, + "learning_rate": 6.9509357868785636e-06, + "loss": 1.352, + "step": 6091 + }, + { + "epoch": 0.64, + "learning_rate": 6.9474500337482396e-06, + "loss": 1.2771, + "step": 6092 + }, + { + "epoch": 0.64, + "learning_rate": 6.943964689581177e-06, + "loss": 1.2925, + "step": 6093 + }, + { + "epoch": 0.64, + "learning_rate": 6.940479754844322e-06, + "loss": 1.2967, + "step": 6094 + }, + { + "epoch": 0.64, + "learning_rate": 6.93699523000457e-06, + "loss": 1.5839, + "step": 6095 + }, + { + "epoch": 0.64, + "learning_rate": 6.933511115528757e-06, + "loss": 1.3051, + "step": 6096 + }, + { + "epoch": 0.64, + "learning_rate": 6.930027411883664e-06, + "loss": 1.5344, + "step": 6097 + }, + { + "epoch": 0.64, + "learning_rate": 6.926544119536014e-06, + "loss": 1.3938, + "step": 6098 + }, + { + "epoch": 0.64, + "learning_rate": 6.923061238952484e-06, + "loss": 1.3504, + "step": 6099 + }, + { + "epoch": 0.64, + "learning_rate": 6.919578770599689e-06, + "loss": 1.3618, + "step": 6100 + }, + { + "epoch": 0.64, + "learning_rate": 6.916096714944187e-06, + "loss": 1.3811, + "step": 6101 + }, + { + "epoch": 0.64, + "learning_rate": 6.912615072452491e-06, + "loss": 1.2673, + "step": 6102 + }, + { + "epoch": 0.64, + "learning_rate": 6.909133843591046e-06, + "loss": 1.3661, + "step": 6103 + }, + { + "epoch": 0.64, + "learning_rate": 6.905653028826249e-06, + "loss": 1.3811, + "step": 6104 + }, + { + "epoch": 0.64, + "learning_rate": 6.902172628624437e-06, + "loss": 1.3399, + "step": 6105 + }, + { + "epoch": 0.64, + "learning_rate": 6.8986926434519e-06, + "loss": 1.281, + "step": 6106 + }, + { + "epoch": 0.64, + "learning_rate": 6.895213073774862e-06, + "loss": 1.3053, + "step": 6107 + }, + { + "epoch": 0.64, + "learning_rate": 6.891733920059498e-06, + "loss": 1.4573, + "step": 6108 + }, + { + "epoch": 0.64, + "learning_rate": 6.8882551827719215e-06, + "loss": 1.355, + "step": 6109 + }, + { + "epoch": 0.64, + "learning_rate": 6.8847768623782e-06, + "loss": 1.3304, + "step": 6110 + }, + { + "epoch": 0.64, + "learning_rate": 6.881298959344335e-06, + "loss": 1.4039, + "step": 6111 + }, + { + "epoch": 0.64, + "learning_rate": 6.877821474136277e-06, + "loss": 1.381, + "step": 6112 + }, + { + "epoch": 0.64, + "learning_rate": 6.874344407219917e-06, + "loss": 1.3503, + "step": 6113 + }, + { + "epoch": 0.64, + "learning_rate": 6.870867759061099e-06, + "loss": 1.2679, + "step": 6114 + }, + { + "epoch": 0.64, + "learning_rate": 6.8673915301256e-06, + "loss": 1.3286, + "step": 6115 + }, + { + "epoch": 0.64, + "learning_rate": 6.863915720879146e-06, + "loss": 1.3528, + "step": 6116 + }, + { + "epoch": 0.64, + "learning_rate": 6.8604403317874055e-06, + "loss": 1.3502, + "step": 6117 + }, + { + "epoch": 0.64, + "learning_rate": 6.856965363315993e-06, + "loss": 1.3507, + "step": 6118 + }, + { + "epoch": 0.64, + "learning_rate": 6.853490815930464e-06, + "loss": 1.2153, + "step": 6119 + }, + { + "epoch": 0.64, + "learning_rate": 6.850016690096319e-06, + "loss": 1.2435, + "step": 6120 + }, + { + "epoch": 0.64, + "learning_rate": 6.846542986279e-06, + "loss": 1.3418, + "step": 6121 + }, + { + "epoch": 0.64, + "learning_rate": 6.843069704943896e-06, + "loss": 1.371, + "step": 6122 + }, + { + "epoch": 0.64, + "learning_rate": 6.8395968465563375e-06, + "loss": 1.1737, + "step": 6123 + }, + { + "epoch": 0.64, + "learning_rate": 6.836124411581598e-06, + "loss": 1.3402, + "step": 6124 + }, + { + "epoch": 0.64, + "learning_rate": 6.8326524004848924e-06, + "loss": 1.3482, + "step": 6125 + }, + { + "epoch": 0.64, + "learning_rate": 6.8291808137313845e-06, + "loss": 1.4585, + "step": 6126 + }, + { + "epoch": 0.64, + "learning_rate": 6.825709651786176e-06, + "loss": 1.2848, + "step": 6127 + }, + { + "epoch": 0.64, + "learning_rate": 6.822238915114312e-06, + "loss": 1.2932, + "step": 6128 + }, + { + "epoch": 0.64, + "learning_rate": 6.818768604180785e-06, + "loss": 1.3124, + "step": 6129 + }, + { + "epoch": 0.64, + "learning_rate": 6.815298719450525e-06, + "loss": 1.2843, + "step": 6130 + }, + { + "epoch": 0.64, + "learning_rate": 6.811829261388409e-06, + "loss": 1.3024, + "step": 6131 + }, + { + "epoch": 0.64, + "learning_rate": 6.808360230459252e-06, + "loss": 1.3612, + "step": 6132 + }, + { + "epoch": 0.64, + "learning_rate": 6.804891627127821e-06, + "loss": 1.3005, + "step": 6133 + }, + { + "epoch": 0.64, + "learning_rate": 6.8014234518588154e-06, + "loss": 1.2614, + "step": 6134 + }, + { + "epoch": 0.64, + "learning_rate": 6.7979557051168835e-06, + "loss": 1.3717, + "step": 6135 + }, + { + "epoch": 0.64, + "learning_rate": 6.794488387366609e-06, + "loss": 1.3873, + "step": 6136 + }, + { + "epoch": 0.64, + "learning_rate": 6.791021499072532e-06, + "loss": 1.2955, + "step": 6137 + }, + { + "epoch": 0.64, + "learning_rate": 6.787555040699121e-06, + "loss": 1.4217, + "step": 6138 + }, + { + "epoch": 0.64, + "learning_rate": 6.784089012710793e-06, + "loss": 1.3805, + "step": 6139 + }, + { + "epoch": 0.64, + "learning_rate": 6.7806234155719055e-06, + "loss": 1.3982, + "step": 6140 + }, + { + "epoch": 0.64, + "learning_rate": 6.7771582497467635e-06, + "loss": 1.4, + "step": 6141 + }, + { + "epoch": 0.64, + "learning_rate": 6.773693515699607e-06, + "loss": 1.439, + "step": 6142 + }, + { + "epoch": 0.64, + "learning_rate": 6.7702292138946235e-06, + "loss": 1.3672, + "step": 6143 + }, + { + "epoch": 0.64, + "learning_rate": 6.7667653447959355e-06, + "loss": 1.2901, + "step": 6144 + }, + { + "epoch": 0.64, + "learning_rate": 6.763301908867619e-06, + "loss": 1.2873, + "step": 6145 + }, + { + "epoch": 0.64, + "learning_rate": 6.759838906573684e-06, + "loss": 1.3582, + "step": 6146 + }, + { + "epoch": 0.64, + "learning_rate": 6.756376338378077e-06, + "loss": 1.3562, + "step": 6147 + }, + { + "epoch": 0.64, + "learning_rate": 6.7529142047447025e-06, + "loss": 1.3091, + "step": 6148 + }, + { + "epoch": 0.64, + "learning_rate": 6.749452506137393e-06, + "loss": 1.4269, + "step": 6149 + }, + { + "epoch": 0.64, + "learning_rate": 6.745991243019927e-06, + "loss": 1.4184, + "step": 6150 + }, + { + "epoch": 0.65, + "learning_rate": 6.7425304158560235e-06, + "loss": 1.4201, + "step": 6151 + }, + { + "epoch": 0.65, + "learning_rate": 6.739070025109349e-06, + "loss": 1.3222, + "step": 6152 + }, + { + "epoch": 0.65, + "learning_rate": 6.7356100712435035e-06, + "loss": 1.3262, + "step": 6153 + }, + { + "epoch": 0.65, + "learning_rate": 6.732150554722034e-06, + "loss": 1.4408, + "step": 6154 + }, + { + "epoch": 0.65, + "learning_rate": 6.728691476008422e-06, + "loss": 1.3441, + "step": 6155 + }, + { + "epoch": 0.65, + "learning_rate": 6.725232835566102e-06, + "loss": 1.3316, + "step": 6156 + }, + { + "epoch": 0.65, + "learning_rate": 6.721774633858438e-06, + "loss": 1.3326, + "step": 6157 + }, + { + "epoch": 0.65, + "learning_rate": 6.7183168713487425e-06, + "loss": 1.3105, + "step": 6158 + }, + { + "epoch": 0.65, + "learning_rate": 6.714859548500265e-06, + "loss": 1.3144, + "step": 6159 + }, + { + "epoch": 0.65, + "learning_rate": 6.7114026657762e-06, + "loss": 1.3472, + "step": 6160 + }, + { + "epoch": 0.65, + "learning_rate": 6.707946223639681e-06, + "loss": 1.3811, + "step": 6161 + }, + { + "epoch": 0.65, + "learning_rate": 6.704490222553781e-06, + "loss": 1.2783, + "step": 6162 + }, + { + "epoch": 0.65, + "learning_rate": 6.701034662981513e-06, + "loss": 1.273, + "step": 6163 + }, + { + "epoch": 0.65, + "learning_rate": 6.697579545385839e-06, + "loss": 1.3522, + "step": 6164 + }, + { + "epoch": 0.65, + "learning_rate": 6.6941248702296524e-06, + "loss": 1.3861, + "step": 6165 + }, + { + "epoch": 0.65, + "learning_rate": 6.6906706379757915e-06, + "loss": 1.3098, + "step": 6166 + }, + { + "epoch": 0.65, + "learning_rate": 6.687216849087032e-06, + "loss": 1.3734, + "step": 6167 + }, + { + "epoch": 0.65, + "learning_rate": 6.6837635040261e-06, + "loss": 1.2289, + "step": 6168 + }, + { + "epoch": 0.65, + "learning_rate": 6.680310603255648e-06, + "loss": 1.3238, + "step": 6169 + }, + { + "epoch": 0.65, + "eval_loss": 1.40826416015625, + "eval_runtime": 77.483, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 6169 + }, + { + "epoch": 0.65, + "learning_rate": 6.676858147238277e-06, + "loss": 1.4317, + "step": 6170 + }, + { + "epoch": 0.65, + "learning_rate": 6.673406136436531e-06, + "loss": 1.3363, + "step": 6171 + }, + { + "epoch": 0.65, + "learning_rate": 6.669954571312889e-06, + "loss": 1.3377, + "step": 6172 + }, + { + "epoch": 0.65, + "learning_rate": 6.666503452329771e-06, + "loss": 1.3382, + "step": 6173 + }, + { + "epoch": 0.65, + "learning_rate": 6.663052779949538e-06, + "loss": 1.3028, + "step": 6174 + }, + { + "epoch": 0.65, + "learning_rate": 6.659602554634494e-06, + "loss": 1.3098, + "step": 6175 + }, + { + "epoch": 0.65, + "learning_rate": 6.656152776846879e-06, + "loss": 1.328, + "step": 6176 + }, + { + "epoch": 0.65, + "learning_rate": 6.652703447048874e-06, + "loss": 1.3014, + "step": 6177 + }, + { + "epoch": 0.65, + "learning_rate": 6.6492545657026e-06, + "loss": 1.2522, + "step": 6178 + }, + { + "epoch": 0.65, + "learning_rate": 6.645806133270121e-06, + "loss": 1.6113, + "step": 6179 + }, + { + "epoch": 0.65, + "learning_rate": 6.642358150213437e-06, + "loss": 1.3431, + "step": 6180 + }, + { + "epoch": 0.65, + "learning_rate": 6.638910616994489e-06, + "loss": 1.2725, + "step": 6181 + }, + { + "epoch": 0.65, + "learning_rate": 6.635463534075156e-06, + "loss": 1.3022, + "step": 6182 + }, + { + "epoch": 0.65, + "learning_rate": 6.632016901917262e-06, + "loss": 1.3496, + "step": 6183 + }, + { + "epoch": 0.65, + "learning_rate": 6.628570720982567e-06, + "loss": 1.2871, + "step": 6184 + }, + { + "epoch": 0.65, + "learning_rate": 6.625124991732767e-06, + "loss": 1.4449, + "step": 6185 + }, + { + "epoch": 0.65, + "learning_rate": 6.621679714629504e-06, + "loss": 1.4395, + "step": 6186 + }, + { + "epoch": 0.65, + "learning_rate": 6.618234890134356e-06, + "loss": 1.4088, + "step": 6187 + }, + { + "epoch": 0.65, + "learning_rate": 6.614790518708843e-06, + "loss": 1.371, + "step": 6188 + }, + { + "epoch": 0.65, + "learning_rate": 6.611346600814419e-06, + "loss": 1.28, + "step": 6189 + }, + { + "epoch": 0.65, + "learning_rate": 6.607903136912482e-06, + "loss": 1.3502, + "step": 6190 + }, + { + "epoch": 0.65, + "learning_rate": 6.604460127464367e-06, + "loss": 1.3398, + "step": 6191 + }, + { + "epoch": 0.65, + "learning_rate": 6.60101757293135e-06, + "loss": 1.4762, + "step": 6192 + }, + { + "epoch": 0.65, + "learning_rate": 6.5975754737746426e-06, + "loss": 1.2981, + "step": 6193 + }, + { + "epoch": 0.65, + "learning_rate": 6.594133830455401e-06, + "loss": 1.3728, + "step": 6194 + }, + { + "epoch": 0.65, + "learning_rate": 6.590692643434715e-06, + "loss": 1.3551, + "step": 6195 + }, + { + "epoch": 0.65, + "learning_rate": 6.5872519131736155e-06, + "loss": 1.3031, + "step": 6196 + }, + { + "epoch": 0.65, + "learning_rate": 6.583811640133071e-06, + "loss": 1.3231, + "step": 6197 + }, + { + "epoch": 0.65, + "learning_rate": 6.5803718247739924e-06, + "loss": 1.2752, + "step": 6198 + }, + { + "epoch": 0.65, + "learning_rate": 6.576932467557223e-06, + "loss": 1.3482, + "step": 6199 + }, + { + "epoch": 0.65, + "learning_rate": 6.573493568943552e-06, + "loss": 1.2612, + "step": 6200 + }, + { + "epoch": 0.65, + "learning_rate": 6.570055129393698e-06, + "loss": 1.6302, + "step": 6201 + }, + { + "epoch": 0.65, + "learning_rate": 6.566617149368331e-06, + "loss": 1.303, + "step": 6202 + }, + { + "epoch": 0.65, + "learning_rate": 6.563179629328047e-06, + "loss": 1.3405, + "step": 6203 + }, + { + "epoch": 0.65, + "learning_rate": 6.559742569733385e-06, + "loss": 1.2816, + "step": 6204 + }, + { + "epoch": 0.65, + "learning_rate": 6.556305971044824e-06, + "loss": 1.3834, + "step": 6205 + }, + { + "epoch": 0.65, + "learning_rate": 6.552869833722781e-06, + "loss": 1.3414, + "step": 6206 + }, + { + "epoch": 0.65, + "learning_rate": 6.5494341582276096e-06, + "loss": 1.3278, + "step": 6207 + }, + { + "epoch": 0.65, + "learning_rate": 6.5459989450196024e-06, + "loss": 1.3577, + "step": 6208 + }, + { + "epoch": 0.65, + "learning_rate": 6.542564194558986e-06, + "loss": 1.3104, + "step": 6209 + }, + { + "epoch": 0.65, + "learning_rate": 6.539129907305933e-06, + "loss": 1.3068, + "step": 6210 + }, + { + "epoch": 0.65, + "learning_rate": 6.53569608372055e-06, + "loss": 1.3769, + "step": 6211 + }, + { + "epoch": 0.65, + "learning_rate": 6.5322627242628775e-06, + "loss": 1.2855, + "step": 6212 + }, + { + "epoch": 0.65, + "learning_rate": 6.528829829392898e-06, + "loss": 1.4129, + "step": 6213 + }, + { + "epoch": 0.65, + "learning_rate": 6.525397399570534e-06, + "loss": 1.3631, + "step": 6214 + }, + { + "epoch": 0.65, + "learning_rate": 6.5219654352556435e-06, + "loss": 1.295, + "step": 6215 + }, + { + "epoch": 0.65, + "learning_rate": 6.518533936908016e-06, + "loss": 1.439, + "step": 6216 + }, + { + "epoch": 0.65, + "learning_rate": 6.515102904987389e-06, + "loss": 1.3148, + "step": 6217 + }, + { + "epoch": 0.65, + "learning_rate": 6.511672339953432e-06, + "loss": 1.3898, + "step": 6218 + }, + { + "epoch": 0.65, + "learning_rate": 6.508242242265752e-06, + "loss": 1.3222, + "step": 6219 + }, + { + "epoch": 0.65, + "learning_rate": 6.504812612383891e-06, + "loss": 1.324, + "step": 6220 + }, + { + "epoch": 0.65, + "learning_rate": 6.501383450767336e-06, + "loss": 1.951, + "step": 6221 + }, + { + "epoch": 0.65, + "learning_rate": 6.4979547578755055e-06, + "loss": 1.2878, + "step": 6222 + }, + { + "epoch": 0.65, + "learning_rate": 6.494526534167754e-06, + "loss": 1.3553, + "step": 6223 + }, + { + "epoch": 0.65, + "learning_rate": 6.491098780103375e-06, + "loss": 1.3898, + "step": 6224 + }, + { + "epoch": 0.65, + "learning_rate": 6.487671496141606e-06, + "loss": 1.4333, + "step": 6225 + }, + { + "epoch": 0.65, + "learning_rate": 6.484244682741606e-06, + "loss": 1.4461, + "step": 6226 + }, + { + "epoch": 0.65, + "learning_rate": 6.480818340362487e-06, + "loss": 1.3461, + "step": 6227 + }, + { + "epoch": 0.65, + "learning_rate": 6.4773924694632835e-06, + "loss": 1.3442, + "step": 6228 + }, + { + "epoch": 0.65, + "learning_rate": 6.473967070502982e-06, + "loss": 1.2692, + "step": 6229 + }, + { + "epoch": 0.65, + "learning_rate": 6.470542143940495e-06, + "loss": 1.446, + "step": 6230 + }, + { + "epoch": 0.65, + "learning_rate": 6.467117690234675e-06, + "loss": 1.3597, + "step": 6231 + }, + { + "epoch": 0.65, + "learning_rate": 6.463693709844305e-06, + "loss": 1.3226, + "step": 6232 + }, + { + "epoch": 0.65, + "learning_rate": 6.46027020322812e-06, + "loss": 1.2702, + "step": 6233 + }, + { + "epoch": 0.65, + "learning_rate": 6.456847170844775e-06, + "loss": 1.2554, + "step": 6234 + }, + { + "epoch": 0.65, + "learning_rate": 6.453424613152872e-06, + "loss": 1.2896, + "step": 6235 + }, + { + "epoch": 0.65, + "learning_rate": 6.450002530610943e-06, + "loss": 1.3148, + "step": 6236 + }, + { + "epoch": 0.65, + "learning_rate": 6.4465809236774635e-06, + "loss": 1.3589, + "step": 6237 + }, + { + "epoch": 0.65, + "learning_rate": 6.443159792810838e-06, + "loss": 1.2938, + "step": 6238 + }, + { + "epoch": 0.65, + "learning_rate": 6.439739138469406e-06, + "loss": 1.366, + "step": 6239 + }, + { + "epoch": 0.65, + "learning_rate": 6.436318961111455e-06, + "loss": 1.4772, + "step": 6240 + }, + { + "epoch": 0.65, + "learning_rate": 6.4328992611951975e-06, + "loss": 1.3131, + "step": 6241 + }, + { + "epoch": 0.65, + "learning_rate": 6.429480039178786e-06, + "loss": 1.2382, + "step": 6242 + }, + { + "epoch": 0.65, + "learning_rate": 6.426061295520304e-06, + "loss": 1.3394, + "step": 6243 + }, + { + "epoch": 0.65, + "learning_rate": 6.422643030677782e-06, + "loss": 1.321, + "step": 6244 + }, + { + "epoch": 0.65, + "learning_rate": 6.419225245109175e-06, + "loss": 1.3478, + "step": 6245 + }, + { + "epoch": 0.65, + "learning_rate": 6.415807939272383e-06, + "loss": 1.3249, + "step": 6246 + }, + { + "epoch": 0.66, + "learning_rate": 6.412391113625231e-06, + "loss": 1.3602, + "step": 6247 + }, + { + "epoch": 0.66, + "learning_rate": 6.408974768625491e-06, + "loss": 1.2799, + "step": 6248 + }, + { + "epoch": 0.66, + "learning_rate": 6.405558904730863e-06, + "loss": 1.3911, + "step": 6249 + }, + { + "epoch": 0.66, + "learning_rate": 6.402143522398987e-06, + "loss": 1.3185, + "step": 6250 + }, + { + "epoch": 0.66, + "learning_rate": 6.398728622087431e-06, + "loss": 1.3198, + "step": 6251 + }, + { + "epoch": 0.66, + "learning_rate": 6.395314204253711e-06, + "loss": 1.361, + "step": 6252 + }, + { + "epoch": 0.66, + "learning_rate": 6.391900269355269e-06, + "loss": 1.3285, + "step": 6253 + }, + { + "epoch": 0.66, + "learning_rate": 6.388486817849484e-06, + "loss": 1.3097, + "step": 6254 + }, + { + "epoch": 0.66, + "learning_rate": 6.385073850193667e-06, + "loss": 1.3057, + "step": 6255 + }, + { + "epoch": 0.66, + "learning_rate": 6.381661366845075e-06, + "loss": 1.4733, + "step": 6256 + }, + { + "epoch": 0.66, + "learning_rate": 6.378249368260889e-06, + "loss": 1.3571, + "step": 6257 + }, + { + "epoch": 0.66, + "learning_rate": 6.374837854898228e-06, + "loss": 1.3278, + "step": 6258 + }, + { + "epoch": 0.66, + "learning_rate": 6.37142682721415e-06, + "loss": 1.3035, + "step": 6259 + }, + { + "epoch": 0.66, + "learning_rate": 6.368016285665645e-06, + "loss": 1.397, + "step": 6260 + }, + { + "epoch": 0.66, + "learning_rate": 6.3646062307096365e-06, + "loss": 1.353, + "step": 6261 + }, + { + "epoch": 0.66, + "learning_rate": 6.361196662802982e-06, + "loss": 1.3534, + "step": 6262 + }, + { + "epoch": 0.66, + "learning_rate": 6.357787582402482e-06, + "loss": 1.3132, + "step": 6263 + }, + { + "epoch": 0.66, + "learning_rate": 6.3543789899648624e-06, + "loss": 1.3551, + "step": 6264 + }, + { + "epoch": 0.66, + "learning_rate": 6.3509708859467855e-06, + "loss": 1.4205, + "step": 6265 + }, + { + "epoch": 0.66, + "learning_rate": 6.347563270804851e-06, + "loss": 1.341, + "step": 6266 + }, + { + "epoch": 0.66, + "learning_rate": 6.344156144995593e-06, + "loss": 1.5188, + "step": 6267 + }, + { + "epoch": 0.66, + "learning_rate": 6.340749508975477e-06, + "loss": 1.4404, + "step": 6268 + }, + { + "epoch": 0.66, + "learning_rate": 6.337343363200905e-06, + "loss": 1.3026, + "step": 6269 + }, + { + "epoch": 0.66, + "learning_rate": 6.3339377081282124e-06, + "loss": 1.3315, + "step": 6270 + }, + { + "epoch": 0.66, + "learning_rate": 6.3305325442136735e-06, + "loss": 1.2503, + "step": 6271 + }, + { + "epoch": 0.66, + "learning_rate": 6.3271278719134885e-06, + "loss": 1.1776, + "step": 6272 + }, + { + "epoch": 0.66, + "learning_rate": 6.323723691683798e-06, + "loss": 1.3033, + "step": 6273 + }, + { + "epoch": 0.66, + "learning_rate": 6.320320003980671e-06, + "loss": 1.3838, + "step": 6274 + }, + { + "epoch": 0.66, + "learning_rate": 6.3169168092601195e-06, + "loss": 1.3691, + "step": 6275 + }, + { + "epoch": 0.66, + "learning_rate": 6.313514107978083e-06, + "loss": 1.3665, + "step": 6276 + }, + { + "epoch": 0.66, + "learning_rate": 6.310111900590432e-06, + "loss": 1.358, + "step": 6277 + }, + { + "epoch": 0.66, + "learning_rate": 6.306710187552978e-06, + "loss": 1.1708, + "step": 6278 + }, + { + "epoch": 0.66, + "learning_rate": 6.303308969321464e-06, + "loss": 1.331, + "step": 6279 + }, + { + "epoch": 0.66, + "learning_rate": 6.299908246351566e-06, + "loss": 1.3914, + "step": 6280 + }, + { + "epoch": 0.66, + "learning_rate": 6.2965080190988896e-06, + "loss": 1.3183, + "step": 6281 + }, + { + "epoch": 0.66, + "learning_rate": 6.293108288018981e-06, + "loss": 1.2969, + "step": 6282 + }, + { + "epoch": 0.66, + "learning_rate": 6.289709053567318e-06, + "loss": 1.2892, + "step": 6283 + }, + { + "epoch": 0.66, + "learning_rate": 6.2863103161993085e-06, + "loss": 1.3517, + "step": 6284 + }, + { + "epoch": 0.66, + "learning_rate": 6.282912076370295e-06, + "loss": 1.3329, + "step": 6285 + }, + { + "epoch": 0.66, + "learning_rate": 6.279514334535557e-06, + "loss": 1.3396, + "step": 6286 + }, + { + "epoch": 0.66, + "learning_rate": 6.276117091150304e-06, + "loss": 1.3878, + "step": 6287 + }, + { + "epoch": 0.66, + "learning_rate": 6.272720346669677e-06, + "loss": 1.2608, + "step": 6288 + }, + { + "epoch": 0.66, + "learning_rate": 6.269324101548754e-06, + "loss": 1.3605, + "step": 6289 + }, + { + "epoch": 0.66, + "learning_rate": 6.265928356242546e-06, + "loss": 1.2682, + "step": 6290 + }, + { + "epoch": 0.66, + "learning_rate": 6.262533111205995e-06, + "loss": 1.3426, + "step": 6291 + }, + { + "epoch": 0.66, + "learning_rate": 6.259138366893975e-06, + "loss": 1.2987, + "step": 6292 + }, + { + "epoch": 0.66, + "learning_rate": 6.255744123761295e-06, + "loss": 1.3521, + "step": 6293 + }, + { + "epoch": 0.66, + "learning_rate": 6.252350382262697e-06, + "loss": 1.2816, + "step": 6294 + }, + { + "epoch": 0.66, + "learning_rate": 6.248957142852856e-06, + "loss": 1.3884, + "step": 6295 + }, + { + "epoch": 0.66, + "learning_rate": 6.2455644059863795e-06, + "loss": 1.3545, + "step": 6296 + }, + { + "epoch": 0.66, + "learning_rate": 6.2421721721178015e-06, + "loss": 1.3636, + "step": 6297 + }, + { + "epoch": 0.66, + "learning_rate": 6.238780441701601e-06, + "loss": 1.3584, + "step": 6298 + }, + { + "epoch": 0.66, + "learning_rate": 6.235389215192179e-06, + "loss": 1.3459, + "step": 6299 + }, + { + "epoch": 0.66, + "learning_rate": 6.231998493043875e-06, + "loss": 1.4654, + "step": 6300 + }, + { + "epoch": 0.66, + "learning_rate": 6.228608275710954e-06, + "loss": 1.3628, + "step": 6301 + }, + { + "epoch": 0.66, + "learning_rate": 6.225218563647623e-06, + "loss": 1.3278, + "step": 6302 + }, + { + "epoch": 0.66, + "learning_rate": 6.221829357308016e-06, + "loss": 1.395, + "step": 6303 + }, + { + "epoch": 0.66, + "learning_rate": 6.218440657146196e-06, + "loss": 1.3481, + "step": 6304 + }, + { + "epoch": 0.66, + "learning_rate": 6.215052463616165e-06, + "loss": 1.309, + "step": 6305 + }, + { + "epoch": 0.66, + "learning_rate": 6.211664777171853e-06, + "loss": 1.275, + "step": 6306 + }, + { + "epoch": 0.66, + "learning_rate": 6.208277598267123e-06, + "loss": 1.4885, + "step": 6307 + }, + { + "epoch": 0.66, + "learning_rate": 6.2048909273557686e-06, + "loss": 1.3334, + "step": 6308 + }, + { + "epoch": 0.66, + "learning_rate": 6.201504764891518e-06, + "loss": 1.3399, + "step": 6309 + }, + { + "epoch": 0.66, + "learning_rate": 6.198119111328032e-06, + "loss": 1.3163, + "step": 6310 + }, + { + "epoch": 0.66, + "learning_rate": 6.1947339671188966e-06, + "loss": 1.2746, + "step": 6311 + }, + { + "epoch": 0.66, + "learning_rate": 6.191349332717635e-06, + "loss": 1.2984, + "step": 6312 + }, + { + "epoch": 0.66, + "learning_rate": 6.187965208577705e-06, + "loss": 1.2295, + "step": 6313 + }, + { + "epoch": 0.66, + "learning_rate": 6.18458159515249e-06, + "loss": 1.3424, + "step": 6314 + }, + { + "epoch": 0.66, + "learning_rate": 6.181198492895308e-06, + "loss": 1.3108, + "step": 6315 + }, + { + "epoch": 0.66, + "learning_rate": 6.1778159022594045e-06, + "loss": 1.4895, + "step": 6316 + }, + { + "epoch": 0.66, + "learning_rate": 6.174433823697964e-06, + "loss": 1.3247, + "step": 6317 + }, + { + "epoch": 0.66, + "learning_rate": 6.171052257664097e-06, + "loss": 1.3659, + "step": 6318 + }, + { + "epoch": 0.66, + "learning_rate": 6.167671204610844e-06, + "loss": 1.3889, + "step": 6319 + }, + { + "epoch": 0.66, + "learning_rate": 6.1642906649911815e-06, + "loss": 1.3946, + "step": 6320 + }, + { + "epoch": 0.66, + "learning_rate": 6.1609106392580155e-06, + "loss": 1.3685, + "step": 6321 + }, + { + "epoch": 0.66, + "learning_rate": 6.157531127864181e-06, + "loss": 1.2584, + "step": 6322 + }, + { + "epoch": 0.66, + "learning_rate": 6.154152131262448e-06, + "loss": 1.3263, + "step": 6323 + }, + { + "epoch": 0.66, + "learning_rate": 6.15077364990551e-06, + "loss": 1.3336, + "step": 6324 + }, + { + "epoch": 0.66, + "learning_rate": 6.147395684246003e-06, + "loss": 1.2513, + "step": 6325 + }, + { + "epoch": 0.66, + "learning_rate": 6.144018234736484e-06, + "loss": 1.3715, + "step": 6326 + }, + { + "epoch": 0.66, + "learning_rate": 6.140641301829444e-06, + "loss": 1.3464, + "step": 6327 + }, + { + "epoch": 0.66, + "learning_rate": 6.1372648859773075e-06, + "loss": 1.4374, + "step": 6328 + }, + { + "epoch": 0.66, + "learning_rate": 6.1338889876324285e-06, + "loss": 1.3903, + "step": 6329 + }, + { + "epoch": 0.66, + "learning_rate": 6.130513607247087e-06, + "loss": 1.3715, + "step": 6330 + }, + { + "epoch": 0.66, + "learning_rate": 6.127138745273497e-06, + "loss": 1.3196, + "step": 6331 + }, + { + "epoch": 0.66, + "learning_rate": 6.123764402163808e-06, + "loss": 1.3013, + "step": 6332 + }, + { + "epoch": 0.66, + "learning_rate": 6.120390578370093e-06, + "loss": 1.2751, + "step": 6333 + }, + { + "epoch": 0.66, + "learning_rate": 6.117017274344356e-06, + "loss": 1.2258, + "step": 6334 + }, + { + "epoch": 0.66, + "learning_rate": 6.113644490538533e-06, + "loss": 1.2982, + "step": 6335 + }, + { + "epoch": 0.66, + "learning_rate": 6.110272227404492e-06, + "loss": 1.3124, + "step": 6336 + }, + { + "epoch": 0.66, + "learning_rate": 6.10690048539403e-06, + "loss": 1.2451, + "step": 6337 + }, + { + "epoch": 0.66, + "learning_rate": 6.103529264958874e-06, + "loss": 1.3896, + "step": 6338 + }, + { + "epoch": 0.66, + "learning_rate": 6.100158566550677e-06, + "loss": 1.46, + "step": 6339 + }, + { + "epoch": 0.66, + "learning_rate": 6.096788390621031e-06, + "loss": 1.2965, + "step": 6340 + }, + { + "epoch": 0.66, + "learning_rate": 6.093418737621452e-06, + "loss": 1.2969, + "step": 6341 + }, + { + "epoch": 0.67, + "learning_rate": 6.0900496080033836e-06, + "loss": 1.3988, + "step": 6342 + }, + { + "epoch": 0.67, + "learning_rate": 6.086681002218204e-06, + "loss": 1.351, + "step": 6343 + }, + { + "epoch": 0.67, + "learning_rate": 6.083312920717224e-06, + "loss": 1.3447, + "step": 6344 + }, + { + "epoch": 0.67, + "learning_rate": 6.079945363951674e-06, + "loss": 1.3361, + "step": 6345 + }, + { + "epoch": 0.67, + "learning_rate": 6.076578332372724e-06, + "loss": 1.3688, + "step": 6346 + }, + { + "epoch": 0.67, + "learning_rate": 6.073211826431467e-06, + "loss": 1.2831, + "step": 6347 + }, + { + "epoch": 0.67, + "learning_rate": 6.069845846578931e-06, + "loss": 1.369, + "step": 6348 + }, + { + "epoch": 0.67, + "learning_rate": 6.06648039326607e-06, + "loss": 1.3247, + "step": 6349 + }, + { + "epoch": 0.67, + "learning_rate": 6.063115466943765e-06, + "loss": 1.288, + "step": 6350 + }, + { + "epoch": 0.67, + "learning_rate": 6.0597510680628345e-06, + "loss": 1.0733, + "step": 6351 + }, + { + "epoch": 0.67, + "learning_rate": 6.056387197074021e-06, + "loss": 1.3386, + "step": 6352 + }, + { + "epoch": 0.67, + "learning_rate": 6.053023854427993e-06, + "loss": 1.3682, + "step": 6353 + }, + { + "epoch": 0.67, + "learning_rate": 6.049661040575353e-06, + "loss": 1.5669, + "step": 6354 + }, + { + "epoch": 0.67, + "learning_rate": 6.0462987559666355e-06, + "loss": 1.3432, + "step": 6355 + }, + { + "epoch": 0.67, + "learning_rate": 6.042937001052298e-06, + "loss": 1.327, + "step": 6356 + }, + { + "epoch": 0.67, + "learning_rate": 6.039575776282728e-06, + "loss": 1.3101, + "step": 6357 + }, + { + "epoch": 0.67, + "learning_rate": 6.0362150821082425e-06, + "loss": 1.3239, + "step": 6358 + }, + { + "epoch": 0.67, + "learning_rate": 6.032854918979092e-06, + "loss": 1.435, + "step": 6359 + }, + { + "epoch": 0.67, + "learning_rate": 6.029495287345448e-06, + "loss": 1.3503, + "step": 6360 + }, + { + "epoch": 0.67, + "learning_rate": 6.0261361876574186e-06, + "loss": 1.3356, + "step": 6361 + }, + { + "epoch": 0.67, + "learning_rate": 6.022777620365032e-06, + "loss": 1.3301, + "step": 6362 + }, + { + "epoch": 0.67, + "learning_rate": 6.019419585918255e-06, + "loss": 1.3925, + "step": 6363 + }, + { + "epoch": 0.67, + "learning_rate": 6.016062084766978e-06, + "loss": 1.3794, + "step": 6364 + }, + { + "epoch": 0.67, + "learning_rate": 6.0127051173610155e-06, + "loss": 1.5496, + "step": 6365 + }, + { + "epoch": 0.67, + "learning_rate": 6.009348684150116e-06, + "loss": 1.3227, + "step": 6366 + }, + { + "epoch": 0.67, + "learning_rate": 6.005992785583958e-06, + "loss": 1.3474, + "step": 6367 + }, + { + "epoch": 0.67, + "learning_rate": 6.002637422112143e-06, + "loss": 1.3262, + "step": 6368 + }, + { + "epoch": 0.67, + "eval_loss": 1.4049769639968872, + "eval_runtime": 77.5156, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 6368 + }, + { + "epoch": 0.67, + "learning_rate": 5.999282594184206e-06, + "loss": 1.3083, + "step": 6369 + }, + { + "epoch": 0.67, + "learning_rate": 5.995928302249603e-06, + "loss": 1.323, + "step": 6370 + }, + { + "epoch": 0.67, + "learning_rate": 5.99257454675773e-06, + "loss": 1.3101, + "step": 6371 + }, + { + "epoch": 0.67, + "learning_rate": 5.989221328157899e-06, + "loss": 1.4546, + "step": 6372 + }, + { + "epoch": 0.67, + "learning_rate": 5.985868646899355e-06, + "loss": 1.3315, + "step": 6373 + }, + { + "epoch": 0.67, + "learning_rate": 5.982516503431273e-06, + "loss": 1.3768, + "step": 6374 + }, + { + "epoch": 0.67, + "learning_rate": 5.979164898202755e-06, + "loss": 1.332, + "step": 6375 + }, + { + "epoch": 0.67, + "learning_rate": 5.975813831662829e-06, + "loss": 1.3154, + "step": 6376 + }, + { + "epoch": 0.67, + "learning_rate": 5.972463304260448e-06, + "loss": 1.3636, + "step": 6377 + }, + { + "epoch": 0.67, + "learning_rate": 5.969113316444504e-06, + "loss": 1.3553, + "step": 6378 + }, + { + "epoch": 0.67, + "learning_rate": 5.965763868663803e-06, + "loss": 1.3805, + "step": 6379 + }, + { + "epoch": 0.67, + "learning_rate": 5.962414961367089e-06, + "loss": 1.3096, + "step": 6380 + }, + { + "epoch": 0.67, + "learning_rate": 5.959066595003025e-06, + "loss": 1.326, + "step": 6381 + }, + { + "epoch": 0.67, + "learning_rate": 5.955718770020212e-06, + "loss": 1.3021, + "step": 6382 + }, + { + "epoch": 0.67, + "learning_rate": 5.952371486867168e-06, + "loss": 1.35, + "step": 6383 + }, + { + "epoch": 0.67, + "learning_rate": 5.949024745992344e-06, + "loss": 1.6749, + "step": 6384 + }, + { + "epoch": 0.67, + "learning_rate": 5.945678547844117e-06, + "loss": 1.4931, + "step": 6385 + }, + { + "epoch": 0.67, + "learning_rate": 5.942332892870793e-06, + "loss": 1.284, + "step": 6386 + }, + { + "epoch": 0.67, + "learning_rate": 5.938987781520604e-06, + "loss": 1.3296, + "step": 6387 + }, + { + "epoch": 0.67, + "learning_rate": 5.9356432142417074e-06, + "loss": 1.4837, + "step": 6388 + }, + { + "epoch": 0.67, + "learning_rate": 5.932299191482188e-06, + "loss": 1.3114, + "step": 6389 + }, + { + "epoch": 0.67, + "learning_rate": 5.928955713690063e-06, + "loss": 1.3328, + "step": 6390 + }, + { + "epoch": 0.67, + "learning_rate": 5.92561278131327e-06, + "loss": 1.3163, + "step": 6391 + }, + { + "epoch": 0.67, + "learning_rate": 5.922270394799676e-06, + "loss": 1.3068, + "step": 6392 + }, + { + "epoch": 0.67, + "learning_rate": 5.918928554597073e-06, + "loss": 1.292, + "step": 6393 + }, + { + "epoch": 0.67, + "learning_rate": 5.915587261153186e-06, + "loss": 1.3359, + "step": 6394 + }, + { + "epoch": 0.67, + "learning_rate": 5.912246514915662e-06, + "loss": 1.4109, + "step": 6395 + }, + { + "epoch": 0.67, + "learning_rate": 5.908906316332071e-06, + "loss": 1.3083, + "step": 6396 + }, + { + "epoch": 0.67, + "learning_rate": 5.905566665849917e-06, + "loss": 1.2973, + "step": 6397 + }, + { + "epoch": 0.67, + "learning_rate": 5.902227563916627e-06, + "loss": 1.4159, + "step": 6398 + }, + { + "epoch": 0.67, + "learning_rate": 5.898889010979556e-06, + "loss": 1.287, + "step": 6399 + }, + { + "epoch": 0.67, + "learning_rate": 5.89555100748598e-06, + "loss": 1.2865, + "step": 6400 + }, + { + "epoch": 0.67, + "learning_rate": 5.89221355388311e-06, + "loss": 1.3137, + "step": 6401 + }, + { + "epoch": 0.67, + "learning_rate": 5.8888766506180785e-06, + "loss": 1.2751, + "step": 6402 + }, + { + "epoch": 0.67, + "learning_rate": 5.885540298137944e-06, + "loss": 1.3687, + "step": 6403 + }, + { + "epoch": 0.67, + "learning_rate": 5.882204496889688e-06, + "loss": 1.2941, + "step": 6404 + }, + { + "epoch": 0.67, + "learning_rate": 5.878869247320231e-06, + "loss": 1.2926, + "step": 6405 + }, + { + "epoch": 0.67, + "learning_rate": 5.875534549876404e-06, + "loss": 1.2675, + "step": 6406 + }, + { + "epoch": 0.67, + "learning_rate": 5.872200405004973e-06, + "loss": 1.2806, + "step": 6407 + }, + { + "epoch": 0.67, + "learning_rate": 5.868866813152625e-06, + "loss": 1.3438, + "step": 6408 + }, + { + "epoch": 0.67, + "learning_rate": 5.865533774765981e-06, + "loss": 1.2947, + "step": 6409 + }, + { + "epoch": 0.67, + "learning_rate": 5.862201290291578e-06, + "loss": 1.3643, + "step": 6410 + }, + { + "epoch": 0.67, + "learning_rate": 5.858869360175887e-06, + "loss": 1.2579, + "step": 6411 + }, + { + "epoch": 0.67, + "learning_rate": 5.855537984865296e-06, + "loss": 1.3479, + "step": 6412 + }, + { + "epoch": 0.67, + "learning_rate": 5.852207164806127e-06, + "loss": 1.3239, + "step": 6413 + }, + { + "epoch": 0.67, + "learning_rate": 5.848876900444626e-06, + "loss": 1.2644, + "step": 6414 + }, + { + "epoch": 0.67, + "learning_rate": 5.845547192226959e-06, + "loss": 1.3279, + "step": 6415 + }, + { + "epoch": 0.67, + "learning_rate": 5.8422180405992216e-06, + "loss": 1.5202, + "step": 6416 + }, + { + "epoch": 0.67, + "learning_rate": 5.838889446007439e-06, + "loss": 1.5714, + "step": 6417 + }, + { + "epoch": 0.67, + "learning_rate": 5.835561408897552e-06, + "loss": 1.2592, + "step": 6418 + }, + { + "epoch": 0.67, + "learning_rate": 5.832233929715434e-06, + "loss": 1.3407, + "step": 6419 + }, + { + "epoch": 0.67, + "learning_rate": 5.828907008906882e-06, + "loss": 1.3555, + "step": 6420 + }, + { + "epoch": 0.67, + "learning_rate": 5.825580646917622e-06, + "loss": 1.2602, + "step": 6421 + }, + { + "epoch": 0.67, + "learning_rate": 5.822254844193293e-06, + "loss": 1.2672, + "step": 6422 + }, + { + "epoch": 0.67, + "learning_rate": 5.818929601179472e-06, + "loss": 1.3361, + "step": 6423 + }, + { + "epoch": 0.67, + "learning_rate": 5.8156049183216575e-06, + "loss": 1.49, + "step": 6424 + }, + { + "epoch": 0.67, + "learning_rate": 5.812280796065269e-06, + "loss": 1.306, + "step": 6425 + }, + { + "epoch": 0.67, + "learning_rate": 5.808957234855654e-06, + "loss": 1.3167, + "step": 6426 + }, + { + "epoch": 0.67, + "learning_rate": 5.805634235138082e-06, + "loss": 1.3103, + "step": 6427 + }, + { + "epoch": 0.67, + "learning_rate": 5.802311797357752e-06, + "loss": 1.2992, + "step": 6428 + }, + { + "epoch": 0.67, + "learning_rate": 5.7989899219597875e-06, + "loss": 1.3269, + "step": 6429 + }, + { + "epoch": 0.67, + "learning_rate": 5.795668609389233e-06, + "loss": 1.3393, + "step": 6430 + }, + { + "epoch": 0.67, + "learning_rate": 5.79234786009105e-06, + "loss": 1.2633, + "step": 6431 + }, + { + "epoch": 0.67, + "learning_rate": 5.7890276745101495e-06, + "loss": 1.2758, + "step": 6432 + }, + { + "epoch": 0.67, + "learning_rate": 5.785708053091339e-06, + "loss": 1.3294, + "step": 6433 + }, + { + "epoch": 0.67, + "learning_rate": 5.782388996279371e-06, + "loss": 1.3657, + "step": 6434 + }, + { + "epoch": 0.67, + "learning_rate": 5.779070504518905e-06, + "loss": 1.3353, + "step": 6435 + }, + { + "epoch": 0.67, + "learning_rate": 5.775752578254539e-06, + "loss": 1.2741, + "step": 6436 + }, + { + "epoch": 0.68, + "learning_rate": 5.772435217930792e-06, + "loss": 1.2979, + "step": 6437 + }, + { + "epoch": 0.68, + "learning_rate": 5.7691184239921026e-06, + "loss": 1.366, + "step": 6438 + }, + { + "epoch": 0.68, + "learning_rate": 5.765802196882828e-06, + "loss": 1.2873, + "step": 6439 + }, + { + "epoch": 0.68, + "learning_rate": 5.762486537047271e-06, + "loss": 1.2865, + "step": 6440 + }, + { + "epoch": 0.68, + "learning_rate": 5.7591714449296365e-06, + "loss": 1.3887, + "step": 6441 + }, + { + "epoch": 0.68, + "learning_rate": 5.755856920974063e-06, + "loss": 1.127, + "step": 6442 + }, + { + "epoch": 0.68, + "learning_rate": 5.752542965624617e-06, + "loss": 1.4331, + "step": 6443 + }, + { + "epoch": 0.68, + "learning_rate": 5.749229579325274e-06, + "loss": 1.3199, + "step": 6444 + }, + { + "epoch": 0.68, + "learning_rate": 5.745916762519952e-06, + "loss": 1.2719, + "step": 6445 + }, + { + "epoch": 0.68, + "learning_rate": 5.742604515652475e-06, + "loss": 1.2991, + "step": 6446 + }, + { + "epoch": 0.68, + "learning_rate": 5.7392928391666014e-06, + "loss": 1.2164, + "step": 6447 + }, + { + "epoch": 0.68, + "learning_rate": 5.735981733506016e-06, + "loss": 1.3636, + "step": 6448 + }, + { + "epoch": 0.68, + "learning_rate": 5.732671199114314e-06, + "loss": 1.3486, + "step": 6449 + }, + { + "epoch": 0.68, + "learning_rate": 5.729361236435027e-06, + "loss": 1.3378, + "step": 6450 + }, + { + "epoch": 0.68, + "learning_rate": 5.726051845911606e-06, + "loss": 1.3521, + "step": 6451 + }, + { + "epoch": 0.68, + "learning_rate": 5.722743027987421e-06, + "loss": 1.4295, + "step": 6452 + }, + { + "epoch": 0.68, + "learning_rate": 5.719434783105772e-06, + "loss": 1.2625, + "step": 6453 + }, + { + "epoch": 0.68, + "learning_rate": 5.716127111709873e-06, + "loss": 1.2944, + "step": 6454 + }, + { + "epoch": 0.68, + "learning_rate": 5.7128200142428695e-06, + "loss": 1.3655, + "step": 6455 + }, + { + "epoch": 0.68, + "learning_rate": 5.7095134911478336e-06, + "loss": 1.3115, + "step": 6456 + }, + { + "epoch": 0.68, + "learning_rate": 5.706207542867747e-06, + "loss": 1.3391, + "step": 6457 + }, + { + "epoch": 0.68, + "learning_rate": 5.702902169845519e-06, + "loss": 1.3911, + "step": 6458 + }, + { + "epoch": 0.68, + "learning_rate": 5.699597372523997e-06, + "loss": 1.2936, + "step": 6459 + }, + { + "epoch": 0.68, + "learning_rate": 5.696293151345928e-06, + "loss": 1.379, + "step": 6460 + }, + { + "epoch": 0.68, + "learning_rate": 5.692989506754e-06, + "loss": 1.4083, + "step": 6461 + }, + { + "epoch": 0.68, + "learning_rate": 5.689686439190809e-06, + "loss": 1.2645, + "step": 6462 + }, + { + "epoch": 0.68, + "learning_rate": 5.686383949098886e-06, + "loss": 1.3207, + "step": 6463 + }, + { + "epoch": 0.68, + "learning_rate": 5.683082036920682e-06, + "loss": 1.4293, + "step": 6464 + }, + { + "epoch": 0.68, + "learning_rate": 5.679780703098563e-06, + "loss": 1.3018, + "step": 6465 + }, + { + "epoch": 0.68, + "learning_rate": 5.676479948074825e-06, + "loss": 1.3568, + "step": 6466 + }, + { + "epoch": 0.68, + "learning_rate": 5.673179772291687e-06, + "loss": 1.3252, + "step": 6467 + }, + { + "epoch": 0.68, + "learning_rate": 5.669880176191283e-06, + "loss": 1.2674, + "step": 6468 + }, + { + "epoch": 0.68, + "learning_rate": 5.666581160215676e-06, + "loss": 1.3774, + "step": 6469 + }, + { + "epoch": 0.68, + "learning_rate": 5.663282724806855e-06, + "loss": 1.3013, + "step": 6470 + }, + { + "epoch": 0.68, + "learning_rate": 5.659984870406715e-06, + "loss": 1.3354, + "step": 6471 + }, + { + "epoch": 0.68, + "learning_rate": 5.656687597457093e-06, + "loss": 1.273, + "step": 6472 + }, + { + "epoch": 0.68, + "learning_rate": 5.653390906399732e-06, + "loss": 1.3041, + "step": 6473 + }, + { + "epoch": 0.68, + "learning_rate": 5.650094797676308e-06, + "loss": 1.3521, + "step": 6474 + }, + { + "epoch": 0.68, + "learning_rate": 5.646799271728417e-06, + "loss": 1.3751, + "step": 6475 + }, + { + "epoch": 0.68, + "learning_rate": 5.643504328997571e-06, + "loss": 1.2882, + "step": 6476 + }, + { + "epoch": 0.68, + "learning_rate": 5.640209969925202e-06, + "loss": 1.2625, + "step": 6477 + }, + { + "epoch": 0.68, + "learning_rate": 5.636916194952683e-06, + "loss": 1.3648, + "step": 6478 + }, + { + "epoch": 0.68, + "learning_rate": 5.633623004521285e-06, + "loss": 1.3115, + "step": 6479 + }, + { + "epoch": 0.68, + "learning_rate": 5.6303303990722154e-06, + "loss": 1.2755, + "step": 6480 + }, + { + "epoch": 0.68, + "learning_rate": 5.627038379046595e-06, + "loss": 1.4546, + "step": 6481 + }, + { + "epoch": 0.68, + "learning_rate": 5.623746944885473e-06, + "loss": 1.3717, + "step": 6482 + }, + { + "epoch": 0.68, + "learning_rate": 5.620456097029818e-06, + "loss": 1.3188, + "step": 6483 + }, + { + "epoch": 0.68, + "learning_rate": 5.61716583592052e-06, + "loss": 1.3166, + "step": 6484 + }, + { + "epoch": 0.68, + "learning_rate": 5.613876161998377e-06, + "loss": 1.3413, + "step": 6485 + }, + { + "epoch": 0.68, + "learning_rate": 5.610587075704139e-06, + "loss": 1.395, + "step": 6486 + }, + { + "epoch": 0.68, + "learning_rate": 5.6072985774784465e-06, + "loss": 1.2914, + "step": 6487 + }, + { + "epoch": 0.68, + "learning_rate": 5.604010667761876e-06, + "loss": 1.3118, + "step": 6488 + }, + { + "epoch": 0.68, + "learning_rate": 5.600723346994932e-06, + "loss": 1.3599, + "step": 6489 + }, + { + "epoch": 0.68, + "learning_rate": 5.597436615618017e-06, + "loss": 1.2862, + "step": 6490 + }, + { + "epoch": 0.68, + "learning_rate": 5.594150474071481e-06, + "loss": 1.3585, + "step": 6491 + }, + { + "epoch": 0.68, + "learning_rate": 5.590864922795573e-06, + "loss": 1.3449, + "step": 6492 + }, + { + "epoch": 0.68, + "learning_rate": 5.587579962230475e-06, + "loss": 1.2787, + "step": 6493 + }, + { + "epoch": 0.68, + "learning_rate": 5.5842955928162934e-06, + "loss": 1.3755, + "step": 6494 + }, + { + "epoch": 0.68, + "learning_rate": 5.5810118149930406e-06, + "loss": 1.2858, + "step": 6495 + }, + { + "epoch": 0.68, + "learning_rate": 5.577728629200662e-06, + "loss": 1.4214, + "step": 6496 + }, + { + "epoch": 0.68, + "learning_rate": 5.574446035879024e-06, + "loss": 1.5007, + "step": 6497 + }, + { + "epoch": 0.68, + "learning_rate": 5.571164035467903e-06, + "loss": 1.2952, + "step": 6498 + }, + { + "epoch": 0.68, + "learning_rate": 5.56788262840701e-06, + "loss": 1.267, + "step": 6499 + }, + { + "epoch": 0.68, + "learning_rate": 5.564601815135962e-06, + "loss": 1.3168, + "step": 6500 + }, + { + "epoch": 0.68, + "learning_rate": 5.561321596094305e-06, + "loss": 1.2992, + "step": 6501 + }, + { + "epoch": 0.68, + "learning_rate": 5.558041971721511e-06, + "loss": 1.4237, + "step": 6502 + }, + { + "epoch": 0.68, + "learning_rate": 5.554762942456959e-06, + "loss": 1.3865, + "step": 6503 + }, + { + "epoch": 0.68, + "learning_rate": 5.5514845087399505e-06, + "loss": 1.2875, + "step": 6504 + }, + { + "epoch": 0.68, + "learning_rate": 5.548206671009724e-06, + "loss": 1.3011, + "step": 6505 + }, + { + "epoch": 0.68, + "learning_rate": 5.544929429705415e-06, + "loss": 1.3425, + "step": 6506 + }, + { + "epoch": 0.68, + "learning_rate": 5.541652785266095e-06, + "loss": 1.4265, + "step": 6507 + }, + { + "epoch": 0.68, + "learning_rate": 5.538376738130747e-06, + "loss": 1.2877, + "step": 6508 + }, + { + "epoch": 0.68, + "learning_rate": 5.535101288738276e-06, + "loss": 1.3652, + "step": 6509 + }, + { + "epoch": 0.68, + "learning_rate": 5.5318264375275145e-06, + "loss": 1.2997, + "step": 6510 + }, + { + "epoch": 0.68, + "learning_rate": 5.528552184937201e-06, + "loss": 1.3223, + "step": 6511 + }, + { + "epoch": 0.68, + "learning_rate": 5.525278531406006e-06, + "loss": 1.2897, + "step": 6512 + }, + { + "epoch": 0.68, + "learning_rate": 5.522005477372516e-06, + "loss": 1.3554, + "step": 6513 + }, + { + "epoch": 0.68, + "learning_rate": 5.51873302327523e-06, + "loss": 1.3233, + "step": 6514 + }, + { + "epoch": 0.68, + "learning_rate": 5.515461169552576e-06, + "loss": 1.3536, + "step": 6515 + }, + { + "epoch": 0.68, + "learning_rate": 5.5121899166429046e-06, + "loss": 1.3485, + "step": 6516 + }, + { + "epoch": 0.68, + "learning_rate": 5.508919264984468e-06, + "loss": 1.3264, + "step": 6517 + }, + { + "epoch": 0.68, + "learning_rate": 5.505649215015461e-06, + "loss": 1.4498, + "step": 6518 + }, + { + "epoch": 0.68, + "learning_rate": 5.5023797671739755e-06, + "loss": 1.4468, + "step": 6519 + }, + { + "epoch": 0.68, + "learning_rate": 5.499110921898038e-06, + "loss": 1.2659, + "step": 6520 + }, + { + "epoch": 0.68, + "learning_rate": 5.4958426796255934e-06, + "loss": 1.318, + "step": 6521 + }, + { + "epoch": 0.68, + "learning_rate": 5.492575040794498e-06, + "loss": 1.3167, + "step": 6522 + }, + { + "epoch": 0.68, + "learning_rate": 5.48930800584253e-06, + "loss": 1.3453, + "step": 6523 + }, + { + "epoch": 0.68, + "learning_rate": 5.486041575207397e-06, + "loss": 1.2557, + "step": 6524 + }, + { + "epoch": 0.68, + "learning_rate": 5.482775749326705e-06, + "loss": 1.3235, + "step": 6525 + }, + { + "epoch": 0.68, + "learning_rate": 5.479510528638001e-06, + "loss": 1.3119, + "step": 6526 + }, + { + "epoch": 0.68, + "learning_rate": 5.476245913578733e-06, + "loss": 1.4639, + "step": 6527 + }, + { + "epoch": 0.68, + "learning_rate": 5.472981904586277e-06, + "loss": 1.3233, + "step": 6528 + }, + { + "epoch": 0.68, + "learning_rate": 5.469718502097931e-06, + "loss": 1.2722, + "step": 6529 + }, + { + "epoch": 0.68, + "learning_rate": 5.466455706550906e-06, + "loss": 1.4428, + "step": 6530 + }, + { + "epoch": 0.68, + "learning_rate": 5.463193518382321e-06, + "loss": 1.5695, + "step": 6531 + }, + { + "epoch": 0.68, + "learning_rate": 5.4599319380292434e-06, + "loss": 1.3161, + "step": 6532 + }, + { + "epoch": 0.69, + "learning_rate": 5.4566709659286296e-06, + "loss": 1.3513, + "step": 6533 + }, + { + "epoch": 0.69, + "learning_rate": 5.453410602517368e-06, + "loss": 1.2716, + "step": 6534 + }, + { + "epoch": 0.69, + "learning_rate": 5.45015084823227e-06, + "loss": 1.4467, + "step": 6535 + }, + { + "epoch": 0.69, + "learning_rate": 5.44689170351005e-06, + "loss": 1.4082, + "step": 6536 + }, + { + "epoch": 0.69, + "learning_rate": 5.443633168787357e-06, + "loss": 1.303, + "step": 6537 + }, + { + "epoch": 0.69, + "learning_rate": 5.440375244500743e-06, + "loss": 1.2765, + "step": 6538 + }, + { + "epoch": 0.69, + "learning_rate": 5.43711793108669e-06, + "loss": 1.6814, + "step": 6539 + }, + { + "epoch": 0.69, + "learning_rate": 5.4338612289816e-06, + "loss": 1.3899, + "step": 6540 + }, + { + "epoch": 0.69, + "learning_rate": 5.430605138621778e-06, + "loss": 1.201, + "step": 6541 + }, + { + "epoch": 0.69, + "learning_rate": 5.42734966044346e-06, + "loss": 1.3214, + "step": 6542 + }, + { + "epoch": 0.69, + "learning_rate": 5.424094794882801e-06, + "loss": 1.2676, + "step": 6543 + }, + { + "epoch": 0.69, + "learning_rate": 5.420840542375862e-06, + "loss": 1.3006, + "step": 6544 + }, + { + "epoch": 0.69, + "learning_rate": 5.4175869033586355e-06, + "loss": 1.32, + "step": 6545 + }, + { + "epoch": 0.69, + "learning_rate": 5.41433387826702e-06, + "loss": 1.3347, + "step": 6546 + }, + { + "epoch": 0.69, + "learning_rate": 5.41108146753684e-06, + "loss": 1.3983, + "step": 6547 + }, + { + "epoch": 0.69, + "learning_rate": 5.407829671603838e-06, + "loss": 1.3756, + "step": 6548 + }, + { + "epoch": 0.69, + "learning_rate": 5.404578490903664e-06, + "loss": 1.3444, + "step": 6549 + }, + { + "epoch": 0.69, + "learning_rate": 5.4013279258718974e-06, + "loss": 1.3369, + "step": 6550 + }, + { + "epoch": 0.69, + "learning_rate": 5.398077976944034e-06, + "loss": 1.2995, + "step": 6551 + }, + { + "epoch": 0.69, + "learning_rate": 5.394828644555475e-06, + "loss": 1.3305, + "step": 6552 + }, + { + "epoch": 0.69, + "learning_rate": 5.391579929141554e-06, + "loss": 1.3743, + "step": 6553 + }, + { + "epoch": 0.69, + "learning_rate": 5.3883318311375095e-06, + "loss": 1.2829, + "step": 6554 + }, + { + "epoch": 0.69, + "learning_rate": 5.3850843509785065e-06, + "loss": 1.379, + "step": 6555 + }, + { + "epoch": 0.69, + "learning_rate": 5.3818374890996295e-06, + "loss": 1.3236, + "step": 6556 + }, + { + "epoch": 0.69, + "learning_rate": 5.378591245935865e-06, + "loss": 1.3469, + "step": 6557 + }, + { + "epoch": 0.69, + "learning_rate": 5.375345621922129e-06, + "loss": 1.3318, + "step": 6558 + }, + { + "epoch": 0.69, + "learning_rate": 5.3721006174932576e-06, + "loss": 1.3395, + "step": 6559 + }, + { + "epoch": 0.69, + "learning_rate": 5.36885623308399e-06, + "loss": 1.4148, + "step": 6560 + }, + { + "epoch": 0.69, + "learning_rate": 5.365612469128993e-06, + "loss": 1.3007, + "step": 6561 + }, + { + "epoch": 0.69, + "learning_rate": 5.362369326062853e-06, + "loss": 1.4365, + "step": 6562 + }, + { + "epoch": 0.69, + "learning_rate": 5.3591268043200585e-06, + "loss": 1.4269, + "step": 6563 + }, + { + "epoch": 0.69, + "learning_rate": 5.355884904335034e-06, + "loss": 1.2619, + "step": 6564 + }, + { + "epoch": 0.69, + "learning_rate": 5.3526436265421e-06, + "loss": 1.2678, + "step": 6565 + }, + { + "epoch": 0.69, + "learning_rate": 5.34940297137551e-06, + "loss": 1.2541, + "step": 6566 + }, + { + "epoch": 0.69, + "learning_rate": 5.3461629392694345e-06, + "loss": 1.3237, + "step": 6567 + }, + { + "epoch": 0.69, + "eval_loss": 1.402653694152832, + "eval_runtime": 77.5033, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 6567 + }, + { + "epoch": 0.69, + "learning_rate": 5.342923530657944e-06, + "loss": 1.357, + "step": 6568 + }, + { + "epoch": 0.69, + "learning_rate": 5.33968474597504e-06, + "loss": 1.3561, + "step": 6569 + }, + { + "epoch": 0.69, + "learning_rate": 5.336446585654642e-06, + "loss": 1.2969, + "step": 6570 + }, + { + "epoch": 0.69, + "learning_rate": 5.33320905013057e-06, + "loss": 1.2922, + "step": 6571 + }, + { + "epoch": 0.69, + "learning_rate": 5.329972139836581e-06, + "loss": 1.3581, + "step": 6572 + }, + { + "epoch": 0.69, + "learning_rate": 5.326735855206328e-06, + "loss": 1.2926, + "step": 6573 + }, + { + "epoch": 0.69, + "learning_rate": 5.3235001966733965e-06, + "loss": 1.3933, + "step": 6574 + }, + { + "epoch": 0.69, + "learning_rate": 5.320265164671283e-06, + "loss": 1.4009, + "step": 6575 + }, + { + "epoch": 0.69, + "learning_rate": 5.3170307596333955e-06, + "loss": 1.4051, + "step": 6576 + }, + { + "epoch": 0.69, + "learning_rate": 5.313796981993054e-06, + "loss": 1.3448, + "step": 6577 + }, + { + "epoch": 0.69, + "learning_rate": 5.310563832183515e-06, + "loss": 1.3141, + "step": 6578 + }, + { + "epoch": 0.69, + "learning_rate": 5.307331310637929e-06, + "loss": 1.3658, + "step": 6579 + }, + { + "epoch": 0.69, + "learning_rate": 5.3040994177893725e-06, + "loss": 1.2881, + "step": 6580 + }, + { + "epoch": 0.69, + "learning_rate": 5.30086815407084e-06, + "loss": 1.3051, + "step": 6581 + }, + { + "epoch": 0.69, + "learning_rate": 5.297637519915231e-06, + "loss": 1.3353, + "step": 6582 + }, + { + "epoch": 0.69, + "learning_rate": 5.2944075157553754e-06, + "loss": 1.3997, + "step": 6583 + }, + { + "epoch": 0.69, + "learning_rate": 5.291178142024002e-06, + "loss": 1.3094, + "step": 6584 + }, + { + "epoch": 0.69, + "learning_rate": 5.287949399153769e-06, + "loss": 1.3384, + "step": 6585 + }, + { + "epoch": 0.69, + "learning_rate": 5.284721287577248e-06, + "loss": 1.3183, + "step": 6586 + }, + { + "epoch": 0.69, + "learning_rate": 5.281493807726916e-06, + "loss": 1.4433, + "step": 6587 + }, + { + "epoch": 0.69, + "learning_rate": 5.278266960035174e-06, + "loss": 1.3103, + "step": 6588 + }, + { + "epoch": 0.69, + "learning_rate": 5.275040744934343e-06, + "loss": 1.3478, + "step": 6589 + }, + { + "epoch": 0.69, + "learning_rate": 5.271815162856645e-06, + "loss": 1.2713, + "step": 6590 + }, + { + "epoch": 0.69, + "learning_rate": 5.268590214234233e-06, + "loss": 1.3697, + "step": 6591 + }, + { + "epoch": 0.69, + "learning_rate": 5.265365899499156e-06, + "loss": 1.6169, + "step": 6592 + }, + { + "epoch": 0.69, + "learning_rate": 5.262142219083398e-06, + "loss": 1.2988, + "step": 6593 + }, + { + "epoch": 0.69, + "learning_rate": 5.258919173418851e-06, + "loss": 1.515, + "step": 6594 + }, + { + "epoch": 0.69, + "learning_rate": 5.2556967629373125e-06, + "loss": 1.3704, + "step": 6595 + }, + { + "epoch": 0.69, + "learning_rate": 5.2524749880705075e-06, + "loss": 1.2404, + "step": 6596 + }, + { + "epoch": 0.69, + "learning_rate": 5.249253849250073e-06, + "loss": 1.2799, + "step": 6597 + }, + { + "epoch": 0.69, + "learning_rate": 5.246033346907553e-06, + "loss": 1.2876, + "step": 6598 + }, + { + "epoch": 0.69, + "learning_rate": 5.24281348147442e-06, + "loss": 1.3058, + "step": 6599 + }, + { + "epoch": 0.69, + "learning_rate": 5.239594253382043e-06, + "loss": 1.3347, + "step": 6600 + }, + { + "epoch": 0.69, + "learning_rate": 5.236375663061722e-06, + "loss": 1.3323, + "step": 6601 + }, + { + "epoch": 0.69, + "learning_rate": 5.23315771094467e-06, + "loss": 1.3254, + "step": 6602 + }, + { + "epoch": 0.69, + "learning_rate": 5.229940397461999e-06, + "loss": 1.3462, + "step": 6603 + }, + { + "epoch": 0.69, + "learning_rate": 5.226723723044753e-06, + "loss": 1.2901, + "step": 6604 + }, + { + "epoch": 0.69, + "learning_rate": 5.223507688123887e-06, + "loss": 1.3079, + "step": 6605 + }, + { + "epoch": 0.69, + "learning_rate": 5.220292293130258e-06, + "loss": 1.4282, + "step": 6606 + }, + { + "epoch": 0.69, + "learning_rate": 5.217077538494651e-06, + "loss": 1.3197, + "step": 6607 + }, + { + "epoch": 0.69, + "learning_rate": 5.213863424647765e-06, + "loss": 1.3581, + "step": 6608 + }, + { + "epoch": 0.69, + "learning_rate": 5.2106499520202005e-06, + "loss": 1.3322, + "step": 6609 + }, + { + "epoch": 0.69, + "learning_rate": 5.207437121042488e-06, + "loss": 1.3368, + "step": 6610 + }, + { + "epoch": 0.69, + "learning_rate": 5.204224932145056e-06, + "loss": 1.2771, + "step": 6611 + }, + { + "epoch": 0.69, + "learning_rate": 5.20101338575826e-06, + "loss": 1.2852, + "step": 6612 + }, + { + "epoch": 0.69, + "learning_rate": 5.197802482312369e-06, + "loss": 1.3733, + "step": 6613 + }, + { + "epoch": 0.69, + "learning_rate": 5.194592222237551e-06, + "loss": 1.3719, + "step": 6614 + }, + { + "epoch": 0.69, + "learning_rate": 5.191382605963906e-06, + "loss": 1.3658, + "step": 6615 + }, + { + "epoch": 0.69, + "learning_rate": 5.1881736339214415e-06, + "loss": 1.3261, + "step": 6616 + }, + { + "epoch": 0.69, + "learning_rate": 5.18496530654007e-06, + "loss": 1.3057, + "step": 6617 + }, + { + "epoch": 0.69, + "learning_rate": 5.181757624249635e-06, + "loss": 1.2665, + "step": 6618 + }, + { + "epoch": 0.69, + "learning_rate": 5.1785505874798716e-06, + "loss": 1.2839, + "step": 6619 + }, + { + "epoch": 0.69, + "learning_rate": 5.175344196660447e-06, + "loss": 1.3131, + "step": 6620 + }, + { + "epoch": 0.69, + "learning_rate": 5.1721384522209385e-06, + "loss": 1.3217, + "step": 6621 + }, + { + "epoch": 0.69, + "learning_rate": 5.168933354590825e-06, + "loss": 1.3306, + "step": 6622 + }, + { + "epoch": 0.69, + "learning_rate": 5.165728904199512e-06, + "loss": 1.3197, + "step": 6623 + }, + { + "epoch": 0.69, + "learning_rate": 5.1625251014763176e-06, + "loss": 1.3035, + "step": 6624 + }, + { + "epoch": 0.69, + "learning_rate": 5.1593219468504605e-06, + "loss": 1.2927, + "step": 6625 + }, + { + "epoch": 0.69, + "learning_rate": 5.156119440751086e-06, + "loss": 1.3333, + "step": 6626 + }, + { + "epoch": 0.69, + "learning_rate": 5.152917583607251e-06, + "loss": 1.3181, + "step": 6627 + }, + { + "epoch": 0.7, + "learning_rate": 5.149716375847913e-06, + "loss": 1.347, + "step": 6628 + }, + { + "epoch": 0.7, + "learning_rate": 5.14651581790196e-06, + "loss": 1.347, + "step": 6629 + }, + { + "epoch": 0.7, + "learning_rate": 5.143315910198179e-06, + "loss": 1.2892, + "step": 6630 + }, + { + "epoch": 0.7, + "learning_rate": 5.140116653165277e-06, + "loss": 1.2996, + "step": 6631 + }, + { + "epoch": 0.7, + "learning_rate": 5.136918047231876e-06, + "loss": 1.2802, + "step": 6632 + }, + { + "epoch": 0.7, + "learning_rate": 5.133720092826501e-06, + "loss": 1.2766, + "step": 6633 + }, + { + "epoch": 0.7, + "learning_rate": 5.130522790377598e-06, + "loss": 1.5365, + "step": 6634 + }, + { + "epoch": 0.7, + "learning_rate": 5.127326140313528e-06, + "loss": 1.4848, + "step": 6635 + }, + { + "epoch": 0.7, + "learning_rate": 5.124130143062551e-06, + "loss": 1.3712, + "step": 6636 + }, + { + "epoch": 0.7, + "learning_rate": 5.120934799052859e-06, + "loss": 1.3094, + "step": 6637 + }, + { + "epoch": 0.7, + "learning_rate": 5.1177401087125355e-06, + "loss": 1.272, + "step": 6638 + }, + { + "epoch": 0.7, + "learning_rate": 5.114546072469593e-06, + "loss": 1.2856, + "step": 6639 + }, + { + "epoch": 0.7, + "learning_rate": 5.111352690751952e-06, + "loss": 1.2886, + "step": 6640 + }, + { + "epoch": 0.7, + "learning_rate": 5.108159963987436e-06, + "loss": 1.277, + "step": 6641 + }, + { + "epoch": 0.7, + "learning_rate": 5.104967892603794e-06, + "loss": 1.3392, + "step": 6642 + }, + { + "epoch": 0.7, + "learning_rate": 5.101776477028684e-06, + "loss": 1.3036, + "step": 6643 + }, + { + "epoch": 0.7, + "learning_rate": 5.098585717689667e-06, + "loss": 1.4116, + "step": 6644 + }, + { + "epoch": 0.7, + "learning_rate": 5.095395615014226e-06, + "loss": 1.3437, + "step": 6645 + }, + { + "epoch": 0.7, + "learning_rate": 5.0922061694297565e-06, + "loss": 1.2608, + "step": 6646 + }, + { + "epoch": 0.7, + "learning_rate": 5.089017381363554e-06, + "loss": 1.2959, + "step": 6647 + }, + { + "epoch": 0.7, + "learning_rate": 5.085829251242844e-06, + "loss": 1.3508, + "step": 6648 + }, + { + "epoch": 0.7, + "learning_rate": 5.0826417794947455e-06, + "loss": 1.34, + "step": 6649 + }, + { + "epoch": 0.7, + "learning_rate": 5.0794549665463e-06, + "loss": 1.3092, + "step": 6650 + }, + { + "epoch": 0.7, + "learning_rate": 5.076268812824463e-06, + "loss": 1.3417, + "step": 6651 + }, + { + "epoch": 0.7, + "learning_rate": 5.073083318756092e-06, + "loss": 1.3424, + "step": 6652 + }, + { + "epoch": 0.7, + "learning_rate": 5.069898484767961e-06, + "loss": 1.3296, + "step": 6653 + }, + { + "epoch": 0.7, + "learning_rate": 5.066714311286762e-06, + "loss": 1.2852, + "step": 6654 + }, + { + "epoch": 0.7, + "learning_rate": 5.063530798739087e-06, + "loss": 1.3462, + "step": 6655 + }, + { + "epoch": 0.7, + "learning_rate": 5.06034794755145e-06, + "loss": 1.3615, + "step": 6656 + }, + { + "epoch": 0.7, + "learning_rate": 5.057165758150262e-06, + "loss": 1.245, + "step": 6657 + }, + { + "epoch": 0.7, + "learning_rate": 5.053984230961862e-06, + "loss": 1.201, + "step": 6658 + }, + { + "epoch": 0.7, + "learning_rate": 5.050803366412494e-06, + "loss": 1.331, + "step": 6659 + }, + { + "epoch": 0.7, + "learning_rate": 5.047623164928306e-06, + "loss": 1.3034, + "step": 6660 + }, + { + "epoch": 0.7, + "learning_rate": 5.044443626935367e-06, + "loss": 1.2822, + "step": 6661 + }, + { + "epoch": 0.7, + "learning_rate": 5.041264752859657e-06, + "loss": 1.2576, + "step": 6662 + }, + { + "epoch": 0.7, + "learning_rate": 5.038086543127055e-06, + "loss": 1.3198, + "step": 6663 + }, + { + "epoch": 0.7, + "learning_rate": 5.034908998163368e-06, + "loss": 1.2892, + "step": 6664 + }, + { + "epoch": 0.7, + "learning_rate": 5.031732118394299e-06, + "loss": 1.3004, + "step": 6665 + }, + { + "epoch": 0.7, + "learning_rate": 5.028555904245469e-06, + "loss": 1.3178, + "step": 6666 + }, + { + "epoch": 0.7, + "learning_rate": 5.0253803561424156e-06, + "loss": 1.3014, + "step": 6667 + }, + { + "epoch": 0.7, + "learning_rate": 5.022205474510571e-06, + "loss": 1.3151, + "step": 6668 + }, + { + "epoch": 0.7, + "learning_rate": 5.019031259775292e-06, + "loss": 1.3551, + "step": 6669 + }, + { + "epoch": 0.7, + "learning_rate": 5.015857712361847e-06, + "loss": 1.4188, + "step": 6670 + }, + { + "epoch": 0.7, + "learning_rate": 5.0126848326954025e-06, + "loss": 1.2743, + "step": 6671 + }, + { + "epoch": 0.7, + "learning_rate": 5.009512621201043e-06, + "loss": 1.3528, + "step": 6672 + }, + { + "epoch": 0.7, + "learning_rate": 5.006341078303771e-06, + "loss": 1.309, + "step": 6673 + }, + { + "epoch": 0.7, + "learning_rate": 5.003170204428483e-06, + "loss": 1.3353, + "step": 6674 + }, + { + "epoch": 0.7, + "learning_rate": 5.000000000000003e-06, + "loss": 1.2753, + "step": 6675 + }, + { + "epoch": 0.7, + "learning_rate": 4.9968304654430465e-06, + "loss": 1.3907, + "step": 6676 + }, + { + "epoch": 0.7, + "learning_rate": 4.993661601182256e-06, + "loss": 1.2876, + "step": 6677 + }, + { + "epoch": 0.7, + "learning_rate": 4.990493407642181e-06, + "loss": 1.2534, + "step": 6678 + }, + { + "epoch": 0.7, + "learning_rate": 4.98732588524727e-06, + "loss": 1.3352, + "step": 6679 + }, + { + "epoch": 0.7, + "learning_rate": 4.984159034421895e-06, + "loss": 1.3302, + "step": 6680 + }, + { + "epoch": 0.7, + "learning_rate": 4.980992855590336e-06, + "loss": 1.3783, + "step": 6681 + }, + { + "epoch": 0.7, + "learning_rate": 4.977827349176769e-06, + "loss": 1.2848, + "step": 6682 + }, + { + "epoch": 0.7, + "learning_rate": 4.974662515605302e-06, + "loss": 1.3269, + "step": 6683 + }, + { + "epoch": 0.7, + "learning_rate": 4.971498355299932e-06, + "loss": 1.3662, + "step": 6684 + }, + { + "epoch": 0.7, + "learning_rate": 4.968334868684579e-06, + "loss": 1.2508, + "step": 6685 + }, + { + "epoch": 0.7, + "learning_rate": 4.965172056183073e-06, + "loss": 1.3872, + "step": 6686 + }, + { + "epoch": 0.7, + "learning_rate": 4.962009918219142e-06, + "loss": 1.3008, + "step": 6687 + }, + { + "epoch": 0.7, + "learning_rate": 4.958848455216434e-06, + "loss": 1.2058, + "step": 6688 + }, + { + "epoch": 0.7, + "learning_rate": 4.95568766759851e-06, + "loss": 1.3127, + "step": 6689 + }, + { + "epoch": 0.7, + "learning_rate": 4.952527555788825e-06, + "loss": 1.2985, + "step": 6690 + }, + { + "epoch": 0.7, + "learning_rate": 4.949368120210757e-06, + "loss": 1.333, + "step": 6691 + }, + { + "epoch": 0.7, + "learning_rate": 4.946209361287593e-06, + "loss": 1.2945, + "step": 6692 + }, + { + "epoch": 0.7, + "learning_rate": 4.943051279442516e-06, + "loss": 1.262, + "step": 6693 + }, + { + "epoch": 0.7, + "learning_rate": 4.93989387509864e-06, + "loss": 1.6155, + "step": 6694 + }, + { + "epoch": 0.7, + "learning_rate": 4.936737148678965e-06, + "loss": 1.2838, + "step": 6695 + }, + { + "epoch": 0.7, + "learning_rate": 4.933581100606415e-06, + "loss": 1.3778, + "step": 6696 + }, + { + "epoch": 0.7, + "learning_rate": 4.930425731303824e-06, + "loss": 1.3624, + "step": 6697 + }, + { + "epoch": 0.7, + "learning_rate": 4.927271041193923e-06, + "loss": 1.2641, + "step": 6698 + }, + { + "epoch": 0.7, + "learning_rate": 4.924117030699362e-06, + "loss": 1.3314, + "step": 6699 + }, + { + "epoch": 0.7, + "learning_rate": 4.920963700242704e-06, + "loss": 1.328, + "step": 6700 + }, + { + "epoch": 0.7, + "learning_rate": 4.917811050246404e-06, + "loss": 1.3128, + "step": 6701 + }, + { + "epoch": 0.7, + "learning_rate": 4.914659081132843e-06, + "loss": 1.3877, + "step": 6702 + }, + { + "epoch": 0.7, + "learning_rate": 4.911507793324299e-06, + "loss": 1.3114, + "step": 6703 + }, + { + "epoch": 0.7, + "learning_rate": 4.908357187242967e-06, + "loss": 1.3592, + "step": 6704 + }, + { + "epoch": 0.7, + "learning_rate": 4.905207263310948e-06, + "loss": 1.329, + "step": 6705 + }, + { + "epoch": 0.7, + "learning_rate": 4.902058021950247e-06, + "loss": 1.2558, + "step": 6706 + }, + { + "epoch": 0.7, + "learning_rate": 4.898909463582784e-06, + "loss": 1.2489, + "step": 6707 + }, + { + "epoch": 0.7, + "learning_rate": 4.895761588630388e-06, + "loss": 1.2817, + "step": 6708 + }, + { + "epoch": 0.7, + "learning_rate": 4.892614397514785e-06, + "loss": 1.1606, + "step": 6709 + }, + { + "epoch": 0.7, + "learning_rate": 4.889467890657628e-06, + "loss": 1.2878, + "step": 6710 + }, + { + "epoch": 0.7, + "learning_rate": 4.886322068480458e-06, + "loss": 1.2747, + "step": 6711 + }, + { + "epoch": 0.7, + "learning_rate": 4.88317693140474e-06, + "loss": 1.3662, + "step": 6712 + }, + { + "epoch": 0.7, + "learning_rate": 4.880032479851844e-06, + "loss": 1.3009, + "step": 6713 + }, + { + "epoch": 0.7, + "learning_rate": 4.8768887142430385e-06, + "loss": 1.3157, + "step": 6714 + }, + { + "epoch": 0.7, + "learning_rate": 4.873745634999511e-06, + "loss": 1.4461, + "step": 6715 + }, + { + "epoch": 0.7, + "learning_rate": 4.870603242542358e-06, + "loss": 1.3818, + "step": 6716 + }, + { + "epoch": 0.7, + "learning_rate": 4.86746153729257e-06, + "loss": 1.3361, + "step": 6717 + }, + { + "epoch": 0.7, + "learning_rate": 4.864320519671061e-06, + "loss": 1.3147, + "step": 6718 + }, + { + "epoch": 0.7, + "learning_rate": 4.8611801900986485e-06, + "loss": 1.3773, + "step": 6719 + }, + { + "epoch": 0.7, + "learning_rate": 4.858040548996049e-06, + "loss": 1.3091, + "step": 6720 + }, + { + "epoch": 0.7, + "learning_rate": 4.854901596783902e-06, + "loss": 1.3314, + "step": 6721 + }, + { + "epoch": 0.7, + "learning_rate": 4.851763333882738e-06, + "loss": 1.3082, + "step": 6722 + }, + { + "epoch": 0.71, + "learning_rate": 4.848625760713007e-06, + "loss": 1.2687, + "step": 6723 + }, + { + "epoch": 0.71, + "learning_rate": 4.845488877695068e-06, + "loss": 1.3378, + "step": 6724 + }, + { + "epoch": 0.71, + "learning_rate": 4.842352685249174e-06, + "loss": 1.3516, + "step": 6725 + }, + { + "epoch": 0.71, + "learning_rate": 4.839217183795501e-06, + "loss": 1.4083, + "step": 6726 + }, + { + "epoch": 0.71, + "learning_rate": 4.836082373754124e-06, + "loss": 1.3073, + "step": 6727 + }, + { + "epoch": 0.71, + "learning_rate": 4.832948255545024e-06, + "loss": 1.2948, + "step": 6728 + }, + { + "epoch": 0.71, + "learning_rate": 4.829814829588099e-06, + "loss": 1.3323, + "step": 6729 + }, + { + "epoch": 0.71, + "learning_rate": 4.826682096303139e-06, + "loss": 1.3101, + "step": 6730 + }, + { + "epoch": 0.71, + "learning_rate": 4.823550056109853e-06, + "loss": 1.3323, + "step": 6731 + }, + { + "epoch": 0.71, + "learning_rate": 4.8204187094278605e-06, + "loss": 1.3862, + "step": 6732 + }, + { + "epoch": 0.71, + "learning_rate": 4.817288056676671e-06, + "loss": 1.3112, + "step": 6733 + }, + { + "epoch": 0.71, + "learning_rate": 4.8141580982757175e-06, + "loss": 1.297, + "step": 6734 + }, + { + "epoch": 0.71, + "learning_rate": 4.811028834644336e-06, + "loss": 1.2604, + "step": 6735 + }, + { + "epoch": 0.71, + "learning_rate": 4.807900266201761e-06, + "loss": 1.343, + "step": 6736 + }, + { + "epoch": 0.71, + "learning_rate": 4.804772393367142e-06, + "loss": 1.3254, + "step": 6737 + }, + { + "epoch": 0.71, + "learning_rate": 4.80164521655954e-06, + "loss": 1.2688, + "step": 6738 + }, + { + "epoch": 0.71, + "learning_rate": 4.798518736197909e-06, + "loss": 1.2693, + "step": 6739 + }, + { + "epoch": 0.71, + "learning_rate": 4.795392952701122e-06, + "loss": 1.4536, + "step": 6740 + }, + { + "epoch": 0.71, + "learning_rate": 4.7922678664879485e-06, + "loss": 1.3811, + "step": 6741 + }, + { + "epoch": 0.71, + "learning_rate": 4.789143477977072e-06, + "loss": 1.2584, + "step": 6742 + }, + { + "epoch": 0.71, + "learning_rate": 4.786019787587084e-06, + "loss": 1.2584, + "step": 6743 + }, + { + "epoch": 0.71, + "learning_rate": 4.782896795736472e-06, + "loss": 1.2005, + "step": 6744 + }, + { + "epoch": 0.71, + "learning_rate": 4.779774502843642e-06, + "loss": 1.335, + "step": 6745 + }, + { + "epoch": 0.71, + "learning_rate": 4.776652909326901e-06, + "loss": 1.3675, + "step": 6746 + }, + { + "epoch": 0.71, + "learning_rate": 4.773532015604457e-06, + "loss": 1.3794, + "step": 6747 + }, + { + "epoch": 0.71, + "learning_rate": 4.770411822094437e-06, + "loss": 1.3629, + "step": 6748 + }, + { + "epoch": 0.71, + "learning_rate": 4.76729232921486e-06, + "loss": 1.0805, + "step": 6749 + }, + { + "epoch": 0.71, + "learning_rate": 4.76417353738366e-06, + "loss": 1.2874, + "step": 6750 + }, + { + "epoch": 0.71, + "learning_rate": 4.761055447018681e-06, + "loss": 1.428, + "step": 6751 + }, + { + "epoch": 0.71, + "learning_rate": 4.757938058537656e-06, + "loss": 1.2935, + "step": 6752 + }, + { + "epoch": 0.71, + "learning_rate": 4.754821372358242e-06, + "loss": 1.4202, + "step": 6753 + }, + { + "epoch": 0.71, + "learning_rate": 4.751705388897997e-06, + "loss": 1.3109, + "step": 6754 + }, + { + "epoch": 0.71, + "learning_rate": 4.7485901085743754e-06, + "loss": 1.3319, + "step": 6755 + }, + { + "epoch": 0.71, + "learning_rate": 4.745475531804753e-06, + "loss": 1.3246, + "step": 6756 + }, + { + "epoch": 0.71, + "learning_rate": 4.742361659006395e-06, + "loss": 1.3407, + "step": 6757 + }, + { + "epoch": 0.71, + "learning_rate": 4.739248490596483e-06, + "loss": 1.2953, + "step": 6758 + }, + { + "epoch": 0.71, + "learning_rate": 4.736136026992107e-06, + "loss": 1.3214, + "step": 6759 + }, + { + "epoch": 0.71, + "learning_rate": 4.733024268610249e-06, + "loss": 1.4112, + "step": 6760 + }, + { + "epoch": 0.71, + "learning_rate": 4.7299132158678085e-06, + "loss": 1.2981, + "step": 6761 + }, + { + "epoch": 0.71, + "learning_rate": 4.726802869181591e-06, + "loss": 1.2975, + "step": 6762 + }, + { + "epoch": 0.71, + "learning_rate": 4.723693228968293e-06, + "loss": 1.3047, + "step": 6763 + }, + { + "epoch": 0.71, + "learning_rate": 4.720584295644533e-06, + "loss": 1.3906, + "step": 6764 + }, + { + "epoch": 0.71, + "learning_rate": 4.717476069626832e-06, + "loss": 1.2523, + "step": 6765 + }, + { + "epoch": 0.71, + "learning_rate": 4.7143685513316025e-06, + "loss": 1.0453, + "step": 6766 + }, + { + "epoch": 0.71, + "eval_loss": 1.4004828929901123, + "eval_runtime": 77.565, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 6766 + }, + { + "epoch": 0.71, + "learning_rate": 4.711261741175182e-06, + "loss": 1.1339, + "step": 6767 + }, + { + "epoch": 0.71, + "learning_rate": 4.7081556395737935e-06, + "loss": 1.2401, + "step": 6768 + }, + { + "epoch": 0.71, + "learning_rate": 4.705050246943581e-06, + "loss": 1.3009, + "step": 6769 + }, + { + "epoch": 0.71, + "learning_rate": 4.7019455637005895e-06, + "loss": 1.3106, + "step": 6770 + }, + { + "epoch": 0.71, + "learning_rate": 4.698841590260758e-06, + "loss": 1.3021, + "step": 6771 + }, + { + "epoch": 0.71, + "learning_rate": 4.695738327039947e-06, + "loss": 1.3147, + "step": 6772 + }, + { + "epoch": 0.71, + "learning_rate": 4.692635774453914e-06, + "loss": 1.238, + "step": 6773 + }, + { + "epoch": 0.71, + "learning_rate": 4.6895339329183154e-06, + "loss": 1.3876, + "step": 6774 + }, + { + "epoch": 0.71, + "learning_rate": 4.686432802848726e-06, + "loss": 1.3012, + "step": 6775 + }, + { + "epoch": 0.71, + "learning_rate": 4.68333238466061e-06, + "loss": 1.1421, + "step": 6776 + }, + { + "epoch": 0.71, + "learning_rate": 4.6802326787693455e-06, + "loss": 1.2838, + "step": 6777 + }, + { + "epoch": 0.71, + "learning_rate": 4.677133685590219e-06, + "loss": 1.3725, + "step": 6778 + }, + { + "epoch": 0.71, + "learning_rate": 4.674035405538409e-06, + "loss": 1.3093, + "step": 6779 + }, + { + "epoch": 0.71, + "learning_rate": 4.6709378390290085e-06, + "loss": 1.2785, + "step": 6780 + }, + { + "epoch": 0.71, + "learning_rate": 4.667840986477015e-06, + "loss": 1.2513, + "step": 6781 + }, + { + "epoch": 0.71, + "learning_rate": 4.66474484829732e-06, + "loss": 1.2903, + "step": 6782 + }, + { + "epoch": 0.71, + "learning_rate": 4.661649424904732e-06, + "loss": 1.4217, + "step": 6783 + }, + { + "epoch": 0.71, + "learning_rate": 4.658554716713959e-06, + "loss": 1.337, + "step": 6784 + }, + { + "epoch": 0.71, + "learning_rate": 4.655460724139605e-06, + "loss": 1.2978, + "step": 6785 + }, + { + "epoch": 0.71, + "learning_rate": 4.652367447596197e-06, + "loss": 1.3036, + "step": 6786 + }, + { + "epoch": 0.71, + "learning_rate": 4.6492748874981415e-06, + "loss": 1.2889, + "step": 6787 + }, + { + "epoch": 0.71, + "learning_rate": 4.646183044259771e-06, + "loss": 1.3046, + "step": 6788 + }, + { + "epoch": 0.71, + "learning_rate": 4.643091918295312e-06, + "loss": 1.3483, + "step": 6789 + }, + { + "epoch": 0.71, + "learning_rate": 4.640001510018893e-06, + "loss": 1.3862, + "step": 6790 + }, + { + "epoch": 0.71, + "learning_rate": 4.6369118198445505e-06, + "loss": 1.2483, + "step": 6791 + }, + { + "epoch": 0.71, + "learning_rate": 4.633822848186228e-06, + "loss": 1.2669, + "step": 6792 + }, + { + "epoch": 0.71, + "learning_rate": 4.63073459545776e-06, + "loss": 1.3535, + "step": 6793 + }, + { + "epoch": 0.71, + "learning_rate": 4.627647062072902e-06, + "loss": 1.2742, + "step": 6794 + }, + { + "epoch": 0.71, + "learning_rate": 4.624560248445295e-06, + "loss": 1.3429, + "step": 6795 + }, + { + "epoch": 0.71, + "learning_rate": 4.621474154988498e-06, + "loss": 1.3548, + "step": 6796 + }, + { + "epoch": 0.71, + "learning_rate": 4.61838878211597e-06, + "loss": 1.2722, + "step": 6797 + }, + { + "epoch": 0.71, + "learning_rate": 4.6153041302410665e-06, + "loss": 1.3357, + "step": 6798 + }, + { + "epoch": 0.71, + "learning_rate": 4.612220199777053e-06, + "loss": 1.2494, + "step": 6799 + }, + { + "epoch": 0.71, + "learning_rate": 4.609136991137103e-06, + "loss": 1.2792, + "step": 6800 + }, + { + "epoch": 0.71, + "learning_rate": 4.60605450473428e-06, + "loss": 1.2892, + "step": 6801 + }, + { + "epoch": 0.71, + "learning_rate": 4.602972740981562e-06, + "loss": 1.316, + "step": 6802 + }, + { + "epoch": 0.71, + "learning_rate": 4.599891700291822e-06, + "loss": 1.3017, + "step": 6803 + }, + { + "epoch": 0.71, + "learning_rate": 4.5968113830778416e-06, + "loss": 1.3133, + "step": 6804 + }, + { + "epoch": 0.71, + "learning_rate": 4.593731789752311e-06, + "loss": 1.3768, + "step": 6805 + }, + { + "epoch": 0.71, + "learning_rate": 4.590652920727806e-06, + "loss": 1.3259, + "step": 6806 + }, + { + "epoch": 0.71, + "learning_rate": 4.5875747764168214e-06, + "loss": 1.328, + "step": 6807 + }, + { + "epoch": 0.71, + "learning_rate": 4.584497357231752e-06, + "loss": 1.2924, + "step": 6808 + }, + { + "epoch": 0.71, + "learning_rate": 4.581420663584886e-06, + "loss": 1.3347, + "step": 6809 + }, + { + "epoch": 0.71, + "learning_rate": 4.578344695888427e-06, + "loss": 1.3042, + "step": 6810 + }, + { + "epoch": 0.71, + "learning_rate": 4.575269454554477e-06, + "loss": 1.3121, + "step": 6811 + }, + { + "epoch": 0.71, + "learning_rate": 4.572194939995031e-06, + "loss": 1.3471, + "step": 6812 + }, + { + "epoch": 0.71, + "learning_rate": 4.569121152622005e-06, + "loss": 1.4279, + "step": 6813 + }, + { + "epoch": 0.71, + "learning_rate": 4.5660480928471985e-06, + "loss": 1.2902, + "step": 6814 + }, + { + "epoch": 0.71, + "learning_rate": 4.562975761082326e-06, + "loss": 1.0803, + "step": 6815 + }, + { + "epoch": 0.71, + "learning_rate": 4.5599041577390065e-06, + "loss": 1.008, + "step": 6816 + }, + { + "epoch": 0.71, + "learning_rate": 4.556833283228748e-06, + "loss": 1.168, + "step": 6817 + }, + { + "epoch": 0.71, + "learning_rate": 4.553763137962971e-06, + "loss": 1.3092, + "step": 6818 + }, + { + "epoch": 0.72, + "learning_rate": 4.550693722353001e-06, + "loss": 1.364, + "step": 6819 + }, + { + "epoch": 0.72, + "learning_rate": 4.547625036810052e-06, + "loss": 1.3079, + "step": 6820 + }, + { + "epoch": 0.72, + "learning_rate": 4.544557081745259e-06, + "loss": 1.2639, + "step": 6821 + }, + { + "epoch": 0.72, + "learning_rate": 4.541489857569639e-06, + "loss": 1.3586, + "step": 6822 + }, + { + "epoch": 0.72, + "learning_rate": 4.5384233646941275e-06, + "loss": 1.4261, + "step": 6823 + }, + { + "epoch": 0.72, + "learning_rate": 4.535357603529558e-06, + "loss": 1.428, + "step": 6824 + }, + { + "epoch": 0.72, + "learning_rate": 4.532292574486656e-06, + "loss": 1.2541, + "step": 6825 + }, + { + "epoch": 0.72, + "learning_rate": 4.529228277976061e-06, + "loss": 1.2761, + "step": 6826 + }, + { + "epoch": 0.72, + "learning_rate": 4.526164714408314e-06, + "loss": 1.3439, + "step": 6827 + }, + { + "epoch": 0.72, + "learning_rate": 4.523101884193845e-06, + "loss": 1.3585, + "step": 6828 + }, + { + "epoch": 0.72, + "learning_rate": 4.520039787742999e-06, + "loss": 1.4035, + "step": 6829 + }, + { + "epoch": 0.72, + "learning_rate": 4.516978425466023e-06, + "loss": 1.3328, + "step": 6830 + }, + { + "epoch": 0.72, + "learning_rate": 4.5139177977730516e-06, + "loss": 1.2931, + "step": 6831 + }, + { + "epoch": 0.72, + "learning_rate": 4.5108579050741395e-06, + "loss": 1.2515, + "step": 6832 + }, + { + "epoch": 0.72, + "learning_rate": 4.507798747779226e-06, + "loss": 1.3178, + "step": 6833 + }, + { + "epoch": 0.72, + "learning_rate": 4.504740326298163e-06, + "loss": 1.3037, + "step": 6834 + }, + { + "epoch": 0.72, + "learning_rate": 4.501682641040702e-06, + "loss": 1.14, + "step": 6835 + }, + { + "epoch": 0.72, + "learning_rate": 4.4986256924164895e-06, + "loss": 1.2801, + "step": 6836 + }, + { + "epoch": 0.72, + "learning_rate": 4.495569480835081e-06, + "loss": 1.3195, + "step": 6837 + }, + { + "epoch": 0.72, + "learning_rate": 4.492514006705935e-06, + "loss": 1.2949, + "step": 6838 + }, + { + "epoch": 0.72, + "learning_rate": 4.489459270438397e-06, + "loss": 1.3297, + "step": 6839 + }, + { + "epoch": 0.72, + "learning_rate": 4.4864052724417315e-06, + "loss": 1.2127, + "step": 6840 + }, + { + "epoch": 0.72, + "learning_rate": 4.4833520131250894e-06, + "loss": 1.3124, + "step": 6841 + }, + { + "epoch": 0.72, + "learning_rate": 4.480299492897532e-06, + "loss": 1.3056, + "step": 6842 + }, + { + "epoch": 0.72, + "learning_rate": 4.477247712168021e-06, + "loss": 1.2853, + "step": 6843 + }, + { + "epoch": 0.72, + "learning_rate": 4.474196671345411e-06, + "loss": 1.2531, + "step": 6844 + }, + { + "epoch": 0.72, + "learning_rate": 4.471146370838466e-06, + "loss": 1.2712, + "step": 6845 + }, + { + "epoch": 0.72, + "learning_rate": 4.468096811055852e-06, + "loss": 1.3443, + "step": 6846 + }, + { + "epoch": 0.72, + "learning_rate": 4.465047992406124e-06, + "loss": 1.2692, + "step": 6847 + }, + { + "epoch": 0.72, + "learning_rate": 4.461999915297752e-06, + "loss": 1.3937, + "step": 6848 + }, + { + "epoch": 0.72, + "learning_rate": 4.458952580139094e-06, + "loss": 1.2743, + "step": 6849 + }, + { + "epoch": 0.72, + "learning_rate": 4.455905987338418e-06, + "loss": 1.3949, + "step": 6850 + }, + { + "epoch": 0.72, + "learning_rate": 4.452860137303892e-06, + "loss": 1.2578, + "step": 6851 + }, + { + "epoch": 0.72, + "learning_rate": 4.449815030443575e-06, + "loss": 1.3199, + "step": 6852 + }, + { + "epoch": 0.72, + "learning_rate": 4.4467706671654365e-06, + "loss": 1.3199, + "step": 6853 + }, + { + "epoch": 0.72, + "learning_rate": 4.4437270478773464e-06, + "loss": 1.3098, + "step": 6854 + }, + { + "epoch": 0.72, + "learning_rate": 4.440684172987064e-06, + "loss": 1.2888, + "step": 6855 + }, + { + "epoch": 0.72, + "learning_rate": 4.4376420429022615e-06, + "loss": 1.646, + "step": 6856 + }, + { + "epoch": 0.72, + "learning_rate": 4.434600658030508e-06, + "loss": 1.3573, + "step": 6857 + }, + { + "epoch": 0.72, + "learning_rate": 4.431560018779264e-06, + "loss": 1.3748, + "step": 6858 + }, + { + "epoch": 0.72, + "learning_rate": 4.428520125555906e-06, + "loss": 1.358, + "step": 6859 + }, + { + "epoch": 0.72, + "learning_rate": 4.425480978767692e-06, + "loss": 1.2707, + "step": 6860 + }, + { + "epoch": 0.72, + "learning_rate": 4.422442578821795e-06, + "loss": 1.4066, + "step": 6861 + }, + { + "epoch": 0.72, + "learning_rate": 4.4194049261252845e-06, + "loss": 1.3725, + "step": 6862 + }, + { + "epoch": 0.72, + "learning_rate": 4.416368021085122e-06, + "loss": 1.2392, + "step": 6863 + }, + { + "epoch": 0.72, + "learning_rate": 4.413331864108178e-06, + "loss": 1.2917, + "step": 6864 + }, + { + "epoch": 0.72, + "learning_rate": 4.410296455601223e-06, + "loss": 1.2685, + "step": 6865 + }, + { + "epoch": 0.72, + "learning_rate": 4.407261795970916e-06, + "loss": 1.265, + "step": 6866 + }, + { + "epoch": 0.72, + "learning_rate": 4.404227885623832e-06, + "loss": 1.3838, + "step": 6867 + }, + { + "epoch": 0.72, + "learning_rate": 4.4011947249664276e-06, + "loss": 1.3496, + "step": 6868 + }, + { + "epoch": 0.72, + "learning_rate": 4.398162314405075e-06, + "loss": 1.3007, + "step": 6869 + }, + { + "epoch": 0.72, + "learning_rate": 4.39513065434604e-06, + "loss": 1.2934, + "step": 6870 + }, + { + "epoch": 0.72, + "learning_rate": 4.392099745195483e-06, + "loss": 1.559, + "step": 6871 + }, + { + "epoch": 0.72, + "learning_rate": 4.389069587359468e-06, + "loss": 1.346, + "step": 6872 + }, + { + "epoch": 0.72, + "learning_rate": 4.386040181243965e-06, + "loss": 1.2433, + "step": 6873 + }, + { + "epoch": 0.72, + "learning_rate": 4.3830115272548275e-06, + "loss": 1.2938, + "step": 6874 + }, + { + "epoch": 0.72, + "learning_rate": 4.379983625797821e-06, + "loss": 1.3463, + "step": 6875 + }, + { + "epoch": 0.72, + "learning_rate": 4.376956477278612e-06, + "loss": 1.2832, + "step": 6876 + }, + { + "epoch": 0.72, + "learning_rate": 4.37393008210275e-06, + "loss": 1.3693, + "step": 6877 + }, + { + "epoch": 0.72, + "learning_rate": 4.370904440675705e-06, + "loss": 1.2652, + "step": 6878 + }, + { + "epoch": 0.72, + "learning_rate": 4.367879553402826e-06, + "loss": 1.3217, + "step": 6879 + }, + { + "epoch": 0.72, + "learning_rate": 4.364855420689375e-06, + "loss": 1.3519, + "step": 6880 + }, + { + "epoch": 0.72, + "learning_rate": 4.36183204294051e-06, + "loss": 1.3131, + "step": 6881 + }, + { + "epoch": 0.72, + "learning_rate": 4.35880942056128e-06, + "loss": 1.4334, + "step": 6882 + }, + { + "epoch": 0.72, + "learning_rate": 4.3557875539566415e-06, + "loss": 1.259, + "step": 6883 + }, + { + "epoch": 0.72, + "learning_rate": 4.352766443531451e-06, + "loss": 1.2841, + "step": 6884 + }, + { + "epoch": 0.72, + "learning_rate": 4.349746089690453e-06, + "loss": 1.35, + "step": 6885 + }, + { + "epoch": 0.72, + "learning_rate": 4.346726492838304e-06, + "loss": 1.3623, + "step": 6886 + }, + { + "epoch": 0.72, + "learning_rate": 4.343707653379544e-06, + "loss": 1.3729, + "step": 6887 + }, + { + "epoch": 0.72, + "learning_rate": 4.340689571718626e-06, + "loss": 1.2992, + "step": 6888 + }, + { + "epoch": 0.72, + "learning_rate": 4.337672248259898e-06, + "loss": 1.3484, + "step": 6889 + }, + { + "epoch": 0.72, + "learning_rate": 4.334655683407594e-06, + "loss": 1.3347, + "step": 6890 + }, + { + "epoch": 0.72, + "learning_rate": 4.331639877565865e-06, + "loss": 1.2986, + "step": 6891 + }, + { + "epoch": 0.72, + "learning_rate": 4.328624831138751e-06, + "loss": 1.3217, + "step": 6892 + }, + { + "epoch": 0.72, + "learning_rate": 4.325610544530184e-06, + "loss": 1.2834, + "step": 6893 + }, + { + "epoch": 0.72, + "learning_rate": 4.32259701814401e-06, + "loss": 1.3474, + "step": 6894 + }, + { + "epoch": 0.72, + "learning_rate": 4.319584252383956e-06, + "loss": 1.2871, + "step": 6895 + }, + { + "epoch": 0.72, + "learning_rate": 4.316572247653659e-06, + "loss": 1.3534, + "step": 6896 + }, + { + "epoch": 0.72, + "learning_rate": 4.313561004356653e-06, + "loss": 1.4421, + "step": 6897 + }, + { + "epoch": 0.72, + "learning_rate": 4.310550522896359e-06, + "loss": 1.3091, + "step": 6898 + }, + { + "epoch": 0.72, + "learning_rate": 4.30754080367611e-06, + "loss": 1.2565, + "step": 6899 + }, + { + "epoch": 0.72, + "learning_rate": 4.304531847099135e-06, + "loss": 1.5767, + "step": 6900 + }, + { + "epoch": 0.72, + "learning_rate": 4.3015236535685475e-06, + "loss": 1.4257, + "step": 6901 + }, + { + "epoch": 0.72, + "learning_rate": 4.298516223487373e-06, + "loss": 1.362, + "step": 6902 + }, + { + "epoch": 0.72, + "learning_rate": 4.2955095572585336e-06, + "loss": 1.3475, + "step": 6903 + }, + { + "epoch": 0.72, + "learning_rate": 4.292503655284838e-06, + "loss": 1.3223, + "step": 6904 + }, + { + "epoch": 0.72, + "learning_rate": 4.289498517969006e-06, + "loss": 1.3142, + "step": 6905 + }, + { + "epoch": 0.72, + "learning_rate": 4.286494145713644e-06, + "loss": 1.3124, + "step": 6906 + }, + { + "epoch": 0.72, + "learning_rate": 4.283490538921261e-06, + "loss": 1.3636, + "step": 6907 + }, + { + "epoch": 0.72, + "learning_rate": 4.280487697994269e-06, + "loss": 1.347, + "step": 6908 + }, + { + "epoch": 0.72, + "learning_rate": 4.277485623334964e-06, + "loss": 1.2986, + "step": 6909 + }, + { + "epoch": 0.72, + "learning_rate": 4.27448431534555e-06, + "loss": 1.3058, + "step": 6910 + }, + { + "epoch": 0.72, + "learning_rate": 4.271483774428128e-06, + "loss": 1.7858, + "step": 6911 + }, + { + "epoch": 0.72, + "learning_rate": 4.268484000984689e-06, + "loss": 1.3529, + "step": 6912 + }, + { + "epoch": 0.72, + "learning_rate": 4.26548499541713e-06, + "loss": 1.3215, + "step": 6913 + }, + { + "epoch": 0.73, + "learning_rate": 4.262486758127234e-06, + "loss": 1.2914, + "step": 6914 + }, + { + "epoch": 0.73, + "learning_rate": 4.259489289516693e-06, + "loss": 1.4562, + "step": 6915 + }, + { + "epoch": 0.73, + "learning_rate": 4.256492589987092e-06, + "loss": 1.2548, + "step": 6916 + }, + { + "epoch": 0.73, + "learning_rate": 4.253496659939907e-06, + "loss": 1.3047, + "step": 6917 + }, + { + "epoch": 0.73, + "learning_rate": 4.250501499776516e-06, + "loss": 1.4184, + "step": 6918 + }, + { + "epoch": 0.73, + "learning_rate": 4.2475071098982e-06, + "loss": 1.3519, + "step": 6919 + }, + { + "epoch": 0.73, + "learning_rate": 4.2445134907061224e-06, + "loss": 1.3274, + "step": 6920 + }, + { + "epoch": 0.73, + "learning_rate": 4.2415206426013545e-06, + "loss": 1.389, + "step": 6921 + }, + { + "epoch": 0.73, + "learning_rate": 4.238528565984865e-06, + "loss": 1.2929, + "step": 6922 + }, + { + "epoch": 0.73, + "learning_rate": 4.235537261257507e-06, + "loss": 1.3883, + "step": 6923 + }, + { + "epoch": 0.73, + "learning_rate": 4.232546728820047e-06, + "loss": 1.3395, + "step": 6924 + }, + { + "epoch": 0.73, + "learning_rate": 4.229556969073133e-06, + "loss": 1.3534, + "step": 6925 + }, + { + "epoch": 0.73, + "learning_rate": 4.226567982417317e-06, + "loss": 1.4218, + "step": 6926 + }, + { + "epoch": 0.73, + "learning_rate": 4.223579769253052e-06, + "loss": 1.3737, + "step": 6927 + }, + { + "epoch": 0.73, + "learning_rate": 4.220592329980674e-06, + "loss": 1.4805, + "step": 6928 + }, + { + "epoch": 0.73, + "learning_rate": 4.217605665000426e-06, + "loss": 1.2409, + "step": 6929 + }, + { + "epoch": 0.73, + "learning_rate": 4.21461977471245e-06, + "loss": 1.3375, + "step": 6930 + }, + { + "epoch": 0.73, + "learning_rate": 4.211634659516769e-06, + "loss": 1.3535, + "step": 6931 + }, + { + "epoch": 0.73, + "learning_rate": 4.20865031981332e-06, + "loss": 1.2723, + "step": 6932 + }, + { + "epoch": 0.73, + "learning_rate": 4.2056667560019206e-06, + "loss": 1.342, + "step": 6933 + }, + { + "epoch": 0.73, + "learning_rate": 4.202683968482296e-06, + "loss": 1.4075, + "step": 6934 + }, + { + "epoch": 0.73, + "learning_rate": 4.199701957654065e-06, + "loss": 1.3003, + "step": 6935 + }, + { + "epoch": 0.73, + "learning_rate": 4.196720723916735e-06, + "loss": 1.3098, + "step": 6936 + }, + { + "epoch": 0.73, + "learning_rate": 4.193740267669718e-06, + "loss": 1.2386, + "step": 6937 + }, + { + "epoch": 0.73, + "learning_rate": 4.19076058931232e-06, + "loss": 1.3271, + "step": 6938 + }, + { + "epoch": 0.73, + "learning_rate": 4.187781689243737e-06, + "loss": 1.4604, + "step": 6939 + }, + { + "epoch": 0.73, + "learning_rate": 4.184803567863072e-06, + "loss": 1.3496, + "step": 6940 + }, + { + "epoch": 0.73, + "learning_rate": 4.181826225569308e-06, + "loss": 1.3056, + "step": 6941 + }, + { + "epoch": 0.73, + "learning_rate": 4.1788496627613366e-06, + "loss": 1.2886, + "step": 6942 + }, + { + "epoch": 0.73, + "learning_rate": 4.175873879837944e-06, + "loss": 1.282, + "step": 6943 + }, + { + "epoch": 0.73, + "learning_rate": 4.172898877197802e-06, + "loss": 1.2984, + "step": 6944 + }, + { + "epoch": 0.73, + "learning_rate": 4.169924655239488e-06, + "loss": 1.2909, + "step": 6945 + }, + { + "epoch": 0.73, + "learning_rate": 4.166951214361474e-06, + "loss": 1.4015, + "step": 6946 + }, + { + "epoch": 0.73, + "learning_rate": 4.16397855496212e-06, + "loss": 1.3772, + "step": 6947 + }, + { + "epoch": 0.73, + "learning_rate": 4.161006677439687e-06, + "loss": 1.3089, + "step": 6948 + }, + { + "epoch": 0.73, + "learning_rate": 4.1580355821923344e-06, + "loss": 1.3599, + "step": 6949 + }, + { + "epoch": 0.73, + "learning_rate": 4.155065269618107e-06, + "loss": 1.2886, + "step": 6950 + }, + { + "epoch": 0.73, + "learning_rate": 4.152095740114955e-06, + "loss": 1.3071, + "step": 6951 + }, + { + "epoch": 0.73, + "learning_rate": 4.149126994080715e-06, + "loss": 1.3332, + "step": 6952 + }, + { + "epoch": 0.73, + "learning_rate": 4.146159031913123e-06, + "loss": 1.3835, + "step": 6953 + }, + { + "epoch": 0.73, + "learning_rate": 4.1431918540098144e-06, + "loss": 1.3399, + "step": 6954 + }, + { + "epoch": 0.73, + "learning_rate": 4.140225460768309e-06, + "loss": 1.2906, + "step": 6955 + }, + { + "epoch": 0.73, + "learning_rate": 4.137259852586029e-06, + "loss": 1.295, + "step": 6956 + }, + { + "epoch": 0.73, + "learning_rate": 4.134295029860295e-06, + "loss": 1.3371, + "step": 6957 + }, + { + "epoch": 0.73, + "learning_rate": 4.131330992988308e-06, + "loss": 1.4441, + "step": 6958 + }, + { + "epoch": 0.73, + "learning_rate": 4.1283677423671805e-06, + "loss": 1.3257, + "step": 6959 + }, + { + "epoch": 0.73, + "learning_rate": 4.125405278393907e-06, + "loss": 1.3958, + "step": 6960 + }, + { + "epoch": 0.73, + "learning_rate": 4.1224436014653826e-06, + "loss": 1.2856, + "step": 6961 + }, + { + "epoch": 0.73, + "learning_rate": 4.1194827119784e-06, + "loss": 1.2943, + "step": 6962 + }, + { + "epoch": 0.73, + "learning_rate": 4.116522610329636e-06, + "loss": 1.2691, + "step": 6963 + }, + { + "epoch": 0.73, + "learning_rate": 4.11356329691567e-06, + "loss": 1.293, + "step": 6964 + }, + { + "epoch": 0.73, + "learning_rate": 4.11060477213298e-06, + "loss": 1.3136, + "step": 6965 + }, + { + "epoch": 0.73, + "eval_loss": 1.399178147315979, + "eval_runtime": 77.5864, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 6965 + }, + { + "epoch": 0.73, + "learning_rate": 4.1076470363779235e-06, + "loss": 1.2833, + "step": 6966 + }, + { + "epoch": 0.73, + "learning_rate": 4.104690090046765e-06, + "loss": 1.3177, + "step": 6967 + }, + { + "epoch": 0.73, + "learning_rate": 4.101733933535663e-06, + "loss": 1.2623, + "step": 6968 + }, + { + "epoch": 0.73, + "learning_rate": 4.0987785672406585e-06, + "loss": 1.2814, + "step": 6969 + }, + { + "epoch": 0.73, + "learning_rate": 4.0958239915577036e-06, + "loss": 1.3823, + "step": 6970 + }, + { + "epoch": 0.73, + "learning_rate": 4.092870206882627e-06, + "loss": 1.2926, + "step": 6971 + }, + { + "epoch": 0.73, + "learning_rate": 4.089917213611164e-06, + "loss": 1.3324, + "step": 6972 + }, + { + "epoch": 0.73, + "learning_rate": 4.086965012138943e-06, + "loss": 1.3521, + "step": 6973 + }, + { + "epoch": 0.73, + "learning_rate": 4.084013602861476e-06, + "loss": 1.4828, + "step": 6974 + }, + { + "epoch": 0.73, + "learning_rate": 4.0810629861741804e-06, + "loss": 1.3187, + "step": 6975 + }, + { + "epoch": 0.73, + "learning_rate": 4.078113162472366e-06, + "loss": 1.3478, + "step": 6976 + }, + { + "epoch": 0.73, + "learning_rate": 4.075164132151227e-06, + "loss": 1.4256, + "step": 6977 + }, + { + "epoch": 0.73, + "learning_rate": 4.0722158956058635e-06, + "loss": 1.2815, + "step": 6978 + }, + { + "epoch": 0.73, + "learning_rate": 4.069268453231257e-06, + "loss": 1.3031, + "step": 6979 + }, + { + "epoch": 0.73, + "learning_rate": 4.066321805422292e-06, + "loss": 1.2983, + "step": 6980 + }, + { + "epoch": 0.73, + "learning_rate": 4.063375952573748e-06, + "loss": 1.3595, + "step": 6981 + }, + { + "epoch": 0.73, + "learning_rate": 4.060430895080286e-06, + "loss": 1.3119, + "step": 6982 + }, + { + "epoch": 0.73, + "learning_rate": 4.057486633336472e-06, + "loss": 1.328, + "step": 6983 + }, + { + "epoch": 0.73, + "learning_rate": 4.054543167736766e-06, + "loss": 1.232, + "step": 6984 + }, + { + "epoch": 0.73, + "learning_rate": 4.0516004986755064e-06, + "loss": 1.3288, + "step": 6985 + }, + { + "epoch": 0.73, + "learning_rate": 4.048658626546945e-06, + "loss": 1.2916, + "step": 6986 + }, + { + "epoch": 0.73, + "learning_rate": 4.045717551745209e-06, + "loss": 1.2411, + "step": 6987 + }, + { + "epoch": 0.73, + "learning_rate": 4.042777274664331e-06, + "loss": 1.3256, + "step": 6988 + }, + { + "epoch": 0.73, + "learning_rate": 4.039837795698237e-06, + "loss": 1.3455, + "step": 6989 + }, + { + "epoch": 0.73, + "learning_rate": 4.036899115240732e-06, + "loss": 1.3303, + "step": 6990 + }, + { + "epoch": 0.73, + "learning_rate": 4.033961233685529e-06, + "loss": 1.2805, + "step": 6991 + }, + { + "epoch": 0.73, + "learning_rate": 4.031024151426233e-06, + "loss": 1.3958, + "step": 6992 + }, + { + "epoch": 0.73, + "learning_rate": 4.0280878688563275e-06, + "loss": 1.2853, + "step": 6993 + }, + { + "epoch": 0.73, + "learning_rate": 4.0251523863692054e-06, + "loss": 1.2433, + "step": 6994 + }, + { + "epoch": 0.73, + "learning_rate": 4.022217704358148e-06, + "loss": 1.2644, + "step": 6995 + }, + { + "epoch": 0.73, + "learning_rate": 4.0192838232163204e-06, + "loss": 1.3218, + "step": 6996 + }, + { + "epoch": 0.73, + "learning_rate": 4.016350743336795e-06, + "loss": 1.2973, + "step": 6997 + }, + { + "epoch": 0.73, + "learning_rate": 4.013418465112521e-06, + "loss": 1.3209, + "step": 6998 + }, + { + "epoch": 0.73, + "learning_rate": 4.010486988936353e-06, + "loss": 1.2855, + "step": 6999 + }, + { + "epoch": 0.73, + "learning_rate": 4.007556315201035e-06, + "loss": 1.2381, + "step": 7000 + }, + { + "epoch": 0.73, + "learning_rate": 4.004626444299198e-06, + "loss": 1.3558, + "step": 7001 + }, + { + "epoch": 0.73, + "learning_rate": 4.001697376623371e-06, + "loss": 1.3139, + "step": 7002 + }, + { + "epoch": 0.73, + "learning_rate": 3.998769112565978e-06, + "loss": 1.3582, + "step": 7003 + }, + { + "epoch": 0.73, + "learning_rate": 3.9958416525193225e-06, + "loss": 1.2684, + "step": 7004 + }, + { + "epoch": 0.73, + "learning_rate": 3.992914996875618e-06, + "loss": 1.2915, + "step": 7005 + }, + { + "epoch": 0.73, + "learning_rate": 3.9899891460269536e-06, + "loss": 1.3205, + "step": 7006 + }, + { + "epoch": 0.73, + "learning_rate": 3.987064100365321e-06, + "loss": 1.2966, + "step": 7007 + }, + { + "epoch": 0.73, + "learning_rate": 3.984139860282606e-06, + "loss": 1.2691, + "step": 7008 + }, + { + "epoch": 0.74, + "learning_rate": 3.981216426170572e-06, + "loss": 1.3421, + "step": 7009 + }, + { + "epoch": 0.74, + "learning_rate": 3.97829379842089e-06, + "loss": 1.3034, + "step": 7010 + }, + { + "epoch": 0.74, + "learning_rate": 3.9753719774251195e-06, + "loss": 1.2863, + "step": 7011 + }, + { + "epoch": 0.74, + "learning_rate": 3.972450963574703e-06, + "loss": 1.3812, + "step": 7012 + }, + { + "epoch": 0.74, + "learning_rate": 3.969530757260986e-06, + "loss": 1.334, + "step": 7013 + }, + { + "epoch": 0.74, + "learning_rate": 3.966611358875201e-06, + "loss": 1.3289, + "step": 7014 + }, + { + "epoch": 0.74, + "learning_rate": 3.963692768808468e-06, + "loss": 1.395, + "step": 7015 + }, + { + "epoch": 0.74, + "learning_rate": 3.960774987451811e-06, + "loss": 1.3298, + "step": 7016 + }, + { + "epoch": 0.74, + "learning_rate": 3.957858015196128e-06, + "loss": 1.3304, + "step": 7017 + }, + { + "epoch": 0.74, + "learning_rate": 3.954941852432224e-06, + "loss": 1.301, + "step": 7018 + }, + { + "epoch": 0.74, + "learning_rate": 3.952026499550791e-06, + "loss": 1.3568, + "step": 7019 + }, + { + "epoch": 0.74, + "learning_rate": 3.949111956942406e-06, + "loss": 1.4464, + "step": 7020 + }, + { + "epoch": 0.74, + "learning_rate": 3.946198224997548e-06, + "loss": 1.4417, + "step": 7021 + }, + { + "epoch": 0.74, + "learning_rate": 3.943285304106583e-06, + "loss": 1.3979, + "step": 7022 + }, + { + "epoch": 0.74, + "learning_rate": 3.940373194659761e-06, + "loss": 1.2943, + "step": 7023 + }, + { + "epoch": 0.74, + "learning_rate": 3.937461897047239e-06, + "loss": 1.2571, + "step": 7024 + }, + { + "epoch": 0.74, + "learning_rate": 3.9345514116590454e-06, + "loss": 1.3433, + "step": 7025 + }, + { + "epoch": 0.74, + "learning_rate": 3.931641738885117e-06, + "loss": 1.4203, + "step": 7026 + }, + { + "epoch": 0.74, + "learning_rate": 3.9287328791152775e-06, + "loss": 1.3657, + "step": 7027 + }, + { + "epoch": 0.74, + "learning_rate": 3.925824832739234e-06, + "loss": 1.3954, + "step": 7028 + }, + { + "epoch": 0.74, + "learning_rate": 3.92291760014659e-06, + "loss": 1.2847, + "step": 7029 + }, + { + "epoch": 0.74, + "learning_rate": 3.920011181726846e-06, + "loss": 1.2776, + "step": 7030 + }, + { + "epoch": 0.74, + "learning_rate": 3.91710557786938e-06, + "loss": 1.3391, + "step": 7031 + }, + { + "epoch": 0.74, + "learning_rate": 3.914200788963472e-06, + "loss": 1.2935, + "step": 7032 + }, + { + "epoch": 0.74, + "learning_rate": 3.911296815398291e-06, + "loss": 1.3775, + "step": 7033 + }, + { + "epoch": 0.74, + "learning_rate": 3.90839365756289e-06, + "loss": 1.3652, + "step": 7034 + }, + { + "epoch": 0.74, + "learning_rate": 3.905491315846224e-06, + "loss": 1.2902, + "step": 7035 + }, + { + "epoch": 0.74, + "learning_rate": 3.902589790637125e-06, + "loss": 1.2859, + "step": 7036 + }, + { + "epoch": 0.74, + "learning_rate": 3.899689082324325e-06, + "loss": 1.4019, + "step": 7037 + }, + { + "epoch": 0.74, + "learning_rate": 3.89678919129645e-06, + "loss": 1.299, + "step": 7038 + }, + { + "epoch": 0.74, + "learning_rate": 3.893890117942003e-06, + "loss": 1.275, + "step": 7039 + }, + { + "epoch": 0.74, + "learning_rate": 3.890991862649388e-06, + "loss": 1.2593, + "step": 7040 + }, + { + "epoch": 0.74, + "learning_rate": 3.888094425806902e-06, + "loss": 1.2932, + "step": 7041 + }, + { + "epoch": 0.74, + "learning_rate": 3.885197807802719e-06, + "loss": 1.3038, + "step": 7042 + }, + { + "epoch": 0.74, + "learning_rate": 3.882302009024917e-06, + "loss": 1.285, + "step": 7043 + }, + { + "epoch": 0.74, + "learning_rate": 3.879407029861455e-06, + "loss": 1.4116, + "step": 7044 + }, + { + "epoch": 0.74, + "learning_rate": 3.876512870700187e-06, + "loss": 1.3823, + "step": 7045 + }, + { + "epoch": 0.74, + "learning_rate": 3.873619531928858e-06, + "loss": 1.2803, + "step": 7046 + }, + { + "epoch": 0.74, + "learning_rate": 3.870727013935099e-06, + "loss": 1.3287, + "step": 7047 + }, + { + "epoch": 0.74, + "learning_rate": 3.867835317106432e-06, + "loss": 1.3919, + "step": 7048 + }, + { + "epoch": 0.74, + "learning_rate": 3.864944441830275e-06, + "loss": 1.3967, + "step": 7049 + }, + { + "epoch": 0.74, + "learning_rate": 3.862054388493924e-06, + "loss": 1.2749, + "step": 7050 + }, + { + "epoch": 0.74, + "learning_rate": 3.85916515748458e-06, + "loss": 1.3408, + "step": 7051 + }, + { + "epoch": 0.74, + "learning_rate": 3.856276749189317e-06, + "loss": 1.3143, + "step": 7052 + }, + { + "epoch": 0.74, + "learning_rate": 3.853389163995111e-06, + "loss": 1.3661, + "step": 7053 + }, + { + "epoch": 0.74, + "learning_rate": 3.8505024022888305e-06, + "loss": 1.3094, + "step": 7054 + }, + { + "epoch": 0.74, + "learning_rate": 3.847616464457216e-06, + "loss": 1.2736, + "step": 7055 + }, + { + "epoch": 0.74, + "learning_rate": 3.844731350886917e-06, + "loss": 1.3628, + "step": 7056 + }, + { + "epoch": 0.74, + "learning_rate": 3.841847061964465e-06, + "loss": 1.2706, + "step": 7057 + }, + { + "epoch": 0.74, + "learning_rate": 3.838963598076275e-06, + "loss": 1.2566, + "step": 7058 + }, + { + "epoch": 0.74, + "learning_rate": 3.83608095960866e-06, + "loss": 1.2415, + "step": 7059 + }, + { + "epoch": 0.74, + "learning_rate": 3.833199146947823e-06, + "loss": 1.2748, + "step": 7060 + }, + { + "epoch": 0.74, + "learning_rate": 3.830318160479847e-06, + "loss": 1.4672, + "step": 7061 + }, + { + "epoch": 0.74, + "learning_rate": 3.827438000590714e-06, + "loss": 1.2907, + "step": 7062 + }, + { + "epoch": 0.74, + "learning_rate": 3.824558667666288e-06, + "loss": 1.3477, + "step": 7063 + }, + { + "epoch": 0.74, + "learning_rate": 3.821680162092328e-06, + "loss": 1.1135, + "step": 7064 + }, + { + "epoch": 0.74, + "learning_rate": 3.8188024842544825e-06, + "loss": 1.3724, + "step": 7065 + }, + { + "epoch": 0.74, + "learning_rate": 3.81592563453828e-06, + "loss": 1.3854, + "step": 7066 + }, + { + "epoch": 0.74, + "learning_rate": 3.8130496133291473e-06, + "loss": 1.3074, + "step": 7067 + }, + { + "epoch": 0.74, + "learning_rate": 3.8101744210124012e-06, + "loss": 1.4434, + "step": 7068 + }, + { + "epoch": 0.74, + "learning_rate": 3.807300057973238e-06, + "loss": 1.2754, + "step": 7069 + }, + { + "epoch": 0.74, + "learning_rate": 3.804426524596754e-06, + "loss": 1.3654, + "step": 7070 + }, + { + "epoch": 0.74, + "learning_rate": 3.8015538212679214e-06, + "loss": 1.2616, + "step": 7071 + }, + { + "epoch": 0.74, + "learning_rate": 3.798681948371613e-06, + "loss": 1.2939, + "step": 7072 + }, + { + "epoch": 0.74, + "learning_rate": 3.7958109062925894e-06, + "loss": 1.2787, + "step": 7073 + }, + { + "epoch": 0.74, + "learning_rate": 3.792940695415489e-06, + "loss": 1.2953, + "step": 7074 + }, + { + "epoch": 0.74, + "learning_rate": 3.7900713161248515e-06, + "loss": 1.2714, + "step": 7075 + }, + { + "epoch": 0.74, + "learning_rate": 3.7872027688051004e-06, + "loss": 1.3085, + "step": 7076 + }, + { + "epoch": 0.74, + "learning_rate": 3.7843350538405433e-06, + "loss": 1.311, + "step": 7077 + }, + { + "epoch": 0.74, + "learning_rate": 3.781468171615382e-06, + "loss": 1.3367, + "step": 7078 + }, + { + "epoch": 0.74, + "learning_rate": 3.7786021225137102e-06, + "loss": 1.2768, + "step": 7079 + }, + { + "epoch": 0.74, + "learning_rate": 3.775736906919496e-06, + "loss": 1.2828, + "step": 7080 + }, + { + "epoch": 0.74, + "learning_rate": 3.772872525216613e-06, + "loss": 1.3682, + "step": 7081 + }, + { + "epoch": 0.74, + "learning_rate": 3.7700089777888072e-06, + "loss": 1.3906, + "step": 7082 + }, + { + "epoch": 0.74, + "learning_rate": 3.767146265019723e-06, + "loss": 1.2712, + "step": 7083 + }, + { + "epoch": 0.74, + "learning_rate": 3.764284387292896e-06, + "loss": 1.3405, + "step": 7084 + }, + { + "epoch": 0.74, + "learning_rate": 3.761423344991736e-06, + "loss": 1.3941, + "step": 7085 + }, + { + "epoch": 0.74, + "learning_rate": 3.7585631384995523e-06, + "loss": 1.3463, + "step": 7086 + }, + { + "epoch": 0.74, + "learning_rate": 3.7557037681995423e-06, + "loss": 1.2771, + "step": 7087 + }, + { + "epoch": 0.74, + "learning_rate": 3.7528452344747834e-06, + "loss": 1.2706, + "step": 7088 + }, + { + "epoch": 0.74, + "learning_rate": 3.7499875377082497e-06, + "loss": 1.2672, + "step": 7089 + }, + { + "epoch": 0.74, + "learning_rate": 3.7471306782827944e-06, + "loss": 1.2638, + "step": 7090 + }, + { + "epoch": 0.74, + "learning_rate": 3.744274656581166e-06, + "loss": 1.3417, + "step": 7091 + }, + { + "epoch": 0.74, + "learning_rate": 3.7414194729860008e-06, + "loss": 1.278, + "step": 7092 + }, + { + "epoch": 0.74, + "learning_rate": 3.738565127879814e-06, + "loss": 1.2753, + "step": 7093 + }, + { + "epoch": 0.74, + "learning_rate": 3.7357116216450183e-06, + "loss": 1.2989, + "step": 7094 + }, + { + "epoch": 0.74, + "learning_rate": 3.7328589546639127e-06, + "loss": 1.263, + "step": 7095 + }, + { + "epoch": 0.74, + "learning_rate": 3.7300071273186745e-06, + "loss": 1.3534, + "step": 7096 + }, + { + "epoch": 0.74, + "learning_rate": 3.7271561399913825e-06, + "loss": 1.2565, + "step": 7097 + }, + { + "epoch": 0.74, + "learning_rate": 3.724305993063989e-06, + "loss": 1.3233, + "step": 7098 + }, + { + "epoch": 0.74, + "learning_rate": 3.7214566869183443e-06, + "loss": 1.3179, + "step": 7099 + }, + { + "epoch": 0.74, + "learning_rate": 3.718608221936184e-06, + "loss": 1.2749, + "step": 7100 + }, + { + "epoch": 0.74, + "learning_rate": 3.715760598499124e-06, + "loss": 1.3106, + "step": 7101 + }, + { + "epoch": 0.74, + "learning_rate": 3.712913816988675e-06, + "loss": 1.3115, + "step": 7102 + }, + { + "epoch": 0.74, + "learning_rate": 3.7100678777862364e-06, + "loss": 1.2798, + "step": 7103 + }, + { + "epoch": 0.74, + "learning_rate": 3.7072227812730853e-06, + "loss": 1.3964, + "step": 7104 + }, + { + "epoch": 0.75, + "learning_rate": 3.7043785278303923e-06, + "loss": 1.4034, + "step": 7105 + }, + { + "epoch": 0.75, + "learning_rate": 3.70153511783922e-06, + "loss": 1.3244, + "step": 7106 + }, + { + "epoch": 0.75, + "learning_rate": 3.698692551680505e-06, + "loss": 1.3283, + "step": 7107 + }, + { + "epoch": 0.75, + "learning_rate": 3.6958508297350847e-06, + "loss": 1.3567, + "step": 7108 + }, + { + "epoch": 0.75, + "learning_rate": 3.6930099523836692e-06, + "loss": 1.3178, + "step": 7109 + }, + { + "epoch": 0.75, + "learning_rate": 3.6901699200068673e-06, + "loss": 1.2697, + "step": 7110 + }, + { + "epoch": 0.75, + "learning_rate": 3.687330732985175e-06, + "loss": 1.2501, + "step": 7111 + }, + { + "epoch": 0.75, + "learning_rate": 3.6844923916989607e-06, + "loss": 1.2772, + "step": 7112 + }, + { + "epoch": 0.75, + "learning_rate": 3.681654896528495e-06, + "loss": 1.2845, + "step": 7113 + }, + { + "epoch": 0.75, + "learning_rate": 3.6788182478539312e-06, + "loss": 1.3151, + "step": 7114 + }, + { + "epoch": 0.75, + "learning_rate": 3.6759824460553016e-06, + "loss": 1.4925, + "step": 7115 + }, + { + "epoch": 0.75, + "learning_rate": 3.673147491512539e-06, + "loss": 1.2892, + "step": 7116 + }, + { + "epoch": 0.75, + "learning_rate": 3.670313384605444e-06, + "loss": 1.2906, + "step": 7117 + }, + { + "epoch": 0.75, + "learning_rate": 3.6674801257137195e-06, + "loss": 1.3927, + "step": 7118 + }, + { + "epoch": 0.75, + "learning_rate": 3.6646477152169522e-06, + "loss": 1.4001, + "step": 7119 + }, + { + "epoch": 0.75, + "learning_rate": 3.6618161534946074e-06, + "loss": 1.3363, + "step": 7120 + }, + { + "epoch": 0.75, + "learning_rate": 3.658985440926044e-06, + "loss": 1.3297, + "step": 7121 + }, + { + "epoch": 0.75, + "learning_rate": 3.656155577890507e-06, + "loss": 1.3029, + "step": 7122 + }, + { + "epoch": 0.75, + "learning_rate": 3.653326564767119e-06, + "loss": 1.3452, + "step": 7123 + }, + { + "epoch": 0.75, + "learning_rate": 3.6504984019348987e-06, + "loss": 1.3246, + "step": 7124 + }, + { + "epoch": 0.75, + "learning_rate": 3.647671089772752e-06, + "loss": 1.3285, + "step": 7125 + }, + { + "epoch": 0.75, + "learning_rate": 3.6448446286594574e-06, + "loss": 1.3127, + "step": 7126 + }, + { + "epoch": 0.75, + "learning_rate": 3.6420190189736946e-06, + "loss": 1.3224, + "step": 7127 + }, + { + "epoch": 0.75, + "learning_rate": 3.6391942610940178e-06, + "loss": 1.3086, + "step": 7128 + }, + { + "epoch": 0.75, + "learning_rate": 3.6363703553988748e-06, + "loss": 1.3741, + "step": 7129 + }, + { + "epoch": 0.75, + "learning_rate": 3.633547302266599e-06, + "loss": 1.3192, + "step": 7130 + }, + { + "epoch": 0.75, + "learning_rate": 3.6307251020754e-06, + "loss": 1.3032, + "step": 7131 + }, + { + "epoch": 0.75, + "learning_rate": 3.6279037552033847e-06, + "loss": 1.2642, + "step": 7132 + }, + { + "epoch": 0.75, + "learning_rate": 3.6250832620285436e-06, + "loss": 1.3948, + "step": 7133 + }, + { + "epoch": 0.75, + "learning_rate": 3.6222636229287445e-06, + "loss": 1.3542, + "step": 7134 + }, + { + "epoch": 0.75, + "learning_rate": 3.6194448382817526e-06, + "loss": 1.3028, + "step": 7135 + }, + { + "epoch": 0.75, + "learning_rate": 3.616626908465205e-06, + "loss": 1.3017, + "step": 7136 + }, + { + "epoch": 0.75, + "learning_rate": 3.613809833856636e-06, + "loss": 1.3072, + "step": 7137 + }, + { + "epoch": 0.75, + "learning_rate": 3.6109936148334666e-06, + "loss": 1.3065, + "step": 7138 + }, + { + "epoch": 0.75, + "learning_rate": 3.608178251772988e-06, + "loss": 1.4268, + "step": 7139 + }, + { + "epoch": 0.75, + "learning_rate": 3.6053637450523914e-06, + "loss": 1.301, + "step": 7140 + }, + { + "epoch": 0.75, + "learning_rate": 3.6025500950487514e-06, + "loss": 1.2873, + "step": 7141 + }, + { + "epoch": 0.75, + "learning_rate": 3.599737302139018e-06, + "loss": 1.2831, + "step": 7142 + }, + { + "epoch": 0.75, + "learning_rate": 3.5969253667000403e-06, + "loss": 1.5125, + "step": 7143 + }, + { + "epoch": 0.75, + "learning_rate": 3.594114289108538e-06, + "loss": 1.3643, + "step": 7144 + }, + { + "epoch": 0.75, + "learning_rate": 3.5913040697411272e-06, + "loss": 1.3157, + "step": 7145 + }, + { + "epoch": 0.75, + "learning_rate": 3.5884947089743084e-06, + "loss": 1.2687, + "step": 7146 + }, + { + "epoch": 0.75, + "learning_rate": 3.585686207184458e-06, + "loss": 1.3227, + "step": 7147 + }, + { + "epoch": 0.75, + "learning_rate": 3.5828785647478435e-06, + "loss": 1.2745, + "step": 7148 + }, + { + "epoch": 0.75, + "learning_rate": 3.5800717820406226e-06, + "loss": 1.332, + "step": 7149 + }, + { + "epoch": 0.75, + "learning_rate": 3.5772658594388253e-06, + "loss": 1.2863, + "step": 7150 + }, + { + "epoch": 0.75, + "learning_rate": 3.5744607973183766e-06, + "loss": 1.3791, + "step": 7151 + }, + { + "epoch": 0.75, + "learning_rate": 3.5716565960550844e-06, + "loss": 1.2781, + "step": 7152 + }, + { + "epoch": 0.75, + "learning_rate": 3.5688532560246348e-06, + "loss": 1.252, + "step": 7153 + }, + { + "epoch": 0.75, + "learning_rate": 3.5660507776026086e-06, + "loss": 1.3158, + "step": 7154 + }, + { + "epoch": 0.75, + "learning_rate": 3.5632491611644603e-06, + "loss": 1.3241, + "step": 7155 + }, + { + "epoch": 0.75, + "learning_rate": 3.5604484070855382e-06, + "loss": 1.2572, + "step": 7156 + }, + { + "epoch": 0.75, + "learning_rate": 3.5576485157410733e-06, + "loss": 1.3734, + "step": 7157 + }, + { + "epoch": 0.75, + "learning_rate": 3.5548494875061724e-06, + "loss": 1.3253, + "step": 7158 + }, + { + "epoch": 0.75, + "learning_rate": 3.5520513227558385e-06, + "loss": 1.2659, + "step": 7159 + }, + { + "epoch": 0.75, + "learning_rate": 3.5492540218649553e-06, + "loss": 1.3149, + "step": 7160 + }, + { + "epoch": 0.75, + "learning_rate": 3.546457585208283e-06, + "loss": 1.3413, + "step": 7161 + }, + { + "epoch": 0.75, + "learning_rate": 3.5436620131604803e-06, + "loss": 1.2846, + "step": 7162 + }, + { + "epoch": 0.75, + "learning_rate": 3.540867306096073e-06, + "loss": 1.3239, + "step": 7163 + }, + { + "epoch": 0.75, + "learning_rate": 3.5380734643894856e-06, + "loss": 1.3137, + "step": 7164 + }, + { + "epoch": 0.75, + "eval_loss": 1.397520899772644, + "eval_runtime": 77.542, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 7164 + }, + { + "epoch": 0.75, + "learning_rate": 3.535280488415024e-06, + "loss": 1.414, + "step": 7165 + }, + { + "epoch": 0.75, + "learning_rate": 3.5324883785468665e-06, + "loss": 1.2708, + "step": 7166 + }, + { + "epoch": 0.75, + "learning_rate": 3.529697135159089e-06, + "loss": 1.2975, + "step": 7167 + }, + { + "epoch": 0.75, + "learning_rate": 3.526906758625651e-06, + "loss": 1.3723, + "step": 7168 + }, + { + "epoch": 0.75, + "learning_rate": 3.5241172493203822e-06, + "loss": 1.4105, + "step": 7169 + }, + { + "epoch": 0.75, + "learning_rate": 3.5213286076170107e-06, + "loss": 1.2592, + "step": 7170 + }, + { + "epoch": 0.75, + "learning_rate": 3.5185408338891437e-06, + "loss": 1.3361, + "step": 7171 + }, + { + "epoch": 0.75, + "learning_rate": 3.515753928510267e-06, + "loss": 1.2591, + "step": 7172 + }, + { + "epoch": 0.75, + "learning_rate": 3.512967891853759e-06, + "loss": 1.2938, + "step": 7173 + }, + { + "epoch": 0.75, + "learning_rate": 3.510182724292872e-06, + "loss": 1.4116, + "step": 7174 + }, + { + "epoch": 0.75, + "learning_rate": 3.5073984262007486e-06, + "loss": 1.3968, + "step": 7175 + }, + { + "epoch": 0.75, + "learning_rate": 3.5046149979504184e-06, + "loss": 1.31, + "step": 7176 + }, + { + "epoch": 0.75, + "learning_rate": 3.5018324399147817e-06, + "loss": 1.2966, + "step": 7177 + }, + { + "epoch": 0.75, + "learning_rate": 3.4990507524666327e-06, + "loss": 1.3431, + "step": 7178 + }, + { + "epoch": 0.75, + "learning_rate": 3.49626993597865e-06, + "loss": 1.3227, + "step": 7179 + }, + { + "epoch": 0.75, + "learning_rate": 3.4934899908233834e-06, + "loss": 1.201, + "step": 7180 + }, + { + "epoch": 0.75, + "learning_rate": 3.490710917373283e-06, + "loss": 1.3003, + "step": 7181 + }, + { + "epoch": 0.75, + "learning_rate": 3.487932716000666e-06, + "loss": 1.2879, + "step": 7182 + }, + { + "epoch": 0.75, + "learning_rate": 3.485155387077742e-06, + "loss": 1.2742, + "step": 7183 + }, + { + "epoch": 0.75, + "learning_rate": 3.4823789309766065e-06, + "loss": 1.2972, + "step": 7184 + }, + { + "epoch": 0.75, + "learning_rate": 3.479603348069226e-06, + "loss": 1.3763, + "step": 7185 + }, + { + "epoch": 0.75, + "learning_rate": 3.4768286387274597e-06, + "loss": 1.4653, + "step": 7186 + }, + { + "epoch": 0.75, + "learning_rate": 3.4740548033230524e-06, + "loss": 1.3534, + "step": 7187 + }, + { + "epoch": 0.75, + "learning_rate": 3.4712818422276207e-06, + "loss": 1.3917, + "step": 7188 + }, + { + "epoch": 0.75, + "learning_rate": 3.4685097558126733e-06, + "loss": 1.306, + "step": 7189 + }, + { + "epoch": 0.75, + "learning_rate": 3.465738544449596e-06, + "loss": 1.4628, + "step": 7190 + }, + { + "epoch": 0.75, + "learning_rate": 3.4629682085096606e-06, + "loss": 1.3916, + "step": 7191 + }, + { + "epoch": 0.75, + "learning_rate": 3.4601987483640243e-06, + "loss": 1.3348, + "step": 7192 + }, + { + "epoch": 0.75, + "learning_rate": 3.457430164383718e-06, + "loss": 1.4771, + "step": 7193 + }, + { + "epoch": 0.75, + "learning_rate": 3.4546624569396635e-06, + "loss": 1.5004, + "step": 7194 + }, + { + "epoch": 0.75, + "learning_rate": 3.451895626402667e-06, + "loss": 1.279, + "step": 7195 + }, + { + "epoch": 0.75, + "learning_rate": 3.4491296731434053e-06, + "loss": 1.3263, + "step": 7196 + }, + { + "epoch": 0.75, + "learning_rate": 3.4463645975324466e-06, + "loss": 1.2449, + "step": 7197 + }, + { + "epoch": 0.75, + "learning_rate": 3.4436003999402466e-06, + "loss": 1.2743, + "step": 7198 + }, + { + "epoch": 0.75, + "learning_rate": 3.4408370807371283e-06, + "loss": 1.3127, + "step": 7199 + }, + { + "epoch": 0.76, + "learning_rate": 3.438074640293312e-06, + "loss": 1.2996, + "step": 7200 + }, + { + "epoch": 0.76, + "learning_rate": 3.435313078978887e-06, + "loss": 1.3114, + "step": 7201 + }, + { + "epoch": 0.76, + "learning_rate": 3.432552397163835e-06, + "loss": 1.2574, + "step": 7202 + }, + { + "epoch": 0.76, + "learning_rate": 3.42979259521802e-06, + "loss": 1.2605, + "step": 7203 + }, + { + "epoch": 0.76, + "learning_rate": 3.4270336735111785e-06, + "loss": 1.2578, + "step": 7204 + }, + { + "epoch": 0.76, + "learning_rate": 3.424275632412938e-06, + "loss": 1.3297, + "step": 7205 + }, + { + "epoch": 0.76, + "learning_rate": 3.4215184722928073e-06, + "loss": 1.2353, + "step": 7206 + }, + { + "epoch": 0.76, + "learning_rate": 3.4187621935201707e-06, + "loss": 1.288, + "step": 7207 + }, + { + "epoch": 0.76, + "learning_rate": 3.416006796464304e-06, + "loss": 1.2947, + "step": 7208 + }, + { + "epoch": 0.76, + "learning_rate": 3.4132522814943513e-06, + "loss": 1.4208, + "step": 7209 + }, + { + "epoch": 0.76, + "learning_rate": 3.4104986489793534e-06, + "loss": 1.3273, + "step": 7210 + }, + { + "epoch": 0.76, + "learning_rate": 3.4077458992882285e-06, + "loss": 1.274, + "step": 7211 + }, + { + "epoch": 0.76, + "learning_rate": 3.404994032789766e-06, + "loss": 1.2782, + "step": 7212 + }, + { + "epoch": 0.76, + "learning_rate": 3.4022430498526505e-06, + "loss": 1.3513, + "step": 7213 + }, + { + "epoch": 0.76, + "learning_rate": 3.3994929508454455e-06, + "loss": 1.2843, + "step": 7214 + }, + { + "epoch": 0.76, + "learning_rate": 3.3967437361365873e-06, + "loss": 1.2764, + "step": 7215 + }, + { + "epoch": 0.76, + "learning_rate": 3.3939954060944036e-06, + "loss": 1.2786, + "step": 7216 + }, + { + "epoch": 0.76, + "learning_rate": 3.391247961087103e-06, + "loss": 1.2927, + "step": 7217 + }, + { + "epoch": 0.76, + "learning_rate": 3.3885014014827657e-06, + "loss": 1.3735, + "step": 7218 + }, + { + "epoch": 0.76, + "learning_rate": 3.385755727649367e-06, + "loss": 1.3065, + "step": 7219 + }, + { + "epoch": 0.76, + "learning_rate": 3.3830109399547506e-06, + "loss": 1.2463, + "step": 7220 + }, + { + "epoch": 0.76, + "learning_rate": 3.3802670387666492e-06, + "loss": 1.2496, + "step": 7221 + }, + { + "epoch": 0.76, + "learning_rate": 3.3775240244526796e-06, + "loss": 1.2807, + "step": 7222 + }, + { + "epoch": 0.76, + "learning_rate": 3.3747818973803294e-06, + "loss": 1.313, + "step": 7223 + }, + { + "epoch": 0.76, + "learning_rate": 3.372040657916974e-06, + "loss": 1.3557, + "step": 7224 + }, + { + "epoch": 0.76, + "learning_rate": 3.3693003064298744e-06, + "loss": 1.3705, + "step": 7225 + }, + { + "epoch": 0.76, + "learning_rate": 3.366560843286161e-06, + "loss": 1.3763, + "step": 7226 + }, + { + "epoch": 0.76, + "learning_rate": 3.3638222688528565e-06, + "loss": 1.3252, + "step": 7227 + }, + { + "epoch": 0.76, + "learning_rate": 3.361084583496853e-06, + "loss": 1.2635, + "step": 7228 + }, + { + "epoch": 0.76, + "learning_rate": 3.3583477875849346e-06, + "loss": 1.3084, + "step": 7229 + }, + { + "epoch": 0.76, + "learning_rate": 3.3556118814837646e-06, + "loss": 1.3347, + "step": 7230 + }, + { + "epoch": 0.76, + "learning_rate": 3.3528768655598764e-06, + "loss": 1.3937, + "step": 7231 + }, + { + "epoch": 0.76, + "learning_rate": 3.350142740179696e-06, + "loss": 1.3251, + "step": 7232 + }, + { + "epoch": 0.76, + "learning_rate": 3.347409505709529e-06, + "loss": 1.3654, + "step": 7233 + }, + { + "epoch": 0.76, + "learning_rate": 3.344677162515553e-06, + "loss": 1.3864, + "step": 7234 + }, + { + "epoch": 0.76, + "learning_rate": 3.3419457109638377e-06, + "loss": 1.3142, + "step": 7235 + }, + { + "epoch": 0.76, + "learning_rate": 3.3392151514203195e-06, + "loss": 1.3557, + "step": 7236 + }, + { + "epoch": 0.76, + "learning_rate": 3.3364854842508276e-06, + "loss": 1.3093, + "step": 7237 + }, + { + "epoch": 0.76, + "learning_rate": 3.333756709821072e-06, + "loss": 1.3763, + "step": 7238 + }, + { + "epoch": 0.76, + "learning_rate": 3.3310288284966297e-06, + "loss": 1.2943, + "step": 7239 + }, + { + "epoch": 0.76, + "learning_rate": 3.3283018406429703e-06, + "loss": 1.473, + "step": 7240 + }, + { + "epoch": 0.76, + "learning_rate": 3.3255757466254448e-06, + "loss": 1.2501, + "step": 7241 + }, + { + "epoch": 0.76, + "learning_rate": 3.322850546809271e-06, + "loss": 1.2893, + "step": 7242 + }, + { + "epoch": 0.76, + "learning_rate": 3.3201262415595614e-06, + "loss": 1.2995, + "step": 7243 + }, + { + "epoch": 0.76, + "learning_rate": 3.3174028312413044e-06, + "loss": 1.2985, + "step": 7244 + }, + { + "epoch": 0.76, + "learning_rate": 3.31468031621936e-06, + "loss": 1.2868, + "step": 7245 + }, + { + "epoch": 0.76, + "learning_rate": 3.311958696858484e-06, + "loss": 1.2467, + "step": 7246 + }, + { + "epoch": 0.76, + "learning_rate": 3.309237973523295e-06, + "loss": 1.2303, + "step": 7247 + }, + { + "epoch": 0.76, + "learning_rate": 3.3065181465783045e-06, + "loss": 1.3172, + "step": 7248 + }, + { + "epoch": 0.76, + "learning_rate": 3.303799216387902e-06, + "loss": 1.2003, + "step": 7249 + }, + { + "epoch": 0.76, + "learning_rate": 3.3010811833163482e-06, + "loss": 1.2931, + "step": 7250 + }, + { + "epoch": 0.76, + "learning_rate": 3.2983640477277925e-06, + "loss": 1.3135, + "step": 7251 + }, + { + "epoch": 0.76, + "learning_rate": 3.2956478099862644e-06, + "loss": 1.2711, + "step": 7252 + }, + { + "epoch": 0.76, + "learning_rate": 3.292932470455663e-06, + "loss": 1.291, + "step": 7253 + }, + { + "epoch": 0.76, + "learning_rate": 3.2902180294997832e-06, + "loss": 1.2838, + "step": 7254 + }, + { + "epoch": 0.76, + "learning_rate": 3.2875044874822804e-06, + "loss": 1.2381, + "step": 7255 + }, + { + "epoch": 0.76, + "learning_rate": 3.284791844766705e-06, + "loss": 1.2966, + "step": 7256 + }, + { + "epoch": 0.76, + "learning_rate": 3.282080101716484e-06, + "loss": 1.3418, + "step": 7257 + }, + { + "epoch": 0.76, + "learning_rate": 3.2793692586949143e-06, + "loss": 1.3247, + "step": 7258 + }, + { + "epoch": 0.76, + "learning_rate": 3.2766593160651827e-06, + "loss": 1.3462, + "step": 7259 + }, + { + "epoch": 0.76, + "learning_rate": 3.273950274190356e-06, + "loss": 1.3699, + "step": 7260 + }, + { + "epoch": 0.76, + "learning_rate": 3.2712421334333687e-06, + "loss": 1.2863, + "step": 7261 + }, + { + "epoch": 0.76, + "learning_rate": 3.268534894157046e-06, + "loss": 1.3791, + "step": 7262 + }, + { + "epoch": 0.76, + "learning_rate": 3.265828556724092e-06, + "loss": 1.3066, + "step": 7263 + }, + { + "epoch": 0.76, + "learning_rate": 3.2631231214970784e-06, + "loss": 1.319, + "step": 7264 + }, + { + "epoch": 0.76, + "learning_rate": 3.260418588838471e-06, + "loss": 1.2939, + "step": 7265 + }, + { + "epoch": 0.76, + "learning_rate": 3.2577149591106017e-06, + "loss": 1.2568, + "step": 7266 + }, + { + "epoch": 0.76, + "learning_rate": 3.2550122326756905e-06, + "loss": 1.3494, + "step": 7267 + }, + { + "epoch": 0.76, + "learning_rate": 3.252310409895837e-06, + "loss": 1.3001, + "step": 7268 + }, + { + "epoch": 0.76, + "learning_rate": 3.2496094911330087e-06, + "loss": 1.4039, + "step": 7269 + }, + { + "epoch": 0.76, + "learning_rate": 3.246909476749063e-06, + "loss": 1.2904, + "step": 7270 + }, + { + "epoch": 0.76, + "learning_rate": 3.2442103671057358e-06, + "loss": 1.2864, + "step": 7271 + }, + { + "epoch": 0.76, + "learning_rate": 3.241512162564632e-06, + "loss": 1.3195, + "step": 7272 + }, + { + "epoch": 0.76, + "learning_rate": 3.2388148634872473e-06, + "loss": 1.2776, + "step": 7273 + }, + { + "epoch": 0.76, + "learning_rate": 3.2361184702349446e-06, + "loss": 1.3391, + "step": 7274 + }, + { + "epoch": 0.76, + "learning_rate": 3.2334229831689745e-06, + "loss": 1.6897, + "step": 7275 + }, + { + "epoch": 0.76, + "learning_rate": 3.2307284026504673e-06, + "loss": 1.4191, + "step": 7276 + }, + { + "epoch": 0.76, + "learning_rate": 3.228034729040419e-06, + "loss": 1.2671, + "step": 7277 + }, + { + "epoch": 0.76, + "learning_rate": 3.2253419626997172e-06, + "loss": 1.3085, + "step": 7278 + }, + { + "epoch": 0.76, + "learning_rate": 3.2226501039891266e-06, + "loss": 1.4378, + "step": 7279 + }, + { + "epoch": 0.76, + "learning_rate": 3.2199591532692807e-06, + "loss": 1.3044, + "step": 7280 + }, + { + "epoch": 0.76, + "learning_rate": 3.2172691109007036e-06, + "loss": 1.2709, + "step": 7281 + }, + { + "epoch": 0.76, + "learning_rate": 3.214579977243787e-06, + "loss": 1.2394, + "step": 7282 + }, + { + "epoch": 0.76, + "learning_rate": 3.2118917526588055e-06, + "loss": 1.2945, + "step": 7283 + }, + { + "epoch": 0.76, + "learning_rate": 3.2092044375059197e-06, + "loss": 1.4074, + "step": 7284 + }, + { + "epoch": 0.76, + "learning_rate": 3.2065180321451504e-06, + "loss": 1.3769, + "step": 7285 + }, + { + "epoch": 0.76, + "learning_rate": 3.203832536936413e-06, + "loss": 1.2479, + "step": 7286 + }, + { + "epoch": 0.76, + "learning_rate": 3.2011479522394973e-06, + "loss": 1.2623, + "step": 7287 + }, + { + "epoch": 0.76, + "learning_rate": 3.1984642784140616e-06, + "loss": 1.3044, + "step": 7288 + }, + { + "epoch": 0.76, + "learning_rate": 3.1957815158196525e-06, + "loss": 1.321, + "step": 7289 + }, + { + "epoch": 0.76, + "learning_rate": 3.1930996648156953e-06, + "loss": 1.3307, + "step": 7290 + }, + { + "epoch": 0.76, + "learning_rate": 3.1904187257614814e-06, + "loss": 1.3135, + "step": 7291 + }, + { + "epoch": 0.76, + "learning_rate": 3.187738699016195e-06, + "loss": 1.2821, + "step": 7292 + }, + { + "epoch": 0.76, + "learning_rate": 3.1850595849388853e-06, + "loss": 1.3069, + "step": 7293 + }, + { + "epoch": 0.76, + "learning_rate": 3.1823813838884865e-06, + "loss": 1.2952, + "step": 7294 + }, + { + "epoch": 0.76, + "learning_rate": 3.179704096223812e-06, + "loss": 1.3313, + "step": 7295 + }, + { + "epoch": 0.77, + "learning_rate": 3.177027722303544e-06, + "loss": 1.3454, + "step": 7296 + }, + { + "epoch": 0.77, + "learning_rate": 3.1743522624862497e-06, + "loss": 1.2904, + "step": 7297 + }, + { + "epoch": 0.77, + "learning_rate": 3.1716777171303783e-06, + "loss": 1.3213, + "step": 7298 + }, + { + "epoch": 0.77, + "learning_rate": 3.1690040865942396e-06, + "loss": 1.3336, + "step": 7299 + }, + { + "epoch": 0.77, + "learning_rate": 3.1663313712360398e-06, + "loss": 1.3399, + "step": 7300 + }, + { + "epoch": 0.77, + "learning_rate": 3.1636595714138483e-06, + "loss": 1.2871, + "step": 7301 + }, + { + "epoch": 0.77, + "learning_rate": 3.16098868748562e-06, + "loss": 1.312, + "step": 7302 + }, + { + "epoch": 0.77, + "learning_rate": 3.158318719809188e-06, + "loss": 1.3325, + "step": 7303 + }, + { + "epoch": 0.77, + "learning_rate": 3.1556496687422534e-06, + "loss": 1.309, + "step": 7304 + }, + { + "epoch": 0.77, + "learning_rate": 3.152981534642403e-06, + "loss": 1.3186, + "step": 7305 + }, + { + "epoch": 0.77, + "learning_rate": 3.1503143178671016e-06, + "loss": 1.3235, + "step": 7306 + }, + { + "epoch": 0.77, + "learning_rate": 3.1476480187736812e-06, + "loss": 1.3557, + "step": 7307 + }, + { + "epoch": 0.77, + "learning_rate": 3.1449826377193613e-06, + "loss": 1.3206, + "step": 7308 + }, + { + "epoch": 0.77, + "learning_rate": 3.1423181750612375e-06, + "loss": 1.2901, + "step": 7309 + }, + { + "epoch": 0.77, + "learning_rate": 3.1396546311562713e-06, + "loss": 1.3232, + "step": 7310 + }, + { + "epoch": 0.77, + "learning_rate": 3.136992006361318e-06, + "loss": 1.3065, + "step": 7311 + }, + { + "epoch": 0.77, + "learning_rate": 3.1343303010330926e-06, + "loss": 1.273, + "step": 7312 + }, + { + "epoch": 0.77, + "learning_rate": 3.1316695155281997e-06, + "loss": 1.2773, + "step": 7313 + }, + { + "epoch": 0.77, + "learning_rate": 3.12900965020312e-06, + "loss": 1.2959, + "step": 7314 + }, + { + "epoch": 0.77, + "learning_rate": 3.1263507054141975e-06, + "loss": 1.2685, + "step": 7315 + }, + { + "epoch": 0.77, + "learning_rate": 3.1236926815176683e-06, + "loss": 1.3908, + "step": 7316 + }, + { + "epoch": 0.77, + "learning_rate": 3.121035578869643e-06, + "loss": 1.3022, + "step": 7317 + }, + { + "epoch": 0.77, + "learning_rate": 3.1183793978260966e-06, + "loss": 1.3144, + "step": 7318 + }, + { + "epoch": 0.77, + "learning_rate": 3.1157241387428972e-06, + "loss": 1.3142, + "step": 7319 + }, + { + "epoch": 0.77, + "learning_rate": 3.1130698019757743e-06, + "loss": 1.3277, + "step": 7320 + }, + { + "epoch": 0.77, + "learning_rate": 3.110416387880344e-06, + "loss": 1.2973, + "step": 7321 + }, + { + "epoch": 0.77, + "learning_rate": 3.1077638968120984e-06, + "loss": 1.2862, + "step": 7322 + }, + { + "epoch": 0.77, + "learning_rate": 3.1051123291263975e-06, + "loss": 1.5172, + "step": 7323 + }, + { + "epoch": 0.77, + "learning_rate": 3.102461685178486e-06, + "loss": 1.3757, + "step": 7324 + }, + { + "epoch": 0.77, + "learning_rate": 3.099811965323485e-06, + "loss": 1.3082, + "step": 7325 + }, + { + "epoch": 0.77, + "learning_rate": 3.097163169916383e-06, + "loss": 1.3674, + "step": 7326 + }, + { + "epoch": 0.77, + "learning_rate": 3.0945152993120574e-06, + "loss": 1.3168, + "step": 7327 + }, + { + "epoch": 0.77, + "learning_rate": 3.0918683538652474e-06, + "loss": 1.3122, + "step": 7328 + }, + { + "epoch": 0.77, + "learning_rate": 3.089222333930579e-06, + "loss": 1.3437, + "step": 7329 + }, + { + "epoch": 0.77, + "learning_rate": 3.0865772398625548e-06, + "loss": 1.371, + "step": 7330 + }, + { + "epoch": 0.77, + "learning_rate": 3.0839330720155426e-06, + "loss": 1.327, + "step": 7331 + }, + { + "epoch": 0.77, + "learning_rate": 3.0812898307437955e-06, + "loss": 1.3369, + "step": 7332 + }, + { + "epoch": 0.77, + "learning_rate": 3.078647516401444e-06, + "loss": 1.2148, + "step": 7333 + }, + { + "epoch": 0.77, + "learning_rate": 3.0760061293424846e-06, + "loss": 1.3074, + "step": 7334 + }, + { + "epoch": 0.77, + "learning_rate": 3.073365669920797e-06, + "loss": 1.3218, + "step": 7335 + }, + { + "epoch": 0.77, + "learning_rate": 3.070726138490139e-06, + "loss": 1.2974, + "step": 7336 + }, + { + "epoch": 0.77, + "learning_rate": 3.0680875354041327e-06, + "loss": 1.3037, + "step": 7337 + }, + { + "epoch": 0.77, + "learning_rate": 3.065449861016291e-06, + "loss": 1.5706, + "step": 7338 + }, + { + "epoch": 0.77, + "learning_rate": 3.0628131156799857e-06, + "loss": 1.3346, + "step": 7339 + }, + { + "epoch": 0.77, + "learning_rate": 3.0601772997484793e-06, + "loss": 1.6488, + "step": 7340 + }, + { + "epoch": 0.77, + "learning_rate": 3.0575424135749045e-06, + "loss": 1.2929, + "step": 7341 + }, + { + "epoch": 0.77, + "learning_rate": 3.0549084575122625e-06, + "loss": 1.3137, + "step": 7342 + }, + { + "epoch": 0.77, + "learning_rate": 3.0522754319134373e-06, + "loss": 1.3218, + "step": 7343 + }, + { + "epoch": 0.77, + "learning_rate": 3.0496433371311927e-06, + "loss": 1.2805, + "step": 7344 + }, + { + "epoch": 0.77, + "learning_rate": 3.0470121735181544e-06, + "loss": 1.2218, + "step": 7345 + }, + { + "epoch": 0.77, + "learning_rate": 3.0443819414268373e-06, + "loss": 1.381, + "step": 7346 + }, + { + "epoch": 0.77, + "learning_rate": 3.0417526412096164e-06, + "loss": 1.3571, + "step": 7347 + }, + { + "epoch": 0.77, + "learning_rate": 3.0391242732187565e-06, + "loss": 1.3295, + "step": 7348 + }, + { + "epoch": 0.77, + "learning_rate": 3.036496837806393e-06, + "loss": 1.3795, + "step": 7349 + }, + { + "epoch": 0.77, + "learning_rate": 3.033870335324528e-06, + "loss": 1.282, + "step": 7350 + }, + { + "epoch": 0.77, + "learning_rate": 3.03124476612505e-06, + "loss": 1.3428, + "step": 7351 + }, + { + "epoch": 0.77, + "learning_rate": 3.0286201305597194e-06, + "loss": 1.3321, + "step": 7352 + }, + { + "epoch": 0.77, + "learning_rate": 3.0259964289801646e-06, + "loss": 1.4135, + "step": 7353 + }, + { + "epoch": 0.77, + "learning_rate": 3.023373661737897e-06, + "loss": 1.3032, + "step": 7354 + }, + { + "epoch": 0.77, + "learning_rate": 3.0207518291843042e-06, + "loss": 1.2676, + "step": 7355 + }, + { + "epoch": 0.77, + "learning_rate": 3.0181309316706362e-06, + "loss": 1.2902, + "step": 7356 + }, + { + "epoch": 0.77, + "learning_rate": 3.0155109695480333e-06, + "loss": 1.3364, + "step": 7357 + }, + { + "epoch": 0.77, + "learning_rate": 3.0128919431674975e-06, + "loss": 1.3733, + "step": 7358 + }, + { + "epoch": 0.77, + "learning_rate": 3.0102738528799125e-06, + "loss": 1.3114, + "step": 7359 + }, + { + "epoch": 0.77, + "learning_rate": 3.007656699036039e-06, + "loss": 1.3176, + "step": 7360 + }, + { + "epoch": 0.77, + "learning_rate": 3.005040481986503e-06, + "loss": 1.301, + "step": 7361 + }, + { + "epoch": 0.77, + "learning_rate": 3.0024252020818124e-06, + "loss": 1.3281, + "step": 7362 + }, + { + "epoch": 0.77, + "learning_rate": 2.9998108596723508e-06, + "loss": 1.1587, + "step": 7363 + }, + { + "epoch": 0.77, + "eval_loss": 1.3964349031448364, + "eval_runtime": 77.4566, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 7363 + }, + { + "epoch": 0.77, + "learning_rate": 2.9971974551083673e-06, + "loss": 1.3628, + "step": 7364 + }, + { + "epoch": 0.77, + "learning_rate": 2.9945849887399958e-06, + "loss": 1.4178, + "step": 7365 + }, + { + "epoch": 0.77, + "learning_rate": 2.9919734609172356e-06, + "loss": 1.3428, + "step": 7366 + }, + { + "epoch": 0.77, + "learning_rate": 2.989362871989965e-06, + "loss": 1.2675, + "step": 7367 + }, + { + "epoch": 0.77, + "learning_rate": 2.986753222307941e-06, + "loss": 1.3353, + "step": 7368 + }, + { + "epoch": 0.77, + "learning_rate": 2.9841445122207826e-06, + "loss": 1.2842, + "step": 7369 + }, + { + "epoch": 0.77, + "learning_rate": 2.981536742077993e-06, + "loss": 1.2237, + "step": 7370 + }, + { + "epoch": 0.77, + "learning_rate": 2.9789299122289493e-06, + "loss": 1.2554, + "step": 7371 + }, + { + "epoch": 0.77, + "learning_rate": 2.976324023022893e-06, + "loss": 1.3277, + "step": 7372 + }, + { + "epoch": 0.77, + "learning_rate": 2.973719074808954e-06, + "loss": 1.3258, + "step": 7373 + }, + { + "epoch": 0.77, + "learning_rate": 2.971115067936122e-06, + "loss": 1.2757, + "step": 7374 + }, + { + "epoch": 0.77, + "learning_rate": 2.9685120027532687e-06, + "loss": 1.3267, + "step": 7375 + }, + { + "epoch": 0.77, + "learning_rate": 2.9659098796091423e-06, + "loss": 1.3451, + "step": 7376 + }, + { + "epoch": 0.77, + "learning_rate": 2.9633086988523507e-06, + "loss": 1.2742, + "step": 7377 + }, + { + "epoch": 0.77, + "learning_rate": 2.9607084608313972e-06, + "loss": 1.3589, + "step": 7378 + }, + { + "epoch": 0.77, + "learning_rate": 2.9581091658946415e-06, + "loss": 1.2839, + "step": 7379 + }, + { + "epoch": 0.77, + "learning_rate": 2.9555108143903187e-06, + "loss": 1.2883, + "step": 7380 + }, + { + "epoch": 0.77, + "learning_rate": 2.9529134066665453e-06, + "loss": 1.2781, + "step": 7381 + }, + { + "epoch": 0.77, + "learning_rate": 2.9503169430713084e-06, + "loss": 1.3638, + "step": 7382 + }, + { + "epoch": 0.77, + "learning_rate": 2.947721423952463e-06, + "loss": 1.3284, + "step": 7383 + }, + { + "epoch": 0.77, + "learning_rate": 2.945126849657748e-06, + "loss": 1.4043, + "step": 7384 + }, + { + "epoch": 0.77, + "learning_rate": 2.9425332205347624e-06, + "loss": 1.3173, + "step": 7385 + }, + { + "epoch": 0.77, + "learning_rate": 2.9399405369309884e-06, + "loss": 1.2099, + "step": 7386 + }, + { + "epoch": 0.77, + "learning_rate": 2.9373487991937845e-06, + "loss": 1.3062, + "step": 7387 + }, + { + "epoch": 0.77, + "learning_rate": 2.9347580076703695e-06, + "loss": 1.3075, + "step": 7388 + }, + { + "epoch": 0.77, + "learning_rate": 2.932168162707846e-06, + "loss": 1.3129, + "step": 7389 + }, + { + "epoch": 0.77, + "learning_rate": 2.9295792646531882e-06, + "loss": 1.4852, + "step": 7390 + }, + { + "epoch": 0.78, + "learning_rate": 2.926991313853239e-06, + "loss": 1.303, + "step": 7391 + }, + { + "epoch": 0.78, + "learning_rate": 2.9244043106547214e-06, + "loss": 1.2761, + "step": 7392 + }, + { + "epoch": 0.78, + "learning_rate": 2.9218182554042206e-06, + "loss": 1.2693, + "step": 7393 + }, + { + "epoch": 0.78, + "learning_rate": 2.9192331484482074e-06, + "loss": 1.2966, + "step": 7394 + }, + { + "epoch": 0.78, + "learning_rate": 2.9166489901330195e-06, + "loss": 1.3091, + "step": 7395 + }, + { + "epoch": 0.78, + "learning_rate": 2.91406578080486e-06, + "loss": 1.373, + "step": 7396 + }, + { + "epoch": 0.78, + "learning_rate": 2.9114835208098257e-06, + "loss": 1.2369, + "step": 7397 + }, + { + "epoch": 0.78, + "learning_rate": 2.908902210493866e-06, + "loss": 1.6399, + "step": 7398 + }, + { + "epoch": 0.78, + "learning_rate": 2.906321850202806e-06, + "loss": 1.3121, + "step": 7399 + }, + { + "epoch": 0.78, + "learning_rate": 2.903742440282352e-06, + "loss": 1.3401, + "step": 7400 + }, + { + "epoch": 0.78, + "learning_rate": 2.9011639810780833e-06, + "loss": 1.2974, + "step": 7401 + }, + { + "epoch": 0.78, + "learning_rate": 2.8985864729354383e-06, + "loss": 1.2825, + "step": 7402 + }, + { + "epoch": 0.78, + "learning_rate": 2.8960099161997434e-06, + "loss": 1.4901, + "step": 7403 + }, + { + "epoch": 0.78, + "learning_rate": 2.8934343112161867e-06, + "loss": 1.3203, + "step": 7404 + }, + { + "epoch": 0.78, + "learning_rate": 2.8908596583298343e-06, + "loss": 1.2859, + "step": 7405 + }, + { + "epoch": 0.78, + "learning_rate": 2.888285957885628e-06, + "loss": 1.334, + "step": 7406 + }, + { + "epoch": 0.78, + "learning_rate": 2.8857132102283703e-06, + "loss": 1.3358, + "step": 7407 + }, + { + "epoch": 0.78, + "learning_rate": 2.883141415702747e-06, + "loss": 1.2927, + "step": 7408 + }, + { + "epoch": 0.78, + "learning_rate": 2.8805705746533154e-06, + "loss": 1.3846, + "step": 7409 + }, + { + "epoch": 0.78, + "learning_rate": 2.8780006874244947e-06, + "loss": 1.2857, + "step": 7410 + }, + { + "epoch": 0.78, + "learning_rate": 2.8754317543605923e-06, + "loss": 1.3791, + "step": 7411 + }, + { + "epoch": 0.78, + "learning_rate": 2.872863775805772e-06, + "loss": 1.3286, + "step": 7412 + }, + { + "epoch": 0.78, + "learning_rate": 2.870296752104079e-06, + "loss": 1.244, + "step": 7413 + }, + { + "epoch": 0.78, + "learning_rate": 2.8677306835994335e-06, + "loss": 1.3673, + "step": 7414 + }, + { + "epoch": 0.78, + "learning_rate": 2.865165570635615e-06, + "loss": 1.3123, + "step": 7415 + }, + { + "epoch": 0.78, + "learning_rate": 2.862601413556286e-06, + "loss": 1.2867, + "step": 7416 + }, + { + "epoch": 0.78, + "learning_rate": 2.860038212704982e-06, + "loss": 1.3254, + "step": 7417 + }, + { + "epoch": 0.78, + "learning_rate": 2.8574759684250985e-06, + "loss": 1.2298, + "step": 7418 + }, + { + "epoch": 0.78, + "learning_rate": 2.854914681059914e-06, + "loss": 1.3054, + "step": 7419 + }, + { + "epoch": 0.78, + "learning_rate": 2.8523543509525785e-06, + "loss": 1.2984, + "step": 7420 + }, + { + "epoch": 0.78, + "learning_rate": 2.8497949784461043e-06, + "loss": 1.2848, + "step": 7421 + }, + { + "epoch": 0.78, + "learning_rate": 2.847236563883388e-06, + "loss": 1.4184, + "step": 7422 + }, + { + "epoch": 0.78, + "learning_rate": 2.84467910760718e-06, + "loss": 1.3967, + "step": 7423 + }, + { + "epoch": 0.78, + "learning_rate": 2.8421226099601284e-06, + "loss": 1.2847, + "step": 7424 + }, + { + "epoch": 0.78, + "learning_rate": 2.8395670712847322e-06, + "loss": 1.3681, + "step": 7425 + }, + { + "epoch": 0.78, + "learning_rate": 2.837012491923363e-06, + "loss": 1.3114, + "step": 7426 + }, + { + "epoch": 0.78, + "learning_rate": 2.834458872218274e-06, + "loss": 1.3264, + "step": 7427 + }, + { + "epoch": 0.78, + "learning_rate": 2.831906212511586e-06, + "loss": 1.3019, + "step": 7428 + }, + { + "epoch": 0.78, + "learning_rate": 2.829354513145284e-06, + "loss": 1.2619, + "step": 7429 + }, + { + "epoch": 0.78, + "learning_rate": 2.8268037744612362e-06, + "loss": 1.2825, + "step": 7430 + }, + { + "epoch": 0.78, + "learning_rate": 2.824253996801172e-06, + "loss": 1.2942, + "step": 7431 + }, + { + "epoch": 0.78, + "learning_rate": 2.8217051805066953e-06, + "loss": 1.3907, + "step": 7432 + }, + { + "epoch": 0.78, + "learning_rate": 2.8191573259192884e-06, + "loss": 1.2871, + "step": 7433 + }, + { + "epoch": 0.78, + "learning_rate": 2.81661043338029e-06, + "loss": 1.3924, + "step": 7434 + }, + { + "epoch": 0.78, + "learning_rate": 2.814064503230923e-06, + "loss": 1.3649, + "step": 7435 + }, + { + "epoch": 0.78, + "learning_rate": 2.8115195358122795e-06, + "loss": 1.3475, + "step": 7436 + }, + { + "epoch": 0.78, + "learning_rate": 2.808975531465312e-06, + "loss": 1.3736, + "step": 7437 + }, + { + "epoch": 0.78, + "learning_rate": 2.806432490530859e-06, + "loss": 1.2908, + "step": 7438 + }, + { + "epoch": 0.78, + "learning_rate": 2.803890413349618e-06, + "loss": 1.3991, + "step": 7439 + }, + { + "epoch": 0.78, + "learning_rate": 2.8013493002621617e-06, + "loss": 1.2928, + "step": 7440 + }, + { + "epoch": 0.78, + "learning_rate": 2.79880915160894e-06, + "loss": 1.3408, + "step": 7441 + }, + { + "epoch": 0.78, + "learning_rate": 2.7962699677302574e-06, + "loss": 1.3045, + "step": 7442 + }, + { + "epoch": 0.78, + "learning_rate": 2.793731748966311e-06, + "loss": 1.3179, + "step": 7443 + }, + { + "epoch": 0.78, + "learning_rate": 2.791194495657151e-06, + "loss": 1.2709, + "step": 7444 + }, + { + "epoch": 0.78, + "learning_rate": 2.7886582081427014e-06, + "loss": 1.3635, + "step": 7445 + }, + { + "epoch": 0.78, + "learning_rate": 2.786122886762762e-06, + "loss": 1.323, + "step": 7446 + }, + { + "epoch": 0.78, + "learning_rate": 2.7835885318570054e-06, + "loss": 1.2629, + "step": 7447 + }, + { + "epoch": 0.78, + "learning_rate": 2.7810551437649613e-06, + "loss": 1.4308, + "step": 7448 + }, + { + "epoch": 0.78, + "learning_rate": 2.778522722826048e-06, + "loss": 1.3546, + "step": 7449 + }, + { + "epoch": 0.78, + "learning_rate": 2.775991269379532e-06, + "loss": 1.4486, + "step": 7450 + }, + { + "epoch": 0.78, + "learning_rate": 2.773460783764579e-06, + "loss": 1.2845, + "step": 7451 + }, + { + "epoch": 0.78, + "learning_rate": 2.7709312663201993e-06, + "loss": 1.2393, + "step": 7452 + }, + { + "epoch": 0.78, + "learning_rate": 2.7684027173852836e-06, + "loss": 1.2939, + "step": 7453 + }, + { + "epoch": 0.78, + "learning_rate": 2.7658751372985926e-06, + "loss": 1.5802, + "step": 7454 + }, + { + "epoch": 0.78, + "learning_rate": 2.7633485263987627e-06, + "loss": 1.258, + "step": 7455 + }, + { + "epoch": 0.78, + "learning_rate": 2.760822885024286e-06, + "loss": 1.3223, + "step": 7456 + }, + { + "epoch": 0.78, + "learning_rate": 2.7582982135135418e-06, + "loss": 1.277, + "step": 7457 + }, + { + "epoch": 0.78, + "learning_rate": 2.755774512204764e-06, + "loss": 1.3047, + "step": 7458 + }, + { + "epoch": 0.78, + "learning_rate": 2.753251781436068e-06, + "loss": 1.3021, + "step": 7459 + }, + { + "epoch": 0.78, + "learning_rate": 2.750730021545437e-06, + "loss": 1.3321, + "step": 7460 + }, + { + "epoch": 0.78, + "learning_rate": 2.7482092328707154e-06, + "loss": 1.2453, + "step": 7461 + }, + { + "epoch": 0.78, + "learning_rate": 2.7456894157496293e-06, + "loss": 1.2628, + "step": 7462 + }, + { + "epoch": 0.78, + "learning_rate": 2.74317057051977e-06, + "loss": 1.4221, + "step": 7463 + }, + { + "epoch": 0.78, + "learning_rate": 2.740652697518593e-06, + "loss": 1.3034, + "step": 7464 + }, + { + "epoch": 0.78, + "learning_rate": 2.738135797083432e-06, + "loss": 1.2944, + "step": 7465 + }, + { + "epoch": 0.78, + "learning_rate": 2.7356198695514893e-06, + "loss": 1.3434, + "step": 7466 + }, + { + "epoch": 0.78, + "learning_rate": 2.733104915259829e-06, + "loss": 1.3127, + "step": 7467 + }, + { + "epoch": 0.78, + "learning_rate": 2.730590934545396e-06, + "loss": 1.2425, + "step": 7468 + }, + { + "epoch": 0.78, + "learning_rate": 2.7280779277449907e-06, + "loss": 1.4366, + "step": 7469 + }, + { + "epoch": 0.78, + "learning_rate": 2.7255658951953036e-06, + "loss": 1.3024, + "step": 7470 + }, + { + "epoch": 0.78, + "learning_rate": 2.7230548372328745e-06, + "loss": 1.2768, + "step": 7471 + }, + { + "epoch": 0.78, + "learning_rate": 2.720544754194121e-06, + "loss": 1.2453, + "step": 7472 + }, + { + "epoch": 0.78, + "learning_rate": 2.7180356464153303e-06, + "loss": 1.2796, + "step": 7473 + }, + { + "epoch": 0.78, + "learning_rate": 2.715527514232661e-06, + "loss": 1.3181, + "step": 7474 + }, + { + "epoch": 0.78, + "learning_rate": 2.7130203579821344e-06, + "loss": 1.4013, + "step": 7475 + }, + { + "epoch": 0.78, + "learning_rate": 2.710514177999649e-06, + "loss": 1.3365, + "step": 7476 + }, + { + "epoch": 0.78, + "learning_rate": 2.7080089746209614e-06, + "loss": 1.31, + "step": 7477 + }, + { + "epoch": 0.78, + "learning_rate": 2.7055047481817153e-06, + "loss": 1.258, + "step": 7478 + }, + { + "epoch": 0.78, + "learning_rate": 2.7030014990174068e-06, + "loss": 1.2199, + "step": 7479 + }, + { + "epoch": 0.78, + "learning_rate": 2.7004992274634046e-06, + "loss": 1.3007, + "step": 7480 + }, + { + "epoch": 0.78, + "learning_rate": 2.69799793385495e-06, + "loss": 1.2772, + "step": 7481 + }, + { + "epoch": 0.78, + "learning_rate": 2.6954976185271576e-06, + "loss": 1.4021, + "step": 7482 + }, + { + "epoch": 0.78, + "learning_rate": 2.692998281814998e-06, + "loss": 1.3183, + "step": 7483 + }, + { + "epoch": 0.78, + "learning_rate": 2.6904999240533246e-06, + "loss": 1.3412, + "step": 7484 + }, + { + "epoch": 0.78, + "learning_rate": 2.6880025455768465e-06, + "loss": 1.2552, + "step": 7485 + }, + { + "epoch": 0.79, + "learning_rate": 2.6855061467201517e-06, + "loss": 1.2525, + "step": 7486 + }, + { + "epoch": 0.79, + "learning_rate": 2.683010727817695e-06, + "loss": 1.269, + "step": 7487 + }, + { + "epoch": 0.79, + "learning_rate": 2.680516289203793e-06, + "loss": 1.5189, + "step": 7488 + }, + { + "epoch": 0.79, + "learning_rate": 2.6780228312126454e-06, + "loss": 1.2999, + "step": 7489 + }, + { + "epoch": 0.79, + "learning_rate": 2.675530354178306e-06, + "loss": 1.3322, + "step": 7490 + }, + { + "epoch": 0.79, + "learning_rate": 2.6730388584347e-06, + "loss": 1.3918, + "step": 7491 + }, + { + "epoch": 0.79, + "learning_rate": 2.670548344315628e-06, + "loss": 1.4438, + "step": 7492 + }, + { + "epoch": 0.79, + "learning_rate": 2.6680588121547546e-06, + "loss": 1.3393, + "step": 7493 + }, + { + "epoch": 0.79, + "learning_rate": 2.6655702622856105e-06, + "loss": 1.301, + "step": 7494 + }, + { + "epoch": 0.79, + "learning_rate": 2.6630826950416024e-06, + "loss": 1.2463, + "step": 7495 + }, + { + "epoch": 0.79, + "learning_rate": 2.660596110755991e-06, + "loss": 1.2641, + "step": 7496 + }, + { + "epoch": 0.79, + "learning_rate": 2.6581105097619264e-06, + "loss": 1.3824, + "step": 7497 + }, + { + "epoch": 0.79, + "learning_rate": 2.6556258923924104e-06, + "loss": 1.339, + "step": 7498 + }, + { + "epoch": 0.79, + "learning_rate": 2.6531422589803134e-06, + "loss": 1.2653, + "step": 7499 + }, + { + "epoch": 0.79, + "learning_rate": 2.6506596098583826e-06, + "loss": 1.2773, + "step": 7500 + }, + { + "epoch": 0.79, + "learning_rate": 2.648177945359233e-06, + "loss": 1.1829, + "step": 7501 + }, + { + "epoch": 0.79, + "learning_rate": 2.6456972658153358e-06, + "loss": 1.4014, + "step": 7502 + }, + { + "epoch": 0.79, + "learning_rate": 2.6432175715590446e-06, + "loss": 1.3648, + "step": 7503 + }, + { + "epoch": 0.79, + "learning_rate": 2.6407388629225706e-06, + "loss": 1.2731, + "step": 7504 + }, + { + "epoch": 0.79, + "learning_rate": 2.6382611402379988e-06, + "loss": 1.3076, + "step": 7505 + }, + { + "epoch": 0.79, + "learning_rate": 2.6357844038372824e-06, + "loss": 1.2054, + "step": 7506 + }, + { + "epoch": 0.79, + "learning_rate": 2.6333086540522366e-06, + "loss": 1.2579, + "step": 7507 + }, + { + "epoch": 0.79, + "learning_rate": 2.6308338912145493e-06, + "loss": 1.316, + "step": 7508 + }, + { + "epoch": 0.79, + "learning_rate": 2.6283601156557792e-06, + "loss": 1.2957, + "step": 7509 + }, + { + "epoch": 0.79, + "learning_rate": 2.625887327707343e-06, + "loss": 1.3017, + "step": 7510 + }, + { + "epoch": 0.79, + "learning_rate": 2.6234155277005334e-06, + "loss": 1.2591, + "step": 7511 + }, + { + "epoch": 0.79, + "learning_rate": 2.62094471596651e-06, + "loss": 1.3582, + "step": 7512 + }, + { + "epoch": 0.79, + "learning_rate": 2.6184748928362934e-06, + "loss": 1.3026, + "step": 7513 + }, + { + "epoch": 0.79, + "learning_rate": 2.616006058640782e-06, + "loss": 1.3222, + "step": 7514 + }, + { + "epoch": 0.79, + "learning_rate": 2.6135382137107268e-06, + "loss": 1.2785, + "step": 7515 + }, + { + "epoch": 0.79, + "learning_rate": 2.6110713583767687e-06, + "loss": 1.3227, + "step": 7516 + }, + { + "epoch": 0.79, + "learning_rate": 2.608605492969396e-06, + "loss": 1.2695, + "step": 7517 + }, + { + "epoch": 0.79, + "learning_rate": 2.6061406178189684e-06, + "loss": 1.2809, + "step": 7518 + }, + { + "epoch": 0.79, + "learning_rate": 2.6036767332557188e-06, + "loss": 1.2934, + "step": 7519 + }, + { + "epoch": 0.79, + "learning_rate": 2.6012138396097473e-06, + "loss": 1.2484, + "step": 7520 + }, + { + "epoch": 0.79, + "learning_rate": 2.5987519372110125e-06, + "loss": 1.3422, + "step": 7521 + }, + { + "epoch": 0.79, + "learning_rate": 2.596291026389354e-06, + "loss": 1.3008, + "step": 7522 + }, + { + "epoch": 0.79, + "learning_rate": 2.5938311074744582e-06, + "loss": 1.3698, + "step": 7523 + }, + { + "epoch": 0.79, + "learning_rate": 2.5913721807959045e-06, + "loss": 1.3034, + "step": 7524 + }, + { + "epoch": 0.79, + "learning_rate": 2.5889142466831208e-06, + "loss": 1.3011, + "step": 7525 + }, + { + "epoch": 0.79, + "learning_rate": 2.586457305465403e-06, + "loss": 1.3626, + "step": 7526 + }, + { + "epoch": 0.79, + "learning_rate": 2.5840013574719213e-06, + "loss": 1.3018, + "step": 7527 + }, + { + "epoch": 0.79, + "learning_rate": 2.581546403031713e-06, + "loss": 1.3316, + "step": 7528 + }, + { + "epoch": 0.79, + "learning_rate": 2.579092442473673e-06, + "loss": 1.2534, + "step": 7529 + }, + { + "epoch": 0.79, + "learning_rate": 2.5766394761265743e-06, + "loss": 1.2949, + "step": 7530 + }, + { + "epoch": 0.79, + "learning_rate": 2.574187504319046e-06, + "loss": 1.2962, + "step": 7531 + }, + { + "epoch": 0.79, + "learning_rate": 2.5717365273795914e-06, + "loss": 1.2926, + "step": 7532 + }, + { + "epoch": 0.79, + "learning_rate": 2.5692865456365824e-06, + "loss": 1.3136, + "step": 7533 + }, + { + "epoch": 0.79, + "learning_rate": 2.5668375594182447e-06, + "loss": 1.3065, + "step": 7534 + }, + { + "epoch": 0.79, + "learning_rate": 2.564389569052691e-06, + "loss": 1.3631, + "step": 7535 + }, + { + "epoch": 0.79, + "learning_rate": 2.5619425748678827e-06, + "loss": 1.3028, + "step": 7536 + }, + { + "epoch": 0.79, + "learning_rate": 2.5594965771916526e-06, + "loss": 1.3212, + "step": 7537 + }, + { + "epoch": 0.79, + "learning_rate": 2.557051576351702e-06, + "loss": 1.3154, + "step": 7538 + }, + { + "epoch": 0.79, + "learning_rate": 2.554607572675605e-06, + "loss": 1.284, + "step": 7539 + }, + { + "epoch": 0.79, + "learning_rate": 2.5521645664907856e-06, + "loss": 1.3833, + "step": 7540 + }, + { + "epoch": 0.79, + "learning_rate": 2.549722558124551e-06, + "loss": 1.3079, + "step": 7541 + }, + { + "epoch": 0.79, + "learning_rate": 2.54728154790406e-06, + "loss": 1.3104, + "step": 7542 + }, + { + "epoch": 0.79, + "learning_rate": 2.544841536156356e-06, + "loss": 1.2933, + "step": 7543 + }, + { + "epoch": 0.79, + "learning_rate": 2.5424025232083315e-06, + "loss": 1.4103, + "step": 7544 + }, + { + "epoch": 0.79, + "learning_rate": 2.53996450938675e-06, + "loss": 1.3602, + "step": 7545 + }, + { + "epoch": 0.79, + "learning_rate": 2.537527495018244e-06, + "loss": 1.381, + "step": 7546 + }, + { + "epoch": 0.79, + "learning_rate": 2.535091480429315e-06, + "loss": 1.4212, + "step": 7547 + }, + { + "epoch": 0.79, + "learning_rate": 2.5326564659463203e-06, + "loss": 1.3662, + "step": 7548 + }, + { + "epoch": 0.79, + "learning_rate": 2.5302224518954944e-06, + "loss": 1.2896, + "step": 7549 + }, + { + "epoch": 0.79, + "learning_rate": 2.5277894386029246e-06, + "loss": 1.3218, + "step": 7550 + }, + { + "epoch": 0.79, + "learning_rate": 2.5253574263945835e-06, + "loss": 1.337, + "step": 7551 + }, + { + "epoch": 0.79, + "learning_rate": 2.522926415596293e-06, + "loss": 1.3457, + "step": 7552 + }, + { + "epoch": 0.79, + "learning_rate": 2.5204964065337423e-06, + "loss": 1.3227, + "step": 7553 + }, + { + "epoch": 0.79, + "learning_rate": 2.5180673995324933e-06, + "loss": 1.2529, + "step": 7554 + }, + { + "epoch": 0.79, + "learning_rate": 2.5156393949179746e-06, + "loss": 1.3193, + "step": 7555 + }, + { + "epoch": 0.79, + "learning_rate": 2.5132123930154697e-06, + "loss": 1.2719, + "step": 7556 + }, + { + "epoch": 0.79, + "learning_rate": 2.5107863941501363e-06, + "loss": 1.3367, + "step": 7557 + }, + { + "epoch": 0.79, + "learning_rate": 2.508361398647e-06, + "loss": 1.2918, + "step": 7558 + }, + { + "epoch": 0.79, + "learning_rate": 2.505937406830942e-06, + "loss": 1.3458, + "step": 7559 + }, + { + "epoch": 0.79, + "learning_rate": 2.5035144190267215e-06, + "loss": 1.3975, + "step": 7560 + }, + { + "epoch": 0.79, + "learning_rate": 2.5010924355589463e-06, + "loss": 1.3717, + "step": 7561 + }, + { + "epoch": 0.79, + "learning_rate": 2.498671456752112e-06, + "loss": 1.316, + "step": 7562 + }, + { + "epoch": 0.79, + "eval_loss": 1.3956769704818726, + "eval_runtime": 77.5888, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 7562 + }, + { + "epoch": 0.79, + "learning_rate": 2.496251482930563e-06, + "loss": 1.2949, + "step": 7563 + }, + { + "epoch": 0.79, + "learning_rate": 2.4938325144185094e-06, + "loss": 1.6856, + "step": 7564 + }, + { + "epoch": 0.79, + "learning_rate": 2.4914145515400347e-06, + "loss": 1.4064, + "step": 7565 + }, + { + "epoch": 0.79, + "learning_rate": 2.4889975946190847e-06, + "loss": 1.3279, + "step": 7566 + }, + { + "epoch": 0.79, + "learning_rate": 2.4865816439794666e-06, + "loss": 1.2923, + "step": 7567 + }, + { + "epoch": 0.79, + "learning_rate": 2.48416669994486e-06, + "loss": 1.3237, + "step": 7568 + }, + { + "epoch": 0.79, + "learning_rate": 2.481752762838796e-06, + "loss": 1.3424, + "step": 7569 + }, + { + "epoch": 0.79, + "learning_rate": 2.479339832984693e-06, + "loss": 1.1656, + "step": 7570 + }, + { + "epoch": 0.79, + "learning_rate": 2.476927910705814e-06, + "loss": 1.1659, + "step": 7571 + }, + { + "epoch": 0.79, + "learning_rate": 2.4745169963252945e-06, + "loss": 1.3452, + "step": 7572 + }, + { + "epoch": 0.79, + "learning_rate": 2.472107090166136e-06, + "loss": 1.4011, + "step": 7573 + }, + { + "epoch": 0.79, + "learning_rate": 2.4696981925512076e-06, + "loss": 1.2312, + "step": 7574 + }, + { + "epoch": 0.79, + "learning_rate": 2.4672903038032335e-06, + "loss": 1.3257, + "step": 7575 + }, + { + "epoch": 0.79, + "learning_rate": 2.464883424244815e-06, + "loss": 1.2795, + "step": 7576 + }, + { + "epoch": 0.79, + "learning_rate": 2.4624775541984025e-06, + "loss": 1.3514, + "step": 7577 + }, + { + "epoch": 0.79, + "learning_rate": 2.4600726939863338e-06, + "loss": 1.3736, + "step": 7578 + }, + { + "epoch": 0.79, + "learning_rate": 2.4576688439307926e-06, + "loss": 1.3361, + "step": 7579 + }, + { + "epoch": 0.79, + "learning_rate": 2.4552660043538255e-06, + "loss": 1.3047, + "step": 7580 + }, + { + "epoch": 0.79, + "learning_rate": 2.452864175577364e-06, + "loss": 1.2987, + "step": 7581 + }, + { + "epoch": 0.8, + "learning_rate": 2.4504633579231863e-06, + "loss": 1.3218, + "step": 7582 + }, + { + "epoch": 0.8, + "learning_rate": 2.448063551712937e-06, + "loss": 1.3159, + "step": 7583 + }, + { + "epoch": 0.8, + "learning_rate": 2.44566475726813e-06, + "loss": 1.3032, + "step": 7584 + }, + { + "epoch": 0.8, + "learning_rate": 2.443266974910147e-06, + "loss": 1.2298, + "step": 7585 + }, + { + "epoch": 0.8, + "learning_rate": 2.4408702049602217e-06, + "loss": 1.288, + "step": 7586 + }, + { + "epoch": 0.8, + "learning_rate": 2.4384744477394663e-06, + "loss": 1.2733, + "step": 7587 + }, + { + "epoch": 0.8, + "learning_rate": 2.4360797035688424e-06, + "loss": 1.3576, + "step": 7588 + }, + { + "epoch": 0.8, + "learning_rate": 2.4336859727691953e-06, + "loss": 1.3029, + "step": 7589 + }, + { + "epoch": 0.8, + "learning_rate": 2.4312932556612178e-06, + "loss": 1.4056, + "step": 7590 + }, + { + "epoch": 0.8, + "learning_rate": 2.4289015525654693e-06, + "loss": 1.3129, + "step": 7591 + }, + { + "epoch": 0.8, + "learning_rate": 2.426510863802379e-06, + "loss": 1.2301, + "step": 7592 + }, + { + "epoch": 0.8, + "learning_rate": 2.4241211896922422e-06, + "loss": 1.282, + "step": 7593 + }, + { + "epoch": 0.8, + "learning_rate": 2.4217325305552073e-06, + "loss": 1.3173, + "step": 7594 + }, + { + "epoch": 0.8, + "learning_rate": 2.419344886711299e-06, + "loss": 1.3387, + "step": 7595 + }, + { + "epoch": 0.8, + "learning_rate": 2.416958258480391e-06, + "loss": 1.3313, + "step": 7596 + }, + { + "epoch": 0.8, + "learning_rate": 2.4145726461822428e-06, + "loss": 1.437, + "step": 7597 + }, + { + "epoch": 0.8, + "learning_rate": 2.412188050136458e-06, + "loss": 1.288, + "step": 7598 + }, + { + "epoch": 0.8, + "learning_rate": 2.40980447066251e-06, + "loss": 1.2815, + "step": 7599 + }, + { + "epoch": 0.8, + "learning_rate": 2.407421908079738e-06, + "loss": 1.3769, + "step": 7600 + }, + { + "epoch": 0.8, + "learning_rate": 2.405040362707349e-06, + "loss": 1.2726, + "step": 7601 + }, + { + "epoch": 0.8, + "learning_rate": 2.4026598348644027e-06, + "loss": 1.3741, + "step": 7602 + }, + { + "epoch": 0.8, + "learning_rate": 2.4002803248698303e-06, + "loss": 1.3046, + "step": 7603 + }, + { + "epoch": 0.8, + "learning_rate": 2.3979018330424284e-06, + "loss": 1.2566, + "step": 7604 + }, + { + "epoch": 0.8, + "learning_rate": 2.3955243597008504e-06, + "loss": 1.3237, + "step": 7605 + }, + { + "epoch": 0.8, + "learning_rate": 2.3931479051636184e-06, + "loss": 1.2446, + "step": 7606 + }, + { + "epoch": 0.8, + "learning_rate": 2.390772469749111e-06, + "loss": 1.2495, + "step": 7607 + }, + { + "epoch": 0.8, + "learning_rate": 2.3883980537755848e-06, + "loss": 1.326, + "step": 7608 + }, + { + "epoch": 0.8, + "learning_rate": 2.386024657561146e-06, + "loss": 1.2979, + "step": 7609 + }, + { + "epoch": 0.8, + "learning_rate": 2.3836522814237652e-06, + "loss": 1.2877, + "step": 7610 + }, + { + "epoch": 0.8, + "learning_rate": 2.381280925681283e-06, + "loss": 1.3327, + "step": 7611 + }, + { + "epoch": 0.8, + "learning_rate": 2.3789105906514034e-06, + "loss": 1.2641, + "step": 7612 + }, + { + "epoch": 0.8, + "learning_rate": 2.3765412766516837e-06, + "loss": 1.2904, + "step": 7613 + }, + { + "epoch": 0.8, + "learning_rate": 2.3741729839995573e-06, + "loss": 1.3153, + "step": 7614 + }, + { + "epoch": 0.8, + "learning_rate": 2.3718057130123063e-06, + "loss": 1.3168, + "step": 7615 + }, + { + "epoch": 0.8, + "learning_rate": 2.369439464007095e-06, + "loss": 1.2751, + "step": 7616 + }, + { + "epoch": 0.8, + "learning_rate": 2.3670742373009358e-06, + "loss": 1.3033, + "step": 7617 + }, + { + "epoch": 0.8, + "learning_rate": 2.364710033210703e-06, + "loss": 1.2788, + "step": 7618 + }, + { + "epoch": 0.8, + "learning_rate": 2.362346852053143e-06, + "loss": 1.3195, + "step": 7619 + }, + { + "epoch": 0.8, + "learning_rate": 2.3599846941448655e-06, + "loss": 1.2592, + "step": 7620 + }, + { + "epoch": 0.8, + "learning_rate": 2.357623559802332e-06, + "loss": 1.2495, + "step": 7621 + }, + { + "epoch": 0.8, + "learning_rate": 2.3552634493418803e-06, + "loss": 1.3111, + "step": 7622 + }, + { + "epoch": 0.8, + "learning_rate": 2.3529043630796954e-06, + "loss": 1.2559, + "step": 7623 + }, + { + "epoch": 0.8, + "learning_rate": 2.3505463013318454e-06, + "loss": 1.2642, + "step": 7624 + }, + { + "epoch": 0.8, + "learning_rate": 2.3481892644142455e-06, + "loss": 1.3277, + "step": 7625 + }, + { + "epoch": 0.8, + "learning_rate": 2.345833252642671e-06, + "loss": 1.3161, + "step": 7626 + }, + { + "epoch": 0.8, + "learning_rate": 2.3434782663327783e-06, + "loss": 1.2901, + "step": 7627 + }, + { + "epoch": 0.8, + "learning_rate": 2.341124305800071e-06, + "loss": 1.26, + "step": 7628 + }, + { + "epoch": 0.8, + "learning_rate": 2.338771371359915e-06, + "loss": 1.2772, + "step": 7629 + }, + { + "epoch": 0.8, + "learning_rate": 2.336419463327546e-06, + "loss": 1.2841, + "step": 7630 + }, + { + "epoch": 0.8, + "learning_rate": 2.334068582018062e-06, + "loss": 1.2036, + "step": 7631 + }, + { + "epoch": 0.8, + "learning_rate": 2.331718727746417e-06, + "loss": 1.2992, + "step": 7632 + }, + { + "epoch": 0.8, + "learning_rate": 2.329369900827434e-06, + "loss": 1.3145, + "step": 7633 + }, + { + "epoch": 0.8, + "learning_rate": 2.327022101575789e-06, + "loss": 1.3954, + "step": 7634 + }, + { + "epoch": 0.8, + "learning_rate": 2.3246753303060364e-06, + "loss": 1.2916, + "step": 7635 + }, + { + "epoch": 0.8, + "learning_rate": 2.322329587332579e-06, + "loss": 1.3013, + "step": 7636 + }, + { + "epoch": 0.8, + "learning_rate": 2.319984872969683e-06, + "loss": 1.2686, + "step": 7637 + }, + { + "epoch": 0.8, + "learning_rate": 2.3176411875314806e-06, + "loss": 1.3407, + "step": 7638 + }, + { + "epoch": 0.8, + "learning_rate": 2.315298531331972e-06, + "loss": 1.5181, + "step": 7639 + }, + { + "epoch": 0.8, + "learning_rate": 2.3129569046850054e-06, + "loss": 1.5231, + "step": 7640 + }, + { + "epoch": 0.8, + "learning_rate": 2.3106163079043033e-06, + "loss": 1.4524, + "step": 7641 + }, + { + "epoch": 0.8, + "learning_rate": 2.308276741303438e-06, + "loss": 1.2935, + "step": 7642 + }, + { + "epoch": 0.8, + "learning_rate": 2.3059382051958635e-06, + "loss": 1.4096, + "step": 7643 + }, + { + "epoch": 0.8, + "learning_rate": 2.303600699894876e-06, + "loss": 1.3598, + "step": 7644 + }, + { + "epoch": 0.8, + "learning_rate": 2.3012642257136397e-06, + "loss": 1.3578, + "step": 7645 + }, + { + "epoch": 0.8, + "learning_rate": 2.2989287829651853e-06, + "loss": 1.3147, + "step": 7646 + }, + { + "epoch": 0.8, + "learning_rate": 2.296594371962403e-06, + "loss": 1.3495, + "step": 7647 + }, + { + "epoch": 0.8, + "learning_rate": 2.2942609930180393e-06, + "loss": 1.4035, + "step": 7648 + }, + { + "epoch": 0.8, + "learning_rate": 2.291928646444711e-06, + "loss": 1.2757, + "step": 7649 + }, + { + "epoch": 0.8, + "learning_rate": 2.2895973325548914e-06, + "loss": 1.2496, + "step": 7650 + }, + { + "epoch": 0.8, + "learning_rate": 2.2872670516609196e-06, + "loss": 1.3372, + "step": 7651 + }, + { + "epoch": 0.8, + "learning_rate": 2.28493780407499e-06, + "loss": 1.276, + "step": 7652 + }, + { + "epoch": 0.8, + "learning_rate": 2.2826095901091574e-06, + "loss": 1.319, + "step": 7653 + }, + { + "epoch": 0.8, + "learning_rate": 2.280282410075354e-06, + "loss": 1.3473, + "step": 7654 + }, + { + "epoch": 0.8, + "learning_rate": 2.2779562642853546e-06, + "loss": 1.2947, + "step": 7655 + }, + { + "epoch": 0.8, + "learning_rate": 2.2756311530508026e-06, + "loss": 1.3485, + "step": 7656 + }, + { + "epoch": 0.8, + "learning_rate": 2.2733070766832042e-06, + "loss": 1.3187, + "step": 7657 + }, + { + "epoch": 0.8, + "learning_rate": 2.2709840354939296e-06, + "loss": 1.3979, + "step": 7658 + }, + { + "epoch": 0.8, + "learning_rate": 2.2686620297942007e-06, + "loss": 1.269, + "step": 7659 + }, + { + "epoch": 0.8, + "learning_rate": 2.266341059895113e-06, + "loss": 1.3572, + "step": 7660 + }, + { + "epoch": 0.8, + "learning_rate": 2.264021126107607e-06, + "loss": 1.2858, + "step": 7661 + }, + { + "epoch": 0.8, + "learning_rate": 2.2617022287425073e-06, + "loss": 1.3677, + "step": 7662 + }, + { + "epoch": 0.8, + "learning_rate": 2.259384368110479e-06, + "loss": 1.3111, + "step": 7663 + }, + { + "epoch": 0.8, + "learning_rate": 2.2570675445220535e-06, + "loss": 1.2969, + "step": 7664 + }, + { + "epoch": 0.8, + "learning_rate": 2.254751758287629e-06, + "loss": 1.2901, + "step": 7665 + }, + { + "epoch": 0.8, + "learning_rate": 2.252437009717464e-06, + "loss": 1.2834, + "step": 7666 + }, + { + "epoch": 0.8, + "learning_rate": 2.2501232991216705e-06, + "loss": 1.2505, + "step": 7667 + }, + { + "epoch": 0.8, + "learning_rate": 2.2478106268102295e-06, + "loss": 1.2763, + "step": 7668 + }, + { + "epoch": 0.8, + "learning_rate": 2.2454989930929737e-06, + "loss": 1.3427, + "step": 7669 + }, + { + "epoch": 0.8, + "learning_rate": 2.2431883982796132e-06, + "loss": 1.3397, + "step": 7670 + }, + { + "epoch": 0.8, + "learning_rate": 2.240878842679702e-06, + "loss": 1.2525, + "step": 7671 + }, + { + "epoch": 0.8, + "learning_rate": 2.238570326602657e-06, + "loss": 1.2085, + "step": 7672 + }, + { + "epoch": 0.8, + "learning_rate": 2.23626285035777e-06, + "loss": 1.2196, + "step": 7673 + }, + { + "epoch": 0.8, + "learning_rate": 2.2339564142541783e-06, + "loss": 1.2602, + "step": 7674 + }, + { + "epoch": 0.8, + "learning_rate": 2.2316510186008824e-06, + "loss": 1.4144, + "step": 7675 + }, + { + "epoch": 0.8, + "learning_rate": 2.2293466637067486e-06, + "loss": 1.3239, + "step": 7676 + }, + { + "epoch": 0.81, + "learning_rate": 2.227043349880501e-06, + "loss": 1.342, + "step": 7677 + }, + { + "epoch": 0.81, + "learning_rate": 2.2247410774307276e-06, + "loss": 1.3395, + "step": 7678 + }, + { + "epoch": 0.81, + "learning_rate": 2.2224398466658712e-06, + "loss": 1.3948, + "step": 7679 + }, + { + "epoch": 0.81, + "learning_rate": 2.2201396578942325e-06, + "loss": 1.2983, + "step": 7680 + }, + { + "epoch": 0.81, + "learning_rate": 2.2178405114239877e-06, + "loss": 1.3779, + "step": 7681 + }, + { + "epoch": 0.81, + "learning_rate": 2.2155424075631583e-06, + "loss": 1.2826, + "step": 7682 + }, + { + "epoch": 0.81, + "learning_rate": 2.213245346619628e-06, + "loss": 1.3939, + "step": 7683 + }, + { + "epoch": 0.81, + "learning_rate": 2.2109493289011474e-06, + "loss": 1.298, + "step": 7684 + }, + { + "epoch": 0.81, + "learning_rate": 2.208654354715326e-06, + "loss": 1.2947, + "step": 7685 + }, + { + "epoch": 0.81, + "learning_rate": 2.2063604243696267e-06, + "loss": 1.3532, + "step": 7686 + }, + { + "epoch": 0.81, + "learning_rate": 2.204067538171382e-06, + "loss": 1.2713, + "step": 7687 + }, + { + "epoch": 0.81, + "learning_rate": 2.2017756964277713e-06, + "loss": 1.3025, + "step": 7688 + }, + { + "epoch": 0.81, + "learning_rate": 2.199484899445854e-06, + "loss": 1.2806, + "step": 7689 + }, + { + "epoch": 0.81, + "learning_rate": 2.1971951475325328e-06, + "loss": 1.3113, + "step": 7690 + }, + { + "epoch": 0.81, + "learning_rate": 2.194906440994572e-06, + "loss": 1.4729, + "step": 7691 + }, + { + "epoch": 0.81, + "learning_rate": 2.1926187801386033e-06, + "loss": 1.29, + "step": 7692 + }, + { + "epoch": 0.81, + "learning_rate": 2.1903321652711163e-06, + "loss": 1.3092, + "step": 7693 + }, + { + "epoch": 0.81, + "learning_rate": 2.188046596698454e-06, + "loss": 1.3286, + "step": 7694 + }, + { + "epoch": 0.81, + "learning_rate": 2.185762074726826e-06, + "loss": 1.3734, + "step": 7695 + }, + { + "epoch": 0.81, + "learning_rate": 2.1834785996622988e-06, + "loss": 1.3218, + "step": 7696 + }, + { + "epoch": 0.81, + "learning_rate": 2.1811961718108034e-06, + "loss": 1.3319, + "step": 7697 + }, + { + "epoch": 0.81, + "learning_rate": 2.178914791478124e-06, + "loss": 1.2732, + "step": 7698 + }, + { + "epoch": 0.81, + "learning_rate": 2.1766344589698996e-06, + "loss": 1.4451, + "step": 7699 + }, + { + "epoch": 0.81, + "learning_rate": 2.1743551745916492e-06, + "loss": 1.338, + "step": 7700 + }, + { + "epoch": 0.81, + "learning_rate": 2.172076938648732e-06, + "loss": 1.3602, + "step": 7701 + }, + { + "epoch": 0.81, + "learning_rate": 2.16979975144637e-06, + "loss": 1.2782, + "step": 7702 + }, + { + "epoch": 0.81, + "learning_rate": 2.1675236132896505e-06, + "loss": 1.2661, + "step": 7703 + }, + { + "epoch": 0.81, + "learning_rate": 2.165248524483521e-06, + "loss": 1.3031, + "step": 7704 + }, + { + "epoch": 0.81, + "learning_rate": 2.1629744853327793e-06, + "loss": 1.3754, + "step": 7705 + }, + { + "epoch": 0.81, + "learning_rate": 2.1607014961420926e-06, + "loss": 1.4255, + "step": 7706 + }, + { + "epoch": 0.81, + "learning_rate": 2.1584295572159764e-06, + "loss": 1.3955, + "step": 7707 + }, + { + "epoch": 0.81, + "learning_rate": 2.156158668858822e-06, + "loss": 1.3691, + "step": 7708 + }, + { + "epoch": 0.81, + "learning_rate": 2.153888831374865e-06, + "loss": 1.3986, + "step": 7709 + }, + { + "epoch": 0.81, + "learning_rate": 2.1516200450682036e-06, + "loss": 1.3231, + "step": 7710 + }, + { + "epoch": 0.81, + "learning_rate": 2.149352310242797e-06, + "loss": 1.2892, + "step": 7711 + }, + { + "epoch": 0.81, + "learning_rate": 2.1470856272024686e-06, + "loss": 1.289, + "step": 7712 + }, + { + "epoch": 0.81, + "learning_rate": 2.1448199962508898e-06, + "loss": 1.2804, + "step": 7713 + }, + { + "epoch": 0.81, + "learning_rate": 2.1425554176916007e-06, + "loss": 1.2599, + "step": 7714 + }, + { + "epoch": 0.81, + "learning_rate": 2.1402918918279904e-06, + "loss": 1.3082, + "step": 7715 + }, + { + "epoch": 0.81, + "learning_rate": 2.1380294189633233e-06, + "loss": 1.306, + "step": 7716 + }, + { + "epoch": 0.81, + "learning_rate": 2.1357679994007076e-06, + "loss": 1.2681, + "step": 7717 + }, + { + "epoch": 0.81, + "learning_rate": 2.1335076334431092e-06, + "loss": 1.2842, + "step": 7718 + }, + { + "epoch": 0.81, + "learning_rate": 2.13124832139337e-06, + "loss": 1.3153, + "step": 7719 + }, + { + "epoch": 0.81, + "learning_rate": 2.128990063554176e-06, + "loss": 1.3312, + "step": 7720 + }, + { + "epoch": 0.81, + "learning_rate": 2.12673286022807e-06, + "loss": 1.2851, + "step": 7721 + }, + { + "epoch": 0.81, + "learning_rate": 2.124476711717465e-06, + "loss": 1.3398, + "step": 7722 + }, + { + "epoch": 0.81, + "learning_rate": 2.1222216183246246e-06, + "loss": 1.2543, + "step": 7723 + }, + { + "epoch": 0.81, + "learning_rate": 2.1199675803516785e-06, + "loss": 1.3686, + "step": 7724 + }, + { + "epoch": 0.81, + "learning_rate": 2.117714598100604e-06, + "loss": 1.3746, + "step": 7725 + }, + { + "epoch": 0.81, + "learning_rate": 2.1154626718732407e-06, + "loss": 1.2664, + "step": 7726 + }, + { + "epoch": 0.81, + "learning_rate": 2.1132118019712976e-06, + "loss": 1.3075, + "step": 7727 + }, + { + "epoch": 0.81, + "learning_rate": 2.1109619886963284e-06, + "loss": 1.739, + "step": 7728 + }, + { + "epoch": 0.81, + "learning_rate": 2.1087132323497483e-06, + "loss": 1.335, + "step": 7729 + }, + { + "epoch": 0.81, + "learning_rate": 2.1064655332328344e-06, + "loss": 1.3371, + "step": 7730 + }, + { + "epoch": 0.81, + "learning_rate": 2.104218891646724e-06, + "loss": 1.3837, + "step": 7731 + }, + { + "epoch": 0.81, + "learning_rate": 2.1019733078924045e-06, + "loss": 1.3436, + "step": 7732 + }, + { + "epoch": 0.81, + "learning_rate": 2.0997287822707304e-06, + "loss": 1.2995, + "step": 7733 + }, + { + "epoch": 0.81, + "learning_rate": 2.0974853150824036e-06, + "loss": 1.2914, + "step": 7734 + }, + { + "epoch": 0.81, + "learning_rate": 2.095242906628001e-06, + "loss": 1.3773, + "step": 7735 + }, + { + "epoch": 0.81, + "learning_rate": 2.0930015572079434e-06, + "loss": 1.3097, + "step": 7736 + }, + { + "epoch": 0.81, + "learning_rate": 2.0907612671225108e-06, + "loss": 1.3261, + "step": 7737 + }, + { + "epoch": 0.81, + "learning_rate": 2.088522036671846e-06, + "loss": 1.2578, + "step": 7738 + }, + { + "epoch": 0.81, + "learning_rate": 2.0862838661559535e-06, + "loss": 1.2898, + "step": 7739 + }, + { + "epoch": 0.81, + "learning_rate": 2.0840467558746837e-06, + "loss": 1.341, + "step": 7740 + }, + { + "epoch": 0.81, + "learning_rate": 2.0818107061277535e-06, + "loss": 1.3332, + "step": 7741 + }, + { + "epoch": 0.81, + "learning_rate": 2.0795757172147392e-06, + "loss": 1.2808, + "step": 7742 + }, + { + "epoch": 0.81, + "learning_rate": 2.077341789435071e-06, + "loss": 1.2795, + "step": 7743 + }, + { + "epoch": 0.81, + "learning_rate": 2.075108923088038e-06, + "loss": 1.3621, + "step": 7744 + }, + { + "epoch": 0.81, + "learning_rate": 2.0728771184727802e-06, + "loss": 1.3179, + "step": 7745 + }, + { + "epoch": 0.81, + "learning_rate": 2.0706463758883134e-06, + "loss": 1.2924, + "step": 7746 + }, + { + "epoch": 0.81, + "learning_rate": 2.0684166956334926e-06, + "loss": 1.3576, + "step": 7747 + }, + { + "epoch": 0.81, + "learning_rate": 2.066188078007039e-06, + "loss": 1.2692, + "step": 7748 + }, + { + "epoch": 0.81, + "learning_rate": 2.0639605233075277e-06, + "loss": 1.2994, + "step": 7749 + }, + { + "epoch": 0.81, + "learning_rate": 2.061734031833398e-06, + "loss": 1.278, + "step": 7750 + }, + { + "epoch": 0.81, + "learning_rate": 2.059508603882943e-06, + "loss": 1.2703, + "step": 7751 + }, + { + "epoch": 0.81, + "learning_rate": 2.0572842397543115e-06, + "loss": 1.2864, + "step": 7752 + }, + { + "epoch": 0.81, + "learning_rate": 2.0550609397455037e-06, + "loss": 1.3387, + "step": 7753 + }, + { + "epoch": 0.81, + "learning_rate": 2.0528387041543974e-06, + "loss": 1.5834, + "step": 7754 + }, + { + "epoch": 0.81, + "learning_rate": 2.0506175332787093e-06, + "loss": 1.2907, + "step": 7755 + }, + { + "epoch": 0.81, + "learning_rate": 2.048397427416016e-06, + "loss": 1.3015, + "step": 7756 + }, + { + "epoch": 0.81, + "learning_rate": 2.0461783868637573e-06, + "loss": 1.2329, + "step": 7757 + }, + { + "epoch": 0.81, + "learning_rate": 2.0439604119192314e-06, + "loss": 1.3166, + "step": 7758 + }, + { + "epoch": 0.81, + "learning_rate": 2.041743502879583e-06, + "loss": 1.2476, + "step": 7759 + }, + { + "epoch": 0.81, + "learning_rate": 2.039527660041828e-06, + "loss": 1.2766, + "step": 7760 + }, + { + "epoch": 0.81, + "learning_rate": 2.0373128837028233e-06, + "loss": 1.2738, + "step": 7761 + }, + { + "epoch": 0.81, + "eval_loss": 1.3951469659805298, + "eval_runtime": 77.4687, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 7761 + }, + { + "epoch": 0.81, + "learning_rate": 2.035099174159302e-06, + "loss": 1.3806, + "step": 7762 + }, + { + "epoch": 0.81, + "learning_rate": 2.0328865317078405e-06, + "loss": 1.2625, + "step": 7763 + }, + { + "epoch": 0.81, + "learning_rate": 2.0306749566448704e-06, + "loss": 1.2709, + "step": 7764 + }, + { + "epoch": 0.81, + "learning_rate": 2.028464449266696e-06, + "loss": 1.3029, + "step": 7765 + }, + { + "epoch": 0.81, + "learning_rate": 2.0262550098694634e-06, + "loss": 1.2867, + "step": 7766 + }, + { + "epoch": 0.81, + "learning_rate": 2.0240466387491774e-06, + "loss": 1.2818, + "step": 7767 + }, + { + "epoch": 0.81, + "learning_rate": 2.0218393362017076e-06, + "loss": 1.2627, + "step": 7768 + }, + { + "epoch": 0.81, + "learning_rate": 2.019633102522773e-06, + "loss": 1.2337, + "step": 7769 + }, + { + "epoch": 0.81, + "learning_rate": 2.0174279380079577e-06, + "loss": 1.4194, + "step": 7770 + }, + { + "epoch": 0.81, + "learning_rate": 2.0152238429526928e-06, + "loss": 1.487, + "step": 7771 + }, + { + "epoch": 0.82, + "learning_rate": 2.013020817652266e-06, + "loss": 1.2802, + "step": 7772 + }, + { + "epoch": 0.82, + "learning_rate": 2.0108188624018353e-06, + "loss": 1.2602, + "step": 7773 + }, + { + "epoch": 0.82, + "learning_rate": 2.008617977496402e-06, + "loss": 1.2986, + "step": 7774 + }, + { + "epoch": 0.82, + "learning_rate": 2.0064181632308244e-06, + "loss": 1.3053, + "step": 7775 + }, + { + "epoch": 0.82, + "learning_rate": 2.0042194198998256e-06, + "loss": 1.3052, + "step": 7776 + }, + { + "epoch": 0.82, + "learning_rate": 2.00202174779798e-06, + "loss": 1.247, + "step": 7777 + }, + { + "epoch": 0.82, + "learning_rate": 1.9998251472197192e-06, + "loss": 1.2762, + "step": 7778 + }, + { + "epoch": 0.82, + "learning_rate": 1.9976296184593335e-06, + "loss": 1.3518, + "step": 7779 + }, + { + "epoch": 0.82, + "learning_rate": 1.995435161810958e-06, + "loss": 1.4015, + "step": 7780 + }, + { + "epoch": 0.82, + "learning_rate": 1.9932417775686052e-06, + "loss": 1.3363, + "step": 7781 + }, + { + "epoch": 0.82, + "learning_rate": 1.991049466026128e-06, + "loss": 1.3039, + "step": 7782 + }, + { + "epoch": 0.82, + "learning_rate": 1.988858227477234e-06, + "loss": 1.3183, + "step": 7783 + }, + { + "epoch": 0.82, + "learning_rate": 1.986668062215502e-06, + "loss": 1.2852, + "step": 7784 + }, + { + "epoch": 0.82, + "learning_rate": 1.984478970534355e-06, + "loss": 1.2791, + "step": 7785 + }, + { + "epoch": 0.82, + "learning_rate": 1.9822909527270696e-06, + "loss": 1.3869, + "step": 7786 + }, + { + "epoch": 0.82, + "learning_rate": 1.9801040090867895e-06, + "loss": 1.3475, + "step": 7787 + }, + { + "epoch": 0.82, + "learning_rate": 1.9779181399065074e-06, + "loss": 1.2977, + "step": 7788 + }, + { + "epoch": 0.82, + "learning_rate": 1.975733345479076e-06, + "loss": 1.2244, + "step": 7789 + }, + { + "epoch": 0.82, + "learning_rate": 1.9735496260971996e-06, + "loss": 1.3136, + "step": 7790 + }, + { + "epoch": 0.82, + "learning_rate": 1.9713669820534352e-06, + "loss": 1.3647, + "step": 7791 + }, + { + "epoch": 0.82, + "learning_rate": 1.969185413640212e-06, + "loss": 1.3136, + "step": 7792 + }, + { + "epoch": 0.82, + "learning_rate": 1.9670049211497977e-06, + "loss": 1.3488, + "step": 7793 + }, + { + "epoch": 0.82, + "learning_rate": 1.9648255048743205e-06, + "loss": 1.3578, + "step": 7794 + }, + { + "epoch": 0.82, + "learning_rate": 1.9626471651057677e-06, + "loss": 1.325, + "step": 7795 + }, + { + "epoch": 0.82, + "learning_rate": 1.960469902135983e-06, + "loss": 1.3408, + "step": 7796 + }, + { + "epoch": 0.82, + "learning_rate": 1.958293716256664e-06, + "loss": 1.3439, + "step": 7797 + }, + { + "epoch": 0.82, + "learning_rate": 1.9561186077593617e-06, + "loss": 1.2767, + "step": 7798 + }, + { + "epoch": 0.82, + "learning_rate": 1.9539445769354814e-06, + "loss": 1.3756, + "step": 7799 + }, + { + "epoch": 0.82, + "learning_rate": 1.9517716240762953e-06, + "loss": 1.313, + "step": 7800 + }, + { + "epoch": 0.82, + "learning_rate": 1.949599749472919e-06, + "loss": 1.3103, + "step": 7801 + }, + { + "epoch": 0.82, + "learning_rate": 1.947428953416326e-06, + "loss": 1.3255, + "step": 7802 + }, + { + "epoch": 0.82, + "learning_rate": 1.945259236197348e-06, + "loss": 1.2959, + "step": 7803 + }, + { + "epoch": 0.82, + "learning_rate": 1.943090598106673e-06, + "loss": 1.2345, + "step": 7804 + }, + { + "epoch": 0.82, + "learning_rate": 1.9409230394348457e-06, + "loss": 1.2664, + "step": 7805 + }, + { + "epoch": 0.82, + "learning_rate": 1.938756560472256e-06, + "loss": 1.5172, + "step": 7806 + }, + { + "epoch": 0.82, + "learning_rate": 1.9365911615091615e-06, + "loss": 1.2878, + "step": 7807 + }, + { + "epoch": 0.82, + "learning_rate": 1.9344268428356707e-06, + "loss": 1.3419, + "step": 7808 + }, + { + "epoch": 0.82, + "learning_rate": 1.9322636047417444e-06, + "loss": 1.3464, + "step": 7809 + }, + { + "epoch": 0.82, + "learning_rate": 1.9301014475171964e-06, + "loss": 1.2695, + "step": 7810 + }, + { + "epoch": 0.82, + "learning_rate": 1.9279403714517098e-06, + "loss": 1.3551, + "step": 7811 + }, + { + "epoch": 0.82, + "learning_rate": 1.9257803768348092e-06, + "loss": 1.4498, + "step": 7812 + }, + { + "epoch": 0.82, + "learning_rate": 1.923621463955876e-06, + "loss": 1.4617, + "step": 7813 + }, + { + "epoch": 0.82, + "learning_rate": 1.9214636331041493e-06, + "loss": 1.6204, + "step": 7814 + }, + { + "epoch": 0.82, + "learning_rate": 1.9193068845687246e-06, + "loss": 1.3202, + "step": 7815 + }, + { + "epoch": 0.82, + "learning_rate": 1.9171512186385543e-06, + "loss": 1.293, + "step": 7816 + }, + { + "epoch": 0.82, + "learning_rate": 1.9149966356024387e-06, + "loss": 1.2511, + "step": 7817 + }, + { + "epoch": 0.82, + "learning_rate": 1.9128431357490296e-06, + "loss": 1.3643, + "step": 7818 + }, + { + "epoch": 0.82, + "learning_rate": 1.9106907193668543e-06, + "loss": 1.4159, + "step": 7819 + }, + { + "epoch": 0.82, + "learning_rate": 1.908539386744274e-06, + "loss": 1.2611, + "step": 7820 + }, + { + "epoch": 0.82, + "learning_rate": 1.9063891381695098e-06, + "loss": 1.3667, + "step": 7821 + }, + { + "epoch": 0.82, + "learning_rate": 1.9042399739306427e-06, + "loss": 1.3456, + "step": 7822 + }, + { + "epoch": 0.82, + "learning_rate": 1.9020918943156053e-06, + "loss": 1.4083, + "step": 7823 + }, + { + "epoch": 0.82, + "learning_rate": 1.8999448996121883e-06, + "loss": 1.3758, + "step": 7824 + }, + { + "epoch": 0.82, + "learning_rate": 1.8977989901080295e-06, + "loss": 1.2757, + "step": 7825 + }, + { + "epoch": 0.82, + "learning_rate": 1.8956541660906214e-06, + "loss": 1.3796, + "step": 7826 + }, + { + "epoch": 0.82, + "learning_rate": 1.893510427847327e-06, + "loss": 1.238, + "step": 7827 + }, + { + "epoch": 0.82, + "learning_rate": 1.8913677756653447e-06, + "loss": 1.3018, + "step": 7828 + }, + { + "epoch": 0.82, + "learning_rate": 1.8892262098317315e-06, + "loss": 1.2712, + "step": 7829 + }, + { + "epoch": 0.82, + "learning_rate": 1.8870857306334113e-06, + "loss": 1.3805, + "step": 7830 + }, + { + "epoch": 0.82, + "learning_rate": 1.8849463383571486e-06, + "loss": 1.3664, + "step": 7831 + }, + { + "epoch": 0.82, + "learning_rate": 1.8828080332895648e-06, + "loss": 1.3709, + "step": 7832 + }, + { + "epoch": 0.82, + "learning_rate": 1.8806708157171393e-06, + "loss": 1.3401, + "step": 7833 + }, + { + "epoch": 0.82, + "learning_rate": 1.8785346859262056e-06, + "loss": 1.3143, + "step": 7834 + }, + { + "epoch": 0.82, + "learning_rate": 1.876399644202952e-06, + "loss": 1.3432, + "step": 7835 + }, + { + "epoch": 0.82, + "learning_rate": 1.8742656908334178e-06, + "loss": 1.2945, + "step": 7836 + }, + { + "epoch": 0.82, + "learning_rate": 1.872132826103491e-06, + "loss": 1.402, + "step": 7837 + }, + { + "epoch": 0.82, + "learning_rate": 1.8700010502989318e-06, + "loss": 1.3004, + "step": 7838 + }, + { + "epoch": 0.82, + "learning_rate": 1.8678703637053386e-06, + "loss": 1.2766, + "step": 7839 + }, + { + "epoch": 0.82, + "learning_rate": 1.8657407666081661e-06, + "loss": 1.3629, + "step": 7840 + }, + { + "epoch": 0.82, + "learning_rate": 1.8636122592927275e-06, + "loss": 1.2527, + "step": 7841 + }, + { + "epoch": 0.82, + "learning_rate": 1.8614848420441888e-06, + "loss": 1.2711, + "step": 7842 + }, + { + "epoch": 0.82, + "learning_rate": 1.8593585151475713e-06, + "loss": 1.3419, + "step": 7843 + }, + { + "epoch": 0.82, + "learning_rate": 1.8572332788877456e-06, + "loss": 1.2953, + "step": 7844 + }, + { + "epoch": 0.82, + "learning_rate": 1.855109133549433e-06, + "loss": 1.2415, + "step": 7845 + }, + { + "epoch": 0.82, + "learning_rate": 1.8529860794172271e-06, + "loss": 1.2367, + "step": 7846 + }, + { + "epoch": 0.82, + "learning_rate": 1.8508641167755548e-06, + "loss": 1.3584, + "step": 7847 + }, + { + "epoch": 0.82, + "learning_rate": 1.848743245908703e-06, + "loss": 1.4259, + "step": 7848 + }, + { + "epoch": 0.82, + "learning_rate": 1.8466234671008165e-06, + "loss": 1.2903, + "step": 7849 + }, + { + "epoch": 0.82, + "learning_rate": 1.8445047806358918e-06, + "loss": 1.3204, + "step": 7850 + }, + { + "epoch": 0.82, + "learning_rate": 1.8423871867977806e-06, + "loss": 1.3938, + "step": 7851 + }, + { + "epoch": 0.82, + "learning_rate": 1.840270685870179e-06, + "loss": 1.2973, + "step": 7852 + }, + { + "epoch": 0.82, + "learning_rate": 1.8381552781366497e-06, + "loss": 1.3506, + "step": 7853 + }, + { + "epoch": 0.82, + "learning_rate": 1.8360409638806031e-06, + "loss": 1.3117, + "step": 7854 + }, + { + "epoch": 0.82, + "learning_rate": 1.833927743385302e-06, + "loss": 1.3072, + "step": 7855 + }, + { + "epoch": 0.82, + "learning_rate": 1.8318156169338562e-06, + "loss": 1.2965, + "step": 7856 + }, + { + "epoch": 0.82, + "learning_rate": 1.82970458480925e-06, + "loss": 1.3161, + "step": 7857 + }, + { + "epoch": 0.82, + "learning_rate": 1.8275946472942995e-06, + "loss": 1.3056, + "step": 7858 + }, + { + "epoch": 0.82, + "learning_rate": 1.8254858046716805e-06, + "loss": 1.249, + "step": 7859 + }, + { + "epoch": 0.82, + "learning_rate": 1.8233780572239268e-06, + "loss": 1.2689, + "step": 7860 + }, + { + "epoch": 0.82, + "learning_rate": 1.8212714052334213e-06, + "loss": 1.2919, + "step": 7861 + }, + { + "epoch": 0.82, + "learning_rate": 1.819165848982405e-06, + "loss": 1.3337, + "step": 7862 + }, + { + "epoch": 0.82, + "learning_rate": 1.8170613887529643e-06, + "loss": 1.2798, + "step": 7863 + }, + { + "epoch": 0.82, + "learning_rate": 1.8149580248270393e-06, + "loss": 1.3296, + "step": 7864 + }, + { + "epoch": 0.82, + "learning_rate": 1.812855757486437e-06, + "loss": 1.4615, + "step": 7865 + }, + { + "epoch": 0.82, + "learning_rate": 1.8107545870128008e-06, + "loss": 1.2883, + "step": 7866 + }, + { + "epoch": 0.82, + "learning_rate": 1.808654513687631e-06, + "loss": 1.3722, + "step": 7867 + }, + { + "epoch": 0.83, + "learning_rate": 1.8065555377922862e-06, + "loss": 1.3648, + "step": 7868 + }, + { + "epoch": 0.83, + "learning_rate": 1.8044576596079766e-06, + "loss": 1.2698, + "step": 7869 + }, + { + "epoch": 0.83, + "learning_rate": 1.8023608794157654e-06, + "loss": 1.3078, + "step": 7870 + }, + { + "epoch": 0.83, + "learning_rate": 1.8002651974965646e-06, + "loss": 1.3037, + "step": 7871 + }, + { + "epoch": 0.83, + "learning_rate": 1.7981706141311373e-06, + "loss": 1.2971, + "step": 7872 + }, + { + "epoch": 0.83, + "learning_rate": 1.7960771296001122e-06, + "loss": 1.3334, + "step": 7873 + }, + { + "epoch": 0.83, + "learning_rate": 1.7939847441839597e-06, + "loss": 1.3301, + "step": 7874 + }, + { + "epoch": 0.83, + "learning_rate": 1.7918934581629998e-06, + "loss": 1.2966, + "step": 7875 + }, + { + "epoch": 0.83, + "learning_rate": 1.7898032718174218e-06, + "loss": 1.3152, + "step": 7876 + }, + { + "epoch": 0.83, + "learning_rate": 1.7877141854272474e-06, + "loss": 1.2867, + "step": 7877 + }, + { + "epoch": 0.83, + "learning_rate": 1.7856261992723678e-06, + "loss": 1.3059, + "step": 7878 + }, + { + "epoch": 0.83, + "learning_rate": 1.783539313632513e-06, + "loss": 1.3425, + "step": 7879 + }, + { + "epoch": 0.83, + "learning_rate": 1.7814535287872748e-06, + "loss": 1.3513, + "step": 7880 + }, + { + "epoch": 0.83, + "learning_rate": 1.7793688450160983e-06, + "loss": 1.3208, + "step": 7881 + }, + { + "epoch": 0.83, + "learning_rate": 1.777285262598274e-06, + "loss": 1.302, + "step": 7882 + }, + { + "epoch": 0.83, + "learning_rate": 1.7752027818129424e-06, + "loss": 1.2783, + "step": 7883 + }, + { + "epoch": 0.83, + "learning_rate": 1.7731214029391153e-06, + "loss": 1.3599, + "step": 7884 + }, + { + "epoch": 0.83, + "learning_rate": 1.771041126255637e-06, + "loss": 1.2158, + "step": 7885 + }, + { + "epoch": 0.83, + "learning_rate": 1.7689619520412094e-06, + "loss": 1.3221, + "step": 7886 + }, + { + "epoch": 0.83, + "learning_rate": 1.7668838805743893e-06, + "loss": 1.3635, + "step": 7887 + }, + { + "epoch": 0.83, + "learning_rate": 1.7648069121335876e-06, + "loss": 1.2742, + "step": 7888 + }, + { + "epoch": 0.83, + "learning_rate": 1.762731046997065e-06, + "loss": 1.3333, + "step": 7889 + }, + { + "epoch": 0.83, + "learning_rate": 1.760656285442932e-06, + "loss": 1.2971, + "step": 7890 + }, + { + "epoch": 0.83, + "learning_rate": 1.7585826277491491e-06, + "loss": 1.3262, + "step": 7891 + }, + { + "epoch": 0.83, + "learning_rate": 1.7565100741935436e-06, + "loss": 1.38, + "step": 7892 + }, + { + "epoch": 0.83, + "learning_rate": 1.754438625053777e-06, + "loss": 1.3814, + "step": 7893 + }, + { + "epoch": 0.83, + "learning_rate": 1.7523682806073706e-06, + "loss": 1.2793, + "step": 7894 + }, + { + "epoch": 0.83, + "learning_rate": 1.7502990411316978e-06, + "loss": 1.266, + "step": 7895 + }, + { + "epoch": 0.83, + "learning_rate": 1.7482309069039838e-06, + "loss": 1.3085, + "step": 7896 + }, + { + "epoch": 0.83, + "learning_rate": 1.746163878201309e-06, + "loss": 1.3518, + "step": 7897 + }, + { + "epoch": 0.83, + "learning_rate": 1.7440979553005976e-06, + "loss": 1.3887, + "step": 7898 + }, + { + "epoch": 0.83, + "learning_rate": 1.7420331384786305e-06, + "loss": 1.3255, + "step": 7899 + }, + { + "epoch": 0.83, + "learning_rate": 1.7399694280120439e-06, + "loss": 1.3702, + "step": 7900 + }, + { + "epoch": 0.83, + "learning_rate": 1.7379068241773188e-06, + "loss": 1.3253, + "step": 7901 + }, + { + "epoch": 0.83, + "learning_rate": 1.735845327250788e-06, + "loss": 1.3055, + "step": 7902 + }, + { + "epoch": 0.83, + "learning_rate": 1.7337849375086468e-06, + "loss": 1.3119, + "step": 7903 + }, + { + "epoch": 0.83, + "learning_rate": 1.7317256552269278e-06, + "loss": 1.2741, + "step": 7904 + }, + { + "epoch": 0.83, + "learning_rate": 1.7296674806815273e-06, + "loss": 1.3101, + "step": 7905 + }, + { + "epoch": 0.83, + "learning_rate": 1.7276104141481832e-06, + "loss": 1.3553, + "step": 7906 + }, + { + "epoch": 0.83, + "learning_rate": 1.7255544559024906e-06, + "loss": 1.2712, + "step": 7907 + }, + { + "epoch": 0.83, + "learning_rate": 1.7234996062198994e-06, + "loss": 1.2814, + "step": 7908 + }, + { + "epoch": 0.83, + "learning_rate": 1.7214458653757027e-06, + "loss": 1.2831, + "step": 7909 + }, + { + "epoch": 0.83, + "learning_rate": 1.7193932336450437e-06, + "loss": 1.3519, + "step": 7910 + }, + { + "epoch": 0.83, + "learning_rate": 1.7173417113029334e-06, + "loss": 1.2559, + "step": 7911 + }, + { + "epoch": 0.83, + "learning_rate": 1.7152912986242187e-06, + "loss": 1.4204, + "step": 7912 + }, + { + "epoch": 0.83, + "learning_rate": 1.7132419958835978e-06, + "loss": 1.302, + "step": 7913 + }, + { + "epoch": 0.83, + "learning_rate": 1.7111938033556286e-06, + "loss": 1.2959, + "step": 7914 + }, + { + "epoch": 0.83, + "learning_rate": 1.7091467213147162e-06, + "loss": 1.3269, + "step": 7915 + }, + { + "epoch": 0.83, + "learning_rate": 1.7071007500351177e-06, + "loss": 1.2966, + "step": 7916 + }, + { + "epoch": 0.83, + "learning_rate": 1.705055889790941e-06, + "loss": 1.2696, + "step": 7917 + }, + { + "epoch": 0.83, + "learning_rate": 1.7030121408561373e-06, + "loss": 1.3431, + "step": 7918 + }, + { + "epoch": 0.83, + "learning_rate": 1.700969503504528e-06, + "loss": 1.2769, + "step": 7919 + }, + { + "epoch": 0.83, + "learning_rate": 1.698927978009769e-06, + "loss": 1.2543, + "step": 7920 + }, + { + "epoch": 0.83, + "learning_rate": 1.6968875646453665e-06, + "loss": 1.2612, + "step": 7921 + }, + { + "epoch": 0.83, + "learning_rate": 1.694848263684693e-06, + "loss": 1.322, + "step": 7922 + }, + { + "epoch": 0.83, + "learning_rate": 1.692810075400957e-06, + "loss": 1.4144, + "step": 7923 + }, + { + "epoch": 0.83, + "learning_rate": 1.6907730000672263e-06, + "loss": 1.4355, + "step": 7924 + }, + { + "epoch": 0.83, + "learning_rate": 1.6887370379564127e-06, + "loss": 1.4024, + "step": 7925 + }, + { + "epoch": 0.83, + "learning_rate": 1.686702189341285e-06, + "loss": 1.3015, + "step": 7926 + }, + { + "epoch": 0.83, + "learning_rate": 1.6846684544944625e-06, + "loss": 1.4337, + "step": 7927 + }, + { + "epoch": 0.83, + "learning_rate": 1.682635833688412e-06, + "loss": 1.3199, + "step": 7928 + }, + { + "epoch": 0.83, + "learning_rate": 1.6806043271954475e-06, + "loss": 1.2927, + "step": 7929 + }, + { + "epoch": 0.83, + "learning_rate": 1.6785739352877472e-06, + "loss": 1.4254, + "step": 7930 + }, + { + "epoch": 0.83, + "learning_rate": 1.676544658237328e-06, + "loss": 1.3653, + "step": 7931 + }, + { + "epoch": 0.83, + "learning_rate": 1.6745164963160576e-06, + "loss": 1.3049, + "step": 7932 + }, + { + "epoch": 0.83, + "learning_rate": 1.6724894497956613e-06, + "loss": 1.2474, + "step": 7933 + }, + { + "epoch": 0.83, + "learning_rate": 1.6704635189477091e-06, + "loss": 1.3146, + "step": 7934 + }, + { + "epoch": 0.83, + "learning_rate": 1.668438704043628e-06, + "loss": 1.2338, + "step": 7935 + }, + { + "epoch": 0.83, + "learning_rate": 1.666415005354688e-06, + "loss": 1.3217, + "step": 7936 + }, + { + "epoch": 0.83, + "learning_rate": 1.6643924231520082e-06, + "loss": 1.3776, + "step": 7937 + }, + { + "epoch": 0.83, + "learning_rate": 1.6623709577065715e-06, + "loss": 1.6173, + "step": 7938 + }, + { + "epoch": 0.83, + "learning_rate": 1.6603506092891975e-06, + "loss": 1.4383, + "step": 7939 + }, + { + "epoch": 0.83, + "learning_rate": 1.6583313781705602e-06, + "loss": 1.304, + "step": 7940 + }, + { + "epoch": 0.83, + "learning_rate": 1.6563132646211856e-06, + "loss": 1.4071, + "step": 7941 + }, + { + "epoch": 0.83, + "learning_rate": 1.6542962689114494e-06, + "loss": 1.3402, + "step": 7942 + }, + { + "epoch": 0.83, + "learning_rate": 1.6522803913115793e-06, + "loss": 1.3298, + "step": 7943 + }, + { + "epoch": 0.83, + "learning_rate": 1.6502656320916466e-06, + "loss": 1.4741, + "step": 7944 + }, + { + "epoch": 0.83, + "learning_rate": 1.64825199152158e-06, + "loss": 1.3373, + "step": 7945 + }, + { + "epoch": 0.83, + "learning_rate": 1.646239469871158e-06, + "loss": 1.6403, + "step": 7946 + }, + { + "epoch": 0.83, + "learning_rate": 1.644228067410004e-06, + "loss": 1.4887, + "step": 7947 + }, + { + "epoch": 0.83, + "learning_rate": 1.6422177844075893e-06, + "loss": 1.2763, + "step": 7948 + }, + { + "epoch": 0.83, + "learning_rate": 1.6402086211332502e-06, + "loss": 1.3298, + "step": 7949 + }, + { + "epoch": 0.83, + "learning_rate": 1.638200577856156e-06, + "loss": 1.3542, + "step": 7950 + }, + { + "epoch": 0.83, + "learning_rate": 1.6361936548453371e-06, + "loss": 1.2628, + "step": 7951 + }, + { + "epoch": 0.83, + "learning_rate": 1.6341878523696642e-06, + "loss": 1.3937, + "step": 7952 + }, + { + "epoch": 0.83, + "learning_rate": 1.6321831706978674e-06, + "loss": 1.2712, + "step": 7953 + }, + { + "epoch": 0.83, + "learning_rate": 1.6301796100985235e-06, + "loss": 1.3303, + "step": 7954 + }, + { + "epoch": 0.83, + "learning_rate": 1.6281771708400563e-06, + "loss": 1.2698, + "step": 7955 + }, + { + "epoch": 0.83, + "learning_rate": 1.6261758531907367e-06, + "loss": 1.3242, + "step": 7956 + }, + { + "epoch": 0.83, + "learning_rate": 1.6241756574186996e-06, + "loss": 1.2774, + "step": 7957 + }, + { + "epoch": 0.83, + "learning_rate": 1.6221765837919135e-06, + "loss": 1.3022, + "step": 7958 + }, + { + "epoch": 0.83, + "learning_rate": 1.620178632578202e-06, + "loss": 1.375, + "step": 7959 + }, + { + "epoch": 0.83, + "learning_rate": 1.6181818040452412e-06, + "loss": 1.308, + "step": 7960 + }, + { + "epoch": 0.83, + "eval_loss": 1.3948875665664673, + "eval_runtime": 77.4765, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 7960 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 3.561017847945206e+20, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-7960/training_args.bin b/checkpoint-7960/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-7960/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-8358/config.json b/checkpoint-8358/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-8358/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-8358/generation_config.json b/checkpoint-8358/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-8358/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-8358/model-00001-of-00003.safetensors b/checkpoint-8358/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..59849b15050fce999b446c2e4f9102f8b8436f81 --- /dev/null +++ b/checkpoint-8358/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfeedaecaedf7feafc86a94604cb8a120682e15eaf99069ac19eff5da40654dc +size 4943162336 diff --git a/checkpoint-8358/model-00002-of-00003.safetensors b/checkpoint-8358/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d04458e78801509f17eee40b757bbb6a8d7a1d1e --- /dev/null +++ b/checkpoint-8358/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5b455bb3191e625219fe87fc2b9e67761453848d3ddca7702307fbb039cea46 +size 4999819336 diff --git a/checkpoint-8358/model-00003-of-00003.safetensors b/checkpoint-8358/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9109ac7466199d782aa090e123ad43b3fa88b2c1 --- /dev/null +++ b/checkpoint-8358/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54a78756b6db9a4fa7c89181c15fe2c0254e2814bb4811d7df272d28bd187874 +size 4540516344 diff --git a/checkpoint-8358/model.safetensors.index.json b/checkpoint-8358/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-8358/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-8358/optimizer.pt b/checkpoint-8358/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..cdbf70a069686003849eb3d8d224744da6ee66e4 --- /dev/null +++ b/checkpoint-8358/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a985e9e410b7283a0a7ef6ef50c26c5cc586f8227fc2d8bec21106c94b02794 +size 14512103560 diff --git a/checkpoint-8358/rng_state_0.pth b/checkpoint-8358/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..2e2dee0cfec683d1e077694078d8e7cf92f6f90b --- /dev/null +++ b/checkpoint-8358/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:805714010bc1ef6feb7a19e304b61b2db0fe7d8a008ab4264246e0edf63db9c3 +size 15984 diff --git a/checkpoint-8358/rng_state_1.pth b/checkpoint-8358/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..9840e611951639e8112d5beb65cb0132ece23e4b --- /dev/null +++ b/checkpoint-8358/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ec5a6ac88cd8798685efe61c8de03e8771c9e88c650f5fc62eb8fd8d00d8152 +size 15984 diff --git a/checkpoint-8358/rng_state_2.pth b/checkpoint-8358/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..18be6df7fdf3a087a01605160cbc61170d0fc502 --- /dev/null +++ b/checkpoint-8358/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc6bf81e1605ee19ac20703a8e90b43c57515c4a6321f29182c72d0e536d2247 +size 15984 diff --git a/checkpoint-8358/rng_state_3.pth b/checkpoint-8358/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..877562609a848a0f0c590b0cf8575e401894cb23 --- /dev/null +++ b/checkpoint-8358/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e875bd349dc038285ddbc52c9661be01de5d95204fc6d87bd98db044153dc395 +size 15984 diff --git a/checkpoint-8358/rng_state_4.pth b/checkpoint-8358/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..8cf348df8fe51c914fe8e672ba5a32d9b9114a1f --- /dev/null +++ b/checkpoint-8358/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a36f8b6fb93a04988cf88a697ec5edf12298acb251e466771b830037447ef20 +size 15984 diff --git a/checkpoint-8358/rng_state_5.pth b/checkpoint-8358/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..7dec6cacf9be3f011b1b5adee6b29c1e227c1501 --- /dev/null +++ b/checkpoint-8358/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab3daa2ca22231b7a8b81336846e03b28d81d102300a04bc8fa98f460f00d5ca +size 15984 diff --git a/checkpoint-8358/rng_state_6.pth b/checkpoint-8358/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..24f2217217949e00b5cee59fb84ce8939cdd949a --- /dev/null +++ b/checkpoint-8358/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d783579e37bd90f6733a31456aa546fac2d49929aa765e5c4bec3b29e7a90eaa +size 15984 diff --git a/checkpoint-8358/rng_state_7.pth b/checkpoint-8358/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..b23c493c8f6b292c7b46da3067eba3e11fa6290a --- /dev/null +++ b/checkpoint-8358/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6f5735f8f8fff97617da6f1803ea8424f1352b8ea83cdd544389bff0f6f16fb +size 15984 diff --git a/checkpoint-8358/scheduler.pt b/checkpoint-8358/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..cdb5f9f4984e2b34d5ee2c65ccafc53ed6cffd2a --- /dev/null +++ b/checkpoint-8358/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c0407cb7fa83cf290e31a9051dd7ffac77bff4c16be819410e6600515460fab +size 1064 diff --git a/checkpoint-8358/special_tokens_map.json b/checkpoint-8358/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-8358/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-8358/tokenizer.model b/checkpoint-8358/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-8358/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-8358/tokenizer_config.json b/checkpoint-8358/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-8358/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-8358/trainer_state.json b/checkpoint-8358/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..2f979c6a88b090b765af51f9dd8dbefd89f74ce3 --- /dev/null +++ b/checkpoint-8358/trainer_state.json @@ -0,0 +1,50504 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.8764681208053692, + "eval_steps": 199, + "global_step": 8358, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + }, + { + "epoch": 0.21, + "learning_rate": 1.928689129323009e-05, + "loss": 1.421, + "step": 1991 + }, + { + "epoch": 0.21, + "learning_rate": 1.928553323396003e-05, + "loss": 1.5625, + "step": 1992 + }, + { + "epoch": 0.21, + "learning_rate": 1.92841739306671e-05, + "loss": 1.5198, + "step": 1993 + }, + { + "epoch": 0.21, + "learning_rate": 1.9282813383533415e-05, + "loss": 1.5116, + "step": 1994 + }, + { + "epoch": 0.21, + "learning_rate": 1.9281451592741247e-05, + "loss": 1.4306, + "step": 1995 + }, + { + "epoch": 0.21, + "learning_rate": 1.9280088558473046e-05, + "loss": 1.5425, + "step": 1996 + }, + { + "epoch": 0.21, + "learning_rate": 1.9278724280911424e-05, + "loss": 1.4972, + "step": 1997 + }, + { + "epoch": 0.21, + "learning_rate": 1.9277358760239156e-05, + "loss": 1.5185, + "step": 1998 + }, + { + "epoch": 0.21, + "learning_rate": 1.9275991996639188e-05, + "loss": 1.5187, + "step": 1999 + }, + { + "epoch": 0.21, + "learning_rate": 1.927462399029463e-05, + "loss": 1.4325, + "step": 2000 + }, + { + "epoch": 0.21, + "learning_rate": 1.9273254741388763e-05, + "loss": 1.4397, + "step": 2001 + }, + { + "epoch": 0.21, + "learning_rate": 1.927188425010503e-05, + "loss": 1.5319, + "step": 2002 + }, + { + "epoch": 0.21, + "learning_rate": 1.9270512516627042e-05, + "loss": 1.5664, + "step": 2003 + }, + { + "epoch": 0.21, + "learning_rate": 1.9269139541138574e-05, + "loss": 1.5227, + "step": 2004 + }, + { + "epoch": 0.21, + "learning_rate": 1.926776532382357e-05, + "loss": 1.5187, + "step": 2005 + }, + { + "epoch": 0.21, + "learning_rate": 1.9266389864866134e-05, + "loss": 1.4029, + "step": 2006 + }, + { + "epoch": 0.21, + "learning_rate": 1.9265013164450557e-05, + "loss": 1.387, + "step": 2007 + }, + { + "epoch": 0.21, + "learning_rate": 1.9263635222761268e-05, + "loss": 1.5047, + "step": 2008 + }, + { + "epoch": 0.21, + "learning_rate": 1.9262256039982882e-05, + "loss": 1.4816, + "step": 2009 + }, + { + "epoch": 0.21, + "learning_rate": 1.9260875616300172e-05, + "loss": 1.4607, + "step": 2010 + }, + { + "epoch": 0.21, + "learning_rate": 1.9259493951898084e-05, + "loss": 1.628, + "step": 2011 + }, + { + "epoch": 0.21, + "learning_rate": 1.9258111046961714e-05, + "loss": 1.4149, + "step": 2012 + }, + { + "epoch": 0.21, + "learning_rate": 1.925672690167635e-05, + "loss": 1.5303, + "step": 2013 + }, + { + "epoch": 0.21, + "learning_rate": 1.925534151622742e-05, + "loss": 1.5198, + "step": 2014 + }, + { + "epoch": 0.21, + "learning_rate": 1.9253954890800535e-05, + "loss": 1.6422, + "step": 2015 + }, + { + "epoch": 0.21, + "learning_rate": 1.925256702558147e-05, + "loss": 1.4738, + "step": 2016 + }, + { + "epoch": 0.21, + "learning_rate": 1.925117792075616e-05, + "loss": 1.4752, + "step": 2017 + }, + { + "epoch": 0.21, + "learning_rate": 1.9249787576510713e-05, + "loss": 1.4547, + "step": 2018 + }, + { + "epoch": 0.21, + "learning_rate": 1.924839599303139e-05, + "loss": 1.4864, + "step": 2019 + }, + { + "epoch": 0.21, + "learning_rate": 1.9247003170504638e-05, + "loss": 1.5037, + "step": 2020 + }, + { + "epoch": 0.21, + "learning_rate": 1.9245609109117053e-05, + "loss": 1.5089, + "step": 2021 + }, + { + "epoch": 0.21, + "learning_rate": 1.924421380905541e-05, + "loss": 1.5616, + "step": 2022 + }, + { + "epoch": 0.21, + "learning_rate": 1.9242817270506634e-05, + "loss": 1.4592, + "step": 2023 + }, + { + "epoch": 0.21, + "learning_rate": 1.9241419493657832e-05, + "loss": 1.5592, + "step": 2024 + }, + { + "epoch": 0.21, + "learning_rate": 1.924002047869627e-05, + "loss": 1.4897, + "step": 2025 + }, + { + "epoch": 0.21, + "learning_rate": 1.9238620225809375e-05, + "loss": 1.4743, + "step": 2026 + }, + { + "epoch": 0.21, + "learning_rate": 1.923721873518475e-05, + "loss": 1.4686, + "step": 2027 + }, + { + "epoch": 0.21, + "learning_rate": 1.923581600701016e-05, + "loss": 1.461, + "step": 2028 + }, + { + "epoch": 0.21, + "learning_rate": 1.9234412041473528e-05, + "loss": 1.6622, + "step": 2029 + }, + { + "epoch": 0.21, + "learning_rate": 1.9233006838762955e-05, + "loss": 1.4707, + "step": 2030 + }, + { + "epoch": 0.21, + "learning_rate": 1.92316003990667e-05, + "loss": 1.5566, + "step": 2031 + }, + { + "epoch": 0.21, + "learning_rate": 1.9230192722573188e-05, + "loss": 1.4881, + "step": 2032 + }, + { + "epoch": 0.21, + "learning_rate": 1.9228783809471015e-05, + "loss": 1.6124, + "step": 2033 + }, + { + "epoch": 0.21, + "learning_rate": 1.9227373659948937e-05, + "loss": 1.3508, + "step": 2034 + }, + { + "epoch": 0.21, + "learning_rate": 1.9225962274195876e-05, + "loss": 1.4418, + "step": 2035 + }, + { + "epoch": 0.21, + "learning_rate": 1.9224549652400927e-05, + "loss": 1.3954, + "step": 2036 + }, + { + "epoch": 0.21, + "learning_rate": 1.922313579475334e-05, + "loss": 1.4798, + "step": 2037 + }, + { + "epoch": 0.21, + "learning_rate": 1.922172070144254e-05, + "loss": 1.4556, + "step": 2038 + }, + { + "epoch": 0.21, + "learning_rate": 1.922030437265811e-05, + "loss": 1.4987, + "step": 2039 + }, + { + "epoch": 0.21, + "learning_rate": 1.9218886808589796e-05, + "loss": 1.4857, + "step": 2040 + }, + { + "epoch": 0.21, + "learning_rate": 1.9217468009427527e-05, + "loss": 1.5289, + "step": 2041 + }, + { + "epoch": 0.21, + "learning_rate": 1.921604797536138e-05, + "loss": 1.5267, + "step": 2042 + }, + { + "epoch": 0.21, + "learning_rate": 1.9214626706581598e-05, + "loss": 1.4655, + "step": 2043 + }, + { + "epoch": 0.21, + "learning_rate": 1.9213204203278602e-05, + "loss": 1.4598, + "step": 2044 + }, + { + "epoch": 0.21, + "learning_rate": 1.9211780465642973e-05, + "loss": 1.4766, + "step": 2045 + }, + { + "epoch": 0.21, + "learning_rate": 1.921035549386545e-05, + "loss": 1.5148, + "step": 2046 + }, + { + "epoch": 0.21, + "learning_rate": 1.9208929288136933e-05, + "loss": 1.5567, + "step": 2047 + }, + { + "epoch": 0.21, + "learning_rate": 1.920750184864852e-05, + "loss": 1.4868, + "step": 2048 + }, + { + "epoch": 0.21, + "learning_rate": 1.920607317559143e-05, + "loss": 1.4752, + "step": 2049 + }, + { + "epoch": 0.21, + "learning_rate": 1.920464326915708e-05, + "loss": 1.4882, + "step": 2050 + }, + { + "epoch": 0.22, + "learning_rate": 1.9203212129537035e-05, + "loss": 1.5933, + "step": 2051 + }, + { + "epoch": 0.22, + "learning_rate": 1.9201779756923037e-05, + "loss": 1.4891, + "step": 2052 + }, + { + "epoch": 0.22, + "learning_rate": 1.9200346151506983e-05, + "loss": 1.4486, + "step": 2053 + }, + { + "epoch": 0.22, + "learning_rate": 1.9198911313480938e-05, + "loss": 1.5091, + "step": 2054 + }, + { + "epoch": 0.22, + "learning_rate": 1.919747524303714e-05, + "loss": 1.4385, + "step": 2055 + }, + { + "epoch": 0.22, + "learning_rate": 1.9196037940367974e-05, + "loss": 1.4104, + "step": 2056 + }, + { + "epoch": 0.22, + "learning_rate": 1.9194599405666015e-05, + "loss": 1.4483, + "step": 2057 + }, + { + "epoch": 0.22, + "learning_rate": 1.9193159639123976e-05, + "loss": 1.4592, + "step": 2058 + }, + { + "epoch": 0.22, + "learning_rate": 1.919171864093476e-05, + "loss": 1.4975, + "step": 2059 + }, + { + "epoch": 0.22, + "learning_rate": 1.9190276411291423e-05, + "loss": 1.4727, + "step": 2060 + }, + { + "epoch": 0.22, + "learning_rate": 1.9188832950387178e-05, + "loss": 1.4791, + "step": 2061 + }, + { + "epoch": 0.22, + "learning_rate": 1.9187388258415423e-05, + "loss": 1.3806, + "step": 2062 + }, + { + "epoch": 0.22, + "learning_rate": 1.9185942335569697e-05, + "loss": 1.4514, + "step": 2063 + }, + { + "epoch": 0.22, + "learning_rate": 1.9184495182043727e-05, + "loss": 1.4389, + "step": 2064 + }, + { + "epoch": 0.22, + "learning_rate": 1.918304679803139e-05, + "loss": 1.5088, + "step": 2065 + }, + { + "epoch": 0.22, + "learning_rate": 1.9181597183726733e-05, + "loss": 1.4665, + "step": 2066 + }, + { + "epoch": 0.22, + "learning_rate": 1.9180146339323966e-05, + "loss": 1.489, + "step": 2067 + }, + { + "epoch": 0.22, + "learning_rate": 1.9178694265017466e-05, + "loss": 1.5215, + "step": 2068 + }, + { + "epoch": 0.22, + "learning_rate": 1.9177240961001775e-05, + "loss": 1.5152, + "step": 2069 + }, + { + "epoch": 0.22, + "learning_rate": 1.9175786427471594e-05, + "loss": 1.4418, + "step": 2070 + }, + { + "epoch": 0.22, + "learning_rate": 1.91743306646218e-05, + "loss": 1.5001, + "step": 2071 + }, + { + "epoch": 0.22, + "learning_rate": 1.9172873672647417e-05, + "loss": 1.4879, + "step": 2072 + }, + { + "epoch": 0.22, + "learning_rate": 1.917141545174366e-05, + "loss": 1.5299, + "step": 2073 + }, + { + "epoch": 0.22, + "learning_rate": 1.9169956002105877e-05, + "loss": 1.4602, + "step": 2074 + }, + { + "epoch": 0.22, + "learning_rate": 1.9168495323929605e-05, + "loss": 1.4921, + "step": 2075 + }, + { + "epoch": 0.22, + "learning_rate": 1.916703341741054e-05, + "loss": 1.4659, + "step": 2076 + }, + { + "epoch": 0.22, + "learning_rate": 1.9165570282744534e-05, + "loss": 1.4707, + "step": 2077 + }, + { + "epoch": 0.22, + "learning_rate": 1.9164105920127613e-05, + "loss": 1.5354, + "step": 2078 + }, + { + "epoch": 0.22, + "learning_rate": 1.9162640329755962e-05, + "loss": 1.526, + "step": 2079 + }, + { + "epoch": 0.22, + "learning_rate": 1.916117351182593e-05, + "loss": 1.6424, + "step": 2080 + }, + { + "epoch": 0.22, + "learning_rate": 1.915970546653404e-05, + "loss": 1.5048, + "step": 2081 + }, + { + "epoch": 0.22, + "learning_rate": 1.915823619407697e-05, + "loss": 1.5344, + "step": 2082 + }, + { + "epoch": 0.22, + "learning_rate": 1.915676569465156e-05, + "loss": 1.4604, + "step": 2083 + }, + { + "epoch": 0.22, + "learning_rate": 1.9155293968454826e-05, + "loss": 1.4929, + "step": 2084 + }, + { + "epoch": 0.22, + "learning_rate": 1.9153821015683937e-05, + "loss": 1.4106, + "step": 2085 + }, + { + "epoch": 0.22, + "learning_rate": 1.915234683653623e-05, + "loss": 1.4146, + "step": 2086 + }, + { + "epoch": 0.22, + "learning_rate": 1.9150871431209207e-05, + "loss": 1.4481, + "step": 2087 + }, + { + "epoch": 0.22, + "learning_rate": 1.914939479990054e-05, + "loss": 1.5206, + "step": 2088 + }, + { + "epoch": 0.22, + "learning_rate": 1.9147916942808054e-05, + "loss": 1.5073, + "step": 2089 + }, + { + "epoch": 0.22, + "learning_rate": 1.9146437860129745e-05, + "loss": 1.5196, + "step": 2090 + }, + { + "epoch": 0.22, + "learning_rate": 1.9144957552063775e-05, + "loss": 1.5389, + "step": 2091 + }, + { + "epoch": 0.22, + "learning_rate": 1.9143476018808463e-05, + "loss": 1.5207, + "step": 2092 + }, + { + "epoch": 0.22, + "learning_rate": 1.9141993260562298e-05, + "loss": 1.3717, + "step": 2093 + }, + { + "epoch": 0.22, + "learning_rate": 1.9140509277523937e-05, + "loss": 1.471, + "step": 2094 + }, + { + "epoch": 0.22, + "learning_rate": 1.9139024069892185e-05, + "loss": 1.4553, + "step": 2095 + }, + { + "epoch": 0.22, + "learning_rate": 1.9137537637866027e-05, + "loss": 1.5311, + "step": 2096 + }, + { + "epoch": 0.22, + "learning_rate": 1.9136049981644614e-05, + "loss": 1.4369, + "step": 2097 + }, + { + "epoch": 0.22, + "learning_rate": 1.913456110142724e-05, + "loss": 1.4528, + "step": 2098 + }, + { + "epoch": 0.22, + "learning_rate": 1.9133070997413384e-05, + "loss": 1.5294, + "step": 2099 + }, + { + "epoch": 0.22, + "learning_rate": 1.9131579669802685e-05, + "loss": 1.4588, + "step": 2100 + }, + { + "epoch": 0.22, + "learning_rate": 1.9130087118794934e-05, + "loss": 1.443, + "step": 2101 + }, + { + "epoch": 0.22, + "learning_rate": 1.9128593344590102e-05, + "loss": 1.4876, + "step": 2102 + }, + { + "epoch": 0.22, + "learning_rate": 1.912709834738831e-05, + "loss": 1.4874, + "step": 2103 + }, + { + "epoch": 0.22, + "learning_rate": 1.9125602127389856e-05, + "loss": 1.4966, + "step": 2104 + }, + { + "epoch": 0.22, + "learning_rate": 1.912410468479519e-05, + "loss": 1.5747, + "step": 2105 + }, + { + "epoch": 0.22, + "learning_rate": 1.9122606019804933e-05, + "loss": 1.4025, + "step": 2106 + }, + { + "epoch": 0.22, + "learning_rate": 1.912110613261987e-05, + "loss": 1.4755, + "step": 2107 + }, + { + "epoch": 0.22, + "learning_rate": 1.911960502344094e-05, + "loss": 1.4739, + "step": 2108 + }, + { + "epoch": 0.22, + "learning_rate": 1.911810269246926e-05, + "loss": 1.4992, + "step": 2109 + }, + { + "epoch": 0.22, + "learning_rate": 1.91165991399061e-05, + "loss": 1.4435, + "step": 2110 + }, + { + "epoch": 0.22, + "learning_rate": 1.91150943659529e-05, + "loss": 1.4918, + "step": 2111 + }, + { + "epoch": 0.22, + "learning_rate": 1.9113588370811258e-05, + "loss": 1.3818, + "step": 2112 + }, + { + "epoch": 0.22, + "learning_rate": 1.911208115468294e-05, + "loss": 1.5105, + "step": 2113 + }, + { + "epoch": 0.22, + "learning_rate": 1.9110572717769878e-05, + "loss": 1.6634, + "step": 2114 + }, + { + "epoch": 0.22, + "learning_rate": 1.9109063060274158e-05, + "loss": 1.5028, + "step": 2115 + }, + { + "epoch": 0.22, + "learning_rate": 1.9107552182398037e-05, + "loss": 1.6657, + "step": 2116 + }, + { + "epoch": 0.22, + "learning_rate": 1.9106040084343935e-05, + "loss": 1.5481, + "step": 2117 + }, + { + "epoch": 0.22, + "learning_rate": 1.910452676631444e-05, + "loss": 1.4505, + "step": 2118 + }, + { + "epoch": 0.22, + "learning_rate": 1.9103012228512284e-05, + "loss": 1.5173, + "step": 2119 + }, + { + "epoch": 0.22, + "learning_rate": 1.9101496471140385e-05, + "loss": 1.3788, + "step": 2120 + }, + { + "epoch": 0.22, + "learning_rate": 1.9099979494401814e-05, + "loss": 1.4649, + "step": 2121 + }, + { + "epoch": 0.22, + "learning_rate": 1.9098461298499805e-05, + "loss": 1.4204, + "step": 2122 + }, + { + "epoch": 0.22, + "learning_rate": 1.9096941883637766e-05, + "loss": 1.4439, + "step": 2123 + }, + { + "epoch": 0.22, + "learning_rate": 1.909542125001925e-05, + "loss": 1.6615, + "step": 2124 + }, + { + "epoch": 0.22, + "learning_rate": 1.9093899397847985e-05, + "loss": 1.4763, + "step": 2125 + }, + { + "epoch": 0.22, + "learning_rate": 1.909237632732786e-05, + "loss": 1.5353, + "step": 2126 + }, + { + "epoch": 0.22, + "learning_rate": 1.909085203866293e-05, + "loss": 1.442, + "step": 2127 + }, + { + "epoch": 0.22, + "learning_rate": 1.9089326532057408e-05, + "loss": 1.4782, + "step": 2128 + }, + { + "epoch": 0.22, + "learning_rate": 1.908779980771567e-05, + "loss": 1.4933, + "step": 2129 + }, + { + "epoch": 0.22, + "learning_rate": 1.9086271865842264e-05, + "loss": 1.5285, + "step": 2130 + }, + { + "epoch": 0.22, + "learning_rate": 1.9084742706641894e-05, + "loss": 1.4736, + "step": 2131 + }, + { + "epoch": 0.22, + "learning_rate": 1.9083212330319427e-05, + "loss": 1.4496, + "step": 2132 + }, + { + "epoch": 0.22, + "learning_rate": 1.908168073707989e-05, + "loss": 1.5099, + "step": 2133 + }, + { + "epoch": 0.22, + "learning_rate": 1.9080147927128483e-05, + "loss": 1.5235, + "step": 2134 + }, + { + "epoch": 0.22, + "learning_rate": 1.9078613900670556e-05, + "loss": 1.4769, + "step": 2135 + }, + { + "epoch": 0.22, + "learning_rate": 1.907707865791164e-05, + "loss": 1.5771, + "step": 2136 + }, + { + "epoch": 0.22, + "learning_rate": 1.907554219905741e-05, + "loss": 1.5116, + "step": 2137 + }, + { + "epoch": 0.22, + "learning_rate": 1.907400452431371e-05, + "loss": 1.5161, + "step": 2138 + }, + { + "epoch": 0.22, + "learning_rate": 1.9072465633886557e-05, + "loss": 1.4356, + "step": 2139 + }, + { + "epoch": 0.22, + "learning_rate": 1.9070925527982117e-05, + "loss": 1.509, + "step": 2140 + }, + { + "epoch": 0.22, + "learning_rate": 1.9069384206806723e-05, + "loss": 1.4681, + "step": 2141 + }, + { + "epoch": 0.22, + "learning_rate": 1.9067841670566883e-05, + "loss": 1.5254, + "step": 2142 + }, + { + "epoch": 0.22, + "learning_rate": 1.9066297919469242e-05, + "loss": 1.4797, + "step": 2143 + }, + { + "epoch": 0.22, + "learning_rate": 1.9064752953720636e-05, + "loss": 1.3996, + "step": 2144 + }, + { + "epoch": 0.22, + "learning_rate": 1.9063206773528042e-05, + "loss": 1.4457, + "step": 2145 + }, + { + "epoch": 0.23, + "learning_rate": 1.9061659379098617e-05, + "loss": 1.5126, + "step": 2146 + }, + { + "epoch": 0.23, + "learning_rate": 1.9060110770639664e-05, + "loss": 1.5925, + "step": 2147 + }, + { + "epoch": 0.23, + "learning_rate": 1.905856094835866e-05, + "loss": 1.5146, + "step": 2148 + }, + { + "epoch": 0.23, + "learning_rate": 1.905700991246324e-05, + "loss": 1.7256, + "step": 2149 + }, + { + "epoch": 0.23, + "learning_rate": 1.90554576631612e-05, + "loss": 1.57, + "step": 2150 + }, + { + "epoch": 0.23, + "learning_rate": 1.905390420066051e-05, + "loss": 1.3722, + "step": 2151 + }, + { + "epoch": 0.23, + "learning_rate": 1.9052349525169292e-05, + "loss": 1.3999, + "step": 2152 + }, + { + "epoch": 0.23, + "learning_rate": 1.9050793636895828e-05, + "loss": 1.586, + "step": 2153 + }, + { + "epoch": 0.23, + "learning_rate": 1.9049236536048567e-05, + "loss": 1.4884, + "step": 2154 + }, + { + "epoch": 0.23, + "learning_rate": 1.9047678222836127e-05, + "loss": 1.5898, + "step": 2155 + }, + { + "epoch": 0.23, + "learning_rate": 1.9046118697467278e-05, + "loss": 1.569, + "step": 2156 + }, + { + "epoch": 0.23, + "learning_rate": 1.904455796015095e-05, + "loss": 1.5592, + "step": 2157 + }, + { + "epoch": 0.23, + "learning_rate": 1.9042996011096253e-05, + "loss": 1.597, + "step": 2158 + }, + { + "epoch": 0.23, + "learning_rate": 1.904143285051244e-05, + "loss": 1.422, + "step": 2159 + }, + { + "epoch": 0.23, + "learning_rate": 1.903986847860894e-05, + "loss": 1.519, + "step": 2160 + }, + { + "epoch": 0.23, + "learning_rate": 1.9038302895595334e-05, + "loss": 1.5197, + "step": 2161 + }, + { + "epoch": 0.23, + "learning_rate": 1.903673610168137e-05, + "loss": 1.4655, + "step": 2162 + }, + { + "epoch": 0.23, + "learning_rate": 1.9035168097076965e-05, + "loss": 1.3909, + "step": 2163 + }, + { + "epoch": 0.23, + "learning_rate": 1.903359888199218e-05, + "loss": 1.4877, + "step": 2164 + }, + { + "epoch": 0.23, + "learning_rate": 1.903202845663726e-05, + "loss": 1.5123, + "step": 2165 + }, + { + "epoch": 0.23, + "learning_rate": 1.9030456821222593e-05, + "loss": 1.4906, + "step": 2166 + }, + { + "epoch": 0.23, + "learning_rate": 1.9028883975958745e-05, + "loss": 1.4574, + "step": 2167 + }, + { + "epoch": 0.23, + "learning_rate": 1.9027309921056435e-05, + "loss": 1.4571, + "step": 2168 + }, + { + "epoch": 0.23, + "learning_rate": 1.902573465672654e-05, + "loss": 1.4281, + "step": 2169 + }, + { + "epoch": 0.23, + "learning_rate": 1.9024158183180116e-05, + "loss": 1.5057, + "step": 2170 + }, + { + "epoch": 0.23, + "learning_rate": 1.902258050062836e-05, + "loss": 1.4514, + "step": 2171 + }, + { + "epoch": 0.23, + "learning_rate": 1.9021001609282646e-05, + "loss": 1.5055, + "step": 2172 + }, + { + "epoch": 0.23, + "learning_rate": 1.9019421509354505e-05, + "loss": 1.4578, + "step": 2173 + }, + { + "epoch": 0.23, + "learning_rate": 1.9017840201055625e-05, + "loss": 1.459, + "step": 2174 + }, + { + "epoch": 0.23, + "learning_rate": 1.9016257684597864e-05, + "loss": 1.5059, + "step": 2175 + }, + { + "epoch": 0.23, + "learning_rate": 1.901467396019324e-05, + "loss": 1.57, + "step": 2176 + }, + { + "epoch": 0.23, + "learning_rate": 1.901308902805393e-05, + "loss": 1.4924, + "step": 2177 + }, + { + "epoch": 0.23, + "learning_rate": 1.9011502888392273e-05, + "loss": 1.4979, + "step": 2178 + }, + { + "epoch": 0.23, + "learning_rate": 1.900991554142077e-05, + "loss": 1.5321, + "step": 2179 + }, + { + "epoch": 0.23, + "learning_rate": 1.9008326987352093e-05, + "loss": 1.493, + "step": 2180 + }, + { + "epoch": 0.23, + "learning_rate": 1.9006737226399056e-05, + "loss": 1.5111, + "step": 2181 + }, + { + "epoch": 0.23, + "learning_rate": 1.900514625877465e-05, + "loss": 1.4154, + "step": 2182 + }, + { + "epoch": 0.23, + "learning_rate": 1.900355408469203e-05, + "loss": 1.4934, + "step": 2183 + }, + { + "epoch": 0.23, + "learning_rate": 1.90019607043645e-05, + "loss": 1.5975, + "step": 2184 + }, + { + "epoch": 0.23, + "learning_rate": 1.9000366118005532e-05, + "loss": 1.3537, + "step": 2185 + }, + { + "epoch": 0.23, + "learning_rate": 1.899877032582876e-05, + "loss": 1.4583, + "step": 2186 + }, + { + "epoch": 0.23, + "learning_rate": 1.8997173328047984e-05, + "loss": 1.4586, + "step": 2187 + }, + { + "epoch": 0.23, + "learning_rate": 1.8995575124877156e-05, + "loss": 1.4774, + "step": 2188 + }, + { + "epoch": 0.23, + "learning_rate": 1.8993975716530394e-05, + "loss": 1.5025, + "step": 2189 + }, + { + "epoch": 0.23, + "eval_loss": 1.5263344049453735, + "eval_runtime": 77.1492, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 2189 + }, + { + "epoch": 0.23, + "learning_rate": 1.899237510322198e-05, + "loss": 1.5438, + "step": 2190 + }, + { + "epoch": 0.23, + "learning_rate": 1.899077328516635e-05, + "loss": 1.5181, + "step": 2191 + }, + { + "epoch": 0.23, + "learning_rate": 1.8989170262578112e-05, + "loss": 1.4454, + "step": 2192 + }, + { + "epoch": 0.23, + "learning_rate": 1.8987566035672028e-05, + "loss": 1.4882, + "step": 2193 + }, + { + "epoch": 0.23, + "learning_rate": 1.8985960604663026e-05, + "loss": 1.5073, + "step": 2194 + }, + { + "epoch": 0.23, + "learning_rate": 1.8984353969766187e-05, + "loss": 1.4478, + "step": 2195 + }, + { + "epoch": 0.23, + "learning_rate": 1.8982746131196763e-05, + "loss": 1.4768, + "step": 2196 + }, + { + "epoch": 0.23, + "learning_rate": 1.8981137089170162e-05, + "loss": 1.5116, + "step": 2197 + }, + { + "epoch": 0.23, + "learning_rate": 1.8979526843901952e-05, + "loss": 1.4202, + "step": 2198 + }, + { + "epoch": 0.23, + "learning_rate": 1.8977915395607867e-05, + "loss": 1.4736, + "step": 2199 + }, + { + "epoch": 0.23, + "learning_rate": 1.89763027445038e-05, + "loss": 1.4489, + "step": 2200 + }, + { + "epoch": 0.23, + "learning_rate": 1.8974688890805804e-05, + "loss": 1.4512, + "step": 2201 + }, + { + "epoch": 0.23, + "learning_rate": 1.897307383473009e-05, + "loss": 1.5091, + "step": 2202 + }, + { + "epoch": 0.23, + "learning_rate": 1.897145757649304e-05, + "loss": 1.5512, + "step": 2203 + }, + { + "epoch": 0.23, + "learning_rate": 1.8969840116311192e-05, + "loss": 1.406, + "step": 2204 + }, + { + "epoch": 0.23, + "learning_rate": 1.896822145440124e-05, + "loss": 1.4531, + "step": 2205 + }, + { + "epoch": 0.23, + "learning_rate": 1.896660159098004e-05, + "loss": 1.4379, + "step": 2206 + }, + { + "epoch": 0.23, + "learning_rate": 1.896498052626462e-05, + "loss": 1.4783, + "step": 2207 + }, + { + "epoch": 0.23, + "learning_rate": 1.896335826047216e-05, + "loss": 1.4801, + "step": 2208 + }, + { + "epoch": 0.23, + "learning_rate": 1.896173479381999e-05, + "loss": 1.4526, + "step": 2209 + }, + { + "epoch": 0.23, + "learning_rate": 1.8960110126525627e-05, + "loss": 1.4952, + "step": 2210 + }, + { + "epoch": 0.23, + "learning_rate": 1.895848425880673e-05, + "loss": 1.5299, + "step": 2211 + }, + { + "epoch": 0.23, + "learning_rate": 1.8956857190881125e-05, + "loss": 1.5274, + "step": 2212 + }, + { + "epoch": 0.23, + "learning_rate": 1.8955228922966792e-05, + "loss": 1.4415, + "step": 2213 + }, + { + "epoch": 0.23, + "learning_rate": 1.8953599455281884e-05, + "loss": 1.5311, + "step": 2214 + }, + { + "epoch": 0.23, + "learning_rate": 1.8951968788044702e-05, + "loss": 1.4972, + "step": 2215 + }, + { + "epoch": 0.23, + "learning_rate": 1.8950336921473715e-05, + "loss": 1.4966, + "step": 2216 + }, + { + "epoch": 0.23, + "learning_rate": 1.8948703855787553e-05, + "loss": 1.4683, + "step": 2217 + }, + { + "epoch": 0.23, + "learning_rate": 1.8947069591205005e-05, + "loss": 1.503, + "step": 2218 + }, + { + "epoch": 0.23, + "learning_rate": 1.8945434127945014e-05, + "loss": 1.4902, + "step": 2219 + }, + { + "epoch": 0.23, + "learning_rate": 1.8943797466226702e-05, + "loss": 1.4835, + "step": 2220 + }, + { + "epoch": 0.23, + "learning_rate": 1.8942159606269332e-05, + "loss": 1.535, + "step": 2221 + }, + { + "epoch": 0.23, + "learning_rate": 1.8940520548292332e-05, + "loss": 1.491, + "step": 2222 + }, + { + "epoch": 0.23, + "learning_rate": 1.89388802925153e-05, + "loss": 1.5157, + "step": 2223 + }, + { + "epoch": 0.23, + "learning_rate": 1.8937238839157987e-05, + "loss": 1.4779, + "step": 2224 + }, + { + "epoch": 0.23, + "learning_rate": 1.8935596188440302e-05, + "loss": 1.4902, + "step": 2225 + }, + { + "epoch": 0.23, + "learning_rate": 1.8933952340582323e-05, + "loss": 1.4988, + "step": 2226 + }, + { + "epoch": 0.23, + "learning_rate": 1.893230729580428e-05, + "loss": 1.4568, + "step": 2227 + }, + { + "epoch": 0.23, + "learning_rate": 1.8930661054326567e-05, + "loss": 1.5163, + "step": 2228 + }, + { + "epoch": 0.23, + "learning_rate": 1.892901361636974e-05, + "loss": 1.4472, + "step": 2229 + }, + { + "epoch": 0.23, + "learning_rate": 1.892736498215451e-05, + "loss": 1.4658, + "step": 2230 + }, + { + "epoch": 0.23, + "learning_rate": 1.8925715151901754e-05, + "loss": 1.4281, + "step": 2231 + }, + { + "epoch": 0.23, + "learning_rate": 1.892406412583251e-05, + "loss": 1.415, + "step": 2232 + }, + { + "epoch": 0.23, + "learning_rate": 1.8922411904167966e-05, + "loss": 1.464, + "step": 2233 + }, + { + "epoch": 0.23, + "learning_rate": 1.892075848712948e-05, + "loss": 1.5014, + "step": 2234 + }, + { + "epoch": 0.23, + "learning_rate": 1.8919103874938568e-05, + "loss": 1.4397, + "step": 2235 + }, + { + "epoch": 0.23, + "learning_rate": 1.891744806781691e-05, + "loss": 1.5508, + "step": 2236 + }, + { + "epoch": 0.23, + "learning_rate": 1.8915791065986335e-05, + "loss": 1.4749, + "step": 2237 + }, + { + "epoch": 0.23, + "learning_rate": 1.891413286966884e-05, + "loss": 1.4538, + "step": 2238 + }, + { + "epoch": 0.23, + "learning_rate": 1.891247347908658e-05, + "loss": 1.4405, + "step": 2239 + }, + { + "epoch": 0.23, + "learning_rate": 1.8910812894461878e-05, + "loss": 1.3562, + "step": 2240 + }, + { + "epoch": 0.24, + "learning_rate": 1.89091511160172e-05, + "loss": 1.4811, + "step": 2241 + }, + { + "epoch": 0.24, + "learning_rate": 1.8907488143975186e-05, + "loss": 1.4286, + "step": 2242 + }, + { + "epoch": 0.24, + "learning_rate": 1.890582397855863e-05, + "loss": 1.4493, + "step": 2243 + }, + { + "epoch": 0.24, + "learning_rate": 1.890415861999049e-05, + "loss": 1.5639, + "step": 2244 + }, + { + "epoch": 0.24, + "learning_rate": 1.890249206849388e-05, + "loss": 1.6375, + "step": 2245 + }, + { + "epoch": 0.24, + "learning_rate": 1.890082432429208e-05, + "loss": 1.4982, + "step": 2246 + }, + { + "epoch": 0.24, + "learning_rate": 1.889915538760851e-05, + "loss": 1.492, + "step": 2247 + }, + { + "epoch": 0.24, + "learning_rate": 1.8897485258666778e-05, + "loss": 1.4294, + "step": 2248 + }, + { + "epoch": 0.24, + "learning_rate": 1.8895813937690638e-05, + "loss": 1.4617, + "step": 2249 + }, + { + "epoch": 0.24, + "learning_rate": 1.8894141424904e-05, + "loss": 1.4763, + "step": 2250 + }, + { + "epoch": 0.24, + "learning_rate": 1.8892467720530937e-05, + "loss": 1.3989, + "step": 2251 + }, + { + "epoch": 0.24, + "learning_rate": 1.8890792824795687e-05, + "loss": 1.4803, + "step": 2252 + }, + { + "epoch": 0.24, + "learning_rate": 1.8889116737922638e-05, + "loss": 1.4734, + "step": 2253 + }, + { + "epoch": 0.24, + "learning_rate": 1.8887439460136342e-05, + "loss": 1.5069, + "step": 2254 + }, + { + "epoch": 0.24, + "learning_rate": 1.8885760991661514e-05, + "loss": 1.5565, + "step": 2255 + }, + { + "epoch": 0.24, + "learning_rate": 1.8884081332723028e-05, + "loss": 1.4707, + "step": 2256 + }, + { + "epoch": 0.24, + "learning_rate": 1.8882400483545913e-05, + "loss": 1.5077, + "step": 2257 + }, + { + "epoch": 0.24, + "learning_rate": 1.888071844435536e-05, + "loss": 1.5075, + "step": 2258 + }, + { + "epoch": 0.24, + "learning_rate": 1.8879035215376717e-05, + "loss": 1.5185, + "step": 2259 + }, + { + "epoch": 0.24, + "learning_rate": 1.887735079683549e-05, + "loss": 1.6266, + "step": 2260 + }, + { + "epoch": 0.24, + "learning_rate": 1.8875665188957354e-05, + "loss": 1.5013, + "step": 2261 + }, + { + "epoch": 0.24, + "learning_rate": 1.887397839196814e-05, + "loss": 1.4362, + "step": 2262 + }, + { + "epoch": 0.24, + "learning_rate": 1.8872290406093827e-05, + "loss": 1.4718, + "step": 2263 + }, + { + "epoch": 0.24, + "learning_rate": 1.8870601231560567e-05, + "loss": 1.5202, + "step": 2264 + }, + { + "epoch": 0.24, + "learning_rate": 1.8868910868594664e-05, + "loss": 1.5168, + "step": 2265 + }, + { + "epoch": 0.24, + "learning_rate": 1.8867219317422588e-05, + "loss": 1.5142, + "step": 2266 + }, + { + "epoch": 0.24, + "learning_rate": 1.8865526578270954e-05, + "loss": 1.4885, + "step": 2267 + }, + { + "epoch": 0.24, + "learning_rate": 1.8863832651366552e-05, + "loss": 1.5441, + "step": 2268 + }, + { + "epoch": 0.24, + "learning_rate": 1.8862137536936328e-05, + "loss": 1.4647, + "step": 2269 + }, + { + "epoch": 0.24, + "learning_rate": 1.8860441235207374e-05, + "loss": 1.5352, + "step": 2270 + }, + { + "epoch": 0.24, + "learning_rate": 1.8858743746406958e-05, + "loss": 1.4568, + "step": 2271 + }, + { + "epoch": 0.24, + "learning_rate": 1.8857045070762497e-05, + "loss": 1.4865, + "step": 2272 + }, + { + "epoch": 0.24, + "learning_rate": 1.8855345208501573e-05, + "loss": 1.4637, + "step": 2273 + }, + { + "epoch": 0.24, + "learning_rate": 1.8853644159851918e-05, + "loss": 1.4348, + "step": 2274 + }, + { + "epoch": 0.24, + "learning_rate": 1.8851941925041436e-05, + "loss": 1.4413, + "step": 2275 + }, + { + "epoch": 0.24, + "learning_rate": 1.8850238504298177e-05, + "loss": 1.4434, + "step": 2276 + }, + { + "epoch": 0.24, + "learning_rate": 1.884853389785036e-05, + "loss": 1.4822, + "step": 2277 + }, + { + "epoch": 0.24, + "learning_rate": 1.8846828105926356e-05, + "loss": 1.4632, + "step": 2278 + }, + { + "epoch": 0.24, + "learning_rate": 1.8845121128754698e-05, + "loss": 1.48, + "step": 2279 + }, + { + "epoch": 0.24, + "learning_rate": 1.8843412966564078e-05, + "loss": 1.4518, + "step": 2280 + }, + { + "epoch": 0.24, + "learning_rate": 1.884170361958334e-05, + "loss": 1.4334, + "step": 2281 + }, + { + "epoch": 0.24, + "learning_rate": 1.8839993088041502e-05, + "loss": 1.5131, + "step": 2282 + }, + { + "epoch": 0.24, + "learning_rate": 1.8838281372167724e-05, + "loss": 1.508, + "step": 2283 + }, + { + "epoch": 0.24, + "learning_rate": 1.8836568472191335e-05, + "loss": 1.4086, + "step": 2284 + }, + { + "epoch": 0.24, + "learning_rate": 1.883485438834182e-05, + "loss": 1.5021, + "step": 2285 + }, + { + "epoch": 0.24, + "learning_rate": 1.8833139120848817e-05, + "loss": 1.5083, + "step": 2286 + }, + { + "epoch": 0.24, + "learning_rate": 1.8831422669942137e-05, + "loss": 1.4162, + "step": 2287 + }, + { + "epoch": 0.24, + "learning_rate": 1.8829705035851734e-05, + "loss": 1.5494, + "step": 2288 + }, + { + "epoch": 0.24, + "learning_rate": 1.8827986218807724e-05, + "loss": 1.425, + "step": 2289 + }, + { + "epoch": 0.24, + "learning_rate": 1.8826266219040396e-05, + "loss": 1.5215, + "step": 2290 + }, + { + "epoch": 0.24, + "learning_rate": 1.8824545036780172e-05, + "loss": 1.5577, + "step": 2291 + }, + { + "epoch": 0.24, + "learning_rate": 1.8822822672257655e-05, + "loss": 1.4923, + "step": 2292 + }, + { + "epoch": 0.24, + "learning_rate": 1.8821099125703595e-05, + "loss": 1.4648, + "step": 2293 + }, + { + "epoch": 0.24, + "learning_rate": 1.8819374397348902e-05, + "loss": 1.471, + "step": 2294 + }, + { + "epoch": 0.24, + "learning_rate": 1.8817648487424648e-05, + "loss": 1.5658, + "step": 2295 + }, + { + "epoch": 0.24, + "learning_rate": 1.8815921396162058e-05, + "loss": 1.5348, + "step": 2296 + }, + { + "epoch": 0.24, + "learning_rate": 1.8814193123792518e-05, + "loss": 1.4081, + "step": 2297 + }, + { + "epoch": 0.24, + "learning_rate": 1.881246367054757e-05, + "loss": 1.4762, + "step": 2298 + }, + { + "epoch": 0.24, + "learning_rate": 1.8810733036658925e-05, + "loss": 1.4399, + "step": 2299 + }, + { + "epoch": 0.24, + "learning_rate": 1.8809001222358432e-05, + "loss": 1.4763, + "step": 2300 + }, + { + "epoch": 0.24, + "learning_rate": 1.880726822787812e-05, + "loss": 1.4874, + "step": 2301 + }, + { + "epoch": 0.24, + "learning_rate": 1.880553405345016e-05, + "loss": 1.4951, + "step": 2302 + }, + { + "epoch": 0.24, + "learning_rate": 1.8803798699306887e-05, + "loss": 1.4697, + "step": 2303 + }, + { + "epoch": 0.24, + "learning_rate": 1.880206216568079e-05, + "loss": 1.481, + "step": 2304 + }, + { + "epoch": 0.24, + "learning_rate": 1.880032445280453e-05, + "loss": 1.4485, + "step": 2305 + }, + { + "epoch": 0.24, + "learning_rate": 1.879858556091091e-05, + "loss": 1.4749, + "step": 2306 + }, + { + "epoch": 0.24, + "learning_rate": 1.8796845490232894e-05, + "loss": 1.5605, + "step": 2307 + }, + { + "epoch": 0.24, + "learning_rate": 1.879510424100361e-05, + "loss": 1.4835, + "step": 2308 + }, + { + "epoch": 0.24, + "learning_rate": 1.8793361813456346e-05, + "loss": 1.4344, + "step": 2309 + }, + { + "epoch": 0.24, + "learning_rate": 1.8791618207824532e-05, + "loss": 1.4571, + "step": 2310 + }, + { + "epoch": 0.24, + "learning_rate": 1.8789873424341772e-05, + "loss": 1.482, + "step": 2311 + }, + { + "epoch": 0.24, + "learning_rate": 1.8788127463241822e-05, + "loss": 1.4736, + "step": 2312 + }, + { + "epoch": 0.24, + "learning_rate": 1.8786380324758597e-05, + "loss": 1.4807, + "step": 2313 + }, + { + "epoch": 0.24, + "learning_rate": 1.8784632009126167e-05, + "loss": 1.4418, + "step": 2314 + }, + { + "epoch": 0.24, + "learning_rate": 1.878288251657876e-05, + "loss": 1.5248, + "step": 2315 + }, + { + "epoch": 0.24, + "learning_rate": 1.8781131847350768e-05, + "loss": 1.483, + "step": 2316 + }, + { + "epoch": 0.24, + "learning_rate": 1.877938000167673e-05, + "loss": 1.5474, + "step": 2317 + }, + { + "epoch": 0.24, + "learning_rate": 1.8777626979791347e-05, + "loss": 1.4671, + "step": 2318 + }, + { + "epoch": 0.24, + "learning_rate": 1.877587278192949e-05, + "loss": 1.3049, + "step": 2319 + }, + { + "epoch": 0.24, + "learning_rate": 1.877411740832616e-05, + "loss": 1.483, + "step": 2320 + }, + { + "epoch": 0.24, + "learning_rate": 1.877236085921655e-05, + "loss": 1.508, + "step": 2321 + }, + { + "epoch": 0.24, + "learning_rate": 1.8770603134835978e-05, + "loss": 1.4854, + "step": 2322 + }, + { + "epoch": 0.24, + "learning_rate": 1.8768844235419942e-05, + "loss": 1.4808, + "step": 2323 + }, + { + "epoch": 0.24, + "learning_rate": 1.8767084161204087e-05, + "loss": 1.5352, + "step": 2324 + }, + { + "epoch": 0.24, + "learning_rate": 1.8765322912424214e-05, + "loss": 1.5628, + "step": 2325 + }, + { + "epoch": 0.24, + "learning_rate": 1.8763560489316292e-05, + "loss": 1.494, + "step": 2326 + }, + { + "epoch": 0.24, + "learning_rate": 1.876179689211643e-05, + "loss": 1.509, + "step": 2327 + }, + { + "epoch": 0.24, + "learning_rate": 1.8760032121060918e-05, + "loss": 1.5021, + "step": 2328 + }, + { + "epoch": 0.24, + "learning_rate": 1.875826617638618e-05, + "loss": 1.4179, + "step": 2329 + }, + { + "epoch": 0.24, + "learning_rate": 1.8756499058328813e-05, + "loss": 1.4302, + "step": 2330 + }, + { + "epoch": 0.24, + "learning_rate": 1.8754730767125564e-05, + "loss": 1.4959, + "step": 2331 + }, + { + "epoch": 0.24, + "learning_rate": 1.8752961303013336e-05, + "loss": 1.4423, + "step": 2332 + }, + { + "epoch": 0.24, + "learning_rate": 1.8751190666229194e-05, + "loss": 1.4564, + "step": 2333 + }, + { + "epoch": 0.24, + "learning_rate": 1.8749418857010358e-05, + "loss": 1.4775, + "step": 2334 + }, + { + "epoch": 0.24, + "learning_rate": 1.8747645875594203e-05, + "loss": 1.4182, + "step": 2335 + }, + { + "epoch": 0.24, + "learning_rate": 1.8745871722218265e-05, + "loss": 1.3957, + "step": 2336 + }, + { + "epoch": 0.25, + "learning_rate": 1.8744096397120235e-05, + "loss": 1.4633, + "step": 2337 + }, + { + "epoch": 0.25, + "learning_rate": 1.874231990053796e-05, + "loss": 1.5512, + "step": 2338 + }, + { + "epoch": 0.25, + "learning_rate": 1.8740542232709444e-05, + "loss": 1.3461, + "step": 2339 + }, + { + "epoch": 0.25, + "learning_rate": 1.8738763393872848e-05, + "loss": 1.4754, + "step": 2340 + }, + { + "epoch": 0.25, + "learning_rate": 1.8736983384266495e-05, + "loss": 1.5448, + "step": 2341 + }, + { + "epoch": 0.25, + "learning_rate": 1.8735202204128854e-05, + "loss": 1.4491, + "step": 2342 + }, + { + "epoch": 0.25, + "learning_rate": 1.8733419853698566e-05, + "loss": 1.457, + "step": 2343 + }, + { + "epoch": 0.25, + "learning_rate": 1.8731636333214414e-05, + "loss": 1.4314, + "step": 2344 + }, + { + "epoch": 0.25, + "learning_rate": 1.8729851642915345e-05, + "loss": 1.3979, + "step": 2345 + }, + { + "epoch": 0.25, + "learning_rate": 1.8728065783040464e-05, + "loss": 1.4146, + "step": 2346 + }, + { + "epoch": 0.25, + "learning_rate": 1.8726278753829027e-05, + "loss": 1.4361, + "step": 2347 + }, + { + "epoch": 0.25, + "learning_rate": 1.872449055552045e-05, + "loss": 1.4989, + "step": 2348 + }, + { + "epoch": 0.25, + "learning_rate": 1.872270118835431e-05, + "loss": 1.5062, + "step": 2349 + }, + { + "epoch": 0.25, + "learning_rate": 1.872091065257033e-05, + "loss": 1.4509, + "step": 2350 + }, + { + "epoch": 0.25, + "learning_rate": 1.8719118948408403e-05, + "loss": 1.4631, + "step": 2351 + }, + { + "epoch": 0.25, + "learning_rate": 1.8717326076108566e-05, + "loss": 1.5119, + "step": 2352 + }, + { + "epoch": 0.25, + "learning_rate": 1.8715532035911017e-05, + "loss": 1.6347, + "step": 2353 + }, + { + "epoch": 0.25, + "learning_rate": 1.8713736828056115e-05, + "loss": 1.5526, + "step": 2354 + }, + { + "epoch": 0.25, + "learning_rate": 1.8711940452784368e-05, + "loss": 1.6348, + "step": 2355 + }, + { + "epoch": 0.25, + "learning_rate": 1.871014291033645e-05, + "loss": 1.5183, + "step": 2356 + }, + { + "epoch": 0.25, + "learning_rate": 1.8708344200953182e-05, + "loss": 1.458, + "step": 2357 + }, + { + "epoch": 0.25, + "learning_rate": 1.8706544324875545e-05, + "loss": 1.524, + "step": 2358 + }, + { + "epoch": 0.25, + "learning_rate": 1.8704743282344672e-05, + "loss": 1.4479, + "step": 2359 + }, + { + "epoch": 0.25, + "learning_rate": 1.870294107360186e-05, + "loss": 1.5408, + "step": 2360 + }, + { + "epoch": 0.25, + "learning_rate": 1.8701137698888563e-05, + "loss": 1.5007, + "step": 2361 + }, + { + "epoch": 0.25, + "learning_rate": 1.8699333158446382e-05, + "loss": 1.5132, + "step": 2362 + }, + { + "epoch": 0.25, + "learning_rate": 1.869752745251708e-05, + "loss": 1.4263, + "step": 2363 + }, + { + "epoch": 0.25, + "learning_rate": 1.8695720581342574e-05, + "loss": 1.422, + "step": 2364 + }, + { + "epoch": 0.25, + "learning_rate": 1.869391254516494e-05, + "loss": 1.4411, + "step": 2365 + }, + { + "epoch": 0.25, + "learning_rate": 1.8692103344226406e-05, + "loss": 1.4594, + "step": 2366 + }, + { + "epoch": 0.25, + "learning_rate": 1.8690292978769364e-05, + "loss": 1.4992, + "step": 2367 + }, + { + "epoch": 0.25, + "learning_rate": 1.868848144903635e-05, + "loss": 1.4822, + "step": 2368 + }, + { + "epoch": 0.25, + "learning_rate": 1.8686668755270064e-05, + "loss": 1.5402, + "step": 2369 + }, + { + "epoch": 0.25, + "learning_rate": 1.8684854897713363e-05, + "loss": 1.5268, + "step": 2370 + }, + { + "epoch": 0.25, + "learning_rate": 1.8683039876609258e-05, + "loss": 1.5587, + "step": 2371 + }, + { + "epoch": 0.25, + "learning_rate": 1.868122369220091e-05, + "loss": 1.4214, + "step": 2372 + }, + { + "epoch": 0.25, + "learning_rate": 1.8679406344731645e-05, + "loss": 1.5089, + "step": 2373 + }, + { + "epoch": 0.25, + "learning_rate": 1.867758783444494e-05, + "loss": 1.5067, + "step": 2374 + }, + { + "epoch": 0.25, + "learning_rate": 1.8675768161584427e-05, + "loss": 2.0616, + "step": 2375 + }, + { + "epoch": 0.25, + "learning_rate": 1.8673947326393903e-05, + "loss": 1.5617, + "step": 2376 + }, + { + "epoch": 0.25, + "learning_rate": 1.86721253291173e-05, + "loss": 1.4422, + "step": 2377 + }, + { + "epoch": 0.25, + "learning_rate": 1.867030216999873e-05, + "loss": 1.4727, + "step": 2378 + }, + { + "epoch": 0.25, + "learning_rate": 1.8668477849282443e-05, + "loss": 1.4152, + "step": 2379 + }, + { + "epoch": 0.25, + "learning_rate": 1.8666652367212856e-05, + "loss": 1.4376, + "step": 2380 + }, + { + "epoch": 0.25, + "learning_rate": 1.8664825724034534e-05, + "loss": 1.393, + "step": 2381 + }, + { + "epoch": 0.25, + "learning_rate": 1.8662997919992197e-05, + "loss": 1.4864, + "step": 2382 + }, + { + "epoch": 0.25, + "learning_rate": 1.866116895533073e-05, + "loss": 1.4261, + "step": 2383 + }, + { + "epoch": 0.25, + "learning_rate": 1.8659338830295163e-05, + "loss": 1.4555, + "step": 2384 + }, + { + "epoch": 0.25, + "learning_rate": 1.8657507545130687e-05, + "loss": 1.4939, + "step": 2385 + }, + { + "epoch": 0.25, + "learning_rate": 1.865567510008265e-05, + "loss": 1.4123, + "step": 2386 + }, + { + "epoch": 0.25, + "learning_rate": 1.8653841495396546e-05, + "loss": 1.4459, + "step": 2387 + }, + { + "epoch": 0.25, + "learning_rate": 1.8652006731318038e-05, + "loss": 1.396, + "step": 2388 + }, + { + "epoch": 0.25, + "eval_loss": 1.5139706134796143, + "eval_runtime": 77.2904, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 2388 + }, + { + "epoch": 0.25, + "learning_rate": 1.8650170808092936e-05, + "loss": 1.4666, + "step": 2389 + }, + { + "epoch": 0.25, + "learning_rate": 1.86483337259672e-05, + "loss": 1.5154, + "step": 2390 + }, + { + "epoch": 0.25, + "learning_rate": 1.864649548518696e-05, + "loss": 1.5163, + "step": 2391 + }, + { + "epoch": 0.25, + "learning_rate": 1.864465608599849e-05, + "loss": 1.4734, + "step": 2392 + }, + { + "epoch": 0.25, + "learning_rate": 1.864281552864822e-05, + "loss": 1.5217, + "step": 2393 + }, + { + "epoch": 0.25, + "learning_rate": 1.8640973813382737e-05, + "loss": 1.4694, + "step": 2394 + }, + { + "epoch": 0.25, + "learning_rate": 1.863913094044879e-05, + "loss": 1.4761, + "step": 2395 + }, + { + "epoch": 0.25, + "learning_rate": 1.863728691009327e-05, + "loss": 1.4766, + "step": 2396 + }, + { + "epoch": 0.25, + "learning_rate": 1.863544172256323e-05, + "loss": 1.5695, + "step": 2397 + }, + { + "epoch": 0.25, + "learning_rate": 1.8633595378105882e-05, + "loss": 1.5079, + "step": 2398 + }, + { + "epoch": 0.25, + "learning_rate": 1.8631747876968584e-05, + "loss": 1.4154, + "step": 2399 + }, + { + "epoch": 0.25, + "learning_rate": 1.862989921939886e-05, + "loss": 1.4488, + "step": 2400 + }, + { + "epoch": 0.25, + "learning_rate": 1.8628049405644376e-05, + "loss": 1.4279, + "step": 2401 + }, + { + "epoch": 0.25, + "learning_rate": 1.8626198435952966e-05, + "loss": 1.4896, + "step": 2402 + }, + { + "epoch": 0.25, + "learning_rate": 1.8624346310572602e-05, + "loss": 1.4315, + "step": 2403 + }, + { + "epoch": 0.25, + "learning_rate": 1.862249302975143e-05, + "loss": 1.4919, + "step": 2404 + }, + { + "epoch": 0.25, + "learning_rate": 1.8620638593737743e-05, + "loss": 1.4561, + "step": 2405 + }, + { + "epoch": 0.25, + "learning_rate": 1.8618783002779985e-05, + "loss": 1.4622, + "step": 2406 + }, + { + "epoch": 0.25, + "learning_rate": 1.8616926257126754e-05, + "loss": 1.4917, + "step": 2407 + }, + { + "epoch": 0.25, + "learning_rate": 1.861506835702681e-05, + "loss": 1.4962, + "step": 2408 + }, + { + "epoch": 0.25, + "learning_rate": 1.861320930272906e-05, + "loss": 1.4164, + "step": 2409 + }, + { + "epoch": 0.25, + "learning_rate": 1.8611349094482578e-05, + "loss": 1.4889, + "step": 2410 + }, + { + "epoch": 0.25, + "learning_rate": 1.8609487732536576e-05, + "loss": 1.543, + "step": 2411 + }, + { + "epoch": 0.25, + "learning_rate": 1.8607625217140433e-05, + "loss": 1.5417, + "step": 2412 + }, + { + "epoch": 0.25, + "learning_rate": 1.8605761548543674e-05, + "loss": 1.5304, + "step": 2413 + }, + { + "epoch": 0.25, + "learning_rate": 1.860389672699599e-05, + "loss": 1.4725, + "step": 2414 + }, + { + "epoch": 0.25, + "learning_rate": 1.860203075274721e-05, + "loss": 1.4745, + "step": 2415 + }, + { + "epoch": 0.25, + "learning_rate": 1.8600163626047334e-05, + "loss": 1.4656, + "step": 2416 + }, + { + "epoch": 0.25, + "learning_rate": 1.8598295347146503e-05, + "loss": 1.5287, + "step": 2417 + }, + { + "epoch": 0.25, + "learning_rate": 1.8596425916295023e-05, + "loss": 1.5024, + "step": 2418 + }, + { + "epoch": 0.25, + "learning_rate": 1.8594555333743348e-05, + "loss": 1.4527, + "step": 2419 + }, + { + "epoch": 0.25, + "learning_rate": 1.859268359974209e-05, + "loss": 1.4897, + "step": 2420 + }, + { + "epoch": 0.25, + "learning_rate": 1.859081071454201e-05, + "loss": 1.3554, + "step": 2421 + }, + { + "epoch": 0.25, + "learning_rate": 1.858893667839403e-05, + "loss": 1.4004, + "step": 2422 + }, + { + "epoch": 0.25, + "learning_rate": 1.858706149154922e-05, + "loss": 1.5582, + "step": 2423 + }, + { + "epoch": 0.25, + "learning_rate": 1.8585185154258803e-05, + "loss": 1.505, + "step": 2424 + }, + { + "epoch": 0.25, + "learning_rate": 1.858330766677417e-05, + "loss": 1.5043, + "step": 2425 + }, + { + "epoch": 0.25, + "learning_rate": 1.858142902934685e-05, + "loss": 1.439, + "step": 2426 + }, + { + "epoch": 0.25, + "learning_rate": 1.857954924222853e-05, + "loss": 1.4927, + "step": 2427 + }, + { + "epoch": 0.25, + "learning_rate": 1.8577668305671056e-05, + "loss": 1.5395, + "step": 2428 + }, + { + "epoch": 0.25, + "learning_rate": 1.8575786219926427e-05, + "loss": 1.4737, + "step": 2429 + }, + { + "epoch": 0.25, + "learning_rate": 1.8573902985246794e-05, + "loss": 1.6151, + "step": 2430 + }, + { + "epoch": 0.25, + "learning_rate": 1.857201860188446e-05, + "loss": 1.4313, + "step": 2431 + }, + { + "epoch": 0.26, + "learning_rate": 1.857013307009188e-05, + "loss": 1.4509, + "step": 2432 + }, + { + "epoch": 0.26, + "learning_rate": 1.8568246390121673e-05, + "loss": 1.3998, + "step": 2433 + }, + { + "epoch": 0.26, + "learning_rate": 1.8566358562226603e-05, + "loss": 1.5268, + "step": 2434 + }, + { + "epoch": 0.26, + "learning_rate": 1.8564469586659593e-05, + "loss": 1.4369, + "step": 2435 + }, + { + "epoch": 0.26, + "learning_rate": 1.8562579463673713e-05, + "loss": 1.4759, + "step": 2436 + }, + { + "epoch": 0.26, + "learning_rate": 1.8560688193522197e-05, + "loss": 1.4092, + "step": 2437 + }, + { + "epoch": 0.26, + "learning_rate": 1.855879577645842e-05, + "loss": 1.43, + "step": 2438 + }, + { + "epoch": 0.26, + "learning_rate": 1.855690221273592e-05, + "loss": 1.5143, + "step": 2439 + }, + { + "epoch": 0.26, + "learning_rate": 1.8555007502608385e-05, + "loss": 1.5482, + "step": 2440 + }, + { + "epoch": 0.26, + "learning_rate": 1.855311164632966e-05, + "loss": 1.4406, + "step": 2441 + }, + { + "epoch": 0.26, + "learning_rate": 1.8551214644153738e-05, + "loss": 1.4551, + "step": 2442 + }, + { + "epoch": 0.26, + "learning_rate": 1.8549316496334774e-05, + "loss": 1.4663, + "step": 2443 + }, + { + "epoch": 0.26, + "learning_rate": 1.8547417203127064e-05, + "loss": 1.4732, + "step": 2444 + }, + { + "epoch": 0.26, + "learning_rate": 1.8545516764785067e-05, + "loss": 1.5378, + "step": 2445 + }, + { + "epoch": 0.26, + "learning_rate": 1.8543615181563397e-05, + "loss": 1.4448, + "step": 2446 + }, + { + "epoch": 0.26, + "learning_rate": 1.854171245371681e-05, + "loss": 1.2861, + "step": 2447 + }, + { + "epoch": 0.26, + "learning_rate": 1.8539808581500228e-05, + "loss": 1.4405, + "step": 2448 + }, + { + "epoch": 0.26, + "learning_rate": 1.8537903565168716e-05, + "loss": 1.4876, + "step": 2449 + }, + { + "epoch": 0.26, + "learning_rate": 1.8535997404977506e-05, + "loss": 1.4119, + "step": 2450 + }, + { + "epoch": 0.26, + "learning_rate": 1.8534090101181967e-05, + "loss": 1.4451, + "step": 2451 + }, + { + "epoch": 0.26, + "learning_rate": 1.8532181654037632e-05, + "loss": 1.4035, + "step": 2452 + }, + { + "epoch": 0.26, + "learning_rate": 1.853027206380018e-05, + "loss": 1.4624, + "step": 2453 + }, + { + "epoch": 0.26, + "learning_rate": 1.852836133072545e-05, + "loss": 1.4935, + "step": 2454 + }, + { + "epoch": 0.26, + "learning_rate": 1.8526449455069434e-05, + "loss": 1.4834, + "step": 2455 + }, + { + "epoch": 0.26, + "learning_rate": 1.8524536437088266e-05, + "loss": 1.498, + "step": 2456 + }, + { + "epoch": 0.26, + "learning_rate": 1.8522622277038247e-05, + "loss": 1.3417, + "step": 2457 + }, + { + "epoch": 0.26, + "learning_rate": 1.852070697517583e-05, + "loss": 1.4455, + "step": 2458 + }, + { + "epoch": 0.26, + "learning_rate": 1.8518790531757607e-05, + "loss": 1.4119, + "step": 2459 + }, + { + "epoch": 0.26, + "learning_rate": 1.8516872947040337e-05, + "loss": 1.558, + "step": 2460 + }, + { + "epoch": 0.26, + "learning_rate": 1.8514954221280926e-05, + "loss": 1.4862, + "step": 2461 + }, + { + "epoch": 0.26, + "learning_rate": 1.8513034354736433e-05, + "loss": 1.6806, + "step": 2462 + }, + { + "epoch": 0.26, + "learning_rate": 1.8511113347664072e-05, + "loss": 1.438, + "step": 2463 + }, + { + "epoch": 0.26, + "learning_rate": 1.850919120032121e-05, + "loss": 1.4975, + "step": 2464 + }, + { + "epoch": 0.26, + "learning_rate": 1.850726791296536e-05, + "loss": 1.4409, + "step": 2465 + }, + { + "epoch": 0.26, + "learning_rate": 1.85053434858542e-05, + "loss": 1.4769, + "step": 2466 + }, + { + "epoch": 0.26, + "learning_rate": 1.8503417919245548e-05, + "loss": 1.5823, + "step": 2467 + }, + { + "epoch": 0.26, + "learning_rate": 1.8501491213397386e-05, + "loss": 1.4045, + "step": 2468 + }, + { + "epoch": 0.26, + "learning_rate": 1.8499563368567837e-05, + "loss": 1.4828, + "step": 2469 + }, + { + "epoch": 0.26, + "learning_rate": 1.849763438501519e-05, + "loss": 1.4684, + "step": 2470 + }, + { + "epoch": 0.26, + "learning_rate": 1.8495704262997873e-05, + "loss": 1.4577, + "step": 2471 + }, + { + "epoch": 0.26, + "learning_rate": 1.8493773002774475e-05, + "loss": 1.4759, + "step": 2472 + }, + { + "epoch": 0.26, + "learning_rate": 1.8491840604603736e-05, + "loss": 1.4259, + "step": 2473 + }, + { + "epoch": 0.26, + "learning_rate": 1.8489907068744543e-05, + "loss": 1.4717, + "step": 2474 + }, + { + "epoch": 0.26, + "learning_rate": 1.848797239545595e-05, + "loss": 1.4247, + "step": 2475 + }, + { + "epoch": 0.26, + "learning_rate": 1.8486036584997143e-05, + "loss": 1.4954, + "step": 2476 + }, + { + "epoch": 0.26, + "learning_rate": 1.8484099637627472e-05, + "loss": 1.4926, + "step": 2477 + }, + { + "epoch": 0.26, + "learning_rate": 1.8482161553606447e-05, + "loss": 1.487, + "step": 2478 + }, + { + "epoch": 0.26, + "learning_rate": 1.8480222333193715e-05, + "loss": 1.4553, + "step": 2479 + }, + { + "epoch": 0.26, + "learning_rate": 1.847828197664908e-05, + "loss": 1.4862, + "step": 2480 + }, + { + "epoch": 0.26, + "learning_rate": 1.8476340484232508e-05, + "loss": 1.4867, + "step": 2481 + }, + { + "epoch": 0.26, + "learning_rate": 1.8474397856204097e-05, + "loss": 1.4736, + "step": 2482 + }, + { + "epoch": 0.26, + "learning_rate": 1.8472454092824122e-05, + "loss": 1.4254, + "step": 2483 + }, + { + "epoch": 0.26, + "learning_rate": 1.8470509194352987e-05, + "loss": 1.4455, + "step": 2484 + }, + { + "epoch": 0.26, + "learning_rate": 1.8468563161051263e-05, + "loss": 1.4402, + "step": 2485 + }, + { + "epoch": 0.26, + "learning_rate": 1.846661599317967e-05, + "loss": 1.4611, + "step": 2486 + }, + { + "epoch": 0.26, + "learning_rate": 1.8464667690999073e-05, + "loss": 1.4814, + "step": 2487 + }, + { + "epoch": 0.26, + "learning_rate": 1.8462718254770503e-05, + "loss": 1.4559, + "step": 2488 + }, + { + "epoch": 0.26, + "learning_rate": 1.8460767684755127e-05, + "loss": 1.4667, + "step": 2489 + }, + { + "epoch": 0.26, + "learning_rate": 1.8458815981214274e-05, + "loss": 1.4427, + "step": 2490 + }, + { + "epoch": 0.26, + "learning_rate": 1.845686314440942e-05, + "loss": 1.4055, + "step": 2491 + }, + { + "epoch": 0.26, + "learning_rate": 1.8454909174602198e-05, + "loss": 1.5563, + "step": 2492 + }, + { + "epoch": 0.26, + "learning_rate": 1.845295407205439e-05, + "loss": 1.4631, + "step": 2493 + }, + { + "epoch": 0.26, + "learning_rate": 1.8450997837027925e-05, + "loss": 1.4887, + "step": 2494 + }, + { + "epoch": 0.26, + "learning_rate": 1.8449040469784895e-05, + "loss": 1.5212, + "step": 2495 + }, + { + "epoch": 0.26, + "learning_rate": 1.844708197058753e-05, + "loss": 1.5582, + "step": 2496 + }, + { + "epoch": 0.26, + "learning_rate": 1.844512233969822e-05, + "loss": 1.4599, + "step": 2497 + }, + { + "epoch": 0.26, + "learning_rate": 1.844316157737951e-05, + "loss": 1.4546, + "step": 2498 + }, + { + "epoch": 0.26, + "learning_rate": 1.844119968389409e-05, + "loss": 1.4631, + "step": 2499 + }, + { + "epoch": 0.26, + "learning_rate": 1.84392366595048e-05, + "loss": 1.4817, + "step": 2500 + }, + { + "epoch": 0.26, + "learning_rate": 1.8437272504474636e-05, + "loss": 1.4214, + "step": 2501 + }, + { + "epoch": 0.26, + "learning_rate": 1.8435307219066744e-05, + "loss": 1.471, + "step": 2502 + }, + { + "epoch": 0.26, + "learning_rate": 1.8433340803544424e-05, + "loss": 1.4693, + "step": 2503 + }, + { + "epoch": 0.26, + "learning_rate": 1.8431373258171127e-05, + "loss": 1.6297, + "step": 2504 + }, + { + "epoch": 0.26, + "learning_rate": 1.842940458321045e-05, + "loss": 1.5916, + "step": 2505 + }, + { + "epoch": 0.26, + "learning_rate": 1.842743477892614e-05, + "loss": 1.4754, + "step": 2506 + }, + { + "epoch": 0.26, + "learning_rate": 1.842546384558211e-05, + "loss": 1.4828, + "step": 2507 + }, + { + "epoch": 0.26, + "learning_rate": 1.842349178344241e-05, + "loss": 1.4239, + "step": 2508 + }, + { + "epoch": 0.26, + "learning_rate": 1.8421518592771243e-05, + "loss": 1.5028, + "step": 2509 + }, + { + "epoch": 0.26, + "learning_rate": 1.841954427383297e-05, + "loss": 1.4848, + "step": 2510 + }, + { + "epoch": 0.26, + "learning_rate": 1.8417568826892097e-05, + "loss": 1.4617, + "step": 2511 + }, + { + "epoch": 0.26, + "learning_rate": 1.8415592252213284e-05, + "loss": 1.4266, + "step": 2512 + }, + { + "epoch": 0.26, + "learning_rate": 1.8413614550061344e-05, + "loss": 1.4321, + "step": 2513 + }, + { + "epoch": 0.26, + "learning_rate": 1.841163572070123e-05, + "loss": 1.4693, + "step": 2514 + }, + { + "epoch": 0.26, + "learning_rate": 1.840965576439806e-05, + "loss": 1.4257, + "step": 2515 + }, + { + "epoch": 0.26, + "learning_rate": 1.84076746814171e-05, + "loss": 1.4488, + "step": 2516 + }, + { + "epoch": 0.26, + "learning_rate": 1.840569247202376e-05, + "loss": 1.5348, + "step": 2517 + }, + { + "epoch": 0.26, + "learning_rate": 1.8403709136483604e-05, + "loss": 1.477, + "step": 2518 + }, + { + "epoch": 0.26, + "learning_rate": 1.840172467506235e-05, + "loss": 1.443, + "step": 2519 + }, + { + "epoch": 0.26, + "learning_rate": 1.839973908802587e-05, + "loss": 1.4772, + "step": 2520 + }, + { + "epoch": 0.26, + "learning_rate": 1.839775237564017e-05, + "loss": 1.4443, + "step": 2521 + }, + { + "epoch": 0.26, + "learning_rate": 1.839576453817143e-05, + "loss": 1.4063, + "step": 2522 + }, + { + "epoch": 0.26, + "learning_rate": 1.8393775575885963e-05, + "loss": 1.5178, + "step": 2523 + }, + { + "epoch": 0.26, + "learning_rate": 1.8391785489050235e-05, + "loss": 1.4337, + "step": 2524 + }, + { + "epoch": 0.26, + "learning_rate": 1.8389794277930875e-05, + "loss": 1.4512, + "step": 2525 + }, + { + "epoch": 0.26, + "learning_rate": 1.838780194279465e-05, + "loss": 1.5578, + "step": 2526 + }, + { + "epoch": 0.26, + "learning_rate": 1.8385808483908484e-05, + "loss": 1.4606, + "step": 2527 + }, + { + "epoch": 0.27, + "learning_rate": 1.8383813901539444e-05, + "loss": 1.4957, + "step": 2528 + }, + { + "epoch": 0.27, + "learning_rate": 1.838181819595476e-05, + "loss": 1.4914, + "step": 2529 + }, + { + "epoch": 0.27, + "learning_rate": 1.8379821367421802e-05, + "loss": 1.4785, + "step": 2530 + }, + { + "epoch": 0.27, + "learning_rate": 1.837782341620809e-05, + "loss": 1.4052, + "step": 2531 + }, + { + "epoch": 0.27, + "learning_rate": 1.8375824342581303e-05, + "loss": 1.4807, + "step": 2532 + }, + { + "epoch": 0.27, + "learning_rate": 1.8373824146809264e-05, + "loss": 1.4313, + "step": 2533 + }, + { + "epoch": 0.27, + "learning_rate": 1.8371822829159945e-05, + "loss": 1.4374, + "step": 2534 + }, + { + "epoch": 0.27, + "learning_rate": 1.836982038990148e-05, + "loss": 1.4482, + "step": 2535 + }, + { + "epoch": 0.27, + "learning_rate": 1.8367816829302133e-05, + "loss": 1.5231, + "step": 2536 + }, + { + "epoch": 0.27, + "learning_rate": 1.8365812147630337e-05, + "loss": 1.4101, + "step": 2537 + }, + { + "epoch": 0.27, + "learning_rate": 1.8363806345154666e-05, + "loss": 1.4372, + "step": 2538 + }, + { + "epoch": 0.27, + "learning_rate": 1.8361799422143845e-05, + "loss": 1.4808, + "step": 2539 + }, + { + "epoch": 0.27, + "learning_rate": 1.835979137886675e-05, + "loss": 1.3515, + "step": 2540 + }, + { + "epoch": 0.27, + "learning_rate": 1.8357782215592412e-05, + "loss": 1.5284, + "step": 2541 + }, + { + "epoch": 0.27, + "learning_rate": 1.835577193259e-05, + "loss": 1.4222, + "step": 2542 + }, + { + "epoch": 0.27, + "learning_rate": 1.8353760530128846e-05, + "loss": 1.4522, + "step": 2543 + }, + { + "epoch": 0.27, + "learning_rate": 1.835174800847842e-05, + "loss": 1.4487, + "step": 2544 + }, + { + "epoch": 0.27, + "learning_rate": 1.8349734367908355e-05, + "loss": 1.3688, + "step": 2545 + }, + { + "epoch": 0.27, + "learning_rate": 1.8347719608688422e-05, + "loss": 1.483, + "step": 2546 + }, + { + "epoch": 0.27, + "learning_rate": 1.8345703731088554e-05, + "loss": 1.4733, + "step": 2547 + }, + { + "epoch": 0.27, + "learning_rate": 1.8343686735378816e-05, + "loss": 1.4594, + "step": 2548 + }, + { + "epoch": 0.27, + "learning_rate": 1.834166862182944e-05, + "loss": 1.4648, + "step": 2549 + }, + { + "epoch": 0.27, + "learning_rate": 1.8339649390710807e-05, + "loss": 1.5249, + "step": 2550 + }, + { + "epoch": 0.27, + "learning_rate": 1.8337629042293434e-05, + "loss": 1.4744, + "step": 2551 + }, + { + "epoch": 0.27, + "learning_rate": 1.8335607576847994e-05, + "loss": 1.5094, + "step": 2552 + }, + { + "epoch": 0.27, + "learning_rate": 1.8333584994645318e-05, + "loss": 1.5122, + "step": 2553 + }, + { + "epoch": 0.27, + "learning_rate": 1.8331561295956374e-05, + "loss": 1.537, + "step": 2554 + }, + { + "epoch": 0.27, + "learning_rate": 1.832953648105229e-05, + "loss": 1.4691, + "step": 2555 + }, + { + "epoch": 0.27, + "learning_rate": 1.8327510550204343e-05, + "loss": 1.4969, + "step": 2556 + }, + { + "epoch": 0.27, + "learning_rate": 1.8325483503683944e-05, + "loss": 1.4596, + "step": 2557 + }, + { + "epoch": 0.27, + "learning_rate": 1.8323455341762675e-05, + "loss": 1.435, + "step": 2558 + }, + { + "epoch": 0.27, + "learning_rate": 1.8321426064712255e-05, + "loss": 1.4883, + "step": 2559 + }, + { + "epoch": 0.27, + "learning_rate": 1.8319395672804554e-05, + "loss": 1.3758, + "step": 2560 + }, + { + "epoch": 0.27, + "learning_rate": 1.8317364166311592e-05, + "loss": 1.4352, + "step": 2561 + }, + { + "epoch": 0.27, + "learning_rate": 1.831533154550554e-05, + "loss": 1.5072, + "step": 2562 + }, + { + "epoch": 0.27, + "learning_rate": 1.8313297810658718e-05, + "loss": 1.4476, + "step": 2563 + }, + { + "epoch": 0.27, + "learning_rate": 1.831126296204359e-05, + "loss": 1.507, + "step": 2564 + }, + { + "epoch": 0.27, + "learning_rate": 1.8309226999932777e-05, + "loss": 1.4677, + "step": 2565 + }, + { + "epoch": 0.27, + "learning_rate": 1.8307189924599044e-05, + "loss": 1.4537, + "step": 2566 + }, + { + "epoch": 0.27, + "learning_rate": 1.8305151736315307e-05, + "loss": 1.4584, + "step": 2567 + }, + { + "epoch": 0.27, + "learning_rate": 1.8303112435354634e-05, + "loss": 1.4944, + "step": 2568 + }, + { + "epoch": 0.27, + "learning_rate": 1.8301072021990232e-05, + "loss": 1.4379, + "step": 2569 + }, + { + "epoch": 0.27, + "learning_rate": 1.8299030496495475e-05, + "loss": 1.539, + "step": 2570 + }, + { + "epoch": 0.27, + "learning_rate": 1.829698785914386e-05, + "loss": 1.4421, + "step": 2571 + }, + { + "epoch": 0.27, + "learning_rate": 1.8294944110209063e-05, + "loss": 1.4693, + "step": 2572 + }, + { + "epoch": 0.27, + "learning_rate": 1.8292899249964887e-05, + "loss": 1.3239, + "step": 2573 + }, + { + "epoch": 0.27, + "learning_rate": 1.8290853278685284e-05, + "loss": 1.472, + "step": 2574 + }, + { + "epoch": 0.27, + "learning_rate": 1.8288806196644374e-05, + "loss": 1.536, + "step": 2575 + }, + { + "epoch": 0.27, + "learning_rate": 1.8286758004116405e-05, + "loss": 1.4644, + "step": 2576 + }, + { + "epoch": 0.27, + "learning_rate": 1.8284708701375783e-05, + "loss": 1.4537, + "step": 2577 + }, + { + "epoch": 0.27, + "learning_rate": 1.8282658288697067e-05, + "loss": 1.4359, + "step": 2578 + }, + { + "epoch": 0.27, + "learning_rate": 1.8280606766354955e-05, + "loss": 1.4842, + "step": 2579 + }, + { + "epoch": 0.27, + "learning_rate": 1.8278554134624302e-05, + "loss": 1.4664, + "step": 2580 + }, + { + "epoch": 0.27, + "learning_rate": 1.8276500393780105e-05, + "loss": 1.4632, + "step": 2581 + }, + { + "epoch": 0.27, + "learning_rate": 1.827444554409751e-05, + "loss": 1.4996, + "step": 2582 + }, + { + "epoch": 0.27, + "learning_rate": 1.827238958585182e-05, + "loss": 1.3399, + "step": 2583 + }, + { + "epoch": 0.27, + "learning_rate": 1.8270332519318476e-05, + "loss": 1.3928, + "step": 2584 + }, + { + "epoch": 0.27, + "learning_rate": 1.8268274344773074e-05, + "loss": 1.4993, + "step": 2585 + }, + { + "epoch": 0.27, + "learning_rate": 1.8266215062491356e-05, + "loss": 1.5398, + "step": 2586 + }, + { + "epoch": 0.27, + "learning_rate": 1.826415467274921e-05, + "loss": 1.4353, + "step": 2587 + }, + { + "epoch": 0.27, + "eval_loss": 1.5104212760925293, + "eval_runtime": 77.3448, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2587 + }, + { + "epoch": 0.27, + "learning_rate": 1.8262093175822685e-05, + "loss": 1.4889, + "step": 2588 + }, + { + "epoch": 0.27, + "learning_rate": 1.826003057198796e-05, + "loss": 1.4912, + "step": 2589 + }, + { + "epoch": 0.27, + "learning_rate": 1.825796686152137e-05, + "loss": 1.4884, + "step": 2590 + }, + { + "epoch": 0.27, + "learning_rate": 1.8255902044699404e-05, + "loss": 1.478, + "step": 2591 + }, + { + "epoch": 0.27, + "learning_rate": 1.8253836121798692e-05, + "loss": 1.6549, + "step": 2592 + }, + { + "epoch": 0.27, + "learning_rate": 1.8251769093096018e-05, + "loss": 1.5146, + "step": 2593 + }, + { + "epoch": 0.27, + "learning_rate": 1.8249700958868306e-05, + "loss": 1.4797, + "step": 2594 + }, + { + "epoch": 0.27, + "learning_rate": 1.8247631719392634e-05, + "loss": 1.4655, + "step": 2595 + }, + { + "epoch": 0.27, + "learning_rate": 1.824556137494623e-05, + "loss": 1.4517, + "step": 2596 + }, + { + "epoch": 0.27, + "learning_rate": 1.8243489925806458e-05, + "loss": 1.4936, + "step": 2597 + }, + { + "epoch": 0.27, + "learning_rate": 1.8241417372250852e-05, + "loss": 1.4614, + "step": 2598 + }, + { + "epoch": 0.27, + "learning_rate": 1.8239343714557073e-05, + "loss": 1.4475, + "step": 2599 + }, + { + "epoch": 0.27, + "learning_rate": 1.8237268953002937e-05, + "loss": 1.5435, + "step": 2600 + }, + { + "epoch": 0.27, + "learning_rate": 1.8235193087866413e-05, + "loss": 1.4616, + "step": 2601 + }, + { + "epoch": 0.27, + "learning_rate": 1.8233116119425612e-05, + "loss": 1.4578, + "step": 2602 + }, + { + "epoch": 0.27, + "learning_rate": 1.8231038047958795e-05, + "loss": 1.434, + "step": 2603 + }, + { + "epoch": 0.27, + "learning_rate": 1.8228958873744368e-05, + "loss": 1.5335, + "step": 2604 + }, + { + "epoch": 0.27, + "learning_rate": 1.8226878597060887e-05, + "loss": 1.415, + "step": 2605 + }, + { + "epoch": 0.27, + "learning_rate": 1.8224797218187058e-05, + "loss": 1.6165, + "step": 2606 + }, + { + "epoch": 0.27, + "learning_rate": 1.822271473740173e-05, + "loss": 1.372, + "step": 2607 + }, + { + "epoch": 0.27, + "learning_rate": 1.8220631154983907e-05, + "loss": 1.4855, + "step": 2608 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218546471212727e-05, + "loss": 1.4093, + "step": 2609 + }, + { + "epoch": 0.27, + "learning_rate": 1.821646068636749e-05, + "loss": 1.4852, + "step": 2610 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214373800727637e-05, + "loss": 1.6959, + "step": 2611 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212285814572755e-05, + "loss": 1.3874, + "step": 2612 + }, + { + "epoch": 0.27, + "learning_rate": 1.821019672818258e-05, + "loss": 1.4425, + "step": 2613 + }, + { + "epoch": 0.27, + "learning_rate": 1.8208106541837e-05, + "loss": 1.6097, + "step": 2614 + }, + { + "epoch": 0.27, + "learning_rate": 1.8206015255816045e-05, + "loss": 1.5675, + "step": 2615 + }, + { + "epoch": 0.27, + "learning_rate": 1.820392287039989e-05, + "loss": 1.4039, + "step": 2616 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201829385868866e-05, + "loss": 1.4872, + "step": 2617 + }, + { + "epoch": 0.27, + "learning_rate": 1.819973480250344e-05, + "loss": 1.4645, + "step": 2618 + }, + { + "epoch": 0.27, + "learning_rate": 1.8197639120584237e-05, + "loss": 1.4923, + "step": 2619 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195542340392025e-05, + "loss": 1.4294, + "step": 2620 + }, + { + "epoch": 0.27, + "learning_rate": 1.8193444462207717e-05, + "loss": 1.4315, + "step": 2621 + }, + { + "epoch": 0.27, + "learning_rate": 1.8191345486312372e-05, + "loss": 1.3972, + "step": 2622 + }, + { + "epoch": 0.28, + "learning_rate": 1.8189245412987205e-05, + "loss": 1.462, + "step": 2623 + }, + { + "epoch": 0.28, + "learning_rate": 1.8187144242513567e-05, + "loss": 1.4738, + "step": 2624 + }, + { + "epoch": 0.28, + "learning_rate": 1.818504197517296e-05, + "loss": 1.4935, + "step": 2625 + }, + { + "epoch": 0.28, + "learning_rate": 1.8182938611247038e-05, + "loss": 1.4231, + "step": 2626 + }, + { + "epoch": 0.28, + "learning_rate": 1.81808341510176e-05, + "loss": 1.4031, + "step": 2627 + }, + { + "epoch": 0.28, + "learning_rate": 1.817872859476658e-05, + "loss": 1.5822, + "step": 2628 + }, + { + "epoch": 0.28, + "learning_rate": 1.8176621942776075e-05, + "loss": 1.432, + "step": 2629 + }, + { + "epoch": 0.28, + "learning_rate": 1.8174514195328324e-05, + "loss": 1.5565, + "step": 2630 + }, + { + "epoch": 0.28, + "learning_rate": 1.8172405352705704e-05, + "loss": 1.4895, + "step": 2631 + }, + { + "epoch": 0.28, + "learning_rate": 1.8170295415190754e-05, + "loss": 1.4032, + "step": 2632 + }, + { + "epoch": 0.28, + "learning_rate": 1.8168184383066144e-05, + "loss": 1.4253, + "step": 2633 + }, + { + "epoch": 0.28, + "learning_rate": 1.8166072256614702e-05, + "loss": 1.5162, + "step": 2634 + }, + { + "epoch": 0.28, + "learning_rate": 1.81639590361194e-05, + "loss": 1.4609, + "step": 2635 + }, + { + "epoch": 0.28, + "learning_rate": 1.816184472186335e-05, + "loss": 1.4351, + "step": 2636 + }, + { + "epoch": 0.28, + "learning_rate": 1.8159729314129823e-05, + "loss": 1.4738, + "step": 2637 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157612813202224e-05, + "loss": 1.5986, + "step": 2638 + }, + { + "epoch": 0.28, + "learning_rate": 1.815549521936411e-05, + "loss": 1.4633, + "step": 2639 + }, + { + "epoch": 0.28, + "learning_rate": 1.8153376532899184e-05, + "loss": 1.4404, + "step": 2640 + }, + { + "epoch": 0.28, + "learning_rate": 1.81512567540913e-05, + "loss": 1.4256, + "step": 2641 + }, + { + "epoch": 0.28, + "learning_rate": 1.814913588322445e-05, + "loss": 1.4054, + "step": 2642 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147013920582773e-05, + "loss": 1.4134, + "step": 2643 + }, + { + "epoch": 0.28, + "learning_rate": 1.8144890866450567e-05, + "loss": 1.4098, + "step": 2644 + }, + { + "epoch": 0.28, + "learning_rate": 1.814276672111226e-05, + "loss": 1.4593, + "step": 2645 + }, + { + "epoch": 0.28, + "learning_rate": 1.814064148485243e-05, + "loss": 1.4679, + "step": 2646 + }, + { + "epoch": 0.28, + "learning_rate": 1.8138515157955812e-05, + "loss": 1.5234, + "step": 2647 + }, + { + "epoch": 0.28, + "learning_rate": 1.8136387740707272e-05, + "loss": 1.4568, + "step": 2648 + }, + { + "epoch": 0.28, + "learning_rate": 1.8134259233391836e-05, + "loss": 1.5057, + "step": 2649 + }, + { + "epoch": 0.28, + "learning_rate": 1.8132129636294665e-05, + "loss": 1.3643, + "step": 2650 + }, + { + "epoch": 0.28, + "learning_rate": 1.812999894970107e-05, + "loss": 1.4766, + "step": 2651 + }, + { + "epoch": 0.28, + "learning_rate": 1.812786717389651e-05, + "loss": 1.5701, + "step": 2652 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125734309166587e-05, + "loss": 1.5341, + "step": 2653 + }, + { + "epoch": 0.28, + "learning_rate": 1.812360035579705e-05, + "loss": 1.3596, + "step": 2654 + }, + { + "epoch": 0.28, + "learning_rate": 1.8121465314073793e-05, + "loss": 1.4847, + "step": 2655 + }, + { + "epoch": 0.28, + "learning_rate": 1.811932918428286e-05, + "loss": 1.4664, + "step": 2656 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117191966710438e-05, + "loss": 1.4673, + "step": 2657 + }, + { + "epoch": 0.28, + "learning_rate": 1.8115053661642856e-05, + "loss": 1.4712, + "step": 2658 + }, + { + "epoch": 0.28, + "learning_rate": 1.811291426936659e-05, + "loss": 1.4458, + "step": 2659 + }, + { + "epoch": 0.28, + "learning_rate": 1.811077379016827e-05, + "loss": 1.4667, + "step": 2660 + }, + { + "epoch": 0.28, + "learning_rate": 1.810863222433466e-05, + "loss": 1.4695, + "step": 2661 + }, + { + "epoch": 0.28, + "learning_rate": 1.8106489572152677e-05, + "loss": 1.5263, + "step": 2662 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104345833909376e-05, + "loss": 1.4148, + "step": 2663 + }, + { + "epoch": 0.28, + "learning_rate": 1.8102201009891976e-05, + "loss": 1.3955, + "step": 2664 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100055100387814e-05, + "loss": 1.6056, + "step": 2665 + }, + { + "epoch": 0.28, + "learning_rate": 1.8097908105684396e-05, + "loss": 1.5394, + "step": 2666 + }, + { + "epoch": 0.28, + "learning_rate": 1.809576002606936e-05, + "loss": 1.479, + "step": 2667 + }, + { + "epoch": 0.28, + "learning_rate": 1.8093610861830494e-05, + "loss": 1.4492, + "step": 2668 + }, + { + "epoch": 0.28, + "learning_rate": 1.8091460613255728e-05, + "loss": 1.4172, + "step": 2669 + }, + { + "epoch": 0.28, + "learning_rate": 1.808930928063315e-05, + "loss": 1.4498, + "step": 2670 + }, + { + "epoch": 0.28, + "learning_rate": 1.808715686425097e-05, + "loss": 1.6203, + "step": 2671 + }, + { + "epoch": 0.28, + "learning_rate": 1.8085003364397567e-05, + "loss": 1.435, + "step": 2672 + }, + { + "epoch": 0.28, + "learning_rate": 1.808284878136145e-05, + "loss": 1.4489, + "step": 2673 + }, + { + "epoch": 0.28, + "learning_rate": 1.8080693115431277e-05, + "loss": 1.4416, + "step": 2674 + }, + { + "epoch": 0.28, + "learning_rate": 1.8078536366895853e-05, + "loss": 1.422, + "step": 2675 + }, + { + "epoch": 0.28, + "learning_rate": 1.8076378536044128e-05, + "loss": 1.4039, + "step": 2676 + }, + { + "epoch": 0.28, + "learning_rate": 1.8074219623165195e-05, + "loss": 1.4705, + "step": 2677 + }, + { + "epoch": 0.28, + "learning_rate": 1.807205962854829e-05, + "loss": 1.5031, + "step": 2678 + }, + { + "epoch": 0.28, + "learning_rate": 1.8069898552482806e-05, + "loss": 1.4812, + "step": 2679 + }, + { + "epoch": 0.28, + "learning_rate": 1.806773639525826e-05, + "loss": 1.4129, + "step": 2680 + }, + { + "epoch": 0.28, + "learning_rate": 1.8065573157164332e-05, + "loss": 1.4559, + "step": 2681 + }, + { + "epoch": 0.28, + "learning_rate": 1.806340883849084e-05, + "loss": 1.3878, + "step": 2682 + }, + { + "epoch": 0.28, + "learning_rate": 1.8061243439527744e-05, + "loss": 1.4752, + "step": 2683 + }, + { + "epoch": 0.28, + "learning_rate": 1.8059076960565156e-05, + "loss": 1.4089, + "step": 2684 + }, + { + "epoch": 0.28, + "learning_rate": 1.8056909401893326e-05, + "loss": 1.4736, + "step": 2685 + }, + { + "epoch": 0.28, + "learning_rate": 1.8054740763802654e-05, + "loss": 1.3796, + "step": 2686 + }, + { + "epoch": 0.28, + "learning_rate": 1.805257104658368e-05, + "loss": 1.4412, + "step": 2687 + }, + { + "epoch": 0.28, + "learning_rate": 1.8050400250527086e-05, + "loss": 1.4639, + "step": 2688 + }, + { + "epoch": 0.28, + "learning_rate": 1.804822837592371e-05, + "loss": 1.4076, + "step": 2689 + }, + { + "epoch": 0.28, + "learning_rate": 1.804605542306452e-05, + "loss": 1.4627, + "step": 2690 + }, + { + "epoch": 0.28, + "learning_rate": 1.8043881392240642e-05, + "loss": 1.5249, + "step": 2691 + }, + { + "epoch": 0.28, + "learning_rate": 1.804170628374334e-05, + "loss": 1.4312, + "step": 2692 + }, + { + "epoch": 0.28, + "learning_rate": 1.803953009786402e-05, + "loss": 1.5676, + "step": 2693 + }, + { + "epoch": 0.28, + "learning_rate": 1.8037352834894233e-05, + "loss": 1.5072, + "step": 2694 + }, + { + "epoch": 0.28, + "learning_rate": 1.803517449512568e-05, + "loss": 1.5662, + "step": 2695 + }, + { + "epoch": 0.28, + "learning_rate": 1.8032995078850207e-05, + "loss": 1.4771, + "step": 2696 + }, + { + "epoch": 0.28, + "learning_rate": 1.803081458635979e-05, + "loss": 1.412, + "step": 2697 + }, + { + "epoch": 0.28, + "learning_rate": 1.8028633017946564e-05, + "loss": 1.497, + "step": 2698 + }, + { + "epoch": 0.28, + "learning_rate": 1.8026450373902804e-05, + "loss": 1.4528, + "step": 2699 + }, + { + "epoch": 0.28, + "learning_rate": 1.802426665452093e-05, + "loss": 1.4785, + "step": 2700 + }, + { + "epoch": 0.28, + "learning_rate": 1.8022081860093493e-05, + "loss": 1.6411, + "step": 2701 + }, + { + "epoch": 0.28, + "learning_rate": 1.8019895990913213e-05, + "loss": 1.4459, + "step": 2702 + }, + { + "epoch": 0.28, + "learning_rate": 1.8017709047272932e-05, + "loss": 1.4418, + "step": 2703 + }, + { + "epoch": 0.28, + "learning_rate": 1.801552102946565e-05, + "loss": 1.4409, + "step": 2704 + }, + { + "epoch": 0.28, + "learning_rate": 1.8013331937784498e-05, + "loss": 1.4651, + "step": 2705 + }, + { + "epoch": 0.28, + "learning_rate": 1.8011141772522766e-05, + "loss": 1.4161, + "step": 2706 + }, + { + "epoch": 0.28, + "learning_rate": 1.8008950533973876e-05, + "loss": 1.458, + "step": 2707 + }, + { + "epoch": 0.28, + "learning_rate": 1.8006758222431398e-05, + "loss": 1.4477, + "step": 2708 + }, + { + "epoch": 0.28, + "learning_rate": 1.800456483818904e-05, + "loss": 1.4433, + "step": 2709 + }, + { + "epoch": 0.28, + "learning_rate": 1.8002370381540672e-05, + "loss": 1.5005, + "step": 2710 + }, + { + "epoch": 0.28, + "learning_rate": 1.8000174852780282e-05, + "loss": 1.4945, + "step": 2711 + }, + { + "epoch": 0.28, + "learning_rate": 1.7997978252202023e-05, + "loss": 1.4298, + "step": 2712 + }, + { + "epoch": 0.28, + "learning_rate": 1.7995780580100177e-05, + "loss": 1.3812, + "step": 2713 + }, + { + "epoch": 0.28, + "learning_rate": 1.799358183676918e-05, + "loss": 1.5559, + "step": 2714 + }, + { + "epoch": 0.28, + "learning_rate": 1.79913820225036e-05, + "loss": 1.4316, + "step": 2715 + }, + { + "epoch": 0.28, + "learning_rate": 1.798918113759817e-05, + "loss": 1.419, + "step": 2716 + }, + { + "epoch": 0.28, + "learning_rate": 1.7986979182347733e-05, + "loss": 1.43, + "step": 2717 + }, + { + "epoch": 0.29, + "learning_rate": 1.798477615704731e-05, + "loss": 1.4964, + "step": 2718 + }, + { + "epoch": 0.29, + "learning_rate": 1.7982572061992044e-05, + "loss": 1.4417, + "step": 2719 + }, + { + "epoch": 0.29, + "learning_rate": 1.7980366897477227e-05, + "loss": 1.4562, + "step": 2720 + }, + { + "epoch": 0.29, + "learning_rate": 1.7978160663798295e-05, + "loss": 1.4386, + "step": 2721 + }, + { + "epoch": 0.29, + "learning_rate": 1.7975953361250824e-05, + "loss": 1.445, + "step": 2722 + }, + { + "epoch": 0.29, + "learning_rate": 1.797374499013054e-05, + "loss": 1.4549, + "step": 2723 + }, + { + "epoch": 0.29, + "learning_rate": 1.7971535550733305e-05, + "loss": 1.5205, + "step": 2724 + }, + { + "epoch": 0.29, + "learning_rate": 1.796932504335513e-05, + "loss": 1.4632, + "step": 2725 + }, + { + "epoch": 0.29, + "learning_rate": 1.796711346829216e-05, + "loss": 1.3767, + "step": 2726 + }, + { + "epoch": 0.29, + "learning_rate": 1.79649008258407e-05, + "loss": 1.4098, + "step": 2727 + }, + { + "epoch": 0.29, + "learning_rate": 1.7962687116297178e-05, + "loss": 1.4675, + "step": 2728 + }, + { + "epoch": 0.29, + "learning_rate": 1.7960472339958176e-05, + "loss": 1.6048, + "step": 2729 + }, + { + "epoch": 0.29, + "learning_rate": 1.7958256497120418e-05, + "loss": 1.5432, + "step": 2730 + }, + { + "epoch": 0.29, + "learning_rate": 1.7956039588080774e-05, + "loss": 1.5453, + "step": 2731 + }, + { + "epoch": 0.29, + "learning_rate": 1.7953821613136246e-05, + "loss": 1.4246, + "step": 2732 + }, + { + "epoch": 0.29, + "learning_rate": 1.7951602572583988e-05, + "loss": 1.3987, + "step": 2733 + }, + { + "epoch": 0.29, + "learning_rate": 1.7949382466721295e-05, + "loss": 1.4943, + "step": 2734 + }, + { + "epoch": 0.29, + "learning_rate": 1.7947161295845606e-05, + "loss": 1.4385, + "step": 2735 + }, + { + "epoch": 0.29, + "learning_rate": 1.7944939060254497e-05, + "loss": 1.4165, + "step": 2736 + }, + { + "epoch": 0.29, + "learning_rate": 1.7942715760245692e-05, + "loss": 1.4004, + "step": 2737 + }, + { + "epoch": 0.29, + "learning_rate": 1.7940491396117063e-05, + "loss": 1.4577, + "step": 2738 + }, + { + "epoch": 0.29, + "learning_rate": 1.7938265968166602e-05, + "loss": 1.4649, + "step": 2739 + }, + { + "epoch": 0.29, + "learning_rate": 1.7936039476692473e-05, + "loss": 1.5273, + "step": 2740 + }, + { + "epoch": 0.29, + "learning_rate": 1.7933811921992962e-05, + "loss": 1.4325, + "step": 2741 + }, + { + "epoch": 0.29, + "learning_rate": 1.793158330436651e-05, + "loss": 1.4388, + "step": 2742 + }, + { + "epoch": 0.29, + "learning_rate": 1.7929353624111687e-05, + "loss": 1.4124, + "step": 2743 + }, + { + "epoch": 0.29, + "learning_rate": 1.7927122881527222e-05, + "loss": 1.5449, + "step": 2744 + }, + { + "epoch": 0.29, + "learning_rate": 1.7924891076911964e-05, + "loss": 1.4728, + "step": 2745 + }, + { + "epoch": 0.29, + "learning_rate": 1.7922658210564932e-05, + "loss": 1.5103, + "step": 2746 + }, + { + "epoch": 0.29, + "learning_rate": 1.792042428278526e-05, + "loss": 1.5975, + "step": 2747 + }, + { + "epoch": 0.29, + "learning_rate": 1.7918189293872247e-05, + "loss": 1.567, + "step": 2748 + }, + { + "epoch": 0.29, + "learning_rate": 1.7915953244125318e-05, + "loss": 1.57, + "step": 2749 + }, + { + "epoch": 0.29, + "learning_rate": 1.791371613384405e-05, + "loss": 1.4372, + "step": 2750 + }, + { + "epoch": 0.29, + "learning_rate": 1.7911477963328155e-05, + "loss": 1.4053, + "step": 2751 + }, + { + "epoch": 0.29, + "learning_rate": 1.7909238732877492e-05, + "loss": 1.3782, + "step": 2752 + }, + { + "epoch": 0.29, + "learning_rate": 1.790699844279206e-05, + "loss": 1.4401, + "step": 2753 + }, + { + "epoch": 0.29, + "learning_rate": 1.7904757093372e-05, + "loss": 1.3749, + "step": 2754 + }, + { + "epoch": 0.29, + "learning_rate": 1.79025146849176e-05, + "loss": 1.4909, + "step": 2755 + }, + { + "epoch": 0.29, + "learning_rate": 1.7900271217729273e-05, + "loss": 1.4103, + "step": 2756 + }, + { + "epoch": 0.29, + "learning_rate": 1.7898026692107597e-05, + "loss": 1.4986, + "step": 2757 + }, + { + "epoch": 0.29, + "learning_rate": 1.7895781108353278e-05, + "loss": 1.5449, + "step": 2758 + }, + { + "epoch": 0.29, + "learning_rate": 1.789353446676717e-05, + "loss": 1.5583, + "step": 2759 + }, + { + "epoch": 0.29, + "learning_rate": 1.7891286767650254e-05, + "loss": 1.5342, + "step": 2760 + }, + { + "epoch": 0.29, + "learning_rate": 1.7889038011303673e-05, + "loss": 1.4233, + "step": 2761 + }, + { + "epoch": 0.29, + "learning_rate": 1.7886788198028707e-05, + "loss": 1.3433, + "step": 2762 + }, + { + "epoch": 0.29, + "learning_rate": 1.788453732812676e-05, + "loss": 1.4451, + "step": 2763 + }, + { + "epoch": 0.29, + "learning_rate": 1.78822854018994e-05, + "loss": 1.4506, + "step": 2764 + }, + { + "epoch": 0.29, + "learning_rate": 1.7880032419648324e-05, + "loss": 1.4386, + "step": 2765 + }, + { + "epoch": 0.29, + "learning_rate": 1.7877778381675374e-05, + "loss": 1.4512, + "step": 2766 + }, + { + "epoch": 0.29, + "learning_rate": 1.7875523288282535e-05, + "loss": 1.4319, + "step": 2767 + }, + { + "epoch": 0.29, + "learning_rate": 1.7873267139771932e-05, + "loss": 1.4753, + "step": 2768 + }, + { + "epoch": 0.29, + "learning_rate": 1.787100993644583e-05, + "loss": 1.4044, + "step": 2769 + }, + { + "epoch": 0.29, + "learning_rate": 1.786875167860663e-05, + "loss": 1.4382, + "step": 2770 + }, + { + "epoch": 0.29, + "learning_rate": 1.786649236655689e-05, + "loss": 1.3977, + "step": 2771 + }, + { + "epoch": 0.29, + "learning_rate": 1.7864232000599298e-05, + "loss": 1.4473, + "step": 2772 + }, + { + "epoch": 0.29, + "learning_rate": 1.7861970581036678e-05, + "loss": 1.4666, + "step": 2773 + }, + { + "epoch": 0.29, + "learning_rate": 1.785970810817201e-05, + "loss": 1.5299, + "step": 2774 + }, + { + "epoch": 0.29, + "learning_rate": 1.7857444582308402e-05, + "loss": 1.3974, + "step": 2775 + }, + { + "epoch": 0.29, + "learning_rate": 1.7855180003749114e-05, + "loss": 1.4603, + "step": 2776 + }, + { + "epoch": 0.29, + "learning_rate": 1.7852914372797535e-05, + "loss": 1.463, + "step": 2777 + }, + { + "epoch": 0.29, + "learning_rate": 1.7850647689757205e-05, + "loss": 1.5317, + "step": 2778 + }, + { + "epoch": 0.29, + "learning_rate": 1.78483799549318e-05, + "loss": 1.4669, + "step": 2779 + }, + { + "epoch": 0.29, + "learning_rate": 1.784611116862514e-05, + "loss": 1.5293, + "step": 2780 + }, + { + "epoch": 0.29, + "learning_rate": 1.7843841331141177e-05, + "loss": 1.5802, + "step": 2781 + }, + { + "epoch": 0.29, + "learning_rate": 1.7841570442784024e-05, + "loss": 1.4486, + "step": 2782 + }, + { + "epoch": 0.29, + "learning_rate": 1.7839298503857913e-05, + "loss": 1.4674, + "step": 2783 + }, + { + "epoch": 0.29, + "learning_rate": 1.7837025514667224e-05, + "loss": 1.4662, + "step": 2784 + }, + { + "epoch": 0.29, + "learning_rate": 1.7834751475516484e-05, + "loss": 1.3555, + "step": 2785 + }, + { + "epoch": 0.29, + "learning_rate": 1.783247638671035e-05, + "loss": 1.4307, + "step": 2786 + }, + { + "epoch": 0.29, + "eval_loss": 1.500258445739746, + "eval_runtime": 77.406, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 2786 + }, + { + "epoch": 0.29, + "learning_rate": 1.7830200248553633e-05, + "loss": 1.4596, + "step": 2787 + }, + { + "epoch": 0.29, + "learning_rate": 1.7827923061351273e-05, + "loss": 1.6118, + "step": 2788 + }, + { + "epoch": 0.29, + "learning_rate": 1.7825644825408353e-05, + "loss": 1.4782, + "step": 2789 + }, + { + "epoch": 0.29, + "learning_rate": 1.78233655410301e-05, + "loss": 1.4681, + "step": 2790 + }, + { + "epoch": 0.29, + "learning_rate": 1.782108520852188e-05, + "loss": 1.6281, + "step": 2791 + }, + { + "epoch": 0.29, + "learning_rate": 1.78188038281892e-05, + "loss": 1.4446, + "step": 2792 + }, + { + "epoch": 0.29, + "learning_rate": 1.7816521400337704e-05, + "loss": 1.479, + "step": 2793 + }, + { + "epoch": 0.29, + "learning_rate": 1.7814237925273178e-05, + "loss": 1.5457, + "step": 2794 + }, + { + "epoch": 0.29, + "learning_rate": 1.7811953403301547e-05, + "loss": 1.3928, + "step": 2795 + }, + { + "epoch": 0.29, + "learning_rate": 1.780966783472889e-05, + "loss": 1.4321, + "step": 2796 + }, + { + "epoch": 0.29, + "learning_rate": 1.78073812198614e-05, + "loss": 1.5734, + "step": 2797 + }, + { + "epoch": 0.29, + "learning_rate": 1.7805093559005432e-05, + "loss": 1.4356, + "step": 2798 + }, + { + "epoch": 0.29, + "learning_rate": 1.7802804852467473e-05, + "loss": 1.4656, + "step": 2799 + }, + { + "epoch": 0.29, + "learning_rate": 1.780051510055415e-05, + "loss": 1.4052, + "step": 2800 + }, + { + "epoch": 0.29, + "learning_rate": 1.7798224303572228e-05, + "loss": 1.4758, + "step": 2801 + }, + { + "epoch": 0.29, + "learning_rate": 1.7795932461828622e-05, + "loss": 1.4326, + "step": 2802 + }, + { + "epoch": 0.29, + "learning_rate": 1.7793639575630376e-05, + "loss": 1.3409, + "step": 2803 + }, + { + "epoch": 0.29, + "learning_rate": 1.7791345645284678e-05, + "loss": 1.4175, + "step": 2804 + }, + { + "epoch": 0.29, + "learning_rate": 1.7789050671098853e-05, + "loss": 1.383, + "step": 2805 + }, + { + "epoch": 0.29, + "learning_rate": 1.7786754653380373e-05, + "loss": 1.5162, + "step": 2806 + }, + { + "epoch": 0.29, + "learning_rate": 1.7784457592436847e-05, + "loss": 1.4899, + "step": 2807 + }, + { + "epoch": 0.29, + "learning_rate": 1.7782159488576016e-05, + "loss": 1.4874, + "step": 2808 + }, + { + "epoch": 0.29, + "learning_rate": 1.777986034210577e-05, + "loss": 1.4363, + "step": 2809 + }, + { + "epoch": 0.29, + "learning_rate": 1.7777560153334134e-05, + "loss": 1.4223, + "step": 2810 + }, + { + "epoch": 0.29, + "learning_rate": 1.7775258922569273e-05, + "loss": 1.4792, + "step": 2811 + }, + { + "epoch": 0.29, + "learning_rate": 1.77729566501195e-05, + "loss": 1.4475, + "step": 2812 + }, + { + "epoch": 0.29, + "learning_rate": 1.7770653336293253e-05, + "loss": 1.5157, + "step": 2813 + }, + { + "epoch": 0.3, + "learning_rate": 1.776834898139912e-05, + "loss": 1.389, + "step": 2814 + }, + { + "epoch": 0.3, + "learning_rate": 1.7766043585745824e-05, + "loss": 1.4358, + "step": 2815 + }, + { + "epoch": 0.3, + "learning_rate": 1.776373714964223e-05, + "loss": 1.4297, + "step": 2816 + }, + { + "epoch": 0.3, + "learning_rate": 1.7761429673397344e-05, + "loss": 1.4102, + "step": 2817 + }, + { + "epoch": 0.3, + "learning_rate": 1.77591211573203e-05, + "loss": 1.4572, + "step": 2818 + }, + { + "epoch": 0.3, + "learning_rate": 1.775681160172039e-05, + "loss": 1.448, + "step": 2819 + }, + { + "epoch": 0.3, + "learning_rate": 1.7754501006907025e-05, + "loss": 1.4426, + "step": 2820 + }, + { + "epoch": 0.3, + "learning_rate": 1.7752189373189773e-05, + "loss": 1.4566, + "step": 2821 + }, + { + "epoch": 0.3, + "learning_rate": 1.7749876700878332e-05, + "loss": 1.4267, + "step": 2822 + }, + { + "epoch": 0.3, + "learning_rate": 1.7747562990282538e-05, + "loss": 1.3951, + "step": 2823 + }, + { + "epoch": 0.3, + "learning_rate": 1.7745248241712373e-05, + "loss": 1.4668, + "step": 2824 + }, + { + "epoch": 0.3, + "learning_rate": 1.774293245547795e-05, + "loss": 1.4924, + "step": 2825 + }, + { + "epoch": 0.3, + "learning_rate": 1.7740615631889525e-05, + "loss": 1.5258, + "step": 2826 + }, + { + "epoch": 0.3, + "learning_rate": 1.7738297771257496e-05, + "loss": 1.4323, + "step": 2827 + }, + { + "epoch": 0.3, + "learning_rate": 1.7735978873892393e-05, + "loss": 1.439, + "step": 2828 + }, + { + "epoch": 0.3, + "learning_rate": 1.773365894010489e-05, + "loss": 1.5658, + "step": 2829 + }, + { + "epoch": 0.3, + "learning_rate": 1.77313379702058e-05, + "loss": 1.4607, + "step": 2830 + }, + { + "epoch": 0.3, + "learning_rate": 1.7729015964506073e-05, + "loss": 1.5544, + "step": 2831 + }, + { + "epoch": 0.3, + "learning_rate": 1.7726692923316798e-05, + "loss": 1.4232, + "step": 2832 + }, + { + "epoch": 0.3, + "learning_rate": 1.77243688469492e-05, + "loss": 1.415, + "step": 2833 + }, + { + "epoch": 0.3, + "learning_rate": 1.772204373571465e-05, + "loss": 1.4658, + "step": 2834 + }, + { + "epoch": 0.3, + "learning_rate": 1.7719717589924647e-05, + "loss": 1.4678, + "step": 2835 + }, + { + "epoch": 0.3, + "learning_rate": 1.771739040989084e-05, + "loss": 1.3021, + "step": 2836 + }, + { + "epoch": 0.3, + "learning_rate": 1.771506219592501e-05, + "loss": 1.4045, + "step": 2837 + }, + { + "epoch": 0.3, + "learning_rate": 1.7712732948339085e-05, + "loss": 1.4593, + "step": 2838 + }, + { + "epoch": 0.3, + "learning_rate": 1.7710402667445108e-05, + "loss": 1.4175, + "step": 2839 + }, + { + "epoch": 0.3, + "learning_rate": 1.770807135355529e-05, + "loss": 1.3939, + "step": 2840 + }, + { + "epoch": 0.3, + "learning_rate": 1.7705739006981963e-05, + "loss": 1.6089, + "step": 2841 + }, + { + "epoch": 0.3, + "learning_rate": 1.77034056280376e-05, + "loss": 1.3952, + "step": 2842 + }, + { + "epoch": 0.3, + "learning_rate": 1.7701071217034818e-05, + "loss": 1.5086, + "step": 2843 + }, + { + "epoch": 0.3, + "learning_rate": 1.7698735774286362e-05, + "loss": 1.4706, + "step": 2844 + }, + { + "epoch": 0.3, + "learning_rate": 1.7696399300105128e-05, + "loss": 1.4286, + "step": 2845 + }, + { + "epoch": 0.3, + "learning_rate": 1.7694061794804137e-05, + "loss": 1.4418, + "step": 2846 + }, + { + "epoch": 0.3, + "learning_rate": 1.7691723258696562e-05, + "loss": 1.516, + "step": 2847 + }, + { + "epoch": 0.3, + "learning_rate": 1.76893836920957e-05, + "loss": 1.4354, + "step": 2848 + }, + { + "epoch": 0.3, + "learning_rate": 1.7687043095314998e-05, + "loss": 1.7503, + "step": 2849 + }, + { + "epoch": 0.3, + "learning_rate": 1.7684701468668032e-05, + "loss": 1.5985, + "step": 2850 + }, + { + "epoch": 0.3, + "learning_rate": 1.768235881246852e-05, + "loss": 1.442, + "step": 2851 + }, + { + "epoch": 0.3, + "learning_rate": 1.7680015127030322e-05, + "loss": 1.4924, + "step": 2852 + }, + { + "epoch": 0.3, + "learning_rate": 1.7677670412667425e-05, + "loss": 1.4461, + "step": 2853 + }, + { + "epoch": 0.3, + "learning_rate": 1.7675324669693968e-05, + "loss": 1.3823, + "step": 2854 + }, + { + "epoch": 0.3, + "learning_rate": 1.767297789842421e-05, + "loss": 1.452, + "step": 2855 + }, + { + "epoch": 0.3, + "learning_rate": 1.767063009917257e-05, + "loss": 1.46, + "step": 2856 + }, + { + "epoch": 0.3, + "learning_rate": 1.7668281272253587e-05, + "loss": 1.4129, + "step": 2857 + }, + { + "epoch": 0.3, + "learning_rate": 1.766593141798194e-05, + "loss": 1.4057, + "step": 2858 + }, + { + "epoch": 0.3, + "learning_rate": 1.7663580536672456e-05, + "loss": 1.5162, + "step": 2859 + }, + { + "epoch": 0.3, + "learning_rate": 1.7661228628640087e-05, + "loss": 1.5177, + "step": 2860 + }, + { + "epoch": 0.3, + "learning_rate": 1.7658875694199933e-05, + "loss": 1.4548, + "step": 2861 + }, + { + "epoch": 0.3, + "learning_rate": 1.7656521733667223e-05, + "loss": 1.4511, + "step": 2862 + }, + { + "epoch": 0.3, + "learning_rate": 1.765416674735733e-05, + "loss": 1.4778, + "step": 2863 + }, + { + "epoch": 0.3, + "learning_rate": 1.765181073558576e-05, + "loss": 1.3935, + "step": 2864 + }, + { + "epoch": 0.3, + "learning_rate": 1.7649453698668156e-05, + "loss": 1.4659, + "step": 2865 + }, + { + "epoch": 0.3, + "learning_rate": 1.7647095636920305e-05, + "loss": 1.7042, + "step": 2866 + }, + { + "epoch": 0.3, + "learning_rate": 1.7644736550658124e-05, + "loss": 1.7957, + "step": 2867 + }, + { + "epoch": 0.3, + "learning_rate": 1.764237644019767e-05, + "loss": 1.5139, + "step": 2868 + }, + { + "epoch": 0.3, + "learning_rate": 1.764001530585514e-05, + "loss": 1.4117, + "step": 2869 + }, + { + "epoch": 0.3, + "learning_rate": 1.7637653147946858e-05, + "loss": 1.4837, + "step": 2870 + }, + { + "epoch": 0.3, + "learning_rate": 1.7635289966789298e-05, + "loss": 1.4379, + "step": 2871 + }, + { + "epoch": 0.3, + "learning_rate": 1.7632925762699068e-05, + "loss": 1.4491, + "step": 2872 + }, + { + "epoch": 0.3, + "learning_rate": 1.7630560535992905e-05, + "loss": 1.4006, + "step": 2873 + }, + { + "epoch": 0.3, + "learning_rate": 1.7628194286987694e-05, + "loss": 1.5484, + "step": 2874 + }, + { + "epoch": 0.3, + "learning_rate": 1.7625827016000446e-05, + "loss": 1.4926, + "step": 2875 + }, + { + "epoch": 0.3, + "learning_rate": 1.762345872334832e-05, + "loss": 1.3909, + "step": 2876 + }, + { + "epoch": 0.3, + "learning_rate": 1.76210894093486e-05, + "loss": 1.405, + "step": 2877 + }, + { + "epoch": 0.3, + "learning_rate": 1.7618719074318718e-05, + "loss": 1.4736, + "step": 2878 + }, + { + "epoch": 0.3, + "learning_rate": 1.7616347718576238e-05, + "loss": 1.4445, + "step": 2879 + }, + { + "epoch": 0.3, + "learning_rate": 1.761397534243886e-05, + "loss": 1.4878, + "step": 2880 + }, + { + "epoch": 0.3, + "learning_rate": 1.7611601946224417e-05, + "loss": 1.4414, + "step": 2881 + }, + { + "epoch": 0.3, + "learning_rate": 1.760922753025089e-05, + "loss": 1.5657, + "step": 2882 + }, + { + "epoch": 0.3, + "learning_rate": 1.7606852094836385e-05, + "loss": 1.5008, + "step": 2883 + }, + { + "epoch": 0.3, + "learning_rate": 1.7604475640299153e-05, + "loss": 1.4922, + "step": 2884 + }, + { + "epoch": 0.3, + "learning_rate": 1.7602098166957577e-05, + "loss": 1.7451, + "step": 2885 + }, + { + "epoch": 0.3, + "learning_rate": 1.759971967513017e-05, + "loss": 1.7077, + "step": 2886 + }, + { + "epoch": 0.3, + "learning_rate": 1.75973401651356e-05, + "loss": 1.3986, + "step": 2887 + }, + { + "epoch": 0.3, + "learning_rate": 1.7594959637292656e-05, + "loss": 1.3966, + "step": 2888 + }, + { + "epoch": 0.3, + "learning_rate": 1.7592578091920264e-05, + "loss": 1.4086, + "step": 2889 + }, + { + "epoch": 0.3, + "learning_rate": 1.7590195529337495e-05, + "loss": 1.4481, + "step": 2890 + }, + { + "epoch": 0.3, + "learning_rate": 1.7587811949863548e-05, + "loss": 1.3974, + "step": 2891 + }, + { + "epoch": 0.3, + "learning_rate": 1.7585427353817758e-05, + "loss": 1.5013, + "step": 2892 + }, + { + "epoch": 0.3, + "learning_rate": 1.7583041741519608e-05, + "loss": 1.5454, + "step": 2893 + }, + { + "epoch": 0.3, + "learning_rate": 1.7580655113288708e-05, + "loss": 1.5033, + "step": 2894 + }, + { + "epoch": 0.3, + "learning_rate": 1.7578267469444793e-05, + "loss": 1.4332, + "step": 2895 + }, + { + "epoch": 0.3, + "learning_rate": 1.757587881030776e-05, + "loss": 1.4667, + "step": 2896 + }, + { + "epoch": 0.3, + "learning_rate": 1.7573489136197623e-05, + "loss": 1.4314, + "step": 2897 + }, + { + "epoch": 0.3, + "learning_rate": 1.7571098447434532e-05, + "loss": 1.4514, + "step": 2898 + }, + { + "epoch": 0.3, + "learning_rate": 1.7568706744338784e-05, + "loss": 1.4872, + "step": 2899 + }, + { + "epoch": 0.3, + "learning_rate": 1.7566314027230808e-05, + "loss": 1.4841, + "step": 2900 + }, + { + "epoch": 0.3, + "learning_rate": 1.7563920296431158e-05, + "loss": 1.3964, + "step": 2901 + }, + { + "epoch": 0.3, + "learning_rate": 1.7561525552260538e-05, + "loss": 1.4932, + "step": 2902 + }, + { + "epoch": 0.3, + "learning_rate": 1.755912979503978e-05, + "loss": 1.4153, + "step": 2903 + }, + { + "epoch": 0.3, + "learning_rate": 1.755673302508986e-05, + "loss": 1.4939, + "step": 2904 + }, + { + "epoch": 0.3, + "learning_rate": 1.755433524273187e-05, + "loss": 1.4437, + "step": 2905 + }, + { + "epoch": 0.3, + "learning_rate": 1.7551936448287067e-05, + "loss": 1.486, + "step": 2906 + }, + { + "epoch": 0.3, + "learning_rate": 1.754953664207682e-05, + "loss": 1.4362, + "step": 2907 + }, + { + "epoch": 0.3, + "learning_rate": 1.7547135824422635e-05, + "loss": 1.4954, + "step": 2908 + }, + { + "epoch": 0.31, + "learning_rate": 1.7544733995646174e-05, + "loss": 1.4552, + "step": 2909 + }, + { + "epoch": 0.31, + "learning_rate": 1.7542331156069213e-05, + "loss": 1.4654, + "step": 2910 + }, + { + "epoch": 0.31, + "learning_rate": 1.753992730601367e-05, + "loss": 1.4531, + "step": 2911 + }, + { + "epoch": 0.31, + "learning_rate": 1.75375224458016e-05, + "loss": 1.4949, + "step": 2912 + }, + { + "epoch": 0.31, + "learning_rate": 1.753511657575519e-05, + "loss": 1.3998, + "step": 2913 + }, + { + "epoch": 0.31, + "learning_rate": 1.753270969619677e-05, + "loss": 1.3904, + "step": 2914 + }, + { + "epoch": 0.31, + "learning_rate": 1.7530301807448794e-05, + "loss": 1.481, + "step": 2915 + }, + { + "epoch": 0.31, + "learning_rate": 1.7527892909833864e-05, + "loss": 1.4301, + "step": 2916 + }, + { + "epoch": 0.31, + "learning_rate": 1.7525483003674707e-05, + "loss": 1.4377, + "step": 2917 + }, + { + "epoch": 0.31, + "learning_rate": 1.7523072089294188e-05, + "loss": 1.5077, + "step": 2918 + }, + { + "epoch": 0.31, + "learning_rate": 1.752066016701531e-05, + "loss": 1.3802, + "step": 2919 + }, + { + "epoch": 0.31, + "learning_rate": 1.7518247237161205e-05, + "loss": 1.3991, + "step": 2920 + }, + { + "epoch": 0.31, + "learning_rate": 1.7515833300055146e-05, + "loss": 1.4283, + "step": 2921 + }, + { + "epoch": 0.31, + "learning_rate": 1.7513418356020535e-05, + "loss": 1.3688, + "step": 2922 + }, + { + "epoch": 0.31, + "learning_rate": 1.751100240538092e-05, + "loss": 1.4336, + "step": 2923 + }, + { + "epoch": 0.31, + "learning_rate": 1.7508585448459967e-05, + "loss": 1.4302, + "step": 2924 + }, + { + "epoch": 0.31, + "learning_rate": 1.7506167485581493e-05, + "loss": 1.4293, + "step": 2925 + }, + { + "epoch": 0.31, + "learning_rate": 1.750374851706944e-05, + "loss": 1.4262, + "step": 2926 + }, + { + "epoch": 0.31, + "learning_rate": 1.7501328543247892e-05, + "loss": 1.4128, + "step": 2927 + }, + { + "epoch": 0.31, + "learning_rate": 1.7498907564441054e-05, + "loss": 1.4258, + "step": 2928 + }, + { + "epoch": 0.31, + "learning_rate": 1.749648558097328e-05, + "loss": 1.4904, + "step": 2929 + }, + { + "epoch": 0.31, + "learning_rate": 1.749406259316906e-05, + "loss": 1.4628, + "step": 2930 + }, + { + "epoch": 0.31, + "learning_rate": 1.7491638601353004e-05, + "loss": 1.4908, + "step": 2931 + }, + { + "epoch": 0.31, + "learning_rate": 1.7489213605849867e-05, + "loss": 1.4563, + "step": 2932 + }, + { + "epoch": 0.31, + "learning_rate": 1.7486787606984533e-05, + "loss": 1.5006, + "step": 2933 + }, + { + "epoch": 0.31, + "learning_rate": 1.748436060508203e-05, + "loss": 1.424, + "step": 2934 + }, + { + "epoch": 0.31, + "learning_rate": 1.7481932600467508e-05, + "loss": 1.4136, + "step": 2935 + }, + { + "epoch": 0.31, + "learning_rate": 1.747950359346626e-05, + "loss": 1.3835, + "step": 2936 + }, + { + "epoch": 0.31, + "learning_rate": 1.747707358440371e-05, + "loss": 1.5284, + "step": 2937 + }, + { + "epoch": 0.31, + "learning_rate": 1.7474642573605418e-05, + "loss": 1.4592, + "step": 2938 + }, + { + "epoch": 0.31, + "learning_rate": 1.7472210561397075e-05, + "loss": 1.5483, + "step": 2939 + }, + { + "epoch": 0.31, + "learning_rate": 1.746977754810451e-05, + "loss": 1.521, + "step": 2940 + }, + { + "epoch": 0.31, + "learning_rate": 1.7467343534053683e-05, + "loss": 1.4276, + "step": 2941 + }, + { + "epoch": 0.31, + "learning_rate": 1.746490851957069e-05, + "loss": 1.4302, + "step": 2942 + }, + { + "epoch": 0.31, + "learning_rate": 1.746247250498176e-05, + "loss": 1.4439, + "step": 2943 + }, + { + "epoch": 0.31, + "learning_rate": 1.7460035490613255e-05, + "loss": 1.4991, + "step": 2944 + }, + { + "epoch": 0.31, + "learning_rate": 1.7457597476791674e-05, + "loss": 1.4188, + "step": 2945 + }, + { + "epoch": 0.31, + "learning_rate": 1.7455158463843648e-05, + "loss": 1.4685, + "step": 2946 + }, + { + "epoch": 0.31, + "learning_rate": 1.745271845209594e-05, + "loss": 1.3811, + "step": 2947 + }, + { + "epoch": 0.31, + "learning_rate": 1.7450277441875454e-05, + "loss": 1.4869, + "step": 2948 + }, + { + "epoch": 0.31, + "learning_rate": 1.7447835433509218e-05, + "loss": 1.5001, + "step": 2949 + }, + { + "epoch": 0.31, + "learning_rate": 1.74453924273244e-05, + "loss": 1.4757, + "step": 2950 + }, + { + "epoch": 0.31, + "learning_rate": 1.74429484236483e-05, + "loss": 1.5072, + "step": 2951 + }, + { + "epoch": 0.31, + "learning_rate": 1.744050342280835e-05, + "loss": 1.4242, + "step": 2952 + }, + { + "epoch": 0.31, + "learning_rate": 1.743805742513212e-05, + "loss": 1.4462, + "step": 2953 + }, + { + "epoch": 0.31, + "learning_rate": 1.743561043094731e-05, + "loss": 1.6815, + "step": 2954 + }, + { + "epoch": 0.31, + "learning_rate": 1.7433162440581755e-05, + "loss": 1.427, + "step": 2955 + }, + { + "epoch": 0.31, + "learning_rate": 1.7430713454363423e-05, + "loss": 1.2933, + "step": 2956 + }, + { + "epoch": 0.31, + "learning_rate": 1.742826347262041e-05, + "loss": 1.4247, + "step": 2957 + }, + { + "epoch": 0.31, + "learning_rate": 1.7425812495680955e-05, + "loss": 1.399, + "step": 2958 + }, + { + "epoch": 0.31, + "learning_rate": 1.742336052387343e-05, + "loss": 1.4818, + "step": 2959 + }, + { + "epoch": 0.31, + "learning_rate": 1.742090755752633e-05, + "loss": 1.3839, + "step": 2960 + }, + { + "epoch": 0.31, + "learning_rate": 1.741845359696829e-05, + "loss": 1.4669, + "step": 2961 + }, + { + "epoch": 0.31, + "learning_rate": 1.741599864252808e-05, + "loss": 1.468, + "step": 2962 + }, + { + "epoch": 0.31, + "learning_rate": 1.74135426945346e-05, + "loss": 1.4135, + "step": 2963 + }, + { + "epoch": 0.31, + "learning_rate": 1.7411085753316882e-05, + "loss": 1.5899, + "step": 2964 + }, + { + "epoch": 0.31, + "learning_rate": 1.74086278192041e-05, + "loss": 1.6115, + "step": 2965 + }, + { + "epoch": 0.31, + "learning_rate": 1.740616889252554e-05, + "loss": 1.3988, + "step": 2966 + }, + { + "epoch": 0.31, + "learning_rate": 1.740370897361065e-05, + "loss": 1.5001, + "step": 2967 + }, + { + "epoch": 0.31, + "learning_rate": 1.740124806278899e-05, + "loss": 1.459, + "step": 2968 + }, + { + "epoch": 0.31, + "learning_rate": 1.7398786160390258e-05, + "loss": 1.4489, + "step": 2969 + }, + { + "epoch": 0.31, + "learning_rate": 1.7396323266744283e-05, + "loss": 1.4397, + "step": 2970 + }, + { + "epoch": 0.31, + "learning_rate": 1.7393859382181033e-05, + "loss": 1.4687, + "step": 2971 + }, + { + "epoch": 0.31, + "learning_rate": 1.7391394507030606e-05, + "loss": 1.4495, + "step": 2972 + }, + { + "epoch": 0.31, + "learning_rate": 1.738892864162323e-05, + "loss": 1.4745, + "step": 2973 + }, + { + "epoch": 0.31, + "learning_rate": 1.7386461786289274e-05, + "loss": 1.3943, + "step": 2974 + }, + { + "epoch": 0.31, + "learning_rate": 1.738399394135922e-05, + "loss": 1.4595, + "step": 2975 + }, + { + "epoch": 0.31, + "learning_rate": 1.738152510716371e-05, + "loss": 1.4023, + "step": 2976 + }, + { + "epoch": 0.31, + "learning_rate": 1.7379055284033493e-05, + "loss": 1.3938, + "step": 2977 + }, + { + "epoch": 0.31, + "learning_rate": 1.7376584472299468e-05, + "loss": 1.4576, + "step": 2978 + }, + { + "epoch": 0.31, + "learning_rate": 1.737411267229266e-05, + "loss": 1.424, + "step": 2979 + }, + { + "epoch": 0.31, + "learning_rate": 1.7371639884344225e-05, + "loss": 1.4224, + "step": 2980 + }, + { + "epoch": 0.31, + "learning_rate": 1.736916610878545e-05, + "loss": 1.4228, + "step": 2981 + }, + { + "epoch": 0.31, + "learning_rate": 1.7366691345947768e-05, + "loss": 1.5021, + "step": 2982 + }, + { + "epoch": 0.31, + "learning_rate": 1.736421559616272e-05, + "loss": 1.3589, + "step": 2983 + }, + { + "epoch": 0.31, + "learning_rate": 1.7361738859762007e-05, + "loss": 1.4748, + "step": 2984 + }, + { + "epoch": 0.31, + "learning_rate": 1.735926113707743e-05, + "loss": 1.3974, + "step": 2985 + }, + { + "epoch": 0.31, + "eval_loss": 1.4849082231521606, + "eval_runtime": 77.3271, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2985 + }, + { + "epoch": 0.31, + "learning_rate": 1.735678242844096e-05, + "loss": 1.392, + "step": 2986 + }, + { + "epoch": 0.31, + "learning_rate": 1.735430273418467e-05, + "loss": 1.4277, + "step": 2987 + }, + { + "epoch": 0.31, + "learning_rate": 1.735182205464077e-05, + "loss": 1.4216, + "step": 2988 + }, + { + "epoch": 0.31, + "learning_rate": 1.7349340390141617e-05, + "loss": 1.4546, + "step": 2989 + }, + { + "epoch": 0.31, + "learning_rate": 1.734685774101969e-05, + "loss": 1.4264, + "step": 2990 + }, + { + "epoch": 0.31, + "learning_rate": 1.7344374107607593e-05, + "loss": 1.4307, + "step": 2991 + }, + { + "epoch": 0.31, + "learning_rate": 1.7341889490238076e-05, + "loss": 1.4266, + "step": 2992 + }, + { + "epoch": 0.31, + "learning_rate": 1.7339403889244008e-05, + "loss": 1.4486, + "step": 2993 + }, + { + "epoch": 0.31, + "learning_rate": 1.7336917304958403e-05, + "loss": 1.4345, + "step": 2994 + }, + { + "epoch": 0.31, + "learning_rate": 1.7334429737714395e-05, + "loss": 1.476, + "step": 2995 + }, + { + "epoch": 0.31, + "learning_rate": 1.7331941187845248e-05, + "loss": 1.5148, + "step": 2996 + }, + { + "epoch": 0.31, + "learning_rate": 1.7329451655684372e-05, + "loss": 1.4026, + "step": 2997 + }, + { + "epoch": 0.31, + "learning_rate": 1.7326961141565303e-05, + "loss": 1.3935, + "step": 2998 + }, + { + "epoch": 0.31, + "learning_rate": 1.73244696458217e-05, + "loss": 1.4483, + "step": 2999 + }, + { + "epoch": 0.31, + "learning_rate": 1.7321977168787356e-05, + "loss": 1.5197, + "step": 3000 + }, + { + "epoch": 0.31, + "learning_rate": 1.7319483710796208e-05, + "loss": 1.4648, + "step": 3001 + }, + { + "epoch": 0.31, + "learning_rate": 1.7316989272182308e-05, + "loss": 1.4171, + "step": 3002 + }, + { + "epoch": 0.31, + "learning_rate": 1.731449385327985e-05, + "loss": 1.4541, + "step": 3003 + }, + { + "epoch": 0.32, + "learning_rate": 1.731199745442316e-05, + "loss": 1.4605, + "step": 3004 + }, + { + "epoch": 0.32, + "learning_rate": 1.7309500075946683e-05, + "loss": 1.5122, + "step": 3005 + }, + { + "epoch": 0.32, + "learning_rate": 1.7307001718185007e-05, + "loss": 1.5243, + "step": 3006 + }, + { + "epoch": 0.32, + "learning_rate": 1.7304502381472844e-05, + "loss": 1.4997, + "step": 3007 + }, + { + "epoch": 0.32, + "learning_rate": 1.730200206614505e-05, + "loss": 1.4891, + "step": 3008 + }, + { + "epoch": 0.32, + "learning_rate": 1.72995007725366e-05, + "loss": 1.4376, + "step": 3009 + }, + { + "epoch": 0.32, + "learning_rate": 1.7296998500982595e-05, + "loss": 1.4403, + "step": 3010 + }, + { + "epoch": 0.32, + "learning_rate": 1.7294495251818285e-05, + "loss": 1.5153, + "step": 3011 + }, + { + "epoch": 0.32, + "learning_rate": 1.729199102537904e-05, + "loss": 1.4996, + "step": 3012 + }, + { + "epoch": 0.32, + "learning_rate": 1.7289485822000356e-05, + "loss": 1.5302, + "step": 3013 + }, + { + "epoch": 0.32, + "learning_rate": 1.7286979642017867e-05, + "loss": 1.5641, + "step": 3014 + }, + { + "epoch": 0.32, + "learning_rate": 1.728447248576734e-05, + "loss": 1.438, + "step": 3015 + }, + { + "epoch": 0.32, + "learning_rate": 1.7281964353584674e-05, + "loss": 1.4796, + "step": 3016 + }, + { + "epoch": 0.32, + "learning_rate": 1.727945524580588e-05, + "loss": 1.4413, + "step": 3017 + }, + { + "epoch": 0.32, + "learning_rate": 1.727694516276713e-05, + "loss": 1.3966, + "step": 3018 + }, + { + "epoch": 0.32, + "learning_rate": 1.72744341048047e-05, + "loss": 1.5267, + "step": 3019 + }, + { + "epoch": 0.32, + "learning_rate": 1.727192207225501e-05, + "loss": 1.4284, + "step": 3020 + }, + { + "epoch": 0.32, + "learning_rate": 1.726940906545461e-05, + "loss": 1.5137, + "step": 3021 + }, + { + "epoch": 0.32, + "learning_rate": 1.7266895084740173e-05, + "loss": 1.3966, + "step": 3022 + }, + { + "epoch": 0.32, + "learning_rate": 1.7264380130448514e-05, + "loss": 1.4156, + "step": 3023 + }, + { + "epoch": 0.32, + "learning_rate": 1.726186420291657e-05, + "loss": 1.4644, + "step": 3024 + }, + { + "epoch": 0.32, + "learning_rate": 1.725934730248141e-05, + "loss": 1.4768, + "step": 3025 + }, + { + "epoch": 0.32, + "learning_rate": 1.7256829429480233e-05, + "loss": 1.4428, + "step": 3026 + }, + { + "epoch": 0.32, + "learning_rate": 1.7254310584250373e-05, + "loss": 1.4495, + "step": 3027 + }, + { + "epoch": 0.32, + "learning_rate": 1.725179076712929e-05, + "loss": 1.3867, + "step": 3028 + }, + { + "epoch": 0.32, + "learning_rate": 1.7249269978454567e-05, + "loss": 1.5011, + "step": 3029 + }, + { + "epoch": 0.32, + "learning_rate": 1.7246748218563937e-05, + "loss": 1.3916, + "step": 3030 + }, + { + "epoch": 0.32, + "learning_rate": 1.7244225487795238e-05, + "loss": 1.4984, + "step": 3031 + }, + { + "epoch": 0.32, + "learning_rate": 1.7241701786486464e-05, + "loss": 1.5776, + "step": 3032 + }, + { + "epoch": 0.32, + "learning_rate": 1.7239177114975717e-05, + "loss": 1.5018, + "step": 3033 + }, + { + "epoch": 0.32, + "learning_rate": 1.7236651473601244e-05, + "loss": 1.5042, + "step": 3034 + }, + { + "epoch": 0.32, + "learning_rate": 1.723412486270141e-05, + "loss": 1.4636, + "step": 3035 + }, + { + "epoch": 0.32, + "learning_rate": 1.723159728261472e-05, + "loss": 1.5612, + "step": 3036 + }, + { + "epoch": 0.32, + "learning_rate": 1.7229068733679803e-05, + "loss": 1.4399, + "step": 3037 + }, + { + "epoch": 0.32, + "learning_rate": 1.7226539216235424e-05, + "loss": 1.5635, + "step": 3038 + }, + { + "epoch": 0.32, + "learning_rate": 1.7224008730620468e-05, + "loss": 1.4329, + "step": 3039 + }, + { + "epoch": 0.32, + "learning_rate": 1.7221477277173956e-05, + "loss": 1.4886, + "step": 3040 + }, + { + "epoch": 0.32, + "learning_rate": 1.721894485623504e-05, + "loss": 1.4741, + "step": 3041 + }, + { + "epoch": 0.32, + "learning_rate": 1.7216411468143e-05, + "loss": 1.4678, + "step": 3042 + }, + { + "epoch": 0.32, + "learning_rate": 1.721387711323724e-05, + "loss": 1.4758, + "step": 3043 + }, + { + "epoch": 0.32, + "learning_rate": 1.72113417918573e-05, + "loss": 1.441, + "step": 3044 + }, + { + "epoch": 0.32, + "learning_rate": 1.7208805504342855e-05, + "loss": 1.4328, + "step": 3045 + }, + { + "epoch": 0.32, + "learning_rate": 1.720626825103369e-05, + "loss": 1.4254, + "step": 3046 + }, + { + "epoch": 0.32, + "learning_rate": 1.7203730032269744e-05, + "loss": 1.4462, + "step": 3047 + }, + { + "epoch": 0.32, + "learning_rate": 1.7201190848391066e-05, + "loss": 1.4826, + "step": 3048 + }, + { + "epoch": 0.32, + "learning_rate": 1.719865069973784e-05, + "loss": 1.4215, + "step": 3049 + }, + { + "epoch": 0.32, + "learning_rate": 1.7196109586650385e-05, + "loss": 1.4291, + "step": 3050 + }, + { + "epoch": 0.32, + "learning_rate": 1.7193567509469146e-05, + "loss": 1.5005, + "step": 3051 + }, + { + "epoch": 0.32, + "learning_rate": 1.719102446853469e-05, + "loss": 1.4216, + "step": 3052 + }, + { + "epoch": 0.32, + "learning_rate": 1.7188480464187725e-05, + "loss": 1.4349, + "step": 3053 + }, + { + "epoch": 0.32, + "learning_rate": 1.718593549676908e-05, + "loss": 1.4784, + "step": 3054 + }, + { + "epoch": 0.32, + "learning_rate": 1.7183389566619714e-05, + "loss": 1.4325, + "step": 3055 + }, + { + "epoch": 0.32, + "learning_rate": 1.7180842674080717e-05, + "loss": 1.5387, + "step": 3056 + }, + { + "epoch": 0.32, + "learning_rate": 1.717829481949331e-05, + "loss": 1.655, + "step": 3057 + }, + { + "epoch": 0.32, + "learning_rate": 1.717574600319883e-05, + "loss": 1.4623, + "step": 3058 + }, + { + "epoch": 0.32, + "learning_rate": 1.7173196225538768e-05, + "loss": 1.4646, + "step": 3059 + }, + { + "epoch": 0.32, + "learning_rate": 1.717064548685472e-05, + "loss": 1.4641, + "step": 3060 + }, + { + "epoch": 0.32, + "learning_rate": 1.7168093787488418e-05, + "loss": 1.4033, + "step": 3061 + }, + { + "epoch": 0.32, + "learning_rate": 1.7165541127781726e-05, + "loss": 1.4085, + "step": 3062 + }, + { + "epoch": 0.32, + "learning_rate": 1.716298750807664e-05, + "loss": 1.387, + "step": 3063 + }, + { + "epoch": 0.32, + "learning_rate": 1.7160432928715272e-05, + "loss": 1.4197, + "step": 3064 + }, + { + "epoch": 0.32, + "learning_rate": 1.7157877390039872e-05, + "loss": 1.4883, + "step": 3065 + }, + { + "epoch": 0.32, + "learning_rate": 1.7155320892392818e-05, + "loss": 1.4865, + "step": 3066 + }, + { + "epoch": 0.32, + "learning_rate": 1.715276343611662e-05, + "loss": 1.4532, + "step": 3067 + }, + { + "epoch": 0.32, + "learning_rate": 1.71502050215539e-05, + "loss": 1.3991, + "step": 3068 + }, + { + "epoch": 0.32, + "learning_rate": 1.7147645649047424e-05, + "loss": 1.4318, + "step": 3069 + }, + { + "epoch": 0.32, + "learning_rate": 1.714508531894009e-05, + "loss": 1.3616, + "step": 3070 + }, + { + "epoch": 0.32, + "learning_rate": 1.7142524031574904e-05, + "loss": 1.4481, + "step": 3071 + }, + { + "epoch": 0.32, + "learning_rate": 1.7139961787295022e-05, + "loss": 1.3897, + "step": 3072 + }, + { + "epoch": 0.32, + "learning_rate": 1.7137398586443716e-05, + "loss": 1.3128, + "step": 3073 + }, + { + "epoch": 0.32, + "learning_rate": 1.713483442936439e-05, + "loss": 1.4481, + "step": 3074 + }, + { + "epoch": 0.32, + "learning_rate": 1.713226931640057e-05, + "loss": 1.5374, + "step": 3075 + }, + { + "epoch": 0.32, + "learning_rate": 1.7129703247895923e-05, + "loss": 1.4247, + "step": 3076 + }, + { + "epoch": 0.32, + "learning_rate": 1.712713622419423e-05, + "loss": 1.4098, + "step": 3077 + }, + { + "epoch": 0.32, + "learning_rate": 1.7124568245639414e-05, + "loss": 1.4558, + "step": 3078 + }, + { + "epoch": 0.32, + "learning_rate": 1.7121999312575507e-05, + "loss": 1.4484, + "step": 3079 + }, + { + "epoch": 0.32, + "learning_rate": 1.711942942534669e-05, + "loss": 1.4236, + "step": 3080 + }, + { + "epoch": 0.32, + "learning_rate": 1.7116858584297253e-05, + "loss": 1.613, + "step": 3081 + }, + { + "epoch": 0.32, + "learning_rate": 1.711428678977163e-05, + "loss": 1.4503, + "step": 3082 + }, + { + "epoch": 0.32, + "learning_rate": 1.7111714042114376e-05, + "loss": 1.4072, + "step": 3083 + }, + { + "epoch": 0.32, + "learning_rate": 1.7109140341670168e-05, + "loss": 1.5999, + "step": 3084 + }, + { + "epoch": 0.32, + "learning_rate": 1.7106565688783815e-05, + "loss": 1.4129, + "step": 3085 + }, + { + "epoch": 0.32, + "learning_rate": 1.710399008380026e-05, + "loss": 1.3973, + "step": 3086 + }, + { + "epoch": 0.32, + "learning_rate": 1.710141352706456e-05, + "loss": 1.4292, + "step": 3087 + }, + { + "epoch": 0.32, + "learning_rate": 1.709883601892192e-05, + "loss": 1.4372, + "step": 3088 + }, + { + "epoch": 0.32, + "learning_rate": 1.7096257559717647e-05, + "loss": 1.4924, + "step": 3089 + }, + { + "epoch": 0.32, + "learning_rate": 1.7093678149797196e-05, + "loss": 1.4222, + "step": 3090 + }, + { + "epoch": 0.32, + "learning_rate": 1.7091097789506137e-05, + "loss": 1.4797, + "step": 3091 + }, + { + "epoch": 0.32, + "learning_rate": 1.7088516479190175e-05, + "loss": 1.4738, + "step": 3092 + }, + { + "epoch": 0.32, + "learning_rate": 1.708593421919514e-05, + "loss": 1.5371, + "step": 3093 + }, + { + "epoch": 0.32, + "learning_rate": 1.7083351009866988e-05, + "loss": 1.3802, + "step": 3094 + }, + { + "epoch": 0.32, + "learning_rate": 1.7080766851551795e-05, + "loss": 1.4292, + "step": 3095 + }, + { + "epoch": 0.32, + "learning_rate": 1.707818174459578e-05, + "loss": 1.4478, + "step": 3096 + }, + { + "epoch": 0.32, + "learning_rate": 1.7075595689345285e-05, + "loss": 1.4619, + "step": 3097 + }, + { + "epoch": 0.32, + "learning_rate": 1.7073008686146763e-05, + "loss": 1.4603, + "step": 3098 + }, + { + "epoch": 0.32, + "learning_rate": 1.7070420735346815e-05, + "loss": 1.4548, + "step": 3099 + }, + { + "epoch": 0.33, + "learning_rate": 1.7067831837292157e-05, + "loss": 1.3638, + "step": 3100 + }, + { + "epoch": 0.33, + "learning_rate": 1.7065241992329634e-05, + "loss": 1.4284, + "step": 3101 + }, + { + "epoch": 0.33, + "learning_rate": 1.7062651200806217e-05, + "loss": 1.386, + "step": 3102 + }, + { + "epoch": 0.33, + "learning_rate": 1.7060059463069013e-05, + "loss": 1.5483, + "step": 3103 + }, + { + "epoch": 0.33, + "learning_rate": 1.705746677946524e-05, + "loss": 1.4963, + "step": 3104 + }, + { + "epoch": 0.33, + "learning_rate": 1.7054873150342257e-05, + "loss": 1.4539, + "step": 3105 + }, + { + "epoch": 0.33, + "learning_rate": 1.705227857604754e-05, + "loss": 1.4361, + "step": 3106 + }, + { + "epoch": 0.33, + "learning_rate": 1.7049683056928695e-05, + "loss": 1.3735, + "step": 3107 + }, + { + "epoch": 0.33, + "learning_rate": 1.7047086593333454e-05, + "loss": 1.4324, + "step": 3108 + }, + { + "epoch": 0.33, + "learning_rate": 1.7044489185609685e-05, + "loss": 1.5037, + "step": 3109 + }, + { + "epoch": 0.33, + "learning_rate": 1.704189083410536e-05, + "loss": 1.3913, + "step": 3110 + }, + { + "epoch": 0.33, + "learning_rate": 1.7039291539168604e-05, + "loss": 1.3233, + "step": 3111 + }, + { + "epoch": 0.33, + "learning_rate": 1.703669130114765e-05, + "loss": 1.4897, + "step": 3112 + }, + { + "epoch": 0.33, + "learning_rate": 1.7034090120390862e-05, + "loss": 1.4843, + "step": 3113 + }, + { + "epoch": 0.33, + "learning_rate": 1.7031487997246735e-05, + "loss": 1.3674, + "step": 3114 + }, + { + "epoch": 0.33, + "learning_rate": 1.7028884932063883e-05, + "loss": 1.4475, + "step": 3115 + }, + { + "epoch": 0.33, + "learning_rate": 1.702628092519105e-05, + "loss": 1.4134, + "step": 3116 + }, + { + "epoch": 0.33, + "learning_rate": 1.7023675976977108e-05, + "loss": 1.4484, + "step": 3117 + }, + { + "epoch": 0.33, + "learning_rate": 1.702107008777106e-05, + "loss": 1.407, + "step": 3118 + }, + { + "epoch": 0.33, + "learning_rate": 1.7018463257922005e-05, + "loss": 1.5443, + "step": 3119 + }, + { + "epoch": 0.33, + "learning_rate": 1.701585548777922e-05, + "loss": 1.4548, + "step": 3120 + }, + { + "epoch": 0.33, + "learning_rate": 1.7013246777692063e-05, + "loss": 1.4252, + "step": 3121 + }, + { + "epoch": 0.33, + "learning_rate": 1.7010637128010037e-05, + "loss": 1.3748, + "step": 3122 + }, + { + "epoch": 0.33, + "learning_rate": 1.7008026539082767e-05, + "loss": 1.3804, + "step": 3123 + }, + { + "epoch": 0.33, + "learning_rate": 1.7005415011260008e-05, + "loss": 1.4203, + "step": 3124 + }, + { + "epoch": 0.33, + "learning_rate": 1.7002802544891634e-05, + "loss": 1.4195, + "step": 3125 + }, + { + "epoch": 0.33, + "learning_rate": 1.700018914032765e-05, + "loss": 1.4188, + "step": 3126 + }, + { + "epoch": 0.33, + "learning_rate": 1.699757479791819e-05, + "loss": 1.3884, + "step": 3127 + }, + { + "epoch": 0.33, + "learning_rate": 1.6994959518013502e-05, + "loss": 1.4111, + "step": 3128 + }, + { + "epoch": 0.33, + "learning_rate": 1.6992343300963963e-05, + "loss": 1.5452, + "step": 3129 + }, + { + "epoch": 0.33, + "learning_rate": 1.6989726147120087e-05, + "loss": 1.4097, + "step": 3130 + }, + { + "epoch": 0.33, + "learning_rate": 1.6987108056832506e-05, + "loss": 1.481, + "step": 3131 + }, + { + "epoch": 0.33, + "learning_rate": 1.6984489030451973e-05, + "loss": 1.4505, + "step": 3132 + }, + { + "epoch": 0.33, + "learning_rate": 1.6981869068329368e-05, + "loss": 1.4281, + "step": 3133 + }, + { + "epoch": 0.33, + "learning_rate": 1.69792481708157e-05, + "loss": 1.4555, + "step": 3134 + }, + { + "epoch": 0.33, + "learning_rate": 1.6976626338262103e-05, + "loss": 1.4525, + "step": 3135 + }, + { + "epoch": 0.33, + "learning_rate": 1.6974003571019837e-05, + "loss": 1.3765, + "step": 3136 + }, + { + "epoch": 0.33, + "learning_rate": 1.6971379869440286e-05, + "loss": 1.3998, + "step": 3137 + }, + { + "epoch": 0.33, + "learning_rate": 1.696875523387495e-05, + "loss": 1.5103, + "step": 3138 + }, + { + "epoch": 0.33, + "learning_rate": 1.6966129664675474e-05, + "loss": 1.427, + "step": 3139 + }, + { + "epoch": 0.33, + "learning_rate": 1.6963503162193612e-05, + "loss": 1.4362, + "step": 3140 + }, + { + "epoch": 0.33, + "learning_rate": 1.6960875726781246e-05, + "loss": 1.4073, + "step": 3141 + }, + { + "epoch": 0.33, + "learning_rate": 1.6958247358790388e-05, + "loss": 1.4014, + "step": 3142 + }, + { + "epoch": 0.33, + "learning_rate": 1.6955618058573165e-05, + "loss": 1.4244, + "step": 3143 + }, + { + "epoch": 0.33, + "learning_rate": 1.6952987826481847e-05, + "loss": 1.47, + "step": 3144 + }, + { + "epoch": 0.33, + "learning_rate": 1.6950356662868814e-05, + "loss": 1.5112, + "step": 3145 + }, + { + "epoch": 0.33, + "learning_rate": 1.6947724568086562e-05, + "loss": 1.3398, + "step": 3146 + }, + { + "epoch": 0.33, + "learning_rate": 1.694509154248774e-05, + "loss": 1.4584, + "step": 3147 + }, + { + "epoch": 0.33, + "learning_rate": 1.69424575864251e-05, + "loss": 1.4383, + "step": 3148 + }, + { + "epoch": 0.33, + "learning_rate": 1.6939822700251523e-05, + "loss": 1.3869, + "step": 3149 + }, + { + "epoch": 0.33, + "learning_rate": 1.6937186884320015e-05, + "loss": 1.4453, + "step": 3150 + }, + { + "epoch": 0.33, + "learning_rate": 1.6934550138983713e-05, + "loss": 1.3355, + "step": 3151 + }, + { + "epoch": 0.33, + "learning_rate": 1.6931912464595866e-05, + "loss": 1.5573, + "step": 3152 + }, + { + "epoch": 0.33, + "learning_rate": 1.6929273861509865e-05, + "loss": 1.439, + "step": 3153 + }, + { + "epoch": 0.33, + "learning_rate": 1.6926634330079203e-05, + "loss": 1.6079, + "step": 3154 + }, + { + "epoch": 0.33, + "learning_rate": 1.692399387065752e-05, + "loss": 1.6973, + "step": 3155 + }, + { + "epoch": 0.33, + "learning_rate": 1.692135248359856e-05, + "loss": 1.3769, + "step": 3156 + }, + { + "epoch": 0.33, + "learning_rate": 1.6918710169256206e-05, + "loss": 1.4454, + "step": 3157 + }, + { + "epoch": 0.33, + "learning_rate": 1.691606692798446e-05, + "loss": 1.4495, + "step": 3158 + }, + { + "epoch": 0.33, + "learning_rate": 1.691342276013745e-05, + "loss": 1.4292, + "step": 3159 + }, + { + "epoch": 0.33, + "learning_rate": 1.691077766606942e-05, + "loss": 1.4405, + "step": 3160 + }, + { + "epoch": 0.33, + "learning_rate": 1.6908131646134757e-05, + "loss": 1.3683, + "step": 3161 + }, + { + "epoch": 0.33, + "learning_rate": 1.690548470068795e-05, + "loss": 1.4731, + "step": 3162 + }, + { + "epoch": 0.33, + "learning_rate": 1.690283683008362e-05, + "loss": 1.4323, + "step": 3163 + }, + { + "epoch": 0.33, + "learning_rate": 1.6900188034676518e-05, + "loss": 1.5133, + "step": 3164 + }, + { + "epoch": 0.33, + "learning_rate": 1.6897538314821516e-05, + "loss": 1.5529, + "step": 3165 + }, + { + "epoch": 0.33, + "learning_rate": 1.6894887670873605e-05, + "loss": 1.4427, + "step": 3166 + }, + { + "epoch": 0.33, + "learning_rate": 1.6892236103187904e-05, + "loss": 1.4344, + "step": 3167 + }, + { + "epoch": 0.33, + "learning_rate": 1.6889583612119657e-05, + "loss": 1.4291, + "step": 3168 + }, + { + "epoch": 0.33, + "learning_rate": 1.6886930198024226e-05, + "loss": 1.4683, + "step": 3169 + }, + { + "epoch": 0.33, + "learning_rate": 1.6884275861257106e-05, + "loss": 1.4442, + "step": 3170 + }, + { + "epoch": 0.33, + "learning_rate": 1.6881620602173905e-05, + "loss": 1.4509, + "step": 3171 + }, + { + "epoch": 0.33, + "learning_rate": 1.6878964421130362e-05, + "loss": 1.5113, + "step": 3172 + }, + { + "epoch": 0.33, + "learning_rate": 1.6876307318482334e-05, + "loss": 1.4261, + "step": 3173 + }, + { + "epoch": 0.33, + "learning_rate": 1.6873649294585805e-05, + "loss": 1.445, + "step": 3174 + }, + { + "epoch": 0.33, + "learning_rate": 1.6870990349796886e-05, + "loss": 1.4603, + "step": 3175 + }, + { + "epoch": 0.33, + "learning_rate": 1.68683304844718e-05, + "loss": 1.41, + "step": 3176 + }, + { + "epoch": 0.33, + "learning_rate": 1.686566969896691e-05, + "loss": 1.4018, + "step": 3177 + }, + { + "epoch": 0.33, + "learning_rate": 1.6863007993638687e-05, + "loss": 1.422, + "step": 3178 + }, + { + "epoch": 0.33, + "learning_rate": 1.6860345368843727e-05, + "loss": 1.4412, + "step": 3179 + }, + { + "epoch": 0.33, + "learning_rate": 1.6857681824938768e-05, + "loss": 1.5411, + "step": 3180 + }, + { + "epoch": 0.33, + "learning_rate": 1.685501736228064e-05, + "loss": 1.4416, + "step": 3181 + }, + { + "epoch": 0.33, + "learning_rate": 1.685235198122632e-05, + "loss": 1.5113, + "step": 3182 + }, + { + "epoch": 0.33, + "learning_rate": 1.6849685682132903e-05, + "loss": 1.423, + "step": 3183 + }, + { + "epoch": 0.33, + "learning_rate": 1.68470184653576e-05, + "loss": 1.404, + "step": 3184 + }, + { + "epoch": 0.33, + "eval_loss": 1.4771089553833008, + "eval_runtime": 77.4034, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3184 + }, + { + "epoch": 0.33, + "learning_rate": 1.6844350331257747e-05, + "loss": 1.4624, + "step": 3185 + }, + { + "epoch": 0.33, + "learning_rate": 1.6841681280190814e-05, + "loss": 1.4306, + "step": 3186 + }, + { + "epoch": 0.33, + "learning_rate": 1.683901131251438e-05, + "loss": 1.42, + "step": 3187 + }, + { + "epoch": 0.33, + "learning_rate": 1.6836340428586155e-05, + "loss": 1.4787, + "step": 3188 + }, + { + "epoch": 0.33, + "learning_rate": 1.6833668628763965e-05, + "loss": 1.3485, + "step": 3189 + }, + { + "epoch": 0.33, + "learning_rate": 1.683099591340576e-05, + "loss": 1.3674, + "step": 3190 + }, + { + "epoch": 0.33, + "learning_rate": 1.6828322282869627e-05, + "loss": 1.5187, + "step": 3191 + }, + { + "epoch": 0.33, + "learning_rate": 1.682564773751375e-05, + "loss": 1.4847, + "step": 3192 + }, + { + "epoch": 0.33, + "learning_rate": 1.682297227769646e-05, + "loss": 1.4815, + "step": 3193 + }, + { + "epoch": 0.33, + "learning_rate": 1.682029590377619e-05, + "loss": 1.4281, + "step": 3194 + }, + { + "epoch": 0.34, + "learning_rate": 1.6817618616111517e-05, + "loss": 1.4734, + "step": 3195 + }, + { + "epoch": 0.34, + "learning_rate": 1.681494041506112e-05, + "loss": 1.4861, + "step": 3196 + }, + { + "epoch": 0.34, + "learning_rate": 1.6812261300983808e-05, + "loss": 1.4372, + "step": 3197 + }, + { + "epoch": 0.34, + "learning_rate": 1.680958127423852e-05, + "loss": 1.4396, + "step": 3198 + }, + { + "epoch": 0.34, + "learning_rate": 1.680690033518431e-05, + "loss": 1.4225, + "step": 3199 + }, + { + "epoch": 0.34, + "learning_rate": 1.6804218484180347e-05, + "loss": 1.4925, + "step": 3200 + }, + { + "epoch": 0.34, + "learning_rate": 1.6801535721585942e-05, + "loss": 1.4306, + "step": 3201 + }, + { + "epoch": 0.34, + "learning_rate": 1.6798852047760506e-05, + "loss": 1.4298, + "step": 3202 + }, + { + "epoch": 0.34, + "learning_rate": 1.6796167463063588e-05, + "loss": 1.4725, + "step": 3203 + }, + { + "epoch": 0.34, + "learning_rate": 1.679348196785485e-05, + "loss": 1.4648, + "step": 3204 + }, + { + "epoch": 0.34, + "learning_rate": 1.6790795562494087e-05, + "loss": 1.4152, + "step": 3205 + }, + { + "epoch": 0.34, + "learning_rate": 1.6788108247341198e-05, + "loss": 1.4637, + "step": 3206 + }, + { + "epoch": 0.34, + "learning_rate": 1.6785420022756216e-05, + "loss": 1.4077, + "step": 3207 + }, + { + "epoch": 0.34, + "learning_rate": 1.67827308890993e-05, + "loss": 1.4585, + "step": 3208 + }, + { + "epoch": 0.34, + "learning_rate": 1.678004084673072e-05, + "loss": 1.3747, + "step": 3209 + }, + { + "epoch": 0.34, + "learning_rate": 1.6777349896010876e-05, + "loss": 1.4264, + "step": 3210 + }, + { + "epoch": 0.34, + "learning_rate": 1.677465803730028e-05, + "loss": 1.4178, + "step": 3211 + }, + { + "epoch": 0.34, + "learning_rate": 1.6771965270959584e-05, + "loss": 1.3876, + "step": 3212 + }, + { + "epoch": 0.34, + "learning_rate": 1.6769271597349538e-05, + "loss": 1.4658, + "step": 3213 + }, + { + "epoch": 0.34, + "learning_rate": 1.6766577016831026e-05, + "loss": 1.3968, + "step": 3214 + }, + { + "epoch": 0.34, + "learning_rate": 1.676388152976506e-05, + "loss": 1.5015, + "step": 3215 + }, + { + "epoch": 0.34, + "learning_rate": 1.6761185136512756e-05, + "loss": 1.4121, + "step": 3216 + }, + { + "epoch": 0.34, + "learning_rate": 1.675848783743537e-05, + "loss": 1.4146, + "step": 3217 + }, + { + "epoch": 0.34, + "learning_rate": 1.675578963289427e-05, + "loss": 1.4113, + "step": 3218 + }, + { + "epoch": 0.34, + "learning_rate": 1.6753090523250937e-05, + "loss": 1.4048, + "step": 3219 + }, + { + "epoch": 0.34, + "learning_rate": 1.6750390508866994e-05, + "loss": 1.4959, + "step": 3220 + }, + { + "epoch": 0.34, + "learning_rate": 1.6747689590104167e-05, + "loss": 1.4445, + "step": 3221 + }, + { + "epoch": 0.34, + "learning_rate": 1.6744987767324312e-05, + "loss": 1.4611, + "step": 3222 + }, + { + "epoch": 0.34, + "learning_rate": 1.67422850408894e-05, + "loss": 1.4141, + "step": 3223 + }, + { + "epoch": 0.34, + "learning_rate": 1.6739581411161535e-05, + "loss": 1.4218, + "step": 3224 + }, + { + "epoch": 0.34, + "learning_rate": 1.6736876878502925e-05, + "loss": 1.4266, + "step": 3225 + }, + { + "epoch": 0.34, + "learning_rate": 1.6734171443275913e-05, + "loss": 1.4941, + "step": 3226 + }, + { + "epoch": 0.34, + "learning_rate": 1.6731465105842955e-05, + "loss": 1.4294, + "step": 3227 + }, + { + "epoch": 0.34, + "learning_rate": 1.6728757866566635e-05, + "loss": 1.4189, + "step": 3228 + }, + { + "epoch": 0.34, + "learning_rate": 1.6726049725809647e-05, + "loss": 1.4713, + "step": 3229 + }, + { + "epoch": 0.34, + "learning_rate": 1.6723340683934818e-05, + "loss": 1.4203, + "step": 3230 + }, + { + "epoch": 0.34, + "learning_rate": 1.6720630741305088e-05, + "loss": 1.4112, + "step": 3231 + }, + { + "epoch": 0.34, + "learning_rate": 1.6717919898283523e-05, + "loss": 1.3811, + "step": 3232 + }, + { + "epoch": 0.34, + "learning_rate": 1.6715208155233296e-05, + "loss": 1.4242, + "step": 3233 + }, + { + "epoch": 0.34, + "learning_rate": 1.6712495512517725e-05, + "loss": 1.4207, + "step": 3234 + }, + { + "epoch": 0.34, + "learning_rate": 1.6709781970500222e-05, + "loss": 1.4888, + "step": 3235 + }, + { + "epoch": 0.34, + "learning_rate": 1.670706752954434e-05, + "loss": 1.4501, + "step": 3236 + }, + { + "epoch": 0.34, + "learning_rate": 1.670435219001374e-05, + "loss": 1.4367, + "step": 3237 + }, + { + "epoch": 0.34, + "learning_rate": 1.6701635952272212e-05, + "loss": 1.3959, + "step": 3238 + }, + { + "epoch": 0.34, + "learning_rate": 1.6698918816683655e-05, + "loss": 1.4257, + "step": 3239 + }, + { + "epoch": 0.34, + "learning_rate": 1.6696200783612102e-05, + "loss": 1.4718, + "step": 3240 + }, + { + "epoch": 0.34, + "learning_rate": 1.6693481853421697e-05, + "loss": 1.5899, + "step": 3241 + }, + { + "epoch": 0.34, + "learning_rate": 1.6690762026476707e-05, + "loss": 1.418, + "step": 3242 + }, + { + "epoch": 0.34, + "learning_rate": 1.668804130314152e-05, + "loss": 1.4076, + "step": 3243 + }, + { + "epoch": 0.34, + "learning_rate": 1.6685319683780645e-05, + "loss": 1.4571, + "step": 3244 + }, + { + "epoch": 0.34, + "learning_rate": 1.66825971687587e-05, + "loss": 1.4066, + "step": 3245 + }, + { + "epoch": 0.34, + "learning_rate": 1.6679873758440442e-05, + "loss": 1.4639, + "step": 3246 + }, + { + "epoch": 0.34, + "learning_rate": 1.6677149453190732e-05, + "loss": 1.453, + "step": 3247 + }, + { + "epoch": 0.34, + "learning_rate": 1.6674424253374558e-05, + "loss": 1.4262, + "step": 3248 + }, + { + "epoch": 0.34, + "learning_rate": 1.667169815935703e-05, + "loss": 1.3687, + "step": 3249 + }, + { + "epoch": 0.34, + "learning_rate": 1.6668971171503372e-05, + "loss": 1.5557, + "step": 3250 + }, + { + "epoch": 0.34, + "learning_rate": 1.6666243290178933e-05, + "loss": 1.4639, + "step": 3251 + }, + { + "epoch": 0.34, + "learning_rate": 1.6663514515749172e-05, + "loss": 1.4334, + "step": 3252 + }, + { + "epoch": 0.34, + "learning_rate": 1.6660784848579685e-05, + "loss": 1.3523, + "step": 3253 + }, + { + "epoch": 0.34, + "learning_rate": 1.6658054289036166e-05, + "loss": 1.3738, + "step": 3254 + }, + { + "epoch": 0.34, + "learning_rate": 1.665532283748445e-05, + "loss": 1.4159, + "step": 3255 + }, + { + "epoch": 0.34, + "learning_rate": 1.6652590494290474e-05, + "loss": 1.3609, + "step": 3256 + }, + { + "epoch": 0.34, + "learning_rate": 1.6649857259820303e-05, + "loss": 1.4449, + "step": 3257 + }, + { + "epoch": 0.34, + "learning_rate": 1.6647123134440126e-05, + "loss": 1.424, + "step": 3258 + }, + { + "epoch": 0.34, + "learning_rate": 1.664438811851624e-05, + "loss": 1.4737, + "step": 3259 + }, + { + "epoch": 0.34, + "learning_rate": 1.6641652212415066e-05, + "loss": 1.2717, + "step": 3260 + }, + { + "epoch": 0.34, + "learning_rate": 1.663891541650315e-05, + "loss": 1.4845, + "step": 3261 + }, + { + "epoch": 0.34, + "learning_rate": 1.663617773114715e-05, + "loss": 1.4115, + "step": 3262 + }, + { + "epoch": 0.34, + "learning_rate": 1.663343915671384e-05, + "loss": 1.4237, + "step": 3263 + }, + { + "epoch": 0.34, + "learning_rate": 1.6630699693570127e-05, + "loss": 1.4209, + "step": 3264 + }, + { + "epoch": 0.34, + "learning_rate": 1.6627959342083026e-05, + "loss": 1.506, + "step": 3265 + }, + { + "epoch": 0.34, + "learning_rate": 1.6625218102619672e-05, + "loss": 1.4466, + "step": 3266 + }, + { + "epoch": 0.34, + "learning_rate": 1.6622475975547324e-05, + "loss": 1.4129, + "step": 3267 + }, + { + "epoch": 0.34, + "learning_rate": 1.661973296123335e-05, + "loss": 1.4152, + "step": 3268 + }, + { + "epoch": 0.34, + "learning_rate": 1.661698906004525e-05, + "loss": 1.43, + "step": 3269 + }, + { + "epoch": 0.34, + "learning_rate": 1.661424427235064e-05, + "loss": 1.4701, + "step": 3270 + }, + { + "epoch": 0.34, + "learning_rate": 1.6611498598517238e-05, + "loss": 1.4598, + "step": 3271 + }, + { + "epoch": 0.34, + "learning_rate": 1.66087520389129e-05, + "loss": 1.4795, + "step": 3272 + }, + { + "epoch": 0.34, + "learning_rate": 1.6606004593905595e-05, + "loss": 1.5264, + "step": 3273 + }, + { + "epoch": 0.34, + "learning_rate": 1.6603256263863415e-05, + "loss": 1.4412, + "step": 3274 + }, + { + "epoch": 0.34, + "learning_rate": 1.6600507049154556e-05, + "loss": 1.45, + "step": 3275 + }, + { + "epoch": 0.34, + "learning_rate": 1.659775695014735e-05, + "loss": 1.4985, + "step": 3276 + }, + { + "epoch": 0.34, + "learning_rate": 1.659500596721024e-05, + "loss": 1.496, + "step": 3277 + }, + { + "epoch": 0.34, + "learning_rate": 1.6592254100711775e-05, + "loss": 1.4386, + "step": 3278 + }, + { + "epoch": 0.34, + "learning_rate": 1.658950135102065e-05, + "loss": 1.4073, + "step": 3279 + }, + { + "epoch": 0.34, + "learning_rate": 1.658674771850565e-05, + "loss": 1.3912, + "step": 3280 + }, + { + "epoch": 0.34, + "learning_rate": 1.6583993203535702e-05, + "loss": 1.3628, + "step": 3281 + }, + { + "epoch": 0.34, + "learning_rate": 1.658123780647983e-05, + "loss": 1.6089, + "step": 3282 + }, + { + "epoch": 0.34, + "learning_rate": 1.6578481527707196e-05, + "loss": 1.2367, + "step": 3283 + }, + { + "epoch": 0.34, + "learning_rate": 1.657572436758706e-05, + "loss": 1.4058, + "step": 3284 + }, + { + "epoch": 0.34, + "learning_rate": 1.6572966326488825e-05, + "loss": 1.4067, + "step": 3285 + }, + { + "epoch": 0.34, + "learning_rate": 1.657020740478198e-05, + "loss": 1.4187, + "step": 3286 + }, + { + "epoch": 0.34, + "learning_rate": 1.6567447602836166e-05, + "loss": 1.4599, + "step": 3287 + }, + { + "epoch": 0.34, + "learning_rate": 1.6564686921021115e-05, + "loss": 1.432, + "step": 3288 + }, + { + "epoch": 0.34, + "learning_rate": 1.6561925359706693e-05, + "loss": 1.3941, + "step": 3289 + }, + { + "epoch": 0.35, + "learning_rate": 1.6559162919262874e-05, + "loss": 1.3644, + "step": 3290 + }, + { + "epoch": 0.35, + "learning_rate": 1.6556399600059756e-05, + "loss": 1.4628, + "step": 3291 + }, + { + "epoch": 0.35, + "learning_rate": 1.6553635402467555e-05, + "loss": 1.4355, + "step": 3292 + }, + { + "epoch": 0.35, + "learning_rate": 1.6550870326856596e-05, + "loss": 1.4627, + "step": 3293 + }, + { + "epoch": 0.35, + "learning_rate": 1.6548104373597335e-05, + "loss": 1.442, + "step": 3294 + }, + { + "epoch": 0.35, + "learning_rate": 1.6545337543060338e-05, + "loss": 1.3991, + "step": 3295 + }, + { + "epoch": 0.35, + "learning_rate": 1.6542569835616283e-05, + "loss": 1.4193, + "step": 3296 + }, + { + "epoch": 0.35, + "learning_rate": 1.6539801251635982e-05, + "loss": 1.4792, + "step": 3297 + }, + { + "epoch": 0.35, + "learning_rate": 1.653703179149034e-05, + "loss": 1.4735, + "step": 3298 + }, + { + "epoch": 0.35, + "learning_rate": 1.6534261455550408e-05, + "loss": 1.451, + "step": 3299 + }, + { + "epoch": 0.35, + "learning_rate": 1.653149024418733e-05, + "loss": 1.3975, + "step": 3300 + }, + { + "epoch": 0.35, + "learning_rate": 1.652871815777238e-05, + "loss": 1.4843, + "step": 3301 + }, + { + "epoch": 0.35, + "learning_rate": 1.6525945196676948e-05, + "loss": 1.4782, + "step": 3302 + }, + { + "epoch": 0.35, + "learning_rate": 1.652317136127254e-05, + "loss": 1.3865, + "step": 3303 + }, + { + "epoch": 0.35, + "learning_rate": 1.6520396651930777e-05, + "loss": 1.4359, + "step": 3304 + }, + { + "epoch": 0.35, + "learning_rate": 1.6517621069023397e-05, + "loss": 1.4289, + "step": 3305 + }, + { + "epoch": 0.35, + "learning_rate": 1.651484461292226e-05, + "loss": 1.3526, + "step": 3306 + }, + { + "epoch": 0.35, + "learning_rate": 1.6512067283999336e-05, + "loss": 1.3671, + "step": 3307 + }, + { + "epoch": 0.35, + "learning_rate": 1.650928908262672e-05, + "loss": 1.6041, + "step": 3308 + }, + { + "epoch": 0.35, + "learning_rate": 1.650651000917662e-05, + "loss": 1.4322, + "step": 3309 + }, + { + "epoch": 0.35, + "learning_rate": 1.6503730064021354e-05, + "loss": 1.3992, + "step": 3310 + }, + { + "epoch": 0.35, + "learning_rate": 1.650094924753337e-05, + "loss": 1.4928, + "step": 3311 + }, + { + "epoch": 0.35, + "learning_rate": 1.6498167560085222e-05, + "loss": 1.4075, + "step": 3312 + }, + { + "epoch": 0.35, + "learning_rate": 1.6495385002049583e-05, + "loss": 1.4535, + "step": 3313 + }, + { + "epoch": 0.35, + "learning_rate": 1.6492601573799253e-05, + "loss": 1.4221, + "step": 3314 + }, + { + "epoch": 0.35, + "learning_rate": 1.6489817275707133e-05, + "loss": 1.3688, + "step": 3315 + }, + { + "epoch": 0.35, + "learning_rate": 1.6487032108146243e-05, + "loss": 1.3889, + "step": 3316 + }, + { + "epoch": 0.35, + "learning_rate": 1.6484246071489733e-05, + "loss": 1.3942, + "step": 3317 + }, + { + "epoch": 0.35, + "learning_rate": 1.6481459166110858e-05, + "loss": 1.4004, + "step": 3318 + }, + { + "epoch": 0.35, + "learning_rate": 1.647867139238299e-05, + "loss": 1.7308, + "step": 3319 + }, + { + "epoch": 0.35, + "learning_rate": 1.6475882750679622e-05, + "loss": 1.5001, + "step": 3320 + }, + { + "epoch": 0.35, + "learning_rate": 1.647309324137435e-05, + "loss": 1.4325, + "step": 3321 + }, + { + "epoch": 0.35, + "learning_rate": 1.6470302864840913e-05, + "loss": 1.4494, + "step": 3322 + }, + { + "epoch": 0.35, + "learning_rate": 1.6467511621453136e-05, + "loss": 1.4418, + "step": 3323 + }, + { + "epoch": 0.35, + "learning_rate": 1.646471951158498e-05, + "loss": 1.4046, + "step": 3324 + }, + { + "epoch": 0.35, + "learning_rate": 1.6461926535610517e-05, + "loss": 1.5031, + "step": 3325 + }, + { + "epoch": 0.35, + "learning_rate": 1.645913269390393e-05, + "loss": 1.4813, + "step": 3326 + }, + { + "epoch": 0.35, + "learning_rate": 1.6456337986839525e-05, + "loss": 1.3842, + "step": 3327 + }, + { + "epoch": 0.35, + "learning_rate": 1.645354241479172e-05, + "loss": 1.4539, + "step": 3328 + }, + { + "epoch": 0.35, + "learning_rate": 1.6450745978135048e-05, + "loss": 1.4503, + "step": 3329 + }, + { + "epoch": 0.35, + "learning_rate": 1.6447948677244163e-05, + "loss": 1.3741, + "step": 3330 + }, + { + "epoch": 0.35, + "learning_rate": 1.6445150512493832e-05, + "loss": 1.425, + "step": 3331 + }, + { + "epoch": 0.35, + "learning_rate": 1.644235148425893e-05, + "loss": 1.4277, + "step": 3332 + }, + { + "epoch": 0.35, + "learning_rate": 1.6439551592914464e-05, + "loss": 1.4918, + "step": 3333 + }, + { + "epoch": 0.35, + "learning_rate": 1.6436750838835543e-05, + "loss": 1.3364, + "step": 3334 + }, + { + "epoch": 0.35, + "learning_rate": 1.6433949222397397e-05, + "loss": 1.4741, + "step": 3335 + }, + { + "epoch": 0.35, + "learning_rate": 1.643114674397537e-05, + "loss": 1.3867, + "step": 3336 + }, + { + "epoch": 0.35, + "learning_rate": 1.642834340394492e-05, + "loss": 1.3817, + "step": 3337 + }, + { + "epoch": 0.35, + "learning_rate": 1.6425539202681625e-05, + "loss": 1.4308, + "step": 3338 + }, + { + "epoch": 0.35, + "learning_rate": 1.6422734140561178e-05, + "loss": 1.4401, + "step": 3339 + }, + { + "epoch": 0.35, + "learning_rate": 1.641992821795938e-05, + "loss": 1.4338, + "step": 3340 + }, + { + "epoch": 0.35, + "learning_rate": 1.641712143525216e-05, + "loss": 1.3804, + "step": 3341 + }, + { + "epoch": 0.35, + "learning_rate": 1.6414313792815546e-05, + "loss": 1.371, + "step": 3342 + }, + { + "epoch": 0.35, + "learning_rate": 1.6411505291025695e-05, + "loss": 1.4102, + "step": 3343 + }, + { + "epoch": 0.35, + "learning_rate": 1.6408695930258875e-05, + "loss": 1.4433, + "step": 3344 + }, + { + "epoch": 0.35, + "learning_rate": 1.6405885710891467e-05, + "loss": 1.3895, + "step": 3345 + }, + { + "epoch": 0.35, + "learning_rate": 1.6403074633299966e-05, + "loss": 1.4321, + "step": 3346 + }, + { + "epoch": 0.35, + "learning_rate": 1.640026269786098e-05, + "loss": 1.4207, + "step": 3347 + }, + { + "epoch": 0.35, + "learning_rate": 1.639744990495125e-05, + "loss": 1.3758, + "step": 3348 + }, + { + "epoch": 0.35, + "learning_rate": 1.6394636254947612e-05, + "loss": 1.4203, + "step": 3349 + }, + { + "epoch": 0.35, + "learning_rate": 1.6391821748227013e-05, + "loss": 1.4596, + "step": 3350 + }, + { + "epoch": 0.35, + "learning_rate": 1.6389006385166537e-05, + "loss": 1.4344, + "step": 3351 + }, + { + "epoch": 0.35, + "learning_rate": 1.6386190166143366e-05, + "loss": 1.4048, + "step": 3352 + }, + { + "epoch": 0.35, + "learning_rate": 1.6383373091534798e-05, + "loss": 1.4348, + "step": 3353 + }, + { + "epoch": 0.35, + "learning_rate": 1.638055516171825e-05, + "loss": 1.4972, + "step": 3354 + }, + { + "epoch": 0.35, + "learning_rate": 1.6377736377071258e-05, + "loss": 1.4685, + "step": 3355 + }, + { + "epoch": 0.35, + "learning_rate": 1.637491673797146e-05, + "loss": 1.4093, + "step": 3356 + }, + { + "epoch": 0.35, + "learning_rate": 1.6372096244796616e-05, + "loss": 1.4452, + "step": 3357 + }, + { + "epoch": 0.35, + "learning_rate": 1.63692748979246e-05, + "loss": 1.4458, + "step": 3358 + }, + { + "epoch": 0.35, + "learning_rate": 1.6366452697733404e-05, + "loss": 1.4187, + "step": 3359 + }, + { + "epoch": 0.35, + "learning_rate": 1.6363629644601126e-05, + "loss": 1.4052, + "step": 3360 + }, + { + "epoch": 0.35, + "learning_rate": 1.6360805738905984e-05, + "loss": 1.439, + "step": 3361 + }, + { + "epoch": 0.35, + "learning_rate": 1.635798098102631e-05, + "loss": 1.4131, + "step": 3362 + }, + { + "epoch": 0.35, + "learning_rate": 1.6355155371340544e-05, + "loss": 1.4391, + "step": 3363 + }, + { + "epoch": 0.35, + "learning_rate": 1.6352328910227252e-05, + "loss": 1.4318, + "step": 3364 + }, + { + "epoch": 0.35, + "learning_rate": 1.63495015980651e-05, + "loss": 1.5112, + "step": 3365 + }, + { + "epoch": 0.35, + "learning_rate": 1.6346673435232884e-05, + "loss": 1.4688, + "step": 3366 + }, + { + "epoch": 0.35, + "learning_rate": 1.6343844422109496e-05, + "loss": 1.3807, + "step": 3367 + }, + { + "epoch": 0.35, + "learning_rate": 1.634101455907396e-05, + "loss": 1.4083, + "step": 3368 + }, + { + "epoch": 0.35, + "learning_rate": 1.6338183846505394e-05, + "loss": 1.3566, + "step": 3369 + }, + { + "epoch": 0.35, + "learning_rate": 1.633535228478305e-05, + "loss": 1.4287, + "step": 3370 + }, + { + "epoch": 0.35, + "learning_rate": 1.6332519874286285e-05, + "loss": 1.3494, + "step": 3371 + }, + { + "epoch": 0.35, + "learning_rate": 1.6329686615394558e-05, + "loss": 1.3813, + "step": 3372 + }, + { + "epoch": 0.35, + "learning_rate": 1.6326852508487468e-05, + "loss": 1.4241, + "step": 3373 + }, + { + "epoch": 0.35, + "learning_rate": 1.63240175539447e-05, + "loss": 1.424, + "step": 3374 + }, + { + "epoch": 0.35, + "learning_rate": 1.632118175214607e-05, + "loss": 1.4212, + "step": 3375 + }, + { + "epoch": 0.35, + "learning_rate": 1.6318345103471504e-05, + "loss": 1.4671, + "step": 3376 + }, + { + "epoch": 0.35, + "learning_rate": 1.6315507608301044e-05, + "loss": 1.4593, + "step": 3377 + }, + { + "epoch": 0.35, + "learning_rate": 1.631266926701483e-05, + "loss": 1.7816, + "step": 3378 + }, + { + "epoch": 0.35, + "learning_rate": 1.6309830079993134e-05, + "loss": 1.5134, + "step": 3379 + }, + { + "epoch": 0.35, + "learning_rate": 1.6306990047616334e-05, + "loss": 0.8933, + "step": 3380 + }, + { + "epoch": 0.35, + "learning_rate": 1.630414917026492e-05, + "loss": 1.1033, + "step": 3381 + }, + { + "epoch": 0.35, + "learning_rate": 1.6301307448319497e-05, + "loss": 1.3494, + "step": 3382 + }, + { + "epoch": 0.35, + "learning_rate": 1.6298464882160784e-05, + "loss": 1.4299, + "step": 3383 + }, + { + "epoch": 0.35, + "eval_loss": 1.482450008392334, + "eval_runtime": 77.3737, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3383 + }, + { + "epoch": 0.35, + "learning_rate": 1.629562147216961e-05, + "loss": 1.3971, + "step": 3384 + }, + { + "epoch": 0.35, + "learning_rate": 1.6292777218726917e-05, + "loss": 1.3706, + "step": 3385 + }, + { + "epoch": 0.36, + "learning_rate": 1.6289932122213765e-05, + "loss": 1.4524, + "step": 3386 + }, + { + "epoch": 0.36, + "learning_rate": 1.6287086183011328e-05, + "loss": 1.4595, + "step": 3387 + }, + { + "epoch": 0.36, + "learning_rate": 1.628423940150088e-05, + "loss": 1.492, + "step": 3388 + }, + { + "epoch": 0.36, + "learning_rate": 1.628139177806382e-05, + "loss": 1.5576, + "step": 3389 + }, + { + "epoch": 0.36, + "learning_rate": 1.6278543313081657e-05, + "loss": 1.4615, + "step": 3390 + }, + { + "epoch": 0.36, + "learning_rate": 1.6275694006936015e-05, + "loss": 1.3456, + "step": 3391 + }, + { + "epoch": 0.36, + "learning_rate": 1.627284386000862e-05, + "loss": 1.4254, + "step": 3392 + }, + { + "epoch": 0.36, + "learning_rate": 1.6269992872681325e-05, + "loss": 1.433, + "step": 3393 + }, + { + "epoch": 0.36, + "learning_rate": 1.626714104533609e-05, + "loss": 1.5291, + "step": 3394 + }, + { + "epoch": 0.36, + "learning_rate": 1.626428837835498e-05, + "loss": 1.4502, + "step": 3395 + }, + { + "epoch": 0.36, + "learning_rate": 1.626143487212019e-05, + "loss": 1.3756, + "step": 3396 + }, + { + "epoch": 0.36, + "learning_rate": 1.6258580527014002e-05, + "loss": 1.414, + "step": 3397 + }, + { + "epoch": 0.36, + "learning_rate": 1.6255725343418835e-05, + "loss": 1.6289, + "step": 3398 + }, + { + "epoch": 0.36, + "learning_rate": 1.6252869321717208e-05, + "loss": 1.4862, + "step": 3399 + }, + { + "epoch": 0.36, + "learning_rate": 1.6250012462291756e-05, + "loss": 1.4213, + "step": 3400 + }, + { + "epoch": 0.36, + "learning_rate": 1.6247154765525217e-05, + "loss": 1.524, + "step": 3401 + }, + { + "epoch": 0.36, + "learning_rate": 1.624429623180046e-05, + "loss": 1.6013, + "step": 3402 + }, + { + "epoch": 0.36, + "learning_rate": 1.624143686150045e-05, + "loss": 1.4557, + "step": 3403 + }, + { + "epoch": 0.36, + "learning_rate": 1.6238576655008266e-05, + "loss": 1.3831, + "step": 3404 + }, + { + "epoch": 0.36, + "learning_rate": 1.6235715612707105e-05, + "loss": 1.4008, + "step": 3405 + }, + { + "epoch": 0.36, + "learning_rate": 1.623285373498028e-05, + "loss": 1.4848, + "step": 3406 + }, + { + "epoch": 0.36, + "learning_rate": 1.6229991022211197e-05, + "loss": 1.4459, + "step": 3407 + }, + { + "epoch": 0.36, + "learning_rate": 1.6227127474783393e-05, + "loss": 1.4334, + "step": 3408 + }, + { + "epoch": 0.36, + "learning_rate": 1.6224263093080507e-05, + "loss": 1.4123, + "step": 3409 + }, + { + "epoch": 0.36, + "learning_rate": 1.6221397877486294e-05, + "loss": 1.3691, + "step": 3410 + }, + { + "epoch": 0.36, + "learning_rate": 1.6218531828384618e-05, + "loss": 1.4128, + "step": 3411 + }, + { + "epoch": 0.36, + "learning_rate": 1.6215664946159457e-05, + "loss": 1.3642, + "step": 3412 + }, + { + "epoch": 0.36, + "learning_rate": 1.6212797231194902e-05, + "loss": 1.4311, + "step": 3413 + }, + { + "epoch": 0.36, + "learning_rate": 1.6209928683875152e-05, + "loss": 1.4695, + "step": 3414 + }, + { + "epoch": 0.36, + "learning_rate": 1.6207059304584514e-05, + "loss": 1.3871, + "step": 3415 + }, + { + "epoch": 0.36, + "learning_rate": 1.6204189093707414e-05, + "loss": 1.4219, + "step": 3416 + }, + { + "epoch": 0.36, + "learning_rate": 1.620131805162839e-05, + "loss": 1.6199, + "step": 3417 + }, + { + "epoch": 0.36, + "learning_rate": 1.619844617873208e-05, + "loss": 1.4433, + "step": 3418 + }, + { + "epoch": 0.36, + "learning_rate": 1.619557347540325e-05, + "loss": 1.4773, + "step": 3419 + }, + { + "epoch": 0.36, + "learning_rate": 1.6192699942026763e-05, + "loss": 1.4551, + "step": 3420 + }, + { + "epoch": 0.36, + "learning_rate": 1.6189825578987603e-05, + "loss": 1.4903, + "step": 3421 + }, + { + "epoch": 0.36, + "learning_rate": 1.6186950386670855e-05, + "loss": 1.473, + "step": 3422 + }, + { + "epoch": 0.36, + "learning_rate": 1.6184074365461722e-05, + "loss": 1.4082, + "step": 3423 + }, + { + "epoch": 0.36, + "learning_rate": 1.6181197515745523e-05, + "loss": 1.4746, + "step": 3424 + }, + { + "epoch": 0.36, + "learning_rate": 1.6178319837907674e-05, + "loss": 1.449, + "step": 3425 + }, + { + "epoch": 0.36, + "learning_rate": 1.6175441332333715e-05, + "loss": 1.377, + "step": 3426 + }, + { + "epoch": 0.36, + "learning_rate": 1.617256199940929e-05, + "loss": 1.2364, + "step": 3427 + }, + { + "epoch": 0.36, + "learning_rate": 1.6169681839520155e-05, + "loss": 1.4437, + "step": 3428 + }, + { + "epoch": 0.36, + "learning_rate": 1.616680085305218e-05, + "loss": 1.4726, + "step": 3429 + }, + { + "epoch": 0.36, + "learning_rate": 1.616391904039134e-05, + "loss": 1.4824, + "step": 3430 + }, + { + "epoch": 0.36, + "learning_rate": 1.616103640192373e-05, + "loss": 1.4052, + "step": 3431 + }, + { + "epoch": 0.36, + "learning_rate": 1.6158152938035537e-05, + "loss": 1.4131, + "step": 3432 + }, + { + "epoch": 0.36, + "learning_rate": 1.6155268649113084e-05, + "loss": 1.4267, + "step": 3433 + }, + { + "epoch": 0.36, + "learning_rate": 1.6152383535542786e-05, + "loss": 1.3735, + "step": 3434 + }, + { + "epoch": 0.36, + "learning_rate": 1.6149497597711175e-05, + "loss": 1.4249, + "step": 3435 + }, + { + "epoch": 0.36, + "learning_rate": 1.614661083600489e-05, + "loss": 1.4312, + "step": 3436 + }, + { + "epoch": 0.36, + "learning_rate": 1.6143723250810686e-05, + "loss": 1.4831, + "step": 3437 + }, + { + "epoch": 0.36, + "learning_rate": 1.6140834842515425e-05, + "loss": 1.4183, + "step": 3438 + }, + { + "epoch": 0.36, + "learning_rate": 1.6137945611506078e-05, + "loss": 1.3908, + "step": 3439 + }, + { + "epoch": 0.36, + "learning_rate": 1.613505555816973e-05, + "loss": 1.425, + "step": 3440 + }, + { + "epoch": 0.36, + "learning_rate": 1.613216468289357e-05, + "loss": 1.3589, + "step": 3441 + }, + { + "epoch": 0.36, + "learning_rate": 1.6129272986064903e-05, + "loss": 1.4272, + "step": 3442 + }, + { + "epoch": 0.36, + "learning_rate": 1.6126380468071142e-05, + "loss": 1.4337, + "step": 3443 + }, + { + "epoch": 0.36, + "learning_rate": 1.6123487129299817e-05, + "loss": 1.3872, + "step": 3444 + }, + { + "epoch": 0.36, + "learning_rate": 1.612059297013855e-05, + "loss": 1.374, + "step": 3445 + }, + { + "epoch": 0.36, + "learning_rate": 1.611769799097509e-05, + "loss": 1.314, + "step": 3446 + }, + { + "epoch": 0.36, + "learning_rate": 1.6114802192197284e-05, + "loss": 1.3951, + "step": 3447 + }, + { + "epoch": 0.36, + "learning_rate": 1.6111905574193102e-05, + "loss": 1.4732, + "step": 3448 + }, + { + "epoch": 0.36, + "learning_rate": 1.6109008137350614e-05, + "loss": 1.3575, + "step": 3449 + }, + { + "epoch": 0.36, + "learning_rate": 1.6106109882058e-05, + "loss": 1.4606, + "step": 3450 + }, + { + "epoch": 0.36, + "learning_rate": 1.6103210808703554e-05, + "loss": 1.4357, + "step": 3451 + }, + { + "epoch": 0.36, + "learning_rate": 1.6100310917675678e-05, + "loss": 0.8456, + "step": 3452 + }, + { + "epoch": 0.36, + "learning_rate": 1.609741020936288e-05, + "loss": 1.07, + "step": 3453 + }, + { + "epoch": 0.36, + "learning_rate": 1.6094508684153782e-05, + "loss": 1.4435, + "step": 3454 + }, + { + "epoch": 0.36, + "learning_rate": 1.609160634243711e-05, + "loss": 1.3696, + "step": 3455 + }, + { + "epoch": 0.36, + "learning_rate": 1.6088703184601712e-05, + "loss": 1.4012, + "step": 3456 + }, + { + "epoch": 0.36, + "learning_rate": 1.608579921103653e-05, + "loss": 1.5212, + "step": 3457 + }, + { + "epoch": 0.36, + "learning_rate": 1.608289442213062e-05, + "loss": 1.4339, + "step": 3458 + }, + { + "epoch": 0.36, + "learning_rate": 1.607998881827316e-05, + "loss": 1.4901, + "step": 3459 + }, + { + "epoch": 0.36, + "learning_rate": 1.6077082399853412e-05, + "loss": 1.4822, + "step": 3460 + }, + { + "epoch": 0.36, + "learning_rate": 1.607417516726077e-05, + "loss": 1.3696, + "step": 3461 + }, + { + "epoch": 0.36, + "learning_rate": 1.6071267120884727e-05, + "loss": 1.4434, + "step": 3462 + }, + { + "epoch": 0.36, + "learning_rate": 1.6068358261114886e-05, + "loss": 1.3916, + "step": 3463 + }, + { + "epoch": 0.36, + "learning_rate": 1.606544858834096e-05, + "loss": 1.422, + "step": 3464 + }, + { + "epoch": 0.36, + "learning_rate": 1.6062538102952763e-05, + "loss": 1.367, + "step": 3465 + }, + { + "epoch": 0.36, + "learning_rate": 1.605962680534024e-05, + "loss": 1.3788, + "step": 3466 + }, + { + "epoch": 0.36, + "learning_rate": 1.605671469589342e-05, + "loss": 1.4366, + "step": 3467 + }, + { + "epoch": 0.36, + "learning_rate": 1.6053801775002453e-05, + "loss": 1.4027, + "step": 3468 + }, + { + "epoch": 0.36, + "learning_rate": 1.6050888043057595e-05, + "loss": 1.4386, + "step": 3469 + }, + { + "epoch": 0.36, + "learning_rate": 1.6047973500449212e-05, + "loss": 1.4675, + "step": 3470 + }, + { + "epoch": 0.36, + "learning_rate": 1.6045058147567778e-05, + "loss": 1.6936, + "step": 3471 + }, + { + "epoch": 0.36, + "learning_rate": 1.6042141984803875e-05, + "loss": 1.4858, + "step": 3472 + }, + { + "epoch": 0.36, + "learning_rate": 1.6039225012548196e-05, + "loss": 1.5004, + "step": 3473 + }, + { + "epoch": 0.36, + "learning_rate": 1.6036307231191534e-05, + "loss": 1.4969, + "step": 3474 + }, + { + "epoch": 0.36, + "learning_rate": 1.6033388641124803e-05, + "loss": 1.4027, + "step": 3475 + }, + { + "epoch": 0.36, + "learning_rate": 1.6030469242739016e-05, + "loss": 1.4741, + "step": 3476 + }, + { + "epoch": 0.36, + "learning_rate": 1.60275490364253e-05, + "loss": 1.3887, + "step": 3477 + }, + { + "epoch": 0.36, + "learning_rate": 1.602462802257488e-05, + "loss": 1.6735, + "step": 3478 + }, + { + "epoch": 0.36, + "learning_rate": 1.602170620157911e-05, + "loss": 1.4997, + "step": 3479 + }, + { + "epoch": 0.36, + "learning_rate": 1.601878357382943e-05, + "loss": 1.3973, + "step": 3480 + }, + { + "epoch": 0.37, + "learning_rate": 1.6015860139717398e-05, + "loss": 1.416, + "step": 3481 + }, + { + "epoch": 0.37, + "learning_rate": 1.6012935899634682e-05, + "loss": 1.4102, + "step": 3482 + }, + { + "epoch": 0.37, + "learning_rate": 1.601001085397305e-05, + "loss": 1.4248, + "step": 3483 + }, + { + "epoch": 0.37, + "learning_rate": 1.6007085003124386e-05, + "loss": 1.3909, + "step": 3484 + }, + { + "epoch": 0.37, + "learning_rate": 1.600415834748068e-05, + "loss": 1.4029, + "step": 3485 + }, + { + "epoch": 0.37, + "learning_rate": 1.6001230887434024e-05, + "loss": 1.4219, + "step": 3486 + }, + { + "epoch": 0.37, + "learning_rate": 1.5998302623376633e-05, + "loss": 1.4008, + "step": 3487 + }, + { + "epoch": 0.37, + "learning_rate": 1.5995373555700806e-05, + "loss": 1.5163, + "step": 3488 + }, + { + "epoch": 0.37, + "learning_rate": 1.599244368479897e-05, + "loss": 1.4541, + "step": 3489 + }, + { + "epoch": 0.37, + "learning_rate": 1.598951301106365e-05, + "loss": 1.4454, + "step": 3490 + }, + { + "epoch": 0.37, + "learning_rate": 1.598658153488748e-05, + "loss": 1.1014, + "step": 3491 + }, + { + "epoch": 0.37, + "learning_rate": 1.598364925666321e-05, + "loss": 1.407, + "step": 3492 + }, + { + "epoch": 0.37, + "learning_rate": 1.5980716176783682e-05, + "loss": 1.5046, + "step": 3493 + }, + { + "epoch": 0.37, + "learning_rate": 1.5977782295641857e-05, + "loss": 1.4265, + "step": 3494 + }, + { + "epoch": 0.37, + "learning_rate": 1.5974847613630796e-05, + "loss": 1.46, + "step": 3495 + }, + { + "epoch": 0.37, + "learning_rate": 1.5971912131143677e-05, + "loss": 1.3996, + "step": 3496 + }, + { + "epoch": 0.37, + "learning_rate": 1.5968975848573772e-05, + "loss": 1.4719, + "step": 3497 + }, + { + "epoch": 0.37, + "learning_rate": 1.596603876631447e-05, + "loss": 1.43, + "step": 3498 + }, + { + "epoch": 0.37, + "learning_rate": 1.596310088475927e-05, + "loss": 1.4109, + "step": 3499 + }, + { + "epoch": 0.37, + "learning_rate": 1.5960162204301768e-05, + "loss": 1.3612, + "step": 3500 + }, + { + "epoch": 0.37, + "learning_rate": 1.5957222725335672e-05, + "loss": 1.5045, + "step": 3501 + }, + { + "epoch": 0.37, + "learning_rate": 1.5954282448254794e-05, + "loss": 1.5323, + "step": 3502 + }, + { + "epoch": 0.37, + "learning_rate": 1.595134137345306e-05, + "loss": 1.4518, + "step": 3503 + }, + { + "epoch": 0.37, + "learning_rate": 1.5948399501324495e-05, + "loss": 1.6131, + "step": 3504 + }, + { + "epoch": 0.37, + "learning_rate": 1.594545683226324e-05, + "loss": 1.5076, + "step": 3505 + }, + { + "epoch": 0.37, + "learning_rate": 1.594251336666353e-05, + "loss": 1.482, + "step": 3506 + }, + { + "epoch": 0.37, + "learning_rate": 1.5939569104919716e-05, + "loss": 1.4429, + "step": 3507 + }, + { + "epoch": 0.37, + "learning_rate": 1.5936624047426254e-05, + "loss": 1.4662, + "step": 3508 + }, + { + "epoch": 0.37, + "learning_rate": 1.5933678194577708e-05, + "loss": 1.425, + "step": 3509 + }, + { + "epoch": 0.37, + "learning_rate": 1.5930731546768744e-05, + "loss": 1.4312, + "step": 3510 + }, + { + "epoch": 0.37, + "learning_rate": 1.592778410439414e-05, + "loss": 1.4336, + "step": 3511 + }, + { + "epoch": 0.37, + "learning_rate": 1.5924835867848775e-05, + "loss": 1.4197, + "step": 3512 + }, + { + "epoch": 0.37, + "learning_rate": 1.5921886837527638e-05, + "loss": 1.4456, + "step": 3513 + }, + { + "epoch": 0.37, + "learning_rate": 1.5918937013825823e-05, + "loss": 1.4394, + "step": 3514 + }, + { + "epoch": 0.37, + "learning_rate": 1.5915986397138526e-05, + "loss": 1.3606, + "step": 3515 + }, + { + "epoch": 0.37, + "learning_rate": 1.591303498786106e-05, + "loss": 1.4382, + "step": 3516 + }, + { + "epoch": 0.37, + "learning_rate": 1.591008278638884e-05, + "loss": 1.4185, + "step": 3517 + }, + { + "epoch": 0.37, + "learning_rate": 1.5907129793117374e-05, + "loss": 1.6692, + "step": 3518 + }, + { + "epoch": 0.37, + "learning_rate": 1.59041760084423e-05, + "loss": 1.501, + "step": 3519 + }, + { + "epoch": 0.37, + "learning_rate": 1.5901221432759345e-05, + "loss": 1.5753, + "step": 3520 + }, + { + "epoch": 0.37, + "learning_rate": 1.589826606646434e-05, + "loss": 1.4795, + "step": 3521 + }, + { + "epoch": 0.37, + "learning_rate": 1.5895309909953236e-05, + "loss": 1.4379, + "step": 3522 + }, + { + "epoch": 0.37, + "learning_rate": 1.5892352963622078e-05, + "loss": 1.3426, + "step": 3523 + }, + { + "epoch": 0.37, + "learning_rate": 1.5889395227867025e-05, + "loss": 1.4048, + "step": 3524 + }, + { + "epoch": 0.37, + "learning_rate": 1.5886436703084332e-05, + "loss": 1.4303, + "step": 3525 + }, + { + "epoch": 0.37, + "learning_rate": 1.5883477389670367e-05, + "loss": 1.3684, + "step": 3526 + }, + { + "epoch": 0.37, + "learning_rate": 1.5880517288021602e-05, + "loss": 1.3701, + "step": 3527 + }, + { + "epoch": 0.37, + "learning_rate": 1.587755639853462e-05, + "loss": 1.4308, + "step": 3528 + }, + { + "epoch": 0.37, + "learning_rate": 1.5874594721606096e-05, + "loss": 1.3981, + "step": 3529 + }, + { + "epoch": 0.37, + "learning_rate": 1.5871632257632823e-05, + "loss": 1.5906, + "step": 3530 + }, + { + "epoch": 0.37, + "learning_rate": 1.5868669007011696e-05, + "loss": 1.4642, + "step": 3531 + }, + { + "epoch": 0.37, + "learning_rate": 1.586570497013971e-05, + "loss": 1.411, + "step": 3532 + }, + { + "epoch": 0.37, + "learning_rate": 1.586274014741397e-05, + "loss": 1.3942, + "step": 3533 + }, + { + "epoch": 0.37, + "learning_rate": 1.5859774539231693e-05, + "loss": 1.3952, + "step": 3534 + }, + { + "epoch": 0.37, + "learning_rate": 1.585680814599019e-05, + "loss": 1.4009, + "step": 3535 + }, + { + "epoch": 0.37, + "learning_rate": 1.585384096808688e-05, + "loss": 1.3238, + "step": 3536 + }, + { + "epoch": 0.37, + "learning_rate": 1.585087300591929e-05, + "loss": 1.346, + "step": 3537 + }, + { + "epoch": 0.37, + "learning_rate": 1.584790425988505e-05, + "loss": 1.3739, + "step": 3538 + }, + { + "epoch": 0.37, + "learning_rate": 1.5844934730381895e-05, + "loss": 1.4264, + "step": 3539 + }, + { + "epoch": 0.37, + "learning_rate": 1.5841964417807668e-05, + "loss": 1.4675, + "step": 3540 + }, + { + "epoch": 0.37, + "learning_rate": 1.5838993322560314e-05, + "loss": 1.3337, + "step": 3541 + }, + { + "epoch": 0.37, + "learning_rate": 1.5836021445037883e-05, + "loss": 1.4052, + "step": 3542 + }, + { + "epoch": 0.37, + "learning_rate": 1.583304878563853e-05, + "loss": 1.4311, + "step": 3543 + }, + { + "epoch": 0.37, + "learning_rate": 1.5830075344760513e-05, + "loss": 1.386, + "step": 3544 + }, + { + "epoch": 0.37, + "learning_rate": 1.58271011228022e-05, + "loss": 1.387, + "step": 3545 + }, + { + "epoch": 0.37, + "learning_rate": 1.582412612016206e-05, + "loss": 1.3601, + "step": 3546 + }, + { + "epoch": 0.37, + "learning_rate": 1.5821150337238663e-05, + "loss": 1.5111, + "step": 3547 + }, + { + "epoch": 0.37, + "learning_rate": 1.5818173774430697e-05, + "loss": 1.471, + "step": 3548 + }, + { + "epoch": 0.37, + "learning_rate": 1.581519643213693e-05, + "loss": 1.4442, + "step": 3549 + }, + { + "epoch": 0.37, + "learning_rate": 1.5812218310756263e-05, + "loss": 1.467, + "step": 3550 + }, + { + "epoch": 0.37, + "learning_rate": 1.5809239410687683e-05, + "loss": 1.3731, + "step": 3551 + }, + { + "epoch": 0.37, + "learning_rate": 1.5806259732330286e-05, + "loss": 1.4072, + "step": 3552 + }, + { + "epoch": 0.37, + "learning_rate": 1.5803279276083268e-05, + "loss": 1.3636, + "step": 3553 + }, + { + "epoch": 0.37, + "learning_rate": 1.5800298042345938e-05, + "loss": 1.3915, + "step": 3554 + }, + { + "epoch": 0.37, + "learning_rate": 1.5797316031517705e-05, + "loss": 1.5038, + "step": 3555 + }, + { + "epoch": 0.37, + "learning_rate": 1.5794333243998082e-05, + "loss": 1.4455, + "step": 3556 + }, + { + "epoch": 0.37, + "learning_rate": 1.5791349680186684e-05, + "loss": 1.5062, + "step": 3557 + }, + { + "epoch": 0.37, + "learning_rate": 1.5788365340483234e-05, + "loss": 1.3899, + "step": 3558 + }, + { + "epoch": 0.37, + "learning_rate": 1.5785380225287554e-05, + "loss": 1.4946, + "step": 3559 + }, + { + "epoch": 0.37, + "learning_rate": 1.5782394334999572e-05, + "loss": 1.3859, + "step": 3560 + }, + { + "epoch": 0.37, + "learning_rate": 1.577940767001933e-05, + "loss": 1.541, + "step": 3561 + }, + { + "epoch": 0.37, + "learning_rate": 1.5776420230746952e-05, + "loss": 1.4952, + "step": 3562 + }, + { + "epoch": 0.37, + "learning_rate": 1.5773432017582684e-05, + "loss": 1.6055, + "step": 3563 + }, + { + "epoch": 0.37, + "learning_rate": 1.577044303092687e-05, + "loss": 1.4661, + "step": 3564 + }, + { + "epoch": 0.37, + "learning_rate": 1.576745327117996e-05, + "loss": 1.4082, + "step": 3565 + }, + { + "epoch": 0.37, + "learning_rate": 1.5764462738742493e-05, + "loss": 1.4005, + "step": 3566 + }, + { + "epoch": 0.37, + "learning_rate": 1.5761471434015137e-05, + "loss": 1.3959, + "step": 3567 + }, + { + "epoch": 0.37, + "learning_rate": 1.5758479357398645e-05, + "loss": 1.4567, + "step": 3568 + }, + { + "epoch": 0.37, + "learning_rate": 1.575548650929388e-05, + "loss": 1.3791, + "step": 3569 + }, + { + "epoch": 0.37, + "learning_rate": 1.57524928901018e-05, + "loss": 1.4428, + "step": 3570 + }, + { + "epoch": 0.37, + "learning_rate": 1.5749498500223486e-05, + "loss": 1.3864, + "step": 3571 + }, + { + "epoch": 0.37, + "learning_rate": 1.5746503340060097e-05, + "loss": 1.4019, + "step": 3572 + }, + { + "epoch": 0.37, + "learning_rate": 1.574350741001291e-05, + "loss": 1.5436, + "step": 3573 + }, + { + "epoch": 0.37, + "learning_rate": 1.5740510710483308e-05, + "loss": 1.4637, + "step": 3574 + }, + { + "epoch": 0.37, + "learning_rate": 1.5737513241872767e-05, + "loss": 1.5097, + "step": 3575 + }, + { + "epoch": 0.38, + "learning_rate": 1.5734515004582873e-05, + "loss": 1.5143, + "step": 3576 + }, + { + "epoch": 0.38, + "learning_rate": 1.5731515999015315e-05, + "loss": 1.3926, + "step": 3577 + }, + { + "epoch": 0.38, + "learning_rate": 1.5728516225571874e-05, + "loss": 1.4242, + "step": 3578 + }, + { + "epoch": 0.38, + "learning_rate": 1.5725515684654453e-05, + "loss": 1.4429, + "step": 3579 + }, + { + "epoch": 0.38, + "learning_rate": 1.572251437666504e-05, + "loss": 1.4638, + "step": 3580 + }, + { + "epoch": 0.38, + "learning_rate": 1.5719512302005735e-05, + "loss": 1.3381, + "step": 3581 + }, + { + "epoch": 0.38, + "learning_rate": 1.571650946107874e-05, + "loss": 1.4342, + "step": 3582 + }, + { + "epoch": 0.38, + "eval_loss": 1.4705015420913696, + "eval_runtime": 77.3664, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3582 + }, + { + "epoch": 0.38, + "learning_rate": 1.571350585428636e-05, + "loss": 1.3991, + "step": 3583 + }, + { + "epoch": 0.38, + "learning_rate": 1.5710501482030998e-05, + "loss": 1.4274, + "step": 3584 + }, + { + "epoch": 0.38, + "learning_rate": 1.5707496344715166e-05, + "loss": 1.438, + "step": 3585 + }, + { + "epoch": 0.38, + "learning_rate": 1.570449044274147e-05, + "loss": 1.4453, + "step": 3586 + }, + { + "epoch": 0.38, + "learning_rate": 1.570148377651263e-05, + "loss": 1.4022, + "step": 3587 + }, + { + "epoch": 0.38, + "learning_rate": 1.5698476346431454e-05, + "loss": 1.4312, + "step": 3588 + }, + { + "epoch": 0.38, + "learning_rate": 1.569546815290087e-05, + "loss": 1.4329, + "step": 3589 + }, + { + "epoch": 0.38, + "learning_rate": 1.569245919632389e-05, + "loss": 1.4036, + "step": 3590 + }, + { + "epoch": 0.38, + "learning_rate": 1.5689449477103644e-05, + "loss": 1.412, + "step": 3591 + }, + { + "epoch": 0.38, + "learning_rate": 1.5686438995643353e-05, + "loss": 1.4492, + "step": 3592 + }, + { + "epoch": 0.38, + "learning_rate": 1.5683427752346343e-05, + "loss": 1.4555, + "step": 3593 + }, + { + "epoch": 0.38, + "learning_rate": 1.5680415747616047e-05, + "loss": 1.5594, + "step": 3594 + }, + { + "epoch": 0.38, + "learning_rate": 1.5677402981855993e-05, + "loss": 1.4813, + "step": 3595 + }, + { + "epoch": 0.38, + "learning_rate": 1.567438945546982e-05, + "loss": 1.5919, + "step": 3596 + }, + { + "epoch": 0.38, + "learning_rate": 1.5671375168861255e-05, + "loss": 1.4235, + "step": 3597 + }, + { + "epoch": 0.38, + "learning_rate": 1.5668360122434135e-05, + "loss": 1.441, + "step": 3598 + }, + { + "epoch": 0.38, + "learning_rate": 1.566534431659241e-05, + "loss": 1.5847, + "step": 3599 + }, + { + "epoch": 0.38, + "learning_rate": 1.566232775174011e-05, + "loss": 1.6123, + "step": 3600 + }, + { + "epoch": 0.38, + "learning_rate": 1.5659310428281374e-05, + "loss": 1.4916, + "step": 3601 + }, + { + "epoch": 0.38, + "learning_rate": 1.5656292346620457e-05, + "loss": 1.4603, + "step": 3602 + }, + { + "epoch": 0.38, + "learning_rate": 1.56532735071617e-05, + "loss": 1.4423, + "step": 3603 + }, + { + "epoch": 0.38, + "learning_rate": 1.5650253910309547e-05, + "loss": 1.4814, + "step": 3604 + }, + { + "epoch": 0.38, + "learning_rate": 1.5647233556468552e-05, + "loss": 1.4015, + "step": 3605 + }, + { + "epoch": 0.38, + "learning_rate": 1.564421244604336e-05, + "loss": 1.3798, + "step": 3606 + }, + { + "epoch": 0.38, + "learning_rate": 1.5641190579438723e-05, + "loss": 1.4259, + "step": 3607 + }, + { + "epoch": 0.38, + "learning_rate": 1.5638167957059493e-05, + "loss": 1.3493, + "step": 3608 + }, + { + "epoch": 0.38, + "learning_rate": 1.5635144579310626e-05, + "loss": 1.3433, + "step": 3609 + }, + { + "epoch": 0.38, + "learning_rate": 1.5632120446597177e-05, + "loss": 1.4661, + "step": 3610 + }, + { + "epoch": 0.38, + "learning_rate": 1.5629095559324297e-05, + "loss": 1.4205, + "step": 3611 + }, + { + "epoch": 0.38, + "learning_rate": 1.562606991789725e-05, + "loss": 1.3976, + "step": 3612 + }, + { + "epoch": 0.38, + "learning_rate": 1.5623043522721393e-05, + "loss": 1.4261, + "step": 3613 + }, + { + "epoch": 0.38, + "learning_rate": 1.562001637420218e-05, + "loss": 1.4358, + "step": 3614 + }, + { + "epoch": 0.38, + "learning_rate": 1.5616988472745175e-05, + "loss": 1.437, + "step": 3615 + }, + { + "epoch": 0.38, + "learning_rate": 1.561395981875604e-05, + "loss": 1.3735, + "step": 3616 + }, + { + "epoch": 0.38, + "learning_rate": 1.5610930412640532e-05, + "loss": 1.4357, + "step": 3617 + }, + { + "epoch": 0.38, + "learning_rate": 1.560790025480452e-05, + "loss": 1.4003, + "step": 3618 + }, + { + "epoch": 0.38, + "learning_rate": 1.5604869345653965e-05, + "loss": 1.4127, + "step": 3619 + }, + { + "epoch": 0.38, + "learning_rate": 1.5601837685594927e-05, + "loss": 1.4666, + "step": 3620 + }, + { + "epoch": 0.38, + "learning_rate": 1.5598805275033574e-05, + "loss": 1.4106, + "step": 3621 + }, + { + "epoch": 0.38, + "learning_rate": 1.5595772114376174e-05, + "loss": 1.3857, + "step": 3622 + }, + { + "epoch": 0.38, + "learning_rate": 1.5592738204029086e-05, + "loss": 1.4704, + "step": 3623 + }, + { + "epoch": 0.38, + "learning_rate": 1.558970354439878e-05, + "loss": 1.4649, + "step": 3624 + }, + { + "epoch": 0.38, + "learning_rate": 1.5586668135891824e-05, + "loss": 1.4812, + "step": 3625 + }, + { + "epoch": 0.38, + "learning_rate": 1.5583631978914882e-05, + "loss": 1.3507, + "step": 3626 + }, + { + "epoch": 0.38, + "learning_rate": 1.5580595073874718e-05, + "loss": 1.3762, + "step": 3627 + }, + { + "epoch": 0.38, + "learning_rate": 1.557755742117821e-05, + "loss": 1.4169, + "step": 3628 + }, + { + "epoch": 0.38, + "learning_rate": 1.557451902123231e-05, + "loss": 1.4098, + "step": 3629 + }, + { + "epoch": 0.38, + "learning_rate": 1.55714798744441e-05, + "loss": 1.5526, + "step": 3630 + }, + { + "epoch": 0.38, + "learning_rate": 1.556843998122074e-05, + "loss": 1.4414, + "step": 3631 + }, + { + "epoch": 0.38, + "learning_rate": 1.5565399341969497e-05, + "loss": 1.4134, + "step": 3632 + }, + { + "epoch": 0.38, + "learning_rate": 1.556235795709774e-05, + "loss": 1.4718, + "step": 3633 + }, + { + "epoch": 0.38, + "learning_rate": 1.5559315827012937e-05, + "loss": 1.412, + "step": 3634 + }, + { + "epoch": 0.38, + "learning_rate": 1.5556272952122657e-05, + "loss": 1.4119, + "step": 3635 + }, + { + "epoch": 0.38, + "learning_rate": 1.5553229332834564e-05, + "loss": 1.3999, + "step": 3636 + }, + { + "epoch": 0.38, + "learning_rate": 1.5550184969556428e-05, + "loss": 1.4626, + "step": 3637 + }, + { + "epoch": 0.38, + "learning_rate": 1.5547139862696113e-05, + "loss": 1.3811, + "step": 3638 + }, + { + "epoch": 0.38, + "learning_rate": 1.5544094012661583e-05, + "loss": 1.4053, + "step": 3639 + }, + { + "epoch": 0.38, + "learning_rate": 1.5541047419860907e-05, + "loss": 1.4059, + "step": 3640 + }, + { + "epoch": 0.38, + "learning_rate": 1.553800008470225e-05, + "loss": 1.4717, + "step": 3641 + }, + { + "epoch": 0.38, + "learning_rate": 1.553495200759388e-05, + "loss": 1.399, + "step": 3642 + }, + { + "epoch": 0.38, + "learning_rate": 1.5531903188944154e-05, + "loss": 1.4143, + "step": 3643 + }, + { + "epoch": 0.38, + "learning_rate": 1.5528853629161536e-05, + "loss": 1.4414, + "step": 3644 + }, + { + "epoch": 0.38, + "learning_rate": 1.5525803328654592e-05, + "loss": 1.4206, + "step": 3645 + }, + { + "epoch": 0.38, + "learning_rate": 1.5522752287831982e-05, + "loss": 1.3869, + "step": 3646 + }, + { + "epoch": 0.38, + "learning_rate": 1.551970050710247e-05, + "loss": 1.5434, + "step": 3647 + }, + { + "epoch": 0.38, + "learning_rate": 1.5516647986874914e-05, + "loss": 1.4574, + "step": 3648 + }, + { + "epoch": 0.38, + "learning_rate": 1.5513594727558273e-05, + "loss": 1.4353, + "step": 3649 + }, + { + "epoch": 0.38, + "learning_rate": 1.5510540729561606e-05, + "loss": 1.4122, + "step": 3650 + }, + { + "epoch": 0.38, + "learning_rate": 1.550748599329407e-05, + "loss": 1.4077, + "step": 3651 + }, + { + "epoch": 0.38, + "learning_rate": 1.550443051916492e-05, + "loss": 1.4433, + "step": 3652 + }, + { + "epoch": 0.38, + "learning_rate": 1.5501374307583514e-05, + "loss": 1.54, + "step": 3653 + }, + { + "epoch": 0.38, + "learning_rate": 1.5498317358959302e-05, + "loss": 1.4522, + "step": 3654 + }, + { + "epoch": 0.38, + "learning_rate": 1.5495259673701842e-05, + "loss": 1.4175, + "step": 3655 + }, + { + "epoch": 0.38, + "learning_rate": 1.5492201252220777e-05, + "loss": 1.4637, + "step": 3656 + }, + { + "epoch": 0.38, + "learning_rate": 1.5489142094925863e-05, + "loss": 1.4701, + "step": 3657 + }, + { + "epoch": 0.38, + "learning_rate": 1.548608220222695e-05, + "loss": 1.4095, + "step": 3658 + }, + { + "epoch": 0.38, + "learning_rate": 1.548302157453398e-05, + "loss": 1.3903, + "step": 3659 + }, + { + "epoch": 0.38, + "learning_rate": 1.5479960212257002e-05, + "loss": 1.4062, + "step": 3660 + }, + { + "epoch": 0.38, + "learning_rate": 1.5476898115806157e-05, + "loss": 1.4706, + "step": 3661 + }, + { + "epoch": 0.38, + "learning_rate": 1.547383528559169e-05, + "loss": 1.4423, + "step": 3662 + }, + { + "epoch": 0.38, + "learning_rate": 1.547077172202394e-05, + "loss": 1.4418, + "step": 3663 + }, + { + "epoch": 0.38, + "learning_rate": 1.5467707425513347e-05, + "loss": 1.4553, + "step": 3664 + }, + { + "epoch": 0.38, + "learning_rate": 1.5464642396470443e-05, + "loss": 1.435, + "step": 3665 + }, + { + "epoch": 0.38, + "learning_rate": 1.5461576635305873e-05, + "loss": 1.4105, + "step": 3666 + }, + { + "epoch": 0.38, + "learning_rate": 1.5458510142430364e-05, + "loss": 1.4118, + "step": 3667 + }, + { + "epoch": 0.38, + "learning_rate": 1.5455442918254746e-05, + "loss": 1.4096, + "step": 3668 + }, + { + "epoch": 0.38, + "learning_rate": 1.545237496318995e-05, + "loss": 1.4248, + "step": 3669 + }, + { + "epoch": 0.38, + "learning_rate": 1.5449306277647003e-05, + "loss": 1.4591, + "step": 3670 + }, + { + "epoch": 0.38, + "learning_rate": 1.544623686203703e-05, + "loss": 1.4764, + "step": 3671 + }, + { + "epoch": 0.39, + "learning_rate": 1.5443166716771255e-05, + "loss": 1.4329, + "step": 3672 + }, + { + "epoch": 0.39, + "learning_rate": 1.5440095842260995e-05, + "loss": 1.4023, + "step": 3673 + }, + { + "epoch": 0.39, + "learning_rate": 1.5437024238917674e-05, + "loss": 1.3802, + "step": 3674 + }, + { + "epoch": 0.39, + "learning_rate": 1.5433951907152806e-05, + "loss": 1.4627, + "step": 3675 + }, + { + "epoch": 0.39, + "learning_rate": 1.5430878847378e-05, + "loss": 1.5164, + "step": 3676 + }, + { + "epoch": 0.39, + "learning_rate": 1.542780506000497e-05, + "loss": 1.3546, + "step": 3677 + }, + { + "epoch": 0.39, + "learning_rate": 1.542473054544553e-05, + "loss": 1.4415, + "step": 3678 + }, + { + "epoch": 0.39, + "learning_rate": 1.5421655304111573e-05, + "loss": 1.4093, + "step": 3679 + }, + { + "epoch": 0.39, + "learning_rate": 1.5418579336415114e-05, + "loss": 1.3943, + "step": 3680 + }, + { + "epoch": 0.39, + "learning_rate": 1.5415502642768252e-05, + "loss": 1.3659, + "step": 3681 + }, + { + "epoch": 0.39, + "learning_rate": 1.541242522358318e-05, + "loss": 1.4322, + "step": 3682 + }, + { + "epoch": 0.39, + "learning_rate": 1.5409347079272198e-05, + "loss": 1.4064, + "step": 3683 + }, + { + "epoch": 0.39, + "learning_rate": 1.5406268210247693e-05, + "loss": 1.4031, + "step": 3684 + }, + { + "epoch": 0.39, + "learning_rate": 1.540318861692216e-05, + "loss": 1.3449, + "step": 3685 + }, + { + "epoch": 0.39, + "learning_rate": 1.5400108299708182e-05, + "loss": 1.5536, + "step": 3686 + }, + { + "epoch": 0.39, + "learning_rate": 1.5397027259018442e-05, + "loss": 1.4106, + "step": 3687 + }, + { + "epoch": 0.39, + "learning_rate": 1.5393945495265722e-05, + "loss": 1.4309, + "step": 3688 + }, + { + "epoch": 0.39, + "learning_rate": 1.53908630088629e-05, + "loss": 1.3765, + "step": 3689 + }, + { + "epoch": 0.39, + "learning_rate": 1.5387779800222947e-05, + "loss": 1.3809, + "step": 3690 + }, + { + "epoch": 0.39, + "learning_rate": 1.5384695869758938e-05, + "loss": 1.4758, + "step": 3691 + }, + { + "epoch": 0.39, + "learning_rate": 1.5381611217884032e-05, + "loss": 1.4249, + "step": 3692 + }, + { + "epoch": 0.39, + "learning_rate": 1.5378525845011503e-05, + "loss": 1.4133, + "step": 3693 + }, + { + "epoch": 0.39, + "learning_rate": 1.5375439751554708e-05, + "loss": 1.418, + "step": 3694 + }, + { + "epoch": 0.39, + "learning_rate": 1.53723529379271e-05, + "loss": 1.441, + "step": 3695 + }, + { + "epoch": 0.39, + "learning_rate": 1.536926540454224e-05, + "loss": 1.3919, + "step": 3696 + }, + { + "epoch": 0.39, + "learning_rate": 1.5366177151813775e-05, + "loss": 1.3722, + "step": 3697 + }, + { + "epoch": 0.39, + "learning_rate": 1.536308818015545e-05, + "loss": 1.4727, + "step": 3698 + }, + { + "epoch": 0.39, + "learning_rate": 1.535999848998111e-05, + "loss": 1.442, + "step": 3699 + }, + { + "epoch": 0.39, + "learning_rate": 1.535690808170469e-05, + "loss": 1.3884, + "step": 3700 + }, + { + "epoch": 0.39, + "learning_rate": 1.535381695574023e-05, + "loss": 1.3226, + "step": 3701 + }, + { + "epoch": 0.39, + "learning_rate": 1.535072511250186e-05, + "loss": 1.4403, + "step": 3702 + }, + { + "epoch": 0.39, + "learning_rate": 1.5347632552403808e-05, + "loss": 1.4144, + "step": 3703 + }, + { + "epoch": 0.39, + "learning_rate": 1.5344539275860395e-05, + "loss": 1.3514, + "step": 3704 + }, + { + "epoch": 0.39, + "learning_rate": 1.5341445283286044e-05, + "loss": 1.519, + "step": 3705 + }, + { + "epoch": 0.39, + "learning_rate": 1.5338350575095268e-05, + "loss": 1.4251, + "step": 3706 + }, + { + "epoch": 0.39, + "learning_rate": 1.5335255151702685e-05, + "loss": 1.392, + "step": 3707 + }, + { + "epoch": 0.39, + "learning_rate": 1.533215901352299e-05, + "loss": 1.3838, + "step": 3708 + }, + { + "epoch": 0.39, + "learning_rate": 1.532906216097099e-05, + "loss": 1.444, + "step": 3709 + }, + { + "epoch": 0.39, + "learning_rate": 1.5325964594461594e-05, + "loss": 1.3459, + "step": 3710 + }, + { + "epoch": 0.39, + "learning_rate": 1.5322866314409783e-05, + "loss": 1.4155, + "step": 3711 + }, + { + "epoch": 0.39, + "learning_rate": 1.5319767321230657e-05, + "loss": 1.4057, + "step": 3712 + }, + { + "epoch": 0.39, + "learning_rate": 1.5316667615339392e-05, + "loss": 1.382, + "step": 3713 + }, + { + "epoch": 0.39, + "learning_rate": 1.5313567197151277e-05, + "loss": 1.3634, + "step": 3714 + }, + { + "epoch": 0.39, + "learning_rate": 1.5310466067081688e-05, + "loss": 1.3434, + "step": 3715 + }, + { + "epoch": 0.39, + "learning_rate": 1.530736422554609e-05, + "loss": 1.4553, + "step": 3716 + }, + { + "epoch": 0.39, + "learning_rate": 1.5304261672960055e-05, + "loss": 1.4193, + "step": 3717 + }, + { + "epoch": 0.39, + "learning_rate": 1.5301158409739242e-05, + "loss": 1.3955, + "step": 3718 + }, + { + "epoch": 0.39, + "learning_rate": 1.5298054436299413e-05, + "loss": 1.4592, + "step": 3719 + }, + { + "epoch": 0.39, + "learning_rate": 1.529494975305642e-05, + "loss": 1.738, + "step": 3720 + }, + { + "epoch": 0.39, + "learning_rate": 1.529184436042621e-05, + "loss": 1.438, + "step": 3721 + }, + { + "epoch": 0.39, + "learning_rate": 1.528873825882482e-05, + "loss": 1.3445, + "step": 3722 + }, + { + "epoch": 0.39, + "learning_rate": 1.5285631448668395e-05, + "loss": 1.4168, + "step": 3723 + }, + { + "epoch": 0.39, + "learning_rate": 1.528252393037317e-05, + "loss": 1.4088, + "step": 3724 + }, + { + "epoch": 0.39, + "learning_rate": 1.5279415704355468e-05, + "loss": 1.4484, + "step": 3725 + }, + { + "epoch": 0.39, + "learning_rate": 1.5276306771031708e-05, + "loss": 1.4706, + "step": 3726 + }, + { + "epoch": 0.39, + "learning_rate": 1.527319713081841e-05, + "loss": 1.3466, + "step": 3727 + }, + { + "epoch": 0.39, + "learning_rate": 1.5270086784132196e-05, + "loss": 1.427, + "step": 3728 + }, + { + "epoch": 0.39, + "learning_rate": 1.5266975731389754e-05, + "loss": 1.4596, + "step": 3729 + }, + { + "epoch": 0.39, + "learning_rate": 1.52638639730079e-05, + "loss": 1.405, + "step": 3730 + }, + { + "epoch": 0.39, + "learning_rate": 1.5260751509403518e-05, + "loss": 1.4572, + "step": 3731 + }, + { + "epoch": 0.39, + "learning_rate": 1.5257638340993608e-05, + "loss": 1.3827, + "step": 3732 + }, + { + "epoch": 0.39, + "learning_rate": 1.5254524468195251e-05, + "loss": 1.3712, + "step": 3733 + }, + { + "epoch": 0.39, + "learning_rate": 1.5251409891425626e-05, + "loss": 1.4541, + "step": 3734 + }, + { + "epoch": 0.39, + "learning_rate": 1.5248294611102006e-05, + "loss": 1.5279, + "step": 3735 + }, + { + "epoch": 0.39, + "learning_rate": 1.5245178627641759e-05, + "loss": 1.3722, + "step": 3736 + }, + { + "epoch": 0.39, + "learning_rate": 1.5242061941462348e-05, + "loss": 1.5158, + "step": 3737 + }, + { + "epoch": 0.39, + "learning_rate": 1.523894455298132e-05, + "loss": 1.4274, + "step": 3738 + }, + { + "epoch": 0.39, + "learning_rate": 1.5235826462616338e-05, + "loss": 1.4543, + "step": 3739 + }, + { + "epoch": 0.39, + "learning_rate": 1.5232707670785144e-05, + "loss": 1.5011, + "step": 3740 + }, + { + "epoch": 0.39, + "learning_rate": 1.5229588177905568e-05, + "loss": 1.24, + "step": 3741 + }, + { + "epoch": 0.39, + "learning_rate": 1.5226467984395544e-05, + "loss": 1.4253, + "step": 3742 + }, + { + "epoch": 0.39, + "learning_rate": 1.5223347090673102e-05, + "loss": 1.3736, + "step": 3743 + }, + { + "epoch": 0.39, + "learning_rate": 1.522022549715636e-05, + "loss": 1.4587, + "step": 3744 + }, + { + "epoch": 0.39, + "learning_rate": 1.521710320426353e-05, + "loss": 1.5024, + "step": 3745 + }, + { + "epoch": 0.39, + "learning_rate": 1.521398021241292e-05, + "loss": 1.427, + "step": 3746 + }, + { + "epoch": 0.39, + "learning_rate": 1.5210856522022929e-05, + "loss": 1.3387, + "step": 3747 + }, + { + "epoch": 0.39, + "learning_rate": 1.5207732133512055e-05, + "loss": 1.3819, + "step": 3748 + }, + { + "epoch": 0.39, + "learning_rate": 1.5204607047298883e-05, + "loss": 1.4571, + "step": 3749 + }, + { + "epoch": 0.39, + "learning_rate": 1.5201481263802094e-05, + "loss": 1.3592, + "step": 3750 + }, + { + "epoch": 0.39, + "learning_rate": 1.5198354783440464e-05, + "loss": 1.3912, + "step": 3751 + }, + { + "epoch": 0.39, + "learning_rate": 1.519522760663286e-05, + "loss": 1.4986, + "step": 3752 + }, + { + "epoch": 0.39, + "learning_rate": 1.5192099733798243e-05, + "loss": 1.4106, + "step": 3753 + }, + { + "epoch": 0.39, + "learning_rate": 1.5188971165355667e-05, + "loss": 1.4145, + "step": 3754 + }, + { + "epoch": 0.39, + "learning_rate": 1.5185841901724282e-05, + "loss": 1.3915, + "step": 3755 + }, + { + "epoch": 0.39, + "learning_rate": 1.5182711943323329e-05, + "loss": 1.4014, + "step": 3756 + }, + { + "epoch": 0.39, + "learning_rate": 1.5179581290572141e-05, + "loss": 1.3651, + "step": 3757 + }, + { + "epoch": 0.39, + "learning_rate": 1.5176449943890147e-05, + "loss": 1.3653, + "step": 3758 + }, + { + "epoch": 0.39, + "learning_rate": 1.5173317903696862e-05, + "loss": 1.4486, + "step": 3759 + }, + { + "epoch": 0.39, + "learning_rate": 1.5170185170411906e-05, + "loss": 1.4459, + "step": 3760 + }, + { + "epoch": 0.39, + "learning_rate": 1.5167051744454977e-05, + "loss": 1.4215, + "step": 3761 + }, + { + "epoch": 0.39, + "learning_rate": 1.5163917626245877e-05, + "loss": 1.4379, + "step": 3762 + }, + { + "epoch": 0.39, + "learning_rate": 1.51607828162045e-05, + "loss": 1.4147, + "step": 3763 + }, + { + "epoch": 0.39, + "learning_rate": 1.5157647314750827e-05, + "loss": 1.4011, + "step": 3764 + }, + { + "epoch": 0.39, + "learning_rate": 1.5154511122304936e-05, + "loss": 1.4309, + "step": 3765 + }, + { + "epoch": 0.39, + "learning_rate": 1.5151374239286993e-05, + "loss": 1.4382, + "step": 3766 + }, + { + "epoch": 0.4, + "learning_rate": 1.5148236666117266e-05, + "loss": 1.405, + "step": 3767 + }, + { + "epoch": 0.4, + "learning_rate": 1.5145098403216104e-05, + "loss": 1.4223, + "step": 3768 + }, + { + "epoch": 0.4, + "learning_rate": 1.5141959451003951e-05, + "loss": 1.4084, + "step": 3769 + }, + { + "epoch": 0.4, + "learning_rate": 1.5138819809901356e-05, + "loss": 1.4063, + "step": 3770 + }, + { + "epoch": 0.4, + "learning_rate": 1.513567948032894e-05, + "loss": 1.3299, + "step": 3771 + }, + { + "epoch": 0.4, + "learning_rate": 1.5132538462707431e-05, + "loss": 1.3901, + "step": 3772 + }, + { + "epoch": 0.4, + "learning_rate": 1.5129396757457646e-05, + "loss": 1.4249, + "step": 3773 + }, + { + "epoch": 0.4, + "learning_rate": 1.512625436500049e-05, + "loss": 1.4087, + "step": 3774 + }, + { + "epoch": 0.4, + "learning_rate": 1.5123111285756964e-05, + "loss": 1.3521, + "step": 3775 + }, + { + "epoch": 0.4, + "learning_rate": 1.5119967520148163e-05, + "loss": 1.4097, + "step": 3776 + }, + { + "epoch": 0.4, + "learning_rate": 1.5116823068595261e-05, + "loss": 1.4871, + "step": 3777 + }, + { + "epoch": 0.4, + "learning_rate": 1.5113677931519543e-05, + "loss": 1.44, + "step": 3778 + }, + { + "epoch": 0.4, + "learning_rate": 1.5110532109342377e-05, + "loss": 1.4518, + "step": 3779 + }, + { + "epoch": 0.4, + "learning_rate": 1.5107385602485214e-05, + "loss": 1.3961, + "step": 3780 + }, + { + "epoch": 0.4, + "learning_rate": 1.5104238411369614e-05, + "loss": 1.4341, + "step": 3781 + }, + { + "epoch": 0.4, + "eval_loss": 1.4642821550369263, + "eval_runtime": 77.3595, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 3781 + }, + { + "epoch": 0.4, + "learning_rate": 1.5101090536417218e-05, + "loss": 1.403, + "step": 3782 + }, + { + "epoch": 0.4, + "learning_rate": 1.5097941978049754e-05, + "loss": 1.4103, + "step": 3783 + }, + { + "epoch": 0.4, + "learning_rate": 1.5094792736689052e-05, + "loss": 1.3478, + "step": 3784 + }, + { + "epoch": 0.4, + "learning_rate": 1.5091642812757035e-05, + "loss": 1.4134, + "step": 3785 + }, + { + "epoch": 0.4, + "learning_rate": 1.5088492206675701e-05, + "loss": 1.4134, + "step": 3786 + }, + { + "epoch": 0.4, + "learning_rate": 1.5085340918867162e-05, + "loss": 1.1494, + "step": 3787 + }, + { + "epoch": 0.4, + "learning_rate": 1.5082188949753598e-05, + "loss": 1.2385, + "step": 3788 + }, + { + "epoch": 0.4, + "learning_rate": 1.5079036299757299e-05, + "loss": 1.4258, + "step": 3789 + }, + { + "epoch": 0.4, + "learning_rate": 1.5075882969300639e-05, + "loss": 1.3781, + "step": 3790 + }, + { + "epoch": 0.4, + "learning_rate": 1.507272895880608e-05, + "loss": 1.5096, + "step": 3791 + }, + { + "epoch": 0.4, + "learning_rate": 1.5069574268696179e-05, + "loss": 1.366, + "step": 3792 + }, + { + "epoch": 0.4, + "learning_rate": 1.5066418899393584e-05, + "loss": 1.3792, + "step": 3793 + }, + { + "epoch": 0.4, + "learning_rate": 1.506326285132104e-05, + "loss": 1.4987, + "step": 3794 + }, + { + "epoch": 0.4, + "learning_rate": 1.5060106124901364e-05, + "loss": 1.445, + "step": 3795 + }, + { + "epoch": 0.4, + "learning_rate": 1.5056948720557482e-05, + "loss": 1.5071, + "step": 3796 + }, + { + "epoch": 0.4, + "learning_rate": 1.505379063871241e-05, + "loss": 1.4029, + "step": 3797 + }, + { + "epoch": 0.4, + "learning_rate": 1.5050631879789244e-05, + "loss": 1.5263, + "step": 3798 + }, + { + "epoch": 0.4, + "learning_rate": 1.5047472444211175e-05, + "loss": 1.3906, + "step": 3799 + }, + { + "epoch": 0.4, + "learning_rate": 1.5044312332401494e-05, + "loss": 1.7352, + "step": 3800 + }, + { + "epoch": 0.4, + "learning_rate": 1.5041151544783565e-05, + "loss": 1.3946, + "step": 3801 + }, + { + "epoch": 0.4, + "learning_rate": 1.5037990081780862e-05, + "loss": 1.3592, + "step": 3802 + }, + { + "epoch": 0.4, + "learning_rate": 1.503482794381693e-05, + "loss": 1.3991, + "step": 3803 + }, + { + "epoch": 0.4, + "learning_rate": 1.5031665131315423e-05, + "loss": 1.4271, + "step": 3804 + }, + { + "epoch": 0.4, + "learning_rate": 1.502850164470007e-05, + "loss": 1.4305, + "step": 3805 + }, + { + "epoch": 0.4, + "learning_rate": 1.5025337484394701e-05, + "loss": 1.4116, + "step": 3806 + }, + { + "epoch": 0.4, + "learning_rate": 1.5022172650823232e-05, + "loss": 1.4242, + "step": 3807 + }, + { + "epoch": 0.4, + "learning_rate": 1.5019007144409667e-05, + "loss": 1.4427, + "step": 3808 + }, + { + "epoch": 0.4, + "learning_rate": 1.5015840965578106e-05, + "loss": 1.3705, + "step": 3809 + }, + { + "epoch": 0.4, + "learning_rate": 1.5012674114752732e-05, + "loss": 1.4498, + "step": 3810 + }, + { + "epoch": 0.4, + "learning_rate": 1.5009506592357822e-05, + "loss": 1.489, + "step": 3811 + }, + { + "epoch": 0.4, + "learning_rate": 1.5006338398817746e-05, + "loss": 1.4801, + "step": 3812 + }, + { + "epoch": 0.4, + "learning_rate": 1.5003169534556956e-05, + "loss": 1.3468, + "step": 3813 + }, + { + "epoch": 0.4, + "learning_rate": 1.5000000000000002e-05, + "loss": 1.4211, + "step": 3814 + }, + { + "epoch": 0.4, + "learning_rate": 1.4996829795571518e-05, + "loss": 1.4683, + "step": 3815 + }, + { + "epoch": 0.4, + "learning_rate": 1.499365892169623e-05, + "loss": 1.4441, + "step": 3816 + }, + { + "epoch": 0.4, + "learning_rate": 1.4990487378798958e-05, + "loss": 1.4368, + "step": 3817 + }, + { + "epoch": 0.4, + "learning_rate": 1.4987315167304602e-05, + "loss": 1.4097, + "step": 3818 + }, + { + "epoch": 0.4, + "learning_rate": 1.4984142287638155e-05, + "loss": 1.4238, + "step": 3819 + }, + { + "epoch": 0.4, + "learning_rate": 1.4980968740224708e-05, + "loss": 1.497, + "step": 3820 + }, + { + "epoch": 0.4, + "learning_rate": 1.4977794525489433e-05, + "loss": 1.3989, + "step": 3821 + }, + { + "epoch": 0.4, + "learning_rate": 1.4974619643857588e-05, + "loss": 1.4415, + "step": 3822 + }, + { + "epoch": 0.4, + "learning_rate": 1.4971444095754533e-05, + "loss": 1.3931, + "step": 3823 + }, + { + "epoch": 0.4, + "learning_rate": 1.4968267881605705e-05, + "loss": 1.3426, + "step": 3824 + }, + { + "epoch": 0.4, + "learning_rate": 1.4965091001836636e-05, + "loss": 1.644, + "step": 3825 + }, + { + "epoch": 0.4, + "learning_rate": 1.4961913456872945e-05, + "loss": 1.3903, + "step": 3826 + }, + { + "epoch": 0.4, + "learning_rate": 1.4958735247140345e-05, + "loss": 1.3764, + "step": 3827 + }, + { + "epoch": 0.4, + "learning_rate": 1.4955556373064632e-05, + "loss": 1.5484, + "step": 3828 + }, + { + "epoch": 0.4, + "learning_rate": 1.4952376835071696e-05, + "loss": 1.5696, + "step": 3829 + }, + { + "epoch": 0.4, + "learning_rate": 1.4949196633587509e-05, + "loss": 1.3844, + "step": 3830 + }, + { + "epoch": 0.4, + "learning_rate": 1.494601576903814e-05, + "loss": 1.3868, + "step": 3831 + }, + { + "epoch": 0.4, + "learning_rate": 1.4942834241849741e-05, + "loss": 1.4229, + "step": 3832 + }, + { + "epoch": 0.4, + "learning_rate": 1.4939652052448557e-05, + "loss": 1.4062, + "step": 3833 + }, + { + "epoch": 0.4, + "learning_rate": 1.4936469201260915e-05, + "loss": 1.3955, + "step": 3834 + }, + { + "epoch": 0.4, + "learning_rate": 1.4933285688713239e-05, + "loss": 1.3959, + "step": 3835 + }, + { + "epoch": 0.4, + "learning_rate": 1.4930101515232038e-05, + "loss": 1.4652, + "step": 3836 + }, + { + "epoch": 0.4, + "learning_rate": 1.4926916681243913e-05, + "loss": 1.5253, + "step": 3837 + }, + { + "epoch": 0.4, + "learning_rate": 1.4923731187175539e-05, + "loss": 1.4694, + "step": 3838 + }, + { + "epoch": 0.4, + "learning_rate": 1.4920545033453702e-05, + "loss": 1.3859, + "step": 3839 + }, + { + "epoch": 0.4, + "learning_rate": 1.4917358220505259e-05, + "loss": 1.4157, + "step": 3840 + }, + { + "epoch": 0.4, + "learning_rate": 1.4914170748757159e-05, + "loss": 1.4491, + "step": 3841 + }, + { + "epoch": 0.4, + "learning_rate": 1.4910982618636445e-05, + "loss": 1.4464, + "step": 3842 + }, + { + "epoch": 0.4, + "learning_rate": 1.4907793830570246e-05, + "loss": 1.3771, + "step": 3843 + }, + { + "epoch": 0.4, + "learning_rate": 1.4904604384985775e-05, + "loss": 1.3673, + "step": 3844 + }, + { + "epoch": 0.4, + "learning_rate": 1.4901414282310334e-05, + "loss": 1.4429, + "step": 3845 + }, + { + "epoch": 0.4, + "learning_rate": 1.4898223522971318e-05, + "loss": 1.4905, + "step": 3846 + }, + { + "epoch": 0.4, + "learning_rate": 1.4895032107396205e-05, + "loss": 1.4039, + "step": 3847 + }, + { + "epoch": 0.4, + "learning_rate": 1.4891840036012566e-05, + "loss": 1.4082, + "step": 3848 + }, + { + "epoch": 0.4, + "learning_rate": 1.4888647309248052e-05, + "loss": 1.3643, + "step": 3849 + }, + { + "epoch": 0.4, + "learning_rate": 1.4885453927530408e-05, + "loss": 1.3116, + "step": 3850 + }, + { + "epoch": 0.4, + "learning_rate": 1.4882259891287467e-05, + "loss": 1.4278, + "step": 3851 + }, + { + "epoch": 0.4, + "learning_rate": 1.4879065200947148e-05, + "loss": 1.3712, + "step": 3852 + }, + { + "epoch": 0.4, + "learning_rate": 1.4875869856937449e-05, + "loss": 1.387, + "step": 3853 + }, + { + "epoch": 0.4, + "learning_rate": 1.4872673859686475e-05, + "loss": 1.5053, + "step": 3854 + }, + { + "epoch": 0.4, + "learning_rate": 1.4869477209622404e-05, + "loss": 1.4427, + "step": 3855 + }, + { + "epoch": 0.4, + "learning_rate": 1.4866279907173502e-05, + "loss": 1.3404, + "step": 3856 + }, + { + "epoch": 0.4, + "learning_rate": 1.4863081952768126e-05, + "loss": 1.3126, + "step": 3857 + }, + { + "epoch": 0.4, + "learning_rate": 1.4859883346834725e-05, + "loss": 1.4588, + "step": 3858 + }, + { + "epoch": 0.4, + "learning_rate": 1.4856684089801822e-05, + "loss": 1.408, + "step": 3859 + }, + { + "epoch": 0.4, + "learning_rate": 1.4853484182098044e-05, + "loss": 1.4356, + "step": 3860 + }, + { + "epoch": 0.4, + "learning_rate": 1.4850283624152088e-05, + "loss": 1.3768, + "step": 3861 + }, + { + "epoch": 0.4, + "learning_rate": 1.4847082416392753e-05, + "loss": 1.4563, + "step": 3862 + }, + { + "epoch": 0.41, + "learning_rate": 1.4843880559248915e-05, + "loss": 1.3648, + "step": 3863 + }, + { + "epoch": 0.41, + "learning_rate": 1.4840678053149542e-05, + "loss": 1.4146, + "step": 3864 + }, + { + "epoch": 0.41, + "learning_rate": 1.4837474898523686e-05, + "loss": 1.4423, + "step": 3865 + }, + { + "epoch": 0.41, + "learning_rate": 1.4834271095800487e-05, + "loss": 1.3351, + "step": 3866 + }, + { + "epoch": 0.41, + "learning_rate": 1.4831066645409178e-05, + "loss": 1.4534, + "step": 3867 + }, + { + "epoch": 0.41, + "learning_rate": 1.4827861547779066e-05, + "loss": 1.4763, + "step": 3868 + }, + { + "epoch": 0.41, + "learning_rate": 1.4824655803339553e-05, + "loss": 1.4019, + "step": 3869 + }, + { + "epoch": 0.41, + "learning_rate": 1.4821449412520132e-05, + "loss": 1.4223, + "step": 3870 + }, + { + "epoch": 0.41, + "learning_rate": 1.4818242375750371e-05, + "loss": 1.4065, + "step": 3871 + }, + { + "epoch": 0.41, + "learning_rate": 1.481503469345993e-05, + "loss": 1.587, + "step": 3872 + }, + { + "epoch": 0.41, + "learning_rate": 1.4811826366078562e-05, + "loss": 1.3746, + "step": 3873 + }, + { + "epoch": 0.41, + "learning_rate": 1.4808617394036096e-05, + "loss": 1.3425, + "step": 3874 + }, + { + "epoch": 0.41, + "learning_rate": 1.480540777776245e-05, + "loss": 0.6637, + "step": 3875 + }, + { + "epoch": 0.41, + "learning_rate": 1.4802197517687634e-05, + "loss": 1.3366, + "step": 3876 + }, + { + "epoch": 0.41, + "learning_rate": 1.479898661424174e-05, + "loss": 1.4033, + "step": 3877 + }, + { + "epoch": 0.41, + "learning_rate": 1.4795775067854947e-05, + "loss": 1.4005, + "step": 3878 + }, + { + "epoch": 0.41, + "learning_rate": 1.4792562878957516e-05, + "loss": 1.3651, + "step": 3879 + }, + { + "epoch": 0.41, + "learning_rate": 1.47893500479798e-05, + "loss": 1.4185, + "step": 3880 + }, + { + "epoch": 0.41, + "learning_rate": 1.4786136575352236e-05, + "loss": 1.4394, + "step": 3881 + }, + { + "epoch": 0.41, + "learning_rate": 1.478292246150535e-05, + "loss": 1.7243, + "step": 3882 + }, + { + "epoch": 0.41, + "learning_rate": 1.4779707706869744e-05, + "loss": 1.3574, + "step": 3883 + }, + { + "epoch": 0.41, + "learning_rate": 1.4776492311876116e-05, + "loss": 1.4031, + "step": 3884 + }, + { + "epoch": 0.41, + "learning_rate": 1.4773276276955248e-05, + "loss": 1.4351, + "step": 3885 + }, + { + "epoch": 0.41, + "learning_rate": 1.4770059602538002e-05, + "loss": 1.3922, + "step": 3886 + }, + { + "epoch": 0.41, + "learning_rate": 1.4766842289055333e-05, + "loss": 1.3374, + "step": 3887 + }, + { + "epoch": 0.41, + "learning_rate": 1.4763624336938278e-05, + "loss": 1.428, + "step": 3888 + }, + { + "epoch": 0.41, + "learning_rate": 1.476040574661796e-05, + "loss": 1.6087, + "step": 3889 + }, + { + "epoch": 0.41, + "learning_rate": 1.4757186518525586e-05, + "loss": 1.4054, + "step": 3890 + }, + { + "epoch": 0.41, + "learning_rate": 1.4753966653092447e-05, + "loss": 1.2595, + "step": 3891 + }, + { + "epoch": 0.41, + "learning_rate": 1.475074615074993e-05, + "loss": 1.4052, + "step": 3892 + }, + { + "epoch": 0.41, + "learning_rate": 1.4747525011929492e-05, + "loss": 1.4296, + "step": 3893 + }, + { + "epoch": 0.41, + "learning_rate": 1.4744303237062689e-05, + "loss": 1.3718, + "step": 3894 + }, + { + "epoch": 0.41, + "learning_rate": 1.4741080826581151e-05, + "loss": 1.4498, + "step": 3895 + }, + { + "epoch": 0.41, + "learning_rate": 1.4737857780916602e-05, + "loss": 1.4029, + "step": 3896 + }, + { + "epoch": 0.41, + "learning_rate": 1.4734634100500846e-05, + "loss": 1.4136, + "step": 3897 + }, + { + "epoch": 0.41, + "learning_rate": 1.4731409785765774e-05, + "loss": 1.348, + "step": 3898 + }, + { + "epoch": 0.41, + "learning_rate": 1.4728184837143355e-05, + "loss": 1.3407, + "step": 3899 + }, + { + "epoch": 0.41, + "learning_rate": 1.472495925506566e-05, + "loss": 1.3737, + "step": 3900 + }, + { + "epoch": 0.41, + "learning_rate": 1.4721733039964826e-05, + "loss": 2.2305, + "step": 3901 + }, + { + "epoch": 0.41, + "learning_rate": 1.4718506192273087e-05, + "loss": 1.4506, + "step": 3902 + }, + { + "epoch": 0.41, + "learning_rate": 1.4715278712422754e-05, + "loss": 1.3657, + "step": 3903 + }, + { + "epoch": 0.41, + "learning_rate": 1.471205060084623e-05, + "loss": 1.4644, + "step": 3904 + }, + { + "epoch": 0.41, + "learning_rate": 1.4708821857976001e-05, + "loss": 1.4823, + "step": 3905 + }, + { + "epoch": 0.41, + "learning_rate": 1.4705592484244628e-05, + "loss": 1.3392, + "step": 3906 + }, + { + "epoch": 0.41, + "learning_rate": 1.4702362480084769e-05, + "loss": 1.3302, + "step": 3907 + }, + { + "epoch": 0.41, + "learning_rate": 1.4699131845929163e-05, + "loss": 1.8952, + "step": 3908 + }, + { + "epoch": 0.41, + "learning_rate": 1.469590058221063e-05, + "loss": 1.4982, + "step": 3909 + }, + { + "epoch": 0.41, + "learning_rate": 1.4692668689362074e-05, + "loss": 1.407, + "step": 3910 + }, + { + "epoch": 0.41, + "learning_rate": 1.4689436167816489e-05, + "loss": 1.3911, + "step": 3911 + }, + { + "epoch": 0.41, + "learning_rate": 1.4686203018006948e-05, + "loss": 1.3421, + "step": 3912 + }, + { + "epoch": 0.41, + "learning_rate": 1.4682969240366612e-05, + "loss": 1.4627, + "step": 3913 + }, + { + "epoch": 0.41, + "learning_rate": 1.4679734835328718e-05, + "loss": 1.394, + "step": 3914 + }, + { + "epoch": 0.41, + "learning_rate": 1.4676499803326603e-05, + "loss": 1.4484, + "step": 3915 + }, + { + "epoch": 0.41, + "learning_rate": 1.4673264144793673e-05, + "loss": 1.4665, + "step": 3916 + }, + { + "epoch": 0.41, + "learning_rate": 1.4670027860163422e-05, + "loss": 1.3191, + "step": 3917 + }, + { + "epoch": 0.41, + "learning_rate": 1.466679094986943e-05, + "loss": 1.4748, + "step": 3918 + }, + { + "epoch": 0.41, + "learning_rate": 1.4663553414345361e-05, + "loss": 1.2467, + "step": 3919 + }, + { + "epoch": 0.41, + "learning_rate": 1.466031525402496e-05, + "loss": 1.4279, + "step": 3920 + }, + { + "epoch": 0.41, + "learning_rate": 1.4657076469342059e-05, + "loss": 1.3822, + "step": 3921 + }, + { + "epoch": 0.41, + "learning_rate": 1.4653837060730566e-05, + "loss": 1.3659, + "step": 3922 + }, + { + "epoch": 0.41, + "learning_rate": 1.465059702862449e-05, + "loss": 1.3663, + "step": 3923 + }, + { + "epoch": 0.41, + "learning_rate": 1.4647356373457902e-05, + "loss": 1.4371, + "step": 3924 + }, + { + "epoch": 0.41, + "learning_rate": 1.4644115095664972e-05, + "loss": 1.3473, + "step": 3925 + }, + { + "epoch": 0.41, + "learning_rate": 1.4640873195679944e-05, + "loss": 1.4797, + "step": 3926 + }, + { + "epoch": 0.41, + "learning_rate": 1.463763067393715e-05, + "loss": 1.3973, + "step": 3927 + }, + { + "epoch": 0.41, + "learning_rate": 1.4634387530871008e-05, + "loss": 1.3899, + "step": 3928 + }, + { + "epoch": 0.41, + "learning_rate": 1.4631143766916015e-05, + "loss": 1.3828, + "step": 3929 + }, + { + "epoch": 0.41, + "learning_rate": 1.4627899382506745e-05, + "loss": 1.4569, + "step": 3930 + }, + { + "epoch": 0.41, + "learning_rate": 1.4624654378077872e-05, + "loss": 1.4011, + "step": 3931 + }, + { + "epoch": 0.41, + "learning_rate": 1.462140875406414e-05, + "loss": 1.3859, + "step": 3932 + }, + { + "epoch": 0.41, + "learning_rate": 1.4618162510900376e-05, + "loss": 1.4518, + "step": 3933 + }, + { + "epoch": 0.41, + "learning_rate": 1.4614915649021493e-05, + "loss": 1.4399, + "step": 3934 + }, + { + "epoch": 0.41, + "learning_rate": 1.4611668168862495e-05, + "loss": 1.4034, + "step": 3935 + }, + { + "epoch": 0.41, + "learning_rate": 1.4608420070858452e-05, + "loss": 1.3919, + "step": 3936 + }, + { + "epoch": 0.41, + "learning_rate": 1.4605171355444528e-05, + "loss": 1.391, + "step": 3937 + }, + { + "epoch": 0.41, + "learning_rate": 1.460192202305597e-05, + "loss": 1.3717, + "step": 3938 + }, + { + "epoch": 0.41, + "learning_rate": 1.4598672074128103e-05, + "loss": 1.4351, + "step": 3939 + }, + { + "epoch": 0.41, + "learning_rate": 1.4595421509096339e-05, + "loss": 1.4202, + "step": 3940 + }, + { + "epoch": 0.41, + "learning_rate": 1.4592170328396165e-05, + "loss": 1.3559, + "step": 3941 + }, + { + "epoch": 0.41, + "learning_rate": 1.458891853246316e-05, + "loss": 1.5878, + "step": 3942 + }, + { + "epoch": 0.41, + "learning_rate": 1.4585666121732982e-05, + "loss": 1.3818, + "step": 3943 + }, + { + "epoch": 0.41, + "learning_rate": 1.4582413096641369e-05, + "loss": 1.4009, + "step": 3944 + }, + { + "epoch": 0.41, + "learning_rate": 1.457915945762414e-05, + "loss": 1.3937, + "step": 3945 + }, + { + "epoch": 0.41, + "learning_rate": 1.4575905205117203e-05, + "loss": 1.381, + "step": 3946 + }, + { + "epoch": 0.41, + "learning_rate": 1.457265033955654e-05, + "loss": 1.3844, + "step": 3947 + }, + { + "epoch": 0.41, + "learning_rate": 1.4569394861378226e-05, + "loss": 1.4059, + "step": 3948 + }, + { + "epoch": 0.41, + "learning_rate": 1.4566138771018403e-05, + "loss": 1.3698, + "step": 3949 + }, + { + "epoch": 0.41, + "learning_rate": 1.4562882068913311e-05, + "loss": 1.4253, + "step": 3950 + }, + { + "epoch": 0.41, + "learning_rate": 1.455962475549926e-05, + "loss": 1.4284, + "step": 3951 + }, + { + "epoch": 0.41, + "learning_rate": 1.4556366831212647e-05, + "loss": 1.4279, + "step": 3952 + }, + { + "epoch": 0.41, + "learning_rate": 1.4553108296489951e-05, + "loss": 1.3072, + "step": 3953 + }, + { + "epoch": 0.41, + "learning_rate": 1.4549849151767731e-05, + "loss": 1.4175, + "step": 3954 + }, + { + "epoch": 0.41, + "learning_rate": 1.4546589397482632e-05, + "loss": 1.5042, + "step": 3955 + }, + { + "epoch": 0.41, + "learning_rate": 1.4543329034071371e-05, + "loss": 1.4363, + "step": 3956 + }, + { + "epoch": 0.41, + "learning_rate": 1.454006806197076e-05, + "loss": 1.4111, + "step": 3957 + }, + { + "epoch": 0.42, + "learning_rate": 1.453680648161768e-05, + "loss": 1.3817, + "step": 3958 + }, + { + "epoch": 0.42, + "learning_rate": 1.45335442934491e-05, + "loss": 1.4689, + "step": 3959 + }, + { + "epoch": 0.42, + "learning_rate": 1.4530281497902072e-05, + "loss": 1.4164, + "step": 3960 + }, + { + "epoch": 0.42, + "learning_rate": 1.4527018095413726e-05, + "loss": 1.3943, + "step": 3961 + }, + { + "epoch": 0.42, + "learning_rate": 1.4523754086421271e-05, + "loss": 1.3851, + "step": 3962 + }, + { + "epoch": 0.42, + "learning_rate": 1.4520489471362003e-05, + "loss": 1.3907, + "step": 3963 + }, + { + "epoch": 0.42, + "learning_rate": 1.4517224250673297e-05, + "loss": 1.2877, + "step": 3964 + }, + { + "epoch": 0.42, + "learning_rate": 1.4513958424792605e-05, + "loss": 1.4696, + "step": 3965 + }, + { + "epoch": 0.42, + "learning_rate": 1.4510691994157471e-05, + "loss": 1.3785, + "step": 3966 + }, + { + "epoch": 0.42, + "learning_rate": 1.4507424959205505e-05, + "loss": 1.3652, + "step": 3967 + }, + { + "epoch": 0.42, + "learning_rate": 1.4504157320374408e-05, + "loss": 1.4198, + "step": 3968 + }, + { + "epoch": 0.42, + "learning_rate": 1.4500889078101962e-05, + "loss": 1.3476, + "step": 3969 + }, + { + "epoch": 0.42, + "learning_rate": 1.4497620232826028e-05, + "loss": 1.4356, + "step": 3970 + }, + { + "epoch": 0.42, + "learning_rate": 1.4494350784984543e-05, + "loss": 1.4993, + "step": 3971 + }, + { + "epoch": 0.42, + "learning_rate": 1.4491080735015533e-05, + "loss": 1.4022, + "step": 3972 + }, + { + "epoch": 0.42, + "learning_rate": 1.44878100833571e-05, + "loss": 1.4074, + "step": 3973 + }, + { + "epoch": 0.42, + "learning_rate": 1.4484538830447423e-05, + "loss": 1.412, + "step": 3974 + }, + { + "epoch": 0.42, + "learning_rate": 1.4481266976724772e-05, + "loss": 1.3872, + "step": 3975 + }, + { + "epoch": 0.42, + "learning_rate": 1.4477994522627485e-05, + "loss": 1.4575, + "step": 3976 + }, + { + "epoch": 0.42, + "learning_rate": 1.4474721468593995e-05, + "loss": 1.3768, + "step": 3977 + }, + { + "epoch": 0.42, + "learning_rate": 1.44714478150628e-05, + "loss": 1.4173, + "step": 3978 + }, + { + "epoch": 0.42, + "learning_rate": 1.4468173562472489e-05, + "loss": 1.3896, + "step": 3979 + }, + { + "epoch": 0.42, + "learning_rate": 1.4464898711261725e-05, + "loss": 1.4535, + "step": 3980 + }, + { + "epoch": 0.42, + "eval_loss": 1.4580057859420776, + "eval_runtime": 77.4537, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 3980 + }, + { + "epoch": 0.42, + "learning_rate": 1.4461623261869258e-05, + "loss": 1.4046, + "step": 3981 + }, + { + "epoch": 0.42, + "learning_rate": 1.445834721473391e-05, + "loss": 1.37, + "step": 3982 + }, + { + "epoch": 0.42, + "learning_rate": 1.4455070570294588e-05, + "loss": 1.4566, + "step": 3983 + }, + { + "epoch": 0.42, + "learning_rate": 1.445179332899028e-05, + "loss": 1.4513, + "step": 3984 + }, + { + "epoch": 0.42, + "learning_rate": 1.4448515491260051e-05, + "loss": 1.3893, + "step": 3985 + }, + { + "epoch": 0.42, + "learning_rate": 1.4445237057543047e-05, + "loss": 1.3955, + "step": 3986 + }, + { + "epoch": 0.42, + "learning_rate": 1.4441958028278493e-05, + "loss": 1.4861, + "step": 3987 + }, + { + "epoch": 0.42, + "learning_rate": 1.4438678403905697e-05, + "loss": 1.4601, + "step": 3988 + }, + { + "epoch": 0.42, + "learning_rate": 1.4435398184864043e-05, + "loss": 1.398, + "step": 3989 + }, + { + "epoch": 0.42, + "learning_rate": 1.4432117371592995e-05, + "loss": 1.4392, + "step": 3990 + }, + { + "epoch": 0.42, + "learning_rate": 1.4428835964532098e-05, + "loss": 1.3772, + "step": 3991 + }, + { + "epoch": 0.42, + "learning_rate": 1.4425553964120979e-05, + "loss": 1.4241, + "step": 3992 + }, + { + "epoch": 0.42, + "learning_rate": 1.4422271370799338e-05, + "loss": 1.3237, + "step": 3993 + }, + { + "epoch": 0.42, + "learning_rate": 1.4418988185006964e-05, + "loss": 1.3813, + "step": 3994 + }, + { + "epoch": 0.42, + "learning_rate": 1.4415704407183709e-05, + "loss": 1.6139, + "step": 3995 + }, + { + "epoch": 0.42, + "learning_rate": 1.4412420037769525e-05, + "loss": 1.4431, + "step": 3996 + }, + { + "epoch": 0.42, + "learning_rate": 1.440913507720443e-05, + "loss": 1.3862, + "step": 3997 + }, + { + "epoch": 0.42, + "learning_rate": 1.4405849525928523e-05, + "loss": 1.3895, + "step": 3998 + }, + { + "epoch": 0.42, + "learning_rate": 1.4402563384381981e-05, + "loss": 1.4068, + "step": 3999 + }, + { + "epoch": 0.42, + "learning_rate": 1.4399276653005072e-05, + "loss": 1.4501, + "step": 4000 + }, + { + "epoch": 0.42, + "learning_rate": 1.4395989332238124e-05, + "loss": 1.3165, + "step": 4001 + }, + { + "epoch": 0.42, + "learning_rate": 1.4392701422521555e-05, + "loss": 1.3783, + "step": 4002 + }, + { + "epoch": 0.42, + "learning_rate": 1.4389412924295865e-05, + "loss": 1.343, + "step": 4003 + }, + { + "epoch": 0.42, + "learning_rate": 1.4386123838001625e-05, + "loss": 1.3456, + "step": 4004 + }, + { + "epoch": 0.42, + "learning_rate": 1.4382834164079486e-05, + "loss": 1.3689, + "step": 4005 + }, + { + "epoch": 0.42, + "learning_rate": 1.4379543902970183e-05, + "loss": 1.3789, + "step": 4006 + }, + { + "epoch": 0.42, + "learning_rate": 1.4376253055114528e-05, + "loss": 1.4912, + "step": 4007 + }, + { + "epoch": 0.42, + "learning_rate": 1.4372961620953407e-05, + "loss": 1.3692, + "step": 4008 + }, + { + "epoch": 0.42, + "learning_rate": 1.436966960092779e-05, + "loss": 1.4901, + "step": 4009 + }, + { + "epoch": 0.42, + "learning_rate": 1.4366376995478717e-05, + "loss": 1.4431, + "step": 4010 + }, + { + "epoch": 0.42, + "learning_rate": 1.436308380504732e-05, + "loss": 1.4626, + "step": 4011 + }, + { + "epoch": 0.42, + "learning_rate": 1.4359790030074798e-05, + "loss": 1.4241, + "step": 4012 + }, + { + "epoch": 0.42, + "learning_rate": 1.4356495671002435e-05, + "loss": 1.3834, + "step": 4013 + }, + { + "epoch": 0.42, + "learning_rate": 1.4353200728271586e-05, + "loss": 1.3626, + "step": 4014 + }, + { + "epoch": 0.42, + "learning_rate": 1.4349905202323692e-05, + "loss": 1.3557, + "step": 4015 + }, + { + "epoch": 0.42, + "learning_rate": 1.434660909360027e-05, + "loss": 1.4077, + "step": 4016 + }, + { + "epoch": 0.42, + "learning_rate": 1.4343312402542911e-05, + "loss": 1.4337, + "step": 4017 + }, + { + "epoch": 0.42, + "learning_rate": 1.4340015129593286e-05, + "loss": 1.419, + "step": 4018 + }, + { + "epoch": 0.42, + "learning_rate": 1.4336717275193148e-05, + "loss": 1.3768, + "step": 4019 + }, + { + "epoch": 0.42, + "learning_rate": 1.4333418839784326e-05, + "loss": 1.383, + "step": 4020 + }, + { + "epoch": 0.42, + "learning_rate": 1.4330119823808719e-05, + "loss": 1.3951, + "step": 4021 + }, + { + "epoch": 0.42, + "learning_rate": 1.4326820227708316e-05, + "loss": 1.3985, + "step": 4022 + }, + { + "epoch": 0.42, + "learning_rate": 1.4323520051925177e-05, + "loss": 1.356, + "step": 4023 + }, + { + "epoch": 0.42, + "learning_rate": 1.4320219296901439e-05, + "loss": 1.5017, + "step": 4024 + }, + { + "epoch": 0.42, + "learning_rate": 1.4316917963079322e-05, + "loss": 1.3594, + "step": 4025 + }, + { + "epoch": 0.42, + "learning_rate": 1.4313616050901114e-05, + "loss": 1.6028, + "step": 4026 + }, + { + "epoch": 0.42, + "learning_rate": 1.4310313560809193e-05, + "loss": 1.4132, + "step": 4027 + }, + { + "epoch": 0.42, + "learning_rate": 1.4307010493246006e-05, + "loss": 1.2969, + "step": 4028 + }, + { + "epoch": 0.42, + "learning_rate": 1.4303706848654073e-05, + "loss": 1.5224, + "step": 4029 + }, + { + "epoch": 0.42, + "learning_rate": 1.4300402627476007e-05, + "loss": 1.3386, + "step": 4030 + }, + { + "epoch": 0.42, + "learning_rate": 1.429709783015448e-05, + "loss": 1.3554, + "step": 4031 + }, + { + "epoch": 0.42, + "learning_rate": 1.4293792457132259e-05, + "loss": 1.3386, + "step": 4032 + }, + { + "epoch": 0.42, + "learning_rate": 1.429048650885217e-05, + "loss": 1.4613, + "step": 4033 + }, + { + "epoch": 0.42, + "learning_rate": 1.4287179985757132e-05, + "loss": 1.3632, + "step": 4034 + }, + { + "epoch": 0.42, + "learning_rate": 1.428387288829013e-05, + "loss": 1.3835, + "step": 4035 + }, + { + "epoch": 0.42, + "learning_rate": 1.4280565216894234e-05, + "loss": 1.3711, + "step": 4036 + }, + { + "epoch": 0.42, + "learning_rate": 1.4277256972012582e-05, + "loss": 1.3385, + "step": 4037 + }, + { + "epoch": 0.42, + "learning_rate": 1.4273948154088395e-05, + "loss": 1.4607, + "step": 4038 + }, + { + "epoch": 0.42, + "learning_rate": 1.4270638763564973e-05, + "loss": 1.4042, + "step": 4039 + }, + { + "epoch": 0.42, + "learning_rate": 1.4267328800885687e-05, + "loss": 1.4006, + "step": 4040 + }, + { + "epoch": 0.42, + "learning_rate": 1.4264018266493987e-05, + "loss": 1.386, + "step": 4041 + }, + { + "epoch": 0.42, + "learning_rate": 1.4260707160833401e-05, + "loss": 1.3487, + "step": 4042 + }, + { + "epoch": 0.42, + "learning_rate": 1.4257395484347529e-05, + "loss": 1.4199, + "step": 4043 + }, + { + "epoch": 0.42, + "learning_rate": 1.4254083237480054e-05, + "loss": 1.3236, + "step": 4044 + }, + { + "epoch": 0.42, + "learning_rate": 1.4250770420674726e-05, + "loss": 1.4056, + "step": 4045 + }, + { + "epoch": 0.42, + "learning_rate": 1.4247457034375387e-05, + "loss": 1.4391, + "step": 4046 + }, + { + "epoch": 0.42, + "learning_rate": 1.4244143079025938e-05, + "loss": 1.3935, + "step": 4047 + }, + { + "epoch": 0.42, + "learning_rate": 1.4240828555070368e-05, + "loss": 1.3623, + "step": 4048 + }, + { + "epoch": 0.42, + "learning_rate": 1.4237513462952733e-05, + "loss": 1.3254, + "step": 4049 + }, + { + "epoch": 0.42, + "learning_rate": 1.4234197803117174e-05, + "loss": 1.4217, + "step": 4050 + }, + { + "epoch": 0.42, + "learning_rate": 1.4230881576007904e-05, + "loss": 1.435, + "step": 4051 + }, + { + "epoch": 0.42, + "learning_rate": 1.422756478206921e-05, + "loss": 1.3687, + "step": 4052 + }, + { + "epoch": 0.43, + "learning_rate": 1.4224247421745464e-05, + "loss": 1.3965, + "step": 4053 + }, + { + "epoch": 0.43, + "learning_rate": 1.4220929495481097e-05, + "loss": 1.4159, + "step": 4054 + }, + { + "epoch": 0.43, + "learning_rate": 1.4217611003720632e-05, + "loss": 1.3632, + "step": 4055 + }, + { + "epoch": 0.43, + "learning_rate": 1.4214291946908661e-05, + "loss": 1.403, + "step": 4056 + }, + { + "epoch": 0.43, + "learning_rate": 1.4210972325489854e-05, + "loss": 1.4093, + "step": 4057 + }, + { + "epoch": 0.43, + "learning_rate": 1.4207652139908952e-05, + "loss": 1.4551, + "step": 4058 + }, + { + "epoch": 0.43, + "learning_rate": 1.4204331390610775e-05, + "loss": 1.4162, + "step": 4059 + }, + { + "epoch": 0.43, + "learning_rate": 1.4201010078040216e-05, + "loss": 1.4492, + "step": 4060 + }, + { + "epoch": 0.43, + "learning_rate": 1.419768820264225e-05, + "loss": 1.4449, + "step": 4061 + }, + { + "epoch": 0.43, + "learning_rate": 1.4194365764861922e-05, + "loss": 1.3382, + "step": 4062 + }, + { + "epoch": 0.43, + "learning_rate": 1.419104276514435e-05, + "loss": 1.3899, + "step": 4063 + }, + { + "epoch": 0.43, + "learning_rate": 1.4187719203934734e-05, + "loss": 1.3513, + "step": 4064 + }, + { + "epoch": 0.43, + "learning_rate": 1.4184395081678344e-05, + "loss": 1.3954, + "step": 4065 + }, + { + "epoch": 0.43, + "learning_rate": 1.4181070398820528e-05, + "loss": 1.442, + "step": 4066 + }, + { + "epoch": 0.43, + "learning_rate": 1.4177745155806708e-05, + "loss": 1.3907, + "step": 4067 + }, + { + "epoch": 0.43, + "learning_rate": 1.417441935308238e-05, + "loss": 1.3757, + "step": 4068 + }, + { + "epoch": 0.43, + "learning_rate": 1.4171092991093118e-05, + "loss": 1.3507, + "step": 4069 + }, + { + "epoch": 0.43, + "learning_rate": 1.4167766070284568e-05, + "loss": 1.4136, + "step": 4070 + }, + { + "epoch": 0.43, + "learning_rate": 1.4164438591102452e-05, + "loss": 1.3835, + "step": 4071 + }, + { + "epoch": 0.43, + "learning_rate": 1.4161110553992565e-05, + "loss": 1.4981, + "step": 4072 + }, + { + "epoch": 0.43, + "learning_rate": 1.415778195940078e-05, + "loss": 1.4387, + "step": 4073 + }, + { + "epoch": 0.43, + "learning_rate": 1.4154452807773047e-05, + "loss": 1.333, + "step": 4074 + }, + { + "epoch": 0.43, + "learning_rate": 1.4151123099555377e-05, + "loss": 1.3558, + "step": 4075 + }, + { + "epoch": 0.43, + "learning_rate": 1.4147792835193875e-05, + "loss": 1.4655, + "step": 4076 + }, + { + "epoch": 0.43, + "learning_rate": 1.4144462015134708e-05, + "loss": 1.4402, + "step": 4077 + }, + { + "epoch": 0.43, + "learning_rate": 1.4141130639824119e-05, + "loss": 1.4227, + "step": 4078 + }, + { + "epoch": 0.43, + "learning_rate": 1.4137798709708423e-05, + "loss": 1.4039, + "step": 4079 + }, + { + "epoch": 0.43, + "learning_rate": 1.4134466225234023e-05, + "loss": 1.3593, + "step": 4080 + }, + { + "epoch": 0.43, + "learning_rate": 1.4131133186847377e-05, + "loss": 1.372, + "step": 4081 + }, + { + "epoch": 0.43, + "learning_rate": 1.412779959499503e-05, + "loss": 1.4487, + "step": 4082 + }, + { + "epoch": 0.43, + "learning_rate": 1.4124465450123599e-05, + "loss": 1.3972, + "step": 4083 + }, + { + "epoch": 0.43, + "learning_rate": 1.4121130752679772e-05, + "loss": 1.3768, + "step": 4084 + }, + { + "epoch": 0.43, + "learning_rate": 1.4117795503110313e-05, + "loss": 1.3827, + "step": 4085 + }, + { + "epoch": 0.43, + "learning_rate": 1.4114459701862062e-05, + "loss": 1.3922, + "step": 4086 + }, + { + "epoch": 0.43, + "learning_rate": 1.4111123349381925e-05, + "loss": 1.3736, + "step": 4087 + }, + { + "epoch": 0.43, + "learning_rate": 1.4107786446116894e-05, + "loss": 1.4338, + "step": 4088 + }, + { + "epoch": 0.43, + "learning_rate": 1.4104448992514023e-05, + "loss": 1.347, + "step": 4089 + }, + { + "epoch": 0.43, + "learning_rate": 1.410111098902045e-05, + "loss": 1.3915, + "step": 4090 + }, + { + "epoch": 0.43, + "learning_rate": 1.4097772436083377e-05, + "loss": 1.3656, + "step": 4091 + }, + { + "epoch": 0.43, + "learning_rate": 1.4094433334150087e-05, + "loss": 1.3461, + "step": 4092 + }, + { + "epoch": 0.43, + "learning_rate": 1.4091093683667934e-05, + "loss": 1.7345, + "step": 4093 + }, + { + "epoch": 0.43, + "learning_rate": 1.4087753485084343e-05, + "loss": 1.6204, + "step": 4094 + }, + { + "epoch": 0.43, + "learning_rate": 1.4084412738846816e-05, + "loss": 1.4074, + "step": 4095 + }, + { + "epoch": 0.43, + "learning_rate": 1.408107144540293e-05, + "loss": 1.3776, + "step": 4096 + }, + { + "epoch": 0.43, + "learning_rate": 1.407772960520033e-05, + "loss": 1.4079, + "step": 4097 + }, + { + "epoch": 0.43, + "learning_rate": 1.4074387218686734e-05, + "loss": 1.4254, + "step": 4098 + }, + { + "epoch": 0.43, + "learning_rate": 1.407104428630994e-05, + "loss": 1.38, + "step": 4099 + }, + { + "epoch": 0.43, + "learning_rate": 1.4067700808517815e-05, + "loss": 1.4175, + "step": 4100 + }, + { + "epoch": 0.43, + "learning_rate": 1.4064356785758298e-05, + "loss": 1.4085, + "step": 4101 + }, + { + "epoch": 0.43, + "learning_rate": 1.4061012218479397e-05, + "loss": 1.4529, + "step": 4102 + }, + { + "epoch": 0.43, + "learning_rate": 1.405766710712921e-05, + "loss": 1.4836, + "step": 4103 + }, + { + "epoch": 0.43, + "learning_rate": 1.4054321452155885e-05, + "loss": 1.3915, + "step": 4104 + }, + { + "epoch": 0.43, + "learning_rate": 1.4050975254007659e-05, + "loss": 1.3044, + "step": 4105 + }, + { + "epoch": 0.43, + "learning_rate": 1.4047628513132835e-05, + "loss": 1.373, + "step": 4106 + }, + { + "epoch": 0.43, + "learning_rate": 1.4044281229979793e-05, + "loss": 1.4266, + "step": 4107 + }, + { + "epoch": 0.43, + "learning_rate": 1.4040933404996977e-05, + "loss": 1.3898, + "step": 4108 + }, + { + "epoch": 0.43, + "learning_rate": 1.4037585038632915e-05, + "loss": 0.9326, + "step": 4109 + }, + { + "epoch": 0.43, + "learning_rate": 1.40342361313362e-05, + "loss": 1.0831, + "step": 4110 + }, + { + "epoch": 0.43, + "learning_rate": 1.40308866835555e-05, + "loss": 1.3898, + "step": 4111 + }, + { + "epoch": 0.43, + "learning_rate": 1.4027536695739554e-05, + "loss": 1.5058, + "step": 4112 + }, + { + "epoch": 0.43, + "learning_rate": 1.4024186168337175e-05, + "loss": 1.3635, + "step": 4113 + }, + { + "epoch": 0.43, + "learning_rate": 1.4020835101797248e-05, + "loss": 1.3871, + "step": 4114 + }, + { + "epoch": 0.43, + "learning_rate": 1.401748349656873e-05, + "loss": 1.3478, + "step": 4115 + }, + { + "epoch": 0.43, + "learning_rate": 1.4014131353100648e-05, + "loss": 1.3356, + "step": 4116 + }, + { + "epoch": 0.43, + "learning_rate": 1.4010778671842107e-05, + "loss": 1.3954, + "step": 4117 + }, + { + "epoch": 0.43, + "learning_rate": 1.4007425453242274e-05, + "loss": 1.3307, + "step": 4118 + }, + { + "epoch": 0.43, + "learning_rate": 1.4004071697750398e-05, + "loss": 1.4508, + "step": 4119 + }, + { + "epoch": 0.43, + "learning_rate": 1.4000717405815799e-05, + "loss": 1.3752, + "step": 4120 + }, + { + "epoch": 0.43, + "learning_rate": 1.399736257788786e-05, + "loss": 1.3654, + "step": 4121 + }, + { + "epoch": 0.43, + "learning_rate": 1.3994007214416046e-05, + "loss": 1.4505, + "step": 4122 + }, + { + "epoch": 0.43, + "learning_rate": 1.3990651315849886e-05, + "loss": 1.4307, + "step": 4123 + }, + { + "epoch": 0.43, + "learning_rate": 1.398729488263899e-05, + "loss": 1.4481, + "step": 4124 + }, + { + "epoch": 0.43, + "learning_rate": 1.3983937915233026e-05, + "loss": 1.4755, + "step": 4125 + }, + { + "epoch": 0.43, + "learning_rate": 1.3980580414081746e-05, + "loss": 1.3402, + "step": 4126 + }, + { + "epoch": 0.43, + "learning_rate": 1.3977222379634969e-05, + "loss": 1.3636, + "step": 4127 + }, + { + "epoch": 0.43, + "learning_rate": 1.3973863812342585e-05, + "loss": 1.4165, + "step": 4128 + }, + { + "epoch": 0.43, + "learning_rate": 1.3970504712654554e-05, + "loss": 1.3832, + "step": 4129 + }, + { + "epoch": 0.43, + "learning_rate": 1.3967145081020912e-05, + "loss": 1.4236, + "step": 4130 + }, + { + "epoch": 0.43, + "learning_rate": 1.396378491789176e-05, + "loss": 1.5022, + "step": 4131 + }, + { + "epoch": 0.43, + "learning_rate": 1.3960424223717276e-05, + "loss": 1.3806, + "step": 4132 + }, + { + "epoch": 0.43, + "learning_rate": 1.3957062998947707e-05, + "loss": 1.3649, + "step": 4133 + }, + { + "epoch": 0.43, + "learning_rate": 1.3953701244033368e-05, + "loss": 1.3787, + "step": 4134 + }, + { + "epoch": 0.43, + "learning_rate": 1.395033895942465e-05, + "loss": 1.3551, + "step": 4135 + }, + { + "epoch": 0.43, + "learning_rate": 1.394697614557201e-05, + "loss": 1.3881, + "step": 4136 + }, + { + "epoch": 0.43, + "learning_rate": 1.3943612802925983e-05, + "loss": 1.4848, + "step": 4137 + }, + { + "epoch": 0.43, + "learning_rate": 1.3940248931937169e-05, + "loss": 1.425, + "step": 4138 + }, + { + "epoch": 0.43, + "learning_rate": 1.3936884533056238e-05, + "loss": 1.4054, + "step": 4139 + }, + { + "epoch": 0.43, + "learning_rate": 1.3933519606733934e-05, + "loss": 1.4028, + "step": 4140 + }, + { + "epoch": 0.43, + "learning_rate": 1.3930154153421072e-05, + "loss": 1.4439, + "step": 4141 + }, + { + "epoch": 0.43, + "learning_rate": 1.3926788173568536e-05, + "loss": 1.4482, + "step": 4142 + }, + { + "epoch": 0.43, + "learning_rate": 1.392342166762728e-05, + "loss": 1.393, + "step": 4143 + }, + { + "epoch": 0.43, + "learning_rate": 1.3920054636048328e-05, + "loss": 1.4097, + "step": 4144 + }, + { + "epoch": 0.43, + "learning_rate": 1.391668707928278e-05, + "loss": 1.5142, + "step": 4145 + }, + { + "epoch": 0.43, + "learning_rate": 1.3913318997781797e-05, + "loss": 1.4118, + "step": 4146 + }, + { + "epoch": 0.43, + "learning_rate": 1.390995039199662e-05, + "loss": 1.4067, + "step": 4147 + }, + { + "epoch": 0.43, + "learning_rate": 1.3906581262378552e-05, + "loss": 1.5214, + "step": 4148 + }, + { + "epoch": 0.44, + "learning_rate": 1.3903211609378971e-05, + "loss": 1.3618, + "step": 4149 + }, + { + "epoch": 0.44, + "learning_rate": 1.3899841433449327e-05, + "loss": 1.338, + "step": 4150 + }, + { + "epoch": 0.44, + "learning_rate": 1.3896470735041132e-05, + "loss": 1.3901, + "step": 4151 + }, + { + "epoch": 0.44, + "learning_rate": 1.3893099514605971e-05, + "loss": 1.4502, + "step": 4152 + }, + { + "epoch": 0.44, + "learning_rate": 1.388972777259551e-05, + "loss": 1.4141, + "step": 4153 + }, + { + "epoch": 0.44, + "learning_rate": 1.3886355509461471e-05, + "loss": 1.3876, + "step": 4154 + }, + { + "epoch": 0.44, + "learning_rate": 1.388298272565565e-05, + "loss": 1.4275, + "step": 4155 + }, + { + "epoch": 0.44, + "learning_rate": 1.3879609421629909e-05, + "loss": 1.3559, + "step": 4156 + }, + { + "epoch": 0.44, + "learning_rate": 1.3876235597836195e-05, + "loss": 1.416, + "step": 4157 + }, + { + "epoch": 0.44, + "learning_rate": 1.3872861254726506e-05, + "loss": 1.437, + "step": 4158 + }, + { + "epoch": 0.44, + "learning_rate": 1.3869486392752918e-05, + "loss": 1.3794, + "step": 4159 + }, + { + "epoch": 0.44, + "learning_rate": 1.3866111012367577e-05, + "loss": 1.4094, + "step": 4160 + }, + { + "epoch": 0.44, + "learning_rate": 1.3862735114022694e-05, + "loss": 1.3957, + "step": 4161 + }, + { + "epoch": 0.44, + "learning_rate": 1.3859358698170559e-05, + "loss": 1.3582, + "step": 4162 + }, + { + "epoch": 0.44, + "learning_rate": 1.3855981765263523e-05, + "loss": 1.4159, + "step": 4163 + }, + { + "epoch": 0.44, + "learning_rate": 1.3852604315754e-05, + "loss": 1.3498, + "step": 4164 + }, + { + "epoch": 0.44, + "learning_rate": 1.3849226350094491e-05, + "loss": 1.3951, + "step": 4165 + }, + { + "epoch": 0.44, + "learning_rate": 1.3845847868737559e-05, + "loss": 1.4087, + "step": 4166 + }, + { + "epoch": 0.44, + "learning_rate": 1.3842468872135821e-05, + "loss": 1.4318, + "step": 4167 + }, + { + "epoch": 0.44, + "learning_rate": 1.3839089360741989e-05, + "loss": 1.4174, + "step": 4168 + }, + { + "epoch": 0.44, + "learning_rate": 1.3835709335008822e-05, + "loss": 1.4499, + "step": 4169 + }, + { + "epoch": 0.44, + "learning_rate": 1.383232879538916e-05, + "loss": 1.3554, + "step": 4170 + }, + { + "epoch": 0.44, + "learning_rate": 1.3828947742335905e-05, + "loss": 1.3873, + "step": 4171 + }, + { + "epoch": 0.44, + "learning_rate": 1.382556617630204e-05, + "loss": 1.3804, + "step": 4172 + }, + { + "epoch": 0.44, + "learning_rate": 1.3822184097740598e-05, + "loss": 1.3856, + "step": 4173 + }, + { + "epoch": 0.44, + "learning_rate": 1.3818801507104697e-05, + "loss": 1.3901, + "step": 4174 + }, + { + "epoch": 0.44, + "learning_rate": 1.381541840484751e-05, + "loss": 1.3714, + "step": 4175 + }, + { + "epoch": 0.44, + "learning_rate": 1.3812034791422297e-05, + "loss": 1.4945, + "step": 4176 + }, + { + "epoch": 0.44, + "learning_rate": 1.3808650667282368e-05, + "loss": 1.429, + "step": 4177 + }, + { + "epoch": 0.44, + "learning_rate": 1.3805266032881108e-05, + "loss": 1.3903, + "step": 4178 + }, + { + "epoch": 0.44, + "learning_rate": 1.3801880888671972e-05, + "loss": 1.4799, + "step": 4179 + }, + { + "epoch": 0.44, + "eval_loss": 1.4521424770355225, + "eval_runtime": 77.3596, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 4179 + }, + { + "epoch": 0.44, + "learning_rate": 1.3798495235108484e-05, + "loss": 1.3912, + "step": 4180 + }, + { + "epoch": 0.44, + "learning_rate": 1.3795109072644235e-05, + "loss": 1.5837, + "step": 4181 + }, + { + "epoch": 0.44, + "learning_rate": 1.379172240173288e-05, + "loss": 1.4255, + "step": 4182 + }, + { + "epoch": 0.44, + "learning_rate": 1.3788335222828148e-05, + "loss": 1.4666, + "step": 4183 + }, + { + "epoch": 0.44, + "learning_rate": 1.3784947536383837e-05, + "loss": 1.3964, + "step": 4184 + }, + { + "epoch": 0.44, + "learning_rate": 1.3781559342853807e-05, + "loss": 1.336, + "step": 4185 + }, + { + "epoch": 0.44, + "learning_rate": 1.3778170642691986e-05, + "loss": 1.4352, + "step": 4186 + }, + { + "epoch": 0.44, + "learning_rate": 1.377478143635238e-05, + "loss": 1.3262, + "step": 4187 + }, + { + "epoch": 0.44, + "learning_rate": 1.3771391724289047e-05, + "loss": 1.3969, + "step": 4188 + }, + { + "epoch": 0.44, + "learning_rate": 1.376800150695613e-05, + "loss": 1.4211, + "step": 4189 + }, + { + "epoch": 0.44, + "learning_rate": 1.3764610784807824e-05, + "loss": 1.4338, + "step": 4190 + }, + { + "epoch": 0.44, + "learning_rate": 1.3761219558298403e-05, + "loss": 1.3815, + "step": 4191 + }, + { + "epoch": 0.44, + "learning_rate": 1.3757827827882203e-05, + "loss": 1.3805, + "step": 4192 + }, + { + "epoch": 0.44, + "learning_rate": 1.3754435594013627e-05, + "loss": 1.4071, + "step": 4193 + }, + { + "epoch": 0.44, + "learning_rate": 1.3751042857147145e-05, + "loss": 1.343, + "step": 4194 + }, + { + "epoch": 0.44, + "learning_rate": 1.3747649617737304e-05, + "loss": 1.4129, + "step": 4195 + }, + { + "epoch": 0.44, + "learning_rate": 1.3744255876238708e-05, + "loss": 1.3939, + "step": 4196 + }, + { + "epoch": 0.44, + "learning_rate": 1.3740861633106029e-05, + "loss": 1.3963, + "step": 4197 + }, + { + "epoch": 0.44, + "learning_rate": 1.3737466888794008e-05, + "loss": 1.5181, + "step": 4198 + }, + { + "epoch": 0.44, + "learning_rate": 1.3734071643757456e-05, + "loss": 1.4397, + "step": 4199 + }, + { + "epoch": 0.44, + "learning_rate": 1.373067589845125e-05, + "loss": 1.6293, + "step": 4200 + }, + { + "epoch": 0.44, + "learning_rate": 1.3727279653330328e-05, + "loss": 1.3498, + "step": 4201 + }, + { + "epoch": 0.44, + "learning_rate": 1.37238829088497e-05, + "loss": 1.4509, + "step": 4202 + }, + { + "epoch": 0.44, + "learning_rate": 1.3720485665464446e-05, + "loss": 1.4477, + "step": 4203 + }, + { + "epoch": 0.44, + "learning_rate": 1.3717087923629709e-05, + "loss": 1.4399, + "step": 4204 + }, + { + "epoch": 0.44, + "learning_rate": 1.3713689683800695e-05, + "loss": 1.4417, + "step": 4205 + }, + { + "epoch": 0.44, + "learning_rate": 1.3710290946432685e-05, + "loss": 1.3957, + "step": 4206 + }, + { + "epoch": 0.44, + "learning_rate": 1.3706891711981021e-05, + "loss": 1.4476, + "step": 4207 + }, + { + "epoch": 0.44, + "learning_rate": 1.3703491980901113e-05, + "loss": 1.3894, + "step": 4208 + }, + { + "epoch": 0.44, + "learning_rate": 1.3700091753648437e-05, + "loss": 1.4745, + "step": 4209 + }, + { + "epoch": 0.44, + "learning_rate": 1.369669103067854e-05, + "loss": 1.4038, + "step": 4210 + }, + { + "epoch": 0.44, + "learning_rate": 1.3693289812447023e-05, + "loss": 1.4151, + "step": 4211 + }, + { + "epoch": 0.44, + "learning_rate": 1.3689888099409572e-05, + "loss": 1.4214, + "step": 4212 + }, + { + "epoch": 0.44, + "learning_rate": 1.368648589202192e-05, + "loss": 1.4287, + "step": 4213 + }, + { + "epoch": 0.44, + "learning_rate": 1.3683083190739883e-05, + "loss": 1.345, + "step": 4214 + }, + { + "epoch": 0.44, + "learning_rate": 1.367967999601933e-05, + "loss": 1.3022, + "step": 4215 + }, + { + "epoch": 0.44, + "learning_rate": 1.3676276308316207e-05, + "loss": 1.3971, + "step": 4216 + }, + { + "epoch": 0.44, + "learning_rate": 1.3672872128086514e-05, + "loss": 1.3335, + "step": 4217 + }, + { + "epoch": 0.44, + "learning_rate": 1.366946745578633e-05, + "loss": 1.3988, + "step": 4218 + }, + { + "epoch": 0.44, + "learning_rate": 1.366606229187179e-05, + "loss": 1.4508, + "step": 4219 + }, + { + "epoch": 0.44, + "learning_rate": 1.3662656636799099e-05, + "loss": 1.3814, + "step": 4220 + }, + { + "epoch": 0.44, + "learning_rate": 1.3659250491024527e-05, + "loss": 1.4128, + "step": 4221 + }, + { + "epoch": 0.44, + "learning_rate": 1.3655843855004411e-05, + "loss": 1.3893, + "step": 4222 + }, + { + "epoch": 0.44, + "learning_rate": 1.3652436729195154e-05, + "loss": 1.2551, + "step": 4223 + }, + { + "epoch": 0.44, + "learning_rate": 1.3649029114053219e-05, + "loss": 1.4386, + "step": 4224 + }, + { + "epoch": 0.44, + "learning_rate": 1.364562101003514e-05, + "loss": 1.4028, + "step": 4225 + }, + { + "epoch": 0.44, + "learning_rate": 1.364221241759752e-05, + "loss": 1.4351, + "step": 4226 + }, + { + "epoch": 0.44, + "learning_rate": 1.363880333719702e-05, + "loss": 1.3941, + "step": 4227 + }, + { + "epoch": 0.44, + "learning_rate": 1.3635393769290368e-05, + "loss": 1.3879, + "step": 4228 + }, + { + "epoch": 0.44, + "learning_rate": 1.3631983714334358e-05, + "loss": 1.3773, + "step": 4229 + }, + { + "epoch": 0.44, + "learning_rate": 1.3628573172785853e-05, + "loss": 1.3679, + "step": 4230 + }, + { + "epoch": 0.44, + "learning_rate": 1.3625162145101776e-05, + "loss": 1.3705, + "step": 4231 + }, + { + "epoch": 0.44, + "learning_rate": 1.3621750631739114e-05, + "loss": 1.8157, + "step": 4232 + }, + { + "epoch": 0.44, + "learning_rate": 1.3618338633154928e-05, + "loss": 1.4056, + "step": 4233 + }, + { + "epoch": 0.44, + "learning_rate": 1.3614926149806334e-05, + "loss": 1.3716, + "step": 4234 + }, + { + "epoch": 0.44, + "learning_rate": 1.3611513182150523e-05, + "loss": 1.3766, + "step": 4235 + }, + { + "epoch": 0.44, + "learning_rate": 1.3608099730644733e-05, + "loss": 1.41, + "step": 4236 + }, + { + "epoch": 0.44, + "learning_rate": 1.3604685795746291e-05, + "loss": 1.421, + "step": 4237 + }, + { + "epoch": 0.44, + "learning_rate": 1.360127137791257e-05, + "loss": 1.3679, + "step": 4238 + }, + { + "epoch": 0.44, + "learning_rate": 1.3597856477601018e-05, + "loss": 1.4615, + "step": 4239 + }, + { + "epoch": 0.44, + "learning_rate": 1.359444109526914e-05, + "loss": 1.3418, + "step": 4240 + }, + { + "epoch": 0.44, + "learning_rate": 1.3591025231374513e-05, + "loss": 1.3631, + "step": 4241 + }, + { + "epoch": 0.44, + "learning_rate": 1.3587608886374772e-05, + "loss": 1.3802, + "step": 4242 + }, + { + "epoch": 0.44, + "learning_rate": 1.3584192060727622e-05, + "loss": 1.4156, + "step": 4243 + }, + { + "epoch": 0.45, + "learning_rate": 1.3580774754890827e-05, + "loss": 1.4161, + "step": 4244 + }, + { + "epoch": 0.45, + "learning_rate": 1.3577356969322222e-05, + "loss": 1.3535, + "step": 4245 + }, + { + "epoch": 0.45, + "learning_rate": 1.3573938704479699e-05, + "loss": 1.3859, + "step": 4246 + }, + { + "epoch": 0.45, + "learning_rate": 1.357051996082122e-05, + "loss": 1.3595, + "step": 4247 + }, + { + "epoch": 0.45, + "learning_rate": 1.3567100738804806e-05, + "loss": 1.4191, + "step": 4248 + }, + { + "epoch": 0.45, + "learning_rate": 1.3563681038888548e-05, + "loss": 1.4186, + "step": 4249 + }, + { + "epoch": 0.45, + "learning_rate": 1.3560260861530596e-05, + "loss": 1.43, + "step": 4250 + }, + { + "epoch": 0.45, + "learning_rate": 1.3556840207189168e-05, + "loss": 1.4139, + "step": 4251 + }, + { + "epoch": 0.45, + "learning_rate": 1.3553419076322539e-05, + "loss": 1.4005, + "step": 4252 + }, + { + "epoch": 0.45, + "learning_rate": 1.3549997469389058e-05, + "loss": 1.3468, + "step": 4253 + }, + { + "epoch": 0.45, + "learning_rate": 1.3546575386847132e-05, + "loss": 1.3756, + "step": 4254 + }, + { + "epoch": 0.45, + "learning_rate": 1.3543152829155226e-05, + "loss": 1.4063, + "step": 4255 + }, + { + "epoch": 0.45, + "learning_rate": 1.3539729796771884e-05, + "loss": 1.4666, + "step": 4256 + }, + { + "epoch": 0.45, + "learning_rate": 1.3536306290155694e-05, + "loss": 1.4212, + "step": 4257 + }, + { + "epoch": 0.45, + "learning_rate": 1.3532882309765332e-05, + "loss": 1.4883, + "step": 4258 + }, + { + "epoch": 0.45, + "learning_rate": 1.3529457856059507e-05, + "loss": 1.6641, + "step": 4259 + }, + { + "epoch": 0.45, + "learning_rate": 1.3526032929497022e-05, + "loss": 1.3659, + "step": 4260 + }, + { + "epoch": 0.45, + "learning_rate": 1.3522607530536717e-05, + "loss": 1.5945, + "step": 4261 + }, + { + "epoch": 0.45, + "learning_rate": 1.351918165963752e-05, + "loss": 1.3643, + "step": 4262 + }, + { + "epoch": 0.45, + "learning_rate": 1.3515755317258397e-05, + "loss": 1.3442, + "step": 4263 + }, + { + "epoch": 0.45, + "learning_rate": 1.3512328503858398e-05, + "loss": 1.3982, + "step": 4264 + }, + { + "epoch": 0.45, + "learning_rate": 1.3508901219896624e-05, + "loss": 1.4985, + "step": 4265 + }, + { + "epoch": 0.45, + "learning_rate": 1.350547346583225e-05, + "loss": 1.3319, + "step": 4266 + }, + { + "epoch": 0.45, + "learning_rate": 1.3502045242124497e-05, + "loss": 1.3961, + "step": 4267 + }, + { + "epoch": 0.45, + "learning_rate": 1.3498616549232665e-05, + "loss": 1.4565, + "step": 4268 + }, + { + "epoch": 0.45, + "learning_rate": 1.349518738761611e-05, + "loss": 1.375, + "step": 4269 + }, + { + "epoch": 0.45, + "learning_rate": 1.3491757757734254e-05, + "loss": 1.3005, + "step": 4270 + }, + { + "epoch": 0.45, + "learning_rate": 1.348832766004657e-05, + "loss": 1.3185, + "step": 4271 + }, + { + "epoch": 0.45, + "learning_rate": 1.3484897095012613e-05, + "loss": 1.4449, + "step": 4272 + }, + { + "epoch": 0.45, + "learning_rate": 1.3481466063091988e-05, + "loss": 1.3587, + "step": 4273 + }, + { + "epoch": 0.45, + "learning_rate": 1.3478034564744362e-05, + "loss": 1.3844, + "step": 4274 + }, + { + "epoch": 0.45, + "learning_rate": 1.3474602600429468e-05, + "loss": 1.4471, + "step": 4275 + }, + { + "epoch": 0.45, + "learning_rate": 1.3471170170607105e-05, + "loss": 1.4686, + "step": 4276 + }, + { + "epoch": 0.45, + "learning_rate": 1.3467737275737127e-05, + "loss": 1.312, + "step": 4277 + }, + { + "epoch": 0.45, + "learning_rate": 1.3464303916279453e-05, + "loss": 1.407, + "step": 4278 + }, + { + "epoch": 0.45, + "learning_rate": 1.346087009269407e-05, + "loss": 1.364, + "step": 4279 + }, + { + "epoch": 0.45, + "learning_rate": 1.3457435805441016e-05, + "loss": 1.4103, + "step": 4280 + }, + { + "epoch": 0.45, + "learning_rate": 1.3454001054980403e-05, + "loss": 1.4243, + "step": 4281 + }, + { + "epoch": 0.45, + "learning_rate": 1.3450565841772392e-05, + "loss": 1.3879, + "step": 4282 + }, + { + "epoch": 0.45, + "learning_rate": 1.344713016627722e-05, + "loss": 1.4688, + "step": 4283 + }, + { + "epoch": 0.45, + "learning_rate": 1.3443694028955176e-05, + "loss": 1.3983, + "step": 4284 + }, + { + "epoch": 0.45, + "learning_rate": 1.344025743026662e-05, + "loss": 1.4316, + "step": 4285 + }, + { + "epoch": 0.45, + "learning_rate": 1.3436820370671956e-05, + "loss": 1.3643, + "step": 4286 + }, + { + "epoch": 0.45, + "learning_rate": 1.3433382850631673e-05, + "loss": 1.4566, + "step": 4287 + }, + { + "epoch": 0.45, + "learning_rate": 1.3429944870606301e-05, + "loss": 1.1263, + "step": 4288 + }, + { + "epoch": 0.45, + "learning_rate": 1.3426506431056452e-05, + "loss": 1.2463, + "step": 4289 + }, + { + "epoch": 0.45, + "learning_rate": 1.342306753244278e-05, + "loss": 1.4753, + "step": 4290 + }, + { + "epoch": 0.45, + "learning_rate": 1.3419628175226012e-05, + "loss": 1.3789, + "step": 4291 + }, + { + "epoch": 0.45, + "learning_rate": 1.3416188359866932e-05, + "loss": 1.3906, + "step": 4292 + }, + { + "epoch": 0.45, + "learning_rate": 1.3412748086826389e-05, + "loss": 1.3995, + "step": 4293 + }, + { + "epoch": 0.45, + "learning_rate": 1.3409307356565288e-05, + "loss": 1.4906, + "step": 4294 + }, + { + "epoch": 0.45, + "learning_rate": 1.3405866169544602e-05, + "loss": 1.3951, + "step": 4295 + }, + { + "epoch": 0.45, + "learning_rate": 1.3402424526225359e-05, + "loss": 1.3753, + "step": 4296 + }, + { + "epoch": 0.45, + "learning_rate": 1.3398982427068654e-05, + "loss": 1.3686, + "step": 4297 + }, + { + "epoch": 0.45, + "learning_rate": 1.3395539872535636e-05, + "loss": 1.3612, + "step": 4298 + }, + { + "epoch": 0.45, + "learning_rate": 1.3392096863087522e-05, + "loss": 1.4043, + "step": 4299 + }, + { + "epoch": 0.45, + "learning_rate": 1.3388653399185585e-05, + "loss": 1.4068, + "step": 4300 + }, + { + "epoch": 0.45, + "learning_rate": 1.338520948129116e-05, + "loss": 1.4066, + "step": 4301 + }, + { + "epoch": 0.45, + "learning_rate": 1.3381765109865646e-05, + "loss": 1.4944, + "step": 4302 + }, + { + "epoch": 0.45, + "learning_rate": 1.3378320285370496e-05, + "loss": 1.3575, + "step": 4303 + }, + { + "epoch": 0.45, + "learning_rate": 1.3374875008267236e-05, + "loss": 1.3807, + "step": 4304 + }, + { + "epoch": 0.45, + "learning_rate": 1.3371429279017437e-05, + "loss": 1.4389, + "step": 4305 + }, + { + "epoch": 0.45, + "learning_rate": 1.3367983098082739e-05, + "loss": 1.4858, + "step": 4306 + }, + { + "epoch": 0.45, + "learning_rate": 1.3364536465924844e-05, + "loss": 1.3282, + "step": 4307 + }, + { + "epoch": 0.45, + "learning_rate": 1.3361089383005515e-05, + "loss": 1.4306, + "step": 4308 + }, + { + "epoch": 0.45, + "learning_rate": 1.3357641849786566e-05, + "loss": 1.3892, + "step": 4309 + }, + { + "epoch": 0.45, + "learning_rate": 1.3354193866729883e-05, + "loss": 1.3621, + "step": 4310 + }, + { + "epoch": 0.45, + "learning_rate": 1.3350745434297401e-05, + "loss": 1.3476, + "step": 4311 + }, + { + "epoch": 0.45, + "learning_rate": 1.334729655295113e-05, + "loss": 1.4477, + "step": 4312 + }, + { + "epoch": 0.45, + "learning_rate": 1.3343847223153123e-05, + "loss": 1.3585, + "step": 4313 + }, + { + "epoch": 0.45, + "learning_rate": 1.334039744536551e-05, + "loss": 1.3616, + "step": 4314 + }, + { + "epoch": 0.45, + "learning_rate": 1.3336947220050462e-05, + "loss": 1.3579, + "step": 4315 + }, + { + "epoch": 0.45, + "learning_rate": 1.3333496547670232e-05, + "loss": 1.3557, + "step": 4316 + }, + { + "epoch": 0.45, + "learning_rate": 1.3330045428687113e-05, + "loss": 1.4443, + "step": 4317 + }, + { + "epoch": 0.45, + "learning_rate": 1.332659386356347e-05, + "loss": 1.3621, + "step": 4318 + }, + { + "epoch": 0.45, + "learning_rate": 1.3323141852761726e-05, + "loss": 1.3295, + "step": 4319 + }, + { + "epoch": 0.45, + "learning_rate": 1.3319689396744358e-05, + "loss": 1.4187, + "step": 4320 + }, + { + "epoch": 0.45, + "learning_rate": 1.3316236495973905e-05, + "loss": 1.335, + "step": 4321 + }, + { + "epoch": 0.45, + "learning_rate": 1.331278315091297e-05, + "loss": 1.4382, + "step": 4322 + }, + { + "epoch": 0.45, + "learning_rate": 1.3309329362024212e-05, + "loss": 1.4244, + "step": 4323 + }, + { + "epoch": 0.45, + "learning_rate": 1.3305875129770351e-05, + "loss": 1.488, + "step": 4324 + }, + { + "epoch": 0.45, + "learning_rate": 1.3302420454614165e-05, + "loss": 1.3369, + "step": 4325 + }, + { + "epoch": 0.45, + "learning_rate": 1.3298965337018487e-05, + "loss": 1.3648, + "step": 4326 + }, + { + "epoch": 0.45, + "learning_rate": 1.3295509777446226e-05, + "loss": 1.3924, + "step": 4327 + }, + { + "epoch": 0.45, + "learning_rate": 1.3292053776360324e-05, + "loss": 1.3789, + "step": 4328 + }, + { + "epoch": 0.45, + "learning_rate": 1.3288597334223802e-05, + "loss": 1.3902, + "step": 4329 + }, + { + "epoch": 0.45, + "learning_rate": 1.3285140451499735e-05, + "loss": 1.4057, + "step": 4330 + }, + { + "epoch": 0.45, + "learning_rate": 1.328168312865126e-05, + "loss": 1.4536, + "step": 4331 + }, + { + "epoch": 0.45, + "learning_rate": 1.3278225366141565e-05, + "loss": 1.3075, + "step": 4332 + }, + { + "epoch": 0.45, + "learning_rate": 1.3274767164433901e-05, + "loss": 1.4579, + "step": 4333 + }, + { + "epoch": 0.45, + "learning_rate": 1.3271308523991579e-05, + "loss": 1.3906, + "step": 4334 + }, + { + "epoch": 0.45, + "learning_rate": 1.326784944527797e-05, + "loss": 1.3992, + "step": 4335 + }, + { + "epoch": 0.45, + "learning_rate": 1.3264389928756498e-05, + "loss": 1.4001, + "step": 4336 + }, + { + "epoch": 0.45, + "learning_rate": 1.3260929974890653e-05, + "loss": 1.2948, + "step": 4337 + }, + { + "epoch": 0.45, + "learning_rate": 1.3257469584143976e-05, + "loss": 1.4041, + "step": 4338 + }, + { + "epoch": 0.46, + "learning_rate": 1.3254008756980076e-05, + "loss": 1.5035, + "step": 4339 + }, + { + "epoch": 0.46, + "learning_rate": 1.3250547493862609e-05, + "loss": 1.4867, + "step": 4340 + }, + { + "epoch": 0.46, + "learning_rate": 1.3247085795255302e-05, + "loss": 1.3612, + "step": 4341 + }, + { + "epoch": 0.46, + "learning_rate": 1.3243623661621925e-05, + "loss": 1.4193, + "step": 4342 + }, + { + "epoch": 0.46, + "learning_rate": 1.3240161093426322e-05, + "loss": 1.3596, + "step": 4343 + }, + { + "epoch": 0.46, + "learning_rate": 1.3236698091132383e-05, + "loss": 1.4448, + "step": 4344 + }, + { + "epoch": 0.46, + "learning_rate": 1.3233234655204066e-05, + "loss": 1.3924, + "step": 4345 + }, + { + "epoch": 0.46, + "learning_rate": 1.322977078610538e-05, + "loss": 1.3552, + "step": 4346 + }, + { + "epoch": 0.46, + "learning_rate": 1.3226306484300395e-05, + "loss": 1.3949, + "step": 4347 + }, + { + "epoch": 0.46, + "learning_rate": 1.322284175025324e-05, + "loss": 1.399, + "step": 4348 + }, + { + "epoch": 0.46, + "learning_rate": 1.3219376584428094e-05, + "loss": 1.4755, + "step": 4349 + }, + { + "epoch": 0.46, + "learning_rate": 1.3215910987289212e-05, + "loss": 1.3877, + "step": 4350 + }, + { + "epoch": 0.46, + "learning_rate": 1.3212444959300882e-05, + "loss": 1.3916, + "step": 4351 + }, + { + "epoch": 0.46, + "learning_rate": 1.3208978500927472e-05, + "loss": 1.3462, + "step": 4352 + }, + { + "epoch": 0.46, + "learning_rate": 1.3205511612633392e-05, + "loss": 1.3834, + "step": 4353 + }, + { + "epoch": 0.46, + "learning_rate": 1.3202044294883123e-05, + "loss": 1.3843, + "step": 4354 + }, + { + "epoch": 0.46, + "learning_rate": 1.3198576548141189e-05, + "loss": 1.2439, + "step": 4355 + }, + { + "epoch": 0.46, + "learning_rate": 1.3195108372872181e-05, + "loss": 1.4106, + "step": 4356 + }, + { + "epoch": 0.46, + "learning_rate": 1.3191639769540746e-05, + "loss": 1.4417, + "step": 4357 + }, + { + "epoch": 0.46, + "learning_rate": 1.3188170738611596e-05, + "loss": 1.4393, + "step": 4358 + }, + { + "epoch": 0.46, + "learning_rate": 1.3184701280549476e-05, + "loss": 1.4616, + "step": 4359 + }, + { + "epoch": 0.46, + "learning_rate": 1.3181231395819218e-05, + "loss": 1.3215, + "step": 4360 + }, + { + "epoch": 0.46, + "learning_rate": 1.3177761084885689e-05, + "loss": 1.368, + "step": 4361 + }, + { + "epoch": 0.46, + "learning_rate": 1.317429034821383e-05, + "loss": 1.3247, + "step": 4362 + }, + { + "epoch": 0.46, + "learning_rate": 1.3170819186268618e-05, + "loss": 1.4512, + "step": 4363 + }, + { + "epoch": 0.46, + "learning_rate": 1.3167347599515111e-05, + "loss": 1.3129, + "step": 4364 + }, + { + "epoch": 0.46, + "learning_rate": 1.3163875588418404e-05, + "loss": 1.3934, + "step": 4365 + }, + { + "epoch": 0.46, + "learning_rate": 1.3160403153443666e-05, + "loss": 1.4518, + "step": 4366 + }, + { + "epoch": 0.46, + "learning_rate": 1.3156930295056105e-05, + "loss": 1.3959, + "step": 4367 + }, + { + "epoch": 0.46, + "learning_rate": 1.3153457013721e-05, + "loss": 1.3475, + "step": 4368 + }, + { + "epoch": 0.46, + "learning_rate": 1.3149983309903687e-05, + "loss": 1.4102, + "step": 4369 + }, + { + "epoch": 0.46, + "learning_rate": 1.3146509184069538e-05, + "loss": 1.3674, + "step": 4370 + }, + { + "epoch": 0.46, + "learning_rate": 1.314303463668401e-05, + "loss": 1.3739, + "step": 4371 + }, + { + "epoch": 0.46, + "learning_rate": 1.3139559668212596e-05, + "loss": 1.4249, + "step": 4372 + }, + { + "epoch": 0.46, + "learning_rate": 1.3136084279120857e-05, + "loss": 1.4473, + "step": 4373 + }, + { + "epoch": 0.46, + "learning_rate": 1.3132608469874404e-05, + "loss": 1.4443, + "step": 4374 + }, + { + "epoch": 0.46, + "learning_rate": 1.3129132240938905e-05, + "loss": 1.3534, + "step": 4375 + }, + { + "epoch": 0.46, + "learning_rate": 1.3125655592780083e-05, + "loss": 1.5663, + "step": 4376 + }, + { + "epoch": 0.46, + "learning_rate": 1.3122178525863727e-05, + "loss": 1.3465, + "step": 4377 + }, + { + "epoch": 0.46, + "learning_rate": 1.3118701040655669e-05, + "loss": 1.35, + "step": 4378 + }, + { + "epoch": 0.46, + "eval_loss": 1.447788953781128, + "eval_runtime": 77.4473, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4378 + }, + { + "epoch": 0.46, + "learning_rate": 1.3115223137621804e-05, + "loss": 1.343, + "step": 4379 + }, + { + "epoch": 0.46, + "learning_rate": 1.3111744817228078e-05, + "loss": 1.4227, + "step": 4380 + }, + { + "epoch": 0.46, + "learning_rate": 1.3108266079940508e-05, + "loss": 1.3982, + "step": 4381 + }, + { + "epoch": 0.46, + "learning_rate": 1.3104786926225141e-05, + "loss": 1.4211, + "step": 4382 + }, + { + "epoch": 0.46, + "learning_rate": 1.3101307356548103e-05, + "loss": 1.382, + "step": 4383 + }, + { + "epoch": 0.46, + "learning_rate": 1.3097827371375562e-05, + "loss": 1.4637, + "step": 4384 + }, + { + "epoch": 0.46, + "learning_rate": 1.3094346971173754e-05, + "loss": 1.4572, + "step": 4385 + }, + { + "epoch": 0.46, + "learning_rate": 1.3090866156408956e-05, + "loss": 1.5113, + "step": 4386 + }, + { + "epoch": 0.46, + "learning_rate": 1.3087384927547512e-05, + "loss": 1.2197, + "step": 4387 + }, + { + "epoch": 0.46, + "learning_rate": 1.3083903285055813e-05, + "loss": 1.3861, + "step": 4388 + }, + { + "epoch": 0.46, + "learning_rate": 1.3080421229400315e-05, + "loss": 1.4754, + "step": 4389 + }, + { + "epoch": 0.46, + "learning_rate": 1.307693876104752e-05, + "loss": 1.3588, + "step": 4390 + }, + { + "epoch": 0.46, + "learning_rate": 1.3073455880463987e-05, + "loss": 1.3995, + "step": 4391 + }, + { + "epoch": 0.46, + "learning_rate": 1.3069972588116341e-05, + "loss": 1.354, + "step": 4392 + }, + { + "epoch": 0.46, + "learning_rate": 1.3066488884471244e-05, + "loss": 1.3378, + "step": 4393 + }, + { + "epoch": 0.46, + "learning_rate": 1.306300476999543e-05, + "loss": 1.5951, + "step": 4394 + }, + { + "epoch": 0.46, + "learning_rate": 1.305952024515568e-05, + "loss": 1.3661, + "step": 4395 + }, + { + "epoch": 0.46, + "learning_rate": 1.3056035310418826e-05, + "loss": 1.4066, + "step": 4396 + }, + { + "epoch": 0.46, + "learning_rate": 1.3052549966251764e-05, + "loss": 1.3687, + "step": 4397 + }, + { + "epoch": 0.46, + "learning_rate": 1.3049064213121438e-05, + "loss": 1.4573, + "step": 4398 + }, + { + "epoch": 0.46, + "learning_rate": 1.3045578051494852e-05, + "loss": 1.3519, + "step": 4399 + }, + { + "epoch": 0.46, + "learning_rate": 1.3042091481839063e-05, + "loss": 1.2803, + "step": 4400 + }, + { + "epoch": 0.46, + "learning_rate": 1.3038604504621173e-05, + "loss": 1.4014, + "step": 4401 + }, + { + "epoch": 0.46, + "learning_rate": 1.3035117120308358e-05, + "loss": 1.4534, + "step": 4402 + }, + { + "epoch": 0.46, + "learning_rate": 1.3031629329367832e-05, + "loss": 1.4747, + "step": 4403 + }, + { + "epoch": 0.46, + "learning_rate": 1.3028141132266877e-05, + "loss": 1.374, + "step": 4404 + }, + { + "epoch": 0.46, + "learning_rate": 1.3024652529472807e-05, + "loss": 1.4328, + "step": 4405 + }, + { + "epoch": 0.46, + "learning_rate": 1.302116352145302e-05, + "loss": 1.468, + "step": 4406 + }, + { + "epoch": 0.46, + "learning_rate": 1.3017674108674942e-05, + "loss": 1.2947, + "step": 4407 + }, + { + "epoch": 0.46, + "learning_rate": 1.3014184291606077e-05, + "loss": 1.3682, + "step": 4408 + }, + { + "epoch": 0.46, + "learning_rate": 1.3010694070713959e-05, + "loss": 1.3651, + "step": 4409 + }, + { + "epoch": 0.46, + "learning_rate": 1.3007203446466194e-05, + "loss": 1.418, + "step": 4410 + }, + { + "epoch": 0.46, + "learning_rate": 1.3003712419330433e-05, + "loss": 1.416, + "step": 4411 + }, + { + "epoch": 0.46, + "learning_rate": 1.300022098977439e-05, + "loss": 1.2979, + "step": 4412 + }, + { + "epoch": 0.46, + "learning_rate": 1.2996729158265819e-05, + "loss": 1.3868, + "step": 4413 + }, + { + "epoch": 0.46, + "learning_rate": 1.2993236925272542e-05, + "loss": 1.3102, + "step": 4414 + }, + { + "epoch": 0.46, + "learning_rate": 1.2989744291262422e-05, + "loss": 1.3506, + "step": 4415 + }, + { + "epoch": 0.46, + "learning_rate": 1.2986251256703388e-05, + "loss": 1.4018, + "step": 4416 + }, + { + "epoch": 0.46, + "learning_rate": 1.2982757822063417e-05, + "loss": 1.4081, + "step": 4417 + }, + { + "epoch": 0.46, + "learning_rate": 1.2979263987810533e-05, + "loss": 1.3592, + "step": 4418 + }, + { + "epoch": 0.46, + "learning_rate": 1.297576975441283e-05, + "loss": 1.4287, + "step": 4419 + }, + { + "epoch": 0.46, + "learning_rate": 1.2972275122338433e-05, + "loss": 1.4099, + "step": 4420 + }, + { + "epoch": 0.46, + "learning_rate": 1.2968780092055546e-05, + "loss": 1.4005, + "step": 4421 + }, + { + "epoch": 0.46, + "learning_rate": 1.2965284664032401e-05, + "loss": 1.365, + "step": 4422 + }, + { + "epoch": 0.46, + "learning_rate": 1.2961788838737309e-05, + "loss": 1.3588, + "step": 4423 + }, + { + "epoch": 0.46, + "learning_rate": 1.2958292616638606e-05, + "loss": 1.3702, + "step": 4424 + }, + { + "epoch": 0.46, + "learning_rate": 1.2954795998204708e-05, + "loss": 1.3487, + "step": 4425 + }, + { + "epoch": 0.46, + "learning_rate": 1.2951298983904063e-05, + "loss": 1.4395, + "step": 4426 + }, + { + "epoch": 0.46, + "learning_rate": 1.2947801574205193e-05, + "loss": 1.3523, + "step": 4427 + }, + { + "epoch": 0.46, + "learning_rate": 1.2944303769576645e-05, + "loss": 1.3125, + "step": 4428 + }, + { + "epoch": 0.46, + "learning_rate": 1.2940805570487048e-05, + "loss": 1.5476, + "step": 4429 + }, + { + "epoch": 0.46, + "learning_rate": 1.2937306977405062e-05, + "loss": 1.4076, + "step": 4430 + }, + { + "epoch": 0.46, + "learning_rate": 1.2933807990799418e-05, + "loss": 1.3007, + "step": 4431 + }, + { + "epoch": 0.46, + "learning_rate": 1.293030861113888e-05, + "loss": 1.3566, + "step": 4432 + }, + { + "epoch": 0.46, + "learning_rate": 1.2926808838892285e-05, + "loss": 1.3907, + "step": 4433 + }, + { + "epoch": 0.46, + "learning_rate": 1.2923308674528501e-05, + "loss": 1.379, + "step": 4434 + }, + { + "epoch": 0.47, + "learning_rate": 1.2919808118516475e-05, + "loss": 1.4319, + "step": 4435 + }, + { + "epoch": 0.47, + "learning_rate": 1.2916307171325176e-05, + "loss": 1.3392, + "step": 4436 + }, + { + "epoch": 0.47, + "learning_rate": 1.291280583342365e-05, + "loss": 1.401, + "step": 4437 + }, + { + "epoch": 0.47, + "learning_rate": 1.2909304105280984e-05, + "loss": 1.3939, + "step": 4438 + }, + { + "epoch": 0.47, + "learning_rate": 1.2905801987366322e-05, + "loss": 1.4676, + "step": 4439 + }, + { + "epoch": 0.47, + "learning_rate": 1.2902299480148855e-05, + "loss": 1.3957, + "step": 4440 + }, + { + "epoch": 0.47, + "learning_rate": 1.2898796584097828e-05, + "loss": 1.3587, + "step": 4441 + }, + { + "epoch": 0.47, + "learning_rate": 1.2895293299682545e-05, + "loss": 1.5809, + "step": 4442 + }, + { + "epoch": 0.47, + "learning_rate": 1.289178962737235e-05, + "loss": 1.3436, + "step": 4443 + }, + { + "epoch": 0.47, + "learning_rate": 1.2888285567636647e-05, + "loss": 1.4535, + "step": 4444 + }, + { + "epoch": 0.47, + "learning_rate": 1.2884781120944889e-05, + "loss": 1.3377, + "step": 4445 + }, + { + "epoch": 0.47, + "learning_rate": 1.2881276287766587e-05, + "loss": 0.8221, + "step": 4446 + }, + { + "epoch": 0.47, + "learning_rate": 1.2877771068571288e-05, + "loss": 0.7259, + "step": 4447 + }, + { + "epoch": 0.47, + "learning_rate": 1.2874265463828612e-05, + "loss": 0.8279, + "step": 4448 + }, + { + "epoch": 0.47, + "learning_rate": 1.2870759474008213e-05, + "loss": 1.3523, + "step": 4449 + }, + { + "epoch": 0.47, + "learning_rate": 1.2867253099579808e-05, + "loss": 1.3658, + "step": 4450 + }, + { + "epoch": 0.47, + "learning_rate": 1.2863746341013158e-05, + "loss": 1.4112, + "step": 4451 + }, + { + "epoch": 0.47, + "learning_rate": 1.2860239198778085e-05, + "loss": 1.389, + "step": 4452 + }, + { + "epoch": 0.47, + "learning_rate": 1.2856731673344442e-05, + "loss": 1.4066, + "step": 4453 + }, + { + "epoch": 0.47, + "learning_rate": 1.2853223765182165e-05, + "loss": 1.3267, + "step": 4454 + }, + { + "epoch": 0.47, + "learning_rate": 1.2849715474761209e-05, + "loss": 1.3381, + "step": 4455 + }, + { + "epoch": 0.47, + "learning_rate": 1.2846206802551602e-05, + "loss": 1.2882, + "step": 4456 + }, + { + "epoch": 0.47, + "learning_rate": 1.2842697749023414e-05, + "loss": 1.3199, + "step": 4457 + }, + { + "epoch": 0.47, + "learning_rate": 1.2839188314646771e-05, + "loss": 1.3896, + "step": 4458 + }, + { + "epoch": 0.47, + "learning_rate": 1.2835678499891842e-05, + "loss": 1.3186, + "step": 4459 + }, + { + "epoch": 0.47, + "learning_rate": 1.283216830522885e-05, + "loss": 1.3466, + "step": 4460 + }, + { + "epoch": 0.47, + "learning_rate": 1.2828657731128083e-05, + "loss": 1.4678, + "step": 4461 + }, + { + "epoch": 0.47, + "learning_rate": 1.2825146778059857e-05, + "loss": 1.4408, + "step": 4462 + }, + { + "epoch": 0.47, + "learning_rate": 1.2821635446494553e-05, + "loss": 1.3672, + "step": 4463 + }, + { + "epoch": 0.47, + "learning_rate": 1.2818123736902597e-05, + "loss": 1.3836, + "step": 4464 + }, + { + "epoch": 0.47, + "learning_rate": 1.2814611649754472e-05, + "loss": 1.3493, + "step": 4465 + }, + { + "epoch": 0.47, + "learning_rate": 1.2811099185520704e-05, + "loss": 1.3584, + "step": 4466 + }, + { + "epoch": 0.47, + "learning_rate": 1.2807586344671875e-05, + "loss": 1.3551, + "step": 4467 + }, + { + "epoch": 0.47, + "learning_rate": 1.2804073127678612e-05, + "loss": 1.3254, + "step": 4468 + }, + { + "epoch": 0.47, + "learning_rate": 1.28005595350116e-05, + "loss": 1.3405, + "step": 4469 + }, + { + "epoch": 0.47, + "learning_rate": 1.2797045567141568e-05, + "loss": 1.3432, + "step": 4470 + }, + { + "epoch": 0.47, + "learning_rate": 1.2793531224539297e-05, + "loss": 1.4347, + "step": 4471 + }, + { + "epoch": 0.47, + "learning_rate": 1.279001650767562e-05, + "loss": 1.3304, + "step": 4472 + }, + { + "epoch": 0.47, + "learning_rate": 1.278650141702142e-05, + "loss": 1.3244, + "step": 4473 + }, + { + "epoch": 0.47, + "learning_rate": 1.2782985953047625e-05, + "loss": 1.3756, + "step": 4474 + }, + { + "epoch": 0.47, + "learning_rate": 1.2779470116225219e-05, + "loss": 1.5468, + "step": 4475 + }, + { + "epoch": 0.47, + "learning_rate": 1.2775953907025232e-05, + "loss": 1.4316, + "step": 4476 + }, + { + "epoch": 0.47, + "learning_rate": 1.2772437325918752e-05, + "loss": 1.3724, + "step": 4477 + }, + { + "epoch": 0.47, + "learning_rate": 1.27689203733769e-05, + "loss": 1.4458, + "step": 4478 + }, + { + "epoch": 0.47, + "learning_rate": 1.2765403049870865e-05, + "loss": 1.3622, + "step": 4479 + }, + { + "epoch": 0.47, + "learning_rate": 1.2761885355871875e-05, + "loss": 1.3875, + "step": 4480 + }, + { + "epoch": 0.47, + "learning_rate": 1.2758367291851217e-05, + "loss": 1.3577, + "step": 4481 + }, + { + "epoch": 0.47, + "learning_rate": 1.2754848858280211e-05, + "loss": 1.4256, + "step": 4482 + }, + { + "epoch": 0.47, + "learning_rate": 1.2751330055630242e-05, + "loss": 1.3771, + "step": 4483 + }, + { + "epoch": 0.47, + "learning_rate": 1.274781088437274e-05, + "loss": 1.357, + "step": 4484 + }, + { + "epoch": 0.47, + "learning_rate": 1.274429134497918e-05, + "loss": 1.3634, + "step": 4485 + }, + { + "epoch": 0.47, + "learning_rate": 1.2740771437921096e-05, + "loss": 1.3661, + "step": 4486 + }, + { + "epoch": 0.47, + "learning_rate": 1.2737251163670057e-05, + "loss": 1.3819, + "step": 4487 + }, + { + "epoch": 0.47, + "learning_rate": 1.2733730522697696e-05, + "loss": 1.4491, + "step": 4488 + }, + { + "epoch": 0.47, + "learning_rate": 1.2730209515475687e-05, + "loss": 1.3857, + "step": 4489 + }, + { + "epoch": 0.47, + "learning_rate": 1.2726688142475751e-05, + "loss": 1.3837, + "step": 4490 + }, + { + "epoch": 0.47, + "learning_rate": 1.2723166404169663e-05, + "loss": 1.3755, + "step": 4491 + }, + { + "epoch": 0.47, + "learning_rate": 1.271964430102925e-05, + "loss": 1.3767, + "step": 4492 + }, + { + "epoch": 0.47, + "learning_rate": 1.2716121833526376e-05, + "loss": 1.4416, + "step": 4493 + }, + { + "epoch": 0.47, + "learning_rate": 1.2712599002132966e-05, + "loss": 1.5573, + "step": 4494 + }, + { + "epoch": 0.47, + "learning_rate": 1.2709075807320988e-05, + "loss": 1.365, + "step": 4495 + }, + { + "epoch": 0.47, + "learning_rate": 1.270555224956246e-05, + "loss": 1.3862, + "step": 4496 + }, + { + "epoch": 0.47, + "learning_rate": 1.2702028329329445e-05, + "loss": 1.3003, + "step": 4497 + }, + { + "epoch": 0.47, + "learning_rate": 1.2698504047094064e-05, + "loss": 1.3806, + "step": 4498 + }, + { + "epoch": 0.47, + "learning_rate": 1.269497940332847e-05, + "loss": 1.5425, + "step": 4499 + }, + { + "epoch": 0.47, + "learning_rate": 1.269145439850489e-05, + "loss": 1.3541, + "step": 4500 + }, + { + "epoch": 0.47, + "learning_rate": 1.268792903309557e-05, + "loss": 1.4337, + "step": 4501 + }, + { + "epoch": 0.47, + "learning_rate": 1.2684403307572825e-05, + "loss": 1.4004, + "step": 4502 + }, + { + "epoch": 0.47, + "learning_rate": 1.268087722240901e-05, + "loss": 1.9453, + "step": 4503 + }, + { + "epoch": 0.47, + "learning_rate": 1.2677350778076532e-05, + "loss": 1.3907, + "step": 4504 + }, + { + "epoch": 0.47, + "learning_rate": 1.2673823975047839e-05, + "loss": 1.4993, + "step": 4505 + }, + { + "epoch": 0.47, + "learning_rate": 1.2670296813795432e-05, + "loss": 1.4386, + "step": 4506 + }, + { + "epoch": 0.47, + "learning_rate": 1.266676929479187e-05, + "loss": 1.4944, + "step": 4507 + }, + { + "epoch": 0.47, + "learning_rate": 1.266324141850974e-05, + "loss": 1.4311, + "step": 4508 + }, + { + "epoch": 0.47, + "learning_rate": 1.265971318542169e-05, + "loss": 1.3607, + "step": 4509 + }, + { + "epoch": 0.47, + "learning_rate": 1.2656184596000412e-05, + "loss": 1.4007, + "step": 4510 + }, + { + "epoch": 0.47, + "learning_rate": 1.2652655650718645e-05, + "loss": 1.4561, + "step": 4511 + }, + { + "epoch": 0.47, + "learning_rate": 1.2649126350049181e-05, + "loss": 1.4321, + "step": 4512 + }, + { + "epoch": 0.47, + "learning_rate": 1.2645596694464851e-05, + "loss": 1.2856, + "step": 4513 + }, + { + "epoch": 0.47, + "learning_rate": 1.2642066684438543e-05, + "loss": 1.3979, + "step": 4514 + }, + { + "epoch": 0.47, + "learning_rate": 1.2638536320443184e-05, + "loss": 1.4977, + "step": 4515 + }, + { + "epoch": 0.47, + "learning_rate": 1.2635005602951752e-05, + "loss": 1.377, + "step": 4516 + }, + { + "epoch": 0.47, + "learning_rate": 1.2631474532437275e-05, + "loss": 1.4266, + "step": 4517 + }, + { + "epoch": 0.47, + "learning_rate": 1.2627943109372822e-05, + "loss": 1.409, + "step": 4518 + }, + { + "epoch": 0.47, + "learning_rate": 1.2624411334231519e-05, + "loss": 1.3374, + "step": 4519 + }, + { + "epoch": 0.47, + "learning_rate": 1.2620879207486525e-05, + "loss": 1.3765, + "step": 4520 + }, + { + "epoch": 0.47, + "learning_rate": 1.2617346729611061e-05, + "loss": 1.3805, + "step": 4521 + }, + { + "epoch": 0.47, + "learning_rate": 1.2613813901078384e-05, + "loss": 1.3326, + "step": 4522 + }, + { + "epoch": 0.47, + "learning_rate": 1.2610280722361807e-05, + "loss": 1.3909, + "step": 4523 + }, + { + "epoch": 0.47, + "learning_rate": 1.260674719393468e-05, + "loss": 1.3815, + "step": 4524 + }, + { + "epoch": 0.47, + "learning_rate": 1.2603213316270409e-05, + "loss": 1.5589, + "step": 4525 + }, + { + "epoch": 0.47, + "learning_rate": 1.2599679089842437e-05, + "loss": 1.4416, + "step": 4526 + }, + { + "epoch": 0.47, + "learning_rate": 1.259614451512427e-05, + "loss": 1.3529, + "step": 4527 + }, + { + "epoch": 0.47, + "learning_rate": 1.2592609592589437e-05, + "loss": 1.3135, + "step": 4528 + }, + { + "epoch": 0.47, + "learning_rate": 1.2589074322711535e-05, + "loss": 1.4177, + "step": 4529 + }, + { + "epoch": 0.48, + "learning_rate": 1.25855387059642e-05, + "loss": 1.353, + "step": 4530 + }, + { + "epoch": 0.48, + "learning_rate": 1.2582002742821111e-05, + "loss": 1.431, + "step": 4531 + }, + { + "epoch": 0.48, + "learning_rate": 1.2578466433755998e-05, + "loss": 1.3803, + "step": 4532 + }, + { + "epoch": 0.48, + "learning_rate": 1.257492977924263e-05, + "loss": 1.3774, + "step": 4533 + }, + { + "epoch": 0.48, + "learning_rate": 1.2571392779754836e-05, + "loss": 1.4339, + "step": 4534 + }, + { + "epoch": 0.48, + "learning_rate": 1.256785543576648e-05, + "loss": 1.4097, + "step": 4535 + }, + { + "epoch": 0.48, + "learning_rate": 1.2564317747751473e-05, + "loss": 1.4223, + "step": 4536 + }, + { + "epoch": 0.48, + "learning_rate": 1.2560779716183775e-05, + "loss": 1.5148, + "step": 4537 + }, + { + "epoch": 0.48, + "learning_rate": 1.2557241341537394e-05, + "loss": 1.3547, + "step": 4538 + }, + { + "epoch": 0.48, + "learning_rate": 1.255370262428638e-05, + "loss": 1.393, + "step": 4539 + }, + { + "epoch": 0.48, + "learning_rate": 1.2550163564904829e-05, + "loss": 1.3312, + "step": 4540 + }, + { + "epoch": 0.48, + "learning_rate": 1.2546624163866882e-05, + "loss": 1.4193, + "step": 4541 + }, + { + "epoch": 0.48, + "learning_rate": 1.2543084421646735e-05, + "loss": 1.4161, + "step": 4542 + }, + { + "epoch": 0.48, + "learning_rate": 1.2539544338718614e-05, + "loss": 1.4224, + "step": 4543 + }, + { + "epoch": 0.48, + "learning_rate": 1.2536003915556805e-05, + "loss": 1.3484, + "step": 4544 + }, + { + "epoch": 0.48, + "learning_rate": 1.253246315263563e-05, + "loss": 1.4492, + "step": 4545 + }, + { + "epoch": 0.48, + "learning_rate": 1.2528922050429467e-05, + "loss": 1.3549, + "step": 4546 + }, + { + "epoch": 0.48, + "learning_rate": 1.252538060941272e-05, + "loss": 1.45, + "step": 4547 + }, + { + "epoch": 0.48, + "learning_rate": 1.2521838830059865e-05, + "loss": 1.3499, + "step": 4548 + }, + { + "epoch": 0.48, + "learning_rate": 1.2518296712845399e-05, + "loss": 1.3786, + "step": 4549 + }, + { + "epoch": 0.48, + "learning_rate": 1.2514754258243884e-05, + "loss": 1.3394, + "step": 4550 + }, + { + "epoch": 0.48, + "learning_rate": 1.2511211466729909e-05, + "loss": 1.2849, + "step": 4551 + }, + { + "epoch": 0.48, + "learning_rate": 1.250766833877812e-05, + "loss": 1.374, + "step": 4552 + }, + { + "epoch": 0.48, + "learning_rate": 1.2504124874863211e-05, + "loss": 1.3084, + "step": 4553 + }, + { + "epoch": 0.48, + "learning_rate": 1.2500581075459905e-05, + "loss": 1.3348, + "step": 4554 + }, + { + "epoch": 0.48, + "learning_rate": 1.249703694104299e-05, + "loss": 1.3797, + "step": 4555 + }, + { + "epoch": 0.48, + "learning_rate": 1.2493492472087279e-05, + "loss": 1.3371, + "step": 4556 + }, + { + "epoch": 0.48, + "learning_rate": 1.248994766906765e-05, + "loss": 1.3974, + "step": 4557 + }, + { + "epoch": 0.48, + "learning_rate": 1.2486402532459007e-05, + "loss": 1.388, + "step": 4558 + }, + { + "epoch": 0.48, + "learning_rate": 1.2482857062736313e-05, + "loss": 1.3619, + "step": 4559 + }, + { + "epoch": 0.48, + "learning_rate": 1.2479311260374565e-05, + "loss": 1.4123, + "step": 4560 + }, + { + "epoch": 0.48, + "learning_rate": 1.2475765125848814e-05, + "loss": 1.5485, + "step": 4561 + }, + { + "epoch": 0.48, + "learning_rate": 1.247221865963415e-05, + "loss": 1.4965, + "step": 4562 + }, + { + "epoch": 0.48, + "learning_rate": 1.2468671862205705e-05, + "loss": 1.4352, + "step": 4563 + }, + { + "epoch": 0.48, + "learning_rate": 1.246512473403866e-05, + "loss": 1.3935, + "step": 4564 + }, + { + "epoch": 0.48, + "learning_rate": 1.2461577275608243e-05, + "loss": 1.3798, + "step": 4565 + }, + { + "epoch": 0.48, + "learning_rate": 1.2458029487389718e-05, + "loss": 1.4039, + "step": 4566 + }, + { + "epoch": 0.48, + "learning_rate": 1.2454481369858397e-05, + "loss": 1.3723, + "step": 4567 + }, + { + "epoch": 0.48, + "learning_rate": 1.245093292348964e-05, + "loss": 1.3713, + "step": 4568 + }, + { + "epoch": 0.48, + "learning_rate": 1.2447384148758847e-05, + "loss": 1.4083, + "step": 4569 + }, + { + "epoch": 0.48, + "learning_rate": 1.244383504614146e-05, + "loss": 1.2811, + "step": 4570 + }, + { + "epoch": 0.48, + "learning_rate": 1.2440285616112968e-05, + "loss": 1.3509, + "step": 4571 + }, + { + "epoch": 0.48, + "learning_rate": 1.2436735859148905e-05, + "loss": 1.3481, + "step": 4572 + }, + { + "epoch": 0.48, + "learning_rate": 1.2433185775724847e-05, + "loss": 1.4168, + "step": 4573 + }, + { + "epoch": 0.48, + "learning_rate": 1.2429635366316418e-05, + "loss": 1.3671, + "step": 4574 + }, + { + "epoch": 0.48, + "learning_rate": 1.2426084631399271e-05, + "loss": 1.6514, + "step": 4575 + }, + { + "epoch": 0.48, + "learning_rate": 1.2422533571449123e-05, + "loss": 1.3564, + "step": 4576 + }, + { + "epoch": 0.48, + "learning_rate": 1.2418982186941721e-05, + "loss": 1.4586, + "step": 4577 + }, + { + "epoch": 0.48, + "eval_loss": 1.4425245523452759, + "eval_runtime": 77.3853, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 4577 + }, + { + "epoch": 0.48, + "learning_rate": 1.2415430478352858e-05, + "loss": 1.3922, + "step": 4578 + }, + { + "epoch": 0.48, + "learning_rate": 1.2411878446158374e-05, + "loss": 1.3903, + "step": 4579 + }, + { + "epoch": 0.48, + "learning_rate": 1.240832609083415e-05, + "loss": 1.3537, + "step": 4580 + }, + { + "epoch": 0.48, + "learning_rate": 1.2404773412856113e-05, + "loss": 1.356, + "step": 4581 + }, + { + "epoch": 0.48, + "learning_rate": 1.2401220412700223e-05, + "loss": 1.4483, + "step": 4582 + }, + { + "epoch": 0.48, + "learning_rate": 1.2397667090842496e-05, + "loss": 1.3926, + "step": 4583 + }, + { + "epoch": 0.48, + "learning_rate": 1.2394113447758986e-05, + "loss": 1.4816, + "step": 4584 + }, + { + "epoch": 0.48, + "learning_rate": 1.2390559483925788e-05, + "loss": 1.3742, + "step": 4585 + }, + { + "epoch": 0.48, + "learning_rate": 1.2387005199819044e-05, + "loss": 1.4476, + "step": 4586 + }, + { + "epoch": 0.48, + "learning_rate": 1.2383450595914932e-05, + "loss": 1.4029, + "step": 4587 + }, + { + "epoch": 0.48, + "learning_rate": 1.2379895672689683e-05, + "loss": 1.4797, + "step": 4588 + }, + { + "epoch": 0.48, + "learning_rate": 1.2376340430619565e-05, + "loss": 1.3366, + "step": 4589 + }, + { + "epoch": 0.48, + "learning_rate": 1.2372784870180885e-05, + "loss": 1.4226, + "step": 4590 + }, + { + "epoch": 0.48, + "learning_rate": 1.2369228991849997e-05, + "loss": 1.3668, + "step": 4591 + }, + { + "epoch": 0.48, + "learning_rate": 1.2365672796103305e-05, + "loss": 1.4932, + "step": 4592 + }, + { + "epoch": 0.48, + "learning_rate": 1.236211628341724e-05, + "loss": 1.4088, + "step": 4593 + }, + { + "epoch": 0.48, + "learning_rate": 1.2358559454268284e-05, + "loss": 1.3616, + "step": 4594 + }, + { + "epoch": 0.48, + "learning_rate": 1.2355002309132961e-05, + "loss": 1.4345, + "step": 4595 + }, + { + "epoch": 0.48, + "learning_rate": 1.2351444848487844e-05, + "loss": 1.4025, + "step": 4596 + }, + { + "epoch": 0.48, + "learning_rate": 1.2347887072809533e-05, + "loss": 1.3895, + "step": 4597 + }, + { + "epoch": 0.48, + "learning_rate": 1.2344328982574678e-05, + "loss": 1.3326, + "step": 4598 + }, + { + "epoch": 0.48, + "learning_rate": 1.234077057825998e-05, + "loss": 1.4249, + "step": 4599 + }, + { + "epoch": 0.48, + "learning_rate": 1.2337211860342167e-05, + "loss": 1.3649, + "step": 4600 + }, + { + "epoch": 0.48, + "learning_rate": 1.2333652829298016e-05, + "loss": 1.3831, + "step": 4601 + }, + { + "epoch": 0.48, + "learning_rate": 1.2330093485604346e-05, + "loss": 1.3748, + "step": 4602 + }, + { + "epoch": 0.48, + "learning_rate": 1.2326533829738022e-05, + "loss": 1.386, + "step": 4603 + }, + { + "epoch": 0.48, + "learning_rate": 1.2322973862175941e-05, + "loss": 1.3923, + "step": 4604 + }, + { + "epoch": 0.48, + "learning_rate": 1.2319413583395052e-05, + "loss": 1.3638, + "step": 4605 + }, + { + "epoch": 0.48, + "learning_rate": 1.2315852993872335e-05, + "loss": 1.3476, + "step": 4606 + }, + { + "epoch": 0.48, + "learning_rate": 1.2312292094084824e-05, + "loss": 1.3581, + "step": 4607 + }, + { + "epoch": 0.48, + "learning_rate": 1.2308730884509583e-05, + "loss": 1.3554, + "step": 4608 + }, + { + "epoch": 0.48, + "learning_rate": 1.2305169365623724e-05, + "loss": 1.3676, + "step": 4609 + }, + { + "epoch": 0.48, + "learning_rate": 1.2301607537904399e-05, + "loss": 1.24, + "step": 4610 + }, + { + "epoch": 0.48, + "learning_rate": 1.2298045401828803e-05, + "loss": 1.3295, + "step": 4611 + }, + { + "epoch": 0.48, + "learning_rate": 1.2294482957874169e-05, + "loss": 1.5684, + "step": 4612 + }, + { + "epoch": 0.48, + "learning_rate": 1.2290920206517774e-05, + "loss": 1.3403, + "step": 4613 + }, + { + "epoch": 0.48, + "learning_rate": 1.2287357148236933e-05, + "loss": 1.349, + "step": 4614 + }, + { + "epoch": 0.48, + "learning_rate": 1.2283793783509008e-05, + "loss": 1.4261, + "step": 4615 + }, + { + "epoch": 0.48, + "learning_rate": 1.2280230112811395e-05, + "loss": 1.322, + "step": 4616 + }, + { + "epoch": 0.48, + "learning_rate": 1.2276666136621538e-05, + "loss": 1.3399, + "step": 4617 + }, + { + "epoch": 0.48, + "learning_rate": 1.2273101855416912e-05, + "loss": 1.3878, + "step": 4618 + }, + { + "epoch": 0.48, + "learning_rate": 1.2269537269675044e-05, + "loss": 1.4733, + "step": 4619 + }, + { + "epoch": 0.48, + "learning_rate": 1.2265972379873497e-05, + "loss": 1.419, + "step": 4620 + }, + { + "epoch": 0.48, + "learning_rate": 1.226240718648987e-05, + "loss": 1.3918, + "step": 4621 + }, + { + "epoch": 0.48, + "learning_rate": 1.2258841690001815e-05, + "loss": 1.3398, + "step": 4622 + }, + { + "epoch": 0.48, + "learning_rate": 1.225527589088701e-05, + "loss": 1.4091, + "step": 4623 + }, + { + "epoch": 0.48, + "learning_rate": 1.2251709789623185e-05, + "loss": 1.3291, + "step": 4624 + }, + { + "epoch": 0.49, + "learning_rate": 1.2248143386688101e-05, + "loss": 1.4288, + "step": 4625 + }, + { + "epoch": 0.49, + "learning_rate": 1.224457668255957e-05, + "loss": 1.2942, + "step": 4626 + }, + { + "epoch": 0.49, + "learning_rate": 1.2241009677715437e-05, + "loss": 1.4014, + "step": 4627 + }, + { + "epoch": 0.49, + "learning_rate": 1.2237442372633586e-05, + "loss": 1.3823, + "step": 4628 + }, + { + "epoch": 0.49, + "learning_rate": 1.2233874767791945e-05, + "loss": 1.3556, + "step": 4629 + }, + { + "epoch": 0.49, + "learning_rate": 1.2230306863668485e-05, + "loss": 1.411, + "step": 4630 + }, + { + "epoch": 0.49, + "learning_rate": 1.2226738660741212e-05, + "loss": 1.4347, + "step": 4631 + }, + { + "epoch": 0.49, + "learning_rate": 1.2223170159488169e-05, + "loss": 1.3095, + "step": 4632 + }, + { + "epoch": 0.49, + "learning_rate": 1.221960136038745e-05, + "loss": 1.4272, + "step": 4633 + }, + { + "epoch": 0.49, + "learning_rate": 1.221603226391718e-05, + "loss": 1.367, + "step": 4634 + }, + { + "epoch": 0.49, + "learning_rate": 1.2212462870555523e-05, + "loss": 1.3357, + "step": 4635 + }, + { + "epoch": 0.49, + "learning_rate": 1.220889318078069e-05, + "loss": 1.3634, + "step": 4636 + }, + { + "epoch": 0.49, + "learning_rate": 1.2205323195070927e-05, + "loss": 1.4143, + "step": 4637 + }, + { + "epoch": 0.49, + "learning_rate": 1.2201752913904519e-05, + "loss": 1.4865, + "step": 4638 + }, + { + "epoch": 0.49, + "learning_rate": 1.2198182337759794e-05, + "loss": 1.451, + "step": 4639 + }, + { + "epoch": 0.49, + "learning_rate": 1.2194611467115116e-05, + "loss": 1.3953, + "step": 4640 + }, + { + "epoch": 0.49, + "learning_rate": 1.2191040302448887e-05, + "loss": 1.4099, + "step": 4641 + }, + { + "epoch": 0.49, + "learning_rate": 1.2187468844239559e-05, + "loss": 1.3338, + "step": 4642 + }, + { + "epoch": 0.49, + "learning_rate": 1.2183897092965609e-05, + "loss": 1.4392, + "step": 4643 + }, + { + "epoch": 0.49, + "learning_rate": 1.2180325049105559e-05, + "loss": 1.3196, + "step": 4644 + }, + { + "epoch": 0.49, + "learning_rate": 1.2176752713137977e-05, + "loss": 1.3727, + "step": 4645 + }, + { + "epoch": 0.49, + "learning_rate": 1.2173180085541464e-05, + "loss": 1.3118, + "step": 4646 + }, + { + "epoch": 0.49, + "learning_rate": 1.2169607166794655e-05, + "loss": 1.3695, + "step": 4647 + }, + { + "epoch": 0.49, + "learning_rate": 1.2166033957376231e-05, + "loss": 1.3568, + "step": 4648 + }, + { + "epoch": 0.49, + "learning_rate": 1.216246045776491e-05, + "loss": 1.3492, + "step": 4649 + }, + { + "epoch": 0.49, + "learning_rate": 1.2158886668439455e-05, + "loss": 1.3445, + "step": 4650 + }, + { + "epoch": 0.49, + "learning_rate": 1.2155312589878654e-05, + "loss": 1.3756, + "step": 4651 + }, + { + "epoch": 0.49, + "learning_rate": 1.2151738222561344e-05, + "loss": 1.3681, + "step": 4652 + }, + { + "epoch": 0.49, + "learning_rate": 1.2148163566966403e-05, + "loss": 1.4345, + "step": 4653 + }, + { + "epoch": 0.49, + "learning_rate": 1.2144588623572738e-05, + "loss": 1.5102, + "step": 4654 + }, + { + "epoch": 0.49, + "learning_rate": 1.2141013392859297e-05, + "loss": 1.3531, + "step": 4655 + }, + { + "epoch": 0.49, + "learning_rate": 1.2137437875305075e-05, + "loss": 1.3824, + "step": 4656 + }, + { + "epoch": 0.49, + "learning_rate": 1.2133862071389099e-05, + "loss": 1.4227, + "step": 4657 + }, + { + "epoch": 0.49, + "learning_rate": 1.2130285981590433e-05, + "loss": 1.3479, + "step": 4658 + }, + { + "epoch": 0.49, + "learning_rate": 1.2126709606388181e-05, + "loss": 1.381, + "step": 4659 + }, + { + "epoch": 0.49, + "learning_rate": 1.2123132946261485e-05, + "loss": 1.3847, + "step": 4660 + }, + { + "epoch": 0.49, + "learning_rate": 1.2119556001689527e-05, + "loss": 1.3549, + "step": 4661 + }, + { + "epoch": 0.49, + "learning_rate": 1.2115978773151527e-05, + "loss": 1.3754, + "step": 4662 + }, + { + "epoch": 0.49, + "learning_rate": 1.2112401261126736e-05, + "loss": 1.3329, + "step": 4663 + }, + { + "epoch": 0.49, + "learning_rate": 1.2108823466094453e-05, + "loss": 1.4228, + "step": 4664 + }, + { + "epoch": 0.49, + "learning_rate": 1.2105245388534013e-05, + "loss": 1.4138, + "step": 4665 + }, + { + "epoch": 0.49, + "learning_rate": 1.2101667028924782e-05, + "loss": 1.3538, + "step": 4666 + }, + { + "epoch": 0.49, + "learning_rate": 1.2098088387746168e-05, + "loss": 1.4848, + "step": 4667 + }, + { + "epoch": 0.49, + "learning_rate": 1.2094509465477619e-05, + "loss": 1.5719, + "step": 4668 + }, + { + "epoch": 0.49, + "learning_rate": 1.209093026259862e-05, + "loss": 1.3863, + "step": 4669 + }, + { + "epoch": 0.49, + "learning_rate": 1.2087350779588691e-05, + "loss": 1.4425, + "step": 4670 + }, + { + "epoch": 0.49, + "learning_rate": 1.2083771016927386e-05, + "loss": 1.3655, + "step": 4671 + }, + { + "epoch": 0.49, + "learning_rate": 1.208019097509431e-05, + "loss": 1.3629, + "step": 4672 + }, + { + "epoch": 0.49, + "learning_rate": 1.2076610654569092e-05, + "loss": 1.3849, + "step": 4673 + }, + { + "epoch": 0.49, + "learning_rate": 1.20730300558314e-05, + "loss": 1.3763, + "step": 4674 + }, + { + "epoch": 0.49, + "learning_rate": 1.2069449179360945e-05, + "loss": 1.5316, + "step": 4675 + }, + { + "epoch": 0.49, + "learning_rate": 1.2065868025637476e-05, + "loss": 1.2873, + "step": 4676 + }, + { + "epoch": 0.49, + "learning_rate": 1.2062286595140773e-05, + "loss": 1.3642, + "step": 4677 + }, + { + "epoch": 0.49, + "learning_rate": 1.2058704888350652e-05, + "loss": 1.3782, + "step": 4678 + }, + { + "epoch": 0.49, + "learning_rate": 1.2055122905746972e-05, + "loss": 1.4597, + "step": 4679 + }, + { + "epoch": 0.49, + "learning_rate": 1.205154064780963e-05, + "loss": 1.3952, + "step": 4680 + }, + { + "epoch": 0.49, + "learning_rate": 1.2047958115018554e-05, + "loss": 1.4012, + "step": 4681 + }, + { + "epoch": 0.49, + "learning_rate": 1.204437530785371e-05, + "loss": 1.3432, + "step": 4682 + }, + { + "epoch": 0.49, + "learning_rate": 1.2040792226795101e-05, + "loss": 1.4111, + "step": 4683 + }, + { + "epoch": 0.49, + "learning_rate": 1.2037208872322773e-05, + "loss": 1.4357, + "step": 4684 + }, + { + "epoch": 0.49, + "learning_rate": 1.2033625244916803e-05, + "loss": 1.3908, + "step": 4685 + }, + { + "epoch": 0.49, + "learning_rate": 1.2030041345057298e-05, + "loss": 1.3804, + "step": 4686 + }, + { + "epoch": 0.49, + "learning_rate": 1.2026457173224412e-05, + "loss": 1.4523, + "step": 4687 + }, + { + "epoch": 0.49, + "learning_rate": 1.2022872729898336e-05, + "loss": 1.4266, + "step": 4688 + }, + { + "epoch": 0.49, + "learning_rate": 1.201928801555929e-05, + "loss": 1.3345, + "step": 4689 + }, + { + "epoch": 0.49, + "learning_rate": 1.2015703030687532e-05, + "loss": 1.1714, + "step": 4690 + }, + { + "epoch": 0.49, + "learning_rate": 1.2012117775763361e-05, + "loss": 1.3899, + "step": 4691 + }, + { + "epoch": 0.49, + "learning_rate": 1.2008532251267109e-05, + "loss": 1.43, + "step": 4692 + }, + { + "epoch": 0.49, + "learning_rate": 1.2004946457679144e-05, + "loss": 1.4302, + "step": 4693 + }, + { + "epoch": 0.49, + "learning_rate": 1.2001360395479865e-05, + "loss": 1.3452, + "step": 4694 + }, + { + "epoch": 0.49, + "learning_rate": 1.1997774065149716e-05, + "loss": 1.3383, + "step": 4695 + }, + { + "epoch": 0.49, + "learning_rate": 1.1994187467169176e-05, + "loss": 1.3677, + "step": 4696 + }, + { + "epoch": 0.49, + "learning_rate": 1.1990600602018755e-05, + "loss": 1.4486, + "step": 4697 + }, + { + "epoch": 0.49, + "learning_rate": 1.1987013470178998e-05, + "loss": 1.4059, + "step": 4698 + }, + { + "epoch": 0.49, + "learning_rate": 1.198342607213049e-05, + "loss": 1.3558, + "step": 4699 + }, + { + "epoch": 0.49, + "learning_rate": 1.1979838408353854e-05, + "loss": 1.3931, + "step": 4700 + }, + { + "epoch": 0.49, + "learning_rate": 1.197625047932974e-05, + "loss": 1.5409, + "step": 4701 + }, + { + "epoch": 0.49, + "learning_rate": 1.197266228553884e-05, + "loss": 1.4878, + "step": 4702 + }, + { + "epoch": 0.49, + "learning_rate": 1.196907382746188e-05, + "loss": 1.3581, + "step": 4703 + }, + { + "epoch": 0.49, + "learning_rate": 1.1965485105579621e-05, + "loss": 1.3617, + "step": 4704 + }, + { + "epoch": 0.49, + "learning_rate": 1.1961896120372857e-05, + "loss": 1.399, + "step": 4705 + }, + { + "epoch": 0.49, + "learning_rate": 1.1958306872322425e-05, + "loss": 1.3861, + "step": 4706 + }, + { + "epoch": 0.49, + "learning_rate": 1.1954717361909186e-05, + "loss": 1.4719, + "step": 4707 + }, + { + "epoch": 0.49, + "learning_rate": 1.195112758961405e-05, + "loss": 1.393, + "step": 4708 + }, + { + "epoch": 0.49, + "learning_rate": 1.1947537555917947e-05, + "loss": 1.4252, + "step": 4709 + }, + { + "epoch": 0.49, + "learning_rate": 1.194394726130185e-05, + "loss": 1.4187, + "step": 4710 + }, + { + "epoch": 0.49, + "learning_rate": 1.1940356706246772e-05, + "loss": 1.4822, + "step": 4711 + }, + { + "epoch": 0.49, + "learning_rate": 1.193676589123375e-05, + "loss": 1.4259, + "step": 4712 + }, + { + "epoch": 0.49, + "learning_rate": 1.1933174816743857e-05, + "loss": 1.4226, + "step": 4713 + }, + { + "epoch": 0.49, + "learning_rate": 1.1929583483258216e-05, + "loss": 1.3701, + "step": 4714 + }, + { + "epoch": 0.49, + "learning_rate": 1.1925991891257967e-05, + "loss": 1.406, + "step": 4715 + }, + { + "epoch": 0.49, + "learning_rate": 1.1922400041224288e-05, + "loss": 1.4593, + "step": 4716 + }, + { + "epoch": 0.49, + "learning_rate": 1.1918807933638401e-05, + "loss": 1.3443, + "step": 4717 + }, + { + "epoch": 0.49, + "learning_rate": 1.1915215568981552e-05, + "loss": 1.3523, + "step": 4718 + }, + { + "epoch": 0.49, + "learning_rate": 1.1911622947735027e-05, + "loss": 1.3175, + "step": 4719 + }, + { + "epoch": 0.49, + "learning_rate": 1.1908030070380143e-05, + "loss": 1.3974, + "step": 4720 + }, + { + "epoch": 0.5, + "learning_rate": 1.1904436937398257e-05, + "loss": 1.386, + "step": 4721 + }, + { + "epoch": 0.5, + "learning_rate": 1.1900843549270753e-05, + "loss": 1.3684, + "step": 4722 + }, + { + "epoch": 0.5, + "learning_rate": 1.1897249906479054e-05, + "loss": 1.383, + "step": 4723 + }, + { + "epoch": 0.5, + "learning_rate": 1.1893656009504617e-05, + "loss": 1.38, + "step": 4724 + }, + { + "epoch": 0.5, + "learning_rate": 1.1890061858828928e-05, + "loss": 1.3844, + "step": 4725 + }, + { + "epoch": 0.5, + "learning_rate": 1.1886467454933515e-05, + "loss": 1.3252, + "step": 4726 + }, + { + "epoch": 0.5, + "learning_rate": 1.1882872798299934e-05, + "loss": 1.3434, + "step": 4727 + }, + { + "epoch": 0.5, + "learning_rate": 1.1879277889409779e-05, + "loss": 1.4115, + "step": 4728 + }, + { + "epoch": 0.5, + "learning_rate": 1.1875682728744669e-05, + "loss": 1.1911, + "step": 4729 + }, + { + "epoch": 0.5, + "learning_rate": 1.1872087316786272e-05, + "loss": 1.2794, + "step": 4730 + }, + { + "epoch": 0.5, + "learning_rate": 1.1868491654016274e-05, + "loss": 1.3961, + "step": 4731 + }, + { + "epoch": 0.5, + "learning_rate": 1.1864895740916404e-05, + "loss": 1.4965, + "step": 4732 + }, + { + "epoch": 0.5, + "learning_rate": 1.1861299577968419e-05, + "loss": 1.3932, + "step": 4733 + }, + { + "epoch": 0.5, + "learning_rate": 1.185770316565412e-05, + "loss": 1.3926, + "step": 4734 + }, + { + "epoch": 0.5, + "learning_rate": 1.1854106504455327e-05, + "loss": 1.3964, + "step": 4735 + }, + { + "epoch": 0.5, + "learning_rate": 1.1850509594853901e-05, + "loss": 1.3666, + "step": 4736 + }, + { + "epoch": 0.5, + "learning_rate": 1.1846912437331736e-05, + "loss": 1.4364, + "step": 4737 + }, + { + "epoch": 0.5, + "learning_rate": 1.1843315032370762e-05, + "loss": 1.3537, + "step": 4738 + }, + { + "epoch": 0.5, + "learning_rate": 1.1839717380452935e-05, + "loss": 1.4083, + "step": 4739 + }, + { + "epoch": 0.5, + "learning_rate": 1.1836119482060247e-05, + "loss": 1.3881, + "step": 4740 + }, + { + "epoch": 0.5, + "learning_rate": 1.1832521337674727e-05, + "loss": 1.4127, + "step": 4741 + }, + { + "epoch": 0.5, + "learning_rate": 1.1828922947778436e-05, + "loss": 1.3433, + "step": 4742 + }, + { + "epoch": 0.5, + "learning_rate": 1.1825324312853461e-05, + "loss": 1.486, + "step": 4743 + }, + { + "epoch": 0.5, + "learning_rate": 1.1821725433381925e-05, + "loss": 1.335, + "step": 4744 + }, + { + "epoch": 0.5, + "learning_rate": 1.1818126309845993e-05, + "loss": 1.3827, + "step": 4745 + }, + { + "epoch": 0.5, + "learning_rate": 1.181452694272785e-05, + "loss": 1.3146, + "step": 4746 + }, + { + "epoch": 0.5, + "learning_rate": 1.1810927332509717e-05, + "loss": 1.3543, + "step": 4747 + }, + { + "epoch": 0.5, + "learning_rate": 1.1807327479673852e-05, + "loss": 1.3544, + "step": 4748 + }, + { + "epoch": 0.5, + "learning_rate": 1.1803727384702543e-05, + "loss": 1.3677, + "step": 4749 + }, + { + "epoch": 0.5, + "learning_rate": 1.1800127048078111e-05, + "loss": 1.3842, + "step": 4750 + }, + { + "epoch": 0.5, + "learning_rate": 1.1796526470282907e-05, + "loss": 1.3495, + "step": 4751 + }, + { + "epoch": 0.5, + "learning_rate": 1.1792925651799314e-05, + "loss": 1.481, + "step": 4752 + }, + { + "epoch": 0.5, + "learning_rate": 1.1789324593109754e-05, + "loss": 1.3482, + "step": 4753 + }, + { + "epoch": 0.5, + "learning_rate": 1.1785723294696673e-05, + "loss": 1.2805, + "step": 4754 + }, + { + "epoch": 0.5, + "learning_rate": 1.1782121757042555e-05, + "loss": 1.3458, + "step": 4755 + }, + { + "epoch": 0.5, + "learning_rate": 1.1778519980629907e-05, + "loss": 1.3937, + "step": 4756 + }, + { + "epoch": 0.5, + "learning_rate": 1.1774917965941284e-05, + "loss": 1.3873, + "step": 4757 + }, + { + "epoch": 0.5, + "learning_rate": 1.1771315713459258e-05, + "loss": 1.3512, + "step": 4758 + }, + { + "epoch": 0.5, + "learning_rate": 1.1767713223666436e-05, + "loss": 1.4465, + "step": 4759 + }, + { + "epoch": 0.5, + "learning_rate": 1.1764110497045463e-05, + "loss": 1.4233, + "step": 4760 + }, + { + "epoch": 0.5, + "learning_rate": 1.1760507534079011e-05, + "loss": 1.4818, + "step": 4761 + }, + { + "epoch": 0.5, + "learning_rate": 1.1756904335249786e-05, + "loss": 1.2933, + "step": 4762 + }, + { + "epoch": 0.5, + "learning_rate": 1.1753300901040518e-05, + "loss": 1.3524, + "step": 4763 + }, + { + "epoch": 0.5, + "learning_rate": 1.1749697231933981e-05, + "loss": 1.4909, + "step": 4764 + }, + { + "epoch": 0.5, + "learning_rate": 1.1746093328412975e-05, + "loss": 1.2912, + "step": 4765 + }, + { + "epoch": 0.5, + "learning_rate": 1.1742489190960325e-05, + "loss": 1.3372, + "step": 4766 + }, + { + "epoch": 0.5, + "learning_rate": 1.1738884820058893e-05, + "loss": 1.3036, + "step": 4767 + }, + { + "epoch": 0.5, + "learning_rate": 1.1735280216191578e-05, + "loss": 1.3189, + "step": 4768 + }, + { + "epoch": 0.5, + "learning_rate": 1.1731675379841298e-05, + "loss": 1.4146, + "step": 4769 + }, + { + "epoch": 0.5, + "learning_rate": 1.1728070311491013e-05, + "loss": 1.3309, + "step": 4770 + }, + { + "epoch": 0.5, + "learning_rate": 1.1724465011623705e-05, + "loss": 1.3427, + "step": 4771 + }, + { + "epoch": 0.5, + "learning_rate": 1.1720859480722395e-05, + "loss": 1.4033, + "step": 4772 + }, + { + "epoch": 0.5, + "learning_rate": 1.1717253719270135e-05, + "loss": 1.3832, + "step": 4773 + }, + { + "epoch": 0.5, + "learning_rate": 1.1713647727749994e-05, + "loss": 1.4074, + "step": 4774 + }, + { + "epoch": 0.5, + "learning_rate": 1.1710041506645092e-05, + "loss": 1.3579, + "step": 4775 + }, + { + "epoch": 0.5, + "learning_rate": 1.1706435056438564e-05, + "loss": 1.3685, + "step": 4776 + }, + { + "epoch": 0.5, + "eval_loss": 1.436767816543579, + "eval_runtime": 77.4332, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4776 + }, + { + "epoch": 0.5, + "learning_rate": 1.1702828377613584e-05, + "loss": 1.5843, + "step": 4777 + }, + { + "epoch": 0.5, + "learning_rate": 1.1699221470653355e-05, + "loss": 1.4168, + "step": 4778 + }, + { + "epoch": 0.5, + "learning_rate": 1.1695614336041108e-05, + "loss": 1.3515, + "step": 4779 + }, + { + "epoch": 0.5, + "learning_rate": 1.169200697426011e-05, + "loss": 1.3214, + "step": 4780 + }, + { + "epoch": 0.5, + "learning_rate": 1.1688399385793652e-05, + "loss": 1.3728, + "step": 4781 + }, + { + "epoch": 0.5, + "learning_rate": 1.1684791571125054e-05, + "loss": 1.3759, + "step": 4782 + }, + { + "epoch": 0.5, + "learning_rate": 1.1681183530737678e-05, + "loss": 1.4955, + "step": 4783 + }, + { + "epoch": 0.5, + "learning_rate": 1.1677575265114904e-05, + "loss": 1.4284, + "step": 4784 + }, + { + "epoch": 0.5, + "learning_rate": 1.1673966774740151e-05, + "loss": 1.3725, + "step": 4785 + }, + { + "epoch": 0.5, + "learning_rate": 1.1670358060096858e-05, + "loss": 1.3612, + "step": 4786 + }, + { + "epoch": 0.5, + "learning_rate": 1.1666749121668506e-05, + "loss": 1.3021, + "step": 4787 + }, + { + "epoch": 0.5, + "learning_rate": 1.1663139959938597e-05, + "loss": 1.4399, + "step": 4788 + }, + { + "epoch": 0.5, + "learning_rate": 1.1659530575390668e-05, + "loss": 1.3511, + "step": 4789 + }, + { + "epoch": 0.5, + "learning_rate": 1.1655920968508276e-05, + "loss": 1.4211, + "step": 4790 + }, + { + "epoch": 0.5, + "learning_rate": 1.1652311139775028e-05, + "loss": 1.343, + "step": 4791 + }, + { + "epoch": 0.5, + "learning_rate": 1.1648701089674541e-05, + "loss": 1.3838, + "step": 4792 + }, + { + "epoch": 0.5, + "learning_rate": 1.164509081869047e-05, + "loss": 1.342, + "step": 4793 + }, + { + "epoch": 0.5, + "learning_rate": 1.1641480327306494e-05, + "loss": 1.3831, + "step": 4794 + }, + { + "epoch": 0.5, + "learning_rate": 1.1637869616006335e-05, + "loss": 1.4102, + "step": 4795 + }, + { + "epoch": 0.5, + "learning_rate": 1.1634258685273732e-05, + "loss": 1.4184, + "step": 4796 + }, + { + "epoch": 0.5, + "learning_rate": 1.1630647535592455e-05, + "loss": 1.3974, + "step": 4797 + }, + { + "epoch": 0.5, + "learning_rate": 1.1627036167446302e-05, + "loss": 1.251, + "step": 4798 + }, + { + "epoch": 0.5, + "learning_rate": 1.1623424581319113e-05, + "loss": 1.3485, + "step": 4799 + }, + { + "epoch": 0.5, + "learning_rate": 1.1619812777694742e-05, + "loss": 1.3544, + "step": 4800 + }, + { + "epoch": 0.5, + "learning_rate": 1.1616200757057076e-05, + "loss": 1.3772, + "step": 4801 + }, + { + "epoch": 0.5, + "learning_rate": 1.1612588519890038e-05, + "loss": 1.3082, + "step": 4802 + }, + { + "epoch": 0.5, + "learning_rate": 1.160897606667757e-05, + "loss": 1.3634, + "step": 4803 + }, + { + "epoch": 0.5, + "learning_rate": 1.1605363397903655e-05, + "loss": 1.3682, + "step": 4804 + }, + { + "epoch": 0.5, + "learning_rate": 1.1601750514052288e-05, + "loss": 1.3258, + "step": 4805 + }, + { + "epoch": 0.5, + "learning_rate": 1.1598137415607511e-05, + "loss": 1.279, + "step": 4806 + }, + { + "epoch": 0.5, + "learning_rate": 1.1594524103053382e-05, + "loss": 1.3759, + "step": 4807 + }, + { + "epoch": 0.5, + "learning_rate": 1.1590910576873995e-05, + "loss": 1.5404, + "step": 4808 + }, + { + "epoch": 0.5, + "learning_rate": 1.1587296837553463e-05, + "loss": 1.4949, + "step": 4809 + }, + { + "epoch": 0.5, + "learning_rate": 1.1583682885575943e-05, + "loss": 1.3501, + "step": 4810 + }, + { + "epoch": 0.5, + "learning_rate": 1.1580068721425608e-05, + "loss": 1.3898, + "step": 4811 + }, + { + "epoch": 0.5, + "learning_rate": 1.157645434558666e-05, + "loss": 1.3265, + "step": 4812 + }, + { + "epoch": 0.5, + "learning_rate": 1.1572839758543338e-05, + "loss": 1.3454, + "step": 4813 + }, + { + "epoch": 0.5, + "learning_rate": 1.1569224960779899e-05, + "loss": 1.4065, + "step": 4814 + }, + { + "epoch": 0.5, + "learning_rate": 1.156560995278064e-05, + "loss": 1.4932, + "step": 4815 + }, + { + "epoch": 0.51, + "learning_rate": 1.156199473502987e-05, + "loss": 1.4224, + "step": 4816 + }, + { + "epoch": 0.51, + "learning_rate": 1.1558379308011937e-05, + "loss": 1.3884, + "step": 4817 + }, + { + "epoch": 0.51, + "learning_rate": 1.1554763672211222e-05, + "loss": 1.3355, + "step": 4818 + }, + { + "epoch": 0.51, + "learning_rate": 1.1551147828112124e-05, + "loss": 1.4281, + "step": 4819 + }, + { + "epoch": 0.51, + "learning_rate": 1.1547531776199072e-05, + "loss": 1.3148, + "step": 4820 + }, + { + "epoch": 0.51, + "learning_rate": 1.1543915516956523e-05, + "loss": 1.3255, + "step": 4821 + }, + { + "epoch": 0.51, + "learning_rate": 1.1540299050868966e-05, + "loss": 1.3361, + "step": 4822 + }, + { + "epoch": 0.51, + "learning_rate": 1.1536682378420912e-05, + "loss": 1.3377, + "step": 4823 + }, + { + "epoch": 0.51, + "learning_rate": 1.1533065500096901e-05, + "loss": 1.4205, + "step": 4824 + }, + { + "epoch": 0.51, + "learning_rate": 1.1529448416381505e-05, + "loss": 1.4193, + "step": 4825 + }, + { + "epoch": 0.51, + "learning_rate": 1.1525831127759322e-05, + "loss": 1.37, + "step": 4826 + }, + { + "epoch": 0.51, + "learning_rate": 1.1522213634714971e-05, + "loss": 1.3642, + "step": 4827 + }, + { + "epoch": 0.51, + "learning_rate": 1.1518595937733103e-05, + "loss": 1.4834, + "step": 4828 + }, + { + "epoch": 0.51, + "learning_rate": 1.1514978037298402e-05, + "loss": 1.2864, + "step": 4829 + }, + { + "epoch": 0.51, + "learning_rate": 1.1511359933895567e-05, + "loss": 1.3468, + "step": 4830 + }, + { + "epoch": 0.51, + "learning_rate": 1.1507741628009337e-05, + "loss": 1.328, + "step": 4831 + }, + { + "epoch": 0.51, + "learning_rate": 1.1504123120124466e-05, + "loss": 1.3489, + "step": 4832 + }, + { + "epoch": 0.51, + "learning_rate": 1.1500504410725746e-05, + "loss": 1.4031, + "step": 4833 + }, + { + "epoch": 0.51, + "learning_rate": 1.149688550029799e-05, + "loss": 1.3482, + "step": 4834 + }, + { + "epoch": 0.51, + "learning_rate": 1.1493266389326037e-05, + "loss": 1.3674, + "step": 4835 + }, + { + "epoch": 0.51, + "learning_rate": 1.1489647078294753e-05, + "loss": 1.2895, + "step": 4836 + }, + { + "epoch": 0.51, + "learning_rate": 1.148602756768904e-05, + "loss": 1.4071, + "step": 4837 + }, + { + "epoch": 0.51, + "learning_rate": 1.1482407857993814e-05, + "loss": 1.5218, + "step": 4838 + }, + { + "epoch": 0.51, + "learning_rate": 1.1478787949694024e-05, + "loss": 1.4577, + "step": 4839 + }, + { + "epoch": 0.51, + "learning_rate": 1.1475167843274643e-05, + "loss": 1.3817, + "step": 4840 + }, + { + "epoch": 0.51, + "learning_rate": 1.1471547539220678e-05, + "loss": 1.3072, + "step": 4841 + }, + { + "epoch": 0.51, + "learning_rate": 1.146792703801715e-05, + "loss": 1.3737, + "step": 4842 + }, + { + "epoch": 0.51, + "learning_rate": 1.1464306340149119e-05, + "loss": 1.4001, + "step": 4843 + }, + { + "epoch": 0.51, + "learning_rate": 1.1460685446101658e-05, + "loss": 1.3963, + "step": 4844 + }, + { + "epoch": 0.51, + "learning_rate": 1.1457064356359882e-05, + "loss": 1.4061, + "step": 4845 + }, + { + "epoch": 0.51, + "learning_rate": 1.145344307140892e-05, + "loss": 1.4211, + "step": 4846 + }, + { + "epoch": 0.51, + "learning_rate": 1.144982159173393e-05, + "loss": 1.3197, + "step": 4847 + }, + { + "epoch": 0.51, + "learning_rate": 1.14461999178201e-05, + "loss": 1.3549, + "step": 4848 + }, + { + "epoch": 0.51, + "learning_rate": 1.1442578050152639e-05, + "loss": 1.3889, + "step": 4849 + }, + { + "epoch": 0.51, + "learning_rate": 1.1438955989216787e-05, + "loss": 1.3847, + "step": 4850 + }, + { + "epoch": 0.51, + "learning_rate": 1.1435333735497803e-05, + "loss": 1.3586, + "step": 4851 + }, + { + "epoch": 0.51, + "learning_rate": 1.1431711289480978e-05, + "loss": 1.503, + "step": 4852 + }, + { + "epoch": 0.51, + "learning_rate": 1.1428088651651627e-05, + "loss": 1.3654, + "step": 4853 + }, + { + "epoch": 0.51, + "learning_rate": 1.1424465822495092e-05, + "loss": 1.3741, + "step": 4854 + }, + { + "epoch": 0.51, + "learning_rate": 1.1420842802496737e-05, + "loss": 1.5437, + "step": 4855 + }, + { + "epoch": 0.51, + "learning_rate": 1.1417219592141953e-05, + "loss": 1.2179, + "step": 4856 + }, + { + "epoch": 0.51, + "learning_rate": 1.1413596191916159e-05, + "loss": 1.3939, + "step": 4857 + }, + { + "epoch": 0.51, + "learning_rate": 1.1409972602304796e-05, + "loss": 1.3383, + "step": 4858 + }, + { + "epoch": 0.51, + "learning_rate": 1.140634882379333e-05, + "loss": 1.3664, + "step": 4859 + }, + { + "epoch": 0.51, + "learning_rate": 1.1402724856867258e-05, + "loss": 1.4002, + "step": 4860 + }, + { + "epoch": 0.51, + "learning_rate": 1.1399100702012098e-05, + "loss": 1.2975, + "step": 4861 + }, + { + "epoch": 0.51, + "learning_rate": 1.1395476359713394e-05, + "loss": 1.3564, + "step": 4862 + }, + { + "epoch": 0.51, + "learning_rate": 1.1391851830456708e-05, + "loss": 1.3574, + "step": 4863 + }, + { + "epoch": 0.51, + "learning_rate": 1.1388227114727644e-05, + "loss": 1.3407, + "step": 4864 + }, + { + "epoch": 0.51, + "learning_rate": 1.1384602213011815e-05, + "loss": 1.3603, + "step": 4865 + }, + { + "epoch": 0.51, + "learning_rate": 1.1380977125794866e-05, + "loss": 1.3465, + "step": 4866 + }, + { + "epoch": 0.51, + "learning_rate": 1.1377351853562461e-05, + "loss": 1.3744, + "step": 4867 + }, + { + "epoch": 0.51, + "learning_rate": 1.1373726396800304e-05, + "loss": 1.3248, + "step": 4868 + }, + { + "epoch": 0.51, + "learning_rate": 1.1370100755994102e-05, + "loss": 1.3352, + "step": 4869 + }, + { + "epoch": 0.51, + "learning_rate": 1.1366474931629603e-05, + "loss": 1.3299, + "step": 4870 + }, + { + "epoch": 0.51, + "learning_rate": 1.1362848924192575e-05, + "loss": 1.344, + "step": 4871 + }, + { + "epoch": 0.51, + "learning_rate": 1.1359222734168809e-05, + "loss": 1.3209, + "step": 4872 + }, + { + "epoch": 0.51, + "learning_rate": 1.135559636204412e-05, + "loss": 1.3927, + "step": 4873 + }, + { + "epoch": 0.51, + "learning_rate": 1.1351969808304349e-05, + "loss": 1.3717, + "step": 4874 + }, + { + "epoch": 0.51, + "learning_rate": 1.1348343073435362e-05, + "loss": 1.3813, + "step": 4875 + }, + { + "epoch": 0.51, + "learning_rate": 1.1344716157923046e-05, + "loss": 1.236, + "step": 4876 + }, + { + "epoch": 0.51, + "learning_rate": 1.1341089062253319e-05, + "loss": 1.2591, + "step": 4877 + }, + { + "epoch": 0.51, + "learning_rate": 1.1337461786912112e-05, + "loss": 1.3211, + "step": 4878 + }, + { + "epoch": 0.51, + "learning_rate": 1.1333834332385394e-05, + "loss": 1.4534, + "step": 4879 + }, + { + "epoch": 0.51, + "learning_rate": 1.1330206699159145e-05, + "loss": 1.346, + "step": 4880 + }, + { + "epoch": 0.51, + "learning_rate": 1.132657888771938e-05, + "loss": 1.3952, + "step": 4881 + }, + { + "epoch": 0.51, + "learning_rate": 1.1322950898552125e-05, + "loss": 1.3008, + "step": 4882 + }, + { + "epoch": 0.51, + "learning_rate": 1.1319322732143445e-05, + "loss": 1.3201, + "step": 4883 + }, + { + "epoch": 0.51, + "learning_rate": 1.1315694388979416e-05, + "loss": 1.3761, + "step": 4884 + }, + { + "epoch": 0.51, + "learning_rate": 1.1312065869546147e-05, + "loss": 1.343, + "step": 4885 + }, + { + "epoch": 0.51, + "learning_rate": 1.1308437174329761e-05, + "loss": 1.3741, + "step": 4886 + }, + { + "epoch": 0.51, + "learning_rate": 1.1304808303816413e-05, + "loss": 1.402, + "step": 4887 + }, + { + "epoch": 0.51, + "learning_rate": 1.130117925849228e-05, + "loss": 1.3834, + "step": 4888 + }, + { + "epoch": 0.51, + "learning_rate": 1.1297550038843559e-05, + "loss": 1.3342, + "step": 4889 + }, + { + "epoch": 0.51, + "learning_rate": 1.1293920645356471e-05, + "loss": 1.3207, + "step": 4890 + }, + { + "epoch": 0.51, + "learning_rate": 1.1290291078517264e-05, + "loss": 1.4274, + "step": 4891 + }, + { + "epoch": 0.51, + "learning_rate": 1.1286661338812203e-05, + "loss": 1.328, + "step": 4892 + }, + { + "epoch": 0.51, + "learning_rate": 1.1283031426727584e-05, + "loss": 1.3823, + "step": 4893 + }, + { + "epoch": 0.51, + "learning_rate": 1.127940134274972e-05, + "loss": 1.3612, + "step": 4894 + }, + { + "epoch": 0.51, + "learning_rate": 1.127577108736495e-05, + "loss": 1.375, + "step": 4895 + }, + { + "epoch": 0.51, + "learning_rate": 1.1272140661059636e-05, + "loss": 1.3531, + "step": 4896 + }, + { + "epoch": 0.51, + "learning_rate": 1.1268510064320155e-05, + "loss": 1.3636, + "step": 4897 + }, + { + "epoch": 0.51, + "learning_rate": 1.1264879297632923e-05, + "loss": 1.3524, + "step": 4898 + }, + { + "epoch": 0.51, + "learning_rate": 1.1261248361484363e-05, + "loss": 1.3865, + "step": 4899 + }, + { + "epoch": 0.51, + "learning_rate": 1.125761725636093e-05, + "loss": 1.4069, + "step": 4900 + }, + { + "epoch": 0.51, + "learning_rate": 1.1253985982749098e-05, + "loss": 1.4643, + "step": 4901 + }, + { + "epoch": 0.51, + "learning_rate": 1.1250354541135364e-05, + "loss": 1.4506, + "step": 4902 + }, + { + "epoch": 0.51, + "learning_rate": 1.124672293200625e-05, + "loss": 1.3857, + "step": 4903 + }, + { + "epoch": 0.51, + "learning_rate": 1.1243091155848295e-05, + "loss": 1.3554, + "step": 4904 + }, + { + "epoch": 0.51, + "learning_rate": 1.1239459213148065e-05, + "loss": 1.4071, + "step": 4905 + }, + { + "epoch": 0.51, + "learning_rate": 1.1235827104392148e-05, + "loss": 1.3981, + "step": 4906 + }, + { + "epoch": 0.51, + "learning_rate": 1.1232194830067153e-05, + "loss": 1.4913, + "step": 4907 + }, + { + "epoch": 0.51, + "learning_rate": 1.1228562390659712e-05, + "loss": 1.3343, + "step": 4908 + }, + { + "epoch": 0.51, + "learning_rate": 1.1224929786656474e-05, + "loss": 1.3832, + "step": 4909 + }, + { + "epoch": 0.51, + "learning_rate": 1.122129701854412e-05, + "loss": 1.367, + "step": 4910 + }, + { + "epoch": 0.51, + "learning_rate": 1.1217664086809345e-05, + "loss": 1.4108, + "step": 4911 + }, + { + "epoch": 0.52, + "learning_rate": 1.1214030991938872e-05, + "loss": 1.3981, + "step": 4912 + }, + { + "epoch": 0.52, + "learning_rate": 1.1210397734419436e-05, + "loss": 1.5266, + "step": 4913 + }, + { + "epoch": 0.52, + "learning_rate": 1.1206764314737806e-05, + "loss": 1.337, + "step": 4914 + }, + { + "epoch": 0.52, + "learning_rate": 1.1203130733380765e-05, + "loss": 1.3784, + "step": 4915 + }, + { + "epoch": 0.52, + "learning_rate": 1.1199496990835117e-05, + "loss": 1.3048, + "step": 4916 + }, + { + "epoch": 0.52, + "learning_rate": 1.1195863087587692e-05, + "loss": 1.2977, + "step": 4917 + }, + { + "epoch": 0.52, + "learning_rate": 1.1192229024125344e-05, + "loss": 1.3304, + "step": 4918 + }, + { + "epoch": 0.52, + "learning_rate": 1.1188594800934938e-05, + "loss": 1.4102, + "step": 4919 + }, + { + "epoch": 0.52, + "learning_rate": 1.1184960418503366e-05, + "loss": 1.3932, + "step": 4920 + }, + { + "epoch": 0.52, + "learning_rate": 1.1181325877317547e-05, + "loss": 1.4985, + "step": 4921 + }, + { + "epoch": 0.52, + "learning_rate": 1.1177691177864415e-05, + "loss": 1.4596, + "step": 4922 + }, + { + "epoch": 0.52, + "learning_rate": 1.1174056320630924e-05, + "loss": 1.3559, + "step": 4923 + }, + { + "epoch": 0.52, + "learning_rate": 1.117042130610405e-05, + "loss": 1.4128, + "step": 4924 + }, + { + "epoch": 0.52, + "learning_rate": 1.1166786134770795e-05, + "loss": 1.3343, + "step": 4925 + }, + { + "epoch": 0.52, + "learning_rate": 1.116315080711818e-05, + "loss": 1.332, + "step": 4926 + }, + { + "epoch": 0.52, + "learning_rate": 1.115951532363324e-05, + "loss": 1.3616, + "step": 4927 + }, + { + "epoch": 0.52, + "learning_rate": 1.1155879684803041e-05, + "loss": 1.4074, + "step": 4928 + }, + { + "epoch": 0.52, + "learning_rate": 1.1152243891114665e-05, + "loss": 1.303, + "step": 4929 + }, + { + "epoch": 0.52, + "learning_rate": 1.1148607943055212e-05, + "loss": 1.4799, + "step": 4930 + }, + { + "epoch": 0.52, + "learning_rate": 1.1144971841111807e-05, + "loss": 1.3881, + "step": 4931 + }, + { + "epoch": 0.52, + "learning_rate": 1.1141335585771593e-05, + "loss": 1.338, + "step": 4932 + }, + { + "epoch": 0.52, + "learning_rate": 1.1137699177521738e-05, + "loss": 1.3289, + "step": 4933 + }, + { + "epoch": 0.52, + "learning_rate": 1.1134062616849426e-05, + "loss": 1.377, + "step": 4934 + }, + { + "epoch": 0.52, + "learning_rate": 1.1130425904241862e-05, + "loss": 1.3596, + "step": 4935 + }, + { + "epoch": 0.52, + "learning_rate": 1.112678904018627e-05, + "loss": 1.4264, + "step": 4936 + }, + { + "epoch": 0.52, + "learning_rate": 1.1123152025169898e-05, + "loss": 1.3526, + "step": 4937 + }, + { + "epoch": 0.52, + "learning_rate": 1.1119514859680016e-05, + "loss": 1.3271, + "step": 4938 + }, + { + "epoch": 0.52, + "learning_rate": 1.1115877544203905e-05, + "loss": 1.3907, + "step": 4939 + }, + { + "epoch": 0.52, + "learning_rate": 1.1112240079228878e-05, + "loss": 1.3415, + "step": 4940 + }, + { + "epoch": 0.52, + "learning_rate": 1.1108602465242258e-05, + "loss": 1.3875, + "step": 4941 + }, + { + "epoch": 0.52, + "learning_rate": 1.110496470273139e-05, + "loss": 1.3964, + "step": 4942 + }, + { + "epoch": 0.52, + "learning_rate": 1.1101326792183645e-05, + "loss": 1.3448, + "step": 4943 + }, + { + "epoch": 0.52, + "learning_rate": 1.1097688734086407e-05, + "loss": 1.3522, + "step": 4944 + }, + { + "epoch": 0.52, + "learning_rate": 1.1094050528927082e-05, + "loss": 1.2742, + "step": 4945 + }, + { + "epoch": 0.52, + "learning_rate": 1.1090412177193097e-05, + "loss": 1.417, + "step": 4946 + }, + { + "epoch": 0.52, + "learning_rate": 1.1086773679371898e-05, + "loss": 1.3993, + "step": 4947 + }, + { + "epoch": 0.52, + "learning_rate": 1.108313503595095e-05, + "loss": 1.3783, + "step": 4948 + }, + { + "epoch": 0.52, + "learning_rate": 1.1079496247417736e-05, + "loss": 1.3975, + "step": 4949 + }, + { + "epoch": 0.52, + "learning_rate": 1.1075857314259763e-05, + "loss": 1.4256, + "step": 4950 + }, + { + "epoch": 0.52, + "learning_rate": 1.1072218236964551e-05, + "loss": 1.3547, + "step": 4951 + }, + { + "epoch": 0.52, + "learning_rate": 1.106857901601965e-05, + "loss": 1.4243, + "step": 4952 + }, + { + "epoch": 0.52, + "learning_rate": 1.1064939651912612e-05, + "loss": 1.4259, + "step": 4953 + }, + { + "epoch": 0.52, + "learning_rate": 1.1061300145131027e-05, + "loss": 1.4323, + "step": 4954 + }, + { + "epoch": 0.52, + "learning_rate": 1.1057660496162488e-05, + "loss": 1.3608, + "step": 4955 + }, + { + "epoch": 0.52, + "learning_rate": 1.1054020705494622e-05, + "loss": 1.3703, + "step": 4956 + }, + { + "epoch": 0.52, + "learning_rate": 1.105038077361506e-05, + "loss": 1.3953, + "step": 4957 + }, + { + "epoch": 0.52, + "learning_rate": 1.1046740701011467e-05, + "loss": 1.392, + "step": 4958 + }, + { + "epoch": 0.52, + "learning_rate": 1.1043100488171513e-05, + "loss": 1.4101, + "step": 4959 + }, + { + "epoch": 0.52, + "learning_rate": 1.1039460135582894e-05, + "loss": 1.5432, + "step": 4960 + }, + { + "epoch": 0.52, + "learning_rate": 1.1035819643733326e-05, + "loss": 1.3822, + "step": 4961 + }, + { + "epoch": 0.52, + "learning_rate": 1.103217901311054e-05, + "loss": 1.3816, + "step": 4962 + }, + { + "epoch": 0.52, + "learning_rate": 1.1028538244202287e-05, + "loss": 1.3137, + "step": 4963 + }, + { + "epoch": 0.52, + "learning_rate": 1.102489733749634e-05, + "loss": 1.3791, + "step": 4964 + }, + { + "epoch": 0.52, + "learning_rate": 1.102125629348048e-05, + "loss": 1.3751, + "step": 4965 + }, + { + "epoch": 0.52, + "learning_rate": 1.1017615112642518e-05, + "loss": 1.3287, + "step": 4966 + }, + { + "epoch": 0.52, + "learning_rate": 1.1013973795470277e-05, + "loss": 1.3187, + "step": 4967 + }, + { + "epoch": 0.52, + "learning_rate": 1.1010332342451602e-05, + "loss": 1.3174, + "step": 4968 + }, + { + "epoch": 0.52, + "learning_rate": 1.1006690754074351e-05, + "loss": 1.3544, + "step": 4969 + }, + { + "epoch": 0.52, + "learning_rate": 1.1003049030826404e-05, + "loss": 1.3789, + "step": 4970 + }, + { + "epoch": 0.52, + "learning_rate": 1.0999407173195662e-05, + "loss": 1.4561, + "step": 4971 + }, + { + "epoch": 0.52, + "learning_rate": 1.0995765181670039e-05, + "loss": 1.3963, + "step": 4972 + }, + { + "epoch": 0.52, + "learning_rate": 1.0992123056737464e-05, + "loss": 1.3519, + "step": 4973 + }, + { + "epoch": 0.52, + "learning_rate": 1.0988480798885892e-05, + "loss": 1.3945, + "step": 4974 + }, + { + "epoch": 0.52, + "learning_rate": 1.0984838408603294e-05, + "loss": 1.4572, + "step": 4975 + }, + { + "epoch": 0.52, + "eval_loss": 1.4313459396362305, + "eval_runtime": 77.4808, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 4975 + }, + { + "epoch": 0.52, + "learning_rate": 1.0981195886377652e-05, + "loss": 1.3493, + "step": 4976 + }, + { + "epoch": 0.52, + "learning_rate": 1.0977553232696972e-05, + "loss": 1.3734, + "step": 4977 + }, + { + "epoch": 0.52, + "learning_rate": 1.0973910448049273e-05, + "loss": 1.3484, + "step": 4978 + }, + { + "epoch": 0.52, + "learning_rate": 1.09702675329226e-05, + "loss": 1.4288, + "step": 4979 + }, + { + "epoch": 0.52, + "learning_rate": 1.096662448780501e-05, + "loss": 1.3748, + "step": 4980 + }, + { + "epoch": 0.52, + "learning_rate": 1.0962981313184575e-05, + "loss": 1.3485, + "step": 4981 + }, + { + "epoch": 0.52, + "learning_rate": 1.0959338009549383e-05, + "loss": 1.3606, + "step": 4982 + }, + { + "epoch": 0.52, + "learning_rate": 1.095569457738755e-05, + "loss": 1.3963, + "step": 4983 + }, + { + "epoch": 0.52, + "learning_rate": 1.09520510171872e-05, + "loss": 1.2986, + "step": 4984 + }, + { + "epoch": 0.52, + "learning_rate": 1.0948407329436474e-05, + "loss": 1.3505, + "step": 4985 + }, + { + "epoch": 0.52, + "learning_rate": 1.0944763514623535e-05, + "loss": 1.4649, + "step": 4986 + }, + { + "epoch": 0.52, + "learning_rate": 1.0941119573236564e-05, + "loss": 1.4743, + "step": 4987 + }, + { + "epoch": 0.52, + "learning_rate": 1.0937475505763745e-05, + "loss": 1.3934, + "step": 4988 + }, + { + "epoch": 0.52, + "learning_rate": 1.09338313126933e-05, + "loss": 1.4225, + "step": 4989 + }, + { + "epoch": 0.52, + "learning_rate": 1.0930186994513453e-05, + "loss": 1.3626, + "step": 4990 + }, + { + "epoch": 0.52, + "learning_rate": 1.0926542551712446e-05, + "loss": 1.3614, + "step": 4991 + }, + { + "epoch": 0.52, + "learning_rate": 1.0922897984778546e-05, + "loss": 1.3766, + "step": 4992 + }, + { + "epoch": 0.52, + "learning_rate": 1.0919253294200027e-05, + "loss": 1.3295, + "step": 4993 + }, + { + "epoch": 0.52, + "learning_rate": 1.091560848046519e-05, + "loss": 1.3802, + "step": 4994 + }, + { + "epoch": 0.52, + "learning_rate": 1.091196354406234e-05, + "loss": 1.2976, + "step": 4995 + }, + { + "epoch": 0.52, + "learning_rate": 1.090831848547981e-05, + "loss": 1.3928, + "step": 4996 + }, + { + "epoch": 0.52, + "learning_rate": 1.0904673305205937e-05, + "loss": 1.3717, + "step": 4997 + }, + { + "epoch": 0.52, + "learning_rate": 1.0901028003729089e-05, + "loss": 1.3164, + "step": 4998 + }, + { + "epoch": 0.52, + "learning_rate": 1.0897382581537638e-05, + "loss": 1.3462, + "step": 4999 + }, + { + "epoch": 0.52, + "learning_rate": 1.0893737039119981e-05, + "loss": 1.3643, + "step": 5000 + }, + { + "epoch": 0.52, + "learning_rate": 1.089009137696452e-05, + "loss": 1.3452, + "step": 5001 + }, + { + "epoch": 0.52, + "learning_rate": 1.0886445595559686e-05, + "loss": 1.358, + "step": 5002 + }, + { + "epoch": 0.52, + "learning_rate": 1.0882799695393922e-05, + "loss": 1.4569, + "step": 5003 + }, + { + "epoch": 0.52, + "learning_rate": 1.0879153676955681e-05, + "loss": 1.2832, + "step": 5004 + }, + { + "epoch": 0.52, + "learning_rate": 1.0875507540733435e-05, + "loss": 1.4089, + "step": 5005 + }, + { + "epoch": 0.52, + "learning_rate": 1.087186128721567e-05, + "loss": 1.3178, + "step": 5006 + }, + { + "epoch": 0.53, + "learning_rate": 1.0868214916890902e-05, + "loss": 1.4883, + "step": 5007 + }, + { + "epoch": 0.53, + "learning_rate": 1.0864568430247638e-05, + "loss": 1.3991, + "step": 5008 + }, + { + "epoch": 0.53, + "learning_rate": 1.0860921827774422e-05, + "loss": 1.4507, + "step": 5009 + }, + { + "epoch": 0.53, + "learning_rate": 1.08572751099598e-05, + "loss": 1.3578, + "step": 5010 + }, + { + "epoch": 0.53, + "learning_rate": 1.0853628277292341e-05, + "loss": 1.4231, + "step": 5011 + }, + { + "epoch": 0.53, + "learning_rate": 1.0849981330260624e-05, + "loss": 1.4835, + "step": 5012 + }, + { + "epoch": 0.53, + "learning_rate": 1.084633426935325e-05, + "loss": 1.4511, + "step": 5013 + }, + { + "epoch": 0.53, + "learning_rate": 1.084268709505883e-05, + "loss": 1.3889, + "step": 5014 + }, + { + "epoch": 0.53, + "learning_rate": 1.0839039807865992e-05, + "loss": 1.355, + "step": 5015 + }, + { + "epoch": 0.53, + "learning_rate": 1.0835392408263375e-05, + "loss": 1.4829, + "step": 5016 + }, + { + "epoch": 0.53, + "learning_rate": 1.0831744896739643e-05, + "loss": 1.3019, + "step": 5017 + }, + { + "epoch": 0.53, + "learning_rate": 1.0828097273783465e-05, + "loss": 1.3418, + "step": 5018 + }, + { + "epoch": 0.53, + "learning_rate": 1.082444953988353e-05, + "loss": 1.4276, + "step": 5019 + }, + { + "epoch": 0.53, + "learning_rate": 1.0820801695528537e-05, + "loss": 1.2816, + "step": 5020 + }, + { + "epoch": 0.53, + "learning_rate": 1.081715374120721e-05, + "loss": 1.5144, + "step": 5021 + }, + { + "epoch": 0.53, + "learning_rate": 1.0813505677408278e-05, + "loss": 1.4063, + "step": 5022 + }, + { + "epoch": 0.53, + "learning_rate": 1.0809857504620487e-05, + "loss": 1.4011, + "step": 5023 + }, + { + "epoch": 0.53, + "learning_rate": 1.0806209223332598e-05, + "loss": 1.373, + "step": 5024 + }, + { + "epoch": 0.53, + "learning_rate": 1.0802560834033388e-05, + "loss": 1.6259, + "step": 5025 + }, + { + "epoch": 0.53, + "learning_rate": 1.0798912337211648e-05, + "loss": 1.4487, + "step": 5026 + }, + { + "epoch": 0.53, + "learning_rate": 1.0795263733356184e-05, + "loss": 1.3056, + "step": 5027 + }, + { + "epoch": 0.53, + "learning_rate": 1.079161502295581e-05, + "loss": 1.2871, + "step": 5028 + }, + { + "epoch": 0.53, + "learning_rate": 1.0787966206499363e-05, + "loss": 1.413, + "step": 5029 + }, + { + "epoch": 0.53, + "learning_rate": 1.0784317284475694e-05, + "loss": 1.3682, + "step": 5030 + }, + { + "epoch": 0.53, + "learning_rate": 1.0780668257373659e-05, + "loss": 1.493, + "step": 5031 + }, + { + "epoch": 0.53, + "learning_rate": 1.0777019125682136e-05, + "loss": 1.6823, + "step": 5032 + }, + { + "epoch": 0.53, + "learning_rate": 1.0773369889890015e-05, + "loss": 1.358, + "step": 5033 + }, + { + "epoch": 0.53, + "learning_rate": 1.07697205504862e-05, + "loss": 1.3532, + "step": 5034 + }, + { + "epoch": 0.53, + "learning_rate": 1.0766071107959608e-05, + "loss": 1.3432, + "step": 5035 + }, + { + "epoch": 0.53, + "learning_rate": 1.0762421562799173e-05, + "loss": 1.3575, + "step": 5036 + }, + { + "epoch": 0.53, + "learning_rate": 1.0758771915493838e-05, + "loss": 1.0924, + "step": 5037 + }, + { + "epoch": 0.53, + "learning_rate": 1.075512216653256e-05, + "loss": 0.7405, + "step": 5038 + }, + { + "epoch": 0.53, + "learning_rate": 1.0751472316404315e-05, + "loss": 0.7134, + "step": 5039 + }, + { + "epoch": 0.53, + "learning_rate": 1.0747822365598088e-05, + "loss": 1.0904, + "step": 5040 + }, + { + "epoch": 0.53, + "learning_rate": 1.0744172314602881e-05, + "loss": 1.4353, + "step": 5041 + }, + { + "epoch": 0.53, + "learning_rate": 1.0740522163907702e-05, + "loss": 1.361, + "step": 5042 + }, + { + "epoch": 0.53, + "learning_rate": 1.073687191400158e-05, + "loss": 1.4024, + "step": 5043 + }, + { + "epoch": 0.53, + "learning_rate": 1.0733221565373557e-05, + "loss": 1.328, + "step": 5044 + }, + { + "epoch": 0.53, + "learning_rate": 1.0729571118512683e-05, + "loss": 1.3309, + "step": 5045 + }, + { + "epoch": 0.53, + "learning_rate": 1.0725920573908024e-05, + "loss": 1.3819, + "step": 5046 + }, + { + "epoch": 0.53, + "learning_rate": 1.0722269932048659e-05, + "loss": 1.3467, + "step": 5047 + }, + { + "epoch": 0.53, + "learning_rate": 1.0718619193423683e-05, + "loss": 1.3036, + "step": 5048 + }, + { + "epoch": 0.53, + "learning_rate": 1.07149683585222e-05, + "loss": 1.3297, + "step": 5049 + }, + { + "epoch": 0.53, + "learning_rate": 1.0711317427833328e-05, + "loss": 1.3439, + "step": 5050 + }, + { + "epoch": 0.53, + "learning_rate": 1.0707666401846192e-05, + "loss": 1.4167, + "step": 5051 + }, + { + "epoch": 0.53, + "learning_rate": 1.0704015281049944e-05, + "loss": 1.4217, + "step": 5052 + }, + { + "epoch": 0.53, + "learning_rate": 1.070036406593374e-05, + "loss": 1.3394, + "step": 5053 + }, + { + "epoch": 0.53, + "learning_rate": 1.0696712756986745e-05, + "loss": 1.3242, + "step": 5054 + }, + { + "epoch": 0.53, + "learning_rate": 1.0693061354698143e-05, + "loss": 1.3957, + "step": 5055 + }, + { + "epoch": 0.53, + "learning_rate": 1.0689409859557123e-05, + "loss": 1.37, + "step": 5056 + }, + { + "epoch": 0.53, + "learning_rate": 1.0685758272052902e-05, + "loss": 1.4524, + "step": 5057 + }, + { + "epoch": 0.53, + "learning_rate": 1.0682106592674688e-05, + "loss": 1.528, + "step": 5058 + }, + { + "epoch": 0.53, + "learning_rate": 1.0678454821911719e-05, + "loss": 1.3613, + "step": 5059 + }, + { + "epoch": 0.53, + "learning_rate": 1.0674802960253234e-05, + "loss": 1.308, + "step": 5060 + }, + { + "epoch": 0.53, + "learning_rate": 1.0671151008188494e-05, + "loss": 1.3343, + "step": 5061 + }, + { + "epoch": 0.53, + "learning_rate": 1.066749896620676e-05, + "loss": 1.365, + "step": 5062 + }, + { + "epoch": 0.53, + "learning_rate": 1.0663846834797316e-05, + "loss": 1.4077, + "step": 5063 + }, + { + "epoch": 0.53, + "learning_rate": 1.0660194614449455e-05, + "loss": 1.324, + "step": 5064 + }, + { + "epoch": 0.53, + "learning_rate": 1.0656542305652478e-05, + "loss": 1.3623, + "step": 5065 + }, + { + "epoch": 0.53, + "learning_rate": 1.0652889908895701e-05, + "loss": 1.4079, + "step": 5066 + }, + { + "epoch": 0.53, + "learning_rate": 1.0649237424668451e-05, + "loss": 1.3089, + "step": 5067 + }, + { + "epoch": 0.53, + "learning_rate": 1.0645584853460069e-05, + "loss": 1.3967, + "step": 5068 + }, + { + "epoch": 0.53, + "learning_rate": 1.0641932195759905e-05, + "loss": 1.3639, + "step": 5069 + }, + { + "epoch": 0.53, + "learning_rate": 1.0638279452057319e-05, + "loss": 1.5919, + "step": 5070 + }, + { + "epoch": 0.53, + "learning_rate": 1.0634626622841686e-05, + "loss": 1.3348, + "step": 5071 + }, + { + "epoch": 0.53, + "learning_rate": 1.0630973708602395e-05, + "loss": 1.3146, + "step": 5072 + }, + { + "epoch": 0.53, + "learning_rate": 1.0627320709828836e-05, + "loss": 1.3375, + "step": 5073 + }, + { + "epoch": 0.53, + "learning_rate": 1.062366762701042e-05, + "loss": 1.3908, + "step": 5074 + }, + { + "epoch": 0.53, + "learning_rate": 1.0620014460636568e-05, + "loss": 1.3726, + "step": 5075 + }, + { + "epoch": 0.53, + "learning_rate": 1.061636121119671e-05, + "loss": 1.2348, + "step": 5076 + }, + { + "epoch": 0.53, + "learning_rate": 1.0612707879180284e-05, + "loss": 1.2957, + "step": 5077 + }, + { + "epoch": 0.53, + "learning_rate": 1.0609054465076749e-05, + "loss": 1.4202, + "step": 5078 + }, + { + "epoch": 0.53, + "learning_rate": 1.060540096937556e-05, + "loss": 1.5809, + "step": 5079 + }, + { + "epoch": 0.53, + "learning_rate": 1.0601747392566202e-05, + "loss": 1.3741, + "step": 5080 + }, + { + "epoch": 0.53, + "learning_rate": 1.059809373513815e-05, + "loss": 1.3537, + "step": 5081 + }, + { + "epoch": 0.53, + "learning_rate": 1.0594439997580907e-05, + "loss": 1.332, + "step": 5082 + }, + { + "epoch": 0.53, + "learning_rate": 1.0590786180383981e-05, + "loss": 1.3267, + "step": 5083 + }, + { + "epoch": 0.53, + "learning_rate": 1.0587132284036883e-05, + "loss": 1.3552, + "step": 5084 + }, + { + "epoch": 0.53, + "learning_rate": 1.0583478309029143e-05, + "loss": 1.2837, + "step": 5085 + }, + { + "epoch": 0.53, + "learning_rate": 1.0579824255850304e-05, + "loss": 1.4311, + "step": 5086 + }, + { + "epoch": 0.53, + "learning_rate": 1.0576170124989915e-05, + "loss": 1.4394, + "step": 5087 + }, + { + "epoch": 0.53, + "learning_rate": 1.0572515916937531e-05, + "loss": 1.3185, + "step": 5088 + }, + { + "epoch": 0.53, + "learning_rate": 1.0568861632182723e-05, + "loss": 1.4212, + "step": 5089 + }, + { + "epoch": 0.53, + "learning_rate": 1.0565207271215075e-05, + "loss": 1.0951, + "step": 5090 + }, + { + "epoch": 0.53, + "learning_rate": 1.0561552834524176e-05, + "loss": 1.4174, + "step": 5091 + }, + { + "epoch": 0.53, + "learning_rate": 1.0557898322599624e-05, + "loss": 1.3349, + "step": 5092 + }, + { + "epoch": 0.53, + "learning_rate": 1.0554243735931031e-05, + "loss": 1.399, + "step": 5093 + }, + { + "epoch": 0.53, + "learning_rate": 1.055058907500802e-05, + "loss": 1.4016, + "step": 5094 + }, + { + "epoch": 0.53, + "learning_rate": 1.0546934340320219e-05, + "loss": 1.3227, + "step": 5095 + }, + { + "epoch": 0.53, + "learning_rate": 1.0543279532357269e-05, + "loss": 1.4017, + "step": 5096 + }, + { + "epoch": 0.53, + "learning_rate": 1.053962465160882e-05, + "loss": 1.3937, + "step": 5097 + }, + { + "epoch": 0.53, + "learning_rate": 1.0535969698564532e-05, + "loss": 1.2405, + "step": 5098 + }, + { + "epoch": 0.53, + "learning_rate": 1.0532314673714081e-05, + "loss": 1.2939, + "step": 5099 + }, + { + "epoch": 0.53, + "learning_rate": 1.0528659577547136e-05, + "loss": 1.4165, + "step": 5100 + }, + { + "epoch": 0.53, + "learning_rate": 1.0525004410553394e-05, + "loss": 1.309, + "step": 5101 + }, + { + "epoch": 0.54, + "learning_rate": 1.0521349173222549e-05, + "loss": 1.4078, + "step": 5102 + }, + { + "epoch": 0.54, + "learning_rate": 1.0517693866044312e-05, + "loss": 1.4026, + "step": 5103 + }, + { + "epoch": 0.54, + "learning_rate": 1.0514038489508396e-05, + "loss": 1.3098, + "step": 5104 + }, + { + "epoch": 0.54, + "learning_rate": 1.0510383044104533e-05, + "loss": 1.2886, + "step": 5105 + }, + { + "epoch": 0.54, + "learning_rate": 1.0506727530322454e-05, + "loss": 1.3114, + "step": 5106 + }, + { + "epoch": 0.54, + "learning_rate": 1.0503071948651908e-05, + "loss": 1.2823, + "step": 5107 + }, + { + "epoch": 0.54, + "learning_rate": 1.0499416299582643e-05, + "loss": 1.4654, + "step": 5108 + }, + { + "epoch": 0.54, + "learning_rate": 1.0495760583604431e-05, + "loss": 1.4043, + "step": 5109 + }, + { + "epoch": 0.54, + "learning_rate": 1.0492104801207035e-05, + "loss": 1.3113, + "step": 5110 + }, + { + "epoch": 0.54, + "learning_rate": 1.0488448952880243e-05, + "loss": 1.3285, + "step": 5111 + }, + { + "epoch": 0.54, + "learning_rate": 1.048479303911384e-05, + "loss": 1.3918, + "step": 5112 + }, + { + "epoch": 0.54, + "learning_rate": 1.0481137060397623e-05, + "loss": 1.346, + "step": 5113 + }, + { + "epoch": 0.54, + "learning_rate": 1.0477481017221407e-05, + "loss": 1.3777, + "step": 5114 + }, + { + "epoch": 0.54, + "learning_rate": 1.0473824910075003e-05, + "loss": 1.3494, + "step": 5115 + }, + { + "epoch": 0.54, + "learning_rate": 1.0470168739448232e-05, + "loss": 1.4173, + "step": 5116 + }, + { + "epoch": 0.54, + "learning_rate": 1.0466512505830932e-05, + "loss": 1.4313, + "step": 5117 + }, + { + "epoch": 0.54, + "learning_rate": 1.0462856209712944e-05, + "loss": 1.335, + "step": 5118 + }, + { + "epoch": 0.54, + "learning_rate": 1.0459199851584117e-05, + "loss": 1.37, + "step": 5119 + }, + { + "epoch": 0.54, + "learning_rate": 1.0455543431934307e-05, + "loss": 1.3504, + "step": 5120 + }, + { + "epoch": 0.54, + "learning_rate": 1.0451886951253381e-05, + "loss": 1.4148, + "step": 5121 + }, + { + "epoch": 0.54, + "learning_rate": 1.0448230410031218e-05, + "loss": 1.3974, + "step": 5122 + }, + { + "epoch": 0.54, + "learning_rate": 1.0444573808757694e-05, + "loss": 1.3644, + "step": 5123 + }, + { + "epoch": 0.54, + "learning_rate": 1.0440917147922705e-05, + "loss": 1.4024, + "step": 5124 + }, + { + "epoch": 0.54, + "learning_rate": 1.0437260428016143e-05, + "loss": 1.3925, + "step": 5125 + }, + { + "epoch": 0.54, + "learning_rate": 1.0433603649527923e-05, + "loss": 1.2907, + "step": 5126 + }, + { + "epoch": 0.54, + "learning_rate": 1.0429946812947953e-05, + "loss": 1.3453, + "step": 5127 + }, + { + "epoch": 0.54, + "learning_rate": 1.0426289918766157e-05, + "loss": 1.3856, + "step": 5128 + }, + { + "epoch": 0.54, + "learning_rate": 1.0422632967472465e-05, + "loss": 1.3309, + "step": 5129 + }, + { + "epoch": 0.54, + "learning_rate": 1.0418975959556819e-05, + "loss": 1.3757, + "step": 5130 + }, + { + "epoch": 0.54, + "learning_rate": 1.0415318895509152e-05, + "loss": 1.406, + "step": 5131 + }, + { + "epoch": 0.54, + "learning_rate": 1.041166177581943e-05, + "loss": 1.3265, + "step": 5132 + }, + { + "epoch": 0.54, + "learning_rate": 1.0408004600977606e-05, + "loss": 1.3377, + "step": 5133 + }, + { + "epoch": 0.54, + "learning_rate": 1.040434737147365e-05, + "loss": 1.3647, + "step": 5134 + }, + { + "epoch": 0.54, + "learning_rate": 1.0400690087797531e-05, + "loss": 1.3262, + "step": 5135 + }, + { + "epoch": 0.54, + "learning_rate": 1.039703275043924e-05, + "loss": 1.3924, + "step": 5136 + }, + { + "epoch": 0.54, + "learning_rate": 1.039337535988876e-05, + "loss": 1.3018, + "step": 5137 + }, + { + "epoch": 0.54, + "learning_rate": 1.038971791663609e-05, + "loss": 1.385, + "step": 5138 + }, + { + "epoch": 0.54, + "learning_rate": 1.0386060421171232e-05, + "loss": 1.3435, + "step": 5139 + }, + { + "epoch": 0.54, + "learning_rate": 1.0382402873984197e-05, + "loss": 1.4023, + "step": 5140 + }, + { + "epoch": 0.54, + "learning_rate": 1.0378745275565003e-05, + "loss": 1.369, + "step": 5141 + }, + { + "epoch": 0.54, + "learning_rate": 1.0375087626403675e-05, + "loss": 1.3199, + "step": 5142 + }, + { + "epoch": 0.54, + "learning_rate": 1.037142992699024e-05, + "loss": 1.4247, + "step": 5143 + }, + { + "epoch": 0.54, + "learning_rate": 1.0367772177814736e-05, + "loss": 1.4015, + "step": 5144 + }, + { + "epoch": 0.54, + "learning_rate": 1.0364114379367217e-05, + "loss": 1.3519, + "step": 5145 + }, + { + "epoch": 0.54, + "learning_rate": 1.0360456532137722e-05, + "loss": 1.3478, + "step": 5146 + }, + { + "epoch": 0.54, + "learning_rate": 1.0356798636616314e-05, + "loss": 1.4876, + "step": 5147 + }, + { + "epoch": 0.54, + "learning_rate": 1.0353140693293056e-05, + "loss": 1.6481, + "step": 5148 + }, + { + "epoch": 0.54, + "learning_rate": 1.034948270265802e-05, + "loss": 1.3851, + "step": 5149 + }, + { + "epoch": 0.54, + "learning_rate": 1.0345824665201281e-05, + "loss": 1.4037, + "step": 5150 + }, + { + "epoch": 0.54, + "learning_rate": 1.0342166581412923e-05, + "loss": 1.3138, + "step": 5151 + }, + { + "epoch": 0.54, + "learning_rate": 1.0338508451783032e-05, + "loss": 1.3536, + "step": 5152 + }, + { + "epoch": 0.54, + "learning_rate": 1.0334850276801712e-05, + "loss": 1.3244, + "step": 5153 + }, + { + "epoch": 0.54, + "learning_rate": 1.0331192056959052e-05, + "loss": 1.3677, + "step": 5154 + }, + { + "epoch": 0.54, + "learning_rate": 1.032753379274517e-05, + "loss": 1.3439, + "step": 5155 + }, + { + "epoch": 0.54, + "learning_rate": 1.0323875484650171e-05, + "loss": 1.365, + "step": 5156 + }, + { + "epoch": 0.54, + "learning_rate": 1.0320217133164186e-05, + "loss": 1.3838, + "step": 5157 + }, + { + "epoch": 0.54, + "learning_rate": 1.0316558738777328e-05, + "loss": 1.3312, + "step": 5158 + }, + { + "epoch": 0.54, + "learning_rate": 1.0312900301979733e-05, + "loss": 1.369, + "step": 5159 + }, + { + "epoch": 0.54, + "learning_rate": 1.030924182326154e-05, + "loss": 1.2712, + "step": 5160 + }, + { + "epoch": 0.54, + "learning_rate": 1.0305583303112887e-05, + "loss": 1.3141, + "step": 5161 + }, + { + "epoch": 0.54, + "learning_rate": 1.030192474202392e-05, + "loss": 1.3708, + "step": 5162 + }, + { + "epoch": 0.54, + "learning_rate": 1.0298266140484798e-05, + "loss": 1.3724, + "step": 5163 + }, + { + "epoch": 0.54, + "learning_rate": 1.0294607498985678e-05, + "loss": 1.3208, + "step": 5164 + }, + { + "epoch": 0.54, + "learning_rate": 1.0290948818016722e-05, + "loss": 1.3379, + "step": 5165 + }, + { + "epoch": 0.54, + "learning_rate": 1.0287290098068099e-05, + "loss": 1.3236, + "step": 5166 + }, + { + "epoch": 0.54, + "learning_rate": 1.0283631339629982e-05, + "loss": 1.3437, + "step": 5167 + }, + { + "epoch": 0.54, + "learning_rate": 1.0279972543192561e-05, + "loss": 1.3381, + "step": 5168 + }, + { + "epoch": 0.54, + "learning_rate": 1.0276313709246007e-05, + "loss": 1.4287, + "step": 5169 + }, + { + "epoch": 0.54, + "learning_rate": 1.0272654838280515e-05, + "loss": 1.3587, + "step": 5170 + }, + { + "epoch": 0.54, + "learning_rate": 1.0268995930786283e-05, + "loss": 1.2982, + "step": 5171 + }, + { + "epoch": 0.54, + "learning_rate": 1.0265336987253509e-05, + "loss": 1.3416, + "step": 5172 + }, + { + "epoch": 0.54, + "learning_rate": 1.0261678008172393e-05, + "loss": 1.3827, + "step": 5173 + }, + { + "epoch": 0.54, + "learning_rate": 1.025801899403315e-05, + "loss": 1.3293, + "step": 5174 + }, + { + "epoch": 0.54, + "eval_loss": 1.4264723062515259, + "eval_runtime": 77.4376, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 5174 + }, + { + "epoch": 0.54, + "learning_rate": 1.0254359945325987e-05, + "loss": 1.3811, + "step": 5175 + }, + { + "epoch": 0.54, + "learning_rate": 1.0250700862541135e-05, + "loss": 1.3423, + "step": 5176 + }, + { + "epoch": 0.54, + "learning_rate": 1.02470417461688e-05, + "loss": 1.3641, + "step": 5177 + }, + { + "epoch": 0.54, + "learning_rate": 1.0243382596699226e-05, + "loss": 1.3211, + "step": 5178 + }, + { + "epoch": 0.54, + "learning_rate": 1.023972341462263e-05, + "loss": 1.4008, + "step": 5179 + }, + { + "epoch": 0.54, + "learning_rate": 1.0236064200429263e-05, + "loss": 1.404, + "step": 5180 + }, + { + "epoch": 0.54, + "learning_rate": 1.0232404954609353e-05, + "loss": 1.3359, + "step": 5181 + }, + { + "epoch": 0.54, + "learning_rate": 1.0228745677653155e-05, + "loss": 1.4069, + "step": 5182 + }, + { + "epoch": 0.54, + "learning_rate": 1.0225086370050914e-05, + "loss": 1.3343, + "step": 5183 + }, + { + "epoch": 0.54, + "learning_rate": 1.0221427032292881e-05, + "loss": 1.3109, + "step": 5184 + }, + { + "epoch": 0.54, + "learning_rate": 1.0217767664869312e-05, + "loss": 1.3611, + "step": 5185 + }, + { + "epoch": 0.54, + "learning_rate": 1.0214108268270476e-05, + "loss": 1.4072, + "step": 5186 + }, + { + "epoch": 0.54, + "learning_rate": 1.0210448842986631e-05, + "loss": 1.3602, + "step": 5187 + }, + { + "epoch": 0.54, + "learning_rate": 1.0206789389508047e-05, + "loss": 1.413, + "step": 5188 + }, + { + "epoch": 0.54, + "learning_rate": 1.0203129908325e-05, + "loss": 1.3209, + "step": 5189 + }, + { + "epoch": 0.54, + "learning_rate": 1.0199470399927764e-05, + "loss": 1.3714, + "step": 5190 + }, + { + "epoch": 0.54, + "learning_rate": 1.0195810864806623e-05, + "loss": 1.3556, + "step": 5191 + }, + { + "epoch": 0.54, + "learning_rate": 1.0192151303451852e-05, + "loss": 1.4116, + "step": 5192 + }, + { + "epoch": 0.54, + "learning_rate": 1.0188491716353745e-05, + "loss": 1.4102, + "step": 5193 + }, + { + "epoch": 0.54, + "learning_rate": 1.0184832104002592e-05, + "loss": 1.4849, + "step": 5194 + }, + { + "epoch": 0.54, + "learning_rate": 1.0181172466888689e-05, + "loss": 1.5395, + "step": 5195 + }, + { + "epoch": 0.54, + "learning_rate": 1.0177512805502325e-05, + "loss": 1.3627, + "step": 5196 + }, + { + "epoch": 0.54, + "learning_rate": 1.017385312033381e-05, + "loss": 1.4152, + "step": 5197 + }, + { + "epoch": 0.55, + "learning_rate": 1.0170193411873442e-05, + "loss": 1.3641, + "step": 5198 + }, + { + "epoch": 0.55, + "learning_rate": 1.0166533680611533e-05, + "loss": 1.3074, + "step": 5199 + }, + { + "epoch": 0.55, + "learning_rate": 1.0162873927038386e-05, + "loss": 1.35, + "step": 5200 + }, + { + "epoch": 0.55, + "learning_rate": 1.015921415164432e-05, + "loss": 1.3551, + "step": 5201 + }, + { + "epoch": 0.55, + "learning_rate": 1.0155554354919643e-05, + "loss": 1.3421, + "step": 5202 + }, + { + "epoch": 0.55, + "learning_rate": 1.0151894537354687e-05, + "loss": 1.4132, + "step": 5203 + }, + { + "epoch": 0.55, + "learning_rate": 1.0148234699439764e-05, + "loss": 1.351, + "step": 5204 + }, + { + "epoch": 0.55, + "learning_rate": 1.0144574841665198e-05, + "loss": 1.3745, + "step": 5205 + }, + { + "epoch": 0.55, + "learning_rate": 1.0140914964521316e-05, + "loss": 1.3151, + "step": 5206 + }, + { + "epoch": 0.55, + "learning_rate": 1.0137255068498456e-05, + "loss": 1.4903, + "step": 5207 + }, + { + "epoch": 0.55, + "learning_rate": 1.0133595154086937e-05, + "loss": 1.3945, + "step": 5208 + }, + { + "epoch": 0.55, + "learning_rate": 1.0129935221777104e-05, + "loss": 1.3924, + "step": 5209 + }, + { + "epoch": 0.55, + "learning_rate": 1.0126275272059286e-05, + "loss": 1.4191, + "step": 5210 + }, + { + "epoch": 0.55, + "learning_rate": 1.012261530542383e-05, + "loss": 1.3408, + "step": 5211 + }, + { + "epoch": 0.55, + "learning_rate": 1.0118955322361071e-05, + "loss": 1.3582, + "step": 5212 + }, + { + "epoch": 0.55, + "learning_rate": 1.0115295323361354e-05, + "loss": 1.3703, + "step": 5213 + }, + { + "epoch": 0.55, + "learning_rate": 1.011163530891503e-05, + "loss": 1.4181, + "step": 5214 + }, + { + "epoch": 0.55, + "learning_rate": 1.0107975279512442e-05, + "loss": 1.5019, + "step": 5215 + }, + { + "epoch": 0.55, + "learning_rate": 1.010431523564394e-05, + "loss": 1.3151, + "step": 5216 + }, + { + "epoch": 0.55, + "learning_rate": 1.0100655177799874e-05, + "loss": 1.4036, + "step": 5217 + }, + { + "epoch": 0.55, + "learning_rate": 1.0096995106470606e-05, + "loss": 1.3584, + "step": 5218 + }, + { + "epoch": 0.55, + "learning_rate": 1.0093335022146482e-05, + "loss": 1.3618, + "step": 5219 + }, + { + "epoch": 0.55, + "learning_rate": 1.0089674925317865e-05, + "loss": 1.3295, + "step": 5220 + }, + { + "epoch": 0.55, + "learning_rate": 1.0086014816475108e-05, + "loss": 1.3968, + "step": 5221 + }, + { + "epoch": 0.55, + "learning_rate": 1.0082354696108586e-05, + "loss": 1.2847, + "step": 5222 + }, + { + "epoch": 0.55, + "learning_rate": 1.007869456470864e-05, + "loss": 1.4461, + "step": 5223 + }, + { + "epoch": 0.55, + "learning_rate": 1.007503442276565e-05, + "loss": 1.3813, + "step": 5224 + }, + { + "epoch": 0.55, + "learning_rate": 1.007137427076997e-05, + "loss": 1.3833, + "step": 5225 + }, + { + "epoch": 0.55, + "learning_rate": 1.006771410921198e-05, + "loss": 1.4024, + "step": 5226 + }, + { + "epoch": 0.55, + "learning_rate": 1.0064053938582032e-05, + "loss": 1.3357, + "step": 5227 + }, + { + "epoch": 0.55, + "learning_rate": 1.0060393759370506e-05, + "loss": 1.35, + "step": 5228 + }, + { + "epoch": 0.55, + "learning_rate": 1.0056733572067765e-05, + "loss": 1.3512, + "step": 5229 + }, + { + "epoch": 0.55, + "learning_rate": 1.0053073377164186e-05, + "loss": 1.3852, + "step": 5230 + }, + { + "epoch": 0.55, + "learning_rate": 1.0049413175150135e-05, + "loss": 1.3502, + "step": 5231 + }, + { + "epoch": 0.55, + "learning_rate": 1.004575296651599e-05, + "loss": 1.4637, + "step": 5232 + }, + { + "epoch": 0.55, + "learning_rate": 1.0042092751752123e-05, + "loss": 1.3877, + "step": 5233 + }, + { + "epoch": 0.55, + "learning_rate": 1.0038432531348909e-05, + "loss": 1.3804, + "step": 5234 + }, + { + "epoch": 0.55, + "learning_rate": 1.0034772305796723e-05, + "loss": 1.3613, + "step": 5235 + }, + { + "epoch": 0.55, + "learning_rate": 1.003111207558594e-05, + "loss": 1.3218, + "step": 5236 + }, + { + "epoch": 0.55, + "learning_rate": 1.0027451841206944e-05, + "loss": 1.3554, + "step": 5237 + }, + { + "epoch": 0.55, + "learning_rate": 1.0023791603150099e-05, + "loss": 1.372, + "step": 5238 + }, + { + "epoch": 0.55, + "learning_rate": 1.0020131361905793e-05, + "loss": 1.3544, + "step": 5239 + }, + { + "epoch": 0.55, + "learning_rate": 1.0016471117964404e-05, + "loss": 1.3472, + "step": 5240 + }, + { + "epoch": 0.55, + "learning_rate": 1.001281087181631e-05, + "loss": 1.4247, + "step": 5241 + }, + { + "epoch": 0.55, + "learning_rate": 1.0009150623951883e-05, + "loss": 1.2685, + "step": 5242 + }, + { + "epoch": 0.55, + "learning_rate": 1.000549037486151e-05, + "loss": 1.4036, + "step": 5243 + }, + { + "epoch": 0.55, + "learning_rate": 1.0001830125035565e-05, + "loss": 1.3602, + "step": 5244 + }, + { + "epoch": 0.55, + "learning_rate": 9.998169874964437e-06, + "loss": 1.3784, + "step": 5245 + }, + { + "epoch": 0.55, + "learning_rate": 9.994509625138496e-06, + "loss": 1.3389, + "step": 5246 + }, + { + "epoch": 0.55, + "learning_rate": 9.990849376048119e-06, + "loss": 1.4561, + "step": 5247 + }, + { + "epoch": 0.55, + "learning_rate": 9.987189128183695e-06, + "loss": 1.3876, + "step": 5248 + }, + { + "epoch": 0.55, + "learning_rate": 9.9835288820356e-06, + "loss": 1.3362, + "step": 5249 + }, + { + "epoch": 0.55, + "learning_rate": 9.97986863809421e-06, + "loss": 1.3449, + "step": 5250 + }, + { + "epoch": 0.55, + "learning_rate": 9.9762083968499e-06, + "loss": 1.3521, + "step": 5251 + }, + { + "epoch": 0.55, + "learning_rate": 9.972548158793061e-06, + "loss": 1.4452, + "step": 5252 + }, + { + "epoch": 0.55, + "learning_rate": 9.968887924414062e-06, + "loss": 1.4126, + "step": 5253 + }, + { + "epoch": 0.55, + "learning_rate": 9.965227694203282e-06, + "loss": 1.3054, + "step": 5254 + }, + { + "epoch": 0.55, + "learning_rate": 9.961567468651093e-06, + "loss": 1.3771, + "step": 5255 + }, + { + "epoch": 0.55, + "learning_rate": 9.957907248247878e-06, + "loss": 1.3566, + "step": 5256 + }, + { + "epoch": 0.55, + "learning_rate": 9.954247033484014e-06, + "loss": 1.4765, + "step": 5257 + }, + { + "epoch": 0.55, + "learning_rate": 9.950586824849865e-06, + "loss": 1.4749, + "step": 5258 + }, + { + "epoch": 0.55, + "learning_rate": 9.946926622835815e-06, + "loss": 1.3679, + "step": 5259 + }, + { + "epoch": 0.55, + "learning_rate": 9.943266427932238e-06, + "loss": 1.2671, + "step": 5260 + }, + { + "epoch": 0.55, + "learning_rate": 9.9396062406295e-06, + "loss": 1.3485, + "step": 5261 + }, + { + "epoch": 0.55, + "learning_rate": 9.935946061417968e-06, + "loss": 1.3136, + "step": 5262 + }, + { + "epoch": 0.55, + "learning_rate": 9.932285890788024e-06, + "loss": 1.3954, + "step": 5263 + }, + { + "epoch": 0.55, + "learning_rate": 9.928625729230031e-06, + "loss": 1.428, + "step": 5264 + }, + { + "epoch": 0.55, + "learning_rate": 9.924965577234356e-06, + "loss": 1.4144, + "step": 5265 + }, + { + "epoch": 0.55, + "learning_rate": 9.92130543529136e-06, + "loss": 1.3361, + "step": 5266 + }, + { + "epoch": 0.55, + "learning_rate": 9.91764530389142e-06, + "loss": 1.4503, + "step": 5267 + }, + { + "epoch": 0.55, + "learning_rate": 9.913985183524893e-06, + "loss": 1.3431, + "step": 5268 + }, + { + "epoch": 0.55, + "learning_rate": 9.91032507468214e-06, + "loss": 1.3206, + "step": 5269 + }, + { + "epoch": 0.55, + "learning_rate": 9.906664977853518e-06, + "loss": 1.4568, + "step": 5270 + }, + { + "epoch": 0.55, + "learning_rate": 9.903004893529397e-06, + "loss": 1.3591, + "step": 5271 + }, + { + "epoch": 0.55, + "learning_rate": 9.899344822200127e-06, + "loss": 1.3382, + "step": 5272 + }, + { + "epoch": 0.55, + "learning_rate": 9.895684764356066e-06, + "loss": 1.3008, + "step": 5273 + }, + { + "epoch": 0.55, + "learning_rate": 9.89202472048756e-06, + "loss": 1.316, + "step": 5274 + }, + { + "epoch": 0.55, + "learning_rate": 9.888364691084971e-06, + "loss": 1.4246, + "step": 5275 + }, + { + "epoch": 0.55, + "learning_rate": 9.88470467663865e-06, + "loss": 1.3615, + "step": 5276 + }, + { + "epoch": 0.55, + "learning_rate": 9.881044677638934e-06, + "loss": 1.3418, + "step": 5277 + }, + { + "epoch": 0.55, + "learning_rate": 9.877384694576172e-06, + "loss": 1.249, + "step": 5278 + }, + { + "epoch": 0.55, + "learning_rate": 9.873724727940715e-06, + "loss": 1.2779, + "step": 5279 + }, + { + "epoch": 0.55, + "learning_rate": 9.870064778222903e-06, + "loss": 1.3529, + "step": 5280 + }, + { + "epoch": 0.55, + "learning_rate": 9.866404845913065e-06, + "loss": 1.3204, + "step": 5281 + }, + { + "epoch": 0.55, + "learning_rate": 9.862744931501548e-06, + "loss": 1.3537, + "step": 5282 + }, + { + "epoch": 0.55, + "learning_rate": 9.859085035478687e-06, + "loss": 1.3681, + "step": 5283 + }, + { + "epoch": 0.55, + "learning_rate": 9.855425158334809e-06, + "loss": 1.3983, + "step": 5284 + }, + { + "epoch": 0.55, + "learning_rate": 9.851765300560238e-06, + "loss": 1.401, + "step": 5285 + }, + { + "epoch": 0.55, + "learning_rate": 9.848105462645315e-06, + "loss": 1.3073, + "step": 5286 + }, + { + "epoch": 0.55, + "learning_rate": 9.844445645080358e-06, + "loss": 1.3162, + "step": 5287 + }, + { + "epoch": 0.55, + "learning_rate": 9.840785848355685e-06, + "loss": 1.3345, + "step": 5288 + }, + { + "epoch": 0.55, + "learning_rate": 9.837126072961616e-06, + "loss": 1.4241, + "step": 5289 + }, + { + "epoch": 0.55, + "learning_rate": 9.83346631938847e-06, + "loss": 1.3339, + "step": 5290 + }, + { + "epoch": 0.55, + "learning_rate": 9.829806588126561e-06, + "loss": 1.3507, + "step": 5291 + }, + { + "epoch": 0.55, + "learning_rate": 9.826146879666196e-06, + "loss": 1.2806, + "step": 5292 + }, + { + "epoch": 0.56, + "learning_rate": 9.822487194497675e-06, + "loss": 1.3952, + "step": 5293 + }, + { + "epoch": 0.56, + "learning_rate": 9.818827533111314e-06, + "loss": 1.3319, + "step": 5294 + }, + { + "epoch": 0.56, + "learning_rate": 9.81516789599741e-06, + "loss": 1.351, + "step": 5295 + }, + { + "epoch": 0.56, + "learning_rate": 9.811508283646258e-06, + "loss": 1.4076, + "step": 5296 + }, + { + "epoch": 0.56, + "learning_rate": 9.80784869654815e-06, + "loss": 1.3271, + "step": 5297 + }, + { + "epoch": 0.56, + "learning_rate": 9.80418913519338e-06, + "loss": 1.4059, + "step": 5298 + }, + { + "epoch": 0.56, + "learning_rate": 9.80052960007224e-06, + "loss": 1.4146, + "step": 5299 + }, + { + "epoch": 0.56, + "learning_rate": 9.796870091675005e-06, + "loss": 1.3454, + "step": 5300 + }, + { + "epoch": 0.56, + "learning_rate": 9.793210610491953e-06, + "loss": 1.4376, + "step": 5301 + }, + { + "epoch": 0.56, + "learning_rate": 9.789551157013372e-06, + "loss": 1.3437, + "step": 5302 + }, + { + "epoch": 0.56, + "learning_rate": 9.78589173172953e-06, + "loss": 1.3073, + "step": 5303 + }, + { + "epoch": 0.56, + "learning_rate": 9.782232335130688e-06, + "loss": 1.2989, + "step": 5304 + }, + { + "epoch": 0.56, + "learning_rate": 9.778572967707122e-06, + "loss": 1.4028, + "step": 5305 + }, + { + "epoch": 0.56, + "learning_rate": 9.77491362994909e-06, + "loss": 1.3096, + "step": 5306 + }, + { + "epoch": 0.56, + "learning_rate": 9.77125432234685e-06, + "loss": 1.3719, + "step": 5307 + }, + { + "epoch": 0.56, + "learning_rate": 9.767595045390647e-06, + "loss": 1.3271, + "step": 5308 + }, + { + "epoch": 0.56, + "learning_rate": 9.763935799570739e-06, + "loss": 1.3693, + "step": 5309 + }, + { + "epoch": 0.56, + "learning_rate": 9.760276585377371e-06, + "loss": 1.3586, + "step": 5310 + }, + { + "epoch": 0.56, + "learning_rate": 9.756617403300781e-06, + "loss": 1.3423, + "step": 5311 + }, + { + "epoch": 0.56, + "learning_rate": 9.7529582538312e-06, + "loss": 1.388, + "step": 5312 + }, + { + "epoch": 0.56, + "learning_rate": 9.74929913745887e-06, + "loss": 1.3594, + "step": 5313 + }, + { + "epoch": 0.56, + "learning_rate": 9.745640054674015e-06, + "loss": 1.2831, + "step": 5314 + }, + { + "epoch": 0.56, + "learning_rate": 9.741981005966856e-06, + "loss": 1.4207, + "step": 5315 + }, + { + "epoch": 0.56, + "learning_rate": 9.738321991827609e-06, + "loss": 1.2807, + "step": 5316 + }, + { + "epoch": 0.56, + "learning_rate": 9.734663012746493e-06, + "loss": 1.3396, + "step": 5317 + }, + { + "epoch": 0.56, + "learning_rate": 9.731004069213722e-06, + "loss": 1.3666, + "step": 5318 + }, + { + "epoch": 0.56, + "learning_rate": 9.72734516171949e-06, + "loss": 1.3466, + "step": 5319 + }, + { + "epoch": 0.56, + "learning_rate": 9.723686290753995e-06, + "loss": 1.4478, + "step": 5320 + }, + { + "epoch": 0.56, + "learning_rate": 9.720027456807442e-06, + "loss": 1.316, + "step": 5321 + }, + { + "epoch": 0.56, + "learning_rate": 9.71636866037002e-06, + "loss": 1.3762, + "step": 5322 + }, + { + "epoch": 0.56, + "learning_rate": 9.712709901931906e-06, + "loss": 1.4156, + "step": 5323 + }, + { + "epoch": 0.56, + "learning_rate": 9.70905118198328e-06, + "loss": 1.2452, + "step": 5324 + }, + { + "epoch": 0.56, + "learning_rate": 9.705392501014325e-06, + "loss": 1.3771, + "step": 5325 + }, + { + "epoch": 0.56, + "learning_rate": 9.701733859515205e-06, + "loss": 1.3433, + "step": 5326 + }, + { + "epoch": 0.56, + "learning_rate": 9.698075257976079e-06, + "loss": 1.3702, + "step": 5327 + }, + { + "epoch": 0.56, + "learning_rate": 9.694416696887115e-06, + "loss": 1.295, + "step": 5328 + }, + { + "epoch": 0.56, + "learning_rate": 9.690758176738463e-06, + "loss": 1.3462, + "step": 5329 + }, + { + "epoch": 0.56, + "learning_rate": 9.68709969802027e-06, + "loss": 1.5304, + "step": 5330 + }, + { + "epoch": 0.56, + "learning_rate": 9.683441261222672e-06, + "loss": 1.3518, + "step": 5331 + }, + { + "epoch": 0.56, + "learning_rate": 9.679782866835816e-06, + "loss": 1.3778, + "step": 5332 + }, + { + "epoch": 0.56, + "learning_rate": 9.67612451534983e-06, + "loss": 1.3731, + "step": 5333 + }, + { + "epoch": 0.56, + "learning_rate": 9.672466207254837e-06, + "loss": 1.3315, + "step": 5334 + }, + { + "epoch": 0.56, + "learning_rate": 9.66880794304095e-06, + "loss": 1.3105, + "step": 5335 + }, + { + "epoch": 0.56, + "learning_rate": 9.665149723198293e-06, + "loss": 1.3903, + "step": 5336 + }, + { + "epoch": 0.56, + "learning_rate": 9.661491548216972e-06, + "loss": 1.3554, + "step": 5337 + }, + { + "epoch": 0.56, + "learning_rate": 9.657833418587084e-06, + "loss": 1.3231, + "step": 5338 + }, + { + "epoch": 0.56, + "learning_rate": 9.65417533479872e-06, + "loss": 1.352, + "step": 5339 + }, + { + "epoch": 0.56, + "learning_rate": 9.650517297341983e-06, + "loss": 1.3957, + "step": 5340 + }, + { + "epoch": 0.56, + "learning_rate": 9.646859306706948e-06, + "loss": 1.3938, + "step": 5341 + }, + { + "epoch": 0.56, + "learning_rate": 9.643201363383693e-06, + "loss": 1.3038, + "step": 5342 + }, + { + "epoch": 0.56, + "learning_rate": 9.63954346786228e-06, + "loss": 1.2973, + "step": 5343 + }, + { + "epoch": 0.56, + "learning_rate": 9.635885620632786e-06, + "loss": 1.379, + "step": 5344 + }, + { + "epoch": 0.56, + "learning_rate": 9.632227822185266e-06, + "loss": 1.5377, + "step": 5345 + }, + { + "epoch": 0.56, + "learning_rate": 9.628570073009767e-06, + "loss": 1.4573, + "step": 5346 + }, + { + "epoch": 0.56, + "learning_rate": 9.624912373596329e-06, + "loss": 1.3394, + "step": 5347 + }, + { + "epoch": 0.56, + "learning_rate": 9.621254724434999e-06, + "loss": 1.4157, + "step": 5348 + }, + { + "epoch": 0.56, + "learning_rate": 9.617597126015808e-06, + "loss": 1.3526, + "step": 5349 + }, + { + "epoch": 0.56, + "learning_rate": 9.61393957882877e-06, + "loss": 1.3795, + "step": 5350 + }, + { + "epoch": 0.56, + "learning_rate": 9.610282083363913e-06, + "loss": 1.3765, + "step": 5351 + }, + { + "epoch": 0.56, + "learning_rate": 9.606624640111243e-06, + "loss": 1.3512, + "step": 5352 + }, + { + "epoch": 0.56, + "learning_rate": 9.602967249560766e-06, + "loss": 1.3298, + "step": 5353 + }, + { + "epoch": 0.56, + "learning_rate": 9.599309912202469e-06, + "loss": 1.3093, + "step": 5354 + }, + { + "epoch": 0.56, + "learning_rate": 9.595652628526354e-06, + "loss": 1.3353, + "step": 5355 + }, + { + "epoch": 0.56, + "learning_rate": 9.591995399022397e-06, + "loss": 1.3081, + "step": 5356 + }, + { + "epoch": 0.56, + "learning_rate": 9.588338224180576e-06, + "loss": 1.343, + "step": 5357 + }, + { + "epoch": 0.56, + "learning_rate": 9.584681104490848e-06, + "loss": 1.3275, + "step": 5358 + }, + { + "epoch": 0.56, + "learning_rate": 9.581024040443185e-06, + "loss": 1.3399, + "step": 5359 + }, + { + "epoch": 0.56, + "learning_rate": 9.577367032527538e-06, + "loss": 1.3181, + "step": 5360 + }, + { + "epoch": 0.56, + "learning_rate": 9.573710081233846e-06, + "loss": 1.3531, + "step": 5361 + }, + { + "epoch": 0.56, + "learning_rate": 9.570053187052049e-06, + "loss": 1.4056, + "step": 5362 + }, + { + "epoch": 0.56, + "learning_rate": 9.566396350472079e-06, + "loss": 1.3303, + "step": 5363 + }, + { + "epoch": 0.56, + "learning_rate": 9.56273957198386e-06, + "loss": 1.3506, + "step": 5364 + }, + { + "epoch": 0.56, + "learning_rate": 9.559082852077302e-06, + "loss": 1.4588, + "step": 5365 + }, + { + "epoch": 0.56, + "learning_rate": 9.555426191242307e-06, + "loss": 1.3434, + "step": 5366 + }, + { + "epoch": 0.56, + "learning_rate": 9.551769589968784e-06, + "loss": 1.3508, + "step": 5367 + }, + { + "epoch": 0.56, + "learning_rate": 9.548113048746622e-06, + "loss": 1.3701, + "step": 5368 + }, + { + "epoch": 0.56, + "learning_rate": 9.544456568065698e-06, + "loss": 1.3664, + "step": 5369 + }, + { + "epoch": 0.56, + "learning_rate": 9.540800148415885e-06, + "loss": 1.6697, + "step": 5370 + }, + { + "epoch": 0.56, + "learning_rate": 9.537143790287057e-06, + "loss": 1.5298, + "step": 5371 + }, + { + "epoch": 0.56, + "learning_rate": 9.533487494169073e-06, + "loss": 1.3884, + "step": 5372 + }, + { + "epoch": 0.56, + "learning_rate": 9.52983126055177e-06, + "loss": 1.403, + "step": 5373 + }, + { + "epoch": 0.56, + "eval_loss": 1.4240995645523071, + "eval_runtime": 77.4615, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 5373 + }, + { + "epoch": 0.56, + "learning_rate": 9.526175089925e-06, + "loss": 1.3141, + "step": 5374 + }, + { + "epoch": 0.56, + "learning_rate": 9.522518982778596e-06, + "loss": 1.3733, + "step": 5375 + }, + { + "epoch": 0.56, + "learning_rate": 9.51886293960238e-06, + "loss": 1.3095, + "step": 5376 + }, + { + "epoch": 0.56, + "learning_rate": 9.515206960886162e-06, + "loss": 1.3713, + "step": 5377 + }, + { + "epoch": 0.56, + "learning_rate": 9.51155104711976e-06, + "loss": 1.3585, + "step": 5378 + }, + { + "epoch": 0.56, + "learning_rate": 9.507895198792967e-06, + "loss": 1.3473, + "step": 5379 + }, + { + "epoch": 0.56, + "learning_rate": 9.504239416395576e-06, + "loss": 1.3282, + "step": 5380 + }, + { + "epoch": 0.56, + "learning_rate": 9.500583700417357e-06, + "loss": 1.3655, + "step": 5381 + }, + { + "epoch": 0.56, + "learning_rate": 9.496928051348095e-06, + "loss": 1.4512, + "step": 5382 + }, + { + "epoch": 0.56, + "learning_rate": 9.49327246967755e-06, + "loss": 1.4071, + "step": 5383 + }, + { + "epoch": 0.56, + "learning_rate": 9.489616955895472e-06, + "loss": 1.3703, + "step": 5384 + }, + { + "epoch": 0.56, + "learning_rate": 9.485961510491604e-06, + "loss": 1.3358, + "step": 5385 + }, + { + "epoch": 0.56, + "learning_rate": 9.482306133955691e-06, + "loss": 1.3505, + "step": 5386 + }, + { + "epoch": 0.56, + "learning_rate": 9.478650826777457e-06, + "loss": 1.2578, + "step": 5387 + }, + { + "epoch": 0.57, + "learning_rate": 9.474995589446612e-06, + "loss": 1.4298, + "step": 5388 + }, + { + "epoch": 0.57, + "learning_rate": 9.471340422452864e-06, + "loss": 1.4044, + "step": 5389 + }, + { + "epoch": 0.57, + "learning_rate": 9.467685326285922e-06, + "loss": 1.3524, + "step": 5390 + }, + { + "epoch": 0.57, + "learning_rate": 9.46403030143547e-06, + "loss": 1.3017, + "step": 5391 + }, + { + "epoch": 0.57, + "learning_rate": 9.460375348391185e-06, + "loss": 1.3361, + "step": 5392 + }, + { + "epoch": 0.57, + "learning_rate": 9.456720467642733e-06, + "loss": 1.3182, + "step": 5393 + }, + { + "epoch": 0.57, + "learning_rate": 9.453065659679785e-06, + "loss": 1.3869, + "step": 5394 + }, + { + "epoch": 0.57, + "learning_rate": 9.449410924991986e-06, + "loss": 1.3161, + "step": 5395 + }, + { + "epoch": 0.57, + "learning_rate": 9.44575626406897e-06, + "loss": 1.3, + "step": 5396 + }, + { + "epoch": 0.57, + "learning_rate": 9.442101677400378e-06, + "loss": 1.5103, + "step": 5397 + }, + { + "epoch": 0.57, + "learning_rate": 9.438447165475828e-06, + "loss": 1.3511, + "step": 5398 + }, + { + "epoch": 0.57, + "learning_rate": 9.43479272878493e-06, + "loss": 1.3461, + "step": 5399 + }, + { + "epoch": 0.57, + "learning_rate": 9.431138367817277e-06, + "loss": 1.2657, + "step": 5400 + }, + { + "epoch": 0.57, + "learning_rate": 9.427484083062472e-06, + "loss": 1.3736, + "step": 5401 + }, + { + "epoch": 0.57, + "learning_rate": 9.423829875010089e-06, + "loss": 1.3476, + "step": 5402 + }, + { + "epoch": 0.57, + "learning_rate": 9.4201757441497e-06, + "loss": 1.3495, + "step": 5403 + }, + { + "epoch": 0.57, + "learning_rate": 9.416521690970857e-06, + "loss": 1.387, + "step": 5404 + }, + { + "epoch": 0.57, + "learning_rate": 9.41286771596312e-06, + "loss": 1.2829, + "step": 5405 + }, + { + "epoch": 0.57, + "learning_rate": 9.409213819616022e-06, + "loss": 1.3544, + "step": 5406 + }, + { + "epoch": 0.57, + "learning_rate": 9.405560002419098e-06, + "loss": 1.3202, + "step": 5407 + }, + { + "epoch": 0.57, + "learning_rate": 9.40190626486185e-06, + "loss": 1.3034, + "step": 5408 + }, + { + "epoch": 0.57, + "learning_rate": 9.398252607433801e-06, + "loss": 1.3223, + "step": 5409 + }, + { + "epoch": 0.57, + "learning_rate": 9.394599030624443e-06, + "loss": 1.3327, + "step": 5410 + }, + { + "epoch": 0.57, + "learning_rate": 9.390945534923258e-06, + "loss": 1.3248, + "step": 5411 + }, + { + "epoch": 0.57, + "learning_rate": 9.387292120819716e-06, + "loss": 1.3084, + "step": 5412 + }, + { + "epoch": 0.57, + "learning_rate": 9.383638788803291e-06, + "loss": 1.344, + "step": 5413 + }, + { + "epoch": 0.57, + "learning_rate": 9.379985539363436e-06, + "loss": 1.3354, + "step": 5414 + }, + { + "epoch": 0.57, + "learning_rate": 9.376332372989586e-06, + "loss": 1.3291, + "step": 5415 + }, + { + "epoch": 0.57, + "learning_rate": 9.372679290171167e-06, + "loss": 1.3468, + "step": 5416 + }, + { + "epoch": 0.57, + "learning_rate": 9.36902629139761e-06, + "loss": 1.3481, + "step": 5417 + }, + { + "epoch": 0.57, + "learning_rate": 9.36537337715832e-06, + "loss": 1.3309, + "step": 5418 + }, + { + "epoch": 0.57, + "learning_rate": 9.361720547942683e-06, + "loss": 1.362, + "step": 5419 + }, + { + "epoch": 0.57, + "learning_rate": 9.358067804240098e-06, + "loss": 1.3647, + "step": 5420 + }, + { + "epoch": 0.57, + "learning_rate": 9.354415146539933e-06, + "loss": 1.4511, + "step": 5421 + }, + { + "epoch": 0.57, + "learning_rate": 9.350762575331554e-06, + "loss": 1.3379, + "step": 5422 + }, + { + "epoch": 0.57, + "learning_rate": 9.3471100911043e-06, + "loss": 1.5468, + "step": 5423 + }, + { + "epoch": 0.57, + "learning_rate": 9.343457694347524e-06, + "loss": 1.4259, + "step": 5424 + }, + { + "epoch": 0.57, + "learning_rate": 9.339805385550548e-06, + "loss": 1.3816, + "step": 5425 + }, + { + "epoch": 0.57, + "learning_rate": 9.336153165202689e-06, + "loss": 1.3627, + "step": 5426 + }, + { + "epoch": 0.57, + "learning_rate": 9.332501033793242e-06, + "loss": 1.3338, + "step": 5427 + }, + { + "epoch": 0.57, + "learning_rate": 9.328848991811509e-06, + "loss": 1.2946, + "step": 5428 + }, + { + "epoch": 0.57, + "learning_rate": 9.325197039746769e-06, + "loss": 1.3405, + "step": 5429 + }, + { + "epoch": 0.57, + "learning_rate": 9.321545178088288e-06, + "loss": 1.3549, + "step": 5430 + }, + { + "epoch": 0.57, + "learning_rate": 9.317893407325314e-06, + "loss": 1.3225, + "step": 5431 + }, + { + "epoch": 0.57, + "learning_rate": 9.314241727947101e-06, + "loss": 1.3457, + "step": 5432 + }, + { + "epoch": 0.57, + "learning_rate": 9.310590140442878e-06, + "loss": 1.311, + "step": 5433 + }, + { + "epoch": 0.57, + "learning_rate": 9.306938645301862e-06, + "loss": 1.3615, + "step": 5434 + }, + { + "epoch": 0.57, + "learning_rate": 9.303287243013255e-06, + "loss": 1.3495, + "step": 5435 + }, + { + "epoch": 0.57, + "learning_rate": 9.29963593406626e-06, + "loss": 1.3899, + "step": 5436 + }, + { + "epoch": 0.57, + "learning_rate": 9.295984718950058e-06, + "loss": 1.3189, + "step": 5437 + }, + { + "epoch": 0.57, + "learning_rate": 9.292333598153813e-06, + "loss": 1.4199, + "step": 5438 + }, + { + "epoch": 0.57, + "learning_rate": 9.288682572166677e-06, + "loss": 1.4751, + "step": 5439 + }, + { + "epoch": 0.57, + "learning_rate": 9.285031641477804e-06, + "loss": 1.3435, + "step": 5440 + }, + { + "epoch": 0.57, + "learning_rate": 9.281380806576322e-06, + "loss": 1.2954, + "step": 5441 + }, + { + "epoch": 0.57, + "learning_rate": 9.277730067951341e-06, + "loss": 1.3414, + "step": 5442 + }, + { + "epoch": 0.57, + "learning_rate": 9.274079426091978e-06, + "loss": 1.3642, + "step": 5443 + }, + { + "epoch": 0.57, + "learning_rate": 9.27042888148732e-06, + "loss": 1.3651, + "step": 5444 + }, + { + "epoch": 0.57, + "learning_rate": 9.266778434626448e-06, + "loss": 1.3995, + "step": 5445 + }, + { + "epoch": 0.57, + "learning_rate": 9.263128085998421e-06, + "loss": 1.2692, + "step": 5446 + }, + { + "epoch": 0.57, + "learning_rate": 9.2594778360923e-06, + "loss": 1.4355, + "step": 5447 + }, + { + "epoch": 0.57, + "learning_rate": 9.255827685397124e-06, + "loss": 1.4262, + "step": 5448 + }, + { + "epoch": 0.57, + "learning_rate": 9.252177634401917e-06, + "loss": 1.3372, + "step": 5449 + }, + { + "epoch": 0.57, + "learning_rate": 9.248527683595685e-06, + "loss": 1.4603, + "step": 5450 + }, + { + "epoch": 0.57, + "learning_rate": 9.24487783346744e-06, + "loss": 1.446, + "step": 5451 + }, + { + "epoch": 0.57, + "learning_rate": 9.241228084506167e-06, + "loss": 1.4088, + "step": 5452 + }, + { + "epoch": 0.57, + "learning_rate": 9.237578437200832e-06, + "loss": 1.3074, + "step": 5453 + }, + { + "epoch": 0.57, + "learning_rate": 9.233928892040392e-06, + "loss": 1.4347, + "step": 5454 + }, + { + "epoch": 0.57, + "learning_rate": 9.230279449513802e-06, + "loss": 1.2982, + "step": 5455 + }, + { + "epoch": 0.57, + "learning_rate": 9.226630110109988e-06, + "loss": 1.2928, + "step": 5456 + }, + { + "epoch": 0.57, + "learning_rate": 9.222980874317869e-06, + "loss": 1.2849, + "step": 5457 + }, + { + "epoch": 0.57, + "learning_rate": 9.219331742626343e-06, + "loss": 1.3137, + "step": 5458 + }, + { + "epoch": 0.57, + "learning_rate": 9.215682715524309e-06, + "loss": 1.3523, + "step": 5459 + }, + { + "epoch": 0.57, + "learning_rate": 9.21203379350064e-06, + "loss": 1.381, + "step": 5460 + }, + { + "epoch": 0.57, + "learning_rate": 9.208384977044191e-06, + "loss": 1.286, + "step": 5461 + }, + { + "epoch": 0.57, + "learning_rate": 9.204736266643819e-06, + "loss": 1.3467, + "step": 5462 + }, + { + "epoch": 0.57, + "learning_rate": 9.201087662788353e-06, + "loss": 1.3582, + "step": 5463 + }, + { + "epoch": 0.57, + "learning_rate": 9.197439165966617e-06, + "loss": 1.3912, + "step": 5464 + }, + { + "epoch": 0.57, + "learning_rate": 9.193790776667402e-06, + "loss": 1.3144, + "step": 5465 + }, + { + "epoch": 0.57, + "learning_rate": 9.190142495379515e-06, + "loss": 1.3403, + "step": 5466 + }, + { + "epoch": 0.57, + "learning_rate": 9.186494322591725e-06, + "loss": 1.3253, + "step": 5467 + }, + { + "epoch": 0.57, + "learning_rate": 9.182846258792794e-06, + "loss": 1.2908, + "step": 5468 + }, + { + "epoch": 0.57, + "learning_rate": 9.179198304471463e-06, + "loss": 1.3486, + "step": 5469 + }, + { + "epoch": 0.57, + "learning_rate": 9.175550460116473e-06, + "loss": 1.3915, + "step": 5470 + }, + { + "epoch": 0.57, + "learning_rate": 9.171902726216538e-06, + "loss": 1.3441, + "step": 5471 + }, + { + "epoch": 0.57, + "learning_rate": 9.168255103260362e-06, + "loss": 1.3196, + "step": 5472 + }, + { + "epoch": 0.57, + "learning_rate": 9.164607591736627e-06, + "loss": 1.3279, + "step": 5473 + }, + { + "epoch": 0.57, + "learning_rate": 9.160960192134011e-06, + "loss": 1.2643, + "step": 5474 + }, + { + "epoch": 0.57, + "learning_rate": 9.157312904941174e-06, + "loss": 1.3327, + "step": 5475 + }, + { + "epoch": 0.57, + "learning_rate": 9.153665730646756e-06, + "loss": 1.4016, + "step": 5476 + }, + { + "epoch": 0.57, + "learning_rate": 9.150018669739378e-06, + "loss": 1.3614, + "step": 5477 + }, + { + "epoch": 0.57, + "learning_rate": 9.146371722707662e-06, + "loss": 1.3469, + "step": 5478 + }, + { + "epoch": 0.57, + "learning_rate": 9.142724890040204e-06, + "loss": 1.3625, + "step": 5479 + }, + { + "epoch": 0.57, + "learning_rate": 9.139078172225585e-06, + "loss": 1.3879, + "step": 5480 + }, + { + "epoch": 0.57, + "learning_rate": 9.135431569752362e-06, + "loss": 1.3738, + "step": 5481 + }, + { + "epoch": 0.57, + "learning_rate": 9.131785083109101e-06, + "loss": 1.3507, + "step": 5482 + }, + { + "epoch": 0.57, + "learning_rate": 9.128138712784331e-06, + "loss": 1.3681, + "step": 5483 + }, + { + "epoch": 0.58, + "learning_rate": 9.124492459266567e-06, + "loss": 1.332, + "step": 5484 + }, + { + "epoch": 0.58, + "learning_rate": 9.12084632304432e-06, + "loss": 1.4746, + "step": 5485 + }, + { + "epoch": 0.58, + "learning_rate": 9.11720030460608e-06, + "loss": 1.2775, + "step": 5486 + }, + { + "epoch": 0.58, + "learning_rate": 9.113554404440317e-06, + "loss": 1.2567, + "step": 5487 + }, + { + "epoch": 0.58, + "learning_rate": 9.10990862303548e-06, + "loss": 1.3935, + "step": 5488 + }, + { + "epoch": 0.58, + "learning_rate": 9.106262960880024e-06, + "loss": 1.3544, + "step": 5489 + }, + { + "epoch": 0.58, + "learning_rate": 9.102617418462365e-06, + "loss": 1.4023, + "step": 5490 + }, + { + "epoch": 0.58, + "learning_rate": 9.098971996270918e-06, + "loss": 1.3759, + "step": 5491 + }, + { + "epoch": 0.58, + "learning_rate": 9.095326694794064e-06, + "loss": 1.4165, + "step": 5492 + }, + { + "epoch": 0.58, + "learning_rate": 9.091681514520194e-06, + "loss": 1.3189, + "step": 5493 + }, + { + "epoch": 0.58, + "learning_rate": 9.088036455937663e-06, + "loss": 1.3135, + "step": 5494 + }, + { + "epoch": 0.58, + "learning_rate": 9.084391519534815e-06, + "loss": 1.3521, + "step": 5495 + }, + { + "epoch": 0.58, + "learning_rate": 9.080746705799971e-06, + "loss": 1.3314, + "step": 5496 + }, + { + "epoch": 0.58, + "learning_rate": 9.077102015221457e-06, + "loss": 1.3119, + "step": 5497 + }, + { + "epoch": 0.58, + "learning_rate": 9.073457448287557e-06, + "loss": 1.2895, + "step": 5498 + }, + { + "epoch": 0.58, + "learning_rate": 9.069813005486554e-06, + "loss": 1.3155, + "step": 5499 + }, + { + "epoch": 0.58, + "learning_rate": 9.066168687306701e-06, + "loss": 1.4048, + "step": 5500 + }, + { + "epoch": 0.58, + "learning_rate": 9.062524494236256e-06, + "loss": 1.3665, + "step": 5501 + }, + { + "epoch": 0.58, + "learning_rate": 9.058880426763442e-06, + "loss": 1.3258, + "step": 5502 + }, + { + "epoch": 0.58, + "learning_rate": 9.05523648537647e-06, + "loss": 1.3078, + "step": 5503 + }, + { + "epoch": 0.58, + "learning_rate": 9.051592670563527e-06, + "loss": 1.361, + "step": 5504 + }, + { + "epoch": 0.58, + "learning_rate": 9.047948982812801e-06, + "loss": 1.3557, + "step": 5505 + }, + { + "epoch": 0.58, + "learning_rate": 9.044305422612453e-06, + "loss": 1.5733, + "step": 5506 + }, + { + "epoch": 0.58, + "learning_rate": 9.040661990450617e-06, + "loss": 1.2835, + "step": 5507 + }, + { + "epoch": 0.58, + "learning_rate": 9.037018686815428e-06, + "loss": 1.311, + "step": 5508 + }, + { + "epoch": 0.58, + "learning_rate": 9.033375512194993e-06, + "loss": 1.3949, + "step": 5509 + }, + { + "epoch": 0.58, + "learning_rate": 9.029732467077405e-06, + "loss": 1.356, + "step": 5510 + }, + { + "epoch": 0.58, + "learning_rate": 9.026089551950727e-06, + "loss": 1.3695, + "step": 5511 + }, + { + "epoch": 0.58, + "learning_rate": 9.022446767303033e-06, + "loss": 1.3325, + "step": 5512 + }, + { + "epoch": 0.58, + "learning_rate": 9.018804113622353e-06, + "loss": 1.401, + "step": 5513 + }, + { + "epoch": 0.58, + "learning_rate": 9.015161591396713e-06, + "loss": 1.3632, + "step": 5514 + }, + { + "epoch": 0.58, + "learning_rate": 9.011519201114108e-06, + "loss": 1.3697, + "step": 5515 + }, + { + "epoch": 0.58, + "learning_rate": 9.007876943262538e-06, + "loss": 1.2604, + "step": 5516 + }, + { + "epoch": 0.58, + "learning_rate": 9.004234818329964e-06, + "loss": 1.3557, + "step": 5517 + }, + { + "epoch": 0.58, + "learning_rate": 9.000592826804342e-06, + "loss": 1.3248, + "step": 5518 + }, + { + "epoch": 0.58, + "learning_rate": 8.996950969173596e-06, + "loss": 1.3237, + "step": 5519 + }, + { + "epoch": 0.58, + "learning_rate": 8.99330924592565e-06, + "loss": 1.339, + "step": 5520 + }, + { + "epoch": 0.58, + "learning_rate": 8.989667657548402e-06, + "loss": 1.3218, + "step": 5521 + }, + { + "epoch": 0.58, + "learning_rate": 8.986026204529728e-06, + "loss": 1.3354, + "step": 5522 + }, + { + "epoch": 0.58, + "learning_rate": 8.982384887357484e-06, + "loss": 1.3011, + "step": 5523 + }, + { + "epoch": 0.58, + "learning_rate": 8.978743706519524e-06, + "loss": 1.3526, + "step": 5524 + }, + { + "epoch": 0.58, + "learning_rate": 8.975102662503666e-06, + "loss": 1.3298, + "step": 5525 + }, + { + "epoch": 0.58, + "learning_rate": 8.971461755797718e-06, + "loss": 1.328, + "step": 5526 + }, + { + "epoch": 0.58, + "learning_rate": 8.967820986889461e-06, + "loss": 1.3705, + "step": 5527 + }, + { + "epoch": 0.58, + "learning_rate": 8.964180356266676e-06, + "loss": 1.3814, + "step": 5528 + }, + { + "epoch": 0.58, + "learning_rate": 8.96053986441711e-06, + "loss": 1.37, + "step": 5529 + }, + { + "epoch": 0.58, + "learning_rate": 8.956899511828489e-06, + "loss": 1.3224, + "step": 5530 + }, + { + "epoch": 0.58, + "learning_rate": 8.953259298988536e-06, + "loss": 1.3416, + "step": 5531 + }, + { + "epoch": 0.58, + "learning_rate": 8.949619226384942e-06, + "loss": 1.4212, + "step": 5532 + }, + { + "epoch": 0.58, + "learning_rate": 8.945979294505383e-06, + "loss": 1.4145, + "step": 5533 + }, + { + "epoch": 0.58, + "learning_rate": 8.942339503837512e-06, + "loss": 1.2179, + "step": 5534 + }, + { + "epoch": 0.58, + "learning_rate": 8.938699854868976e-06, + "loss": 1.3239, + "step": 5535 + }, + { + "epoch": 0.58, + "learning_rate": 8.93506034808739e-06, + "loss": 1.3488, + "step": 5536 + }, + { + "epoch": 0.58, + "learning_rate": 8.931420983980357e-06, + "loss": 1.3283, + "step": 5537 + }, + { + "epoch": 0.58, + "learning_rate": 8.927781763035449e-06, + "loss": 1.3866, + "step": 5538 + }, + { + "epoch": 0.58, + "learning_rate": 8.924142685740239e-06, + "loss": 1.3877, + "step": 5539 + }, + { + "epoch": 0.58, + "learning_rate": 8.920503752582265e-06, + "loss": 1.2511, + "step": 5540 + }, + { + "epoch": 0.58, + "learning_rate": 8.916864964049056e-06, + "loss": 1.3581, + "step": 5541 + }, + { + "epoch": 0.58, + "learning_rate": 8.913226320628104e-06, + "loss": 1.387, + "step": 5542 + }, + { + "epoch": 0.58, + "learning_rate": 8.909587822806905e-06, + "loss": 1.3785, + "step": 5543 + }, + { + "epoch": 0.58, + "learning_rate": 8.905949471072921e-06, + "loss": 1.4302, + "step": 5544 + }, + { + "epoch": 0.58, + "learning_rate": 8.9023112659136e-06, + "loss": 1.439, + "step": 5545 + }, + { + "epoch": 0.58, + "learning_rate": 8.898673207816357e-06, + "loss": 1.3257, + "step": 5546 + }, + { + "epoch": 0.58, + "learning_rate": 8.895035297268611e-06, + "loss": 1.4237, + "step": 5547 + }, + { + "epoch": 0.58, + "learning_rate": 8.891397534757745e-06, + "loss": 1.3141, + "step": 5548 + }, + { + "epoch": 0.58, + "learning_rate": 8.887759920771127e-06, + "loss": 1.3069, + "step": 5549 + }, + { + "epoch": 0.58, + "learning_rate": 8.884122455796095e-06, + "loss": 1.2703, + "step": 5550 + }, + { + "epoch": 0.58, + "learning_rate": 8.880485140319986e-06, + "loss": 1.2929, + "step": 5551 + }, + { + "epoch": 0.58, + "learning_rate": 8.876847974830103e-06, + "loss": 1.3719, + "step": 5552 + }, + { + "epoch": 0.58, + "learning_rate": 8.873210959813731e-06, + "loss": 1.3481, + "step": 5553 + }, + { + "epoch": 0.58, + "learning_rate": 8.869574095758141e-06, + "loss": 1.3609, + "step": 5554 + }, + { + "epoch": 0.58, + "learning_rate": 8.865937383150577e-06, + "loss": 1.3137, + "step": 5555 + }, + { + "epoch": 0.58, + "learning_rate": 8.862300822478265e-06, + "loss": 1.3602, + "step": 5556 + }, + { + "epoch": 0.58, + "learning_rate": 8.858664414228409e-06, + "loss": 1.3142, + "step": 5557 + }, + { + "epoch": 0.58, + "learning_rate": 8.855028158888196e-06, + "loss": 1.288, + "step": 5558 + }, + { + "epoch": 0.58, + "learning_rate": 8.851392056944791e-06, + "loss": 1.3407, + "step": 5559 + }, + { + "epoch": 0.58, + "learning_rate": 8.847756108885342e-06, + "loss": 1.3118, + "step": 5560 + }, + { + "epoch": 0.58, + "learning_rate": 8.84412031519696e-06, + "loss": 1.3646, + "step": 5561 + }, + { + "epoch": 0.58, + "learning_rate": 8.840484676366761e-06, + "loss": 1.3896, + "step": 5562 + }, + { + "epoch": 0.58, + "learning_rate": 8.836849192881822e-06, + "loss": 1.3296, + "step": 5563 + }, + { + "epoch": 0.58, + "learning_rate": 8.833213865229208e-06, + "loss": 1.2918, + "step": 5564 + }, + { + "epoch": 0.58, + "learning_rate": 8.82957869389595e-06, + "loss": 1.4811, + "step": 5565 + }, + { + "epoch": 0.58, + "learning_rate": 8.82594367936908e-06, + "loss": 1.3877, + "step": 5566 + }, + { + "epoch": 0.58, + "learning_rate": 8.822308822135588e-06, + "loss": 1.3716, + "step": 5567 + }, + { + "epoch": 0.58, + "learning_rate": 8.818674122682456e-06, + "loss": 1.3204, + "step": 5568 + }, + { + "epoch": 0.58, + "learning_rate": 8.815039581496634e-06, + "loss": 1.326, + "step": 5569 + }, + { + "epoch": 0.58, + "learning_rate": 8.811405199065066e-06, + "loss": 1.3762, + "step": 5570 + }, + { + "epoch": 0.58, + "learning_rate": 8.807770975874658e-06, + "loss": 1.2944, + "step": 5571 + }, + { + "epoch": 0.58, + "learning_rate": 8.804136912412311e-06, + "loss": 1.3057, + "step": 5572 + }, + { + "epoch": 0.58, + "eval_loss": 1.4187605381011963, + "eval_runtime": 77.5157, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 5572 + }, + { + "epoch": 0.58, + "learning_rate": 8.800503009164884e-06, + "loss": 1.4144, + "step": 5573 + }, + { + "epoch": 0.58, + "learning_rate": 8.796869266619238e-06, + "loss": 1.2218, + "step": 5574 + }, + { + "epoch": 0.58, + "learning_rate": 8.793235685262197e-06, + "loss": 1.4445, + "step": 5575 + }, + { + "epoch": 0.58, + "learning_rate": 8.789602265580565e-06, + "loss": 1.3761, + "step": 5576 + }, + { + "epoch": 0.58, + "learning_rate": 8.78596900806113e-06, + "loss": 1.3762, + "step": 5577 + }, + { + "epoch": 0.58, + "learning_rate": 8.782335913190657e-06, + "loss": 1.3506, + "step": 5578 + }, + { + "epoch": 0.59, + "learning_rate": 8.778702981455883e-06, + "loss": 1.4183, + "step": 5579 + }, + { + "epoch": 0.59, + "learning_rate": 8.775070213343528e-06, + "loss": 1.3123, + "step": 5580 + }, + { + "epoch": 0.59, + "learning_rate": 8.771437609340291e-06, + "loss": 1.3168, + "step": 5581 + }, + { + "epoch": 0.59, + "learning_rate": 8.76780516993285e-06, + "loss": 1.3939, + "step": 5582 + }, + { + "epoch": 0.59, + "learning_rate": 8.764172895607856e-06, + "loss": 1.3317, + "step": 5583 + }, + { + "epoch": 0.59, + "learning_rate": 8.760540786851937e-06, + "loss": 1.3094, + "step": 5584 + }, + { + "epoch": 0.59, + "learning_rate": 8.756908844151708e-06, + "loss": 1.2853, + "step": 5585 + }, + { + "epoch": 0.59, + "learning_rate": 8.753277067993752e-06, + "loss": 1.2625, + "step": 5586 + }, + { + "epoch": 0.59, + "learning_rate": 8.74964545886464e-06, + "loss": 1.4246, + "step": 5587 + }, + { + "epoch": 0.59, + "learning_rate": 8.746014017250904e-06, + "loss": 1.2891, + "step": 5588 + }, + { + "epoch": 0.59, + "learning_rate": 8.742382743639071e-06, + "loss": 1.3135, + "step": 5589 + }, + { + "epoch": 0.59, + "learning_rate": 8.738751638515639e-06, + "loss": 1.3021, + "step": 5590 + }, + { + "epoch": 0.59, + "learning_rate": 8.735120702367082e-06, + "loss": 1.3398, + "step": 5591 + }, + { + "epoch": 0.59, + "learning_rate": 8.731489935679845e-06, + "loss": 1.4173, + "step": 5592 + }, + { + "epoch": 0.59, + "learning_rate": 8.727859338940367e-06, + "loss": 1.4129, + "step": 5593 + }, + { + "epoch": 0.59, + "learning_rate": 8.724228912635053e-06, + "loss": 1.3807, + "step": 5594 + }, + { + "epoch": 0.59, + "learning_rate": 8.720598657250284e-06, + "loss": 1.2962, + "step": 5595 + }, + { + "epoch": 0.59, + "learning_rate": 8.716968573272416e-06, + "loss": 1.3784, + "step": 5596 + }, + { + "epoch": 0.59, + "learning_rate": 8.713338661187799e-06, + "loss": 1.3751, + "step": 5597 + }, + { + "epoch": 0.59, + "learning_rate": 8.70970892148274e-06, + "loss": 1.3122, + "step": 5598 + }, + { + "epoch": 0.59, + "learning_rate": 8.70607935464353e-06, + "loss": 1.4174, + "step": 5599 + }, + { + "epoch": 0.59, + "learning_rate": 8.702449961156445e-06, + "loss": 1.3275, + "step": 5600 + }, + { + "epoch": 0.59, + "learning_rate": 8.698820741507723e-06, + "loss": 1.33, + "step": 5601 + }, + { + "epoch": 0.59, + "learning_rate": 8.695191696183589e-06, + "loss": 1.4075, + "step": 5602 + }, + { + "epoch": 0.59, + "learning_rate": 8.69156282567024e-06, + "loss": 1.3778, + "step": 5603 + }, + { + "epoch": 0.59, + "learning_rate": 8.687934130453857e-06, + "loss": 1.3222, + "step": 5604 + }, + { + "epoch": 0.59, + "learning_rate": 8.684305611020587e-06, + "loss": 1.3443, + "step": 5605 + }, + { + "epoch": 0.59, + "learning_rate": 8.680677267856558e-06, + "loss": 1.3167, + "step": 5606 + }, + { + "epoch": 0.59, + "learning_rate": 8.677049101447877e-06, + "loss": 1.3209, + "step": 5607 + }, + { + "epoch": 0.59, + "learning_rate": 8.673421112280624e-06, + "loss": 1.3125, + "step": 5608 + }, + { + "epoch": 0.59, + "learning_rate": 8.669793300840857e-06, + "loss": 1.375, + "step": 5609 + }, + { + "epoch": 0.59, + "learning_rate": 8.666165667614612e-06, + "loss": 1.3627, + "step": 5610 + }, + { + "epoch": 0.59, + "learning_rate": 8.662538213087888e-06, + "loss": 1.3064, + "step": 5611 + }, + { + "epoch": 0.59, + "learning_rate": 8.658910937746685e-06, + "loss": 1.4251, + "step": 5612 + }, + { + "epoch": 0.59, + "learning_rate": 8.655283842076956e-06, + "loss": 1.3011, + "step": 5613 + }, + { + "epoch": 0.59, + "learning_rate": 8.651656926564645e-06, + "loss": 1.3299, + "step": 5614 + }, + { + "epoch": 0.59, + "learning_rate": 8.648030191695653e-06, + "loss": 1.3448, + "step": 5615 + }, + { + "epoch": 0.59, + "learning_rate": 8.644403637955883e-06, + "loss": 1.4048, + "step": 5616 + }, + { + "epoch": 0.59, + "learning_rate": 8.640777265831195e-06, + "loss": 1.336, + "step": 5617 + }, + { + "epoch": 0.59, + "learning_rate": 8.63715107580743e-06, + "loss": 1.4959, + "step": 5618 + }, + { + "epoch": 0.59, + "learning_rate": 8.633525068370397e-06, + "loss": 1.3822, + "step": 5619 + }, + { + "epoch": 0.59, + "learning_rate": 8.6298992440059e-06, + "loss": 1.282, + "step": 5620 + }, + { + "epoch": 0.59, + "learning_rate": 8.626273603199699e-06, + "loss": 1.1873, + "step": 5621 + }, + { + "epoch": 0.59, + "learning_rate": 8.622648146437538e-06, + "loss": 1.3706, + "step": 5622 + }, + { + "epoch": 0.59, + "learning_rate": 8.619022874205138e-06, + "loss": 1.2709, + "step": 5623 + }, + { + "epoch": 0.59, + "learning_rate": 8.615397786988188e-06, + "loss": 1.3608, + "step": 5624 + }, + { + "epoch": 0.59, + "learning_rate": 8.61177288527236e-06, + "loss": 1.3821, + "step": 5625 + }, + { + "epoch": 0.59, + "learning_rate": 8.608148169543292e-06, + "loss": 1.327, + "step": 5626 + }, + { + "epoch": 0.59, + "learning_rate": 8.604523640286611e-06, + "loss": 1.3544, + "step": 5627 + }, + { + "epoch": 0.59, + "learning_rate": 8.600899297987905e-06, + "loss": 1.3269, + "step": 5628 + }, + { + "epoch": 0.59, + "learning_rate": 8.597275143132745e-06, + "loss": 1.3142, + "step": 5629 + }, + { + "epoch": 0.59, + "learning_rate": 8.593651176206671e-06, + "loss": 1.3878, + "step": 5630 + }, + { + "epoch": 0.59, + "learning_rate": 8.59002739769521e-06, + "loss": 1.3386, + "step": 5631 + }, + { + "epoch": 0.59, + "learning_rate": 8.586403808083846e-06, + "loss": 1.3484, + "step": 5632 + }, + { + "epoch": 0.59, + "learning_rate": 8.582780407858052e-06, + "loss": 1.3676, + "step": 5633 + }, + { + "epoch": 0.59, + "learning_rate": 8.579157197503265e-06, + "loss": 1.3753, + "step": 5634 + }, + { + "epoch": 0.59, + "learning_rate": 8.57553417750491e-06, + "loss": 1.4058, + "step": 5635 + }, + { + "epoch": 0.59, + "learning_rate": 8.571911348348375e-06, + "loss": 1.4434, + "step": 5636 + }, + { + "epoch": 0.59, + "learning_rate": 8.568288710519027e-06, + "loss": 1.3398, + "step": 5637 + }, + { + "epoch": 0.59, + "learning_rate": 8.564666264502199e-06, + "loss": 1.3294, + "step": 5638 + }, + { + "epoch": 0.59, + "learning_rate": 8.561044010783216e-06, + "loss": 1.3165, + "step": 5639 + }, + { + "epoch": 0.59, + "learning_rate": 8.557421949847363e-06, + "loss": 1.3437, + "step": 5640 + }, + { + "epoch": 0.59, + "learning_rate": 8.553800082179905e-06, + "loss": 1.3473, + "step": 5641 + }, + { + "epoch": 0.59, + "learning_rate": 8.55017840826607e-06, + "loss": 1.3378, + "step": 5642 + }, + { + "epoch": 0.59, + "learning_rate": 8.546556928591082e-06, + "loss": 1.3357, + "step": 5643 + }, + { + "epoch": 0.59, + "learning_rate": 8.54293564364012e-06, + "loss": 1.3435, + "step": 5644 + }, + { + "epoch": 0.59, + "learning_rate": 8.53931455389834e-06, + "loss": 1.3335, + "step": 5645 + }, + { + "epoch": 0.59, + "learning_rate": 8.535693659850885e-06, + "loss": 1.2917, + "step": 5646 + }, + { + "epoch": 0.59, + "learning_rate": 8.532072961982851e-06, + "loss": 1.3785, + "step": 5647 + }, + { + "epoch": 0.59, + "learning_rate": 8.528452460779327e-06, + "loss": 1.3634, + "step": 5648 + }, + { + "epoch": 0.59, + "learning_rate": 8.524832156725359e-06, + "loss": 1.3541, + "step": 5649 + }, + { + "epoch": 0.59, + "learning_rate": 8.521212050305978e-06, + "loss": 1.335, + "step": 5650 + }, + { + "epoch": 0.59, + "learning_rate": 8.51759214200619e-06, + "loss": 1.3011, + "step": 5651 + }, + { + "epoch": 0.59, + "learning_rate": 8.513972432310965e-06, + "loss": 1.3982, + "step": 5652 + }, + { + "epoch": 0.59, + "learning_rate": 8.510352921705247e-06, + "loss": 1.3217, + "step": 5653 + }, + { + "epoch": 0.59, + "learning_rate": 8.506733610673968e-06, + "loss": 1.3275, + "step": 5654 + }, + { + "epoch": 0.59, + "learning_rate": 8.503114499702015e-06, + "loss": 1.3335, + "step": 5655 + }, + { + "epoch": 0.59, + "learning_rate": 8.499495589274257e-06, + "loss": 1.3567, + "step": 5656 + }, + { + "epoch": 0.59, + "learning_rate": 8.495876879875536e-06, + "loss": 1.348, + "step": 5657 + }, + { + "epoch": 0.59, + "learning_rate": 8.492258371990667e-06, + "loss": 1.3991, + "step": 5658 + }, + { + "epoch": 0.59, + "learning_rate": 8.488640066104435e-06, + "loss": 1.3528, + "step": 5659 + }, + { + "epoch": 0.59, + "learning_rate": 8.485021962701603e-06, + "loss": 1.3275, + "step": 5660 + }, + { + "epoch": 0.59, + "learning_rate": 8.481404062266897e-06, + "loss": 1.3605, + "step": 5661 + }, + { + "epoch": 0.59, + "learning_rate": 8.477786365285032e-06, + "loss": 1.3288, + "step": 5662 + }, + { + "epoch": 0.59, + "learning_rate": 8.474168872240682e-06, + "loss": 1.3274, + "step": 5663 + }, + { + "epoch": 0.59, + "learning_rate": 8.470551583618498e-06, + "loss": 1.273, + "step": 5664 + }, + { + "epoch": 0.59, + "learning_rate": 8.4669344999031e-06, + "loss": 1.3142, + "step": 5665 + }, + { + "epoch": 0.59, + "learning_rate": 8.463317621579091e-06, + "loss": 1.2912, + "step": 5666 + }, + { + "epoch": 0.59, + "learning_rate": 8.459700949131037e-06, + "loss": 1.3162, + "step": 5667 + }, + { + "epoch": 0.59, + "learning_rate": 8.456084483043479e-06, + "loss": 1.3377, + "step": 5668 + }, + { + "epoch": 0.59, + "learning_rate": 8.452468223800931e-06, + "loss": 1.3545, + "step": 5669 + }, + { + "epoch": 0.59, + "learning_rate": 8.448852171887878e-06, + "loss": 1.4052, + "step": 5670 + }, + { + "epoch": 0.59, + "learning_rate": 8.44523632778878e-06, + "loss": 1.3389, + "step": 5671 + }, + { + "epoch": 0.59, + "learning_rate": 8.441620691988063e-06, + "loss": 1.3801, + "step": 5672 + }, + { + "epoch": 0.59, + "learning_rate": 8.438005264970134e-06, + "loss": 1.2978, + "step": 5673 + }, + { + "epoch": 0.6, + "learning_rate": 8.434390047219366e-06, + "loss": 1.437, + "step": 5674 + }, + { + "epoch": 0.6, + "learning_rate": 8.430775039220103e-06, + "loss": 1.3602, + "step": 5675 + }, + { + "epoch": 0.6, + "learning_rate": 8.427160241456664e-06, + "loss": 1.4971, + "step": 5676 + }, + { + "epoch": 0.6, + "learning_rate": 8.423545654413342e-06, + "loss": 1.2765, + "step": 5677 + }, + { + "epoch": 0.6, + "learning_rate": 8.419931278574397e-06, + "loss": 1.4346, + "step": 5678 + }, + { + "epoch": 0.6, + "learning_rate": 8.416317114424059e-06, + "loss": 1.366, + "step": 5679 + }, + { + "epoch": 0.6, + "learning_rate": 8.412703162446536e-06, + "loss": 1.3776, + "step": 5680 + }, + { + "epoch": 0.6, + "learning_rate": 8.409089423126009e-06, + "loss": 1.2516, + "step": 5681 + }, + { + "epoch": 0.6, + "learning_rate": 8.405475896946621e-06, + "loss": 1.4257, + "step": 5682 + }, + { + "epoch": 0.6, + "learning_rate": 8.401862584392492e-06, + "loss": 1.3523, + "step": 5683 + }, + { + "epoch": 0.6, + "learning_rate": 8.398249485947712e-06, + "loss": 1.3791, + "step": 5684 + }, + { + "epoch": 0.6, + "learning_rate": 8.394636602096348e-06, + "loss": 1.3574, + "step": 5685 + }, + { + "epoch": 0.6, + "learning_rate": 8.39102393332243e-06, + "loss": 1.4748, + "step": 5686 + }, + { + "epoch": 0.6, + "learning_rate": 8.387411480109967e-06, + "loss": 1.3693, + "step": 5687 + }, + { + "epoch": 0.6, + "learning_rate": 8.383799242942925e-06, + "loss": 1.3643, + "step": 5688 + }, + { + "epoch": 0.6, + "learning_rate": 8.38018722230526e-06, + "loss": 1.3446, + "step": 5689 + }, + { + "epoch": 0.6, + "learning_rate": 8.37657541868089e-06, + "loss": 1.3552, + "step": 5690 + }, + { + "epoch": 0.6, + "learning_rate": 8.372963832553698e-06, + "loss": 1.3636, + "step": 5691 + }, + { + "epoch": 0.6, + "learning_rate": 8.36935246440755e-06, + "loss": 1.3398, + "step": 5692 + }, + { + "epoch": 0.6, + "learning_rate": 8.365741314726273e-06, + "loss": 1.3336, + "step": 5693 + }, + { + "epoch": 0.6, + "learning_rate": 8.362130383993667e-06, + "loss": 1.3023, + "step": 5694 + }, + { + "epoch": 0.6, + "learning_rate": 8.358519672693506e-06, + "loss": 1.3591, + "step": 5695 + }, + { + "epoch": 0.6, + "learning_rate": 8.354909181309533e-06, + "loss": 1.3113, + "step": 5696 + }, + { + "epoch": 0.6, + "learning_rate": 8.351298910325462e-06, + "loss": 1.3747, + "step": 5697 + }, + { + "epoch": 0.6, + "learning_rate": 8.347688860224976e-06, + "loss": 1.3555, + "step": 5698 + }, + { + "epoch": 0.6, + "learning_rate": 8.344079031491722e-06, + "loss": 1.2947, + "step": 5699 + }, + { + "epoch": 0.6, + "learning_rate": 8.340469424609337e-06, + "loss": 1.4099, + "step": 5700 + }, + { + "epoch": 0.6, + "learning_rate": 8.336860040061404e-06, + "loss": 1.3263, + "step": 5701 + }, + { + "epoch": 0.6, + "learning_rate": 8.333250878331498e-06, + "loss": 1.372, + "step": 5702 + }, + { + "epoch": 0.6, + "learning_rate": 8.329641939903142e-06, + "loss": 1.3523, + "step": 5703 + }, + { + "epoch": 0.6, + "learning_rate": 8.32603322525985e-06, + "loss": 1.3451, + "step": 5704 + }, + { + "epoch": 0.6, + "learning_rate": 8.322424734885098e-06, + "loss": 1.3296, + "step": 5705 + }, + { + "epoch": 0.6, + "learning_rate": 8.318816469262325e-06, + "loss": 1.449, + "step": 5706 + }, + { + "epoch": 0.6, + "learning_rate": 8.315208428874946e-06, + "loss": 1.3611, + "step": 5707 + }, + { + "epoch": 0.6, + "learning_rate": 8.311600614206352e-06, + "loss": 1.3849, + "step": 5708 + }, + { + "epoch": 0.6, + "learning_rate": 8.307993025739893e-06, + "loss": 1.3968, + "step": 5709 + }, + { + "epoch": 0.6, + "learning_rate": 8.304385663958895e-06, + "loss": 1.4428, + "step": 5710 + }, + { + "epoch": 0.6, + "learning_rate": 8.300778529346647e-06, + "loss": 1.3095, + "step": 5711 + }, + { + "epoch": 0.6, + "learning_rate": 8.297171622386418e-06, + "loss": 1.3135, + "step": 5712 + }, + { + "epoch": 0.6, + "learning_rate": 8.293564943561438e-06, + "loss": 1.3069, + "step": 5713 + }, + { + "epoch": 0.6, + "learning_rate": 8.28995849335491e-06, + "loss": 1.3736, + "step": 5714 + }, + { + "epoch": 0.6, + "learning_rate": 8.286352272250007e-06, + "loss": 1.343, + "step": 5715 + }, + { + "epoch": 0.6, + "learning_rate": 8.28274628072987e-06, + "loss": 1.2929, + "step": 5716 + }, + { + "epoch": 0.6, + "learning_rate": 8.279140519277607e-06, + "loss": 1.3356, + "step": 5717 + }, + { + "epoch": 0.6, + "learning_rate": 8.275534988376295e-06, + "loss": 1.2683, + "step": 5718 + }, + { + "epoch": 0.6, + "learning_rate": 8.27192968850899e-06, + "loss": 1.3738, + "step": 5719 + }, + { + "epoch": 0.6, + "learning_rate": 8.268324620158704e-06, + "loss": 1.3369, + "step": 5720 + }, + { + "epoch": 0.6, + "learning_rate": 8.264719783808425e-06, + "loss": 1.3684, + "step": 5721 + }, + { + "epoch": 0.6, + "learning_rate": 8.261115179941108e-06, + "loss": 1.4081, + "step": 5722 + }, + { + "epoch": 0.6, + "learning_rate": 8.257510809039678e-06, + "loss": 1.2504, + "step": 5723 + }, + { + "epoch": 0.6, + "learning_rate": 8.253906671587029e-06, + "loss": 1.417, + "step": 5724 + }, + { + "epoch": 0.6, + "learning_rate": 8.25030276806602e-06, + "loss": 1.3631, + "step": 5725 + }, + { + "epoch": 0.6, + "learning_rate": 8.246699098959483e-06, + "loss": 1.499, + "step": 5726 + }, + { + "epoch": 0.6, + "learning_rate": 8.243095664750217e-06, + "loss": 1.3656, + "step": 5727 + }, + { + "epoch": 0.6, + "learning_rate": 8.239492465920992e-06, + "loss": 1.3563, + "step": 5728 + }, + { + "epoch": 0.6, + "learning_rate": 8.23588950295454e-06, + "loss": 1.3554, + "step": 5729 + }, + { + "epoch": 0.6, + "learning_rate": 8.232286776333566e-06, + "loss": 1.2705, + "step": 5730 + }, + { + "epoch": 0.6, + "learning_rate": 8.228684286540747e-06, + "loss": 1.3792, + "step": 5731 + }, + { + "epoch": 0.6, + "learning_rate": 8.22508203405872e-06, + "loss": 1.3301, + "step": 5732 + }, + { + "epoch": 0.6, + "learning_rate": 8.221480019370095e-06, + "loss": 1.36, + "step": 5733 + }, + { + "epoch": 0.6, + "learning_rate": 8.217878242957448e-06, + "loss": 1.4406, + "step": 5734 + }, + { + "epoch": 0.6, + "learning_rate": 8.214276705303328e-06, + "loss": 1.2886, + "step": 5735 + }, + { + "epoch": 0.6, + "learning_rate": 8.210675406890248e-06, + "loss": 1.3072, + "step": 5736 + }, + { + "epoch": 0.6, + "learning_rate": 8.207074348200686e-06, + "loss": 1.3734, + "step": 5737 + }, + { + "epoch": 0.6, + "learning_rate": 8.203473529717095e-06, + "loss": 1.3893, + "step": 5738 + }, + { + "epoch": 0.6, + "learning_rate": 8.199872951921892e-06, + "loss": 1.3427, + "step": 5739 + }, + { + "epoch": 0.6, + "learning_rate": 8.196272615297459e-06, + "loss": 1.3125, + "step": 5740 + }, + { + "epoch": 0.6, + "learning_rate": 8.19267252032615e-06, + "loss": 1.3079, + "step": 5741 + }, + { + "epoch": 0.6, + "learning_rate": 8.189072667490285e-06, + "loss": 1.2971, + "step": 5742 + }, + { + "epoch": 0.6, + "learning_rate": 8.185473057272154e-06, + "loss": 1.3003, + "step": 5743 + }, + { + "epoch": 0.6, + "learning_rate": 8.18187369015401e-06, + "loss": 1.3002, + "step": 5744 + }, + { + "epoch": 0.6, + "learning_rate": 8.178274566618075e-06, + "loss": 1.2852, + "step": 5745 + }, + { + "epoch": 0.6, + "learning_rate": 8.174675687146542e-06, + "loss": 1.2807, + "step": 5746 + }, + { + "epoch": 0.6, + "learning_rate": 8.171077052221567e-06, + "loss": 1.2983, + "step": 5747 + }, + { + "epoch": 0.6, + "learning_rate": 8.167478662325274e-06, + "loss": 1.3002, + "step": 5748 + }, + { + "epoch": 0.6, + "learning_rate": 8.163880517939753e-06, + "loss": 1.2575, + "step": 5749 + }, + { + "epoch": 0.6, + "learning_rate": 8.160282619547068e-06, + "loss": 1.2627, + "step": 5750 + }, + { + "epoch": 0.6, + "learning_rate": 8.156684967629242e-06, + "loss": 1.2549, + "step": 5751 + }, + { + "epoch": 0.6, + "learning_rate": 8.153087562668265e-06, + "loss": 1.2595, + "step": 5752 + }, + { + "epoch": 0.6, + "learning_rate": 8.1494904051461e-06, + "loss": 1.2788, + "step": 5753 + }, + { + "epoch": 0.6, + "learning_rate": 8.145893495544676e-06, + "loss": 1.3028, + "step": 5754 + }, + { + "epoch": 0.6, + "learning_rate": 8.142296834345883e-06, + "loss": 1.3019, + "step": 5755 + }, + { + "epoch": 0.6, + "learning_rate": 8.138700422031583e-06, + "loss": 1.2998, + "step": 5756 + }, + { + "epoch": 0.6, + "learning_rate": 8.135104259083598e-06, + "loss": 1.3298, + "step": 5757 + }, + { + "epoch": 0.6, + "learning_rate": 8.13150834598373e-06, + "loss": 1.2681, + "step": 5758 + }, + { + "epoch": 0.6, + "learning_rate": 8.127912683213733e-06, + "loss": 1.2987, + "step": 5759 + }, + { + "epoch": 0.6, + "learning_rate": 8.124317271255331e-06, + "loss": 1.3181, + "step": 5760 + }, + { + "epoch": 0.6, + "learning_rate": 8.120722110590224e-06, + "loss": 1.423, + "step": 5761 + }, + { + "epoch": 0.6, + "learning_rate": 8.117127201700067e-06, + "loss": 1.5029, + "step": 5762 + }, + { + "epoch": 0.6, + "learning_rate": 8.113532545066488e-06, + "loss": 1.3016, + "step": 5763 + }, + { + "epoch": 0.6, + "learning_rate": 8.109938141171074e-06, + "loss": 1.3906, + "step": 5764 + }, + { + "epoch": 0.6, + "learning_rate": 8.106343990495387e-06, + "loss": 1.3363, + "step": 5765 + }, + { + "epoch": 0.6, + "learning_rate": 8.10275009352095e-06, + "loss": 1.314, + "step": 5766 + }, + { + "epoch": 0.6, + "learning_rate": 8.09915645072925e-06, + "loss": 1.3484, + "step": 5767 + }, + { + "epoch": 0.6, + "learning_rate": 8.095563062601745e-06, + "loss": 1.3757, + "step": 5768 + }, + { + "epoch": 0.6, + "learning_rate": 8.091969929619859e-06, + "loss": 1.3068, + "step": 5769 + }, + { + "epoch": 0.61, + "learning_rate": 8.088377052264976e-06, + "loss": 1.3486, + "step": 5770 + }, + { + "epoch": 0.61, + "learning_rate": 8.08478443101845e-06, + "loss": 1.244, + "step": 5771 + }, + { + "epoch": 0.61, + "eval_loss": 1.4178493022918701, + "eval_runtime": 77.6086, + "eval_samples_per_second": 1.662, + "eval_steps_per_second": 0.116, + "step": 5771 + }, + { + "epoch": 0.61, + "learning_rate": 8.0811920663616e-06, + "loss": 1.3325, + "step": 5772 + }, + { + "epoch": 0.61, + "learning_rate": 8.077599958775713e-06, + "loss": 1.336, + "step": 5773 + }, + { + "epoch": 0.61, + "learning_rate": 8.074008108742037e-06, + "loss": 1.3167, + "step": 5774 + }, + { + "epoch": 0.61, + "learning_rate": 8.070416516741786e-06, + "loss": 1.3166, + "step": 5775 + }, + { + "epoch": 0.61, + "learning_rate": 8.066825183256141e-06, + "loss": 1.3377, + "step": 5776 + }, + { + "epoch": 0.61, + "learning_rate": 8.063234108766253e-06, + "loss": 1.3704, + "step": 5777 + }, + { + "epoch": 0.61, + "learning_rate": 8.059643293753233e-06, + "loss": 1.3596, + "step": 5778 + }, + { + "epoch": 0.61, + "learning_rate": 8.056052738698153e-06, + "loss": 1.4477, + "step": 5779 + }, + { + "epoch": 0.61, + "learning_rate": 8.052462444082055e-06, + "loss": 1.338, + "step": 5780 + }, + { + "epoch": 0.61, + "learning_rate": 8.048872410385952e-06, + "loss": 1.2714, + "step": 5781 + }, + { + "epoch": 0.61, + "learning_rate": 8.045282638090815e-06, + "loss": 0.9642, + "step": 5782 + }, + { + "epoch": 0.61, + "learning_rate": 8.041693127677576e-06, + "loss": 0.8702, + "step": 5783 + }, + { + "epoch": 0.61, + "learning_rate": 8.038103879627144e-06, + "loss": 0.8986, + "step": 5784 + }, + { + "epoch": 0.61, + "learning_rate": 8.034514894420382e-06, + "loss": 0.804, + "step": 5785 + }, + { + "epoch": 0.61, + "learning_rate": 8.030926172538122e-06, + "loss": 0.7958, + "step": 5786 + }, + { + "epoch": 0.61, + "learning_rate": 8.02733771446116e-06, + "loss": 0.7608, + "step": 5787 + }, + { + "epoch": 0.61, + "learning_rate": 8.023749520670261e-06, + "loss": 0.7792, + "step": 5788 + }, + { + "epoch": 0.61, + "learning_rate": 8.020161591646147e-06, + "loss": 0.7293, + "step": 5789 + }, + { + "epoch": 0.61, + "learning_rate": 8.016573927869511e-06, + "loss": 1.1287, + "step": 5790 + }, + { + "epoch": 0.61, + "learning_rate": 8.012986529821004e-06, + "loss": 1.3344, + "step": 5791 + }, + { + "epoch": 0.61, + "learning_rate": 8.009399397981248e-06, + "loss": 1.4415, + "step": 5792 + }, + { + "epoch": 0.61, + "learning_rate": 8.005812532830826e-06, + "loss": 1.4265, + "step": 5793 + }, + { + "epoch": 0.61, + "learning_rate": 8.002225934850287e-06, + "loss": 1.3429, + "step": 5794 + }, + { + "epoch": 0.61, + "learning_rate": 7.998639604520137e-06, + "loss": 1.3653, + "step": 5795 + }, + { + "epoch": 0.61, + "learning_rate": 7.995053542320861e-06, + "loss": 1.486, + "step": 5796 + }, + { + "epoch": 0.61, + "learning_rate": 7.991467748732894e-06, + "loss": 1.3389, + "step": 5797 + }, + { + "epoch": 0.61, + "learning_rate": 7.98788222423664e-06, + "loss": 1.3206, + "step": 5798 + }, + { + "epoch": 0.61, + "learning_rate": 7.984296969312468e-06, + "loss": 1.3121, + "step": 5799 + }, + { + "epoch": 0.61, + "learning_rate": 7.980711984440712e-06, + "loss": 1.3512, + "step": 5800 + }, + { + "epoch": 0.61, + "learning_rate": 7.977127270101665e-06, + "loss": 1.3291, + "step": 5801 + }, + { + "epoch": 0.61, + "learning_rate": 7.97354282677559e-06, + "loss": 1.3948, + "step": 5802 + }, + { + "epoch": 0.61, + "learning_rate": 7.969958654942704e-06, + "loss": 1.3076, + "step": 5803 + }, + { + "epoch": 0.61, + "learning_rate": 7.966374755083202e-06, + "loss": 1.3838, + "step": 5804 + }, + { + "epoch": 0.61, + "learning_rate": 7.962791127677228e-06, + "loss": 1.4205, + "step": 5805 + }, + { + "epoch": 0.61, + "learning_rate": 7.959207773204899e-06, + "loss": 1.3635, + "step": 5806 + }, + { + "epoch": 0.61, + "learning_rate": 7.955624692146293e-06, + "loss": 1.3299, + "step": 5807 + }, + { + "epoch": 0.61, + "learning_rate": 7.95204188498145e-06, + "loss": 1.4435, + "step": 5808 + }, + { + "epoch": 0.61, + "learning_rate": 7.948459352190372e-06, + "loss": 1.4335, + "step": 5809 + }, + { + "epoch": 0.61, + "learning_rate": 7.944877094253027e-06, + "loss": 1.3391, + "step": 5810 + }, + { + "epoch": 0.61, + "learning_rate": 7.94129511164935e-06, + "loss": 1.2852, + "step": 5811 + }, + { + "epoch": 0.61, + "learning_rate": 7.93771340485923e-06, + "loss": 1.3174, + "step": 5812 + }, + { + "epoch": 0.61, + "learning_rate": 7.934131974362527e-06, + "loss": 1.3415, + "step": 5813 + }, + { + "epoch": 0.61, + "learning_rate": 7.930550820639055e-06, + "loss": 1.2764, + "step": 5814 + }, + { + "epoch": 0.61, + "learning_rate": 7.926969944168603e-06, + "loss": 1.2978, + "step": 5815 + }, + { + "epoch": 0.61, + "learning_rate": 7.923389345430911e-06, + "loss": 1.3046, + "step": 5816 + }, + { + "epoch": 0.61, + "learning_rate": 7.919809024905694e-06, + "loss": 1.3484, + "step": 5817 + }, + { + "epoch": 0.61, + "learning_rate": 7.916228983072614e-06, + "loss": 1.3207, + "step": 5818 + }, + { + "epoch": 0.61, + "learning_rate": 7.912649220411312e-06, + "loss": 1.4289, + "step": 5819 + }, + { + "epoch": 0.61, + "learning_rate": 7.909069737401382e-06, + "loss": 1.4359, + "step": 5820 + }, + { + "epoch": 0.61, + "learning_rate": 7.905490534522384e-06, + "loss": 1.3316, + "step": 5821 + }, + { + "epoch": 0.61, + "learning_rate": 7.901911612253834e-06, + "loss": 1.3112, + "step": 5822 + }, + { + "epoch": 0.61, + "learning_rate": 7.898332971075221e-06, + "loss": 1.3318, + "step": 5823 + }, + { + "epoch": 0.61, + "learning_rate": 7.894754611465992e-06, + "loss": 1.4373, + "step": 5824 + }, + { + "epoch": 0.61, + "learning_rate": 7.891176533905549e-06, + "loss": 1.2938, + "step": 5825 + }, + { + "epoch": 0.61, + "learning_rate": 7.887598738873266e-06, + "loss": 1.3471, + "step": 5826 + }, + { + "epoch": 0.61, + "learning_rate": 7.884021226848478e-06, + "loss": 1.2999, + "step": 5827 + }, + { + "epoch": 0.61, + "learning_rate": 7.880443998310475e-06, + "loss": 1.35, + "step": 5828 + }, + { + "epoch": 0.61, + "learning_rate": 7.876867053738517e-06, + "loss": 1.3307, + "step": 5829 + }, + { + "epoch": 0.61, + "learning_rate": 7.87329039361182e-06, + "loss": 1.393, + "step": 5830 + }, + { + "epoch": 0.61, + "learning_rate": 7.869714018409568e-06, + "loss": 1.2933, + "step": 5831 + }, + { + "epoch": 0.61, + "learning_rate": 7.866137928610903e-06, + "loss": 1.319, + "step": 5832 + }, + { + "epoch": 0.61, + "learning_rate": 7.862562124694925e-06, + "loss": 1.3088, + "step": 5833 + }, + { + "epoch": 0.61, + "learning_rate": 7.858986607140705e-06, + "loss": 1.2941, + "step": 5834 + }, + { + "epoch": 0.61, + "learning_rate": 7.855411376427267e-06, + "loss": 1.3214, + "step": 5835 + }, + { + "epoch": 0.61, + "learning_rate": 7.851836433033602e-06, + "loss": 1.2991, + "step": 5836 + }, + { + "epoch": 0.61, + "learning_rate": 7.848261777438656e-06, + "loss": 1.3117, + "step": 5837 + }, + { + "epoch": 0.61, + "learning_rate": 7.844687410121348e-06, + "loss": 1.2905, + "step": 5838 + }, + { + "epoch": 0.61, + "learning_rate": 7.841113331560548e-06, + "loss": 1.3688, + "step": 5839 + }, + { + "epoch": 0.61, + "learning_rate": 7.837539542235091e-06, + "loss": 1.3987, + "step": 5840 + }, + { + "epoch": 0.61, + "learning_rate": 7.83396604262377e-06, + "loss": 1.2693, + "step": 5841 + }, + { + "epoch": 0.61, + "learning_rate": 7.830392833205348e-06, + "loss": 1.3205, + "step": 5842 + }, + { + "epoch": 0.61, + "learning_rate": 7.826819914458538e-06, + "loss": 1.3325, + "step": 5843 + }, + { + "epoch": 0.61, + "learning_rate": 7.823247286862024e-06, + "loss": 1.3451, + "step": 5844 + }, + { + "epoch": 0.61, + "learning_rate": 7.81967495089444e-06, + "loss": 1.3484, + "step": 5845 + }, + { + "epoch": 0.61, + "learning_rate": 7.816102907034395e-06, + "loss": 1.4949, + "step": 5846 + }, + { + "epoch": 0.61, + "learning_rate": 7.812531155760445e-06, + "loss": 1.4293, + "step": 5847 + }, + { + "epoch": 0.61, + "learning_rate": 7.808959697551113e-06, + "loss": 1.4314, + "step": 5848 + }, + { + "epoch": 0.61, + "learning_rate": 7.805388532884887e-06, + "loss": 1.3188, + "step": 5849 + }, + { + "epoch": 0.61, + "learning_rate": 7.80181766224021e-06, + "loss": 1.4396, + "step": 5850 + }, + { + "epoch": 0.61, + "learning_rate": 7.798247086095484e-06, + "loss": 1.3448, + "step": 5851 + }, + { + "epoch": 0.61, + "learning_rate": 7.794676804929075e-06, + "loss": 1.3591, + "step": 5852 + }, + { + "epoch": 0.61, + "learning_rate": 7.791106819219311e-06, + "loss": 1.3108, + "step": 5853 + }, + { + "epoch": 0.61, + "learning_rate": 7.78753712944448e-06, + "loss": 1.3773, + "step": 5854 + }, + { + "epoch": 0.61, + "learning_rate": 7.783967736082824e-06, + "loss": 1.3313, + "step": 5855 + }, + { + "epoch": 0.61, + "learning_rate": 7.780398639612551e-06, + "loss": 1.3635, + "step": 5856 + }, + { + "epoch": 0.61, + "learning_rate": 7.776829840511833e-06, + "loss": 1.3225, + "step": 5857 + }, + { + "epoch": 0.61, + "learning_rate": 7.773261339258792e-06, + "loss": 1.3142, + "step": 5858 + }, + { + "epoch": 0.61, + "learning_rate": 7.769693136331519e-06, + "loss": 1.3337, + "step": 5859 + }, + { + "epoch": 0.61, + "learning_rate": 7.766125232208057e-06, + "loss": 1.5289, + "step": 5860 + }, + { + "epoch": 0.61, + "learning_rate": 7.762557627366418e-06, + "loss": 1.573, + "step": 5861 + }, + { + "epoch": 0.61, + "learning_rate": 7.758990322284568e-06, + "loss": 1.322, + "step": 5862 + }, + { + "epoch": 0.61, + "learning_rate": 7.755423317440432e-06, + "loss": 1.3281, + "step": 5863 + }, + { + "epoch": 0.61, + "learning_rate": 7.751856613311899e-06, + "loss": 1.3405, + "step": 5864 + }, + { + "epoch": 0.62, + "learning_rate": 7.748290210376817e-06, + "loss": 1.3083, + "step": 5865 + }, + { + "epoch": 0.62, + "learning_rate": 7.744724109112991e-06, + "loss": 1.3587, + "step": 5866 + }, + { + "epoch": 0.62, + "learning_rate": 7.741158309998188e-06, + "loss": 1.3204, + "step": 5867 + }, + { + "epoch": 0.62, + "learning_rate": 7.73759281351013e-06, + "loss": 1.343, + "step": 5868 + }, + { + "epoch": 0.62, + "learning_rate": 7.734027620126507e-06, + "loss": 1.2874, + "step": 5869 + }, + { + "epoch": 0.62, + "learning_rate": 7.73046273032496e-06, + "loss": 1.3306, + "step": 5870 + }, + { + "epoch": 0.62, + "learning_rate": 7.72689814458309e-06, + "loss": 1.3958, + "step": 5871 + }, + { + "epoch": 0.62, + "learning_rate": 7.723333863378465e-06, + "loss": 1.3135, + "step": 5872 + }, + { + "epoch": 0.62, + "learning_rate": 7.719769887188608e-06, + "loss": 1.3241, + "step": 5873 + }, + { + "epoch": 0.62, + "learning_rate": 7.716206216490995e-06, + "loss": 1.3487, + "step": 5874 + }, + { + "epoch": 0.62, + "learning_rate": 7.712642851763067e-06, + "loss": 1.0263, + "step": 5875 + }, + { + "epoch": 0.62, + "learning_rate": 7.709079793482228e-06, + "loss": 1.4238, + "step": 5876 + }, + { + "epoch": 0.62, + "learning_rate": 7.705517042125833e-06, + "loss": 1.3284, + "step": 5877 + }, + { + "epoch": 0.62, + "learning_rate": 7.701954598171199e-06, + "loss": 1.2965, + "step": 5878 + }, + { + "epoch": 0.62, + "learning_rate": 7.698392462095601e-06, + "loss": 1.3578, + "step": 5879 + }, + { + "epoch": 0.62, + "learning_rate": 7.694830634376278e-06, + "loss": 1.3711, + "step": 5880 + }, + { + "epoch": 0.62, + "learning_rate": 7.69126911549042e-06, + "loss": 1.3274, + "step": 5881 + }, + { + "epoch": 0.62, + "learning_rate": 7.687707905915181e-06, + "loss": 1.4208, + "step": 5882 + }, + { + "epoch": 0.62, + "learning_rate": 7.684147006127665e-06, + "loss": 1.3478, + "step": 5883 + }, + { + "epoch": 0.62, + "learning_rate": 7.68058641660495e-06, + "loss": 1.2997, + "step": 5884 + }, + { + "epoch": 0.62, + "learning_rate": 7.67702613782406e-06, + "loss": 1.2981, + "step": 5885 + }, + { + "epoch": 0.62, + "learning_rate": 7.67346617026198e-06, + "loss": 1.3834, + "step": 5886 + }, + { + "epoch": 0.62, + "learning_rate": 7.669906514395654e-06, + "loss": 1.3585, + "step": 5887 + }, + { + "epoch": 0.62, + "learning_rate": 7.666347170701986e-06, + "loss": 1.3282, + "step": 5888 + }, + { + "epoch": 0.62, + "learning_rate": 7.662788139657838e-06, + "loss": 1.3397, + "step": 5889 + }, + { + "epoch": 0.62, + "learning_rate": 7.659229421740024e-06, + "loss": 1.3367, + "step": 5890 + }, + { + "epoch": 0.62, + "learning_rate": 7.655671017425322e-06, + "loss": 1.3497, + "step": 5891 + }, + { + "epoch": 0.62, + "learning_rate": 7.65211292719047e-06, + "loss": 1.3661, + "step": 5892 + }, + { + "epoch": 0.62, + "learning_rate": 7.64855515151216e-06, + "loss": 1.2793, + "step": 5893 + }, + { + "epoch": 0.62, + "learning_rate": 7.644997690867037e-06, + "loss": 1.3288, + "step": 5894 + }, + { + "epoch": 0.62, + "learning_rate": 7.641440545731717e-06, + "loss": 1.3877, + "step": 5895 + }, + { + "epoch": 0.62, + "learning_rate": 7.637883716582764e-06, + "loss": 1.4467, + "step": 5896 + }, + { + "epoch": 0.62, + "learning_rate": 7.634327203896698e-06, + "loss": 1.304, + "step": 5897 + }, + { + "epoch": 0.62, + "learning_rate": 7.630771008150002e-06, + "loss": 1.374, + "step": 5898 + }, + { + "epoch": 0.62, + "learning_rate": 7.627215129819118e-06, + "loss": 1.3893, + "step": 5899 + }, + { + "epoch": 0.62, + "learning_rate": 7.623659569380439e-06, + "loss": 1.325, + "step": 5900 + }, + { + "epoch": 0.62, + "learning_rate": 7.620104327310319e-06, + "loss": 1.2495, + "step": 5901 + }, + { + "epoch": 0.62, + "learning_rate": 7.616549404085068e-06, + "loss": 1.4034, + "step": 5902 + }, + { + "epoch": 0.62, + "learning_rate": 7.61299480018096e-06, + "loss": 1.2758, + "step": 5903 + }, + { + "epoch": 0.62, + "learning_rate": 7.609440516074215e-06, + "loss": 1.4203, + "step": 5904 + }, + { + "epoch": 0.62, + "learning_rate": 7.605886552241017e-06, + "loss": 1.3162, + "step": 5905 + }, + { + "epoch": 0.62, + "learning_rate": 7.602332909157505e-06, + "loss": 1.3368, + "step": 5906 + }, + { + "epoch": 0.62, + "learning_rate": 7.598779587299778e-06, + "loss": 1.314, + "step": 5907 + }, + { + "epoch": 0.62, + "learning_rate": 7.59522658714389e-06, + "loss": 1.3332, + "step": 5908 + }, + { + "epoch": 0.62, + "learning_rate": 7.5916739091658505e-06, + "loss": 1.3513, + "step": 5909 + }, + { + "epoch": 0.62, + "learning_rate": 7.5881215538416255e-06, + "loss": 1.3767, + "step": 5910 + }, + { + "epoch": 0.62, + "learning_rate": 7.5845695216471426e-06, + "loss": 1.3651, + "step": 5911 + }, + { + "epoch": 0.62, + "learning_rate": 7.581017813058283e-06, + "loss": 1.2676, + "step": 5912 + }, + { + "epoch": 0.62, + "learning_rate": 7.57746642855088e-06, + "loss": 1.3509, + "step": 5913 + }, + { + "epoch": 0.62, + "learning_rate": 7.5739153686007305e-06, + "loss": 1.2854, + "step": 5914 + }, + { + "epoch": 0.62, + "learning_rate": 7.570364633683586e-06, + "loss": 1.4041, + "step": 5915 + }, + { + "epoch": 0.62, + "learning_rate": 7.5668142242751545e-06, + "loss": 1.3218, + "step": 5916 + }, + { + "epoch": 0.62, + "learning_rate": 7.563264140851095e-06, + "loss": 1.398, + "step": 5917 + }, + { + "epoch": 0.62, + "learning_rate": 7.559714383887033e-06, + "loss": 1.3495, + "step": 5918 + }, + { + "epoch": 0.62, + "learning_rate": 7.556164953858543e-06, + "loss": 1.365, + "step": 5919 + }, + { + "epoch": 0.62, + "learning_rate": 7.552615851241157e-06, + "loss": 1.4611, + "step": 5920 + }, + { + "epoch": 0.62, + "learning_rate": 7.549067076510361e-06, + "loss": 1.4031, + "step": 5921 + }, + { + "epoch": 0.62, + "learning_rate": 7.545518630141605e-06, + "loss": 1.2745, + "step": 5922 + }, + { + "epoch": 0.62, + "learning_rate": 7.541970512610286e-06, + "loss": 1.3435, + "step": 5923 + }, + { + "epoch": 0.62, + "learning_rate": 7.538422724391761e-06, + "loss": 1.3433, + "step": 5924 + }, + { + "epoch": 0.62, + "learning_rate": 7.534875265961341e-06, + "loss": 1.3605, + "step": 5925 + }, + { + "epoch": 0.62, + "learning_rate": 7.5313281377942985e-06, + "loss": 1.3896, + "step": 5926 + }, + { + "epoch": 0.62, + "learning_rate": 7.527781340365854e-06, + "loss": 1.3922, + "step": 5927 + }, + { + "epoch": 0.62, + "learning_rate": 7.524234874151189e-06, + "loss": 1.3305, + "step": 5928 + }, + { + "epoch": 0.62, + "learning_rate": 7.520688739625436e-06, + "loss": 1.3117, + "step": 5929 + }, + { + "epoch": 0.62, + "learning_rate": 7.51714293726369e-06, + "loss": 1.3581, + "step": 5930 + }, + { + "epoch": 0.62, + "learning_rate": 7.5135974675409955e-06, + "loss": 1.3973, + "step": 5931 + }, + { + "epoch": 0.62, + "learning_rate": 7.510052330932354e-06, + "loss": 1.3499, + "step": 5932 + }, + { + "epoch": 0.62, + "learning_rate": 7.506507527912721e-06, + "loss": 1.3068, + "step": 5933 + }, + { + "epoch": 0.62, + "learning_rate": 7.502963058957014e-06, + "loss": 1.3689, + "step": 5934 + }, + { + "epoch": 0.62, + "learning_rate": 7.499418924540096e-06, + "loss": 1.3356, + "step": 5935 + }, + { + "epoch": 0.62, + "learning_rate": 7.495875125136793e-06, + "loss": 1.2593, + "step": 5936 + }, + { + "epoch": 0.62, + "learning_rate": 7.492331661221881e-06, + "loss": 1.272, + "step": 5937 + }, + { + "epoch": 0.62, + "learning_rate": 7.488788533270093e-06, + "loss": 1.3552, + "step": 5938 + }, + { + "epoch": 0.62, + "learning_rate": 7.485245741756121e-06, + "loss": 1.3425, + "step": 5939 + }, + { + "epoch": 0.62, + "learning_rate": 7.481703287154602e-06, + "loss": 1.3694, + "step": 5940 + }, + { + "epoch": 0.62, + "learning_rate": 7.478161169940139e-06, + "loss": 1.3281, + "step": 5941 + }, + { + "epoch": 0.62, + "learning_rate": 7.4746193905872825e-06, + "loss": 1.3109, + "step": 5942 + }, + { + "epoch": 0.62, + "learning_rate": 7.47107794957054e-06, + "loss": 1.5121, + "step": 5943 + }, + { + "epoch": 0.62, + "learning_rate": 7.467536847364372e-06, + "loss": 1.4472, + "step": 5944 + }, + { + "epoch": 0.62, + "learning_rate": 7.463996084443198e-06, + "loss": 1.4615, + "step": 5945 + }, + { + "epoch": 0.62, + "learning_rate": 7.460455661281389e-06, + "loss": 1.3764, + "step": 5946 + }, + { + "epoch": 0.62, + "learning_rate": 7.45691557835327e-06, + "loss": 1.3091, + "step": 5947 + }, + { + "epoch": 0.62, + "learning_rate": 7.4533758361331185e-06, + "loss": 1.1841, + "step": 5948 + }, + { + "epoch": 0.62, + "learning_rate": 7.449836435095175e-06, + "loss": 1.3345, + "step": 5949 + }, + { + "epoch": 0.62, + "learning_rate": 7.446297375713622e-06, + "loss": 1.3573, + "step": 5950 + }, + { + "epoch": 0.62, + "learning_rate": 7.442758658462608e-06, + "loss": 1.3161, + "step": 5951 + }, + { + "epoch": 0.62, + "learning_rate": 7.4392202838162245e-06, + "loss": 1.3089, + "step": 5952 + }, + { + "epoch": 0.62, + "learning_rate": 7.435682252248528e-06, + "loss": 1.3069, + "step": 5953 + }, + { + "epoch": 0.62, + "learning_rate": 7.4321445642335234e-06, + "loss": 1.2969, + "step": 5954 + }, + { + "epoch": 0.62, + "learning_rate": 7.428607220245165e-06, + "loss": 1.4706, + "step": 5955 + }, + { + "epoch": 0.62, + "learning_rate": 7.42507022075737e-06, + "loss": 1.3028, + "step": 5956 + }, + { + "epoch": 0.62, + "learning_rate": 7.421533566244006e-06, + "loss": 1.2786, + "step": 5957 + }, + { + "epoch": 0.62, + "learning_rate": 7.417997257178893e-06, + "loss": 1.3534, + "step": 5958 + }, + { + "epoch": 0.62, + "learning_rate": 7.414461294035804e-06, + "loss": 1.2829, + "step": 5959 + }, + { + "epoch": 0.62, + "learning_rate": 7.410925677288467e-06, + "loss": 1.3626, + "step": 5960 + }, + { + "epoch": 0.63, + "learning_rate": 7.407390407410566e-06, + "loss": 1.4531, + "step": 5961 + }, + { + "epoch": 0.63, + "learning_rate": 7.4038554848757375e-06, + "loss": 1.3549, + "step": 5962 + }, + { + "epoch": 0.63, + "learning_rate": 7.400320910157563e-06, + "loss": 1.3407, + "step": 5963 + }, + { + "epoch": 0.63, + "learning_rate": 7.396786683729595e-06, + "loss": 1.2736, + "step": 5964 + }, + { + "epoch": 0.63, + "learning_rate": 7.393252806065323e-06, + "loss": 1.3377, + "step": 5965 + }, + { + "epoch": 0.63, + "learning_rate": 7.389719277638196e-06, + "loss": 1.3479, + "step": 5966 + }, + { + "epoch": 0.63, + "learning_rate": 7.3861860989216175e-06, + "loss": 1.3605, + "step": 5967 + }, + { + "epoch": 0.63, + "learning_rate": 7.382653270388942e-06, + "loss": 1.3175, + "step": 5968 + }, + { + "epoch": 0.63, + "learning_rate": 7.379120792513477e-06, + "loss": 1.3072, + "step": 5969 + }, + { + "epoch": 0.63, + "learning_rate": 7.375588665768485e-06, + "loss": 1.3224, + "step": 5970 + }, + { + "epoch": 0.63, + "eval_loss": 1.4110088348388672, + "eval_runtime": 77.5326, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 5970 + }, + { + "epoch": 0.63, + "learning_rate": 7.37205689062718e-06, + "loss": 1.3491, + "step": 5971 + }, + { + "epoch": 0.63, + "learning_rate": 7.368525467562728e-06, + "loss": 1.3289, + "step": 5972 + }, + { + "epoch": 0.63, + "learning_rate": 7.364994397048251e-06, + "loss": 1.3362, + "step": 5973 + }, + { + "epoch": 0.63, + "learning_rate": 7.36146367955682e-06, + "loss": 1.3754, + "step": 5974 + }, + { + "epoch": 0.63, + "learning_rate": 7.3579333155614585e-06, + "loss": 1.3159, + "step": 5975 + }, + { + "epoch": 0.63, + "learning_rate": 7.354403305535149e-06, + "loss": 1.4366, + "step": 5976 + }, + { + "epoch": 0.63, + "learning_rate": 7.350873649950822e-06, + "loss": 1.3243, + "step": 5977 + }, + { + "epoch": 0.63, + "learning_rate": 7.347344349281358e-06, + "loss": 1.2911, + "step": 5978 + }, + { + "epoch": 0.63, + "learning_rate": 7.34381540399959e-06, + "loss": 1.338, + "step": 5979 + }, + { + "epoch": 0.63, + "learning_rate": 7.340286814578312e-06, + "loss": 1.3241, + "step": 5980 + }, + { + "epoch": 0.63, + "learning_rate": 7.336758581490263e-06, + "loss": 1.3427, + "step": 5981 + }, + { + "epoch": 0.63, + "learning_rate": 7.333230705208134e-06, + "loss": 1.3328, + "step": 5982 + }, + { + "epoch": 0.63, + "learning_rate": 7.3297031862045676e-06, + "loss": 1.2857, + "step": 5983 + }, + { + "epoch": 0.63, + "learning_rate": 7.3261760249521655e-06, + "loss": 1.9065, + "step": 5984 + }, + { + "epoch": 0.63, + "learning_rate": 7.322649221923473e-06, + "loss": 1.3797, + "step": 5985 + }, + { + "epoch": 0.63, + "learning_rate": 7.3191227775909925e-06, + "loss": 1.2343, + "step": 5986 + }, + { + "epoch": 0.63, + "learning_rate": 7.315596692427178e-06, + "loss": 1.3479, + "step": 5987 + }, + { + "epoch": 0.63, + "learning_rate": 7.312070966904432e-06, + "loss": 1.3226, + "step": 5988 + }, + { + "epoch": 0.63, + "learning_rate": 7.308545601495114e-06, + "loss": 1.3329, + "step": 5989 + }, + { + "epoch": 0.63, + "learning_rate": 7.305020596671528e-06, + "loss": 1.3285, + "step": 5990 + }, + { + "epoch": 0.63, + "learning_rate": 7.301495952905939e-06, + "loss": 1.3635, + "step": 5991 + }, + { + "epoch": 0.63, + "learning_rate": 7.297971670670556e-06, + "loss": 1.3343, + "step": 5992 + }, + { + "epoch": 0.63, + "learning_rate": 7.294447750437543e-06, + "loss": 1.3943, + "step": 5993 + }, + { + "epoch": 0.63, + "learning_rate": 7.290924192679014e-06, + "loss": 1.4601, + "step": 5994 + }, + { + "epoch": 0.63, + "learning_rate": 7.287400997867036e-06, + "loss": 1.3813, + "step": 5995 + }, + { + "epoch": 0.63, + "learning_rate": 7.2838781664736266e-06, + "loss": 1.3505, + "step": 5996 + }, + { + "epoch": 0.63, + "learning_rate": 7.2803556989707555e-06, + "loss": 1.3062, + "step": 5997 + }, + { + "epoch": 0.63, + "learning_rate": 7.276833595830338e-06, + "loss": 1.4504, + "step": 5998 + }, + { + "epoch": 0.63, + "learning_rate": 7.273311857524252e-06, + "loss": 1.4935, + "step": 5999 + }, + { + "epoch": 0.63, + "learning_rate": 7.269790484524317e-06, + "loss": 1.296, + "step": 6000 + }, + { + "epoch": 0.63, + "learning_rate": 7.266269477302308e-06, + "loss": 1.3469, + "step": 6001 + }, + { + "epoch": 0.63, + "learning_rate": 7.262748836329944e-06, + "loss": 1.3586, + "step": 6002 + }, + { + "epoch": 0.63, + "learning_rate": 7.259228562078908e-06, + "loss": 1.3643, + "step": 6003 + }, + { + "epoch": 0.63, + "learning_rate": 7.255708655020821e-06, + "loss": 1.3096, + "step": 6004 + }, + { + "epoch": 0.63, + "learning_rate": 7.252189115627264e-06, + "loss": 1.3163, + "step": 6005 + }, + { + "epoch": 0.63, + "learning_rate": 7.2486699443697595e-06, + "loss": 1.3526, + "step": 6006 + }, + { + "epoch": 0.63, + "learning_rate": 7.245151141719793e-06, + "loss": 1.401, + "step": 6007 + }, + { + "epoch": 0.63, + "learning_rate": 7.241632708148788e-06, + "loss": 1.2651, + "step": 6008 + }, + { + "epoch": 0.63, + "learning_rate": 7.238114644128124e-06, + "loss": 1.348, + "step": 6009 + }, + { + "epoch": 0.63, + "learning_rate": 7.234596950129137e-06, + "loss": 1.6934, + "step": 6010 + }, + { + "epoch": 0.63, + "learning_rate": 7.231079626623103e-06, + "loss": 1.3382, + "step": 6011 + }, + { + "epoch": 0.63, + "learning_rate": 7.227562674081254e-06, + "loss": 1.2925, + "step": 6012 + }, + { + "epoch": 0.63, + "learning_rate": 7.22404609297477e-06, + "loss": 1.3365, + "step": 6013 + }, + { + "epoch": 0.63, + "learning_rate": 7.220529883774785e-06, + "loss": 1.3169, + "step": 6014 + }, + { + "epoch": 0.63, + "learning_rate": 7.217014046952379e-06, + "loss": 1.319, + "step": 6015 + }, + { + "epoch": 0.63, + "learning_rate": 7.2134985829785846e-06, + "loss": 1.4049, + "step": 6016 + }, + { + "epoch": 0.63, + "learning_rate": 7.209983492324382e-06, + "loss": 1.2947, + "step": 6017 + }, + { + "epoch": 0.63, + "learning_rate": 7.206468775460704e-06, + "loss": 1.2854, + "step": 6018 + }, + { + "epoch": 0.63, + "learning_rate": 7.202954432858436e-06, + "loss": 1.3381, + "step": 6019 + }, + { + "epoch": 0.63, + "learning_rate": 7.199440464988403e-06, + "loss": 1.3912, + "step": 6020 + }, + { + "epoch": 0.63, + "learning_rate": 7.195926872321391e-06, + "loss": 1.384, + "step": 6021 + }, + { + "epoch": 0.63, + "learning_rate": 7.192413655328129e-06, + "loss": 1.2909, + "step": 6022 + }, + { + "epoch": 0.63, + "learning_rate": 7.188900814479299e-06, + "loss": 1.2951, + "step": 6023 + }, + { + "epoch": 0.63, + "learning_rate": 7.185388350245532e-06, + "loss": 1.2655, + "step": 6024 + }, + { + "epoch": 0.63, + "learning_rate": 7.1818762630974035e-06, + "loss": 1.3288, + "step": 6025 + }, + { + "epoch": 0.63, + "learning_rate": 7.17836455350545e-06, + "loss": 1.2873, + "step": 6026 + }, + { + "epoch": 0.63, + "learning_rate": 7.174853221940146e-06, + "loss": 1.3027, + "step": 6027 + }, + { + "epoch": 0.63, + "learning_rate": 7.17134226887192e-06, + "loss": 1.3273, + "step": 6028 + }, + { + "epoch": 0.63, + "learning_rate": 7.167831694771149e-06, + "loss": 1.3096, + "step": 6029 + }, + { + "epoch": 0.63, + "learning_rate": 7.1643215001081625e-06, + "loss": 1.2904, + "step": 6030 + }, + { + "epoch": 0.63, + "learning_rate": 7.160811685353234e-06, + "loss": 1.2977, + "step": 6031 + }, + { + "epoch": 0.63, + "learning_rate": 7.157302250976588e-06, + "loss": 1.3281, + "step": 6032 + }, + { + "epoch": 0.63, + "learning_rate": 7.1537931974483996e-06, + "loss": 1.3831, + "step": 6033 + }, + { + "epoch": 0.63, + "learning_rate": 7.150284525238794e-06, + "loss": 1.3173, + "step": 6034 + }, + { + "epoch": 0.63, + "learning_rate": 7.146776234817841e-06, + "loss": 1.4148, + "step": 6035 + }, + { + "epoch": 0.63, + "learning_rate": 7.143268326655557e-06, + "loss": 1.3381, + "step": 6036 + }, + { + "epoch": 0.63, + "learning_rate": 7.13976080122192e-06, + "loss": 1.3221, + "step": 6037 + }, + { + "epoch": 0.63, + "learning_rate": 7.136253658986843e-06, + "loss": 1.4373, + "step": 6038 + }, + { + "epoch": 0.63, + "learning_rate": 7.132746900420195e-06, + "loss": 1.3758, + "step": 6039 + }, + { + "epoch": 0.63, + "learning_rate": 7.129240525991788e-06, + "loss": 1.3964, + "step": 6040 + }, + { + "epoch": 0.63, + "learning_rate": 7.125734536171391e-06, + "loss": 1.3136, + "step": 6041 + }, + { + "epoch": 0.63, + "learning_rate": 7.122228931428715e-06, + "loss": 1.2195, + "step": 6042 + }, + { + "epoch": 0.63, + "learning_rate": 7.11872371223342e-06, + "loss": 1.3842, + "step": 6043 + }, + { + "epoch": 0.63, + "learning_rate": 7.115218879055113e-06, + "loss": 1.3369, + "step": 6044 + }, + { + "epoch": 0.63, + "learning_rate": 7.111714432363356e-06, + "loss": 1.2704, + "step": 6045 + }, + { + "epoch": 0.63, + "learning_rate": 7.108210372627653e-06, + "loss": 1.307, + "step": 6046 + }, + { + "epoch": 0.63, + "learning_rate": 7.104706700317459e-06, + "loss": 1.3024, + "step": 6047 + }, + { + "epoch": 0.63, + "learning_rate": 7.1012034159021715e-06, + "loss": 1.4157, + "step": 6048 + }, + { + "epoch": 0.63, + "learning_rate": 7.0977005198511475e-06, + "loss": 1.2314, + "step": 6049 + }, + { + "epoch": 0.63, + "learning_rate": 7.09419801263368e-06, + "loss": 1.4304, + "step": 6050 + }, + { + "epoch": 0.63, + "learning_rate": 7.090695894719019e-06, + "loss": 1.3085, + "step": 6051 + }, + { + "epoch": 0.63, + "learning_rate": 7.0871941665763525e-06, + "loss": 1.367, + "step": 6052 + }, + { + "epoch": 0.63, + "learning_rate": 7.083692828674827e-06, + "loss": 1.2913, + "step": 6053 + }, + { + "epoch": 0.63, + "learning_rate": 7.080191881483531e-06, + "loss": 1.3751, + "step": 6054 + }, + { + "epoch": 0.63, + "learning_rate": 7.0766913254714985e-06, + "loss": 1.3178, + "step": 6055 + }, + { + "epoch": 0.64, + "learning_rate": 7.07319116110772e-06, + "loss": 1.3182, + "step": 6056 + }, + { + "epoch": 0.64, + "learning_rate": 7.069691388861122e-06, + "loss": 1.373, + "step": 6057 + }, + { + "epoch": 0.64, + "learning_rate": 7.066192009200588e-06, + "loss": 1.3235, + "step": 6058 + }, + { + "epoch": 0.64, + "learning_rate": 7.0626930225949395e-06, + "loss": 1.3765, + "step": 6059 + }, + { + "epoch": 0.64, + "learning_rate": 7.0591944295129565e-06, + "loss": 1.4408, + "step": 6060 + }, + { + "epoch": 0.64, + "learning_rate": 7.055696230423359e-06, + "loss": 1.3271, + "step": 6061 + }, + { + "epoch": 0.64, + "learning_rate": 7.052198425794814e-06, + "loss": 1.2194, + "step": 6062 + }, + { + "epoch": 0.64, + "learning_rate": 7.048701016095938e-06, + "loss": 1.3707, + "step": 6063 + }, + { + "epoch": 0.64, + "learning_rate": 7.045204001795296e-06, + "loss": 1.3878, + "step": 6064 + }, + { + "epoch": 0.64, + "learning_rate": 7.041707383361396e-06, + "loss": 1.3674, + "step": 6065 + }, + { + "epoch": 0.64, + "learning_rate": 7.038211161262697e-06, + "loss": 1.4525, + "step": 6066 + }, + { + "epoch": 0.64, + "learning_rate": 7.034715335967599e-06, + "loss": 1.3801, + "step": 6067 + }, + { + "epoch": 0.64, + "learning_rate": 7.031219907944458e-06, + "loss": 1.4855, + "step": 6068 + }, + { + "epoch": 0.64, + "learning_rate": 7.027724877661568e-06, + "loss": 1.3659, + "step": 6069 + }, + { + "epoch": 0.64, + "learning_rate": 7.024230245587176e-06, + "loss": 1.3649, + "step": 6070 + }, + { + "epoch": 0.64, + "learning_rate": 7.020736012189467e-06, + "loss": 1.2629, + "step": 6071 + }, + { + "epoch": 0.64, + "learning_rate": 7.017242177936586e-06, + "loss": 1.2474, + "step": 6072 + }, + { + "epoch": 0.64, + "learning_rate": 7.013748743296614e-06, + "loss": 1.45, + "step": 6073 + }, + { + "epoch": 0.64, + "learning_rate": 7.010255708737581e-06, + "loss": 1.3624, + "step": 6074 + }, + { + "epoch": 0.64, + "learning_rate": 7.006763074727461e-06, + "loss": 0.9335, + "step": 6075 + }, + { + "epoch": 0.64, + "learning_rate": 7.0032708417341835e-06, + "loss": 0.6376, + "step": 6076 + }, + { + "epoch": 0.64, + "learning_rate": 6.999779010225613e-06, + "loss": 0.7882, + "step": 6077 + }, + { + "epoch": 0.64, + "learning_rate": 6.996287580669567e-06, + "loss": 1.3001, + "step": 6078 + }, + { + "epoch": 0.64, + "learning_rate": 6.9927965535338085e-06, + "loss": 1.323, + "step": 6079 + }, + { + "epoch": 0.64, + "learning_rate": 6.989305929286043e-06, + "loss": 1.3478, + "step": 6080 + }, + { + "epoch": 0.64, + "learning_rate": 6.985815708393928e-06, + "loss": 1.319, + "step": 6081 + }, + { + "epoch": 0.64, + "learning_rate": 6.9823258913250566e-06, + "loss": 1.3458, + "step": 6082 + }, + { + "epoch": 0.64, + "learning_rate": 6.978836478546985e-06, + "loss": 1.2481, + "step": 6083 + }, + { + "epoch": 0.64, + "learning_rate": 6.975347470527195e-06, + "loss": 1.4051, + "step": 6084 + }, + { + "epoch": 0.64, + "learning_rate": 6.97185886773313e-06, + "loss": 1.3705, + "step": 6085 + }, + { + "epoch": 0.64, + "learning_rate": 6.9683706706321676e-06, + "loss": 1.3415, + "step": 6086 + }, + { + "epoch": 0.64, + "learning_rate": 6.964882879691643e-06, + "loss": 1.3462, + "step": 6087 + }, + { + "epoch": 0.64, + "learning_rate": 6.961395495378829e-06, + "loss": 1.2974, + "step": 6088 + }, + { + "epoch": 0.64, + "learning_rate": 6.957908518160943e-06, + "loss": 1.3353, + "step": 6089 + }, + { + "epoch": 0.64, + "learning_rate": 6.95442194850515e-06, + "loss": 1.3073, + "step": 6090 + }, + { + "epoch": 0.64, + "learning_rate": 6.9509357868785636e-06, + "loss": 1.352, + "step": 6091 + }, + { + "epoch": 0.64, + "learning_rate": 6.9474500337482396e-06, + "loss": 1.2771, + "step": 6092 + }, + { + "epoch": 0.64, + "learning_rate": 6.943964689581177e-06, + "loss": 1.2925, + "step": 6093 + }, + { + "epoch": 0.64, + "learning_rate": 6.940479754844322e-06, + "loss": 1.2967, + "step": 6094 + }, + { + "epoch": 0.64, + "learning_rate": 6.93699523000457e-06, + "loss": 1.5839, + "step": 6095 + }, + { + "epoch": 0.64, + "learning_rate": 6.933511115528757e-06, + "loss": 1.3051, + "step": 6096 + }, + { + "epoch": 0.64, + "learning_rate": 6.930027411883664e-06, + "loss": 1.5344, + "step": 6097 + }, + { + "epoch": 0.64, + "learning_rate": 6.926544119536014e-06, + "loss": 1.3938, + "step": 6098 + }, + { + "epoch": 0.64, + "learning_rate": 6.923061238952484e-06, + "loss": 1.3504, + "step": 6099 + }, + { + "epoch": 0.64, + "learning_rate": 6.919578770599689e-06, + "loss": 1.3618, + "step": 6100 + }, + { + "epoch": 0.64, + "learning_rate": 6.916096714944187e-06, + "loss": 1.3811, + "step": 6101 + }, + { + "epoch": 0.64, + "learning_rate": 6.912615072452491e-06, + "loss": 1.2673, + "step": 6102 + }, + { + "epoch": 0.64, + "learning_rate": 6.909133843591046e-06, + "loss": 1.3661, + "step": 6103 + }, + { + "epoch": 0.64, + "learning_rate": 6.905653028826249e-06, + "loss": 1.3811, + "step": 6104 + }, + { + "epoch": 0.64, + "learning_rate": 6.902172628624437e-06, + "loss": 1.3399, + "step": 6105 + }, + { + "epoch": 0.64, + "learning_rate": 6.8986926434519e-06, + "loss": 1.281, + "step": 6106 + }, + { + "epoch": 0.64, + "learning_rate": 6.895213073774862e-06, + "loss": 1.3053, + "step": 6107 + }, + { + "epoch": 0.64, + "learning_rate": 6.891733920059498e-06, + "loss": 1.4573, + "step": 6108 + }, + { + "epoch": 0.64, + "learning_rate": 6.8882551827719215e-06, + "loss": 1.355, + "step": 6109 + }, + { + "epoch": 0.64, + "learning_rate": 6.8847768623782e-06, + "loss": 1.3304, + "step": 6110 + }, + { + "epoch": 0.64, + "learning_rate": 6.881298959344335e-06, + "loss": 1.4039, + "step": 6111 + }, + { + "epoch": 0.64, + "learning_rate": 6.877821474136277e-06, + "loss": 1.381, + "step": 6112 + }, + { + "epoch": 0.64, + "learning_rate": 6.874344407219917e-06, + "loss": 1.3503, + "step": 6113 + }, + { + "epoch": 0.64, + "learning_rate": 6.870867759061099e-06, + "loss": 1.2679, + "step": 6114 + }, + { + "epoch": 0.64, + "learning_rate": 6.8673915301256e-06, + "loss": 1.3286, + "step": 6115 + }, + { + "epoch": 0.64, + "learning_rate": 6.863915720879146e-06, + "loss": 1.3528, + "step": 6116 + }, + { + "epoch": 0.64, + "learning_rate": 6.8604403317874055e-06, + "loss": 1.3502, + "step": 6117 + }, + { + "epoch": 0.64, + "learning_rate": 6.856965363315993e-06, + "loss": 1.3507, + "step": 6118 + }, + { + "epoch": 0.64, + "learning_rate": 6.853490815930464e-06, + "loss": 1.2153, + "step": 6119 + }, + { + "epoch": 0.64, + "learning_rate": 6.850016690096319e-06, + "loss": 1.2435, + "step": 6120 + }, + { + "epoch": 0.64, + "learning_rate": 6.846542986279e-06, + "loss": 1.3418, + "step": 6121 + }, + { + "epoch": 0.64, + "learning_rate": 6.843069704943896e-06, + "loss": 1.371, + "step": 6122 + }, + { + "epoch": 0.64, + "learning_rate": 6.8395968465563375e-06, + "loss": 1.1737, + "step": 6123 + }, + { + "epoch": 0.64, + "learning_rate": 6.836124411581598e-06, + "loss": 1.3402, + "step": 6124 + }, + { + "epoch": 0.64, + "learning_rate": 6.8326524004848924e-06, + "loss": 1.3482, + "step": 6125 + }, + { + "epoch": 0.64, + "learning_rate": 6.8291808137313845e-06, + "loss": 1.4585, + "step": 6126 + }, + { + "epoch": 0.64, + "learning_rate": 6.825709651786176e-06, + "loss": 1.2848, + "step": 6127 + }, + { + "epoch": 0.64, + "learning_rate": 6.822238915114312e-06, + "loss": 1.2932, + "step": 6128 + }, + { + "epoch": 0.64, + "learning_rate": 6.818768604180785e-06, + "loss": 1.3124, + "step": 6129 + }, + { + "epoch": 0.64, + "learning_rate": 6.815298719450525e-06, + "loss": 1.2843, + "step": 6130 + }, + { + "epoch": 0.64, + "learning_rate": 6.811829261388409e-06, + "loss": 1.3024, + "step": 6131 + }, + { + "epoch": 0.64, + "learning_rate": 6.808360230459252e-06, + "loss": 1.3612, + "step": 6132 + }, + { + "epoch": 0.64, + "learning_rate": 6.804891627127821e-06, + "loss": 1.3005, + "step": 6133 + }, + { + "epoch": 0.64, + "learning_rate": 6.8014234518588154e-06, + "loss": 1.2614, + "step": 6134 + }, + { + "epoch": 0.64, + "learning_rate": 6.7979557051168835e-06, + "loss": 1.3717, + "step": 6135 + }, + { + "epoch": 0.64, + "learning_rate": 6.794488387366609e-06, + "loss": 1.3873, + "step": 6136 + }, + { + "epoch": 0.64, + "learning_rate": 6.791021499072532e-06, + "loss": 1.2955, + "step": 6137 + }, + { + "epoch": 0.64, + "learning_rate": 6.787555040699121e-06, + "loss": 1.4217, + "step": 6138 + }, + { + "epoch": 0.64, + "learning_rate": 6.784089012710793e-06, + "loss": 1.3805, + "step": 6139 + }, + { + "epoch": 0.64, + "learning_rate": 6.7806234155719055e-06, + "loss": 1.3982, + "step": 6140 + }, + { + "epoch": 0.64, + "learning_rate": 6.7771582497467635e-06, + "loss": 1.4, + "step": 6141 + }, + { + "epoch": 0.64, + "learning_rate": 6.773693515699607e-06, + "loss": 1.439, + "step": 6142 + }, + { + "epoch": 0.64, + "learning_rate": 6.7702292138946235e-06, + "loss": 1.3672, + "step": 6143 + }, + { + "epoch": 0.64, + "learning_rate": 6.7667653447959355e-06, + "loss": 1.2901, + "step": 6144 + }, + { + "epoch": 0.64, + "learning_rate": 6.763301908867619e-06, + "loss": 1.2873, + "step": 6145 + }, + { + "epoch": 0.64, + "learning_rate": 6.759838906573684e-06, + "loss": 1.3582, + "step": 6146 + }, + { + "epoch": 0.64, + "learning_rate": 6.756376338378077e-06, + "loss": 1.3562, + "step": 6147 + }, + { + "epoch": 0.64, + "learning_rate": 6.7529142047447025e-06, + "loss": 1.3091, + "step": 6148 + }, + { + "epoch": 0.64, + "learning_rate": 6.749452506137393e-06, + "loss": 1.4269, + "step": 6149 + }, + { + "epoch": 0.64, + "learning_rate": 6.745991243019927e-06, + "loss": 1.4184, + "step": 6150 + }, + { + "epoch": 0.65, + "learning_rate": 6.7425304158560235e-06, + "loss": 1.4201, + "step": 6151 + }, + { + "epoch": 0.65, + "learning_rate": 6.739070025109349e-06, + "loss": 1.3222, + "step": 6152 + }, + { + "epoch": 0.65, + "learning_rate": 6.7356100712435035e-06, + "loss": 1.3262, + "step": 6153 + }, + { + "epoch": 0.65, + "learning_rate": 6.732150554722034e-06, + "loss": 1.4408, + "step": 6154 + }, + { + "epoch": 0.65, + "learning_rate": 6.728691476008422e-06, + "loss": 1.3441, + "step": 6155 + }, + { + "epoch": 0.65, + "learning_rate": 6.725232835566102e-06, + "loss": 1.3316, + "step": 6156 + }, + { + "epoch": 0.65, + "learning_rate": 6.721774633858438e-06, + "loss": 1.3326, + "step": 6157 + }, + { + "epoch": 0.65, + "learning_rate": 6.7183168713487425e-06, + "loss": 1.3105, + "step": 6158 + }, + { + "epoch": 0.65, + "learning_rate": 6.714859548500265e-06, + "loss": 1.3144, + "step": 6159 + }, + { + "epoch": 0.65, + "learning_rate": 6.7114026657762e-06, + "loss": 1.3472, + "step": 6160 + }, + { + "epoch": 0.65, + "learning_rate": 6.707946223639681e-06, + "loss": 1.3811, + "step": 6161 + }, + { + "epoch": 0.65, + "learning_rate": 6.704490222553781e-06, + "loss": 1.2783, + "step": 6162 + }, + { + "epoch": 0.65, + "learning_rate": 6.701034662981513e-06, + "loss": 1.273, + "step": 6163 + }, + { + "epoch": 0.65, + "learning_rate": 6.697579545385839e-06, + "loss": 1.3522, + "step": 6164 + }, + { + "epoch": 0.65, + "learning_rate": 6.6941248702296524e-06, + "loss": 1.3861, + "step": 6165 + }, + { + "epoch": 0.65, + "learning_rate": 6.6906706379757915e-06, + "loss": 1.3098, + "step": 6166 + }, + { + "epoch": 0.65, + "learning_rate": 6.687216849087032e-06, + "loss": 1.3734, + "step": 6167 + }, + { + "epoch": 0.65, + "learning_rate": 6.6837635040261e-06, + "loss": 1.2289, + "step": 6168 + }, + { + "epoch": 0.65, + "learning_rate": 6.680310603255648e-06, + "loss": 1.3238, + "step": 6169 + }, + { + "epoch": 0.65, + "eval_loss": 1.40826416015625, + "eval_runtime": 77.483, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 6169 + }, + { + "epoch": 0.65, + "learning_rate": 6.676858147238277e-06, + "loss": 1.4317, + "step": 6170 + }, + { + "epoch": 0.65, + "learning_rate": 6.673406136436531e-06, + "loss": 1.3363, + "step": 6171 + }, + { + "epoch": 0.65, + "learning_rate": 6.669954571312889e-06, + "loss": 1.3377, + "step": 6172 + }, + { + "epoch": 0.65, + "learning_rate": 6.666503452329771e-06, + "loss": 1.3382, + "step": 6173 + }, + { + "epoch": 0.65, + "learning_rate": 6.663052779949538e-06, + "loss": 1.3028, + "step": 6174 + }, + { + "epoch": 0.65, + "learning_rate": 6.659602554634494e-06, + "loss": 1.3098, + "step": 6175 + }, + { + "epoch": 0.65, + "learning_rate": 6.656152776846879e-06, + "loss": 1.328, + "step": 6176 + }, + { + "epoch": 0.65, + "learning_rate": 6.652703447048874e-06, + "loss": 1.3014, + "step": 6177 + }, + { + "epoch": 0.65, + "learning_rate": 6.6492545657026e-06, + "loss": 1.2522, + "step": 6178 + }, + { + "epoch": 0.65, + "learning_rate": 6.645806133270121e-06, + "loss": 1.6113, + "step": 6179 + }, + { + "epoch": 0.65, + "learning_rate": 6.642358150213437e-06, + "loss": 1.3431, + "step": 6180 + }, + { + "epoch": 0.65, + "learning_rate": 6.638910616994489e-06, + "loss": 1.2725, + "step": 6181 + }, + { + "epoch": 0.65, + "learning_rate": 6.635463534075156e-06, + "loss": 1.3022, + "step": 6182 + }, + { + "epoch": 0.65, + "learning_rate": 6.632016901917262e-06, + "loss": 1.3496, + "step": 6183 + }, + { + "epoch": 0.65, + "learning_rate": 6.628570720982567e-06, + "loss": 1.2871, + "step": 6184 + }, + { + "epoch": 0.65, + "learning_rate": 6.625124991732767e-06, + "loss": 1.4449, + "step": 6185 + }, + { + "epoch": 0.65, + "learning_rate": 6.621679714629504e-06, + "loss": 1.4395, + "step": 6186 + }, + { + "epoch": 0.65, + "learning_rate": 6.618234890134356e-06, + "loss": 1.4088, + "step": 6187 + }, + { + "epoch": 0.65, + "learning_rate": 6.614790518708843e-06, + "loss": 1.371, + "step": 6188 + }, + { + "epoch": 0.65, + "learning_rate": 6.611346600814419e-06, + "loss": 1.28, + "step": 6189 + }, + { + "epoch": 0.65, + "learning_rate": 6.607903136912482e-06, + "loss": 1.3502, + "step": 6190 + }, + { + "epoch": 0.65, + "learning_rate": 6.604460127464367e-06, + "loss": 1.3398, + "step": 6191 + }, + { + "epoch": 0.65, + "learning_rate": 6.60101757293135e-06, + "loss": 1.4762, + "step": 6192 + }, + { + "epoch": 0.65, + "learning_rate": 6.5975754737746426e-06, + "loss": 1.2981, + "step": 6193 + }, + { + "epoch": 0.65, + "learning_rate": 6.594133830455401e-06, + "loss": 1.3728, + "step": 6194 + }, + { + "epoch": 0.65, + "learning_rate": 6.590692643434715e-06, + "loss": 1.3551, + "step": 6195 + }, + { + "epoch": 0.65, + "learning_rate": 6.5872519131736155e-06, + "loss": 1.3031, + "step": 6196 + }, + { + "epoch": 0.65, + "learning_rate": 6.583811640133071e-06, + "loss": 1.3231, + "step": 6197 + }, + { + "epoch": 0.65, + "learning_rate": 6.5803718247739924e-06, + "loss": 1.2752, + "step": 6198 + }, + { + "epoch": 0.65, + "learning_rate": 6.576932467557223e-06, + "loss": 1.3482, + "step": 6199 + }, + { + "epoch": 0.65, + "learning_rate": 6.573493568943552e-06, + "loss": 1.2612, + "step": 6200 + }, + { + "epoch": 0.65, + "learning_rate": 6.570055129393698e-06, + "loss": 1.6302, + "step": 6201 + }, + { + "epoch": 0.65, + "learning_rate": 6.566617149368331e-06, + "loss": 1.303, + "step": 6202 + }, + { + "epoch": 0.65, + "learning_rate": 6.563179629328047e-06, + "loss": 1.3405, + "step": 6203 + }, + { + "epoch": 0.65, + "learning_rate": 6.559742569733385e-06, + "loss": 1.2816, + "step": 6204 + }, + { + "epoch": 0.65, + "learning_rate": 6.556305971044824e-06, + "loss": 1.3834, + "step": 6205 + }, + { + "epoch": 0.65, + "learning_rate": 6.552869833722781e-06, + "loss": 1.3414, + "step": 6206 + }, + { + "epoch": 0.65, + "learning_rate": 6.5494341582276096e-06, + "loss": 1.3278, + "step": 6207 + }, + { + "epoch": 0.65, + "learning_rate": 6.5459989450196024e-06, + "loss": 1.3577, + "step": 6208 + }, + { + "epoch": 0.65, + "learning_rate": 6.542564194558986e-06, + "loss": 1.3104, + "step": 6209 + }, + { + "epoch": 0.65, + "learning_rate": 6.539129907305933e-06, + "loss": 1.3068, + "step": 6210 + }, + { + "epoch": 0.65, + "learning_rate": 6.53569608372055e-06, + "loss": 1.3769, + "step": 6211 + }, + { + "epoch": 0.65, + "learning_rate": 6.5322627242628775e-06, + "loss": 1.2855, + "step": 6212 + }, + { + "epoch": 0.65, + "learning_rate": 6.528829829392898e-06, + "loss": 1.4129, + "step": 6213 + }, + { + "epoch": 0.65, + "learning_rate": 6.525397399570534e-06, + "loss": 1.3631, + "step": 6214 + }, + { + "epoch": 0.65, + "learning_rate": 6.5219654352556435e-06, + "loss": 1.295, + "step": 6215 + }, + { + "epoch": 0.65, + "learning_rate": 6.518533936908016e-06, + "loss": 1.439, + "step": 6216 + }, + { + "epoch": 0.65, + "learning_rate": 6.515102904987389e-06, + "loss": 1.3148, + "step": 6217 + }, + { + "epoch": 0.65, + "learning_rate": 6.511672339953432e-06, + "loss": 1.3898, + "step": 6218 + }, + { + "epoch": 0.65, + "learning_rate": 6.508242242265752e-06, + "loss": 1.3222, + "step": 6219 + }, + { + "epoch": 0.65, + "learning_rate": 6.504812612383891e-06, + "loss": 1.324, + "step": 6220 + }, + { + "epoch": 0.65, + "learning_rate": 6.501383450767336e-06, + "loss": 1.951, + "step": 6221 + }, + { + "epoch": 0.65, + "learning_rate": 6.4979547578755055e-06, + "loss": 1.2878, + "step": 6222 + }, + { + "epoch": 0.65, + "learning_rate": 6.494526534167754e-06, + "loss": 1.3553, + "step": 6223 + }, + { + "epoch": 0.65, + "learning_rate": 6.491098780103375e-06, + "loss": 1.3898, + "step": 6224 + }, + { + "epoch": 0.65, + "learning_rate": 6.487671496141606e-06, + "loss": 1.4333, + "step": 6225 + }, + { + "epoch": 0.65, + "learning_rate": 6.484244682741606e-06, + "loss": 1.4461, + "step": 6226 + }, + { + "epoch": 0.65, + "learning_rate": 6.480818340362487e-06, + "loss": 1.3461, + "step": 6227 + }, + { + "epoch": 0.65, + "learning_rate": 6.4773924694632835e-06, + "loss": 1.3442, + "step": 6228 + }, + { + "epoch": 0.65, + "learning_rate": 6.473967070502982e-06, + "loss": 1.2692, + "step": 6229 + }, + { + "epoch": 0.65, + "learning_rate": 6.470542143940495e-06, + "loss": 1.446, + "step": 6230 + }, + { + "epoch": 0.65, + "learning_rate": 6.467117690234675e-06, + "loss": 1.3597, + "step": 6231 + }, + { + "epoch": 0.65, + "learning_rate": 6.463693709844305e-06, + "loss": 1.3226, + "step": 6232 + }, + { + "epoch": 0.65, + "learning_rate": 6.46027020322812e-06, + "loss": 1.2702, + "step": 6233 + }, + { + "epoch": 0.65, + "learning_rate": 6.456847170844775e-06, + "loss": 1.2554, + "step": 6234 + }, + { + "epoch": 0.65, + "learning_rate": 6.453424613152872e-06, + "loss": 1.2896, + "step": 6235 + }, + { + "epoch": 0.65, + "learning_rate": 6.450002530610943e-06, + "loss": 1.3148, + "step": 6236 + }, + { + "epoch": 0.65, + "learning_rate": 6.4465809236774635e-06, + "loss": 1.3589, + "step": 6237 + }, + { + "epoch": 0.65, + "learning_rate": 6.443159792810838e-06, + "loss": 1.2938, + "step": 6238 + }, + { + "epoch": 0.65, + "learning_rate": 6.439739138469406e-06, + "loss": 1.366, + "step": 6239 + }, + { + "epoch": 0.65, + "learning_rate": 6.436318961111455e-06, + "loss": 1.4772, + "step": 6240 + }, + { + "epoch": 0.65, + "learning_rate": 6.4328992611951975e-06, + "loss": 1.3131, + "step": 6241 + }, + { + "epoch": 0.65, + "learning_rate": 6.429480039178786e-06, + "loss": 1.2382, + "step": 6242 + }, + { + "epoch": 0.65, + "learning_rate": 6.426061295520304e-06, + "loss": 1.3394, + "step": 6243 + }, + { + "epoch": 0.65, + "learning_rate": 6.422643030677782e-06, + "loss": 1.321, + "step": 6244 + }, + { + "epoch": 0.65, + "learning_rate": 6.419225245109175e-06, + "loss": 1.3478, + "step": 6245 + }, + { + "epoch": 0.65, + "learning_rate": 6.415807939272383e-06, + "loss": 1.3249, + "step": 6246 + }, + { + "epoch": 0.66, + "learning_rate": 6.412391113625231e-06, + "loss": 1.3602, + "step": 6247 + }, + { + "epoch": 0.66, + "learning_rate": 6.408974768625491e-06, + "loss": 1.2799, + "step": 6248 + }, + { + "epoch": 0.66, + "learning_rate": 6.405558904730863e-06, + "loss": 1.3911, + "step": 6249 + }, + { + "epoch": 0.66, + "learning_rate": 6.402143522398987e-06, + "loss": 1.3185, + "step": 6250 + }, + { + "epoch": 0.66, + "learning_rate": 6.398728622087431e-06, + "loss": 1.3198, + "step": 6251 + }, + { + "epoch": 0.66, + "learning_rate": 6.395314204253711e-06, + "loss": 1.361, + "step": 6252 + }, + { + "epoch": 0.66, + "learning_rate": 6.391900269355269e-06, + "loss": 1.3285, + "step": 6253 + }, + { + "epoch": 0.66, + "learning_rate": 6.388486817849484e-06, + "loss": 1.3097, + "step": 6254 + }, + { + "epoch": 0.66, + "learning_rate": 6.385073850193667e-06, + "loss": 1.3057, + "step": 6255 + }, + { + "epoch": 0.66, + "learning_rate": 6.381661366845075e-06, + "loss": 1.4733, + "step": 6256 + }, + { + "epoch": 0.66, + "learning_rate": 6.378249368260889e-06, + "loss": 1.3571, + "step": 6257 + }, + { + "epoch": 0.66, + "learning_rate": 6.374837854898228e-06, + "loss": 1.3278, + "step": 6258 + }, + { + "epoch": 0.66, + "learning_rate": 6.37142682721415e-06, + "loss": 1.3035, + "step": 6259 + }, + { + "epoch": 0.66, + "learning_rate": 6.368016285665645e-06, + "loss": 1.397, + "step": 6260 + }, + { + "epoch": 0.66, + "learning_rate": 6.3646062307096365e-06, + "loss": 1.353, + "step": 6261 + }, + { + "epoch": 0.66, + "learning_rate": 6.361196662802982e-06, + "loss": 1.3534, + "step": 6262 + }, + { + "epoch": 0.66, + "learning_rate": 6.357787582402482e-06, + "loss": 1.3132, + "step": 6263 + }, + { + "epoch": 0.66, + "learning_rate": 6.3543789899648624e-06, + "loss": 1.3551, + "step": 6264 + }, + { + "epoch": 0.66, + "learning_rate": 6.3509708859467855e-06, + "loss": 1.4205, + "step": 6265 + }, + { + "epoch": 0.66, + "learning_rate": 6.347563270804851e-06, + "loss": 1.341, + "step": 6266 + }, + { + "epoch": 0.66, + "learning_rate": 6.344156144995593e-06, + "loss": 1.5188, + "step": 6267 + }, + { + "epoch": 0.66, + "learning_rate": 6.340749508975477e-06, + "loss": 1.4404, + "step": 6268 + }, + { + "epoch": 0.66, + "learning_rate": 6.337343363200905e-06, + "loss": 1.3026, + "step": 6269 + }, + { + "epoch": 0.66, + "learning_rate": 6.3339377081282124e-06, + "loss": 1.3315, + "step": 6270 + }, + { + "epoch": 0.66, + "learning_rate": 6.3305325442136735e-06, + "loss": 1.2503, + "step": 6271 + }, + { + "epoch": 0.66, + "learning_rate": 6.3271278719134885e-06, + "loss": 1.1776, + "step": 6272 + }, + { + "epoch": 0.66, + "learning_rate": 6.323723691683798e-06, + "loss": 1.3033, + "step": 6273 + }, + { + "epoch": 0.66, + "learning_rate": 6.320320003980671e-06, + "loss": 1.3838, + "step": 6274 + }, + { + "epoch": 0.66, + "learning_rate": 6.3169168092601195e-06, + "loss": 1.3691, + "step": 6275 + }, + { + "epoch": 0.66, + "learning_rate": 6.313514107978083e-06, + "loss": 1.3665, + "step": 6276 + }, + { + "epoch": 0.66, + "learning_rate": 6.310111900590432e-06, + "loss": 1.358, + "step": 6277 + }, + { + "epoch": 0.66, + "learning_rate": 6.306710187552978e-06, + "loss": 1.1708, + "step": 6278 + }, + { + "epoch": 0.66, + "learning_rate": 6.303308969321464e-06, + "loss": 1.331, + "step": 6279 + }, + { + "epoch": 0.66, + "learning_rate": 6.299908246351566e-06, + "loss": 1.3914, + "step": 6280 + }, + { + "epoch": 0.66, + "learning_rate": 6.2965080190988896e-06, + "loss": 1.3183, + "step": 6281 + }, + { + "epoch": 0.66, + "learning_rate": 6.293108288018981e-06, + "loss": 1.2969, + "step": 6282 + }, + { + "epoch": 0.66, + "learning_rate": 6.289709053567318e-06, + "loss": 1.2892, + "step": 6283 + }, + { + "epoch": 0.66, + "learning_rate": 6.2863103161993085e-06, + "loss": 1.3517, + "step": 6284 + }, + { + "epoch": 0.66, + "learning_rate": 6.282912076370295e-06, + "loss": 1.3329, + "step": 6285 + }, + { + "epoch": 0.66, + "learning_rate": 6.279514334535557e-06, + "loss": 1.3396, + "step": 6286 + }, + { + "epoch": 0.66, + "learning_rate": 6.276117091150304e-06, + "loss": 1.3878, + "step": 6287 + }, + { + "epoch": 0.66, + "learning_rate": 6.272720346669677e-06, + "loss": 1.2608, + "step": 6288 + }, + { + "epoch": 0.66, + "learning_rate": 6.269324101548754e-06, + "loss": 1.3605, + "step": 6289 + }, + { + "epoch": 0.66, + "learning_rate": 6.265928356242546e-06, + "loss": 1.2682, + "step": 6290 + }, + { + "epoch": 0.66, + "learning_rate": 6.262533111205995e-06, + "loss": 1.3426, + "step": 6291 + }, + { + "epoch": 0.66, + "learning_rate": 6.259138366893975e-06, + "loss": 1.2987, + "step": 6292 + }, + { + "epoch": 0.66, + "learning_rate": 6.255744123761295e-06, + "loss": 1.3521, + "step": 6293 + }, + { + "epoch": 0.66, + "learning_rate": 6.252350382262697e-06, + "loss": 1.2816, + "step": 6294 + }, + { + "epoch": 0.66, + "learning_rate": 6.248957142852856e-06, + "loss": 1.3884, + "step": 6295 + }, + { + "epoch": 0.66, + "learning_rate": 6.2455644059863795e-06, + "loss": 1.3545, + "step": 6296 + }, + { + "epoch": 0.66, + "learning_rate": 6.2421721721178015e-06, + "loss": 1.3636, + "step": 6297 + }, + { + "epoch": 0.66, + "learning_rate": 6.238780441701601e-06, + "loss": 1.3584, + "step": 6298 + }, + { + "epoch": 0.66, + "learning_rate": 6.235389215192179e-06, + "loss": 1.3459, + "step": 6299 + }, + { + "epoch": 0.66, + "learning_rate": 6.231998493043875e-06, + "loss": 1.4654, + "step": 6300 + }, + { + "epoch": 0.66, + "learning_rate": 6.228608275710954e-06, + "loss": 1.3628, + "step": 6301 + }, + { + "epoch": 0.66, + "learning_rate": 6.225218563647623e-06, + "loss": 1.3278, + "step": 6302 + }, + { + "epoch": 0.66, + "learning_rate": 6.221829357308016e-06, + "loss": 1.395, + "step": 6303 + }, + { + "epoch": 0.66, + "learning_rate": 6.218440657146196e-06, + "loss": 1.3481, + "step": 6304 + }, + { + "epoch": 0.66, + "learning_rate": 6.215052463616165e-06, + "loss": 1.309, + "step": 6305 + }, + { + "epoch": 0.66, + "learning_rate": 6.211664777171853e-06, + "loss": 1.275, + "step": 6306 + }, + { + "epoch": 0.66, + "learning_rate": 6.208277598267123e-06, + "loss": 1.4885, + "step": 6307 + }, + { + "epoch": 0.66, + "learning_rate": 6.2048909273557686e-06, + "loss": 1.3334, + "step": 6308 + }, + { + "epoch": 0.66, + "learning_rate": 6.201504764891518e-06, + "loss": 1.3399, + "step": 6309 + }, + { + "epoch": 0.66, + "learning_rate": 6.198119111328032e-06, + "loss": 1.3163, + "step": 6310 + }, + { + "epoch": 0.66, + "learning_rate": 6.1947339671188966e-06, + "loss": 1.2746, + "step": 6311 + }, + { + "epoch": 0.66, + "learning_rate": 6.191349332717635e-06, + "loss": 1.2984, + "step": 6312 + }, + { + "epoch": 0.66, + "learning_rate": 6.187965208577705e-06, + "loss": 1.2295, + "step": 6313 + }, + { + "epoch": 0.66, + "learning_rate": 6.18458159515249e-06, + "loss": 1.3424, + "step": 6314 + }, + { + "epoch": 0.66, + "learning_rate": 6.181198492895308e-06, + "loss": 1.3108, + "step": 6315 + }, + { + "epoch": 0.66, + "learning_rate": 6.1778159022594045e-06, + "loss": 1.4895, + "step": 6316 + }, + { + "epoch": 0.66, + "learning_rate": 6.174433823697964e-06, + "loss": 1.3247, + "step": 6317 + }, + { + "epoch": 0.66, + "learning_rate": 6.171052257664097e-06, + "loss": 1.3659, + "step": 6318 + }, + { + "epoch": 0.66, + "learning_rate": 6.167671204610844e-06, + "loss": 1.3889, + "step": 6319 + }, + { + "epoch": 0.66, + "learning_rate": 6.1642906649911815e-06, + "loss": 1.3946, + "step": 6320 + }, + { + "epoch": 0.66, + "learning_rate": 6.1609106392580155e-06, + "loss": 1.3685, + "step": 6321 + }, + { + "epoch": 0.66, + "learning_rate": 6.157531127864181e-06, + "loss": 1.2584, + "step": 6322 + }, + { + "epoch": 0.66, + "learning_rate": 6.154152131262448e-06, + "loss": 1.3263, + "step": 6323 + }, + { + "epoch": 0.66, + "learning_rate": 6.15077364990551e-06, + "loss": 1.3336, + "step": 6324 + }, + { + "epoch": 0.66, + "learning_rate": 6.147395684246003e-06, + "loss": 1.2513, + "step": 6325 + }, + { + "epoch": 0.66, + "learning_rate": 6.144018234736484e-06, + "loss": 1.3715, + "step": 6326 + }, + { + "epoch": 0.66, + "learning_rate": 6.140641301829444e-06, + "loss": 1.3464, + "step": 6327 + }, + { + "epoch": 0.66, + "learning_rate": 6.1372648859773075e-06, + "loss": 1.4374, + "step": 6328 + }, + { + "epoch": 0.66, + "learning_rate": 6.1338889876324285e-06, + "loss": 1.3903, + "step": 6329 + }, + { + "epoch": 0.66, + "learning_rate": 6.130513607247087e-06, + "loss": 1.3715, + "step": 6330 + }, + { + "epoch": 0.66, + "learning_rate": 6.127138745273497e-06, + "loss": 1.3196, + "step": 6331 + }, + { + "epoch": 0.66, + "learning_rate": 6.123764402163808e-06, + "loss": 1.3013, + "step": 6332 + }, + { + "epoch": 0.66, + "learning_rate": 6.120390578370093e-06, + "loss": 1.2751, + "step": 6333 + }, + { + "epoch": 0.66, + "learning_rate": 6.117017274344356e-06, + "loss": 1.2258, + "step": 6334 + }, + { + "epoch": 0.66, + "learning_rate": 6.113644490538533e-06, + "loss": 1.2982, + "step": 6335 + }, + { + "epoch": 0.66, + "learning_rate": 6.110272227404492e-06, + "loss": 1.3124, + "step": 6336 + }, + { + "epoch": 0.66, + "learning_rate": 6.10690048539403e-06, + "loss": 1.2451, + "step": 6337 + }, + { + "epoch": 0.66, + "learning_rate": 6.103529264958874e-06, + "loss": 1.3896, + "step": 6338 + }, + { + "epoch": 0.66, + "learning_rate": 6.100158566550677e-06, + "loss": 1.46, + "step": 6339 + }, + { + "epoch": 0.66, + "learning_rate": 6.096788390621031e-06, + "loss": 1.2965, + "step": 6340 + }, + { + "epoch": 0.66, + "learning_rate": 6.093418737621452e-06, + "loss": 1.2969, + "step": 6341 + }, + { + "epoch": 0.67, + "learning_rate": 6.0900496080033836e-06, + "loss": 1.3988, + "step": 6342 + }, + { + "epoch": 0.67, + "learning_rate": 6.086681002218204e-06, + "loss": 1.351, + "step": 6343 + }, + { + "epoch": 0.67, + "learning_rate": 6.083312920717224e-06, + "loss": 1.3447, + "step": 6344 + }, + { + "epoch": 0.67, + "learning_rate": 6.079945363951674e-06, + "loss": 1.3361, + "step": 6345 + }, + { + "epoch": 0.67, + "learning_rate": 6.076578332372724e-06, + "loss": 1.3688, + "step": 6346 + }, + { + "epoch": 0.67, + "learning_rate": 6.073211826431467e-06, + "loss": 1.2831, + "step": 6347 + }, + { + "epoch": 0.67, + "learning_rate": 6.069845846578931e-06, + "loss": 1.369, + "step": 6348 + }, + { + "epoch": 0.67, + "learning_rate": 6.06648039326607e-06, + "loss": 1.3247, + "step": 6349 + }, + { + "epoch": 0.67, + "learning_rate": 6.063115466943765e-06, + "loss": 1.288, + "step": 6350 + }, + { + "epoch": 0.67, + "learning_rate": 6.0597510680628345e-06, + "loss": 1.0733, + "step": 6351 + }, + { + "epoch": 0.67, + "learning_rate": 6.056387197074021e-06, + "loss": 1.3386, + "step": 6352 + }, + { + "epoch": 0.67, + "learning_rate": 6.053023854427993e-06, + "loss": 1.3682, + "step": 6353 + }, + { + "epoch": 0.67, + "learning_rate": 6.049661040575353e-06, + "loss": 1.5669, + "step": 6354 + }, + { + "epoch": 0.67, + "learning_rate": 6.0462987559666355e-06, + "loss": 1.3432, + "step": 6355 + }, + { + "epoch": 0.67, + "learning_rate": 6.042937001052298e-06, + "loss": 1.327, + "step": 6356 + }, + { + "epoch": 0.67, + "learning_rate": 6.039575776282728e-06, + "loss": 1.3101, + "step": 6357 + }, + { + "epoch": 0.67, + "learning_rate": 6.0362150821082425e-06, + "loss": 1.3239, + "step": 6358 + }, + { + "epoch": 0.67, + "learning_rate": 6.032854918979092e-06, + "loss": 1.435, + "step": 6359 + }, + { + "epoch": 0.67, + "learning_rate": 6.029495287345448e-06, + "loss": 1.3503, + "step": 6360 + }, + { + "epoch": 0.67, + "learning_rate": 6.0261361876574186e-06, + "loss": 1.3356, + "step": 6361 + }, + { + "epoch": 0.67, + "learning_rate": 6.022777620365032e-06, + "loss": 1.3301, + "step": 6362 + }, + { + "epoch": 0.67, + "learning_rate": 6.019419585918255e-06, + "loss": 1.3925, + "step": 6363 + }, + { + "epoch": 0.67, + "learning_rate": 6.016062084766978e-06, + "loss": 1.3794, + "step": 6364 + }, + { + "epoch": 0.67, + "learning_rate": 6.0127051173610155e-06, + "loss": 1.5496, + "step": 6365 + }, + { + "epoch": 0.67, + "learning_rate": 6.009348684150116e-06, + "loss": 1.3227, + "step": 6366 + }, + { + "epoch": 0.67, + "learning_rate": 6.005992785583958e-06, + "loss": 1.3474, + "step": 6367 + }, + { + "epoch": 0.67, + "learning_rate": 6.002637422112143e-06, + "loss": 1.3262, + "step": 6368 + }, + { + "epoch": 0.67, + "eval_loss": 1.4049769639968872, + "eval_runtime": 77.5156, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 6368 + }, + { + "epoch": 0.67, + "learning_rate": 5.999282594184206e-06, + "loss": 1.3083, + "step": 6369 + }, + { + "epoch": 0.67, + "learning_rate": 5.995928302249603e-06, + "loss": 1.323, + "step": 6370 + }, + { + "epoch": 0.67, + "learning_rate": 5.99257454675773e-06, + "loss": 1.3101, + "step": 6371 + }, + { + "epoch": 0.67, + "learning_rate": 5.989221328157899e-06, + "loss": 1.4546, + "step": 6372 + }, + { + "epoch": 0.67, + "learning_rate": 5.985868646899355e-06, + "loss": 1.3315, + "step": 6373 + }, + { + "epoch": 0.67, + "learning_rate": 5.982516503431273e-06, + "loss": 1.3768, + "step": 6374 + }, + { + "epoch": 0.67, + "learning_rate": 5.979164898202755e-06, + "loss": 1.332, + "step": 6375 + }, + { + "epoch": 0.67, + "learning_rate": 5.975813831662829e-06, + "loss": 1.3154, + "step": 6376 + }, + { + "epoch": 0.67, + "learning_rate": 5.972463304260448e-06, + "loss": 1.3636, + "step": 6377 + }, + { + "epoch": 0.67, + "learning_rate": 5.969113316444504e-06, + "loss": 1.3553, + "step": 6378 + }, + { + "epoch": 0.67, + "learning_rate": 5.965763868663803e-06, + "loss": 1.3805, + "step": 6379 + }, + { + "epoch": 0.67, + "learning_rate": 5.962414961367089e-06, + "loss": 1.3096, + "step": 6380 + }, + { + "epoch": 0.67, + "learning_rate": 5.959066595003025e-06, + "loss": 1.326, + "step": 6381 + }, + { + "epoch": 0.67, + "learning_rate": 5.955718770020212e-06, + "loss": 1.3021, + "step": 6382 + }, + { + "epoch": 0.67, + "learning_rate": 5.952371486867168e-06, + "loss": 1.35, + "step": 6383 + }, + { + "epoch": 0.67, + "learning_rate": 5.949024745992344e-06, + "loss": 1.6749, + "step": 6384 + }, + { + "epoch": 0.67, + "learning_rate": 5.945678547844117e-06, + "loss": 1.4931, + "step": 6385 + }, + { + "epoch": 0.67, + "learning_rate": 5.942332892870793e-06, + "loss": 1.284, + "step": 6386 + }, + { + "epoch": 0.67, + "learning_rate": 5.938987781520604e-06, + "loss": 1.3296, + "step": 6387 + }, + { + "epoch": 0.67, + "learning_rate": 5.9356432142417074e-06, + "loss": 1.4837, + "step": 6388 + }, + { + "epoch": 0.67, + "learning_rate": 5.932299191482188e-06, + "loss": 1.3114, + "step": 6389 + }, + { + "epoch": 0.67, + "learning_rate": 5.928955713690063e-06, + "loss": 1.3328, + "step": 6390 + }, + { + "epoch": 0.67, + "learning_rate": 5.92561278131327e-06, + "loss": 1.3163, + "step": 6391 + }, + { + "epoch": 0.67, + "learning_rate": 5.922270394799676e-06, + "loss": 1.3068, + "step": 6392 + }, + { + "epoch": 0.67, + "learning_rate": 5.918928554597073e-06, + "loss": 1.292, + "step": 6393 + }, + { + "epoch": 0.67, + "learning_rate": 5.915587261153186e-06, + "loss": 1.3359, + "step": 6394 + }, + { + "epoch": 0.67, + "learning_rate": 5.912246514915662e-06, + "loss": 1.4109, + "step": 6395 + }, + { + "epoch": 0.67, + "learning_rate": 5.908906316332071e-06, + "loss": 1.3083, + "step": 6396 + }, + { + "epoch": 0.67, + "learning_rate": 5.905566665849917e-06, + "loss": 1.2973, + "step": 6397 + }, + { + "epoch": 0.67, + "learning_rate": 5.902227563916627e-06, + "loss": 1.4159, + "step": 6398 + }, + { + "epoch": 0.67, + "learning_rate": 5.898889010979556e-06, + "loss": 1.287, + "step": 6399 + }, + { + "epoch": 0.67, + "learning_rate": 5.89555100748598e-06, + "loss": 1.2865, + "step": 6400 + }, + { + "epoch": 0.67, + "learning_rate": 5.89221355388311e-06, + "loss": 1.3137, + "step": 6401 + }, + { + "epoch": 0.67, + "learning_rate": 5.8888766506180785e-06, + "loss": 1.2751, + "step": 6402 + }, + { + "epoch": 0.67, + "learning_rate": 5.885540298137944e-06, + "loss": 1.3687, + "step": 6403 + }, + { + "epoch": 0.67, + "learning_rate": 5.882204496889688e-06, + "loss": 1.2941, + "step": 6404 + }, + { + "epoch": 0.67, + "learning_rate": 5.878869247320231e-06, + "loss": 1.2926, + "step": 6405 + }, + { + "epoch": 0.67, + "learning_rate": 5.875534549876404e-06, + "loss": 1.2675, + "step": 6406 + }, + { + "epoch": 0.67, + "learning_rate": 5.872200405004973e-06, + "loss": 1.2806, + "step": 6407 + }, + { + "epoch": 0.67, + "learning_rate": 5.868866813152625e-06, + "loss": 1.3438, + "step": 6408 + }, + { + "epoch": 0.67, + "learning_rate": 5.865533774765981e-06, + "loss": 1.2947, + "step": 6409 + }, + { + "epoch": 0.67, + "learning_rate": 5.862201290291578e-06, + "loss": 1.3643, + "step": 6410 + }, + { + "epoch": 0.67, + "learning_rate": 5.858869360175887e-06, + "loss": 1.2579, + "step": 6411 + }, + { + "epoch": 0.67, + "learning_rate": 5.855537984865296e-06, + "loss": 1.3479, + "step": 6412 + }, + { + "epoch": 0.67, + "learning_rate": 5.852207164806127e-06, + "loss": 1.3239, + "step": 6413 + }, + { + "epoch": 0.67, + "learning_rate": 5.848876900444626e-06, + "loss": 1.2644, + "step": 6414 + }, + { + "epoch": 0.67, + "learning_rate": 5.845547192226959e-06, + "loss": 1.3279, + "step": 6415 + }, + { + "epoch": 0.67, + "learning_rate": 5.8422180405992216e-06, + "loss": 1.5202, + "step": 6416 + }, + { + "epoch": 0.67, + "learning_rate": 5.838889446007439e-06, + "loss": 1.5714, + "step": 6417 + }, + { + "epoch": 0.67, + "learning_rate": 5.835561408897552e-06, + "loss": 1.2592, + "step": 6418 + }, + { + "epoch": 0.67, + "learning_rate": 5.832233929715434e-06, + "loss": 1.3407, + "step": 6419 + }, + { + "epoch": 0.67, + "learning_rate": 5.828907008906882e-06, + "loss": 1.3555, + "step": 6420 + }, + { + "epoch": 0.67, + "learning_rate": 5.825580646917622e-06, + "loss": 1.2602, + "step": 6421 + }, + { + "epoch": 0.67, + "learning_rate": 5.822254844193293e-06, + "loss": 1.2672, + "step": 6422 + }, + { + "epoch": 0.67, + "learning_rate": 5.818929601179472e-06, + "loss": 1.3361, + "step": 6423 + }, + { + "epoch": 0.67, + "learning_rate": 5.8156049183216575e-06, + "loss": 1.49, + "step": 6424 + }, + { + "epoch": 0.67, + "learning_rate": 5.812280796065269e-06, + "loss": 1.306, + "step": 6425 + }, + { + "epoch": 0.67, + "learning_rate": 5.808957234855654e-06, + "loss": 1.3167, + "step": 6426 + }, + { + "epoch": 0.67, + "learning_rate": 5.805634235138082e-06, + "loss": 1.3103, + "step": 6427 + }, + { + "epoch": 0.67, + "learning_rate": 5.802311797357752e-06, + "loss": 1.2992, + "step": 6428 + }, + { + "epoch": 0.67, + "learning_rate": 5.7989899219597875e-06, + "loss": 1.3269, + "step": 6429 + }, + { + "epoch": 0.67, + "learning_rate": 5.795668609389233e-06, + "loss": 1.3393, + "step": 6430 + }, + { + "epoch": 0.67, + "learning_rate": 5.79234786009105e-06, + "loss": 1.2633, + "step": 6431 + }, + { + "epoch": 0.67, + "learning_rate": 5.7890276745101495e-06, + "loss": 1.2758, + "step": 6432 + }, + { + "epoch": 0.67, + "learning_rate": 5.785708053091339e-06, + "loss": 1.3294, + "step": 6433 + }, + { + "epoch": 0.67, + "learning_rate": 5.782388996279371e-06, + "loss": 1.3657, + "step": 6434 + }, + { + "epoch": 0.67, + "learning_rate": 5.779070504518905e-06, + "loss": 1.3353, + "step": 6435 + }, + { + "epoch": 0.67, + "learning_rate": 5.775752578254539e-06, + "loss": 1.2741, + "step": 6436 + }, + { + "epoch": 0.68, + "learning_rate": 5.772435217930792e-06, + "loss": 1.2979, + "step": 6437 + }, + { + "epoch": 0.68, + "learning_rate": 5.7691184239921026e-06, + "loss": 1.366, + "step": 6438 + }, + { + "epoch": 0.68, + "learning_rate": 5.765802196882828e-06, + "loss": 1.2873, + "step": 6439 + }, + { + "epoch": 0.68, + "learning_rate": 5.762486537047271e-06, + "loss": 1.2865, + "step": 6440 + }, + { + "epoch": 0.68, + "learning_rate": 5.7591714449296365e-06, + "loss": 1.3887, + "step": 6441 + }, + { + "epoch": 0.68, + "learning_rate": 5.755856920974063e-06, + "loss": 1.127, + "step": 6442 + }, + { + "epoch": 0.68, + "learning_rate": 5.752542965624617e-06, + "loss": 1.4331, + "step": 6443 + }, + { + "epoch": 0.68, + "learning_rate": 5.749229579325274e-06, + "loss": 1.3199, + "step": 6444 + }, + { + "epoch": 0.68, + "learning_rate": 5.745916762519952e-06, + "loss": 1.2719, + "step": 6445 + }, + { + "epoch": 0.68, + "learning_rate": 5.742604515652475e-06, + "loss": 1.2991, + "step": 6446 + }, + { + "epoch": 0.68, + "learning_rate": 5.7392928391666014e-06, + "loss": 1.2164, + "step": 6447 + }, + { + "epoch": 0.68, + "learning_rate": 5.735981733506016e-06, + "loss": 1.3636, + "step": 6448 + }, + { + "epoch": 0.68, + "learning_rate": 5.732671199114314e-06, + "loss": 1.3486, + "step": 6449 + }, + { + "epoch": 0.68, + "learning_rate": 5.729361236435027e-06, + "loss": 1.3378, + "step": 6450 + }, + { + "epoch": 0.68, + "learning_rate": 5.726051845911606e-06, + "loss": 1.3521, + "step": 6451 + }, + { + "epoch": 0.68, + "learning_rate": 5.722743027987421e-06, + "loss": 1.4295, + "step": 6452 + }, + { + "epoch": 0.68, + "learning_rate": 5.719434783105772e-06, + "loss": 1.2625, + "step": 6453 + }, + { + "epoch": 0.68, + "learning_rate": 5.716127111709873e-06, + "loss": 1.2944, + "step": 6454 + }, + { + "epoch": 0.68, + "learning_rate": 5.7128200142428695e-06, + "loss": 1.3655, + "step": 6455 + }, + { + "epoch": 0.68, + "learning_rate": 5.7095134911478336e-06, + "loss": 1.3115, + "step": 6456 + }, + { + "epoch": 0.68, + "learning_rate": 5.706207542867747e-06, + "loss": 1.3391, + "step": 6457 + }, + { + "epoch": 0.68, + "learning_rate": 5.702902169845519e-06, + "loss": 1.3911, + "step": 6458 + }, + { + "epoch": 0.68, + "learning_rate": 5.699597372523997e-06, + "loss": 1.2936, + "step": 6459 + }, + { + "epoch": 0.68, + "learning_rate": 5.696293151345928e-06, + "loss": 1.379, + "step": 6460 + }, + { + "epoch": 0.68, + "learning_rate": 5.692989506754e-06, + "loss": 1.4083, + "step": 6461 + }, + { + "epoch": 0.68, + "learning_rate": 5.689686439190809e-06, + "loss": 1.2645, + "step": 6462 + }, + { + "epoch": 0.68, + "learning_rate": 5.686383949098886e-06, + "loss": 1.3207, + "step": 6463 + }, + { + "epoch": 0.68, + "learning_rate": 5.683082036920682e-06, + "loss": 1.4293, + "step": 6464 + }, + { + "epoch": 0.68, + "learning_rate": 5.679780703098563e-06, + "loss": 1.3018, + "step": 6465 + }, + { + "epoch": 0.68, + "learning_rate": 5.676479948074825e-06, + "loss": 1.3568, + "step": 6466 + }, + { + "epoch": 0.68, + "learning_rate": 5.673179772291687e-06, + "loss": 1.3252, + "step": 6467 + }, + { + "epoch": 0.68, + "learning_rate": 5.669880176191283e-06, + "loss": 1.2674, + "step": 6468 + }, + { + "epoch": 0.68, + "learning_rate": 5.666581160215676e-06, + "loss": 1.3774, + "step": 6469 + }, + { + "epoch": 0.68, + "learning_rate": 5.663282724806855e-06, + "loss": 1.3013, + "step": 6470 + }, + { + "epoch": 0.68, + "learning_rate": 5.659984870406715e-06, + "loss": 1.3354, + "step": 6471 + }, + { + "epoch": 0.68, + "learning_rate": 5.656687597457093e-06, + "loss": 1.273, + "step": 6472 + }, + { + "epoch": 0.68, + "learning_rate": 5.653390906399732e-06, + "loss": 1.3041, + "step": 6473 + }, + { + "epoch": 0.68, + "learning_rate": 5.650094797676308e-06, + "loss": 1.3521, + "step": 6474 + }, + { + "epoch": 0.68, + "learning_rate": 5.646799271728417e-06, + "loss": 1.3751, + "step": 6475 + }, + { + "epoch": 0.68, + "learning_rate": 5.643504328997571e-06, + "loss": 1.2882, + "step": 6476 + }, + { + "epoch": 0.68, + "learning_rate": 5.640209969925202e-06, + "loss": 1.2625, + "step": 6477 + }, + { + "epoch": 0.68, + "learning_rate": 5.636916194952683e-06, + "loss": 1.3648, + "step": 6478 + }, + { + "epoch": 0.68, + "learning_rate": 5.633623004521285e-06, + "loss": 1.3115, + "step": 6479 + }, + { + "epoch": 0.68, + "learning_rate": 5.6303303990722154e-06, + "loss": 1.2755, + "step": 6480 + }, + { + "epoch": 0.68, + "learning_rate": 5.627038379046595e-06, + "loss": 1.4546, + "step": 6481 + }, + { + "epoch": 0.68, + "learning_rate": 5.623746944885473e-06, + "loss": 1.3717, + "step": 6482 + }, + { + "epoch": 0.68, + "learning_rate": 5.620456097029818e-06, + "loss": 1.3188, + "step": 6483 + }, + { + "epoch": 0.68, + "learning_rate": 5.61716583592052e-06, + "loss": 1.3166, + "step": 6484 + }, + { + "epoch": 0.68, + "learning_rate": 5.613876161998377e-06, + "loss": 1.3413, + "step": 6485 + }, + { + "epoch": 0.68, + "learning_rate": 5.610587075704139e-06, + "loss": 1.395, + "step": 6486 + }, + { + "epoch": 0.68, + "learning_rate": 5.6072985774784465e-06, + "loss": 1.2914, + "step": 6487 + }, + { + "epoch": 0.68, + "learning_rate": 5.604010667761876e-06, + "loss": 1.3118, + "step": 6488 + }, + { + "epoch": 0.68, + "learning_rate": 5.600723346994932e-06, + "loss": 1.3599, + "step": 6489 + }, + { + "epoch": 0.68, + "learning_rate": 5.597436615618017e-06, + "loss": 1.2862, + "step": 6490 + }, + { + "epoch": 0.68, + "learning_rate": 5.594150474071481e-06, + "loss": 1.3585, + "step": 6491 + }, + { + "epoch": 0.68, + "learning_rate": 5.590864922795573e-06, + "loss": 1.3449, + "step": 6492 + }, + { + "epoch": 0.68, + "learning_rate": 5.587579962230475e-06, + "loss": 1.2787, + "step": 6493 + }, + { + "epoch": 0.68, + "learning_rate": 5.5842955928162934e-06, + "loss": 1.3755, + "step": 6494 + }, + { + "epoch": 0.68, + "learning_rate": 5.5810118149930406e-06, + "loss": 1.2858, + "step": 6495 + }, + { + "epoch": 0.68, + "learning_rate": 5.577728629200662e-06, + "loss": 1.4214, + "step": 6496 + }, + { + "epoch": 0.68, + "learning_rate": 5.574446035879024e-06, + "loss": 1.5007, + "step": 6497 + }, + { + "epoch": 0.68, + "learning_rate": 5.571164035467903e-06, + "loss": 1.2952, + "step": 6498 + }, + { + "epoch": 0.68, + "learning_rate": 5.56788262840701e-06, + "loss": 1.267, + "step": 6499 + }, + { + "epoch": 0.68, + "learning_rate": 5.564601815135962e-06, + "loss": 1.3168, + "step": 6500 + }, + { + "epoch": 0.68, + "learning_rate": 5.561321596094305e-06, + "loss": 1.2992, + "step": 6501 + }, + { + "epoch": 0.68, + "learning_rate": 5.558041971721511e-06, + "loss": 1.4237, + "step": 6502 + }, + { + "epoch": 0.68, + "learning_rate": 5.554762942456959e-06, + "loss": 1.3865, + "step": 6503 + }, + { + "epoch": 0.68, + "learning_rate": 5.5514845087399505e-06, + "loss": 1.2875, + "step": 6504 + }, + { + "epoch": 0.68, + "learning_rate": 5.548206671009724e-06, + "loss": 1.3011, + "step": 6505 + }, + { + "epoch": 0.68, + "learning_rate": 5.544929429705415e-06, + "loss": 1.3425, + "step": 6506 + }, + { + "epoch": 0.68, + "learning_rate": 5.541652785266095e-06, + "loss": 1.4265, + "step": 6507 + }, + { + "epoch": 0.68, + "learning_rate": 5.538376738130747e-06, + "loss": 1.2877, + "step": 6508 + }, + { + "epoch": 0.68, + "learning_rate": 5.535101288738276e-06, + "loss": 1.3652, + "step": 6509 + }, + { + "epoch": 0.68, + "learning_rate": 5.5318264375275145e-06, + "loss": 1.2997, + "step": 6510 + }, + { + "epoch": 0.68, + "learning_rate": 5.528552184937201e-06, + "loss": 1.3223, + "step": 6511 + }, + { + "epoch": 0.68, + "learning_rate": 5.525278531406006e-06, + "loss": 1.2897, + "step": 6512 + }, + { + "epoch": 0.68, + "learning_rate": 5.522005477372516e-06, + "loss": 1.3554, + "step": 6513 + }, + { + "epoch": 0.68, + "learning_rate": 5.51873302327523e-06, + "loss": 1.3233, + "step": 6514 + }, + { + "epoch": 0.68, + "learning_rate": 5.515461169552576e-06, + "loss": 1.3536, + "step": 6515 + }, + { + "epoch": 0.68, + "learning_rate": 5.5121899166429046e-06, + "loss": 1.3485, + "step": 6516 + }, + { + "epoch": 0.68, + "learning_rate": 5.508919264984468e-06, + "loss": 1.3264, + "step": 6517 + }, + { + "epoch": 0.68, + "learning_rate": 5.505649215015461e-06, + "loss": 1.4498, + "step": 6518 + }, + { + "epoch": 0.68, + "learning_rate": 5.5023797671739755e-06, + "loss": 1.4468, + "step": 6519 + }, + { + "epoch": 0.68, + "learning_rate": 5.499110921898038e-06, + "loss": 1.2659, + "step": 6520 + }, + { + "epoch": 0.68, + "learning_rate": 5.4958426796255934e-06, + "loss": 1.318, + "step": 6521 + }, + { + "epoch": 0.68, + "learning_rate": 5.492575040794498e-06, + "loss": 1.3167, + "step": 6522 + }, + { + "epoch": 0.68, + "learning_rate": 5.48930800584253e-06, + "loss": 1.3453, + "step": 6523 + }, + { + "epoch": 0.68, + "learning_rate": 5.486041575207397e-06, + "loss": 1.2557, + "step": 6524 + }, + { + "epoch": 0.68, + "learning_rate": 5.482775749326705e-06, + "loss": 1.3235, + "step": 6525 + }, + { + "epoch": 0.68, + "learning_rate": 5.479510528638001e-06, + "loss": 1.3119, + "step": 6526 + }, + { + "epoch": 0.68, + "learning_rate": 5.476245913578733e-06, + "loss": 1.4639, + "step": 6527 + }, + { + "epoch": 0.68, + "learning_rate": 5.472981904586277e-06, + "loss": 1.3233, + "step": 6528 + }, + { + "epoch": 0.68, + "learning_rate": 5.469718502097931e-06, + "loss": 1.2722, + "step": 6529 + }, + { + "epoch": 0.68, + "learning_rate": 5.466455706550906e-06, + "loss": 1.4428, + "step": 6530 + }, + { + "epoch": 0.68, + "learning_rate": 5.463193518382321e-06, + "loss": 1.5695, + "step": 6531 + }, + { + "epoch": 0.68, + "learning_rate": 5.4599319380292434e-06, + "loss": 1.3161, + "step": 6532 + }, + { + "epoch": 0.69, + "learning_rate": 5.4566709659286296e-06, + "loss": 1.3513, + "step": 6533 + }, + { + "epoch": 0.69, + "learning_rate": 5.453410602517368e-06, + "loss": 1.2716, + "step": 6534 + }, + { + "epoch": 0.69, + "learning_rate": 5.45015084823227e-06, + "loss": 1.4467, + "step": 6535 + }, + { + "epoch": 0.69, + "learning_rate": 5.44689170351005e-06, + "loss": 1.4082, + "step": 6536 + }, + { + "epoch": 0.69, + "learning_rate": 5.443633168787357e-06, + "loss": 1.303, + "step": 6537 + }, + { + "epoch": 0.69, + "learning_rate": 5.440375244500743e-06, + "loss": 1.2765, + "step": 6538 + }, + { + "epoch": 0.69, + "learning_rate": 5.43711793108669e-06, + "loss": 1.6814, + "step": 6539 + }, + { + "epoch": 0.69, + "learning_rate": 5.4338612289816e-06, + "loss": 1.3899, + "step": 6540 + }, + { + "epoch": 0.69, + "learning_rate": 5.430605138621778e-06, + "loss": 1.201, + "step": 6541 + }, + { + "epoch": 0.69, + "learning_rate": 5.42734966044346e-06, + "loss": 1.3214, + "step": 6542 + }, + { + "epoch": 0.69, + "learning_rate": 5.424094794882801e-06, + "loss": 1.2676, + "step": 6543 + }, + { + "epoch": 0.69, + "learning_rate": 5.420840542375862e-06, + "loss": 1.3006, + "step": 6544 + }, + { + "epoch": 0.69, + "learning_rate": 5.4175869033586355e-06, + "loss": 1.32, + "step": 6545 + }, + { + "epoch": 0.69, + "learning_rate": 5.41433387826702e-06, + "loss": 1.3347, + "step": 6546 + }, + { + "epoch": 0.69, + "learning_rate": 5.41108146753684e-06, + "loss": 1.3983, + "step": 6547 + }, + { + "epoch": 0.69, + "learning_rate": 5.407829671603838e-06, + "loss": 1.3756, + "step": 6548 + }, + { + "epoch": 0.69, + "learning_rate": 5.404578490903664e-06, + "loss": 1.3444, + "step": 6549 + }, + { + "epoch": 0.69, + "learning_rate": 5.4013279258718974e-06, + "loss": 1.3369, + "step": 6550 + }, + { + "epoch": 0.69, + "learning_rate": 5.398077976944034e-06, + "loss": 1.2995, + "step": 6551 + }, + { + "epoch": 0.69, + "learning_rate": 5.394828644555475e-06, + "loss": 1.3305, + "step": 6552 + }, + { + "epoch": 0.69, + "learning_rate": 5.391579929141554e-06, + "loss": 1.3743, + "step": 6553 + }, + { + "epoch": 0.69, + "learning_rate": 5.3883318311375095e-06, + "loss": 1.2829, + "step": 6554 + }, + { + "epoch": 0.69, + "learning_rate": 5.3850843509785065e-06, + "loss": 1.379, + "step": 6555 + }, + { + "epoch": 0.69, + "learning_rate": 5.3818374890996295e-06, + "loss": 1.3236, + "step": 6556 + }, + { + "epoch": 0.69, + "learning_rate": 5.378591245935865e-06, + "loss": 1.3469, + "step": 6557 + }, + { + "epoch": 0.69, + "learning_rate": 5.375345621922129e-06, + "loss": 1.3318, + "step": 6558 + }, + { + "epoch": 0.69, + "learning_rate": 5.3721006174932576e-06, + "loss": 1.3395, + "step": 6559 + }, + { + "epoch": 0.69, + "learning_rate": 5.36885623308399e-06, + "loss": 1.4148, + "step": 6560 + }, + { + "epoch": 0.69, + "learning_rate": 5.365612469128993e-06, + "loss": 1.3007, + "step": 6561 + }, + { + "epoch": 0.69, + "learning_rate": 5.362369326062853e-06, + "loss": 1.4365, + "step": 6562 + }, + { + "epoch": 0.69, + "learning_rate": 5.3591268043200585e-06, + "loss": 1.4269, + "step": 6563 + }, + { + "epoch": 0.69, + "learning_rate": 5.355884904335034e-06, + "loss": 1.2619, + "step": 6564 + }, + { + "epoch": 0.69, + "learning_rate": 5.3526436265421e-06, + "loss": 1.2678, + "step": 6565 + }, + { + "epoch": 0.69, + "learning_rate": 5.34940297137551e-06, + "loss": 1.2541, + "step": 6566 + }, + { + "epoch": 0.69, + "learning_rate": 5.3461629392694345e-06, + "loss": 1.3237, + "step": 6567 + }, + { + "epoch": 0.69, + "eval_loss": 1.402653694152832, + "eval_runtime": 77.5033, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 6567 + }, + { + "epoch": 0.69, + "learning_rate": 5.342923530657944e-06, + "loss": 1.357, + "step": 6568 + }, + { + "epoch": 0.69, + "learning_rate": 5.33968474597504e-06, + "loss": 1.3561, + "step": 6569 + }, + { + "epoch": 0.69, + "learning_rate": 5.336446585654642e-06, + "loss": 1.2969, + "step": 6570 + }, + { + "epoch": 0.69, + "learning_rate": 5.33320905013057e-06, + "loss": 1.2922, + "step": 6571 + }, + { + "epoch": 0.69, + "learning_rate": 5.329972139836581e-06, + "loss": 1.3581, + "step": 6572 + }, + { + "epoch": 0.69, + "learning_rate": 5.326735855206328e-06, + "loss": 1.2926, + "step": 6573 + }, + { + "epoch": 0.69, + "learning_rate": 5.3235001966733965e-06, + "loss": 1.3933, + "step": 6574 + }, + { + "epoch": 0.69, + "learning_rate": 5.320265164671283e-06, + "loss": 1.4009, + "step": 6575 + }, + { + "epoch": 0.69, + "learning_rate": 5.3170307596333955e-06, + "loss": 1.4051, + "step": 6576 + }, + { + "epoch": 0.69, + "learning_rate": 5.313796981993054e-06, + "loss": 1.3448, + "step": 6577 + }, + { + "epoch": 0.69, + "learning_rate": 5.310563832183515e-06, + "loss": 1.3141, + "step": 6578 + }, + { + "epoch": 0.69, + "learning_rate": 5.307331310637929e-06, + "loss": 1.3658, + "step": 6579 + }, + { + "epoch": 0.69, + "learning_rate": 5.3040994177893725e-06, + "loss": 1.2881, + "step": 6580 + }, + { + "epoch": 0.69, + "learning_rate": 5.30086815407084e-06, + "loss": 1.3051, + "step": 6581 + }, + { + "epoch": 0.69, + "learning_rate": 5.297637519915231e-06, + "loss": 1.3353, + "step": 6582 + }, + { + "epoch": 0.69, + "learning_rate": 5.2944075157553754e-06, + "loss": 1.3997, + "step": 6583 + }, + { + "epoch": 0.69, + "learning_rate": 5.291178142024002e-06, + "loss": 1.3094, + "step": 6584 + }, + { + "epoch": 0.69, + "learning_rate": 5.287949399153769e-06, + "loss": 1.3384, + "step": 6585 + }, + { + "epoch": 0.69, + "learning_rate": 5.284721287577248e-06, + "loss": 1.3183, + "step": 6586 + }, + { + "epoch": 0.69, + "learning_rate": 5.281493807726916e-06, + "loss": 1.4433, + "step": 6587 + }, + { + "epoch": 0.69, + "learning_rate": 5.278266960035174e-06, + "loss": 1.3103, + "step": 6588 + }, + { + "epoch": 0.69, + "learning_rate": 5.275040744934343e-06, + "loss": 1.3478, + "step": 6589 + }, + { + "epoch": 0.69, + "learning_rate": 5.271815162856645e-06, + "loss": 1.2713, + "step": 6590 + }, + { + "epoch": 0.69, + "learning_rate": 5.268590214234233e-06, + "loss": 1.3697, + "step": 6591 + }, + { + "epoch": 0.69, + "learning_rate": 5.265365899499156e-06, + "loss": 1.6169, + "step": 6592 + }, + { + "epoch": 0.69, + "learning_rate": 5.262142219083398e-06, + "loss": 1.2988, + "step": 6593 + }, + { + "epoch": 0.69, + "learning_rate": 5.258919173418851e-06, + "loss": 1.515, + "step": 6594 + }, + { + "epoch": 0.69, + "learning_rate": 5.2556967629373125e-06, + "loss": 1.3704, + "step": 6595 + }, + { + "epoch": 0.69, + "learning_rate": 5.2524749880705075e-06, + "loss": 1.2404, + "step": 6596 + }, + { + "epoch": 0.69, + "learning_rate": 5.249253849250073e-06, + "loss": 1.2799, + "step": 6597 + }, + { + "epoch": 0.69, + "learning_rate": 5.246033346907553e-06, + "loss": 1.2876, + "step": 6598 + }, + { + "epoch": 0.69, + "learning_rate": 5.24281348147442e-06, + "loss": 1.3058, + "step": 6599 + }, + { + "epoch": 0.69, + "learning_rate": 5.239594253382043e-06, + "loss": 1.3347, + "step": 6600 + }, + { + "epoch": 0.69, + "learning_rate": 5.236375663061722e-06, + "loss": 1.3323, + "step": 6601 + }, + { + "epoch": 0.69, + "learning_rate": 5.23315771094467e-06, + "loss": 1.3254, + "step": 6602 + }, + { + "epoch": 0.69, + "learning_rate": 5.229940397461999e-06, + "loss": 1.3462, + "step": 6603 + }, + { + "epoch": 0.69, + "learning_rate": 5.226723723044753e-06, + "loss": 1.2901, + "step": 6604 + }, + { + "epoch": 0.69, + "learning_rate": 5.223507688123887e-06, + "loss": 1.3079, + "step": 6605 + }, + { + "epoch": 0.69, + "learning_rate": 5.220292293130258e-06, + "loss": 1.4282, + "step": 6606 + }, + { + "epoch": 0.69, + "learning_rate": 5.217077538494651e-06, + "loss": 1.3197, + "step": 6607 + }, + { + "epoch": 0.69, + "learning_rate": 5.213863424647765e-06, + "loss": 1.3581, + "step": 6608 + }, + { + "epoch": 0.69, + "learning_rate": 5.2106499520202005e-06, + "loss": 1.3322, + "step": 6609 + }, + { + "epoch": 0.69, + "learning_rate": 5.207437121042488e-06, + "loss": 1.3368, + "step": 6610 + }, + { + "epoch": 0.69, + "learning_rate": 5.204224932145056e-06, + "loss": 1.2771, + "step": 6611 + }, + { + "epoch": 0.69, + "learning_rate": 5.20101338575826e-06, + "loss": 1.2852, + "step": 6612 + }, + { + "epoch": 0.69, + "learning_rate": 5.197802482312369e-06, + "loss": 1.3733, + "step": 6613 + }, + { + "epoch": 0.69, + "learning_rate": 5.194592222237551e-06, + "loss": 1.3719, + "step": 6614 + }, + { + "epoch": 0.69, + "learning_rate": 5.191382605963906e-06, + "loss": 1.3658, + "step": 6615 + }, + { + "epoch": 0.69, + "learning_rate": 5.1881736339214415e-06, + "loss": 1.3261, + "step": 6616 + }, + { + "epoch": 0.69, + "learning_rate": 5.18496530654007e-06, + "loss": 1.3057, + "step": 6617 + }, + { + "epoch": 0.69, + "learning_rate": 5.181757624249635e-06, + "loss": 1.2665, + "step": 6618 + }, + { + "epoch": 0.69, + "learning_rate": 5.1785505874798716e-06, + "loss": 1.2839, + "step": 6619 + }, + { + "epoch": 0.69, + "learning_rate": 5.175344196660447e-06, + "loss": 1.3131, + "step": 6620 + }, + { + "epoch": 0.69, + "learning_rate": 5.1721384522209385e-06, + "loss": 1.3217, + "step": 6621 + }, + { + "epoch": 0.69, + "learning_rate": 5.168933354590825e-06, + "loss": 1.3306, + "step": 6622 + }, + { + "epoch": 0.69, + "learning_rate": 5.165728904199512e-06, + "loss": 1.3197, + "step": 6623 + }, + { + "epoch": 0.69, + "learning_rate": 5.1625251014763176e-06, + "loss": 1.3035, + "step": 6624 + }, + { + "epoch": 0.69, + "learning_rate": 5.1593219468504605e-06, + "loss": 1.2927, + "step": 6625 + }, + { + "epoch": 0.69, + "learning_rate": 5.156119440751086e-06, + "loss": 1.3333, + "step": 6626 + }, + { + "epoch": 0.69, + "learning_rate": 5.152917583607251e-06, + "loss": 1.3181, + "step": 6627 + }, + { + "epoch": 0.7, + "learning_rate": 5.149716375847913e-06, + "loss": 1.347, + "step": 6628 + }, + { + "epoch": 0.7, + "learning_rate": 5.14651581790196e-06, + "loss": 1.347, + "step": 6629 + }, + { + "epoch": 0.7, + "learning_rate": 5.143315910198179e-06, + "loss": 1.2892, + "step": 6630 + }, + { + "epoch": 0.7, + "learning_rate": 5.140116653165277e-06, + "loss": 1.2996, + "step": 6631 + }, + { + "epoch": 0.7, + "learning_rate": 5.136918047231876e-06, + "loss": 1.2802, + "step": 6632 + }, + { + "epoch": 0.7, + "learning_rate": 5.133720092826501e-06, + "loss": 1.2766, + "step": 6633 + }, + { + "epoch": 0.7, + "learning_rate": 5.130522790377598e-06, + "loss": 1.5365, + "step": 6634 + }, + { + "epoch": 0.7, + "learning_rate": 5.127326140313528e-06, + "loss": 1.4848, + "step": 6635 + }, + { + "epoch": 0.7, + "learning_rate": 5.124130143062551e-06, + "loss": 1.3712, + "step": 6636 + }, + { + "epoch": 0.7, + "learning_rate": 5.120934799052859e-06, + "loss": 1.3094, + "step": 6637 + }, + { + "epoch": 0.7, + "learning_rate": 5.1177401087125355e-06, + "loss": 1.272, + "step": 6638 + }, + { + "epoch": 0.7, + "learning_rate": 5.114546072469593e-06, + "loss": 1.2856, + "step": 6639 + }, + { + "epoch": 0.7, + "learning_rate": 5.111352690751952e-06, + "loss": 1.2886, + "step": 6640 + }, + { + "epoch": 0.7, + "learning_rate": 5.108159963987436e-06, + "loss": 1.277, + "step": 6641 + }, + { + "epoch": 0.7, + "learning_rate": 5.104967892603794e-06, + "loss": 1.3392, + "step": 6642 + }, + { + "epoch": 0.7, + "learning_rate": 5.101776477028684e-06, + "loss": 1.3036, + "step": 6643 + }, + { + "epoch": 0.7, + "learning_rate": 5.098585717689667e-06, + "loss": 1.4116, + "step": 6644 + }, + { + "epoch": 0.7, + "learning_rate": 5.095395615014226e-06, + "loss": 1.3437, + "step": 6645 + }, + { + "epoch": 0.7, + "learning_rate": 5.0922061694297565e-06, + "loss": 1.2608, + "step": 6646 + }, + { + "epoch": 0.7, + "learning_rate": 5.089017381363554e-06, + "loss": 1.2959, + "step": 6647 + }, + { + "epoch": 0.7, + "learning_rate": 5.085829251242844e-06, + "loss": 1.3508, + "step": 6648 + }, + { + "epoch": 0.7, + "learning_rate": 5.0826417794947455e-06, + "loss": 1.34, + "step": 6649 + }, + { + "epoch": 0.7, + "learning_rate": 5.0794549665463e-06, + "loss": 1.3092, + "step": 6650 + }, + { + "epoch": 0.7, + "learning_rate": 5.076268812824463e-06, + "loss": 1.3417, + "step": 6651 + }, + { + "epoch": 0.7, + "learning_rate": 5.073083318756092e-06, + "loss": 1.3424, + "step": 6652 + }, + { + "epoch": 0.7, + "learning_rate": 5.069898484767961e-06, + "loss": 1.3296, + "step": 6653 + }, + { + "epoch": 0.7, + "learning_rate": 5.066714311286762e-06, + "loss": 1.2852, + "step": 6654 + }, + { + "epoch": 0.7, + "learning_rate": 5.063530798739087e-06, + "loss": 1.3462, + "step": 6655 + }, + { + "epoch": 0.7, + "learning_rate": 5.06034794755145e-06, + "loss": 1.3615, + "step": 6656 + }, + { + "epoch": 0.7, + "learning_rate": 5.057165758150262e-06, + "loss": 1.245, + "step": 6657 + }, + { + "epoch": 0.7, + "learning_rate": 5.053984230961862e-06, + "loss": 1.201, + "step": 6658 + }, + { + "epoch": 0.7, + "learning_rate": 5.050803366412494e-06, + "loss": 1.331, + "step": 6659 + }, + { + "epoch": 0.7, + "learning_rate": 5.047623164928306e-06, + "loss": 1.3034, + "step": 6660 + }, + { + "epoch": 0.7, + "learning_rate": 5.044443626935367e-06, + "loss": 1.2822, + "step": 6661 + }, + { + "epoch": 0.7, + "learning_rate": 5.041264752859657e-06, + "loss": 1.2576, + "step": 6662 + }, + { + "epoch": 0.7, + "learning_rate": 5.038086543127055e-06, + "loss": 1.3198, + "step": 6663 + }, + { + "epoch": 0.7, + "learning_rate": 5.034908998163368e-06, + "loss": 1.2892, + "step": 6664 + }, + { + "epoch": 0.7, + "learning_rate": 5.031732118394299e-06, + "loss": 1.3004, + "step": 6665 + }, + { + "epoch": 0.7, + "learning_rate": 5.028555904245469e-06, + "loss": 1.3178, + "step": 6666 + }, + { + "epoch": 0.7, + "learning_rate": 5.0253803561424156e-06, + "loss": 1.3014, + "step": 6667 + }, + { + "epoch": 0.7, + "learning_rate": 5.022205474510571e-06, + "loss": 1.3151, + "step": 6668 + }, + { + "epoch": 0.7, + "learning_rate": 5.019031259775292e-06, + "loss": 1.3551, + "step": 6669 + }, + { + "epoch": 0.7, + "learning_rate": 5.015857712361847e-06, + "loss": 1.4188, + "step": 6670 + }, + { + "epoch": 0.7, + "learning_rate": 5.0126848326954025e-06, + "loss": 1.2743, + "step": 6671 + }, + { + "epoch": 0.7, + "learning_rate": 5.009512621201043e-06, + "loss": 1.3528, + "step": 6672 + }, + { + "epoch": 0.7, + "learning_rate": 5.006341078303771e-06, + "loss": 1.309, + "step": 6673 + }, + { + "epoch": 0.7, + "learning_rate": 5.003170204428483e-06, + "loss": 1.3353, + "step": 6674 + }, + { + "epoch": 0.7, + "learning_rate": 5.000000000000003e-06, + "loss": 1.2753, + "step": 6675 + }, + { + "epoch": 0.7, + "learning_rate": 4.9968304654430465e-06, + "loss": 1.3907, + "step": 6676 + }, + { + "epoch": 0.7, + "learning_rate": 4.993661601182256e-06, + "loss": 1.2876, + "step": 6677 + }, + { + "epoch": 0.7, + "learning_rate": 4.990493407642181e-06, + "loss": 1.2534, + "step": 6678 + }, + { + "epoch": 0.7, + "learning_rate": 4.98732588524727e-06, + "loss": 1.3352, + "step": 6679 + }, + { + "epoch": 0.7, + "learning_rate": 4.984159034421895e-06, + "loss": 1.3302, + "step": 6680 + }, + { + "epoch": 0.7, + "learning_rate": 4.980992855590336e-06, + "loss": 1.3783, + "step": 6681 + }, + { + "epoch": 0.7, + "learning_rate": 4.977827349176769e-06, + "loss": 1.2848, + "step": 6682 + }, + { + "epoch": 0.7, + "learning_rate": 4.974662515605302e-06, + "loss": 1.3269, + "step": 6683 + }, + { + "epoch": 0.7, + "learning_rate": 4.971498355299932e-06, + "loss": 1.3662, + "step": 6684 + }, + { + "epoch": 0.7, + "learning_rate": 4.968334868684579e-06, + "loss": 1.2508, + "step": 6685 + }, + { + "epoch": 0.7, + "learning_rate": 4.965172056183073e-06, + "loss": 1.3872, + "step": 6686 + }, + { + "epoch": 0.7, + "learning_rate": 4.962009918219142e-06, + "loss": 1.3008, + "step": 6687 + }, + { + "epoch": 0.7, + "learning_rate": 4.958848455216434e-06, + "loss": 1.2058, + "step": 6688 + }, + { + "epoch": 0.7, + "learning_rate": 4.95568766759851e-06, + "loss": 1.3127, + "step": 6689 + }, + { + "epoch": 0.7, + "learning_rate": 4.952527555788825e-06, + "loss": 1.2985, + "step": 6690 + }, + { + "epoch": 0.7, + "learning_rate": 4.949368120210757e-06, + "loss": 1.333, + "step": 6691 + }, + { + "epoch": 0.7, + "learning_rate": 4.946209361287593e-06, + "loss": 1.2945, + "step": 6692 + }, + { + "epoch": 0.7, + "learning_rate": 4.943051279442516e-06, + "loss": 1.262, + "step": 6693 + }, + { + "epoch": 0.7, + "learning_rate": 4.93989387509864e-06, + "loss": 1.6155, + "step": 6694 + }, + { + "epoch": 0.7, + "learning_rate": 4.936737148678965e-06, + "loss": 1.2838, + "step": 6695 + }, + { + "epoch": 0.7, + "learning_rate": 4.933581100606415e-06, + "loss": 1.3778, + "step": 6696 + }, + { + "epoch": 0.7, + "learning_rate": 4.930425731303824e-06, + "loss": 1.3624, + "step": 6697 + }, + { + "epoch": 0.7, + "learning_rate": 4.927271041193923e-06, + "loss": 1.2641, + "step": 6698 + }, + { + "epoch": 0.7, + "learning_rate": 4.924117030699362e-06, + "loss": 1.3314, + "step": 6699 + }, + { + "epoch": 0.7, + "learning_rate": 4.920963700242704e-06, + "loss": 1.328, + "step": 6700 + }, + { + "epoch": 0.7, + "learning_rate": 4.917811050246404e-06, + "loss": 1.3128, + "step": 6701 + }, + { + "epoch": 0.7, + "learning_rate": 4.914659081132843e-06, + "loss": 1.3877, + "step": 6702 + }, + { + "epoch": 0.7, + "learning_rate": 4.911507793324299e-06, + "loss": 1.3114, + "step": 6703 + }, + { + "epoch": 0.7, + "learning_rate": 4.908357187242967e-06, + "loss": 1.3592, + "step": 6704 + }, + { + "epoch": 0.7, + "learning_rate": 4.905207263310948e-06, + "loss": 1.329, + "step": 6705 + }, + { + "epoch": 0.7, + "learning_rate": 4.902058021950247e-06, + "loss": 1.2558, + "step": 6706 + }, + { + "epoch": 0.7, + "learning_rate": 4.898909463582784e-06, + "loss": 1.2489, + "step": 6707 + }, + { + "epoch": 0.7, + "learning_rate": 4.895761588630388e-06, + "loss": 1.2817, + "step": 6708 + }, + { + "epoch": 0.7, + "learning_rate": 4.892614397514785e-06, + "loss": 1.1606, + "step": 6709 + }, + { + "epoch": 0.7, + "learning_rate": 4.889467890657628e-06, + "loss": 1.2878, + "step": 6710 + }, + { + "epoch": 0.7, + "learning_rate": 4.886322068480458e-06, + "loss": 1.2747, + "step": 6711 + }, + { + "epoch": 0.7, + "learning_rate": 4.88317693140474e-06, + "loss": 1.3662, + "step": 6712 + }, + { + "epoch": 0.7, + "learning_rate": 4.880032479851844e-06, + "loss": 1.3009, + "step": 6713 + }, + { + "epoch": 0.7, + "learning_rate": 4.8768887142430385e-06, + "loss": 1.3157, + "step": 6714 + }, + { + "epoch": 0.7, + "learning_rate": 4.873745634999511e-06, + "loss": 1.4461, + "step": 6715 + }, + { + "epoch": 0.7, + "learning_rate": 4.870603242542358e-06, + "loss": 1.3818, + "step": 6716 + }, + { + "epoch": 0.7, + "learning_rate": 4.86746153729257e-06, + "loss": 1.3361, + "step": 6717 + }, + { + "epoch": 0.7, + "learning_rate": 4.864320519671061e-06, + "loss": 1.3147, + "step": 6718 + }, + { + "epoch": 0.7, + "learning_rate": 4.8611801900986485e-06, + "loss": 1.3773, + "step": 6719 + }, + { + "epoch": 0.7, + "learning_rate": 4.858040548996049e-06, + "loss": 1.3091, + "step": 6720 + }, + { + "epoch": 0.7, + "learning_rate": 4.854901596783902e-06, + "loss": 1.3314, + "step": 6721 + }, + { + "epoch": 0.7, + "learning_rate": 4.851763333882738e-06, + "loss": 1.3082, + "step": 6722 + }, + { + "epoch": 0.71, + "learning_rate": 4.848625760713007e-06, + "loss": 1.2687, + "step": 6723 + }, + { + "epoch": 0.71, + "learning_rate": 4.845488877695068e-06, + "loss": 1.3378, + "step": 6724 + }, + { + "epoch": 0.71, + "learning_rate": 4.842352685249174e-06, + "loss": 1.3516, + "step": 6725 + }, + { + "epoch": 0.71, + "learning_rate": 4.839217183795501e-06, + "loss": 1.4083, + "step": 6726 + }, + { + "epoch": 0.71, + "learning_rate": 4.836082373754124e-06, + "loss": 1.3073, + "step": 6727 + }, + { + "epoch": 0.71, + "learning_rate": 4.832948255545024e-06, + "loss": 1.2948, + "step": 6728 + }, + { + "epoch": 0.71, + "learning_rate": 4.829814829588099e-06, + "loss": 1.3323, + "step": 6729 + }, + { + "epoch": 0.71, + "learning_rate": 4.826682096303139e-06, + "loss": 1.3101, + "step": 6730 + }, + { + "epoch": 0.71, + "learning_rate": 4.823550056109853e-06, + "loss": 1.3323, + "step": 6731 + }, + { + "epoch": 0.71, + "learning_rate": 4.8204187094278605e-06, + "loss": 1.3862, + "step": 6732 + }, + { + "epoch": 0.71, + "learning_rate": 4.817288056676671e-06, + "loss": 1.3112, + "step": 6733 + }, + { + "epoch": 0.71, + "learning_rate": 4.8141580982757175e-06, + "loss": 1.297, + "step": 6734 + }, + { + "epoch": 0.71, + "learning_rate": 4.811028834644336e-06, + "loss": 1.2604, + "step": 6735 + }, + { + "epoch": 0.71, + "learning_rate": 4.807900266201761e-06, + "loss": 1.343, + "step": 6736 + }, + { + "epoch": 0.71, + "learning_rate": 4.804772393367142e-06, + "loss": 1.3254, + "step": 6737 + }, + { + "epoch": 0.71, + "learning_rate": 4.80164521655954e-06, + "loss": 1.2688, + "step": 6738 + }, + { + "epoch": 0.71, + "learning_rate": 4.798518736197909e-06, + "loss": 1.2693, + "step": 6739 + }, + { + "epoch": 0.71, + "learning_rate": 4.795392952701122e-06, + "loss": 1.4536, + "step": 6740 + }, + { + "epoch": 0.71, + "learning_rate": 4.7922678664879485e-06, + "loss": 1.3811, + "step": 6741 + }, + { + "epoch": 0.71, + "learning_rate": 4.789143477977072e-06, + "loss": 1.2584, + "step": 6742 + }, + { + "epoch": 0.71, + "learning_rate": 4.786019787587084e-06, + "loss": 1.2584, + "step": 6743 + }, + { + "epoch": 0.71, + "learning_rate": 4.782896795736472e-06, + "loss": 1.2005, + "step": 6744 + }, + { + "epoch": 0.71, + "learning_rate": 4.779774502843642e-06, + "loss": 1.335, + "step": 6745 + }, + { + "epoch": 0.71, + "learning_rate": 4.776652909326901e-06, + "loss": 1.3675, + "step": 6746 + }, + { + "epoch": 0.71, + "learning_rate": 4.773532015604457e-06, + "loss": 1.3794, + "step": 6747 + }, + { + "epoch": 0.71, + "learning_rate": 4.770411822094437e-06, + "loss": 1.3629, + "step": 6748 + }, + { + "epoch": 0.71, + "learning_rate": 4.76729232921486e-06, + "loss": 1.0805, + "step": 6749 + }, + { + "epoch": 0.71, + "learning_rate": 4.76417353738366e-06, + "loss": 1.2874, + "step": 6750 + }, + { + "epoch": 0.71, + "learning_rate": 4.761055447018681e-06, + "loss": 1.428, + "step": 6751 + }, + { + "epoch": 0.71, + "learning_rate": 4.757938058537656e-06, + "loss": 1.2935, + "step": 6752 + }, + { + "epoch": 0.71, + "learning_rate": 4.754821372358242e-06, + "loss": 1.4202, + "step": 6753 + }, + { + "epoch": 0.71, + "learning_rate": 4.751705388897997e-06, + "loss": 1.3109, + "step": 6754 + }, + { + "epoch": 0.71, + "learning_rate": 4.7485901085743754e-06, + "loss": 1.3319, + "step": 6755 + }, + { + "epoch": 0.71, + "learning_rate": 4.745475531804753e-06, + "loss": 1.3246, + "step": 6756 + }, + { + "epoch": 0.71, + "learning_rate": 4.742361659006395e-06, + "loss": 1.3407, + "step": 6757 + }, + { + "epoch": 0.71, + "learning_rate": 4.739248490596483e-06, + "loss": 1.2953, + "step": 6758 + }, + { + "epoch": 0.71, + "learning_rate": 4.736136026992107e-06, + "loss": 1.3214, + "step": 6759 + }, + { + "epoch": 0.71, + "learning_rate": 4.733024268610249e-06, + "loss": 1.4112, + "step": 6760 + }, + { + "epoch": 0.71, + "learning_rate": 4.7299132158678085e-06, + "loss": 1.2981, + "step": 6761 + }, + { + "epoch": 0.71, + "learning_rate": 4.726802869181591e-06, + "loss": 1.2975, + "step": 6762 + }, + { + "epoch": 0.71, + "learning_rate": 4.723693228968293e-06, + "loss": 1.3047, + "step": 6763 + }, + { + "epoch": 0.71, + "learning_rate": 4.720584295644533e-06, + "loss": 1.3906, + "step": 6764 + }, + { + "epoch": 0.71, + "learning_rate": 4.717476069626832e-06, + "loss": 1.2523, + "step": 6765 + }, + { + "epoch": 0.71, + "learning_rate": 4.7143685513316025e-06, + "loss": 1.0453, + "step": 6766 + }, + { + "epoch": 0.71, + "eval_loss": 1.4004828929901123, + "eval_runtime": 77.565, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 6766 + }, + { + "epoch": 0.71, + "learning_rate": 4.711261741175182e-06, + "loss": 1.1339, + "step": 6767 + }, + { + "epoch": 0.71, + "learning_rate": 4.7081556395737935e-06, + "loss": 1.2401, + "step": 6768 + }, + { + "epoch": 0.71, + "learning_rate": 4.705050246943581e-06, + "loss": 1.3009, + "step": 6769 + }, + { + "epoch": 0.71, + "learning_rate": 4.7019455637005895e-06, + "loss": 1.3106, + "step": 6770 + }, + { + "epoch": 0.71, + "learning_rate": 4.698841590260758e-06, + "loss": 1.3021, + "step": 6771 + }, + { + "epoch": 0.71, + "learning_rate": 4.695738327039947e-06, + "loss": 1.3147, + "step": 6772 + }, + { + "epoch": 0.71, + "learning_rate": 4.692635774453914e-06, + "loss": 1.238, + "step": 6773 + }, + { + "epoch": 0.71, + "learning_rate": 4.6895339329183154e-06, + "loss": 1.3876, + "step": 6774 + }, + { + "epoch": 0.71, + "learning_rate": 4.686432802848726e-06, + "loss": 1.3012, + "step": 6775 + }, + { + "epoch": 0.71, + "learning_rate": 4.68333238466061e-06, + "loss": 1.1421, + "step": 6776 + }, + { + "epoch": 0.71, + "learning_rate": 4.6802326787693455e-06, + "loss": 1.2838, + "step": 6777 + }, + { + "epoch": 0.71, + "learning_rate": 4.677133685590219e-06, + "loss": 1.3725, + "step": 6778 + }, + { + "epoch": 0.71, + "learning_rate": 4.674035405538409e-06, + "loss": 1.3093, + "step": 6779 + }, + { + "epoch": 0.71, + "learning_rate": 4.6709378390290085e-06, + "loss": 1.2785, + "step": 6780 + }, + { + "epoch": 0.71, + "learning_rate": 4.667840986477015e-06, + "loss": 1.2513, + "step": 6781 + }, + { + "epoch": 0.71, + "learning_rate": 4.66474484829732e-06, + "loss": 1.2903, + "step": 6782 + }, + { + "epoch": 0.71, + "learning_rate": 4.661649424904732e-06, + "loss": 1.4217, + "step": 6783 + }, + { + "epoch": 0.71, + "learning_rate": 4.658554716713959e-06, + "loss": 1.337, + "step": 6784 + }, + { + "epoch": 0.71, + "learning_rate": 4.655460724139605e-06, + "loss": 1.2978, + "step": 6785 + }, + { + "epoch": 0.71, + "learning_rate": 4.652367447596197e-06, + "loss": 1.3036, + "step": 6786 + }, + { + "epoch": 0.71, + "learning_rate": 4.6492748874981415e-06, + "loss": 1.2889, + "step": 6787 + }, + { + "epoch": 0.71, + "learning_rate": 4.646183044259771e-06, + "loss": 1.3046, + "step": 6788 + }, + { + "epoch": 0.71, + "learning_rate": 4.643091918295312e-06, + "loss": 1.3483, + "step": 6789 + }, + { + "epoch": 0.71, + "learning_rate": 4.640001510018893e-06, + "loss": 1.3862, + "step": 6790 + }, + { + "epoch": 0.71, + "learning_rate": 4.6369118198445505e-06, + "loss": 1.2483, + "step": 6791 + }, + { + "epoch": 0.71, + "learning_rate": 4.633822848186228e-06, + "loss": 1.2669, + "step": 6792 + }, + { + "epoch": 0.71, + "learning_rate": 4.63073459545776e-06, + "loss": 1.3535, + "step": 6793 + }, + { + "epoch": 0.71, + "learning_rate": 4.627647062072902e-06, + "loss": 1.2742, + "step": 6794 + }, + { + "epoch": 0.71, + "learning_rate": 4.624560248445295e-06, + "loss": 1.3429, + "step": 6795 + }, + { + "epoch": 0.71, + "learning_rate": 4.621474154988498e-06, + "loss": 1.3548, + "step": 6796 + }, + { + "epoch": 0.71, + "learning_rate": 4.61838878211597e-06, + "loss": 1.2722, + "step": 6797 + }, + { + "epoch": 0.71, + "learning_rate": 4.6153041302410665e-06, + "loss": 1.3357, + "step": 6798 + }, + { + "epoch": 0.71, + "learning_rate": 4.612220199777053e-06, + "loss": 1.2494, + "step": 6799 + }, + { + "epoch": 0.71, + "learning_rate": 4.609136991137103e-06, + "loss": 1.2792, + "step": 6800 + }, + { + "epoch": 0.71, + "learning_rate": 4.60605450473428e-06, + "loss": 1.2892, + "step": 6801 + }, + { + "epoch": 0.71, + "learning_rate": 4.602972740981562e-06, + "loss": 1.316, + "step": 6802 + }, + { + "epoch": 0.71, + "learning_rate": 4.599891700291822e-06, + "loss": 1.3017, + "step": 6803 + }, + { + "epoch": 0.71, + "learning_rate": 4.5968113830778416e-06, + "loss": 1.3133, + "step": 6804 + }, + { + "epoch": 0.71, + "learning_rate": 4.593731789752311e-06, + "loss": 1.3768, + "step": 6805 + }, + { + "epoch": 0.71, + "learning_rate": 4.590652920727806e-06, + "loss": 1.3259, + "step": 6806 + }, + { + "epoch": 0.71, + "learning_rate": 4.5875747764168214e-06, + "loss": 1.328, + "step": 6807 + }, + { + "epoch": 0.71, + "learning_rate": 4.584497357231752e-06, + "loss": 1.2924, + "step": 6808 + }, + { + "epoch": 0.71, + "learning_rate": 4.581420663584886e-06, + "loss": 1.3347, + "step": 6809 + }, + { + "epoch": 0.71, + "learning_rate": 4.578344695888427e-06, + "loss": 1.3042, + "step": 6810 + }, + { + "epoch": 0.71, + "learning_rate": 4.575269454554477e-06, + "loss": 1.3121, + "step": 6811 + }, + { + "epoch": 0.71, + "learning_rate": 4.572194939995031e-06, + "loss": 1.3471, + "step": 6812 + }, + { + "epoch": 0.71, + "learning_rate": 4.569121152622005e-06, + "loss": 1.4279, + "step": 6813 + }, + { + "epoch": 0.71, + "learning_rate": 4.5660480928471985e-06, + "loss": 1.2902, + "step": 6814 + }, + { + "epoch": 0.71, + "learning_rate": 4.562975761082326e-06, + "loss": 1.0803, + "step": 6815 + }, + { + "epoch": 0.71, + "learning_rate": 4.5599041577390065e-06, + "loss": 1.008, + "step": 6816 + }, + { + "epoch": 0.71, + "learning_rate": 4.556833283228748e-06, + "loss": 1.168, + "step": 6817 + }, + { + "epoch": 0.71, + "learning_rate": 4.553763137962971e-06, + "loss": 1.3092, + "step": 6818 + }, + { + "epoch": 0.72, + "learning_rate": 4.550693722353001e-06, + "loss": 1.364, + "step": 6819 + }, + { + "epoch": 0.72, + "learning_rate": 4.547625036810052e-06, + "loss": 1.3079, + "step": 6820 + }, + { + "epoch": 0.72, + "learning_rate": 4.544557081745259e-06, + "loss": 1.2639, + "step": 6821 + }, + { + "epoch": 0.72, + "learning_rate": 4.541489857569639e-06, + "loss": 1.3586, + "step": 6822 + }, + { + "epoch": 0.72, + "learning_rate": 4.5384233646941275e-06, + "loss": 1.4261, + "step": 6823 + }, + { + "epoch": 0.72, + "learning_rate": 4.535357603529558e-06, + "loss": 1.428, + "step": 6824 + }, + { + "epoch": 0.72, + "learning_rate": 4.532292574486656e-06, + "loss": 1.2541, + "step": 6825 + }, + { + "epoch": 0.72, + "learning_rate": 4.529228277976061e-06, + "loss": 1.2761, + "step": 6826 + }, + { + "epoch": 0.72, + "learning_rate": 4.526164714408314e-06, + "loss": 1.3439, + "step": 6827 + }, + { + "epoch": 0.72, + "learning_rate": 4.523101884193845e-06, + "loss": 1.3585, + "step": 6828 + }, + { + "epoch": 0.72, + "learning_rate": 4.520039787742999e-06, + "loss": 1.4035, + "step": 6829 + }, + { + "epoch": 0.72, + "learning_rate": 4.516978425466023e-06, + "loss": 1.3328, + "step": 6830 + }, + { + "epoch": 0.72, + "learning_rate": 4.5139177977730516e-06, + "loss": 1.2931, + "step": 6831 + }, + { + "epoch": 0.72, + "learning_rate": 4.5108579050741395e-06, + "loss": 1.2515, + "step": 6832 + }, + { + "epoch": 0.72, + "learning_rate": 4.507798747779226e-06, + "loss": 1.3178, + "step": 6833 + }, + { + "epoch": 0.72, + "learning_rate": 4.504740326298163e-06, + "loss": 1.3037, + "step": 6834 + }, + { + "epoch": 0.72, + "learning_rate": 4.501682641040702e-06, + "loss": 1.14, + "step": 6835 + }, + { + "epoch": 0.72, + "learning_rate": 4.4986256924164895e-06, + "loss": 1.2801, + "step": 6836 + }, + { + "epoch": 0.72, + "learning_rate": 4.495569480835081e-06, + "loss": 1.3195, + "step": 6837 + }, + { + "epoch": 0.72, + "learning_rate": 4.492514006705935e-06, + "loss": 1.2949, + "step": 6838 + }, + { + "epoch": 0.72, + "learning_rate": 4.489459270438397e-06, + "loss": 1.3297, + "step": 6839 + }, + { + "epoch": 0.72, + "learning_rate": 4.4864052724417315e-06, + "loss": 1.2127, + "step": 6840 + }, + { + "epoch": 0.72, + "learning_rate": 4.4833520131250894e-06, + "loss": 1.3124, + "step": 6841 + }, + { + "epoch": 0.72, + "learning_rate": 4.480299492897532e-06, + "loss": 1.3056, + "step": 6842 + }, + { + "epoch": 0.72, + "learning_rate": 4.477247712168021e-06, + "loss": 1.2853, + "step": 6843 + }, + { + "epoch": 0.72, + "learning_rate": 4.474196671345411e-06, + "loss": 1.2531, + "step": 6844 + }, + { + "epoch": 0.72, + "learning_rate": 4.471146370838466e-06, + "loss": 1.2712, + "step": 6845 + }, + { + "epoch": 0.72, + "learning_rate": 4.468096811055852e-06, + "loss": 1.3443, + "step": 6846 + }, + { + "epoch": 0.72, + "learning_rate": 4.465047992406124e-06, + "loss": 1.2692, + "step": 6847 + }, + { + "epoch": 0.72, + "learning_rate": 4.461999915297752e-06, + "loss": 1.3937, + "step": 6848 + }, + { + "epoch": 0.72, + "learning_rate": 4.458952580139094e-06, + "loss": 1.2743, + "step": 6849 + }, + { + "epoch": 0.72, + "learning_rate": 4.455905987338418e-06, + "loss": 1.3949, + "step": 6850 + }, + { + "epoch": 0.72, + "learning_rate": 4.452860137303892e-06, + "loss": 1.2578, + "step": 6851 + }, + { + "epoch": 0.72, + "learning_rate": 4.449815030443575e-06, + "loss": 1.3199, + "step": 6852 + }, + { + "epoch": 0.72, + "learning_rate": 4.4467706671654365e-06, + "loss": 1.3199, + "step": 6853 + }, + { + "epoch": 0.72, + "learning_rate": 4.4437270478773464e-06, + "loss": 1.3098, + "step": 6854 + }, + { + "epoch": 0.72, + "learning_rate": 4.440684172987064e-06, + "loss": 1.2888, + "step": 6855 + }, + { + "epoch": 0.72, + "learning_rate": 4.4376420429022615e-06, + "loss": 1.646, + "step": 6856 + }, + { + "epoch": 0.72, + "learning_rate": 4.434600658030508e-06, + "loss": 1.3573, + "step": 6857 + }, + { + "epoch": 0.72, + "learning_rate": 4.431560018779264e-06, + "loss": 1.3748, + "step": 6858 + }, + { + "epoch": 0.72, + "learning_rate": 4.428520125555906e-06, + "loss": 1.358, + "step": 6859 + }, + { + "epoch": 0.72, + "learning_rate": 4.425480978767692e-06, + "loss": 1.2707, + "step": 6860 + }, + { + "epoch": 0.72, + "learning_rate": 4.422442578821795e-06, + "loss": 1.4066, + "step": 6861 + }, + { + "epoch": 0.72, + "learning_rate": 4.4194049261252845e-06, + "loss": 1.3725, + "step": 6862 + }, + { + "epoch": 0.72, + "learning_rate": 4.416368021085122e-06, + "loss": 1.2392, + "step": 6863 + }, + { + "epoch": 0.72, + "learning_rate": 4.413331864108178e-06, + "loss": 1.2917, + "step": 6864 + }, + { + "epoch": 0.72, + "learning_rate": 4.410296455601223e-06, + "loss": 1.2685, + "step": 6865 + }, + { + "epoch": 0.72, + "learning_rate": 4.407261795970916e-06, + "loss": 1.265, + "step": 6866 + }, + { + "epoch": 0.72, + "learning_rate": 4.404227885623832e-06, + "loss": 1.3838, + "step": 6867 + }, + { + "epoch": 0.72, + "learning_rate": 4.4011947249664276e-06, + "loss": 1.3496, + "step": 6868 + }, + { + "epoch": 0.72, + "learning_rate": 4.398162314405075e-06, + "loss": 1.3007, + "step": 6869 + }, + { + "epoch": 0.72, + "learning_rate": 4.39513065434604e-06, + "loss": 1.2934, + "step": 6870 + }, + { + "epoch": 0.72, + "learning_rate": 4.392099745195483e-06, + "loss": 1.559, + "step": 6871 + }, + { + "epoch": 0.72, + "learning_rate": 4.389069587359468e-06, + "loss": 1.346, + "step": 6872 + }, + { + "epoch": 0.72, + "learning_rate": 4.386040181243965e-06, + "loss": 1.2433, + "step": 6873 + }, + { + "epoch": 0.72, + "learning_rate": 4.3830115272548275e-06, + "loss": 1.2938, + "step": 6874 + }, + { + "epoch": 0.72, + "learning_rate": 4.379983625797821e-06, + "loss": 1.3463, + "step": 6875 + }, + { + "epoch": 0.72, + "learning_rate": 4.376956477278612e-06, + "loss": 1.2832, + "step": 6876 + }, + { + "epoch": 0.72, + "learning_rate": 4.37393008210275e-06, + "loss": 1.3693, + "step": 6877 + }, + { + "epoch": 0.72, + "learning_rate": 4.370904440675705e-06, + "loss": 1.2652, + "step": 6878 + }, + { + "epoch": 0.72, + "learning_rate": 4.367879553402826e-06, + "loss": 1.3217, + "step": 6879 + }, + { + "epoch": 0.72, + "learning_rate": 4.364855420689375e-06, + "loss": 1.3519, + "step": 6880 + }, + { + "epoch": 0.72, + "learning_rate": 4.36183204294051e-06, + "loss": 1.3131, + "step": 6881 + }, + { + "epoch": 0.72, + "learning_rate": 4.35880942056128e-06, + "loss": 1.4334, + "step": 6882 + }, + { + "epoch": 0.72, + "learning_rate": 4.3557875539566415e-06, + "loss": 1.259, + "step": 6883 + }, + { + "epoch": 0.72, + "learning_rate": 4.352766443531451e-06, + "loss": 1.2841, + "step": 6884 + }, + { + "epoch": 0.72, + "learning_rate": 4.349746089690453e-06, + "loss": 1.35, + "step": 6885 + }, + { + "epoch": 0.72, + "learning_rate": 4.346726492838304e-06, + "loss": 1.3623, + "step": 6886 + }, + { + "epoch": 0.72, + "learning_rate": 4.343707653379544e-06, + "loss": 1.3729, + "step": 6887 + }, + { + "epoch": 0.72, + "learning_rate": 4.340689571718626e-06, + "loss": 1.2992, + "step": 6888 + }, + { + "epoch": 0.72, + "learning_rate": 4.337672248259898e-06, + "loss": 1.3484, + "step": 6889 + }, + { + "epoch": 0.72, + "learning_rate": 4.334655683407594e-06, + "loss": 1.3347, + "step": 6890 + }, + { + "epoch": 0.72, + "learning_rate": 4.331639877565865e-06, + "loss": 1.2986, + "step": 6891 + }, + { + "epoch": 0.72, + "learning_rate": 4.328624831138751e-06, + "loss": 1.3217, + "step": 6892 + }, + { + "epoch": 0.72, + "learning_rate": 4.325610544530184e-06, + "loss": 1.2834, + "step": 6893 + }, + { + "epoch": 0.72, + "learning_rate": 4.32259701814401e-06, + "loss": 1.3474, + "step": 6894 + }, + { + "epoch": 0.72, + "learning_rate": 4.319584252383956e-06, + "loss": 1.2871, + "step": 6895 + }, + { + "epoch": 0.72, + "learning_rate": 4.316572247653659e-06, + "loss": 1.3534, + "step": 6896 + }, + { + "epoch": 0.72, + "learning_rate": 4.313561004356653e-06, + "loss": 1.4421, + "step": 6897 + }, + { + "epoch": 0.72, + "learning_rate": 4.310550522896359e-06, + "loss": 1.3091, + "step": 6898 + }, + { + "epoch": 0.72, + "learning_rate": 4.30754080367611e-06, + "loss": 1.2565, + "step": 6899 + }, + { + "epoch": 0.72, + "learning_rate": 4.304531847099135e-06, + "loss": 1.5767, + "step": 6900 + }, + { + "epoch": 0.72, + "learning_rate": 4.3015236535685475e-06, + "loss": 1.4257, + "step": 6901 + }, + { + "epoch": 0.72, + "learning_rate": 4.298516223487373e-06, + "loss": 1.362, + "step": 6902 + }, + { + "epoch": 0.72, + "learning_rate": 4.2955095572585336e-06, + "loss": 1.3475, + "step": 6903 + }, + { + "epoch": 0.72, + "learning_rate": 4.292503655284838e-06, + "loss": 1.3223, + "step": 6904 + }, + { + "epoch": 0.72, + "learning_rate": 4.289498517969006e-06, + "loss": 1.3142, + "step": 6905 + }, + { + "epoch": 0.72, + "learning_rate": 4.286494145713644e-06, + "loss": 1.3124, + "step": 6906 + }, + { + "epoch": 0.72, + "learning_rate": 4.283490538921261e-06, + "loss": 1.3636, + "step": 6907 + }, + { + "epoch": 0.72, + "learning_rate": 4.280487697994269e-06, + "loss": 1.347, + "step": 6908 + }, + { + "epoch": 0.72, + "learning_rate": 4.277485623334964e-06, + "loss": 1.2986, + "step": 6909 + }, + { + "epoch": 0.72, + "learning_rate": 4.27448431534555e-06, + "loss": 1.3058, + "step": 6910 + }, + { + "epoch": 0.72, + "learning_rate": 4.271483774428128e-06, + "loss": 1.7858, + "step": 6911 + }, + { + "epoch": 0.72, + "learning_rate": 4.268484000984689e-06, + "loss": 1.3529, + "step": 6912 + }, + { + "epoch": 0.72, + "learning_rate": 4.26548499541713e-06, + "loss": 1.3215, + "step": 6913 + }, + { + "epoch": 0.73, + "learning_rate": 4.262486758127234e-06, + "loss": 1.2914, + "step": 6914 + }, + { + "epoch": 0.73, + "learning_rate": 4.259489289516693e-06, + "loss": 1.4562, + "step": 6915 + }, + { + "epoch": 0.73, + "learning_rate": 4.256492589987092e-06, + "loss": 1.2548, + "step": 6916 + }, + { + "epoch": 0.73, + "learning_rate": 4.253496659939907e-06, + "loss": 1.3047, + "step": 6917 + }, + { + "epoch": 0.73, + "learning_rate": 4.250501499776516e-06, + "loss": 1.4184, + "step": 6918 + }, + { + "epoch": 0.73, + "learning_rate": 4.2475071098982e-06, + "loss": 1.3519, + "step": 6919 + }, + { + "epoch": 0.73, + "learning_rate": 4.2445134907061224e-06, + "loss": 1.3274, + "step": 6920 + }, + { + "epoch": 0.73, + "learning_rate": 4.2415206426013545e-06, + "loss": 1.389, + "step": 6921 + }, + { + "epoch": 0.73, + "learning_rate": 4.238528565984865e-06, + "loss": 1.2929, + "step": 6922 + }, + { + "epoch": 0.73, + "learning_rate": 4.235537261257507e-06, + "loss": 1.3883, + "step": 6923 + }, + { + "epoch": 0.73, + "learning_rate": 4.232546728820047e-06, + "loss": 1.3395, + "step": 6924 + }, + { + "epoch": 0.73, + "learning_rate": 4.229556969073133e-06, + "loss": 1.3534, + "step": 6925 + }, + { + "epoch": 0.73, + "learning_rate": 4.226567982417317e-06, + "loss": 1.4218, + "step": 6926 + }, + { + "epoch": 0.73, + "learning_rate": 4.223579769253052e-06, + "loss": 1.3737, + "step": 6927 + }, + { + "epoch": 0.73, + "learning_rate": 4.220592329980674e-06, + "loss": 1.4805, + "step": 6928 + }, + { + "epoch": 0.73, + "learning_rate": 4.217605665000426e-06, + "loss": 1.2409, + "step": 6929 + }, + { + "epoch": 0.73, + "learning_rate": 4.21461977471245e-06, + "loss": 1.3375, + "step": 6930 + }, + { + "epoch": 0.73, + "learning_rate": 4.211634659516769e-06, + "loss": 1.3535, + "step": 6931 + }, + { + "epoch": 0.73, + "learning_rate": 4.20865031981332e-06, + "loss": 1.2723, + "step": 6932 + }, + { + "epoch": 0.73, + "learning_rate": 4.2056667560019206e-06, + "loss": 1.342, + "step": 6933 + }, + { + "epoch": 0.73, + "learning_rate": 4.202683968482296e-06, + "loss": 1.4075, + "step": 6934 + }, + { + "epoch": 0.73, + "learning_rate": 4.199701957654065e-06, + "loss": 1.3003, + "step": 6935 + }, + { + "epoch": 0.73, + "learning_rate": 4.196720723916735e-06, + "loss": 1.3098, + "step": 6936 + }, + { + "epoch": 0.73, + "learning_rate": 4.193740267669718e-06, + "loss": 1.2386, + "step": 6937 + }, + { + "epoch": 0.73, + "learning_rate": 4.19076058931232e-06, + "loss": 1.3271, + "step": 6938 + }, + { + "epoch": 0.73, + "learning_rate": 4.187781689243737e-06, + "loss": 1.4604, + "step": 6939 + }, + { + "epoch": 0.73, + "learning_rate": 4.184803567863072e-06, + "loss": 1.3496, + "step": 6940 + }, + { + "epoch": 0.73, + "learning_rate": 4.181826225569308e-06, + "loss": 1.3056, + "step": 6941 + }, + { + "epoch": 0.73, + "learning_rate": 4.1788496627613366e-06, + "loss": 1.2886, + "step": 6942 + }, + { + "epoch": 0.73, + "learning_rate": 4.175873879837944e-06, + "loss": 1.282, + "step": 6943 + }, + { + "epoch": 0.73, + "learning_rate": 4.172898877197802e-06, + "loss": 1.2984, + "step": 6944 + }, + { + "epoch": 0.73, + "learning_rate": 4.169924655239488e-06, + "loss": 1.2909, + "step": 6945 + }, + { + "epoch": 0.73, + "learning_rate": 4.166951214361474e-06, + "loss": 1.4015, + "step": 6946 + }, + { + "epoch": 0.73, + "learning_rate": 4.16397855496212e-06, + "loss": 1.3772, + "step": 6947 + }, + { + "epoch": 0.73, + "learning_rate": 4.161006677439687e-06, + "loss": 1.3089, + "step": 6948 + }, + { + "epoch": 0.73, + "learning_rate": 4.1580355821923344e-06, + "loss": 1.3599, + "step": 6949 + }, + { + "epoch": 0.73, + "learning_rate": 4.155065269618107e-06, + "loss": 1.2886, + "step": 6950 + }, + { + "epoch": 0.73, + "learning_rate": 4.152095740114955e-06, + "loss": 1.3071, + "step": 6951 + }, + { + "epoch": 0.73, + "learning_rate": 4.149126994080715e-06, + "loss": 1.3332, + "step": 6952 + }, + { + "epoch": 0.73, + "learning_rate": 4.146159031913123e-06, + "loss": 1.3835, + "step": 6953 + }, + { + "epoch": 0.73, + "learning_rate": 4.1431918540098144e-06, + "loss": 1.3399, + "step": 6954 + }, + { + "epoch": 0.73, + "learning_rate": 4.140225460768309e-06, + "loss": 1.2906, + "step": 6955 + }, + { + "epoch": 0.73, + "learning_rate": 4.137259852586029e-06, + "loss": 1.295, + "step": 6956 + }, + { + "epoch": 0.73, + "learning_rate": 4.134295029860295e-06, + "loss": 1.3371, + "step": 6957 + }, + { + "epoch": 0.73, + "learning_rate": 4.131330992988308e-06, + "loss": 1.4441, + "step": 6958 + }, + { + "epoch": 0.73, + "learning_rate": 4.1283677423671805e-06, + "loss": 1.3257, + "step": 6959 + }, + { + "epoch": 0.73, + "learning_rate": 4.125405278393907e-06, + "loss": 1.3958, + "step": 6960 + }, + { + "epoch": 0.73, + "learning_rate": 4.1224436014653826e-06, + "loss": 1.2856, + "step": 6961 + }, + { + "epoch": 0.73, + "learning_rate": 4.1194827119784e-06, + "loss": 1.2943, + "step": 6962 + }, + { + "epoch": 0.73, + "learning_rate": 4.116522610329636e-06, + "loss": 1.2691, + "step": 6963 + }, + { + "epoch": 0.73, + "learning_rate": 4.11356329691567e-06, + "loss": 1.293, + "step": 6964 + }, + { + "epoch": 0.73, + "learning_rate": 4.11060477213298e-06, + "loss": 1.3136, + "step": 6965 + }, + { + "epoch": 0.73, + "eval_loss": 1.399178147315979, + "eval_runtime": 77.5864, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 6965 + }, + { + "epoch": 0.73, + "learning_rate": 4.1076470363779235e-06, + "loss": 1.2833, + "step": 6966 + }, + { + "epoch": 0.73, + "learning_rate": 4.104690090046765e-06, + "loss": 1.3177, + "step": 6967 + }, + { + "epoch": 0.73, + "learning_rate": 4.101733933535663e-06, + "loss": 1.2623, + "step": 6968 + }, + { + "epoch": 0.73, + "learning_rate": 4.0987785672406585e-06, + "loss": 1.2814, + "step": 6969 + }, + { + "epoch": 0.73, + "learning_rate": 4.0958239915577036e-06, + "loss": 1.3823, + "step": 6970 + }, + { + "epoch": 0.73, + "learning_rate": 4.092870206882627e-06, + "loss": 1.2926, + "step": 6971 + }, + { + "epoch": 0.73, + "learning_rate": 4.089917213611164e-06, + "loss": 1.3324, + "step": 6972 + }, + { + "epoch": 0.73, + "learning_rate": 4.086965012138943e-06, + "loss": 1.3521, + "step": 6973 + }, + { + "epoch": 0.73, + "learning_rate": 4.084013602861476e-06, + "loss": 1.4828, + "step": 6974 + }, + { + "epoch": 0.73, + "learning_rate": 4.0810629861741804e-06, + "loss": 1.3187, + "step": 6975 + }, + { + "epoch": 0.73, + "learning_rate": 4.078113162472366e-06, + "loss": 1.3478, + "step": 6976 + }, + { + "epoch": 0.73, + "learning_rate": 4.075164132151227e-06, + "loss": 1.4256, + "step": 6977 + }, + { + "epoch": 0.73, + "learning_rate": 4.0722158956058635e-06, + "loss": 1.2815, + "step": 6978 + }, + { + "epoch": 0.73, + "learning_rate": 4.069268453231257e-06, + "loss": 1.3031, + "step": 6979 + }, + { + "epoch": 0.73, + "learning_rate": 4.066321805422292e-06, + "loss": 1.2983, + "step": 6980 + }, + { + "epoch": 0.73, + "learning_rate": 4.063375952573748e-06, + "loss": 1.3595, + "step": 6981 + }, + { + "epoch": 0.73, + "learning_rate": 4.060430895080286e-06, + "loss": 1.3119, + "step": 6982 + }, + { + "epoch": 0.73, + "learning_rate": 4.057486633336472e-06, + "loss": 1.328, + "step": 6983 + }, + { + "epoch": 0.73, + "learning_rate": 4.054543167736766e-06, + "loss": 1.232, + "step": 6984 + }, + { + "epoch": 0.73, + "learning_rate": 4.0516004986755064e-06, + "loss": 1.3288, + "step": 6985 + }, + { + "epoch": 0.73, + "learning_rate": 4.048658626546945e-06, + "loss": 1.2916, + "step": 6986 + }, + { + "epoch": 0.73, + "learning_rate": 4.045717551745209e-06, + "loss": 1.2411, + "step": 6987 + }, + { + "epoch": 0.73, + "learning_rate": 4.042777274664331e-06, + "loss": 1.3256, + "step": 6988 + }, + { + "epoch": 0.73, + "learning_rate": 4.039837795698237e-06, + "loss": 1.3455, + "step": 6989 + }, + { + "epoch": 0.73, + "learning_rate": 4.036899115240732e-06, + "loss": 1.3303, + "step": 6990 + }, + { + "epoch": 0.73, + "learning_rate": 4.033961233685529e-06, + "loss": 1.2805, + "step": 6991 + }, + { + "epoch": 0.73, + "learning_rate": 4.031024151426233e-06, + "loss": 1.3958, + "step": 6992 + }, + { + "epoch": 0.73, + "learning_rate": 4.0280878688563275e-06, + "loss": 1.2853, + "step": 6993 + }, + { + "epoch": 0.73, + "learning_rate": 4.0251523863692054e-06, + "loss": 1.2433, + "step": 6994 + }, + { + "epoch": 0.73, + "learning_rate": 4.022217704358148e-06, + "loss": 1.2644, + "step": 6995 + }, + { + "epoch": 0.73, + "learning_rate": 4.0192838232163204e-06, + "loss": 1.3218, + "step": 6996 + }, + { + "epoch": 0.73, + "learning_rate": 4.016350743336795e-06, + "loss": 1.2973, + "step": 6997 + }, + { + "epoch": 0.73, + "learning_rate": 4.013418465112521e-06, + "loss": 1.3209, + "step": 6998 + }, + { + "epoch": 0.73, + "learning_rate": 4.010486988936353e-06, + "loss": 1.2855, + "step": 6999 + }, + { + "epoch": 0.73, + "learning_rate": 4.007556315201035e-06, + "loss": 1.2381, + "step": 7000 + }, + { + "epoch": 0.73, + "learning_rate": 4.004626444299198e-06, + "loss": 1.3558, + "step": 7001 + }, + { + "epoch": 0.73, + "learning_rate": 4.001697376623371e-06, + "loss": 1.3139, + "step": 7002 + }, + { + "epoch": 0.73, + "learning_rate": 3.998769112565978e-06, + "loss": 1.3582, + "step": 7003 + }, + { + "epoch": 0.73, + "learning_rate": 3.9958416525193225e-06, + "loss": 1.2684, + "step": 7004 + }, + { + "epoch": 0.73, + "learning_rate": 3.992914996875618e-06, + "loss": 1.2915, + "step": 7005 + }, + { + "epoch": 0.73, + "learning_rate": 3.9899891460269536e-06, + "loss": 1.3205, + "step": 7006 + }, + { + "epoch": 0.73, + "learning_rate": 3.987064100365321e-06, + "loss": 1.2966, + "step": 7007 + }, + { + "epoch": 0.73, + "learning_rate": 3.984139860282606e-06, + "loss": 1.2691, + "step": 7008 + }, + { + "epoch": 0.74, + "learning_rate": 3.981216426170572e-06, + "loss": 1.3421, + "step": 7009 + }, + { + "epoch": 0.74, + "learning_rate": 3.97829379842089e-06, + "loss": 1.3034, + "step": 7010 + }, + { + "epoch": 0.74, + "learning_rate": 3.9753719774251195e-06, + "loss": 1.2863, + "step": 7011 + }, + { + "epoch": 0.74, + "learning_rate": 3.972450963574703e-06, + "loss": 1.3812, + "step": 7012 + }, + { + "epoch": 0.74, + "learning_rate": 3.969530757260986e-06, + "loss": 1.334, + "step": 7013 + }, + { + "epoch": 0.74, + "learning_rate": 3.966611358875201e-06, + "loss": 1.3289, + "step": 7014 + }, + { + "epoch": 0.74, + "learning_rate": 3.963692768808468e-06, + "loss": 1.395, + "step": 7015 + }, + { + "epoch": 0.74, + "learning_rate": 3.960774987451811e-06, + "loss": 1.3298, + "step": 7016 + }, + { + "epoch": 0.74, + "learning_rate": 3.957858015196128e-06, + "loss": 1.3304, + "step": 7017 + }, + { + "epoch": 0.74, + "learning_rate": 3.954941852432224e-06, + "loss": 1.301, + "step": 7018 + }, + { + "epoch": 0.74, + "learning_rate": 3.952026499550791e-06, + "loss": 1.3568, + "step": 7019 + }, + { + "epoch": 0.74, + "learning_rate": 3.949111956942406e-06, + "loss": 1.4464, + "step": 7020 + }, + { + "epoch": 0.74, + "learning_rate": 3.946198224997548e-06, + "loss": 1.4417, + "step": 7021 + }, + { + "epoch": 0.74, + "learning_rate": 3.943285304106583e-06, + "loss": 1.3979, + "step": 7022 + }, + { + "epoch": 0.74, + "learning_rate": 3.940373194659761e-06, + "loss": 1.2943, + "step": 7023 + }, + { + "epoch": 0.74, + "learning_rate": 3.937461897047239e-06, + "loss": 1.2571, + "step": 7024 + }, + { + "epoch": 0.74, + "learning_rate": 3.9345514116590454e-06, + "loss": 1.3433, + "step": 7025 + }, + { + "epoch": 0.74, + "learning_rate": 3.931641738885117e-06, + "loss": 1.4203, + "step": 7026 + }, + { + "epoch": 0.74, + "learning_rate": 3.9287328791152775e-06, + "loss": 1.3657, + "step": 7027 + }, + { + "epoch": 0.74, + "learning_rate": 3.925824832739234e-06, + "loss": 1.3954, + "step": 7028 + }, + { + "epoch": 0.74, + "learning_rate": 3.92291760014659e-06, + "loss": 1.2847, + "step": 7029 + }, + { + "epoch": 0.74, + "learning_rate": 3.920011181726846e-06, + "loss": 1.2776, + "step": 7030 + }, + { + "epoch": 0.74, + "learning_rate": 3.91710557786938e-06, + "loss": 1.3391, + "step": 7031 + }, + { + "epoch": 0.74, + "learning_rate": 3.914200788963472e-06, + "loss": 1.2935, + "step": 7032 + }, + { + "epoch": 0.74, + "learning_rate": 3.911296815398291e-06, + "loss": 1.3775, + "step": 7033 + }, + { + "epoch": 0.74, + "learning_rate": 3.90839365756289e-06, + "loss": 1.3652, + "step": 7034 + }, + { + "epoch": 0.74, + "learning_rate": 3.905491315846224e-06, + "loss": 1.2902, + "step": 7035 + }, + { + "epoch": 0.74, + "learning_rate": 3.902589790637125e-06, + "loss": 1.2859, + "step": 7036 + }, + { + "epoch": 0.74, + "learning_rate": 3.899689082324325e-06, + "loss": 1.4019, + "step": 7037 + }, + { + "epoch": 0.74, + "learning_rate": 3.89678919129645e-06, + "loss": 1.299, + "step": 7038 + }, + { + "epoch": 0.74, + "learning_rate": 3.893890117942003e-06, + "loss": 1.275, + "step": 7039 + }, + { + "epoch": 0.74, + "learning_rate": 3.890991862649388e-06, + "loss": 1.2593, + "step": 7040 + }, + { + "epoch": 0.74, + "learning_rate": 3.888094425806902e-06, + "loss": 1.2932, + "step": 7041 + }, + { + "epoch": 0.74, + "learning_rate": 3.885197807802719e-06, + "loss": 1.3038, + "step": 7042 + }, + { + "epoch": 0.74, + "learning_rate": 3.882302009024917e-06, + "loss": 1.285, + "step": 7043 + }, + { + "epoch": 0.74, + "learning_rate": 3.879407029861455e-06, + "loss": 1.4116, + "step": 7044 + }, + { + "epoch": 0.74, + "learning_rate": 3.876512870700187e-06, + "loss": 1.3823, + "step": 7045 + }, + { + "epoch": 0.74, + "learning_rate": 3.873619531928858e-06, + "loss": 1.2803, + "step": 7046 + }, + { + "epoch": 0.74, + "learning_rate": 3.870727013935099e-06, + "loss": 1.3287, + "step": 7047 + }, + { + "epoch": 0.74, + "learning_rate": 3.867835317106432e-06, + "loss": 1.3919, + "step": 7048 + }, + { + "epoch": 0.74, + "learning_rate": 3.864944441830275e-06, + "loss": 1.3967, + "step": 7049 + }, + { + "epoch": 0.74, + "learning_rate": 3.862054388493924e-06, + "loss": 1.2749, + "step": 7050 + }, + { + "epoch": 0.74, + "learning_rate": 3.85916515748458e-06, + "loss": 1.3408, + "step": 7051 + }, + { + "epoch": 0.74, + "learning_rate": 3.856276749189317e-06, + "loss": 1.3143, + "step": 7052 + }, + { + "epoch": 0.74, + "learning_rate": 3.853389163995111e-06, + "loss": 1.3661, + "step": 7053 + }, + { + "epoch": 0.74, + "learning_rate": 3.8505024022888305e-06, + "loss": 1.3094, + "step": 7054 + }, + { + "epoch": 0.74, + "learning_rate": 3.847616464457216e-06, + "loss": 1.2736, + "step": 7055 + }, + { + "epoch": 0.74, + "learning_rate": 3.844731350886917e-06, + "loss": 1.3628, + "step": 7056 + }, + { + "epoch": 0.74, + "learning_rate": 3.841847061964465e-06, + "loss": 1.2706, + "step": 7057 + }, + { + "epoch": 0.74, + "learning_rate": 3.838963598076275e-06, + "loss": 1.2566, + "step": 7058 + }, + { + "epoch": 0.74, + "learning_rate": 3.83608095960866e-06, + "loss": 1.2415, + "step": 7059 + }, + { + "epoch": 0.74, + "learning_rate": 3.833199146947823e-06, + "loss": 1.2748, + "step": 7060 + }, + { + "epoch": 0.74, + "learning_rate": 3.830318160479847e-06, + "loss": 1.4672, + "step": 7061 + }, + { + "epoch": 0.74, + "learning_rate": 3.827438000590714e-06, + "loss": 1.2907, + "step": 7062 + }, + { + "epoch": 0.74, + "learning_rate": 3.824558667666288e-06, + "loss": 1.3477, + "step": 7063 + }, + { + "epoch": 0.74, + "learning_rate": 3.821680162092328e-06, + "loss": 1.1135, + "step": 7064 + }, + { + "epoch": 0.74, + "learning_rate": 3.8188024842544825e-06, + "loss": 1.3724, + "step": 7065 + }, + { + "epoch": 0.74, + "learning_rate": 3.81592563453828e-06, + "loss": 1.3854, + "step": 7066 + }, + { + "epoch": 0.74, + "learning_rate": 3.8130496133291473e-06, + "loss": 1.3074, + "step": 7067 + }, + { + "epoch": 0.74, + "learning_rate": 3.8101744210124012e-06, + "loss": 1.4434, + "step": 7068 + }, + { + "epoch": 0.74, + "learning_rate": 3.807300057973238e-06, + "loss": 1.2754, + "step": 7069 + }, + { + "epoch": 0.74, + "learning_rate": 3.804426524596754e-06, + "loss": 1.3654, + "step": 7070 + }, + { + "epoch": 0.74, + "learning_rate": 3.8015538212679214e-06, + "loss": 1.2616, + "step": 7071 + }, + { + "epoch": 0.74, + "learning_rate": 3.798681948371613e-06, + "loss": 1.2939, + "step": 7072 + }, + { + "epoch": 0.74, + "learning_rate": 3.7958109062925894e-06, + "loss": 1.2787, + "step": 7073 + }, + { + "epoch": 0.74, + "learning_rate": 3.792940695415489e-06, + "loss": 1.2953, + "step": 7074 + }, + { + "epoch": 0.74, + "learning_rate": 3.7900713161248515e-06, + "loss": 1.2714, + "step": 7075 + }, + { + "epoch": 0.74, + "learning_rate": 3.7872027688051004e-06, + "loss": 1.3085, + "step": 7076 + }, + { + "epoch": 0.74, + "learning_rate": 3.7843350538405433e-06, + "loss": 1.311, + "step": 7077 + }, + { + "epoch": 0.74, + "learning_rate": 3.781468171615382e-06, + "loss": 1.3367, + "step": 7078 + }, + { + "epoch": 0.74, + "learning_rate": 3.7786021225137102e-06, + "loss": 1.2768, + "step": 7079 + }, + { + "epoch": 0.74, + "learning_rate": 3.775736906919496e-06, + "loss": 1.2828, + "step": 7080 + }, + { + "epoch": 0.74, + "learning_rate": 3.772872525216613e-06, + "loss": 1.3682, + "step": 7081 + }, + { + "epoch": 0.74, + "learning_rate": 3.7700089777888072e-06, + "loss": 1.3906, + "step": 7082 + }, + { + "epoch": 0.74, + "learning_rate": 3.767146265019723e-06, + "loss": 1.2712, + "step": 7083 + }, + { + "epoch": 0.74, + "learning_rate": 3.764284387292896e-06, + "loss": 1.3405, + "step": 7084 + }, + { + "epoch": 0.74, + "learning_rate": 3.761423344991736e-06, + "loss": 1.3941, + "step": 7085 + }, + { + "epoch": 0.74, + "learning_rate": 3.7585631384995523e-06, + "loss": 1.3463, + "step": 7086 + }, + { + "epoch": 0.74, + "learning_rate": 3.7557037681995423e-06, + "loss": 1.2771, + "step": 7087 + }, + { + "epoch": 0.74, + "learning_rate": 3.7528452344747834e-06, + "loss": 1.2706, + "step": 7088 + }, + { + "epoch": 0.74, + "learning_rate": 3.7499875377082497e-06, + "loss": 1.2672, + "step": 7089 + }, + { + "epoch": 0.74, + "learning_rate": 3.7471306782827944e-06, + "loss": 1.2638, + "step": 7090 + }, + { + "epoch": 0.74, + "learning_rate": 3.744274656581166e-06, + "loss": 1.3417, + "step": 7091 + }, + { + "epoch": 0.74, + "learning_rate": 3.7414194729860008e-06, + "loss": 1.278, + "step": 7092 + }, + { + "epoch": 0.74, + "learning_rate": 3.738565127879814e-06, + "loss": 1.2753, + "step": 7093 + }, + { + "epoch": 0.74, + "learning_rate": 3.7357116216450183e-06, + "loss": 1.2989, + "step": 7094 + }, + { + "epoch": 0.74, + "learning_rate": 3.7328589546639127e-06, + "loss": 1.263, + "step": 7095 + }, + { + "epoch": 0.74, + "learning_rate": 3.7300071273186745e-06, + "loss": 1.3534, + "step": 7096 + }, + { + "epoch": 0.74, + "learning_rate": 3.7271561399913825e-06, + "loss": 1.2565, + "step": 7097 + }, + { + "epoch": 0.74, + "learning_rate": 3.724305993063989e-06, + "loss": 1.3233, + "step": 7098 + }, + { + "epoch": 0.74, + "learning_rate": 3.7214566869183443e-06, + "loss": 1.3179, + "step": 7099 + }, + { + "epoch": 0.74, + "learning_rate": 3.718608221936184e-06, + "loss": 1.2749, + "step": 7100 + }, + { + "epoch": 0.74, + "learning_rate": 3.715760598499124e-06, + "loss": 1.3106, + "step": 7101 + }, + { + "epoch": 0.74, + "learning_rate": 3.712913816988675e-06, + "loss": 1.3115, + "step": 7102 + }, + { + "epoch": 0.74, + "learning_rate": 3.7100678777862364e-06, + "loss": 1.2798, + "step": 7103 + }, + { + "epoch": 0.74, + "learning_rate": 3.7072227812730853e-06, + "loss": 1.3964, + "step": 7104 + }, + { + "epoch": 0.75, + "learning_rate": 3.7043785278303923e-06, + "loss": 1.4034, + "step": 7105 + }, + { + "epoch": 0.75, + "learning_rate": 3.70153511783922e-06, + "loss": 1.3244, + "step": 7106 + }, + { + "epoch": 0.75, + "learning_rate": 3.698692551680505e-06, + "loss": 1.3283, + "step": 7107 + }, + { + "epoch": 0.75, + "learning_rate": 3.6958508297350847e-06, + "loss": 1.3567, + "step": 7108 + }, + { + "epoch": 0.75, + "learning_rate": 3.6930099523836692e-06, + "loss": 1.3178, + "step": 7109 + }, + { + "epoch": 0.75, + "learning_rate": 3.6901699200068673e-06, + "loss": 1.2697, + "step": 7110 + }, + { + "epoch": 0.75, + "learning_rate": 3.687330732985175e-06, + "loss": 1.2501, + "step": 7111 + }, + { + "epoch": 0.75, + "learning_rate": 3.6844923916989607e-06, + "loss": 1.2772, + "step": 7112 + }, + { + "epoch": 0.75, + "learning_rate": 3.681654896528495e-06, + "loss": 1.2845, + "step": 7113 + }, + { + "epoch": 0.75, + "learning_rate": 3.6788182478539312e-06, + "loss": 1.3151, + "step": 7114 + }, + { + "epoch": 0.75, + "learning_rate": 3.6759824460553016e-06, + "loss": 1.4925, + "step": 7115 + }, + { + "epoch": 0.75, + "learning_rate": 3.673147491512539e-06, + "loss": 1.2892, + "step": 7116 + }, + { + "epoch": 0.75, + "learning_rate": 3.670313384605444e-06, + "loss": 1.2906, + "step": 7117 + }, + { + "epoch": 0.75, + "learning_rate": 3.6674801257137195e-06, + "loss": 1.3927, + "step": 7118 + }, + { + "epoch": 0.75, + "learning_rate": 3.6646477152169522e-06, + "loss": 1.4001, + "step": 7119 + }, + { + "epoch": 0.75, + "learning_rate": 3.6618161534946074e-06, + "loss": 1.3363, + "step": 7120 + }, + { + "epoch": 0.75, + "learning_rate": 3.658985440926044e-06, + "loss": 1.3297, + "step": 7121 + }, + { + "epoch": 0.75, + "learning_rate": 3.656155577890507e-06, + "loss": 1.3029, + "step": 7122 + }, + { + "epoch": 0.75, + "learning_rate": 3.653326564767119e-06, + "loss": 1.3452, + "step": 7123 + }, + { + "epoch": 0.75, + "learning_rate": 3.6504984019348987e-06, + "loss": 1.3246, + "step": 7124 + }, + { + "epoch": 0.75, + "learning_rate": 3.647671089772752e-06, + "loss": 1.3285, + "step": 7125 + }, + { + "epoch": 0.75, + "learning_rate": 3.6448446286594574e-06, + "loss": 1.3127, + "step": 7126 + }, + { + "epoch": 0.75, + "learning_rate": 3.6420190189736946e-06, + "loss": 1.3224, + "step": 7127 + }, + { + "epoch": 0.75, + "learning_rate": 3.6391942610940178e-06, + "loss": 1.3086, + "step": 7128 + }, + { + "epoch": 0.75, + "learning_rate": 3.6363703553988748e-06, + "loss": 1.3741, + "step": 7129 + }, + { + "epoch": 0.75, + "learning_rate": 3.633547302266599e-06, + "loss": 1.3192, + "step": 7130 + }, + { + "epoch": 0.75, + "learning_rate": 3.6307251020754e-06, + "loss": 1.3032, + "step": 7131 + }, + { + "epoch": 0.75, + "learning_rate": 3.6279037552033847e-06, + "loss": 1.2642, + "step": 7132 + }, + { + "epoch": 0.75, + "learning_rate": 3.6250832620285436e-06, + "loss": 1.3948, + "step": 7133 + }, + { + "epoch": 0.75, + "learning_rate": 3.6222636229287445e-06, + "loss": 1.3542, + "step": 7134 + }, + { + "epoch": 0.75, + "learning_rate": 3.6194448382817526e-06, + "loss": 1.3028, + "step": 7135 + }, + { + "epoch": 0.75, + "learning_rate": 3.616626908465205e-06, + "loss": 1.3017, + "step": 7136 + }, + { + "epoch": 0.75, + "learning_rate": 3.613809833856636e-06, + "loss": 1.3072, + "step": 7137 + }, + { + "epoch": 0.75, + "learning_rate": 3.6109936148334666e-06, + "loss": 1.3065, + "step": 7138 + }, + { + "epoch": 0.75, + "learning_rate": 3.608178251772988e-06, + "loss": 1.4268, + "step": 7139 + }, + { + "epoch": 0.75, + "learning_rate": 3.6053637450523914e-06, + "loss": 1.301, + "step": 7140 + }, + { + "epoch": 0.75, + "learning_rate": 3.6025500950487514e-06, + "loss": 1.2873, + "step": 7141 + }, + { + "epoch": 0.75, + "learning_rate": 3.599737302139018e-06, + "loss": 1.2831, + "step": 7142 + }, + { + "epoch": 0.75, + "learning_rate": 3.5969253667000403e-06, + "loss": 1.5125, + "step": 7143 + }, + { + "epoch": 0.75, + "learning_rate": 3.594114289108538e-06, + "loss": 1.3643, + "step": 7144 + }, + { + "epoch": 0.75, + "learning_rate": 3.5913040697411272e-06, + "loss": 1.3157, + "step": 7145 + }, + { + "epoch": 0.75, + "learning_rate": 3.5884947089743084e-06, + "loss": 1.2687, + "step": 7146 + }, + { + "epoch": 0.75, + "learning_rate": 3.585686207184458e-06, + "loss": 1.3227, + "step": 7147 + }, + { + "epoch": 0.75, + "learning_rate": 3.5828785647478435e-06, + "loss": 1.2745, + "step": 7148 + }, + { + "epoch": 0.75, + "learning_rate": 3.5800717820406226e-06, + "loss": 1.332, + "step": 7149 + }, + { + "epoch": 0.75, + "learning_rate": 3.5772658594388253e-06, + "loss": 1.2863, + "step": 7150 + }, + { + "epoch": 0.75, + "learning_rate": 3.5744607973183766e-06, + "loss": 1.3791, + "step": 7151 + }, + { + "epoch": 0.75, + "learning_rate": 3.5716565960550844e-06, + "loss": 1.2781, + "step": 7152 + }, + { + "epoch": 0.75, + "learning_rate": 3.5688532560246348e-06, + "loss": 1.252, + "step": 7153 + }, + { + "epoch": 0.75, + "learning_rate": 3.5660507776026086e-06, + "loss": 1.3158, + "step": 7154 + }, + { + "epoch": 0.75, + "learning_rate": 3.5632491611644603e-06, + "loss": 1.3241, + "step": 7155 + }, + { + "epoch": 0.75, + "learning_rate": 3.5604484070855382e-06, + "loss": 1.2572, + "step": 7156 + }, + { + "epoch": 0.75, + "learning_rate": 3.5576485157410733e-06, + "loss": 1.3734, + "step": 7157 + }, + { + "epoch": 0.75, + "learning_rate": 3.5548494875061724e-06, + "loss": 1.3253, + "step": 7158 + }, + { + "epoch": 0.75, + "learning_rate": 3.5520513227558385e-06, + "loss": 1.2659, + "step": 7159 + }, + { + "epoch": 0.75, + "learning_rate": 3.5492540218649553e-06, + "loss": 1.3149, + "step": 7160 + }, + { + "epoch": 0.75, + "learning_rate": 3.546457585208283e-06, + "loss": 1.3413, + "step": 7161 + }, + { + "epoch": 0.75, + "learning_rate": 3.5436620131604803e-06, + "loss": 1.2846, + "step": 7162 + }, + { + "epoch": 0.75, + "learning_rate": 3.540867306096073e-06, + "loss": 1.3239, + "step": 7163 + }, + { + "epoch": 0.75, + "learning_rate": 3.5380734643894856e-06, + "loss": 1.3137, + "step": 7164 + }, + { + "epoch": 0.75, + "eval_loss": 1.397520899772644, + "eval_runtime": 77.542, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 7164 + }, + { + "epoch": 0.75, + "learning_rate": 3.535280488415024e-06, + "loss": 1.414, + "step": 7165 + }, + { + "epoch": 0.75, + "learning_rate": 3.5324883785468665e-06, + "loss": 1.2708, + "step": 7166 + }, + { + "epoch": 0.75, + "learning_rate": 3.529697135159089e-06, + "loss": 1.2975, + "step": 7167 + }, + { + "epoch": 0.75, + "learning_rate": 3.526906758625651e-06, + "loss": 1.3723, + "step": 7168 + }, + { + "epoch": 0.75, + "learning_rate": 3.5241172493203822e-06, + "loss": 1.4105, + "step": 7169 + }, + { + "epoch": 0.75, + "learning_rate": 3.5213286076170107e-06, + "loss": 1.2592, + "step": 7170 + }, + { + "epoch": 0.75, + "learning_rate": 3.5185408338891437e-06, + "loss": 1.3361, + "step": 7171 + }, + { + "epoch": 0.75, + "learning_rate": 3.515753928510267e-06, + "loss": 1.2591, + "step": 7172 + }, + { + "epoch": 0.75, + "learning_rate": 3.512967891853759e-06, + "loss": 1.2938, + "step": 7173 + }, + { + "epoch": 0.75, + "learning_rate": 3.510182724292872e-06, + "loss": 1.4116, + "step": 7174 + }, + { + "epoch": 0.75, + "learning_rate": 3.5073984262007486e-06, + "loss": 1.3968, + "step": 7175 + }, + { + "epoch": 0.75, + "learning_rate": 3.5046149979504184e-06, + "loss": 1.31, + "step": 7176 + }, + { + "epoch": 0.75, + "learning_rate": 3.5018324399147817e-06, + "loss": 1.2966, + "step": 7177 + }, + { + "epoch": 0.75, + "learning_rate": 3.4990507524666327e-06, + "loss": 1.3431, + "step": 7178 + }, + { + "epoch": 0.75, + "learning_rate": 3.49626993597865e-06, + "loss": 1.3227, + "step": 7179 + }, + { + "epoch": 0.75, + "learning_rate": 3.4934899908233834e-06, + "loss": 1.201, + "step": 7180 + }, + { + "epoch": 0.75, + "learning_rate": 3.490710917373283e-06, + "loss": 1.3003, + "step": 7181 + }, + { + "epoch": 0.75, + "learning_rate": 3.487932716000666e-06, + "loss": 1.2879, + "step": 7182 + }, + { + "epoch": 0.75, + "learning_rate": 3.485155387077742e-06, + "loss": 1.2742, + "step": 7183 + }, + { + "epoch": 0.75, + "learning_rate": 3.4823789309766065e-06, + "loss": 1.2972, + "step": 7184 + }, + { + "epoch": 0.75, + "learning_rate": 3.479603348069226e-06, + "loss": 1.3763, + "step": 7185 + }, + { + "epoch": 0.75, + "learning_rate": 3.4768286387274597e-06, + "loss": 1.4653, + "step": 7186 + }, + { + "epoch": 0.75, + "learning_rate": 3.4740548033230524e-06, + "loss": 1.3534, + "step": 7187 + }, + { + "epoch": 0.75, + "learning_rate": 3.4712818422276207e-06, + "loss": 1.3917, + "step": 7188 + }, + { + "epoch": 0.75, + "learning_rate": 3.4685097558126733e-06, + "loss": 1.306, + "step": 7189 + }, + { + "epoch": 0.75, + "learning_rate": 3.465738544449596e-06, + "loss": 1.4628, + "step": 7190 + }, + { + "epoch": 0.75, + "learning_rate": 3.4629682085096606e-06, + "loss": 1.3916, + "step": 7191 + }, + { + "epoch": 0.75, + "learning_rate": 3.4601987483640243e-06, + "loss": 1.3348, + "step": 7192 + }, + { + "epoch": 0.75, + "learning_rate": 3.457430164383718e-06, + "loss": 1.4771, + "step": 7193 + }, + { + "epoch": 0.75, + "learning_rate": 3.4546624569396635e-06, + "loss": 1.5004, + "step": 7194 + }, + { + "epoch": 0.75, + "learning_rate": 3.451895626402667e-06, + "loss": 1.279, + "step": 7195 + }, + { + "epoch": 0.75, + "learning_rate": 3.4491296731434053e-06, + "loss": 1.3263, + "step": 7196 + }, + { + "epoch": 0.75, + "learning_rate": 3.4463645975324466e-06, + "loss": 1.2449, + "step": 7197 + }, + { + "epoch": 0.75, + "learning_rate": 3.4436003999402466e-06, + "loss": 1.2743, + "step": 7198 + }, + { + "epoch": 0.75, + "learning_rate": 3.4408370807371283e-06, + "loss": 1.3127, + "step": 7199 + }, + { + "epoch": 0.76, + "learning_rate": 3.438074640293312e-06, + "loss": 1.2996, + "step": 7200 + }, + { + "epoch": 0.76, + "learning_rate": 3.435313078978887e-06, + "loss": 1.3114, + "step": 7201 + }, + { + "epoch": 0.76, + "learning_rate": 3.432552397163835e-06, + "loss": 1.2574, + "step": 7202 + }, + { + "epoch": 0.76, + "learning_rate": 3.42979259521802e-06, + "loss": 1.2605, + "step": 7203 + }, + { + "epoch": 0.76, + "learning_rate": 3.4270336735111785e-06, + "loss": 1.2578, + "step": 7204 + }, + { + "epoch": 0.76, + "learning_rate": 3.424275632412938e-06, + "loss": 1.3297, + "step": 7205 + }, + { + "epoch": 0.76, + "learning_rate": 3.4215184722928073e-06, + "loss": 1.2353, + "step": 7206 + }, + { + "epoch": 0.76, + "learning_rate": 3.4187621935201707e-06, + "loss": 1.288, + "step": 7207 + }, + { + "epoch": 0.76, + "learning_rate": 3.416006796464304e-06, + "loss": 1.2947, + "step": 7208 + }, + { + "epoch": 0.76, + "learning_rate": 3.4132522814943513e-06, + "loss": 1.4208, + "step": 7209 + }, + { + "epoch": 0.76, + "learning_rate": 3.4104986489793534e-06, + "loss": 1.3273, + "step": 7210 + }, + { + "epoch": 0.76, + "learning_rate": 3.4077458992882285e-06, + "loss": 1.274, + "step": 7211 + }, + { + "epoch": 0.76, + "learning_rate": 3.404994032789766e-06, + "loss": 1.2782, + "step": 7212 + }, + { + "epoch": 0.76, + "learning_rate": 3.4022430498526505e-06, + "loss": 1.3513, + "step": 7213 + }, + { + "epoch": 0.76, + "learning_rate": 3.3994929508454455e-06, + "loss": 1.2843, + "step": 7214 + }, + { + "epoch": 0.76, + "learning_rate": 3.3967437361365873e-06, + "loss": 1.2764, + "step": 7215 + }, + { + "epoch": 0.76, + "learning_rate": 3.3939954060944036e-06, + "loss": 1.2786, + "step": 7216 + }, + { + "epoch": 0.76, + "learning_rate": 3.391247961087103e-06, + "loss": 1.2927, + "step": 7217 + }, + { + "epoch": 0.76, + "learning_rate": 3.3885014014827657e-06, + "loss": 1.3735, + "step": 7218 + }, + { + "epoch": 0.76, + "learning_rate": 3.385755727649367e-06, + "loss": 1.3065, + "step": 7219 + }, + { + "epoch": 0.76, + "learning_rate": 3.3830109399547506e-06, + "loss": 1.2463, + "step": 7220 + }, + { + "epoch": 0.76, + "learning_rate": 3.3802670387666492e-06, + "loss": 1.2496, + "step": 7221 + }, + { + "epoch": 0.76, + "learning_rate": 3.3775240244526796e-06, + "loss": 1.2807, + "step": 7222 + }, + { + "epoch": 0.76, + "learning_rate": 3.3747818973803294e-06, + "loss": 1.313, + "step": 7223 + }, + { + "epoch": 0.76, + "learning_rate": 3.372040657916974e-06, + "loss": 1.3557, + "step": 7224 + }, + { + "epoch": 0.76, + "learning_rate": 3.3693003064298744e-06, + "loss": 1.3705, + "step": 7225 + }, + { + "epoch": 0.76, + "learning_rate": 3.366560843286161e-06, + "loss": 1.3763, + "step": 7226 + }, + { + "epoch": 0.76, + "learning_rate": 3.3638222688528565e-06, + "loss": 1.3252, + "step": 7227 + }, + { + "epoch": 0.76, + "learning_rate": 3.361084583496853e-06, + "loss": 1.2635, + "step": 7228 + }, + { + "epoch": 0.76, + "learning_rate": 3.3583477875849346e-06, + "loss": 1.3084, + "step": 7229 + }, + { + "epoch": 0.76, + "learning_rate": 3.3556118814837646e-06, + "loss": 1.3347, + "step": 7230 + }, + { + "epoch": 0.76, + "learning_rate": 3.3528768655598764e-06, + "loss": 1.3937, + "step": 7231 + }, + { + "epoch": 0.76, + "learning_rate": 3.350142740179696e-06, + "loss": 1.3251, + "step": 7232 + }, + { + "epoch": 0.76, + "learning_rate": 3.347409505709529e-06, + "loss": 1.3654, + "step": 7233 + }, + { + "epoch": 0.76, + "learning_rate": 3.344677162515553e-06, + "loss": 1.3864, + "step": 7234 + }, + { + "epoch": 0.76, + "learning_rate": 3.3419457109638377e-06, + "loss": 1.3142, + "step": 7235 + }, + { + "epoch": 0.76, + "learning_rate": 3.3392151514203195e-06, + "loss": 1.3557, + "step": 7236 + }, + { + "epoch": 0.76, + "learning_rate": 3.3364854842508276e-06, + "loss": 1.3093, + "step": 7237 + }, + { + "epoch": 0.76, + "learning_rate": 3.333756709821072e-06, + "loss": 1.3763, + "step": 7238 + }, + { + "epoch": 0.76, + "learning_rate": 3.3310288284966297e-06, + "loss": 1.2943, + "step": 7239 + }, + { + "epoch": 0.76, + "learning_rate": 3.3283018406429703e-06, + "loss": 1.473, + "step": 7240 + }, + { + "epoch": 0.76, + "learning_rate": 3.3255757466254448e-06, + "loss": 1.2501, + "step": 7241 + }, + { + "epoch": 0.76, + "learning_rate": 3.322850546809271e-06, + "loss": 1.2893, + "step": 7242 + }, + { + "epoch": 0.76, + "learning_rate": 3.3201262415595614e-06, + "loss": 1.2995, + "step": 7243 + }, + { + "epoch": 0.76, + "learning_rate": 3.3174028312413044e-06, + "loss": 1.2985, + "step": 7244 + }, + { + "epoch": 0.76, + "learning_rate": 3.31468031621936e-06, + "loss": 1.2868, + "step": 7245 + }, + { + "epoch": 0.76, + "learning_rate": 3.311958696858484e-06, + "loss": 1.2467, + "step": 7246 + }, + { + "epoch": 0.76, + "learning_rate": 3.309237973523295e-06, + "loss": 1.2303, + "step": 7247 + }, + { + "epoch": 0.76, + "learning_rate": 3.3065181465783045e-06, + "loss": 1.3172, + "step": 7248 + }, + { + "epoch": 0.76, + "learning_rate": 3.303799216387902e-06, + "loss": 1.2003, + "step": 7249 + }, + { + "epoch": 0.76, + "learning_rate": 3.3010811833163482e-06, + "loss": 1.2931, + "step": 7250 + }, + { + "epoch": 0.76, + "learning_rate": 3.2983640477277925e-06, + "loss": 1.3135, + "step": 7251 + }, + { + "epoch": 0.76, + "learning_rate": 3.2956478099862644e-06, + "loss": 1.2711, + "step": 7252 + }, + { + "epoch": 0.76, + "learning_rate": 3.292932470455663e-06, + "loss": 1.291, + "step": 7253 + }, + { + "epoch": 0.76, + "learning_rate": 3.2902180294997832e-06, + "loss": 1.2838, + "step": 7254 + }, + { + "epoch": 0.76, + "learning_rate": 3.2875044874822804e-06, + "loss": 1.2381, + "step": 7255 + }, + { + "epoch": 0.76, + "learning_rate": 3.284791844766705e-06, + "loss": 1.2966, + "step": 7256 + }, + { + "epoch": 0.76, + "learning_rate": 3.282080101716484e-06, + "loss": 1.3418, + "step": 7257 + }, + { + "epoch": 0.76, + "learning_rate": 3.2793692586949143e-06, + "loss": 1.3247, + "step": 7258 + }, + { + "epoch": 0.76, + "learning_rate": 3.2766593160651827e-06, + "loss": 1.3462, + "step": 7259 + }, + { + "epoch": 0.76, + "learning_rate": 3.273950274190356e-06, + "loss": 1.3699, + "step": 7260 + }, + { + "epoch": 0.76, + "learning_rate": 3.2712421334333687e-06, + "loss": 1.2863, + "step": 7261 + }, + { + "epoch": 0.76, + "learning_rate": 3.268534894157046e-06, + "loss": 1.3791, + "step": 7262 + }, + { + "epoch": 0.76, + "learning_rate": 3.265828556724092e-06, + "loss": 1.3066, + "step": 7263 + }, + { + "epoch": 0.76, + "learning_rate": 3.2631231214970784e-06, + "loss": 1.319, + "step": 7264 + }, + { + "epoch": 0.76, + "learning_rate": 3.260418588838471e-06, + "loss": 1.2939, + "step": 7265 + }, + { + "epoch": 0.76, + "learning_rate": 3.2577149591106017e-06, + "loss": 1.2568, + "step": 7266 + }, + { + "epoch": 0.76, + "learning_rate": 3.2550122326756905e-06, + "loss": 1.3494, + "step": 7267 + }, + { + "epoch": 0.76, + "learning_rate": 3.252310409895837e-06, + "loss": 1.3001, + "step": 7268 + }, + { + "epoch": 0.76, + "learning_rate": 3.2496094911330087e-06, + "loss": 1.4039, + "step": 7269 + }, + { + "epoch": 0.76, + "learning_rate": 3.246909476749063e-06, + "loss": 1.2904, + "step": 7270 + }, + { + "epoch": 0.76, + "learning_rate": 3.2442103671057358e-06, + "loss": 1.2864, + "step": 7271 + }, + { + "epoch": 0.76, + "learning_rate": 3.241512162564632e-06, + "loss": 1.3195, + "step": 7272 + }, + { + "epoch": 0.76, + "learning_rate": 3.2388148634872473e-06, + "loss": 1.2776, + "step": 7273 + }, + { + "epoch": 0.76, + "learning_rate": 3.2361184702349446e-06, + "loss": 1.3391, + "step": 7274 + }, + { + "epoch": 0.76, + "learning_rate": 3.2334229831689745e-06, + "loss": 1.6897, + "step": 7275 + }, + { + "epoch": 0.76, + "learning_rate": 3.2307284026504673e-06, + "loss": 1.4191, + "step": 7276 + }, + { + "epoch": 0.76, + "learning_rate": 3.228034729040419e-06, + "loss": 1.2671, + "step": 7277 + }, + { + "epoch": 0.76, + "learning_rate": 3.2253419626997172e-06, + "loss": 1.3085, + "step": 7278 + }, + { + "epoch": 0.76, + "learning_rate": 3.2226501039891266e-06, + "loss": 1.4378, + "step": 7279 + }, + { + "epoch": 0.76, + "learning_rate": 3.2199591532692807e-06, + "loss": 1.3044, + "step": 7280 + }, + { + "epoch": 0.76, + "learning_rate": 3.2172691109007036e-06, + "loss": 1.2709, + "step": 7281 + }, + { + "epoch": 0.76, + "learning_rate": 3.214579977243787e-06, + "loss": 1.2394, + "step": 7282 + }, + { + "epoch": 0.76, + "learning_rate": 3.2118917526588055e-06, + "loss": 1.2945, + "step": 7283 + }, + { + "epoch": 0.76, + "learning_rate": 3.2092044375059197e-06, + "loss": 1.4074, + "step": 7284 + }, + { + "epoch": 0.76, + "learning_rate": 3.2065180321451504e-06, + "loss": 1.3769, + "step": 7285 + }, + { + "epoch": 0.76, + "learning_rate": 3.203832536936413e-06, + "loss": 1.2479, + "step": 7286 + }, + { + "epoch": 0.76, + "learning_rate": 3.2011479522394973e-06, + "loss": 1.2623, + "step": 7287 + }, + { + "epoch": 0.76, + "learning_rate": 3.1984642784140616e-06, + "loss": 1.3044, + "step": 7288 + }, + { + "epoch": 0.76, + "learning_rate": 3.1957815158196525e-06, + "loss": 1.321, + "step": 7289 + }, + { + "epoch": 0.76, + "learning_rate": 3.1930996648156953e-06, + "loss": 1.3307, + "step": 7290 + }, + { + "epoch": 0.76, + "learning_rate": 3.1904187257614814e-06, + "loss": 1.3135, + "step": 7291 + }, + { + "epoch": 0.76, + "learning_rate": 3.187738699016195e-06, + "loss": 1.2821, + "step": 7292 + }, + { + "epoch": 0.76, + "learning_rate": 3.1850595849388853e-06, + "loss": 1.3069, + "step": 7293 + }, + { + "epoch": 0.76, + "learning_rate": 3.1823813838884865e-06, + "loss": 1.2952, + "step": 7294 + }, + { + "epoch": 0.76, + "learning_rate": 3.179704096223812e-06, + "loss": 1.3313, + "step": 7295 + }, + { + "epoch": 0.77, + "learning_rate": 3.177027722303544e-06, + "loss": 1.3454, + "step": 7296 + }, + { + "epoch": 0.77, + "learning_rate": 3.1743522624862497e-06, + "loss": 1.2904, + "step": 7297 + }, + { + "epoch": 0.77, + "learning_rate": 3.1716777171303783e-06, + "loss": 1.3213, + "step": 7298 + }, + { + "epoch": 0.77, + "learning_rate": 3.1690040865942396e-06, + "loss": 1.3336, + "step": 7299 + }, + { + "epoch": 0.77, + "learning_rate": 3.1663313712360398e-06, + "loss": 1.3399, + "step": 7300 + }, + { + "epoch": 0.77, + "learning_rate": 3.1636595714138483e-06, + "loss": 1.2871, + "step": 7301 + }, + { + "epoch": 0.77, + "learning_rate": 3.16098868748562e-06, + "loss": 1.312, + "step": 7302 + }, + { + "epoch": 0.77, + "learning_rate": 3.158318719809188e-06, + "loss": 1.3325, + "step": 7303 + }, + { + "epoch": 0.77, + "learning_rate": 3.1556496687422534e-06, + "loss": 1.309, + "step": 7304 + }, + { + "epoch": 0.77, + "learning_rate": 3.152981534642403e-06, + "loss": 1.3186, + "step": 7305 + }, + { + "epoch": 0.77, + "learning_rate": 3.1503143178671016e-06, + "loss": 1.3235, + "step": 7306 + }, + { + "epoch": 0.77, + "learning_rate": 3.1476480187736812e-06, + "loss": 1.3557, + "step": 7307 + }, + { + "epoch": 0.77, + "learning_rate": 3.1449826377193613e-06, + "loss": 1.3206, + "step": 7308 + }, + { + "epoch": 0.77, + "learning_rate": 3.1423181750612375e-06, + "loss": 1.2901, + "step": 7309 + }, + { + "epoch": 0.77, + "learning_rate": 3.1396546311562713e-06, + "loss": 1.3232, + "step": 7310 + }, + { + "epoch": 0.77, + "learning_rate": 3.136992006361318e-06, + "loss": 1.3065, + "step": 7311 + }, + { + "epoch": 0.77, + "learning_rate": 3.1343303010330926e-06, + "loss": 1.273, + "step": 7312 + }, + { + "epoch": 0.77, + "learning_rate": 3.1316695155281997e-06, + "loss": 1.2773, + "step": 7313 + }, + { + "epoch": 0.77, + "learning_rate": 3.12900965020312e-06, + "loss": 1.2959, + "step": 7314 + }, + { + "epoch": 0.77, + "learning_rate": 3.1263507054141975e-06, + "loss": 1.2685, + "step": 7315 + }, + { + "epoch": 0.77, + "learning_rate": 3.1236926815176683e-06, + "loss": 1.3908, + "step": 7316 + }, + { + "epoch": 0.77, + "learning_rate": 3.121035578869643e-06, + "loss": 1.3022, + "step": 7317 + }, + { + "epoch": 0.77, + "learning_rate": 3.1183793978260966e-06, + "loss": 1.3144, + "step": 7318 + }, + { + "epoch": 0.77, + "learning_rate": 3.1157241387428972e-06, + "loss": 1.3142, + "step": 7319 + }, + { + "epoch": 0.77, + "learning_rate": 3.1130698019757743e-06, + "loss": 1.3277, + "step": 7320 + }, + { + "epoch": 0.77, + "learning_rate": 3.110416387880344e-06, + "loss": 1.2973, + "step": 7321 + }, + { + "epoch": 0.77, + "learning_rate": 3.1077638968120984e-06, + "loss": 1.2862, + "step": 7322 + }, + { + "epoch": 0.77, + "learning_rate": 3.1051123291263975e-06, + "loss": 1.5172, + "step": 7323 + }, + { + "epoch": 0.77, + "learning_rate": 3.102461685178486e-06, + "loss": 1.3757, + "step": 7324 + }, + { + "epoch": 0.77, + "learning_rate": 3.099811965323485e-06, + "loss": 1.3082, + "step": 7325 + }, + { + "epoch": 0.77, + "learning_rate": 3.097163169916383e-06, + "loss": 1.3674, + "step": 7326 + }, + { + "epoch": 0.77, + "learning_rate": 3.0945152993120574e-06, + "loss": 1.3168, + "step": 7327 + }, + { + "epoch": 0.77, + "learning_rate": 3.0918683538652474e-06, + "loss": 1.3122, + "step": 7328 + }, + { + "epoch": 0.77, + "learning_rate": 3.089222333930579e-06, + "loss": 1.3437, + "step": 7329 + }, + { + "epoch": 0.77, + "learning_rate": 3.0865772398625548e-06, + "loss": 1.371, + "step": 7330 + }, + { + "epoch": 0.77, + "learning_rate": 3.0839330720155426e-06, + "loss": 1.327, + "step": 7331 + }, + { + "epoch": 0.77, + "learning_rate": 3.0812898307437955e-06, + "loss": 1.3369, + "step": 7332 + }, + { + "epoch": 0.77, + "learning_rate": 3.078647516401444e-06, + "loss": 1.2148, + "step": 7333 + }, + { + "epoch": 0.77, + "learning_rate": 3.0760061293424846e-06, + "loss": 1.3074, + "step": 7334 + }, + { + "epoch": 0.77, + "learning_rate": 3.073365669920797e-06, + "loss": 1.3218, + "step": 7335 + }, + { + "epoch": 0.77, + "learning_rate": 3.070726138490139e-06, + "loss": 1.2974, + "step": 7336 + }, + { + "epoch": 0.77, + "learning_rate": 3.0680875354041327e-06, + "loss": 1.3037, + "step": 7337 + }, + { + "epoch": 0.77, + "learning_rate": 3.065449861016291e-06, + "loss": 1.5706, + "step": 7338 + }, + { + "epoch": 0.77, + "learning_rate": 3.0628131156799857e-06, + "loss": 1.3346, + "step": 7339 + }, + { + "epoch": 0.77, + "learning_rate": 3.0601772997484793e-06, + "loss": 1.6488, + "step": 7340 + }, + { + "epoch": 0.77, + "learning_rate": 3.0575424135749045e-06, + "loss": 1.2929, + "step": 7341 + }, + { + "epoch": 0.77, + "learning_rate": 3.0549084575122625e-06, + "loss": 1.3137, + "step": 7342 + }, + { + "epoch": 0.77, + "learning_rate": 3.0522754319134373e-06, + "loss": 1.3218, + "step": 7343 + }, + { + "epoch": 0.77, + "learning_rate": 3.0496433371311927e-06, + "loss": 1.2805, + "step": 7344 + }, + { + "epoch": 0.77, + "learning_rate": 3.0470121735181544e-06, + "loss": 1.2218, + "step": 7345 + }, + { + "epoch": 0.77, + "learning_rate": 3.0443819414268373e-06, + "loss": 1.381, + "step": 7346 + }, + { + "epoch": 0.77, + "learning_rate": 3.0417526412096164e-06, + "loss": 1.3571, + "step": 7347 + }, + { + "epoch": 0.77, + "learning_rate": 3.0391242732187565e-06, + "loss": 1.3295, + "step": 7348 + }, + { + "epoch": 0.77, + "learning_rate": 3.036496837806393e-06, + "loss": 1.3795, + "step": 7349 + }, + { + "epoch": 0.77, + "learning_rate": 3.033870335324528e-06, + "loss": 1.282, + "step": 7350 + }, + { + "epoch": 0.77, + "learning_rate": 3.03124476612505e-06, + "loss": 1.3428, + "step": 7351 + }, + { + "epoch": 0.77, + "learning_rate": 3.0286201305597194e-06, + "loss": 1.3321, + "step": 7352 + }, + { + "epoch": 0.77, + "learning_rate": 3.0259964289801646e-06, + "loss": 1.4135, + "step": 7353 + }, + { + "epoch": 0.77, + "learning_rate": 3.023373661737897e-06, + "loss": 1.3032, + "step": 7354 + }, + { + "epoch": 0.77, + "learning_rate": 3.0207518291843042e-06, + "loss": 1.2676, + "step": 7355 + }, + { + "epoch": 0.77, + "learning_rate": 3.0181309316706362e-06, + "loss": 1.2902, + "step": 7356 + }, + { + "epoch": 0.77, + "learning_rate": 3.0155109695480333e-06, + "loss": 1.3364, + "step": 7357 + }, + { + "epoch": 0.77, + "learning_rate": 3.0128919431674975e-06, + "loss": 1.3733, + "step": 7358 + }, + { + "epoch": 0.77, + "learning_rate": 3.0102738528799125e-06, + "loss": 1.3114, + "step": 7359 + }, + { + "epoch": 0.77, + "learning_rate": 3.007656699036039e-06, + "loss": 1.3176, + "step": 7360 + }, + { + "epoch": 0.77, + "learning_rate": 3.005040481986503e-06, + "loss": 1.301, + "step": 7361 + }, + { + "epoch": 0.77, + "learning_rate": 3.0024252020818124e-06, + "loss": 1.3281, + "step": 7362 + }, + { + "epoch": 0.77, + "learning_rate": 2.9998108596723508e-06, + "loss": 1.1587, + "step": 7363 + }, + { + "epoch": 0.77, + "eval_loss": 1.3964349031448364, + "eval_runtime": 77.4566, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 7363 + }, + { + "epoch": 0.77, + "learning_rate": 2.9971974551083673e-06, + "loss": 1.3628, + "step": 7364 + }, + { + "epoch": 0.77, + "learning_rate": 2.9945849887399958e-06, + "loss": 1.4178, + "step": 7365 + }, + { + "epoch": 0.77, + "learning_rate": 2.9919734609172356e-06, + "loss": 1.3428, + "step": 7366 + }, + { + "epoch": 0.77, + "learning_rate": 2.989362871989965e-06, + "loss": 1.2675, + "step": 7367 + }, + { + "epoch": 0.77, + "learning_rate": 2.986753222307941e-06, + "loss": 1.3353, + "step": 7368 + }, + { + "epoch": 0.77, + "learning_rate": 2.9841445122207826e-06, + "loss": 1.2842, + "step": 7369 + }, + { + "epoch": 0.77, + "learning_rate": 2.981536742077993e-06, + "loss": 1.2237, + "step": 7370 + }, + { + "epoch": 0.77, + "learning_rate": 2.9789299122289493e-06, + "loss": 1.2554, + "step": 7371 + }, + { + "epoch": 0.77, + "learning_rate": 2.976324023022893e-06, + "loss": 1.3277, + "step": 7372 + }, + { + "epoch": 0.77, + "learning_rate": 2.973719074808954e-06, + "loss": 1.3258, + "step": 7373 + }, + { + "epoch": 0.77, + "learning_rate": 2.971115067936122e-06, + "loss": 1.2757, + "step": 7374 + }, + { + "epoch": 0.77, + "learning_rate": 2.9685120027532687e-06, + "loss": 1.3267, + "step": 7375 + }, + { + "epoch": 0.77, + "learning_rate": 2.9659098796091423e-06, + "loss": 1.3451, + "step": 7376 + }, + { + "epoch": 0.77, + "learning_rate": 2.9633086988523507e-06, + "loss": 1.2742, + "step": 7377 + }, + { + "epoch": 0.77, + "learning_rate": 2.9607084608313972e-06, + "loss": 1.3589, + "step": 7378 + }, + { + "epoch": 0.77, + "learning_rate": 2.9581091658946415e-06, + "loss": 1.2839, + "step": 7379 + }, + { + "epoch": 0.77, + "learning_rate": 2.9555108143903187e-06, + "loss": 1.2883, + "step": 7380 + }, + { + "epoch": 0.77, + "learning_rate": 2.9529134066665453e-06, + "loss": 1.2781, + "step": 7381 + }, + { + "epoch": 0.77, + "learning_rate": 2.9503169430713084e-06, + "loss": 1.3638, + "step": 7382 + }, + { + "epoch": 0.77, + "learning_rate": 2.947721423952463e-06, + "loss": 1.3284, + "step": 7383 + }, + { + "epoch": 0.77, + "learning_rate": 2.945126849657748e-06, + "loss": 1.4043, + "step": 7384 + }, + { + "epoch": 0.77, + "learning_rate": 2.9425332205347624e-06, + "loss": 1.3173, + "step": 7385 + }, + { + "epoch": 0.77, + "learning_rate": 2.9399405369309884e-06, + "loss": 1.2099, + "step": 7386 + }, + { + "epoch": 0.77, + "learning_rate": 2.9373487991937845e-06, + "loss": 1.3062, + "step": 7387 + }, + { + "epoch": 0.77, + "learning_rate": 2.9347580076703695e-06, + "loss": 1.3075, + "step": 7388 + }, + { + "epoch": 0.77, + "learning_rate": 2.932168162707846e-06, + "loss": 1.3129, + "step": 7389 + }, + { + "epoch": 0.77, + "learning_rate": 2.9295792646531882e-06, + "loss": 1.4852, + "step": 7390 + }, + { + "epoch": 0.78, + "learning_rate": 2.926991313853239e-06, + "loss": 1.303, + "step": 7391 + }, + { + "epoch": 0.78, + "learning_rate": 2.9244043106547214e-06, + "loss": 1.2761, + "step": 7392 + }, + { + "epoch": 0.78, + "learning_rate": 2.9218182554042206e-06, + "loss": 1.2693, + "step": 7393 + }, + { + "epoch": 0.78, + "learning_rate": 2.9192331484482074e-06, + "loss": 1.2966, + "step": 7394 + }, + { + "epoch": 0.78, + "learning_rate": 2.9166489901330195e-06, + "loss": 1.3091, + "step": 7395 + }, + { + "epoch": 0.78, + "learning_rate": 2.91406578080486e-06, + "loss": 1.373, + "step": 7396 + }, + { + "epoch": 0.78, + "learning_rate": 2.9114835208098257e-06, + "loss": 1.2369, + "step": 7397 + }, + { + "epoch": 0.78, + "learning_rate": 2.908902210493866e-06, + "loss": 1.6399, + "step": 7398 + }, + { + "epoch": 0.78, + "learning_rate": 2.906321850202806e-06, + "loss": 1.3121, + "step": 7399 + }, + { + "epoch": 0.78, + "learning_rate": 2.903742440282352e-06, + "loss": 1.3401, + "step": 7400 + }, + { + "epoch": 0.78, + "learning_rate": 2.9011639810780833e-06, + "loss": 1.2974, + "step": 7401 + }, + { + "epoch": 0.78, + "learning_rate": 2.8985864729354383e-06, + "loss": 1.2825, + "step": 7402 + }, + { + "epoch": 0.78, + "learning_rate": 2.8960099161997434e-06, + "loss": 1.4901, + "step": 7403 + }, + { + "epoch": 0.78, + "learning_rate": 2.8934343112161867e-06, + "loss": 1.3203, + "step": 7404 + }, + { + "epoch": 0.78, + "learning_rate": 2.8908596583298343e-06, + "loss": 1.2859, + "step": 7405 + }, + { + "epoch": 0.78, + "learning_rate": 2.888285957885628e-06, + "loss": 1.334, + "step": 7406 + }, + { + "epoch": 0.78, + "learning_rate": 2.8857132102283703e-06, + "loss": 1.3358, + "step": 7407 + }, + { + "epoch": 0.78, + "learning_rate": 2.883141415702747e-06, + "loss": 1.2927, + "step": 7408 + }, + { + "epoch": 0.78, + "learning_rate": 2.8805705746533154e-06, + "loss": 1.3846, + "step": 7409 + }, + { + "epoch": 0.78, + "learning_rate": 2.8780006874244947e-06, + "loss": 1.2857, + "step": 7410 + }, + { + "epoch": 0.78, + "learning_rate": 2.8754317543605923e-06, + "loss": 1.3791, + "step": 7411 + }, + { + "epoch": 0.78, + "learning_rate": 2.872863775805772e-06, + "loss": 1.3286, + "step": 7412 + }, + { + "epoch": 0.78, + "learning_rate": 2.870296752104079e-06, + "loss": 1.244, + "step": 7413 + }, + { + "epoch": 0.78, + "learning_rate": 2.8677306835994335e-06, + "loss": 1.3673, + "step": 7414 + }, + { + "epoch": 0.78, + "learning_rate": 2.865165570635615e-06, + "loss": 1.3123, + "step": 7415 + }, + { + "epoch": 0.78, + "learning_rate": 2.862601413556286e-06, + "loss": 1.2867, + "step": 7416 + }, + { + "epoch": 0.78, + "learning_rate": 2.860038212704982e-06, + "loss": 1.3254, + "step": 7417 + }, + { + "epoch": 0.78, + "learning_rate": 2.8574759684250985e-06, + "loss": 1.2298, + "step": 7418 + }, + { + "epoch": 0.78, + "learning_rate": 2.854914681059914e-06, + "loss": 1.3054, + "step": 7419 + }, + { + "epoch": 0.78, + "learning_rate": 2.8523543509525785e-06, + "loss": 1.2984, + "step": 7420 + }, + { + "epoch": 0.78, + "learning_rate": 2.8497949784461043e-06, + "loss": 1.2848, + "step": 7421 + }, + { + "epoch": 0.78, + "learning_rate": 2.847236563883388e-06, + "loss": 1.4184, + "step": 7422 + }, + { + "epoch": 0.78, + "learning_rate": 2.84467910760718e-06, + "loss": 1.3967, + "step": 7423 + }, + { + "epoch": 0.78, + "learning_rate": 2.8421226099601284e-06, + "loss": 1.2847, + "step": 7424 + }, + { + "epoch": 0.78, + "learning_rate": 2.8395670712847322e-06, + "loss": 1.3681, + "step": 7425 + }, + { + "epoch": 0.78, + "learning_rate": 2.837012491923363e-06, + "loss": 1.3114, + "step": 7426 + }, + { + "epoch": 0.78, + "learning_rate": 2.834458872218274e-06, + "loss": 1.3264, + "step": 7427 + }, + { + "epoch": 0.78, + "learning_rate": 2.831906212511586e-06, + "loss": 1.3019, + "step": 7428 + }, + { + "epoch": 0.78, + "learning_rate": 2.829354513145284e-06, + "loss": 1.2619, + "step": 7429 + }, + { + "epoch": 0.78, + "learning_rate": 2.8268037744612362e-06, + "loss": 1.2825, + "step": 7430 + }, + { + "epoch": 0.78, + "learning_rate": 2.824253996801172e-06, + "loss": 1.2942, + "step": 7431 + }, + { + "epoch": 0.78, + "learning_rate": 2.8217051805066953e-06, + "loss": 1.3907, + "step": 7432 + }, + { + "epoch": 0.78, + "learning_rate": 2.8191573259192884e-06, + "loss": 1.2871, + "step": 7433 + }, + { + "epoch": 0.78, + "learning_rate": 2.81661043338029e-06, + "loss": 1.3924, + "step": 7434 + }, + { + "epoch": 0.78, + "learning_rate": 2.814064503230923e-06, + "loss": 1.3649, + "step": 7435 + }, + { + "epoch": 0.78, + "learning_rate": 2.8115195358122795e-06, + "loss": 1.3475, + "step": 7436 + }, + { + "epoch": 0.78, + "learning_rate": 2.808975531465312e-06, + "loss": 1.3736, + "step": 7437 + }, + { + "epoch": 0.78, + "learning_rate": 2.806432490530859e-06, + "loss": 1.2908, + "step": 7438 + }, + { + "epoch": 0.78, + "learning_rate": 2.803890413349618e-06, + "loss": 1.3991, + "step": 7439 + }, + { + "epoch": 0.78, + "learning_rate": 2.8013493002621617e-06, + "loss": 1.2928, + "step": 7440 + }, + { + "epoch": 0.78, + "learning_rate": 2.79880915160894e-06, + "loss": 1.3408, + "step": 7441 + }, + { + "epoch": 0.78, + "learning_rate": 2.7962699677302574e-06, + "loss": 1.3045, + "step": 7442 + }, + { + "epoch": 0.78, + "learning_rate": 2.793731748966311e-06, + "loss": 1.3179, + "step": 7443 + }, + { + "epoch": 0.78, + "learning_rate": 2.791194495657151e-06, + "loss": 1.2709, + "step": 7444 + }, + { + "epoch": 0.78, + "learning_rate": 2.7886582081427014e-06, + "loss": 1.3635, + "step": 7445 + }, + { + "epoch": 0.78, + "learning_rate": 2.786122886762762e-06, + "loss": 1.323, + "step": 7446 + }, + { + "epoch": 0.78, + "learning_rate": 2.7835885318570054e-06, + "loss": 1.2629, + "step": 7447 + }, + { + "epoch": 0.78, + "learning_rate": 2.7810551437649613e-06, + "loss": 1.4308, + "step": 7448 + }, + { + "epoch": 0.78, + "learning_rate": 2.778522722826048e-06, + "loss": 1.3546, + "step": 7449 + }, + { + "epoch": 0.78, + "learning_rate": 2.775991269379532e-06, + "loss": 1.4486, + "step": 7450 + }, + { + "epoch": 0.78, + "learning_rate": 2.773460783764579e-06, + "loss": 1.2845, + "step": 7451 + }, + { + "epoch": 0.78, + "learning_rate": 2.7709312663201993e-06, + "loss": 1.2393, + "step": 7452 + }, + { + "epoch": 0.78, + "learning_rate": 2.7684027173852836e-06, + "loss": 1.2939, + "step": 7453 + }, + { + "epoch": 0.78, + "learning_rate": 2.7658751372985926e-06, + "loss": 1.5802, + "step": 7454 + }, + { + "epoch": 0.78, + "learning_rate": 2.7633485263987627e-06, + "loss": 1.258, + "step": 7455 + }, + { + "epoch": 0.78, + "learning_rate": 2.760822885024286e-06, + "loss": 1.3223, + "step": 7456 + }, + { + "epoch": 0.78, + "learning_rate": 2.7582982135135418e-06, + "loss": 1.277, + "step": 7457 + }, + { + "epoch": 0.78, + "learning_rate": 2.755774512204764e-06, + "loss": 1.3047, + "step": 7458 + }, + { + "epoch": 0.78, + "learning_rate": 2.753251781436068e-06, + "loss": 1.3021, + "step": 7459 + }, + { + "epoch": 0.78, + "learning_rate": 2.750730021545437e-06, + "loss": 1.3321, + "step": 7460 + }, + { + "epoch": 0.78, + "learning_rate": 2.7482092328707154e-06, + "loss": 1.2453, + "step": 7461 + }, + { + "epoch": 0.78, + "learning_rate": 2.7456894157496293e-06, + "loss": 1.2628, + "step": 7462 + }, + { + "epoch": 0.78, + "learning_rate": 2.74317057051977e-06, + "loss": 1.4221, + "step": 7463 + }, + { + "epoch": 0.78, + "learning_rate": 2.740652697518593e-06, + "loss": 1.3034, + "step": 7464 + }, + { + "epoch": 0.78, + "learning_rate": 2.738135797083432e-06, + "loss": 1.2944, + "step": 7465 + }, + { + "epoch": 0.78, + "learning_rate": 2.7356198695514893e-06, + "loss": 1.3434, + "step": 7466 + }, + { + "epoch": 0.78, + "learning_rate": 2.733104915259829e-06, + "loss": 1.3127, + "step": 7467 + }, + { + "epoch": 0.78, + "learning_rate": 2.730590934545396e-06, + "loss": 1.2425, + "step": 7468 + }, + { + "epoch": 0.78, + "learning_rate": 2.7280779277449907e-06, + "loss": 1.4366, + "step": 7469 + }, + { + "epoch": 0.78, + "learning_rate": 2.7255658951953036e-06, + "loss": 1.3024, + "step": 7470 + }, + { + "epoch": 0.78, + "learning_rate": 2.7230548372328745e-06, + "loss": 1.2768, + "step": 7471 + }, + { + "epoch": 0.78, + "learning_rate": 2.720544754194121e-06, + "loss": 1.2453, + "step": 7472 + }, + { + "epoch": 0.78, + "learning_rate": 2.7180356464153303e-06, + "loss": 1.2796, + "step": 7473 + }, + { + "epoch": 0.78, + "learning_rate": 2.715527514232661e-06, + "loss": 1.3181, + "step": 7474 + }, + { + "epoch": 0.78, + "learning_rate": 2.7130203579821344e-06, + "loss": 1.4013, + "step": 7475 + }, + { + "epoch": 0.78, + "learning_rate": 2.710514177999649e-06, + "loss": 1.3365, + "step": 7476 + }, + { + "epoch": 0.78, + "learning_rate": 2.7080089746209614e-06, + "loss": 1.31, + "step": 7477 + }, + { + "epoch": 0.78, + "learning_rate": 2.7055047481817153e-06, + "loss": 1.258, + "step": 7478 + }, + { + "epoch": 0.78, + "learning_rate": 2.7030014990174068e-06, + "loss": 1.2199, + "step": 7479 + }, + { + "epoch": 0.78, + "learning_rate": 2.7004992274634046e-06, + "loss": 1.3007, + "step": 7480 + }, + { + "epoch": 0.78, + "learning_rate": 2.69799793385495e-06, + "loss": 1.2772, + "step": 7481 + }, + { + "epoch": 0.78, + "learning_rate": 2.6954976185271576e-06, + "loss": 1.4021, + "step": 7482 + }, + { + "epoch": 0.78, + "learning_rate": 2.692998281814998e-06, + "loss": 1.3183, + "step": 7483 + }, + { + "epoch": 0.78, + "learning_rate": 2.6904999240533246e-06, + "loss": 1.3412, + "step": 7484 + }, + { + "epoch": 0.78, + "learning_rate": 2.6880025455768465e-06, + "loss": 1.2552, + "step": 7485 + }, + { + "epoch": 0.79, + "learning_rate": 2.6855061467201517e-06, + "loss": 1.2525, + "step": 7486 + }, + { + "epoch": 0.79, + "learning_rate": 2.683010727817695e-06, + "loss": 1.269, + "step": 7487 + }, + { + "epoch": 0.79, + "learning_rate": 2.680516289203793e-06, + "loss": 1.5189, + "step": 7488 + }, + { + "epoch": 0.79, + "learning_rate": 2.6780228312126454e-06, + "loss": 1.2999, + "step": 7489 + }, + { + "epoch": 0.79, + "learning_rate": 2.675530354178306e-06, + "loss": 1.3322, + "step": 7490 + }, + { + "epoch": 0.79, + "learning_rate": 2.6730388584347e-06, + "loss": 1.3918, + "step": 7491 + }, + { + "epoch": 0.79, + "learning_rate": 2.670548344315628e-06, + "loss": 1.4438, + "step": 7492 + }, + { + "epoch": 0.79, + "learning_rate": 2.6680588121547546e-06, + "loss": 1.3393, + "step": 7493 + }, + { + "epoch": 0.79, + "learning_rate": 2.6655702622856105e-06, + "loss": 1.301, + "step": 7494 + }, + { + "epoch": 0.79, + "learning_rate": 2.6630826950416024e-06, + "loss": 1.2463, + "step": 7495 + }, + { + "epoch": 0.79, + "learning_rate": 2.660596110755991e-06, + "loss": 1.2641, + "step": 7496 + }, + { + "epoch": 0.79, + "learning_rate": 2.6581105097619264e-06, + "loss": 1.3824, + "step": 7497 + }, + { + "epoch": 0.79, + "learning_rate": 2.6556258923924104e-06, + "loss": 1.339, + "step": 7498 + }, + { + "epoch": 0.79, + "learning_rate": 2.6531422589803134e-06, + "loss": 1.2653, + "step": 7499 + }, + { + "epoch": 0.79, + "learning_rate": 2.6506596098583826e-06, + "loss": 1.2773, + "step": 7500 + }, + { + "epoch": 0.79, + "learning_rate": 2.648177945359233e-06, + "loss": 1.1829, + "step": 7501 + }, + { + "epoch": 0.79, + "learning_rate": 2.6456972658153358e-06, + "loss": 1.4014, + "step": 7502 + }, + { + "epoch": 0.79, + "learning_rate": 2.6432175715590446e-06, + "loss": 1.3648, + "step": 7503 + }, + { + "epoch": 0.79, + "learning_rate": 2.6407388629225706e-06, + "loss": 1.2731, + "step": 7504 + }, + { + "epoch": 0.79, + "learning_rate": 2.6382611402379988e-06, + "loss": 1.3076, + "step": 7505 + }, + { + "epoch": 0.79, + "learning_rate": 2.6357844038372824e-06, + "loss": 1.2054, + "step": 7506 + }, + { + "epoch": 0.79, + "learning_rate": 2.6333086540522366e-06, + "loss": 1.2579, + "step": 7507 + }, + { + "epoch": 0.79, + "learning_rate": 2.6308338912145493e-06, + "loss": 1.316, + "step": 7508 + }, + { + "epoch": 0.79, + "learning_rate": 2.6283601156557792e-06, + "loss": 1.2957, + "step": 7509 + }, + { + "epoch": 0.79, + "learning_rate": 2.625887327707343e-06, + "loss": 1.3017, + "step": 7510 + }, + { + "epoch": 0.79, + "learning_rate": 2.6234155277005334e-06, + "loss": 1.2591, + "step": 7511 + }, + { + "epoch": 0.79, + "learning_rate": 2.62094471596651e-06, + "loss": 1.3582, + "step": 7512 + }, + { + "epoch": 0.79, + "learning_rate": 2.6184748928362934e-06, + "loss": 1.3026, + "step": 7513 + }, + { + "epoch": 0.79, + "learning_rate": 2.616006058640782e-06, + "loss": 1.3222, + "step": 7514 + }, + { + "epoch": 0.79, + "learning_rate": 2.6135382137107268e-06, + "loss": 1.2785, + "step": 7515 + }, + { + "epoch": 0.79, + "learning_rate": 2.6110713583767687e-06, + "loss": 1.3227, + "step": 7516 + }, + { + "epoch": 0.79, + "learning_rate": 2.608605492969396e-06, + "loss": 1.2695, + "step": 7517 + }, + { + "epoch": 0.79, + "learning_rate": 2.6061406178189684e-06, + "loss": 1.2809, + "step": 7518 + }, + { + "epoch": 0.79, + "learning_rate": 2.6036767332557188e-06, + "loss": 1.2934, + "step": 7519 + }, + { + "epoch": 0.79, + "learning_rate": 2.6012138396097473e-06, + "loss": 1.2484, + "step": 7520 + }, + { + "epoch": 0.79, + "learning_rate": 2.5987519372110125e-06, + "loss": 1.3422, + "step": 7521 + }, + { + "epoch": 0.79, + "learning_rate": 2.596291026389354e-06, + "loss": 1.3008, + "step": 7522 + }, + { + "epoch": 0.79, + "learning_rate": 2.5938311074744582e-06, + "loss": 1.3698, + "step": 7523 + }, + { + "epoch": 0.79, + "learning_rate": 2.5913721807959045e-06, + "loss": 1.3034, + "step": 7524 + }, + { + "epoch": 0.79, + "learning_rate": 2.5889142466831208e-06, + "loss": 1.3011, + "step": 7525 + }, + { + "epoch": 0.79, + "learning_rate": 2.586457305465403e-06, + "loss": 1.3626, + "step": 7526 + }, + { + "epoch": 0.79, + "learning_rate": 2.5840013574719213e-06, + "loss": 1.3018, + "step": 7527 + }, + { + "epoch": 0.79, + "learning_rate": 2.581546403031713e-06, + "loss": 1.3316, + "step": 7528 + }, + { + "epoch": 0.79, + "learning_rate": 2.579092442473673e-06, + "loss": 1.2534, + "step": 7529 + }, + { + "epoch": 0.79, + "learning_rate": 2.5766394761265743e-06, + "loss": 1.2949, + "step": 7530 + }, + { + "epoch": 0.79, + "learning_rate": 2.574187504319046e-06, + "loss": 1.2962, + "step": 7531 + }, + { + "epoch": 0.79, + "learning_rate": 2.5717365273795914e-06, + "loss": 1.2926, + "step": 7532 + }, + { + "epoch": 0.79, + "learning_rate": 2.5692865456365824e-06, + "loss": 1.3136, + "step": 7533 + }, + { + "epoch": 0.79, + "learning_rate": 2.5668375594182447e-06, + "loss": 1.3065, + "step": 7534 + }, + { + "epoch": 0.79, + "learning_rate": 2.564389569052691e-06, + "loss": 1.3631, + "step": 7535 + }, + { + "epoch": 0.79, + "learning_rate": 2.5619425748678827e-06, + "loss": 1.3028, + "step": 7536 + }, + { + "epoch": 0.79, + "learning_rate": 2.5594965771916526e-06, + "loss": 1.3212, + "step": 7537 + }, + { + "epoch": 0.79, + "learning_rate": 2.557051576351702e-06, + "loss": 1.3154, + "step": 7538 + }, + { + "epoch": 0.79, + "learning_rate": 2.554607572675605e-06, + "loss": 1.284, + "step": 7539 + }, + { + "epoch": 0.79, + "learning_rate": 2.5521645664907856e-06, + "loss": 1.3833, + "step": 7540 + }, + { + "epoch": 0.79, + "learning_rate": 2.549722558124551e-06, + "loss": 1.3079, + "step": 7541 + }, + { + "epoch": 0.79, + "learning_rate": 2.54728154790406e-06, + "loss": 1.3104, + "step": 7542 + }, + { + "epoch": 0.79, + "learning_rate": 2.544841536156356e-06, + "loss": 1.2933, + "step": 7543 + }, + { + "epoch": 0.79, + "learning_rate": 2.5424025232083315e-06, + "loss": 1.4103, + "step": 7544 + }, + { + "epoch": 0.79, + "learning_rate": 2.53996450938675e-06, + "loss": 1.3602, + "step": 7545 + }, + { + "epoch": 0.79, + "learning_rate": 2.537527495018244e-06, + "loss": 1.381, + "step": 7546 + }, + { + "epoch": 0.79, + "learning_rate": 2.535091480429315e-06, + "loss": 1.4212, + "step": 7547 + }, + { + "epoch": 0.79, + "learning_rate": 2.5326564659463203e-06, + "loss": 1.3662, + "step": 7548 + }, + { + "epoch": 0.79, + "learning_rate": 2.5302224518954944e-06, + "loss": 1.2896, + "step": 7549 + }, + { + "epoch": 0.79, + "learning_rate": 2.5277894386029246e-06, + "loss": 1.3218, + "step": 7550 + }, + { + "epoch": 0.79, + "learning_rate": 2.5253574263945835e-06, + "loss": 1.337, + "step": 7551 + }, + { + "epoch": 0.79, + "learning_rate": 2.522926415596293e-06, + "loss": 1.3457, + "step": 7552 + }, + { + "epoch": 0.79, + "learning_rate": 2.5204964065337423e-06, + "loss": 1.3227, + "step": 7553 + }, + { + "epoch": 0.79, + "learning_rate": 2.5180673995324933e-06, + "loss": 1.2529, + "step": 7554 + }, + { + "epoch": 0.79, + "learning_rate": 2.5156393949179746e-06, + "loss": 1.3193, + "step": 7555 + }, + { + "epoch": 0.79, + "learning_rate": 2.5132123930154697e-06, + "loss": 1.2719, + "step": 7556 + }, + { + "epoch": 0.79, + "learning_rate": 2.5107863941501363e-06, + "loss": 1.3367, + "step": 7557 + }, + { + "epoch": 0.79, + "learning_rate": 2.508361398647e-06, + "loss": 1.2918, + "step": 7558 + }, + { + "epoch": 0.79, + "learning_rate": 2.505937406830942e-06, + "loss": 1.3458, + "step": 7559 + }, + { + "epoch": 0.79, + "learning_rate": 2.5035144190267215e-06, + "loss": 1.3975, + "step": 7560 + }, + { + "epoch": 0.79, + "learning_rate": 2.5010924355589463e-06, + "loss": 1.3717, + "step": 7561 + }, + { + "epoch": 0.79, + "learning_rate": 2.498671456752112e-06, + "loss": 1.316, + "step": 7562 + }, + { + "epoch": 0.79, + "eval_loss": 1.3956769704818726, + "eval_runtime": 77.5888, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 7562 + }, + { + "epoch": 0.79, + "learning_rate": 2.496251482930563e-06, + "loss": 1.2949, + "step": 7563 + }, + { + "epoch": 0.79, + "learning_rate": 2.4938325144185094e-06, + "loss": 1.6856, + "step": 7564 + }, + { + "epoch": 0.79, + "learning_rate": 2.4914145515400347e-06, + "loss": 1.4064, + "step": 7565 + }, + { + "epoch": 0.79, + "learning_rate": 2.4889975946190847e-06, + "loss": 1.3279, + "step": 7566 + }, + { + "epoch": 0.79, + "learning_rate": 2.4865816439794666e-06, + "loss": 1.2923, + "step": 7567 + }, + { + "epoch": 0.79, + "learning_rate": 2.48416669994486e-06, + "loss": 1.3237, + "step": 7568 + }, + { + "epoch": 0.79, + "learning_rate": 2.481752762838796e-06, + "loss": 1.3424, + "step": 7569 + }, + { + "epoch": 0.79, + "learning_rate": 2.479339832984693e-06, + "loss": 1.1656, + "step": 7570 + }, + { + "epoch": 0.79, + "learning_rate": 2.476927910705814e-06, + "loss": 1.1659, + "step": 7571 + }, + { + "epoch": 0.79, + "learning_rate": 2.4745169963252945e-06, + "loss": 1.3452, + "step": 7572 + }, + { + "epoch": 0.79, + "learning_rate": 2.472107090166136e-06, + "loss": 1.4011, + "step": 7573 + }, + { + "epoch": 0.79, + "learning_rate": 2.4696981925512076e-06, + "loss": 1.2312, + "step": 7574 + }, + { + "epoch": 0.79, + "learning_rate": 2.4672903038032335e-06, + "loss": 1.3257, + "step": 7575 + }, + { + "epoch": 0.79, + "learning_rate": 2.464883424244815e-06, + "loss": 1.2795, + "step": 7576 + }, + { + "epoch": 0.79, + "learning_rate": 2.4624775541984025e-06, + "loss": 1.3514, + "step": 7577 + }, + { + "epoch": 0.79, + "learning_rate": 2.4600726939863338e-06, + "loss": 1.3736, + "step": 7578 + }, + { + "epoch": 0.79, + "learning_rate": 2.4576688439307926e-06, + "loss": 1.3361, + "step": 7579 + }, + { + "epoch": 0.79, + "learning_rate": 2.4552660043538255e-06, + "loss": 1.3047, + "step": 7580 + }, + { + "epoch": 0.79, + "learning_rate": 2.452864175577364e-06, + "loss": 1.2987, + "step": 7581 + }, + { + "epoch": 0.8, + "learning_rate": 2.4504633579231863e-06, + "loss": 1.3218, + "step": 7582 + }, + { + "epoch": 0.8, + "learning_rate": 2.448063551712937e-06, + "loss": 1.3159, + "step": 7583 + }, + { + "epoch": 0.8, + "learning_rate": 2.44566475726813e-06, + "loss": 1.3032, + "step": 7584 + }, + { + "epoch": 0.8, + "learning_rate": 2.443266974910147e-06, + "loss": 1.2298, + "step": 7585 + }, + { + "epoch": 0.8, + "learning_rate": 2.4408702049602217e-06, + "loss": 1.288, + "step": 7586 + }, + { + "epoch": 0.8, + "learning_rate": 2.4384744477394663e-06, + "loss": 1.2733, + "step": 7587 + }, + { + "epoch": 0.8, + "learning_rate": 2.4360797035688424e-06, + "loss": 1.3576, + "step": 7588 + }, + { + "epoch": 0.8, + "learning_rate": 2.4336859727691953e-06, + "loss": 1.3029, + "step": 7589 + }, + { + "epoch": 0.8, + "learning_rate": 2.4312932556612178e-06, + "loss": 1.4056, + "step": 7590 + }, + { + "epoch": 0.8, + "learning_rate": 2.4289015525654693e-06, + "loss": 1.3129, + "step": 7591 + }, + { + "epoch": 0.8, + "learning_rate": 2.426510863802379e-06, + "loss": 1.2301, + "step": 7592 + }, + { + "epoch": 0.8, + "learning_rate": 2.4241211896922422e-06, + "loss": 1.282, + "step": 7593 + }, + { + "epoch": 0.8, + "learning_rate": 2.4217325305552073e-06, + "loss": 1.3173, + "step": 7594 + }, + { + "epoch": 0.8, + "learning_rate": 2.419344886711299e-06, + "loss": 1.3387, + "step": 7595 + }, + { + "epoch": 0.8, + "learning_rate": 2.416958258480391e-06, + "loss": 1.3313, + "step": 7596 + }, + { + "epoch": 0.8, + "learning_rate": 2.4145726461822428e-06, + "loss": 1.437, + "step": 7597 + }, + { + "epoch": 0.8, + "learning_rate": 2.412188050136458e-06, + "loss": 1.288, + "step": 7598 + }, + { + "epoch": 0.8, + "learning_rate": 2.40980447066251e-06, + "loss": 1.2815, + "step": 7599 + }, + { + "epoch": 0.8, + "learning_rate": 2.407421908079738e-06, + "loss": 1.3769, + "step": 7600 + }, + { + "epoch": 0.8, + "learning_rate": 2.405040362707349e-06, + "loss": 1.2726, + "step": 7601 + }, + { + "epoch": 0.8, + "learning_rate": 2.4026598348644027e-06, + "loss": 1.3741, + "step": 7602 + }, + { + "epoch": 0.8, + "learning_rate": 2.4002803248698303e-06, + "loss": 1.3046, + "step": 7603 + }, + { + "epoch": 0.8, + "learning_rate": 2.3979018330424284e-06, + "loss": 1.2566, + "step": 7604 + }, + { + "epoch": 0.8, + "learning_rate": 2.3955243597008504e-06, + "loss": 1.3237, + "step": 7605 + }, + { + "epoch": 0.8, + "learning_rate": 2.3931479051636184e-06, + "loss": 1.2446, + "step": 7606 + }, + { + "epoch": 0.8, + "learning_rate": 2.390772469749111e-06, + "loss": 1.2495, + "step": 7607 + }, + { + "epoch": 0.8, + "learning_rate": 2.3883980537755848e-06, + "loss": 1.326, + "step": 7608 + }, + { + "epoch": 0.8, + "learning_rate": 2.386024657561146e-06, + "loss": 1.2979, + "step": 7609 + }, + { + "epoch": 0.8, + "learning_rate": 2.3836522814237652e-06, + "loss": 1.2877, + "step": 7610 + }, + { + "epoch": 0.8, + "learning_rate": 2.381280925681283e-06, + "loss": 1.3327, + "step": 7611 + }, + { + "epoch": 0.8, + "learning_rate": 2.3789105906514034e-06, + "loss": 1.2641, + "step": 7612 + }, + { + "epoch": 0.8, + "learning_rate": 2.3765412766516837e-06, + "loss": 1.2904, + "step": 7613 + }, + { + "epoch": 0.8, + "learning_rate": 2.3741729839995573e-06, + "loss": 1.3153, + "step": 7614 + }, + { + "epoch": 0.8, + "learning_rate": 2.3718057130123063e-06, + "loss": 1.3168, + "step": 7615 + }, + { + "epoch": 0.8, + "learning_rate": 2.369439464007095e-06, + "loss": 1.2751, + "step": 7616 + }, + { + "epoch": 0.8, + "learning_rate": 2.3670742373009358e-06, + "loss": 1.3033, + "step": 7617 + }, + { + "epoch": 0.8, + "learning_rate": 2.364710033210703e-06, + "loss": 1.2788, + "step": 7618 + }, + { + "epoch": 0.8, + "learning_rate": 2.362346852053143e-06, + "loss": 1.3195, + "step": 7619 + }, + { + "epoch": 0.8, + "learning_rate": 2.3599846941448655e-06, + "loss": 1.2592, + "step": 7620 + }, + { + "epoch": 0.8, + "learning_rate": 2.357623559802332e-06, + "loss": 1.2495, + "step": 7621 + }, + { + "epoch": 0.8, + "learning_rate": 2.3552634493418803e-06, + "loss": 1.3111, + "step": 7622 + }, + { + "epoch": 0.8, + "learning_rate": 2.3529043630796954e-06, + "loss": 1.2559, + "step": 7623 + }, + { + "epoch": 0.8, + "learning_rate": 2.3505463013318454e-06, + "loss": 1.2642, + "step": 7624 + }, + { + "epoch": 0.8, + "learning_rate": 2.3481892644142455e-06, + "loss": 1.3277, + "step": 7625 + }, + { + "epoch": 0.8, + "learning_rate": 2.345833252642671e-06, + "loss": 1.3161, + "step": 7626 + }, + { + "epoch": 0.8, + "learning_rate": 2.3434782663327783e-06, + "loss": 1.2901, + "step": 7627 + }, + { + "epoch": 0.8, + "learning_rate": 2.341124305800071e-06, + "loss": 1.26, + "step": 7628 + }, + { + "epoch": 0.8, + "learning_rate": 2.338771371359915e-06, + "loss": 1.2772, + "step": 7629 + }, + { + "epoch": 0.8, + "learning_rate": 2.336419463327546e-06, + "loss": 1.2841, + "step": 7630 + }, + { + "epoch": 0.8, + "learning_rate": 2.334068582018062e-06, + "loss": 1.2036, + "step": 7631 + }, + { + "epoch": 0.8, + "learning_rate": 2.331718727746417e-06, + "loss": 1.2992, + "step": 7632 + }, + { + "epoch": 0.8, + "learning_rate": 2.329369900827434e-06, + "loss": 1.3145, + "step": 7633 + }, + { + "epoch": 0.8, + "learning_rate": 2.327022101575789e-06, + "loss": 1.3954, + "step": 7634 + }, + { + "epoch": 0.8, + "learning_rate": 2.3246753303060364e-06, + "loss": 1.2916, + "step": 7635 + }, + { + "epoch": 0.8, + "learning_rate": 2.322329587332579e-06, + "loss": 1.3013, + "step": 7636 + }, + { + "epoch": 0.8, + "learning_rate": 2.319984872969683e-06, + "loss": 1.2686, + "step": 7637 + }, + { + "epoch": 0.8, + "learning_rate": 2.3176411875314806e-06, + "loss": 1.3407, + "step": 7638 + }, + { + "epoch": 0.8, + "learning_rate": 2.315298531331972e-06, + "loss": 1.5181, + "step": 7639 + }, + { + "epoch": 0.8, + "learning_rate": 2.3129569046850054e-06, + "loss": 1.5231, + "step": 7640 + }, + { + "epoch": 0.8, + "learning_rate": 2.3106163079043033e-06, + "loss": 1.4524, + "step": 7641 + }, + { + "epoch": 0.8, + "learning_rate": 2.308276741303438e-06, + "loss": 1.2935, + "step": 7642 + }, + { + "epoch": 0.8, + "learning_rate": 2.3059382051958635e-06, + "loss": 1.4096, + "step": 7643 + }, + { + "epoch": 0.8, + "learning_rate": 2.303600699894876e-06, + "loss": 1.3598, + "step": 7644 + }, + { + "epoch": 0.8, + "learning_rate": 2.3012642257136397e-06, + "loss": 1.3578, + "step": 7645 + }, + { + "epoch": 0.8, + "learning_rate": 2.2989287829651853e-06, + "loss": 1.3147, + "step": 7646 + }, + { + "epoch": 0.8, + "learning_rate": 2.296594371962403e-06, + "loss": 1.3495, + "step": 7647 + }, + { + "epoch": 0.8, + "learning_rate": 2.2942609930180393e-06, + "loss": 1.4035, + "step": 7648 + }, + { + "epoch": 0.8, + "learning_rate": 2.291928646444711e-06, + "loss": 1.2757, + "step": 7649 + }, + { + "epoch": 0.8, + "learning_rate": 2.2895973325548914e-06, + "loss": 1.2496, + "step": 7650 + }, + { + "epoch": 0.8, + "learning_rate": 2.2872670516609196e-06, + "loss": 1.3372, + "step": 7651 + }, + { + "epoch": 0.8, + "learning_rate": 2.28493780407499e-06, + "loss": 1.276, + "step": 7652 + }, + { + "epoch": 0.8, + "learning_rate": 2.2826095901091574e-06, + "loss": 1.319, + "step": 7653 + }, + { + "epoch": 0.8, + "learning_rate": 2.280282410075354e-06, + "loss": 1.3473, + "step": 7654 + }, + { + "epoch": 0.8, + "learning_rate": 2.2779562642853546e-06, + "loss": 1.2947, + "step": 7655 + }, + { + "epoch": 0.8, + "learning_rate": 2.2756311530508026e-06, + "loss": 1.3485, + "step": 7656 + }, + { + "epoch": 0.8, + "learning_rate": 2.2733070766832042e-06, + "loss": 1.3187, + "step": 7657 + }, + { + "epoch": 0.8, + "learning_rate": 2.2709840354939296e-06, + "loss": 1.3979, + "step": 7658 + }, + { + "epoch": 0.8, + "learning_rate": 2.2686620297942007e-06, + "loss": 1.269, + "step": 7659 + }, + { + "epoch": 0.8, + "learning_rate": 2.266341059895113e-06, + "loss": 1.3572, + "step": 7660 + }, + { + "epoch": 0.8, + "learning_rate": 2.264021126107607e-06, + "loss": 1.2858, + "step": 7661 + }, + { + "epoch": 0.8, + "learning_rate": 2.2617022287425073e-06, + "loss": 1.3677, + "step": 7662 + }, + { + "epoch": 0.8, + "learning_rate": 2.259384368110479e-06, + "loss": 1.3111, + "step": 7663 + }, + { + "epoch": 0.8, + "learning_rate": 2.2570675445220535e-06, + "loss": 1.2969, + "step": 7664 + }, + { + "epoch": 0.8, + "learning_rate": 2.254751758287629e-06, + "loss": 1.2901, + "step": 7665 + }, + { + "epoch": 0.8, + "learning_rate": 2.252437009717464e-06, + "loss": 1.2834, + "step": 7666 + }, + { + "epoch": 0.8, + "learning_rate": 2.2501232991216705e-06, + "loss": 1.2505, + "step": 7667 + }, + { + "epoch": 0.8, + "learning_rate": 2.2478106268102295e-06, + "loss": 1.2763, + "step": 7668 + }, + { + "epoch": 0.8, + "learning_rate": 2.2454989930929737e-06, + "loss": 1.3427, + "step": 7669 + }, + { + "epoch": 0.8, + "learning_rate": 2.2431883982796132e-06, + "loss": 1.3397, + "step": 7670 + }, + { + "epoch": 0.8, + "learning_rate": 2.240878842679702e-06, + "loss": 1.2525, + "step": 7671 + }, + { + "epoch": 0.8, + "learning_rate": 2.238570326602657e-06, + "loss": 1.2085, + "step": 7672 + }, + { + "epoch": 0.8, + "learning_rate": 2.23626285035777e-06, + "loss": 1.2196, + "step": 7673 + }, + { + "epoch": 0.8, + "learning_rate": 2.2339564142541783e-06, + "loss": 1.2602, + "step": 7674 + }, + { + "epoch": 0.8, + "learning_rate": 2.2316510186008824e-06, + "loss": 1.4144, + "step": 7675 + }, + { + "epoch": 0.8, + "learning_rate": 2.2293466637067486e-06, + "loss": 1.3239, + "step": 7676 + }, + { + "epoch": 0.81, + "learning_rate": 2.227043349880501e-06, + "loss": 1.342, + "step": 7677 + }, + { + "epoch": 0.81, + "learning_rate": 2.2247410774307276e-06, + "loss": 1.3395, + "step": 7678 + }, + { + "epoch": 0.81, + "learning_rate": 2.2224398466658712e-06, + "loss": 1.3948, + "step": 7679 + }, + { + "epoch": 0.81, + "learning_rate": 2.2201396578942325e-06, + "loss": 1.2983, + "step": 7680 + }, + { + "epoch": 0.81, + "learning_rate": 2.2178405114239877e-06, + "loss": 1.3779, + "step": 7681 + }, + { + "epoch": 0.81, + "learning_rate": 2.2155424075631583e-06, + "loss": 1.2826, + "step": 7682 + }, + { + "epoch": 0.81, + "learning_rate": 2.213245346619628e-06, + "loss": 1.3939, + "step": 7683 + }, + { + "epoch": 0.81, + "learning_rate": 2.2109493289011474e-06, + "loss": 1.298, + "step": 7684 + }, + { + "epoch": 0.81, + "learning_rate": 2.208654354715326e-06, + "loss": 1.2947, + "step": 7685 + }, + { + "epoch": 0.81, + "learning_rate": 2.2063604243696267e-06, + "loss": 1.3532, + "step": 7686 + }, + { + "epoch": 0.81, + "learning_rate": 2.204067538171382e-06, + "loss": 1.2713, + "step": 7687 + }, + { + "epoch": 0.81, + "learning_rate": 2.2017756964277713e-06, + "loss": 1.3025, + "step": 7688 + }, + { + "epoch": 0.81, + "learning_rate": 2.199484899445854e-06, + "loss": 1.2806, + "step": 7689 + }, + { + "epoch": 0.81, + "learning_rate": 2.1971951475325328e-06, + "loss": 1.3113, + "step": 7690 + }, + { + "epoch": 0.81, + "learning_rate": 2.194906440994572e-06, + "loss": 1.4729, + "step": 7691 + }, + { + "epoch": 0.81, + "learning_rate": 2.1926187801386033e-06, + "loss": 1.29, + "step": 7692 + }, + { + "epoch": 0.81, + "learning_rate": 2.1903321652711163e-06, + "loss": 1.3092, + "step": 7693 + }, + { + "epoch": 0.81, + "learning_rate": 2.188046596698454e-06, + "loss": 1.3286, + "step": 7694 + }, + { + "epoch": 0.81, + "learning_rate": 2.185762074726826e-06, + "loss": 1.3734, + "step": 7695 + }, + { + "epoch": 0.81, + "learning_rate": 2.1834785996622988e-06, + "loss": 1.3218, + "step": 7696 + }, + { + "epoch": 0.81, + "learning_rate": 2.1811961718108034e-06, + "loss": 1.3319, + "step": 7697 + }, + { + "epoch": 0.81, + "learning_rate": 2.178914791478124e-06, + "loss": 1.2732, + "step": 7698 + }, + { + "epoch": 0.81, + "learning_rate": 2.1766344589698996e-06, + "loss": 1.4451, + "step": 7699 + }, + { + "epoch": 0.81, + "learning_rate": 2.1743551745916492e-06, + "loss": 1.338, + "step": 7700 + }, + { + "epoch": 0.81, + "learning_rate": 2.172076938648732e-06, + "loss": 1.3602, + "step": 7701 + }, + { + "epoch": 0.81, + "learning_rate": 2.16979975144637e-06, + "loss": 1.2782, + "step": 7702 + }, + { + "epoch": 0.81, + "learning_rate": 2.1675236132896505e-06, + "loss": 1.2661, + "step": 7703 + }, + { + "epoch": 0.81, + "learning_rate": 2.165248524483521e-06, + "loss": 1.3031, + "step": 7704 + }, + { + "epoch": 0.81, + "learning_rate": 2.1629744853327793e-06, + "loss": 1.3754, + "step": 7705 + }, + { + "epoch": 0.81, + "learning_rate": 2.1607014961420926e-06, + "loss": 1.4255, + "step": 7706 + }, + { + "epoch": 0.81, + "learning_rate": 2.1584295572159764e-06, + "loss": 1.3955, + "step": 7707 + }, + { + "epoch": 0.81, + "learning_rate": 2.156158668858822e-06, + "loss": 1.3691, + "step": 7708 + }, + { + "epoch": 0.81, + "learning_rate": 2.153888831374865e-06, + "loss": 1.3986, + "step": 7709 + }, + { + "epoch": 0.81, + "learning_rate": 2.1516200450682036e-06, + "loss": 1.3231, + "step": 7710 + }, + { + "epoch": 0.81, + "learning_rate": 2.149352310242797e-06, + "loss": 1.2892, + "step": 7711 + }, + { + "epoch": 0.81, + "learning_rate": 2.1470856272024686e-06, + "loss": 1.289, + "step": 7712 + }, + { + "epoch": 0.81, + "learning_rate": 2.1448199962508898e-06, + "loss": 1.2804, + "step": 7713 + }, + { + "epoch": 0.81, + "learning_rate": 2.1425554176916007e-06, + "loss": 1.2599, + "step": 7714 + }, + { + "epoch": 0.81, + "learning_rate": 2.1402918918279904e-06, + "loss": 1.3082, + "step": 7715 + }, + { + "epoch": 0.81, + "learning_rate": 2.1380294189633233e-06, + "loss": 1.306, + "step": 7716 + }, + { + "epoch": 0.81, + "learning_rate": 2.1357679994007076e-06, + "loss": 1.2681, + "step": 7717 + }, + { + "epoch": 0.81, + "learning_rate": 2.1335076334431092e-06, + "loss": 1.2842, + "step": 7718 + }, + { + "epoch": 0.81, + "learning_rate": 2.13124832139337e-06, + "loss": 1.3153, + "step": 7719 + }, + { + "epoch": 0.81, + "learning_rate": 2.128990063554176e-06, + "loss": 1.3312, + "step": 7720 + }, + { + "epoch": 0.81, + "learning_rate": 2.12673286022807e-06, + "loss": 1.2851, + "step": 7721 + }, + { + "epoch": 0.81, + "learning_rate": 2.124476711717465e-06, + "loss": 1.3398, + "step": 7722 + }, + { + "epoch": 0.81, + "learning_rate": 2.1222216183246246e-06, + "loss": 1.2543, + "step": 7723 + }, + { + "epoch": 0.81, + "learning_rate": 2.1199675803516785e-06, + "loss": 1.3686, + "step": 7724 + }, + { + "epoch": 0.81, + "learning_rate": 2.117714598100604e-06, + "loss": 1.3746, + "step": 7725 + }, + { + "epoch": 0.81, + "learning_rate": 2.1154626718732407e-06, + "loss": 1.2664, + "step": 7726 + }, + { + "epoch": 0.81, + "learning_rate": 2.1132118019712976e-06, + "loss": 1.3075, + "step": 7727 + }, + { + "epoch": 0.81, + "learning_rate": 2.1109619886963284e-06, + "loss": 1.739, + "step": 7728 + }, + { + "epoch": 0.81, + "learning_rate": 2.1087132323497483e-06, + "loss": 1.335, + "step": 7729 + }, + { + "epoch": 0.81, + "learning_rate": 2.1064655332328344e-06, + "loss": 1.3371, + "step": 7730 + }, + { + "epoch": 0.81, + "learning_rate": 2.104218891646724e-06, + "loss": 1.3837, + "step": 7731 + }, + { + "epoch": 0.81, + "learning_rate": 2.1019733078924045e-06, + "loss": 1.3436, + "step": 7732 + }, + { + "epoch": 0.81, + "learning_rate": 2.0997287822707304e-06, + "loss": 1.2995, + "step": 7733 + }, + { + "epoch": 0.81, + "learning_rate": 2.0974853150824036e-06, + "loss": 1.2914, + "step": 7734 + }, + { + "epoch": 0.81, + "learning_rate": 2.095242906628001e-06, + "loss": 1.3773, + "step": 7735 + }, + { + "epoch": 0.81, + "learning_rate": 2.0930015572079434e-06, + "loss": 1.3097, + "step": 7736 + }, + { + "epoch": 0.81, + "learning_rate": 2.0907612671225108e-06, + "loss": 1.3261, + "step": 7737 + }, + { + "epoch": 0.81, + "learning_rate": 2.088522036671846e-06, + "loss": 1.2578, + "step": 7738 + }, + { + "epoch": 0.81, + "learning_rate": 2.0862838661559535e-06, + "loss": 1.2898, + "step": 7739 + }, + { + "epoch": 0.81, + "learning_rate": 2.0840467558746837e-06, + "loss": 1.341, + "step": 7740 + }, + { + "epoch": 0.81, + "learning_rate": 2.0818107061277535e-06, + "loss": 1.3332, + "step": 7741 + }, + { + "epoch": 0.81, + "learning_rate": 2.0795757172147392e-06, + "loss": 1.2808, + "step": 7742 + }, + { + "epoch": 0.81, + "learning_rate": 2.077341789435071e-06, + "loss": 1.2795, + "step": 7743 + }, + { + "epoch": 0.81, + "learning_rate": 2.075108923088038e-06, + "loss": 1.3621, + "step": 7744 + }, + { + "epoch": 0.81, + "learning_rate": 2.0728771184727802e-06, + "loss": 1.3179, + "step": 7745 + }, + { + "epoch": 0.81, + "learning_rate": 2.0706463758883134e-06, + "loss": 1.2924, + "step": 7746 + }, + { + "epoch": 0.81, + "learning_rate": 2.0684166956334926e-06, + "loss": 1.3576, + "step": 7747 + }, + { + "epoch": 0.81, + "learning_rate": 2.066188078007039e-06, + "loss": 1.2692, + "step": 7748 + }, + { + "epoch": 0.81, + "learning_rate": 2.0639605233075277e-06, + "loss": 1.2994, + "step": 7749 + }, + { + "epoch": 0.81, + "learning_rate": 2.061734031833398e-06, + "loss": 1.278, + "step": 7750 + }, + { + "epoch": 0.81, + "learning_rate": 2.059508603882943e-06, + "loss": 1.2703, + "step": 7751 + }, + { + "epoch": 0.81, + "learning_rate": 2.0572842397543115e-06, + "loss": 1.2864, + "step": 7752 + }, + { + "epoch": 0.81, + "learning_rate": 2.0550609397455037e-06, + "loss": 1.3387, + "step": 7753 + }, + { + "epoch": 0.81, + "learning_rate": 2.0528387041543974e-06, + "loss": 1.5834, + "step": 7754 + }, + { + "epoch": 0.81, + "learning_rate": 2.0506175332787093e-06, + "loss": 1.2907, + "step": 7755 + }, + { + "epoch": 0.81, + "learning_rate": 2.048397427416016e-06, + "loss": 1.3015, + "step": 7756 + }, + { + "epoch": 0.81, + "learning_rate": 2.0461783868637573e-06, + "loss": 1.2329, + "step": 7757 + }, + { + "epoch": 0.81, + "learning_rate": 2.0439604119192314e-06, + "loss": 1.3166, + "step": 7758 + }, + { + "epoch": 0.81, + "learning_rate": 2.041743502879583e-06, + "loss": 1.2476, + "step": 7759 + }, + { + "epoch": 0.81, + "learning_rate": 2.039527660041828e-06, + "loss": 1.2766, + "step": 7760 + }, + { + "epoch": 0.81, + "learning_rate": 2.0373128837028233e-06, + "loss": 1.2738, + "step": 7761 + }, + { + "epoch": 0.81, + "eval_loss": 1.3951469659805298, + "eval_runtime": 77.4687, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 7761 + }, + { + "epoch": 0.81, + "learning_rate": 2.035099174159302e-06, + "loss": 1.3806, + "step": 7762 + }, + { + "epoch": 0.81, + "learning_rate": 2.0328865317078405e-06, + "loss": 1.2625, + "step": 7763 + }, + { + "epoch": 0.81, + "learning_rate": 2.0306749566448704e-06, + "loss": 1.2709, + "step": 7764 + }, + { + "epoch": 0.81, + "learning_rate": 2.028464449266696e-06, + "loss": 1.3029, + "step": 7765 + }, + { + "epoch": 0.81, + "learning_rate": 2.0262550098694634e-06, + "loss": 1.2867, + "step": 7766 + }, + { + "epoch": 0.81, + "learning_rate": 2.0240466387491774e-06, + "loss": 1.2818, + "step": 7767 + }, + { + "epoch": 0.81, + "learning_rate": 2.0218393362017076e-06, + "loss": 1.2627, + "step": 7768 + }, + { + "epoch": 0.81, + "learning_rate": 2.019633102522773e-06, + "loss": 1.2337, + "step": 7769 + }, + { + "epoch": 0.81, + "learning_rate": 2.0174279380079577e-06, + "loss": 1.4194, + "step": 7770 + }, + { + "epoch": 0.81, + "learning_rate": 2.0152238429526928e-06, + "loss": 1.487, + "step": 7771 + }, + { + "epoch": 0.82, + "learning_rate": 2.013020817652266e-06, + "loss": 1.2802, + "step": 7772 + }, + { + "epoch": 0.82, + "learning_rate": 2.0108188624018353e-06, + "loss": 1.2602, + "step": 7773 + }, + { + "epoch": 0.82, + "learning_rate": 2.008617977496402e-06, + "loss": 1.2986, + "step": 7774 + }, + { + "epoch": 0.82, + "learning_rate": 2.0064181632308244e-06, + "loss": 1.3053, + "step": 7775 + }, + { + "epoch": 0.82, + "learning_rate": 2.0042194198998256e-06, + "loss": 1.3052, + "step": 7776 + }, + { + "epoch": 0.82, + "learning_rate": 2.00202174779798e-06, + "loss": 1.247, + "step": 7777 + }, + { + "epoch": 0.82, + "learning_rate": 1.9998251472197192e-06, + "loss": 1.2762, + "step": 7778 + }, + { + "epoch": 0.82, + "learning_rate": 1.9976296184593335e-06, + "loss": 1.3518, + "step": 7779 + }, + { + "epoch": 0.82, + "learning_rate": 1.995435161810958e-06, + "loss": 1.4015, + "step": 7780 + }, + { + "epoch": 0.82, + "learning_rate": 1.9932417775686052e-06, + "loss": 1.3363, + "step": 7781 + }, + { + "epoch": 0.82, + "learning_rate": 1.991049466026128e-06, + "loss": 1.3039, + "step": 7782 + }, + { + "epoch": 0.82, + "learning_rate": 1.988858227477234e-06, + "loss": 1.3183, + "step": 7783 + }, + { + "epoch": 0.82, + "learning_rate": 1.986668062215502e-06, + "loss": 1.2852, + "step": 7784 + }, + { + "epoch": 0.82, + "learning_rate": 1.984478970534355e-06, + "loss": 1.2791, + "step": 7785 + }, + { + "epoch": 0.82, + "learning_rate": 1.9822909527270696e-06, + "loss": 1.3869, + "step": 7786 + }, + { + "epoch": 0.82, + "learning_rate": 1.9801040090867895e-06, + "loss": 1.3475, + "step": 7787 + }, + { + "epoch": 0.82, + "learning_rate": 1.9779181399065074e-06, + "loss": 1.2977, + "step": 7788 + }, + { + "epoch": 0.82, + "learning_rate": 1.975733345479076e-06, + "loss": 1.2244, + "step": 7789 + }, + { + "epoch": 0.82, + "learning_rate": 1.9735496260971996e-06, + "loss": 1.3136, + "step": 7790 + }, + { + "epoch": 0.82, + "learning_rate": 1.9713669820534352e-06, + "loss": 1.3647, + "step": 7791 + }, + { + "epoch": 0.82, + "learning_rate": 1.969185413640212e-06, + "loss": 1.3136, + "step": 7792 + }, + { + "epoch": 0.82, + "learning_rate": 1.9670049211497977e-06, + "loss": 1.3488, + "step": 7793 + }, + { + "epoch": 0.82, + "learning_rate": 1.9648255048743205e-06, + "loss": 1.3578, + "step": 7794 + }, + { + "epoch": 0.82, + "learning_rate": 1.9626471651057677e-06, + "loss": 1.325, + "step": 7795 + }, + { + "epoch": 0.82, + "learning_rate": 1.960469902135983e-06, + "loss": 1.3408, + "step": 7796 + }, + { + "epoch": 0.82, + "learning_rate": 1.958293716256664e-06, + "loss": 1.3439, + "step": 7797 + }, + { + "epoch": 0.82, + "learning_rate": 1.9561186077593617e-06, + "loss": 1.2767, + "step": 7798 + }, + { + "epoch": 0.82, + "learning_rate": 1.9539445769354814e-06, + "loss": 1.3756, + "step": 7799 + }, + { + "epoch": 0.82, + "learning_rate": 1.9517716240762953e-06, + "loss": 1.313, + "step": 7800 + }, + { + "epoch": 0.82, + "learning_rate": 1.949599749472919e-06, + "loss": 1.3103, + "step": 7801 + }, + { + "epoch": 0.82, + "learning_rate": 1.947428953416326e-06, + "loss": 1.3255, + "step": 7802 + }, + { + "epoch": 0.82, + "learning_rate": 1.945259236197348e-06, + "loss": 1.2959, + "step": 7803 + }, + { + "epoch": 0.82, + "learning_rate": 1.943090598106673e-06, + "loss": 1.2345, + "step": 7804 + }, + { + "epoch": 0.82, + "learning_rate": 1.9409230394348457e-06, + "loss": 1.2664, + "step": 7805 + }, + { + "epoch": 0.82, + "learning_rate": 1.938756560472256e-06, + "loss": 1.5172, + "step": 7806 + }, + { + "epoch": 0.82, + "learning_rate": 1.9365911615091615e-06, + "loss": 1.2878, + "step": 7807 + }, + { + "epoch": 0.82, + "learning_rate": 1.9344268428356707e-06, + "loss": 1.3419, + "step": 7808 + }, + { + "epoch": 0.82, + "learning_rate": 1.9322636047417444e-06, + "loss": 1.3464, + "step": 7809 + }, + { + "epoch": 0.82, + "learning_rate": 1.9301014475171964e-06, + "loss": 1.2695, + "step": 7810 + }, + { + "epoch": 0.82, + "learning_rate": 1.9279403714517098e-06, + "loss": 1.3551, + "step": 7811 + }, + { + "epoch": 0.82, + "learning_rate": 1.9257803768348092e-06, + "loss": 1.4498, + "step": 7812 + }, + { + "epoch": 0.82, + "learning_rate": 1.923621463955876e-06, + "loss": 1.4617, + "step": 7813 + }, + { + "epoch": 0.82, + "learning_rate": 1.9214636331041493e-06, + "loss": 1.6204, + "step": 7814 + }, + { + "epoch": 0.82, + "learning_rate": 1.9193068845687246e-06, + "loss": 1.3202, + "step": 7815 + }, + { + "epoch": 0.82, + "learning_rate": 1.9171512186385543e-06, + "loss": 1.293, + "step": 7816 + }, + { + "epoch": 0.82, + "learning_rate": 1.9149966356024387e-06, + "loss": 1.2511, + "step": 7817 + }, + { + "epoch": 0.82, + "learning_rate": 1.9128431357490296e-06, + "loss": 1.3643, + "step": 7818 + }, + { + "epoch": 0.82, + "learning_rate": 1.9106907193668543e-06, + "loss": 1.4159, + "step": 7819 + }, + { + "epoch": 0.82, + "learning_rate": 1.908539386744274e-06, + "loss": 1.2611, + "step": 7820 + }, + { + "epoch": 0.82, + "learning_rate": 1.9063891381695098e-06, + "loss": 1.3667, + "step": 7821 + }, + { + "epoch": 0.82, + "learning_rate": 1.9042399739306427e-06, + "loss": 1.3456, + "step": 7822 + }, + { + "epoch": 0.82, + "learning_rate": 1.9020918943156053e-06, + "loss": 1.4083, + "step": 7823 + }, + { + "epoch": 0.82, + "learning_rate": 1.8999448996121883e-06, + "loss": 1.3758, + "step": 7824 + }, + { + "epoch": 0.82, + "learning_rate": 1.8977989901080295e-06, + "loss": 1.2757, + "step": 7825 + }, + { + "epoch": 0.82, + "learning_rate": 1.8956541660906214e-06, + "loss": 1.3796, + "step": 7826 + }, + { + "epoch": 0.82, + "learning_rate": 1.893510427847327e-06, + "loss": 1.238, + "step": 7827 + }, + { + "epoch": 0.82, + "learning_rate": 1.8913677756653447e-06, + "loss": 1.3018, + "step": 7828 + }, + { + "epoch": 0.82, + "learning_rate": 1.8892262098317315e-06, + "loss": 1.2712, + "step": 7829 + }, + { + "epoch": 0.82, + "learning_rate": 1.8870857306334113e-06, + "loss": 1.3805, + "step": 7830 + }, + { + "epoch": 0.82, + "learning_rate": 1.8849463383571486e-06, + "loss": 1.3664, + "step": 7831 + }, + { + "epoch": 0.82, + "learning_rate": 1.8828080332895648e-06, + "loss": 1.3709, + "step": 7832 + }, + { + "epoch": 0.82, + "learning_rate": 1.8806708157171393e-06, + "loss": 1.3401, + "step": 7833 + }, + { + "epoch": 0.82, + "learning_rate": 1.8785346859262056e-06, + "loss": 1.3143, + "step": 7834 + }, + { + "epoch": 0.82, + "learning_rate": 1.876399644202952e-06, + "loss": 1.3432, + "step": 7835 + }, + { + "epoch": 0.82, + "learning_rate": 1.8742656908334178e-06, + "loss": 1.2945, + "step": 7836 + }, + { + "epoch": 0.82, + "learning_rate": 1.872132826103491e-06, + "loss": 1.402, + "step": 7837 + }, + { + "epoch": 0.82, + "learning_rate": 1.8700010502989318e-06, + "loss": 1.3004, + "step": 7838 + }, + { + "epoch": 0.82, + "learning_rate": 1.8678703637053386e-06, + "loss": 1.2766, + "step": 7839 + }, + { + "epoch": 0.82, + "learning_rate": 1.8657407666081661e-06, + "loss": 1.3629, + "step": 7840 + }, + { + "epoch": 0.82, + "learning_rate": 1.8636122592927275e-06, + "loss": 1.2527, + "step": 7841 + }, + { + "epoch": 0.82, + "learning_rate": 1.8614848420441888e-06, + "loss": 1.2711, + "step": 7842 + }, + { + "epoch": 0.82, + "learning_rate": 1.8593585151475713e-06, + "loss": 1.3419, + "step": 7843 + }, + { + "epoch": 0.82, + "learning_rate": 1.8572332788877456e-06, + "loss": 1.2953, + "step": 7844 + }, + { + "epoch": 0.82, + "learning_rate": 1.855109133549433e-06, + "loss": 1.2415, + "step": 7845 + }, + { + "epoch": 0.82, + "learning_rate": 1.8529860794172271e-06, + "loss": 1.2367, + "step": 7846 + }, + { + "epoch": 0.82, + "learning_rate": 1.8508641167755548e-06, + "loss": 1.3584, + "step": 7847 + }, + { + "epoch": 0.82, + "learning_rate": 1.848743245908703e-06, + "loss": 1.4259, + "step": 7848 + }, + { + "epoch": 0.82, + "learning_rate": 1.8466234671008165e-06, + "loss": 1.2903, + "step": 7849 + }, + { + "epoch": 0.82, + "learning_rate": 1.8445047806358918e-06, + "loss": 1.3204, + "step": 7850 + }, + { + "epoch": 0.82, + "learning_rate": 1.8423871867977806e-06, + "loss": 1.3938, + "step": 7851 + }, + { + "epoch": 0.82, + "learning_rate": 1.840270685870179e-06, + "loss": 1.2973, + "step": 7852 + }, + { + "epoch": 0.82, + "learning_rate": 1.8381552781366497e-06, + "loss": 1.3506, + "step": 7853 + }, + { + "epoch": 0.82, + "learning_rate": 1.8360409638806031e-06, + "loss": 1.3117, + "step": 7854 + }, + { + "epoch": 0.82, + "learning_rate": 1.833927743385302e-06, + "loss": 1.3072, + "step": 7855 + }, + { + "epoch": 0.82, + "learning_rate": 1.8318156169338562e-06, + "loss": 1.2965, + "step": 7856 + }, + { + "epoch": 0.82, + "learning_rate": 1.82970458480925e-06, + "loss": 1.3161, + "step": 7857 + }, + { + "epoch": 0.82, + "learning_rate": 1.8275946472942995e-06, + "loss": 1.3056, + "step": 7858 + }, + { + "epoch": 0.82, + "learning_rate": 1.8254858046716805e-06, + "loss": 1.249, + "step": 7859 + }, + { + "epoch": 0.82, + "learning_rate": 1.8233780572239268e-06, + "loss": 1.2689, + "step": 7860 + }, + { + "epoch": 0.82, + "learning_rate": 1.8212714052334213e-06, + "loss": 1.2919, + "step": 7861 + }, + { + "epoch": 0.82, + "learning_rate": 1.819165848982405e-06, + "loss": 1.3337, + "step": 7862 + }, + { + "epoch": 0.82, + "learning_rate": 1.8170613887529643e-06, + "loss": 1.2798, + "step": 7863 + }, + { + "epoch": 0.82, + "learning_rate": 1.8149580248270393e-06, + "loss": 1.3296, + "step": 7864 + }, + { + "epoch": 0.82, + "learning_rate": 1.812855757486437e-06, + "loss": 1.4615, + "step": 7865 + }, + { + "epoch": 0.82, + "learning_rate": 1.8107545870128008e-06, + "loss": 1.2883, + "step": 7866 + }, + { + "epoch": 0.82, + "learning_rate": 1.808654513687631e-06, + "loss": 1.3722, + "step": 7867 + }, + { + "epoch": 0.83, + "learning_rate": 1.8065555377922862e-06, + "loss": 1.3648, + "step": 7868 + }, + { + "epoch": 0.83, + "learning_rate": 1.8044576596079766e-06, + "loss": 1.2698, + "step": 7869 + }, + { + "epoch": 0.83, + "learning_rate": 1.8023608794157654e-06, + "loss": 1.3078, + "step": 7870 + }, + { + "epoch": 0.83, + "learning_rate": 1.8002651974965646e-06, + "loss": 1.3037, + "step": 7871 + }, + { + "epoch": 0.83, + "learning_rate": 1.7981706141311373e-06, + "loss": 1.2971, + "step": 7872 + }, + { + "epoch": 0.83, + "learning_rate": 1.7960771296001122e-06, + "loss": 1.3334, + "step": 7873 + }, + { + "epoch": 0.83, + "learning_rate": 1.7939847441839597e-06, + "loss": 1.3301, + "step": 7874 + }, + { + "epoch": 0.83, + "learning_rate": 1.7918934581629998e-06, + "loss": 1.2966, + "step": 7875 + }, + { + "epoch": 0.83, + "learning_rate": 1.7898032718174218e-06, + "loss": 1.3152, + "step": 7876 + }, + { + "epoch": 0.83, + "learning_rate": 1.7877141854272474e-06, + "loss": 1.2867, + "step": 7877 + }, + { + "epoch": 0.83, + "learning_rate": 1.7856261992723678e-06, + "loss": 1.3059, + "step": 7878 + }, + { + "epoch": 0.83, + "learning_rate": 1.783539313632513e-06, + "loss": 1.3425, + "step": 7879 + }, + { + "epoch": 0.83, + "learning_rate": 1.7814535287872748e-06, + "loss": 1.3513, + "step": 7880 + }, + { + "epoch": 0.83, + "learning_rate": 1.7793688450160983e-06, + "loss": 1.3208, + "step": 7881 + }, + { + "epoch": 0.83, + "learning_rate": 1.777285262598274e-06, + "loss": 1.302, + "step": 7882 + }, + { + "epoch": 0.83, + "learning_rate": 1.7752027818129424e-06, + "loss": 1.2783, + "step": 7883 + }, + { + "epoch": 0.83, + "learning_rate": 1.7731214029391153e-06, + "loss": 1.3599, + "step": 7884 + }, + { + "epoch": 0.83, + "learning_rate": 1.771041126255637e-06, + "loss": 1.2158, + "step": 7885 + }, + { + "epoch": 0.83, + "learning_rate": 1.7689619520412094e-06, + "loss": 1.3221, + "step": 7886 + }, + { + "epoch": 0.83, + "learning_rate": 1.7668838805743893e-06, + "loss": 1.3635, + "step": 7887 + }, + { + "epoch": 0.83, + "learning_rate": 1.7648069121335876e-06, + "loss": 1.2742, + "step": 7888 + }, + { + "epoch": 0.83, + "learning_rate": 1.762731046997065e-06, + "loss": 1.3333, + "step": 7889 + }, + { + "epoch": 0.83, + "learning_rate": 1.760656285442932e-06, + "loss": 1.2971, + "step": 7890 + }, + { + "epoch": 0.83, + "learning_rate": 1.7585826277491491e-06, + "loss": 1.3262, + "step": 7891 + }, + { + "epoch": 0.83, + "learning_rate": 1.7565100741935436e-06, + "loss": 1.38, + "step": 7892 + }, + { + "epoch": 0.83, + "learning_rate": 1.754438625053777e-06, + "loss": 1.3814, + "step": 7893 + }, + { + "epoch": 0.83, + "learning_rate": 1.7523682806073706e-06, + "loss": 1.2793, + "step": 7894 + }, + { + "epoch": 0.83, + "learning_rate": 1.7502990411316978e-06, + "loss": 1.266, + "step": 7895 + }, + { + "epoch": 0.83, + "learning_rate": 1.7482309069039838e-06, + "loss": 1.3085, + "step": 7896 + }, + { + "epoch": 0.83, + "learning_rate": 1.746163878201309e-06, + "loss": 1.3518, + "step": 7897 + }, + { + "epoch": 0.83, + "learning_rate": 1.7440979553005976e-06, + "loss": 1.3887, + "step": 7898 + }, + { + "epoch": 0.83, + "learning_rate": 1.7420331384786305e-06, + "loss": 1.3255, + "step": 7899 + }, + { + "epoch": 0.83, + "learning_rate": 1.7399694280120439e-06, + "loss": 1.3702, + "step": 7900 + }, + { + "epoch": 0.83, + "learning_rate": 1.7379068241773188e-06, + "loss": 1.3253, + "step": 7901 + }, + { + "epoch": 0.83, + "learning_rate": 1.735845327250788e-06, + "loss": 1.3055, + "step": 7902 + }, + { + "epoch": 0.83, + "learning_rate": 1.7337849375086468e-06, + "loss": 1.3119, + "step": 7903 + }, + { + "epoch": 0.83, + "learning_rate": 1.7317256552269278e-06, + "loss": 1.2741, + "step": 7904 + }, + { + "epoch": 0.83, + "learning_rate": 1.7296674806815273e-06, + "loss": 1.3101, + "step": 7905 + }, + { + "epoch": 0.83, + "learning_rate": 1.7276104141481832e-06, + "loss": 1.3553, + "step": 7906 + }, + { + "epoch": 0.83, + "learning_rate": 1.7255544559024906e-06, + "loss": 1.2712, + "step": 7907 + }, + { + "epoch": 0.83, + "learning_rate": 1.7234996062198994e-06, + "loss": 1.2814, + "step": 7908 + }, + { + "epoch": 0.83, + "learning_rate": 1.7214458653757027e-06, + "loss": 1.2831, + "step": 7909 + }, + { + "epoch": 0.83, + "learning_rate": 1.7193932336450437e-06, + "loss": 1.3519, + "step": 7910 + }, + { + "epoch": 0.83, + "learning_rate": 1.7173417113029334e-06, + "loss": 1.2559, + "step": 7911 + }, + { + "epoch": 0.83, + "learning_rate": 1.7152912986242187e-06, + "loss": 1.4204, + "step": 7912 + }, + { + "epoch": 0.83, + "learning_rate": 1.7132419958835978e-06, + "loss": 1.302, + "step": 7913 + }, + { + "epoch": 0.83, + "learning_rate": 1.7111938033556286e-06, + "loss": 1.2959, + "step": 7914 + }, + { + "epoch": 0.83, + "learning_rate": 1.7091467213147162e-06, + "loss": 1.3269, + "step": 7915 + }, + { + "epoch": 0.83, + "learning_rate": 1.7071007500351177e-06, + "loss": 1.2966, + "step": 7916 + }, + { + "epoch": 0.83, + "learning_rate": 1.705055889790941e-06, + "loss": 1.2696, + "step": 7917 + }, + { + "epoch": 0.83, + "learning_rate": 1.7030121408561373e-06, + "loss": 1.3431, + "step": 7918 + }, + { + "epoch": 0.83, + "learning_rate": 1.700969503504528e-06, + "loss": 1.2769, + "step": 7919 + }, + { + "epoch": 0.83, + "learning_rate": 1.698927978009769e-06, + "loss": 1.2543, + "step": 7920 + }, + { + "epoch": 0.83, + "learning_rate": 1.6968875646453665e-06, + "loss": 1.2612, + "step": 7921 + }, + { + "epoch": 0.83, + "learning_rate": 1.694848263684693e-06, + "loss": 1.322, + "step": 7922 + }, + { + "epoch": 0.83, + "learning_rate": 1.692810075400957e-06, + "loss": 1.4144, + "step": 7923 + }, + { + "epoch": 0.83, + "learning_rate": 1.6907730000672263e-06, + "loss": 1.4355, + "step": 7924 + }, + { + "epoch": 0.83, + "learning_rate": 1.6887370379564127e-06, + "loss": 1.4024, + "step": 7925 + }, + { + "epoch": 0.83, + "learning_rate": 1.686702189341285e-06, + "loss": 1.3015, + "step": 7926 + }, + { + "epoch": 0.83, + "learning_rate": 1.6846684544944625e-06, + "loss": 1.4337, + "step": 7927 + }, + { + "epoch": 0.83, + "learning_rate": 1.682635833688412e-06, + "loss": 1.3199, + "step": 7928 + }, + { + "epoch": 0.83, + "learning_rate": 1.6806043271954475e-06, + "loss": 1.2927, + "step": 7929 + }, + { + "epoch": 0.83, + "learning_rate": 1.6785739352877472e-06, + "loss": 1.4254, + "step": 7930 + }, + { + "epoch": 0.83, + "learning_rate": 1.676544658237328e-06, + "loss": 1.3653, + "step": 7931 + }, + { + "epoch": 0.83, + "learning_rate": 1.6745164963160576e-06, + "loss": 1.3049, + "step": 7932 + }, + { + "epoch": 0.83, + "learning_rate": 1.6724894497956613e-06, + "loss": 1.2474, + "step": 7933 + }, + { + "epoch": 0.83, + "learning_rate": 1.6704635189477091e-06, + "loss": 1.3146, + "step": 7934 + }, + { + "epoch": 0.83, + "learning_rate": 1.668438704043628e-06, + "loss": 1.2338, + "step": 7935 + }, + { + "epoch": 0.83, + "learning_rate": 1.666415005354688e-06, + "loss": 1.3217, + "step": 7936 + }, + { + "epoch": 0.83, + "learning_rate": 1.6643924231520082e-06, + "loss": 1.3776, + "step": 7937 + }, + { + "epoch": 0.83, + "learning_rate": 1.6623709577065715e-06, + "loss": 1.6173, + "step": 7938 + }, + { + "epoch": 0.83, + "learning_rate": 1.6603506092891975e-06, + "loss": 1.4383, + "step": 7939 + }, + { + "epoch": 0.83, + "learning_rate": 1.6583313781705602e-06, + "loss": 1.304, + "step": 7940 + }, + { + "epoch": 0.83, + "learning_rate": 1.6563132646211856e-06, + "loss": 1.4071, + "step": 7941 + }, + { + "epoch": 0.83, + "learning_rate": 1.6542962689114494e-06, + "loss": 1.3402, + "step": 7942 + }, + { + "epoch": 0.83, + "learning_rate": 1.6522803913115793e-06, + "loss": 1.3298, + "step": 7943 + }, + { + "epoch": 0.83, + "learning_rate": 1.6502656320916466e-06, + "loss": 1.4741, + "step": 7944 + }, + { + "epoch": 0.83, + "learning_rate": 1.64825199152158e-06, + "loss": 1.3373, + "step": 7945 + }, + { + "epoch": 0.83, + "learning_rate": 1.646239469871158e-06, + "loss": 1.6403, + "step": 7946 + }, + { + "epoch": 0.83, + "learning_rate": 1.644228067410004e-06, + "loss": 1.4887, + "step": 7947 + }, + { + "epoch": 0.83, + "learning_rate": 1.6422177844075893e-06, + "loss": 1.2763, + "step": 7948 + }, + { + "epoch": 0.83, + "learning_rate": 1.6402086211332502e-06, + "loss": 1.3298, + "step": 7949 + }, + { + "epoch": 0.83, + "learning_rate": 1.638200577856156e-06, + "loss": 1.3542, + "step": 7950 + }, + { + "epoch": 0.83, + "learning_rate": 1.6361936548453371e-06, + "loss": 1.2628, + "step": 7951 + }, + { + "epoch": 0.83, + "learning_rate": 1.6341878523696642e-06, + "loss": 1.3937, + "step": 7952 + }, + { + "epoch": 0.83, + "learning_rate": 1.6321831706978674e-06, + "loss": 1.2712, + "step": 7953 + }, + { + "epoch": 0.83, + "learning_rate": 1.6301796100985235e-06, + "loss": 1.3303, + "step": 7954 + }, + { + "epoch": 0.83, + "learning_rate": 1.6281771708400563e-06, + "loss": 1.2698, + "step": 7955 + }, + { + "epoch": 0.83, + "learning_rate": 1.6261758531907367e-06, + "loss": 1.3242, + "step": 7956 + }, + { + "epoch": 0.83, + "learning_rate": 1.6241756574186996e-06, + "loss": 1.2774, + "step": 7957 + }, + { + "epoch": 0.83, + "learning_rate": 1.6221765837919135e-06, + "loss": 1.3022, + "step": 7958 + }, + { + "epoch": 0.83, + "learning_rate": 1.620178632578202e-06, + "loss": 1.375, + "step": 7959 + }, + { + "epoch": 0.83, + "learning_rate": 1.6181818040452412e-06, + "loss": 1.308, + "step": 7960 + }, + { + "epoch": 0.83, + "eval_loss": 1.3948875665664673, + "eval_runtime": 77.4765, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 7960 + }, + { + "epoch": 0.83, + "learning_rate": 1.616186098460555e-06, + "loss": 1.3674, + "step": 7961 + }, + { + "epoch": 0.83, + "learning_rate": 1.614191516091519e-06, + "loss": 1.4367, + "step": 7962 + }, + { + "epoch": 0.84, + "learning_rate": 1.612198057205353e-06, + "loss": 1.3105, + "step": 7963 + }, + { + "epoch": 0.84, + "learning_rate": 1.6102057220691258e-06, + "loss": 1.2591, + "step": 7964 + }, + { + "epoch": 0.84, + "learning_rate": 1.608214510949767e-06, + "loss": 1.3503, + "step": 7965 + }, + { + "epoch": 0.84, + "learning_rate": 1.6062244241140435e-06, + "loss": 1.3278, + "step": 7966 + }, + { + "epoch": 0.84, + "learning_rate": 1.6042354618285727e-06, + "loss": 1.2831, + "step": 7967 + }, + { + "epoch": 0.84, + "learning_rate": 1.6022476243598317e-06, + "loss": 1.2535, + "step": 7968 + }, + { + "epoch": 0.84, + "learning_rate": 1.600260911974133e-06, + "loss": 1.2719, + "step": 7969 + }, + { + "epoch": 0.84, + "learning_rate": 1.5982753249376503e-06, + "loss": 1.2615, + "step": 7970 + }, + { + "epoch": 0.84, + "learning_rate": 1.5962908635163965e-06, + "loss": 1.2996, + "step": 7971 + }, + { + "epoch": 0.84, + "learning_rate": 1.594307527976241e-06, + "loss": 1.3323, + "step": 7972 + }, + { + "epoch": 0.84, + "learning_rate": 1.5923253185829024e-06, + "loss": 1.2993, + "step": 7973 + }, + { + "epoch": 0.84, + "learning_rate": 1.5903442356019415e-06, + "loss": 1.3064, + "step": 7974 + }, + { + "epoch": 0.84, + "learning_rate": 1.5883642792987697e-06, + "loss": 1.3171, + "step": 7975 + }, + { + "epoch": 0.84, + "learning_rate": 1.58638544993866e-06, + "loss": 1.4238, + "step": 7976 + }, + { + "epoch": 0.84, + "learning_rate": 1.584407747786716e-06, + "loss": 1.356, + "step": 7977 + }, + { + "epoch": 0.84, + "learning_rate": 1.5824311731079046e-06, + "loss": 1.4523, + "step": 7978 + }, + { + "epoch": 0.84, + "learning_rate": 1.5804557261670318e-06, + "loss": 1.3206, + "step": 7979 + }, + { + "epoch": 0.84, + "learning_rate": 1.578481407228758e-06, + "loss": 1.2639, + "step": 7980 + }, + { + "epoch": 0.84, + "learning_rate": 1.576508216557594e-06, + "loss": 1.2428, + "step": 7981 + }, + { + "epoch": 0.84, + "learning_rate": 1.574536154417895e-06, + "loss": 1.3779, + "step": 7982 + }, + { + "epoch": 0.84, + "learning_rate": 1.5725652210738606e-06, + "loss": 1.3071, + "step": 7983 + }, + { + "epoch": 0.84, + "learning_rate": 1.5705954167895553e-06, + "loss": 1.2604, + "step": 7984 + }, + { + "epoch": 0.84, + "learning_rate": 1.568626741828878e-06, + "loss": 1.2565, + "step": 7985 + }, + { + "epoch": 0.84, + "learning_rate": 1.5666591964555777e-06, + "loss": 1.2742, + "step": 7986 + }, + { + "epoch": 0.84, + "learning_rate": 1.564692780933258e-06, + "loss": 1.3199, + "step": 7987 + }, + { + "epoch": 0.84, + "learning_rate": 1.5627274955253669e-06, + "loss": 1.4034, + "step": 7988 + }, + { + "epoch": 0.84, + "learning_rate": 1.5607633404952048e-06, + "loss": 1.3411, + "step": 7989 + }, + { + "epoch": 0.84, + "learning_rate": 1.558800316105914e-06, + "loss": 1.2874, + "step": 7990 + }, + { + "epoch": 0.84, + "learning_rate": 1.5568384226204903e-06, + "loss": 1.2678, + "step": 7991 + }, + { + "epoch": 0.84, + "learning_rate": 1.5548776603017813e-06, + "loss": 1.3038, + "step": 7992 + }, + { + "epoch": 0.84, + "learning_rate": 1.5529180294124757e-06, + "loss": 1.0848, + "step": 7993 + }, + { + "epoch": 0.84, + "learning_rate": 1.550959530215108e-06, + "loss": 1.2062, + "step": 7994 + }, + { + "epoch": 0.84, + "learning_rate": 1.5490021629720763e-06, + "loss": 1.3028, + "step": 7995 + }, + { + "epoch": 0.84, + "learning_rate": 1.547045927945613e-06, + "loss": 1.3513, + "step": 7996 + }, + { + "epoch": 0.84, + "learning_rate": 1.5450908253978047e-06, + "loss": 1.426, + "step": 7997 + }, + { + "epoch": 0.84, + "learning_rate": 1.5431368555905813e-06, + "loss": 1.2943, + "step": 7998 + }, + { + "epoch": 0.84, + "learning_rate": 1.5411840187857275e-06, + "loss": 1.272, + "step": 7999 + }, + { + "epoch": 0.84, + "learning_rate": 1.5392323152448762e-06, + "loss": 1.3819, + "step": 8000 + }, + { + "epoch": 0.84, + "learning_rate": 1.537281745229502e-06, + "loss": 1.2186, + "step": 8001 + }, + { + "epoch": 0.84, + "learning_rate": 1.5353323090009253e-06, + "loss": 1.4509, + "step": 8002 + }, + { + "epoch": 0.84, + "learning_rate": 1.5333840068203332e-06, + "loss": 1.3629, + "step": 8003 + }, + { + "epoch": 0.84, + "learning_rate": 1.5314368389487378e-06, + "loss": 1.2865, + "step": 8004 + }, + { + "epoch": 0.84, + "learning_rate": 1.529490805647016e-06, + "loss": 1.2645, + "step": 8005 + }, + { + "epoch": 0.84, + "learning_rate": 1.5275459071758813e-06, + "loss": 1.3248, + "step": 8006 + }, + { + "epoch": 0.84, + "learning_rate": 1.5256021437959023e-06, + "loss": 1.2202, + "step": 8007 + }, + { + "epoch": 0.84, + "learning_rate": 1.523659515767496e-06, + "loss": 1.3728, + "step": 8008 + }, + { + "epoch": 0.84, + "learning_rate": 1.5217180233509222e-06, + "loss": 1.2981, + "step": 8009 + }, + { + "epoch": 0.84, + "learning_rate": 1.5197776668062857e-06, + "loss": 1.4002, + "step": 8010 + }, + { + "epoch": 0.84, + "learning_rate": 1.5178384463935546e-06, + "loss": 1.3403, + "step": 8011 + }, + { + "epoch": 0.84, + "learning_rate": 1.51590036237253e-06, + "loss": 1.2629, + "step": 8012 + }, + { + "epoch": 0.84, + "learning_rate": 1.5139634150028594e-06, + "loss": 1.298, + "step": 8013 + }, + { + "epoch": 0.84, + "learning_rate": 1.5120276045440553e-06, + "loss": 1.412, + "step": 8014 + }, + { + "epoch": 0.84, + "learning_rate": 1.510092931255458e-06, + "loss": 1.3025, + "step": 8015 + }, + { + "epoch": 0.84, + "learning_rate": 1.508159395396268e-06, + "loss": 1.2494, + "step": 8016 + }, + { + "epoch": 0.84, + "learning_rate": 1.5062269972255273e-06, + "loss": 1.3295, + "step": 8017 + }, + { + "epoch": 0.84, + "learning_rate": 1.5042957370021282e-06, + "loss": 1.3227, + "step": 8018 + }, + { + "epoch": 0.84, + "learning_rate": 1.5023656149848132e-06, + "loss": 1.3122, + "step": 8019 + }, + { + "epoch": 0.84, + "learning_rate": 1.500436631432165e-06, + "loss": 1.2789, + "step": 8020 + }, + { + "epoch": 0.84, + "learning_rate": 1.4985087866026148e-06, + "loss": 1.2753, + "step": 8021 + }, + { + "epoch": 0.84, + "learning_rate": 1.4965820807544529e-06, + "loss": 1.3296, + "step": 8022 + }, + { + "epoch": 0.84, + "learning_rate": 1.4946565141458024e-06, + "loss": 1.2886, + "step": 8023 + }, + { + "epoch": 0.84, + "learning_rate": 1.492732087034643e-06, + "loss": 1.3137, + "step": 8024 + }, + { + "epoch": 0.84, + "learning_rate": 1.4908087996787944e-06, + "loss": 1.2785, + "step": 8025 + }, + { + "epoch": 0.84, + "learning_rate": 1.4888866523359302e-06, + "loss": 1.3674, + "step": 8026 + }, + { + "epoch": 0.84, + "learning_rate": 1.4869656452635705e-06, + "loss": 1.367, + "step": 8027 + }, + { + "epoch": 0.84, + "learning_rate": 1.4850457787190797e-06, + "loss": 1.3342, + "step": 8028 + }, + { + "epoch": 0.84, + "learning_rate": 1.483127052959664e-06, + "loss": 1.3091, + "step": 8029 + }, + { + "epoch": 0.84, + "learning_rate": 1.481209468242396e-06, + "loss": 1.3729, + "step": 8030 + }, + { + "epoch": 0.84, + "learning_rate": 1.4792930248241744e-06, + "loss": 1.3051, + "step": 8031 + }, + { + "epoch": 0.84, + "learning_rate": 1.4773777229617537e-06, + "loss": 1.2458, + "step": 8032 + }, + { + "epoch": 0.84, + "learning_rate": 1.4754635629117353e-06, + "loss": 1.2803, + "step": 8033 + }, + { + "epoch": 0.84, + "learning_rate": 1.4735505449305687e-06, + "loss": 1.3193, + "step": 8034 + }, + { + "epoch": 0.84, + "learning_rate": 1.4716386692745522e-06, + "loss": 1.2537, + "step": 8035 + }, + { + "epoch": 0.84, + "learning_rate": 1.4697279361998218e-06, + "loss": 1.2816, + "step": 8036 + }, + { + "epoch": 0.84, + "learning_rate": 1.4678183459623708e-06, + "loss": 1.3422, + "step": 8037 + }, + { + "epoch": 0.84, + "learning_rate": 1.4659098988180353e-06, + "loss": 1.34, + "step": 8038 + }, + { + "epoch": 0.84, + "learning_rate": 1.464002595022498e-06, + "loss": 1.3328, + "step": 8039 + }, + { + "epoch": 0.84, + "learning_rate": 1.4620964348312817e-06, + "loss": 1.3415, + "step": 8040 + }, + { + "epoch": 0.84, + "learning_rate": 1.4601914184997744e-06, + "loss": 1.3124, + "step": 8041 + }, + { + "epoch": 0.84, + "learning_rate": 1.4582875462831913e-06, + "loss": 1.3219, + "step": 8042 + }, + { + "epoch": 0.84, + "learning_rate": 1.4563848184366069e-06, + "loss": 1.3322, + "step": 8043 + }, + { + "epoch": 0.84, + "learning_rate": 1.454483235214934e-06, + "loss": 1.2926, + "step": 8044 + }, + { + "epoch": 0.84, + "learning_rate": 1.4525827968729366e-06, + "loss": 1.2796, + "step": 8045 + }, + { + "epoch": 0.84, + "learning_rate": 1.4506835036652289e-06, + "loss": 1.3504, + "step": 8046 + }, + { + "epoch": 0.84, + "learning_rate": 1.448785355846264e-06, + "loss": 1.2122, + "step": 8047 + }, + { + "epoch": 0.84, + "learning_rate": 1.4468883536703405e-06, + "loss": 1.3121, + "step": 8048 + }, + { + "epoch": 0.84, + "learning_rate": 1.4449924973916163e-06, + "loss": 1.3268, + "step": 8049 + }, + { + "epoch": 0.84, + "learning_rate": 1.4430977872640817e-06, + "loss": 1.3911, + "step": 8050 + }, + { + "epoch": 0.84, + "learning_rate": 1.4412042235415836e-06, + "loss": 1.3366, + "step": 8051 + }, + { + "epoch": 0.84, + "learning_rate": 1.4393118064778066e-06, + "loss": 1.2953, + "step": 8052 + }, + { + "epoch": 0.84, + "learning_rate": 1.4374205363262872e-06, + "loss": 1.3222, + "step": 8053 + }, + { + "epoch": 0.84, + "learning_rate": 1.4355304133404102e-06, + "loss": 1.2385, + "step": 8054 + }, + { + "epoch": 0.84, + "learning_rate": 1.433641437773401e-06, + "loss": 1.3245, + "step": 8055 + }, + { + "epoch": 0.84, + "learning_rate": 1.431753609878328e-06, + "loss": 1.2401, + "step": 8056 + }, + { + "epoch": 0.84, + "learning_rate": 1.4298669299081236e-06, + "loss": 1.4646, + "step": 8057 + }, + { + "epoch": 0.85, + "learning_rate": 1.4279813981155465e-06, + "loss": 1.253, + "step": 8058 + }, + { + "epoch": 0.85, + "learning_rate": 1.426097014753207e-06, + "loss": 1.393, + "step": 8059 + }, + { + "epoch": 0.85, + "learning_rate": 1.4242137800735734e-06, + "loss": 1.3527, + "step": 8060 + }, + { + "epoch": 0.85, + "learning_rate": 1.4223316943289435e-06, + "loss": 1.2528, + "step": 8061 + }, + { + "epoch": 0.85, + "learning_rate": 1.420450757771472e-06, + "loss": 1.2165, + "step": 8062 + }, + { + "epoch": 0.85, + "learning_rate": 1.4185709706531526e-06, + "loss": 1.2348, + "step": 8063 + }, + { + "epoch": 0.85, + "learning_rate": 1.4166923332258308e-06, + "loss": 1.3145, + "step": 8064 + }, + { + "epoch": 0.85, + "learning_rate": 1.414814845741197e-06, + "loss": 1.2026, + "step": 8065 + }, + { + "epoch": 0.85, + "learning_rate": 1.4129385084507852e-06, + "loss": 1.3398, + "step": 8066 + }, + { + "epoch": 0.85, + "learning_rate": 1.4110633216059711e-06, + "loss": 1.3166, + "step": 8067 + }, + { + "epoch": 0.85, + "learning_rate": 1.4091892854579913e-06, + "loss": 1.5105, + "step": 8068 + }, + { + "epoch": 0.85, + "learning_rate": 1.407316400257911e-06, + "loss": 1.3002, + "step": 8069 + }, + { + "epoch": 0.85, + "learning_rate": 1.4054446662566535e-06, + "loss": 1.2826, + "step": 8070 + }, + { + "epoch": 0.85, + "learning_rate": 1.4035740837049782e-06, + "loss": 1.338, + "step": 8071 + }, + { + "epoch": 0.85, + "learning_rate": 1.4017046528534983e-06, + "loss": 1.393, + "step": 8072 + }, + { + "epoch": 0.85, + "learning_rate": 1.3998363739526699e-06, + "loss": 1.3082, + "step": 8073 + }, + { + "epoch": 0.85, + "learning_rate": 1.397969247252794e-06, + "loss": 1.345, + "step": 8074 + }, + { + "epoch": 0.85, + "learning_rate": 1.3961032730040126e-06, + "loss": 1.3075, + "step": 8075 + }, + { + "epoch": 0.85, + "learning_rate": 1.394238451456328e-06, + "loss": 1.3432, + "step": 8076 + }, + { + "epoch": 0.85, + "learning_rate": 1.392374782859569e-06, + "loss": 1.3096, + "step": 8077 + }, + { + "epoch": 0.85, + "learning_rate": 1.3905122674634274e-06, + "loss": 1.2686, + "step": 8078 + }, + { + "epoch": 0.85, + "learning_rate": 1.3886509055174247e-06, + "loss": 1.3075, + "step": 8079 + }, + { + "epoch": 0.85, + "learning_rate": 1.38679069727094e-06, + "loss": 1.3446, + "step": 8080 + }, + { + "epoch": 0.85, + "learning_rate": 1.3849316429731941e-06, + "loss": 1.3646, + "step": 8081 + }, + { + "epoch": 0.85, + "learning_rate": 1.3830737428732499e-06, + "loss": 1.3074, + "step": 8082 + }, + { + "epoch": 0.85, + "learning_rate": 1.3812169972200184e-06, + "loss": 1.277, + "step": 8083 + }, + { + "epoch": 0.85, + "learning_rate": 1.3793614062622595e-06, + "loss": 1.2978, + "step": 8084 + }, + { + "epoch": 0.85, + "learning_rate": 1.3775069702485722e-06, + "loss": 1.3978, + "step": 8085 + }, + { + "epoch": 0.85, + "learning_rate": 1.3756536894273974e-06, + "loss": 1.4198, + "step": 8086 + }, + { + "epoch": 0.85, + "learning_rate": 1.3738015640470381e-06, + "loss": 1.2901, + "step": 8087 + }, + { + "epoch": 0.85, + "learning_rate": 1.3719505943556243e-06, + "loss": 1.2916, + "step": 8088 + }, + { + "epoch": 0.85, + "learning_rate": 1.3701007806011423e-06, + "loss": 1.2845, + "step": 8089 + }, + { + "epoch": 0.85, + "learning_rate": 1.368252123031416e-06, + "loss": 1.3261, + "step": 8090 + }, + { + "epoch": 0.85, + "learning_rate": 1.3664046218941185e-06, + "loss": 1.321, + "step": 8091 + }, + { + "epoch": 0.85, + "learning_rate": 1.3645582774367717e-06, + "loss": 1.2968, + "step": 8092 + }, + { + "epoch": 0.85, + "learning_rate": 1.3627130899067353e-06, + "loss": 1.2595, + "step": 8093 + }, + { + "epoch": 0.85, + "learning_rate": 1.360869059551212e-06, + "loss": 1.4081, + "step": 8094 + }, + { + "epoch": 0.85, + "learning_rate": 1.3590261866172638e-06, + "loss": 1.2949, + "step": 8095 + }, + { + "epoch": 0.85, + "learning_rate": 1.3571844713517823e-06, + "loss": 1.3563, + "step": 8096 + }, + { + "epoch": 0.85, + "learning_rate": 1.3553439140015135e-06, + "loss": 1.3063, + "step": 8097 + }, + { + "epoch": 0.85, + "learning_rate": 1.353504514813041e-06, + "loss": 1.2896, + "step": 8098 + }, + { + "epoch": 0.85, + "learning_rate": 1.351666274032799e-06, + "loss": 1.3338, + "step": 8099 + }, + { + "epoch": 0.85, + "learning_rate": 1.349829191907066e-06, + "loss": 1.2932, + "step": 8100 + }, + { + "epoch": 0.85, + "learning_rate": 1.3479932686819642e-06, + "loss": 1.3287, + "step": 8101 + }, + { + "epoch": 0.85, + "learning_rate": 1.346158504603452e-06, + "loss": 1.3343, + "step": 8102 + }, + { + "epoch": 0.85, + "learning_rate": 1.344324899917352e-06, + "loss": 1.3419, + "step": 8103 + }, + { + "epoch": 0.85, + "learning_rate": 1.342492454869313e-06, + "loss": 1.3138, + "step": 8104 + }, + { + "epoch": 0.85, + "learning_rate": 1.3406611697048377e-06, + "loss": 1.3473, + "step": 8105 + }, + { + "epoch": 0.85, + "learning_rate": 1.338831044669273e-06, + "loss": 1.3035, + "step": 8106 + }, + { + "epoch": 0.85, + "learning_rate": 1.3370020800078043e-06, + "loss": 1.3299, + "step": 8107 + }, + { + "epoch": 0.85, + "learning_rate": 1.3351742759654707e-06, + "loss": 1.357, + "step": 8108 + }, + { + "epoch": 0.85, + "learning_rate": 1.3333476327871475e-06, + "loss": 1.3777, + "step": 8109 + }, + { + "epoch": 0.85, + "learning_rate": 1.331522150717558e-06, + "loss": 1.3359, + "step": 8110 + }, + { + "epoch": 0.85, + "learning_rate": 1.329697830001273e-06, + "loss": 1.2436, + "step": 8111 + }, + { + "epoch": 0.85, + "learning_rate": 1.3278746708827028e-06, + "loss": 1.2916, + "step": 8112 + }, + { + "epoch": 0.85, + "learning_rate": 1.3260526736060998e-06, + "loss": 1.3127, + "step": 8113 + }, + { + "epoch": 0.85, + "learning_rate": 1.3242318384155728e-06, + "loss": 1.2876, + "step": 8114 + }, + { + "epoch": 0.85, + "learning_rate": 1.3224121655550603e-06, + "loss": 1.4193, + "step": 8115 + }, + { + "epoch": 0.85, + "learning_rate": 1.3205936552683573e-06, + "loss": 1.2978, + "step": 8116 + }, + { + "epoch": 0.85, + "learning_rate": 1.3187763077990912e-06, + "loss": 1.344, + "step": 8117 + }, + { + "epoch": 0.85, + "learning_rate": 1.3169601233907436e-06, + "loss": 1.2493, + "step": 8118 + }, + { + "epoch": 0.85, + "learning_rate": 1.315145102286638e-06, + "loss": 1.344, + "step": 8119 + }, + { + "epoch": 0.85, + "learning_rate": 1.3133312447299385e-06, + "loss": 1.3235, + "step": 8120 + }, + { + "epoch": 0.85, + "learning_rate": 1.3115185509636508e-06, + "loss": 1.3134, + "step": 8121 + }, + { + "epoch": 0.85, + "learning_rate": 1.3097070212306385e-06, + "loss": 1.2735, + "step": 8122 + }, + { + "epoch": 0.85, + "learning_rate": 1.307896655773594e-06, + "loss": 1.4682, + "step": 8123 + }, + { + "epoch": 0.85, + "learning_rate": 1.3060874548350632e-06, + "loss": 1.2092, + "step": 8124 + }, + { + "epoch": 0.85, + "learning_rate": 1.304279418657428e-06, + "loss": 1.314, + "step": 8125 + }, + { + "epoch": 0.85, + "learning_rate": 1.3024725474829215e-06, + "loss": 1.4204, + "step": 8126 + }, + { + "epoch": 0.85, + "learning_rate": 1.3006668415536195e-06, + "loss": 1.298, + "step": 8127 + }, + { + "epoch": 0.85, + "learning_rate": 1.2988623011114377e-06, + "loss": 1.2639, + "step": 8128 + }, + { + "epoch": 0.85, + "learning_rate": 1.2970589263981382e-06, + "loss": 1.291, + "step": 8129 + }, + { + "epoch": 0.85, + "learning_rate": 1.2952567176553298e-06, + "loss": 1.3849, + "step": 8130 + }, + { + "epoch": 0.85, + "learning_rate": 1.293455675124461e-06, + "loss": 1.2594, + "step": 8131 + }, + { + "epoch": 0.85, + "learning_rate": 1.2916557990468192e-06, + "loss": 1.3696, + "step": 8132 + }, + { + "epoch": 0.85, + "learning_rate": 1.289857089663551e-06, + "loss": 1.3263, + "step": 8133 + }, + { + "epoch": 0.85, + "learning_rate": 1.288059547215631e-06, + "loss": 1.302, + "step": 8134 + }, + { + "epoch": 0.85, + "learning_rate": 1.2862631719438878e-06, + "loss": 1.2587, + "step": 8135 + }, + { + "epoch": 0.85, + "learning_rate": 1.2844679640889857e-06, + "loss": 1.3579, + "step": 8136 + }, + { + "epoch": 0.85, + "learning_rate": 1.2826739238914376e-06, + "loss": 1.3246, + "step": 8137 + }, + { + "epoch": 0.85, + "learning_rate": 1.2808810515916016e-06, + "loss": 1.3346, + "step": 8138 + }, + { + "epoch": 0.85, + "learning_rate": 1.279089347429674e-06, + "loss": 1.264, + "step": 8139 + }, + { + "epoch": 0.85, + "learning_rate": 1.277298811645692e-06, + "loss": 1.2276, + "step": 8140 + }, + { + "epoch": 0.85, + "learning_rate": 1.2755094444795524e-06, + "loss": 1.2699, + "step": 8141 + }, + { + "epoch": 0.85, + "learning_rate": 1.273721246170976e-06, + "loss": 1.2784, + "step": 8142 + }, + { + "epoch": 0.85, + "learning_rate": 1.2719342169595406e-06, + "loss": 1.3973, + "step": 8143 + }, + { + "epoch": 0.85, + "learning_rate": 1.2701483570846572e-06, + "loss": 1.2869, + "step": 8144 + }, + { + "epoch": 0.85, + "learning_rate": 1.268363666785588e-06, + "loss": 1.0653, + "step": 8145 + }, + { + "epoch": 0.85, + "learning_rate": 1.266580146301437e-06, + "loss": 1.0105, + "step": 8146 + }, + { + "epoch": 0.85, + "learning_rate": 1.264797795871149e-06, + "loss": 1.3069, + "step": 8147 + }, + { + "epoch": 0.85, + "learning_rate": 1.2630166157335077e-06, + "loss": 1.303, + "step": 8148 + }, + { + "epoch": 0.85, + "learning_rate": 1.2612366061271552e-06, + "loss": 1.2883, + "step": 8149 + }, + { + "epoch": 0.85, + "learning_rate": 1.2594577672905594e-06, + "loss": 1.4152, + "step": 8150 + }, + { + "epoch": 0.85, + "learning_rate": 1.257680099462043e-06, + "loss": 1.273, + "step": 8151 + }, + { + "epoch": 0.85, + "learning_rate": 1.2559036028797677e-06, + "loss": 1.2793, + "step": 8152 + }, + { + "epoch": 0.85, + "learning_rate": 1.2541282777817354e-06, + "loss": 1.3001, + "step": 8153 + }, + { + "epoch": 0.86, + "learning_rate": 1.252354124405799e-06, + "loss": 1.3743, + "step": 8154 + }, + { + "epoch": 0.86, + "learning_rate": 1.2505811429896432e-06, + "loss": 1.2804, + "step": 8155 + }, + { + "epoch": 0.86, + "learning_rate": 1.2488093337708062e-06, + "loss": 1.3354, + "step": 8156 + }, + { + "epoch": 0.86, + "learning_rate": 1.2470386969866655e-06, + "loss": 1.3836, + "step": 8157 + }, + { + "epoch": 0.86, + "learning_rate": 1.2452692328744386e-06, + "loss": 1.2499, + "step": 8158 + }, + { + "epoch": 0.86, + "learning_rate": 1.2435009416711853e-06, + "loss": 1.4049, + "step": 8159 + }, + { + "epoch": 0.86, + "eval_loss": 1.3945679664611816, + "eval_runtime": 77.4963, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 8159 + }, + { + "epoch": 0.86, + "learning_rate": 1.2417338236138199e-06, + "loss": 1.261, + "step": 8160 + }, + { + "epoch": 0.86, + "learning_rate": 1.2399678789390823e-06, + "loss": 1.3172, + "step": 8161 + }, + { + "epoch": 0.86, + "learning_rate": 1.238203107883571e-06, + "loss": 1.3836, + "step": 8162 + }, + { + "epoch": 0.86, + "learning_rate": 1.2364395106837124e-06, + "loss": 1.3116, + "step": 8163 + }, + { + "epoch": 0.86, + "learning_rate": 1.2346770875757874e-06, + "loss": 1.2897, + "step": 8164 + }, + { + "epoch": 0.86, + "learning_rate": 1.2329158387959172e-06, + "loss": 1.3148, + "step": 8165 + }, + { + "epoch": 0.86, + "learning_rate": 1.231155764580062e-06, + "loss": 1.2744, + "step": 8166 + }, + { + "epoch": 0.86, + "learning_rate": 1.229396865164022e-06, + "loss": 1.3159, + "step": 8167 + }, + { + "epoch": 0.86, + "learning_rate": 1.2276391407834532e-06, + "loss": 1.3238, + "step": 8168 + }, + { + "epoch": 0.86, + "learning_rate": 1.2258825916738383e-06, + "loss": 1.3376, + "step": 8169 + }, + { + "epoch": 0.86, + "learning_rate": 1.2241272180705143e-06, + "loss": 1.2715, + "step": 8170 + }, + { + "epoch": 0.86, + "learning_rate": 1.2223730202086525e-06, + "loss": 1.3022, + "step": 8171 + }, + { + "epoch": 0.86, + "learning_rate": 1.2206199983232726e-06, + "loss": 1.3354, + "step": 8172 + }, + { + "epoch": 0.86, + "learning_rate": 1.2188681526492363e-06, + "loss": 1.4273, + "step": 8173 + }, + { + "epoch": 0.86, + "learning_rate": 1.2171174834212407e-06, + "loss": 1.3272, + "step": 8174 + }, + { + "epoch": 0.86, + "learning_rate": 1.2153679908738337e-06, + "loss": 1.3173, + "step": 8175 + }, + { + "epoch": 0.86, + "learning_rate": 1.2136196752414042e-06, + "loss": 1.2679, + "step": 8176 + }, + { + "epoch": 0.86, + "learning_rate": 1.2118725367581784e-06, + "loss": 1.3409, + "step": 8177 + }, + { + "epoch": 0.86, + "learning_rate": 1.210126575658228e-06, + "loss": 1.3393, + "step": 8178 + }, + { + "epoch": 0.86, + "learning_rate": 1.2083817921754705e-06, + "loss": 1.3126, + "step": 8179 + }, + { + "epoch": 0.86, + "learning_rate": 1.2066381865436571e-06, + "loss": 1.3525, + "step": 8180 + }, + { + "epoch": 0.86, + "learning_rate": 1.2048957589963907e-06, + "loss": 1.3107, + "step": 8181 + }, + { + "epoch": 0.86, + "learning_rate": 1.2031545097671082e-06, + "loss": 1.3374, + "step": 8182 + }, + { + "epoch": 0.86, + "learning_rate": 1.2014144390890937e-06, + "loss": 1.2889, + "step": 8183 + }, + { + "epoch": 0.86, + "learning_rate": 1.1996755471954734e-06, + "loss": 1.3043, + "step": 8184 + }, + { + "epoch": 0.86, + "learning_rate": 1.1979378343192126e-06, + "loss": 1.3172, + "step": 8185 + }, + { + "epoch": 0.86, + "learning_rate": 1.1962013006931172e-06, + "loss": 1.3526, + "step": 8186 + }, + { + "epoch": 0.86, + "learning_rate": 1.1944659465498443e-06, + "loss": 1.32, + "step": 8187 + }, + { + "epoch": 0.86, + "learning_rate": 1.1927317721218822e-06, + "loss": 1.3449, + "step": 8188 + }, + { + "epoch": 0.86, + "learning_rate": 1.1909987776415699e-06, + "loss": 1.2887, + "step": 8189 + }, + { + "epoch": 0.86, + "learning_rate": 1.189266963341078e-06, + "loss": 1.368, + "step": 8190 + }, + { + "epoch": 0.86, + "learning_rate": 1.18753632945243e-06, + "loss": 1.3297, + "step": 8191 + }, + { + "epoch": 0.86, + "learning_rate": 1.185806876207486e-06, + "loss": 1.3447, + "step": 8192 + }, + { + "epoch": 0.86, + "learning_rate": 1.184078603837946e-06, + "loss": 1.291, + "step": 8193 + }, + { + "epoch": 0.86, + "learning_rate": 1.182351512575355e-06, + "loss": 1.3272, + "step": 8194 + }, + { + "epoch": 0.86, + "learning_rate": 1.180625602651101e-06, + "loss": 1.2771, + "step": 8195 + }, + { + "epoch": 0.86, + "learning_rate": 1.178900874296407e-06, + "loss": 1.2562, + "step": 8196 + }, + { + "epoch": 0.86, + "learning_rate": 1.177177327742346e-06, + "loss": 1.2508, + "step": 8197 + }, + { + "epoch": 0.86, + "learning_rate": 1.1754549632198298e-06, + "loss": 1.2923, + "step": 8198 + }, + { + "epoch": 0.86, + "learning_rate": 1.1737337809596072e-06, + "loss": 1.3251, + "step": 8199 + }, + { + "epoch": 0.86, + "learning_rate": 1.1720137811922761e-06, + "loss": 1.2729, + "step": 8200 + }, + { + "epoch": 0.86, + "learning_rate": 1.1702949641482687e-06, + "loss": 1.2635, + "step": 8201 + }, + { + "epoch": 0.86, + "learning_rate": 1.1685773300578651e-06, + "loss": 1.3456, + "step": 8202 + }, + { + "epoch": 0.86, + "learning_rate": 1.1668608791511838e-06, + "loss": 1.2506, + "step": 8203 + }, + { + "epoch": 0.86, + "learning_rate": 1.1651456116581838e-06, + "loss": 1.4416, + "step": 8204 + }, + { + "epoch": 0.86, + "learning_rate": 1.163431527808666e-06, + "loss": 1.3066, + "step": 8205 + }, + { + "epoch": 0.86, + "learning_rate": 1.161718627832279e-06, + "loss": 1.2943, + "step": 8206 + }, + { + "epoch": 0.86, + "learning_rate": 1.1600069119585e-06, + "loss": 1.2785, + "step": 8207 + }, + { + "epoch": 0.86, + "learning_rate": 1.1582963804166614e-06, + "loss": 1.3252, + "step": 8208 + }, + { + "epoch": 0.86, + "learning_rate": 1.1565870334359263e-06, + "loss": 1.2878, + "step": 8209 + }, + { + "epoch": 0.86, + "learning_rate": 1.154878871245303e-06, + "loss": 1.2809, + "step": 8210 + }, + { + "epoch": 0.86, + "learning_rate": 1.1531718940736458e-06, + "loss": 1.3194, + "step": 8211 + }, + { + "epoch": 0.86, + "learning_rate": 1.1514661021496432e-06, + "loss": 1.2898, + "step": 8212 + }, + { + "epoch": 0.86, + "learning_rate": 1.1497614957018233e-06, + "loss": 1.3392, + "step": 8213 + }, + { + "epoch": 0.86, + "learning_rate": 1.1480580749585669e-06, + "loss": 1.2746, + "step": 8214 + }, + { + "epoch": 0.86, + "learning_rate": 1.1463558401480824e-06, + "loss": 1.2374, + "step": 8215 + }, + { + "epoch": 0.86, + "learning_rate": 1.1446547914984296e-06, + "loss": 1.334, + "step": 8216 + }, + { + "epoch": 0.86, + "learning_rate": 1.1429549292375053e-06, + "loss": 1.0102, + "step": 8217 + }, + { + "epoch": 0.86, + "learning_rate": 1.1412562535930448e-06, + "loss": 0.9128, + "step": 8218 + }, + { + "epoch": 0.86, + "learning_rate": 1.13955876479263e-06, + "loss": 0.8105, + "step": 8219 + }, + { + "epoch": 0.86, + "learning_rate": 1.137862463063677e-06, + "loss": 0.8131, + "step": 8220 + }, + { + "epoch": 0.86, + "learning_rate": 1.1361673486334478e-06, + "loss": 1.277, + "step": 8221 + }, + { + "epoch": 0.86, + "learning_rate": 1.1344734217290475e-06, + "loss": 1.2847, + "step": 8222 + }, + { + "epoch": 0.86, + "learning_rate": 1.1327806825774158e-06, + "loss": 1.4042, + "step": 8223 + }, + { + "epoch": 0.86, + "learning_rate": 1.1310891314053353e-06, + "loss": 1.1244, + "step": 8224 + }, + { + "epoch": 0.86, + "learning_rate": 1.1293987684394347e-06, + "loss": 1.1722, + "step": 8225 + }, + { + "epoch": 0.86, + "learning_rate": 1.1277095939061732e-06, + "loss": 1.3665, + "step": 8226 + }, + { + "epoch": 0.86, + "learning_rate": 1.1260216080318632e-06, + "loss": 1.3327, + "step": 8227 + }, + { + "epoch": 0.86, + "learning_rate": 1.1243348110426455e-06, + "loss": 1.3167, + "step": 8228 + }, + { + "epoch": 0.86, + "learning_rate": 1.1226492031645109e-06, + "loss": 1.3049, + "step": 8229 + }, + { + "epoch": 0.86, + "learning_rate": 1.1209647846232884e-06, + "loss": 1.2995, + "step": 8230 + }, + { + "epoch": 0.86, + "learning_rate": 1.1192815556446445e-06, + "loss": 1.3078, + "step": 8231 + }, + { + "epoch": 0.86, + "learning_rate": 1.1175995164540887e-06, + "loss": 1.4174, + "step": 8232 + }, + { + "epoch": 0.86, + "learning_rate": 1.1159186672769728e-06, + "loss": 1.2479, + "step": 8233 + }, + { + "epoch": 0.86, + "learning_rate": 1.1142390083384857e-06, + "loss": 1.3166, + "step": 8234 + }, + { + "epoch": 0.86, + "learning_rate": 1.1125605398636607e-06, + "loss": 1.2816, + "step": 8235 + }, + { + "epoch": 0.86, + "learning_rate": 1.1108832620773668e-06, + "loss": 1.3271, + "step": 8236 + }, + { + "epoch": 0.86, + "learning_rate": 1.1092071752043166e-06, + "loss": 1.3389, + "step": 8237 + }, + { + "epoch": 0.86, + "learning_rate": 1.1075322794690658e-06, + "loss": 1.3243, + "step": 8238 + }, + { + "epoch": 0.86, + "learning_rate": 1.1058585750960028e-06, + "loss": 1.2811, + "step": 8239 + }, + { + "epoch": 0.86, + "learning_rate": 1.1041860623093625e-06, + "loss": 1.3068, + "step": 8240 + }, + { + "epoch": 0.86, + "learning_rate": 1.1025147413332215e-06, + "loss": 1.3694, + "step": 8241 + }, + { + "epoch": 0.86, + "learning_rate": 1.1008446123914907e-06, + "loss": 1.3659, + "step": 8242 + }, + { + "epoch": 0.86, + "learning_rate": 1.0991756757079243e-06, + "loss": 1.3976, + "step": 8243 + }, + { + "epoch": 0.86, + "learning_rate": 1.097507931506121e-06, + "loss": 1.3445, + "step": 8244 + }, + { + "epoch": 0.86, + "learning_rate": 1.0958413800095102e-06, + "loss": 1.3606, + "step": 8245 + }, + { + "epoch": 0.86, + "learning_rate": 1.0941760214413721e-06, + "loss": 1.2929, + "step": 8246 + }, + { + "epoch": 0.86, + "learning_rate": 1.0925118560248172e-06, + "loss": 1.3275, + "step": 8247 + }, + { + "epoch": 0.86, + "learning_rate": 1.0908488839828024e-06, + "loss": 1.2897, + "step": 8248 + }, + { + "epoch": 0.87, + "learning_rate": 1.0891871055381264e-06, + "loss": 1.3044, + "step": 8249 + }, + { + "epoch": 0.87, + "learning_rate": 1.08752652091342e-06, + "loss": 1.3451, + "step": 8250 + }, + { + "epoch": 0.87, + "learning_rate": 1.085867130331162e-06, + "loss": 1.3619, + "step": 8251 + }, + { + "epoch": 0.87, + "learning_rate": 1.0842089340136685e-06, + "loss": 1.2743, + "step": 8252 + }, + { + "epoch": 0.87, + "learning_rate": 1.0825519321830925e-06, + "loss": 1.2792, + "step": 8253 + }, + { + "epoch": 0.87, + "learning_rate": 1.0808961250614335e-06, + "loss": 1.3186, + "step": 8254 + }, + { + "epoch": 0.87, + "learning_rate": 1.0792415128705224e-06, + "loss": 1.3143, + "step": 8255 + }, + { + "epoch": 0.87, + "learning_rate": 1.0775880958320362e-06, + "loss": 1.3303, + "step": 8256 + }, + { + "epoch": 0.87, + "learning_rate": 1.075935874167494e-06, + "loss": 1.2601, + "step": 8257 + }, + { + "epoch": 0.87, + "learning_rate": 1.0742848480982494e-06, + "loss": 1.3004, + "step": 8258 + }, + { + "epoch": 0.87, + "learning_rate": 1.0726350178454903e-06, + "loss": 1.2705, + "step": 8259 + }, + { + "epoch": 0.87, + "learning_rate": 1.0709863836302624e-06, + "loss": 1.2801, + "step": 8260 + }, + { + "epoch": 0.87, + "learning_rate": 1.0693389456734338e-06, + "loss": 1.322, + "step": 8261 + }, + { + "epoch": 0.87, + "learning_rate": 1.067692704195721e-06, + "loss": 1.2792, + "step": 8262 + }, + { + "epoch": 0.87, + "learning_rate": 1.0660476594176794e-06, + "loss": 1.3454, + "step": 8263 + }, + { + "epoch": 0.87, + "learning_rate": 1.0644038115596976e-06, + "loss": 1.2557, + "step": 8264 + }, + { + "epoch": 0.87, + "learning_rate": 1.0627611608420163e-06, + "loss": 1.3196, + "step": 8265 + }, + { + "epoch": 0.87, + "learning_rate": 1.0611197074847014e-06, + "loss": 1.3078, + "step": 8266 + }, + { + "epoch": 0.87, + "learning_rate": 1.059479451707669e-06, + "loss": 1.2815, + "step": 8267 + }, + { + "epoch": 0.87, + "learning_rate": 1.0578403937306726e-06, + "loss": 1.2226, + "step": 8268 + }, + { + "epoch": 0.87, + "learning_rate": 1.0562025337732995e-06, + "loss": 1.3396, + "step": 8269 + }, + { + "epoch": 0.87, + "learning_rate": 1.0545658720549844e-06, + "loss": 1.4786, + "step": 8270 + }, + { + "epoch": 0.87, + "learning_rate": 1.0529304087949988e-06, + "loss": 1.2319, + "step": 8271 + }, + { + "epoch": 0.87, + "learning_rate": 1.0512961442124492e-06, + "loss": 1.2866, + "step": 8272 + }, + { + "epoch": 0.87, + "learning_rate": 1.0496630785262874e-06, + "loss": 1.365, + "step": 8273 + }, + { + "epoch": 0.87, + "learning_rate": 1.0480312119553015e-06, + "loss": 1.3054, + "step": 8274 + }, + { + "epoch": 0.87, + "learning_rate": 1.046400544718118e-06, + "loss": 1.3268, + "step": 8275 + }, + { + "epoch": 0.87, + "learning_rate": 1.0447710770332098e-06, + "loss": 1.3574, + "step": 8276 + }, + { + "epoch": 0.87, + "learning_rate": 1.0431428091188766e-06, + "loss": 1.371, + "step": 8277 + }, + { + "epoch": 0.87, + "learning_rate": 1.0415157411932698e-06, + "loss": 1.3201, + "step": 8278 + }, + { + "epoch": 0.87, + "learning_rate": 1.0398898734743734e-06, + "loss": 1.3135, + "step": 8279 + }, + { + "epoch": 0.87, + "learning_rate": 1.0382652061800102e-06, + "loss": 1.2796, + "step": 8280 + }, + { + "epoch": 0.87, + "learning_rate": 1.036641739527846e-06, + "loss": 1.3704, + "step": 8281 + }, + { + "epoch": 0.87, + "learning_rate": 1.0350194737353814e-06, + "loss": 1.2913, + "step": 8282 + }, + { + "epoch": 0.87, + "learning_rate": 1.03339840901996e-06, + "loss": 1.3408, + "step": 8283 + }, + { + "epoch": 0.87, + "learning_rate": 1.0317785455987638e-06, + "loss": 1.2652, + "step": 8284 + }, + { + "epoch": 0.87, + "learning_rate": 1.0301598836888105e-06, + "loss": 1.2724, + "step": 8285 + }, + { + "epoch": 0.87, + "learning_rate": 1.0285424235069586e-06, + "loss": 1.2985, + "step": 8286 + }, + { + "epoch": 0.87, + "learning_rate": 1.0269261652699115e-06, + "loss": 1.3631, + "step": 8287 + }, + { + "epoch": 0.87, + "learning_rate": 1.0253111091941992e-06, + "loss": 1.2494, + "step": 8288 + }, + { + "epoch": 0.87, + "learning_rate": 1.0236972554962022e-06, + "loss": 1.3331, + "step": 8289 + }, + { + "epoch": 0.87, + "learning_rate": 1.0220846043921351e-06, + "loss": 1.2884, + "step": 8290 + }, + { + "epoch": 0.87, + "learning_rate": 1.0204731560980496e-06, + "loss": 1.3488, + "step": 8291 + }, + { + "epoch": 0.87, + "learning_rate": 1.018862910829842e-06, + "loss": 1.2698, + "step": 8292 + }, + { + "epoch": 0.87, + "learning_rate": 1.0172538688032396e-06, + "loss": 1.2873, + "step": 8293 + }, + { + "epoch": 0.87, + "learning_rate": 1.0156460302338135e-06, + "loss": 1.3644, + "step": 8294 + }, + { + "epoch": 0.87, + "learning_rate": 1.0140393953369764e-06, + "loss": 1.3445, + "step": 8295 + }, + { + "epoch": 0.87, + "learning_rate": 1.0124339643279724e-06, + "loss": 1.3448, + "step": 8296 + }, + { + "epoch": 0.87, + "learning_rate": 1.0108297374218877e-06, + "loss": 1.2984, + "step": 8297 + }, + { + "epoch": 0.87, + "learning_rate": 1.009226714833652e-06, + "loss": 1.3224, + "step": 8298 + }, + { + "epoch": 0.87, + "learning_rate": 1.0076248967780245e-06, + "loss": 1.2924, + "step": 8299 + }, + { + "epoch": 0.87, + "learning_rate": 1.00602428346961e-06, + "loss": 1.2344, + "step": 8300 + }, + { + "epoch": 0.87, + "learning_rate": 1.004424875122848e-06, + "loss": 1.3089, + "step": 8301 + }, + { + "epoch": 0.87, + "learning_rate": 1.0028266719520174e-06, + "loss": 1.291, + "step": 8302 + }, + { + "epoch": 0.87, + "learning_rate": 1.0012296741712414e-06, + "loss": 1.3404, + "step": 8303 + }, + { + "epoch": 0.87, + "learning_rate": 9.996338819944706e-07, + "loss": 1.5152, + "step": 8304 + }, + { + "epoch": 0.87, + "learning_rate": 9.980392956355023e-07, + "loss": 1.3492, + "step": 8305 + }, + { + "epoch": 0.87, + "learning_rate": 9.96445915307973e-07, + "loss": 1.3056, + "step": 8306 + }, + { + "epoch": 0.87, + "learning_rate": 9.948537412253502e-07, + "loss": 1.3223, + "step": 8307 + }, + { + "epoch": 0.87, + "learning_rate": 9.93262773600946e-07, + "loss": 1.3295, + "step": 8308 + }, + { + "epoch": 0.87, + "learning_rate": 9.916730126479113e-07, + "loss": 1.3156, + "step": 8309 + }, + { + "epoch": 0.87, + "learning_rate": 9.900844585792301e-07, + "loss": 1.2701, + "step": 8310 + }, + { + "epoch": 0.87, + "learning_rate": 9.884971116077302e-07, + "loss": 1.3171, + "step": 8311 + }, + { + "epoch": 0.87, + "learning_rate": 9.869109719460735e-07, + "loss": 1.2599, + "step": 8312 + }, + { + "epoch": 0.87, + "learning_rate": 9.85326039806762e-07, + "loss": 1.2999, + "step": 8313 + }, + { + "epoch": 0.87, + "learning_rate": 9.837423154021385e-07, + "loss": 1.3691, + "step": 8314 + }, + { + "epoch": 0.87, + "learning_rate": 9.821597989443775e-07, + "loss": 1.279, + "step": 8315 + }, + { + "epoch": 0.87, + "learning_rate": 9.805784906454985e-07, + "loss": 1.2682, + "step": 8316 + }, + { + "epoch": 0.87, + "learning_rate": 9.789983907173562e-07, + "loss": 1.3321, + "step": 8317 + }, + { + "epoch": 0.87, + "learning_rate": 9.774194993716413e-07, + "loss": 1.326, + "step": 8318 + }, + { + "epoch": 0.87, + "learning_rate": 9.75841816819887e-07, + "loss": 1.2541, + "step": 8319 + }, + { + "epoch": 0.87, + "learning_rate": 9.742653432734594e-07, + "loss": 1.2871, + "step": 8320 + }, + { + "epoch": 0.87, + "learning_rate": 9.726900789435668e-07, + "loss": 1.2535, + "step": 8321 + }, + { + "epoch": 0.87, + "learning_rate": 9.711160240412564e-07, + "loss": 1.3008, + "step": 8322 + }, + { + "epoch": 0.87, + "learning_rate": 9.695431787774068e-07, + "loss": 1.2925, + "step": 8323 + }, + { + "epoch": 0.87, + "learning_rate": 9.679715433627424e-07, + "loss": 1.4127, + "step": 8324 + }, + { + "epoch": 0.87, + "learning_rate": 9.664011180078215e-07, + "loss": 1.2961, + "step": 8325 + }, + { + "epoch": 0.87, + "learning_rate": 9.64831902923038e-07, + "loss": 1.2446, + "step": 8326 + }, + { + "epoch": 0.87, + "learning_rate": 9.632638983186316e-07, + "loss": 1.3279, + "step": 8327 + }, + { + "epoch": 0.87, + "learning_rate": 9.616971044046686e-07, + "loss": 1.3128, + "step": 8328 + }, + { + "epoch": 0.87, + "learning_rate": 9.601315213910622e-07, + "loss": 1.2371, + "step": 8329 + }, + { + "epoch": 0.87, + "learning_rate": 9.585671494875614e-07, + "loss": 1.2844, + "step": 8330 + }, + { + "epoch": 0.87, + "learning_rate": 9.570039889037485e-07, + "loss": 1.3417, + "step": 8331 + }, + { + "epoch": 0.87, + "learning_rate": 9.554420398490494e-07, + "loss": 1.3149, + "step": 8332 + }, + { + "epoch": 0.87, + "learning_rate": 9.538813025327266e-07, + "loss": 1.2588, + "step": 8333 + }, + { + "epoch": 0.87, + "learning_rate": 9.523217771638748e-07, + "loss": 1.2999, + "step": 8334 + }, + { + "epoch": 0.87, + "learning_rate": 9.507634639514319e-07, + "loss": 1.4602, + "step": 8335 + }, + { + "epoch": 0.87, + "learning_rate": 9.492063631041737e-07, + "loss": 1.3576, + "step": 8336 + }, + { + "epoch": 0.87, + "learning_rate": 9.476504748307091e-07, + "loss": 1.3507, + "step": 8337 + }, + { + "epoch": 0.87, + "learning_rate": 9.460957993394903e-07, + "loss": 1.3293, + "step": 8338 + }, + { + "epoch": 0.87, + "learning_rate": 9.445423368387995e-07, + "loss": 1.3586, + "step": 8339 + }, + { + "epoch": 0.87, + "learning_rate": 9.429900875367637e-07, + "loss": 1.4114, + "step": 8340 + }, + { + "epoch": 0.87, + "learning_rate": 9.414390516413452e-07, + "loss": 1.3932, + "step": 8341 + }, + { + "epoch": 0.87, + "learning_rate": 9.398892293603401e-07, + "loss": 1.357, + "step": 8342 + }, + { + "epoch": 0.87, + "learning_rate": 9.383406209013856e-07, + "loss": 1.2858, + "step": 8343 + }, + { + "epoch": 0.88, + "learning_rate": 9.367932264719581e-07, + "loss": 1.2484, + "step": 8344 + }, + { + "epoch": 0.88, + "learning_rate": 9.352470462793651e-07, + "loss": 1.3251, + "step": 8345 + }, + { + "epoch": 0.88, + "learning_rate": 9.337020805307583e-07, + "loss": 1.2653, + "step": 8346 + }, + { + "epoch": 0.88, + "learning_rate": 9.321583294331204e-07, + "loss": 1.2925, + "step": 8347 + }, + { + "epoch": 0.88, + "learning_rate": 9.306157931932758e-07, + "loss": 1.3092, + "step": 8348 + }, + { + "epoch": 0.88, + "learning_rate": 9.290744720178857e-07, + "loss": 1.3858, + "step": 8349 + }, + { + "epoch": 0.88, + "learning_rate": 9.275343661134451e-07, + "loss": 1.2612, + "step": 8350 + }, + { + "epoch": 0.88, + "learning_rate": 9.259954756862899e-07, + "loss": 1.3053, + "step": 8351 + }, + { + "epoch": 0.88, + "learning_rate": 9.244578009425942e-07, + "loss": 1.3401, + "step": 8352 + }, + { + "epoch": 0.88, + "learning_rate": 9.229213420883621e-07, + "loss": 1.3442, + "step": 8353 + }, + { + "epoch": 0.88, + "learning_rate": 9.213860993294421e-07, + "loss": 1.3501, + "step": 8354 + }, + { + "epoch": 0.88, + "learning_rate": 9.198520728715199e-07, + "loss": 1.2916, + "step": 8355 + }, + { + "epoch": 0.88, + "learning_rate": 9.18319262920111e-07, + "loss": 1.3291, + "step": 8356 + }, + { + "epoch": 0.88, + "learning_rate": 9.167876696805767e-07, + "loss": 1.3369, + "step": 8357 + }, + { + "epoch": 0.88, + "learning_rate": 9.152572933581061e-07, + "loss": 1.3324, + "step": 8358 + }, + { + "epoch": 0.88, + "eval_loss": 1.3944451808929443, + "eval_runtime": 77.5126, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 8358 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 3.7390687403424665e+20, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-8358/training_args.bin b/checkpoint-8358/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-8358/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-8756/config.json b/checkpoint-8756/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-8756/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-8756/generation_config.json b/checkpoint-8756/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-8756/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-8756/model-00001-of-00003.safetensors b/checkpoint-8756/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eb9e360ab802fb229dbdb6b35b8776890e52e746 --- /dev/null +++ b/checkpoint-8756/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:054909732cc67540eb1bc050f87f96ed6df25b7f45605bb4af2d6f03c06a9800 +size 4943162336 diff --git a/checkpoint-8756/model-00002-of-00003.safetensors b/checkpoint-8756/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c35f4998772b60eb5628e9b31ab8d625ac73ee6f --- /dev/null +++ b/checkpoint-8756/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5705452bf3290f0d97908f659be29a95e38bf40541017b95101acb8cec05863b +size 4999819336 diff --git a/checkpoint-8756/model-00003-of-00003.safetensors b/checkpoint-8756/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..23b3b5fc99e8949faf43a83200d7991e2ffca200 --- /dev/null +++ b/checkpoint-8756/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e501e3064dc83e8d9b4454c548adeb155273585fcce724d1490bf82e3b730cf +size 4540516344 diff --git a/checkpoint-8756/model.safetensors.index.json b/checkpoint-8756/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-8756/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-8756/optimizer.pt b/checkpoint-8756/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..a5af906b61c7baec711ede181e9cb3d7377df121 --- /dev/null +++ b/checkpoint-8756/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33acb317a5e588d65eb6fc134c56c2aea24caf1d1fa74a63fed5b1502a908f80 +size 14512103560 diff --git a/checkpoint-8756/rng_state_0.pth b/checkpoint-8756/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..664379f814c1d5323360c9ab7be65ba32284b8b1 --- /dev/null +++ b/checkpoint-8756/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb456f4fc4058353f0fe61e36bec6c29ff9749fbc9a234579b7a4ade46b24e57 +size 15984 diff --git a/checkpoint-8756/rng_state_1.pth b/checkpoint-8756/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..92a568be081b08d5f56c8195eca156f8993863dc --- /dev/null +++ b/checkpoint-8756/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57f6b3eaee130f616e6f627c7cd9977ea0300f868e1e032b92ecee6592ad7db4 +size 15984 diff --git a/checkpoint-8756/rng_state_2.pth b/checkpoint-8756/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..d8b2005e64998287a627dbcfb36dbe62359151f0 --- /dev/null +++ b/checkpoint-8756/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d15e0cb87c4514f01fec418ddd5986a68fb59e04c1e57567145e89d234075413 +size 15984 diff --git a/checkpoint-8756/rng_state_3.pth b/checkpoint-8756/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..886e4db5619c677b20e503204d052e270da97c3f --- /dev/null +++ b/checkpoint-8756/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7ebba5744da6b7bdff467af62db592885ae35f6cd318e7bf24ba309bd7ff5f1 +size 15984 diff --git a/checkpoint-8756/rng_state_4.pth b/checkpoint-8756/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..8ae0b4c943ce5fedac0bd774eab31980f6a78601 --- /dev/null +++ b/checkpoint-8756/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3ee064c89d3c6cd6a11b4dc9d3e90682d858b4205ed6f1c8c18ec8ff25dd69f +size 15984 diff --git a/checkpoint-8756/rng_state_5.pth b/checkpoint-8756/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..a2fcef585576e8622ea8261b7b90ea9eb5082efa --- /dev/null +++ b/checkpoint-8756/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd2db6574fecdf700e93419061f0620ceb867b0f29772cd68d9a1e4fd3efe7b4 +size 15984 diff --git a/checkpoint-8756/rng_state_6.pth b/checkpoint-8756/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..7bb81951e4a126d01ffbc9a7ce59b0d0b0e340c7 --- /dev/null +++ b/checkpoint-8756/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e7a571a771ed85709e0ff953b4264ea2339395123c86dd8b1e1f8d2d2c3b31c +size 15984 diff --git a/checkpoint-8756/rng_state_7.pth b/checkpoint-8756/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..f050e70a6d6c2570127f31edd20adc2ffefb28b7 --- /dev/null +++ b/checkpoint-8756/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f417ff0fbe40614aa3732b1414158c1582576ed65616350232e29afbd0792a87 +size 15984 diff --git a/checkpoint-8756/scheduler.pt b/checkpoint-8756/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..a196403ad417c45cbcfa74548c35b6fdc8ec89f7 --- /dev/null +++ b/checkpoint-8756/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71da86bac530f461fcf1ba672c6df8a3d271b34f4b98056da843cb38d181e98d +size 1064 diff --git a/checkpoint-8756/special_tokens_map.json b/checkpoint-8756/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-8756/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-8756/tokenizer.model b/checkpoint-8756/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-8756/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-8756/tokenizer_config.json b/checkpoint-8756/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-8756/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-8756/trainer_state.json b/checkpoint-8756/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..f11b4bace90fe256c8d32f04379ba23cd1ab6ee9 --- /dev/null +++ b/checkpoint-8756/trainer_state.json @@ -0,0 +1,52908 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.9182046979865772, + "eval_steps": 199, + "global_step": 8756, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + }, + { + "epoch": 0.21, + "learning_rate": 1.928689129323009e-05, + "loss": 1.421, + "step": 1991 + }, + { + "epoch": 0.21, + "learning_rate": 1.928553323396003e-05, + "loss": 1.5625, + "step": 1992 + }, + { + "epoch": 0.21, + "learning_rate": 1.92841739306671e-05, + "loss": 1.5198, + "step": 1993 + }, + { + "epoch": 0.21, + "learning_rate": 1.9282813383533415e-05, + "loss": 1.5116, + "step": 1994 + }, + { + "epoch": 0.21, + "learning_rate": 1.9281451592741247e-05, + "loss": 1.4306, + "step": 1995 + }, + { + "epoch": 0.21, + "learning_rate": 1.9280088558473046e-05, + "loss": 1.5425, + "step": 1996 + }, + { + "epoch": 0.21, + "learning_rate": 1.9278724280911424e-05, + "loss": 1.4972, + "step": 1997 + }, + { + "epoch": 0.21, + "learning_rate": 1.9277358760239156e-05, + "loss": 1.5185, + "step": 1998 + }, + { + "epoch": 0.21, + "learning_rate": 1.9275991996639188e-05, + "loss": 1.5187, + "step": 1999 + }, + { + "epoch": 0.21, + "learning_rate": 1.927462399029463e-05, + "loss": 1.4325, + "step": 2000 + }, + { + "epoch": 0.21, + "learning_rate": 1.9273254741388763e-05, + "loss": 1.4397, + "step": 2001 + }, + { + "epoch": 0.21, + "learning_rate": 1.927188425010503e-05, + "loss": 1.5319, + "step": 2002 + }, + { + "epoch": 0.21, + "learning_rate": 1.9270512516627042e-05, + "loss": 1.5664, + "step": 2003 + }, + { + "epoch": 0.21, + "learning_rate": 1.9269139541138574e-05, + "loss": 1.5227, + "step": 2004 + }, + { + "epoch": 0.21, + "learning_rate": 1.926776532382357e-05, + "loss": 1.5187, + "step": 2005 + }, + { + "epoch": 0.21, + "learning_rate": 1.9266389864866134e-05, + "loss": 1.4029, + "step": 2006 + }, + { + "epoch": 0.21, + "learning_rate": 1.9265013164450557e-05, + "loss": 1.387, + "step": 2007 + }, + { + "epoch": 0.21, + "learning_rate": 1.9263635222761268e-05, + "loss": 1.5047, + "step": 2008 + }, + { + "epoch": 0.21, + "learning_rate": 1.9262256039982882e-05, + "loss": 1.4816, + "step": 2009 + }, + { + "epoch": 0.21, + "learning_rate": 1.9260875616300172e-05, + "loss": 1.4607, + "step": 2010 + }, + { + "epoch": 0.21, + "learning_rate": 1.9259493951898084e-05, + "loss": 1.628, + "step": 2011 + }, + { + "epoch": 0.21, + "learning_rate": 1.9258111046961714e-05, + "loss": 1.4149, + "step": 2012 + }, + { + "epoch": 0.21, + "learning_rate": 1.925672690167635e-05, + "loss": 1.5303, + "step": 2013 + }, + { + "epoch": 0.21, + "learning_rate": 1.925534151622742e-05, + "loss": 1.5198, + "step": 2014 + }, + { + "epoch": 0.21, + "learning_rate": 1.9253954890800535e-05, + "loss": 1.6422, + "step": 2015 + }, + { + "epoch": 0.21, + "learning_rate": 1.925256702558147e-05, + "loss": 1.4738, + "step": 2016 + }, + { + "epoch": 0.21, + "learning_rate": 1.925117792075616e-05, + "loss": 1.4752, + "step": 2017 + }, + { + "epoch": 0.21, + "learning_rate": 1.9249787576510713e-05, + "loss": 1.4547, + "step": 2018 + }, + { + "epoch": 0.21, + "learning_rate": 1.924839599303139e-05, + "loss": 1.4864, + "step": 2019 + }, + { + "epoch": 0.21, + "learning_rate": 1.9247003170504638e-05, + "loss": 1.5037, + "step": 2020 + }, + { + "epoch": 0.21, + "learning_rate": 1.9245609109117053e-05, + "loss": 1.5089, + "step": 2021 + }, + { + "epoch": 0.21, + "learning_rate": 1.924421380905541e-05, + "loss": 1.5616, + "step": 2022 + }, + { + "epoch": 0.21, + "learning_rate": 1.9242817270506634e-05, + "loss": 1.4592, + "step": 2023 + }, + { + "epoch": 0.21, + "learning_rate": 1.9241419493657832e-05, + "loss": 1.5592, + "step": 2024 + }, + { + "epoch": 0.21, + "learning_rate": 1.924002047869627e-05, + "loss": 1.4897, + "step": 2025 + }, + { + "epoch": 0.21, + "learning_rate": 1.9238620225809375e-05, + "loss": 1.4743, + "step": 2026 + }, + { + "epoch": 0.21, + "learning_rate": 1.923721873518475e-05, + "loss": 1.4686, + "step": 2027 + }, + { + "epoch": 0.21, + "learning_rate": 1.923581600701016e-05, + "loss": 1.461, + "step": 2028 + }, + { + "epoch": 0.21, + "learning_rate": 1.9234412041473528e-05, + "loss": 1.6622, + "step": 2029 + }, + { + "epoch": 0.21, + "learning_rate": 1.9233006838762955e-05, + "loss": 1.4707, + "step": 2030 + }, + { + "epoch": 0.21, + "learning_rate": 1.92316003990667e-05, + "loss": 1.5566, + "step": 2031 + }, + { + "epoch": 0.21, + "learning_rate": 1.9230192722573188e-05, + "loss": 1.4881, + "step": 2032 + }, + { + "epoch": 0.21, + "learning_rate": 1.9228783809471015e-05, + "loss": 1.6124, + "step": 2033 + }, + { + "epoch": 0.21, + "learning_rate": 1.9227373659948937e-05, + "loss": 1.3508, + "step": 2034 + }, + { + "epoch": 0.21, + "learning_rate": 1.9225962274195876e-05, + "loss": 1.4418, + "step": 2035 + }, + { + "epoch": 0.21, + "learning_rate": 1.9224549652400927e-05, + "loss": 1.3954, + "step": 2036 + }, + { + "epoch": 0.21, + "learning_rate": 1.922313579475334e-05, + "loss": 1.4798, + "step": 2037 + }, + { + "epoch": 0.21, + "learning_rate": 1.922172070144254e-05, + "loss": 1.4556, + "step": 2038 + }, + { + "epoch": 0.21, + "learning_rate": 1.922030437265811e-05, + "loss": 1.4987, + "step": 2039 + }, + { + "epoch": 0.21, + "learning_rate": 1.9218886808589796e-05, + "loss": 1.4857, + "step": 2040 + }, + { + "epoch": 0.21, + "learning_rate": 1.9217468009427527e-05, + "loss": 1.5289, + "step": 2041 + }, + { + "epoch": 0.21, + "learning_rate": 1.921604797536138e-05, + "loss": 1.5267, + "step": 2042 + }, + { + "epoch": 0.21, + "learning_rate": 1.9214626706581598e-05, + "loss": 1.4655, + "step": 2043 + }, + { + "epoch": 0.21, + "learning_rate": 1.9213204203278602e-05, + "loss": 1.4598, + "step": 2044 + }, + { + "epoch": 0.21, + "learning_rate": 1.9211780465642973e-05, + "loss": 1.4766, + "step": 2045 + }, + { + "epoch": 0.21, + "learning_rate": 1.921035549386545e-05, + "loss": 1.5148, + "step": 2046 + }, + { + "epoch": 0.21, + "learning_rate": 1.9208929288136933e-05, + "loss": 1.5567, + "step": 2047 + }, + { + "epoch": 0.21, + "learning_rate": 1.920750184864852e-05, + "loss": 1.4868, + "step": 2048 + }, + { + "epoch": 0.21, + "learning_rate": 1.920607317559143e-05, + "loss": 1.4752, + "step": 2049 + }, + { + "epoch": 0.21, + "learning_rate": 1.920464326915708e-05, + "loss": 1.4882, + "step": 2050 + }, + { + "epoch": 0.22, + "learning_rate": 1.9203212129537035e-05, + "loss": 1.5933, + "step": 2051 + }, + { + "epoch": 0.22, + "learning_rate": 1.9201779756923037e-05, + "loss": 1.4891, + "step": 2052 + }, + { + "epoch": 0.22, + "learning_rate": 1.9200346151506983e-05, + "loss": 1.4486, + "step": 2053 + }, + { + "epoch": 0.22, + "learning_rate": 1.9198911313480938e-05, + "loss": 1.5091, + "step": 2054 + }, + { + "epoch": 0.22, + "learning_rate": 1.919747524303714e-05, + "loss": 1.4385, + "step": 2055 + }, + { + "epoch": 0.22, + "learning_rate": 1.9196037940367974e-05, + "loss": 1.4104, + "step": 2056 + }, + { + "epoch": 0.22, + "learning_rate": 1.9194599405666015e-05, + "loss": 1.4483, + "step": 2057 + }, + { + "epoch": 0.22, + "learning_rate": 1.9193159639123976e-05, + "loss": 1.4592, + "step": 2058 + }, + { + "epoch": 0.22, + "learning_rate": 1.919171864093476e-05, + "loss": 1.4975, + "step": 2059 + }, + { + "epoch": 0.22, + "learning_rate": 1.9190276411291423e-05, + "loss": 1.4727, + "step": 2060 + }, + { + "epoch": 0.22, + "learning_rate": 1.9188832950387178e-05, + "loss": 1.4791, + "step": 2061 + }, + { + "epoch": 0.22, + "learning_rate": 1.9187388258415423e-05, + "loss": 1.3806, + "step": 2062 + }, + { + "epoch": 0.22, + "learning_rate": 1.9185942335569697e-05, + "loss": 1.4514, + "step": 2063 + }, + { + "epoch": 0.22, + "learning_rate": 1.9184495182043727e-05, + "loss": 1.4389, + "step": 2064 + }, + { + "epoch": 0.22, + "learning_rate": 1.918304679803139e-05, + "loss": 1.5088, + "step": 2065 + }, + { + "epoch": 0.22, + "learning_rate": 1.9181597183726733e-05, + "loss": 1.4665, + "step": 2066 + }, + { + "epoch": 0.22, + "learning_rate": 1.9180146339323966e-05, + "loss": 1.489, + "step": 2067 + }, + { + "epoch": 0.22, + "learning_rate": 1.9178694265017466e-05, + "loss": 1.5215, + "step": 2068 + }, + { + "epoch": 0.22, + "learning_rate": 1.9177240961001775e-05, + "loss": 1.5152, + "step": 2069 + }, + { + "epoch": 0.22, + "learning_rate": 1.9175786427471594e-05, + "loss": 1.4418, + "step": 2070 + }, + { + "epoch": 0.22, + "learning_rate": 1.91743306646218e-05, + "loss": 1.5001, + "step": 2071 + }, + { + "epoch": 0.22, + "learning_rate": 1.9172873672647417e-05, + "loss": 1.4879, + "step": 2072 + }, + { + "epoch": 0.22, + "learning_rate": 1.917141545174366e-05, + "loss": 1.5299, + "step": 2073 + }, + { + "epoch": 0.22, + "learning_rate": 1.9169956002105877e-05, + "loss": 1.4602, + "step": 2074 + }, + { + "epoch": 0.22, + "learning_rate": 1.9168495323929605e-05, + "loss": 1.4921, + "step": 2075 + }, + { + "epoch": 0.22, + "learning_rate": 1.916703341741054e-05, + "loss": 1.4659, + "step": 2076 + }, + { + "epoch": 0.22, + "learning_rate": 1.9165570282744534e-05, + "loss": 1.4707, + "step": 2077 + }, + { + "epoch": 0.22, + "learning_rate": 1.9164105920127613e-05, + "loss": 1.5354, + "step": 2078 + }, + { + "epoch": 0.22, + "learning_rate": 1.9162640329755962e-05, + "loss": 1.526, + "step": 2079 + }, + { + "epoch": 0.22, + "learning_rate": 1.916117351182593e-05, + "loss": 1.6424, + "step": 2080 + }, + { + "epoch": 0.22, + "learning_rate": 1.915970546653404e-05, + "loss": 1.5048, + "step": 2081 + }, + { + "epoch": 0.22, + "learning_rate": 1.915823619407697e-05, + "loss": 1.5344, + "step": 2082 + }, + { + "epoch": 0.22, + "learning_rate": 1.915676569465156e-05, + "loss": 1.4604, + "step": 2083 + }, + { + "epoch": 0.22, + "learning_rate": 1.9155293968454826e-05, + "loss": 1.4929, + "step": 2084 + }, + { + "epoch": 0.22, + "learning_rate": 1.9153821015683937e-05, + "loss": 1.4106, + "step": 2085 + }, + { + "epoch": 0.22, + "learning_rate": 1.915234683653623e-05, + "loss": 1.4146, + "step": 2086 + }, + { + "epoch": 0.22, + "learning_rate": 1.9150871431209207e-05, + "loss": 1.4481, + "step": 2087 + }, + { + "epoch": 0.22, + "learning_rate": 1.914939479990054e-05, + "loss": 1.5206, + "step": 2088 + }, + { + "epoch": 0.22, + "learning_rate": 1.9147916942808054e-05, + "loss": 1.5073, + "step": 2089 + }, + { + "epoch": 0.22, + "learning_rate": 1.9146437860129745e-05, + "loss": 1.5196, + "step": 2090 + }, + { + "epoch": 0.22, + "learning_rate": 1.9144957552063775e-05, + "loss": 1.5389, + "step": 2091 + }, + { + "epoch": 0.22, + "learning_rate": 1.9143476018808463e-05, + "loss": 1.5207, + "step": 2092 + }, + { + "epoch": 0.22, + "learning_rate": 1.9141993260562298e-05, + "loss": 1.3717, + "step": 2093 + }, + { + "epoch": 0.22, + "learning_rate": 1.9140509277523937e-05, + "loss": 1.471, + "step": 2094 + }, + { + "epoch": 0.22, + "learning_rate": 1.9139024069892185e-05, + "loss": 1.4553, + "step": 2095 + }, + { + "epoch": 0.22, + "learning_rate": 1.9137537637866027e-05, + "loss": 1.5311, + "step": 2096 + }, + { + "epoch": 0.22, + "learning_rate": 1.9136049981644614e-05, + "loss": 1.4369, + "step": 2097 + }, + { + "epoch": 0.22, + "learning_rate": 1.913456110142724e-05, + "loss": 1.4528, + "step": 2098 + }, + { + "epoch": 0.22, + "learning_rate": 1.9133070997413384e-05, + "loss": 1.5294, + "step": 2099 + }, + { + "epoch": 0.22, + "learning_rate": 1.9131579669802685e-05, + "loss": 1.4588, + "step": 2100 + }, + { + "epoch": 0.22, + "learning_rate": 1.9130087118794934e-05, + "loss": 1.443, + "step": 2101 + }, + { + "epoch": 0.22, + "learning_rate": 1.9128593344590102e-05, + "loss": 1.4876, + "step": 2102 + }, + { + "epoch": 0.22, + "learning_rate": 1.912709834738831e-05, + "loss": 1.4874, + "step": 2103 + }, + { + "epoch": 0.22, + "learning_rate": 1.9125602127389856e-05, + "loss": 1.4966, + "step": 2104 + }, + { + "epoch": 0.22, + "learning_rate": 1.912410468479519e-05, + "loss": 1.5747, + "step": 2105 + }, + { + "epoch": 0.22, + "learning_rate": 1.9122606019804933e-05, + "loss": 1.4025, + "step": 2106 + }, + { + "epoch": 0.22, + "learning_rate": 1.912110613261987e-05, + "loss": 1.4755, + "step": 2107 + }, + { + "epoch": 0.22, + "learning_rate": 1.911960502344094e-05, + "loss": 1.4739, + "step": 2108 + }, + { + "epoch": 0.22, + "learning_rate": 1.911810269246926e-05, + "loss": 1.4992, + "step": 2109 + }, + { + "epoch": 0.22, + "learning_rate": 1.91165991399061e-05, + "loss": 1.4435, + "step": 2110 + }, + { + "epoch": 0.22, + "learning_rate": 1.91150943659529e-05, + "loss": 1.4918, + "step": 2111 + }, + { + "epoch": 0.22, + "learning_rate": 1.9113588370811258e-05, + "loss": 1.3818, + "step": 2112 + }, + { + "epoch": 0.22, + "learning_rate": 1.911208115468294e-05, + "loss": 1.5105, + "step": 2113 + }, + { + "epoch": 0.22, + "learning_rate": 1.9110572717769878e-05, + "loss": 1.6634, + "step": 2114 + }, + { + "epoch": 0.22, + "learning_rate": 1.9109063060274158e-05, + "loss": 1.5028, + "step": 2115 + }, + { + "epoch": 0.22, + "learning_rate": 1.9107552182398037e-05, + "loss": 1.6657, + "step": 2116 + }, + { + "epoch": 0.22, + "learning_rate": 1.9106040084343935e-05, + "loss": 1.5481, + "step": 2117 + }, + { + "epoch": 0.22, + "learning_rate": 1.910452676631444e-05, + "loss": 1.4505, + "step": 2118 + }, + { + "epoch": 0.22, + "learning_rate": 1.9103012228512284e-05, + "loss": 1.5173, + "step": 2119 + }, + { + "epoch": 0.22, + "learning_rate": 1.9101496471140385e-05, + "loss": 1.3788, + "step": 2120 + }, + { + "epoch": 0.22, + "learning_rate": 1.9099979494401814e-05, + "loss": 1.4649, + "step": 2121 + }, + { + "epoch": 0.22, + "learning_rate": 1.9098461298499805e-05, + "loss": 1.4204, + "step": 2122 + }, + { + "epoch": 0.22, + "learning_rate": 1.9096941883637766e-05, + "loss": 1.4439, + "step": 2123 + }, + { + "epoch": 0.22, + "learning_rate": 1.909542125001925e-05, + "loss": 1.6615, + "step": 2124 + }, + { + "epoch": 0.22, + "learning_rate": 1.9093899397847985e-05, + "loss": 1.4763, + "step": 2125 + }, + { + "epoch": 0.22, + "learning_rate": 1.909237632732786e-05, + "loss": 1.5353, + "step": 2126 + }, + { + "epoch": 0.22, + "learning_rate": 1.909085203866293e-05, + "loss": 1.442, + "step": 2127 + }, + { + "epoch": 0.22, + "learning_rate": 1.9089326532057408e-05, + "loss": 1.4782, + "step": 2128 + }, + { + "epoch": 0.22, + "learning_rate": 1.908779980771567e-05, + "loss": 1.4933, + "step": 2129 + }, + { + "epoch": 0.22, + "learning_rate": 1.9086271865842264e-05, + "loss": 1.5285, + "step": 2130 + }, + { + "epoch": 0.22, + "learning_rate": 1.9084742706641894e-05, + "loss": 1.4736, + "step": 2131 + }, + { + "epoch": 0.22, + "learning_rate": 1.9083212330319427e-05, + "loss": 1.4496, + "step": 2132 + }, + { + "epoch": 0.22, + "learning_rate": 1.908168073707989e-05, + "loss": 1.5099, + "step": 2133 + }, + { + "epoch": 0.22, + "learning_rate": 1.9080147927128483e-05, + "loss": 1.5235, + "step": 2134 + }, + { + "epoch": 0.22, + "learning_rate": 1.9078613900670556e-05, + "loss": 1.4769, + "step": 2135 + }, + { + "epoch": 0.22, + "learning_rate": 1.907707865791164e-05, + "loss": 1.5771, + "step": 2136 + }, + { + "epoch": 0.22, + "learning_rate": 1.907554219905741e-05, + "loss": 1.5116, + "step": 2137 + }, + { + "epoch": 0.22, + "learning_rate": 1.907400452431371e-05, + "loss": 1.5161, + "step": 2138 + }, + { + "epoch": 0.22, + "learning_rate": 1.9072465633886557e-05, + "loss": 1.4356, + "step": 2139 + }, + { + "epoch": 0.22, + "learning_rate": 1.9070925527982117e-05, + "loss": 1.509, + "step": 2140 + }, + { + "epoch": 0.22, + "learning_rate": 1.9069384206806723e-05, + "loss": 1.4681, + "step": 2141 + }, + { + "epoch": 0.22, + "learning_rate": 1.9067841670566883e-05, + "loss": 1.5254, + "step": 2142 + }, + { + "epoch": 0.22, + "learning_rate": 1.9066297919469242e-05, + "loss": 1.4797, + "step": 2143 + }, + { + "epoch": 0.22, + "learning_rate": 1.9064752953720636e-05, + "loss": 1.3996, + "step": 2144 + }, + { + "epoch": 0.22, + "learning_rate": 1.9063206773528042e-05, + "loss": 1.4457, + "step": 2145 + }, + { + "epoch": 0.23, + "learning_rate": 1.9061659379098617e-05, + "loss": 1.5126, + "step": 2146 + }, + { + "epoch": 0.23, + "learning_rate": 1.9060110770639664e-05, + "loss": 1.5925, + "step": 2147 + }, + { + "epoch": 0.23, + "learning_rate": 1.905856094835866e-05, + "loss": 1.5146, + "step": 2148 + }, + { + "epoch": 0.23, + "learning_rate": 1.905700991246324e-05, + "loss": 1.7256, + "step": 2149 + }, + { + "epoch": 0.23, + "learning_rate": 1.90554576631612e-05, + "loss": 1.57, + "step": 2150 + }, + { + "epoch": 0.23, + "learning_rate": 1.905390420066051e-05, + "loss": 1.3722, + "step": 2151 + }, + { + "epoch": 0.23, + "learning_rate": 1.9052349525169292e-05, + "loss": 1.3999, + "step": 2152 + }, + { + "epoch": 0.23, + "learning_rate": 1.9050793636895828e-05, + "loss": 1.586, + "step": 2153 + }, + { + "epoch": 0.23, + "learning_rate": 1.9049236536048567e-05, + "loss": 1.4884, + "step": 2154 + }, + { + "epoch": 0.23, + "learning_rate": 1.9047678222836127e-05, + "loss": 1.5898, + "step": 2155 + }, + { + "epoch": 0.23, + "learning_rate": 1.9046118697467278e-05, + "loss": 1.569, + "step": 2156 + }, + { + "epoch": 0.23, + "learning_rate": 1.904455796015095e-05, + "loss": 1.5592, + "step": 2157 + }, + { + "epoch": 0.23, + "learning_rate": 1.9042996011096253e-05, + "loss": 1.597, + "step": 2158 + }, + { + "epoch": 0.23, + "learning_rate": 1.904143285051244e-05, + "loss": 1.422, + "step": 2159 + }, + { + "epoch": 0.23, + "learning_rate": 1.903986847860894e-05, + "loss": 1.519, + "step": 2160 + }, + { + "epoch": 0.23, + "learning_rate": 1.9038302895595334e-05, + "loss": 1.5197, + "step": 2161 + }, + { + "epoch": 0.23, + "learning_rate": 1.903673610168137e-05, + "loss": 1.4655, + "step": 2162 + }, + { + "epoch": 0.23, + "learning_rate": 1.9035168097076965e-05, + "loss": 1.3909, + "step": 2163 + }, + { + "epoch": 0.23, + "learning_rate": 1.903359888199218e-05, + "loss": 1.4877, + "step": 2164 + }, + { + "epoch": 0.23, + "learning_rate": 1.903202845663726e-05, + "loss": 1.5123, + "step": 2165 + }, + { + "epoch": 0.23, + "learning_rate": 1.9030456821222593e-05, + "loss": 1.4906, + "step": 2166 + }, + { + "epoch": 0.23, + "learning_rate": 1.9028883975958745e-05, + "loss": 1.4574, + "step": 2167 + }, + { + "epoch": 0.23, + "learning_rate": 1.9027309921056435e-05, + "loss": 1.4571, + "step": 2168 + }, + { + "epoch": 0.23, + "learning_rate": 1.902573465672654e-05, + "loss": 1.4281, + "step": 2169 + }, + { + "epoch": 0.23, + "learning_rate": 1.9024158183180116e-05, + "loss": 1.5057, + "step": 2170 + }, + { + "epoch": 0.23, + "learning_rate": 1.902258050062836e-05, + "loss": 1.4514, + "step": 2171 + }, + { + "epoch": 0.23, + "learning_rate": 1.9021001609282646e-05, + "loss": 1.5055, + "step": 2172 + }, + { + "epoch": 0.23, + "learning_rate": 1.9019421509354505e-05, + "loss": 1.4578, + "step": 2173 + }, + { + "epoch": 0.23, + "learning_rate": 1.9017840201055625e-05, + "loss": 1.459, + "step": 2174 + }, + { + "epoch": 0.23, + "learning_rate": 1.9016257684597864e-05, + "loss": 1.5059, + "step": 2175 + }, + { + "epoch": 0.23, + "learning_rate": 1.901467396019324e-05, + "loss": 1.57, + "step": 2176 + }, + { + "epoch": 0.23, + "learning_rate": 1.901308902805393e-05, + "loss": 1.4924, + "step": 2177 + }, + { + "epoch": 0.23, + "learning_rate": 1.9011502888392273e-05, + "loss": 1.4979, + "step": 2178 + }, + { + "epoch": 0.23, + "learning_rate": 1.900991554142077e-05, + "loss": 1.5321, + "step": 2179 + }, + { + "epoch": 0.23, + "learning_rate": 1.9008326987352093e-05, + "loss": 1.493, + "step": 2180 + }, + { + "epoch": 0.23, + "learning_rate": 1.9006737226399056e-05, + "loss": 1.5111, + "step": 2181 + }, + { + "epoch": 0.23, + "learning_rate": 1.900514625877465e-05, + "loss": 1.4154, + "step": 2182 + }, + { + "epoch": 0.23, + "learning_rate": 1.900355408469203e-05, + "loss": 1.4934, + "step": 2183 + }, + { + "epoch": 0.23, + "learning_rate": 1.90019607043645e-05, + "loss": 1.5975, + "step": 2184 + }, + { + "epoch": 0.23, + "learning_rate": 1.9000366118005532e-05, + "loss": 1.3537, + "step": 2185 + }, + { + "epoch": 0.23, + "learning_rate": 1.899877032582876e-05, + "loss": 1.4583, + "step": 2186 + }, + { + "epoch": 0.23, + "learning_rate": 1.8997173328047984e-05, + "loss": 1.4586, + "step": 2187 + }, + { + "epoch": 0.23, + "learning_rate": 1.8995575124877156e-05, + "loss": 1.4774, + "step": 2188 + }, + { + "epoch": 0.23, + "learning_rate": 1.8993975716530394e-05, + "loss": 1.5025, + "step": 2189 + }, + { + "epoch": 0.23, + "eval_loss": 1.5263344049453735, + "eval_runtime": 77.1492, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 2189 + }, + { + "epoch": 0.23, + "learning_rate": 1.899237510322198e-05, + "loss": 1.5438, + "step": 2190 + }, + { + "epoch": 0.23, + "learning_rate": 1.899077328516635e-05, + "loss": 1.5181, + "step": 2191 + }, + { + "epoch": 0.23, + "learning_rate": 1.8989170262578112e-05, + "loss": 1.4454, + "step": 2192 + }, + { + "epoch": 0.23, + "learning_rate": 1.8987566035672028e-05, + "loss": 1.4882, + "step": 2193 + }, + { + "epoch": 0.23, + "learning_rate": 1.8985960604663026e-05, + "loss": 1.5073, + "step": 2194 + }, + { + "epoch": 0.23, + "learning_rate": 1.8984353969766187e-05, + "loss": 1.4478, + "step": 2195 + }, + { + "epoch": 0.23, + "learning_rate": 1.8982746131196763e-05, + "loss": 1.4768, + "step": 2196 + }, + { + "epoch": 0.23, + "learning_rate": 1.8981137089170162e-05, + "loss": 1.5116, + "step": 2197 + }, + { + "epoch": 0.23, + "learning_rate": 1.8979526843901952e-05, + "loss": 1.4202, + "step": 2198 + }, + { + "epoch": 0.23, + "learning_rate": 1.8977915395607867e-05, + "loss": 1.4736, + "step": 2199 + }, + { + "epoch": 0.23, + "learning_rate": 1.89763027445038e-05, + "loss": 1.4489, + "step": 2200 + }, + { + "epoch": 0.23, + "learning_rate": 1.8974688890805804e-05, + "loss": 1.4512, + "step": 2201 + }, + { + "epoch": 0.23, + "learning_rate": 1.897307383473009e-05, + "loss": 1.5091, + "step": 2202 + }, + { + "epoch": 0.23, + "learning_rate": 1.897145757649304e-05, + "loss": 1.5512, + "step": 2203 + }, + { + "epoch": 0.23, + "learning_rate": 1.8969840116311192e-05, + "loss": 1.406, + "step": 2204 + }, + { + "epoch": 0.23, + "learning_rate": 1.896822145440124e-05, + "loss": 1.4531, + "step": 2205 + }, + { + "epoch": 0.23, + "learning_rate": 1.896660159098004e-05, + "loss": 1.4379, + "step": 2206 + }, + { + "epoch": 0.23, + "learning_rate": 1.896498052626462e-05, + "loss": 1.4783, + "step": 2207 + }, + { + "epoch": 0.23, + "learning_rate": 1.896335826047216e-05, + "loss": 1.4801, + "step": 2208 + }, + { + "epoch": 0.23, + "learning_rate": 1.896173479381999e-05, + "loss": 1.4526, + "step": 2209 + }, + { + "epoch": 0.23, + "learning_rate": 1.8960110126525627e-05, + "loss": 1.4952, + "step": 2210 + }, + { + "epoch": 0.23, + "learning_rate": 1.895848425880673e-05, + "loss": 1.5299, + "step": 2211 + }, + { + "epoch": 0.23, + "learning_rate": 1.8956857190881125e-05, + "loss": 1.5274, + "step": 2212 + }, + { + "epoch": 0.23, + "learning_rate": 1.8955228922966792e-05, + "loss": 1.4415, + "step": 2213 + }, + { + "epoch": 0.23, + "learning_rate": 1.8953599455281884e-05, + "loss": 1.5311, + "step": 2214 + }, + { + "epoch": 0.23, + "learning_rate": 1.8951968788044702e-05, + "loss": 1.4972, + "step": 2215 + }, + { + "epoch": 0.23, + "learning_rate": 1.8950336921473715e-05, + "loss": 1.4966, + "step": 2216 + }, + { + "epoch": 0.23, + "learning_rate": 1.8948703855787553e-05, + "loss": 1.4683, + "step": 2217 + }, + { + "epoch": 0.23, + "learning_rate": 1.8947069591205005e-05, + "loss": 1.503, + "step": 2218 + }, + { + "epoch": 0.23, + "learning_rate": 1.8945434127945014e-05, + "loss": 1.4902, + "step": 2219 + }, + { + "epoch": 0.23, + "learning_rate": 1.8943797466226702e-05, + "loss": 1.4835, + "step": 2220 + }, + { + "epoch": 0.23, + "learning_rate": 1.8942159606269332e-05, + "loss": 1.535, + "step": 2221 + }, + { + "epoch": 0.23, + "learning_rate": 1.8940520548292332e-05, + "loss": 1.491, + "step": 2222 + }, + { + "epoch": 0.23, + "learning_rate": 1.89388802925153e-05, + "loss": 1.5157, + "step": 2223 + }, + { + "epoch": 0.23, + "learning_rate": 1.8937238839157987e-05, + "loss": 1.4779, + "step": 2224 + }, + { + "epoch": 0.23, + "learning_rate": 1.8935596188440302e-05, + "loss": 1.4902, + "step": 2225 + }, + { + "epoch": 0.23, + "learning_rate": 1.8933952340582323e-05, + "loss": 1.4988, + "step": 2226 + }, + { + "epoch": 0.23, + "learning_rate": 1.893230729580428e-05, + "loss": 1.4568, + "step": 2227 + }, + { + "epoch": 0.23, + "learning_rate": 1.8930661054326567e-05, + "loss": 1.5163, + "step": 2228 + }, + { + "epoch": 0.23, + "learning_rate": 1.892901361636974e-05, + "loss": 1.4472, + "step": 2229 + }, + { + "epoch": 0.23, + "learning_rate": 1.892736498215451e-05, + "loss": 1.4658, + "step": 2230 + }, + { + "epoch": 0.23, + "learning_rate": 1.8925715151901754e-05, + "loss": 1.4281, + "step": 2231 + }, + { + "epoch": 0.23, + "learning_rate": 1.892406412583251e-05, + "loss": 1.415, + "step": 2232 + }, + { + "epoch": 0.23, + "learning_rate": 1.8922411904167966e-05, + "loss": 1.464, + "step": 2233 + }, + { + "epoch": 0.23, + "learning_rate": 1.892075848712948e-05, + "loss": 1.5014, + "step": 2234 + }, + { + "epoch": 0.23, + "learning_rate": 1.8919103874938568e-05, + "loss": 1.4397, + "step": 2235 + }, + { + "epoch": 0.23, + "learning_rate": 1.891744806781691e-05, + "loss": 1.5508, + "step": 2236 + }, + { + "epoch": 0.23, + "learning_rate": 1.8915791065986335e-05, + "loss": 1.4749, + "step": 2237 + }, + { + "epoch": 0.23, + "learning_rate": 1.891413286966884e-05, + "loss": 1.4538, + "step": 2238 + }, + { + "epoch": 0.23, + "learning_rate": 1.891247347908658e-05, + "loss": 1.4405, + "step": 2239 + }, + { + "epoch": 0.23, + "learning_rate": 1.8910812894461878e-05, + "loss": 1.3562, + "step": 2240 + }, + { + "epoch": 0.24, + "learning_rate": 1.89091511160172e-05, + "loss": 1.4811, + "step": 2241 + }, + { + "epoch": 0.24, + "learning_rate": 1.8907488143975186e-05, + "loss": 1.4286, + "step": 2242 + }, + { + "epoch": 0.24, + "learning_rate": 1.890582397855863e-05, + "loss": 1.4493, + "step": 2243 + }, + { + "epoch": 0.24, + "learning_rate": 1.890415861999049e-05, + "loss": 1.5639, + "step": 2244 + }, + { + "epoch": 0.24, + "learning_rate": 1.890249206849388e-05, + "loss": 1.6375, + "step": 2245 + }, + { + "epoch": 0.24, + "learning_rate": 1.890082432429208e-05, + "loss": 1.4982, + "step": 2246 + }, + { + "epoch": 0.24, + "learning_rate": 1.889915538760851e-05, + "loss": 1.492, + "step": 2247 + }, + { + "epoch": 0.24, + "learning_rate": 1.8897485258666778e-05, + "loss": 1.4294, + "step": 2248 + }, + { + "epoch": 0.24, + "learning_rate": 1.8895813937690638e-05, + "loss": 1.4617, + "step": 2249 + }, + { + "epoch": 0.24, + "learning_rate": 1.8894141424904e-05, + "loss": 1.4763, + "step": 2250 + }, + { + "epoch": 0.24, + "learning_rate": 1.8892467720530937e-05, + "loss": 1.3989, + "step": 2251 + }, + { + "epoch": 0.24, + "learning_rate": 1.8890792824795687e-05, + "loss": 1.4803, + "step": 2252 + }, + { + "epoch": 0.24, + "learning_rate": 1.8889116737922638e-05, + "loss": 1.4734, + "step": 2253 + }, + { + "epoch": 0.24, + "learning_rate": 1.8887439460136342e-05, + "loss": 1.5069, + "step": 2254 + }, + { + "epoch": 0.24, + "learning_rate": 1.8885760991661514e-05, + "loss": 1.5565, + "step": 2255 + }, + { + "epoch": 0.24, + "learning_rate": 1.8884081332723028e-05, + "loss": 1.4707, + "step": 2256 + }, + { + "epoch": 0.24, + "learning_rate": 1.8882400483545913e-05, + "loss": 1.5077, + "step": 2257 + }, + { + "epoch": 0.24, + "learning_rate": 1.888071844435536e-05, + "loss": 1.5075, + "step": 2258 + }, + { + "epoch": 0.24, + "learning_rate": 1.8879035215376717e-05, + "loss": 1.5185, + "step": 2259 + }, + { + "epoch": 0.24, + "learning_rate": 1.887735079683549e-05, + "loss": 1.6266, + "step": 2260 + }, + { + "epoch": 0.24, + "learning_rate": 1.8875665188957354e-05, + "loss": 1.5013, + "step": 2261 + }, + { + "epoch": 0.24, + "learning_rate": 1.887397839196814e-05, + "loss": 1.4362, + "step": 2262 + }, + { + "epoch": 0.24, + "learning_rate": 1.8872290406093827e-05, + "loss": 1.4718, + "step": 2263 + }, + { + "epoch": 0.24, + "learning_rate": 1.8870601231560567e-05, + "loss": 1.5202, + "step": 2264 + }, + { + "epoch": 0.24, + "learning_rate": 1.8868910868594664e-05, + "loss": 1.5168, + "step": 2265 + }, + { + "epoch": 0.24, + "learning_rate": 1.8867219317422588e-05, + "loss": 1.5142, + "step": 2266 + }, + { + "epoch": 0.24, + "learning_rate": 1.8865526578270954e-05, + "loss": 1.4885, + "step": 2267 + }, + { + "epoch": 0.24, + "learning_rate": 1.8863832651366552e-05, + "loss": 1.5441, + "step": 2268 + }, + { + "epoch": 0.24, + "learning_rate": 1.8862137536936328e-05, + "loss": 1.4647, + "step": 2269 + }, + { + "epoch": 0.24, + "learning_rate": 1.8860441235207374e-05, + "loss": 1.5352, + "step": 2270 + }, + { + "epoch": 0.24, + "learning_rate": 1.8858743746406958e-05, + "loss": 1.4568, + "step": 2271 + }, + { + "epoch": 0.24, + "learning_rate": 1.8857045070762497e-05, + "loss": 1.4865, + "step": 2272 + }, + { + "epoch": 0.24, + "learning_rate": 1.8855345208501573e-05, + "loss": 1.4637, + "step": 2273 + }, + { + "epoch": 0.24, + "learning_rate": 1.8853644159851918e-05, + "loss": 1.4348, + "step": 2274 + }, + { + "epoch": 0.24, + "learning_rate": 1.8851941925041436e-05, + "loss": 1.4413, + "step": 2275 + }, + { + "epoch": 0.24, + "learning_rate": 1.8850238504298177e-05, + "loss": 1.4434, + "step": 2276 + }, + { + "epoch": 0.24, + "learning_rate": 1.884853389785036e-05, + "loss": 1.4822, + "step": 2277 + }, + { + "epoch": 0.24, + "learning_rate": 1.8846828105926356e-05, + "loss": 1.4632, + "step": 2278 + }, + { + "epoch": 0.24, + "learning_rate": 1.8845121128754698e-05, + "loss": 1.48, + "step": 2279 + }, + { + "epoch": 0.24, + "learning_rate": 1.8843412966564078e-05, + "loss": 1.4518, + "step": 2280 + }, + { + "epoch": 0.24, + "learning_rate": 1.884170361958334e-05, + "loss": 1.4334, + "step": 2281 + }, + { + "epoch": 0.24, + "learning_rate": 1.8839993088041502e-05, + "loss": 1.5131, + "step": 2282 + }, + { + "epoch": 0.24, + "learning_rate": 1.8838281372167724e-05, + "loss": 1.508, + "step": 2283 + }, + { + "epoch": 0.24, + "learning_rate": 1.8836568472191335e-05, + "loss": 1.4086, + "step": 2284 + }, + { + "epoch": 0.24, + "learning_rate": 1.883485438834182e-05, + "loss": 1.5021, + "step": 2285 + }, + { + "epoch": 0.24, + "learning_rate": 1.8833139120848817e-05, + "loss": 1.5083, + "step": 2286 + }, + { + "epoch": 0.24, + "learning_rate": 1.8831422669942137e-05, + "loss": 1.4162, + "step": 2287 + }, + { + "epoch": 0.24, + "learning_rate": 1.8829705035851734e-05, + "loss": 1.5494, + "step": 2288 + }, + { + "epoch": 0.24, + "learning_rate": 1.8827986218807724e-05, + "loss": 1.425, + "step": 2289 + }, + { + "epoch": 0.24, + "learning_rate": 1.8826266219040396e-05, + "loss": 1.5215, + "step": 2290 + }, + { + "epoch": 0.24, + "learning_rate": 1.8824545036780172e-05, + "loss": 1.5577, + "step": 2291 + }, + { + "epoch": 0.24, + "learning_rate": 1.8822822672257655e-05, + "loss": 1.4923, + "step": 2292 + }, + { + "epoch": 0.24, + "learning_rate": 1.8821099125703595e-05, + "loss": 1.4648, + "step": 2293 + }, + { + "epoch": 0.24, + "learning_rate": 1.8819374397348902e-05, + "loss": 1.471, + "step": 2294 + }, + { + "epoch": 0.24, + "learning_rate": 1.8817648487424648e-05, + "loss": 1.5658, + "step": 2295 + }, + { + "epoch": 0.24, + "learning_rate": 1.8815921396162058e-05, + "loss": 1.5348, + "step": 2296 + }, + { + "epoch": 0.24, + "learning_rate": 1.8814193123792518e-05, + "loss": 1.4081, + "step": 2297 + }, + { + "epoch": 0.24, + "learning_rate": 1.881246367054757e-05, + "loss": 1.4762, + "step": 2298 + }, + { + "epoch": 0.24, + "learning_rate": 1.8810733036658925e-05, + "loss": 1.4399, + "step": 2299 + }, + { + "epoch": 0.24, + "learning_rate": 1.8809001222358432e-05, + "loss": 1.4763, + "step": 2300 + }, + { + "epoch": 0.24, + "learning_rate": 1.880726822787812e-05, + "loss": 1.4874, + "step": 2301 + }, + { + "epoch": 0.24, + "learning_rate": 1.880553405345016e-05, + "loss": 1.4951, + "step": 2302 + }, + { + "epoch": 0.24, + "learning_rate": 1.8803798699306887e-05, + "loss": 1.4697, + "step": 2303 + }, + { + "epoch": 0.24, + "learning_rate": 1.880206216568079e-05, + "loss": 1.481, + "step": 2304 + }, + { + "epoch": 0.24, + "learning_rate": 1.880032445280453e-05, + "loss": 1.4485, + "step": 2305 + }, + { + "epoch": 0.24, + "learning_rate": 1.879858556091091e-05, + "loss": 1.4749, + "step": 2306 + }, + { + "epoch": 0.24, + "learning_rate": 1.8796845490232894e-05, + "loss": 1.5605, + "step": 2307 + }, + { + "epoch": 0.24, + "learning_rate": 1.879510424100361e-05, + "loss": 1.4835, + "step": 2308 + }, + { + "epoch": 0.24, + "learning_rate": 1.8793361813456346e-05, + "loss": 1.4344, + "step": 2309 + }, + { + "epoch": 0.24, + "learning_rate": 1.8791618207824532e-05, + "loss": 1.4571, + "step": 2310 + }, + { + "epoch": 0.24, + "learning_rate": 1.8789873424341772e-05, + "loss": 1.482, + "step": 2311 + }, + { + "epoch": 0.24, + "learning_rate": 1.8788127463241822e-05, + "loss": 1.4736, + "step": 2312 + }, + { + "epoch": 0.24, + "learning_rate": 1.8786380324758597e-05, + "loss": 1.4807, + "step": 2313 + }, + { + "epoch": 0.24, + "learning_rate": 1.8784632009126167e-05, + "loss": 1.4418, + "step": 2314 + }, + { + "epoch": 0.24, + "learning_rate": 1.878288251657876e-05, + "loss": 1.5248, + "step": 2315 + }, + { + "epoch": 0.24, + "learning_rate": 1.8781131847350768e-05, + "loss": 1.483, + "step": 2316 + }, + { + "epoch": 0.24, + "learning_rate": 1.877938000167673e-05, + "loss": 1.5474, + "step": 2317 + }, + { + "epoch": 0.24, + "learning_rate": 1.8777626979791347e-05, + "loss": 1.4671, + "step": 2318 + }, + { + "epoch": 0.24, + "learning_rate": 1.877587278192949e-05, + "loss": 1.3049, + "step": 2319 + }, + { + "epoch": 0.24, + "learning_rate": 1.877411740832616e-05, + "loss": 1.483, + "step": 2320 + }, + { + "epoch": 0.24, + "learning_rate": 1.877236085921655e-05, + "loss": 1.508, + "step": 2321 + }, + { + "epoch": 0.24, + "learning_rate": 1.8770603134835978e-05, + "loss": 1.4854, + "step": 2322 + }, + { + "epoch": 0.24, + "learning_rate": 1.8768844235419942e-05, + "loss": 1.4808, + "step": 2323 + }, + { + "epoch": 0.24, + "learning_rate": 1.8767084161204087e-05, + "loss": 1.5352, + "step": 2324 + }, + { + "epoch": 0.24, + "learning_rate": 1.8765322912424214e-05, + "loss": 1.5628, + "step": 2325 + }, + { + "epoch": 0.24, + "learning_rate": 1.8763560489316292e-05, + "loss": 1.494, + "step": 2326 + }, + { + "epoch": 0.24, + "learning_rate": 1.876179689211643e-05, + "loss": 1.509, + "step": 2327 + }, + { + "epoch": 0.24, + "learning_rate": 1.8760032121060918e-05, + "loss": 1.5021, + "step": 2328 + }, + { + "epoch": 0.24, + "learning_rate": 1.875826617638618e-05, + "loss": 1.4179, + "step": 2329 + }, + { + "epoch": 0.24, + "learning_rate": 1.8756499058328813e-05, + "loss": 1.4302, + "step": 2330 + }, + { + "epoch": 0.24, + "learning_rate": 1.8754730767125564e-05, + "loss": 1.4959, + "step": 2331 + }, + { + "epoch": 0.24, + "learning_rate": 1.8752961303013336e-05, + "loss": 1.4423, + "step": 2332 + }, + { + "epoch": 0.24, + "learning_rate": 1.8751190666229194e-05, + "loss": 1.4564, + "step": 2333 + }, + { + "epoch": 0.24, + "learning_rate": 1.8749418857010358e-05, + "loss": 1.4775, + "step": 2334 + }, + { + "epoch": 0.24, + "learning_rate": 1.8747645875594203e-05, + "loss": 1.4182, + "step": 2335 + }, + { + "epoch": 0.24, + "learning_rate": 1.8745871722218265e-05, + "loss": 1.3957, + "step": 2336 + }, + { + "epoch": 0.25, + "learning_rate": 1.8744096397120235e-05, + "loss": 1.4633, + "step": 2337 + }, + { + "epoch": 0.25, + "learning_rate": 1.874231990053796e-05, + "loss": 1.5512, + "step": 2338 + }, + { + "epoch": 0.25, + "learning_rate": 1.8740542232709444e-05, + "loss": 1.3461, + "step": 2339 + }, + { + "epoch": 0.25, + "learning_rate": 1.8738763393872848e-05, + "loss": 1.4754, + "step": 2340 + }, + { + "epoch": 0.25, + "learning_rate": 1.8736983384266495e-05, + "loss": 1.5448, + "step": 2341 + }, + { + "epoch": 0.25, + "learning_rate": 1.8735202204128854e-05, + "loss": 1.4491, + "step": 2342 + }, + { + "epoch": 0.25, + "learning_rate": 1.8733419853698566e-05, + "loss": 1.457, + "step": 2343 + }, + { + "epoch": 0.25, + "learning_rate": 1.8731636333214414e-05, + "loss": 1.4314, + "step": 2344 + }, + { + "epoch": 0.25, + "learning_rate": 1.8729851642915345e-05, + "loss": 1.3979, + "step": 2345 + }, + { + "epoch": 0.25, + "learning_rate": 1.8728065783040464e-05, + "loss": 1.4146, + "step": 2346 + }, + { + "epoch": 0.25, + "learning_rate": 1.8726278753829027e-05, + "loss": 1.4361, + "step": 2347 + }, + { + "epoch": 0.25, + "learning_rate": 1.872449055552045e-05, + "loss": 1.4989, + "step": 2348 + }, + { + "epoch": 0.25, + "learning_rate": 1.872270118835431e-05, + "loss": 1.5062, + "step": 2349 + }, + { + "epoch": 0.25, + "learning_rate": 1.872091065257033e-05, + "loss": 1.4509, + "step": 2350 + }, + { + "epoch": 0.25, + "learning_rate": 1.8719118948408403e-05, + "loss": 1.4631, + "step": 2351 + }, + { + "epoch": 0.25, + "learning_rate": 1.8717326076108566e-05, + "loss": 1.5119, + "step": 2352 + }, + { + "epoch": 0.25, + "learning_rate": 1.8715532035911017e-05, + "loss": 1.6347, + "step": 2353 + }, + { + "epoch": 0.25, + "learning_rate": 1.8713736828056115e-05, + "loss": 1.5526, + "step": 2354 + }, + { + "epoch": 0.25, + "learning_rate": 1.8711940452784368e-05, + "loss": 1.6348, + "step": 2355 + }, + { + "epoch": 0.25, + "learning_rate": 1.871014291033645e-05, + "loss": 1.5183, + "step": 2356 + }, + { + "epoch": 0.25, + "learning_rate": 1.8708344200953182e-05, + "loss": 1.458, + "step": 2357 + }, + { + "epoch": 0.25, + "learning_rate": 1.8706544324875545e-05, + "loss": 1.524, + "step": 2358 + }, + { + "epoch": 0.25, + "learning_rate": 1.8704743282344672e-05, + "loss": 1.4479, + "step": 2359 + }, + { + "epoch": 0.25, + "learning_rate": 1.870294107360186e-05, + "loss": 1.5408, + "step": 2360 + }, + { + "epoch": 0.25, + "learning_rate": 1.8701137698888563e-05, + "loss": 1.5007, + "step": 2361 + }, + { + "epoch": 0.25, + "learning_rate": 1.8699333158446382e-05, + "loss": 1.5132, + "step": 2362 + }, + { + "epoch": 0.25, + "learning_rate": 1.869752745251708e-05, + "loss": 1.4263, + "step": 2363 + }, + { + "epoch": 0.25, + "learning_rate": 1.8695720581342574e-05, + "loss": 1.422, + "step": 2364 + }, + { + "epoch": 0.25, + "learning_rate": 1.869391254516494e-05, + "loss": 1.4411, + "step": 2365 + }, + { + "epoch": 0.25, + "learning_rate": 1.8692103344226406e-05, + "loss": 1.4594, + "step": 2366 + }, + { + "epoch": 0.25, + "learning_rate": 1.8690292978769364e-05, + "loss": 1.4992, + "step": 2367 + }, + { + "epoch": 0.25, + "learning_rate": 1.868848144903635e-05, + "loss": 1.4822, + "step": 2368 + }, + { + "epoch": 0.25, + "learning_rate": 1.8686668755270064e-05, + "loss": 1.5402, + "step": 2369 + }, + { + "epoch": 0.25, + "learning_rate": 1.8684854897713363e-05, + "loss": 1.5268, + "step": 2370 + }, + { + "epoch": 0.25, + "learning_rate": 1.8683039876609258e-05, + "loss": 1.5587, + "step": 2371 + }, + { + "epoch": 0.25, + "learning_rate": 1.868122369220091e-05, + "loss": 1.4214, + "step": 2372 + }, + { + "epoch": 0.25, + "learning_rate": 1.8679406344731645e-05, + "loss": 1.5089, + "step": 2373 + }, + { + "epoch": 0.25, + "learning_rate": 1.867758783444494e-05, + "loss": 1.5067, + "step": 2374 + }, + { + "epoch": 0.25, + "learning_rate": 1.8675768161584427e-05, + "loss": 2.0616, + "step": 2375 + }, + { + "epoch": 0.25, + "learning_rate": 1.8673947326393903e-05, + "loss": 1.5617, + "step": 2376 + }, + { + "epoch": 0.25, + "learning_rate": 1.86721253291173e-05, + "loss": 1.4422, + "step": 2377 + }, + { + "epoch": 0.25, + "learning_rate": 1.867030216999873e-05, + "loss": 1.4727, + "step": 2378 + }, + { + "epoch": 0.25, + "learning_rate": 1.8668477849282443e-05, + "loss": 1.4152, + "step": 2379 + }, + { + "epoch": 0.25, + "learning_rate": 1.8666652367212856e-05, + "loss": 1.4376, + "step": 2380 + }, + { + "epoch": 0.25, + "learning_rate": 1.8664825724034534e-05, + "loss": 1.393, + "step": 2381 + }, + { + "epoch": 0.25, + "learning_rate": 1.8662997919992197e-05, + "loss": 1.4864, + "step": 2382 + }, + { + "epoch": 0.25, + "learning_rate": 1.866116895533073e-05, + "loss": 1.4261, + "step": 2383 + }, + { + "epoch": 0.25, + "learning_rate": 1.8659338830295163e-05, + "loss": 1.4555, + "step": 2384 + }, + { + "epoch": 0.25, + "learning_rate": 1.8657507545130687e-05, + "loss": 1.4939, + "step": 2385 + }, + { + "epoch": 0.25, + "learning_rate": 1.865567510008265e-05, + "loss": 1.4123, + "step": 2386 + }, + { + "epoch": 0.25, + "learning_rate": 1.8653841495396546e-05, + "loss": 1.4459, + "step": 2387 + }, + { + "epoch": 0.25, + "learning_rate": 1.8652006731318038e-05, + "loss": 1.396, + "step": 2388 + }, + { + "epoch": 0.25, + "eval_loss": 1.5139706134796143, + "eval_runtime": 77.2904, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 2388 + }, + { + "epoch": 0.25, + "learning_rate": 1.8650170808092936e-05, + "loss": 1.4666, + "step": 2389 + }, + { + "epoch": 0.25, + "learning_rate": 1.86483337259672e-05, + "loss": 1.5154, + "step": 2390 + }, + { + "epoch": 0.25, + "learning_rate": 1.864649548518696e-05, + "loss": 1.5163, + "step": 2391 + }, + { + "epoch": 0.25, + "learning_rate": 1.864465608599849e-05, + "loss": 1.4734, + "step": 2392 + }, + { + "epoch": 0.25, + "learning_rate": 1.864281552864822e-05, + "loss": 1.5217, + "step": 2393 + }, + { + "epoch": 0.25, + "learning_rate": 1.8640973813382737e-05, + "loss": 1.4694, + "step": 2394 + }, + { + "epoch": 0.25, + "learning_rate": 1.863913094044879e-05, + "loss": 1.4761, + "step": 2395 + }, + { + "epoch": 0.25, + "learning_rate": 1.863728691009327e-05, + "loss": 1.4766, + "step": 2396 + }, + { + "epoch": 0.25, + "learning_rate": 1.863544172256323e-05, + "loss": 1.5695, + "step": 2397 + }, + { + "epoch": 0.25, + "learning_rate": 1.8633595378105882e-05, + "loss": 1.5079, + "step": 2398 + }, + { + "epoch": 0.25, + "learning_rate": 1.8631747876968584e-05, + "loss": 1.4154, + "step": 2399 + }, + { + "epoch": 0.25, + "learning_rate": 1.862989921939886e-05, + "loss": 1.4488, + "step": 2400 + }, + { + "epoch": 0.25, + "learning_rate": 1.8628049405644376e-05, + "loss": 1.4279, + "step": 2401 + }, + { + "epoch": 0.25, + "learning_rate": 1.8626198435952966e-05, + "loss": 1.4896, + "step": 2402 + }, + { + "epoch": 0.25, + "learning_rate": 1.8624346310572602e-05, + "loss": 1.4315, + "step": 2403 + }, + { + "epoch": 0.25, + "learning_rate": 1.862249302975143e-05, + "loss": 1.4919, + "step": 2404 + }, + { + "epoch": 0.25, + "learning_rate": 1.8620638593737743e-05, + "loss": 1.4561, + "step": 2405 + }, + { + "epoch": 0.25, + "learning_rate": 1.8618783002779985e-05, + "loss": 1.4622, + "step": 2406 + }, + { + "epoch": 0.25, + "learning_rate": 1.8616926257126754e-05, + "loss": 1.4917, + "step": 2407 + }, + { + "epoch": 0.25, + "learning_rate": 1.861506835702681e-05, + "loss": 1.4962, + "step": 2408 + }, + { + "epoch": 0.25, + "learning_rate": 1.861320930272906e-05, + "loss": 1.4164, + "step": 2409 + }, + { + "epoch": 0.25, + "learning_rate": 1.8611349094482578e-05, + "loss": 1.4889, + "step": 2410 + }, + { + "epoch": 0.25, + "learning_rate": 1.8609487732536576e-05, + "loss": 1.543, + "step": 2411 + }, + { + "epoch": 0.25, + "learning_rate": 1.8607625217140433e-05, + "loss": 1.5417, + "step": 2412 + }, + { + "epoch": 0.25, + "learning_rate": 1.8605761548543674e-05, + "loss": 1.5304, + "step": 2413 + }, + { + "epoch": 0.25, + "learning_rate": 1.860389672699599e-05, + "loss": 1.4725, + "step": 2414 + }, + { + "epoch": 0.25, + "learning_rate": 1.860203075274721e-05, + "loss": 1.4745, + "step": 2415 + }, + { + "epoch": 0.25, + "learning_rate": 1.8600163626047334e-05, + "loss": 1.4656, + "step": 2416 + }, + { + "epoch": 0.25, + "learning_rate": 1.8598295347146503e-05, + "loss": 1.5287, + "step": 2417 + }, + { + "epoch": 0.25, + "learning_rate": 1.8596425916295023e-05, + "loss": 1.5024, + "step": 2418 + }, + { + "epoch": 0.25, + "learning_rate": 1.8594555333743348e-05, + "loss": 1.4527, + "step": 2419 + }, + { + "epoch": 0.25, + "learning_rate": 1.859268359974209e-05, + "loss": 1.4897, + "step": 2420 + }, + { + "epoch": 0.25, + "learning_rate": 1.859081071454201e-05, + "loss": 1.3554, + "step": 2421 + }, + { + "epoch": 0.25, + "learning_rate": 1.858893667839403e-05, + "loss": 1.4004, + "step": 2422 + }, + { + "epoch": 0.25, + "learning_rate": 1.858706149154922e-05, + "loss": 1.5582, + "step": 2423 + }, + { + "epoch": 0.25, + "learning_rate": 1.8585185154258803e-05, + "loss": 1.505, + "step": 2424 + }, + { + "epoch": 0.25, + "learning_rate": 1.858330766677417e-05, + "loss": 1.5043, + "step": 2425 + }, + { + "epoch": 0.25, + "learning_rate": 1.858142902934685e-05, + "loss": 1.439, + "step": 2426 + }, + { + "epoch": 0.25, + "learning_rate": 1.857954924222853e-05, + "loss": 1.4927, + "step": 2427 + }, + { + "epoch": 0.25, + "learning_rate": 1.8577668305671056e-05, + "loss": 1.5395, + "step": 2428 + }, + { + "epoch": 0.25, + "learning_rate": 1.8575786219926427e-05, + "loss": 1.4737, + "step": 2429 + }, + { + "epoch": 0.25, + "learning_rate": 1.8573902985246794e-05, + "loss": 1.6151, + "step": 2430 + }, + { + "epoch": 0.25, + "learning_rate": 1.857201860188446e-05, + "loss": 1.4313, + "step": 2431 + }, + { + "epoch": 0.26, + "learning_rate": 1.857013307009188e-05, + "loss": 1.4509, + "step": 2432 + }, + { + "epoch": 0.26, + "learning_rate": 1.8568246390121673e-05, + "loss": 1.3998, + "step": 2433 + }, + { + "epoch": 0.26, + "learning_rate": 1.8566358562226603e-05, + "loss": 1.5268, + "step": 2434 + }, + { + "epoch": 0.26, + "learning_rate": 1.8564469586659593e-05, + "loss": 1.4369, + "step": 2435 + }, + { + "epoch": 0.26, + "learning_rate": 1.8562579463673713e-05, + "loss": 1.4759, + "step": 2436 + }, + { + "epoch": 0.26, + "learning_rate": 1.8560688193522197e-05, + "loss": 1.4092, + "step": 2437 + }, + { + "epoch": 0.26, + "learning_rate": 1.855879577645842e-05, + "loss": 1.43, + "step": 2438 + }, + { + "epoch": 0.26, + "learning_rate": 1.855690221273592e-05, + "loss": 1.5143, + "step": 2439 + }, + { + "epoch": 0.26, + "learning_rate": 1.8555007502608385e-05, + "loss": 1.5482, + "step": 2440 + }, + { + "epoch": 0.26, + "learning_rate": 1.855311164632966e-05, + "loss": 1.4406, + "step": 2441 + }, + { + "epoch": 0.26, + "learning_rate": 1.8551214644153738e-05, + "loss": 1.4551, + "step": 2442 + }, + { + "epoch": 0.26, + "learning_rate": 1.8549316496334774e-05, + "loss": 1.4663, + "step": 2443 + }, + { + "epoch": 0.26, + "learning_rate": 1.8547417203127064e-05, + "loss": 1.4732, + "step": 2444 + }, + { + "epoch": 0.26, + "learning_rate": 1.8545516764785067e-05, + "loss": 1.5378, + "step": 2445 + }, + { + "epoch": 0.26, + "learning_rate": 1.8543615181563397e-05, + "loss": 1.4448, + "step": 2446 + }, + { + "epoch": 0.26, + "learning_rate": 1.854171245371681e-05, + "loss": 1.2861, + "step": 2447 + }, + { + "epoch": 0.26, + "learning_rate": 1.8539808581500228e-05, + "loss": 1.4405, + "step": 2448 + }, + { + "epoch": 0.26, + "learning_rate": 1.8537903565168716e-05, + "loss": 1.4876, + "step": 2449 + }, + { + "epoch": 0.26, + "learning_rate": 1.8535997404977506e-05, + "loss": 1.4119, + "step": 2450 + }, + { + "epoch": 0.26, + "learning_rate": 1.8534090101181967e-05, + "loss": 1.4451, + "step": 2451 + }, + { + "epoch": 0.26, + "learning_rate": 1.8532181654037632e-05, + "loss": 1.4035, + "step": 2452 + }, + { + "epoch": 0.26, + "learning_rate": 1.853027206380018e-05, + "loss": 1.4624, + "step": 2453 + }, + { + "epoch": 0.26, + "learning_rate": 1.852836133072545e-05, + "loss": 1.4935, + "step": 2454 + }, + { + "epoch": 0.26, + "learning_rate": 1.8526449455069434e-05, + "loss": 1.4834, + "step": 2455 + }, + { + "epoch": 0.26, + "learning_rate": 1.8524536437088266e-05, + "loss": 1.498, + "step": 2456 + }, + { + "epoch": 0.26, + "learning_rate": 1.8522622277038247e-05, + "loss": 1.3417, + "step": 2457 + }, + { + "epoch": 0.26, + "learning_rate": 1.852070697517583e-05, + "loss": 1.4455, + "step": 2458 + }, + { + "epoch": 0.26, + "learning_rate": 1.8518790531757607e-05, + "loss": 1.4119, + "step": 2459 + }, + { + "epoch": 0.26, + "learning_rate": 1.8516872947040337e-05, + "loss": 1.558, + "step": 2460 + }, + { + "epoch": 0.26, + "learning_rate": 1.8514954221280926e-05, + "loss": 1.4862, + "step": 2461 + }, + { + "epoch": 0.26, + "learning_rate": 1.8513034354736433e-05, + "loss": 1.6806, + "step": 2462 + }, + { + "epoch": 0.26, + "learning_rate": 1.8511113347664072e-05, + "loss": 1.438, + "step": 2463 + }, + { + "epoch": 0.26, + "learning_rate": 1.850919120032121e-05, + "loss": 1.4975, + "step": 2464 + }, + { + "epoch": 0.26, + "learning_rate": 1.850726791296536e-05, + "loss": 1.4409, + "step": 2465 + }, + { + "epoch": 0.26, + "learning_rate": 1.85053434858542e-05, + "loss": 1.4769, + "step": 2466 + }, + { + "epoch": 0.26, + "learning_rate": 1.8503417919245548e-05, + "loss": 1.5823, + "step": 2467 + }, + { + "epoch": 0.26, + "learning_rate": 1.8501491213397386e-05, + "loss": 1.4045, + "step": 2468 + }, + { + "epoch": 0.26, + "learning_rate": 1.8499563368567837e-05, + "loss": 1.4828, + "step": 2469 + }, + { + "epoch": 0.26, + "learning_rate": 1.849763438501519e-05, + "loss": 1.4684, + "step": 2470 + }, + { + "epoch": 0.26, + "learning_rate": 1.8495704262997873e-05, + "loss": 1.4577, + "step": 2471 + }, + { + "epoch": 0.26, + "learning_rate": 1.8493773002774475e-05, + "loss": 1.4759, + "step": 2472 + }, + { + "epoch": 0.26, + "learning_rate": 1.8491840604603736e-05, + "loss": 1.4259, + "step": 2473 + }, + { + "epoch": 0.26, + "learning_rate": 1.8489907068744543e-05, + "loss": 1.4717, + "step": 2474 + }, + { + "epoch": 0.26, + "learning_rate": 1.848797239545595e-05, + "loss": 1.4247, + "step": 2475 + }, + { + "epoch": 0.26, + "learning_rate": 1.8486036584997143e-05, + "loss": 1.4954, + "step": 2476 + }, + { + "epoch": 0.26, + "learning_rate": 1.8484099637627472e-05, + "loss": 1.4926, + "step": 2477 + }, + { + "epoch": 0.26, + "learning_rate": 1.8482161553606447e-05, + "loss": 1.487, + "step": 2478 + }, + { + "epoch": 0.26, + "learning_rate": 1.8480222333193715e-05, + "loss": 1.4553, + "step": 2479 + }, + { + "epoch": 0.26, + "learning_rate": 1.847828197664908e-05, + "loss": 1.4862, + "step": 2480 + }, + { + "epoch": 0.26, + "learning_rate": 1.8476340484232508e-05, + "loss": 1.4867, + "step": 2481 + }, + { + "epoch": 0.26, + "learning_rate": 1.8474397856204097e-05, + "loss": 1.4736, + "step": 2482 + }, + { + "epoch": 0.26, + "learning_rate": 1.8472454092824122e-05, + "loss": 1.4254, + "step": 2483 + }, + { + "epoch": 0.26, + "learning_rate": 1.8470509194352987e-05, + "loss": 1.4455, + "step": 2484 + }, + { + "epoch": 0.26, + "learning_rate": 1.8468563161051263e-05, + "loss": 1.4402, + "step": 2485 + }, + { + "epoch": 0.26, + "learning_rate": 1.846661599317967e-05, + "loss": 1.4611, + "step": 2486 + }, + { + "epoch": 0.26, + "learning_rate": 1.8464667690999073e-05, + "loss": 1.4814, + "step": 2487 + }, + { + "epoch": 0.26, + "learning_rate": 1.8462718254770503e-05, + "loss": 1.4559, + "step": 2488 + }, + { + "epoch": 0.26, + "learning_rate": 1.8460767684755127e-05, + "loss": 1.4667, + "step": 2489 + }, + { + "epoch": 0.26, + "learning_rate": 1.8458815981214274e-05, + "loss": 1.4427, + "step": 2490 + }, + { + "epoch": 0.26, + "learning_rate": 1.845686314440942e-05, + "loss": 1.4055, + "step": 2491 + }, + { + "epoch": 0.26, + "learning_rate": 1.8454909174602198e-05, + "loss": 1.5563, + "step": 2492 + }, + { + "epoch": 0.26, + "learning_rate": 1.845295407205439e-05, + "loss": 1.4631, + "step": 2493 + }, + { + "epoch": 0.26, + "learning_rate": 1.8450997837027925e-05, + "loss": 1.4887, + "step": 2494 + }, + { + "epoch": 0.26, + "learning_rate": 1.8449040469784895e-05, + "loss": 1.5212, + "step": 2495 + }, + { + "epoch": 0.26, + "learning_rate": 1.844708197058753e-05, + "loss": 1.5582, + "step": 2496 + }, + { + "epoch": 0.26, + "learning_rate": 1.844512233969822e-05, + "loss": 1.4599, + "step": 2497 + }, + { + "epoch": 0.26, + "learning_rate": 1.844316157737951e-05, + "loss": 1.4546, + "step": 2498 + }, + { + "epoch": 0.26, + "learning_rate": 1.844119968389409e-05, + "loss": 1.4631, + "step": 2499 + }, + { + "epoch": 0.26, + "learning_rate": 1.84392366595048e-05, + "loss": 1.4817, + "step": 2500 + }, + { + "epoch": 0.26, + "learning_rate": 1.8437272504474636e-05, + "loss": 1.4214, + "step": 2501 + }, + { + "epoch": 0.26, + "learning_rate": 1.8435307219066744e-05, + "loss": 1.471, + "step": 2502 + }, + { + "epoch": 0.26, + "learning_rate": 1.8433340803544424e-05, + "loss": 1.4693, + "step": 2503 + }, + { + "epoch": 0.26, + "learning_rate": 1.8431373258171127e-05, + "loss": 1.6297, + "step": 2504 + }, + { + "epoch": 0.26, + "learning_rate": 1.842940458321045e-05, + "loss": 1.5916, + "step": 2505 + }, + { + "epoch": 0.26, + "learning_rate": 1.842743477892614e-05, + "loss": 1.4754, + "step": 2506 + }, + { + "epoch": 0.26, + "learning_rate": 1.842546384558211e-05, + "loss": 1.4828, + "step": 2507 + }, + { + "epoch": 0.26, + "learning_rate": 1.842349178344241e-05, + "loss": 1.4239, + "step": 2508 + }, + { + "epoch": 0.26, + "learning_rate": 1.8421518592771243e-05, + "loss": 1.5028, + "step": 2509 + }, + { + "epoch": 0.26, + "learning_rate": 1.841954427383297e-05, + "loss": 1.4848, + "step": 2510 + }, + { + "epoch": 0.26, + "learning_rate": 1.8417568826892097e-05, + "loss": 1.4617, + "step": 2511 + }, + { + "epoch": 0.26, + "learning_rate": 1.8415592252213284e-05, + "loss": 1.4266, + "step": 2512 + }, + { + "epoch": 0.26, + "learning_rate": 1.8413614550061344e-05, + "loss": 1.4321, + "step": 2513 + }, + { + "epoch": 0.26, + "learning_rate": 1.841163572070123e-05, + "loss": 1.4693, + "step": 2514 + }, + { + "epoch": 0.26, + "learning_rate": 1.840965576439806e-05, + "loss": 1.4257, + "step": 2515 + }, + { + "epoch": 0.26, + "learning_rate": 1.84076746814171e-05, + "loss": 1.4488, + "step": 2516 + }, + { + "epoch": 0.26, + "learning_rate": 1.840569247202376e-05, + "loss": 1.5348, + "step": 2517 + }, + { + "epoch": 0.26, + "learning_rate": 1.8403709136483604e-05, + "loss": 1.477, + "step": 2518 + }, + { + "epoch": 0.26, + "learning_rate": 1.840172467506235e-05, + "loss": 1.443, + "step": 2519 + }, + { + "epoch": 0.26, + "learning_rate": 1.839973908802587e-05, + "loss": 1.4772, + "step": 2520 + }, + { + "epoch": 0.26, + "learning_rate": 1.839775237564017e-05, + "loss": 1.4443, + "step": 2521 + }, + { + "epoch": 0.26, + "learning_rate": 1.839576453817143e-05, + "loss": 1.4063, + "step": 2522 + }, + { + "epoch": 0.26, + "learning_rate": 1.8393775575885963e-05, + "loss": 1.5178, + "step": 2523 + }, + { + "epoch": 0.26, + "learning_rate": 1.8391785489050235e-05, + "loss": 1.4337, + "step": 2524 + }, + { + "epoch": 0.26, + "learning_rate": 1.8389794277930875e-05, + "loss": 1.4512, + "step": 2525 + }, + { + "epoch": 0.26, + "learning_rate": 1.838780194279465e-05, + "loss": 1.5578, + "step": 2526 + }, + { + "epoch": 0.26, + "learning_rate": 1.8385808483908484e-05, + "loss": 1.4606, + "step": 2527 + }, + { + "epoch": 0.27, + "learning_rate": 1.8383813901539444e-05, + "loss": 1.4957, + "step": 2528 + }, + { + "epoch": 0.27, + "learning_rate": 1.838181819595476e-05, + "loss": 1.4914, + "step": 2529 + }, + { + "epoch": 0.27, + "learning_rate": 1.8379821367421802e-05, + "loss": 1.4785, + "step": 2530 + }, + { + "epoch": 0.27, + "learning_rate": 1.837782341620809e-05, + "loss": 1.4052, + "step": 2531 + }, + { + "epoch": 0.27, + "learning_rate": 1.8375824342581303e-05, + "loss": 1.4807, + "step": 2532 + }, + { + "epoch": 0.27, + "learning_rate": 1.8373824146809264e-05, + "loss": 1.4313, + "step": 2533 + }, + { + "epoch": 0.27, + "learning_rate": 1.8371822829159945e-05, + "loss": 1.4374, + "step": 2534 + }, + { + "epoch": 0.27, + "learning_rate": 1.836982038990148e-05, + "loss": 1.4482, + "step": 2535 + }, + { + "epoch": 0.27, + "learning_rate": 1.8367816829302133e-05, + "loss": 1.5231, + "step": 2536 + }, + { + "epoch": 0.27, + "learning_rate": 1.8365812147630337e-05, + "loss": 1.4101, + "step": 2537 + }, + { + "epoch": 0.27, + "learning_rate": 1.8363806345154666e-05, + "loss": 1.4372, + "step": 2538 + }, + { + "epoch": 0.27, + "learning_rate": 1.8361799422143845e-05, + "loss": 1.4808, + "step": 2539 + }, + { + "epoch": 0.27, + "learning_rate": 1.835979137886675e-05, + "loss": 1.3515, + "step": 2540 + }, + { + "epoch": 0.27, + "learning_rate": 1.8357782215592412e-05, + "loss": 1.5284, + "step": 2541 + }, + { + "epoch": 0.27, + "learning_rate": 1.835577193259e-05, + "loss": 1.4222, + "step": 2542 + }, + { + "epoch": 0.27, + "learning_rate": 1.8353760530128846e-05, + "loss": 1.4522, + "step": 2543 + }, + { + "epoch": 0.27, + "learning_rate": 1.835174800847842e-05, + "loss": 1.4487, + "step": 2544 + }, + { + "epoch": 0.27, + "learning_rate": 1.8349734367908355e-05, + "loss": 1.3688, + "step": 2545 + }, + { + "epoch": 0.27, + "learning_rate": 1.8347719608688422e-05, + "loss": 1.483, + "step": 2546 + }, + { + "epoch": 0.27, + "learning_rate": 1.8345703731088554e-05, + "loss": 1.4733, + "step": 2547 + }, + { + "epoch": 0.27, + "learning_rate": 1.8343686735378816e-05, + "loss": 1.4594, + "step": 2548 + }, + { + "epoch": 0.27, + "learning_rate": 1.834166862182944e-05, + "loss": 1.4648, + "step": 2549 + }, + { + "epoch": 0.27, + "learning_rate": 1.8339649390710807e-05, + "loss": 1.5249, + "step": 2550 + }, + { + "epoch": 0.27, + "learning_rate": 1.8337629042293434e-05, + "loss": 1.4744, + "step": 2551 + }, + { + "epoch": 0.27, + "learning_rate": 1.8335607576847994e-05, + "loss": 1.5094, + "step": 2552 + }, + { + "epoch": 0.27, + "learning_rate": 1.8333584994645318e-05, + "loss": 1.5122, + "step": 2553 + }, + { + "epoch": 0.27, + "learning_rate": 1.8331561295956374e-05, + "loss": 1.537, + "step": 2554 + }, + { + "epoch": 0.27, + "learning_rate": 1.832953648105229e-05, + "loss": 1.4691, + "step": 2555 + }, + { + "epoch": 0.27, + "learning_rate": 1.8327510550204343e-05, + "loss": 1.4969, + "step": 2556 + }, + { + "epoch": 0.27, + "learning_rate": 1.8325483503683944e-05, + "loss": 1.4596, + "step": 2557 + }, + { + "epoch": 0.27, + "learning_rate": 1.8323455341762675e-05, + "loss": 1.435, + "step": 2558 + }, + { + "epoch": 0.27, + "learning_rate": 1.8321426064712255e-05, + "loss": 1.4883, + "step": 2559 + }, + { + "epoch": 0.27, + "learning_rate": 1.8319395672804554e-05, + "loss": 1.3758, + "step": 2560 + }, + { + "epoch": 0.27, + "learning_rate": 1.8317364166311592e-05, + "loss": 1.4352, + "step": 2561 + }, + { + "epoch": 0.27, + "learning_rate": 1.831533154550554e-05, + "loss": 1.5072, + "step": 2562 + }, + { + "epoch": 0.27, + "learning_rate": 1.8313297810658718e-05, + "loss": 1.4476, + "step": 2563 + }, + { + "epoch": 0.27, + "learning_rate": 1.831126296204359e-05, + "loss": 1.507, + "step": 2564 + }, + { + "epoch": 0.27, + "learning_rate": 1.8309226999932777e-05, + "loss": 1.4677, + "step": 2565 + }, + { + "epoch": 0.27, + "learning_rate": 1.8307189924599044e-05, + "loss": 1.4537, + "step": 2566 + }, + { + "epoch": 0.27, + "learning_rate": 1.8305151736315307e-05, + "loss": 1.4584, + "step": 2567 + }, + { + "epoch": 0.27, + "learning_rate": 1.8303112435354634e-05, + "loss": 1.4944, + "step": 2568 + }, + { + "epoch": 0.27, + "learning_rate": 1.8301072021990232e-05, + "loss": 1.4379, + "step": 2569 + }, + { + "epoch": 0.27, + "learning_rate": 1.8299030496495475e-05, + "loss": 1.539, + "step": 2570 + }, + { + "epoch": 0.27, + "learning_rate": 1.829698785914386e-05, + "loss": 1.4421, + "step": 2571 + }, + { + "epoch": 0.27, + "learning_rate": 1.8294944110209063e-05, + "loss": 1.4693, + "step": 2572 + }, + { + "epoch": 0.27, + "learning_rate": 1.8292899249964887e-05, + "loss": 1.3239, + "step": 2573 + }, + { + "epoch": 0.27, + "learning_rate": 1.8290853278685284e-05, + "loss": 1.472, + "step": 2574 + }, + { + "epoch": 0.27, + "learning_rate": 1.8288806196644374e-05, + "loss": 1.536, + "step": 2575 + }, + { + "epoch": 0.27, + "learning_rate": 1.8286758004116405e-05, + "loss": 1.4644, + "step": 2576 + }, + { + "epoch": 0.27, + "learning_rate": 1.8284708701375783e-05, + "loss": 1.4537, + "step": 2577 + }, + { + "epoch": 0.27, + "learning_rate": 1.8282658288697067e-05, + "loss": 1.4359, + "step": 2578 + }, + { + "epoch": 0.27, + "learning_rate": 1.8280606766354955e-05, + "loss": 1.4842, + "step": 2579 + }, + { + "epoch": 0.27, + "learning_rate": 1.8278554134624302e-05, + "loss": 1.4664, + "step": 2580 + }, + { + "epoch": 0.27, + "learning_rate": 1.8276500393780105e-05, + "loss": 1.4632, + "step": 2581 + }, + { + "epoch": 0.27, + "learning_rate": 1.827444554409751e-05, + "loss": 1.4996, + "step": 2582 + }, + { + "epoch": 0.27, + "learning_rate": 1.827238958585182e-05, + "loss": 1.3399, + "step": 2583 + }, + { + "epoch": 0.27, + "learning_rate": 1.8270332519318476e-05, + "loss": 1.3928, + "step": 2584 + }, + { + "epoch": 0.27, + "learning_rate": 1.8268274344773074e-05, + "loss": 1.4993, + "step": 2585 + }, + { + "epoch": 0.27, + "learning_rate": 1.8266215062491356e-05, + "loss": 1.5398, + "step": 2586 + }, + { + "epoch": 0.27, + "learning_rate": 1.826415467274921e-05, + "loss": 1.4353, + "step": 2587 + }, + { + "epoch": 0.27, + "eval_loss": 1.5104212760925293, + "eval_runtime": 77.3448, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2587 + }, + { + "epoch": 0.27, + "learning_rate": 1.8262093175822685e-05, + "loss": 1.4889, + "step": 2588 + }, + { + "epoch": 0.27, + "learning_rate": 1.826003057198796e-05, + "loss": 1.4912, + "step": 2589 + }, + { + "epoch": 0.27, + "learning_rate": 1.825796686152137e-05, + "loss": 1.4884, + "step": 2590 + }, + { + "epoch": 0.27, + "learning_rate": 1.8255902044699404e-05, + "loss": 1.478, + "step": 2591 + }, + { + "epoch": 0.27, + "learning_rate": 1.8253836121798692e-05, + "loss": 1.6549, + "step": 2592 + }, + { + "epoch": 0.27, + "learning_rate": 1.8251769093096018e-05, + "loss": 1.5146, + "step": 2593 + }, + { + "epoch": 0.27, + "learning_rate": 1.8249700958868306e-05, + "loss": 1.4797, + "step": 2594 + }, + { + "epoch": 0.27, + "learning_rate": 1.8247631719392634e-05, + "loss": 1.4655, + "step": 2595 + }, + { + "epoch": 0.27, + "learning_rate": 1.824556137494623e-05, + "loss": 1.4517, + "step": 2596 + }, + { + "epoch": 0.27, + "learning_rate": 1.8243489925806458e-05, + "loss": 1.4936, + "step": 2597 + }, + { + "epoch": 0.27, + "learning_rate": 1.8241417372250852e-05, + "loss": 1.4614, + "step": 2598 + }, + { + "epoch": 0.27, + "learning_rate": 1.8239343714557073e-05, + "loss": 1.4475, + "step": 2599 + }, + { + "epoch": 0.27, + "learning_rate": 1.8237268953002937e-05, + "loss": 1.5435, + "step": 2600 + }, + { + "epoch": 0.27, + "learning_rate": 1.8235193087866413e-05, + "loss": 1.4616, + "step": 2601 + }, + { + "epoch": 0.27, + "learning_rate": 1.8233116119425612e-05, + "loss": 1.4578, + "step": 2602 + }, + { + "epoch": 0.27, + "learning_rate": 1.8231038047958795e-05, + "loss": 1.434, + "step": 2603 + }, + { + "epoch": 0.27, + "learning_rate": 1.8228958873744368e-05, + "loss": 1.5335, + "step": 2604 + }, + { + "epoch": 0.27, + "learning_rate": 1.8226878597060887e-05, + "loss": 1.415, + "step": 2605 + }, + { + "epoch": 0.27, + "learning_rate": 1.8224797218187058e-05, + "loss": 1.6165, + "step": 2606 + }, + { + "epoch": 0.27, + "learning_rate": 1.822271473740173e-05, + "loss": 1.372, + "step": 2607 + }, + { + "epoch": 0.27, + "learning_rate": 1.8220631154983907e-05, + "loss": 1.4855, + "step": 2608 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218546471212727e-05, + "loss": 1.4093, + "step": 2609 + }, + { + "epoch": 0.27, + "learning_rate": 1.821646068636749e-05, + "loss": 1.4852, + "step": 2610 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214373800727637e-05, + "loss": 1.6959, + "step": 2611 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212285814572755e-05, + "loss": 1.3874, + "step": 2612 + }, + { + "epoch": 0.27, + "learning_rate": 1.821019672818258e-05, + "loss": 1.4425, + "step": 2613 + }, + { + "epoch": 0.27, + "learning_rate": 1.8208106541837e-05, + "loss": 1.6097, + "step": 2614 + }, + { + "epoch": 0.27, + "learning_rate": 1.8206015255816045e-05, + "loss": 1.5675, + "step": 2615 + }, + { + "epoch": 0.27, + "learning_rate": 1.820392287039989e-05, + "loss": 1.4039, + "step": 2616 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201829385868866e-05, + "loss": 1.4872, + "step": 2617 + }, + { + "epoch": 0.27, + "learning_rate": 1.819973480250344e-05, + "loss": 1.4645, + "step": 2618 + }, + { + "epoch": 0.27, + "learning_rate": 1.8197639120584237e-05, + "loss": 1.4923, + "step": 2619 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195542340392025e-05, + "loss": 1.4294, + "step": 2620 + }, + { + "epoch": 0.27, + "learning_rate": 1.8193444462207717e-05, + "loss": 1.4315, + "step": 2621 + }, + { + "epoch": 0.27, + "learning_rate": 1.8191345486312372e-05, + "loss": 1.3972, + "step": 2622 + }, + { + "epoch": 0.28, + "learning_rate": 1.8189245412987205e-05, + "loss": 1.462, + "step": 2623 + }, + { + "epoch": 0.28, + "learning_rate": 1.8187144242513567e-05, + "loss": 1.4738, + "step": 2624 + }, + { + "epoch": 0.28, + "learning_rate": 1.818504197517296e-05, + "loss": 1.4935, + "step": 2625 + }, + { + "epoch": 0.28, + "learning_rate": 1.8182938611247038e-05, + "loss": 1.4231, + "step": 2626 + }, + { + "epoch": 0.28, + "learning_rate": 1.81808341510176e-05, + "loss": 1.4031, + "step": 2627 + }, + { + "epoch": 0.28, + "learning_rate": 1.817872859476658e-05, + "loss": 1.5822, + "step": 2628 + }, + { + "epoch": 0.28, + "learning_rate": 1.8176621942776075e-05, + "loss": 1.432, + "step": 2629 + }, + { + "epoch": 0.28, + "learning_rate": 1.8174514195328324e-05, + "loss": 1.5565, + "step": 2630 + }, + { + "epoch": 0.28, + "learning_rate": 1.8172405352705704e-05, + "loss": 1.4895, + "step": 2631 + }, + { + "epoch": 0.28, + "learning_rate": 1.8170295415190754e-05, + "loss": 1.4032, + "step": 2632 + }, + { + "epoch": 0.28, + "learning_rate": 1.8168184383066144e-05, + "loss": 1.4253, + "step": 2633 + }, + { + "epoch": 0.28, + "learning_rate": 1.8166072256614702e-05, + "loss": 1.5162, + "step": 2634 + }, + { + "epoch": 0.28, + "learning_rate": 1.81639590361194e-05, + "loss": 1.4609, + "step": 2635 + }, + { + "epoch": 0.28, + "learning_rate": 1.816184472186335e-05, + "loss": 1.4351, + "step": 2636 + }, + { + "epoch": 0.28, + "learning_rate": 1.8159729314129823e-05, + "loss": 1.4738, + "step": 2637 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157612813202224e-05, + "loss": 1.5986, + "step": 2638 + }, + { + "epoch": 0.28, + "learning_rate": 1.815549521936411e-05, + "loss": 1.4633, + "step": 2639 + }, + { + "epoch": 0.28, + "learning_rate": 1.8153376532899184e-05, + "loss": 1.4404, + "step": 2640 + }, + { + "epoch": 0.28, + "learning_rate": 1.81512567540913e-05, + "loss": 1.4256, + "step": 2641 + }, + { + "epoch": 0.28, + "learning_rate": 1.814913588322445e-05, + "loss": 1.4054, + "step": 2642 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147013920582773e-05, + "loss": 1.4134, + "step": 2643 + }, + { + "epoch": 0.28, + "learning_rate": 1.8144890866450567e-05, + "loss": 1.4098, + "step": 2644 + }, + { + "epoch": 0.28, + "learning_rate": 1.814276672111226e-05, + "loss": 1.4593, + "step": 2645 + }, + { + "epoch": 0.28, + "learning_rate": 1.814064148485243e-05, + "loss": 1.4679, + "step": 2646 + }, + { + "epoch": 0.28, + "learning_rate": 1.8138515157955812e-05, + "loss": 1.5234, + "step": 2647 + }, + { + "epoch": 0.28, + "learning_rate": 1.8136387740707272e-05, + "loss": 1.4568, + "step": 2648 + }, + { + "epoch": 0.28, + "learning_rate": 1.8134259233391836e-05, + "loss": 1.5057, + "step": 2649 + }, + { + "epoch": 0.28, + "learning_rate": 1.8132129636294665e-05, + "loss": 1.3643, + "step": 2650 + }, + { + "epoch": 0.28, + "learning_rate": 1.812999894970107e-05, + "loss": 1.4766, + "step": 2651 + }, + { + "epoch": 0.28, + "learning_rate": 1.812786717389651e-05, + "loss": 1.5701, + "step": 2652 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125734309166587e-05, + "loss": 1.5341, + "step": 2653 + }, + { + "epoch": 0.28, + "learning_rate": 1.812360035579705e-05, + "loss": 1.3596, + "step": 2654 + }, + { + "epoch": 0.28, + "learning_rate": 1.8121465314073793e-05, + "loss": 1.4847, + "step": 2655 + }, + { + "epoch": 0.28, + "learning_rate": 1.811932918428286e-05, + "loss": 1.4664, + "step": 2656 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117191966710438e-05, + "loss": 1.4673, + "step": 2657 + }, + { + "epoch": 0.28, + "learning_rate": 1.8115053661642856e-05, + "loss": 1.4712, + "step": 2658 + }, + { + "epoch": 0.28, + "learning_rate": 1.811291426936659e-05, + "loss": 1.4458, + "step": 2659 + }, + { + "epoch": 0.28, + "learning_rate": 1.811077379016827e-05, + "loss": 1.4667, + "step": 2660 + }, + { + "epoch": 0.28, + "learning_rate": 1.810863222433466e-05, + "loss": 1.4695, + "step": 2661 + }, + { + "epoch": 0.28, + "learning_rate": 1.8106489572152677e-05, + "loss": 1.5263, + "step": 2662 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104345833909376e-05, + "loss": 1.4148, + "step": 2663 + }, + { + "epoch": 0.28, + "learning_rate": 1.8102201009891976e-05, + "loss": 1.3955, + "step": 2664 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100055100387814e-05, + "loss": 1.6056, + "step": 2665 + }, + { + "epoch": 0.28, + "learning_rate": 1.8097908105684396e-05, + "loss": 1.5394, + "step": 2666 + }, + { + "epoch": 0.28, + "learning_rate": 1.809576002606936e-05, + "loss": 1.479, + "step": 2667 + }, + { + "epoch": 0.28, + "learning_rate": 1.8093610861830494e-05, + "loss": 1.4492, + "step": 2668 + }, + { + "epoch": 0.28, + "learning_rate": 1.8091460613255728e-05, + "loss": 1.4172, + "step": 2669 + }, + { + "epoch": 0.28, + "learning_rate": 1.808930928063315e-05, + "loss": 1.4498, + "step": 2670 + }, + { + "epoch": 0.28, + "learning_rate": 1.808715686425097e-05, + "loss": 1.6203, + "step": 2671 + }, + { + "epoch": 0.28, + "learning_rate": 1.8085003364397567e-05, + "loss": 1.435, + "step": 2672 + }, + { + "epoch": 0.28, + "learning_rate": 1.808284878136145e-05, + "loss": 1.4489, + "step": 2673 + }, + { + "epoch": 0.28, + "learning_rate": 1.8080693115431277e-05, + "loss": 1.4416, + "step": 2674 + }, + { + "epoch": 0.28, + "learning_rate": 1.8078536366895853e-05, + "loss": 1.422, + "step": 2675 + }, + { + "epoch": 0.28, + "learning_rate": 1.8076378536044128e-05, + "loss": 1.4039, + "step": 2676 + }, + { + "epoch": 0.28, + "learning_rate": 1.8074219623165195e-05, + "loss": 1.4705, + "step": 2677 + }, + { + "epoch": 0.28, + "learning_rate": 1.807205962854829e-05, + "loss": 1.5031, + "step": 2678 + }, + { + "epoch": 0.28, + "learning_rate": 1.8069898552482806e-05, + "loss": 1.4812, + "step": 2679 + }, + { + "epoch": 0.28, + "learning_rate": 1.806773639525826e-05, + "loss": 1.4129, + "step": 2680 + }, + { + "epoch": 0.28, + "learning_rate": 1.8065573157164332e-05, + "loss": 1.4559, + "step": 2681 + }, + { + "epoch": 0.28, + "learning_rate": 1.806340883849084e-05, + "loss": 1.3878, + "step": 2682 + }, + { + "epoch": 0.28, + "learning_rate": 1.8061243439527744e-05, + "loss": 1.4752, + "step": 2683 + }, + { + "epoch": 0.28, + "learning_rate": 1.8059076960565156e-05, + "loss": 1.4089, + "step": 2684 + }, + { + "epoch": 0.28, + "learning_rate": 1.8056909401893326e-05, + "loss": 1.4736, + "step": 2685 + }, + { + "epoch": 0.28, + "learning_rate": 1.8054740763802654e-05, + "loss": 1.3796, + "step": 2686 + }, + { + "epoch": 0.28, + "learning_rate": 1.805257104658368e-05, + "loss": 1.4412, + "step": 2687 + }, + { + "epoch": 0.28, + "learning_rate": 1.8050400250527086e-05, + "loss": 1.4639, + "step": 2688 + }, + { + "epoch": 0.28, + "learning_rate": 1.804822837592371e-05, + "loss": 1.4076, + "step": 2689 + }, + { + "epoch": 0.28, + "learning_rate": 1.804605542306452e-05, + "loss": 1.4627, + "step": 2690 + }, + { + "epoch": 0.28, + "learning_rate": 1.8043881392240642e-05, + "loss": 1.5249, + "step": 2691 + }, + { + "epoch": 0.28, + "learning_rate": 1.804170628374334e-05, + "loss": 1.4312, + "step": 2692 + }, + { + "epoch": 0.28, + "learning_rate": 1.803953009786402e-05, + "loss": 1.5676, + "step": 2693 + }, + { + "epoch": 0.28, + "learning_rate": 1.8037352834894233e-05, + "loss": 1.5072, + "step": 2694 + }, + { + "epoch": 0.28, + "learning_rate": 1.803517449512568e-05, + "loss": 1.5662, + "step": 2695 + }, + { + "epoch": 0.28, + "learning_rate": 1.8032995078850207e-05, + "loss": 1.4771, + "step": 2696 + }, + { + "epoch": 0.28, + "learning_rate": 1.803081458635979e-05, + "loss": 1.412, + "step": 2697 + }, + { + "epoch": 0.28, + "learning_rate": 1.8028633017946564e-05, + "loss": 1.497, + "step": 2698 + }, + { + "epoch": 0.28, + "learning_rate": 1.8026450373902804e-05, + "loss": 1.4528, + "step": 2699 + }, + { + "epoch": 0.28, + "learning_rate": 1.802426665452093e-05, + "loss": 1.4785, + "step": 2700 + }, + { + "epoch": 0.28, + "learning_rate": 1.8022081860093493e-05, + "loss": 1.6411, + "step": 2701 + }, + { + "epoch": 0.28, + "learning_rate": 1.8019895990913213e-05, + "loss": 1.4459, + "step": 2702 + }, + { + "epoch": 0.28, + "learning_rate": 1.8017709047272932e-05, + "loss": 1.4418, + "step": 2703 + }, + { + "epoch": 0.28, + "learning_rate": 1.801552102946565e-05, + "loss": 1.4409, + "step": 2704 + }, + { + "epoch": 0.28, + "learning_rate": 1.8013331937784498e-05, + "loss": 1.4651, + "step": 2705 + }, + { + "epoch": 0.28, + "learning_rate": 1.8011141772522766e-05, + "loss": 1.4161, + "step": 2706 + }, + { + "epoch": 0.28, + "learning_rate": 1.8008950533973876e-05, + "loss": 1.458, + "step": 2707 + }, + { + "epoch": 0.28, + "learning_rate": 1.8006758222431398e-05, + "loss": 1.4477, + "step": 2708 + }, + { + "epoch": 0.28, + "learning_rate": 1.800456483818904e-05, + "loss": 1.4433, + "step": 2709 + }, + { + "epoch": 0.28, + "learning_rate": 1.8002370381540672e-05, + "loss": 1.5005, + "step": 2710 + }, + { + "epoch": 0.28, + "learning_rate": 1.8000174852780282e-05, + "loss": 1.4945, + "step": 2711 + }, + { + "epoch": 0.28, + "learning_rate": 1.7997978252202023e-05, + "loss": 1.4298, + "step": 2712 + }, + { + "epoch": 0.28, + "learning_rate": 1.7995780580100177e-05, + "loss": 1.3812, + "step": 2713 + }, + { + "epoch": 0.28, + "learning_rate": 1.799358183676918e-05, + "loss": 1.5559, + "step": 2714 + }, + { + "epoch": 0.28, + "learning_rate": 1.79913820225036e-05, + "loss": 1.4316, + "step": 2715 + }, + { + "epoch": 0.28, + "learning_rate": 1.798918113759817e-05, + "loss": 1.419, + "step": 2716 + }, + { + "epoch": 0.28, + "learning_rate": 1.7986979182347733e-05, + "loss": 1.43, + "step": 2717 + }, + { + "epoch": 0.29, + "learning_rate": 1.798477615704731e-05, + "loss": 1.4964, + "step": 2718 + }, + { + "epoch": 0.29, + "learning_rate": 1.7982572061992044e-05, + "loss": 1.4417, + "step": 2719 + }, + { + "epoch": 0.29, + "learning_rate": 1.7980366897477227e-05, + "loss": 1.4562, + "step": 2720 + }, + { + "epoch": 0.29, + "learning_rate": 1.7978160663798295e-05, + "loss": 1.4386, + "step": 2721 + }, + { + "epoch": 0.29, + "learning_rate": 1.7975953361250824e-05, + "loss": 1.445, + "step": 2722 + }, + { + "epoch": 0.29, + "learning_rate": 1.797374499013054e-05, + "loss": 1.4549, + "step": 2723 + }, + { + "epoch": 0.29, + "learning_rate": 1.7971535550733305e-05, + "loss": 1.5205, + "step": 2724 + }, + { + "epoch": 0.29, + "learning_rate": 1.796932504335513e-05, + "loss": 1.4632, + "step": 2725 + }, + { + "epoch": 0.29, + "learning_rate": 1.796711346829216e-05, + "loss": 1.3767, + "step": 2726 + }, + { + "epoch": 0.29, + "learning_rate": 1.79649008258407e-05, + "loss": 1.4098, + "step": 2727 + }, + { + "epoch": 0.29, + "learning_rate": 1.7962687116297178e-05, + "loss": 1.4675, + "step": 2728 + }, + { + "epoch": 0.29, + "learning_rate": 1.7960472339958176e-05, + "loss": 1.6048, + "step": 2729 + }, + { + "epoch": 0.29, + "learning_rate": 1.7958256497120418e-05, + "loss": 1.5432, + "step": 2730 + }, + { + "epoch": 0.29, + "learning_rate": 1.7956039588080774e-05, + "loss": 1.5453, + "step": 2731 + }, + { + "epoch": 0.29, + "learning_rate": 1.7953821613136246e-05, + "loss": 1.4246, + "step": 2732 + }, + { + "epoch": 0.29, + "learning_rate": 1.7951602572583988e-05, + "loss": 1.3987, + "step": 2733 + }, + { + "epoch": 0.29, + "learning_rate": 1.7949382466721295e-05, + "loss": 1.4943, + "step": 2734 + }, + { + "epoch": 0.29, + "learning_rate": 1.7947161295845606e-05, + "loss": 1.4385, + "step": 2735 + }, + { + "epoch": 0.29, + "learning_rate": 1.7944939060254497e-05, + "loss": 1.4165, + "step": 2736 + }, + { + "epoch": 0.29, + "learning_rate": 1.7942715760245692e-05, + "loss": 1.4004, + "step": 2737 + }, + { + "epoch": 0.29, + "learning_rate": 1.7940491396117063e-05, + "loss": 1.4577, + "step": 2738 + }, + { + "epoch": 0.29, + "learning_rate": 1.7938265968166602e-05, + "loss": 1.4649, + "step": 2739 + }, + { + "epoch": 0.29, + "learning_rate": 1.7936039476692473e-05, + "loss": 1.5273, + "step": 2740 + }, + { + "epoch": 0.29, + "learning_rate": 1.7933811921992962e-05, + "loss": 1.4325, + "step": 2741 + }, + { + "epoch": 0.29, + "learning_rate": 1.793158330436651e-05, + "loss": 1.4388, + "step": 2742 + }, + { + "epoch": 0.29, + "learning_rate": 1.7929353624111687e-05, + "loss": 1.4124, + "step": 2743 + }, + { + "epoch": 0.29, + "learning_rate": 1.7927122881527222e-05, + "loss": 1.5449, + "step": 2744 + }, + { + "epoch": 0.29, + "learning_rate": 1.7924891076911964e-05, + "loss": 1.4728, + "step": 2745 + }, + { + "epoch": 0.29, + "learning_rate": 1.7922658210564932e-05, + "loss": 1.5103, + "step": 2746 + }, + { + "epoch": 0.29, + "learning_rate": 1.792042428278526e-05, + "loss": 1.5975, + "step": 2747 + }, + { + "epoch": 0.29, + "learning_rate": 1.7918189293872247e-05, + "loss": 1.567, + "step": 2748 + }, + { + "epoch": 0.29, + "learning_rate": 1.7915953244125318e-05, + "loss": 1.57, + "step": 2749 + }, + { + "epoch": 0.29, + "learning_rate": 1.791371613384405e-05, + "loss": 1.4372, + "step": 2750 + }, + { + "epoch": 0.29, + "learning_rate": 1.7911477963328155e-05, + "loss": 1.4053, + "step": 2751 + }, + { + "epoch": 0.29, + "learning_rate": 1.7909238732877492e-05, + "loss": 1.3782, + "step": 2752 + }, + { + "epoch": 0.29, + "learning_rate": 1.790699844279206e-05, + "loss": 1.4401, + "step": 2753 + }, + { + "epoch": 0.29, + "learning_rate": 1.7904757093372e-05, + "loss": 1.3749, + "step": 2754 + }, + { + "epoch": 0.29, + "learning_rate": 1.79025146849176e-05, + "loss": 1.4909, + "step": 2755 + }, + { + "epoch": 0.29, + "learning_rate": 1.7900271217729273e-05, + "loss": 1.4103, + "step": 2756 + }, + { + "epoch": 0.29, + "learning_rate": 1.7898026692107597e-05, + "loss": 1.4986, + "step": 2757 + }, + { + "epoch": 0.29, + "learning_rate": 1.7895781108353278e-05, + "loss": 1.5449, + "step": 2758 + }, + { + "epoch": 0.29, + "learning_rate": 1.789353446676717e-05, + "loss": 1.5583, + "step": 2759 + }, + { + "epoch": 0.29, + "learning_rate": 1.7891286767650254e-05, + "loss": 1.5342, + "step": 2760 + }, + { + "epoch": 0.29, + "learning_rate": 1.7889038011303673e-05, + "loss": 1.4233, + "step": 2761 + }, + { + "epoch": 0.29, + "learning_rate": 1.7886788198028707e-05, + "loss": 1.3433, + "step": 2762 + }, + { + "epoch": 0.29, + "learning_rate": 1.788453732812676e-05, + "loss": 1.4451, + "step": 2763 + }, + { + "epoch": 0.29, + "learning_rate": 1.78822854018994e-05, + "loss": 1.4506, + "step": 2764 + }, + { + "epoch": 0.29, + "learning_rate": 1.7880032419648324e-05, + "loss": 1.4386, + "step": 2765 + }, + { + "epoch": 0.29, + "learning_rate": 1.7877778381675374e-05, + "loss": 1.4512, + "step": 2766 + }, + { + "epoch": 0.29, + "learning_rate": 1.7875523288282535e-05, + "loss": 1.4319, + "step": 2767 + }, + { + "epoch": 0.29, + "learning_rate": 1.7873267139771932e-05, + "loss": 1.4753, + "step": 2768 + }, + { + "epoch": 0.29, + "learning_rate": 1.787100993644583e-05, + "loss": 1.4044, + "step": 2769 + }, + { + "epoch": 0.29, + "learning_rate": 1.786875167860663e-05, + "loss": 1.4382, + "step": 2770 + }, + { + "epoch": 0.29, + "learning_rate": 1.786649236655689e-05, + "loss": 1.3977, + "step": 2771 + }, + { + "epoch": 0.29, + "learning_rate": 1.7864232000599298e-05, + "loss": 1.4473, + "step": 2772 + }, + { + "epoch": 0.29, + "learning_rate": 1.7861970581036678e-05, + "loss": 1.4666, + "step": 2773 + }, + { + "epoch": 0.29, + "learning_rate": 1.785970810817201e-05, + "loss": 1.5299, + "step": 2774 + }, + { + "epoch": 0.29, + "learning_rate": 1.7857444582308402e-05, + "loss": 1.3974, + "step": 2775 + }, + { + "epoch": 0.29, + "learning_rate": 1.7855180003749114e-05, + "loss": 1.4603, + "step": 2776 + }, + { + "epoch": 0.29, + "learning_rate": 1.7852914372797535e-05, + "loss": 1.463, + "step": 2777 + }, + { + "epoch": 0.29, + "learning_rate": 1.7850647689757205e-05, + "loss": 1.5317, + "step": 2778 + }, + { + "epoch": 0.29, + "learning_rate": 1.78483799549318e-05, + "loss": 1.4669, + "step": 2779 + }, + { + "epoch": 0.29, + "learning_rate": 1.784611116862514e-05, + "loss": 1.5293, + "step": 2780 + }, + { + "epoch": 0.29, + "learning_rate": 1.7843841331141177e-05, + "loss": 1.5802, + "step": 2781 + }, + { + "epoch": 0.29, + "learning_rate": 1.7841570442784024e-05, + "loss": 1.4486, + "step": 2782 + }, + { + "epoch": 0.29, + "learning_rate": 1.7839298503857913e-05, + "loss": 1.4674, + "step": 2783 + }, + { + "epoch": 0.29, + "learning_rate": 1.7837025514667224e-05, + "loss": 1.4662, + "step": 2784 + }, + { + "epoch": 0.29, + "learning_rate": 1.7834751475516484e-05, + "loss": 1.3555, + "step": 2785 + }, + { + "epoch": 0.29, + "learning_rate": 1.783247638671035e-05, + "loss": 1.4307, + "step": 2786 + }, + { + "epoch": 0.29, + "eval_loss": 1.500258445739746, + "eval_runtime": 77.406, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 2786 + }, + { + "epoch": 0.29, + "learning_rate": 1.7830200248553633e-05, + "loss": 1.4596, + "step": 2787 + }, + { + "epoch": 0.29, + "learning_rate": 1.7827923061351273e-05, + "loss": 1.6118, + "step": 2788 + }, + { + "epoch": 0.29, + "learning_rate": 1.7825644825408353e-05, + "loss": 1.4782, + "step": 2789 + }, + { + "epoch": 0.29, + "learning_rate": 1.78233655410301e-05, + "loss": 1.4681, + "step": 2790 + }, + { + "epoch": 0.29, + "learning_rate": 1.782108520852188e-05, + "loss": 1.6281, + "step": 2791 + }, + { + "epoch": 0.29, + "learning_rate": 1.78188038281892e-05, + "loss": 1.4446, + "step": 2792 + }, + { + "epoch": 0.29, + "learning_rate": 1.7816521400337704e-05, + "loss": 1.479, + "step": 2793 + }, + { + "epoch": 0.29, + "learning_rate": 1.7814237925273178e-05, + "loss": 1.5457, + "step": 2794 + }, + { + "epoch": 0.29, + "learning_rate": 1.7811953403301547e-05, + "loss": 1.3928, + "step": 2795 + }, + { + "epoch": 0.29, + "learning_rate": 1.780966783472889e-05, + "loss": 1.4321, + "step": 2796 + }, + { + "epoch": 0.29, + "learning_rate": 1.78073812198614e-05, + "loss": 1.5734, + "step": 2797 + }, + { + "epoch": 0.29, + "learning_rate": 1.7805093559005432e-05, + "loss": 1.4356, + "step": 2798 + }, + { + "epoch": 0.29, + "learning_rate": 1.7802804852467473e-05, + "loss": 1.4656, + "step": 2799 + }, + { + "epoch": 0.29, + "learning_rate": 1.780051510055415e-05, + "loss": 1.4052, + "step": 2800 + }, + { + "epoch": 0.29, + "learning_rate": 1.7798224303572228e-05, + "loss": 1.4758, + "step": 2801 + }, + { + "epoch": 0.29, + "learning_rate": 1.7795932461828622e-05, + "loss": 1.4326, + "step": 2802 + }, + { + "epoch": 0.29, + "learning_rate": 1.7793639575630376e-05, + "loss": 1.3409, + "step": 2803 + }, + { + "epoch": 0.29, + "learning_rate": 1.7791345645284678e-05, + "loss": 1.4175, + "step": 2804 + }, + { + "epoch": 0.29, + "learning_rate": 1.7789050671098853e-05, + "loss": 1.383, + "step": 2805 + }, + { + "epoch": 0.29, + "learning_rate": 1.7786754653380373e-05, + "loss": 1.5162, + "step": 2806 + }, + { + "epoch": 0.29, + "learning_rate": 1.7784457592436847e-05, + "loss": 1.4899, + "step": 2807 + }, + { + "epoch": 0.29, + "learning_rate": 1.7782159488576016e-05, + "loss": 1.4874, + "step": 2808 + }, + { + "epoch": 0.29, + "learning_rate": 1.777986034210577e-05, + "loss": 1.4363, + "step": 2809 + }, + { + "epoch": 0.29, + "learning_rate": 1.7777560153334134e-05, + "loss": 1.4223, + "step": 2810 + }, + { + "epoch": 0.29, + "learning_rate": 1.7775258922569273e-05, + "loss": 1.4792, + "step": 2811 + }, + { + "epoch": 0.29, + "learning_rate": 1.77729566501195e-05, + "loss": 1.4475, + "step": 2812 + }, + { + "epoch": 0.29, + "learning_rate": 1.7770653336293253e-05, + "loss": 1.5157, + "step": 2813 + }, + { + "epoch": 0.3, + "learning_rate": 1.776834898139912e-05, + "loss": 1.389, + "step": 2814 + }, + { + "epoch": 0.3, + "learning_rate": 1.7766043585745824e-05, + "loss": 1.4358, + "step": 2815 + }, + { + "epoch": 0.3, + "learning_rate": 1.776373714964223e-05, + "loss": 1.4297, + "step": 2816 + }, + { + "epoch": 0.3, + "learning_rate": 1.7761429673397344e-05, + "loss": 1.4102, + "step": 2817 + }, + { + "epoch": 0.3, + "learning_rate": 1.77591211573203e-05, + "loss": 1.4572, + "step": 2818 + }, + { + "epoch": 0.3, + "learning_rate": 1.775681160172039e-05, + "loss": 1.448, + "step": 2819 + }, + { + "epoch": 0.3, + "learning_rate": 1.7754501006907025e-05, + "loss": 1.4426, + "step": 2820 + }, + { + "epoch": 0.3, + "learning_rate": 1.7752189373189773e-05, + "loss": 1.4566, + "step": 2821 + }, + { + "epoch": 0.3, + "learning_rate": 1.7749876700878332e-05, + "loss": 1.4267, + "step": 2822 + }, + { + "epoch": 0.3, + "learning_rate": 1.7747562990282538e-05, + "loss": 1.3951, + "step": 2823 + }, + { + "epoch": 0.3, + "learning_rate": 1.7745248241712373e-05, + "loss": 1.4668, + "step": 2824 + }, + { + "epoch": 0.3, + "learning_rate": 1.774293245547795e-05, + "loss": 1.4924, + "step": 2825 + }, + { + "epoch": 0.3, + "learning_rate": 1.7740615631889525e-05, + "loss": 1.5258, + "step": 2826 + }, + { + "epoch": 0.3, + "learning_rate": 1.7738297771257496e-05, + "loss": 1.4323, + "step": 2827 + }, + { + "epoch": 0.3, + "learning_rate": 1.7735978873892393e-05, + "loss": 1.439, + "step": 2828 + }, + { + "epoch": 0.3, + "learning_rate": 1.773365894010489e-05, + "loss": 1.5658, + "step": 2829 + }, + { + "epoch": 0.3, + "learning_rate": 1.77313379702058e-05, + "loss": 1.4607, + "step": 2830 + }, + { + "epoch": 0.3, + "learning_rate": 1.7729015964506073e-05, + "loss": 1.5544, + "step": 2831 + }, + { + "epoch": 0.3, + "learning_rate": 1.7726692923316798e-05, + "loss": 1.4232, + "step": 2832 + }, + { + "epoch": 0.3, + "learning_rate": 1.77243688469492e-05, + "loss": 1.415, + "step": 2833 + }, + { + "epoch": 0.3, + "learning_rate": 1.772204373571465e-05, + "loss": 1.4658, + "step": 2834 + }, + { + "epoch": 0.3, + "learning_rate": 1.7719717589924647e-05, + "loss": 1.4678, + "step": 2835 + }, + { + "epoch": 0.3, + "learning_rate": 1.771739040989084e-05, + "loss": 1.3021, + "step": 2836 + }, + { + "epoch": 0.3, + "learning_rate": 1.771506219592501e-05, + "loss": 1.4045, + "step": 2837 + }, + { + "epoch": 0.3, + "learning_rate": 1.7712732948339085e-05, + "loss": 1.4593, + "step": 2838 + }, + { + "epoch": 0.3, + "learning_rate": 1.7710402667445108e-05, + "loss": 1.4175, + "step": 2839 + }, + { + "epoch": 0.3, + "learning_rate": 1.770807135355529e-05, + "loss": 1.3939, + "step": 2840 + }, + { + "epoch": 0.3, + "learning_rate": 1.7705739006981963e-05, + "loss": 1.6089, + "step": 2841 + }, + { + "epoch": 0.3, + "learning_rate": 1.77034056280376e-05, + "loss": 1.3952, + "step": 2842 + }, + { + "epoch": 0.3, + "learning_rate": 1.7701071217034818e-05, + "loss": 1.5086, + "step": 2843 + }, + { + "epoch": 0.3, + "learning_rate": 1.7698735774286362e-05, + "loss": 1.4706, + "step": 2844 + }, + { + "epoch": 0.3, + "learning_rate": 1.7696399300105128e-05, + "loss": 1.4286, + "step": 2845 + }, + { + "epoch": 0.3, + "learning_rate": 1.7694061794804137e-05, + "loss": 1.4418, + "step": 2846 + }, + { + "epoch": 0.3, + "learning_rate": 1.7691723258696562e-05, + "loss": 1.516, + "step": 2847 + }, + { + "epoch": 0.3, + "learning_rate": 1.76893836920957e-05, + "loss": 1.4354, + "step": 2848 + }, + { + "epoch": 0.3, + "learning_rate": 1.7687043095314998e-05, + "loss": 1.7503, + "step": 2849 + }, + { + "epoch": 0.3, + "learning_rate": 1.7684701468668032e-05, + "loss": 1.5985, + "step": 2850 + }, + { + "epoch": 0.3, + "learning_rate": 1.768235881246852e-05, + "loss": 1.442, + "step": 2851 + }, + { + "epoch": 0.3, + "learning_rate": 1.7680015127030322e-05, + "loss": 1.4924, + "step": 2852 + }, + { + "epoch": 0.3, + "learning_rate": 1.7677670412667425e-05, + "loss": 1.4461, + "step": 2853 + }, + { + "epoch": 0.3, + "learning_rate": 1.7675324669693968e-05, + "loss": 1.3823, + "step": 2854 + }, + { + "epoch": 0.3, + "learning_rate": 1.767297789842421e-05, + "loss": 1.452, + "step": 2855 + }, + { + "epoch": 0.3, + "learning_rate": 1.767063009917257e-05, + "loss": 1.46, + "step": 2856 + }, + { + "epoch": 0.3, + "learning_rate": 1.7668281272253587e-05, + "loss": 1.4129, + "step": 2857 + }, + { + "epoch": 0.3, + "learning_rate": 1.766593141798194e-05, + "loss": 1.4057, + "step": 2858 + }, + { + "epoch": 0.3, + "learning_rate": 1.7663580536672456e-05, + "loss": 1.5162, + "step": 2859 + }, + { + "epoch": 0.3, + "learning_rate": 1.7661228628640087e-05, + "loss": 1.5177, + "step": 2860 + }, + { + "epoch": 0.3, + "learning_rate": 1.7658875694199933e-05, + "loss": 1.4548, + "step": 2861 + }, + { + "epoch": 0.3, + "learning_rate": 1.7656521733667223e-05, + "loss": 1.4511, + "step": 2862 + }, + { + "epoch": 0.3, + "learning_rate": 1.765416674735733e-05, + "loss": 1.4778, + "step": 2863 + }, + { + "epoch": 0.3, + "learning_rate": 1.765181073558576e-05, + "loss": 1.3935, + "step": 2864 + }, + { + "epoch": 0.3, + "learning_rate": 1.7649453698668156e-05, + "loss": 1.4659, + "step": 2865 + }, + { + "epoch": 0.3, + "learning_rate": 1.7647095636920305e-05, + "loss": 1.7042, + "step": 2866 + }, + { + "epoch": 0.3, + "learning_rate": 1.7644736550658124e-05, + "loss": 1.7957, + "step": 2867 + }, + { + "epoch": 0.3, + "learning_rate": 1.764237644019767e-05, + "loss": 1.5139, + "step": 2868 + }, + { + "epoch": 0.3, + "learning_rate": 1.764001530585514e-05, + "loss": 1.4117, + "step": 2869 + }, + { + "epoch": 0.3, + "learning_rate": 1.7637653147946858e-05, + "loss": 1.4837, + "step": 2870 + }, + { + "epoch": 0.3, + "learning_rate": 1.7635289966789298e-05, + "loss": 1.4379, + "step": 2871 + }, + { + "epoch": 0.3, + "learning_rate": 1.7632925762699068e-05, + "loss": 1.4491, + "step": 2872 + }, + { + "epoch": 0.3, + "learning_rate": 1.7630560535992905e-05, + "loss": 1.4006, + "step": 2873 + }, + { + "epoch": 0.3, + "learning_rate": 1.7628194286987694e-05, + "loss": 1.5484, + "step": 2874 + }, + { + "epoch": 0.3, + "learning_rate": 1.7625827016000446e-05, + "loss": 1.4926, + "step": 2875 + }, + { + "epoch": 0.3, + "learning_rate": 1.762345872334832e-05, + "loss": 1.3909, + "step": 2876 + }, + { + "epoch": 0.3, + "learning_rate": 1.76210894093486e-05, + "loss": 1.405, + "step": 2877 + }, + { + "epoch": 0.3, + "learning_rate": 1.7618719074318718e-05, + "loss": 1.4736, + "step": 2878 + }, + { + "epoch": 0.3, + "learning_rate": 1.7616347718576238e-05, + "loss": 1.4445, + "step": 2879 + }, + { + "epoch": 0.3, + "learning_rate": 1.761397534243886e-05, + "loss": 1.4878, + "step": 2880 + }, + { + "epoch": 0.3, + "learning_rate": 1.7611601946224417e-05, + "loss": 1.4414, + "step": 2881 + }, + { + "epoch": 0.3, + "learning_rate": 1.760922753025089e-05, + "loss": 1.5657, + "step": 2882 + }, + { + "epoch": 0.3, + "learning_rate": 1.7606852094836385e-05, + "loss": 1.5008, + "step": 2883 + }, + { + "epoch": 0.3, + "learning_rate": 1.7604475640299153e-05, + "loss": 1.4922, + "step": 2884 + }, + { + "epoch": 0.3, + "learning_rate": 1.7602098166957577e-05, + "loss": 1.7451, + "step": 2885 + }, + { + "epoch": 0.3, + "learning_rate": 1.759971967513017e-05, + "loss": 1.7077, + "step": 2886 + }, + { + "epoch": 0.3, + "learning_rate": 1.75973401651356e-05, + "loss": 1.3986, + "step": 2887 + }, + { + "epoch": 0.3, + "learning_rate": 1.7594959637292656e-05, + "loss": 1.3966, + "step": 2888 + }, + { + "epoch": 0.3, + "learning_rate": 1.7592578091920264e-05, + "loss": 1.4086, + "step": 2889 + }, + { + "epoch": 0.3, + "learning_rate": 1.7590195529337495e-05, + "loss": 1.4481, + "step": 2890 + }, + { + "epoch": 0.3, + "learning_rate": 1.7587811949863548e-05, + "loss": 1.3974, + "step": 2891 + }, + { + "epoch": 0.3, + "learning_rate": 1.7585427353817758e-05, + "loss": 1.5013, + "step": 2892 + }, + { + "epoch": 0.3, + "learning_rate": 1.7583041741519608e-05, + "loss": 1.5454, + "step": 2893 + }, + { + "epoch": 0.3, + "learning_rate": 1.7580655113288708e-05, + "loss": 1.5033, + "step": 2894 + }, + { + "epoch": 0.3, + "learning_rate": 1.7578267469444793e-05, + "loss": 1.4332, + "step": 2895 + }, + { + "epoch": 0.3, + "learning_rate": 1.757587881030776e-05, + "loss": 1.4667, + "step": 2896 + }, + { + "epoch": 0.3, + "learning_rate": 1.7573489136197623e-05, + "loss": 1.4314, + "step": 2897 + }, + { + "epoch": 0.3, + "learning_rate": 1.7571098447434532e-05, + "loss": 1.4514, + "step": 2898 + }, + { + "epoch": 0.3, + "learning_rate": 1.7568706744338784e-05, + "loss": 1.4872, + "step": 2899 + }, + { + "epoch": 0.3, + "learning_rate": 1.7566314027230808e-05, + "loss": 1.4841, + "step": 2900 + }, + { + "epoch": 0.3, + "learning_rate": 1.7563920296431158e-05, + "loss": 1.3964, + "step": 2901 + }, + { + "epoch": 0.3, + "learning_rate": 1.7561525552260538e-05, + "loss": 1.4932, + "step": 2902 + }, + { + "epoch": 0.3, + "learning_rate": 1.755912979503978e-05, + "loss": 1.4153, + "step": 2903 + }, + { + "epoch": 0.3, + "learning_rate": 1.755673302508986e-05, + "loss": 1.4939, + "step": 2904 + }, + { + "epoch": 0.3, + "learning_rate": 1.755433524273187e-05, + "loss": 1.4437, + "step": 2905 + }, + { + "epoch": 0.3, + "learning_rate": 1.7551936448287067e-05, + "loss": 1.486, + "step": 2906 + }, + { + "epoch": 0.3, + "learning_rate": 1.754953664207682e-05, + "loss": 1.4362, + "step": 2907 + }, + { + "epoch": 0.3, + "learning_rate": 1.7547135824422635e-05, + "loss": 1.4954, + "step": 2908 + }, + { + "epoch": 0.31, + "learning_rate": 1.7544733995646174e-05, + "loss": 1.4552, + "step": 2909 + }, + { + "epoch": 0.31, + "learning_rate": 1.7542331156069213e-05, + "loss": 1.4654, + "step": 2910 + }, + { + "epoch": 0.31, + "learning_rate": 1.753992730601367e-05, + "loss": 1.4531, + "step": 2911 + }, + { + "epoch": 0.31, + "learning_rate": 1.75375224458016e-05, + "loss": 1.4949, + "step": 2912 + }, + { + "epoch": 0.31, + "learning_rate": 1.753511657575519e-05, + "loss": 1.3998, + "step": 2913 + }, + { + "epoch": 0.31, + "learning_rate": 1.753270969619677e-05, + "loss": 1.3904, + "step": 2914 + }, + { + "epoch": 0.31, + "learning_rate": 1.7530301807448794e-05, + "loss": 1.481, + "step": 2915 + }, + { + "epoch": 0.31, + "learning_rate": 1.7527892909833864e-05, + "loss": 1.4301, + "step": 2916 + }, + { + "epoch": 0.31, + "learning_rate": 1.7525483003674707e-05, + "loss": 1.4377, + "step": 2917 + }, + { + "epoch": 0.31, + "learning_rate": 1.7523072089294188e-05, + "loss": 1.5077, + "step": 2918 + }, + { + "epoch": 0.31, + "learning_rate": 1.752066016701531e-05, + "loss": 1.3802, + "step": 2919 + }, + { + "epoch": 0.31, + "learning_rate": 1.7518247237161205e-05, + "loss": 1.3991, + "step": 2920 + }, + { + "epoch": 0.31, + "learning_rate": 1.7515833300055146e-05, + "loss": 1.4283, + "step": 2921 + }, + { + "epoch": 0.31, + "learning_rate": 1.7513418356020535e-05, + "loss": 1.3688, + "step": 2922 + }, + { + "epoch": 0.31, + "learning_rate": 1.751100240538092e-05, + "loss": 1.4336, + "step": 2923 + }, + { + "epoch": 0.31, + "learning_rate": 1.7508585448459967e-05, + "loss": 1.4302, + "step": 2924 + }, + { + "epoch": 0.31, + "learning_rate": 1.7506167485581493e-05, + "loss": 1.4293, + "step": 2925 + }, + { + "epoch": 0.31, + "learning_rate": 1.750374851706944e-05, + "loss": 1.4262, + "step": 2926 + }, + { + "epoch": 0.31, + "learning_rate": 1.7501328543247892e-05, + "loss": 1.4128, + "step": 2927 + }, + { + "epoch": 0.31, + "learning_rate": 1.7498907564441054e-05, + "loss": 1.4258, + "step": 2928 + }, + { + "epoch": 0.31, + "learning_rate": 1.749648558097328e-05, + "loss": 1.4904, + "step": 2929 + }, + { + "epoch": 0.31, + "learning_rate": 1.749406259316906e-05, + "loss": 1.4628, + "step": 2930 + }, + { + "epoch": 0.31, + "learning_rate": 1.7491638601353004e-05, + "loss": 1.4908, + "step": 2931 + }, + { + "epoch": 0.31, + "learning_rate": 1.7489213605849867e-05, + "loss": 1.4563, + "step": 2932 + }, + { + "epoch": 0.31, + "learning_rate": 1.7486787606984533e-05, + "loss": 1.5006, + "step": 2933 + }, + { + "epoch": 0.31, + "learning_rate": 1.748436060508203e-05, + "loss": 1.424, + "step": 2934 + }, + { + "epoch": 0.31, + "learning_rate": 1.7481932600467508e-05, + "loss": 1.4136, + "step": 2935 + }, + { + "epoch": 0.31, + "learning_rate": 1.747950359346626e-05, + "loss": 1.3835, + "step": 2936 + }, + { + "epoch": 0.31, + "learning_rate": 1.747707358440371e-05, + "loss": 1.5284, + "step": 2937 + }, + { + "epoch": 0.31, + "learning_rate": 1.7474642573605418e-05, + "loss": 1.4592, + "step": 2938 + }, + { + "epoch": 0.31, + "learning_rate": 1.7472210561397075e-05, + "loss": 1.5483, + "step": 2939 + }, + { + "epoch": 0.31, + "learning_rate": 1.746977754810451e-05, + "loss": 1.521, + "step": 2940 + }, + { + "epoch": 0.31, + "learning_rate": 1.7467343534053683e-05, + "loss": 1.4276, + "step": 2941 + }, + { + "epoch": 0.31, + "learning_rate": 1.746490851957069e-05, + "loss": 1.4302, + "step": 2942 + }, + { + "epoch": 0.31, + "learning_rate": 1.746247250498176e-05, + "loss": 1.4439, + "step": 2943 + }, + { + "epoch": 0.31, + "learning_rate": 1.7460035490613255e-05, + "loss": 1.4991, + "step": 2944 + }, + { + "epoch": 0.31, + "learning_rate": 1.7457597476791674e-05, + "loss": 1.4188, + "step": 2945 + }, + { + "epoch": 0.31, + "learning_rate": 1.7455158463843648e-05, + "loss": 1.4685, + "step": 2946 + }, + { + "epoch": 0.31, + "learning_rate": 1.745271845209594e-05, + "loss": 1.3811, + "step": 2947 + }, + { + "epoch": 0.31, + "learning_rate": 1.7450277441875454e-05, + "loss": 1.4869, + "step": 2948 + }, + { + "epoch": 0.31, + "learning_rate": 1.7447835433509218e-05, + "loss": 1.5001, + "step": 2949 + }, + { + "epoch": 0.31, + "learning_rate": 1.74453924273244e-05, + "loss": 1.4757, + "step": 2950 + }, + { + "epoch": 0.31, + "learning_rate": 1.74429484236483e-05, + "loss": 1.5072, + "step": 2951 + }, + { + "epoch": 0.31, + "learning_rate": 1.744050342280835e-05, + "loss": 1.4242, + "step": 2952 + }, + { + "epoch": 0.31, + "learning_rate": 1.743805742513212e-05, + "loss": 1.4462, + "step": 2953 + }, + { + "epoch": 0.31, + "learning_rate": 1.743561043094731e-05, + "loss": 1.6815, + "step": 2954 + }, + { + "epoch": 0.31, + "learning_rate": 1.7433162440581755e-05, + "loss": 1.427, + "step": 2955 + }, + { + "epoch": 0.31, + "learning_rate": 1.7430713454363423e-05, + "loss": 1.2933, + "step": 2956 + }, + { + "epoch": 0.31, + "learning_rate": 1.742826347262041e-05, + "loss": 1.4247, + "step": 2957 + }, + { + "epoch": 0.31, + "learning_rate": 1.7425812495680955e-05, + "loss": 1.399, + "step": 2958 + }, + { + "epoch": 0.31, + "learning_rate": 1.742336052387343e-05, + "loss": 1.4818, + "step": 2959 + }, + { + "epoch": 0.31, + "learning_rate": 1.742090755752633e-05, + "loss": 1.3839, + "step": 2960 + }, + { + "epoch": 0.31, + "learning_rate": 1.741845359696829e-05, + "loss": 1.4669, + "step": 2961 + }, + { + "epoch": 0.31, + "learning_rate": 1.741599864252808e-05, + "loss": 1.468, + "step": 2962 + }, + { + "epoch": 0.31, + "learning_rate": 1.74135426945346e-05, + "loss": 1.4135, + "step": 2963 + }, + { + "epoch": 0.31, + "learning_rate": 1.7411085753316882e-05, + "loss": 1.5899, + "step": 2964 + }, + { + "epoch": 0.31, + "learning_rate": 1.74086278192041e-05, + "loss": 1.6115, + "step": 2965 + }, + { + "epoch": 0.31, + "learning_rate": 1.740616889252554e-05, + "loss": 1.3988, + "step": 2966 + }, + { + "epoch": 0.31, + "learning_rate": 1.740370897361065e-05, + "loss": 1.5001, + "step": 2967 + }, + { + "epoch": 0.31, + "learning_rate": 1.740124806278899e-05, + "loss": 1.459, + "step": 2968 + }, + { + "epoch": 0.31, + "learning_rate": 1.7398786160390258e-05, + "loss": 1.4489, + "step": 2969 + }, + { + "epoch": 0.31, + "learning_rate": 1.7396323266744283e-05, + "loss": 1.4397, + "step": 2970 + }, + { + "epoch": 0.31, + "learning_rate": 1.7393859382181033e-05, + "loss": 1.4687, + "step": 2971 + }, + { + "epoch": 0.31, + "learning_rate": 1.7391394507030606e-05, + "loss": 1.4495, + "step": 2972 + }, + { + "epoch": 0.31, + "learning_rate": 1.738892864162323e-05, + "loss": 1.4745, + "step": 2973 + }, + { + "epoch": 0.31, + "learning_rate": 1.7386461786289274e-05, + "loss": 1.3943, + "step": 2974 + }, + { + "epoch": 0.31, + "learning_rate": 1.738399394135922e-05, + "loss": 1.4595, + "step": 2975 + }, + { + "epoch": 0.31, + "learning_rate": 1.738152510716371e-05, + "loss": 1.4023, + "step": 2976 + }, + { + "epoch": 0.31, + "learning_rate": 1.7379055284033493e-05, + "loss": 1.3938, + "step": 2977 + }, + { + "epoch": 0.31, + "learning_rate": 1.7376584472299468e-05, + "loss": 1.4576, + "step": 2978 + }, + { + "epoch": 0.31, + "learning_rate": 1.737411267229266e-05, + "loss": 1.424, + "step": 2979 + }, + { + "epoch": 0.31, + "learning_rate": 1.7371639884344225e-05, + "loss": 1.4224, + "step": 2980 + }, + { + "epoch": 0.31, + "learning_rate": 1.736916610878545e-05, + "loss": 1.4228, + "step": 2981 + }, + { + "epoch": 0.31, + "learning_rate": 1.7366691345947768e-05, + "loss": 1.5021, + "step": 2982 + }, + { + "epoch": 0.31, + "learning_rate": 1.736421559616272e-05, + "loss": 1.3589, + "step": 2983 + }, + { + "epoch": 0.31, + "learning_rate": 1.7361738859762007e-05, + "loss": 1.4748, + "step": 2984 + }, + { + "epoch": 0.31, + "learning_rate": 1.735926113707743e-05, + "loss": 1.3974, + "step": 2985 + }, + { + "epoch": 0.31, + "eval_loss": 1.4849082231521606, + "eval_runtime": 77.3271, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2985 + }, + { + "epoch": 0.31, + "learning_rate": 1.735678242844096e-05, + "loss": 1.392, + "step": 2986 + }, + { + "epoch": 0.31, + "learning_rate": 1.735430273418467e-05, + "loss": 1.4277, + "step": 2987 + }, + { + "epoch": 0.31, + "learning_rate": 1.735182205464077e-05, + "loss": 1.4216, + "step": 2988 + }, + { + "epoch": 0.31, + "learning_rate": 1.7349340390141617e-05, + "loss": 1.4546, + "step": 2989 + }, + { + "epoch": 0.31, + "learning_rate": 1.734685774101969e-05, + "loss": 1.4264, + "step": 2990 + }, + { + "epoch": 0.31, + "learning_rate": 1.7344374107607593e-05, + "loss": 1.4307, + "step": 2991 + }, + { + "epoch": 0.31, + "learning_rate": 1.7341889490238076e-05, + "loss": 1.4266, + "step": 2992 + }, + { + "epoch": 0.31, + "learning_rate": 1.7339403889244008e-05, + "loss": 1.4486, + "step": 2993 + }, + { + "epoch": 0.31, + "learning_rate": 1.7336917304958403e-05, + "loss": 1.4345, + "step": 2994 + }, + { + "epoch": 0.31, + "learning_rate": 1.7334429737714395e-05, + "loss": 1.476, + "step": 2995 + }, + { + "epoch": 0.31, + "learning_rate": 1.7331941187845248e-05, + "loss": 1.5148, + "step": 2996 + }, + { + "epoch": 0.31, + "learning_rate": 1.7329451655684372e-05, + "loss": 1.4026, + "step": 2997 + }, + { + "epoch": 0.31, + "learning_rate": 1.7326961141565303e-05, + "loss": 1.3935, + "step": 2998 + }, + { + "epoch": 0.31, + "learning_rate": 1.73244696458217e-05, + "loss": 1.4483, + "step": 2999 + }, + { + "epoch": 0.31, + "learning_rate": 1.7321977168787356e-05, + "loss": 1.5197, + "step": 3000 + }, + { + "epoch": 0.31, + "learning_rate": 1.7319483710796208e-05, + "loss": 1.4648, + "step": 3001 + }, + { + "epoch": 0.31, + "learning_rate": 1.7316989272182308e-05, + "loss": 1.4171, + "step": 3002 + }, + { + "epoch": 0.31, + "learning_rate": 1.731449385327985e-05, + "loss": 1.4541, + "step": 3003 + }, + { + "epoch": 0.32, + "learning_rate": 1.731199745442316e-05, + "loss": 1.4605, + "step": 3004 + }, + { + "epoch": 0.32, + "learning_rate": 1.7309500075946683e-05, + "loss": 1.5122, + "step": 3005 + }, + { + "epoch": 0.32, + "learning_rate": 1.7307001718185007e-05, + "loss": 1.5243, + "step": 3006 + }, + { + "epoch": 0.32, + "learning_rate": 1.7304502381472844e-05, + "loss": 1.4997, + "step": 3007 + }, + { + "epoch": 0.32, + "learning_rate": 1.730200206614505e-05, + "loss": 1.4891, + "step": 3008 + }, + { + "epoch": 0.32, + "learning_rate": 1.72995007725366e-05, + "loss": 1.4376, + "step": 3009 + }, + { + "epoch": 0.32, + "learning_rate": 1.7296998500982595e-05, + "loss": 1.4403, + "step": 3010 + }, + { + "epoch": 0.32, + "learning_rate": 1.7294495251818285e-05, + "loss": 1.5153, + "step": 3011 + }, + { + "epoch": 0.32, + "learning_rate": 1.729199102537904e-05, + "loss": 1.4996, + "step": 3012 + }, + { + "epoch": 0.32, + "learning_rate": 1.7289485822000356e-05, + "loss": 1.5302, + "step": 3013 + }, + { + "epoch": 0.32, + "learning_rate": 1.7286979642017867e-05, + "loss": 1.5641, + "step": 3014 + }, + { + "epoch": 0.32, + "learning_rate": 1.728447248576734e-05, + "loss": 1.438, + "step": 3015 + }, + { + "epoch": 0.32, + "learning_rate": 1.7281964353584674e-05, + "loss": 1.4796, + "step": 3016 + }, + { + "epoch": 0.32, + "learning_rate": 1.727945524580588e-05, + "loss": 1.4413, + "step": 3017 + }, + { + "epoch": 0.32, + "learning_rate": 1.727694516276713e-05, + "loss": 1.3966, + "step": 3018 + }, + { + "epoch": 0.32, + "learning_rate": 1.72744341048047e-05, + "loss": 1.5267, + "step": 3019 + }, + { + "epoch": 0.32, + "learning_rate": 1.727192207225501e-05, + "loss": 1.4284, + "step": 3020 + }, + { + "epoch": 0.32, + "learning_rate": 1.726940906545461e-05, + "loss": 1.5137, + "step": 3021 + }, + { + "epoch": 0.32, + "learning_rate": 1.7266895084740173e-05, + "loss": 1.3966, + "step": 3022 + }, + { + "epoch": 0.32, + "learning_rate": 1.7264380130448514e-05, + "loss": 1.4156, + "step": 3023 + }, + { + "epoch": 0.32, + "learning_rate": 1.726186420291657e-05, + "loss": 1.4644, + "step": 3024 + }, + { + "epoch": 0.32, + "learning_rate": 1.725934730248141e-05, + "loss": 1.4768, + "step": 3025 + }, + { + "epoch": 0.32, + "learning_rate": 1.7256829429480233e-05, + "loss": 1.4428, + "step": 3026 + }, + { + "epoch": 0.32, + "learning_rate": 1.7254310584250373e-05, + "loss": 1.4495, + "step": 3027 + }, + { + "epoch": 0.32, + "learning_rate": 1.725179076712929e-05, + "loss": 1.3867, + "step": 3028 + }, + { + "epoch": 0.32, + "learning_rate": 1.7249269978454567e-05, + "loss": 1.5011, + "step": 3029 + }, + { + "epoch": 0.32, + "learning_rate": 1.7246748218563937e-05, + "loss": 1.3916, + "step": 3030 + }, + { + "epoch": 0.32, + "learning_rate": 1.7244225487795238e-05, + "loss": 1.4984, + "step": 3031 + }, + { + "epoch": 0.32, + "learning_rate": 1.7241701786486464e-05, + "loss": 1.5776, + "step": 3032 + }, + { + "epoch": 0.32, + "learning_rate": 1.7239177114975717e-05, + "loss": 1.5018, + "step": 3033 + }, + { + "epoch": 0.32, + "learning_rate": 1.7236651473601244e-05, + "loss": 1.5042, + "step": 3034 + }, + { + "epoch": 0.32, + "learning_rate": 1.723412486270141e-05, + "loss": 1.4636, + "step": 3035 + }, + { + "epoch": 0.32, + "learning_rate": 1.723159728261472e-05, + "loss": 1.5612, + "step": 3036 + }, + { + "epoch": 0.32, + "learning_rate": 1.7229068733679803e-05, + "loss": 1.4399, + "step": 3037 + }, + { + "epoch": 0.32, + "learning_rate": 1.7226539216235424e-05, + "loss": 1.5635, + "step": 3038 + }, + { + "epoch": 0.32, + "learning_rate": 1.7224008730620468e-05, + "loss": 1.4329, + "step": 3039 + }, + { + "epoch": 0.32, + "learning_rate": 1.7221477277173956e-05, + "loss": 1.4886, + "step": 3040 + }, + { + "epoch": 0.32, + "learning_rate": 1.721894485623504e-05, + "loss": 1.4741, + "step": 3041 + }, + { + "epoch": 0.32, + "learning_rate": 1.7216411468143e-05, + "loss": 1.4678, + "step": 3042 + }, + { + "epoch": 0.32, + "learning_rate": 1.721387711323724e-05, + "loss": 1.4758, + "step": 3043 + }, + { + "epoch": 0.32, + "learning_rate": 1.72113417918573e-05, + "loss": 1.441, + "step": 3044 + }, + { + "epoch": 0.32, + "learning_rate": 1.7208805504342855e-05, + "loss": 1.4328, + "step": 3045 + }, + { + "epoch": 0.32, + "learning_rate": 1.720626825103369e-05, + "loss": 1.4254, + "step": 3046 + }, + { + "epoch": 0.32, + "learning_rate": 1.7203730032269744e-05, + "loss": 1.4462, + "step": 3047 + }, + { + "epoch": 0.32, + "learning_rate": 1.7201190848391066e-05, + "loss": 1.4826, + "step": 3048 + }, + { + "epoch": 0.32, + "learning_rate": 1.719865069973784e-05, + "loss": 1.4215, + "step": 3049 + }, + { + "epoch": 0.32, + "learning_rate": 1.7196109586650385e-05, + "loss": 1.4291, + "step": 3050 + }, + { + "epoch": 0.32, + "learning_rate": 1.7193567509469146e-05, + "loss": 1.5005, + "step": 3051 + }, + { + "epoch": 0.32, + "learning_rate": 1.719102446853469e-05, + "loss": 1.4216, + "step": 3052 + }, + { + "epoch": 0.32, + "learning_rate": 1.7188480464187725e-05, + "loss": 1.4349, + "step": 3053 + }, + { + "epoch": 0.32, + "learning_rate": 1.718593549676908e-05, + "loss": 1.4784, + "step": 3054 + }, + { + "epoch": 0.32, + "learning_rate": 1.7183389566619714e-05, + "loss": 1.4325, + "step": 3055 + }, + { + "epoch": 0.32, + "learning_rate": 1.7180842674080717e-05, + "loss": 1.5387, + "step": 3056 + }, + { + "epoch": 0.32, + "learning_rate": 1.717829481949331e-05, + "loss": 1.655, + "step": 3057 + }, + { + "epoch": 0.32, + "learning_rate": 1.717574600319883e-05, + "loss": 1.4623, + "step": 3058 + }, + { + "epoch": 0.32, + "learning_rate": 1.7173196225538768e-05, + "loss": 1.4646, + "step": 3059 + }, + { + "epoch": 0.32, + "learning_rate": 1.717064548685472e-05, + "loss": 1.4641, + "step": 3060 + }, + { + "epoch": 0.32, + "learning_rate": 1.7168093787488418e-05, + "loss": 1.4033, + "step": 3061 + }, + { + "epoch": 0.32, + "learning_rate": 1.7165541127781726e-05, + "loss": 1.4085, + "step": 3062 + }, + { + "epoch": 0.32, + "learning_rate": 1.716298750807664e-05, + "loss": 1.387, + "step": 3063 + }, + { + "epoch": 0.32, + "learning_rate": 1.7160432928715272e-05, + "loss": 1.4197, + "step": 3064 + }, + { + "epoch": 0.32, + "learning_rate": 1.7157877390039872e-05, + "loss": 1.4883, + "step": 3065 + }, + { + "epoch": 0.32, + "learning_rate": 1.7155320892392818e-05, + "loss": 1.4865, + "step": 3066 + }, + { + "epoch": 0.32, + "learning_rate": 1.715276343611662e-05, + "loss": 1.4532, + "step": 3067 + }, + { + "epoch": 0.32, + "learning_rate": 1.71502050215539e-05, + "loss": 1.3991, + "step": 3068 + }, + { + "epoch": 0.32, + "learning_rate": 1.7147645649047424e-05, + "loss": 1.4318, + "step": 3069 + }, + { + "epoch": 0.32, + "learning_rate": 1.714508531894009e-05, + "loss": 1.3616, + "step": 3070 + }, + { + "epoch": 0.32, + "learning_rate": 1.7142524031574904e-05, + "loss": 1.4481, + "step": 3071 + }, + { + "epoch": 0.32, + "learning_rate": 1.7139961787295022e-05, + "loss": 1.3897, + "step": 3072 + }, + { + "epoch": 0.32, + "learning_rate": 1.7137398586443716e-05, + "loss": 1.3128, + "step": 3073 + }, + { + "epoch": 0.32, + "learning_rate": 1.713483442936439e-05, + "loss": 1.4481, + "step": 3074 + }, + { + "epoch": 0.32, + "learning_rate": 1.713226931640057e-05, + "loss": 1.5374, + "step": 3075 + }, + { + "epoch": 0.32, + "learning_rate": 1.7129703247895923e-05, + "loss": 1.4247, + "step": 3076 + }, + { + "epoch": 0.32, + "learning_rate": 1.712713622419423e-05, + "loss": 1.4098, + "step": 3077 + }, + { + "epoch": 0.32, + "learning_rate": 1.7124568245639414e-05, + "loss": 1.4558, + "step": 3078 + }, + { + "epoch": 0.32, + "learning_rate": 1.7121999312575507e-05, + "loss": 1.4484, + "step": 3079 + }, + { + "epoch": 0.32, + "learning_rate": 1.711942942534669e-05, + "loss": 1.4236, + "step": 3080 + }, + { + "epoch": 0.32, + "learning_rate": 1.7116858584297253e-05, + "loss": 1.613, + "step": 3081 + }, + { + "epoch": 0.32, + "learning_rate": 1.711428678977163e-05, + "loss": 1.4503, + "step": 3082 + }, + { + "epoch": 0.32, + "learning_rate": 1.7111714042114376e-05, + "loss": 1.4072, + "step": 3083 + }, + { + "epoch": 0.32, + "learning_rate": 1.7109140341670168e-05, + "loss": 1.5999, + "step": 3084 + }, + { + "epoch": 0.32, + "learning_rate": 1.7106565688783815e-05, + "loss": 1.4129, + "step": 3085 + }, + { + "epoch": 0.32, + "learning_rate": 1.710399008380026e-05, + "loss": 1.3973, + "step": 3086 + }, + { + "epoch": 0.32, + "learning_rate": 1.710141352706456e-05, + "loss": 1.4292, + "step": 3087 + }, + { + "epoch": 0.32, + "learning_rate": 1.709883601892192e-05, + "loss": 1.4372, + "step": 3088 + }, + { + "epoch": 0.32, + "learning_rate": 1.7096257559717647e-05, + "loss": 1.4924, + "step": 3089 + }, + { + "epoch": 0.32, + "learning_rate": 1.7093678149797196e-05, + "loss": 1.4222, + "step": 3090 + }, + { + "epoch": 0.32, + "learning_rate": 1.7091097789506137e-05, + "loss": 1.4797, + "step": 3091 + }, + { + "epoch": 0.32, + "learning_rate": 1.7088516479190175e-05, + "loss": 1.4738, + "step": 3092 + }, + { + "epoch": 0.32, + "learning_rate": 1.708593421919514e-05, + "loss": 1.5371, + "step": 3093 + }, + { + "epoch": 0.32, + "learning_rate": 1.7083351009866988e-05, + "loss": 1.3802, + "step": 3094 + }, + { + "epoch": 0.32, + "learning_rate": 1.7080766851551795e-05, + "loss": 1.4292, + "step": 3095 + }, + { + "epoch": 0.32, + "learning_rate": 1.707818174459578e-05, + "loss": 1.4478, + "step": 3096 + }, + { + "epoch": 0.32, + "learning_rate": 1.7075595689345285e-05, + "loss": 1.4619, + "step": 3097 + }, + { + "epoch": 0.32, + "learning_rate": 1.7073008686146763e-05, + "loss": 1.4603, + "step": 3098 + }, + { + "epoch": 0.32, + "learning_rate": 1.7070420735346815e-05, + "loss": 1.4548, + "step": 3099 + }, + { + "epoch": 0.33, + "learning_rate": 1.7067831837292157e-05, + "loss": 1.3638, + "step": 3100 + }, + { + "epoch": 0.33, + "learning_rate": 1.7065241992329634e-05, + "loss": 1.4284, + "step": 3101 + }, + { + "epoch": 0.33, + "learning_rate": 1.7062651200806217e-05, + "loss": 1.386, + "step": 3102 + }, + { + "epoch": 0.33, + "learning_rate": 1.7060059463069013e-05, + "loss": 1.5483, + "step": 3103 + }, + { + "epoch": 0.33, + "learning_rate": 1.705746677946524e-05, + "loss": 1.4963, + "step": 3104 + }, + { + "epoch": 0.33, + "learning_rate": 1.7054873150342257e-05, + "loss": 1.4539, + "step": 3105 + }, + { + "epoch": 0.33, + "learning_rate": 1.705227857604754e-05, + "loss": 1.4361, + "step": 3106 + }, + { + "epoch": 0.33, + "learning_rate": 1.7049683056928695e-05, + "loss": 1.3735, + "step": 3107 + }, + { + "epoch": 0.33, + "learning_rate": 1.7047086593333454e-05, + "loss": 1.4324, + "step": 3108 + }, + { + "epoch": 0.33, + "learning_rate": 1.7044489185609685e-05, + "loss": 1.5037, + "step": 3109 + }, + { + "epoch": 0.33, + "learning_rate": 1.704189083410536e-05, + "loss": 1.3913, + "step": 3110 + }, + { + "epoch": 0.33, + "learning_rate": 1.7039291539168604e-05, + "loss": 1.3233, + "step": 3111 + }, + { + "epoch": 0.33, + "learning_rate": 1.703669130114765e-05, + "loss": 1.4897, + "step": 3112 + }, + { + "epoch": 0.33, + "learning_rate": 1.7034090120390862e-05, + "loss": 1.4843, + "step": 3113 + }, + { + "epoch": 0.33, + "learning_rate": 1.7031487997246735e-05, + "loss": 1.3674, + "step": 3114 + }, + { + "epoch": 0.33, + "learning_rate": 1.7028884932063883e-05, + "loss": 1.4475, + "step": 3115 + }, + { + "epoch": 0.33, + "learning_rate": 1.702628092519105e-05, + "loss": 1.4134, + "step": 3116 + }, + { + "epoch": 0.33, + "learning_rate": 1.7023675976977108e-05, + "loss": 1.4484, + "step": 3117 + }, + { + "epoch": 0.33, + "learning_rate": 1.702107008777106e-05, + "loss": 1.407, + "step": 3118 + }, + { + "epoch": 0.33, + "learning_rate": 1.7018463257922005e-05, + "loss": 1.5443, + "step": 3119 + }, + { + "epoch": 0.33, + "learning_rate": 1.701585548777922e-05, + "loss": 1.4548, + "step": 3120 + }, + { + "epoch": 0.33, + "learning_rate": 1.7013246777692063e-05, + "loss": 1.4252, + "step": 3121 + }, + { + "epoch": 0.33, + "learning_rate": 1.7010637128010037e-05, + "loss": 1.3748, + "step": 3122 + }, + { + "epoch": 0.33, + "learning_rate": 1.7008026539082767e-05, + "loss": 1.3804, + "step": 3123 + }, + { + "epoch": 0.33, + "learning_rate": 1.7005415011260008e-05, + "loss": 1.4203, + "step": 3124 + }, + { + "epoch": 0.33, + "learning_rate": 1.7002802544891634e-05, + "loss": 1.4195, + "step": 3125 + }, + { + "epoch": 0.33, + "learning_rate": 1.700018914032765e-05, + "loss": 1.4188, + "step": 3126 + }, + { + "epoch": 0.33, + "learning_rate": 1.699757479791819e-05, + "loss": 1.3884, + "step": 3127 + }, + { + "epoch": 0.33, + "learning_rate": 1.6994959518013502e-05, + "loss": 1.4111, + "step": 3128 + }, + { + "epoch": 0.33, + "learning_rate": 1.6992343300963963e-05, + "loss": 1.5452, + "step": 3129 + }, + { + "epoch": 0.33, + "learning_rate": 1.6989726147120087e-05, + "loss": 1.4097, + "step": 3130 + }, + { + "epoch": 0.33, + "learning_rate": 1.6987108056832506e-05, + "loss": 1.481, + "step": 3131 + }, + { + "epoch": 0.33, + "learning_rate": 1.6984489030451973e-05, + "loss": 1.4505, + "step": 3132 + }, + { + "epoch": 0.33, + "learning_rate": 1.6981869068329368e-05, + "loss": 1.4281, + "step": 3133 + }, + { + "epoch": 0.33, + "learning_rate": 1.69792481708157e-05, + "loss": 1.4555, + "step": 3134 + }, + { + "epoch": 0.33, + "learning_rate": 1.6976626338262103e-05, + "loss": 1.4525, + "step": 3135 + }, + { + "epoch": 0.33, + "learning_rate": 1.6974003571019837e-05, + "loss": 1.3765, + "step": 3136 + }, + { + "epoch": 0.33, + "learning_rate": 1.6971379869440286e-05, + "loss": 1.3998, + "step": 3137 + }, + { + "epoch": 0.33, + "learning_rate": 1.696875523387495e-05, + "loss": 1.5103, + "step": 3138 + }, + { + "epoch": 0.33, + "learning_rate": 1.6966129664675474e-05, + "loss": 1.427, + "step": 3139 + }, + { + "epoch": 0.33, + "learning_rate": 1.6963503162193612e-05, + "loss": 1.4362, + "step": 3140 + }, + { + "epoch": 0.33, + "learning_rate": 1.6960875726781246e-05, + "loss": 1.4073, + "step": 3141 + }, + { + "epoch": 0.33, + "learning_rate": 1.6958247358790388e-05, + "loss": 1.4014, + "step": 3142 + }, + { + "epoch": 0.33, + "learning_rate": 1.6955618058573165e-05, + "loss": 1.4244, + "step": 3143 + }, + { + "epoch": 0.33, + "learning_rate": 1.6952987826481847e-05, + "loss": 1.47, + "step": 3144 + }, + { + "epoch": 0.33, + "learning_rate": 1.6950356662868814e-05, + "loss": 1.5112, + "step": 3145 + }, + { + "epoch": 0.33, + "learning_rate": 1.6947724568086562e-05, + "loss": 1.3398, + "step": 3146 + }, + { + "epoch": 0.33, + "learning_rate": 1.694509154248774e-05, + "loss": 1.4584, + "step": 3147 + }, + { + "epoch": 0.33, + "learning_rate": 1.69424575864251e-05, + "loss": 1.4383, + "step": 3148 + }, + { + "epoch": 0.33, + "learning_rate": 1.6939822700251523e-05, + "loss": 1.3869, + "step": 3149 + }, + { + "epoch": 0.33, + "learning_rate": 1.6937186884320015e-05, + "loss": 1.4453, + "step": 3150 + }, + { + "epoch": 0.33, + "learning_rate": 1.6934550138983713e-05, + "loss": 1.3355, + "step": 3151 + }, + { + "epoch": 0.33, + "learning_rate": 1.6931912464595866e-05, + "loss": 1.5573, + "step": 3152 + }, + { + "epoch": 0.33, + "learning_rate": 1.6929273861509865e-05, + "loss": 1.439, + "step": 3153 + }, + { + "epoch": 0.33, + "learning_rate": 1.6926634330079203e-05, + "loss": 1.6079, + "step": 3154 + }, + { + "epoch": 0.33, + "learning_rate": 1.692399387065752e-05, + "loss": 1.6973, + "step": 3155 + }, + { + "epoch": 0.33, + "learning_rate": 1.692135248359856e-05, + "loss": 1.3769, + "step": 3156 + }, + { + "epoch": 0.33, + "learning_rate": 1.6918710169256206e-05, + "loss": 1.4454, + "step": 3157 + }, + { + "epoch": 0.33, + "learning_rate": 1.691606692798446e-05, + "loss": 1.4495, + "step": 3158 + }, + { + "epoch": 0.33, + "learning_rate": 1.691342276013745e-05, + "loss": 1.4292, + "step": 3159 + }, + { + "epoch": 0.33, + "learning_rate": 1.691077766606942e-05, + "loss": 1.4405, + "step": 3160 + }, + { + "epoch": 0.33, + "learning_rate": 1.6908131646134757e-05, + "loss": 1.3683, + "step": 3161 + }, + { + "epoch": 0.33, + "learning_rate": 1.690548470068795e-05, + "loss": 1.4731, + "step": 3162 + }, + { + "epoch": 0.33, + "learning_rate": 1.690283683008362e-05, + "loss": 1.4323, + "step": 3163 + }, + { + "epoch": 0.33, + "learning_rate": 1.6900188034676518e-05, + "loss": 1.5133, + "step": 3164 + }, + { + "epoch": 0.33, + "learning_rate": 1.6897538314821516e-05, + "loss": 1.5529, + "step": 3165 + }, + { + "epoch": 0.33, + "learning_rate": 1.6894887670873605e-05, + "loss": 1.4427, + "step": 3166 + }, + { + "epoch": 0.33, + "learning_rate": 1.6892236103187904e-05, + "loss": 1.4344, + "step": 3167 + }, + { + "epoch": 0.33, + "learning_rate": 1.6889583612119657e-05, + "loss": 1.4291, + "step": 3168 + }, + { + "epoch": 0.33, + "learning_rate": 1.6886930198024226e-05, + "loss": 1.4683, + "step": 3169 + }, + { + "epoch": 0.33, + "learning_rate": 1.6884275861257106e-05, + "loss": 1.4442, + "step": 3170 + }, + { + "epoch": 0.33, + "learning_rate": 1.6881620602173905e-05, + "loss": 1.4509, + "step": 3171 + }, + { + "epoch": 0.33, + "learning_rate": 1.6878964421130362e-05, + "loss": 1.5113, + "step": 3172 + }, + { + "epoch": 0.33, + "learning_rate": 1.6876307318482334e-05, + "loss": 1.4261, + "step": 3173 + }, + { + "epoch": 0.33, + "learning_rate": 1.6873649294585805e-05, + "loss": 1.445, + "step": 3174 + }, + { + "epoch": 0.33, + "learning_rate": 1.6870990349796886e-05, + "loss": 1.4603, + "step": 3175 + }, + { + "epoch": 0.33, + "learning_rate": 1.68683304844718e-05, + "loss": 1.41, + "step": 3176 + }, + { + "epoch": 0.33, + "learning_rate": 1.686566969896691e-05, + "loss": 1.4018, + "step": 3177 + }, + { + "epoch": 0.33, + "learning_rate": 1.6863007993638687e-05, + "loss": 1.422, + "step": 3178 + }, + { + "epoch": 0.33, + "learning_rate": 1.6860345368843727e-05, + "loss": 1.4412, + "step": 3179 + }, + { + "epoch": 0.33, + "learning_rate": 1.6857681824938768e-05, + "loss": 1.5411, + "step": 3180 + }, + { + "epoch": 0.33, + "learning_rate": 1.685501736228064e-05, + "loss": 1.4416, + "step": 3181 + }, + { + "epoch": 0.33, + "learning_rate": 1.685235198122632e-05, + "loss": 1.5113, + "step": 3182 + }, + { + "epoch": 0.33, + "learning_rate": 1.6849685682132903e-05, + "loss": 1.423, + "step": 3183 + }, + { + "epoch": 0.33, + "learning_rate": 1.68470184653576e-05, + "loss": 1.404, + "step": 3184 + }, + { + "epoch": 0.33, + "eval_loss": 1.4771089553833008, + "eval_runtime": 77.4034, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3184 + }, + { + "epoch": 0.33, + "learning_rate": 1.6844350331257747e-05, + "loss": 1.4624, + "step": 3185 + }, + { + "epoch": 0.33, + "learning_rate": 1.6841681280190814e-05, + "loss": 1.4306, + "step": 3186 + }, + { + "epoch": 0.33, + "learning_rate": 1.683901131251438e-05, + "loss": 1.42, + "step": 3187 + }, + { + "epoch": 0.33, + "learning_rate": 1.6836340428586155e-05, + "loss": 1.4787, + "step": 3188 + }, + { + "epoch": 0.33, + "learning_rate": 1.6833668628763965e-05, + "loss": 1.3485, + "step": 3189 + }, + { + "epoch": 0.33, + "learning_rate": 1.683099591340576e-05, + "loss": 1.3674, + "step": 3190 + }, + { + "epoch": 0.33, + "learning_rate": 1.6828322282869627e-05, + "loss": 1.5187, + "step": 3191 + }, + { + "epoch": 0.33, + "learning_rate": 1.682564773751375e-05, + "loss": 1.4847, + "step": 3192 + }, + { + "epoch": 0.33, + "learning_rate": 1.682297227769646e-05, + "loss": 1.4815, + "step": 3193 + }, + { + "epoch": 0.33, + "learning_rate": 1.682029590377619e-05, + "loss": 1.4281, + "step": 3194 + }, + { + "epoch": 0.34, + "learning_rate": 1.6817618616111517e-05, + "loss": 1.4734, + "step": 3195 + }, + { + "epoch": 0.34, + "learning_rate": 1.681494041506112e-05, + "loss": 1.4861, + "step": 3196 + }, + { + "epoch": 0.34, + "learning_rate": 1.6812261300983808e-05, + "loss": 1.4372, + "step": 3197 + }, + { + "epoch": 0.34, + "learning_rate": 1.680958127423852e-05, + "loss": 1.4396, + "step": 3198 + }, + { + "epoch": 0.34, + "learning_rate": 1.680690033518431e-05, + "loss": 1.4225, + "step": 3199 + }, + { + "epoch": 0.34, + "learning_rate": 1.6804218484180347e-05, + "loss": 1.4925, + "step": 3200 + }, + { + "epoch": 0.34, + "learning_rate": 1.6801535721585942e-05, + "loss": 1.4306, + "step": 3201 + }, + { + "epoch": 0.34, + "learning_rate": 1.6798852047760506e-05, + "loss": 1.4298, + "step": 3202 + }, + { + "epoch": 0.34, + "learning_rate": 1.6796167463063588e-05, + "loss": 1.4725, + "step": 3203 + }, + { + "epoch": 0.34, + "learning_rate": 1.679348196785485e-05, + "loss": 1.4648, + "step": 3204 + }, + { + "epoch": 0.34, + "learning_rate": 1.6790795562494087e-05, + "loss": 1.4152, + "step": 3205 + }, + { + "epoch": 0.34, + "learning_rate": 1.6788108247341198e-05, + "loss": 1.4637, + "step": 3206 + }, + { + "epoch": 0.34, + "learning_rate": 1.6785420022756216e-05, + "loss": 1.4077, + "step": 3207 + }, + { + "epoch": 0.34, + "learning_rate": 1.67827308890993e-05, + "loss": 1.4585, + "step": 3208 + }, + { + "epoch": 0.34, + "learning_rate": 1.678004084673072e-05, + "loss": 1.3747, + "step": 3209 + }, + { + "epoch": 0.34, + "learning_rate": 1.6777349896010876e-05, + "loss": 1.4264, + "step": 3210 + }, + { + "epoch": 0.34, + "learning_rate": 1.677465803730028e-05, + "loss": 1.4178, + "step": 3211 + }, + { + "epoch": 0.34, + "learning_rate": 1.6771965270959584e-05, + "loss": 1.3876, + "step": 3212 + }, + { + "epoch": 0.34, + "learning_rate": 1.6769271597349538e-05, + "loss": 1.4658, + "step": 3213 + }, + { + "epoch": 0.34, + "learning_rate": 1.6766577016831026e-05, + "loss": 1.3968, + "step": 3214 + }, + { + "epoch": 0.34, + "learning_rate": 1.676388152976506e-05, + "loss": 1.5015, + "step": 3215 + }, + { + "epoch": 0.34, + "learning_rate": 1.6761185136512756e-05, + "loss": 1.4121, + "step": 3216 + }, + { + "epoch": 0.34, + "learning_rate": 1.675848783743537e-05, + "loss": 1.4146, + "step": 3217 + }, + { + "epoch": 0.34, + "learning_rate": 1.675578963289427e-05, + "loss": 1.4113, + "step": 3218 + }, + { + "epoch": 0.34, + "learning_rate": 1.6753090523250937e-05, + "loss": 1.4048, + "step": 3219 + }, + { + "epoch": 0.34, + "learning_rate": 1.6750390508866994e-05, + "loss": 1.4959, + "step": 3220 + }, + { + "epoch": 0.34, + "learning_rate": 1.6747689590104167e-05, + "loss": 1.4445, + "step": 3221 + }, + { + "epoch": 0.34, + "learning_rate": 1.6744987767324312e-05, + "loss": 1.4611, + "step": 3222 + }, + { + "epoch": 0.34, + "learning_rate": 1.67422850408894e-05, + "loss": 1.4141, + "step": 3223 + }, + { + "epoch": 0.34, + "learning_rate": 1.6739581411161535e-05, + "loss": 1.4218, + "step": 3224 + }, + { + "epoch": 0.34, + "learning_rate": 1.6736876878502925e-05, + "loss": 1.4266, + "step": 3225 + }, + { + "epoch": 0.34, + "learning_rate": 1.6734171443275913e-05, + "loss": 1.4941, + "step": 3226 + }, + { + "epoch": 0.34, + "learning_rate": 1.6731465105842955e-05, + "loss": 1.4294, + "step": 3227 + }, + { + "epoch": 0.34, + "learning_rate": 1.6728757866566635e-05, + "loss": 1.4189, + "step": 3228 + }, + { + "epoch": 0.34, + "learning_rate": 1.6726049725809647e-05, + "loss": 1.4713, + "step": 3229 + }, + { + "epoch": 0.34, + "learning_rate": 1.6723340683934818e-05, + "loss": 1.4203, + "step": 3230 + }, + { + "epoch": 0.34, + "learning_rate": 1.6720630741305088e-05, + "loss": 1.4112, + "step": 3231 + }, + { + "epoch": 0.34, + "learning_rate": 1.6717919898283523e-05, + "loss": 1.3811, + "step": 3232 + }, + { + "epoch": 0.34, + "learning_rate": 1.6715208155233296e-05, + "loss": 1.4242, + "step": 3233 + }, + { + "epoch": 0.34, + "learning_rate": 1.6712495512517725e-05, + "loss": 1.4207, + "step": 3234 + }, + { + "epoch": 0.34, + "learning_rate": 1.6709781970500222e-05, + "loss": 1.4888, + "step": 3235 + }, + { + "epoch": 0.34, + "learning_rate": 1.670706752954434e-05, + "loss": 1.4501, + "step": 3236 + }, + { + "epoch": 0.34, + "learning_rate": 1.670435219001374e-05, + "loss": 1.4367, + "step": 3237 + }, + { + "epoch": 0.34, + "learning_rate": 1.6701635952272212e-05, + "loss": 1.3959, + "step": 3238 + }, + { + "epoch": 0.34, + "learning_rate": 1.6698918816683655e-05, + "loss": 1.4257, + "step": 3239 + }, + { + "epoch": 0.34, + "learning_rate": 1.6696200783612102e-05, + "loss": 1.4718, + "step": 3240 + }, + { + "epoch": 0.34, + "learning_rate": 1.6693481853421697e-05, + "loss": 1.5899, + "step": 3241 + }, + { + "epoch": 0.34, + "learning_rate": 1.6690762026476707e-05, + "loss": 1.418, + "step": 3242 + }, + { + "epoch": 0.34, + "learning_rate": 1.668804130314152e-05, + "loss": 1.4076, + "step": 3243 + }, + { + "epoch": 0.34, + "learning_rate": 1.6685319683780645e-05, + "loss": 1.4571, + "step": 3244 + }, + { + "epoch": 0.34, + "learning_rate": 1.66825971687587e-05, + "loss": 1.4066, + "step": 3245 + }, + { + "epoch": 0.34, + "learning_rate": 1.6679873758440442e-05, + "loss": 1.4639, + "step": 3246 + }, + { + "epoch": 0.34, + "learning_rate": 1.6677149453190732e-05, + "loss": 1.453, + "step": 3247 + }, + { + "epoch": 0.34, + "learning_rate": 1.6674424253374558e-05, + "loss": 1.4262, + "step": 3248 + }, + { + "epoch": 0.34, + "learning_rate": 1.667169815935703e-05, + "loss": 1.3687, + "step": 3249 + }, + { + "epoch": 0.34, + "learning_rate": 1.6668971171503372e-05, + "loss": 1.5557, + "step": 3250 + }, + { + "epoch": 0.34, + "learning_rate": 1.6666243290178933e-05, + "loss": 1.4639, + "step": 3251 + }, + { + "epoch": 0.34, + "learning_rate": 1.6663514515749172e-05, + "loss": 1.4334, + "step": 3252 + }, + { + "epoch": 0.34, + "learning_rate": 1.6660784848579685e-05, + "loss": 1.3523, + "step": 3253 + }, + { + "epoch": 0.34, + "learning_rate": 1.6658054289036166e-05, + "loss": 1.3738, + "step": 3254 + }, + { + "epoch": 0.34, + "learning_rate": 1.665532283748445e-05, + "loss": 1.4159, + "step": 3255 + }, + { + "epoch": 0.34, + "learning_rate": 1.6652590494290474e-05, + "loss": 1.3609, + "step": 3256 + }, + { + "epoch": 0.34, + "learning_rate": 1.6649857259820303e-05, + "loss": 1.4449, + "step": 3257 + }, + { + "epoch": 0.34, + "learning_rate": 1.6647123134440126e-05, + "loss": 1.424, + "step": 3258 + }, + { + "epoch": 0.34, + "learning_rate": 1.664438811851624e-05, + "loss": 1.4737, + "step": 3259 + }, + { + "epoch": 0.34, + "learning_rate": 1.6641652212415066e-05, + "loss": 1.2717, + "step": 3260 + }, + { + "epoch": 0.34, + "learning_rate": 1.663891541650315e-05, + "loss": 1.4845, + "step": 3261 + }, + { + "epoch": 0.34, + "learning_rate": 1.663617773114715e-05, + "loss": 1.4115, + "step": 3262 + }, + { + "epoch": 0.34, + "learning_rate": 1.663343915671384e-05, + "loss": 1.4237, + "step": 3263 + }, + { + "epoch": 0.34, + "learning_rate": 1.6630699693570127e-05, + "loss": 1.4209, + "step": 3264 + }, + { + "epoch": 0.34, + "learning_rate": 1.6627959342083026e-05, + "loss": 1.506, + "step": 3265 + }, + { + "epoch": 0.34, + "learning_rate": 1.6625218102619672e-05, + "loss": 1.4466, + "step": 3266 + }, + { + "epoch": 0.34, + "learning_rate": 1.6622475975547324e-05, + "loss": 1.4129, + "step": 3267 + }, + { + "epoch": 0.34, + "learning_rate": 1.661973296123335e-05, + "loss": 1.4152, + "step": 3268 + }, + { + "epoch": 0.34, + "learning_rate": 1.661698906004525e-05, + "loss": 1.43, + "step": 3269 + }, + { + "epoch": 0.34, + "learning_rate": 1.661424427235064e-05, + "loss": 1.4701, + "step": 3270 + }, + { + "epoch": 0.34, + "learning_rate": 1.6611498598517238e-05, + "loss": 1.4598, + "step": 3271 + }, + { + "epoch": 0.34, + "learning_rate": 1.66087520389129e-05, + "loss": 1.4795, + "step": 3272 + }, + { + "epoch": 0.34, + "learning_rate": 1.6606004593905595e-05, + "loss": 1.5264, + "step": 3273 + }, + { + "epoch": 0.34, + "learning_rate": 1.6603256263863415e-05, + "loss": 1.4412, + "step": 3274 + }, + { + "epoch": 0.34, + "learning_rate": 1.6600507049154556e-05, + "loss": 1.45, + "step": 3275 + }, + { + "epoch": 0.34, + "learning_rate": 1.659775695014735e-05, + "loss": 1.4985, + "step": 3276 + }, + { + "epoch": 0.34, + "learning_rate": 1.659500596721024e-05, + "loss": 1.496, + "step": 3277 + }, + { + "epoch": 0.34, + "learning_rate": 1.6592254100711775e-05, + "loss": 1.4386, + "step": 3278 + }, + { + "epoch": 0.34, + "learning_rate": 1.658950135102065e-05, + "loss": 1.4073, + "step": 3279 + }, + { + "epoch": 0.34, + "learning_rate": 1.658674771850565e-05, + "loss": 1.3912, + "step": 3280 + }, + { + "epoch": 0.34, + "learning_rate": 1.6583993203535702e-05, + "loss": 1.3628, + "step": 3281 + }, + { + "epoch": 0.34, + "learning_rate": 1.658123780647983e-05, + "loss": 1.6089, + "step": 3282 + }, + { + "epoch": 0.34, + "learning_rate": 1.6578481527707196e-05, + "loss": 1.2367, + "step": 3283 + }, + { + "epoch": 0.34, + "learning_rate": 1.657572436758706e-05, + "loss": 1.4058, + "step": 3284 + }, + { + "epoch": 0.34, + "learning_rate": 1.6572966326488825e-05, + "loss": 1.4067, + "step": 3285 + }, + { + "epoch": 0.34, + "learning_rate": 1.657020740478198e-05, + "loss": 1.4187, + "step": 3286 + }, + { + "epoch": 0.34, + "learning_rate": 1.6567447602836166e-05, + "loss": 1.4599, + "step": 3287 + }, + { + "epoch": 0.34, + "learning_rate": 1.6564686921021115e-05, + "loss": 1.432, + "step": 3288 + }, + { + "epoch": 0.34, + "learning_rate": 1.6561925359706693e-05, + "loss": 1.3941, + "step": 3289 + }, + { + "epoch": 0.35, + "learning_rate": 1.6559162919262874e-05, + "loss": 1.3644, + "step": 3290 + }, + { + "epoch": 0.35, + "learning_rate": 1.6556399600059756e-05, + "loss": 1.4628, + "step": 3291 + }, + { + "epoch": 0.35, + "learning_rate": 1.6553635402467555e-05, + "loss": 1.4355, + "step": 3292 + }, + { + "epoch": 0.35, + "learning_rate": 1.6550870326856596e-05, + "loss": 1.4627, + "step": 3293 + }, + { + "epoch": 0.35, + "learning_rate": 1.6548104373597335e-05, + "loss": 1.442, + "step": 3294 + }, + { + "epoch": 0.35, + "learning_rate": 1.6545337543060338e-05, + "loss": 1.3991, + "step": 3295 + }, + { + "epoch": 0.35, + "learning_rate": 1.6542569835616283e-05, + "loss": 1.4193, + "step": 3296 + }, + { + "epoch": 0.35, + "learning_rate": 1.6539801251635982e-05, + "loss": 1.4792, + "step": 3297 + }, + { + "epoch": 0.35, + "learning_rate": 1.653703179149034e-05, + "loss": 1.4735, + "step": 3298 + }, + { + "epoch": 0.35, + "learning_rate": 1.6534261455550408e-05, + "loss": 1.451, + "step": 3299 + }, + { + "epoch": 0.35, + "learning_rate": 1.653149024418733e-05, + "loss": 1.3975, + "step": 3300 + }, + { + "epoch": 0.35, + "learning_rate": 1.652871815777238e-05, + "loss": 1.4843, + "step": 3301 + }, + { + "epoch": 0.35, + "learning_rate": 1.6525945196676948e-05, + "loss": 1.4782, + "step": 3302 + }, + { + "epoch": 0.35, + "learning_rate": 1.652317136127254e-05, + "loss": 1.3865, + "step": 3303 + }, + { + "epoch": 0.35, + "learning_rate": 1.6520396651930777e-05, + "loss": 1.4359, + "step": 3304 + }, + { + "epoch": 0.35, + "learning_rate": 1.6517621069023397e-05, + "loss": 1.4289, + "step": 3305 + }, + { + "epoch": 0.35, + "learning_rate": 1.651484461292226e-05, + "loss": 1.3526, + "step": 3306 + }, + { + "epoch": 0.35, + "learning_rate": 1.6512067283999336e-05, + "loss": 1.3671, + "step": 3307 + }, + { + "epoch": 0.35, + "learning_rate": 1.650928908262672e-05, + "loss": 1.6041, + "step": 3308 + }, + { + "epoch": 0.35, + "learning_rate": 1.650651000917662e-05, + "loss": 1.4322, + "step": 3309 + }, + { + "epoch": 0.35, + "learning_rate": 1.6503730064021354e-05, + "loss": 1.3992, + "step": 3310 + }, + { + "epoch": 0.35, + "learning_rate": 1.650094924753337e-05, + "loss": 1.4928, + "step": 3311 + }, + { + "epoch": 0.35, + "learning_rate": 1.6498167560085222e-05, + "loss": 1.4075, + "step": 3312 + }, + { + "epoch": 0.35, + "learning_rate": 1.6495385002049583e-05, + "loss": 1.4535, + "step": 3313 + }, + { + "epoch": 0.35, + "learning_rate": 1.6492601573799253e-05, + "loss": 1.4221, + "step": 3314 + }, + { + "epoch": 0.35, + "learning_rate": 1.6489817275707133e-05, + "loss": 1.3688, + "step": 3315 + }, + { + "epoch": 0.35, + "learning_rate": 1.6487032108146243e-05, + "loss": 1.3889, + "step": 3316 + }, + { + "epoch": 0.35, + "learning_rate": 1.6484246071489733e-05, + "loss": 1.3942, + "step": 3317 + }, + { + "epoch": 0.35, + "learning_rate": 1.6481459166110858e-05, + "loss": 1.4004, + "step": 3318 + }, + { + "epoch": 0.35, + "learning_rate": 1.647867139238299e-05, + "loss": 1.7308, + "step": 3319 + }, + { + "epoch": 0.35, + "learning_rate": 1.6475882750679622e-05, + "loss": 1.5001, + "step": 3320 + }, + { + "epoch": 0.35, + "learning_rate": 1.647309324137435e-05, + "loss": 1.4325, + "step": 3321 + }, + { + "epoch": 0.35, + "learning_rate": 1.6470302864840913e-05, + "loss": 1.4494, + "step": 3322 + }, + { + "epoch": 0.35, + "learning_rate": 1.6467511621453136e-05, + "loss": 1.4418, + "step": 3323 + }, + { + "epoch": 0.35, + "learning_rate": 1.646471951158498e-05, + "loss": 1.4046, + "step": 3324 + }, + { + "epoch": 0.35, + "learning_rate": 1.6461926535610517e-05, + "loss": 1.5031, + "step": 3325 + }, + { + "epoch": 0.35, + "learning_rate": 1.645913269390393e-05, + "loss": 1.4813, + "step": 3326 + }, + { + "epoch": 0.35, + "learning_rate": 1.6456337986839525e-05, + "loss": 1.3842, + "step": 3327 + }, + { + "epoch": 0.35, + "learning_rate": 1.645354241479172e-05, + "loss": 1.4539, + "step": 3328 + }, + { + "epoch": 0.35, + "learning_rate": 1.6450745978135048e-05, + "loss": 1.4503, + "step": 3329 + }, + { + "epoch": 0.35, + "learning_rate": 1.6447948677244163e-05, + "loss": 1.3741, + "step": 3330 + }, + { + "epoch": 0.35, + "learning_rate": 1.6445150512493832e-05, + "loss": 1.425, + "step": 3331 + }, + { + "epoch": 0.35, + "learning_rate": 1.644235148425893e-05, + "loss": 1.4277, + "step": 3332 + }, + { + "epoch": 0.35, + "learning_rate": 1.6439551592914464e-05, + "loss": 1.4918, + "step": 3333 + }, + { + "epoch": 0.35, + "learning_rate": 1.6436750838835543e-05, + "loss": 1.3364, + "step": 3334 + }, + { + "epoch": 0.35, + "learning_rate": 1.6433949222397397e-05, + "loss": 1.4741, + "step": 3335 + }, + { + "epoch": 0.35, + "learning_rate": 1.643114674397537e-05, + "loss": 1.3867, + "step": 3336 + }, + { + "epoch": 0.35, + "learning_rate": 1.642834340394492e-05, + "loss": 1.3817, + "step": 3337 + }, + { + "epoch": 0.35, + "learning_rate": 1.6425539202681625e-05, + "loss": 1.4308, + "step": 3338 + }, + { + "epoch": 0.35, + "learning_rate": 1.6422734140561178e-05, + "loss": 1.4401, + "step": 3339 + }, + { + "epoch": 0.35, + "learning_rate": 1.641992821795938e-05, + "loss": 1.4338, + "step": 3340 + }, + { + "epoch": 0.35, + "learning_rate": 1.641712143525216e-05, + "loss": 1.3804, + "step": 3341 + }, + { + "epoch": 0.35, + "learning_rate": 1.6414313792815546e-05, + "loss": 1.371, + "step": 3342 + }, + { + "epoch": 0.35, + "learning_rate": 1.6411505291025695e-05, + "loss": 1.4102, + "step": 3343 + }, + { + "epoch": 0.35, + "learning_rate": 1.6408695930258875e-05, + "loss": 1.4433, + "step": 3344 + }, + { + "epoch": 0.35, + "learning_rate": 1.6405885710891467e-05, + "loss": 1.3895, + "step": 3345 + }, + { + "epoch": 0.35, + "learning_rate": 1.6403074633299966e-05, + "loss": 1.4321, + "step": 3346 + }, + { + "epoch": 0.35, + "learning_rate": 1.640026269786098e-05, + "loss": 1.4207, + "step": 3347 + }, + { + "epoch": 0.35, + "learning_rate": 1.639744990495125e-05, + "loss": 1.3758, + "step": 3348 + }, + { + "epoch": 0.35, + "learning_rate": 1.6394636254947612e-05, + "loss": 1.4203, + "step": 3349 + }, + { + "epoch": 0.35, + "learning_rate": 1.6391821748227013e-05, + "loss": 1.4596, + "step": 3350 + }, + { + "epoch": 0.35, + "learning_rate": 1.6389006385166537e-05, + "loss": 1.4344, + "step": 3351 + }, + { + "epoch": 0.35, + "learning_rate": 1.6386190166143366e-05, + "loss": 1.4048, + "step": 3352 + }, + { + "epoch": 0.35, + "learning_rate": 1.6383373091534798e-05, + "loss": 1.4348, + "step": 3353 + }, + { + "epoch": 0.35, + "learning_rate": 1.638055516171825e-05, + "loss": 1.4972, + "step": 3354 + }, + { + "epoch": 0.35, + "learning_rate": 1.6377736377071258e-05, + "loss": 1.4685, + "step": 3355 + }, + { + "epoch": 0.35, + "learning_rate": 1.637491673797146e-05, + "loss": 1.4093, + "step": 3356 + }, + { + "epoch": 0.35, + "learning_rate": 1.6372096244796616e-05, + "loss": 1.4452, + "step": 3357 + }, + { + "epoch": 0.35, + "learning_rate": 1.63692748979246e-05, + "loss": 1.4458, + "step": 3358 + }, + { + "epoch": 0.35, + "learning_rate": 1.6366452697733404e-05, + "loss": 1.4187, + "step": 3359 + }, + { + "epoch": 0.35, + "learning_rate": 1.6363629644601126e-05, + "loss": 1.4052, + "step": 3360 + }, + { + "epoch": 0.35, + "learning_rate": 1.6360805738905984e-05, + "loss": 1.439, + "step": 3361 + }, + { + "epoch": 0.35, + "learning_rate": 1.635798098102631e-05, + "loss": 1.4131, + "step": 3362 + }, + { + "epoch": 0.35, + "learning_rate": 1.6355155371340544e-05, + "loss": 1.4391, + "step": 3363 + }, + { + "epoch": 0.35, + "learning_rate": 1.6352328910227252e-05, + "loss": 1.4318, + "step": 3364 + }, + { + "epoch": 0.35, + "learning_rate": 1.63495015980651e-05, + "loss": 1.5112, + "step": 3365 + }, + { + "epoch": 0.35, + "learning_rate": 1.6346673435232884e-05, + "loss": 1.4688, + "step": 3366 + }, + { + "epoch": 0.35, + "learning_rate": 1.6343844422109496e-05, + "loss": 1.3807, + "step": 3367 + }, + { + "epoch": 0.35, + "learning_rate": 1.634101455907396e-05, + "loss": 1.4083, + "step": 3368 + }, + { + "epoch": 0.35, + "learning_rate": 1.6338183846505394e-05, + "loss": 1.3566, + "step": 3369 + }, + { + "epoch": 0.35, + "learning_rate": 1.633535228478305e-05, + "loss": 1.4287, + "step": 3370 + }, + { + "epoch": 0.35, + "learning_rate": 1.6332519874286285e-05, + "loss": 1.3494, + "step": 3371 + }, + { + "epoch": 0.35, + "learning_rate": 1.6329686615394558e-05, + "loss": 1.3813, + "step": 3372 + }, + { + "epoch": 0.35, + "learning_rate": 1.6326852508487468e-05, + "loss": 1.4241, + "step": 3373 + }, + { + "epoch": 0.35, + "learning_rate": 1.63240175539447e-05, + "loss": 1.424, + "step": 3374 + }, + { + "epoch": 0.35, + "learning_rate": 1.632118175214607e-05, + "loss": 1.4212, + "step": 3375 + }, + { + "epoch": 0.35, + "learning_rate": 1.6318345103471504e-05, + "loss": 1.4671, + "step": 3376 + }, + { + "epoch": 0.35, + "learning_rate": 1.6315507608301044e-05, + "loss": 1.4593, + "step": 3377 + }, + { + "epoch": 0.35, + "learning_rate": 1.631266926701483e-05, + "loss": 1.7816, + "step": 3378 + }, + { + "epoch": 0.35, + "learning_rate": 1.6309830079993134e-05, + "loss": 1.5134, + "step": 3379 + }, + { + "epoch": 0.35, + "learning_rate": 1.6306990047616334e-05, + "loss": 0.8933, + "step": 3380 + }, + { + "epoch": 0.35, + "learning_rate": 1.630414917026492e-05, + "loss": 1.1033, + "step": 3381 + }, + { + "epoch": 0.35, + "learning_rate": 1.6301307448319497e-05, + "loss": 1.3494, + "step": 3382 + }, + { + "epoch": 0.35, + "learning_rate": 1.6298464882160784e-05, + "loss": 1.4299, + "step": 3383 + }, + { + "epoch": 0.35, + "eval_loss": 1.482450008392334, + "eval_runtime": 77.3737, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3383 + }, + { + "epoch": 0.35, + "learning_rate": 1.629562147216961e-05, + "loss": 1.3971, + "step": 3384 + }, + { + "epoch": 0.35, + "learning_rate": 1.6292777218726917e-05, + "loss": 1.3706, + "step": 3385 + }, + { + "epoch": 0.36, + "learning_rate": 1.6289932122213765e-05, + "loss": 1.4524, + "step": 3386 + }, + { + "epoch": 0.36, + "learning_rate": 1.6287086183011328e-05, + "loss": 1.4595, + "step": 3387 + }, + { + "epoch": 0.36, + "learning_rate": 1.628423940150088e-05, + "loss": 1.492, + "step": 3388 + }, + { + "epoch": 0.36, + "learning_rate": 1.628139177806382e-05, + "loss": 1.5576, + "step": 3389 + }, + { + "epoch": 0.36, + "learning_rate": 1.6278543313081657e-05, + "loss": 1.4615, + "step": 3390 + }, + { + "epoch": 0.36, + "learning_rate": 1.6275694006936015e-05, + "loss": 1.3456, + "step": 3391 + }, + { + "epoch": 0.36, + "learning_rate": 1.627284386000862e-05, + "loss": 1.4254, + "step": 3392 + }, + { + "epoch": 0.36, + "learning_rate": 1.6269992872681325e-05, + "loss": 1.433, + "step": 3393 + }, + { + "epoch": 0.36, + "learning_rate": 1.626714104533609e-05, + "loss": 1.5291, + "step": 3394 + }, + { + "epoch": 0.36, + "learning_rate": 1.626428837835498e-05, + "loss": 1.4502, + "step": 3395 + }, + { + "epoch": 0.36, + "learning_rate": 1.626143487212019e-05, + "loss": 1.3756, + "step": 3396 + }, + { + "epoch": 0.36, + "learning_rate": 1.6258580527014002e-05, + "loss": 1.414, + "step": 3397 + }, + { + "epoch": 0.36, + "learning_rate": 1.6255725343418835e-05, + "loss": 1.6289, + "step": 3398 + }, + { + "epoch": 0.36, + "learning_rate": 1.6252869321717208e-05, + "loss": 1.4862, + "step": 3399 + }, + { + "epoch": 0.36, + "learning_rate": 1.6250012462291756e-05, + "loss": 1.4213, + "step": 3400 + }, + { + "epoch": 0.36, + "learning_rate": 1.6247154765525217e-05, + "loss": 1.524, + "step": 3401 + }, + { + "epoch": 0.36, + "learning_rate": 1.624429623180046e-05, + "loss": 1.6013, + "step": 3402 + }, + { + "epoch": 0.36, + "learning_rate": 1.624143686150045e-05, + "loss": 1.4557, + "step": 3403 + }, + { + "epoch": 0.36, + "learning_rate": 1.6238576655008266e-05, + "loss": 1.3831, + "step": 3404 + }, + { + "epoch": 0.36, + "learning_rate": 1.6235715612707105e-05, + "loss": 1.4008, + "step": 3405 + }, + { + "epoch": 0.36, + "learning_rate": 1.623285373498028e-05, + "loss": 1.4848, + "step": 3406 + }, + { + "epoch": 0.36, + "learning_rate": 1.6229991022211197e-05, + "loss": 1.4459, + "step": 3407 + }, + { + "epoch": 0.36, + "learning_rate": 1.6227127474783393e-05, + "loss": 1.4334, + "step": 3408 + }, + { + "epoch": 0.36, + "learning_rate": 1.6224263093080507e-05, + "loss": 1.4123, + "step": 3409 + }, + { + "epoch": 0.36, + "learning_rate": 1.6221397877486294e-05, + "loss": 1.3691, + "step": 3410 + }, + { + "epoch": 0.36, + "learning_rate": 1.6218531828384618e-05, + "loss": 1.4128, + "step": 3411 + }, + { + "epoch": 0.36, + "learning_rate": 1.6215664946159457e-05, + "loss": 1.3642, + "step": 3412 + }, + { + "epoch": 0.36, + "learning_rate": 1.6212797231194902e-05, + "loss": 1.4311, + "step": 3413 + }, + { + "epoch": 0.36, + "learning_rate": 1.6209928683875152e-05, + "loss": 1.4695, + "step": 3414 + }, + { + "epoch": 0.36, + "learning_rate": 1.6207059304584514e-05, + "loss": 1.3871, + "step": 3415 + }, + { + "epoch": 0.36, + "learning_rate": 1.6204189093707414e-05, + "loss": 1.4219, + "step": 3416 + }, + { + "epoch": 0.36, + "learning_rate": 1.620131805162839e-05, + "loss": 1.6199, + "step": 3417 + }, + { + "epoch": 0.36, + "learning_rate": 1.619844617873208e-05, + "loss": 1.4433, + "step": 3418 + }, + { + "epoch": 0.36, + "learning_rate": 1.619557347540325e-05, + "loss": 1.4773, + "step": 3419 + }, + { + "epoch": 0.36, + "learning_rate": 1.6192699942026763e-05, + "loss": 1.4551, + "step": 3420 + }, + { + "epoch": 0.36, + "learning_rate": 1.6189825578987603e-05, + "loss": 1.4903, + "step": 3421 + }, + { + "epoch": 0.36, + "learning_rate": 1.6186950386670855e-05, + "loss": 1.473, + "step": 3422 + }, + { + "epoch": 0.36, + "learning_rate": 1.6184074365461722e-05, + "loss": 1.4082, + "step": 3423 + }, + { + "epoch": 0.36, + "learning_rate": 1.6181197515745523e-05, + "loss": 1.4746, + "step": 3424 + }, + { + "epoch": 0.36, + "learning_rate": 1.6178319837907674e-05, + "loss": 1.449, + "step": 3425 + }, + { + "epoch": 0.36, + "learning_rate": 1.6175441332333715e-05, + "loss": 1.377, + "step": 3426 + }, + { + "epoch": 0.36, + "learning_rate": 1.617256199940929e-05, + "loss": 1.2364, + "step": 3427 + }, + { + "epoch": 0.36, + "learning_rate": 1.6169681839520155e-05, + "loss": 1.4437, + "step": 3428 + }, + { + "epoch": 0.36, + "learning_rate": 1.616680085305218e-05, + "loss": 1.4726, + "step": 3429 + }, + { + "epoch": 0.36, + "learning_rate": 1.616391904039134e-05, + "loss": 1.4824, + "step": 3430 + }, + { + "epoch": 0.36, + "learning_rate": 1.616103640192373e-05, + "loss": 1.4052, + "step": 3431 + }, + { + "epoch": 0.36, + "learning_rate": 1.6158152938035537e-05, + "loss": 1.4131, + "step": 3432 + }, + { + "epoch": 0.36, + "learning_rate": 1.6155268649113084e-05, + "loss": 1.4267, + "step": 3433 + }, + { + "epoch": 0.36, + "learning_rate": 1.6152383535542786e-05, + "loss": 1.3735, + "step": 3434 + }, + { + "epoch": 0.36, + "learning_rate": 1.6149497597711175e-05, + "loss": 1.4249, + "step": 3435 + }, + { + "epoch": 0.36, + "learning_rate": 1.614661083600489e-05, + "loss": 1.4312, + "step": 3436 + }, + { + "epoch": 0.36, + "learning_rate": 1.6143723250810686e-05, + "loss": 1.4831, + "step": 3437 + }, + { + "epoch": 0.36, + "learning_rate": 1.6140834842515425e-05, + "loss": 1.4183, + "step": 3438 + }, + { + "epoch": 0.36, + "learning_rate": 1.6137945611506078e-05, + "loss": 1.3908, + "step": 3439 + }, + { + "epoch": 0.36, + "learning_rate": 1.613505555816973e-05, + "loss": 1.425, + "step": 3440 + }, + { + "epoch": 0.36, + "learning_rate": 1.613216468289357e-05, + "loss": 1.3589, + "step": 3441 + }, + { + "epoch": 0.36, + "learning_rate": 1.6129272986064903e-05, + "loss": 1.4272, + "step": 3442 + }, + { + "epoch": 0.36, + "learning_rate": 1.6126380468071142e-05, + "loss": 1.4337, + "step": 3443 + }, + { + "epoch": 0.36, + "learning_rate": 1.6123487129299817e-05, + "loss": 1.3872, + "step": 3444 + }, + { + "epoch": 0.36, + "learning_rate": 1.612059297013855e-05, + "loss": 1.374, + "step": 3445 + }, + { + "epoch": 0.36, + "learning_rate": 1.611769799097509e-05, + "loss": 1.314, + "step": 3446 + }, + { + "epoch": 0.36, + "learning_rate": 1.6114802192197284e-05, + "loss": 1.3951, + "step": 3447 + }, + { + "epoch": 0.36, + "learning_rate": 1.6111905574193102e-05, + "loss": 1.4732, + "step": 3448 + }, + { + "epoch": 0.36, + "learning_rate": 1.6109008137350614e-05, + "loss": 1.3575, + "step": 3449 + }, + { + "epoch": 0.36, + "learning_rate": 1.6106109882058e-05, + "loss": 1.4606, + "step": 3450 + }, + { + "epoch": 0.36, + "learning_rate": 1.6103210808703554e-05, + "loss": 1.4357, + "step": 3451 + }, + { + "epoch": 0.36, + "learning_rate": 1.6100310917675678e-05, + "loss": 0.8456, + "step": 3452 + }, + { + "epoch": 0.36, + "learning_rate": 1.609741020936288e-05, + "loss": 1.07, + "step": 3453 + }, + { + "epoch": 0.36, + "learning_rate": 1.6094508684153782e-05, + "loss": 1.4435, + "step": 3454 + }, + { + "epoch": 0.36, + "learning_rate": 1.609160634243711e-05, + "loss": 1.3696, + "step": 3455 + }, + { + "epoch": 0.36, + "learning_rate": 1.6088703184601712e-05, + "loss": 1.4012, + "step": 3456 + }, + { + "epoch": 0.36, + "learning_rate": 1.608579921103653e-05, + "loss": 1.5212, + "step": 3457 + }, + { + "epoch": 0.36, + "learning_rate": 1.608289442213062e-05, + "loss": 1.4339, + "step": 3458 + }, + { + "epoch": 0.36, + "learning_rate": 1.607998881827316e-05, + "loss": 1.4901, + "step": 3459 + }, + { + "epoch": 0.36, + "learning_rate": 1.6077082399853412e-05, + "loss": 1.4822, + "step": 3460 + }, + { + "epoch": 0.36, + "learning_rate": 1.607417516726077e-05, + "loss": 1.3696, + "step": 3461 + }, + { + "epoch": 0.36, + "learning_rate": 1.6071267120884727e-05, + "loss": 1.4434, + "step": 3462 + }, + { + "epoch": 0.36, + "learning_rate": 1.6068358261114886e-05, + "loss": 1.3916, + "step": 3463 + }, + { + "epoch": 0.36, + "learning_rate": 1.606544858834096e-05, + "loss": 1.422, + "step": 3464 + }, + { + "epoch": 0.36, + "learning_rate": 1.6062538102952763e-05, + "loss": 1.367, + "step": 3465 + }, + { + "epoch": 0.36, + "learning_rate": 1.605962680534024e-05, + "loss": 1.3788, + "step": 3466 + }, + { + "epoch": 0.36, + "learning_rate": 1.605671469589342e-05, + "loss": 1.4366, + "step": 3467 + }, + { + "epoch": 0.36, + "learning_rate": 1.6053801775002453e-05, + "loss": 1.4027, + "step": 3468 + }, + { + "epoch": 0.36, + "learning_rate": 1.6050888043057595e-05, + "loss": 1.4386, + "step": 3469 + }, + { + "epoch": 0.36, + "learning_rate": 1.6047973500449212e-05, + "loss": 1.4675, + "step": 3470 + }, + { + "epoch": 0.36, + "learning_rate": 1.6045058147567778e-05, + "loss": 1.6936, + "step": 3471 + }, + { + "epoch": 0.36, + "learning_rate": 1.6042141984803875e-05, + "loss": 1.4858, + "step": 3472 + }, + { + "epoch": 0.36, + "learning_rate": 1.6039225012548196e-05, + "loss": 1.5004, + "step": 3473 + }, + { + "epoch": 0.36, + "learning_rate": 1.6036307231191534e-05, + "loss": 1.4969, + "step": 3474 + }, + { + "epoch": 0.36, + "learning_rate": 1.6033388641124803e-05, + "loss": 1.4027, + "step": 3475 + }, + { + "epoch": 0.36, + "learning_rate": 1.6030469242739016e-05, + "loss": 1.4741, + "step": 3476 + }, + { + "epoch": 0.36, + "learning_rate": 1.60275490364253e-05, + "loss": 1.3887, + "step": 3477 + }, + { + "epoch": 0.36, + "learning_rate": 1.602462802257488e-05, + "loss": 1.6735, + "step": 3478 + }, + { + "epoch": 0.36, + "learning_rate": 1.602170620157911e-05, + "loss": 1.4997, + "step": 3479 + }, + { + "epoch": 0.36, + "learning_rate": 1.601878357382943e-05, + "loss": 1.3973, + "step": 3480 + }, + { + "epoch": 0.37, + "learning_rate": 1.6015860139717398e-05, + "loss": 1.416, + "step": 3481 + }, + { + "epoch": 0.37, + "learning_rate": 1.6012935899634682e-05, + "loss": 1.4102, + "step": 3482 + }, + { + "epoch": 0.37, + "learning_rate": 1.601001085397305e-05, + "loss": 1.4248, + "step": 3483 + }, + { + "epoch": 0.37, + "learning_rate": 1.6007085003124386e-05, + "loss": 1.3909, + "step": 3484 + }, + { + "epoch": 0.37, + "learning_rate": 1.600415834748068e-05, + "loss": 1.4029, + "step": 3485 + }, + { + "epoch": 0.37, + "learning_rate": 1.6001230887434024e-05, + "loss": 1.4219, + "step": 3486 + }, + { + "epoch": 0.37, + "learning_rate": 1.5998302623376633e-05, + "loss": 1.4008, + "step": 3487 + }, + { + "epoch": 0.37, + "learning_rate": 1.5995373555700806e-05, + "loss": 1.5163, + "step": 3488 + }, + { + "epoch": 0.37, + "learning_rate": 1.599244368479897e-05, + "loss": 1.4541, + "step": 3489 + }, + { + "epoch": 0.37, + "learning_rate": 1.598951301106365e-05, + "loss": 1.4454, + "step": 3490 + }, + { + "epoch": 0.37, + "learning_rate": 1.598658153488748e-05, + "loss": 1.1014, + "step": 3491 + }, + { + "epoch": 0.37, + "learning_rate": 1.598364925666321e-05, + "loss": 1.407, + "step": 3492 + }, + { + "epoch": 0.37, + "learning_rate": 1.5980716176783682e-05, + "loss": 1.5046, + "step": 3493 + }, + { + "epoch": 0.37, + "learning_rate": 1.5977782295641857e-05, + "loss": 1.4265, + "step": 3494 + }, + { + "epoch": 0.37, + "learning_rate": 1.5974847613630796e-05, + "loss": 1.46, + "step": 3495 + }, + { + "epoch": 0.37, + "learning_rate": 1.5971912131143677e-05, + "loss": 1.3996, + "step": 3496 + }, + { + "epoch": 0.37, + "learning_rate": 1.5968975848573772e-05, + "loss": 1.4719, + "step": 3497 + }, + { + "epoch": 0.37, + "learning_rate": 1.596603876631447e-05, + "loss": 1.43, + "step": 3498 + }, + { + "epoch": 0.37, + "learning_rate": 1.596310088475927e-05, + "loss": 1.4109, + "step": 3499 + }, + { + "epoch": 0.37, + "learning_rate": 1.5960162204301768e-05, + "loss": 1.3612, + "step": 3500 + }, + { + "epoch": 0.37, + "learning_rate": 1.5957222725335672e-05, + "loss": 1.5045, + "step": 3501 + }, + { + "epoch": 0.37, + "learning_rate": 1.5954282448254794e-05, + "loss": 1.5323, + "step": 3502 + }, + { + "epoch": 0.37, + "learning_rate": 1.595134137345306e-05, + "loss": 1.4518, + "step": 3503 + }, + { + "epoch": 0.37, + "learning_rate": 1.5948399501324495e-05, + "loss": 1.6131, + "step": 3504 + }, + { + "epoch": 0.37, + "learning_rate": 1.594545683226324e-05, + "loss": 1.5076, + "step": 3505 + }, + { + "epoch": 0.37, + "learning_rate": 1.594251336666353e-05, + "loss": 1.482, + "step": 3506 + }, + { + "epoch": 0.37, + "learning_rate": 1.5939569104919716e-05, + "loss": 1.4429, + "step": 3507 + }, + { + "epoch": 0.37, + "learning_rate": 1.5936624047426254e-05, + "loss": 1.4662, + "step": 3508 + }, + { + "epoch": 0.37, + "learning_rate": 1.5933678194577708e-05, + "loss": 1.425, + "step": 3509 + }, + { + "epoch": 0.37, + "learning_rate": 1.5930731546768744e-05, + "loss": 1.4312, + "step": 3510 + }, + { + "epoch": 0.37, + "learning_rate": 1.592778410439414e-05, + "loss": 1.4336, + "step": 3511 + }, + { + "epoch": 0.37, + "learning_rate": 1.5924835867848775e-05, + "loss": 1.4197, + "step": 3512 + }, + { + "epoch": 0.37, + "learning_rate": 1.5921886837527638e-05, + "loss": 1.4456, + "step": 3513 + }, + { + "epoch": 0.37, + "learning_rate": 1.5918937013825823e-05, + "loss": 1.4394, + "step": 3514 + }, + { + "epoch": 0.37, + "learning_rate": 1.5915986397138526e-05, + "loss": 1.3606, + "step": 3515 + }, + { + "epoch": 0.37, + "learning_rate": 1.591303498786106e-05, + "loss": 1.4382, + "step": 3516 + }, + { + "epoch": 0.37, + "learning_rate": 1.591008278638884e-05, + "loss": 1.4185, + "step": 3517 + }, + { + "epoch": 0.37, + "learning_rate": 1.5907129793117374e-05, + "loss": 1.6692, + "step": 3518 + }, + { + "epoch": 0.37, + "learning_rate": 1.59041760084423e-05, + "loss": 1.501, + "step": 3519 + }, + { + "epoch": 0.37, + "learning_rate": 1.5901221432759345e-05, + "loss": 1.5753, + "step": 3520 + }, + { + "epoch": 0.37, + "learning_rate": 1.589826606646434e-05, + "loss": 1.4795, + "step": 3521 + }, + { + "epoch": 0.37, + "learning_rate": 1.5895309909953236e-05, + "loss": 1.4379, + "step": 3522 + }, + { + "epoch": 0.37, + "learning_rate": 1.5892352963622078e-05, + "loss": 1.3426, + "step": 3523 + }, + { + "epoch": 0.37, + "learning_rate": 1.5889395227867025e-05, + "loss": 1.4048, + "step": 3524 + }, + { + "epoch": 0.37, + "learning_rate": 1.5886436703084332e-05, + "loss": 1.4303, + "step": 3525 + }, + { + "epoch": 0.37, + "learning_rate": 1.5883477389670367e-05, + "loss": 1.3684, + "step": 3526 + }, + { + "epoch": 0.37, + "learning_rate": 1.5880517288021602e-05, + "loss": 1.3701, + "step": 3527 + }, + { + "epoch": 0.37, + "learning_rate": 1.587755639853462e-05, + "loss": 1.4308, + "step": 3528 + }, + { + "epoch": 0.37, + "learning_rate": 1.5874594721606096e-05, + "loss": 1.3981, + "step": 3529 + }, + { + "epoch": 0.37, + "learning_rate": 1.5871632257632823e-05, + "loss": 1.5906, + "step": 3530 + }, + { + "epoch": 0.37, + "learning_rate": 1.5868669007011696e-05, + "loss": 1.4642, + "step": 3531 + }, + { + "epoch": 0.37, + "learning_rate": 1.586570497013971e-05, + "loss": 1.411, + "step": 3532 + }, + { + "epoch": 0.37, + "learning_rate": 1.586274014741397e-05, + "loss": 1.3942, + "step": 3533 + }, + { + "epoch": 0.37, + "learning_rate": 1.5859774539231693e-05, + "loss": 1.3952, + "step": 3534 + }, + { + "epoch": 0.37, + "learning_rate": 1.585680814599019e-05, + "loss": 1.4009, + "step": 3535 + }, + { + "epoch": 0.37, + "learning_rate": 1.585384096808688e-05, + "loss": 1.3238, + "step": 3536 + }, + { + "epoch": 0.37, + "learning_rate": 1.585087300591929e-05, + "loss": 1.346, + "step": 3537 + }, + { + "epoch": 0.37, + "learning_rate": 1.584790425988505e-05, + "loss": 1.3739, + "step": 3538 + }, + { + "epoch": 0.37, + "learning_rate": 1.5844934730381895e-05, + "loss": 1.4264, + "step": 3539 + }, + { + "epoch": 0.37, + "learning_rate": 1.5841964417807668e-05, + "loss": 1.4675, + "step": 3540 + }, + { + "epoch": 0.37, + "learning_rate": 1.5838993322560314e-05, + "loss": 1.3337, + "step": 3541 + }, + { + "epoch": 0.37, + "learning_rate": 1.5836021445037883e-05, + "loss": 1.4052, + "step": 3542 + }, + { + "epoch": 0.37, + "learning_rate": 1.583304878563853e-05, + "loss": 1.4311, + "step": 3543 + }, + { + "epoch": 0.37, + "learning_rate": 1.5830075344760513e-05, + "loss": 1.386, + "step": 3544 + }, + { + "epoch": 0.37, + "learning_rate": 1.58271011228022e-05, + "loss": 1.387, + "step": 3545 + }, + { + "epoch": 0.37, + "learning_rate": 1.582412612016206e-05, + "loss": 1.3601, + "step": 3546 + }, + { + "epoch": 0.37, + "learning_rate": 1.5821150337238663e-05, + "loss": 1.5111, + "step": 3547 + }, + { + "epoch": 0.37, + "learning_rate": 1.5818173774430697e-05, + "loss": 1.471, + "step": 3548 + }, + { + "epoch": 0.37, + "learning_rate": 1.581519643213693e-05, + "loss": 1.4442, + "step": 3549 + }, + { + "epoch": 0.37, + "learning_rate": 1.5812218310756263e-05, + "loss": 1.467, + "step": 3550 + }, + { + "epoch": 0.37, + "learning_rate": 1.5809239410687683e-05, + "loss": 1.3731, + "step": 3551 + }, + { + "epoch": 0.37, + "learning_rate": 1.5806259732330286e-05, + "loss": 1.4072, + "step": 3552 + }, + { + "epoch": 0.37, + "learning_rate": 1.5803279276083268e-05, + "loss": 1.3636, + "step": 3553 + }, + { + "epoch": 0.37, + "learning_rate": 1.5800298042345938e-05, + "loss": 1.3915, + "step": 3554 + }, + { + "epoch": 0.37, + "learning_rate": 1.5797316031517705e-05, + "loss": 1.5038, + "step": 3555 + }, + { + "epoch": 0.37, + "learning_rate": 1.5794333243998082e-05, + "loss": 1.4455, + "step": 3556 + }, + { + "epoch": 0.37, + "learning_rate": 1.5791349680186684e-05, + "loss": 1.5062, + "step": 3557 + }, + { + "epoch": 0.37, + "learning_rate": 1.5788365340483234e-05, + "loss": 1.3899, + "step": 3558 + }, + { + "epoch": 0.37, + "learning_rate": 1.5785380225287554e-05, + "loss": 1.4946, + "step": 3559 + }, + { + "epoch": 0.37, + "learning_rate": 1.5782394334999572e-05, + "loss": 1.3859, + "step": 3560 + }, + { + "epoch": 0.37, + "learning_rate": 1.577940767001933e-05, + "loss": 1.541, + "step": 3561 + }, + { + "epoch": 0.37, + "learning_rate": 1.5776420230746952e-05, + "loss": 1.4952, + "step": 3562 + }, + { + "epoch": 0.37, + "learning_rate": 1.5773432017582684e-05, + "loss": 1.6055, + "step": 3563 + }, + { + "epoch": 0.37, + "learning_rate": 1.577044303092687e-05, + "loss": 1.4661, + "step": 3564 + }, + { + "epoch": 0.37, + "learning_rate": 1.576745327117996e-05, + "loss": 1.4082, + "step": 3565 + }, + { + "epoch": 0.37, + "learning_rate": 1.5764462738742493e-05, + "loss": 1.4005, + "step": 3566 + }, + { + "epoch": 0.37, + "learning_rate": 1.5761471434015137e-05, + "loss": 1.3959, + "step": 3567 + }, + { + "epoch": 0.37, + "learning_rate": 1.5758479357398645e-05, + "loss": 1.4567, + "step": 3568 + }, + { + "epoch": 0.37, + "learning_rate": 1.575548650929388e-05, + "loss": 1.3791, + "step": 3569 + }, + { + "epoch": 0.37, + "learning_rate": 1.57524928901018e-05, + "loss": 1.4428, + "step": 3570 + }, + { + "epoch": 0.37, + "learning_rate": 1.5749498500223486e-05, + "loss": 1.3864, + "step": 3571 + }, + { + "epoch": 0.37, + "learning_rate": 1.5746503340060097e-05, + "loss": 1.4019, + "step": 3572 + }, + { + "epoch": 0.37, + "learning_rate": 1.574350741001291e-05, + "loss": 1.5436, + "step": 3573 + }, + { + "epoch": 0.37, + "learning_rate": 1.5740510710483308e-05, + "loss": 1.4637, + "step": 3574 + }, + { + "epoch": 0.37, + "learning_rate": 1.5737513241872767e-05, + "loss": 1.5097, + "step": 3575 + }, + { + "epoch": 0.38, + "learning_rate": 1.5734515004582873e-05, + "loss": 1.5143, + "step": 3576 + }, + { + "epoch": 0.38, + "learning_rate": 1.5731515999015315e-05, + "loss": 1.3926, + "step": 3577 + }, + { + "epoch": 0.38, + "learning_rate": 1.5728516225571874e-05, + "loss": 1.4242, + "step": 3578 + }, + { + "epoch": 0.38, + "learning_rate": 1.5725515684654453e-05, + "loss": 1.4429, + "step": 3579 + }, + { + "epoch": 0.38, + "learning_rate": 1.572251437666504e-05, + "loss": 1.4638, + "step": 3580 + }, + { + "epoch": 0.38, + "learning_rate": 1.5719512302005735e-05, + "loss": 1.3381, + "step": 3581 + }, + { + "epoch": 0.38, + "learning_rate": 1.571650946107874e-05, + "loss": 1.4342, + "step": 3582 + }, + { + "epoch": 0.38, + "eval_loss": 1.4705015420913696, + "eval_runtime": 77.3664, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3582 + }, + { + "epoch": 0.38, + "learning_rate": 1.571350585428636e-05, + "loss": 1.3991, + "step": 3583 + }, + { + "epoch": 0.38, + "learning_rate": 1.5710501482030998e-05, + "loss": 1.4274, + "step": 3584 + }, + { + "epoch": 0.38, + "learning_rate": 1.5707496344715166e-05, + "loss": 1.438, + "step": 3585 + }, + { + "epoch": 0.38, + "learning_rate": 1.570449044274147e-05, + "loss": 1.4453, + "step": 3586 + }, + { + "epoch": 0.38, + "learning_rate": 1.570148377651263e-05, + "loss": 1.4022, + "step": 3587 + }, + { + "epoch": 0.38, + "learning_rate": 1.5698476346431454e-05, + "loss": 1.4312, + "step": 3588 + }, + { + "epoch": 0.38, + "learning_rate": 1.569546815290087e-05, + "loss": 1.4329, + "step": 3589 + }, + { + "epoch": 0.38, + "learning_rate": 1.569245919632389e-05, + "loss": 1.4036, + "step": 3590 + }, + { + "epoch": 0.38, + "learning_rate": 1.5689449477103644e-05, + "loss": 1.412, + "step": 3591 + }, + { + "epoch": 0.38, + "learning_rate": 1.5686438995643353e-05, + "loss": 1.4492, + "step": 3592 + }, + { + "epoch": 0.38, + "learning_rate": 1.5683427752346343e-05, + "loss": 1.4555, + "step": 3593 + }, + { + "epoch": 0.38, + "learning_rate": 1.5680415747616047e-05, + "loss": 1.5594, + "step": 3594 + }, + { + "epoch": 0.38, + "learning_rate": 1.5677402981855993e-05, + "loss": 1.4813, + "step": 3595 + }, + { + "epoch": 0.38, + "learning_rate": 1.567438945546982e-05, + "loss": 1.5919, + "step": 3596 + }, + { + "epoch": 0.38, + "learning_rate": 1.5671375168861255e-05, + "loss": 1.4235, + "step": 3597 + }, + { + "epoch": 0.38, + "learning_rate": 1.5668360122434135e-05, + "loss": 1.441, + "step": 3598 + }, + { + "epoch": 0.38, + "learning_rate": 1.566534431659241e-05, + "loss": 1.5847, + "step": 3599 + }, + { + "epoch": 0.38, + "learning_rate": 1.566232775174011e-05, + "loss": 1.6123, + "step": 3600 + }, + { + "epoch": 0.38, + "learning_rate": 1.5659310428281374e-05, + "loss": 1.4916, + "step": 3601 + }, + { + "epoch": 0.38, + "learning_rate": 1.5656292346620457e-05, + "loss": 1.4603, + "step": 3602 + }, + { + "epoch": 0.38, + "learning_rate": 1.56532735071617e-05, + "loss": 1.4423, + "step": 3603 + }, + { + "epoch": 0.38, + "learning_rate": 1.5650253910309547e-05, + "loss": 1.4814, + "step": 3604 + }, + { + "epoch": 0.38, + "learning_rate": 1.5647233556468552e-05, + "loss": 1.4015, + "step": 3605 + }, + { + "epoch": 0.38, + "learning_rate": 1.564421244604336e-05, + "loss": 1.3798, + "step": 3606 + }, + { + "epoch": 0.38, + "learning_rate": 1.5641190579438723e-05, + "loss": 1.4259, + "step": 3607 + }, + { + "epoch": 0.38, + "learning_rate": 1.5638167957059493e-05, + "loss": 1.3493, + "step": 3608 + }, + { + "epoch": 0.38, + "learning_rate": 1.5635144579310626e-05, + "loss": 1.3433, + "step": 3609 + }, + { + "epoch": 0.38, + "learning_rate": 1.5632120446597177e-05, + "loss": 1.4661, + "step": 3610 + }, + { + "epoch": 0.38, + "learning_rate": 1.5629095559324297e-05, + "loss": 1.4205, + "step": 3611 + }, + { + "epoch": 0.38, + "learning_rate": 1.562606991789725e-05, + "loss": 1.3976, + "step": 3612 + }, + { + "epoch": 0.38, + "learning_rate": 1.5623043522721393e-05, + "loss": 1.4261, + "step": 3613 + }, + { + "epoch": 0.38, + "learning_rate": 1.562001637420218e-05, + "loss": 1.4358, + "step": 3614 + }, + { + "epoch": 0.38, + "learning_rate": 1.5616988472745175e-05, + "loss": 1.437, + "step": 3615 + }, + { + "epoch": 0.38, + "learning_rate": 1.561395981875604e-05, + "loss": 1.3735, + "step": 3616 + }, + { + "epoch": 0.38, + "learning_rate": 1.5610930412640532e-05, + "loss": 1.4357, + "step": 3617 + }, + { + "epoch": 0.38, + "learning_rate": 1.560790025480452e-05, + "loss": 1.4003, + "step": 3618 + }, + { + "epoch": 0.38, + "learning_rate": 1.5604869345653965e-05, + "loss": 1.4127, + "step": 3619 + }, + { + "epoch": 0.38, + "learning_rate": 1.5601837685594927e-05, + "loss": 1.4666, + "step": 3620 + }, + { + "epoch": 0.38, + "learning_rate": 1.5598805275033574e-05, + "loss": 1.4106, + "step": 3621 + }, + { + "epoch": 0.38, + "learning_rate": 1.5595772114376174e-05, + "loss": 1.3857, + "step": 3622 + }, + { + "epoch": 0.38, + "learning_rate": 1.5592738204029086e-05, + "loss": 1.4704, + "step": 3623 + }, + { + "epoch": 0.38, + "learning_rate": 1.558970354439878e-05, + "loss": 1.4649, + "step": 3624 + }, + { + "epoch": 0.38, + "learning_rate": 1.5586668135891824e-05, + "loss": 1.4812, + "step": 3625 + }, + { + "epoch": 0.38, + "learning_rate": 1.5583631978914882e-05, + "loss": 1.3507, + "step": 3626 + }, + { + "epoch": 0.38, + "learning_rate": 1.5580595073874718e-05, + "loss": 1.3762, + "step": 3627 + }, + { + "epoch": 0.38, + "learning_rate": 1.557755742117821e-05, + "loss": 1.4169, + "step": 3628 + }, + { + "epoch": 0.38, + "learning_rate": 1.557451902123231e-05, + "loss": 1.4098, + "step": 3629 + }, + { + "epoch": 0.38, + "learning_rate": 1.55714798744441e-05, + "loss": 1.5526, + "step": 3630 + }, + { + "epoch": 0.38, + "learning_rate": 1.556843998122074e-05, + "loss": 1.4414, + "step": 3631 + }, + { + "epoch": 0.38, + "learning_rate": 1.5565399341969497e-05, + "loss": 1.4134, + "step": 3632 + }, + { + "epoch": 0.38, + "learning_rate": 1.556235795709774e-05, + "loss": 1.4718, + "step": 3633 + }, + { + "epoch": 0.38, + "learning_rate": 1.5559315827012937e-05, + "loss": 1.412, + "step": 3634 + }, + { + "epoch": 0.38, + "learning_rate": 1.5556272952122657e-05, + "loss": 1.4119, + "step": 3635 + }, + { + "epoch": 0.38, + "learning_rate": 1.5553229332834564e-05, + "loss": 1.3999, + "step": 3636 + }, + { + "epoch": 0.38, + "learning_rate": 1.5550184969556428e-05, + "loss": 1.4626, + "step": 3637 + }, + { + "epoch": 0.38, + "learning_rate": 1.5547139862696113e-05, + "loss": 1.3811, + "step": 3638 + }, + { + "epoch": 0.38, + "learning_rate": 1.5544094012661583e-05, + "loss": 1.4053, + "step": 3639 + }, + { + "epoch": 0.38, + "learning_rate": 1.5541047419860907e-05, + "loss": 1.4059, + "step": 3640 + }, + { + "epoch": 0.38, + "learning_rate": 1.553800008470225e-05, + "loss": 1.4717, + "step": 3641 + }, + { + "epoch": 0.38, + "learning_rate": 1.553495200759388e-05, + "loss": 1.399, + "step": 3642 + }, + { + "epoch": 0.38, + "learning_rate": 1.5531903188944154e-05, + "loss": 1.4143, + "step": 3643 + }, + { + "epoch": 0.38, + "learning_rate": 1.5528853629161536e-05, + "loss": 1.4414, + "step": 3644 + }, + { + "epoch": 0.38, + "learning_rate": 1.5525803328654592e-05, + "loss": 1.4206, + "step": 3645 + }, + { + "epoch": 0.38, + "learning_rate": 1.5522752287831982e-05, + "loss": 1.3869, + "step": 3646 + }, + { + "epoch": 0.38, + "learning_rate": 1.551970050710247e-05, + "loss": 1.5434, + "step": 3647 + }, + { + "epoch": 0.38, + "learning_rate": 1.5516647986874914e-05, + "loss": 1.4574, + "step": 3648 + }, + { + "epoch": 0.38, + "learning_rate": 1.5513594727558273e-05, + "loss": 1.4353, + "step": 3649 + }, + { + "epoch": 0.38, + "learning_rate": 1.5510540729561606e-05, + "loss": 1.4122, + "step": 3650 + }, + { + "epoch": 0.38, + "learning_rate": 1.550748599329407e-05, + "loss": 1.4077, + "step": 3651 + }, + { + "epoch": 0.38, + "learning_rate": 1.550443051916492e-05, + "loss": 1.4433, + "step": 3652 + }, + { + "epoch": 0.38, + "learning_rate": 1.5501374307583514e-05, + "loss": 1.54, + "step": 3653 + }, + { + "epoch": 0.38, + "learning_rate": 1.5498317358959302e-05, + "loss": 1.4522, + "step": 3654 + }, + { + "epoch": 0.38, + "learning_rate": 1.5495259673701842e-05, + "loss": 1.4175, + "step": 3655 + }, + { + "epoch": 0.38, + "learning_rate": 1.5492201252220777e-05, + "loss": 1.4637, + "step": 3656 + }, + { + "epoch": 0.38, + "learning_rate": 1.5489142094925863e-05, + "loss": 1.4701, + "step": 3657 + }, + { + "epoch": 0.38, + "learning_rate": 1.548608220222695e-05, + "loss": 1.4095, + "step": 3658 + }, + { + "epoch": 0.38, + "learning_rate": 1.548302157453398e-05, + "loss": 1.3903, + "step": 3659 + }, + { + "epoch": 0.38, + "learning_rate": 1.5479960212257002e-05, + "loss": 1.4062, + "step": 3660 + }, + { + "epoch": 0.38, + "learning_rate": 1.5476898115806157e-05, + "loss": 1.4706, + "step": 3661 + }, + { + "epoch": 0.38, + "learning_rate": 1.547383528559169e-05, + "loss": 1.4423, + "step": 3662 + }, + { + "epoch": 0.38, + "learning_rate": 1.547077172202394e-05, + "loss": 1.4418, + "step": 3663 + }, + { + "epoch": 0.38, + "learning_rate": 1.5467707425513347e-05, + "loss": 1.4553, + "step": 3664 + }, + { + "epoch": 0.38, + "learning_rate": 1.5464642396470443e-05, + "loss": 1.435, + "step": 3665 + }, + { + "epoch": 0.38, + "learning_rate": 1.5461576635305873e-05, + "loss": 1.4105, + "step": 3666 + }, + { + "epoch": 0.38, + "learning_rate": 1.5458510142430364e-05, + "loss": 1.4118, + "step": 3667 + }, + { + "epoch": 0.38, + "learning_rate": 1.5455442918254746e-05, + "loss": 1.4096, + "step": 3668 + }, + { + "epoch": 0.38, + "learning_rate": 1.545237496318995e-05, + "loss": 1.4248, + "step": 3669 + }, + { + "epoch": 0.38, + "learning_rate": 1.5449306277647003e-05, + "loss": 1.4591, + "step": 3670 + }, + { + "epoch": 0.38, + "learning_rate": 1.544623686203703e-05, + "loss": 1.4764, + "step": 3671 + }, + { + "epoch": 0.39, + "learning_rate": 1.5443166716771255e-05, + "loss": 1.4329, + "step": 3672 + }, + { + "epoch": 0.39, + "learning_rate": 1.5440095842260995e-05, + "loss": 1.4023, + "step": 3673 + }, + { + "epoch": 0.39, + "learning_rate": 1.5437024238917674e-05, + "loss": 1.3802, + "step": 3674 + }, + { + "epoch": 0.39, + "learning_rate": 1.5433951907152806e-05, + "loss": 1.4627, + "step": 3675 + }, + { + "epoch": 0.39, + "learning_rate": 1.5430878847378e-05, + "loss": 1.5164, + "step": 3676 + }, + { + "epoch": 0.39, + "learning_rate": 1.542780506000497e-05, + "loss": 1.3546, + "step": 3677 + }, + { + "epoch": 0.39, + "learning_rate": 1.542473054544553e-05, + "loss": 1.4415, + "step": 3678 + }, + { + "epoch": 0.39, + "learning_rate": 1.5421655304111573e-05, + "loss": 1.4093, + "step": 3679 + }, + { + "epoch": 0.39, + "learning_rate": 1.5418579336415114e-05, + "loss": 1.3943, + "step": 3680 + }, + { + "epoch": 0.39, + "learning_rate": 1.5415502642768252e-05, + "loss": 1.3659, + "step": 3681 + }, + { + "epoch": 0.39, + "learning_rate": 1.541242522358318e-05, + "loss": 1.4322, + "step": 3682 + }, + { + "epoch": 0.39, + "learning_rate": 1.5409347079272198e-05, + "loss": 1.4064, + "step": 3683 + }, + { + "epoch": 0.39, + "learning_rate": 1.5406268210247693e-05, + "loss": 1.4031, + "step": 3684 + }, + { + "epoch": 0.39, + "learning_rate": 1.540318861692216e-05, + "loss": 1.3449, + "step": 3685 + }, + { + "epoch": 0.39, + "learning_rate": 1.5400108299708182e-05, + "loss": 1.5536, + "step": 3686 + }, + { + "epoch": 0.39, + "learning_rate": 1.5397027259018442e-05, + "loss": 1.4106, + "step": 3687 + }, + { + "epoch": 0.39, + "learning_rate": 1.5393945495265722e-05, + "loss": 1.4309, + "step": 3688 + }, + { + "epoch": 0.39, + "learning_rate": 1.53908630088629e-05, + "loss": 1.3765, + "step": 3689 + }, + { + "epoch": 0.39, + "learning_rate": 1.5387779800222947e-05, + "loss": 1.3809, + "step": 3690 + }, + { + "epoch": 0.39, + "learning_rate": 1.5384695869758938e-05, + "loss": 1.4758, + "step": 3691 + }, + { + "epoch": 0.39, + "learning_rate": 1.5381611217884032e-05, + "loss": 1.4249, + "step": 3692 + }, + { + "epoch": 0.39, + "learning_rate": 1.5378525845011503e-05, + "loss": 1.4133, + "step": 3693 + }, + { + "epoch": 0.39, + "learning_rate": 1.5375439751554708e-05, + "loss": 1.418, + "step": 3694 + }, + { + "epoch": 0.39, + "learning_rate": 1.53723529379271e-05, + "loss": 1.441, + "step": 3695 + }, + { + "epoch": 0.39, + "learning_rate": 1.536926540454224e-05, + "loss": 1.3919, + "step": 3696 + }, + { + "epoch": 0.39, + "learning_rate": 1.5366177151813775e-05, + "loss": 1.3722, + "step": 3697 + }, + { + "epoch": 0.39, + "learning_rate": 1.536308818015545e-05, + "loss": 1.4727, + "step": 3698 + }, + { + "epoch": 0.39, + "learning_rate": 1.535999848998111e-05, + "loss": 1.442, + "step": 3699 + }, + { + "epoch": 0.39, + "learning_rate": 1.535690808170469e-05, + "loss": 1.3884, + "step": 3700 + }, + { + "epoch": 0.39, + "learning_rate": 1.535381695574023e-05, + "loss": 1.3226, + "step": 3701 + }, + { + "epoch": 0.39, + "learning_rate": 1.535072511250186e-05, + "loss": 1.4403, + "step": 3702 + }, + { + "epoch": 0.39, + "learning_rate": 1.5347632552403808e-05, + "loss": 1.4144, + "step": 3703 + }, + { + "epoch": 0.39, + "learning_rate": 1.5344539275860395e-05, + "loss": 1.3514, + "step": 3704 + }, + { + "epoch": 0.39, + "learning_rate": 1.5341445283286044e-05, + "loss": 1.519, + "step": 3705 + }, + { + "epoch": 0.39, + "learning_rate": 1.5338350575095268e-05, + "loss": 1.4251, + "step": 3706 + }, + { + "epoch": 0.39, + "learning_rate": 1.5335255151702685e-05, + "loss": 1.392, + "step": 3707 + }, + { + "epoch": 0.39, + "learning_rate": 1.533215901352299e-05, + "loss": 1.3838, + "step": 3708 + }, + { + "epoch": 0.39, + "learning_rate": 1.532906216097099e-05, + "loss": 1.444, + "step": 3709 + }, + { + "epoch": 0.39, + "learning_rate": 1.5325964594461594e-05, + "loss": 1.3459, + "step": 3710 + }, + { + "epoch": 0.39, + "learning_rate": 1.5322866314409783e-05, + "loss": 1.4155, + "step": 3711 + }, + { + "epoch": 0.39, + "learning_rate": 1.5319767321230657e-05, + "loss": 1.4057, + "step": 3712 + }, + { + "epoch": 0.39, + "learning_rate": 1.5316667615339392e-05, + "loss": 1.382, + "step": 3713 + }, + { + "epoch": 0.39, + "learning_rate": 1.5313567197151277e-05, + "loss": 1.3634, + "step": 3714 + }, + { + "epoch": 0.39, + "learning_rate": 1.5310466067081688e-05, + "loss": 1.3434, + "step": 3715 + }, + { + "epoch": 0.39, + "learning_rate": 1.530736422554609e-05, + "loss": 1.4553, + "step": 3716 + }, + { + "epoch": 0.39, + "learning_rate": 1.5304261672960055e-05, + "loss": 1.4193, + "step": 3717 + }, + { + "epoch": 0.39, + "learning_rate": 1.5301158409739242e-05, + "loss": 1.3955, + "step": 3718 + }, + { + "epoch": 0.39, + "learning_rate": 1.5298054436299413e-05, + "loss": 1.4592, + "step": 3719 + }, + { + "epoch": 0.39, + "learning_rate": 1.529494975305642e-05, + "loss": 1.738, + "step": 3720 + }, + { + "epoch": 0.39, + "learning_rate": 1.529184436042621e-05, + "loss": 1.438, + "step": 3721 + }, + { + "epoch": 0.39, + "learning_rate": 1.528873825882482e-05, + "loss": 1.3445, + "step": 3722 + }, + { + "epoch": 0.39, + "learning_rate": 1.5285631448668395e-05, + "loss": 1.4168, + "step": 3723 + }, + { + "epoch": 0.39, + "learning_rate": 1.528252393037317e-05, + "loss": 1.4088, + "step": 3724 + }, + { + "epoch": 0.39, + "learning_rate": 1.5279415704355468e-05, + "loss": 1.4484, + "step": 3725 + }, + { + "epoch": 0.39, + "learning_rate": 1.5276306771031708e-05, + "loss": 1.4706, + "step": 3726 + }, + { + "epoch": 0.39, + "learning_rate": 1.527319713081841e-05, + "loss": 1.3466, + "step": 3727 + }, + { + "epoch": 0.39, + "learning_rate": 1.5270086784132196e-05, + "loss": 1.427, + "step": 3728 + }, + { + "epoch": 0.39, + "learning_rate": 1.5266975731389754e-05, + "loss": 1.4596, + "step": 3729 + }, + { + "epoch": 0.39, + "learning_rate": 1.52638639730079e-05, + "loss": 1.405, + "step": 3730 + }, + { + "epoch": 0.39, + "learning_rate": 1.5260751509403518e-05, + "loss": 1.4572, + "step": 3731 + }, + { + "epoch": 0.39, + "learning_rate": 1.5257638340993608e-05, + "loss": 1.3827, + "step": 3732 + }, + { + "epoch": 0.39, + "learning_rate": 1.5254524468195251e-05, + "loss": 1.3712, + "step": 3733 + }, + { + "epoch": 0.39, + "learning_rate": 1.5251409891425626e-05, + "loss": 1.4541, + "step": 3734 + }, + { + "epoch": 0.39, + "learning_rate": 1.5248294611102006e-05, + "loss": 1.5279, + "step": 3735 + }, + { + "epoch": 0.39, + "learning_rate": 1.5245178627641759e-05, + "loss": 1.3722, + "step": 3736 + }, + { + "epoch": 0.39, + "learning_rate": 1.5242061941462348e-05, + "loss": 1.5158, + "step": 3737 + }, + { + "epoch": 0.39, + "learning_rate": 1.523894455298132e-05, + "loss": 1.4274, + "step": 3738 + }, + { + "epoch": 0.39, + "learning_rate": 1.5235826462616338e-05, + "loss": 1.4543, + "step": 3739 + }, + { + "epoch": 0.39, + "learning_rate": 1.5232707670785144e-05, + "loss": 1.5011, + "step": 3740 + }, + { + "epoch": 0.39, + "learning_rate": 1.5229588177905568e-05, + "loss": 1.24, + "step": 3741 + }, + { + "epoch": 0.39, + "learning_rate": 1.5226467984395544e-05, + "loss": 1.4253, + "step": 3742 + }, + { + "epoch": 0.39, + "learning_rate": 1.5223347090673102e-05, + "loss": 1.3736, + "step": 3743 + }, + { + "epoch": 0.39, + "learning_rate": 1.522022549715636e-05, + "loss": 1.4587, + "step": 3744 + }, + { + "epoch": 0.39, + "learning_rate": 1.521710320426353e-05, + "loss": 1.5024, + "step": 3745 + }, + { + "epoch": 0.39, + "learning_rate": 1.521398021241292e-05, + "loss": 1.427, + "step": 3746 + }, + { + "epoch": 0.39, + "learning_rate": 1.5210856522022929e-05, + "loss": 1.3387, + "step": 3747 + }, + { + "epoch": 0.39, + "learning_rate": 1.5207732133512055e-05, + "loss": 1.3819, + "step": 3748 + }, + { + "epoch": 0.39, + "learning_rate": 1.5204607047298883e-05, + "loss": 1.4571, + "step": 3749 + }, + { + "epoch": 0.39, + "learning_rate": 1.5201481263802094e-05, + "loss": 1.3592, + "step": 3750 + }, + { + "epoch": 0.39, + "learning_rate": 1.5198354783440464e-05, + "loss": 1.3912, + "step": 3751 + }, + { + "epoch": 0.39, + "learning_rate": 1.519522760663286e-05, + "loss": 1.4986, + "step": 3752 + }, + { + "epoch": 0.39, + "learning_rate": 1.5192099733798243e-05, + "loss": 1.4106, + "step": 3753 + }, + { + "epoch": 0.39, + "learning_rate": 1.5188971165355667e-05, + "loss": 1.4145, + "step": 3754 + }, + { + "epoch": 0.39, + "learning_rate": 1.5185841901724282e-05, + "loss": 1.3915, + "step": 3755 + }, + { + "epoch": 0.39, + "learning_rate": 1.5182711943323329e-05, + "loss": 1.4014, + "step": 3756 + }, + { + "epoch": 0.39, + "learning_rate": 1.5179581290572141e-05, + "loss": 1.3651, + "step": 3757 + }, + { + "epoch": 0.39, + "learning_rate": 1.5176449943890147e-05, + "loss": 1.3653, + "step": 3758 + }, + { + "epoch": 0.39, + "learning_rate": 1.5173317903696862e-05, + "loss": 1.4486, + "step": 3759 + }, + { + "epoch": 0.39, + "learning_rate": 1.5170185170411906e-05, + "loss": 1.4459, + "step": 3760 + }, + { + "epoch": 0.39, + "learning_rate": 1.5167051744454977e-05, + "loss": 1.4215, + "step": 3761 + }, + { + "epoch": 0.39, + "learning_rate": 1.5163917626245877e-05, + "loss": 1.4379, + "step": 3762 + }, + { + "epoch": 0.39, + "learning_rate": 1.51607828162045e-05, + "loss": 1.4147, + "step": 3763 + }, + { + "epoch": 0.39, + "learning_rate": 1.5157647314750827e-05, + "loss": 1.4011, + "step": 3764 + }, + { + "epoch": 0.39, + "learning_rate": 1.5154511122304936e-05, + "loss": 1.4309, + "step": 3765 + }, + { + "epoch": 0.39, + "learning_rate": 1.5151374239286993e-05, + "loss": 1.4382, + "step": 3766 + }, + { + "epoch": 0.4, + "learning_rate": 1.5148236666117266e-05, + "loss": 1.405, + "step": 3767 + }, + { + "epoch": 0.4, + "learning_rate": 1.5145098403216104e-05, + "loss": 1.4223, + "step": 3768 + }, + { + "epoch": 0.4, + "learning_rate": 1.5141959451003951e-05, + "loss": 1.4084, + "step": 3769 + }, + { + "epoch": 0.4, + "learning_rate": 1.5138819809901356e-05, + "loss": 1.4063, + "step": 3770 + }, + { + "epoch": 0.4, + "learning_rate": 1.513567948032894e-05, + "loss": 1.3299, + "step": 3771 + }, + { + "epoch": 0.4, + "learning_rate": 1.5132538462707431e-05, + "loss": 1.3901, + "step": 3772 + }, + { + "epoch": 0.4, + "learning_rate": 1.5129396757457646e-05, + "loss": 1.4249, + "step": 3773 + }, + { + "epoch": 0.4, + "learning_rate": 1.512625436500049e-05, + "loss": 1.4087, + "step": 3774 + }, + { + "epoch": 0.4, + "learning_rate": 1.5123111285756964e-05, + "loss": 1.3521, + "step": 3775 + }, + { + "epoch": 0.4, + "learning_rate": 1.5119967520148163e-05, + "loss": 1.4097, + "step": 3776 + }, + { + "epoch": 0.4, + "learning_rate": 1.5116823068595261e-05, + "loss": 1.4871, + "step": 3777 + }, + { + "epoch": 0.4, + "learning_rate": 1.5113677931519543e-05, + "loss": 1.44, + "step": 3778 + }, + { + "epoch": 0.4, + "learning_rate": 1.5110532109342377e-05, + "loss": 1.4518, + "step": 3779 + }, + { + "epoch": 0.4, + "learning_rate": 1.5107385602485214e-05, + "loss": 1.3961, + "step": 3780 + }, + { + "epoch": 0.4, + "learning_rate": 1.5104238411369614e-05, + "loss": 1.4341, + "step": 3781 + }, + { + "epoch": 0.4, + "eval_loss": 1.4642821550369263, + "eval_runtime": 77.3595, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 3781 + }, + { + "epoch": 0.4, + "learning_rate": 1.5101090536417218e-05, + "loss": 1.403, + "step": 3782 + }, + { + "epoch": 0.4, + "learning_rate": 1.5097941978049754e-05, + "loss": 1.4103, + "step": 3783 + }, + { + "epoch": 0.4, + "learning_rate": 1.5094792736689052e-05, + "loss": 1.3478, + "step": 3784 + }, + { + "epoch": 0.4, + "learning_rate": 1.5091642812757035e-05, + "loss": 1.4134, + "step": 3785 + }, + { + "epoch": 0.4, + "learning_rate": 1.5088492206675701e-05, + "loss": 1.4134, + "step": 3786 + }, + { + "epoch": 0.4, + "learning_rate": 1.5085340918867162e-05, + "loss": 1.1494, + "step": 3787 + }, + { + "epoch": 0.4, + "learning_rate": 1.5082188949753598e-05, + "loss": 1.2385, + "step": 3788 + }, + { + "epoch": 0.4, + "learning_rate": 1.5079036299757299e-05, + "loss": 1.4258, + "step": 3789 + }, + { + "epoch": 0.4, + "learning_rate": 1.5075882969300639e-05, + "loss": 1.3781, + "step": 3790 + }, + { + "epoch": 0.4, + "learning_rate": 1.507272895880608e-05, + "loss": 1.5096, + "step": 3791 + }, + { + "epoch": 0.4, + "learning_rate": 1.5069574268696179e-05, + "loss": 1.366, + "step": 3792 + }, + { + "epoch": 0.4, + "learning_rate": 1.5066418899393584e-05, + "loss": 1.3792, + "step": 3793 + }, + { + "epoch": 0.4, + "learning_rate": 1.506326285132104e-05, + "loss": 1.4987, + "step": 3794 + }, + { + "epoch": 0.4, + "learning_rate": 1.5060106124901364e-05, + "loss": 1.445, + "step": 3795 + }, + { + "epoch": 0.4, + "learning_rate": 1.5056948720557482e-05, + "loss": 1.5071, + "step": 3796 + }, + { + "epoch": 0.4, + "learning_rate": 1.505379063871241e-05, + "loss": 1.4029, + "step": 3797 + }, + { + "epoch": 0.4, + "learning_rate": 1.5050631879789244e-05, + "loss": 1.5263, + "step": 3798 + }, + { + "epoch": 0.4, + "learning_rate": 1.5047472444211175e-05, + "loss": 1.3906, + "step": 3799 + }, + { + "epoch": 0.4, + "learning_rate": 1.5044312332401494e-05, + "loss": 1.7352, + "step": 3800 + }, + { + "epoch": 0.4, + "learning_rate": 1.5041151544783565e-05, + "loss": 1.3946, + "step": 3801 + }, + { + "epoch": 0.4, + "learning_rate": 1.5037990081780862e-05, + "loss": 1.3592, + "step": 3802 + }, + { + "epoch": 0.4, + "learning_rate": 1.503482794381693e-05, + "loss": 1.3991, + "step": 3803 + }, + { + "epoch": 0.4, + "learning_rate": 1.5031665131315423e-05, + "loss": 1.4271, + "step": 3804 + }, + { + "epoch": 0.4, + "learning_rate": 1.502850164470007e-05, + "loss": 1.4305, + "step": 3805 + }, + { + "epoch": 0.4, + "learning_rate": 1.5025337484394701e-05, + "loss": 1.4116, + "step": 3806 + }, + { + "epoch": 0.4, + "learning_rate": 1.5022172650823232e-05, + "loss": 1.4242, + "step": 3807 + }, + { + "epoch": 0.4, + "learning_rate": 1.5019007144409667e-05, + "loss": 1.4427, + "step": 3808 + }, + { + "epoch": 0.4, + "learning_rate": 1.5015840965578106e-05, + "loss": 1.3705, + "step": 3809 + }, + { + "epoch": 0.4, + "learning_rate": 1.5012674114752732e-05, + "loss": 1.4498, + "step": 3810 + }, + { + "epoch": 0.4, + "learning_rate": 1.5009506592357822e-05, + "loss": 1.489, + "step": 3811 + }, + { + "epoch": 0.4, + "learning_rate": 1.5006338398817746e-05, + "loss": 1.4801, + "step": 3812 + }, + { + "epoch": 0.4, + "learning_rate": 1.5003169534556956e-05, + "loss": 1.3468, + "step": 3813 + }, + { + "epoch": 0.4, + "learning_rate": 1.5000000000000002e-05, + "loss": 1.4211, + "step": 3814 + }, + { + "epoch": 0.4, + "learning_rate": 1.4996829795571518e-05, + "loss": 1.4683, + "step": 3815 + }, + { + "epoch": 0.4, + "learning_rate": 1.499365892169623e-05, + "loss": 1.4441, + "step": 3816 + }, + { + "epoch": 0.4, + "learning_rate": 1.4990487378798958e-05, + "loss": 1.4368, + "step": 3817 + }, + { + "epoch": 0.4, + "learning_rate": 1.4987315167304602e-05, + "loss": 1.4097, + "step": 3818 + }, + { + "epoch": 0.4, + "learning_rate": 1.4984142287638155e-05, + "loss": 1.4238, + "step": 3819 + }, + { + "epoch": 0.4, + "learning_rate": 1.4980968740224708e-05, + "loss": 1.497, + "step": 3820 + }, + { + "epoch": 0.4, + "learning_rate": 1.4977794525489433e-05, + "loss": 1.3989, + "step": 3821 + }, + { + "epoch": 0.4, + "learning_rate": 1.4974619643857588e-05, + "loss": 1.4415, + "step": 3822 + }, + { + "epoch": 0.4, + "learning_rate": 1.4971444095754533e-05, + "loss": 1.3931, + "step": 3823 + }, + { + "epoch": 0.4, + "learning_rate": 1.4968267881605705e-05, + "loss": 1.3426, + "step": 3824 + }, + { + "epoch": 0.4, + "learning_rate": 1.4965091001836636e-05, + "loss": 1.644, + "step": 3825 + }, + { + "epoch": 0.4, + "learning_rate": 1.4961913456872945e-05, + "loss": 1.3903, + "step": 3826 + }, + { + "epoch": 0.4, + "learning_rate": 1.4958735247140345e-05, + "loss": 1.3764, + "step": 3827 + }, + { + "epoch": 0.4, + "learning_rate": 1.4955556373064632e-05, + "loss": 1.5484, + "step": 3828 + }, + { + "epoch": 0.4, + "learning_rate": 1.4952376835071696e-05, + "loss": 1.5696, + "step": 3829 + }, + { + "epoch": 0.4, + "learning_rate": 1.4949196633587509e-05, + "loss": 1.3844, + "step": 3830 + }, + { + "epoch": 0.4, + "learning_rate": 1.494601576903814e-05, + "loss": 1.3868, + "step": 3831 + }, + { + "epoch": 0.4, + "learning_rate": 1.4942834241849741e-05, + "loss": 1.4229, + "step": 3832 + }, + { + "epoch": 0.4, + "learning_rate": 1.4939652052448557e-05, + "loss": 1.4062, + "step": 3833 + }, + { + "epoch": 0.4, + "learning_rate": 1.4936469201260915e-05, + "loss": 1.3955, + "step": 3834 + }, + { + "epoch": 0.4, + "learning_rate": 1.4933285688713239e-05, + "loss": 1.3959, + "step": 3835 + }, + { + "epoch": 0.4, + "learning_rate": 1.4930101515232038e-05, + "loss": 1.4652, + "step": 3836 + }, + { + "epoch": 0.4, + "learning_rate": 1.4926916681243913e-05, + "loss": 1.5253, + "step": 3837 + }, + { + "epoch": 0.4, + "learning_rate": 1.4923731187175539e-05, + "loss": 1.4694, + "step": 3838 + }, + { + "epoch": 0.4, + "learning_rate": 1.4920545033453702e-05, + "loss": 1.3859, + "step": 3839 + }, + { + "epoch": 0.4, + "learning_rate": 1.4917358220505259e-05, + "loss": 1.4157, + "step": 3840 + }, + { + "epoch": 0.4, + "learning_rate": 1.4914170748757159e-05, + "loss": 1.4491, + "step": 3841 + }, + { + "epoch": 0.4, + "learning_rate": 1.4910982618636445e-05, + "loss": 1.4464, + "step": 3842 + }, + { + "epoch": 0.4, + "learning_rate": 1.4907793830570246e-05, + "loss": 1.3771, + "step": 3843 + }, + { + "epoch": 0.4, + "learning_rate": 1.4904604384985775e-05, + "loss": 1.3673, + "step": 3844 + }, + { + "epoch": 0.4, + "learning_rate": 1.4901414282310334e-05, + "loss": 1.4429, + "step": 3845 + }, + { + "epoch": 0.4, + "learning_rate": 1.4898223522971318e-05, + "loss": 1.4905, + "step": 3846 + }, + { + "epoch": 0.4, + "learning_rate": 1.4895032107396205e-05, + "loss": 1.4039, + "step": 3847 + }, + { + "epoch": 0.4, + "learning_rate": 1.4891840036012566e-05, + "loss": 1.4082, + "step": 3848 + }, + { + "epoch": 0.4, + "learning_rate": 1.4888647309248052e-05, + "loss": 1.3643, + "step": 3849 + }, + { + "epoch": 0.4, + "learning_rate": 1.4885453927530408e-05, + "loss": 1.3116, + "step": 3850 + }, + { + "epoch": 0.4, + "learning_rate": 1.4882259891287467e-05, + "loss": 1.4278, + "step": 3851 + }, + { + "epoch": 0.4, + "learning_rate": 1.4879065200947148e-05, + "loss": 1.3712, + "step": 3852 + }, + { + "epoch": 0.4, + "learning_rate": 1.4875869856937449e-05, + "loss": 1.387, + "step": 3853 + }, + { + "epoch": 0.4, + "learning_rate": 1.4872673859686475e-05, + "loss": 1.5053, + "step": 3854 + }, + { + "epoch": 0.4, + "learning_rate": 1.4869477209622404e-05, + "loss": 1.4427, + "step": 3855 + }, + { + "epoch": 0.4, + "learning_rate": 1.4866279907173502e-05, + "loss": 1.3404, + "step": 3856 + }, + { + "epoch": 0.4, + "learning_rate": 1.4863081952768126e-05, + "loss": 1.3126, + "step": 3857 + }, + { + "epoch": 0.4, + "learning_rate": 1.4859883346834725e-05, + "loss": 1.4588, + "step": 3858 + }, + { + "epoch": 0.4, + "learning_rate": 1.4856684089801822e-05, + "loss": 1.408, + "step": 3859 + }, + { + "epoch": 0.4, + "learning_rate": 1.4853484182098044e-05, + "loss": 1.4356, + "step": 3860 + }, + { + "epoch": 0.4, + "learning_rate": 1.4850283624152088e-05, + "loss": 1.3768, + "step": 3861 + }, + { + "epoch": 0.4, + "learning_rate": 1.4847082416392753e-05, + "loss": 1.4563, + "step": 3862 + }, + { + "epoch": 0.41, + "learning_rate": 1.4843880559248915e-05, + "loss": 1.3648, + "step": 3863 + }, + { + "epoch": 0.41, + "learning_rate": 1.4840678053149542e-05, + "loss": 1.4146, + "step": 3864 + }, + { + "epoch": 0.41, + "learning_rate": 1.4837474898523686e-05, + "loss": 1.4423, + "step": 3865 + }, + { + "epoch": 0.41, + "learning_rate": 1.4834271095800487e-05, + "loss": 1.3351, + "step": 3866 + }, + { + "epoch": 0.41, + "learning_rate": 1.4831066645409178e-05, + "loss": 1.4534, + "step": 3867 + }, + { + "epoch": 0.41, + "learning_rate": 1.4827861547779066e-05, + "loss": 1.4763, + "step": 3868 + }, + { + "epoch": 0.41, + "learning_rate": 1.4824655803339553e-05, + "loss": 1.4019, + "step": 3869 + }, + { + "epoch": 0.41, + "learning_rate": 1.4821449412520132e-05, + "loss": 1.4223, + "step": 3870 + }, + { + "epoch": 0.41, + "learning_rate": 1.4818242375750371e-05, + "loss": 1.4065, + "step": 3871 + }, + { + "epoch": 0.41, + "learning_rate": 1.481503469345993e-05, + "loss": 1.587, + "step": 3872 + }, + { + "epoch": 0.41, + "learning_rate": 1.4811826366078562e-05, + "loss": 1.3746, + "step": 3873 + }, + { + "epoch": 0.41, + "learning_rate": 1.4808617394036096e-05, + "loss": 1.3425, + "step": 3874 + }, + { + "epoch": 0.41, + "learning_rate": 1.480540777776245e-05, + "loss": 0.6637, + "step": 3875 + }, + { + "epoch": 0.41, + "learning_rate": 1.4802197517687634e-05, + "loss": 1.3366, + "step": 3876 + }, + { + "epoch": 0.41, + "learning_rate": 1.479898661424174e-05, + "loss": 1.4033, + "step": 3877 + }, + { + "epoch": 0.41, + "learning_rate": 1.4795775067854947e-05, + "loss": 1.4005, + "step": 3878 + }, + { + "epoch": 0.41, + "learning_rate": 1.4792562878957516e-05, + "loss": 1.3651, + "step": 3879 + }, + { + "epoch": 0.41, + "learning_rate": 1.47893500479798e-05, + "loss": 1.4185, + "step": 3880 + }, + { + "epoch": 0.41, + "learning_rate": 1.4786136575352236e-05, + "loss": 1.4394, + "step": 3881 + }, + { + "epoch": 0.41, + "learning_rate": 1.478292246150535e-05, + "loss": 1.7243, + "step": 3882 + }, + { + "epoch": 0.41, + "learning_rate": 1.4779707706869744e-05, + "loss": 1.3574, + "step": 3883 + }, + { + "epoch": 0.41, + "learning_rate": 1.4776492311876116e-05, + "loss": 1.4031, + "step": 3884 + }, + { + "epoch": 0.41, + "learning_rate": 1.4773276276955248e-05, + "loss": 1.4351, + "step": 3885 + }, + { + "epoch": 0.41, + "learning_rate": 1.4770059602538002e-05, + "loss": 1.3922, + "step": 3886 + }, + { + "epoch": 0.41, + "learning_rate": 1.4766842289055333e-05, + "loss": 1.3374, + "step": 3887 + }, + { + "epoch": 0.41, + "learning_rate": 1.4763624336938278e-05, + "loss": 1.428, + "step": 3888 + }, + { + "epoch": 0.41, + "learning_rate": 1.476040574661796e-05, + "loss": 1.6087, + "step": 3889 + }, + { + "epoch": 0.41, + "learning_rate": 1.4757186518525586e-05, + "loss": 1.4054, + "step": 3890 + }, + { + "epoch": 0.41, + "learning_rate": 1.4753966653092447e-05, + "loss": 1.2595, + "step": 3891 + }, + { + "epoch": 0.41, + "learning_rate": 1.475074615074993e-05, + "loss": 1.4052, + "step": 3892 + }, + { + "epoch": 0.41, + "learning_rate": 1.4747525011929492e-05, + "loss": 1.4296, + "step": 3893 + }, + { + "epoch": 0.41, + "learning_rate": 1.4744303237062689e-05, + "loss": 1.3718, + "step": 3894 + }, + { + "epoch": 0.41, + "learning_rate": 1.4741080826581151e-05, + "loss": 1.4498, + "step": 3895 + }, + { + "epoch": 0.41, + "learning_rate": 1.4737857780916602e-05, + "loss": 1.4029, + "step": 3896 + }, + { + "epoch": 0.41, + "learning_rate": 1.4734634100500846e-05, + "loss": 1.4136, + "step": 3897 + }, + { + "epoch": 0.41, + "learning_rate": 1.4731409785765774e-05, + "loss": 1.348, + "step": 3898 + }, + { + "epoch": 0.41, + "learning_rate": 1.4728184837143355e-05, + "loss": 1.3407, + "step": 3899 + }, + { + "epoch": 0.41, + "learning_rate": 1.472495925506566e-05, + "loss": 1.3737, + "step": 3900 + }, + { + "epoch": 0.41, + "learning_rate": 1.4721733039964826e-05, + "loss": 2.2305, + "step": 3901 + }, + { + "epoch": 0.41, + "learning_rate": 1.4718506192273087e-05, + "loss": 1.4506, + "step": 3902 + }, + { + "epoch": 0.41, + "learning_rate": 1.4715278712422754e-05, + "loss": 1.3657, + "step": 3903 + }, + { + "epoch": 0.41, + "learning_rate": 1.471205060084623e-05, + "loss": 1.4644, + "step": 3904 + }, + { + "epoch": 0.41, + "learning_rate": 1.4708821857976001e-05, + "loss": 1.4823, + "step": 3905 + }, + { + "epoch": 0.41, + "learning_rate": 1.4705592484244628e-05, + "loss": 1.3392, + "step": 3906 + }, + { + "epoch": 0.41, + "learning_rate": 1.4702362480084769e-05, + "loss": 1.3302, + "step": 3907 + }, + { + "epoch": 0.41, + "learning_rate": 1.4699131845929163e-05, + "loss": 1.8952, + "step": 3908 + }, + { + "epoch": 0.41, + "learning_rate": 1.469590058221063e-05, + "loss": 1.4982, + "step": 3909 + }, + { + "epoch": 0.41, + "learning_rate": 1.4692668689362074e-05, + "loss": 1.407, + "step": 3910 + }, + { + "epoch": 0.41, + "learning_rate": 1.4689436167816489e-05, + "loss": 1.3911, + "step": 3911 + }, + { + "epoch": 0.41, + "learning_rate": 1.4686203018006948e-05, + "loss": 1.3421, + "step": 3912 + }, + { + "epoch": 0.41, + "learning_rate": 1.4682969240366612e-05, + "loss": 1.4627, + "step": 3913 + }, + { + "epoch": 0.41, + "learning_rate": 1.4679734835328718e-05, + "loss": 1.394, + "step": 3914 + }, + { + "epoch": 0.41, + "learning_rate": 1.4676499803326603e-05, + "loss": 1.4484, + "step": 3915 + }, + { + "epoch": 0.41, + "learning_rate": 1.4673264144793673e-05, + "loss": 1.4665, + "step": 3916 + }, + { + "epoch": 0.41, + "learning_rate": 1.4670027860163422e-05, + "loss": 1.3191, + "step": 3917 + }, + { + "epoch": 0.41, + "learning_rate": 1.466679094986943e-05, + "loss": 1.4748, + "step": 3918 + }, + { + "epoch": 0.41, + "learning_rate": 1.4663553414345361e-05, + "loss": 1.2467, + "step": 3919 + }, + { + "epoch": 0.41, + "learning_rate": 1.466031525402496e-05, + "loss": 1.4279, + "step": 3920 + }, + { + "epoch": 0.41, + "learning_rate": 1.4657076469342059e-05, + "loss": 1.3822, + "step": 3921 + }, + { + "epoch": 0.41, + "learning_rate": 1.4653837060730566e-05, + "loss": 1.3659, + "step": 3922 + }, + { + "epoch": 0.41, + "learning_rate": 1.465059702862449e-05, + "loss": 1.3663, + "step": 3923 + }, + { + "epoch": 0.41, + "learning_rate": 1.4647356373457902e-05, + "loss": 1.4371, + "step": 3924 + }, + { + "epoch": 0.41, + "learning_rate": 1.4644115095664972e-05, + "loss": 1.3473, + "step": 3925 + }, + { + "epoch": 0.41, + "learning_rate": 1.4640873195679944e-05, + "loss": 1.4797, + "step": 3926 + }, + { + "epoch": 0.41, + "learning_rate": 1.463763067393715e-05, + "loss": 1.3973, + "step": 3927 + }, + { + "epoch": 0.41, + "learning_rate": 1.4634387530871008e-05, + "loss": 1.3899, + "step": 3928 + }, + { + "epoch": 0.41, + "learning_rate": 1.4631143766916015e-05, + "loss": 1.3828, + "step": 3929 + }, + { + "epoch": 0.41, + "learning_rate": 1.4627899382506745e-05, + "loss": 1.4569, + "step": 3930 + }, + { + "epoch": 0.41, + "learning_rate": 1.4624654378077872e-05, + "loss": 1.4011, + "step": 3931 + }, + { + "epoch": 0.41, + "learning_rate": 1.462140875406414e-05, + "loss": 1.3859, + "step": 3932 + }, + { + "epoch": 0.41, + "learning_rate": 1.4618162510900376e-05, + "loss": 1.4518, + "step": 3933 + }, + { + "epoch": 0.41, + "learning_rate": 1.4614915649021493e-05, + "loss": 1.4399, + "step": 3934 + }, + { + "epoch": 0.41, + "learning_rate": 1.4611668168862495e-05, + "loss": 1.4034, + "step": 3935 + }, + { + "epoch": 0.41, + "learning_rate": 1.4608420070858452e-05, + "loss": 1.3919, + "step": 3936 + }, + { + "epoch": 0.41, + "learning_rate": 1.4605171355444528e-05, + "loss": 1.391, + "step": 3937 + }, + { + "epoch": 0.41, + "learning_rate": 1.460192202305597e-05, + "loss": 1.3717, + "step": 3938 + }, + { + "epoch": 0.41, + "learning_rate": 1.4598672074128103e-05, + "loss": 1.4351, + "step": 3939 + }, + { + "epoch": 0.41, + "learning_rate": 1.4595421509096339e-05, + "loss": 1.4202, + "step": 3940 + }, + { + "epoch": 0.41, + "learning_rate": 1.4592170328396165e-05, + "loss": 1.3559, + "step": 3941 + }, + { + "epoch": 0.41, + "learning_rate": 1.458891853246316e-05, + "loss": 1.5878, + "step": 3942 + }, + { + "epoch": 0.41, + "learning_rate": 1.4585666121732982e-05, + "loss": 1.3818, + "step": 3943 + }, + { + "epoch": 0.41, + "learning_rate": 1.4582413096641369e-05, + "loss": 1.4009, + "step": 3944 + }, + { + "epoch": 0.41, + "learning_rate": 1.457915945762414e-05, + "loss": 1.3937, + "step": 3945 + }, + { + "epoch": 0.41, + "learning_rate": 1.4575905205117203e-05, + "loss": 1.381, + "step": 3946 + }, + { + "epoch": 0.41, + "learning_rate": 1.457265033955654e-05, + "loss": 1.3844, + "step": 3947 + }, + { + "epoch": 0.41, + "learning_rate": 1.4569394861378226e-05, + "loss": 1.4059, + "step": 3948 + }, + { + "epoch": 0.41, + "learning_rate": 1.4566138771018403e-05, + "loss": 1.3698, + "step": 3949 + }, + { + "epoch": 0.41, + "learning_rate": 1.4562882068913311e-05, + "loss": 1.4253, + "step": 3950 + }, + { + "epoch": 0.41, + "learning_rate": 1.455962475549926e-05, + "loss": 1.4284, + "step": 3951 + }, + { + "epoch": 0.41, + "learning_rate": 1.4556366831212647e-05, + "loss": 1.4279, + "step": 3952 + }, + { + "epoch": 0.41, + "learning_rate": 1.4553108296489951e-05, + "loss": 1.3072, + "step": 3953 + }, + { + "epoch": 0.41, + "learning_rate": 1.4549849151767731e-05, + "loss": 1.4175, + "step": 3954 + }, + { + "epoch": 0.41, + "learning_rate": 1.4546589397482632e-05, + "loss": 1.5042, + "step": 3955 + }, + { + "epoch": 0.41, + "learning_rate": 1.4543329034071371e-05, + "loss": 1.4363, + "step": 3956 + }, + { + "epoch": 0.41, + "learning_rate": 1.454006806197076e-05, + "loss": 1.4111, + "step": 3957 + }, + { + "epoch": 0.42, + "learning_rate": 1.453680648161768e-05, + "loss": 1.3817, + "step": 3958 + }, + { + "epoch": 0.42, + "learning_rate": 1.45335442934491e-05, + "loss": 1.4689, + "step": 3959 + }, + { + "epoch": 0.42, + "learning_rate": 1.4530281497902072e-05, + "loss": 1.4164, + "step": 3960 + }, + { + "epoch": 0.42, + "learning_rate": 1.4527018095413726e-05, + "loss": 1.3943, + "step": 3961 + }, + { + "epoch": 0.42, + "learning_rate": 1.4523754086421271e-05, + "loss": 1.3851, + "step": 3962 + }, + { + "epoch": 0.42, + "learning_rate": 1.4520489471362003e-05, + "loss": 1.3907, + "step": 3963 + }, + { + "epoch": 0.42, + "learning_rate": 1.4517224250673297e-05, + "loss": 1.2877, + "step": 3964 + }, + { + "epoch": 0.42, + "learning_rate": 1.4513958424792605e-05, + "loss": 1.4696, + "step": 3965 + }, + { + "epoch": 0.42, + "learning_rate": 1.4510691994157471e-05, + "loss": 1.3785, + "step": 3966 + }, + { + "epoch": 0.42, + "learning_rate": 1.4507424959205505e-05, + "loss": 1.3652, + "step": 3967 + }, + { + "epoch": 0.42, + "learning_rate": 1.4504157320374408e-05, + "loss": 1.4198, + "step": 3968 + }, + { + "epoch": 0.42, + "learning_rate": 1.4500889078101962e-05, + "loss": 1.3476, + "step": 3969 + }, + { + "epoch": 0.42, + "learning_rate": 1.4497620232826028e-05, + "loss": 1.4356, + "step": 3970 + }, + { + "epoch": 0.42, + "learning_rate": 1.4494350784984543e-05, + "loss": 1.4993, + "step": 3971 + }, + { + "epoch": 0.42, + "learning_rate": 1.4491080735015533e-05, + "loss": 1.4022, + "step": 3972 + }, + { + "epoch": 0.42, + "learning_rate": 1.44878100833571e-05, + "loss": 1.4074, + "step": 3973 + }, + { + "epoch": 0.42, + "learning_rate": 1.4484538830447423e-05, + "loss": 1.412, + "step": 3974 + }, + { + "epoch": 0.42, + "learning_rate": 1.4481266976724772e-05, + "loss": 1.3872, + "step": 3975 + }, + { + "epoch": 0.42, + "learning_rate": 1.4477994522627485e-05, + "loss": 1.4575, + "step": 3976 + }, + { + "epoch": 0.42, + "learning_rate": 1.4474721468593995e-05, + "loss": 1.3768, + "step": 3977 + }, + { + "epoch": 0.42, + "learning_rate": 1.44714478150628e-05, + "loss": 1.4173, + "step": 3978 + }, + { + "epoch": 0.42, + "learning_rate": 1.4468173562472489e-05, + "loss": 1.3896, + "step": 3979 + }, + { + "epoch": 0.42, + "learning_rate": 1.4464898711261725e-05, + "loss": 1.4535, + "step": 3980 + }, + { + "epoch": 0.42, + "eval_loss": 1.4580057859420776, + "eval_runtime": 77.4537, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 3980 + }, + { + "epoch": 0.42, + "learning_rate": 1.4461623261869258e-05, + "loss": 1.4046, + "step": 3981 + }, + { + "epoch": 0.42, + "learning_rate": 1.445834721473391e-05, + "loss": 1.37, + "step": 3982 + }, + { + "epoch": 0.42, + "learning_rate": 1.4455070570294588e-05, + "loss": 1.4566, + "step": 3983 + }, + { + "epoch": 0.42, + "learning_rate": 1.445179332899028e-05, + "loss": 1.4513, + "step": 3984 + }, + { + "epoch": 0.42, + "learning_rate": 1.4448515491260051e-05, + "loss": 1.3893, + "step": 3985 + }, + { + "epoch": 0.42, + "learning_rate": 1.4445237057543047e-05, + "loss": 1.3955, + "step": 3986 + }, + { + "epoch": 0.42, + "learning_rate": 1.4441958028278493e-05, + "loss": 1.4861, + "step": 3987 + }, + { + "epoch": 0.42, + "learning_rate": 1.4438678403905697e-05, + "loss": 1.4601, + "step": 3988 + }, + { + "epoch": 0.42, + "learning_rate": 1.4435398184864043e-05, + "loss": 1.398, + "step": 3989 + }, + { + "epoch": 0.42, + "learning_rate": 1.4432117371592995e-05, + "loss": 1.4392, + "step": 3990 + }, + { + "epoch": 0.42, + "learning_rate": 1.4428835964532098e-05, + "loss": 1.3772, + "step": 3991 + }, + { + "epoch": 0.42, + "learning_rate": 1.4425553964120979e-05, + "loss": 1.4241, + "step": 3992 + }, + { + "epoch": 0.42, + "learning_rate": 1.4422271370799338e-05, + "loss": 1.3237, + "step": 3993 + }, + { + "epoch": 0.42, + "learning_rate": 1.4418988185006964e-05, + "loss": 1.3813, + "step": 3994 + }, + { + "epoch": 0.42, + "learning_rate": 1.4415704407183709e-05, + "loss": 1.6139, + "step": 3995 + }, + { + "epoch": 0.42, + "learning_rate": 1.4412420037769525e-05, + "loss": 1.4431, + "step": 3996 + }, + { + "epoch": 0.42, + "learning_rate": 1.440913507720443e-05, + "loss": 1.3862, + "step": 3997 + }, + { + "epoch": 0.42, + "learning_rate": 1.4405849525928523e-05, + "loss": 1.3895, + "step": 3998 + }, + { + "epoch": 0.42, + "learning_rate": 1.4402563384381981e-05, + "loss": 1.4068, + "step": 3999 + }, + { + "epoch": 0.42, + "learning_rate": 1.4399276653005072e-05, + "loss": 1.4501, + "step": 4000 + }, + { + "epoch": 0.42, + "learning_rate": 1.4395989332238124e-05, + "loss": 1.3165, + "step": 4001 + }, + { + "epoch": 0.42, + "learning_rate": 1.4392701422521555e-05, + "loss": 1.3783, + "step": 4002 + }, + { + "epoch": 0.42, + "learning_rate": 1.4389412924295865e-05, + "loss": 1.343, + "step": 4003 + }, + { + "epoch": 0.42, + "learning_rate": 1.4386123838001625e-05, + "loss": 1.3456, + "step": 4004 + }, + { + "epoch": 0.42, + "learning_rate": 1.4382834164079486e-05, + "loss": 1.3689, + "step": 4005 + }, + { + "epoch": 0.42, + "learning_rate": 1.4379543902970183e-05, + "loss": 1.3789, + "step": 4006 + }, + { + "epoch": 0.42, + "learning_rate": 1.4376253055114528e-05, + "loss": 1.4912, + "step": 4007 + }, + { + "epoch": 0.42, + "learning_rate": 1.4372961620953407e-05, + "loss": 1.3692, + "step": 4008 + }, + { + "epoch": 0.42, + "learning_rate": 1.436966960092779e-05, + "loss": 1.4901, + "step": 4009 + }, + { + "epoch": 0.42, + "learning_rate": 1.4366376995478717e-05, + "loss": 1.4431, + "step": 4010 + }, + { + "epoch": 0.42, + "learning_rate": 1.436308380504732e-05, + "loss": 1.4626, + "step": 4011 + }, + { + "epoch": 0.42, + "learning_rate": 1.4359790030074798e-05, + "loss": 1.4241, + "step": 4012 + }, + { + "epoch": 0.42, + "learning_rate": 1.4356495671002435e-05, + "loss": 1.3834, + "step": 4013 + }, + { + "epoch": 0.42, + "learning_rate": 1.4353200728271586e-05, + "loss": 1.3626, + "step": 4014 + }, + { + "epoch": 0.42, + "learning_rate": 1.4349905202323692e-05, + "loss": 1.3557, + "step": 4015 + }, + { + "epoch": 0.42, + "learning_rate": 1.434660909360027e-05, + "loss": 1.4077, + "step": 4016 + }, + { + "epoch": 0.42, + "learning_rate": 1.4343312402542911e-05, + "loss": 1.4337, + "step": 4017 + }, + { + "epoch": 0.42, + "learning_rate": 1.4340015129593286e-05, + "loss": 1.419, + "step": 4018 + }, + { + "epoch": 0.42, + "learning_rate": 1.4336717275193148e-05, + "loss": 1.3768, + "step": 4019 + }, + { + "epoch": 0.42, + "learning_rate": 1.4333418839784326e-05, + "loss": 1.383, + "step": 4020 + }, + { + "epoch": 0.42, + "learning_rate": 1.4330119823808719e-05, + "loss": 1.3951, + "step": 4021 + }, + { + "epoch": 0.42, + "learning_rate": 1.4326820227708316e-05, + "loss": 1.3985, + "step": 4022 + }, + { + "epoch": 0.42, + "learning_rate": 1.4323520051925177e-05, + "loss": 1.356, + "step": 4023 + }, + { + "epoch": 0.42, + "learning_rate": 1.4320219296901439e-05, + "loss": 1.5017, + "step": 4024 + }, + { + "epoch": 0.42, + "learning_rate": 1.4316917963079322e-05, + "loss": 1.3594, + "step": 4025 + }, + { + "epoch": 0.42, + "learning_rate": 1.4313616050901114e-05, + "loss": 1.6028, + "step": 4026 + }, + { + "epoch": 0.42, + "learning_rate": 1.4310313560809193e-05, + "loss": 1.4132, + "step": 4027 + }, + { + "epoch": 0.42, + "learning_rate": 1.4307010493246006e-05, + "loss": 1.2969, + "step": 4028 + }, + { + "epoch": 0.42, + "learning_rate": 1.4303706848654073e-05, + "loss": 1.5224, + "step": 4029 + }, + { + "epoch": 0.42, + "learning_rate": 1.4300402627476007e-05, + "loss": 1.3386, + "step": 4030 + }, + { + "epoch": 0.42, + "learning_rate": 1.429709783015448e-05, + "loss": 1.3554, + "step": 4031 + }, + { + "epoch": 0.42, + "learning_rate": 1.4293792457132259e-05, + "loss": 1.3386, + "step": 4032 + }, + { + "epoch": 0.42, + "learning_rate": 1.429048650885217e-05, + "loss": 1.4613, + "step": 4033 + }, + { + "epoch": 0.42, + "learning_rate": 1.4287179985757132e-05, + "loss": 1.3632, + "step": 4034 + }, + { + "epoch": 0.42, + "learning_rate": 1.428387288829013e-05, + "loss": 1.3835, + "step": 4035 + }, + { + "epoch": 0.42, + "learning_rate": 1.4280565216894234e-05, + "loss": 1.3711, + "step": 4036 + }, + { + "epoch": 0.42, + "learning_rate": 1.4277256972012582e-05, + "loss": 1.3385, + "step": 4037 + }, + { + "epoch": 0.42, + "learning_rate": 1.4273948154088395e-05, + "loss": 1.4607, + "step": 4038 + }, + { + "epoch": 0.42, + "learning_rate": 1.4270638763564973e-05, + "loss": 1.4042, + "step": 4039 + }, + { + "epoch": 0.42, + "learning_rate": 1.4267328800885687e-05, + "loss": 1.4006, + "step": 4040 + }, + { + "epoch": 0.42, + "learning_rate": 1.4264018266493987e-05, + "loss": 1.386, + "step": 4041 + }, + { + "epoch": 0.42, + "learning_rate": 1.4260707160833401e-05, + "loss": 1.3487, + "step": 4042 + }, + { + "epoch": 0.42, + "learning_rate": 1.4257395484347529e-05, + "loss": 1.4199, + "step": 4043 + }, + { + "epoch": 0.42, + "learning_rate": 1.4254083237480054e-05, + "loss": 1.3236, + "step": 4044 + }, + { + "epoch": 0.42, + "learning_rate": 1.4250770420674726e-05, + "loss": 1.4056, + "step": 4045 + }, + { + "epoch": 0.42, + "learning_rate": 1.4247457034375387e-05, + "loss": 1.4391, + "step": 4046 + }, + { + "epoch": 0.42, + "learning_rate": 1.4244143079025938e-05, + "loss": 1.3935, + "step": 4047 + }, + { + "epoch": 0.42, + "learning_rate": 1.4240828555070368e-05, + "loss": 1.3623, + "step": 4048 + }, + { + "epoch": 0.42, + "learning_rate": 1.4237513462952733e-05, + "loss": 1.3254, + "step": 4049 + }, + { + "epoch": 0.42, + "learning_rate": 1.4234197803117174e-05, + "loss": 1.4217, + "step": 4050 + }, + { + "epoch": 0.42, + "learning_rate": 1.4230881576007904e-05, + "loss": 1.435, + "step": 4051 + }, + { + "epoch": 0.42, + "learning_rate": 1.422756478206921e-05, + "loss": 1.3687, + "step": 4052 + }, + { + "epoch": 0.43, + "learning_rate": 1.4224247421745464e-05, + "loss": 1.3965, + "step": 4053 + }, + { + "epoch": 0.43, + "learning_rate": 1.4220929495481097e-05, + "loss": 1.4159, + "step": 4054 + }, + { + "epoch": 0.43, + "learning_rate": 1.4217611003720632e-05, + "loss": 1.3632, + "step": 4055 + }, + { + "epoch": 0.43, + "learning_rate": 1.4214291946908661e-05, + "loss": 1.403, + "step": 4056 + }, + { + "epoch": 0.43, + "learning_rate": 1.4210972325489854e-05, + "loss": 1.4093, + "step": 4057 + }, + { + "epoch": 0.43, + "learning_rate": 1.4207652139908952e-05, + "loss": 1.4551, + "step": 4058 + }, + { + "epoch": 0.43, + "learning_rate": 1.4204331390610775e-05, + "loss": 1.4162, + "step": 4059 + }, + { + "epoch": 0.43, + "learning_rate": 1.4201010078040216e-05, + "loss": 1.4492, + "step": 4060 + }, + { + "epoch": 0.43, + "learning_rate": 1.419768820264225e-05, + "loss": 1.4449, + "step": 4061 + }, + { + "epoch": 0.43, + "learning_rate": 1.4194365764861922e-05, + "loss": 1.3382, + "step": 4062 + }, + { + "epoch": 0.43, + "learning_rate": 1.419104276514435e-05, + "loss": 1.3899, + "step": 4063 + }, + { + "epoch": 0.43, + "learning_rate": 1.4187719203934734e-05, + "loss": 1.3513, + "step": 4064 + }, + { + "epoch": 0.43, + "learning_rate": 1.4184395081678344e-05, + "loss": 1.3954, + "step": 4065 + }, + { + "epoch": 0.43, + "learning_rate": 1.4181070398820528e-05, + "loss": 1.442, + "step": 4066 + }, + { + "epoch": 0.43, + "learning_rate": 1.4177745155806708e-05, + "loss": 1.3907, + "step": 4067 + }, + { + "epoch": 0.43, + "learning_rate": 1.417441935308238e-05, + "loss": 1.3757, + "step": 4068 + }, + { + "epoch": 0.43, + "learning_rate": 1.4171092991093118e-05, + "loss": 1.3507, + "step": 4069 + }, + { + "epoch": 0.43, + "learning_rate": 1.4167766070284568e-05, + "loss": 1.4136, + "step": 4070 + }, + { + "epoch": 0.43, + "learning_rate": 1.4164438591102452e-05, + "loss": 1.3835, + "step": 4071 + }, + { + "epoch": 0.43, + "learning_rate": 1.4161110553992565e-05, + "loss": 1.4981, + "step": 4072 + }, + { + "epoch": 0.43, + "learning_rate": 1.415778195940078e-05, + "loss": 1.4387, + "step": 4073 + }, + { + "epoch": 0.43, + "learning_rate": 1.4154452807773047e-05, + "loss": 1.333, + "step": 4074 + }, + { + "epoch": 0.43, + "learning_rate": 1.4151123099555377e-05, + "loss": 1.3558, + "step": 4075 + }, + { + "epoch": 0.43, + "learning_rate": 1.4147792835193875e-05, + "loss": 1.4655, + "step": 4076 + }, + { + "epoch": 0.43, + "learning_rate": 1.4144462015134708e-05, + "loss": 1.4402, + "step": 4077 + }, + { + "epoch": 0.43, + "learning_rate": 1.4141130639824119e-05, + "loss": 1.4227, + "step": 4078 + }, + { + "epoch": 0.43, + "learning_rate": 1.4137798709708423e-05, + "loss": 1.4039, + "step": 4079 + }, + { + "epoch": 0.43, + "learning_rate": 1.4134466225234023e-05, + "loss": 1.3593, + "step": 4080 + }, + { + "epoch": 0.43, + "learning_rate": 1.4131133186847377e-05, + "loss": 1.372, + "step": 4081 + }, + { + "epoch": 0.43, + "learning_rate": 1.412779959499503e-05, + "loss": 1.4487, + "step": 4082 + }, + { + "epoch": 0.43, + "learning_rate": 1.4124465450123599e-05, + "loss": 1.3972, + "step": 4083 + }, + { + "epoch": 0.43, + "learning_rate": 1.4121130752679772e-05, + "loss": 1.3768, + "step": 4084 + }, + { + "epoch": 0.43, + "learning_rate": 1.4117795503110313e-05, + "loss": 1.3827, + "step": 4085 + }, + { + "epoch": 0.43, + "learning_rate": 1.4114459701862062e-05, + "loss": 1.3922, + "step": 4086 + }, + { + "epoch": 0.43, + "learning_rate": 1.4111123349381925e-05, + "loss": 1.3736, + "step": 4087 + }, + { + "epoch": 0.43, + "learning_rate": 1.4107786446116894e-05, + "loss": 1.4338, + "step": 4088 + }, + { + "epoch": 0.43, + "learning_rate": 1.4104448992514023e-05, + "loss": 1.347, + "step": 4089 + }, + { + "epoch": 0.43, + "learning_rate": 1.410111098902045e-05, + "loss": 1.3915, + "step": 4090 + }, + { + "epoch": 0.43, + "learning_rate": 1.4097772436083377e-05, + "loss": 1.3656, + "step": 4091 + }, + { + "epoch": 0.43, + "learning_rate": 1.4094433334150087e-05, + "loss": 1.3461, + "step": 4092 + }, + { + "epoch": 0.43, + "learning_rate": 1.4091093683667934e-05, + "loss": 1.7345, + "step": 4093 + }, + { + "epoch": 0.43, + "learning_rate": 1.4087753485084343e-05, + "loss": 1.6204, + "step": 4094 + }, + { + "epoch": 0.43, + "learning_rate": 1.4084412738846816e-05, + "loss": 1.4074, + "step": 4095 + }, + { + "epoch": 0.43, + "learning_rate": 1.408107144540293e-05, + "loss": 1.3776, + "step": 4096 + }, + { + "epoch": 0.43, + "learning_rate": 1.407772960520033e-05, + "loss": 1.4079, + "step": 4097 + }, + { + "epoch": 0.43, + "learning_rate": 1.4074387218686734e-05, + "loss": 1.4254, + "step": 4098 + }, + { + "epoch": 0.43, + "learning_rate": 1.407104428630994e-05, + "loss": 1.38, + "step": 4099 + }, + { + "epoch": 0.43, + "learning_rate": 1.4067700808517815e-05, + "loss": 1.4175, + "step": 4100 + }, + { + "epoch": 0.43, + "learning_rate": 1.4064356785758298e-05, + "loss": 1.4085, + "step": 4101 + }, + { + "epoch": 0.43, + "learning_rate": 1.4061012218479397e-05, + "loss": 1.4529, + "step": 4102 + }, + { + "epoch": 0.43, + "learning_rate": 1.405766710712921e-05, + "loss": 1.4836, + "step": 4103 + }, + { + "epoch": 0.43, + "learning_rate": 1.4054321452155885e-05, + "loss": 1.3915, + "step": 4104 + }, + { + "epoch": 0.43, + "learning_rate": 1.4050975254007659e-05, + "loss": 1.3044, + "step": 4105 + }, + { + "epoch": 0.43, + "learning_rate": 1.4047628513132835e-05, + "loss": 1.373, + "step": 4106 + }, + { + "epoch": 0.43, + "learning_rate": 1.4044281229979793e-05, + "loss": 1.4266, + "step": 4107 + }, + { + "epoch": 0.43, + "learning_rate": 1.4040933404996977e-05, + "loss": 1.3898, + "step": 4108 + }, + { + "epoch": 0.43, + "learning_rate": 1.4037585038632915e-05, + "loss": 0.9326, + "step": 4109 + }, + { + "epoch": 0.43, + "learning_rate": 1.40342361313362e-05, + "loss": 1.0831, + "step": 4110 + }, + { + "epoch": 0.43, + "learning_rate": 1.40308866835555e-05, + "loss": 1.3898, + "step": 4111 + }, + { + "epoch": 0.43, + "learning_rate": 1.4027536695739554e-05, + "loss": 1.5058, + "step": 4112 + }, + { + "epoch": 0.43, + "learning_rate": 1.4024186168337175e-05, + "loss": 1.3635, + "step": 4113 + }, + { + "epoch": 0.43, + "learning_rate": 1.4020835101797248e-05, + "loss": 1.3871, + "step": 4114 + }, + { + "epoch": 0.43, + "learning_rate": 1.401748349656873e-05, + "loss": 1.3478, + "step": 4115 + }, + { + "epoch": 0.43, + "learning_rate": 1.4014131353100648e-05, + "loss": 1.3356, + "step": 4116 + }, + { + "epoch": 0.43, + "learning_rate": 1.4010778671842107e-05, + "loss": 1.3954, + "step": 4117 + }, + { + "epoch": 0.43, + "learning_rate": 1.4007425453242274e-05, + "loss": 1.3307, + "step": 4118 + }, + { + "epoch": 0.43, + "learning_rate": 1.4004071697750398e-05, + "loss": 1.4508, + "step": 4119 + }, + { + "epoch": 0.43, + "learning_rate": 1.4000717405815799e-05, + "loss": 1.3752, + "step": 4120 + }, + { + "epoch": 0.43, + "learning_rate": 1.399736257788786e-05, + "loss": 1.3654, + "step": 4121 + }, + { + "epoch": 0.43, + "learning_rate": 1.3994007214416046e-05, + "loss": 1.4505, + "step": 4122 + }, + { + "epoch": 0.43, + "learning_rate": 1.3990651315849886e-05, + "loss": 1.4307, + "step": 4123 + }, + { + "epoch": 0.43, + "learning_rate": 1.398729488263899e-05, + "loss": 1.4481, + "step": 4124 + }, + { + "epoch": 0.43, + "learning_rate": 1.3983937915233026e-05, + "loss": 1.4755, + "step": 4125 + }, + { + "epoch": 0.43, + "learning_rate": 1.3980580414081746e-05, + "loss": 1.3402, + "step": 4126 + }, + { + "epoch": 0.43, + "learning_rate": 1.3977222379634969e-05, + "loss": 1.3636, + "step": 4127 + }, + { + "epoch": 0.43, + "learning_rate": 1.3973863812342585e-05, + "loss": 1.4165, + "step": 4128 + }, + { + "epoch": 0.43, + "learning_rate": 1.3970504712654554e-05, + "loss": 1.3832, + "step": 4129 + }, + { + "epoch": 0.43, + "learning_rate": 1.3967145081020912e-05, + "loss": 1.4236, + "step": 4130 + }, + { + "epoch": 0.43, + "learning_rate": 1.396378491789176e-05, + "loss": 1.5022, + "step": 4131 + }, + { + "epoch": 0.43, + "learning_rate": 1.3960424223717276e-05, + "loss": 1.3806, + "step": 4132 + }, + { + "epoch": 0.43, + "learning_rate": 1.3957062998947707e-05, + "loss": 1.3649, + "step": 4133 + }, + { + "epoch": 0.43, + "learning_rate": 1.3953701244033368e-05, + "loss": 1.3787, + "step": 4134 + }, + { + "epoch": 0.43, + "learning_rate": 1.395033895942465e-05, + "loss": 1.3551, + "step": 4135 + }, + { + "epoch": 0.43, + "learning_rate": 1.394697614557201e-05, + "loss": 1.3881, + "step": 4136 + }, + { + "epoch": 0.43, + "learning_rate": 1.3943612802925983e-05, + "loss": 1.4848, + "step": 4137 + }, + { + "epoch": 0.43, + "learning_rate": 1.3940248931937169e-05, + "loss": 1.425, + "step": 4138 + }, + { + "epoch": 0.43, + "learning_rate": 1.3936884533056238e-05, + "loss": 1.4054, + "step": 4139 + }, + { + "epoch": 0.43, + "learning_rate": 1.3933519606733934e-05, + "loss": 1.4028, + "step": 4140 + }, + { + "epoch": 0.43, + "learning_rate": 1.3930154153421072e-05, + "loss": 1.4439, + "step": 4141 + }, + { + "epoch": 0.43, + "learning_rate": 1.3926788173568536e-05, + "loss": 1.4482, + "step": 4142 + }, + { + "epoch": 0.43, + "learning_rate": 1.392342166762728e-05, + "loss": 1.393, + "step": 4143 + }, + { + "epoch": 0.43, + "learning_rate": 1.3920054636048328e-05, + "loss": 1.4097, + "step": 4144 + }, + { + "epoch": 0.43, + "learning_rate": 1.391668707928278e-05, + "loss": 1.5142, + "step": 4145 + }, + { + "epoch": 0.43, + "learning_rate": 1.3913318997781797e-05, + "loss": 1.4118, + "step": 4146 + }, + { + "epoch": 0.43, + "learning_rate": 1.390995039199662e-05, + "loss": 1.4067, + "step": 4147 + }, + { + "epoch": 0.43, + "learning_rate": 1.3906581262378552e-05, + "loss": 1.5214, + "step": 4148 + }, + { + "epoch": 0.44, + "learning_rate": 1.3903211609378971e-05, + "loss": 1.3618, + "step": 4149 + }, + { + "epoch": 0.44, + "learning_rate": 1.3899841433449327e-05, + "loss": 1.338, + "step": 4150 + }, + { + "epoch": 0.44, + "learning_rate": 1.3896470735041132e-05, + "loss": 1.3901, + "step": 4151 + }, + { + "epoch": 0.44, + "learning_rate": 1.3893099514605971e-05, + "loss": 1.4502, + "step": 4152 + }, + { + "epoch": 0.44, + "learning_rate": 1.388972777259551e-05, + "loss": 1.4141, + "step": 4153 + }, + { + "epoch": 0.44, + "learning_rate": 1.3886355509461471e-05, + "loss": 1.3876, + "step": 4154 + }, + { + "epoch": 0.44, + "learning_rate": 1.388298272565565e-05, + "loss": 1.4275, + "step": 4155 + }, + { + "epoch": 0.44, + "learning_rate": 1.3879609421629909e-05, + "loss": 1.3559, + "step": 4156 + }, + { + "epoch": 0.44, + "learning_rate": 1.3876235597836195e-05, + "loss": 1.416, + "step": 4157 + }, + { + "epoch": 0.44, + "learning_rate": 1.3872861254726506e-05, + "loss": 1.437, + "step": 4158 + }, + { + "epoch": 0.44, + "learning_rate": 1.3869486392752918e-05, + "loss": 1.3794, + "step": 4159 + }, + { + "epoch": 0.44, + "learning_rate": 1.3866111012367577e-05, + "loss": 1.4094, + "step": 4160 + }, + { + "epoch": 0.44, + "learning_rate": 1.3862735114022694e-05, + "loss": 1.3957, + "step": 4161 + }, + { + "epoch": 0.44, + "learning_rate": 1.3859358698170559e-05, + "loss": 1.3582, + "step": 4162 + }, + { + "epoch": 0.44, + "learning_rate": 1.3855981765263523e-05, + "loss": 1.4159, + "step": 4163 + }, + { + "epoch": 0.44, + "learning_rate": 1.3852604315754e-05, + "loss": 1.3498, + "step": 4164 + }, + { + "epoch": 0.44, + "learning_rate": 1.3849226350094491e-05, + "loss": 1.3951, + "step": 4165 + }, + { + "epoch": 0.44, + "learning_rate": 1.3845847868737559e-05, + "loss": 1.4087, + "step": 4166 + }, + { + "epoch": 0.44, + "learning_rate": 1.3842468872135821e-05, + "loss": 1.4318, + "step": 4167 + }, + { + "epoch": 0.44, + "learning_rate": 1.3839089360741989e-05, + "loss": 1.4174, + "step": 4168 + }, + { + "epoch": 0.44, + "learning_rate": 1.3835709335008822e-05, + "loss": 1.4499, + "step": 4169 + }, + { + "epoch": 0.44, + "learning_rate": 1.383232879538916e-05, + "loss": 1.3554, + "step": 4170 + }, + { + "epoch": 0.44, + "learning_rate": 1.3828947742335905e-05, + "loss": 1.3873, + "step": 4171 + }, + { + "epoch": 0.44, + "learning_rate": 1.382556617630204e-05, + "loss": 1.3804, + "step": 4172 + }, + { + "epoch": 0.44, + "learning_rate": 1.3822184097740598e-05, + "loss": 1.3856, + "step": 4173 + }, + { + "epoch": 0.44, + "learning_rate": 1.3818801507104697e-05, + "loss": 1.3901, + "step": 4174 + }, + { + "epoch": 0.44, + "learning_rate": 1.381541840484751e-05, + "loss": 1.3714, + "step": 4175 + }, + { + "epoch": 0.44, + "learning_rate": 1.3812034791422297e-05, + "loss": 1.4945, + "step": 4176 + }, + { + "epoch": 0.44, + "learning_rate": 1.3808650667282368e-05, + "loss": 1.429, + "step": 4177 + }, + { + "epoch": 0.44, + "learning_rate": 1.3805266032881108e-05, + "loss": 1.3903, + "step": 4178 + }, + { + "epoch": 0.44, + "learning_rate": 1.3801880888671972e-05, + "loss": 1.4799, + "step": 4179 + }, + { + "epoch": 0.44, + "eval_loss": 1.4521424770355225, + "eval_runtime": 77.3596, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 4179 + }, + { + "epoch": 0.44, + "learning_rate": 1.3798495235108484e-05, + "loss": 1.3912, + "step": 4180 + }, + { + "epoch": 0.44, + "learning_rate": 1.3795109072644235e-05, + "loss": 1.5837, + "step": 4181 + }, + { + "epoch": 0.44, + "learning_rate": 1.379172240173288e-05, + "loss": 1.4255, + "step": 4182 + }, + { + "epoch": 0.44, + "learning_rate": 1.3788335222828148e-05, + "loss": 1.4666, + "step": 4183 + }, + { + "epoch": 0.44, + "learning_rate": 1.3784947536383837e-05, + "loss": 1.3964, + "step": 4184 + }, + { + "epoch": 0.44, + "learning_rate": 1.3781559342853807e-05, + "loss": 1.336, + "step": 4185 + }, + { + "epoch": 0.44, + "learning_rate": 1.3778170642691986e-05, + "loss": 1.4352, + "step": 4186 + }, + { + "epoch": 0.44, + "learning_rate": 1.377478143635238e-05, + "loss": 1.3262, + "step": 4187 + }, + { + "epoch": 0.44, + "learning_rate": 1.3771391724289047e-05, + "loss": 1.3969, + "step": 4188 + }, + { + "epoch": 0.44, + "learning_rate": 1.376800150695613e-05, + "loss": 1.4211, + "step": 4189 + }, + { + "epoch": 0.44, + "learning_rate": 1.3764610784807824e-05, + "loss": 1.4338, + "step": 4190 + }, + { + "epoch": 0.44, + "learning_rate": 1.3761219558298403e-05, + "loss": 1.3815, + "step": 4191 + }, + { + "epoch": 0.44, + "learning_rate": 1.3757827827882203e-05, + "loss": 1.3805, + "step": 4192 + }, + { + "epoch": 0.44, + "learning_rate": 1.3754435594013627e-05, + "loss": 1.4071, + "step": 4193 + }, + { + "epoch": 0.44, + "learning_rate": 1.3751042857147145e-05, + "loss": 1.343, + "step": 4194 + }, + { + "epoch": 0.44, + "learning_rate": 1.3747649617737304e-05, + "loss": 1.4129, + "step": 4195 + }, + { + "epoch": 0.44, + "learning_rate": 1.3744255876238708e-05, + "loss": 1.3939, + "step": 4196 + }, + { + "epoch": 0.44, + "learning_rate": 1.3740861633106029e-05, + "loss": 1.3963, + "step": 4197 + }, + { + "epoch": 0.44, + "learning_rate": 1.3737466888794008e-05, + "loss": 1.5181, + "step": 4198 + }, + { + "epoch": 0.44, + "learning_rate": 1.3734071643757456e-05, + "loss": 1.4397, + "step": 4199 + }, + { + "epoch": 0.44, + "learning_rate": 1.373067589845125e-05, + "loss": 1.6293, + "step": 4200 + }, + { + "epoch": 0.44, + "learning_rate": 1.3727279653330328e-05, + "loss": 1.3498, + "step": 4201 + }, + { + "epoch": 0.44, + "learning_rate": 1.37238829088497e-05, + "loss": 1.4509, + "step": 4202 + }, + { + "epoch": 0.44, + "learning_rate": 1.3720485665464446e-05, + "loss": 1.4477, + "step": 4203 + }, + { + "epoch": 0.44, + "learning_rate": 1.3717087923629709e-05, + "loss": 1.4399, + "step": 4204 + }, + { + "epoch": 0.44, + "learning_rate": 1.3713689683800695e-05, + "loss": 1.4417, + "step": 4205 + }, + { + "epoch": 0.44, + "learning_rate": 1.3710290946432685e-05, + "loss": 1.3957, + "step": 4206 + }, + { + "epoch": 0.44, + "learning_rate": 1.3706891711981021e-05, + "loss": 1.4476, + "step": 4207 + }, + { + "epoch": 0.44, + "learning_rate": 1.3703491980901113e-05, + "loss": 1.3894, + "step": 4208 + }, + { + "epoch": 0.44, + "learning_rate": 1.3700091753648437e-05, + "loss": 1.4745, + "step": 4209 + }, + { + "epoch": 0.44, + "learning_rate": 1.369669103067854e-05, + "loss": 1.4038, + "step": 4210 + }, + { + "epoch": 0.44, + "learning_rate": 1.3693289812447023e-05, + "loss": 1.4151, + "step": 4211 + }, + { + "epoch": 0.44, + "learning_rate": 1.3689888099409572e-05, + "loss": 1.4214, + "step": 4212 + }, + { + "epoch": 0.44, + "learning_rate": 1.368648589202192e-05, + "loss": 1.4287, + "step": 4213 + }, + { + "epoch": 0.44, + "learning_rate": 1.3683083190739883e-05, + "loss": 1.345, + "step": 4214 + }, + { + "epoch": 0.44, + "learning_rate": 1.367967999601933e-05, + "loss": 1.3022, + "step": 4215 + }, + { + "epoch": 0.44, + "learning_rate": 1.3676276308316207e-05, + "loss": 1.3971, + "step": 4216 + }, + { + "epoch": 0.44, + "learning_rate": 1.3672872128086514e-05, + "loss": 1.3335, + "step": 4217 + }, + { + "epoch": 0.44, + "learning_rate": 1.366946745578633e-05, + "loss": 1.3988, + "step": 4218 + }, + { + "epoch": 0.44, + "learning_rate": 1.366606229187179e-05, + "loss": 1.4508, + "step": 4219 + }, + { + "epoch": 0.44, + "learning_rate": 1.3662656636799099e-05, + "loss": 1.3814, + "step": 4220 + }, + { + "epoch": 0.44, + "learning_rate": 1.3659250491024527e-05, + "loss": 1.4128, + "step": 4221 + }, + { + "epoch": 0.44, + "learning_rate": 1.3655843855004411e-05, + "loss": 1.3893, + "step": 4222 + }, + { + "epoch": 0.44, + "learning_rate": 1.3652436729195154e-05, + "loss": 1.2551, + "step": 4223 + }, + { + "epoch": 0.44, + "learning_rate": 1.3649029114053219e-05, + "loss": 1.4386, + "step": 4224 + }, + { + "epoch": 0.44, + "learning_rate": 1.364562101003514e-05, + "loss": 1.4028, + "step": 4225 + }, + { + "epoch": 0.44, + "learning_rate": 1.364221241759752e-05, + "loss": 1.4351, + "step": 4226 + }, + { + "epoch": 0.44, + "learning_rate": 1.363880333719702e-05, + "loss": 1.3941, + "step": 4227 + }, + { + "epoch": 0.44, + "learning_rate": 1.3635393769290368e-05, + "loss": 1.3879, + "step": 4228 + }, + { + "epoch": 0.44, + "learning_rate": 1.3631983714334358e-05, + "loss": 1.3773, + "step": 4229 + }, + { + "epoch": 0.44, + "learning_rate": 1.3628573172785853e-05, + "loss": 1.3679, + "step": 4230 + }, + { + "epoch": 0.44, + "learning_rate": 1.3625162145101776e-05, + "loss": 1.3705, + "step": 4231 + }, + { + "epoch": 0.44, + "learning_rate": 1.3621750631739114e-05, + "loss": 1.8157, + "step": 4232 + }, + { + "epoch": 0.44, + "learning_rate": 1.3618338633154928e-05, + "loss": 1.4056, + "step": 4233 + }, + { + "epoch": 0.44, + "learning_rate": 1.3614926149806334e-05, + "loss": 1.3716, + "step": 4234 + }, + { + "epoch": 0.44, + "learning_rate": 1.3611513182150523e-05, + "loss": 1.3766, + "step": 4235 + }, + { + "epoch": 0.44, + "learning_rate": 1.3608099730644733e-05, + "loss": 1.41, + "step": 4236 + }, + { + "epoch": 0.44, + "learning_rate": 1.3604685795746291e-05, + "loss": 1.421, + "step": 4237 + }, + { + "epoch": 0.44, + "learning_rate": 1.360127137791257e-05, + "loss": 1.3679, + "step": 4238 + }, + { + "epoch": 0.44, + "learning_rate": 1.3597856477601018e-05, + "loss": 1.4615, + "step": 4239 + }, + { + "epoch": 0.44, + "learning_rate": 1.359444109526914e-05, + "loss": 1.3418, + "step": 4240 + }, + { + "epoch": 0.44, + "learning_rate": 1.3591025231374513e-05, + "loss": 1.3631, + "step": 4241 + }, + { + "epoch": 0.44, + "learning_rate": 1.3587608886374772e-05, + "loss": 1.3802, + "step": 4242 + }, + { + "epoch": 0.44, + "learning_rate": 1.3584192060727622e-05, + "loss": 1.4156, + "step": 4243 + }, + { + "epoch": 0.45, + "learning_rate": 1.3580774754890827e-05, + "loss": 1.4161, + "step": 4244 + }, + { + "epoch": 0.45, + "learning_rate": 1.3577356969322222e-05, + "loss": 1.3535, + "step": 4245 + }, + { + "epoch": 0.45, + "learning_rate": 1.3573938704479699e-05, + "loss": 1.3859, + "step": 4246 + }, + { + "epoch": 0.45, + "learning_rate": 1.357051996082122e-05, + "loss": 1.3595, + "step": 4247 + }, + { + "epoch": 0.45, + "learning_rate": 1.3567100738804806e-05, + "loss": 1.4191, + "step": 4248 + }, + { + "epoch": 0.45, + "learning_rate": 1.3563681038888548e-05, + "loss": 1.4186, + "step": 4249 + }, + { + "epoch": 0.45, + "learning_rate": 1.3560260861530596e-05, + "loss": 1.43, + "step": 4250 + }, + { + "epoch": 0.45, + "learning_rate": 1.3556840207189168e-05, + "loss": 1.4139, + "step": 4251 + }, + { + "epoch": 0.45, + "learning_rate": 1.3553419076322539e-05, + "loss": 1.4005, + "step": 4252 + }, + { + "epoch": 0.45, + "learning_rate": 1.3549997469389058e-05, + "loss": 1.3468, + "step": 4253 + }, + { + "epoch": 0.45, + "learning_rate": 1.3546575386847132e-05, + "loss": 1.3756, + "step": 4254 + }, + { + "epoch": 0.45, + "learning_rate": 1.3543152829155226e-05, + "loss": 1.4063, + "step": 4255 + }, + { + "epoch": 0.45, + "learning_rate": 1.3539729796771884e-05, + "loss": 1.4666, + "step": 4256 + }, + { + "epoch": 0.45, + "learning_rate": 1.3536306290155694e-05, + "loss": 1.4212, + "step": 4257 + }, + { + "epoch": 0.45, + "learning_rate": 1.3532882309765332e-05, + "loss": 1.4883, + "step": 4258 + }, + { + "epoch": 0.45, + "learning_rate": 1.3529457856059507e-05, + "loss": 1.6641, + "step": 4259 + }, + { + "epoch": 0.45, + "learning_rate": 1.3526032929497022e-05, + "loss": 1.3659, + "step": 4260 + }, + { + "epoch": 0.45, + "learning_rate": 1.3522607530536717e-05, + "loss": 1.5945, + "step": 4261 + }, + { + "epoch": 0.45, + "learning_rate": 1.351918165963752e-05, + "loss": 1.3643, + "step": 4262 + }, + { + "epoch": 0.45, + "learning_rate": 1.3515755317258397e-05, + "loss": 1.3442, + "step": 4263 + }, + { + "epoch": 0.45, + "learning_rate": 1.3512328503858398e-05, + "loss": 1.3982, + "step": 4264 + }, + { + "epoch": 0.45, + "learning_rate": 1.3508901219896624e-05, + "loss": 1.4985, + "step": 4265 + }, + { + "epoch": 0.45, + "learning_rate": 1.350547346583225e-05, + "loss": 1.3319, + "step": 4266 + }, + { + "epoch": 0.45, + "learning_rate": 1.3502045242124497e-05, + "loss": 1.3961, + "step": 4267 + }, + { + "epoch": 0.45, + "learning_rate": 1.3498616549232665e-05, + "loss": 1.4565, + "step": 4268 + }, + { + "epoch": 0.45, + "learning_rate": 1.349518738761611e-05, + "loss": 1.375, + "step": 4269 + }, + { + "epoch": 0.45, + "learning_rate": 1.3491757757734254e-05, + "loss": 1.3005, + "step": 4270 + }, + { + "epoch": 0.45, + "learning_rate": 1.348832766004657e-05, + "loss": 1.3185, + "step": 4271 + }, + { + "epoch": 0.45, + "learning_rate": 1.3484897095012613e-05, + "loss": 1.4449, + "step": 4272 + }, + { + "epoch": 0.45, + "learning_rate": 1.3481466063091988e-05, + "loss": 1.3587, + "step": 4273 + }, + { + "epoch": 0.45, + "learning_rate": 1.3478034564744362e-05, + "loss": 1.3844, + "step": 4274 + }, + { + "epoch": 0.45, + "learning_rate": 1.3474602600429468e-05, + "loss": 1.4471, + "step": 4275 + }, + { + "epoch": 0.45, + "learning_rate": 1.3471170170607105e-05, + "loss": 1.4686, + "step": 4276 + }, + { + "epoch": 0.45, + "learning_rate": 1.3467737275737127e-05, + "loss": 1.312, + "step": 4277 + }, + { + "epoch": 0.45, + "learning_rate": 1.3464303916279453e-05, + "loss": 1.407, + "step": 4278 + }, + { + "epoch": 0.45, + "learning_rate": 1.346087009269407e-05, + "loss": 1.364, + "step": 4279 + }, + { + "epoch": 0.45, + "learning_rate": 1.3457435805441016e-05, + "loss": 1.4103, + "step": 4280 + }, + { + "epoch": 0.45, + "learning_rate": 1.3454001054980403e-05, + "loss": 1.4243, + "step": 4281 + }, + { + "epoch": 0.45, + "learning_rate": 1.3450565841772392e-05, + "loss": 1.3879, + "step": 4282 + }, + { + "epoch": 0.45, + "learning_rate": 1.344713016627722e-05, + "loss": 1.4688, + "step": 4283 + }, + { + "epoch": 0.45, + "learning_rate": 1.3443694028955176e-05, + "loss": 1.3983, + "step": 4284 + }, + { + "epoch": 0.45, + "learning_rate": 1.344025743026662e-05, + "loss": 1.4316, + "step": 4285 + }, + { + "epoch": 0.45, + "learning_rate": 1.3436820370671956e-05, + "loss": 1.3643, + "step": 4286 + }, + { + "epoch": 0.45, + "learning_rate": 1.3433382850631673e-05, + "loss": 1.4566, + "step": 4287 + }, + { + "epoch": 0.45, + "learning_rate": 1.3429944870606301e-05, + "loss": 1.1263, + "step": 4288 + }, + { + "epoch": 0.45, + "learning_rate": 1.3426506431056452e-05, + "loss": 1.2463, + "step": 4289 + }, + { + "epoch": 0.45, + "learning_rate": 1.342306753244278e-05, + "loss": 1.4753, + "step": 4290 + }, + { + "epoch": 0.45, + "learning_rate": 1.3419628175226012e-05, + "loss": 1.3789, + "step": 4291 + }, + { + "epoch": 0.45, + "learning_rate": 1.3416188359866932e-05, + "loss": 1.3906, + "step": 4292 + }, + { + "epoch": 0.45, + "learning_rate": 1.3412748086826389e-05, + "loss": 1.3995, + "step": 4293 + }, + { + "epoch": 0.45, + "learning_rate": 1.3409307356565288e-05, + "loss": 1.4906, + "step": 4294 + }, + { + "epoch": 0.45, + "learning_rate": 1.3405866169544602e-05, + "loss": 1.3951, + "step": 4295 + }, + { + "epoch": 0.45, + "learning_rate": 1.3402424526225359e-05, + "loss": 1.3753, + "step": 4296 + }, + { + "epoch": 0.45, + "learning_rate": 1.3398982427068654e-05, + "loss": 1.3686, + "step": 4297 + }, + { + "epoch": 0.45, + "learning_rate": 1.3395539872535636e-05, + "loss": 1.3612, + "step": 4298 + }, + { + "epoch": 0.45, + "learning_rate": 1.3392096863087522e-05, + "loss": 1.4043, + "step": 4299 + }, + { + "epoch": 0.45, + "learning_rate": 1.3388653399185585e-05, + "loss": 1.4068, + "step": 4300 + }, + { + "epoch": 0.45, + "learning_rate": 1.338520948129116e-05, + "loss": 1.4066, + "step": 4301 + }, + { + "epoch": 0.45, + "learning_rate": 1.3381765109865646e-05, + "loss": 1.4944, + "step": 4302 + }, + { + "epoch": 0.45, + "learning_rate": 1.3378320285370496e-05, + "loss": 1.3575, + "step": 4303 + }, + { + "epoch": 0.45, + "learning_rate": 1.3374875008267236e-05, + "loss": 1.3807, + "step": 4304 + }, + { + "epoch": 0.45, + "learning_rate": 1.3371429279017437e-05, + "loss": 1.4389, + "step": 4305 + }, + { + "epoch": 0.45, + "learning_rate": 1.3367983098082739e-05, + "loss": 1.4858, + "step": 4306 + }, + { + "epoch": 0.45, + "learning_rate": 1.3364536465924844e-05, + "loss": 1.3282, + "step": 4307 + }, + { + "epoch": 0.45, + "learning_rate": 1.3361089383005515e-05, + "loss": 1.4306, + "step": 4308 + }, + { + "epoch": 0.45, + "learning_rate": 1.3357641849786566e-05, + "loss": 1.3892, + "step": 4309 + }, + { + "epoch": 0.45, + "learning_rate": 1.3354193866729883e-05, + "loss": 1.3621, + "step": 4310 + }, + { + "epoch": 0.45, + "learning_rate": 1.3350745434297401e-05, + "loss": 1.3476, + "step": 4311 + }, + { + "epoch": 0.45, + "learning_rate": 1.334729655295113e-05, + "loss": 1.4477, + "step": 4312 + }, + { + "epoch": 0.45, + "learning_rate": 1.3343847223153123e-05, + "loss": 1.3585, + "step": 4313 + }, + { + "epoch": 0.45, + "learning_rate": 1.334039744536551e-05, + "loss": 1.3616, + "step": 4314 + }, + { + "epoch": 0.45, + "learning_rate": 1.3336947220050462e-05, + "loss": 1.3579, + "step": 4315 + }, + { + "epoch": 0.45, + "learning_rate": 1.3333496547670232e-05, + "loss": 1.3557, + "step": 4316 + }, + { + "epoch": 0.45, + "learning_rate": 1.3330045428687113e-05, + "loss": 1.4443, + "step": 4317 + }, + { + "epoch": 0.45, + "learning_rate": 1.332659386356347e-05, + "loss": 1.3621, + "step": 4318 + }, + { + "epoch": 0.45, + "learning_rate": 1.3323141852761726e-05, + "loss": 1.3295, + "step": 4319 + }, + { + "epoch": 0.45, + "learning_rate": 1.3319689396744358e-05, + "loss": 1.4187, + "step": 4320 + }, + { + "epoch": 0.45, + "learning_rate": 1.3316236495973905e-05, + "loss": 1.335, + "step": 4321 + }, + { + "epoch": 0.45, + "learning_rate": 1.331278315091297e-05, + "loss": 1.4382, + "step": 4322 + }, + { + "epoch": 0.45, + "learning_rate": 1.3309329362024212e-05, + "loss": 1.4244, + "step": 4323 + }, + { + "epoch": 0.45, + "learning_rate": 1.3305875129770351e-05, + "loss": 1.488, + "step": 4324 + }, + { + "epoch": 0.45, + "learning_rate": 1.3302420454614165e-05, + "loss": 1.3369, + "step": 4325 + }, + { + "epoch": 0.45, + "learning_rate": 1.3298965337018487e-05, + "loss": 1.3648, + "step": 4326 + }, + { + "epoch": 0.45, + "learning_rate": 1.3295509777446226e-05, + "loss": 1.3924, + "step": 4327 + }, + { + "epoch": 0.45, + "learning_rate": 1.3292053776360324e-05, + "loss": 1.3789, + "step": 4328 + }, + { + "epoch": 0.45, + "learning_rate": 1.3288597334223802e-05, + "loss": 1.3902, + "step": 4329 + }, + { + "epoch": 0.45, + "learning_rate": 1.3285140451499735e-05, + "loss": 1.4057, + "step": 4330 + }, + { + "epoch": 0.45, + "learning_rate": 1.328168312865126e-05, + "loss": 1.4536, + "step": 4331 + }, + { + "epoch": 0.45, + "learning_rate": 1.3278225366141565e-05, + "loss": 1.3075, + "step": 4332 + }, + { + "epoch": 0.45, + "learning_rate": 1.3274767164433901e-05, + "loss": 1.4579, + "step": 4333 + }, + { + "epoch": 0.45, + "learning_rate": 1.3271308523991579e-05, + "loss": 1.3906, + "step": 4334 + }, + { + "epoch": 0.45, + "learning_rate": 1.326784944527797e-05, + "loss": 1.3992, + "step": 4335 + }, + { + "epoch": 0.45, + "learning_rate": 1.3264389928756498e-05, + "loss": 1.4001, + "step": 4336 + }, + { + "epoch": 0.45, + "learning_rate": 1.3260929974890653e-05, + "loss": 1.2948, + "step": 4337 + }, + { + "epoch": 0.45, + "learning_rate": 1.3257469584143976e-05, + "loss": 1.4041, + "step": 4338 + }, + { + "epoch": 0.46, + "learning_rate": 1.3254008756980076e-05, + "loss": 1.5035, + "step": 4339 + }, + { + "epoch": 0.46, + "learning_rate": 1.3250547493862609e-05, + "loss": 1.4867, + "step": 4340 + }, + { + "epoch": 0.46, + "learning_rate": 1.3247085795255302e-05, + "loss": 1.3612, + "step": 4341 + }, + { + "epoch": 0.46, + "learning_rate": 1.3243623661621925e-05, + "loss": 1.4193, + "step": 4342 + }, + { + "epoch": 0.46, + "learning_rate": 1.3240161093426322e-05, + "loss": 1.3596, + "step": 4343 + }, + { + "epoch": 0.46, + "learning_rate": 1.3236698091132383e-05, + "loss": 1.4448, + "step": 4344 + }, + { + "epoch": 0.46, + "learning_rate": 1.3233234655204066e-05, + "loss": 1.3924, + "step": 4345 + }, + { + "epoch": 0.46, + "learning_rate": 1.322977078610538e-05, + "loss": 1.3552, + "step": 4346 + }, + { + "epoch": 0.46, + "learning_rate": 1.3226306484300395e-05, + "loss": 1.3949, + "step": 4347 + }, + { + "epoch": 0.46, + "learning_rate": 1.322284175025324e-05, + "loss": 1.399, + "step": 4348 + }, + { + "epoch": 0.46, + "learning_rate": 1.3219376584428094e-05, + "loss": 1.4755, + "step": 4349 + }, + { + "epoch": 0.46, + "learning_rate": 1.3215910987289212e-05, + "loss": 1.3877, + "step": 4350 + }, + { + "epoch": 0.46, + "learning_rate": 1.3212444959300882e-05, + "loss": 1.3916, + "step": 4351 + }, + { + "epoch": 0.46, + "learning_rate": 1.3208978500927472e-05, + "loss": 1.3462, + "step": 4352 + }, + { + "epoch": 0.46, + "learning_rate": 1.3205511612633392e-05, + "loss": 1.3834, + "step": 4353 + }, + { + "epoch": 0.46, + "learning_rate": 1.3202044294883123e-05, + "loss": 1.3843, + "step": 4354 + }, + { + "epoch": 0.46, + "learning_rate": 1.3198576548141189e-05, + "loss": 1.2439, + "step": 4355 + }, + { + "epoch": 0.46, + "learning_rate": 1.3195108372872181e-05, + "loss": 1.4106, + "step": 4356 + }, + { + "epoch": 0.46, + "learning_rate": 1.3191639769540746e-05, + "loss": 1.4417, + "step": 4357 + }, + { + "epoch": 0.46, + "learning_rate": 1.3188170738611596e-05, + "loss": 1.4393, + "step": 4358 + }, + { + "epoch": 0.46, + "learning_rate": 1.3184701280549476e-05, + "loss": 1.4616, + "step": 4359 + }, + { + "epoch": 0.46, + "learning_rate": 1.3181231395819218e-05, + "loss": 1.3215, + "step": 4360 + }, + { + "epoch": 0.46, + "learning_rate": 1.3177761084885689e-05, + "loss": 1.368, + "step": 4361 + }, + { + "epoch": 0.46, + "learning_rate": 1.317429034821383e-05, + "loss": 1.3247, + "step": 4362 + }, + { + "epoch": 0.46, + "learning_rate": 1.3170819186268618e-05, + "loss": 1.4512, + "step": 4363 + }, + { + "epoch": 0.46, + "learning_rate": 1.3167347599515111e-05, + "loss": 1.3129, + "step": 4364 + }, + { + "epoch": 0.46, + "learning_rate": 1.3163875588418404e-05, + "loss": 1.3934, + "step": 4365 + }, + { + "epoch": 0.46, + "learning_rate": 1.3160403153443666e-05, + "loss": 1.4518, + "step": 4366 + }, + { + "epoch": 0.46, + "learning_rate": 1.3156930295056105e-05, + "loss": 1.3959, + "step": 4367 + }, + { + "epoch": 0.46, + "learning_rate": 1.3153457013721e-05, + "loss": 1.3475, + "step": 4368 + }, + { + "epoch": 0.46, + "learning_rate": 1.3149983309903687e-05, + "loss": 1.4102, + "step": 4369 + }, + { + "epoch": 0.46, + "learning_rate": 1.3146509184069538e-05, + "loss": 1.3674, + "step": 4370 + }, + { + "epoch": 0.46, + "learning_rate": 1.314303463668401e-05, + "loss": 1.3739, + "step": 4371 + }, + { + "epoch": 0.46, + "learning_rate": 1.3139559668212596e-05, + "loss": 1.4249, + "step": 4372 + }, + { + "epoch": 0.46, + "learning_rate": 1.3136084279120857e-05, + "loss": 1.4473, + "step": 4373 + }, + { + "epoch": 0.46, + "learning_rate": 1.3132608469874404e-05, + "loss": 1.4443, + "step": 4374 + }, + { + "epoch": 0.46, + "learning_rate": 1.3129132240938905e-05, + "loss": 1.3534, + "step": 4375 + }, + { + "epoch": 0.46, + "learning_rate": 1.3125655592780083e-05, + "loss": 1.5663, + "step": 4376 + }, + { + "epoch": 0.46, + "learning_rate": 1.3122178525863727e-05, + "loss": 1.3465, + "step": 4377 + }, + { + "epoch": 0.46, + "learning_rate": 1.3118701040655669e-05, + "loss": 1.35, + "step": 4378 + }, + { + "epoch": 0.46, + "eval_loss": 1.447788953781128, + "eval_runtime": 77.4473, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4378 + }, + { + "epoch": 0.46, + "learning_rate": 1.3115223137621804e-05, + "loss": 1.343, + "step": 4379 + }, + { + "epoch": 0.46, + "learning_rate": 1.3111744817228078e-05, + "loss": 1.4227, + "step": 4380 + }, + { + "epoch": 0.46, + "learning_rate": 1.3108266079940508e-05, + "loss": 1.3982, + "step": 4381 + }, + { + "epoch": 0.46, + "learning_rate": 1.3104786926225141e-05, + "loss": 1.4211, + "step": 4382 + }, + { + "epoch": 0.46, + "learning_rate": 1.3101307356548103e-05, + "loss": 1.382, + "step": 4383 + }, + { + "epoch": 0.46, + "learning_rate": 1.3097827371375562e-05, + "loss": 1.4637, + "step": 4384 + }, + { + "epoch": 0.46, + "learning_rate": 1.3094346971173754e-05, + "loss": 1.4572, + "step": 4385 + }, + { + "epoch": 0.46, + "learning_rate": 1.3090866156408956e-05, + "loss": 1.5113, + "step": 4386 + }, + { + "epoch": 0.46, + "learning_rate": 1.3087384927547512e-05, + "loss": 1.2197, + "step": 4387 + }, + { + "epoch": 0.46, + "learning_rate": 1.3083903285055813e-05, + "loss": 1.3861, + "step": 4388 + }, + { + "epoch": 0.46, + "learning_rate": 1.3080421229400315e-05, + "loss": 1.4754, + "step": 4389 + }, + { + "epoch": 0.46, + "learning_rate": 1.307693876104752e-05, + "loss": 1.3588, + "step": 4390 + }, + { + "epoch": 0.46, + "learning_rate": 1.3073455880463987e-05, + "loss": 1.3995, + "step": 4391 + }, + { + "epoch": 0.46, + "learning_rate": 1.3069972588116341e-05, + "loss": 1.354, + "step": 4392 + }, + { + "epoch": 0.46, + "learning_rate": 1.3066488884471244e-05, + "loss": 1.3378, + "step": 4393 + }, + { + "epoch": 0.46, + "learning_rate": 1.306300476999543e-05, + "loss": 1.5951, + "step": 4394 + }, + { + "epoch": 0.46, + "learning_rate": 1.305952024515568e-05, + "loss": 1.3661, + "step": 4395 + }, + { + "epoch": 0.46, + "learning_rate": 1.3056035310418826e-05, + "loss": 1.4066, + "step": 4396 + }, + { + "epoch": 0.46, + "learning_rate": 1.3052549966251764e-05, + "loss": 1.3687, + "step": 4397 + }, + { + "epoch": 0.46, + "learning_rate": 1.3049064213121438e-05, + "loss": 1.4573, + "step": 4398 + }, + { + "epoch": 0.46, + "learning_rate": 1.3045578051494852e-05, + "loss": 1.3519, + "step": 4399 + }, + { + "epoch": 0.46, + "learning_rate": 1.3042091481839063e-05, + "loss": 1.2803, + "step": 4400 + }, + { + "epoch": 0.46, + "learning_rate": 1.3038604504621173e-05, + "loss": 1.4014, + "step": 4401 + }, + { + "epoch": 0.46, + "learning_rate": 1.3035117120308358e-05, + "loss": 1.4534, + "step": 4402 + }, + { + "epoch": 0.46, + "learning_rate": 1.3031629329367832e-05, + "loss": 1.4747, + "step": 4403 + }, + { + "epoch": 0.46, + "learning_rate": 1.3028141132266877e-05, + "loss": 1.374, + "step": 4404 + }, + { + "epoch": 0.46, + "learning_rate": 1.3024652529472807e-05, + "loss": 1.4328, + "step": 4405 + }, + { + "epoch": 0.46, + "learning_rate": 1.302116352145302e-05, + "loss": 1.468, + "step": 4406 + }, + { + "epoch": 0.46, + "learning_rate": 1.3017674108674942e-05, + "loss": 1.2947, + "step": 4407 + }, + { + "epoch": 0.46, + "learning_rate": 1.3014184291606077e-05, + "loss": 1.3682, + "step": 4408 + }, + { + "epoch": 0.46, + "learning_rate": 1.3010694070713959e-05, + "loss": 1.3651, + "step": 4409 + }, + { + "epoch": 0.46, + "learning_rate": 1.3007203446466194e-05, + "loss": 1.418, + "step": 4410 + }, + { + "epoch": 0.46, + "learning_rate": 1.3003712419330433e-05, + "loss": 1.416, + "step": 4411 + }, + { + "epoch": 0.46, + "learning_rate": 1.300022098977439e-05, + "loss": 1.2979, + "step": 4412 + }, + { + "epoch": 0.46, + "learning_rate": 1.2996729158265819e-05, + "loss": 1.3868, + "step": 4413 + }, + { + "epoch": 0.46, + "learning_rate": 1.2993236925272542e-05, + "loss": 1.3102, + "step": 4414 + }, + { + "epoch": 0.46, + "learning_rate": 1.2989744291262422e-05, + "loss": 1.3506, + "step": 4415 + }, + { + "epoch": 0.46, + "learning_rate": 1.2986251256703388e-05, + "loss": 1.4018, + "step": 4416 + }, + { + "epoch": 0.46, + "learning_rate": 1.2982757822063417e-05, + "loss": 1.4081, + "step": 4417 + }, + { + "epoch": 0.46, + "learning_rate": 1.2979263987810533e-05, + "loss": 1.3592, + "step": 4418 + }, + { + "epoch": 0.46, + "learning_rate": 1.297576975441283e-05, + "loss": 1.4287, + "step": 4419 + }, + { + "epoch": 0.46, + "learning_rate": 1.2972275122338433e-05, + "loss": 1.4099, + "step": 4420 + }, + { + "epoch": 0.46, + "learning_rate": 1.2968780092055546e-05, + "loss": 1.4005, + "step": 4421 + }, + { + "epoch": 0.46, + "learning_rate": 1.2965284664032401e-05, + "loss": 1.365, + "step": 4422 + }, + { + "epoch": 0.46, + "learning_rate": 1.2961788838737309e-05, + "loss": 1.3588, + "step": 4423 + }, + { + "epoch": 0.46, + "learning_rate": 1.2958292616638606e-05, + "loss": 1.3702, + "step": 4424 + }, + { + "epoch": 0.46, + "learning_rate": 1.2954795998204708e-05, + "loss": 1.3487, + "step": 4425 + }, + { + "epoch": 0.46, + "learning_rate": 1.2951298983904063e-05, + "loss": 1.4395, + "step": 4426 + }, + { + "epoch": 0.46, + "learning_rate": 1.2947801574205193e-05, + "loss": 1.3523, + "step": 4427 + }, + { + "epoch": 0.46, + "learning_rate": 1.2944303769576645e-05, + "loss": 1.3125, + "step": 4428 + }, + { + "epoch": 0.46, + "learning_rate": 1.2940805570487048e-05, + "loss": 1.5476, + "step": 4429 + }, + { + "epoch": 0.46, + "learning_rate": 1.2937306977405062e-05, + "loss": 1.4076, + "step": 4430 + }, + { + "epoch": 0.46, + "learning_rate": 1.2933807990799418e-05, + "loss": 1.3007, + "step": 4431 + }, + { + "epoch": 0.46, + "learning_rate": 1.293030861113888e-05, + "loss": 1.3566, + "step": 4432 + }, + { + "epoch": 0.46, + "learning_rate": 1.2926808838892285e-05, + "loss": 1.3907, + "step": 4433 + }, + { + "epoch": 0.46, + "learning_rate": 1.2923308674528501e-05, + "loss": 1.379, + "step": 4434 + }, + { + "epoch": 0.47, + "learning_rate": 1.2919808118516475e-05, + "loss": 1.4319, + "step": 4435 + }, + { + "epoch": 0.47, + "learning_rate": 1.2916307171325176e-05, + "loss": 1.3392, + "step": 4436 + }, + { + "epoch": 0.47, + "learning_rate": 1.291280583342365e-05, + "loss": 1.401, + "step": 4437 + }, + { + "epoch": 0.47, + "learning_rate": 1.2909304105280984e-05, + "loss": 1.3939, + "step": 4438 + }, + { + "epoch": 0.47, + "learning_rate": 1.2905801987366322e-05, + "loss": 1.4676, + "step": 4439 + }, + { + "epoch": 0.47, + "learning_rate": 1.2902299480148855e-05, + "loss": 1.3957, + "step": 4440 + }, + { + "epoch": 0.47, + "learning_rate": 1.2898796584097828e-05, + "loss": 1.3587, + "step": 4441 + }, + { + "epoch": 0.47, + "learning_rate": 1.2895293299682545e-05, + "loss": 1.5809, + "step": 4442 + }, + { + "epoch": 0.47, + "learning_rate": 1.289178962737235e-05, + "loss": 1.3436, + "step": 4443 + }, + { + "epoch": 0.47, + "learning_rate": 1.2888285567636647e-05, + "loss": 1.4535, + "step": 4444 + }, + { + "epoch": 0.47, + "learning_rate": 1.2884781120944889e-05, + "loss": 1.3377, + "step": 4445 + }, + { + "epoch": 0.47, + "learning_rate": 1.2881276287766587e-05, + "loss": 0.8221, + "step": 4446 + }, + { + "epoch": 0.47, + "learning_rate": 1.2877771068571288e-05, + "loss": 0.7259, + "step": 4447 + }, + { + "epoch": 0.47, + "learning_rate": 1.2874265463828612e-05, + "loss": 0.8279, + "step": 4448 + }, + { + "epoch": 0.47, + "learning_rate": 1.2870759474008213e-05, + "loss": 1.3523, + "step": 4449 + }, + { + "epoch": 0.47, + "learning_rate": 1.2867253099579808e-05, + "loss": 1.3658, + "step": 4450 + }, + { + "epoch": 0.47, + "learning_rate": 1.2863746341013158e-05, + "loss": 1.4112, + "step": 4451 + }, + { + "epoch": 0.47, + "learning_rate": 1.2860239198778085e-05, + "loss": 1.389, + "step": 4452 + }, + { + "epoch": 0.47, + "learning_rate": 1.2856731673344442e-05, + "loss": 1.4066, + "step": 4453 + }, + { + "epoch": 0.47, + "learning_rate": 1.2853223765182165e-05, + "loss": 1.3267, + "step": 4454 + }, + { + "epoch": 0.47, + "learning_rate": 1.2849715474761209e-05, + "loss": 1.3381, + "step": 4455 + }, + { + "epoch": 0.47, + "learning_rate": 1.2846206802551602e-05, + "loss": 1.2882, + "step": 4456 + }, + { + "epoch": 0.47, + "learning_rate": 1.2842697749023414e-05, + "loss": 1.3199, + "step": 4457 + }, + { + "epoch": 0.47, + "learning_rate": 1.2839188314646771e-05, + "loss": 1.3896, + "step": 4458 + }, + { + "epoch": 0.47, + "learning_rate": 1.2835678499891842e-05, + "loss": 1.3186, + "step": 4459 + }, + { + "epoch": 0.47, + "learning_rate": 1.283216830522885e-05, + "loss": 1.3466, + "step": 4460 + }, + { + "epoch": 0.47, + "learning_rate": 1.2828657731128083e-05, + "loss": 1.4678, + "step": 4461 + }, + { + "epoch": 0.47, + "learning_rate": 1.2825146778059857e-05, + "loss": 1.4408, + "step": 4462 + }, + { + "epoch": 0.47, + "learning_rate": 1.2821635446494553e-05, + "loss": 1.3672, + "step": 4463 + }, + { + "epoch": 0.47, + "learning_rate": 1.2818123736902597e-05, + "loss": 1.3836, + "step": 4464 + }, + { + "epoch": 0.47, + "learning_rate": 1.2814611649754472e-05, + "loss": 1.3493, + "step": 4465 + }, + { + "epoch": 0.47, + "learning_rate": 1.2811099185520704e-05, + "loss": 1.3584, + "step": 4466 + }, + { + "epoch": 0.47, + "learning_rate": 1.2807586344671875e-05, + "loss": 1.3551, + "step": 4467 + }, + { + "epoch": 0.47, + "learning_rate": 1.2804073127678612e-05, + "loss": 1.3254, + "step": 4468 + }, + { + "epoch": 0.47, + "learning_rate": 1.28005595350116e-05, + "loss": 1.3405, + "step": 4469 + }, + { + "epoch": 0.47, + "learning_rate": 1.2797045567141568e-05, + "loss": 1.3432, + "step": 4470 + }, + { + "epoch": 0.47, + "learning_rate": 1.2793531224539297e-05, + "loss": 1.4347, + "step": 4471 + }, + { + "epoch": 0.47, + "learning_rate": 1.279001650767562e-05, + "loss": 1.3304, + "step": 4472 + }, + { + "epoch": 0.47, + "learning_rate": 1.278650141702142e-05, + "loss": 1.3244, + "step": 4473 + }, + { + "epoch": 0.47, + "learning_rate": 1.2782985953047625e-05, + "loss": 1.3756, + "step": 4474 + }, + { + "epoch": 0.47, + "learning_rate": 1.2779470116225219e-05, + "loss": 1.5468, + "step": 4475 + }, + { + "epoch": 0.47, + "learning_rate": 1.2775953907025232e-05, + "loss": 1.4316, + "step": 4476 + }, + { + "epoch": 0.47, + "learning_rate": 1.2772437325918752e-05, + "loss": 1.3724, + "step": 4477 + }, + { + "epoch": 0.47, + "learning_rate": 1.27689203733769e-05, + "loss": 1.4458, + "step": 4478 + }, + { + "epoch": 0.47, + "learning_rate": 1.2765403049870865e-05, + "loss": 1.3622, + "step": 4479 + }, + { + "epoch": 0.47, + "learning_rate": 1.2761885355871875e-05, + "loss": 1.3875, + "step": 4480 + }, + { + "epoch": 0.47, + "learning_rate": 1.2758367291851217e-05, + "loss": 1.3577, + "step": 4481 + }, + { + "epoch": 0.47, + "learning_rate": 1.2754848858280211e-05, + "loss": 1.4256, + "step": 4482 + }, + { + "epoch": 0.47, + "learning_rate": 1.2751330055630242e-05, + "loss": 1.3771, + "step": 4483 + }, + { + "epoch": 0.47, + "learning_rate": 1.274781088437274e-05, + "loss": 1.357, + "step": 4484 + }, + { + "epoch": 0.47, + "learning_rate": 1.274429134497918e-05, + "loss": 1.3634, + "step": 4485 + }, + { + "epoch": 0.47, + "learning_rate": 1.2740771437921096e-05, + "loss": 1.3661, + "step": 4486 + }, + { + "epoch": 0.47, + "learning_rate": 1.2737251163670057e-05, + "loss": 1.3819, + "step": 4487 + }, + { + "epoch": 0.47, + "learning_rate": 1.2733730522697696e-05, + "loss": 1.4491, + "step": 4488 + }, + { + "epoch": 0.47, + "learning_rate": 1.2730209515475687e-05, + "loss": 1.3857, + "step": 4489 + }, + { + "epoch": 0.47, + "learning_rate": 1.2726688142475751e-05, + "loss": 1.3837, + "step": 4490 + }, + { + "epoch": 0.47, + "learning_rate": 1.2723166404169663e-05, + "loss": 1.3755, + "step": 4491 + }, + { + "epoch": 0.47, + "learning_rate": 1.271964430102925e-05, + "loss": 1.3767, + "step": 4492 + }, + { + "epoch": 0.47, + "learning_rate": 1.2716121833526376e-05, + "loss": 1.4416, + "step": 4493 + }, + { + "epoch": 0.47, + "learning_rate": 1.2712599002132966e-05, + "loss": 1.5573, + "step": 4494 + }, + { + "epoch": 0.47, + "learning_rate": 1.2709075807320988e-05, + "loss": 1.365, + "step": 4495 + }, + { + "epoch": 0.47, + "learning_rate": 1.270555224956246e-05, + "loss": 1.3862, + "step": 4496 + }, + { + "epoch": 0.47, + "learning_rate": 1.2702028329329445e-05, + "loss": 1.3003, + "step": 4497 + }, + { + "epoch": 0.47, + "learning_rate": 1.2698504047094064e-05, + "loss": 1.3806, + "step": 4498 + }, + { + "epoch": 0.47, + "learning_rate": 1.269497940332847e-05, + "loss": 1.5425, + "step": 4499 + }, + { + "epoch": 0.47, + "learning_rate": 1.269145439850489e-05, + "loss": 1.3541, + "step": 4500 + }, + { + "epoch": 0.47, + "learning_rate": 1.268792903309557e-05, + "loss": 1.4337, + "step": 4501 + }, + { + "epoch": 0.47, + "learning_rate": 1.2684403307572825e-05, + "loss": 1.4004, + "step": 4502 + }, + { + "epoch": 0.47, + "learning_rate": 1.268087722240901e-05, + "loss": 1.9453, + "step": 4503 + }, + { + "epoch": 0.47, + "learning_rate": 1.2677350778076532e-05, + "loss": 1.3907, + "step": 4504 + }, + { + "epoch": 0.47, + "learning_rate": 1.2673823975047839e-05, + "loss": 1.4993, + "step": 4505 + }, + { + "epoch": 0.47, + "learning_rate": 1.2670296813795432e-05, + "loss": 1.4386, + "step": 4506 + }, + { + "epoch": 0.47, + "learning_rate": 1.266676929479187e-05, + "loss": 1.4944, + "step": 4507 + }, + { + "epoch": 0.47, + "learning_rate": 1.266324141850974e-05, + "loss": 1.4311, + "step": 4508 + }, + { + "epoch": 0.47, + "learning_rate": 1.265971318542169e-05, + "loss": 1.3607, + "step": 4509 + }, + { + "epoch": 0.47, + "learning_rate": 1.2656184596000412e-05, + "loss": 1.4007, + "step": 4510 + }, + { + "epoch": 0.47, + "learning_rate": 1.2652655650718645e-05, + "loss": 1.4561, + "step": 4511 + }, + { + "epoch": 0.47, + "learning_rate": 1.2649126350049181e-05, + "loss": 1.4321, + "step": 4512 + }, + { + "epoch": 0.47, + "learning_rate": 1.2645596694464851e-05, + "loss": 1.2856, + "step": 4513 + }, + { + "epoch": 0.47, + "learning_rate": 1.2642066684438543e-05, + "loss": 1.3979, + "step": 4514 + }, + { + "epoch": 0.47, + "learning_rate": 1.2638536320443184e-05, + "loss": 1.4977, + "step": 4515 + }, + { + "epoch": 0.47, + "learning_rate": 1.2635005602951752e-05, + "loss": 1.377, + "step": 4516 + }, + { + "epoch": 0.47, + "learning_rate": 1.2631474532437275e-05, + "loss": 1.4266, + "step": 4517 + }, + { + "epoch": 0.47, + "learning_rate": 1.2627943109372822e-05, + "loss": 1.409, + "step": 4518 + }, + { + "epoch": 0.47, + "learning_rate": 1.2624411334231519e-05, + "loss": 1.3374, + "step": 4519 + }, + { + "epoch": 0.47, + "learning_rate": 1.2620879207486525e-05, + "loss": 1.3765, + "step": 4520 + }, + { + "epoch": 0.47, + "learning_rate": 1.2617346729611061e-05, + "loss": 1.3805, + "step": 4521 + }, + { + "epoch": 0.47, + "learning_rate": 1.2613813901078384e-05, + "loss": 1.3326, + "step": 4522 + }, + { + "epoch": 0.47, + "learning_rate": 1.2610280722361807e-05, + "loss": 1.3909, + "step": 4523 + }, + { + "epoch": 0.47, + "learning_rate": 1.260674719393468e-05, + "loss": 1.3815, + "step": 4524 + }, + { + "epoch": 0.47, + "learning_rate": 1.2603213316270409e-05, + "loss": 1.5589, + "step": 4525 + }, + { + "epoch": 0.47, + "learning_rate": 1.2599679089842437e-05, + "loss": 1.4416, + "step": 4526 + }, + { + "epoch": 0.47, + "learning_rate": 1.259614451512427e-05, + "loss": 1.3529, + "step": 4527 + }, + { + "epoch": 0.47, + "learning_rate": 1.2592609592589437e-05, + "loss": 1.3135, + "step": 4528 + }, + { + "epoch": 0.47, + "learning_rate": 1.2589074322711535e-05, + "loss": 1.4177, + "step": 4529 + }, + { + "epoch": 0.48, + "learning_rate": 1.25855387059642e-05, + "loss": 1.353, + "step": 4530 + }, + { + "epoch": 0.48, + "learning_rate": 1.2582002742821111e-05, + "loss": 1.431, + "step": 4531 + }, + { + "epoch": 0.48, + "learning_rate": 1.2578466433755998e-05, + "loss": 1.3803, + "step": 4532 + }, + { + "epoch": 0.48, + "learning_rate": 1.257492977924263e-05, + "loss": 1.3774, + "step": 4533 + }, + { + "epoch": 0.48, + "learning_rate": 1.2571392779754836e-05, + "loss": 1.4339, + "step": 4534 + }, + { + "epoch": 0.48, + "learning_rate": 1.256785543576648e-05, + "loss": 1.4097, + "step": 4535 + }, + { + "epoch": 0.48, + "learning_rate": 1.2564317747751473e-05, + "loss": 1.4223, + "step": 4536 + }, + { + "epoch": 0.48, + "learning_rate": 1.2560779716183775e-05, + "loss": 1.5148, + "step": 4537 + }, + { + "epoch": 0.48, + "learning_rate": 1.2557241341537394e-05, + "loss": 1.3547, + "step": 4538 + }, + { + "epoch": 0.48, + "learning_rate": 1.255370262428638e-05, + "loss": 1.393, + "step": 4539 + }, + { + "epoch": 0.48, + "learning_rate": 1.2550163564904829e-05, + "loss": 1.3312, + "step": 4540 + }, + { + "epoch": 0.48, + "learning_rate": 1.2546624163866882e-05, + "loss": 1.4193, + "step": 4541 + }, + { + "epoch": 0.48, + "learning_rate": 1.2543084421646735e-05, + "loss": 1.4161, + "step": 4542 + }, + { + "epoch": 0.48, + "learning_rate": 1.2539544338718614e-05, + "loss": 1.4224, + "step": 4543 + }, + { + "epoch": 0.48, + "learning_rate": 1.2536003915556805e-05, + "loss": 1.3484, + "step": 4544 + }, + { + "epoch": 0.48, + "learning_rate": 1.253246315263563e-05, + "loss": 1.4492, + "step": 4545 + }, + { + "epoch": 0.48, + "learning_rate": 1.2528922050429467e-05, + "loss": 1.3549, + "step": 4546 + }, + { + "epoch": 0.48, + "learning_rate": 1.252538060941272e-05, + "loss": 1.45, + "step": 4547 + }, + { + "epoch": 0.48, + "learning_rate": 1.2521838830059865e-05, + "loss": 1.3499, + "step": 4548 + }, + { + "epoch": 0.48, + "learning_rate": 1.2518296712845399e-05, + "loss": 1.3786, + "step": 4549 + }, + { + "epoch": 0.48, + "learning_rate": 1.2514754258243884e-05, + "loss": 1.3394, + "step": 4550 + }, + { + "epoch": 0.48, + "learning_rate": 1.2511211466729909e-05, + "loss": 1.2849, + "step": 4551 + }, + { + "epoch": 0.48, + "learning_rate": 1.250766833877812e-05, + "loss": 1.374, + "step": 4552 + }, + { + "epoch": 0.48, + "learning_rate": 1.2504124874863211e-05, + "loss": 1.3084, + "step": 4553 + }, + { + "epoch": 0.48, + "learning_rate": 1.2500581075459905e-05, + "loss": 1.3348, + "step": 4554 + }, + { + "epoch": 0.48, + "learning_rate": 1.249703694104299e-05, + "loss": 1.3797, + "step": 4555 + }, + { + "epoch": 0.48, + "learning_rate": 1.2493492472087279e-05, + "loss": 1.3371, + "step": 4556 + }, + { + "epoch": 0.48, + "learning_rate": 1.248994766906765e-05, + "loss": 1.3974, + "step": 4557 + }, + { + "epoch": 0.48, + "learning_rate": 1.2486402532459007e-05, + "loss": 1.388, + "step": 4558 + }, + { + "epoch": 0.48, + "learning_rate": 1.2482857062736313e-05, + "loss": 1.3619, + "step": 4559 + }, + { + "epoch": 0.48, + "learning_rate": 1.2479311260374565e-05, + "loss": 1.4123, + "step": 4560 + }, + { + "epoch": 0.48, + "learning_rate": 1.2475765125848814e-05, + "loss": 1.5485, + "step": 4561 + }, + { + "epoch": 0.48, + "learning_rate": 1.247221865963415e-05, + "loss": 1.4965, + "step": 4562 + }, + { + "epoch": 0.48, + "learning_rate": 1.2468671862205705e-05, + "loss": 1.4352, + "step": 4563 + }, + { + "epoch": 0.48, + "learning_rate": 1.246512473403866e-05, + "loss": 1.3935, + "step": 4564 + }, + { + "epoch": 0.48, + "learning_rate": 1.2461577275608243e-05, + "loss": 1.3798, + "step": 4565 + }, + { + "epoch": 0.48, + "learning_rate": 1.2458029487389718e-05, + "loss": 1.4039, + "step": 4566 + }, + { + "epoch": 0.48, + "learning_rate": 1.2454481369858397e-05, + "loss": 1.3723, + "step": 4567 + }, + { + "epoch": 0.48, + "learning_rate": 1.245093292348964e-05, + "loss": 1.3713, + "step": 4568 + }, + { + "epoch": 0.48, + "learning_rate": 1.2447384148758847e-05, + "loss": 1.4083, + "step": 4569 + }, + { + "epoch": 0.48, + "learning_rate": 1.244383504614146e-05, + "loss": 1.2811, + "step": 4570 + }, + { + "epoch": 0.48, + "learning_rate": 1.2440285616112968e-05, + "loss": 1.3509, + "step": 4571 + }, + { + "epoch": 0.48, + "learning_rate": 1.2436735859148905e-05, + "loss": 1.3481, + "step": 4572 + }, + { + "epoch": 0.48, + "learning_rate": 1.2433185775724847e-05, + "loss": 1.4168, + "step": 4573 + }, + { + "epoch": 0.48, + "learning_rate": 1.2429635366316418e-05, + "loss": 1.3671, + "step": 4574 + }, + { + "epoch": 0.48, + "learning_rate": 1.2426084631399271e-05, + "loss": 1.6514, + "step": 4575 + }, + { + "epoch": 0.48, + "learning_rate": 1.2422533571449123e-05, + "loss": 1.3564, + "step": 4576 + }, + { + "epoch": 0.48, + "learning_rate": 1.2418982186941721e-05, + "loss": 1.4586, + "step": 4577 + }, + { + "epoch": 0.48, + "eval_loss": 1.4425245523452759, + "eval_runtime": 77.3853, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 4577 + }, + { + "epoch": 0.48, + "learning_rate": 1.2415430478352858e-05, + "loss": 1.3922, + "step": 4578 + }, + { + "epoch": 0.48, + "learning_rate": 1.2411878446158374e-05, + "loss": 1.3903, + "step": 4579 + }, + { + "epoch": 0.48, + "learning_rate": 1.240832609083415e-05, + "loss": 1.3537, + "step": 4580 + }, + { + "epoch": 0.48, + "learning_rate": 1.2404773412856113e-05, + "loss": 1.356, + "step": 4581 + }, + { + "epoch": 0.48, + "learning_rate": 1.2401220412700223e-05, + "loss": 1.4483, + "step": 4582 + }, + { + "epoch": 0.48, + "learning_rate": 1.2397667090842496e-05, + "loss": 1.3926, + "step": 4583 + }, + { + "epoch": 0.48, + "learning_rate": 1.2394113447758986e-05, + "loss": 1.4816, + "step": 4584 + }, + { + "epoch": 0.48, + "learning_rate": 1.2390559483925788e-05, + "loss": 1.3742, + "step": 4585 + }, + { + "epoch": 0.48, + "learning_rate": 1.2387005199819044e-05, + "loss": 1.4476, + "step": 4586 + }, + { + "epoch": 0.48, + "learning_rate": 1.2383450595914932e-05, + "loss": 1.4029, + "step": 4587 + }, + { + "epoch": 0.48, + "learning_rate": 1.2379895672689683e-05, + "loss": 1.4797, + "step": 4588 + }, + { + "epoch": 0.48, + "learning_rate": 1.2376340430619565e-05, + "loss": 1.3366, + "step": 4589 + }, + { + "epoch": 0.48, + "learning_rate": 1.2372784870180885e-05, + "loss": 1.4226, + "step": 4590 + }, + { + "epoch": 0.48, + "learning_rate": 1.2369228991849997e-05, + "loss": 1.3668, + "step": 4591 + }, + { + "epoch": 0.48, + "learning_rate": 1.2365672796103305e-05, + "loss": 1.4932, + "step": 4592 + }, + { + "epoch": 0.48, + "learning_rate": 1.236211628341724e-05, + "loss": 1.4088, + "step": 4593 + }, + { + "epoch": 0.48, + "learning_rate": 1.2358559454268284e-05, + "loss": 1.3616, + "step": 4594 + }, + { + "epoch": 0.48, + "learning_rate": 1.2355002309132961e-05, + "loss": 1.4345, + "step": 4595 + }, + { + "epoch": 0.48, + "learning_rate": 1.2351444848487844e-05, + "loss": 1.4025, + "step": 4596 + }, + { + "epoch": 0.48, + "learning_rate": 1.2347887072809533e-05, + "loss": 1.3895, + "step": 4597 + }, + { + "epoch": 0.48, + "learning_rate": 1.2344328982574678e-05, + "loss": 1.3326, + "step": 4598 + }, + { + "epoch": 0.48, + "learning_rate": 1.234077057825998e-05, + "loss": 1.4249, + "step": 4599 + }, + { + "epoch": 0.48, + "learning_rate": 1.2337211860342167e-05, + "loss": 1.3649, + "step": 4600 + }, + { + "epoch": 0.48, + "learning_rate": 1.2333652829298016e-05, + "loss": 1.3831, + "step": 4601 + }, + { + "epoch": 0.48, + "learning_rate": 1.2330093485604346e-05, + "loss": 1.3748, + "step": 4602 + }, + { + "epoch": 0.48, + "learning_rate": 1.2326533829738022e-05, + "loss": 1.386, + "step": 4603 + }, + { + "epoch": 0.48, + "learning_rate": 1.2322973862175941e-05, + "loss": 1.3923, + "step": 4604 + }, + { + "epoch": 0.48, + "learning_rate": 1.2319413583395052e-05, + "loss": 1.3638, + "step": 4605 + }, + { + "epoch": 0.48, + "learning_rate": 1.2315852993872335e-05, + "loss": 1.3476, + "step": 4606 + }, + { + "epoch": 0.48, + "learning_rate": 1.2312292094084824e-05, + "loss": 1.3581, + "step": 4607 + }, + { + "epoch": 0.48, + "learning_rate": 1.2308730884509583e-05, + "loss": 1.3554, + "step": 4608 + }, + { + "epoch": 0.48, + "learning_rate": 1.2305169365623724e-05, + "loss": 1.3676, + "step": 4609 + }, + { + "epoch": 0.48, + "learning_rate": 1.2301607537904399e-05, + "loss": 1.24, + "step": 4610 + }, + { + "epoch": 0.48, + "learning_rate": 1.2298045401828803e-05, + "loss": 1.3295, + "step": 4611 + }, + { + "epoch": 0.48, + "learning_rate": 1.2294482957874169e-05, + "loss": 1.5684, + "step": 4612 + }, + { + "epoch": 0.48, + "learning_rate": 1.2290920206517774e-05, + "loss": 1.3403, + "step": 4613 + }, + { + "epoch": 0.48, + "learning_rate": 1.2287357148236933e-05, + "loss": 1.349, + "step": 4614 + }, + { + "epoch": 0.48, + "learning_rate": 1.2283793783509008e-05, + "loss": 1.4261, + "step": 4615 + }, + { + "epoch": 0.48, + "learning_rate": 1.2280230112811395e-05, + "loss": 1.322, + "step": 4616 + }, + { + "epoch": 0.48, + "learning_rate": 1.2276666136621538e-05, + "loss": 1.3399, + "step": 4617 + }, + { + "epoch": 0.48, + "learning_rate": 1.2273101855416912e-05, + "loss": 1.3878, + "step": 4618 + }, + { + "epoch": 0.48, + "learning_rate": 1.2269537269675044e-05, + "loss": 1.4733, + "step": 4619 + }, + { + "epoch": 0.48, + "learning_rate": 1.2265972379873497e-05, + "loss": 1.419, + "step": 4620 + }, + { + "epoch": 0.48, + "learning_rate": 1.226240718648987e-05, + "loss": 1.3918, + "step": 4621 + }, + { + "epoch": 0.48, + "learning_rate": 1.2258841690001815e-05, + "loss": 1.3398, + "step": 4622 + }, + { + "epoch": 0.48, + "learning_rate": 1.225527589088701e-05, + "loss": 1.4091, + "step": 4623 + }, + { + "epoch": 0.48, + "learning_rate": 1.2251709789623185e-05, + "loss": 1.3291, + "step": 4624 + }, + { + "epoch": 0.49, + "learning_rate": 1.2248143386688101e-05, + "loss": 1.4288, + "step": 4625 + }, + { + "epoch": 0.49, + "learning_rate": 1.224457668255957e-05, + "loss": 1.2942, + "step": 4626 + }, + { + "epoch": 0.49, + "learning_rate": 1.2241009677715437e-05, + "loss": 1.4014, + "step": 4627 + }, + { + "epoch": 0.49, + "learning_rate": 1.2237442372633586e-05, + "loss": 1.3823, + "step": 4628 + }, + { + "epoch": 0.49, + "learning_rate": 1.2233874767791945e-05, + "loss": 1.3556, + "step": 4629 + }, + { + "epoch": 0.49, + "learning_rate": 1.2230306863668485e-05, + "loss": 1.411, + "step": 4630 + }, + { + "epoch": 0.49, + "learning_rate": 1.2226738660741212e-05, + "loss": 1.4347, + "step": 4631 + }, + { + "epoch": 0.49, + "learning_rate": 1.2223170159488169e-05, + "loss": 1.3095, + "step": 4632 + }, + { + "epoch": 0.49, + "learning_rate": 1.221960136038745e-05, + "loss": 1.4272, + "step": 4633 + }, + { + "epoch": 0.49, + "learning_rate": 1.221603226391718e-05, + "loss": 1.367, + "step": 4634 + }, + { + "epoch": 0.49, + "learning_rate": 1.2212462870555523e-05, + "loss": 1.3357, + "step": 4635 + }, + { + "epoch": 0.49, + "learning_rate": 1.220889318078069e-05, + "loss": 1.3634, + "step": 4636 + }, + { + "epoch": 0.49, + "learning_rate": 1.2205323195070927e-05, + "loss": 1.4143, + "step": 4637 + }, + { + "epoch": 0.49, + "learning_rate": 1.2201752913904519e-05, + "loss": 1.4865, + "step": 4638 + }, + { + "epoch": 0.49, + "learning_rate": 1.2198182337759794e-05, + "loss": 1.451, + "step": 4639 + }, + { + "epoch": 0.49, + "learning_rate": 1.2194611467115116e-05, + "loss": 1.3953, + "step": 4640 + }, + { + "epoch": 0.49, + "learning_rate": 1.2191040302448887e-05, + "loss": 1.4099, + "step": 4641 + }, + { + "epoch": 0.49, + "learning_rate": 1.2187468844239559e-05, + "loss": 1.3338, + "step": 4642 + }, + { + "epoch": 0.49, + "learning_rate": 1.2183897092965609e-05, + "loss": 1.4392, + "step": 4643 + }, + { + "epoch": 0.49, + "learning_rate": 1.2180325049105559e-05, + "loss": 1.3196, + "step": 4644 + }, + { + "epoch": 0.49, + "learning_rate": 1.2176752713137977e-05, + "loss": 1.3727, + "step": 4645 + }, + { + "epoch": 0.49, + "learning_rate": 1.2173180085541464e-05, + "loss": 1.3118, + "step": 4646 + }, + { + "epoch": 0.49, + "learning_rate": 1.2169607166794655e-05, + "loss": 1.3695, + "step": 4647 + }, + { + "epoch": 0.49, + "learning_rate": 1.2166033957376231e-05, + "loss": 1.3568, + "step": 4648 + }, + { + "epoch": 0.49, + "learning_rate": 1.216246045776491e-05, + "loss": 1.3492, + "step": 4649 + }, + { + "epoch": 0.49, + "learning_rate": 1.2158886668439455e-05, + "loss": 1.3445, + "step": 4650 + }, + { + "epoch": 0.49, + "learning_rate": 1.2155312589878654e-05, + "loss": 1.3756, + "step": 4651 + }, + { + "epoch": 0.49, + "learning_rate": 1.2151738222561344e-05, + "loss": 1.3681, + "step": 4652 + }, + { + "epoch": 0.49, + "learning_rate": 1.2148163566966403e-05, + "loss": 1.4345, + "step": 4653 + }, + { + "epoch": 0.49, + "learning_rate": 1.2144588623572738e-05, + "loss": 1.5102, + "step": 4654 + }, + { + "epoch": 0.49, + "learning_rate": 1.2141013392859297e-05, + "loss": 1.3531, + "step": 4655 + }, + { + "epoch": 0.49, + "learning_rate": 1.2137437875305075e-05, + "loss": 1.3824, + "step": 4656 + }, + { + "epoch": 0.49, + "learning_rate": 1.2133862071389099e-05, + "loss": 1.4227, + "step": 4657 + }, + { + "epoch": 0.49, + "learning_rate": 1.2130285981590433e-05, + "loss": 1.3479, + "step": 4658 + }, + { + "epoch": 0.49, + "learning_rate": 1.2126709606388181e-05, + "loss": 1.381, + "step": 4659 + }, + { + "epoch": 0.49, + "learning_rate": 1.2123132946261485e-05, + "loss": 1.3847, + "step": 4660 + }, + { + "epoch": 0.49, + "learning_rate": 1.2119556001689527e-05, + "loss": 1.3549, + "step": 4661 + }, + { + "epoch": 0.49, + "learning_rate": 1.2115978773151527e-05, + "loss": 1.3754, + "step": 4662 + }, + { + "epoch": 0.49, + "learning_rate": 1.2112401261126736e-05, + "loss": 1.3329, + "step": 4663 + }, + { + "epoch": 0.49, + "learning_rate": 1.2108823466094453e-05, + "loss": 1.4228, + "step": 4664 + }, + { + "epoch": 0.49, + "learning_rate": 1.2105245388534013e-05, + "loss": 1.4138, + "step": 4665 + }, + { + "epoch": 0.49, + "learning_rate": 1.2101667028924782e-05, + "loss": 1.3538, + "step": 4666 + }, + { + "epoch": 0.49, + "learning_rate": 1.2098088387746168e-05, + "loss": 1.4848, + "step": 4667 + }, + { + "epoch": 0.49, + "learning_rate": 1.2094509465477619e-05, + "loss": 1.5719, + "step": 4668 + }, + { + "epoch": 0.49, + "learning_rate": 1.209093026259862e-05, + "loss": 1.3863, + "step": 4669 + }, + { + "epoch": 0.49, + "learning_rate": 1.2087350779588691e-05, + "loss": 1.4425, + "step": 4670 + }, + { + "epoch": 0.49, + "learning_rate": 1.2083771016927386e-05, + "loss": 1.3655, + "step": 4671 + }, + { + "epoch": 0.49, + "learning_rate": 1.208019097509431e-05, + "loss": 1.3629, + "step": 4672 + }, + { + "epoch": 0.49, + "learning_rate": 1.2076610654569092e-05, + "loss": 1.3849, + "step": 4673 + }, + { + "epoch": 0.49, + "learning_rate": 1.20730300558314e-05, + "loss": 1.3763, + "step": 4674 + }, + { + "epoch": 0.49, + "learning_rate": 1.2069449179360945e-05, + "loss": 1.5316, + "step": 4675 + }, + { + "epoch": 0.49, + "learning_rate": 1.2065868025637476e-05, + "loss": 1.2873, + "step": 4676 + }, + { + "epoch": 0.49, + "learning_rate": 1.2062286595140773e-05, + "loss": 1.3642, + "step": 4677 + }, + { + "epoch": 0.49, + "learning_rate": 1.2058704888350652e-05, + "loss": 1.3782, + "step": 4678 + }, + { + "epoch": 0.49, + "learning_rate": 1.2055122905746972e-05, + "loss": 1.4597, + "step": 4679 + }, + { + "epoch": 0.49, + "learning_rate": 1.205154064780963e-05, + "loss": 1.3952, + "step": 4680 + }, + { + "epoch": 0.49, + "learning_rate": 1.2047958115018554e-05, + "loss": 1.4012, + "step": 4681 + }, + { + "epoch": 0.49, + "learning_rate": 1.204437530785371e-05, + "loss": 1.3432, + "step": 4682 + }, + { + "epoch": 0.49, + "learning_rate": 1.2040792226795101e-05, + "loss": 1.4111, + "step": 4683 + }, + { + "epoch": 0.49, + "learning_rate": 1.2037208872322773e-05, + "loss": 1.4357, + "step": 4684 + }, + { + "epoch": 0.49, + "learning_rate": 1.2033625244916803e-05, + "loss": 1.3908, + "step": 4685 + }, + { + "epoch": 0.49, + "learning_rate": 1.2030041345057298e-05, + "loss": 1.3804, + "step": 4686 + }, + { + "epoch": 0.49, + "learning_rate": 1.2026457173224412e-05, + "loss": 1.4523, + "step": 4687 + }, + { + "epoch": 0.49, + "learning_rate": 1.2022872729898336e-05, + "loss": 1.4266, + "step": 4688 + }, + { + "epoch": 0.49, + "learning_rate": 1.201928801555929e-05, + "loss": 1.3345, + "step": 4689 + }, + { + "epoch": 0.49, + "learning_rate": 1.2015703030687532e-05, + "loss": 1.1714, + "step": 4690 + }, + { + "epoch": 0.49, + "learning_rate": 1.2012117775763361e-05, + "loss": 1.3899, + "step": 4691 + }, + { + "epoch": 0.49, + "learning_rate": 1.2008532251267109e-05, + "loss": 1.43, + "step": 4692 + }, + { + "epoch": 0.49, + "learning_rate": 1.2004946457679144e-05, + "loss": 1.4302, + "step": 4693 + }, + { + "epoch": 0.49, + "learning_rate": 1.2001360395479865e-05, + "loss": 1.3452, + "step": 4694 + }, + { + "epoch": 0.49, + "learning_rate": 1.1997774065149716e-05, + "loss": 1.3383, + "step": 4695 + }, + { + "epoch": 0.49, + "learning_rate": 1.1994187467169176e-05, + "loss": 1.3677, + "step": 4696 + }, + { + "epoch": 0.49, + "learning_rate": 1.1990600602018755e-05, + "loss": 1.4486, + "step": 4697 + }, + { + "epoch": 0.49, + "learning_rate": 1.1987013470178998e-05, + "loss": 1.4059, + "step": 4698 + }, + { + "epoch": 0.49, + "learning_rate": 1.198342607213049e-05, + "loss": 1.3558, + "step": 4699 + }, + { + "epoch": 0.49, + "learning_rate": 1.1979838408353854e-05, + "loss": 1.3931, + "step": 4700 + }, + { + "epoch": 0.49, + "learning_rate": 1.197625047932974e-05, + "loss": 1.5409, + "step": 4701 + }, + { + "epoch": 0.49, + "learning_rate": 1.197266228553884e-05, + "loss": 1.4878, + "step": 4702 + }, + { + "epoch": 0.49, + "learning_rate": 1.196907382746188e-05, + "loss": 1.3581, + "step": 4703 + }, + { + "epoch": 0.49, + "learning_rate": 1.1965485105579621e-05, + "loss": 1.3617, + "step": 4704 + }, + { + "epoch": 0.49, + "learning_rate": 1.1961896120372857e-05, + "loss": 1.399, + "step": 4705 + }, + { + "epoch": 0.49, + "learning_rate": 1.1958306872322425e-05, + "loss": 1.3861, + "step": 4706 + }, + { + "epoch": 0.49, + "learning_rate": 1.1954717361909186e-05, + "loss": 1.4719, + "step": 4707 + }, + { + "epoch": 0.49, + "learning_rate": 1.195112758961405e-05, + "loss": 1.393, + "step": 4708 + }, + { + "epoch": 0.49, + "learning_rate": 1.1947537555917947e-05, + "loss": 1.4252, + "step": 4709 + }, + { + "epoch": 0.49, + "learning_rate": 1.194394726130185e-05, + "loss": 1.4187, + "step": 4710 + }, + { + "epoch": 0.49, + "learning_rate": 1.1940356706246772e-05, + "loss": 1.4822, + "step": 4711 + }, + { + "epoch": 0.49, + "learning_rate": 1.193676589123375e-05, + "loss": 1.4259, + "step": 4712 + }, + { + "epoch": 0.49, + "learning_rate": 1.1933174816743857e-05, + "loss": 1.4226, + "step": 4713 + }, + { + "epoch": 0.49, + "learning_rate": 1.1929583483258216e-05, + "loss": 1.3701, + "step": 4714 + }, + { + "epoch": 0.49, + "learning_rate": 1.1925991891257967e-05, + "loss": 1.406, + "step": 4715 + }, + { + "epoch": 0.49, + "learning_rate": 1.1922400041224288e-05, + "loss": 1.4593, + "step": 4716 + }, + { + "epoch": 0.49, + "learning_rate": 1.1918807933638401e-05, + "loss": 1.3443, + "step": 4717 + }, + { + "epoch": 0.49, + "learning_rate": 1.1915215568981552e-05, + "loss": 1.3523, + "step": 4718 + }, + { + "epoch": 0.49, + "learning_rate": 1.1911622947735027e-05, + "loss": 1.3175, + "step": 4719 + }, + { + "epoch": 0.49, + "learning_rate": 1.1908030070380143e-05, + "loss": 1.3974, + "step": 4720 + }, + { + "epoch": 0.5, + "learning_rate": 1.1904436937398257e-05, + "loss": 1.386, + "step": 4721 + }, + { + "epoch": 0.5, + "learning_rate": 1.1900843549270753e-05, + "loss": 1.3684, + "step": 4722 + }, + { + "epoch": 0.5, + "learning_rate": 1.1897249906479054e-05, + "loss": 1.383, + "step": 4723 + }, + { + "epoch": 0.5, + "learning_rate": 1.1893656009504617e-05, + "loss": 1.38, + "step": 4724 + }, + { + "epoch": 0.5, + "learning_rate": 1.1890061858828928e-05, + "loss": 1.3844, + "step": 4725 + }, + { + "epoch": 0.5, + "learning_rate": 1.1886467454933515e-05, + "loss": 1.3252, + "step": 4726 + }, + { + "epoch": 0.5, + "learning_rate": 1.1882872798299934e-05, + "loss": 1.3434, + "step": 4727 + }, + { + "epoch": 0.5, + "learning_rate": 1.1879277889409779e-05, + "loss": 1.4115, + "step": 4728 + }, + { + "epoch": 0.5, + "learning_rate": 1.1875682728744669e-05, + "loss": 1.1911, + "step": 4729 + }, + { + "epoch": 0.5, + "learning_rate": 1.1872087316786272e-05, + "loss": 1.2794, + "step": 4730 + }, + { + "epoch": 0.5, + "learning_rate": 1.1868491654016274e-05, + "loss": 1.3961, + "step": 4731 + }, + { + "epoch": 0.5, + "learning_rate": 1.1864895740916404e-05, + "loss": 1.4965, + "step": 4732 + }, + { + "epoch": 0.5, + "learning_rate": 1.1861299577968419e-05, + "loss": 1.3932, + "step": 4733 + }, + { + "epoch": 0.5, + "learning_rate": 1.185770316565412e-05, + "loss": 1.3926, + "step": 4734 + }, + { + "epoch": 0.5, + "learning_rate": 1.1854106504455327e-05, + "loss": 1.3964, + "step": 4735 + }, + { + "epoch": 0.5, + "learning_rate": 1.1850509594853901e-05, + "loss": 1.3666, + "step": 4736 + }, + { + "epoch": 0.5, + "learning_rate": 1.1846912437331736e-05, + "loss": 1.4364, + "step": 4737 + }, + { + "epoch": 0.5, + "learning_rate": 1.1843315032370762e-05, + "loss": 1.3537, + "step": 4738 + }, + { + "epoch": 0.5, + "learning_rate": 1.1839717380452935e-05, + "loss": 1.4083, + "step": 4739 + }, + { + "epoch": 0.5, + "learning_rate": 1.1836119482060247e-05, + "loss": 1.3881, + "step": 4740 + }, + { + "epoch": 0.5, + "learning_rate": 1.1832521337674727e-05, + "loss": 1.4127, + "step": 4741 + }, + { + "epoch": 0.5, + "learning_rate": 1.1828922947778436e-05, + "loss": 1.3433, + "step": 4742 + }, + { + "epoch": 0.5, + "learning_rate": 1.1825324312853461e-05, + "loss": 1.486, + "step": 4743 + }, + { + "epoch": 0.5, + "learning_rate": 1.1821725433381925e-05, + "loss": 1.335, + "step": 4744 + }, + { + "epoch": 0.5, + "learning_rate": 1.1818126309845993e-05, + "loss": 1.3827, + "step": 4745 + }, + { + "epoch": 0.5, + "learning_rate": 1.181452694272785e-05, + "loss": 1.3146, + "step": 4746 + }, + { + "epoch": 0.5, + "learning_rate": 1.1810927332509717e-05, + "loss": 1.3543, + "step": 4747 + }, + { + "epoch": 0.5, + "learning_rate": 1.1807327479673852e-05, + "loss": 1.3544, + "step": 4748 + }, + { + "epoch": 0.5, + "learning_rate": 1.1803727384702543e-05, + "loss": 1.3677, + "step": 4749 + }, + { + "epoch": 0.5, + "learning_rate": 1.1800127048078111e-05, + "loss": 1.3842, + "step": 4750 + }, + { + "epoch": 0.5, + "learning_rate": 1.1796526470282907e-05, + "loss": 1.3495, + "step": 4751 + }, + { + "epoch": 0.5, + "learning_rate": 1.1792925651799314e-05, + "loss": 1.481, + "step": 4752 + }, + { + "epoch": 0.5, + "learning_rate": 1.1789324593109754e-05, + "loss": 1.3482, + "step": 4753 + }, + { + "epoch": 0.5, + "learning_rate": 1.1785723294696673e-05, + "loss": 1.2805, + "step": 4754 + }, + { + "epoch": 0.5, + "learning_rate": 1.1782121757042555e-05, + "loss": 1.3458, + "step": 4755 + }, + { + "epoch": 0.5, + "learning_rate": 1.1778519980629907e-05, + "loss": 1.3937, + "step": 4756 + }, + { + "epoch": 0.5, + "learning_rate": 1.1774917965941284e-05, + "loss": 1.3873, + "step": 4757 + }, + { + "epoch": 0.5, + "learning_rate": 1.1771315713459258e-05, + "loss": 1.3512, + "step": 4758 + }, + { + "epoch": 0.5, + "learning_rate": 1.1767713223666436e-05, + "loss": 1.4465, + "step": 4759 + }, + { + "epoch": 0.5, + "learning_rate": 1.1764110497045463e-05, + "loss": 1.4233, + "step": 4760 + }, + { + "epoch": 0.5, + "learning_rate": 1.1760507534079011e-05, + "loss": 1.4818, + "step": 4761 + }, + { + "epoch": 0.5, + "learning_rate": 1.1756904335249786e-05, + "loss": 1.2933, + "step": 4762 + }, + { + "epoch": 0.5, + "learning_rate": 1.1753300901040518e-05, + "loss": 1.3524, + "step": 4763 + }, + { + "epoch": 0.5, + "learning_rate": 1.1749697231933981e-05, + "loss": 1.4909, + "step": 4764 + }, + { + "epoch": 0.5, + "learning_rate": 1.1746093328412975e-05, + "loss": 1.2912, + "step": 4765 + }, + { + "epoch": 0.5, + "learning_rate": 1.1742489190960325e-05, + "loss": 1.3372, + "step": 4766 + }, + { + "epoch": 0.5, + "learning_rate": 1.1738884820058893e-05, + "loss": 1.3036, + "step": 4767 + }, + { + "epoch": 0.5, + "learning_rate": 1.1735280216191578e-05, + "loss": 1.3189, + "step": 4768 + }, + { + "epoch": 0.5, + "learning_rate": 1.1731675379841298e-05, + "loss": 1.4146, + "step": 4769 + }, + { + "epoch": 0.5, + "learning_rate": 1.1728070311491013e-05, + "loss": 1.3309, + "step": 4770 + }, + { + "epoch": 0.5, + "learning_rate": 1.1724465011623705e-05, + "loss": 1.3427, + "step": 4771 + }, + { + "epoch": 0.5, + "learning_rate": 1.1720859480722395e-05, + "loss": 1.4033, + "step": 4772 + }, + { + "epoch": 0.5, + "learning_rate": 1.1717253719270135e-05, + "loss": 1.3832, + "step": 4773 + }, + { + "epoch": 0.5, + "learning_rate": 1.1713647727749994e-05, + "loss": 1.4074, + "step": 4774 + }, + { + "epoch": 0.5, + "learning_rate": 1.1710041506645092e-05, + "loss": 1.3579, + "step": 4775 + }, + { + "epoch": 0.5, + "learning_rate": 1.1706435056438564e-05, + "loss": 1.3685, + "step": 4776 + }, + { + "epoch": 0.5, + "eval_loss": 1.436767816543579, + "eval_runtime": 77.4332, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4776 + }, + { + "epoch": 0.5, + "learning_rate": 1.1702828377613584e-05, + "loss": 1.5843, + "step": 4777 + }, + { + "epoch": 0.5, + "learning_rate": 1.1699221470653355e-05, + "loss": 1.4168, + "step": 4778 + }, + { + "epoch": 0.5, + "learning_rate": 1.1695614336041108e-05, + "loss": 1.3515, + "step": 4779 + }, + { + "epoch": 0.5, + "learning_rate": 1.169200697426011e-05, + "loss": 1.3214, + "step": 4780 + }, + { + "epoch": 0.5, + "learning_rate": 1.1688399385793652e-05, + "loss": 1.3728, + "step": 4781 + }, + { + "epoch": 0.5, + "learning_rate": 1.1684791571125054e-05, + "loss": 1.3759, + "step": 4782 + }, + { + "epoch": 0.5, + "learning_rate": 1.1681183530737678e-05, + "loss": 1.4955, + "step": 4783 + }, + { + "epoch": 0.5, + "learning_rate": 1.1677575265114904e-05, + "loss": 1.4284, + "step": 4784 + }, + { + "epoch": 0.5, + "learning_rate": 1.1673966774740151e-05, + "loss": 1.3725, + "step": 4785 + }, + { + "epoch": 0.5, + "learning_rate": 1.1670358060096858e-05, + "loss": 1.3612, + "step": 4786 + }, + { + "epoch": 0.5, + "learning_rate": 1.1666749121668506e-05, + "loss": 1.3021, + "step": 4787 + }, + { + "epoch": 0.5, + "learning_rate": 1.1663139959938597e-05, + "loss": 1.4399, + "step": 4788 + }, + { + "epoch": 0.5, + "learning_rate": 1.1659530575390668e-05, + "loss": 1.3511, + "step": 4789 + }, + { + "epoch": 0.5, + "learning_rate": 1.1655920968508276e-05, + "loss": 1.4211, + "step": 4790 + }, + { + "epoch": 0.5, + "learning_rate": 1.1652311139775028e-05, + "loss": 1.343, + "step": 4791 + }, + { + "epoch": 0.5, + "learning_rate": 1.1648701089674541e-05, + "loss": 1.3838, + "step": 4792 + }, + { + "epoch": 0.5, + "learning_rate": 1.164509081869047e-05, + "loss": 1.342, + "step": 4793 + }, + { + "epoch": 0.5, + "learning_rate": 1.1641480327306494e-05, + "loss": 1.3831, + "step": 4794 + }, + { + "epoch": 0.5, + "learning_rate": 1.1637869616006335e-05, + "loss": 1.4102, + "step": 4795 + }, + { + "epoch": 0.5, + "learning_rate": 1.1634258685273732e-05, + "loss": 1.4184, + "step": 4796 + }, + { + "epoch": 0.5, + "learning_rate": 1.1630647535592455e-05, + "loss": 1.3974, + "step": 4797 + }, + { + "epoch": 0.5, + "learning_rate": 1.1627036167446302e-05, + "loss": 1.251, + "step": 4798 + }, + { + "epoch": 0.5, + "learning_rate": 1.1623424581319113e-05, + "loss": 1.3485, + "step": 4799 + }, + { + "epoch": 0.5, + "learning_rate": 1.1619812777694742e-05, + "loss": 1.3544, + "step": 4800 + }, + { + "epoch": 0.5, + "learning_rate": 1.1616200757057076e-05, + "loss": 1.3772, + "step": 4801 + }, + { + "epoch": 0.5, + "learning_rate": 1.1612588519890038e-05, + "loss": 1.3082, + "step": 4802 + }, + { + "epoch": 0.5, + "learning_rate": 1.160897606667757e-05, + "loss": 1.3634, + "step": 4803 + }, + { + "epoch": 0.5, + "learning_rate": 1.1605363397903655e-05, + "loss": 1.3682, + "step": 4804 + }, + { + "epoch": 0.5, + "learning_rate": 1.1601750514052288e-05, + "loss": 1.3258, + "step": 4805 + }, + { + "epoch": 0.5, + "learning_rate": 1.1598137415607511e-05, + "loss": 1.279, + "step": 4806 + }, + { + "epoch": 0.5, + "learning_rate": 1.1594524103053382e-05, + "loss": 1.3759, + "step": 4807 + }, + { + "epoch": 0.5, + "learning_rate": 1.1590910576873995e-05, + "loss": 1.5404, + "step": 4808 + }, + { + "epoch": 0.5, + "learning_rate": 1.1587296837553463e-05, + "loss": 1.4949, + "step": 4809 + }, + { + "epoch": 0.5, + "learning_rate": 1.1583682885575943e-05, + "loss": 1.3501, + "step": 4810 + }, + { + "epoch": 0.5, + "learning_rate": 1.1580068721425608e-05, + "loss": 1.3898, + "step": 4811 + }, + { + "epoch": 0.5, + "learning_rate": 1.157645434558666e-05, + "loss": 1.3265, + "step": 4812 + }, + { + "epoch": 0.5, + "learning_rate": 1.1572839758543338e-05, + "loss": 1.3454, + "step": 4813 + }, + { + "epoch": 0.5, + "learning_rate": 1.1569224960779899e-05, + "loss": 1.4065, + "step": 4814 + }, + { + "epoch": 0.5, + "learning_rate": 1.156560995278064e-05, + "loss": 1.4932, + "step": 4815 + }, + { + "epoch": 0.51, + "learning_rate": 1.156199473502987e-05, + "loss": 1.4224, + "step": 4816 + }, + { + "epoch": 0.51, + "learning_rate": 1.1558379308011937e-05, + "loss": 1.3884, + "step": 4817 + }, + { + "epoch": 0.51, + "learning_rate": 1.1554763672211222e-05, + "loss": 1.3355, + "step": 4818 + }, + { + "epoch": 0.51, + "learning_rate": 1.1551147828112124e-05, + "loss": 1.4281, + "step": 4819 + }, + { + "epoch": 0.51, + "learning_rate": 1.1547531776199072e-05, + "loss": 1.3148, + "step": 4820 + }, + { + "epoch": 0.51, + "learning_rate": 1.1543915516956523e-05, + "loss": 1.3255, + "step": 4821 + }, + { + "epoch": 0.51, + "learning_rate": 1.1540299050868966e-05, + "loss": 1.3361, + "step": 4822 + }, + { + "epoch": 0.51, + "learning_rate": 1.1536682378420912e-05, + "loss": 1.3377, + "step": 4823 + }, + { + "epoch": 0.51, + "learning_rate": 1.1533065500096901e-05, + "loss": 1.4205, + "step": 4824 + }, + { + "epoch": 0.51, + "learning_rate": 1.1529448416381505e-05, + "loss": 1.4193, + "step": 4825 + }, + { + "epoch": 0.51, + "learning_rate": 1.1525831127759322e-05, + "loss": 1.37, + "step": 4826 + }, + { + "epoch": 0.51, + "learning_rate": 1.1522213634714971e-05, + "loss": 1.3642, + "step": 4827 + }, + { + "epoch": 0.51, + "learning_rate": 1.1518595937733103e-05, + "loss": 1.4834, + "step": 4828 + }, + { + "epoch": 0.51, + "learning_rate": 1.1514978037298402e-05, + "loss": 1.2864, + "step": 4829 + }, + { + "epoch": 0.51, + "learning_rate": 1.1511359933895567e-05, + "loss": 1.3468, + "step": 4830 + }, + { + "epoch": 0.51, + "learning_rate": 1.1507741628009337e-05, + "loss": 1.328, + "step": 4831 + }, + { + "epoch": 0.51, + "learning_rate": 1.1504123120124466e-05, + "loss": 1.3489, + "step": 4832 + }, + { + "epoch": 0.51, + "learning_rate": 1.1500504410725746e-05, + "loss": 1.4031, + "step": 4833 + }, + { + "epoch": 0.51, + "learning_rate": 1.149688550029799e-05, + "loss": 1.3482, + "step": 4834 + }, + { + "epoch": 0.51, + "learning_rate": 1.1493266389326037e-05, + "loss": 1.3674, + "step": 4835 + }, + { + "epoch": 0.51, + "learning_rate": 1.1489647078294753e-05, + "loss": 1.2895, + "step": 4836 + }, + { + "epoch": 0.51, + "learning_rate": 1.148602756768904e-05, + "loss": 1.4071, + "step": 4837 + }, + { + "epoch": 0.51, + "learning_rate": 1.1482407857993814e-05, + "loss": 1.5218, + "step": 4838 + }, + { + "epoch": 0.51, + "learning_rate": 1.1478787949694024e-05, + "loss": 1.4577, + "step": 4839 + }, + { + "epoch": 0.51, + "learning_rate": 1.1475167843274643e-05, + "loss": 1.3817, + "step": 4840 + }, + { + "epoch": 0.51, + "learning_rate": 1.1471547539220678e-05, + "loss": 1.3072, + "step": 4841 + }, + { + "epoch": 0.51, + "learning_rate": 1.146792703801715e-05, + "loss": 1.3737, + "step": 4842 + }, + { + "epoch": 0.51, + "learning_rate": 1.1464306340149119e-05, + "loss": 1.4001, + "step": 4843 + }, + { + "epoch": 0.51, + "learning_rate": 1.1460685446101658e-05, + "loss": 1.3963, + "step": 4844 + }, + { + "epoch": 0.51, + "learning_rate": 1.1457064356359882e-05, + "loss": 1.4061, + "step": 4845 + }, + { + "epoch": 0.51, + "learning_rate": 1.145344307140892e-05, + "loss": 1.4211, + "step": 4846 + }, + { + "epoch": 0.51, + "learning_rate": 1.144982159173393e-05, + "loss": 1.3197, + "step": 4847 + }, + { + "epoch": 0.51, + "learning_rate": 1.14461999178201e-05, + "loss": 1.3549, + "step": 4848 + }, + { + "epoch": 0.51, + "learning_rate": 1.1442578050152639e-05, + "loss": 1.3889, + "step": 4849 + }, + { + "epoch": 0.51, + "learning_rate": 1.1438955989216787e-05, + "loss": 1.3847, + "step": 4850 + }, + { + "epoch": 0.51, + "learning_rate": 1.1435333735497803e-05, + "loss": 1.3586, + "step": 4851 + }, + { + "epoch": 0.51, + "learning_rate": 1.1431711289480978e-05, + "loss": 1.503, + "step": 4852 + }, + { + "epoch": 0.51, + "learning_rate": 1.1428088651651627e-05, + "loss": 1.3654, + "step": 4853 + }, + { + "epoch": 0.51, + "learning_rate": 1.1424465822495092e-05, + "loss": 1.3741, + "step": 4854 + }, + { + "epoch": 0.51, + "learning_rate": 1.1420842802496737e-05, + "loss": 1.5437, + "step": 4855 + }, + { + "epoch": 0.51, + "learning_rate": 1.1417219592141953e-05, + "loss": 1.2179, + "step": 4856 + }, + { + "epoch": 0.51, + "learning_rate": 1.1413596191916159e-05, + "loss": 1.3939, + "step": 4857 + }, + { + "epoch": 0.51, + "learning_rate": 1.1409972602304796e-05, + "loss": 1.3383, + "step": 4858 + }, + { + "epoch": 0.51, + "learning_rate": 1.140634882379333e-05, + "loss": 1.3664, + "step": 4859 + }, + { + "epoch": 0.51, + "learning_rate": 1.1402724856867258e-05, + "loss": 1.4002, + "step": 4860 + }, + { + "epoch": 0.51, + "learning_rate": 1.1399100702012098e-05, + "loss": 1.2975, + "step": 4861 + }, + { + "epoch": 0.51, + "learning_rate": 1.1395476359713394e-05, + "loss": 1.3564, + "step": 4862 + }, + { + "epoch": 0.51, + "learning_rate": 1.1391851830456708e-05, + "loss": 1.3574, + "step": 4863 + }, + { + "epoch": 0.51, + "learning_rate": 1.1388227114727644e-05, + "loss": 1.3407, + "step": 4864 + }, + { + "epoch": 0.51, + "learning_rate": 1.1384602213011815e-05, + "loss": 1.3603, + "step": 4865 + }, + { + "epoch": 0.51, + "learning_rate": 1.1380977125794866e-05, + "loss": 1.3465, + "step": 4866 + }, + { + "epoch": 0.51, + "learning_rate": 1.1377351853562461e-05, + "loss": 1.3744, + "step": 4867 + }, + { + "epoch": 0.51, + "learning_rate": 1.1373726396800304e-05, + "loss": 1.3248, + "step": 4868 + }, + { + "epoch": 0.51, + "learning_rate": 1.1370100755994102e-05, + "loss": 1.3352, + "step": 4869 + }, + { + "epoch": 0.51, + "learning_rate": 1.1366474931629603e-05, + "loss": 1.3299, + "step": 4870 + }, + { + "epoch": 0.51, + "learning_rate": 1.1362848924192575e-05, + "loss": 1.344, + "step": 4871 + }, + { + "epoch": 0.51, + "learning_rate": 1.1359222734168809e-05, + "loss": 1.3209, + "step": 4872 + }, + { + "epoch": 0.51, + "learning_rate": 1.135559636204412e-05, + "loss": 1.3927, + "step": 4873 + }, + { + "epoch": 0.51, + "learning_rate": 1.1351969808304349e-05, + "loss": 1.3717, + "step": 4874 + }, + { + "epoch": 0.51, + "learning_rate": 1.1348343073435362e-05, + "loss": 1.3813, + "step": 4875 + }, + { + "epoch": 0.51, + "learning_rate": 1.1344716157923046e-05, + "loss": 1.236, + "step": 4876 + }, + { + "epoch": 0.51, + "learning_rate": 1.1341089062253319e-05, + "loss": 1.2591, + "step": 4877 + }, + { + "epoch": 0.51, + "learning_rate": 1.1337461786912112e-05, + "loss": 1.3211, + "step": 4878 + }, + { + "epoch": 0.51, + "learning_rate": 1.1333834332385394e-05, + "loss": 1.4534, + "step": 4879 + }, + { + "epoch": 0.51, + "learning_rate": 1.1330206699159145e-05, + "loss": 1.346, + "step": 4880 + }, + { + "epoch": 0.51, + "learning_rate": 1.132657888771938e-05, + "loss": 1.3952, + "step": 4881 + }, + { + "epoch": 0.51, + "learning_rate": 1.1322950898552125e-05, + "loss": 1.3008, + "step": 4882 + }, + { + "epoch": 0.51, + "learning_rate": 1.1319322732143445e-05, + "loss": 1.3201, + "step": 4883 + }, + { + "epoch": 0.51, + "learning_rate": 1.1315694388979416e-05, + "loss": 1.3761, + "step": 4884 + }, + { + "epoch": 0.51, + "learning_rate": 1.1312065869546147e-05, + "loss": 1.343, + "step": 4885 + }, + { + "epoch": 0.51, + "learning_rate": 1.1308437174329761e-05, + "loss": 1.3741, + "step": 4886 + }, + { + "epoch": 0.51, + "learning_rate": 1.1304808303816413e-05, + "loss": 1.402, + "step": 4887 + }, + { + "epoch": 0.51, + "learning_rate": 1.130117925849228e-05, + "loss": 1.3834, + "step": 4888 + }, + { + "epoch": 0.51, + "learning_rate": 1.1297550038843559e-05, + "loss": 1.3342, + "step": 4889 + }, + { + "epoch": 0.51, + "learning_rate": 1.1293920645356471e-05, + "loss": 1.3207, + "step": 4890 + }, + { + "epoch": 0.51, + "learning_rate": 1.1290291078517264e-05, + "loss": 1.4274, + "step": 4891 + }, + { + "epoch": 0.51, + "learning_rate": 1.1286661338812203e-05, + "loss": 1.328, + "step": 4892 + }, + { + "epoch": 0.51, + "learning_rate": 1.1283031426727584e-05, + "loss": 1.3823, + "step": 4893 + }, + { + "epoch": 0.51, + "learning_rate": 1.127940134274972e-05, + "loss": 1.3612, + "step": 4894 + }, + { + "epoch": 0.51, + "learning_rate": 1.127577108736495e-05, + "loss": 1.375, + "step": 4895 + }, + { + "epoch": 0.51, + "learning_rate": 1.1272140661059636e-05, + "loss": 1.3531, + "step": 4896 + }, + { + "epoch": 0.51, + "learning_rate": 1.1268510064320155e-05, + "loss": 1.3636, + "step": 4897 + }, + { + "epoch": 0.51, + "learning_rate": 1.1264879297632923e-05, + "loss": 1.3524, + "step": 4898 + }, + { + "epoch": 0.51, + "learning_rate": 1.1261248361484363e-05, + "loss": 1.3865, + "step": 4899 + }, + { + "epoch": 0.51, + "learning_rate": 1.125761725636093e-05, + "loss": 1.4069, + "step": 4900 + }, + { + "epoch": 0.51, + "learning_rate": 1.1253985982749098e-05, + "loss": 1.4643, + "step": 4901 + }, + { + "epoch": 0.51, + "learning_rate": 1.1250354541135364e-05, + "loss": 1.4506, + "step": 4902 + }, + { + "epoch": 0.51, + "learning_rate": 1.124672293200625e-05, + "loss": 1.3857, + "step": 4903 + }, + { + "epoch": 0.51, + "learning_rate": 1.1243091155848295e-05, + "loss": 1.3554, + "step": 4904 + }, + { + "epoch": 0.51, + "learning_rate": 1.1239459213148065e-05, + "loss": 1.4071, + "step": 4905 + }, + { + "epoch": 0.51, + "learning_rate": 1.1235827104392148e-05, + "loss": 1.3981, + "step": 4906 + }, + { + "epoch": 0.51, + "learning_rate": 1.1232194830067153e-05, + "loss": 1.4913, + "step": 4907 + }, + { + "epoch": 0.51, + "learning_rate": 1.1228562390659712e-05, + "loss": 1.3343, + "step": 4908 + }, + { + "epoch": 0.51, + "learning_rate": 1.1224929786656474e-05, + "loss": 1.3832, + "step": 4909 + }, + { + "epoch": 0.51, + "learning_rate": 1.122129701854412e-05, + "loss": 1.367, + "step": 4910 + }, + { + "epoch": 0.51, + "learning_rate": 1.1217664086809345e-05, + "loss": 1.4108, + "step": 4911 + }, + { + "epoch": 0.52, + "learning_rate": 1.1214030991938872e-05, + "loss": 1.3981, + "step": 4912 + }, + { + "epoch": 0.52, + "learning_rate": 1.1210397734419436e-05, + "loss": 1.5266, + "step": 4913 + }, + { + "epoch": 0.52, + "learning_rate": 1.1206764314737806e-05, + "loss": 1.337, + "step": 4914 + }, + { + "epoch": 0.52, + "learning_rate": 1.1203130733380765e-05, + "loss": 1.3784, + "step": 4915 + }, + { + "epoch": 0.52, + "learning_rate": 1.1199496990835117e-05, + "loss": 1.3048, + "step": 4916 + }, + { + "epoch": 0.52, + "learning_rate": 1.1195863087587692e-05, + "loss": 1.2977, + "step": 4917 + }, + { + "epoch": 0.52, + "learning_rate": 1.1192229024125344e-05, + "loss": 1.3304, + "step": 4918 + }, + { + "epoch": 0.52, + "learning_rate": 1.1188594800934938e-05, + "loss": 1.4102, + "step": 4919 + }, + { + "epoch": 0.52, + "learning_rate": 1.1184960418503366e-05, + "loss": 1.3932, + "step": 4920 + }, + { + "epoch": 0.52, + "learning_rate": 1.1181325877317547e-05, + "loss": 1.4985, + "step": 4921 + }, + { + "epoch": 0.52, + "learning_rate": 1.1177691177864415e-05, + "loss": 1.4596, + "step": 4922 + }, + { + "epoch": 0.52, + "learning_rate": 1.1174056320630924e-05, + "loss": 1.3559, + "step": 4923 + }, + { + "epoch": 0.52, + "learning_rate": 1.117042130610405e-05, + "loss": 1.4128, + "step": 4924 + }, + { + "epoch": 0.52, + "learning_rate": 1.1166786134770795e-05, + "loss": 1.3343, + "step": 4925 + }, + { + "epoch": 0.52, + "learning_rate": 1.116315080711818e-05, + "loss": 1.332, + "step": 4926 + }, + { + "epoch": 0.52, + "learning_rate": 1.115951532363324e-05, + "loss": 1.3616, + "step": 4927 + }, + { + "epoch": 0.52, + "learning_rate": 1.1155879684803041e-05, + "loss": 1.4074, + "step": 4928 + }, + { + "epoch": 0.52, + "learning_rate": 1.1152243891114665e-05, + "loss": 1.303, + "step": 4929 + }, + { + "epoch": 0.52, + "learning_rate": 1.1148607943055212e-05, + "loss": 1.4799, + "step": 4930 + }, + { + "epoch": 0.52, + "learning_rate": 1.1144971841111807e-05, + "loss": 1.3881, + "step": 4931 + }, + { + "epoch": 0.52, + "learning_rate": 1.1141335585771593e-05, + "loss": 1.338, + "step": 4932 + }, + { + "epoch": 0.52, + "learning_rate": 1.1137699177521738e-05, + "loss": 1.3289, + "step": 4933 + }, + { + "epoch": 0.52, + "learning_rate": 1.1134062616849426e-05, + "loss": 1.377, + "step": 4934 + }, + { + "epoch": 0.52, + "learning_rate": 1.1130425904241862e-05, + "loss": 1.3596, + "step": 4935 + }, + { + "epoch": 0.52, + "learning_rate": 1.112678904018627e-05, + "loss": 1.4264, + "step": 4936 + }, + { + "epoch": 0.52, + "learning_rate": 1.1123152025169898e-05, + "loss": 1.3526, + "step": 4937 + }, + { + "epoch": 0.52, + "learning_rate": 1.1119514859680016e-05, + "loss": 1.3271, + "step": 4938 + }, + { + "epoch": 0.52, + "learning_rate": 1.1115877544203905e-05, + "loss": 1.3907, + "step": 4939 + }, + { + "epoch": 0.52, + "learning_rate": 1.1112240079228878e-05, + "loss": 1.3415, + "step": 4940 + }, + { + "epoch": 0.52, + "learning_rate": 1.1108602465242258e-05, + "loss": 1.3875, + "step": 4941 + }, + { + "epoch": 0.52, + "learning_rate": 1.110496470273139e-05, + "loss": 1.3964, + "step": 4942 + }, + { + "epoch": 0.52, + "learning_rate": 1.1101326792183645e-05, + "loss": 1.3448, + "step": 4943 + }, + { + "epoch": 0.52, + "learning_rate": 1.1097688734086407e-05, + "loss": 1.3522, + "step": 4944 + }, + { + "epoch": 0.52, + "learning_rate": 1.1094050528927082e-05, + "loss": 1.2742, + "step": 4945 + }, + { + "epoch": 0.52, + "learning_rate": 1.1090412177193097e-05, + "loss": 1.417, + "step": 4946 + }, + { + "epoch": 0.52, + "learning_rate": 1.1086773679371898e-05, + "loss": 1.3993, + "step": 4947 + }, + { + "epoch": 0.52, + "learning_rate": 1.108313503595095e-05, + "loss": 1.3783, + "step": 4948 + }, + { + "epoch": 0.52, + "learning_rate": 1.1079496247417736e-05, + "loss": 1.3975, + "step": 4949 + }, + { + "epoch": 0.52, + "learning_rate": 1.1075857314259763e-05, + "loss": 1.4256, + "step": 4950 + }, + { + "epoch": 0.52, + "learning_rate": 1.1072218236964551e-05, + "loss": 1.3547, + "step": 4951 + }, + { + "epoch": 0.52, + "learning_rate": 1.106857901601965e-05, + "loss": 1.4243, + "step": 4952 + }, + { + "epoch": 0.52, + "learning_rate": 1.1064939651912612e-05, + "loss": 1.4259, + "step": 4953 + }, + { + "epoch": 0.52, + "learning_rate": 1.1061300145131027e-05, + "loss": 1.4323, + "step": 4954 + }, + { + "epoch": 0.52, + "learning_rate": 1.1057660496162488e-05, + "loss": 1.3608, + "step": 4955 + }, + { + "epoch": 0.52, + "learning_rate": 1.1054020705494622e-05, + "loss": 1.3703, + "step": 4956 + }, + { + "epoch": 0.52, + "learning_rate": 1.105038077361506e-05, + "loss": 1.3953, + "step": 4957 + }, + { + "epoch": 0.52, + "learning_rate": 1.1046740701011467e-05, + "loss": 1.392, + "step": 4958 + }, + { + "epoch": 0.52, + "learning_rate": 1.1043100488171513e-05, + "loss": 1.4101, + "step": 4959 + }, + { + "epoch": 0.52, + "learning_rate": 1.1039460135582894e-05, + "loss": 1.5432, + "step": 4960 + }, + { + "epoch": 0.52, + "learning_rate": 1.1035819643733326e-05, + "loss": 1.3822, + "step": 4961 + }, + { + "epoch": 0.52, + "learning_rate": 1.103217901311054e-05, + "loss": 1.3816, + "step": 4962 + }, + { + "epoch": 0.52, + "learning_rate": 1.1028538244202287e-05, + "loss": 1.3137, + "step": 4963 + }, + { + "epoch": 0.52, + "learning_rate": 1.102489733749634e-05, + "loss": 1.3791, + "step": 4964 + }, + { + "epoch": 0.52, + "learning_rate": 1.102125629348048e-05, + "loss": 1.3751, + "step": 4965 + }, + { + "epoch": 0.52, + "learning_rate": 1.1017615112642518e-05, + "loss": 1.3287, + "step": 4966 + }, + { + "epoch": 0.52, + "learning_rate": 1.1013973795470277e-05, + "loss": 1.3187, + "step": 4967 + }, + { + "epoch": 0.52, + "learning_rate": 1.1010332342451602e-05, + "loss": 1.3174, + "step": 4968 + }, + { + "epoch": 0.52, + "learning_rate": 1.1006690754074351e-05, + "loss": 1.3544, + "step": 4969 + }, + { + "epoch": 0.52, + "learning_rate": 1.1003049030826404e-05, + "loss": 1.3789, + "step": 4970 + }, + { + "epoch": 0.52, + "learning_rate": 1.0999407173195662e-05, + "loss": 1.4561, + "step": 4971 + }, + { + "epoch": 0.52, + "learning_rate": 1.0995765181670039e-05, + "loss": 1.3963, + "step": 4972 + }, + { + "epoch": 0.52, + "learning_rate": 1.0992123056737464e-05, + "loss": 1.3519, + "step": 4973 + }, + { + "epoch": 0.52, + "learning_rate": 1.0988480798885892e-05, + "loss": 1.3945, + "step": 4974 + }, + { + "epoch": 0.52, + "learning_rate": 1.0984838408603294e-05, + "loss": 1.4572, + "step": 4975 + }, + { + "epoch": 0.52, + "eval_loss": 1.4313459396362305, + "eval_runtime": 77.4808, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 4975 + }, + { + "epoch": 0.52, + "learning_rate": 1.0981195886377652e-05, + "loss": 1.3493, + "step": 4976 + }, + { + "epoch": 0.52, + "learning_rate": 1.0977553232696972e-05, + "loss": 1.3734, + "step": 4977 + }, + { + "epoch": 0.52, + "learning_rate": 1.0973910448049273e-05, + "loss": 1.3484, + "step": 4978 + }, + { + "epoch": 0.52, + "learning_rate": 1.09702675329226e-05, + "loss": 1.4288, + "step": 4979 + }, + { + "epoch": 0.52, + "learning_rate": 1.096662448780501e-05, + "loss": 1.3748, + "step": 4980 + }, + { + "epoch": 0.52, + "learning_rate": 1.0962981313184575e-05, + "loss": 1.3485, + "step": 4981 + }, + { + "epoch": 0.52, + "learning_rate": 1.0959338009549383e-05, + "loss": 1.3606, + "step": 4982 + }, + { + "epoch": 0.52, + "learning_rate": 1.095569457738755e-05, + "loss": 1.3963, + "step": 4983 + }, + { + "epoch": 0.52, + "learning_rate": 1.09520510171872e-05, + "loss": 1.2986, + "step": 4984 + }, + { + "epoch": 0.52, + "learning_rate": 1.0948407329436474e-05, + "loss": 1.3505, + "step": 4985 + }, + { + "epoch": 0.52, + "learning_rate": 1.0944763514623535e-05, + "loss": 1.4649, + "step": 4986 + }, + { + "epoch": 0.52, + "learning_rate": 1.0941119573236564e-05, + "loss": 1.4743, + "step": 4987 + }, + { + "epoch": 0.52, + "learning_rate": 1.0937475505763745e-05, + "loss": 1.3934, + "step": 4988 + }, + { + "epoch": 0.52, + "learning_rate": 1.09338313126933e-05, + "loss": 1.4225, + "step": 4989 + }, + { + "epoch": 0.52, + "learning_rate": 1.0930186994513453e-05, + "loss": 1.3626, + "step": 4990 + }, + { + "epoch": 0.52, + "learning_rate": 1.0926542551712446e-05, + "loss": 1.3614, + "step": 4991 + }, + { + "epoch": 0.52, + "learning_rate": 1.0922897984778546e-05, + "loss": 1.3766, + "step": 4992 + }, + { + "epoch": 0.52, + "learning_rate": 1.0919253294200027e-05, + "loss": 1.3295, + "step": 4993 + }, + { + "epoch": 0.52, + "learning_rate": 1.091560848046519e-05, + "loss": 1.3802, + "step": 4994 + }, + { + "epoch": 0.52, + "learning_rate": 1.091196354406234e-05, + "loss": 1.2976, + "step": 4995 + }, + { + "epoch": 0.52, + "learning_rate": 1.090831848547981e-05, + "loss": 1.3928, + "step": 4996 + }, + { + "epoch": 0.52, + "learning_rate": 1.0904673305205937e-05, + "loss": 1.3717, + "step": 4997 + }, + { + "epoch": 0.52, + "learning_rate": 1.0901028003729089e-05, + "loss": 1.3164, + "step": 4998 + }, + { + "epoch": 0.52, + "learning_rate": 1.0897382581537638e-05, + "loss": 1.3462, + "step": 4999 + }, + { + "epoch": 0.52, + "learning_rate": 1.0893737039119981e-05, + "loss": 1.3643, + "step": 5000 + }, + { + "epoch": 0.52, + "learning_rate": 1.089009137696452e-05, + "loss": 1.3452, + "step": 5001 + }, + { + "epoch": 0.52, + "learning_rate": 1.0886445595559686e-05, + "loss": 1.358, + "step": 5002 + }, + { + "epoch": 0.52, + "learning_rate": 1.0882799695393922e-05, + "loss": 1.4569, + "step": 5003 + }, + { + "epoch": 0.52, + "learning_rate": 1.0879153676955681e-05, + "loss": 1.2832, + "step": 5004 + }, + { + "epoch": 0.52, + "learning_rate": 1.0875507540733435e-05, + "loss": 1.4089, + "step": 5005 + }, + { + "epoch": 0.52, + "learning_rate": 1.087186128721567e-05, + "loss": 1.3178, + "step": 5006 + }, + { + "epoch": 0.53, + "learning_rate": 1.0868214916890902e-05, + "loss": 1.4883, + "step": 5007 + }, + { + "epoch": 0.53, + "learning_rate": 1.0864568430247638e-05, + "loss": 1.3991, + "step": 5008 + }, + { + "epoch": 0.53, + "learning_rate": 1.0860921827774422e-05, + "loss": 1.4507, + "step": 5009 + }, + { + "epoch": 0.53, + "learning_rate": 1.08572751099598e-05, + "loss": 1.3578, + "step": 5010 + }, + { + "epoch": 0.53, + "learning_rate": 1.0853628277292341e-05, + "loss": 1.4231, + "step": 5011 + }, + { + "epoch": 0.53, + "learning_rate": 1.0849981330260624e-05, + "loss": 1.4835, + "step": 5012 + }, + { + "epoch": 0.53, + "learning_rate": 1.084633426935325e-05, + "loss": 1.4511, + "step": 5013 + }, + { + "epoch": 0.53, + "learning_rate": 1.084268709505883e-05, + "loss": 1.3889, + "step": 5014 + }, + { + "epoch": 0.53, + "learning_rate": 1.0839039807865992e-05, + "loss": 1.355, + "step": 5015 + }, + { + "epoch": 0.53, + "learning_rate": 1.0835392408263375e-05, + "loss": 1.4829, + "step": 5016 + }, + { + "epoch": 0.53, + "learning_rate": 1.0831744896739643e-05, + "loss": 1.3019, + "step": 5017 + }, + { + "epoch": 0.53, + "learning_rate": 1.0828097273783465e-05, + "loss": 1.3418, + "step": 5018 + }, + { + "epoch": 0.53, + "learning_rate": 1.082444953988353e-05, + "loss": 1.4276, + "step": 5019 + }, + { + "epoch": 0.53, + "learning_rate": 1.0820801695528537e-05, + "loss": 1.2816, + "step": 5020 + }, + { + "epoch": 0.53, + "learning_rate": 1.081715374120721e-05, + "loss": 1.5144, + "step": 5021 + }, + { + "epoch": 0.53, + "learning_rate": 1.0813505677408278e-05, + "loss": 1.4063, + "step": 5022 + }, + { + "epoch": 0.53, + "learning_rate": 1.0809857504620487e-05, + "loss": 1.4011, + "step": 5023 + }, + { + "epoch": 0.53, + "learning_rate": 1.0806209223332598e-05, + "loss": 1.373, + "step": 5024 + }, + { + "epoch": 0.53, + "learning_rate": 1.0802560834033388e-05, + "loss": 1.6259, + "step": 5025 + }, + { + "epoch": 0.53, + "learning_rate": 1.0798912337211648e-05, + "loss": 1.4487, + "step": 5026 + }, + { + "epoch": 0.53, + "learning_rate": 1.0795263733356184e-05, + "loss": 1.3056, + "step": 5027 + }, + { + "epoch": 0.53, + "learning_rate": 1.079161502295581e-05, + "loss": 1.2871, + "step": 5028 + }, + { + "epoch": 0.53, + "learning_rate": 1.0787966206499363e-05, + "loss": 1.413, + "step": 5029 + }, + { + "epoch": 0.53, + "learning_rate": 1.0784317284475694e-05, + "loss": 1.3682, + "step": 5030 + }, + { + "epoch": 0.53, + "learning_rate": 1.0780668257373659e-05, + "loss": 1.493, + "step": 5031 + }, + { + "epoch": 0.53, + "learning_rate": 1.0777019125682136e-05, + "loss": 1.6823, + "step": 5032 + }, + { + "epoch": 0.53, + "learning_rate": 1.0773369889890015e-05, + "loss": 1.358, + "step": 5033 + }, + { + "epoch": 0.53, + "learning_rate": 1.07697205504862e-05, + "loss": 1.3532, + "step": 5034 + }, + { + "epoch": 0.53, + "learning_rate": 1.0766071107959608e-05, + "loss": 1.3432, + "step": 5035 + }, + { + "epoch": 0.53, + "learning_rate": 1.0762421562799173e-05, + "loss": 1.3575, + "step": 5036 + }, + { + "epoch": 0.53, + "learning_rate": 1.0758771915493838e-05, + "loss": 1.0924, + "step": 5037 + }, + { + "epoch": 0.53, + "learning_rate": 1.075512216653256e-05, + "loss": 0.7405, + "step": 5038 + }, + { + "epoch": 0.53, + "learning_rate": 1.0751472316404315e-05, + "loss": 0.7134, + "step": 5039 + }, + { + "epoch": 0.53, + "learning_rate": 1.0747822365598088e-05, + "loss": 1.0904, + "step": 5040 + }, + { + "epoch": 0.53, + "learning_rate": 1.0744172314602881e-05, + "loss": 1.4353, + "step": 5041 + }, + { + "epoch": 0.53, + "learning_rate": 1.0740522163907702e-05, + "loss": 1.361, + "step": 5042 + }, + { + "epoch": 0.53, + "learning_rate": 1.073687191400158e-05, + "loss": 1.4024, + "step": 5043 + }, + { + "epoch": 0.53, + "learning_rate": 1.0733221565373557e-05, + "loss": 1.328, + "step": 5044 + }, + { + "epoch": 0.53, + "learning_rate": 1.0729571118512683e-05, + "loss": 1.3309, + "step": 5045 + }, + { + "epoch": 0.53, + "learning_rate": 1.0725920573908024e-05, + "loss": 1.3819, + "step": 5046 + }, + { + "epoch": 0.53, + "learning_rate": 1.0722269932048659e-05, + "loss": 1.3467, + "step": 5047 + }, + { + "epoch": 0.53, + "learning_rate": 1.0718619193423683e-05, + "loss": 1.3036, + "step": 5048 + }, + { + "epoch": 0.53, + "learning_rate": 1.07149683585222e-05, + "loss": 1.3297, + "step": 5049 + }, + { + "epoch": 0.53, + "learning_rate": 1.0711317427833328e-05, + "loss": 1.3439, + "step": 5050 + }, + { + "epoch": 0.53, + "learning_rate": 1.0707666401846192e-05, + "loss": 1.4167, + "step": 5051 + }, + { + "epoch": 0.53, + "learning_rate": 1.0704015281049944e-05, + "loss": 1.4217, + "step": 5052 + }, + { + "epoch": 0.53, + "learning_rate": 1.070036406593374e-05, + "loss": 1.3394, + "step": 5053 + }, + { + "epoch": 0.53, + "learning_rate": 1.0696712756986745e-05, + "loss": 1.3242, + "step": 5054 + }, + { + "epoch": 0.53, + "learning_rate": 1.0693061354698143e-05, + "loss": 1.3957, + "step": 5055 + }, + { + "epoch": 0.53, + "learning_rate": 1.0689409859557123e-05, + "loss": 1.37, + "step": 5056 + }, + { + "epoch": 0.53, + "learning_rate": 1.0685758272052902e-05, + "loss": 1.4524, + "step": 5057 + }, + { + "epoch": 0.53, + "learning_rate": 1.0682106592674688e-05, + "loss": 1.528, + "step": 5058 + }, + { + "epoch": 0.53, + "learning_rate": 1.0678454821911719e-05, + "loss": 1.3613, + "step": 5059 + }, + { + "epoch": 0.53, + "learning_rate": 1.0674802960253234e-05, + "loss": 1.308, + "step": 5060 + }, + { + "epoch": 0.53, + "learning_rate": 1.0671151008188494e-05, + "loss": 1.3343, + "step": 5061 + }, + { + "epoch": 0.53, + "learning_rate": 1.066749896620676e-05, + "loss": 1.365, + "step": 5062 + }, + { + "epoch": 0.53, + "learning_rate": 1.0663846834797316e-05, + "loss": 1.4077, + "step": 5063 + }, + { + "epoch": 0.53, + "learning_rate": 1.0660194614449455e-05, + "loss": 1.324, + "step": 5064 + }, + { + "epoch": 0.53, + "learning_rate": 1.0656542305652478e-05, + "loss": 1.3623, + "step": 5065 + }, + { + "epoch": 0.53, + "learning_rate": 1.0652889908895701e-05, + "loss": 1.4079, + "step": 5066 + }, + { + "epoch": 0.53, + "learning_rate": 1.0649237424668451e-05, + "loss": 1.3089, + "step": 5067 + }, + { + "epoch": 0.53, + "learning_rate": 1.0645584853460069e-05, + "loss": 1.3967, + "step": 5068 + }, + { + "epoch": 0.53, + "learning_rate": 1.0641932195759905e-05, + "loss": 1.3639, + "step": 5069 + }, + { + "epoch": 0.53, + "learning_rate": 1.0638279452057319e-05, + "loss": 1.5919, + "step": 5070 + }, + { + "epoch": 0.53, + "learning_rate": 1.0634626622841686e-05, + "loss": 1.3348, + "step": 5071 + }, + { + "epoch": 0.53, + "learning_rate": 1.0630973708602395e-05, + "loss": 1.3146, + "step": 5072 + }, + { + "epoch": 0.53, + "learning_rate": 1.0627320709828836e-05, + "loss": 1.3375, + "step": 5073 + }, + { + "epoch": 0.53, + "learning_rate": 1.062366762701042e-05, + "loss": 1.3908, + "step": 5074 + }, + { + "epoch": 0.53, + "learning_rate": 1.0620014460636568e-05, + "loss": 1.3726, + "step": 5075 + }, + { + "epoch": 0.53, + "learning_rate": 1.061636121119671e-05, + "loss": 1.2348, + "step": 5076 + }, + { + "epoch": 0.53, + "learning_rate": 1.0612707879180284e-05, + "loss": 1.2957, + "step": 5077 + }, + { + "epoch": 0.53, + "learning_rate": 1.0609054465076749e-05, + "loss": 1.4202, + "step": 5078 + }, + { + "epoch": 0.53, + "learning_rate": 1.060540096937556e-05, + "loss": 1.5809, + "step": 5079 + }, + { + "epoch": 0.53, + "learning_rate": 1.0601747392566202e-05, + "loss": 1.3741, + "step": 5080 + }, + { + "epoch": 0.53, + "learning_rate": 1.059809373513815e-05, + "loss": 1.3537, + "step": 5081 + }, + { + "epoch": 0.53, + "learning_rate": 1.0594439997580907e-05, + "loss": 1.332, + "step": 5082 + }, + { + "epoch": 0.53, + "learning_rate": 1.0590786180383981e-05, + "loss": 1.3267, + "step": 5083 + }, + { + "epoch": 0.53, + "learning_rate": 1.0587132284036883e-05, + "loss": 1.3552, + "step": 5084 + }, + { + "epoch": 0.53, + "learning_rate": 1.0583478309029143e-05, + "loss": 1.2837, + "step": 5085 + }, + { + "epoch": 0.53, + "learning_rate": 1.0579824255850304e-05, + "loss": 1.4311, + "step": 5086 + }, + { + "epoch": 0.53, + "learning_rate": 1.0576170124989915e-05, + "loss": 1.4394, + "step": 5087 + }, + { + "epoch": 0.53, + "learning_rate": 1.0572515916937531e-05, + "loss": 1.3185, + "step": 5088 + }, + { + "epoch": 0.53, + "learning_rate": 1.0568861632182723e-05, + "loss": 1.4212, + "step": 5089 + }, + { + "epoch": 0.53, + "learning_rate": 1.0565207271215075e-05, + "loss": 1.0951, + "step": 5090 + }, + { + "epoch": 0.53, + "learning_rate": 1.0561552834524176e-05, + "loss": 1.4174, + "step": 5091 + }, + { + "epoch": 0.53, + "learning_rate": 1.0557898322599624e-05, + "loss": 1.3349, + "step": 5092 + }, + { + "epoch": 0.53, + "learning_rate": 1.0554243735931031e-05, + "loss": 1.399, + "step": 5093 + }, + { + "epoch": 0.53, + "learning_rate": 1.055058907500802e-05, + "loss": 1.4016, + "step": 5094 + }, + { + "epoch": 0.53, + "learning_rate": 1.0546934340320219e-05, + "loss": 1.3227, + "step": 5095 + }, + { + "epoch": 0.53, + "learning_rate": 1.0543279532357269e-05, + "loss": 1.4017, + "step": 5096 + }, + { + "epoch": 0.53, + "learning_rate": 1.053962465160882e-05, + "loss": 1.3937, + "step": 5097 + }, + { + "epoch": 0.53, + "learning_rate": 1.0535969698564532e-05, + "loss": 1.2405, + "step": 5098 + }, + { + "epoch": 0.53, + "learning_rate": 1.0532314673714081e-05, + "loss": 1.2939, + "step": 5099 + }, + { + "epoch": 0.53, + "learning_rate": 1.0528659577547136e-05, + "loss": 1.4165, + "step": 5100 + }, + { + "epoch": 0.53, + "learning_rate": 1.0525004410553394e-05, + "loss": 1.309, + "step": 5101 + }, + { + "epoch": 0.54, + "learning_rate": 1.0521349173222549e-05, + "loss": 1.4078, + "step": 5102 + }, + { + "epoch": 0.54, + "learning_rate": 1.0517693866044312e-05, + "loss": 1.4026, + "step": 5103 + }, + { + "epoch": 0.54, + "learning_rate": 1.0514038489508396e-05, + "loss": 1.3098, + "step": 5104 + }, + { + "epoch": 0.54, + "learning_rate": 1.0510383044104533e-05, + "loss": 1.2886, + "step": 5105 + }, + { + "epoch": 0.54, + "learning_rate": 1.0506727530322454e-05, + "loss": 1.3114, + "step": 5106 + }, + { + "epoch": 0.54, + "learning_rate": 1.0503071948651908e-05, + "loss": 1.2823, + "step": 5107 + }, + { + "epoch": 0.54, + "learning_rate": 1.0499416299582643e-05, + "loss": 1.4654, + "step": 5108 + }, + { + "epoch": 0.54, + "learning_rate": 1.0495760583604431e-05, + "loss": 1.4043, + "step": 5109 + }, + { + "epoch": 0.54, + "learning_rate": 1.0492104801207035e-05, + "loss": 1.3113, + "step": 5110 + }, + { + "epoch": 0.54, + "learning_rate": 1.0488448952880243e-05, + "loss": 1.3285, + "step": 5111 + }, + { + "epoch": 0.54, + "learning_rate": 1.048479303911384e-05, + "loss": 1.3918, + "step": 5112 + }, + { + "epoch": 0.54, + "learning_rate": 1.0481137060397623e-05, + "loss": 1.346, + "step": 5113 + }, + { + "epoch": 0.54, + "learning_rate": 1.0477481017221407e-05, + "loss": 1.3777, + "step": 5114 + }, + { + "epoch": 0.54, + "learning_rate": 1.0473824910075003e-05, + "loss": 1.3494, + "step": 5115 + }, + { + "epoch": 0.54, + "learning_rate": 1.0470168739448232e-05, + "loss": 1.4173, + "step": 5116 + }, + { + "epoch": 0.54, + "learning_rate": 1.0466512505830932e-05, + "loss": 1.4313, + "step": 5117 + }, + { + "epoch": 0.54, + "learning_rate": 1.0462856209712944e-05, + "loss": 1.335, + "step": 5118 + }, + { + "epoch": 0.54, + "learning_rate": 1.0459199851584117e-05, + "loss": 1.37, + "step": 5119 + }, + { + "epoch": 0.54, + "learning_rate": 1.0455543431934307e-05, + "loss": 1.3504, + "step": 5120 + }, + { + "epoch": 0.54, + "learning_rate": 1.0451886951253381e-05, + "loss": 1.4148, + "step": 5121 + }, + { + "epoch": 0.54, + "learning_rate": 1.0448230410031218e-05, + "loss": 1.3974, + "step": 5122 + }, + { + "epoch": 0.54, + "learning_rate": 1.0444573808757694e-05, + "loss": 1.3644, + "step": 5123 + }, + { + "epoch": 0.54, + "learning_rate": 1.0440917147922705e-05, + "loss": 1.4024, + "step": 5124 + }, + { + "epoch": 0.54, + "learning_rate": 1.0437260428016143e-05, + "loss": 1.3925, + "step": 5125 + }, + { + "epoch": 0.54, + "learning_rate": 1.0433603649527923e-05, + "loss": 1.2907, + "step": 5126 + }, + { + "epoch": 0.54, + "learning_rate": 1.0429946812947953e-05, + "loss": 1.3453, + "step": 5127 + }, + { + "epoch": 0.54, + "learning_rate": 1.0426289918766157e-05, + "loss": 1.3856, + "step": 5128 + }, + { + "epoch": 0.54, + "learning_rate": 1.0422632967472465e-05, + "loss": 1.3309, + "step": 5129 + }, + { + "epoch": 0.54, + "learning_rate": 1.0418975959556819e-05, + "loss": 1.3757, + "step": 5130 + }, + { + "epoch": 0.54, + "learning_rate": 1.0415318895509152e-05, + "loss": 1.406, + "step": 5131 + }, + { + "epoch": 0.54, + "learning_rate": 1.041166177581943e-05, + "loss": 1.3265, + "step": 5132 + }, + { + "epoch": 0.54, + "learning_rate": 1.0408004600977606e-05, + "loss": 1.3377, + "step": 5133 + }, + { + "epoch": 0.54, + "learning_rate": 1.040434737147365e-05, + "loss": 1.3647, + "step": 5134 + }, + { + "epoch": 0.54, + "learning_rate": 1.0400690087797531e-05, + "loss": 1.3262, + "step": 5135 + }, + { + "epoch": 0.54, + "learning_rate": 1.039703275043924e-05, + "loss": 1.3924, + "step": 5136 + }, + { + "epoch": 0.54, + "learning_rate": 1.039337535988876e-05, + "loss": 1.3018, + "step": 5137 + }, + { + "epoch": 0.54, + "learning_rate": 1.038971791663609e-05, + "loss": 1.385, + "step": 5138 + }, + { + "epoch": 0.54, + "learning_rate": 1.0386060421171232e-05, + "loss": 1.3435, + "step": 5139 + }, + { + "epoch": 0.54, + "learning_rate": 1.0382402873984197e-05, + "loss": 1.4023, + "step": 5140 + }, + { + "epoch": 0.54, + "learning_rate": 1.0378745275565003e-05, + "loss": 1.369, + "step": 5141 + }, + { + "epoch": 0.54, + "learning_rate": 1.0375087626403675e-05, + "loss": 1.3199, + "step": 5142 + }, + { + "epoch": 0.54, + "learning_rate": 1.037142992699024e-05, + "loss": 1.4247, + "step": 5143 + }, + { + "epoch": 0.54, + "learning_rate": 1.0367772177814736e-05, + "loss": 1.4015, + "step": 5144 + }, + { + "epoch": 0.54, + "learning_rate": 1.0364114379367217e-05, + "loss": 1.3519, + "step": 5145 + }, + { + "epoch": 0.54, + "learning_rate": 1.0360456532137722e-05, + "loss": 1.3478, + "step": 5146 + }, + { + "epoch": 0.54, + "learning_rate": 1.0356798636616314e-05, + "loss": 1.4876, + "step": 5147 + }, + { + "epoch": 0.54, + "learning_rate": 1.0353140693293056e-05, + "loss": 1.6481, + "step": 5148 + }, + { + "epoch": 0.54, + "learning_rate": 1.034948270265802e-05, + "loss": 1.3851, + "step": 5149 + }, + { + "epoch": 0.54, + "learning_rate": 1.0345824665201281e-05, + "loss": 1.4037, + "step": 5150 + }, + { + "epoch": 0.54, + "learning_rate": 1.0342166581412923e-05, + "loss": 1.3138, + "step": 5151 + }, + { + "epoch": 0.54, + "learning_rate": 1.0338508451783032e-05, + "loss": 1.3536, + "step": 5152 + }, + { + "epoch": 0.54, + "learning_rate": 1.0334850276801712e-05, + "loss": 1.3244, + "step": 5153 + }, + { + "epoch": 0.54, + "learning_rate": 1.0331192056959052e-05, + "loss": 1.3677, + "step": 5154 + }, + { + "epoch": 0.54, + "learning_rate": 1.032753379274517e-05, + "loss": 1.3439, + "step": 5155 + }, + { + "epoch": 0.54, + "learning_rate": 1.0323875484650171e-05, + "loss": 1.365, + "step": 5156 + }, + { + "epoch": 0.54, + "learning_rate": 1.0320217133164186e-05, + "loss": 1.3838, + "step": 5157 + }, + { + "epoch": 0.54, + "learning_rate": 1.0316558738777328e-05, + "loss": 1.3312, + "step": 5158 + }, + { + "epoch": 0.54, + "learning_rate": 1.0312900301979733e-05, + "loss": 1.369, + "step": 5159 + }, + { + "epoch": 0.54, + "learning_rate": 1.030924182326154e-05, + "loss": 1.2712, + "step": 5160 + }, + { + "epoch": 0.54, + "learning_rate": 1.0305583303112887e-05, + "loss": 1.3141, + "step": 5161 + }, + { + "epoch": 0.54, + "learning_rate": 1.030192474202392e-05, + "loss": 1.3708, + "step": 5162 + }, + { + "epoch": 0.54, + "learning_rate": 1.0298266140484798e-05, + "loss": 1.3724, + "step": 5163 + }, + { + "epoch": 0.54, + "learning_rate": 1.0294607498985678e-05, + "loss": 1.3208, + "step": 5164 + }, + { + "epoch": 0.54, + "learning_rate": 1.0290948818016722e-05, + "loss": 1.3379, + "step": 5165 + }, + { + "epoch": 0.54, + "learning_rate": 1.0287290098068099e-05, + "loss": 1.3236, + "step": 5166 + }, + { + "epoch": 0.54, + "learning_rate": 1.0283631339629982e-05, + "loss": 1.3437, + "step": 5167 + }, + { + "epoch": 0.54, + "learning_rate": 1.0279972543192561e-05, + "loss": 1.3381, + "step": 5168 + }, + { + "epoch": 0.54, + "learning_rate": 1.0276313709246007e-05, + "loss": 1.4287, + "step": 5169 + }, + { + "epoch": 0.54, + "learning_rate": 1.0272654838280515e-05, + "loss": 1.3587, + "step": 5170 + }, + { + "epoch": 0.54, + "learning_rate": 1.0268995930786283e-05, + "loss": 1.2982, + "step": 5171 + }, + { + "epoch": 0.54, + "learning_rate": 1.0265336987253509e-05, + "loss": 1.3416, + "step": 5172 + }, + { + "epoch": 0.54, + "learning_rate": 1.0261678008172393e-05, + "loss": 1.3827, + "step": 5173 + }, + { + "epoch": 0.54, + "learning_rate": 1.025801899403315e-05, + "loss": 1.3293, + "step": 5174 + }, + { + "epoch": 0.54, + "eval_loss": 1.4264723062515259, + "eval_runtime": 77.4376, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 5174 + }, + { + "epoch": 0.54, + "learning_rate": 1.0254359945325987e-05, + "loss": 1.3811, + "step": 5175 + }, + { + "epoch": 0.54, + "learning_rate": 1.0250700862541135e-05, + "loss": 1.3423, + "step": 5176 + }, + { + "epoch": 0.54, + "learning_rate": 1.02470417461688e-05, + "loss": 1.3641, + "step": 5177 + }, + { + "epoch": 0.54, + "learning_rate": 1.0243382596699226e-05, + "loss": 1.3211, + "step": 5178 + }, + { + "epoch": 0.54, + "learning_rate": 1.023972341462263e-05, + "loss": 1.4008, + "step": 5179 + }, + { + "epoch": 0.54, + "learning_rate": 1.0236064200429263e-05, + "loss": 1.404, + "step": 5180 + }, + { + "epoch": 0.54, + "learning_rate": 1.0232404954609353e-05, + "loss": 1.3359, + "step": 5181 + }, + { + "epoch": 0.54, + "learning_rate": 1.0228745677653155e-05, + "loss": 1.4069, + "step": 5182 + }, + { + "epoch": 0.54, + "learning_rate": 1.0225086370050914e-05, + "loss": 1.3343, + "step": 5183 + }, + { + "epoch": 0.54, + "learning_rate": 1.0221427032292881e-05, + "loss": 1.3109, + "step": 5184 + }, + { + "epoch": 0.54, + "learning_rate": 1.0217767664869312e-05, + "loss": 1.3611, + "step": 5185 + }, + { + "epoch": 0.54, + "learning_rate": 1.0214108268270476e-05, + "loss": 1.4072, + "step": 5186 + }, + { + "epoch": 0.54, + "learning_rate": 1.0210448842986631e-05, + "loss": 1.3602, + "step": 5187 + }, + { + "epoch": 0.54, + "learning_rate": 1.0206789389508047e-05, + "loss": 1.413, + "step": 5188 + }, + { + "epoch": 0.54, + "learning_rate": 1.0203129908325e-05, + "loss": 1.3209, + "step": 5189 + }, + { + "epoch": 0.54, + "learning_rate": 1.0199470399927764e-05, + "loss": 1.3714, + "step": 5190 + }, + { + "epoch": 0.54, + "learning_rate": 1.0195810864806623e-05, + "loss": 1.3556, + "step": 5191 + }, + { + "epoch": 0.54, + "learning_rate": 1.0192151303451852e-05, + "loss": 1.4116, + "step": 5192 + }, + { + "epoch": 0.54, + "learning_rate": 1.0188491716353745e-05, + "loss": 1.4102, + "step": 5193 + }, + { + "epoch": 0.54, + "learning_rate": 1.0184832104002592e-05, + "loss": 1.4849, + "step": 5194 + }, + { + "epoch": 0.54, + "learning_rate": 1.0181172466888689e-05, + "loss": 1.5395, + "step": 5195 + }, + { + "epoch": 0.54, + "learning_rate": 1.0177512805502325e-05, + "loss": 1.3627, + "step": 5196 + }, + { + "epoch": 0.54, + "learning_rate": 1.017385312033381e-05, + "loss": 1.4152, + "step": 5197 + }, + { + "epoch": 0.55, + "learning_rate": 1.0170193411873442e-05, + "loss": 1.3641, + "step": 5198 + }, + { + "epoch": 0.55, + "learning_rate": 1.0166533680611533e-05, + "loss": 1.3074, + "step": 5199 + }, + { + "epoch": 0.55, + "learning_rate": 1.0162873927038386e-05, + "loss": 1.35, + "step": 5200 + }, + { + "epoch": 0.55, + "learning_rate": 1.015921415164432e-05, + "loss": 1.3551, + "step": 5201 + }, + { + "epoch": 0.55, + "learning_rate": 1.0155554354919643e-05, + "loss": 1.3421, + "step": 5202 + }, + { + "epoch": 0.55, + "learning_rate": 1.0151894537354687e-05, + "loss": 1.4132, + "step": 5203 + }, + { + "epoch": 0.55, + "learning_rate": 1.0148234699439764e-05, + "loss": 1.351, + "step": 5204 + }, + { + "epoch": 0.55, + "learning_rate": 1.0144574841665198e-05, + "loss": 1.3745, + "step": 5205 + }, + { + "epoch": 0.55, + "learning_rate": 1.0140914964521316e-05, + "loss": 1.3151, + "step": 5206 + }, + { + "epoch": 0.55, + "learning_rate": 1.0137255068498456e-05, + "loss": 1.4903, + "step": 5207 + }, + { + "epoch": 0.55, + "learning_rate": 1.0133595154086937e-05, + "loss": 1.3945, + "step": 5208 + }, + { + "epoch": 0.55, + "learning_rate": 1.0129935221777104e-05, + "loss": 1.3924, + "step": 5209 + }, + { + "epoch": 0.55, + "learning_rate": 1.0126275272059286e-05, + "loss": 1.4191, + "step": 5210 + }, + { + "epoch": 0.55, + "learning_rate": 1.012261530542383e-05, + "loss": 1.3408, + "step": 5211 + }, + { + "epoch": 0.55, + "learning_rate": 1.0118955322361071e-05, + "loss": 1.3582, + "step": 5212 + }, + { + "epoch": 0.55, + "learning_rate": 1.0115295323361354e-05, + "loss": 1.3703, + "step": 5213 + }, + { + "epoch": 0.55, + "learning_rate": 1.011163530891503e-05, + "loss": 1.4181, + "step": 5214 + }, + { + "epoch": 0.55, + "learning_rate": 1.0107975279512442e-05, + "loss": 1.5019, + "step": 5215 + }, + { + "epoch": 0.55, + "learning_rate": 1.010431523564394e-05, + "loss": 1.3151, + "step": 5216 + }, + { + "epoch": 0.55, + "learning_rate": 1.0100655177799874e-05, + "loss": 1.4036, + "step": 5217 + }, + { + "epoch": 0.55, + "learning_rate": 1.0096995106470606e-05, + "loss": 1.3584, + "step": 5218 + }, + { + "epoch": 0.55, + "learning_rate": 1.0093335022146482e-05, + "loss": 1.3618, + "step": 5219 + }, + { + "epoch": 0.55, + "learning_rate": 1.0089674925317865e-05, + "loss": 1.3295, + "step": 5220 + }, + { + "epoch": 0.55, + "learning_rate": 1.0086014816475108e-05, + "loss": 1.3968, + "step": 5221 + }, + { + "epoch": 0.55, + "learning_rate": 1.0082354696108586e-05, + "loss": 1.2847, + "step": 5222 + }, + { + "epoch": 0.55, + "learning_rate": 1.007869456470864e-05, + "loss": 1.4461, + "step": 5223 + }, + { + "epoch": 0.55, + "learning_rate": 1.007503442276565e-05, + "loss": 1.3813, + "step": 5224 + }, + { + "epoch": 0.55, + "learning_rate": 1.007137427076997e-05, + "loss": 1.3833, + "step": 5225 + }, + { + "epoch": 0.55, + "learning_rate": 1.006771410921198e-05, + "loss": 1.4024, + "step": 5226 + }, + { + "epoch": 0.55, + "learning_rate": 1.0064053938582032e-05, + "loss": 1.3357, + "step": 5227 + }, + { + "epoch": 0.55, + "learning_rate": 1.0060393759370506e-05, + "loss": 1.35, + "step": 5228 + }, + { + "epoch": 0.55, + "learning_rate": 1.0056733572067765e-05, + "loss": 1.3512, + "step": 5229 + }, + { + "epoch": 0.55, + "learning_rate": 1.0053073377164186e-05, + "loss": 1.3852, + "step": 5230 + }, + { + "epoch": 0.55, + "learning_rate": 1.0049413175150135e-05, + "loss": 1.3502, + "step": 5231 + }, + { + "epoch": 0.55, + "learning_rate": 1.004575296651599e-05, + "loss": 1.4637, + "step": 5232 + }, + { + "epoch": 0.55, + "learning_rate": 1.0042092751752123e-05, + "loss": 1.3877, + "step": 5233 + }, + { + "epoch": 0.55, + "learning_rate": 1.0038432531348909e-05, + "loss": 1.3804, + "step": 5234 + }, + { + "epoch": 0.55, + "learning_rate": 1.0034772305796723e-05, + "loss": 1.3613, + "step": 5235 + }, + { + "epoch": 0.55, + "learning_rate": 1.003111207558594e-05, + "loss": 1.3218, + "step": 5236 + }, + { + "epoch": 0.55, + "learning_rate": 1.0027451841206944e-05, + "loss": 1.3554, + "step": 5237 + }, + { + "epoch": 0.55, + "learning_rate": 1.0023791603150099e-05, + "loss": 1.372, + "step": 5238 + }, + { + "epoch": 0.55, + "learning_rate": 1.0020131361905793e-05, + "loss": 1.3544, + "step": 5239 + }, + { + "epoch": 0.55, + "learning_rate": 1.0016471117964404e-05, + "loss": 1.3472, + "step": 5240 + }, + { + "epoch": 0.55, + "learning_rate": 1.001281087181631e-05, + "loss": 1.4247, + "step": 5241 + }, + { + "epoch": 0.55, + "learning_rate": 1.0009150623951883e-05, + "loss": 1.2685, + "step": 5242 + }, + { + "epoch": 0.55, + "learning_rate": 1.000549037486151e-05, + "loss": 1.4036, + "step": 5243 + }, + { + "epoch": 0.55, + "learning_rate": 1.0001830125035565e-05, + "loss": 1.3602, + "step": 5244 + }, + { + "epoch": 0.55, + "learning_rate": 9.998169874964437e-06, + "loss": 1.3784, + "step": 5245 + }, + { + "epoch": 0.55, + "learning_rate": 9.994509625138496e-06, + "loss": 1.3389, + "step": 5246 + }, + { + "epoch": 0.55, + "learning_rate": 9.990849376048119e-06, + "loss": 1.4561, + "step": 5247 + }, + { + "epoch": 0.55, + "learning_rate": 9.987189128183695e-06, + "loss": 1.3876, + "step": 5248 + }, + { + "epoch": 0.55, + "learning_rate": 9.9835288820356e-06, + "loss": 1.3362, + "step": 5249 + }, + { + "epoch": 0.55, + "learning_rate": 9.97986863809421e-06, + "loss": 1.3449, + "step": 5250 + }, + { + "epoch": 0.55, + "learning_rate": 9.9762083968499e-06, + "loss": 1.3521, + "step": 5251 + }, + { + "epoch": 0.55, + "learning_rate": 9.972548158793061e-06, + "loss": 1.4452, + "step": 5252 + }, + { + "epoch": 0.55, + "learning_rate": 9.968887924414062e-06, + "loss": 1.4126, + "step": 5253 + }, + { + "epoch": 0.55, + "learning_rate": 9.965227694203282e-06, + "loss": 1.3054, + "step": 5254 + }, + { + "epoch": 0.55, + "learning_rate": 9.961567468651093e-06, + "loss": 1.3771, + "step": 5255 + }, + { + "epoch": 0.55, + "learning_rate": 9.957907248247878e-06, + "loss": 1.3566, + "step": 5256 + }, + { + "epoch": 0.55, + "learning_rate": 9.954247033484014e-06, + "loss": 1.4765, + "step": 5257 + }, + { + "epoch": 0.55, + "learning_rate": 9.950586824849865e-06, + "loss": 1.4749, + "step": 5258 + }, + { + "epoch": 0.55, + "learning_rate": 9.946926622835815e-06, + "loss": 1.3679, + "step": 5259 + }, + { + "epoch": 0.55, + "learning_rate": 9.943266427932238e-06, + "loss": 1.2671, + "step": 5260 + }, + { + "epoch": 0.55, + "learning_rate": 9.9396062406295e-06, + "loss": 1.3485, + "step": 5261 + }, + { + "epoch": 0.55, + "learning_rate": 9.935946061417968e-06, + "loss": 1.3136, + "step": 5262 + }, + { + "epoch": 0.55, + "learning_rate": 9.932285890788024e-06, + "loss": 1.3954, + "step": 5263 + }, + { + "epoch": 0.55, + "learning_rate": 9.928625729230031e-06, + "loss": 1.428, + "step": 5264 + }, + { + "epoch": 0.55, + "learning_rate": 9.924965577234356e-06, + "loss": 1.4144, + "step": 5265 + }, + { + "epoch": 0.55, + "learning_rate": 9.92130543529136e-06, + "loss": 1.3361, + "step": 5266 + }, + { + "epoch": 0.55, + "learning_rate": 9.91764530389142e-06, + "loss": 1.4503, + "step": 5267 + }, + { + "epoch": 0.55, + "learning_rate": 9.913985183524893e-06, + "loss": 1.3431, + "step": 5268 + }, + { + "epoch": 0.55, + "learning_rate": 9.91032507468214e-06, + "loss": 1.3206, + "step": 5269 + }, + { + "epoch": 0.55, + "learning_rate": 9.906664977853518e-06, + "loss": 1.4568, + "step": 5270 + }, + { + "epoch": 0.55, + "learning_rate": 9.903004893529397e-06, + "loss": 1.3591, + "step": 5271 + }, + { + "epoch": 0.55, + "learning_rate": 9.899344822200127e-06, + "loss": 1.3382, + "step": 5272 + }, + { + "epoch": 0.55, + "learning_rate": 9.895684764356066e-06, + "loss": 1.3008, + "step": 5273 + }, + { + "epoch": 0.55, + "learning_rate": 9.89202472048756e-06, + "loss": 1.316, + "step": 5274 + }, + { + "epoch": 0.55, + "learning_rate": 9.888364691084971e-06, + "loss": 1.4246, + "step": 5275 + }, + { + "epoch": 0.55, + "learning_rate": 9.88470467663865e-06, + "loss": 1.3615, + "step": 5276 + }, + { + "epoch": 0.55, + "learning_rate": 9.881044677638934e-06, + "loss": 1.3418, + "step": 5277 + }, + { + "epoch": 0.55, + "learning_rate": 9.877384694576172e-06, + "loss": 1.249, + "step": 5278 + }, + { + "epoch": 0.55, + "learning_rate": 9.873724727940715e-06, + "loss": 1.2779, + "step": 5279 + }, + { + "epoch": 0.55, + "learning_rate": 9.870064778222903e-06, + "loss": 1.3529, + "step": 5280 + }, + { + "epoch": 0.55, + "learning_rate": 9.866404845913065e-06, + "loss": 1.3204, + "step": 5281 + }, + { + "epoch": 0.55, + "learning_rate": 9.862744931501548e-06, + "loss": 1.3537, + "step": 5282 + }, + { + "epoch": 0.55, + "learning_rate": 9.859085035478687e-06, + "loss": 1.3681, + "step": 5283 + }, + { + "epoch": 0.55, + "learning_rate": 9.855425158334809e-06, + "loss": 1.3983, + "step": 5284 + }, + { + "epoch": 0.55, + "learning_rate": 9.851765300560238e-06, + "loss": 1.401, + "step": 5285 + }, + { + "epoch": 0.55, + "learning_rate": 9.848105462645315e-06, + "loss": 1.3073, + "step": 5286 + }, + { + "epoch": 0.55, + "learning_rate": 9.844445645080358e-06, + "loss": 1.3162, + "step": 5287 + }, + { + "epoch": 0.55, + "learning_rate": 9.840785848355685e-06, + "loss": 1.3345, + "step": 5288 + }, + { + "epoch": 0.55, + "learning_rate": 9.837126072961616e-06, + "loss": 1.4241, + "step": 5289 + }, + { + "epoch": 0.55, + "learning_rate": 9.83346631938847e-06, + "loss": 1.3339, + "step": 5290 + }, + { + "epoch": 0.55, + "learning_rate": 9.829806588126561e-06, + "loss": 1.3507, + "step": 5291 + }, + { + "epoch": 0.55, + "learning_rate": 9.826146879666196e-06, + "loss": 1.2806, + "step": 5292 + }, + { + "epoch": 0.56, + "learning_rate": 9.822487194497675e-06, + "loss": 1.3952, + "step": 5293 + }, + { + "epoch": 0.56, + "learning_rate": 9.818827533111314e-06, + "loss": 1.3319, + "step": 5294 + }, + { + "epoch": 0.56, + "learning_rate": 9.81516789599741e-06, + "loss": 1.351, + "step": 5295 + }, + { + "epoch": 0.56, + "learning_rate": 9.811508283646258e-06, + "loss": 1.4076, + "step": 5296 + }, + { + "epoch": 0.56, + "learning_rate": 9.80784869654815e-06, + "loss": 1.3271, + "step": 5297 + }, + { + "epoch": 0.56, + "learning_rate": 9.80418913519338e-06, + "loss": 1.4059, + "step": 5298 + }, + { + "epoch": 0.56, + "learning_rate": 9.80052960007224e-06, + "loss": 1.4146, + "step": 5299 + }, + { + "epoch": 0.56, + "learning_rate": 9.796870091675005e-06, + "loss": 1.3454, + "step": 5300 + }, + { + "epoch": 0.56, + "learning_rate": 9.793210610491953e-06, + "loss": 1.4376, + "step": 5301 + }, + { + "epoch": 0.56, + "learning_rate": 9.789551157013372e-06, + "loss": 1.3437, + "step": 5302 + }, + { + "epoch": 0.56, + "learning_rate": 9.78589173172953e-06, + "loss": 1.3073, + "step": 5303 + }, + { + "epoch": 0.56, + "learning_rate": 9.782232335130688e-06, + "loss": 1.2989, + "step": 5304 + }, + { + "epoch": 0.56, + "learning_rate": 9.778572967707122e-06, + "loss": 1.4028, + "step": 5305 + }, + { + "epoch": 0.56, + "learning_rate": 9.77491362994909e-06, + "loss": 1.3096, + "step": 5306 + }, + { + "epoch": 0.56, + "learning_rate": 9.77125432234685e-06, + "loss": 1.3719, + "step": 5307 + }, + { + "epoch": 0.56, + "learning_rate": 9.767595045390647e-06, + "loss": 1.3271, + "step": 5308 + }, + { + "epoch": 0.56, + "learning_rate": 9.763935799570739e-06, + "loss": 1.3693, + "step": 5309 + }, + { + "epoch": 0.56, + "learning_rate": 9.760276585377371e-06, + "loss": 1.3586, + "step": 5310 + }, + { + "epoch": 0.56, + "learning_rate": 9.756617403300781e-06, + "loss": 1.3423, + "step": 5311 + }, + { + "epoch": 0.56, + "learning_rate": 9.7529582538312e-06, + "loss": 1.388, + "step": 5312 + }, + { + "epoch": 0.56, + "learning_rate": 9.74929913745887e-06, + "loss": 1.3594, + "step": 5313 + }, + { + "epoch": 0.56, + "learning_rate": 9.745640054674015e-06, + "loss": 1.2831, + "step": 5314 + }, + { + "epoch": 0.56, + "learning_rate": 9.741981005966856e-06, + "loss": 1.4207, + "step": 5315 + }, + { + "epoch": 0.56, + "learning_rate": 9.738321991827609e-06, + "loss": 1.2807, + "step": 5316 + }, + { + "epoch": 0.56, + "learning_rate": 9.734663012746493e-06, + "loss": 1.3396, + "step": 5317 + }, + { + "epoch": 0.56, + "learning_rate": 9.731004069213722e-06, + "loss": 1.3666, + "step": 5318 + }, + { + "epoch": 0.56, + "learning_rate": 9.72734516171949e-06, + "loss": 1.3466, + "step": 5319 + }, + { + "epoch": 0.56, + "learning_rate": 9.723686290753995e-06, + "loss": 1.4478, + "step": 5320 + }, + { + "epoch": 0.56, + "learning_rate": 9.720027456807442e-06, + "loss": 1.316, + "step": 5321 + }, + { + "epoch": 0.56, + "learning_rate": 9.71636866037002e-06, + "loss": 1.3762, + "step": 5322 + }, + { + "epoch": 0.56, + "learning_rate": 9.712709901931906e-06, + "loss": 1.4156, + "step": 5323 + }, + { + "epoch": 0.56, + "learning_rate": 9.70905118198328e-06, + "loss": 1.2452, + "step": 5324 + }, + { + "epoch": 0.56, + "learning_rate": 9.705392501014325e-06, + "loss": 1.3771, + "step": 5325 + }, + { + "epoch": 0.56, + "learning_rate": 9.701733859515205e-06, + "loss": 1.3433, + "step": 5326 + }, + { + "epoch": 0.56, + "learning_rate": 9.698075257976079e-06, + "loss": 1.3702, + "step": 5327 + }, + { + "epoch": 0.56, + "learning_rate": 9.694416696887115e-06, + "loss": 1.295, + "step": 5328 + }, + { + "epoch": 0.56, + "learning_rate": 9.690758176738463e-06, + "loss": 1.3462, + "step": 5329 + }, + { + "epoch": 0.56, + "learning_rate": 9.68709969802027e-06, + "loss": 1.5304, + "step": 5330 + }, + { + "epoch": 0.56, + "learning_rate": 9.683441261222672e-06, + "loss": 1.3518, + "step": 5331 + }, + { + "epoch": 0.56, + "learning_rate": 9.679782866835816e-06, + "loss": 1.3778, + "step": 5332 + }, + { + "epoch": 0.56, + "learning_rate": 9.67612451534983e-06, + "loss": 1.3731, + "step": 5333 + }, + { + "epoch": 0.56, + "learning_rate": 9.672466207254837e-06, + "loss": 1.3315, + "step": 5334 + }, + { + "epoch": 0.56, + "learning_rate": 9.66880794304095e-06, + "loss": 1.3105, + "step": 5335 + }, + { + "epoch": 0.56, + "learning_rate": 9.665149723198293e-06, + "loss": 1.3903, + "step": 5336 + }, + { + "epoch": 0.56, + "learning_rate": 9.661491548216972e-06, + "loss": 1.3554, + "step": 5337 + }, + { + "epoch": 0.56, + "learning_rate": 9.657833418587084e-06, + "loss": 1.3231, + "step": 5338 + }, + { + "epoch": 0.56, + "learning_rate": 9.65417533479872e-06, + "loss": 1.352, + "step": 5339 + }, + { + "epoch": 0.56, + "learning_rate": 9.650517297341983e-06, + "loss": 1.3957, + "step": 5340 + }, + { + "epoch": 0.56, + "learning_rate": 9.646859306706948e-06, + "loss": 1.3938, + "step": 5341 + }, + { + "epoch": 0.56, + "learning_rate": 9.643201363383693e-06, + "loss": 1.3038, + "step": 5342 + }, + { + "epoch": 0.56, + "learning_rate": 9.63954346786228e-06, + "loss": 1.2973, + "step": 5343 + }, + { + "epoch": 0.56, + "learning_rate": 9.635885620632786e-06, + "loss": 1.379, + "step": 5344 + }, + { + "epoch": 0.56, + "learning_rate": 9.632227822185266e-06, + "loss": 1.5377, + "step": 5345 + }, + { + "epoch": 0.56, + "learning_rate": 9.628570073009767e-06, + "loss": 1.4573, + "step": 5346 + }, + { + "epoch": 0.56, + "learning_rate": 9.624912373596329e-06, + "loss": 1.3394, + "step": 5347 + }, + { + "epoch": 0.56, + "learning_rate": 9.621254724434999e-06, + "loss": 1.4157, + "step": 5348 + }, + { + "epoch": 0.56, + "learning_rate": 9.617597126015808e-06, + "loss": 1.3526, + "step": 5349 + }, + { + "epoch": 0.56, + "learning_rate": 9.61393957882877e-06, + "loss": 1.3795, + "step": 5350 + }, + { + "epoch": 0.56, + "learning_rate": 9.610282083363913e-06, + "loss": 1.3765, + "step": 5351 + }, + { + "epoch": 0.56, + "learning_rate": 9.606624640111243e-06, + "loss": 1.3512, + "step": 5352 + }, + { + "epoch": 0.56, + "learning_rate": 9.602967249560766e-06, + "loss": 1.3298, + "step": 5353 + }, + { + "epoch": 0.56, + "learning_rate": 9.599309912202469e-06, + "loss": 1.3093, + "step": 5354 + }, + { + "epoch": 0.56, + "learning_rate": 9.595652628526354e-06, + "loss": 1.3353, + "step": 5355 + }, + { + "epoch": 0.56, + "learning_rate": 9.591995399022397e-06, + "loss": 1.3081, + "step": 5356 + }, + { + "epoch": 0.56, + "learning_rate": 9.588338224180576e-06, + "loss": 1.343, + "step": 5357 + }, + { + "epoch": 0.56, + "learning_rate": 9.584681104490848e-06, + "loss": 1.3275, + "step": 5358 + }, + { + "epoch": 0.56, + "learning_rate": 9.581024040443185e-06, + "loss": 1.3399, + "step": 5359 + }, + { + "epoch": 0.56, + "learning_rate": 9.577367032527538e-06, + "loss": 1.3181, + "step": 5360 + }, + { + "epoch": 0.56, + "learning_rate": 9.573710081233846e-06, + "loss": 1.3531, + "step": 5361 + }, + { + "epoch": 0.56, + "learning_rate": 9.570053187052049e-06, + "loss": 1.4056, + "step": 5362 + }, + { + "epoch": 0.56, + "learning_rate": 9.566396350472079e-06, + "loss": 1.3303, + "step": 5363 + }, + { + "epoch": 0.56, + "learning_rate": 9.56273957198386e-06, + "loss": 1.3506, + "step": 5364 + }, + { + "epoch": 0.56, + "learning_rate": 9.559082852077302e-06, + "loss": 1.4588, + "step": 5365 + }, + { + "epoch": 0.56, + "learning_rate": 9.555426191242307e-06, + "loss": 1.3434, + "step": 5366 + }, + { + "epoch": 0.56, + "learning_rate": 9.551769589968784e-06, + "loss": 1.3508, + "step": 5367 + }, + { + "epoch": 0.56, + "learning_rate": 9.548113048746622e-06, + "loss": 1.3701, + "step": 5368 + }, + { + "epoch": 0.56, + "learning_rate": 9.544456568065698e-06, + "loss": 1.3664, + "step": 5369 + }, + { + "epoch": 0.56, + "learning_rate": 9.540800148415885e-06, + "loss": 1.6697, + "step": 5370 + }, + { + "epoch": 0.56, + "learning_rate": 9.537143790287057e-06, + "loss": 1.5298, + "step": 5371 + }, + { + "epoch": 0.56, + "learning_rate": 9.533487494169073e-06, + "loss": 1.3884, + "step": 5372 + }, + { + "epoch": 0.56, + "learning_rate": 9.52983126055177e-06, + "loss": 1.403, + "step": 5373 + }, + { + "epoch": 0.56, + "eval_loss": 1.4240995645523071, + "eval_runtime": 77.4615, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 5373 + }, + { + "epoch": 0.56, + "learning_rate": 9.526175089925e-06, + "loss": 1.3141, + "step": 5374 + }, + { + "epoch": 0.56, + "learning_rate": 9.522518982778596e-06, + "loss": 1.3733, + "step": 5375 + }, + { + "epoch": 0.56, + "learning_rate": 9.51886293960238e-06, + "loss": 1.3095, + "step": 5376 + }, + { + "epoch": 0.56, + "learning_rate": 9.515206960886162e-06, + "loss": 1.3713, + "step": 5377 + }, + { + "epoch": 0.56, + "learning_rate": 9.51155104711976e-06, + "loss": 1.3585, + "step": 5378 + }, + { + "epoch": 0.56, + "learning_rate": 9.507895198792967e-06, + "loss": 1.3473, + "step": 5379 + }, + { + "epoch": 0.56, + "learning_rate": 9.504239416395576e-06, + "loss": 1.3282, + "step": 5380 + }, + { + "epoch": 0.56, + "learning_rate": 9.500583700417357e-06, + "loss": 1.3655, + "step": 5381 + }, + { + "epoch": 0.56, + "learning_rate": 9.496928051348095e-06, + "loss": 1.4512, + "step": 5382 + }, + { + "epoch": 0.56, + "learning_rate": 9.49327246967755e-06, + "loss": 1.4071, + "step": 5383 + }, + { + "epoch": 0.56, + "learning_rate": 9.489616955895472e-06, + "loss": 1.3703, + "step": 5384 + }, + { + "epoch": 0.56, + "learning_rate": 9.485961510491604e-06, + "loss": 1.3358, + "step": 5385 + }, + { + "epoch": 0.56, + "learning_rate": 9.482306133955691e-06, + "loss": 1.3505, + "step": 5386 + }, + { + "epoch": 0.56, + "learning_rate": 9.478650826777457e-06, + "loss": 1.2578, + "step": 5387 + }, + { + "epoch": 0.57, + "learning_rate": 9.474995589446612e-06, + "loss": 1.4298, + "step": 5388 + }, + { + "epoch": 0.57, + "learning_rate": 9.471340422452864e-06, + "loss": 1.4044, + "step": 5389 + }, + { + "epoch": 0.57, + "learning_rate": 9.467685326285922e-06, + "loss": 1.3524, + "step": 5390 + }, + { + "epoch": 0.57, + "learning_rate": 9.46403030143547e-06, + "loss": 1.3017, + "step": 5391 + }, + { + "epoch": 0.57, + "learning_rate": 9.460375348391185e-06, + "loss": 1.3361, + "step": 5392 + }, + { + "epoch": 0.57, + "learning_rate": 9.456720467642733e-06, + "loss": 1.3182, + "step": 5393 + }, + { + "epoch": 0.57, + "learning_rate": 9.453065659679785e-06, + "loss": 1.3869, + "step": 5394 + }, + { + "epoch": 0.57, + "learning_rate": 9.449410924991986e-06, + "loss": 1.3161, + "step": 5395 + }, + { + "epoch": 0.57, + "learning_rate": 9.44575626406897e-06, + "loss": 1.3, + "step": 5396 + }, + { + "epoch": 0.57, + "learning_rate": 9.442101677400378e-06, + "loss": 1.5103, + "step": 5397 + }, + { + "epoch": 0.57, + "learning_rate": 9.438447165475828e-06, + "loss": 1.3511, + "step": 5398 + }, + { + "epoch": 0.57, + "learning_rate": 9.43479272878493e-06, + "loss": 1.3461, + "step": 5399 + }, + { + "epoch": 0.57, + "learning_rate": 9.431138367817277e-06, + "loss": 1.2657, + "step": 5400 + }, + { + "epoch": 0.57, + "learning_rate": 9.427484083062472e-06, + "loss": 1.3736, + "step": 5401 + }, + { + "epoch": 0.57, + "learning_rate": 9.423829875010089e-06, + "loss": 1.3476, + "step": 5402 + }, + { + "epoch": 0.57, + "learning_rate": 9.4201757441497e-06, + "loss": 1.3495, + "step": 5403 + }, + { + "epoch": 0.57, + "learning_rate": 9.416521690970857e-06, + "loss": 1.387, + "step": 5404 + }, + { + "epoch": 0.57, + "learning_rate": 9.41286771596312e-06, + "loss": 1.2829, + "step": 5405 + }, + { + "epoch": 0.57, + "learning_rate": 9.409213819616022e-06, + "loss": 1.3544, + "step": 5406 + }, + { + "epoch": 0.57, + "learning_rate": 9.405560002419098e-06, + "loss": 1.3202, + "step": 5407 + }, + { + "epoch": 0.57, + "learning_rate": 9.40190626486185e-06, + "loss": 1.3034, + "step": 5408 + }, + { + "epoch": 0.57, + "learning_rate": 9.398252607433801e-06, + "loss": 1.3223, + "step": 5409 + }, + { + "epoch": 0.57, + "learning_rate": 9.394599030624443e-06, + "loss": 1.3327, + "step": 5410 + }, + { + "epoch": 0.57, + "learning_rate": 9.390945534923258e-06, + "loss": 1.3248, + "step": 5411 + }, + { + "epoch": 0.57, + "learning_rate": 9.387292120819716e-06, + "loss": 1.3084, + "step": 5412 + }, + { + "epoch": 0.57, + "learning_rate": 9.383638788803291e-06, + "loss": 1.344, + "step": 5413 + }, + { + "epoch": 0.57, + "learning_rate": 9.379985539363436e-06, + "loss": 1.3354, + "step": 5414 + }, + { + "epoch": 0.57, + "learning_rate": 9.376332372989586e-06, + "loss": 1.3291, + "step": 5415 + }, + { + "epoch": 0.57, + "learning_rate": 9.372679290171167e-06, + "loss": 1.3468, + "step": 5416 + }, + { + "epoch": 0.57, + "learning_rate": 9.36902629139761e-06, + "loss": 1.3481, + "step": 5417 + }, + { + "epoch": 0.57, + "learning_rate": 9.36537337715832e-06, + "loss": 1.3309, + "step": 5418 + }, + { + "epoch": 0.57, + "learning_rate": 9.361720547942683e-06, + "loss": 1.362, + "step": 5419 + }, + { + "epoch": 0.57, + "learning_rate": 9.358067804240098e-06, + "loss": 1.3647, + "step": 5420 + }, + { + "epoch": 0.57, + "learning_rate": 9.354415146539933e-06, + "loss": 1.4511, + "step": 5421 + }, + { + "epoch": 0.57, + "learning_rate": 9.350762575331554e-06, + "loss": 1.3379, + "step": 5422 + }, + { + "epoch": 0.57, + "learning_rate": 9.3471100911043e-06, + "loss": 1.5468, + "step": 5423 + }, + { + "epoch": 0.57, + "learning_rate": 9.343457694347524e-06, + "loss": 1.4259, + "step": 5424 + }, + { + "epoch": 0.57, + "learning_rate": 9.339805385550548e-06, + "loss": 1.3816, + "step": 5425 + }, + { + "epoch": 0.57, + "learning_rate": 9.336153165202689e-06, + "loss": 1.3627, + "step": 5426 + }, + { + "epoch": 0.57, + "learning_rate": 9.332501033793242e-06, + "loss": 1.3338, + "step": 5427 + }, + { + "epoch": 0.57, + "learning_rate": 9.328848991811509e-06, + "loss": 1.2946, + "step": 5428 + }, + { + "epoch": 0.57, + "learning_rate": 9.325197039746769e-06, + "loss": 1.3405, + "step": 5429 + }, + { + "epoch": 0.57, + "learning_rate": 9.321545178088288e-06, + "loss": 1.3549, + "step": 5430 + }, + { + "epoch": 0.57, + "learning_rate": 9.317893407325314e-06, + "loss": 1.3225, + "step": 5431 + }, + { + "epoch": 0.57, + "learning_rate": 9.314241727947101e-06, + "loss": 1.3457, + "step": 5432 + }, + { + "epoch": 0.57, + "learning_rate": 9.310590140442878e-06, + "loss": 1.311, + "step": 5433 + }, + { + "epoch": 0.57, + "learning_rate": 9.306938645301862e-06, + "loss": 1.3615, + "step": 5434 + }, + { + "epoch": 0.57, + "learning_rate": 9.303287243013255e-06, + "loss": 1.3495, + "step": 5435 + }, + { + "epoch": 0.57, + "learning_rate": 9.29963593406626e-06, + "loss": 1.3899, + "step": 5436 + }, + { + "epoch": 0.57, + "learning_rate": 9.295984718950058e-06, + "loss": 1.3189, + "step": 5437 + }, + { + "epoch": 0.57, + "learning_rate": 9.292333598153813e-06, + "loss": 1.4199, + "step": 5438 + }, + { + "epoch": 0.57, + "learning_rate": 9.288682572166677e-06, + "loss": 1.4751, + "step": 5439 + }, + { + "epoch": 0.57, + "learning_rate": 9.285031641477804e-06, + "loss": 1.3435, + "step": 5440 + }, + { + "epoch": 0.57, + "learning_rate": 9.281380806576322e-06, + "loss": 1.2954, + "step": 5441 + }, + { + "epoch": 0.57, + "learning_rate": 9.277730067951341e-06, + "loss": 1.3414, + "step": 5442 + }, + { + "epoch": 0.57, + "learning_rate": 9.274079426091978e-06, + "loss": 1.3642, + "step": 5443 + }, + { + "epoch": 0.57, + "learning_rate": 9.27042888148732e-06, + "loss": 1.3651, + "step": 5444 + }, + { + "epoch": 0.57, + "learning_rate": 9.266778434626448e-06, + "loss": 1.3995, + "step": 5445 + }, + { + "epoch": 0.57, + "learning_rate": 9.263128085998421e-06, + "loss": 1.2692, + "step": 5446 + }, + { + "epoch": 0.57, + "learning_rate": 9.2594778360923e-06, + "loss": 1.4355, + "step": 5447 + }, + { + "epoch": 0.57, + "learning_rate": 9.255827685397124e-06, + "loss": 1.4262, + "step": 5448 + }, + { + "epoch": 0.57, + "learning_rate": 9.252177634401917e-06, + "loss": 1.3372, + "step": 5449 + }, + { + "epoch": 0.57, + "learning_rate": 9.248527683595685e-06, + "loss": 1.4603, + "step": 5450 + }, + { + "epoch": 0.57, + "learning_rate": 9.24487783346744e-06, + "loss": 1.446, + "step": 5451 + }, + { + "epoch": 0.57, + "learning_rate": 9.241228084506167e-06, + "loss": 1.4088, + "step": 5452 + }, + { + "epoch": 0.57, + "learning_rate": 9.237578437200832e-06, + "loss": 1.3074, + "step": 5453 + }, + { + "epoch": 0.57, + "learning_rate": 9.233928892040392e-06, + "loss": 1.4347, + "step": 5454 + }, + { + "epoch": 0.57, + "learning_rate": 9.230279449513802e-06, + "loss": 1.2982, + "step": 5455 + }, + { + "epoch": 0.57, + "learning_rate": 9.226630110109988e-06, + "loss": 1.2928, + "step": 5456 + }, + { + "epoch": 0.57, + "learning_rate": 9.222980874317869e-06, + "loss": 1.2849, + "step": 5457 + }, + { + "epoch": 0.57, + "learning_rate": 9.219331742626343e-06, + "loss": 1.3137, + "step": 5458 + }, + { + "epoch": 0.57, + "learning_rate": 9.215682715524309e-06, + "loss": 1.3523, + "step": 5459 + }, + { + "epoch": 0.57, + "learning_rate": 9.21203379350064e-06, + "loss": 1.381, + "step": 5460 + }, + { + "epoch": 0.57, + "learning_rate": 9.208384977044191e-06, + "loss": 1.286, + "step": 5461 + }, + { + "epoch": 0.57, + "learning_rate": 9.204736266643819e-06, + "loss": 1.3467, + "step": 5462 + }, + { + "epoch": 0.57, + "learning_rate": 9.201087662788353e-06, + "loss": 1.3582, + "step": 5463 + }, + { + "epoch": 0.57, + "learning_rate": 9.197439165966617e-06, + "loss": 1.3912, + "step": 5464 + }, + { + "epoch": 0.57, + "learning_rate": 9.193790776667402e-06, + "loss": 1.3144, + "step": 5465 + }, + { + "epoch": 0.57, + "learning_rate": 9.190142495379515e-06, + "loss": 1.3403, + "step": 5466 + }, + { + "epoch": 0.57, + "learning_rate": 9.186494322591725e-06, + "loss": 1.3253, + "step": 5467 + }, + { + "epoch": 0.57, + "learning_rate": 9.182846258792794e-06, + "loss": 1.2908, + "step": 5468 + }, + { + "epoch": 0.57, + "learning_rate": 9.179198304471463e-06, + "loss": 1.3486, + "step": 5469 + }, + { + "epoch": 0.57, + "learning_rate": 9.175550460116473e-06, + "loss": 1.3915, + "step": 5470 + }, + { + "epoch": 0.57, + "learning_rate": 9.171902726216538e-06, + "loss": 1.3441, + "step": 5471 + }, + { + "epoch": 0.57, + "learning_rate": 9.168255103260362e-06, + "loss": 1.3196, + "step": 5472 + }, + { + "epoch": 0.57, + "learning_rate": 9.164607591736627e-06, + "loss": 1.3279, + "step": 5473 + }, + { + "epoch": 0.57, + "learning_rate": 9.160960192134011e-06, + "loss": 1.2643, + "step": 5474 + }, + { + "epoch": 0.57, + "learning_rate": 9.157312904941174e-06, + "loss": 1.3327, + "step": 5475 + }, + { + "epoch": 0.57, + "learning_rate": 9.153665730646756e-06, + "loss": 1.4016, + "step": 5476 + }, + { + "epoch": 0.57, + "learning_rate": 9.150018669739378e-06, + "loss": 1.3614, + "step": 5477 + }, + { + "epoch": 0.57, + "learning_rate": 9.146371722707662e-06, + "loss": 1.3469, + "step": 5478 + }, + { + "epoch": 0.57, + "learning_rate": 9.142724890040204e-06, + "loss": 1.3625, + "step": 5479 + }, + { + "epoch": 0.57, + "learning_rate": 9.139078172225585e-06, + "loss": 1.3879, + "step": 5480 + }, + { + "epoch": 0.57, + "learning_rate": 9.135431569752362e-06, + "loss": 1.3738, + "step": 5481 + }, + { + "epoch": 0.57, + "learning_rate": 9.131785083109101e-06, + "loss": 1.3507, + "step": 5482 + }, + { + "epoch": 0.57, + "learning_rate": 9.128138712784331e-06, + "loss": 1.3681, + "step": 5483 + }, + { + "epoch": 0.58, + "learning_rate": 9.124492459266567e-06, + "loss": 1.332, + "step": 5484 + }, + { + "epoch": 0.58, + "learning_rate": 9.12084632304432e-06, + "loss": 1.4746, + "step": 5485 + }, + { + "epoch": 0.58, + "learning_rate": 9.11720030460608e-06, + "loss": 1.2775, + "step": 5486 + }, + { + "epoch": 0.58, + "learning_rate": 9.113554404440317e-06, + "loss": 1.2567, + "step": 5487 + }, + { + "epoch": 0.58, + "learning_rate": 9.10990862303548e-06, + "loss": 1.3935, + "step": 5488 + }, + { + "epoch": 0.58, + "learning_rate": 9.106262960880024e-06, + "loss": 1.3544, + "step": 5489 + }, + { + "epoch": 0.58, + "learning_rate": 9.102617418462365e-06, + "loss": 1.4023, + "step": 5490 + }, + { + "epoch": 0.58, + "learning_rate": 9.098971996270918e-06, + "loss": 1.3759, + "step": 5491 + }, + { + "epoch": 0.58, + "learning_rate": 9.095326694794064e-06, + "loss": 1.4165, + "step": 5492 + }, + { + "epoch": 0.58, + "learning_rate": 9.091681514520194e-06, + "loss": 1.3189, + "step": 5493 + }, + { + "epoch": 0.58, + "learning_rate": 9.088036455937663e-06, + "loss": 1.3135, + "step": 5494 + }, + { + "epoch": 0.58, + "learning_rate": 9.084391519534815e-06, + "loss": 1.3521, + "step": 5495 + }, + { + "epoch": 0.58, + "learning_rate": 9.080746705799971e-06, + "loss": 1.3314, + "step": 5496 + }, + { + "epoch": 0.58, + "learning_rate": 9.077102015221457e-06, + "loss": 1.3119, + "step": 5497 + }, + { + "epoch": 0.58, + "learning_rate": 9.073457448287557e-06, + "loss": 1.2895, + "step": 5498 + }, + { + "epoch": 0.58, + "learning_rate": 9.069813005486554e-06, + "loss": 1.3155, + "step": 5499 + }, + { + "epoch": 0.58, + "learning_rate": 9.066168687306701e-06, + "loss": 1.4048, + "step": 5500 + }, + { + "epoch": 0.58, + "learning_rate": 9.062524494236256e-06, + "loss": 1.3665, + "step": 5501 + }, + { + "epoch": 0.58, + "learning_rate": 9.058880426763442e-06, + "loss": 1.3258, + "step": 5502 + }, + { + "epoch": 0.58, + "learning_rate": 9.05523648537647e-06, + "loss": 1.3078, + "step": 5503 + }, + { + "epoch": 0.58, + "learning_rate": 9.051592670563527e-06, + "loss": 1.361, + "step": 5504 + }, + { + "epoch": 0.58, + "learning_rate": 9.047948982812801e-06, + "loss": 1.3557, + "step": 5505 + }, + { + "epoch": 0.58, + "learning_rate": 9.044305422612453e-06, + "loss": 1.5733, + "step": 5506 + }, + { + "epoch": 0.58, + "learning_rate": 9.040661990450617e-06, + "loss": 1.2835, + "step": 5507 + }, + { + "epoch": 0.58, + "learning_rate": 9.037018686815428e-06, + "loss": 1.311, + "step": 5508 + }, + { + "epoch": 0.58, + "learning_rate": 9.033375512194993e-06, + "loss": 1.3949, + "step": 5509 + }, + { + "epoch": 0.58, + "learning_rate": 9.029732467077405e-06, + "loss": 1.356, + "step": 5510 + }, + { + "epoch": 0.58, + "learning_rate": 9.026089551950727e-06, + "loss": 1.3695, + "step": 5511 + }, + { + "epoch": 0.58, + "learning_rate": 9.022446767303033e-06, + "loss": 1.3325, + "step": 5512 + }, + { + "epoch": 0.58, + "learning_rate": 9.018804113622353e-06, + "loss": 1.401, + "step": 5513 + }, + { + "epoch": 0.58, + "learning_rate": 9.015161591396713e-06, + "loss": 1.3632, + "step": 5514 + }, + { + "epoch": 0.58, + "learning_rate": 9.011519201114108e-06, + "loss": 1.3697, + "step": 5515 + }, + { + "epoch": 0.58, + "learning_rate": 9.007876943262538e-06, + "loss": 1.2604, + "step": 5516 + }, + { + "epoch": 0.58, + "learning_rate": 9.004234818329964e-06, + "loss": 1.3557, + "step": 5517 + }, + { + "epoch": 0.58, + "learning_rate": 9.000592826804342e-06, + "loss": 1.3248, + "step": 5518 + }, + { + "epoch": 0.58, + "learning_rate": 8.996950969173596e-06, + "loss": 1.3237, + "step": 5519 + }, + { + "epoch": 0.58, + "learning_rate": 8.99330924592565e-06, + "loss": 1.339, + "step": 5520 + }, + { + "epoch": 0.58, + "learning_rate": 8.989667657548402e-06, + "loss": 1.3218, + "step": 5521 + }, + { + "epoch": 0.58, + "learning_rate": 8.986026204529728e-06, + "loss": 1.3354, + "step": 5522 + }, + { + "epoch": 0.58, + "learning_rate": 8.982384887357484e-06, + "loss": 1.3011, + "step": 5523 + }, + { + "epoch": 0.58, + "learning_rate": 8.978743706519524e-06, + "loss": 1.3526, + "step": 5524 + }, + { + "epoch": 0.58, + "learning_rate": 8.975102662503666e-06, + "loss": 1.3298, + "step": 5525 + }, + { + "epoch": 0.58, + "learning_rate": 8.971461755797718e-06, + "loss": 1.328, + "step": 5526 + }, + { + "epoch": 0.58, + "learning_rate": 8.967820986889461e-06, + "loss": 1.3705, + "step": 5527 + }, + { + "epoch": 0.58, + "learning_rate": 8.964180356266676e-06, + "loss": 1.3814, + "step": 5528 + }, + { + "epoch": 0.58, + "learning_rate": 8.96053986441711e-06, + "loss": 1.37, + "step": 5529 + }, + { + "epoch": 0.58, + "learning_rate": 8.956899511828489e-06, + "loss": 1.3224, + "step": 5530 + }, + { + "epoch": 0.58, + "learning_rate": 8.953259298988536e-06, + "loss": 1.3416, + "step": 5531 + }, + { + "epoch": 0.58, + "learning_rate": 8.949619226384942e-06, + "loss": 1.4212, + "step": 5532 + }, + { + "epoch": 0.58, + "learning_rate": 8.945979294505383e-06, + "loss": 1.4145, + "step": 5533 + }, + { + "epoch": 0.58, + "learning_rate": 8.942339503837512e-06, + "loss": 1.2179, + "step": 5534 + }, + { + "epoch": 0.58, + "learning_rate": 8.938699854868976e-06, + "loss": 1.3239, + "step": 5535 + }, + { + "epoch": 0.58, + "learning_rate": 8.93506034808739e-06, + "loss": 1.3488, + "step": 5536 + }, + { + "epoch": 0.58, + "learning_rate": 8.931420983980357e-06, + "loss": 1.3283, + "step": 5537 + }, + { + "epoch": 0.58, + "learning_rate": 8.927781763035449e-06, + "loss": 1.3866, + "step": 5538 + }, + { + "epoch": 0.58, + "learning_rate": 8.924142685740239e-06, + "loss": 1.3877, + "step": 5539 + }, + { + "epoch": 0.58, + "learning_rate": 8.920503752582265e-06, + "loss": 1.2511, + "step": 5540 + }, + { + "epoch": 0.58, + "learning_rate": 8.916864964049056e-06, + "loss": 1.3581, + "step": 5541 + }, + { + "epoch": 0.58, + "learning_rate": 8.913226320628104e-06, + "loss": 1.387, + "step": 5542 + }, + { + "epoch": 0.58, + "learning_rate": 8.909587822806905e-06, + "loss": 1.3785, + "step": 5543 + }, + { + "epoch": 0.58, + "learning_rate": 8.905949471072921e-06, + "loss": 1.4302, + "step": 5544 + }, + { + "epoch": 0.58, + "learning_rate": 8.9023112659136e-06, + "loss": 1.439, + "step": 5545 + }, + { + "epoch": 0.58, + "learning_rate": 8.898673207816357e-06, + "loss": 1.3257, + "step": 5546 + }, + { + "epoch": 0.58, + "learning_rate": 8.895035297268611e-06, + "loss": 1.4237, + "step": 5547 + }, + { + "epoch": 0.58, + "learning_rate": 8.891397534757745e-06, + "loss": 1.3141, + "step": 5548 + }, + { + "epoch": 0.58, + "learning_rate": 8.887759920771127e-06, + "loss": 1.3069, + "step": 5549 + }, + { + "epoch": 0.58, + "learning_rate": 8.884122455796095e-06, + "loss": 1.2703, + "step": 5550 + }, + { + "epoch": 0.58, + "learning_rate": 8.880485140319986e-06, + "loss": 1.2929, + "step": 5551 + }, + { + "epoch": 0.58, + "learning_rate": 8.876847974830103e-06, + "loss": 1.3719, + "step": 5552 + }, + { + "epoch": 0.58, + "learning_rate": 8.873210959813731e-06, + "loss": 1.3481, + "step": 5553 + }, + { + "epoch": 0.58, + "learning_rate": 8.869574095758141e-06, + "loss": 1.3609, + "step": 5554 + }, + { + "epoch": 0.58, + "learning_rate": 8.865937383150577e-06, + "loss": 1.3137, + "step": 5555 + }, + { + "epoch": 0.58, + "learning_rate": 8.862300822478265e-06, + "loss": 1.3602, + "step": 5556 + }, + { + "epoch": 0.58, + "learning_rate": 8.858664414228409e-06, + "loss": 1.3142, + "step": 5557 + }, + { + "epoch": 0.58, + "learning_rate": 8.855028158888196e-06, + "loss": 1.288, + "step": 5558 + }, + { + "epoch": 0.58, + "learning_rate": 8.851392056944791e-06, + "loss": 1.3407, + "step": 5559 + }, + { + "epoch": 0.58, + "learning_rate": 8.847756108885342e-06, + "loss": 1.3118, + "step": 5560 + }, + { + "epoch": 0.58, + "learning_rate": 8.84412031519696e-06, + "loss": 1.3646, + "step": 5561 + }, + { + "epoch": 0.58, + "learning_rate": 8.840484676366761e-06, + "loss": 1.3896, + "step": 5562 + }, + { + "epoch": 0.58, + "learning_rate": 8.836849192881822e-06, + "loss": 1.3296, + "step": 5563 + }, + { + "epoch": 0.58, + "learning_rate": 8.833213865229208e-06, + "loss": 1.2918, + "step": 5564 + }, + { + "epoch": 0.58, + "learning_rate": 8.82957869389595e-06, + "loss": 1.4811, + "step": 5565 + }, + { + "epoch": 0.58, + "learning_rate": 8.82594367936908e-06, + "loss": 1.3877, + "step": 5566 + }, + { + "epoch": 0.58, + "learning_rate": 8.822308822135588e-06, + "loss": 1.3716, + "step": 5567 + }, + { + "epoch": 0.58, + "learning_rate": 8.818674122682456e-06, + "loss": 1.3204, + "step": 5568 + }, + { + "epoch": 0.58, + "learning_rate": 8.815039581496634e-06, + "loss": 1.326, + "step": 5569 + }, + { + "epoch": 0.58, + "learning_rate": 8.811405199065066e-06, + "loss": 1.3762, + "step": 5570 + }, + { + "epoch": 0.58, + "learning_rate": 8.807770975874658e-06, + "loss": 1.2944, + "step": 5571 + }, + { + "epoch": 0.58, + "learning_rate": 8.804136912412311e-06, + "loss": 1.3057, + "step": 5572 + }, + { + "epoch": 0.58, + "eval_loss": 1.4187605381011963, + "eval_runtime": 77.5157, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 5572 + }, + { + "epoch": 0.58, + "learning_rate": 8.800503009164884e-06, + "loss": 1.4144, + "step": 5573 + }, + { + "epoch": 0.58, + "learning_rate": 8.796869266619238e-06, + "loss": 1.2218, + "step": 5574 + }, + { + "epoch": 0.58, + "learning_rate": 8.793235685262197e-06, + "loss": 1.4445, + "step": 5575 + }, + { + "epoch": 0.58, + "learning_rate": 8.789602265580565e-06, + "loss": 1.3761, + "step": 5576 + }, + { + "epoch": 0.58, + "learning_rate": 8.78596900806113e-06, + "loss": 1.3762, + "step": 5577 + }, + { + "epoch": 0.58, + "learning_rate": 8.782335913190657e-06, + "loss": 1.3506, + "step": 5578 + }, + { + "epoch": 0.59, + "learning_rate": 8.778702981455883e-06, + "loss": 1.4183, + "step": 5579 + }, + { + "epoch": 0.59, + "learning_rate": 8.775070213343528e-06, + "loss": 1.3123, + "step": 5580 + }, + { + "epoch": 0.59, + "learning_rate": 8.771437609340291e-06, + "loss": 1.3168, + "step": 5581 + }, + { + "epoch": 0.59, + "learning_rate": 8.76780516993285e-06, + "loss": 1.3939, + "step": 5582 + }, + { + "epoch": 0.59, + "learning_rate": 8.764172895607856e-06, + "loss": 1.3317, + "step": 5583 + }, + { + "epoch": 0.59, + "learning_rate": 8.760540786851937e-06, + "loss": 1.3094, + "step": 5584 + }, + { + "epoch": 0.59, + "learning_rate": 8.756908844151708e-06, + "loss": 1.2853, + "step": 5585 + }, + { + "epoch": 0.59, + "learning_rate": 8.753277067993752e-06, + "loss": 1.2625, + "step": 5586 + }, + { + "epoch": 0.59, + "learning_rate": 8.74964545886464e-06, + "loss": 1.4246, + "step": 5587 + }, + { + "epoch": 0.59, + "learning_rate": 8.746014017250904e-06, + "loss": 1.2891, + "step": 5588 + }, + { + "epoch": 0.59, + "learning_rate": 8.742382743639071e-06, + "loss": 1.3135, + "step": 5589 + }, + { + "epoch": 0.59, + "learning_rate": 8.738751638515639e-06, + "loss": 1.3021, + "step": 5590 + }, + { + "epoch": 0.59, + "learning_rate": 8.735120702367082e-06, + "loss": 1.3398, + "step": 5591 + }, + { + "epoch": 0.59, + "learning_rate": 8.731489935679845e-06, + "loss": 1.4173, + "step": 5592 + }, + { + "epoch": 0.59, + "learning_rate": 8.727859338940367e-06, + "loss": 1.4129, + "step": 5593 + }, + { + "epoch": 0.59, + "learning_rate": 8.724228912635053e-06, + "loss": 1.3807, + "step": 5594 + }, + { + "epoch": 0.59, + "learning_rate": 8.720598657250284e-06, + "loss": 1.2962, + "step": 5595 + }, + { + "epoch": 0.59, + "learning_rate": 8.716968573272416e-06, + "loss": 1.3784, + "step": 5596 + }, + { + "epoch": 0.59, + "learning_rate": 8.713338661187799e-06, + "loss": 1.3751, + "step": 5597 + }, + { + "epoch": 0.59, + "learning_rate": 8.70970892148274e-06, + "loss": 1.3122, + "step": 5598 + }, + { + "epoch": 0.59, + "learning_rate": 8.70607935464353e-06, + "loss": 1.4174, + "step": 5599 + }, + { + "epoch": 0.59, + "learning_rate": 8.702449961156445e-06, + "loss": 1.3275, + "step": 5600 + }, + { + "epoch": 0.59, + "learning_rate": 8.698820741507723e-06, + "loss": 1.33, + "step": 5601 + }, + { + "epoch": 0.59, + "learning_rate": 8.695191696183589e-06, + "loss": 1.4075, + "step": 5602 + }, + { + "epoch": 0.59, + "learning_rate": 8.69156282567024e-06, + "loss": 1.3778, + "step": 5603 + }, + { + "epoch": 0.59, + "learning_rate": 8.687934130453857e-06, + "loss": 1.3222, + "step": 5604 + }, + { + "epoch": 0.59, + "learning_rate": 8.684305611020587e-06, + "loss": 1.3443, + "step": 5605 + }, + { + "epoch": 0.59, + "learning_rate": 8.680677267856558e-06, + "loss": 1.3167, + "step": 5606 + }, + { + "epoch": 0.59, + "learning_rate": 8.677049101447877e-06, + "loss": 1.3209, + "step": 5607 + }, + { + "epoch": 0.59, + "learning_rate": 8.673421112280624e-06, + "loss": 1.3125, + "step": 5608 + }, + { + "epoch": 0.59, + "learning_rate": 8.669793300840857e-06, + "loss": 1.375, + "step": 5609 + }, + { + "epoch": 0.59, + "learning_rate": 8.666165667614612e-06, + "loss": 1.3627, + "step": 5610 + }, + { + "epoch": 0.59, + "learning_rate": 8.662538213087888e-06, + "loss": 1.3064, + "step": 5611 + }, + { + "epoch": 0.59, + "learning_rate": 8.658910937746685e-06, + "loss": 1.4251, + "step": 5612 + }, + { + "epoch": 0.59, + "learning_rate": 8.655283842076956e-06, + "loss": 1.3011, + "step": 5613 + }, + { + "epoch": 0.59, + "learning_rate": 8.651656926564645e-06, + "loss": 1.3299, + "step": 5614 + }, + { + "epoch": 0.59, + "learning_rate": 8.648030191695653e-06, + "loss": 1.3448, + "step": 5615 + }, + { + "epoch": 0.59, + "learning_rate": 8.644403637955883e-06, + "loss": 1.4048, + "step": 5616 + }, + { + "epoch": 0.59, + "learning_rate": 8.640777265831195e-06, + "loss": 1.336, + "step": 5617 + }, + { + "epoch": 0.59, + "learning_rate": 8.63715107580743e-06, + "loss": 1.4959, + "step": 5618 + }, + { + "epoch": 0.59, + "learning_rate": 8.633525068370397e-06, + "loss": 1.3822, + "step": 5619 + }, + { + "epoch": 0.59, + "learning_rate": 8.6298992440059e-06, + "loss": 1.282, + "step": 5620 + }, + { + "epoch": 0.59, + "learning_rate": 8.626273603199699e-06, + "loss": 1.1873, + "step": 5621 + }, + { + "epoch": 0.59, + "learning_rate": 8.622648146437538e-06, + "loss": 1.3706, + "step": 5622 + }, + { + "epoch": 0.59, + "learning_rate": 8.619022874205138e-06, + "loss": 1.2709, + "step": 5623 + }, + { + "epoch": 0.59, + "learning_rate": 8.615397786988188e-06, + "loss": 1.3608, + "step": 5624 + }, + { + "epoch": 0.59, + "learning_rate": 8.61177288527236e-06, + "loss": 1.3821, + "step": 5625 + }, + { + "epoch": 0.59, + "learning_rate": 8.608148169543292e-06, + "loss": 1.327, + "step": 5626 + }, + { + "epoch": 0.59, + "learning_rate": 8.604523640286611e-06, + "loss": 1.3544, + "step": 5627 + }, + { + "epoch": 0.59, + "learning_rate": 8.600899297987905e-06, + "loss": 1.3269, + "step": 5628 + }, + { + "epoch": 0.59, + "learning_rate": 8.597275143132745e-06, + "loss": 1.3142, + "step": 5629 + }, + { + "epoch": 0.59, + "learning_rate": 8.593651176206671e-06, + "loss": 1.3878, + "step": 5630 + }, + { + "epoch": 0.59, + "learning_rate": 8.59002739769521e-06, + "loss": 1.3386, + "step": 5631 + }, + { + "epoch": 0.59, + "learning_rate": 8.586403808083846e-06, + "loss": 1.3484, + "step": 5632 + }, + { + "epoch": 0.59, + "learning_rate": 8.582780407858052e-06, + "loss": 1.3676, + "step": 5633 + }, + { + "epoch": 0.59, + "learning_rate": 8.579157197503265e-06, + "loss": 1.3753, + "step": 5634 + }, + { + "epoch": 0.59, + "learning_rate": 8.57553417750491e-06, + "loss": 1.4058, + "step": 5635 + }, + { + "epoch": 0.59, + "learning_rate": 8.571911348348375e-06, + "loss": 1.4434, + "step": 5636 + }, + { + "epoch": 0.59, + "learning_rate": 8.568288710519027e-06, + "loss": 1.3398, + "step": 5637 + }, + { + "epoch": 0.59, + "learning_rate": 8.564666264502199e-06, + "loss": 1.3294, + "step": 5638 + }, + { + "epoch": 0.59, + "learning_rate": 8.561044010783216e-06, + "loss": 1.3165, + "step": 5639 + }, + { + "epoch": 0.59, + "learning_rate": 8.557421949847363e-06, + "loss": 1.3437, + "step": 5640 + }, + { + "epoch": 0.59, + "learning_rate": 8.553800082179905e-06, + "loss": 1.3473, + "step": 5641 + }, + { + "epoch": 0.59, + "learning_rate": 8.55017840826607e-06, + "loss": 1.3378, + "step": 5642 + }, + { + "epoch": 0.59, + "learning_rate": 8.546556928591082e-06, + "loss": 1.3357, + "step": 5643 + }, + { + "epoch": 0.59, + "learning_rate": 8.54293564364012e-06, + "loss": 1.3435, + "step": 5644 + }, + { + "epoch": 0.59, + "learning_rate": 8.53931455389834e-06, + "loss": 1.3335, + "step": 5645 + }, + { + "epoch": 0.59, + "learning_rate": 8.535693659850885e-06, + "loss": 1.2917, + "step": 5646 + }, + { + "epoch": 0.59, + "learning_rate": 8.532072961982851e-06, + "loss": 1.3785, + "step": 5647 + }, + { + "epoch": 0.59, + "learning_rate": 8.528452460779327e-06, + "loss": 1.3634, + "step": 5648 + }, + { + "epoch": 0.59, + "learning_rate": 8.524832156725359e-06, + "loss": 1.3541, + "step": 5649 + }, + { + "epoch": 0.59, + "learning_rate": 8.521212050305978e-06, + "loss": 1.335, + "step": 5650 + }, + { + "epoch": 0.59, + "learning_rate": 8.51759214200619e-06, + "loss": 1.3011, + "step": 5651 + }, + { + "epoch": 0.59, + "learning_rate": 8.513972432310965e-06, + "loss": 1.3982, + "step": 5652 + }, + { + "epoch": 0.59, + "learning_rate": 8.510352921705247e-06, + "loss": 1.3217, + "step": 5653 + }, + { + "epoch": 0.59, + "learning_rate": 8.506733610673968e-06, + "loss": 1.3275, + "step": 5654 + }, + { + "epoch": 0.59, + "learning_rate": 8.503114499702015e-06, + "loss": 1.3335, + "step": 5655 + }, + { + "epoch": 0.59, + "learning_rate": 8.499495589274257e-06, + "loss": 1.3567, + "step": 5656 + }, + { + "epoch": 0.59, + "learning_rate": 8.495876879875536e-06, + "loss": 1.348, + "step": 5657 + }, + { + "epoch": 0.59, + "learning_rate": 8.492258371990667e-06, + "loss": 1.3991, + "step": 5658 + }, + { + "epoch": 0.59, + "learning_rate": 8.488640066104435e-06, + "loss": 1.3528, + "step": 5659 + }, + { + "epoch": 0.59, + "learning_rate": 8.485021962701603e-06, + "loss": 1.3275, + "step": 5660 + }, + { + "epoch": 0.59, + "learning_rate": 8.481404062266897e-06, + "loss": 1.3605, + "step": 5661 + }, + { + "epoch": 0.59, + "learning_rate": 8.477786365285032e-06, + "loss": 1.3288, + "step": 5662 + }, + { + "epoch": 0.59, + "learning_rate": 8.474168872240682e-06, + "loss": 1.3274, + "step": 5663 + }, + { + "epoch": 0.59, + "learning_rate": 8.470551583618498e-06, + "loss": 1.273, + "step": 5664 + }, + { + "epoch": 0.59, + "learning_rate": 8.4669344999031e-06, + "loss": 1.3142, + "step": 5665 + }, + { + "epoch": 0.59, + "learning_rate": 8.463317621579091e-06, + "loss": 1.2912, + "step": 5666 + }, + { + "epoch": 0.59, + "learning_rate": 8.459700949131037e-06, + "loss": 1.3162, + "step": 5667 + }, + { + "epoch": 0.59, + "learning_rate": 8.456084483043479e-06, + "loss": 1.3377, + "step": 5668 + }, + { + "epoch": 0.59, + "learning_rate": 8.452468223800931e-06, + "loss": 1.3545, + "step": 5669 + }, + { + "epoch": 0.59, + "learning_rate": 8.448852171887878e-06, + "loss": 1.4052, + "step": 5670 + }, + { + "epoch": 0.59, + "learning_rate": 8.44523632778878e-06, + "loss": 1.3389, + "step": 5671 + }, + { + "epoch": 0.59, + "learning_rate": 8.441620691988063e-06, + "loss": 1.3801, + "step": 5672 + }, + { + "epoch": 0.59, + "learning_rate": 8.438005264970134e-06, + "loss": 1.2978, + "step": 5673 + }, + { + "epoch": 0.6, + "learning_rate": 8.434390047219366e-06, + "loss": 1.437, + "step": 5674 + }, + { + "epoch": 0.6, + "learning_rate": 8.430775039220103e-06, + "loss": 1.3602, + "step": 5675 + }, + { + "epoch": 0.6, + "learning_rate": 8.427160241456664e-06, + "loss": 1.4971, + "step": 5676 + }, + { + "epoch": 0.6, + "learning_rate": 8.423545654413342e-06, + "loss": 1.2765, + "step": 5677 + }, + { + "epoch": 0.6, + "learning_rate": 8.419931278574397e-06, + "loss": 1.4346, + "step": 5678 + }, + { + "epoch": 0.6, + "learning_rate": 8.416317114424059e-06, + "loss": 1.366, + "step": 5679 + }, + { + "epoch": 0.6, + "learning_rate": 8.412703162446536e-06, + "loss": 1.3776, + "step": 5680 + }, + { + "epoch": 0.6, + "learning_rate": 8.409089423126009e-06, + "loss": 1.2516, + "step": 5681 + }, + { + "epoch": 0.6, + "learning_rate": 8.405475896946621e-06, + "loss": 1.4257, + "step": 5682 + }, + { + "epoch": 0.6, + "learning_rate": 8.401862584392492e-06, + "loss": 1.3523, + "step": 5683 + }, + { + "epoch": 0.6, + "learning_rate": 8.398249485947712e-06, + "loss": 1.3791, + "step": 5684 + }, + { + "epoch": 0.6, + "learning_rate": 8.394636602096348e-06, + "loss": 1.3574, + "step": 5685 + }, + { + "epoch": 0.6, + "learning_rate": 8.39102393332243e-06, + "loss": 1.4748, + "step": 5686 + }, + { + "epoch": 0.6, + "learning_rate": 8.387411480109967e-06, + "loss": 1.3693, + "step": 5687 + }, + { + "epoch": 0.6, + "learning_rate": 8.383799242942925e-06, + "loss": 1.3643, + "step": 5688 + }, + { + "epoch": 0.6, + "learning_rate": 8.38018722230526e-06, + "loss": 1.3446, + "step": 5689 + }, + { + "epoch": 0.6, + "learning_rate": 8.37657541868089e-06, + "loss": 1.3552, + "step": 5690 + }, + { + "epoch": 0.6, + "learning_rate": 8.372963832553698e-06, + "loss": 1.3636, + "step": 5691 + }, + { + "epoch": 0.6, + "learning_rate": 8.36935246440755e-06, + "loss": 1.3398, + "step": 5692 + }, + { + "epoch": 0.6, + "learning_rate": 8.365741314726273e-06, + "loss": 1.3336, + "step": 5693 + }, + { + "epoch": 0.6, + "learning_rate": 8.362130383993667e-06, + "loss": 1.3023, + "step": 5694 + }, + { + "epoch": 0.6, + "learning_rate": 8.358519672693506e-06, + "loss": 1.3591, + "step": 5695 + }, + { + "epoch": 0.6, + "learning_rate": 8.354909181309533e-06, + "loss": 1.3113, + "step": 5696 + }, + { + "epoch": 0.6, + "learning_rate": 8.351298910325462e-06, + "loss": 1.3747, + "step": 5697 + }, + { + "epoch": 0.6, + "learning_rate": 8.347688860224976e-06, + "loss": 1.3555, + "step": 5698 + }, + { + "epoch": 0.6, + "learning_rate": 8.344079031491722e-06, + "loss": 1.2947, + "step": 5699 + }, + { + "epoch": 0.6, + "learning_rate": 8.340469424609337e-06, + "loss": 1.4099, + "step": 5700 + }, + { + "epoch": 0.6, + "learning_rate": 8.336860040061404e-06, + "loss": 1.3263, + "step": 5701 + }, + { + "epoch": 0.6, + "learning_rate": 8.333250878331498e-06, + "loss": 1.372, + "step": 5702 + }, + { + "epoch": 0.6, + "learning_rate": 8.329641939903142e-06, + "loss": 1.3523, + "step": 5703 + }, + { + "epoch": 0.6, + "learning_rate": 8.32603322525985e-06, + "loss": 1.3451, + "step": 5704 + }, + { + "epoch": 0.6, + "learning_rate": 8.322424734885098e-06, + "loss": 1.3296, + "step": 5705 + }, + { + "epoch": 0.6, + "learning_rate": 8.318816469262325e-06, + "loss": 1.449, + "step": 5706 + }, + { + "epoch": 0.6, + "learning_rate": 8.315208428874946e-06, + "loss": 1.3611, + "step": 5707 + }, + { + "epoch": 0.6, + "learning_rate": 8.311600614206352e-06, + "loss": 1.3849, + "step": 5708 + }, + { + "epoch": 0.6, + "learning_rate": 8.307993025739893e-06, + "loss": 1.3968, + "step": 5709 + }, + { + "epoch": 0.6, + "learning_rate": 8.304385663958895e-06, + "loss": 1.4428, + "step": 5710 + }, + { + "epoch": 0.6, + "learning_rate": 8.300778529346647e-06, + "loss": 1.3095, + "step": 5711 + }, + { + "epoch": 0.6, + "learning_rate": 8.297171622386418e-06, + "loss": 1.3135, + "step": 5712 + }, + { + "epoch": 0.6, + "learning_rate": 8.293564943561438e-06, + "loss": 1.3069, + "step": 5713 + }, + { + "epoch": 0.6, + "learning_rate": 8.28995849335491e-06, + "loss": 1.3736, + "step": 5714 + }, + { + "epoch": 0.6, + "learning_rate": 8.286352272250007e-06, + "loss": 1.343, + "step": 5715 + }, + { + "epoch": 0.6, + "learning_rate": 8.28274628072987e-06, + "loss": 1.2929, + "step": 5716 + }, + { + "epoch": 0.6, + "learning_rate": 8.279140519277607e-06, + "loss": 1.3356, + "step": 5717 + }, + { + "epoch": 0.6, + "learning_rate": 8.275534988376295e-06, + "loss": 1.2683, + "step": 5718 + }, + { + "epoch": 0.6, + "learning_rate": 8.27192968850899e-06, + "loss": 1.3738, + "step": 5719 + }, + { + "epoch": 0.6, + "learning_rate": 8.268324620158704e-06, + "loss": 1.3369, + "step": 5720 + }, + { + "epoch": 0.6, + "learning_rate": 8.264719783808425e-06, + "loss": 1.3684, + "step": 5721 + }, + { + "epoch": 0.6, + "learning_rate": 8.261115179941108e-06, + "loss": 1.4081, + "step": 5722 + }, + { + "epoch": 0.6, + "learning_rate": 8.257510809039678e-06, + "loss": 1.2504, + "step": 5723 + }, + { + "epoch": 0.6, + "learning_rate": 8.253906671587029e-06, + "loss": 1.417, + "step": 5724 + }, + { + "epoch": 0.6, + "learning_rate": 8.25030276806602e-06, + "loss": 1.3631, + "step": 5725 + }, + { + "epoch": 0.6, + "learning_rate": 8.246699098959483e-06, + "loss": 1.499, + "step": 5726 + }, + { + "epoch": 0.6, + "learning_rate": 8.243095664750217e-06, + "loss": 1.3656, + "step": 5727 + }, + { + "epoch": 0.6, + "learning_rate": 8.239492465920992e-06, + "loss": 1.3563, + "step": 5728 + }, + { + "epoch": 0.6, + "learning_rate": 8.23588950295454e-06, + "loss": 1.3554, + "step": 5729 + }, + { + "epoch": 0.6, + "learning_rate": 8.232286776333566e-06, + "loss": 1.2705, + "step": 5730 + }, + { + "epoch": 0.6, + "learning_rate": 8.228684286540747e-06, + "loss": 1.3792, + "step": 5731 + }, + { + "epoch": 0.6, + "learning_rate": 8.22508203405872e-06, + "loss": 1.3301, + "step": 5732 + }, + { + "epoch": 0.6, + "learning_rate": 8.221480019370095e-06, + "loss": 1.36, + "step": 5733 + }, + { + "epoch": 0.6, + "learning_rate": 8.217878242957448e-06, + "loss": 1.4406, + "step": 5734 + }, + { + "epoch": 0.6, + "learning_rate": 8.214276705303328e-06, + "loss": 1.2886, + "step": 5735 + }, + { + "epoch": 0.6, + "learning_rate": 8.210675406890248e-06, + "loss": 1.3072, + "step": 5736 + }, + { + "epoch": 0.6, + "learning_rate": 8.207074348200686e-06, + "loss": 1.3734, + "step": 5737 + }, + { + "epoch": 0.6, + "learning_rate": 8.203473529717095e-06, + "loss": 1.3893, + "step": 5738 + }, + { + "epoch": 0.6, + "learning_rate": 8.199872951921892e-06, + "loss": 1.3427, + "step": 5739 + }, + { + "epoch": 0.6, + "learning_rate": 8.196272615297459e-06, + "loss": 1.3125, + "step": 5740 + }, + { + "epoch": 0.6, + "learning_rate": 8.19267252032615e-06, + "loss": 1.3079, + "step": 5741 + }, + { + "epoch": 0.6, + "learning_rate": 8.189072667490285e-06, + "loss": 1.2971, + "step": 5742 + }, + { + "epoch": 0.6, + "learning_rate": 8.185473057272154e-06, + "loss": 1.3003, + "step": 5743 + }, + { + "epoch": 0.6, + "learning_rate": 8.18187369015401e-06, + "loss": 1.3002, + "step": 5744 + }, + { + "epoch": 0.6, + "learning_rate": 8.178274566618075e-06, + "loss": 1.2852, + "step": 5745 + }, + { + "epoch": 0.6, + "learning_rate": 8.174675687146542e-06, + "loss": 1.2807, + "step": 5746 + }, + { + "epoch": 0.6, + "learning_rate": 8.171077052221567e-06, + "loss": 1.2983, + "step": 5747 + }, + { + "epoch": 0.6, + "learning_rate": 8.167478662325274e-06, + "loss": 1.3002, + "step": 5748 + }, + { + "epoch": 0.6, + "learning_rate": 8.163880517939753e-06, + "loss": 1.2575, + "step": 5749 + }, + { + "epoch": 0.6, + "learning_rate": 8.160282619547068e-06, + "loss": 1.2627, + "step": 5750 + }, + { + "epoch": 0.6, + "learning_rate": 8.156684967629242e-06, + "loss": 1.2549, + "step": 5751 + }, + { + "epoch": 0.6, + "learning_rate": 8.153087562668265e-06, + "loss": 1.2595, + "step": 5752 + }, + { + "epoch": 0.6, + "learning_rate": 8.1494904051461e-06, + "loss": 1.2788, + "step": 5753 + }, + { + "epoch": 0.6, + "learning_rate": 8.145893495544676e-06, + "loss": 1.3028, + "step": 5754 + }, + { + "epoch": 0.6, + "learning_rate": 8.142296834345883e-06, + "loss": 1.3019, + "step": 5755 + }, + { + "epoch": 0.6, + "learning_rate": 8.138700422031583e-06, + "loss": 1.2998, + "step": 5756 + }, + { + "epoch": 0.6, + "learning_rate": 8.135104259083598e-06, + "loss": 1.3298, + "step": 5757 + }, + { + "epoch": 0.6, + "learning_rate": 8.13150834598373e-06, + "loss": 1.2681, + "step": 5758 + }, + { + "epoch": 0.6, + "learning_rate": 8.127912683213733e-06, + "loss": 1.2987, + "step": 5759 + }, + { + "epoch": 0.6, + "learning_rate": 8.124317271255331e-06, + "loss": 1.3181, + "step": 5760 + }, + { + "epoch": 0.6, + "learning_rate": 8.120722110590224e-06, + "loss": 1.423, + "step": 5761 + }, + { + "epoch": 0.6, + "learning_rate": 8.117127201700067e-06, + "loss": 1.5029, + "step": 5762 + }, + { + "epoch": 0.6, + "learning_rate": 8.113532545066488e-06, + "loss": 1.3016, + "step": 5763 + }, + { + "epoch": 0.6, + "learning_rate": 8.109938141171074e-06, + "loss": 1.3906, + "step": 5764 + }, + { + "epoch": 0.6, + "learning_rate": 8.106343990495387e-06, + "loss": 1.3363, + "step": 5765 + }, + { + "epoch": 0.6, + "learning_rate": 8.10275009352095e-06, + "loss": 1.314, + "step": 5766 + }, + { + "epoch": 0.6, + "learning_rate": 8.09915645072925e-06, + "loss": 1.3484, + "step": 5767 + }, + { + "epoch": 0.6, + "learning_rate": 8.095563062601745e-06, + "loss": 1.3757, + "step": 5768 + }, + { + "epoch": 0.6, + "learning_rate": 8.091969929619859e-06, + "loss": 1.3068, + "step": 5769 + }, + { + "epoch": 0.61, + "learning_rate": 8.088377052264976e-06, + "loss": 1.3486, + "step": 5770 + }, + { + "epoch": 0.61, + "learning_rate": 8.08478443101845e-06, + "loss": 1.244, + "step": 5771 + }, + { + "epoch": 0.61, + "eval_loss": 1.4178493022918701, + "eval_runtime": 77.6086, + "eval_samples_per_second": 1.662, + "eval_steps_per_second": 0.116, + "step": 5771 + }, + { + "epoch": 0.61, + "learning_rate": 8.0811920663616e-06, + "loss": 1.3325, + "step": 5772 + }, + { + "epoch": 0.61, + "learning_rate": 8.077599958775713e-06, + "loss": 1.336, + "step": 5773 + }, + { + "epoch": 0.61, + "learning_rate": 8.074008108742037e-06, + "loss": 1.3167, + "step": 5774 + }, + { + "epoch": 0.61, + "learning_rate": 8.070416516741786e-06, + "loss": 1.3166, + "step": 5775 + }, + { + "epoch": 0.61, + "learning_rate": 8.066825183256141e-06, + "loss": 1.3377, + "step": 5776 + }, + { + "epoch": 0.61, + "learning_rate": 8.063234108766253e-06, + "loss": 1.3704, + "step": 5777 + }, + { + "epoch": 0.61, + "learning_rate": 8.059643293753233e-06, + "loss": 1.3596, + "step": 5778 + }, + { + "epoch": 0.61, + "learning_rate": 8.056052738698153e-06, + "loss": 1.4477, + "step": 5779 + }, + { + "epoch": 0.61, + "learning_rate": 8.052462444082055e-06, + "loss": 1.338, + "step": 5780 + }, + { + "epoch": 0.61, + "learning_rate": 8.048872410385952e-06, + "loss": 1.2714, + "step": 5781 + }, + { + "epoch": 0.61, + "learning_rate": 8.045282638090815e-06, + "loss": 0.9642, + "step": 5782 + }, + { + "epoch": 0.61, + "learning_rate": 8.041693127677576e-06, + "loss": 0.8702, + "step": 5783 + }, + { + "epoch": 0.61, + "learning_rate": 8.038103879627144e-06, + "loss": 0.8986, + "step": 5784 + }, + { + "epoch": 0.61, + "learning_rate": 8.034514894420382e-06, + "loss": 0.804, + "step": 5785 + }, + { + "epoch": 0.61, + "learning_rate": 8.030926172538122e-06, + "loss": 0.7958, + "step": 5786 + }, + { + "epoch": 0.61, + "learning_rate": 8.02733771446116e-06, + "loss": 0.7608, + "step": 5787 + }, + { + "epoch": 0.61, + "learning_rate": 8.023749520670261e-06, + "loss": 0.7792, + "step": 5788 + }, + { + "epoch": 0.61, + "learning_rate": 8.020161591646147e-06, + "loss": 0.7293, + "step": 5789 + }, + { + "epoch": 0.61, + "learning_rate": 8.016573927869511e-06, + "loss": 1.1287, + "step": 5790 + }, + { + "epoch": 0.61, + "learning_rate": 8.012986529821004e-06, + "loss": 1.3344, + "step": 5791 + }, + { + "epoch": 0.61, + "learning_rate": 8.009399397981248e-06, + "loss": 1.4415, + "step": 5792 + }, + { + "epoch": 0.61, + "learning_rate": 8.005812532830826e-06, + "loss": 1.4265, + "step": 5793 + }, + { + "epoch": 0.61, + "learning_rate": 8.002225934850287e-06, + "loss": 1.3429, + "step": 5794 + }, + { + "epoch": 0.61, + "learning_rate": 7.998639604520137e-06, + "loss": 1.3653, + "step": 5795 + }, + { + "epoch": 0.61, + "learning_rate": 7.995053542320861e-06, + "loss": 1.486, + "step": 5796 + }, + { + "epoch": 0.61, + "learning_rate": 7.991467748732894e-06, + "loss": 1.3389, + "step": 5797 + }, + { + "epoch": 0.61, + "learning_rate": 7.98788222423664e-06, + "loss": 1.3206, + "step": 5798 + }, + { + "epoch": 0.61, + "learning_rate": 7.984296969312468e-06, + "loss": 1.3121, + "step": 5799 + }, + { + "epoch": 0.61, + "learning_rate": 7.980711984440712e-06, + "loss": 1.3512, + "step": 5800 + }, + { + "epoch": 0.61, + "learning_rate": 7.977127270101665e-06, + "loss": 1.3291, + "step": 5801 + }, + { + "epoch": 0.61, + "learning_rate": 7.97354282677559e-06, + "loss": 1.3948, + "step": 5802 + }, + { + "epoch": 0.61, + "learning_rate": 7.969958654942704e-06, + "loss": 1.3076, + "step": 5803 + }, + { + "epoch": 0.61, + "learning_rate": 7.966374755083202e-06, + "loss": 1.3838, + "step": 5804 + }, + { + "epoch": 0.61, + "learning_rate": 7.962791127677228e-06, + "loss": 1.4205, + "step": 5805 + }, + { + "epoch": 0.61, + "learning_rate": 7.959207773204899e-06, + "loss": 1.3635, + "step": 5806 + }, + { + "epoch": 0.61, + "learning_rate": 7.955624692146293e-06, + "loss": 1.3299, + "step": 5807 + }, + { + "epoch": 0.61, + "learning_rate": 7.95204188498145e-06, + "loss": 1.4435, + "step": 5808 + }, + { + "epoch": 0.61, + "learning_rate": 7.948459352190372e-06, + "loss": 1.4335, + "step": 5809 + }, + { + "epoch": 0.61, + "learning_rate": 7.944877094253027e-06, + "loss": 1.3391, + "step": 5810 + }, + { + "epoch": 0.61, + "learning_rate": 7.94129511164935e-06, + "loss": 1.2852, + "step": 5811 + }, + { + "epoch": 0.61, + "learning_rate": 7.93771340485923e-06, + "loss": 1.3174, + "step": 5812 + }, + { + "epoch": 0.61, + "learning_rate": 7.934131974362527e-06, + "loss": 1.3415, + "step": 5813 + }, + { + "epoch": 0.61, + "learning_rate": 7.930550820639055e-06, + "loss": 1.2764, + "step": 5814 + }, + { + "epoch": 0.61, + "learning_rate": 7.926969944168603e-06, + "loss": 1.2978, + "step": 5815 + }, + { + "epoch": 0.61, + "learning_rate": 7.923389345430911e-06, + "loss": 1.3046, + "step": 5816 + }, + { + "epoch": 0.61, + "learning_rate": 7.919809024905694e-06, + "loss": 1.3484, + "step": 5817 + }, + { + "epoch": 0.61, + "learning_rate": 7.916228983072614e-06, + "loss": 1.3207, + "step": 5818 + }, + { + "epoch": 0.61, + "learning_rate": 7.912649220411312e-06, + "loss": 1.4289, + "step": 5819 + }, + { + "epoch": 0.61, + "learning_rate": 7.909069737401382e-06, + "loss": 1.4359, + "step": 5820 + }, + { + "epoch": 0.61, + "learning_rate": 7.905490534522384e-06, + "loss": 1.3316, + "step": 5821 + }, + { + "epoch": 0.61, + "learning_rate": 7.901911612253834e-06, + "loss": 1.3112, + "step": 5822 + }, + { + "epoch": 0.61, + "learning_rate": 7.898332971075221e-06, + "loss": 1.3318, + "step": 5823 + }, + { + "epoch": 0.61, + "learning_rate": 7.894754611465992e-06, + "loss": 1.4373, + "step": 5824 + }, + { + "epoch": 0.61, + "learning_rate": 7.891176533905549e-06, + "loss": 1.2938, + "step": 5825 + }, + { + "epoch": 0.61, + "learning_rate": 7.887598738873266e-06, + "loss": 1.3471, + "step": 5826 + }, + { + "epoch": 0.61, + "learning_rate": 7.884021226848478e-06, + "loss": 1.2999, + "step": 5827 + }, + { + "epoch": 0.61, + "learning_rate": 7.880443998310475e-06, + "loss": 1.35, + "step": 5828 + }, + { + "epoch": 0.61, + "learning_rate": 7.876867053738517e-06, + "loss": 1.3307, + "step": 5829 + }, + { + "epoch": 0.61, + "learning_rate": 7.87329039361182e-06, + "loss": 1.393, + "step": 5830 + }, + { + "epoch": 0.61, + "learning_rate": 7.869714018409568e-06, + "loss": 1.2933, + "step": 5831 + }, + { + "epoch": 0.61, + "learning_rate": 7.866137928610903e-06, + "loss": 1.319, + "step": 5832 + }, + { + "epoch": 0.61, + "learning_rate": 7.862562124694925e-06, + "loss": 1.3088, + "step": 5833 + }, + { + "epoch": 0.61, + "learning_rate": 7.858986607140705e-06, + "loss": 1.2941, + "step": 5834 + }, + { + "epoch": 0.61, + "learning_rate": 7.855411376427267e-06, + "loss": 1.3214, + "step": 5835 + }, + { + "epoch": 0.61, + "learning_rate": 7.851836433033602e-06, + "loss": 1.2991, + "step": 5836 + }, + { + "epoch": 0.61, + "learning_rate": 7.848261777438656e-06, + "loss": 1.3117, + "step": 5837 + }, + { + "epoch": 0.61, + "learning_rate": 7.844687410121348e-06, + "loss": 1.2905, + "step": 5838 + }, + { + "epoch": 0.61, + "learning_rate": 7.841113331560548e-06, + "loss": 1.3688, + "step": 5839 + }, + { + "epoch": 0.61, + "learning_rate": 7.837539542235091e-06, + "loss": 1.3987, + "step": 5840 + }, + { + "epoch": 0.61, + "learning_rate": 7.83396604262377e-06, + "loss": 1.2693, + "step": 5841 + }, + { + "epoch": 0.61, + "learning_rate": 7.830392833205348e-06, + "loss": 1.3205, + "step": 5842 + }, + { + "epoch": 0.61, + "learning_rate": 7.826819914458538e-06, + "loss": 1.3325, + "step": 5843 + }, + { + "epoch": 0.61, + "learning_rate": 7.823247286862024e-06, + "loss": 1.3451, + "step": 5844 + }, + { + "epoch": 0.61, + "learning_rate": 7.81967495089444e-06, + "loss": 1.3484, + "step": 5845 + }, + { + "epoch": 0.61, + "learning_rate": 7.816102907034395e-06, + "loss": 1.4949, + "step": 5846 + }, + { + "epoch": 0.61, + "learning_rate": 7.812531155760445e-06, + "loss": 1.4293, + "step": 5847 + }, + { + "epoch": 0.61, + "learning_rate": 7.808959697551113e-06, + "loss": 1.4314, + "step": 5848 + }, + { + "epoch": 0.61, + "learning_rate": 7.805388532884887e-06, + "loss": 1.3188, + "step": 5849 + }, + { + "epoch": 0.61, + "learning_rate": 7.80181766224021e-06, + "loss": 1.4396, + "step": 5850 + }, + { + "epoch": 0.61, + "learning_rate": 7.798247086095484e-06, + "loss": 1.3448, + "step": 5851 + }, + { + "epoch": 0.61, + "learning_rate": 7.794676804929075e-06, + "loss": 1.3591, + "step": 5852 + }, + { + "epoch": 0.61, + "learning_rate": 7.791106819219311e-06, + "loss": 1.3108, + "step": 5853 + }, + { + "epoch": 0.61, + "learning_rate": 7.78753712944448e-06, + "loss": 1.3773, + "step": 5854 + }, + { + "epoch": 0.61, + "learning_rate": 7.783967736082824e-06, + "loss": 1.3313, + "step": 5855 + }, + { + "epoch": 0.61, + "learning_rate": 7.780398639612551e-06, + "loss": 1.3635, + "step": 5856 + }, + { + "epoch": 0.61, + "learning_rate": 7.776829840511833e-06, + "loss": 1.3225, + "step": 5857 + }, + { + "epoch": 0.61, + "learning_rate": 7.773261339258792e-06, + "loss": 1.3142, + "step": 5858 + }, + { + "epoch": 0.61, + "learning_rate": 7.769693136331519e-06, + "loss": 1.3337, + "step": 5859 + }, + { + "epoch": 0.61, + "learning_rate": 7.766125232208057e-06, + "loss": 1.5289, + "step": 5860 + }, + { + "epoch": 0.61, + "learning_rate": 7.762557627366418e-06, + "loss": 1.573, + "step": 5861 + }, + { + "epoch": 0.61, + "learning_rate": 7.758990322284568e-06, + "loss": 1.322, + "step": 5862 + }, + { + "epoch": 0.61, + "learning_rate": 7.755423317440432e-06, + "loss": 1.3281, + "step": 5863 + }, + { + "epoch": 0.61, + "learning_rate": 7.751856613311899e-06, + "loss": 1.3405, + "step": 5864 + }, + { + "epoch": 0.62, + "learning_rate": 7.748290210376817e-06, + "loss": 1.3083, + "step": 5865 + }, + { + "epoch": 0.62, + "learning_rate": 7.744724109112991e-06, + "loss": 1.3587, + "step": 5866 + }, + { + "epoch": 0.62, + "learning_rate": 7.741158309998188e-06, + "loss": 1.3204, + "step": 5867 + }, + { + "epoch": 0.62, + "learning_rate": 7.73759281351013e-06, + "loss": 1.343, + "step": 5868 + }, + { + "epoch": 0.62, + "learning_rate": 7.734027620126507e-06, + "loss": 1.2874, + "step": 5869 + }, + { + "epoch": 0.62, + "learning_rate": 7.73046273032496e-06, + "loss": 1.3306, + "step": 5870 + }, + { + "epoch": 0.62, + "learning_rate": 7.72689814458309e-06, + "loss": 1.3958, + "step": 5871 + }, + { + "epoch": 0.62, + "learning_rate": 7.723333863378465e-06, + "loss": 1.3135, + "step": 5872 + }, + { + "epoch": 0.62, + "learning_rate": 7.719769887188608e-06, + "loss": 1.3241, + "step": 5873 + }, + { + "epoch": 0.62, + "learning_rate": 7.716206216490995e-06, + "loss": 1.3487, + "step": 5874 + }, + { + "epoch": 0.62, + "learning_rate": 7.712642851763067e-06, + "loss": 1.0263, + "step": 5875 + }, + { + "epoch": 0.62, + "learning_rate": 7.709079793482228e-06, + "loss": 1.4238, + "step": 5876 + }, + { + "epoch": 0.62, + "learning_rate": 7.705517042125833e-06, + "loss": 1.3284, + "step": 5877 + }, + { + "epoch": 0.62, + "learning_rate": 7.701954598171199e-06, + "loss": 1.2965, + "step": 5878 + }, + { + "epoch": 0.62, + "learning_rate": 7.698392462095601e-06, + "loss": 1.3578, + "step": 5879 + }, + { + "epoch": 0.62, + "learning_rate": 7.694830634376278e-06, + "loss": 1.3711, + "step": 5880 + }, + { + "epoch": 0.62, + "learning_rate": 7.69126911549042e-06, + "loss": 1.3274, + "step": 5881 + }, + { + "epoch": 0.62, + "learning_rate": 7.687707905915181e-06, + "loss": 1.4208, + "step": 5882 + }, + { + "epoch": 0.62, + "learning_rate": 7.684147006127665e-06, + "loss": 1.3478, + "step": 5883 + }, + { + "epoch": 0.62, + "learning_rate": 7.68058641660495e-06, + "loss": 1.2997, + "step": 5884 + }, + { + "epoch": 0.62, + "learning_rate": 7.67702613782406e-06, + "loss": 1.2981, + "step": 5885 + }, + { + "epoch": 0.62, + "learning_rate": 7.67346617026198e-06, + "loss": 1.3834, + "step": 5886 + }, + { + "epoch": 0.62, + "learning_rate": 7.669906514395654e-06, + "loss": 1.3585, + "step": 5887 + }, + { + "epoch": 0.62, + "learning_rate": 7.666347170701986e-06, + "loss": 1.3282, + "step": 5888 + }, + { + "epoch": 0.62, + "learning_rate": 7.662788139657838e-06, + "loss": 1.3397, + "step": 5889 + }, + { + "epoch": 0.62, + "learning_rate": 7.659229421740024e-06, + "loss": 1.3367, + "step": 5890 + }, + { + "epoch": 0.62, + "learning_rate": 7.655671017425322e-06, + "loss": 1.3497, + "step": 5891 + }, + { + "epoch": 0.62, + "learning_rate": 7.65211292719047e-06, + "loss": 1.3661, + "step": 5892 + }, + { + "epoch": 0.62, + "learning_rate": 7.64855515151216e-06, + "loss": 1.2793, + "step": 5893 + }, + { + "epoch": 0.62, + "learning_rate": 7.644997690867037e-06, + "loss": 1.3288, + "step": 5894 + }, + { + "epoch": 0.62, + "learning_rate": 7.641440545731717e-06, + "loss": 1.3877, + "step": 5895 + }, + { + "epoch": 0.62, + "learning_rate": 7.637883716582764e-06, + "loss": 1.4467, + "step": 5896 + }, + { + "epoch": 0.62, + "learning_rate": 7.634327203896698e-06, + "loss": 1.304, + "step": 5897 + }, + { + "epoch": 0.62, + "learning_rate": 7.630771008150002e-06, + "loss": 1.374, + "step": 5898 + }, + { + "epoch": 0.62, + "learning_rate": 7.627215129819118e-06, + "loss": 1.3893, + "step": 5899 + }, + { + "epoch": 0.62, + "learning_rate": 7.623659569380439e-06, + "loss": 1.325, + "step": 5900 + }, + { + "epoch": 0.62, + "learning_rate": 7.620104327310319e-06, + "loss": 1.2495, + "step": 5901 + }, + { + "epoch": 0.62, + "learning_rate": 7.616549404085068e-06, + "loss": 1.4034, + "step": 5902 + }, + { + "epoch": 0.62, + "learning_rate": 7.61299480018096e-06, + "loss": 1.2758, + "step": 5903 + }, + { + "epoch": 0.62, + "learning_rate": 7.609440516074215e-06, + "loss": 1.4203, + "step": 5904 + }, + { + "epoch": 0.62, + "learning_rate": 7.605886552241017e-06, + "loss": 1.3162, + "step": 5905 + }, + { + "epoch": 0.62, + "learning_rate": 7.602332909157505e-06, + "loss": 1.3368, + "step": 5906 + }, + { + "epoch": 0.62, + "learning_rate": 7.598779587299778e-06, + "loss": 1.314, + "step": 5907 + }, + { + "epoch": 0.62, + "learning_rate": 7.59522658714389e-06, + "loss": 1.3332, + "step": 5908 + }, + { + "epoch": 0.62, + "learning_rate": 7.5916739091658505e-06, + "loss": 1.3513, + "step": 5909 + }, + { + "epoch": 0.62, + "learning_rate": 7.5881215538416255e-06, + "loss": 1.3767, + "step": 5910 + }, + { + "epoch": 0.62, + "learning_rate": 7.5845695216471426e-06, + "loss": 1.3651, + "step": 5911 + }, + { + "epoch": 0.62, + "learning_rate": 7.581017813058283e-06, + "loss": 1.2676, + "step": 5912 + }, + { + "epoch": 0.62, + "learning_rate": 7.57746642855088e-06, + "loss": 1.3509, + "step": 5913 + }, + { + "epoch": 0.62, + "learning_rate": 7.5739153686007305e-06, + "loss": 1.2854, + "step": 5914 + }, + { + "epoch": 0.62, + "learning_rate": 7.570364633683586e-06, + "loss": 1.4041, + "step": 5915 + }, + { + "epoch": 0.62, + "learning_rate": 7.5668142242751545e-06, + "loss": 1.3218, + "step": 5916 + }, + { + "epoch": 0.62, + "learning_rate": 7.563264140851095e-06, + "loss": 1.398, + "step": 5917 + }, + { + "epoch": 0.62, + "learning_rate": 7.559714383887033e-06, + "loss": 1.3495, + "step": 5918 + }, + { + "epoch": 0.62, + "learning_rate": 7.556164953858543e-06, + "loss": 1.365, + "step": 5919 + }, + { + "epoch": 0.62, + "learning_rate": 7.552615851241157e-06, + "loss": 1.4611, + "step": 5920 + }, + { + "epoch": 0.62, + "learning_rate": 7.549067076510361e-06, + "loss": 1.4031, + "step": 5921 + }, + { + "epoch": 0.62, + "learning_rate": 7.545518630141605e-06, + "loss": 1.2745, + "step": 5922 + }, + { + "epoch": 0.62, + "learning_rate": 7.541970512610286e-06, + "loss": 1.3435, + "step": 5923 + }, + { + "epoch": 0.62, + "learning_rate": 7.538422724391761e-06, + "loss": 1.3433, + "step": 5924 + }, + { + "epoch": 0.62, + "learning_rate": 7.534875265961341e-06, + "loss": 1.3605, + "step": 5925 + }, + { + "epoch": 0.62, + "learning_rate": 7.5313281377942985e-06, + "loss": 1.3896, + "step": 5926 + }, + { + "epoch": 0.62, + "learning_rate": 7.527781340365854e-06, + "loss": 1.3922, + "step": 5927 + }, + { + "epoch": 0.62, + "learning_rate": 7.524234874151189e-06, + "loss": 1.3305, + "step": 5928 + }, + { + "epoch": 0.62, + "learning_rate": 7.520688739625436e-06, + "loss": 1.3117, + "step": 5929 + }, + { + "epoch": 0.62, + "learning_rate": 7.51714293726369e-06, + "loss": 1.3581, + "step": 5930 + }, + { + "epoch": 0.62, + "learning_rate": 7.5135974675409955e-06, + "loss": 1.3973, + "step": 5931 + }, + { + "epoch": 0.62, + "learning_rate": 7.510052330932354e-06, + "loss": 1.3499, + "step": 5932 + }, + { + "epoch": 0.62, + "learning_rate": 7.506507527912721e-06, + "loss": 1.3068, + "step": 5933 + }, + { + "epoch": 0.62, + "learning_rate": 7.502963058957014e-06, + "loss": 1.3689, + "step": 5934 + }, + { + "epoch": 0.62, + "learning_rate": 7.499418924540096e-06, + "loss": 1.3356, + "step": 5935 + }, + { + "epoch": 0.62, + "learning_rate": 7.495875125136793e-06, + "loss": 1.2593, + "step": 5936 + }, + { + "epoch": 0.62, + "learning_rate": 7.492331661221881e-06, + "loss": 1.272, + "step": 5937 + }, + { + "epoch": 0.62, + "learning_rate": 7.488788533270093e-06, + "loss": 1.3552, + "step": 5938 + }, + { + "epoch": 0.62, + "learning_rate": 7.485245741756121e-06, + "loss": 1.3425, + "step": 5939 + }, + { + "epoch": 0.62, + "learning_rate": 7.481703287154602e-06, + "loss": 1.3694, + "step": 5940 + }, + { + "epoch": 0.62, + "learning_rate": 7.478161169940139e-06, + "loss": 1.3281, + "step": 5941 + }, + { + "epoch": 0.62, + "learning_rate": 7.4746193905872825e-06, + "loss": 1.3109, + "step": 5942 + }, + { + "epoch": 0.62, + "learning_rate": 7.47107794957054e-06, + "loss": 1.5121, + "step": 5943 + }, + { + "epoch": 0.62, + "learning_rate": 7.467536847364372e-06, + "loss": 1.4472, + "step": 5944 + }, + { + "epoch": 0.62, + "learning_rate": 7.463996084443198e-06, + "loss": 1.4615, + "step": 5945 + }, + { + "epoch": 0.62, + "learning_rate": 7.460455661281389e-06, + "loss": 1.3764, + "step": 5946 + }, + { + "epoch": 0.62, + "learning_rate": 7.45691557835327e-06, + "loss": 1.3091, + "step": 5947 + }, + { + "epoch": 0.62, + "learning_rate": 7.4533758361331185e-06, + "loss": 1.1841, + "step": 5948 + }, + { + "epoch": 0.62, + "learning_rate": 7.449836435095175e-06, + "loss": 1.3345, + "step": 5949 + }, + { + "epoch": 0.62, + "learning_rate": 7.446297375713622e-06, + "loss": 1.3573, + "step": 5950 + }, + { + "epoch": 0.62, + "learning_rate": 7.442758658462608e-06, + "loss": 1.3161, + "step": 5951 + }, + { + "epoch": 0.62, + "learning_rate": 7.4392202838162245e-06, + "loss": 1.3089, + "step": 5952 + }, + { + "epoch": 0.62, + "learning_rate": 7.435682252248528e-06, + "loss": 1.3069, + "step": 5953 + }, + { + "epoch": 0.62, + "learning_rate": 7.4321445642335234e-06, + "loss": 1.2969, + "step": 5954 + }, + { + "epoch": 0.62, + "learning_rate": 7.428607220245165e-06, + "loss": 1.4706, + "step": 5955 + }, + { + "epoch": 0.62, + "learning_rate": 7.42507022075737e-06, + "loss": 1.3028, + "step": 5956 + }, + { + "epoch": 0.62, + "learning_rate": 7.421533566244006e-06, + "loss": 1.2786, + "step": 5957 + }, + { + "epoch": 0.62, + "learning_rate": 7.417997257178893e-06, + "loss": 1.3534, + "step": 5958 + }, + { + "epoch": 0.62, + "learning_rate": 7.414461294035804e-06, + "loss": 1.2829, + "step": 5959 + }, + { + "epoch": 0.62, + "learning_rate": 7.410925677288467e-06, + "loss": 1.3626, + "step": 5960 + }, + { + "epoch": 0.63, + "learning_rate": 7.407390407410566e-06, + "loss": 1.4531, + "step": 5961 + }, + { + "epoch": 0.63, + "learning_rate": 7.4038554848757375e-06, + "loss": 1.3549, + "step": 5962 + }, + { + "epoch": 0.63, + "learning_rate": 7.400320910157563e-06, + "loss": 1.3407, + "step": 5963 + }, + { + "epoch": 0.63, + "learning_rate": 7.396786683729595e-06, + "loss": 1.2736, + "step": 5964 + }, + { + "epoch": 0.63, + "learning_rate": 7.393252806065323e-06, + "loss": 1.3377, + "step": 5965 + }, + { + "epoch": 0.63, + "learning_rate": 7.389719277638196e-06, + "loss": 1.3479, + "step": 5966 + }, + { + "epoch": 0.63, + "learning_rate": 7.3861860989216175e-06, + "loss": 1.3605, + "step": 5967 + }, + { + "epoch": 0.63, + "learning_rate": 7.382653270388942e-06, + "loss": 1.3175, + "step": 5968 + }, + { + "epoch": 0.63, + "learning_rate": 7.379120792513477e-06, + "loss": 1.3072, + "step": 5969 + }, + { + "epoch": 0.63, + "learning_rate": 7.375588665768485e-06, + "loss": 1.3224, + "step": 5970 + }, + { + "epoch": 0.63, + "eval_loss": 1.4110088348388672, + "eval_runtime": 77.5326, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 5970 + }, + { + "epoch": 0.63, + "learning_rate": 7.37205689062718e-06, + "loss": 1.3491, + "step": 5971 + }, + { + "epoch": 0.63, + "learning_rate": 7.368525467562728e-06, + "loss": 1.3289, + "step": 5972 + }, + { + "epoch": 0.63, + "learning_rate": 7.364994397048251e-06, + "loss": 1.3362, + "step": 5973 + }, + { + "epoch": 0.63, + "learning_rate": 7.36146367955682e-06, + "loss": 1.3754, + "step": 5974 + }, + { + "epoch": 0.63, + "learning_rate": 7.3579333155614585e-06, + "loss": 1.3159, + "step": 5975 + }, + { + "epoch": 0.63, + "learning_rate": 7.354403305535149e-06, + "loss": 1.4366, + "step": 5976 + }, + { + "epoch": 0.63, + "learning_rate": 7.350873649950822e-06, + "loss": 1.3243, + "step": 5977 + }, + { + "epoch": 0.63, + "learning_rate": 7.347344349281358e-06, + "loss": 1.2911, + "step": 5978 + }, + { + "epoch": 0.63, + "learning_rate": 7.34381540399959e-06, + "loss": 1.338, + "step": 5979 + }, + { + "epoch": 0.63, + "learning_rate": 7.340286814578312e-06, + "loss": 1.3241, + "step": 5980 + }, + { + "epoch": 0.63, + "learning_rate": 7.336758581490263e-06, + "loss": 1.3427, + "step": 5981 + }, + { + "epoch": 0.63, + "learning_rate": 7.333230705208134e-06, + "loss": 1.3328, + "step": 5982 + }, + { + "epoch": 0.63, + "learning_rate": 7.3297031862045676e-06, + "loss": 1.2857, + "step": 5983 + }, + { + "epoch": 0.63, + "learning_rate": 7.3261760249521655e-06, + "loss": 1.9065, + "step": 5984 + }, + { + "epoch": 0.63, + "learning_rate": 7.322649221923473e-06, + "loss": 1.3797, + "step": 5985 + }, + { + "epoch": 0.63, + "learning_rate": 7.3191227775909925e-06, + "loss": 1.2343, + "step": 5986 + }, + { + "epoch": 0.63, + "learning_rate": 7.315596692427178e-06, + "loss": 1.3479, + "step": 5987 + }, + { + "epoch": 0.63, + "learning_rate": 7.312070966904432e-06, + "loss": 1.3226, + "step": 5988 + }, + { + "epoch": 0.63, + "learning_rate": 7.308545601495114e-06, + "loss": 1.3329, + "step": 5989 + }, + { + "epoch": 0.63, + "learning_rate": 7.305020596671528e-06, + "loss": 1.3285, + "step": 5990 + }, + { + "epoch": 0.63, + "learning_rate": 7.301495952905939e-06, + "loss": 1.3635, + "step": 5991 + }, + { + "epoch": 0.63, + "learning_rate": 7.297971670670556e-06, + "loss": 1.3343, + "step": 5992 + }, + { + "epoch": 0.63, + "learning_rate": 7.294447750437543e-06, + "loss": 1.3943, + "step": 5993 + }, + { + "epoch": 0.63, + "learning_rate": 7.290924192679014e-06, + "loss": 1.4601, + "step": 5994 + }, + { + "epoch": 0.63, + "learning_rate": 7.287400997867036e-06, + "loss": 1.3813, + "step": 5995 + }, + { + "epoch": 0.63, + "learning_rate": 7.2838781664736266e-06, + "loss": 1.3505, + "step": 5996 + }, + { + "epoch": 0.63, + "learning_rate": 7.2803556989707555e-06, + "loss": 1.3062, + "step": 5997 + }, + { + "epoch": 0.63, + "learning_rate": 7.276833595830338e-06, + "loss": 1.4504, + "step": 5998 + }, + { + "epoch": 0.63, + "learning_rate": 7.273311857524252e-06, + "loss": 1.4935, + "step": 5999 + }, + { + "epoch": 0.63, + "learning_rate": 7.269790484524317e-06, + "loss": 1.296, + "step": 6000 + }, + { + "epoch": 0.63, + "learning_rate": 7.266269477302308e-06, + "loss": 1.3469, + "step": 6001 + }, + { + "epoch": 0.63, + "learning_rate": 7.262748836329944e-06, + "loss": 1.3586, + "step": 6002 + }, + { + "epoch": 0.63, + "learning_rate": 7.259228562078908e-06, + "loss": 1.3643, + "step": 6003 + }, + { + "epoch": 0.63, + "learning_rate": 7.255708655020821e-06, + "loss": 1.3096, + "step": 6004 + }, + { + "epoch": 0.63, + "learning_rate": 7.252189115627264e-06, + "loss": 1.3163, + "step": 6005 + }, + { + "epoch": 0.63, + "learning_rate": 7.2486699443697595e-06, + "loss": 1.3526, + "step": 6006 + }, + { + "epoch": 0.63, + "learning_rate": 7.245151141719793e-06, + "loss": 1.401, + "step": 6007 + }, + { + "epoch": 0.63, + "learning_rate": 7.241632708148788e-06, + "loss": 1.2651, + "step": 6008 + }, + { + "epoch": 0.63, + "learning_rate": 7.238114644128124e-06, + "loss": 1.348, + "step": 6009 + }, + { + "epoch": 0.63, + "learning_rate": 7.234596950129137e-06, + "loss": 1.6934, + "step": 6010 + }, + { + "epoch": 0.63, + "learning_rate": 7.231079626623103e-06, + "loss": 1.3382, + "step": 6011 + }, + { + "epoch": 0.63, + "learning_rate": 7.227562674081254e-06, + "loss": 1.2925, + "step": 6012 + }, + { + "epoch": 0.63, + "learning_rate": 7.22404609297477e-06, + "loss": 1.3365, + "step": 6013 + }, + { + "epoch": 0.63, + "learning_rate": 7.220529883774785e-06, + "loss": 1.3169, + "step": 6014 + }, + { + "epoch": 0.63, + "learning_rate": 7.217014046952379e-06, + "loss": 1.319, + "step": 6015 + }, + { + "epoch": 0.63, + "learning_rate": 7.2134985829785846e-06, + "loss": 1.4049, + "step": 6016 + }, + { + "epoch": 0.63, + "learning_rate": 7.209983492324382e-06, + "loss": 1.2947, + "step": 6017 + }, + { + "epoch": 0.63, + "learning_rate": 7.206468775460704e-06, + "loss": 1.2854, + "step": 6018 + }, + { + "epoch": 0.63, + "learning_rate": 7.202954432858436e-06, + "loss": 1.3381, + "step": 6019 + }, + { + "epoch": 0.63, + "learning_rate": 7.199440464988403e-06, + "loss": 1.3912, + "step": 6020 + }, + { + "epoch": 0.63, + "learning_rate": 7.195926872321391e-06, + "loss": 1.384, + "step": 6021 + }, + { + "epoch": 0.63, + "learning_rate": 7.192413655328129e-06, + "loss": 1.2909, + "step": 6022 + }, + { + "epoch": 0.63, + "learning_rate": 7.188900814479299e-06, + "loss": 1.2951, + "step": 6023 + }, + { + "epoch": 0.63, + "learning_rate": 7.185388350245532e-06, + "loss": 1.2655, + "step": 6024 + }, + { + "epoch": 0.63, + "learning_rate": 7.1818762630974035e-06, + "loss": 1.3288, + "step": 6025 + }, + { + "epoch": 0.63, + "learning_rate": 7.17836455350545e-06, + "loss": 1.2873, + "step": 6026 + }, + { + "epoch": 0.63, + "learning_rate": 7.174853221940146e-06, + "loss": 1.3027, + "step": 6027 + }, + { + "epoch": 0.63, + "learning_rate": 7.17134226887192e-06, + "loss": 1.3273, + "step": 6028 + }, + { + "epoch": 0.63, + "learning_rate": 7.167831694771149e-06, + "loss": 1.3096, + "step": 6029 + }, + { + "epoch": 0.63, + "learning_rate": 7.1643215001081625e-06, + "loss": 1.2904, + "step": 6030 + }, + { + "epoch": 0.63, + "learning_rate": 7.160811685353234e-06, + "loss": 1.2977, + "step": 6031 + }, + { + "epoch": 0.63, + "learning_rate": 7.157302250976588e-06, + "loss": 1.3281, + "step": 6032 + }, + { + "epoch": 0.63, + "learning_rate": 7.1537931974483996e-06, + "loss": 1.3831, + "step": 6033 + }, + { + "epoch": 0.63, + "learning_rate": 7.150284525238794e-06, + "loss": 1.3173, + "step": 6034 + }, + { + "epoch": 0.63, + "learning_rate": 7.146776234817841e-06, + "loss": 1.4148, + "step": 6035 + }, + { + "epoch": 0.63, + "learning_rate": 7.143268326655557e-06, + "loss": 1.3381, + "step": 6036 + }, + { + "epoch": 0.63, + "learning_rate": 7.13976080122192e-06, + "loss": 1.3221, + "step": 6037 + }, + { + "epoch": 0.63, + "learning_rate": 7.136253658986843e-06, + "loss": 1.4373, + "step": 6038 + }, + { + "epoch": 0.63, + "learning_rate": 7.132746900420195e-06, + "loss": 1.3758, + "step": 6039 + }, + { + "epoch": 0.63, + "learning_rate": 7.129240525991788e-06, + "loss": 1.3964, + "step": 6040 + }, + { + "epoch": 0.63, + "learning_rate": 7.125734536171391e-06, + "loss": 1.3136, + "step": 6041 + }, + { + "epoch": 0.63, + "learning_rate": 7.122228931428715e-06, + "loss": 1.2195, + "step": 6042 + }, + { + "epoch": 0.63, + "learning_rate": 7.11872371223342e-06, + "loss": 1.3842, + "step": 6043 + }, + { + "epoch": 0.63, + "learning_rate": 7.115218879055113e-06, + "loss": 1.3369, + "step": 6044 + }, + { + "epoch": 0.63, + "learning_rate": 7.111714432363356e-06, + "loss": 1.2704, + "step": 6045 + }, + { + "epoch": 0.63, + "learning_rate": 7.108210372627653e-06, + "loss": 1.307, + "step": 6046 + }, + { + "epoch": 0.63, + "learning_rate": 7.104706700317459e-06, + "loss": 1.3024, + "step": 6047 + }, + { + "epoch": 0.63, + "learning_rate": 7.1012034159021715e-06, + "loss": 1.4157, + "step": 6048 + }, + { + "epoch": 0.63, + "learning_rate": 7.0977005198511475e-06, + "loss": 1.2314, + "step": 6049 + }, + { + "epoch": 0.63, + "learning_rate": 7.09419801263368e-06, + "loss": 1.4304, + "step": 6050 + }, + { + "epoch": 0.63, + "learning_rate": 7.090695894719019e-06, + "loss": 1.3085, + "step": 6051 + }, + { + "epoch": 0.63, + "learning_rate": 7.0871941665763525e-06, + "loss": 1.367, + "step": 6052 + }, + { + "epoch": 0.63, + "learning_rate": 7.083692828674827e-06, + "loss": 1.2913, + "step": 6053 + }, + { + "epoch": 0.63, + "learning_rate": 7.080191881483531e-06, + "loss": 1.3751, + "step": 6054 + }, + { + "epoch": 0.63, + "learning_rate": 7.0766913254714985e-06, + "loss": 1.3178, + "step": 6055 + }, + { + "epoch": 0.64, + "learning_rate": 7.07319116110772e-06, + "loss": 1.3182, + "step": 6056 + }, + { + "epoch": 0.64, + "learning_rate": 7.069691388861122e-06, + "loss": 1.373, + "step": 6057 + }, + { + "epoch": 0.64, + "learning_rate": 7.066192009200588e-06, + "loss": 1.3235, + "step": 6058 + }, + { + "epoch": 0.64, + "learning_rate": 7.0626930225949395e-06, + "loss": 1.3765, + "step": 6059 + }, + { + "epoch": 0.64, + "learning_rate": 7.0591944295129565e-06, + "loss": 1.4408, + "step": 6060 + }, + { + "epoch": 0.64, + "learning_rate": 7.055696230423359e-06, + "loss": 1.3271, + "step": 6061 + }, + { + "epoch": 0.64, + "learning_rate": 7.052198425794814e-06, + "loss": 1.2194, + "step": 6062 + }, + { + "epoch": 0.64, + "learning_rate": 7.048701016095938e-06, + "loss": 1.3707, + "step": 6063 + }, + { + "epoch": 0.64, + "learning_rate": 7.045204001795296e-06, + "loss": 1.3878, + "step": 6064 + }, + { + "epoch": 0.64, + "learning_rate": 7.041707383361396e-06, + "loss": 1.3674, + "step": 6065 + }, + { + "epoch": 0.64, + "learning_rate": 7.038211161262697e-06, + "loss": 1.4525, + "step": 6066 + }, + { + "epoch": 0.64, + "learning_rate": 7.034715335967599e-06, + "loss": 1.3801, + "step": 6067 + }, + { + "epoch": 0.64, + "learning_rate": 7.031219907944458e-06, + "loss": 1.4855, + "step": 6068 + }, + { + "epoch": 0.64, + "learning_rate": 7.027724877661568e-06, + "loss": 1.3659, + "step": 6069 + }, + { + "epoch": 0.64, + "learning_rate": 7.024230245587176e-06, + "loss": 1.3649, + "step": 6070 + }, + { + "epoch": 0.64, + "learning_rate": 7.020736012189467e-06, + "loss": 1.2629, + "step": 6071 + }, + { + "epoch": 0.64, + "learning_rate": 7.017242177936586e-06, + "loss": 1.2474, + "step": 6072 + }, + { + "epoch": 0.64, + "learning_rate": 7.013748743296614e-06, + "loss": 1.45, + "step": 6073 + }, + { + "epoch": 0.64, + "learning_rate": 7.010255708737581e-06, + "loss": 1.3624, + "step": 6074 + }, + { + "epoch": 0.64, + "learning_rate": 7.006763074727461e-06, + "loss": 0.9335, + "step": 6075 + }, + { + "epoch": 0.64, + "learning_rate": 7.0032708417341835e-06, + "loss": 0.6376, + "step": 6076 + }, + { + "epoch": 0.64, + "learning_rate": 6.999779010225613e-06, + "loss": 0.7882, + "step": 6077 + }, + { + "epoch": 0.64, + "learning_rate": 6.996287580669567e-06, + "loss": 1.3001, + "step": 6078 + }, + { + "epoch": 0.64, + "learning_rate": 6.9927965535338085e-06, + "loss": 1.323, + "step": 6079 + }, + { + "epoch": 0.64, + "learning_rate": 6.989305929286043e-06, + "loss": 1.3478, + "step": 6080 + }, + { + "epoch": 0.64, + "learning_rate": 6.985815708393928e-06, + "loss": 1.319, + "step": 6081 + }, + { + "epoch": 0.64, + "learning_rate": 6.9823258913250566e-06, + "loss": 1.3458, + "step": 6082 + }, + { + "epoch": 0.64, + "learning_rate": 6.978836478546985e-06, + "loss": 1.2481, + "step": 6083 + }, + { + "epoch": 0.64, + "learning_rate": 6.975347470527195e-06, + "loss": 1.4051, + "step": 6084 + }, + { + "epoch": 0.64, + "learning_rate": 6.97185886773313e-06, + "loss": 1.3705, + "step": 6085 + }, + { + "epoch": 0.64, + "learning_rate": 6.9683706706321676e-06, + "loss": 1.3415, + "step": 6086 + }, + { + "epoch": 0.64, + "learning_rate": 6.964882879691643e-06, + "loss": 1.3462, + "step": 6087 + }, + { + "epoch": 0.64, + "learning_rate": 6.961395495378829e-06, + "loss": 1.2974, + "step": 6088 + }, + { + "epoch": 0.64, + "learning_rate": 6.957908518160943e-06, + "loss": 1.3353, + "step": 6089 + }, + { + "epoch": 0.64, + "learning_rate": 6.95442194850515e-06, + "loss": 1.3073, + "step": 6090 + }, + { + "epoch": 0.64, + "learning_rate": 6.9509357868785636e-06, + "loss": 1.352, + "step": 6091 + }, + { + "epoch": 0.64, + "learning_rate": 6.9474500337482396e-06, + "loss": 1.2771, + "step": 6092 + }, + { + "epoch": 0.64, + "learning_rate": 6.943964689581177e-06, + "loss": 1.2925, + "step": 6093 + }, + { + "epoch": 0.64, + "learning_rate": 6.940479754844322e-06, + "loss": 1.2967, + "step": 6094 + }, + { + "epoch": 0.64, + "learning_rate": 6.93699523000457e-06, + "loss": 1.5839, + "step": 6095 + }, + { + "epoch": 0.64, + "learning_rate": 6.933511115528757e-06, + "loss": 1.3051, + "step": 6096 + }, + { + "epoch": 0.64, + "learning_rate": 6.930027411883664e-06, + "loss": 1.5344, + "step": 6097 + }, + { + "epoch": 0.64, + "learning_rate": 6.926544119536014e-06, + "loss": 1.3938, + "step": 6098 + }, + { + "epoch": 0.64, + "learning_rate": 6.923061238952484e-06, + "loss": 1.3504, + "step": 6099 + }, + { + "epoch": 0.64, + "learning_rate": 6.919578770599689e-06, + "loss": 1.3618, + "step": 6100 + }, + { + "epoch": 0.64, + "learning_rate": 6.916096714944187e-06, + "loss": 1.3811, + "step": 6101 + }, + { + "epoch": 0.64, + "learning_rate": 6.912615072452491e-06, + "loss": 1.2673, + "step": 6102 + }, + { + "epoch": 0.64, + "learning_rate": 6.909133843591046e-06, + "loss": 1.3661, + "step": 6103 + }, + { + "epoch": 0.64, + "learning_rate": 6.905653028826249e-06, + "loss": 1.3811, + "step": 6104 + }, + { + "epoch": 0.64, + "learning_rate": 6.902172628624437e-06, + "loss": 1.3399, + "step": 6105 + }, + { + "epoch": 0.64, + "learning_rate": 6.8986926434519e-06, + "loss": 1.281, + "step": 6106 + }, + { + "epoch": 0.64, + "learning_rate": 6.895213073774862e-06, + "loss": 1.3053, + "step": 6107 + }, + { + "epoch": 0.64, + "learning_rate": 6.891733920059498e-06, + "loss": 1.4573, + "step": 6108 + }, + { + "epoch": 0.64, + "learning_rate": 6.8882551827719215e-06, + "loss": 1.355, + "step": 6109 + }, + { + "epoch": 0.64, + "learning_rate": 6.8847768623782e-06, + "loss": 1.3304, + "step": 6110 + }, + { + "epoch": 0.64, + "learning_rate": 6.881298959344335e-06, + "loss": 1.4039, + "step": 6111 + }, + { + "epoch": 0.64, + "learning_rate": 6.877821474136277e-06, + "loss": 1.381, + "step": 6112 + }, + { + "epoch": 0.64, + "learning_rate": 6.874344407219917e-06, + "loss": 1.3503, + "step": 6113 + }, + { + "epoch": 0.64, + "learning_rate": 6.870867759061099e-06, + "loss": 1.2679, + "step": 6114 + }, + { + "epoch": 0.64, + "learning_rate": 6.8673915301256e-06, + "loss": 1.3286, + "step": 6115 + }, + { + "epoch": 0.64, + "learning_rate": 6.863915720879146e-06, + "loss": 1.3528, + "step": 6116 + }, + { + "epoch": 0.64, + "learning_rate": 6.8604403317874055e-06, + "loss": 1.3502, + "step": 6117 + }, + { + "epoch": 0.64, + "learning_rate": 6.856965363315993e-06, + "loss": 1.3507, + "step": 6118 + }, + { + "epoch": 0.64, + "learning_rate": 6.853490815930464e-06, + "loss": 1.2153, + "step": 6119 + }, + { + "epoch": 0.64, + "learning_rate": 6.850016690096319e-06, + "loss": 1.2435, + "step": 6120 + }, + { + "epoch": 0.64, + "learning_rate": 6.846542986279e-06, + "loss": 1.3418, + "step": 6121 + }, + { + "epoch": 0.64, + "learning_rate": 6.843069704943896e-06, + "loss": 1.371, + "step": 6122 + }, + { + "epoch": 0.64, + "learning_rate": 6.8395968465563375e-06, + "loss": 1.1737, + "step": 6123 + }, + { + "epoch": 0.64, + "learning_rate": 6.836124411581598e-06, + "loss": 1.3402, + "step": 6124 + }, + { + "epoch": 0.64, + "learning_rate": 6.8326524004848924e-06, + "loss": 1.3482, + "step": 6125 + }, + { + "epoch": 0.64, + "learning_rate": 6.8291808137313845e-06, + "loss": 1.4585, + "step": 6126 + }, + { + "epoch": 0.64, + "learning_rate": 6.825709651786176e-06, + "loss": 1.2848, + "step": 6127 + }, + { + "epoch": 0.64, + "learning_rate": 6.822238915114312e-06, + "loss": 1.2932, + "step": 6128 + }, + { + "epoch": 0.64, + "learning_rate": 6.818768604180785e-06, + "loss": 1.3124, + "step": 6129 + }, + { + "epoch": 0.64, + "learning_rate": 6.815298719450525e-06, + "loss": 1.2843, + "step": 6130 + }, + { + "epoch": 0.64, + "learning_rate": 6.811829261388409e-06, + "loss": 1.3024, + "step": 6131 + }, + { + "epoch": 0.64, + "learning_rate": 6.808360230459252e-06, + "loss": 1.3612, + "step": 6132 + }, + { + "epoch": 0.64, + "learning_rate": 6.804891627127821e-06, + "loss": 1.3005, + "step": 6133 + }, + { + "epoch": 0.64, + "learning_rate": 6.8014234518588154e-06, + "loss": 1.2614, + "step": 6134 + }, + { + "epoch": 0.64, + "learning_rate": 6.7979557051168835e-06, + "loss": 1.3717, + "step": 6135 + }, + { + "epoch": 0.64, + "learning_rate": 6.794488387366609e-06, + "loss": 1.3873, + "step": 6136 + }, + { + "epoch": 0.64, + "learning_rate": 6.791021499072532e-06, + "loss": 1.2955, + "step": 6137 + }, + { + "epoch": 0.64, + "learning_rate": 6.787555040699121e-06, + "loss": 1.4217, + "step": 6138 + }, + { + "epoch": 0.64, + "learning_rate": 6.784089012710793e-06, + "loss": 1.3805, + "step": 6139 + }, + { + "epoch": 0.64, + "learning_rate": 6.7806234155719055e-06, + "loss": 1.3982, + "step": 6140 + }, + { + "epoch": 0.64, + "learning_rate": 6.7771582497467635e-06, + "loss": 1.4, + "step": 6141 + }, + { + "epoch": 0.64, + "learning_rate": 6.773693515699607e-06, + "loss": 1.439, + "step": 6142 + }, + { + "epoch": 0.64, + "learning_rate": 6.7702292138946235e-06, + "loss": 1.3672, + "step": 6143 + }, + { + "epoch": 0.64, + "learning_rate": 6.7667653447959355e-06, + "loss": 1.2901, + "step": 6144 + }, + { + "epoch": 0.64, + "learning_rate": 6.763301908867619e-06, + "loss": 1.2873, + "step": 6145 + }, + { + "epoch": 0.64, + "learning_rate": 6.759838906573684e-06, + "loss": 1.3582, + "step": 6146 + }, + { + "epoch": 0.64, + "learning_rate": 6.756376338378077e-06, + "loss": 1.3562, + "step": 6147 + }, + { + "epoch": 0.64, + "learning_rate": 6.7529142047447025e-06, + "loss": 1.3091, + "step": 6148 + }, + { + "epoch": 0.64, + "learning_rate": 6.749452506137393e-06, + "loss": 1.4269, + "step": 6149 + }, + { + "epoch": 0.64, + "learning_rate": 6.745991243019927e-06, + "loss": 1.4184, + "step": 6150 + }, + { + "epoch": 0.65, + "learning_rate": 6.7425304158560235e-06, + "loss": 1.4201, + "step": 6151 + }, + { + "epoch": 0.65, + "learning_rate": 6.739070025109349e-06, + "loss": 1.3222, + "step": 6152 + }, + { + "epoch": 0.65, + "learning_rate": 6.7356100712435035e-06, + "loss": 1.3262, + "step": 6153 + }, + { + "epoch": 0.65, + "learning_rate": 6.732150554722034e-06, + "loss": 1.4408, + "step": 6154 + }, + { + "epoch": 0.65, + "learning_rate": 6.728691476008422e-06, + "loss": 1.3441, + "step": 6155 + }, + { + "epoch": 0.65, + "learning_rate": 6.725232835566102e-06, + "loss": 1.3316, + "step": 6156 + }, + { + "epoch": 0.65, + "learning_rate": 6.721774633858438e-06, + "loss": 1.3326, + "step": 6157 + }, + { + "epoch": 0.65, + "learning_rate": 6.7183168713487425e-06, + "loss": 1.3105, + "step": 6158 + }, + { + "epoch": 0.65, + "learning_rate": 6.714859548500265e-06, + "loss": 1.3144, + "step": 6159 + }, + { + "epoch": 0.65, + "learning_rate": 6.7114026657762e-06, + "loss": 1.3472, + "step": 6160 + }, + { + "epoch": 0.65, + "learning_rate": 6.707946223639681e-06, + "loss": 1.3811, + "step": 6161 + }, + { + "epoch": 0.65, + "learning_rate": 6.704490222553781e-06, + "loss": 1.2783, + "step": 6162 + }, + { + "epoch": 0.65, + "learning_rate": 6.701034662981513e-06, + "loss": 1.273, + "step": 6163 + }, + { + "epoch": 0.65, + "learning_rate": 6.697579545385839e-06, + "loss": 1.3522, + "step": 6164 + }, + { + "epoch": 0.65, + "learning_rate": 6.6941248702296524e-06, + "loss": 1.3861, + "step": 6165 + }, + { + "epoch": 0.65, + "learning_rate": 6.6906706379757915e-06, + "loss": 1.3098, + "step": 6166 + }, + { + "epoch": 0.65, + "learning_rate": 6.687216849087032e-06, + "loss": 1.3734, + "step": 6167 + }, + { + "epoch": 0.65, + "learning_rate": 6.6837635040261e-06, + "loss": 1.2289, + "step": 6168 + }, + { + "epoch": 0.65, + "learning_rate": 6.680310603255648e-06, + "loss": 1.3238, + "step": 6169 + }, + { + "epoch": 0.65, + "eval_loss": 1.40826416015625, + "eval_runtime": 77.483, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 6169 + }, + { + "epoch": 0.65, + "learning_rate": 6.676858147238277e-06, + "loss": 1.4317, + "step": 6170 + }, + { + "epoch": 0.65, + "learning_rate": 6.673406136436531e-06, + "loss": 1.3363, + "step": 6171 + }, + { + "epoch": 0.65, + "learning_rate": 6.669954571312889e-06, + "loss": 1.3377, + "step": 6172 + }, + { + "epoch": 0.65, + "learning_rate": 6.666503452329771e-06, + "loss": 1.3382, + "step": 6173 + }, + { + "epoch": 0.65, + "learning_rate": 6.663052779949538e-06, + "loss": 1.3028, + "step": 6174 + }, + { + "epoch": 0.65, + "learning_rate": 6.659602554634494e-06, + "loss": 1.3098, + "step": 6175 + }, + { + "epoch": 0.65, + "learning_rate": 6.656152776846879e-06, + "loss": 1.328, + "step": 6176 + }, + { + "epoch": 0.65, + "learning_rate": 6.652703447048874e-06, + "loss": 1.3014, + "step": 6177 + }, + { + "epoch": 0.65, + "learning_rate": 6.6492545657026e-06, + "loss": 1.2522, + "step": 6178 + }, + { + "epoch": 0.65, + "learning_rate": 6.645806133270121e-06, + "loss": 1.6113, + "step": 6179 + }, + { + "epoch": 0.65, + "learning_rate": 6.642358150213437e-06, + "loss": 1.3431, + "step": 6180 + }, + { + "epoch": 0.65, + "learning_rate": 6.638910616994489e-06, + "loss": 1.2725, + "step": 6181 + }, + { + "epoch": 0.65, + "learning_rate": 6.635463534075156e-06, + "loss": 1.3022, + "step": 6182 + }, + { + "epoch": 0.65, + "learning_rate": 6.632016901917262e-06, + "loss": 1.3496, + "step": 6183 + }, + { + "epoch": 0.65, + "learning_rate": 6.628570720982567e-06, + "loss": 1.2871, + "step": 6184 + }, + { + "epoch": 0.65, + "learning_rate": 6.625124991732767e-06, + "loss": 1.4449, + "step": 6185 + }, + { + "epoch": 0.65, + "learning_rate": 6.621679714629504e-06, + "loss": 1.4395, + "step": 6186 + }, + { + "epoch": 0.65, + "learning_rate": 6.618234890134356e-06, + "loss": 1.4088, + "step": 6187 + }, + { + "epoch": 0.65, + "learning_rate": 6.614790518708843e-06, + "loss": 1.371, + "step": 6188 + }, + { + "epoch": 0.65, + "learning_rate": 6.611346600814419e-06, + "loss": 1.28, + "step": 6189 + }, + { + "epoch": 0.65, + "learning_rate": 6.607903136912482e-06, + "loss": 1.3502, + "step": 6190 + }, + { + "epoch": 0.65, + "learning_rate": 6.604460127464367e-06, + "loss": 1.3398, + "step": 6191 + }, + { + "epoch": 0.65, + "learning_rate": 6.60101757293135e-06, + "loss": 1.4762, + "step": 6192 + }, + { + "epoch": 0.65, + "learning_rate": 6.5975754737746426e-06, + "loss": 1.2981, + "step": 6193 + }, + { + "epoch": 0.65, + "learning_rate": 6.594133830455401e-06, + "loss": 1.3728, + "step": 6194 + }, + { + "epoch": 0.65, + "learning_rate": 6.590692643434715e-06, + "loss": 1.3551, + "step": 6195 + }, + { + "epoch": 0.65, + "learning_rate": 6.5872519131736155e-06, + "loss": 1.3031, + "step": 6196 + }, + { + "epoch": 0.65, + "learning_rate": 6.583811640133071e-06, + "loss": 1.3231, + "step": 6197 + }, + { + "epoch": 0.65, + "learning_rate": 6.5803718247739924e-06, + "loss": 1.2752, + "step": 6198 + }, + { + "epoch": 0.65, + "learning_rate": 6.576932467557223e-06, + "loss": 1.3482, + "step": 6199 + }, + { + "epoch": 0.65, + "learning_rate": 6.573493568943552e-06, + "loss": 1.2612, + "step": 6200 + }, + { + "epoch": 0.65, + "learning_rate": 6.570055129393698e-06, + "loss": 1.6302, + "step": 6201 + }, + { + "epoch": 0.65, + "learning_rate": 6.566617149368331e-06, + "loss": 1.303, + "step": 6202 + }, + { + "epoch": 0.65, + "learning_rate": 6.563179629328047e-06, + "loss": 1.3405, + "step": 6203 + }, + { + "epoch": 0.65, + "learning_rate": 6.559742569733385e-06, + "loss": 1.2816, + "step": 6204 + }, + { + "epoch": 0.65, + "learning_rate": 6.556305971044824e-06, + "loss": 1.3834, + "step": 6205 + }, + { + "epoch": 0.65, + "learning_rate": 6.552869833722781e-06, + "loss": 1.3414, + "step": 6206 + }, + { + "epoch": 0.65, + "learning_rate": 6.5494341582276096e-06, + "loss": 1.3278, + "step": 6207 + }, + { + "epoch": 0.65, + "learning_rate": 6.5459989450196024e-06, + "loss": 1.3577, + "step": 6208 + }, + { + "epoch": 0.65, + "learning_rate": 6.542564194558986e-06, + "loss": 1.3104, + "step": 6209 + }, + { + "epoch": 0.65, + "learning_rate": 6.539129907305933e-06, + "loss": 1.3068, + "step": 6210 + }, + { + "epoch": 0.65, + "learning_rate": 6.53569608372055e-06, + "loss": 1.3769, + "step": 6211 + }, + { + "epoch": 0.65, + "learning_rate": 6.5322627242628775e-06, + "loss": 1.2855, + "step": 6212 + }, + { + "epoch": 0.65, + "learning_rate": 6.528829829392898e-06, + "loss": 1.4129, + "step": 6213 + }, + { + "epoch": 0.65, + "learning_rate": 6.525397399570534e-06, + "loss": 1.3631, + "step": 6214 + }, + { + "epoch": 0.65, + "learning_rate": 6.5219654352556435e-06, + "loss": 1.295, + "step": 6215 + }, + { + "epoch": 0.65, + "learning_rate": 6.518533936908016e-06, + "loss": 1.439, + "step": 6216 + }, + { + "epoch": 0.65, + "learning_rate": 6.515102904987389e-06, + "loss": 1.3148, + "step": 6217 + }, + { + "epoch": 0.65, + "learning_rate": 6.511672339953432e-06, + "loss": 1.3898, + "step": 6218 + }, + { + "epoch": 0.65, + "learning_rate": 6.508242242265752e-06, + "loss": 1.3222, + "step": 6219 + }, + { + "epoch": 0.65, + "learning_rate": 6.504812612383891e-06, + "loss": 1.324, + "step": 6220 + }, + { + "epoch": 0.65, + "learning_rate": 6.501383450767336e-06, + "loss": 1.951, + "step": 6221 + }, + { + "epoch": 0.65, + "learning_rate": 6.4979547578755055e-06, + "loss": 1.2878, + "step": 6222 + }, + { + "epoch": 0.65, + "learning_rate": 6.494526534167754e-06, + "loss": 1.3553, + "step": 6223 + }, + { + "epoch": 0.65, + "learning_rate": 6.491098780103375e-06, + "loss": 1.3898, + "step": 6224 + }, + { + "epoch": 0.65, + "learning_rate": 6.487671496141606e-06, + "loss": 1.4333, + "step": 6225 + }, + { + "epoch": 0.65, + "learning_rate": 6.484244682741606e-06, + "loss": 1.4461, + "step": 6226 + }, + { + "epoch": 0.65, + "learning_rate": 6.480818340362487e-06, + "loss": 1.3461, + "step": 6227 + }, + { + "epoch": 0.65, + "learning_rate": 6.4773924694632835e-06, + "loss": 1.3442, + "step": 6228 + }, + { + "epoch": 0.65, + "learning_rate": 6.473967070502982e-06, + "loss": 1.2692, + "step": 6229 + }, + { + "epoch": 0.65, + "learning_rate": 6.470542143940495e-06, + "loss": 1.446, + "step": 6230 + }, + { + "epoch": 0.65, + "learning_rate": 6.467117690234675e-06, + "loss": 1.3597, + "step": 6231 + }, + { + "epoch": 0.65, + "learning_rate": 6.463693709844305e-06, + "loss": 1.3226, + "step": 6232 + }, + { + "epoch": 0.65, + "learning_rate": 6.46027020322812e-06, + "loss": 1.2702, + "step": 6233 + }, + { + "epoch": 0.65, + "learning_rate": 6.456847170844775e-06, + "loss": 1.2554, + "step": 6234 + }, + { + "epoch": 0.65, + "learning_rate": 6.453424613152872e-06, + "loss": 1.2896, + "step": 6235 + }, + { + "epoch": 0.65, + "learning_rate": 6.450002530610943e-06, + "loss": 1.3148, + "step": 6236 + }, + { + "epoch": 0.65, + "learning_rate": 6.4465809236774635e-06, + "loss": 1.3589, + "step": 6237 + }, + { + "epoch": 0.65, + "learning_rate": 6.443159792810838e-06, + "loss": 1.2938, + "step": 6238 + }, + { + "epoch": 0.65, + "learning_rate": 6.439739138469406e-06, + "loss": 1.366, + "step": 6239 + }, + { + "epoch": 0.65, + "learning_rate": 6.436318961111455e-06, + "loss": 1.4772, + "step": 6240 + }, + { + "epoch": 0.65, + "learning_rate": 6.4328992611951975e-06, + "loss": 1.3131, + "step": 6241 + }, + { + "epoch": 0.65, + "learning_rate": 6.429480039178786e-06, + "loss": 1.2382, + "step": 6242 + }, + { + "epoch": 0.65, + "learning_rate": 6.426061295520304e-06, + "loss": 1.3394, + "step": 6243 + }, + { + "epoch": 0.65, + "learning_rate": 6.422643030677782e-06, + "loss": 1.321, + "step": 6244 + }, + { + "epoch": 0.65, + "learning_rate": 6.419225245109175e-06, + "loss": 1.3478, + "step": 6245 + }, + { + "epoch": 0.65, + "learning_rate": 6.415807939272383e-06, + "loss": 1.3249, + "step": 6246 + }, + { + "epoch": 0.66, + "learning_rate": 6.412391113625231e-06, + "loss": 1.3602, + "step": 6247 + }, + { + "epoch": 0.66, + "learning_rate": 6.408974768625491e-06, + "loss": 1.2799, + "step": 6248 + }, + { + "epoch": 0.66, + "learning_rate": 6.405558904730863e-06, + "loss": 1.3911, + "step": 6249 + }, + { + "epoch": 0.66, + "learning_rate": 6.402143522398987e-06, + "loss": 1.3185, + "step": 6250 + }, + { + "epoch": 0.66, + "learning_rate": 6.398728622087431e-06, + "loss": 1.3198, + "step": 6251 + }, + { + "epoch": 0.66, + "learning_rate": 6.395314204253711e-06, + "loss": 1.361, + "step": 6252 + }, + { + "epoch": 0.66, + "learning_rate": 6.391900269355269e-06, + "loss": 1.3285, + "step": 6253 + }, + { + "epoch": 0.66, + "learning_rate": 6.388486817849484e-06, + "loss": 1.3097, + "step": 6254 + }, + { + "epoch": 0.66, + "learning_rate": 6.385073850193667e-06, + "loss": 1.3057, + "step": 6255 + }, + { + "epoch": 0.66, + "learning_rate": 6.381661366845075e-06, + "loss": 1.4733, + "step": 6256 + }, + { + "epoch": 0.66, + "learning_rate": 6.378249368260889e-06, + "loss": 1.3571, + "step": 6257 + }, + { + "epoch": 0.66, + "learning_rate": 6.374837854898228e-06, + "loss": 1.3278, + "step": 6258 + }, + { + "epoch": 0.66, + "learning_rate": 6.37142682721415e-06, + "loss": 1.3035, + "step": 6259 + }, + { + "epoch": 0.66, + "learning_rate": 6.368016285665645e-06, + "loss": 1.397, + "step": 6260 + }, + { + "epoch": 0.66, + "learning_rate": 6.3646062307096365e-06, + "loss": 1.353, + "step": 6261 + }, + { + "epoch": 0.66, + "learning_rate": 6.361196662802982e-06, + "loss": 1.3534, + "step": 6262 + }, + { + "epoch": 0.66, + "learning_rate": 6.357787582402482e-06, + "loss": 1.3132, + "step": 6263 + }, + { + "epoch": 0.66, + "learning_rate": 6.3543789899648624e-06, + "loss": 1.3551, + "step": 6264 + }, + { + "epoch": 0.66, + "learning_rate": 6.3509708859467855e-06, + "loss": 1.4205, + "step": 6265 + }, + { + "epoch": 0.66, + "learning_rate": 6.347563270804851e-06, + "loss": 1.341, + "step": 6266 + }, + { + "epoch": 0.66, + "learning_rate": 6.344156144995593e-06, + "loss": 1.5188, + "step": 6267 + }, + { + "epoch": 0.66, + "learning_rate": 6.340749508975477e-06, + "loss": 1.4404, + "step": 6268 + }, + { + "epoch": 0.66, + "learning_rate": 6.337343363200905e-06, + "loss": 1.3026, + "step": 6269 + }, + { + "epoch": 0.66, + "learning_rate": 6.3339377081282124e-06, + "loss": 1.3315, + "step": 6270 + }, + { + "epoch": 0.66, + "learning_rate": 6.3305325442136735e-06, + "loss": 1.2503, + "step": 6271 + }, + { + "epoch": 0.66, + "learning_rate": 6.3271278719134885e-06, + "loss": 1.1776, + "step": 6272 + }, + { + "epoch": 0.66, + "learning_rate": 6.323723691683798e-06, + "loss": 1.3033, + "step": 6273 + }, + { + "epoch": 0.66, + "learning_rate": 6.320320003980671e-06, + "loss": 1.3838, + "step": 6274 + }, + { + "epoch": 0.66, + "learning_rate": 6.3169168092601195e-06, + "loss": 1.3691, + "step": 6275 + }, + { + "epoch": 0.66, + "learning_rate": 6.313514107978083e-06, + "loss": 1.3665, + "step": 6276 + }, + { + "epoch": 0.66, + "learning_rate": 6.310111900590432e-06, + "loss": 1.358, + "step": 6277 + }, + { + "epoch": 0.66, + "learning_rate": 6.306710187552978e-06, + "loss": 1.1708, + "step": 6278 + }, + { + "epoch": 0.66, + "learning_rate": 6.303308969321464e-06, + "loss": 1.331, + "step": 6279 + }, + { + "epoch": 0.66, + "learning_rate": 6.299908246351566e-06, + "loss": 1.3914, + "step": 6280 + }, + { + "epoch": 0.66, + "learning_rate": 6.2965080190988896e-06, + "loss": 1.3183, + "step": 6281 + }, + { + "epoch": 0.66, + "learning_rate": 6.293108288018981e-06, + "loss": 1.2969, + "step": 6282 + }, + { + "epoch": 0.66, + "learning_rate": 6.289709053567318e-06, + "loss": 1.2892, + "step": 6283 + }, + { + "epoch": 0.66, + "learning_rate": 6.2863103161993085e-06, + "loss": 1.3517, + "step": 6284 + }, + { + "epoch": 0.66, + "learning_rate": 6.282912076370295e-06, + "loss": 1.3329, + "step": 6285 + }, + { + "epoch": 0.66, + "learning_rate": 6.279514334535557e-06, + "loss": 1.3396, + "step": 6286 + }, + { + "epoch": 0.66, + "learning_rate": 6.276117091150304e-06, + "loss": 1.3878, + "step": 6287 + }, + { + "epoch": 0.66, + "learning_rate": 6.272720346669677e-06, + "loss": 1.2608, + "step": 6288 + }, + { + "epoch": 0.66, + "learning_rate": 6.269324101548754e-06, + "loss": 1.3605, + "step": 6289 + }, + { + "epoch": 0.66, + "learning_rate": 6.265928356242546e-06, + "loss": 1.2682, + "step": 6290 + }, + { + "epoch": 0.66, + "learning_rate": 6.262533111205995e-06, + "loss": 1.3426, + "step": 6291 + }, + { + "epoch": 0.66, + "learning_rate": 6.259138366893975e-06, + "loss": 1.2987, + "step": 6292 + }, + { + "epoch": 0.66, + "learning_rate": 6.255744123761295e-06, + "loss": 1.3521, + "step": 6293 + }, + { + "epoch": 0.66, + "learning_rate": 6.252350382262697e-06, + "loss": 1.2816, + "step": 6294 + }, + { + "epoch": 0.66, + "learning_rate": 6.248957142852856e-06, + "loss": 1.3884, + "step": 6295 + }, + { + "epoch": 0.66, + "learning_rate": 6.2455644059863795e-06, + "loss": 1.3545, + "step": 6296 + }, + { + "epoch": 0.66, + "learning_rate": 6.2421721721178015e-06, + "loss": 1.3636, + "step": 6297 + }, + { + "epoch": 0.66, + "learning_rate": 6.238780441701601e-06, + "loss": 1.3584, + "step": 6298 + }, + { + "epoch": 0.66, + "learning_rate": 6.235389215192179e-06, + "loss": 1.3459, + "step": 6299 + }, + { + "epoch": 0.66, + "learning_rate": 6.231998493043875e-06, + "loss": 1.4654, + "step": 6300 + }, + { + "epoch": 0.66, + "learning_rate": 6.228608275710954e-06, + "loss": 1.3628, + "step": 6301 + }, + { + "epoch": 0.66, + "learning_rate": 6.225218563647623e-06, + "loss": 1.3278, + "step": 6302 + }, + { + "epoch": 0.66, + "learning_rate": 6.221829357308016e-06, + "loss": 1.395, + "step": 6303 + }, + { + "epoch": 0.66, + "learning_rate": 6.218440657146196e-06, + "loss": 1.3481, + "step": 6304 + }, + { + "epoch": 0.66, + "learning_rate": 6.215052463616165e-06, + "loss": 1.309, + "step": 6305 + }, + { + "epoch": 0.66, + "learning_rate": 6.211664777171853e-06, + "loss": 1.275, + "step": 6306 + }, + { + "epoch": 0.66, + "learning_rate": 6.208277598267123e-06, + "loss": 1.4885, + "step": 6307 + }, + { + "epoch": 0.66, + "learning_rate": 6.2048909273557686e-06, + "loss": 1.3334, + "step": 6308 + }, + { + "epoch": 0.66, + "learning_rate": 6.201504764891518e-06, + "loss": 1.3399, + "step": 6309 + }, + { + "epoch": 0.66, + "learning_rate": 6.198119111328032e-06, + "loss": 1.3163, + "step": 6310 + }, + { + "epoch": 0.66, + "learning_rate": 6.1947339671188966e-06, + "loss": 1.2746, + "step": 6311 + }, + { + "epoch": 0.66, + "learning_rate": 6.191349332717635e-06, + "loss": 1.2984, + "step": 6312 + }, + { + "epoch": 0.66, + "learning_rate": 6.187965208577705e-06, + "loss": 1.2295, + "step": 6313 + }, + { + "epoch": 0.66, + "learning_rate": 6.18458159515249e-06, + "loss": 1.3424, + "step": 6314 + }, + { + "epoch": 0.66, + "learning_rate": 6.181198492895308e-06, + "loss": 1.3108, + "step": 6315 + }, + { + "epoch": 0.66, + "learning_rate": 6.1778159022594045e-06, + "loss": 1.4895, + "step": 6316 + }, + { + "epoch": 0.66, + "learning_rate": 6.174433823697964e-06, + "loss": 1.3247, + "step": 6317 + }, + { + "epoch": 0.66, + "learning_rate": 6.171052257664097e-06, + "loss": 1.3659, + "step": 6318 + }, + { + "epoch": 0.66, + "learning_rate": 6.167671204610844e-06, + "loss": 1.3889, + "step": 6319 + }, + { + "epoch": 0.66, + "learning_rate": 6.1642906649911815e-06, + "loss": 1.3946, + "step": 6320 + }, + { + "epoch": 0.66, + "learning_rate": 6.1609106392580155e-06, + "loss": 1.3685, + "step": 6321 + }, + { + "epoch": 0.66, + "learning_rate": 6.157531127864181e-06, + "loss": 1.2584, + "step": 6322 + }, + { + "epoch": 0.66, + "learning_rate": 6.154152131262448e-06, + "loss": 1.3263, + "step": 6323 + }, + { + "epoch": 0.66, + "learning_rate": 6.15077364990551e-06, + "loss": 1.3336, + "step": 6324 + }, + { + "epoch": 0.66, + "learning_rate": 6.147395684246003e-06, + "loss": 1.2513, + "step": 6325 + }, + { + "epoch": 0.66, + "learning_rate": 6.144018234736484e-06, + "loss": 1.3715, + "step": 6326 + }, + { + "epoch": 0.66, + "learning_rate": 6.140641301829444e-06, + "loss": 1.3464, + "step": 6327 + }, + { + "epoch": 0.66, + "learning_rate": 6.1372648859773075e-06, + "loss": 1.4374, + "step": 6328 + }, + { + "epoch": 0.66, + "learning_rate": 6.1338889876324285e-06, + "loss": 1.3903, + "step": 6329 + }, + { + "epoch": 0.66, + "learning_rate": 6.130513607247087e-06, + "loss": 1.3715, + "step": 6330 + }, + { + "epoch": 0.66, + "learning_rate": 6.127138745273497e-06, + "loss": 1.3196, + "step": 6331 + }, + { + "epoch": 0.66, + "learning_rate": 6.123764402163808e-06, + "loss": 1.3013, + "step": 6332 + }, + { + "epoch": 0.66, + "learning_rate": 6.120390578370093e-06, + "loss": 1.2751, + "step": 6333 + }, + { + "epoch": 0.66, + "learning_rate": 6.117017274344356e-06, + "loss": 1.2258, + "step": 6334 + }, + { + "epoch": 0.66, + "learning_rate": 6.113644490538533e-06, + "loss": 1.2982, + "step": 6335 + }, + { + "epoch": 0.66, + "learning_rate": 6.110272227404492e-06, + "loss": 1.3124, + "step": 6336 + }, + { + "epoch": 0.66, + "learning_rate": 6.10690048539403e-06, + "loss": 1.2451, + "step": 6337 + }, + { + "epoch": 0.66, + "learning_rate": 6.103529264958874e-06, + "loss": 1.3896, + "step": 6338 + }, + { + "epoch": 0.66, + "learning_rate": 6.100158566550677e-06, + "loss": 1.46, + "step": 6339 + }, + { + "epoch": 0.66, + "learning_rate": 6.096788390621031e-06, + "loss": 1.2965, + "step": 6340 + }, + { + "epoch": 0.66, + "learning_rate": 6.093418737621452e-06, + "loss": 1.2969, + "step": 6341 + }, + { + "epoch": 0.67, + "learning_rate": 6.0900496080033836e-06, + "loss": 1.3988, + "step": 6342 + }, + { + "epoch": 0.67, + "learning_rate": 6.086681002218204e-06, + "loss": 1.351, + "step": 6343 + }, + { + "epoch": 0.67, + "learning_rate": 6.083312920717224e-06, + "loss": 1.3447, + "step": 6344 + }, + { + "epoch": 0.67, + "learning_rate": 6.079945363951674e-06, + "loss": 1.3361, + "step": 6345 + }, + { + "epoch": 0.67, + "learning_rate": 6.076578332372724e-06, + "loss": 1.3688, + "step": 6346 + }, + { + "epoch": 0.67, + "learning_rate": 6.073211826431467e-06, + "loss": 1.2831, + "step": 6347 + }, + { + "epoch": 0.67, + "learning_rate": 6.069845846578931e-06, + "loss": 1.369, + "step": 6348 + }, + { + "epoch": 0.67, + "learning_rate": 6.06648039326607e-06, + "loss": 1.3247, + "step": 6349 + }, + { + "epoch": 0.67, + "learning_rate": 6.063115466943765e-06, + "loss": 1.288, + "step": 6350 + }, + { + "epoch": 0.67, + "learning_rate": 6.0597510680628345e-06, + "loss": 1.0733, + "step": 6351 + }, + { + "epoch": 0.67, + "learning_rate": 6.056387197074021e-06, + "loss": 1.3386, + "step": 6352 + }, + { + "epoch": 0.67, + "learning_rate": 6.053023854427993e-06, + "loss": 1.3682, + "step": 6353 + }, + { + "epoch": 0.67, + "learning_rate": 6.049661040575353e-06, + "loss": 1.5669, + "step": 6354 + }, + { + "epoch": 0.67, + "learning_rate": 6.0462987559666355e-06, + "loss": 1.3432, + "step": 6355 + }, + { + "epoch": 0.67, + "learning_rate": 6.042937001052298e-06, + "loss": 1.327, + "step": 6356 + }, + { + "epoch": 0.67, + "learning_rate": 6.039575776282728e-06, + "loss": 1.3101, + "step": 6357 + }, + { + "epoch": 0.67, + "learning_rate": 6.0362150821082425e-06, + "loss": 1.3239, + "step": 6358 + }, + { + "epoch": 0.67, + "learning_rate": 6.032854918979092e-06, + "loss": 1.435, + "step": 6359 + }, + { + "epoch": 0.67, + "learning_rate": 6.029495287345448e-06, + "loss": 1.3503, + "step": 6360 + }, + { + "epoch": 0.67, + "learning_rate": 6.0261361876574186e-06, + "loss": 1.3356, + "step": 6361 + }, + { + "epoch": 0.67, + "learning_rate": 6.022777620365032e-06, + "loss": 1.3301, + "step": 6362 + }, + { + "epoch": 0.67, + "learning_rate": 6.019419585918255e-06, + "loss": 1.3925, + "step": 6363 + }, + { + "epoch": 0.67, + "learning_rate": 6.016062084766978e-06, + "loss": 1.3794, + "step": 6364 + }, + { + "epoch": 0.67, + "learning_rate": 6.0127051173610155e-06, + "loss": 1.5496, + "step": 6365 + }, + { + "epoch": 0.67, + "learning_rate": 6.009348684150116e-06, + "loss": 1.3227, + "step": 6366 + }, + { + "epoch": 0.67, + "learning_rate": 6.005992785583958e-06, + "loss": 1.3474, + "step": 6367 + }, + { + "epoch": 0.67, + "learning_rate": 6.002637422112143e-06, + "loss": 1.3262, + "step": 6368 + }, + { + "epoch": 0.67, + "eval_loss": 1.4049769639968872, + "eval_runtime": 77.5156, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 6368 + }, + { + "epoch": 0.67, + "learning_rate": 5.999282594184206e-06, + "loss": 1.3083, + "step": 6369 + }, + { + "epoch": 0.67, + "learning_rate": 5.995928302249603e-06, + "loss": 1.323, + "step": 6370 + }, + { + "epoch": 0.67, + "learning_rate": 5.99257454675773e-06, + "loss": 1.3101, + "step": 6371 + }, + { + "epoch": 0.67, + "learning_rate": 5.989221328157899e-06, + "loss": 1.4546, + "step": 6372 + }, + { + "epoch": 0.67, + "learning_rate": 5.985868646899355e-06, + "loss": 1.3315, + "step": 6373 + }, + { + "epoch": 0.67, + "learning_rate": 5.982516503431273e-06, + "loss": 1.3768, + "step": 6374 + }, + { + "epoch": 0.67, + "learning_rate": 5.979164898202755e-06, + "loss": 1.332, + "step": 6375 + }, + { + "epoch": 0.67, + "learning_rate": 5.975813831662829e-06, + "loss": 1.3154, + "step": 6376 + }, + { + "epoch": 0.67, + "learning_rate": 5.972463304260448e-06, + "loss": 1.3636, + "step": 6377 + }, + { + "epoch": 0.67, + "learning_rate": 5.969113316444504e-06, + "loss": 1.3553, + "step": 6378 + }, + { + "epoch": 0.67, + "learning_rate": 5.965763868663803e-06, + "loss": 1.3805, + "step": 6379 + }, + { + "epoch": 0.67, + "learning_rate": 5.962414961367089e-06, + "loss": 1.3096, + "step": 6380 + }, + { + "epoch": 0.67, + "learning_rate": 5.959066595003025e-06, + "loss": 1.326, + "step": 6381 + }, + { + "epoch": 0.67, + "learning_rate": 5.955718770020212e-06, + "loss": 1.3021, + "step": 6382 + }, + { + "epoch": 0.67, + "learning_rate": 5.952371486867168e-06, + "loss": 1.35, + "step": 6383 + }, + { + "epoch": 0.67, + "learning_rate": 5.949024745992344e-06, + "loss": 1.6749, + "step": 6384 + }, + { + "epoch": 0.67, + "learning_rate": 5.945678547844117e-06, + "loss": 1.4931, + "step": 6385 + }, + { + "epoch": 0.67, + "learning_rate": 5.942332892870793e-06, + "loss": 1.284, + "step": 6386 + }, + { + "epoch": 0.67, + "learning_rate": 5.938987781520604e-06, + "loss": 1.3296, + "step": 6387 + }, + { + "epoch": 0.67, + "learning_rate": 5.9356432142417074e-06, + "loss": 1.4837, + "step": 6388 + }, + { + "epoch": 0.67, + "learning_rate": 5.932299191482188e-06, + "loss": 1.3114, + "step": 6389 + }, + { + "epoch": 0.67, + "learning_rate": 5.928955713690063e-06, + "loss": 1.3328, + "step": 6390 + }, + { + "epoch": 0.67, + "learning_rate": 5.92561278131327e-06, + "loss": 1.3163, + "step": 6391 + }, + { + "epoch": 0.67, + "learning_rate": 5.922270394799676e-06, + "loss": 1.3068, + "step": 6392 + }, + { + "epoch": 0.67, + "learning_rate": 5.918928554597073e-06, + "loss": 1.292, + "step": 6393 + }, + { + "epoch": 0.67, + "learning_rate": 5.915587261153186e-06, + "loss": 1.3359, + "step": 6394 + }, + { + "epoch": 0.67, + "learning_rate": 5.912246514915662e-06, + "loss": 1.4109, + "step": 6395 + }, + { + "epoch": 0.67, + "learning_rate": 5.908906316332071e-06, + "loss": 1.3083, + "step": 6396 + }, + { + "epoch": 0.67, + "learning_rate": 5.905566665849917e-06, + "loss": 1.2973, + "step": 6397 + }, + { + "epoch": 0.67, + "learning_rate": 5.902227563916627e-06, + "loss": 1.4159, + "step": 6398 + }, + { + "epoch": 0.67, + "learning_rate": 5.898889010979556e-06, + "loss": 1.287, + "step": 6399 + }, + { + "epoch": 0.67, + "learning_rate": 5.89555100748598e-06, + "loss": 1.2865, + "step": 6400 + }, + { + "epoch": 0.67, + "learning_rate": 5.89221355388311e-06, + "loss": 1.3137, + "step": 6401 + }, + { + "epoch": 0.67, + "learning_rate": 5.8888766506180785e-06, + "loss": 1.2751, + "step": 6402 + }, + { + "epoch": 0.67, + "learning_rate": 5.885540298137944e-06, + "loss": 1.3687, + "step": 6403 + }, + { + "epoch": 0.67, + "learning_rate": 5.882204496889688e-06, + "loss": 1.2941, + "step": 6404 + }, + { + "epoch": 0.67, + "learning_rate": 5.878869247320231e-06, + "loss": 1.2926, + "step": 6405 + }, + { + "epoch": 0.67, + "learning_rate": 5.875534549876404e-06, + "loss": 1.2675, + "step": 6406 + }, + { + "epoch": 0.67, + "learning_rate": 5.872200405004973e-06, + "loss": 1.2806, + "step": 6407 + }, + { + "epoch": 0.67, + "learning_rate": 5.868866813152625e-06, + "loss": 1.3438, + "step": 6408 + }, + { + "epoch": 0.67, + "learning_rate": 5.865533774765981e-06, + "loss": 1.2947, + "step": 6409 + }, + { + "epoch": 0.67, + "learning_rate": 5.862201290291578e-06, + "loss": 1.3643, + "step": 6410 + }, + { + "epoch": 0.67, + "learning_rate": 5.858869360175887e-06, + "loss": 1.2579, + "step": 6411 + }, + { + "epoch": 0.67, + "learning_rate": 5.855537984865296e-06, + "loss": 1.3479, + "step": 6412 + }, + { + "epoch": 0.67, + "learning_rate": 5.852207164806127e-06, + "loss": 1.3239, + "step": 6413 + }, + { + "epoch": 0.67, + "learning_rate": 5.848876900444626e-06, + "loss": 1.2644, + "step": 6414 + }, + { + "epoch": 0.67, + "learning_rate": 5.845547192226959e-06, + "loss": 1.3279, + "step": 6415 + }, + { + "epoch": 0.67, + "learning_rate": 5.8422180405992216e-06, + "loss": 1.5202, + "step": 6416 + }, + { + "epoch": 0.67, + "learning_rate": 5.838889446007439e-06, + "loss": 1.5714, + "step": 6417 + }, + { + "epoch": 0.67, + "learning_rate": 5.835561408897552e-06, + "loss": 1.2592, + "step": 6418 + }, + { + "epoch": 0.67, + "learning_rate": 5.832233929715434e-06, + "loss": 1.3407, + "step": 6419 + }, + { + "epoch": 0.67, + "learning_rate": 5.828907008906882e-06, + "loss": 1.3555, + "step": 6420 + }, + { + "epoch": 0.67, + "learning_rate": 5.825580646917622e-06, + "loss": 1.2602, + "step": 6421 + }, + { + "epoch": 0.67, + "learning_rate": 5.822254844193293e-06, + "loss": 1.2672, + "step": 6422 + }, + { + "epoch": 0.67, + "learning_rate": 5.818929601179472e-06, + "loss": 1.3361, + "step": 6423 + }, + { + "epoch": 0.67, + "learning_rate": 5.8156049183216575e-06, + "loss": 1.49, + "step": 6424 + }, + { + "epoch": 0.67, + "learning_rate": 5.812280796065269e-06, + "loss": 1.306, + "step": 6425 + }, + { + "epoch": 0.67, + "learning_rate": 5.808957234855654e-06, + "loss": 1.3167, + "step": 6426 + }, + { + "epoch": 0.67, + "learning_rate": 5.805634235138082e-06, + "loss": 1.3103, + "step": 6427 + }, + { + "epoch": 0.67, + "learning_rate": 5.802311797357752e-06, + "loss": 1.2992, + "step": 6428 + }, + { + "epoch": 0.67, + "learning_rate": 5.7989899219597875e-06, + "loss": 1.3269, + "step": 6429 + }, + { + "epoch": 0.67, + "learning_rate": 5.795668609389233e-06, + "loss": 1.3393, + "step": 6430 + }, + { + "epoch": 0.67, + "learning_rate": 5.79234786009105e-06, + "loss": 1.2633, + "step": 6431 + }, + { + "epoch": 0.67, + "learning_rate": 5.7890276745101495e-06, + "loss": 1.2758, + "step": 6432 + }, + { + "epoch": 0.67, + "learning_rate": 5.785708053091339e-06, + "loss": 1.3294, + "step": 6433 + }, + { + "epoch": 0.67, + "learning_rate": 5.782388996279371e-06, + "loss": 1.3657, + "step": 6434 + }, + { + "epoch": 0.67, + "learning_rate": 5.779070504518905e-06, + "loss": 1.3353, + "step": 6435 + }, + { + "epoch": 0.67, + "learning_rate": 5.775752578254539e-06, + "loss": 1.2741, + "step": 6436 + }, + { + "epoch": 0.68, + "learning_rate": 5.772435217930792e-06, + "loss": 1.2979, + "step": 6437 + }, + { + "epoch": 0.68, + "learning_rate": 5.7691184239921026e-06, + "loss": 1.366, + "step": 6438 + }, + { + "epoch": 0.68, + "learning_rate": 5.765802196882828e-06, + "loss": 1.2873, + "step": 6439 + }, + { + "epoch": 0.68, + "learning_rate": 5.762486537047271e-06, + "loss": 1.2865, + "step": 6440 + }, + { + "epoch": 0.68, + "learning_rate": 5.7591714449296365e-06, + "loss": 1.3887, + "step": 6441 + }, + { + "epoch": 0.68, + "learning_rate": 5.755856920974063e-06, + "loss": 1.127, + "step": 6442 + }, + { + "epoch": 0.68, + "learning_rate": 5.752542965624617e-06, + "loss": 1.4331, + "step": 6443 + }, + { + "epoch": 0.68, + "learning_rate": 5.749229579325274e-06, + "loss": 1.3199, + "step": 6444 + }, + { + "epoch": 0.68, + "learning_rate": 5.745916762519952e-06, + "loss": 1.2719, + "step": 6445 + }, + { + "epoch": 0.68, + "learning_rate": 5.742604515652475e-06, + "loss": 1.2991, + "step": 6446 + }, + { + "epoch": 0.68, + "learning_rate": 5.7392928391666014e-06, + "loss": 1.2164, + "step": 6447 + }, + { + "epoch": 0.68, + "learning_rate": 5.735981733506016e-06, + "loss": 1.3636, + "step": 6448 + }, + { + "epoch": 0.68, + "learning_rate": 5.732671199114314e-06, + "loss": 1.3486, + "step": 6449 + }, + { + "epoch": 0.68, + "learning_rate": 5.729361236435027e-06, + "loss": 1.3378, + "step": 6450 + }, + { + "epoch": 0.68, + "learning_rate": 5.726051845911606e-06, + "loss": 1.3521, + "step": 6451 + }, + { + "epoch": 0.68, + "learning_rate": 5.722743027987421e-06, + "loss": 1.4295, + "step": 6452 + }, + { + "epoch": 0.68, + "learning_rate": 5.719434783105772e-06, + "loss": 1.2625, + "step": 6453 + }, + { + "epoch": 0.68, + "learning_rate": 5.716127111709873e-06, + "loss": 1.2944, + "step": 6454 + }, + { + "epoch": 0.68, + "learning_rate": 5.7128200142428695e-06, + "loss": 1.3655, + "step": 6455 + }, + { + "epoch": 0.68, + "learning_rate": 5.7095134911478336e-06, + "loss": 1.3115, + "step": 6456 + }, + { + "epoch": 0.68, + "learning_rate": 5.706207542867747e-06, + "loss": 1.3391, + "step": 6457 + }, + { + "epoch": 0.68, + "learning_rate": 5.702902169845519e-06, + "loss": 1.3911, + "step": 6458 + }, + { + "epoch": 0.68, + "learning_rate": 5.699597372523997e-06, + "loss": 1.2936, + "step": 6459 + }, + { + "epoch": 0.68, + "learning_rate": 5.696293151345928e-06, + "loss": 1.379, + "step": 6460 + }, + { + "epoch": 0.68, + "learning_rate": 5.692989506754e-06, + "loss": 1.4083, + "step": 6461 + }, + { + "epoch": 0.68, + "learning_rate": 5.689686439190809e-06, + "loss": 1.2645, + "step": 6462 + }, + { + "epoch": 0.68, + "learning_rate": 5.686383949098886e-06, + "loss": 1.3207, + "step": 6463 + }, + { + "epoch": 0.68, + "learning_rate": 5.683082036920682e-06, + "loss": 1.4293, + "step": 6464 + }, + { + "epoch": 0.68, + "learning_rate": 5.679780703098563e-06, + "loss": 1.3018, + "step": 6465 + }, + { + "epoch": 0.68, + "learning_rate": 5.676479948074825e-06, + "loss": 1.3568, + "step": 6466 + }, + { + "epoch": 0.68, + "learning_rate": 5.673179772291687e-06, + "loss": 1.3252, + "step": 6467 + }, + { + "epoch": 0.68, + "learning_rate": 5.669880176191283e-06, + "loss": 1.2674, + "step": 6468 + }, + { + "epoch": 0.68, + "learning_rate": 5.666581160215676e-06, + "loss": 1.3774, + "step": 6469 + }, + { + "epoch": 0.68, + "learning_rate": 5.663282724806855e-06, + "loss": 1.3013, + "step": 6470 + }, + { + "epoch": 0.68, + "learning_rate": 5.659984870406715e-06, + "loss": 1.3354, + "step": 6471 + }, + { + "epoch": 0.68, + "learning_rate": 5.656687597457093e-06, + "loss": 1.273, + "step": 6472 + }, + { + "epoch": 0.68, + "learning_rate": 5.653390906399732e-06, + "loss": 1.3041, + "step": 6473 + }, + { + "epoch": 0.68, + "learning_rate": 5.650094797676308e-06, + "loss": 1.3521, + "step": 6474 + }, + { + "epoch": 0.68, + "learning_rate": 5.646799271728417e-06, + "loss": 1.3751, + "step": 6475 + }, + { + "epoch": 0.68, + "learning_rate": 5.643504328997571e-06, + "loss": 1.2882, + "step": 6476 + }, + { + "epoch": 0.68, + "learning_rate": 5.640209969925202e-06, + "loss": 1.2625, + "step": 6477 + }, + { + "epoch": 0.68, + "learning_rate": 5.636916194952683e-06, + "loss": 1.3648, + "step": 6478 + }, + { + "epoch": 0.68, + "learning_rate": 5.633623004521285e-06, + "loss": 1.3115, + "step": 6479 + }, + { + "epoch": 0.68, + "learning_rate": 5.6303303990722154e-06, + "loss": 1.2755, + "step": 6480 + }, + { + "epoch": 0.68, + "learning_rate": 5.627038379046595e-06, + "loss": 1.4546, + "step": 6481 + }, + { + "epoch": 0.68, + "learning_rate": 5.623746944885473e-06, + "loss": 1.3717, + "step": 6482 + }, + { + "epoch": 0.68, + "learning_rate": 5.620456097029818e-06, + "loss": 1.3188, + "step": 6483 + }, + { + "epoch": 0.68, + "learning_rate": 5.61716583592052e-06, + "loss": 1.3166, + "step": 6484 + }, + { + "epoch": 0.68, + "learning_rate": 5.613876161998377e-06, + "loss": 1.3413, + "step": 6485 + }, + { + "epoch": 0.68, + "learning_rate": 5.610587075704139e-06, + "loss": 1.395, + "step": 6486 + }, + { + "epoch": 0.68, + "learning_rate": 5.6072985774784465e-06, + "loss": 1.2914, + "step": 6487 + }, + { + "epoch": 0.68, + "learning_rate": 5.604010667761876e-06, + "loss": 1.3118, + "step": 6488 + }, + { + "epoch": 0.68, + "learning_rate": 5.600723346994932e-06, + "loss": 1.3599, + "step": 6489 + }, + { + "epoch": 0.68, + "learning_rate": 5.597436615618017e-06, + "loss": 1.2862, + "step": 6490 + }, + { + "epoch": 0.68, + "learning_rate": 5.594150474071481e-06, + "loss": 1.3585, + "step": 6491 + }, + { + "epoch": 0.68, + "learning_rate": 5.590864922795573e-06, + "loss": 1.3449, + "step": 6492 + }, + { + "epoch": 0.68, + "learning_rate": 5.587579962230475e-06, + "loss": 1.2787, + "step": 6493 + }, + { + "epoch": 0.68, + "learning_rate": 5.5842955928162934e-06, + "loss": 1.3755, + "step": 6494 + }, + { + "epoch": 0.68, + "learning_rate": 5.5810118149930406e-06, + "loss": 1.2858, + "step": 6495 + }, + { + "epoch": 0.68, + "learning_rate": 5.577728629200662e-06, + "loss": 1.4214, + "step": 6496 + }, + { + "epoch": 0.68, + "learning_rate": 5.574446035879024e-06, + "loss": 1.5007, + "step": 6497 + }, + { + "epoch": 0.68, + "learning_rate": 5.571164035467903e-06, + "loss": 1.2952, + "step": 6498 + }, + { + "epoch": 0.68, + "learning_rate": 5.56788262840701e-06, + "loss": 1.267, + "step": 6499 + }, + { + "epoch": 0.68, + "learning_rate": 5.564601815135962e-06, + "loss": 1.3168, + "step": 6500 + }, + { + "epoch": 0.68, + "learning_rate": 5.561321596094305e-06, + "loss": 1.2992, + "step": 6501 + }, + { + "epoch": 0.68, + "learning_rate": 5.558041971721511e-06, + "loss": 1.4237, + "step": 6502 + }, + { + "epoch": 0.68, + "learning_rate": 5.554762942456959e-06, + "loss": 1.3865, + "step": 6503 + }, + { + "epoch": 0.68, + "learning_rate": 5.5514845087399505e-06, + "loss": 1.2875, + "step": 6504 + }, + { + "epoch": 0.68, + "learning_rate": 5.548206671009724e-06, + "loss": 1.3011, + "step": 6505 + }, + { + "epoch": 0.68, + "learning_rate": 5.544929429705415e-06, + "loss": 1.3425, + "step": 6506 + }, + { + "epoch": 0.68, + "learning_rate": 5.541652785266095e-06, + "loss": 1.4265, + "step": 6507 + }, + { + "epoch": 0.68, + "learning_rate": 5.538376738130747e-06, + "loss": 1.2877, + "step": 6508 + }, + { + "epoch": 0.68, + "learning_rate": 5.535101288738276e-06, + "loss": 1.3652, + "step": 6509 + }, + { + "epoch": 0.68, + "learning_rate": 5.5318264375275145e-06, + "loss": 1.2997, + "step": 6510 + }, + { + "epoch": 0.68, + "learning_rate": 5.528552184937201e-06, + "loss": 1.3223, + "step": 6511 + }, + { + "epoch": 0.68, + "learning_rate": 5.525278531406006e-06, + "loss": 1.2897, + "step": 6512 + }, + { + "epoch": 0.68, + "learning_rate": 5.522005477372516e-06, + "loss": 1.3554, + "step": 6513 + }, + { + "epoch": 0.68, + "learning_rate": 5.51873302327523e-06, + "loss": 1.3233, + "step": 6514 + }, + { + "epoch": 0.68, + "learning_rate": 5.515461169552576e-06, + "loss": 1.3536, + "step": 6515 + }, + { + "epoch": 0.68, + "learning_rate": 5.5121899166429046e-06, + "loss": 1.3485, + "step": 6516 + }, + { + "epoch": 0.68, + "learning_rate": 5.508919264984468e-06, + "loss": 1.3264, + "step": 6517 + }, + { + "epoch": 0.68, + "learning_rate": 5.505649215015461e-06, + "loss": 1.4498, + "step": 6518 + }, + { + "epoch": 0.68, + "learning_rate": 5.5023797671739755e-06, + "loss": 1.4468, + "step": 6519 + }, + { + "epoch": 0.68, + "learning_rate": 5.499110921898038e-06, + "loss": 1.2659, + "step": 6520 + }, + { + "epoch": 0.68, + "learning_rate": 5.4958426796255934e-06, + "loss": 1.318, + "step": 6521 + }, + { + "epoch": 0.68, + "learning_rate": 5.492575040794498e-06, + "loss": 1.3167, + "step": 6522 + }, + { + "epoch": 0.68, + "learning_rate": 5.48930800584253e-06, + "loss": 1.3453, + "step": 6523 + }, + { + "epoch": 0.68, + "learning_rate": 5.486041575207397e-06, + "loss": 1.2557, + "step": 6524 + }, + { + "epoch": 0.68, + "learning_rate": 5.482775749326705e-06, + "loss": 1.3235, + "step": 6525 + }, + { + "epoch": 0.68, + "learning_rate": 5.479510528638001e-06, + "loss": 1.3119, + "step": 6526 + }, + { + "epoch": 0.68, + "learning_rate": 5.476245913578733e-06, + "loss": 1.4639, + "step": 6527 + }, + { + "epoch": 0.68, + "learning_rate": 5.472981904586277e-06, + "loss": 1.3233, + "step": 6528 + }, + { + "epoch": 0.68, + "learning_rate": 5.469718502097931e-06, + "loss": 1.2722, + "step": 6529 + }, + { + "epoch": 0.68, + "learning_rate": 5.466455706550906e-06, + "loss": 1.4428, + "step": 6530 + }, + { + "epoch": 0.68, + "learning_rate": 5.463193518382321e-06, + "loss": 1.5695, + "step": 6531 + }, + { + "epoch": 0.68, + "learning_rate": 5.4599319380292434e-06, + "loss": 1.3161, + "step": 6532 + }, + { + "epoch": 0.69, + "learning_rate": 5.4566709659286296e-06, + "loss": 1.3513, + "step": 6533 + }, + { + "epoch": 0.69, + "learning_rate": 5.453410602517368e-06, + "loss": 1.2716, + "step": 6534 + }, + { + "epoch": 0.69, + "learning_rate": 5.45015084823227e-06, + "loss": 1.4467, + "step": 6535 + }, + { + "epoch": 0.69, + "learning_rate": 5.44689170351005e-06, + "loss": 1.4082, + "step": 6536 + }, + { + "epoch": 0.69, + "learning_rate": 5.443633168787357e-06, + "loss": 1.303, + "step": 6537 + }, + { + "epoch": 0.69, + "learning_rate": 5.440375244500743e-06, + "loss": 1.2765, + "step": 6538 + }, + { + "epoch": 0.69, + "learning_rate": 5.43711793108669e-06, + "loss": 1.6814, + "step": 6539 + }, + { + "epoch": 0.69, + "learning_rate": 5.4338612289816e-06, + "loss": 1.3899, + "step": 6540 + }, + { + "epoch": 0.69, + "learning_rate": 5.430605138621778e-06, + "loss": 1.201, + "step": 6541 + }, + { + "epoch": 0.69, + "learning_rate": 5.42734966044346e-06, + "loss": 1.3214, + "step": 6542 + }, + { + "epoch": 0.69, + "learning_rate": 5.424094794882801e-06, + "loss": 1.2676, + "step": 6543 + }, + { + "epoch": 0.69, + "learning_rate": 5.420840542375862e-06, + "loss": 1.3006, + "step": 6544 + }, + { + "epoch": 0.69, + "learning_rate": 5.4175869033586355e-06, + "loss": 1.32, + "step": 6545 + }, + { + "epoch": 0.69, + "learning_rate": 5.41433387826702e-06, + "loss": 1.3347, + "step": 6546 + }, + { + "epoch": 0.69, + "learning_rate": 5.41108146753684e-06, + "loss": 1.3983, + "step": 6547 + }, + { + "epoch": 0.69, + "learning_rate": 5.407829671603838e-06, + "loss": 1.3756, + "step": 6548 + }, + { + "epoch": 0.69, + "learning_rate": 5.404578490903664e-06, + "loss": 1.3444, + "step": 6549 + }, + { + "epoch": 0.69, + "learning_rate": 5.4013279258718974e-06, + "loss": 1.3369, + "step": 6550 + }, + { + "epoch": 0.69, + "learning_rate": 5.398077976944034e-06, + "loss": 1.2995, + "step": 6551 + }, + { + "epoch": 0.69, + "learning_rate": 5.394828644555475e-06, + "loss": 1.3305, + "step": 6552 + }, + { + "epoch": 0.69, + "learning_rate": 5.391579929141554e-06, + "loss": 1.3743, + "step": 6553 + }, + { + "epoch": 0.69, + "learning_rate": 5.3883318311375095e-06, + "loss": 1.2829, + "step": 6554 + }, + { + "epoch": 0.69, + "learning_rate": 5.3850843509785065e-06, + "loss": 1.379, + "step": 6555 + }, + { + "epoch": 0.69, + "learning_rate": 5.3818374890996295e-06, + "loss": 1.3236, + "step": 6556 + }, + { + "epoch": 0.69, + "learning_rate": 5.378591245935865e-06, + "loss": 1.3469, + "step": 6557 + }, + { + "epoch": 0.69, + "learning_rate": 5.375345621922129e-06, + "loss": 1.3318, + "step": 6558 + }, + { + "epoch": 0.69, + "learning_rate": 5.3721006174932576e-06, + "loss": 1.3395, + "step": 6559 + }, + { + "epoch": 0.69, + "learning_rate": 5.36885623308399e-06, + "loss": 1.4148, + "step": 6560 + }, + { + "epoch": 0.69, + "learning_rate": 5.365612469128993e-06, + "loss": 1.3007, + "step": 6561 + }, + { + "epoch": 0.69, + "learning_rate": 5.362369326062853e-06, + "loss": 1.4365, + "step": 6562 + }, + { + "epoch": 0.69, + "learning_rate": 5.3591268043200585e-06, + "loss": 1.4269, + "step": 6563 + }, + { + "epoch": 0.69, + "learning_rate": 5.355884904335034e-06, + "loss": 1.2619, + "step": 6564 + }, + { + "epoch": 0.69, + "learning_rate": 5.3526436265421e-06, + "loss": 1.2678, + "step": 6565 + }, + { + "epoch": 0.69, + "learning_rate": 5.34940297137551e-06, + "loss": 1.2541, + "step": 6566 + }, + { + "epoch": 0.69, + "learning_rate": 5.3461629392694345e-06, + "loss": 1.3237, + "step": 6567 + }, + { + "epoch": 0.69, + "eval_loss": 1.402653694152832, + "eval_runtime": 77.5033, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 6567 + }, + { + "epoch": 0.69, + "learning_rate": 5.342923530657944e-06, + "loss": 1.357, + "step": 6568 + }, + { + "epoch": 0.69, + "learning_rate": 5.33968474597504e-06, + "loss": 1.3561, + "step": 6569 + }, + { + "epoch": 0.69, + "learning_rate": 5.336446585654642e-06, + "loss": 1.2969, + "step": 6570 + }, + { + "epoch": 0.69, + "learning_rate": 5.33320905013057e-06, + "loss": 1.2922, + "step": 6571 + }, + { + "epoch": 0.69, + "learning_rate": 5.329972139836581e-06, + "loss": 1.3581, + "step": 6572 + }, + { + "epoch": 0.69, + "learning_rate": 5.326735855206328e-06, + "loss": 1.2926, + "step": 6573 + }, + { + "epoch": 0.69, + "learning_rate": 5.3235001966733965e-06, + "loss": 1.3933, + "step": 6574 + }, + { + "epoch": 0.69, + "learning_rate": 5.320265164671283e-06, + "loss": 1.4009, + "step": 6575 + }, + { + "epoch": 0.69, + "learning_rate": 5.3170307596333955e-06, + "loss": 1.4051, + "step": 6576 + }, + { + "epoch": 0.69, + "learning_rate": 5.313796981993054e-06, + "loss": 1.3448, + "step": 6577 + }, + { + "epoch": 0.69, + "learning_rate": 5.310563832183515e-06, + "loss": 1.3141, + "step": 6578 + }, + { + "epoch": 0.69, + "learning_rate": 5.307331310637929e-06, + "loss": 1.3658, + "step": 6579 + }, + { + "epoch": 0.69, + "learning_rate": 5.3040994177893725e-06, + "loss": 1.2881, + "step": 6580 + }, + { + "epoch": 0.69, + "learning_rate": 5.30086815407084e-06, + "loss": 1.3051, + "step": 6581 + }, + { + "epoch": 0.69, + "learning_rate": 5.297637519915231e-06, + "loss": 1.3353, + "step": 6582 + }, + { + "epoch": 0.69, + "learning_rate": 5.2944075157553754e-06, + "loss": 1.3997, + "step": 6583 + }, + { + "epoch": 0.69, + "learning_rate": 5.291178142024002e-06, + "loss": 1.3094, + "step": 6584 + }, + { + "epoch": 0.69, + "learning_rate": 5.287949399153769e-06, + "loss": 1.3384, + "step": 6585 + }, + { + "epoch": 0.69, + "learning_rate": 5.284721287577248e-06, + "loss": 1.3183, + "step": 6586 + }, + { + "epoch": 0.69, + "learning_rate": 5.281493807726916e-06, + "loss": 1.4433, + "step": 6587 + }, + { + "epoch": 0.69, + "learning_rate": 5.278266960035174e-06, + "loss": 1.3103, + "step": 6588 + }, + { + "epoch": 0.69, + "learning_rate": 5.275040744934343e-06, + "loss": 1.3478, + "step": 6589 + }, + { + "epoch": 0.69, + "learning_rate": 5.271815162856645e-06, + "loss": 1.2713, + "step": 6590 + }, + { + "epoch": 0.69, + "learning_rate": 5.268590214234233e-06, + "loss": 1.3697, + "step": 6591 + }, + { + "epoch": 0.69, + "learning_rate": 5.265365899499156e-06, + "loss": 1.6169, + "step": 6592 + }, + { + "epoch": 0.69, + "learning_rate": 5.262142219083398e-06, + "loss": 1.2988, + "step": 6593 + }, + { + "epoch": 0.69, + "learning_rate": 5.258919173418851e-06, + "loss": 1.515, + "step": 6594 + }, + { + "epoch": 0.69, + "learning_rate": 5.2556967629373125e-06, + "loss": 1.3704, + "step": 6595 + }, + { + "epoch": 0.69, + "learning_rate": 5.2524749880705075e-06, + "loss": 1.2404, + "step": 6596 + }, + { + "epoch": 0.69, + "learning_rate": 5.249253849250073e-06, + "loss": 1.2799, + "step": 6597 + }, + { + "epoch": 0.69, + "learning_rate": 5.246033346907553e-06, + "loss": 1.2876, + "step": 6598 + }, + { + "epoch": 0.69, + "learning_rate": 5.24281348147442e-06, + "loss": 1.3058, + "step": 6599 + }, + { + "epoch": 0.69, + "learning_rate": 5.239594253382043e-06, + "loss": 1.3347, + "step": 6600 + }, + { + "epoch": 0.69, + "learning_rate": 5.236375663061722e-06, + "loss": 1.3323, + "step": 6601 + }, + { + "epoch": 0.69, + "learning_rate": 5.23315771094467e-06, + "loss": 1.3254, + "step": 6602 + }, + { + "epoch": 0.69, + "learning_rate": 5.229940397461999e-06, + "loss": 1.3462, + "step": 6603 + }, + { + "epoch": 0.69, + "learning_rate": 5.226723723044753e-06, + "loss": 1.2901, + "step": 6604 + }, + { + "epoch": 0.69, + "learning_rate": 5.223507688123887e-06, + "loss": 1.3079, + "step": 6605 + }, + { + "epoch": 0.69, + "learning_rate": 5.220292293130258e-06, + "loss": 1.4282, + "step": 6606 + }, + { + "epoch": 0.69, + "learning_rate": 5.217077538494651e-06, + "loss": 1.3197, + "step": 6607 + }, + { + "epoch": 0.69, + "learning_rate": 5.213863424647765e-06, + "loss": 1.3581, + "step": 6608 + }, + { + "epoch": 0.69, + "learning_rate": 5.2106499520202005e-06, + "loss": 1.3322, + "step": 6609 + }, + { + "epoch": 0.69, + "learning_rate": 5.207437121042488e-06, + "loss": 1.3368, + "step": 6610 + }, + { + "epoch": 0.69, + "learning_rate": 5.204224932145056e-06, + "loss": 1.2771, + "step": 6611 + }, + { + "epoch": 0.69, + "learning_rate": 5.20101338575826e-06, + "loss": 1.2852, + "step": 6612 + }, + { + "epoch": 0.69, + "learning_rate": 5.197802482312369e-06, + "loss": 1.3733, + "step": 6613 + }, + { + "epoch": 0.69, + "learning_rate": 5.194592222237551e-06, + "loss": 1.3719, + "step": 6614 + }, + { + "epoch": 0.69, + "learning_rate": 5.191382605963906e-06, + "loss": 1.3658, + "step": 6615 + }, + { + "epoch": 0.69, + "learning_rate": 5.1881736339214415e-06, + "loss": 1.3261, + "step": 6616 + }, + { + "epoch": 0.69, + "learning_rate": 5.18496530654007e-06, + "loss": 1.3057, + "step": 6617 + }, + { + "epoch": 0.69, + "learning_rate": 5.181757624249635e-06, + "loss": 1.2665, + "step": 6618 + }, + { + "epoch": 0.69, + "learning_rate": 5.1785505874798716e-06, + "loss": 1.2839, + "step": 6619 + }, + { + "epoch": 0.69, + "learning_rate": 5.175344196660447e-06, + "loss": 1.3131, + "step": 6620 + }, + { + "epoch": 0.69, + "learning_rate": 5.1721384522209385e-06, + "loss": 1.3217, + "step": 6621 + }, + { + "epoch": 0.69, + "learning_rate": 5.168933354590825e-06, + "loss": 1.3306, + "step": 6622 + }, + { + "epoch": 0.69, + "learning_rate": 5.165728904199512e-06, + "loss": 1.3197, + "step": 6623 + }, + { + "epoch": 0.69, + "learning_rate": 5.1625251014763176e-06, + "loss": 1.3035, + "step": 6624 + }, + { + "epoch": 0.69, + "learning_rate": 5.1593219468504605e-06, + "loss": 1.2927, + "step": 6625 + }, + { + "epoch": 0.69, + "learning_rate": 5.156119440751086e-06, + "loss": 1.3333, + "step": 6626 + }, + { + "epoch": 0.69, + "learning_rate": 5.152917583607251e-06, + "loss": 1.3181, + "step": 6627 + }, + { + "epoch": 0.7, + "learning_rate": 5.149716375847913e-06, + "loss": 1.347, + "step": 6628 + }, + { + "epoch": 0.7, + "learning_rate": 5.14651581790196e-06, + "loss": 1.347, + "step": 6629 + }, + { + "epoch": 0.7, + "learning_rate": 5.143315910198179e-06, + "loss": 1.2892, + "step": 6630 + }, + { + "epoch": 0.7, + "learning_rate": 5.140116653165277e-06, + "loss": 1.2996, + "step": 6631 + }, + { + "epoch": 0.7, + "learning_rate": 5.136918047231876e-06, + "loss": 1.2802, + "step": 6632 + }, + { + "epoch": 0.7, + "learning_rate": 5.133720092826501e-06, + "loss": 1.2766, + "step": 6633 + }, + { + "epoch": 0.7, + "learning_rate": 5.130522790377598e-06, + "loss": 1.5365, + "step": 6634 + }, + { + "epoch": 0.7, + "learning_rate": 5.127326140313528e-06, + "loss": 1.4848, + "step": 6635 + }, + { + "epoch": 0.7, + "learning_rate": 5.124130143062551e-06, + "loss": 1.3712, + "step": 6636 + }, + { + "epoch": 0.7, + "learning_rate": 5.120934799052859e-06, + "loss": 1.3094, + "step": 6637 + }, + { + "epoch": 0.7, + "learning_rate": 5.1177401087125355e-06, + "loss": 1.272, + "step": 6638 + }, + { + "epoch": 0.7, + "learning_rate": 5.114546072469593e-06, + "loss": 1.2856, + "step": 6639 + }, + { + "epoch": 0.7, + "learning_rate": 5.111352690751952e-06, + "loss": 1.2886, + "step": 6640 + }, + { + "epoch": 0.7, + "learning_rate": 5.108159963987436e-06, + "loss": 1.277, + "step": 6641 + }, + { + "epoch": 0.7, + "learning_rate": 5.104967892603794e-06, + "loss": 1.3392, + "step": 6642 + }, + { + "epoch": 0.7, + "learning_rate": 5.101776477028684e-06, + "loss": 1.3036, + "step": 6643 + }, + { + "epoch": 0.7, + "learning_rate": 5.098585717689667e-06, + "loss": 1.4116, + "step": 6644 + }, + { + "epoch": 0.7, + "learning_rate": 5.095395615014226e-06, + "loss": 1.3437, + "step": 6645 + }, + { + "epoch": 0.7, + "learning_rate": 5.0922061694297565e-06, + "loss": 1.2608, + "step": 6646 + }, + { + "epoch": 0.7, + "learning_rate": 5.089017381363554e-06, + "loss": 1.2959, + "step": 6647 + }, + { + "epoch": 0.7, + "learning_rate": 5.085829251242844e-06, + "loss": 1.3508, + "step": 6648 + }, + { + "epoch": 0.7, + "learning_rate": 5.0826417794947455e-06, + "loss": 1.34, + "step": 6649 + }, + { + "epoch": 0.7, + "learning_rate": 5.0794549665463e-06, + "loss": 1.3092, + "step": 6650 + }, + { + "epoch": 0.7, + "learning_rate": 5.076268812824463e-06, + "loss": 1.3417, + "step": 6651 + }, + { + "epoch": 0.7, + "learning_rate": 5.073083318756092e-06, + "loss": 1.3424, + "step": 6652 + }, + { + "epoch": 0.7, + "learning_rate": 5.069898484767961e-06, + "loss": 1.3296, + "step": 6653 + }, + { + "epoch": 0.7, + "learning_rate": 5.066714311286762e-06, + "loss": 1.2852, + "step": 6654 + }, + { + "epoch": 0.7, + "learning_rate": 5.063530798739087e-06, + "loss": 1.3462, + "step": 6655 + }, + { + "epoch": 0.7, + "learning_rate": 5.06034794755145e-06, + "loss": 1.3615, + "step": 6656 + }, + { + "epoch": 0.7, + "learning_rate": 5.057165758150262e-06, + "loss": 1.245, + "step": 6657 + }, + { + "epoch": 0.7, + "learning_rate": 5.053984230961862e-06, + "loss": 1.201, + "step": 6658 + }, + { + "epoch": 0.7, + "learning_rate": 5.050803366412494e-06, + "loss": 1.331, + "step": 6659 + }, + { + "epoch": 0.7, + "learning_rate": 5.047623164928306e-06, + "loss": 1.3034, + "step": 6660 + }, + { + "epoch": 0.7, + "learning_rate": 5.044443626935367e-06, + "loss": 1.2822, + "step": 6661 + }, + { + "epoch": 0.7, + "learning_rate": 5.041264752859657e-06, + "loss": 1.2576, + "step": 6662 + }, + { + "epoch": 0.7, + "learning_rate": 5.038086543127055e-06, + "loss": 1.3198, + "step": 6663 + }, + { + "epoch": 0.7, + "learning_rate": 5.034908998163368e-06, + "loss": 1.2892, + "step": 6664 + }, + { + "epoch": 0.7, + "learning_rate": 5.031732118394299e-06, + "loss": 1.3004, + "step": 6665 + }, + { + "epoch": 0.7, + "learning_rate": 5.028555904245469e-06, + "loss": 1.3178, + "step": 6666 + }, + { + "epoch": 0.7, + "learning_rate": 5.0253803561424156e-06, + "loss": 1.3014, + "step": 6667 + }, + { + "epoch": 0.7, + "learning_rate": 5.022205474510571e-06, + "loss": 1.3151, + "step": 6668 + }, + { + "epoch": 0.7, + "learning_rate": 5.019031259775292e-06, + "loss": 1.3551, + "step": 6669 + }, + { + "epoch": 0.7, + "learning_rate": 5.015857712361847e-06, + "loss": 1.4188, + "step": 6670 + }, + { + "epoch": 0.7, + "learning_rate": 5.0126848326954025e-06, + "loss": 1.2743, + "step": 6671 + }, + { + "epoch": 0.7, + "learning_rate": 5.009512621201043e-06, + "loss": 1.3528, + "step": 6672 + }, + { + "epoch": 0.7, + "learning_rate": 5.006341078303771e-06, + "loss": 1.309, + "step": 6673 + }, + { + "epoch": 0.7, + "learning_rate": 5.003170204428483e-06, + "loss": 1.3353, + "step": 6674 + }, + { + "epoch": 0.7, + "learning_rate": 5.000000000000003e-06, + "loss": 1.2753, + "step": 6675 + }, + { + "epoch": 0.7, + "learning_rate": 4.9968304654430465e-06, + "loss": 1.3907, + "step": 6676 + }, + { + "epoch": 0.7, + "learning_rate": 4.993661601182256e-06, + "loss": 1.2876, + "step": 6677 + }, + { + "epoch": 0.7, + "learning_rate": 4.990493407642181e-06, + "loss": 1.2534, + "step": 6678 + }, + { + "epoch": 0.7, + "learning_rate": 4.98732588524727e-06, + "loss": 1.3352, + "step": 6679 + }, + { + "epoch": 0.7, + "learning_rate": 4.984159034421895e-06, + "loss": 1.3302, + "step": 6680 + }, + { + "epoch": 0.7, + "learning_rate": 4.980992855590336e-06, + "loss": 1.3783, + "step": 6681 + }, + { + "epoch": 0.7, + "learning_rate": 4.977827349176769e-06, + "loss": 1.2848, + "step": 6682 + }, + { + "epoch": 0.7, + "learning_rate": 4.974662515605302e-06, + "loss": 1.3269, + "step": 6683 + }, + { + "epoch": 0.7, + "learning_rate": 4.971498355299932e-06, + "loss": 1.3662, + "step": 6684 + }, + { + "epoch": 0.7, + "learning_rate": 4.968334868684579e-06, + "loss": 1.2508, + "step": 6685 + }, + { + "epoch": 0.7, + "learning_rate": 4.965172056183073e-06, + "loss": 1.3872, + "step": 6686 + }, + { + "epoch": 0.7, + "learning_rate": 4.962009918219142e-06, + "loss": 1.3008, + "step": 6687 + }, + { + "epoch": 0.7, + "learning_rate": 4.958848455216434e-06, + "loss": 1.2058, + "step": 6688 + }, + { + "epoch": 0.7, + "learning_rate": 4.95568766759851e-06, + "loss": 1.3127, + "step": 6689 + }, + { + "epoch": 0.7, + "learning_rate": 4.952527555788825e-06, + "loss": 1.2985, + "step": 6690 + }, + { + "epoch": 0.7, + "learning_rate": 4.949368120210757e-06, + "loss": 1.333, + "step": 6691 + }, + { + "epoch": 0.7, + "learning_rate": 4.946209361287593e-06, + "loss": 1.2945, + "step": 6692 + }, + { + "epoch": 0.7, + "learning_rate": 4.943051279442516e-06, + "loss": 1.262, + "step": 6693 + }, + { + "epoch": 0.7, + "learning_rate": 4.93989387509864e-06, + "loss": 1.6155, + "step": 6694 + }, + { + "epoch": 0.7, + "learning_rate": 4.936737148678965e-06, + "loss": 1.2838, + "step": 6695 + }, + { + "epoch": 0.7, + "learning_rate": 4.933581100606415e-06, + "loss": 1.3778, + "step": 6696 + }, + { + "epoch": 0.7, + "learning_rate": 4.930425731303824e-06, + "loss": 1.3624, + "step": 6697 + }, + { + "epoch": 0.7, + "learning_rate": 4.927271041193923e-06, + "loss": 1.2641, + "step": 6698 + }, + { + "epoch": 0.7, + "learning_rate": 4.924117030699362e-06, + "loss": 1.3314, + "step": 6699 + }, + { + "epoch": 0.7, + "learning_rate": 4.920963700242704e-06, + "loss": 1.328, + "step": 6700 + }, + { + "epoch": 0.7, + "learning_rate": 4.917811050246404e-06, + "loss": 1.3128, + "step": 6701 + }, + { + "epoch": 0.7, + "learning_rate": 4.914659081132843e-06, + "loss": 1.3877, + "step": 6702 + }, + { + "epoch": 0.7, + "learning_rate": 4.911507793324299e-06, + "loss": 1.3114, + "step": 6703 + }, + { + "epoch": 0.7, + "learning_rate": 4.908357187242967e-06, + "loss": 1.3592, + "step": 6704 + }, + { + "epoch": 0.7, + "learning_rate": 4.905207263310948e-06, + "loss": 1.329, + "step": 6705 + }, + { + "epoch": 0.7, + "learning_rate": 4.902058021950247e-06, + "loss": 1.2558, + "step": 6706 + }, + { + "epoch": 0.7, + "learning_rate": 4.898909463582784e-06, + "loss": 1.2489, + "step": 6707 + }, + { + "epoch": 0.7, + "learning_rate": 4.895761588630388e-06, + "loss": 1.2817, + "step": 6708 + }, + { + "epoch": 0.7, + "learning_rate": 4.892614397514785e-06, + "loss": 1.1606, + "step": 6709 + }, + { + "epoch": 0.7, + "learning_rate": 4.889467890657628e-06, + "loss": 1.2878, + "step": 6710 + }, + { + "epoch": 0.7, + "learning_rate": 4.886322068480458e-06, + "loss": 1.2747, + "step": 6711 + }, + { + "epoch": 0.7, + "learning_rate": 4.88317693140474e-06, + "loss": 1.3662, + "step": 6712 + }, + { + "epoch": 0.7, + "learning_rate": 4.880032479851844e-06, + "loss": 1.3009, + "step": 6713 + }, + { + "epoch": 0.7, + "learning_rate": 4.8768887142430385e-06, + "loss": 1.3157, + "step": 6714 + }, + { + "epoch": 0.7, + "learning_rate": 4.873745634999511e-06, + "loss": 1.4461, + "step": 6715 + }, + { + "epoch": 0.7, + "learning_rate": 4.870603242542358e-06, + "loss": 1.3818, + "step": 6716 + }, + { + "epoch": 0.7, + "learning_rate": 4.86746153729257e-06, + "loss": 1.3361, + "step": 6717 + }, + { + "epoch": 0.7, + "learning_rate": 4.864320519671061e-06, + "loss": 1.3147, + "step": 6718 + }, + { + "epoch": 0.7, + "learning_rate": 4.8611801900986485e-06, + "loss": 1.3773, + "step": 6719 + }, + { + "epoch": 0.7, + "learning_rate": 4.858040548996049e-06, + "loss": 1.3091, + "step": 6720 + }, + { + "epoch": 0.7, + "learning_rate": 4.854901596783902e-06, + "loss": 1.3314, + "step": 6721 + }, + { + "epoch": 0.7, + "learning_rate": 4.851763333882738e-06, + "loss": 1.3082, + "step": 6722 + }, + { + "epoch": 0.71, + "learning_rate": 4.848625760713007e-06, + "loss": 1.2687, + "step": 6723 + }, + { + "epoch": 0.71, + "learning_rate": 4.845488877695068e-06, + "loss": 1.3378, + "step": 6724 + }, + { + "epoch": 0.71, + "learning_rate": 4.842352685249174e-06, + "loss": 1.3516, + "step": 6725 + }, + { + "epoch": 0.71, + "learning_rate": 4.839217183795501e-06, + "loss": 1.4083, + "step": 6726 + }, + { + "epoch": 0.71, + "learning_rate": 4.836082373754124e-06, + "loss": 1.3073, + "step": 6727 + }, + { + "epoch": 0.71, + "learning_rate": 4.832948255545024e-06, + "loss": 1.2948, + "step": 6728 + }, + { + "epoch": 0.71, + "learning_rate": 4.829814829588099e-06, + "loss": 1.3323, + "step": 6729 + }, + { + "epoch": 0.71, + "learning_rate": 4.826682096303139e-06, + "loss": 1.3101, + "step": 6730 + }, + { + "epoch": 0.71, + "learning_rate": 4.823550056109853e-06, + "loss": 1.3323, + "step": 6731 + }, + { + "epoch": 0.71, + "learning_rate": 4.8204187094278605e-06, + "loss": 1.3862, + "step": 6732 + }, + { + "epoch": 0.71, + "learning_rate": 4.817288056676671e-06, + "loss": 1.3112, + "step": 6733 + }, + { + "epoch": 0.71, + "learning_rate": 4.8141580982757175e-06, + "loss": 1.297, + "step": 6734 + }, + { + "epoch": 0.71, + "learning_rate": 4.811028834644336e-06, + "loss": 1.2604, + "step": 6735 + }, + { + "epoch": 0.71, + "learning_rate": 4.807900266201761e-06, + "loss": 1.343, + "step": 6736 + }, + { + "epoch": 0.71, + "learning_rate": 4.804772393367142e-06, + "loss": 1.3254, + "step": 6737 + }, + { + "epoch": 0.71, + "learning_rate": 4.80164521655954e-06, + "loss": 1.2688, + "step": 6738 + }, + { + "epoch": 0.71, + "learning_rate": 4.798518736197909e-06, + "loss": 1.2693, + "step": 6739 + }, + { + "epoch": 0.71, + "learning_rate": 4.795392952701122e-06, + "loss": 1.4536, + "step": 6740 + }, + { + "epoch": 0.71, + "learning_rate": 4.7922678664879485e-06, + "loss": 1.3811, + "step": 6741 + }, + { + "epoch": 0.71, + "learning_rate": 4.789143477977072e-06, + "loss": 1.2584, + "step": 6742 + }, + { + "epoch": 0.71, + "learning_rate": 4.786019787587084e-06, + "loss": 1.2584, + "step": 6743 + }, + { + "epoch": 0.71, + "learning_rate": 4.782896795736472e-06, + "loss": 1.2005, + "step": 6744 + }, + { + "epoch": 0.71, + "learning_rate": 4.779774502843642e-06, + "loss": 1.335, + "step": 6745 + }, + { + "epoch": 0.71, + "learning_rate": 4.776652909326901e-06, + "loss": 1.3675, + "step": 6746 + }, + { + "epoch": 0.71, + "learning_rate": 4.773532015604457e-06, + "loss": 1.3794, + "step": 6747 + }, + { + "epoch": 0.71, + "learning_rate": 4.770411822094437e-06, + "loss": 1.3629, + "step": 6748 + }, + { + "epoch": 0.71, + "learning_rate": 4.76729232921486e-06, + "loss": 1.0805, + "step": 6749 + }, + { + "epoch": 0.71, + "learning_rate": 4.76417353738366e-06, + "loss": 1.2874, + "step": 6750 + }, + { + "epoch": 0.71, + "learning_rate": 4.761055447018681e-06, + "loss": 1.428, + "step": 6751 + }, + { + "epoch": 0.71, + "learning_rate": 4.757938058537656e-06, + "loss": 1.2935, + "step": 6752 + }, + { + "epoch": 0.71, + "learning_rate": 4.754821372358242e-06, + "loss": 1.4202, + "step": 6753 + }, + { + "epoch": 0.71, + "learning_rate": 4.751705388897997e-06, + "loss": 1.3109, + "step": 6754 + }, + { + "epoch": 0.71, + "learning_rate": 4.7485901085743754e-06, + "loss": 1.3319, + "step": 6755 + }, + { + "epoch": 0.71, + "learning_rate": 4.745475531804753e-06, + "loss": 1.3246, + "step": 6756 + }, + { + "epoch": 0.71, + "learning_rate": 4.742361659006395e-06, + "loss": 1.3407, + "step": 6757 + }, + { + "epoch": 0.71, + "learning_rate": 4.739248490596483e-06, + "loss": 1.2953, + "step": 6758 + }, + { + "epoch": 0.71, + "learning_rate": 4.736136026992107e-06, + "loss": 1.3214, + "step": 6759 + }, + { + "epoch": 0.71, + "learning_rate": 4.733024268610249e-06, + "loss": 1.4112, + "step": 6760 + }, + { + "epoch": 0.71, + "learning_rate": 4.7299132158678085e-06, + "loss": 1.2981, + "step": 6761 + }, + { + "epoch": 0.71, + "learning_rate": 4.726802869181591e-06, + "loss": 1.2975, + "step": 6762 + }, + { + "epoch": 0.71, + "learning_rate": 4.723693228968293e-06, + "loss": 1.3047, + "step": 6763 + }, + { + "epoch": 0.71, + "learning_rate": 4.720584295644533e-06, + "loss": 1.3906, + "step": 6764 + }, + { + "epoch": 0.71, + "learning_rate": 4.717476069626832e-06, + "loss": 1.2523, + "step": 6765 + }, + { + "epoch": 0.71, + "learning_rate": 4.7143685513316025e-06, + "loss": 1.0453, + "step": 6766 + }, + { + "epoch": 0.71, + "eval_loss": 1.4004828929901123, + "eval_runtime": 77.565, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 6766 + }, + { + "epoch": 0.71, + "learning_rate": 4.711261741175182e-06, + "loss": 1.1339, + "step": 6767 + }, + { + "epoch": 0.71, + "learning_rate": 4.7081556395737935e-06, + "loss": 1.2401, + "step": 6768 + }, + { + "epoch": 0.71, + "learning_rate": 4.705050246943581e-06, + "loss": 1.3009, + "step": 6769 + }, + { + "epoch": 0.71, + "learning_rate": 4.7019455637005895e-06, + "loss": 1.3106, + "step": 6770 + }, + { + "epoch": 0.71, + "learning_rate": 4.698841590260758e-06, + "loss": 1.3021, + "step": 6771 + }, + { + "epoch": 0.71, + "learning_rate": 4.695738327039947e-06, + "loss": 1.3147, + "step": 6772 + }, + { + "epoch": 0.71, + "learning_rate": 4.692635774453914e-06, + "loss": 1.238, + "step": 6773 + }, + { + "epoch": 0.71, + "learning_rate": 4.6895339329183154e-06, + "loss": 1.3876, + "step": 6774 + }, + { + "epoch": 0.71, + "learning_rate": 4.686432802848726e-06, + "loss": 1.3012, + "step": 6775 + }, + { + "epoch": 0.71, + "learning_rate": 4.68333238466061e-06, + "loss": 1.1421, + "step": 6776 + }, + { + "epoch": 0.71, + "learning_rate": 4.6802326787693455e-06, + "loss": 1.2838, + "step": 6777 + }, + { + "epoch": 0.71, + "learning_rate": 4.677133685590219e-06, + "loss": 1.3725, + "step": 6778 + }, + { + "epoch": 0.71, + "learning_rate": 4.674035405538409e-06, + "loss": 1.3093, + "step": 6779 + }, + { + "epoch": 0.71, + "learning_rate": 4.6709378390290085e-06, + "loss": 1.2785, + "step": 6780 + }, + { + "epoch": 0.71, + "learning_rate": 4.667840986477015e-06, + "loss": 1.2513, + "step": 6781 + }, + { + "epoch": 0.71, + "learning_rate": 4.66474484829732e-06, + "loss": 1.2903, + "step": 6782 + }, + { + "epoch": 0.71, + "learning_rate": 4.661649424904732e-06, + "loss": 1.4217, + "step": 6783 + }, + { + "epoch": 0.71, + "learning_rate": 4.658554716713959e-06, + "loss": 1.337, + "step": 6784 + }, + { + "epoch": 0.71, + "learning_rate": 4.655460724139605e-06, + "loss": 1.2978, + "step": 6785 + }, + { + "epoch": 0.71, + "learning_rate": 4.652367447596197e-06, + "loss": 1.3036, + "step": 6786 + }, + { + "epoch": 0.71, + "learning_rate": 4.6492748874981415e-06, + "loss": 1.2889, + "step": 6787 + }, + { + "epoch": 0.71, + "learning_rate": 4.646183044259771e-06, + "loss": 1.3046, + "step": 6788 + }, + { + "epoch": 0.71, + "learning_rate": 4.643091918295312e-06, + "loss": 1.3483, + "step": 6789 + }, + { + "epoch": 0.71, + "learning_rate": 4.640001510018893e-06, + "loss": 1.3862, + "step": 6790 + }, + { + "epoch": 0.71, + "learning_rate": 4.6369118198445505e-06, + "loss": 1.2483, + "step": 6791 + }, + { + "epoch": 0.71, + "learning_rate": 4.633822848186228e-06, + "loss": 1.2669, + "step": 6792 + }, + { + "epoch": 0.71, + "learning_rate": 4.63073459545776e-06, + "loss": 1.3535, + "step": 6793 + }, + { + "epoch": 0.71, + "learning_rate": 4.627647062072902e-06, + "loss": 1.2742, + "step": 6794 + }, + { + "epoch": 0.71, + "learning_rate": 4.624560248445295e-06, + "loss": 1.3429, + "step": 6795 + }, + { + "epoch": 0.71, + "learning_rate": 4.621474154988498e-06, + "loss": 1.3548, + "step": 6796 + }, + { + "epoch": 0.71, + "learning_rate": 4.61838878211597e-06, + "loss": 1.2722, + "step": 6797 + }, + { + "epoch": 0.71, + "learning_rate": 4.6153041302410665e-06, + "loss": 1.3357, + "step": 6798 + }, + { + "epoch": 0.71, + "learning_rate": 4.612220199777053e-06, + "loss": 1.2494, + "step": 6799 + }, + { + "epoch": 0.71, + "learning_rate": 4.609136991137103e-06, + "loss": 1.2792, + "step": 6800 + }, + { + "epoch": 0.71, + "learning_rate": 4.60605450473428e-06, + "loss": 1.2892, + "step": 6801 + }, + { + "epoch": 0.71, + "learning_rate": 4.602972740981562e-06, + "loss": 1.316, + "step": 6802 + }, + { + "epoch": 0.71, + "learning_rate": 4.599891700291822e-06, + "loss": 1.3017, + "step": 6803 + }, + { + "epoch": 0.71, + "learning_rate": 4.5968113830778416e-06, + "loss": 1.3133, + "step": 6804 + }, + { + "epoch": 0.71, + "learning_rate": 4.593731789752311e-06, + "loss": 1.3768, + "step": 6805 + }, + { + "epoch": 0.71, + "learning_rate": 4.590652920727806e-06, + "loss": 1.3259, + "step": 6806 + }, + { + "epoch": 0.71, + "learning_rate": 4.5875747764168214e-06, + "loss": 1.328, + "step": 6807 + }, + { + "epoch": 0.71, + "learning_rate": 4.584497357231752e-06, + "loss": 1.2924, + "step": 6808 + }, + { + "epoch": 0.71, + "learning_rate": 4.581420663584886e-06, + "loss": 1.3347, + "step": 6809 + }, + { + "epoch": 0.71, + "learning_rate": 4.578344695888427e-06, + "loss": 1.3042, + "step": 6810 + }, + { + "epoch": 0.71, + "learning_rate": 4.575269454554477e-06, + "loss": 1.3121, + "step": 6811 + }, + { + "epoch": 0.71, + "learning_rate": 4.572194939995031e-06, + "loss": 1.3471, + "step": 6812 + }, + { + "epoch": 0.71, + "learning_rate": 4.569121152622005e-06, + "loss": 1.4279, + "step": 6813 + }, + { + "epoch": 0.71, + "learning_rate": 4.5660480928471985e-06, + "loss": 1.2902, + "step": 6814 + }, + { + "epoch": 0.71, + "learning_rate": 4.562975761082326e-06, + "loss": 1.0803, + "step": 6815 + }, + { + "epoch": 0.71, + "learning_rate": 4.5599041577390065e-06, + "loss": 1.008, + "step": 6816 + }, + { + "epoch": 0.71, + "learning_rate": 4.556833283228748e-06, + "loss": 1.168, + "step": 6817 + }, + { + "epoch": 0.71, + "learning_rate": 4.553763137962971e-06, + "loss": 1.3092, + "step": 6818 + }, + { + "epoch": 0.72, + "learning_rate": 4.550693722353001e-06, + "loss": 1.364, + "step": 6819 + }, + { + "epoch": 0.72, + "learning_rate": 4.547625036810052e-06, + "loss": 1.3079, + "step": 6820 + }, + { + "epoch": 0.72, + "learning_rate": 4.544557081745259e-06, + "loss": 1.2639, + "step": 6821 + }, + { + "epoch": 0.72, + "learning_rate": 4.541489857569639e-06, + "loss": 1.3586, + "step": 6822 + }, + { + "epoch": 0.72, + "learning_rate": 4.5384233646941275e-06, + "loss": 1.4261, + "step": 6823 + }, + { + "epoch": 0.72, + "learning_rate": 4.535357603529558e-06, + "loss": 1.428, + "step": 6824 + }, + { + "epoch": 0.72, + "learning_rate": 4.532292574486656e-06, + "loss": 1.2541, + "step": 6825 + }, + { + "epoch": 0.72, + "learning_rate": 4.529228277976061e-06, + "loss": 1.2761, + "step": 6826 + }, + { + "epoch": 0.72, + "learning_rate": 4.526164714408314e-06, + "loss": 1.3439, + "step": 6827 + }, + { + "epoch": 0.72, + "learning_rate": 4.523101884193845e-06, + "loss": 1.3585, + "step": 6828 + }, + { + "epoch": 0.72, + "learning_rate": 4.520039787742999e-06, + "loss": 1.4035, + "step": 6829 + }, + { + "epoch": 0.72, + "learning_rate": 4.516978425466023e-06, + "loss": 1.3328, + "step": 6830 + }, + { + "epoch": 0.72, + "learning_rate": 4.5139177977730516e-06, + "loss": 1.2931, + "step": 6831 + }, + { + "epoch": 0.72, + "learning_rate": 4.5108579050741395e-06, + "loss": 1.2515, + "step": 6832 + }, + { + "epoch": 0.72, + "learning_rate": 4.507798747779226e-06, + "loss": 1.3178, + "step": 6833 + }, + { + "epoch": 0.72, + "learning_rate": 4.504740326298163e-06, + "loss": 1.3037, + "step": 6834 + }, + { + "epoch": 0.72, + "learning_rate": 4.501682641040702e-06, + "loss": 1.14, + "step": 6835 + }, + { + "epoch": 0.72, + "learning_rate": 4.4986256924164895e-06, + "loss": 1.2801, + "step": 6836 + }, + { + "epoch": 0.72, + "learning_rate": 4.495569480835081e-06, + "loss": 1.3195, + "step": 6837 + }, + { + "epoch": 0.72, + "learning_rate": 4.492514006705935e-06, + "loss": 1.2949, + "step": 6838 + }, + { + "epoch": 0.72, + "learning_rate": 4.489459270438397e-06, + "loss": 1.3297, + "step": 6839 + }, + { + "epoch": 0.72, + "learning_rate": 4.4864052724417315e-06, + "loss": 1.2127, + "step": 6840 + }, + { + "epoch": 0.72, + "learning_rate": 4.4833520131250894e-06, + "loss": 1.3124, + "step": 6841 + }, + { + "epoch": 0.72, + "learning_rate": 4.480299492897532e-06, + "loss": 1.3056, + "step": 6842 + }, + { + "epoch": 0.72, + "learning_rate": 4.477247712168021e-06, + "loss": 1.2853, + "step": 6843 + }, + { + "epoch": 0.72, + "learning_rate": 4.474196671345411e-06, + "loss": 1.2531, + "step": 6844 + }, + { + "epoch": 0.72, + "learning_rate": 4.471146370838466e-06, + "loss": 1.2712, + "step": 6845 + }, + { + "epoch": 0.72, + "learning_rate": 4.468096811055852e-06, + "loss": 1.3443, + "step": 6846 + }, + { + "epoch": 0.72, + "learning_rate": 4.465047992406124e-06, + "loss": 1.2692, + "step": 6847 + }, + { + "epoch": 0.72, + "learning_rate": 4.461999915297752e-06, + "loss": 1.3937, + "step": 6848 + }, + { + "epoch": 0.72, + "learning_rate": 4.458952580139094e-06, + "loss": 1.2743, + "step": 6849 + }, + { + "epoch": 0.72, + "learning_rate": 4.455905987338418e-06, + "loss": 1.3949, + "step": 6850 + }, + { + "epoch": 0.72, + "learning_rate": 4.452860137303892e-06, + "loss": 1.2578, + "step": 6851 + }, + { + "epoch": 0.72, + "learning_rate": 4.449815030443575e-06, + "loss": 1.3199, + "step": 6852 + }, + { + "epoch": 0.72, + "learning_rate": 4.4467706671654365e-06, + "loss": 1.3199, + "step": 6853 + }, + { + "epoch": 0.72, + "learning_rate": 4.4437270478773464e-06, + "loss": 1.3098, + "step": 6854 + }, + { + "epoch": 0.72, + "learning_rate": 4.440684172987064e-06, + "loss": 1.2888, + "step": 6855 + }, + { + "epoch": 0.72, + "learning_rate": 4.4376420429022615e-06, + "loss": 1.646, + "step": 6856 + }, + { + "epoch": 0.72, + "learning_rate": 4.434600658030508e-06, + "loss": 1.3573, + "step": 6857 + }, + { + "epoch": 0.72, + "learning_rate": 4.431560018779264e-06, + "loss": 1.3748, + "step": 6858 + }, + { + "epoch": 0.72, + "learning_rate": 4.428520125555906e-06, + "loss": 1.358, + "step": 6859 + }, + { + "epoch": 0.72, + "learning_rate": 4.425480978767692e-06, + "loss": 1.2707, + "step": 6860 + }, + { + "epoch": 0.72, + "learning_rate": 4.422442578821795e-06, + "loss": 1.4066, + "step": 6861 + }, + { + "epoch": 0.72, + "learning_rate": 4.4194049261252845e-06, + "loss": 1.3725, + "step": 6862 + }, + { + "epoch": 0.72, + "learning_rate": 4.416368021085122e-06, + "loss": 1.2392, + "step": 6863 + }, + { + "epoch": 0.72, + "learning_rate": 4.413331864108178e-06, + "loss": 1.2917, + "step": 6864 + }, + { + "epoch": 0.72, + "learning_rate": 4.410296455601223e-06, + "loss": 1.2685, + "step": 6865 + }, + { + "epoch": 0.72, + "learning_rate": 4.407261795970916e-06, + "loss": 1.265, + "step": 6866 + }, + { + "epoch": 0.72, + "learning_rate": 4.404227885623832e-06, + "loss": 1.3838, + "step": 6867 + }, + { + "epoch": 0.72, + "learning_rate": 4.4011947249664276e-06, + "loss": 1.3496, + "step": 6868 + }, + { + "epoch": 0.72, + "learning_rate": 4.398162314405075e-06, + "loss": 1.3007, + "step": 6869 + }, + { + "epoch": 0.72, + "learning_rate": 4.39513065434604e-06, + "loss": 1.2934, + "step": 6870 + }, + { + "epoch": 0.72, + "learning_rate": 4.392099745195483e-06, + "loss": 1.559, + "step": 6871 + }, + { + "epoch": 0.72, + "learning_rate": 4.389069587359468e-06, + "loss": 1.346, + "step": 6872 + }, + { + "epoch": 0.72, + "learning_rate": 4.386040181243965e-06, + "loss": 1.2433, + "step": 6873 + }, + { + "epoch": 0.72, + "learning_rate": 4.3830115272548275e-06, + "loss": 1.2938, + "step": 6874 + }, + { + "epoch": 0.72, + "learning_rate": 4.379983625797821e-06, + "loss": 1.3463, + "step": 6875 + }, + { + "epoch": 0.72, + "learning_rate": 4.376956477278612e-06, + "loss": 1.2832, + "step": 6876 + }, + { + "epoch": 0.72, + "learning_rate": 4.37393008210275e-06, + "loss": 1.3693, + "step": 6877 + }, + { + "epoch": 0.72, + "learning_rate": 4.370904440675705e-06, + "loss": 1.2652, + "step": 6878 + }, + { + "epoch": 0.72, + "learning_rate": 4.367879553402826e-06, + "loss": 1.3217, + "step": 6879 + }, + { + "epoch": 0.72, + "learning_rate": 4.364855420689375e-06, + "loss": 1.3519, + "step": 6880 + }, + { + "epoch": 0.72, + "learning_rate": 4.36183204294051e-06, + "loss": 1.3131, + "step": 6881 + }, + { + "epoch": 0.72, + "learning_rate": 4.35880942056128e-06, + "loss": 1.4334, + "step": 6882 + }, + { + "epoch": 0.72, + "learning_rate": 4.3557875539566415e-06, + "loss": 1.259, + "step": 6883 + }, + { + "epoch": 0.72, + "learning_rate": 4.352766443531451e-06, + "loss": 1.2841, + "step": 6884 + }, + { + "epoch": 0.72, + "learning_rate": 4.349746089690453e-06, + "loss": 1.35, + "step": 6885 + }, + { + "epoch": 0.72, + "learning_rate": 4.346726492838304e-06, + "loss": 1.3623, + "step": 6886 + }, + { + "epoch": 0.72, + "learning_rate": 4.343707653379544e-06, + "loss": 1.3729, + "step": 6887 + }, + { + "epoch": 0.72, + "learning_rate": 4.340689571718626e-06, + "loss": 1.2992, + "step": 6888 + }, + { + "epoch": 0.72, + "learning_rate": 4.337672248259898e-06, + "loss": 1.3484, + "step": 6889 + }, + { + "epoch": 0.72, + "learning_rate": 4.334655683407594e-06, + "loss": 1.3347, + "step": 6890 + }, + { + "epoch": 0.72, + "learning_rate": 4.331639877565865e-06, + "loss": 1.2986, + "step": 6891 + }, + { + "epoch": 0.72, + "learning_rate": 4.328624831138751e-06, + "loss": 1.3217, + "step": 6892 + }, + { + "epoch": 0.72, + "learning_rate": 4.325610544530184e-06, + "loss": 1.2834, + "step": 6893 + }, + { + "epoch": 0.72, + "learning_rate": 4.32259701814401e-06, + "loss": 1.3474, + "step": 6894 + }, + { + "epoch": 0.72, + "learning_rate": 4.319584252383956e-06, + "loss": 1.2871, + "step": 6895 + }, + { + "epoch": 0.72, + "learning_rate": 4.316572247653659e-06, + "loss": 1.3534, + "step": 6896 + }, + { + "epoch": 0.72, + "learning_rate": 4.313561004356653e-06, + "loss": 1.4421, + "step": 6897 + }, + { + "epoch": 0.72, + "learning_rate": 4.310550522896359e-06, + "loss": 1.3091, + "step": 6898 + }, + { + "epoch": 0.72, + "learning_rate": 4.30754080367611e-06, + "loss": 1.2565, + "step": 6899 + }, + { + "epoch": 0.72, + "learning_rate": 4.304531847099135e-06, + "loss": 1.5767, + "step": 6900 + }, + { + "epoch": 0.72, + "learning_rate": 4.3015236535685475e-06, + "loss": 1.4257, + "step": 6901 + }, + { + "epoch": 0.72, + "learning_rate": 4.298516223487373e-06, + "loss": 1.362, + "step": 6902 + }, + { + "epoch": 0.72, + "learning_rate": 4.2955095572585336e-06, + "loss": 1.3475, + "step": 6903 + }, + { + "epoch": 0.72, + "learning_rate": 4.292503655284838e-06, + "loss": 1.3223, + "step": 6904 + }, + { + "epoch": 0.72, + "learning_rate": 4.289498517969006e-06, + "loss": 1.3142, + "step": 6905 + }, + { + "epoch": 0.72, + "learning_rate": 4.286494145713644e-06, + "loss": 1.3124, + "step": 6906 + }, + { + "epoch": 0.72, + "learning_rate": 4.283490538921261e-06, + "loss": 1.3636, + "step": 6907 + }, + { + "epoch": 0.72, + "learning_rate": 4.280487697994269e-06, + "loss": 1.347, + "step": 6908 + }, + { + "epoch": 0.72, + "learning_rate": 4.277485623334964e-06, + "loss": 1.2986, + "step": 6909 + }, + { + "epoch": 0.72, + "learning_rate": 4.27448431534555e-06, + "loss": 1.3058, + "step": 6910 + }, + { + "epoch": 0.72, + "learning_rate": 4.271483774428128e-06, + "loss": 1.7858, + "step": 6911 + }, + { + "epoch": 0.72, + "learning_rate": 4.268484000984689e-06, + "loss": 1.3529, + "step": 6912 + }, + { + "epoch": 0.72, + "learning_rate": 4.26548499541713e-06, + "loss": 1.3215, + "step": 6913 + }, + { + "epoch": 0.73, + "learning_rate": 4.262486758127234e-06, + "loss": 1.2914, + "step": 6914 + }, + { + "epoch": 0.73, + "learning_rate": 4.259489289516693e-06, + "loss": 1.4562, + "step": 6915 + }, + { + "epoch": 0.73, + "learning_rate": 4.256492589987092e-06, + "loss": 1.2548, + "step": 6916 + }, + { + "epoch": 0.73, + "learning_rate": 4.253496659939907e-06, + "loss": 1.3047, + "step": 6917 + }, + { + "epoch": 0.73, + "learning_rate": 4.250501499776516e-06, + "loss": 1.4184, + "step": 6918 + }, + { + "epoch": 0.73, + "learning_rate": 4.2475071098982e-06, + "loss": 1.3519, + "step": 6919 + }, + { + "epoch": 0.73, + "learning_rate": 4.2445134907061224e-06, + "loss": 1.3274, + "step": 6920 + }, + { + "epoch": 0.73, + "learning_rate": 4.2415206426013545e-06, + "loss": 1.389, + "step": 6921 + }, + { + "epoch": 0.73, + "learning_rate": 4.238528565984865e-06, + "loss": 1.2929, + "step": 6922 + }, + { + "epoch": 0.73, + "learning_rate": 4.235537261257507e-06, + "loss": 1.3883, + "step": 6923 + }, + { + "epoch": 0.73, + "learning_rate": 4.232546728820047e-06, + "loss": 1.3395, + "step": 6924 + }, + { + "epoch": 0.73, + "learning_rate": 4.229556969073133e-06, + "loss": 1.3534, + "step": 6925 + }, + { + "epoch": 0.73, + "learning_rate": 4.226567982417317e-06, + "loss": 1.4218, + "step": 6926 + }, + { + "epoch": 0.73, + "learning_rate": 4.223579769253052e-06, + "loss": 1.3737, + "step": 6927 + }, + { + "epoch": 0.73, + "learning_rate": 4.220592329980674e-06, + "loss": 1.4805, + "step": 6928 + }, + { + "epoch": 0.73, + "learning_rate": 4.217605665000426e-06, + "loss": 1.2409, + "step": 6929 + }, + { + "epoch": 0.73, + "learning_rate": 4.21461977471245e-06, + "loss": 1.3375, + "step": 6930 + }, + { + "epoch": 0.73, + "learning_rate": 4.211634659516769e-06, + "loss": 1.3535, + "step": 6931 + }, + { + "epoch": 0.73, + "learning_rate": 4.20865031981332e-06, + "loss": 1.2723, + "step": 6932 + }, + { + "epoch": 0.73, + "learning_rate": 4.2056667560019206e-06, + "loss": 1.342, + "step": 6933 + }, + { + "epoch": 0.73, + "learning_rate": 4.202683968482296e-06, + "loss": 1.4075, + "step": 6934 + }, + { + "epoch": 0.73, + "learning_rate": 4.199701957654065e-06, + "loss": 1.3003, + "step": 6935 + }, + { + "epoch": 0.73, + "learning_rate": 4.196720723916735e-06, + "loss": 1.3098, + "step": 6936 + }, + { + "epoch": 0.73, + "learning_rate": 4.193740267669718e-06, + "loss": 1.2386, + "step": 6937 + }, + { + "epoch": 0.73, + "learning_rate": 4.19076058931232e-06, + "loss": 1.3271, + "step": 6938 + }, + { + "epoch": 0.73, + "learning_rate": 4.187781689243737e-06, + "loss": 1.4604, + "step": 6939 + }, + { + "epoch": 0.73, + "learning_rate": 4.184803567863072e-06, + "loss": 1.3496, + "step": 6940 + }, + { + "epoch": 0.73, + "learning_rate": 4.181826225569308e-06, + "loss": 1.3056, + "step": 6941 + }, + { + "epoch": 0.73, + "learning_rate": 4.1788496627613366e-06, + "loss": 1.2886, + "step": 6942 + }, + { + "epoch": 0.73, + "learning_rate": 4.175873879837944e-06, + "loss": 1.282, + "step": 6943 + }, + { + "epoch": 0.73, + "learning_rate": 4.172898877197802e-06, + "loss": 1.2984, + "step": 6944 + }, + { + "epoch": 0.73, + "learning_rate": 4.169924655239488e-06, + "loss": 1.2909, + "step": 6945 + }, + { + "epoch": 0.73, + "learning_rate": 4.166951214361474e-06, + "loss": 1.4015, + "step": 6946 + }, + { + "epoch": 0.73, + "learning_rate": 4.16397855496212e-06, + "loss": 1.3772, + "step": 6947 + }, + { + "epoch": 0.73, + "learning_rate": 4.161006677439687e-06, + "loss": 1.3089, + "step": 6948 + }, + { + "epoch": 0.73, + "learning_rate": 4.1580355821923344e-06, + "loss": 1.3599, + "step": 6949 + }, + { + "epoch": 0.73, + "learning_rate": 4.155065269618107e-06, + "loss": 1.2886, + "step": 6950 + }, + { + "epoch": 0.73, + "learning_rate": 4.152095740114955e-06, + "loss": 1.3071, + "step": 6951 + }, + { + "epoch": 0.73, + "learning_rate": 4.149126994080715e-06, + "loss": 1.3332, + "step": 6952 + }, + { + "epoch": 0.73, + "learning_rate": 4.146159031913123e-06, + "loss": 1.3835, + "step": 6953 + }, + { + "epoch": 0.73, + "learning_rate": 4.1431918540098144e-06, + "loss": 1.3399, + "step": 6954 + }, + { + "epoch": 0.73, + "learning_rate": 4.140225460768309e-06, + "loss": 1.2906, + "step": 6955 + }, + { + "epoch": 0.73, + "learning_rate": 4.137259852586029e-06, + "loss": 1.295, + "step": 6956 + }, + { + "epoch": 0.73, + "learning_rate": 4.134295029860295e-06, + "loss": 1.3371, + "step": 6957 + }, + { + "epoch": 0.73, + "learning_rate": 4.131330992988308e-06, + "loss": 1.4441, + "step": 6958 + }, + { + "epoch": 0.73, + "learning_rate": 4.1283677423671805e-06, + "loss": 1.3257, + "step": 6959 + }, + { + "epoch": 0.73, + "learning_rate": 4.125405278393907e-06, + "loss": 1.3958, + "step": 6960 + }, + { + "epoch": 0.73, + "learning_rate": 4.1224436014653826e-06, + "loss": 1.2856, + "step": 6961 + }, + { + "epoch": 0.73, + "learning_rate": 4.1194827119784e-06, + "loss": 1.2943, + "step": 6962 + }, + { + "epoch": 0.73, + "learning_rate": 4.116522610329636e-06, + "loss": 1.2691, + "step": 6963 + }, + { + "epoch": 0.73, + "learning_rate": 4.11356329691567e-06, + "loss": 1.293, + "step": 6964 + }, + { + "epoch": 0.73, + "learning_rate": 4.11060477213298e-06, + "loss": 1.3136, + "step": 6965 + }, + { + "epoch": 0.73, + "eval_loss": 1.399178147315979, + "eval_runtime": 77.5864, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 6965 + }, + { + "epoch": 0.73, + "learning_rate": 4.1076470363779235e-06, + "loss": 1.2833, + "step": 6966 + }, + { + "epoch": 0.73, + "learning_rate": 4.104690090046765e-06, + "loss": 1.3177, + "step": 6967 + }, + { + "epoch": 0.73, + "learning_rate": 4.101733933535663e-06, + "loss": 1.2623, + "step": 6968 + }, + { + "epoch": 0.73, + "learning_rate": 4.0987785672406585e-06, + "loss": 1.2814, + "step": 6969 + }, + { + "epoch": 0.73, + "learning_rate": 4.0958239915577036e-06, + "loss": 1.3823, + "step": 6970 + }, + { + "epoch": 0.73, + "learning_rate": 4.092870206882627e-06, + "loss": 1.2926, + "step": 6971 + }, + { + "epoch": 0.73, + "learning_rate": 4.089917213611164e-06, + "loss": 1.3324, + "step": 6972 + }, + { + "epoch": 0.73, + "learning_rate": 4.086965012138943e-06, + "loss": 1.3521, + "step": 6973 + }, + { + "epoch": 0.73, + "learning_rate": 4.084013602861476e-06, + "loss": 1.4828, + "step": 6974 + }, + { + "epoch": 0.73, + "learning_rate": 4.0810629861741804e-06, + "loss": 1.3187, + "step": 6975 + }, + { + "epoch": 0.73, + "learning_rate": 4.078113162472366e-06, + "loss": 1.3478, + "step": 6976 + }, + { + "epoch": 0.73, + "learning_rate": 4.075164132151227e-06, + "loss": 1.4256, + "step": 6977 + }, + { + "epoch": 0.73, + "learning_rate": 4.0722158956058635e-06, + "loss": 1.2815, + "step": 6978 + }, + { + "epoch": 0.73, + "learning_rate": 4.069268453231257e-06, + "loss": 1.3031, + "step": 6979 + }, + { + "epoch": 0.73, + "learning_rate": 4.066321805422292e-06, + "loss": 1.2983, + "step": 6980 + }, + { + "epoch": 0.73, + "learning_rate": 4.063375952573748e-06, + "loss": 1.3595, + "step": 6981 + }, + { + "epoch": 0.73, + "learning_rate": 4.060430895080286e-06, + "loss": 1.3119, + "step": 6982 + }, + { + "epoch": 0.73, + "learning_rate": 4.057486633336472e-06, + "loss": 1.328, + "step": 6983 + }, + { + "epoch": 0.73, + "learning_rate": 4.054543167736766e-06, + "loss": 1.232, + "step": 6984 + }, + { + "epoch": 0.73, + "learning_rate": 4.0516004986755064e-06, + "loss": 1.3288, + "step": 6985 + }, + { + "epoch": 0.73, + "learning_rate": 4.048658626546945e-06, + "loss": 1.2916, + "step": 6986 + }, + { + "epoch": 0.73, + "learning_rate": 4.045717551745209e-06, + "loss": 1.2411, + "step": 6987 + }, + { + "epoch": 0.73, + "learning_rate": 4.042777274664331e-06, + "loss": 1.3256, + "step": 6988 + }, + { + "epoch": 0.73, + "learning_rate": 4.039837795698237e-06, + "loss": 1.3455, + "step": 6989 + }, + { + "epoch": 0.73, + "learning_rate": 4.036899115240732e-06, + "loss": 1.3303, + "step": 6990 + }, + { + "epoch": 0.73, + "learning_rate": 4.033961233685529e-06, + "loss": 1.2805, + "step": 6991 + }, + { + "epoch": 0.73, + "learning_rate": 4.031024151426233e-06, + "loss": 1.3958, + "step": 6992 + }, + { + "epoch": 0.73, + "learning_rate": 4.0280878688563275e-06, + "loss": 1.2853, + "step": 6993 + }, + { + "epoch": 0.73, + "learning_rate": 4.0251523863692054e-06, + "loss": 1.2433, + "step": 6994 + }, + { + "epoch": 0.73, + "learning_rate": 4.022217704358148e-06, + "loss": 1.2644, + "step": 6995 + }, + { + "epoch": 0.73, + "learning_rate": 4.0192838232163204e-06, + "loss": 1.3218, + "step": 6996 + }, + { + "epoch": 0.73, + "learning_rate": 4.016350743336795e-06, + "loss": 1.2973, + "step": 6997 + }, + { + "epoch": 0.73, + "learning_rate": 4.013418465112521e-06, + "loss": 1.3209, + "step": 6998 + }, + { + "epoch": 0.73, + "learning_rate": 4.010486988936353e-06, + "loss": 1.2855, + "step": 6999 + }, + { + "epoch": 0.73, + "learning_rate": 4.007556315201035e-06, + "loss": 1.2381, + "step": 7000 + }, + { + "epoch": 0.73, + "learning_rate": 4.004626444299198e-06, + "loss": 1.3558, + "step": 7001 + }, + { + "epoch": 0.73, + "learning_rate": 4.001697376623371e-06, + "loss": 1.3139, + "step": 7002 + }, + { + "epoch": 0.73, + "learning_rate": 3.998769112565978e-06, + "loss": 1.3582, + "step": 7003 + }, + { + "epoch": 0.73, + "learning_rate": 3.9958416525193225e-06, + "loss": 1.2684, + "step": 7004 + }, + { + "epoch": 0.73, + "learning_rate": 3.992914996875618e-06, + "loss": 1.2915, + "step": 7005 + }, + { + "epoch": 0.73, + "learning_rate": 3.9899891460269536e-06, + "loss": 1.3205, + "step": 7006 + }, + { + "epoch": 0.73, + "learning_rate": 3.987064100365321e-06, + "loss": 1.2966, + "step": 7007 + }, + { + "epoch": 0.73, + "learning_rate": 3.984139860282606e-06, + "loss": 1.2691, + "step": 7008 + }, + { + "epoch": 0.74, + "learning_rate": 3.981216426170572e-06, + "loss": 1.3421, + "step": 7009 + }, + { + "epoch": 0.74, + "learning_rate": 3.97829379842089e-06, + "loss": 1.3034, + "step": 7010 + }, + { + "epoch": 0.74, + "learning_rate": 3.9753719774251195e-06, + "loss": 1.2863, + "step": 7011 + }, + { + "epoch": 0.74, + "learning_rate": 3.972450963574703e-06, + "loss": 1.3812, + "step": 7012 + }, + { + "epoch": 0.74, + "learning_rate": 3.969530757260986e-06, + "loss": 1.334, + "step": 7013 + }, + { + "epoch": 0.74, + "learning_rate": 3.966611358875201e-06, + "loss": 1.3289, + "step": 7014 + }, + { + "epoch": 0.74, + "learning_rate": 3.963692768808468e-06, + "loss": 1.395, + "step": 7015 + }, + { + "epoch": 0.74, + "learning_rate": 3.960774987451811e-06, + "loss": 1.3298, + "step": 7016 + }, + { + "epoch": 0.74, + "learning_rate": 3.957858015196128e-06, + "loss": 1.3304, + "step": 7017 + }, + { + "epoch": 0.74, + "learning_rate": 3.954941852432224e-06, + "loss": 1.301, + "step": 7018 + }, + { + "epoch": 0.74, + "learning_rate": 3.952026499550791e-06, + "loss": 1.3568, + "step": 7019 + }, + { + "epoch": 0.74, + "learning_rate": 3.949111956942406e-06, + "loss": 1.4464, + "step": 7020 + }, + { + "epoch": 0.74, + "learning_rate": 3.946198224997548e-06, + "loss": 1.4417, + "step": 7021 + }, + { + "epoch": 0.74, + "learning_rate": 3.943285304106583e-06, + "loss": 1.3979, + "step": 7022 + }, + { + "epoch": 0.74, + "learning_rate": 3.940373194659761e-06, + "loss": 1.2943, + "step": 7023 + }, + { + "epoch": 0.74, + "learning_rate": 3.937461897047239e-06, + "loss": 1.2571, + "step": 7024 + }, + { + "epoch": 0.74, + "learning_rate": 3.9345514116590454e-06, + "loss": 1.3433, + "step": 7025 + }, + { + "epoch": 0.74, + "learning_rate": 3.931641738885117e-06, + "loss": 1.4203, + "step": 7026 + }, + { + "epoch": 0.74, + "learning_rate": 3.9287328791152775e-06, + "loss": 1.3657, + "step": 7027 + }, + { + "epoch": 0.74, + "learning_rate": 3.925824832739234e-06, + "loss": 1.3954, + "step": 7028 + }, + { + "epoch": 0.74, + "learning_rate": 3.92291760014659e-06, + "loss": 1.2847, + "step": 7029 + }, + { + "epoch": 0.74, + "learning_rate": 3.920011181726846e-06, + "loss": 1.2776, + "step": 7030 + }, + { + "epoch": 0.74, + "learning_rate": 3.91710557786938e-06, + "loss": 1.3391, + "step": 7031 + }, + { + "epoch": 0.74, + "learning_rate": 3.914200788963472e-06, + "loss": 1.2935, + "step": 7032 + }, + { + "epoch": 0.74, + "learning_rate": 3.911296815398291e-06, + "loss": 1.3775, + "step": 7033 + }, + { + "epoch": 0.74, + "learning_rate": 3.90839365756289e-06, + "loss": 1.3652, + "step": 7034 + }, + { + "epoch": 0.74, + "learning_rate": 3.905491315846224e-06, + "loss": 1.2902, + "step": 7035 + }, + { + "epoch": 0.74, + "learning_rate": 3.902589790637125e-06, + "loss": 1.2859, + "step": 7036 + }, + { + "epoch": 0.74, + "learning_rate": 3.899689082324325e-06, + "loss": 1.4019, + "step": 7037 + }, + { + "epoch": 0.74, + "learning_rate": 3.89678919129645e-06, + "loss": 1.299, + "step": 7038 + }, + { + "epoch": 0.74, + "learning_rate": 3.893890117942003e-06, + "loss": 1.275, + "step": 7039 + }, + { + "epoch": 0.74, + "learning_rate": 3.890991862649388e-06, + "loss": 1.2593, + "step": 7040 + }, + { + "epoch": 0.74, + "learning_rate": 3.888094425806902e-06, + "loss": 1.2932, + "step": 7041 + }, + { + "epoch": 0.74, + "learning_rate": 3.885197807802719e-06, + "loss": 1.3038, + "step": 7042 + }, + { + "epoch": 0.74, + "learning_rate": 3.882302009024917e-06, + "loss": 1.285, + "step": 7043 + }, + { + "epoch": 0.74, + "learning_rate": 3.879407029861455e-06, + "loss": 1.4116, + "step": 7044 + }, + { + "epoch": 0.74, + "learning_rate": 3.876512870700187e-06, + "loss": 1.3823, + "step": 7045 + }, + { + "epoch": 0.74, + "learning_rate": 3.873619531928858e-06, + "loss": 1.2803, + "step": 7046 + }, + { + "epoch": 0.74, + "learning_rate": 3.870727013935099e-06, + "loss": 1.3287, + "step": 7047 + }, + { + "epoch": 0.74, + "learning_rate": 3.867835317106432e-06, + "loss": 1.3919, + "step": 7048 + }, + { + "epoch": 0.74, + "learning_rate": 3.864944441830275e-06, + "loss": 1.3967, + "step": 7049 + }, + { + "epoch": 0.74, + "learning_rate": 3.862054388493924e-06, + "loss": 1.2749, + "step": 7050 + }, + { + "epoch": 0.74, + "learning_rate": 3.85916515748458e-06, + "loss": 1.3408, + "step": 7051 + }, + { + "epoch": 0.74, + "learning_rate": 3.856276749189317e-06, + "loss": 1.3143, + "step": 7052 + }, + { + "epoch": 0.74, + "learning_rate": 3.853389163995111e-06, + "loss": 1.3661, + "step": 7053 + }, + { + "epoch": 0.74, + "learning_rate": 3.8505024022888305e-06, + "loss": 1.3094, + "step": 7054 + }, + { + "epoch": 0.74, + "learning_rate": 3.847616464457216e-06, + "loss": 1.2736, + "step": 7055 + }, + { + "epoch": 0.74, + "learning_rate": 3.844731350886917e-06, + "loss": 1.3628, + "step": 7056 + }, + { + "epoch": 0.74, + "learning_rate": 3.841847061964465e-06, + "loss": 1.2706, + "step": 7057 + }, + { + "epoch": 0.74, + "learning_rate": 3.838963598076275e-06, + "loss": 1.2566, + "step": 7058 + }, + { + "epoch": 0.74, + "learning_rate": 3.83608095960866e-06, + "loss": 1.2415, + "step": 7059 + }, + { + "epoch": 0.74, + "learning_rate": 3.833199146947823e-06, + "loss": 1.2748, + "step": 7060 + }, + { + "epoch": 0.74, + "learning_rate": 3.830318160479847e-06, + "loss": 1.4672, + "step": 7061 + }, + { + "epoch": 0.74, + "learning_rate": 3.827438000590714e-06, + "loss": 1.2907, + "step": 7062 + }, + { + "epoch": 0.74, + "learning_rate": 3.824558667666288e-06, + "loss": 1.3477, + "step": 7063 + }, + { + "epoch": 0.74, + "learning_rate": 3.821680162092328e-06, + "loss": 1.1135, + "step": 7064 + }, + { + "epoch": 0.74, + "learning_rate": 3.8188024842544825e-06, + "loss": 1.3724, + "step": 7065 + }, + { + "epoch": 0.74, + "learning_rate": 3.81592563453828e-06, + "loss": 1.3854, + "step": 7066 + }, + { + "epoch": 0.74, + "learning_rate": 3.8130496133291473e-06, + "loss": 1.3074, + "step": 7067 + }, + { + "epoch": 0.74, + "learning_rate": 3.8101744210124012e-06, + "loss": 1.4434, + "step": 7068 + }, + { + "epoch": 0.74, + "learning_rate": 3.807300057973238e-06, + "loss": 1.2754, + "step": 7069 + }, + { + "epoch": 0.74, + "learning_rate": 3.804426524596754e-06, + "loss": 1.3654, + "step": 7070 + }, + { + "epoch": 0.74, + "learning_rate": 3.8015538212679214e-06, + "loss": 1.2616, + "step": 7071 + }, + { + "epoch": 0.74, + "learning_rate": 3.798681948371613e-06, + "loss": 1.2939, + "step": 7072 + }, + { + "epoch": 0.74, + "learning_rate": 3.7958109062925894e-06, + "loss": 1.2787, + "step": 7073 + }, + { + "epoch": 0.74, + "learning_rate": 3.792940695415489e-06, + "loss": 1.2953, + "step": 7074 + }, + { + "epoch": 0.74, + "learning_rate": 3.7900713161248515e-06, + "loss": 1.2714, + "step": 7075 + }, + { + "epoch": 0.74, + "learning_rate": 3.7872027688051004e-06, + "loss": 1.3085, + "step": 7076 + }, + { + "epoch": 0.74, + "learning_rate": 3.7843350538405433e-06, + "loss": 1.311, + "step": 7077 + }, + { + "epoch": 0.74, + "learning_rate": 3.781468171615382e-06, + "loss": 1.3367, + "step": 7078 + }, + { + "epoch": 0.74, + "learning_rate": 3.7786021225137102e-06, + "loss": 1.2768, + "step": 7079 + }, + { + "epoch": 0.74, + "learning_rate": 3.775736906919496e-06, + "loss": 1.2828, + "step": 7080 + }, + { + "epoch": 0.74, + "learning_rate": 3.772872525216613e-06, + "loss": 1.3682, + "step": 7081 + }, + { + "epoch": 0.74, + "learning_rate": 3.7700089777888072e-06, + "loss": 1.3906, + "step": 7082 + }, + { + "epoch": 0.74, + "learning_rate": 3.767146265019723e-06, + "loss": 1.2712, + "step": 7083 + }, + { + "epoch": 0.74, + "learning_rate": 3.764284387292896e-06, + "loss": 1.3405, + "step": 7084 + }, + { + "epoch": 0.74, + "learning_rate": 3.761423344991736e-06, + "loss": 1.3941, + "step": 7085 + }, + { + "epoch": 0.74, + "learning_rate": 3.7585631384995523e-06, + "loss": 1.3463, + "step": 7086 + }, + { + "epoch": 0.74, + "learning_rate": 3.7557037681995423e-06, + "loss": 1.2771, + "step": 7087 + }, + { + "epoch": 0.74, + "learning_rate": 3.7528452344747834e-06, + "loss": 1.2706, + "step": 7088 + }, + { + "epoch": 0.74, + "learning_rate": 3.7499875377082497e-06, + "loss": 1.2672, + "step": 7089 + }, + { + "epoch": 0.74, + "learning_rate": 3.7471306782827944e-06, + "loss": 1.2638, + "step": 7090 + }, + { + "epoch": 0.74, + "learning_rate": 3.744274656581166e-06, + "loss": 1.3417, + "step": 7091 + }, + { + "epoch": 0.74, + "learning_rate": 3.7414194729860008e-06, + "loss": 1.278, + "step": 7092 + }, + { + "epoch": 0.74, + "learning_rate": 3.738565127879814e-06, + "loss": 1.2753, + "step": 7093 + }, + { + "epoch": 0.74, + "learning_rate": 3.7357116216450183e-06, + "loss": 1.2989, + "step": 7094 + }, + { + "epoch": 0.74, + "learning_rate": 3.7328589546639127e-06, + "loss": 1.263, + "step": 7095 + }, + { + "epoch": 0.74, + "learning_rate": 3.7300071273186745e-06, + "loss": 1.3534, + "step": 7096 + }, + { + "epoch": 0.74, + "learning_rate": 3.7271561399913825e-06, + "loss": 1.2565, + "step": 7097 + }, + { + "epoch": 0.74, + "learning_rate": 3.724305993063989e-06, + "loss": 1.3233, + "step": 7098 + }, + { + "epoch": 0.74, + "learning_rate": 3.7214566869183443e-06, + "loss": 1.3179, + "step": 7099 + }, + { + "epoch": 0.74, + "learning_rate": 3.718608221936184e-06, + "loss": 1.2749, + "step": 7100 + }, + { + "epoch": 0.74, + "learning_rate": 3.715760598499124e-06, + "loss": 1.3106, + "step": 7101 + }, + { + "epoch": 0.74, + "learning_rate": 3.712913816988675e-06, + "loss": 1.3115, + "step": 7102 + }, + { + "epoch": 0.74, + "learning_rate": 3.7100678777862364e-06, + "loss": 1.2798, + "step": 7103 + }, + { + "epoch": 0.74, + "learning_rate": 3.7072227812730853e-06, + "loss": 1.3964, + "step": 7104 + }, + { + "epoch": 0.75, + "learning_rate": 3.7043785278303923e-06, + "loss": 1.4034, + "step": 7105 + }, + { + "epoch": 0.75, + "learning_rate": 3.70153511783922e-06, + "loss": 1.3244, + "step": 7106 + }, + { + "epoch": 0.75, + "learning_rate": 3.698692551680505e-06, + "loss": 1.3283, + "step": 7107 + }, + { + "epoch": 0.75, + "learning_rate": 3.6958508297350847e-06, + "loss": 1.3567, + "step": 7108 + }, + { + "epoch": 0.75, + "learning_rate": 3.6930099523836692e-06, + "loss": 1.3178, + "step": 7109 + }, + { + "epoch": 0.75, + "learning_rate": 3.6901699200068673e-06, + "loss": 1.2697, + "step": 7110 + }, + { + "epoch": 0.75, + "learning_rate": 3.687330732985175e-06, + "loss": 1.2501, + "step": 7111 + }, + { + "epoch": 0.75, + "learning_rate": 3.6844923916989607e-06, + "loss": 1.2772, + "step": 7112 + }, + { + "epoch": 0.75, + "learning_rate": 3.681654896528495e-06, + "loss": 1.2845, + "step": 7113 + }, + { + "epoch": 0.75, + "learning_rate": 3.6788182478539312e-06, + "loss": 1.3151, + "step": 7114 + }, + { + "epoch": 0.75, + "learning_rate": 3.6759824460553016e-06, + "loss": 1.4925, + "step": 7115 + }, + { + "epoch": 0.75, + "learning_rate": 3.673147491512539e-06, + "loss": 1.2892, + "step": 7116 + }, + { + "epoch": 0.75, + "learning_rate": 3.670313384605444e-06, + "loss": 1.2906, + "step": 7117 + }, + { + "epoch": 0.75, + "learning_rate": 3.6674801257137195e-06, + "loss": 1.3927, + "step": 7118 + }, + { + "epoch": 0.75, + "learning_rate": 3.6646477152169522e-06, + "loss": 1.4001, + "step": 7119 + }, + { + "epoch": 0.75, + "learning_rate": 3.6618161534946074e-06, + "loss": 1.3363, + "step": 7120 + }, + { + "epoch": 0.75, + "learning_rate": 3.658985440926044e-06, + "loss": 1.3297, + "step": 7121 + }, + { + "epoch": 0.75, + "learning_rate": 3.656155577890507e-06, + "loss": 1.3029, + "step": 7122 + }, + { + "epoch": 0.75, + "learning_rate": 3.653326564767119e-06, + "loss": 1.3452, + "step": 7123 + }, + { + "epoch": 0.75, + "learning_rate": 3.6504984019348987e-06, + "loss": 1.3246, + "step": 7124 + }, + { + "epoch": 0.75, + "learning_rate": 3.647671089772752e-06, + "loss": 1.3285, + "step": 7125 + }, + { + "epoch": 0.75, + "learning_rate": 3.6448446286594574e-06, + "loss": 1.3127, + "step": 7126 + }, + { + "epoch": 0.75, + "learning_rate": 3.6420190189736946e-06, + "loss": 1.3224, + "step": 7127 + }, + { + "epoch": 0.75, + "learning_rate": 3.6391942610940178e-06, + "loss": 1.3086, + "step": 7128 + }, + { + "epoch": 0.75, + "learning_rate": 3.6363703553988748e-06, + "loss": 1.3741, + "step": 7129 + }, + { + "epoch": 0.75, + "learning_rate": 3.633547302266599e-06, + "loss": 1.3192, + "step": 7130 + }, + { + "epoch": 0.75, + "learning_rate": 3.6307251020754e-06, + "loss": 1.3032, + "step": 7131 + }, + { + "epoch": 0.75, + "learning_rate": 3.6279037552033847e-06, + "loss": 1.2642, + "step": 7132 + }, + { + "epoch": 0.75, + "learning_rate": 3.6250832620285436e-06, + "loss": 1.3948, + "step": 7133 + }, + { + "epoch": 0.75, + "learning_rate": 3.6222636229287445e-06, + "loss": 1.3542, + "step": 7134 + }, + { + "epoch": 0.75, + "learning_rate": 3.6194448382817526e-06, + "loss": 1.3028, + "step": 7135 + }, + { + "epoch": 0.75, + "learning_rate": 3.616626908465205e-06, + "loss": 1.3017, + "step": 7136 + }, + { + "epoch": 0.75, + "learning_rate": 3.613809833856636e-06, + "loss": 1.3072, + "step": 7137 + }, + { + "epoch": 0.75, + "learning_rate": 3.6109936148334666e-06, + "loss": 1.3065, + "step": 7138 + }, + { + "epoch": 0.75, + "learning_rate": 3.608178251772988e-06, + "loss": 1.4268, + "step": 7139 + }, + { + "epoch": 0.75, + "learning_rate": 3.6053637450523914e-06, + "loss": 1.301, + "step": 7140 + }, + { + "epoch": 0.75, + "learning_rate": 3.6025500950487514e-06, + "loss": 1.2873, + "step": 7141 + }, + { + "epoch": 0.75, + "learning_rate": 3.599737302139018e-06, + "loss": 1.2831, + "step": 7142 + }, + { + "epoch": 0.75, + "learning_rate": 3.5969253667000403e-06, + "loss": 1.5125, + "step": 7143 + }, + { + "epoch": 0.75, + "learning_rate": 3.594114289108538e-06, + "loss": 1.3643, + "step": 7144 + }, + { + "epoch": 0.75, + "learning_rate": 3.5913040697411272e-06, + "loss": 1.3157, + "step": 7145 + }, + { + "epoch": 0.75, + "learning_rate": 3.5884947089743084e-06, + "loss": 1.2687, + "step": 7146 + }, + { + "epoch": 0.75, + "learning_rate": 3.585686207184458e-06, + "loss": 1.3227, + "step": 7147 + }, + { + "epoch": 0.75, + "learning_rate": 3.5828785647478435e-06, + "loss": 1.2745, + "step": 7148 + }, + { + "epoch": 0.75, + "learning_rate": 3.5800717820406226e-06, + "loss": 1.332, + "step": 7149 + }, + { + "epoch": 0.75, + "learning_rate": 3.5772658594388253e-06, + "loss": 1.2863, + "step": 7150 + }, + { + "epoch": 0.75, + "learning_rate": 3.5744607973183766e-06, + "loss": 1.3791, + "step": 7151 + }, + { + "epoch": 0.75, + "learning_rate": 3.5716565960550844e-06, + "loss": 1.2781, + "step": 7152 + }, + { + "epoch": 0.75, + "learning_rate": 3.5688532560246348e-06, + "loss": 1.252, + "step": 7153 + }, + { + "epoch": 0.75, + "learning_rate": 3.5660507776026086e-06, + "loss": 1.3158, + "step": 7154 + }, + { + "epoch": 0.75, + "learning_rate": 3.5632491611644603e-06, + "loss": 1.3241, + "step": 7155 + }, + { + "epoch": 0.75, + "learning_rate": 3.5604484070855382e-06, + "loss": 1.2572, + "step": 7156 + }, + { + "epoch": 0.75, + "learning_rate": 3.5576485157410733e-06, + "loss": 1.3734, + "step": 7157 + }, + { + "epoch": 0.75, + "learning_rate": 3.5548494875061724e-06, + "loss": 1.3253, + "step": 7158 + }, + { + "epoch": 0.75, + "learning_rate": 3.5520513227558385e-06, + "loss": 1.2659, + "step": 7159 + }, + { + "epoch": 0.75, + "learning_rate": 3.5492540218649553e-06, + "loss": 1.3149, + "step": 7160 + }, + { + "epoch": 0.75, + "learning_rate": 3.546457585208283e-06, + "loss": 1.3413, + "step": 7161 + }, + { + "epoch": 0.75, + "learning_rate": 3.5436620131604803e-06, + "loss": 1.2846, + "step": 7162 + }, + { + "epoch": 0.75, + "learning_rate": 3.540867306096073e-06, + "loss": 1.3239, + "step": 7163 + }, + { + "epoch": 0.75, + "learning_rate": 3.5380734643894856e-06, + "loss": 1.3137, + "step": 7164 + }, + { + "epoch": 0.75, + "eval_loss": 1.397520899772644, + "eval_runtime": 77.542, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 7164 + }, + { + "epoch": 0.75, + "learning_rate": 3.535280488415024e-06, + "loss": 1.414, + "step": 7165 + }, + { + "epoch": 0.75, + "learning_rate": 3.5324883785468665e-06, + "loss": 1.2708, + "step": 7166 + }, + { + "epoch": 0.75, + "learning_rate": 3.529697135159089e-06, + "loss": 1.2975, + "step": 7167 + }, + { + "epoch": 0.75, + "learning_rate": 3.526906758625651e-06, + "loss": 1.3723, + "step": 7168 + }, + { + "epoch": 0.75, + "learning_rate": 3.5241172493203822e-06, + "loss": 1.4105, + "step": 7169 + }, + { + "epoch": 0.75, + "learning_rate": 3.5213286076170107e-06, + "loss": 1.2592, + "step": 7170 + }, + { + "epoch": 0.75, + "learning_rate": 3.5185408338891437e-06, + "loss": 1.3361, + "step": 7171 + }, + { + "epoch": 0.75, + "learning_rate": 3.515753928510267e-06, + "loss": 1.2591, + "step": 7172 + }, + { + "epoch": 0.75, + "learning_rate": 3.512967891853759e-06, + "loss": 1.2938, + "step": 7173 + }, + { + "epoch": 0.75, + "learning_rate": 3.510182724292872e-06, + "loss": 1.4116, + "step": 7174 + }, + { + "epoch": 0.75, + "learning_rate": 3.5073984262007486e-06, + "loss": 1.3968, + "step": 7175 + }, + { + "epoch": 0.75, + "learning_rate": 3.5046149979504184e-06, + "loss": 1.31, + "step": 7176 + }, + { + "epoch": 0.75, + "learning_rate": 3.5018324399147817e-06, + "loss": 1.2966, + "step": 7177 + }, + { + "epoch": 0.75, + "learning_rate": 3.4990507524666327e-06, + "loss": 1.3431, + "step": 7178 + }, + { + "epoch": 0.75, + "learning_rate": 3.49626993597865e-06, + "loss": 1.3227, + "step": 7179 + }, + { + "epoch": 0.75, + "learning_rate": 3.4934899908233834e-06, + "loss": 1.201, + "step": 7180 + }, + { + "epoch": 0.75, + "learning_rate": 3.490710917373283e-06, + "loss": 1.3003, + "step": 7181 + }, + { + "epoch": 0.75, + "learning_rate": 3.487932716000666e-06, + "loss": 1.2879, + "step": 7182 + }, + { + "epoch": 0.75, + "learning_rate": 3.485155387077742e-06, + "loss": 1.2742, + "step": 7183 + }, + { + "epoch": 0.75, + "learning_rate": 3.4823789309766065e-06, + "loss": 1.2972, + "step": 7184 + }, + { + "epoch": 0.75, + "learning_rate": 3.479603348069226e-06, + "loss": 1.3763, + "step": 7185 + }, + { + "epoch": 0.75, + "learning_rate": 3.4768286387274597e-06, + "loss": 1.4653, + "step": 7186 + }, + { + "epoch": 0.75, + "learning_rate": 3.4740548033230524e-06, + "loss": 1.3534, + "step": 7187 + }, + { + "epoch": 0.75, + "learning_rate": 3.4712818422276207e-06, + "loss": 1.3917, + "step": 7188 + }, + { + "epoch": 0.75, + "learning_rate": 3.4685097558126733e-06, + "loss": 1.306, + "step": 7189 + }, + { + "epoch": 0.75, + "learning_rate": 3.465738544449596e-06, + "loss": 1.4628, + "step": 7190 + }, + { + "epoch": 0.75, + "learning_rate": 3.4629682085096606e-06, + "loss": 1.3916, + "step": 7191 + }, + { + "epoch": 0.75, + "learning_rate": 3.4601987483640243e-06, + "loss": 1.3348, + "step": 7192 + }, + { + "epoch": 0.75, + "learning_rate": 3.457430164383718e-06, + "loss": 1.4771, + "step": 7193 + }, + { + "epoch": 0.75, + "learning_rate": 3.4546624569396635e-06, + "loss": 1.5004, + "step": 7194 + }, + { + "epoch": 0.75, + "learning_rate": 3.451895626402667e-06, + "loss": 1.279, + "step": 7195 + }, + { + "epoch": 0.75, + "learning_rate": 3.4491296731434053e-06, + "loss": 1.3263, + "step": 7196 + }, + { + "epoch": 0.75, + "learning_rate": 3.4463645975324466e-06, + "loss": 1.2449, + "step": 7197 + }, + { + "epoch": 0.75, + "learning_rate": 3.4436003999402466e-06, + "loss": 1.2743, + "step": 7198 + }, + { + "epoch": 0.75, + "learning_rate": 3.4408370807371283e-06, + "loss": 1.3127, + "step": 7199 + }, + { + "epoch": 0.76, + "learning_rate": 3.438074640293312e-06, + "loss": 1.2996, + "step": 7200 + }, + { + "epoch": 0.76, + "learning_rate": 3.435313078978887e-06, + "loss": 1.3114, + "step": 7201 + }, + { + "epoch": 0.76, + "learning_rate": 3.432552397163835e-06, + "loss": 1.2574, + "step": 7202 + }, + { + "epoch": 0.76, + "learning_rate": 3.42979259521802e-06, + "loss": 1.2605, + "step": 7203 + }, + { + "epoch": 0.76, + "learning_rate": 3.4270336735111785e-06, + "loss": 1.2578, + "step": 7204 + }, + { + "epoch": 0.76, + "learning_rate": 3.424275632412938e-06, + "loss": 1.3297, + "step": 7205 + }, + { + "epoch": 0.76, + "learning_rate": 3.4215184722928073e-06, + "loss": 1.2353, + "step": 7206 + }, + { + "epoch": 0.76, + "learning_rate": 3.4187621935201707e-06, + "loss": 1.288, + "step": 7207 + }, + { + "epoch": 0.76, + "learning_rate": 3.416006796464304e-06, + "loss": 1.2947, + "step": 7208 + }, + { + "epoch": 0.76, + "learning_rate": 3.4132522814943513e-06, + "loss": 1.4208, + "step": 7209 + }, + { + "epoch": 0.76, + "learning_rate": 3.4104986489793534e-06, + "loss": 1.3273, + "step": 7210 + }, + { + "epoch": 0.76, + "learning_rate": 3.4077458992882285e-06, + "loss": 1.274, + "step": 7211 + }, + { + "epoch": 0.76, + "learning_rate": 3.404994032789766e-06, + "loss": 1.2782, + "step": 7212 + }, + { + "epoch": 0.76, + "learning_rate": 3.4022430498526505e-06, + "loss": 1.3513, + "step": 7213 + }, + { + "epoch": 0.76, + "learning_rate": 3.3994929508454455e-06, + "loss": 1.2843, + "step": 7214 + }, + { + "epoch": 0.76, + "learning_rate": 3.3967437361365873e-06, + "loss": 1.2764, + "step": 7215 + }, + { + "epoch": 0.76, + "learning_rate": 3.3939954060944036e-06, + "loss": 1.2786, + "step": 7216 + }, + { + "epoch": 0.76, + "learning_rate": 3.391247961087103e-06, + "loss": 1.2927, + "step": 7217 + }, + { + "epoch": 0.76, + "learning_rate": 3.3885014014827657e-06, + "loss": 1.3735, + "step": 7218 + }, + { + "epoch": 0.76, + "learning_rate": 3.385755727649367e-06, + "loss": 1.3065, + "step": 7219 + }, + { + "epoch": 0.76, + "learning_rate": 3.3830109399547506e-06, + "loss": 1.2463, + "step": 7220 + }, + { + "epoch": 0.76, + "learning_rate": 3.3802670387666492e-06, + "loss": 1.2496, + "step": 7221 + }, + { + "epoch": 0.76, + "learning_rate": 3.3775240244526796e-06, + "loss": 1.2807, + "step": 7222 + }, + { + "epoch": 0.76, + "learning_rate": 3.3747818973803294e-06, + "loss": 1.313, + "step": 7223 + }, + { + "epoch": 0.76, + "learning_rate": 3.372040657916974e-06, + "loss": 1.3557, + "step": 7224 + }, + { + "epoch": 0.76, + "learning_rate": 3.3693003064298744e-06, + "loss": 1.3705, + "step": 7225 + }, + { + "epoch": 0.76, + "learning_rate": 3.366560843286161e-06, + "loss": 1.3763, + "step": 7226 + }, + { + "epoch": 0.76, + "learning_rate": 3.3638222688528565e-06, + "loss": 1.3252, + "step": 7227 + }, + { + "epoch": 0.76, + "learning_rate": 3.361084583496853e-06, + "loss": 1.2635, + "step": 7228 + }, + { + "epoch": 0.76, + "learning_rate": 3.3583477875849346e-06, + "loss": 1.3084, + "step": 7229 + }, + { + "epoch": 0.76, + "learning_rate": 3.3556118814837646e-06, + "loss": 1.3347, + "step": 7230 + }, + { + "epoch": 0.76, + "learning_rate": 3.3528768655598764e-06, + "loss": 1.3937, + "step": 7231 + }, + { + "epoch": 0.76, + "learning_rate": 3.350142740179696e-06, + "loss": 1.3251, + "step": 7232 + }, + { + "epoch": 0.76, + "learning_rate": 3.347409505709529e-06, + "loss": 1.3654, + "step": 7233 + }, + { + "epoch": 0.76, + "learning_rate": 3.344677162515553e-06, + "loss": 1.3864, + "step": 7234 + }, + { + "epoch": 0.76, + "learning_rate": 3.3419457109638377e-06, + "loss": 1.3142, + "step": 7235 + }, + { + "epoch": 0.76, + "learning_rate": 3.3392151514203195e-06, + "loss": 1.3557, + "step": 7236 + }, + { + "epoch": 0.76, + "learning_rate": 3.3364854842508276e-06, + "loss": 1.3093, + "step": 7237 + }, + { + "epoch": 0.76, + "learning_rate": 3.333756709821072e-06, + "loss": 1.3763, + "step": 7238 + }, + { + "epoch": 0.76, + "learning_rate": 3.3310288284966297e-06, + "loss": 1.2943, + "step": 7239 + }, + { + "epoch": 0.76, + "learning_rate": 3.3283018406429703e-06, + "loss": 1.473, + "step": 7240 + }, + { + "epoch": 0.76, + "learning_rate": 3.3255757466254448e-06, + "loss": 1.2501, + "step": 7241 + }, + { + "epoch": 0.76, + "learning_rate": 3.322850546809271e-06, + "loss": 1.2893, + "step": 7242 + }, + { + "epoch": 0.76, + "learning_rate": 3.3201262415595614e-06, + "loss": 1.2995, + "step": 7243 + }, + { + "epoch": 0.76, + "learning_rate": 3.3174028312413044e-06, + "loss": 1.2985, + "step": 7244 + }, + { + "epoch": 0.76, + "learning_rate": 3.31468031621936e-06, + "loss": 1.2868, + "step": 7245 + }, + { + "epoch": 0.76, + "learning_rate": 3.311958696858484e-06, + "loss": 1.2467, + "step": 7246 + }, + { + "epoch": 0.76, + "learning_rate": 3.309237973523295e-06, + "loss": 1.2303, + "step": 7247 + }, + { + "epoch": 0.76, + "learning_rate": 3.3065181465783045e-06, + "loss": 1.3172, + "step": 7248 + }, + { + "epoch": 0.76, + "learning_rate": 3.303799216387902e-06, + "loss": 1.2003, + "step": 7249 + }, + { + "epoch": 0.76, + "learning_rate": 3.3010811833163482e-06, + "loss": 1.2931, + "step": 7250 + }, + { + "epoch": 0.76, + "learning_rate": 3.2983640477277925e-06, + "loss": 1.3135, + "step": 7251 + }, + { + "epoch": 0.76, + "learning_rate": 3.2956478099862644e-06, + "loss": 1.2711, + "step": 7252 + }, + { + "epoch": 0.76, + "learning_rate": 3.292932470455663e-06, + "loss": 1.291, + "step": 7253 + }, + { + "epoch": 0.76, + "learning_rate": 3.2902180294997832e-06, + "loss": 1.2838, + "step": 7254 + }, + { + "epoch": 0.76, + "learning_rate": 3.2875044874822804e-06, + "loss": 1.2381, + "step": 7255 + }, + { + "epoch": 0.76, + "learning_rate": 3.284791844766705e-06, + "loss": 1.2966, + "step": 7256 + }, + { + "epoch": 0.76, + "learning_rate": 3.282080101716484e-06, + "loss": 1.3418, + "step": 7257 + }, + { + "epoch": 0.76, + "learning_rate": 3.2793692586949143e-06, + "loss": 1.3247, + "step": 7258 + }, + { + "epoch": 0.76, + "learning_rate": 3.2766593160651827e-06, + "loss": 1.3462, + "step": 7259 + }, + { + "epoch": 0.76, + "learning_rate": 3.273950274190356e-06, + "loss": 1.3699, + "step": 7260 + }, + { + "epoch": 0.76, + "learning_rate": 3.2712421334333687e-06, + "loss": 1.2863, + "step": 7261 + }, + { + "epoch": 0.76, + "learning_rate": 3.268534894157046e-06, + "loss": 1.3791, + "step": 7262 + }, + { + "epoch": 0.76, + "learning_rate": 3.265828556724092e-06, + "loss": 1.3066, + "step": 7263 + }, + { + "epoch": 0.76, + "learning_rate": 3.2631231214970784e-06, + "loss": 1.319, + "step": 7264 + }, + { + "epoch": 0.76, + "learning_rate": 3.260418588838471e-06, + "loss": 1.2939, + "step": 7265 + }, + { + "epoch": 0.76, + "learning_rate": 3.2577149591106017e-06, + "loss": 1.2568, + "step": 7266 + }, + { + "epoch": 0.76, + "learning_rate": 3.2550122326756905e-06, + "loss": 1.3494, + "step": 7267 + }, + { + "epoch": 0.76, + "learning_rate": 3.252310409895837e-06, + "loss": 1.3001, + "step": 7268 + }, + { + "epoch": 0.76, + "learning_rate": 3.2496094911330087e-06, + "loss": 1.4039, + "step": 7269 + }, + { + "epoch": 0.76, + "learning_rate": 3.246909476749063e-06, + "loss": 1.2904, + "step": 7270 + }, + { + "epoch": 0.76, + "learning_rate": 3.2442103671057358e-06, + "loss": 1.2864, + "step": 7271 + }, + { + "epoch": 0.76, + "learning_rate": 3.241512162564632e-06, + "loss": 1.3195, + "step": 7272 + }, + { + "epoch": 0.76, + "learning_rate": 3.2388148634872473e-06, + "loss": 1.2776, + "step": 7273 + }, + { + "epoch": 0.76, + "learning_rate": 3.2361184702349446e-06, + "loss": 1.3391, + "step": 7274 + }, + { + "epoch": 0.76, + "learning_rate": 3.2334229831689745e-06, + "loss": 1.6897, + "step": 7275 + }, + { + "epoch": 0.76, + "learning_rate": 3.2307284026504673e-06, + "loss": 1.4191, + "step": 7276 + }, + { + "epoch": 0.76, + "learning_rate": 3.228034729040419e-06, + "loss": 1.2671, + "step": 7277 + }, + { + "epoch": 0.76, + "learning_rate": 3.2253419626997172e-06, + "loss": 1.3085, + "step": 7278 + }, + { + "epoch": 0.76, + "learning_rate": 3.2226501039891266e-06, + "loss": 1.4378, + "step": 7279 + }, + { + "epoch": 0.76, + "learning_rate": 3.2199591532692807e-06, + "loss": 1.3044, + "step": 7280 + }, + { + "epoch": 0.76, + "learning_rate": 3.2172691109007036e-06, + "loss": 1.2709, + "step": 7281 + }, + { + "epoch": 0.76, + "learning_rate": 3.214579977243787e-06, + "loss": 1.2394, + "step": 7282 + }, + { + "epoch": 0.76, + "learning_rate": 3.2118917526588055e-06, + "loss": 1.2945, + "step": 7283 + }, + { + "epoch": 0.76, + "learning_rate": 3.2092044375059197e-06, + "loss": 1.4074, + "step": 7284 + }, + { + "epoch": 0.76, + "learning_rate": 3.2065180321451504e-06, + "loss": 1.3769, + "step": 7285 + }, + { + "epoch": 0.76, + "learning_rate": 3.203832536936413e-06, + "loss": 1.2479, + "step": 7286 + }, + { + "epoch": 0.76, + "learning_rate": 3.2011479522394973e-06, + "loss": 1.2623, + "step": 7287 + }, + { + "epoch": 0.76, + "learning_rate": 3.1984642784140616e-06, + "loss": 1.3044, + "step": 7288 + }, + { + "epoch": 0.76, + "learning_rate": 3.1957815158196525e-06, + "loss": 1.321, + "step": 7289 + }, + { + "epoch": 0.76, + "learning_rate": 3.1930996648156953e-06, + "loss": 1.3307, + "step": 7290 + }, + { + "epoch": 0.76, + "learning_rate": 3.1904187257614814e-06, + "loss": 1.3135, + "step": 7291 + }, + { + "epoch": 0.76, + "learning_rate": 3.187738699016195e-06, + "loss": 1.2821, + "step": 7292 + }, + { + "epoch": 0.76, + "learning_rate": 3.1850595849388853e-06, + "loss": 1.3069, + "step": 7293 + }, + { + "epoch": 0.76, + "learning_rate": 3.1823813838884865e-06, + "loss": 1.2952, + "step": 7294 + }, + { + "epoch": 0.76, + "learning_rate": 3.179704096223812e-06, + "loss": 1.3313, + "step": 7295 + }, + { + "epoch": 0.77, + "learning_rate": 3.177027722303544e-06, + "loss": 1.3454, + "step": 7296 + }, + { + "epoch": 0.77, + "learning_rate": 3.1743522624862497e-06, + "loss": 1.2904, + "step": 7297 + }, + { + "epoch": 0.77, + "learning_rate": 3.1716777171303783e-06, + "loss": 1.3213, + "step": 7298 + }, + { + "epoch": 0.77, + "learning_rate": 3.1690040865942396e-06, + "loss": 1.3336, + "step": 7299 + }, + { + "epoch": 0.77, + "learning_rate": 3.1663313712360398e-06, + "loss": 1.3399, + "step": 7300 + }, + { + "epoch": 0.77, + "learning_rate": 3.1636595714138483e-06, + "loss": 1.2871, + "step": 7301 + }, + { + "epoch": 0.77, + "learning_rate": 3.16098868748562e-06, + "loss": 1.312, + "step": 7302 + }, + { + "epoch": 0.77, + "learning_rate": 3.158318719809188e-06, + "loss": 1.3325, + "step": 7303 + }, + { + "epoch": 0.77, + "learning_rate": 3.1556496687422534e-06, + "loss": 1.309, + "step": 7304 + }, + { + "epoch": 0.77, + "learning_rate": 3.152981534642403e-06, + "loss": 1.3186, + "step": 7305 + }, + { + "epoch": 0.77, + "learning_rate": 3.1503143178671016e-06, + "loss": 1.3235, + "step": 7306 + }, + { + "epoch": 0.77, + "learning_rate": 3.1476480187736812e-06, + "loss": 1.3557, + "step": 7307 + }, + { + "epoch": 0.77, + "learning_rate": 3.1449826377193613e-06, + "loss": 1.3206, + "step": 7308 + }, + { + "epoch": 0.77, + "learning_rate": 3.1423181750612375e-06, + "loss": 1.2901, + "step": 7309 + }, + { + "epoch": 0.77, + "learning_rate": 3.1396546311562713e-06, + "loss": 1.3232, + "step": 7310 + }, + { + "epoch": 0.77, + "learning_rate": 3.136992006361318e-06, + "loss": 1.3065, + "step": 7311 + }, + { + "epoch": 0.77, + "learning_rate": 3.1343303010330926e-06, + "loss": 1.273, + "step": 7312 + }, + { + "epoch": 0.77, + "learning_rate": 3.1316695155281997e-06, + "loss": 1.2773, + "step": 7313 + }, + { + "epoch": 0.77, + "learning_rate": 3.12900965020312e-06, + "loss": 1.2959, + "step": 7314 + }, + { + "epoch": 0.77, + "learning_rate": 3.1263507054141975e-06, + "loss": 1.2685, + "step": 7315 + }, + { + "epoch": 0.77, + "learning_rate": 3.1236926815176683e-06, + "loss": 1.3908, + "step": 7316 + }, + { + "epoch": 0.77, + "learning_rate": 3.121035578869643e-06, + "loss": 1.3022, + "step": 7317 + }, + { + "epoch": 0.77, + "learning_rate": 3.1183793978260966e-06, + "loss": 1.3144, + "step": 7318 + }, + { + "epoch": 0.77, + "learning_rate": 3.1157241387428972e-06, + "loss": 1.3142, + "step": 7319 + }, + { + "epoch": 0.77, + "learning_rate": 3.1130698019757743e-06, + "loss": 1.3277, + "step": 7320 + }, + { + "epoch": 0.77, + "learning_rate": 3.110416387880344e-06, + "loss": 1.2973, + "step": 7321 + }, + { + "epoch": 0.77, + "learning_rate": 3.1077638968120984e-06, + "loss": 1.2862, + "step": 7322 + }, + { + "epoch": 0.77, + "learning_rate": 3.1051123291263975e-06, + "loss": 1.5172, + "step": 7323 + }, + { + "epoch": 0.77, + "learning_rate": 3.102461685178486e-06, + "loss": 1.3757, + "step": 7324 + }, + { + "epoch": 0.77, + "learning_rate": 3.099811965323485e-06, + "loss": 1.3082, + "step": 7325 + }, + { + "epoch": 0.77, + "learning_rate": 3.097163169916383e-06, + "loss": 1.3674, + "step": 7326 + }, + { + "epoch": 0.77, + "learning_rate": 3.0945152993120574e-06, + "loss": 1.3168, + "step": 7327 + }, + { + "epoch": 0.77, + "learning_rate": 3.0918683538652474e-06, + "loss": 1.3122, + "step": 7328 + }, + { + "epoch": 0.77, + "learning_rate": 3.089222333930579e-06, + "loss": 1.3437, + "step": 7329 + }, + { + "epoch": 0.77, + "learning_rate": 3.0865772398625548e-06, + "loss": 1.371, + "step": 7330 + }, + { + "epoch": 0.77, + "learning_rate": 3.0839330720155426e-06, + "loss": 1.327, + "step": 7331 + }, + { + "epoch": 0.77, + "learning_rate": 3.0812898307437955e-06, + "loss": 1.3369, + "step": 7332 + }, + { + "epoch": 0.77, + "learning_rate": 3.078647516401444e-06, + "loss": 1.2148, + "step": 7333 + }, + { + "epoch": 0.77, + "learning_rate": 3.0760061293424846e-06, + "loss": 1.3074, + "step": 7334 + }, + { + "epoch": 0.77, + "learning_rate": 3.073365669920797e-06, + "loss": 1.3218, + "step": 7335 + }, + { + "epoch": 0.77, + "learning_rate": 3.070726138490139e-06, + "loss": 1.2974, + "step": 7336 + }, + { + "epoch": 0.77, + "learning_rate": 3.0680875354041327e-06, + "loss": 1.3037, + "step": 7337 + }, + { + "epoch": 0.77, + "learning_rate": 3.065449861016291e-06, + "loss": 1.5706, + "step": 7338 + }, + { + "epoch": 0.77, + "learning_rate": 3.0628131156799857e-06, + "loss": 1.3346, + "step": 7339 + }, + { + "epoch": 0.77, + "learning_rate": 3.0601772997484793e-06, + "loss": 1.6488, + "step": 7340 + }, + { + "epoch": 0.77, + "learning_rate": 3.0575424135749045e-06, + "loss": 1.2929, + "step": 7341 + }, + { + "epoch": 0.77, + "learning_rate": 3.0549084575122625e-06, + "loss": 1.3137, + "step": 7342 + }, + { + "epoch": 0.77, + "learning_rate": 3.0522754319134373e-06, + "loss": 1.3218, + "step": 7343 + }, + { + "epoch": 0.77, + "learning_rate": 3.0496433371311927e-06, + "loss": 1.2805, + "step": 7344 + }, + { + "epoch": 0.77, + "learning_rate": 3.0470121735181544e-06, + "loss": 1.2218, + "step": 7345 + }, + { + "epoch": 0.77, + "learning_rate": 3.0443819414268373e-06, + "loss": 1.381, + "step": 7346 + }, + { + "epoch": 0.77, + "learning_rate": 3.0417526412096164e-06, + "loss": 1.3571, + "step": 7347 + }, + { + "epoch": 0.77, + "learning_rate": 3.0391242732187565e-06, + "loss": 1.3295, + "step": 7348 + }, + { + "epoch": 0.77, + "learning_rate": 3.036496837806393e-06, + "loss": 1.3795, + "step": 7349 + }, + { + "epoch": 0.77, + "learning_rate": 3.033870335324528e-06, + "loss": 1.282, + "step": 7350 + }, + { + "epoch": 0.77, + "learning_rate": 3.03124476612505e-06, + "loss": 1.3428, + "step": 7351 + }, + { + "epoch": 0.77, + "learning_rate": 3.0286201305597194e-06, + "loss": 1.3321, + "step": 7352 + }, + { + "epoch": 0.77, + "learning_rate": 3.0259964289801646e-06, + "loss": 1.4135, + "step": 7353 + }, + { + "epoch": 0.77, + "learning_rate": 3.023373661737897e-06, + "loss": 1.3032, + "step": 7354 + }, + { + "epoch": 0.77, + "learning_rate": 3.0207518291843042e-06, + "loss": 1.2676, + "step": 7355 + }, + { + "epoch": 0.77, + "learning_rate": 3.0181309316706362e-06, + "loss": 1.2902, + "step": 7356 + }, + { + "epoch": 0.77, + "learning_rate": 3.0155109695480333e-06, + "loss": 1.3364, + "step": 7357 + }, + { + "epoch": 0.77, + "learning_rate": 3.0128919431674975e-06, + "loss": 1.3733, + "step": 7358 + }, + { + "epoch": 0.77, + "learning_rate": 3.0102738528799125e-06, + "loss": 1.3114, + "step": 7359 + }, + { + "epoch": 0.77, + "learning_rate": 3.007656699036039e-06, + "loss": 1.3176, + "step": 7360 + }, + { + "epoch": 0.77, + "learning_rate": 3.005040481986503e-06, + "loss": 1.301, + "step": 7361 + }, + { + "epoch": 0.77, + "learning_rate": 3.0024252020818124e-06, + "loss": 1.3281, + "step": 7362 + }, + { + "epoch": 0.77, + "learning_rate": 2.9998108596723508e-06, + "loss": 1.1587, + "step": 7363 + }, + { + "epoch": 0.77, + "eval_loss": 1.3964349031448364, + "eval_runtime": 77.4566, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 7363 + }, + { + "epoch": 0.77, + "learning_rate": 2.9971974551083673e-06, + "loss": 1.3628, + "step": 7364 + }, + { + "epoch": 0.77, + "learning_rate": 2.9945849887399958e-06, + "loss": 1.4178, + "step": 7365 + }, + { + "epoch": 0.77, + "learning_rate": 2.9919734609172356e-06, + "loss": 1.3428, + "step": 7366 + }, + { + "epoch": 0.77, + "learning_rate": 2.989362871989965e-06, + "loss": 1.2675, + "step": 7367 + }, + { + "epoch": 0.77, + "learning_rate": 2.986753222307941e-06, + "loss": 1.3353, + "step": 7368 + }, + { + "epoch": 0.77, + "learning_rate": 2.9841445122207826e-06, + "loss": 1.2842, + "step": 7369 + }, + { + "epoch": 0.77, + "learning_rate": 2.981536742077993e-06, + "loss": 1.2237, + "step": 7370 + }, + { + "epoch": 0.77, + "learning_rate": 2.9789299122289493e-06, + "loss": 1.2554, + "step": 7371 + }, + { + "epoch": 0.77, + "learning_rate": 2.976324023022893e-06, + "loss": 1.3277, + "step": 7372 + }, + { + "epoch": 0.77, + "learning_rate": 2.973719074808954e-06, + "loss": 1.3258, + "step": 7373 + }, + { + "epoch": 0.77, + "learning_rate": 2.971115067936122e-06, + "loss": 1.2757, + "step": 7374 + }, + { + "epoch": 0.77, + "learning_rate": 2.9685120027532687e-06, + "loss": 1.3267, + "step": 7375 + }, + { + "epoch": 0.77, + "learning_rate": 2.9659098796091423e-06, + "loss": 1.3451, + "step": 7376 + }, + { + "epoch": 0.77, + "learning_rate": 2.9633086988523507e-06, + "loss": 1.2742, + "step": 7377 + }, + { + "epoch": 0.77, + "learning_rate": 2.9607084608313972e-06, + "loss": 1.3589, + "step": 7378 + }, + { + "epoch": 0.77, + "learning_rate": 2.9581091658946415e-06, + "loss": 1.2839, + "step": 7379 + }, + { + "epoch": 0.77, + "learning_rate": 2.9555108143903187e-06, + "loss": 1.2883, + "step": 7380 + }, + { + "epoch": 0.77, + "learning_rate": 2.9529134066665453e-06, + "loss": 1.2781, + "step": 7381 + }, + { + "epoch": 0.77, + "learning_rate": 2.9503169430713084e-06, + "loss": 1.3638, + "step": 7382 + }, + { + "epoch": 0.77, + "learning_rate": 2.947721423952463e-06, + "loss": 1.3284, + "step": 7383 + }, + { + "epoch": 0.77, + "learning_rate": 2.945126849657748e-06, + "loss": 1.4043, + "step": 7384 + }, + { + "epoch": 0.77, + "learning_rate": 2.9425332205347624e-06, + "loss": 1.3173, + "step": 7385 + }, + { + "epoch": 0.77, + "learning_rate": 2.9399405369309884e-06, + "loss": 1.2099, + "step": 7386 + }, + { + "epoch": 0.77, + "learning_rate": 2.9373487991937845e-06, + "loss": 1.3062, + "step": 7387 + }, + { + "epoch": 0.77, + "learning_rate": 2.9347580076703695e-06, + "loss": 1.3075, + "step": 7388 + }, + { + "epoch": 0.77, + "learning_rate": 2.932168162707846e-06, + "loss": 1.3129, + "step": 7389 + }, + { + "epoch": 0.77, + "learning_rate": 2.9295792646531882e-06, + "loss": 1.4852, + "step": 7390 + }, + { + "epoch": 0.78, + "learning_rate": 2.926991313853239e-06, + "loss": 1.303, + "step": 7391 + }, + { + "epoch": 0.78, + "learning_rate": 2.9244043106547214e-06, + "loss": 1.2761, + "step": 7392 + }, + { + "epoch": 0.78, + "learning_rate": 2.9218182554042206e-06, + "loss": 1.2693, + "step": 7393 + }, + { + "epoch": 0.78, + "learning_rate": 2.9192331484482074e-06, + "loss": 1.2966, + "step": 7394 + }, + { + "epoch": 0.78, + "learning_rate": 2.9166489901330195e-06, + "loss": 1.3091, + "step": 7395 + }, + { + "epoch": 0.78, + "learning_rate": 2.91406578080486e-06, + "loss": 1.373, + "step": 7396 + }, + { + "epoch": 0.78, + "learning_rate": 2.9114835208098257e-06, + "loss": 1.2369, + "step": 7397 + }, + { + "epoch": 0.78, + "learning_rate": 2.908902210493866e-06, + "loss": 1.6399, + "step": 7398 + }, + { + "epoch": 0.78, + "learning_rate": 2.906321850202806e-06, + "loss": 1.3121, + "step": 7399 + }, + { + "epoch": 0.78, + "learning_rate": 2.903742440282352e-06, + "loss": 1.3401, + "step": 7400 + }, + { + "epoch": 0.78, + "learning_rate": 2.9011639810780833e-06, + "loss": 1.2974, + "step": 7401 + }, + { + "epoch": 0.78, + "learning_rate": 2.8985864729354383e-06, + "loss": 1.2825, + "step": 7402 + }, + { + "epoch": 0.78, + "learning_rate": 2.8960099161997434e-06, + "loss": 1.4901, + "step": 7403 + }, + { + "epoch": 0.78, + "learning_rate": 2.8934343112161867e-06, + "loss": 1.3203, + "step": 7404 + }, + { + "epoch": 0.78, + "learning_rate": 2.8908596583298343e-06, + "loss": 1.2859, + "step": 7405 + }, + { + "epoch": 0.78, + "learning_rate": 2.888285957885628e-06, + "loss": 1.334, + "step": 7406 + }, + { + "epoch": 0.78, + "learning_rate": 2.8857132102283703e-06, + "loss": 1.3358, + "step": 7407 + }, + { + "epoch": 0.78, + "learning_rate": 2.883141415702747e-06, + "loss": 1.2927, + "step": 7408 + }, + { + "epoch": 0.78, + "learning_rate": 2.8805705746533154e-06, + "loss": 1.3846, + "step": 7409 + }, + { + "epoch": 0.78, + "learning_rate": 2.8780006874244947e-06, + "loss": 1.2857, + "step": 7410 + }, + { + "epoch": 0.78, + "learning_rate": 2.8754317543605923e-06, + "loss": 1.3791, + "step": 7411 + }, + { + "epoch": 0.78, + "learning_rate": 2.872863775805772e-06, + "loss": 1.3286, + "step": 7412 + }, + { + "epoch": 0.78, + "learning_rate": 2.870296752104079e-06, + "loss": 1.244, + "step": 7413 + }, + { + "epoch": 0.78, + "learning_rate": 2.8677306835994335e-06, + "loss": 1.3673, + "step": 7414 + }, + { + "epoch": 0.78, + "learning_rate": 2.865165570635615e-06, + "loss": 1.3123, + "step": 7415 + }, + { + "epoch": 0.78, + "learning_rate": 2.862601413556286e-06, + "loss": 1.2867, + "step": 7416 + }, + { + "epoch": 0.78, + "learning_rate": 2.860038212704982e-06, + "loss": 1.3254, + "step": 7417 + }, + { + "epoch": 0.78, + "learning_rate": 2.8574759684250985e-06, + "loss": 1.2298, + "step": 7418 + }, + { + "epoch": 0.78, + "learning_rate": 2.854914681059914e-06, + "loss": 1.3054, + "step": 7419 + }, + { + "epoch": 0.78, + "learning_rate": 2.8523543509525785e-06, + "loss": 1.2984, + "step": 7420 + }, + { + "epoch": 0.78, + "learning_rate": 2.8497949784461043e-06, + "loss": 1.2848, + "step": 7421 + }, + { + "epoch": 0.78, + "learning_rate": 2.847236563883388e-06, + "loss": 1.4184, + "step": 7422 + }, + { + "epoch": 0.78, + "learning_rate": 2.84467910760718e-06, + "loss": 1.3967, + "step": 7423 + }, + { + "epoch": 0.78, + "learning_rate": 2.8421226099601284e-06, + "loss": 1.2847, + "step": 7424 + }, + { + "epoch": 0.78, + "learning_rate": 2.8395670712847322e-06, + "loss": 1.3681, + "step": 7425 + }, + { + "epoch": 0.78, + "learning_rate": 2.837012491923363e-06, + "loss": 1.3114, + "step": 7426 + }, + { + "epoch": 0.78, + "learning_rate": 2.834458872218274e-06, + "loss": 1.3264, + "step": 7427 + }, + { + "epoch": 0.78, + "learning_rate": 2.831906212511586e-06, + "loss": 1.3019, + "step": 7428 + }, + { + "epoch": 0.78, + "learning_rate": 2.829354513145284e-06, + "loss": 1.2619, + "step": 7429 + }, + { + "epoch": 0.78, + "learning_rate": 2.8268037744612362e-06, + "loss": 1.2825, + "step": 7430 + }, + { + "epoch": 0.78, + "learning_rate": 2.824253996801172e-06, + "loss": 1.2942, + "step": 7431 + }, + { + "epoch": 0.78, + "learning_rate": 2.8217051805066953e-06, + "loss": 1.3907, + "step": 7432 + }, + { + "epoch": 0.78, + "learning_rate": 2.8191573259192884e-06, + "loss": 1.2871, + "step": 7433 + }, + { + "epoch": 0.78, + "learning_rate": 2.81661043338029e-06, + "loss": 1.3924, + "step": 7434 + }, + { + "epoch": 0.78, + "learning_rate": 2.814064503230923e-06, + "loss": 1.3649, + "step": 7435 + }, + { + "epoch": 0.78, + "learning_rate": 2.8115195358122795e-06, + "loss": 1.3475, + "step": 7436 + }, + { + "epoch": 0.78, + "learning_rate": 2.808975531465312e-06, + "loss": 1.3736, + "step": 7437 + }, + { + "epoch": 0.78, + "learning_rate": 2.806432490530859e-06, + "loss": 1.2908, + "step": 7438 + }, + { + "epoch": 0.78, + "learning_rate": 2.803890413349618e-06, + "loss": 1.3991, + "step": 7439 + }, + { + "epoch": 0.78, + "learning_rate": 2.8013493002621617e-06, + "loss": 1.2928, + "step": 7440 + }, + { + "epoch": 0.78, + "learning_rate": 2.79880915160894e-06, + "loss": 1.3408, + "step": 7441 + }, + { + "epoch": 0.78, + "learning_rate": 2.7962699677302574e-06, + "loss": 1.3045, + "step": 7442 + }, + { + "epoch": 0.78, + "learning_rate": 2.793731748966311e-06, + "loss": 1.3179, + "step": 7443 + }, + { + "epoch": 0.78, + "learning_rate": 2.791194495657151e-06, + "loss": 1.2709, + "step": 7444 + }, + { + "epoch": 0.78, + "learning_rate": 2.7886582081427014e-06, + "loss": 1.3635, + "step": 7445 + }, + { + "epoch": 0.78, + "learning_rate": 2.786122886762762e-06, + "loss": 1.323, + "step": 7446 + }, + { + "epoch": 0.78, + "learning_rate": 2.7835885318570054e-06, + "loss": 1.2629, + "step": 7447 + }, + { + "epoch": 0.78, + "learning_rate": 2.7810551437649613e-06, + "loss": 1.4308, + "step": 7448 + }, + { + "epoch": 0.78, + "learning_rate": 2.778522722826048e-06, + "loss": 1.3546, + "step": 7449 + }, + { + "epoch": 0.78, + "learning_rate": 2.775991269379532e-06, + "loss": 1.4486, + "step": 7450 + }, + { + "epoch": 0.78, + "learning_rate": 2.773460783764579e-06, + "loss": 1.2845, + "step": 7451 + }, + { + "epoch": 0.78, + "learning_rate": 2.7709312663201993e-06, + "loss": 1.2393, + "step": 7452 + }, + { + "epoch": 0.78, + "learning_rate": 2.7684027173852836e-06, + "loss": 1.2939, + "step": 7453 + }, + { + "epoch": 0.78, + "learning_rate": 2.7658751372985926e-06, + "loss": 1.5802, + "step": 7454 + }, + { + "epoch": 0.78, + "learning_rate": 2.7633485263987627e-06, + "loss": 1.258, + "step": 7455 + }, + { + "epoch": 0.78, + "learning_rate": 2.760822885024286e-06, + "loss": 1.3223, + "step": 7456 + }, + { + "epoch": 0.78, + "learning_rate": 2.7582982135135418e-06, + "loss": 1.277, + "step": 7457 + }, + { + "epoch": 0.78, + "learning_rate": 2.755774512204764e-06, + "loss": 1.3047, + "step": 7458 + }, + { + "epoch": 0.78, + "learning_rate": 2.753251781436068e-06, + "loss": 1.3021, + "step": 7459 + }, + { + "epoch": 0.78, + "learning_rate": 2.750730021545437e-06, + "loss": 1.3321, + "step": 7460 + }, + { + "epoch": 0.78, + "learning_rate": 2.7482092328707154e-06, + "loss": 1.2453, + "step": 7461 + }, + { + "epoch": 0.78, + "learning_rate": 2.7456894157496293e-06, + "loss": 1.2628, + "step": 7462 + }, + { + "epoch": 0.78, + "learning_rate": 2.74317057051977e-06, + "loss": 1.4221, + "step": 7463 + }, + { + "epoch": 0.78, + "learning_rate": 2.740652697518593e-06, + "loss": 1.3034, + "step": 7464 + }, + { + "epoch": 0.78, + "learning_rate": 2.738135797083432e-06, + "loss": 1.2944, + "step": 7465 + }, + { + "epoch": 0.78, + "learning_rate": 2.7356198695514893e-06, + "loss": 1.3434, + "step": 7466 + }, + { + "epoch": 0.78, + "learning_rate": 2.733104915259829e-06, + "loss": 1.3127, + "step": 7467 + }, + { + "epoch": 0.78, + "learning_rate": 2.730590934545396e-06, + "loss": 1.2425, + "step": 7468 + }, + { + "epoch": 0.78, + "learning_rate": 2.7280779277449907e-06, + "loss": 1.4366, + "step": 7469 + }, + { + "epoch": 0.78, + "learning_rate": 2.7255658951953036e-06, + "loss": 1.3024, + "step": 7470 + }, + { + "epoch": 0.78, + "learning_rate": 2.7230548372328745e-06, + "loss": 1.2768, + "step": 7471 + }, + { + "epoch": 0.78, + "learning_rate": 2.720544754194121e-06, + "loss": 1.2453, + "step": 7472 + }, + { + "epoch": 0.78, + "learning_rate": 2.7180356464153303e-06, + "loss": 1.2796, + "step": 7473 + }, + { + "epoch": 0.78, + "learning_rate": 2.715527514232661e-06, + "loss": 1.3181, + "step": 7474 + }, + { + "epoch": 0.78, + "learning_rate": 2.7130203579821344e-06, + "loss": 1.4013, + "step": 7475 + }, + { + "epoch": 0.78, + "learning_rate": 2.710514177999649e-06, + "loss": 1.3365, + "step": 7476 + }, + { + "epoch": 0.78, + "learning_rate": 2.7080089746209614e-06, + "loss": 1.31, + "step": 7477 + }, + { + "epoch": 0.78, + "learning_rate": 2.7055047481817153e-06, + "loss": 1.258, + "step": 7478 + }, + { + "epoch": 0.78, + "learning_rate": 2.7030014990174068e-06, + "loss": 1.2199, + "step": 7479 + }, + { + "epoch": 0.78, + "learning_rate": 2.7004992274634046e-06, + "loss": 1.3007, + "step": 7480 + }, + { + "epoch": 0.78, + "learning_rate": 2.69799793385495e-06, + "loss": 1.2772, + "step": 7481 + }, + { + "epoch": 0.78, + "learning_rate": 2.6954976185271576e-06, + "loss": 1.4021, + "step": 7482 + }, + { + "epoch": 0.78, + "learning_rate": 2.692998281814998e-06, + "loss": 1.3183, + "step": 7483 + }, + { + "epoch": 0.78, + "learning_rate": 2.6904999240533246e-06, + "loss": 1.3412, + "step": 7484 + }, + { + "epoch": 0.78, + "learning_rate": 2.6880025455768465e-06, + "loss": 1.2552, + "step": 7485 + }, + { + "epoch": 0.79, + "learning_rate": 2.6855061467201517e-06, + "loss": 1.2525, + "step": 7486 + }, + { + "epoch": 0.79, + "learning_rate": 2.683010727817695e-06, + "loss": 1.269, + "step": 7487 + }, + { + "epoch": 0.79, + "learning_rate": 2.680516289203793e-06, + "loss": 1.5189, + "step": 7488 + }, + { + "epoch": 0.79, + "learning_rate": 2.6780228312126454e-06, + "loss": 1.2999, + "step": 7489 + }, + { + "epoch": 0.79, + "learning_rate": 2.675530354178306e-06, + "loss": 1.3322, + "step": 7490 + }, + { + "epoch": 0.79, + "learning_rate": 2.6730388584347e-06, + "loss": 1.3918, + "step": 7491 + }, + { + "epoch": 0.79, + "learning_rate": 2.670548344315628e-06, + "loss": 1.4438, + "step": 7492 + }, + { + "epoch": 0.79, + "learning_rate": 2.6680588121547546e-06, + "loss": 1.3393, + "step": 7493 + }, + { + "epoch": 0.79, + "learning_rate": 2.6655702622856105e-06, + "loss": 1.301, + "step": 7494 + }, + { + "epoch": 0.79, + "learning_rate": 2.6630826950416024e-06, + "loss": 1.2463, + "step": 7495 + }, + { + "epoch": 0.79, + "learning_rate": 2.660596110755991e-06, + "loss": 1.2641, + "step": 7496 + }, + { + "epoch": 0.79, + "learning_rate": 2.6581105097619264e-06, + "loss": 1.3824, + "step": 7497 + }, + { + "epoch": 0.79, + "learning_rate": 2.6556258923924104e-06, + "loss": 1.339, + "step": 7498 + }, + { + "epoch": 0.79, + "learning_rate": 2.6531422589803134e-06, + "loss": 1.2653, + "step": 7499 + }, + { + "epoch": 0.79, + "learning_rate": 2.6506596098583826e-06, + "loss": 1.2773, + "step": 7500 + }, + { + "epoch": 0.79, + "learning_rate": 2.648177945359233e-06, + "loss": 1.1829, + "step": 7501 + }, + { + "epoch": 0.79, + "learning_rate": 2.6456972658153358e-06, + "loss": 1.4014, + "step": 7502 + }, + { + "epoch": 0.79, + "learning_rate": 2.6432175715590446e-06, + "loss": 1.3648, + "step": 7503 + }, + { + "epoch": 0.79, + "learning_rate": 2.6407388629225706e-06, + "loss": 1.2731, + "step": 7504 + }, + { + "epoch": 0.79, + "learning_rate": 2.6382611402379988e-06, + "loss": 1.3076, + "step": 7505 + }, + { + "epoch": 0.79, + "learning_rate": 2.6357844038372824e-06, + "loss": 1.2054, + "step": 7506 + }, + { + "epoch": 0.79, + "learning_rate": 2.6333086540522366e-06, + "loss": 1.2579, + "step": 7507 + }, + { + "epoch": 0.79, + "learning_rate": 2.6308338912145493e-06, + "loss": 1.316, + "step": 7508 + }, + { + "epoch": 0.79, + "learning_rate": 2.6283601156557792e-06, + "loss": 1.2957, + "step": 7509 + }, + { + "epoch": 0.79, + "learning_rate": 2.625887327707343e-06, + "loss": 1.3017, + "step": 7510 + }, + { + "epoch": 0.79, + "learning_rate": 2.6234155277005334e-06, + "loss": 1.2591, + "step": 7511 + }, + { + "epoch": 0.79, + "learning_rate": 2.62094471596651e-06, + "loss": 1.3582, + "step": 7512 + }, + { + "epoch": 0.79, + "learning_rate": 2.6184748928362934e-06, + "loss": 1.3026, + "step": 7513 + }, + { + "epoch": 0.79, + "learning_rate": 2.616006058640782e-06, + "loss": 1.3222, + "step": 7514 + }, + { + "epoch": 0.79, + "learning_rate": 2.6135382137107268e-06, + "loss": 1.2785, + "step": 7515 + }, + { + "epoch": 0.79, + "learning_rate": 2.6110713583767687e-06, + "loss": 1.3227, + "step": 7516 + }, + { + "epoch": 0.79, + "learning_rate": 2.608605492969396e-06, + "loss": 1.2695, + "step": 7517 + }, + { + "epoch": 0.79, + "learning_rate": 2.6061406178189684e-06, + "loss": 1.2809, + "step": 7518 + }, + { + "epoch": 0.79, + "learning_rate": 2.6036767332557188e-06, + "loss": 1.2934, + "step": 7519 + }, + { + "epoch": 0.79, + "learning_rate": 2.6012138396097473e-06, + "loss": 1.2484, + "step": 7520 + }, + { + "epoch": 0.79, + "learning_rate": 2.5987519372110125e-06, + "loss": 1.3422, + "step": 7521 + }, + { + "epoch": 0.79, + "learning_rate": 2.596291026389354e-06, + "loss": 1.3008, + "step": 7522 + }, + { + "epoch": 0.79, + "learning_rate": 2.5938311074744582e-06, + "loss": 1.3698, + "step": 7523 + }, + { + "epoch": 0.79, + "learning_rate": 2.5913721807959045e-06, + "loss": 1.3034, + "step": 7524 + }, + { + "epoch": 0.79, + "learning_rate": 2.5889142466831208e-06, + "loss": 1.3011, + "step": 7525 + }, + { + "epoch": 0.79, + "learning_rate": 2.586457305465403e-06, + "loss": 1.3626, + "step": 7526 + }, + { + "epoch": 0.79, + "learning_rate": 2.5840013574719213e-06, + "loss": 1.3018, + "step": 7527 + }, + { + "epoch": 0.79, + "learning_rate": 2.581546403031713e-06, + "loss": 1.3316, + "step": 7528 + }, + { + "epoch": 0.79, + "learning_rate": 2.579092442473673e-06, + "loss": 1.2534, + "step": 7529 + }, + { + "epoch": 0.79, + "learning_rate": 2.5766394761265743e-06, + "loss": 1.2949, + "step": 7530 + }, + { + "epoch": 0.79, + "learning_rate": 2.574187504319046e-06, + "loss": 1.2962, + "step": 7531 + }, + { + "epoch": 0.79, + "learning_rate": 2.5717365273795914e-06, + "loss": 1.2926, + "step": 7532 + }, + { + "epoch": 0.79, + "learning_rate": 2.5692865456365824e-06, + "loss": 1.3136, + "step": 7533 + }, + { + "epoch": 0.79, + "learning_rate": 2.5668375594182447e-06, + "loss": 1.3065, + "step": 7534 + }, + { + "epoch": 0.79, + "learning_rate": 2.564389569052691e-06, + "loss": 1.3631, + "step": 7535 + }, + { + "epoch": 0.79, + "learning_rate": 2.5619425748678827e-06, + "loss": 1.3028, + "step": 7536 + }, + { + "epoch": 0.79, + "learning_rate": 2.5594965771916526e-06, + "loss": 1.3212, + "step": 7537 + }, + { + "epoch": 0.79, + "learning_rate": 2.557051576351702e-06, + "loss": 1.3154, + "step": 7538 + }, + { + "epoch": 0.79, + "learning_rate": 2.554607572675605e-06, + "loss": 1.284, + "step": 7539 + }, + { + "epoch": 0.79, + "learning_rate": 2.5521645664907856e-06, + "loss": 1.3833, + "step": 7540 + }, + { + "epoch": 0.79, + "learning_rate": 2.549722558124551e-06, + "loss": 1.3079, + "step": 7541 + }, + { + "epoch": 0.79, + "learning_rate": 2.54728154790406e-06, + "loss": 1.3104, + "step": 7542 + }, + { + "epoch": 0.79, + "learning_rate": 2.544841536156356e-06, + "loss": 1.2933, + "step": 7543 + }, + { + "epoch": 0.79, + "learning_rate": 2.5424025232083315e-06, + "loss": 1.4103, + "step": 7544 + }, + { + "epoch": 0.79, + "learning_rate": 2.53996450938675e-06, + "loss": 1.3602, + "step": 7545 + }, + { + "epoch": 0.79, + "learning_rate": 2.537527495018244e-06, + "loss": 1.381, + "step": 7546 + }, + { + "epoch": 0.79, + "learning_rate": 2.535091480429315e-06, + "loss": 1.4212, + "step": 7547 + }, + { + "epoch": 0.79, + "learning_rate": 2.5326564659463203e-06, + "loss": 1.3662, + "step": 7548 + }, + { + "epoch": 0.79, + "learning_rate": 2.5302224518954944e-06, + "loss": 1.2896, + "step": 7549 + }, + { + "epoch": 0.79, + "learning_rate": 2.5277894386029246e-06, + "loss": 1.3218, + "step": 7550 + }, + { + "epoch": 0.79, + "learning_rate": 2.5253574263945835e-06, + "loss": 1.337, + "step": 7551 + }, + { + "epoch": 0.79, + "learning_rate": 2.522926415596293e-06, + "loss": 1.3457, + "step": 7552 + }, + { + "epoch": 0.79, + "learning_rate": 2.5204964065337423e-06, + "loss": 1.3227, + "step": 7553 + }, + { + "epoch": 0.79, + "learning_rate": 2.5180673995324933e-06, + "loss": 1.2529, + "step": 7554 + }, + { + "epoch": 0.79, + "learning_rate": 2.5156393949179746e-06, + "loss": 1.3193, + "step": 7555 + }, + { + "epoch": 0.79, + "learning_rate": 2.5132123930154697e-06, + "loss": 1.2719, + "step": 7556 + }, + { + "epoch": 0.79, + "learning_rate": 2.5107863941501363e-06, + "loss": 1.3367, + "step": 7557 + }, + { + "epoch": 0.79, + "learning_rate": 2.508361398647e-06, + "loss": 1.2918, + "step": 7558 + }, + { + "epoch": 0.79, + "learning_rate": 2.505937406830942e-06, + "loss": 1.3458, + "step": 7559 + }, + { + "epoch": 0.79, + "learning_rate": 2.5035144190267215e-06, + "loss": 1.3975, + "step": 7560 + }, + { + "epoch": 0.79, + "learning_rate": 2.5010924355589463e-06, + "loss": 1.3717, + "step": 7561 + }, + { + "epoch": 0.79, + "learning_rate": 2.498671456752112e-06, + "loss": 1.316, + "step": 7562 + }, + { + "epoch": 0.79, + "eval_loss": 1.3956769704818726, + "eval_runtime": 77.5888, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 7562 + }, + { + "epoch": 0.79, + "learning_rate": 2.496251482930563e-06, + "loss": 1.2949, + "step": 7563 + }, + { + "epoch": 0.79, + "learning_rate": 2.4938325144185094e-06, + "loss": 1.6856, + "step": 7564 + }, + { + "epoch": 0.79, + "learning_rate": 2.4914145515400347e-06, + "loss": 1.4064, + "step": 7565 + }, + { + "epoch": 0.79, + "learning_rate": 2.4889975946190847e-06, + "loss": 1.3279, + "step": 7566 + }, + { + "epoch": 0.79, + "learning_rate": 2.4865816439794666e-06, + "loss": 1.2923, + "step": 7567 + }, + { + "epoch": 0.79, + "learning_rate": 2.48416669994486e-06, + "loss": 1.3237, + "step": 7568 + }, + { + "epoch": 0.79, + "learning_rate": 2.481752762838796e-06, + "loss": 1.3424, + "step": 7569 + }, + { + "epoch": 0.79, + "learning_rate": 2.479339832984693e-06, + "loss": 1.1656, + "step": 7570 + }, + { + "epoch": 0.79, + "learning_rate": 2.476927910705814e-06, + "loss": 1.1659, + "step": 7571 + }, + { + "epoch": 0.79, + "learning_rate": 2.4745169963252945e-06, + "loss": 1.3452, + "step": 7572 + }, + { + "epoch": 0.79, + "learning_rate": 2.472107090166136e-06, + "loss": 1.4011, + "step": 7573 + }, + { + "epoch": 0.79, + "learning_rate": 2.4696981925512076e-06, + "loss": 1.2312, + "step": 7574 + }, + { + "epoch": 0.79, + "learning_rate": 2.4672903038032335e-06, + "loss": 1.3257, + "step": 7575 + }, + { + "epoch": 0.79, + "learning_rate": 2.464883424244815e-06, + "loss": 1.2795, + "step": 7576 + }, + { + "epoch": 0.79, + "learning_rate": 2.4624775541984025e-06, + "loss": 1.3514, + "step": 7577 + }, + { + "epoch": 0.79, + "learning_rate": 2.4600726939863338e-06, + "loss": 1.3736, + "step": 7578 + }, + { + "epoch": 0.79, + "learning_rate": 2.4576688439307926e-06, + "loss": 1.3361, + "step": 7579 + }, + { + "epoch": 0.79, + "learning_rate": 2.4552660043538255e-06, + "loss": 1.3047, + "step": 7580 + }, + { + "epoch": 0.79, + "learning_rate": 2.452864175577364e-06, + "loss": 1.2987, + "step": 7581 + }, + { + "epoch": 0.8, + "learning_rate": 2.4504633579231863e-06, + "loss": 1.3218, + "step": 7582 + }, + { + "epoch": 0.8, + "learning_rate": 2.448063551712937e-06, + "loss": 1.3159, + "step": 7583 + }, + { + "epoch": 0.8, + "learning_rate": 2.44566475726813e-06, + "loss": 1.3032, + "step": 7584 + }, + { + "epoch": 0.8, + "learning_rate": 2.443266974910147e-06, + "loss": 1.2298, + "step": 7585 + }, + { + "epoch": 0.8, + "learning_rate": 2.4408702049602217e-06, + "loss": 1.288, + "step": 7586 + }, + { + "epoch": 0.8, + "learning_rate": 2.4384744477394663e-06, + "loss": 1.2733, + "step": 7587 + }, + { + "epoch": 0.8, + "learning_rate": 2.4360797035688424e-06, + "loss": 1.3576, + "step": 7588 + }, + { + "epoch": 0.8, + "learning_rate": 2.4336859727691953e-06, + "loss": 1.3029, + "step": 7589 + }, + { + "epoch": 0.8, + "learning_rate": 2.4312932556612178e-06, + "loss": 1.4056, + "step": 7590 + }, + { + "epoch": 0.8, + "learning_rate": 2.4289015525654693e-06, + "loss": 1.3129, + "step": 7591 + }, + { + "epoch": 0.8, + "learning_rate": 2.426510863802379e-06, + "loss": 1.2301, + "step": 7592 + }, + { + "epoch": 0.8, + "learning_rate": 2.4241211896922422e-06, + "loss": 1.282, + "step": 7593 + }, + { + "epoch": 0.8, + "learning_rate": 2.4217325305552073e-06, + "loss": 1.3173, + "step": 7594 + }, + { + "epoch": 0.8, + "learning_rate": 2.419344886711299e-06, + "loss": 1.3387, + "step": 7595 + }, + { + "epoch": 0.8, + "learning_rate": 2.416958258480391e-06, + "loss": 1.3313, + "step": 7596 + }, + { + "epoch": 0.8, + "learning_rate": 2.4145726461822428e-06, + "loss": 1.437, + "step": 7597 + }, + { + "epoch": 0.8, + "learning_rate": 2.412188050136458e-06, + "loss": 1.288, + "step": 7598 + }, + { + "epoch": 0.8, + "learning_rate": 2.40980447066251e-06, + "loss": 1.2815, + "step": 7599 + }, + { + "epoch": 0.8, + "learning_rate": 2.407421908079738e-06, + "loss": 1.3769, + "step": 7600 + }, + { + "epoch": 0.8, + "learning_rate": 2.405040362707349e-06, + "loss": 1.2726, + "step": 7601 + }, + { + "epoch": 0.8, + "learning_rate": 2.4026598348644027e-06, + "loss": 1.3741, + "step": 7602 + }, + { + "epoch": 0.8, + "learning_rate": 2.4002803248698303e-06, + "loss": 1.3046, + "step": 7603 + }, + { + "epoch": 0.8, + "learning_rate": 2.3979018330424284e-06, + "loss": 1.2566, + "step": 7604 + }, + { + "epoch": 0.8, + "learning_rate": 2.3955243597008504e-06, + "loss": 1.3237, + "step": 7605 + }, + { + "epoch": 0.8, + "learning_rate": 2.3931479051636184e-06, + "loss": 1.2446, + "step": 7606 + }, + { + "epoch": 0.8, + "learning_rate": 2.390772469749111e-06, + "loss": 1.2495, + "step": 7607 + }, + { + "epoch": 0.8, + "learning_rate": 2.3883980537755848e-06, + "loss": 1.326, + "step": 7608 + }, + { + "epoch": 0.8, + "learning_rate": 2.386024657561146e-06, + "loss": 1.2979, + "step": 7609 + }, + { + "epoch": 0.8, + "learning_rate": 2.3836522814237652e-06, + "loss": 1.2877, + "step": 7610 + }, + { + "epoch": 0.8, + "learning_rate": 2.381280925681283e-06, + "loss": 1.3327, + "step": 7611 + }, + { + "epoch": 0.8, + "learning_rate": 2.3789105906514034e-06, + "loss": 1.2641, + "step": 7612 + }, + { + "epoch": 0.8, + "learning_rate": 2.3765412766516837e-06, + "loss": 1.2904, + "step": 7613 + }, + { + "epoch": 0.8, + "learning_rate": 2.3741729839995573e-06, + "loss": 1.3153, + "step": 7614 + }, + { + "epoch": 0.8, + "learning_rate": 2.3718057130123063e-06, + "loss": 1.3168, + "step": 7615 + }, + { + "epoch": 0.8, + "learning_rate": 2.369439464007095e-06, + "loss": 1.2751, + "step": 7616 + }, + { + "epoch": 0.8, + "learning_rate": 2.3670742373009358e-06, + "loss": 1.3033, + "step": 7617 + }, + { + "epoch": 0.8, + "learning_rate": 2.364710033210703e-06, + "loss": 1.2788, + "step": 7618 + }, + { + "epoch": 0.8, + "learning_rate": 2.362346852053143e-06, + "loss": 1.3195, + "step": 7619 + }, + { + "epoch": 0.8, + "learning_rate": 2.3599846941448655e-06, + "loss": 1.2592, + "step": 7620 + }, + { + "epoch": 0.8, + "learning_rate": 2.357623559802332e-06, + "loss": 1.2495, + "step": 7621 + }, + { + "epoch": 0.8, + "learning_rate": 2.3552634493418803e-06, + "loss": 1.3111, + "step": 7622 + }, + { + "epoch": 0.8, + "learning_rate": 2.3529043630796954e-06, + "loss": 1.2559, + "step": 7623 + }, + { + "epoch": 0.8, + "learning_rate": 2.3505463013318454e-06, + "loss": 1.2642, + "step": 7624 + }, + { + "epoch": 0.8, + "learning_rate": 2.3481892644142455e-06, + "loss": 1.3277, + "step": 7625 + }, + { + "epoch": 0.8, + "learning_rate": 2.345833252642671e-06, + "loss": 1.3161, + "step": 7626 + }, + { + "epoch": 0.8, + "learning_rate": 2.3434782663327783e-06, + "loss": 1.2901, + "step": 7627 + }, + { + "epoch": 0.8, + "learning_rate": 2.341124305800071e-06, + "loss": 1.26, + "step": 7628 + }, + { + "epoch": 0.8, + "learning_rate": 2.338771371359915e-06, + "loss": 1.2772, + "step": 7629 + }, + { + "epoch": 0.8, + "learning_rate": 2.336419463327546e-06, + "loss": 1.2841, + "step": 7630 + }, + { + "epoch": 0.8, + "learning_rate": 2.334068582018062e-06, + "loss": 1.2036, + "step": 7631 + }, + { + "epoch": 0.8, + "learning_rate": 2.331718727746417e-06, + "loss": 1.2992, + "step": 7632 + }, + { + "epoch": 0.8, + "learning_rate": 2.329369900827434e-06, + "loss": 1.3145, + "step": 7633 + }, + { + "epoch": 0.8, + "learning_rate": 2.327022101575789e-06, + "loss": 1.3954, + "step": 7634 + }, + { + "epoch": 0.8, + "learning_rate": 2.3246753303060364e-06, + "loss": 1.2916, + "step": 7635 + }, + { + "epoch": 0.8, + "learning_rate": 2.322329587332579e-06, + "loss": 1.3013, + "step": 7636 + }, + { + "epoch": 0.8, + "learning_rate": 2.319984872969683e-06, + "loss": 1.2686, + "step": 7637 + }, + { + "epoch": 0.8, + "learning_rate": 2.3176411875314806e-06, + "loss": 1.3407, + "step": 7638 + }, + { + "epoch": 0.8, + "learning_rate": 2.315298531331972e-06, + "loss": 1.5181, + "step": 7639 + }, + { + "epoch": 0.8, + "learning_rate": 2.3129569046850054e-06, + "loss": 1.5231, + "step": 7640 + }, + { + "epoch": 0.8, + "learning_rate": 2.3106163079043033e-06, + "loss": 1.4524, + "step": 7641 + }, + { + "epoch": 0.8, + "learning_rate": 2.308276741303438e-06, + "loss": 1.2935, + "step": 7642 + }, + { + "epoch": 0.8, + "learning_rate": 2.3059382051958635e-06, + "loss": 1.4096, + "step": 7643 + }, + { + "epoch": 0.8, + "learning_rate": 2.303600699894876e-06, + "loss": 1.3598, + "step": 7644 + }, + { + "epoch": 0.8, + "learning_rate": 2.3012642257136397e-06, + "loss": 1.3578, + "step": 7645 + }, + { + "epoch": 0.8, + "learning_rate": 2.2989287829651853e-06, + "loss": 1.3147, + "step": 7646 + }, + { + "epoch": 0.8, + "learning_rate": 2.296594371962403e-06, + "loss": 1.3495, + "step": 7647 + }, + { + "epoch": 0.8, + "learning_rate": 2.2942609930180393e-06, + "loss": 1.4035, + "step": 7648 + }, + { + "epoch": 0.8, + "learning_rate": 2.291928646444711e-06, + "loss": 1.2757, + "step": 7649 + }, + { + "epoch": 0.8, + "learning_rate": 2.2895973325548914e-06, + "loss": 1.2496, + "step": 7650 + }, + { + "epoch": 0.8, + "learning_rate": 2.2872670516609196e-06, + "loss": 1.3372, + "step": 7651 + }, + { + "epoch": 0.8, + "learning_rate": 2.28493780407499e-06, + "loss": 1.276, + "step": 7652 + }, + { + "epoch": 0.8, + "learning_rate": 2.2826095901091574e-06, + "loss": 1.319, + "step": 7653 + }, + { + "epoch": 0.8, + "learning_rate": 2.280282410075354e-06, + "loss": 1.3473, + "step": 7654 + }, + { + "epoch": 0.8, + "learning_rate": 2.2779562642853546e-06, + "loss": 1.2947, + "step": 7655 + }, + { + "epoch": 0.8, + "learning_rate": 2.2756311530508026e-06, + "loss": 1.3485, + "step": 7656 + }, + { + "epoch": 0.8, + "learning_rate": 2.2733070766832042e-06, + "loss": 1.3187, + "step": 7657 + }, + { + "epoch": 0.8, + "learning_rate": 2.2709840354939296e-06, + "loss": 1.3979, + "step": 7658 + }, + { + "epoch": 0.8, + "learning_rate": 2.2686620297942007e-06, + "loss": 1.269, + "step": 7659 + }, + { + "epoch": 0.8, + "learning_rate": 2.266341059895113e-06, + "loss": 1.3572, + "step": 7660 + }, + { + "epoch": 0.8, + "learning_rate": 2.264021126107607e-06, + "loss": 1.2858, + "step": 7661 + }, + { + "epoch": 0.8, + "learning_rate": 2.2617022287425073e-06, + "loss": 1.3677, + "step": 7662 + }, + { + "epoch": 0.8, + "learning_rate": 2.259384368110479e-06, + "loss": 1.3111, + "step": 7663 + }, + { + "epoch": 0.8, + "learning_rate": 2.2570675445220535e-06, + "loss": 1.2969, + "step": 7664 + }, + { + "epoch": 0.8, + "learning_rate": 2.254751758287629e-06, + "loss": 1.2901, + "step": 7665 + }, + { + "epoch": 0.8, + "learning_rate": 2.252437009717464e-06, + "loss": 1.2834, + "step": 7666 + }, + { + "epoch": 0.8, + "learning_rate": 2.2501232991216705e-06, + "loss": 1.2505, + "step": 7667 + }, + { + "epoch": 0.8, + "learning_rate": 2.2478106268102295e-06, + "loss": 1.2763, + "step": 7668 + }, + { + "epoch": 0.8, + "learning_rate": 2.2454989930929737e-06, + "loss": 1.3427, + "step": 7669 + }, + { + "epoch": 0.8, + "learning_rate": 2.2431883982796132e-06, + "loss": 1.3397, + "step": 7670 + }, + { + "epoch": 0.8, + "learning_rate": 2.240878842679702e-06, + "loss": 1.2525, + "step": 7671 + }, + { + "epoch": 0.8, + "learning_rate": 2.238570326602657e-06, + "loss": 1.2085, + "step": 7672 + }, + { + "epoch": 0.8, + "learning_rate": 2.23626285035777e-06, + "loss": 1.2196, + "step": 7673 + }, + { + "epoch": 0.8, + "learning_rate": 2.2339564142541783e-06, + "loss": 1.2602, + "step": 7674 + }, + { + "epoch": 0.8, + "learning_rate": 2.2316510186008824e-06, + "loss": 1.4144, + "step": 7675 + }, + { + "epoch": 0.8, + "learning_rate": 2.2293466637067486e-06, + "loss": 1.3239, + "step": 7676 + }, + { + "epoch": 0.81, + "learning_rate": 2.227043349880501e-06, + "loss": 1.342, + "step": 7677 + }, + { + "epoch": 0.81, + "learning_rate": 2.2247410774307276e-06, + "loss": 1.3395, + "step": 7678 + }, + { + "epoch": 0.81, + "learning_rate": 2.2224398466658712e-06, + "loss": 1.3948, + "step": 7679 + }, + { + "epoch": 0.81, + "learning_rate": 2.2201396578942325e-06, + "loss": 1.2983, + "step": 7680 + }, + { + "epoch": 0.81, + "learning_rate": 2.2178405114239877e-06, + "loss": 1.3779, + "step": 7681 + }, + { + "epoch": 0.81, + "learning_rate": 2.2155424075631583e-06, + "loss": 1.2826, + "step": 7682 + }, + { + "epoch": 0.81, + "learning_rate": 2.213245346619628e-06, + "loss": 1.3939, + "step": 7683 + }, + { + "epoch": 0.81, + "learning_rate": 2.2109493289011474e-06, + "loss": 1.298, + "step": 7684 + }, + { + "epoch": 0.81, + "learning_rate": 2.208654354715326e-06, + "loss": 1.2947, + "step": 7685 + }, + { + "epoch": 0.81, + "learning_rate": 2.2063604243696267e-06, + "loss": 1.3532, + "step": 7686 + }, + { + "epoch": 0.81, + "learning_rate": 2.204067538171382e-06, + "loss": 1.2713, + "step": 7687 + }, + { + "epoch": 0.81, + "learning_rate": 2.2017756964277713e-06, + "loss": 1.3025, + "step": 7688 + }, + { + "epoch": 0.81, + "learning_rate": 2.199484899445854e-06, + "loss": 1.2806, + "step": 7689 + }, + { + "epoch": 0.81, + "learning_rate": 2.1971951475325328e-06, + "loss": 1.3113, + "step": 7690 + }, + { + "epoch": 0.81, + "learning_rate": 2.194906440994572e-06, + "loss": 1.4729, + "step": 7691 + }, + { + "epoch": 0.81, + "learning_rate": 2.1926187801386033e-06, + "loss": 1.29, + "step": 7692 + }, + { + "epoch": 0.81, + "learning_rate": 2.1903321652711163e-06, + "loss": 1.3092, + "step": 7693 + }, + { + "epoch": 0.81, + "learning_rate": 2.188046596698454e-06, + "loss": 1.3286, + "step": 7694 + }, + { + "epoch": 0.81, + "learning_rate": 2.185762074726826e-06, + "loss": 1.3734, + "step": 7695 + }, + { + "epoch": 0.81, + "learning_rate": 2.1834785996622988e-06, + "loss": 1.3218, + "step": 7696 + }, + { + "epoch": 0.81, + "learning_rate": 2.1811961718108034e-06, + "loss": 1.3319, + "step": 7697 + }, + { + "epoch": 0.81, + "learning_rate": 2.178914791478124e-06, + "loss": 1.2732, + "step": 7698 + }, + { + "epoch": 0.81, + "learning_rate": 2.1766344589698996e-06, + "loss": 1.4451, + "step": 7699 + }, + { + "epoch": 0.81, + "learning_rate": 2.1743551745916492e-06, + "loss": 1.338, + "step": 7700 + }, + { + "epoch": 0.81, + "learning_rate": 2.172076938648732e-06, + "loss": 1.3602, + "step": 7701 + }, + { + "epoch": 0.81, + "learning_rate": 2.16979975144637e-06, + "loss": 1.2782, + "step": 7702 + }, + { + "epoch": 0.81, + "learning_rate": 2.1675236132896505e-06, + "loss": 1.2661, + "step": 7703 + }, + { + "epoch": 0.81, + "learning_rate": 2.165248524483521e-06, + "loss": 1.3031, + "step": 7704 + }, + { + "epoch": 0.81, + "learning_rate": 2.1629744853327793e-06, + "loss": 1.3754, + "step": 7705 + }, + { + "epoch": 0.81, + "learning_rate": 2.1607014961420926e-06, + "loss": 1.4255, + "step": 7706 + }, + { + "epoch": 0.81, + "learning_rate": 2.1584295572159764e-06, + "loss": 1.3955, + "step": 7707 + }, + { + "epoch": 0.81, + "learning_rate": 2.156158668858822e-06, + "loss": 1.3691, + "step": 7708 + }, + { + "epoch": 0.81, + "learning_rate": 2.153888831374865e-06, + "loss": 1.3986, + "step": 7709 + }, + { + "epoch": 0.81, + "learning_rate": 2.1516200450682036e-06, + "loss": 1.3231, + "step": 7710 + }, + { + "epoch": 0.81, + "learning_rate": 2.149352310242797e-06, + "loss": 1.2892, + "step": 7711 + }, + { + "epoch": 0.81, + "learning_rate": 2.1470856272024686e-06, + "loss": 1.289, + "step": 7712 + }, + { + "epoch": 0.81, + "learning_rate": 2.1448199962508898e-06, + "loss": 1.2804, + "step": 7713 + }, + { + "epoch": 0.81, + "learning_rate": 2.1425554176916007e-06, + "loss": 1.2599, + "step": 7714 + }, + { + "epoch": 0.81, + "learning_rate": 2.1402918918279904e-06, + "loss": 1.3082, + "step": 7715 + }, + { + "epoch": 0.81, + "learning_rate": 2.1380294189633233e-06, + "loss": 1.306, + "step": 7716 + }, + { + "epoch": 0.81, + "learning_rate": 2.1357679994007076e-06, + "loss": 1.2681, + "step": 7717 + }, + { + "epoch": 0.81, + "learning_rate": 2.1335076334431092e-06, + "loss": 1.2842, + "step": 7718 + }, + { + "epoch": 0.81, + "learning_rate": 2.13124832139337e-06, + "loss": 1.3153, + "step": 7719 + }, + { + "epoch": 0.81, + "learning_rate": 2.128990063554176e-06, + "loss": 1.3312, + "step": 7720 + }, + { + "epoch": 0.81, + "learning_rate": 2.12673286022807e-06, + "loss": 1.2851, + "step": 7721 + }, + { + "epoch": 0.81, + "learning_rate": 2.124476711717465e-06, + "loss": 1.3398, + "step": 7722 + }, + { + "epoch": 0.81, + "learning_rate": 2.1222216183246246e-06, + "loss": 1.2543, + "step": 7723 + }, + { + "epoch": 0.81, + "learning_rate": 2.1199675803516785e-06, + "loss": 1.3686, + "step": 7724 + }, + { + "epoch": 0.81, + "learning_rate": 2.117714598100604e-06, + "loss": 1.3746, + "step": 7725 + }, + { + "epoch": 0.81, + "learning_rate": 2.1154626718732407e-06, + "loss": 1.2664, + "step": 7726 + }, + { + "epoch": 0.81, + "learning_rate": 2.1132118019712976e-06, + "loss": 1.3075, + "step": 7727 + }, + { + "epoch": 0.81, + "learning_rate": 2.1109619886963284e-06, + "loss": 1.739, + "step": 7728 + }, + { + "epoch": 0.81, + "learning_rate": 2.1087132323497483e-06, + "loss": 1.335, + "step": 7729 + }, + { + "epoch": 0.81, + "learning_rate": 2.1064655332328344e-06, + "loss": 1.3371, + "step": 7730 + }, + { + "epoch": 0.81, + "learning_rate": 2.104218891646724e-06, + "loss": 1.3837, + "step": 7731 + }, + { + "epoch": 0.81, + "learning_rate": 2.1019733078924045e-06, + "loss": 1.3436, + "step": 7732 + }, + { + "epoch": 0.81, + "learning_rate": 2.0997287822707304e-06, + "loss": 1.2995, + "step": 7733 + }, + { + "epoch": 0.81, + "learning_rate": 2.0974853150824036e-06, + "loss": 1.2914, + "step": 7734 + }, + { + "epoch": 0.81, + "learning_rate": 2.095242906628001e-06, + "loss": 1.3773, + "step": 7735 + }, + { + "epoch": 0.81, + "learning_rate": 2.0930015572079434e-06, + "loss": 1.3097, + "step": 7736 + }, + { + "epoch": 0.81, + "learning_rate": 2.0907612671225108e-06, + "loss": 1.3261, + "step": 7737 + }, + { + "epoch": 0.81, + "learning_rate": 2.088522036671846e-06, + "loss": 1.2578, + "step": 7738 + }, + { + "epoch": 0.81, + "learning_rate": 2.0862838661559535e-06, + "loss": 1.2898, + "step": 7739 + }, + { + "epoch": 0.81, + "learning_rate": 2.0840467558746837e-06, + "loss": 1.341, + "step": 7740 + }, + { + "epoch": 0.81, + "learning_rate": 2.0818107061277535e-06, + "loss": 1.3332, + "step": 7741 + }, + { + "epoch": 0.81, + "learning_rate": 2.0795757172147392e-06, + "loss": 1.2808, + "step": 7742 + }, + { + "epoch": 0.81, + "learning_rate": 2.077341789435071e-06, + "loss": 1.2795, + "step": 7743 + }, + { + "epoch": 0.81, + "learning_rate": 2.075108923088038e-06, + "loss": 1.3621, + "step": 7744 + }, + { + "epoch": 0.81, + "learning_rate": 2.0728771184727802e-06, + "loss": 1.3179, + "step": 7745 + }, + { + "epoch": 0.81, + "learning_rate": 2.0706463758883134e-06, + "loss": 1.2924, + "step": 7746 + }, + { + "epoch": 0.81, + "learning_rate": 2.0684166956334926e-06, + "loss": 1.3576, + "step": 7747 + }, + { + "epoch": 0.81, + "learning_rate": 2.066188078007039e-06, + "loss": 1.2692, + "step": 7748 + }, + { + "epoch": 0.81, + "learning_rate": 2.0639605233075277e-06, + "loss": 1.2994, + "step": 7749 + }, + { + "epoch": 0.81, + "learning_rate": 2.061734031833398e-06, + "loss": 1.278, + "step": 7750 + }, + { + "epoch": 0.81, + "learning_rate": 2.059508603882943e-06, + "loss": 1.2703, + "step": 7751 + }, + { + "epoch": 0.81, + "learning_rate": 2.0572842397543115e-06, + "loss": 1.2864, + "step": 7752 + }, + { + "epoch": 0.81, + "learning_rate": 2.0550609397455037e-06, + "loss": 1.3387, + "step": 7753 + }, + { + "epoch": 0.81, + "learning_rate": 2.0528387041543974e-06, + "loss": 1.5834, + "step": 7754 + }, + { + "epoch": 0.81, + "learning_rate": 2.0506175332787093e-06, + "loss": 1.2907, + "step": 7755 + }, + { + "epoch": 0.81, + "learning_rate": 2.048397427416016e-06, + "loss": 1.3015, + "step": 7756 + }, + { + "epoch": 0.81, + "learning_rate": 2.0461783868637573e-06, + "loss": 1.2329, + "step": 7757 + }, + { + "epoch": 0.81, + "learning_rate": 2.0439604119192314e-06, + "loss": 1.3166, + "step": 7758 + }, + { + "epoch": 0.81, + "learning_rate": 2.041743502879583e-06, + "loss": 1.2476, + "step": 7759 + }, + { + "epoch": 0.81, + "learning_rate": 2.039527660041828e-06, + "loss": 1.2766, + "step": 7760 + }, + { + "epoch": 0.81, + "learning_rate": 2.0373128837028233e-06, + "loss": 1.2738, + "step": 7761 + }, + { + "epoch": 0.81, + "eval_loss": 1.3951469659805298, + "eval_runtime": 77.4687, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 7761 + }, + { + "epoch": 0.81, + "learning_rate": 2.035099174159302e-06, + "loss": 1.3806, + "step": 7762 + }, + { + "epoch": 0.81, + "learning_rate": 2.0328865317078405e-06, + "loss": 1.2625, + "step": 7763 + }, + { + "epoch": 0.81, + "learning_rate": 2.0306749566448704e-06, + "loss": 1.2709, + "step": 7764 + }, + { + "epoch": 0.81, + "learning_rate": 2.028464449266696e-06, + "loss": 1.3029, + "step": 7765 + }, + { + "epoch": 0.81, + "learning_rate": 2.0262550098694634e-06, + "loss": 1.2867, + "step": 7766 + }, + { + "epoch": 0.81, + "learning_rate": 2.0240466387491774e-06, + "loss": 1.2818, + "step": 7767 + }, + { + "epoch": 0.81, + "learning_rate": 2.0218393362017076e-06, + "loss": 1.2627, + "step": 7768 + }, + { + "epoch": 0.81, + "learning_rate": 2.019633102522773e-06, + "loss": 1.2337, + "step": 7769 + }, + { + "epoch": 0.81, + "learning_rate": 2.0174279380079577e-06, + "loss": 1.4194, + "step": 7770 + }, + { + "epoch": 0.81, + "learning_rate": 2.0152238429526928e-06, + "loss": 1.487, + "step": 7771 + }, + { + "epoch": 0.82, + "learning_rate": 2.013020817652266e-06, + "loss": 1.2802, + "step": 7772 + }, + { + "epoch": 0.82, + "learning_rate": 2.0108188624018353e-06, + "loss": 1.2602, + "step": 7773 + }, + { + "epoch": 0.82, + "learning_rate": 2.008617977496402e-06, + "loss": 1.2986, + "step": 7774 + }, + { + "epoch": 0.82, + "learning_rate": 2.0064181632308244e-06, + "loss": 1.3053, + "step": 7775 + }, + { + "epoch": 0.82, + "learning_rate": 2.0042194198998256e-06, + "loss": 1.3052, + "step": 7776 + }, + { + "epoch": 0.82, + "learning_rate": 2.00202174779798e-06, + "loss": 1.247, + "step": 7777 + }, + { + "epoch": 0.82, + "learning_rate": 1.9998251472197192e-06, + "loss": 1.2762, + "step": 7778 + }, + { + "epoch": 0.82, + "learning_rate": 1.9976296184593335e-06, + "loss": 1.3518, + "step": 7779 + }, + { + "epoch": 0.82, + "learning_rate": 1.995435161810958e-06, + "loss": 1.4015, + "step": 7780 + }, + { + "epoch": 0.82, + "learning_rate": 1.9932417775686052e-06, + "loss": 1.3363, + "step": 7781 + }, + { + "epoch": 0.82, + "learning_rate": 1.991049466026128e-06, + "loss": 1.3039, + "step": 7782 + }, + { + "epoch": 0.82, + "learning_rate": 1.988858227477234e-06, + "loss": 1.3183, + "step": 7783 + }, + { + "epoch": 0.82, + "learning_rate": 1.986668062215502e-06, + "loss": 1.2852, + "step": 7784 + }, + { + "epoch": 0.82, + "learning_rate": 1.984478970534355e-06, + "loss": 1.2791, + "step": 7785 + }, + { + "epoch": 0.82, + "learning_rate": 1.9822909527270696e-06, + "loss": 1.3869, + "step": 7786 + }, + { + "epoch": 0.82, + "learning_rate": 1.9801040090867895e-06, + "loss": 1.3475, + "step": 7787 + }, + { + "epoch": 0.82, + "learning_rate": 1.9779181399065074e-06, + "loss": 1.2977, + "step": 7788 + }, + { + "epoch": 0.82, + "learning_rate": 1.975733345479076e-06, + "loss": 1.2244, + "step": 7789 + }, + { + "epoch": 0.82, + "learning_rate": 1.9735496260971996e-06, + "loss": 1.3136, + "step": 7790 + }, + { + "epoch": 0.82, + "learning_rate": 1.9713669820534352e-06, + "loss": 1.3647, + "step": 7791 + }, + { + "epoch": 0.82, + "learning_rate": 1.969185413640212e-06, + "loss": 1.3136, + "step": 7792 + }, + { + "epoch": 0.82, + "learning_rate": 1.9670049211497977e-06, + "loss": 1.3488, + "step": 7793 + }, + { + "epoch": 0.82, + "learning_rate": 1.9648255048743205e-06, + "loss": 1.3578, + "step": 7794 + }, + { + "epoch": 0.82, + "learning_rate": 1.9626471651057677e-06, + "loss": 1.325, + "step": 7795 + }, + { + "epoch": 0.82, + "learning_rate": 1.960469902135983e-06, + "loss": 1.3408, + "step": 7796 + }, + { + "epoch": 0.82, + "learning_rate": 1.958293716256664e-06, + "loss": 1.3439, + "step": 7797 + }, + { + "epoch": 0.82, + "learning_rate": 1.9561186077593617e-06, + "loss": 1.2767, + "step": 7798 + }, + { + "epoch": 0.82, + "learning_rate": 1.9539445769354814e-06, + "loss": 1.3756, + "step": 7799 + }, + { + "epoch": 0.82, + "learning_rate": 1.9517716240762953e-06, + "loss": 1.313, + "step": 7800 + }, + { + "epoch": 0.82, + "learning_rate": 1.949599749472919e-06, + "loss": 1.3103, + "step": 7801 + }, + { + "epoch": 0.82, + "learning_rate": 1.947428953416326e-06, + "loss": 1.3255, + "step": 7802 + }, + { + "epoch": 0.82, + "learning_rate": 1.945259236197348e-06, + "loss": 1.2959, + "step": 7803 + }, + { + "epoch": 0.82, + "learning_rate": 1.943090598106673e-06, + "loss": 1.2345, + "step": 7804 + }, + { + "epoch": 0.82, + "learning_rate": 1.9409230394348457e-06, + "loss": 1.2664, + "step": 7805 + }, + { + "epoch": 0.82, + "learning_rate": 1.938756560472256e-06, + "loss": 1.5172, + "step": 7806 + }, + { + "epoch": 0.82, + "learning_rate": 1.9365911615091615e-06, + "loss": 1.2878, + "step": 7807 + }, + { + "epoch": 0.82, + "learning_rate": 1.9344268428356707e-06, + "loss": 1.3419, + "step": 7808 + }, + { + "epoch": 0.82, + "learning_rate": 1.9322636047417444e-06, + "loss": 1.3464, + "step": 7809 + }, + { + "epoch": 0.82, + "learning_rate": 1.9301014475171964e-06, + "loss": 1.2695, + "step": 7810 + }, + { + "epoch": 0.82, + "learning_rate": 1.9279403714517098e-06, + "loss": 1.3551, + "step": 7811 + }, + { + "epoch": 0.82, + "learning_rate": 1.9257803768348092e-06, + "loss": 1.4498, + "step": 7812 + }, + { + "epoch": 0.82, + "learning_rate": 1.923621463955876e-06, + "loss": 1.4617, + "step": 7813 + }, + { + "epoch": 0.82, + "learning_rate": 1.9214636331041493e-06, + "loss": 1.6204, + "step": 7814 + }, + { + "epoch": 0.82, + "learning_rate": 1.9193068845687246e-06, + "loss": 1.3202, + "step": 7815 + }, + { + "epoch": 0.82, + "learning_rate": 1.9171512186385543e-06, + "loss": 1.293, + "step": 7816 + }, + { + "epoch": 0.82, + "learning_rate": 1.9149966356024387e-06, + "loss": 1.2511, + "step": 7817 + }, + { + "epoch": 0.82, + "learning_rate": 1.9128431357490296e-06, + "loss": 1.3643, + "step": 7818 + }, + { + "epoch": 0.82, + "learning_rate": 1.9106907193668543e-06, + "loss": 1.4159, + "step": 7819 + }, + { + "epoch": 0.82, + "learning_rate": 1.908539386744274e-06, + "loss": 1.2611, + "step": 7820 + }, + { + "epoch": 0.82, + "learning_rate": 1.9063891381695098e-06, + "loss": 1.3667, + "step": 7821 + }, + { + "epoch": 0.82, + "learning_rate": 1.9042399739306427e-06, + "loss": 1.3456, + "step": 7822 + }, + { + "epoch": 0.82, + "learning_rate": 1.9020918943156053e-06, + "loss": 1.4083, + "step": 7823 + }, + { + "epoch": 0.82, + "learning_rate": 1.8999448996121883e-06, + "loss": 1.3758, + "step": 7824 + }, + { + "epoch": 0.82, + "learning_rate": 1.8977989901080295e-06, + "loss": 1.2757, + "step": 7825 + }, + { + "epoch": 0.82, + "learning_rate": 1.8956541660906214e-06, + "loss": 1.3796, + "step": 7826 + }, + { + "epoch": 0.82, + "learning_rate": 1.893510427847327e-06, + "loss": 1.238, + "step": 7827 + }, + { + "epoch": 0.82, + "learning_rate": 1.8913677756653447e-06, + "loss": 1.3018, + "step": 7828 + }, + { + "epoch": 0.82, + "learning_rate": 1.8892262098317315e-06, + "loss": 1.2712, + "step": 7829 + }, + { + "epoch": 0.82, + "learning_rate": 1.8870857306334113e-06, + "loss": 1.3805, + "step": 7830 + }, + { + "epoch": 0.82, + "learning_rate": 1.8849463383571486e-06, + "loss": 1.3664, + "step": 7831 + }, + { + "epoch": 0.82, + "learning_rate": 1.8828080332895648e-06, + "loss": 1.3709, + "step": 7832 + }, + { + "epoch": 0.82, + "learning_rate": 1.8806708157171393e-06, + "loss": 1.3401, + "step": 7833 + }, + { + "epoch": 0.82, + "learning_rate": 1.8785346859262056e-06, + "loss": 1.3143, + "step": 7834 + }, + { + "epoch": 0.82, + "learning_rate": 1.876399644202952e-06, + "loss": 1.3432, + "step": 7835 + }, + { + "epoch": 0.82, + "learning_rate": 1.8742656908334178e-06, + "loss": 1.2945, + "step": 7836 + }, + { + "epoch": 0.82, + "learning_rate": 1.872132826103491e-06, + "loss": 1.402, + "step": 7837 + }, + { + "epoch": 0.82, + "learning_rate": 1.8700010502989318e-06, + "loss": 1.3004, + "step": 7838 + }, + { + "epoch": 0.82, + "learning_rate": 1.8678703637053386e-06, + "loss": 1.2766, + "step": 7839 + }, + { + "epoch": 0.82, + "learning_rate": 1.8657407666081661e-06, + "loss": 1.3629, + "step": 7840 + }, + { + "epoch": 0.82, + "learning_rate": 1.8636122592927275e-06, + "loss": 1.2527, + "step": 7841 + }, + { + "epoch": 0.82, + "learning_rate": 1.8614848420441888e-06, + "loss": 1.2711, + "step": 7842 + }, + { + "epoch": 0.82, + "learning_rate": 1.8593585151475713e-06, + "loss": 1.3419, + "step": 7843 + }, + { + "epoch": 0.82, + "learning_rate": 1.8572332788877456e-06, + "loss": 1.2953, + "step": 7844 + }, + { + "epoch": 0.82, + "learning_rate": 1.855109133549433e-06, + "loss": 1.2415, + "step": 7845 + }, + { + "epoch": 0.82, + "learning_rate": 1.8529860794172271e-06, + "loss": 1.2367, + "step": 7846 + }, + { + "epoch": 0.82, + "learning_rate": 1.8508641167755548e-06, + "loss": 1.3584, + "step": 7847 + }, + { + "epoch": 0.82, + "learning_rate": 1.848743245908703e-06, + "loss": 1.4259, + "step": 7848 + }, + { + "epoch": 0.82, + "learning_rate": 1.8466234671008165e-06, + "loss": 1.2903, + "step": 7849 + }, + { + "epoch": 0.82, + "learning_rate": 1.8445047806358918e-06, + "loss": 1.3204, + "step": 7850 + }, + { + "epoch": 0.82, + "learning_rate": 1.8423871867977806e-06, + "loss": 1.3938, + "step": 7851 + }, + { + "epoch": 0.82, + "learning_rate": 1.840270685870179e-06, + "loss": 1.2973, + "step": 7852 + }, + { + "epoch": 0.82, + "learning_rate": 1.8381552781366497e-06, + "loss": 1.3506, + "step": 7853 + }, + { + "epoch": 0.82, + "learning_rate": 1.8360409638806031e-06, + "loss": 1.3117, + "step": 7854 + }, + { + "epoch": 0.82, + "learning_rate": 1.833927743385302e-06, + "loss": 1.3072, + "step": 7855 + }, + { + "epoch": 0.82, + "learning_rate": 1.8318156169338562e-06, + "loss": 1.2965, + "step": 7856 + }, + { + "epoch": 0.82, + "learning_rate": 1.82970458480925e-06, + "loss": 1.3161, + "step": 7857 + }, + { + "epoch": 0.82, + "learning_rate": 1.8275946472942995e-06, + "loss": 1.3056, + "step": 7858 + }, + { + "epoch": 0.82, + "learning_rate": 1.8254858046716805e-06, + "loss": 1.249, + "step": 7859 + }, + { + "epoch": 0.82, + "learning_rate": 1.8233780572239268e-06, + "loss": 1.2689, + "step": 7860 + }, + { + "epoch": 0.82, + "learning_rate": 1.8212714052334213e-06, + "loss": 1.2919, + "step": 7861 + }, + { + "epoch": 0.82, + "learning_rate": 1.819165848982405e-06, + "loss": 1.3337, + "step": 7862 + }, + { + "epoch": 0.82, + "learning_rate": 1.8170613887529643e-06, + "loss": 1.2798, + "step": 7863 + }, + { + "epoch": 0.82, + "learning_rate": 1.8149580248270393e-06, + "loss": 1.3296, + "step": 7864 + }, + { + "epoch": 0.82, + "learning_rate": 1.812855757486437e-06, + "loss": 1.4615, + "step": 7865 + }, + { + "epoch": 0.82, + "learning_rate": 1.8107545870128008e-06, + "loss": 1.2883, + "step": 7866 + }, + { + "epoch": 0.82, + "learning_rate": 1.808654513687631e-06, + "loss": 1.3722, + "step": 7867 + }, + { + "epoch": 0.83, + "learning_rate": 1.8065555377922862e-06, + "loss": 1.3648, + "step": 7868 + }, + { + "epoch": 0.83, + "learning_rate": 1.8044576596079766e-06, + "loss": 1.2698, + "step": 7869 + }, + { + "epoch": 0.83, + "learning_rate": 1.8023608794157654e-06, + "loss": 1.3078, + "step": 7870 + }, + { + "epoch": 0.83, + "learning_rate": 1.8002651974965646e-06, + "loss": 1.3037, + "step": 7871 + }, + { + "epoch": 0.83, + "learning_rate": 1.7981706141311373e-06, + "loss": 1.2971, + "step": 7872 + }, + { + "epoch": 0.83, + "learning_rate": 1.7960771296001122e-06, + "loss": 1.3334, + "step": 7873 + }, + { + "epoch": 0.83, + "learning_rate": 1.7939847441839597e-06, + "loss": 1.3301, + "step": 7874 + }, + { + "epoch": 0.83, + "learning_rate": 1.7918934581629998e-06, + "loss": 1.2966, + "step": 7875 + }, + { + "epoch": 0.83, + "learning_rate": 1.7898032718174218e-06, + "loss": 1.3152, + "step": 7876 + }, + { + "epoch": 0.83, + "learning_rate": 1.7877141854272474e-06, + "loss": 1.2867, + "step": 7877 + }, + { + "epoch": 0.83, + "learning_rate": 1.7856261992723678e-06, + "loss": 1.3059, + "step": 7878 + }, + { + "epoch": 0.83, + "learning_rate": 1.783539313632513e-06, + "loss": 1.3425, + "step": 7879 + }, + { + "epoch": 0.83, + "learning_rate": 1.7814535287872748e-06, + "loss": 1.3513, + "step": 7880 + }, + { + "epoch": 0.83, + "learning_rate": 1.7793688450160983e-06, + "loss": 1.3208, + "step": 7881 + }, + { + "epoch": 0.83, + "learning_rate": 1.777285262598274e-06, + "loss": 1.302, + "step": 7882 + }, + { + "epoch": 0.83, + "learning_rate": 1.7752027818129424e-06, + "loss": 1.2783, + "step": 7883 + }, + { + "epoch": 0.83, + "learning_rate": 1.7731214029391153e-06, + "loss": 1.3599, + "step": 7884 + }, + { + "epoch": 0.83, + "learning_rate": 1.771041126255637e-06, + "loss": 1.2158, + "step": 7885 + }, + { + "epoch": 0.83, + "learning_rate": 1.7689619520412094e-06, + "loss": 1.3221, + "step": 7886 + }, + { + "epoch": 0.83, + "learning_rate": 1.7668838805743893e-06, + "loss": 1.3635, + "step": 7887 + }, + { + "epoch": 0.83, + "learning_rate": 1.7648069121335876e-06, + "loss": 1.2742, + "step": 7888 + }, + { + "epoch": 0.83, + "learning_rate": 1.762731046997065e-06, + "loss": 1.3333, + "step": 7889 + }, + { + "epoch": 0.83, + "learning_rate": 1.760656285442932e-06, + "loss": 1.2971, + "step": 7890 + }, + { + "epoch": 0.83, + "learning_rate": 1.7585826277491491e-06, + "loss": 1.3262, + "step": 7891 + }, + { + "epoch": 0.83, + "learning_rate": 1.7565100741935436e-06, + "loss": 1.38, + "step": 7892 + }, + { + "epoch": 0.83, + "learning_rate": 1.754438625053777e-06, + "loss": 1.3814, + "step": 7893 + }, + { + "epoch": 0.83, + "learning_rate": 1.7523682806073706e-06, + "loss": 1.2793, + "step": 7894 + }, + { + "epoch": 0.83, + "learning_rate": 1.7502990411316978e-06, + "loss": 1.266, + "step": 7895 + }, + { + "epoch": 0.83, + "learning_rate": 1.7482309069039838e-06, + "loss": 1.3085, + "step": 7896 + }, + { + "epoch": 0.83, + "learning_rate": 1.746163878201309e-06, + "loss": 1.3518, + "step": 7897 + }, + { + "epoch": 0.83, + "learning_rate": 1.7440979553005976e-06, + "loss": 1.3887, + "step": 7898 + }, + { + "epoch": 0.83, + "learning_rate": 1.7420331384786305e-06, + "loss": 1.3255, + "step": 7899 + }, + { + "epoch": 0.83, + "learning_rate": 1.7399694280120439e-06, + "loss": 1.3702, + "step": 7900 + }, + { + "epoch": 0.83, + "learning_rate": 1.7379068241773188e-06, + "loss": 1.3253, + "step": 7901 + }, + { + "epoch": 0.83, + "learning_rate": 1.735845327250788e-06, + "loss": 1.3055, + "step": 7902 + }, + { + "epoch": 0.83, + "learning_rate": 1.7337849375086468e-06, + "loss": 1.3119, + "step": 7903 + }, + { + "epoch": 0.83, + "learning_rate": 1.7317256552269278e-06, + "loss": 1.2741, + "step": 7904 + }, + { + "epoch": 0.83, + "learning_rate": 1.7296674806815273e-06, + "loss": 1.3101, + "step": 7905 + }, + { + "epoch": 0.83, + "learning_rate": 1.7276104141481832e-06, + "loss": 1.3553, + "step": 7906 + }, + { + "epoch": 0.83, + "learning_rate": 1.7255544559024906e-06, + "loss": 1.2712, + "step": 7907 + }, + { + "epoch": 0.83, + "learning_rate": 1.7234996062198994e-06, + "loss": 1.2814, + "step": 7908 + }, + { + "epoch": 0.83, + "learning_rate": 1.7214458653757027e-06, + "loss": 1.2831, + "step": 7909 + }, + { + "epoch": 0.83, + "learning_rate": 1.7193932336450437e-06, + "loss": 1.3519, + "step": 7910 + }, + { + "epoch": 0.83, + "learning_rate": 1.7173417113029334e-06, + "loss": 1.2559, + "step": 7911 + }, + { + "epoch": 0.83, + "learning_rate": 1.7152912986242187e-06, + "loss": 1.4204, + "step": 7912 + }, + { + "epoch": 0.83, + "learning_rate": 1.7132419958835978e-06, + "loss": 1.302, + "step": 7913 + }, + { + "epoch": 0.83, + "learning_rate": 1.7111938033556286e-06, + "loss": 1.2959, + "step": 7914 + }, + { + "epoch": 0.83, + "learning_rate": 1.7091467213147162e-06, + "loss": 1.3269, + "step": 7915 + }, + { + "epoch": 0.83, + "learning_rate": 1.7071007500351177e-06, + "loss": 1.2966, + "step": 7916 + }, + { + "epoch": 0.83, + "learning_rate": 1.705055889790941e-06, + "loss": 1.2696, + "step": 7917 + }, + { + "epoch": 0.83, + "learning_rate": 1.7030121408561373e-06, + "loss": 1.3431, + "step": 7918 + }, + { + "epoch": 0.83, + "learning_rate": 1.700969503504528e-06, + "loss": 1.2769, + "step": 7919 + }, + { + "epoch": 0.83, + "learning_rate": 1.698927978009769e-06, + "loss": 1.2543, + "step": 7920 + }, + { + "epoch": 0.83, + "learning_rate": 1.6968875646453665e-06, + "loss": 1.2612, + "step": 7921 + }, + { + "epoch": 0.83, + "learning_rate": 1.694848263684693e-06, + "loss": 1.322, + "step": 7922 + }, + { + "epoch": 0.83, + "learning_rate": 1.692810075400957e-06, + "loss": 1.4144, + "step": 7923 + }, + { + "epoch": 0.83, + "learning_rate": 1.6907730000672263e-06, + "loss": 1.4355, + "step": 7924 + }, + { + "epoch": 0.83, + "learning_rate": 1.6887370379564127e-06, + "loss": 1.4024, + "step": 7925 + }, + { + "epoch": 0.83, + "learning_rate": 1.686702189341285e-06, + "loss": 1.3015, + "step": 7926 + }, + { + "epoch": 0.83, + "learning_rate": 1.6846684544944625e-06, + "loss": 1.4337, + "step": 7927 + }, + { + "epoch": 0.83, + "learning_rate": 1.682635833688412e-06, + "loss": 1.3199, + "step": 7928 + }, + { + "epoch": 0.83, + "learning_rate": 1.6806043271954475e-06, + "loss": 1.2927, + "step": 7929 + }, + { + "epoch": 0.83, + "learning_rate": 1.6785739352877472e-06, + "loss": 1.4254, + "step": 7930 + }, + { + "epoch": 0.83, + "learning_rate": 1.676544658237328e-06, + "loss": 1.3653, + "step": 7931 + }, + { + "epoch": 0.83, + "learning_rate": 1.6745164963160576e-06, + "loss": 1.3049, + "step": 7932 + }, + { + "epoch": 0.83, + "learning_rate": 1.6724894497956613e-06, + "loss": 1.2474, + "step": 7933 + }, + { + "epoch": 0.83, + "learning_rate": 1.6704635189477091e-06, + "loss": 1.3146, + "step": 7934 + }, + { + "epoch": 0.83, + "learning_rate": 1.668438704043628e-06, + "loss": 1.2338, + "step": 7935 + }, + { + "epoch": 0.83, + "learning_rate": 1.666415005354688e-06, + "loss": 1.3217, + "step": 7936 + }, + { + "epoch": 0.83, + "learning_rate": 1.6643924231520082e-06, + "loss": 1.3776, + "step": 7937 + }, + { + "epoch": 0.83, + "learning_rate": 1.6623709577065715e-06, + "loss": 1.6173, + "step": 7938 + }, + { + "epoch": 0.83, + "learning_rate": 1.6603506092891975e-06, + "loss": 1.4383, + "step": 7939 + }, + { + "epoch": 0.83, + "learning_rate": 1.6583313781705602e-06, + "loss": 1.304, + "step": 7940 + }, + { + "epoch": 0.83, + "learning_rate": 1.6563132646211856e-06, + "loss": 1.4071, + "step": 7941 + }, + { + "epoch": 0.83, + "learning_rate": 1.6542962689114494e-06, + "loss": 1.3402, + "step": 7942 + }, + { + "epoch": 0.83, + "learning_rate": 1.6522803913115793e-06, + "loss": 1.3298, + "step": 7943 + }, + { + "epoch": 0.83, + "learning_rate": 1.6502656320916466e-06, + "loss": 1.4741, + "step": 7944 + }, + { + "epoch": 0.83, + "learning_rate": 1.64825199152158e-06, + "loss": 1.3373, + "step": 7945 + }, + { + "epoch": 0.83, + "learning_rate": 1.646239469871158e-06, + "loss": 1.6403, + "step": 7946 + }, + { + "epoch": 0.83, + "learning_rate": 1.644228067410004e-06, + "loss": 1.4887, + "step": 7947 + }, + { + "epoch": 0.83, + "learning_rate": 1.6422177844075893e-06, + "loss": 1.2763, + "step": 7948 + }, + { + "epoch": 0.83, + "learning_rate": 1.6402086211332502e-06, + "loss": 1.3298, + "step": 7949 + }, + { + "epoch": 0.83, + "learning_rate": 1.638200577856156e-06, + "loss": 1.3542, + "step": 7950 + }, + { + "epoch": 0.83, + "learning_rate": 1.6361936548453371e-06, + "loss": 1.2628, + "step": 7951 + }, + { + "epoch": 0.83, + "learning_rate": 1.6341878523696642e-06, + "loss": 1.3937, + "step": 7952 + }, + { + "epoch": 0.83, + "learning_rate": 1.6321831706978674e-06, + "loss": 1.2712, + "step": 7953 + }, + { + "epoch": 0.83, + "learning_rate": 1.6301796100985235e-06, + "loss": 1.3303, + "step": 7954 + }, + { + "epoch": 0.83, + "learning_rate": 1.6281771708400563e-06, + "loss": 1.2698, + "step": 7955 + }, + { + "epoch": 0.83, + "learning_rate": 1.6261758531907367e-06, + "loss": 1.3242, + "step": 7956 + }, + { + "epoch": 0.83, + "learning_rate": 1.6241756574186996e-06, + "loss": 1.2774, + "step": 7957 + }, + { + "epoch": 0.83, + "learning_rate": 1.6221765837919135e-06, + "loss": 1.3022, + "step": 7958 + }, + { + "epoch": 0.83, + "learning_rate": 1.620178632578202e-06, + "loss": 1.375, + "step": 7959 + }, + { + "epoch": 0.83, + "learning_rate": 1.6181818040452412e-06, + "loss": 1.308, + "step": 7960 + }, + { + "epoch": 0.83, + "eval_loss": 1.3948875665664673, + "eval_runtime": 77.4765, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 7960 + }, + { + "epoch": 0.83, + "learning_rate": 1.616186098460555e-06, + "loss": 1.3674, + "step": 7961 + }, + { + "epoch": 0.83, + "learning_rate": 1.614191516091519e-06, + "loss": 1.4367, + "step": 7962 + }, + { + "epoch": 0.84, + "learning_rate": 1.612198057205353e-06, + "loss": 1.3105, + "step": 7963 + }, + { + "epoch": 0.84, + "learning_rate": 1.6102057220691258e-06, + "loss": 1.2591, + "step": 7964 + }, + { + "epoch": 0.84, + "learning_rate": 1.608214510949767e-06, + "loss": 1.3503, + "step": 7965 + }, + { + "epoch": 0.84, + "learning_rate": 1.6062244241140435e-06, + "loss": 1.3278, + "step": 7966 + }, + { + "epoch": 0.84, + "learning_rate": 1.6042354618285727e-06, + "loss": 1.2831, + "step": 7967 + }, + { + "epoch": 0.84, + "learning_rate": 1.6022476243598317e-06, + "loss": 1.2535, + "step": 7968 + }, + { + "epoch": 0.84, + "learning_rate": 1.600260911974133e-06, + "loss": 1.2719, + "step": 7969 + }, + { + "epoch": 0.84, + "learning_rate": 1.5982753249376503e-06, + "loss": 1.2615, + "step": 7970 + }, + { + "epoch": 0.84, + "learning_rate": 1.5962908635163965e-06, + "loss": 1.2996, + "step": 7971 + }, + { + "epoch": 0.84, + "learning_rate": 1.594307527976241e-06, + "loss": 1.3323, + "step": 7972 + }, + { + "epoch": 0.84, + "learning_rate": 1.5923253185829024e-06, + "loss": 1.2993, + "step": 7973 + }, + { + "epoch": 0.84, + "learning_rate": 1.5903442356019415e-06, + "loss": 1.3064, + "step": 7974 + }, + { + "epoch": 0.84, + "learning_rate": 1.5883642792987697e-06, + "loss": 1.3171, + "step": 7975 + }, + { + "epoch": 0.84, + "learning_rate": 1.58638544993866e-06, + "loss": 1.4238, + "step": 7976 + }, + { + "epoch": 0.84, + "learning_rate": 1.584407747786716e-06, + "loss": 1.356, + "step": 7977 + }, + { + "epoch": 0.84, + "learning_rate": 1.5824311731079046e-06, + "loss": 1.4523, + "step": 7978 + }, + { + "epoch": 0.84, + "learning_rate": 1.5804557261670318e-06, + "loss": 1.3206, + "step": 7979 + }, + { + "epoch": 0.84, + "learning_rate": 1.578481407228758e-06, + "loss": 1.2639, + "step": 7980 + }, + { + "epoch": 0.84, + "learning_rate": 1.576508216557594e-06, + "loss": 1.2428, + "step": 7981 + }, + { + "epoch": 0.84, + "learning_rate": 1.574536154417895e-06, + "loss": 1.3779, + "step": 7982 + }, + { + "epoch": 0.84, + "learning_rate": 1.5725652210738606e-06, + "loss": 1.3071, + "step": 7983 + }, + { + "epoch": 0.84, + "learning_rate": 1.5705954167895553e-06, + "loss": 1.2604, + "step": 7984 + }, + { + "epoch": 0.84, + "learning_rate": 1.568626741828878e-06, + "loss": 1.2565, + "step": 7985 + }, + { + "epoch": 0.84, + "learning_rate": 1.5666591964555777e-06, + "loss": 1.2742, + "step": 7986 + }, + { + "epoch": 0.84, + "learning_rate": 1.564692780933258e-06, + "loss": 1.3199, + "step": 7987 + }, + { + "epoch": 0.84, + "learning_rate": 1.5627274955253669e-06, + "loss": 1.4034, + "step": 7988 + }, + { + "epoch": 0.84, + "learning_rate": 1.5607633404952048e-06, + "loss": 1.3411, + "step": 7989 + }, + { + "epoch": 0.84, + "learning_rate": 1.558800316105914e-06, + "loss": 1.2874, + "step": 7990 + }, + { + "epoch": 0.84, + "learning_rate": 1.5568384226204903e-06, + "loss": 1.2678, + "step": 7991 + }, + { + "epoch": 0.84, + "learning_rate": 1.5548776603017813e-06, + "loss": 1.3038, + "step": 7992 + }, + { + "epoch": 0.84, + "learning_rate": 1.5529180294124757e-06, + "loss": 1.0848, + "step": 7993 + }, + { + "epoch": 0.84, + "learning_rate": 1.550959530215108e-06, + "loss": 1.2062, + "step": 7994 + }, + { + "epoch": 0.84, + "learning_rate": 1.5490021629720763e-06, + "loss": 1.3028, + "step": 7995 + }, + { + "epoch": 0.84, + "learning_rate": 1.547045927945613e-06, + "loss": 1.3513, + "step": 7996 + }, + { + "epoch": 0.84, + "learning_rate": 1.5450908253978047e-06, + "loss": 1.426, + "step": 7997 + }, + { + "epoch": 0.84, + "learning_rate": 1.5431368555905813e-06, + "loss": 1.2943, + "step": 7998 + }, + { + "epoch": 0.84, + "learning_rate": 1.5411840187857275e-06, + "loss": 1.272, + "step": 7999 + }, + { + "epoch": 0.84, + "learning_rate": 1.5392323152448762e-06, + "loss": 1.3819, + "step": 8000 + }, + { + "epoch": 0.84, + "learning_rate": 1.537281745229502e-06, + "loss": 1.2186, + "step": 8001 + }, + { + "epoch": 0.84, + "learning_rate": 1.5353323090009253e-06, + "loss": 1.4509, + "step": 8002 + }, + { + "epoch": 0.84, + "learning_rate": 1.5333840068203332e-06, + "loss": 1.3629, + "step": 8003 + }, + { + "epoch": 0.84, + "learning_rate": 1.5314368389487378e-06, + "loss": 1.2865, + "step": 8004 + }, + { + "epoch": 0.84, + "learning_rate": 1.529490805647016e-06, + "loss": 1.2645, + "step": 8005 + }, + { + "epoch": 0.84, + "learning_rate": 1.5275459071758813e-06, + "loss": 1.3248, + "step": 8006 + }, + { + "epoch": 0.84, + "learning_rate": 1.5256021437959023e-06, + "loss": 1.2202, + "step": 8007 + }, + { + "epoch": 0.84, + "learning_rate": 1.523659515767496e-06, + "loss": 1.3728, + "step": 8008 + }, + { + "epoch": 0.84, + "learning_rate": 1.5217180233509222e-06, + "loss": 1.2981, + "step": 8009 + }, + { + "epoch": 0.84, + "learning_rate": 1.5197776668062857e-06, + "loss": 1.4002, + "step": 8010 + }, + { + "epoch": 0.84, + "learning_rate": 1.5178384463935546e-06, + "loss": 1.3403, + "step": 8011 + }, + { + "epoch": 0.84, + "learning_rate": 1.51590036237253e-06, + "loss": 1.2629, + "step": 8012 + }, + { + "epoch": 0.84, + "learning_rate": 1.5139634150028594e-06, + "loss": 1.298, + "step": 8013 + }, + { + "epoch": 0.84, + "learning_rate": 1.5120276045440553e-06, + "loss": 1.412, + "step": 8014 + }, + { + "epoch": 0.84, + "learning_rate": 1.510092931255458e-06, + "loss": 1.3025, + "step": 8015 + }, + { + "epoch": 0.84, + "learning_rate": 1.508159395396268e-06, + "loss": 1.2494, + "step": 8016 + }, + { + "epoch": 0.84, + "learning_rate": 1.5062269972255273e-06, + "loss": 1.3295, + "step": 8017 + }, + { + "epoch": 0.84, + "learning_rate": 1.5042957370021282e-06, + "loss": 1.3227, + "step": 8018 + }, + { + "epoch": 0.84, + "learning_rate": 1.5023656149848132e-06, + "loss": 1.3122, + "step": 8019 + }, + { + "epoch": 0.84, + "learning_rate": 1.500436631432165e-06, + "loss": 1.2789, + "step": 8020 + }, + { + "epoch": 0.84, + "learning_rate": 1.4985087866026148e-06, + "loss": 1.2753, + "step": 8021 + }, + { + "epoch": 0.84, + "learning_rate": 1.4965820807544529e-06, + "loss": 1.3296, + "step": 8022 + }, + { + "epoch": 0.84, + "learning_rate": 1.4946565141458024e-06, + "loss": 1.2886, + "step": 8023 + }, + { + "epoch": 0.84, + "learning_rate": 1.492732087034643e-06, + "loss": 1.3137, + "step": 8024 + }, + { + "epoch": 0.84, + "learning_rate": 1.4908087996787944e-06, + "loss": 1.2785, + "step": 8025 + }, + { + "epoch": 0.84, + "learning_rate": 1.4888866523359302e-06, + "loss": 1.3674, + "step": 8026 + }, + { + "epoch": 0.84, + "learning_rate": 1.4869656452635705e-06, + "loss": 1.367, + "step": 8027 + }, + { + "epoch": 0.84, + "learning_rate": 1.4850457787190797e-06, + "loss": 1.3342, + "step": 8028 + }, + { + "epoch": 0.84, + "learning_rate": 1.483127052959664e-06, + "loss": 1.3091, + "step": 8029 + }, + { + "epoch": 0.84, + "learning_rate": 1.481209468242396e-06, + "loss": 1.3729, + "step": 8030 + }, + { + "epoch": 0.84, + "learning_rate": 1.4792930248241744e-06, + "loss": 1.3051, + "step": 8031 + }, + { + "epoch": 0.84, + "learning_rate": 1.4773777229617537e-06, + "loss": 1.2458, + "step": 8032 + }, + { + "epoch": 0.84, + "learning_rate": 1.4754635629117353e-06, + "loss": 1.2803, + "step": 8033 + }, + { + "epoch": 0.84, + "learning_rate": 1.4735505449305687e-06, + "loss": 1.3193, + "step": 8034 + }, + { + "epoch": 0.84, + "learning_rate": 1.4716386692745522e-06, + "loss": 1.2537, + "step": 8035 + }, + { + "epoch": 0.84, + "learning_rate": 1.4697279361998218e-06, + "loss": 1.2816, + "step": 8036 + }, + { + "epoch": 0.84, + "learning_rate": 1.4678183459623708e-06, + "loss": 1.3422, + "step": 8037 + }, + { + "epoch": 0.84, + "learning_rate": 1.4659098988180353e-06, + "loss": 1.34, + "step": 8038 + }, + { + "epoch": 0.84, + "learning_rate": 1.464002595022498e-06, + "loss": 1.3328, + "step": 8039 + }, + { + "epoch": 0.84, + "learning_rate": 1.4620964348312817e-06, + "loss": 1.3415, + "step": 8040 + }, + { + "epoch": 0.84, + "learning_rate": 1.4601914184997744e-06, + "loss": 1.3124, + "step": 8041 + }, + { + "epoch": 0.84, + "learning_rate": 1.4582875462831913e-06, + "loss": 1.3219, + "step": 8042 + }, + { + "epoch": 0.84, + "learning_rate": 1.4563848184366069e-06, + "loss": 1.3322, + "step": 8043 + }, + { + "epoch": 0.84, + "learning_rate": 1.454483235214934e-06, + "loss": 1.2926, + "step": 8044 + }, + { + "epoch": 0.84, + "learning_rate": 1.4525827968729366e-06, + "loss": 1.2796, + "step": 8045 + }, + { + "epoch": 0.84, + "learning_rate": 1.4506835036652289e-06, + "loss": 1.3504, + "step": 8046 + }, + { + "epoch": 0.84, + "learning_rate": 1.448785355846264e-06, + "loss": 1.2122, + "step": 8047 + }, + { + "epoch": 0.84, + "learning_rate": 1.4468883536703405e-06, + "loss": 1.3121, + "step": 8048 + }, + { + "epoch": 0.84, + "learning_rate": 1.4449924973916163e-06, + "loss": 1.3268, + "step": 8049 + }, + { + "epoch": 0.84, + "learning_rate": 1.4430977872640817e-06, + "loss": 1.3911, + "step": 8050 + }, + { + "epoch": 0.84, + "learning_rate": 1.4412042235415836e-06, + "loss": 1.3366, + "step": 8051 + }, + { + "epoch": 0.84, + "learning_rate": 1.4393118064778066e-06, + "loss": 1.2953, + "step": 8052 + }, + { + "epoch": 0.84, + "learning_rate": 1.4374205363262872e-06, + "loss": 1.3222, + "step": 8053 + }, + { + "epoch": 0.84, + "learning_rate": 1.4355304133404102e-06, + "loss": 1.2385, + "step": 8054 + }, + { + "epoch": 0.84, + "learning_rate": 1.433641437773401e-06, + "loss": 1.3245, + "step": 8055 + }, + { + "epoch": 0.84, + "learning_rate": 1.431753609878328e-06, + "loss": 1.2401, + "step": 8056 + }, + { + "epoch": 0.84, + "learning_rate": 1.4298669299081236e-06, + "loss": 1.4646, + "step": 8057 + }, + { + "epoch": 0.85, + "learning_rate": 1.4279813981155465e-06, + "loss": 1.253, + "step": 8058 + }, + { + "epoch": 0.85, + "learning_rate": 1.426097014753207e-06, + "loss": 1.393, + "step": 8059 + }, + { + "epoch": 0.85, + "learning_rate": 1.4242137800735734e-06, + "loss": 1.3527, + "step": 8060 + }, + { + "epoch": 0.85, + "learning_rate": 1.4223316943289435e-06, + "loss": 1.2528, + "step": 8061 + }, + { + "epoch": 0.85, + "learning_rate": 1.420450757771472e-06, + "loss": 1.2165, + "step": 8062 + }, + { + "epoch": 0.85, + "learning_rate": 1.4185709706531526e-06, + "loss": 1.2348, + "step": 8063 + }, + { + "epoch": 0.85, + "learning_rate": 1.4166923332258308e-06, + "loss": 1.3145, + "step": 8064 + }, + { + "epoch": 0.85, + "learning_rate": 1.414814845741197e-06, + "loss": 1.2026, + "step": 8065 + }, + { + "epoch": 0.85, + "learning_rate": 1.4129385084507852e-06, + "loss": 1.3398, + "step": 8066 + }, + { + "epoch": 0.85, + "learning_rate": 1.4110633216059711e-06, + "loss": 1.3166, + "step": 8067 + }, + { + "epoch": 0.85, + "learning_rate": 1.4091892854579913e-06, + "loss": 1.5105, + "step": 8068 + }, + { + "epoch": 0.85, + "learning_rate": 1.407316400257911e-06, + "loss": 1.3002, + "step": 8069 + }, + { + "epoch": 0.85, + "learning_rate": 1.4054446662566535e-06, + "loss": 1.2826, + "step": 8070 + }, + { + "epoch": 0.85, + "learning_rate": 1.4035740837049782e-06, + "loss": 1.338, + "step": 8071 + }, + { + "epoch": 0.85, + "learning_rate": 1.4017046528534983e-06, + "loss": 1.393, + "step": 8072 + }, + { + "epoch": 0.85, + "learning_rate": 1.3998363739526699e-06, + "loss": 1.3082, + "step": 8073 + }, + { + "epoch": 0.85, + "learning_rate": 1.397969247252794e-06, + "loss": 1.345, + "step": 8074 + }, + { + "epoch": 0.85, + "learning_rate": 1.3961032730040126e-06, + "loss": 1.3075, + "step": 8075 + }, + { + "epoch": 0.85, + "learning_rate": 1.394238451456328e-06, + "loss": 1.3432, + "step": 8076 + }, + { + "epoch": 0.85, + "learning_rate": 1.392374782859569e-06, + "loss": 1.3096, + "step": 8077 + }, + { + "epoch": 0.85, + "learning_rate": 1.3905122674634274e-06, + "loss": 1.2686, + "step": 8078 + }, + { + "epoch": 0.85, + "learning_rate": 1.3886509055174247e-06, + "loss": 1.3075, + "step": 8079 + }, + { + "epoch": 0.85, + "learning_rate": 1.38679069727094e-06, + "loss": 1.3446, + "step": 8080 + }, + { + "epoch": 0.85, + "learning_rate": 1.3849316429731941e-06, + "loss": 1.3646, + "step": 8081 + }, + { + "epoch": 0.85, + "learning_rate": 1.3830737428732499e-06, + "loss": 1.3074, + "step": 8082 + }, + { + "epoch": 0.85, + "learning_rate": 1.3812169972200184e-06, + "loss": 1.277, + "step": 8083 + }, + { + "epoch": 0.85, + "learning_rate": 1.3793614062622595e-06, + "loss": 1.2978, + "step": 8084 + }, + { + "epoch": 0.85, + "learning_rate": 1.3775069702485722e-06, + "loss": 1.3978, + "step": 8085 + }, + { + "epoch": 0.85, + "learning_rate": 1.3756536894273974e-06, + "loss": 1.4198, + "step": 8086 + }, + { + "epoch": 0.85, + "learning_rate": 1.3738015640470381e-06, + "loss": 1.2901, + "step": 8087 + }, + { + "epoch": 0.85, + "learning_rate": 1.3719505943556243e-06, + "loss": 1.2916, + "step": 8088 + }, + { + "epoch": 0.85, + "learning_rate": 1.3701007806011423e-06, + "loss": 1.2845, + "step": 8089 + }, + { + "epoch": 0.85, + "learning_rate": 1.368252123031416e-06, + "loss": 1.3261, + "step": 8090 + }, + { + "epoch": 0.85, + "learning_rate": 1.3664046218941185e-06, + "loss": 1.321, + "step": 8091 + }, + { + "epoch": 0.85, + "learning_rate": 1.3645582774367717e-06, + "loss": 1.2968, + "step": 8092 + }, + { + "epoch": 0.85, + "learning_rate": 1.3627130899067353e-06, + "loss": 1.2595, + "step": 8093 + }, + { + "epoch": 0.85, + "learning_rate": 1.360869059551212e-06, + "loss": 1.4081, + "step": 8094 + }, + { + "epoch": 0.85, + "learning_rate": 1.3590261866172638e-06, + "loss": 1.2949, + "step": 8095 + }, + { + "epoch": 0.85, + "learning_rate": 1.3571844713517823e-06, + "loss": 1.3563, + "step": 8096 + }, + { + "epoch": 0.85, + "learning_rate": 1.3553439140015135e-06, + "loss": 1.3063, + "step": 8097 + }, + { + "epoch": 0.85, + "learning_rate": 1.353504514813041e-06, + "loss": 1.2896, + "step": 8098 + }, + { + "epoch": 0.85, + "learning_rate": 1.351666274032799e-06, + "loss": 1.3338, + "step": 8099 + }, + { + "epoch": 0.85, + "learning_rate": 1.349829191907066e-06, + "loss": 1.2932, + "step": 8100 + }, + { + "epoch": 0.85, + "learning_rate": 1.3479932686819642e-06, + "loss": 1.3287, + "step": 8101 + }, + { + "epoch": 0.85, + "learning_rate": 1.346158504603452e-06, + "loss": 1.3343, + "step": 8102 + }, + { + "epoch": 0.85, + "learning_rate": 1.344324899917352e-06, + "loss": 1.3419, + "step": 8103 + }, + { + "epoch": 0.85, + "learning_rate": 1.342492454869313e-06, + "loss": 1.3138, + "step": 8104 + }, + { + "epoch": 0.85, + "learning_rate": 1.3406611697048377e-06, + "loss": 1.3473, + "step": 8105 + }, + { + "epoch": 0.85, + "learning_rate": 1.338831044669273e-06, + "loss": 1.3035, + "step": 8106 + }, + { + "epoch": 0.85, + "learning_rate": 1.3370020800078043e-06, + "loss": 1.3299, + "step": 8107 + }, + { + "epoch": 0.85, + "learning_rate": 1.3351742759654707e-06, + "loss": 1.357, + "step": 8108 + }, + { + "epoch": 0.85, + "learning_rate": 1.3333476327871475e-06, + "loss": 1.3777, + "step": 8109 + }, + { + "epoch": 0.85, + "learning_rate": 1.331522150717558e-06, + "loss": 1.3359, + "step": 8110 + }, + { + "epoch": 0.85, + "learning_rate": 1.329697830001273e-06, + "loss": 1.2436, + "step": 8111 + }, + { + "epoch": 0.85, + "learning_rate": 1.3278746708827028e-06, + "loss": 1.2916, + "step": 8112 + }, + { + "epoch": 0.85, + "learning_rate": 1.3260526736060998e-06, + "loss": 1.3127, + "step": 8113 + }, + { + "epoch": 0.85, + "learning_rate": 1.3242318384155728e-06, + "loss": 1.2876, + "step": 8114 + }, + { + "epoch": 0.85, + "learning_rate": 1.3224121655550603e-06, + "loss": 1.4193, + "step": 8115 + }, + { + "epoch": 0.85, + "learning_rate": 1.3205936552683573e-06, + "loss": 1.2978, + "step": 8116 + }, + { + "epoch": 0.85, + "learning_rate": 1.3187763077990912e-06, + "loss": 1.344, + "step": 8117 + }, + { + "epoch": 0.85, + "learning_rate": 1.3169601233907436e-06, + "loss": 1.2493, + "step": 8118 + }, + { + "epoch": 0.85, + "learning_rate": 1.315145102286638e-06, + "loss": 1.344, + "step": 8119 + }, + { + "epoch": 0.85, + "learning_rate": 1.3133312447299385e-06, + "loss": 1.3235, + "step": 8120 + }, + { + "epoch": 0.85, + "learning_rate": 1.3115185509636508e-06, + "loss": 1.3134, + "step": 8121 + }, + { + "epoch": 0.85, + "learning_rate": 1.3097070212306385e-06, + "loss": 1.2735, + "step": 8122 + }, + { + "epoch": 0.85, + "learning_rate": 1.307896655773594e-06, + "loss": 1.4682, + "step": 8123 + }, + { + "epoch": 0.85, + "learning_rate": 1.3060874548350632e-06, + "loss": 1.2092, + "step": 8124 + }, + { + "epoch": 0.85, + "learning_rate": 1.304279418657428e-06, + "loss": 1.314, + "step": 8125 + }, + { + "epoch": 0.85, + "learning_rate": 1.3024725474829215e-06, + "loss": 1.4204, + "step": 8126 + }, + { + "epoch": 0.85, + "learning_rate": 1.3006668415536195e-06, + "loss": 1.298, + "step": 8127 + }, + { + "epoch": 0.85, + "learning_rate": 1.2988623011114377e-06, + "loss": 1.2639, + "step": 8128 + }, + { + "epoch": 0.85, + "learning_rate": 1.2970589263981382e-06, + "loss": 1.291, + "step": 8129 + }, + { + "epoch": 0.85, + "learning_rate": 1.2952567176553298e-06, + "loss": 1.3849, + "step": 8130 + }, + { + "epoch": 0.85, + "learning_rate": 1.293455675124461e-06, + "loss": 1.2594, + "step": 8131 + }, + { + "epoch": 0.85, + "learning_rate": 1.2916557990468192e-06, + "loss": 1.3696, + "step": 8132 + }, + { + "epoch": 0.85, + "learning_rate": 1.289857089663551e-06, + "loss": 1.3263, + "step": 8133 + }, + { + "epoch": 0.85, + "learning_rate": 1.288059547215631e-06, + "loss": 1.302, + "step": 8134 + }, + { + "epoch": 0.85, + "learning_rate": 1.2862631719438878e-06, + "loss": 1.2587, + "step": 8135 + }, + { + "epoch": 0.85, + "learning_rate": 1.2844679640889857e-06, + "loss": 1.3579, + "step": 8136 + }, + { + "epoch": 0.85, + "learning_rate": 1.2826739238914376e-06, + "loss": 1.3246, + "step": 8137 + }, + { + "epoch": 0.85, + "learning_rate": 1.2808810515916016e-06, + "loss": 1.3346, + "step": 8138 + }, + { + "epoch": 0.85, + "learning_rate": 1.279089347429674e-06, + "loss": 1.264, + "step": 8139 + }, + { + "epoch": 0.85, + "learning_rate": 1.277298811645692e-06, + "loss": 1.2276, + "step": 8140 + }, + { + "epoch": 0.85, + "learning_rate": 1.2755094444795524e-06, + "loss": 1.2699, + "step": 8141 + }, + { + "epoch": 0.85, + "learning_rate": 1.273721246170976e-06, + "loss": 1.2784, + "step": 8142 + }, + { + "epoch": 0.85, + "learning_rate": 1.2719342169595406e-06, + "loss": 1.3973, + "step": 8143 + }, + { + "epoch": 0.85, + "learning_rate": 1.2701483570846572e-06, + "loss": 1.2869, + "step": 8144 + }, + { + "epoch": 0.85, + "learning_rate": 1.268363666785588e-06, + "loss": 1.0653, + "step": 8145 + }, + { + "epoch": 0.85, + "learning_rate": 1.266580146301437e-06, + "loss": 1.0105, + "step": 8146 + }, + { + "epoch": 0.85, + "learning_rate": 1.264797795871149e-06, + "loss": 1.3069, + "step": 8147 + }, + { + "epoch": 0.85, + "learning_rate": 1.2630166157335077e-06, + "loss": 1.303, + "step": 8148 + }, + { + "epoch": 0.85, + "learning_rate": 1.2612366061271552e-06, + "loss": 1.2883, + "step": 8149 + }, + { + "epoch": 0.85, + "learning_rate": 1.2594577672905594e-06, + "loss": 1.4152, + "step": 8150 + }, + { + "epoch": 0.85, + "learning_rate": 1.257680099462043e-06, + "loss": 1.273, + "step": 8151 + }, + { + "epoch": 0.85, + "learning_rate": 1.2559036028797677e-06, + "loss": 1.2793, + "step": 8152 + }, + { + "epoch": 0.85, + "learning_rate": 1.2541282777817354e-06, + "loss": 1.3001, + "step": 8153 + }, + { + "epoch": 0.86, + "learning_rate": 1.252354124405799e-06, + "loss": 1.3743, + "step": 8154 + }, + { + "epoch": 0.86, + "learning_rate": 1.2505811429896432e-06, + "loss": 1.2804, + "step": 8155 + }, + { + "epoch": 0.86, + "learning_rate": 1.2488093337708062e-06, + "loss": 1.3354, + "step": 8156 + }, + { + "epoch": 0.86, + "learning_rate": 1.2470386969866655e-06, + "loss": 1.3836, + "step": 8157 + }, + { + "epoch": 0.86, + "learning_rate": 1.2452692328744386e-06, + "loss": 1.2499, + "step": 8158 + }, + { + "epoch": 0.86, + "learning_rate": 1.2435009416711853e-06, + "loss": 1.4049, + "step": 8159 + }, + { + "epoch": 0.86, + "eval_loss": 1.3945679664611816, + "eval_runtime": 77.4963, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 8159 + }, + { + "epoch": 0.86, + "learning_rate": 1.2417338236138199e-06, + "loss": 1.261, + "step": 8160 + }, + { + "epoch": 0.86, + "learning_rate": 1.2399678789390823e-06, + "loss": 1.3172, + "step": 8161 + }, + { + "epoch": 0.86, + "learning_rate": 1.238203107883571e-06, + "loss": 1.3836, + "step": 8162 + }, + { + "epoch": 0.86, + "learning_rate": 1.2364395106837124e-06, + "loss": 1.3116, + "step": 8163 + }, + { + "epoch": 0.86, + "learning_rate": 1.2346770875757874e-06, + "loss": 1.2897, + "step": 8164 + }, + { + "epoch": 0.86, + "learning_rate": 1.2329158387959172e-06, + "loss": 1.3148, + "step": 8165 + }, + { + "epoch": 0.86, + "learning_rate": 1.231155764580062e-06, + "loss": 1.2744, + "step": 8166 + }, + { + "epoch": 0.86, + "learning_rate": 1.229396865164022e-06, + "loss": 1.3159, + "step": 8167 + }, + { + "epoch": 0.86, + "learning_rate": 1.2276391407834532e-06, + "loss": 1.3238, + "step": 8168 + }, + { + "epoch": 0.86, + "learning_rate": 1.2258825916738383e-06, + "loss": 1.3376, + "step": 8169 + }, + { + "epoch": 0.86, + "learning_rate": 1.2241272180705143e-06, + "loss": 1.2715, + "step": 8170 + }, + { + "epoch": 0.86, + "learning_rate": 1.2223730202086525e-06, + "loss": 1.3022, + "step": 8171 + }, + { + "epoch": 0.86, + "learning_rate": 1.2206199983232726e-06, + "loss": 1.3354, + "step": 8172 + }, + { + "epoch": 0.86, + "learning_rate": 1.2188681526492363e-06, + "loss": 1.4273, + "step": 8173 + }, + { + "epoch": 0.86, + "learning_rate": 1.2171174834212407e-06, + "loss": 1.3272, + "step": 8174 + }, + { + "epoch": 0.86, + "learning_rate": 1.2153679908738337e-06, + "loss": 1.3173, + "step": 8175 + }, + { + "epoch": 0.86, + "learning_rate": 1.2136196752414042e-06, + "loss": 1.2679, + "step": 8176 + }, + { + "epoch": 0.86, + "learning_rate": 1.2118725367581784e-06, + "loss": 1.3409, + "step": 8177 + }, + { + "epoch": 0.86, + "learning_rate": 1.210126575658228e-06, + "loss": 1.3393, + "step": 8178 + }, + { + "epoch": 0.86, + "learning_rate": 1.2083817921754705e-06, + "loss": 1.3126, + "step": 8179 + }, + { + "epoch": 0.86, + "learning_rate": 1.2066381865436571e-06, + "loss": 1.3525, + "step": 8180 + }, + { + "epoch": 0.86, + "learning_rate": 1.2048957589963907e-06, + "loss": 1.3107, + "step": 8181 + }, + { + "epoch": 0.86, + "learning_rate": 1.2031545097671082e-06, + "loss": 1.3374, + "step": 8182 + }, + { + "epoch": 0.86, + "learning_rate": 1.2014144390890937e-06, + "loss": 1.2889, + "step": 8183 + }, + { + "epoch": 0.86, + "learning_rate": 1.1996755471954734e-06, + "loss": 1.3043, + "step": 8184 + }, + { + "epoch": 0.86, + "learning_rate": 1.1979378343192126e-06, + "loss": 1.3172, + "step": 8185 + }, + { + "epoch": 0.86, + "learning_rate": 1.1962013006931172e-06, + "loss": 1.3526, + "step": 8186 + }, + { + "epoch": 0.86, + "learning_rate": 1.1944659465498443e-06, + "loss": 1.32, + "step": 8187 + }, + { + "epoch": 0.86, + "learning_rate": 1.1927317721218822e-06, + "loss": 1.3449, + "step": 8188 + }, + { + "epoch": 0.86, + "learning_rate": 1.1909987776415699e-06, + "loss": 1.2887, + "step": 8189 + }, + { + "epoch": 0.86, + "learning_rate": 1.189266963341078e-06, + "loss": 1.368, + "step": 8190 + }, + { + "epoch": 0.86, + "learning_rate": 1.18753632945243e-06, + "loss": 1.3297, + "step": 8191 + }, + { + "epoch": 0.86, + "learning_rate": 1.185806876207486e-06, + "loss": 1.3447, + "step": 8192 + }, + { + "epoch": 0.86, + "learning_rate": 1.184078603837946e-06, + "loss": 1.291, + "step": 8193 + }, + { + "epoch": 0.86, + "learning_rate": 1.182351512575355e-06, + "loss": 1.3272, + "step": 8194 + }, + { + "epoch": 0.86, + "learning_rate": 1.180625602651101e-06, + "loss": 1.2771, + "step": 8195 + }, + { + "epoch": 0.86, + "learning_rate": 1.178900874296407e-06, + "loss": 1.2562, + "step": 8196 + }, + { + "epoch": 0.86, + "learning_rate": 1.177177327742346e-06, + "loss": 1.2508, + "step": 8197 + }, + { + "epoch": 0.86, + "learning_rate": 1.1754549632198298e-06, + "loss": 1.2923, + "step": 8198 + }, + { + "epoch": 0.86, + "learning_rate": 1.1737337809596072e-06, + "loss": 1.3251, + "step": 8199 + }, + { + "epoch": 0.86, + "learning_rate": 1.1720137811922761e-06, + "loss": 1.2729, + "step": 8200 + }, + { + "epoch": 0.86, + "learning_rate": 1.1702949641482687e-06, + "loss": 1.2635, + "step": 8201 + }, + { + "epoch": 0.86, + "learning_rate": 1.1685773300578651e-06, + "loss": 1.3456, + "step": 8202 + }, + { + "epoch": 0.86, + "learning_rate": 1.1668608791511838e-06, + "loss": 1.2506, + "step": 8203 + }, + { + "epoch": 0.86, + "learning_rate": 1.1651456116581838e-06, + "loss": 1.4416, + "step": 8204 + }, + { + "epoch": 0.86, + "learning_rate": 1.163431527808666e-06, + "loss": 1.3066, + "step": 8205 + }, + { + "epoch": 0.86, + "learning_rate": 1.161718627832279e-06, + "loss": 1.2943, + "step": 8206 + }, + { + "epoch": 0.86, + "learning_rate": 1.1600069119585e-06, + "loss": 1.2785, + "step": 8207 + }, + { + "epoch": 0.86, + "learning_rate": 1.1582963804166614e-06, + "loss": 1.3252, + "step": 8208 + }, + { + "epoch": 0.86, + "learning_rate": 1.1565870334359263e-06, + "loss": 1.2878, + "step": 8209 + }, + { + "epoch": 0.86, + "learning_rate": 1.154878871245303e-06, + "loss": 1.2809, + "step": 8210 + }, + { + "epoch": 0.86, + "learning_rate": 1.1531718940736458e-06, + "loss": 1.3194, + "step": 8211 + }, + { + "epoch": 0.86, + "learning_rate": 1.1514661021496432e-06, + "loss": 1.2898, + "step": 8212 + }, + { + "epoch": 0.86, + "learning_rate": 1.1497614957018233e-06, + "loss": 1.3392, + "step": 8213 + }, + { + "epoch": 0.86, + "learning_rate": 1.1480580749585669e-06, + "loss": 1.2746, + "step": 8214 + }, + { + "epoch": 0.86, + "learning_rate": 1.1463558401480824e-06, + "loss": 1.2374, + "step": 8215 + }, + { + "epoch": 0.86, + "learning_rate": 1.1446547914984296e-06, + "loss": 1.334, + "step": 8216 + }, + { + "epoch": 0.86, + "learning_rate": 1.1429549292375053e-06, + "loss": 1.0102, + "step": 8217 + }, + { + "epoch": 0.86, + "learning_rate": 1.1412562535930448e-06, + "loss": 0.9128, + "step": 8218 + }, + { + "epoch": 0.86, + "learning_rate": 1.13955876479263e-06, + "loss": 0.8105, + "step": 8219 + }, + { + "epoch": 0.86, + "learning_rate": 1.137862463063677e-06, + "loss": 0.8131, + "step": 8220 + }, + { + "epoch": 0.86, + "learning_rate": 1.1361673486334478e-06, + "loss": 1.277, + "step": 8221 + }, + { + "epoch": 0.86, + "learning_rate": 1.1344734217290475e-06, + "loss": 1.2847, + "step": 8222 + }, + { + "epoch": 0.86, + "learning_rate": 1.1327806825774158e-06, + "loss": 1.4042, + "step": 8223 + }, + { + "epoch": 0.86, + "learning_rate": 1.1310891314053353e-06, + "loss": 1.1244, + "step": 8224 + }, + { + "epoch": 0.86, + "learning_rate": 1.1293987684394347e-06, + "loss": 1.1722, + "step": 8225 + }, + { + "epoch": 0.86, + "learning_rate": 1.1277095939061732e-06, + "loss": 1.3665, + "step": 8226 + }, + { + "epoch": 0.86, + "learning_rate": 1.1260216080318632e-06, + "loss": 1.3327, + "step": 8227 + }, + { + "epoch": 0.86, + "learning_rate": 1.1243348110426455e-06, + "loss": 1.3167, + "step": 8228 + }, + { + "epoch": 0.86, + "learning_rate": 1.1226492031645109e-06, + "loss": 1.3049, + "step": 8229 + }, + { + "epoch": 0.86, + "learning_rate": 1.1209647846232884e-06, + "loss": 1.2995, + "step": 8230 + }, + { + "epoch": 0.86, + "learning_rate": 1.1192815556446445e-06, + "loss": 1.3078, + "step": 8231 + }, + { + "epoch": 0.86, + "learning_rate": 1.1175995164540887e-06, + "loss": 1.4174, + "step": 8232 + }, + { + "epoch": 0.86, + "learning_rate": 1.1159186672769728e-06, + "loss": 1.2479, + "step": 8233 + }, + { + "epoch": 0.86, + "learning_rate": 1.1142390083384857e-06, + "loss": 1.3166, + "step": 8234 + }, + { + "epoch": 0.86, + "learning_rate": 1.1125605398636607e-06, + "loss": 1.2816, + "step": 8235 + }, + { + "epoch": 0.86, + "learning_rate": 1.1108832620773668e-06, + "loss": 1.3271, + "step": 8236 + }, + { + "epoch": 0.86, + "learning_rate": 1.1092071752043166e-06, + "loss": 1.3389, + "step": 8237 + }, + { + "epoch": 0.86, + "learning_rate": 1.1075322794690658e-06, + "loss": 1.3243, + "step": 8238 + }, + { + "epoch": 0.86, + "learning_rate": 1.1058585750960028e-06, + "loss": 1.2811, + "step": 8239 + }, + { + "epoch": 0.86, + "learning_rate": 1.1041860623093625e-06, + "loss": 1.3068, + "step": 8240 + }, + { + "epoch": 0.86, + "learning_rate": 1.1025147413332215e-06, + "loss": 1.3694, + "step": 8241 + }, + { + "epoch": 0.86, + "learning_rate": 1.1008446123914907e-06, + "loss": 1.3659, + "step": 8242 + }, + { + "epoch": 0.86, + "learning_rate": 1.0991756757079243e-06, + "loss": 1.3976, + "step": 8243 + }, + { + "epoch": 0.86, + "learning_rate": 1.097507931506121e-06, + "loss": 1.3445, + "step": 8244 + }, + { + "epoch": 0.86, + "learning_rate": 1.0958413800095102e-06, + "loss": 1.3606, + "step": 8245 + }, + { + "epoch": 0.86, + "learning_rate": 1.0941760214413721e-06, + "loss": 1.2929, + "step": 8246 + }, + { + "epoch": 0.86, + "learning_rate": 1.0925118560248172e-06, + "loss": 1.3275, + "step": 8247 + }, + { + "epoch": 0.86, + "learning_rate": 1.0908488839828024e-06, + "loss": 1.2897, + "step": 8248 + }, + { + "epoch": 0.87, + "learning_rate": 1.0891871055381264e-06, + "loss": 1.3044, + "step": 8249 + }, + { + "epoch": 0.87, + "learning_rate": 1.08752652091342e-06, + "loss": 1.3451, + "step": 8250 + }, + { + "epoch": 0.87, + "learning_rate": 1.085867130331162e-06, + "loss": 1.3619, + "step": 8251 + }, + { + "epoch": 0.87, + "learning_rate": 1.0842089340136685e-06, + "loss": 1.2743, + "step": 8252 + }, + { + "epoch": 0.87, + "learning_rate": 1.0825519321830925e-06, + "loss": 1.2792, + "step": 8253 + }, + { + "epoch": 0.87, + "learning_rate": 1.0808961250614335e-06, + "loss": 1.3186, + "step": 8254 + }, + { + "epoch": 0.87, + "learning_rate": 1.0792415128705224e-06, + "loss": 1.3143, + "step": 8255 + }, + { + "epoch": 0.87, + "learning_rate": 1.0775880958320362e-06, + "loss": 1.3303, + "step": 8256 + }, + { + "epoch": 0.87, + "learning_rate": 1.075935874167494e-06, + "loss": 1.2601, + "step": 8257 + }, + { + "epoch": 0.87, + "learning_rate": 1.0742848480982494e-06, + "loss": 1.3004, + "step": 8258 + }, + { + "epoch": 0.87, + "learning_rate": 1.0726350178454903e-06, + "loss": 1.2705, + "step": 8259 + }, + { + "epoch": 0.87, + "learning_rate": 1.0709863836302624e-06, + "loss": 1.2801, + "step": 8260 + }, + { + "epoch": 0.87, + "learning_rate": 1.0693389456734338e-06, + "loss": 1.322, + "step": 8261 + }, + { + "epoch": 0.87, + "learning_rate": 1.067692704195721e-06, + "loss": 1.2792, + "step": 8262 + }, + { + "epoch": 0.87, + "learning_rate": 1.0660476594176794e-06, + "loss": 1.3454, + "step": 8263 + }, + { + "epoch": 0.87, + "learning_rate": 1.0644038115596976e-06, + "loss": 1.2557, + "step": 8264 + }, + { + "epoch": 0.87, + "learning_rate": 1.0627611608420163e-06, + "loss": 1.3196, + "step": 8265 + }, + { + "epoch": 0.87, + "learning_rate": 1.0611197074847014e-06, + "loss": 1.3078, + "step": 8266 + }, + { + "epoch": 0.87, + "learning_rate": 1.059479451707669e-06, + "loss": 1.2815, + "step": 8267 + }, + { + "epoch": 0.87, + "learning_rate": 1.0578403937306726e-06, + "loss": 1.2226, + "step": 8268 + }, + { + "epoch": 0.87, + "learning_rate": 1.0562025337732995e-06, + "loss": 1.3396, + "step": 8269 + }, + { + "epoch": 0.87, + "learning_rate": 1.0545658720549844e-06, + "loss": 1.4786, + "step": 8270 + }, + { + "epoch": 0.87, + "learning_rate": 1.0529304087949988e-06, + "loss": 1.2319, + "step": 8271 + }, + { + "epoch": 0.87, + "learning_rate": 1.0512961442124492e-06, + "loss": 1.2866, + "step": 8272 + }, + { + "epoch": 0.87, + "learning_rate": 1.0496630785262874e-06, + "loss": 1.365, + "step": 8273 + }, + { + "epoch": 0.87, + "learning_rate": 1.0480312119553015e-06, + "loss": 1.3054, + "step": 8274 + }, + { + "epoch": 0.87, + "learning_rate": 1.046400544718118e-06, + "loss": 1.3268, + "step": 8275 + }, + { + "epoch": 0.87, + "learning_rate": 1.0447710770332098e-06, + "loss": 1.3574, + "step": 8276 + }, + { + "epoch": 0.87, + "learning_rate": 1.0431428091188766e-06, + "loss": 1.371, + "step": 8277 + }, + { + "epoch": 0.87, + "learning_rate": 1.0415157411932698e-06, + "loss": 1.3201, + "step": 8278 + }, + { + "epoch": 0.87, + "learning_rate": 1.0398898734743734e-06, + "loss": 1.3135, + "step": 8279 + }, + { + "epoch": 0.87, + "learning_rate": 1.0382652061800102e-06, + "loss": 1.2796, + "step": 8280 + }, + { + "epoch": 0.87, + "learning_rate": 1.036641739527846e-06, + "loss": 1.3704, + "step": 8281 + }, + { + "epoch": 0.87, + "learning_rate": 1.0350194737353814e-06, + "loss": 1.2913, + "step": 8282 + }, + { + "epoch": 0.87, + "learning_rate": 1.03339840901996e-06, + "loss": 1.3408, + "step": 8283 + }, + { + "epoch": 0.87, + "learning_rate": 1.0317785455987638e-06, + "loss": 1.2652, + "step": 8284 + }, + { + "epoch": 0.87, + "learning_rate": 1.0301598836888105e-06, + "loss": 1.2724, + "step": 8285 + }, + { + "epoch": 0.87, + "learning_rate": 1.0285424235069586e-06, + "loss": 1.2985, + "step": 8286 + }, + { + "epoch": 0.87, + "learning_rate": 1.0269261652699115e-06, + "loss": 1.3631, + "step": 8287 + }, + { + "epoch": 0.87, + "learning_rate": 1.0253111091941992e-06, + "loss": 1.2494, + "step": 8288 + }, + { + "epoch": 0.87, + "learning_rate": 1.0236972554962022e-06, + "loss": 1.3331, + "step": 8289 + }, + { + "epoch": 0.87, + "learning_rate": 1.0220846043921351e-06, + "loss": 1.2884, + "step": 8290 + }, + { + "epoch": 0.87, + "learning_rate": 1.0204731560980496e-06, + "loss": 1.3488, + "step": 8291 + }, + { + "epoch": 0.87, + "learning_rate": 1.018862910829842e-06, + "loss": 1.2698, + "step": 8292 + }, + { + "epoch": 0.87, + "learning_rate": 1.0172538688032396e-06, + "loss": 1.2873, + "step": 8293 + }, + { + "epoch": 0.87, + "learning_rate": 1.0156460302338135e-06, + "loss": 1.3644, + "step": 8294 + }, + { + "epoch": 0.87, + "learning_rate": 1.0140393953369764e-06, + "loss": 1.3445, + "step": 8295 + }, + { + "epoch": 0.87, + "learning_rate": 1.0124339643279724e-06, + "loss": 1.3448, + "step": 8296 + }, + { + "epoch": 0.87, + "learning_rate": 1.0108297374218877e-06, + "loss": 1.2984, + "step": 8297 + }, + { + "epoch": 0.87, + "learning_rate": 1.009226714833652e-06, + "loss": 1.3224, + "step": 8298 + }, + { + "epoch": 0.87, + "learning_rate": 1.0076248967780245e-06, + "loss": 1.2924, + "step": 8299 + }, + { + "epoch": 0.87, + "learning_rate": 1.00602428346961e-06, + "loss": 1.2344, + "step": 8300 + }, + { + "epoch": 0.87, + "learning_rate": 1.004424875122848e-06, + "loss": 1.3089, + "step": 8301 + }, + { + "epoch": 0.87, + "learning_rate": 1.0028266719520174e-06, + "loss": 1.291, + "step": 8302 + }, + { + "epoch": 0.87, + "learning_rate": 1.0012296741712414e-06, + "loss": 1.3404, + "step": 8303 + }, + { + "epoch": 0.87, + "learning_rate": 9.996338819944706e-07, + "loss": 1.5152, + "step": 8304 + }, + { + "epoch": 0.87, + "learning_rate": 9.980392956355023e-07, + "loss": 1.3492, + "step": 8305 + }, + { + "epoch": 0.87, + "learning_rate": 9.96445915307973e-07, + "loss": 1.3056, + "step": 8306 + }, + { + "epoch": 0.87, + "learning_rate": 9.948537412253502e-07, + "loss": 1.3223, + "step": 8307 + }, + { + "epoch": 0.87, + "learning_rate": 9.93262773600946e-07, + "loss": 1.3295, + "step": 8308 + }, + { + "epoch": 0.87, + "learning_rate": 9.916730126479113e-07, + "loss": 1.3156, + "step": 8309 + }, + { + "epoch": 0.87, + "learning_rate": 9.900844585792301e-07, + "loss": 1.2701, + "step": 8310 + }, + { + "epoch": 0.87, + "learning_rate": 9.884971116077302e-07, + "loss": 1.3171, + "step": 8311 + }, + { + "epoch": 0.87, + "learning_rate": 9.869109719460735e-07, + "loss": 1.2599, + "step": 8312 + }, + { + "epoch": 0.87, + "learning_rate": 9.85326039806762e-07, + "loss": 1.2999, + "step": 8313 + }, + { + "epoch": 0.87, + "learning_rate": 9.837423154021385e-07, + "loss": 1.3691, + "step": 8314 + }, + { + "epoch": 0.87, + "learning_rate": 9.821597989443775e-07, + "loss": 1.279, + "step": 8315 + }, + { + "epoch": 0.87, + "learning_rate": 9.805784906454985e-07, + "loss": 1.2682, + "step": 8316 + }, + { + "epoch": 0.87, + "learning_rate": 9.789983907173562e-07, + "loss": 1.3321, + "step": 8317 + }, + { + "epoch": 0.87, + "learning_rate": 9.774194993716413e-07, + "loss": 1.326, + "step": 8318 + }, + { + "epoch": 0.87, + "learning_rate": 9.75841816819887e-07, + "loss": 1.2541, + "step": 8319 + }, + { + "epoch": 0.87, + "learning_rate": 9.742653432734594e-07, + "loss": 1.2871, + "step": 8320 + }, + { + "epoch": 0.87, + "learning_rate": 9.726900789435668e-07, + "loss": 1.2535, + "step": 8321 + }, + { + "epoch": 0.87, + "learning_rate": 9.711160240412564e-07, + "loss": 1.3008, + "step": 8322 + }, + { + "epoch": 0.87, + "learning_rate": 9.695431787774068e-07, + "loss": 1.2925, + "step": 8323 + }, + { + "epoch": 0.87, + "learning_rate": 9.679715433627424e-07, + "loss": 1.4127, + "step": 8324 + }, + { + "epoch": 0.87, + "learning_rate": 9.664011180078215e-07, + "loss": 1.2961, + "step": 8325 + }, + { + "epoch": 0.87, + "learning_rate": 9.64831902923038e-07, + "loss": 1.2446, + "step": 8326 + }, + { + "epoch": 0.87, + "learning_rate": 9.632638983186316e-07, + "loss": 1.3279, + "step": 8327 + }, + { + "epoch": 0.87, + "learning_rate": 9.616971044046686e-07, + "loss": 1.3128, + "step": 8328 + }, + { + "epoch": 0.87, + "learning_rate": 9.601315213910622e-07, + "loss": 1.2371, + "step": 8329 + }, + { + "epoch": 0.87, + "learning_rate": 9.585671494875614e-07, + "loss": 1.2844, + "step": 8330 + }, + { + "epoch": 0.87, + "learning_rate": 9.570039889037485e-07, + "loss": 1.3417, + "step": 8331 + }, + { + "epoch": 0.87, + "learning_rate": 9.554420398490494e-07, + "loss": 1.3149, + "step": 8332 + }, + { + "epoch": 0.87, + "learning_rate": 9.538813025327266e-07, + "loss": 1.2588, + "step": 8333 + }, + { + "epoch": 0.87, + "learning_rate": 9.523217771638748e-07, + "loss": 1.2999, + "step": 8334 + }, + { + "epoch": 0.87, + "learning_rate": 9.507634639514319e-07, + "loss": 1.4602, + "step": 8335 + }, + { + "epoch": 0.87, + "learning_rate": 9.492063631041737e-07, + "loss": 1.3576, + "step": 8336 + }, + { + "epoch": 0.87, + "learning_rate": 9.476504748307091e-07, + "loss": 1.3507, + "step": 8337 + }, + { + "epoch": 0.87, + "learning_rate": 9.460957993394903e-07, + "loss": 1.3293, + "step": 8338 + }, + { + "epoch": 0.87, + "learning_rate": 9.445423368387995e-07, + "loss": 1.3586, + "step": 8339 + }, + { + "epoch": 0.87, + "learning_rate": 9.429900875367637e-07, + "loss": 1.4114, + "step": 8340 + }, + { + "epoch": 0.87, + "learning_rate": 9.414390516413452e-07, + "loss": 1.3932, + "step": 8341 + }, + { + "epoch": 0.87, + "learning_rate": 9.398892293603401e-07, + "loss": 1.357, + "step": 8342 + }, + { + "epoch": 0.87, + "learning_rate": 9.383406209013856e-07, + "loss": 1.2858, + "step": 8343 + }, + { + "epoch": 0.88, + "learning_rate": 9.367932264719581e-07, + "loss": 1.2484, + "step": 8344 + }, + { + "epoch": 0.88, + "learning_rate": 9.352470462793651e-07, + "loss": 1.3251, + "step": 8345 + }, + { + "epoch": 0.88, + "learning_rate": 9.337020805307583e-07, + "loss": 1.2653, + "step": 8346 + }, + { + "epoch": 0.88, + "learning_rate": 9.321583294331204e-07, + "loss": 1.2925, + "step": 8347 + }, + { + "epoch": 0.88, + "learning_rate": 9.306157931932758e-07, + "loss": 1.3092, + "step": 8348 + }, + { + "epoch": 0.88, + "learning_rate": 9.290744720178857e-07, + "loss": 1.3858, + "step": 8349 + }, + { + "epoch": 0.88, + "learning_rate": 9.275343661134451e-07, + "loss": 1.2612, + "step": 8350 + }, + { + "epoch": 0.88, + "learning_rate": 9.259954756862899e-07, + "loss": 1.3053, + "step": 8351 + }, + { + "epoch": 0.88, + "learning_rate": 9.244578009425942e-07, + "loss": 1.3401, + "step": 8352 + }, + { + "epoch": 0.88, + "learning_rate": 9.229213420883621e-07, + "loss": 1.3442, + "step": 8353 + }, + { + "epoch": 0.88, + "learning_rate": 9.213860993294421e-07, + "loss": 1.3501, + "step": 8354 + }, + { + "epoch": 0.88, + "learning_rate": 9.198520728715199e-07, + "loss": 1.2916, + "step": 8355 + }, + { + "epoch": 0.88, + "learning_rate": 9.18319262920111e-07, + "loss": 1.3291, + "step": 8356 + }, + { + "epoch": 0.88, + "learning_rate": 9.167876696805767e-07, + "loss": 1.3369, + "step": 8357 + }, + { + "epoch": 0.88, + "learning_rate": 9.152572933581061e-07, + "loss": 1.3324, + "step": 8358 + }, + { + "epoch": 0.88, + "eval_loss": 1.3944451808929443, + "eval_runtime": 77.5126, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 8358 + }, + { + "epoch": 0.88, + "learning_rate": 9.137281341577342e-07, + "loss": 1.3, + "step": 8359 + }, + { + "epoch": 0.88, + "learning_rate": 9.122001922843304e-07, + "loss": 1.2892, + "step": 8360 + }, + { + "epoch": 0.88, + "learning_rate": 9.106734679425944e-07, + "loss": 1.2715, + "step": 8361 + }, + { + "epoch": 0.88, + "learning_rate": 9.091479613370723e-07, + "loss": 1.2606, + "step": 8362 + }, + { + "epoch": 0.88, + "learning_rate": 9.076236726721421e-07, + "loss": 1.2707, + "step": 8363 + }, + { + "epoch": 0.88, + "learning_rate": 9.06100602152018e-07, + "loss": 1.3153, + "step": 8364 + }, + { + "epoch": 0.88, + "learning_rate": 9.045787499807545e-07, + "loss": 1.3709, + "step": 8365 + }, + { + "epoch": 0.88, + "learning_rate": 9.030581163622365e-07, + "loss": 1.3828, + "step": 8366 + }, + { + "epoch": 0.88, + "learning_rate": 9.015387015001942e-07, + "loss": 1.2626, + "step": 8367 + }, + { + "epoch": 0.88, + "learning_rate": 9.000205055981892e-07, + "loss": 1.3162, + "step": 8368 + }, + { + "epoch": 0.88, + "learning_rate": 8.985035288596178e-07, + "loss": 1.2654, + "step": 8369 + }, + { + "epoch": 0.88, + "learning_rate": 8.969877714877195e-07, + "loss": 1.3058, + "step": 8370 + }, + { + "epoch": 0.88, + "learning_rate": 8.954732336855665e-07, + "loss": 1.2438, + "step": 8371 + }, + { + "epoch": 0.88, + "learning_rate": 8.939599156560652e-07, + "loss": 1.3767, + "step": 8372 + }, + { + "epoch": 0.88, + "learning_rate": 8.924478176019647e-07, + "loss": 1.3284, + "step": 8373 + }, + { + "epoch": 0.88, + "learning_rate": 8.90936939725845e-07, + "loss": 1.3417, + "step": 8374 + }, + { + "epoch": 0.88, + "learning_rate": 8.894272822301242e-07, + "loss": 1.3662, + "step": 8375 + }, + { + "epoch": 0.88, + "learning_rate": 8.879188453170606e-07, + "loss": 1.2383, + "step": 8376 + }, + { + "epoch": 0.88, + "learning_rate": 8.864116291887437e-07, + "loss": 1.2515, + "step": 8377 + }, + { + "epoch": 0.88, + "learning_rate": 8.849056340471018e-07, + "loss": 1.356, + "step": 8378 + }, + { + "epoch": 0.88, + "learning_rate": 8.834008600939025e-07, + "loss": 1.3366, + "step": 8379 + }, + { + "epoch": 0.88, + "learning_rate": 8.818973075307424e-07, + "loss": 1.2689, + "step": 8380 + }, + { + "epoch": 0.88, + "learning_rate": 8.803949765590614e-07, + "loss": 1.3408, + "step": 8381 + }, + { + "epoch": 0.88, + "learning_rate": 8.788938673801339e-07, + "loss": 1.3399, + "step": 8382 + }, + { + "epoch": 0.88, + "learning_rate": 8.773939801950671e-07, + "loss": 1.2561, + "step": 8383 + }, + { + "epoch": 0.88, + "learning_rate": 8.758953152048121e-07, + "loss": 1.3255, + "step": 8384 + }, + { + "epoch": 0.88, + "learning_rate": 8.743978726101454e-07, + "loss": 1.2811, + "step": 8385 + }, + { + "epoch": 0.88, + "learning_rate": 8.729016526116907e-07, + "loss": 1.3295, + "step": 8386 + }, + { + "epoch": 0.88, + "learning_rate": 8.714066554099021e-07, + "loss": 1.2932, + "step": 8387 + }, + { + "epoch": 0.88, + "learning_rate": 8.699128812050683e-07, + "loss": 1.335, + "step": 8388 + }, + { + "epoch": 0.88, + "learning_rate": 8.684203301973182e-07, + "loss": 1.3336, + "step": 8389 + }, + { + "epoch": 0.88, + "learning_rate": 8.669290025866173e-07, + "loss": 1.3123, + "step": 8390 + }, + { + "epoch": 0.88, + "learning_rate": 8.654388985727624e-07, + "loss": 1.4056, + "step": 8391 + }, + { + "epoch": 0.88, + "learning_rate": 8.639500183553917e-07, + "loss": 1.2079, + "step": 8392 + }, + { + "epoch": 0.88, + "learning_rate": 8.624623621339723e-07, + "loss": 1.3789, + "step": 8393 + }, + { + "epoch": 0.88, + "learning_rate": 8.609759301078168e-07, + "loss": 1.2845, + "step": 8394 + }, + { + "epoch": 0.88, + "learning_rate": 8.594907224760674e-07, + "loss": 1.2322, + "step": 8395 + }, + { + "epoch": 0.88, + "learning_rate": 8.580067394377023e-07, + "loss": 1.2595, + "step": 8396 + }, + { + "epoch": 0.88, + "learning_rate": 8.565239811915382e-07, + "loss": 1.2703, + "step": 8397 + }, + { + "epoch": 0.88, + "learning_rate": 8.550424479362285e-07, + "loss": 1.2627, + "step": 8398 + }, + { + "epoch": 0.88, + "learning_rate": 8.535621398702565e-07, + "loss": 1.311, + "step": 8399 + }, + { + "epoch": 0.88, + "learning_rate": 8.520830571919481e-07, + "loss": 1.2656, + "step": 8400 + }, + { + "epoch": 0.88, + "learning_rate": 8.506052000994636e-07, + "loss": 1.2514, + "step": 8401 + }, + { + "epoch": 0.88, + "learning_rate": 8.491285687907935e-07, + "loss": 1.2494, + "step": 8402 + }, + { + "epoch": 0.88, + "learning_rate": 8.476531634637741e-07, + "loss": 0.9287, + "step": 8403 + }, + { + "epoch": 0.88, + "learning_rate": 8.461789843160662e-07, + "loss": 0.6155, + "step": 8404 + }, + { + "epoch": 0.88, + "learning_rate": 8.44706031545176e-07, + "loss": 0.9869, + "step": 8405 + }, + { + "epoch": 0.88, + "learning_rate": 8.432343053484404e-07, + "loss": 1.3074, + "step": 8406 + }, + { + "epoch": 0.88, + "learning_rate": 8.417638059230305e-07, + "loss": 1.3175, + "step": 8407 + }, + { + "epoch": 0.88, + "learning_rate": 8.402945334659584e-07, + "loss": 1.2605, + "step": 8408 + }, + { + "epoch": 0.88, + "learning_rate": 8.388264881740693e-07, + "loss": 1.3429, + "step": 8409 + }, + { + "epoch": 0.88, + "learning_rate": 8.373596702440401e-07, + "loss": 1.2985, + "step": 8410 + }, + { + "epoch": 0.88, + "learning_rate": 8.358940798723903e-07, + "loss": 1.2686, + "step": 8411 + }, + { + "epoch": 0.88, + "learning_rate": 8.344297172554672e-07, + "loss": 1.353, + "step": 8412 + }, + { + "epoch": 0.88, + "learning_rate": 8.329665825894617e-07, + "loss": 1.3329, + "step": 8413 + }, + { + "epoch": 0.88, + "learning_rate": 8.31504676070396e-07, + "loss": 1.3813, + "step": 8414 + }, + { + "epoch": 0.88, + "learning_rate": 8.300439978941244e-07, + "loss": 1.2658, + "step": 8415 + }, + { + "epoch": 0.88, + "learning_rate": 8.285845482563437e-07, + "loss": 1.2827, + "step": 8416 + }, + { + "epoch": 0.88, + "learning_rate": 8.271263273525832e-07, + "loss": 1.2247, + "step": 8417 + }, + { + "epoch": 0.88, + "learning_rate": 8.256693353782042e-07, + "loss": 1.29, + "step": 8418 + }, + { + "epoch": 0.88, + "learning_rate": 8.242135725284084e-07, + "loss": 1.3085, + "step": 8419 + }, + { + "epoch": 0.88, + "learning_rate": 8.227590389982276e-07, + "loss": 1.2828, + "step": 8420 + }, + { + "epoch": 0.88, + "learning_rate": 8.213057349825348e-07, + "loss": 1.3721, + "step": 8421 + }, + { + "epoch": 0.88, + "learning_rate": 8.198536606760366e-07, + "loss": 1.3304, + "step": 8422 + }, + { + "epoch": 0.88, + "learning_rate": 8.184028162732694e-07, + "loss": 1.3184, + "step": 8423 + }, + { + "epoch": 0.88, + "learning_rate": 8.16953201968611e-07, + "loss": 1.3326, + "step": 8424 + }, + { + "epoch": 0.88, + "learning_rate": 8.155048179562752e-07, + "loss": 1.3035, + "step": 8425 + }, + { + "epoch": 0.88, + "learning_rate": 8.140576644303033e-07, + "loss": 1.155, + "step": 8426 + }, + { + "epoch": 0.88, + "learning_rate": 8.126117415845802e-07, + "loss": 1.2749, + "step": 8427 + }, + { + "epoch": 0.88, + "learning_rate": 8.111670496128222e-07, + "loss": 1.2703, + "step": 8428 + }, + { + "epoch": 0.88, + "learning_rate": 8.097235887085786e-07, + "loss": 1.4058, + "step": 8429 + }, + { + "epoch": 0.88, + "learning_rate": 8.082813590652405e-07, + "loss": 1.2774, + "step": 8430 + }, + { + "epoch": 0.88, + "learning_rate": 8.068403608760233e-07, + "loss": 1.2792, + "step": 8431 + }, + { + "epoch": 0.88, + "learning_rate": 8.054005943339883e-07, + "loss": 1.3317, + "step": 8432 + }, + { + "epoch": 0.88, + "learning_rate": 8.039620596320275e-07, + "loss": 1.2015, + "step": 8433 + }, + { + "epoch": 0.88, + "learning_rate": 8.025247569628647e-07, + "loss": 1.2729, + "step": 8434 + }, + { + "epoch": 0.88, + "learning_rate": 8.010886865190626e-07, + "loss": 1.2649, + "step": 8435 + }, + { + "epoch": 0.88, + "learning_rate": 7.996538484930194e-07, + "loss": 1.3821, + "step": 8436 + }, + { + "epoch": 0.88, + "learning_rate": 7.982202430769648e-07, + "loss": 1.3019, + "step": 8437 + }, + { + "epoch": 0.88, + "learning_rate": 7.967878704629662e-07, + "loss": 1.2648, + "step": 8438 + }, + { + "epoch": 0.88, + "learning_rate": 7.953567308429222e-07, + "loss": 1.2948, + "step": 8439 + }, + { + "epoch": 0.89, + "learning_rate": 7.939268244085718e-07, + "loss": 1.2666, + "step": 8440 + }, + { + "epoch": 0.89, + "learning_rate": 7.924981513514851e-07, + "loss": 1.3525, + "step": 8441 + }, + { + "epoch": 0.89, + "learning_rate": 7.910707118630667e-07, + "loss": 1.2863, + "step": 8442 + }, + { + "epoch": 0.89, + "learning_rate": 7.896445061345559e-07, + "loss": 1.2562, + "step": 8443 + }, + { + "epoch": 0.89, + "learning_rate": 7.882195343570309e-07, + "loss": 1.2945, + "step": 8444 + }, + { + "epoch": 0.89, + "learning_rate": 7.86795796721398e-07, + "loss": 1.3206, + "step": 8445 + }, + { + "epoch": 0.89, + "learning_rate": 7.853732934184022e-07, + "loss": 1.2354, + "step": 8446 + }, + { + "epoch": 0.89, + "learning_rate": 7.839520246386245e-07, + "loss": 1.2769, + "step": 8447 + }, + { + "epoch": 0.89, + "learning_rate": 7.825319905724749e-07, + "loss": 1.2897, + "step": 8448 + }, + { + "epoch": 0.89, + "learning_rate": 7.811131914102055e-07, + "loss": 1.2605, + "step": 8449 + }, + { + "epoch": 0.89, + "learning_rate": 7.796956273418954e-07, + "loss": 1.2689, + "step": 8450 + }, + { + "epoch": 0.89, + "learning_rate": 7.782792985574628e-07, + "loss": 1.2753, + "step": 8451 + }, + { + "epoch": 0.89, + "learning_rate": 7.768642052466624e-07, + "loss": 1.3375, + "step": 8452 + }, + { + "epoch": 0.89, + "learning_rate": 7.754503475990749e-07, + "loss": 1.2566, + "step": 8453 + }, + { + "epoch": 0.89, + "learning_rate": 7.740377258041242e-07, + "loss": 1.3821, + "step": 8454 + }, + { + "epoch": 0.89, + "learning_rate": 7.726263400510659e-07, + "loss": 1.2773, + "step": 8455 + }, + { + "epoch": 0.89, + "learning_rate": 7.712161905289872e-07, + "loss": 1.3096, + "step": 8456 + }, + { + "epoch": 0.89, + "learning_rate": 7.698072774268151e-07, + "loss": 1.2952, + "step": 8457 + }, + { + "epoch": 0.89, + "learning_rate": 7.683996009333028e-07, + "loss": 1.3119, + "step": 8458 + }, + { + "epoch": 0.89, + "learning_rate": 7.669931612370463e-07, + "loss": 1.244, + "step": 8459 + }, + { + "epoch": 0.89, + "learning_rate": 7.655879585264736e-07, + "loss": 1.3594, + "step": 8460 + }, + { + "epoch": 0.89, + "learning_rate": 7.64183992989842e-07, + "loss": 1.3677, + "step": 8461 + }, + { + "epoch": 0.89, + "learning_rate": 7.627812648152488e-07, + "loss": 1.3049, + "step": 8462 + }, + { + "epoch": 0.89, + "learning_rate": 7.61379774190626e-07, + "loss": 1.2744, + "step": 8463 + }, + { + "epoch": 0.89, + "learning_rate": 7.59979521303732e-07, + "loss": 1.3516, + "step": 8464 + }, + { + "epoch": 0.89, + "learning_rate": 7.585805063421703e-07, + "loss": 1.4835, + "step": 8465 + }, + { + "epoch": 0.89, + "learning_rate": 7.571827294933675e-07, + "loss": 1.3016, + "step": 8466 + }, + { + "epoch": 0.89, + "learning_rate": 7.55786190944593e-07, + "loss": 1.2985, + "step": 8467 + }, + { + "epoch": 0.89, + "learning_rate": 7.543908908829478e-07, + "loss": 1.3137, + "step": 8468 + }, + { + "epoch": 0.89, + "learning_rate": 7.529968294953627e-07, + "loss": 1.3084, + "step": 8469 + }, + { + "epoch": 0.89, + "learning_rate": 7.516040069686092e-07, + "loss": 1.3923, + "step": 8470 + }, + { + "epoch": 0.89, + "learning_rate": 7.502124234892905e-07, + "loss": 1.3569, + "step": 8471 + }, + { + "epoch": 0.89, + "learning_rate": 7.488220792438405e-07, + "loss": 1.2567, + "step": 8472 + }, + { + "epoch": 0.89, + "learning_rate": 7.474329744185294e-07, + "loss": 1.2666, + "step": 8473 + }, + { + "epoch": 0.89, + "learning_rate": 7.460451091994647e-07, + "loss": 1.3691, + "step": 8474 + }, + { + "epoch": 0.89, + "learning_rate": 7.446584837725812e-07, + "loss": 1.2708, + "step": 8475 + }, + { + "epoch": 0.89, + "learning_rate": 7.432730983236547e-07, + "loss": 1.3529, + "step": 8476 + }, + { + "epoch": 0.89, + "learning_rate": 7.418889530382866e-07, + "loss": 1.298, + "step": 8477 + }, + { + "epoch": 0.89, + "learning_rate": 7.405060481019199e-07, + "loss": 1.2789, + "step": 8478 + }, + { + "epoch": 0.89, + "learning_rate": 7.391243836998296e-07, + "loss": 1.3352, + "step": 8479 + }, + { + "epoch": 0.89, + "learning_rate": 7.377439600171199e-07, + "loss": 1.3876, + "step": 8480 + }, + { + "epoch": 0.89, + "learning_rate": 7.363647772387328e-07, + "loss": 1.3081, + "step": 8481 + }, + { + "epoch": 0.89, + "learning_rate": 7.349868355494461e-07, + "loss": 1.2536, + "step": 8482 + }, + { + "epoch": 0.89, + "learning_rate": 7.336101351338654e-07, + "loss": 1.3303, + "step": 8483 + }, + { + "epoch": 0.89, + "learning_rate": 7.322346761764354e-07, + "loss": 1.2785, + "step": 8484 + }, + { + "epoch": 0.89, + "learning_rate": 7.308604588614298e-07, + "loss": 1.3334, + "step": 8485 + }, + { + "epoch": 0.89, + "learning_rate": 7.294874833729603e-07, + "loss": 1.2595, + "step": 8486 + }, + { + "epoch": 0.89, + "learning_rate": 7.281157498949709e-07, + "loss": 1.2814, + "step": 8487 + }, + { + "epoch": 0.89, + "learning_rate": 7.267452586112367e-07, + "loss": 1.3282, + "step": 8488 + }, + { + "epoch": 0.89, + "learning_rate": 7.253760097053686e-07, + "loss": 1.3333, + "step": 8489 + }, + { + "epoch": 0.89, + "learning_rate": 7.240080033608133e-07, + "loss": 1.3541, + "step": 8490 + }, + { + "epoch": 0.89, + "learning_rate": 7.226412397608451e-07, + "loss": 1.3371, + "step": 8491 + }, + { + "epoch": 0.89, + "learning_rate": 7.212757190885767e-07, + "loss": 1.2419, + "step": 8492 + }, + { + "epoch": 0.89, + "learning_rate": 7.199114415269548e-07, + "loss": 1.2842, + "step": 8493 + }, + { + "epoch": 0.89, + "learning_rate": 7.185484072587545e-07, + "loss": 1.283, + "step": 8494 + }, + { + "epoch": 0.89, + "learning_rate": 7.171866164665886e-07, + "loss": 1.1896, + "step": 8495 + }, + { + "epoch": 0.89, + "learning_rate": 7.158260693329011e-07, + "loss": 1.3974, + "step": 8496 + }, + { + "epoch": 0.89, + "learning_rate": 7.144667660399717e-07, + "loss": 1.3376, + "step": 8497 + }, + { + "epoch": 0.89, + "learning_rate": 7.131087067699127e-07, + "loss": 1.2702, + "step": 8498 + }, + { + "epoch": 0.89, + "learning_rate": 7.117518917046662e-07, + "loss": 1.287, + "step": 8499 + }, + { + "epoch": 0.89, + "learning_rate": 7.103963210260123e-07, + "loss": 1.2826, + "step": 8500 + }, + { + "epoch": 0.89, + "learning_rate": 7.090419949155647e-07, + "loss": 1.3345, + "step": 8501 + }, + { + "epoch": 0.89, + "learning_rate": 7.076889135547649e-07, + "loss": 1.2774, + "step": 8502 + }, + { + "epoch": 0.89, + "learning_rate": 7.063370771248934e-07, + "loss": 1.3094, + "step": 8503 + }, + { + "epoch": 0.89, + "learning_rate": 7.049864858070599e-07, + "loss": 1.3025, + "step": 8504 + }, + { + "epoch": 0.89, + "learning_rate": 7.036371397822095e-07, + "loss": 1.2819, + "step": 8505 + }, + { + "epoch": 0.89, + "learning_rate": 7.02289039231121e-07, + "loss": 1.3229, + "step": 8506 + }, + { + "epoch": 0.89, + "learning_rate": 7.009421843344033e-07, + "loss": 1.2722, + "step": 8507 + }, + { + "epoch": 0.89, + "learning_rate": 6.995965752725009e-07, + "loss": 1.2996, + "step": 8508 + }, + { + "epoch": 0.89, + "learning_rate": 6.982522122256929e-07, + "loss": 1.2642, + "step": 8509 + }, + { + "epoch": 0.89, + "learning_rate": 6.969090953740865e-07, + "loss": 1.3545, + "step": 8510 + }, + { + "epoch": 0.89, + "learning_rate": 6.955672248976286e-07, + "loss": 1.3123, + "step": 8511 + }, + { + "epoch": 0.89, + "learning_rate": 6.942266009760901e-07, + "loss": 1.2652, + "step": 8512 + }, + { + "epoch": 0.89, + "learning_rate": 6.928872237890826e-07, + "loss": 1.253, + "step": 8513 + }, + { + "epoch": 0.89, + "learning_rate": 6.915490935160518e-07, + "loss": 1.2942, + "step": 8514 + }, + { + "epoch": 0.89, + "learning_rate": 6.902122103362663e-07, + "loss": 1.2654, + "step": 8515 + }, + { + "epoch": 0.89, + "learning_rate": 6.888765744288384e-07, + "loss": 1.2584, + "step": 8516 + }, + { + "epoch": 0.89, + "learning_rate": 6.875421859727094e-07, + "loss": 1.2705, + "step": 8517 + }, + { + "epoch": 0.89, + "learning_rate": 6.862090451466497e-07, + "loss": 1.2818, + "step": 8518 + }, + { + "epoch": 0.89, + "learning_rate": 6.848771521292686e-07, + "loss": 1.2926, + "step": 8519 + }, + { + "epoch": 0.89, + "learning_rate": 6.835465070990055e-07, + "loss": 1.3328, + "step": 8520 + }, + { + "epoch": 0.89, + "learning_rate": 6.822171102341302e-07, + "loss": 1.2258, + "step": 8521 + }, + { + "epoch": 0.89, + "learning_rate": 6.808889617127523e-07, + "loss": 1.2564, + "step": 8522 + }, + { + "epoch": 0.89, + "learning_rate": 6.79562061712804e-07, + "loss": 1.2874, + "step": 8523 + }, + { + "epoch": 0.89, + "learning_rate": 6.782364104120587e-07, + "loss": 1.3414, + "step": 8524 + }, + { + "epoch": 0.89, + "learning_rate": 6.769120079881209e-07, + "loss": 1.283, + "step": 8525 + }, + { + "epoch": 0.89, + "learning_rate": 6.755888546184242e-07, + "loss": 1.3711, + "step": 8526 + }, + { + "epoch": 0.89, + "learning_rate": 6.742669504802379e-07, + "loss": 1.2608, + "step": 8527 + }, + { + "epoch": 0.89, + "learning_rate": 6.729462957506638e-07, + "loss": 1.219, + "step": 8528 + }, + { + "epoch": 0.89, + "learning_rate": 6.716268906066348e-07, + "loss": 1.3034, + "step": 8529 + }, + { + "epoch": 0.89, + "learning_rate": 6.703087352249183e-07, + "loss": 1.32, + "step": 8530 + }, + { + "epoch": 0.89, + "learning_rate": 6.689918297821119e-07, + "loss": 1.3378, + "step": 8531 + }, + { + "epoch": 0.89, + "learning_rate": 6.676761744546478e-07, + "loss": 1.4375, + "step": 8532 + }, + { + "epoch": 0.89, + "learning_rate": 6.663617694187907e-07, + "loss": 1.285, + "step": 8533 + }, + { + "epoch": 0.89, + "learning_rate": 6.650486148506352e-07, + "loss": 1.3853, + "step": 8534 + }, + { + "epoch": 0.9, + "learning_rate": 6.637367109261117e-07, + "loss": 1.3802, + "step": 8535 + }, + { + "epoch": 0.9, + "learning_rate": 6.62426057820983e-07, + "loss": 1.2851, + "step": 8536 + }, + { + "epoch": 0.9, + "learning_rate": 6.611166557108406e-07, + "loss": 1.2538, + "step": 8537 + }, + { + "epoch": 0.9, + "learning_rate": 6.5980850477111e-07, + "loss": 1.3407, + "step": 8538 + }, + { + "epoch": 0.9, + "learning_rate": 6.585016051770543e-07, + "loss": 1.2401, + "step": 8539 + }, + { + "epoch": 0.9, + "learning_rate": 6.57195957103759e-07, + "loss": 1.3364, + "step": 8540 + }, + { + "epoch": 0.9, + "learning_rate": 6.558915607261517e-07, + "loss": 1.2885, + "step": 8541 + }, + { + "epoch": 0.9, + "learning_rate": 6.545884162189841e-07, + "loss": 1.3406, + "step": 8542 + }, + { + "epoch": 0.9, + "learning_rate": 6.532865237568465e-07, + "loss": 1.3203, + "step": 8543 + }, + { + "epoch": 0.9, + "learning_rate": 6.519858835141601e-07, + "loss": 1.268, + "step": 8544 + }, + { + "epoch": 0.9, + "learning_rate": 6.506864956651749e-07, + "loss": 1.3219, + "step": 8545 + }, + { + "epoch": 0.9, + "learning_rate": 6.493883603839757e-07, + "loss": 1.222, + "step": 8546 + }, + { + "epoch": 0.9, + "learning_rate": 6.480914778444824e-07, + "loss": 1.2386, + "step": 8547 + }, + { + "epoch": 0.9, + "learning_rate": 6.467958482204396e-07, + "loss": 1.3695, + "step": 8548 + }, + { + "epoch": 0.9, + "learning_rate": 6.455014716854324e-07, + "loss": 1.2788, + "step": 8549 + }, + { + "epoch": 0.9, + "learning_rate": 6.442083484128692e-07, + "loss": 1.3252, + "step": 8550 + }, + { + "epoch": 0.9, + "learning_rate": 6.429164785759989e-07, + "loss": 1.366, + "step": 8551 + }, + { + "epoch": 0.9, + "learning_rate": 6.416258623478988e-07, + "loss": 1.329, + "step": 8552 + }, + { + "epoch": 0.9, + "learning_rate": 6.403364999014771e-07, + "loss": 1.3641, + "step": 8553 + }, + { + "epoch": 0.9, + "learning_rate": 6.390483914094747e-07, + "loss": 1.3228, + "step": 8554 + }, + { + "epoch": 0.9, + "learning_rate": 6.377615370444678e-07, + "loss": 1.283, + "step": 8555 + }, + { + "epoch": 0.9, + "learning_rate": 6.364759369788587e-07, + "loss": 1.3105, + "step": 8556 + }, + { + "epoch": 0.9, + "learning_rate": 6.351915913848882e-07, + "loss": 1.3446, + "step": 8557 + }, + { + "epoch": 0.9, + "eval_loss": 1.3943825960159302, + "eval_runtime": 77.555, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 8557 + }, + { + "epoch": 0.9, + "learning_rate": 6.339085004346213e-07, + "loss": 1.3038, + "step": 8558 + }, + { + "epoch": 0.9, + "learning_rate": 6.326266642999612e-07, + "loss": 1.3111, + "step": 8559 + }, + { + "epoch": 0.9, + "learning_rate": 6.31346083152643e-07, + "loss": 1.3205, + "step": 8560 + }, + { + "epoch": 0.9, + "learning_rate": 6.300667571642283e-07, + "loss": 1.2894, + "step": 8561 + }, + { + "epoch": 0.9, + "learning_rate": 6.287886865061155e-07, + "loss": 1.2867, + "step": 8562 + }, + { + "epoch": 0.9, + "learning_rate": 6.275118713495343e-07, + "loss": 1.2754, + "step": 8563 + }, + { + "epoch": 0.9, + "learning_rate": 6.262363118655434e-07, + "loss": 1.3261, + "step": 8564 + }, + { + "epoch": 0.9, + "learning_rate": 6.249620082250351e-07, + "loss": 1.2957, + "step": 8565 + }, + { + "epoch": 0.9, + "learning_rate": 6.236889605987351e-07, + "loss": 1.3127, + "step": 8566 + }, + { + "epoch": 0.9, + "learning_rate": 6.224171691571967e-07, + "loss": 1.2833, + "step": 8567 + }, + { + "epoch": 0.9, + "learning_rate": 6.211466340708105e-07, + "loss": 1.319, + "step": 8568 + }, + { + "epoch": 0.9, + "learning_rate": 6.198773555097914e-07, + "loss": 1.3115, + "step": 8569 + }, + { + "epoch": 0.9, + "learning_rate": 6.186093336441922e-07, + "loss": 1.6219, + "step": 8570 + }, + { + "epoch": 0.9, + "learning_rate": 6.173425686438972e-07, + "loss": 1.284, + "step": 8571 + }, + { + "epoch": 0.9, + "learning_rate": 6.160770606786171e-07, + "loss": 1.3606, + "step": 8572 + }, + { + "epoch": 0.9, + "learning_rate": 6.148128099178974e-07, + "loss": 1.3493, + "step": 8573 + }, + { + "epoch": 0.9, + "learning_rate": 6.135498165311193e-07, + "loss": 1.292, + "step": 8574 + }, + { + "epoch": 0.9, + "learning_rate": 6.122880806874875e-07, + "loss": 1.2998, + "step": 8575 + }, + { + "epoch": 0.9, + "learning_rate": 6.110276025560446e-07, + "loss": 1.2683, + "step": 8576 + }, + { + "epoch": 0.9, + "learning_rate": 6.097683823056589e-07, + "loss": 1.3264, + "step": 8577 + }, + { + "epoch": 0.9, + "learning_rate": 6.085104201050363e-07, + "loss": 1.2534, + "step": 8578 + }, + { + "epoch": 0.9, + "learning_rate": 6.072537161227121e-07, + "loss": 1.3249, + "step": 8579 + }, + { + "epoch": 0.9, + "learning_rate": 6.059982705270507e-07, + "loss": 1.2675, + "step": 8580 + }, + { + "epoch": 0.9, + "learning_rate": 6.047440834862495e-07, + "loss": 1.2406, + "step": 8581 + }, + { + "epoch": 0.9, + "learning_rate": 6.034911551683387e-07, + "loss": 1.3016, + "step": 8582 + }, + { + "epoch": 0.9, + "learning_rate": 6.022394857411762e-07, + "loss": 1.1855, + "step": 8583 + }, + { + "epoch": 0.9, + "learning_rate": 6.009890753724556e-07, + "loss": 1.3572, + "step": 8584 + }, + { + "epoch": 0.9, + "learning_rate": 5.997399242297009e-07, + "loss": 1.2925, + "step": 8585 + }, + { + "epoch": 0.9, + "learning_rate": 5.984920324802624e-07, + "loss": 1.2864, + "step": 8586 + }, + { + "epoch": 0.9, + "learning_rate": 5.972454002913286e-07, + "loss": 1.4783, + "step": 8587 + }, + { + "epoch": 0.9, + "learning_rate": 5.960000278299139e-07, + "loss": 1.273, + "step": 8588 + }, + { + "epoch": 0.9, + "learning_rate": 5.94755915262868e-07, + "loss": 1.2771, + "step": 8589 + }, + { + "epoch": 0.9, + "learning_rate": 5.935130627568708e-07, + "loss": 1.2951, + "step": 8590 + }, + { + "epoch": 0.9, + "learning_rate": 5.922714704784304e-07, + "loss": 1.2976, + "step": 8591 + }, + { + "epoch": 0.9, + "learning_rate": 5.910311385938893e-07, + "loss": 1.3319, + "step": 8592 + }, + { + "epoch": 0.9, + "learning_rate": 5.897920672694202e-07, + "loss": 1.1034, + "step": 8593 + }, + { + "epoch": 0.9, + "learning_rate": 5.885542566710267e-07, + "loss": 1.2838, + "step": 8594 + }, + { + "epoch": 0.9, + "learning_rate": 5.873177069645442e-07, + "loss": 1.3344, + "step": 8595 + }, + { + "epoch": 0.9, + "learning_rate": 5.860824183156356e-07, + "loss": 1.3194, + "step": 8596 + }, + { + "epoch": 0.9, + "learning_rate": 5.848483908898017e-07, + "loss": 1.3043, + "step": 8597 + }, + { + "epoch": 0.9, + "learning_rate": 5.836156248523694e-07, + "loss": 1.3296, + "step": 8598 + }, + { + "epoch": 0.9, + "learning_rate": 5.823841203684965e-07, + "loss": 1.3101, + "step": 8599 + }, + { + "epoch": 0.9, + "learning_rate": 5.811538776031733e-07, + "loss": 1.2394, + "step": 8600 + }, + { + "epoch": 0.9, + "learning_rate": 5.799248967212223e-07, + "loss": 1.3053, + "step": 8601 + }, + { + "epoch": 0.9, + "learning_rate": 5.786971778872929e-07, + "loss": 1.3227, + "step": 8602 + }, + { + "epoch": 0.9, + "learning_rate": 5.774707212658692e-07, + "loss": 1.2454, + "step": 8603 + }, + { + "epoch": 0.9, + "learning_rate": 5.762455270212663e-07, + "loss": 1.2644, + "step": 8604 + }, + { + "epoch": 0.9, + "learning_rate": 5.750215953176253e-07, + "loss": 1.3815, + "step": 8605 + }, + { + "epoch": 0.9, + "learning_rate": 5.737989263189258e-07, + "loss": 1.3419, + "step": 8606 + }, + { + "epoch": 0.9, + "learning_rate": 5.725775201889694e-07, + "loss": 1.3521, + "step": 8607 + }, + { + "epoch": 0.9, + "learning_rate": 5.71357377091396e-07, + "loss": 1.3061, + "step": 8608 + }, + { + "epoch": 0.9, + "learning_rate": 5.701384971896751e-07, + "loss": 1.2356, + "step": 8609 + }, + { + "epoch": 0.9, + "learning_rate": 5.689208806471002e-07, + "loss": 1.4948, + "step": 8610 + }, + { + "epoch": 0.9, + "learning_rate": 5.677045276268045e-07, + "loss": 1.3552, + "step": 8611 + }, + { + "epoch": 0.9, + "learning_rate": 5.664894382917485e-07, + "loss": 1.3498, + "step": 8612 + }, + { + "epoch": 0.9, + "learning_rate": 5.652756128047199e-07, + "loss": 1.3089, + "step": 8613 + }, + { + "epoch": 0.9, + "learning_rate": 5.64063051328344e-07, + "loss": 1.3001, + "step": 8614 + }, + { + "epoch": 0.9, + "learning_rate": 5.628517540250688e-07, + "loss": 1.4114, + "step": 8615 + }, + { + "epoch": 0.9, + "learning_rate": 5.616417210571779e-07, + "loss": 1.2972, + "step": 8616 + }, + { + "epoch": 0.9, + "learning_rate": 5.60432952586788e-07, + "loss": 1.3059, + "step": 8617 + }, + { + "epoch": 0.9, + "learning_rate": 5.592254487758397e-07, + "loss": 1.3642, + "step": 8618 + }, + { + "epoch": 0.9, + "learning_rate": 5.58019209786107e-07, + "loss": 1.3047, + "step": 8619 + }, + { + "epoch": 0.9, + "learning_rate": 5.568142357791995e-07, + "loss": 1.3061, + "step": 8620 + }, + { + "epoch": 0.9, + "learning_rate": 5.556105269165468e-07, + "loss": 1.2628, + "step": 8621 + }, + { + "epoch": 0.9, + "learning_rate": 5.5440808335942e-07, + "loss": 1.3286, + "step": 8622 + }, + { + "epoch": 0.9, + "learning_rate": 5.532069052689115e-07, + "loss": 1.335, + "step": 8623 + }, + { + "epoch": 0.9, + "learning_rate": 5.520069928059502e-07, + "loss": 1.2729, + "step": 8624 + }, + { + "epoch": 0.9, + "learning_rate": 5.508083461312952e-07, + "loss": 1.3037, + "step": 8625 + }, + { + "epoch": 0.9, + "learning_rate": 5.496109654055315e-07, + "loss": 1.3028, + "step": 8626 + }, + { + "epoch": 0.9, + "learning_rate": 5.484148507890775e-07, + "loss": 1.3384, + "step": 8627 + }, + { + "epoch": 0.9, + "learning_rate": 5.472200024421859e-07, + "loss": 1.3019, + "step": 8628 + }, + { + "epoch": 0.9, + "learning_rate": 5.460264205249299e-07, + "loss": 1.3803, + "step": 8629 + }, + { + "epoch": 0.9, + "learning_rate": 5.448341051972217e-07, + "loss": 1.3179, + "step": 8630 + }, + { + "epoch": 0.91, + "learning_rate": 5.436430566188033e-07, + "loss": 1.2734, + "step": 8631 + }, + { + "epoch": 0.91, + "learning_rate": 5.424532749492394e-07, + "loss": 1.3184, + "step": 8632 + }, + { + "epoch": 0.91, + "learning_rate": 5.412647603479348e-07, + "loss": 1.2912, + "step": 8633 + }, + { + "epoch": 0.91, + "learning_rate": 5.400775129741165e-07, + "loss": 1.2942, + "step": 8634 + }, + { + "epoch": 0.91, + "learning_rate": 5.388915329868472e-07, + "loss": 1.3066, + "step": 8635 + }, + { + "epoch": 0.91, + "learning_rate": 5.377068205450175e-07, + "loss": 1.2963, + "step": 8636 + }, + { + "epoch": 0.91, + "learning_rate": 5.365233758073474e-07, + "loss": 1.2821, + "step": 8637 + }, + { + "epoch": 0.91, + "learning_rate": 5.353411989323887e-07, + "loss": 1.2637, + "step": 8638 + }, + { + "epoch": 0.91, + "learning_rate": 5.341602900785236e-07, + "loss": 1.3744, + "step": 8639 + }, + { + "epoch": 0.91, + "learning_rate": 5.329806494039624e-07, + "loss": 1.3841, + "step": 8640 + }, + { + "epoch": 0.91, + "learning_rate": 5.318022770667475e-07, + "loss": 1.3201, + "step": 8641 + }, + { + "epoch": 0.91, + "learning_rate": 5.306251732247492e-07, + "loss": 1.2934, + "step": 8642 + }, + { + "epoch": 0.91, + "learning_rate": 5.294493380356703e-07, + "loss": 1.2184, + "step": 8643 + }, + { + "epoch": 0.91, + "learning_rate": 5.282747716570425e-07, + "loss": 1.3003, + "step": 8644 + }, + { + "epoch": 0.91, + "learning_rate": 5.271014742462266e-07, + "loss": 1.339, + "step": 8645 + }, + { + "epoch": 0.91, + "learning_rate": 5.259294459604148e-07, + "loss": 1.2801, + "step": 8646 + }, + { + "epoch": 0.91, + "learning_rate": 5.247586869566301e-07, + "loss": 1.2954, + "step": 8647 + }, + { + "epoch": 0.91, + "learning_rate": 5.235891973917218e-07, + "loss": 1.2388, + "step": 8648 + }, + { + "epoch": 0.91, + "learning_rate": 5.224209774223721e-07, + "loss": 1.3775, + "step": 8649 + }, + { + "epoch": 0.91, + "learning_rate": 5.212540272050948e-07, + "loss": 1.2997, + "step": 8650 + }, + { + "epoch": 0.91, + "learning_rate": 5.200883468962281e-07, + "loss": 1.4565, + "step": 8651 + }, + { + "epoch": 0.91, + "learning_rate": 5.18923936651945e-07, + "loss": 1.3555, + "step": 8652 + }, + { + "epoch": 0.91, + "learning_rate": 5.17760796628245e-07, + "loss": 1.3218, + "step": 8653 + }, + { + "epoch": 0.91, + "learning_rate": 5.165989269809602e-07, + "loss": 1.268, + "step": 8654 + }, + { + "epoch": 0.91, + "learning_rate": 5.154383278657527e-07, + "loss": 1.3607, + "step": 8655 + }, + { + "epoch": 0.91, + "learning_rate": 5.142789994381092e-07, + "loss": 1.2846, + "step": 8656 + }, + { + "epoch": 0.91, + "learning_rate": 5.131209418533534e-07, + "loss": 1.2988, + "step": 8657 + }, + { + "epoch": 0.91, + "learning_rate": 5.119641552666343e-07, + "loss": 1.3256, + "step": 8658 + }, + { + "epoch": 0.91, + "learning_rate": 5.108086398329304e-07, + "loss": 1.3138, + "step": 8659 + }, + { + "epoch": 0.91, + "learning_rate": 5.096543957070521e-07, + "loss": 1.2735, + "step": 8660 + }, + { + "epoch": 0.91, + "learning_rate": 5.08501423043638e-07, + "loss": 1.2265, + "step": 8661 + }, + { + "epoch": 0.91, + "learning_rate": 5.073497219971568e-07, + "loss": 1.4353, + "step": 8662 + }, + { + "epoch": 0.91, + "learning_rate": 5.061992927219084e-07, + "loss": 1.3996, + "step": 8663 + }, + { + "epoch": 0.91, + "learning_rate": 5.050501353720184e-07, + "loss": 1.4069, + "step": 8664 + }, + { + "epoch": 0.91, + "learning_rate": 5.039022501014445e-07, + "loss": 1.7528, + "step": 8665 + }, + { + "epoch": 0.91, + "learning_rate": 5.027556370639764e-07, + "loss": 1.2997, + "step": 8666 + }, + { + "epoch": 0.91, + "learning_rate": 5.016102964132286e-07, + "loss": 1.2629, + "step": 8667 + }, + { + "epoch": 0.91, + "learning_rate": 5.004662283026485e-07, + "loss": 1.3199, + "step": 8668 + }, + { + "epoch": 0.91, + "learning_rate": 4.993234328855101e-07, + "loss": 1.3457, + "step": 8669 + }, + { + "epoch": 0.91, + "learning_rate": 4.981819103149199e-07, + "loss": 1.2669, + "step": 8670 + }, + { + "epoch": 0.91, + "learning_rate": 4.970416607438133e-07, + "loss": 1.2051, + "step": 8671 + }, + { + "epoch": 0.91, + "learning_rate": 4.959026843249526e-07, + "loss": 1.3008, + "step": 8672 + }, + { + "epoch": 0.91, + "learning_rate": 4.947649812109323e-07, + "loss": 1.2823, + "step": 8673 + }, + { + "epoch": 0.91, + "learning_rate": 4.936285515541761e-07, + "loss": 1.3427, + "step": 8674 + }, + { + "epoch": 0.91, + "learning_rate": 4.924933955069356e-07, + "loss": 1.3132, + "step": 8675 + }, + { + "epoch": 0.91, + "learning_rate": 4.913595132212911e-07, + "loss": 1.2673, + "step": 8676 + }, + { + "epoch": 0.91, + "learning_rate": 4.902269048491581e-07, + "loss": 1.3132, + "step": 8677 + }, + { + "epoch": 0.91, + "learning_rate": 4.890955705422718e-07, + "loss": 1.398, + "step": 8678 + }, + { + "epoch": 0.91, + "learning_rate": 4.879655104522052e-07, + "loss": 1.3282, + "step": 8679 + }, + { + "epoch": 0.91, + "learning_rate": 4.868367247303562e-07, + "loss": 1.316, + "step": 8680 + }, + { + "epoch": 0.91, + "learning_rate": 4.857092135279529e-07, + "loss": 1.3533, + "step": 8681 + }, + { + "epoch": 0.91, + "learning_rate": 4.845829769960542e-07, + "loss": 1.2295, + "step": 8682 + }, + { + "epoch": 0.91, + "learning_rate": 4.83458015285545e-07, + "loss": 1.338, + "step": 8683 + }, + { + "epoch": 0.91, + "learning_rate": 4.823343285471416e-07, + "loss": 1.2782, + "step": 8684 + }, + { + "epoch": 0.91, + "learning_rate": 4.812119169313911e-07, + "loss": 1.3285, + "step": 8685 + }, + { + "epoch": 0.91, + "learning_rate": 4.800907805886656e-07, + "loss": 1.319, + "step": 8686 + }, + { + "epoch": 0.91, + "learning_rate": 4.789709196691705e-07, + "loss": 1.2571, + "step": 8687 + }, + { + "epoch": 0.91, + "learning_rate": 4.778523343229358e-07, + "loss": 1.4777, + "step": 8688 + }, + { + "epoch": 0.91, + "learning_rate": 4.767350246998248e-07, + "loss": 1.2571, + "step": 8689 + }, + { + "epoch": 0.91, + "learning_rate": 4.75618990949529e-07, + "loss": 1.3119, + "step": 8690 + }, + { + "epoch": 0.91, + "learning_rate": 4.745042332215666e-07, + "loss": 1.2801, + "step": 8691 + }, + { + "epoch": 0.91, + "learning_rate": 4.7339075166528694e-07, + "loss": 1.3656, + "step": 8692 + }, + { + "epoch": 0.91, + "learning_rate": 4.722785464298696e-07, + "loss": 1.3113, + "step": 8693 + }, + { + "epoch": 0.91, + "learning_rate": 4.711676176643187e-07, + "loss": 1.2282, + "step": 8694 + }, + { + "epoch": 0.91, + "learning_rate": 4.7005796551747195e-07, + "loss": 1.2845, + "step": 8695 + }, + { + "epoch": 0.91, + "learning_rate": 4.689495901379948e-07, + "loss": 1.3165, + "step": 8696 + }, + { + "epoch": 0.91, + "learning_rate": 4.6784249167437843e-07, + "loss": 1.304, + "step": 8697 + }, + { + "epoch": 0.91, + "learning_rate": 4.6673667027494986e-07, + "loss": 1.4249, + "step": 8698 + }, + { + "epoch": 0.91, + "learning_rate": 4.65632126087856e-07, + "loss": 1.2408, + "step": 8699 + }, + { + "epoch": 0.91, + "learning_rate": 4.6452885926107973e-07, + "loss": 1.3566, + "step": 8700 + }, + { + "epoch": 0.91, + "learning_rate": 4.6342686994243267e-07, + "loss": 1.3258, + "step": 8701 + }, + { + "epoch": 0.91, + "learning_rate": 4.6232615827954795e-07, + "loss": 1.2556, + "step": 8702 + }, + { + "epoch": 0.91, + "learning_rate": 4.6122672441989645e-07, + "loss": 1.3285, + "step": 8703 + }, + { + "epoch": 0.91, + "learning_rate": 4.601285685107737e-07, + "loss": 1.4333, + "step": 8704 + }, + { + "epoch": 0.91, + "learning_rate": 4.590316906993031e-07, + "loss": 1.3094, + "step": 8705 + }, + { + "epoch": 0.91, + "learning_rate": 4.579360911324393e-07, + "loss": 1.3309, + "step": 8706 + }, + { + "epoch": 0.91, + "learning_rate": 4.568417699569627e-07, + "loss": 1.3601, + "step": 8707 + }, + { + "epoch": 0.91, + "learning_rate": 4.557487273194849e-07, + "loss": 1.264, + "step": 8708 + }, + { + "epoch": 0.91, + "learning_rate": 4.546569633664488e-07, + "loss": 1.3169, + "step": 8709 + }, + { + "epoch": 0.91, + "learning_rate": 4.5356647824411737e-07, + "loss": 1.34, + "step": 8710 + }, + { + "epoch": 0.91, + "learning_rate": 4.524772720985904e-07, + "loss": 1.4068, + "step": 8711 + }, + { + "epoch": 0.91, + "learning_rate": 4.5138934507579555e-07, + "loss": 1.2908, + "step": 8712 + }, + { + "epoch": 0.91, + "learning_rate": 4.5030269732148304e-07, + "loss": 1.3185, + "step": 8713 + }, + { + "epoch": 0.91, + "learning_rate": 4.492173289812385e-07, + "loss": 1.4087, + "step": 8714 + }, + { + "epoch": 0.91, + "learning_rate": 4.4813324020047124e-07, + "loss": 1.2899, + "step": 8715 + }, + { + "epoch": 0.91, + "learning_rate": 4.4705043112442284e-07, + "loss": 1.3228, + "step": 8716 + }, + { + "epoch": 0.91, + "learning_rate": 4.4596890189816277e-07, + "loss": 1.3172, + "step": 8717 + }, + { + "epoch": 0.91, + "learning_rate": 4.448886526665852e-07, + "loss": 1.3063, + "step": 8718 + }, + { + "epoch": 0.91, + "learning_rate": 4.438096835744188e-07, + "loss": 1.3737, + "step": 8719 + }, + { + "epoch": 0.91, + "learning_rate": 4.4273199476621677e-07, + "loss": 1.3713, + "step": 8720 + }, + { + "epoch": 0.91, + "learning_rate": 4.416555863863603e-07, + "loss": 1.2843, + "step": 8721 + }, + { + "epoch": 0.91, + "learning_rate": 4.4058045857906075e-07, + "loss": 1.2903, + "step": 8722 + }, + { + "epoch": 0.91, + "learning_rate": 4.395066114883606e-07, + "loss": 1.2618, + "step": 8723 + }, + { + "epoch": 0.91, + "learning_rate": 4.384340452581248e-07, + "loss": 1.278, + "step": 8724 + }, + { + "epoch": 0.91, + "learning_rate": 4.3736276003205067e-07, + "loss": 1.3721, + "step": 8725 + }, + { + "epoch": 0.92, + "learning_rate": 4.3629275595366226e-07, + "loss": 1.2787, + "step": 8726 + }, + { + "epoch": 0.92, + "learning_rate": 4.3522403316631266e-07, + "loss": 1.3116, + "step": 8727 + }, + { + "epoch": 0.92, + "learning_rate": 4.34156591813184e-07, + "loss": 1.2237, + "step": 8728 + }, + { + "epoch": 0.92, + "learning_rate": 4.330904320372853e-07, + "loss": 1.3205, + "step": 8729 + }, + { + "epoch": 0.92, + "learning_rate": 4.3202555398145554e-07, + "loss": 1.2894, + "step": 8730 + }, + { + "epoch": 0.92, + "learning_rate": 4.309619577883606e-07, + "loss": 1.2975, + "step": 8731 + }, + { + "epoch": 0.92, + "learning_rate": 4.298996436004943e-07, + "loss": 1.4334, + "step": 8732 + }, + { + "epoch": 0.92, + "learning_rate": 4.288386115601806e-07, + "loss": 1.3884, + "step": 8733 + }, + { + "epoch": 0.92, + "learning_rate": 4.277788618095691e-07, + "loss": 1.3426, + "step": 8734 + }, + { + "epoch": 0.92, + "learning_rate": 4.267203944906395e-07, + "loss": 1.3099, + "step": 8735 + }, + { + "epoch": 0.92, + "learning_rate": 4.256632097452018e-07, + "loss": 1.3105, + "step": 8736 + }, + { + "epoch": 0.92, + "learning_rate": 4.2460730771488714e-07, + "loss": 1.2708, + "step": 8737 + }, + { + "epoch": 0.92, + "learning_rate": 4.2355268854116227e-07, + "loss": 1.262, + "step": 8738 + }, + { + "epoch": 0.92, + "learning_rate": 4.224993523653187e-07, + "loss": 1.3263, + "step": 8739 + }, + { + "epoch": 0.92, + "learning_rate": 4.214472993284746e-07, + "loss": 1.3225, + "step": 8740 + }, + { + "epoch": 0.92, + "learning_rate": 4.2039652957158063e-07, + "loss": 1.3678, + "step": 8741 + }, + { + "epoch": 0.92, + "learning_rate": 4.1934704323541187e-07, + "loss": 1.3537, + "step": 8742 + }, + { + "epoch": 0.92, + "learning_rate": 4.182988404605726e-07, + "loss": 1.329, + "step": 8743 + }, + { + "epoch": 0.92, + "learning_rate": 4.172519213874948e-07, + "loss": 1.332, + "step": 8744 + }, + { + "epoch": 0.92, + "learning_rate": 4.1620628615643753e-07, + "loss": 1.3303, + "step": 8745 + }, + { + "epoch": 0.92, + "learning_rate": 4.151619349074909e-07, + "loss": 1.359, + "step": 8746 + }, + { + "epoch": 0.92, + "learning_rate": 4.1411886778057185e-07, + "loss": 1.3323, + "step": 8747 + }, + { + "epoch": 0.92, + "learning_rate": 4.1307708491542196e-07, + "loss": 1.2995, + "step": 8748 + }, + { + "epoch": 0.92, + "learning_rate": 4.12036586451614e-07, + "loss": 1.3312, + "step": 8749 + }, + { + "epoch": 0.92, + "learning_rate": 4.10997372528551e-07, + "loss": 1.39, + "step": 8750 + }, + { + "epoch": 0.92, + "learning_rate": 4.0995944328545703e-07, + "loss": 1.31, + "step": 8751 + }, + { + "epoch": 0.92, + "learning_rate": 4.0892279886138976e-07, + "loss": 1.2908, + "step": 8752 + }, + { + "epoch": 0.92, + "learning_rate": 4.0788743939523257e-07, + "loss": 1.2324, + "step": 8753 + }, + { + "epoch": 0.92, + "learning_rate": 4.068533650256967e-07, + "loss": 1.3102, + "step": 8754 + }, + { + "epoch": 0.92, + "learning_rate": 4.058205758913236e-07, + "loss": 1.2724, + "step": 8755 + }, + { + "epoch": 0.92, + "learning_rate": 4.0478907213047816e-07, + "loss": 1.2489, + "step": 8756 + }, + { + "epoch": 0.92, + "eval_loss": 1.394278645515442, + "eval_runtime": 77.5397, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 8756 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 3.917119632739727e+20, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-8756/training_args.bin b/checkpoint-8756/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-8756/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/checkpoint-9154/config.json b/checkpoint-9154/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e51867edd7bb621aea6f78e0ebeba5ba00f40340 --- /dev/null +++ b/checkpoint-9154/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 2, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/checkpoint-9154/generation_config.json b/checkpoint-9154/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c441554e91bd20deec0e4c45388b2ac2cc602f2b --- /dev/null +++ b/checkpoint-9154/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.0.dev0" +} diff --git a/checkpoint-9154/model-00001-of-00003.safetensors b/checkpoint-9154/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..19b677ba653a07f0d742ee85ea36d0c2dfceaf2b --- /dev/null +++ b/checkpoint-9154/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b851590d66e9ce85a4228991e074a2364b17cbdf9a216f751411fc54c4015b97 +size 4943162336 diff --git a/checkpoint-9154/model-00002-of-00003.safetensors b/checkpoint-9154/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dc4b1f3e284138a7b1edff635c2663bde17cbf09 --- /dev/null +++ b/checkpoint-9154/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19c95f4ceb0ef12801fe2182330f29cfa1bebbfb7bd337ebe83fb49d51844b69 +size 4999819336 diff --git a/checkpoint-9154/model-00003-of-00003.safetensors b/checkpoint-9154/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c3dd698349027be1d138cfaffad3f101776033c6 --- /dev/null +++ b/checkpoint-9154/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac979c76d6babeddf18d00a2436238a74a1df008916033ee7dcd8ae8979bf3b8 +size 4540516344 diff --git a/checkpoint-9154/model.safetensors.index.json b/checkpoint-9154/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b349bc0ce8075a2a5df1e0210450308018d396c8 --- /dev/null +++ b/checkpoint-9154/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/checkpoint-9154/optimizer.pt b/checkpoint-9154/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..faf157199a37ff1bddc13dbc48221d0f86a2ffb1 --- /dev/null +++ b/checkpoint-9154/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2944858b0f0ca6405ce3adfd0b29ff000ca0e9c6e7a6996d26e252ae455dac8 +size 14512103560 diff --git a/checkpoint-9154/rng_state_0.pth b/checkpoint-9154/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..c7eb8dd7590455ee27e4b802fd971f237c460b5a --- /dev/null +++ b/checkpoint-9154/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dc3a6ff2ad466c1875b691cf6f5b687effad1dd27ab8d9dd5a4ca8a8172e778 +size 15984 diff --git a/checkpoint-9154/rng_state_1.pth b/checkpoint-9154/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..a9257a2fbfa52d09c00608d017396209ff2f524d --- /dev/null +++ b/checkpoint-9154/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:868792adc35566a1c6bb4d533f7be8fbb9009a7c1e94ca608e1ce5790dd89417 +size 15984 diff --git a/checkpoint-9154/rng_state_2.pth b/checkpoint-9154/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..eb7d13ff773e6d9e47da94eb030c49f2495893ba --- /dev/null +++ b/checkpoint-9154/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd6d1ba59244fddc9deb0b008964f0f1ff362b4f11b7055dda931e292b5ce626 +size 15984 diff --git a/checkpoint-9154/rng_state_3.pth b/checkpoint-9154/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..38089d8975508dcd5e1cc697ae7e616ac178b392 --- /dev/null +++ b/checkpoint-9154/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c50bbc6f8e7bf091f80dbf9c60208c3f228fbdcf296ac665c1e8cc87e8b1a24f +size 15984 diff --git a/checkpoint-9154/rng_state_4.pth b/checkpoint-9154/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..4ed565425795c2429183c4a986d9a8e928b13393 --- /dev/null +++ b/checkpoint-9154/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08b9d3660eb3a583085637f4a44ca5437338aa2d6330a12b601aac0fad7baa25 +size 15984 diff --git a/checkpoint-9154/rng_state_5.pth b/checkpoint-9154/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..d2005c8a7441cce8262c0a7a42747c117d4cd5b9 --- /dev/null +++ b/checkpoint-9154/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f10cc4559b73d57f512db4173c9561d7d52b361141f6f0df4ae5fed38091e3e +size 15984 diff --git a/checkpoint-9154/rng_state_6.pth b/checkpoint-9154/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..2589d125dc4f7b2b4f0fd4649ebe9076f6134d04 --- /dev/null +++ b/checkpoint-9154/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:630b1a190a4d39c3aee935c77a0073fc8c8198ed724faa8bc8a4d2dbb976558e +size 15984 diff --git a/checkpoint-9154/rng_state_7.pth b/checkpoint-9154/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..32f47bc4d645c60c552a4a491e4433806185fbb2 --- /dev/null +++ b/checkpoint-9154/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:387366282361f1b12e2c2cea1548bb09a809daed3d86011706c8912d37f06891 +size 15984 diff --git a/checkpoint-9154/scheduler.pt b/checkpoint-9154/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..fc88e82a6b6bd2a06dce6c2c6eb8c9b9bd1d0d0a --- /dev/null +++ b/checkpoint-9154/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42158621a1a9b0e86a2d0b82af24fba062f560830ad262d455ab9282501057a7 +size 1064 diff --git a/checkpoint-9154/special_tokens_map.json b/checkpoint-9154/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..72ecfeeb7e14d244c936169d2ed139eeae235ef1 --- /dev/null +++ b/checkpoint-9154/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-9154/tokenizer.model b/checkpoint-9154/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..8b443ef19c2a19acc3ac64fb9c3db4a72921dff6 --- /dev/null +++ b/checkpoint-9154/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/checkpoint-9154/tokenizer_config.json b/checkpoint-9154/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..666ce4e1bb278f728040737ffa997d98008b984a --- /dev/null +++ b/checkpoint-9154/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +} diff --git a/checkpoint-9154/trainer_state.json b/checkpoint-9154/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..5e4fd58926096357356b47494d6a6617d0b2a153 --- /dev/null +++ b/checkpoint-9154/trainer_state.json @@ -0,0 +1,55312 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.9599412751677853, + "eval_steps": 199, + "global_step": 9154, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0986358866736623e-08, + "loss": 2.1261, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473246e-08, + "loss": 2.0696, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020988e-08, + "loss": 2.0664, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-08, + "loss": 2.0793, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0493179433368311e-07, + "loss": 1.9493, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.2591815320041975e-07, + "loss": 2.0603, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4690451206715635e-07, + "loss": 2.2201, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.6789087093389298e-07, + "loss": 2.0475, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.888772298006296e-07, + "loss": 1.8393, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.0986358866736621e-07, + "loss": 2.1082, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3084994753410284e-07, + "loss": 2.0846, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.518363064008395e-07, + "loss": 2.2172, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282266526757613e-07, + "loss": 2.0091, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.938090241343127e-07, + "loss": 2.1092, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1479538300104934e-07, + "loss": 2.0882, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578174186778596e-07, + "loss": 2.0103, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.567681007345226e-07, + "loss": 2.119, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.777544596012592e-07, + "loss": 2.005, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874081846799585e-07, + "loss": 2.0261, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.1972717733473243e-07, + "loss": 1.8976, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.407135362014691e-07, + "loss": 2.0584, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.616998950682057e-07, + "loss": 1.9565, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.826862539349423e-07, + "loss": 2.1067, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.03672612801679e-07, + "loss": 1.9939, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.246589716684156e-07, + "loss": 1.9337, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.456453305351523e-07, + "loss": 2.0869, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.666316894018888e-07, + "loss": 2.0134, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.876180482686254e-07, + "loss": 1.5282, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.086044071353621e-07, + "loss": 1.8605, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.295907660020987e-07, + "loss": 1.9561, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.505771248688352e-07, + "loss": 1.9562, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.715634837355719e-07, + "loss": 1.9124, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 6.925498426023086e-07, + "loss": 1.908, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.135362014690452e-07, + "loss": 1.9148, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.345225603357818e-07, + "loss": 1.9861, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.555089192025184e-07, + "loss": 1.8246, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.76495278069255e-07, + "loss": 1.9355, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 7.974816369359917e-07, + "loss": 1.9849, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.184679958027284e-07, + "loss": 1.8894, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 8.394543546694649e-07, + "loss": 1.9615, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 8.604407135362015e-07, + "loss": 1.8815, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 8.814270724029382e-07, + "loss": 1.9888, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 9.024134312696747e-07, + "loss": 1.8663, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 9.233997901364114e-07, + "loss": 1.8711, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 9.443861490031481e-07, + "loss": 1.8709, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 9.653725078698846e-07, + "loss": 1.8837, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 9.863588667366212e-07, + "loss": 1.9386, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.007345225603358e-06, + "loss": 1.8926, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.0283315844700944e-06, + "loss": 1.8623, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.0493179433368312e-06, + "loss": 1.9017, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703043022035677e-06, + "loss": 1.883, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.0912906610703045e-06, + "loss": 2.0128, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1122770199370409e-06, + "loss": 1.9405, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1332633788037777e-06, + "loss": 2.1205, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1542497376705142e-06, + "loss": 1.8373, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1752360965372508e-06, + "loss": 1.9386, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.1962224554039876e-06, + "loss": 1.831, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.2172088142707242e-06, + "loss": 1.8523, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.2381951731374608e-06, + "loss": 1.8641, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.2591815320041973e-06, + "loss": 1.8386, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.280167890870934e-06, + "loss": 1.8628, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3011542497376705e-06, + "loss": 1.8578, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3221406086044073e-06, + "loss": 1.868, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3431269674711439e-06, + "loss": 1.9356, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3641133263378806e-06, + "loss": 1.7525, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.3850996852046172e-06, + "loss": 1.8815, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4060860440713536e-06, + "loss": 1.8752, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4270724029380904e-06, + "loss": 1.8017, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.448058761804827e-06, + "loss": 1.8209, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4690451206715635e-06, + "loss": 1.7979, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.4900314795383003e-06, + "loss": 1.8267, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.511017838405037e-06, + "loss": 1.862, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5320041972717733e-06, + "loss": 1.8278, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.55299055613851e-06, + "loss": 1.816, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5739769150052466e-06, + "loss": 1.8465, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.5949632738719834e-06, + "loss": 1.7981, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.61594963273872e-06, + "loss": 1.9075, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6369359916054568e-06, + "loss": 1.7548, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6579223504721931e-06, + "loss": 1.8585, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789087093389297e-06, + "loss": 1.7725, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.6998950682056665e-06, + "loss": 1.8273, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.720881427072403e-06, + "loss": 1.777, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7418677859391397e-06, + "loss": 1.8077, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.7628541448058764e-06, + "loss": 1.821, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.783840503672613e-06, + "loss": 1.8287, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8048268625393494e-06, + "loss": 1.7358, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8258132214060862e-06, + "loss": 1.7546, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8467995802728228e-06, + "loss": 1.8147, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8677859391395595e-06, + "loss": 1.8309, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.8887722980062961e-06, + "loss": 1.6292, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.909758656873033e-06, + "loss": 1.7222, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9307450157397693e-06, + "loss": 1.809, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.951731374606506e-06, + "loss": 1.8691, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.9727177334732424e-06, + "loss": 1.8777, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937040923399792e-06, + "loss": 1.7701, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.014690451206716e-06, + "loss": 1.885, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.0356768100734524e-06, + "loss": 1.7737, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.0566631689401887e-06, + "loss": 1.7554, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776495278069255e-06, + "loss": 1.8553, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986358866736623e-06, + "loss": 1.8386, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.119622245540399e-06, + "loss": 1.8325, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1406086044071355e-06, + "loss": 1.7812, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1615949632738722e-06, + "loss": 1.7537, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.182581322140609e-06, + "loss": 1.7558, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.2035676810073454e-06, + "loss": 1.7278, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245540398740818e-06, + "loss": 1.761, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.2455403987408186e-06, + "loss": 1.792, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.2665267576075553e-06, + "loss": 1.7965, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.287513116474292e-06, + "loss": 1.7624, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084994753410285e-06, + "loss": 1.7744, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.329485834207765e-06, + "loss": 1.7691, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3504721930745016e-06, + "loss": 1.8194, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3714585519412384e-06, + "loss": 1.691, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.3924449108079752e-06, + "loss": 1.7505, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.4134312696747116e-06, + "loss": 1.7492, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.4344176285414484e-06, + "loss": 1.8426, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.4554039874081847e-06, + "loss": 1.855, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 2.4763903462749215e-06, + "loss": 1.7778, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 2.497376705141658e-06, + "loss": 1.7715, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 2.5183630640083947e-06, + "loss": 1.7382, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5393494228751315e-06, + "loss": 1.7027, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 2.560335781741868e-06, + "loss": 1.7508, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 2.5813221406086046e-06, + "loss": 1.7119, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 2.602308499475341e-06, + "loss": 1.8291, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 2.623294858342078e-06, + "loss": 1.7568, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 2.6442812172088146e-06, + "loss": 1.9176, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 2.665267576075551e-06, + "loss": 1.7036, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862539349422877e-06, + "loss": 1.7842, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 2.707240293809024e-06, + "loss": 1.7883, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 2.7282266526757613e-06, + "loss": 1.7662, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 2.7492130115424977e-06, + "loss": 1.5587, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 2.7701993704092344e-06, + "loss": 1.7486, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 2.791185729275971e-06, + "loss": 1.7515, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 2.812172088142707e-06, + "loss": 1.7668, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331584470094444e-06, + "loss": 1.7895, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 2.8541448058761808e-06, + "loss": 1.7961, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 2.8751311647429175e-06, + "loss": 1.6693, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 2.896117523609654e-06, + "loss": 1.776, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 2.9171038824763903e-06, + "loss": 1.7422, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 2.938090241343127e-06, + "loss": 1.7845, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 2.959076600209864e-06, + "loss": 1.8011, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 2.9800629590766006e-06, + "loss": 1.6759, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 3.001049317943337e-06, + "loss": 1.7367, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.022035676810074e-06, + "loss": 1.7511, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.04302203567681e-06, + "loss": 1.779, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.0640083945435465e-06, + "loss": 1.7542, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.0849947534102837e-06, + "loss": 1.742, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.10598111227702e-06, + "loss": 1.7408, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.126967471143757e-06, + "loss": 1.6937, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.1479538300104932e-06, + "loss": 1.7198, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.1689401888772305e-06, + "loss": 1.674, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.189926547743967e-06, + "loss": 1.7469, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.210912906610703e-06, + "loss": 1.7192, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.23189926547744e-06, + "loss": 1.9507, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.2528856243441763e-06, + "loss": 1.8311, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.2738719832109136e-06, + "loss": 1.7125, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.29485834207765e-06, + "loss": 1.8235, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3158447009443863e-06, + "loss": 1.7358, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.336831059811123e-06, + "loss": 1.774, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.3578174186778594e-06, + "loss": 1.7717, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788037775445962e-06, + "loss": 1.6815, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790136411333e-06, + "loss": 1.6993, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.42077649527807e-06, + "loss": 1.5911, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.441762854144806e-06, + "loss": 1.7484, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.4627492130115425e-06, + "loss": 1.8047, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.4837355718782793e-06, + "loss": 1.7397, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.5047219307450157e-06, + "loss": 1.7384, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.525708289611753e-06, + "loss": 1.7369, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.5466946484784893e-06, + "loss": 1.7013, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.567681007345226e-06, + "loss": 1.6896, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.5886673662119624e-06, + "loss": 1.6953, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.6096537250786988e-06, + "loss": 1.7638, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.630640083945436e-06, + "loss": 1.6814, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.6516264428121724e-06, + "loss": 1.6938, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.672612801678909e-06, + "loss": 1.8404, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.6935991605456455e-06, + "loss": 1.7429, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.714585519412382e-06, + "loss": 1.7408, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.735571878279119e-06, + "loss": 1.6916, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.7565582371458554e-06, + "loss": 1.7668, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.7775445960125922e-06, + "loss": 1.7444, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.7985309548793286e-06, + "loss": 1.7478, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.819517313746066e-06, + "loss": 1.7812, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.840503672612802e-06, + "loss": 1.7029, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.8614900314795385e-06, + "loss": 1.66, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.882476390346275e-06, + "loss": 1.7375, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.903462749213012e-06, + "loss": 1.7702, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.924449108079749e-06, + "loss": 1.7368, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 3.945435466946485e-06, + "loss": 1.7121, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 3.966421825813222e-06, + "loss": 1.7639, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 3.9874081846799584e-06, + "loss": 1.6665, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.008394543546694e-06, + "loss": 1.6536, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.029380902413432e-06, + "loss": 1.7049, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.050367261280168e-06, + "loss": 1.8199, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.071353620146905e-06, + "loss": 1.747, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.0923399790136415e-06, + "loss": 1.7382, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 4.1133263378803775e-06, + "loss": 1.6958, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 4.134312696747115e-06, + "loss": 1.6974, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 4.155299055613851e-06, + "loss": 1.6909, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 4.176285414480588e-06, + "loss": 1.6995, + "step": 199 + }, + { + "epoch": 0.02, + "eval_loss": 1.7673084735870361, + "eval_runtime": 77.3397, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 4.197271773347325e-06, + "loss": 1.6732, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 4.218258132214061e-06, + "loss": 1.7269, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 4.239244491080798e-06, + "loss": 1.6493, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 4.260230849947534e-06, + "loss": 1.6544, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 4.281217208814271e-06, + "loss": 1.8876, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 4.302203567681008e-06, + "loss": 1.7196, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 4.3231899265477445e-06, + "loss": 1.7659, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 4.344176285414481e-06, + "loss": 1.7129, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 4.365162644281218e-06, + "loss": 1.7269, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 4.386149003147954e-06, + "loss": 1.7957, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 4.407135362014691e-06, + "loss": 1.681, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 4.428121720881428e-06, + "loss": 1.7112, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 4.4491080797481635e-06, + "loss": 1.7149, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 4.470094438614901e-06, + "loss": 1.6928, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 4.491080797481637e-06, + "loss": 1.6171, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 4.512067156348374e-06, + "loss": 1.7275, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 4.533053515215111e-06, + "loss": 1.7502, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 4.554039874081847e-06, + "loss": 1.7948, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 4.575026232948584e-06, + "loss": 1.8349, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 4.59601259181532e-06, + "loss": 1.6717, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 4.616998950682057e-06, + "loss": 1.7387, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 4.637985309548794e-06, + "loss": 1.836, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 4.65897166841553e-06, + "loss": 1.7285, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 4.679958027282267e-06, + "loss": 1.6988, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 4.700944386149003e-06, + "loss": 1.642, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 4.72193074501574e-06, + "loss": 1.7184, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 4.742917103882477e-06, + "loss": 1.6935, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 4.763903462749214e-06, + "loss": 1.7593, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 4.7848898216159504e-06, + "loss": 1.6854, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 4.805876180482686e-06, + "loss": 1.7047, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 4.826862539349423e-06, + "loss": 1.6543, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 4.84784889821616e-06, + "loss": 1.6321, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 4.868835257082897e-06, + "loss": 1.6938, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 4.889821615949633e-06, + "loss": 1.725, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 4.9108079748163695e-06, + "loss": 1.7119, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 4.931794333683106e-06, + "loss": 1.7741, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 4.952780692549843e-06, + "loss": 1.702, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 4.97376705141658e-06, + "loss": 1.6566, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 4.994753410283316e-06, + "loss": 1.7506, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.0157397691500534e-06, + "loss": 1.7185, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.036726128016789e-06, + "loss": 1.8174, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.057712486883526e-06, + "loss": 1.6781, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.078698845750263e-06, + "loss": 1.7818, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.099685204617e-06, + "loss": 1.6647, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.120671563483736e-06, + "loss": 1.6918, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.1416579223504725e-06, + "loss": 1.7119, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.162644281217209e-06, + "loss": 1.612, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.183630640083945e-06, + "loss": 1.5301, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.204616998950682e-06, + "loss": 1.7407, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.22560335781742e-06, + "loss": 1.7838, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.246589716684156e-06, + "loss": 1.6825, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.267576075550892e-06, + "loss": 1.6821, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.288562434417629e-06, + "loss": 1.6712, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.309548793284366e-06, + "loss": 1.6599, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.330535152151102e-06, + "loss": 1.7009, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.351521511017839e-06, + "loss": 1.6845, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.3725078698845754e-06, + "loss": 1.6832, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.393494228751312e-06, + "loss": 1.8023, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.414480587618048e-06, + "loss": 1.718, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.435466946484785e-06, + "loss": 1.602, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.456453305351523e-06, + "loss": 1.6133, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.4774396642182585e-06, + "loss": 1.704, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.498426023084995e-06, + "loss": 1.6702, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.519412381951732e-06, + "loss": 1.7256, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.540398740818469e-06, + "loss": 1.7384, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.561385099685205e-06, + "loss": 1.6504, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.582371458551942e-06, + "loss": 1.6896, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.603357817418678e-06, + "loss": 1.6566, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.624344176285414e-06, + "loss": 1.7107, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.645330535152151e-06, + "loss": 1.6883, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.666316894018889e-06, + "loss": 1.74, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.6873032528856256e-06, + "loss": 1.7273, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.7082896117523615e-06, + "loss": 1.7397, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.729275970619098e-06, + "loss": 1.723, + "step": 273 + }, + { + "epoch": 0.03, + "learning_rate": 5.750262329485835e-06, + "loss": 1.6811, + "step": 274 + }, + { + "epoch": 0.03, + "learning_rate": 5.771248688352571e-06, + "loss": 1.7044, + "step": 275 + }, + { + "epoch": 0.03, + "learning_rate": 5.792235047219308e-06, + "loss": 1.6937, + "step": 276 + }, + { + "epoch": 0.03, + "learning_rate": 5.813221406086045e-06, + "loss": 1.5984, + "step": 277 + }, + { + "epoch": 0.03, + "learning_rate": 5.8342077649527805e-06, + "loss": 1.7853, + "step": 278 + }, + { + "epoch": 0.03, + "learning_rate": 5.855194123819517e-06, + "loss": 1.6742, + "step": 279 + }, + { + "epoch": 0.03, + "learning_rate": 5.876180482686254e-06, + "loss": 1.5612, + "step": 280 + }, + { + "epoch": 0.03, + "learning_rate": 5.897166841552992e-06, + "loss": 1.6945, + "step": 281 + }, + { + "epoch": 0.03, + "learning_rate": 5.918153200419728e-06, + "loss": 1.6618, + "step": 282 + }, + { + "epoch": 0.03, + "learning_rate": 5.9391395592864645e-06, + "loss": 1.6928, + "step": 283 + }, + { + "epoch": 0.03, + "learning_rate": 5.960125918153201e-06, + "loss": 1.7438, + "step": 284 + }, + { + "epoch": 0.03, + "learning_rate": 5.981112277019937e-06, + "loss": 1.5858, + "step": 285 + }, + { + "epoch": 0.03, + "learning_rate": 6.002098635886674e-06, + "loss": 1.6936, + "step": 286 + }, + { + "epoch": 0.03, + "learning_rate": 6.023084994753411e-06, + "loss": 1.6522, + "step": 287 + }, + { + "epoch": 0.03, + "learning_rate": 6.044071353620148e-06, + "loss": 1.7174, + "step": 288 + }, + { + "epoch": 0.03, + "learning_rate": 6.0650577124868835e-06, + "loss": 1.6747, + "step": 289 + }, + { + "epoch": 0.03, + "learning_rate": 6.08604407135362e-06, + "loss": 1.6525, + "step": 290 + }, + { + "epoch": 0.03, + "learning_rate": 6.107030430220358e-06, + "loss": 1.6615, + "step": 291 + }, + { + "epoch": 0.03, + "learning_rate": 6.128016789087093e-06, + "loss": 1.7633, + "step": 292 + }, + { + "epoch": 0.03, + "learning_rate": 6.149003147953831e-06, + "loss": 1.6597, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 6.1699895068205675e-06, + "loss": 1.6356, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 6.190975865687304e-06, + "loss": 1.5906, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 6.21196222455404e-06, + "loss": 1.7179, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 6.232948583420777e-06, + "loss": 1.6571, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 6.253934942287514e-06, + "loss": 1.655, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 6.27492130115425e-06, + "loss": 1.6705, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 6.2959076600209865e-06, + "loss": 1.6931, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 6.316894018887723e-06, + "loss": 1.6721, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 6.337880377754461e-06, + "loss": 1.6573, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 6.358866736621197e-06, + "loss": 1.7316, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 6.379853095487934e-06, + "loss": 1.6635, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 6.4008394543546704e-06, + "loss": 1.7145, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 6.421825813221406e-06, + "loss": 1.6044, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 6.442812172088143e-06, + "loss": 1.6659, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 6.46379853095488e-06, + "loss": 1.6645, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 6.484784889821617e-06, + "loss": 1.6803, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 6.505771248688353e-06, + "loss": 1.6705, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 6.5267576075550895e-06, + "loss": 1.6768, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 6.547743966421827e-06, + "loss": 1.6768, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 6.568730325288562e-06, + "loss": 1.6345, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 6.5897166841553e-06, + "loss": 1.6363, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 6.610703043022037e-06, + "loss": 1.6689, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 6.6316894018887726e-06, + "loss": 1.6641, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 6.652675760755509e-06, + "loss": 1.7221, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 6.673662119622246e-06, + "loss": 1.6427, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 6.694648478488983e-06, + "loss": 1.6451, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 6.715634837355719e-06, + "loss": 1.8635, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 6.736621196222456e-06, + "loss": 1.6825, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 6.7576075550891924e-06, + "loss": 1.7618, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 6.778593913955928e-06, + "loss": 1.776, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 6.799580272822666e-06, + "loss": 1.6075, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 6.820566631689403e-06, + "loss": 1.5783, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 6.84155299055614e-06, + "loss": 1.6573, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 6.8625393494228755e-06, + "loss": 1.6736, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 6.883525708289612e-06, + "loss": 1.7454, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 6.904512067156349e-06, + "loss": 1.658, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 6.925498426023085e-06, + "loss": 1.645, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 6.946484784889822e-06, + "loss": 1.6697, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 6.967471143756559e-06, + "loss": 1.633, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 6.988457502623296e-06, + "loss": 1.879, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.009443861490031e-06, + "loss": 1.6834, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.030430220356769e-06, + "loss": 1.6658, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.051416579223506e-06, + "loss": 1.6606, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.072402938090242e-06, + "loss": 1.6488, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.0933892969569785e-06, + "loss": 1.6356, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.114375655823715e-06, + "loss": 1.6584, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.135362014690452e-06, + "loss": 1.6851, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.156348373557188e-06, + "loss": 1.5969, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.177334732423925e-06, + "loss": 1.6009, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.198321091290662e-06, + "loss": 1.6188, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.2193074501573976e-06, + "loss": 1.6295, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.240293809024135e-06, + "loss": 1.7956, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.261280167890872e-06, + "loss": 1.7044, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.282266526757609e-06, + "loss": 1.6785, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.303252885624345e-06, + "loss": 1.6323, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.3242392444910815e-06, + "loss": 1.5752, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.345225603357818e-06, + "loss": 1.5829, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.366211962224554e-06, + "loss": 1.6529, + "step": 351 + }, + { + "epoch": 0.04, + "learning_rate": 7.387198321091291e-06, + "loss": 1.7484, + "step": 352 + }, + { + "epoch": 0.04, + "learning_rate": 7.408184679958028e-06, + "loss": 1.6692, + "step": 353 + }, + { + "epoch": 0.04, + "learning_rate": 7.429171038824764e-06, + "loss": 1.6153, + "step": 354 + }, + { + "epoch": 0.04, + "learning_rate": 7.4501573976915005e-06, + "loss": 1.6408, + "step": 355 + }, + { + "epoch": 0.04, + "learning_rate": 7.471143756558238e-06, + "loss": 1.5987, + "step": 356 + }, + { + "epoch": 0.04, + "learning_rate": 7.492130115424975e-06, + "loss": 1.6204, + "step": 357 + }, + { + "epoch": 0.04, + "learning_rate": 7.513116474291711e-06, + "loss": 1.6793, + "step": 358 + }, + { + "epoch": 0.04, + "learning_rate": 7.534102833158448e-06, + "loss": 1.6736, + "step": 359 + }, + { + "epoch": 0.04, + "learning_rate": 7.5550891920251845e-06, + "loss": 1.6899, + "step": 360 + }, + { + "epoch": 0.04, + "learning_rate": 7.57607555089192e-06, + "loss": 1.668, + "step": 361 + }, + { + "epoch": 0.04, + "learning_rate": 7.597061909758657e-06, + "loss": 1.6286, + "step": 362 + }, + { + "epoch": 0.04, + "learning_rate": 7.618048268625394e-06, + "loss": 1.6475, + "step": 363 + }, + { + "epoch": 0.04, + "learning_rate": 7.639034627492132e-06, + "loss": 1.6378, + "step": 364 + }, + { + "epoch": 0.04, + "learning_rate": 7.660020986358867e-06, + "loss": 1.6705, + "step": 365 + }, + { + "epoch": 0.04, + "learning_rate": 7.681007345225604e-06, + "loss": 1.5835, + "step": 366 + }, + { + "epoch": 0.04, + "learning_rate": 7.70199370409234e-06, + "loss": 1.7316, + "step": 367 + }, + { + "epoch": 0.04, + "learning_rate": 7.722980062959077e-06, + "loss": 1.6678, + "step": 368 + }, + { + "epoch": 0.04, + "learning_rate": 7.743966421825814e-06, + "loss": 1.6155, + "step": 369 + }, + { + "epoch": 0.04, + "learning_rate": 7.76495278069255e-06, + "loss": 1.6493, + "step": 370 + }, + { + "epoch": 0.04, + "learning_rate": 7.785939139559287e-06, + "loss": 1.6038, + "step": 371 + }, + { + "epoch": 0.04, + "learning_rate": 7.806925498426024e-06, + "loss": 1.6313, + "step": 372 + }, + { + "epoch": 0.04, + "learning_rate": 7.827911857292761e-06, + "loss": 1.5703, + "step": 373 + }, + { + "epoch": 0.04, + "learning_rate": 7.848898216159498e-06, + "loss": 1.7095, + "step": 374 + }, + { + "epoch": 0.04, + "learning_rate": 7.869884575026233e-06, + "loss": 1.6805, + "step": 375 + }, + { + "epoch": 0.04, + "learning_rate": 7.89087093389297e-06, + "loss": 1.6683, + "step": 376 + }, + { + "epoch": 0.04, + "learning_rate": 7.911857292759706e-06, + "loss": 1.6528, + "step": 377 + }, + { + "epoch": 0.04, + "learning_rate": 7.932843651626443e-06, + "loss": 1.6633, + "step": 378 + }, + { + "epoch": 0.04, + "learning_rate": 7.95383001049318e-06, + "loss": 1.722, + "step": 379 + }, + { + "epoch": 0.04, + "learning_rate": 7.974816369359917e-06, + "loss": 1.6455, + "step": 380 + }, + { + "epoch": 0.04, + "learning_rate": 7.995802728226654e-06, + "loss": 1.7223, + "step": 381 + }, + { + "epoch": 0.04, + "learning_rate": 8.016789087093389e-06, + "loss": 1.7372, + "step": 382 + }, + { + "epoch": 0.04, + "learning_rate": 8.037775445960127e-06, + "loss": 1.7798, + "step": 383 + }, + { + "epoch": 0.04, + "learning_rate": 8.058761804826864e-06, + "loss": 1.5855, + "step": 384 + }, + { + "epoch": 0.04, + "learning_rate": 8.079748163693599e-06, + "loss": 1.651, + "step": 385 + }, + { + "epoch": 0.04, + "learning_rate": 8.100734522560336e-06, + "loss": 1.6762, + "step": 386 + }, + { + "epoch": 0.04, + "learning_rate": 8.121720881427073e-06, + "loss": 1.6231, + "step": 387 + }, + { + "epoch": 0.04, + "learning_rate": 8.14270724029381e-06, + "loss": 1.6123, + "step": 388 + }, + { + "epoch": 0.04, + "learning_rate": 8.163693599160546e-06, + "loss": 1.6126, + "step": 389 + }, + { + "epoch": 0.04, + "learning_rate": 8.184679958027283e-06, + "loss": 1.6737, + "step": 390 + }, + { + "epoch": 0.04, + "learning_rate": 8.20566631689402e-06, + "loss": 1.788, + "step": 391 + }, + { + "epoch": 0.04, + "learning_rate": 8.226652675760755e-06, + "loss": 1.6406, + "step": 392 + }, + { + "epoch": 0.04, + "learning_rate": 8.247639034627493e-06, + "loss": 1.6647, + "step": 393 + }, + { + "epoch": 0.04, + "learning_rate": 8.26862539349423e-06, + "loss": 1.6685, + "step": 394 + }, + { + "epoch": 0.04, + "learning_rate": 8.289611752360967e-06, + "loss": 1.6328, + "step": 395 + }, + { + "epoch": 0.04, + "learning_rate": 8.310598111227702e-06, + "loss": 1.5943, + "step": 396 + }, + { + "epoch": 0.04, + "learning_rate": 8.331584470094439e-06, + "loss": 1.8615, + "step": 397 + }, + { + "epoch": 0.04, + "learning_rate": 8.352570828961176e-06, + "loss": 1.6949, + "step": 398 + }, + { + "epoch": 0.04, + "eval_loss": 1.6879847049713135, + "eval_runtime": 77.2874, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 398 + }, + { + "epoch": 0.04, + "learning_rate": 8.373557187827912e-06, + "loss": 1.6748, + "step": 399 + }, + { + "epoch": 0.04, + "learning_rate": 8.39454354669465e-06, + "loss": 1.6461, + "step": 400 + }, + { + "epoch": 0.04, + "learning_rate": 8.415529905561386e-06, + "loss": 1.6726, + "step": 401 + }, + { + "epoch": 0.04, + "learning_rate": 8.436516264428123e-06, + "loss": 1.7563, + "step": 402 + }, + { + "epoch": 0.04, + "learning_rate": 8.457502623294858e-06, + "loss": 1.6398, + "step": 403 + }, + { + "epoch": 0.04, + "learning_rate": 8.478488982161596e-06, + "loss": 1.6176, + "step": 404 + }, + { + "epoch": 0.04, + "learning_rate": 8.499475341028333e-06, + "loss": 1.7346, + "step": 405 + }, + { + "epoch": 0.04, + "learning_rate": 8.520461699895068e-06, + "loss": 1.5992, + "step": 406 + }, + { + "epoch": 0.04, + "learning_rate": 8.541448058761805e-06, + "loss": 1.6699, + "step": 407 + }, + { + "epoch": 0.04, + "learning_rate": 8.562434417628542e-06, + "loss": 1.6153, + "step": 408 + }, + { + "epoch": 0.04, + "learning_rate": 8.583420776495279e-06, + "loss": 1.5813, + "step": 409 + }, + { + "epoch": 0.04, + "learning_rate": 8.604407135362015e-06, + "loss": 1.6643, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 8.625393494228752e-06, + "loss": 1.6114, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 8.646379853095489e-06, + "loss": 1.6375, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 8.667366211962224e-06, + "loss": 1.5735, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 8.688352570828963e-06, + "loss": 1.6772, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 8.7093389296957e-06, + "loss": 1.5998, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 8.730325288562436e-06, + "loss": 1.6519, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 8.751311647429171e-06, + "loss": 1.6153, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 8.772298006295908e-06, + "loss": 1.696, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 8.793284365162645e-06, + "loss": 1.8254, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 8.814270724029382e-06, + "loss": 1.6961, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 8.835257082896118e-06, + "loss": 1.7149, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 8.856243441762855e-06, + "loss": 1.6383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 8.87722980062959e-06, + "loss": 1.5654, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 8.898216159496327e-06, + "loss": 1.667, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 8.919202518363066e-06, + "loss": 1.6383, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 8.940188877229802e-06, + "loss": 1.5623, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 8.961175236096537e-06, + "loss": 1.6241, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 8.982161594963274e-06, + "loss": 1.6148, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 9.003147953830011e-06, + "loss": 1.5868, + "step": 429 + }, + { + "epoch": 0.05, + "learning_rate": 9.024134312696748e-06, + "loss": 1.567, + "step": 430 + }, + { + "epoch": 0.05, + "learning_rate": 9.045120671563485e-06, + "loss": 1.6605, + "step": 431 + }, + { + "epoch": 0.05, + "learning_rate": 9.066107030430221e-06, + "loss": 1.5792, + "step": 432 + }, + { + "epoch": 0.05, + "learning_rate": 9.087093389296958e-06, + "loss": 1.6467, + "step": 433 + }, + { + "epoch": 0.05, + "learning_rate": 9.108079748163693e-06, + "loss": 1.5783, + "step": 434 + }, + { + "epoch": 0.05, + "learning_rate": 9.129066107030432e-06, + "loss": 1.6502, + "step": 435 + }, + { + "epoch": 0.05, + "learning_rate": 9.150052465897169e-06, + "loss": 1.6256, + "step": 436 + }, + { + "epoch": 0.05, + "learning_rate": 9.171038824763904e-06, + "loss": 1.6528, + "step": 437 + }, + { + "epoch": 0.05, + "learning_rate": 9.19202518363064e-06, + "loss": 1.6235, + "step": 438 + }, + { + "epoch": 0.05, + "learning_rate": 9.213011542497377e-06, + "loss": 1.5698, + "step": 439 + }, + { + "epoch": 0.05, + "learning_rate": 9.233997901364114e-06, + "loss": 1.72, + "step": 440 + }, + { + "epoch": 0.05, + "learning_rate": 9.25498426023085e-06, + "loss": 1.6564, + "step": 441 + }, + { + "epoch": 0.05, + "learning_rate": 9.275970619097588e-06, + "loss": 1.6199, + "step": 442 + }, + { + "epoch": 0.05, + "learning_rate": 9.296956977964324e-06, + "loss": 1.629, + "step": 443 + }, + { + "epoch": 0.05, + "learning_rate": 9.31794333683106e-06, + "loss": 1.6373, + "step": 444 + }, + { + "epoch": 0.05, + "learning_rate": 9.338929695697796e-06, + "loss": 1.5384, + "step": 445 + }, + { + "epoch": 0.05, + "learning_rate": 9.359916054564535e-06, + "loss": 1.6797, + "step": 446 + }, + { + "epoch": 0.05, + "learning_rate": 9.380902413431271e-06, + "loss": 1.7051, + "step": 447 + }, + { + "epoch": 0.05, + "learning_rate": 9.401888772298007e-06, + "loss": 1.5762, + "step": 448 + }, + { + "epoch": 0.05, + "learning_rate": 9.422875131164743e-06, + "loss": 1.644, + "step": 449 + }, + { + "epoch": 0.05, + "learning_rate": 9.44386149003148e-06, + "loss": 1.6213, + "step": 450 + }, + { + "epoch": 0.05, + "learning_rate": 9.464847848898217e-06, + "loss": 1.5922, + "step": 451 + }, + { + "epoch": 0.05, + "learning_rate": 9.485834207764954e-06, + "loss": 1.6557, + "step": 452 + }, + { + "epoch": 0.05, + "learning_rate": 9.50682056663169e-06, + "loss": 1.6089, + "step": 453 + }, + { + "epoch": 0.05, + "learning_rate": 9.527806925498427e-06, + "loss": 1.5902, + "step": 454 + }, + { + "epoch": 0.05, + "learning_rate": 9.548793284365162e-06, + "loss": 1.6236, + "step": 455 + }, + { + "epoch": 0.05, + "learning_rate": 9.569779643231901e-06, + "loss": 1.5851, + "step": 456 + }, + { + "epoch": 0.05, + "learning_rate": 9.590766002098638e-06, + "loss": 1.6097, + "step": 457 + }, + { + "epoch": 0.05, + "learning_rate": 9.611752360965373e-06, + "loss": 1.6116, + "step": 458 + }, + { + "epoch": 0.05, + "learning_rate": 9.63273871983211e-06, + "loss": 1.6326, + "step": 459 + }, + { + "epoch": 0.05, + "learning_rate": 9.653725078698846e-06, + "loss": 1.6402, + "step": 460 + }, + { + "epoch": 0.05, + "learning_rate": 9.674711437565583e-06, + "loss": 1.6108, + "step": 461 + }, + { + "epoch": 0.05, + "learning_rate": 9.69569779643232e-06, + "loss": 1.6395, + "step": 462 + }, + { + "epoch": 0.05, + "learning_rate": 9.716684155299057e-06, + "loss": 1.5837, + "step": 463 + }, + { + "epoch": 0.05, + "learning_rate": 9.737670514165794e-06, + "loss": 1.6523, + "step": 464 + }, + { + "epoch": 0.05, + "learning_rate": 9.758656873032529e-06, + "loss": 1.5901, + "step": 465 + }, + { + "epoch": 0.05, + "learning_rate": 9.779643231899265e-06, + "loss": 1.5935, + "step": 466 + }, + { + "epoch": 0.05, + "learning_rate": 9.800629590766004e-06, + "loss": 1.6661, + "step": 467 + }, + { + "epoch": 0.05, + "learning_rate": 9.821615949632739e-06, + "loss": 1.6674, + "step": 468 + }, + { + "epoch": 0.05, + "learning_rate": 9.842602308499476e-06, + "loss": 1.6202, + "step": 469 + }, + { + "epoch": 0.05, + "learning_rate": 9.863588667366213e-06, + "loss": 2.3063, + "step": 470 + }, + { + "epoch": 0.05, + "learning_rate": 9.88457502623295e-06, + "loss": 1.6931, + "step": 471 + }, + { + "epoch": 0.05, + "learning_rate": 9.905561385099686e-06, + "loss": 1.6628, + "step": 472 + }, + { + "epoch": 0.05, + "learning_rate": 9.926547743966423e-06, + "loss": 1.7019, + "step": 473 + }, + { + "epoch": 0.05, + "learning_rate": 9.94753410283316e-06, + "loss": 1.6177, + "step": 474 + }, + { + "epoch": 0.05, + "learning_rate": 9.968520461699895e-06, + "loss": 1.6433, + "step": 475 + }, + { + "epoch": 0.05, + "learning_rate": 9.989506820566632e-06, + "loss": 1.5849, + "step": 476 + }, + { + "epoch": 0.05, + "learning_rate": 1.001049317943337e-05, + "loss": 1.6873, + "step": 477 + }, + { + "epoch": 0.05, + "learning_rate": 1.0031479538300107e-05, + "loss": 1.5504, + "step": 478 + }, + { + "epoch": 0.05, + "learning_rate": 1.0052465897166844e-05, + "loss": 1.7235, + "step": 479 + }, + { + "epoch": 0.05, + "learning_rate": 1.0073452256033579e-05, + "loss": 1.5909, + "step": 480 + }, + { + "epoch": 0.05, + "learning_rate": 1.0094438614900316e-05, + "loss": 1.6982, + "step": 481 + }, + { + "epoch": 0.05, + "learning_rate": 1.0115424973767052e-05, + "loss": 1.6433, + "step": 482 + }, + { + "epoch": 0.05, + "learning_rate": 1.0136411332633789e-05, + "loss": 1.6281, + "step": 483 + }, + { + "epoch": 0.05, + "learning_rate": 1.0157397691500526e-05, + "loss": 1.6722, + "step": 484 + }, + { + "epoch": 0.05, + "learning_rate": 1.0178384050367263e-05, + "loss": 1.6298, + "step": 485 + }, + { + "epoch": 0.05, + "learning_rate": 1.0199370409234e-05, + "loss": 1.5791, + "step": 486 + }, + { + "epoch": 0.05, + "learning_rate": 1.0220356768100735e-05, + "loss": 1.8025, + "step": 487 + }, + { + "epoch": 0.05, + "learning_rate": 1.0241343126967471e-05, + "loss": 1.609, + "step": 488 + }, + { + "epoch": 0.05, + "learning_rate": 1.0262329485834208e-05, + "loss": 1.6356, + "step": 489 + }, + { + "epoch": 0.05, + "learning_rate": 1.0283315844700945e-05, + "loss": 1.5952, + "step": 490 + }, + { + "epoch": 0.05, + "learning_rate": 1.0304302203567682e-05, + "loss": 1.6137, + "step": 491 + }, + { + "epoch": 0.05, + "learning_rate": 1.0325288562434418e-05, + "loss": 1.5489, + "step": 492 + }, + { + "epoch": 0.05, + "learning_rate": 1.0346274921301155e-05, + "loss": 1.625, + "step": 493 + }, + { + "epoch": 0.05, + "learning_rate": 1.036726128016789e-05, + "loss": 1.666, + "step": 494 + }, + { + "epoch": 0.05, + "learning_rate": 1.0388247639034627e-05, + "loss": 1.6412, + "step": 495 + }, + { + "epoch": 0.05, + "learning_rate": 1.0409233997901364e-05, + "loss": 1.5354, + "step": 496 + }, + { + "epoch": 0.05, + "learning_rate": 1.04302203567681e-05, + "loss": 1.6083, + "step": 497 + }, + { + "epoch": 0.05, + "learning_rate": 1.045120671563484e-05, + "loss": 1.6053, + "step": 498 + }, + { + "epoch": 0.05, + "learning_rate": 1.0472193074501576e-05, + "loss": 1.6284, + "step": 499 + }, + { + "epoch": 0.05, + "learning_rate": 1.0493179433368313e-05, + "loss": 1.62, + "step": 500 + }, + { + "epoch": 0.05, + "learning_rate": 1.0514165792235048e-05, + "loss": 1.6059, + "step": 501 + }, + { + "epoch": 0.05, + "learning_rate": 1.0535152151101785e-05, + "loss": 1.6375, + "step": 502 + }, + { + "epoch": 0.05, + "learning_rate": 1.0556138509968521e-05, + "loss": 1.5768, + "step": 503 + }, + { + "epoch": 0.05, + "learning_rate": 1.0577124868835258e-05, + "loss": 1.6851, + "step": 504 + }, + { + "epoch": 0.05, + "learning_rate": 1.0598111227701995e-05, + "loss": 1.5886, + "step": 505 + }, + { + "epoch": 0.05, + "learning_rate": 1.0619097586568732e-05, + "loss": 1.6843, + "step": 506 + }, + { + "epoch": 0.05, + "learning_rate": 1.0640083945435469e-05, + "loss": 1.6105, + "step": 507 + }, + { + "epoch": 0.05, + "learning_rate": 1.0661070304302204e-05, + "loss": 1.6059, + "step": 508 + }, + { + "epoch": 0.05, + "learning_rate": 1.068205666316894e-05, + "loss": 1.6103, + "step": 509 + }, + { + "epoch": 0.05, + "learning_rate": 1.0703043022035677e-05, + "loss": 1.5691, + "step": 510 + }, + { + "epoch": 0.05, + "learning_rate": 1.0724029380902414e-05, + "loss": 1.7106, + "step": 511 + }, + { + "epoch": 0.05, + "learning_rate": 1.0745015739769151e-05, + "loss": 1.564, + "step": 512 + }, + { + "epoch": 0.05, + "learning_rate": 1.0766002098635888e-05, + "loss": 1.5815, + "step": 513 + }, + { + "epoch": 0.05, + "learning_rate": 1.0786988457502624e-05, + "loss": 1.6302, + "step": 514 + }, + { + "epoch": 0.05, + "learning_rate": 1.080797481636936e-05, + "loss": 1.5964, + "step": 515 + }, + { + "epoch": 0.05, + "learning_rate": 1.0828961175236096e-05, + "loss": 1.5569, + "step": 516 + }, + { + "epoch": 0.05, + "learning_rate": 1.0849947534102833e-05, + "loss": 1.6172, + "step": 517 + }, + { + "epoch": 0.05, + "learning_rate": 1.087093389296957e-05, + "loss": 1.6113, + "step": 518 + }, + { + "epoch": 0.05, + "learning_rate": 1.0891920251836308e-05, + "loss": 1.614, + "step": 519 + }, + { + "epoch": 0.05, + "learning_rate": 1.0912906610703045e-05, + "loss": 1.639, + "step": 520 + }, + { + "epoch": 0.05, + "learning_rate": 1.0933892969569782e-05, + "loss": 1.656, + "step": 521 + }, + { + "epoch": 0.05, + "learning_rate": 1.0954879328436517e-05, + "loss": 1.6146, + "step": 522 + }, + { + "epoch": 0.05, + "learning_rate": 1.0975865687303254e-05, + "loss": 1.6553, + "step": 523 + }, + { + "epoch": 0.05, + "learning_rate": 1.099685204616999e-05, + "loss": 1.6367, + "step": 524 + }, + { + "epoch": 0.06, + "learning_rate": 1.1017838405036727e-05, + "loss": 1.6827, + "step": 525 + }, + { + "epoch": 0.06, + "learning_rate": 1.1038824763903464e-05, + "loss": 1.6049, + "step": 526 + }, + { + "epoch": 0.06, + "learning_rate": 1.1059811122770201e-05, + "loss": 1.5824, + "step": 527 + }, + { + "epoch": 0.06, + "learning_rate": 1.1080797481636938e-05, + "loss": 1.6282, + "step": 528 + }, + { + "epoch": 0.06, + "learning_rate": 1.1101783840503673e-05, + "loss": 1.6213, + "step": 529 + }, + { + "epoch": 0.06, + "learning_rate": 1.112277019937041e-05, + "loss": 1.6201, + "step": 530 + }, + { + "epoch": 0.06, + "learning_rate": 1.1143756558237146e-05, + "loss": 1.6007, + "step": 531 + }, + { + "epoch": 0.06, + "learning_rate": 1.1164742917103883e-05, + "loss": 1.6385, + "step": 532 + }, + { + "epoch": 0.06, + "learning_rate": 1.118572927597062e-05, + "loss": 1.614, + "step": 533 + }, + { + "epoch": 0.06, + "learning_rate": 1.1206715634837357e-05, + "loss": 1.6435, + "step": 534 + }, + { + "epoch": 0.06, + "learning_rate": 1.1227701993704094e-05, + "loss": 1.5764, + "step": 535 + }, + { + "epoch": 0.06, + "learning_rate": 1.1248688352570829e-05, + "loss": 1.67, + "step": 536 + }, + { + "epoch": 0.06, + "learning_rate": 1.1269674711437565e-05, + "loss": 1.5781, + "step": 537 + }, + { + "epoch": 0.06, + "learning_rate": 1.1290661070304302e-05, + "loss": 1.5912, + "step": 538 + }, + { + "epoch": 0.06, + "learning_rate": 1.1311647429171039e-05, + "loss": 1.5667, + "step": 539 + }, + { + "epoch": 0.06, + "learning_rate": 1.1332633788037778e-05, + "loss": 1.5808, + "step": 540 + }, + { + "epoch": 0.06, + "learning_rate": 1.1353620146904514e-05, + "loss": 1.6758, + "step": 541 + }, + { + "epoch": 0.06, + "learning_rate": 1.1374606505771251e-05, + "loss": 1.5756, + "step": 542 + }, + { + "epoch": 0.06, + "learning_rate": 1.1395592864637986e-05, + "loss": 1.6306, + "step": 543 + }, + { + "epoch": 0.06, + "learning_rate": 1.1416579223504723e-05, + "loss": 1.6251, + "step": 544 + }, + { + "epoch": 0.06, + "learning_rate": 1.143756558237146e-05, + "loss": 1.5508, + "step": 545 + }, + { + "epoch": 0.06, + "learning_rate": 1.1458551941238197e-05, + "loss": 1.5342, + "step": 546 + }, + { + "epoch": 0.06, + "learning_rate": 1.1479538300104933e-05, + "loss": 1.6361, + "step": 547 + }, + { + "epoch": 0.06, + "learning_rate": 1.150052465897167e-05, + "loss": 1.6582, + "step": 548 + }, + { + "epoch": 0.06, + "learning_rate": 1.1521511017838407e-05, + "loss": 1.6617, + "step": 549 + }, + { + "epoch": 0.06, + "learning_rate": 1.1542497376705142e-05, + "loss": 1.6189, + "step": 550 + }, + { + "epoch": 0.06, + "learning_rate": 1.1563483735571879e-05, + "loss": 1.5812, + "step": 551 + }, + { + "epoch": 0.06, + "learning_rate": 1.1584470094438616e-05, + "loss": 1.7048, + "step": 552 + }, + { + "epoch": 0.06, + "learning_rate": 1.1605456453305352e-05, + "loss": 1.6509, + "step": 553 + }, + { + "epoch": 0.06, + "learning_rate": 1.162644281217209e-05, + "loss": 1.5905, + "step": 554 + }, + { + "epoch": 0.06, + "learning_rate": 1.1647429171038826e-05, + "loss": 1.5302, + "step": 555 + }, + { + "epoch": 0.06, + "learning_rate": 1.1668415529905561e-05, + "loss": 1.5373, + "step": 556 + }, + { + "epoch": 0.06, + "learning_rate": 1.1689401888772298e-05, + "loss": 1.551, + "step": 557 + }, + { + "epoch": 0.06, + "learning_rate": 1.1710388247639035e-05, + "loss": 1.5356, + "step": 558 + }, + { + "epoch": 0.06, + "learning_rate": 1.1731374606505771e-05, + "loss": 1.5445, + "step": 559 + }, + { + "epoch": 0.06, + "learning_rate": 1.1752360965372508e-05, + "loss": 1.949, + "step": 560 + }, + { + "epoch": 0.06, + "learning_rate": 1.1773347324239247e-05, + "loss": 1.7391, + "step": 561 + }, + { + "epoch": 0.06, + "learning_rate": 1.1794333683105984e-05, + "loss": 1.5847, + "step": 562 + }, + { + "epoch": 0.06, + "learning_rate": 1.1815320041972717e-05, + "loss": 1.6091, + "step": 563 + }, + { + "epoch": 0.06, + "learning_rate": 1.1836306400839455e-05, + "loss": 1.5864, + "step": 564 + }, + { + "epoch": 0.06, + "learning_rate": 1.1857292759706192e-05, + "loss": 1.6074, + "step": 565 + }, + { + "epoch": 0.06, + "learning_rate": 1.1878279118572929e-05, + "loss": 1.5872, + "step": 566 + }, + { + "epoch": 0.06, + "learning_rate": 1.1899265477439666e-05, + "loss": 1.579, + "step": 567 + }, + { + "epoch": 0.06, + "learning_rate": 1.1920251836306403e-05, + "loss": 1.6643, + "step": 568 + }, + { + "epoch": 0.06, + "learning_rate": 1.194123819517314e-05, + "loss": 1.5755, + "step": 569 + }, + { + "epoch": 0.06, + "learning_rate": 1.1962224554039874e-05, + "loss": 1.5936, + "step": 570 + }, + { + "epoch": 0.06, + "learning_rate": 1.1983210912906611e-05, + "loss": 1.5796, + "step": 571 + }, + { + "epoch": 0.06, + "learning_rate": 1.2004197271773348e-05, + "loss": 1.6583, + "step": 572 + }, + { + "epoch": 0.06, + "learning_rate": 1.2025183630640085e-05, + "loss": 1.5116, + "step": 573 + }, + { + "epoch": 0.06, + "learning_rate": 1.2046169989506822e-05, + "loss": 1.598, + "step": 574 + }, + { + "epoch": 0.06, + "learning_rate": 1.2067156348373558e-05, + "loss": 1.6624, + "step": 575 + }, + { + "epoch": 0.06, + "learning_rate": 1.2088142707240295e-05, + "loss": 1.5728, + "step": 576 + }, + { + "epoch": 0.06, + "learning_rate": 1.210912906610703e-05, + "loss": 1.7116, + "step": 577 + }, + { + "epoch": 0.06, + "learning_rate": 1.2130115424973767e-05, + "loss": 1.8864, + "step": 578 + }, + { + "epoch": 0.06, + "learning_rate": 1.2151101783840504e-05, + "loss": 1.5962, + "step": 579 + }, + { + "epoch": 0.06, + "learning_rate": 1.217208814270724e-05, + "loss": 1.5681, + "step": 580 + }, + { + "epoch": 0.06, + "learning_rate": 1.2193074501573977e-05, + "loss": 1.638, + "step": 581 + }, + { + "epoch": 0.06, + "learning_rate": 1.2214060860440716e-05, + "loss": 1.6252, + "step": 582 + }, + { + "epoch": 0.06, + "learning_rate": 1.2235047219307453e-05, + "loss": 1.5895, + "step": 583 + }, + { + "epoch": 0.06, + "learning_rate": 1.2256033578174186e-05, + "loss": 1.6143, + "step": 584 + }, + { + "epoch": 0.06, + "learning_rate": 1.2277019937040925e-05, + "loss": 1.6593, + "step": 585 + }, + { + "epoch": 0.06, + "learning_rate": 1.2298006295907661e-05, + "loss": 1.5382, + "step": 586 + }, + { + "epoch": 0.06, + "learning_rate": 1.2318992654774398e-05, + "loss": 1.5573, + "step": 587 + }, + { + "epoch": 0.06, + "learning_rate": 1.2339979013641135e-05, + "loss": 1.5502, + "step": 588 + }, + { + "epoch": 0.06, + "learning_rate": 1.2360965372507872e-05, + "loss": 1.6078, + "step": 589 + }, + { + "epoch": 0.06, + "learning_rate": 1.2381951731374608e-05, + "loss": 1.5852, + "step": 590 + }, + { + "epoch": 0.06, + "learning_rate": 1.2402938090241344e-05, + "loss": 1.5747, + "step": 591 + }, + { + "epoch": 0.06, + "learning_rate": 1.242392444910808e-05, + "loss": 1.6304, + "step": 592 + }, + { + "epoch": 0.06, + "learning_rate": 1.2444910807974817e-05, + "loss": 1.5659, + "step": 593 + }, + { + "epoch": 0.06, + "learning_rate": 1.2465897166841554e-05, + "loss": 1.5801, + "step": 594 + }, + { + "epoch": 0.06, + "learning_rate": 1.248688352570829e-05, + "loss": 1.576, + "step": 595 + }, + { + "epoch": 0.06, + "learning_rate": 1.2507869884575028e-05, + "loss": 1.6446, + "step": 596 + }, + { + "epoch": 0.06, + "learning_rate": 1.2528856243441764e-05, + "loss": 1.6377, + "step": 597 + }, + { + "epoch": 0.06, + "eval_loss": 1.6429214477539062, + "eval_runtime": 77.2709, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 597 + }, + { + "epoch": 0.06, + "learning_rate": 1.25498426023085e-05, + "loss": 1.6151, + "step": 598 + }, + { + "epoch": 0.06, + "learning_rate": 1.2570828961175236e-05, + "loss": 2.2074, + "step": 599 + }, + { + "epoch": 0.06, + "learning_rate": 1.2591815320041973e-05, + "loss": 1.7116, + "step": 600 + }, + { + "epoch": 0.06, + "learning_rate": 1.261280167890871e-05, + "loss": 1.5336, + "step": 601 + }, + { + "epoch": 0.06, + "learning_rate": 1.2633788037775447e-05, + "loss": 1.5948, + "step": 602 + }, + { + "epoch": 0.06, + "learning_rate": 1.2654774396642185e-05, + "loss": 1.6338, + "step": 603 + }, + { + "epoch": 0.06, + "learning_rate": 1.2675760755508922e-05, + "loss": 1.5316, + "step": 604 + }, + { + "epoch": 0.06, + "learning_rate": 1.2696747114375655e-05, + "loss": 1.5703, + "step": 605 + }, + { + "epoch": 0.06, + "learning_rate": 1.2717733473242394e-05, + "loss": 1.6207, + "step": 606 + }, + { + "epoch": 0.06, + "learning_rate": 1.273871983210913e-05, + "loss": 1.625, + "step": 607 + }, + { + "epoch": 0.06, + "learning_rate": 1.2759706190975867e-05, + "loss": 1.5978, + "step": 608 + }, + { + "epoch": 0.06, + "learning_rate": 1.2780692549842604e-05, + "loss": 1.5619, + "step": 609 + }, + { + "epoch": 0.06, + "learning_rate": 1.2801678908709341e-05, + "loss": 1.6132, + "step": 610 + }, + { + "epoch": 0.06, + "learning_rate": 1.2822665267576078e-05, + "loss": 1.5934, + "step": 611 + }, + { + "epoch": 0.06, + "learning_rate": 1.2843651626442813e-05, + "loss": 1.5927, + "step": 612 + }, + { + "epoch": 0.06, + "learning_rate": 1.286463798530955e-05, + "loss": 1.5585, + "step": 613 + }, + { + "epoch": 0.06, + "learning_rate": 1.2885624344176286e-05, + "loss": 1.5742, + "step": 614 + }, + { + "epoch": 0.06, + "learning_rate": 1.2906610703043023e-05, + "loss": 1.5541, + "step": 615 + }, + { + "epoch": 0.06, + "learning_rate": 1.292759706190976e-05, + "loss": 1.7178, + "step": 616 + }, + { + "epoch": 0.06, + "learning_rate": 1.2948583420776497e-05, + "loss": 1.5816, + "step": 617 + }, + { + "epoch": 0.06, + "learning_rate": 1.2969569779643233e-05, + "loss": 1.5809, + "step": 618 + }, + { + "epoch": 0.06, + "learning_rate": 1.2990556138509969e-05, + "loss": 1.5444, + "step": 619 + }, + { + "epoch": 0.07, + "learning_rate": 1.3011542497376705e-05, + "loss": 1.6537, + "step": 620 + }, + { + "epoch": 0.07, + "learning_rate": 1.3032528856243442e-05, + "loss": 1.5833, + "step": 621 + }, + { + "epoch": 0.07, + "learning_rate": 1.3053515215110179e-05, + "loss": 1.6522, + "step": 622 + }, + { + "epoch": 0.07, + "learning_rate": 1.3074501573976916e-05, + "loss": 1.5983, + "step": 623 + }, + { + "epoch": 0.07, + "learning_rate": 1.3095487932843654e-05, + "loss": 1.4808, + "step": 624 + }, + { + "epoch": 0.07, + "learning_rate": 1.3116474291710388e-05, + "loss": 1.6065, + "step": 625 + }, + { + "epoch": 0.07, + "learning_rate": 1.3137460650577124e-05, + "loss": 1.4926, + "step": 626 + }, + { + "epoch": 0.07, + "learning_rate": 1.3158447009443863e-05, + "loss": 1.5984, + "step": 627 + }, + { + "epoch": 0.07, + "learning_rate": 1.31794333683106e-05, + "loss": 1.5363, + "step": 628 + }, + { + "epoch": 0.07, + "learning_rate": 1.3200419727177336e-05, + "loss": 1.5889, + "step": 629 + }, + { + "epoch": 0.07, + "learning_rate": 1.3221406086044073e-05, + "loss": 1.5801, + "step": 630 + }, + { + "epoch": 0.07, + "learning_rate": 1.324239244491081e-05, + "loss": 1.6418, + "step": 631 + }, + { + "epoch": 0.07, + "learning_rate": 1.3263378803777545e-05, + "loss": 1.6004, + "step": 632 + }, + { + "epoch": 0.07, + "learning_rate": 1.3284365162644282e-05, + "loss": 1.6094, + "step": 633 + }, + { + "epoch": 0.07, + "learning_rate": 1.3305351521511019e-05, + "loss": 1.5918, + "step": 634 + }, + { + "epoch": 0.07, + "learning_rate": 1.3326337880377755e-05, + "loss": 1.6469, + "step": 635 + }, + { + "epoch": 0.07, + "learning_rate": 1.3347324239244492e-05, + "loss": 1.5664, + "step": 636 + }, + { + "epoch": 0.07, + "learning_rate": 1.3368310598111229e-05, + "loss": 1.6178, + "step": 637 + }, + { + "epoch": 0.07, + "learning_rate": 1.3389296956977966e-05, + "loss": 1.6241, + "step": 638 + }, + { + "epoch": 0.07, + "learning_rate": 1.3410283315844701e-05, + "loss": 1.4875, + "step": 639 + }, + { + "epoch": 0.07, + "learning_rate": 1.3431269674711438e-05, + "loss": 1.5979, + "step": 640 + }, + { + "epoch": 0.07, + "learning_rate": 1.3452256033578175e-05, + "loss": 1.6157, + "step": 641 + }, + { + "epoch": 0.07, + "learning_rate": 1.3473242392444911e-05, + "loss": 1.5507, + "step": 642 + }, + { + "epoch": 0.07, + "learning_rate": 1.3494228751311648e-05, + "loss": 1.5974, + "step": 643 + }, + { + "epoch": 0.07, + "learning_rate": 1.3515215110178385e-05, + "loss": 1.5852, + "step": 644 + }, + { + "epoch": 0.07, + "learning_rate": 1.3536201469045123e-05, + "loss": 1.6494, + "step": 645 + }, + { + "epoch": 0.07, + "learning_rate": 1.3557187827911857e-05, + "loss": 1.6005, + "step": 646 + }, + { + "epoch": 0.07, + "learning_rate": 1.3578174186778594e-05, + "loss": 1.5783, + "step": 647 + }, + { + "epoch": 0.07, + "learning_rate": 1.3599160545645332e-05, + "loss": 1.5363, + "step": 648 + }, + { + "epoch": 0.07, + "learning_rate": 1.3620146904512069e-05, + "loss": 1.5401, + "step": 649 + }, + { + "epoch": 0.07, + "learning_rate": 1.3641133263378806e-05, + "loss": 1.611, + "step": 650 + }, + { + "epoch": 0.07, + "learning_rate": 1.3662119622245542e-05, + "loss": 1.6207, + "step": 651 + }, + { + "epoch": 0.07, + "learning_rate": 1.368310598111228e-05, + "loss": 1.5563, + "step": 652 + }, + { + "epoch": 0.07, + "learning_rate": 1.3704092339979014e-05, + "loss": 1.583, + "step": 653 + }, + { + "epoch": 0.07, + "learning_rate": 1.3725078698845751e-05, + "loss": 1.6386, + "step": 654 + }, + { + "epoch": 0.07, + "learning_rate": 1.3746065057712488e-05, + "loss": 1.5913, + "step": 655 + }, + { + "epoch": 0.07, + "learning_rate": 1.3767051416579225e-05, + "loss": 1.6088, + "step": 656 + }, + { + "epoch": 0.07, + "learning_rate": 1.3788037775445961e-05, + "loss": 1.5821, + "step": 657 + }, + { + "epoch": 0.07, + "learning_rate": 1.3809024134312698e-05, + "loss": 1.4714, + "step": 658 + }, + { + "epoch": 0.07, + "learning_rate": 1.3830010493179435e-05, + "loss": 1.5414, + "step": 659 + }, + { + "epoch": 0.07, + "learning_rate": 1.385099685204617e-05, + "loss": 1.5732, + "step": 660 + }, + { + "epoch": 0.07, + "learning_rate": 1.3871983210912907e-05, + "loss": 1.6069, + "step": 661 + }, + { + "epoch": 0.07, + "learning_rate": 1.3892969569779644e-05, + "loss": 1.6316, + "step": 662 + }, + { + "epoch": 0.07, + "learning_rate": 1.391395592864638e-05, + "loss": 1.5834, + "step": 663 + }, + { + "epoch": 0.07, + "learning_rate": 1.3934942287513117e-05, + "loss": 1.5639, + "step": 664 + }, + { + "epoch": 0.07, + "learning_rate": 1.3955928646379854e-05, + "loss": 1.5151, + "step": 665 + }, + { + "epoch": 0.07, + "learning_rate": 1.3976915005246593e-05, + "loss": 1.5352, + "step": 666 + }, + { + "epoch": 0.07, + "learning_rate": 1.3997901364113326e-05, + "loss": 1.5703, + "step": 667 + }, + { + "epoch": 0.07, + "learning_rate": 1.4018887722980063e-05, + "loss": 1.6609, + "step": 668 + }, + { + "epoch": 0.07, + "learning_rate": 1.4039874081846801e-05, + "loss": 1.5805, + "step": 669 + }, + { + "epoch": 0.07, + "learning_rate": 1.4060860440713538e-05, + "loss": 1.5583, + "step": 670 + }, + { + "epoch": 0.07, + "learning_rate": 1.4081846799580275e-05, + "loss": 1.5771, + "step": 671 + }, + { + "epoch": 0.07, + "learning_rate": 1.4102833158447012e-05, + "loss": 1.6637, + "step": 672 + }, + { + "epoch": 0.07, + "learning_rate": 1.4123819517313748e-05, + "loss": 1.5315, + "step": 673 + }, + { + "epoch": 0.07, + "learning_rate": 1.4144805876180483e-05, + "loss": 1.5379, + "step": 674 + }, + { + "epoch": 0.07, + "learning_rate": 1.416579223504722e-05, + "loss": 1.5173, + "step": 675 + }, + { + "epoch": 0.07, + "learning_rate": 1.4186778593913957e-05, + "loss": 1.5092, + "step": 676 + }, + { + "epoch": 0.07, + "learning_rate": 1.4207764952780694e-05, + "loss": 1.5365, + "step": 677 + }, + { + "epoch": 0.07, + "learning_rate": 1.422875131164743e-05, + "loss": 1.6046, + "step": 678 + }, + { + "epoch": 0.07, + "learning_rate": 1.4249737670514167e-05, + "loss": 1.6644, + "step": 679 + }, + { + "epoch": 0.07, + "learning_rate": 1.4270724029380904e-05, + "loss": 1.6196, + "step": 680 + }, + { + "epoch": 0.07, + "learning_rate": 1.429171038824764e-05, + "loss": 1.5573, + "step": 681 + }, + { + "epoch": 0.07, + "learning_rate": 1.4312696747114376e-05, + "loss": 1.5819, + "step": 682 + }, + { + "epoch": 0.07, + "learning_rate": 1.4333683105981113e-05, + "loss": 1.5788, + "step": 683 + }, + { + "epoch": 0.07, + "learning_rate": 1.435466946484785e-05, + "loss": 1.6133, + "step": 684 + }, + { + "epoch": 0.07, + "learning_rate": 1.4375655823714586e-05, + "loss": 1.5393, + "step": 685 + }, + { + "epoch": 0.07, + "learning_rate": 1.4396642182581323e-05, + "loss": 1.5798, + "step": 686 + }, + { + "epoch": 0.07, + "learning_rate": 1.4417628541448062e-05, + "loss": 1.5651, + "step": 687 + }, + { + "epoch": 0.07, + "learning_rate": 1.4438614900314795e-05, + "loss": 1.5316, + "step": 688 + }, + { + "epoch": 0.07, + "learning_rate": 1.4459601259181532e-05, + "loss": 1.604, + "step": 689 + }, + { + "epoch": 0.07, + "learning_rate": 1.448058761804827e-05, + "loss": 1.5658, + "step": 690 + }, + { + "epoch": 0.07, + "learning_rate": 1.4501573976915007e-05, + "loss": 1.5505, + "step": 691 + }, + { + "epoch": 0.07, + "learning_rate": 1.4522560335781744e-05, + "loss": 1.5486, + "step": 692 + }, + { + "epoch": 0.07, + "learning_rate": 1.454354669464848e-05, + "loss": 1.6992, + "step": 693 + }, + { + "epoch": 0.07, + "learning_rate": 1.4564533053515218e-05, + "loss": 1.6283, + "step": 694 + }, + { + "epoch": 0.07, + "learning_rate": 1.4585519412381953e-05, + "loss": 1.601, + "step": 695 + }, + { + "epoch": 0.07, + "learning_rate": 1.460650577124869e-05, + "loss": 1.6118, + "step": 696 + }, + { + "epoch": 0.07, + "learning_rate": 1.4627492130115426e-05, + "loss": 1.5565, + "step": 697 + }, + { + "epoch": 0.07, + "learning_rate": 1.4648478488982163e-05, + "loss": 1.639, + "step": 698 + }, + { + "epoch": 0.07, + "learning_rate": 1.46694648478489e-05, + "loss": 1.5883, + "step": 699 + }, + { + "epoch": 0.07, + "learning_rate": 1.4690451206715637e-05, + "loss": 1.5758, + "step": 700 + }, + { + "epoch": 0.07, + "learning_rate": 1.4711437565582372e-05, + "loss": 1.6378, + "step": 701 + }, + { + "epoch": 0.07, + "learning_rate": 1.4732423924449108e-05, + "loss": 1.6504, + "step": 702 + }, + { + "epoch": 0.07, + "learning_rate": 1.4753410283315845e-05, + "loss": 1.5978, + "step": 703 + }, + { + "epoch": 0.07, + "learning_rate": 1.4774396642182582e-05, + "loss": 1.5471, + "step": 704 + }, + { + "epoch": 0.07, + "learning_rate": 1.4795383001049319e-05, + "loss": 1.5618, + "step": 705 + }, + { + "epoch": 0.07, + "learning_rate": 1.4816369359916056e-05, + "loss": 1.6846, + "step": 706 + }, + { + "epoch": 0.07, + "learning_rate": 1.4837355718782794e-05, + "loss": 1.5838, + "step": 707 + }, + { + "epoch": 0.07, + "learning_rate": 1.4858342077649527e-05, + "loss": 1.5858, + "step": 708 + }, + { + "epoch": 0.07, + "learning_rate": 1.4879328436516264e-05, + "loss": 1.5917, + "step": 709 + }, + { + "epoch": 0.07, + "learning_rate": 1.4900314795383001e-05, + "loss": 1.5929, + "step": 710 + }, + { + "epoch": 0.07, + "learning_rate": 1.492130115424974e-05, + "loss": 1.5476, + "step": 711 + }, + { + "epoch": 0.07, + "learning_rate": 1.4942287513116476e-05, + "loss": 1.587, + "step": 712 + }, + { + "epoch": 0.07, + "learning_rate": 1.4963273871983213e-05, + "loss": 1.6299, + "step": 713 + }, + { + "epoch": 0.07, + "learning_rate": 1.498426023084995e-05, + "loss": 1.5708, + "step": 714 + }, + { + "epoch": 0.07, + "learning_rate": 1.5005246589716685e-05, + "loss": 1.6735, + "step": 715 + }, + { + "epoch": 0.08, + "learning_rate": 1.5026232948583422e-05, + "loss": 1.5452, + "step": 716 + }, + { + "epoch": 0.08, + "learning_rate": 1.5047219307450159e-05, + "loss": 1.5681, + "step": 717 + }, + { + "epoch": 0.08, + "learning_rate": 1.5068205666316895e-05, + "loss": 1.7473, + "step": 718 + }, + { + "epoch": 0.08, + "learning_rate": 1.5089192025183632e-05, + "loss": 1.5579, + "step": 719 + }, + { + "epoch": 0.08, + "learning_rate": 1.5110178384050369e-05, + "loss": 1.6335, + "step": 720 + }, + { + "epoch": 0.08, + "learning_rate": 1.5131164742917106e-05, + "loss": 1.6215, + "step": 721 + }, + { + "epoch": 0.08, + "learning_rate": 1.515215110178384e-05, + "loss": 1.5444, + "step": 722 + }, + { + "epoch": 0.08, + "learning_rate": 1.5173137460650578e-05, + "loss": 1.5838, + "step": 723 + }, + { + "epoch": 0.08, + "learning_rate": 1.5194123819517314e-05, + "loss": 1.5643, + "step": 724 + }, + { + "epoch": 0.08, + "learning_rate": 1.5215110178384051e-05, + "loss": 1.5059, + "step": 725 + }, + { + "epoch": 0.08, + "learning_rate": 1.5236096537250788e-05, + "loss": 1.5571, + "step": 726 + }, + { + "epoch": 0.08, + "learning_rate": 1.5257082896117525e-05, + "loss": 1.558, + "step": 727 + }, + { + "epoch": 0.08, + "learning_rate": 1.5278069254984263e-05, + "loss": 1.7263, + "step": 728 + }, + { + "epoch": 0.08, + "learning_rate": 1.5299055613851e-05, + "loss": 1.647, + "step": 729 + }, + { + "epoch": 0.08, + "learning_rate": 1.5320041972717733e-05, + "loss": 1.5449, + "step": 730 + }, + { + "epoch": 0.08, + "learning_rate": 1.5341028331584472e-05, + "loss": 1.5539, + "step": 731 + }, + { + "epoch": 0.08, + "learning_rate": 1.5362014690451207e-05, + "loss": 1.6365, + "step": 732 + }, + { + "epoch": 0.08, + "learning_rate": 1.5383001049317945e-05, + "loss": 1.6481, + "step": 733 + }, + { + "epoch": 0.08, + "learning_rate": 1.540398740818468e-05, + "loss": 1.6083, + "step": 734 + }, + { + "epoch": 0.08, + "learning_rate": 1.542497376705142e-05, + "loss": 1.5466, + "step": 735 + }, + { + "epoch": 0.08, + "learning_rate": 1.5445960125918154e-05, + "loss": 1.5735, + "step": 736 + }, + { + "epoch": 0.08, + "learning_rate": 1.546694648478489e-05, + "loss": 1.5326, + "step": 737 + }, + { + "epoch": 0.08, + "learning_rate": 1.5487932843651628e-05, + "loss": 1.4715, + "step": 738 + }, + { + "epoch": 0.08, + "learning_rate": 1.5508919202518363e-05, + "loss": 1.5341, + "step": 739 + }, + { + "epoch": 0.08, + "learning_rate": 1.55299055613851e-05, + "loss": 1.8178, + "step": 740 + }, + { + "epoch": 0.08, + "learning_rate": 1.555089192025184e-05, + "loss": 1.597, + "step": 741 + }, + { + "epoch": 0.08, + "learning_rate": 1.5571878279118575e-05, + "loss": 1.5185, + "step": 742 + }, + { + "epoch": 0.08, + "learning_rate": 1.559286463798531e-05, + "loss": 1.6017, + "step": 743 + }, + { + "epoch": 0.08, + "learning_rate": 1.561385099685205e-05, + "loss": 1.535, + "step": 744 + }, + { + "epoch": 0.08, + "learning_rate": 1.5634837355718784e-05, + "loss": 1.5732, + "step": 745 + }, + { + "epoch": 0.08, + "learning_rate": 1.5655823714585522e-05, + "loss": 1.4951, + "step": 746 + }, + { + "epoch": 0.08, + "learning_rate": 1.5676810073452257e-05, + "loss": 1.6071, + "step": 747 + }, + { + "epoch": 0.08, + "learning_rate": 1.5697796432318996e-05, + "loss": 1.5926, + "step": 748 + }, + { + "epoch": 0.08, + "learning_rate": 1.571878279118573e-05, + "loss": 1.5553, + "step": 749 + }, + { + "epoch": 0.08, + "learning_rate": 1.5739769150052466e-05, + "loss": 1.7759, + "step": 750 + }, + { + "epoch": 0.08, + "learning_rate": 1.5760755508919204e-05, + "loss": 1.6264, + "step": 751 + }, + { + "epoch": 0.08, + "learning_rate": 1.578174186778594e-05, + "loss": 1.5323, + "step": 752 + }, + { + "epoch": 0.08, + "learning_rate": 1.5802728226652678e-05, + "loss": 1.5629, + "step": 753 + }, + { + "epoch": 0.08, + "learning_rate": 1.5823714585519413e-05, + "loss": 1.6094, + "step": 754 + }, + { + "epoch": 0.08, + "learning_rate": 1.584470094438615e-05, + "loss": 1.6321, + "step": 755 + }, + { + "epoch": 0.08, + "learning_rate": 1.5865687303252887e-05, + "loss": 1.6866, + "step": 756 + }, + { + "epoch": 0.08, + "learning_rate": 1.588667366211962e-05, + "loss": 1.6107, + "step": 757 + }, + { + "epoch": 0.08, + "learning_rate": 1.590766002098636e-05, + "loss": 1.6612, + "step": 758 + }, + { + "epoch": 0.08, + "learning_rate": 1.5928646379853095e-05, + "loss": 1.8321, + "step": 759 + }, + { + "epoch": 0.08, + "learning_rate": 1.5949632738719834e-05, + "loss": 1.5567, + "step": 760 + }, + { + "epoch": 0.08, + "learning_rate": 1.597061909758657e-05, + "loss": 1.5805, + "step": 761 + }, + { + "epoch": 0.08, + "learning_rate": 1.5991605456453307e-05, + "loss": 1.5654, + "step": 762 + }, + { + "epoch": 0.08, + "learning_rate": 1.6012591815320046e-05, + "loss": 1.5912, + "step": 763 + }, + { + "epoch": 0.08, + "learning_rate": 1.6033578174186777e-05, + "loss": 1.4732, + "step": 764 + }, + { + "epoch": 0.08, + "learning_rate": 1.6054564533053516e-05, + "loss": 1.5568, + "step": 765 + }, + { + "epoch": 0.08, + "learning_rate": 1.6075550891920254e-05, + "loss": 1.6122, + "step": 766 + }, + { + "epoch": 0.08, + "learning_rate": 1.609653725078699e-05, + "loss": 1.5611, + "step": 767 + }, + { + "epoch": 0.08, + "learning_rate": 1.6117523609653728e-05, + "loss": 1.5996, + "step": 768 + }, + { + "epoch": 0.08, + "learning_rate": 1.6138509968520463e-05, + "loss": 1.5696, + "step": 769 + }, + { + "epoch": 0.08, + "learning_rate": 1.6159496327387198e-05, + "loss": 1.5436, + "step": 770 + }, + { + "epoch": 0.08, + "learning_rate": 1.6180482686253937e-05, + "loss": 1.5601, + "step": 771 + }, + { + "epoch": 0.08, + "learning_rate": 1.6201469045120672e-05, + "loss": 1.6172, + "step": 772 + }, + { + "epoch": 0.08, + "learning_rate": 1.622245540398741e-05, + "loss": 1.5121, + "step": 773 + }, + { + "epoch": 0.08, + "learning_rate": 1.6243441762854145e-05, + "loss": 1.5513, + "step": 774 + }, + { + "epoch": 0.08, + "learning_rate": 1.6264428121720884e-05, + "loss": 1.5661, + "step": 775 + }, + { + "epoch": 0.08, + "learning_rate": 1.628541448058762e-05, + "loss": 1.5684, + "step": 776 + }, + { + "epoch": 0.08, + "learning_rate": 1.6306400839454354e-05, + "loss": 1.5548, + "step": 777 + }, + { + "epoch": 0.08, + "learning_rate": 1.6327387198321092e-05, + "loss": 1.5235, + "step": 778 + }, + { + "epoch": 0.08, + "learning_rate": 1.6348373557187828e-05, + "loss": 1.5705, + "step": 779 + }, + { + "epoch": 0.08, + "learning_rate": 1.6369359916054566e-05, + "loss": 1.5811, + "step": 780 + }, + { + "epoch": 0.08, + "learning_rate": 1.63903462749213e-05, + "loss": 1.6117, + "step": 781 + }, + { + "epoch": 0.08, + "learning_rate": 1.641133263378804e-05, + "loss": 1.5395, + "step": 782 + }, + { + "epoch": 0.08, + "learning_rate": 1.6432318992654778e-05, + "loss": 1.543, + "step": 783 + }, + { + "epoch": 0.08, + "learning_rate": 1.645330535152151e-05, + "loss": 1.5557, + "step": 784 + }, + { + "epoch": 0.08, + "learning_rate": 1.647429171038825e-05, + "loss": 1.6305, + "step": 785 + }, + { + "epoch": 0.08, + "learning_rate": 1.6495278069254987e-05, + "loss": 1.5439, + "step": 786 + }, + { + "epoch": 0.08, + "learning_rate": 1.6516264428121722e-05, + "loss": 1.5047, + "step": 787 + }, + { + "epoch": 0.08, + "learning_rate": 1.653725078698846e-05, + "loss": 1.6241, + "step": 788 + }, + { + "epoch": 0.08, + "learning_rate": 1.6558237145855195e-05, + "loss": 1.5123, + "step": 789 + }, + { + "epoch": 0.08, + "learning_rate": 1.6579223504721934e-05, + "loss": 1.5872, + "step": 790 + }, + { + "epoch": 0.08, + "learning_rate": 1.660020986358867e-05, + "loss": 1.6289, + "step": 791 + }, + { + "epoch": 0.08, + "learning_rate": 1.6621196222455404e-05, + "loss": 1.5276, + "step": 792 + }, + { + "epoch": 0.08, + "learning_rate": 1.6642182581322143e-05, + "loss": 1.6422, + "step": 793 + }, + { + "epoch": 0.08, + "learning_rate": 1.6663168940188878e-05, + "loss": 1.634, + "step": 794 + }, + { + "epoch": 0.08, + "learning_rate": 1.6684155299055616e-05, + "loss": 1.5484, + "step": 795 + }, + { + "epoch": 0.08, + "learning_rate": 1.670514165792235e-05, + "loss": 1.6011, + "step": 796 + }, + { + "epoch": 0.08, + "eval_loss": 1.6383761167526245, + "eval_runtime": 77.154, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 796 + }, + { + "epoch": 0.08, + "learning_rate": 1.672612801678909e-05, + "loss": 1.5683, + "step": 797 + }, + { + "epoch": 0.08, + "learning_rate": 1.6747114375655825e-05, + "loss": 1.703, + "step": 798 + }, + { + "epoch": 0.08, + "learning_rate": 1.676810073452256e-05, + "loss": 1.5666, + "step": 799 + }, + { + "epoch": 0.08, + "learning_rate": 1.67890870933893e-05, + "loss": 1.586, + "step": 800 + }, + { + "epoch": 0.08, + "learning_rate": 1.6810073452256034e-05, + "loss": 1.5253, + "step": 801 + }, + { + "epoch": 0.08, + "learning_rate": 1.6831059811122772e-05, + "loss": 1.6577, + "step": 802 + }, + { + "epoch": 0.08, + "learning_rate": 1.685204616998951e-05, + "loss": 1.6639, + "step": 803 + }, + { + "epoch": 0.08, + "learning_rate": 1.6873032528856246e-05, + "loss": 1.5758, + "step": 804 + }, + { + "epoch": 0.08, + "learning_rate": 1.689401888772298e-05, + "loss": 1.624, + "step": 805 + }, + { + "epoch": 0.08, + "learning_rate": 1.6915005246589716e-05, + "loss": 1.5652, + "step": 806 + }, + { + "epoch": 0.08, + "learning_rate": 1.6935991605456454e-05, + "loss": 1.6917, + "step": 807 + }, + { + "epoch": 0.08, + "learning_rate": 1.6956977964323193e-05, + "loss": 1.5333, + "step": 808 + }, + { + "epoch": 0.08, + "learning_rate": 1.6977964323189928e-05, + "loss": 1.7285, + "step": 809 + }, + { + "epoch": 0.08, + "learning_rate": 1.6998950682056666e-05, + "loss": 1.7412, + "step": 810 + }, + { + "epoch": 0.09, + "learning_rate": 1.70199370409234e-05, + "loss": 1.6371, + "step": 811 + }, + { + "epoch": 0.09, + "learning_rate": 1.7040923399790137e-05, + "loss": 1.6427, + "step": 812 + }, + { + "epoch": 0.09, + "learning_rate": 1.7061909758656875e-05, + "loss": 1.5976, + "step": 813 + }, + { + "epoch": 0.09, + "learning_rate": 1.708289611752361e-05, + "loss": 1.5828, + "step": 814 + }, + { + "epoch": 0.09, + "learning_rate": 1.710388247639035e-05, + "loss": 1.5149, + "step": 815 + }, + { + "epoch": 0.09, + "learning_rate": 1.7124868835257084e-05, + "loss": 1.5048, + "step": 816 + }, + { + "epoch": 0.09, + "learning_rate": 1.7145855194123822e-05, + "loss": 1.5827, + "step": 817 + }, + { + "epoch": 0.09, + "learning_rate": 1.7166841552990557e-05, + "loss": 1.5407, + "step": 818 + }, + { + "epoch": 0.09, + "learning_rate": 1.7187827911857292e-05, + "loss": 1.5344, + "step": 819 + }, + { + "epoch": 0.09, + "learning_rate": 1.720881427072403e-05, + "loss": 1.6077, + "step": 820 + }, + { + "epoch": 0.09, + "learning_rate": 1.7229800629590766e-05, + "loss": 1.556, + "step": 821 + }, + { + "epoch": 0.09, + "learning_rate": 1.7250786988457504e-05, + "loss": 1.6861, + "step": 822 + }, + { + "epoch": 0.09, + "learning_rate": 1.727177334732424e-05, + "loss": 1.5831, + "step": 823 + }, + { + "epoch": 0.09, + "learning_rate": 1.7292759706190978e-05, + "loss": 1.6158, + "step": 824 + }, + { + "epoch": 0.09, + "learning_rate": 1.7313746065057716e-05, + "loss": 1.4739, + "step": 825 + }, + { + "epoch": 0.09, + "learning_rate": 1.7334732423924448e-05, + "loss": 1.5502, + "step": 826 + }, + { + "epoch": 0.09, + "learning_rate": 1.7355718782791187e-05, + "loss": 1.5744, + "step": 827 + }, + { + "epoch": 0.09, + "learning_rate": 1.7376705141657925e-05, + "loss": 1.5399, + "step": 828 + }, + { + "epoch": 0.09, + "learning_rate": 1.739769150052466e-05, + "loss": 1.606, + "step": 829 + }, + { + "epoch": 0.09, + "learning_rate": 1.74186778593914e-05, + "loss": 1.5352, + "step": 830 + }, + { + "epoch": 0.09, + "learning_rate": 1.7439664218258134e-05, + "loss": 1.6509, + "step": 831 + }, + { + "epoch": 0.09, + "learning_rate": 1.7460650577124872e-05, + "loss": 1.5447, + "step": 832 + }, + { + "epoch": 0.09, + "learning_rate": 1.7481636935991607e-05, + "loss": 1.5429, + "step": 833 + }, + { + "epoch": 0.09, + "learning_rate": 1.7502623294858342e-05, + "loss": 1.6183, + "step": 834 + }, + { + "epoch": 0.09, + "learning_rate": 1.752360965372508e-05, + "loss": 1.5557, + "step": 835 + }, + { + "epoch": 0.09, + "learning_rate": 1.7544596012591816e-05, + "loss": 1.573, + "step": 836 + }, + { + "epoch": 0.09, + "learning_rate": 1.7565582371458555e-05, + "loss": 1.5983, + "step": 837 + }, + { + "epoch": 0.09, + "learning_rate": 1.758656873032529e-05, + "loss": 1.5386, + "step": 838 + }, + { + "epoch": 0.09, + "learning_rate": 1.7607555089192028e-05, + "loss": 1.5736, + "step": 839 + }, + { + "epoch": 0.09, + "learning_rate": 1.7628541448058763e-05, + "loss": 1.5197, + "step": 840 + }, + { + "epoch": 0.09, + "learning_rate": 1.7649527806925498e-05, + "loss": 1.5786, + "step": 841 + }, + { + "epoch": 0.09, + "learning_rate": 1.7670514165792237e-05, + "loss": 1.508, + "step": 842 + }, + { + "epoch": 0.09, + "learning_rate": 1.7691500524658972e-05, + "loss": 1.6392, + "step": 843 + }, + { + "epoch": 0.09, + "learning_rate": 1.771248688352571e-05, + "loss": 1.1548, + "step": 844 + }, + { + "epoch": 0.09, + "learning_rate": 1.773347324239245e-05, + "loss": 0.9182, + "step": 845 + }, + { + "epoch": 0.09, + "learning_rate": 1.775445960125918e-05, + "loss": 0.9304, + "step": 846 + }, + { + "epoch": 0.09, + "learning_rate": 1.777544596012592e-05, + "loss": 0.8864, + "step": 847 + }, + { + "epoch": 0.09, + "learning_rate": 1.7796432318992654e-05, + "loss": 1.0287, + "step": 848 + }, + { + "epoch": 0.09, + "learning_rate": 1.7817418677859393e-05, + "loss": 1.5457, + "step": 849 + }, + { + "epoch": 0.09, + "learning_rate": 1.783840503672613e-05, + "loss": 1.6043, + "step": 850 + }, + { + "epoch": 0.09, + "learning_rate": 1.7859391395592866e-05, + "loss": 1.5983, + "step": 851 + }, + { + "epoch": 0.09, + "learning_rate": 1.7880377754459605e-05, + "loss": 1.5686, + "step": 852 + }, + { + "epoch": 0.09, + "learning_rate": 1.790136411332634e-05, + "loss": 1.5884, + "step": 853 + }, + { + "epoch": 0.09, + "learning_rate": 1.7922350472193075e-05, + "loss": 1.6224, + "step": 854 + }, + { + "epoch": 0.09, + "learning_rate": 1.7943336831059813e-05, + "loss": 1.6756, + "step": 855 + }, + { + "epoch": 0.09, + "learning_rate": 1.796432318992655e-05, + "loss": 1.6088, + "step": 856 + }, + { + "epoch": 0.09, + "learning_rate": 1.7985309548793287e-05, + "loss": 1.5734, + "step": 857 + }, + { + "epoch": 0.09, + "learning_rate": 1.8006295907660022e-05, + "loss": 1.5858, + "step": 858 + }, + { + "epoch": 0.09, + "learning_rate": 1.802728226652676e-05, + "loss": 1.5623, + "step": 859 + }, + { + "epoch": 0.09, + "learning_rate": 1.8048268625393496e-05, + "loss": 1.586, + "step": 860 + }, + { + "epoch": 0.09, + "learning_rate": 1.806925498426023e-05, + "loss": 1.5358, + "step": 861 + }, + { + "epoch": 0.09, + "learning_rate": 1.809024134312697e-05, + "loss": 1.5501, + "step": 862 + }, + { + "epoch": 0.09, + "learning_rate": 1.8111227701993704e-05, + "loss": 1.5555, + "step": 863 + }, + { + "epoch": 0.09, + "learning_rate": 1.8132214060860443e-05, + "loss": 1.5547, + "step": 864 + }, + { + "epoch": 0.09, + "learning_rate": 1.8153200419727178e-05, + "loss": 1.6531, + "step": 865 + }, + { + "epoch": 0.09, + "learning_rate": 1.8174186778593916e-05, + "loss": 1.5032, + "step": 866 + }, + { + "epoch": 0.09, + "learning_rate": 1.819517313746065e-05, + "loss": 1.5672, + "step": 867 + }, + { + "epoch": 0.09, + "learning_rate": 1.8216159496327386e-05, + "loss": 1.588, + "step": 868 + }, + { + "epoch": 0.09, + "learning_rate": 1.8237145855194125e-05, + "loss": 1.5914, + "step": 869 + }, + { + "epoch": 0.09, + "learning_rate": 1.8258132214060863e-05, + "loss": 1.5484, + "step": 870 + }, + { + "epoch": 0.09, + "learning_rate": 1.82791185729276e-05, + "loss": 1.5893, + "step": 871 + }, + { + "epoch": 0.09, + "learning_rate": 1.8300104931794337e-05, + "loss": 1.6191, + "step": 872 + }, + { + "epoch": 0.09, + "learning_rate": 1.8321091290661072e-05, + "loss": 1.55, + "step": 873 + }, + { + "epoch": 0.09, + "learning_rate": 1.8342077649527807e-05, + "loss": 1.5245, + "step": 874 + }, + { + "epoch": 0.09, + "learning_rate": 1.8363064008394546e-05, + "loss": 1.5176, + "step": 875 + }, + { + "epoch": 0.09, + "learning_rate": 1.838405036726128e-05, + "loss": 1.64, + "step": 876 + }, + { + "epoch": 0.09, + "learning_rate": 1.840503672612802e-05, + "loss": 1.5436, + "step": 877 + }, + { + "epoch": 0.09, + "learning_rate": 1.8426023084994754e-05, + "loss": 1.6874, + "step": 878 + }, + { + "epoch": 0.09, + "learning_rate": 1.8447009443861493e-05, + "loss": 1.788, + "step": 879 + }, + { + "epoch": 0.09, + "learning_rate": 1.8467995802728228e-05, + "loss": 1.5587, + "step": 880 + }, + { + "epoch": 0.09, + "learning_rate": 1.8488982161594963e-05, + "loss": 1.5652, + "step": 881 + }, + { + "epoch": 0.09, + "learning_rate": 1.85099685204617e-05, + "loss": 1.5103, + "step": 882 + }, + { + "epoch": 0.09, + "learning_rate": 1.8530954879328437e-05, + "loss": 1.5965, + "step": 883 + }, + { + "epoch": 0.09, + "learning_rate": 1.8551941238195175e-05, + "loss": 1.548, + "step": 884 + }, + { + "epoch": 0.09, + "learning_rate": 1.857292759706191e-05, + "loss": 1.6627, + "step": 885 + }, + { + "epoch": 0.09, + "learning_rate": 1.859391395592865e-05, + "loss": 1.5303, + "step": 886 + }, + { + "epoch": 0.09, + "learning_rate": 1.8614900314795387e-05, + "loss": 1.6205, + "step": 887 + }, + { + "epoch": 0.09, + "learning_rate": 1.863588667366212e-05, + "loss": 1.5995, + "step": 888 + }, + { + "epoch": 0.09, + "learning_rate": 1.8656873032528857e-05, + "loss": 1.6407, + "step": 889 + }, + { + "epoch": 0.09, + "learning_rate": 1.8677859391395592e-05, + "loss": 1.5884, + "step": 890 + }, + { + "epoch": 0.09, + "learning_rate": 1.869884575026233e-05, + "loss": 1.535, + "step": 891 + }, + { + "epoch": 0.09, + "learning_rate": 1.871983210912907e-05, + "loss": 1.5703, + "step": 892 + }, + { + "epoch": 0.09, + "learning_rate": 1.8740818467995805e-05, + "loss": 1.5606, + "step": 893 + }, + { + "epoch": 0.09, + "learning_rate": 1.8761804826862543e-05, + "loss": 1.6007, + "step": 894 + }, + { + "epoch": 0.09, + "learning_rate": 1.8782791185729278e-05, + "loss": 1.5868, + "step": 895 + }, + { + "epoch": 0.09, + "learning_rate": 1.8803777544596013e-05, + "loss": 1.5695, + "step": 896 + }, + { + "epoch": 0.09, + "learning_rate": 1.882476390346275e-05, + "loss": 1.5453, + "step": 897 + }, + { + "epoch": 0.09, + "learning_rate": 1.8845750262329487e-05, + "loss": 1.5878, + "step": 898 + }, + { + "epoch": 0.09, + "learning_rate": 1.8866736621196225e-05, + "loss": 1.5869, + "step": 899 + }, + { + "epoch": 0.09, + "learning_rate": 1.888772298006296e-05, + "loss": 1.5699, + "step": 900 + }, + { + "epoch": 0.09, + "learning_rate": 1.89087093389297e-05, + "loss": 1.567, + "step": 901 + }, + { + "epoch": 0.09, + "learning_rate": 1.8929695697796434e-05, + "loss": 1.6158, + "step": 902 + }, + { + "epoch": 0.09, + "learning_rate": 1.895068205666317e-05, + "loss": 1.5887, + "step": 903 + }, + { + "epoch": 0.09, + "learning_rate": 1.8971668415529907e-05, + "loss": 1.5829, + "step": 904 + }, + { + "epoch": 0.09, + "learning_rate": 1.8992654774396643e-05, + "loss": 1.5321, + "step": 905 + }, + { + "epoch": 0.1, + "learning_rate": 1.901364113326338e-05, + "loss": 1.5625, + "step": 906 + }, + { + "epoch": 0.1, + "learning_rate": 1.9034627492130116e-05, + "loss": 1.5512, + "step": 907 + }, + { + "epoch": 0.1, + "learning_rate": 1.9055613850996855e-05, + "loss": 1.6162, + "step": 908 + }, + { + "epoch": 0.1, + "learning_rate": 1.907660020986359e-05, + "loss": 1.5466, + "step": 909 + }, + { + "epoch": 0.1, + "learning_rate": 1.9097586568730325e-05, + "loss": 1.5268, + "step": 910 + }, + { + "epoch": 0.1, + "learning_rate": 1.9118572927597063e-05, + "loss": 1.5332, + "step": 911 + }, + { + "epoch": 0.1, + "learning_rate": 1.9139559286463802e-05, + "loss": 1.5468, + "step": 912 + }, + { + "epoch": 0.1, + "learning_rate": 1.9160545645330537e-05, + "loss": 1.6147, + "step": 913 + }, + { + "epoch": 0.1, + "learning_rate": 1.9181532004197275e-05, + "loss": 1.5977, + "step": 914 + }, + { + "epoch": 0.1, + "learning_rate": 1.920251836306401e-05, + "loss": 1.5964, + "step": 915 + }, + { + "epoch": 0.1, + "learning_rate": 1.9223504721930746e-05, + "loss": 1.55, + "step": 916 + }, + { + "epoch": 0.1, + "learning_rate": 1.9244491080797484e-05, + "loss": 1.5841, + "step": 917 + }, + { + "epoch": 0.1, + "learning_rate": 1.926547743966422e-05, + "loss": 1.6234, + "step": 918 + }, + { + "epoch": 0.1, + "learning_rate": 1.9286463798530958e-05, + "loss": 1.577, + "step": 919 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307450157397693e-05, + "loss": 1.5822, + "step": 920 + }, + { + "epoch": 0.1, + "learning_rate": 1.932843651626443e-05, + "loss": 1.5758, + "step": 921 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349422875131166e-05, + "loss": 1.5701, + "step": 922 + }, + { + "epoch": 0.1, + "learning_rate": 1.93704092339979e-05, + "loss": 1.5647, + "step": 923 + }, + { + "epoch": 0.1, + "learning_rate": 1.939139559286464e-05, + "loss": 1.5702, + "step": 924 + }, + { + "epoch": 0.1, + "learning_rate": 1.9412381951731375e-05, + "loss": 1.6056, + "step": 925 + }, + { + "epoch": 0.1, + "learning_rate": 1.9433368310598113e-05, + "loss": 1.5622, + "step": 926 + }, + { + "epoch": 0.1, + "learning_rate": 1.945435466946485e-05, + "loss": 1.639, + "step": 927 + }, + { + "epoch": 0.1, + "learning_rate": 1.9475341028331587e-05, + "loss": 1.5483, + "step": 928 + }, + { + "epoch": 0.1, + "learning_rate": 1.9496327387198322e-05, + "loss": 1.5727, + "step": 929 + }, + { + "epoch": 0.1, + "learning_rate": 1.9517313746065057e-05, + "loss": 1.5567, + "step": 930 + }, + { + "epoch": 0.1, + "learning_rate": 1.9538300104931796e-05, + "loss": 1.534, + "step": 931 + }, + { + "epoch": 0.1, + "learning_rate": 1.955928646379853e-05, + "loss": 1.5235, + "step": 932 + }, + { + "epoch": 0.1, + "learning_rate": 1.958027282266527e-05, + "loss": 1.5701, + "step": 933 + }, + { + "epoch": 0.1, + "learning_rate": 1.9601259181532008e-05, + "loss": 1.6203, + "step": 934 + }, + { + "epoch": 0.1, + "learning_rate": 1.9622245540398743e-05, + "loss": 1.532, + "step": 935 + }, + { + "epoch": 0.1, + "learning_rate": 1.9643231899265478e-05, + "loss": 1.6, + "step": 936 + }, + { + "epoch": 0.1, + "learning_rate": 1.9664218258132216e-05, + "loss": 1.5812, + "step": 937 + }, + { + "epoch": 0.1, + "learning_rate": 1.968520461699895e-05, + "loss": 1.6079, + "step": 938 + }, + { + "epoch": 0.1, + "learning_rate": 1.970619097586569e-05, + "loss": 1.5699, + "step": 939 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727177334732425e-05, + "loss": 1.5731, + "step": 940 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748163693599164e-05, + "loss": 1.6092, + "step": 941 + }, + { + "epoch": 0.1, + "learning_rate": 1.97691500524659e-05, + "loss": 1.5324, + "step": 942 + }, + { + "epoch": 0.1, + "learning_rate": 1.9790136411332634e-05, + "loss": 1.5997, + "step": 943 + }, + { + "epoch": 0.1, + "learning_rate": 1.9811122770199372e-05, + "loss": 1.6267, + "step": 944 + }, + { + "epoch": 0.1, + "learning_rate": 1.9832109129066107e-05, + "loss": 1.5912, + "step": 945 + }, + { + "epoch": 0.1, + "learning_rate": 1.9853095487932846e-05, + "loss": 1.5486, + "step": 946 + }, + { + "epoch": 0.1, + "learning_rate": 1.987408184679958e-05, + "loss": 1.5681, + "step": 947 + }, + { + "epoch": 0.1, + "learning_rate": 1.989506820566632e-05, + "loss": 1.5839, + "step": 948 + }, + { + "epoch": 0.1, + "learning_rate": 1.9916054564533054e-05, + "loss": 1.5247, + "step": 949 + }, + { + "epoch": 0.1, + "learning_rate": 1.993704092339979e-05, + "loss": 1.6515, + "step": 950 + }, + { + "epoch": 0.1, + "learning_rate": 1.9958027282266528e-05, + "loss": 1.5125, + "step": 951 + }, + { + "epoch": 0.1, + "learning_rate": 1.9979013641133263e-05, + "loss": 1.4875, + "step": 952 + }, + { + "epoch": 0.1, + "learning_rate": 2e-05, + "loss": 1.5045, + "step": 953 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999933012847e-05, + "loss": 1.5198, + "step": 954 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999997320513974e-05, + "loss": 1.6102, + "step": 955 + }, + { + "epoch": 0.1, + "learning_rate": 1.999999397115678e-05, + "loss": 1.5699, + "step": 956 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998928205733e-05, + "loss": 1.5528, + "step": 957 + }, + { + "epoch": 0.1, + "learning_rate": 1.999998325321626e-05, + "loss": 1.5786, + "step": 958 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999975884634376e-05, + "loss": 1.6234, + "step": 959 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999967176312664e-05, + "loss": 1.524, + "step": 960 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999957128252288e-05, + "loss": 1.5765, + "step": 961 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999945740454604e-05, + "loss": 1.602, + "step": 962 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999933012921127e-05, + "loss": 1.5577, + "step": 963 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999918945653563e-05, + "loss": 1.5573, + "step": 964 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999903538653807e-05, + "loss": 1.5538, + "step": 965 + }, + { + "epoch": 0.1, + "learning_rate": 1.999988679192391e-05, + "loss": 1.578, + "step": 966 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999868705466126e-05, + "loss": 1.5514, + "step": 967 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999849279282872e-05, + "loss": 1.58, + "step": 968 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999828513376753e-05, + "loss": 1.5879, + "step": 969 + }, + { + "epoch": 0.1, + "learning_rate": 1.999980640775055e-05, + "loss": 1.6396, + "step": 970 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999782962407222e-05, + "loss": 1.5468, + "step": 971 + }, + { + "epoch": 0.1, + "learning_rate": 1.999975817734992e-05, + "loss": 1.6131, + "step": 972 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999732052581954e-05, + "loss": 1.7201, + "step": 973 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999704588106822e-05, + "loss": 1.567, + "step": 974 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999675783928216e-05, + "loss": 1.5601, + "step": 975 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999645640049988e-05, + "loss": 1.3966, + "step": 976 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999614156476177e-05, + "loss": 1.5359, + "step": 977 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999581333211e-05, + "loss": 1.5001, + "step": 978 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999547170258853e-05, + "loss": 1.6212, + "step": 979 + }, + { + "epoch": 0.1, + "learning_rate": 1.999951166762432e-05, + "loss": 1.5539, + "step": 980 + }, + { + "epoch": 0.1, + "learning_rate": 1.999947482531215e-05, + "loss": 1.5813, + "step": 981 + }, + { + "epoch": 0.1, + "learning_rate": 1.999943664332728e-05, + "loss": 1.6095, + "step": 982 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999397121674828e-05, + "loss": 1.4996, + "step": 983 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999356260360086e-05, + "loss": 1.5519, + "step": 984 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999314059388534e-05, + "loss": 1.5799, + "step": 985 + }, + { + "epoch": 0.1, + "learning_rate": 1.999927051876582e-05, + "loss": 1.5265, + "step": 986 + }, + { + "epoch": 0.1, + "learning_rate": 1.999922563849778e-05, + "loss": 1.6101, + "step": 987 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999179418590427e-05, + "loss": 1.5486, + "step": 988 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999131859049954e-05, + "loss": 1.5245, + "step": 989 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999082959882727e-05, + "loss": 1.6696, + "step": 990 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999032721095303e-05, + "loss": 1.5314, + "step": 991 + }, + { + "epoch": 0.1, + "learning_rate": 1.999898114269441e-05, + "loss": 1.564, + "step": 992 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998928224686964e-05, + "loss": 1.5138, + "step": 993 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998873967080046e-05, + "loss": 1.5107, + "step": 994 + }, + { + "epoch": 0.1, + "learning_rate": 1.999881836988093e-05, + "loss": 1.5196, + "step": 995 + }, + { + "epoch": 0.1, + "eval_loss": 1.6060134172439575, + "eval_runtime": 77.2855, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 995 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998761433097066e-05, + "loss": 1.6001, + "step": 996 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998703156736078e-05, + "loss": 1.6015, + "step": 997 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998643540805776e-05, + "loss": 1.5665, + "step": 998 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998582585314145e-05, + "loss": 1.6225, + "step": 999 + }, + { + "epoch": 0.1, + "learning_rate": 1.999852029026935e-05, + "loss": 1.5486, + "step": 1000 + }, + { + "epoch": 0.1, + "learning_rate": 1.9998456655679746e-05, + "loss": 1.5435, + "step": 1001 + }, + { + "epoch": 0.11, + "learning_rate": 1.999839168155385e-05, + "loss": 1.5444, + "step": 1002 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998325367900368e-05, + "loss": 1.5587, + "step": 1003 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998257714728187e-05, + "loss": 1.5964, + "step": 1004 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998188722046366e-05, + "loss": 1.5703, + "step": 1005 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998118389864153e-05, + "loss": 1.5835, + "step": 1006 + }, + { + "epoch": 0.11, + "learning_rate": 1.999804671819097e-05, + "loss": 1.6584, + "step": 1007 + }, + { + "epoch": 0.11, + "learning_rate": 1.999797370703642e-05, + "loss": 1.8835, + "step": 1008 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997899356410276e-05, + "loss": 1.649, + "step": 1009 + }, + { + "epoch": 0.11, + "learning_rate": 1.999782366632251e-05, + "loss": 1.448, + "step": 1010 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997746636783262e-05, + "loss": 1.5062, + "step": 1011 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997668267802842e-05, + "loss": 1.533, + "step": 1012 + }, + { + "epoch": 0.11, + "learning_rate": 1.999758855939176e-05, + "loss": 1.6005, + "step": 1013 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997507511560692e-05, + "loss": 1.561, + "step": 1014 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997425124320494e-05, + "loss": 1.5232, + "step": 1015 + }, + { + "epoch": 0.11, + "learning_rate": 1.99973413976822e-05, + "loss": 1.5334, + "step": 1016 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997256331657037e-05, + "loss": 1.5691, + "step": 1017 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997169926256397e-05, + "loss": 1.6222, + "step": 1018 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997082181491855e-05, + "loss": 1.571, + "step": 1019 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996993097375164e-05, + "loss": 1.5638, + "step": 1020 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996902673918268e-05, + "loss": 1.5877, + "step": 1021 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996810911133272e-05, + "loss": 1.5456, + "step": 1022 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996717809032475e-05, + "loss": 1.5446, + "step": 1023 + }, + { + "epoch": 0.11, + "learning_rate": 1.999662336762835e-05, + "loss": 1.5521, + "step": 1024 + }, + { + "epoch": 0.11, + "learning_rate": 1.999652758693355e-05, + "loss": 1.5221, + "step": 1025 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996430466960898e-05, + "loss": 1.5721, + "step": 1026 + }, + { + "epoch": 0.11, + "learning_rate": 1.999633200772342e-05, + "loss": 1.5508, + "step": 1027 + }, + { + "epoch": 0.11, + "learning_rate": 1.99962322092343e-05, + "loss": 1.5228, + "step": 1028 + }, + { + "epoch": 0.11, + "learning_rate": 1.999613107150691e-05, + "loss": 1.523, + "step": 1029 + }, + { + "epoch": 0.11, + "learning_rate": 1.9996028594554794e-05, + "loss": 1.5308, + "step": 1030 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995924778391686e-05, + "loss": 1.5751, + "step": 1031 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995819623031498e-05, + "loss": 1.5671, + "step": 1032 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995713128488313e-05, + "loss": 1.5968, + "step": 1033 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995605294776403e-05, + "loss": 1.5225, + "step": 1034 + }, + { + "epoch": 0.11, + "learning_rate": 1.999549612191021e-05, + "loss": 1.5656, + "step": 1035 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995385609904363e-05, + "loss": 1.6424, + "step": 1036 + }, + { + "epoch": 0.11, + "learning_rate": 1.9995273758773667e-05, + "loss": 1.4378, + "step": 1037 + }, + { + "epoch": 0.11, + "learning_rate": 1.999516056853311e-05, + "loss": 1.5453, + "step": 1038 + }, + { + "epoch": 0.11, + "learning_rate": 1.999504603919785e-05, + "loss": 1.5093, + "step": 1039 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994930170783238e-05, + "loss": 1.5994, + "step": 1040 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994812963304794e-05, + "loss": 1.5814, + "step": 1041 + }, + { + "epoch": 0.11, + "learning_rate": 1.999469441677822e-05, + "loss": 1.5619, + "step": 1042 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994574531219402e-05, + "loss": 1.5861, + "step": 1043 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994453306644397e-05, + "loss": 1.6174, + "step": 1044 + }, + { + "epoch": 0.11, + "learning_rate": 1.999433074306945e-05, + "loss": 1.6974, + "step": 1045 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994206840510975e-05, + "loss": 1.7326, + "step": 1046 + }, + { + "epoch": 0.11, + "learning_rate": 1.9994081598985583e-05, + "loss": 1.5321, + "step": 1047 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993955018510044e-05, + "loss": 1.5742, + "step": 1048 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993827099101315e-05, + "loss": 1.5586, + "step": 1049 + }, + { + "epoch": 0.11, + "learning_rate": 1.999369784077654e-05, + "loss": 1.5359, + "step": 1050 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993567243553036e-05, + "loss": 1.5896, + "step": 1051 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993435307448297e-05, + "loss": 1.6072, + "step": 1052 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993302032479996e-05, + "loss": 1.6707, + "step": 1053 + }, + { + "epoch": 0.11, + "learning_rate": 1.9993167418665997e-05, + "loss": 1.5265, + "step": 1054 + }, + { + "epoch": 0.11, + "learning_rate": 1.999303146602433e-05, + "loss": 1.6136, + "step": 1055 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992894174573206e-05, + "loss": 1.6654, + "step": 1056 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992755544331022e-05, + "loss": 1.5838, + "step": 1057 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992615575316355e-05, + "loss": 1.5751, + "step": 1058 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992474267547948e-05, + "loss": 1.451, + "step": 1059 + }, + { + "epoch": 0.11, + "learning_rate": 1.999233162104474e-05, + "loss": 1.4902, + "step": 1060 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992187635825837e-05, + "loss": 1.5157, + "step": 1061 + }, + { + "epoch": 0.11, + "learning_rate": 1.9992042311910534e-05, + "loss": 1.6304, + "step": 1062 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991895649318297e-05, + "loss": 1.6828, + "step": 1063 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991747648068776e-05, + "loss": 1.5534, + "step": 1064 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991598308181802e-05, + "loss": 1.5296, + "step": 1065 + }, + { + "epoch": 0.11, + "learning_rate": 1.999144762967738e-05, + "loss": 1.5465, + "step": 1066 + }, + { + "epoch": 0.11, + "learning_rate": 1.9991295612575697e-05, + "loss": 1.5044, + "step": 1067 + }, + { + "epoch": 0.11, + "learning_rate": 1.999114225689712e-05, + "loss": 1.5644, + "step": 1068 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990987562662194e-05, + "loss": 1.5296, + "step": 1069 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990831529891645e-05, + "loss": 1.5701, + "step": 1070 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990674158606378e-05, + "loss": 1.5579, + "step": 1071 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990515448827477e-05, + "loss": 1.5989, + "step": 1072 + }, + { + "epoch": 0.11, + "learning_rate": 1.99903554005762e-05, + "loss": 1.5712, + "step": 1073 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990194013873997e-05, + "loss": 1.5244, + "step": 1074 + }, + { + "epoch": 0.11, + "learning_rate": 1.9990031288742485e-05, + "loss": 1.5237, + "step": 1075 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989867225203465e-05, + "loss": 1.5279, + "step": 1076 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989701823278917e-05, + "loss": 1.5552, + "step": 1077 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989535082991002e-05, + "loss": 1.5221, + "step": 1078 + }, + { + "epoch": 0.11, + "learning_rate": 1.998936700436206e-05, + "loss": 1.5706, + "step": 1079 + }, + { + "epoch": 0.11, + "learning_rate": 1.9989197587414605e-05, + "loss": 1.469, + "step": 1080 + }, + { + "epoch": 0.11, + "learning_rate": 1.998902683217134e-05, + "loss": 1.4973, + "step": 1081 + }, + { + "epoch": 0.11, + "learning_rate": 1.998885473865514e-05, + "loss": 1.6985, + "step": 1082 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988681306889058e-05, + "loss": 1.5801, + "step": 1083 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988506536896336e-05, + "loss": 1.4841, + "step": 1084 + }, + { + "epoch": 0.11, + "learning_rate": 1.998833042870038e-05, + "loss": 1.5433, + "step": 1085 + }, + { + "epoch": 0.11, + "learning_rate": 1.9988152982324788e-05, + "loss": 1.736, + "step": 1086 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987974197793338e-05, + "loss": 1.5823, + "step": 1087 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987794075129975e-05, + "loss": 1.528, + "step": 1088 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987612614358835e-05, + "loss": 1.5557, + "step": 1089 + }, + { + "epoch": 0.11, + "learning_rate": 1.998742981550423e-05, + "loss": 1.5393, + "step": 1090 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987245678590644e-05, + "loss": 1.538, + "step": 1091 + }, + { + "epoch": 0.11, + "learning_rate": 1.9987060203642754e-05, + "loss": 1.5764, + "step": 1092 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986873390685405e-05, + "loss": 1.4883, + "step": 1093 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986685239743625e-05, + "loss": 1.5683, + "step": 1094 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986495750842624e-05, + "loss": 1.5445, + "step": 1095 + }, + { + "epoch": 0.11, + "learning_rate": 1.9986304924007788e-05, + "loss": 1.5576, + "step": 1096 + }, + { + "epoch": 0.12, + "learning_rate": 1.998611275926468e-05, + "loss": 1.5164, + "step": 1097 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985919256639046e-05, + "loss": 1.5223, + "step": 1098 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985724416156814e-05, + "loss": 1.5501, + "step": 1099 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985528237844084e-05, + "loss": 1.5639, + "step": 1100 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985330721727144e-05, + "loss": 1.561, + "step": 1101 + }, + { + "epoch": 0.12, + "learning_rate": 1.9985131867832445e-05, + "loss": 1.4891, + "step": 1102 + }, + { + "epoch": 0.12, + "learning_rate": 1.998493167618664e-05, + "loss": 1.5038, + "step": 1103 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984730146816543e-05, + "loss": 1.5025, + "step": 1104 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984527279749157e-05, + "loss": 1.5344, + "step": 1105 + }, + { + "epoch": 0.12, + "learning_rate": 1.998432307501166e-05, + "loss": 1.5562, + "step": 1106 + }, + { + "epoch": 0.12, + "learning_rate": 1.9984117532631407e-05, + "loss": 1.5406, + "step": 1107 + }, + { + "epoch": 0.12, + "learning_rate": 1.998391065263594e-05, + "loss": 1.5669, + "step": 1108 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983702435052976e-05, + "loss": 1.569, + "step": 1109 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983492879910407e-05, + "loss": 1.6172, + "step": 1110 + }, + { + "epoch": 0.12, + "learning_rate": 1.998328198723631e-05, + "loss": 1.5511, + "step": 1111 + }, + { + "epoch": 0.12, + "learning_rate": 1.9983069757058936e-05, + "loss": 1.585, + "step": 1112 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982856189406722e-05, + "loss": 1.588, + "step": 1113 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982641284308282e-05, + "loss": 1.5751, + "step": 1114 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982425041792404e-05, + "loss": 1.5794, + "step": 1115 + }, + { + "epoch": 0.12, + "learning_rate": 1.9982207461888065e-05, + "loss": 1.5905, + "step": 1116 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981988544624404e-05, + "loss": 1.5579, + "step": 1117 + }, + { + "epoch": 0.12, + "learning_rate": 1.998176829003076e-05, + "loss": 1.5642, + "step": 1118 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981546698136638e-05, + "loss": 1.5751, + "step": 1119 + }, + { + "epoch": 0.12, + "learning_rate": 1.9981323768971727e-05, + "loss": 1.506, + "step": 1120 + }, + { + "epoch": 0.12, + "learning_rate": 1.998109950256589e-05, + "loss": 1.4748, + "step": 1121 + }, + { + "epoch": 0.12, + "learning_rate": 1.998087389894918e-05, + "loss": 1.5659, + "step": 1122 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980646958151814e-05, + "loss": 1.6106, + "step": 1123 + }, + { + "epoch": 0.12, + "learning_rate": 1.99804186802042e-05, + "loss": 1.58, + "step": 1124 + }, + { + "epoch": 0.12, + "learning_rate": 1.9980189065136924e-05, + "loss": 1.5812, + "step": 1125 + }, + { + "epoch": 0.12, + "learning_rate": 1.997995811298074e-05, + "loss": 1.6222, + "step": 1126 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979725823766602e-05, + "loss": 1.485, + "step": 1127 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979492197525622e-05, + "loss": 1.5596, + "step": 1128 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979257234289106e-05, + "loss": 1.6098, + "step": 1129 + }, + { + "epoch": 0.12, + "learning_rate": 1.9979020934088525e-05, + "loss": 1.5064, + "step": 1130 + }, + { + "epoch": 0.12, + "learning_rate": 1.997878329695554e-05, + "loss": 1.5365, + "step": 1131 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978544322921993e-05, + "loss": 1.4867, + "step": 1132 + }, + { + "epoch": 0.12, + "learning_rate": 1.9978304012019898e-05, + "loss": 1.5235, + "step": 1133 + }, + { + "epoch": 0.12, + "learning_rate": 1.997806236428145e-05, + "loss": 1.5239, + "step": 1134 + }, + { + "epoch": 0.12, + "learning_rate": 1.997781937973902e-05, + "loss": 1.4978, + "step": 1135 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977575058425166e-05, + "loss": 1.5116, + "step": 1136 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977329400372622e-05, + "loss": 1.5382, + "step": 1137 + }, + { + "epoch": 0.12, + "learning_rate": 1.9977082405614293e-05, + "loss": 1.5398, + "step": 1138 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976834074183276e-05, + "loss": 1.6178, + "step": 1139 + }, + { + "epoch": 0.12, + "learning_rate": 1.997658440611284e-05, + "loss": 1.5242, + "step": 1140 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976333401436433e-05, + "loss": 1.5686, + "step": 1141 + }, + { + "epoch": 0.12, + "learning_rate": 1.9976081060187686e-05, + "loss": 1.5536, + "step": 1142 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975827382400403e-05, + "loss": 1.5566, + "step": 1143 + }, + { + "epoch": 0.12, + "learning_rate": 1.997557236810857e-05, + "loss": 1.5506, + "step": 1144 + }, + { + "epoch": 0.12, + "learning_rate": 1.9975316017346356e-05, + "loss": 1.5996, + "step": 1145 + }, + { + "epoch": 0.12, + "learning_rate": 1.99750583301481e-05, + "loss": 1.5492, + "step": 1146 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974799306548333e-05, + "loss": 1.5857, + "step": 1147 + }, + { + "epoch": 0.12, + "learning_rate": 1.997453894658175e-05, + "loss": 1.6161, + "step": 1148 + }, + { + "epoch": 0.12, + "learning_rate": 1.9974277250283237e-05, + "loss": 1.6501, + "step": 1149 + }, + { + "epoch": 0.12, + "learning_rate": 1.997401421768785e-05, + "loss": 1.7257, + "step": 1150 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973749848830835e-05, + "loss": 1.4917, + "step": 1151 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973484143747604e-05, + "loss": 1.5374, + "step": 1152 + }, + { + "epoch": 0.12, + "learning_rate": 1.9973217102473765e-05, + "loss": 1.567, + "step": 1153 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972948725045083e-05, + "loss": 1.5835, + "step": 1154 + }, + { + "epoch": 0.12, + "learning_rate": 1.997267901149752e-05, + "loss": 1.5808, + "step": 1155 + }, + { + "epoch": 0.12, + "learning_rate": 1.9972407961867208e-05, + "loss": 1.6002, + "step": 1156 + }, + { + "epoch": 0.12, + "learning_rate": 1.997213557619046e-05, + "loss": 1.534, + "step": 1157 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971861854503772e-05, + "loss": 1.5806, + "step": 1158 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971586796843815e-05, + "loss": 1.5429, + "step": 1159 + }, + { + "epoch": 0.12, + "learning_rate": 1.997131040324744e-05, + "loss": 1.5448, + "step": 1160 + }, + { + "epoch": 0.12, + "learning_rate": 1.9971032673751673e-05, + "loss": 1.5598, + "step": 1161 + }, + { + "epoch": 0.12, + "learning_rate": 1.9970753608393727e-05, + "loss": 1.5355, + "step": 1162 + }, + { + "epoch": 0.12, + "learning_rate": 1.997047320721099e-05, + "loss": 1.5599, + "step": 1163 + }, + { + "epoch": 0.12, + "learning_rate": 1.997019147024102e-05, + "loss": 1.5372, + "step": 1164 + }, + { + "epoch": 0.12, + "learning_rate": 1.996990839752157e-05, + "loss": 1.5287, + "step": 1165 + }, + { + "epoch": 0.12, + "learning_rate": 1.9969623989090566e-05, + "loss": 1.6099, + "step": 1166 + }, + { + "epoch": 0.12, + "learning_rate": 1.996933824498611e-05, + "loss": 1.5386, + "step": 1167 + }, + { + "epoch": 0.12, + "learning_rate": 1.996905116524648e-05, + "loss": 1.5641, + "step": 1168 + }, + { + "epoch": 0.12, + "learning_rate": 1.996876274991014e-05, + "loss": 1.5728, + "step": 1169 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968472999015734e-05, + "loss": 1.4114, + "step": 1170 + }, + { + "epoch": 0.12, + "learning_rate": 1.9968181912602074e-05, + "loss": 1.5279, + "step": 1171 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967889490708164e-05, + "loss": 1.5374, + "step": 1172 + }, + { + "epoch": 0.12, + "learning_rate": 1.996759573337318e-05, + "loss": 1.699, + "step": 1173 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967300640636474e-05, + "loss": 1.6061, + "step": 1174 + }, + { + "epoch": 0.12, + "learning_rate": 1.9967004212537583e-05, + "loss": 1.4681, + "step": 1175 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966706449116225e-05, + "loss": 1.5457, + "step": 1176 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966407350412284e-05, + "loss": 1.5293, + "step": 1177 + }, + { + "epoch": 0.12, + "learning_rate": 1.9966106916465842e-05, + "loss": 1.5011, + "step": 1178 + }, + { + "epoch": 0.12, + "learning_rate": 1.996580514731714e-05, + "loss": 1.534, + "step": 1179 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965502043006613e-05, + "loss": 1.4692, + "step": 1180 + }, + { + "epoch": 0.12, + "learning_rate": 1.9965197603574867e-05, + "loss": 1.4711, + "step": 1181 + }, + { + "epoch": 0.12, + "learning_rate": 1.996489182906269e-05, + "loss": 1.4407, + "step": 1182 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964584719511048e-05, + "loss": 1.5076, + "step": 1183 + }, + { + "epoch": 0.12, + "learning_rate": 1.9964276274961086e-05, + "loss": 1.5695, + "step": 1184 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963966495454126e-05, + "loss": 1.4995, + "step": 1185 + }, + { + "epoch": 0.12, + "learning_rate": 1.996365538103167e-05, + "loss": 1.5609, + "step": 1186 + }, + { + "epoch": 0.12, + "learning_rate": 1.9963342931735402e-05, + "loss": 1.5052, + "step": 1187 + }, + { + "epoch": 0.12, + "learning_rate": 1.996302914760718e-05, + "loss": 1.4803, + "step": 1188 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962714028689046e-05, + "loss": 1.5778, + "step": 1189 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962397575023216e-05, + "loss": 1.5188, + "step": 1190 + }, + { + "epoch": 0.12, + "learning_rate": 1.9962079786652084e-05, + "loss": 1.5627, + "step": 1191 + }, + { + "epoch": 0.12, + "learning_rate": 1.9961760663618232e-05, + "loss": 1.5204, + "step": 1192 + }, + { + "epoch": 0.13, + "learning_rate": 1.9961440205964404e-05, + "loss": 1.6796, + "step": 1193 + }, + { + "epoch": 0.13, + "learning_rate": 1.996111841373354e-05, + "loss": 1.5158, + "step": 1194 + }, + { + "epoch": 0.13, + "eval_loss": 1.5832440853118896, + "eval_runtime": 77.2765, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 1194 + }, + { + "epoch": 0.13, + "learning_rate": 1.996079528696876e-05, + "loss": 1.467, + "step": 1195 + }, + { + "epoch": 0.13, + "learning_rate": 1.996047082571334e-05, + "loss": 1.5276, + "step": 1196 + }, + { + "epoch": 0.13, + "learning_rate": 1.9960145030010752e-05, + "loss": 1.4959, + "step": 1197 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959817899904654e-05, + "loss": 1.5513, + "step": 1198 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959489435438863e-05, + "loss": 1.6125, + "step": 1199 + }, + { + "epoch": 0.13, + "learning_rate": 1.9959159636657385e-05, + "loss": 1.5535, + "step": 1200 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958828503604414e-05, + "loss": 1.5446, + "step": 1201 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958496036324308e-05, + "loss": 1.4983, + "step": 1202 + }, + { + "epoch": 0.13, + "learning_rate": 1.9958162234861603e-05, + "loss": 1.5009, + "step": 1203 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957827099261027e-05, + "loss": 1.5564, + "step": 1204 + }, + { + "epoch": 0.13, + "learning_rate": 1.995749062956748e-05, + "loss": 1.4037, + "step": 1205 + }, + { + "epoch": 0.13, + "learning_rate": 1.9957152825826035e-05, + "loss": 1.607, + "step": 1206 + }, + { + "epoch": 0.13, + "learning_rate": 1.9956813688081954e-05, + "loss": 1.5404, + "step": 1207 + }, + { + "epoch": 0.13, + "learning_rate": 1.995647321638067e-05, + "loss": 1.5485, + "step": 1208 + }, + { + "epoch": 0.13, + "learning_rate": 1.99561314107678e-05, + "loss": 1.5897, + "step": 1209 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955788271289132e-05, + "loss": 1.5297, + "step": 1210 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955443797990647e-05, + "loss": 1.675, + "step": 1211 + }, + { + "epoch": 0.13, + "learning_rate": 1.9955097990918485e-05, + "loss": 1.5825, + "step": 1212 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954750850118984e-05, + "loss": 1.553, + "step": 1213 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954402375638643e-05, + "loss": 1.5298, + "step": 1214 + }, + { + "epoch": 0.13, + "learning_rate": 1.9954052567524158e-05, + "loss": 1.6591, + "step": 1215 + }, + { + "epoch": 0.13, + "learning_rate": 1.995370142582239e-05, + "loss": 1.5252, + "step": 1216 + }, + { + "epoch": 0.13, + "learning_rate": 1.995334895058038e-05, + "loss": 1.5124, + "step": 1217 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952995141845357e-05, + "loss": 1.5119, + "step": 1218 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952639999664716e-05, + "loss": 1.4908, + "step": 1219 + }, + { + "epoch": 0.13, + "learning_rate": 1.9952283524086043e-05, + "loss": 1.4798, + "step": 1220 + }, + { + "epoch": 0.13, + "learning_rate": 1.995192571515709e-05, + "loss": 1.5116, + "step": 1221 + }, + { + "epoch": 0.13, + "learning_rate": 1.99515665729258e-05, + "loss": 1.5127, + "step": 1222 + }, + { + "epoch": 0.13, + "learning_rate": 1.9951206097440284e-05, + "loss": 1.5158, + "step": 1223 + }, + { + "epoch": 0.13, + "learning_rate": 1.9950844288748842e-05, + "loss": 1.5894, + "step": 1224 + }, + { + "epoch": 0.13, + "learning_rate": 1.995048114689994e-05, + "loss": 1.6717, + "step": 1225 + }, + { + "epoch": 0.13, + "learning_rate": 1.995011667194224e-05, + "loss": 1.7595, + "step": 1226 + }, + { + "epoch": 0.13, + "learning_rate": 1.994975086392456e-05, + "loss": 1.5495, + "step": 1227 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949383722895918e-05, + "loss": 1.5844, + "step": 1228 + }, + { + "epoch": 0.13, + "learning_rate": 1.9949015248905493e-05, + "loss": 1.6022, + "step": 1229 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948645442002663e-05, + "loss": 1.5495, + "step": 1230 + }, + { + "epoch": 0.13, + "learning_rate": 1.9948274302236964e-05, + "loss": 1.5465, + "step": 1231 + }, + { + "epoch": 0.13, + "learning_rate": 1.994790182965812e-05, + "loss": 1.553, + "step": 1232 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947528024316034e-05, + "loss": 1.5895, + "step": 1233 + }, + { + "epoch": 0.13, + "learning_rate": 1.9947152886260784e-05, + "loss": 1.4625, + "step": 1234 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946776415542635e-05, + "loss": 1.5255, + "step": 1235 + }, + { + "epoch": 0.13, + "learning_rate": 1.994639861221202e-05, + "loss": 1.5293, + "step": 1236 + }, + { + "epoch": 0.13, + "learning_rate": 1.9946019476319556e-05, + "loss": 1.6018, + "step": 1237 + }, + { + "epoch": 0.13, + "learning_rate": 1.9945639007916035e-05, + "loss": 1.53, + "step": 1238 + }, + { + "epoch": 0.13, + "learning_rate": 1.994525720705243e-05, + "loss": 1.4906, + "step": 1239 + }, + { + "epoch": 0.13, + "learning_rate": 1.99448740737799e-05, + "loss": 1.5203, + "step": 1240 + }, + { + "epoch": 0.13, + "learning_rate": 1.9944489608149763e-05, + "loss": 1.532, + "step": 1241 + }, + { + "epoch": 0.13, + "learning_rate": 1.994410381021354e-05, + "loss": 1.5899, + "step": 1242 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943716680022906e-05, + "loss": 1.5295, + "step": 1243 + }, + { + "epoch": 0.13, + "learning_rate": 1.9943328217629736e-05, + "loss": 1.5269, + "step": 1244 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942938423086068e-05, + "loss": 1.5067, + "step": 1245 + }, + { + "epoch": 0.13, + "learning_rate": 1.994254729644413e-05, + "loss": 1.557, + "step": 1246 + }, + { + "epoch": 0.13, + "learning_rate": 1.9942154837756318e-05, + "loss": 1.5343, + "step": 1247 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941761047075214e-05, + "loss": 1.5815, + "step": 1248 + }, + { + "epoch": 0.13, + "learning_rate": 1.9941365924453574e-05, + "loss": 1.5704, + "step": 1249 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940969469944334e-05, + "loss": 1.5795, + "step": 1250 + }, + { + "epoch": 0.13, + "learning_rate": 1.9940571683600614e-05, + "loss": 1.4563, + "step": 1251 + }, + { + "epoch": 0.13, + "learning_rate": 1.99401725654757e-05, + "loss": 1.5214, + "step": 1252 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939772115623065e-05, + "loss": 1.4633, + "step": 1253 + }, + { + "epoch": 0.13, + "learning_rate": 1.9939370334096363e-05, + "loss": 1.5729, + "step": 1254 + }, + { + "epoch": 0.13, + "learning_rate": 1.993896722094942e-05, + "loss": 1.5483, + "step": 1255 + }, + { + "epoch": 0.13, + "learning_rate": 1.9938562776236245e-05, + "loss": 1.557, + "step": 1256 + }, + { + "epoch": 0.13, + "learning_rate": 1.993815700001102e-05, + "loss": 1.5357, + "step": 1257 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937749892328107e-05, + "loss": 1.5176, + "step": 1258 + }, + { + "epoch": 0.13, + "learning_rate": 1.9937341453242053e-05, + "loss": 1.4549, + "step": 1259 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936931682807574e-05, + "loss": 1.5058, + "step": 1260 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936520581079573e-05, + "loss": 1.5079, + "step": 1261 + }, + { + "epoch": 0.13, + "learning_rate": 1.9936108148113122e-05, + "loss": 1.4598, + "step": 1262 + }, + { + "epoch": 0.13, + "learning_rate": 1.993569438396348e-05, + "loss": 1.5505, + "step": 1263 + }, + { + "epoch": 0.13, + "learning_rate": 1.9935279288686082e-05, + "loss": 1.5665, + "step": 1264 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934862862336536e-05, + "loss": 1.4822, + "step": 1265 + }, + { + "epoch": 0.13, + "learning_rate": 1.9934445104970638e-05, + "loss": 1.4724, + "step": 1266 + }, + { + "epoch": 0.13, + "learning_rate": 1.993402601664435e-05, + "loss": 1.4477, + "step": 1267 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933605597413824e-05, + "loss": 1.4769, + "step": 1268 + }, + { + "epoch": 0.13, + "learning_rate": 1.9933183847335383e-05, + "loss": 1.5726, + "step": 1269 + }, + { + "epoch": 0.13, + "learning_rate": 1.9932760766465532e-05, + "loss": 1.4443, + "step": 1270 + }, + { + "epoch": 0.13, + "learning_rate": 1.993233635486095e-05, + "loss": 1.6652, + "step": 1271 + }, + { + "epoch": 0.13, + "learning_rate": 1.99319106125785e-05, + "loss": 1.7169, + "step": 1272 + }, + { + "epoch": 0.13, + "learning_rate": 1.9931483539675222e-05, + "loss": 1.4327, + "step": 1273 + }, + { + "epoch": 0.13, + "learning_rate": 1.993105513620833e-05, + "loss": 1.5174, + "step": 1274 + }, + { + "epoch": 0.13, + "learning_rate": 1.993062540223522e-05, + "loss": 1.5318, + "step": 1275 + }, + { + "epoch": 0.13, + "learning_rate": 1.9930194337813464e-05, + "loss": 1.4658, + "step": 1276 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929761943000815e-05, + "loss": 1.5312, + "step": 1277 + }, + { + "epoch": 0.13, + "learning_rate": 1.9929328217855203e-05, + "loss": 1.5339, + "step": 1278 + }, + { + "epoch": 0.13, + "learning_rate": 1.9928893162434738e-05, + "loss": 1.5304, + "step": 1279 + }, + { + "epoch": 0.13, + "learning_rate": 1.99284567767977e-05, + "loss": 1.5715, + "step": 1280 + }, + { + "epoch": 0.13, + "learning_rate": 1.992801906100256e-05, + "loss": 1.5644, + "step": 1281 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927580015107958e-05, + "loss": 1.5434, + "step": 1282 + }, + { + "epoch": 0.13, + "learning_rate": 1.9927139639172713e-05, + "loss": 1.7514, + "step": 1283 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926697933255828e-05, + "loss": 1.5085, + "step": 1284 + }, + { + "epoch": 0.13, + "learning_rate": 1.9926254897416476e-05, + "loss": 1.5304, + "step": 1285 + }, + { + "epoch": 0.13, + "learning_rate": 1.9925810531714015e-05, + "loss": 1.557, + "step": 1286 + }, + { + "epoch": 0.13, + "learning_rate": 1.992536483620798e-05, + "loss": 1.5159, + "step": 1287 + }, + { + "epoch": 0.14, + "learning_rate": 1.992491781095808e-05, + "loss": 1.5138, + "step": 1288 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924469456024206e-05, + "loss": 1.5264, + "step": 1289 + }, + { + "epoch": 0.14, + "learning_rate": 1.9924019771466427e-05, + "loss": 1.5213, + "step": 1290 + }, + { + "epoch": 0.14, + "learning_rate": 1.9923568757344985e-05, + "loss": 1.6664, + "step": 1291 + }, + { + "epoch": 0.14, + "learning_rate": 1.992311641372031e-05, + "loss": 1.5334, + "step": 1292 + }, + { + "epoch": 0.14, + "learning_rate": 1.9922662740653003e-05, + "loss": 1.5541, + "step": 1293 + }, + { + "epoch": 0.14, + "learning_rate": 1.992220773820384e-05, + "loss": 1.4788, + "step": 1294 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921751406433783e-05, + "loss": 1.5413, + "step": 1295 + }, + { + "epoch": 0.14, + "learning_rate": 1.9921293745403972e-05, + "loss": 1.6117, + "step": 1296 + }, + { + "epoch": 0.14, + "learning_rate": 1.9920834755175714e-05, + "loss": 1.5822, + "step": 1297 + }, + { + "epoch": 0.14, + "learning_rate": 1.992037443581051e-05, + "loss": 1.7076, + "step": 1298 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919912787370025e-05, + "loss": 1.5648, + "step": 1299 + }, + { + "epoch": 0.14, + "learning_rate": 1.9919449809916114e-05, + "loss": 1.5338, + "step": 1300 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918985503510796e-05, + "loss": 1.5155, + "step": 1301 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918519868216284e-05, + "loss": 1.5157, + "step": 1302 + }, + { + "epoch": 0.14, + "learning_rate": 1.9918052904094955e-05, + "loss": 1.5318, + "step": 1303 + }, + { + "epoch": 0.14, + "learning_rate": 1.9917584611209376e-05, + "loss": 1.6008, + "step": 1304 + }, + { + "epoch": 0.14, + "learning_rate": 1.991711498962228e-05, + "loss": 1.4786, + "step": 1305 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916644039396592e-05, + "loss": 1.5199, + "step": 1306 + }, + { + "epoch": 0.14, + "learning_rate": 1.9916171760595398e-05, + "loss": 1.5193, + "step": 1307 + }, + { + "epoch": 0.14, + "learning_rate": 1.9915698153281977e-05, + "loss": 1.5439, + "step": 1308 + }, + { + "epoch": 0.14, + "learning_rate": 1.991522321751978e-05, + "loss": 1.5282, + "step": 1309 + }, + { + "epoch": 0.14, + "learning_rate": 1.9914746953372435e-05, + "loss": 1.477, + "step": 1310 + }, + { + "epoch": 0.14, + "learning_rate": 1.991426936090375e-05, + "loss": 1.5301, + "step": 1311 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913790440177708e-05, + "loss": 1.4783, + "step": 1312 + }, + { + "epoch": 0.14, + "learning_rate": 1.9913310191258476e-05, + "loss": 1.5308, + "step": 1313 + }, + { + "epoch": 0.14, + "learning_rate": 1.991282861421039e-05, + "loss": 1.5223, + "step": 1314 + }, + { + "epoch": 0.14, + "learning_rate": 1.9912345709097974e-05, + "loss": 1.5472, + "step": 1315 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911861475985918e-05, + "loss": 1.5483, + "step": 1316 + }, + { + "epoch": 0.14, + "learning_rate": 1.9911375914939106e-05, + "loss": 1.5503, + "step": 1317 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910889026022583e-05, + "loss": 1.684, + "step": 1318 + }, + { + "epoch": 0.14, + "learning_rate": 1.9910400809301585e-05, + "loss": 1.5614, + "step": 1319 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909911264841514e-05, + "loss": 1.5388, + "step": 1320 + }, + { + "epoch": 0.14, + "learning_rate": 1.9909420392707965e-05, + "loss": 1.5537, + "step": 1321 + }, + { + "epoch": 0.14, + "learning_rate": 1.9908928192966697e-05, + "loss": 1.4993, + "step": 1322 + }, + { + "epoch": 0.14, + "learning_rate": 1.990843466568365e-05, + "loss": 1.6789, + "step": 1323 + }, + { + "epoch": 0.14, + "learning_rate": 1.990793981092495e-05, + "loss": 1.5477, + "step": 1324 + }, + { + "epoch": 0.14, + "learning_rate": 1.990744362875689e-05, + "loss": 1.5408, + "step": 1325 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906946119245945e-05, + "loss": 1.5897, + "step": 1326 + }, + { + "epoch": 0.14, + "learning_rate": 1.9906447282458777e-05, + "loss": 1.5161, + "step": 1327 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905947118462207e-05, + "loss": 1.5298, + "step": 1328 + }, + { + "epoch": 0.14, + "learning_rate": 1.9905445627323247e-05, + "loss": 1.6533, + "step": 1329 + }, + { + "epoch": 0.14, + "learning_rate": 1.9904942809109088e-05, + "loss": 1.5175, + "step": 1330 + }, + { + "epoch": 0.14, + "learning_rate": 1.990443866388709e-05, + "loss": 1.5637, + "step": 1331 + }, + { + "epoch": 0.14, + "learning_rate": 1.9903933191724798e-05, + "loss": 1.6731, + "step": 1332 + }, + { + "epoch": 0.14, + "learning_rate": 1.990342639268993e-05, + "loss": 1.5462, + "step": 1333 + }, + { + "epoch": 0.14, + "learning_rate": 1.990291826685039e-05, + "loss": 1.5438, + "step": 1334 + }, + { + "epoch": 0.14, + "learning_rate": 1.9902408814274246e-05, + "loss": 1.6058, + "step": 1335 + }, + { + "epoch": 0.14, + "learning_rate": 1.9901898035029753e-05, + "loss": 1.5122, + "step": 1336 + }, + { + "epoch": 0.14, + "learning_rate": 1.990138592918535e-05, + "loss": 1.5462, + "step": 1337 + }, + { + "epoch": 0.14, + "learning_rate": 1.9900872496809636e-05, + "loss": 1.5612, + "step": 1338 + }, + { + "epoch": 0.14, + "learning_rate": 1.99003577379714e-05, + "loss": 1.5255, + "step": 1339 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899841652739616e-05, + "loss": 1.5259, + "step": 1340 + }, + { + "epoch": 0.14, + "learning_rate": 1.9899324241183413e-05, + "loss": 1.458, + "step": 1341 + }, + { + "epoch": 0.14, + "learning_rate": 1.9898805503372118e-05, + "loss": 1.4987, + "step": 1342 + }, + { + "epoch": 0.14, + "learning_rate": 1.989828543937523e-05, + "loss": 1.5304, + "step": 1343 + }, + { + "epoch": 0.14, + "learning_rate": 1.9897764049262416e-05, + "loss": 1.5741, + "step": 1344 + }, + { + "epoch": 0.14, + "learning_rate": 1.989724133310354e-05, + "loss": 1.5537, + "step": 1345 + }, + { + "epoch": 0.14, + "learning_rate": 1.989671729096862e-05, + "loss": 1.5428, + "step": 1346 + }, + { + "epoch": 0.14, + "learning_rate": 1.9896191922927875e-05, + "loss": 1.4843, + "step": 1347 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895665229051686e-05, + "loss": 1.5322, + "step": 1348 + }, + { + "epoch": 0.14, + "learning_rate": 1.9895137209410617e-05, + "loss": 1.5133, + "step": 1349 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894607864075413e-05, + "loss": 1.5155, + "step": 1350 + }, + { + "epoch": 0.14, + "learning_rate": 1.9894077193116983e-05, + "loss": 1.5303, + "step": 1351 + }, + { + "epoch": 0.14, + "learning_rate": 1.9893545196606432e-05, + "loss": 1.549, + "step": 1352 + }, + { + "epoch": 0.14, + "learning_rate": 1.989301187461503e-05, + "loss": 1.4972, + "step": 1353 + }, + { + "epoch": 0.14, + "learning_rate": 1.989247722721423e-05, + "loss": 1.444, + "step": 1354 + }, + { + "epoch": 0.14, + "learning_rate": 1.989194125447566e-05, + "loss": 1.6561, + "step": 1355 + }, + { + "epoch": 0.14, + "learning_rate": 1.989140395647113e-05, + "loss": 1.7125, + "step": 1356 + }, + { + "epoch": 0.14, + "learning_rate": 1.989086533327262e-05, + "loss": 1.5723, + "step": 1357 + }, + { + "epoch": 0.14, + "learning_rate": 1.9890325384952293e-05, + "loss": 1.4852, + "step": 1358 + }, + { + "epoch": 0.14, + "learning_rate": 1.988978411158249e-05, + "loss": 1.591, + "step": 1359 + }, + { + "epoch": 0.14, + "learning_rate": 1.988924151323572e-05, + "loss": 1.5385, + "step": 1360 + }, + { + "epoch": 0.14, + "learning_rate": 1.9888697589984685e-05, + "loss": 1.577, + "step": 1361 + }, + { + "epoch": 0.14, + "learning_rate": 1.988815234190226e-05, + "loss": 1.4827, + "step": 1362 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887605769061484e-05, + "loss": 1.5193, + "step": 1363 + }, + { + "epoch": 0.14, + "learning_rate": 1.9887057871535588e-05, + "loss": 1.5391, + "step": 1364 + }, + { + "epoch": 0.14, + "learning_rate": 1.988650864939798e-05, + "loss": 1.7037, + "step": 1365 + }, + { + "epoch": 0.14, + "learning_rate": 1.9885958102722238e-05, + "loss": 1.4816, + "step": 1366 + }, + { + "epoch": 0.14, + "learning_rate": 1.988540623158212e-05, + "loss": 1.4663, + "step": 1367 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884853036051567e-05, + "loss": 1.5254, + "step": 1368 + }, + { + "epoch": 0.14, + "learning_rate": 1.9884298516204687e-05, + "loss": 1.5087, + "step": 1369 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883742672115777e-05, + "loss": 1.5178, + "step": 1370 + }, + { + "epoch": 0.14, + "learning_rate": 1.9883185503859302e-05, + "loss": 1.473, + "step": 1371 + }, + { + "epoch": 0.14, + "learning_rate": 1.988262701150991e-05, + "loss": 1.5245, + "step": 1372 + }, + { + "epoch": 0.14, + "learning_rate": 1.9882067195142426e-05, + "loss": 1.3492, + "step": 1373 + }, + { + "epoch": 0.14, + "learning_rate": 1.9881506054831847e-05, + "loss": 1.5338, + "step": 1374 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880943590653356e-05, + "loss": 1.5214, + "step": 1375 + }, + { + "epoch": 0.14, + "learning_rate": 1.9880379802682305e-05, + "loss": 1.4902, + "step": 1376 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879814690994226e-05, + "loss": 1.6882, + "step": 1377 + }, + { + "epoch": 0.14, + "learning_rate": 1.9879248255664836e-05, + "loss": 1.4952, + "step": 1378 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878680496770016e-05, + "loss": 1.5286, + "step": 1379 + }, + { + "epoch": 0.14, + "learning_rate": 1.9878111414385837e-05, + "loss": 1.5065, + "step": 1380 + }, + { + "epoch": 0.14, + "learning_rate": 1.9877541008588537e-05, + "loss": 1.5064, + "step": 1381 + }, + { + "epoch": 0.14, + "learning_rate": 1.9876969279454538e-05, + "loss": 1.5136, + "step": 1382 + }, + { + "epoch": 0.15, + "learning_rate": 1.9876396227060437e-05, + "loss": 1.5103, + "step": 1383 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875821851483002e-05, + "loss": 1.4873, + "step": 1384 + }, + { + "epoch": 0.15, + "learning_rate": 1.9875246152799192e-05, + "loss": 1.5025, + "step": 1385 + }, + { + "epoch": 0.15, + "learning_rate": 1.9874669131086138e-05, + "loss": 1.5064, + "step": 1386 + }, + { + "epoch": 0.15, + "learning_rate": 1.987409078642114e-05, + "loss": 1.5356, + "step": 1387 + }, + { + "epoch": 0.15, + "learning_rate": 1.987351111888168e-05, + "loss": 1.7061, + "step": 1388 + }, + { + "epoch": 0.15, + "learning_rate": 1.987293012854542e-05, + "loss": 1.5003, + "step": 1389 + }, + { + "epoch": 0.15, + "learning_rate": 1.9872347815490207e-05, + "loss": 1.541, + "step": 1390 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871764179794046e-05, + "loss": 1.5038, + "step": 1391 + }, + { + "epoch": 0.15, + "learning_rate": 1.9871179221535128e-05, + "loss": 1.502, + "step": 1392 + }, + { + "epoch": 0.15, + "learning_rate": 1.9870592940791828e-05, + "loss": 1.5181, + "step": 1393 + }, + { + "epoch": 0.15, + "eval_loss": 1.5540661811828613, + "eval_runtime": 77.2268, + "eval_samples_per_second": 1.67, + "eval_steps_per_second": 0.117, + "step": 1393 + }, + { + "epoch": 0.15, + "learning_rate": 1.987000533764269e-05, + "loss": 1.5556, + "step": 1394 + }, + { + "epoch": 0.15, + "learning_rate": 1.9869416412166443e-05, + "loss": 1.5699, + "step": 1395 + }, + { + "epoch": 0.15, + "learning_rate": 1.9868826164441977e-05, + "loss": 1.5438, + "step": 1396 + }, + { + "epoch": 0.15, + "learning_rate": 1.986823459454838e-05, + "loss": 1.6003, + "step": 1397 + }, + { + "epoch": 0.15, + "learning_rate": 1.98676417025649e-05, + "loss": 1.5009, + "step": 1398 + }, + { + "epoch": 0.15, + "learning_rate": 1.986704748857098e-05, + "loss": 1.5066, + "step": 1399 + }, + { + "epoch": 0.15, + "learning_rate": 1.9866451952646212e-05, + "loss": 1.4497, + "step": 1400 + }, + { + "epoch": 0.15, + "learning_rate": 1.98658550948704e-05, + "loss": 1.5807, + "step": 1401 + }, + { + "epoch": 0.15, + "learning_rate": 1.9865256915323495e-05, + "loss": 1.5399, + "step": 1402 + }, + { + "epoch": 0.15, + "learning_rate": 1.9864657414085648e-05, + "loss": 1.5325, + "step": 1403 + }, + { + "epoch": 0.15, + "learning_rate": 1.986405659123717e-05, + "loss": 1.6155, + "step": 1404 + }, + { + "epoch": 0.15, + "learning_rate": 1.9863454446858558e-05, + "loss": 1.5468, + "step": 1405 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862850981030482e-05, + "loss": 1.4848, + "step": 1406 + }, + { + "epoch": 0.15, + "learning_rate": 1.9862246193833793e-05, + "loss": 1.2032, + "step": 1407 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861640085349516e-05, + "loss": 1.4645, + "step": 1408 + }, + { + "epoch": 0.15, + "learning_rate": 1.9861032655658852e-05, + "loss": 1.4402, + "step": 1409 + }, + { + "epoch": 0.15, + "learning_rate": 1.9860423904843187e-05, + "loss": 1.5101, + "step": 1410 + }, + { + "epoch": 0.15, + "learning_rate": 1.985981383298407e-05, + "loss": 1.5337, + "step": 1411 + }, + { + "epoch": 0.15, + "learning_rate": 1.9859202440163243e-05, + "loss": 1.5493, + "step": 1412 + }, + { + "epoch": 0.15, + "learning_rate": 1.985858972646261e-05, + "loss": 1.5393, + "step": 1413 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857975691964264e-05, + "loss": 1.5077, + "step": 1414 + }, + { + "epoch": 0.15, + "learning_rate": 1.9857360336750465e-05, + "loss": 1.5027, + "step": 1415 + }, + { + "epoch": 0.15, + "learning_rate": 1.985674366090366e-05, + "loss": 1.5995, + "step": 1416 + }, + { + "epoch": 0.15, + "learning_rate": 1.9856125664506468e-05, + "loss": 1.6216, + "step": 1417 + }, + { + "epoch": 0.15, + "learning_rate": 1.9855506347641678e-05, + "loss": 1.6285, + "step": 1418 + }, + { + "epoch": 0.15, + "learning_rate": 1.985488571039227e-05, + "loss": 1.5688, + "step": 1419 + }, + { + "epoch": 0.15, + "learning_rate": 1.9854263752841385e-05, + "loss": 1.4989, + "step": 1420 + }, + { + "epoch": 0.15, + "learning_rate": 1.985364047507236e-05, + "loss": 1.4919, + "step": 1421 + }, + { + "epoch": 0.15, + "learning_rate": 1.9853015877168684e-05, + "loss": 1.5362, + "step": 1422 + }, + { + "epoch": 0.15, + "learning_rate": 1.985238995921405e-05, + "loss": 1.5068, + "step": 1423 + }, + { + "epoch": 0.15, + "learning_rate": 1.9851762721292314e-05, + "loss": 1.5215, + "step": 1424 + }, + { + "epoch": 0.15, + "learning_rate": 1.98511341634875e-05, + "loss": 1.6322, + "step": 1425 + }, + { + "epoch": 0.15, + "learning_rate": 1.9850504285883828e-05, + "loss": 1.589, + "step": 1426 + }, + { + "epoch": 0.15, + "learning_rate": 1.9849873088565684e-05, + "loss": 1.5862, + "step": 1427 + }, + { + "epoch": 0.15, + "learning_rate": 1.984924057161763e-05, + "loss": 1.5645, + "step": 1428 + }, + { + "epoch": 0.15, + "learning_rate": 1.9848606735124402e-05, + "loss": 1.4309, + "step": 1429 + }, + { + "epoch": 0.15, + "learning_rate": 1.984797157917093e-05, + "loss": 1.5717, + "step": 1430 + }, + { + "epoch": 0.15, + "learning_rate": 1.9847335103842297e-05, + "loss": 1.5764, + "step": 1431 + }, + { + "epoch": 0.15, + "learning_rate": 1.984669730922378e-05, + "loss": 1.4737, + "step": 1432 + }, + { + "epoch": 0.15, + "learning_rate": 1.984605819540083e-05, + "loss": 1.5157, + "step": 1433 + }, + { + "epoch": 0.15, + "learning_rate": 1.9845417762459064e-05, + "loss": 1.5413, + "step": 1434 + }, + { + "epoch": 0.15, + "learning_rate": 1.984477601048429e-05, + "loss": 1.5784, + "step": 1435 + }, + { + "epoch": 0.15, + "learning_rate": 1.984413293956248e-05, + "loss": 1.4951, + "step": 1436 + }, + { + "epoch": 0.15, + "learning_rate": 1.98434885497798e-05, + "loss": 1.4805, + "step": 1437 + }, + { + "epoch": 0.15, + "learning_rate": 1.9842842841222566e-05, + "loss": 1.5163, + "step": 1438 + }, + { + "epoch": 0.15, + "learning_rate": 1.98421958139773e-05, + "loss": 1.5094, + "step": 1439 + }, + { + "epoch": 0.15, + "learning_rate": 1.9841547468130683e-05, + "loss": 1.511, + "step": 1440 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840897803769574e-05, + "loss": 1.621, + "step": 1441 + }, + { + "epoch": 0.15, + "learning_rate": 1.9840246820981012e-05, + "loss": 1.6741, + "step": 1442 + }, + { + "epoch": 0.15, + "learning_rate": 1.9839594519852213e-05, + "loss": 1.5389, + "step": 1443 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838940900470572e-05, + "loss": 1.6525, + "step": 1444 + }, + { + "epoch": 0.15, + "learning_rate": 1.9838285962923648e-05, + "loss": 1.5325, + "step": 1445 + }, + { + "epoch": 0.15, + "learning_rate": 1.9837629707299196e-05, + "loss": 1.4859, + "step": 1446 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836972133685133e-05, + "loss": 1.4992, + "step": 1447 + }, + { + "epoch": 0.15, + "learning_rate": 1.9836313242169556e-05, + "loss": 1.4715, + "step": 1448 + }, + { + "epoch": 0.15, + "learning_rate": 1.983565303284074e-05, + "loss": 1.7241, + "step": 1449 + }, + { + "epoch": 0.15, + "learning_rate": 1.9834991505787135e-05, + "loss": 1.6196, + "step": 1450 + }, + { + "epoch": 0.15, + "learning_rate": 1.983432866109737e-05, + "loss": 1.5365, + "step": 1451 + }, + { + "epoch": 0.15, + "learning_rate": 1.9833664498860252e-05, + "loss": 1.4572, + "step": 1452 + }, + { + "epoch": 0.15, + "learning_rate": 1.983299901916476e-05, + "loss": 1.5122, + "step": 1453 + }, + { + "epoch": 0.15, + "learning_rate": 1.9832332222100046e-05, + "loss": 1.5531, + "step": 1454 + }, + { + "epoch": 0.15, + "learning_rate": 1.983166410775545e-05, + "loss": 1.5377, + "step": 1455 + }, + { + "epoch": 0.15, + "learning_rate": 1.983099467622048e-05, + "loss": 1.5294, + "step": 1456 + }, + { + "epoch": 0.15, + "learning_rate": 1.9830323927584824e-05, + "loss": 1.5397, + "step": 1457 + }, + { + "epoch": 0.15, + "learning_rate": 1.9829651861938342e-05, + "loss": 1.5659, + "step": 1458 + }, + { + "epoch": 0.15, + "learning_rate": 1.9828978479371076e-05, + "loss": 1.5035, + "step": 1459 + }, + { + "epoch": 0.15, + "learning_rate": 1.982830377997324e-05, + "loss": 1.3996, + "step": 1460 + }, + { + "epoch": 0.15, + "learning_rate": 1.9827627763835227e-05, + "loss": 1.4924, + "step": 1461 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826950431047608e-05, + "loss": 1.5412, + "step": 1462 + }, + { + "epoch": 0.15, + "learning_rate": 1.9826271781701128e-05, + "loss": 1.5036, + "step": 1463 + }, + { + "epoch": 0.15, + "learning_rate": 1.9825591815886703e-05, + "loss": 1.4907, + "step": 1464 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824910533695437e-05, + "loss": 1.4982, + "step": 1465 + }, + { + "epoch": 0.15, + "learning_rate": 1.9824227935218604e-05, + "loss": 1.466, + "step": 1466 + }, + { + "epoch": 0.15, + "learning_rate": 1.9823544020547652e-05, + "loss": 1.557, + "step": 1467 + }, + { + "epoch": 0.15, + "learning_rate": 1.982285878977421e-05, + "loss": 1.5511, + "step": 1468 + }, + { + "epoch": 0.15, + "learning_rate": 1.9822172242990078e-05, + "loss": 1.5287, + "step": 1469 + }, + { + "epoch": 0.15, + "learning_rate": 1.982148438028724e-05, + "loss": 1.532, + "step": 1470 + }, + { + "epoch": 0.15, + "learning_rate": 1.982079520175785e-05, + "loss": 1.5558, + "step": 1471 + }, + { + "epoch": 0.15, + "learning_rate": 1.9820104707494238e-05, + "loss": 1.4756, + "step": 1472 + }, + { + "epoch": 0.15, + "learning_rate": 1.9819412897588913e-05, + "loss": 1.4943, + "step": 1473 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818719772134566e-05, + "loss": 1.5284, + "step": 1474 + }, + { + "epoch": 0.15, + "learning_rate": 1.9818025331224052e-05, + "loss": 1.3625, + "step": 1475 + }, + { + "epoch": 0.15, + "learning_rate": 1.9817329574950406e-05, + "loss": 1.5042, + "step": 1476 + }, + { + "epoch": 0.15, + "learning_rate": 1.981663250340685e-05, + "loss": 1.5595, + "step": 1477 + }, + { + "epoch": 0.15, + "learning_rate": 1.981593411668677e-05, + "loss": 1.5317, + "step": 1478 + }, + { + "epoch": 0.16, + "learning_rate": 1.9815234414883723e-05, + "loss": 1.6197, + "step": 1479 + }, + { + "epoch": 0.16, + "learning_rate": 1.9814533398091463e-05, + "loss": 1.5507, + "step": 1480 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813831066403905e-05, + "loss": 1.6891, + "step": 1481 + }, + { + "epoch": 0.16, + "learning_rate": 1.9813127419915143e-05, + "loss": 1.5163, + "step": 1482 + }, + { + "epoch": 0.16, + "learning_rate": 1.9812422458719448e-05, + "loss": 1.5262, + "step": 1483 + }, + { + "epoch": 0.16, + "learning_rate": 1.9811716182911262e-05, + "loss": 1.5741, + "step": 1484 + }, + { + "epoch": 0.16, + "learning_rate": 1.981100859258521e-05, + "loss": 1.6361, + "step": 1485 + }, + { + "epoch": 0.16, + "learning_rate": 1.9810299687836093e-05, + "loss": 1.4907, + "step": 1486 + }, + { + "epoch": 0.16, + "learning_rate": 1.9809589468758886e-05, + "loss": 1.5192, + "step": 1487 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808877935448747e-05, + "loss": 1.505, + "step": 1488 + }, + { + "epoch": 0.16, + "learning_rate": 1.9808165088000986e-05, + "loss": 1.4637, + "step": 1489 + }, + { + "epoch": 0.16, + "learning_rate": 1.980745092651112e-05, + "loss": 1.4928, + "step": 1490 + }, + { + "epoch": 0.16, + "learning_rate": 1.980673545107482e-05, + "loss": 1.7325, + "step": 1491 + }, + { + "epoch": 0.16, + "learning_rate": 1.980601866178795e-05, + "loss": 1.5425, + "step": 1492 + }, + { + "epoch": 0.16, + "learning_rate": 1.9805300558746535e-05, + "loss": 1.5345, + "step": 1493 + }, + { + "epoch": 0.16, + "learning_rate": 1.9804581142046783e-05, + "loss": 1.5256, + "step": 1494 + }, + { + "epoch": 0.16, + "learning_rate": 1.980386041178508e-05, + "loss": 1.4853, + "step": 1495 + }, + { + "epoch": 0.16, + "learning_rate": 1.9803138368057985e-05, + "loss": 1.4834, + "step": 1496 + }, + { + "epoch": 0.16, + "learning_rate": 1.980241501096223e-05, + "loss": 1.504, + "step": 1497 + }, + { + "epoch": 0.16, + "learning_rate": 1.980169034059473e-05, + "loss": 1.5379, + "step": 1498 + }, + { + "epoch": 0.16, + "learning_rate": 1.980096435705257e-05, + "loss": 1.5264, + "step": 1499 + }, + { + "epoch": 0.16, + "learning_rate": 1.9800237060433014e-05, + "loss": 1.52, + "step": 1500 + }, + { + "epoch": 0.16, + "learning_rate": 1.97995084508335e-05, + "loss": 1.5411, + "step": 1501 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798778528351645e-05, + "loss": 1.509, + "step": 1502 + }, + { + "epoch": 0.16, + "learning_rate": 1.9798047293085236e-05, + "loss": 1.4869, + "step": 1503 + }, + { + "epoch": 0.16, + "learning_rate": 1.9797314745132247e-05, + "loss": 1.4347, + "step": 1504 + }, + { + "epoch": 0.16, + "learning_rate": 1.9796580884590813e-05, + "loss": 1.6105, + "step": 1505 + }, + { + "epoch": 0.16, + "learning_rate": 1.9795845711559254e-05, + "loss": 1.5335, + "step": 1506 + }, + { + "epoch": 0.16, + "learning_rate": 1.979510922613607e-05, + "loss": 1.6023, + "step": 1507 + }, + { + "epoch": 0.16, + "learning_rate": 1.9794371428419922e-05, + "loss": 1.4844, + "step": 1508 + }, + { + "epoch": 0.16, + "learning_rate": 1.9793632318509664e-05, + "loss": 1.5876, + "step": 1509 + }, + { + "epoch": 0.16, + "learning_rate": 1.9792891896504313e-05, + "loss": 1.5566, + "step": 1510 + }, + { + "epoch": 0.16, + "learning_rate": 1.979215016250307e-05, + "loss": 1.4877, + "step": 1511 + }, + { + "epoch": 0.16, + "learning_rate": 1.9791407116605304e-05, + "loss": 1.6041, + "step": 1512 + }, + { + "epoch": 0.16, + "learning_rate": 1.979066275891057e-05, + "loss": 1.6285, + "step": 1513 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789917089518584e-05, + "loss": 1.4881, + "step": 1514 + }, + { + "epoch": 0.16, + "learning_rate": 1.9789170108529256e-05, + "loss": 1.5249, + "step": 1515 + }, + { + "epoch": 0.16, + "learning_rate": 1.9788421816042657e-05, + "loss": 1.4931, + "step": 1516 + }, + { + "epoch": 0.16, + "learning_rate": 1.978767221215904e-05, + "loss": 1.5066, + "step": 1517 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786921296978834e-05, + "loss": 1.4409, + "step": 1518 + }, + { + "epoch": 0.16, + "learning_rate": 1.9786169070602638e-05, + "loss": 1.4639, + "step": 1519 + }, + { + "epoch": 0.16, + "learning_rate": 1.9785415533131237e-05, + "loss": 1.4504, + "step": 1520 + }, + { + "epoch": 0.16, + "learning_rate": 1.978466068466558e-05, + "loss": 1.5162, + "step": 1521 + }, + { + "epoch": 0.16, + "learning_rate": 1.97839045253068e-05, + "loss": 1.5009, + "step": 1522 + }, + { + "epoch": 0.16, + "learning_rate": 1.9783147055156203e-05, + "loss": 1.5544, + "step": 1523 + }, + { + "epoch": 0.16, + "learning_rate": 1.9782388274315272e-05, + "loss": 1.439, + "step": 1524 + }, + { + "epoch": 0.16, + "learning_rate": 1.9781628182885662e-05, + "loss": 1.5164, + "step": 1525 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780866780969208e-05, + "loss": 1.5664, + "step": 1526 + }, + { + "epoch": 0.16, + "learning_rate": 1.9780104068667912e-05, + "loss": 1.5479, + "step": 1527 + }, + { + "epoch": 0.16, + "learning_rate": 1.9779340046083968e-05, + "loss": 1.588, + "step": 1528 + }, + { + "epoch": 0.16, + "learning_rate": 1.9778574713319726e-05, + "loss": 1.5177, + "step": 1529 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777808070477726e-05, + "loss": 1.5231, + "step": 1530 + }, + { + "epoch": 0.16, + "learning_rate": 1.9777040117660676e-05, + "loss": 1.4482, + "step": 1531 + }, + { + "epoch": 0.16, + "learning_rate": 1.9776270854971466e-05, + "loss": 1.6153, + "step": 1532 + }, + { + "epoch": 0.16, + "learning_rate": 1.9775500282513153e-05, + "loss": 1.4942, + "step": 1533 + }, + { + "epoch": 0.16, + "learning_rate": 1.9774728400388973e-05, + "loss": 1.5073, + "step": 1534 + }, + { + "epoch": 0.16, + "learning_rate": 1.9773955208702346e-05, + "loss": 1.5183, + "step": 1535 + }, + { + "epoch": 0.16, + "learning_rate": 1.977318070755685e-05, + "loss": 1.4683, + "step": 1536 + }, + { + "epoch": 0.16, + "learning_rate": 1.9772404897056255e-05, + "loss": 1.508, + "step": 1537 + }, + { + "epoch": 0.16, + "learning_rate": 1.97716277773045e-05, + "loss": 1.4162, + "step": 1538 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770849348405693e-05, + "loss": 1.7016, + "step": 1539 + }, + { + "epoch": 0.16, + "learning_rate": 1.9770069610464127e-05, + "loss": 1.563, + "step": 1540 + }, + { + "epoch": 0.16, + "learning_rate": 1.976928856358427e-05, + "loss": 1.4684, + "step": 1541 + }, + { + "epoch": 0.16, + "learning_rate": 1.9768506207870754e-05, + "loss": 1.4793, + "step": 1542 + }, + { + "epoch": 0.16, + "learning_rate": 1.9767722543428408e-05, + "loss": 1.4873, + "step": 1543 + }, + { + "epoch": 0.16, + "learning_rate": 1.9766937570362205e-05, + "loss": 1.5214, + "step": 1544 + }, + { + "epoch": 0.16, + "learning_rate": 1.976615128877733e-05, + "loss": 1.432, + "step": 1545 + }, + { + "epoch": 0.16, + "learning_rate": 1.976536369877911e-05, + "loss": 1.5505, + "step": 1546 + }, + { + "epoch": 0.16, + "learning_rate": 1.976457480047307e-05, + "loss": 1.4637, + "step": 1547 + }, + { + "epoch": 0.16, + "learning_rate": 1.9763784593964895e-05, + "loss": 1.5864, + "step": 1548 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762993079360463e-05, + "loss": 1.4304, + "step": 1549 + }, + { + "epoch": 0.16, + "learning_rate": 1.9762200256765805e-05, + "loss": 1.5836, + "step": 1550 + }, + { + "epoch": 0.16, + "learning_rate": 1.9761406126287147e-05, + "loss": 1.5544, + "step": 1551 + }, + { + "epoch": 0.16, + "learning_rate": 1.9760610688030876e-05, + "loss": 1.4907, + "step": 1552 + }, + { + "epoch": 0.16, + "learning_rate": 1.975981394210357e-05, + "loss": 1.5456, + "step": 1553 + }, + { + "epoch": 0.16, + "learning_rate": 1.9759015888611958e-05, + "loss": 1.5319, + "step": 1554 + }, + { + "epoch": 0.16, + "learning_rate": 1.975821652766297e-05, + "loss": 1.5175, + "step": 1555 + }, + { + "epoch": 0.16, + "learning_rate": 1.97574158593637e-05, + "loss": 1.5868, + "step": 1556 + }, + { + "epoch": 0.16, + "learning_rate": 1.975661388382141e-05, + "loss": 1.4747, + "step": 1557 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755810601143547e-05, + "loss": 1.4935, + "step": 1558 + }, + { + "epoch": 0.16, + "learning_rate": 1.9755006011437733e-05, + "loss": 1.5117, + "step": 1559 + }, + { + "epoch": 0.16, + "learning_rate": 1.975420011481176e-05, + "loss": 1.5053, + "step": 1560 + }, + { + "epoch": 0.16, + "learning_rate": 1.9753392911373598e-05, + "loss": 1.5281, + "step": 1561 + }, + { + "epoch": 0.16, + "learning_rate": 1.975258440123139e-05, + "loss": 1.6066, + "step": 1562 + }, + { + "epoch": 0.16, + "learning_rate": 1.9751774584493457e-05, + "loss": 1.47, + "step": 1563 + }, + { + "epoch": 0.16, + "learning_rate": 1.975096346126829e-05, + "loss": 1.4469, + "step": 1564 + }, + { + "epoch": 0.16, + "learning_rate": 1.9750151031664567e-05, + "loss": 1.4246, + "step": 1565 + }, + { + "epoch": 0.16, + "learning_rate": 1.9749337295791127e-05, + "loss": 1.484, + "step": 1566 + }, + { + "epoch": 0.16, + "learning_rate": 1.9748522253756993e-05, + "loss": 1.5078, + "step": 1567 + }, + { + "epoch": 0.16, + "learning_rate": 1.9747705905671352e-05, + "loss": 1.4212, + "step": 1568 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746888251643585e-05, + "loss": 1.5456, + "step": 1569 + }, + { + "epoch": 0.16, + "learning_rate": 1.9746069291783222e-05, + "loss": 1.4714, + "step": 1570 + }, + { + "epoch": 0.16, + "learning_rate": 1.97452490262e-05, + "loss": 1.6635, + "step": 1571 + }, + { + "epoch": 0.16, + "learning_rate": 1.9744427455003796e-05, + "loss": 1.5673, + "step": 1572 + }, + { + "epoch": 0.16, + "learning_rate": 1.974360457830469e-05, + "loss": 1.509, + "step": 1573 + }, + { + "epoch": 0.17, + "learning_rate": 1.974278039621293e-05, + "loss": 1.5395, + "step": 1574 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741954908838925e-05, + "loss": 1.5275, + "step": 1575 + }, + { + "epoch": 0.17, + "learning_rate": 1.9741128116293273e-05, + "loss": 1.5819, + "step": 1576 + }, + { + "epoch": 0.17, + "learning_rate": 1.9740300018686748e-05, + "loss": 1.4704, + "step": 1577 + }, + { + "epoch": 0.17, + "learning_rate": 1.9739470616130286e-05, + "loss": 1.4483, + "step": 1578 + }, + { + "epoch": 0.17, + "learning_rate": 1.973863990873501e-05, + "loss": 1.4504, + "step": 1579 + }, + { + "epoch": 0.17, + "learning_rate": 1.973780789661221e-05, + "loss": 1.4911, + "step": 1580 + }, + { + "epoch": 0.17, + "learning_rate": 1.9736974579873358e-05, + "loss": 1.5782, + "step": 1581 + }, + { + "epoch": 0.17, + "learning_rate": 1.97361399586301e-05, + "loss": 1.5845, + "step": 1582 + }, + { + "epoch": 0.17, + "learning_rate": 1.9735304032994246e-05, + "loss": 1.4845, + "step": 1583 + }, + { + "epoch": 0.17, + "learning_rate": 1.973446680307779e-05, + "loss": 1.4675, + "step": 1584 + }, + { + "epoch": 0.17, + "learning_rate": 1.9733628268992904e-05, + "loss": 1.4783, + "step": 1585 + }, + { + "epoch": 0.17, + "learning_rate": 1.9732788430851927e-05, + "loss": 1.4978, + "step": 1586 + }, + { + "epoch": 0.17, + "learning_rate": 1.9731947288767377e-05, + "loss": 1.4674, + "step": 1587 + }, + { + "epoch": 0.17, + "learning_rate": 1.973110484285194e-05, + "loss": 1.4698, + "step": 1588 + }, + { + "epoch": 0.17, + "learning_rate": 1.9730261093218493e-05, + "loss": 1.5383, + "step": 1589 + }, + { + "epoch": 0.17, + "learning_rate": 1.972941603998007e-05, + "loss": 1.5175, + "step": 1590 + }, + { + "epoch": 0.17, + "learning_rate": 1.9728569683249882e-05, + "loss": 1.4905, + "step": 1591 + }, + { + "epoch": 0.17, + "learning_rate": 1.9727722023141327e-05, + "loss": 1.4931, + "step": 1592 + }, + { + "epoch": 0.17, + "eval_loss": 1.5493406057357788, + "eval_runtime": 77.1952, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1592 + }, + { + "epoch": 0.17, + "learning_rate": 1.9726873059767965e-05, + "loss": 1.4205, + "step": 1593 + }, + { + "epoch": 0.17, + "learning_rate": 1.972602279324354e-05, + "loss": 1.454, + "step": 1594 + }, + { + "epoch": 0.17, + "learning_rate": 1.972517122368196e-05, + "loss": 1.4603, + "step": 1595 + }, + { + "epoch": 0.17, + "learning_rate": 1.972431835119732e-05, + "loss": 1.4607, + "step": 1596 + }, + { + "epoch": 0.17, + "learning_rate": 1.9723464175903874e-05, + "loss": 1.3517, + "step": 1597 + }, + { + "epoch": 0.17, + "learning_rate": 1.9722608697916068e-05, + "loss": 1.6674, + "step": 1598 + }, + { + "epoch": 0.17, + "learning_rate": 1.9721751917348507e-05, + "loss": 1.5046, + "step": 1599 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720893834315985e-05, + "loss": 1.4661, + "step": 1600 + }, + { + "epoch": 0.17, + "learning_rate": 1.9720034448933463e-05, + "loss": 1.4868, + "step": 1601 + }, + { + "epoch": 0.17, + "learning_rate": 1.9719173761316068e-05, + "loss": 1.5264, + "step": 1602 + }, + { + "epoch": 0.17, + "learning_rate": 1.9718311771579114e-05, + "loss": 1.6156, + "step": 1603 + }, + { + "epoch": 0.17, + "learning_rate": 1.971744847983809e-05, + "loss": 1.5134, + "step": 1604 + }, + { + "epoch": 0.17, + "learning_rate": 1.9716583886208652e-05, + "loss": 1.4823, + "step": 1605 + }, + { + "epoch": 0.17, + "learning_rate": 1.9715717990806627e-05, + "loss": 1.5776, + "step": 1606 + }, + { + "epoch": 0.17, + "learning_rate": 1.9714850793748032e-05, + "loss": 1.4972, + "step": 1607 + }, + { + "epoch": 0.17, + "learning_rate": 1.971398229514905e-05, + "loss": 1.5078, + "step": 1608 + }, + { + "epoch": 0.17, + "learning_rate": 1.9713112495126027e-05, + "loss": 1.489, + "step": 1609 + }, + { + "epoch": 0.17, + "learning_rate": 1.97122413937955e-05, + "loss": 1.5013, + "step": 1610 + }, + { + "epoch": 0.17, + "learning_rate": 1.971136899127418e-05, + "loss": 1.4875, + "step": 1611 + }, + { + "epoch": 0.17, + "learning_rate": 1.9710495287678935e-05, + "loss": 1.489, + "step": 1612 + }, + { + "epoch": 0.17, + "learning_rate": 1.9709620283126827e-05, + "loss": 1.4884, + "step": 1613 + }, + { + "epoch": 0.17, + "learning_rate": 1.9708743977735082e-05, + "loss": 1.545, + "step": 1614 + }, + { + "epoch": 0.17, + "learning_rate": 1.97078663716211e-05, + "loss": 1.5468, + "step": 1615 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706987464902463e-05, + "loss": 1.5588, + "step": 1616 + }, + { + "epoch": 0.17, + "learning_rate": 1.9706107257696913e-05, + "loss": 1.5196, + "step": 1617 + }, + { + "epoch": 0.17, + "learning_rate": 1.9705225750122387e-05, + "loss": 1.4972, + "step": 1618 + }, + { + "epoch": 0.17, + "learning_rate": 1.9704342942296976e-05, + "loss": 1.5124, + "step": 1619 + }, + { + "epoch": 0.17, + "learning_rate": 1.9703458834338956e-05, + "loss": 1.5484, + "step": 1620 + }, + { + "epoch": 0.17, + "learning_rate": 1.970257342636677e-05, + "loss": 1.6969, + "step": 1621 + }, + { + "epoch": 0.17, + "learning_rate": 1.970168671849905e-05, + "loss": 1.5168, + "step": 1622 + }, + { + "epoch": 0.17, + "learning_rate": 1.9700798710854587e-05, + "loss": 1.5206, + "step": 1623 + }, + { + "epoch": 0.17, + "learning_rate": 1.969990940355235e-05, + "loss": 1.5506, + "step": 1624 + }, + { + "epoch": 0.17, + "learning_rate": 1.969901879671148e-05, + "loss": 1.4989, + "step": 1625 + }, + { + "epoch": 0.17, + "learning_rate": 1.9698126890451302e-05, + "loss": 1.497, + "step": 1626 + }, + { + "epoch": 0.17, + "learning_rate": 1.9697233684891307e-05, + "loss": 1.4643, + "step": 1627 + }, + { + "epoch": 0.17, + "learning_rate": 1.9696339180151158e-05, + "loss": 1.6567, + "step": 1628 + }, + { + "epoch": 0.17, + "learning_rate": 1.96954433763507e-05, + "loss": 1.5363, + "step": 1629 + }, + { + "epoch": 0.17, + "learning_rate": 1.9694546273609946e-05, + "loss": 1.5112, + "step": 1630 + }, + { + "epoch": 0.17, + "learning_rate": 1.9693647872049085e-05, + "loss": 1.5175, + "step": 1631 + }, + { + "epoch": 0.17, + "learning_rate": 1.969274817178848e-05, + "loss": 1.5139, + "step": 1632 + }, + { + "epoch": 0.17, + "learning_rate": 1.9691847172948663e-05, + "loss": 1.6995, + "step": 1633 + }, + { + "epoch": 0.17, + "learning_rate": 1.9690944875650354e-05, + "loss": 1.6399, + "step": 1634 + }, + { + "epoch": 0.17, + "learning_rate": 1.969004128001443e-05, + "loss": 1.5386, + "step": 1635 + }, + { + "epoch": 0.17, + "learning_rate": 1.968913638616195e-05, + "loss": 1.5735, + "step": 1636 + }, + { + "epoch": 0.17, + "learning_rate": 1.968823019421415e-05, + "loss": 1.4948, + "step": 1637 + }, + { + "epoch": 0.17, + "learning_rate": 1.9687322704292436e-05, + "loss": 1.5309, + "step": 1638 + }, + { + "epoch": 0.17, + "learning_rate": 1.9686413916518388e-05, + "loss": 1.4924, + "step": 1639 + }, + { + "epoch": 0.17, + "learning_rate": 1.9685503831013757e-05, + "loss": 1.4575, + "step": 1640 + }, + { + "epoch": 0.17, + "learning_rate": 1.9684592447900478e-05, + "loss": 1.4604, + "step": 1641 + }, + { + "epoch": 0.17, + "learning_rate": 1.9683679767300643e-05, + "loss": 1.4625, + "step": 1642 + }, + { + "epoch": 0.17, + "learning_rate": 1.9682765789336534e-05, + "loss": 1.483, + "step": 1643 + }, + { + "epoch": 0.17, + "learning_rate": 1.9681850514130603e-05, + "loss": 1.4649, + "step": 1644 + }, + { + "epoch": 0.17, + "learning_rate": 1.968093394180547e-05, + "loss": 1.5248, + "step": 1645 + }, + { + "epoch": 0.17, + "learning_rate": 1.968001607248393e-05, + "loss": 1.5093, + "step": 1646 + }, + { + "epoch": 0.17, + "learning_rate": 1.9679096906288958e-05, + "loss": 1.5106, + "step": 1647 + }, + { + "epoch": 0.17, + "learning_rate": 1.9678176443343697e-05, + "loss": 1.6438, + "step": 1648 + }, + { + "epoch": 0.17, + "learning_rate": 1.9677254683771466e-05, + "loss": 1.5193, + "step": 1649 + }, + { + "epoch": 0.17, + "learning_rate": 1.9676331627695756e-05, + "loss": 1.5299, + "step": 1650 + }, + { + "epoch": 0.17, + "learning_rate": 1.967540727524023e-05, + "loss": 1.6404, + "step": 1651 + }, + { + "epoch": 0.17, + "learning_rate": 1.9674481626528734e-05, + "loss": 1.5398, + "step": 1652 + }, + { + "epoch": 0.17, + "learning_rate": 1.9673554681685277e-05, + "loss": 1.5611, + "step": 1653 + }, + { + "epoch": 0.17, + "learning_rate": 1.9672626440834045e-05, + "loss": 1.4949, + "step": 1654 + }, + { + "epoch": 0.17, + "learning_rate": 1.9671696904099403e-05, + "loss": 1.5426, + "step": 1655 + }, + { + "epoch": 0.17, + "learning_rate": 1.9670766071605877e-05, + "loss": 1.5039, + "step": 1656 + }, + { + "epoch": 0.17, + "learning_rate": 1.9669833943478185e-05, + "loss": 1.418, + "step": 1657 + }, + { + "epoch": 0.17, + "learning_rate": 1.96689005198412e-05, + "loss": 1.4904, + "step": 1658 + }, + { + "epoch": 0.17, + "learning_rate": 1.966796580081998e-05, + "loss": 1.4831, + "step": 1659 + }, + { + "epoch": 0.17, + "learning_rate": 1.9667029786539754e-05, + "loss": 1.5287, + "step": 1660 + }, + { + "epoch": 0.17, + "learning_rate": 1.9666092477125923e-05, + "loss": 1.4392, + "step": 1661 + }, + { + "epoch": 0.17, + "learning_rate": 1.966515387270406e-05, + "loss": 1.4647, + "step": 1662 + }, + { + "epoch": 0.17, + "learning_rate": 1.966421397339992e-05, + "loss": 1.5023, + "step": 1663 + }, + { + "epoch": 0.17, + "learning_rate": 1.966327277933942e-05, + "loss": 1.4992, + "step": 1664 + }, + { + "epoch": 0.17, + "learning_rate": 1.9662330290648658e-05, + "loss": 1.486, + "step": 1665 + }, + { + "epoch": 0.17, + "learning_rate": 1.9661386507453898e-05, + "loss": 1.8505, + "step": 1666 + }, + { + "epoch": 0.17, + "learning_rate": 1.9660441429881592e-05, + "loss": 1.4769, + "step": 1667 + }, + { + "epoch": 0.17, + "learning_rate": 1.965949505805835e-05, + "loss": 1.4882, + "step": 1668 + }, + { + "epoch": 0.18, + "learning_rate": 1.9658547392110962e-05, + "loss": 1.5867, + "step": 1669 + }, + { + "epoch": 0.18, + "learning_rate": 1.9657598432166392e-05, + "loss": 1.5892, + "step": 1670 + }, + { + "epoch": 0.18, + "learning_rate": 1.9656648178351778e-05, + "loss": 1.9443, + "step": 1671 + }, + { + "epoch": 0.18, + "learning_rate": 1.9655696630794426e-05, + "loss": 1.4952, + "step": 1672 + }, + { + "epoch": 0.18, + "learning_rate": 1.965474378962182e-05, + "loss": 1.461, + "step": 1673 + }, + { + "epoch": 0.18, + "learning_rate": 1.9653789654961618e-05, + "loss": 1.4979, + "step": 1674 + }, + { + "epoch": 0.18, + "learning_rate": 1.9652834226941647e-05, + "loss": 1.4456, + "step": 1675 + }, + { + "epoch": 0.18, + "learning_rate": 1.9651877505689912e-05, + "loss": 1.4105, + "step": 1676 + }, + { + "epoch": 0.18, + "learning_rate": 1.965091949133459e-05, + "loss": 1.5391, + "step": 1677 + }, + { + "epoch": 0.18, + "learning_rate": 1.9649960184004027e-05, + "loss": 1.4479, + "step": 1678 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648999583826747e-05, + "loss": 1.4842, + "step": 1679 + }, + { + "epoch": 0.18, + "learning_rate": 1.9648037690931446e-05, + "loss": 1.5078, + "step": 1680 + }, + { + "epoch": 0.18, + "learning_rate": 1.964707450544699e-05, + "loss": 1.5522, + "step": 1681 + }, + { + "epoch": 0.18, + "learning_rate": 1.964611002750243e-05, + "loss": 1.548, + "step": 1682 + }, + { + "epoch": 0.18, + "learning_rate": 1.9645144257226972e-05, + "loss": 1.4941, + "step": 1683 + }, + { + "epoch": 0.18, + "learning_rate": 1.9644177194750006e-05, + "loss": 1.4791, + "step": 1684 + }, + { + "epoch": 0.18, + "learning_rate": 1.9643208840201095e-05, + "loss": 1.5588, + "step": 1685 + }, + { + "epoch": 0.18, + "learning_rate": 1.9642239193709974e-05, + "loss": 1.5159, + "step": 1686 + }, + { + "epoch": 0.18, + "learning_rate": 1.9641268255406553e-05, + "loss": 1.5366, + "step": 1687 + }, + { + "epoch": 0.18, + "learning_rate": 1.9640296025420907e-05, + "loss": 1.501, + "step": 1688 + }, + { + "epoch": 0.18, + "learning_rate": 1.9639322503883292e-05, + "loss": 1.4766, + "step": 1689 + }, + { + "epoch": 0.18, + "learning_rate": 1.9638347690924138e-05, + "loss": 1.5004, + "step": 1690 + }, + { + "epoch": 0.18, + "learning_rate": 1.9637371586674044e-05, + "loss": 1.4943, + "step": 1691 + }, + { + "epoch": 0.18, + "learning_rate": 1.9636394191263777e-05, + "loss": 1.5243, + "step": 1692 + }, + { + "epoch": 0.18, + "learning_rate": 1.9635415504824294e-05, + "loss": 1.4976, + "step": 1693 + }, + { + "epoch": 0.18, + "learning_rate": 1.9634435527486704e-05, + "loss": 1.478, + "step": 1694 + }, + { + "epoch": 0.18, + "learning_rate": 1.96334542593823e-05, + "loss": 1.4437, + "step": 1695 + }, + { + "epoch": 0.18, + "learning_rate": 1.9632471700642553e-05, + "loss": 1.4769, + "step": 1696 + }, + { + "epoch": 0.18, + "learning_rate": 1.9631487851399095e-05, + "loss": 1.4387, + "step": 1697 + }, + { + "epoch": 0.18, + "learning_rate": 1.9630502711783737e-05, + "loss": 1.5988, + "step": 1698 + }, + { + "epoch": 0.18, + "learning_rate": 1.962951628192846e-05, + "loss": 1.5576, + "step": 1699 + }, + { + "epoch": 0.18, + "learning_rate": 1.962852856196543e-05, + "loss": 1.5591, + "step": 1700 + }, + { + "epoch": 0.18, + "learning_rate": 1.962753955202697e-05, + "loss": 1.5206, + "step": 1701 + }, + { + "epoch": 0.18, + "learning_rate": 1.9626549252245578e-05, + "loss": 1.5233, + "step": 1702 + }, + { + "epoch": 0.18, + "learning_rate": 1.9625557662753933e-05, + "loss": 1.5083, + "step": 1703 + }, + { + "epoch": 0.18, + "learning_rate": 1.962456478368488e-05, + "loss": 1.5737, + "step": 1704 + }, + { + "epoch": 0.18, + "learning_rate": 1.9623570615171445e-05, + "loss": 1.5038, + "step": 1705 + }, + { + "epoch": 0.18, + "learning_rate": 1.9622575157346815e-05, + "loss": 1.3908, + "step": 1706 + }, + { + "epoch": 0.18, + "learning_rate": 1.9621578410344358e-05, + "loss": 1.5274, + "step": 1707 + }, + { + "epoch": 0.18, + "learning_rate": 1.962058037429761e-05, + "loss": 1.508, + "step": 1708 + }, + { + "epoch": 0.18, + "learning_rate": 1.9619581049340288e-05, + "loss": 1.518, + "step": 1709 + }, + { + "epoch": 0.18, + "learning_rate": 1.9618580435606274e-05, + "loss": 1.5158, + "step": 1710 + }, + { + "epoch": 0.18, + "learning_rate": 1.9617578533229622e-05, + "loss": 1.4889, + "step": 1711 + }, + { + "epoch": 0.18, + "learning_rate": 1.961657534234456e-05, + "loss": 1.5163, + "step": 1712 + }, + { + "epoch": 0.18, + "learning_rate": 1.9615570863085492e-05, + "loss": 1.5993, + "step": 1713 + }, + { + "epoch": 0.18, + "learning_rate": 1.9614565095586995e-05, + "loss": 1.4754, + "step": 1714 + }, + { + "epoch": 0.18, + "learning_rate": 1.961355803998381e-05, + "loss": 1.5367, + "step": 1715 + }, + { + "epoch": 0.18, + "learning_rate": 1.9612549696410865e-05, + "loss": 1.5441, + "step": 1716 + }, + { + "epoch": 0.18, + "learning_rate": 1.9611540065003246e-05, + "loss": 1.5446, + "step": 1717 + }, + { + "epoch": 0.18, + "learning_rate": 1.9610529145896215e-05, + "loss": 1.5358, + "step": 1718 + }, + { + "epoch": 0.18, + "learning_rate": 1.9609516939225216e-05, + "loss": 1.4814, + "step": 1719 + }, + { + "epoch": 0.18, + "learning_rate": 1.9608503445125855e-05, + "loss": 1.4851, + "step": 1720 + }, + { + "epoch": 0.18, + "learning_rate": 1.9607488663733915e-05, + "loss": 1.4926, + "step": 1721 + }, + { + "epoch": 0.18, + "learning_rate": 1.960647259518535e-05, + "loss": 1.5555, + "step": 1722 + }, + { + "epoch": 0.18, + "learning_rate": 1.9605455239616287e-05, + "loss": 1.4419, + "step": 1723 + }, + { + "epoch": 0.18, + "learning_rate": 1.9604436597163025e-05, + "loss": 1.4961, + "step": 1724 + }, + { + "epoch": 0.18, + "learning_rate": 1.9603416667962037e-05, + "loss": 1.5422, + "step": 1725 + }, + { + "epoch": 0.18, + "learning_rate": 1.9602395452149972e-05, + "loss": 1.5925, + "step": 1726 + }, + { + "epoch": 0.18, + "learning_rate": 1.960137294986364e-05, + "loss": 1.4478, + "step": 1727 + }, + { + "epoch": 0.18, + "learning_rate": 1.960034916124003e-05, + "loss": 1.5802, + "step": 1728 + }, + { + "epoch": 0.18, + "learning_rate": 1.9599324086416307e-05, + "loss": 1.5275, + "step": 1729 + }, + { + "epoch": 0.18, + "learning_rate": 1.95982977255298e-05, + "loss": 1.4577, + "step": 1730 + }, + { + "epoch": 0.18, + "learning_rate": 1.9597270078718022e-05, + "loss": 1.5157, + "step": 1731 + }, + { + "epoch": 0.18, + "learning_rate": 1.9596241146118648e-05, + "loss": 1.5256, + "step": 1732 + }, + { + "epoch": 0.18, + "learning_rate": 1.9595210927869525e-05, + "loss": 1.5512, + "step": 1733 + }, + { + "epoch": 0.18, + "learning_rate": 1.959417942410868e-05, + "loss": 1.5273, + "step": 1734 + }, + { + "epoch": 0.18, + "learning_rate": 1.9593146634974305e-05, + "loss": 1.494, + "step": 1735 + }, + { + "epoch": 0.18, + "learning_rate": 1.959211256060477e-05, + "loss": 1.5764, + "step": 1736 + }, + { + "epoch": 0.18, + "learning_rate": 1.9591077201138612e-05, + "loss": 1.2567, + "step": 1737 + }, + { + "epoch": 0.18, + "learning_rate": 1.9590040556714546e-05, + "loss": 1.5334, + "step": 1738 + }, + { + "epoch": 0.18, + "learning_rate": 1.958900262747145e-05, + "loss": 1.4827, + "step": 1739 + }, + { + "epoch": 0.18, + "learning_rate": 1.9587963413548388e-05, + "loss": 1.483, + "step": 1740 + }, + { + "epoch": 0.18, + "learning_rate": 1.958692291508458e-05, + "loss": 1.5099, + "step": 1741 + }, + { + "epoch": 0.18, + "learning_rate": 1.958588113221943e-05, + "loss": 1.5064, + "step": 1742 + }, + { + "epoch": 0.18, + "learning_rate": 1.958483806509251e-05, + "loss": 1.5683, + "step": 1743 + }, + { + "epoch": 0.18, + "learning_rate": 1.9583793713843563e-05, + "loss": 1.4854, + "step": 1744 + }, + { + "epoch": 0.18, + "learning_rate": 1.9582748078612507e-05, + "loss": 1.461, + "step": 1745 + }, + { + "epoch": 0.18, + "learning_rate": 1.958170115953943e-05, + "loss": 1.4945, + "step": 1746 + }, + { + "epoch": 0.18, + "learning_rate": 1.958065295676459e-05, + "loss": 1.698, + "step": 1747 + }, + { + "epoch": 0.18, + "learning_rate": 1.957960347042842e-05, + "loss": 1.4092, + "step": 1748 + }, + { + "epoch": 0.18, + "learning_rate": 1.9578552700671527e-05, + "loss": 1.4639, + "step": 1749 + }, + { + "epoch": 0.18, + "learning_rate": 1.9577500647634683e-05, + "loss": 1.4459, + "step": 1750 + }, + { + "epoch": 0.18, + "learning_rate": 1.957644731145884e-05, + "loss": 1.4512, + "step": 1751 + }, + { + "epoch": 0.18, + "learning_rate": 1.9575392692285114e-05, + "loss": 1.4468, + "step": 1752 + }, + { + "epoch": 0.18, + "learning_rate": 1.95743367902548e-05, + "loss": 1.5132, + "step": 1753 + }, + { + "epoch": 0.18, + "learning_rate": 1.957327960550936e-05, + "loss": 1.5159, + "step": 1754 + }, + { + "epoch": 0.18, + "learning_rate": 1.9572221138190433e-05, + "loss": 1.498, + "step": 1755 + }, + { + "epoch": 0.18, + "learning_rate": 1.9571161388439823e-05, + "loss": 1.5547, + "step": 1756 + }, + { + "epoch": 0.18, + "learning_rate": 1.9570100356399505e-05, + "loss": 1.4997, + "step": 1757 + }, + { + "epoch": 0.18, + "learning_rate": 1.9569038042211642e-05, + "loss": 1.4873, + "step": 1758 + }, + { + "epoch": 0.18, + "learning_rate": 1.9567974446018546e-05, + "loss": 1.5333, + "step": 1759 + }, + { + "epoch": 0.18, + "learning_rate": 1.956690956796272e-05, + "loss": 1.4821, + "step": 1760 + }, + { + "epoch": 0.18, + "learning_rate": 1.9565843408186816e-05, + "loss": 1.6178, + "step": 1761 + }, + { + "epoch": 0.18, + "learning_rate": 1.956477596683369e-05, + "loss": 1.4491, + "step": 1762 + }, + { + "epoch": 0.18, + "learning_rate": 1.956370724404634e-05, + "loss": 1.5331, + "step": 1763 + }, + { + "epoch": 0.18, + "learning_rate": 1.9562637239967953e-05, + "loss": 1.4756, + "step": 1764 + }, + { + "epoch": 0.19, + "learning_rate": 1.956156595474188e-05, + "loss": 1.4727, + "step": 1765 + }, + { + "epoch": 0.19, + "learning_rate": 1.9560493388511642e-05, + "loss": 1.4892, + "step": 1766 + }, + { + "epoch": 0.19, + "learning_rate": 1.9559419541420942e-05, + "loss": 1.4899, + "step": 1767 + }, + { + "epoch": 0.19, + "learning_rate": 1.9558344413613645e-05, + "loss": 1.4929, + "step": 1768 + }, + { + "epoch": 0.19, + "learning_rate": 1.955726800523379e-05, + "loss": 1.5537, + "step": 1769 + }, + { + "epoch": 0.19, + "learning_rate": 1.9556190316425583e-05, + "loss": 1.4552, + "step": 1770 + }, + { + "epoch": 0.19, + "learning_rate": 1.9555111347333414e-05, + "loss": 1.5802, + "step": 1771 + }, + { + "epoch": 0.19, + "learning_rate": 1.955403109810184e-05, + "loss": 1.5085, + "step": 1772 + }, + { + "epoch": 0.19, + "learning_rate": 1.955294956887558e-05, + "loss": 1.4562, + "step": 1773 + }, + { + "epoch": 0.19, + "learning_rate": 1.955186675979953e-05, + "loss": 1.4304, + "step": 1774 + }, + { + "epoch": 0.19, + "learning_rate": 1.9550782671018766e-05, + "loss": 1.4944, + "step": 1775 + }, + { + "epoch": 0.19, + "learning_rate": 1.9549697302678518e-05, + "loss": 1.6818, + "step": 1776 + }, + { + "epoch": 0.19, + "learning_rate": 1.9548610654924206e-05, + "loss": 1.4304, + "step": 1777 + }, + { + "epoch": 0.19, + "learning_rate": 1.9547522727901408e-05, + "loss": 1.5663, + "step": 1778 + }, + { + "epoch": 0.19, + "learning_rate": 1.9546433521755883e-05, + "loss": 1.483, + "step": 1779 + }, + { + "epoch": 0.19, + "learning_rate": 1.9545343036633553e-05, + "loss": 1.4762, + "step": 1780 + }, + { + "epoch": 0.19, + "learning_rate": 1.9544251272680514e-05, + "loss": 1.4492, + "step": 1781 + }, + { + "epoch": 0.19, + "learning_rate": 1.954315823004304e-05, + "loss": 1.5822, + "step": 1782 + }, + { + "epoch": 0.19, + "learning_rate": 1.9542063908867565e-05, + "loss": 1.4646, + "step": 1783 + }, + { + "epoch": 0.19, + "learning_rate": 1.95409683093007e-05, + "loss": 1.5238, + "step": 1784 + }, + { + "epoch": 0.19, + "learning_rate": 1.953987143148923e-05, + "loss": 1.5326, + "step": 1785 + }, + { + "epoch": 0.19, + "learning_rate": 1.9538773275580106e-05, + "loss": 1.4933, + "step": 1786 + }, + { + "epoch": 0.19, + "learning_rate": 1.9537673841720455e-05, + "loss": 1.5095, + "step": 1787 + }, + { + "epoch": 0.19, + "learning_rate": 1.953657313005757e-05, + "loss": 1.5628, + "step": 1788 + }, + { + "epoch": 0.19, + "learning_rate": 1.9535471140738922e-05, + "loss": 1.4666, + "step": 1789 + }, + { + "epoch": 0.19, + "learning_rate": 1.9534367873912146e-05, + "loss": 1.5552, + "step": 1790 + }, + { + "epoch": 0.19, + "learning_rate": 1.9533263329725054e-05, + "loss": 1.4972, + "step": 1791 + }, + { + "epoch": 0.19, + "eval_loss": 1.540722131729126, + "eval_runtime": 77.1546, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 1791 + }, + { + "epoch": 0.19, + "learning_rate": 1.9532157508325622e-05, + "loss": 1.4485, + "step": 1792 + }, + { + "epoch": 0.19, + "learning_rate": 1.9531050409862008e-05, + "loss": 1.418, + "step": 1793 + }, + { + "epoch": 0.19, + "learning_rate": 1.952994203448253e-05, + "loss": 1.4201, + "step": 1794 + }, + { + "epoch": 0.19, + "learning_rate": 1.9528832382335683e-05, + "loss": 1.4707, + "step": 1795 + }, + { + "epoch": 0.19, + "learning_rate": 1.952772145357013e-05, + "loss": 1.4557, + "step": 1796 + }, + { + "epoch": 0.19, + "learning_rate": 1.9526609248334717e-05, + "loss": 1.5078, + "step": 1797 + }, + { + "epoch": 0.19, + "learning_rate": 1.9525495766778437e-05, + "loss": 1.5126, + "step": 1798 + }, + { + "epoch": 0.19, + "learning_rate": 1.9524381009050476e-05, + "loss": 1.565, + "step": 1799 + }, + { + "epoch": 0.19, + "learning_rate": 1.9523264975300175e-05, + "loss": 1.4532, + "step": 1800 + }, + { + "epoch": 0.19, + "learning_rate": 1.9522147665677067e-05, + "loss": 1.4712, + "step": 1801 + }, + { + "epoch": 0.19, + "learning_rate": 1.952102908033083e-05, + "loss": 1.601, + "step": 1802 + }, + { + "epoch": 0.19, + "learning_rate": 1.9519909219411336e-05, + "loss": 1.5504, + "step": 1803 + }, + { + "epoch": 0.19, + "learning_rate": 1.951878808306861e-05, + "loss": 1.4609, + "step": 1804 + }, + { + "epoch": 0.19, + "learning_rate": 1.9517665671452862e-05, + "loss": 1.5569, + "step": 1805 + }, + { + "epoch": 0.19, + "learning_rate": 1.9516541984714457e-05, + "loss": 1.6178, + "step": 1806 + }, + { + "epoch": 0.19, + "learning_rate": 1.9515417023003947e-05, + "loss": 1.5168, + "step": 1807 + }, + { + "epoch": 0.19, + "learning_rate": 1.951429078647205e-05, + "loss": 1.6349, + "step": 1808 + }, + { + "epoch": 0.19, + "learning_rate": 1.9513163275269645e-05, + "loss": 1.4643, + "step": 1809 + }, + { + "epoch": 0.19, + "learning_rate": 1.9512034489547796e-05, + "loss": 1.4292, + "step": 1810 + }, + { + "epoch": 0.19, + "learning_rate": 1.951090442945773e-05, + "loss": 1.4776, + "step": 1811 + }, + { + "epoch": 0.19, + "learning_rate": 1.9509773095150843e-05, + "loss": 1.5103, + "step": 1812 + }, + { + "epoch": 0.19, + "learning_rate": 1.950864048677871e-05, + "loss": 1.3963, + "step": 1813 + }, + { + "epoch": 0.19, + "learning_rate": 1.9507506604493068e-05, + "loss": 1.5503, + "step": 1814 + }, + { + "epoch": 0.19, + "learning_rate": 1.9506371448445826e-05, + "loss": 1.5578, + "step": 1815 + }, + { + "epoch": 0.19, + "learning_rate": 1.950523501878907e-05, + "loss": 1.5377, + "step": 1816 + }, + { + "epoch": 0.19, + "learning_rate": 1.950409731567505e-05, + "loss": 1.5077, + "step": 1817 + }, + { + "epoch": 0.19, + "learning_rate": 1.9502958339256192e-05, + "loss": 1.4658, + "step": 1818 + }, + { + "epoch": 0.19, + "learning_rate": 1.950181808968508e-05, + "loss": 1.5149, + "step": 1819 + }, + { + "epoch": 0.19, + "learning_rate": 1.9500676567114493e-05, + "loss": 1.4722, + "step": 1820 + }, + { + "epoch": 0.19, + "learning_rate": 1.9499533771697355e-05, + "loss": 1.5173, + "step": 1821 + }, + { + "epoch": 0.19, + "learning_rate": 1.9498389703586772e-05, + "loss": 1.4565, + "step": 1822 + }, + { + "epoch": 0.19, + "learning_rate": 1.9497244362936024e-05, + "loss": 1.5425, + "step": 1823 + }, + { + "epoch": 0.19, + "learning_rate": 1.9496097749898556e-05, + "loss": 1.5643, + "step": 1824 + }, + { + "epoch": 0.19, + "learning_rate": 1.9494949864627983e-05, + "loss": 1.6174, + "step": 1825 + }, + { + "epoch": 0.19, + "learning_rate": 1.9493800707278094e-05, + "loss": 1.4554, + "step": 1826 + }, + { + "epoch": 0.19, + "learning_rate": 1.9492650278002844e-05, + "loss": 1.4995, + "step": 1827 + }, + { + "epoch": 0.19, + "learning_rate": 1.9491498576956362e-05, + "loss": 1.3844, + "step": 1828 + }, + { + "epoch": 0.19, + "learning_rate": 1.949034560429295e-05, + "loss": 1.4938, + "step": 1829 + }, + { + "epoch": 0.19, + "learning_rate": 1.948919136016707e-05, + "loss": 1.4207, + "step": 1830 + }, + { + "epoch": 0.19, + "learning_rate": 1.9488035844733367e-05, + "loss": 1.5429, + "step": 1831 + }, + { + "epoch": 0.19, + "learning_rate": 1.9486879058146647e-05, + "loss": 1.4942, + "step": 1832 + }, + { + "epoch": 0.19, + "learning_rate": 1.948572100056189e-05, + "loss": 1.461, + "step": 1833 + }, + { + "epoch": 0.19, + "learning_rate": 1.948456167213425e-05, + "loss": 1.5331, + "step": 1834 + }, + { + "epoch": 0.19, + "learning_rate": 1.948340107301904e-05, + "loss": 1.5576, + "step": 1835 + }, + { + "epoch": 0.19, + "learning_rate": 1.9482239203371755e-05, + "loss": 1.61, + "step": 1836 + }, + { + "epoch": 0.19, + "learning_rate": 1.948107606334806e-05, + "loss": 1.5192, + "step": 1837 + }, + { + "epoch": 0.19, + "learning_rate": 1.9479911653103775e-05, + "loss": 1.4498, + "step": 1838 + }, + { + "epoch": 0.19, + "learning_rate": 1.9478745972794907e-05, + "loss": 1.5356, + "step": 1839 + }, + { + "epoch": 0.19, + "learning_rate": 1.947757902257763e-05, + "loss": 1.574, + "step": 1840 + }, + { + "epoch": 0.19, + "learning_rate": 1.9476410802608278e-05, + "loss": 1.4712, + "step": 1841 + }, + { + "epoch": 0.19, + "learning_rate": 1.9475241313043372e-05, + "loss": 1.5113, + "step": 1842 + }, + { + "epoch": 0.19, + "learning_rate": 1.9474070554039587e-05, + "loss": 1.4674, + "step": 1843 + }, + { + "epoch": 0.19, + "learning_rate": 1.9472898525753776e-05, + "loss": 1.429, + "step": 1844 + }, + { + "epoch": 0.19, + "learning_rate": 1.947172522834296e-05, + "loss": 1.5034, + "step": 1845 + }, + { + "epoch": 0.19, + "learning_rate": 1.9470550661964332e-05, + "loss": 1.4387, + "step": 1846 + }, + { + "epoch": 0.19, + "learning_rate": 1.9469374826775252e-05, + "loss": 1.4123, + "step": 1847 + }, + { + "epoch": 0.19, + "learning_rate": 1.9468197722933255e-05, + "loss": 1.5181, + "step": 1848 + }, + { + "epoch": 0.19, + "learning_rate": 1.9467019350596038e-05, + "loss": 1.5571, + "step": 1849 + }, + { + "epoch": 0.19, + "learning_rate": 1.9465839709921477e-05, + "loss": 1.527, + "step": 1850 + }, + { + "epoch": 0.19, + "learning_rate": 1.9464658801067612e-05, + "loss": 1.4841, + "step": 1851 + }, + { + "epoch": 0.19, + "learning_rate": 1.9463476624192655e-05, + "loss": 1.6462, + "step": 1852 + }, + { + "epoch": 0.19, + "learning_rate": 1.9462293179454985e-05, + "loss": 1.4558, + "step": 1853 + }, + { + "epoch": 0.19, + "learning_rate": 1.9461108467013155e-05, + "loss": 1.4901, + "step": 1854 + }, + { + "epoch": 0.19, + "learning_rate": 1.9459922487025883e-05, + "loss": 1.4548, + "step": 1855 + }, + { + "epoch": 0.19, + "learning_rate": 1.9458735239652068e-05, + "loss": 1.3878, + "step": 1856 + }, + { + "epoch": 0.19, + "learning_rate": 1.945754672505076e-05, + "loss": 1.4575, + "step": 1857 + }, + { + "epoch": 0.19, + "learning_rate": 1.94563569433812e-05, + "loss": 1.5251, + "step": 1858 + }, + { + "epoch": 0.19, + "learning_rate": 1.945516589480278e-05, + "loss": 1.4804, + "step": 1859 + }, + { + "epoch": 0.2, + "learning_rate": 1.9453973579475073e-05, + "loss": 1.4914, + "step": 1860 + }, + { + "epoch": 0.2, + "learning_rate": 1.9452779997557817e-05, + "loss": 1.4812, + "step": 1861 + }, + { + "epoch": 0.2, + "learning_rate": 1.9451585149210923e-05, + "loss": 1.4823, + "step": 1862 + }, + { + "epoch": 0.2, + "learning_rate": 1.945038903459447e-05, + "loss": 1.511, + "step": 1863 + }, + { + "epoch": 0.2, + "learning_rate": 1.9449191653868705e-05, + "loss": 1.5289, + "step": 1864 + }, + { + "epoch": 0.2, + "learning_rate": 1.9447993007194052e-05, + "loss": 1.4989, + "step": 1865 + }, + { + "epoch": 0.2, + "learning_rate": 1.944679309473109e-05, + "loss": 1.5965, + "step": 1866 + }, + { + "epoch": 0.2, + "learning_rate": 1.944559191664058e-05, + "loss": 1.4929, + "step": 1867 + }, + { + "epoch": 0.2, + "learning_rate": 1.9444389473083456e-05, + "loss": 1.5537, + "step": 1868 + }, + { + "epoch": 0.2, + "learning_rate": 1.9443185764220805e-05, + "loss": 1.5499, + "step": 1869 + }, + { + "epoch": 0.2, + "learning_rate": 1.9441980790213892e-05, + "loss": 1.4963, + "step": 1870 + }, + { + "epoch": 0.2, + "learning_rate": 1.944077455122416e-05, + "loss": 1.5099, + "step": 1871 + }, + { + "epoch": 0.2, + "learning_rate": 1.9439567047413214e-05, + "loss": 1.5104, + "step": 1872 + }, + { + "epoch": 0.2, + "learning_rate": 1.9438358278942822e-05, + "loss": 1.548, + "step": 1873 + }, + { + "epoch": 0.2, + "learning_rate": 1.9437148245974934e-05, + "loss": 1.5168, + "step": 1874 + }, + { + "epoch": 0.2, + "learning_rate": 1.943593694867166e-05, + "loss": 1.4347, + "step": 1875 + }, + { + "epoch": 0.2, + "learning_rate": 1.9434724387195282e-05, + "loss": 1.483, + "step": 1876 + }, + { + "epoch": 0.2, + "learning_rate": 1.9433510561708253e-05, + "loss": 1.5192, + "step": 1877 + }, + { + "epoch": 0.2, + "learning_rate": 1.94322954723732e-05, + "loss": 1.4881, + "step": 1878 + }, + { + "epoch": 0.2, + "learning_rate": 1.94310791193529e-05, + "loss": 1.4582, + "step": 1879 + }, + { + "epoch": 0.2, + "learning_rate": 1.9429861502810326e-05, + "loss": 1.4948, + "step": 1880 + }, + { + "epoch": 0.2, + "learning_rate": 1.9428642622908606e-05, + "loss": 1.3547, + "step": 1881 + }, + { + "epoch": 0.2, + "learning_rate": 1.9427422479811032e-05, + "loss": 1.5116, + "step": 1882 + }, + { + "epoch": 0.2, + "learning_rate": 1.942620107368108e-05, + "loss": 1.6105, + "step": 1883 + }, + { + "epoch": 0.2, + "learning_rate": 1.942497840468238e-05, + "loss": 1.5252, + "step": 1884 + }, + { + "epoch": 0.2, + "learning_rate": 1.942375447297874e-05, + "loss": 1.583, + "step": 1885 + }, + { + "epoch": 0.2, + "learning_rate": 1.9422529278734133e-05, + "loss": 1.4526, + "step": 1886 + }, + { + "epoch": 0.2, + "learning_rate": 1.9421302822112708e-05, + "loss": 1.4635, + "step": 1887 + }, + { + "epoch": 0.2, + "learning_rate": 1.942007510327878e-05, + "loss": 1.4575, + "step": 1888 + }, + { + "epoch": 0.2, + "learning_rate": 1.9418846122396827e-05, + "loss": 1.5382, + "step": 1889 + }, + { + "epoch": 0.2, + "learning_rate": 1.9417615879631508e-05, + "loss": 1.5819, + "step": 1890 + }, + { + "epoch": 0.2, + "learning_rate": 1.9416384375147635e-05, + "loss": 1.5065, + "step": 1891 + }, + { + "epoch": 0.2, + "learning_rate": 1.94151516091102e-05, + "loss": 1.4488, + "step": 1892 + }, + { + "epoch": 0.2, + "learning_rate": 1.9413917581684366e-05, + "loss": 1.4391, + "step": 1893 + }, + { + "epoch": 0.2, + "learning_rate": 1.9412682293035458e-05, + "loss": 1.5256, + "step": 1894 + }, + { + "epoch": 0.2, + "learning_rate": 1.9411445743328974e-05, + "loss": 1.4471, + "step": 1895 + }, + { + "epoch": 0.2, + "learning_rate": 1.941020793273058e-05, + "loss": 1.5442, + "step": 1896 + }, + { + "epoch": 0.2, + "learning_rate": 1.9408968861406113e-05, + "loss": 1.5141, + "step": 1897 + }, + { + "epoch": 0.2, + "learning_rate": 1.940772852952157e-05, + "loss": 1.4379, + "step": 1898 + }, + { + "epoch": 0.2, + "learning_rate": 1.940648693724313e-05, + "loss": 1.4989, + "step": 1899 + }, + { + "epoch": 0.2, + "learning_rate": 1.940524408473713e-05, + "loss": 1.501, + "step": 1900 + }, + { + "epoch": 0.2, + "learning_rate": 1.9403999972170088e-05, + "loss": 1.5277, + "step": 1901 + }, + { + "epoch": 0.2, + "learning_rate": 1.9402754599708675e-05, + "loss": 1.5655, + "step": 1902 + }, + { + "epoch": 0.2, + "learning_rate": 1.9401507967519738e-05, + "loss": 1.5326, + "step": 1903 + }, + { + "epoch": 0.2, + "learning_rate": 1.9400260075770304e-05, + "loss": 1.508, + "step": 1904 + }, + { + "epoch": 0.2, + "learning_rate": 1.9399010924627548e-05, + "loss": 1.4971, + "step": 1905 + }, + { + "epoch": 0.2, + "learning_rate": 1.9397760514258825e-05, + "loss": 1.5248, + "step": 1906 + }, + { + "epoch": 0.2, + "learning_rate": 1.9396508844831663e-05, + "loss": 1.5119, + "step": 1907 + }, + { + "epoch": 0.2, + "learning_rate": 1.9395255916513753e-05, + "loss": 1.4492, + "step": 1908 + }, + { + "epoch": 0.2, + "learning_rate": 1.9394001729472954e-05, + "loss": 1.3187, + "step": 1909 + }, + { + "epoch": 0.2, + "learning_rate": 1.939274628387729e-05, + "loss": 0.7899, + "step": 1910 + }, + { + "epoch": 0.2, + "learning_rate": 1.9391489579894967e-05, + "loss": 1.2956, + "step": 1911 + }, + { + "epoch": 0.2, + "learning_rate": 1.9390231617694343e-05, + "loss": 1.5321, + "step": 1912 + }, + { + "epoch": 0.2, + "learning_rate": 1.938897239744396e-05, + "loss": 1.4484, + "step": 1913 + }, + { + "epoch": 0.2, + "learning_rate": 1.9387711919312516e-05, + "loss": 1.5293, + "step": 1914 + }, + { + "epoch": 0.2, + "learning_rate": 1.9386450183468883e-05, + "loss": 1.477, + "step": 1915 + }, + { + "epoch": 0.2, + "learning_rate": 1.93851871900821e-05, + "loss": 1.4962, + "step": 1916 + }, + { + "epoch": 0.2, + "learning_rate": 1.9383922939321388e-05, + "loss": 1.4596, + "step": 1917 + }, + { + "epoch": 0.2, + "learning_rate": 1.9382657431356105e-05, + "loss": 1.6164, + "step": 1918 + }, + { + "epoch": 0.2, + "learning_rate": 1.938139066635581e-05, + "loss": 1.4752, + "step": 1919 + }, + { + "epoch": 0.2, + "learning_rate": 1.938012264449021e-05, + "loss": 1.5322, + "step": 1920 + }, + { + "epoch": 0.2, + "learning_rate": 1.937885336592919e-05, + "loss": 1.4607, + "step": 1921 + }, + { + "epoch": 0.2, + "learning_rate": 1.9377582830842803e-05, + "loss": 1.6286, + "step": 1922 + }, + { + "epoch": 0.2, + "learning_rate": 1.9376311039401265e-05, + "loss": 1.553, + "step": 1923 + }, + { + "epoch": 0.2, + "learning_rate": 1.937503799177497e-05, + "loss": 1.48, + "step": 1924 + }, + { + "epoch": 0.2, + "learning_rate": 1.937376368813446e-05, + "loss": 1.5161, + "step": 1925 + }, + { + "epoch": 0.2, + "learning_rate": 1.937248812865047e-05, + "loss": 1.5614, + "step": 1926 + }, + { + "epoch": 0.2, + "learning_rate": 1.937121131349389e-05, + "loss": 1.503, + "step": 1927 + }, + { + "epoch": 0.2, + "learning_rate": 1.9369933242835773e-05, + "loss": 1.5059, + "step": 1928 + }, + { + "epoch": 0.2, + "learning_rate": 1.936865391684736e-05, + "loss": 1.3895, + "step": 1929 + }, + { + "epoch": 0.2, + "learning_rate": 1.936737333570004e-05, + "loss": 1.1535, + "step": 1930 + }, + { + "epoch": 0.2, + "learning_rate": 1.936609149956538e-05, + "loss": 1.1182, + "step": 1931 + }, + { + "epoch": 0.2, + "learning_rate": 1.9364808408615118e-05, + "loss": 1.0568, + "step": 1932 + }, + { + "epoch": 0.2, + "learning_rate": 1.9363524063021143e-05, + "loss": 1.066, + "step": 1933 + }, + { + "epoch": 0.2, + "learning_rate": 1.9362238462955533e-05, + "loss": 0.9715, + "step": 1934 + }, + { + "epoch": 0.2, + "learning_rate": 1.936095160859053e-05, + "loss": 0.9349, + "step": 1935 + }, + { + "epoch": 0.2, + "learning_rate": 1.9359663500098524e-05, + "loss": 0.9757, + "step": 1936 + }, + { + "epoch": 0.2, + "learning_rate": 1.9358374137652103e-05, + "loss": 0.9194, + "step": 1937 + }, + { + "epoch": 0.2, + "learning_rate": 1.9357083521424004e-05, + "loss": 1.4673, + "step": 1938 + }, + { + "epoch": 0.2, + "learning_rate": 1.9355791651587132e-05, + "loss": 1.5178, + "step": 1939 + }, + { + "epoch": 0.2, + "learning_rate": 1.9354498528314568e-05, + "loss": 1.5177, + "step": 1940 + }, + { + "epoch": 0.2, + "learning_rate": 1.935320415177956e-05, + "loss": 1.4736, + "step": 1941 + }, + { + "epoch": 0.2, + "learning_rate": 1.935190852215552e-05, + "loss": 1.4444, + "step": 1942 + }, + { + "epoch": 0.2, + "learning_rate": 1.9350611639616023e-05, + "loss": 1.5774, + "step": 1943 + }, + { + "epoch": 0.2, + "learning_rate": 1.9349313504334825e-05, + "loss": 1.4976, + "step": 1944 + }, + { + "epoch": 0.2, + "learning_rate": 1.934801411648584e-05, + "loss": 1.4697, + "step": 1945 + }, + { + "epoch": 0.2, + "learning_rate": 1.9346713476243154e-05, + "loss": 1.5035, + "step": 1946 + }, + { + "epoch": 0.2, + "learning_rate": 1.934541158378102e-05, + "loss": 1.4809, + "step": 1947 + }, + { + "epoch": 0.2, + "learning_rate": 1.9344108439273853e-05, + "loss": 1.5242, + "step": 1948 + }, + { + "epoch": 0.2, + "learning_rate": 1.9342804042896244e-05, + "loss": 1.4528, + "step": 1949 + }, + { + "epoch": 0.2, + "learning_rate": 1.9341498394822947e-05, + "loss": 1.473, + "step": 1950 + }, + { + "epoch": 0.2, + "learning_rate": 1.9340191495228892e-05, + "loss": 1.4217, + "step": 1951 + }, + { + "epoch": 0.2, + "learning_rate": 1.9338883344289165e-05, + "loss": 1.5586, + "step": 1952 + }, + { + "epoch": 0.2, + "learning_rate": 1.933757394217902e-05, + "loss": 1.5473, + "step": 1953 + }, + { + "epoch": 0.2, + "learning_rate": 1.933626328907389e-05, + "loss": 1.4718, + "step": 1954 + }, + { + "epoch": 0.21, + "learning_rate": 1.9334951385149367e-05, + "loss": 1.3981, + "step": 1955 + }, + { + "epoch": 0.21, + "learning_rate": 1.9333638230581214e-05, + "loss": 1.4659, + "step": 1956 + }, + { + "epoch": 0.21, + "learning_rate": 1.9332323825545355e-05, + "loss": 1.4542, + "step": 1957 + }, + { + "epoch": 0.21, + "learning_rate": 1.933100817021789e-05, + "loss": 1.433, + "step": 1958 + }, + { + "epoch": 0.21, + "learning_rate": 1.9329691264775087e-05, + "loss": 1.5316, + "step": 1959 + }, + { + "epoch": 0.21, + "learning_rate": 1.932837310939337e-05, + "loss": 1.443, + "step": 1960 + }, + { + "epoch": 0.21, + "learning_rate": 1.932705370424934e-05, + "loss": 1.5022, + "step": 1961 + }, + { + "epoch": 0.21, + "learning_rate": 1.9325733049519763e-05, + "loss": 1.5283, + "step": 1962 + }, + { + "epoch": 0.21, + "learning_rate": 1.9324411145381575e-05, + "loss": 1.4691, + "step": 1963 + }, + { + "epoch": 0.21, + "learning_rate": 1.9323087992011878e-05, + "loss": 1.5221, + "step": 1964 + }, + { + "epoch": 0.21, + "learning_rate": 1.9321763589587943e-05, + "loss": 1.4747, + "step": 1965 + }, + { + "epoch": 0.21, + "learning_rate": 1.9320437938287198e-05, + "loss": 1.4269, + "step": 1966 + }, + { + "epoch": 0.21, + "learning_rate": 1.931911103828725e-05, + "loss": 1.5038, + "step": 1967 + }, + { + "epoch": 0.21, + "learning_rate": 1.9317782889765872e-05, + "loss": 1.4501, + "step": 1968 + }, + { + "epoch": 0.21, + "learning_rate": 1.9316453492900996e-05, + "loss": 1.4949, + "step": 1969 + }, + { + "epoch": 0.21, + "learning_rate": 1.931512284787073e-05, + "loss": 1.5188, + "step": 1970 + }, + { + "epoch": 0.21, + "learning_rate": 1.931379095485335e-05, + "loss": 1.4313, + "step": 1971 + }, + { + "epoch": 0.21, + "learning_rate": 1.9312457814027293e-05, + "loss": 1.4908, + "step": 1972 + }, + { + "epoch": 0.21, + "learning_rate": 1.9311123425571164e-05, + "loss": 1.537, + "step": 1973 + }, + { + "epoch": 0.21, + "learning_rate": 1.9309787789663735e-05, + "loss": 1.4315, + "step": 1974 + }, + { + "epoch": 0.21, + "learning_rate": 1.930845090648395e-05, + "loss": 1.4784, + "step": 1975 + }, + { + "epoch": 0.21, + "learning_rate": 1.930711277621092e-05, + "loss": 1.6129, + "step": 1976 + }, + { + "epoch": 0.21, + "learning_rate": 1.9305773399023913e-05, + "loss": 1.5168, + "step": 1977 + }, + { + "epoch": 0.21, + "learning_rate": 1.9304432775102376e-05, + "loss": 1.479, + "step": 1978 + }, + { + "epoch": 0.21, + "learning_rate": 1.9303090904625917e-05, + "loss": 1.472, + "step": 1979 + }, + { + "epoch": 0.21, + "learning_rate": 1.930174778777431e-05, + "loss": 1.4995, + "step": 1980 + }, + { + "epoch": 0.21, + "learning_rate": 1.93004034247275e-05, + "loss": 1.5154, + "step": 1981 + }, + { + "epoch": 0.21, + "learning_rate": 1.9299057815665598e-05, + "loss": 1.5628, + "step": 1982 + }, + { + "epoch": 0.21, + "learning_rate": 1.929771096076888e-05, + "loss": 1.5196, + "step": 1983 + }, + { + "epoch": 0.21, + "learning_rate": 1.929636286021779e-05, + "loss": 1.4267, + "step": 1984 + }, + { + "epoch": 0.21, + "learning_rate": 1.9295013514192943e-05, + "loss": 1.5249, + "step": 1985 + }, + { + "epoch": 0.21, + "learning_rate": 1.929366292287511e-05, + "loss": 1.4895, + "step": 1986 + }, + { + "epoch": 0.21, + "learning_rate": 1.9292311086445237e-05, + "loss": 1.4965, + "step": 1987 + }, + { + "epoch": 0.21, + "learning_rate": 1.9290958005084438e-05, + "loss": 1.5273, + "step": 1988 + }, + { + "epoch": 0.21, + "learning_rate": 1.9289603678973988e-05, + "loss": 1.4002, + "step": 1989 + }, + { + "epoch": 0.21, + "learning_rate": 1.9288248108295335e-05, + "loss": 1.5349, + "step": 1990 + }, + { + "epoch": 0.21, + "eval_loss": 1.530476450920105, + "eval_runtime": 77.2115, + "eval_samples_per_second": 1.671, + "eval_steps_per_second": 0.117, + "step": 1990 + }, + { + "epoch": 0.21, + "learning_rate": 1.928689129323009e-05, + "loss": 1.421, + "step": 1991 + }, + { + "epoch": 0.21, + "learning_rate": 1.928553323396003e-05, + "loss": 1.5625, + "step": 1992 + }, + { + "epoch": 0.21, + "learning_rate": 1.92841739306671e-05, + "loss": 1.5198, + "step": 1993 + }, + { + "epoch": 0.21, + "learning_rate": 1.9282813383533415e-05, + "loss": 1.5116, + "step": 1994 + }, + { + "epoch": 0.21, + "learning_rate": 1.9281451592741247e-05, + "loss": 1.4306, + "step": 1995 + }, + { + "epoch": 0.21, + "learning_rate": 1.9280088558473046e-05, + "loss": 1.5425, + "step": 1996 + }, + { + "epoch": 0.21, + "learning_rate": 1.9278724280911424e-05, + "loss": 1.4972, + "step": 1997 + }, + { + "epoch": 0.21, + "learning_rate": 1.9277358760239156e-05, + "loss": 1.5185, + "step": 1998 + }, + { + "epoch": 0.21, + "learning_rate": 1.9275991996639188e-05, + "loss": 1.5187, + "step": 1999 + }, + { + "epoch": 0.21, + "learning_rate": 1.927462399029463e-05, + "loss": 1.4325, + "step": 2000 + }, + { + "epoch": 0.21, + "learning_rate": 1.9273254741388763e-05, + "loss": 1.4397, + "step": 2001 + }, + { + "epoch": 0.21, + "learning_rate": 1.927188425010503e-05, + "loss": 1.5319, + "step": 2002 + }, + { + "epoch": 0.21, + "learning_rate": 1.9270512516627042e-05, + "loss": 1.5664, + "step": 2003 + }, + { + "epoch": 0.21, + "learning_rate": 1.9269139541138574e-05, + "loss": 1.5227, + "step": 2004 + }, + { + "epoch": 0.21, + "learning_rate": 1.926776532382357e-05, + "loss": 1.5187, + "step": 2005 + }, + { + "epoch": 0.21, + "learning_rate": 1.9266389864866134e-05, + "loss": 1.4029, + "step": 2006 + }, + { + "epoch": 0.21, + "learning_rate": 1.9265013164450557e-05, + "loss": 1.387, + "step": 2007 + }, + { + "epoch": 0.21, + "learning_rate": 1.9263635222761268e-05, + "loss": 1.5047, + "step": 2008 + }, + { + "epoch": 0.21, + "learning_rate": 1.9262256039982882e-05, + "loss": 1.4816, + "step": 2009 + }, + { + "epoch": 0.21, + "learning_rate": 1.9260875616300172e-05, + "loss": 1.4607, + "step": 2010 + }, + { + "epoch": 0.21, + "learning_rate": 1.9259493951898084e-05, + "loss": 1.628, + "step": 2011 + }, + { + "epoch": 0.21, + "learning_rate": 1.9258111046961714e-05, + "loss": 1.4149, + "step": 2012 + }, + { + "epoch": 0.21, + "learning_rate": 1.925672690167635e-05, + "loss": 1.5303, + "step": 2013 + }, + { + "epoch": 0.21, + "learning_rate": 1.925534151622742e-05, + "loss": 1.5198, + "step": 2014 + }, + { + "epoch": 0.21, + "learning_rate": 1.9253954890800535e-05, + "loss": 1.6422, + "step": 2015 + }, + { + "epoch": 0.21, + "learning_rate": 1.925256702558147e-05, + "loss": 1.4738, + "step": 2016 + }, + { + "epoch": 0.21, + "learning_rate": 1.925117792075616e-05, + "loss": 1.4752, + "step": 2017 + }, + { + "epoch": 0.21, + "learning_rate": 1.9249787576510713e-05, + "loss": 1.4547, + "step": 2018 + }, + { + "epoch": 0.21, + "learning_rate": 1.924839599303139e-05, + "loss": 1.4864, + "step": 2019 + }, + { + "epoch": 0.21, + "learning_rate": 1.9247003170504638e-05, + "loss": 1.5037, + "step": 2020 + }, + { + "epoch": 0.21, + "learning_rate": 1.9245609109117053e-05, + "loss": 1.5089, + "step": 2021 + }, + { + "epoch": 0.21, + "learning_rate": 1.924421380905541e-05, + "loss": 1.5616, + "step": 2022 + }, + { + "epoch": 0.21, + "learning_rate": 1.9242817270506634e-05, + "loss": 1.4592, + "step": 2023 + }, + { + "epoch": 0.21, + "learning_rate": 1.9241419493657832e-05, + "loss": 1.5592, + "step": 2024 + }, + { + "epoch": 0.21, + "learning_rate": 1.924002047869627e-05, + "loss": 1.4897, + "step": 2025 + }, + { + "epoch": 0.21, + "learning_rate": 1.9238620225809375e-05, + "loss": 1.4743, + "step": 2026 + }, + { + "epoch": 0.21, + "learning_rate": 1.923721873518475e-05, + "loss": 1.4686, + "step": 2027 + }, + { + "epoch": 0.21, + "learning_rate": 1.923581600701016e-05, + "loss": 1.461, + "step": 2028 + }, + { + "epoch": 0.21, + "learning_rate": 1.9234412041473528e-05, + "loss": 1.6622, + "step": 2029 + }, + { + "epoch": 0.21, + "learning_rate": 1.9233006838762955e-05, + "loss": 1.4707, + "step": 2030 + }, + { + "epoch": 0.21, + "learning_rate": 1.92316003990667e-05, + "loss": 1.5566, + "step": 2031 + }, + { + "epoch": 0.21, + "learning_rate": 1.9230192722573188e-05, + "loss": 1.4881, + "step": 2032 + }, + { + "epoch": 0.21, + "learning_rate": 1.9228783809471015e-05, + "loss": 1.6124, + "step": 2033 + }, + { + "epoch": 0.21, + "learning_rate": 1.9227373659948937e-05, + "loss": 1.3508, + "step": 2034 + }, + { + "epoch": 0.21, + "learning_rate": 1.9225962274195876e-05, + "loss": 1.4418, + "step": 2035 + }, + { + "epoch": 0.21, + "learning_rate": 1.9224549652400927e-05, + "loss": 1.3954, + "step": 2036 + }, + { + "epoch": 0.21, + "learning_rate": 1.922313579475334e-05, + "loss": 1.4798, + "step": 2037 + }, + { + "epoch": 0.21, + "learning_rate": 1.922172070144254e-05, + "loss": 1.4556, + "step": 2038 + }, + { + "epoch": 0.21, + "learning_rate": 1.922030437265811e-05, + "loss": 1.4987, + "step": 2039 + }, + { + "epoch": 0.21, + "learning_rate": 1.9218886808589796e-05, + "loss": 1.4857, + "step": 2040 + }, + { + "epoch": 0.21, + "learning_rate": 1.9217468009427527e-05, + "loss": 1.5289, + "step": 2041 + }, + { + "epoch": 0.21, + "learning_rate": 1.921604797536138e-05, + "loss": 1.5267, + "step": 2042 + }, + { + "epoch": 0.21, + "learning_rate": 1.9214626706581598e-05, + "loss": 1.4655, + "step": 2043 + }, + { + "epoch": 0.21, + "learning_rate": 1.9213204203278602e-05, + "loss": 1.4598, + "step": 2044 + }, + { + "epoch": 0.21, + "learning_rate": 1.9211780465642973e-05, + "loss": 1.4766, + "step": 2045 + }, + { + "epoch": 0.21, + "learning_rate": 1.921035549386545e-05, + "loss": 1.5148, + "step": 2046 + }, + { + "epoch": 0.21, + "learning_rate": 1.9208929288136933e-05, + "loss": 1.5567, + "step": 2047 + }, + { + "epoch": 0.21, + "learning_rate": 1.920750184864852e-05, + "loss": 1.4868, + "step": 2048 + }, + { + "epoch": 0.21, + "learning_rate": 1.920607317559143e-05, + "loss": 1.4752, + "step": 2049 + }, + { + "epoch": 0.21, + "learning_rate": 1.920464326915708e-05, + "loss": 1.4882, + "step": 2050 + }, + { + "epoch": 0.22, + "learning_rate": 1.9203212129537035e-05, + "loss": 1.5933, + "step": 2051 + }, + { + "epoch": 0.22, + "learning_rate": 1.9201779756923037e-05, + "loss": 1.4891, + "step": 2052 + }, + { + "epoch": 0.22, + "learning_rate": 1.9200346151506983e-05, + "loss": 1.4486, + "step": 2053 + }, + { + "epoch": 0.22, + "learning_rate": 1.9198911313480938e-05, + "loss": 1.5091, + "step": 2054 + }, + { + "epoch": 0.22, + "learning_rate": 1.919747524303714e-05, + "loss": 1.4385, + "step": 2055 + }, + { + "epoch": 0.22, + "learning_rate": 1.9196037940367974e-05, + "loss": 1.4104, + "step": 2056 + }, + { + "epoch": 0.22, + "learning_rate": 1.9194599405666015e-05, + "loss": 1.4483, + "step": 2057 + }, + { + "epoch": 0.22, + "learning_rate": 1.9193159639123976e-05, + "loss": 1.4592, + "step": 2058 + }, + { + "epoch": 0.22, + "learning_rate": 1.919171864093476e-05, + "loss": 1.4975, + "step": 2059 + }, + { + "epoch": 0.22, + "learning_rate": 1.9190276411291423e-05, + "loss": 1.4727, + "step": 2060 + }, + { + "epoch": 0.22, + "learning_rate": 1.9188832950387178e-05, + "loss": 1.4791, + "step": 2061 + }, + { + "epoch": 0.22, + "learning_rate": 1.9187388258415423e-05, + "loss": 1.3806, + "step": 2062 + }, + { + "epoch": 0.22, + "learning_rate": 1.9185942335569697e-05, + "loss": 1.4514, + "step": 2063 + }, + { + "epoch": 0.22, + "learning_rate": 1.9184495182043727e-05, + "loss": 1.4389, + "step": 2064 + }, + { + "epoch": 0.22, + "learning_rate": 1.918304679803139e-05, + "loss": 1.5088, + "step": 2065 + }, + { + "epoch": 0.22, + "learning_rate": 1.9181597183726733e-05, + "loss": 1.4665, + "step": 2066 + }, + { + "epoch": 0.22, + "learning_rate": 1.9180146339323966e-05, + "loss": 1.489, + "step": 2067 + }, + { + "epoch": 0.22, + "learning_rate": 1.9178694265017466e-05, + "loss": 1.5215, + "step": 2068 + }, + { + "epoch": 0.22, + "learning_rate": 1.9177240961001775e-05, + "loss": 1.5152, + "step": 2069 + }, + { + "epoch": 0.22, + "learning_rate": 1.9175786427471594e-05, + "loss": 1.4418, + "step": 2070 + }, + { + "epoch": 0.22, + "learning_rate": 1.91743306646218e-05, + "loss": 1.5001, + "step": 2071 + }, + { + "epoch": 0.22, + "learning_rate": 1.9172873672647417e-05, + "loss": 1.4879, + "step": 2072 + }, + { + "epoch": 0.22, + "learning_rate": 1.917141545174366e-05, + "loss": 1.5299, + "step": 2073 + }, + { + "epoch": 0.22, + "learning_rate": 1.9169956002105877e-05, + "loss": 1.4602, + "step": 2074 + }, + { + "epoch": 0.22, + "learning_rate": 1.9168495323929605e-05, + "loss": 1.4921, + "step": 2075 + }, + { + "epoch": 0.22, + "learning_rate": 1.916703341741054e-05, + "loss": 1.4659, + "step": 2076 + }, + { + "epoch": 0.22, + "learning_rate": 1.9165570282744534e-05, + "loss": 1.4707, + "step": 2077 + }, + { + "epoch": 0.22, + "learning_rate": 1.9164105920127613e-05, + "loss": 1.5354, + "step": 2078 + }, + { + "epoch": 0.22, + "learning_rate": 1.9162640329755962e-05, + "loss": 1.526, + "step": 2079 + }, + { + "epoch": 0.22, + "learning_rate": 1.916117351182593e-05, + "loss": 1.6424, + "step": 2080 + }, + { + "epoch": 0.22, + "learning_rate": 1.915970546653404e-05, + "loss": 1.5048, + "step": 2081 + }, + { + "epoch": 0.22, + "learning_rate": 1.915823619407697e-05, + "loss": 1.5344, + "step": 2082 + }, + { + "epoch": 0.22, + "learning_rate": 1.915676569465156e-05, + "loss": 1.4604, + "step": 2083 + }, + { + "epoch": 0.22, + "learning_rate": 1.9155293968454826e-05, + "loss": 1.4929, + "step": 2084 + }, + { + "epoch": 0.22, + "learning_rate": 1.9153821015683937e-05, + "loss": 1.4106, + "step": 2085 + }, + { + "epoch": 0.22, + "learning_rate": 1.915234683653623e-05, + "loss": 1.4146, + "step": 2086 + }, + { + "epoch": 0.22, + "learning_rate": 1.9150871431209207e-05, + "loss": 1.4481, + "step": 2087 + }, + { + "epoch": 0.22, + "learning_rate": 1.914939479990054e-05, + "loss": 1.5206, + "step": 2088 + }, + { + "epoch": 0.22, + "learning_rate": 1.9147916942808054e-05, + "loss": 1.5073, + "step": 2089 + }, + { + "epoch": 0.22, + "learning_rate": 1.9146437860129745e-05, + "loss": 1.5196, + "step": 2090 + }, + { + "epoch": 0.22, + "learning_rate": 1.9144957552063775e-05, + "loss": 1.5389, + "step": 2091 + }, + { + "epoch": 0.22, + "learning_rate": 1.9143476018808463e-05, + "loss": 1.5207, + "step": 2092 + }, + { + "epoch": 0.22, + "learning_rate": 1.9141993260562298e-05, + "loss": 1.3717, + "step": 2093 + }, + { + "epoch": 0.22, + "learning_rate": 1.9140509277523937e-05, + "loss": 1.471, + "step": 2094 + }, + { + "epoch": 0.22, + "learning_rate": 1.9139024069892185e-05, + "loss": 1.4553, + "step": 2095 + }, + { + "epoch": 0.22, + "learning_rate": 1.9137537637866027e-05, + "loss": 1.5311, + "step": 2096 + }, + { + "epoch": 0.22, + "learning_rate": 1.9136049981644614e-05, + "loss": 1.4369, + "step": 2097 + }, + { + "epoch": 0.22, + "learning_rate": 1.913456110142724e-05, + "loss": 1.4528, + "step": 2098 + }, + { + "epoch": 0.22, + "learning_rate": 1.9133070997413384e-05, + "loss": 1.5294, + "step": 2099 + }, + { + "epoch": 0.22, + "learning_rate": 1.9131579669802685e-05, + "loss": 1.4588, + "step": 2100 + }, + { + "epoch": 0.22, + "learning_rate": 1.9130087118794934e-05, + "loss": 1.443, + "step": 2101 + }, + { + "epoch": 0.22, + "learning_rate": 1.9128593344590102e-05, + "loss": 1.4876, + "step": 2102 + }, + { + "epoch": 0.22, + "learning_rate": 1.912709834738831e-05, + "loss": 1.4874, + "step": 2103 + }, + { + "epoch": 0.22, + "learning_rate": 1.9125602127389856e-05, + "loss": 1.4966, + "step": 2104 + }, + { + "epoch": 0.22, + "learning_rate": 1.912410468479519e-05, + "loss": 1.5747, + "step": 2105 + }, + { + "epoch": 0.22, + "learning_rate": 1.9122606019804933e-05, + "loss": 1.4025, + "step": 2106 + }, + { + "epoch": 0.22, + "learning_rate": 1.912110613261987e-05, + "loss": 1.4755, + "step": 2107 + }, + { + "epoch": 0.22, + "learning_rate": 1.911960502344094e-05, + "loss": 1.4739, + "step": 2108 + }, + { + "epoch": 0.22, + "learning_rate": 1.911810269246926e-05, + "loss": 1.4992, + "step": 2109 + }, + { + "epoch": 0.22, + "learning_rate": 1.91165991399061e-05, + "loss": 1.4435, + "step": 2110 + }, + { + "epoch": 0.22, + "learning_rate": 1.91150943659529e-05, + "loss": 1.4918, + "step": 2111 + }, + { + "epoch": 0.22, + "learning_rate": 1.9113588370811258e-05, + "loss": 1.3818, + "step": 2112 + }, + { + "epoch": 0.22, + "learning_rate": 1.911208115468294e-05, + "loss": 1.5105, + "step": 2113 + }, + { + "epoch": 0.22, + "learning_rate": 1.9110572717769878e-05, + "loss": 1.6634, + "step": 2114 + }, + { + "epoch": 0.22, + "learning_rate": 1.9109063060274158e-05, + "loss": 1.5028, + "step": 2115 + }, + { + "epoch": 0.22, + "learning_rate": 1.9107552182398037e-05, + "loss": 1.6657, + "step": 2116 + }, + { + "epoch": 0.22, + "learning_rate": 1.9106040084343935e-05, + "loss": 1.5481, + "step": 2117 + }, + { + "epoch": 0.22, + "learning_rate": 1.910452676631444e-05, + "loss": 1.4505, + "step": 2118 + }, + { + "epoch": 0.22, + "learning_rate": 1.9103012228512284e-05, + "loss": 1.5173, + "step": 2119 + }, + { + "epoch": 0.22, + "learning_rate": 1.9101496471140385e-05, + "loss": 1.3788, + "step": 2120 + }, + { + "epoch": 0.22, + "learning_rate": 1.9099979494401814e-05, + "loss": 1.4649, + "step": 2121 + }, + { + "epoch": 0.22, + "learning_rate": 1.9098461298499805e-05, + "loss": 1.4204, + "step": 2122 + }, + { + "epoch": 0.22, + "learning_rate": 1.9096941883637766e-05, + "loss": 1.4439, + "step": 2123 + }, + { + "epoch": 0.22, + "learning_rate": 1.909542125001925e-05, + "loss": 1.6615, + "step": 2124 + }, + { + "epoch": 0.22, + "learning_rate": 1.9093899397847985e-05, + "loss": 1.4763, + "step": 2125 + }, + { + "epoch": 0.22, + "learning_rate": 1.909237632732786e-05, + "loss": 1.5353, + "step": 2126 + }, + { + "epoch": 0.22, + "learning_rate": 1.909085203866293e-05, + "loss": 1.442, + "step": 2127 + }, + { + "epoch": 0.22, + "learning_rate": 1.9089326532057408e-05, + "loss": 1.4782, + "step": 2128 + }, + { + "epoch": 0.22, + "learning_rate": 1.908779980771567e-05, + "loss": 1.4933, + "step": 2129 + }, + { + "epoch": 0.22, + "learning_rate": 1.9086271865842264e-05, + "loss": 1.5285, + "step": 2130 + }, + { + "epoch": 0.22, + "learning_rate": 1.9084742706641894e-05, + "loss": 1.4736, + "step": 2131 + }, + { + "epoch": 0.22, + "learning_rate": 1.9083212330319427e-05, + "loss": 1.4496, + "step": 2132 + }, + { + "epoch": 0.22, + "learning_rate": 1.908168073707989e-05, + "loss": 1.5099, + "step": 2133 + }, + { + "epoch": 0.22, + "learning_rate": 1.9080147927128483e-05, + "loss": 1.5235, + "step": 2134 + }, + { + "epoch": 0.22, + "learning_rate": 1.9078613900670556e-05, + "loss": 1.4769, + "step": 2135 + }, + { + "epoch": 0.22, + "learning_rate": 1.907707865791164e-05, + "loss": 1.5771, + "step": 2136 + }, + { + "epoch": 0.22, + "learning_rate": 1.907554219905741e-05, + "loss": 1.5116, + "step": 2137 + }, + { + "epoch": 0.22, + "learning_rate": 1.907400452431371e-05, + "loss": 1.5161, + "step": 2138 + }, + { + "epoch": 0.22, + "learning_rate": 1.9072465633886557e-05, + "loss": 1.4356, + "step": 2139 + }, + { + "epoch": 0.22, + "learning_rate": 1.9070925527982117e-05, + "loss": 1.509, + "step": 2140 + }, + { + "epoch": 0.22, + "learning_rate": 1.9069384206806723e-05, + "loss": 1.4681, + "step": 2141 + }, + { + "epoch": 0.22, + "learning_rate": 1.9067841670566883e-05, + "loss": 1.5254, + "step": 2142 + }, + { + "epoch": 0.22, + "learning_rate": 1.9066297919469242e-05, + "loss": 1.4797, + "step": 2143 + }, + { + "epoch": 0.22, + "learning_rate": 1.9064752953720636e-05, + "loss": 1.3996, + "step": 2144 + }, + { + "epoch": 0.22, + "learning_rate": 1.9063206773528042e-05, + "loss": 1.4457, + "step": 2145 + }, + { + "epoch": 0.23, + "learning_rate": 1.9061659379098617e-05, + "loss": 1.5126, + "step": 2146 + }, + { + "epoch": 0.23, + "learning_rate": 1.9060110770639664e-05, + "loss": 1.5925, + "step": 2147 + }, + { + "epoch": 0.23, + "learning_rate": 1.905856094835866e-05, + "loss": 1.5146, + "step": 2148 + }, + { + "epoch": 0.23, + "learning_rate": 1.905700991246324e-05, + "loss": 1.7256, + "step": 2149 + }, + { + "epoch": 0.23, + "learning_rate": 1.90554576631612e-05, + "loss": 1.57, + "step": 2150 + }, + { + "epoch": 0.23, + "learning_rate": 1.905390420066051e-05, + "loss": 1.3722, + "step": 2151 + }, + { + "epoch": 0.23, + "learning_rate": 1.9052349525169292e-05, + "loss": 1.3999, + "step": 2152 + }, + { + "epoch": 0.23, + "learning_rate": 1.9050793636895828e-05, + "loss": 1.586, + "step": 2153 + }, + { + "epoch": 0.23, + "learning_rate": 1.9049236536048567e-05, + "loss": 1.4884, + "step": 2154 + }, + { + "epoch": 0.23, + "learning_rate": 1.9047678222836127e-05, + "loss": 1.5898, + "step": 2155 + }, + { + "epoch": 0.23, + "learning_rate": 1.9046118697467278e-05, + "loss": 1.569, + "step": 2156 + }, + { + "epoch": 0.23, + "learning_rate": 1.904455796015095e-05, + "loss": 1.5592, + "step": 2157 + }, + { + "epoch": 0.23, + "learning_rate": 1.9042996011096253e-05, + "loss": 1.597, + "step": 2158 + }, + { + "epoch": 0.23, + "learning_rate": 1.904143285051244e-05, + "loss": 1.422, + "step": 2159 + }, + { + "epoch": 0.23, + "learning_rate": 1.903986847860894e-05, + "loss": 1.519, + "step": 2160 + }, + { + "epoch": 0.23, + "learning_rate": 1.9038302895595334e-05, + "loss": 1.5197, + "step": 2161 + }, + { + "epoch": 0.23, + "learning_rate": 1.903673610168137e-05, + "loss": 1.4655, + "step": 2162 + }, + { + "epoch": 0.23, + "learning_rate": 1.9035168097076965e-05, + "loss": 1.3909, + "step": 2163 + }, + { + "epoch": 0.23, + "learning_rate": 1.903359888199218e-05, + "loss": 1.4877, + "step": 2164 + }, + { + "epoch": 0.23, + "learning_rate": 1.903202845663726e-05, + "loss": 1.5123, + "step": 2165 + }, + { + "epoch": 0.23, + "learning_rate": 1.9030456821222593e-05, + "loss": 1.4906, + "step": 2166 + }, + { + "epoch": 0.23, + "learning_rate": 1.9028883975958745e-05, + "loss": 1.4574, + "step": 2167 + }, + { + "epoch": 0.23, + "learning_rate": 1.9027309921056435e-05, + "loss": 1.4571, + "step": 2168 + }, + { + "epoch": 0.23, + "learning_rate": 1.902573465672654e-05, + "loss": 1.4281, + "step": 2169 + }, + { + "epoch": 0.23, + "learning_rate": 1.9024158183180116e-05, + "loss": 1.5057, + "step": 2170 + }, + { + "epoch": 0.23, + "learning_rate": 1.902258050062836e-05, + "loss": 1.4514, + "step": 2171 + }, + { + "epoch": 0.23, + "learning_rate": 1.9021001609282646e-05, + "loss": 1.5055, + "step": 2172 + }, + { + "epoch": 0.23, + "learning_rate": 1.9019421509354505e-05, + "loss": 1.4578, + "step": 2173 + }, + { + "epoch": 0.23, + "learning_rate": 1.9017840201055625e-05, + "loss": 1.459, + "step": 2174 + }, + { + "epoch": 0.23, + "learning_rate": 1.9016257684597864e-05, + "loss": 1.5059, + "step": 2175 + }, + { + "epoch": 0.23, + "learning_rate": 1.901467396019324e-05, + "loss": 1.57, + "step": 2176 + }, + { + "epoch": 0.23, + "learning_rate": 1.901308902805393e-05, + "loss": 1.4924, + "step": 2177 + }, + { + "epoch": 0.23, + "learning_rate": 1.9011502888392273e-05, + "loss": 1.4979, + "step": 2178 + }, + { + "epoch": 0.23, + "learning_rate": 1.900991554142077e-05, + "loss": 1.5321, + "step": 2179 + }, + { + "epoch": 0.23, + "learning_rate": 1.9008326987352093e-05, + "loss": 1.493, + "step": 2180 + }, + { + "epoch": 0.23, + "learning_rate": 1.9006737226399056e-05, + "loss": 1.5111, + "step": 2181 + }, + { + "epoch": 0.23, + "learning_rate": 1.900514625877465e-05, + "loss": 1.4154, + "step": 2182 + }, + { + "epoch": 0.23, + "learning_rate": 1.900355408469203e-05, + "loss": 1.4934, + "step": 2183 + }, + { + "epoch": 0.23, + "learning_rate": 1.90019607043645e-05, + "loss": 1.5975, + "step": 2184 + }, + { + "epoch": 0.23, + "learning_rate": 1.9000366118005532e-05, + "loss": 1.3537, + "step": 2185 + }, + { + "epoch": 0.23, + "learning_rate": 1.899877032582876e-05, + "loss": 1.4583, + "step": 2186 + }, + { + "epoch": 0.23, + "learning_rate": 1.8997173328047984e-05, + "loss": 1.4586, + "step": 2187 + }, + { + "epoch": 0.23, + "learning_rate": 1.8995575124877156e-05, + "loss": 1.4774, + "step": 2188 + }, + { + "epoch": 0.23, + "learning_rate": 1.8993975716530394e-05, + "loss": 1.5025, + "step": 2189 + }, + { + "epoch": 0.23, + "eval_loss": 1.5263344049453735, + "eval_runtime": 77.1492, + "eval_samples_per_second": 1.672, + "eval_steps_per_second": 0.117, + "step": 2189 + }, + { + "epoch": 0.23, + "learning_rate": 1.899237510322198e-05, + "loss": 1.5438, + "step": 2190 + }, + { + "epoch": 0.23, + "learning_rate": 1.899077328516635e-05, + "loss": 1.5181, + "step": 2191 + }, + { + "epoch": 0.23, + "learning_rate": 1.8989170262578112e-05, + "loss": 1.4454, + "step": 2192 + }, + { + "epoch": 0.23, + "learning_rate": 1.8987566035672028e-05, + "loss": 1.4882, + "step": 2193 + }, + { + "epoch": 0.23, + "learning_rate": 1.8985960604663026e-05, + "loss": 1.5073, + "step": 2194 + }, + { + "epoch": 0.23, + "learning_rate": 1.8984353969766187e-05, + "loss": 1.4478, + "step": 2195 + }, + { + "epoch": 0.23, + "learning_rate": 1.8982746131196763e-05, + "loss": 1.4768, + "step": 2196 + }, + { + "epoch": 0.23, + "learning_rate": 1.8981137089170162e-05, + "loss": 1.5116, + "step": 2197 + }, + { + "epoch": 0.23, + "learning_rate": 1.8979526843901952e-05, + "loss": 1.4202, + "step": 2198 + }, + { + "epoch": 0.23, + "learning_rate": 1.8977915395607867e-05, + "loss": 1.4736, + "step": 2199 + }, + { + "epoch": 0.23, + "learning_rate": 1.89763027445038e-05, + "loss": 1.4489, + "step": 2200 + }, + { + "epoch": 0.23, + "learning_rate": 1.8974688890805804e-05, + "loss": 1.4512, + "step": 2201 + }, + { + "epoch": 0.23, + "learning_rate": 1.897307383473009e-05, + "loss": 1.5091, + "step": 2202 + }, + { + "epoch": 0.23, + "learning_rate": 1.897145757649304e-05, + "loss": 1.5512, + "step": 2203 + }, + { + "epoch": 0.23, + "learning_rate": 1.8969840116311192e-05, + "loss": 1.406, + "step": 2204 + }, + { + "epoch": 0.23, + "learning_rate": 1.896822145440124e-05, + "loss": 1.4531, + "step": 2205 + }, + { + "epoch": 0.23, + "learning_rate": 1.896660159098004e-05, + "loss": 1.4379, + "step": 2206 + }, + { + "epoch": 0.23, + "learning_rate": 1.896498052626462e-05, + "loss": 1.4783, + "step": 2207 + }, + { + "epoch": 0.23, + "learning_rate": 1.896335826047216e-05, + "loss": 1.4801, + "step": 2208 + }, + { + "epoch": 0.23, + "learning_rate": 1.896173479381999e-05, + "loss": 1.4526, + "step": 2209 + }, + { + "epoch": 0.23, + "learning_rate": 1.8960110126525627e-05, + "loss": 1.4952, + "step": 2210 + }, + { + "epoch": 0.23, + "learning_rate": 1.895848425880673e-05, + "loss": 1.5299, + "step": 2211 + }, + { + "epoch": 0.23, + "learning_rate": 1.8956857190881125e-05, + "loss": 1.5274, + "step": 2212 + }, + { + "epoch": 0.23, + "learning_rate": 1.8955228922966792e-05, + "loss": 1.4415, + "step": 2213 + }, + { + "epoch": 0.23, + "learning_rate": 1.8953599455281884e-05, + "loss": 1.5311, + "step": 2214 + }, + { + "epoch": 0.23, + "learning_rate": 1.8951968788044702e-05, + "loss": 1.4972, + "step": 2215 + }, + { + "epoch": 0.23, + "learning_rate": 1.8950336921473715e-05, + "loss": 1.4966, + "step": 2216 + }, + { + "epoch": 0.23, + "learning_rate": 1.8948703855787553e-05, + "loss": 1.4683, + "step": 2217 + }, + { + "epoch": 0.23, + "learning_rate": 1.8947069591205005e-05, + "loss": 1.503, + "step": 2218 + }, + { + "epoch": 0.23, + "learning_rate": 1.8945434127945014e-05, + "loss": 1.4902, + "step": 2219 + }, + { + "epoch": 0.23, + "learning_rate": 1.8943797466226702e-05, + "loss": 1.4835, + "step": 2220 + }, + { + "epoch": 0.23, + "learning_rate": 1.8942159606269332e-05, + "loss": 1.535, + "step": 2221 + }, + { + "epoch": 0.23, + "learning_rate": 1.8940520548292332e-05, + "loss": 1.491, + "step": 2222 + }, + { + "epoch": 0.23, + "learning_rate": 1.89388802925153e-05, + "loss": 1.5157, + "step": 2223 + }, + { + "epoch": 0.23, + "learning_rate": 1.8937238839157987e-05, + "loss": 1.4779, + "step": 2224 + }, + { + "epoch": 0.23, + "learning_rate": 1.8935596188440302e-05, + "loss": 1.4902, + "step": 2225 + }, + { + "epoch": 0.23, + "learning_rate": 1.8933952340582323e-05, + "loss": 1.4988, + "step": 2226 + }, + { + "epoch": 0.23, + "learning_rate": 1.893230729580428e-05, + "loss": 1.4568, + "step": 2227 + }, + { + "epoch": 0.23, + "learning_rate": 1.8930661054326567e-05, + "loss": 1.5163, + "step": 2228 + }, + { + "epoch": 0.23, + "learning_rate": 1.892901361636974e-05, + "loss": 1.4472, + "step": 2229 + }, + { + "epoch": 0.23, + "learning_rate": 1.892736498215451e-05, + "loss": 1.4658, + "step": 2230 + }, + { + "epoch": 0.23, + "learning_rate": 1.8925715151901754e-05, + "loss": 1.4281, + "step": 2231 + }, + { + "epoch": 0.23, + "learning_rate": 1.892406412583251e-05, + "loss": 1.415, + "step": 2232 + }, + { + "epoch": 0.23, + "learning_rate": 1.8922411904167966e-05, + "loss": 1.464, + "step": 2233 + }, + { + "epoch": 0.23, + "learning_rate": 1.892075848712948e-05, + "loss": 1.5014, + "step": 2234 + }, + { + "epoch": 0.23, + "learning_rate": 1.8919103874938568e-05, + "loss": 1.4397, + "step": 2235 + }, + { + "epoch": 0.23, + "learning_rate": 1.891744806781691e-05, + "loss": 1.5508, + "step": 2236 + }, + { + "epoch": 0.23, + "learning_rate": 1.8915791065986335e-05, + "loss": 1.4749, + "step": 2237 + }, + { + "epoch": 0.23, + "learning_rate": 1.891413286966884e-05, + "loss": 1.4538, + "step": 2238 + }, + { + "epoch": 0.23, + "learning_rate": 1.891247347908658e-05, + "loss": 1.4405, + "step": 2239 + }, + { + "epoch": 0.23, + "learning_rate": 1.8910812894461878e-05, + "loss": 1.3562, + "step": 2240 + }, + { + "epoch": 0.24, + "learning_rate": 1.89091511160172e-05, + "loss": 1.4811, + "step": 2241 + }, + { + "epoch": 0.24, + "learning_rate": 1.8907488143975186e-05, + "loss": 1.4286, + "step": 2242 + }, + { + "epoch": 0.24, + "learning_rate": 1.890582397855863e-05, + "loss": 1.4493, + "step": 2243 + }, + { + "epoch": 0.24, + "learning_rate": 1.890415861999049e-05, + "loss": 1.5639, + "step": 2244 + }, + { + "epoch": 0.24, + "learning_rate": 1.890249206849388e-05, + "loss": 1.6375, + "step": 2245 + }, + { + "epoch": 0.24, + "learning_rate": 1.890082432429208e-05, + "loss": 1.4982, + "step": 2246 + }, + { + "epoch": 0.24, + "learning_rate": 1.889915538760851e-05, + "loss": 1.492, + "step": 2247 + }, + { + "epoch": 0.24, + "learning_rate": 1.8897485258666778e-05, + "loss": 1.4294, + "step": 2248 + }, + { + "epoch": 0.24, + "learning_rate": 1.8895813937690638e-05, + "loss": 1.4617, + "step": 2249 + }, + { + "epoch": 0.24, + "learning_rate": 1.8894141424904e-05, + "loss": 1.4763, + "step": 2250 + }, + { + "epoch": 0.24, + "learning_rate": 1.8892467720530937e-05, + "loss": 1.3989, + "step": 2251 + }, + { + "epoch": 0.24, + "learning_rate": 1.8890792824795687e-05, + "loss": 1.4803, + "step": 2252 + }, + { + "epoch": 0.24, + "learning_rate": 1.8889116737922638e-05, + "loss": 1.4734, + "step": 2253 + }, + { + "epoch": 0.24, + "learning_rate": 1.8887439460136342e-05, + "loss": 1.5069, + "step": 2254 + }, + { + "epoch": 0.24, + "learning_rate": 1.8885760991661514e-05, + "loss": 1.5565, + "step": 2255 + }, + { + "epoch": 0.24, + "learning_rate": 1.8884081332723028e-05, + "loss": 1.4707, + "step": 2256 + }, + { + "epoch": 0.24, + "learning_rate": 1.8882400483545913e-05, + "loss": 1.5077, + "step": 2257 + }, + { + "epoch": 0.24, + "learning_rate": 1.888071844435536e-05, + "loss": 1.5075, + "step": 2258 + }, + { + "epoch": 0.24, + "learning_rate": 1.8879035215376717e-05, + "loss": 1.5185, + "step": 2259 + }, + { + "epoch": 0.24, + "learning_rate": 1.887735079683549e-05, + "loss": 1.6266, + "step": 2260 + }, + { + "epoch": 0.24, + "learning_rate": 1.8875665188957354e-05, + "loss": 1.5013, + "step": 2261 + }, + { + "epoch": 0.24, + "learning_rate": 1.887397839196814e-05, + "loss": 1.4362, + "step": 2262 + }, + { + "epoch": 0.24, + "learning_rate": 1.8872290406093827e-05, + "loss": 1.4718, + "step": 2263 + }, + { + "epoch": 0.24, + "learning_rate": 1.8870601231560567e-05, + "loss": 1.5202, + "step": 2264 + }, + { + "epoch": 0.24, + "learning_rate": 1.8868910868594664e-05, + "loss": 1.5168, + "step": 2265 + }, + { + "epoch": 0.24, + "learning_rate": 1.8867219317422588e-05, + "loss": 1.5142, + "step": 2266 + }, + { + "epoch": 0.24, + "learning_rate": 1.8865526578270954e-05, + "loss": 1.4885, + "step": 2267 + }, + { + "epoch": 0.24, + "learning_rate": 1.8863832651366552e-05, + "loss": 1.5441, + "step": 2268 + }, + { + "epoch": 0.24, + "learning_rate": 1.8862137536936328e-05, + "loss": 1.4647, + "step": 2269 + }, + { + "epoch": 0.24, + "learning_rate": 1.8860441235207374e-05, + "loss": 1.5352, + "step": 2270 + }, + { + "epoch": 0.24, + "learning_rate": 1.8858743746406958e-05, + "loss": 1.4568, + "step": 2271 + }, + { + "epoch": 0.24, + "learning_rate": 1.8857045070762497e-05, + "loss": 1.4865, + "step": 2272 + }, + { + "epoch": 0.24, + "learning_rate": 1.8855345208501573e-05, + "loss": 1.4637, + "step": 2273 + }, + { + "epoch": 0.24, + "learning_rate": 1.8853644159851918e-05, + "loss": 1.4348, + "step": 2274 + }, + { + "epoch": 0.24, + "learning_rate": 1.8851941925041436e-05, + "loss": 1.4413, + "step": 2275 + }, + { + "epoch": 0.24, + "learning_rate": 1.8850238504298177e-05, + "loss": 1.4434, + "step": 2276 + }, + { + "epoch": 0.24, + "learning_rate": 1.884853389785036e-05, + "loss": 1.4822, + "step": 2277 + }, + { + "epoch": 0.24, + "learning_rate": 1.8846828105926356e-05, + "loss": 1.4632, + "step": 2278 + }, + { + "epoch": 0.24, + "learning_rate": 1.8845121128754698e-05, + "loss": 1.48, + "step": 2279 + }, + { + "epoch": 0.24, + "learning_rate": 1.8843412966564078e-05, + "loss": 1.4518, + "step": 2280 + }, + { + "epoch": 0.24, + "learning_rate": 1.884170361958334e-05, + "loss": 1.4334, + "step": 2281 + }, + { + "epoch": 0.24, + "learning_rate": 1.8839993088041502e-05, + "loss": 1.5131, + "step": 2282 + }, + { + "epoch": 0.24, + "learning_rate": 1.8838281372167724e-05, + "loss": 1.508, + "step": 2283 + }, + { + "epoch": 0.24, + "learning_rate": 1.8836568472191335e-05, + "loss": 1.4086, + "step": 2284 + }, + { + "epoch": 0.24, + "learning_rate": 1.883485438834182e-05, + "loss": 1.5021, + "step": 2285 + }, + { + "epoch": 0.24, + "learning_rate": 1.8833139120848817e-05, + "loss": 1.5083, + "step": 2286 + }, + { + "epoch": 0.24, + "learning_rate": 1.8831422669942137e-05, + "loss": 1.4162, + "step": 2287 + }, + { + "epoch": 0.24, + "learning_rate": 1.8829705035851734e-05, + "loss": 1.5494, + "step": 2288 + }, + { + "epoch": 0.24, + "learning_rate": 1.8827986218807724e-05, + "loss": 1.425, + "step": 2289 + }, + { + "epoch": 0.24, + "learning_rate": 1.8826266219040396e-05, + "loss": 1.5215, + "step": 2290 + }, + { + "epoch": 0.24, + "learning_rate": 1.8824545036780172e-05, + "loss": 1.5577, + "step": 2291 + }, + { + "epoch": 0.24, + "learning_rate": 1.8822822672257655e-05, + "loss": 1.4923, + "step": 2292 + }, + { + "epoch": 0.24, + "learning_rate": 1.8821099125703595e-05, + "loss": 1.4648, + "step": 2293 + }, + { + "epoch": 0.24, + "learning_rate": 1.8819374397348902e-05, + "loss": 1.471, + "step": 2294 + }, + { + "epoch": 0.24, + "learning_rate": 1.8817648487424648e-05, + "loss": 1.5658, + "step": 2295 + }, + { + "epoch": 0.24, + "learning_rate": 1.8815921396162058e-05, + "loss": 1.5348, + "step": 2296 + }, + { + "epoch": 0.24, + "learning_rate": 1.8814193123792518e-05, + "loss": 1.4081, + "step": 2297 + }, + { + "epoch": 0.24, + "learning_rate": 1.881246367054757e-05, + "loss": 1.4762, + "step": 2298 + }, + { + "epoch": 0.24, + "learning_rate": 1.8810733036658925e-05, + "loss": 1.4399, + "step": 2299 + }, + { + "epoch": 0.24, + "learning_rate": 1.8809001222358432e-05, + "loss": 1.4763, + "step": 2300 + }, + { + "epoch": 0.24, + "learning_rate": 1.880726822787812e-05, + "loss": 1.4874, + "step": 2301 + }, + { + "epoch": 0.24, + "learning_rate": 1.880553405345016e-05, + "loss": 1.4951, + "step": 2302 + }, + { + "epoch": 0.24, + "learning_rate": 1.8803798699306887e-05, + "loss": 1.4697, + "step": 2303 + }, + { + "epoch": 0.24, + "learning_rate": 1.880206216568079e-05, + "loss": 1.481, + "step": 2304 + }, + { + "epoch": 0.24, + "learning_rate": 1.880032445280453e-05, + "loss": 1.4485, + "step": 2305 + }, + { + "epoch": 0.24, + "learning_rate": 1.879858556091091e-05, + "loss": 1.4749, + "step": 2306 + }, + { + "epoch": 0.24, + "learning_rate": 1.8796845490232894e-05, + "loss": 1.5605, + "step": 2307 + }, + { + "epoch": 0.24, + "learning_rate": 1.879510424100361e-05, + "loss": 1.4835, + "step": 2308 + }, + { + "epoch": 0.24, + "learning_rate": 1.8793361813456346e-05, + "loss": 1.4344, + "step": 2309 + }, + { + "epoch": 0.24, + "learning_rate": 1.8791618207824532e-05, + "loss": 1.4571, + "step": 2310 + }, + { + "epoch": 0.24, + "learning_rate": 1.8789873424341772e-05, + "loss": 1.482, + "step": 2311 + }, + { + "epoch": 0.24, + "learning_rate": 1.8788127463241822e-05, + "loss": 1.4736, + "step": 2312 + }, + { + "epoch": 0.24, + "learning_rate": 1.8786380324758597e-05, + "loss": 1.4807, + "step": 2313 + }, + { + "epoch": 0.24, + "learning_rate": 1.8784632009126167e-05, + "loss": 1.4418, + "step": 2314 + }, + { + "epoch": 0.24, + "learning_rate": 1.878288251657876e-05, + "loss": 1.5248, + "step": 2315 + }, + { + "epoch": 0.24, + "learning_rate": 1.8781131847350768e-05, + "loss": 1.483, + "step": 2316 + }, + { + "epoch": 0.24, + "learning_rate": 1.877938000167673e-05, + "loss": 1.5474, + "step": 2317 + }, + { + "epoch": 0.24, + "learning_rate": 1.8777626979791347e-05, + "loss": 1.4671, + "step": 2318 + }, + { + "epoch": 0.24, + "learning_rate": 1.877587278192949e-05, + "loss": 1.3049, + "step": 2319 + }, + { + "epoch": 0.24, + "learning_rate": 1.877411740832616e-05, + "loss": 1.483, + "step": 2320 + }, + { + "epoch": 0.24, + "learning_rate": 1.877236085921655e-05, + "loss": 1.508, + "step": 2321 + }, + { + "epoch": 0.24, + "learning_rate": 1.8770603134835978e-05, + "loss": 1.4854, + "step": 2322 + }, + { + "epoch": 0.24, + "learning_rate": 1.8768844235419942e-05, + "loss": 1.4808, + "step": 2323 + }, + { + "epoch": 0.24, + "learning_rate": 1.8767084161204087e-05, + "loss": 1.5352, + "step": 2324 + }, + { + "epoch": 0.24, + "learning_rate": 1.8765322912424214e-05, + "loss": 1.5628, + "step": 2325 + }, + { + "epoch": 0.24, + "learning_rate": 1.8763560489316292e-05, + "loss": 1.494, + "step": 2326 + }, + { + "epoch": 0.24, + "learning_rate": 1.876179689211643e-05, + "loss": 1.509, + "step": 2327 + }, + { + "epoch": 0.24, + "learning_rate": 1.8760032121060918e-05, + "loss": 1.5021, + "step": 2328 + }, + { + "epoch": 0.24, + "learning_rate": 1.875826617638618e-05, + "loss": 1.4179, + "step": 2329 + }, + { + "epoch": 0.24, + "learning_rate": 1.8756499058328813e-05, + "loss": 1.4302, + "step": 2330 + }, + { + "epoch": 0.24, + "learning_rate": 1.8754730767125564e-05, + "loss": 1.4959, + "step": 2331 + }, + { + "epoch": 0.24, + "learning_rate": 1.8752961303013336e-05, + "loss": 1.4423, + "step": 2332 + }, + { + "epoch": 0.24, + "learning_rate": 1.8751190666229194e-05, + "loss": 1.4564, + "step": 2333 + }, + { + "epoch": 0.24, + "learning_rate": 1.8749418857010358e-05, + "loss": 1.4775, + "step": 2334 + }, + { + "epoch": 0.24, + "learning_rate": 1.8747645875594203e-05, + "loss": 1.4182, + "step": 2335 + }, + { + "epoch": 0.24, + "learning_rate": 1.8745871722218265e-05, + "loss": 1.3957, + "step": 2336 + }, + { + "epoch": 0.25, + "learning_rate": 1.8744096397120235e-05, + "loss": 1.4633, + "step": 2337 + }, + { + "epoch": 0.25, + "learning_rate": 1.874231990053796e-05, + "loss": 1.5512, + "step": 2338 + }, + { + "epoch": 0.25, + "learning_rate": 1.8740542232709444e-05, + "loss": 1.3461, + "step": 2339 + }, + { + "epoch": 0.25, + "learning_rate": 1.8738763393872848e-05, + "loss": 1.4754, + "step": 2340 + }, + { + "epoch": 0.25, + "learning_rate": 1.8736983384266495e-05, + "loss": 1.5448, + "step": 2341 + }, + { + "epoch": 0.25, + "learning_rate": 1.8735202204128854e-05, + "loss": 1.4491, + "step": 2342 + }, + { + "epoch": 0.25, + "learning_rate": 1.8733419853698566e-05, + "loss": 1.457, + "step": 2343 + }, + { + "epoch": 0.25, + "learning_rate": 1.8731636333214414e-05, + "loss": 1.4314, + "step": 2344 + }, + { + "epoch": 0.25, + "learning_rate": 1.8729851642915345e-05, + "loss": 1.3979, + "step": 2345 + }, + { + "epoch": 0.25, + "learning_rate": 1.8728065783040464e-05, + "loss": 1.4146, + "step": 2346 + }, + { + "epoch": 0.25, + "learning_rate": 1.8726278753829027e-05, + "loss": 1.4361, + "step": 2347 + }, + { + "epoch": 0.25, + "learning_rate": 1.872449055552045e-05, + "loss": 1.4989, + "step": 2348 + }, + { + "epoch": 0.25, + "learning_rate": 1.872270118835431e-05, + "loss": 1.5062, + "step": 2349 + }, + { + "epoch": 0.25, + "learning_rate": 1.872091065257033e-05, + "loss": 1.4509, + "step": 2350 + }, + { + "epoch": 0.25, + "learning_rate": 1.8719118948408403e-05, + "loss": 1.4631, + "step": 2351 + }, + { + "epoch": 0.25, + "learning_rate": 1.8717326076108566e-05, + "loss": 1.5119, + "step": 2352 + }, + { + "epoch": 0.25, + "learning_rate": 1.8715532035911017e-05, + "loss": 1.6347, + "step": 2353 + }, + { + "epoch": 0.25, + "learning_rate": 1.8713736828056115e-05, + "loss": 1.5526, + "step": 2354 + }, + { + "epoch": 0.25, + "learning_rate": 1.8711940452784368e-05, + "loss": 1.6348, + "step": 2355 + }, + { + "epoch": 0.25, + "learning_rate": 1.871014291033645e-05, + "loss": 1.5183, + "step": 2356 + }, + { + "epoch": 0.25, + "learning_rate": 1.8708344200953182e-05, + "loss": 1.458, + "step": 2357 + }, + { + "epoch": 0.25, + "learning_rate": 1.8706544324875545e-05, + "loss": 1.524, + "step": 2358 + }, + { + "epoch": 0.25, + "learning_rate": 1.8704743282344672e-05, + "loss": 1.4479, + "step": 2359 + }, + { + "epoch": 0.25, + "learning_rate": 1.870294107360186e-05, + "loss": 1.5408, + "step": 2360 + }, + { + "epoch": 0.25, + "learning_rate": 1.8701137698888563e-05, + "loss": 1.5007, + "step": 2361 + }, + { + "epoch": 0.25, + "learning_rate": 1.8699333158446382e-05, + "loss": 1.5132, + "step": 2362 + }, + { + "epoch": 0.25, + "learning_rate": 1.869752745251708e-05, + "loss": 1.4263, + "step": 2363 + }, + { + "epoch": 0.25, + "learning_rate": 1.8695720581342574e-05, + "loss": 1.422, + "step": 2364 + }, + { + "epoch": 0.25, + "learning_rate": 1.869391254516494e-05, + "loss": 1.4411, + "step": 2365 + }, + { + "epoch": 0.25, + "learning_rate": 1.8692103344226406e-05, + "loss": 1.4594, + "step": 2366 + }, + { + "epoch": 0.25, + "learning_rate": 1.8690292978769364e-05, + "loss": 1.4992, + "step": 2367 + }, + { + "epoch": 0.25, + "learning_rate": 1.868848144903635e-05, + "loss": 1.4822, + "step": 2368 + }, + { + "epoch": 0.25, + "learning_rate": 1.8686668755270064e-05, + "loss": 1.5402, + "step": 2369 + }, + { + "epoch": 0.25, + "learning_rate": 1.8684854897713363e-05, + "loss": 1.5268, + "step": 2370 + }, + { + "epoch": 0.25, + "learning_rate": 1.8683039876609258e-05, + "loss": 1.5587, + "step": 2371 + }, + { + "epoch": 0.25, + "learning_rate": 1.868122369220091e-05, + "loss": 1.4214, + "step": 2372 + }, + { + "epoch": 0.25, + "learning_rate": 1.8679406344731645e-05, + "loss": 1.5089, + "step": 2373 + }, + { + "epoch": 0.25, + "learning_rate": 1.867758783444494e-05, + "loss": 1.5067, + "step": 2374 + }, + { + "epoch": 0.25, + "learning_rate": 1.8675768161584427e-05, + "loss": 2.0616, + "step": 2375 + }, + { + "epoch": 0.25, + "learning_rate": 1.8673947326393903e-05, + "loss": 1.5617, + "step": 2376 + }, + { + "epoch": 0.25, + "learning_rate": 1.86721253291173e-05, + "loss": 1.4422, + "step": 2377 + }, + { + "epoch": 0.25, + "learning_rate": 1.867030216999873e-05, + "loss": 1.4727, + "step": 2378 + }, + { + "epoch": 0.25, + "learning_rate": 1.8668477849282443e-05, + "loss": 1.4152, + "step": 2379 + }, + { + "epoch": 0.25, + "learning_rate": 1.8666652367212856e-05, + "loss": 1.4376, + "step": 2380 + }, + { + "epoch": 0.25, + "learning_rate": 1.8664825724034534e-05, + "loss": 1.393, + "step": 2381 + }, + { + "epoch": 0.25, + "learning_rate": 1.8662997919992197e-05, + "loss": 1.4864, + "step": 2382 + }, + { + "epoch": 0.25, + "learning_rate": 1.866116895533073e-05, + "loss": 1.4261, + "step": 2383 + }, + { + "epoch": 0.25, + "learning_rate": 1.8659338830295163e-05, + "loss": 1.4555, + "step": 2384 + }, + { + "epoch": 0.25, + "learning_rate": 1.8657507545130687e-05, + "loss": 1.4939, + "step": 2385 + }, + { + "epoch": 0.25, + "learning_rate": 1.865567510008265e-05, + "loss": 1.4123, + "step": 2386 + }, + { + "epoch": 0.25, + "learning_rate": 1.8653841495396546e-05, + "loss": 1.4459, + "step": 2387 + }, + { + "epoch": 0.25, + "learning_rate": 1.8652006731318038e-05, + "loss": 1.396, + "step": 2388 + }, + { + "epoch": 0.25, + "eval_loss": 1.5139706134796143, + "eval_runtime": 77.2904, + "eval_samples_per_second": 1.669, + "eval_steps_per_second": 0.116, + "step": 2388 + }, + { + "epoch": 0.25, + "learning_rate": 1.8650170808092936e-05, + "loss": 1.4666, + "step": 2389 + }, + { + "epoch": 0.25, + "learning_rate": 1.86483337259672e-05, + "loss": 1.5154, + "step": 2390 + }, + { + "epoch": 0.25, + "learning_rate": 1.864649548518696e-05, + "loss": 1.5163, + "step": 2391 + }, + { + "epoch": 0.25, + "learning_rate": 1.864465608599849e-05, + "loss": 1.4734, + "step": 2392 + }, + { + "epoch": 0.25, + "learning_rate": 1.864281552864822e-05, + "loss": 1.5217, + "step": 2393 + }, + { + "epoch": 0.25, + "learning_rate": 1.8640973813382737e-05, + "loss": 1.4694, + "step": 2394 + }, + { + "epoch": 0.25, + "learning_rate": 1.863913094044879e-05, + "loss": 1.4761, + "step": 2395 + }, + { + "epoch": 0.25, + "learning_rate": 1.863728691009327e-05, + "loss": 1.4766, + "step": 2396 + }, + { + "epoch": 0.25, + "learning_rate": 1.863544172256323e-05, + "loss": 1.5695, + "step": 2397 + }, + { + "epoch": 0.25, + "learning_rate": 1.8633595378105882e-05, + "loss": 1.5079, + "step": 2398 + }, + { + "epoch": 0.25, + "learning_rate": 1.8631747876968584e-05, + "loss": 1.4154, + "step": 2399 + }, + { + "epoch": 0.25, + "learning_rate": 1.862989921939886e-05, + "loss": 1.4488, + "step": 2400 + }, + { + "epoch": 0.25, + "learning_rate": 1.8628049405644376e-05, + "loss": 1.4279, + "step": 2401 + }, + { + "epoch": 0.25, + "learning_rate": 1.8626198435952966e-05, + "loss": 1.4896, + "step": 2402 + }, + { + "epoch": 0.25, + "learning_rate": 1.8624346310572602e-05, + "loss": 1.4315, + "step": 2403 + }, + { + "epoch": 0.25, + "learning_rate": 1.862249302975143e-05, + "loss": 1.4919, + "step": 2404 + }, + { + "epoch": 0.25, + "learning_rate": 1.8620638593737743e-05, + "loss": 1.4561, + "step": 2405 + }, + { + "epoch": 0.25, + "learning_rate": 1.8618783002779985e-05, + "loss": 1.4622, + "step": 2406 + }, + { + "epoch": 0.25, + "learning_rate": 1.8616926257126754e-05, + "loss": 1.4917, + "step": 2407 + }, + { + "epoch": 0.25, + "learning_rate": 1.861506835702681e-05, + "loss": 1.4962, + "step": 2408 + }, + { + "epoch": 0.25, + "learning_rate": 1.861320930272906e-05, + "loss": 1.4164, + "step": 2409 + }, + { + "epoch": 0.25, + "learning_rate": 1.8611349094482578e-05, + "loss": 1.4889, + "step": 2410 + }, + { + "epoch": 0.25, + "learning_rate": 1.8609487732536576e-05, + "loss": 1.543, + "step": 2411 + }, + { + "epoch": 0.25, + "learning_rate": 1.8607625217140433e-05, + "loss": 1.5417, + "step": 2412 + }, + { + "epoch": 0.25, + "learning_rate": 1.8605761548543674e-05, + "loss": 1.5304, + "step": 2413 + }, + { + "epoch": 0.25, + "learning_rate": 1.860389672699599e-05, + "loss": 1.4725, + "step": 2414 + }, + { + "epoch": 0.25, + "learning_rate": 1.860203075274721e-05, + "loss": 1.4745, + "step": 2415 + }, + { + "epoch": 0.25, + "learning_rate": 1.8600163626047334e-05, + "loss": 1.4656, + "step": 2416 + }, + { + "epoch": 0.25, + "learning_rate": 1.8598295347146503e-05, + "loss": 1.5287, + "step": 2417 + }, + { + "epoch": 0.25, + "learning_rate": 1.8596425916295023e-05, + "loss": 1.5024, + "step": 2418 + }, + { + "epoch": 0.25, + "learning_rate": 1.8594555333743348e-05, + "loss": 1.4527, + "step": 2419 + }, + { + "epoch": 0.25, + "learning_rate": 1.859268359974209e-05, + "loss": 1.4897, + "step": 2420 + }, + { + "epoch": 0.25, + "learning_rate": 1.859081071454201e-05, + "loss": 1.3554, + "step": 2421 + }, + { + "epoch": 0.25, + "learning_rate": 1.858893667839403e-05, + "loss": 1.4004, + "step": 2422 + }, + { + "epoch": 0.25, + "learning_rate": 1.858706149154922e-05, + "loss": 1.5582, + "step": 2423 + }, + { + "epoch": 0.25, + "learning_rate": 1.8585185154258803e-05, + "loss": 1.505, + "step": 2424 + }, + { + "epoch": 0.25, + "learning_rate": 1.858330766677417e-05, + "loss": 1.5043, + "step": 2425 + }, + { + "epoch": 0.25, + "learning_rate": 1.858142902934685e-05, + "loss": 1.439, + "step": 2426 + }, + { + "epoch": 0.25, + "learning_rate": 1.857954924222853e-05, + "loss": 1.4927, + "step": 2427 + }, + { + "epoch": 0.25, + "learning_rate": 1.8577668305671056e-05, + "loss": 1.5395, + "step": 2428 + }, + { + "epoch": 0.25, + "learning_rate": 1.8575786219926427e-05, + "loss": 1.4737, + "step": 2429 + }, + { + "epoch": 0.25, + "learning_rate": 1.8573902985246794e-05, + "loss": 1.6151, + "step": 2430 + }, + { + "epoch": 0.25, + "learning_rate": 1.857201860188446e-05, + "loss": 1.4313, + "step": 2431 + }, + { + "epoch": 0.26, + "learning_rate": 1.857013307009188e-05, + "loss": 1.4509, + "step": 2432 + }, + { + "epoch": 0.26, + "learning_rate": 1.8568246390121673e-05, + "loss": 1.3998, + "step": 2433 + }, + { + "epoch": 0.26, + "learning_rate": 1.8566358562226603e-05, + "loss": 1.5268, + "step": 2434 + }, + { + "epoch": 0.26, + "learning_rate": 1.8564469586659593e-05, + "loss": 1.4369, + "step": 2435 + }, + { + "epoch": 0.26, + "learning_rate": 1.8562579463673713e-05, + "loss": 1.4759, + "step": 2436 + }, + { + "epoch": 0.26, + "learning_rate": 1.8560688193522197e-05, + "loss": 1.4092, + "step": 2437 + }, + { + "epoch": 0.26, + "learning_rate": 1.855879577645842e-05, + "loss": 1.43, + "step": 2438 + }, + { + "epoch": 0.26, + "learning_rate": 1.855690221273592e-05, + "loss": 1.5143, + "step": 2439 + }, + { + "epoch": 0.26, + "learning_rate": 1.8555007502608385e-05, + "loss": 1.5482, + "step": 2440 + }, + { + "epoch": 0.26, + "learning_rate": 1.855311164632966e-05, + "loss": 1.4406, + "step": 2441 + }, + { + "epoch": 0.26, + "learning_rate": 1.8551214644153738e-05, + "loss": 1.4551, + "step": 2442 + }, + { + "epoch": 0.26, + "learning_rate": 1.8549316496334774e-05, + "loss": 1.4663, + "step": 2443 + }, + { + "epoch": 0.26, + "learning_rate": 1.8547417203127064e-05, + "loss": 1.4732, + "step": 2444 + }, + { + "epoch": 0.26, + "learning_rate": 1.8545516764785067e-05, + "loss": 1.5378, + "step": 2445 + }, + { + "epoch": 0.26, + "learning_rate": 1.8543615181563397e-05, + "loss": 1.4448, + "step": 2446 + }, + { + "epoch": 0.26, + "learning_rate": 1.854171245371681e-05, + "loss": 1.2861, + "step": 2447 + }, + { + "epoch": 0.26, + "learning_rate": 1.8539808581500228e-05, + "loss": 1.4405, + "step": 2448 + }, + { + "epoch": 0.26, + "learning_rate": 1.8537903565168716e-05, + "loss": 1.4876, + "step": 2449 + }, + { + "epoch": 0.26, + "learning_rate": 1.8535997404977506e-05, + "loss": 1.4119, + "step": 2450 + }, + { + "epoch": 0.26, + "learning_rate": 1.8534090101181967e-05, + "loss": 1.4451, + "step": 2451 + }, + { + "epoch": 0.26, + "learning_rate": 1.8532181654037632e-05, + "loss": 1.4035, + "step": 2452 + }, + { + "epoch": 0.26, + "learning_rate": 1.853027206380018e-05, + "loss": 1.4624, + "step": 2453 + }, + { + "epoch": 0.26, + "learning_rate": 1.852836133072545e-05, + "loss": 1.4935, + "step": 2454 + }, + { + "epoch": 0.26, + "learning_rate": 1.8526449455069434e-05, + "loss": 1.4834, + "step": 2455 + }, + { + "epoch": 0.26, + "learning_rate": 1.8524536437088266e-05, + "loss": 1.498, + "step": 2456 + }, + { + "epoch": 0.26, + "learning_rate": 1.8522622277038247e-05, + "loss": 1.3417, + "step": 2457 + }, + { + "epoch": 0.26, + "learning_rate": 1.852070697517583e-05, + "loss": 1.4455, + "step": 2458 + }, + { + "epoch": 0.26, + "learning_rate": 1.8518790531757607e-05, + "loss": 1.4119, + "step": 2459 + }, + { + "epoch": 0.26, + "learning_rate": 1.8516872947040337e-05, + "loss": 1.558, + "step": 2460 + }, + { + "epoch": 0.26, + "learning_rate": 1.8514954221280926e-05, + "loss": 1.4862, + "step": 2461 + }, + { + "epoch": 0.26, + "learning_rate": 1.8513034354736433e-05, + "loss": 1.6806, + "step": 2462 + }, + { + "epoch": 0.26, + "learning_rate": 1.8511113347664072e-05, + "loss": 1.438, + "step": 2463 + }, + { + "epoch": 0.26, + "learning_rate": 1.850919120032121e-05, + "loss": 1.4975, + "step": 2464 + }, + { + "epoch": 0.26, + "learning_rate": 1.850726791296536e-05, + "loss": 1.4409, + "step": 2465 + }, + { + "epoch": 0.26, + "learning_rate": 1.85053434858542e-05, + "loss": 1.4769, + "step": 2466 + }, + { + "epoch": 0.26, + "learning_rate": 1.8503417919245548e-05, + "loss": 1.5823, + "step": 2467 + }, + { + "epoch": 0.26, + "learning_rate": 1.8501491213397386e-05, + "loss": 1.4045, + "step": 2468 + }, + { + "epoch": 0.26, + "learning_rate": 1.8499563368567837e-05, + "loss": 1.4828, + "step": 2469 + }, + { + "epoch": 0.26, + "learning_rate": 1.849763438501519e-05, + "loss": 1.4684, + "step": 2470 + }, + { + "epoch": 0.26, + "learning_rate": 1.8495704262997873e-05, + "loss": 1.4577, + "step": 2471 + }, + { + "epoch": 0.26, + "learning_rate": 1.8493773002774475e-05, + "loss": 1.4759, + "step": 2472 + }, + { + "epoch": 0.26, + "learning_rate": 1.8491840604603736e-05, + "loss": 1.4259, + "step": 2473 + }, + { + "epoch": 0.26, + "learning_rate": 1.8489907068744543e-05, + "loss": 1.4717, + "step": 2474 + }, + { + "epoch": 0.26, + "learning_rate": 1.848797239545595e-05, + "loss": 1.4247, + "step": 2475 + }, + { + "epoch": 0.26, + "learning_rate": 1.8486036584997143e-05, + "loss": 1.4954, + "step": 2476 + }, + { + "epoch": 0.26, + "learning_rate": 1.8484099637627472e-05, + "loss": 1.4926, + "step": 2477 + }, + { + "epoch": 0.26, + "learning_rate": 1.8482161553606447e-05, + "loss": 1.487, + "step": 2478 + }, + { + "epoch": 0.26, + "learning_rate": 1.8480222333193715e-05, + "loss": 1.4553, + "step": 2479 + }, + { + "epoch": 0.26, + "learning_rate": 1.847828197664908e-05, + "loss": 1.4862, + "step": 2480 + }, + { + "epoch": 0.26, + "learning_rate": 1.8476340484232508e-05, + "loss": 1.4867, + "step": 2481 + }, + { + "epoch": 0.26, + "learning_rate": 1.8474397856204097e-05, + "loss": 1.4736, + "step": 2482 + }, + { + "epoch": 0.26, + "learning_rate": 1.8472454092824122e-05, + "loss": 1.4254, + "step": 2483 + }, + { + "epoch": 0.26, + "learning_rate": 1.8470509194352987e-05, + "loss": 1.4455, + "step": 2484 + }, + { + "epoch": 0.26, + "learning_rate": 1.8468563161051263e-05, + "loss": 1.4402, + "step": 2485 + }, + { + "epoch": 0.26, + "learning_rate": 1.846661599317967e-05, + "loss": 1.4611, + "step": 2486 + }, + { + "epoch": 0.26, + "learning_rate": 1.8464667690999073e-05, + "loss": 1.4814, + "step": 2487 + }, + { + "epoch": 0.26, + "learning_rate": 1.8462718254770503e-05, + "loss": 1.4559, + "step": 2488 + }, + { + "epoch": 0.26, + "learning_rate": 1.8460767684755127e-05, + "loss": 1.4667, + "step": 2489 + }, + { + "epoch": 0.26, + "learning_rate": 1.8458815981214274e-05, + "loss": 1.4427, + "step": 2490 + }, + { + "epoch": 0.26, + "learning_rate": 1.845686314440942e-05, + "loss": 1.4055, + "step": 2491 + }, + { + "epoch": 0.26, + "learning_rate": 1.8454909174602198e-05, + "loss": 1.5563, + "step": 2492 + }, + { + "epoch": 0.26, + "learning_rate": 1.845295407205439e-05, + "loss": 1.4631, + "step": 2493 + }, + { + "epoch": 0.26, + "learning_rate": 1.8450997837027925e-05, + "loss": 1.4887, + "step": 2494 + }, + { + "epoch": 0.26, + "learning_rate": 1.8449040469784895e-05, + "loss": 1.5212, + "step": 2495 + }, + { + "epoch": 0.26, + "learning_rate": 1.844708197058753e-05, + "loss": 1.5582, + "step": 2496 + }, + { + "epoch": 0.26, + "learning_rate": 1.844512233969822e-05, + "loss": 1.4599, + "step": 2497 + }, + { + "epoch": 0.26, + "learning_rate": 1.844316157737951e-05, + "loss": 1.4546, + "step": 2498 + }, + { + "epoch": 0.26, + "learning_rate": 1.844119968389409e-05, + "loss": 1.4631, + "step": 2499 + }, + { + "epoch": 0.26, + "learning_rate": 1.84392366595048e-05, + "loss": 1.4817, + "step": 2500 + }, + { + "epoch": 0.26, + "learning_rate": 1.8437272504474636e-05, + "loss": 1.4214, + "step": 2501 + }, + { + "epoch": 0.26, + "learning_rate": 1.8435307219066744e-05, + "loss": 1.471, + "step": 2502 + }, + { + "epoch": 0.26, + "learning_rate": 1.8433340803544424e-05, + "loss": 1.4693, + "step": 2503 + }, + { + "epoch": 0.26, + "learning_rate": 1.8431373258171127e-05, + "loss": 1.6297, + "step": 2504 + }, + { + "epoch": 0.26, + "learning_rate": 1.842940458321045e-05, + "loss": 1.5916, + "step": 2505 + }, + { + "epoch": 0.26, + "learning_rate": 1.842743477892614e-05, + "loss": 1.4754, + "step": 2506 + }, + { + "epoch": 0.26, + "learning_rate": 1.842546384558211e-05, + "loss": 1.4828, + "step": 2507 + }, + { + "epoch": 0.26, + "learning_rate": 1.842349178344241e-05, + "loss": 1.4239, + "step": 2508 + }, + { + "epoch": 0.26, + "learning_rate": 1.8421518592771243e-05, + "loss": 1.5028, + "step": 2509 + }, + { + "epoch": 0.26, + "learning_rate": 1.841954427383297e-05, + "loss": 1.4848, + "step": 2510 + }, + { + "epoch": 0.26, + "learning_rate": 1.8417568826892097e-05, + "loss": 1.4617, + "step": 2511 + }, + { + "epoch": 0.26, + "learning_rate": 1.8415592252213284e-05, + "loss": 1.4266, + "step": 2512 + }, + { + "epoch": 0.26, + "learning_rate": 1.8413614550061344e-05, + "loss": 1.4321, + "step": 2513 + }, + { + "epoch": 0.26, + "learning_rate": 1.841163572070123e-05, + "loss": 1.4693, + "step": 2514 + }, + { + "epoch": 0.26, + "learning_rate": 1.840965576439806e-05, + "loss": 1.4257, + "step": 2515 + }, + { + "epoch": 0.26, + "learning_rate": 1.84076746814171e-05, + "loss": 1.4488, + "step": 2516 + }, + { + "epoch": 0.26, + "learning_rate": 1.840569247202376e-05, + "loss": 1.5348, + "step": 2517 + }, + { + "epoch": 0.26, + "learning_rate": 1.8403709136483604e-05, + "loss": 1.477, + "step": 2518 + }, + { + "epoch": 0.26, + "learning_rate": 1.840172467506235e-05, + "loss": 1.443, + "step": 2519 + }, + { + "epoch": 0.26, + "learning_rate": 1.839973908802587e-05, + "loss": 1.4772, + "step": 2520 + }, + { + "epoch": 0.26, + "learning_rate": 1.839775237564017e-05, + "loss": 1.4443, + "step": 2521 + }, + { + "epoch": 0.26, + "learning_rate": 1.839576453817143e-05, + "loss": 1.4063, + "step": 2522 + }, + { + "epoch": 0.26, + "learning_rate": 1.8393775575885963e-05, + "loss": 1.5178, + "step": 2523 + }, + { + "epoch": 0.26, + "learning_rate": 1.8391785489050235e-05, + "loss": 1.4337, + "step": 2524 + }, + { + "epoch": 0.26, + "learning_rate": 1.8389794277930875e-05, + "loss": 1.4512, + "step": 2525 + }, + { + "epoch": 0.26, + "learning_rate": 1.838780194279465e-05, + "loss": 1.5578, + "step": 2526 + }, + { + "epoch": 0.26, + "learning_rate": 1.8385808483908484e-05, + "loss": 1.4606, + "step": 2527 + }, + { + "epoch": 0.27, + "learning_rate": 1.8383813901539444e-05, + "loss": 1.4957, + "step": 2528 + }, + { + "epoch": 0.27, + "learning_rate": 1.838181819595476e-05, + "loss": 1.4914, + "step": 2529 + }, + { + "epoch": 0.27, + "learning_rate": 1.8379821367421802e-05, + "loss": 1.4785, + "step": 2530 + }, + { + "epoch": 0.27, + "learning_rate": 1.837782341620809e-05, + "loss": 1.4052, + "step": 2531 + }, + { + "epoch": 0.27, + "learning_rate": 1.8375824342581303e-05, + "loss": 1.4807, + "step": 2532 + }, + { + "epoch": 0.27, + "learning_rate": 1.8373824146809264e-05, + "loss": 1.4313, + "step": 2533 + }, + { + "epoch": 0.27, + "learning_rate": 1.8371822829159945e-05, + "loss": 1.4374, + "step": 2534 + }, + { + "epoch": 0.27, + "learning_rate": 1.836982038990148e-05, + "loss": 1.4482, + "step": 2535 + }, + { + "epoch": 0.27, + "learning_rate": 1.8367816829302133e-05, + "loss": 1.5231, + "step": 2536 + }, + { + "epoch": 0.27, + "learning_rate": 1.8365812147630337e-05, + "loss": 1.4101, + "step": 2537 + }, + { + "epoch": 0.27, + "learning_rate": 1.8363806345154666e-05, + "loss": 1.4372, + "step": 2538 + }, + { + "epoch": 0.27, + "learning_rate": 1.8361799422143845e-05, + "loss": 1.4808, + "step": 2539 + }, + { + "epoch": 0.27, + "learning_rate": 1.835979137886675e-05, + "loss": 1.3515, + "step": 2540 + }, + { + "epoch": 0.27, + "learning_rate": 1.8357782215592412e-05, + "loss": 1.5284, + "step": 2541 + }, + { + "epoch": 0.27, + "learning_rate": 1.835577193259e-05, + "loss": 1.4222, + "step": 2542 + }, + { + "epoch": 0.27, + "learning_rate": 1.8353760530128846e-05, + "loss": 1.4522, + "step": 2543 + }, + { + "epoch": 0.27, + "learning_rate": 1.835174800847842e-05, + "loss": 1.4487, + "step": 2544 + }, + { + "epoch": 0.27, + "learning_rate": 1.8349734367908355e-05, + "loss": 1.3688, + "step": 2545 + }, + { + "epoch": 0.27, + "learning_rate": 1.8347719608688422e-05, + "loss": 1.483, + "step": 2546 + }, + { + "epoch": 0.27, + "learning_rate": 1.8345703731088554e-05, + "loss": 1.4733, + "step": 2547 + }, + { + "epoch": 0.27, + "learning_rate": 1.8343686735378816e-05, + "loss": 1.4594, + "step": 2548 + }, + { + "epoch": 0.27, + "learning_rate": 1.834166862182944e-05, + "loss": 1.4648, + "step": 2549 + }, + { + "epoch": 0.27, + "learning_rate": 1.8339649390710807e-05, + "loss": 1.5249, + "step": 2550 + }, + { + "epoch": 0.27, + "learning_rate": 1.8337629042293434e-05, + "loss": 1.4744, + "step": 2551 + }, + { + "epoch": 0.27, + "learning_rate": 1.8335607576847994e-05, + "loss": 1.5094, + "step": 2552 + }, + { + "epoch": 0.27, + "learning_rate": 1.8333584994645318e-05, + "loss": 1.5122, + "step": 2553 + }, + { + "epoch": 0.27, + "learning_rate": 1.8331561295956374e-05, + "loss": 1.537, + "step": 2554 + }, + { + "epoch": 0.27, + "learning_rate": 1.832953648105229e-05, + "loss": 1.4691, + "step": 2555 + }, + { + "epoch": 0.27, + "learning_rate": 1.8327510550204343e-05, + "loss": 1.4969, + "step": 2556 + }, + { + "epoch": 0.27, + "learning_rate": 1.8325483503683944e-05, + "loss": 1.4596, + "step": 2557 + }, + { + "epoch": 0.27, + "learning_rate": 1.8323455341762675e-05, + "loss": 1.435, + "step": 2558 + }, + { + "epoch": 0.27, + "learning_rate": 1.8321426064712255e-05, + "loss": 1.4883, + "step": 2559 + }, + { + "epoch": 0.27, + "learning_rate": 1.8319395672804554e-05, + "loss": 1.3758, + "step": 2560 + }, + { + "epoch": 0.27, + "learning_rate": 1.8317364166311592e-05, + "loss": 1.4352, + "step": 2561 + }, + { + "epoch": 0.27, + "learning_rate": 1.831533154550554e-05, + "loss": 1.5072, + "step": 2562 + }, + { + "epoch": 0.27, + "learning_rate": 1.8313297810658718e-05, + "loss": 1.4476, + "step": 2563 + }, + { + "epoch": 0.27, + "learning_rate": 1.831126296204359e-05, + "loss": 1.507, + "step": 2564 + }, + { + "epoch": 0.27, + "learning_rate": 1.8309226999932777e-05, + "loss": 1.4677, + "step": 2565 + }, + { + "epoch": 0.27, + "learning_rate": 1.8307189924599044e-05, + "loss": 1.4537, + "step": 2566 + }, + { + "epoch": 0.27, + "learning_rate": 1.8305151736315307e-05, + "loss": 1.4584, + "step": 2567 + }, + { + "epoch": 0.27, + "learning_rate": 1.8303112435354634e-05, + "loss": 1.4944, + "step": 2568 + }, + { + "epoch": 0.27, + "learning_rate": 1.8301072021990232e-05, + "loss": 1.4379, + "step": 2569 + }, + { + "epoch": 0.27, + "learning_rate": 1.8299030496495475e-05, + "loss": 1.539, + "step": 2570 + }, + { + "epoch": 0.27, + "learning_rate": 1.829698785914386e-05, + "loss": 1.4421, + "step": 2571 + }, + { + "epoch": 0.27, + "learning_rate": 1.8294944110209063e-05, + "loss": 1.4693, + "step": 2572 + }, + { + "epoch": 0.27, + "learning_rate": 1.8292899249964887e-05, + "loss": 1.3239, + "step": 2573 + }, + { + "epoch": 0.27, + "learning_rate": 1.8290853278685284e-05, + "loss": 1.472, + "step": 2574 + }, + { + "epoch": 0.27, + "learning_rate": 1.8288806196644374e-05, + "loss": 1.536, + "step": 2575 + }, + { + "epoch": 0.27, + "learning_rate": 1.8286758004116405e-05, + "loss": 1.4644, + "step": 2576 + }, + { + "epoch": 0.27, + "learning_rate": 1.8284708701375783e-05, + "loss": 1.4537, + "step": 2577 + }, + { + "epoch": 0.27, + "learning_rate": 1.8282658288697067e-05, + "loss": 1.4359, + "step": 2578 + }, + { + "epoch": 0.27, + "learning_rate": 1.8280606766354955e-05, + "loss": 1.4842, + "step": 2579 + }, + { + "epoch": 0.27, + "learning_rate": 1.8278554134624302e-05, + "loss": 1.4664, + "step": 2580 + }, + { + "epoch": 0.27, + "learning_rate": 1.8276500393780105e-05, + "loss": 1.4632, + "step": 2581 + }, + { + "epoch": 0.27, + "learning_rate": 1.827444554409751e-05, + "loss": 1.4996, + "step": 2582 + }, + { + "epoch": 0.27, + "learning_rate": 1.827238958585182e-05, + "loss": 1.3399, + "step": 2583 + }, + { + "epoch": 0.27, + "learning_rate": 1.8270332519318476e-05, + "loss": 1.3928, + "step": 2584 + }, + { + "epoch": 0.27, + "learning_rate": 1.8268274344773074e-05, + "loss": 1.4993, + "step": 2585 + }, + { + "epoch": 0.27, + "learning_rate": 1.8266215062491356e-05, + "loss": 1.5398, + "step": 2586 + }, + { + "epoch": 0.27, + "learning_rate": 1.826415467274921e-05, + "loss": 1.4353, + "step": 2587 + }, + { + "epoch": 0.27, + "eval_loss": 1.5104212760925293, + "eval_runtime": 77.3448, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2587 + }, + { + "epoch": 0.27, + "learning_rate": 1.8262093175822685e-05, + "loss": 1.4889, + "step": 2588 + }, + { + "epoch": 0.27, + "learning_rate": 1.826003057198796e-05, + "loss": 1.4912, + "step": 2589 + }, + { + "epoch": 0.27, + "learning_rate": 1.825796686152137e-05, + "loss": 1.4884, + "step": 2590 + }, + { + "epoch": 0.27, + "learning_rate": 1.8255902044699404e-05, + "loss": 1.478, + "step": 2591 + }, + { + "epoch": 0.27, + "learning_rate": 1.8253836121798692e-05, + "loss": 1.6549, + "step": 2592 + }, + { + "epoch": 0.27, + "learning_rate": 1.8251769093096018e-05, + "loss": 1.5146, + "step": 2593 + }, + { + "epoch": 0.27, + "learning_rate": 1.8249700958868306e-05, + "loss": 1.4797, + "step": 2594 + }, + { + "epoch": 0.27, + "learning_rate": 1.8247631719392634e-05, + "loss": 1.4655, + "step": 2595 + }, + { + "epoch": 0.27, + "learning_rate": 1.824556137494623e-05, + "loss": 1.4517, + "step": 2596 + }, + { + "epoch": 0.27, + "learning_rate": 1.8243489925806458e-05, + "loss": 1.4936, + "step": 2597 + }, + { + "epoch": 0.27, + "learning_rate": 1.8241417372250852e-05, + "loss": 1.4614, + "step": 2598 + }, + { + "epoch": 0.27, + "learning_rate": 1.8239343714557073e-05, + "loss": 1.4475, + "step": 2599 + }, + { + "epoch": 0.27, + "learning_rate": 1.8237268953002937e-05, + "loss": 1.5435, + "step": 2600 + }, + { + "epoch": 0.27, + "learning_rate": 1.8235193087866413e-05, + "loss": 1.4616, + "step": 2601 + }, + { + "epoch": 0.27, + "learning_rate": 1.8233116119425612e-05, + "loss": 1.4578, + "step": 2602 + }, + { + "epoch": 0.27, + "learning_rate": 1.8231038047958795e-05, + "loss": 1.434, + "step": 2603 + }, + { + "epoch": 0.27, + "learning_rate": 1.8228958873744368e-05, + "loss": 1.5335, + "step": 2604 + }, + { + "epoch": 0.27, + "learning_rate": 1.8226878597060887e-05, + "loss": 1.415, + "step": 2605 + }, + { + "epoch": 0.27, + "learning_rate": 1.8224797218187058e-05, + "loss": 1.6165, + "step": 2606 + }, + { + "epoch": 0.27, + "learning_rate": 1.822271473740173e-05, + "loss": 1.372, + "step": 2607 + }, + { + "epoch": 0.27, + "learning_rate": 1.8220631154983907e-05, + "loss": 1.4855, + "step": 2608 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218546471212727e-05, + "loss": 1.4093, + "step": 2609 + }, + { + "epoch": 0.27, + "learning_rate": 1.821646068636749e-05, + "loss": 1.4852, + "step": 2610 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214373800727637e-05, + "loss": 1.6959, + "step": 2611 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212285814572755e-05, + "loss": 1.3874, + "step": 2612 + }, + { + "epoch": 0.27, + "learning_rate": 1.821019672818258e-05, + "loss": 1.4425, + "step": 2613 + }, + { + "epoch": 0.27, + "learning_rate": 1.8208106541837e-05, + "loss": 1.6097, + "step": 2614 + }, + { + "epoch": 0.27, + "learning_rate": 1.8206015255816045e-05, + "loss": 1.5675, + "step": 2615 + }, + { + "epoch": 0.27, + "learning_rate": 1.820392287039989e-05, + "loss": 1.4039, + "step": 2616 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201829385868866e-05, + "loss": 1.4872, + "step": 2617 + }, + { + "epoch": 0.27, + "learning_rate": 1.819973480250344e-05, + "loss": 1.4645, + "step": 2618 + }, + { + "epoch": 0.27, + "learning_rate": 1.8197639120584237e-05, + "loss": 1.4923, + "step": 2619 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195542340392025e-05, + "loss": 1.4294, + "step": 2620 + }, + { + "epoch": 0.27, + "learning_rate": 1.8193444462207717e-05, + "loss": 1.4315, + "step": 2621 + }, + { + "epoch": 0.27, + "learning_rate": 1.8191345486312372e-05, + "loss": 1.3972, + "step": 2622 + }, + { + "epoch": 0.28, + "learning_rate": 1.8189245412987205e-05, + "loss": 1.462, + "step": 2623 + }, + { + "epoch": 0.28, + "learning_rate": 1.8187144242513567e-05, + "loss": 1.4738, + "step": 2624 + }, + { + "epoch": 0.28, + "learning_rate": 1.818504197517296e-05, + "loss": 1.4935, + "step": 2625 + }, + { + "epoch": 0.28, + "learning_rate": 1.8182938611247038e-05, + "loss": 1.4231, + "step": 2626 + }, + { + "epoch": 0.28, + "learning_rate": 1.81808341510176e-05, + "loss": 1.4031, + "step": 2627 + }, + { + "epoch": 0.28, + "learning_rate": 1.817872859476658e-05, + "loss": 1.5822, + "step": 2628 + }, + { + "epoch": 0.28, + "learning_rate": 1.8176621942776075e-05, + "loss": 1.432, + "step": 2629 + }, + { + "epoch": 0.28, + "learning_rate": 1.8174514195328324e-05, + "loss": 1.5565, + "step": 2630 + }, + { + "epoch": 0.28, + "learning_rate": 1.8172405352705704e-05, + "loss": 1.4895, + "step": 2631 + }, + { + "epoch": 0.28, + "learning_rate": 1.8170295415190754e-05, + "loss": 1.4032, + "step": 2632 + }, + { + "epoch": 0.28, + "learning_rate": 1.8168184383066144e-05, + "loss": 1.4253, + "step": 2633 + }, + { + "epoch": 0.28, + "learning_rate": 1.8166072256614702e-05, + "loss": 1.5162, + "step": 2634 + }, + { + "epoch": 0.28, + "learning_rate": 1.81639590361194e-05, + "loss": 1.4609, + "step": 2635 + }, + { + "epoch": 0.28, + "learning_rate": 1.816184472186335e-05, + "loss": 1.4351, + "step": 2636 + }, + { + "epoch": 0.28, + "learning_rate": 1.8159729314129823e-05, + "loss": 1.4738, + "step": 2637 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157612813202224e-05, + "loss": 1.5986, + "step": 2638 + }, + { + "epoch": 0.28, + "learning_rate": 1.815549521936411e-05, + "loss": 1.4633, + "step": 2639 + }, + { + "epoch": 0.28, + "learning_rate": 1.8153376532899184e-05, + "loss": 1.4404, + "step": 2640 + }, + { + "epoch": 0.28, + "learning_rate": 1.81512567540913e-05, + "loss": 1.4256, + "step": 2641 + }, + { + "epoch": 0.28, + "learning_rate": 1.814913588322445e-05, + "loss": 1.4054, + "step": 2642 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147013920582773e-05, + "loss": 1.4134, + "step": 2643 + }, + { + "epoch": 0.28, + "learning_rate": 1.8144890866450567e-05, + "loss": 1.4098, + "step": 2644 + }, + { + "epoch": 0.28, + "learning_rate": 1.814276672111226e-05, + "loss": 1.4593, + "step": 2645 + }, + { + "epoch": 0.28, + "learning_rate": 1.814064148485243e-05, + "loss": 1.4679, + "step": 2646 + }, + { + "epoch": 0.28, + "learning_rate": 1.8138515157955812e-05, + "loss": 1.5234, + "step": 2647 + }, + { + "epoch": 0.28, + "learning_rate": 1.8136387740707272e-05, + "loss": 1.4568, + "step": 2648 + }, + { + "epoch": 0.28, + "learning_rate": 1.8134259233391836e-05, + "loss": 1.5057, + "step": 2649 + }, + { + "epoch": 0.28, + "learning_rate": 1.8132129636294665e-05, + "loss": 1.3643, + "step": 2650 + }, + { + "epoch": 0.28, + "learning_rate": 1.812999894970107e-05, + "loss": 1.4766, + "step": 2651 + }, + { + "epoch": 0.28, + "learning_rate": 1.812786717389651e-05, + "loss": 1.5701, + "step": 2652 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125734309166587e-05, + "loss": 1.5341, + "step": 2653 + }, + { + "epoch": 0.28, + "learning_rate": 1.812360035579705e-05, + "loss": 1.3596, + "step": 2654 + }, + { + "epoch": 0.28, + "learning_rate": 1.8121465314073793e-05, + "loss": 1.4847, + "step": 2655 + }, + { + "epoch": 0.28, + "learning_rate": 1.811932918428286e-05, + "loss": 1.4664, + "step": 2656 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117191966710438e-05, + "loss": 1.4673, + "step": 2657 + }, + { + "epoch": 0.28, + "learning_rate": 1.8115053661642856e-05, + "loss": 1.4712, + "step": 2658 + }, + { + "epoch": 0.28, + "learning_rate": 1.811291426936659e-05, + "loss": 1.4458, + "step": 2659 + }, + { + "epoch": 0.28, + "learning_rate": 1.811077379016827e-05, + "loss": 1.4667, + "step": 2660 + }, + { + "epoch": 0.28, + "learning_rate": 1.810863222433466e-05, + "loss": 1.4695, + "step": 2661 + }, + { + "epoch": 0.28, + "learning_rate": 1.8106489572152677e-05, + "loss": 1.5263, + "step": 2662 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104345833909376e-05, + "loss": 1.4148, + "step": 2663 + }, + { + "epoch": 0.28, + "learning_rate": 1.8102201009891976e-05, + "loss": 1.3955, + "step": 2664 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100055100387814e-05, + "loss": 1.6056, + "step": 2665 + }, + { + "epoch": 0.28, + "learning_rate": 1.8097908105684396e-05, + "loss": 1.5394, + "step": 2666 + }, + { + "epoch": 0.28, + "learning_rate": 1.809576002606936e-05, + "loss": 1.479, + "step": 2667 + }, + { + "epoch": 0.28, + "learning_rate": 1.8093610861830494e-05, + "loss": 1.4492, + "step": 2668 + }, + { + "epoch": 0.28, + "learning_rate": 1.8091460613255728e-05, + "loss": 1.4172, + "step": 2669 + }, + { + "epoch": 0.28, + "learning_rate": 1.808930928063315e-05, + "loss": 1.4498, + "step": 2670 + }, + { + "epoch": 0.28, + "learning_rate": 1.808715686425097e-05, + "loss": 1.6203, + "step": 2671 + }, + { + "epoch": 0.28, + "learning_rate": 1.8085003364397567e-05, + "loss": 1.435, + "step": 2672 + }, + { + "epoch": 0.28, + "learning_rate": 1.808284878136145e-05, + "loss": 1.4489, + "step": 2673 + }, + { + "epoch": 0.28, + "learning_rate": 1.8080693115431277e-05, + "loss": 1.4416, + "step": 2674 + }, + { + "epoch": 0.28, + "learning_rate": 1.8078536366895853e-05, + "loss": 1.422, + "step": 2675 + }, + { + "epoch": 0.28, + "learning_rate": 1.8076378536044128e-05, + "loss": 1.4039, + "step": 2676 + }, + { + "epoch": 0.28, + "learning_rate": 1.8074219623165195e-05, + "loss": 1.4705, + "step": 2677 + }, + { + "epoch": 0.28, + "learning_rate": 1.807205962854829e-05, + "loss": 1.5031, + "step": 2678 + }, + { + "epoch": 0.28, + "learning_rate": 1.8069898552482806e-05, + "loss": 1.4812, + "step": 2679 + }, + { + "epoch": 0.28, + "learning_rate": 1.806773639525826e-05, + "loss": 1.4129, + "step": 2680 + }, + { + "epoch": 0.28, + "learning_rate": 1.8065573157164332e-05, + "loss": 1.4559, + "step": 2681 + }, + { + "epoch": 0.28, + "learning_rate": 1.806340883849084e-05, + "loss": 1.3878, + "step": 2682 + }, + { + "epoch": 0.28, + "learning_rate": 1.8061243439527744e-05, + "loss": 1.4752, + "step": 2683 + }, + { + "epoch": 0.28, + "learning_rate": 1.8059076960565156e-05, + "loss": 1.4089, + "step": 2684 + }, + { + "epoch": 0.28, + "learning_rate": 1.8056909401893326e-05, + "loss": 1.4736, + "step": 2685 + }, + { + "epoch": 0.28, + "learning_rate": 1.8054740763802654e-05, + "loss": 1.3796, + "step": 2686 + }, + { + "epoch": 0.28, + "learning_rate": 1.805257104658368e-05, + "loss": 1.4412, + "step": 2687 + }, + { + "epoch": 0.28, + "learning_rate": 1.8050400250527086e-05, + "loss": 1.4639, + "step": 2688 + }, + { + "epoch": 0.28, + "learning_rate": 1.804822837592371e-05, + "loss": 1.4076, + "step": 2689 + }, + { + "epoch": 0.28, + "learning_rate": 1.804605542306452e-05, + "loss": 1.4627, + "step": 2690 + }, + { + "epoch": 0.28, + "learning_rate": 1.8043881392240642e-05, + "loss": 1.5249, + "step": 2691 + }, + { + "epoch": 0.28, + "learning_rate": 1.804170628374334e-05, + "loss": 1.4312, + "step": 2692 + }, + { + "epoch": 0.28, + "learning_rate": 1.803953009786402e-05, + "loss": 1.5676, + "step": 2693 + }, + { + "epoch": 0.28, + "learning_rate": 1.8037352834894233e-05, + "loss": 1.5072, + "step": 2694 + }, + { + "epoch": 0.28, + "learning_rate": 1.803517449512568e-05, + "loss": 1.5662, + "step": 2695 + }, + { + "epoch": 0.28, + "learning_rate": 1.8032995078850207e-05, + "loss": 1.4771, + "step": 2696 + }, + { + "epoch": 0.28, + "learning_rate": 1.803081458635979e-05, + "loss": 1.412, + "step": 2697 + }, + { + "epoch": 0.28, + "learning_rate": 1.8028633017946564e-05, + "loss": 1.497, + "step": 2698 + }, + { + "epoch": 0.28, + "learning_rate": 1.8026450373902804e-05, + "loss": 1.4528, + "step": 2699 + }, + { + "epoch": 0.28, + "learning_rate": 1.802426665452093e-05, + "loss": 1.4785, + "step": 2700 + }, + { + "epoch": 0.28, + "learning_rate": 1.8022081860093493e-05, + "loss": 1.6411, + "step": 2701 + }, + { + "epoch": 0.28, + "learning_rate": 1.8019895990913213e-05, + "loss": 1.4459, + "step": 2702 + }, + { + "epoch": 0.28, + "learning_rate": 1.8017709047272932e-05, + "loss": 1.4418, + "step": 2703 + }, + { + "epoch": 0.28, + "learning_rate": 1.801552102946565e-05, + "loss": 1.4409, + "step": 2704 + }, + { + "epoch": 0.28, + "learning_rate": 1.8013331937784498e-05, + "loss": 1.4651, + "step": 2705 + }, + { + "epoch": 0.28, + "learning_rate": 1.8011141772522766e-05, + "loss": 1.4161, + "step": 2706 + }, + { + "epoch": 0.28, + "learning_rate": 1.8008950533973876e-05, + "loss": 1.458, + "step": 2707 + }, + { + "epoch": 0.28, + "learning_rate": 1.8006758222431398e-05, + "loss": 1.4477, + "step": 2708 + }, + { + "epoch": 0.28, + "learning_rate": 1.800456483818904e-05, + "loss": 1.4433, + "step": 2709 + }, + { + "epoch": 0.28, + "learning_rate": 1.8002370381540672e-05, + "loss": 1.5005, + "step": 2710 + }, + { + "epoch": 0.28, + "learning_rate": 1.8000174852780282e-05, + "loss": 1.4945, + "step": 2711 + }, + { + "epoch": 0.28, + "learning_rate": 1.7997978252202023e-05, + "loss": 1.4298, + "step": 2712 + }, + { + "epoch": 0.28, + "learning_rate": 1.7995780580100177e-05, + "loss": 1.3812, + "step": 2713 + }, + { + "epoch": 0.28, + "learning_rate": 1.799358183676918e-05, + "loss": 1.5559, + "step": 2714 + }, + { + "epoch": 0.28, + "learning_rate": 1.79913820225036e-05, + "loss": 1.4316, + "step": 2715 + }, + { + "epoch": 0.28, + "learning_rate": 1.798918113759817e-05, + "loss": 1.419, + "step": 2716 + }, + { + "epoch": 0.28, + "learning_rate": 1.7986979182347733e-05, + "loss": 1.43, + "step": 2717 + }, + { + "epoch": 0.29, + "learning_rate": 1.798477615704731e-05, + "loss": 1.4964, + "step": 2718 + }, + { + "epoch": 0.29, + "learning_rate": 1.7982572061992044e-05, + "loss": 1.4417, + "step": 2719 + }, + { + "epoch": 0.29, + "learning_rate": 1.7980366897477227e-05, + "loss": 1.4562, + "step": 2720 + }, + { + "epoch": 0.29, + "learning_rate": 1.7978160663798295e-05, + "loss": 1.4386, + "step": 2721 + }, + { + "epoch": 0.29, + "learning_rate": 1.7975953361250824e-05, + "loss": 1.445, + "step": 2722 + }, + { + "epoch": 0.29, + "learning_rate": 1.797374499013054e-05, + "loss": 1.4549, + "step": 2723 + }, + { + "epoch": 0.29, + "learning_rate": 1.7971535550733305e-05, + "loss": 1.5205, + "step": 2724 + }, + { + "epoch": 0.29, + "learning_rate": 1.796932504335513e-05, + "loss": 1.4632, + "step": 2725 + }, + { + "epoch": 0.29, + "learning_rate": 1.796711346829216e-05, + "loss": 1.3767, + "step": 2726 + }, + { + "epoch": 0.29, + "learning_rate": 1.79649008258407e-05, + "loss": 1.4098, + "step": 2727 + }, + { + "epoch": 0.29, + "learning_rate": 1.7962687116297178e-05, + "loss": 1.4675, + "step": 2728 + }, + { + "epoch": 0.29, + "learning_rate": 1.7960472339958176e-05, + "loss": 1.6048, + "step": 2729 + }, + { + "epoch": 0.29, + "learning_rate": 1.7958256497120418e-05, + "loss": 1.5432, + "step": 2730 + }, + { + "epoch": 0.29, + "learning_rate": 1.7956039588080774e-05, + "loss": 1.5453, + "step": 2731 + }, + { + "epoch": 0.29, + "learning_rate": 1.7953821613136246e-05, + "loss": 1.4246, + "step": 2732 + }, + { + "epoch": 0.29, + "learning_rate": 1.7951602572583988e-05, + "loss": 1.3987, + "step": 2733 + }, + { + "epoch": 0.29, + "learning_rate": 1.7949382466721295e-05, + "loss": 1.4943, + "step": 2734 + }, + { + "epoch": 0.29, + "learning_rate": 1.7947161295845606e-05, + "loss": 1.4385, + "step": 2735 + }, + { + "epoch": 0.29, + "learning_rate": 1.7944939060254497e-05, + "loss": 1.4165, + "step": 2736 + }, + { + "epoch": 0.29, + "learning_rate": 1.7942715760245692e-05, + "loss": 1.4004, + "step": 2737 + }, + { + "epoch": 0.29, + "learning_rate": 1.7940491396117063e-05, + "loss": 1.4577, + "step": 2738 + }, + { + "epoch": 0.29, + "learning_rate": 1.7938265968166602e-05, + "loss": 1.4649, + "step": 2739 + }, + { + "epoch": 0.29, + "learning_rate": 1.7936039476692473e-05, + "loss": 1.5273, + "step": 2740 + }, + { + "epoch": 0.29, + "learning_rate": 1.7933811921992962e-05, + "loss": 1.4325, + "step": 2741 + }, + { + "epoch": 0.29, + "learning_rate": 1.793158330436651e-05, + "loss": 1.4388, + "step": 2742 + }, + { + "epoch": 0.29, + "learning_rate": 1.7929353624111687e-05, + "loss": 1.4124, + "step": 2743 + }, + { + "epoch": 0.29, + "learning_rate": 1.7927122881527222e-05, + "loss": 1.5449, + "step": 2744 + }, + { + "epoch": 0.29, + "learning_rate": 1.7924891076911964e-05, + "loss": 1.4728, + "step": 2745 + }, + { + "epoch": 0.29, + "learning_rate": 1.7922658210564932e-05, + "loss": 1.5103, + "step": 2746 + }, + { + "epoch": 0.29, + "learning_rate": 1.792042428278526e-05, + "loss": 1.5975, + "step": 2747 + }, + { + "epoch": 0.29, + "learning_rate": 1.7918189293872247e-05, + "loss": 1.567, + "step": 2748 + }, + { + "epoch": 0.29, + "learning_rate": 1.7915953244125318e-05, + "loss": 1.57, + "step": 2749 + }, + { + "epoch": 0.29, + "learning_rate": 1.791371613384405e-05, + "loss": 1.4372, + "step": 2750 + }, + { + "epoch": 0.29, + "learning_rate": 1.7911477963328155e-05, + "loss": 1.4053, + "step": 2751 + }, + { + "epoch": 0.29, + "learning_rate": 1.7909238732877492e-05, + "loss": 1.3782, + "step": 2752 + }, + { + "epoch": 0.29, + "learning_rate": 1.790699844279206e-05, + "loss": 1.4401, + "step": 2753 + }, + { + "epoch": 0.29, + "learning_rate": 1.7904757093372e-05, + "loss": 1.3749, + "step": 2754 + }, + { + "epoch": 0.29, + "learning_rate": 1.79025146849176e-05, + "loss": 1.4909, + "step": 2755 + }, + { + "epoch": 0.29, + "learning_rate": 1.7900271217729273e-05, + "loss": 1.4103, + "step": 2756 + }, + { + "epoch": 0.29, + "learning_rate": 1.7898026692107597e-05, + "loss": 1.4986, + "step": 2757 + }, + { + "epoch": 0.29, + "learning_rate": 1.7895781108353278e-05, + "loss": 1.5449, + "step": 2758 + }, + { + "epoch": 0.29, + "learning_rate": 1.789353446676717e-05, + "loss": 1.5583, + "step": 2759 + }, + { + "epoch": 0.29, + "learning_rate": 1.7891286767650254e-05, + "loss": 1.5342, + "step": 2760 + }, + { + "epoch": 0.29, + "learning_rate": 1.7889038011303673e-05, + "loss": 1.4233, + "step": 2761 + }, + { + "epoch": 0.29, + "learning_rate": 1.7886788198028707e-05, + "loss": 1.3433, + "step": 2762 + }, + { + "epoch": 0.29, + "learning_rate": 1.788453732812676e-05, + "loss": 1.4451, + "step": 2763 + }, + { + "epoch": 0.29, + "learning_rate": 1.78822854018994e-05, + "loss": 1.4506, + "step": 2764 + }, + { + "epoch": 0.29, + "learning_rate": 1.7880032419648324e-05, + "loss": 1.4386, + "step": 2765 + }, + { + "epoch": 0.29, + "learning_rate": 1.7877778381675374e-05, + "loss": 1.4512, + "step": 2766 + }, + { + "epoch": 0.29, + "learning_rate": 1.7875523288282535e-05, + "loss": 1.4319, + "step": 2767 + }, + { + "epoch": 0.29, + "learning_rate": 1.7873267139771932e-05, + "loss": 1.4753, + "step": 2768 + }, + { + "epoch": 0.29, + "learning_rate": 1.787100993644583e-05, + "loss": 1.4044, + "step": 2769 + }, + { + "epoch": 0.29, + "learning_rate": 1.786875167860663e-05, + "loss": 1.4382, + "step": 2770 + }, + { + "epoch": 0.29, + "learning_rate": 1.786649236655689e-05, + "loss": 1.3977, + "step": 2771 + }, + { + "epoch": 0.29, + "learning_rate": 1.7864232000599298e-05, + "loss": 1.4473, + "step": 2772 + }, + { + "epoch": 0.29, + "learning_rate": 1.7861970581036678e-05, + "loss": 1.4666, + "step": 2773 + }, + { + "epoch": 0.29, + "learning_rate": 1.785970810817201e-05, + "loss": 1.5299, + "step": 2774 + }, + { + "epoch": 0.29, + "learning_rate": 1.7857444582308402e-05, + "loss": 1.3974, + "step": 2775 + }, + { + "epoch": 0.29, + "learning_rate": 1.7855180003749114e-05, + "loss": 1.4603, + "step": 2776 + }, + { + "epoch": 0.29, + "learning_rate": 1.7852914372797535e-05, + "loss": 1.463, + "step": 2777 + }, + { + "epoch": 0.29, + "learning_rate": 1.7850647689757205e-05, + "loss": 1.5317, + "step": 2778 + }, + { + "epoch": 0.29, + "learning_rate": 1.78483799549318e-05, + "loss": 1.4669, + "step": 2779 + }, + { + "epoch": 0.29, + "learning_rate": 1.784611116862514e-05, + "loss": 1.5293, + "step": 2780 + }, + { + "epoch": 0.29, + "learning_rate": 1.7843841331141177e-05, + "loss": 1.5802, + "step": 2781 + }, + { + "epoch": 0.29, + "learning_rate": 1.7841570442784024e-05, + "loss": 1.4486, + "step": 2782 + }, + { + "epoch": 0.29, + "learning_rate": 1.7839298503857913e-05, + "loss": 1.4674, + "step": 2783 + }, + { + "epoch": 0.29, + "learning_rate": 1.7837025514667224e-05, + "loss": 1.4662, + "step": 2784 + }, + { + "epoch": 0.29, + "learning_rate": 1.7834751475516484e-05, + "loss": 1.3555, + "step": 2785 + }, + { + "epoch": 0.29, + "learning_rate": 1.783247638671035e-05, + "loss": 1.4307, + "step": 2786 + }, + { + "epoch": 0.29, + "eval_loss": 1.500258445739746, + "eval_runtime": 77.406, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 2786 + }, + { + "epoch": 0.29, + "learning_rate": 1.7830200248553633e-05, + "loss": 1.4596, + "step": 2787 + }, + { + "epoch": 0.29, + "learning_rate": 1.7827923061351273e-05, + "loss": 1.6118, + "step": 2788 + }, + { + "epoch": 0.29, + "learning_rate": 1.7825644825408353e-05, + "loss": 1.4782, + "step": 2789 + }, + { + "epoch": 0.29, + "learning_rate": 1.78233655410301e-05, + "loss": 1.4681, + "step": 2790 + }, + { + "epoch": 0.29, + "learning_rate": 1.782108520852188e-05, + "loss": 1.6281, + "step": 2791 + }, + { + "epoch": 0.29, + "learning_rate": 1.78188038281892e-05, + "loss": 1.4446, + "step": 2792 + }, + { + "epoch": 0.29, + "learning_rate": 1.7816521400337704e-05, + "loss": 1.479, + "step": 2793 + }, + { + "epoch": 0.29, + "learning_rate": 1.7814237925273178e-05, + "loss": 1.5457, + "step": 2794 + }, + { + "epoch": 0.29, + "learning_rate": 1.7811953403301547e-05, + "loss": 1.3928, + "step": 2795 + }, + { + "epoch": 0.29, + "learning_rate": 1.780966783472889e-05, + "loss": 1.4321, + "step": 2796 + }, + { + "epoch": 0.29, + "learning_rate": 1.78073812198614e-05, + "loss": 1.5734, + "step": 2797 + }, + { + "epoch": 0.29, + "learning_rate": 1.7805093559005432e-05, + "loss": 1.4356, + "step": 2798 + }, + { + "epoch": 0.29, + "learning_rate": 1.7802804852467473e-05, + "loss": 1.4656, + "step": 2799 + }, + { + "epoch": 0.29, + "learning_rate": 1.780051510055415e-05, + "loss": 1.4052, + "step": 2800 + }, + { + "epoch": 0.29, + "learning_rate": 1.7798224303572228e-05, + "loss": 1.4758, + "step": 2801 + }, + { + "epoch": 0.29, + "learning_rate": 1.7795932461828622e-05, + "loss": 1.4326, + "step": 2802 + }, + { + "epoch": 0.29, + "learning_rate": 1.7793639575630376e-05, + "loss": 1.3409, + "step": 2803 + }, + { + "epoch": 0.29, + "learning_rate": 1.7791345645284678e-05, + "loss": 1.4175, + "step": 2804 + }, + { + "epoch": 0.29, + "learning_rate": 1.7789050671098853e-05, + "loss": 1.383, + "step": 2805 + }, + { + "epoch": 0.29, + "learning_rate": 1.7786754653380373e-05, + "loss": 1.5162, + "step": 2806 + }, + { + "epoch": 0.29, + "learning_rate": 1.7784457592436847e-05, + "loss": 1.4899, + "step": 2807 + }, + { + "epoch": 0.29, + "learning_rate": 1.7782159488576016e-05, + "loss": 1.4874, + "step": 2808 + }, + { + "epoch": 0.29, + "learning_rate": 1.777986034210577e-05, + "loss": 1.4363, + "step": 2809 + }, + { + "epoch": 0.29, + "learning_rate": 1.7777560153334134e-05, + "loss": 1.4223, + "step": 2810 + }, + { + "epoch": 0.29, + "learning_rate": 1.7775258922569273e-05, + "loss": 1.4792, + "step": 2811 + }, + { + "epoch": 0.29, + "learning_rate": 1.77729566501195e-05, + "loss": 1.4475, + "step": 2812 + }, + { + "epoch": 0.29, + "learning_rate": 1.7770653336293253e-05, + "loss": 1.5157, + "step": 2813 + }, + { + "epoch": 0.3, + "learning_rate": 1.776834898139912e-05, + "loss": 1.389, + "step": 2814 + }, + { + "epoch": 0.3, + "learning_rate": 1.7766043585745824e-05, + "loss": 1.4358, + "step": 2815 + }, + { + "epoch": 0.3, + "learning_rate": 1.776373714964223e-05, + "loss": 1.4297, + "step": 2816 + }, + { + "epoch": 0.3, + "learning_rate": 1.7761429673397344e-05, + "loss": 1.4102, + "step": 2817 + }, + { + "epoch": 0.3, + "learning_rate": 1.77591211573203e-05, + "loss": 1.4572, + "step": 2818 + }, + { + "epoch": 0.3, + "learning_rate": 1.775681160172039e-05, + "loss": 1.448, + "step": 2819 + }, + { + "epoch": 0.3, + "learning_rate": 1.7754501006907025e-05, + "loss": 1.4426, + "step": 2820 + }, + { + "epoch": 0.3, + "learning_rate": 1.7752189373189773e-05, + "loss": 1.4566, + "step": 2821 + }, + { + "epoch": 0.3, + "learning_rate": 1.7749876700878332e-05, + "loss": 1.4267, + "step": 2822 + }, + { + "epoch": 0.3, + "learning_rate": 1.7747562990282538e-05, + "loss": 1.3951, + "step": 2823 + }, + { + "epoch": 0.3, + "learning_rate": 1.7745248241712373e-05, + "loss": 1.4668, + "step": 2824 + }, + { + "epoch": 0.3, + "learning_rate": 1.774293245547795e-05, + "loss": 1.4924, + "step": 2825 + }, + { + "epoch": 0.3, + "learning_rate": 1.7740615631889525e-05, + "loss": 1.5258, + "step": 2826 + }, + { + "epoch": 0.3, + "learning_rate": 1.7738297771257496e-05, + "loss": 1.4323, + "step": 2827 + }, + { + "epoch": 0.3, + "learning_rate": 1.7735978873892393e-05, + "loss": 1.439, + "step": 2828 + }, + { + "epoch": 0.3, + "learning_rate": 1.773365894010489e-05, + "loss": 1.5658, + "step": 2829 + }, + { + "epoch": 0.3, + "learning_rate": 1.77313379702058e-05, + "loss": 1.4607, + "step": 2830 + }, + { + "epoch": 0.3, + "learning_rate": 1.7729015964506073e-05, + "loss": 1.5544, + "step": 2831 + }, + { + "epoch": 0.3, + "learning_rate": 1.7726692923316798e-05, + "loss": 1.4232, + "step": 2832 + }, + { + "epoch": 0.3, + "learning_rate": 1.77243688469492e-05, + "loss": 1.415, + "step": 2833 + }, + { + "epoch": 0.3, + "learning_rate": 1.772204373571465e-05, + "loss": 1.4658, + "step": 2834 + }, + { + "epoch": 0.3, + "learning_rate": 1.7719717589924647e-05, + "loss": 1.4678, + "step": 2835 + }, + { + "epoch": 0.3, + "learning_rate": 1.771739040989084e-05, + "loss": 1.3021, + "step": 2836 + }, + { + "epoch": 0.3, + "learning_rate": 1.771506219592501e-05, + "loss": 1.4045, + "step": 2837 + }, + { + "epoch": 0.3, + "learning_rate": 1.7712732948339085e-05, + "loss": 1.4593, + "step": 2838 + }, + { + "epoch": 0.3, + "learning_rate": 1.7710402667445108e-05, + "loss": 1.4175, + "step": 2839 + }, + { + "epoch": 0.3, + "learning_rate": 1.770807135355529e-05, + "loss": 1.3939, + "step": 2840 + }, + { + "epoch": 0.3, + "learning_rate": 1.7705739006981963e-05, + "loss": 1.6089, + "step": 2841 + }, + { + "epoch": 0.3, + "learning_rate": 1.77034056280376e-05, + "loss": 1.3952, + "step": 2842 + }, + { + "epoch": 0.3, + "learning_rate": 1.7701071217034818e-05, + "loss": 1.5086, + "step": 2843 + }, + { + "epoch": 0.3, + "learning_rate": 1.7698735774286362e-05, + "loss": 1.4706, + "step": 2844 + }, + { + "epoch": 0.3, + "learning_rate": 1.7696399300105128e-05, + "loss": 1.4286, + "step": 2845 + }, + { + "epoch": 0.3, + "learning_rate": 1.7694061794804137e-05, + "loss": 1.4418, + "step": 2846 + }, + { + "epoch": 0.3, + "learning_rate": 1.7691723258696562e-05, + "loss": 1.516, + "step": 2847 + }, + { + "epoch": 0.3, + "learning_rate": 1.76893836920957e-05, + "loss": 1.4354, + "step": 2848 + }, + { + "epoch": 0.3, + "learning_rate": 1.7687043095314998e-05, + "loss": 1.7503, + "step": 2849 + }, + { + "epoch": 0.3, + "learning_rate": 1.7684701468668032e-05, + "loss": 1.5985, + "step": 2850 + }, + { + "epoch": 0.3, + "learning_rate": 1.768235881246852e-05, + "loss": 1.442, + "step": 2851 + }, + { + "epoch": 0.3, + "learning_rate": 1.7680015127030322e-05, + "loss": 1.4924, + "step": 2852 + }, + { + "epoch": 0.3, + "learning_rate": 1.7677670412667425e-05, + "loss": 1.4461, + "step": 2853 + }, + { + "epoch": 0.3, + "learning_rate": 1.7675324669693968e-05, + "loss": 1.3823, + "step": 2854 + }, + { + "epoch": 0.3, + "learning_rate": 1.767297789842421e-05, + "loss": 1.452, + "step": 2855 + }, + { + "epoch": 0.3, + "learning_rate": 1.767063009917257e-05, + "loss": 1.46, + "step": 2856 + }, + { + "epoch": 0.3, + "learning_rate": 1.7668281272253587e-05, + "loss": 1.4129, + "step": 2857 + }, + { + "epoch": 0.3, + "learning_rate": 1.766593141798194e-05, + "loss": 1.4057, + "step": 2858 + }, + { + "epoch": 0.3, + "learning_rate": 1.7663580536672456e-05, + "loss": 1.5162, + "step": 2859 + }, + { + "epoch": 0.3, + "learning_rate": 1.7661228628640087e-05, + "loss": 1.5177, + "step": 2860 + }, + { + "epoch": 0.3, + "learning_rate": 1.7658875694199933e-05, + "loss": 1.4548, + "step": 2861 + }, + { + "epoch": 0.3, + "learning_rate": 1.7656521733667223e-05, + "loss": 1.4511, + "step": 2862 + }, + { + "epoch": 0.3, + "learning_rate": 1.765416674735733e-05, + "loss": 1.4778, + "step": 2863 + }, + { + "epoch": 0.3, + "learning_rate": 1.765181073558576e-05, + "loss": 1.3935, + "step": 2864 + }, + { + "epoch": 0.3, + "learning_rate": 1.7649453698668156e-05, + "loss": 1.4659, + "step": 2865 + }, + { + "epoch": 0.3, + "learning_rate": 1.7647095636920305e-05, + "loss": 1.7042, + "step": 2866 + }, + { + "epoch": 0.3, + "learning_rate": 1.7644736550658124e-05, + "loss": 1.7957, + "step": 2867 + }, + { + "epoch": 0.3, + "learning_rate": 1.764237644019767e-05, + "loss": 1.5139, + "step": 2868 + }, + { + "epoch": 0.3, + "learning_rate": 1.764001530585514e-05, + "loss": 1.4117, + "step": 2869 + }, + { + "epoch": 0.3, + "learning_rate": 1.7637653147946858e-05, + "loss": 1.4837, + "step": 2870 + }, + { + "epoch": 0.3, + "learning_rate": 1.7635289966789298e-05, + "loss": 1.4379, + "step": 2871 + }, + { + "epoch": 0.3, + "learning_rate": 1.7632925762699068e-05, + "loss": 1.4491, + "step": 2872 + }, + { + "epoch": 0.3, + "learning_rate": 1.7630560535992905e-05, + "loss": 1.4006, + "step": 2873 + }, + { + "epoch": 0.3, + "learning_rate": 1.7628194286987694e-05, + "loss": 1.5484, + "step": 2874 + }, + { + "epoch": 0.3, + "learning_rate": 1.7625827016000446e-05, + "loss": 1.4926, + "step": 2875 + }, + { + "epoch": 0.3, + "learning_rate": 1.762345872334832e-05, + "loss": 1.3909, + "step": 2876 + }, + { + "epoch": 0.3, + "learning_rate": 1.76210894093486e-05, + "loss": 1.405, + "step": 2877 + }, + { + "epoch": 0.3, + "learning_rate": 1.7618719074318718e-05, + "loss": 1.4736, + "step": 2878 + }, + { + "epoch": 0.3, + "learning_rate": 1.7616347718576238e-05, + "loss": 1.4445, + "step": 2879 + }, + { + "epoch": 0.3, + "learning_rate": 1.761397534243886e-05, + "loss": 1.4878, + "step": 2880 + }, + { + "epoch": 0.3, + "learning_rate": 1.7611601946224417e-05, + "loss": 1.4414, + "step": 2881 + }, + { + "epoch": 0.3, + "learning_rate": 1.760922753025089e-05, + "loss": 1.5657, + "step": 2882 + }, + { + "epoch": 0.3, + "learning_rate": 1.7606852094836385e-05, + "loss": 1.5008, + "step": 2883 + }, + { + "epoch": 0.3, + "learning_rate": 1.7604475640299153e-05, + "loss": 1.4922, + "step": 2884 + }, + { + "epoch": 0.3, + "learning_rate": 1.7602098166957577e-05, + "loss": 1.7451, + "step": 2885 + }, + { + "epoch": 0.3, + "learning_rate": 1.759971967513017e-05, + "loss": 1.7077, + "step": 2886 + }, + { + "epoch": 0.3, + "learning_rate": 1.75973401651356e-05, + "loss": 1.3986, + "step": 2887 + }, + { + "epoch": 0.3, + "learning_rate": 1.7594959637292656e-05, + "loss": 1.3966, + "step": 2888 + }, + { + "epoch": 0.3, + "learning_rate": 1.7592578091920264e-05, + "loss": 1.4086, + "step": 2889 + }, + { + "epoch": 0.3, + "learning_rate": 1.7590195529337495e-05, + "loss": 1.4481, + "step": 2890 + }, + { + "epoch": 0.3, + "learning_rate": 1.7587811949863548e-05, + "loss": 1.3974, + "step": 2891 + }, + { + "epoch": 0.3, + "learning_rate": 1.7585427353817758e-05, + "loss": 1.5013, + "step": 2892 + }, + { + "epoch": 0.3, + "learning_rate": 1.7583041741519608e-05, + "loss": 1.5454, + "step": 2893 + }, + { + "epoch": 0.3, + "learning_rate": 1.7580655113288708e-05, + "loss": 1.5033, + "step": 2894 + }, + { + "epoch": 0.3, + "learning_rate": 1.7578267469444793e-05, + "loss": 1.4332, + "step": 2895 + }, + { + "epoch": 0.3, + "learning_rate": 1.757587881030776e-05, + "loss": 1.4667, + "step": 2896 + }, + { + "epoch": 0.3, + "learning_rate": 1.7573489136197623e-05, + "loss": 1.4314, + "step": 2897 + }, + { + "epoch": 0.3, + "learning_rate": 1.7571098447434532e-05, + "loss": 1.4514, + "step": 2898 + }, + { + "epoch": 0.3, + "learning_rate": 1.7568706744338784e-05, + "loss": 1.4872, + "step": 2899 + }, + { + "epoch": 0.3, + "learning_rate": 1.7566314027230808e-05, + "loss": 1.4841, + "step": 2900 + }, + { + "epoch": 0.3, + "learning_rate": 1.7563920296431158e-05, + "loss": 1.3964, + "step": 2901 + }, + { + "epoch": 0.3, + "learning_rate": 1.7561525552260538e-05, + "loss": 1.4932, + "step": 2902 + }, + { + "epoch": 0.3, + "learning_rate": 1.755912979503978e-05, + "loss": 1.4153, + "step": 2903 + }, + { + "epoch": 0.3, + "learning_rate": 1.755673302508986e-05, + "loss": 1.4939, + "step": 2904 + }, + { + "epoch": 0.3, + "learning_rate": 1.755433524273187e-05, + "loss": 1.4437, + "step": 2905 + }, + { + "epoch": 0.3, + "learning_rate": 1.7551936448287067e-05, + "loss": 1.486, + "step": 2906 + }, + { + "epoch": 0.3, + "learning_rate": 1.754953664207682e-05, + "loss": 1.4362, + "step": 2907 + }, + { + "epoch": 0.3, + "learning_rate": 1.7547135824422635e-05, + "loss": 1.4954, + "step": 2908 + }, + { + "epoch": 0.31, + "learning_rate": 1.7544733995646174e-05, + "loss": 1.4552, + "step": 2909 + }, + { + "epoch": 0.31, + "learning_rate": 1.7542331156069213e-05, + "loss": 1.4654, + "step": 2910 + }, + { + "epoch": 0.31, + "learning_rate": 1.753992730601367e-05, + "loss": 1.4531, + "step": 2911 + }, + { + "epoch": 0.31, + "learning_rate": 1.75375224458016e-05, + "loss": 1.4949, + "step": 2912 + }, + { + "epoch": 0.31, + "learning_rate": 1.753511657575519e-05, + "loss": 1.3998, + "step": 2913 + }, + { + "epoch": 0.31, + "learning_rate": 1.753270969619677e-05, + "loss": 1.3904, + "step": 2914 + }, + { + "epoch": 0.31, + "learning_rate": 1.7530301807448794e-05, + "loss": 1.481, + "step": 2915 + }, + { + "epoch": 0.31, + "learning_rate": 1.7527892909833864e-05, + "loss": 1.4301, + "step": 2916 + }, + { + "epoch": 0.31, + "learning_rate": 1.7525483003674707e-05, + "loss": 1.4377, + "step": 2917 + }, + { + "epoch": 0.31, + "learning_rate": 1.7523072089294188e-05, + "loss": 1.5077, + "step": 2918 + }, + { + "epoch": 0.31, + "learning_rate": 1.752066016701531e-05, + "loss": 1.3802, + "step": 2919 + }, + { + "epoch": 0.31, + "learning_rate": 1.7518247237161205e-05, + "loss": 1.3991, + "step": 2920 + }, + { + "epoch": 0.31, + "learning_rate": 1.7515833300055146e-05, + "loss": 1.4283, + "step": 2921 + }, + { + "epoch": 0.31, + "learning_rate": 1.7513418356020535e-05, + "loss": 1.3688, + "step": 2922 + }, + { + "epoch": 0.31, + "learning_rate": 1.751100240538092e-05, + "loss": 1.4336, + "step": 2923 + }, + { + "epoch": 0.31, + "learning_rate": 1.7508585448459967e-05, + "loss": 1.4302, + "step": 2924 + }, + { + "epoch": 0.31, + "learning_rate": 1.7506167485581493e-05, + "loss": 1.4293, + "step": 2925 + }, + { + "epoch": 0.31, + "learning_rate": 1.750374851706944e-05, + "loss": 1.4262, + "step": 2926 + }, + { + "epoch": 0.31, + "learning_rate": 1.7501328543247892e-05, + "loss": 1.4128, + "step": 2927 + }, + { + "epoch": 0.31, + "learning_rate": 1.7498907564441054e-05, + "loss": 1.4258, + "step": 2928 + }, + { + "epoch": 0.31, + "learning_rate": 1.749648558097328e-05, + "loss": 1.4904, + "step": 2929 + }, + { + "epoch": 0.31, + "learning_rate": 1.749406259316906e-05, + "loss": 1.4628, + "step": 2930 + }, + { + "epoch": 0.31, + "learning_rate": 1.7491638601353004e-05, + "loss": 1.4908, + "step": 2931 + }, + { + "epoch": 0.31, + "learning_rate": 1.7489213605849867e-05, + "loss": 1.4563, + "step": 2932 + }, + { + "epoch": 0.31, + "learning_rate": 1.7486787606984533e-05, + "loss": 1.5006, + "step": 2933 + }, + { + "epoch": 0.31, + "learning_rate": 1.748436060508203e-05, + "loss": 1.424, + "step": 2934 + }, + { + "epoch": 0.31, + "learning_rate": 1.7481932600467508e-05, + "loss": 1.4136, + "step": 2935 + }, + { + "epoch": 0.31, + "learning_rate": 1.747950359346626e-05, + "loss": 1.3835, + "step": 2936 + }, + { + "epoch": 0.31, + "learning_rate": 1.747707358440371e-05, + "loss": 1.5284, + "step": 2937 + }, + { + "epoch": 0.31, + "learning_rate": 1.7474642573605418e-05, + "loss": 1.4592, + "step": 2938 + }, + { + "epoch": 0.31, + "learning_rate": 1.7472210561397075e-05, + "loss": 1.5483, + "step": 2939 + }, + { + "epoch": 0.31, + "learning_rate": 1.746977754810451e-05, + "loss": 1.521, + "step": 2940 + }, + { + "epoch": 0.31, + "learning_rate": 1.7467343534053683e-05, + "loss": 1.4276, + "step": 2941 + }, + { + "epoch": 0.31, + "learning_rate": 1.746490851957069e-05, + "loss": 1.4302, + "step": 2942 + }, + { + "epoch": 0.31, + "learning_rate": 1.746247250498176e-05, + "loss": 1.4439, + "step": 2943 + }, + { + "epoch": 0.31, + "learning_rate": 1.7460035490613255e-05, + "loss": 1.4991, + "step": 2944 + }, + { + "epoch": 0.31, + "learning_rate": 1.7457597476791674e-05, + "loss": 1.4188, + "step": 2945 + }, + { + "epoch": 0.31, + "learning_rate": 1.7455158463843648e-05, + "loss": 1.4685, + "step": 2946 + }, + { + "epoch": 0.31, + "learning_rate": 1.745271845209594e-05, + "loss": 1.3811, + "step": 2947 + }, + { + "epoch": 0.31, + "learning_rate": 1.7450277441875454e-05, + "loss": 1.4869, + "step": 2948 + }, + { + "epoch": 0.31, + "learning_rate": 1.7447835433509218e-05, + "loss": 1.5001, + "step": 2949 + }, + { + "epoch": 0.31, + "learning_rate": 1.74453924273244e-05, + "loss": 1.4757, + "step": 2950 + }, + { + "epoch": 0.31, + "learning_rate": 1.74429484236483e-05, + "loss": 1.5072, + "step": 2951 + }, + { + "epoch": 0.31, + "learning_rate": 1.744050342280835e-05, + "loss": 1.4242, + "step": 2952 + }, + { + "epoch": 0.31, + "learning_rate": 1.743805742513212e-05, + "loss": 1.4462, + "step": 2953 + }, + { + "epoch": 0.31, + "learning_rate": 1.743561043094731e-05, + "loss": 1.6815, + "step": 2954 + }, + { + "epoch": 0.31, + "learning_rate": 1.7433162440581755e-05, + "loss": 1.427, + "step": 2955 + }, + { + "epoch": 0.31, + "learning_rate": 1.7430713454363423e-05, + "loss": 1.2933, + "step": 2956 + }, + { + "epoch": 0.31, + "learning_rate": 1.742826347262041e-05, + "loss": 1.4247, + "step": 2957 + }, + { + "epoch": 0.31, + "learning_rate": 1.7425812495680955e-05, + "loss": 1.399, + "step": 2958 + }, + { + "epoch": 0.31, + "learning_rate": 1.742336052387343e-05, + "loss": 1.4818, + "step": 2959 + }, + { + "epoch": 0.31, + "learning_rate": 1.742090755752633e-05, + "loss": 1.3839, + "step": 2960 + }, + { + "epoch": 0.31, + "learning_rate": 1.741845359696829e-05, + "loss": 1.4669, + "step": 2961 + }, + { + "epoch": 0.31, + "learning_rate": 1.741599864252808e-05, + "loss": 1.468, + "step": 2962 + }, + { + "epoch": 0.31, + "learning_rate": 1.74135426945346e-05, + "loss": 1.4135, + "step": 2963 + }, + { + "epoch": 0.31, + "learning_rate": 1.7411085753316882e-05, + "loss": 1.5899, + "step": 2964 + }, + { + "epoch": 0.31, + "learning_rate": 1.74086278192041e-05, + "loss": 1.6115, + "step": 2965 + }, + { + "epoch": 0.31, + "learning_rate": 1.740616889252554e-05, + "loss": 1.3988, + "step": 2966 + }, + { + "epoch": 0.31, + "learning_rate": 1.740370897361065e-05, + "loss": 1.5001, + "step": 2967 + }, + { + "epoch": 0.31, + "learning_rate": 1.740124806278899e-05, + "loss": 1.459, + "step": 2968 + }, + { + "epoch": 0.31, + "learning_rate": 1.7398786160390258e-05, + "loss": 1.4489, + "step": 2969 + }, + { + "epoch": 0.31, + "learning_rate": 1.7396323266744283e-05, + "loss": 1.4397, + "step": 2970 + }, + { + "epoch": 0.31, + "learning_rate": 1.7393859382181033e-05, + "loss": 1.4687, + "step": 2971 + }, + { + "epoch": 0.31, + "learning_rate": 1.7391394507030606e-05, + "loss": 1.4495, + "step": 2972 + }, + { + "epoch": 0.31, + "learning_rate": 1.738892864162323e-05, + "loss": 1.4745, + "step": 2973 + }, + { + "epoch": 0.31, + "learning_rate": 1.7386461786289274e-05, + "loss": 1.3943, + "step": 2974 + }, + { + "epoch": 0.31, + "learning_rate": 1.738399394135922e-05, + "loss": 1.4595, + "step": 2975 + }, + { + "epoch": 0.31, + "learning_rate": 1.738152510716371e-05, + "loss": 1.4023, + "step": 2976 + }, + { + "epoch": 0.31, + "learning_rate": 1.7379055284033493e-05, + "loss": 1.3938, + "step": 2977 + }, + { + "epoch": 0.31, + "learning_rate": 1.7376584472299468e-05, + "loss": 1.4576, + "step": 2978 + }, + { + "epoch": 0.31, + "learning_rate": 1.737411267229266e-05, + "loss": 1.424, + "step": 2979 + }, + { + "epoch": 0.31, + "learning_rate": 1.7371639884344225e-05, + "loss": 1.4224, + "step": 2980 + }, + { + "epoch": 0.31, + "learning_rate": 1.736916610878545e-05, + "loss": 1.4228, + "step": 2981 + }, + { + "epoch": 0.31, + "learning_rate": 1.7366691345947768e-05, + "loss": 1.5021, + "step": 2982 + }, + { + "epoch": 0.31, + "learning_rate": 1.736421559616272e-05, + "loss": 1.3589, + "step": 2983 + }, + { + "epoch": 0.31, + "learning_rate": 1.7361738859762007e-05, + "loss": 1.4748, + "step": 2984 + }, + { + "epoch": 0.31, + "learning_rate": 1.735926113707743e-05, + "loss": 1.3974, + "step": 2985 + }, + { + "epoch": 0.31, + "eval_loss": 1.4849082231521606, + "eval_runtime": 77.3271, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 2985 + }, + { + "epoch": 0.31, + "learning_rate": 1.735678242844096e-05, + "loss": 1.392, + "step": 2986 + }, + { + "epoch": 0.31, + "learning_rate": 1.735430273418467e-05, + "loss": 1.4277, + "step": 2987 + }, + { + "epoch": 0.31, + "learning_rate": 1.735182205464077e-05, + "loss": 1.4216, + "step": 2988 + }, + { + "epoch": 0.31, + "learning_rate": 1.7349340390141617e-05, + "loss": 1.4546, + "step": 2989 + }, + { + "epoch": 0.31, + "learning_rate": 1.734685774101969e-05, + "loss": 1.4264, + "step": 2990 + }, + { + "epoch": 0.31, + "learning_rate": 1.7344374107607593e-05, + "loss": 1.4307, + "step": 2991 + }, + { + "epoch": 0.31, + "learning_rate": 1.7341889490238076e-05, + "loss": 1.4266, + "step": 2992 + }, + { + "epoch": 0.31, + "learning_rate": 1.7339403889244008e-05, + "loss": 1.4486, + "step": 2993 + }, + { + "epoch": 0.31, + "learning_rate": 1.7336917304958403e-05, + "loss": 1.4345, + "step": 2994 + }, + { + "epoch": 0.31, + "learning_rate": 1.7334429737714395e-05, + "loss": 1.476, + "step": 2995 + }, + { + "epoch": 0.31, + "learning_rate": 1.7331941187845248e-05, + "loss": 1.5148, + "step": 2996 + }, + { + "epoch": 0.31, + "learning_rate": 1.7329451655684372e-05, + "loss": 1.4026, + "step": 2997 + }, + { + "epoch": 0.31, + "learning_rate": 1.7326961141565303e-05, + "loss": 1.3935, + "step": 2998 + }, + { + "epoch": 0.31, + "learning_rate": 1.73244696458217e-05, + "loss": 1.4483, + "step": 2999 + }, + { + "epoch": 0.31, + "learning_rate": 1.7321977168787356e-05, + "loss": 1.5197, + "step": 3000 + }, + { + "epoch": 0.31, + "learning_rate": 1.7319483710796208e-05, + "loss": 1.4648, + "step": 3001 + }, + { + "epoch": 0.31, + "learning_rate": 1.7316989272182308e-05, + "loss": 1.4171, + "step": 3002 + }, + { + "epoch": 0.31, + "learning_rate": 1.731449385327985e-05, + "loss": 1.4541, + "step": 3003 + }, + { + "epoch": 0.32, + "learning_rate": 1.731199745442316e-05, + "loss": 1.4605, + "step": 3004 + }, + { + "epoch": 0.32, + "learning_rate": 1.7309500075946683e-05, + "loss": 1.5122, + "step": 3005 + }, + { + "epoch": 0.32, + "learning_rate": 1.7307001718185007e-05, + "loss": 1.5243, + "step": 3006 + }, + { + "epoch": 0.32, + "learning_rate": 1.7304502381472844e-05, + "loss": 1.4997, + "step": 3007 + }, + { + "epoch": 0.32, + "learning_rate": 1.730200206614505e-05, + "loss": 1.4891, + "step": 3008 + }, + { + "epoch": 0.32, + "learning_rate": 1.72995007725366e-05, + "loss": 1.4376, + "step": 3009 + }, + { + "epoch": 0.32, + "learning_rate": 1.7296998500982595e-05, + "loss": 1.4403, + "step": 3010 + }, + { + "epoch": 0.32, + "learning_rate": 1.7294495251818285e-05, + "loss": 1.5153, + "step": 3011 + }, + { + "epoch": 0.32, + "learning_rate": 1.729199102537904e-05, + "loss": 1.4996, + "step": 3012 + }, + { + "epoch": 0.32, + "learning_rate": 1.7289485822000356e-05, + "loss": 1.5302, + "step": 3013 + }, + { + "epoch": 0.32, + "learning_rate": 1.7286979642017867e-05, + "loss": 1.5641, + "step": 3014 + }, + { + "epoch": 0.32, + "learning_rate": 1.728447248576734e-05, + "loss": 1.438, + "step": 3015 + }, + { + "epoch": 0.32, + "learning_rate": 1.7281964353584674e-05, + "loss": 1.4796, + "step": 3016 + }, + { + "epoch": 0.32, + "learning_rate": 1.727945524580588e-05, + "loss": 1.4413, + "step": 3017 + }, + { + "epoch": 0.32, + "learning_rate": 1.727694516276713e-05, + "loss": 1.3966, + "step": 3018 + }, + { + "epoch": 0.32, + "learning_rate": 1.72744341048047e-05, + "loss": 1.5267, + "step": 3019 + }, + { + "epoch": 0.32, + "learning_rate": 1.727192207225501e-05, + "loss": 1.4284, + "step": 3020 + }, + { + "epoch": 0.32, + "learning_rate": 1.726940906545461e-05, + "loss": 1.5137, + "step": 3021 + }, + { + "epoch": 0.32, + "learning_rate": 1.7266895084740173e-05, + "loss": 1.3966, + "step": 3022 + }, + { + "epoch": 0.32, + "learning_rate": 1.7264380130448514e-05, + "loss": 1.4156, + "step": 3023 + }, + { + "epoch": 0.32, + "learning_rate": 1.726186420291657e-05, + "loss": 1.4644, + "step": 3024 + }, + { + "epoch": 0.32, + "learning_rate": 1.725934730248141e-05, + "loss": 1.4768, + "step": 3025 + }, + { + "epoch": 0.32, + "learning_rate": 1.7256829429480233e-05, + "loss": 1.4428, + "step": 3026 + }, + { + "epoch": 0.32, + "learning_rate": 1.7254310584250373e-05, + "loss": 1.4495, + "step": 3027 + }, + { + "epoch": 0.32, + "learning_rate": 1.725179076712929e-05, + "loss": 1.3867, + "step": 3028 + }, + { + "epoch": 0.32, + "learning_rate": 1.7249269978454567e-05, + "loss": 1.5011, + "step": 3029 + }, + { + "epoch": 0.32, + "learning_rate": 1.7246748218563937e-05, + "loss": 1.3916, + "step": 3030 + }, + { + "epoch": 0.32, + "learning_rate": 1.7244225487795238e-05, + "loss": 1.4984, + "step": 3031 + }, + { + "epoch": 0.32, + "learning_rate": 1.7241701786486464e-05, + "loss": 1.5776, + "step": 3032 + }, + { + "epoch": 0.32, + "learning_rate": 1.7239177114975717e-05, + "loss": 1.5018, + "step": 3033 + }, + { + "epoch": 0.32, + "learning_rate": 1.7236651473601244e-05, + "loss": 1.5042, + "step": 3034 + }, + { + "epoch": 0.32, + "learning_rate": 1.723412486270141e-05, + "loss": 1.4636, + "step": 3035 + }, + { + "epoch": 0.32, + "learning_rate": 1.723159728261472e-05, + "loss": 1.5612, + "step": 3036 + }, + { + "epoch": 0.32, + "learning_rate": 1.7229068733679803e-05, + "loss": 1.4399, + "step": 3037 + }, + { + "epoch": 0.32, + "learning_rate": 1.7226539216235424e-05, + "loss": 1.5635, + "step": 3038 + }, + { + "epoch": 0.32, + "learning_rate": 1.7224008730620468e-05, + "loss": 1.4329, + "step": 3039 + }, + { + "epoch": 0.32, + "learning_rate": 1.7221477277173956e-05, + "loss": 1.4886, + "step": 3040 + }, + { + "epoch": 0.32, + "learning_rate": 1.721894485623504e-05, + "loss": 1.4741, + "step": 3041 + }, + { + "epoch": 0.32, + "learning_rate": 1.7216411468143e-05, + "loss": 1.4678, + "step": 3042 + }, + { + "epoch": 0.32, + "learning_rate": 1.721387711323724e-05, + "loss": 1.4758, + "step": 3043 + }, + { + "epoch": 0.32, + "learning_rate": 1.72113417918573e-05, + "loss": 1.441, + "step": 3044 + }, + { + "epoch": 0.32, + "learning_rate": 1.7208805504342855e-05, + "loss": 1.4328, + "step": 3045 + }, + { + "epoch": 0.32, + "learning_rate": 1.720626825103369e-05, + "loss": 1.4254, + "step": 3046 + }, + { + "epoch": 0.32, + "learning_rate": 1.7203730032269744e-05, + "loss": 1.4462, + "step": 3047 + }, + { + "epoch": 0.32, + "learning_rate": 1.7201190848391066e-05, + "loss": 1.4826, + "step": 3048 + }, + { + "epoch": 0.32, + "learning_rate": 1.719865069973784e-05, + "loss": 1.4215, + "step": 3049 + }, + { + "epoch": 0.32, + "learning_rate": 1.7196109586650385e-05, + "loss": 1.4291, + "step": 3050 + }, + { + "epoch": 0.32, + "learning_rate": 1.7193567509469146e-05, + "loss": 1.5005, + "step": 3051 + }, + { + "epoch": 0.32, + "learning_rate": 1.719102446853469e-05, + "loss": 1.4216, + "step": 3052 + }, + { + "epoch": 0.32, + "learning_rate": 1.7188480464187725e-05, + "loss": 1.4349, + "step": 3053 + }, + { + "epoch": 0.32, + "learning_rate": 1.718593549676908e-05, + "loss": 1.4784, + "step": 3054 + }, + { + "epoch": 0.32, + "learning_rate": 1.7183389566619714e-05, + "loss": 1.4325, + "step": 3055 + }, + { + "epoch": 0.32, + "learning_rate": 1.7180842674080717e-05, + "loss": 1.5387, + "step": 3056 + }, + { + "epoch": 0.32, + "learning_rate": 1.717829481949331e-05, + "loss": 1.655, + "step": 3057 + }, + { + "epoch": 0.32, + "learning_rate": 1.717574600319883e-05, + "loss": 1.4623, + "step": 3058 + }, + { + "epoch": 0.32, + "learning_rate": 1.7173196225538768e-05, + "loss": 1.4646, + "step": 3059 + }, + { + "epoch": 0.32, + "learning_rate": 1.717064548685472e-05, + "loss": 1.4641, + "step": 3060 + }, + { + "epoch": 0.32, + "learning_rate": 1.7168093787488418e-05, + "loss": 1.4033, + "step": 3061 + }, + { + "epoch": 0.32, + "learning_rate": 1.7165541127781726e-05, + "loss": 1.4085, + "step": 3062 + }, + { + "epoch": 0.32, + "learning_rate": 1.716298750807664e-05, + "loss": 1.387, + "step": 3063 + }, + { + "epoch": 0.32, + "learning_rate": 1.7160432928715272e-05, + "loss": 1.4197, + "step": 3064 + }, + { + "epoch": 0.32, + "learning_rate": 1.7157877390039872e-05, + "loss": 1.4883, + "step": 3065 + }, + { + "epoch": 0.32, + "learning_rate": 1.7155320892392818e-05, + "loss": 1.4865, + "step": 3066 + }, + { + "epoch": 0.32, + "learning_rate": 1.715276343611662e-05, + "loss": 1.4532, + "step": 3067 + }, + { + "epoch": 0.32, + "learning_rate": 1.71502050215539e-05, + "loss": 1.3991, + "step": 3068 + }, + { + "epoch": 0.32, + "learning_rate": 1.7147645649047424e-05, + "loss": 1.4318, + "step": 3069 + }, + { + "epoch": 0.32, + "learning_rate": 1.714508531894009e-05, + "loss": 1.3616, + "step": 3070 + }, + { + "epoch": 0.32, + "learning_rate": 1.7142524031574904e-05, + "loss": 1.4481, + "step": 3071 + }, + { + "epoch": 0.32, + "learning_rate": 1.7139961787295022e-05, + "loss": 1.3897, + "step": 3072 + }, + { + "epoch": 0.32, + "learning_rate": 1.7137398586443716e-05, + "loss": 1.3128, + "step": 3073 + }, + { + "epoch": 0.32, + "learning_rate": 1.713483442936439e-05, + "loss": 1.4481, + "step": 3074 + }, + { + "epoch": 0.32, + "learning_rate": 1.713226931640057e-05, + "loss": 1.5374, + "step": 3075 + }, + { + "epoch": 0.32, + "learning_rate": 1.7129703247895923e-05, + "loss": 1.4247, + "step": 3076 + }, + { + "epoch": 0.32, + "learning_rate": 1.712713622419423e-05, + "loss": 1.4098, + "step": 3077 + }, + { + "epoch": 0.32, + "learning_rate": 1.7124568245639414e-05, + "loss": 1.4558, + "step": 3078 + }, + { + "epoch": 0.32, + "learning_rate": 1.7121999312575507e-05, + "loss": 1.4484, + "step": 3079 + }, + { + "epoch": 0.32, + "learning_rate": 1.711942942534669e-05, + "loss": 1.4236, + "step": 3080 + }, + { + "epoch": 0.32, + "learning_rate": 1.7116858584297253e-05, + "loss": 1.613, + "step": 3081 + }, + { + "epoch": 0.32, + "learning_rate": 1.711428678977163e-05, + "loss": 1.4503, + "step": 3082 + }, + { + "epoch": 0.32, + "learning_rate": 1.7111714042114376e-05, + "loss": 1.4072, + "step": 3083 + }, + { + "epoch": 0.32, + "learning_rate": 1.7109140341670168e-05, + "loss": 1.5999, + "step": 3084 + }, + { + "epoch": 0.32, + "learning_rate": 1.7106565688783815e-05, + "loss": 1.4129, + "step": 3085 + }, + { + "epoch": 0.32, + "learning_rate": 1.710399008380026e-05, + "loss": 1.3973, + "step": 3086 + }, + { + "epoch": 0.32, + "learning_rate": 1.710141352706456e-05, + "loss": 1.4292, + "step": 3087 + }, + { + "epoch": 0.32, + "learning_rate": 1.709883601892192e-05, + "loss": 1.4372, + "step": 3088 + }, + { + "epoch": 0.32, + "learning_rate": 1.7096257559717647e-05, + "loss": 1.4924, + "step": 3089 + }, + { + "epoch": 0.32, + "learning_rate": 1.7093678149797196e-05, + "loss": 1.4222, + "step": 3090 + }, + { + "epoch": 0.32, + "learning_rate": 1.7091097789506137e-05, + "loss": 1.4797, + "step": 3091 + }, + { + "epoch": 0.32, + "learning_rate": 1.7088516479190175e-05, + "loss": 1.4738, + "step": 3092 + }, + { + "epoch": 0.32, + "learning_rate": 1.708593421919514e-05, + "loss": 1.5371, + "step": 3093 + }, + { + "epoch": 0.32, + "learning_rate": 1.7083351009866988e-05, + "loss": 1.3802, + "step": 3094 + }, + { + "epoch": 0.32, + "learning_rate": 1.7080766851551795e-05, + "loss": 1.4292, + "step": 3095 + }, + { + "epoch": 0.32, + "learning_rate": 1.707818174459578e-05, + "loss": 1.4478, + "step": 3096 + }, + { + "epoch": 0.32, + "learning_rate": 1.7075595689345285e-05, + "loss": 1.4619, + "step": 3097 + }, + { + "epoch": 0.32, + "learning_rate": 1.7073008686146763e-05, + "loss": 1.4603, + "step": 3098 + }, + { + "epoch": 0.32, + "learning_rate": 1.7070420735346815e-05, + "loss": 1.4548, + "step": 3099 + }, + { + "epoch": 0.33, + "learning_rate": 1.7067831837292157e-05, + "loss": 1.3638, + "step": 3100 + }, + { + "epoch": 0.33, + "learning_rate": 1.7065241992329634e-05, + "loss": 1.4284, + "step": 3101 + }, + { + "epoch": 0.33, + "learning_rate": 1.7062651200806217e-05, + "loss": 1.386, + "step": 3102 + }, + { + "epoch": 0.33, + "learning_rate": 1.7060059463069013e-05, + "loss": 1.5483, + "step": 3103 + }, + { + "epoch": 0.33, + "learning_rate": 1.705746677946524e-05, + "loss": 1.4963, + "step": 3104 + }, + { + "epoch": 0.33, + "learning_rate": 1.7054873150342257e-05, + "loss": 1.4539, + "step": 3105 + }, + { + "epoch": 0.33, + "learning_rate": 1.705227857604754e-05, + "loss": 1.4361, + "step": 3106 + }, + { + "epoch": 0.33, + "learning_rate": 1.7049683056928695e-05, + "loss": 1.3735, + "step": 3107 + }, + { + "epoch": 0.33, + "learning_rate": 1.7047086593333454e-05, + "loss": 1.4324, + "step": 3108 + }, + { + "epoch": 0.33, + "learning_rate": 1.7044489185609685e-05, + "loss": 1.5037, + "step": 3109 + }, + { + "epoch": 0.33, + "learning_rate": 1.704189083410536e-05, + "loss": 1.3913, + "step": 3110 + }, + { + "epoch": 0.33, + "learning_rate": 1.7039291539168604e-05, + "loss": 1.3233, + "step": 3111 + }, + { + "epoch": 0.33, + "learning_rate": 1.703669130114765e-05, + "loss": 1.4897, + "step": 3112 + }, + { + "epoch": 0.33, + "learning_rate": 1.7034090120390862e-05, + "loss": 1.4843, + "step": 3113 + }, + { + "epoch": 0.33, + "learning_rate": 1.7031487997246735e-05, + "loss": 1.3674, + "step": 3114 + }, + { + "epoch": 0.33, + "learning_rate": 1.7028884932063883e-05, + "loss": 1.4475, + "step": 3115 + }, + { + "epoch": 0.33, + "learning_rate": 1.702628092519105e-05, + "loss": 1.4134, + "step": 3116 + }, + { + "epoch": 0.33, + "learning_rate": 1.7023675976977108e-05, + "loss": 1.4484, + "step": 3117 + }, + { + "epoch": 0.33, + "learning_rate": 1.702107008777106e-05, + "loss": 1.407, + "step": 3118 + }, + { + "epoch": 0.33, + "learning_rate": 1.7018463257922005e-05, + "loss": 1.5443, + "step": 3119 + }, + { + "epoch": 0.33, + "learning_rate": 1.701585548777922e-05, + "loss": 1.4548, + "step": 3120 + }, + { + "epoch": 0.33, + "learning_rate": 1.7013246777692063e-05, + "loss": 1.4252, + "step": 3121 + }, + { + "epoch": 0.33, + "learning_rate": 1.7010637128010037e-05, + "loss": 1.3748, + "step": 3122 + }, + { + "epoch": 0.33, + "learning_rate": 1.7008026539082767e-05, + "loss": 1.3804, + "step": 3123 + }, + { + "epoch": 0.33, + "learning_rate": 1.7005415011260008e-05, + "loss": 1.4203, + "step": 3124 + }, + { + "epoch": 0.33, + "learning_rate": 1.7002802544891634e-05, + "loss": 1.4195, + "step": 3125 + }, + { + "epoch": 0.33, + "learning_rate": 1.700018914032765e-05, + "loss": 1.4188, + "step": 3126 + }, + { + "epoch": 0.33, + "learning_rate": 1.699757479791819e-05, + "loss": 1.3884, + "step": 3127 + }, + { + "epoch": 0.33, + "learning_rate": 1.6994959518013502e-05, + "loss": 1.4111, + "step": 3128 + }, + { + "epoch": 0.33, + "learning_rate": 1.6992343300963963e-05, + "loss": 1.5452, + "step": 3129 + }, + { + "epoch": 0.33, + "learning_rate": 1.6989726147120087e-05, + "loss": 1.4097, + "step": 3130 + }, + { + "epoch": 0.33, + "learning_rate": 1.6987108056832506e-05, + "loss": 1.481, + "step": 3131 + }, + { + "epoch": 0.33, + "learning_rate": 1.6984489030451973e-05, + "loss": 1.4505, + "step": 3132 + }, + { + "epoch": 0.33, + "learning_rate": 1.6981869068329368e-05, + "loss": 1.4281, + "step": 3133 + }, + { + "epoch": 0.33, + "learning_rate": 1.69792481708157e-05, + "loss": 1.4555, + "step": 3134 + }, + { + "epoch": 0.33, + "learning_rate": 1.6976626338262103e-05, + "loss": 1.4525, + "step": 3135 + }, + { + "epoch": 0.33, + "learning_rate": 1.6974003571019837e-05, + "loss": 1.3765, + "step": 3136 + }, + { + "epoch": 0.33, + "learning_rate": 1.6971379869440286e-05, + "loss": 1.3998, + "step": 3137 + }, + { + "epoch": 0.33, + "learning_rate": 1.696875523387495e-05, + "loss": 1.5103, + "step": 3138 + }, + { + "epoch": 0.33, + "learning_rate": 1.6966129664675474e-05, + "loss": 1.427, + "step": 3139 + }, + { + "epoch": 0.33, + "learning_rate": 1.6963503162193612e-05, + "loss": 1.4362, + "step": 3140 + }, + { + "epoch": 0.33, + "learning_rate": 1.6960875726781246e-05, + "loss": 1.4073, + "step": 3141 + }, + { + "epoch": 0.33, + "learning_rate": 1.6958247358790388e-05, + "loss": 1.4014, + "step": 3142 + }, + { + "epoch": 0.33, + "learning_rate": 1.6955618058573165e-05, + "loss": 1.4244, + "step": 3143 + }, + { + "epoch": 0.33, + "learning_rate": 1.6952987826481847e-05, + "loss": 1.47, + "step": 3144 + }, + { + "epoch": 0.33, + "learning_rate": 1.6950356662868814e-05, + "loss": 1.5112, + "step": 3145 + }, + { + "epoch": 0.33, + "learning_rate": 1.6947724568086562e-05, + "loss": 1.3398, + "step": 3146 + }, + { + "epoch": 0.33, + "learning_rate": 1.694509154248774e-05, + "loss": 1.4584, + "step": 3147 + }, + { + "epoch": 0.33, + "learning_rate": 1.69424575864251e-05, + "loss": 1.4383, + "step": 3148 + }, + { + "epoch": 0.33, + "learning_rate": 1.6939822700251523e-05, + "loss": 1.3869, + "step": 3149 + }, + { + "epoch": 0.33, + "learning_rate": 1.6937186884320015e-05, + "loss": 1.4453, + "step": 3150 + }, + { + "epoch": 0.33, + "learning_rate": 1.6934550138983713e-05, + "loss": 1.3355, + "step": 3151 + }, + { + "epoch": 0.33, + "learning_rate": 1.6931912464595866e-05, + "loss": 1.5573, + "step": 3152 + }, + { + "epoch": 0.33, + "learning_rate": 1.6929273861509865e-05, + "loss": 1.439, + "step": 3153 + }, + { + "epoch": 0.33, + "learning_rate": 1.6926634330079203e-05, + "loss": 1.6079, + "step": 3154 + }, + { + "epoch": 0.33, + "learning_rate": 1.692399387065752e-05, + "loss": 1.6973, + "step": 3155 + }, + { + "epoch": 0.33, + "learning_rate": 1.692135248359856e-05, + "loss": 1.3769, + "step": 3156 + }, + { + "epoch": 0.33, + "learning_rate": 1.6918710169256206e-05, + "loss": 1.4454, + "step": 3157 + }, + { + "epoch": 0.33, + "learning_rate": 1.691606692798446e-05, + "loss": 1.4495, + "step": 3158 + }, + { + "epoch": 0.33, + "learning_rate": 1.691342276013745e-05, + "loss": 1.4292, + "step": 3159 + }, + { + "epoch": 0.33, + "learning_rate": 1.691077766606942e-05, + "loss": 1.4405, + "step": 3160 + }, + { + "epoch": 0.33, + "learning_rate": 1.6908131646134757e-05, + "loss": 1.3683, + "step": 3161 + }, + { + "epoch": 0.33, + "learning_rate": 1.690548470068795e-05, + "loss": 1.4731, + "step": 3162 + }, + { + "epoch": 0.33, + "learning_rate": 1.690283683008362e-05, + "loss": 1.4323, + "step": 3163 + }, + { + "epoch": 0.33, + "learning_rate": 1.6900188034676518e-05, + "loss": 1.5133, + "step": 3164 + }, + { + "epoch": 0.33, + "learning_rate": 1.6897538314821516e-05, + "loss": 1.5529, + "step": 3165 + }, + { + "epoch": 0.33, + "learning_rate": 1.6894887670873605e-05, + "loss": 1.4427, + "step": 3166 + }, + { + "epoch": 0.33, + "learning_rate": 1.6892236103187904e-05, + "loss": 1.4344, + "step": 3167 + }, + { + "epoch": 0.33, + "learning_rate": 1.6889583612119657e-05, + "loss": 1.4291, + "step": 3168 + }, + { + "epoch": 0.33, + "learning_rate": 1.6886930198024226e-05, + "loss": 1.4683, + "step": 3169 + }, + { + "epoch": 0.33, + "learning_rate": 1.6884275861257106e-05, + "loss": 1.4442, + "step": 3170 + }, + { + "epoch": 0.33, + "learning_rate": 1.6881620602173905e-05, + "loss": 1.4509, + "step": 3171 + }, + { + "epoch": 0.33, + "learning_rate": 1.6878964421130362e-05, + "loss": 1.5113, + "step": 3172 + }, + { + "epoch": 0.33, + "learning_rate": 1.6876307318482334e-05, + "loss": 1.4261, + "step": 3173 + }, + { + "epoch": 0.33, + "learning_rate": 1.6873649294585805e-05, + "loss": 1.445, + "step": 3174 + }, + { + "epoch": 0.33, + "learning_rate": 1.6870990349796886e-05, + "loss": 1.4603, + "step": 3175 + }, + { + "epoch": 0.33, + "learning_rate": 1.68683304844718e-05, + "loss": 1.41, + "step": 3176 + }, + { + "epoch": 0.33, + "learning_rate": 1.686566969896691e-05, + "loss": 1.4018, + "step": 3177 + }, + { + "epoch": 0.33, + "learning_rate": 1.6863007993638687e-05, + "loss": 1.422, + "step": 3178 + }, + { + "epoch": 0.33, + "learning_rate": 1.6860345368843727e-05, + "loss": 1.4412, + "step": 3179 + }, + { + "epoch": 0.33, + "learning_rate": 1.6857681824938768e-05, + "loss": 1.5411, + "step": 3180 + }, + { + "epoch": 0.33, + "learning_rate": 1.685501736228064e-05, + "loss": 1.4416, + "step": 3181 + }, + { + "epoch": 0.33, + "learning_rate": 1.685235198122632e-05, + "loss": 1.5113, + "step": 3182 + }, + { + "epoch": 0.33, + "learning_rate": 1.6849685682132903e-05, + "loss": 1.423, + "step": 3183 + }, + { + "epoch": 0.33, + "learning_rate": 1.68470184653576e-05, + "loss": 1.404, + "step": 3184 + }, + { + "epoch": 0.33, + "eval_loss": 1.4771089553833008, + "eval_runtime": 77.4034, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3184 + }, + { + "epoch": 0.33, + "learning_rate": 1.6844350331257747e-05, + "loss": 1.4624, + "step": 3185 + }, + { + "epoch": 0.33, + "learning_rate": 1.6841681280190814e-05, + "loss": 1.4306, + "step": 3186 + }, + { + "epoch": 0.33, + "learning_rate": 1.683901131251438e-05, + "loss": 1.42, + "step": 3187 + }, + { + "epoch": 0.33, + "learning_rate": 1.6836340428586155e-05, + "loss": 1.4787, + "step": 3188 + }, + { + "epoch": 0.33, + "learning_rate": 1.6833668628763965e-05, + "loss": 1.3485, + "step": 3189 + }, + { + "epoch": 0.33, + "learning_rate": 1.683099591340576e-05, + "loss": 1.3674, + "step": 3190 + }, + { + "epoch": 0.33, + "learning_rate": 1.6828322282869627e-05, + "loss": 1.5187, + "step": 3191 + }, + { + "epoch": 0.33, + "learning_rate": 1.682564773751375e-05, + "loss": 1.4847, + "step": 3192 + }, + { + "epoch": 0.33, + "learning_rate": 1.682297227769646e-05, + "loss": 1.4815, + "step": 3193 + }, + { + "epoch": 0.33, + "learning_rate": 1.682029590377619e-05, + "loss": 1.4281, + "step": 3194 + }, + { + "epoch": 0.34, + "learning_rate": 1.6817618616111517e-05, + "loss": 1.4734, + "step": 3195 + }, + { + "epoch": 0.34, + "learning_rate": 1.681494041506112e-05, + "loss": 1.4861, + "step": 3196 + }, + { + "epoch": 0.34, + "learning_rate": 1.6812261300983808e-05, + "loss": 1.4372, + "step": 3197 + }, + { + "epoch": 0.34, + "learning_rate": 1.680958127423852e-05, + "loss": 1.4396, + "step": 3198 + }, + { + "epoch": 0.34, + "learning_rate": 1.680690033518431e-05, + "loss": 1.4225, + "step": 3199 + }, + { + "epoch": 0.34, + "learning_rate": 1.6804218484180347e-05, + "loss": 1.4925, + "step": 3200 + }, + { + "epoch": 0.34, + "learning_rate": 1.6801535721585942e-05, + "loss": 1.4306, + "step": 3201 + }, + { + "epoch": 0.34, + "learning_rate": 1.6798852047760506e-05, + "loss": 1.4298, + "step": 3202 + }, + { + "epoch": 0.34, + "learning_rate": 1.6796167463063588e-05, + "loss": 1.4725, + "step": 3203 + }, + { + "epoch": 0.34, + "learning_rate": 1.679348196785485e-05, + "loss": 1.4648, + "step": 3204 + }, + { + "epoch": 0.34, + "learning_rate": 1.6790795562494087e-05, + "loss": 1.4152, + "step": 3205 + }, + { + "epoch": 0.34, + "learning_rate": 1.6788108247341198e-05, + "loss": 1.4637, + "step": 3206 + }, + { + "epoch": 0.34, + "learning_rate": 1.6785420022756216e-05, + "loss": 1.4077, + "step": 3207 + }, + { + "epoch": 0.34, + "learning_rate": 1.67827308890993e-05, + "loss": 1.4585, + "step": 3208 + }, + { + "epoch": 0.34, + "learning_rate": 1.678004084673072e-05, + "loss": 1.3747, + "step": 3209 + }, + { + "epoch": 0.34, + "learning_rate": 1.6777349896010876e-05, + "loss": 1.4264, + "step": 3210 + }, + { + "epoch": 0.34, + "learning_rate": 1.677465803730028e-05, + "loss": 1.4178, + "step": 3211 + }, + { + "epoch": 0.34, + "learning_rate": 1.6771965270959584e-05, + "loss": 1.3876, + "step": 3212 + }, + { + "epoch": 0.34, + "learning_rate": 1.6769271597349538e-05, + "loss": 1.4658, + "step": 3213 + }, + { + "epoch": 0.34, + "learning_rate": 1.6766577016831026e-05, + "loss": 1.3968, + "step": 3214 + }, + { + "epoch": 0.34, + "learning_rate": 1.676388152976506e-05, + "loss": 1.5015, + "step": 3215 + }, + { + "epoch": 0.34, + "learning_rate": 1.6761185136512756e-05, + "loss": 1.4121, + "step": 3216 + }, + { + "epoch": 0.34, + "learning_rate": 1.675848783743537e-05, + "loss": 1.4146, + "step": 3217 + }, + { + "epoch": 0.34, + "learning_rate": 1.675578963289427e-05, + "loss": 1.4113, + "step": 3218 + }, + { + "epoch": 0.34, + "learning_rate": 1.6753090523250937e-05, + "loss": 1.4048, + "step": 3219 + }, + { + "epoch": 0.34, + "learning_rate": 1.6750390508866994e-05, + "loss": 1.4959, + "step": 3220 + }, + { + "epoch": 0.34, + "learning_rate": 1.6747689590104167e-05, + "loss": 1.4445, + "step": 3221 + }, + { + "epoch": 0.34, + "learning_rate": 1.6744987767324312e-05, + "loss": 1.4611, + "step": 3222 + }, + { + "epoch": 0.34, + "learning_rate": 1.67422850408894e-05, + "loss": 1.4141, + "step": 3223 + }, + { + "epoch": 0.34, + "learning_rate": 1.6739581411161535e-05, + "loss": 1.4218, + "step": 3224 + }, + { + "epoch": 0.34, + "learning_rate": 1.6736876878502925e-05, + "loss": 1.4266, + "step": 3225 + }, + { + "epoch": 0.34, + "learning_rate": 1.6734171443275913e-05, + "loss": 1.4941, + "step": 3226 + }, + { + "epoch": 0.34, + "learning_rate": 1.6731465105842955e-05, + "loss": 1.4294, + "step": 3227 + }, + { + "epoch": 0.34, + "learning_rate": 1.6728757866566635e-05, + "loss": 1.4189, + "step": 3228 + }, + { + "epoch": 0.34, + "learning_rate": 1.6726049725809647e-05, + "loss": 1.4713, + "step": 3229 + }, + { + "epoch": 0.34, + "learning_rate": 1.6723340683934818e-05, + "loss": 1.4203, + "step": 3230 + }, + { + "epoch": 0.34, + "learning_rate": 1.6720630741305088e-05, + "loss": 1.4112, + "step": 3231 + }, + { + "epoch": 0.34, + "learning_rate": 1.6717919898283523e-05, + "loss": 1.3811, + "step": 3232 + }, + { + "epoch": 0.34, + "learning_rate": 1.6715208155233296e-05, + "loss": 1.4242, + "step": 3233 + }, + { + "epoch": 0.34, + "learning_rate": 1.6712495512517725e-05, + "loss": 1.4207, + "step": 3234 + }, + { + "epoch": 0.34, + "learning_rate": 1.6709781970500222e-05, + "loss": 1.4888, + "step": 3235 + }, + { + "epoch": 0.34, + "learning_rate": 1.670706752954434e-05, + "loss": 1.4501, + "step": 3236 + }, + { + "epoch": 0.34, + "learning_rate": 1.670435219001374e-05, + "loss": 1.4367, + "step": 3237 + }, + { + "epoch": 0.34, + "learning_rate": 1.6701635952272212e-05, + "loss": 1.3959, + "step": 3238 + }, + { + "epoch": 0.34, + "learning_rate": 1.6698918816683655e-05, + "loss": 1.4257, + "step": 3239 + }, + { + "epoch": 0.34, + "learning_rate": 1.6696200783612102e-05, + "loss": 1.4718, + "step": 3240 + }, + { + "epoch": 0.34, + "learning_rate": 1.6693481853421697e-05, + "loss": 1.5899, + "step": 3241 + }, + { + "epoch": 0.34, + "learning_rate": 1.6690762026476707e-05, + "loss": 1.418, + "step": 3242 + }, + { + "epoch": 0.34, + "learning_rate": 1.668804130314152e-05, + "loss": 1.4076, + "step": 3243 + }, + { + "epoch": 0.34, + "learning_rate": 1.6685319683780645e-05, + "loss": 1.4571, + "step": 3244 + }, + { + "epoch": 0.34, + "learning_rate": 1.66825971687587e-05, + "loss": 1.4066, + "step": 3245 + }, + { + "epoch": 0.34, + "learning_rate": 1.6679873758440442e-05, + "loss": 1.4639, + "step": 3246 + }, + { + "epoch": 0.34, + "learning_rate": 1.6677149453190732e-05, + "loss": 1.453, + "step": 3247 + }, + { + "epoch": 0.34, + "learning_rate": 1.6674424253374558e-05, + "loss": 1.4262, + "step": 3248 + }, + { + "epoch": 0.34, + "learning_rate": 1.667169815935703e-05, + "loss": 1.3687, + "step": 3249 + }, + { + "epoch": 0.34, + "learning_rate": 1.6668971171503372e-05, + "loss": 1.5557, + "step": 3250 + }, + { + "epoch": 0.34, + "learning_rate": 1.6666243290178933e-05, + "loss": 1.4639, + "step": 3251 + }, + { + "epoch": 0.34, + "learning_rate": 1.6663514515749172e-05, + "loss": 1.4334, + "step": 3252 + }, + { + "epoch": 0.34, + "learning_rate": 1.6660784848579685e-05, + "loss": 1.3523, + "step": 3253 + }, + { + "epoch": 0.34, + "learning_rate": 1.6658054289036166e-05, + "loss": 1.3738, + "step": 3254 + }, + { + "epoch": 0.34, + "learning_rate": 1.665532283748445e-05, + "loss": 1.4159, + "step": 3255 + }, + { + "epoch": 0.34, + "learning_rate": 1.6652590494290474e-05, + "loss": 1.3609, + "step": 3256 + }, + { + "epoch": 0.34, + "learning_rate": 1.6649857259820303e-05, + "loss": 1.4449, + "step": 3257 + }, + { + "epoch": 0.34, + "learning_rate": 1.6647123134440126e-05, + "loss": 1.424, + "step": 3258 + }, + { + "epoch": 0.34, + "learning_rate": 1.664438811851624e-05, + "loss": 1.4737, + "step": 3259 + }, + { + "epoch": 0.34, + "learning_rate": 1.6641652212415066e-05, + "loss": 1.2717, + "step": 3260 + }, + { + "epoch": 0.34, + "learning_rate": 1.663891541650315e-05, + "loss": 1.4845, + "step": 3261 + }, + { + "epoch": 0.34, + "learning_rate": 1.663617773114715e-05, + "loss": 1.4115, + "step": 3262 + }, + { + "epoch": 0.34, + "learning_rate": 1.663343915671384e-05, + "loss": 1.4237, + "step": 3263 + }, + { + "epoch": 0.34, + "learning_rate": 1.6630699693570127e-05, + "loss": 1.4209, + "step": 3264 + }, + { + "epoch": 0.34, + "learning_rate": 1.6627959342083026e-05, + "loss": 1.506, + "step": 3265 + }, + { + "epoch": 0.34, + "learning_rate": 1.6625218102619672e-05, + "loss": 1.4466, + "step": 3266 + }, + { + "epoch": 0.34, + "learning_rate": 1.6622475975547324e-05, + "loss": 1.4129, + "step": 3267 + }, + { + "epoch": 0.34, + "learning_rate": 1.661973296123335e-05, + "loss": 1.4152, + "step": 3268 + }, + { + "epoch": 0.34, + "learning_rate": 1.661698906004525e-05, + "loss": 1.43, + "step": 3269 + }, + { + "epoch": 0.34, + "learning_rate": 1.661424427235064e-05, + "loss": 1.4701, + "step": 3270 + }, + { + "epoch": 0.34, + "learning_rate": 1.6611498598517238e-05, + "loss": 1.4598, + "step": 3271 + }, + { + "epoch": 0.34, + "learning_rate": 1.66087520389129e-05, + "loss": 1.4795, + "step": 3272 + }, + { + "epoch": 0.34, + "learning_rate": 1.6606004593905595e-05, + "loss": 1.5264, + "step": 3273 + }, + { + "epoch": 0.34, + "learning_rate": 1.6603256263863415e-05, + "loss": 1.4412, + "step": 3274 + }, + { + "epoch": 0.34, + "learning_rate": 1.6600507049154556e-05, + "loss": 1.45, + "step": 3275 + }, + { + "epoch": 0.34, + "learning_rate": 1.659775695014735e-05, + "loss": 1.4985, + "step": 3276 + }, + { + "epoch": 0.34, + "learning_rate": 1.659500596721024e-05, + "loss": 1.496, + "step": 3277 + }, + { + "epoch": 0.34, + "learning_rate": 1.6592254100711775e-05, + "loss": 1.4386, + "step": 3278 + }, + { + "epoch": 0.34, + "learning_rate": 1.658950135102065e-05, + "loss": 1.4073, + "step": 3279 + }, + { + "epoch": 0.34, + "learning_rate": 1.658674771850565e-05, + "loss": 1.3912, + "step": 3280 + }, + { + "epoch": 0.34, + "learning_rate": 1.6583993203535702e-05, + "loss": 1.3628, + "step": 3281 + }, + { + "epoch": 0.34, + "learning_rate": 1.658123780647983e-05, + "loss": 1.6089, + "step": 3282 + }, + { + "epoch": 0.34, + "learning_rate": 1.6578481527707196e-05, + "loss": 1.2367, + "step": 3283 + }, + { + "epoch": 0.34, + "learning_rate": 1.657572436758706e-05, + "loss": 1.4058, + "step": 3284 + }, + { + "epoch": 0.34, + "learning_rate": 1.6572966326488825e-05, + "loss": 1.4067, + "step": 3285 + }, + { + "epoch": 0.34, + "learning_rate": 1.657020740478198e-05, + "loss": 1.4187, + "step": 3286 + }, + { + "epoch": 0.34, + "learning_rate": 1.6567447602836166e-05, + "loss": 1.4599, + "step": 3287 + }, + { + "epoch": 0.34, + "learning_rate": 1.6564686921021115e-05, + "loss": 1.432, + "step": 3288 + }, + { + "epoch": 0.34, + "learning_rate": 1.6561925359706693e-05, + "loss": 1.3941, + "step": 3289 + }, + { + "epoch": 0.35, + "learning_rate": 1.6559162919262874e-05, + "loss": 1.3644, + "step": 3290 + }, + { + "epoch": 0.35, + "learning_rate": 1.6556399600059756e-05, + "loss": 1.4628, + "step": 3291 + }, + { + "epoch": 0.35, + "learning_rate": 1.6553635402467555e-05, + "loss": 1.4355, + "step": 3292 + }, + { + "epoch": 0.35, + "learning_rate": 1.6550870326856596e-05, + "loss": 1.4627, + "step": 3293 + }, + { + "epoch": 0.35, + "learning_rate": 1.6548104373597335e-05, + "loss": 1.442, + "step": 3294 + }, + { + "epoch": 0.35, + "learning_rate": 1.6545337543060338e-05, + "loss": 1.3991, + "step": 3295 + }, + { + "epoch": 0.35, + "learning_rate": 1.6542569835616283e-05, + "loss": 1.4193, + "step": 3296 + }, + { + "epoch": 0.35, + "learning_rate": 1.6539801251635982e-05, + "loss": 1.4792, + "step": 3297 + }, + { + "epoch": 0.35, + "learning_rate": 1.653703179149034e-05, + "loss": 1.4735, + "step": 3298 + }, + { + "epoch": 0.35, + "learning_rate": 1.6534261455550408e-05, + "loss": 1.451, + "step": 3299 + }, + { + "epoch": 0.35, + "learning_rate": 1.653149024418733e-05, + "loss": 1.3975, + "step": 3300 + }, + { + "epoch": 0.35, + "learning_rate": 1.652871815777238e-05, + "loss": 1.4843, + "step": 3301 + }, + { + "epoch": 0.35, + "learning_rate": 1.6525945196676948e-05, + "loss": 1.4782, + "step": 3302 + }, + { + "epoch": 0.35, + "learning_rate": 1.652317136127254e-05, + "loss": 1.3865, + "step": 3303 + }, + { + "epoch": 0.35, + "learning_rate": 1.6520396651930777e-05, + "loss": 1.4359, + "step": 3304 + }, + { + "epoch": 0.35, + "learning_rate": 1.6517621069023397e-05, + "loss": 1.4289, + "step": 3305 + }, + { + "epoch": 0.35, + "learning_rate": 1.651484461292226e-05, + "loss": 1.3526, + "step": 3306 + }, + { + "epoch": 0.35, + "learning_rate": 1.6512067283999336e-05, + "loss": 1.3671, + "step": 3307 + }, + { + "epoch": 0.35, + "learning_rate": 1.650928908262672e-05, + "loss": 1.6041, + "step": 3308 + }, + { + "epoch": 0.35, + "learning_rate": 1.650651000917662e-05, + "loss": 1.4322, + "step": 3309 + }, + { + "epoch": 0.35, + "learning_rate": 1.6503730064021354e-05, + "loss": 1.3992, + "step": 3310 + }, + { + "epoch": 0.35, + "learning_rate": 1.650094924753337e-05, + "loss": 1.4928, + "step": 3311 + }, + { + "epoch": 0.35, + "learning_rate": 1.6498167560085222e-05, + "loss": 1.4075, + "step": 3312 + }, + { + "epoch": 0.35, + "learning_rate": 1.6495385002049583e-05, + "loss": 1.4535, + "step": 3313 + }, + { + "epoch": 0.35, + "learning_rate": 1.6492601573799253e-05, + "loss": 1.4221, + "step": 3314 + }, + { + "epoch": 0.35, + "learning_rate": 1.6489817275707133e-05, + "loss": 1.3688, + "step": 3315 + }, + { + "epoch": 0.35, + "learning_rate": 1.6487032108146243e-05, + "loss": 1.3889, + "step": 3316 + }, + { + "epoch": 0.35, + "learning_rate": 1.6484246071489733e-05, + "loss": 1.3942, + "step": 3317 + }, + { + "epoch": 0.35, + "learning_rate": 1.6481459166110858e-05, + "loss": 1.4004, + "step": 3318 + }, + { + "epoch": 0.35, + "learning_rate": 1.647867139238299e-05, + "loss": 1.7308, + "step": 3319 + }, + { + "epoch": 0.35, + "learning_rate": 1.6475882750679622e-05, + "loss": 1.5001, + "step": 3320 + }, + { + "epoch": 0.35, + "learning_rate": 1.647309324137435e-05, + "loss": 1.4325, + "step": 3321 + }, + { + "epoch": 0.35, + "learning_rate": 1.6470302864840913e-05, + "loss": 1.4494, + "step": 3322 + }, + { + "epoch": 0.35, + "learning_rate": 1.6467511621453136e-05, + "loss": 1.4418, + "step": 3323 + }, + { + "epoch": 0.35, + "learning_rate": 1.646471951158498e-05, + "loss": 1.4046, + "step": 3324 + }, + { + "epoch": 0.35, + "learning_rate": 1.6461926535610517e-05, + "loss": 1.5031, + "step": 3325 + }, + { + "epoch": 0.35, + "learning_rate": 1.645913269390393e-05, + "loss": 1.4813, + "step": 3326 + }, + { + "epoch": 0.35, + "learning_rate": 1.6456337986839525e-05, + "loss": 1.3842, + "step": 3327 + }, + { + "epoch": 0.35, + "learning_rate": 1.645354241479172e-05, + "loss": 1.4539, + "step": 3328 + }, + { + "epoch": 0.35, + "learning_rate": 1.6450745978135048e-05, + "loss": 1.4503, + "step": 3329 + }, + { + "epoch": 0.35, + "learning_rate": 1.6447948677244163e-05, + "loss": 1.3741, + "step": 3330 + }, + { + "epoch": 0.35, + "learning_rate": 1.6445150512493832e-05, + "loss": 1.425, + "step": 3331 + }, + { + "epoch": 0.35, + "learning_rate": 1.644235148425893e-05, + "loss": 1.4277, + "step": 3332 + }, + { + "epoch": 0.35, + "learning_rate": 1.6439551592914464e-05, + "loss": 1.4918, + "step": 3333 + }, + { + "epoch": 0.35, + "learning_rate": 1.6436750838835543e-05, + "loss": 1.3364, + "step": 3334 + }, + { + "epoch": 0.35, + "learning_rate": 1.6433949222397397e-05, + "loss": 1.4741, + "step": 3335 + }, + { + "epoch": 0.35, + "learning_rate": 1.643114674397537e-05, + "loss": 1.3867, + "step": 3336 + }, + { + "epoch": 0.35, + "learning_rate": 1.642834340394492e-05, + "loss": 1.3817, + "step": 3337 + }, + { + "epoch": 0.35, + "learning_rate": 1.6425539202681625e-05, + "loss": 1.4308, + "step": 3338 + }, + { + "epoch": 0.35, + "learning_rate": 1.6422734140561178e-05, + "loss": 1.4401, + "step": 3339 + }, + { + "epoch": 0.35, + "learning_rate": 1.641992821795938e-05, + "loss": 1.4338, + "step": 3340 + }, + { + "epoch": 0.35, + "learning_rate": 1.641712143525216e-05, + "loss": 1.3804, + "step": 3341 + }, + { + "epoch": 0.35, + "learning_rate": 1.6414313792815546e-05, + "loss": 1.371, + "step": 3342 + }, + { + "epoch": 0.35, + "learning_rate": 1.6411505291025695e-05, + "loss": 1.4102, + "step": 3343 + }, + { + "epoch": 0.35, + "learning_rate": 1.6408695930258875e-05, + "loss": 1.4433, + "step": 3344 + }, + { + "epoch": 0.35, + "learning_rate": 1.6405885710891467e-05, + "loss": 1.3895, + "step": 3345 + }, + { + "epoch": 0.35, + "learning_rate": 1.6403074633299966e-05, + "loss": 1.4321, + "step": 3346 + }, + { + "epoch": 0.35, + "learning_rate": 1.640026269786098e-05, + "loss": 1.4207, + "step": 3347 + }, + { + "epoch": 0.35, + "learning_rate": 1.639744990495125e-05, + "loss": 1.3758, + "step": 3348 + }, + { + "epoch": 0.35, + "learning_rate": 1.6394636254947612e-05, + "loss": 1.4203, + "step": 3349 + }, + { + "epoch": 0.35, + "learning_rate": 1.6391821748227013e-05, + "loss": 1.4596, + "step": 3350 + }, + { + "epoch": 0.35, + "learning_rate": 1.6389006385166537e-05, + "loss": 1.4344, + "step": 3351 + }, + { + "epoch": 0.35, + "learning_rate": 1.6386190166143366e-05, + "loss": 1.4048, + "step": 3352 + }, + { + "epoch": 0.35, + "learning_rate": 1.6383373091534798e-05, + "loss": 1.4348, + "step": 3353 + }, + { + "epoch": 0.35, + "learning_rate": 1.638055516171825e-05, + "loss": 1.4972, + "step": 3354 + }, + { + "epoch": 0.35, + "learning_rate": 1.6377736377071258e-05, + "loss": 1.4685, + "step": 3355 + }, + { + "epoch": 0.35, + "learning_rate": 1.637491673797146e-05, + "loss": 1.4093, + "step": 3356 + }, + { + "epoch": 0.35, + "learning_rate": 1.6372096244796616e-05, + "loss": 1.4452, + "step": 3357 + }, + { + "epoch": 0.35, + "learning_rate": 1.63692748979246e-05, + "loss": 1.4458, + "step": 3358 + }, + { + "epoch": 0.35, + "learning_rate": 1.6366452697733404e-05, + "loss": 1.4187, + "step": 3359 + }, + { + "epoch": 0.35, + "learning_rate": 1.6363629644601126e-05, + "loss": 1.4052, + "step": 3360 + }, + { + "epoch": 0.35, + "learning_rate": 1.6360805738905984e-05, + "loss": 1.439, + "step": 3361 + }, + { + "epoch": 0.35, + "learning_rate": 1.635798098102631e-05, + "loss": 1.4131, + "step": 3362 + }, + { + "epoch": 0.35, + "learning_rate": 1.6355155371340544e-05, + "loss": 1.4391, + "step": 3363 + }, + { + "epoch": 0.35, + "learning_rate": 1.6352328910227252e-05, + "loss": 1.4318, + "step": 3364 + }, + { + "epoch": 0.35, + "learning_rate": 1.63495015980651e-05, + "loss": 1.5112, + "step": 3365 + }, + { + "epoch": 0.35, + "learning_rate": 1.6346673435232884e-05, + "loss": 1.4688, + "step": 3366 + }, + { + "epoch": 0.35, + "learning_rate": 1.6343844422109496e-05, + "loss": 1.3807, + "step": 3367 + }, + { + "epoch": 0.35, + "learning_rate": 1.634101455907396e-05, + "loss": 1.4083, + "step": 3368 + }, + { + "epoch": 0.35, + "learning_rate": 1.6338183846505394e-05, + "loss": 1.3566, + "step": 3369 + }, + { + "epoch": 0.35, + "learning_rate": 1.633535228478305e-05, + "loss": 1.4287, + "step": 3370 + }, + { + "epoch": 0.35, + "learning_rate": 1.6332519874286285e-05, + "loss": 1.3494, + "step": 3371 + }, + { + "epoch": 0.35, + "learning_rate": 1.6329686615394558e-05, + "loss": 1.3813, + "step": 3372 + }, + { + "epoch": 0.35, + "learning_rate": 1.6326852508487468e-05, + "loss": 1.4241, + "step": 3373 + }, + { + "epoch": 0.35, + "learning_rate": 1.63240175539447e-05, + "loss": 1.424, + "step": 3374 + }, + { + "epoch": 0.35, + "learning_rate": 1.632118175214607e-05, + "loss": 1.4212, + "step": 3375 + }, + { + "epoch": 0.35, + "learning_rate": 1.6318345103471504e-05, + "loss": 1.4671, + "step": 3376 + }, + { + "epoch": 0.35, + "learning_rate": 1.6315507608301044e-05, + "loss": 1.4593, + "step": 3377 + }, + { + "epoch": 0.35, + "learning_rate": 1.631266926701483e-05, + "loss": 1.7816, + "step": 3378 + }, + { + "epoch": 0.35, + "learning_rate": 1.6309830079993134e-05, + "loss": 1.5134, + "step": 3379 + }, + { + "epoch": 0.35, + "learning_rate": 1.6306990047616334e-05, + "loss": 0.8933, + "step": 3380 + }, + { + "epoch": 0.35, + "learning_rate": 1.630414917026492e-05, + "loss": 1.1033, + "step": 3381 + }, + { + "epoch": 0.35, + "learning_rate": 1.6301307448319497e-05, + "loss": 1.3494, + "step": 3382 + }, + { + "epoch": 0.35, + "learning_rate": 1.6298464882160784e-05, + "loss": 1.4299, + "step": 3383 + }, + { + "epoch": 0.35, + "eval_loss": 1.482450008392334, + "eval_runtime": 77.3737, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3383 + }, + { + "epoch": 0.35, + "learning_rate": 1.629562147216961e-05, + "loss": 1.3971, + "step": 3384 + }, + { + "epoch": 0.35, + "learning_rate": 1.6292777218726917e-05, + "loss": 1.3706, + "step": 3385 + }, + { + "epoch": 0.36, + "learning_rate": 1.6289932122213765e-05, + "loss": 1.4524, + "step": 3386 + }, + { + "epoch": 0.36, + "learning_rate": 1.6287086183011328e-05, + "loss": 1.4595, + "step": 3387 + }, + { + "epoch": 0.36, + "learning_rate": 1.628423940150088e-05, + "loss": 1.492, + "step": 3388 + }, + { + "epoch": 0.36, + "learning_rate": 1.628139177806382e-05, + "loss": 1.5576, + "step": 3389 + }, + { + "epoch": 0.36, + "learning_rate": 1.6278543313081657e-05, + "loss": 1.4615, + "step": 3390 + }, + { + "epoch": 0.36, + "learning_rate": 1.6275694006936015e-05, + "loss": 1.3456, + "step": 3391 + }, + { + "epoch": 0.36, + "learning_rate": 1.627284386000862e-05, + "loss": 1.4254, + "step": 3392 + }, + { + "epoch": 0.36, + "learning_rate": 1.6269992872681325e-05, + "loss": 1.433, + "step": 3393 + }, + { + "epoch": 0.36, + "learning_rate": 1.626714104533609e-05, + "loss": 1.5291, + "step": 3394 + }, + { + "epoch": 0.36, + "learning_rate": 1.626428837835498e-05, + "loss": 1.4502, + "step": 3395 + }, + { + "epoch": 0.36, + "learning_rate": 1.626143487212019e-05, + "loss": 1.3756, + "step": 3396 + }, + { + "epoch": 0.36, + "learning_rate": 1.6258580527014002e-05, + "loss": 1.414, + "step": 3397 + }, + { + "epoch": 0.36, + "learning_rate": 1.6255725343418835e-05, + "loss": 1.6289, + "step": 3398 + }, + { + "epoch": 0.36, + "learning_rate": 1.6252869321717208e-05, + "loss": 1.4862, + "step": 3399 + }, + { + "epoch": 0.36, + "learning_rate": 1.6250012462291756e-05, + "loss": 1.4213, + "step": 3400 + }, + { + "epoch": 0.36, + "learning_rate": 1.6247154765525217e-05, + "loss": 1.524, + "step": 3401 + }, + { + "epoch": 0.36, + "learning_rate": 1.624429623180046e-05, + "loss": 1.6013, + "step": 3402 + }, + { + "epoch": 0.36, + "learning_rate": 1.624143686150045e-05, + "loss": 1.4557, + "step": 3403 + }, + { + "epoch": 0.36, + "learning_rate": 1.6238576655008266e-05, + "loss": 1.3831, + "step": 3404 + }, + { + "epoch": 0.36, + "learning_rate": 1.6235715612707105e-05, + "loss": 1.4008, + "step": 3405 + }, + { + "epoch": 0.36, + "learning_rate": 1.623285373498028e-05, + "loss": 1.4848, + "step": 3406 + }, + { + "epoch": 0.36, + "learning_rate": 1.6229991022211197e-05, + "loss": 1.4459, + "step": 3407 + }, + { + "epoch": 0.36, + "learning_rate": 1.6227127474783393e-05, + "loss": 1.4334, + "step": 3408 + }, + { + "epoch": 0.36, + "learning_rate": 1.6224263093080507e-05, + "loss": 1.4123, + "step": 3409 + }, + { + "epoch": 0.36, + "learning_rate": 1.6221397877486294e-05, + "loss": 1.3691, + "step": 3410 + }, + { + "epoch": 0.36, + "learning_rate": 1.6218531828384618e-05, + "loss": 1.4128, + "step": 3411 + }, + { + "epoch": 0.36, + "learning_rate": 1.6215664946159457e-05, + "loss": 1.3642, + "step": 3412 + }, + { + "epoch": 0.36, + "learning_rate": 1.6212797231194902e-05, + "loss": 1.4311, + "step": 3413 + }, + { + "epoch": 0.36, + "learning_rate": 1.6209928683875152e-05, + "loss": 1.4695, + "step": 3414 + }, + { + "epoch": 0.36, + "learning_rate": 1.6207059304584514e-05, + "loss": 1.3871, + "step": 3415 + }, + { + "epoch": 0.36, + "learning_rate": 1.6204189093707414e-05, + "loss": 1.4219, + "step": 3416 + }, + { + "epoch": 0.36, + "learning_rate": 1.620131805162839e-05, + "loss": 1.6199, + "step": 3417 + }, + { + "epoch": 0.36, + "learning_rate": 1.619844617873208e-05, + "loss": 1.4433, + "step": 3418 + }, + { + "epoch": 0.36, + "learning_rate": 1.619557347540325e-05, + "loss": 1.4773, + "step": 3419 + }, + { + "epoch": 0.36, + "learning_rate": 1.6192699942026763e-05, + "loss": 1.4551, + "step": 3420 + }, + { + "epoch": 0.36, + "learning_rate": 1.6189825578987603e-05, + "loss": 1.4903, + "step": 3421 + }, + { + "epoch": 0.36, + "learning_rate": 1.6186950386670855e-05, + "loss": 1.473, + "step": 3422 + }, + { + "epoch": 0.36, + "learning_rate": 1.6184074365461722e-05, + "loss": 1.4082, + "step": 3423 + }, + { + "epoch": 0.36, + "learning_rate": 1.6181197515745523e-05, + "loss": 1.4746, + "step": 3424 + }, + { + "epoch": 0.36, + "learning_rate": 1.6178319837907674e-05, + "loss": 1.449, + "step": 3425 + }, + { + "epoch": 0.36, + "learning_rate": 1.6175441332333715e-05, + "loss": 1.377, + "step": 3426 + }, + { + "epoch": 0.36, + "learning_rate": 1.617256199940929e-05, + "loss": 1.2364, + "step": 3427 + }, + { + "epoch": 0.36, + "learning_rate": 1.6169681839520155e-05, + "loss": 1.4437, + "step": 3428 + }, + { + "epoch": 0.36, + "learning_rate": 1.616680085305218e-05, + "loss": 1.4726, + "step": 3429 + }, + { + "epoch": 0.36, + "learning_rate": 1.616391904039134e-05, + "loss": 1.4824, + "step": 3430 + }, + { + "epoch": 0.36, + "learning_rate": 1.616103640192373e-05, + "loss": 1.4052, + "step": 3431 + }, + { + "epoch": 0.36, + "learning_rate": 1.6158152938035537e-05, + "loss": 1.4131, + "step": 3432 + }, + { + "epoch": 0.36, + "learning_rate": 1.6155268649113084e-05, + "loss": 1.4267, + "step": 3433 + }, + { + "epoch": 0.36, + "learning_rate": 1.6152383535542786e-05, + "loss": 1.3735, + "step": 3434 + }, + { + "epoch": 0.36, + "learning_rate": 1.6149497597711175e-05, + "loss": 1.4249, + "step": 3435 + }, + { + "epoch": 0.36, + "learning_rate": 1.614661083600489e-05, + "loss": 1.4312, + "step": 3436 + }, + { + "epoch": 0.36, + "learning_rate": 1.6143723250810686e-05, + "loss": 1.4831, + "step": 3437 + }, + { + "epoch": 0.36, + "learning_rate": 1.6140834842515425e-05, + "loss": 1.4183, + "step": 3438 + }, + { + "epoch": 0.36, + "learning_rate": 1.6137945611506078e-05, + "loss": 1.3908, + "step": 3439 + }, + { + "epoch": 0.36, + "learning_rate": 1.613505555816973e-05, + "loss": 1.425, + "step": 3440 + }, + { + "epoch": 0.36, + "learning_rate": 1.613216468289357e-05, + "loss": 1.3589, + "step": 3441 + }, + { + "epoch": 0.36, + "learning_rate": 1.6129272986064903e-05, + "loss": 1.4272, + "step": 3442 + }, + { + "epoch": 0.36, + "learning_rate": 1.6126380468071142e-05, + "loss": 1.4337, + "step": 3443 + }, + { + "epoch": 0.36, + "learning_rate": 1.6123487129299817e-05, + "loss": 1.3872, + "step": 3444 + }, + { + "epoch": 0.36, + "learning_rate": 1.612059297013855e-05, + "loss": 1.374, + "step": 3445 + }, + { + "epoch": 0.36, + "learning_rate": 1.611769799097509e-05, + "loss": 1.314, + "step": 3446 + }, + { + "epoch": 0.36, + "learning_rate": 1.6114802192197284e-05, + "loss": 1.3951, + "step": 3447 + }, + { + "epoch": 0.36, + "learning_rate": 1.6111905574193102e-05, + "loss": 1.4732, + "step": 3448 + }, + { + "epoch": 0.36, + "learning_rate": 1.6109008137350614e-05, + "loss": 1.3575, + "step": 3449 + }, + { + "epoch": 0.36, + "learning_rate": 1.6106109882058e-05, + "loss": 1.4606, + "step": 3450 + }, + { + "epoch": 0.36, + "learning_rate": 1.6103210808703554e-05, + "loss": 1.4357, + "step": 3451 + }, + { + "epoch": 0.36, + "learning_rate": 1.6100310917675678e-05, + "loss": 0.8456, + "step": 3452 + }, + { + "epoch": 0.36, + "learning_rate": 1.609741020936288e-05, + "loss": 1.07, + "step": 3453 + }, + { + "epoch": 0.36, + "learning_rate": 1.6094508684153782e-05, + "loss": 1.4435, + "step": 3454 + }, + { + "epoch": 0.36, + "learning_rate": 1.609160634243711e-05, + "loss": 1.3696, + "step": 3455 + }, + { + "epoch": 0.36, + "learning_rate": 1.6088703184601712e-05, + "loss": 1.4012, + "step": 3456 + }, + { + "epoch": 0.36, + "learning_rate": 1.608579921103653e-05, + "loss": 1.5212, + "step": 3457 + }, + { + "epoch": 0.36, + "learning_rate": 1.608289442213062e-05, + "loss": 1.4339, + "step": 3458 + }, + { + "epoch": 0.36, + "learning_rate": 1.607998881827316e-05, + "loss": 1.4901, + "step": 3459 + }, + { + "epoch": 0.36, + "learning_rate": 1.6077082399853412e-05, + "loss": 1.4822, + "step": 3460 + }, + { + "epoch": 0.36, + "learning_rate": 1.607417516726077e-05, + "loss": 1.3696, + "step": 3461 + }, + { + "epoch": 0.36, + "learning_rate": 1.6071267120884727e-05, + "loss": 1.4434, + "step": 3462 + }, + { + "epoch": 0.36, + "learning_rate": 1.6068358261114886e-05, + "loss": 1.3916, + "step": 3463 + }, + { + "epoch": 0.36, + "learning_rate": 1.606544858834096e-05, + "loss": 1.422, + "step": 3464 + }, + { + "epoch": 0.36, + "learning_rate": 1.6062538102952763e-05, + "loss": 1.367, + "step": 3465 + }, + { + "epoch": 0.36, + "learning_rate": 1.605962680534024e-05, + "loss": 1.3788, + "step": 3466 + }, + { + "epoch": 0.36, + "learning_rate": 1.605671469589342e-05, + "loss": 1.4366, + "step": 3467 + }, + { + "epoch": 0.36, + "learning_rate": 1.6053801775002453e-05, + "loss": 1.4027, + "step": 3468 + }, + { + "epoch": 0.36, + "learning_rate": 1.6050888043057595e-05, + "loss": 1.4386, + "step": 3469 + }, + { + "epoch": 0.36, + "learning_rate": 1.6047973500449212e-05, + "loss": 1.4675, + "step": 3470 + }, + { + "epoch": 0.36, + "learning_rate": 1.6045058147567778e-05, + "loss": 1.6936, + "step": 3471 + }, + { + "epoch": 0.36, + "learning_rate": 1.6042141984803875e-05, + "loss": 1.4858, + "step": 3472 + }, + { + "epoch": 0.36, + "learning_rate": 1.6039225012548196e-05, + "loss": 1.5004, + "step": 3473 + }, + { + "epoch": 0.36, + "learning_rate": 1.6036307231191534e-05, + "loss": 1.4969, + "step": 3474 + }, + { + "epoch": 0.36, + "learning_rate": 1.6033388641124803e-05, + "loss": 1.4027, + "step": 3475 + }, + { + "epoch": 0.36, + "learning_rate": 1.6030469242739016e-05, + "loss": 1.4741, + "step": 3476 + }, + { + "epoch": 0.36, + "learning_rate": 1.60275490364253e-05, + "loss": 1.3887, + "step": 3477 + }, + { + "epoch": 0.36, + "learning_rate": 1.602462802257488e-05, + "loss": 1.6735, + "step": 3478 + }, + { + "epoch": 0.36, + "learning_rate": 1.602170620157911e-05, + "loss": 1.4997, + "step": 3479 + }, + { + "epoch": 0.36, + "learning_rate": 1.601878357382943e-05, + "loss": 1.3973, + "step": 3480 + }, + { + "epoch": 0.37, + "learning_rate": 1.6015860139717398e-05, + "loss": 1.416, + "step": 3481 + }, + { + "epoch": 0.37, + "learning_rate": 1.6012935899634682e-05, + "loss": 1.4102, + "step": 3482 + }, + { + "epoch": 0.37, + "learning_rate": 1.601001085397305e-05, + "loss": 1.4248, + "step": 3483 + }, + { + "epoch": 0.37, + "learning_rate": 1.6007085003124386e-05, + "loss": 1.3909, + "step": 3484 + }, + { + "epoch": 0.37, + "learning_rate": 1.600415834748068e-05, + "loss": 1.4029, + "step": 3485 + }, + { + "epoch": 0.37, + "learning_rate": 1.6001230887434024e-05, + "loss": 1.4219, + "step": 3486 + }, + { + "epoch": 0.37, + "learning_rate": 1.5998302623376633e-05, + "loss": 1.4008, + "step": 3487 + }, + { + "epoch": 0.37, + "learning_rate": 1.5995373555700806e-05, + "loss": 1.5163, + "step": 3488 + }, + { + "epoch": 0.37, + "learning_rate": 1.599244368479897e-05, + "loss": 1.4541, + "step": 3489 + }, + { + "epoch": 0.37, + "learning_rate": 1.598951301106365e-05, + "loss": 1.4454, + "step": 3490 + }, + { + "epoch": 0.37, + "learning_rate": 1.598658153488748e-05, + "loss": 1.1014, + "step": 3491 + }, + { + "epoch": 0.37, + "learning_rate": 1.598364925666321e-05, + "loss": 1.407, + "step": 3492 + }, + { + "epoch": 0.37, + "learning_rate": 1.5980716176783682e-05, + "loss": 1.5046, + "step": 3493 + }, + { + "epoch": 0.37, + "learning_rate": 1.5977782295641857e-05, + "loss": 1.4265, + "step": 3494 + }, + { + "epoch": 0.37, + "learning_rate": 1.5974847613630796e-05, + "loss": 1.46, + "step": 3495 + }, + { + "epoch": 0.37, + "learning_rate": 1.5971912131143677e-05, + "loss": 1.3996, + "step": 3496 + }, + { + "epoch": 0.37, + "learning_rate": 1.5968975848573772e-05, + "loss": 1.4719, + "step": 3497 + }, + { + "epoch": 0.37, + "learning_rate": 1.596603876631447e-05, + "loss": 1.43, + "step": 3498 + }, + { + "epoch": 0.37, + "learning_rate": 1.596310088475927e-05, + "loss": 1.4109, + "step": 3499 + }, + { + "epoch": 0.37, + "learning_rate": 1.5960162204301768e-05, + "loss": 1.3612, + "step": 3500 + }, + { + "epoch": 0.37, + "learning_rate": 1.5957222725335672e-05, + "loss": 1.5045, + "step": 3501 + }, + { + "epoch": 0.37, + "learning_rate": 1.5954282448254794e-05, + "loss": 1.5323, + "step": 3502 + }, + { + "epoch": 0.37, + "learning_rate": 1.595134137345306e-05, + "loss": 1.4518, + "step": 3503 + }, + { + "epoch": 0.37, + "learning_rate": 1.5948399501324495e-05, + "loss": 1.6131, + "step": 3504 + }, + { + "epoch": 0.37, + "learning_rate": 1.594545683226324e-05, + "loss": 1.5076, + "step": 3505 + }, + { + "epoch": 0.37, + "learning_rate": 1.594251336666353e-05, + "loss": 1.482, + "step": 3506 + }, + { + "epoch": 0.37, + "learning_rate": 1.5939569104919716e-05, + "loss": 1.4429, + "step": 3507 + }, + { + "epoch": 0.37, + "learning_rate": 1.5936624047426254e-05, + "loss": 1.4662, + "step": 3508 + }, + { + "epoch": 0.37, + "learning_rate": 1.5933678194577708e-05, + "loss": 1.425, + "step": 3509 + }, + { + "epoch": 0.37, + "learning_rate": 1.5930731546768744e-05, + "loss": 1.4312, + "step": 3510 + }, + { + "epoch": 0.37, + "learning_rate": 1.592778410439414e-05, + "loss": 1.4336, + "step": 3511 + }, + { + "epoch": 0.37, + "learning_rate": 1.5924835867848775e-05, + "loss": 1.4197, + "step": 3512 + }, + { + "epoch": 0.37, + "learning_rate": 1.5921886837527638e-05, + "loss": 1.4456, + "step": 3513 + }, + { + "epoch": 0.37, + "learning_rate": 1.5918937013825823e-05, + "loss": 1.4394, + "step": 3514 + }, + { + "epoch": 0.37, + "learning_rate": 1.5915986397138526e-05, + "loss": 1.3606, + "step": 3515 + }, + { + "epoch": 0.37, + "learning_rate": 1.591303498786106e-05, + "loss": 1.4382, + "step": 3516 + }, + { + "epoch": 0.37, + "learning_rate": 1.591008278638884e-05, + "loss": 1.4185, + "step": 3517 + }, + { + "epoch": 0.37, + "learning_rate": 1.5907129793117374e-05, + "loss": 1.6692, + "step": 3518 + }, + { + "epoch": 0.37, + "learning_rate": 1.59041760084423e-05, + "loss": 1.501, + "step": 3519 + }, + { + "epoch": 0.37, + "learning_rate": 1.5901221432759345e-05, + "loss": 1.5753, + "step": 3520 + }, + { + "epoch": 0.37, + "learning_rate": 1.589826606646434e-05, + "loss": 1.4795, + "step": 3521 + }, + { + "epoch": 0.37, + "learning_rate": 1.5895309909953236e-05, + "loss": 1.4379, + "step": 3522 + }, + { + "epoch": 0.37, + "learning_rate": 1.5892352963622078e-05, + "loss": 1.3426, + "step": 3523 + }, + { + "epoch": 0.37, + "learning_rate": 1.5889395227867025e-05, + "loss": 1.4048, + "step": 3524 + }, + { + "epoch": 0.37, + "learning_rate": 1.5886436703084332e-05, + "loss": 1.4303, + "step": 3525 + }, + { + "epoch": 0.37, + "learning_rate": 1.5883477389670367e-05, + "loss": 1.3684, + "step": 3526 + }, + { + "epoch": 0.37, + "learning_rate": 1.5880517288021602e-05, + "loss": 1.3701, + "step": 3527 + }, + { + "epoch": 0.37, + "learning_rate": 1.587755639853462e-05, + "loss": 1.4308, + "step": 3528 + }, + { + "epoch": 0.37, + "learning_rate": 1.5874594721606096e-05, + "loss": 1.3981, + "step": 3529 + }, + { + "epoch": 0.37, + "learning_rate": 1.5871632257632823e-05, + "loss": 1.5906, + "step": 3530 + }, + { + "epoch": 0.37, + "learning_rate": 1.5868669007011696e-05, + "loss": 1.4642, + "step": 3531 + }, + { + "epoch": 0.37, + "learning_rate": 1.586570497013971e-05, + "loss": 1.411, + "step": 3532 + }, + { + "epoch": 0.37, + "learning_rate": 1.586274014741397e-05, + "loss": 1.3942, + "step": 3533 + }, + { + "epoch": 0.37, + "learning_rate": 1.5859774539231693e-05, + "loss": 1.3952, + "step": 3534 + }, + { + "epoch": 0.37, + "learning_rate": 1.585680814599019e-05, + "loss": 1.4009, + "step": 3535 + }, + { + "epoch": 0.37, + "learning_rate": 1.585384096808688e-05, + "loss": 1.3238, + "step": 3536 + }, + { + "epoch": 0.37, + "learning_rate": 1.585087300591929e-05, + "loss": 1.346, + "step": 3537 + }, + { + "epoch": 0.37, + "learning_rate": 1.584790425988505e-05, + "loss": 1.3739, + "step": 3538 + }, + { + "epoch": 0.37, + "learning_rate": 1.5844934730381895e-05, + "loss": 1.4264, + "step": 3539 + }, + { + "epoch": 0.37, + "learning_rate": 1.5841964417807668e-05, + "loss": 1.4675, + "step": 3540 + }, + { + "epoch": 0.37, + "learning_rate": 1.5838993322560314e-05, + "loss": 1.3337, + "step": 3541 + }, + { + "epoch": 0.37, + "learning_rate": 1.5836021445037883e-05, + "loss": 1.4052, + "step": 3542 + }, + { + "epoch": 0.37, + "learning_rate": 1.583304878563853e-05, + "loss": 1.4311, + "step": 3543 + }, + { + "epoch": 0.37, + "learning_rate": 1.5830075344760513e-05, + "loss": 1.386, + "step": 3544 + }, + { + "epoch": 0.37, + "learning_rate": 1.58271011228022e-05, + "loss": 1.387, + "step": 3545 + }, + { + "epoch": 0.37, + "learning_rate": 1.582412612016206e-05, + "loss": 1.3601, + "step": 3546 + }, + { + "epoch": 0.37, + "learning_rate": 1.5821150337238663e-05, + "loss": 1.5111, + "step": 3547 + }, + { + "epoch": 0.37, + "learning_rate": 1.5818173774430697e-05, + "loss": 1.471, + "step": 3548 + }, + { + "epoch": 0.37, + "learning_rate": 1.581519643213693e-05, + "loss": 1.4442, + "step": 3549 + }, + { + "epoch": 0.37, + "learning_rate": 1.5812218310756263e-05, + "loss": 1.467, + "step": 3550 + }, + { + "epoch": 0.37, + "learning_rate": 1.5809239410687683e-05, + "loss": 1.3731, + "step": 3551 + }, + { + "epoch": 0.37, + "learning_rate": 1.5806259732330286e-05, + "loss": 1.4072, + "step": 3552 + }, + { + "epoch": 0.37, + "learning_rate": 1.5803279276083268e-05, + "loss": 1.3636, + "step": 3553 + }, + { + "epoch": 0.37, + "learning_rate": 1.5800298042345938e-05, + "loss": 1.3915, + "step": 3554 + }, + { + "epoch": 0.37, + "learning_rate": 1.5797316031517705e-05, + "loss": 1.5038, + "step": 3555 + }, + { + "epoch": 0.37, + "learning_rate": 1.5794333243998082e-05, + "loss": 1.4455, + "step": 3556 + }, + { + "epoch": 0.37, + "learning_rate": 1.5791349680186684e-05, + "loss": 1.5062, + "step": 3557 + }, + { + "epoch": 0.37, + "learning_rate": 1.5788365340483234e-05, + "loss": 1.3899, + "step": 3558 + }, + { + "epoch": 0.37, + "learning_rate": 1.5785380225287554e-05, + "loss": 1.4946, + "step": 3559 + }, + { + "epoch": 0.37, + "learning_rate": 1.5782394334999572e-05, + "loss": 1.3859, + "step": 3560 + }, + { + "epoch": 0.37, + "learning_rate": 1.577940767001933e-05, + "loss": 1.541, + "step": 3561 + }, + { + "epoch": 0.37, + "learning_rate": 1.5776420230746952e-05, + "loss": 1.4952, + "step": 3562 + }, + { + "epoch": 0.37, + "learning_rate": 1.5773432017582684e-05, + "loss": 1.6055, + "step": 3563 + }, + { + "epoch": 0.37, + "learning_rate": 1.577044303092687e-05, + "loss": 1.4661, + "step": 3564 + }, + { + "epoch": 0.37, + "learning_rate": 1.576745327117996e-05, + "loss": 1.4082, + "step": 3565 + }, + { + "epoch": 0.37, + "learning_rate": 1.5764462738742493e-05, + "loss": 1.4005, + "step": 3566 + }, + { + "epoch": 0.37, + "learning_rate": 1.5761471434015137e-05, + "loss": 1.3959, + "step": 3567 + }, + { + "epoch": 0.37, + "learning_rate": 1.5758479357398645e-05, + "loss": 1.4567, + "step": 3568 + }, + { + "epoch": 0.37, + "learning_rate": 1.575548650929388e-05, + "loss": 1.3791, + "step": 3569 + }, + { + "epoch": 0.37, + "learning_rate": 1.57524928901018e-05, + "loss": 1.4428, + "step": 3570 + }, + { + "epoch": 0.37, + "learning_rate": 1.5749498500223486e-05, + "loss": 1.3864, + "step": 3571 + }, + { + "epoch": 0.37, + "learning_rate": 1.5746503340060097e-05, + "loss": 1.4019, + "step": 3572 + }, + { + "epoch": 0.37, + "learning_rate": 1.574350741001291e-05, + "loss": 1.5436, + "step": 3573 + }, + { + "epoch": 0.37, + "learning_rate": 1.5740510710483308e-05, + "loss": 1.4637, + "step": 3574 + }, + { + "epoch": 0.37, + "learning_rate": 1.5737513241872767e-05, + "loss": 1.5097, + "step": 3575 + }, + { + "epoch": 0.38, + "learning_rate": 1.5734515004582873e-05, + "loss": 1.5143, + "step": 3576 + }, + { + "epoch": 0.38, + "learning_rate": 1.5731515999015315e-05, + "loss": 1.3926, + "step": 3577 + }, + { + "epoch": 0.38, + "learning_rate": 1.5728516225571874e-05, + "loss": 1.4242, + "step": 3578 + }, + { + "epoch": 0.38, + "learning_rate": 1.5725515684654453e-05, + "loss": 1.4429, + "step": 3579 + }, + { + "epoch": 0.38, + "learning_rate": 1.572251437666504e-05, + "loss": 1.4638, + "step": 3580 + }, + { + "epoch": 0.38, + "learning_rate": 1.5719512302005735e-05, + "loss": 1.3381, + "step": 3581 + }, + { + "epoch": 0.38, + "learning_rate": 1.571650946107874e-05, + "loss": 1.4342, + "step": 3582 + }, + { + "epoch": 0.38, + "eval_loss": 1.4705015420913696, + "eval_runtime": 77.3664, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 3582 + }, + { + "epoch": 0.38, + "learning_rate": 1.571350585428636e-05, + "loss": 1.3991, + "step": 3583 + }, + { + "epoch": 0.38, + "learning_rate": 1.5710501482030998e-05, + "loss": 1.4274, + "step": 3584 + }, + { + "epoch": 0.38, + "learning_rate": 1.5707496344715166e-05, + "loss": 1.438, + "step": 3585 + }, + { + "epoch": 0.38, + "learning_rate": 1.570449044274147e-05, + "loss": 1.4453, + "step": 3586 + }, + { + "epoch": 0.38, + "learning_rate": 1.570148377651263e-05, + "loss": 1.4022, + "step": 3587 + }, + { + "epoch": 0.38, + "learning_rate": 1.5698476346431454e-05, + "loss": 1.4312, + "step": 3588 + }, + { + "epoch": 0.38, + "learning_rate": 1.569546815290087e-05, + "loss": 1.4329, + "step": 3589 + }, + { + "epoch": 0.38, + "learning_rate": 1.569245919632389e-05, + "loss": 1.4036, + "step": 3590 + }, + { + "epoch": 0.38, + "learning_rate": 1.5689449477103644e-05, + "loss": 1.412, + "step": 3591 + }, + { + "epoch": 0.38, + "learning_rate": 1.5686438995643353e-05, + "loss": 1.4492, + "step": 3592 + }, + { + "epoch": 0.38, + "learning_rate": 1.5683427752346343e-05, + "loss": 1.4555, + "step": 3593 + }, + { + "epoch": 0.38, + "learning_rate": 1.5680415747616047e-05, + "loss": 1.5594, + "step": 3594 + }, + { + "epoch": 0.38, + "learning_rate": 1.5677402981855993e-05, + "loss": 1.4813, + "step": 3595 + }, + { + "epoch": 0.38, + "learning_rate": 1.567438945546982e-05, + "loss": 1.5919, + "step": 3596 + }, + { + "epoch": 0.38, + "learning_rate": 1.5671375168861255e-05, + "loss": 1.4235, + "step": 3597 + }, + { + "epoch": 0.38, + "learning_rate": 1.5668360122434135e-05, + "loss": 1.441, + "step": 3598 + }, + { + "epoch": 0.38, + "learning_rate": 1.566534431659241e-05, + "loss": 1.5847, + "step": 3599 + }, + { + "epoch": 0.38, + "learning_rate": 1.566232775174011e-05, + "loss": 1.6123, + "step": 3600 + }, + { + "epoch": 0.38, + "learning_rate": 1.5659310428281374e-05, + "loss": 1.4916, + "step": 3601 + }, + { + "epoch": 0.38, + "learning_rate": 1.5656292346620457e-05, + "loss": 1.4603, + "step": 3602 + }, + { + "epoch": 0.38, + "learning_rate": 1.56532735071617e-05, + "loss": 1.4423, + "step": 3603 + }, + { + "epoch": 0.38, + "learning_rate": 1.5650253910309547e-05, + "loss": 1.4814, + "step": 3604 + }, + { + "epoch": 0.38, + "learning_rate": 1.5647233556468552e-05, + "loss": 1.4015, + "step": 3605 + }, + { + "epoch": 0.38, + "learning_rate": 1.564421244604336e-05, + "loss": 1.3798, + "step": 3606 + }, + { + "epoch": 0.38, + "learning_rate": 1.5641190579438723e-05, + "loss": 1.4259, + "step": 3607 + }, + { + "epoch": 0.38, + "learning_rate": 1.5638167957059493e-05, + "loss": 1.3493, + "step": 3608 + }, + { + "epoch": 0.38, + "learning_rate": 1.5635144579310626e-05, + "loss": 1.3433, + "step": 3609 + }, + { + "epoch": 0.38, + "learning_rate": 1.5632120446597177e-05, + "loss": 1.4661, + "step": 3610 + }, + { + "epoch": 0.38, + "learning_rate": 1.5629095559324297e-05, + "loss": 1.4205, + "step": 3611 + }, + { + "epoch": 0.38, + "learning_rate": 1.562606991789725e-05, + "loss": 1.3976, + "step": 3612 + }, + { + "epoch": 0.38, + "learning_rate": 1.5623043522721393e-05, + "loss": 1.4261, + "step": 3613 + }, + { + "epoch": 0.38, + "learning_rate": 1.562001637420218e-05, + "loss": 1.4358, + "step": 3614 + }, + { + "epoch": 0.38, + "learning_rate": 1.5616988472745175e-05, + "loss": 1.437, + "step": 3615 + }, + { + "epoch": 0.38, + "learning_rate": 1.561395981875604e-05, + "loss": 1.3735, + "step": 3616 + }, + { + "epoch": 0.38, + "learning_rate": 1.5610930412640532e-05, + "loss": 1.4357, + "step": 3617 + }, + { + "epoch": 0.38, + "learning_rate": 1.560790025480452e-05, + "loss": 1.4003, + "step": 3618 + }, + { + "epoch": 0.38, + "learning_rate": 1.5604869345653965e-05, + "loss": 1.4127, + "step": 3619 + }, + { + "epoch": 0.38, + "learning_rate": 1.5601837685594927e-05, + "loss": 1.4666, + "step": 3620 + }, + { + "epoch": 0.38, + "learning_rate": 1.5598805275033574e-05, + "loss": 1.4106, + "step": 3621 + }, + { + "epoch": 0.38, + "learning_rate": 1.5595772114376174e-05, + "loss": 1.3857, + "step": 3622 + }, + { + "epoch": 0.38, + "learning_rate": 1.5592738204029086e-05, + "loss": 1.4704, + "step": 3623 + }, + { + "epoch": 0.38, + "learning_rate": 1.558970354439878e-05, + "loss": 1.4649, + "step": 3624 + }, + { + "epoch": 0.38, + "learning_rate": 1.5586668135891824e-05, + "loss": 1.4812, + "step": 3625 + }, + { + "epoch": 0.38, + "learning_rate": 1.5583631978914882e-05, + "loss": 1.3507, + "step": 3626 + }, + { + "epoch": 0.38, + "learning_rate": 1.5580595073874718e-05, + "loss": 1.3762, + "step": 3627 + }, + { + "epoch": 0.38, + "learning_rate": 1.557755742117821e-05, + "loss": 1.4169, + "step": 3628 + }, + { + "epoch": 0.38, + "learning_rate": 1.557451902123231e-05, + "loss": 1.4098, + "step": 3629 + }, + { + "epoch": 0.38, + "learning_rate": 1.55714798744441e-05, + "loss": 1.5526, + "step": 3630 + }, + { + "epoch": 0.38, + "learning_rate": 1.556843998122074e-05, + "loss": 1.4414, + "step": 3631 + }, + { + "epoch": 0.38, + "learning_rate": 1.5565399341969497e-05, + "loss": 1.4134, + "step": 3632 + }, + { + "epoch": 0.38, + "learning_rate": 1.556235795709774e-05, + "loss": 1.4718, + "step": 3633 + }, + { + "epoch": 0.38, + "learning_rate": 1.5559315827012937e-05, + "loss": 1.412, + "step": 3634 + }, + { + "epoch": 0.38, + "learning_rate": 1.5556272952122657e-05, + "loss": 1.4119, + "step": 3635 + }, + { + "epoch": 0.38, + "learning_rate": 1.5553229332834564e-05, + "loss": 1.3999, + "step": 3636 + }, + { + "epoch": 0.38, + "learning_rate": 1.5550184969556428e-05, + "loss": 1.4626, + "step": 3637 + }, + { + "epoch": 0.38, + "learning_rate": 1.5547139862696113e-05, + "loss": 1.3811, + "step": 3638 + }, + { + "epoch": 0.38, + "learning_rate": 1.5544094012661583e-05, + "loss": 1.4053, + "step": 3639 + }, + { + "epoch": 0.38, + "learning_rate": 1.5541047419860907e-05, + "loss": 1.4059, + "step": 3640 + }, + { + "epoch": 0.38, + "learning_rate": 1.553800008470225e-05, + "loss": 1.4717, + "step": 3641 + }, + { + "epoch": 0.38, + "learning_rate": 1.553495200759388e-05, + "loss": 1.399, + "step": 3642 + }, + { + "epoch": 0.38, + "learning_rate": 1.5531903188944154e-05, + "loss": 1.4143, + "step": 3643 + }, + { + "epoch": 0.38, + "learning_rate": 1.5528853629161536e-05, + "loss": 1.4414, + "step": 3644 + }, + { + "epoch": 0.38, + "learning_rate": 1.5525803328654592e-05, + "loss": 1.4206, + "step": 3645 + }, + { + "epoch": 0.38, + "learning_rate": 1.5522752287831982e-05, + "loss": 1.3869, + "step": 3646 + }, + { + "epoch": 0.38, + "learning_rate": 1.551970050710247e-05, + "loss": 1.5434, + "step": 3647 + }, + { + "epoch": 0.38, + "learning_rate": 1.5516647986874914e-05, + "loss": 1.4574, + "step": 3648 + }, + { + "epoch": 0.38, + "learning_rate": 1.5513594727558273e-05, + "loss": 1.4353, + "step": 3649 + }, + { + "epoch": 0.38, + "learning_rate": 1.5510540729561606e-05, + "loss": 1.4122, + "step": 3650 + }, + { + "epoch": 0.38, + "learning_rate": 1.550748599329407e-05, + "loss": 1.4077, + "step": 3651 + }, + { + "epoch": 0.38, + "learning_rate": 1.550443051916492e-05, + "loss": 1.4433, + "step": 3652 + }, + { + "epoch": 0.38, + "learning_rate": 1.5501374307583514e-05, + "loss": 1.54, + "step": 3653 + }, + { + "epoch": 0.38, + "learning_rate": 1.5498317358959302e-05, + "loss": 1.4522, + "step": 3654 + }, + { + "epoch": 0.38, + "learning_rate": 1.5495259673701842e-05, + "loss": 1.4175, + "step": 3655 + }, + { + "epoch": 0.38, + "learning_rate": 1.5492201252220777e-05, + "loss": 1.4637, + "step": 3656 + }, + { + "epoch": 0.38, + "learning_rate": 1.5489142094925863e-05, + "loss": 1.4701, + "step": 3657 + }, + { + "epoch": 0.38, + "learning_rate": 1.548608220222695e-05, + "loss": 1.4095, + "step": 3658 + }, + { + "epoch": 0.38, + "learning_rate": 1.548302157453398e-05, + "loss": 1.3903, + "step": 3659 + }, + { + "epoch": 0.38, + "learning_rate": 1.5479960212257002e-05, + "loss": 1.4062, + "step": 3660 + }, + { + "epoch": 0.38, + "learning_rate": 1.5476898115806157e-05, + "loss": 1.4706, + "step": 3661 + }, + { + "epoch": 0.38, + "learning_rate": 1.547383528559169e-05, + "loss": 1.4423, + "step": 3662 + }, + { + "epoch": 0.38, + "learning_rate": 1.547077172202394e-05, + "loss": 1.4418, + "step": 3663 + }, + { + "epoch": 0.38, + "learning_rate": 1.5467707425513347e-05, + "loss": 1.4553, + "step": 3664 + }, + { + "epoch": 0.38, + "learning_rate": 1.5464642396470443e-05, + "loss": 1.435, + "step": 3665 + }, + { + "epoch": 0.38, + "learning_rate": 1.5461576635305873e-05, + "loss": 1.4105, + "step": 3666 + }, + { + "epoch": 0.38, + "learning_rate": 1.5458510142430364e-05, + "loss": 1.4118, + "step": 3667 + }, + { + "epoch": 0.38, + "learning_rate": 1.5455442918254746e-05, + "loss": 1.4096, + "step": 3668 + }, + { + "epoch": 0.38, + "learning_rate": 1.545237496318995e-05, + "loss": 1.4248, + "step": 3669 + }, + { + "epoch": 0.38, + "learning_rate": 1.5449306277647003e-05, + "loss": 1.4591, + "step": 3670 + }, + { + "epoch": 0.38, + "learning_rate": 1.544623686203703e-05, + "loss": 1.4764, + "step": 3671 + }, + { + "epoch": 0.39, + "learning_rate": 1.5443166716771255e-05, + "loss": 1.4329, + "step": 3672 + }, + { + "epoch": 0.39, + "learning_rate": 1.5440095842260995e-05, + "loss": 1.4023, + "step": 3673 + }, + { + "epoch": 0.39, + "learning_rate": 1.5437024238917674e-05, + "loss": 1.3802, + "step": 3674 + }, + { + "epoch": 0.39, + "learning_rate": 1.5433951907152806e-05, + "loss": 1.4627, + "step": 3675 + }, + { + "epoch": 0.39, + "learning_rate": 1.5430878847378e-05, + "loss": 1.5164, + "step": 3676 + }, + { + "epoch": 0.39, + "learning_rate": 1.542780506000497e-05, + "loss": 1.3546, + "step": 3677 + }, + { + "epoch": 0.39, + "learning_rate": 1.542473054544553e-05, + "loss": 1.4415, + "step": 3678 + }, + { + "epoch": 0.39, + "learning_rate": 1.5421655304111573e-05, + "loss": 1.4093, + "step": 3679 + }, + { + "epoch": 0.39, + "learning_rate": 1.5418579336415114e-05, + "loss": 1.3943, + "step": 3680 + }, + { + "epoch": 0.39, + "learning_rate": 1.5415502642768252e-05, + "loss": 1.3659, + "step": 3681 + }, + { + "epoch": 0.39, + "learning_rate": 1.541242522358318e-05, + "loss": 1.4322, + "step": 3682 + }, + { + "epoch": 0.39, + "learning_rate": 1.5409347079272198e-05, + "loss": 1.4064, + "step": 3683 + }, + { + "epoch": 0.39, + "learning_rate": 1.5406268210247693e-05, + "loss": 1.4031, + "step": 3684 + }, + { + "epoch": 0.39, + "learning_rate": 1.540318861692216e-05, + "loss": 1.3449, + "step": 3685 + }, + { + "epoch": 0.39, + "learning_rate": 1.5400108299708182e-05, + "loss": 1.5536, + "step": 3686 + }, + { + "epoch": 0.39, + "learning_rate": 1.5397027259018442e-05, + "loss": 1.4106, + "step": 3687 + }, + { + "epoch": 0.39, + "learning_rate": 1.5393945495265722e-05, + "loss": 1.4309, + "step": 3688 + }, + { + "epoch": 0.39, + "learning_rate": 1.53908630088629e-05, + "loss": 1.3765, + "step": 3689 + }, + { + "epoch": 0.39, + "learning_rate": 1.5387779800222947e-05, + "loss": 1.3809, + "step": 3690 + }, + { + "epoch": 0.39, + "learning_rate": 1.5384695869758938e-05, + "loss": 1.4758, + "step": 3691 + }, + { + "epoch": 0.39, + "learning_rate": 1.5381611217884032e-05, + "loss": 1.4249, + "step": 3692 + }, + { + "epoch": 0.39, + "learning_rate": 1.5378525845011503e-05, + "loss": 1.4133, + "step": 3693 + }, + { + "epoch": 0.39, + "learning_rate": 1.5375439751554708e-05, + "loss": 1.418, + "step": 3694 + }, + { + "epoch": 0.39, + "learning_rate": 1.53723529379271e-05, + "loss": 1.441, + "step": 3695 + }, + { + "epoch": 0.39, + "learning_rate": 1.536926540454224e-05, + "loss": 1.3919, + "step": 3696 + }, + { + "epoch": 0.39, + "learning_rate": 1.5366177151813775e-05, + "loss": 1.3722, + "step": 3697 + }, + { + "epoch": 0.39, + "learning_rate": 1.536308818015545e-05, + "loss": 1.4727, + "step": 3698 + }, + { + "epoch": 0.39, + "learning_rate": 1.535999848998111e-05, + "loss": 1.442, + "step": 3699 + }, + { + "epoch": 0.39, + "learning_rate": 1.535690808170469e-05, + "loss": 1.3884, + "step": 3700 + }, + { + "epoch": 0.39, + "learning_rate": 1.535381695574023e-05, + "loss": 1.3226, + "step": 3701 + }, + { + "epoch": 0.39, + "learning_rate": 1.535072511250186e-05, + "loss": 1.4403, + "step": 3702 + }, + { + "epoch": 0.39, + "learning_rate": 1.5347632552403808e-05, + "loss": 1.4144, + "step": 3703 + }, + { + "epoch": 0.39, + "learning_rate": 1.5344539275860395e-05, + "loss": 1.3514, + "step": 3704 + }, + { + "epoch": 0.39, + "learning_rate": 1.5341445283286044e-05, + "loss": 1.519, + "step": 3705 + }, + { + "epoch": 0.39, + "learning_rate": 1.5338350575095268e-05, + "loss": 1.4251, + "step": 3706 + }, + { + "epoch": 0.39, + "learning_rate": 1.5335255151702685e-05, + "loss": 1.392, + "step": 3707 + }, + { + "epoch": 0.39, + "learning_rate": 1.533215901352299e-05, + "loss": 1.3838, + "step": 3708 + }, + { + "epoch": 0.39, + "learning_rate": 1.532906216097099e-05, + "loss": 1.444, + "step": 3709 + }, + { + "epoch": 0.39, + "learning_rate": 1.5325964594461594e-05, + "loss": 1.3459, + "step": 3710 + }, + { + "epoch": 0.39, + "learning_rate": 1.5322866314409783e-05, + "loss": 1.4155, + "step": 3711 + }, + { + "epoch": 0.39, + "learning_rate": 1.5319767321230657e-05, + "loss": 1.4057, + "step": 3712 + }, + { + "epoch": 0.39, + "learning_rate": 1.5316667615339392e-05, + "loss": 1.382, + "step": 3713 + }, + { + "epoch": 0.39, + "learning_rate": 1.5313567197151277e-05, + "loss": 1.3634, + "step": 3714 + }, + { + "epoch": 0.39, + "learning_rate": 1.5310466067081688e-05, + "loss": 1.3434, + "step": 3715 + }, + { + "epoch": 0.39, + "learning_rate": 1.530736422554609e-05, + "loss": 1.4553, + "step": 3716 + }, + { + "epoch": 0.39, + "learning_rate": 1.5304261672960055e-05, + "loss": 1.4193, + "step": 3717 + }, + { + "epoch": 0.39, + "learning_rate": 1.5301158409739242e-05, + "loss": 1.3955, + "step": 3718 + }, + { + "epoch": 0.39, + "learning_rate": 1.5298054436299413e-05, + "loss": 1.4592, + "step": 3719 + }, + { + "epoch": 0.39, + "learning_rate": 1.529494975305642e-05, + "loss": 1.738, + "step": 3720 + }, + { + "epoch": 0.39, + "learning_rate": 1.529184436042621e-05, + "loss": 1.438, + "step": 3721 + }, + { + "epoch": 0.39, + "learning_rate": 1.528873825882482e-05, + "loss": 1.3445, + "step": 3722 + }, + { + "epoch": 0.39, + "learning_rate": 1.5285631448668395e-05, + "loss": 1.4168, + "step": 3723 + }, + { + "epoch": 0.39, + "learning_rate": 1.528252393037317e-05, + "loss": 1.4088, + "step": 3724 + }, + { + "epoch": 0.39, + "learning_rate": 1.5279415704355468e-05, + "loss": 1.4484, + "step": 3725 + }, + { + "epoch": 0.39, + "learning_rate": 1.5276306771031708e-05, + "loss": 1.4706, + "step": 3726 + }, + { + "epoch": 0.39, + "learning_rate": 1.527319713081841e-05, + "loss": 1.3466, + "step": 3727 + }, + { + "epoch": 0.39, + "learning_rate": 1.5270086784132196e-05, + "loss": 1.427, + "step": 3728 + }, + { + "epoch": 0.39, + "learning_rate": 1.5266975731389754e-05, + "loss": 1.4596, + "step": 3729 + }, + { + "epoch": 0.39, + "learning_rate": 1.52638639730079e-05, + "loss": 1.405, + "step": 3730 + }, + { + "epoch": 0.39, + "learning_rate": 1.5260751509403518e-05, + "loss": 1.4572, + "step": 3731 + }, + { + "epoch": 0.39, + "learning_rate": 1.5257638340993608e-05, + "loss": 1.3827, + "step": 3732 + }, + { + "epoch": 0.39, + "learning_rate": 1.5254524468195251e-05, + "loss": 1.3712, + "step": 3733 + }, + { + "epoch": 0.39, + "learning_rate": 1.5251409891425626e-05, + "loss": 1.4541, + "step": 3734 + }, + { + "epoch": 0.39, + "learning_rate": 1.5248294611102006e-05, + "loss": 1.5279, + "step": 3735 + }, + { + "epoch": 0.39, + "learning_rate": 1.5245178627641759e-05, + "loss": 1.3722, + "step": 3736 + }, + { + "epoch": 0.39, + "learning_rate": 1.5242061941462348e-05, + "loss": 1.5158, + "step": 3737 + }, + { + "epoch": 0.39, + "learning_rate": 1.523894455298132e-05, + "loss": 1.4274, + "step": 3738 + }, + { + "epoch": 0.39, + "learning_rate": 1.5235826462616338e-05, + "loss": 1.4543, + "step": 3739 + }, + { + "epoch": 0.39, + "learning_rate": 1.5232707670785144e-05, + "loss": 1.5011, + "step": 3740 + }, + { + "epoch": 0.39, + "learning_rate": 1.5229588177905568e-05, + "loss": 1.24, + "step": 3741 + }, + { + "epoch": 0.39, + "learning_rate": 1.5226467984395544e-05, + "loss": 1.4253, + "step": 3742 + }, + { + "epoch": 0.39, + "learning_rate": 1.5223347090673102e-05, + "loss": 1.3736, + "step": 3743 + }, + { + "epoch": 0.39, + "learning_rate": 1.522022549715636e-05, + "loss": 1.4587, + "step": 3744 + }, + { + "epoch": 0.39, + "learning_rate": 1.521710320426353e-05, + "loss": 1.5024, + "step": 3745 + }, + { + "epoch": 0.39, + "learning_rate": 1.521398021241292e-05, + "loss": 1.427, + "step": 3746 + }, + { + "epoch": 0.39, + "learning_rate": 1.5210856522022929e-05, + "loss": 1.3387, + "step": 3747 + }, + { + "epoch": 0.39, + "learning_rate": 1.5207732133512055e-05, + "loss": 1.3819, + "step": 3748 + }, + { + "epoch": 0.39, + "learning_rate": 1.5204607047298883e-05, + "loss": 1.4571, + "step": 3749 + }, + { + "epoch": 0.39, + "learning_rate": 1.5201481263802094e-05, + "loss": 1.3592, + "step": 3750 + }, + { + "epoch": 0.39, + "learning_rate": 1.5198354783440464e-05, + "loss": 1.3912, + "step": 3751 + }, + { + "epoch": 0.39, + "learning_rate": 1.519522760663286e-05, + "loss": 1.4986, + "step": 3752 + }, + { + "epoch": 0.39, + "learning_rate": 1.5192099733798243e-05, + "loss": 1.4106, + "step": 3753 + }, + { + "epoch": 0.39, + "learning_rate": 1.5188971165355667e-05, + "loss": 1.4145, + "step": 3754 + }, + { + "epoch": 0.39, + "learning_rate": 1.5185841901724282e-05, + "loss": 1.3915, + "step": 3755 + }, + { + "epoch": 0.39, + "learning_rate": 1.5182711943323329e-05, + "loss": 1.4014, + "step": 3756 + }, + { + "epoch": 0.39, + "learning_rate": 1.5179581290572141e-05, + "loss": 1.3651, + "step": 3757 + }, + { + "epoch": 0.39, + "learning_rate": 1.5176449943890147e-05, + "loss": 1.3653, + "step": 3758 + }, + { + "epoch": 0.39, + "learning_rate": 1.5173317903696862e-05, + "loss": 1.4486, + "step": 3759 + }, + { + "epoch": 0.39, + "learning_rate": 1.5170185170411906e-05, + "loss": 1.4459, + "step": 3760 + }, + { + "epoch": 0.39, + "learning_rate": 1.5167051744454977e-05, + "loss": 1.4215, + "step": 3761 + }, + { + "epoch": 0.39, + "learning_rate": 1.5163917626245877e-05, + "loss": 1.4379, + "step": 3762 + }, + { + "epoch": 0.39, + "learning_rate": 1.51607828162045e-05, + "loss": 1.4147, + "step": 3763 + }, + { + "epoch": 0.39, + "learning_rate": 1.5157647314750827e-05, + "loss": 1.4011, + "step": 3764 + }, + { + "epoch": 0.39, + "learning_rate": 1.5154511122304936e-05, + "loss": 1.4309, + "step": 3765 + }, + { + "epoch": 0.39, + "learning_rate": 1.5151374239286993e-05, + "loss": 1.4382, + "step": 3766 + }, + { + "epoch": 0.4, + "learning_rate": 1.5148236666117266e-05, + "loss": 1.405, + "step": 3767 + }, + { + "epoch": 0.4, + "learning_rate": 1.5145098403216104e-05, + "loss": 1.4223, + "step": 3768 + }, + { + "epoch": 0.4, + "learning_rate": 1.5141959451003951e-05, + "loss": 1.4084, + "step": 3769 + }, + { + "epoch": 0.4, + "learning_rate": 1.5138819809901356e-05, + "loss": 1.4063, + "step": 3770 + }, + { + "epoch": 0.4, + "learning_rate": 1.513567948032894e-05, + "loss": 1.3299, + "step": 3771 + }, + { + "epoch": 0.4, + "learning_rate": 1.5132538462707431e-05, + "loss": 1.3901, + "step": 3772 + }, + { + "epoch": 0.4, + "learning_rate": 1.5129396757457646e-05, + "loss": 1.4249, + "step": 3773 + }, + { + "epoch": 0.4, + "learning_rate": 1.512625436500049e-05, + "loss": 1.4087, + "step": 3774 + }, + { + "epoch": 0.4, + "learning_rate": 1.5123111285756964e-05, + "loss": 1.3521, + "step": 3775 + }, + { + "epoch": 0.4, + "learning_rate": 1.5119967520148163e-05, + "loss": 1.4097, + "step": 3776 + }, + { + "epoch": 0.4, + "learning_rate": 1.5116823068595261e-05, + "loss": 1.4871, + "step": 3777 + }, + { + "epoch": 0.4, + "learning_rate": 1.5113677931519543e-05, + "loss": 1.44, + "step": 3778 + }, + { + "epoch": 0.4, + "learning_rate": 1.5110532109342377e-05, + "loss": 1.4518, + "step": 3779 + }, + { + "epoch": 0.4, + "learning_rate": 1.5107385602485214e-05, + "loss": 1.3961, + "step": 3780 + }, + { + "epoch": 0.4, + "learning_rate": 1.5104238411369614e-05, + "loss": 1.4341, + "step": 3781 + }, + { + "epoch": 0.4, + "eval_loss": 1.4642821550369263, + "eval_runtime": 77.3595, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 3781 + }, + { + "epoch": 0.4, + "learning_rate": 1.5101090536417218e-05, + "loss": 1.403, + "step": 3782 + }, + { + "epoch": 0.4, + "learning_rate": 1.5097941978049754e-05, + "loss": 1.4103, + "step": 3783 + }, + { + "epoch": 0.4, + "learning_rate": 1.5094792736689052e-05, + "loss": 1.3478, + "step": 3784 + }, + { + "epoch": 0.4, + "learning_rate": 1.5091642812757035e-05, + "loss": 1.4134, + "step": 3785 + }, + { + "epoch": 0.4, + "learning_rate": 1.5088492206675701e-05, + "loss": 1.4134, + "step": 3786 + }, + { + "epoch": 0.4, + "learning_rate": 1.5085340918867162e-05, + "loss": 1.1494, + "step": 3787 + }, + { + "epoch": 0.4, + "learning_rate": 1.5082188949753598e-05, + "loss": 1.2385, + "step": 3788 + }, + { + "epoch": 0.4, + "learning_rate": 1.5079036299757299e-05, + "loss": 1.4258, + "step": 3789 + }, + { + "epoch": 0.4, + "learning_rate": 1.5075882969300639e-05, + "loss": 1.3781, + "step": 3790 + }, + { + "epoch": 0.4, + "learning_rate": 1.507272895880608e-05, + "loss": 1.5096, + "step": 3791 + }, + { + "epoch": 0.4, + "learning_rate": 1.5069574268696179e-05, + "loss": 1.366, + "step": 3792 + }, + { + "epoch": 0.4, + "learning_rate": 1.5066418899393584e-05, + "loss": 1.3792, + "step": 3793 + }, + { + "epoch": 0.4, + "learning_rate": 1.506326285132104e-05, + "loss": 1.4987, + "step": 3794 + }, + { + "epoch": 0.4, + "learning_rate": 1.5060106124901364e-05, + "loss": 1.445, + "step": 3795 + }, + { + "epoch": 0.4, + "learning_rate": 1.5056948720557482e-05, + "loss": 1.5071, + "step": 3796 + }, + { + "epoch": 0.4, + "learning_rate": 1.505379063871241e-05, + "loss": 1.4029, + "step": 3797 + }, + { + "epoch": 0.4, + "learning_rate": 1.5050631879789244e-05, + "loss": 1.5263, + "step": 3798 + }, + { + "epoch": 0.4, + "learning_rate": 1.5047472444211175e-05, + "loss": 1.3906, + "step": 3799 + }, + { + "epoch": 0.4, + "learning_rate": 1.5044312332401494e-05, + "loss": 1.7352, + "step": 3800 + }, + { + "epoch": 0.4, + "learning_rate": 1.5041151544783565e-05, + "loss": 1.3946, + "step": 3801 + }, + { + "epoch": 0.4, + "learning_rate": 1.5037990081780862e-05, + "loss": 1.3592, + "step": 3802 + }, + { + "epoch": 0.4, + "learning_rate": 1.503482794381693e-05, + "loss": 1.3991, + "step": 3803 + }, + { + "epoch": 0.4, + "learning_rate": 1.5031665131315423e-05, + "loss": 1.4271, + "step": 3804 + }, + { + "epoch": 0.4, + "learning_rate": 1.502850164470007e-05, + "loss": 1.4305, + "step": 3805 + }, + { + "epoch": 0.4, + "learning_rate": 1.5025337484394701e-05, + "loss": 1.4116, + "step": 3806 + }, + { + "epoch": 0.4, + "learning_rate": 1.5022172650823232e-05, + "loss": 1.4242, + "step": 3807 + }, + { + "epoch": 0.4, + "learning_rate": 1.5019007144409667e-05, + "loss": 1.4427, + "step": 3808 + }, + { + "epoch": 0.4, + "learning_rate": 1.5015840965578106e-05, + "loss": 1.3705, + "step": 3809 + }, + { + "epoch": 0.4, + "learning_rate": 1.5012674114752732e-05, + "loss": 1.4498, + "step": 3810 + }, + { + "epoch": 0.4, + "learning_rate": 1.5009506592357822e-05, + "loss": 1.489, + "step": 3811 + }, + { + "epoch": 0.4, + "learning_rate": 1.5006338398817746e-05, + "loss": 1.4801, + "step": 3812 + }, + { + "epoch": 0.4, + "learning_rate": 1.5003169534556956e-05, + "loss": 1.3468, + "step": 3813 + }, + { + "epoch": 0.4, + "learning_rate": 1.5000000000000002e-05, + "loss": 1.4211, + "step": 3814 + }, + { + "epoch": 0.4, + "learning_rate": 1.4996829795571518e-05, + "loss": 1.4683, + "step": 3815 + }, + { + "epoch": 0.4, + "learning_rate": 1.499365892169623e-05, + "loss": 1.4441, + "step": 3816 + }, + { + "epoch": 0.4, + "learning_rate": 1.4990487378798958e-05, + "loss": 1.4368, + "step": 3817 + }, + { + "epoch": 0.4, + "learning_rate": 1.4987315167304602e-05, + "loss": 1.4097, + "step": 3818 + }, + { + "epoch": 0.4, + "learning_rate": 1.4984142287638155e-05, + "loss": 1.4238, + "step": 3819 + }, + { + "epoch": 0.4, + "learning_rate": 1.4980968740224708e-05, + "loss": 1.497, + "step": 3820 + }, + { + "epoch": 0.4, + "learning_rate": 1.4977794525489433e-05, + "loss": 1.3989, + "step": 3821 + }, + { + "epoch": 0.4, + "learning_rate": 1.4974619643857588e-05, + "loss": 1.4415, + "step": 3822 + }, + { + "epoch": 0.4, + "learning_rate": 1.4971444095754533e-05, + "loss": 1.3931, + "step": 3823 + }, + { + "epoch": 0.4, + "learning_rate": 1.4968267881605705e-05, + "loss": 1.3426, + "step": 3824 + }, + { + "epoch": 0.4, + "learning_rate": 1.4965091001836636e-05, + "loss": 1.644, + "step": 3825 + }, + { + "epoch": 0.4, + "learning_rate": 1.4961913456872945e-05, + "loss": 1.3903, + "step": 3826 + }, + { + "epoch": 0.4, + "learning_rate": 1.4958735247140345e-05, + "loss": 1.3764, + "step": 3827 + }, + { + "epoch": 0.4, + "learning_rate": 1.4955556373064632e-05, + "loss": 1.5484, + "step": 3828 + }, + { + "epoch": 0.4, + "learning_rate": 1.4952376835071696e-05, + "loss": 1.5696, + "step": 3829 + }, + { + "epoch": 0.4, + "learning_rate": 1.4949196633587509e-05, + "loss": 1.3844, + "step": 3830 + }, + { + "epoch": 0.4, + "learning_rate": 1.494601576903814e-05, + "loss": 1.3868, + "step": 3831 + }, + { + "epoch": 0.4, + "learning_rate": 1.4942834241849741e-05, + "loss": 1.4229, + "step": 3832 + }, + { + "epoch": 0.4, + "learning_rate": 1.4939652052448557e-05, + "loss": 1.4062, + "step": 3833 + }, + { + "epoch": 0.4, + "learning_rate": 1.4936469201260915e-05, + "loss": 1.3955, + "step": 3834 + }, + { + "epoch": 0.4, + "learning_rate": 1.4933285688713239e-05, + "loss": 1.3959, + "step": 3835 + }, + { + "epoch": 0.4, + "learning_rate": 1.4930101515232038e-05, + "loss": 1.4652, + "step": 3836 + }, + { + "epoch": 0.4, + "learning_rate": 1.4926916681243913e-05, + "loss": 1.5253, + "step": 3837 + }, + { + "epoch": 0.4, + "learning_rate": 1.4923731187175539e-05, + "loss": 1.4694, + "step": 3838 + }, + { + "epoch": 0.4, + "learning_rate": 1.4920545033453702e-05, + "loss": 1.3859, + "step": 3839 + }, + { + "epoch": 0.4, + "learning_rate": 1.4917358220505259e-05, + "loss": 1.4157, + "step": 3840 + }, + { + "epoch": 0.4, + "learning_rate": 1.4914170748757159e-05, + "loss": 1.4491, + "step": 3841 + }, + { + "epoch": 0.4, + "learning_rate": 1.4910982618636445e-05, + "loss": 1.4464, + "step": 3842 + }, + { + "epoch": 0.4, + "learning_rate": 1.4907793830570246e-05, + "loss": 1.3771, + "step": 3843 + }, + { + "epoch": 0.4, + "learning_rate": 1.4904604384985775e-05, + "loss": 1.3673, + "step": 3844 + }, + { + "epoch": 0.4, + "learning_rate": 1.4901414282310334e-05, + "loss": 1.4429, + "step": 3845 + }, + { + "epoch": 0.4, + "learning_rate": 1.4898223522971318e-05, + "loss": 1.4905, + "step": 3846 + }, + { + "epoch": 0.4, + "learning_rate": 1.4895032107396205e-05, + "loss": 1.4039, + "step": 3847 + }, + { + "epoch": 0.4, + "learning_rate": 1.4891840036012566e-05, + "loss": 1.4082, + "step": 3848 + }, + { + "epoch": 0.4, + "learning_rate": 1.4888647309248052e-05, + "loss": 1.3643, + "step": 3849 + }, + { + "epoch": 0.4, + "learning_rate": 1.4885453927530408e-05, + "loss": 1.3116, + "step": 3850 + }, + { + "epoch": 0.4, + "learning_rate": 1.4882259891287467e-05, + "loss": 1.4278, + "step": 3851 + }, + { + "epoch": 0.4, + "learning_rate": 1.4879065200947148e-05, + "loss": 1.3712, + "step": 3852 + }, + { + "epoch": 0.4, + "learning_rate": 1.4875869856937449e-05, + "loss": 1.387, + "step": 3853 + }, + { + "epoch": 0.4, + "learning_rate": 1.4872673859686475e-05, + "loss": 1.5053, + "step": 3854 + }, + { + "epoch": 0.4, + "learning_rate": 1.4869477209622404e-05, + "loss": 1.4427, + "step": 3855 + }, + { + "epoch": 0.4, + "learning_rate": 1.4866279907173502e-05, + "loss": 1.3404, + "step": 3856 + }, + { + "epoch": 0.4, + "learning_rate": 1.4863081952768126e-05, + "loss": 1.3126, + "step": 3857 + }, + { + "epoch": 0.4, + "learning_rate": 1.4859883346834725e-05, + "loss": 1.4588, + "step": 3858 + }, + { + "epoch": 0.4, + "learning_rate": 1.4856684089801822e-05, + "loss": 1.408, + "step": 3859 + }, + { + "epoch": 0.4, + "learning_rate": 1.4853484182098044e-05, + "loss": 1.4356, + "step": 3860 + }, + { + "epoch": 0.4, + "learning_rate": 1.4850283624152088e-05, + "loss": 1.3768, + "step": 3861 + }, + { + "epoch": 0.4, + "learning_rate": 1.4847082416392753e-05, + "loss": 1.4563, + "step": 3862 + }, + { + "epoch": 0.41, + "learning_rate": 1.4843880559248915e-05, + "loss": 1.3648, + "step": 3863 + }, + { + "epoch": 0.41, + "learning_rate": 1.4840678053149542e-05, + "loss": 1.4146, + "step": 3864 + }, + { + "epoch": 0.41, + "learning_rate": 1.4837474898523686e-05, + "loss": 1.4423, + "step": 3865 + }, + { + "epoch": 0.41, + "learning_rate": 1.4834271095800487e-05, + "loss": 1.3351, + "step": 3866 + }, + { + "epoch": 0.41, + "learning_rate": 1.4831066645409178e-05, + "loss": 1.4534, + "step": 3867 + }, + { + "epoch": 0.41, + "learning_rate": 1.4827861547779066e-05, + "loss": 1.4763, + "step": 3868 + }, + { + "epoch": 0.41, + "learning_rate": 1.4824655803339553e-05, + "loss": 1.4019, + "step": 3869 + }, + { + "epoch": 0.41, + "learning_rate": 1.4821449412520132e-05, + "loss": 1.4223, + "step": 3870 + }, + { + "epoch": 0.41, + "learning_rate": 1.4818242375750371e-05, + "loss": 1.4065, + "step": 3871 + }, + { + "epoch": 0.41, + "learning_rate": 1.481503469345993e-05, + "loss": 1.587, + "step": 3872 + }, + { + "epoch": 0.41, + "learning_rate": 1.4811826366078562e-05, + "loss": 1.3746, + "step": 3873 + }, + { + "epoch": 0.41, + "learning_rate": 1.4808617394036096e-05, + "loss": 1.3425, + "step": 3874 + }, + { + "epoch": 0.41, + "learning_rate": 1.480540777776245e-05, + "loss": 0.6637, + "step": 3875 + }, + { + "epoch": 0.41, + "learning_rate": 1.4802197517687634e-05, + "loss": 1.3366, + "step": 3876 + }, + { + "epoch": 0.41, + "learning_rate": 1.479898661424174e-05, + "loss": 1.4033, + "step": 3877 + }, + { + "epoch": 0.41, + "learning_rate": 1.4795775067854947e-05, + "loss": 1.4005, + "step": 3878 + }, + { + "epoch": 0.41, + "learning_rate": 1.4792562878957516e-05, + "loss": 1.3651, + "step": 3879 + }, + { + "epoch": 0.41, + "learning_rate": 1.47893500479798e-05, + "loss": 1.4185, + "step": 3880 + }, + { + "epoch": 0.41, + "learning_rate": 1.4786136575352236e-05, + "loss": 1.4394, + "step": 3881 + }, + { + "epoch": 0.41, + "learning_rate": 1.478292246150535e-05, + "loss": 1.7243, + "step": 3882 + }, + { + "epoch": 0.41, + "learning_rate": 1.4779707706869744e-05, + "loss": 1.3574, + "step": 3883 + }, + { + "epoch": 0.41, + "learning_rate": 1.4776492311876116e-05, + "loss": 1.4031, + "step": 3884 + }, + { + "epoch": 0.41, + "learning_rate": 1.4773276276955248e-05, + "loss": 1.4351, + "step": 3885 + }, + { + "epoch": 0.41, + "learning_rate": 1.4770059602538002e-05, + "loss": 1.3922, + "step": 3886 + }, + { + "epoch": 0.41, + "learning_rate": 1.4766842289055333e-05, + "loss": 1.3374, + "step": 3887 + }, + { + "epoch": 0.41, + "learning_rate": 1.4763624336938278e-05, + "loss": 1.428, + "step": 3888 + }, + { + "epoch": 0.41, + "learning_rate": 1.476040574661796e-05, + "loss": 1.6087, + "step": 3889 + }, + { + "epoch": 0.41, + "learning_rate": 1.4757186518525586e-05, + "loss": 1.4054, + "step": 3890 + }, + { + "epoch": 0.41, + "learning_rate": 1.4753966653092447e-05, + "loss": 1.2595, + "step": 3891 + }, + { + "epoch": 0.41, + "learning_rate": 1.475074615074993e-05, + "loss": 1.4052, + "step": 3892 + }, + { + "epoch": 0.41, + "learning_rate": 1.4747525011929492e-05, + "loss": 1.4296, + "step": 3893 + }, + { + "epoch": 0.41, + "learning_rate": 1.4744303237062689e-05, + "loss": 1.3718, + "step": 3894 + }, + { + "epoch": 0.41, + "learning_rate": 1.4741080826581151e-05, + "loss": 1.4498, + "step": 3895 + }, + { + "epoch": 0.41, + "learning_rate": 1.4737857780916602e-05, + "loss": 1.4029, + "step": 3896 + }, + { + "epoch": 0.41, + "learning_rate": 1.4734634100500846e-05, + "loss": 1.4136, + "step": 3897 + }, + { + "epoch": 0.41, + "learning_rate": 1.4731409785765774e-05, + "loss": 1.348, + "step": 3898 + }, + { + "epoch": 0.41, + "learning_rate": 1.4728184837143355e-05, + "loss": 1.3407, + "step": 3899 + }, + { + "epoch": 0.41, + "learning_rate": 1.472495925506566e-05, + "loss": 1.3737, + "step": 3900 + }, + { + "epoch": 0.41, + "learning_rate": 1.4721733039964826e-05, + "loss": 2.2305, + "step": 3901 + }, + { + "epoch": 0.41, + "learning_rate": 1.4718506192273087e-05, + "loss": 1.4506, + "step": 3902 + }, + { + "epoch": 0.41, + "learning_rate": 1.4715278712422754e-05, + "loss": 1.3657, + "step": 3903 + }, + { + "epoch": 0.41, + "learning_rate": 1.471205060084623e-05, + "loss": 1.4644, + "step": 3904 + }, + { + "epoch": 0.41, + "learning_rate": 1.4708821857976001e-05, + "loss": 1.4823, + "step": 3905 + }, + { + "epoch": 0.41, + "learning_rate": 1.4705592484244628e-05, + "loss": 1.3392, + "step": 3906 + }, + { + "epoch": 0.41, + "learning_rate": 1.4702362480084769e-05, + "loss": 1.3302, + "step": 3907 + }, + { + "epoch": 0.41, + "learning_rate": 1.4699131845929163e-05, + "loss": 1.8952, + "step": 3908 + }, + { + "epoch": 0.41, + "learning_rate": 1.469590058221063e-05, + "loss": 1.4982, + "step": 3909 + }, + { + "epoch": 0.41, + "learning_rate": 1.4692668689362074e-05, + "loss": 1.407, + "step": 3910 + }, + { + "epoch": 0.41, + "learning_rate": 1.4689436167816489e-05, + "loss": 1.3911, + "step": 3911 + }, + { + "epoch": 0.41, + "learning_rate": 1.4686203018006948e-05, + "loss": 1.3421, + "step": 3912 + }, + { + "epoch": 0.41, + "learning_rate": 1.4682969240366612e-05, + "loss": 1.4627, + "step": 3913 + }, + { + "epoch": 0.41, + "learning_rate": 1.4679734835328718e-05, + "loss": 1.394, + "step": 3914 + }, + { + "epoch": 0.41, + "learning_rate": 1.4676499803326603e-05, + "loss": 1.4484, + "step": 3915 + }, + { + "epoch": 0.41, + "learning_rate": 1.4673264144793673e-05, + "loss": 1.4665, + "step": 3916 + }, + { + "epoch": 0.41, + "learning_rate": 1.4670027860163422e-05, + "loss": 1.3191, + "step": 3917 + }, + { + "epoch": 0.41, + "learning_rate": 1.466679094986943e-05, + "loss": 1.4748, + "step": 3918 + }, + { + "epoch": 0.41, + "learning_rate": 1.4663553414345361e-05, + "loss": 1.2467, + "step": 3919 + }, + { + "epoch": 0.41, + "learning_rate": 1.466031525402496e-05, + "loss": 1.4279, + "step": 3920 + }, + { + "epoch": 0.41, + "learning_rate": 1.4657076469342059e-05, + "loss": 1.3822, + "step": 3921 + }, + { + "epoch": 0.41, + "learning_rate": 1.4653837060730566e-05, + "loss": 1.3659, + "step": 3922 + }, + { + "epoch": 0.41, + "learning_rate": 1.465059702862449e-05, + "loss": 1.3663, + "step": 3923 + }, + { + "epoch": 0.41, + "learning_rate": 1.4647356373457902e-05, + "loss": 1.4371, + "step": 3924 + }, + { + "epoch": 0.41, + "learning_rate": 1.4644115095664972e-05, + "loss": 1.3473, + "step": 3925 + }, + { + "epoch": 0.41, + "learning_rate": 1.4640873195679944e-05, + "loss": 1.4797, + "step": 3926 + }, + { + "epoch": 0.41, + "learning_rate": 1.463763067393715e-05, + "loss": 1.3973, + "step": 3927 + }, + { + "epoch": 0.41, + "learning_rate": 1.4634387530871008e-05, + "loss": 1.3899, + "step": 3928 + }, + { + "epoch": 0.41, + "learning_rate": 1.4631143766916015e-05, + "loss": 1.3828, + "step": 3929 + }, + { + "epoch": 0.41, + "learning_rate": 1.4627899382506745e-05, + "loss": 1.4569, + "step": 3930 + }, + { + "epoch": 0.41, + "learning_rate": 1.4624654378077872e-05, + "loss": 1.4011, + "step": 3931 + }, + { + "epoch": 0.41, + "learning_rate": 1.462140875406414e-05, + "loss": 1.3859, + "step": 3932 + }, + { + "epoch": 0.41, + "learning_rate": 1.4618162510900376e-05, + "loss": 1.4518, + "step": 3933 + }, + { + "epoch": 0.41, + "learning_rate": 1.4614915649021493e-05, + "loss": 1.4399, + "step": 3934 + }, + { + "epoch": 0.41, + "learning_rate": 1.4611668168862495e-05, + "loss": 1.4034, + "step": 3935 + }, + { + "epoch": 0.41, + "learning_rate": 1.4608420070858452e-05, + "loss": 1.3919, + "step": 3936 + }, + { + "epoch": 0.41, + "learning_rate": 1.4605171355444528e-05, + "loss": 1.391, + "step": 3937 + }, + { + "epoch": 0.41, + "learning_rate": 1.460192202305597e-05, + "loss": 1.3717, + "step": 3938 + }, + { + "epoch": 0.41, + "learning_rate": 1.4598672074128103e-05, + "loss": 1.4351, + "step": 3939 + }, + { + "epoch": 0.41, + "learning_rate": 1.4595421509096339e-05, + "loss": 1.4202, + "step": 3940 + }, + { + "epoch": 0.41, + "learning_rate": 1.4592170328396165e-05, + "loss": 1.3559, + "step": 3941 + }, + { + "epoch": 0.41, + "learning_rate": 1.458891853246316e-05, + "loss": 1.5878, + "step": 3942 + }, + { + "epoch": 0.41, + "learning_rate": 1.4585666121732982e-05, + "loss": 1.3818, + "step": 3943 + }, + { + "epoch": 0.41, + "learning_rate": 1.4582413096641369e-05, + "loss": 1.4009, + "step": 3944 + }, + { + "epoch": 0.41, + "learning_rate": 1.457915945762414e-05, + "loss": 1.3937, + "step": 3945 + }, + { + "epoch": 0.41, + "learning_rate": 1.4575905205117203e-05, + "loss": 1.381, + "step": 3946 + }, + { + "epoch": 0.41, + "learning_rate": 1.457265033955654e-05, + "loss": 1.3844, + "step": 3947 + }, + { + "epoch": 0.41, + "learning_rate": 1.4569394861378226e-05, + "loss": 1.4059, + "step": 3948 + }, + { + "epoch": 0.41, + "learning_rate": 1.4566138771018403e-05, + "loss": 1.3698, + "step": 3949 + }, + { + "epoch": 0.41, + "learning_rate": 1.4562882068913311e-05, + "loss": 1.4253, + "step": 3950 + }, + { + "epoch": 0.41, + "learning_rate": 1.455962475549926e-05, + "loss": 1.4284, + "step": 3951 + }, + { + "epoch": 0.41, + "learning_rate": 1.4556366831212647e-05, + "loss": 1.4279, + "step": 3952 + }, + { + "epoch": 0.41, + "learning_rate": 1.4553108296489951e-05, + "loss": 1.3072, + "step": 3953 + }, + { + "epoch": 0.41, + "learning_rate": 1.4549849151767731e-05, + "loss": 1.4175, + "step": 3954 + }, + { + "epoch": 0.41, + "learning_rate": 1.4546589397482632e-05, + "loss": 1.5042, + "step": 3955 + }, + { + "epoch": 0.41, + "learning_rate": 1.4543329034071371e-05, + "loss": 1.4363, + "step": 3956 + }, + { + "epoch": 0.41, + "learning_rate": 1.454006806197076e-05, + "loss": 1.4111, + "step": 3957 + }, + { + "epoch": 0.42, + "learning_rate": 1.453680648161768e-05, + "loss": 1.3817, + "step": 3958 + }, + { + "epoch": 0.42, + "learning_rate": 1.45335442934491e-05, + "loss": 1.4689, + "step": 3959 + }, + { + "epoch": 0.42, + "learning_rate": 1.4530281497902072e-05, + "loss": 1.4164, + "step": 3960 + }, + { + "epoch": 0.42, + "learning_rate": 1.4527018095413726e-05, + "loss": 1.3943, + "step": 3961 + }, + { + "epoch": 0.42, + "learning_rate": 1.4523754086421271e-05, + "loss": 1.3851, + "step": 3962 + }, + { + "epoch": 0.42, + "learning_rate": 1.4520489471362003e-05, + "loss": 1.3907, + "step": 3963 + }, + { + "epoch": 0.42, + "learning_rate": 1.4517224250673297e-05, + "loss": 1.2877, + "step": 3964 + }, + { + "epoch": 0.42, + "learning_rate": 1.4513958424792605e-05, + "loss": 1.4696, + "step": 3965 + }, + { + "epoch": 0.42, + "learning_rate": 1.4510691994157471e-05, + "loss": 1.3785, + "step": 3966 + }, + { + "epoch": 0.42, + "learning_rate": 1.4507424959205505e-05, + "loss": 1.3652, + "step": 3967 + }, + { + "epoch": 0.42, + "learning_rate": 1.4504157320374408e-05, + "loss": 1.4198, + "step": 3968 + }, + { + "epoch": 0.42, + "learning_rate": 1.4500889078101962e-05, + "loss": 1.3476, + "step": 3969 + }, + { + "epoch": 0.42, + "learning_rate": 1.4497620232826028e-05, + "loss": 1.4356, + "step": 3970 + }, + { + "epoch": 0.42, + "learning_rate": 1.4494350784984543e-05, + "loss": 1.4993, + "step": 3971 + }, + { + "epoch": 0.42, + "learning_rate": 1.4491080735015533e-05, + "loss": 1.4022, + "step": 3972 + }, + { + "epoch": 0.42, + "learning_rate": 1.44878100833571e-05, + "loss": 1.4074, + "step": 3973 + }, + { + "epoch": 0.42, + "learning_rate": 1.4484538830447423e-05, + "loss": 1.412, + "step": 3974 + }, + { + "epoch": 0.42, + "learning_rate": 1.4481266976724772e-05, + "loss": 1.3872, + "step": 3975 + }, + { + "epoch": 0.42, + "learning_rate": 1.4477994522627485e-05, + "loss": 1.4575, + "step": 3976 + }, + { + "epoch": 0.42, + "learning_rate": 1.4474721468593995e-05, + "loss": 1.3768, + "step": 3977 + }, + { + "epoch": 0.42, + "learning_rate": 1.44714478150628e-05, + "loss": 1.4173, + "step": 3978 + }, + { + "epoch": 0.42, + "learning_rate": 1.4468173562472489e-05, + "loss": 1.3896, + "step": 3979 + }, + { + "epoch": 0.42, + "learning_rate": 1.4464898711261725e-05, + "loss": 1.4535, + "step": 3980 + }, + { + "epoch": 0.42, + "eval_loss": 1.4580057859420776, + "eval_runtime": 77.4537, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 3980 + }, + { + "epoch": 0.42, + "learning_rate": 1.4461623261869258e-05, + "loss": 1.4046, + "step": 3981 + }, + { + "epoch": 0.42, + "learning_rate": 1.445834721473391e-05, + "loss": 1.37, + "step": 3982 + }, + { + "epoch": 0.42, + "learning_rate": 1.4455070570294588e-05, + "loss": 1.4566, + "step": 3983 + }, + { + "epoch": 0.42, + "learning_rate": 1.445179332899028e-05, + "loss": 1.4513, + "step": 3984 + }, + { + "epoch": 0.42, + "learning_rate": 1.4448515491260051e-05, + "loss": 1.3893, + "step": 3985 + }, + { + "epoch": 0.42, + "learning_rate": 1.4445237057543047e-05, + "loss": 1.3955, + "step": 3986 + }, + { + "epoch": 0.42, + "learning_rate": 1.4441958028278493e-05, + "loss": 1.4861, + "step": 3987 + }, + { + "epoch": 0.42, + "learning_rate": 1.4438678403905697e-05, + "loss": 1.4601, + "step": 3988 + }, + { + "epoch": 0.42, + "learning_rate": 1.4435398184864043e-05, + "loss": 1.398, + "step": 3989 + }, + { + "epoch": 0.42, + "learning_rate": 1.4432117371592995e-05, + "loss": 1.4392, + "step": 3990 + }, + { + "epoch": 0.42, + "learning_rate": 1.4428835964532098e-05, + "loss": 1.3772, + "step": 3991 + }, + { + "epoch": 0.42, + "learning_rate": 1.4425553964120979e-05, + "loss": 1.4241, + "step": 3992 + }, + { + "epoch": 0.42, + "learning_rate": 1.4422271370799338e-05, + "loss": 1.3237, + "step": 3993 + }, + { + "epoch": 0.42, + "learning_rate": 1.4418988185006964e-05, + "loss": 1.3813, + "step": 3994 + }, + { + "epoch": 0.42, + "learning_rate": 1.4415704407183709e-05, + "loss": 1.6139, + "step": 3995 + }, + { + "epoch": 0.42, + "learning_rate": 1.4412420037769525e-05, + "loss": 1.4431, + "step": 3996 + }, + { + "epoch": 0.42, + "learning_rate": 1.440913507720443e-05, + "loss": 1.3862, + "step": 3997 + }, + { + "epoch": 0.42, + "learning_rate": 1.4405849525928523e-05, + "loss": 1.3895, + "step": 3998 + }, + { + "epoch": 0.42, + "learning_rate": 1.4402563384381981e-05, + "loss": 1.4068, + "step": 3999 + }, + { + "epoch": 0.42, + "learning_rate": 1.4399276653005072e-05, + "loss": 1.4501, + "step": 4000 + }, + { + "epoch": 0.42, + "learning_rate": 1.4395989332238124e-05, + "loss": 1.3165, + "step": 4001 + }, + { + "epoch": 0.42, + "learning_rate": 1.4392701422521555e-05, + "loss": 1.3783, + "step": 4002 + }, + { + "epoch": 0.42, + "learning_rate": 1.4389412924295865e-05, + "loss": 1.343, + "step": 4003 + }, + { + "epoch": 0.42, + "learning_rate": 1.4386123838001625e-05, + "loss": 1.3456, + "step": 4004 + }, + { + "epoch": 0.42, + "learning_rate": 1.4382834164079486e-05, + "loss": 1.3689, + "step": 4005 + }, + { + "epoch": 0.42, + "learning_rate": 1.4379543902970183e-05, + "loss": 1.3789, + "step": 4006 + }, + { + "epoch": 0.42, + "learning_rate": 1.4376253055114528e-05, + "loss": 1.4912, + "step": 4007 + }, + { + "epoch": 0.42, + "learning_rate": 1.4372961620953407e-05, + "loss": 1.3692, + "step": 4008 + }, + { + "epoch": 0.42, + "learning_rate": 1.436966960092779e-05, + "loss": 1.4901, + "step": 4009 + }, + { + "epoch": 0.42, + "learning_rate": 1.4366376995478717e-05, + "loss": 1.4431, + "step": 4010 + }, + { + "epoch": 0.42, + "learning_rate": 1.436308380504732e-05, + "loss": 1.4626, + "step": 4011 + }, + { + "epoch": 0.42, + "learning_rate": 1.4359790030074798e-05, + "loss": 1.4241, + "step": 4012 + }, + { + "epoch": 0.42, + "learning_rate": 1.4356495671002435e-05, + "loss": 1.3834, + "step": 4013 + }, + { + "epoch": 0.42, + "learning_rate": 1.4353200728271586e-05, + "loss": 1.3626, + "step": 4014 + }, + { + "epoch": 0.42, + "learning_rate": 1.4349905202323692e-05, + "loss": 1.3557, + "step": 4015 + }, + { + "epoch": 0.42, + "learning_rate": 1.434660909360027e-05, + "loss": 1.4077, + "step": 4016 + }, + { + "epoch": 0.42, + "learning_rate": 1.4343312402542911e-05, + "loss": 1.4337, + "step": 4017 + }, + { + "epoch": 0.42, + "learning_rate": 1.4340015129593286e-05, + "loss": 1.419, + "step": 4018 + }, + { + "epoch": 0.42, + "learning_rate": 1.4336717275193148e-05, + "loss": 1.3768, + "step": 4019 + }, + { + "epoch": 0.42, + "learning_rate": 1.4333418839784326e-05, + "loss": 1.383, + "step": 4020 + }, + { + "epoch": 0.42, + "learning_rate": 1.4330119823808719e-05, + "loss": 1.3951, + "step": 4021 + }, + { + "epoch": 0.42, + "learning_rate": 1.4326820227708316e-05, + "loss": 1.3985, + "step": 4022 + }, + { + "epoch": 0.42, + "learning_rate": 1.4323520051925177e-05, + "loss": 1.356, + "step": 4023 + }, + { + "epoch": 0.42, + "learning_rate": 1.4320219296901439e-05, + "loss": 1.5017, + "step": 4024 + }, + { + "epoch": 0.42, + "learning_rate": 1.4316917963079322e-05, + "loss": 1.3594, + "step": 4025 + }, + { + "epoch": 0.42, + "learning_rate": 1.4313616050901114e-05, + "loss": 1.6028, + "step": 4026 + }, + { + "epoch": 0.42, + "learning_rate": 1.4310313560809193e-05, + "loss": 1.4132, + "step": 4027 + }, + { + "epoch": 0.42, + "learning_rate": 1.4307010493246006e-05, + "loss": 1.2969, + "step": 4028 + }, + { + "epoch": 0.42, + "learning_rate": 1.4303706848654073e-05, + "loss": 1.5224, + "step": 4029 + }, + { + "epoch": 0.42, + "learning_rate": 1.4300402627476007e-05, + "loss": 1.3386, + "step": 4030 + }, + { + "epoch": 0.42, + "learning_rate": 1.429709783015448e-05, + "loss": 1.3554, + "step": 4031 + }, + { + "epoch": 0.42, + "learning_rate": 1.4293792457132259e-05, + "loss": 1.3386, + "step": 4032 + }, + { + "epoch": 0.42, + "learning_rate": 1.429048650885217e-05, + "loss": 1.4613, + "step": 4033 + }, + { + "epoch": 0.42, + "learning_rate": 1.4287179985757132e-05, + "loss": 1.3632, + "step": 4034 + }, + { + "epoch": 0.42, + "learning_rate": 1.428387288829013e-05, + "loss": 1.3835, + "step": 4035 + }, + { + "epoch": 0.42, + "learning_rate": 1.4280565216894234e-05, + "loss": 1.3711, + "step": 4036 + }, + { + "epoch": 0.42, + "learning_rate": 1.4277256972012582e-05, + "loss": 1.3385, + "step": 4037 + }, + { + "epoch": 0.42, + "learning_rate": 1.4273948154088395e-05, + "loss": 1.4607, + "step": 4038 + }, + { + "epoch": 0.42, + "learning_rate": 1.4270638763564973e-05, + "loss": 1.4042, + "step": 4039 + }, + { + "epoch": 0.42, + "learning_rate": 1.4267328800885687e-05, + "loss": 1.4006, + "step": 4040 + }, + { + "epoch": 0.42, + "learning_rate": 1.4264018266493987e-05, + "loss": 1.386, + "step": 4041 + }, + { + "epoch": 0.42, + "learning_rate": 1.4260707160833401e-05, + "loss": 1.3487, + "step": 4042 + }, + { + "epoch": 0.42, + "learning_rate": 1.4257395484347529e-05, + "loss": 1.4199, + "step": 4043 + }, + { + "epoch": 0.42, + "learning_rate": 1.4254083237480054e-05, + "loss": 1.3236, + "step": 4044 + }, + { + "epoch": 0.42, + "learning_rate": 1.4250770420674726e-05, + "loss": 1.4056, + "step": 4045 + }, + { + "epoch": 0.42, + "learning_rate": 1.4247457034375387e-05, + "loss": 1.4391, + "step": 4046 + }, + { + "epoch": 0.42, + "learning_rate": 1.4244143079025938e-05, + "loss": 1.3935, + "step": 4047 + }, + { + "epoch": 0.42, + "learning_rate": 1.4240828555070368e-05, + "loss": 1.3623, + "step": 4048 + }, + { + "epoch": 0.42, + "learning_rate": 1.4237513462952733e-05, + "loss": 1.3254, + "step": 4049 + }, + { + "epoch": 0.42, + "learning_rate": 1.4234197803117174e-05, + "loss": 1.4217, + "step": 4050 + }, + { + "epoch": 0.42, + "learning_rate": 1.4230881576007904e-05, + "loss": 1.435, + "step": 4051 + }, + { + "epoch": 0.42, + "learning_rate": 1.422756478206921e-05, + "loss": 1.3687, + "step": 4052 + }, + { + "epoch": 0.43, + "learning_rate": 1.4224247421745464e-05, + "loss": 1.3965, + "step": 4053 + }, + { + "epoch": 0.43, + "learning_rate": 1.4220929495481097e-05, + "loss": 1.4159, + "step": 4054 + }, + { + "epoch": 0.43, + "learning_rate": 1.4217611003720632e-05, + "loss": 1.3632, + "step": 4055 + }, + { + "epoch": 0.43, + "learning_rate": 1.4214291946908661e-05, + "loss": 1.403, + "step": 4056 + }, + { + "epoch": 0.43, + "learning_rate": 1.4210972325489854e-05, + "loss": 1.4093, + "step": 4057 + }, + { + "epoch": 0.43, + "learning_rate": 1.4207652139908952e-05, + "loss": 1.4551, + "step": 4058 + }, + { + "epoch": 0.43, + "learning_rate": 1.4204331390610775e-05, + "loss": 1.4162, + "step": 4059 + }, + { + "epoch": 0.43, + "learning_rate": 1.4201010078040216e-05, + "loss": 1.4492, + "step": 4060 + }, + { + "epoch": 0.43, + "learning_rate": 1.419768820264225e-05, + "loss": 1.4449, + "step": 4061 + }, + { + "epoch": 0.43, + "learning_rate": 1.4194365764861922e-05, + "loss": 1.3382, + "step": 4062 + }, + { + "epoch": 0.43, + "learning_rate": 1.419104276514435e-05, + "loss": 1.3899, + "step": 4063 + }, + { + "epoch": 0.43, + "learning_rate": 1.4187719203934734e-05, + "loss": 1.3513, + "step": 4064 + }, + { + "epoch": 0.43, + "learning_rate": 1.4184395081678344e-05, + "loss": 1.3954, + "step": 4065 + }, + { + "epoch": 0.43, + "learning_rate": 1.4181070398820528e-05, + "loss": 1.442, + "step": 4066 + }, + { + "epoch": 0.43, + "learning_rate": 1.4177745155806708e-05, + "loss": 1.3907, + "step": 4067 + }, + { + "epoch": 0.43, + "learning_rate": 1.417441935308238e-05, + "loss": 1.3757, + "step": 4068 + }, + { + "epoch": 0.43, + "learning_rate": 1.4171092991093118e-05, + "loss": 1.3507, + "step": 4069 + }, + { + "epoch": 0.43, + "learning_rate": 1.4167766070284568e-05, + "loss": 1.4136, + "step": 4070 + }, + { + "epoch": 0.43, + "learning_rate": 1.4164438591102452e-05, + "loss": 1.3835, + "step": 4071 + }, + { + "epoch": 0.43, + "learning_rate": 1.4161110553992565e-05, + "loss": 1.4981, + "step": 4072 + }, + { + "epoch": 0.43, + "learning_rate": 1.415778195940078e-05, + "loss": 1.4387, + "step": 4073 + }, + { + "epoch": 0.43, + "learning_rate": 1.4154452807773047e-05, + "loss": 1.333, + "step": 4074 + }, + { + "epoch": 0.43, + "learning_rate": 1.4151123099555377e-05, + "loss": 1.3558, + "step": 4075 + }, + { + "epoch": 0.43, + "learning_rate": 1.4147792835193875e-05, + "loss": 1.4655, + "step": 4076 + }, + { + "epoch": 0.43, + "learning_rate": 1.4144462015134708e-05, + "loss": 1.4402, + "step": 4077 + }, + { + "epoch": 0.43, + "learning_rate": 1.4141130639824119e-05, + "loss": 1.4227, + "step": 4078 + }, + { + "epoch": 0.43, + "learning_rate": 1.4137798709708423e-05, + "loss": 1.4039, + "step": 4079 + }, + { + "epoch": 0.43, + "learning_rate": 1.4134466225234023e-05, + "loss": 1.3593, + "step": 4080 + }, + { + "epoch": 0.43, + "learning_rate": 1.4131133186847377e-05, + "loss": 1.372, + "step": 4081 + }, + { + "epoch": 0.43, + "learning_rate": 1.412779959499503e-05, + "loss": 1.4487, + "step": 4082 + }, + { + "epoch": 0.43, + "learning_rate": 1.4124465450123599e-05, + "loss": 1.3972, + "step": 4083 + }, + { + "epoch": 0.43, + "learning_rate": 1.4121130752679772e-05, + "loss": 1.3768, + "step": 4084 + }, + { + "epoch": 0.43, + "learning_rate": 1.4117795503110313e-05, + "loss": 1.3827, + "step": 4085 + }, + { + "epoch": 0.43, + "learning_rate": 1.4114459701862062e-05, + "loss": 1.3922, + "step": 4086 + }, + { + "epoch": 0.43, + "learning_rate": 1.4111123349381925e-05, + "loss": 1.3736, + "step": 4087 + }, + { + "epoch": 0.43, + "learning_rate": 1.4107786446116894e-05, + "loss": 1.4338, + "step": 4088 + }, + { + "epoch": 0.43, + "learning_rate": 1.4104448992514023e-05, + "loss": 1.347, + "step": 4089 + }, + { + "epoch": 0.43, + "learning_rate": 1.410111098902045e-05, + "loss": 1.3915, + "step": 4090 + }, + { + "epoch": 0.43, + "learning_rate": 1.4097772436083377e-05, + "loss": 1.3656, + "step": 4091 + }, + { + "epoch": 0.43, + "learning_rate": 1.4094433334150087e-05, + "loss": 1.3461, + "step": 4092 + }, + { + "epoch": 0.43, + "learning_rate": 1.4091093683667934e-05, + "loss": 1.7345, + "step": 4093 + }, + { + "epoch": 0.43, + "learning_rate": 1.4087753485084343e-05, + "loss": 1.6204, + "step": 4094 + }, + { + "epoch": 0.43, + "learning_rate": 1.4084412738846816e-05, + "loss": 1.4074, + "step": 4095 + }, + { + "epoch": 0.43, + "learning_rate": 1.408107144540293e-05, + "loss": 1.3776, + "step": 4096 + }, + { + "epoch": 0.43, + "learning_rate": 1.407772960520033e-05, + "loss": 1.4079, + "step": 4097 + }, + { + "epoch": 0.43, + "learning_rate": 1.4074387218686734e-05, + "loss": 1.4254, + "step": 4098 + }, + { + "epoch": 0.43, + "learning_rate": 1.407104428630994e-05, + "loss": 1.38, + "step": 4099 + }, + { + "epoch": 0.43, + "learning_rate": 1.4067700808517815e-05, + "loss": 1.4175, + "step": 4100 + }, + { + "epoch": 0.43, + "learning_rate": 1.4064356785758298e-05, + "loss": 1.4085, + "step": 4101 + }, + { + "epoch": 0.43, + "learning_rate": 1.4061012218479397e-05, + "loss": 1.4529, + "step": 4102 + }, + { + "epoch": 0.43, + "learning_rate": 1.405766710712921e-05, + "loss": 1.4836, + "step": 4103 + }, + { + "epoch": 0.43, + "learning_rate": 1.4054321452155885e-05, + "loss": 1.3915, + "step": 4104 + }, + { + "epoch": 0.43, + "learning_rate": 1.4050975254007659e-05, + "loss": 1.3044, + "step": 4105 + }, + { + "epoch": 0.43, + "learning_rate": 1.4047628513132835e-05, + "loss": 1.373, + "step": 4106 + }, + { + "epoch": 0.43, + "learning_rate": 1.4044281229979793e-05, + "loss": 1.4266, + "step": 4107 + }, + { + "epoch": 0.43, + "learning_rate": 1.4040933404996977e-05, + "loss": 1.3898, + "step": 4108 + }, + { + "epoch": 0.43, + "learning_rate": 1.4037585038632915e-05, + "loss": 0.9326, + "step": 4109 + }, + { + "epoch": 0.43, + "learning_rate": 1.40342361313362e-05, + "loss": 1.0831, + "step": 4110 + }, + { + "epoch": 0.43, + "learning_rate": 1.40308866835555e-05, + "loss": 1.3898, + "step": 4111 + }, + { + "epoch": 0.43, + "learning_rate": 1.4027536695739554e-05, + "loss": 1.5058, + "step": 4112 + }, + { + "epoch": 0.43, + "learning_rate": 1.4024186168337175e-05, + "loss": 1.3635, + "step": 4113 + }, + { + "epoch": 0.43, + "learning_rate": 1.4020835101797248e-05, + "loss": 1.3871, + "step": 4114 + }, + { + "epoch": 0.43, + "learning_rate": 1.401748349656873e-05, + "loss": 1.3478, + "step": 4115 + }, + { + "epoch": 0.43, + "learning_rate": 1.4014131353100648e-05, + "loss": 1.3356, + "step": 4116 + }, + { + "epoch": 0.43, + "learning_rate": 1.4010778671842107e-05, + "loss": 1.3954, + "step": 4117 + }, + { + "epoch": 0.43, + "learning_rate": 1.4007425453242274e-05, + "loss": 1.3307, + "step": 4118 + }, + { + "epoch": 0.43, + "learning_rate": 1.4004071697750398e-05, + "loss": 1.4508, + "step": 4119 + }, + { + "epoch": 0.43, + "learning_rate": 1.4000717405815799e-05, + "loss": 1.3752, + "step": 4120 + }, + { + "epoch": 0.43, + "learning_rate": 1.399736257788786e-05, + "loss": 1.3654, + "step": 4121 + }, + { + "epoch": 0.43, + "learning_rate": 1.3994007214416046e-05, + "loss": 1.4505, + "step": 4122 + }, + { + "epoch": 0.43, + "learning_rate": 1.3990651315849886e-05, + "loss": 1.4307, + "step": 4123 + }, + { + "epoch": 0.43, + "learning_rate": 1.398729488263899e-05, + "loss": 1.4481, + "step": 4124 + }, + { + "epoch": 0.43, + "learning_rate": 1.3983937915233026e-05, + "loss": 1.4755, + "step": 4125 + }, + { + "epoch": 0.43, + "learning_rate": 1.3980580414081746e-05, + "loss": 1.3402, + "step": 4126 + }, + { + "epoch": 0.43, + "learning_rate": 1.3977222379634969e-05, + "loss": 1.3636, + "step": 4127 + }, + { + "epoch": 0.43, + "learning_rate": 1.3973863812342585e-05, + "loss": 1.4165, + "step": 4128 + }, + { + "epoch": 0.43, + "learning_rate": 1.3970504712654554e-05, + "loss": 1.3832, + "step": 4129 + }, + { + "epoch": 0.43, + "learning_rate": 1.3967145081020912e-05, + "loss": 1.4236, + "step": 4130 + }, + { + "epoch": 0.43, + "learning_rate": 1.396378491789176e-05, + "loss": 1.5022, + "step": 4131 + }, + { + "epoch": 0.43, + "learning_rate": 1.3960424223717276e-05, + "loss": 1.3806, + "step": 4132 + }, + { + "epoch": 0.43, + "learning_rate": 1.3957062998947707e-05, + "loss": 1.3649, + "step": 4133 + }, + { + "epoch": 0.43, + "learning_rate": 1.3953701244033368e-05, + "loss": 1.3787, + "step": 4134 + }, + { + "epoch": 0.43, + "learning_rate": 1.395033895942465e-05, + "loss": 1.3551, + "step": 4135 + }, + { + "epoch": 0.43, + "learning_rate": 1.394697614557201e-05, + "loss": 1.3881, + "step": 4136 + }, + { + "epoch": 0.43, + "learning_rate": 1.3943612802925983e-05, + "loss": 1.4848, + "step": 4137 + }, + { + "epoch": 0.43, + "learning_rate": 1.3940248931937169e-05, + "loss": 1.425, + "step": 4138 + }, + { + "epoch": 0.43, + "learning_rate": 1.3936884533056238e-05, + "loss": 1.4054, + "step": 4139 + }, + { + "epoch": 0.43, + "learning_rate": 1.3933519606733934e-05, + "loss": 1.4028, + "step": 4140 + }, + { + "epoch": 0.43, + "learning_rate": 1.3930154153421072e-05, + "loss": 1.4439, + "step": 4141 + }, + { + "epoch": 0.43, + "learning_rate": 1.3926788173568536e-05, + "loss": 1.4482, + "step": 4142 + }, + { + "epoch": 0.43, + "learning_rate": 1.392342166762728e-05, + "loss": 1.393, + "step": 4143 + }, + { + "epoch": 0.43, + "learning_rate": 1.3920054636048328e-05, + "loss": 1.4097, + "step": 4144 + }, + { + "epoch": 0.43, + "learning_rate": 1.391668707928278e-05, + "loss": 1.5142, + "step": 4145 + }, + { + "epoch": 0.43, + "learning_rate": 1.3913318997781797e-05, + "loss": 1.4118, + "step": 4146 + }, + { + "epoch": 0.43, + "learning_rate": 1.390995039199662e-05, + "loss": 1.4067, + "step": 4147 + }, + { + "epoch": 0.43, + "learning_rate": 1.3906581262378552e-05, + "loss": 1.5214, + "step": 4148 + }, + { + "epoch": 0.44, + "learning_rate": 1.3903211609378971e-05, + "loss": 1.3618, + "step": 4149 + }, + { + "epoch": 0.44, + "learning_rate": 1.3899841433449327e-05, + "loss": 1.338, + "step": 4150 + }, + { + "epoch": 0.44, + "learning_rate": 1.3896470735041132e-05, + "loss": 1.3901, + "step": 4151 + }, + { + "epoch": 0.44, + "learning_rate": 1.3893099514605971e-05, + "loss": 1.4502, + "step": 4152 + }, + { + "epoch": 0.44, + "learning_rate": 1.388972777259551e-05, + "loss": 1.4141, + "step": 4153 + }, + { + "epoch": 0.44, + "learning_rate": 1.3886355509461471e-05, + "loss": 1.3876, + "step": 4154 + }, + { + "epoch": 0.44, + "learning_rate": 1.388298272565565e-05, + "loss": 1.4275, + "step": 4155 + }, + { + "epoch": 0.44, + "learning_rate": 1.3879609421629909e-05, + "loss": 1.3559, + "step": 4156 + }, + { + "epoch": 0.44, + "learning_rate": 1.3876235597836195e-05, + "loss": 1.416, + "step": 4157 + }, + { + "epoch": 0.44, + "learning_rate": 1.3872861254726506e-05, + "loss": 1.437, + "step": 4158 + }, + { + "epoch": 0.44, + "learning_rate": 1.3869486392752918e-05, + "loss": 1.3794, + "step": 4159 + }, + { + "epoch": 0.44, + "learning_rate": 1.3866111012367577e-05, + "loss": 1.4094, + "step": 4160 + }, + { + "epoch": 0.44, + "learning_rate": 1.3862735114022694e-05, + "loss": 1.3957, + "step": 4161 + }, + { + "epoch": 0.44, + "learning_rate": 1.3859358698170559e-05, + "loss": 1.3582, + "step": 4162 + }, + { + "epoch": 0.44, + "learning_rate": 1.3855981765263523e-05, + "loss": 1.4159, + "step": 4163 + }, + { + "epoch": 0.44, + "learning_rate": 1.3852604315754e-05, + "loss": 1.3498, + "step": 4164 + }, + { + "epoch": 0.44, + "learning_rate": 1.3849226350094491e-05, + "loss": 1.3951, + "step": 4165 + }, + { + "epoch": 0.44, + "learning_rate": 1.3845847868737559e-05, + "loss": 1.4087, + "step": 4166 + }, + { + "epoch": 0.44, + "learning_rate": 1.3842468872135821e-05, + "loss": 1.4318, + "step": 4167 + }, + { + "epoch": 0.44, + "learning_rate": 1.3839089360741989e-05, + "loss": 1.4174, + "step": 4168 + }, + { + "epoch": 0.44, + "learning_rate": 1.3835709335008822e-05, + "loss": 1.4499, + "step": 4169 + }, + { + "epoch": 0.44, + "learning_rate": 1.383232879538916e-05, + "loss": 1.3554, + "step": 4170 + }, + { + "epoch": 0.44, + "learning_rate": 1.3828947742335905e-05, + "loss": 1.3873, + "step": 4171 + }, + { + "epoch": 0.44, + "learning_rate": 1.382556617630204e-05, + "loss": 1.3804, + "step": 4172 + }, + { + "epoch": 0.44, + "learning_rate": 1.3822184097740598e-05, + "loss": 1.3856, + "step": 4173 + }, + { + "epoch": 0.44, + "learning_rate": 1.3818801507104697e-05, + "loss": 1.3901, + "step": 4174 + }, + { + "epoch": 0.44, + "learning_rate": 1.381541840484751e-05, + "loss": 1.3714, + "step": 4175 + }, + { + "epoch": 0.44, + "learning_rate": 1.3812034791422297e-05, + "loss": 1.4945, + "step": 4176 + }, + { + "epoch": 0.44, + "learning_rate": 1.3808650667282368e-05, + "loss": 1.429, + "step": 4177 + }, + { + "epoch": 0.44, + "learning_rate": 1.3805266032881108e-05, + "loss": 1.3903, + "step": 4178 + }, + { + "epoch": 0.44, + "learning_rate": 1.3801880888671972e-05, + "loss": 1.4799, + "step": 4179 + }, + { + "epoch": 0.44, + "eval_loss": 1.4521424770355225, + "eval_runtime": 77.3596, + "eval_samples_per_second": 1.668, + "eval_steps_per_second": 0.116, + "step": 4179 + }, + { + "epoch": 0.44, + "learning_rate": 1.3798495235108484e-05, + "loss": 1.3912, + "step": 4180 + }, + { + "epoch": 0.44, + "learning_rate": 1.3795109072644235e-05, + "loss": 1.5837, + "step": 4181 + }, + { + "epoch": 0.44, + "learning_rate": 1.379172240173288e-05, + "loss": 1.4255, + "step": 4182 + }, + { + "epoch": 0.44, + "learning_rate": 1.3788335222828148e-05, + "loss": 1.4666, + "step": 4183 + }, + { + "epoch": 0.44, + "learning_rate": 1.3784947536383837e-05, + "loss": 1.3964, + "step": 4184 + }, + { + "epoch": 0.44, + "learning_rate": 1.3781559342853807e-05, + "loss": 1.336, + "step": 4185 + }, + { + "epoch": 0.44, + "learning_rate": 1.3778170642691986e-05, + "loss": 1.4352, + "step": 4186 + }, + { + "epoch": 0.44, + "learning_rate": 1.377478143635238e-05, + "loss": 1.3262, + "step": 4187 + }, + { + "epoch": 0.44, + "learning_rate": 1.3771391724289047e-05, + "loss": 1.3969, + "step": 4188 + }, + { + "epoch": 0.44, + "learning_rate": 1.376800150695613e-05, + "loss": 1.4211, + "step": 4189 + }, + { + "epoch": 0.44, + "learning_rate": 1.3764610784807824e-05, + "loss": 1.4338, + "step": 4190 + }, + { + "epoch": 0.44, + "learning_rate": 1.3761219558298403e-05, + "loss": 1.3815, + "step": 4191 + }, + { + "epoch": 0.44, + "learning_rate": 1.3757827827882203e-05, + "loss": 1.3805, + "step": 4192 + }, + { + "epoch": 0.44, + "learning_rate": 1.3754435594013627e-05, + "loss": 1.4071, + "step": 4193 + }, + { + "epoch": 0.44, + "learning_rate": 1.3751042857147145e-05, + "loss": 1.343, + "step": 4194 + }, + { + "epoch": 0.44, + "learning_rate": 1.3747649617737304e-05, + "loss": 1.4129, + "step": 4195 + }, + { + "epoch": 0.44, + "learning_rate": 1.3744255876238708e-05, + "loss": 1.3939, + "step": 4196 + }, + { + "epoch": 0.44, + "learning_rate": 1.3740861633106029e-05, + "loss": 1.3963, + "step": 4197 + }, + { + "epoch": 0.44, + "learning_rate": 1.3737466888794008e-05, + "loss": 1.5181, + "step": 4198 + }, + { + "epoch": 0.44, + "learning_rate": 1.3734071643757456e-05, + "loss": 1.4397, + "step": 4199 + }, + { + "epoch": 0.44, + "learning_rate": 1.373067589845125e-05, + "loss": 1.6293, + "step": 4200 + }, + { + "epoch": 0.44, + "learning_rate": 1.3727279653330328e-05, + "loss": 1.3498, + "step": 4201 + }, + { + "epoch": 0.44, + "learning_rate": 1.37238829088497e-05, + "loss": 1.4509, + "step": 4202 + }, + { + "epoch": 0.44, + "learning_rate": 1.3720485665464446e-05, + "loss": 1.4477, + "step": 4203 + }, + { + "epoch": 0.44, + "learning_rate": 1.3717087923629709e-05, + "loss": 1.4399, + "step": 4204 + }, + { + "epoch": 0.44, + "learning_rate": 1.3713689683800695e-05, + "loss": 1.4417, + "step": 4205 + }, + { + "epoch": 0.44, + "learning_rate": 1.3710290946432685e-05, + "loss": 1.3957, + "step": 4206 + }, + { + "epoch": 0.44, + "learning_rate": 1.3706891711981021e-05, + "loss": 1.4476, + "step": 4207 + }, + { + "epoch": 0.44, + "learning_rate": 1.3703491980901113e-05, + "loss": 1.3894, + "step": 4208 + }, + { + "epoch": 0.44, + "learning_rate": 1.3700091753648437e-05, + "loss": 1.4745, + "step": 4209 + }, + { + "epoch": 0.44, + "learning_rate": 1.369669103067854e-05, + "loss": 1.4038, + "step": 4210 + }, + { + "epoch": 0.44, + "learning_rate": 1.3693289812447023e-05, + "loss": 1.4151, + "step": 4211 + }, + { + "epoch": 0.44, + "learning_rate": 1.3689888099409572e-05, + "loss": 1.4214, + "step": 4212 + }, + { + "epoch": 0.44, + "learning_rate": 1.368648589202192e-05, + "loss": 1.4287, + "step": 4213 + }, + { + "epoch": 0.44, + "learning_rate": 1.3683083190739883e-05, + "loss": 1.345, + "step": 4214 + }, + { + "epoch": 0.44, + "learning_rate": 1.367967999601933e-05, + "loss": 1.3022, + "step": 4215 + }, + { + "epoch": 0.44, + "learning_rate": 1.3676276308316207e-05, + "loss": 1.3971, + "step": 4216 + }, + { + "epoch": 0.44, + "learning_rate": 1.3672872128086514e-05, + "loss": 1.3335, + "step": 4217 + }, + { + "epoch": 0.44, + "learning_rate": 1.366946745578633e-05, + "loss": 1.3988, + "step": 4218 + }, + { + "epoch": 0.44, + "learning_rate": 1.366606229187179e-05, + "loss": 1.4508, + "step": 4219 + }, + { + "epoch": 0.44, + "learning_rate": 1.3662656636799099e-05, + "loss": 1.3814, + "step": 4220 + }, + { + "epoch": 0.44, + "learning_rate": 1.3659250491024527e-05, + "loss": 1.4128, + "step": 4221 + }, + { + "epoch": 0.44, + "learning_rate": 1.3655843855004411e-05, + "loss": 1.3893, + "step": 4222 + }, + { + "epoch": 0.44, + "learning_rate": 1.3652436729195154e-05, + "loss": 1.2551, + "step": 4223 + }, + { + "epoch": 0.44, + "learning_rate": 1.3649029114053219e-05, + "loss": 1.4386, + "step": 4224 + }, + { + "epoch": 0.44, + "learning_rate": 1.364562101003514e-05, + "loss": 1.4028, + "step": 4225 + }, + { + "epoch": 0.44, + "learning_rate": 1.364221241759752e-05, + "loss": 1.4351, + "step": 4226 + }, + { + "epoch": 0.44, + "learning_rate": 1.363880333719702e-05, + "loss": 1.3941, + "step": 4227 + }, + { + "epoch": 0.44, + "learning_rate": 1.3635393769290368e-05, + "loss": 1.3879, + "step": 4228 + }, + { + "epoch": 0.44, + "learning_rate": 1.3631983714334358e-05, + "loss": 1.3773, + "step": 4229 + }, + { + "epoch": 0.44, + "learning_rate": 1.3628573172785853e-05, + "loss": 1.3679, + "step": 4230 + }, + { + "epoch": 0.44, + "learning_rate": 1.3625162145101776e-05, + "loss": 1.3705, + "step": 4231 + }, + { + "epoch": 0.44, + "learning_rate": 1.3621750631739114e-05, + "loss": 1.8157, + "step": 4232 + }, + { + "epoch": 0.44, + "learning_rate": 1.3618338633154928e-05, + "loss": 1.4056, + "step": 4233 + }, + { + "epoch": 0.44, + "learning_rate": 1.3614926149806334e-05, + "loss": 1.3716, + "step": 4234 + }, + { + "epoch": 0.44, + "learning_rate": 1.3611513182150523e-05, + "loss": 1.3766, + "step": 4235 + }, + { + "epoch": 0.44, + "learning_rate": 1.3608099730644733e-05, + "loss": 1.41, + "step": 4236 + }, + { + "epoch": 0.44, + "learning_rate": 1.3604685795746291e-05, + "loss": 1.421, + "step": 4237 + }, + { + "epoch": 0.44, + "learning_rate": 1.360127137791257e-05, + "loss": 1.3679, + "step": 4238 + }, + { + "epoch": 0.44, + "learning_rate": 1.3597856477601018e-05, + "loss": 1.4615, + "step": 4239 + }, + { + "epoch": 0.44, + "learning_rate": 1.359444109526914e-05, + "loss": 1.3418, + "step": 4240 + }, + { + "epoch": 0.44, + "learning_rate": 1.3591025231374513e-05, + "loss": 1.3631, + "step": 4241 + }, + { + "epoch": 0.44, + "learning_rate": 1.3587608886374772e-05, + "loss": 1.3802, + "step": 4242 + }, + { + "epoch": 0.44, + "learning_rate": 1.3584192060727622e-05, + "loss": 1.4156, + "step": 4243 + }, + { + "epoch": 0.45, + "learning_rate": 1.3580774754890827e-05, + "loss": 1.4161, + "step": 4244 + }, + { + "epoch": 0.45, + "learning_rate": 1.3577356969322222e-05, + "loss": 1.3535, + "step": 4245 + }, + { + "epoch": 0.45, + "learning_rate": 1.3573938704479699e-05, + "loss": 1.3859, + "step": 4246 + }, + { + "epoch": 0.45, + "learning_rate": 1.357051996082122e-05, + "loss": 1.3595, + "step": 4247 + }, + { + "epoch": 0.45, + "learning_rate": 1.3567100738804806e-05, + "loss": 1.4191, + "step": 4248 + }, + { + "epoch": 0.45, + "learning_rate": 1.3563681038888548e-05, + "loss": 1.4186, + "step": 4249 + }, + { + "epoch": 0.45, + "learning_rate": 1.3560260861530596e-05, + "loss": 1.43, + "step": 4250 + }, + { + "epoch": 0.45, + "learning_rate": 1.3556840207189168e-05, + "loss": 1.4139, + "step": 4251 + }, + { + "epoch": 0.45, + "learning_rate": 1.3553419076322539e-05, + "loss": 1.4005, + "step": 4252 + }, + { + "epoch": 0.45, + "learning_rate": 1.3549997469389058e-05, + "loss": 1.3468, + "step": 4253 + }, + { + "epoch": 0.45, + "learning_rate": 1.3546575386847132e-05, + "loss": 1.3756, + "step": 4254 + }, + { + "epoch": 0.45, + "learning_rate": 1.3543152829155226e-05, + "loss": 1.4063, + "step": 4255 + }, + { + "epoch": 0.45, + "learning_rate": 1.3539729796771884e-05, + "loss": 1.4666, + "step": 4256 + }, + { + "epoch": 0.45, + "learning_rate": 1.3536306290155694e-05, + "loss": 1.4212, + "step": 4257 + }, + { + "epoch": 0.45, + "learning_rate": 1.3532882309765332e-05, + "loss": 1.4883, + "step": 4258 + }, + { + "epoch": 0.45, + "learning_rate": 1.3529457856059507e-05, + "loss": 1.6641, + "step": 4259 + }, + { + "epoch": 0.45, + "learning_rate": 1.3526032929497022e-05, + "loss": 1.3659, + "step": 4260 + }, + { + "epoch": 0.45, + "learning_rate": 1.3522607530536717e-05, + "loss": 1.5945, + "step": 4261 + }, + { + "epoch": 0.45, + "learning_rate": 1.351918165963752e-05, + "loss": 1.3643, + "step": 4262 + }, + { + "epoch": 0.45, + "learning_rate": 1.3515755317258397e-05, + "loss": 1.3442, + "step": 4263 + }, + { + "epoch": 0.45, + "learning_rate": 1.3512328503858398e-05, + "loss": 1.3982, + "step": 4264 + }, + { + "epoch": 0.45, + "learning_rate": 1.3508901219896624e-05, + "loss": 1.4985, + "step": 4265 + }, + { + "epoch": 0.45, + "learning_rate": 1.350547346583225e-05, + "loss": 1.3319, + "step": 4266 + }, + { + "epoch": 0.45, + "learning_rate": 1.3502045242124497e-05, + "loss": 1.3961, + "step": 4267 + }, + { + "epoch": 0.45, + "learning_rate": 1.3498616549232665e-05, + "loss": 1.4565, + "step": 4268 + }, + { + "epoch": 0.45, + "learning_rate": 1.349518738761611e-05, + "loss": 1.375, + "step": 4269 + }, + { + "epoch": 0.45, + "learning_rate": 1.3491757757734254e-05, + "loss": 1.3005, + "step": 4270 + }, + { + "epoch": 0.45, + "learning_rate": 1.348832766004657e-05, + "loss": 1.3185, + "step": 4271 + }, + { + "epoch": 0.45, + "learning_rate": 1.3484897095012613e-05, + "loss": 1.4449, + "step": 4272 + }, + { + "epoch": 0.45, + "learning_rate": 1.3481466063091988e-05, + "loss": 1.3587, + "step": 4273 + }, + { + "epoch": 0.45, + "learning_rate": 1.3478034564744362e-05, + "loss": 1.3844, + "step": 4274 + }, + { + "epoch": 0.45, + "learning_rate": 1.3474602600429468e-05, + "loss": 1.4471, + "step": 4275 + }, + { + "epoch": 0.45, + "learning_rate": 1.3471170170607105e-05, + "loss": 1.4686, + "step": 4276 + }, + { + "epoch": 0.45, + "learning_rate": 1.3467737275737127e-05, + "loss": 1.312, + "step": 4277 + }, + { + "epoch": 0.45, + "learning_rate": 1.3464303916279453e-05, + "loss": 1.407, + "step": 4278 + }, + { + "epoch": 0.45, + "learning_rate": 1.346087009269407e-05, + "loss": 1.364, + "step": 4279 + }, + { + "epoch": 0.45, + "learning_rate": 1.3457435805441016e-05, + "loss": 1.4103, + "step": 4280 + }, + { + "epoch": 0.45, + "learning_rate": 1.3454001054980403e-05, + "loss": 1.4243, + "step": 4281 + }, + { + "epoch": 0.45, + "learning_rate": 1.3450565841772392e-05, + "loss": 1.3879, + "step": 4282 + }, + { + "epoch": 0.45, + "learning_rate": 1.344713016627722e-05, + "loss": 1.4688, + "step": 4283 + }, + { + "epoch": 0.45, + "learning_rate": 1.3443694028955176e-05, + "loss": 1.3983, + "step": 4284 + }, + { + "epoch": 0.45, + "learning_rate": 1.344025743026662e-05, + "loss": 1.4316, + "step": 4285 + }, + { + "epoch": 0.45, + "learning_rate": 1.3436820370671956e-05, + "loss": 1.3643, + "step": 4286 + }, + { + "epoch": 0.45, + "learning_rate": 1.3433382850631673e-05, + "loss": 1.4566, + "step": 4287 + }, + { + "epoch": 0.45, + "learning_rate": 1.3429944870606301e-05, + "loss": 1.1263, + "step": 4288 + }, + { + "epoch": 0.45, + "learning_rate": 1.3426506431056452e-05, + "loss": 1.2463, + "step": 4289 + }, + { + "epoch": 0.45, + "learning_rate": 1.342306753244278e-05, + "loss": 1.4753, + "step": 4290 + }, + { + "epoch": 0.45, + "learning_rate": 1.3419628175226012e-05, + "loss": 1.3789, + "step": 4291 + }, + { + "epoch": 0.45, + "learning_rate": 1.3416188359866932e-05, + "loss": 1.3906, + "step": 4292 + }, + { + "epoch": 0.45, + "learning_rate": 1.3412748086826389e-05, + "loss": 1.3995, + "step": 4293 + }, + { + "epoch": 0.45, + "learning_rate": 1.3409307356565288e-05, + "loss": 1.4906, + "step": 4294 + }, + { + "epoch": 0.45, + "learning_rate": 1.3405866169544602e-05, + "loss": 1.3951, + "step": 4295 + }, + { + "epoch": 0.45, + "learning_rate": 1.3402424526225359e-05, + "loss": 1.3753, + "step": 4296 + }, + { + "epoch": 0.45, + "learning_rate": 1.3398982427068654e-05, + "loss": 1.3686, + "step": 4297 + }, + { + "epoch": 0.45, + "learning_rate": 1.3395539872535636e-05, + "loss": 1.3612, + "step": 4298 + }, + { + "epoch": 0.45, + "learning_rate": 1.3392096863087522e-05, + "loss": 1.4043, + "step": 4299 + }, + { + "epoch": 0.45, + "learning_rate": 1.3388653399185585e-05, + "loss": 1.4068, + "step": 4300 + }, + { + "epoch": 0.45, + "learning_rate": 1.338520948129116e-05, + "loss": 1.4066, + "step": 4301 + }, + { + "epoch": 0.45, + "learning_rate": 1.3381765109865646e-05, + "loss": 1.4944, + "step": 4302 + }, + { + "epoch": 0.45, + "learning_rate": 1.3378320285370496e-05, + "loss": 1.3575, + "step": 4303 + }, + { + "epoch": 0.45, + "learning_rate": 1.3374875008267236e-05, + "loss": 1.3807, + "step": 4304 + }, + { + "epoch": 0.45, + "learning_rate": 1.3371429279017437e-05, + "loss": 1.4389, + "step": 4305 + }, + { + "epoch": 0.45, + "learning_rate": 1.3367983098082739e-05, + "loss": 1.4858, + "step": 4306 + }, + { + "epoch": 0.45, + "learning_rate": 1.3364536465924844e-05, + "loss": 1.3282, + "step": 4307 + }, + { + "epoch": 0.45, + "learning_rate": 1.3361089383005515e-05, + "loss": 1.4306, + "step": 4308 + }, + { + "epoch": 0.45, + "learning_rate": 1.3357641849786566e-05, + "loss": 1.3892, + "step": 4309 + }, + { + "epoch": 0.45, + "learning_rate": 1.3354193866729883e-05, + "loss": 1.3621, + "step": 4310 + }, + { + "epoch": 0.45, + "learning_rate": 1.3350745434297401e-05, + "loss": 1.3476, + "step": 4311 + }, + { + "epoch": 0.45, + "learning_rate": 1.334729655295113e-05, + "loss": 1.4477, + "step": 4312 + }, + { + "epoch": 0.45, + "learning_rate": 1.3343847223153123e-05, + "loss": 1.3585, + "step": 4313 + }, + { + "epoch": 0.45, + "learning_rate": 1.334039744536551e-05, + "loss": 1.3616, + "step": 4314 + }, + { + "epoch": 0.45, + "learning_rate": 1.3336947220050462e-05, + "loss": 1.3579, + "step": 4315 + }, + { + "epoch": 0.45, + "learning_rate": 1.3333496547670232e-05, + "loss": 1.3557, + "step": 4316 + }, + { + "epoch": 0.45, + "learning_rate": 1.3330045428687113e-05, + "loss": 1.4443, + "step": 4317 + }, + { + "epoch": 0.45, + "learning_rate": 1.332659386356347e-05, + "loss": 1.3621, + "step": 4318 + }, + { + "epoch": 0.45, + "learning_rate": 1.3323141852761726e-05, + "loss": 1.3295, + "step": 4319 + }, + { + "epoch": 0.45, + "learning_rate": 1.3319689396744358e-05, + "loss": 1.4187, + "step": 4320 + }, + { + "epoch": 0.45, + "learning_rate": 1.3316236495973905e-05, + "loss": 1.335, + "step": 4321 + }, + { + "epoch": 0.45, + "learning_rate": 1.331278315091297e-05, + "loss": 1.4382, + "step": 4322 + }, + { + "epoch": 0.45, + "learning_rate": 1.3309329362024212e-05, + "loss": 1.4244, + "step": 4323 + }, + { + "epoch": 0.45, + "learning_rate": 1.3305875129770351e-05, + "loss": 1.488, + "step": 4324 + }, + { + "epoch": 0.45, + "learning_rate": 1.3302420454614165e-05, + "loss": 1.3369, + "step": 4325 + }, + { + "epoch": 0.45, + "learning_rate": 1.3298965337018487e-05, + "loss": 1.3648, + "step": 4326 + }, + { + "epoch": 0.45, + "learning_rate": 1.3295509777446226e-05, + "loss": 1.3924, + "step": 4327 + }, + { + "epoch": 0.45, + "learning_rate": 1.3292053776360324e-05, + "loss": 1.3789, + "step": 4328 + }, + { + "epoch": 0.45, + "learning_rate": 1.3288597334223802e-05, + "loss": 1.3902, + "step": 4329 + }, + { + "epoch": 0.45, + "learning_rate": 1.3285140451499735e-05, + "loss": 1.4057, + "step": 4330 + }, + { + "epoch": 0.45, + "learning_rate": 1.328168312865126e-05, + "loss": 1.4536, + "step": 4331 + }, + { + "epoch": 0.45, + "learning_rate": 1.3278225366141565e-05, + "loss": 1.3075, + "step": 4332 + }, + { + "epoch": 0.45, + "learning_rate": 1.3274767164433901e-05, + "loss": 1.4579, + "step": 4333 + }, + { + "epoch": 0.45, + "learning_rate": 1.3271308523991579e-05, + "loss": 1.3906, + "step": 4334 + }, + { + "epoch": 0.45, + "learning_rate": 1.326784944527797e-05, + "loss": 1.3992, + "step": 4335 + }, + { + "epoch": 0.45, + "learning_rate": 1.3264389928756498e-05, + "loss": 1.4001, + "step": 4336 + }, + { + "epoch": 0.45, + "learning_rate": 1.3260929974890653e-05, + "loss": 1.2948, + "step": 4337 + }, + { + "epoch": 0.45, + "learning_rate": 1.3257469584143976e-05, + "loss": 1.4041, + "step": 4338 + }, + { + "epoch": 0.46, + "learning_rate": 1.3254008756980076e-05, + "loss": 1.5035, + "step": 4339 + }, + { + "epoch": 0.46, + "learning_rate": 1.3250547493862609e-05, + "loss": 1.4867, + "step": 4340 + }, + { + "epoch": 0.46, + "learning_rate": 1.3247085795255302e-05, + "loss": 1.3612, + "step": 4341 + }, + { + "epoch": 0.46, + "learning_rate": 1.3243623661621925e-05, + "loss": 1.4193, + "step": 4342 + }, + { + "epoch": 0.46, + "learning_rate": 1.3240161093426322e-05, + "loss": 1.3596, + "step": 4343 + }, + { + "epoch": 0.46, + "learning_rate": 1.3236698091132383e-05, + "loss": 1.4448, + "step": 4344 + }, + { + "epoch": 0.46, + "learning_rate": 1.3233234655204066e-05, + "loss": 1.3924, + "step": 4345 + }, + { + "epoch": 0.46, + "learning_rate": 1.322977078610538e-05, + "loss": 1.3552, + "step": 4346 + }, + { + "epoch": 0.46, + "learning_rate": 1.3226306484300395e-05, + "loss": 1.3949, + "step": 4347 + }, + { + "epoch": 0.46, + "learning_rate": 1.322284175025324e-05, + "loss": 1.399, + "step": 4348 + }, + { + "epoch": 0.46, + "learning_rate": 1.3219376584428094e-05, + "loss": 1.4755, + "step": 4349 + }, + { + "epoch": 0.46, + "learning_rate": 1.3215910987289212e-05, + "loss": 1.3877, + "step": 4350 + }, + { + "epoch": 0.46, + "learning_rate": 1.3212444959300882e-05, + "loss": 1.3916, + "step": 4351 + }, + { + "epoch": 0.46, + "learning_rate": 1.3208978500927472e-05, + "loss": 1.3462, + "step": 4352 + }, + { + "epoch": 0.46, + "learning_rate": 1.3205511612633392e-05, + "loss": 1.3834, + "step": 4353 + }, + { + "epoch": 0.46, + "learning_rate": 1.3202044294883123e-05, + "loss": 1.3843, + "step": 4354 + }, + { + "epoch": 0.46, + "learning_rate": 1.3198576548141189e-05, + "loss": 1.2439, + "step": 4355 + }, + { + "epoch": 0.46, + "learning_rate": 1.3195108372872181e-05, + "loss": 1.4106, + "step": 4356 + }, + { + "epoch": 0.46, + "learning_rate": 1.3191639769540746e-05, + "loss": 1.4417, + "step": 4357 + }, + { + "epoch": 0.46, + "learning_rate": 1.3188170738611596e-05, + "loss": 1.4393, + "step": 4358 + }, + { + "epoch": 0.46, + "learning_rate": 1.3184701280549476e-05, + "loss": 1.4616, + "step": 4359 + }, + { + "epoch": 0.46, + "learning_rate": 1.3181231395819218e-05, + "loss": 1.3215, + "step": 4360 + }, + { + "epoch": 0.46, + "learning_rate": 1.3177761084885689e-05, + "loss": 1.368, + "step": 4361 + }, + { + "epoch": 0.46, + "learning_rate": 1.317429034821383e-05, + "loss": 1.3247, + "step": 4362 + }, + { + "epoch": 0.46, + "learning_rate": 1.3170819186268618e-05, + "loss": 1.4512, + "step": 4363 + }, + { + "epoch": 0.46, + "learning_rate": 1.3167347599515111e-05, + "loss": 1.3129, + "step": 4364 + }, + { + "epoch": 0.46, + "learning_rate": 1.3163875588418404e-05, + "loss": 1.3934, + "step": 4365 + }, + { + "epoch": 0.46, + "learning_rate": 1.3160403153443666e-05, + "loss": 1.4518, + "step": 4366 + }, + { + "epoch": 0.46, + "learning_rate": 1.3156930295056105e-05, + "loss": 1.3959, + "step": 4367 + }, + { + "epoch": 0.46, + "learning_rate": 1.3153457013721e-05, + "loss": 1.3475, + "step": 4368 + }, + { + "epoch": 0.46, + "learning_rate": 1.3149983309903687e-05, + "loss": 1.4102, + "step": 4369 + }, + { + "epoch": 0.46, + "learning_rate": 1.3146509184069538e-05, + "loss": 1.3674, + "step": 4370 + }, + { + "epoch": 0.46, + "learning_rate": 1.314303463668401e-05, + "loss": 1.3739, + "step": 4371 + }, + { + "epoch": 0.46, + "learning_rate": 1.3139559668212596e-05, + "loss": 1.4249, + "step": 4372 + }, + { + "epoch": 0.46, + "learning_rate": 1.3136084279120857e-05, + "loss": 1.4473, + "step": 4373 + }, + { + "epoch": 0.46, + "learning_rate": 1.3132608469874404e-05, + "loss": 1.4443, + "step": 4374 + }, + { + "epoch": 0.46, + "learning_rate": 1.3129132240938905e-05, + "loss": 1.3534, + "step": 4375 + }, + { + "epoch": 0.46, + "learning_rate": 1.3125655592780083e-05, + "loss": 1.5663, + "step": 4376 + }, + { + "epoch": 0.46, + "learning_rate": 1.3122178525863727e-05, + "loss": 1.3465, + "step": 4377 + }, + { + "epoch": 0.46, + "learning_rate": 1.3118701040655669e-05, + "loss": 1.35, + "step": 4378 + }, + { + "epoch": 0.46, + "eval_loss": 1.447788953781128, + "eval_runtime": 77.4473, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4378 + }, + { + "epoch": 0.46, + "learning_rate": 1.3115223137621804e-05, + "loss": 1.343, + "step": 4379 + }, + { + "epoch": 0.46, + "learning_rate": 1.3111744817228078e-05, + "loss": 1.4227, + "step": 4380 + }, + { + "epoch": 0.46, + "learning_rate": 1.3108266079940508e-05, + "loss": 1.3982, + "step": 4381 + }, + { + "epoch": 0.46, + "learning_rate": 1.3104786926225141e-05, + "loss": 1.4211, + "step": 4382 + }, + { + "epoch": 0.46, + "learning_rate": 1.3101307356548103e-05, + "loss": 1.382, + "step": 4383 + }, + { + "epoch": 0.46, + "learning_rate": 1.3097827371375562e-05, + "loss": 1.4637, + "step": 4384 + }, + { + "epoch": 0.46, + "learning_rate": 1.3094346971173754e-05, + "loss": 1.4572, + "step": 4385 + }, + { + "epoch": 0.46, + "learning_rate": 1.3090866156408956e-05, + "loss": 1.5113, + "step": 4386 + }, + { + "epoch": 0.46, + "learning_rate": 1.3087384927547512e-05, + "loss": 1.2197, + "step": 4387 + }, + { + "epoch": 0.46, + "learning_rate": 1.3083903285055813e-05, + "loss": 1.3861, + "step": 4388 + }, + { + "epoch": 0.46, + "learning_rate": 1.3080421229400315e-05, + "loss": 1.4754, + "step": 4389 + }, + { + "epoch": 0.46, + "learning_rate": 1.307693876104752e-05, + "loss": 1.3588, + "step": 4390 + }, + { + "epoch": 0.46, + "learning_rate": 1.3073455880463987e-05, + "loss": 1.3995, + "step": 4391 + }, + { + "epoch": 0.46, + "learning_rate": 1.3069972588116341e-05, + "loss": 1.354, + "step": 4392 + }, + { + "epoch": 0.46, + "learning_rate": 1.3066488884471244e-05, + "loss": 1.3378, + "step": 4393 + }, + { + "epoch": 0.46, + "learning_rate": 1.306300476999543e-05, + "loss": 1.5951, + "step": 4394 + }, + { + "epoch": 0.46, + "learning_rate": 1.305952024515568e-05, + "loss": 1.3661, + "step": 4395 + }, + { + "epoch": 0.46, + "learning_rate": 1.3056035310418826e-05, + "loss": 1.4066, + "step": 4396 + }, + { + "epoch": 0.46, + "learning_rate": 1.3052549966251764e-05, + "loss": 1.3687, + "step": 4397 + }, + { + "epoch": 0.46, + "learning_rate": 1.3049064213121438e-05, + "loss": 1.4573, + "step": 4398 + }, + { + "epoch": 0.46, + "learning_rate": 1.3045578051494852e-05, + "loss": 1.3519, + "step": 4399 + }, + { + "epoch": 0.46, + "learning_rate": 1.3042091481839063e-05, + "loss": 1.2803, + "step": 4400 + }, + { + "epoch": 0.46, + "learning_rate": 1.3038604504621173e-05, + "loss": 1.4014, + "step": 4401 + }, + { + "epoch": 0.46, + "learning_rate": 1.3035117120308358e-05, + "loss": 1.4534, + "step": 4402 + }, + { + "epoch": 0.46, + "learning_rate": 1.3031629329367832e-05, + "loss": 1.4747, + "step": 4403 + }, + { + "epoch": 0.46, + "learning_rate": 1.3028141132266877e-05, + "loss": 1.374, + "step": 4404 + }, + { + "epoch": 0.46, + "learning_rate": 1.3024652529472807e-05, + "loss": 1.4328, + "step": 4405 + }, + { + "epoch": 0.46, + "learning_rate": 1.302116352145302e-05, + "loss": 1.468, + "step": 4406 + }, + { + "epoch": 0.46, + "learning_rate": 1.3017674108674942e-05, + "loss": 1.2947, + "step": 4407 + }, + { + "epoch": 0.46, + "learning_rate": 1.3014184291606077e-05, + "loss": 1.3682, + "step": 4408 + }, + { + "epoch": 0.46, + "learning_rate": 1.3010694070713959e-05, + "loss": 1.3651, + "step": 4409 + }, + { + "epoch": 0.46, + "learning_rate": 1.3007203446466194e-05, + "loss": 1.418, + "step": 4410 + }, + { + "epoch": 0.46, + "learning_rate": 1.3003712419330433e-05, + "loss": 1.416, + "step": 4411 + }, + { + "epoch": 0.46, + "learning_rate": 1.300022098977439e-05, + "loss": 1.2979, + "step": 4412 + }, + { + "epoch": 0.46, + "learning_rate": 1.2996729158265819e-05, + "loss": 1.3868, + "step": 4413 + }, + { + "epoch": 0.46, + "learning_rate": 1.2993236925272542e-05, + "loss": 1.3102, + "step": 4414 + }, + { + "epoch": 0.46, + "learning_rate": 1.2989744291262422e-05, + "loss": 1.3506, + "step": 4415 + }, + { + "epoch": 0.46, + "learning_rate": 1.2986251256703388e-05, + "loss": 1.4018, + "step": 4416 + }, + { + "epoch": 0.46, + "learning_rate": 1.2982757822063417e-05, + "loss": 1.4081, + "step": 4417 + }, + { + "epoch": 0.46, + "learning_rate": 1.2979263987810533e-05, + "loss": 1.3592, + "step": 4418 + }, + { + "epoch": 0.46, + "learning_rate": 1.297576975441283e-05, + "loss": 1.4287, + "step": 4419 + }, + { + "epoch": 0.46, + "learning_rate": 1.2972275122338433e-05, + "loss": 1.4099, + "step": 4420 + }, + { + "epoch": 0.46, + "learning_rate": 1.2968780092055546e-05, + "loss": 1.4005, + "step": 4421 + }, + { + "epoch": 0.46, + "learning_rate": 1.2965284664032401e-05, + "loss": 1.365, + "step": 4422 + }, + { + "epoch": 0.46, + "learning_rate": 1.2961788838737309e-05, + "loss": 1.3588, + "step": 4423 + }, + { + "epoch": 0.46, + "learning_rate": 1.2958292616638606e-05, + "loss": 1.3702, + "step": 4424 + }, + { + "epoch": 0.46, + "learning_rate": 1.2954795998204708e-05, + "loss": 1.3487, + "step": 4425 + }, + { + "epoch": 0.46, + "learning_rate": 1.2951298983904063e-05, + "loss": 1.4395, + "step": 4426 + }, + { + "epoch": 0.46, + "learning_rate": 1.2947801574205193e-05, + "loss": 1.3523, + "step": 4427 + }, + { + "epoch": 0.46, + "learning_rate": 1.2944303769576645e-05, + "loss": 1.3125, + "step": 4428 + }, + { + "epoch": 0.46, + "learning_rate": 1.2940805570487048e-05, + "loss": 1.5476, + "step": 4429 + }, + { + "epoch": 0.46, + "learning_rate": 1.2937306977405062e-05, + "loss": 1.4076, + "step": 4430 + }, + { + "epoch": 0.46, + "learning_rate": 1.2933807990799418e-05, + "loss": 1.3007, + "step": 4431 + }, + { + "epoch": 0.46, + "learning_rate": 1.293030861113888e-05, + "loss": 1.3566, + "step": 4432 + }, + { + "epoch": 0.46, + "learning_rate": 1.2926808838892285e-05, + "loss": 1.3907, + "step": 4433 + }, + { + "epoch": 0.46, + "learning_rate": 1.2923308674528501e-05, + "loss": 1.379, + "step": 4434 + }, + { + "epoch": 0.47, + "learning_rate": 1.2919808118516475e-05, + "loss": 1.4319, + "step": 4435 + }, + { + "epoch": 0.47, + "learning_rate": 1.2916307171325176e-05, + "loss": 1.3392, + "step": 4436 + }, + { + "epoch": 0.47, + "learning_rate": 1.291280583342365e-05, + "loss": 1.401, + "step": 4437 + }, + { + "epoch": 0.47, + "learning_rate": 1.2909304105280984e-05, + "loss": 1.3939, + "step": 4438 + }, + { + "epoch": 0.47, + "learning_rate": 1.2905801987366322e-05, + "loss": 1.4676, + "step": 4439 + }, + { + "epoch": 0.47, + "learning_rate": 1.2902299480148855e-05, + "loss": 1.3957, + "step": 4440 + }, + { + "epoch": 0.47, + "learning_rate": 1.2898796584097828e-05, + "loss": 1.3587, + "step": 4441 + }, + { + "epoch": 0.47, + "learning_rate": 1.2895293299682545e-05, + "loss": 1.5809, + "step": 4442 + }, + { + "epoch": 0.47, + "learning_rate": 1.289178962737235e-05, + "loss": 1.3436, + "step": 4443 + }, + { + "epoch": 0.47, + "learning_rate": 1.2888285567636647e-05, + "loss": 1.4535, + "step": 4444 + }, + { + "epoch": 0.47, + "learning_rate": 1.2884781120944889e-05, + "loss": 1.3377, + "step": 4445 + }, + { + "epoch": 0.47, + "learning_rate": 1.2881276287766587e-05, + "loss": 0.8221, + "step": 4446 + }, + { + "epoch": 0.47, + "learning_rate": 1.2877771068571288e-05, + "loss": 0.7259, + "step": 4447 + }, + { + "epoch": 0.47, + "learning_rate": 1.2874265463828612e-05, + "loss": 0.8279, + "step": 4448 + }, + { + "epoch": 0.47, + "learning_rate": 1.2870759474008213e-05, + "loss": 1.3523, + "step": 4449 + }, + { + "epoch": 0.47, + "learning_rate": 1.2867253099579808e-05, + "loss": 1.3658, + "step": 4450 + }, + { + "epoch": 0.47, + "learning_rate": 1.2863746341013158e-05, + "loss": 1.4112, + "step": 4451 + }, + { + "epoch": 0.47, + "learning_rate": 1.2860239198778085e-05, + "loss": 1.389, + "step": 4452 + }, + { + "epoch": 0.47, + "learning_rate": 1.2856731673344442e-05, + "loss": 1.4066, + "step": 4453 + }, + { + "epoch": 0.47, + "learning_rate": 1.2853223765182165e-05, + "loss": 1.3267, + "step": 4454 + }, + { + "epoch": 0.47, + "learning_rate": 1.2849715474761209e-05, + "loss": 1.3381, + "step": 4455 + }, + { + "epoch": 0.47, + "learning_rate": 1.2846206802551602e-05, + "loss": 1.2882, + "step": 4456 + }, + { + "epoch": 0.47, + "learning_rate": 1.2842697749023414e-05, + "loss": 1.3199, + "step": 4457 + }, + { + "epoch": 0.47, + "learning_rate": 1.2839188314646771e-05, + "loss": 1.3896, + "step": 4458 + }, + { + "epoch": 0.47, + "learning_rate": 1.2835678499891842e-05, + "loss": 1.3186, + "step": 4459 + }, + { + "epoch": 0.47, + "learning_rate": 1.283216830522885e-05, + "loss": 1.3466, + "step": 4460 + }, + { + "epoch": 0.47, + "learning_rate": 1.2828657731128083e-05, + "loss": 1.4678, + "step": 4461 + }, + { + "epoch": 0.47, + "learning_rate": 1.2825146778059857e-05, + "loss": 1.4408, + "step": 4462 + }, + { + "epoch": 0.47, + "learning_rate": 1.2821635446494553e-05, + "loss": 1.3672, + "step": 4463 + }, + { + "epoch": 0.47, + "learning_rate": 1.2818123736902597e-05, + "loss": 1.3836, + "step": 4464 + }, + { + "epoch": 0.47, + "learning_rate": 1.2814611649754472e-05, + "loss": 1.3493, + "step": 4465 + }, + { + "epoch": 0.47, + "learning_rate": 1.2811099185520704e-05, + "loss": 1.3584, + "step": 4466 + }, + { + "epoch": 0.47, + "learning_rate": 1.2807586344671875e-05, + "loss": 1.3551, + "step": 4467 + }, + { + "epoch": 0.47, + "learning_rate": 1.2804073127678612e-05, + "loss": 1.3254, + "step": 4468 + }, + { + "epoch": 0.47, + "learning_rate": 1.28005595350116e-05, + "loss": 1.3405, + "step": 4469 + }, + { + "epoch": 0.47, + "learning_rate": 1.2797045567141568e-05, + "loss": 1.3432, + "step": 4470 + }, + { + "epoch": 0.47, + "learning_rate": 1.2793531224539297e-05, + "loss": 1.4347, + "step": 4471 + }, + { + "epoch": 0.47, + "learning_rate": 1.279001650767562e-05, + "loss": 1.3304, + "step": 4472 + }, + { + "epoch": 0.47, + "learning_rate": 1.278650141702142e-05, + "loss": 1.3244, + "step": 4473 + }, + { + "epoch": 0.47, + "learning_rate": 1.2782985953047625e-05, + "loss": 1.3756, + "step": 4474 + }, + { + "epoch": 0.47, + "learning_rate": 1.2779470116225219e-05, + "loss": 1.5468, + "step": 4475 + }, + { + "epoch": 0.47, + "learning_rate": 1.2775953907025232e-05, + "loss": 1.4316, + "step": 4476 + }, + { + "epoch": 0.47, + "learning_rate": 1.2772437325918752e-05, + "loss": 1.3724, + "step": 4477 + }, + { + "epoch": 0.47, + "learning_rate": 1.27689203733769e-05, + "loss": 1.4458, + "step": 4478 + }, + { + "epoch": 0.47, + "learning_rate": 1.2765403049870865e-05, + "loss": 1.3622, + "step": 4479 + }, + { + "epoch": 0.47, + "learning_rate": 1.2761885355871875e-05, + "loss": 1.3875, + "step": 4480 + }, + { + "epoch": 0.47, + "learning_rate": 1.2758367291851217e-05, + "loss": 1.3577, + "step": 4481 + }, + { + "epoch": 0.47, + "learning_rate": 1.2754848858280211e-05, + "loss": 1.4256, + "step": 4482 + }, + { + "epoch": 0.47, + "learning_rate": 1.2751330055630242e-05, + "loss": 1.3771, + "step": 4483 + }, + { + "epoch": 0.47, + "learning_rate": 1.274781088437274e-05, + "loss": 1.357, + "step": 4484 + }, + { + "epoch": 0.47, + "learning_rate": 1.274429134497918e-05, + "loss": 1.3634, + "step": 4485 + }, + { + "epoch": 0.47, + "learning_rate": 1.2740771437921096e-05, + "loss": 1.3661, + "step": 4486 + }, + { + "epoch": 0.47, + "learning_rate": 1.2737251163670057e-05, + "loss": 1.3819, + "step": 4487 + }, + { + "epoch": 0.47, + "learning_rate": 1.2733730522697696e-05, + "loss": 1.4491, + "step": 4488 + }, + { + "epoch": 0.47, + "learning_rate": 1.2730209515475687e-05, + "loss": 1.3857, + "step": 4489 + }, + { + "epoch": 0.47, + "learning_rate": 1.2726688142475751e-05, + "loss": 1.3837, + "step": 4490 + }, + { + "epoch": 0.47, + "learning_rate": 1.2723166404169663e-05, + "loss": 1.3755, + "step": 4491 + }, + { + "epoch": 0.47, + "learning_rate": 1.271964430102925e-05, + "loss": 1.3767, + "step": 4492 + }, + { + "epoch": 0.47, + "learning_rate": 1.2716121833526376e-05, + "loss": 1.4416, + "step": 4493 + }, + { + "epoch": 0.47, + "learning_rate": 1.2712599002132966e-05, + "loss": 1.5573, + "step": 4494 + }, + { + "epoch": 0.47, + "learning_rate": 1.2709075807320988e-05, + "loss": 1.365, + "step": 4495 + }, + { + "epoch": 0.47, + "learning_rate": 1.270555224956246e-05, + "loss": 1.3862, + "step": 4496 + }, + { + "epoch": 0.47, + "learning_rate": 1.2702028329329445e-05, + "loss": 1.3003, + "step": 4497 + }, + { + "epoch": 0.47, + "learning_rate": 1.2698504047094064e-05, + "loss": 1.3806, + "step": 4498 + }, + { + "epoch": 0.47, + "learning_rate": 1.269497940332847e-05, + "loss": 1.5425, + "step": 4499 + }, + { + "epoch": 0.47, + "learning_rate": 1.269145439850489e-05, + "loss": 1.3541, + "step": 4500 + }, + { + "epoch": 0.47, + "learning_rate": 1.268792903309557e-05, + "loss": 1.4337, + "step": 4501 + }, + { + "epoch": 0.47, + "learning_rate": 1.2684403307572825e-05, + "loss": 1.4004, + "step": 4502 + }, + { + "epoch": 0.47, + "learning_rate": 1.268087722240901e-05, + "loss": 1.9453, + "step": 4503 + }, + { + "epoch": 0.47, + "learning_rate": 1.2677350778076532e-05, + "loss": 1.3907, + "step": 4504 + }, + { + "epoch": 0.47, + "learning_rate": 1.2673823975047839e-05, + "loss": 1.4993, + "step": 4505 + }, + { + "epoch": 0.47, + "learning_rate": 1.2670296813795432e-05, + "loss": 1.4386, + "step": 4506 + }, + { + "epoch": 0.47, + "learning_rate": 1.266676929479187e-05, + "loss": 1.4944, + "step": 4507 + }, + { + "epoch": 0.47, + "learning_rate": 1.266324141850974e-05, + "loss": 1.4311, + "step": 4508 + }, + { + "epoch": 0.47, + "learning_rate": 1.265971318542169e-05, + "loss": 1.3607, + "step": 4509 + }, + { + "epoch": 0.47, + "learning_rate": 1.2656184596000412e-05, + "loss": 1.4007, + "step": 4510 + }, + { + "epoch": 0.47, + "learning_rate": 1.2652655650718645e-05, + "loss": 1.4561, + "step": 4511 + }, + { + "epoch": 0.47, + "learning_rate": 1.2649126350049181e-05, + "loss": 1.4321, + "step": 4512 + }, + { + "epoch": 0.47, + "learning_rate": 1.2645596694464851e-05, + "loss": 1.2856, + "step": 4513 + }, + { + "epoch": 0.47, + "learning_rate": 1.2642066684438543e-05, + "loss": 1.3979, + "step": 4514 + }, + { + "epoch": 0.47, + "learning_rate": 1.2638536320443184e-05, + "loss": 1.4977, + "step": 4515 + }, + { + "epoch": 0.47, + "learning_rate": 1.2635005602951752e-05, + "loss": 1.377, + "step": 4516 + }, + { + "epoch": 0.47, + "learning_rate": 1.2631474532437275e-05, + "loss": 1.4266, + "step": 4517 + }, + { + "epoch": 0.47, + "learning_rate": 1.2627943109372822e-05, + "loss": 1.409, + "step": 4518 + }, + { + "epoch": 0.47, + "learning_rate": 1.2624411334231519e-05, + "loss": 1.3374, + "step": 4519 + }, + { + "epoch": 0.47, + "learning_rate": 1.2620879207486525e-05, + "loss": 1.3765, + "step": 4520 + }, + { + "epoch": 0.47, + "learning_rate": 1.2617346729611061e-05, + "loss": 1.3805, + "step": 4521 + }, + { + "epoch": 0.47, + "learning_rate": 1.2613813901078384e-05, + "loss": 1.3326, + "step": 4522 + }, + { + "epoch": 0.47, + "learning_rate": 1.2610280722361807e-05, + "loss": 1.3909, + "step": 4523 + }, + { + "epoch": 0.47, + "learning_rate": 1.260674719393468e-05, + "loss": 1.3815, + "step": 4524 + }, + { + "epoch": 0.47, + "learning_rate": 1.2603213316270409e-05, + "loss": 1.5589, + "step": 4525 + }, + { + "epoch": 0.47, + "learning_rate": 1.2599679089842437e-05, + "loss": 1.4416, + "step": 4526 + }, + { + "epoch": 0.47, + "learning_rate": 1.259614451512427e-05, + "loss": 1.3529, + "step": 4527 + }, + { + "epoch": 0.47, + "learning_rate": 1.2592609592589437e-05, + "loss": 1.3135, + "step": 4528 + }, + { + "epoch": 0.47, + "learning_rate": 1.2589074322711535e-05, + "loss": 1.4177, + "step": 4529 + }, + { + "epoch": 0.48, + "learning_rate": 1.25855387059642e-05, + "loss": 1.353, + "step": 4530 + }, + { + "epoch": 0.48, + "learning_rate": 1.2582002742821111e-05, + "loss": 1.431, + "step": 4531 + }, + { + "epoch": 0.48, + "learning_rate": 1.2578466433755998e-05, + "loss": 1.3803, + "step": 4532 + }, + { + "epoch": 0.48, + "learning_rate": 1.257492977924263e-05, + "loss": 1.3774, + "step": 4533 + }, + { + "epoch": 0.48, + "learning_rate": 1.2571392779754836e-05, + "loss": 1.4339, + "step": 4534 + }, + { + "epoch": 0.48, + "learning_rate": 1.256785543576648e-05, + "loss": 1.4097, + "step": 4535 + }, + { + "epoch": 0.48, + "learning_rate": 1.2564317747751473e-05, + "loss": 1.4223, + "step": 4536 + }, + { + "epoch": 0.48, + "learning_rate": 1.2560779716183775e-05, + "loss": 1.5148, + "step": 4537 + }, + { + "epoch": 0.48, + "learning_rate": 1.2557241341537394e-05, + "loss": 1.3547, + "step": 4538 + }, + { + "epoch": 0.48, + "learning_rate": 1.255370262428638e-05, + "loss": 1.393, + "step": 4539 + }, + { + "epoch": 0.48, + "learning_rate": 1.2550163564904829e-05, + "loss": 1.3312, + "step": 4540 + }, + { + "epoch": 0.48, + "learning_rate": 1.2546624163866882e-05, + "loss": 1.4193, + "step": 4541 + }, + { + "epoch": 0.48, + "learning_rate": 1.2543084421646735e-05, + "loss": 1.4161, + "step": 4542 + }, + { + "epoch": 0.48, + "learning_rate": 1.2539544338718614e-05, + "loss": 1.4224, + "step": 4543 + }, + { + "epoch": 0.48, + "learning_rate": 1.2536003915556805e-05, + "loss": 1.3484, + "step": 4544 + }, + { + "epoch": 0.48, + "learning_rate": 1.253246315263563e-05, + "loss": 1.4492, + "step": 4545 + }, + { + "epoch": 0.48, + "learning_rate": 1.2528922050429467e-05, + "loss": 1.3549, + "step": 4546 + }, + { + "epoch": 0.48, + "learning_rate": 1.252538060941272e-05, + "loss": 1.45, + "step": 4547 + }, + { + "epoch": 0.48, + "learning_rate": 1.2521838830059865e-05, + "loss": 1.3499, + "step": 4548 + }, + { + "epoch": 0.48, + "learning_rate": 1.2518296712845399e-05, + "loss": 1.3786, + "step": 4549 + }, + { + "epoch": 0.48, + "learning_rate": 1.2514754258243884e-05, + "loss": 1.3394, + "step": 4550 + }, + { + "epoch": 0.48, + "learning_rate": 1.2511211466729909e-05, + "loss": 1.2849, + "step": 4551 + }, + { + "epoch": 0.48, + "learning_rate": 1.250766833877812e-05, + "loss": 1.374, + "step": 4552 + }, + { + "epoch": 0.48, + "learning_rate": 1.2504124874863211e-05, + "loss": 1.3084, + "step": 4553 + }, + { + "epoch": 0.48, + "learning_rate": 1.2500581075459905e-05, + "loss": 1.3348, + "step": 4554 + }, + { + "epoch": 0.48, + "learning_rate": 1.249703694104299e-05, + "loss": 1.3797, + "step": 4555 + }, + { + "epoch": 0.48, + "learning_rate": 1.2493492472087279e-05, + "loss": 1.3371, + "step": 4556 + }, + { + "epoch": 0.48, + "learning_rate": 1.248994766906765e-05, + "loss": 1.3974, + "step": 4557 + }, + { + "epoch": 0.48, + "learning_rate": 1.2486402532459007e-05, + "loss": 1.388, + "step": 4558 + }, + { + "epoch": 0.48, + "learning_rate": 1.2482857062736313e-05, + "loss": 1.3619, + "step": 4559 + }, + { + "epoch": 0.48, + "learning_rate": 1.2479311260374565e-05, + "loss": 1.4123, + "step": 4560 + }, + { + "epoch": 0.48, + "learning_rate": 1.2475765125848814e-05, + "loss": 1.5485, + "step": 4561 + }, + { + "epoch": 0.48, + "learning_rate": 1.247221865963415e-05, + "loss": 1.4965, + "step": 4562 + }, + { + "epoch": 0.48, + "learning_rate": 1.2468671862205705e-05, + "loss": 1.4352, + "step": 4563 + }, + { + "epoch": 0.48, + "learning_rate": 1.246512473403866e-05, + "loss": 1.3935, + "step": 4564 + }, + { + "epoch": 0.48, + "learning_rate": 1.2461577275608243e-05, + "loss": 1.3798, + "step": 4565 + }, + { + "epoch": 0.48, + "learning_rate": 1.2458029487389718e-05, + "loss": 1.4039, + "step": 4566 + }, + { + "epoch": 0.48, + "learning_rate": 1.2454481369858397e-05, + "loss": 1.3723, + "step": 4567 + }, + { + "epoch": 0.48, + "learning_rate": 1.245093292348964e-05, + "loss": 1.3713, + "step": 4568 + }, + { + "epoch": 0.48, + "learning_rate": 1.2447384148758847e-05, + "loss": 1.4083, + "step": 4569 + }, + { + "epoch": 0.48, + "learning_rate": 1.244383504614146e-05, + "loss": 1.2811, + "step": 4570 + }, + { + "epoch": 0.48, + "learning_rate": 1.2440285616112968e-05, + "loss": 1.3509, + "step": 4571 + }, + { + "epoch": 0.48, + "learning_rate": 1.2436735859148905e-05, + "loss": 1.3481, + "step": 4572 + }, + { + "epoch": 0.48, + "learning_rate": 1.2433185775724847e-05, + "loss": 1.4168, + "step": 4573 + }, + { + "epoch": 0.48, + "learning_rate": 1.2429635366316418e-05, + "loss": 1.3671, + "step": 4574 + }, + { + "epoch": 0.48, + "learning_rate": 1.2426084631399271e-05, + "loss": 1.6514, + "step": 4575 + }, + { + "epoch": 0.48, + "learning_rate": 1.2422533571449123e-05, + "loss": 1.3564, + "step": 4576 + }, + { + "epoch": 0.48, + "learning_rate": 1.2418982186941721e-05, + "loss": 1.4586, + "step": 4577 + }, + { + "epoch": 0.48, + "eval_loss": 1.4425245523452759, + "eval_runtime": 77.3853, + "eval_samples_per_second": 1.667, + "eval_steps_per_second": 0.116, + "step": 4577 + }, + { + "epoch": 0.48, + "learning_rate": 1.2415430478352858e-05, + "loss": 1.3922, + "step": 4578 + }, + { + "epoch": 0.48, + "learning_rate": 1.2411878446158374e-05, + "loss": 1.3903, + "step": 4579 + }, + { + "epoch": 0.48, + "learning_rate": 1.240832609083415e-05, + "loss": 1.3537, + "step": 4580 + }, + { + "epoch": 0.48, + "learning_rate": 1.2404773412856113e-05, + "loss": 1.356, + "step": 4581 + }, + { + "epoch": 0.48, + "learning_rate": 1.2401220412700223e-05, + "loss": 1.4483, + "step": 4582 + }, + { + "epoch": 0.48, + "learning_rate": 1.2397667090842496e-05, + "loss": 1.3926, + "step": 4583 + }, + { + "epoch": 0.48, + "learning_rate": 1.2394113447758986e-05, + "loss": 1.4816, + "step": 4584 + }, + { + "epoch": 0.48, + "learning_rate": 1.2390559483925788e-05, + "loss": 1.3742, + "step": 4585 + }, + { + "epoch": 0.48, + "learning_rate": 1.2387005199819044e-05, + "loss": 1.4476, + "step": 4586 + }, + { + "epoch": 0.48, + "learning_rate": 1.2383450595914932e-05, + "loss": 1.4029, + "step": 4587 + }, + { + "epoch": 0.48, + "learning_rate": 1.2379895672689683e-05, + "loss": 1.4797, + "step": 4588 + }, + { + "epoch": 0.48, + "learning_rate": 1.2376340430619565e-05, + "loss": 1.3366, + "step": 4589 + }, + { + "epoch": 0.48, + "learning_rate": 1.2372784870180885e-05, + "loss": 1.4226, + "step": 4590 + }, + { + "epoch": 0.48, + "learning_rate": 1.2369228991849997e-05, + "loss": 1.3668, + "step": 4591 + }, + { + "epoch": 0.48, + "learning_rate": 1.2365672796103305e-05, + "loss": 1.4932, + "step": 4592 + }, + { + "epoch": 0.48, + "learning_rate": 1.236211628341724e-05, + "loss": 1.4088, + "step": 4593 + }, + { + "epoch": 0.48, + "learning_rate": 1.2358559454268284e-05, + "loss": 1.3616, + "step": 4594 + }, + { + "epoch": 0.48, + "learning_rate": 1.2355002309132961e-05, + "loss": 1.4345, + "step": 4595 + }, + { + "epoch": 0.48, + "learning_rate": 1.2351444848487844e-05, + "loss": 1.4025, + "step": 4596 + }, + { + "epoch": 0.48, + "learning_rate": 1.2347887072809533e-05, + "loss": 1.3895, + "step": 4597 + }, + { + "epoch": 0.48, + "learning_rate": 1.2344328982574678e-05, + "loss": 1.3326, + "step": 4598 + }, + { + "epoch": 0.48, + "learning_rate": 1.234077057825998e-05, + "loss": 1.4249, + "step": 4599 + }, + { + "epoch": 0.48, + "learning_rate": 1.2337211860342167e-05, + "loss": 1.3649, + "step": 4600 + }, + { + "epoch": 0.48, + "learning_rate": 1.2333652829298016e-05, + "loss": 1.3831, + "step": 4601 + }, + { + "epoch": 0.48, + "learning_rate": 1.2330093485604346e-05, + "loss": 1.3748, + "step": 4602 + }, + { + "epoch": 0.48, + "learning_rate": 1.2326533829738022e-05, + "loss": 1.386, + "step": 4603 + }, + { + "epoch": 0.48, + "learning_rate": 1.2322973862175941e-05, + "loss": 1.3923, + "step": 4604 + }, + { + "epoch": 0.48, + "learning_rate": 1.2319413583395052e-05, + "loss": 1.3638, + "step": 4605 + }, + { + "epoch": 0.48, + "learning_rate": 1.2315852993872335e-05, + "loss": 1.3476, + "step": 4606 + }, + { + "epoch": 0.48, + "learning_rate": 1.2312292094084824e-05, + "loss": 1.3581, + "step": 4607 + }, + { + "epoch": 0.48, + "learning_rate": 1.2308730884509583e-05, + "loss": 1.3554, + "step": 4608 + }, + { + "epoch": 0.48, + "learning_rate": 1.2305169365623724e-05, + "loss": 1.3676, + "step": 4609 + }, + { + "epoch": 0.48, + "learning_rate": 1.2301607537904399e-05, + "loss": 1.24, + "step": 4610 + }, + { + "epoch": 0.48, + "learning_rate": 1.2298045401828803e-05, + "loss": 1.3295, + "step": 4611 + }, + { + "epoch": 0.48, + "learning_rate": 1.2294482957874169e-05, + "loss": 1.5684, + "step": 4612 + }, + { + "epoch": 0.48, + "learning_rate": 1.2290920206517774e-05, + "loss": 1.3403, + "step": 4613 + }, + { + "epoch": 0.48, + "learning_rate": 1.2287357148236933e-05, + "loss": 1.349, + "step": 4614 + }, + { + "epoch": 0.48, + "learning_rate": 1.2283793783509008e-05, + "loss": 1.4261, + "step": 4615 + }, + { + "epoch": 0.48, + "learning_rate": 1.2280230112811395e-05, + "loss": 1.322, + "step": 4616 + }, + { + "epoch": 0.48, + "learning_rate": 1.2276666136621538e-05, + "loss": 1.3399, + "step": 4617 + }, + { + "epoch": 0.48, + "learning_rate": 1.2273101855416912e-05, + "loss": 1.3878, + "step": 4618 + }, + { + "epoch": 0.48, + "learning_rate": 1.2269537269675044e-05, + "loss": 1.4733, + "step": 4619 + }, + { + "epoch": 0.48, + "learning_rate": 1.2265972379873497e-05, + "loss": 1.419, + "step": 4620 + }, + { + "epoch": 0.48, + "learning_rate": 1.226240718648987e-05, + "loss": 1.3918, + "step": 4621 + }, + { + "epoch": 0.48, + "learning_rate": 1.2258841690001815e-05, + "loss": 1.3398, + "step": 4622 + }, + { + "epoch": 0.48, + "learning_rate": 1.225527589088701e-05, + "loss": 1.4091, + "step": 4623 + }, + { + "epoch": 0.48, + "learning_rate": 1.2251709789623185e-05, + "loss": 1.3291, + "step": 4624 + }, + { + "epoch": 0.49, + "learning_rate": 1.2248143386688101e-05, + "loss": 1.4288, + "step": 4625 + }, + { + "epoch": 0.49, + "learning_rate": 1.224457668255957e-05, + "loss": 1.2942, + "step": 4626 + }, + { + "epoch": 0.49, + "learning_rate": 1.2241009677715437e-05, + "loss": 1.4014, + "step": 4627 + }, + { + "epoch": 0.49, + "learning_rate": 1.2237442372633586e-05, + "loss": 1.3823, + "step": 4628 + }, + { + "epoch": 0.49, + "learning_rate": 1.2233874767791945e-05, + "loss": 1.3556, + "step": 4629 + }, + { + "epoch": 0.49, + "learning_rate": 1.2230306863668485e-05, + "loss": 1.411, + "step": 4630 + }, + { + "epoch": 0.49, + "learning_rate": 1.2226738660741212e-05, + "loss": 1.4347, + "step": 4631 + }, + { + "epoch": 0.49, + "learning_rate": 1.2223170159488169e-05, + "loss": 1.3095, + "step": 4632 + }, + { + "epoch": 0.49, + "learning_rate": 1.221960136038745e-05, + "loss": 1.4272, + "step": 4633 + }, + { + "epoch": 0.49, + "learning_rate": 1.221603226391718e-05, + "loss": 1.367, + "step": 4634 + }, + { + "epoch": 0.49, + "learning_rate": 1.2212462870555523e-05, + "loss": 1.3357, + "step": 4635 + }, + { + "epoch": 0.49, + "learning_rate": 1.220889318078069e-05, + "loss": 1.3634, + "step": 4636 + }, + { + "epoch": 0.49, + "learning_rate": 1.2205323195070927e-05, + "loss": 1.4143, + "step": 4637 + }, + { + "epoch": 0.49, + "learning_rate": 1.2201752913904519e-05, + "loss": 1.4865, + "step": 4638 + }, + { + "epoch": 0.49, + "learning_rate": 1.2198182337759794e-05, + "loss": 1.451, + "step": 4639 + }, + { + "epoch": 0.49, + "learning_rate": 1.2194611467115116e-05, + "loss": 1.3953, + "step": 4640 + }, + { + "epoch": 0.49, + "learning_rate": 1.2191040302448887e-05, + "loss": 1.4099, + "step": 4641 + }, + { + "epoch": 0.49, + "learning_rate": 1.2187468844239559e-05, + "loss": 1.3338, + "step": 4642 + }, + { + "epoch": 0.49, + "learning_rate": 1.2183897092965609e-05, + "loss": 1.4392, + "step": 4643 + }, + { + "epoch": 0.49, + "learning_rate": 1.2180325049105559e-05, + "loss": 1.3196, + "step": 4644 + }, + { + "epoch": 0.49, + "learning_rate": 1.2176752713137977e-05, + "loss": 1.3727, + "step": 4645 + }, + { + "epoch": 0.49, + "learning_rate": 1.2173180085541464e-05, + "loss": 1.3118, + "step": 4646 + }, + { + "epoch": 0.49, + "learning_rate": 1.2169607166794655e-05, + "loss": 1.3695, + "step": 4647 + }, + { + "epoch": 0.49, + "learning_rate": 1.2166033957376231e-05, + "loss": 1.3568, + "step": 4648 + }, + { + "epoch": 0.49, + "learning_rate": 1.216246045776491e-05, + "loss": 1.3492, + "step": 4649 + }, + { + "epoch": 0.49, + "learning_rate": 1.2158886668439455e-05, + "loss": 1.3445, + "step": 4650 + }, + { + "epoch": 0.49, + "learning_rate": 1.2155312589878654e-05, + "loss": 1.3756, + "step": 4651 + }, + { + "epoch": 0.49, + "learning_rate": 1.2151738222561344e-05, + "loss": 1.3681, + "step": 4652 + }, + { + "epoch": 0.49, + "learning_rate": 1.2148163566966403e-05, + "loss": 1.4345, + "step": 4653 + }, + { + "epoch": 0.49, + "learning_rate": 1.2144588623572738e-05, + "loss": 1.5102, + "step": 4654 + }, + { + "epoch": 0.49, + "learning_rate": 1.2141013392859297e-05, + "loss": 1.3531, + "step": 4655 + }, + { + "epoch": 0.49, + "learning_rate": 1.2137437875305075e-05, + "loss": 1.3824, + "step": 4656 + }, + { + "epoch": 0.49, + "learning_rate": 1.2133862071389099e-05, + "loss": 1.4227, + "step": 4657 + }, + { + "epoch": 0.49, + "learning_rate": 1.2130285981590433e-05, + "loss": 1.3479, + "step": 4658 + }, + { + "epoch": 0.49, + "learning_rate": 1.2126709606388181e-05, + "loss": 1.381, + "step": 4659 + }, + { + "epoch": 0.49, + "learning_rate": 1.2123132946261485e-05, + "loss": 1.3847, + "step": 4660 + }, + { + "epoch": 0.49, + "learning_rate": 1.2119556001689527e-05, + "loss": 1.3549, + "step": 4661 + }, + { + "epoch": 0.49, + "learning_rate": 1.2115978773151527e-05, + "loss": 1.3754, + "step": 4662 + }, + { + "epoch": 0.49, + "learning_rate": 1.2112401261126736e-05, + "loss": 1.3329, + "step": 4663 + }, + { + "epoch": 0.49, + "learning_rate": 1.2108823466094453e-05, + "loss": 1.4228, + "step": 4664 + }, + { + "epoch": 0.49, + "learning_rate": 1.2105245388534013e-05, + "loss": 1.4138, + "step": 4665 + }, + { + "epoch": 0.49, + "learning_rate": 1.2101667028924782e-05, + "loss": 1.3538, + "step": 4666 + }, + { + "epoch": 0.49, + "learning_rate": 1.2098088387746168e-05, + "loss": 1.4848, + "step": 4667 + }, + { + "epoch": 0.49, + "learning_rate": 1.2094509465477619e-05, + "loss": 1.5719, + "step": 4668 + }, + { + "epoch": 0.49, + "learning_rate": 1.209093026259862e-05, + "loss": 1.3863, + "step": 4669 + }, + { + "epoch": 0.49, + "learning_rate": 1.2087350779588691e-05, + "loss": 1.4425, + "step": 4670 + }, + { + "epoch": 0.49, + "learning_rate": 1.2083771016927386e-05, + "loss": 1.3655, + "step": 4671 + }, + { + "epoch": 0.49, + "learning_rate": 1.208019097509431e-05, + "loss": 1.3629, + "step": 4672 + }, + { + "epoch": 0.49, + "learning_rate": 1.2076610654569092e-05, + "loss": 1.3849, + "step": 4673 + }, + { + "epoch": 0.49, + "learning_rate": 1.20730300558314e-05, + "loss": 1.3763, + "step": 4674 + }, + { + "epoch": 0.49, + "learning_rate": 1.2069449179360945e-05, + "loss": 1.5316, + "step": 4675 + }, + { + "epoch": 0.49, + "learning_rate": 1.2065868025637476e-05, + "loss": 1.2873, + "step": 4676 + }, + { + "epoch": 0.49, + "learning_rate": 1.2062286595140773e-05, + "loss": 1.3642, + "step": 4677 + }, + { + "epoch": 0.49, + "learning_rate": 1.2058704888350652e-05, + "loss": 1.3782, + "step": 4678 + }, + { + "epoch": 0.49, + "learning_rate": 1.2055122905746972e-05, + "loss": 1.4597, + "step": 4679 + }, + { + "epoch": 0.49, + "learning_rate": 1.205154064780963e-05, + "loss": 1.3952, + "step": 4680 + }, + { + "epoch": 0.49, + "learning_rate": 1.2047958115018554e-05, + "loss": 1.4012, + "step": 4681 + }, + { + "epoch": 0.49, + "learning_rate": 1.204437530785371e-05, + "loss": 1.3432, + "step": 4682 + }, + { + "epoch": 0.49, + "learning_rate": 1.2040792226795101e-05, + "loss": 1.4111, + "step": 4683 + }, + { + "epoch": 0.49, + "learning_rate": 1.2037208872322773e-05, + "loss": 1.4357, + "step": 4684 + }, + { + "epoch": 0.49, + "learning_rate": 1.2033625244916803e-05, + "loss": 1.3908, + "step": 4685 + }, + { + "epoch": 0.49, + "learning_rate": 1.2030041345057298e-05, + "loss": 1.3804, + "step": 4686 + }, + { + "epoch": 0.49, + "learning_rate": 1.2026457173224412e-05, + "loss": 1.4523, + "step": 4687 + }, + { + "epoch": 0.49, + "learning_rate": 1.2022872729898336e-05, + "loss": 1.4266, + "step": 4688 + }, + { + "epoch": 0.49, + "learning_rate": 1.201928801555929e-05, + "loss": 1.3345, + "step": 4689 + }, + { + "epoch": 0.49, + "learning_rate": 1.2015703030687532e-05, + "loss": 1.1714, + "step": 4690 + }, + { + "epoch": 0.49, + "learning_rate": 1.2012117775763361e-05, + "loss": 1.3899, + "step": 4691 + }, + { + "epoch": 0.49, + "learning_rate": 1.2008532251267109e-05, + "loss": 1.43, + "step": 4692 + }, + { + "epoch": 0.49, + "learning_rate": 1.2004946457679144e-05, + "loss": 1.4302, + "step": 4693 + }, + { + "epoch": 0.49, + "learning_rate": 1.2001360395479865e-05, + "loss": 1.3452, + "step": 4694 + }, + { + "epoch": 0.49, + "learning_rate": 1.1997774065149716e-05, + "loss": 1.3383, + "step": 4695 + }, + { + "epoch": 0.49, + "learning_rate": 1.1994187467169176e-05, + "loss": 1.3677, + "step": 4696 + }, + { + "epoch": 0.49, + "learning_rate": 1.1990600602018755e-05, + "loss": 1.4486, + "step": 4697 + }, + { + "epoch": 0.49, + "learning_rate": 1.1987013470178998e-05, + "loss": 1.4059, + "step": 4698 + }, + { + "epoch": 0.49, + "learning_rate": 1.198342607213049e-05, + "loss": 1.3558, + "step": 4699 + }, + { + "epoch": 0.49, + "learning_rate": 1.1979838408353854e-05, + "loss": 1.3931, + "step": 4700 + }, + { + "epoch": 0.49, + "learning_rate": 1.197625047932974e-05, + "loss": 1.5409, + "step": 4701 + }, + { + "epoch": 0.49, + "learning_rate": 1.197266228553884e-05, + "loss": 1.4878, + "step": 4702 + }, + { + "epoch": 0.49, + "learning_rate": 1.196907382746188e-05, + "loss": 1.3581, + "step": 4703 + }, + { + "epoch": 0.49, + "learning_rate": 1.1965485105579621e-05, + "loss": 1.3617, + "step": 4704 + }, + { + "epoch": 0.49, + "learning_rate": 1.1961896120372857e-05, + "loss": 1.399, + "step": 4705 + }, + { + "epoch": 0.49, + "learning_rate": 1.1958306872322425e-05, + "loss": 1.3861, + "step": 4706 + }, + { + "epoch": 0.49, + "learning_rate": 1.1954717361909186e-05, + "loss": 1.4719, + "step": 4707 + }, + { + "epoch": 0.49, + "learning_rate": 1.195112758961405e-05, + "loss": 1.393, + "step": 4708 + }, + { + "epoch": 0.49, + "learning_rate": 1.1947537555917947e-05, + "loss": 1.4252, + "step": 4709 + }, + { + "epoch": 0.49, + "learning_rate": 1.194394726130185e-05, + "loss": 1.4187, + "step": 4710 + }, + { + "epoch": 0.49, + "learning_rate": 1.1940356706246772e-05, + "loss": 1.4822, + "step": 4711 + }, + { + "epoch": 0.49, + "learning_rate": 1.193676589123375e-05, + "loss": 1.4259, + "step": 4712 + }, + { + "epoch": 0.49, + "learning_rate": 1.1933174816743857e-05, + "loss": 1.4226, + "step": 4713 + }, + { + "epoch": 0.49, + "learning_rate": 1.1929583483258216e-05, + "loss": 1.3701, + "step": 4714 + }, + { + "epoch": 0.49, + "learning_rate": 1.1925991891257967e-05, + "loss": 1.406, + "step": 4715 + }, + { + "epoch": 0.49, + "learning_rate": 1.1922400041224288e-05, + "loss": 1.4593, + "step": 4716 + }, + { + "epoch": 0.49, + "learning_rate": 1.1918807933638401e-05, + "loss": 1.3443, + "step": 4717 + }, + { + "epoch": 0.49, + "learning_rate": 1.1915215568981552e-05, + "loss": 1.3523, + "step": 4718 + }, + { + "epoch": 0.49, + "learning_rate": 1.1911622947735027e-05, + "loss": 1.3175, + "step": 4719 + }, + { + "epoch": 0.49, + "learning_rate": 1.1908030070380143e-05, + "loss": 1.3974, + "step": 4720 + }, + { + "epoch": 0.5, + "learning_rate": 1.1904436937398257e-05, + "loss": 1.386, + "step": 4721 + }, + { + "epoch": 0.5, + "learning_rate": 1.1900843549270753e-05, + "loss": 1.3684, + "step": 4722 + }, + { + "epoch": 0.5, + "learning_rate": 1.1897249906479054e-05, + "loss": 1.383, + "step": 4723 + }, + { + "epoch": 0.5, + "learning_rate": 1.1893656009504617e-05, + "loss": 1.38, + "step": 4724 + }, + { + "epoch": 0.5, + "learning_rate": 1.1890061858828928e-05, + "loss": 1.3844, + "step": 4725 + }, + { + "epoch": 0.5, + "learning_rate": 1.1886467454933515e-05, + "loss": 1.3252, + "step": 4726 + }, + { + "epoch": 0.5, + "learning_rate": 1.1882872798299934e-05, + "loss": 1.3434, + "step": 4727 + }, + { + "epoch": 0.5, + "learning_rate": 1.1879277889409779e-05, + "loss": 1.4115, + "step": 4728 + }, + { + "epoch": 0.5, + "learning_rate": 1.1875682728744669e-05, + "loss": 1.1911, + "step": 4729 + }, + { + "epoch": 0.5, + "learning_rate": 1.1872087316786272e-05, + "loss": 1.2794, + "step": 4730 + }, + { + "epoch": 0.5, + "learning_rate": 1.1868491654016274e-05, + "loss": 1.3961, + "step": 4731 + }, + { + "epoch": 0.5, + "learning_rate": 1.1864895740916404e-05, + "loss": 1.4965, + "step": 4732 + }, + { + "epoch": 0.5, + "learning_rate": 1.1861299577968419e-05, + "loss": 1.3932, + "step": 4733 + }, + { + "epoch": 0.5, + "learning_rate": 1.185770316565412e-05, + "loss": 1.3926, + "step": 4734 + }, + { + "epoch": 0.5, + "learning_rate": 1.1854106504455327e-05, + "loss": 1.3964, + "step": 4735 + }, + { + "epoch": 0.5, + "learning_rate": 1.1850509594853901e-05, + "loss": 1.3666, + "step": 4736 + }, + { + "epoch": 0.5, + "learning_rate": 1.1846912437331736e-05, + "loss": 1.4364, + "step": 4737 + }, + { + "epoch": 0.5, + "learning_rate": 1.1843315032370762e-05, + "loss": 1.3537, + "step": 4738 + }, + { + "epoch": 0.5, + "learning_rate": 1.1839717380452935e-05, + "loss": 1.4083, + "step": 4739 + }, + { + "epoch": 0.5, + "learning_rate": 1.1836119482060247e-05, + "loss": 1.3881, + "step": 4740 + }, + { + "epoch": 0.5, + "learning_rate": 1.1832521337674727e-05, + "loss": 1.4127, + "step": 4741 + }, + { + "epoch": 0.5, + "learning_rate": 1.1828922947778436e-05, + "loss": 1.3433, + "step": 4742 + }, + { + "epoch": 0.5, + "learning_rate": 1.1825324312853461e-05, + "loss": 1.486, + "step": 4743 + }, + { + "epoch": 0.5, + "learning_rate": 1.1821725433381925e-05, + "loss": 1.335, + "step": 4744 + }, + { + "epoch": 0.5, + "learning_rate": 1.1818126309845993e-05, + "loss": 1.3827, + "step": 4745 + }, + { + "epoch": 0.5, + "learning_rate": 1.181452694272785e-05, + "loss": 1.3146, + "step": 4746 + }, + { + "epoch": 0.5, + "learning_rate": 1.1810927332509717e-05, + "loss": 1.3543, + "step": 4747 + }, + { + "epoch": 0.5, + "learning_rate": 1.1807327479673852e-05, + "loss": 1.3544, + "step": 4748 + }, + { + "epoch": 0.5, + "learning_rate": 1.1803727384702543e-05, + "loss": 1.3677, + "step": 4749 + }, + { + "epoch": 0.5, + "learning_rate": 1.1800127048078111e-05, + "loss": 1.3842, + "step": 4750 + }, + { + "epoch": 0.5, + "learning_rate": 1.1796526470282907e-05, + "loss": 1.3495, + "step": 4751 + }, + { + "epoch": 0.5, + "learning_rate": 1.1792925651799314e-05, + "loss": 1.481, + "step": 4752 + }, + { + "epoch": 0.5, + "learning_rate": 1.1789324593109754e-05, + "loss": 1.3482, + "step": 4753 + }, + { + "epoch": 0.5, + "learning_rate": 1.1785723294696673e-05, + "loss": 1.2805, + "step": 4754 + }, + { + "epoch": 0.5, + "learning_rate": 1.1782121757042555e-05, + "loss": 1.3458, + "step": 4755 + }, + { + "epoch": 0.5, + "learning_rate": 1.1778519980629907e-05, + "loss": 1.3937, + "step": 4756 + }, + { + "epoch": 0.5, + "learning_rate": 1.1774917965941284e-05, + "loss": 1.3873, + "step": 4757 + }, + { + "epoch": 0.5, + "learning_rate": 1.1771315713459258e-05, + "loss": 1.3512, + "step": 4758 + }, + { + "epoch": 0.5, + "learning_rate": 1.1767713223666436e-05, + "loss": 1.4465, + "step": 4759 + }, + { + "epoch": 0.5, + "learning_rate": 1.1764110497045463e-05, + "loss": 1.4233, + "step": 4760 + }, + { + "epoch": 0.5, + "learning_rate": 1.1760507534079011e-05, + "loss": 1.4818, + "step": 4761 + }, + { + "epoch": 0.5, + "learning_rate": 1.1756904335249786e-05, + "loss": 1.2933, + "step": 4762 + }, + { + "epoch": 0.5, + "learning_rate": 1.1753300901040518e-05, + "loss": 1.3524, + "step": 4763 + }, + { + "epoch": 0.5, + "learning_rate": 1.1749697231933981e-05, + "loss": 1.4909, + "step": 4764 + }, + { + "epoch": 0.5, + "learning_rate": 1.1746093328412975e-05, + "loss": 1.2912, + "step": 4765 + }, + { + "epoch": 0.5, + "learning_rate": 1.1742489190960325e-05, + "loss": 1.3372, + "step": 4766 + }, + { + "epoch": 0.5, + "learning_rate": 1.1738884820058893e-05, + "loss": 1.3036, + "step": 4767 + }, + { + "epoch": 0.5, + "learning_rate": 1.1735280216191578e-05, + "loss": 1.3189, + "step": 4768 + }, + { + "epoch": 0.5, + "learning_rate": 1.1731675379841298e-05, + "loss": 1.4146, + "step": 4769 + }, + { + "epoch": 0.5, + "learning_rate": 1.1728070311491013e-05, + "loss": 1.3309, + "step": 4770 + }, + { + "epoch": 0.5, + "learning_rate": 1.1724465011623705e-05, + "loss": 1.3427, + "step": 4771 + }, + { + "epoch": 0.5, + "learning_rate": 1.1720859480722395e-05, + "loss": 1.4033, + "step": 4772 + }, + { + "epoch": 0.5, + "learning_rate": 1.1717253719270135e-05, + "loss": 1.3832, + "step": 4773 + }, + { + "epoch": 0.5, + "learning_rate": 1.1713647727749994e-05, + "loss": 1.4074, + "step": 4774 + }, + { + "epoch": 0.5, + "learning_rate": 1.1710041506645092e-05, + "loss": 1.3579, + "step": 4775 + }, + { + "epoch": 0.5, + "learning_rate": 1.1706435056438564e-05, + "loss": 1.3685, + "step": 4776 + }, + { + "epoch": 0.5, + "eval_loss": 1.436767816543579, + "eval_runtime": 77.4332, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 4776 + }, + { + "epoch": 0.5, + "learning_rate": 1.1702828377613584e-05, + "loss": 1.5843, + "step": 4777 + }, + { + "epoch": 0.5, + "learning_rate": 1.1699221470653355e-05, + "loss": 1.4168, + "step": 4778 + }, + { + "epoch": 0.5, + "learning_rate": 1.1695614336041108e-05, + "loss": 1.3515, + "step": 4779 + }, + { + "epoch": 0.5, + "learning_rate": 1.169200697426011e-05, + "loss": 1.3214, + "step": 4780 + }, + { + "epoch": 0.5, + "learning_rate": 1.1688399385793652e-05, + "loss": 1.3728, + "step": 4781 + }, + { + "epoch": 0.5, + "learning_rate": 1.1684791571125054e-05, + "loss": 1.3759, + "step": 4782 + }, + { + "epoch": 0.5, + "learning_rate": 1.1681183530737678e-05, + "loss": 1.4955, + "step": 4783 + }, + { + "epoch": 0.5, + "learning_rate": 1.1677575265114904e-05, + "loss": 1.4284, + "step": 4784 + }, + { + "epoch": 0.5, + "learning_rate": 1.1673966774740151e-05, + "loss": 1.3725, + "step": 4785 + }, + { + "epoch": 0.5, + "learning_rate": 1.1670358060096858e-05, + "loss": 1.3612, + "step": 4786 + }, + { + "epoch": 0.5, + "learning_rate": 1.1666749121668506e-05, + "loss": 1.3021, + "step": 4787 + }, + { + "epoch": 0.5, + "learning_rate": 1.1663139959938597e-05, + "loss": 1.4399, + "step": 4788 + }, + { + "epoch": 0.5, + "learning_rate": 1.1659530575390668e-05, + "loss": 1.3511, + "step": 4789 + }, + { + "epoch": 0.5, + "learning_rate": 1.1655920968508276e-05, + "loss": 1.4211, + "step": 4790 + }, + { + "epoch": 0.5, + "learning_rate": 1.1652311139775028e-05, + "loss": 1.343, + "step": 4791 + }, + { + "epoch": 0.5, + "learning_rate": 1.1648701089674541e-05, + "loss": 1.3838, + "step": 4792 + }, + { + "epoch": 0.5, + "learning_rate": 1.164509081869047e-05, + "loss": 1.342, + "step": 4793 + }, + { + "epoch": 0.5, + "learning_rate": 1.1641480327306494e-05, + "loss": 1.3831, + "step": 4794 + }, + { + "epoch": 0.5, + "learning_rate": 1.1637869616006335e-05, + "loss": 1.4102, + "step": 4795 + }, + { + "epoch": 0.5, + "learning_rate": 1.1634258685273732e-05, + "loss": 1.4184, + "step": 4796 + }, + { + "epoch": 0.5, + "learning_rate": 1.1630647535592455e-05, + "loss": 1.3974, + "step": 4797 + }, + { + "epoch": 0.5, + "learning_rate": 1.1627036167446302e-05, + "loss": 1.251, + "step": 4798 + }, + { + "epoch": 0.5, + "learning_rate": 1.1623424581319113e-05, + "loss": 1.3485, + "step": 4799 + }, + { + "epoch": 0.5, + "learning_rate": 1.1619812777694742e-05, + "loss": 1.3544, + "step": 4800 + }, + { + "epoch": 0.5, + "learning_rate": 1.1616200757057076e-05, + "loss": 1.3772, + "step": 4801 + }, + { + "epoch": 0.5, + "learning_rate": 1.1612588519890038e-05, + "loss": 1.3082, + "step": 4802 + }, + { + "epoch": 0.5, + "learning_rate": 1.160897606667757e-05, + "loss": 1.3634, + "step": 4803 + }, + { + "epoch": 0.5, + "learning_rate": 1.1605363397903655e-05, + "loss": 1.3682, + "step": 4804 + }, + { + "epoch": 0.5, + "learning_rate": 1.1601750514052288e-05, + "loss": 1.3258, + "step": 4805 + }, + { + "epoch": 0.5, + "learning_rate": 1.1598137415607511e-05, + "loss": 1.279, + "step": 4806 + }, + { + "epoch": 0.5, + "learning_rate": 1.1594524103053382e-05, + "loss": 1.3759, + "step": 4807 + }, + { + "epoch": 0.5, + "learning_rate": 1.1590910576873995e-05, + "loss": 1.5404, + "step": 4808 + }, + { + "epoch": 0.5, + "learning_rate": 1.1587296837553463e-05, + "loss": 1.4949, + "step": 4809 + }, + { + "epoch": 0.5, + "learning_rate": 1.1583682885575943e-05, + "loss": 1.3501, + "step": 4810 + }, + { + "epoch": 0.5, + "learning_rate": 1.1580068721425608e-05, + "loss": 1.3898, + "step": 4811 + }, + { + "epoch": 0.5, + "learning_rate": 1.157645434558666e-05, + "loss": 1.3265, + "step": 4812 + }, + { + "epoch": 0.5, + "learning_rate": 1.1572839758543338e-05, + "loss": 1.3454, + "step": 4813 + }, + { + "epoch": 0.5, + "learning_rate": 1.1569224960779899e-05, + "loss": 1.4065, + "step": 4814 + }, + { + "epoch": 0.5, + "learning_rate": 1.156560995278064e-05, + "loss": 1.4932, + "step": 4815 + }, + { + "epoch": 0.51, + "learning_rate": 1.156199473502987e-05, + "loss": 1.4224, + "step": 4816 + }, + { + "epoch": 0.51, + "learning_rate": 1.1558379308011937e-05, + "loss": 1.3884, + "step": 4817 + }, + { + "epoch": 0.51, + "learning_rate": 1.1554763672211222e-05, + "loss": 1.3355, + "step": 4818 + }, + { + "epoch": 0.51, + "learning_rate": 1.1551147828112124e-05, + "loss": 1.4281, + "step": 4819 + }, + { + "epoch": 0.51, + "learning_rate": 1.1547531776199072e-05, + "loss": 1.3148, + "step": 4820 + }, + { + "epoch": 0.51, + "learning_rate": 1.1543915516956523e-05, + "loss": 1.3255, + "step": 4821 + }, + { + "epoch": 0.51, + "learning_rate": 1.1540299050868966e-05, + "loss": 1.3361, + "step": 4822 + }, + { + "epoch": 0.51, + "learning_rate": 1.1536682378420912e-05, + "loss": 1.3377, + "step": 4823 + }, + { + "epoch": 0.51, + "learning_rate": 1.1533065500096901e-05, + "loss": 1.4205, + "step": 4824 + }, + { + "epoch": 0.51, + "learning_rate": 1.1529448416381505e-05, + "loss": 1.4193, + "step": 4825 + }, + { + "epoch": 0.51, + "learning_rate": 1.1525831127759322e-05, + "loss": 1.37, + "step": 4826 + }, + { + "epoch": 0.51, + "learning_rate": 1.1522213634714971e-05, + "loss": 1.3642, + "step": 4827 + }, + { + "epoch": 0.51, + "learning_rate": 1.1518595937733103e-05, + "loss": 1.4834, + "step": 4828 + }, + { + "epoch": 0.51, + "learning_rate": 1.1514978037298402e-05, + "loss": 1.2864, + "step": 4829 + }, + { + "epoch": 0.51, + "learning_rate": 1.1511359933895567e-05, + "loss": 1.3468, + "step": 4830 + }, + { + "epoch": 0.51, + "learning_rate": 1.1507741628009337e-05, + "loss": 1.328, + "step": 4831 + }, + { + "epoch": 0.51, + "learning_rate": 1.1504123120124466e-05, + "loss": 1.3489, + "step": 4832 + }, + { + "epoch": 0.51, + "learning_rate": 1.1500504410725746e-05, + "loss": 1.4031, + "step": 4833 + }, + { + "epoch": 0.51, + "learning_rate": 1.149688550029799e-05, + "loss": 1.3482, + "step": 4834 + }, + { + "epoch": 0.51, + "learning_rate": 1.1493266389326037e-05, + "loss": 1.3674, + "step": 4835 + }, + { + "epoch": 0.51, + "learning_rate": 1.1489647078294753e-05, + "loss": 1.2895, + "step": 4836 + }, + { + "epoch": 0.51, + "learning_rate": 1.148602756768904e-05, + "loss": 1.4071, + "step": 4837 + }, + { + "epoch": 0.51, + "learning_rate": 1.1482407857993814e-05, + "loss": 1.5218, + "step": 4838 + }, + { + "epoch": 0.51, + "learning_rate": 1.1478787949694024e-05, + "loss": 1.4577, + "step": 4839 + }, + { + "epoch": 0.51, + "learning_rate": 1.1475167843274643e-05, + "loss": 1.3817, + "step": 4840 + }, + { + "epoch": 0.51, + "learning_rate": 1.1471547539220678e-05, + "loss": 1.3072, + "step": 4841 + }, + { + "epoch": 0.51, + "learning_rate": 1.146792703801715e-05, + "loss": 1.3737, + "step": 4842 + }, + { + "epoch": 0.51, + "learning_rate": 1.1464306340149119e-05, + "loss": 1.4001, + "step": 4843 + }, + { + "epoch": 0.51, + "learning_rate": 1.1460685446101658e-05, + "loss": 1.3963, + "step": 4844 + }, + { + "epoch": 0.51, + "learning_rate": 1.1457064356359882e-05, + "loss": 1.4061, + "step": 4845 + }, + { + "epoch": 0.51, + "learning_rate": 1.145344307140892e-05, + "loss": 1.4211, + "step": 4846 + }, + { + "epoch": 0.51, + "learning_rate": 1.144982159173393e-05, + "loss": 1.3197, + "step": 4847 + }, + { + "epoch": 0.51, + "learning_rate": 1.14461999178201e-05, + "loss": 1.3549, + "step": 4848 + }, + { + "epoch": 0.51, + "learning_rate": 1.1442578050152639e-05, + "loss": 1.3889, + "step": 4849 + }, + { + "epoch": 0.51, + "learning_rate": 1.1438955989216787e-05, + "loss": 1.3847, + "step": 4850 + }, + { + "epoch": 0.51, + "learning_rate": 1.1435333735497803e-05, + "loss": 1.3586, + "step": 4851 + }, + { + "epoch": 0.51, + "learning_rate": 1.1431711289480978e-05, + "loss": 1.503, + "step": 4852 + }, + { + "epoch": 0.51, + "learning_rate": 1.1428088651651627e-05, + "loss": 1.3654, + "step": 4853 + }, + { + "epoch": 0.51, + "learning_rate": 1.1424465822495092e-05, + "loss": 1.3741, + "step": 4854 + }, + { + "epoch": 0.51, + "learning_rate": 1.1420842802496737e-05, + "loss": 1.5437, + "step": 4855 + }, + { + "epoch": 0.51, + "learning_rate": 1.1417219592141953e-05, + "loss": 1.2179, + "step": 4856 + }, + { + "epoch": 0.51, + "learning_rate": 1.1413596191916159e-05, + "loss": 1.3939, + "step": 4857 + }, + { + "epoch": 0.51, + "learning_rate": 1.1409972602304796e-05, + "loss": 1.3383, + "step": 4858 + }, + { + "epoch": 0.51, + "learning_rate": 1.140634882379333e-05, + "loss": 1.3664, + "step": 4859 + }, + { + "epoch": 0.51, + "learning_rate": 1.1402724856867258e-05, + "loss": 1.4002, + "step": 4860 + }, + { + "epoch": 0.51, + "learning_rate": 1.1399100702012098e-05, + "loss": 1.2975, + "step": 4861 + }, + { + "epoch": 0.51, + "learning_rate": 1.1395476359713394e-05, + "loss": 1.3564, + "step": 4862 + }, + { + "epoch": 0.51, + "learning_rate": 1.1391851830456708e-05, + "loss": 1.3574, + "step": 4863 + }, + { + "epoch": 0.51, + "learning_rate": 1.1388227114727644e-05, + "loss": 1.3407, + "step": 4864 + }, + { + "epoch": 0.51, + "learning_rate": 1.1384602213011815e-05, + "loss": 1.3603, + "step": 4865 + }, + { + "epoch": 0.51, + "learning_rate": 1.1380977125794866e-05, + "loss": 1.3465, + "step": 4866 + }, + { + "epoch": 0.51, + "learning_rate": 1.1377351853562461e-05, + "loss": 1.3744, + "step": 4867 + }, + { + "epoch": 0.51, + "learning_rate": 1.1373726396800304e-05, + "loss": 1.3248, + "step": 4868 + }, + { + "epoch": 0.51, + "learning_rate": 1.1370100755994102e-05, + "loss": 1.3352, + "step": 4869 + }, + { + "epoch": 0.51, + "learning_rate": 1.1366474931629603e-05, + "loss": 1.3299, + "step": 4870 + }, + { + "epoch": 0.51, + "learning_rate": 1.1362848924192575e-05, + "loss": 1.344, + "step": 4871 + }, + { + "epoch": 0.51, + "learning_rate": 1.1359222734168809e-05, + "loss": 1.3209, + "step": 4872 + }, + { + "epoch": 0.51, + "learning_rate": 1.135559636204412e-05, + "loss": 1.3927, + "step": 4873 + }, + { + "epoch": 0.51, + "learning_rate": 1.1351969808304349e-05, + "loss": 1.3717, + "step": 4874 + }, + { + "epoch": 0.51, + "learning_rate": 1.1348343073435362e-05, + "loss": 1.3813, + "step": 4875 + }, + { + "epoch": 0.51, + "learning_rate": 1.1344716157923046e-05, + "loss": 1.236, + "step": 4876 + }, + { + "epoch": 0.51, + "learning_rate": 1.1341089062253319e-05, + "loss": 1.2591, + "step": 4877 + }, + { + "epoch": 0.51, + "learning_rate": 1.1337461786912112e-05, + "loss": 1.3211, + "step": 4878 + }, + { + "epoch": 0.51, + "learning_rate": 1.1333834332385394e-05, + "loss": 1.4534, + "step": 4879 + }, + { + "epoch": 0.51, + "learning_rate": 1.1330206699159145e-05, + "loss": 1.346, + "step": 4880 + }, + { + "epoch": 0.51, + "learning_rate": 1.132657888771938e-05, + "loss": 1.3952, + "step": 4881 + }, + { + "epoch": 0.51, + "learning_rate": 1.1322950898552125e-05, + "loss": 1.3008, + "step": 4882 + }, + { + "epoch": 0.51, + "learning_rate": 1.1319322732143445e-05, + "loss": 1.3201, + "step": 4883 + }, + { + "epoch": 0.51, + "learning_rate": 1.1315694388979416e-05, + "loss": 1.3761, + "step": 4884 + }, + { + "epoch": 0.51, + "learning_rate": 1.1312065869546147e-05, + "loss": 1.343, + "step": 4885 + }, + { + "epoch": 0.51, + "learning_rate": 1.1308437174329761e-05, + "loss": 1.3741, + "step": 4886 + }, + { + "epoch": 0.51, + "learning_rate": 1.1304808303816413e-05, + "loss": 1.402, + "step": 4887 + }, + { + "epoch": 0.51, + "learning_rate": 1.130117925849228e-05, + "loss": 1.3834, + "step": 4888 + }, + { + "epoch": 0.51, + "learning_rate": 1.1297550038843559e-05, + "loss": 1.3342, + "step": 4889 + }, + { + "epoch": 0.51, + "learning_rate": 1.1293920645356471e-05, + "loss": 1.3207, + "step": 4890 + }, + { + "epoch": 0.51, + "learning_rate": 1.1290291078517264e-05, + "loss": 1.4274, + "step": 4891 + }, + { + "epoch": 0.51, + "learning_rate": 1.1286661338812203e-05, + "loss": 1.328, + "step": 4892 + }, + { + "epoch": 0.51, + "learning_rate": 1.1283031426727584e-05, + "loss": 1.3823, + "step": 4893 + }, + { + "epoch": 0.51, + "learning_rate": 1.127940134274972e-05, + "loss": 1.3612, + "step": 4894 + }, + { + "epoch": 0.51, + "learning_rate": 1.127577108736495e-05, + "loss": 1.375, + "step": 4895 + }, + { + "epoch": 0.51, + "learning_rate": 1.1272140661059636e-05, + "loss": 1.3531, + "step": 4896 + }, + { + "epoch": 0.51, + "learning_rate": 1.1268510064320155e-05, + "loss": 1.3636, + "step": 4897 + }, + { + "epoch": 0.51, + "learning_rate": 1.1264879297632923e-05, + "loss": 1.3524, + "step": 4898 + }, + { + "epoch": 0.51, + "learning_rate": 1.1261248361484363e-05, + "loss": 1.3865, + "step": 4899 + }, + { + "epoch": 0.51, + "learning_rate": 1.125761725636093e-05, + "loss": 1.4069, + "step": 4900 + }, + { + "epoch": 0.51, + "learning_rate": 1.1253985982749098e-05, + "loss": 1.4643, + "step": 4901 + }, + { + "epoch": 0.51, + "learning_rate": 1.1250354541135364e-05, + "loss": 1.4506, + "step": 4902 + }, + { + "epoch": 0.51, + "learning_rate": 1.124672293200625e-05, + "loss": 1.3857, + "step": 4903 + }, + { + "epoch": 0.51, + "learning_rate": 1.1243091155848295e-05, + "loss": 1.3554, + "step": 4904 + }, + { + "epoch": 0.51, + "learning_rate": 1.1239459213148065e-05, + "loss": 1.4071, + "step": 4905 + }, + { + "epoch": 0.51, + "learning_rate": 1.1235827104392148e-05, + "loss": 1.3981, + "step": 4906 + }, + { + "epoch": 0.51, + "learning_rate": 1.1232194830067153e-05, + "loss": 1.4913, + "step": 4907 + }, + { + "epoch": 0.51, + "learning_rate": 1.1228562390659712e-05, + "loss": 1.3343, + "step": 4908 + }, + { + "epoch": 0.51, + "learning_rate": 1.1224929786656474e-05, + "loss": 1.3832, + "step": 4909 + }, + { + "epoch": 0.51, + "learning_rate": 1.122129701854412e-05, + "loss": 1.367, + "step": 4910 + }, + { + "epoch": 0.51, + "learning_rate": 1.1217664086809345e-05, + "loss": 1.4108, + "step": 4911 + }, + { + "epoch": 0.52, + "learning_rate": 1.1214030991938872e-05, + "loss": 1.3981, + "step": 4912 + }, + { + "epoch": 0.52, + "learning_rate": 1.1210397734419436e-05, + "loss": 1.5266, + "step": 4913 + }, + { + "epoch": 0.52, + "learning_rate": 1.1206764314737806e-05, + "loss": 1.337, + "step": 4914 + }, + { + "epoch": 0.52, + "learning_rate": 1.1203130733380765e-05, + "loss": 1.3784, + "step": 4915 + }, + { + "epoch": 0.52, + "learning_rate": 1.1199496990835117e-05, + "loss": 1.3048, + "step": 4916 + }, + { + "epoch": 0.52, + "learning_rate": 1.1195863087587692e-05, + "loss": 1.2977, + "step": 4917 + }, + { + "epoch": 0.52, + "learning_rate": 1.1192229024125344e-05, + "loss": 1.3304, + "step": 4918 + }, + { + "epoch": 0.52, + "learning_rate": 1.1188594800934938e-05, + "loss": 1.4102, + "step": 4919 + }, + { + "epoch": 0.52, + "learning_rate": 1.1184960418503366e-05, + "loss": 1.3932, + "step": 4920 + }, + { + "epoch": 0.52, + "learning_rate": 1.1181325877317547e-05, + "loss": 1.4985, + "step": 4921 + }, + { + "epoch": 0.52, + "learning_rate": 1.1177691177864415e-05, + "loss": 1.4596, + "step": 4922 + }, + { + "epoch": 0.52, + "learning_rate": 1.1174056320630924e-05, + "loss": 1.3559, + "step": 4923 + }, + { + "epoch": 0.52, + "learning_rate": 1.117042130610405e-05, + "loss": 1.4128, + "step": 4924 + }, + { + "epoch": 0.52, + "learning_rate": 1.1166786134770795e-05, + "loss": 1.3343, + "step": 4925 + }, + { + "epoch": 0.52, + "learning_rate": 1.116315080711818e-05, + "loss": 1.332, + "step": 4926 + }, + { + "epoch": 0.52, + "learning_rate": 1.115951532363324e-05, + "loss": 1.3616, + "step": 4927 + }, + { + "epoch": 0.52, + "learning_rate": 1.1155879684803041e-05, + "loss": 1.4074, + "step": 4928 + }, + { + "epoch": 0.52, + "learning_rate": 1.1152243891114665e-05, + "loss": 1.303, + "step": 4929 + }, + { + "epoch": 0.52, + "learning_rate": 1.1148607943055212e-05, + "loss": 1.4799, + "step": 4930 + }, + { + "epoch": 0.52, + "learning_rate": 1.1144971841111807e-05, + "loss": 1.3881, + "step": 4931 + }, + { + "epoch": 0.52, + "learning_rate": 1.1141335585771593e-05, + "loss": 1.338, + "step": 4932 + }, + { + "epoch": 0.52, + "learning_rate": 1.1137699177521738e-05, + "loss": 1.3289, + "step": 4933 + }, + { + "epoch": 0.52, + "learning_rate": 1.1134062616849426e-05, + "loss": 1.377, + "step": 4934 + }, + { + "epoch": 0.52, + "learning_rate": 1.1130425904241862e-05, + "loss": 1.3596, + "step": 4935 + }, + { + "epoch": 0.52, + "learning_rate": 1.112678904018627e-05, + "loss": 1.4264, + "step": 4936 + }, + { + "epoch": 0.52, + "learning_rate": 1.1123152025169898e-05, + "loss": 1.3526, + "step": 4937 + }, + { + "epoch": 0.52, + "learning_rate": 1.1119514859680016e-05, + "loss": 1.3271, + "step": 4938 + }, + { + "epoch": 0.52, + "learning_rate": 1.1115877544203905e-05, + "loss": 1.3907, + "step": 4939 + }, + { + "epoch": 0.52, + "learning_rate": 1.1112240079228878e-05, + "loss": 1.3415, + "step": 4940 + }, + { + "epoch": 0.52, + "learning_rate": 1.1108602465242258e-05, + "loss": 1.3875, + "step": 4941 + }, + { + "epoch": 0.52, + "learning_rate": 1.110496470273139e-05, + "loss": 1.3964, + "step": 4942 + }, + { + "epoch": 0.52, + "learning_rate": 1.1101326792183645e-05, + "loss": 1.3448, + "step": 4943 + }, + { + "epoch": 0.52, + "learning_rate": 1.1097688734086407e-05, + "loss": 1.3522, + "step": 4944 + }, + { + "epoch": 0.52, + "learning_rate": 1.1094050528927082e-05, + "loss": 1.2742, + "step": 4945 + }, + { + "epoch": 0.52, + "learning_rate": 1.1090412177193097e-05, + "loss": 1.417, + "step": 4946 + }, + { + "epoch": 0.52, + "learning_rate": 1.1086773679371898e-05, + "loss": 1.3993, + "step": 4947 + }, + { + "epoch": 0.52, + "learning_rate": 1.108313503595095e-05, + "loss": 1.3783, + "step": 4948 + }, + { + "epoch": 0.52, + "learning_rate": 1.1079496247417736e-05, + "loss": 1.3975, + "step": 4949 + }, + { + "epoch": 0.52, + "learning_rate": 1.1075857314259763e-05, + "loss": 1.4256, + "step": 4950 + }, + { + "epoch": 0.52, + "learning_rate": 1.1072218236964551e-05, + "loss": 1.3547, + "step": 4951 + }, + { + "epoch": 0.52, + "learning_rate": 1.106857901601965e-05, + "loss": 1.4243, + "step": 4952 + }, + { + "epoch": 0.52, + "learning_rate": 1.1064939651912612e-05, + "loss": 1.4259, + "step": 4953 + }, + { + "epoch": 0.52, + "learning_rate": 1.1061300145131027e-05, + "loss": 1.4323, + "step": 4954 + }, + { + "epoch": 0.52, + "learning_rate": 1.1057660496162488e-05, + "loss": 1.3608, + "step": 4955 + }, + { + "epoch": 0.52, + "learning_rate": 1.1054020705494622e-05, + "loss": 1.3703, + "step": 4956 + }, + { + "epoch": 0.52, + "learning_rate": 1.105038077361506e-05, + "loss": 1.3953, + "step": 4957 + }, + { + "epoch": 0.52, + "learning_rate": 1.1046740701011467e-05, + "loss": 1.392, + "step": 4958 + }, + { + "epoch": 0.52, + "learning_rate": 1.1043100488171513e-05, + "loss": 1.4101, + "step": 4959 + }, + { + "epoch": 0.52, + "learning_rate": 1.1039460135582894e-05, + "loss": 1.5432, + "step": 4960 + }, + { + "epoch": 0.52, + "learning_rate": 1.1035819643733326e-05, + "loss": 1.3822, + "step": 4961 + }, + { + "epoch": 0.52, + "learning_rate": 1.103217901311054e-05, + "loss": 1.3816, + "step": 4962 + }, + { + "epoch": 0.52, + "learning_rate": 1.1028538244202287e-05, + "loss": 1.3137, + "step": 4963 + }, + { + "epoch": 0.52, + "learning_rate": 1.102489733749634e-05, + "loss": 1.3791, + "step": 4964 + }, + { + "epoch": 0.52, + "learning_rate": 1.102125629348048e-05, + "loss": 1.3751, + "step": 4965 + }, + { + "epoch": 0.52, + "learning_rate": 1.1017615112642518e-05, + "loss": 1.3287, + "step": 4966 + }, + { + "epoch": 0.52, + "learning_rate": 1.1013973795470277e-05, + "loss": 1.3187, + "step": 4967 + }, + { + "epoch": 0.52, + "learning_rate": 1.1010332342451602e-05, + "loss": 1.3174, + "step": 4968 + }, + { + "epoch": 0.52, + "learning_rate": 1.1006690754074351e-05, + "loss": 1.3544, + "step": 4969 + }, + { + "epoch": 0.52, + "learning_rate": 1.1003049030826404e-05, + "loss": 1.3789, + "step": 4970 + }, + { + "epoch": 0.52, + "learning_rate": 1.0999407173195662e-05, + "loss": 1.4561, + "step": 4971 + }, + { + "epoch": 0.52, + "learning_rate": 1.0995765181670039e-05, + "loss": 1.3963, + "step": 4972 + }, + { + "epoch": 0.52, + "learning_rate": 1.0992123056737464e-05, + "loss": 1.3519, + "step": 4973 + }, + { + "epoch": 0.52, + "learning_rate": 1.0988480798885892e-05, + "loss": 1.3945, + "step": 4974 + }, + { + "epoch": 0.52, + "learning_rate": 1.0984838408603294e-05, + "loss": 1.4572, + "step": 4975 + }, + { + "epoch": 0.52, + "eval_loss": 1.4313459396362305, + "eval_runtime": 77.4808, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 4975 + }, + { + "epoch": 0.52, + "learning_rate": 1.0981195886377652e-05, + "loss": 1.3493, + "step": 4976 + }, + { + "epoch": 0.52, + "learning_rate": 1.0977553232696972e-05, + "loss": 1.3734, + "step": 4977 + }, + { + "epoch": 0.52, + "learning_rate": 1.0973910448049273e-05, + "loss": 1.3484, + "step": 4978 + }, + { + "epoch": 0.52, + "learning_rate": 1.09702675329226e-05, + "loss": 1.4288, + "step": 4979 + }, + { + "epoch": 0.52, + "learning_rate": 1.096662448780501e-05, + "loss": 1.3748, + "step": 4980 + }, + { + "epoch": 0.52, + "learning_rate": 1.0962981313184575e-05, + "loss": 1.3485, + "step": 4981 + }, + { + "epoch": 0.52, + "learning_rate": 1.0959338009549383e-05, + "loss": 1.3606, + "step": 4982 + }, + { + "epoch": 0.52, + "learning_rate": 1.095569457738755e-05, + "loss": 1.3963, + "step": 4983 + }, + { + "epoch": 0.52, + "learning_rate": 1.09520510171872e-05, + "loss": 1.2986, + "step": 4984 + }, + { + "epoch": 0.52, + "learning_rate": 1.0948407329436474e-05, + "loss": 1.3505, + "step": 4985 + }, + { + "epoch": 0.52, + "learning_rate": 1.0944763514623535e-05, + "loss": 1.4649, + "step": 4986 + }, + { + "epoch": 0.52, + "learning_rate": 1.0941119573236564e-05, + "loss": 1.4743, + "step": 4987 + }, + { + "epoch": 0.52, + "learning_rate": 1.0937475505763745e-05, + "loss": 1.3934, + "step": 4988 + }, + { + "epoch": 0.52, + "learning_rate": 1.09338313126933e-05, + "loss": 1.4225, + "step": 4989 + }, + { + "epoch": 0.52, + "learning_rate": 1.0930186994513453e-05, + "loss": 1.3626, + "step": 4990 + }, + { + "epoch": 0.52, + "learning_rate": 1.0926542551712446e-05, + "loss": 1.3614, + "step": 4991 + }, + { + "epoch": 0.52, + "learning_rate": 1.0922897984778546e-05, + "loss": 1.3766, + "step": 4992 + }, + { + "epoch": 0.52, + "learning_rate": 1.0919253294200027e-05, + "loss": 1.3295, + "step": 4993 + }, + { + "epoch": 0.52, + "learning_rate": 1.091560848046519e-05, + "loss": 1.3802, + "step": 4994 + }, + { + "epoch": 0.52, + "learning_rate": 1.091196354406234e-05, + "loss": 1.2976, + "step": 4995 + }, + { + "epoch": 0.52, + "learning_rate": 1.090831848547981e-05, + "loss": 1.3928, + "step": 4996 + }, + { + "epoch": 0.52, + "learning_rate": 1.0904673305205937e-05, + "loss": 1.3717, + "step": 4997 + }, + { + "epoch": 0.52, + "learning_rate": 1.0901028003729089e-05, + "loss": 1.3164, + "step": 4998 + }, + { + "epoch": 0.52, + "learning_rate": 1.0897382581537638e-05, + "loss": 1.3462, + "step": 4999 + }, + { + "epoch": 0.52, + "learning_rate": 1.0893737039119981e-05, + "loss": 1.3643, + "step": 5000 + }, + { + "epoch": 0.52, + "learning_rate": 1.089009137696452e-05, + "loss": 1.3452, + "step": 5001 + }, + { + "epoch": 0.52, + "learning_rate": 1.0886445595559686e-05, + "loss": 1.358, + "step": 5002 + }, + { + "epoch": 0.52, + "learning_rate": 1.0882799695393922e-05, + "loss": 1.4569, + "step": 5003 + }, + { + "epoch": 0.52, + "learning_rate": 1.0879153676955681e-05, + "loss": 1.2832, + "step": 5004 + }, + { + "epoch": 0.52, + "learning_rate": 1.0875507540733435e-05, + "loss": 1.4089, + "step": 5005 + }, + { + "epoch": 0.52, + "learning_rate": 1.087186128721567e-05, + "loss": 1.3178, + "step": 5006 + }, + { + "epoch": 0.53, + "learning_rate": 1.0868214916890902e-05, + "loss": 1.4883, + "step": 5007 + }, + { + "epoch": 0.53, + "learning_rate": 1.0864568430247638e-05, + "loss": 1.3991, + "step": 5008 + }, + { + "epoch": 0.53, + "learning_rate": 1.0860921827774422e-05, + "loss": 1.4507, + "step": 5009 + }, + { + "epoch": 0.53, + "learning_rate": 1.08572751099598e-05, + "loss": 1.3578, + "step": 5010 + }, + { + "epoch": 0.53, + "learning_rate": 1.0853628277292341e-05, + "loss": 1.4231, + "step": 5011 + }, + { + "epoch": 0.53, + "learning_rate": 1.0849981330260624e-05, + "loss": 1.4835, + "step": 5012 + }, + { + "epoch": 0.53, + "learning_rate": 1.084633426935325e-05, + "loss": 1.4511, + "step": 5013 + }, + { + "epoch": 0.53, + "learning_rate": 1.084268709505883e-05, + "loss": 1.3889, + "step": 5014 + }, + { + "epoch": 0.53, + "learning_rate": 1.0839039807865992e-05, + "loss": 1.355, + "step": 5015 + }, + { + "epoch": 0.53, + "learning_rate": 1.0835392408263375e-05, + "loss": 1.4829, + "step": 5016 + }, + { + "epoch": 0.53, + "learning_rate": 1.0831744896739643e-05, + "loss": 1.3019, + "step": 5017 + }, + { + "epoch": 0.53, + "learning_rate": 1.0828097273783465e-05, + "loss": 1.3418, + "step": 5018 + }, + { + "epoch": 0.53, + "learning_rate": 1.082444953988353e-05, + "loss": 1.4276, + "step": 5019 + }, + { + "epoch": 0.53, + "learning_rate": 1.0820801695528537e-05, + "loss": 1.2816, + "step": 5020 + }, + { + "epoch": 0.53, + "learning_rate": 1.081715374120721e-05, + "loss": 1.5144, + "step": 5021 + }, + { + "epoch": 0.53, + "learning_rate": 1.0813505677408278e-05, + "loss": 1.4063, + "step": 5022 + }, + { + "epoch": 0.53, + "learning_rate": 1.0809857504620487e-05, + "loss": 1.4011, + "step": 5023 + }, + { + "epoch": 0.53, + "learning_rate": 1.0806209223332598e-05, + "loss": 1.373, + "step": 5024 + }, + { + "epoch": 0.53, + "learning_rate": 1.0802560834033388e-05, + "loss": 1.6259, + "step": 5025 + }, + { + "epoch": 0.53, + "learning_rate": 1.0798912337211648e-05, + "loss": 1.4487, + "step": 5026 + }, + { + "epoch": 0.53, + "learning_rate": 1.0795263733356184e-05, + "loss": 1.3056, + "step": 5027 + }, + { + "epoch": 0.53, + "learning_rate": 1.079161502295581e-05, + "loss": 1.2871, + "step": 5028 + }, + { + "epoch": 0.53, + "learning_rate": 1.0787966206499363e-05, + "loss": 1.413, + "step": 5029 + }, + { + "epoch": 0.53, + "learning_rate": 1.0784317284475694e-05, + "loss": 1.3682, + "step": 5030 + }, + { + "epoch": 0.53, + "learning_rate": 1.0780668257373659e-05, + "loss": 1.493, + "step": 5031 + }, + { + "epoch": 0.53, + "learning_rate": 1.0777019125682136e-05, + "loss": 1.6823, + "step": 5032 + }, + { + "epoch": 0.53, + "learning_rate": 1.0773369889890015e-05, + "loss": 1.358, + "step": 5033 + }, + { + "epoch": 0.53, + "learning_rate": 1.07697205504862e-05, + "loss": 1.3532, + "step": 5034 + }, + { + "epoch": 0.53, + "learning_rate": 1.0766071107959608e-05, + "loss": 1.3432, + "step": 5035 + }, + { + "epoch": 0.53, + "learning_rate": 1.0762421562799173e-05, + "loss": 1.3575, + "step": 5036 + }, + { + "epoch": 0.53, + "learning_rate": 1.0758771915493838e-05, + "loss": 1.0924, + "step": 5037 + }, + { + "epoch": 0.53, + "learning_rate": 1.075512216653256e-05, + "loss": 0.7405, + "step": 5038 + }, + { + "epoch": 0.53, + "learning_rate": 1.0751472316404315e-05, + "loss": 0.7134, + "step": 5039 + }, + { + "epoch": 0.53, + "learning_rate": 1.0747822365598088e-05, + "loss": 1.0904, + "step": 5040 + }, + { + "epoch": 0.53, + "learning_rate": 1.0744172314602881e-05, + "loss": 1.4353, + "step": 5041 + }, + { + "epoch": 0.53, + "learning_rate": 1.0740522163907702e-05, + "loss": 1.361, + "step": 5042 + }, + { + "epoch": 0.53, + "learning_rate": 1.073687191400158e-05, + "loss": 1.4024, + "step": 5043 + }, + { + "epoch": 0.53, + "learning_rate": 1.0733221565373557e-05, + "loss": 1.328, + "step": 5044 + }, + { + "epoch": 0.53, + "learning_rate": 1.0729571118512683e-05, + "loss": 1.3309, + "step": 5045 + }, + { + "epoch": 0.53, + "learning_rate": 1.0725920573908024e-05, + "loss": 1.3819, + "step": 5046 + }, + { + "epoch": 0.53, + "learning_rate": 1.0722269932048659e-05, + "loss": 1.3467, + "step": 5047 + }, + { + "epoch": 0.53, + "learning_rate": 1.0718619193423683e-05, + "loss": 1.3036, + "step": 5048 + }, + { + "epoch": 0.53, + "learning_rate": 1.07149683585222e-05, + "loss": 1.3297, + "step": 5049 + }, + { + "epoch": 0.53, + "learning_rate": 1.0711317427833328e-05, + "loss": 1.3439, + "step": 5050 + }, + { + "epoch": 0.53, + "learning_rate": 1.0707666401846192e-05, + "loss": 1.4167, + "step": 5051 + }, + { + "epoch": 0.53, + "learning_rate": 1.0704015281049944e-05, + "loss": 1.4217, + "step": 5052 + }, + { + "epoch": 0.53, + "learning_rate": 1.070036406593374e-05, + "loss": 1.3394, + "step": 5053 + }, + { + "epoch": 0.53, + "learning_rate": 1.0696712756986745e-05, + "loss": 1.3242, + "step": 5054 + }, + { + "epoch": 0.53, + "learning_rate": 1.0693061354698143e-05, + "loss": 1.3957, + "step": 5055 + }, + { + "epoch": 0.53, + "learning_rate": 1.0689409859557123e-05, + "loss": 1.37, + "step": 5056 + }, + { + "epoch": 0.53, + "learning_rate": 1.0685758272052902e-05, + "loss": 1.4524, + "step": 5057 + }, + { + "epoch": 0.53, + "learning_rate": 1.0682106592674688e-05, + "loss": 1.528, + "step": 5058 + }, + { + "epoch": 0.53, + "learning_rate": 1.0678454821911719e-05, + "loss": 1.3613, + "step": 5059 + }, + { + "epoch": 0.53, + "learning_rate": 1.0674802960253234e-05, + "loss": 1.308, + "step": 5060 + }, + { + "epoch": 0.53, + "learning_rate": 1.0671151008188494e-05, + "loss": 1.3343, + "step": 5061 + }, + { + "epoch": 0.53, + "learning_rate": 1.066749896620676e-05, + "loss": 1.365, + "step": 5062 + }, + { + "epoch": 0.53, + "learning_rate": 1.0663846834797316e-05, + "loss": 1.4077, + "step": 5063 + }, + { + "epoch": 0.53, + "learning_rate": 1.0660194614449455e-05, + "loss": 1.324, + "step": 5064 + }, + { + "epoch": 0.53, + "learning_rate": 1.0656542305652478e-05, + "loss": 1.3623, + "step": 5065 + }, + { + "epoch": 0.53, + "learning_rate": 1.0652889908895701e-05, + "loss": 1.4079, + "step": 5066 + }, + { + "epoch": 0.53, + "learning_rate": 1.0649237424668451e-05, + "loss": 1.3089, + "step": 5067 + }, + { + "epoch": 0.53, + "learning_rate": 1.0645584853460069e-05, + "loss": 1.3967, + "step": 5068 + }, + { + "epoch": 0.53, + "learning_rate": 1.0641932195759905e-05, + "loss": 1.3639, + "step": 5069 + }, + { + "epoch": 0.53, + "learning_rate": 1.0638279452057319e-05, + "loss": 1.5919, + "step": 5070 + }, + { + "epoch": 0.53, + "learning_rate": 1.0634626622841686e-05, + "loss": 1.3348, + "step": 5071 + }, + { + "epoch": 0.53, + "learning_rate": 1.0630973708602395e-05, + "loss": 1.3146, + "step": 5072 + }, + { + "epoch": 0.53, + "learning_rate": 1.0627320709828836e-05, + "loss": 1.3375, + "step": 5073 + }, + { + "epoch": 0.53, + "learning_rate": 1.062366762701042e-05, + "loss": 1.3908, + "step": 5074 + }, + { + "epoch": 0.53, + "learning_rate": 1.0620014460636568e-05, + "loss": 1.3726, + "step": 5075 + }, + { + "epoch": 0.53, + "learning_rate": 1.061636121119671e-05, + "loss": 1.2348, + "step": 5076 + }, + { + "epoch": 0.53, + "learning_rate": 1.0612707879180284e-05, + "loss": 1.2957, + "step": 5077 + }, + { + "epoch": 0.53, + "learning_rate": 1.0609054465076749e-05, + "loss": 1.4202, + "step": 5078 + }, + { + "epoch": 0.53, + "learning_rate": 1.060540096937556e-05, + "loss": 1.5809, + "step": 5079 + }, + { + "epoch": 0.53, + "learning_rate": 1.0601747392566202e-05, + "loss": 1.3741, + "step": 5080 + }, + { + "epoch": 0.53, + "learning_rate": 1.059809373513815e-05, + "loss": 1.3537, + "step": 5081 + }, + { + "epoch": 0.53, + "learning_rate": 1.0594439997580907e-05, + "loss": 1.332, + "step": 5082 + }, + { + "epoch": 0.53, + "learning_rate": 1.0590786180383981e-05, + "loss": 1.3267, + "step": 5083 + }, + { + "epoch": 0.53, + "learning_rate": 1.0587132284036883e-05, + "loss": 1.3552, + "step": 5084 + }, + { + "epoch": 0.53, + "learning_rate": 1.0583478309029143e-05, + "loss": 1.2837, + "step": 5085 + }, + { + "epoch": 0.53, + "learning_rate": 1.0579824255850304e-05, + "loss": 1.4311, + "step": 5086 + }, + { + "epoch": 0.53, + "learning_rate": 1.0576170124989915e-05, + "loss": 1.4394, + "step": 5087 + }, + { + "epoch": 0.53, + "learning_rate": 1.0572515916937531e-05, + "loss": 1.3185, + "step": 5088 + }, + { + "epoch": 0.53, + "learning_rate": 1.0568861632182723e-05, + "loss": 1.4212, + "step": 5089 + }, + { + "epoch": 0.53, + "learning_rate": 1.0565207271215075e-05, + "loss": 1.0951, + "step": 5090 + }, + { + "epoch": 0.53, + "learning_rate": 1.0561552834524176e-05, + "loss": 1.4174, + "step": 5091 + }, + { + "epoch": 0.53, + "learning_rate": 1.0557898322599624e-05, + "loss": 1.3349, + "step": 5092 + }, + { + "epoch": 0.53, + "learning_rate": 1.0554243735931031e-05, + "loss": 1.399, + "step": 5093 + }, + { + "epoch": 0.53, + "learning_rate": 1.055058907500802e-05, + "loss": 1.4016, + "step": 5094 + }, + { + "epoch": 0.53, + "learning_rate": 1.0546934340320219e-05, + "loss": 1.3227, + "step": 5095 + }, + { + "epoch": 0.53, + "learning_rate": 1.0543279532357269e-05, + "loss": 1.4017, + "step": 5096 + }, + { + "epoch": 0.53, + "learning_rate": 1.053962465160882e-05, + "loss": 1.3937, + "step": 5097 + }, + { + "epoch": 0.53, + "learning_rate": 1.0535969698564532e-05, + "loss": 1.2405, + "step": 5098 + }, + { + "epoch": 0.53, + "learning_rate": 1.0532314673714081e-05, + "loss": 1.2939, + "step": 5099 + }, + { + "epoch": 0.53, + "learning_rate": 1.0528659577547136e-05, + "loss": 1.4165, + "step": 5100 + }, + { + "epoch": 0.53, + "learning_rate": 1.0525004410553394e-05, + "loss": 1.309, + "step": 5101 + }, + { + "epoch": 0.54, + "learning_rate": 1.0521349173222549e-05, + "loss": 1.4078, + "step": 5102 + }, + { + "epoch": 0.54, + "learning_rate": 1.0517693866044312e-05, + "loss": 1.4026, + "step": 5103 + }, + { + "epoch": 0.54, + "learning_rate": 1.0514038489508396e-05, + "loss": 1.3098, + "step": 5104 + }, + { + "epoch": 0.54, + "learning_rate": 1.0510383044104533e-05, + "loss": 1.2886, + "step": 5105 + }, + { + "epoch": 0.54, + "learning_rate": 1.0506727530322454e-05, + "loss": 1.3114, + "step": 5106 + }, + { + "epoch": 0.54, + "learning_rate": 1.0503071948651908e-05, + "loss": 1.2823, + "step": 5107 + }, + { + "epoch": 0.54, + "learning_rate": 1.0499416299582643e-05, + "loss": 1.4654, + "step": 5108 + }, + { + "epoch": 0.54, + "learning_rate": 1.0495760583604431e-05, + "loss": 1.4043, + "step": 5109 + }, + { + "epoch": 0.54, + "learning_rate": 1.0492104801207035e-05, + "loss": 1.3113, + "step": 5110 + }, + { + "epoch": 0.54, + "learning_rate": 1.0488448952880243e-05, + "loss": 1.3285, + "step": 5111 + }, + { + "epoch": 0.54, + "learning_rate": 1.048479303911384e-05, + "loss": 1.3918, + "step": 5112 + }, + { + "epoch": 0.54, + "learning_rate": 1.0481137060397623e-05, + "loss": 1.346, + "step": 5113 + }, + { + "epoch": 0.54, + "learning_rate": 1.0477481017221407e-05, + "loss": 1.3777, + "step": 5114 + }, + { + "epoch": 0.54, + "learning_rate": 1.0473824910075003e-05, + "loss": 1.3494, + "step": 5115 + }, + { + "epoch": 0.54, + "learning_rate": 1.0470168739448232e-05, + "loss": 1.4173, + "step": 5116 + }, + { + "epoch": 0.54, + "learning_rate": 1.0466512505830932e-05, + "loss": 1.4313, + "step": 5117 + }, + { + "epoch": 0.54, + "learning_rate": 1.0462856209712944e-05, + "loss": 1.335, + "step": 5118 + }, + { + "epoch": 0.54, + "learning_rate": 1.0459199851584117e-05, + "loss": 1.37, + "step": 5119 + }, + { + "epoch": 0.54, + "learning_rate": 1.0455543431934307e-05, + "loss": 1.3504, + "step": 5120 + }, + { + "epoch": 0.54, + "learning_rate": 1.0451886951253381e-05, + "loss": 1.4148, + "step": 5121 + }, + { + "epoch": 0.54, + "learning_rate": 1.0448230410031218e-05, + "loss": 1.3974, + "step": 5122 + }, + { + "epoch": 0.54, + "learning_rate": 1.0444573808757694e-05, + "loss": 1.3644, + "step": 5123 + }, + { + "epoch": 0.54, + "learning_rate": 1.0440917147922705e-05, + "loss": 1.4024, + "step": 5124 + }, + { + "epoch": 0.54, + "learning_rate": 1.0437260428016143e-05, + "loss": 1.3925, + "step": 5125 + }, + { + "epoch": 0.54, + "learning_rate": 1.0433603649527923e-05, + "loss": 1.2907, + "step": 5126 + }, + { + "epoch": 0.54, + "learning_rate": 1.0429946812947953e-05, + "loss": 1.3453, + "step": 5127 + }, + { + "epoch": 0.54, + "learning_rate": 1.0426289918766157e-05, + "loss": 1.3856, + "step": 5128 + }, + { + "epoch": 0.54, + "learning_rate": 1.0422632967472465e-05, + "loss": 1.3309, + "step": 5129 + }, + { + "epoch": 0.54, + "learning_rate": 1.0418975959556819e-05, + "loss": 1.3757, + "step": 5130 + }, + { + "epoch": 0.54, + "learning_rate": 1.0415318895509152e-05, + "loss": 1.406, + "step": 5131 + }, + { + "epoch": 0.54, + "learning_rate": 1.041166177581943e-05, + "loss": 1.3265, + "step": 5132 + }, + { + "epoch": 0.54, + "learning_rate": 1.0408004600977606e-05, + "loss": 1.3377, + "step": 5133 + }, + { + "epoch": 0.54, + "learning_rate": 1.040434737147365e-05, + "loss": 1.3647, + "step": 5134 + }, + { + "epoch": 0.54, + "learning_rate": 1.0400690087797531e-05, + "loss": 1.3262, + "step": 5135 + }, + { + "epoch": 0.54, + "learning_rate": 1.039703275043924e-05, + "loss": 1.3924, + "step": 5136 + }, + { + "epoch": 0.54, + "learning_rate": 1.039337535988876e-05, + "loss": 1.3018, + "step": 5137 + }, + { + "epoch": 0.54, + "learning_rate": 1.038971791663609e-05, + "loss": 1.385, + "step": 5138 + }, + { + "epoch": 0.54, + "learning_rate": 1.0386060421171232e-05, + "loss": 1.3435, + "step": 5139 + }, + { + "epoch": 0.54, + "learning_rate": 1.0382402873984197e-05, + "loss": 1.4023, + "step": 5140 + }, + { + "epoch": 0.54, + "learning_rate": 1.0378745275565003e-05, + "loss": 1.369, + "step": 5141 + }, + { + "epoch": 0.54, + "learning_rate": 1.0375087626403675e-05, + "loss": 1.3199, + "step": 5142 + }, + { + "epoch": 0.54, + "learning_rate": 1.037142992699024e-05, + "loss": 1.4247, + "step": 5143 + }, + { + "epoch": 0.54, + "learning_rate": 1.0367772177814736e-05, + "loss": 1.4015, + "step": 5144 + }, + { + "epoch": 0.54, + "learning_rate": 1.0364114379367217e-05, + "loss": 1.3519, + "step": 5145 + }, + { + "epoch": 0.54, + "learning_rate": 1.0360456532137722e-05, + "loss": 1.3478, + "step": 5146 + }, + { + "epoch": 0.54, + "learning_rate": 1.0356798636616314e-05, + "loss": 1.4876, + "step": 5147 + }, + { + "epoch": 0.54, + "learning_rate": 1.0353140693293056e-05, + "loss": 1.6481, + "step": 5148 + }, + { + "epoch": 0.54, + "learning_rate": 1.034948270265802e-05, + "loss": 1.3851, + "step": 5149 + }, + { + "epoch": 0.54, + "learning_rate": 1.0345824665201281e-05, + "loss": 1.4037, + "step": 5150 + }, + { + "epoch": 0.54, + "learning_rate": 1.0342166581412923e-05, + "loss": 1.3138, + "step": 5151 + }, + { + "epoch": 0.54, + "learning_rate": 1.0338508451783032e-05, + "loss": 1.3536, + "step": 5152 + }, + { + "epoch": 0.54, + "learning_rate": 1.0334850276801712e-05, + "loss": 1.3244, + "step": 5153 + }, + { + "epoch": 0.54, + "learning_rate": 1.0331192056959052e-05, + "loss": 1.3677, + "step": 5154 + }, + { + "epoch": 0.54, + "learning_rate": 1.032753379274517e-05, + "loss": 1.3439, + "step": 5155 + }, + { + "epoch": 0.54, + "learning_rate": 1.0323875484650171e-05, + "loss": 1.365, + "step": 5156 + }, + { + "epoch": 0.54, + "learning_rate": 1.0320217133164186e-05, + "loss": 1.3838, + "step": 5157 + }, + { + "epoch": 0.54, + "learning_rate": 1.0316558738777328e-05, + "loss": 1.3312, + "step": 5158 + }, + { + "epoch": 0.54, + "learning_rate": 1.0312900301979733e-05, + "loss": 1.369, + "step": 5159 + }, + { + "epoch": 0.54, + "learning_rate": 1.030924182326154e-05, + "loss": 1.2712, + "step": 5160 + }, + { + "epoch": 0.54, + "learning_rate": 1.0305583303112887e-05, + "loss": 1.3141, + "step": 5161 + }, + { + "epoch": 0.54, + "learning_rate": 1.030192474202392e-05, + "loss": 1.3708, + "step": 5162 + }, + { + "epoch": 0.54, + "learning_rate": 1.0298266140484798e-05, + "loss": 1.3724, + "step": 5163 + }, + { + "epoch": 0.54, + "learning_rate": 1.0294607498985678e-05, + "loss": 1.3208, + "step": 5164 + }, + { + "epoch": 0.54, + "learning_rate": 1.0290948818016722e-05, + "loss": 1.3379, + "step": 5165 + }, + { + "epoch": 0.54, + "learning_rate": 1.0287290098068099e-05, + "loss": 1.3236, + "step": 5166 + }, + { + "epoch": 0.54, + "learning_rate": 1.0283631339629982e-05, + "loss": 1.3437, + "step": 5167 + }, + { + "epoch": 0.54, + "learning_rate": 1.0279972543192561e-05, + "loss": 1.3381, + "step": 5168 + }, + { + "epoch": 0.54, + "learning_rate": 1.0276313709246007e-05, + "loss": 1.4287, + "step": 5169 + }, + { + "epoch": 0.54, + "learning_rate": 1.0272654838280515e-05, + "loss": 1.3587, + "step": 5170 + }, + { + "epoch": 0.54, + "learning_rate": 1.0268995930786283e-05, + "loss": 1.2982, + "step": 5171 + }, + { + "epoch": 0.54, + "learning_rate": 1.0265336987253509e-05, + "loss": 1.3416, + "step": 5172 + }, + { + "epoch": 0.54, + "learning_rate": 1.0261678008172393e-05, + "loss": 1.3827, + "step": 5173 + }, + { + "epoch": 0.54, + "learning_rate": 1.025801899403315e-05, + "loss": 1.3293, + "step": 5174 + }, + { + "epoch": 0.54, + "eval_loss": 1.4264723062515259, + "eval_runtime": 77.4376, + "eval_samples_per_second": 1.666, + "eval_steps_per_second": 0.116, + "step": 5174 + }, + { + "epoch": 0.54, + "learning_rate": 1.0254359945325987e-05, + "loss": 1.3811, + "step": 5175 + }, + { + "epoch": 0.54, + "learning_rate": 1.0250700862541135e-05, + "loss": 1.3423, + "step": 5176 + }, + { + "epoch": 0.54, + "learning_rate": 1.02470417461688e-05, + "loss": 1.3641, + "step": 5177 + }, + { + "epoch": 0.54, + "learning_rate": 1.0243382596699226e-05, + "loss": 1.3211, + "step": 5178 + }, + { + "epoch": 0.54, + "learning_rate": 1.023972341462263e-05, + "loss": 1.4008, + "step": 5179 + }, + { + "epoch": 0.54, + "learning_rate": 1.0236064200429263e-05, + "loss": 1.404, + "step": 5180 + }, + { + "epoch": 0.54, + "learning_rate": 1.0232404954609353e-05, + "loss": 1.3359, + "step": 5181 + }, + { + "epoch": 0.54, + "learning_rate": 1.0228745677653155e-05, + "loss": 1.4069, + "step": 5182 + }, + { + "epoch": 0.54, + "learning_rate": 1.0225086370050914e-05, + "loss": 1.3343, + "step": 5183 + }, + { + "epoch": 0.54, + "learning_rate": 1.0221427032292881e-05, + "loss": 1.3109, + "step": 5184 + }, + { + "epoch": 0.54, + "learning_rate": 1.0217767664869312e-05, + "loss": 1.3611, + "step": 5185 + }, + { + "epoch": 0.54, + "learning_rate": 1.0214108268270476e-05, + "loss": 1.4072, + "step": 5186 + }, + { + "epoch": 0.54, + "learning_rate": 1.0210448842986631e-05, + "loss": 1.3602, + "step": 5187 + }, + { + "epoch": 0.54, + "learning_rate": 1.0206789389508047e-05, + "loss": 1.413, + "step": 5188 + }, + { + "epoch": 0.54, + "learning_rate": 1.0203129908325e-05, + "loss": 1.3209, + "step": 5189 + }, + { + "epoch": 0.54, + "learning_rate": 1.0199470399927764e-05, + "loss": 1.3714, + "step": 5190 + }, + { + "epoch": 0.54, + "learning_rate": 1.0195810864806623e-05, + "loss": 1.3556, + "step": 5191 + }, + { + "epoch": 0.54, + "learning_rate": 1.0192151303451852e-05, + "loss": 1.4116, + "step": 5192 + }, + { + "epoch": 0.54, + "learning_rate": 1.0188491716353745e-05, + "loss": 1.4102, + "step": 5193 + }, + { + "epoch": 0.54, + "learning_rate": 1.0184832104002592e-05, + "loss": 1.4849, + "step": 5194 + }, + { + "epoch": 0.54, + "learning_rate": 1.0181172466888689e-05, + "loss": 1.5395, + "step": 5195 + }, + { + "epoch": 0.54, + "learning_rate": 1.0177512805502325e-05, + "loss": 1.3627, + "step": 5196 + }, + { + "epoch": 0.54, + "learning_rate": 1.017385312033381e-05, + "loss": 1.4152, + "step": 5197 + }, + { + "epoch": 0.55, + "learning_rate": 1.0170193411873442e-05, + "loss": 1.3641, + "step": 5198 + }, + { + "epoch": 0.55, + "learning_rate": 1.0166533680611533e-05, + "loss": 1.3074, + "step": 5199 + }, + { + "epoch": 0.55, + "learning_rate": 1.0162873927038386e-05, + "loss": 1.35, + "step": 5200 + }, + { + "epoch": 0.55, + "learning_rate": 1.015921415164432e-05, + "loss": 1.3551, + "step": 5201 + }, + { + "epoch": 0.55, + "learning_rate": 1.0155554354919643e-05, + "loss": 1.3421, + "step": 5202 + }, + { + "epoch": 0.55, + "learning_rate": 1.0151894537354687e-05, + "loss": 1.4132, + "step": 5203 + }, + { + "epoch": 0.55, + "learning_rate": 1.0148234699439764e-05, + "loss": 1.351, + "step": 5204 + }, + { + "epoch": 0.55, + "learning_rate": 1.0144574841665198e-05, + "loss": 1.3745, + "step": 5205 + }, + { + "epoch": 0.55, + "learning_rate": 1.0140914964521316e-05, + "loss": 1.3151, + "step": 5206 + }, + { + "epoch": 0.55, + "learning_rate": 1.0137255068498456e-05, + "loss": 1.4903, + "step": 5207 + }, + { + "epoch": 0.55, + "learning_rate": 1.0133595154086937e-05, + "loss": 1.3945, + "step": 5208 + }, + { + "epoch": 0.55, + "learning_rate": 1.0129935221777104e-05, + "loss": 1.3924, + "step": 5209 + }, + { + "epoch": 0.55, + "learning_rate": 1.0126275272059286e-05, + "loss": 1.4191, + "step": 5210 + }, + { + "epoch": 0.55, + "learning_rate": 1.012261530542383e-05, + "loss": 1.3408, + "step": 5211 + }, + { + "epoch": 0.55, + "learning_rate": 1.0118955322361071e-05, + "loss": 1.3582, + "step": 5212 + }, + { + "epoch": 0.55, + "learning_rate": 1.0115295323361354e-05, + "loss": 1.3703, + "step": 5213 + }, + { + "epoch": 0.55, + "learning_rate": 1.011163530891503e-05, + "loss": 1.4181, + "step": 5214 + }, + { + "epoch": 0.55, + "learning_rate": 1.0107975279512442e-05, + "loss": 1.5019, + "step": 5215 + }, + { + "epoch": 0.55, + "learning_rate": 1.010431523564394e-05, + "loss": 1.3151, + "step": 5216 + }, + { + "epoch": 0.55, + "learning_rate": 1.0100655177799874e-05, + "loss": 1.4036, + "step": 5217 + }, + { + "epoch": 0.55, + "learning_rate": 1.0096995106470606e-05, + "loss": 1.3584, + "step": 5218 + }, + { + "epoch": 0.55, + "learning_rate": 1.0093335022146482e-05, + "loss": 1.3618, + "step": 5219 + }, + { + "epoch": 0.55, + "learning_rate": 1.0089674925317865e-05, + "loss": 1.3295, + "step": 5220 + }, + { + "epoch": 0.55, + "learning_rate": 1.0086014816475108e-05, + "loss": 1.3968, + "step": 5221 + }, + { + "epoch": 0.55, + "learning_rate": 1.0082354696108586e-05, + "loss": 1.2847, + "step": 5222 + }, + { + "epoch": 0.55, + "learning_rate": 1.007869456470864e-05, + "loss": 1.4461, + "step": 5223 + }, + { + "epoch": 0.55, + "learning_rate": 1.007503442276565e-05, + "loss": 1.3813, + "step": 5224 + }, + { + "epoch": 0.55, + "learning_rate": 1.007137427076997e-05, + "loss": 1.3833, + "step": 5225 + }, + { + "epoch": 0.55, + "learning_rate": 1.006771410921198e-05, + "loss": 1.4024, + "step": 5226 + }, + { + "epoch": 0.55, + "learning_rate": 1.0064053938582032e-05, + "loss": 1.3357, + "step": 5227 + }, + { + "epoch": 0.55, + "learning_rate": 1.0060393759370506e-05, + "loss": 1.35, + "step": 5228 + }, + { + "epoch": 0.55, + "learning_rate": 1.0056733572067765e-05, + "loss": 1.3512, + "step": 5229 + }, + { + "epoch": 0.55, + "learning_rate": 1.0053073377164186e-05, + "loss": 1.3852, + "step": 5230 + }, + { + "epoch": 0.55, + "learning_rate": 1.0049413175150135e-05, + "loss": 1.3502, + "step": 5231 + }, + { + "epoch": 0.55, + "learning_rate": 1.004575296651599e-05, + "loss": 1.4637, + "step": 5232 + }, + { + "epoch": 0.55, + "learning_rate": 1.0042092751752123e-05, + "loss": 1.3877, + "step": 5233 + }, + { + "epoch": 0.55, + "learning_rate": 1.0038432531348909e-05, + "loss": 1.3804, + "step": 5234 + }, + { + "epoch": 0.55, + "learning_rate": 1.0034772305796723e-05, + "loss": 1.3613, + "step": 5235 + }, + { + "epoch": 0.55, + "learning_rate": 1.003111207558594e-05, + "loss": 1.3218, + "step": 5236 + }, + { + "epoch": 0.55, + "learning_rate": 1.0027451841206944e-05, + "loss": 1.3554, + "step": 5237 + }, + { + "epoch": 0.55, + "learning_rate": 1.0023791603150099e-05, + "loss": 1.372, + "step": 5238 + }, + { + "epoch": 0.55, + "learning_rate": 1.0020131361905793e-05, + "loss": 1.3544, + "step": 5239 + }, + { + "epoch": 0.55, + "learning_rate": 1.0016471117964404e-05, + "loss": 1.3472, + "step": 5240 + }, + { + "epoch": 0.55, + "learning_rate": 1.001281087181631e-05, + "loss": 1.4247, + "step": 5241 + }, + { + "epoch": 0.55, + "learning_rate": 1.0009150623951883e-05, + "loss": 1.2685, + "step": 5242 + }, + { + "epoch": 0.55, + "learning_rate": 1.000549037486151e-05, + "loss": 1.4036, + "step": 5243 + }, + { + "epoch": 0.55, + "learning_rate": 1.0001830125035565e-05, + "loss": 1.3602, + "step": 5244 + }, + { + "epoch": 0.55, + "learning_rate": 9.998169874964437e-06, + "loss": 1.3784, + "step": 5245 + }, + { + "epoch": 0.55, + "learning_rate": 9.994509625138496e-06, + "loss": 1.3389, + "step": 5246 + }, + { + "epoch": 0.55, + "learning_rate": 9.990849376048119e-06, + "loss": 1.4561, + "step": 5247 + }, + { + "epoch": 0.55, + "learning_rate": 9.987189128183695e-06, + "loss": 1.3876, + "step": 5248 + }, + { + "epoch": 0.55, + "learning_rate": 9.9835288820356e-06, + "loss": 1.3362, + "step": 5249 + }, + { + "epoch": 0.55, + "learning_rate": 9.97986863809421e-06, + "loss": 1.3449, + "step": 5250 + }, + { + "epoch": 0.55, + "learning_rate": 9.9762083968499e-06, + "loss": 1.3521, + "step": 5251 + }, + { + "epoch": 0.55, + "learning_rate": 9.972548158793061e-06, + "loss": 1.4452, + "step": 5252 + }, + { + "epoch": 0.55, + "learning_rate": 9.968887924414062e-06, + "loss": 1.4126, + "step": 5253 + }, + { + "epoch": 0.55, + "learning_rate": 9.965227694203282e-06, + "loss": 1.3054, + "step": 5254 + }, + { + "epoch": 0.55, + "learning_rate": 9.961567468651093e-06, + "loss": 1.3771, + "step": 5255 + }, + { + "epoch": 0.55, + "learning_rate": 9.957907248247878e-06, + "loss": 1.3566, + "step": 5256 + }, + { + "epoch": 0.55, + "learning_rate": 9.954247033484014e-06, + "loss": 1.4765, + "step": 5257 + }, + { + "epoch": 0.55, + "learning_rate": 9.950586824849865e-06, + "loss": 1.4749, + "step": 5258 + }, + { + "epoch": 0.55, + "learning_rate": 9.946926622835815e-06, + "loss": 1.3679, + "step": 5259 + }, + { + "epoch": 0.55, + "learning_rate": 9.943266427932238e-06, + "loss": 1.2671, + "step": 5260 + }, + { + "epoch": 0.55, + "learning_rate": 9.9396062406295e-06, + "loss": 1.3485, + "step": 5261 + }, + { + "epoch": 0.55, + "learning_rate": 9.935946061417968e-06, + "loss": 1.3136, + "step": 5262 + }, + { + "epoch": 0.55, + "learning_rate": 9.932285890788024e-06, + "loss": 1.3954, + "step": 5263 + }, + { + "epoch": 0.55, + "learning_rate": 9.928625729230031e-06, + "loss": 1.428, + "step": 5264 + }, + { + "epoch": 0.55, + "learning_rate": 9.924965577234356e-06, + "loss": 1.4144, + "step": 5265 + }, + { + "epoch": 0.55, + "learning_rate": 9.92130543529136e-06, + "loss": 1.3361, + "step": 5266 + }, + { + "epoch": 0.55, + "learning_rate": 9.91764530389142e-06, + "loss": 1.4503, + "step": 5267 + }, + { + "epoch": 0.55, + "learning_rate": 9.913985183524893e-06, + "loss": 1.3431, + "step": 5268 + }, + { + "epoch": 0.55, + "learning_rate": 9.91032507468214e-06, + "loss": 1.3206, + "step": 5269 + }, + { + "epoch": 0.55, + "learning_rate": 9.906664977853518e-06, + "loss": 1.4568, + "step": 5270 + }, + { + "epoch": 0.55, + "learning_rate": 9.903004893529397e-06, + "loss": 1.3591, + "step": 5271 + }, + { + "epoch": 0.55, + "learning_rate": 9.899344822200127e-06, + "loss": 1.3382, + "step": 5272 + }, + { + "epoch": 0.55, + "learning_rate": 9.895684764356066e-06, + "loss": 1.3008, + "step": 5273 + }, + { + "epoch": 0.55, + "learning_rate": 9.89202472048756e-06, + "loss": 1.316, + "step": 5274 + }, + { + "epoch": 0.55, + "learning_rate": 9.888364691084971e-06, + "loss": 1.4246, + "step": 5275 + }, + { + "epoch": 0.55, + "learning_rate": 9.88470467663865e-06, + "loss": 1.3615, + "step": 5276 + }, + { + "epoch": 0.55, + "learning_rate": 9.881044677638934e-06, + "loss": 1.3418, + "step": 5277 + }, + { + "epoch": 0.55, + "learning_rate": 9.877384694576172e-06, + "loss": 1.249, + "step": 5278 + }, + { + "epoch": 0.55, + "learning_rate": 9.873724727940715e-06, + "loss": 1.2779, + "step": 5279 + }, + { + "epoch": 0.55, + "learning_rate": 9.870064778222903e-06, + "loss": 1.3529, + "step": 5280 + }, + { + "epoch": 0.55, + "learning_rate": 9.866404845913065e-06, + "loss": 1.3204, + "step": 5281 + }, + { + "epoch": 0.55, + "learning_rate": 9.862744931501548e-06, + "loss": 1.3537, + "step": 5282 + }, + { + "epoch": 0.55, + "learning_rate": 9.859085035478687e-06, + "loss": 1.3681, + "step": 5283 + }, + { + "epoch": 0.55, + "learning_rate": 9.855425158334809e-06, + "loss": 1.3983, + "step": 5284 + }, + { + "epoch": 0.55, + "learning_rate": 9.851765300560238e-06, + "loss": 1.401, + "step": 5285 + }, + { + "epoch": 0.55, + "learning_rate": 9.848105462645315e-06, + "loss": 1.3073, + "step": 5286 + }, + { + "epoch": 0.55, + "learning_rate": 9.844445645080358e-06, + "loss": 1.3162, + "step": 5287 + }, + { + "epoch": 0.55, + "learning_rate": 9.840785848355685e-06, + "loss": 1.3345, + "step": 5288 + }, + { + "epoch": 0.55, + "learning_rate": 9.837126072961616e-06, + "loss": 1.4241, + "step": 5289 + }, + { + "epoch": 0.55, + "learning_rate": 9.83346631938847e-06, + "loss": 1.3339, + "step": 5290 + }, + { + "epoch": 0.55, + "learning_rate": 9.829806588126561e-06, + "loss": 1.3507, + "step": 5291 + }, + { + "epoch": 0.55, + "learning_rate": 9.826146879666196e-06, + "loss": 1.2806, + "step": 5292 + }, + { + "epoch": 0.56, + "learning_rate": 9.822487194497675e-06, + "loss": 1.3952, + "step": 5293 + }, + { + "epoch": 0.56, + "learning_rate": 9.818827533111314e-06, + "loss": 1.3319, + "step": 5294 + }, + { + "epoch": 0.56, + "learning_rate": 9.81516789599741e-06, + "loss": 1.351, + "step": 5295 + }, + { + "epoch": 0.56, + "learning_rate": 9.811508283646258e-06, + "loss": 1.4076, + "step": 5296 + }, + { + "epoch": 0.56, + "learning_rate": 9.80784869654815e-06, + "loss": 1.3271, + "step": 5297 + }, + { + "epoch": 0.56, + "learning_rate": 9.80418913519338e-06, + "loss": 1.4059, + "step": 5298 + }, + { + "epoch": 0.56, + "learning_rate": 9.80052960007224e-06, + "loss": 1.4146, + "step": 5299 + }, + { + "epoch": 0.56, + "learning_rate": 9.796870091675005e-06, + "loss": 1.3454, + "step": 5300 + }, + { + "epoch": 0.56, + "learning_rate": 9.793210610491953e-06, + "loss": 1.4376, + "step": 5301 + }, + { + "epoch": 0.56, + "learning_rate": 9.789551157013372e-06, + "loss": 1.3437, + "step": 5302 + }, + { + "epoch": 0.56, + "learning_rate": 9.78589173172953e-06, + "loss": 1.3073, + "step": 5303 + }, + { + "epoch": 0.56, + "learning_rate": 9.782232335130688e-06, + "loss": 1.2989, + "step": 5304 + }, + { + "epoch": 0.56, + "learning_rate": 9.778572967707122e-06, + "loss": 1.4028, + "step": 5305 + }, + { + "epoch": 0.56, + "learning_rate": 9.77491362994909e-06, + "loss": 1.3096, + "step": 5306 + }, + { + "epoch": 0.56, + "learning_rate": 9.77125432234685e-06, + "loss": 1.3719, + "step": 5307 + }, + { + "epoch": 0.56, + "learning_rate": 9.767595045390647e-06, + "loss": 1.3271, + "step": 5308 + }, + { + "epoch": 0.56, + "learning_rate": 9.763935799570739e-06, + "loss": 1.3693, + "step": 5309 + }, + { + "epoch": 0.56, + "learning_rate": 9.760276585377371e-06, + "loss": 1.3586, + "step": 5310 + }, + { + "epoch": 0.56, + "learning_rate": 9.756617403300781e-06, + "loss": 1.3423, + "step": 5311 + }, + { + "epoch": 0.56, + "learning_rate": 9.7529582538312e-06, + "loss": 1.388, + "step": 5312 + }, + { + "epoch": 0.56, + "learning_rate": 9.74929913745887e-06, + "loss": 1.3594, + "step": 5313 + }, + { + "epoch": 0.56, + "learning_rate": 9.745640054674015e-06, + "loss": 1.2831, + "step": 5314 + }, + { + "epoch": 0.56, + "learning_rate": 9.741981005966856e-06, + "loss": 1.4207, + "step": 5315 + }, + { + "epoch": 0.56, + "learning_rate": 9.738321991827609e-06, + "loss": 1.2807, + "step": 5316 + }, + { + "epoch": 0.56, + "learning_rate": 9.734663012746493e-06, + "loss": 1.3396, + "step": 5317 + }, + { + "epoch": 0.56, + "learning_rate": 9.731004069213722e-06, + "loss": 1.3666, + "step": 5318 + }, + { + "epoch": 0.56, + "learning_rate": 9.72734516171949e-06, + "loss": 1.3466, + "step": 5319 + }, + { + "epoch": 0.56, + "learning_rate": 9.723686290753995e-06, + "loss": 1.4478, + "step": 5320 + }, + { + "epoch": 0.56, + "learning_rate": 9.720027456807442e-06, + "loss": 1.316, + "step": 5321 + }, + { + "epoch": 0.56, + "learning_rate": 9.71636866037002e-06, + "loss": 1.3762, + "step": 5322 + }, + { + "epoch": 0.56, + "learning_rate": 9.712709901931906e-06, + "loss": 1.4156, + "step": 5323 + }, + { + "epoch": 0.56, + "learning_rate": 9.70905118198328e-06, + "loss": 1.2452, + "step": 5324 + }, + { + "epoch": 0.56, + "learning_rate": 9.705392501014325e-06, + "loss": 1.3771, + "step": 5325 + }, + { + "epoch": 0.56, + "learning_rate": 9.701733859515205e-06, + "loss": 1.3433, + "step": 5326 + }, + { + "epoch": 0.56, + "learning_rate": 9.698075257976079e-06, + "loss": 1.3702, + "step": 5327 + }, + { + "epoch": 0.56, + "learning_rate": 9.694416696887115e-06, + "loss": 1.295, + "step": 5328 + }, + { + "epoch": 0.56, + "learning_rate": 9.690758176738463e-06, + "loss": 1.3462, + "step": 5329 + }, + { + "epoch": 0.56, + "learning_rate": 9.68709969802027e-06, + "loss": 1.5304, + "step": 5330 + }, + { + "epoch": 0.56, + "learning_rate": 9.683441261222672e-06, + "loss": 1.3518, + "step": 5331 + }, + { + "epoch": 0.56, + "learning_rate": 9.679782866835816e-06, + "loss": 1.3778, + "step": 5332 + }, + { + "epoch": 0.56, + "learning_rate": 9.67612451534983e-06, + "loss": 1.3731, + "step": 5333 + }, + { + "epoch": 0.56, + "learning_rate": 9.672466207254837e-06, + "loss": 1.3315, + "step": 5334 + }, + { + "epoch": 0.56, + "learning_rate": 9.66880794304095e-06, + "loss": 1.3105, + "step": 5335 + }, + { + "epoch": 0.56, + "learning_rate": 9.665149723198293e-06, + "loss": 1.3903, + "step": 5336 + }, + { + "epoch": 0.56, + "learning_rate": 9.661491548216972e-06, + "loss": 1.3554, + "step": 5337 + }, + { + "epoch": 0.56, + "learning_rate": 9.657833418587084e-06, + "loss": 1.3231, + "step": 5338 + }, + { + "epoch": 0.56, + "learning_rate": 9.65417533479872e-06, + "loss": 1.352, + "step": 5339 + }, + { + "epoch": 0.56, + "learning_rate": 9.650517297341983e-06, + "loss": 1.3957, + "step": 5340 + }, + { + "epoch": 0.56, + "learning_rate": 9.646859306706948e-06, + "loss": 1.3938, + "step": 5341 + }, + { + "epoch": 0.56, + "learning_rate": 9.643201363383693e-06, + "loss": 1.3038, + "step": 5342 + }, + { + "epoch": 0.56, + "learning_rate": 9.63954346786228e-06, + "loss": 1.2973, + "step": 5343 + }, + { + "epoch": 0.56, + "learning_rate": 9.635885620632786e-06, + "loss": 1.379, + "step": 5344 + }, + { + "epoch": 0.56, + "learning_rate": 9.632227822185266e-06, + "loss": 1.5377, + "step": 5345 + }, + { + "epoch": 0.56, + "learning_rate": 9.628570073009767e-06, + "loss": 1.4573, + "step": 5346 + }, + { + "epoch": 0.56, + "learning_rate": 9.624912373596329e-06, + "loss": 1.3394, + "step": 5347 + }, + { + "epoch": 0.56, + "learning_rate": 9.621254724434999e-06, + "loss": 1.4157, + "step": 5348 + }, + { + "epoch": 0.56, + "learning_rate": 9.617597126015808e-06, + "loss": 1.3526, + "step": 5349 + }, + { + "epoch": 0.56, + "learning_rate": 9.61393957882877e-06, + "loss": 1.3795, + "step": 5350 + }, + { + "epoch": 0.56, + "learning_rate": 9.610282083363913e-06, + "loss": 1.3765, + "step": 5351 + }, + { + "epoch": 0.56, + "learning_rate": 9.606624640111243e-06, + "loss": 1.3512, + "step": 5352 + }, + { + "epoch": 0.56, + "learning_rate": 9.602967249560766e-06, + "loss": 1.3298, + "step": 5353 + }, + { + "epoch": 0.56, + "learning_rate": 9.599309912202469e-06, + "loss": 1.3093, + "step": 5354 + }, + { + "epoch": 0.56, + "learning_rate": 9.595652628526354e-06, + "loss": 1.3353, + "step": 5355 + }, + { + "epoch": 0.56, + "learning_rate": 9.591995399022397e-06, + "loss": 1.3081, + "step": 5356 + }, + { + "epoch": 0.56, + "learning_rate": 9.588338224180576e-06, + "loss": 1.343, + "step": 5357 + }, + { + "epoch": 0.56, + "learning_rate": 9.584681104490848e-06, + "loss": 1.3275, + "step": 5358 + }, + { + "epoch": 0.56, + "learning_rate": 9.581024040443185e-06, + "loss": 1.3399, + "step": 5359 + }, + { + "epoch": 0.56, + "learning_rate": 9.577367032527538e-06, + "loss": 1.3181, + "step": 5360 + }, + { + "epoch": 0.56, + "learning_rate": 9.573710081233846e-06, + "loss": 1.3531, + "step": 5361 + }, + { + "epoch": 0.56, + "learning_rate": 9.570053187052049e-06, + "loss": 1.4056, + "step": 5362 + }, + { + "epoch": 0.56, + "learning_rate": 9.566396350472079e-06, + "loss": 1.3303, + "step": 5363 + }, + { + "epoch": 0.56, + "learning_rate": 9.56273957198386e-06, + "loss": 1.3506, + "step": 5364 + }, + { + "epoch": 0.56, + "learning_rate": 9.559082852077302e-06, + "loss": 1.4588, + "step": 5365 + }, + { + "epoch": 0.56, + "learning_rate": 9.555426191242307e-06, + "loss": 1.3434, + "step": 5366 + }, + { + "epoch": 0.56, + "learning_rate": 9.551769589968784e-06, + "loss": 1.3508, + "step": 5367 + }, + { + "epoch": 0.56, + "learning_rate": 9.548113048746622e-06, + "loss": 1.3701, + "step": 5368 + }, + { + "epoch": 0.56, + "learning_rate": 9.544456568065698e-06, + "loss": 1.3664, + "step": 5369 + }, + { + "epoch": 0.56, + "learning_rate": 9.540800148415885e-06, + "loss": 1.6697, + "step": 5370 + }, + { + "epoch": 0.56, + "learning_rate": 9.537143790287057e-06, + "loss": 1.5298, + "step": 5371 + }, + { + "epoch": 0.56, + "learning_rate": 9.533487494169073e-06, + "loss": 1.3884, + "step": 5372 + }, + { + "epoch": 0.56, + "learning_rate": 9.52983126055177e-06, + "loss": 1.403, + "step": 5373 + }, + { + "epoch": 0.56, + "eval_loss": 1.4240995645523071, + "eval_runtime": 77.4615, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 5373 + }, + { + "epoch": 0.56, + "learning_rate": 9.526175089925e-06, + "loss": 1.3141, + "step": 5374 + }, + { + "epoch": 0.56, + "learning_rate": 9.522518982778596e-06, + "loss": 1.3733, + "step": 5375 + }, + { + "epoch": 0.56, + "learning_rate": 9.51886293960238e-06, + "loss": 1.3095, + "step": 5376 + }, + { + "epoch": 0.56, + "learning_rate": 9.515206960886162e-06, + "loss": 1.3713, + "step": 5377 + }, + { + "epoch": 0.56, + "learning_rate": 9.51155104711976e-06, + "loss": 1.3585, + "step": 5378 + }, + { + "epoch": 0.56, + "learning_rate": 9.507895198792967e-06, + "loss": 1.3473, + "step": 5379 + }, + { + "epoch": 0.56, + "learning_rate": 9.504239416395576e-06, + "loss": 1.3282, + "step": 5380 + }, + { + "epoch": 0.56, + "learning_rate": 9.500583700417357e-06, + "loss": 1.3655, + "step": 5381 + }, + { + "epoch": 0.56, + "learning_rate": 9.496928051348095e-06, + "loss": 1.4512, + "step": 5382 + }, + { + "epoch": 0.56, + "learning_rate": 9.49327246967755e-06, + "loss": 1.4071, + "step": 5383 + }, + { + "epoch": 0.56, + "learning_rate": 9.489616955895472e-06, + "loss": 1.3703, + "step": 5384 + }, + { + "epoch": 0.56, + "learning_rate": 9.485961510491604e-06, + "loss": 1.3358, + "step": 5385 + }, + { + "epoch": 0.56, + "learning_rate": 9.482306133955691e-06, + "loss": 1.3505, + "step": 5386 + }, + { + "epoch": 0.56, + "learning_rate": 9.478650826777457e-06, + "loss": 1.2578, + "step": 5387 + }, + { + "epoch": 0.57, + "learning_rate": 9.474995589446612e-06, + "loss": 1.4298, + "step": 5388 + }, + { + "epoch": 0.57, + "learning_rate": 9.471340422452864e-06, + "loss": 1.4044, + "step": 5389 + }, + { + "epoch": 0.57, + "learning_rate": 9.467685326285922e-06, + "loss": 1.3524, + "step": 5390 + }, + { + "epoch": 0.57, + "learning_rate": 9.46403030143547e-06, + "loss": 1.3017, + "step": 5391 + }, + { + "epoch": 0.57, + "learning_rate": 9.460375348391185e-06, + "loss": 1.3361, + "step": 5392 + }, + { + "epoch": 0.57, + "learning_rate": 9.456720467642733e-06, + "loss": 1.3182, + "step": 5393 + }, + { + "epoch": 0.57, + "learning_rate": 9.453065659679785e-06, + "loss": 1.3869, + "step": 5394 + }, + { + "epoch": 0.57, + "learning_rate": 9.449410924991986e-06, + "loss": 1.3161, + "step": 5395 + }, + { + "epoch": 0.57, + "learning_rate": 9.44575626406897e-06, + "loss": 1.3, + "step": 5396 + }, + { + "epoch": 0.57, + "learning_rate": 9.442101677400378e-06, + "loss": 1.5103, + "step": 5397 + }, + { + "epoch": 0.57, + "learning_rate": 9.438447165475828e-06, + "loss": 1.3511, + "step": 5398 + }, + { + "epoch": 0.57, + "learning_rate": 9.43479272878493e-06, + "loss": 1.3461, + "step": 5399 + }, + { + "epoch": 0.57, + "learning_rate": 9.431138367817277e-06, + "loss": 1.2657, + "step": 5400 + }, + { + "epoch": 0.57, + "learning_rate": 9.427484083062472e-06, + "loss": 1.3736, + "step": 5401 + }, + { + "epoch": 0.57, + "learning_rate": 9.423829875010089e-06, + "loss": 1.3476, + "step": 5402 + }, + { + "epoch": 0.57, + "learning_rate": 9.4201757441497e-06, + "loss": 1.3495, + "step": 5403 + }, + { + "epoch": 0.57, + "learning_rate": 9.416521690970857e-06, + "loss": 1.387, + "step": 5404 + }, + { + "epoch": 0.57, + "learning_rate": 9.41286771596312e-06, + "loss": 1.2829, + "step": 5405 + }, + { + "epoch": 0.57, + "learning_rate": 9.409213819616022e-06, + "loss": 1.3544, + "step": 5406 + }, + { + "epoch": 0.57, + "learning_rate": 9.405560002419098e-06, + "loss": 1.3202, + "step": 5407 + }, + { + "epoch": 0.57, + "learning_rate": 9.40190626486185e-06, + "loss": 1.3034, + "step": 5408 + }, + { + "epoch": 0.57, + "learning_rate": 9.398252607433801e-06, + "loss": 1.3223, + "step": 5409 + }, + { + "epoch": 0.57, + "learning_rate": 9.394599030624443e-06, + "loss": 1.3327, + "step": 5410 + }, + { + "epoch": 0.57, + "learning_rate": 9.390945534923258e-06, + "loss": 1.3248, + "step": 5411 + }, + { + "epoch": 0.57, + "learning_rate": 9.387292120819716e-06, + "loss": 1.3084, + "step": 5412 + }, + { + "epoch": 0.57, + "learning_rate": 9.383638788803291e-06, + "loss": 1.344, + "step": 5413 + }, + { + "epoch": 0.57, + "learning_rate": 9.379985539363436e-06, + "loss": 1.3354, + "step": 5414 + }, + { + "epoch": 0.57, + "learning_rate": 9.376332372989586e-06, + "loss": 1.3291, + "step": 5415 + }, + { + "epoch": 0.57, + "learning_rate": 9.372679290171167e-06, + "loss": 1.3468, + "step": 5416 + }, + { + "epoch": 0.57, + "learning_rate": 9.36902629139761e-06, + "loss": 1.3481, + "step": 5417 + }, + { + "epoch": 0.57, + "learning_rate": 9.36537337715832e-06, + "loss": 1.3309, + "step": 5418 + }, + { + "epoch": 0.57, + "learning_rate": 9.361720547942683e-06, + "loss": 1.362, + "step": 5419 + }, + { + "epoch": 0.57, + "learning_rate": 9.358067804240098e-06, + "loss": 1.3647, + "step": 5420 + }, + { + "epoch": 0.57, + "learning_rate": 9.354415146539933e-06, + "loss": 1.4511, + "step": 5421 + }, + { + "epoch": 0.57, + "learning_rate": 9.350762575331554e-06, + "loss": 1.3379, + "step": 5422 + }, + { + "epoch": 0.57, + "learning_rate": 9.3471100911043e-06, + "loss": 1.5468, + "step": 5423 + }, + { + "epoch": 0.57, + "learning_rate": 9.343457694347524e-06, + "loss": 1.4259, + "step": 5424 + }, + { + "epoch": 0.57, + "learning_rate": 9.339805385550548e-06, + "loss": 1.3816, + "step": 5425 + }, + { + "epoch": 0.57, + "learning_rate": 9.336153165202689e-06, + "loss": 1.3627, + "step": 5426 + }, + { + "epoch": 0.57, + "learning_rate": 9.332501033793242e-06, + "loss": 1.3338, + "step": 5427 + }, + { + "epoch": 0.57, + "learning_rate": 9.328848991811509e-06, + "loss": 1.2946, + "step": 5428 + }, + { + "epoch": 0.57, + "learning_rate": 9.325197039746769e-06, + "loss": 1.3405, + "step": 5429 + }, + { + "epoch": 0.57, + "learning_rate": 9.321545178088288e-06, + "loss": 1.3549, + "step": 5430 + }, + { + "epoch": 0.57, + "learning_rate": 9.317893407325314e-06, + "loss": 1.3225, + "step": 5431 + }, + { + "epoch": 0.57, + "learning_rate": 9.314241727947101e-06, + "loss": 1.3457, + "step": 5432 + }, + { + "epoch": 0.57, + "learning_rate": 9.310590140442878e-06, + "loss": 1.311, + "step": 5433 + }, + { + "epoch": 0.57, + "learning_rate": 9.306938645301862e-06, + "loss": 1.3615, + "step": 5434 + }, + { + "epoch": 0.57, + "learning_rate": 9.303287243013255e-06, + "loss": 1.3495, + "step": 5435 + }, + { + "epoch": 0.57, + "learning_rate": 9.29963593406626e-06, + "loss": 1.3899, + "step": 5436 + }, + { + "epoch": 0.57, + "learning_rate": 9.295984718950058e-06, + "loss": 1.3189, + "step": 5437 + }, + { + "epoch": 0.57, + "learning_rate": 9.292333598153813e-06, + "loss": 1.4199, + "step": 5438 + }, + { + "epoch": 0.57, + "learning_rate": 9.288682572166677e-06, + "loss": 1.4751, + "step": 5439 + }, + { + "epoch": 0.57, + "learning_rate": 9.285031641477804e-06, + "loss": 1.3435, + "step": 5440 + }, + { + "epoch": 0.57, + "learning_rate": 9.281380806576322e-06, + "loss": 1.2954, + "step": 5441 + }, + { + "epoch": 0.57, + "learning_rate": 9.277730067951341e-06, + "loss": 1.3414, + "step": 5442 + }, + { + "epoch": 0.57, + "learning_rate": 9.274079426091978e-06, + "loss": 1.3642, + "step": 5443 + }, + { + "epoch": 0.57, + "learning_rate": 9.27042888148732e-06, + "loss": 1.3651, + "step": 5444 + }, + { + "epoch": 0.57, + "learning_rate": 9.266778434626448e-06, + "loss": 1.3995, + "step": 5445 + }, + { + "epoch": 0.57, + "learning_rate": 9.263128085998421e-06, + "loss": 1.2692, + "step": 5446 + }, + { + "epoch": 0.57, + "learning_rate": 9.2594778360923e-06, + "loss": 1.4355, + "step": 5447 + }, + { + "epoch": 0.57, + "learning_rate": 9.255827685397124e-06, + "loss": 1.4262, + "step": 5448 + }, + { + "epoch": 0.57, + "learning_rate": 9.252177634401917e-06, + "loss": 1.3372, + "step": 5449 + }, + { + "epoch": 0.57, + "learning_rate": 9.248527683595685e-06, + "loss": 1.4603, + "step": 5450 + }, + { + "epoch": 0.57, + "learning_rate": 9.24487783346744e-06, + "loss": 1.446, + "step": 5451 + }, + { + "epoch": 0.57, + "learning_rate": 9.241228084506167e-06, + "loss": 1.4088, + "step": 5452 + }, + { + "epoch": 0.57, + "learning_rate": 9.237578437200832e-06, + "loss": 1.3074, + "step": 5453 + }, + { + "epoch": 0.57, + "learning_rate": 9.233928892040392e-06, + "loss": 1.4347, + "step": 5454 + }, + { + "epoch": 0.57, + "learning_rate": 9.230279449513802e-06, + "loss": 1.2982, + "step": 5455 + }, + { + "epoch": 0.57, + "learning_rate": 9.226630110109988e-06, + "loss": 1.2928, + "step": 5456 + }, + { + "epoch": 0.57, + "learning_rate": 9.222980874317869e-06, + "loss": 1.2849, + "step": 5457 + }, + { + "epoch": 0.57, + "learning_rate": 9.219331742626343e-06, + "loss": 1.3137, + "step": 5458 + }, + { + "epoch": 0.57, + "learning_rate": 9.215682715524309e-06, + "loss": 1.3523, + "step": 5459 + }, + { + "epoch": 0.57, + "learning_rate": 9.21203379350064e-06, + "loss": 1.381, + "step": 5460 + }, + { + "epoch": 0.57, + "learning_rate": 9.208384977044191e-06, + "loss": 1.286, + "step": 5461 + }, + { + "epoch": 0.57, + "learning_rate": 9.204736266643819e-06, + "loss": 1.3467, + "step": 5462 + }, + { + "epoch": 0.57, + "learning_rate": 9.201087662788353e-06, + "loss": 1.3582, + "step": 5463 + }, + { + "epoch": 0.57, + "learning_rate": 9.197439165966617e-06, + "loss": 1.3912, + "step": 5464 + }, + { + "epoch": 0.57, + "learning_rate": 9.193790776667402e-06, + "loss": 1.3144, + "step": 5465 + }, + { + "epoch": 0.57, + "learning_rate": 9.190142495379515e-06, + "loss": 1.3403, + "step": 5466 + }, + { + "epoch": 0.57, + "learning_rate": 9.186494322591725e-06, + "loss": 1.3253, + "step": 5467 + }, + { + "epoch": 0.57, + "learning_rate": 9.182846258792794e-06, + "loss": 1.2908, + "step": 5468 + }, + { + "epoch": 0.57, + "learning_rate": 9.179198304471463e-06, + "loss": 1.3486, + "step": 5469 + }, + { + "epoch": 0.57, + "learning_rate": 9.175550460116473e-06, + "loss": 1.3915, + "step": 5470 + }, + { + "epoch": 0.57, + "learning_rate": 9.171902726216538e-06, + "loss": 1.3441, + "step": 5471 + }, + { + "epoch": 0.57, + "learning_rate": 9.168255103260362e-06, + "loss": 1.3196, + "step": 5472 + }, + { + "epoch": 0.57, + "learning_rate": 9.164607591736627e-06, + "loss": 1.3279, + "step": 5473 + }, + { + "epoch": 0.57, + "learning_rate": 9.160960192134011e-06, + "loss": 1.2643, + "step": 5474 + }, + { + "epoch": 0.57, + "learning_rate": 9.157312904941174e-06, + "loss": 1.3327, + "step": 5475 + }, + { + "epoch": 0.57, + "learning_rate": 9.153665730646756e-06, + "loss": 1.4016, + "step": 5476 + }, + { + "epoch": 0.57, + "learning_rate": 9.150018669739378e-06, + "loss": 1.3614, + "step": 5477 + }, + { + "epoch": 0.57, + "learning_rate": 9.146371722707662e-06, + "loss": 1.3469, + "step": 5478 + }, + { + "epoch": 0.57, + "learning_rate": 9.142724890040204e-06, + "loss": 1.3625, + "step": 5479 + }, + { + "epoch": 0.57, + "learning_rate": 9.139078172225585e-06, + "loss": 1.3879, + "step": 5480 + }, + { + "epoch": 0.57, + "learning_rate": 9.135431569752362e-06, + "loss": 1.3738, + "step": 5481 + }, + { + "epoch": 0.57, + "learning_rate": 9.131785083109101e-06, + "loss": 1.3507, + "step": 5482 + }, + { + "epoch": 0.57, + "learning_rate": 9.128138712784331e-06, + "loss": 1.3681, + "step": 5483 + }, + { + "epoch": 0.58, + "learning_rate": 9.124492459266567e-06, + "loss": 1.332, + "step": 5484 + }, + { + "epoch": 0.58, + "learning_rate": 9.12084632304432e-06, + "loss": 1.4746, + "step": 5485 + }, + { + "epoch": 0.58, + "learning_rate": 9.11720030460608e-06, + "loss": 1.2775, + "step": 5486 + }, + { + "epoch": 0.58, + "learning_rate": 9.113554404440317e-06, + "loss": 1.2567, + "step": 5487 + }, + { + "epoch": 0.58, + "learning_rate": 9.10990862303548e-06, + "loss": 1.3935, + "step": 5488 + }, + { + "epoch": 0.58, + "learning_rate": 9.106262960880024e-06, + "loss": 1.3544, + "step": 5489 + }, + { + "epoch": 0.58, + "learning_rate": 9.102617418462365e-06, + "loss": 1.4023, + "step": 5490 + }, + { + "epoch": 0.58, + "learning_rate": 9.098971996270918e-06, + "loss": 1.3759, + "step": 5491 + }, + { + "epoch": 0.58, + "learning_rate": 9.095326694794064e-06, + "loss": 1.4165, + "step": 5492 + }, + { + "epoch": 0.58, + "learning_rate": 9.091681514520194e-06, + "loss": 1.3189, + "step": 5493 + }, + { + "epoch": 0.58, + "learning_rate": 9.088036455937663e-06, + "loss": 1.3135, + "step": 5494 + }, + { + "epoch": 0.58, + "learning_rate": 9.084391519534815e-06, + "loss": 1.3521, + "step": 5495 + }, + { + "epoch": 0.58, + "learning_rate": 9.080746705799971e-06, + "loss": 1.3314, + "step": 5496 + }, + { + "epoch": 0.58, + "learning_rate": 9.077102015221457e-06, + "loss": 1.3119, + "step": 5497 + }, + { + "epoch": 0.58, + "learning_rate": 9.073457448287557e-06, + "loss": 1.2895, + "step": 5498 + }, + { + "epoch": 0.58, + "learning_rate": 9.069813005486554e-06, + "loss": 1.3155, + "step": 5499 + }, + { + "epoch": 0.58, + "learning_rate": 9.066168687306701e-06, + "loss": 1.4048, + "step": 5500 + }, + { + "epoch": 0.58, + "learning_rate": 9.062524494236256e-06, + "loss": 1.3665, + "step": 5501 + }, + { + "epoch": 0.58, + "learning_rate": 9.058880426763442e-06, + "loss": 1.3258, + "step": 5502 + }, + { + "epoch": 0.58, + "learning_rate": 9.05523648537647e-06, + "loss": 1.3078, + "step": 5503 + }, + { + "epoch": 0.58, + "learning_rate": 9.051592670563527e-06, + "loss": 1.361, + "step": 5504 + }, + { + "epoch": 0.58, + "learning_rate": 9.047948982812801e-06, + "loss": 1.3557, + "step": 5505 + }, + { + "epoch": 0.58, + "learning_rate": 9.044305422612453e-06, + "loss": 1.5733, + "step": 5506 + }, + { + "epoch": 0.58, + "learning_rate": 9.040661990450617e-06, + "loss": 1.2835, + "step": 5507 + }, + { + "epoch": 0.58, + "learning_rate": 9.037018686815428e-06, + "loss": 1.311, + "step": 5508 + }, + { + "epoch": 0.58, + "learning_rate": 9.033375512194993e-06, + "loss": 1.3949, + "step": 5509 + }, + { + "epoch": 0.58, + "learning_rate": 9.029732467077405e-06, + "loss": 1.356, + "step": 5510 + }, + { + "epoch": 0.58, + "learning_rate": 9.026089551950727e-06, + "loss": 1.3695, + "step": 5511 + }, + { + "epoch": 0.58, + "learning_rate": 9.022446767303033e-06, + "loss": 1.3325, + "step": 5512 + }, + { + "epoch": 0.58, + "learning_rate": 9.018804113622353e-06, + "loss": 1.401, + "step": 5513 + }, + { + "epoch": 0.58, + "learning_rate": 9.015161591396713e-06, + "loss": 1.3632, + "step": 5514 + }, + { + "epoch": 0.58, + "learning_rate": 9.011519201114108e-06, + "loss": 1.3697, + "step": 5515 + }, + { + "epoch": 0.58, + "learning_rate": 9.007876943262538e-06, + "loss": 1.2604, + "step": 5516 + }, + { + "epoch": 0.58, + "learning_rate": 9.004234818329964e-06, + "loss": 1.3557, + "step": 5517 + }, + { + "epoch": 0.58, + "learning_rate": 9.000592826804342e-06, + "loss": 1.3248, + "step": 5518 + }, + { + "epoch": 0.58, + "learning_rate": 8.996950969173596e-06, + "loss": 1.3237, + "step": 5519 + }, + { + "epoch": 0.58, + "learning_rate": 8.99330924592565e-06, + "loss": 1.339, + "step": 5520 + }, + { + "epoch": 0.58, + "learning_rate": 8.989667657548402e-06, + "loss": 1.3218, + "step": 5521 + }, + { + "epoch": 0.58, + "learning_rate": 8.986026204529728e-06, + "loss": 1.3354, + "step": 5522 + }, + { + "epoch": 0.58, + "learning_rate": 8.982384887357484e-06, + "loss": 1.3011, + "step": 5523 + }, + { + "epoch": 0.58, + "learning_rate": 8.978743706519524e-06, + "loss": 1.3526, + "step": 5524 + }, + { + "epoch": 0.58, + "learning_rate": 8.975102662503666e-06, + "loss": 1.3298, + "step": 5525 + }, + { + "epoch": 0.58, + "learning_rate": 8.971461755797718e-06, + "loss": 1.328, + "step": 5526 + }, + { + "epoch": 0.58, + "learning_rate": 8.967820986889461e-06, + "loss": 1.3705, + "step": 5527 + }, + { + "epoch": 0.58, + "learning_rate": 8.964180356266676e-06, + "loss": 1.3814, + "step": 5528 + }, + { + "epoch": 0.58, + "learning_rate": 8.96053986441711e-06, + "loss": 1.37, + "step": 5529 + }, + { + "epoch": 0.58, + "learning_rate": 8.956899511828489e-06, + "loss": 1.3224, + "step": 5530 + }, + { + "epoch": 0.58, + "learning_rate": 8.953259298988536e-06, + "loss": 1.3416, + "step": 5531 + }, + { + "epoch": 0.58, + "learning_rate": 8.949619226384942e-06, + "loss": 1.4212, + "step": 5532 + }, + { + "epoch": 0.58, + "learning_rate": 8.945979294505383e-06, + "loss": 1.4145, + "step": 5533 + }, + { + "epoch": 0.58, + "learning_rate": 8.942339503837512e-06, + "loss": 1.2179, + "step": 5534 + }, + { + "epoch": 0.58, + "learning_rate": 8.938699854868976e-06, + "loss": 1.3239, + "step": 5535 + }, + { + "epoch": 0.58, + "learning_rate": 8.93506034808739e-06, + "loss": 1.3488, + "step": 5536 + }, + { + "epoch": 0.58, + "learning_rate": 8.931420983980357e-06, + "loss": 1.3283, + "step": 5537 + }, + { + "epoch": 0.58, + "learning_rate": 8.927781763035449e-06, + "loss": 1.3866, + "step": 5538 + }, + { + "epoch": 0.58, + "learning_rate": 8.924142685740239e-06, + "loss": 1.3877, + "step": 5539 + }, + { + "epoch": 0.58, + "learning_rate": 8.920503752582265e-06, + "loss": 1.2511, + "step": 5540 + }, + { + "epoch": 0.58, + "learning_rate": 8.916864964049056e-06, + "loss": 1.3581, + "step": 5541 + }, + { + "epoch": 0.58, + "learning_rate": 8.913226320628104e-06, + "loss": 1.387, + "step": 5542 + }, + { + "epoch": 0.58, + "learning_rate": 8.909587822806905e-06, + "loss": 1.3785, + "step": 5543 + }, + { + "epoch": 0.58, + "learning_rate": 8.905949471072921e-06, + "loss": 1.4302, + "step": 5544 + }, + { + "epoch": 0.58, + "learning_rate": 8.9023112659136e-06, + "loss": 1.439, + "step": 5545 + }, + { + "epoch": 0.58, + "learning_rate": 8.898673207816357e-06, + "loss": 1.3257, + "step": 5546 + }, + { + "epoch": 0.58, + "learning_rate": 8.895035297268611e-06, + "loss": 1.4237, + "step": 5547 + }, + { + "epoch": 0.58, + "learning_rate": 8.891397534757745e-06, + "loss": 1.3141, + "step": 5548 + }, + { + "epoch": 0.58, + "learning_rate": 8.887759920771127e-06, + "loss": 1.3069, + "step": 5549 + }, + { + "epoch": 0.58, + "learning_rate": 8.884122455796095e-06, + "loss": 1.2703, + "step": 5550 + }, + { + "epoch": 0.58, + "learning_rate": 8.880485140319986e-06, + "loss": 1.2929, + "step": 5551 + }, + { + "epoch": 0.58, + "learning_rate": 8.876847974830103e-06, + "loss": 1.3719, + "step": 5552 + }, + { + "epoch": 0.58, + "learning_rate": 8.873210959813731e-06, + "loss": 1.3481, + "step": 5553 + }, + { + "epoch": 0.58, + "learning_rate": 8.869574095758141e-06, + "loss": 1.3609, + "step": 5554 + }, + { + "epoch": 0.58, + "learning_rate": 8.865937383150577e-06, + "loss": 1.3137, + "step": 5555 + }, + { + "epoch": 0.58, + "learning_rate": 8.862300822478265e-06, + "loss": 1.3602, + "step": 5556 + }, + { + "epoch": 0.58, + "learning_rate": 8.858664414228409e-06, + "loss": 1.3142, + "step": 5557 + }, + { + "epoch": 0.58, + "learning_rate": 8.855028158888196e-06, + "loss": 1.288, + "step": 5558 + }, + { + "epoch": 0.58, + "learning_rate": 8.851392056944791e-06, + "loss": 1.3407, + "step": 5559 + }, + { + "epoch": 0.58, + "learning_rate": 8.847756108885342e-06, + "loss": 1.3118, + "step": 5560 + }, + { + "epoch": 0.58, + "learning_rate": 8.84412031519696e-06, + "loss": 1.3646, + "step": 5561 + }, + { + "epoch": 0.58, + "learning_rate": 8.840484676366761e-06, + "loss": 1.3896, + "step": 5562 + }, + { + "epoch": 0.58, + "learning_rate": 8.836849192881822e-06, + "loss": 1.3296, + "step": 5563 + }, + { + "epoch": 0.58, + "learning_rate": 8.833213865229208e-06, + "loss": 1.2918, + "step": 5564 + }, + { + "epoch": 0.58, + "learning_rate": 8.82957869389595e-06, + "loss": 1.4811, + "step": 5565 + }, + { + "epoch": 0.58, + "learning_rate": 8.82594367936908e-06, + "loss": 1.3877, + "step": 5566 + }, + { + "epoch": 0.58, + "learning_rate": 8.822308822135588e-06, + "loss": 1.3716, + "step": 5567 + }, + { + "epoch": 0.58, + "learning_rate": 8.818674122682456e-06, + "loss": 1.3204, + "step": 5568 + }, + { + "epoch": 0.58, + "learning_rate": 8.815039581496634e-06, + "loss": 1.326, + "step": 5569 + }, + { + "epoch": 0.58, + "learning_rate": 8.811405199065066e-06, + "loss": 1.3762, + "step": 5570 + }, + { + "epoch": 0.58, + "learning_rate": 8.807770975874658e-06, + "loss": 1.2944, + "step": 5571 + }, + { + "epoch": 0.58, + "learning_rate": 8.804136912412311e-06, + "loss": 1.3057, + "step": 5572 + }, + { + "epoch": 0.58, + "eval_loss": 1.4187605381011963, + "eval_runtime": 77.5157, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 5572 + }, + { + "epoch": 0.58, + "learning_rate": 8.800503009164884e-06, + "loss": 1.4144, + "step": 5573 + }, + { + "epoch": 0.58, + "learning_rate": 8.796869266619238e-06, + "loss": 1.2218, + "step": 5574 + }, + { + "epoch": 0.58, + "learning_rate": 8.793235685262197e-06, + "loss": 1.4445, + "step": 5575 + }, + { + "epoch": 0.58, + "learning_rate": 8.789602265580565e-06, + "loss": 1.3761, + "step": 5576 + }, + { + "epoch": 0.58, + "learning_rate": 8.78596900806113e-06, + "loss": 1.3762, + "step": 5577 + }, + { + "epoch": 0.58, + "learning_rate": 8.782335913190657e-06, + "loss": 1.3506, + "step": 5578 + }, + { + "epoch": 0.59, + "learning_rate": 8.778702981455883e-06, + "loss": 1.4183, + "step": 5579 + }, + { + "epoch": 0.59, + "learning_rate": 8.775070213343528e-06, + "loss": 1.3123, + "step": 5580 + }, + { + "epoch": 0.59, + "learning_rate": 8.771437609340291e-06, + "loss": 1.3168, + "step": 5581 + }, + { + "epoch": 0.59, + "learning_rate": 8.76780516993285e-06, + "loss": 1.3939, + "step": 5582 + }, + { + "epoch": 0.59, + "learning_rate": 8.764172895607856e-06, + "loss": 1.3317, + "step": 5583 + }, + { + "epoch": 0.59, + "learning_rate": 8.760540786851937e-06, + "loss": 1.3094, + "step": 5584 + }, + { + "epoch": 0.59, + "learning_rate": 8.756908844151708e-06, + "loss": 1.2853, + "step": 5585 + }, + { + "epoch": 0.59, + "learning_rate": 8.753277067993752e-06, + "loss": 1.2625, + "step": 5586 + }, + { + "epoch": 0.59, + "learning_rate": 8.74964545886464e-06, + "loss": 1.4246, + "step": 5587 + }, + { + "epoch": 0.59, + "learning_rate": 8.746014017250904e-06, + "loss": 1.2891, + "step": 5588 + }, + { + "epoch": 0.59, + "learning_rate": 8.742382743639071e-06, + "loss": 1.3135, + "step": 5589 + }, + { + "epoch": 0.59, + "learning_rate": 8.738751638515639e-06, + "loss": 1.3021, + "step": 5590 + }, + { + "epoch": 0.59, + "learning_rate": 8.735120702367082e-06, + "loss": 1.3398, + "step": 5591 + }, + { + "epoch": 0.59, + "learning_rate": 8.731489935679845e-06, + "loss": 1.4173, + "step": 5592 + }, + { + "epoch": 0.59, + "learning_rate": 8.727859338940367e-06, + "loss": 1.4129, + "step": 5593 + }, + { + "epoch": 0.59, + "learning_rate": 8.724228912635053e-06, + "loss": 1.3807, + "step": 5594 + }, + { + "epoch": 0.59, + "learning_rate": 8.720598657250284e-06, + "loss": 1.2962, + "step": 5595 + }, + { + "epoch": 0.59, + "learning_rate": 8.716968573272416e-06, + "loss": 1.3784, + "step": 5596 + }, + { + "epoch": 0.59, + "learning_rate": 8.713338661187799e-06, + "loss": 1.3751, + "step": 5597 + }, + { + "epoch": 0.59, + "learning_rate": 8.70970892148274e-06, + "loss": 1.3122, + "step": 5598 + }, + { + "epoch": 0.59, + "learning_rate": 8.70607935464353e-06, + "loss": 1.4174, + "step": 5599 + }, + { + "epoch": 0.59, + "learning_rate": 8.702449961156445e-06, + "loss": 1.3275, + "step": 5600 + }, + { + "epoch": 0.59, + "learning_rate": 8.698820741507723e-06, + "loss": 1.33, + "step": 5601 + }, + { + "epoch": 0.59, + "learning_rate": 8.695191696183589e-06, + "loss": 1.4075, + "step": 5602 + }, + { + "epoch": 0.59, + "learning_rate": 8.69156282567024e-06, + "loss": 1.3778, + "step": 5603 + }, + { + "epoch": 0.59, + "learning_rate": 8.687934130453857e-06, + "loss": 1.3222, + "step": 5604 + }, + { + "epoch": 0.59, + "learning_rate": 8.684305611020587e-06, + "loss": 1.3443, + "step": 5605 + }, + { + "epoch": 0.59, + "learning_rate": 8.680677267856558e-06, + "loss": 1.3167, + "step": 5606 + }, + { + "epoch": 0.59, + "learning_rate": 8.677049101447877e-06, + "loss": 1.3209, + "step": 5607 + }, + { + "epoch": 0.59, + "learning_rate": 8.673421112280624e-06, + "loss": 1.3125, + "step": 5608 + }, + { + "epoch": 0.59, + "learning_rate": 8.669793300840857e-06, + "loss": 1.375, + "step": 5609 + }, + { + "epoch": 0.59, + "learning_rate": 8.666165667614612e-06, + "loss": 1.3627, + "step": 5610 + }, + { + "epoch": 0.59, + "learning_rate": 8.662538213087888e-06, + "loss": 1.3064, + "step": 5611 + }, + { + "epoch": 0.59, + "learning_rate": 8.658910937746685e-06, + "loss": 1.4251, + "step": 5612 + }, + { + "epoch": 0.59, + "learning_rate": 8.655283842076956e-06, + "loss": 1.3011, + "step": 5613 + }, + { + "epoch": 0.59, + "learning_rate": 8.651656926564645e-06, + "loss": 1.3299, + "step": 5614 + }, + { + "epoch": 0.59, + "learning_rate": 8.648030191695653e-06, + "loss": 1.3448, + "step": 5615 + }, + { + "epoch": 0.59, + "learning_rate": 8.644403637955883e-06, + "loss": 1.4048, + "step": 5616 + }, + { + "epoch": 0.59, + "learning_rate": 8.640777265831195e-06, + "loss": 1.336, + "step": 5617 + }, + { + "epoch": 0.59, + "learning_rate": 8.63715107580743e-06, + "loss": 1.4959, + "step": 5618 + }, + { + "epoch": 0.59, + "learning_rate": 8.633525068370397e-06, + "loss": 1.3822, + "step": 5619 + }, + { + "epoch": 0.59, + "learning_rate": 8.6298992440059e-06, + "loss": 1.282, + "step": 5620 + }, + { + "epoch": 0.59, + "learning_rate": 8.626273603199699e-06, + "loss": 1.1873, + "step": 5621 + }, + { + "epoch": 0.59, + "learning_rate": 8.622648146437538e-06, + "loss": 1.3706, + "step": 5622 + }, + { + "epoch": 0.59, + "learning_rate": 8.619022874205138e-06, + "loss": 1.2709, + "step": 5623 + }, + { + "epoch": 0.59, + "learning_rate": 8.615397786988188e-06, + "loss": 1.3608, + "step": 5624 + }, + { + "epoch": 0.59, + "learning_rate": 8.61177288527236e-06, + "loss": 1.3821, + "step": 5625 + }, + { + "epoch": 0.59, + "learning_rate": 8.608148169543292e-06, + "loss": 1.327, + "step": 5626 + }, + { + "epoch": 0.59, + "learning_rate": 8.604523640286611e-06, + "loss": 1.3544, + "step": 5627 + }, + { + "epoch": 0.59, + "learning_rate": 8.600899297987905e-06, + "loss": 1.3269, + "step": 5628 + }, + { + "epoch": 0.59, + "learning_rate": 8.597275143132745e-06, + "loss": 1.3142, + "step": 5629 + }, + { + "epoch": 0.59, + "learning_rate": 8.593651176206671e-06, + "loss": 1.3878, + "step": 5630 + }, + { + "epoch": 0.59, + "learning_rate": 8.59002739769521e-06, + "loss": 1.3386, + "step": 5631 + }, + { + "epoch": 0.59, + "learning_rate": 8.586403808083846e-06, + "loss": 1.3484, + "step": 5632 + }, + { + "epoch": 0.59, + "learning_rate": 8.582780407858052e-06, + "loss": 1.3676, + "step": 5633 + }, + { + "epoch": 0.59, + "learning_rate": 8.579157197503265e-06, + "loss": 1.3753, + "step": 5634 + }, + { + "epoch": 0.59, + "learning_rate": 8.57553417750491e-06, + "loss": 1.4058, + "step": 5635 + }, + { + "epoch": 0.59, + "learning_rate": 8.571911348348375e-06, + "loss": 1.4434, + "step": 5636 + }, + { + "epoch": 0.59, + "learning_rate": 8.568288710519027e-06, + "loss": 1.3398, + "step": 5637 + }, + { + "epoch": 0.59, + "learning_rate": 8.564666264502199e-06, + "loss": 1.3294, + "step": 5638 + }, + { + "epoch": 0.59, + "learning_rate": 8.561044010783216e-06, + "loss": 1.3165, + "step": 5639 + }, + { + "epoch": 0.59, + "learning_rate": 8.557421949847363e-06, + "loss": 1.3437, + "step": 5640 + }, + { + "epoch": 0.59, + "learning_rate": 8.553800082179905e-06, + "loss": 1.3473, + "step": 5641 + }, + { + "epoch": 0.59, + "learning_rate": 8.55017840826607e-06, + "loss": 1.3378, + "step": 5642 + }, + { + "epoch": 0.59, + "learning_rate": 8.546556928591082e-06, + "loss": 1.3357, + "step": 5643 + }, + { + "epoch": 0.59, + "learning_rate": 8.54293564364012e-06, + "loss": 1.3435, + "step": 5644 + }, + { + "epoch": 0.59, + "learning_rate": 8.53931455389834e-06, + "loss": 1.3335, + "step": 5645 + }, + { + "epoch": 0.59, + "learning_rate": 8.535693659850885e-06, + "loss": 1.2917, + "step": 5646 + }, + { + "epoch": 0.59, + "learning_rate": 8.532072961982851e-06, + "loss": 1.3785, + "step": 5647 + }, + { + "epoch": 0.59, + "learning_rate": 8.528452460779327e-06, + "loss": 1.3634, + "step": 5648 + }, + { + "epoch": 0.59, + "learning_rate": 8.524832156725359e-06, + "loss": 1.3541, + "step": 5649 + }, + { + "epoch": 0.59, + "learning_rate": 8.521212050305978e-06, + "loss": 1.335, + "step": 5650 + }, + { + "epoch": 0.59, + "learning_rate": 8.51759214200619e-06, + "loss": 1.3011, + "step": 5651 + }, + { + "epoch": 0.59, + "learning_rate": 8.513972432310965e-06, + "loss": 1.3982, + "step": 5652 + }, + { + "epoch": 0.59, + "learning_rate": 8.510352921705247e-06, + "loss": 1.3217, + "step": 5653 + }, + { + "epoch": 0.59, + "learning_rate": 8.506733610673968e-06, + "loss": 1.3275, + "step": 5654 + }, + { + "epoch": 0.59, + "learning_rate": 8.503114499702015e-06, + "loss": 1.3335, + "step": 5655 + }, + { + "epoch": 0.59, + "learning_rate": 8.499495589274257e-06, + "loss": 1.3567, + "step": 5656 + }, + { + "epoch": 0.59, + "learning_rate": 8.495876879875536e-06, + "loss": 1.348, + "step": 5657 + }, + { + "epoch": 0.59, + "learning_rate": 8.492258371990667e-06, + "loss": 1.3991, + "step": 5658 + }, + { + "epoch": 0.59, + "learning_rate": 8.488640066104435e-06, + "loss": 1.3528, + "step": 5659 + }, + { + "epoch": 0.59, + "learning_rate": 8.485021962701603e-06, + "loss": 1.3275, + "step": 5660 + }, + { + "epoch": 0.59, + "learning_rate": 8.481404062266897e-06, + "loss": 1.3605, + "step": 5661 + }, + { + "epoch": 0.59, + "learning_rate": 8.477786365285032e-06, + "loss": 1.3288, + "step": 5662 + }, + { + "epoch": 0.59, + "learning_rate": 8.474168872240682e-06, + "loss": 1.3274, + "step": 5663 + }, + { + "epoch": 0.59, + "learning_rate": 8.470551583618498e-06, + "loss": 1.273, + "step": 5664 + }, + { + "epoch": 0.59, + "learning_rate": 8.4669344999031e-06, + "loss": 1.3142, + "step": 5665 + }, + { + "epoch": 0.59, + "learning_rate": 8.463317621579091e-06, + "loss": 1.2912, + "step": 5666 + }, + { + "epoch": 0.59, + "learning_rate": 8.459700949131037e-06, + "loss": 1.3162, + "step": 5667 + }, + { + "epoch": 0.59, + "learning_rate": 8.456084483043479e-06, + "loss": 1.3377, + "step": 5668 + }, + { + "epoch": 0.59, + "learning_rate": 8.452468223800931e-06, + "loss": 1.3545, + "step": 5669 + }, + { + "epoch": 0.59, + "learning_rate": 8.448852171887878e-06, + "loss": 1.4052, + "step": 5670 + }, + { + "epoch": 0.59, + "learning_rate": 8.44523632778878e-06, + "loss": 1.3389, + "step": 5671 + }, + { + "epoch": 0.59, + "learning_rate": 8.441620691988063e-06, + "loss": 1.3801, + "step": 5672 + }, + { + "epoch": 0.59, + "learning_rate": 8.438005264970134e-06, + "loss": 1.2978, + "step": 5673 + }, + { + "epoch": 0.6, + "learning_rate": 8.434390047219366e-06, + "loss": 1.437, + "step": 5674 + }, + { + "epoch": 0.6, + "learning_rate": 8.430775039220103e-06, + "loss": 1.3602, + "step": 5675 + }, + { + "epoch": 0.6, + "learning_rate": 8.427160241456664e-06, + "loss": 1.4971, + "step": 5676 + }, + { + "epoch": 0.6, + "learning_rate": 8.423545654413342e-06, + "loss": 1.2765, + "step": 5677 + }, + { + "epoch": 0.6, + "learning_rate": 8.419931278574397e-06, + "loss": 1.4346, + "step": 5678 + }, + { + "epoch": 0.6, + "learning_rate": 8.416317114424059e-06, + "loss": 1.366, + "step": 5679 + }, + { + "epoch": 0.6, + "learning_rate": 8.412703162446536e-06, + "loss": 1.3776, + "step": 5680 + }, + { + "epoch": 0.6, + "learning_rate": 8.409089423126009e-06, + "loss": 1.2516, + "step": 5681 + }, + { + "epoch": 0.6, + "learning_rate": 8.405475896946621e-06, + "loss": 1.4257, + "step": 5682 + }, + { + "epoch": 0.6, + "learning_rate": 8.401862584392492e-06, + "loss": 1.3523, + "step": 5683 + }, + { + "epoch": 0.6, + "learning_rate": 8.398249485947712e-06, + "loss": 1.3791, + "step": 5684 + }, + { + "epoch": 0.6, + "learning_rate": 8.394636602096348e-06, + "loss": 1.3574, + "step": 5685 + }, + { + "epoch": 0.6, + "learning_rate": 8.39102393332243e-06, + "loss": 1.4748, + "step": 5686 + }, + { + "epoch": 0.6, + "learning_rate": 8.387411480109967e-06, + "loss": 1.3693, + "step": 5687 + }, + { + "epoch": 0.6, + "learning_rate": 8.383799242942925e-06, + "loss": 1.3643, + "step": 5688 + }, + { + "epoch": 0.6, + "learning_rate": 8.38018722230526e-06, + "loss": 1.3446, + "step": 5689 + }, + { + "epoch": 0.6, + "learning_rate": 8.37657541868089e-06, + "loss": 1.3552, + "step": 5690 + }, + { + "epoch": 0.6, + "learning_rate": 8.372963832553698e-06, + "loss": 1.3636, + "step": 5691 + }, + { + "epoch": 0.6, + "learning_rate": 8.36935246440755e-06, + "loss": 1.3398, + "step": 5692 + }, + { + "epoch": 0.6, + "learning_rate": 8.365741314726273e-06, + "loss": 1.3336, + "step": 5693 + }, + { + "epoch": 0.6, + "learning_rate": 8.362130383993667e-06, + "loss": 1.3023, + "step": 5694 + }, + { + "epoch": 0.6, + "learning_rate": 8.358519672693506e-06, + "loss": 1.3591, + "step": 5695 + }, + { + "epoch": 0.6, + "learning_rate": 8.354909181309533e-06, + "loss": 1.3113, + "step": 5696 + }, + { + "epoch": 0.6, + "learning_rate": 8.351298910325462e-06, + "loss": 1.3747, + "step": 5697 + }, + { + "epoch": 0.6, + "learning_rate": 8.347688860224976e-06, + "loss": 1.3555, + "step": 5698 + }, + { + "epoch": 0.6, + "learning_rate": 8.344079031491722e-06, + "loss": 1.2947, + "step": 5699 + }, + { + "epoch": 0.6, + "learning_rate": 8.340469424609337e-06, + "loss": 1.4099, + "step": 5700 + }, + { + "epoch": 0.6, + "learning_rate": 8.336860040061404e-06, + "loss": 1.3263, + "step": 5701 + }, + { + "epoch": 0.6, + "learning_rate": 8.333250878331498e-06, + "loss": 1.372, + "step": 5702 + }, + { + "epoch": 0.6, + "learning_rate": 8.329641939903142e-06, + "loss": 1.3523, + "step": 5703 + }, + { + "epoch": 0.6, + "learning_rate": 8.32603322525985e-06, + "loss": 1.3451, + "step": 5704 + }, + { + "epoch": 0.6, + "learning_rate": 8.322424734885098e-06, + "loss": 1.3296, + "step": 5705 + }, + { + "epoch": 0.6, + "learning_rate": 8.318816469262325e-06, + "loss": 1.449, + "step": 5706 + }, + { + "epoch": 0.6, + "learning_rate": 8.315208428874946e-06, + "loss": 1.3611, + "step": 5707 + }, + { + "epoch": 0.6, + "learning_rate": 8.311600614206352e-06, + "loss": 1.3849, + "step": 5708 + }, + { + "epoch": 0.6, + "learning_rate": 8.307993025739893e-06, + "loss": 1.3968, + "step": 5709 + }, + { + "epoch": 0.6, + "learning_rate": 8.304385663958895e-06, + "loss": 1.4428, + "step": 5710 + }, + { + "epoch": 0.6, + "learning_rate": 8.300778529346647e-06, + "loss": 1.3095, + "step": 5711 + }, + { + "epoch": 0.6, + "learning_rate": 8.297171622386418e-06, + "loss": 1.3135, + "step": 5712 + }, + { + "epoch": 0.6, + "learning_rate": 8.293564943561438e-06, + "loss": 1.3069, + "step": 5713 + }, + { + "epoch": 0.6, + "learning_rate": 8.28995849335491e-06, + "loss": 1.3736, + "step": 5714 + }, + { + "epoch": 0.6, + "learning_rate": 8.286352272250007e-06, + "loss": 1.343, + "step": 5715 + }, + { + "epoch": 0.6, + "learning_rate": 8.28274628072987e-06, + "loss": 1.2929, + "step": 5716 + }, + { + "epoch": 0.6, + "learning_rate": 8.279140519277607e-06, + "loss": 1.3356, + "step": 5717 + }, + { + "epoch": 0.6, + "learning_rate": 8.275534988376295e-06, + "loss": 1.2683, + "step": 5718 + }, + { + "epoch": 0.6, + "learning_rate": 8.27192968850899e-06, + "loss": 1.3738, + "step": 5719 + }, + { + "epoch": 0.6, + "learning_rate": 8.268324620158704e-06, + "loss": 1.3369, + "step": 5720 + }, + { + "epoch": 0.6, + "learning_rate": 8.264719783808425e-06, + "loss": 1.3684, + "step": 5721 + }, + { + "epoch": 0.6, + "learning_rate": 8.261115179941108e-06, + "loss": 1.4081, + "step": 5722 + }, + { + "epoch": 0.6, + "learning_rate": 8.257510809039678e-06, + "loss": 1.2504, + "step": 5723 + }, + { + "epoch": 0.6, + "learning_rate": 8.253906671587029e-06, + "loss": 1.417, + "step": 5724 + }, + { + "epoch": 0.6, + "learning_rate": 8.25030276806602e-06, + "loss": 1.3631, + "step": 5725 + }, + { + "epoch": 0.6, + "learning_rate": 8.246699098959483e-06, + "loss": 1.499, + "step": 5726 + }, + { + "epoch": 0.6, + "learning_rate": 8.243095664750217e-06, + "loss": 1.3656, + "step": 5727 + }, + { + "epoch": 0.6, + "learning_rate": 8.239492465920992e-06, + "loss": 1.3563, + "step": 5728 + }, + { + "epoch": 0.6, + "learning_rate": 8.23588950295454e-06, + "loss": 1.3554, + "step": 5729 + }, + { + "epoch": 0.6, + "learning_rate": 8.232286776333566e-06, + "loss": 1.2705, + "step": 5730 + }, + { + "epoch": 0.6, + "learning_rate": 8.228684286540747e-06, + "loss": 1.3792, + "step": 5731 + }, + { + "epoch": 0.6, + "learning_rate": 8.22508203405872e-06, + "loss": 1.3301, + "step": 5732 + }, + { + "epoch": 0.6, + "learning_rate": 8.221480019370095e-06, + "loss": 1.36, + "step": 5733 + }, + { + "epoch": 0.6, + "learning_rate": 8.217878242957448e-06, + "loss": 1.4406, + "step": 5734 + }, + { + "epoch": 0.6, + "learning_rate": 8.214276705303328e-06, + "loss": 1.2886, + "step": 5735 + }, + { + "epoch": 0.6, + "learning_rate": 8.210675406890248e-06, + "loss": 1.3072, + "step": 5736 + }, + { + "epoch": 0.6, + "learning_rate": 8.207074348200686e-06, + "loss": 1.3734, + "step": 5737 + }, + { + "epoch": 0.6, + "learning_rate": 8.203473529717095e-06, + "loss": 1.3893, + "step": 5738 + }, + { + "epoch": 0.6, + "learning_rate": 8.199872951921892e-06, + "loss": 1.3427, + "step": 5739 + }, + { + "epoch": 0.6, + "learning_rate": 8.196272615297459e-06, + "loss": 1.3125, + "step": 5740 + }, + { + "epoch": 0.6, + "learning_rate": 8.19267252032615e-06, + "loss": 1.3079, + "step": 5741 + }, + { + "epoch": 0.6, + "learning_rate": 8.189072667490285e-06, + "loss": 1.2971, + "step": 5742 + }, + { + "epoch": 0.6, + "learning_rate": 8.185473057272154e-06, + "loss": 1.3003, + "step": 5743 + }, + { + "epoch": 0.6, + "learning_rate": 8.18187369015401e-06, + "loss": 1.3002, + "step": 5744 + }, + { + "epoch": 0.6, + "learning_rate": 8.178274566618075e-06, + "loss": 1.2852, + "step": 5745 + }, + { + "epoch": 0.6, + "learning_rate": 8.174675687146542e-06, + "loss": 1.2807, + "step": 5746 + }, + { + "epoch": 0.6, + "learning_rate": 8.171077052221567e-06, + "loss": 1.2983, + "step": 5747 + }, + { + "epoch": 0.6, + "learning_rate": 8.167478662325274e-06, + "loss": 1.3002, + "step": 5748 + }, + { + "epoch": 0.6, + "learning_rate": 8.163880517939753e-06, + "loss": 1.2575, + "step": 5749 + }, + { + "epoch": 0.6, + "learning_rate": 8.160282619547068e-06, + "loss": 1.2627, + "step": 5750 + }, + { + "epoch": 0.6, + "learning_rate": 8.156684967629242e-06, + "loss": 1.2549, + "step": 5751 + }, + { + "epoch": 0.6, + "learning_rate": 8.153087562668265e-06, + "loss": 1.2595, + "step": 5752 + }, + { + "epoch": 0.6, + "learning_rate": 8.1494904051461e-06, + "loss": 1.2788, + "step": 5753 + }, + { + "epoch": 0.6, + "learning_rate": 8.145893495544676e-06, + "loss": 1.3028, + "step": 5754 + }, + { + "epoch": 0.6, + "learning_rate": 8.142296834345883e-06, + "loss": 1.3019, + "step": 5755 + }, + { + "epoch": 0.6, + "learning_rate": 8.138700422031583e-06, + "loss": 1.2998, + "step": 5756 + }, + { + "epoch": 0.6, + "learning_rate": 8.135104259083598e-06, + "loss": 1.3298, + "step": 5757 + }, + { + "epoch": 0.6, + "learning_rate": 8.13150834598373e-06, + "loss": 1.2681, + "step": 5758 + }, + { + "epoch": 0.6, + "learning_rate": 8.127912683213733e-06, + "loss": 1.2987, + "step": 5759 + }, + { + "epoch": 0.6, + "learning_rate": 8.124317271255331e-06, + "loss": 1.3181, + "step": 5760 + }, + { + "epoch": 0.6, + "learning_rate": 8.120722110590224e-06, + "loss": 1.423, + "step": 5761 + }, + { + "epoch": 0.6, + "learning_rate": 8.117127201700067e-06, + "loss": 1.5029, + "step": 5762 + }, + { + "epoch": 0.6, + "learning_rate": 8.113532545066488e-06, + "loss": 1.3016, + "step": 5763 + }, + { + "epoch": 0.6, + "learning_rate": 8.109938141171074e-06, + "loss": 1.3906, + "step": 5764 + }, + { + "epoch": 0.6, + "learning_rate": 8.106343990495387e-06, + "loss": 1.3363, + "step": 5765 + }, + { + "epoch": 0.6, + "learning_rate": 8.10275009352095e-06, + "loss": 1.314, + "step": 5766 + }, + { + "epoch": 0.6, + "learning_rate": 8.09915645072925e-06, + "loss": 1.3484, + "step": 5767 + }, + { + "epoch": 0.6, + "learning_rate": 8.095563062601745e-06, + "loss": 1.3757, + "step": 5768 + }, + { + "epoch": 0.6, + "learning_rate": 8.091969929619859e-06, + "loss": 1.3068, + "step": 5769 + }, + { + "epoch": 0.61, + "learning_rate": 8.088377052264976e-06, + "loss": 1.3486, + "step": 5770 + }, + { + "epoch": 0.61, + "learning_rate": 8.08478443101845e-06, + "loss": 1.244, + "step": 5771 + }, + { + "epoch": 0.61, + "eval_loss": 1.4178493022918701, + "eval_runtime": 77.6086, + "eval_samples_per_second": 1.662, + "eval_steps_per_second": 0.116, + "step": 5771 + }, + { + "epoch": 0.61, + "learning_rate": 8.0811920663616e-06, + "loss": 1.3325, + "step": 5772 + }, + { + "epoch": 0.61, + "learning_rate": 8.077599958775713e-06, + "loss": 1.336, + "step": 5773 + }, + { + "epoch": 0.61, + "learning_rate": 8.074008108742037e-06, + "loss": 1.3167, + "step": 5774 + }, + { + "epoch": 0.61, + "learning_rate": 8.070416516741786e-06, + "loss": 1.3166, + "step": 5775 + }, + { + "epoch": 0.61, + "learning_rate": 8.066825183256141e-06, + "loss": 1.3377, + "step": 5776 + }, + { + "epoch": 0.61, + "learning_rate": 8.063234108766253e-06, + "loss": 1.3704, + "step": 5777 + }, + { + "epoch": 0.61, + "learning_rate": 8.059643293753233e-06, + "loss": 1.3596, + "step": 5778 + }, + { + "epoch": 0.61, + "learning_rate": 8.056052738698153e-06, + "loss": 1.4477, + "step": 5779 + }, + { + "epoch": 0.61, + "learning_rate": 8.052462444082055e-06, + "loss": 1.338, + "step": 5780 + }, + { + "epoch": 0.61, + "learning_rate": 8.048872410385952e-06, + "loss": 1.2714, + "step": 5781 + }, + { + "epoch": 0.61, + "learning_rate": 8.045282638090815e-06, + "loss": 0.9642, + "step": 5782 + }, + { + "epoch": 0.61, + "learning_rate": 8.041693127677576e-06, + "loss": 0.8702, + "step": 5783 + }, + { + "epoch": 0.61, + "learning_rate": 8.038103879627144e-06, + "loss": 0.8986, + "step": 5784 + }, + { + "epoch": 0.61, + "learning_rate": 8.034514894420382e-06, + "loss": 0.804, + "step": 5785 + }, + { + "epoch": 0.61, + "learning_rate": 8.030926172538122e-06, + "loss": 0.7958, + "step": 5786 + }, + { + "epoch": 0.61, + "learning_rate": 8.02733771446116e-06, + "loss": 0.7608, + "step": 5787 + }, + { + "epoch": 0.61, + "learning_rate": 8.023749520670261e-06, + "loss": 0.7792, + "step": 5788 + }, + { + "epoch": 0.61, + "learning_rate": 8.020161591646147e-06, + "loss": 0.7293, + "step": 5789 + }, + { + "epoch": 0.61, + "learning_rate": 8.016573927869511e-06, + "loss": 1.1287, + "step": 5790 + }, + { + "epoch": 0.61, + "learning_rate": 8.012986529821004e-06, + "loss": 1.3344, + "step": 5791 + }, + { + "epoch": 0.61, + "learning_rate": 8.009399397981248e-06, + "loss": 1.4415, + "step": 5792 + }, + { + "epoch": 0.61, + "learning_rate": 8.005812532830826e-06, + "loss": 1.4265, + "step": 5793 + }, + { + "epoch": 0.61, + "learning_rate": 8.002225934850287e-06, + "loss": 1.3429, + "step": 5794 + }, + { + "epoch": 0.61, + "learning_rate": 7.998639604520137e-06, + "loss": 1.3653, + "step": 5795 + }, + { + "epoch": 0.61, + "learning_rate": 7.995053542320861e-06, + "loss": 1.486, + "step": 5796 + }, + { + "epoch": 0.61, + "learning_rate": 7.991467748732894e-06, + "loss": 1.3389, + "step": 5797 + }, + { + "epoch": 0.61, + "learning_rate": 7.98788222423664e-06, + "loss": 1.3206, + "step": 5798 + }, + { + "epoch": 0.61, + "learning_rate": 7.984296969312468e-06, + "loss": 1.3121, + "step": 5799 + }, + { + "epoch": 0.61, + "learning_rate": 7.980711984440712e-06, + "loss": 1.3512, + "step": 5800 + }, + { + "epoch": 0.61, + "learning_rate": 7.977127270101665e-06, + "loss": 1.3291, + "step": 5801 + }, + { + "epoch": 0.61, + "learning_rate": 7.97354282677559e-06, + "loss": 1.3948, + "step": 5802 + }, + { + "epoch": 0.61, + "learning_rate": 7.969958654942704e-06, + "loss": 1.3076, + "step": 5803 + }, + { + "epoch": 0.61, + "learning_rate": 7.966374755083202e-06, + "loss": 1.3838, + "step": 5804 + }, + { + "epoch": 0.61, + "learning_rate": 7.962791127677228e-06, + "loss": 1.4205, + "step": 5805 + }, + { + "epoch": 0.61, + "learning_rate": 7.959207773204899e-06, + "loss": 1.3635, + "step": 5806 + }, + { + "epoch": 0.61, + "learning_rate": 7.955624692146293e-06, + "loss": 1.3299, + "step": 5807 + }, + { + "epoch": 0.61, + "learning_rate": 7.95204188498145e-06, + "loss": 1.4435, + "step": 5808 + }, + { + "epoch": 0.61, + "learning_rate": 7.948459352190372e-06, + "loss": 1.4335, + "step": 5809 + }, + { + "epoch": 0.61, + "learning_rate": 7.944877094253027e-06, + "loss": 1.3391, + "step": 5810 + }, + { + "epoch": 0.61, + "learning_rate": 7.94129511164935e-06, + "loss": 1.2852, + "step": 5811 + }, + { + "epoch": 0.61, + "learning_rate": 7.93771340485923e-06, + "loss": 1.3174, + "step": 5812 + }, + { + "epoch": 0.61, + "learning_rate": 7.934131974362527e-06, + "loss": 1.3415, + "step": 5813 + }, + { + "epoch": 0.61, + "learning_rate": 7.930550820639055e-06, + "loss": 1.2764, + "step": 5814 + }, + { + "epoch": 0.61, + "learning_rate": 7.926969944168603e-06, + "loss": 1.2978, + "step": 5815 + }, + { + "epoch": 0.61, + "learning_rate": 7.923389345430911e-06, + "loss": 1.3046, + "step": 5816 + }, + { + "epoch": 0.61, + "learning_rate": 7.919809024905694e-06, + "loss": 1.3484, + "step": 5817 + }, + { + "epoch": 0.61, + "learning_rate": 7.916228983072614e-06, + "loss": 1.3207, + "step": 5818 + }, + { + "epoch": 0.61, + "learning_rate": 7.912649220411312e-06, + "loss": 1.4289, + "step": 5819 + }, + { + "epoch": 0.61, + "learning_rate": 7.909069737401382e-06, + "loss": 1.4359, + "step": 5820 + }, + { + "epoch": 0.61, + "learning_rate": 7.905490534522384e-06, + "loss": 1.3316, + "step": 5821 + }, + { + "epoch": 0.61, + "learning_rate": 7.901911612253834e-06, + "loss": 1.3112, + "step": 5822 + }, + { + "epoch": 0.61, + "learning_rate": 7.898332971075221e-06, + "loss": 1.3318, + "step": 5823 + }, + { + "epoch": 0.61, + "learning_rate": 7.894754611465992e-06, + "loss": 1.4373, + "step": 5824 + }, + { + "epoch": 0.61, + "learning_rate": 7.891176533905549e-06, + "loss": 1.2938, + "step": 5825 + }, + { + "epoch": 0.61, + "learning_rate": 7.887598738873266e-06, + "loss": 1.3471, + "step": 5826 + }, + { + "epoch": 0.61, + "learning_rate": 7.884021226848478e-06, + "loss": 1.2999, + "step": 5827 + }, + { + "epoch": 0.61, + "learning_rate": 7.880443998310475e-06, + "loss": 1.35, + "step": 5828 + }, + { + "epoch": 0.61, + "learning_rate": 7.876867053738517e-06, + "loss": 1.3307, + "step": 5829 + }, + { + "epoch": 0.61, + "learning_rate": 7.87329039361182e-06, + "loss": 1.393, + "step": 5830 + }, + { + "epoch": 0.61, + "learning_rate": 7.869714018409568e-06, + "loss": 1.2933, + "step": 5831 + }, + { + "epoch": 0.61, + "learning_rate": 7.866137928610903e-06, + "loss": 1.319, + "step": 5832 + }, + { + "epoch": 0.61, + "learning_rate": 7.862562124694925e-06, + "loss": 1.3088, + "step": 5833 + }, + { + "epoch": 0.61, + "learning_rate": 7.858986607140705e-06, + "loss": 1.2941, + "step": 5834 + }, + { + "epoch": 0.61, + "learning_rate": 7.855411376427267e-06, + "loss": 1.3214, + "step": 5835 + }, + { + "epoch": 0.61, + "learning_rate": 7.851836433033602e-06, + "loss": 1.2991, + "step": 5836 + }, + { + "epoch": 0.61, + "learning_rate": 7.848261777438656e-06, + "loss": 1.3117, + "step": 5837 + }, + { + "epoch": 0.61, + "learning_rate": 7.844687410121348e-06, + "loss": 1.2905, + "step": 5838 + }, + { + "epoch": 0.61, + "learning_rate": 7.841113331560548e-06, + "loss": 1.3688, + "step": 5839 + }, + { + "epoch": 0.61, + "learning_rate": 7.837539542235091e-06, + "loss": 1.3987, + "step": 5840 + }, + { + "epoch": 0.61, + "learning_rate": 7.83396604262377e-06, + "loss": 1.2693, + "step": 5841 + }, + { + "epoch": 0.61, + "learning_rate": 7.830392833205348e-06, + "loss": 1.3205, + "step": 5842 + }, + { + "epoch": 0.61, + "learning_rate": 7.826819914458538e-06, + "loss": 1.3325, + "step": 5843 + }, + { + "epoch": 0.61, + "learning_rate": 7.823247286862024e-06, + "loss": 1.3451, + "step": 5844 + }, + { + "epoch": 0.61, + "learning_rate": 7.81967495089444e-06, + "loss": 1.3484, + "step": 5845 + }, + { + "epoch": 0.61, + "learning_rate": 7.816102907034395e-06, + "loss": 1.4949, + "step": 5846 + }, + { + "epoch": 0.61, + "learning_rate": 7.812531155760445e-06, + "loss": 1.4293, + "step": 5847 + }, + { + "epoch": 0.61, + "learning_rate": 7.808959697551113e-06, + "loss": 1.4314, + "step": 5848 + }, + { + "epoch": 0.61, + "learning_rate": 7.805388532884887e-06, + "loss": 1.3188, + "step": 5849 + }, + { + "epoch": 0.61, + "learning_rate": 7.80181766224021e-06, + "loss": 1.4396, + "step": 5850 + }, + { + "epoch": 0.61, + "learning_rate": 7.798247086095484e-06, + "loss": 1.3448, + "step": 5851 + }, + { + "epoch": 0.61, + "learning_rate": 7.794676804929075e-06, + "loss": 1.3591, + "step": 5852 + }, + { + "epoch": 0.61, + "learning_rate": 7.791106819219311e-06, + "loss": 1.3108, + "step": 5853 + }, + { + "epoch": 0.61, + "learning_rate": 7.78753712944448e-06, + "loss": 1.3773, + "step": 5854 + }, + { + "epoch": 0.61, + "learning_rate": 7.783967736082824e-06, + "loss": 1.3313, + "step": 5855 + }, + { + "epoch": 0.61, + "learning_rate": 7.780398639612551e-06, + "loss": 1.3635, + "step": 5856 + }, + { + "epoch": 0.61, + "learning_rate": 7.776829840511833e-06, + "loss": 1.3225, + "step": 5857 + }, + { + "epoch": 0.61, + "learning_rate": 7.773261339258792e-06, + "loss": 1.3142, + "step": 5858 + }, + { + "epoch": 0.61, + "learning_rate": 7.769693136331519e-06, + "loss": 1.3337, + "step": 5859 + }, + { + "epoch": 0.61, + "learning_rate": 7.766125232208057e-06, + "loss": 1.5289, + "step": 5860 + }, + { + "epoch": 0.61, + "learning_rate": 7.762557627366418e-06, + "loss": 1.573, + "step": 5861 + }, + { + "epoch": 0.61, + "learning_rate": 7.758990322284568e-06, + "loss": 1.322, + "step": 5862 + }, + { + "epoch": 0.61, + "learning_rate": 7.755423317440432e-06, + "loss": 1.3281, + "step": 5863 + }, + { + "epoch": 0.61, + "learning_rate": 7.751856613311899e-06, + "loss": 1.3405, + "step": 5864 + }, + { + "epoch": 0.62, + "learning_rate": 7.748290210376817e-06, + "loss": 1.3083, + "step": 5865 + }, + { + "epoch": 0.62, + "learning_rate": 7.744724109112991e-06, + "loss": 1.3587, + "step": 5866 + }, + { + "epoch": 0.62, + "learning_rate": 7.741158309998188e-06, + "loss": 1.3204, + "step": 5867 + }, + { + "epoch": 0.62, + "learning_rate": 7.73759281351013e-06, + "loss": 1.343, + "step": 5868 + }, + { + "epoch": 0.62, + "learning_rate": 7.734027620126507e-06, + "loss": 1.2874, + "step": 5869 + }, + { + "epoch": 0.62, + "learning_rate": 7.73046273032496e-06, + "loss": 1.3306, + "step": 5870 + }, + { + "epoch": 0.62, + "learning_rate": 7.72689814458309e-06, + "loss": 1.3958, + "step": 5871 + }, + { + "epoch": 0.62, + "learning_rate": 7.723333863378465e-06, + "loss": 1.3135, + "step": 5872 + }, + { + "epoch": 0.62, + "learning_rate": 7.719769887188608e-06, + "loss": 1.3241, + "step": 5873 + }, + { + "epoch": 0.62, + "learning_rate": 7.716206216490995e-06, + "loss": 1.3487, + "step": 5874 + }, + { + "epoch": 0.62, + "learning_rate": 7.712642851763067e-06, + "loss": 1.0263, + "step": 5875 + }, + { + "epoch": 0.62, + "learning_rate": 7.709079793482228e-06, + "loss": 1.4238, + "step": 5876 + }, + { + "epoch": 0.62, + "learning_rate": 7.705517042125833e-06, + "loss": 1.3284, + "step": 5877 + }, + { + "epoch": 0.62, + "learning_rate": 7.701954598171199e-06, + "loss": 1.2965, + "step": 5878 + }, + { + "epoch": 0.62, + "learning_rate": 7.698392462095601e-06, + "loss": 1.3578, + "step": 5879 + }, + { + "epoch": 0.62, + "learning_rate": 7.694830634376278e-06, + "loss": 1.3711, + "step": 5880 + }, + { + "epoch": 0.62, + "learning_rate": 7.69126911549042e-06, + "loss": 1.3274, + "step": 5881 + }, + { + "epoch": 0.62, + "learning_rate": 7.687707905915181e-06, + "loss": 1.4208, + "step": 5882 + }, + { + "epoch": 0.62, + "learning_rate": 7.684147006127665e-06, + "loss": 1.3478, + "step": 5883 + }, + { + "epoch": 0.62, + "learning_rate": 7.68058641660495e-06, + "loss": 1.2997, + "step": 5884 + }, + { + "epoch": 0.62, + "learning_rate": 7.67702613782406e-06, + "loss": 1.2981, + "step": 5885 + }, + { + "epoch": 0.62, + "learning_rate": 7.67346617026198e-06, + "loss": 1.3834, + "step": 5886 + }, + { + "epoch": 0.62, + "learning_rate": 7.669906514395654e-06, + "loss": 1.3585, + "step": 5887 + }, + { + "epoch": 0.62, + "learning_rate": 7.666347170701986e-06, + "loss": 1.3282, + "step": 5888 + }, + { + "epoch": 0.62, + "learning_rate": 7.662788139657838e-06, + "loss": 1.3397, + "step": 5889 + }, + { + "epoch": 0.62, + "learning_rate": 7.659229421740024e-06, + "loss": 1.3367, + "step": 5890 + }, + { + "epoch": 0.62, + "learning_rate": 7.655671017425322e-06, + "loss": 1.3497, + "step": 5891 + }, + { + "epoch": 0.62, + "learning_rate": 7.65211292719047e-06, + "loss": 1.3661, + "step": 5892 + }, + { + "epoch": 0.62, + "learning_rate": 7.64855515151216e-06, + "loss": 1.2793, + "step": 5893 + }, + { + "epoch": 0.62, + "learning_rate": 7.644997690867037e-06, + "loss": 1.3288, + "step": 5894 + }, + { + "epoch": 0.62, + "learning_rate": 7.641440545731717e-06, + "loss": 1.3877, + "step": 5895 + }, + { + "epoch": 0.62, + "learning_rate": 7.637883716582764e-06, + "loss": 1.4467, + "step": 5896 + }, + { + "epoch": 0.62, + "learning_rate": 7.634327203896698e-06, + "loss": 1.304, + "step": 5897 + }, + { + "epoch": 0.62, + "learning_rate": 7.630771008150002e-06, + "loss": 1.374, + "step": 5898 + }, + { + "epoch": 0.62, + "learning_rate": 7.627215129819118e-06, + "loss": 1.3893, + "step": 5899 + }, + { + "epoch": 0.62, + "learning_rate": 7.623659569380439e-06, + "loss": 1.325, + "step": 5900 + }, + { + "epoch": 0.62, + "learning_rate": 7.620104327310319e-06, + "loss": 1.2495, + "step": 5901 + }, + { + "epoch": 0.62, + "learning_rate": 7.616549404085068e-06, + "loss": 1.4034, + "step": 5902 + }, + { + "epoch": 0.62, + "learning_rate": 7.61299480018096e-06, + "loss": 1.2758, + "step": 5903 + }, + { + "epoch": 0.62, + "learning_rate": 7.609440516074215e-06, + "loss": 1.4203, + "step": 5904 + }, + { + "epoch": 0.62, + "learning_rate": 7.605886552241017e-06, + "loss": 1.3162, + "step": 5905 + }, + { + "epoch": 0.62, + "learning_rate": 7.602332909157505e-06, + "loss": 1.3368, + "step": 5906 + }, + { + "epoch": 0.62, + "learning_rate": 7.598779587299778e-06, + "loss": 1.314, + "step": 5907 + }, + { + "epoch": 0.62, + "learning_rate": 7.59522658714389e-06, + "loss": 1.3332, + "step": 5908 + }, + { + "epoch": 0.62, + "learning_rate": 7.5916739091658505e-06, + "loss": 1.3513, + "step": 5909 + }, + { + "epoch": 0.62, + "learning_rate": 7.5881215538416255e-06, + "loss": 1.3767, + "step": 5910 + }, + { + "epoch": 0.62, + "learning_rate": 7.5845695216471426e-06, + "loss": 1.3651, + "step": 5911 + }, + { + "epoch": 0.62, + "learning_rate": 7.581017813058283e-06, + "loss": 1.2676, + "step": 5912 + }, + { + "epoch": 0.62, + "learning_rate": 7.57746642855088e-06, + "loss": 1.3509, + "step": 5913 + }, + { + "epoch": 0.62, + "learning_rate": 7.5739153686007305e-06, + "loss": 1.2854, + "step": 5914 + }, + { + "epoch": 0.62, + "learning_rate": 7.570364633683586e-06, + "loss": 1.4041, + "step": 5915 + }, + { + "epoch": 0.62, + "learning_rate": 7.5668142242751545e-06, + "loss": 1.3218, + "step": 5916 + }, + { + "epoch": 0.62, + "learning_rate": 7.563264140851095e-06, + "loss": 1.398, + "step": 5917 + }, + { + "epoch": 0.62, + "learning_rate": 7.559714383887033e-06, + "loss": 1.3495, + "step": 5918 + }, + { + "epoch": 0.62, + "learning_rate": 7.556164953858543e-06, + "loss": 1.365, + "step": 5919 + }, + { + "epoch": 0.62, + "learning_rate": 7.552615851241157e-06, + "loss": 1.4611, + "step": 5920 + }, + { + "epoch": 0.62, + "learning_rate": 7.549067076510361e-06, + "loss": 1.4031, + "step": 5921 + }, + { + "epoch": 0.62, + "learning_rate": 7.545518630141605e-06, + "loss": 1.2745, + "step": 5922 + }, + { + "epoch": 0.62, + "learning_rate": 7.541970512610286e-06, + "loss": 1.3435, + "step": 5923 + }, + { + "epoch": 0.62, + "learning_rate": 7.538422724391761e-06, + "loss": 1.3433, + "step": 5924 + }, + { + "epoch": 0.62, + "learning_rate": 7.534875265961341e-06, + "loss": 1.3605, + "step": 5925 + }, + { + "epoch": 0.62, + "learning_rate": 7.5313281377942985e-06, + "loss": 1.3896, + "step": 5926 + }, + { + "epoch": 0.62, + "learning_rate": 7.527781340365854e-06, + "loss": 1.3922, + "step": 5927 + }, + { + "epoch": 0.62, + "learning_rate": 7.524234874151189e-06, + "loss": 1.3305, + "step": 5928 + }, + { + "epoch": 0.62, + "learning_rate": 7.520688739625436e-06, + "loss": 1.3117, + "step": 5929 + }, + { + "epoch": 0.62, + "learning_rate": 7.51714293726369e-06, + "loss": 1.3581, + "step": 5930 + }, + { + "epoch": 0.62, + "learning_rate": 7.5135974675409955e-06, + "loss": 1.3973, + "step": 5931 + }, + { + "epoch": 0.62, + "learning_rate": 7.510052330932354e-06, + "loss": 1.3499, + "step": 5932 + }, + { + "epoch": 0.62, + "learning_rate": 7.506507527912721e-06, + "loss": 1.3068, + "step": 5933 + }, + { + "epoch": 0.62, + "learning_rate": 7.502963058957014e-06, + "loss": 1.3689, + "step": 5934 + }, + { + "epoch": 0.62, + "learning_rate": 7.499418924540096e-06, + "loss": 1.3356, + "step": 5935 + }, + { + "epoch": 0.62, + "learning_rate": 7.495875125136793e-06, + "loss": 1.2593, + "step": 5936 + }, + { + "epoch": 0.62, + "learning_rate": 7.492331661221881e-06, + "loss": 1.272, + "step": 5937 + }, + { + "epoch": 0.62, + "learning_rate": 7.488788533270093e-06, + "loss": 1.3552, + "step": 5938 + }, + { + "epoch": 0.62, + "learning_rate": 7.485245741756121e-06, + "loss": 1.3425, + "step": 5939 + }, + { + "epoch": 0.62, + "learning_rate": 7.481703287154602e-06, + "loss": 1.3694, + "step": 5940 + }, + { + "epoch": 0.62, + "learning_rate": 7.478161169940139e-06, + "loss": 1.3281, + "step": 5941 + }, + { + "epoch": 0.62, + "learning_rate": 7.4746193905872825e-06, + "loss": 1.3109, + "step": 5942 + }, + { + "epoch": 0.62, + "learning_rate": 7.47107794957054e-06, + "loss": 1.5121, + "step": 5943 + }, + { + "epoch": 0.62, + "learning_rate": 7.467536847364372e-06, + "loss": 1.4472, + "step": 5944 + }, + { + "epoch": 0.62, + "learning_rate": 7.463996084443198e-06, + "loss": 1.4615, + "step": 5945 + }, + { + "epoch": 0.62, + "learning_rate": 7.460455661281389e-06, + "loss": 1.3764, + "step": 5946 + }, + { + "epoch": 0.62, + "learning_rate": 7.45691557835327e-06, + "loss": 1.3091, + "step": 5947 + }, + { + "epoch": 0.62, + "learning_rate": 7.4533758361331185e-06, + "loss": 1.1841, + "step": 5948 + }, + { + "epoch": 0.62, + "learning_rate": 7.449836435095175e-06, + "loss": 1.3345, + "step": 5949 + }, + { + "epoch": 0.62, + "learning_rate": 7.446297375713622e-06, + "loss": 1.3573, + "step": 5950 + }, + { + "epoch": 0.62, + "learning_rate": 7.442758658462608e-06, + "loss": 1.3161, + "step": 5951 + }, + { + "epoch": 0.62, + "learning_rate": 7.4392202838162245e-06, + "loss": 1.3089, + "step": 5952 + }, + { + "epoch": 0.62, + "learning_rate": 7.435682252248528e-06, + "loss": 1.3069, + "step": 5953 + }, + { + "epoch": 0.62, + "learning_rate": 7.4321445642335234e-06, + "loss": 1.2969, + "step": 5954 + }, + { + "epoch": 0.62, + "learning_rate": 7.428607220245165e-06, + "loss": 1.4706, + "step": 5955 + }, + { + "epoch": 0.62, + "learning_rate": 7.42507022075737e-06, + "loss": 1.3028, + "step": 5956 + }, + { + "epoch": 0.62, + "learning_rate": 7.421533566244006e-06, + "loss": 1.2786, + "step": 5957 + }, + { + "epoch": 0.62, + "learning_rate": 7.417997257178893e-06, + "loss": 1.3534, + "step": 5958 + }, + { + "epoch": 0.62, + "learning_rate": 7.414461294035804e-06, + "loss": 1.2829, + "step": 5959 + }, + { + "epoch": 0.62, + "learning_rate": 7.410925677288467e-06, + "loss": 1.3626, + "step": 5960 + }, + { + "epoch": 0.63, + "learning_rate": 7.407390407410566e-06, + "loss": 1.4531, + "step": 5961 + }, + { + "epoch": 0.63, + "learning_rate": 7.4038554848757375e-06, + "loss": 1.3549, + "step": 5962 + }, + { + "epoch": 0.63, + "learning_rate": 7.400320910157563e-06, + "loss": 1.3407, + "step": 5963 + }, + { + "epoch": 0.63, + "learning_rate": 7.396786683729595e-06, + "loss": 1.2736, + "step": 5964 + }, + { + "epoch": 0.63, + "learning_rate": 7.393252806065323e-06, + "loss": 1.3377, + "step": 5965 + }, + { + "epoch": 0.63, + "learning_rate": 7.389719277638196e-06, + "loss": 1.3479, + "step": 5966 + }, + { + "epoch": 0.63, + "learning_rate": 7.3861860989216175e-06, + "loss": 1.3605, + "step": 5967 + }, + { + "epoch": 0.63, + "learning_rate": 7.382653270388942e-06, + "loss": 1.3175, + "step": 5968 + }, + { + "epoch": 0.63, + "learning_rate": 7.379120792513477e-06, + "loss": 1.3072, + "step": 5969 + }, + { + "epoch": 0.63, + "learning_rate": 7.375588665768485e-06, + "loss": 1.3224, + "step": 5970 + }, + { + "epoch": 0.63, + "eval_loss": 1.4110088348388672, + "eval_runtime": 77.5326, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 5970 + }, + { + "epoch": 0.63, + "learning_rate": 7.37205689062718e-06, + "loss": 1.3491, + "step": 5971 + }, + { + "epoch": 0.63, + "learning_rate": 7.368525467562728e-06, + "loss": 1.3289, + "step": 5972 + }, + { + "epoch": 0.63, + "learning_rate": 7.364994397048251e-06, + "loss": 1.3362, + "step": 5973 + }, + { + "epoch": 0.63, + "learning_rate": 7.36146367955682e-06, + "loss": 1.3754, + "step": 5974 + }, + { + "epoch": 0.63, + "learning_rate": 7.3579333155614585e-06, + "loss": 1.3159, + "step": 5975 + }, + { + "epoch": 0.63, + "learning_rate": 7.354403305535149e-06, + "loss": 1.4366, + "step": 5976 + }, + { + "epoch": 0.63, + "learning_rate": 7.350873649950822e-06, + "loss": 1.3243, + "step": 5977 + }, + { + "epoch": 0.63, + "learning_rate": 7.347344349281358e-06, + "loss": 1.2911, + "step": 5978 + }, + { + "epoch": 0.63, + "learning_rate": 7.34381540399959e-06, + "loss": 1.338, + "step": 5979 + }, + { + "epoch": 0.63, + "learning_rate": 7.340286814578312e-06, + "loss": 1.3241, + "step": 5980 + }, + { + "epoch": 0.63, + "learning_rate": 7.336758581490263e-06, + "loss": 1.3427, + "step": 5981 + }, + { + "epoch": 0.63, + "learning_rate": 7.333230705208134e-06, + "loss": 1.3328, + "step": 5982 + }, + { + "epoch": 0.63, + "learning_rate": 7.3297031862045676e-06, + "loss": 1.2857, + "step": 5983 + }, + { + "epoch": 0.63, + "learning_rate": 7.3261760249521655e-06, + "loss": 1.9065, + "step": 5984 + }, + { + "epoch": 0.63, + "learning_rate": 7.322649221923473e-06, + "loss": 1.3797, + "step": 5985 + }, + { + "epoch": 0.63, + "learning_rate": 7.3191227775909925e-06, + "loss": 1.2343, + "step": 5986 + }, + { + "epoch": 0.63, + "learning_rate": 7.315596692427178e-06, + "loss": 1.3479, + "step": 5987 + }, + { + "epoch": 0.63, + "learning_rate": 7.312070966904432e-06, + "loss": 1.3226, + "step": 5988 + }, + { + "epoch": 0.63, + "learning_rate": 7.308545601495114e-06, + "loss": 1.3329, + "step": 5989 + }, + { + "epoch": 0.63, + "learning_rate": 7.305020596671528e-06, + "loss": 1.3285, + "step": 5990 + }, + { + "epoch": 0.63, + "learning_rate": 7.301495952905939e-06, + "loss": 1.3635, + "step": 5991 + }, + { + "epoch": 0.63, + "learning_rate": 7.297971670670556e-06, + "loss": 1.3343, + "step": 5992 + }, + { + "epoch": 0.63, + "learning_rate": 7.294447750437543e-06, + "loss": 1.3943, + "step": 5993 + }, + { + "epoch": 0.63, + "learning_rate": 7.290924192679014e-06, + "loss": 1.4601, + "step": 5994 + }, + { + "epoch": 0.63, + "learning_rate": 7.287400997867036e-06, + "loss": 1.3813, + "step": 5995 + }, + { + "epoch": 0.63, + "learning_rate": 7.2838781664736266e-06, + "loss": 1.3505, + "step": 5996 + }, + { + "epoch": 0.63, + "learning_rate": 7.2803556989707555e-06, + "loss": 1.3062, + "step": 5997 + }, + { + "epoch": 0.63, + "learning_rate": 7.276833595830338e-06, + "loss": 1.4504, + "step": 5998 + }, + { + "epoch": 0.63, + "learning_rate": 7.273311857524252e-06, + "loss": 1.4935, + "step": 5999 + }, + { + "epoch": 0.63, + "learning_rate": 7.269790484524317e-06, + "loss": 1.296, + "step": 6000 + }, + { + "epoch": 0.63, + "learning_rate": 7.266269477302308e-06, + "loss": 1.3469, + "step": 6001 + }, + { + "epoch": 0.63, + "learning_rate": 7.262748836329944e-06, + "loss": 1.3586, + "step": 6002 + }, + { + "epoch": 0.63, + "learning_rate": 7.259228562078908e-06, + "loss": 1.3643, + "step": 6003 + }, + { + "epoch": 0.63, + "learning_rate": 7.255708655020821e-06, + "loss": 1.3096, + "step": 6004 + }, + { + "epoch": 0.63, + "learning_rate": 7.252189115627264e-06, + "loss": 1.3163, + "step": 6005 + }, + { + "epoch": 0.63, + "learning_rate": 7.2486699443697595e-06, + "loss": 1.3526, + "step": 6006 + }, + { + "epoch": 0.63, + "learning_rate": 7.245151141719793e-06, + "loss": 1.401, + "step": 6007 + }, + { + "epoch": 0.63, + "learning_rate": 7.241632708148788e-06, + "loss": 1.2651, + "step": 6008 + }, + { + "epoch": 0.63, + "learning_rate": 7.238114644128124e-06, + "loss": 1.348, + "step": 6009 + }, + { + "epoch": 0.63, + "learning_rate": 7.234596950129137e-06, + "loss": 1.6934, + "step": 6010 + }, + { + "epoch": 0.63, + "learning_rate": 7.231079626623103e-06, + "loss": 1.3382, + "step": 6011 + }, + { + "epoch": 0.63, + "learning_rate": 7.227562674081254e-06, + "loss": 1.2925, + "step": 6012 + }, + { + "epoch": 0.63, + "learning_rate": 7.22404609297477e-06, + "loss": 1.3365, + "step": 6013 + }, + { + "epoch": 0.63, + "learning_rate": 7.220529883774785e-06, + "loss": 1.3169, + "step": 6014 + }, + { + "epoch": 0.63, + "learning_rate": 7.217014046952379e-06, + "loss": 1.319, + "step": 6015 + }, + { + "epoch": 0.63, + "learning_rate": 7.2134985829785846e-06, + "loss": 1.4049, + "step": 6016 + }, + { + "epoch": 0.63, + "learning_rate": 7.209983492324382e-06, + "loss": 1.2947, + "step": 6017 + }, + { + "epoch": 0.63, + "learning_rate": 7.206468775460704e-06, + "loss": 1.2854, + "step": 6018 + }, + { + "epoch": 0.63, + "learning_rate": 7.202954432858436e-06, + "loss": 1.3381, + "step": 6019 + }, + { + "epoch": 0.63, + "learning_rate": 7.199440464988403e-06, + "loss": 1.3912, + "step": 6020 + }, + { + "epoch": 0.63, + "learning_rate": 7.195926872321391e-06, + "loss": 1.384, + "step": 6021 + }, + { + "epoch": 0.63, + "learning_rate": 7.192413655328129e-06, + "loss": 1.2909, + "step": 6022 + }, + { + "epoch": 0.63, + "learning_rate": 7.188900814479299e-06, + "loss": 1.2951, + "step": 6023 + }, + { + "epoch": 0.63, + "learning_rate": 7.185388350245532e-06, + "loss": 1.2655, + "step": 6024 + }, + { + "epoch": 0.63, + "learning_rate": 7.1818762630974035e-06, + "loss": 1.3288, + "step": 6025 + }, + { + "epoch": 0.63, + "learning_rate": 7.17836455350545e-06, + "loss": 1.2873, + "step": 6026 + }, + { + "epoch": 0.63, + "learning_rate": 7.174853221940146e-06, + "loss": 1.3027, + "step": 6027 + }, + { + "epoch": 0.63, + "learning_rate": 7.17134226887192e-06, + "loss": 1.3273, + "step": 6028 + }, + { + "epoch": 0.63, + "learning_rate": 7.167831694771149e-06, + "loss": 1.3096, + "step": 6029 + }, + { + "epoch": 0.63, + "learning_rate": 7.1643215001081625e-06, + "loss": 1.2904, + "step": 6030 + }, + { + "epoch": 0.63, + "learning_rate": 7.160811685353234e-06, + "loss": 1.2977, + "step": 6031 + }, + { + "epoch": 0.63, + "learning_rate": 7.157302250976588e-06, + "loss": 1.3281, + "step": 6032 + }, + { + "epoch": 0.63, + "learning_rate": 7.1537931974483996e-06, + "loss": 1.3831, + "step": 6033 + }, + { + "epoch": 0.63, + "learning_rate": 7.150284525238794e-06, + "loss": 1.3173, + "step": 6034 + }, + { + "epoch": 0.63, + "learning_rate": 7.146776234817841e-06, + "loss": 1.4148, + "step": 6035 + }, + { + "epoch": 0.63, + "learning_rate": 7.143268326655557e-06, + "loss": 1.3381, + "step": 6036 + }, + { + "epoch": 0.63, + "learning_rate": 7.13976080122192e-06, + "loss": 1.3221, + "step": 6037 + }, + { + "epoch": 0.63, + "learning_rate": 7.136253658986843e-06, + "loss": 1.4373, + "step": 6038 + }, + { + "epoch": 0.63, + "learning_rate": 7.132746900420195e-06, + "loss": 1.3758, + "step": 6039 + }, + { + "epoch": 0.63, + "learning_rate": 7.129240525991788e-06, + "loss": 1.3964, + "step": 6040 + }, + { + "epoch": 0.63, + "learning_rate": 7.125734536171391e-06, + "loss": 1.3136, + "step": 6041 + }, + { + "epoch": 0.63, + "learning_rate": 7.122228931428715e-06, + "loss": 1.2195, + "step": 6042 + }, + { + "epoch": 0.63, + "learning_rate": 7.11872371223342e-06, + "loss": 1.3842, + "step": 6043 + }, + { + "epoch": 0.63, + "learning_rate": 7.115218879055113e-06, + "loss": 1.3369, + "step": 6044 + }, + { + "epoch": 0.63, + "learning_rate": 7.111714432363356e-06, + "loss": 1.2704, + "step": 6045 + }, + { + "epoch": 0.63, + "learning_rate": 7.108210372627653e-06, + "loss": 1.307, + "step": 6046 + }, + { + "epoch": 0.63, + "learning_rate": 7.104706700317459e-06, + "loss": 1.3024, + "step": 6047 + }, + { + "epoch": 0.63, + "learning_rate": 7.1012034159021715e-06, + "loss": 1.4157, + "step": 6048 + }, + { + "epoch": 0.63, + "learning_rate": 7.0977005198511475e-06, + "loss": 1.2314, + "step": 6049 + }, + { + "epoch": 0.63, + "learning_rate": 7.09419801263368e-06, + "loss": 1.4304, + "step": 6050 + }, + { + "epoch": 0.63, + "learning_rate": 7.090695894719019e-06, + "loss": 1.3085, + "step": 6051 + }, + { + "epoch": 0.63, + "learning_rate": 7.0871941665763525e-06, + "loss": 1.367, + "step": 6052 + }, + { + "epoch": 0.63, + "learning_rate": 7.083692828674827e-06, + "loss": 1.2913, + "step": 6053 + }, + { + "epoch": 0.63, + "learning_rate": 7.080191881483531e-06, + "loss": 1.3751, + "step": 6054 + }, + { + "epoch": 0.63, + "learning_rate": 7.0766913254714985e-06, + "loss": 1.3178, + "step": 6055 + }, + { + "epoch": 0.64, + "learning_rate": 7.07319116110772e-06, + "loss": 1.3182, + "step": 6056 + }, + { + "epoch": 0.64, + "learning_rate": 7.069691388861122e-06, + "loss": 1.373, + "step": 6057 + }, + { + "epoch": 0.64, + "learning_rate": 7.066192009200588e-06, + "loss": 1.3235, + "step": 6058 + }, + { + "epoch": 0.64, + "learning_rate": 7.0626930225949395e-06, + "loss": 1.3765, + "step": 6059 + }, + { + "epoch": 0.64, + "learning_rate": 7.0591944295129565e-06, + "loss": 1.4408, + "step": 6060 + }, + { + "epoch": 0.64, + "learning_rate": 7.055696230423359e-06, + "loss": 1.3271, + "step": 6061 + }, + { + "epoch": 0.64, + "learning_rate": 7.052198425794814e-06, + "loss": 1.2194, + "step": 6062 + }, + { + "epoch": 0.64, + "learning_rate": 7.048701016095938e-06, + "loss": 1.3707, + "step": 6063 + }, + { + "epoch": 0.64, + "learning_rate": 7.045204001795296e-06, + "loss": 1.3878, + "step": 6064 + }, + { + "epoch": 0.64, + "learning_rate": 7.041707383361396e-06, + "loss": 1.3674, + "step": 6065 + }, + { + "epoch": 0.64, + "learning_rate": 7.038211161262697e-06, + "loss": 1.4525, + "step": 6066 + }, + { + "epoch": 0.64, + "learning_rate": 7.034715335967599e-06, + "loss": 1.3801, + "step": 6067 + }, + { + "epoch": 0.64, + "learning_rate": 7.031219907944458e-06, + "loss": 1.4855, + "step": 6068 + }, + { + "epoch": 0.64, + "learning_rate": 7.027724877661568e-06, + "loss": 1.3659, + "step": 6069 + }, + { + "epoch": 0.64, + "learning_rate": 7.024230245587176e-06, + "loss": 1.3649, + "step": 6070 + }, + { + "epoch": 0.64, + "learning_rate": 7.020736012189467e-06, + "loss": 1.2629, + "step": 6071 + }, + { + "epoch": 0.64, + "learning_rate": 7.017242177936586e-06, + "loss": 1.2474, + "step": 6072 + }, + { + "epoch": 0.64, + "learning_rate": 7.013748743296614e-06, + "loss": 1.45, + "step": 6073 + }, + { + "epoch": 0.64, + "learning_rate": 7.010255708737581e-06, + "loss": 1.3624, + "step": 6074 + }, + { + "epoch": 0.64, + "learning_rate": 7.006763074727461e-06, + "loss": 0.9335, + "step": 6075 + }, + { + "epoch": 0.64, + "learning_rate": 7.0032708417341835e-06, + "loss": 0.6376, + "step": 6076 + }, + { + "epoch": 0.64, + "learning_rate": 6.999779010225613e-06, + "loss": 0.7882, + "step": 6077 + }, + { + "epoch": 0.64, + "learning_rate": 6.996287580669567e-06, + "loss": 1.3001, + "step": 6078 + }, + { + "epoch": 0.64, + "learning_rate": 6.9927965535338085e-06, + "loss": 1.323, + "step": 6079 + }, + { + "epoch": 0.64, + "learning_rate": 6.989305929286043e-06, + "loss": 1.3478, + "step": 6080 + }, + { + "epoch": 0.64, + "learning_rate": 6.985815708393928e-06, + "loss": 1.319, + "step": 6081 + }, + { + "epoch": 0.64, + "learning_rate": 6.9823258913250566e-06, + "loss": 1.3458, + "step": 6082 + }, + { + "epoch": 0.64, + "learning_rate": 6.978836478546985e-06, + "loss": 1.2481, + "step": 6083 + }, + { + "epoch": 0.64, + "learning_rate": 6.975347470527195e-06, + "loss": 1.4051, + "step": 6084 + }, + { + "epoch": 0.64, + "learning_rate": 6.97185886773313e-06, + "loss": 1.3705, + "step": 6085 + }, + { + "epoch": 0.64, + "learning_rate": 6.9683706706321676e-06, + "loss": 1.3415, + "step": 6086 + }, + { + "epoch": 0.64, + "learning_rate": 6.964882879691643e-06, + "loss": 1.3462, + "step": 6087 + }, + { + "epoch": 0.64, + "learning_rate": 6.961395495378829e-06, + "loss": 1.2974, + "step": 6088 + }, + { + "epoch": 0.64, + "learning_rate": 6.957908518160943e-06, + "loss": 1.3353, + "step": 6089 + }, + { + "epoch": 0.64, + "learning_rate": 6.95442194850515e-06, + "loss": 1.3073, + "step": 6090 + }, + { + "epoch": 0.64, + "learning_rate": 6.9509357868785636e-06, + "loss": 1.352, + "step": 6091 + }, + { + "epoch": 0.64, + "learning_rate": 6.9474500337482396e-06, + "loss": 1.2771, + "step": 6092 + }, + { + "epoch": 0.64, + "learning_rate": 6.943964689581177e-06, + "loss": 1.2925, + "step": 6093 + }, + { + "epoch": 0.64, + "learning_rate": 6.940479754844322e-06, + "loss": 1.2967, + "step": 6094 + }, + { + "epoch": 0.64, + "learning_rate": 6.93699523000457e-06, + "loss": 1.5839, + "step": 6095 + }, + { + "epoch": 0.64, + "learning_rate": 6.933511115528757e-06, + "loss": 1.3051, + "step": 6096 + }, + { + "epoch": 0.64, + "learning_rate": 6.930027411883664e-06, + "loss": 1.5344, + "step": 6097 + }, + { + "epoch": 0.64, + "learning_rate": 6.926544119536014e-06, + "loss": 1.3938, + "step": 6098 + }, + { + "epoch": 0.64, + "learning_rate": 6.923061238952484e-06, + "loss": 1.3504, + "step": 6099 + }, + { + "epoch": 0.64, + "learning_rate": 6.919578770599689e-06, + "loss": 1.3618, + "step": 6100 + }, + { + "epoch": 0.64, + "learning_rate": 6.916096714944187e-06, + "loss": 1.3811, + "step": 6101 + }, + { + "epoch": 0.64, + "learning_rate": 6.912615072452491e-06, + "loss": 1.2673, + "step": 6102 + }, + { + "epoch": 0.64, + "learning_rate": 6.909133843591046e-06, + "loss": 1.3661, + "step": 6103 + }, + { + "epoch": 0.64, + "learning_rate": 6.905653028826249e-06, + "loss": 1.3811, + "step": 6104 + }, + { + "epoch": 0.64, + "learning_rate": 6.902172628624437e-06, + "loss": 1.3399, + "step": 6105 + }, + { + "epoch": 0.64, + "learning_rate": 6.8986926434519e-06, + "loss": 1.281, + "step": 6106 + }, + { + "epoch": 0.64, + "learning_rate": 6.895213073774862e-06, + "loss": 1.3053, + "step": 6107 + }, + { + "epoch": 0.64, + "learning_rate": 6.891733920059498e-06, + "loss": 1.4573, + "step": 6108 + }, + { + "epoch": 0.64, + "learning_rate": 6.8882551827719215e-06, + "loss": 1.355, + "step": 6109 + }, + { + "epoch": 0.64, + "learning_rate": 6.8847768623782e-06, + "loss": 1.3304, + "step": 6110 + }, + { + "epoch": 0.64, + "learning_rate": 6.881298959344335e-06, + "loss": 1.4039, + "step": 6111 + }, + { + "epoch": 0.64, + "learning_rate": 6.877821474136277e-06, + "loss": 1.381, + "step": 6112 + }, + { + "epoch": 0.64, + "learning_rate": 6.874344407219917e-06, + "loss": 1.3503, + "step": 6113 + }, + { + "epoch": 0.64, + "learning_rate": 6.870867759061099e-06, + "loss": 1.2679, + "step": 6114 + }, + { + "epoch": 0.64, + "learning_rate": 6.8673915301256e-06, + "loss": 1.3286, + "step": 6115 + }, + { + "epoch": 0.64, + "learning_rate": 6.863915720879146e-06, + "loss": 1.3528, + "step": 6116 + }, + { + "epoch": 0.64, + "learning_rate": 6.8604403317874055e-06, + "loss": 1.3502, + "step": 6117 + }, + { + "epoch": 0.64, + "learning_rate": 6.856965363315993e-06, + "loss": 1.3507, + "step": 6118 + }, + { + "epoch": 0.64, + "learning_rate": 6.853490815930464e-06, + "loss": 1.2153, + "step": 6119 + }, + { + "epoch": 0.64, + "learning_rate": 6.850016690096319e-06, + "loss": 1.2435, + "step": 6120 + }, + { + "epoch": 0.64, + "learning_rate": 6.846542986279e-06, + "loss": 1.3418, + "step": 6121 + }, + { + "epoch": 0.64, + "learning_rate": 6.843069704943896e-06, + "loss": 1.371, + "step": 6122 + }, + { + "epoch": 0.64, + "learning_rate": 6.8395968465563375e-06, + "loss": 1.1737, + "step": 6123 + }, + { + "epoch": 0.64, + "learning_rate": 6.836124411581598e-06, + "loss": 1.3402, + "step": 6124 + }, + { + "epoch": 0.64, + "learning_rate": 6.8326524004848924e-06, + "loss": 1.3482, + "step": 6125 + }, + { + "epoch": 0.64, + "learning_rate": 6.8291808137313845e-06, + "loss": 1.4585, + "step": 6126 + }, + { + "epoch": 0.64, + "learning_rate": 6.825709651786176e-06, + "loss": 1.2848, + "step": 6127 + }, + { + "epoch": 0.64, + "learning_rate": 6.822238915114312e-06, + "loss": 1.2932, + "step": 6128 + }, + { + "epoch": 0.64, + "learning_rate": 6.818768604180785e-06, + "loss": 1.3124, + "step": 6129 + }, + { + "epoch": 0.64, + "learning_rate": 6.815298719450525e-06, + "loss": 1.2843, + "step": 6130 + }, + { + "epoch": 0.64, + "learning_rate": 6.811829261388409e-06, + "loss": 1.3024, + "step": 6131 + }, + { + "epoch": 0.64, + "learning_rate": 6.808360230459252e-06, + "loss": 1.3612, + "step": 6132 + }, + { + "epoch": 0.64, + "learning_rate": 6.804891627127821e-06, + "loss": 1.3005, + "step": 6133 + }, + { + "epoch": 0.64, + "learning_rate": 6.8014234518588154e-06, + "loss": 1.2614, + "step": 6134 + }, + { + "epoch": 0.64, + "learning_rate": 6.7979557051168835e-06, + "loss": 1.3717, + "step": 6135 + }, + { + "epoch": 0.64, + "learning_rate": 6.794488387366609e-06, + "loss": 1.3873, + "step": 6136 + }, + { + "epoch": 0.64, + "learning_rate": 6.791021499072532e-06, + "loss": 1.2955, + "step": 6137 + }, + { + "epoch": 0.64, + "learning_rate": 6.787555040699121e-06, + "loss": 1.4217, + "step": 6138 + }, + { + "epoch": 0.64, + "learning_rate": 6.784089012710793e-06, + "loss": 1.3805, + "step": 6139 + }, + { + "epoch": 0.64, + "learning_rate": 6.7806234155719055e-06, + "loss": 1.3982, + "step": 6140 + }, + { + "epoch": 0.64, + "learning_rate": 6.7771582497467635e-06, + "loss": 1.4, + "step": 6141 + }, + { + "epoch": 0.64, + "learning_rate": 6.773693515699607e-06, + "loss": 1.439, + "step": 6142 + }, + { + "epoch": 0.64, + "learning_rate": 6.7702292138946235e-06, + "loss": 1.3672, + "step": 6143 + }, + { + "epoch": 0.64, + "learning_rate": 6.7667653447959355e-06, + "loss": 1.2901, + "step": 6144 + }, + { + "epoch": 0.64, + "learning_rate": 6.763301908867619e-06, + "loss": 1.2873, + "step": 6145 + }, + { + "epoch": 0.64, + "learning_rate": 6.759838906573684e-06, + "loss": 1.3582, + "step": 6146 + }, + { + "epoch": 0.64, + "learning_rate": 6.756376338378077e-06, + "loss": 1.3562, + "step": 6147 + }, + { + "epoch": 0.64, + "learning_rate": 6.7529142047447025e-06, + "loss": 1.3091, + "step": 6148 + }, + { + "epoch": 0.64, + "learning_rate": 6.749452506137393e-06, + "loss": 1.4269, + "step": 6149 + }, + { + "epoch": 0.64, + "learning_rate": 6.745991243019927e-06, + "loss": 1.4184, + "step": 6150 + }, + { + "epoch": 0.65, + "learning_rate": 6.7425304158560235e-06, + "loss": 1.4201, + "step": 6151 + }, + { + "epoch": 0.65, + "learning_rate": 6.739070025109349e-06, + "loss": 1.3222, + "step": 6152 + }, + { + "epoch": 0.65, + "learning_rate": 6.7356100712435035e-06, + "loss": 1.3262, + "step": 6153 + }, + { + "epoch": 0.65, + "learning_rate": 6.732150554722034e-06, + "loss": 1.4408, + "step": 6154 + }, + { + "epoch": 0.65, + "learning_rate": 6.728691476008422e-06, + "loss": 1.3441, + "step": 6155 + }, + { + "epoch": 0.65, + "learning_rate": 6.725232835566102e-06, + "loss": 1.3316, + "step": 6156 + }, + { + "epoch": 0.65, + "learning_rate": 6.721774633858438e-06, + "loss": 1.3326, + "step": 6157 + }, + { + "epoch": 0.65, + "learning_rate": 6.7183168713487425e-06, + "loss": 1.3105, + "step": 6158 + }, + { + "epoch": 0.65, + "learning_rate": 6.714859548500265e-06, + "loss": 1.3144, + "step": 6159 + }, + { + "epoch": 0.65, + "learning_rate": 6.7114026657762e-06, + "loss": 1.3472, + "step": 6160 + }, + { + "epoch": 0.65, + "learning_rate": 6.707946223639681e-06, + "loss": 1.3811, + "step": 6161 + }, + { + "epoch": 0.65, + "learning_rate": 6.704490222553781e-06, + "loss": 1.2783, + "step": 6162 + }, + { + "epoch": 0.65, + "learning_rate": 6.701034662981513e-06, + "loss": 1.273, + "step": 6163 + }, + { + "epoch": 0.65, + "learning_rate": 6.697579545385839e-06, + "loss": 1.3522, + "step": 6164 + }, + { + "epoch": 0.65, + "learning_rate": 6.6941248702296524e-06, + "loss": 1.3861, + "step": 6165 + }, + { + "epoch": 0.65, + "learning_rate": 6.6906706379757915e-06, + "loss": 1.3098, + "step": 6166 + }, + { + "epoch": 0.65, + "learning_rate": 6.687216849087032e-06, + "loss": 1.3734, + "step": 6167 + }, + { + "epoch": 0.65, + "learning_rate": 6.6837635040261e-06, + "loss": 1.2289, + "step": 6168 + }, + { + "epoch": 0.65, + "learning_rate": 6.680310603255648e-06, + "loss": 1.3238, + "step": 6169 + }, + { + "epoch": 0.65, + "eval_loss": 1.40826416015625, + "eval_runtime": 77.483, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 6169 + }, + { + "epoch": 0.65, + "learning_rate": 6.676858147238277e-06, + "loss": 1.4317, + "step": 6170 + }, + { + "epoch": 0.65, + "learning_rate": 6.673406136436531e-06, + "loss": 1.3363, + "step": 6171 + }, + { + "epoch": 0.65, + "learning_rate": 6.669954571312889e-06, + "loss": 1.3377, + "step": 6172 + }, + { + "epoch": 0.65, + "learning_rate": 6.666503452329771e-06, + "loss": 1.3382, + "step": 6173 + }, + { + "epoch": 0.65, + "learning_rate": 6.663052779949538e-06, + "loss": 1.3028, + "step": 6174 + }, + { + "epoch": 0.65, + "learning_rate": 6.659602554634494e-06, + "loss": 1.3098, + "step": 6175 + }, + { + "epoch": 0.65, + "learning_rate": 6.656152776846879e-06, + "loss": 1.328, + "step": 6176 + }, + { + "epoch": 0.65, + "learning_rate": 6.652703447048874e-06, + "loss": 1.3014, + "step": 6177 + }, + { + "epoch": 0.65, + "learning_rate": 6.6492545657026e-06, + "loss": 1.2522, + "step": 6178 + }, + { + "epoch": 0.65, + "learning_rate": 6.645806133270121e-06, + "loss": 1.6113, + "step": 6179 + }, + { + "epoch": 0.65, + "learning_rate": 6.642358150213437e-06, + "loss": 1.3431, + "step": 6180 + }, + { + "epoch": 0.65, + "learning_rate": 6.638910616994489e-06, + "loss": 1.2725, + "step": 6181 + }, + { + "epoch": 0.65, + "learning_rate": 6.635463534075156e-06, + "loss": 1.3022, + "step": 6182 + }, + { + "epoch": 0.65, + "learning_rate": 6.632016901917262e-06, + "loss": 1.3496, + "step": 6183 + }, + { + "epoch": 0.65, + "learning_rate": 6.628570720982567e-06, + "loss": 1.2871, + "step": 6184 + }, + { + "epoch": 0.65, + "learning_rate": 6.625124991732767e-06, + "loss": 1.4449, + "step": 6185 + }, + { + "epoch": 0.65, + "learning_rate": 6.621679714629504e-06, + "loss": 1.4395, + "step": 6186 + }, + { + "epoch": 0.65, + "learning_rate": 6.618234890134356e-06, + "loss": 1.4088, + "step": 6187 + }, + { + "epoch": 0.65, + "learning_rate": 6.614790518708843e-06, + "loss": 1.371, + "step": 6188 + }, + { + "epoch": 0.65, + "learning_rate": 6.611346600814419e-06, + "loss": 1.28, + "step": 6189 + }, + { + "epoch": 0.65, + "learning_rate": 6.607903136912482e-06, + "loss": 1.3502, + "step": 6190 + }, + { + "epoch": 0.65, + "learning_rate": 6.604460127464367e-06, + "loss": 1.3398, + "step": 6191 + }, + { + "epoch": 0.65, + "learning_rate": 6.60101757293135e-06, + "loss": 1.4762, + "step": 6192 + }, + { + "epoch": 0.65, + "learning_rate": 6.5975754737746426e-06, + "loss": 1.2981, + "step": 6193 + }, + { + "epoch": 0.65, + "learning_rate": 6.594133830455401e-06, + "loss": 1.3728, + "step": 6194 + }, + { + "epoch": 0.65, + "learning_rate": 6.590692643434715e-06, + "loss": 1.3551, + "step": 6195 + }, + { + "epoch": 0.65, + "learning_rate": 6.5872519131736155e-06, + "loss": 1.3031, + "step": 6196 + }, + { + "epoch": 0.65, + "learning_rate": 6.583811640133071e-06, + "loss": 1.3231, + "step": 6197 + }, + { + "epoch": 0.65, + "learning_rate": 6.5803718247739924e-06, + "loss": 1.2752, + "step": 6198 + }, + { + "epoch": 0.65, + "learning_rate": 6.576932467557223e-06, + "loss": 1.3482, + "step": 6199 + }, + { + "epoch": 0.65, + "learning_rate": 6.573493568943552e-06, + "loss": 1.2612, + "step": 6200 + }, + { + "epoch": 0.65, + "learning_rate": 6.570055129393698e-06, + "loss": 1.6302, + "step": 6201 + }, + { + "epoch": 0.65, + "learning_rate": 6.566617149368331e-06, + "loss": 1.303, + "step": 6202 + }, + { + "epoch": 0.65, + "learning_rate": 6.563179629328047e-06, + "loss": 1.3405, + "step": 6203 + }, + { + "epoch": 0.65, + "learning_rate": 6.559742569733385e-06, + "loss": 1.2816, + "step": 6204 + }, + { + "epoch": 0.65, + "learning_rate": 6.556305971044824e-06, + "loss": 1.3834, + "step": 6205 + }, + { + "epoch": 0.65, + "learning_rate": 6.552869833722781e-06, + "loss": 1.3414, + "step": 6206 + }, + { + "epoch": 0.65, + "learning_rate": 6.5494341582276096e-06, + "loss": 1.3278, + "step": 6207 + }, + { + "epoch": 0.65, + "learning_rate": 6.5459989450196024e-06, + "loss": 1.3577, + "step": 6208 + }, + { + "epoch": 0.65, + "learning_rate": 6.542564194558986e-06, + "loss": 1.3104, + "step": 6209 + }, + { + "epoch": 0.65, + "learning_rate": 6.539129907305933e-06, + "loss": 1.3068, + "step": 6210 + }, + { + "epoch": 0.65, + "learning_rate": 6.53569608372055e-06, + "loss": 1.3769, + "step": 6211 + }, + { + "epoch": 0.65, + "learning_rate": 6.5322627242628775e-06, + "loss": 1.2855, + "step": 6212 + }, + { + "epoch": 0.65, + "learning_rate": 6.528829829392898e-06, + "loss": 1.4129, + "step": 6213 + }, + { + "epoch": 0.65, + "learning_rate": 6.525397399570534e-06, + "loss": 1.3631, + "step": 6214 + }, + { + "epoch": 0.65, + "learning_rate": 6.5219654352556435e-06, + "loss": 1.295, + "step": 6215 + }, + { + "epoch": 0.65, + "learning_rate": 6.518533936908016e-06, + "loss": 1.439, + "step": 6216 + }, + { + "epoch": 0.65, + "learning_rate": 6.515102904987389e-06, + "loss": 1.3148, + "step": 6217 + }, + { + "epoch": 0.65, + "learning_rate": 6.511672339953432e-06, + "loss": 1.3898, + "step": 6218 + }, + { + "epoch": 0.65, + "learning_rate": 6.508242242265752e-06, + "loss": 1.3222, + "step": 6219 + }, + { + "epoch": 0.65, + "learning_rate": 6.504812612383891e-06, + "loss": 1.324, + "step": 6220 + }, + { + "epoch": 0.65, + "learning_rate": 6.501383450767336e-06, + "loss": 1.951, + "step": 6221 + }, + { + "epoch": 0.65, + "learning_rate": 6.4979547578755055e-06, + "loss": 1.2878, + "step": 6222 + }, + { + "epoch": 0.65, + "learning_rate": 6.494526534167754e-06, + "loss": 1.3553, + "step": 6223 + }, + { + "epoch": 0.65, + "learning_rate": 6.491098780103375e-06, + "loss": 1.3898, + "step": 6224 + }, + { + "epoch": 0.65, + "learning_rate": 6.487671496141606e-06, + "loss": 1.4333, + "step": 6225 + }, + { + "epoch": 0.65, + "learning_rate": 6.484244682741606e-06, + "loss": 1.4461, + "step": 6226 + }, + { + "epoch": 0.65, + "learning_rate": 6.480818340362487e-06, + "loss": 1.3461, + "step": 6227 + }, + { + "epoch": 0.65, + "learning_rate": 6.4773924694632835e-06, + "loss": 1.3442, + "step": 6228 + }, + { + "epoch": 0.65, + "learning_rate": 6.473967070502982e-06, + "loss": 1.2692, + "step": 6229 + }, + { + "epoch": 0.65, + "learning_rate": 6.470542143940495e-06, + "loss": 1.446, + "step": 6230 + }, + { + "epoch": 0.65, + "learning_rate": 6.467117690234675e-06, + "loss": 1.3597, + "step": 6231 + }, + { + "epoch": 0.65, + "learning_rate": 6.463693709844305e-06, + "loss": 1.3226, + "step": 6232 + }, + { + "epoch": 0.65, + "learning_rate": 6.46027020322812e-06, + "loss": 1.2702, + "step": 6233 + }, + { + "epoch": 0.65, + "learning_rate": 6.456847170844775e-06, + "loss": 1.2554, + "step": 6234 + }, + { + "epoch": 0.65, + "learning_rate": 6.453424613152872e-06, + "loss": 1.2896, + "step": 6235 + }, + { + "epoch": 0.65, + "learning_rate": 6.450002530610943e-06, + "loss": 1.3148, + "step": 6236 + }, + { + "epoch": 0.65, + "learning_rate": 6.4465809236774635e-06, + "loss": 1.3589, + "step": 6237 + }, + { + "epoch": 0.65, + "learning_rate": 6.443159792810838e-06, + "loss": 1.2938, + "step": 6238 + }, + { + "epoch": 0.65, + "learning_rate": 6.439739138469406e-06, + "loss": 1.366, + "step": 6239 + }, + { + "epoch": 0.65, + "learning_rate": 6.436318961111455e-06, + "loss": 1.4772, + "step": 6240 + }, + { + "epoch": 0.65, + "learning_rate": 6.4328992611951975e-06, + "loss": 1.3131, + "step": 6241 + }, + { + "epoch": 0.65, + "learning_rate": 6.429480039178786e-06, + "loss": 1.2382, + "step": 6242 + }, + { + "epoch": 0.65, + "learning_rate": 6.426061295520304e-06, + "loss": 1.3394, + "step": 6243 + }, + { + "epoch": 0.65, + "learning_rate": 6.422643030677782e-06, + "loss": 1.321, + "step": 6244 + }, + { + "epoch": 0.65, + "learning_rate": 6.419225245109175e-06, + "loss": 1.3478, + "step": 6245 + }, + { + "epoch": 0.65, + "learning_rate": 6.415807939272383e-06, + "loss": 1.3249, + "step": 6246 + }, + { + "epoch": 0.66, + "learning_rate": 6.412391113625231e-06, + "loss": 1.3602, + "step": 6247 + }, + { + "epoch": 0.66, + "learning_rate": 6.408974768625491e-06, + "loss": 1.2799, + "step": 6248 + }, + { + "epoch": 0.66, + "learning_rate": 6.405558904730863e-06, + "loss": 1.3911, + "step": 6249 + }, + { + "epoch": 0.66, + "learning_rate": 6.402143522398987e-06, + "loss": 1.3185, + "step": 6250 + }, + { + "epoch": 0.66, + "learning_rate": 6.398728622087431e-06, + "loss": 1.3198, + "step": 6251 + }, + { + "epoch": 0.66, + "learning_rate": 6.395314204253711e-06, + "loss": 1.361, + "step": 6252 + }, + { + "epoch": 0.66, + "learning_rate": 6.391900269355269e-06, + "loss": 1.3285, + "step": 6253 + }, + { + "epoch": 0.66, + "learning_rate": 6.388486817849484e-06, + "loss": 1.3097, + "step": 6254 + }, + { + "epoch": 0.66, + "learning_rate": 6.385073850193667e-06, + "loss": 1.3057, + "step": 6255 + }, + { + "epoch": 0.66, + "learning_rate": 6.381661366845075e-06, + "loss": 1.4733, + "step": 6256 + }, + { + "epoch": 0.66, + "learning_rate": 6.378249368260889e-06, + "loss": 1.3571, + "step": 6257 + }, + { + "epoch": 0.66, + "learning_rate": 6.374837854898228e-06, + "loss": 1.3278, + "step": 6258 + }, + { + "epoch": 0.66, + "learning_rate": 6.37142682721415e-06, + "loss": 1.3035, + "step": 6259 + }, + { + "epoch": 0.66, + "learning_rate": 6.368016285665645e-06, + "loss": 1.397, + "step": 6260 + }, + { + "epoch": 0.66, + "learning_rate": 6.3646062307096365e-06, + "loss": 1.353, + "step": 6261 + }, + { + "epoch": 0.66, + "learning_rate": 6.361196662802982e-06, + "loss": 1.3534, + "step": 6262 + }, + { + "epoch": 0.66, + "learning_rate": 6.357787582402482e-06, + "loss": 1.3132, + "step": 6263 + }, + { + "epoch": 0.66, + "learning_rate": 6.3543789899648624e-06, + "loss": 1.3551, + "step": 6264 + }, + { + "epoch": 0.66, + "learning_rate": 6.3509708859467855e-06, + "loss": 1.4205, + "step": 6265 + }, + { + "epoch": 0.66, + "learning_rate": 6.347563270804851e-06, + "loss": 1.341, + "step": 6266 + }, + { + "epoch": 0.66, + "learning_rate": 6.344156144995593e-06, + "loss": 1.5188, + "step": 6267 + }, + { + "epoch": 0.66, + "learning_rate": 6.340749508975477e-06, + "loss": 1.4404, + "step": 6268 + }, + { + "epoch": 0.66, + "learning_rate": 6.337343363200905e-06, + "loss": 1.3026, + "step": 6269 + }, + { + "epoch": 0.66, + "learning_rate": 6.3339377081282124e-06, + "loss": 1.3315, + "step": 6270 + }, + { + "epoch": 0.66, + "learning_rate": 6.3305325442136735e-06, + "loss": 1.2503, + "step": 6271 + }, + { + "epoch": 0.66, + "learning_rate": 6.3271278719134885e-06, + "loss": 1.1776, + "step": 6272 + }, + { + "epoch": 0.66, + "learning_rate": 6.323723691683798e-06, + "loss": 1.3033, + "step": 6273 + }, + { + "epoch": 0.66, + "learning_rate": 6.320320003980671e-06, + "loss": 1.3838, + "step": 6274 + }, + { + "epoch": 0.66, + "learning_rate": 6.3169168092601195e-06, + "loss": 1.3691, + "step": 6275 + }, + { + "epoch": 0.66, + "learning_rate": 6.313514107978083e-06, + "loss": 1.3665, + "step": 6276 + }, + { + "epoch": 0.66, + "learning_rate": 6.310111900590432e-06, + "loss": 1.358, + "step": 6277 + }, + { + "epoch": 0.66, + "learning_rate": 6.306710187552978e-06, + "loss": 1.1708, + "step": 6278 + }, + { + "epoch": 0.66, + "learning_rate": 6.303308969321464e-06, + "loss": 1.331, + "step": 6279 + }, + { + "epoch": 0.66, + "learning_rate": 6.299908246351566e-06, + "loss": 1.3914, + "step": 6280 + }, + { + "epoch": 0.66, + "learning_rate": 6.2965080190988896e-06, + "loss": 1.3183, + "step": 6281 + }, + { + "epoch": 0.66, + "learning_rate": 6.293108288018981e-06, + "loss": 1.2969, + "step": 6282 + }, + { + "epoch": 0.66, + "learning_rate": 6.289709053567318e-06, + "loss": 1.2892, + "step": 6283 + }, + { + "epoch": 0.66, + "learning_rate": 6.2863103161993085e-06, + "loss": 1.3517, + "step": 6284 + }, + { + "epoch": 0.66, + "learning_rate": 6.282912076370295e-06, + "loss": 1.3329, + "step": 6285 + }, + { + "epoch": 0.66, + "learning_rate": 6.279514334535557e-06, + "loss": 1.3396, + "step": 6286 + }, + { + "epoch": 0.66, + "learning_rate": 6.276117091150304e-06, + "loss": 1.3878, + "step": 6287 + }, + { + "epoch": 0.66, + "learning_rate": 6.272720346669677e-06, + "loss": 1.2608, + "step": 6288 + }, + { + "epoch": 0.66, + "learning_rate": 6.269324101548754e-06, + "loss": 1.3605, + "step": 6289 + }, + { + "epoch": 0.66, + "learning_rate": 6.265928356242546e-06, + "loss": 1.2682, + "step": 6290 + }, + { + "epoch": 0.66, + "learning_rate": 6.262533111205995e-06, + "loss": 1.3426, + "step": 6291 + }, + { + "epoch": 0.66, + "learning_rate": 6.259138366893975e-06, + "loss": 1.2987, + "step": 6292 + }, + { + "epoch": 0.66, + "learning_rate": 6.255744123761295e-06, + "loss": 1.3521, + "step": 6293 + }, + { + "epoch": 0.66, + "learning_rate": 6.252350382262697e-06, + "loss": 1.2816, + "step": 6294 + }, + { + "epoch": 0.66, + "learning_rate": 6.248957142852856e-06, + "loss": 1.3884, + "step": 6295 + }, + { + "epoch": 0.66, + "learning_rate": 6.2455644059863795e-06, + "loss": 1.3545, + "step": 6296 + }, + { + "epoch": 0.66, + "learning_rate": 6.2421721721178015e-06, + "loss": 1.3636, + "step": 6297 + }, + { + "epoch": 0.66, + "learning_rate": 6.238780441701601e-06, + "loss": 1.3584, + "step": 6298 + }, + { + "epoch": 0.66, + "learning_rate": 6.235389215192179e-06, + "loss": 1.3459, + "step": 6299 + }, + { + "epoch": 0.66, + "learning_rate": 6.231998493043875e-06, + "loss": 1.4654, + "step": 6300 + }, + { + "epoch": 0.66, + "learning_rate": 6.228608275710954e-06, + "loss": 1.3628, + "step": 6301 + }, + { + "epoch": 0.66, + "learning_rate": 6.225218563647623e-06, + "loss": 1.3278, + "step": 6302 + }, + { + "epoch": 0.66, + "learning_rate": 6.221829357308016e-06, + "loss": 1.395, + "step": 6303 + }, + { + "epoch": 0.66, + "learning_rate": 6.218440657146196e-06, + "loss": 1.3481, + "step": 6304 + }, + { + "epoch": 0.66, + "learning_rate": 6.215052463616165e-06, + "loss": 1.309, + "step": 6305 + }, + { + "epoch": 0.66, + "learning_rate": 6.211664777171853e-06, + "loss": 1.275, + "step": 6306 + }, + { + "epoch": 0.66, + "learning_rate": 6.208277598267123e-06, + "loss": 1.4885, + "step": 6307 + }, + { + "epoch": 0.66, + "learning_rate": 6.2048909273557686e-06, + "loss": 1.3334, + "step": 6308 + }, + { + "epoch": 0.66, + "learning_rate": 6.201504764891518e-06, + "loss": 1.3399, + "step": 6309 + }, + { + "epoch": 0.66, + "learning_rate": 6.198119111328032e-06, + "loss": 1.3163, + "step": 6310 + }, + { + "epoch": 0.66, + "learning_rate": 6.1947339671188966e-06, + "loss": 1.2746, + "step": 6311 + }, + { + "epoch": 0.66, + "learning_rate": 6.191349332717635e-06, + "loss": 1.2984, + "step": 6312 + }, + { + "epoch": 0.66, + "learning_rate": 6.187965208577705e-06, + "loss": 1.2295, + "step": 6313 + }, + { + "epoch": 0.66, + "learning_rate": 6.18458159515249e-06, + "loss": 1.3424, + "step": 6314 + }, + { + "epoch": 0.66, + "learning_rate": 6.181198492895308e-06, + "loss": 1.3108, + "step": 6315 + }, + { + "epoch": 0.66, + "learning_rate": 6.1778159022594045e-06, + "loss": 1.4895, + "step": 6316 + }, + { + "epoch": 0.66, + "learning_rate": 6.174433823697964e-06, + "loss": 1.3247, + "step": 6317 + }, + { + "epoch": 0.66, + "learning_rate": 6.171052257664097e-06, + "loss": 1.3659, + "step": 6318 + }, + { + "epoch": 0.66, + "learning_rate": 6.167671204610844e-06, + "loss": 1.3889, + "step": 6319 + }, + { + "epoch": 0.66, + "learning_rate": 6.1642906649911815e-06, + "loss": 1.3946, + "step": 6320 + }, + { + "epoch": 0.66, + "learning_rate": 6.1609106392580155e-06, + "loss": 1.3685, + "step": 6321 + }, + { + "epoch": 0.66, + "learning_rate": 6.157531127864181e-06, + "loss": 1.2584, + "step": 6322 + }, + { + "epoch": 0.66, + "learning_rate": 6.154152131262448e-06, + "loss": 1.3263, + "step": 6323 + }, + { + "epoch": 0.66, + "learning_rate": 6.15077364990551e-06, + "loss": 1.3336, + "step": 6324 + }, + { + "epoch": 0.66, + "learning_rate": 6.147395684246003e-06, + "loss": 1.2513, + "step": 6325 + }, + { + "epoch": 0.66, + "learning_rate": 6.144018234736484e-06, + "loss": 1.3715, + "step": 6326 + }, + { + "epoch": 0.66, + "learning_rate": 6.140641301829444e-06, + "loss": 1.3464, + "step": 6327 + }, + { + "epoch": 0.66, + "learning_rate": 6.1372648859773075e-06, + "loss": 1.4374, + "step": 6328 + }, + { + "epoch": 0.66, + "learning_rate": 6.1338889876324285e-06, + "loss": 1.3903, + "step": 6329 + }, + { + "epoch": 0.66, + "learning_rate": 6.130513607247087e-06, + "loss": 1.3715, + "step": 6330 + }, + { + "epoch": 0.66, + "learning_rate": 6.127138745273497e-06, + "loss": 1.3196, + "step": 6331 + }, + { + "epoch": 0.66, + "learning_rate": 6.123764402163808e-06, + "loss": 1.3013, + "step": 6332 + }, + { + "epoch": 0.66, + "learning_rate": 6.120390578370093e-06, + "loss": 1.2751, + "step": 6333 + }, + { + "epoch": 0.66, + "learning_rate": 6.117017274344356e-06, + "loss": 1.2258, + "step": 6334 + }, + { + "epoch": 0.66, + "learning_rate": 6.113644490538533e-06, + "loss": 1.2982, + "step": 6335 + }, + { + "epoch": 0.66, + "learning_rate": 6.110272227404492e-06, + "loss": 1.3124, + "step": 6336 + }, + { + "epoch": 0.66, + "learning_rate": 6.10690048539403e-06, + "loss": 1.2451, + "step": 6337 + }, + { + "epoch": 0.66, + "learning_rate": 6.103529264958874e-06, + "loss": 1.3896, + "step": 6338 + }, + { + "epoch": 0.66, + "learning_rate": 6.100158566550677e-06, + "loss": 1.46, + "step": 6339 + }, + { + "epoch": 0.66, + "learning_rate": 6.096788390621031e-06, + "loss": 1.2965, + "step": 6340 + }, + { + "epoch": 0.66, + "learning_rate": 6.093418737621452e-06, + "loss": 1.2969, + "step": 6341 + }, + { + "epoch": 0.67, + "learning_rate": 6.0900496080033836e-06, + "loss": 1.3988, + "step": 6342 + }, + { + "epoch": 0.67, + "learning_rate": 6.086681002218204e-06, + "loss": 1.351, + "step": 6343 + }, + { + "epoch": 0.67, + "learning_rate": 6.083312920717224e-06, + "loss": 1.3447, + "step": 6344 + }, + { + "epoch": 0.67, + "learning_rate": 6.079945363951674e-06, + "loss": 1.3361, + "step": 6345 + }, + { + "epoch": 0.67, + "learning_rate": 6.076578332372724e-06, + "loss": 1.3688, + "step": 6346 + }, + { + "epoch": 0.67, + "learning_rate": 6.073211826431467e-06, + "loss": 1.2831, + "step": 6347 + }, + { + "epoch": 0.67, + "learning_rate": 6.069845846578931e-06, + "loss": 1.369, + "step": 6348 + }, + { + "epoch": 0.67, + "learning_rate": 6.06648039326607e-06, + "loss": 1.3247, + "step": 6349 + }, + { + "epoch": 0.67, + "learning_rate": 6.063115466943765e-06, + "loss": 1.288, + "step": 6350 + }, + { + "epoch": 0.67, + "learning_rate": 6.0597510680628345e-06, + "loss": 1.0733, + "step": 6351 + }, + { + "epoch": 0.67, + "learning_rate": 6.056387197074021e-06, + "loss": 1.3386, + "step": 6352 + }, + { + "epoch": 0.67, + "learning_rate": 6.053023854427993e-06, + "loss": 1.3682, + "step": 6353 + }, + { + "epoch": 0.67, + "learning_rate": 6.049661040575353e-06, + "loss": 1.5669, + "step": 6354 + }, + { + "epoch": 0.67, + "learning_rate": 6.0462987559666355e-06, + "loss": 1.3432, + "step": 6355 + }, + { + "epoch": 0.67, + "learning_rate": 6.042937001052298e-06, + "loss": 1.327, + "step": 6356 + }, + { + "epoch": 0.67, + "learning_rate": 6.039575776282728e-06, + "loss": 1.3101, + "step": 6357 + }, + { + "epoch": 0.67, + "learning_rate": 6.0362150821082425e-06, + "loss": 1.3239, + "step": 6358 + }, + { + "epoch": 0.67, + "learning_rate": 6.032854918979092e-06, + "loss": 1.435, + "step": 6359 + }, + { + "epoch": 0.67, + "learning_rate": 6.029495287345448e-06, + "loss": 1.3503, + "step": 6360 + }, + { + "epoch": 0.67, + "learning_rate": 6.0261361876574186e-06, + "loss": 1.3356, + "step": 6361 + }, + { + "epoch": 0.67, + "learning_rate": 6.022777620365032e-06, + "loss": 1.3301, + "step": 6362 + }, + { + "epoch": 0.67, + "learning_rate": 6.019419585918255e-06, + "loss": 1.3925, + "step": 6363 + }, + { + "epoch": 0.67, + "learning_rate": 6.016062084766978e-06, + "loss": 1.3794, + "step": 6364 + }, + { + "epoch": 0.67, + "learning_rate": 6.0127051173610155e-06, + "loss": 1.5496, + "step": 6365 + }, + { + "epoch": 0.67, + "learning_rate": 6.009348684150116e-06, + "loss": 1.3227, + "step": 6366 + }, + { + "epoch": 0.67, + "learning_rate": 6.005992785583958e-06, + "loss": 1.3474, + "step": 6367 + }, + { + "epoch": 0.67, + "learning_rate": 6.002637422112143e-06, + "loss": 1.3262, + "step": 6368 + }, + { + "epoch": 0.67, + "eval_loss": 1.4049769639968872, + "eval_runtime": 77.5156, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 6368 + }, + { + "epoch": 0.67, + "learning_rate": 5.999282594184206e-06, + "loss": 1.3083, + "step": 6369 + }, + { + "epoch": 0.67, + "learning_rate": 5.995928302249603e-06, + "loss": 1.323, + "step": 6370 + }, + { + "epoch": 0.67, + "learning_rate": 5.99257454675773e-06, + "loss": 1.3101, + "step": 6371 + }, + { + "epoch": 0.67, + "learning_rate": 5.989221328157899e-06, + "loss": 1.4546, + "step": 6372 + }, + { + "epoch": 0.67, + "learning_rate": 5.985868646899355e-06, + "loss": 1.3315, + "step": 6373 + }, + { + "epoch": 0.67, + "learning_rate": 5.982516503431273e-06, + "loss": 1.3768, + "step": 6374 + }, + { + "epoch": 0.67, + "learning_rate": 5.979164898202755e-06, + "loss": 1.332, + "step": 6375 + }, + { + "epoch": 0.67, + "learning_rate": 5.975813831662829e-06, + "loss": 1.3154, + "step": 6376 + }, + { + "epoch": 0.67, + "learning_rate": 5.972463304260448e-06, + "loss": 1.3636, + "step": 6377 + }, + { + "epoch": 0.67, + "learning_rate": 5.969113316444504e-06, + "loss": 1.3553, + "step": 6378 + }, + { + "epoch": 0.67, + "learning_rate": 5.965763868663803e-06, + "loss": 1.3805, + "step": 6379 + }, + { + "epoch": 0.67, + "learning_rate": 5.962414961367089e-06, + "loss": 1.3096, + "step": 6380 + }, + { + "epoch": 0.67, + "learning_rate": 5.959066595003025e-06, + "loss": 1.326, + "step": 6381 + }, + { + "epoch": 0.67, + "learning_rate": 5.955718770020212e-06, + "loss": 1.3021, + "step": 6382 + }, + { + "epoch": 0.67, + "learning_rate": 5.952371486867168e-06, + "loss": 1.35, + "step": 6383 + }, + { + "epoch": 0.67, + "learning_rate": 5.949024745992344e-06, + "loss": 1.6749, + "step": 6384 + }, + { + "epoch": 0.67, + "learning_rate": 5.945678547844117e-06, + "loss": 1.4931, + "step": 6385 + }, + { + "epoch": 0.67, + "learning_rate": 5.942332892870793e-06, + "loss": 1.284, + "step": 6386 + }, + { + "epoch": 0.67, + "learning_rate": 5.938987781520604e-06, + "loss": 1.3296, + "step": 6387 + }, + { + "epoch": 0.67, + "learning_rate": 5.9356432142417074e-06, + "loss": 1.4837, + "step": 6388 + }, + { + "epoch": 0.67, + "learning_rate": 5.932299191482188e-06, + "loss": 1.3114, + "step": 6389 + }, + { + "epoch": 0.67, + "learning_rate": 5.928955713690063e-06, + "loss": 1.3328, + "step": 6390 + }, + { + "epoch": 0.67, + "learning_rate": 5.92561278131327e-06, + "loss": 1.3163, + "step": 6391 + }, + { + "epoch": 0.67, + "learning_rate": 5.922270394799676e-06, + "loss": 1.3068, + "step": 6392 + }, + { + "epoch": 0.67, + "learning_rate": 5.918928554597073e-06, + "loss": 1.292, + "step": 6393 + }, + { + "epoch": 0.67, + "learning_rate": 5.915587261153186e-06, + "loss": 1.3359, + "step": 6394 + }, + { + "epoch": 0.67, + "learning_rate": 5.912246514915662e-06, + "loss": 1.4109, + "step": 6395 + }, + { + "epoch": 0.67, + "learning_rate": 5.908906316332071e-06, + "loss": 1.3083, + "step": 6396 + }, + { + "epoch": 0.67, + "learning_rate": 5.905566665849917e-06, + "loss": 1.2973, + "step": 6397 + }, + { + "epoch": 0.67, + "learning_rate": 5.902227563916627e-06, + "loss": 1.4159, + "step": 6398 + }, + { + "epoch": 0.67, + "learning_rate": 5.898889010979556e-06, + "loss": 1.287, + "step": 6399 + }, + { + "epoch": 0.67, + "learning_rate": 5.89555100748598e-06, + "loss": 1.2865, + "step": 6400 + }, + { + "epoch": 0.67, + "learning_rate": 5.89221355388311e-06, + "loss": 1.3137, + "step": 6401 + }, + { + "epoch": 0.67, + "learning_rate": 5.8888766506180785e-06, + "loss": 1.2751, + "step": 6402 + }, + { + "epoch": 0.67, + "learning_rate": 5.885540298137944e-06, + "loss": 1.3687, + "step": 6403 + }, + { + "epoch": 0.67, + "learning_rate": 5.882204496889688e-06, + "loss": 1.2941, + "step": 6404 + }, + { + "epoch": 0.67, + "learning_rate": 5.878869247320231e-06, + "loss": 1.2926, + "step": 6405 + }, + { + "epoch": 0.67, + "learning_rate": 5.875534549876404e-06, + "loss": 1.2675, + "step": 6406 + }, + { + "epoch": 0.67, + "learning_rate": 5.872200405004973e-06, + "loss": 1.2806, + "step": 6407 + }, + { + "epoch": 0.67, + "learning_rate": 5.868866813152625e-06, + "loss": 1.3438, + "step": 6408 + }, + { + "epoch": 0.67, + "learning_rate": 5.865533774765981e-06, + "loss": 1.2947, + "step": 6409 + }, + { + "epoch": 0.67, + "learning_rate": 5.862201290291578e-06, + "loss": 1.3643, + "step": 6410 + }, + { + "epoch": 0.67, + "learning_rate": 5.858869360175887e-06, + "loss": 1.2579, + "step": 6411 + }, + { + "epoch": 0.67, + "learning_rate": 5.855537984865296e-06, + "loss": 1.3479, + "step": 6412 + }, + { + "epoch": 0.67, + "learning_rate": 5.852207164806127e-06, + "loss": 1.3239, + "step": 6413 + }, + { + "epoch": 0.67, + "learning_rate": 5.848876900444626e-06, + "loss": 1.2644, + "step": 6414 + }, + { + "epoch": 0.67, + "learning_rate": 5.845547192226959e-06, + "loss": 1.3279, + "step": 6415 + }, + { + "epoch": 0.67, + "learning_rate": 5.8422180405992216e-06, + "loss": 1.5202, + "step": 6416 + }, + { + "epoch": 0.67, + "learning_rate": 5.838889446007439e-06, + "loss": 1.5714, + "step": 6417 + }, + { + "epoch": 0.67, + "learning_rate": 5.835561408897552e-06, + "loss": 1.2592, + "step": 6418 + }, + { + "epoch": 0.67, + "learning_rate": 5.832233929715434e-06, + "loss": 1.3407, + "step": 6419 + }, + { + "epoch": 0.67, + "learning_rate": 5.828907008906882e-06, + "loss": 1.3555, + "step": 6420 + }, + { + "epoch": 0.67, + "learning_rate": 5.825580646917622e-06, + "loss": 1.2602, + "step": 6421 + }, + { + "epoch": 0.67, + "learning_rate": 5.822254844193293e-06, + "loss": 1.2672, + "step": 6422 + }, + { + "epoch": 0.67, + "learning_rate": 5.818929601179472e-06, + "loss": 1.3361, + "step": 6423 + }, + { + "epoch": 0.67, + "learning_rate": 5.8156049183216575e-06, + "loss": 1.49, + "step": 6424 + }, + { + "epoch": 0.67, + "learning_rate": 5.812280796065269e-06, + "loss": 1.306, + "step": 6425 + }, + { + "epoch": 0.67, + "learning_rate": 5.808957234855654e-06, + "loss": 1.3167, + "step": 6426 + }, + { + "epoch": 0.67, + "learning_rate": 5.805634235138082e-06, + "loss": 1.3103, + "step": 6427 + }, + { + "epoch": 0.67, + "learning_rate": 5.802311797357752e-06, + "loss": 1.2992, + "step": 6428 + }, + { + "epoch": 0.67, + "learning_rate": 5.7989899219597875e-06, + "loss": 1.3269, + "step": 6429 + }, + { + "epoch": 0.67, + "learning_rate": 5.795668609389233e-06, + "loss": 1.3393, + "step": 6430 + }, + { + "epoch": 0.67, + "learning_rate": 5.79234786009105e-06, + "loss": 1.2633, + "step": 6431 + }, + { + "epoch": 0.67, + "learning_rate": 5.7890276745101495e-06, + "loss": 1.2758, + "step": 6432 + }, + { + "epoch": 0.67, + "learning_rate": 5.785708053091339e-06, + "loss": 1.3294, + "step": 6433 + }, + { + "epoch": 0.67, + "learning_rate": 5.782388996279371e-06, + "loss": 1.3657, + "step": 6434 + }, + { + "epoch": 0.67, + "learning_rate": 5.779070504518905e-06, + "loss": 1.3353, + "step": 6435 + }, + { + "epoch": 0.67, + "learning_rate": 5.775752578254539e-06, + "loss": 1.2741, + "step": 6436 + }, + { + "epoch": 0.68, + "learning_rate": 5.772435217930792e-06, + "loss": 1.2979, + "step": 6437 + }, + { + "epoch": 0.68, + "learning_rate": 5.7691184239921026e-06, + "loss": 1.366, + "step": 6438 + }, + { + "epoch": 0.68, + "learning_rate": 5.765802196882828e-06, + "loss": 1.2873, + "step": 6439 + }, + { + "epoch": 0.68, + "learning_rate": 5.762486537047271e-06, + "loss": 1.2865, + "step": 6440 + }, + { + "epoch": 0.68, + "learning_rate": 5.7591714449296365e-06, + "loss": 1.3887, + "step": 6441 + }, + { + "epoch": 0.68, + "learning_rate": 5.755856920974063e-06, + "loss": 1.127, + "step": 6442 + }, + { + "epoch": 0.68, + "learning_rate": 5.752542965624617e-06, + "loss": 1.4331, + "step": 6443 + }, + { + "epoch": 0.68, + "learning_rate": 5.749229579325274e-06, + "loss": 1.3199, + "step": 6444 + }, + { + "epoch": 0.68, + "learning_rate": 5.745916762519952e-06, + "loss": 1.2719, + "step": 6445 + }, + { + "epoch": 0.68, + "learning_rate": 5.742604515652475e-06, + "loss": 1.2991, + "step": 6446 + }, + { + "epoch": 0.68, + "learning_rate": 5.7392928391666014e-06, + "loss": 1.2164, + "step": 6447 + }, + { + "epoch": 0.68, + "learning_rate": 5.735981733506016e-06, + "loss": 1.3636, + "step": 6448 + }, + { + "epoch": 0.68, + "learning_rate": 5.732671199114314e-06, + "loss": 1.3486, + "step": 6449 + }, + { + "epoch": 0.68, + "learning_rate": 5.729361236435027e-06, + "loss": 1.3378, + "step": 6450 + }, + { + "epoch": 0.68, + "learning_rate": 5.726051845911606e-06, + "loss": 1.3521, + "step": 6451 + }, + { + "epoch": 0.68, + "learning_rate": 5.722743027987421e-06, + "loss": 1.4295, + "step": 6452 + }, + { + "epoch": 0.68, + "learning_rate": 5.719434783105772e-06, + "loss": 1.2625, + "step": 6453 + }, + { + "epoch": 0.68, + "learning_rate": 5.716127111709873e-06, + "loss": 1.2944, + "step": 6454 + }, + { + "epoch": 0.68, + "learning_rate": 5.7128200142428695e-06, + "loss": 1.3655, + "step": 6455 + }, + { + "epoch": 0.68, + "learning_rate": 5.7095134911478336e-06, + "loss": 1.3115, + "step": 6456 + }, + { + "epoch": 0.68, + "learning_rate": 5.706207542867747e-06, + "loss": 1.3391, + "step": 6457 + }, + { + "epoch": 0.68, + "learning_rate": 5.702902169845519e-06, + "loss": 1.3911, + "step": 6458 + }, + { + "epoch": 0.68, + "learning_rate": 5.699597372523997e-06, + "loss": 1.2936, + "step": 6459 + }, + { + "epoch": 0.68, + "learning_rate": 5.696293151345928e-06, + "loss": 1.379, + "step": 6460 + }, + { + "epoch": 0.68, + "learning_rate": 5.692989506754e-06, + "loss": 1.4083, + "step": 6461 + }, + { + "epoch": 0.68, + "learning_rate": 5.689686439190809e-06, + "loss": 1.2645, + "step": 6462 + }, + { + "epoch": 0.68, + "learning_rate": 5.686383949098886e-06, + "loss": 1.3207, + "step": 6463 + }, + { + "epoch": 0.68, + "learning_rate": 5.683082036920682e-06, + "loss": 1.4293, + "step": 6464 + }, + { + "epoch": 0.68, + "learning_rate": 5.679780703098563e-06, + "loss": 1.3018, + "step": 6465 + }, + { + "epoch": 0.68, + "learning_rate": 5.676479948074825e-06, + "loss": 1.3568, + "step": 6466 + }, + { + "epoch": 0.68, + "learning_rate": 5.673179772291687e-06, + "loss": 1.3252, + "step": 6467 + }, + { + "epoch": 0.68, + "learning_rate": 5.669880176191283e-06, + "loss": 1.2674, + "step": 6468 + }, + { + "epoch": 0.68, + "learning_rate": 5.666581160215676e-06, + "loss": 1.3774, + "step": 6469 + }, + { + "epoch": 0.68, + "learning_rate": 5.663282724806855e-06, + "loss": 1.3013, + "step": 6470 + }, + { + "epoch": 0.68, + "learning_rate": 5.659984870406715e-06, + "loss": 1.3354, + "step": 6471 + }, + { + "epoch": 0.68, + "learning_rate": 5.656687597457093e-06, + "loss": 1.273, + "step": 6472 + }, + { + "epoch": 0.68, + "learning_rate": 5.653390906399732e-06, + "loss": 1.3041, + "step": 6473 + }, + { + "epoch": 0.68, + "learning_rate": 5.650094797676308e-06, + "loss": 1.3521, + "step": 6474 + }, + { + "epoch": 0.68, + "learning_rate": 5.646799271728417e-06, + "loss": 1.3751, + "step": 6475 + }, + { + "epoch": 0.68, + "learning_rate": 5.643504328997571e-06, + "loss": 1.2882, + "step": 6476 + }, + { + "epoch": 0.68, + "learning_rate": 5.640209969925202e-06, + "loss": 1.2625, + "step": 6477 + }, + { + "epoch": 0.68, + "learning_rate": 5.636916194952683e-06, + "loss": 1.3648, + "step": 6478 + }, + { + "epoch": 0.68, + "learning_rate": 5.633623004521285e-06, + "loss": 1.3115, + "step": 6479 + }, + { + "epoch": 0.68, + "learning_rate": 5.6303303990722154e-06, + "loss": 1.2755, + "step": 6480 + }, + { + "epoch": 0.68, + "learning_rate": 5.627038379046595e-06, + "loss": 1.4546, + "step": 6481 + }, + { + "epoch": 0.68, + "learning_rate": 5.623746944885473e-06, + "loss": 1.3717, + "step": 6482 + }, + { + "epoch": 0.68, + "learning_rate": 5.620456097029818e-06, + "loss": 1.3188, + "step": 6483 + }, + { + "epoch": 0.68, + "learning_rate": 5.61716583592052e-06, + "loss": 1.3166, + "step": 6484 + }, + { + "epoch": 0.68, + "learning_rate": 5.613876161998377e-06, + "loss": 1.3413, + "step": 6485 + }, + { + "epoch": 0.68, + "learning_rate": 5.610587075704139e-06, + "loss": 1.395, + "step": 6486 + }, + { + "epoch": 0.68, + "learning_rate": 5.6072985774784465e-06, + "loss": 1.2914, + "step": 6487 + }, + { + "epoch": 0.68, + "learning_rate": 5.604010667761876e-06, + "loss": 1.3118, + "step": 6488 + }, + { + "epoch": 0.68, + "learning_rate": 5.600723346994932e-06, + "loss": 1.3599, + "step": 6489 + }, + { + "epoch": 0.68, + "learning_rate": 5.597436615618017e-06, + "loss": 1.2862, + "step": 6490 + }, + { + "epoch": 0.68, + "learning_rate": 5.594150474071481e-06, + "loss": 1.3585, + "step": 6491 + }, + { + "epoch": 0.68, + "learning_rate": 5.590864922795573e-06, + "loss": 1.3449, + "step": 6492 + }, + { + "epoch": 0.68, + "learning_rate": 5.587579962230475e-06, + "loss": 1.2787, + "step": 6493 + }, + { + "epoch": 0.68, + "learning_rate": 5.5842955928162934e-06, + "loss": 1.3755, + "step": 6494 + }, + { + "epoch": 0.68, + "learning_rate": 5.5810118149930406e-06, + "loss": 1.2858, + "step": 6495 + }, + { + "epoch": 0.68, + "learning_rate": 5.577728629200662e-06, + "loss": 1.4214, + "step": 6496 + }, + { + "epoch": 0.68, + "learning_rate": 5.574446035879024e-06, + "loss": 1.5007, + "step": 6497 + }, + { + "epoch": 0.68, + "learning_rate": 5.571164035467903e-06, + "loss": 1.2952, + "step": 6498 + }, + { + "epoch": 0.68, + "learning_rate": 5.56788262840701e-06, + "loss": 1.267, + "step": 6499 + }, + { + "epoch": 0.68, + "learning_rate": 5.564601815135962e-06, + "loss": 1.3168, + "step": 6500 + }, + { + "epoch": 0.68, + "learning_rate": 5.561321596094305e-06, + "loss": 1.2992, + "step": 6501 + }, + { + "epoch": 0.68, + "learning_rate": 5.558041971721511e-06, + "loss": 1.4237, + "step": 6502 + }, + { + "epoch": 0.68, + "learning_rate": 5.554762942456959e-06, + "loss": 1.3865, + "step": 6503 + }, + { + "epoch": 0.68, + "learning_rate": 5.5514845087399505e-06, + "loss": 1.2875, + "step": 6504 + }, + { + "epoch": 0.68, + "learning_rate": 5.548206671009724e-06, + "loss": 1.3011, + "step": 6505 + }, + { + "epoch": 0.68, + "learning_rate": 5.544929429705415e-06, + "loss": 1.3425, + "step": 6506 + }, + { + "epoch": 0.68, + "learning_rate": 5.541652785266095e-06, + "loss": 1.4265, + "step": 6507 + }, + { + "epoch": 0.68, + "learning_rate": 5.538376738130747e-06, + "loss": 1.2877, + "step": 6508 + }, + { + "epoch": 0.68, + "learning_rate": 5.535101288738276e-06, + "loss": 1.3652, + "step": 6509 + }, + { + "epoch": 0.68, + "learning_rate": 5.5318264375275145e-06, + "loss": 1.2997, + "step": 6510 + }, + { + "epoch": 0.68, + "learning_rate": 5.528552184937201e-06, + "loss": 1.3223, + "step": 6511 + }, + { + "epoch": 0.68, + "learning_rate": 5.525278531406006e-06, + "loss": 1.2897, + "step": 6512 + }, + { + "epoch": 0.68, + "learning_rate": 5.522005477372516e-06, + "loss": 1.3554, + "step": 6513 + }, + { + "epoch": 0.68, + "learning_rate": 5.51873302327523e-06, + "loss": 1.3233, + "step": 6514 + }, + { + "epoch": 0.68, + "learning_rate": 5.515461169552576e-06, + "loss": 1.3536, + "step": 6515 + }, + { + "epoch": 0.68, + "learning_rate": 5.5121899166429046e-06, + "loss": 1.3485, + "step": 6516 + }, + { + "epoch": 0.68, + "learning_rate": 5.508919264984468e-06, + "loss": 1.3264, + "step": 6517 + }, + { + "epoch": 0.68, + "learning_rate": 5.505649215015461e-06, + "loss": 1.4498, + "step": 6518 + }, + { + "epoch": 0.68, + "learning_rate": 5.5023797671739755e-06, + "loss": 1.4468, + "step": 6519 + }, + { + "epoch": 0.68, + "learning_rate": 5.499110921898038e-06, + "loss": 1.2659, + "step": 6520 + }, + { + "epoch": 0.68, + "learning_rate": 5.4958426796255934e-06, + "loss": 1.318, + "step": 6521 + }, + { + "epoch": 0.68, + "learning_rate": 5.492575040794498e-06, + "loss": 1.3167, + "step": 6522 + }, + { + "epoch": 0.68, + "learning_rate": 5.48930800584253e-06, + "loss": 1.3453, + "step": 6523 + }, + { + "epoch": 0.68, + "learning_rate": 5.486041575207397e-06, + "loss": 1.2557, + "step": 6524 + }, + { + "epoch": 0.68, + "learning_rate": 5.482775749326705e-06, + "loss": 1.3235, + "step": 6525 + }, + { + "epoch": 0.68, + "learning_rate": 5.479510528638001e-06, + "loss": 1.3119, + "step": 6526 + }, + { + "epoch": 0.68, + "learning_rate": 5.476245913578733e-06, + "loss": 1.4639, + "step": 6527 + }, + { + "epoch": 0.68, + "learning_rate": 5.472981904586277e-06, + "loss": 1.3233, + "step": 6528 + }, + { + "epoch": 0.68, + "learning_rate": 5.469718502097931e-06, + "loss": 1.2722, + "step": 6529 + }, + { + "epoch": 0.68, + "learning_rate": 5.466455706550906e-06, + "loss": 1.4428, + "step": 6530 + }, + { + "epoch": 0.68, + "learning_rate": 5.463193518382321e-06, + "loss": 1.5695, + "step": 6531 + }, + { + "epoch": 0.68, + "learning_rate": 5.4599319380292434e-06, + "loss": 1.3161, + "step": 6532 + }, + { + "epoch": 0.69, + "learning_rate": 5.4566709659286296e-06, + "loss": 1.3513, + "step": 6533 + }, + { + "epoch": 0.69, + "learning_rate": 5.453410602517368e-06, + "loss": 1.2716, + "step": 6534 + }, + { + "epoch": 0.69, + "learning_rate": 5.45015084823227e-06, + "loss": 1.4467, + "step": 6535 + }, + { + "epoch": 0.69, + "learning_rate": 5.44689170351005e-06, + "loss": 1.4082, + "step": 6536 + }, + { + "epoch": 0.69, + "learning_rate": 5.443633168787357e-06, + "loss": 1.303, + "step": 6537 + }, + { + "epoch": 0.69, + "learning_rate": 5.440375244500743e-06, + "loss": 1.2765, + "step": 6538 + }, + { + "epoch": 0.69, + "learning_rate": 5.43711793108669e-06, + "loss": 1.6814, + "step": 6539 + }, + { + "epoch": 0.69, + "learning_rate": 5.4338612289816e-06, + "loss": 1.3899, + "step": 6540 + }, + { + "epoch": 0.69, + "learning_rate": 5.430605138621778e-06, + "loss": 1.201, + "step": 6541 + }, + { + "epoch": 0.69, + "learning_rate": 5.42734966044346e-06, + "loss": 1.3214, + "step": 6542 + }, + { + "epoch": 0.69, + "learning_rate": 5.424094794882801e-06, + "loss": 1.2676, + "step": 6543 + }, + { + "epoch": 0.69, + "learning_rate": 5.420840542375862e-06, + "loss": 1.3006, + "step": 6544 + }, + { + "epoch": 0.69, + "learning_rate": 5.4175869033586355e-06, + "loss": 1.32, + "step": 6545 + }, + { + "epoch": 0.69, + "learning_rate": 5.41433387826702e-06, + "loss": 1.3347, + "step": 6546 + }, + { + "epoch": 0.69, + "learning_rate": 5.41108146753684e-06, + "loss": 1.3983, + "step": 6547 + }, + { + "epoch": 0.69, + "learning_rate": 5.407829671603838e-06, + "loss": 1.3756, + "step": 6548 + }, + { + "epoch": 0.69, + "learning_rate": 5.404578490903664e-06, + "loss": 1.3444, + "step": 6549 + }, + { + "epoch": 0.69, + "learning_rate": 5.4013279258718974e-06, + "loss": 1.3369, + "step": 6550 + }, + { + "epoch": 0.69, + "learning_rate": 5.398077976944034e-06, + "loss": 1.2995, + "step": 6551 + }, + { + "epoch": 0.69, + "learning_rate": 5.394828644555475e-06, + "loss": 1.3305, + "step": 6552 + }, + { + "epoch": 0.69, + "learning_rate": 5.391579929141554e-06, + "loss": 1.3743, + "step": 6553 + }, + { + "epoch": 0.69, + "learning_rate": 5.3883318311375095e-06, + "loss": 1.2829, + "step": 6554 + }, + { + "epoch": 0.69, + "learning_rate": 5.3850843509785065e-06, + "loss": 1.379, + "step": 6555 + }, + { + "epoch": 0.69, + "learning_rate": 5.3818374890996295e-06, + "loss": 1.3236, + "step": 6556 + }, + { + "epoch": 0.69, + "learning_rate": 5.378591245935865e-06, + "loss": 1.3469, + "step": 6557 + }, + { + "epoch": 0.69, + "learning_rate": 5.375345621922129e-06, + "loss": 1.3318, + "step": 6558 + }, + { + "epoch": 0.69, + "learning_rate": 5.3721006174932576e-06, + "loss": 1.3395, + "step": 6559 + }, + { + "epoch": 0.69, + "learning_rate": 5.36885623308399e-06, + "loss": 1.4148, + "step": 6560 + }, + { + "epoch": 0.69, + "learning_rate": 5.365612469128993e-06, + "loss": 1.3007, + "step": 6561 + }, + { + "epoch": 0.69, + "learning_rate": 5.362369326062853e-06, + "loss": 1.4365, + "step": 6562 + }, + { + "epoch": 0.69, + "learning_rate": 5.3591268043200585e-06, + "loss": 1.4269, + "step": 6563 + }, + { + "epoch": 0.69, + "learning_rate": 5.355884904335034e-06, + "loss": 1.2619, + "step": 6564 + }, + { + "epoch": 0.69, + "learning_rate": 5.3526436265421e-06, + "loss": 1.2678, + "step": 6565 + }, + { + "epoch": 0.69, + "learning_rate": 5.34940297137551e-06, + "loss": 1.2541, + "step": 6566 + }, + { + "epoch": 0.69, + "learning_rate": 5.3461629392694345e-06, + "loss": 1.3237, + "step": 6567 + }, + { + "epoch": 0.69, + "eval_loss": 1.402653694152832, + "eval_runtime": 77.5033, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 6567 + }, + { + "epoch": 0.69, + "learning_rate": 5.342923530657944e-06, + "loss": 1.357, + "step": 6568 + }, + { + "epoch": 0.69, + "learning_rate": 5.33968474597504e-06, + "loss": 1.3561, + "step": 6569 + }, + { + "epoch": 0.69, + "learning_rate": 5.336446585654642e-06, + "loss": 1.2969, + "step": 6570 + }, + { + "epoch": 0.69, + "learning_rate": 5.33320905013057e-06, + "loss": 1.2922, + "step": 6571 + }, + { + "epoch": 0.69, + "learning_rate": 5.329972139836581e-06, + "loss": 1.3581, + "step": 6572 + }, + { + "epoch": 0.69, + "learning_rate": 5.326735855206328e-06, + "loss": 1.2926, + "step": 6573 + }, + { + "epoch": 0.69, + "learning_rate": 5.3235001966733965e-06, + "loss": 1.3933, + "step": 6574 + }, + { + "epoch": 0.69, + "learning_rate": 5.320265164671283e-06, + "loss": 1.4009, + "step": 6575 + }, + { + "epoch": 0.69, + "learning_rate": 5.3170307596333955e-06, + "loss": 1.4051, + "step": 6576 + }, + { + "epoch": 0.69, + "learning_rate": 5.313796981993054e-06, + "loss": 1.3448, + "step": 6577 + }, + { + "epoch": 0.69, + "learning_rate": 5.310563832183515e-06, + "loss": 1.3141, + "step": 6578 + }, + { + "epoch": 0.69, + "learning_rate": 5.307331310637929e-06, + "loss": 1.3658, + "step": 6579 + }, + { + "epoch": 0.69, + "learning_rate": 5.3040994177893725e-06, + "loss": 1.2881, + "step": 6580 + }, + { + "epoch": 0.69, + "learning_rate": 5.30086815407084e-06, + "loss": 1.3051, + "step": 6581 + }, + { + "epoch": 0.69, + "learning_rate": 5.297637519915231e-06, + "loss": 1.3353, + "step": 6582 + }, + { + "epoch": 0.69, + "learning_rate": 5.2944075157553754e-06, + "loss": 1.3997, + "step": 6583 + }, + { + "epoch": 0.69, + "learning_rate": 5.291178142024002e-06, + "loss": 1.3094, + "step": 6584 + }, + { + "epoch": 0.69, + "learning_rate": 5.287949399153769e-06, + "loss": 1.3384, + "step": 6585 + }, + { + "epoch": 0.69, + "learning_rate": 5.284721287577248e-06, + "loss": 1.3183, + "step": 6586 + }, + { + "epoch": 0.69, + "learning_rate": 5.281493807726916e-06, + "loss": 1.4433, + "step": 6587 + }, + { + "epoch": 0.69, + "learning_rate": 5.278266960035174e-06, + "loss": 1.3103, + "step": 6588 + }, + { + "epoch": 0.69, + "learning_rate": 5.275040744934343e-06, + "loss": 1.3478, + "step": 6589 + }, + { + "epoch": 0.69, + "learning_rate": 5.271815162856645e-06, + "loss": 1.2713, + "step": 6590 + }, + { + "epoch": 0.69, + "learning_rate": 5.268590214234233e-06, + "loss": 1.3697, + "step": 6591 + }, + { + "epoch": 0.69, + "learning_rate": 5.265365899499156e-06, + "loss": 1.6169, + "step": 6592 + }, + { + "epoch": 0.69, + "learning_rate": 5.262142219083398e-06, + "loss": 1.2988, + "step": 6593 + }, + { + "epoch": 0.69, + "learning_rate": 5.258919173418851e-06, + "loss": 1.515, + "step": 6594 + }, + { + "epoch": 0.69, + "learning_rate": 5.2556967629373125e-06, + "loss": 1.3704, + "step": 6595 + }, + { + "epoch": 0.69, + "learning_rate": 5.2524749880705075e-06, + "loss": 1.2404, + "step": 6596 + }, + { + "epoch": 0.69, + "learning_rate": 5.249253849250073e-06, + "loss": 1.2799, + "step": 6597 + }, + { + "epoch": 0.69, + "learning_rate": 5.246033346907553e-06, + "loss": 1.2876, + "step": 6598 + }, + { + "epoch": 0.69, + "learning_rate": 5.24281348147442e-06, + "loss": 1.3058, + "step": 6599 + }, + { + "epoch": 0.69, + "learning_rate": 5.239594253382043e-06, + "loss": 1.3347, + "step": 6600 + }, + { + "epoch": 0.69, + "learning_rate": 5.236375663061722e-06, + "loss": 1.3323, + "step": 6601 + }, + { + "epoch": 0.69, + "learning_rate": 5.23315771094467e-06, + "loss": 1.3254, + "step": 6602 + }, + { + "epoch": 0.69, + "learning_rate": 5.229940397461999e-06, + "loss": 1.3462, + "step": 6603 + }, + { + "epoch": 0.69, + "learning_rate": 5.226723723044753e-06, + "loss": 1.2901, + "step": 6604 + }, + { + "epoch": 0.69, + "learning_rate": 5.223507688123887e-06, + "loss": 1.3079, + "step": 6605 + }, + { + "epoch": 0.69, + "learning_rate": 5.220292293130258e-06, + "loss": 1.4282, + "step": 6606 + }, + { + "epoch": 0.69, + "learning_rate": 5.217077538494651e-06, + "loss": 1.3197, + "step": 6607 + }, + { + "epoch": 0.69, + "learning_rate": 5.213863424647765e-06, + "loss": 1.3581, + "step": 6608 + }, + { + "epoch": 0.69, + "learning_rate": 5.2106499520202005e-06, + "loss": 1.3322, + "step": 6609 + }, + { + "epoch": 0.69, + "learning_rate": 5.207437121042488e-06, + "loss": 1.3368, + "step": 6610 + }, + { + "epoch": 0.69, + "learning_rate": 5.204224932145056e-06, + "loss": 1.2771, + "step": 6611 + }, + { + "epoch": 0.69, + "learning_rate": 5.20101338575826e-06, + "loss": 1.2852, + "step": 6612 + }, + { + "epoch": 0.69, + "learning_rate": 5.197802482312369e-06, + "loss": 1.3733, + "step": 6613 + }, + { + "epoch": 0.69, + "learning_rate": 5.194592222237551e-06, + "loss": 1.3719, + "step": 6614 + }, + { + "epoch": 0.69, + "learning_rate": 5.191382605963906e-06, + "loss": 1.3658, + "step": 6615 + }, + { + "epoch": 0.69, + "learning_rate": 5.1881736339214415e-06, + "loss": 1.3261, + "step": 6616 + }, + { + "epoch": 0.69, + "learning_rate": 5.18496530654007e-06, + "loss": 1.3057, + "step": 6617 + }, + { + "epoch": 0.69, + "learning_rate": 5.181757624249635e-06, + "loss": 1.2665, + "step": 6618 + }, + { + "epoch": 0.69, + "learning_rate": 5.1785505874798716e-06, + "loss": 1.2839, + "step": 6619 + }, + { + "epoch": 0.69, + "learning_rate": 5.175344196660447e-06, + "loss": 1.3131, + "step": 6620 + }, + { + "epoch": 0.69, + "learning_rate": 5.1721384522209385e-06, + "loss": 1.3217, + "step": 6621 + }, + { + "epoch": 0.69, + "learning_rate": 5.168933354590825e-06, + "loss": 1.3306, + "step": 6622 + }, + { + "epoch": 0.69, + "learning_rate": 5.165728904199512e-06, + "loss": 1.3197, + "step": 6623 + }, + { + "epoch": 0.69, + "learning_rate": 5.1625251014763176e-06, + "loss": 1.3035, + "step": 6624 + }, + { + "epoch": 0.69, + "learning_rate": 5.1593219468504605e-06, + "loss": 1.2927, + "step": 6625 + }, + { + "epoch": 0.69, + "learning_rate": 5.156119440751086e-06, + "loss": 1.3333, + "step": 6626 + }, + { + "epoch": 0.69, + "learning_rate": 5.152917583607251e-06, + "loss": 1.3181, + "step": 6627 + }, + { + "epoch": 0.7, + "learning_rate": 5.149716375847913e-06, + "loss": 1.347, + "step": 6628 + }, + { + "epoch": 0.7, + "learning_rate": 5.14651581790196e-06, + "loss": 1.347, + "step": 6629 + }, + { + "epoch": 0.7, + "learning_rate": 5.143315910198179e-06, + "loss": 1.2892, + "step": 6630 + }, + { + "epoch": 0.7, + "learning_rate": 5.140116653165277e-06, + "loss": 1.2996, + "step": 6631 + }, + { + "epoch": 0.7, + "learning_rate": 5.136918047231876e-06, + "loss": 1.2802, + "step": 6632 + }, + { + "epoch": 0.7, + "learning_rate": 5.133720092826501e-06, + "loss": 1.2766, + "step": 6633 + }, + { + "epoch": 0.7, + "learning_rate": 5.130522790377598e-06, + "loss": 1.5365, + "step": 6634 + }, + { + "epoch": 0.7, + "learning_rate": 5.127326140313528e-06, + "loss": 1.4848, + "step": 6635 + }, + { + "epoch": 0.7, + "learning_rate": 5.124130143062551e-06, + "loss": 1.3712, + "step": 6636 + }, + { + "epoch": 0.7, + "learning_rate": 5.120934799052859e-06, + "loss": 1.3094, + "step": 6637 + }, + { + "epoch": 0.7, + "learning_rate": 5.1177401087125355e-06, + "loss": 1.272, + "step": 6638 + }, + { + "epoch": 0.7, + "learning_rate": 5.114546072469593e-06, + "loss": 1.2856, + "step": 6639 + }, + { + "epoch": 0.7, + "learning_rate": 5.111352690751952e-06, + "loss": 1.2886, + "step": 6640 + }, + { + "epoch": 0.7, + "learning_rate": 5.108159963987436e-06, + "loss": 1.277, + "step": 6641 + }, + { + "epoch": 0.7, + "learning_rate": 5.104967892603794e-06, + "loss": 1.3392, + "step": 6642 + }, + { + "epoch": 0.7, + "learning_rate": 5.101776477028684e-06, + "loss": 1.3036, + "step": 6643 + }, + { + "epoch": 0.7, + "learning_rate": 5.098585717689667e-06, + "loss": 1.4116, + "step": 6644 + }, + { + "epoch": 0.7, + "learning_rate": 5.095395615014226e-06, + "loss": 1.3437, + "step": 6645 + }, + { + "epoch": 0.7, + "learning_rate": 5.0922061694297565e-06, + "loss": 1.2608, + "step": 6646 + }, + { + "epoch": 0.7, + "learning_rate": 5.089017381363554e-06, + "loss": 1.2959, + "step": 6647 + }, + { + "epoch": 0.7, + "learning_rate": 5.085829251242844e-06, + "loss": 1.3508, + "step": 6648 + }, + { + "epoch": 0.7, + "learning_rate": 5.0826417794947455e-06, + "loss": 1.34, + "step": 6649 + }, + { + "epoch": 0.7, + "learning_rate": 5.0794549665463e-06, + "loss": 1.3092, + "step": 6650 + }, + { + "epoch": 0.7, + "learning_rate": 5.076268812824463e-06, + "loss": 1.3417, + "step": 6651 + }, + { + "epoch": 0.7, + "learning_rate": 5.073083318756092e-06, + "loss": 1.3424, + "step": 6652 + }, + { + "epoch": 0.7, + "learning_rate": 5.069898484767961e-06, + "loss": 1.3296, + "step": 6653 + }, + { + "epoch": 0.7, + "learning_rate": 5.066714311286762e-06, + "loss": 1.2852, + "step": 6654 + }, + { + "epoch": 0.7, + "learning_rate": 5.063530798739087e-06, + "loss": 1.3462, + "step": 6655 + }, + { + "epoch": 0.7, + "learning_rate": 5.06034794755145e-06, + "loss": 1.3615, + "step": 6656 + }, + { + "epoch": 0.7, + "learning_rate": 5.057165758150262e-06, + "loss": 1.245, + "step": 6657 + }, + { + "epoch": 0.7, + "learning_rate": 5.053984230961862e-06, + "loss": 1.201, + "step": 6658 + }, + { + "epoch": 0.7, + "learning_rate": 5.050803366412494e-06, + "loss": 1.331, + "step": 6659 + }, + { + "epoch": 0.7, + "learning_rate": 5.047623164928306e-06, + "loss": 1.3034, + "step": 6660 + }, + { + "epoch": 0.7, + "learning_rate": 5.044443626935367e-06, + "loss": 1.2822, + "step": 6661 + }, + { + "epoch": 0.7, + "learning_rate": 5.041264752859657e-06, + "loss": 1.2576, + "step": 6662 + }, + { + "epoch": 0.7, + "learning_rate": 5.038086543127055e-06, + "loss": 1.3198, + "step": 6663 + }, + { + "epoch": 0.7, + "learning_rate": 5.034908998163368e-06, + "loss": 1.2892, + "step": 6664 + }, + { + "epoch": 0.7, + "learning_rate": 5.031732118394299e-06, + "loss": 1.3004, + "step": 6665 + }, + { + "epoch": 0.7, + "learning_rate": 5.028555904245469e-06, + "loss": 1.3178, + "step": 6666 + }, + { + "epoch": 0.7, + "learning_rate": 5.0253803561424156e-06, + "loss": 1.3014, + "step": 6667 + }, + { + "epoch": 0.7, + "learning_rate": 5.022205474510571e-06, + "loss": 1.3151, + "step": 6668 + }, + { + "epoch": 0.7, + "learning_rate": 5.019031259775292e-06, + "loss": 1.3551, + "step": 6669 + }, + { + "epoch": 0.7, + "learning_rate": 5.015857712361847e-06, + "loss": 1.4188, + "step": 6670 + }, + { + "epoch": 0.7, + "learning_rate": 5.0126848326954025e-06, + "loss": 1.2743, + "step": 6671 + }, + { + "epoch": 0.7, + "learning_rate": 5.009512621201043e-06, + "loss": 1.3528, + "step": 6672 + }, + { + "epoch": 0.7, + "learning_rate": 5.006341078303771e-06, + "loss": 1.309, + "step": 6673 + }, + { + "epoch": 0.7, + "learning_rate": 5.003170204428483e-06, + "loss": 1.3353, + "step": 6674 + }, + { + "epoch": 0.7, + "learning_rate": 5.000000000000003e-06, + "loss": 1.2753, + "step": 6675 + }, + { + "epoch": 0.7, + "learning_rate": 4.9968304654430465e-06, + "loss": 1.3907, + "step": 6676 + }, + { + "epoch": 0.7, + "learning_rate": 4.993661601182256e-06, + "loss": 1.2876, + "step": 6677 + }, + { + "epoch": 0.7, + "learning_rate": 4.990493407642181e-06, + "loss": 1.2534, + "step": 6678 + }, + { + "epoch": 0.7, + "learning_rate": 4.98732588524727e-06, + "loss": 1.3352, + "step": 6679 + }, + { + "epoch": 0.7, + "learning_rate": 4.984159034421895e-06, + "loss": 1.3302, + "step": 6680 + }, + { + "epoch": 0.7, + "learning_rate": 4.980992855590336e-06, + "loss": 1.3783, + "step": 6681 + }, + { + "epoch": 0.7, + "learning_rate": 4.977827349176769e-06, + "loss": 1.2848, + "step": 6682 + }, + { + "epoch": 0.7, + "learning_rate": 4.974662515605302e-06, + "loss": 1.3269, + "step": 6683 + }, + { + "epoch": 0.7, + "learning_rate": 4.971498355299932e-06, + "loss": 1.3662, + "step": 6684 + }, + { + "epoch": 0.7, + "learning_rate": 4.968334868684579e-06, + "loss": 1.2508, + "step": 6685 + }, + { + "epoch": 0.7, + "learning_rate": 4.965172056183073e-06, + "loss": 1.3872, + "step": 6686 + }, + { + "epoch": 0.7, + "learning_rate": 4.962009918219142e-06, + "loss": 1.3008, + "step": 6687 + }, + { + "epoch": 0.7, + "learning_rate": 4.958848455216434e-06, + "loss": 1.2058, + "step": 6688 + }, + { + "epoch": 0.7, + "learning_rate": 4.95568766759851e-06, + "loss": 1.3127, + "step": 6689 + }, + { + "epoch": 0.7, + "learning_rate": 4.952527555788825e-06, + "loss": 1.2985, + "step": 6690 + }, + { + "epoch": 0.7, + "learning_rate": 4.949368120210757e-06, + "loss": 1.333, + "step": 6691 + }, + { + "epoch": 0.7, + "learning_rate": 4.946209361287593e-06, + "loss": 1.2945, + "step": 6692 + }, + { + "epoch": 0.7, + "learning_rate": 4.943051279442516e-06, + "loss": 1.262, + "step": 6693 + }, + { + "epoch": 0.7, + "learning_rate": 4.93989387509864e-06, + "loss": 1.6155, + "step": 6694 + }, + { + "epoch": 0.7, + "learning_rate": 4.936737148678965e-06, + "loss": 1.2838, + "step": 6695 + }, + { + "epoch": 0.7, + "learning_rate": 4.933581100606415e-06, + "loss": 1.3778, + "step": 6696 + }, + { + "epoch": 0.7, + "learning_rate": 4.930425731303824e-06, + "loss": 1.3624, + "step": 6697 + }, + { + "epoch": 0.7, + "learning_rate": 4.927271041193923e-06, + "loss": 1.2641, + "step": 6698 + }, + { + "epoch": 0.7, + "learning_rate": 4.924117030699362e-06, + "loss": 1.3314, + "step": 6699 + }, + { + "epoch": 0.7, + "learning_rate": 4.920963700242704e-06, + "loss": 1.328, + "step": 6700 + }, + { + "epoch": 0.7, + "learning_rate": 4.917811050246404e-06, + "loss": 1.3128, + "step": 6701 + }, + { + "epoch": 0.7, + "learning_rate": 4.914659081132843e-06, + "loss": 1.3877, + "step": 6702 + }, + { + "epoch": 0.7, + "learning_rate": 4.911507793324299e-06, + "loss": 1.3114, + "step": 6703 + }, + { + "epoch": 0.7, + "learning_rate": 4.908357187242967e-06, + "loss": 1.3592, + "step": 6704 + }, + { + "epoch": 0.7, + "learning_rate": 4.905207263310948e-06, + "loss": 1.329, + "step": 6705 + }, + { + "epoch": 0.7, + "learning_rate": 4.902058021950247e-06, + "loss": 1.2558, + "step": 6706 + }, + { + "epoch": 0.7, + "learning_rate": 4.898909463582784e-06, + "loss": 1.2489, + "step": 6707 + }, + { + "epoch": 0.7, + "learning_rate": 4.895761588630388e-06, + "loss": 1.2817, + "step": 6708 + }, + { + "epoch": 0.7, + "learning_rate": 4.892614397514785e-06, + "loss": 1.1606, + "step": 6709 + }, + { + "epoch": 0.7, + "learning_rate": 4.889467890657628e-06, + "loss": 1.2878, + "step": 6710 + }, + { + "epoch": 0.7, + "learning_rate": 4.886322068480458e-06, + "loss": 1.2747, + "step": 6711 + }, + { + "epoch": 0.7, + "learning_rate": 4.88317693140474e-06, + "loss": 1.3662, + "step": 6712 + }, + { + "epoch": 0.7, + "learning_rate": 4.880032479851844e-06, + "loss": 1.3009, + "step": 6713 + }, + { + "epoch": 0.7, + "learning_rate": 4.8768887142430385e-06, + "loss": 1.3157, + "step": 6714 + }, + { + "epoch": 0.7, + "learning_rate": 4.873745634999511e-06, + "loss": 1.4461, + "step": 6715 + }, + { + "epoch": 0.7, + "learning_rate": 4.870603242542358e-06, + "loss": 1.3818, + "step": 6716 + }, + { + "epoch": 0.7, + "learning_rate": 4.86746153729257e-06, + "loss": 1.3361, + "step": 6717 + }, + { + "epoch": 0.7, + "learning_rate": 4.864320519671061e-06, + "loss": 1.3147, + "step": 6718 + }, + { + "epoch": 0.7, + "learning_rate": 4.8611801900986485e-06, + "loss": 1.3773, + "step": 6719 + }, + { + "epoch": 0.7, + "learning_rate": 4.858040548996049e-06, + "loss": 1.3091, + "step": 6720 + }, + { + "epoch": 0.7, + "learning_rate": 4.854901596783902e-06, + "loss": 1.3314, + "step": 6721 + }, + { + "epoch": 0.7, + "learning_rate": 4.851763333882738e-06, + "loss": 1.3082, + "step": 6722 + }, + { + "epoch": 0.71, + "learning_rate": 4.848625760713007e-06, + "loss": 1.2687, + "step": 6723 + }, + { + "epoch": 0.71, + "learning_rate": 4.845488877695068e-06, + "loss": 1.3378, + "step": 6724 + }, + { + "epoch": 0.71, + "learning_rate": 4.842352685249174e-06, + "loss": 1.3516, + "step": 6725 + }, + { + "epoch": 0.71, + "learning_rate": 4.839217183795501e-06, + "loss": 1.4083, + "step": 6726 + }, + { + "epoch": 0.71, + "learning_rate": 4.836082373754124e-06, + "loss": 1.3073, + "step": 6727 + }, + { + "epoch": 0.71, + "learning_rate": 4.832948255545024e-06, + "loss": 1.2948, + "step": 6728 + }, + { + "epoch": 0.71, + "learning_rate": 4.829814829588099e-06, + "loss": 1.3323, + "step": 6729 + }, + { + "epoch": 0.71, + "learning_rate": 4.826682096303139e-06, + "loss": 1.3101, + "step": 6730 + }, + { + "epoch": 0.71, + "learning_rate": 4.823550056109853e-06, + "loss": 1.3323, + "step": 6731 + }, + { + "epoch": 0.71, + "learning_rate": 4.8204187094278605e-06, + "loss": 1.3862, + "step": 6732 + }, + { + "epoch": 0.71, + "learning_rate": 4.817288056676671e-06, + "loss": 1.3112, + "step": 6733 + }, + { + "epoch": 0.71, + "learning_rate": 4.8141580982757175e-06, + "loss": 1.297, + "step": 6734 + }, + { + "epoch": 0.71, + "learning_rate": 4.811028834644336e-06, + "loss": 1.2604, + "step": 6735 + }, + { + "epoch": 0.71, + "learning_rate": 4.807900266201761e-06, + "loss": 1.343, + "step": 6736 + }, + { + "epoch": 0.71, + "learning_rate": 4.804772393367142e-06, + "loss": 1.3254, + "step": 6737 + }, + { + "epoch": 0.71, + "learning_rate": 4.80164521655954e-06, + "loss": 1.2688, + "step": 6738 + }, + { + "epoch": 0.71, + "learning_rate": 4.798518736197909e-06, + "loss": 1.2693, + "step": 6739 + }, + { + "epoch": 0.71, + "learning_rate": 4.795392952701122e-06, + "loss": 1.4536, + "step": 6740 + }, + { + "epoch": 0.71, + "learning_rate": 4.7922678664879485e-06, + "loss": 1.3811, + "step": 6741 + }, + { + "epoch": 0.71, + "learning_rate": 4.789143477977072e-06, + "loss": 1.2584, + "step": 6742 + }, + { + "epoch": 0.71, + "learning_rate": 4.786019787587084e-06, + "loss": 1.2584, + "step": 6743 + }, + { + "epoch": 0.71, + "learning_rate": 4.782896795736472e-06, + "loss": 1.2005, + "step": 6744 + }, + { + "epoch": 0.71, + "learning_rate": 4.779774502843642e-06, + "loss": 1.335, + "step": 6745 + }, + { + "epoch": 0.71, + "learning_rate": 4.776652909326901e-06, + "loss": 1.3675, + "step": 6746 + }, + { + "epoch": 0.71, + "learning_rate": 4.773532015604457e-06, + "loss": 1.3794, + "step": 6747 + }, + { + "epoch": 0.71, + "learning_rate": 4.770411822094437e-06, + "loss": 1.3629, + "step": 6748 + }, + { + "epoch": 0.71, + "learning_rate": 4.76729232921486e-06, + "loss": 1.0805, + "step": 6749 + }, + { + "epoch": 0.71, + "learning_rate": 4.76417353738366e-06, + "loss": 1.2874, + "step": 6750 + }, + { + "epoch": 0.71, + "learning_rate": 4.761055447018681e-06, + "loss": 1.428, + "step": 6751 + }, + { + "epoch": 0.71, + "learning_rate": 4.757938058537656e-06, + "loss": 1.2935, + "step": 6752 + }, + { + "epoch": 0.71, + "learning_rate": 4.754821372358242e-06, + "loss": 1.4202, + "step": 6753 + }, + { + "epoch": 0.71, + "learning_rate": 4.751705388897997e-06, + "loss": 1.3109, + "step": 6754 + }, + { + "epoch": 0.71, + "learning_rate": 4.7485901085743754e-06, + "loss": 1.3319, + "step": 6755 + }, + { + "epoch": 0.71, + "learning_rate": 4.745475531804753e-06, + "loss": 1.3246, + "step": 6756 + }, + { + "epoch": 0.71, + "learning_rate": 4.742361659006395e-06, + "loss": 1.3407, + "step": 6757 + }, + { + "epoch": 0.71, + "learning_rate": 4.739248490596483e-06, + "loss": 1.2953, + "step": 6758 + }, + { + "epoch": 0.71, + "learning_rate": 4.736136026992107e-06, + "loss": 1.3214, + "step": 6759 + }, + { + "epoch": 0.71, + "learning_rate": 4.733024268610249e-06, + "loss": 1.4112, + "step": 6760 + }, + { + "epoch": 0.71, + "learning_rate": 4.7299132158678085e-06, + "loss": 1.2981, + "step": 6761 + }, + { + "epoch": 0.71, + "learning_rate": 4.726802869181591e-06, + "loss": 1.2975, + "step": 6762 + }, + { + "epoch": 0.71, + "learning_rate": 4.723693228968293e-06, + "loss": 1.3047, + "step": 6763 + }, + { + "epoch": 0.71, + "learning_rate": 4.720584295644533e-06, + "loss": 1.3906, + "step": 6764 + }, + { + "epoch": 0.71, + "learning_rate": 4.717476069626832e-06, + "loss": 1.2523, + "step": 6765 + }, + { + "epoch": 0.71, + "learning_rate": 4.7143685513316025e-06, + "loss": 1.0453, + "step": 6766 + }, + { + "epoch": 0.71, + "eval_loss": 1.4004828929901123, + "eval_runtime": 77.565, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 6766 + }, + { + "epoch": 0.71, + "learning_rate": 4.711261741175182e-06, + "loss": 1.1339, + "step": 6767 + }, + { + "epoch": 0.71, + "learning_rate": 4.7081556395737935e-06, + "loss": 1.2401, + "step": 6768 + }, + { + "epoch": 0.71, + "learning_rate": 4.705050246943581e-06, + "loss": 1.3009, + "step": 6769 + }, + { + "epoch": 0.71, + "learning_rate": 4.7019455637005895e-06, + "loss": 1.3106, + "step": 6770 + }, + { + "epoch": 0.71, + "learning_rate": 4.698841590260758e-06, + "loss": 1.3021, + "step": 6771 + }, + { + "epoch": 0.71, + "learning_rate": 4.695738327039947e-06, + "loss": 1.3147, + "step": 6772 + }, + { + "epoch": 0.71, + "learning_rate": 4.692635774453914e-06, + "loss": 1.238, + "step": 6773 + }, + { + "epoch": 0.71, + "learning_rate": 4.6895339329183154e-06, + "loss": 1.3876, + "step": 6774 + }, + { + "epoch": 0.71, + "learning_rate": 4.686432802848726e-06, + "loss": 1.3012, + "step": 6775 + }, + { + "epoch": 0.71, + "learning_rate": 4.68333238466061e-06, + "loss": 1.1421, + "step": 6776 + }, + { + "epoch": 0.71, + "learning_rate": 4.6802326787693455e-06, + "loss": 1.2838, + "step": 6777 + }, + { + "epoch": 0.71, + "learning_rate": 4.677133685590219e-06, + "loss": 1.3725, + "step": 6778 + }, + { + "epoch": 0.71, + "learning_rate": 4.674035405538409e-06, + "loss": 1.3093, + "step": 6779 + }, + { + "epoch": 0.71, + "learning_rate": 4.6709378390290085e-06, + "loss": 1.2785, + "step": 6780 + }, + { + "epoch": 0.71, + "learning_rate": 4.667840986477015e-06, + "loss": 1.2513, + "step": 6781 + }, + { + "epoch": 0.71, + "learning_rate": 4.66474484829732e-06, + "loss": 1.2903, + "step": 6782 + }, + { + "epoch": 0.71, + "learning_rate": 4.661649424904732e-06, + "loss": 1.4217, + "step": 6783 + }, + { + "epoch": 0.71, + "learning_rate": 4.658554716713959e-06, + "loss": 1.337, + "step": 6784 + }, + { + "epoch": 0.71, + "learning_rate": 4.655460724139605e-06, + "loss": 1.2978, + "step": 6785 + }, + { + "epoch": 0.71, + "learning_rate": 4.652367447596197e-06, + "loss": 1.3036, + "step": 6786 + }, + { + "epoch": 0.71, + "learning_rate": 4.6492748874981415e-06, + "loss": 1.2889, + "step": 6787 + }, + { + "epoch": 0.71, + "learning_rate": 4.646183044259771e-06, + "loss": 1.3046, + "step": 6788 + }, + { + "epoch": 0.71, + "learning_rate": 4.643091918295312e-06, + "loss": 1.3483, + "step": 6789 + }, + { + "epoch": 0.71, + "learning_rate": 4.640001510018893e-06, + "loss": 1.3862, + "step": 6790 + }, + { + "epoch": 0.71, + "learning_rate": 4.6369118198445505e-06, + "loss": 1.2483, + "step": 6791 + }, + { + "epoch": 0.71, + "learning_rate": 4.633822848186228e-06, + "loss": 1.2669, + "step": 6792 + }, + { + "epoch": 0.71, + "learning_rate": 4.63073459545776e-06, + "loss": 1.3535, + "step": 6793 + }, + { + "epoch": 0.71, + "learning_rate": 4.627647062072902e-06, + "loss": 1.2742, + "step": 6794 + }, + { + "epoch": 0.71, + "learning_rate": 4.624560248445295e-06, + "loss": 1.3429, + "step": 6795 + }, + { + "epoch": 0.71, + "learning_rate": 4.621474154988498e-06, + "loss": 1.3548, + "step": 6796 + }, + { + "epoch": 0.71, + "learning_rate": 4.61838878211597e-06, + "loss": 1.2722, + "step": 6797 + }, + { + "epoch": 0.71, + "learning_rate": 4.6153041302410665e-06, + "loss": 1.3357, + "step": 6798 + }, + { + "epoch": 0.71, + "learning_rate": 4.612220199777053e-06, + "loss": 1.2494, + "step": 6799 + }, + { + "epoch": 0.71, + "learning_rate": 4.609136991137103e-06, + "loss": 1.2792, + "step": 6800 + }, + { + "epoch": 0.71, + "learning_rate": 4.60605450473428e-06, + "loss": 1.2892, + "step": 6801 + }, + { + "epoch": 0.71, + "learning_rate": 4.602972740981562e-06, + "loss": 1.316, + "step": 6802 + }, + { + "epoch": 0.71, + "learning_rate": 4.599891700291822e-06, + "loss": 1.3017, + "step": 6803 + }, + { + "epoch": 0.71, + "learning_rate": 4.5968113830778416e-06, + "loss": 1.3133, + "step": 6804 + }, + { + "epoch": 0.71, + "learning_rate": 4.593731789752311e-06, + "loss": 1.3768, + "step": 6805 + }, + { + "epoch": 0.71, + "learning_rate": 4.590652920727806e-06, + "loss": 1.3259, + "step": 6806 + }, + { + "epoch": 0.71, + "learning_rate": 4.5875747764168214e-06, + "loss": 1.328, + "step": 6807 + }, + { + "epoch": 0.71, + "learning_rate": 4.584497357231752e-06, + "loss": 1.2924, + "step": 6808 + }, + { + "epoch": 0.71, + "learning_rate": 4.581420663584886e-06, + "loss": 1.3347, + "step": 6809 + }, + { + "epoch": 0.71, + "learning_rate": 4.578344695888427e-06, + "loss": 1.3042, + "step": 6810 + }, + { + "epoch": 0.71, + "learning_rate": 4.575269454554477e-06, + "loss": 1.3121, + "step": 6811 + }, + { + "epoch": 0.71, + "learning_rate": 4.572194939995031e-06, + "loss": 1.3471, + "step": 6812 + }, + { + "epoch": 0.71, + "learning_rate": 4.569121152622005e-06, + "loss": 1.4279, + "step": 6813 + }, + { + "epoch": 0.71, + "learning_rate": 4.5660480928471985e-06, + "loss": 1.2902, + "step": 6814 + }, + { + "epoch": 0.71, + "learning_rate": 4.562975761082326e-06, + "loss": 1.0803, + "step": 6815 + }, + { + "epoch": 0.71, + "learning_rate": 4.5599041577390065e-06, + "loss": 1.008, + "step": 6816 + }, + { + "epoch": 0.71, + "learning_rate": 4.556833283228748e-06, + "loss": 1.168, + "step": 6817 + }, + { + "epoch": 0.71, + "learning_rate": 4.553763137962971e-06, + "loss": 1.3092, + "step": 6818 + }, + { + "epoch": 0.72, + "learning_rate": 4.550693722353001e-06, + "loss": 1.364, + "step": 6819 + }, + { + "epoch": 0.72, + "learning_rate": 4.547625036810052e-06, + "loss": 1.3079, + "step": 6820 + }, + { + "epoch": 0.72, + "learning_rate": 4.544557081745259e-06, + "loss": 1.2639, + "step": 6821 + }, + { + "epoch": 0.72, + "learning_rate": 4.541489857569639e-06, + "loss": 1.3586, + "step": 6822 + }, + { + "epoch": 0.72, + "learning_rate": 4.5384233646941275e-06, + "loss": 1.4261, + "step": 6823 + }, + { + "epoch": 0.72, + "learning_rate": 4.535357603529558e-06, + "loss": 1.428, + "step": 6824 + }, + { + "epoch": 0.72, + "learning_rate": 4.532292574486656e-06, + "loss": 1.2541, + "step": 6825 + }, + { + "epoch": 0.72, + "learning_rate": 4.529228277976061e-06, + "loss": 1.2761, + "step": 6826 + }, + { + "epoch": 0.72, + "learning_rate": 4.526164714408314e-06, + "loss": 1.3439, + "step": 6827 + }, + { + "epoch": 0.72, + "learning_rate": 4.523101884193845e-06, + "loss": 1.3585, + "step": 6828 + }, + { + "epoch": 0.72, + "learning_rate": 4.520039787742999e-06, + "loss": 1.4035, + "step": 6829 + }, + { + "epoch": 0.72, + "learning_rate": 4.516978425466023e-06, + "loss": 1.3328, + "step": 6830 + }, + { + "epoch": 0.72, + "learning_rate": 4.5139177977730516e-06, + "loss": 1.2931, + "step": 6831 + }, + { + "epoch": 0.72, + "learning_rate": 4.5108579050741395e-06, + "loss": 1.2515, + "step": 6832 + }, + { + "epoch": 0.72, + "learning_rate": 4.507798747779226e-06, + "loss": 1.3178, + "step": 6833 + }, + { + "epoch": 0.72, + "learning_rate": 4.504740326298163e-06, + "loss": 1.3037, + "step": 6834 + }, + { + "epoch": 0.72, + "learning_rate": 4.501682641040702e-06, + "loss": 1.14, + "step": 6835 + }, + { + "epoch": 0.72, + "learning_rate": 4.4986256924164895e-06, + "loss": 1.2801, + "step": 6836 + }, + { + "epoch": 0.72, + "learning_rate": 4.495569480835081e-06, + "loss": 1.3195, + "step": 6837 + }, + { + "epoch": 0.72, + "learning_rate": 4.492514006705935e-06, + "loss": 1.2949, + "step": 6838 + }, + { + "epoch": 0.72, + "learning_rate": 4.489459270438397e-06, + "loss": 1.3297, + "step": 6839 + }, + { + "epoch": 0.72, + "learning_rate": 4.4864052724417315e-06, + "loss": 1.2127, + "step": 6840 + }, + { + "epoch": 0.72, + "learning_rate": 4.4833520131250894e-06, + "loss": 1.3124, + "step": 6841 + }, + { + "epoch": 0.72, + "learning_rate": 4.480299492897532e-06, + "loss": 1.3056, + "step": 6842 + }, + { + "epoch": 0.72, + "learning_rate": 4.477247712168021e-06, + "loss": 1.2853, + "step": 6843 + }, + { + "epoch": 0.72, + "learning_rate": 4.474196671345411e-06, + "loss": 1.2531, + "step": 6844 + }, + { + "epoch": 0.72, + "learning_rate": 4.471146370838466e-06, + "loss": 1.2712, + "step": 6845 + }, + { + "epoch": 0.72, + "learning_rate": 4.468096811055852e-06, + "loss": 1.3443, + "step": 6846 + }, + { + "epoch": 0.72, + "learning_rate": 4.465047992406124e-06, + "loss": 1.2692, + "step": 6847 + }, + { + "epoch": 0.72, + "learning_rate": 4.461999915297752e-06, + "loss": 1.3937, + "step": 6848 + }, + { + "epoch": 0.72, + "learning_rate": 4.458952580139094e-06, + "loss": 1.2743, + "step": 6849 + }, + { + "epoch": 0.72, + "learning_rate": 4.455905987338418e-06, + "loss": 1.3949, + "step": 6850 + }, + { + "epoch": 0.72, + "learning_rate": 4.452860137303892e-06, + "loss": 1.2578, + "step": 6851 + }, + { + "epoch": 0.72, + "learning_rate": 4.449815030443575e-06, + "loss": 1.3199, + "step": 6852 + }, + { + "epoch": 0.72, + "learning_rate": 4.4467706671654365e-06, + "loss": 1.3199, + "step": 6853 + }, + { + "epoch": 0.72, + "learning_rate": 4.4437270478773464e-06, + "loss": 1.3098, + "step": 6854 + }, + { + "epoch": 0.72, + "learning_rate": 4.440684172987064e-06, + "loss": 1.2888, + "step": 6855 + }, + { + "epoch": 0.72, + "learning_rate": 4.4376420429022615e-06, + "loss": 1.646, + "step": 6856 + }, + { + "epoch": 0.72, + "learning_rate": 4.434600658030508e-06, + "loss": 1.3573, + "step": 6857 + }, + { + "epoch": 0.72, + "learning_rate": 4.431560018779264e-06, + "loss": 1.3748, + "step": 6858 + }, + { + "epoch": 0.72, + "learning_rate": 4.428520125555906e-06, + "loss": 1.358, + "step": 6859 + }, + { + "epoch": 0.72, + "learning_rate": 4.425480978767692e-06, + "loss": 1.2707, + "step": 6860 + }, + { + "epoch": 0.72, + "learning_rate": 4.422442578821795e-06, + "loss": 1.4066, + "step": 6861 + }, + { + "epoch": 0.72, + "learning_rate": 4.4194049261252845e-06, + "loss": 1.3725, + "step": 6862 + }, + { + "epoch": 0.72, + "learning_rate": 4.416368021085122e-06, + "loss": 1.2392, + "step": 6863 + }, + { + "epoch": 0.72, + "learning_rate": 4.413331864108178e-06, + "loss": 1.2917, + "step": 6864 + }, + { + "epoch": 0.72, + "learning_rate": 4.410296455601223e-06, + "loss": 1.2685, + "step": 6865 + }, + { + "epoch": 0.72, + "learning_rate": 4.407261795970916e-06, + "loss": 1.265, + "step": 6866 + }, + { + "epoch": 0.72, + "learning_rate": 4.404227885623832e-06, + "loss": 1.3838, + "step": 6867 + }, + { + "epoch": 0.72, + "learning_rate": 4.4011947249664276e-06, + "loss": 1.3496, + "step": 6868 + }, + { + "epoch": 0.72, + "learning_rate": 4.398162314405075e-06, + "loss": 1.3007, + "step": 6869 + }, + { + "epoch": 0.72, + "learning_rate": 4.39513065434604e-06, + "loss": 1.2934, + "step": 6870 + }, + { + "epoch": 0.72, + "learning_rate": 4.392099745195483e-06, + "loss": 1.559, + "step": 6871 + }, + { + "epoch": 0.72, + "learning_rate": 4.389069587359468e-06, + "loss": 1.346, + "step": 6872 + }, + { + "epoch": 0.72, + "learning_rate": 4.386040181243965e-06, + "loss": 1.2433, + "step": 6873 + }, + { + "epoch": 0.72, + "learning_rate": 4.3830115272548275e-06, + "loss": 1.2938, + "step": 6874 + }, + { + "epoch": 0.72, + "learning_rate": 4.379983625797821e-06, + "loss": 1.3463, + "step": 6875 + }, + { + "epoch": 0.72, + "learning_rate": 4.376956477278612e-06, + "loss": 1.2832, + "step": 6876 + }, + { + "epoch": 0.72, + "learning_rate": 4.37393008210275e-06, + "loss": 1.3693, + "step": 6877 + }, + { + "epoch": 0.72, + "learning_rate": 4.370904440675705e-06, + "loss": 1.2652, + "step": 6878 + }, + { + "epoch": 0.72, + "learning_rate": 4.367879553402826e-06, + "loss": 1.3217, + "step": 6879 + }, + { + "epoch": 0.72, + "learning_rate": 4.364855420689375e-06, + "loss": 1.3519, + "step": 6880 + }, + { + "epoch": 0.72, + "learning_rate": 4.36183204294051e-06, + "loss": 1.3131, + "step": 6881 + }, + { + "epoch": 0.72, + "learning_rate": 4.35880942056128e-06, + "loss": 1.4334, + "step": 6882 + }, + { + "epoch": 0.72, + "learning_rate": 4.3557875539566415e-06, + "loss": 1.259, + "step": 6883 + }, + { + "epoch": 0.72, + "learning_rate": 4.352766443531451e-06, + "loss": 1.2841, + "step": 6884 + }, + { + "epoch": 0.72, + "learning_rate": 4.349746089690453e-06, + "loss": 1.35, + "step": 6885 + }, + { + "epoch": 0.72, + "learning_rate": 4.346726492838304e-06, + "loss": 1.3623, + "step": 6886 + }, + { + "epoch": 0.72, + "learning_rate": 4.343707653379544e-06, + "loss": 1.3729, + "step": 6887 + }, + { + "epoch": 0.72, + "learning_rate": 4.340689571718626e-06, + "loss": 1.2992, + "step": 6888 + }, + { + "epoch": 0.72, + "learning_rate": 4.337672248259898e-06, + "loss": 1.3484, + "step": 6889 + }, + { + "epoch": 0.72, + "learning_rate": 4.334655683407594e-06, + "loss": 1.3347, + "step": 6890 + }, + { + "epoch": 0.72, + "learning_rate": 4.331639877565865e-06, + "loss": 1.2986, + "step": 6891 + }, + { + "epoch": 0.72, + "learning_rate": 4.328624831138751e-06, + "loss": 1.3217, + "step": 6892 + }, + { + "epoch": 0.72, + "learning_rate": 4.325610544530184e-06, + "loss": 1.2834, + "step": 6893 + }, + { + "epoch": 0.72, + "learning_rate": 4.32259701814401e-06, + "loss": 1.3474, + "step": 6894 + }, + { + "epoch": 0.72, + "learning_rate": 4.319584252383956e-06, + "loss": 1.2871, + "step": 6895 + }, + { + "epoch": 0.72, + "learning_rate": 4.316572247653659e-06, + "loss": 1.3534, + "step": 6896 + }, + { + "epoch": 0.72, + "learning_rate": 4.313561004356653e-06, + "loss": 1.4421, + "step": 6897 + }, + { + "epoch": 0.72, + "learning_rate": 4.310550522896359e-06, + "loss": 1.3091, + "step": 6898 + }, + { + "epoch": 0.72, + "learning_rate": 4.30754080367611e-06, + "loss": 1.2565, + "step": 6899 + }, + { + "epoch": 0.72, + "learning_rate": 4.304531847099135e-06, + "loss": 1.5767, + "step": 6900 + }, + { + "epoch": 0.72, + "learning_rate": 4.3015236535685475e-06, + "loss": 1.4257, + "step": 6901 + }, + { + "epoch": 0.72, + "learning_rate": 4.298516223487373e-06, + "loss": 1.362, + "step": 6902 + }, + { + "epoch": 0.72, + "learning_rate": 4.2955095572585336e-06, + "loss": 1.3475, + "step": 6903 + }, + { + "epoch": 0.72, + "learning_rate": 4.292503655284838e-06, + "loss": 1.3223, + "step": 6904 + }, + { + "epoch": 0.72, + "learning_rate": 4.289498517969006e-06, + "loss": 1.3142, + "step": 6905 + }, + { + "epoch": 0.72, + "learning_rate": 4.286494145713644e-06, + "loss": 1.3124, + "step": 6906 + }, + { + "epoch": 0.72, + "learning_rate": 4.283490538921261e-06, + "loss": 1.3636, + "step": 6907 + }, + { + "epoch": 0.72, + "learning_rate": 4.280487697994269e-06, + "loss": 1.347, + "step": 6908 + }, + { + "epoch": 0.72, + "learning_rate": 4.277485623334964e-06, + "loss": 1.2986, + "step": 6909 + }, + { + "epoch": 0.72, + "learning_rate": 4.27448431534555e-06, + "loss": 1.3058, + "step": 6910 + }, + { + "epoch": 0.72, + "learning_rate": 4.271483774428128e-06, + "loss": 1.7858, + "step": 6911 + }, + { + "epoch": 0.72, + "learning_rate": 4.268484000984689e-06, + "loss": 1.3529, + "step": 6912 + }, + { + "epoch": 0.72, + "learning_rate": 4.26548499541713e-06, + "loss": 1.3215, + "step": 6913 + }, + { + "epoch": 0.73, + "learning_rate": 4.262486758127234e-06, + "loss": 1.2914, + "step": 6914 + }, + { + "epoch": 0.73, + "learning_rate": 4.259489289516693e-06, + "loss": 1.4562, + "step": 6915 + }, + { + "epoch": 0.73, + "learning_rate": 4.256492589987092e-06, + "loss": 1.2548, + "step": 6916 + }, + { + "epoch": 0.73, + "learning_rate": 4.253496659939907e-06, + "loss": 1.3047, + "step": 6917 + }, + { + "epoch": 0.73, + "learning_rate": 4.250501499776516e-06, + "loss": 1.4184, + "step": 6918 + }, + { + "epoch": 0.73, + "learning_rate": 4.2475071098982e-06, + "loss": 1.3519, + "step": 6919 + }, + { + "epoch": 0.73, + "learning_rate": 4.2445134907061224e-06, + "loss": 1.3274, + "step": 6920 + }, + { + "epoch": 0.73, + "learning_rate": 4.2415206426013545e-06, + "loss": 1.389, + "step": 6921 + }, + { + "epoch": 0.73, + "learning_rate": 4.238528565984865e-06, + "loss": 1.2929, + "step": 6922 + }, + { + "epoch": 0.73, + "learning_rate": 4.235537261257507e-06, + "loss": 1.3883, + "step": 6923 + }, + { + "epoch": 0.73, + "learning_rate": 4.232546728820047e-06, + "loss": 1.3395, + "step": 6924 + }, + { + "epoch": 0.73, + "learning_rate": 4.229556969073133e-06, + "loss": 1.3534, + "step": 6925 + }, + { + "epoch": 0.73, + "learning_rate": 4.226567982417317e-06, + "loss": 1.4218, + "step": 6926 + }, + { + "epoch": 0.73, + "learning_rate": 4.223579769253052e-06, + "loss": 1.3737, + "step": 6927 + }, + { + "epoch": 0.73, + "learning_rate": 4.220592329980674e-06, + "loss": 1.4805, + "step": 6928 + }, + { + "epoch": 0.73, + "learning_rate": 4.217605665000426e-06, + "loss": 1.2409, + "step": 6929 + }, + { + "epoch": 0.73, + "learning_rate": 4.21461977471245e-06, + "loss": 1.3375, + "step": 6930 + }, + { + "epoch": 0.73, + "learning_rate": 4.211634659516769e-06, + "loss": 1.3535, + "step": 6931 + }, + { + "epoch": 0.73, + "learning_rate": 4.20865031981332e-06, + "loss": 1.2723, + "step": 6932 + }, + { + "epoch": 0.73, + "learning_rate": 4.2056667560019206e-06, + "loss": 1.342, + "step": 6933 + }, + { + "epoch": 0.73, + "learning_rate": 4.202683968482296e-06, + "loss": 1.4075, + "step": 6934 + }, + { + "epoch": 0.73, + "learning_rate": 4.199701957654065e-06, + "loss": 1.3003, + "step": 6935 + }, + { + "epoch": 0.73, + "learning_rate": 4.196720723916735e-06, + "loss": 1.3098, + "step": 6936 + }, + { + "epoch": 0.73, + "learning_rate": 4.193740267669718e-06, + "loss": 1.2386, + "step": 6937 + }, + { + "epoch": 0.73, + "learning_rate": 4.19076058931232e-06, + "loss": 1.3271, + "step": 6938 + }, + { + "epoch": 0.73, + "learning_rate": 4.187781689243737e-06, + "loss": 1.4604, + "step": 6939 + }, + { + "epoch": 0.73, + "learning_rate": 4.184803567863072e-06, + "loss": 1.3496, + "step": 6940 + }, + { + "epoch": 0.73, + "learning_rate": 4.181826225569308e-06, + "loss": 1.3056, + "step": 6941 + }, + { + "epoch": 0.73, + "learning_rate": 4.1788496627613366e-06, + "loss": 1.2886, + "step": 6942 + }, + { + "epoch": 0.73, + "learning_rate": 4.175873879837944e-06, + "loss": 1.282, + "step": 6943 + }, + { + "epoch": 0.73, + "learning_rate": 4.172898877197802e-06, + "loss": 1.2984, + "step": 6944 + }, + { + "epoch": 0.73, + "learning_rate": 4.169924655239488e-06, + "loss": 1.2909, + "step": 6945 + }, + { + "epoch": 0.73, + "learning_rate": 4.166951214361474e-06, + "loss": 1.4015, + "step": 6946 + }, + { + "epoch": 0.73, + "learning_rate": 4.16397855496212e-06, + "loss": 1.3772, + "step": 6947 + }, + { + "epoch": 0.73, + "learning_rate": 4.161006677439687e-06, + "loss": 1.3089, + "step": 6948 + }, + { + "epoch": 0.73, + "learning_rate": 4.1580355821923344e-06, + "loss": 1.3599, + "step": 6949 + }, + { + "epoch": 0.73, + "learning_rate": 4.155065269618107e-06, + "loss": 1.2886, + "step": 6950 + }, + { + "epoch": 0.73, + "learning_rate": 4.152095740114955e-06, + "loss": 1.3071, + "step": 6951 + }, + { + "epoch": 0.73, + "learning_rate": 4.149126994080715e-06, + "loss": 1.3332, + "step": 6952 + }, + { + "epoch": 0.73, + "learning_rate": 4.146159031913123e-06, + "loss": 1.3835, + "step": 6953 + }, + { + "epoch": 0.73, + "learning_rate": 4.1431918540098144e-06, + "loss": 1.3399, + "step": 6954 + }, + { + "epoch": 0.73, + "learning_rate": 4.140225460768309e-06, + "loss": 1.2906, + "step": 6955 + }, + { + "epoch": 0.73, + "learning_rate": 4.137259852586029e-06, + "loss": 1.295, + "step": 6956 + }, + { + "epoch": 0.73, + "learning_rate": 4.134295029860295e-06, + "loss": 1.3371, + "step": 6957 + }, + { + "epoch": 0.73, + "learning_rate": 4.131330992988308e-06, + "loss": 1.4441, + "step": 6958 + }, + { + "epoch": 0.73, + "learning_rate": 4.1283677423671805e-06, + "loss": 1.3257, + "step": 6959 + }, + { + "epoch": 0.73, + "learning_rate": 4.125405278393907e-06, + "loss": 1.3958, + "step": 6960 + }, + { + "epoch": 0.73, + "learning_rate": 4.1224436014653826e-06, + "loss": 1.2856, + "step": 6961 + }, + { + "epoch": 0.73, + "learning_rate": 4.1194827119784e-06, + "loss": 1.2943, + "step": 6962 + }, + { + "epoch": 0.73, + "learning_rate": 4.116522610329636e-06, + "loss": 1.2691, + "step": 6963 + }, + { + "epoch": 0.73, + "learning_rate": 4.11356329691567e-06, + "loss": 1.293, + "step": 6964 + }, + { + "epoch": 0.73, + "learning_rate": 4.11060477213298e-06, + "loss": 1.3136, + "step": 6965 + }, + { + "epoch": 0.73, + "eval_loss": 1.399178147315979, + "eval_runtime": 77.5864, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 6965 + }, + { + "epoch": 0.73, + "learning_rate": 4.1076470363779235e-06, + "loss": 1.2833, + "step": 6966 + }, + { + "epoch": 0.73, + "learning_rate": 4.104690090046765e-06, + "loss": 1.3177, + "step": 6967 + }, + { + "epoch": 0.73, + "learning_rate": 4.101733933535663e-06, + "loss": 1.2623, + "step": 6968 + }, + { + "epoch": 0.73, + "learning_rate": 4.0987785672406585e-06, + "loss": 1.2814, + "step": 6969 + }, + { + "epoch": 0.73, + "learning_rate": 4.0958239915577036e-06, + "loss": 1.3823, + "step": 6970 + }, + { + "epoch": 0.73, + "learning_rate": 4.092870206882627e-06, + "loss": 1.2926, + "step": 6971 + }, + { + "epoch": 0.73, + "learning_rate": 4.089917213611164e-06, + "loss": 1.3324, + "step": 6972 + }, + { + "epoch": 0.73, + "learning_rate": 4.086965012138943e-06, + "loss": 1.3521, + "step": 6973 + }, + { + "epoch": 0.73, + "learning_rate": 4.084013602861476e-06, + "loss": 1.4828, + "step": 6974 + }, + { + "epoch": 0.73, + "learning_rate": 4.0810629861741804e-06, + "loss": 1.3187, + "step": 6975 + }, + { + "epoch": 0.73, + "learning_rate": 4.078113162472366e-06, + "loss": 1.3478, + "step": 6976 + }, + { + "epoch": 0.73, + "learning_rate": 4.075164132151227e-06, + "loss": 1.4256, + "step": 6977 + }, + { + "epoch": 0.73, + "learning_rate": 4.0722158956058635e-06, + "loss": 1.2815, + "step": 6978 + }, + { + "epoch": 0.73, + "learning_rate": 4.069268453231257e-06, + "loss": 1.3031, + "step": 6979 + }, + { + "epoch": 0.73, + "learning_rate": 4.066321805422292e-06, + "loss": 1.2983, + "step": 6980 + }, + { + "epoch": 0.73, + "learning_rate": 4.063375952573748e-06, + "loss": 1.3595, + "step": 6981 + }, + { + "epoch": 0.73, + "learning_rate": 4.060430895080286e-06, + "loss": 1.3119, + "step": 6982 + }, + { + "epoch": 0.73, + "learning_rate": 4.057486633336472e-06, + "loss": 1.328, + "step": 6983 + }, + { + "epoch": 0.73, + "learning_rate": 4.054543167736766e-06, + "loss": 1.232, + "step": 6984 + }, + { + "epoch": 0.73, + "learning_rate": 4.0516004986755064e-06, + "loss": 1.3288, + "step": 6985 + }, + { + "epoch": 0.73, + "learning_rate": 4.048658626546945e-06, + "loss": 1.2916, + "step": 6986 + }, + { + "epoch": 0.73, + "learning_rate": 4.045717551745209e-06, + "loss": 1.2411, + "step": 6987 + }, + { + "epoch": 0.73, + "learning_rate": 4.042777274664331e-06, + "loss": 1.3256, + "step": 6988 + }, + { + "epoch": 0.73, + "learning_rate": 4.039837795698237e-06, + "loss": 1.3455, + "step": 6989 + }, + { + "epoch": 0.73, + "learning_rate": 4.036899115240732e-06, + "loss": 1.3303, + "step": 6990 + }, + { + "epoch": 0.73, + "learning_rate": 4.033961233685529e-06, + "loss": 1.2805, + "step": 6991 + }, + { + "epoch": 0.73, + "learning_rate": 4.031024151426233e-06, + "loss": 1.3958, + "step": 6992 + }, + { + "epoch": 0.73, + "learning_rate": 4.0280878688563275e-06, + "loss": 1.2853, + "step": 6993 + }, + { + "epoch": 0.73, + "learning_rate": 4.0251523863692054e-06, + "loss": 1.2433, + "step": 6994 + }, + { + "epoch": 0.73, + "learning_rate": 4.022217704358148e-06, + "loss": 1.2644, + "step": 6995 + }, + { + "epoch": 0.73, + "learning_rate": 4.0192838232163204e-06, + "loss": 1.3218, + "step": 6996 + }, + { + "epoch": 0.73, + "learning_rate": 4.016350743336795e-06, + "loss": 1.2973, + "step": 6997 + }, + { + "epoch": 0.73, + "learning_rate": 4.013418465112521e-06, + "loss": 1.3209, + "step": 6998 + }, + { + "epoch": 0.73, + "learning_rate": 4.010486988936353e-06, + "loss": 1.2855, + "step": 6999 + }, + { + "epoch": 0.73, + "learning_rate": 4.007556315201035e-06, + "loss": 1.2381, + "step": 7000 + }, + { + "epoch": 0.73, + "learning_rate": 4.004626444299198e-06, + "loss": 1.3558, + "step": 7001 + }, + { + "epoch": 0.73, + "learning_rate": 4.001697376623371e-06, + "loss": 1.3139, + "step": 7002 + }, + { + "epoch": 0.73, + "learning_rate": 3.998769112565978e-06, + "loss": 1.3582, + "step": 7003 + }, + { + "epoch": 0.73, + "learning_rate": 3.9958416525193225e-06, + "loss": 1.2684, + "step": 7004 + }, + { + "epoch": 0.73, + "learning_rate": 3.992914996875618e-06, + "loss": 1.2915, + "step": 7005 + }, + { + "epoch": 0.73, + "learning_rate": 3.9899891460269536e-06, + "loss": 1.3205, + "step": 7006 + }, + { + "epoch": 0.73, + "learning_rate": 3.987064100365321e-06, + "loss": 1.2966, + "step": 7007 + }, + { + "epoch": 0.73, + "learning_rate": 3.984139860282606e-06, + "loss": 1.2691, + "step": 7008 + }, + { + "epoch": 0.74, + "learning_rate": 3.981216426170572e-06, + "loss": 1.3421, + "step": 7009 + }, + { + "epoch": 0.74, + "learning_rate": 3.97829379842089e-06, + "loss": 1.3034, + "step": 7010 + }, + { + "epoch": 0.74, + "learning_rate": 3.9753719774251195e-06, + "loss": 1.2863, + "step": 7011 + }, + { + "epoch": 0.74, + "learning_rate": 3.972450963574703e-06, + "loss": 1.3812, + "step": 7012 + }, + { + "epoch": 0.74, + "learning_rate": 3.969530757260986e-06, + "loss": 1.334, + "step": 7013 + }, + { + "epoch": 0.74, + "learning_rate": 3.966611358875201e-06, + "loss": 1.3289, + "step": 7014 + }, + { + "epoch": 0.74, + "learning_rate": 3.963692768808468e-06, + "loss": 1.395, + "step": 7015 + }, + { + "epoch": 0.74, + "learning_rate": 3.960774987451811e-06, + "loss": 1.3298, + "step": 7016 + }, + { + "epoch": 0.74, + "learning_rate": 3.957858015196128e-06, + "loss": 1.3304, + "step": 7017 + }, + { + "epoch": 0.74, + "learning_rate": 3.954941852432224e-06, + "loss": 1.301, + "step": 7018 + }, + { + "epoch": 0.74, + "learning_rate": 3.952026499550791e-06, + "loss": 1.3568, + "step": 7019 + }, + { + "epoch": 0.74, + "learning_rate": 3.949111956942406e-06, + "loss": 1.4464, + "step": 7020 + }, + { + "epoch": 0.74, + "learning_rate": 3.946198224997548e-06, + "loss": 1.4417, + "step": 7021 + }, + { + "epoch": 0.74, + "learning_rate": 3.943285304106583e-06, + "loss": 1.3979, + "step": 7022 + }, + { + "epoch": 0.74, + "learning_rate": 3.940373194659761e-06, + "loss": 1.2943, + "step": 7023 + }, + { + "epoch": 0.74, + "learning_rate": 3.937461897047239e-06, + "loss": 1.2571, + "step": 7024 + }, + { + "epoch": 0.74, + "learning_rate": 3.9345514116590454e-06, + "loss": 1.3433, + "step": 7025 + }, + { + "epoch": 0.74, + "learning_rate": 3.931641738885117e-06, + "loss": 1.4203, + "step": 7026 + }, + { + "epoch": 0.74, + "learning_rate": 3.9287328791152775e-06, + "loss": 1.3657, + "step": 7027 + }, + { + "epoch": 0.74, + "learning_rate": 3.925824832739234e-06, + "loss": 1.3954, + "step": 7028 + }, + { + "epoch": 0.74, + "learning_rate": 3.92291760014659e-06, + "loss": 1.2847, + "step": 7029 + }, + { + "epoch": 0.74, + "learning_rate": 3.920011181726846e-06, + "loss": 1.2776, + "step": 7030 + }, + { + "epoch": 0.74, + "learning_rate": 3.91710557786938e-06, + "loss": 1.3391, + "step": 7031 + }, + { + "epoch": 0.74, + "learning_rate": 3.914200788963472e-06, + "loss": 1.2935, + "step": 7032 + }, + { + "epoch": 0.74, + "learning_rate": 3.911296815398291e-06, + "loss": 1.3775, + "step": 7033 + }, + { + "epoch": 0.74, + "learning_rate": 3.90839365756289e-06, + "loss": 1.3652, + "step": 7034 + }, + { + "epoch": 0.74, + "learning_rate": 3.905491315846224e-06, + "loss": 1.2902, + "step": 7035 + }, + { + "epoch": 0.74, + "learning_rate": 3.902589790637125e-06, + "loss": 1.2859, + "step": 7036 + }, + { + "epoch": 0.74, + "learning_rate": 3.899689082324325e-06, + "loss": 1.4019, + "step": 7037 + }, + { + "epoch": 0.74, + "learning_rate": 3.89678919129645e-06, + "loss": 1.299, + "step": 7038 + }, + { + "epoch": 0.74, + "learning_rate": 3.893890117942003e-06, + "loss": 1.275, + "step": 7039 + }, + { + "epoch": 0.74, + "learning_rate": 3.890991862649388e-06, + "loss": 1.2593, + "step": 7040 + }, + { + "epoch": 0.74, + "learning_rate": 3.888094425806902e-06, + "loss": 1.2932, + "step": 7041 + }, + { + "epoch": 0.74, + "learning_rate": 3.885197807802719e-06, + "loss": 1.3038, + "step": 7042 + }, + { + "epoch": 0.74, + "learning_rate": 3.882302009024917e-06, + "loss": 1.285, + "step": 7043 + }, + { + "epoch": 0.74, + "learning_rate": 3.879407029861455e-06, + "loss": 1.4116, + "step": 7044 + }, + { + "epoch": 0.74, + "learning_rate": 3.876512870700187e-06, + "loss": 1.3823, + "step": 7045 + }, + { + "epoch": 0.74, + "learning_rate": 3.873619531928858e-06, + "loss": 1.2803, + "step": 7046 + }, + { + "epoch": 0.74, + "learning_rate": 3.870727013935099e-06, + "loss": 1.3287, + "step": 7047 + }, + { + "epoch": 0.74, + "learning_rate": 3.867835317106432e-06, + "loss": 1.3919, + "step": 7048 + }, + { + "epoch": 0.74, + "learning_rate": 3.864944441830275e-06, + "loss": 1.3967, + "step": 7049 + }, + { + "epoch": 0.74, + "learning_rate": 3.862054388493924e-06, + "loss": 1.2749, + "step": 7050 + }, + { + "epoch": 0.74, + "learning_rate": 3.85916515748458e-06, + "loss": 1.3408, + "step": 7051 + }, + { + "epoch": 0.74, + "learning_rate": 3.856276749189317e-06, + "loss": 1.3143, + "step": 7052 + }, + { + "epoch": 0.74, + "learning_rate": 3.853389163995111e-06, + "loss": 1.3661, + "step": 7053 + }, + { + "epoch": 0.74, + "learning_rate": 3.8505024022888305e-06, + "loss": 1.3094, + "step": 7054 + }, + { + "epoch": 0.74, + "learning_rate": 3.847616464457216e-06, + "loss": 1.2736, + "step": 7055 + }, + { + "epoch": 0.74, + "learning_rate": 3.844731350886917e-06, + "loss": 1.3628, + "step": 7056 + }, + { + "epoch": 0.74, + "learning_rate": 3.841847061964465e-06, + "loss": 1.2706, + "step": 7057 + }, + { + "epoch": 0.74, + "learning_rate": 3.838963598076275e-06, + "loss": 1.2566, + "step": 7058 + }, + { + "epoch": 0.74, + "learning_rate": 3.83608095960866e-06, + "loss": 1.2415, + "step": 7059 + }, + { + "epoch": 0.74, + "learning_rate": 3.833199146947823e-06, + "loss": 1.2748, + "step": 7060 + }, + { + "epoch": 0.74, + "learning_rate": 3.830318160479847e-06, + "loss": 1.4672, + "step": 7061 + }, + { + "epoch": 0.74, + "learning_rate": 3.827438000590714e-06, + "loss": 1.2907, + "step": 7062 + }, + { + "epoch": 0.74, + "learning_rate": 3.824558667666288e-06, + "loss": 1.3477, + "step": 7063 + }, + { + "epoch": 0.74, + "learning_rate": 3.821680162092328e-06, + "loss": 1.1135, + "step": 7064 + }, + { + "epoch": 0.74, + "learning_rate": 3.8188024842544825e-06, + "loss": 1.3724, + "step": 7065 + }, + { + "epoch": 0.74, + "learning_rate": 3.81592563453828e-06, + "loss": 1.3854, + "step": 7066 + }, + { + "epoch": 0.74, + "learning_rate": 3.8130496133291473e-06, + "loss": 1.3074, + "step": 7067 + }, + { + "epoch": 0.74, + "learning_rate": 3.8101744210124012e-06, + "loss": 1.4434, + "step": 7068 + }, + { + "epoch": 0.74, + "learning_rate": 3.807300057973238e-06, + "loss": 1.2754, + "step": 7069 + }, + { + "epoch": 0.74, + "learning_rate": 3.804426524596754e-06, + "loss": 1.3654, + "step": 7070 + }, + { + "epoch": 0.74, + "learning_rate": 3.8015538212679214e-06, + "loss": 1.2616, + "step": 7071 + }, + { + "epoch": 0.74, + "learning_rate": 3.798681948371613e-06, + "loss": 1.2939, + "step": 7072 + }, + { + "epoch": 0.74, + "learning_rate": 3.7958109062925894e-06, + "loss": 1.2787, + "step": 7073 + }, + { + "epoch": 0.74, + "learning_rate": 3.792940695415489e-06, + "loss": 1.2953, + "step": 7074 + }, + { + "epoch": 0.74, + "learning_rate": 3.7900713161248515e-06, + "loss": 1.2714, + "step": 7075 + }, + { + "epoch": 0.74, + "learning_rate": 3.7872027688051004e-06, + "loss": 1.3085, + "step": 7076 + }, + { + "epoch": 0.74, + "learning_rate": 3.7843350538405433e-06, + "loss": 1.311, + "step": 7077 + }, + { + "epoch": 0.74, + "learning_rate": 3.781468171615382e-06, + "loss": 1.3367, + "step": 7078 + }, + { + "epoch": 0.74, + "learning_rate": 3.7786021225137102e-06, + "loss": 1.2768, + "step": 7079 + }, + { + "epoch": 0.74, + "learning_rate": 3.775736906919496e-06, + "loss": 1.2828, + "step": 7080 + }, + { + "epoch": 0.74, + "learning_rate": 3.772872525216613e-06, + "loss": 1.3682, + "step": 7081 + }, + { + "epoch": 0.74, + "learning_rate": 3.7700089777888072e-06, + "loss": 1.3906, + "step": 7082 + }, + { + "epoch": 0.74, + "learning_rate": 3.767146265019723e-06, + "loss": 1.2712, + "step": 7083 + }, + { + "epoch": 0.74, + "learning_rate": 3.764284387292896e-06, + "loss": 1.3405, + "step": 7084 + }, + { + "epoch": 0.74, + "learning_rate": 3.761423344991736e-06, + "loss": 1.3941, + "step": 7085 + }, + { + "epoch": 0.74, + "learning_rate": 3.7585631384995523e-06, + "loss": 1.3463, + "step": 7086 + }, + { + "epoch": 0.74, + "learning_rate": 3.7557037681995423e-06, + "loss": 1.2771, + "step": 7087 + }, + { + "epoch": 0.74, + "learning_rate": 3.7528452344747834e-06, + "loss": 1.2706, + "step": 7088 + }, + { + "epoch": 0.74, + "learning_rate": 3.7499875377082497e-06, + "loss": 1.2672, + "step": 7089 + }, + { + "epoch": 0.74, + "learning_rate": 3.7471306782827944e-06, + "loss": 1.2638, + "step": 7090 + }, + { + "epoch": 0.74, + "learning_rate": 3.744274656581166e-06, + "loss": 1.3417, + "step": 7091 + }, + { + "epoch": 0.74, + "learning_rate": 3.7414194729860008e-06, + "loss": 1.278, + "step": 7092 + }, + { + "epoch": 0.74, + "learning_rate": 3.738565127879814e-06, + "loss": 1.2753, + "step": 7093 + }, + { + "epoch": 0.74, + "learning_rate": 3.7357116216450183e-06, + "loss": 1.2989, + "step": 7094 + }, + { + "epoch": 0.74, + "learning_rate": 3.7328589546639127e-06, + "loss": 1.263, + "step": 7095 + }, + { + "epoch": 0.74, + "learning_rate": 3.7300071273186745e-06, + "loss": 1.3534, + "step": 7096 + }, + { + "epoch": 0.74, + "learning_rate": 3.7271561399913825e-06, + "loss": 1.2565, + "step": 7097 + }, + { + "epoch": 0.74, + "learning_rate": 3.724305993063989e-06, + "loss": 1.3233, + "step": 7098 + }, + { + "epoch": 0.74, + "learning_rate": 3.7214566869183443e-06, + "loss": 1.3179, + "step": 7099 + }, + { + "epoch": 0.74, + "learning_rate": 3.718608221936184e-06, + "loss": 1.2749, + "step": 7100 + }, + { + "epoch": 0.74, + "learning_rate": 3.715760598499124e-06, + "loss": 1.3106, + "step": 7101 + }, + { + "epoch": 0.74, + "learning_rate": 3.712913816988675e-06, + "loss": 1.3115, + "step": 7102 + }, + { + "epoch": 0.74, + "learning_rate": 3.7100678777862364e-06, + "loss": 1.2798, + "step": 7103 + }, + { + "epoch": 0.74, + "learning_rate": 3.7072227812730853e-06, + "loss": 1.3964, + "step": 7104 + }, + { + "epoch": 0.75, + "learning_rate": 3.7043785278303923e-06, + "loss": 1.4034, + "step": 7105 + }, + { + "epoch": 0.75, + "learning_rate": 3.70153511783922e-06, + "loss": 1.3244, + "step": 7106 + }, + { + "epoch": 0.75, + "learning_rate": 3.698692551680505e-06, + "loss": 1.3283, + "step": 7107 + }, + { + "epoch": 0.75, + "learning_rate": 3.6958508297350847e-06, + "loss": 1.3567, + "step": 7108 + }, + { + "epoch": 0.75, + "learning_rate": 3.6930099523836692e-06, + "loss": 1.3178, + "step": 7109 + }, + { + "epoch": 0.75, + "learning_rate": 3.6901699200068673e-06, + "loss": 1.2697, + "step": 7110 + }, + { + "epoch": 0.75, + "learning_rate": 3.687330732985175e-06, + "loss": 1.2501, + "step": 7111 + }, + { + "epoch": 0.75, + "learning_rate": 3.6844923916989607e-06, + "loss": 1.2772, + "step": 7112 + }, + { + "epoch": 0.75, + "learning_rate": 3.681654896528495e-06, + "loss": 1.2845, + "step": 7113 + }, + { + "epoch": 0.75, + "learning_rate": 3.6788182478539312e-06, + "loss": 1.3151, + "step": 7114 + }, + { + "epoch": 0.75, + "learning_rate": 3.6759824460553016e-06, + "loss": 1.4925, + "step": 7115 + }, + { + "epoch": 0.75, + "learning_rate": 3.673147491512539e-06, + "loss": 1.2892, + "step": 7116 + }, + { + "epoch": 0.75, + "learning_rate": 3.670313384605444e-06, + "loss": 1.2906, + "step": 7117 + }, + { + "epoch": 0.75, + "learning_rate": 3.6674801257137195e-06, + "loss": 1.3927, + "step": 7118 + }, + { + "epoch": 0.75, + "learning_rate": 3.6646477152169522e-06, + "loss": 1.4001, + "step": 7119 + }, + { + "epoch": 0.75, + "learning_rate": 3.6618161534946074e-06, + "loss": 1.3363, + "step": 7120 + }, + { + "epoch": 0.75, + "learning_rate": 3.658985440926044e-06, + "loss": 1.3297, + "step": 7121 + }, + { + "epoch": 0.75, + "learning_rate": 3.656155577890507e-06, + "loss": 1.3029, + "step": 7122 + }, + { + "epoch": 0.75, + "learning_rate": 3.653326564767119e-06, + "loss": 1.3452, + "step": 7123 + }, + { + "epoch": 0.75, + "learning_rate": 3.6504984019348987e-06, + "loss": 1.3246, + "step": 7124 + }, + { + "epoch": 0.75, + "learning_rate": 3.647671089772752e-06, + "loss": 1.3285, + "step": 7125 + }, + { + "epoch": 0.75, + "learning_rate": 3.6448446286594574e-06, + "loss": 1.3127, + "step": 7126 + }, + { + "epoch": 0.75, + "learning_rate": 3.6420190189736946e-06, + "loss": 1.3224, + "step": 7127 + }, + { + "epoch": 0.75, + "learning_rate": 3.6391942610940178e-06, + "loss": 1.3086, + "step": 7128 + }, + { + "epoch": 0.75, + "learning_rate": 3.6363703553988748e-06, + "loss": 1.3741, + "step": 7129 + }, + { + "epoch": 0.75, + "learning_rate": 3.633547302266599e-06, + "loss": 1.3192, + "step": 7130 + }, + { + "epoch": 0.75, + "learning_rate": 3.6307251020754e-06, + "loss": 1.3032, + "step": 7131 + }, + { + "epoch": 0.75, + "learning_rate": 3.6279037552033847e-06, + "loss": 1.2642, + "step": 7132 + }, + { + "epoch": 0.75, + "learning_rate": 3.6250832620285436e-06, + "loss": 1.3948, + "step": 7133 + }, + { + "epoch": 0.75, + "learning_rate": 3.6222636229287445e-06, + "loss": 1.3542, + "step": 7134 + }, + { + "epoch": 0.75, + "learning_rate": 3.6194448382817526e-06, + "loss": 1.3028, + "step": 7135 + }, + { + "epoch": 0.75, + "learning_rate": 3.616626908465205e-06, + "loss": 1.3017, + "step": 7136 + }, + { + "epoch": 0.75, + "learning_rate": 3.613809833856636e-06, + "loss": 1.3072, + "step": 7137 + }, + { + "epoch": 0.75, + "learning_rate": 3.6109936148334666e-06, + "loss": 1.3065, + "step": 7138 + }, + { + "epoch": 0.75, + "learning_rate": 3.608178251772988e-06, + "loss": 1.4268, + "step": 7139 + }, + { + "epoch": 0.75, + "learning_rate": 3.6053637450523914e-06, + "loss": 1.301, + "step": 7140 + }, + { + "epoch": 0.75, + "learning_rate": 3.6025500950487514e-06, + "loss": 1.2873, + "step": 7141 + }, + { + "epoch": 0.75, + "learning_rate": 3.599737302139018e-06, + "loss": 1.2831, + "step": 7142 + }, + { + "epoch": 0.75, + "learning_rate": 3.5969253667000403e-06, + "loss": 1.5125, + "step": 7143 + }, + { + "epoch": 0.75, + "learning_rate": 3.594114289108538e-06, + "loss": 1.3643, + "step": 7144 + }, + { + "epoch": 0.75, + "learning_rate": 3.5913040697411272e-06, + "loss": 1.3157, + "step": 7145 + }, + { + "epoch": 0.75, + "learning_rate": 3.5884947089743084e-06, + "loss": 1.2687, + "step": 7146 + }, + { + "epoch": 0.75, + "learning_rate": 3.585686207184458e-06, + "loss": 1.3227, + "step": 7147 + }, + { + "epoch": 0.75, + "learning_rate": 3.5828785647478435e-06, + "loss": 1.2745, + "step": 7148 + }, + { + "epoch": 0.75, + "learning_rate": 3.5800717820406226e-06, + "loss": 1.332, + "step": 7149 + }, + { + "epoch": 0.75, + "learning_rate": 3.5772658594388253e-06, + "loss": 1.2863, + "step": 7150 + }, + { + "epoch": 0.75, + "learning_rate": 3.5744607973183766e-06, + "loss": 1.3791, + "step": 7151 + }, + { + "epoch": 0.75, + "learning_rate": 3.5716565960550844e-06, + "loss": 1.2781, + "step": 7152 + }, + { + "epoch": 0.75, + "learning_rate": 3.5688532560246348e-06, + "loss": 1.252, + "step": 7153 + }, + { + "epoch": 0.75, + "learning_rate": 3.5660507776026086e-06, + "loss": 1.3158, + "step": 7154 + }, + { + "epoch": 0.75, + "learning_rate": 3.5632491611644603e-06, + "loss": 1.3241, + "step": 7155 + }, + { + "epoch": 0.75, + "learning_rate": 3.5604484070855382e-06, + "loss": 1.2572, + "step": 7156 + }, + { + "epoch": 0.75, + "learning_rate": 3.5576485157410733e-06, + "loss": 1.3734, + "step": 7157 + }, + { + "epoch": 0.75, + "learning_rate": 3.5548494875061724e-06, + "loss": 1.3253, + "step": 7158 + }, + { + "epoch": 0.75, + "learning_rate": 3.5520513227558385e-06, + "loss": 1.2659, + "step": 7159 + }, + { + "epoch": 0.75, + "learning_rate": 3.5492540218649553e-06, + "loss": 1.3149, + "step": 7160 + }, + { + "epoch": 0.75, + "learning_rate": 3.546457585208283e-06, + "loss": 1.3413, + "step": 7161 + }, + { + "epoch": 0.75, + "learning_rate": 3.5436620131604803e-06, + "loss": 1.2846, + "step": 7162 + }, + { + "epoch": 0.75, + "learning_rate": 3.540867306096073e-06, + "loss": 1.3239, + "step": 7163 + }, + { + "epoch": 0.75, + "learning_rate": 3.5380734643894856e-06, + "loss": 1.3137, + "step": 7164 + }, + { + "epoch": 0.75, + "eval_loss": 1.397520899772644, + "eval_runtime": 77.542, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 7164 + }, + { + "epoch": 0.75, + "learning_rate": 3.535280488415024e-06, + "loss": 1.414, + "step": 7165 + }, + { + "epoch": 0.75, + "learning_rate": 3.5324883785468665e-06, + "loss": 1.2708, + "step": 7166 + }, + { + "epoch": 0.75, + "learning_rate": 3.529697135159089e-06, + "loss": 1.2975, + "step": 7167 + }, + { + "epoch": 0.75, + "learning_rate": 3.526906758625651e-06, + "loss": 1.3723, + "step": 7168 + }, + { + "epoch": 0.75, + "learning_rate": 3.5241172493203822e-06, + "loss": 1.4105, + "step": 7169 + }, + { + "epoch": 0.75, + "learning_rate": 3.5213286076170107e-06, + "loss": 1.2592, + "step": 7170 + }, + { + "epoch": 0.75, + "learning_rate": 3.5185408338891437e-06, + "loss": 1.3361, + "step": 7171 + }, + { + "epoch": 0.75, + "learning_rate": 3.515753928510267e-06, + "loss": 1.2591, + "step": 7172 + }, + { + "epoch": 0.75, + "learning_rate": 3.512967891853759e-06, + "loss": 1.2938, + "step": 7173 + }, + { + "epoch": 0.75, + "learning_rate": 3.510182724292872e-06, + "loss": 1.4116, + "step": 7174 + }, + { + "epoch": 0.75, + "learning_rate": 3.5073984262007486e-06, + "loss": 1.3968, + "step": 7175 + }, + { + "epoch": 0.75, + "learning_rate": 3.5046149979504184e-06, + "loss": 1.31, + "step": 7176 + }, + { + "epoch": 0.75, + "learning_rate": 3.5018324399147817e-06, + "loss": 1.2966, + "step": 7177 + }, + { + "epoch": 0.75, + "learning_rate": 3.4990507524666327e-06, + "loss": 1.3431, + "step": 7178 + }, + { + "epoch": 0.75, + "learning_rate": 3.49626993597865e-06, + "loss": 1.3227, + "step": 7179 + }, + { + "epoch": 0.75, + "learning_rate": 3.4934899908233834e-06, + "loss": 1.201, + "step": 7180 + }, + { + "epoch": 0.75, + "learning_rate": 3.490710917373283e-06, + "loss": 1.3003, + "step": 7181 + }, + { + "epoch": 0.75, + "learning_rate": 3.487932716000666e-06, + "loss": 1.2879, + "step": 7182 + }, + { + "epoch": 0.75, + "learning_rate": 3.485155387077742e-06, + "loss": 1.2742, + "step": 7183 + }, + { + "epoch": 0.75, + "learning_rate": 3.4823789309766065e-06, + "loss": 1.2972, + "step": 7184 + }, + { + "epoch": 0.75, + "learning_rate": 3.479603348069226e-06, + "loss": 1.3763, + "step": 7185 + }, + { + "epoch": 0.75, + "learning_rate": 3.4768286387274597e-06, + "loss": 1.4653, + "step": 7186 + }, + { + "epoch": 0.75, + "learning_rate": 3.4740548033230524e-06, + "loss": 1.3534, + "step": 7187 + }, + { + "epoch": 0.75, + "learning_rate": 3.4712818422276207e-06, + "loss": 1.3917, + "step": 7188 + }, + { + "epoch": 0.75, + "learning_rate": 3.4685097558126733e-06, + "loss": 1.306, + "step": 7189 + }, + { + "epoch": 0.75, + "learning_rate": 3.465738544449596e-06, + "loss": 1.4628, + "step": 7190 + }, + { + "epoch": 0.75, + "learning_rate": 3.4629682085096606e-06, + "loss": 1.3916, + "step": 7191 + }, + { + "epoch": 0.75, + "learning_rate": 3.4601987483640243e-06, + "loss": 1.3348, + "step": 7192 + }, + { + "epoch": 0.75, + "learning_rate": 3.457430164383718e-06, + "loss": 1.4771, + "step": 7193 + }, + { + "epoch": 0.75, + "learning_rate": 3.4546624569396635e-06, + "loss": 1.5004, + "step": 7194 + }, + { + "epoch": 0.75, + "learning_rate": 3.451895626402667e-06, + "loss": 1.279, + "step": 7195 + }, + { + "epoch": 0.75, + "learning_rate": 3.4491296731434053e-06, + "loss": 1.3263, + "step": 7196 + }, + { + "epoch": 0.75, + "learning_rate": 3.4463645975324466e-06, + "loss": 1.2449, + "step": 7197 + }, + { + "epoch": 0.75, + "learning_rate": 3.4436003999402466e-06, + "loss": 1.2743, + "step": 7198 + }, + { + "epoch": 0.75, + "learning_rate": 3.4408370807371283e-06, + "loss": 1.3127, + "step": 7199 + }, + { + "epoch": 0.76, + "learning_rate": 3.438074640293312e-06, + "loss": 1.2996, + "step": 7200 + }, + { + "epoch": 0.76, + "learning_rate": 3.435313078978887e-06, + "loss": 1.3114, + "step": 7201 + }, + { + "epoch": 0.76, + "learning_rate": 3.432552397163835e-06, + "loss": 1.2574, + "step": 7202 + }, + { + "epoch": 0.76, + "learning_rate": 3.42979259521802e-06, + "loss": 1.2605, + "step": 7203 + }, + { + "epoch": 0.76, + "learning_rate": 3.4270336735111785e-06, + "loss": 1.2578, + "step": 7204 + }, + { + "epoch": 0.76, + "learning_rate": 3.424275632412938e-06, + "loss": 1.3297, + "step": 7205 + }, + { + "epoch": 0.76, + "learning_rate": 3.4215184722928073e-06, + "loss": 1.2353, + "step": 7206 + }, + { + "epoch": 0.76, + "learning_rate": 3.4187621935201707e-06, + "loss": 1.288, + "step": 7207 + }, + { + "epoch": 0.76, + "learning_rate": 3.416006796464304e-06, + "loss": 1.2947, + "step": 7208 + }, + { + "epoch": 0.76, + "learning_rate": 3.4132522814943513e-06, + "loss": 1.4208, + "step": 7209 + }, + { + "epoch": 0.76, + "learning_rate": 3.4104986489793534e-06, + "loss": 1.3273, + "step": 7210 + }, + { + "epoch": 0.76, + "learning_rate": 3.4077458992882285e-06, + "loss": 1.274, + "step": 7211 + }, + { + "epoch": 0.76, + "learning_rate": 3.404994032789766e-06, + "loss": 1.2782, + "step": 7212 + }, + { + "epoch": 0.76, + "learning_rate": 3.4022430498526505e-06, + "loss": 1.3513, + "step": 7213 + }, + { + "epoch": 0.76, + "learning_rate": 3.3994929508454455e-06, + "loss": 1.2843, + "step": 7214 + }, + { + "epoch": 0.76, + "learning_rate": 3.3967437361365873e-06, + "loss": 1.2764, + "step": 7215 + }, + { + "epoch": 0.76, + "learning_rate": 3.3939954060944036e-06, + "loss": 1.2786, + "step": 7216 + }, + { + "epoch": 0.76, + "learning_rate": 3.391247961087103e-06, + "loss": 1.2927, + "step": 7217 + }, + { + "epoch": 0.76, + "learning_rate": 3.3885014014827657e-06, + "loss": 1.3735, + "step": 7218 + }, + { + "epoch": 0.76, + "learning_rate": 3.385755727649367e-06, + "loss": 1.3065, + "step": 7219 + }, + { + "epoch": 0.76, + "learning_rate": 3.3830109399547506e-06, + "loss": 1.2463, + "step": 7220 + }, + { + "epoch": 0.76, + "learning_rate": 3.3802670387666492e-06, + "loss": 1.2496, + "step": 7221 + }, + { + "epoch": 0.76, + "learning_rate": 3.3775240244526796e-06, + "loss": 1.2807, + "step": 7222 + }, + { + "epoch": 0.76, + "learning_rate": 3.3747818973803294e-06, + "loss": 1.313, + "step": 7223 + }, + { + "epoch": 0.76, + "learning_rate": 3.372040657916974e-06, + "loss": 1.3557, + "step": 7224 + }, + { + "epoch": 0.76, + "learning_rate": 3.3693003064298744e-06, + "loss": 1.3705, + "step": 7225 + }, + { + "epoch": 0.76, + "learning_rate": 3.366560843286161e-06, + "loss": 1.3763, + "step": 7226 + }, + { + "epoch": 0.76, + "learning_rate": 3.3638222688528565e-06, + "loss": 1.3252, + "step": 7227 + }, + { + "epoch": 0.76, + "learning_rate": 3.361084583496853e-06, + "loss": 1.2635, + "step": 7228 + }, + { + "epoch": 0.76, + "learning_rate": 3.3583477875849346e-06, + "loss": 1.3084, + "step": 7229 + }, + { + "epoch": 0.76, + "learning_rate": 3.3556118814837646e-06, + "loss": 1.3347, + "step": 7230 + }, + { + "epoch": 0.76, + "learning_rate": 3.3528768655598764e-06, + "loss": 1.3937, + "step": 7231 + }, + { + "epoch": 0.76, + "learning_rate": 3.350142740179696e-06, + "loss": 1.3251, + "step": 7232 + }, + { + "epoch": 0.76, + "learning_rate": 3.347409505709529e-06, + "loss": 1.3654, + "step": 7233 + }, + { + "epoch": 0.76, + "learning_rate": 3.344677162515553e-06, + "loss": 1.3864, + "step": 7234 + }, + { + "epoch": 0.76, + "learning_rate": 3.3419457109638377e-06, + "loss": 1.3142, + "step": 7235 + }, + { + "epoch": 0.76, + "learning_rate": 3.3392151514203195e-06, + "loss": 1.3557, + "step": 7236 + }, + { + "epoch": 0.76, + "learning_rate": 3.3364854842508276e-06, + "loss": 1.3093, + "step": 7237 + }, + { + "epoch": 0.76, + "learning_rate": 3.333756709821072e-06, + "loss": 1.3763, + "step": 7238 + }, + { + "epoch": 0.76, + "learning_rate": 3.3310288284966297e-06, + "loss": 1.2943, + "step": 7239 + }, + { + "epoch": 0.76, + "learning_rate": 3.3283018406429703e-06, + "loss": 1.473, + "step": 7240 + }, + { + "epoch": 0.76, + "learning_rate": 3.3255757466254448e-06, + "loss": 1.2501, + "step": 7241 + }, + { + "epoch": 0.76, + "learning_rate": 3.322850546809271e-06, + "loss": 1.2893, + "step": 7242 + }, + { + "epoch": 0.76, + "learning_rate": 3.3201262415595614e-06, + "loss": 1.2995, + "step": 7243 + }, + { + "epoch": 0.76, + "learning_rate": 3.3174028312413044e-06, + "loss": 1.2985, + "step": 7244 + }, + { + "epoch": 0.76, + "learning_rate": 3.31468031621936e-06, + "loss": 1.2868, + "step": 7245 + }, + { + "epoch": 0.76, + "learning_rate": 3.311958696858484e-06, + "loss": 1.2467, + "step": 7246 + }, + { + "epoch": 0.76, + "learning_rate": 3.309237973523295e-06, + "loss": 1.2303, + "step": 7247 + }, + { + "epoch": 0.76, + "learning_rate": 3.3065181465783045e-06, + "loss": 1.3172, + "step": 7248 + }, + { + "epoch": 0.76, + "learning_rate": 3.303799216387902e-06, + "loss": 1.2003, + "step": 7249 + }, + { + "epoch": 0.76, + "learning_rate": 3.3010811833163482e-06, + "loss": 1.2931, + "step": 7250 + }, + { + "epoch": 0.76, + "learning_rate": 3.2983640477277925e-06, + "loss": 1.3135, + "step": 7251 + }, + { + "epoch": 0.76, + "learning_rate": 3.2956478099862644e-06, + "loss": 1.2711, + "step": 7252 + }, + { + "epoch": 0.76, + "learning_rate": 3.292932470455663e-06, + "loss": 1.291, + "step": 7253 + }, + { + "epoch": 0.76, + "learning_rate": 3.2902180294997832e-06, + "loss": 1.2838, + "step": 7254 + }, + { + "epoch": 0.76, + "learning_rate": 3.2875044874822804e-06, + "loss": 1.2381, + "step": 7255 + }, + { + "epoch": 0.76, + "learning_rate": 3.284791844766705e-06, + "loss": 1.2966, + "step": 7256 + }, + { + "epoch": 0.76, + "learning_rate": 3.282080101716484e-06, + "loss": 1.3418, + "step": 7257 + }, + { + "epoch": 0.76, + "learning_rate": 3.2793692586949143e-06, + "loss": 1.3247, + "step": 7258 + }, + { + "epoch": 0.76, + "learning_rate": 3.2766593160651827e-06, + "loss": 1.3462, + "step": 7259 + }, + { + "epoch": 0.76, + "learning_rate": 3.273950274190356e-06, + "loss": 1.3699, + "step": 7260 + }, + { + "epoch": 0.76, + "learning_rate": 3.2712421334333687e-06, + "loss": 1.2863, + "step": 7261 + }, + { + "epoch": 0.76, + "learning_rate": 3.268534894157046e-06, + "loss": 1.3791, + "step": 7262 + }, + { + "epoch": 0.76, + "learning_rate": 3.265828556724092e-06, + "loss": 1.3066, + "step": 7263 + }, + { + "epoch": 0.76, + "learning_rate": 3.2631231214970784e-06, + "loss": 1.319, + "step": 7264 + }, + { + "epoch": 0.76, + "learning_rate": 3.260418588838471e-06, + "loss": 1.2939, + "step": 7265 + }, + { + "epoch": 0.76, + "learning_rate": 3.2577149591106017e-06, + "loss": 1.2568, + "step": 7266 + }, + { + "epoch": 0.76, + "learning_rate": 3.2550122326756905e-06, + "loss": 1.3494, + "step": 7267 + }, + { + "epoch": 0.76, + "learning_rate": 3.252310409895837e-06, + "loss": 1.3001, + "step": 7268 + }, + { + "epoch": 0.76, + "learning_rate": 3.2496094911330087e-06, + "loss": 1.4039, + "step": 7269 + }, + { + "epoch": 0.76, + "learning_rate": 3.246909476749063e-06, + "loss": 1.2904, + "step": 7270 + }, + { + "epoch": 0.76, + "learning_rate": 3.2442103671057358e-06, + "loss": 1.2864, + "step": 7271 + }, + { + "epoch": 0.76, + "learning_rate": 3.241512162564632e-06, + "loss": 1.3195, + "step": 7272 + }, + { + "epoch": 0.76, + "learning_rate": 3.2388148634872473e-06, + "loss": 1.2776, + "step": 7273 + }, + { + "epoch": 0.76, + "learning_rate": 3.2361184702349446e-06, + "loss": 1.3391, + "step": 7274 + }, + { + "epoch": 0.76, + "learning_rate": 3.2334229831689745e-06, + "loss": 1.6897, + "step": 7275 + }, + { + "epoch": 0.76, + "learning_rate": 3.2307284026504673e-06, + "loss": 1.4191, + "step": 7276 + }, + { + "epoch": 0.76, + "learning_rate": 3.228034729040419e-06, + "loss": 1.2671, + "step": 7277 + }, + { + "epoch": 0.76, + "learning_rate": 3.2253419626997172e-06, + "loss": 1.3085, + "step": 7278 + }, + { + "epoch": 0.76, + "learning_rate": 3.2226501039891266e-06, + "loss": 1.4378, + "step": 7279 + }, + { + "epoch": 0.76, + "learning_rate": 3.2199591532692807e-06, + "loss": 1.3044, + "step": 7280 + }, + { + "epoch": 0.76, + "learning_rate": 3.2172691109007036e-06, + "loss": 1.2709, + "step": 7281 + }, + { + "epoch": 0.76, + "learning_rate": 3.214579977243787e-06, + "loss": 1.2394, + "step": 7282 + }, + { + "epoch": 0.76, + "learning_rate": 3.2118917526588055e-06, + "loss": 1.2945, + "step": 7283 + }, + { + "epoch": 0.76, + "learning_rate": 3.2092044375059197e-06, + "loss": 1.4074, + "step": 7284 + }, + { + "epoch": 0.76, + "learning_rate": 3.2065180321451504e-06, + "loss": 1.3769, + "step": 7285 + }, + { + "epoch": 0.76, + "learning_rate": 3.203832536936413e-06, + "loss": 1.2479, + "step": 7286 + }, + { + "epoch": 0.76, + "learning_rate": 3.2011479522394973e-06, + "loss": 1.2623, + "step": 7287 + }, + { + "epoch": 0.76, + "learning_rate": 3.1984642784140616e-06, + "loss": 1.3044, + "step": 7288 + }, + { + "epoch": 0.76, + "learning_rate": 3.1957815158196525e-06, + "loss": 1.321, + "step": 7289 + }, + { + "epoch": 0.76, + "learning_rate": 3.1930996648156953e-06, + "loss": 1.3307, + "step": 7290 + }, + { + "epoch": 0.76, + "learning_rate": 3.1904187257614814e-06, + "loss": 1.3135, + "step": 7291 + }, + { + "epoch": 0.76, + "learning_rate": 3.187738699016195e-06, + "loss": 1.2821, + "step": 7292 + }, + { + "epoch": 0.76, + "learning_rate": 3.1850595849388853e-06, + "loss": 1.3069, + "step": 7293 + }, + { + "epoch": 0.76, + "learning_rate": 3.1823813838884865e-06, + "loss": 1.2952, + "step": 7294 + }, + { + "epoch": 0.76, + "learning_rate": 3.179704096223812e-06, + "loss": 1.3313, + "step": 7295 + }, + { + "epoch": 0.77, + "learning_rate": 3.177027722303544e-06, + "loss": 1.3454, + "step": 7296 + }, + { + "epoch": 0.77, + "learning_rate": 3.1743522624862497e-06, + "loss": 1.2904, + "step": 7297 + }, + { + "epoch": 0.77, + "learning_rate": 3.1716777171303783e-06, + "loss": 1.3213, + "step": 7298 + }, + { + "epoch": 0.77, + "learning_rate": 3.1690040865942396e-06, + "loss": 1.3336, + "step": 7299 + }, + { + "epoch": 0.77, + "learning_rate": 3.1663313712360398e-06, + "loss": 1.3399, + "step": 7300 + }, + { + "epoch": 0.77, + "learning_rate": 3.1636595714138483e-06, + "loss": 1.2871, + "step": 7301 + }, + { + "epoch": 0.77, + "learning_rate": 3.16098868748562e-06, + "loss": 1.312, + "step": 7302 + }, + { + "epoch": 0.77, + "learning_rate": 3.158318719809188e-06, + "loss": 1.3325, + "step": 7303 + }, + { + "epoch": 0.77, + "learning_rate": 3.1556496687422534e-06, + "loss": 1.309, + "step": 7304 + }, + { + "epoch": 0.77, + "learning_rate": 3.152981534642403e-06, + "loss": 1.3186, + "step": 7305 + }, + { + "epoch": 0.77, + "learning_rate": 3.1503143178671016e-06, + "loss": 1.3235, + "step": 7306 + }, + { + "epoch": 0.77, + "learning_rate": 3.1476480187736812e-06, + "loss": 1.3557, + "step": 7307 + }, + { + "epoch": 0.77, + "learning_rate": 3.1449826377193613e-06, + "loss": 1.3206, + "step": 7308 + }, + { + "epoch": 0.77, + "learning_rate": 3.1423181750612375e-06, + "loss": 1.2901, + "step": 7309 + }, + { + "epoch": 0.77, + "learning_rate": 3.1396546311562713e-06, + "loss": 1.3232, + "step": 7310 + }, + { + "epoch": 0.77, + "learning_rate": 3.136992006361318e-06, + "loss": 1.3065, + "step": 7311 + }, + { + "epoch": 0.77, + "learning_rate": 3.1343303010330926e-06, + "loss": 1.273, + "step": 7312 + }, + { + "epoch": 0.77, + "learning_rate": 3.1316695155281997e-06, + "loss": 1.2773, + "step": 7313 + }, + { + "epoch": 0.77, + "learning_rate": 3.12900965020312e-06, + "loss": 1.2959, + "step": 7314 + }, + { + "epoch": 0.77, + "learning_rate": 3.1263507054141975e-06, + "loss": 1.2685, + "step": 7315 + }, + { + "epoch": 0.77, + "learning_rate": 3.1236926815176683e-06, + "loss": 1.3908, + "step": 7316 + }, + { + "epoch": 0.77, + "learning_rate": 3.121035578869643e-06, + "loss": 1.3022, + "step": 7317 + }, + { + "epoch": 0.77, + "learning_rate": 3.1183793978260966e-06, + "loss": 1.3144, + "step": 7318 + }, + { + "epoch": 0.77, + "learning_rate": 3.1157241387428972e-06, + "loss": 1.3142, + "step": 7319 + }, + { + "epoch": 0.77, + "learning_rate": 3.1130698019757743e-06, + "loss": 1.3277, + "step": 7320 + }, + { + "epoch": 0.77, + "learning_rate": 3.110416387880344e-06, + "loss": 1.2973, + "step": 7321 + }, + { + "epoch": 0.77, + "learning_rate": 3.1077638968120984e-06, + "loss": 1.2862, + "step": 7322 + }, + { + "epoch": 0.77, + "learning_rate": 3.1051123291263975e-06, + "loss": 1.5172, + "step": 7323 + }, + { + "epoch": 0.77, + "learning_rate": 3.102461685178486e-06, + "loss": 1.3757, + "step": 7324 + }, + { + "epoch": 0.77, + "learning_rate": 3.099811965323485e-06, + "loss": 1.3082, + "step": 7325 + }, + { + "epoch": 0.77, + "learning_rate": 3.097163169916383e-06, + "loss": 1.3674, + "step": 7326 + }, + { + "epoch": 0.77, + "learning_rate": 3.0945152993120574e-06, + "loss": 1.3168, + "step": 7327 + }, + { + "epoch": 0.77, + "learning_rate": 3.0918683538652474e-06, + "loss": 1.3122, + "step": 7328 + }, + { + "epoch": 0.77, + "learning_rate": 3.089222333930579e-06, + "loss": 1.3437, + "step": 7329 + }, + { + "epoch": 0.77, + "learning_rate": 3.0865772398625548e-06, + "loss": 1.371, + "step": 7330 + }, + { + "epoch": 0.77, + "learning_rate": 3.0839330720155426e-06, + "loss": 1.327, + "step": 7331 + }, + { + "epoch": 0.77, + "learning_rate": 3.0812898307437955e-06, + "loss": 1.3369, + "step": 7332 + }, + { + "epoch": 0.77, + "learning_rate": 3.078647516401444e-06, + "loss": 1.2148, + "step": 7333 + }, + { + "epoch": 0.77, + "learning_rate": 3.0760061293424846e-06, + "loss": 1.3074, + "step": 7334 + }, + { + "epoch": 0.77, + "learning_rate": 3.073365669920797e-06, + "loss": 1.3218, + "step": 7335 + }, + { + "epoch": 0.77, + "learning_rate": 3.070726138490139e-06, + "loss": 1.2974, + "step": 7336 + }, + { + "epoch": 0.77, + "learning_rate": 3.0680875354041327e-06, + "loss": 1.3037, + "step": 7337 + }, + { + "epoch": 0.77, + "learning_rate": 3.065449861016291e-06, + "loss": 1.5706, + "step": 7338 + }, + { + "epoch": 0.77, + "learning_rate": 3.0628131156799857e-06, + "loss": 1.3346, + "step": 7339 + }, + { + "epoch": 0.77, + "learning_rate": 3.0601772997484793e-06, + "loss": 1.6488, + "step": 7340 + }, + { + "epoch": 0.77, + "learning_rate": 3.0575424135749045e-06, + "loss": 1.2929, + "step": 7341 + }, + { + "epoch": 0.77, + "learning_rate": 3.0549084575122625e-06, + "loss": 1.3137, + "step": 7342 + }, + { + "epoch": 0.77, + "learning_rate": 3.0522754319134373e-06, + "loss": 1.3218, + "step": 7343 + }, + { + "epoch": 0.77, + "learning_rate": 3.0496433371311927e-06, + "loss": 1.2805, + "step": 7344 + }, + { + "epoch": 0.77, + "learning_rate": 3.0470121735181544e-06, + "loss": 1.2218, + "step": 7345 + }, + { + "epoch": 0.77, + "learning_rate": 3.0443819414268373e-06, + "loss": 1.381, + "step": 7346 + }, + { + "epoch": 0.77, + "learning_rate": 3.0417526412096164e-06, + "loss": 1.3571, + "step": 7347 + }, + { + "epoch": 0.77, + "learning_rate": 3.0391242732187565e-06, + "loss": 1.3295, + "step": 7348 + }, + { + "epoch": 0.77, + "learning_rate": 3.036496837806393e-06, + "loss": 1.3795, + "step": 7349 + }, + { + "epoch": 0.77, + "learning_rate": 3.033870335324528e-06, + "loss": 1.282, + "step": 7350 + }, + { + "epoch": 0.77, + "learning_rate": 3.03124476612505e-06, + "loss": 1.3428, + "step": 7351 + }, + { + "epoch": 0.77, + "learning_rate": 3.0286201305597194e-06, + "loss": 1.3321, + "step": 7352 + }, + { + "epoch": 0.77, + "learning_rate": 3.0259964289801646e-06, + "loss": 1.4135, + "step": 7353 + }, + { + "epoch": 0.77, + "learning_rate": 3.023373661737897e-06, + "loss": 1.3032, + "step": 7354 + }, + { + "epoch": 0.77, + "learning_rate": 3.0207518291843042e-06, + "loss": 1.2676, + "step": 7355 + }, + { + "epoch": 0.77, + "learning_rate": 3.0181309316706362e-06, + "loss": 1.2902, + "step": 7356 + }, + { + "epoch": 0.77, + "learning_rate": 3.0155109695480333e-06, + "loss": 1.3364, + "step": 7357 + }, + { + "epoch": 0.77, + "learning_rate": 3.0128919431674975e-06, + "loss": 1.3733, + "step": 7358 + }, + { + "epoch": 0.77, + "learning_rate": 3.0102738528799125e-06, + "loss": 1.3114, + "step": 7359 + }, + { + "epoch": 0.77, + "learning_rate": 3.007656699036039e-06, + "loss": 1.3176, + "step": 7360 + }, + { + "epoch": 0.77, + "learning_rate": 3.005040481986503e-06, + "loss": 1.301, + "step": 7361 + }, + { + "epoch": 0.77, + "learning_rate": 3.0024252020818124e-06, + "loss": 1.3281, + "step": 7362 + }, + { + "epoch": 0.77, + "learning_rate": 2.9998108596723508e-06, + "loss": 1.1587, + "step": 7363 + }, + { + "epoch": 0.77, + "eval_loss": 1.3964349031448364, + "eval_runtime": 77.4566, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 7363 + }, + { + "epoch": 0.77, + "learning_rate": 2.9971974551083673e-06, + "loss": 1.3628, + "step": 7364 + }, + { + "epoch": 0.77, + "learning_rate": 2.9945849887399958e-06, + "loss": 1.4178, + "step": 7365 + }, + { + "epoch": 0.77, + "learning_rate": 2.9919734609172356e-06, + "loss": 1.3428, + "step": 7366 + }, + { + "epoch": 0.77, + "learning_rate": 2.989362871989965e-06, + "loss": 1.2675, + "step": 7367 + }, + { + "epoch": 0.77, + "learning_rate": 2.986753222307941e-06, + "loss": 1.3353, + "step": 7368 + }, + { + "epoch": 0.77, + "learning_rate": 2.9841445122207826e-06, + "loss": 1.2842, + "step": 7369 + }, + { + "epoch": 0.77, + "learning_rate": 2.981536742077993e-06, + "loss": 1.2237, + "step": 7370 + }, + { + "epoch": 0.77, + "learning_rate": 2.9789299122289493e-06, + "loss": 1.2554, + "step": 7371 + }, + { + "epoch": 0.77, + "learning_rate": 2.976324023022893e-06, + "loss": 1.3277, + "step": 7372 + }, + { + "epoch": 0.77, + "learning_rate": 2.973719074808954e-06, + "loss": 1.3258, + "step": 7373 + }, + { + "epoch": 0.77, + "learning_rate": 2.971115067936122e-06, + "loss": 1.2757, + "step": 7374 + }, + { + "epoch": 0.77, + "learning_rate": 2.9685120027532687e-06, + "loss": 1.3267, + "step": 7375 + }, + { + "epoch": 0.77, + "learning_rate": 2.9659098796091423e-06, + "loss": 1.3451, + "step": 7376 + }, + { + "epoch": 0.77, + "learning_rate": 2.9633086988523507e-06, + "loss": 1.2742, + "step": 7377 + }, + { + "epoch": 0.77, + "learning_rate": 2.9607084608313972e-06, + "loss": 1.3589, + "step": 7378 + }, + { + "epoch": 0.77, + "learning_rate": 2.9581091658946415e-06, + "loss": 1.2839, + "step": 7379 + }, + { + "epoch": 0.77, + "learning_rate": 2.9555108143903187e-06, + "loss": 1.2883, + "step": 7380 + }, + { + "epoch": 0.77, + "learning_rate": 2.9529134066665453e-06, + "loss": 1.2781, + "step": 7381 + }, + { + "epoch": 0.77, + "learning_rate": 2.9503169430713084e-06, + "loss": 1.3638, + "step": 7382 + }, + { + "epoch": 0.77, + "learning_rate": 2.947721423952463e-06, + "loss": 1.3284, + "step": 7383 + }, + { + "epoch": 0.77, + "learning_rate": 2.945126849657748e-06, + "loss": 1.4043, + "step": 7384 + }, + { + "epoch": 0.77, + "learning_rate": 2.9425332205347624e-06, + "loss": 1.3173, + "step": 7385 + }, + { + "epoch": 0.77, + "learning_rate": 2.9399405369309884e-06, + "loss": 1.2099, + "step": 7386 + }, + { + "epoch": 0.77, + "learning_rate": 2.9373487991937845e-06, + "loss": 1.3062, + "step": 7387 + }, + { + "epoch": 0.77, + "learning_rate": 2.9347580076703695e-06, + "loss": 1.3075, + "step": 7388 + }, + { + "epoch": 0.77, + "learning_rate": 2.932168162707846e-06, + "loss": 1.3129, + "step": 7389 + }, + { + "epoch": 0.77, + "learning_rate": 2.9295792646531882e-06, + "loss": 1.4852, + "step": 7390 + }, + { + "epoch": 0.78, + "learning_rate": 2.926991313853239e-06, + "loss": 1.303, + "step": 7391 + }, + { + "epoch": 0.78, + "learning_rate": 2.9244043106547214e-06, + "loss": 1.2761, + "step": 7392 + }, + { + "epoch": 0.78, + "learning_rate": 2.9218182554042206e-06, + "loss": 1.2693, + "step": 7393 + }, + { + "epoch": 0.78, + "learning_rate": 2.9192331484482074e-06, + "loss": 1.2966, + "step": 7394 + }, + { + "epoch": 0.78, + "learning_rate": 2.9166489901330195e-06, + "loss": 1.3091, + "step": 7395 + }, + { + "epoch": 0.78, + "learning_rate": 2.91406578080486e-06, + "loss": 1.373, + "step": 7396 + }, + { + "epoch": 0.78, + "learning_rate": 2.9114835208098257e-06, + "loss": 1.2369, + "step": 7397 + }, + { + "epoch": 0.78, + "learning_rate": 2.908902210493866e-06, + "loss": 1.6399, + "step": 7398 + }, + { + "epoch": 0.78, + "learning_rate": 2.906321850202806e-06, + "loss": 1.3121, + "step": 7399 + }, + { + "epoch": 0.78, + "learning_rate": 2.903742440282352e-06, + "loss": 1.3401, + "step": 7400 + }, + { + "epoch": 0.78, + "learning_rate": 2.9011639810780833e-06, + "loss": 1.2974, + "step": 7401 + }, + { + "epoch": 0.78, + "learning_rate": 2.8985864729354383e-06, + "loss": 1.2825, + "step": 7402 + }, + { + "epoch": 0.78, + "learning_rate": 2.8960099161997434e-06, + "loss": 1.4901, + "step": 7403 + }, + { + "epoch": 0.78, + "learning_rate": 2.8934343112161867e-06, + "loss": 1.3203, + "step": 7404 + }, + { + "epoch": 0.78, + "learning_rate": 2.8908596583298343e-06, + "loss": 1.2859, + "step": 7405 + }, + { + "epoch": 0.78, + "learning_rate": 2.888285957885628e-06, + "loss": 1.334, + "step": 7406 + }, + { + "epoch": 0.78, + "learning_rate": 2.8857132102283703e-06, + "loss": 1.3358, + "step": 7407 + }, + { + "epoch": 0.78, + "learning_rate": 2.883141415702747e-06, + "loss": 1.2927, + "step": 7408 + }, + { + "epoch": 0.78, + "learning_rate": 2.8805705746533154e-06, + "loss": 1.3846, + "step": 7409 + }, + { + "epoch": 0.78, + "learning_rate": 2.8780006874244947e-06, + "loss": 1.2857, + "step": 7410 + }, + { + "epoch": 0.78, + "learning_rate": 2.8754317543605923e-06, + "loss": 1.3791, + "step": 7411 + }, + { + "epoch": 0.78, + "learning_rate": 2.872863775805772e-06, + "loss": 1.3286, + "step": 7412 + }, + { + "epoch": 0.78, + "learning_rate": 2.870296752104079e-06, + "loss": 1.244, + "step": 7413 + }, + { + "epoch": 0.78, + "learning_rate": 2.8677306835994335e-06, + "loss": 1.3673, + "step": 7414 + }, + { + "epoch": 0.78, + "learning_rate": 2.865165570635615e-06, + "loss": 1.3123, + "step": 7415 + }, + { + "epoch": 0.78, + "learning_rate": 2.862601413556286e-06, + "loss": 1.2867, + "step": 7416 + }, + { + "epoch": 0.78, + "learning_rate": 2.860038212704982e-06, + "loss": 1.3254, + "step": 7417 + }, + { + "epoch": 0.78, + "learning_rate": 2.8574759684250985e-06, + "loss": 1.2298, + "step": 7418 + }, + { + "epoch": 0.78, + "learning_rate": 2.854914681059914e-06, + "loss": 1.3054, + "step": 7419 + }, + { + "epoch": 0.78, + "learning_rate": 2.8523543509525785e-06, + "loss": 1.2984, + "step": 7420 + }, + { + "epoch": 0.78, + "learning_rate": 2.8497949784461043e-06, + "loss": 1.2848, + "step": 7421 + }, + { + "epoch": 0.78, + "learning_rate": 2.847236563883388e-06, + "loss": 1.4184, + "step": 7422 + }, + { + "epoch": 0.78, + "learning_rate": 2.84467910760718e-06, + "loss": 1.3967, + "step": 7423 + }, + { + "epoch": 0.78, + "learning_rate": 2.8421226099601284e-06, + "loss": 1.2847, + "step": 7424 + }, + { + "epoch": 0.78, + "learning_rate": 2.8395670712847322e-06, + "loss": 1.3681, + "step": 7425 + }, + { + "epoch": 0.78, + "learning_rate": 2.837012491923363e-06, + "loss": 1.3114, + "step": 7426 + }, + { + "epoch": 0.78, + "learning_rate": 2.834458872218274e-06, + "loss": 1.3264, + "step": 7427 + }, + { + "epoch": 0.78, + "learning_rate": 2.831906212511586e-06, + "loss": 1.3019, + "step": 7428 + }, + { + "epoch": 0.78, + "learning_rate": 2.829354513145284e-06, + "loss": 1.2619, + "step": 7429 + }, + { + "epoch": 0.78, + "learning_rate": 2.8268037744612362e-06, + "loss": 1.2825, + "step": 7430 + }, + { + "epoch": 0.78, + "learning_rate": 2.824253996801172e-06, + "loss": 1.2942, + "step": 7431 + }, + { + "epoch": 0.78, + "learning_rate": 2.8217051805066953e-06, + "loss": 1.3907, + "step": 7432 + }, + { + "epoch": 0.78, + "learning_rate": 2.8191573259192884e-06, + "loss": 1.2871, + "step": 7433 + }, + { + "epoch": 0.78, + "learning_rate": 2.81661043338029e-06, + "loss": 1.3924, + "step": 7434 + }, + { + "epoch": 0.78, + "learning_rate": 2.814064503230923e-06, + "loss": 1.3649, + "step": 7435 + }, + { + "epoch": 0.78, + "learning_rate": 2.8115195358122795e-06, + "loss": 1.3475, + "step": 7436 + }, + { + "epoch": 0.78, + "learning_rate": 2.808975531465312e-06, + "loss": 1.3736, + "step": 7437 + }, + { + "epoch": 0.78, + "learning_rate": 2.806432490530859e-06, + "loss": 1.2908, + "step": 7438 + }, + { + "epoch": 0.78, + "learning_rate": 2.803890413349618e-06, + "loss": 1.3991, + "step": 7439 + }, + { + "epoch": 0.78, + "learning_rate": 2.8013493002621617e-06, + "loss": 1.2928, + "step": 7440 + }, + { + "epoch": 0.78, + "learning_rate": 2.79880915160894e-06, + "loss": 1.3408, + "step": 7441 + }, + { + "epoch": 0.78, + "learning_rate": 2.7962699677302574e-06, + "loss": 1.3045, + "step": 7442 + }, + { + "epoch": 0.78, + "learning_rate": 2.793731748966311e-06, + "loss": 1.3179, + "step": 7443 + }, + { + "epoch": 0.78, + "learning_rate": 2.791194495657151e-06, + "loss": 1.2709, + "step": 7444 + }, + { + "epoch": 0.78, + "learning_rate": 2.7886582081427014e-06, + "loss": 1.3635, + "step": 7445 + }, + { + "epoch": 0.78, + "learning_rate": 2.786122886762762e-06, + "loss": 1.323, + "step": 7446 + }, + { + "epoch": 0.78, + "learning_rate": 2.7835885318570054e-06, + "loss": 1.2629, + "step": 7447 + }, + { + "epoch": 0.78, + "learning_rate": 2.7810551437649613e-06, + "loss": 1.4308, + "step": 7448 + }, + { + "epoch": 0.78, + "learning_rate": 2.778522722826048e-06, + "loss": 1.3546, + "step": 7449 + }, + { + "epoch": 0.78, + "learning_rate": 2.775991269379532e-06, + "loss": 1.4486, + "step": 7450 + }, + { + "epoch": 0.78, + "learning_rate": 2.773460783764579e-06, + "loss": 1.2845, + "step": 7451 + }, + { + "epoch": 0.78, + "learning_rate": 2.7709312663201993e-06, + "loss": 1.2393, + "step": 7452 + }, + { + "epoch": 0.78, + "learning_rate": 2.7684027173852836e-06, + "loss": 1.2939, + "step": 7453 + }, + { + "epoch": 0.78, + "learning_rate": 2.7658751372985926e-06, + "loss": 1.5802, + "step": 7454 + }, + { + "epoch": 0.78, + "learning_rate": 2.7633485263987627e-06, + "loss": 1.258, + "step": 7455 + }, + { + "epoch": 0.78, + "learning_rate": 2.760822885024286e-06, + "loss": 1.3223, + "step": 7456 + }, + { + "epoch": 0.78, + "learning_rate": 2.7582982135135418e-06, + "loss": 1.277, + "step": 7457 + }, + { + "epoch": 0.78, + "learning_rate": 2.755774512204764e-06, + "loss": 1.3047, + "step": 7458 + }, + { + "epoch": 0.78, + "learning_rate": 2.753251781436068e-06, + "loss": 1.3021, + "step": 7459 + }, + { + "epoch": 0.78, + "learning_rate": 2.750730021545437e-06, + "loss": 1.3321, + "step": 7460 + }, + { + "epoch": 0.78, + "learning_rate": 2.7482092328707154e-06, + "loss": 1.2453, + "step": 7461 + }, + { + "epoch": 0.78, + "learning_rate": 2.7456894157496293e-06, + "loss": 1.2628, + "step": 7462 + }, + { + "epoch": 0.78, + "learning_rate": 2.74317057051977e-06, + "loss": 1.4221, + "step": 7463 + }, + { + "epoch": 0.78, + "learning_rate": 2.740652697518593e-06, + "loss": 1.3034, + "step": 7464 + }, + { + "epoch": 0.78, + "learning_rate": 2.738135797083432e-06, + "loss": 1.2944, + "step": 7465 + }, + { + "epoch": 0.78, + "learning_rate": 2.7356198695514893e-06, + "loss": 1.3434, + "step": 7466 + }, + { + "epoch": 0.78, + "learning_rate": 2.733104915259829e-06, + "loss": 1.3127, + "step": 7467 + }, + { + "epoch": 0.78, + "learning_rate": 2.730590934545396e-06, + "loss": 1.2425, + "step": 7468 + }, + { + "epoch": 0.78, + "learning_rate": 2.7280779277449907e-06, + "loss": 1.4366, + "step": 7469 + }, + { + "epoch": 0.78, + "learning_rate": 2.7255658951953036e-06, + "loss": 1.3024, + "step": 7470 + }, + { + "epoch": 0.78, + "learning_rate": 2.7230548372328745e-06, + "loss": 1.2768, + "step": 7471 + }, + { + "epoch": 0.78, + "learning_rate": 2.720544754194121e-06, + "loss": 1.2453, + "step": 7472 + }, + { + "epoch": 0.78, + "learning_rate": 2.7180356464153303e-06, + "loss": 1.2796, + "step": 7473 + }, + { + "epoch": 0.78, + "learning_rate": 2.715527514232661e-06, + "loss": 1.3181, + "step": 7474 + }, + { + "epoch": 0.78, + "learning_rate": 2.7130203579821344e-06, + "loss": 1.4013, + "step": 7475 + }, + { + "epoch": 0.78, + "learning_rate": 2.710514177999649e-06, + "loss": 1.3365, + "step": 7476 + }, + { + "epoch": 0.78, + "learning_rate": 2.7080089746209614e-06, + "loss": 1.31, + "step": 7477 + }, + { + "epoch": 0.78, + "learning_rate": 2.7055047481817153e-06, + "loss": 1.258, + "step": 7478 + }, + { + "epoch": 0.78, + "learning_rate": 2.7030014990174068e-06, + "loss": 1.2199, + "step": 7479 + }, + { + "epoch": 0.78, + "learning_rate": 2.7004992274634046e-06, + "loss": 1.3007, + "step": 7480 + }, + { + "epoch": 0.78, + "learning_rate": 2.69799793385495e-06, + "loss": 1.2772, + "step": 7481 + }, + { + "epoch": 0.78, + "learning_rate": 2.6954976185271576e-06, + "loss": 1.4021, + "step": 7482 + }, + { + "epoch": 0.78, + "learning_rate": 2.692998281814998e-06, + "loss": 1.3183, + "step": 7483 + }, + { + "epoch": 0.78, + "learning_rate": 2.6904999240533246e-06, + "loss": 1.3412, + "step": 7484 + }, + { + "epoch": 0.78, + "learning_rate": 2.6880025455768465e-06, + "loss": 1.2552, + "step": 7485 + }, + { + "epoch": 0.79, + "learning_rate": 2.6855061467201517e-06, + "loss": 1.2525, + "step": 7486 + }, + { + "epoch": 0.79, + "learning_rate": 2.683010727817695e-06, + "loss": 1.269, + "step": 7487 + }, + { + "epoch": 0.79, + "learning_rate": 2.680516289203793e-06, + "loss": 1.5189, + "step": 7488 + }, + { + "epoch": 0.79, + "learning_rate": 2.6780228312126454e-06, + "loss": 1.2999, + "step": 7489 + }, + { + "epoch": 0.79, + "learning_rate": 2.675530354178306e-06, + "loss": 1.3322, + "step": 7490 + }, + { + "epoch": 0.79, + "learning_rate": 2.6730388584347e-06, + "loss": 1.3918, + "step": 7491 + }, + { + "epoch": 0.79, + "learning_rate": 2.670548344315628e-06, + "loss": 1.4438, + "step": 7492 + }, + { + "epoch": 0.79, + "learning_rate": 2.6680588121547546e-06, + "loss": 1.3393, + "step": 7493 + }, + { + "epoch": 0.79, + "learning_rate": 2.6655702622856105e-06, + "loss": 1.301, + "step": 7494 + }, + { + "epoch": 0.79, + "learning_rate": 2.6630826950416024e-06, + "loss": 1.2463, + "step": 7495 + }, + { + "epoch": 0.79, + "learning_rate": 2.660596110755991e-06, + "loss": 1.2641, + "step": 7496 + }, + { + "epoch": 0.79, + "learning_rate": 2.6581105097619264e-06, + "loss": 1.3824, + "step": 7497 + }, + { + "epoch": 0.79, + "learning_rate": 2.6556258923924104e-06, + "loss": 1.339, + "step": 7498 + }, + { + "epoch": 0.79, + "learning_rate": 2.6531422589803134e-06, + "loss": 1.2653, + "step": 7499 + }, + { + "epoch": 0.79, + "learning_rate": 2.6506596098583826e-06, + "loss": 1.2773, + "step": 7500 + }, + { + "epoch": 0.79, + "learning_rate": 2.648177945359233e-06, + "loss": 1.1829, + "step": 7501 + }, + { + "epoch": 0.79, + "learning_rate": 2.6456972658153358e-06, + "loss": 1.4014, + "step": 7502 + }, + { + "epoch": 0.79, + "learning_rate": 2.6432175715590446e-06, + "loss": 1.3648, + "step": 7503 + }, + { + "epoch": 0.79, + "learning_rate": 2.6407388629225706e-06, + "loss": 1.2731, + "step": 7504 + }, + { + "epoch": 0.79, + "learning_rate": 2.6382611402379988e-06, + "loss": 1.3076, + "step": 7505 + }, + { + "epoch": 0.79, + "learning_rate": 2.6357844038372824e-06, + "loss": 1.2054, + "step": 7506 + }, + { + "epoch": 0.79, + "learning_rate": 2.6333086540522366e-06, + "loss": 1.2579, + "step": 7507 + }, + { + "epoch": 0.79, + "learning_rate": 2.6308338912145493e-06, + "loss": 1.316, + "step": 7508 + }, + { + "epoch": 0.79, + "learning_rate": 2.6283601156557792e-06, + "loss": 1.2957, + "step": 7509 + }, + { + "epoch": 0.79, + "learning_rate": 2.625887327707343e-06, + "loss": 1.3017, + "step": 7510 + }, + { + "epoch": 0.79, + "learning_rate": 2.6234155277005334e-06, + "loss": 1.2591, + "step": 7511 + }, + { + "epoch": 0.79, + "learning_rate": 2.62094471596651e-06, + "loss": 1.3582, + "step": 7512 + }, + { + "epoch": 0.79, + "learning_rate": 2.6184748928362934e-06, + "loss": 1.3026, + "step": 7513 + }, + { + "epoch": 0.79, + "learning_rate": 2.616006058640782e-06, + "loss": 1.3222, + "step": 7514 + }, + { + "epoch": 0.79, + "learning_rate": 2.6135382137107268e-06, + "loss": 1.2785, + "step": 7515 + }, + { + "epoch": 0.79, + "learning_rate": 2.6110713583767687e-06, + "loss": 1.3227, + "step": 7516 + }, + { + "epoch": 0.79, + "learning_rate": 2.608605492969396e-06, + "loss": 1.2695, + "step": 7517 + }, + { + "epoch": 0.79, + "learning_rate": 2.6061406178189684e-06, + "loss": 1.2809, + "step": 7518 + }, + { + "epoch": 0.79, + "learning_rate": 2.6036767332557188e-06, + "loss": 1.2934, + "step": 7519 + }, + { + "epoch": 0.79, + "learning_rate": 2.6012138396097473e-06, + "loss": 1.2484, + "step": 7520 + }, + { + "epoch": 0.79, + "learning_rate": 2.5987519372110125e-06, + "loss": 1.3422, + "step": 7521 + }, + { + "epoch": 0.79, + "learning_rate": 2.596291026389354e-06, + "loss": 1.3008, + "step": 7522 + }, + { + "epoch": 0.79, + "learning_rate": 2.5938311074744582e-06, + "loss": 1.3698, + "step": 7523 + }, + { + "epoch": 0.79, + "learning_rate": 2.5913721807959045e-06, + "loss": 1.3034, + "step": 7524 + }, + { + "epoch": 0.79, + "learning_rate": 2.5889142466831208e-06, + "loss": 1.3011, + "step": 7525 + }, + { + "epoch": 0.79, + "learning_rate": 2.586457305465403e-06, + "loss": 1.3626, + "step": 7526 + }, + { + "epoch": 0.79, + "learning_rate": 2.5840013574719213e-06, + "loss": 1.3018, + "step": 7527 + }, + { + "epoch": 0.79, + "learning_rate": 2.581546403031713e-06, + "loss": 1.3316, + "step": 7528 + }, + { + "epoch": 0.79, + "learning_rate": 2.579092442473673e-06, + "loss": 1.2534, + "step": 7529 + }, + { + "epoch": 0.79, + "learning_rate": 2.5766394761265743e-06, + "loss": 1.2949, + "step": 7530 + }, + { + "epoch": 0.79, + "learning_rate": 2.574187504319046e-06, + "loss": 1.2962, + "step": 7531 + }, + { + "epoch": 0.79, + "learning_rate": 2.5717365273795914e-06, + "loss": 1.2926, + "step": 7532 + }, + { + "epoch": 0.79, + "learning_rate": 2.5692865456365824e-06, + "loss": 1.3136, + "step": 7533 + }, + { + "epoch": 0.79, + "learning_rate": 2.5668375594182447e-06, + "loss": 1.3065, + "step": 7534 + }, + { + "epoch": 0.79, + "learning_rate": 2.564389569052691e-06, + "loss": 1.3631, + "step": 7535 + }, + { + "epoch": 0.79, + "learning_rate": 2.5619425748678827e-06, + "loss": 1.3028, + "step": 7536 + }, + { + "epoch": 0.79, + "learning_rate": 2.5594965771916526e-06, + "loss": 1.3212, + "step": 7537 + }, + { + "epoch": 0.79, + "learning_rate": 2.557051576351702e-06, + "loss": 1.3154, + "step": 7538 + }, + { + "epoch": 0.79, + "learning_rate": 2.554607572675605e-06, + "loss": 1.284, + "step": 7539 + }, + { + "epoch": 0.79, + "learning_rate": 2.5521645664907856e-06, + "loss": 1.3833, + "step": 7540 + }, + { + "epoch": 0.79, + "learning_rate": 2.549722558124551e-06, + "loss": 1.3079, + "step": 7541 + }, + { + "epoch": 0.79, + "learning_rate": 2.54728154790406e-06, + "loss": 1.3104, + "step": 7542 + }, + { + "epoch": 0.79, + "learning_rate": 2.544841536156356e-06, + "loss": 1.2933, + "step": 7543 + }, + { + "epoch": 0.79, + "learning_rate": 2.5424025232083315e-06, + "loss": 1.4103, + "step": 7544 + }, + { + "epoch": 0.79, + "learning_rate": 2.53996450938675e-06, + "loss": 1.3602, + "step": 7545 + }, + { + "epoch": 0.79, + "learning_rate": 2.537527495018244e-06, + "loss": 1.381, + "step": 7546 + }, + { + "epoch": 0.79, + "learning_rate": 2.535091480429315e-06, + "loss": 1.4212, + "step": 7547 + }, + { + "epoch": 0.79, + "learning_rate": 2.5326564659463203e-06, + "loss": 1.3662, + "step": 7548 + }, + { + "epoch": 0.79, + "learning_rate": 2.5302224518954944e-06, + "loss": 1.2896, + "step": 7549 + }, + { + "epoch": 0.79, + "learning_rate": 2.5277894386029246e-06, + "loss": 1.3218, + "step": 7550 + }, + { + "epoch": 0.79, + "learning_rate": 2.5253574263945835e-06, + "loss": 1.337, + "step": 7551 + }, + { + "epoch": 0.79, + "learning_rate": 2.522926415596293e-06, + "loss": 1.3457, + "step": 7552 + }, + { + "epoch": 0.79, + "learning_rate": 2.5204964065337423e-06, + "loss": 1.3227, + "step": 7553 + }, + { + "epoch": 0.79, + "learning_rate": 2.5180673995324933e-06, + "loss": 1.2529, + "step": 7554 + }, + { + "epoch": 0.79, + "learning_rate": 2.5156393949179746e-06, + "loss": 1.3193, + "step": 7555 + }, + { + "epoch": 0.79, + "learning_rate": 2.5132123930154697e-06, + "loss": 1.2719, + "step": 7556 + }, + { + "epoch": 0.79, + "learning_rate": 2.5107863941501363e-06, + "loss": 1.3367, + "step": 7557 + }, + { + "epoch": 0.79, + "learning_rate": 2.508361398647e-06, + "loss": 1.2918, + "step": 7558 + }, + { + "epoch": 0.79, + "learning_rate": 2.505937406830942e-06, + "loss": 1.3458, + "step": 7559 + }, + { + "epoch": 0.79, + "learning_rate": 2.5035144190267215e-06, + "loss": 1.3975, + "step": 7560 + }, + { + "epoch": 0.79, + "learning_rate": 2.5010924355589463e-06, + "loss": 1.3717, + "step": 7561 + }, + { + "epoch": 0.79, + "learning_rate": 2.498671456752112e-06, + "loss": 1.316, + "step": 7562 + }, + { + "epoch": 0.79, + "eval_loss": 1.3956769704818726, + "eval_runtime": 77.5888, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 7562 + }, + { + "epoch": 0.79, + "learning_rate": 2.496251482930563e-06, + "loss": 1.2949, + "step": 7563 + }, + { + "epoch": 0.79, + "learning_rate": 2.4938325144185094e-06, + "loss": 1.6856, + "step": 7564 + }, + { + "epoch": 0.79, + "learning_rate": 2.4914145515400347e-06, + "loss": 1.4064, + "step": 7565 + }, + { + "epoch": 0.79, + "learning_rate": 2.4889975946190847e-06, + "loss": 1.3279, + "step": 7566 + }, + { + "epoch": 0.79, + "learning_rate": 2.4865816439794666e-06, + "loss": 1.2923, + "step": 7567 + }, + { + "epoch": 0.79, + "learning_rate": 2.48416669994486e-06, + "loss": 1.3237, + "step": 7568 + }, + { + "epoch": 0.79, + "learning_rate": 2.481752762838796e-06, + "loss": 1.3424, + "step": 7569 + }, + { + "epoch": 0.79, + "learning_rate": 2.479339832984693e-06, + "loss": 1.1656, + "step": 7570 + }, + { + "epoch": 0.79, + "learning_rate": 2.476927910705814e-06, + "loss": 1.1659, + "step": 7571 + }, + { + "epoch": 0.79, + "learning_rate": 2.4745169963252945e-06, + "loss": 1.3452, + "step": 7572 + }, + { + "epoch": 0.79, + "learning_rate": 2.472107090166136e-06, + "loss": 1.4011, + "step": 7573 + }, + { + "epoch": 0.79, + "learning_rate": 2.4696981925512076e-06, + "loss": 1.2312, + "step": 7574 + }, + { + "epoch": 0.79, + "learning_rate": 2.4672903038032335e-06, + "loss": 1.3257, + "step": 7575 + }, + { + "epoch": 0.79, + "learning_rate": 2.464883424244815e-06, + "loss": 1.2795, + "step": 7576 + }, + { + "epoch": 0.79, + "learning_rate": 2.4624775541984025e-06, + "loss": 1.3514, + "step": 7577 + }, + { + "epoch": 0.79, + "learning_rate": 2.4600726939863338e-06, + "loss": 1.3736, + "step": 7578 + }, + { + "epoch": 0.79, + "learning_rate": 2.4576688439307926e-06, + "loss": 1.3361, + "step": 7579 + }, + { + "epoch": 0.79, + "learning_rate": 2.4552660043538255e-06, + "loss": 1.3047, + "step": 7580 + }, + { + "epoch": 0.79, + "learning_rate": 2.452864175577364e-06, + "loss": 1.2987, + "step": 7581 + }, + { + "epoch": 0.8, + "learning_rate": 2.4504633579231863e-06, + "loss": 1.3218, + "step": 7582 + }, + { + "epoch": 0.8, + "learning_rate": 2.448063551712937e-06, + "loss": 1.3159, + "step": 7583 + }, + { + "epoch": 0.8, + "learning_rate": 2.44566475726813e-06, + "loss": 1.3032, + "step": 7584 + }, + { + "epoch": 0.8, + "learning_rate": 2.443266974910147e-06, + "loss": 1.2298, + "step": 7585 + }, + { + "epoch": 0.8, + "learning_rate": 2.4408702049602217e-06, + "loss": 1.288, + "step": 7586 + }, + { + "epoch": 0.8, + "learning_rate": 2.4384744477394663e-06, + "loss": 1.2733, + "step": 7587 + }, + { + "epoch": 0.8, + "learning_rate": 2.4360797035688424e-06, + "loss": 1.3576, + "step": 7588 + }, + { + "epoch": 0.8, + "learning_rate": 2.4336859727691953e-06, + "loss": 1.3029, + "step": 7589 + }, + { + "epoch": 0.8, + "learning_rate": 2.4312932556612178e-06, + "loss": 1.4056, + "step": 7590 + }, + { + "epoch": 0.8, + "learning_rate": 2.4289015525654693e-06, + "loss": 1.3129, + "step": 7591 + }, + { + "epoch": 0.8, + "learning_rate": 2.426510863802379e-06, + "loss": 1.2301, + "step": 7592 + }, + { + "epoch": 0.8, + "learning_rate": 2.4241211896922422e-06, + "loss": 1.282, + "step": 7593 + }, + { + "epoch": 0.8, + "learning_rate": 2.4217325305552073e-06, + "loss": 1.3173, + "step": 7594 + }, + { + "epoch": 0.8, + "learning_rate": 2.419344886711299e-06, + "loss": 1.3387, + "step": 7595 + }, + { + "epoch": 0.8, + "learning_rate": 2.416958258480391e-06, + "loss": 1.3313, + "step": 7596 + }, + { + "epoch": 0.8, + "learning_rate": 2.4145726461822428e-06, + "loss": 1.437, + "step": 7597 + }, + { + "epoch": 0.8, + "learning_rate": 2.412188050136458e-06, + "loss": 1.288, + "step": 7598 + }, + { + "epoch": 0.8, + "learning_rate": 2.40980447066251e-06, + "loss": 1.2815, + "step": 7599 + }, + { + "epoch": 0.8, + "learning_rate": 2.407421908079738e-06, + "loss": 1.3769, + "step": 7600 + }, + { + "epoch": 0.8, + "learning_rate": 2.405040362707349e-06, + "loss": 1.2726, + "step": 7601 + }, + { + "epoch": 0.8, + "learning_rate": 2.4026598348644027e-06, + "loss": 1.3741, + "step": 7602 + }, + { + "epoch": 0.8, + "learning_rate": 2.4002803248698303e-06, + "loss": 1.3046, + "step": 7603 + }, + { + "epoch": 0.8, + "learning_rate": 2.3979018330424284e-06, + "loss": 1.2566, + "step": 7604 + }, + { + "epoch": 0.8, + "learning_rate": 2.3955243597008504e-06, + "loss": 1.3237, + "step": 7605 + }, + { + "epoch": 0.8, + "learning_rate": 2.3931479051636184e-06, + "loss": 1.2446, + "step": 7606 + }, + { + "epoch": 0.8, + "learning_rate": 2.390772469749111e-06, + "loss": 1.2495, + "step": 7607 + }, + { + "epoch": 0.8, + "learning_rate": 2.3883980537755848e-06, + "loss": 1.326, + "step": 7608 + }, + { + "epoch": 0.8, + "learning_rate": 2.386024657561146e-06, + "loss": 1.2979, + "step": 7609 + }, + { + "epoch": 0.8, + "learning_rate": 2.3836522814237652e-06, + "loss": 1.2877, + "step": 7610 + }, + { + "epoch": 0.8, + "learning_rate": 2.381280925681283e-06, + "loss": 1.3327, + "step": 7611 + }, + { + "epoch": 0.8, + "learning_rate": 2.3789105906514034e-06, + "loss": 1.2641, + "step": 7612 + }, + { + "epoch": 0.8, + "learning_rate": 2.3765412766516837e-06, + "loss": 1.2904, + "step": 7613 + }, + { + "epoch": 0.8, + "learning_rate": 2.3741729839995573e-06, + "loss": 1.3153, + "step": 7614 + }, + { + "epoch": 0.8, + "learning_rate": 2.3718057130123063e-06, + "loss": 1.3168, + "step": 7615 + }, + { + "epoch": 0.8, + "learning_rate": 2.369439464007095e-06, + "loss": 1.2751, + "step": 7616 + }, + { + "epoch": 0.8, + "learning_rate": 2.3670742373009358e-06, + "loss": 1.3033, + "step": 7617 + }, + { + "epoch": 0.8, + "learning_rate": 2.364710033210703e-06, + "loss": 1.2788, + "step": 7618 + }, + { + "epoch": 0.8, + "learning_rate": 2.362346852053143e-06, + "loss": 1.3195, + "step": 7619 + }, + { + "epoch": 0.8, + "learning_rate": 2.3599846941448655e-06, + "loss": 1.2592, + "step": 7620 + }, + { + "epoch": 0.8, + "learning_rate": 2.357623559802332e-06, + "loss": 1.2495, + "step": 7621 + }, + { + "epoch": 0.8, + "learning_rate": 2.3552634493418803e-06, + "loss": 1.3111, + "step": 7622 + }, + { + "epoch": 0.8, + "learning_rate": 2.3529043630796954e-06, + "loss": 1.2559, + "step": 7623 + }, + { + "epoch": 0.8, + "learning_rate": 2.3505463013318454e-06, + "loss": 1.2642, + "step": 7624 + }, + { + "epoch": 0.8, + "learning_rate": 2.3481892644142455e-06, + "loss": 1.3277, + "step": 7625 + }, + { + "epoch": 0.8, + "learning_rate": 2.345833252642671e-06, + "loss": 1.3161, + "step": 7626 + }, + { + "epoch": 0.8, + "learning_rate": 2.3434782663327783e-06, + "loss": 1.2901, + "step": 7627 + }, + { + "epoch": 0.8, + "learning_rate": 2.341124305800071e-06, + "loss": 1.26, + "step": 7628 + }, + { + "epoch": 0.8, + "learning_rate": 2.338771371359915e-06, + "loss": 1.2772, + "step": 7629 + }, + { + "epoch": 0.8, + "learning_rate": 2.336419463327546e-06, + "loss": 1.2841, + "step": 7630 + }, + { + "epoch": 0.8, + "learning_rate": 2.334068582018062e-06, + "loss": 1.2036, + "step": 7631 + }, + { + "epoch": 0.8, + "learning_rate": 2.331718727746417e-06, + "loss": 1.2992, + "step": 7632 + }, + { + "epoch": 0.8, + "learning_rate": 2.329369900827434e-06, + "loss": 1.3145, + "step": 7633 + }, + { + "epoch": 0.8, + "learning_rate": 2.327022101575789e-06, + "loss": 1.3954, + "step": 7634 + }, + { + "epoch": 0.8, + "learning_rate": 2.3246753303060364e-06, + "loss": 1.2916, + "step": 7635 + }, + { + "epoch": 0.8, + "learning_rate": 2.322329587332579e-06, + "loss": 1.3013, + "step": 7636 + }, + { + "epoch": 0.8, + "learning_rate": 2.319984872969683e-06, + "loss": 1.2686, + "step": 7637 + }, + { + "epoch": 0.8, + "learning_rate": 2.3176411875314806e-06, + "loss": 1.3407, + "step": 7638 + }, + { + "epoch": 0.8, + "learning_rate": 2.315298531331972e-06, + "loss": 1.5181, + "step": 7639 + }, + { + "epoch": 0.8, + "learning_rate": 2.3129569046850054e-06, + "loss": 1.5231, + "step": 7640 + }, + { + "epoch": 0.8, + "learning_rate": 2.3106163079043033e-06, + "loss": 1.4524, + "step": 7641 + }, + { + "epoch": 0.8, + "learning_rate": 2.308276741303438e-06, + "loss": 1.2935, + "step": 7642 + }, + { + "epoch": 0.8, + "learning_rate": 2.3059382051958635e-06, + "loss": 1.4096, + "step": 7643 + }, + { + "epoch": 0.8, + "learning_rate": 2.303600699894876e-06, + "loss": 1.3598, + "step": 7644 + }, + { + "epoch": 0.8, + "learning_rate": 2.3012642257136397e-06, + "loss": 1.3578, + "step": 7645 + }, + { + "epoch": 0.8, + "learning_rate": 2.2989287829651853e-06, + "loss": 1.3147, + "step": 7646 + }, + { + "epoch": 0.8, + "learning_rate": 2.296594371962403e-06, + "loss": 1.3495, + "step": 7647 + }, + { + "epoch": 0.8, + "learning_rate": 2.2942609930180393e-06, + "loss": 1.4035, + "step": 7648 + }, + { + "epoch": 0.8, + "learning_rate": 2.291928646444711e-06, + "loss": 1.2757, + "step": 7649 + }, + { + "epoch": 0.8, + "learning_rate": 2.2895973325548914e-06, + "loss": 1.2496, + "step": 7650 + }, + { + "epoch": 0.8, + "learning_rate": 2.2872670516609196e-06, + "loss": 1.3372, + "step": 7651 + }, + { + "epoch": 0.8, + "learning_rate": 2.28493780407499e-06, + "loss": 1.276, + "step": 7652 + }, + { + "epoch": 0.8, + "learning_rate": 2.2826095901091574e-06, + "loss": 1.319, + "step": 7653 + }, + { + "epoch": 0.8, + "learning_rate": 2.280282410075354e-06, + "loss": 1.3473, + "step": 7654 + }, + { + "epoch": 0.8, + "learning_rate": 2.2779562642853546e-06, + "loss": 1.2947, + "step": 7655 + }, + { + "epoch": 0.8, + "learning_rate": 2.2756311530508026e-06, + "loss": 1.3485, + "step": 7656 + }, + { + "epoch": 0.8, + "learning_rate": 2.2733070766832042e-06, + "loss": 1.3187, + "step": 7657 + }, + { + "epoch": 0.8, + "learning_rate": 2.2709840354939296e-06, + "loss": 1.3979, + "step": 7658 + }, + { + "epoch": 0.8, + "learning_rate": 2.2686620297942007e-06, + "loss": 1.269, + "step": 7659 + }, + { + "epoch": 0.8, + "learning_rate": 2.266341059895113e-06, + "loss": 1.3572, + "step": 7660 + }, + { + "epoch": 0.8, + "learning_rate": 2.264021126107607e-06, + "loss": 1.2858, + "step": 7661 + }, + { + "epoch": 0.8, + "learning_rate": 2.2617022287425073e-06, + "loss": 1.3677, + "step": 7662 + }, + { + "epoch": 0.8, + "learning_rate": 2.259384368110479e-06, + "loss": 1.3111, + "step": 7663 + }, + { + "epoch": 0.8, + "learning_rate": 2.2570675445220535e-06, + "loss": 1.2969, + "step": 7664 + }, + { + "epoch": 0.8, + "learning_rate": 2.254751758287629e-06, + "loss": 1.2901, + "step": 7665 + }, + { + "epoch": 0.8, + "learning_rate": 2.252437009717464e-06, + "loss": 1.2834, + "step": 7666 + }, + { + "epoch": 0.8, + "learning_rate": 2.2501232991216705e-06, + "loss": 1.2505, + "step": 7667 + }, + { + "epoch": 0.8, + "learning_rate": 2.2478106268102295e-06, + "loss": 1.2763, + "step": 7668 + }, + { + "epoch": 0.8, + "learning_rate": 2.2454989930929737e-06, + "loss": 1.3427, + "step": 7669 + }, + { + "epoch": 0.8, + "learning_rate": 2.2431883982796132e-06, + "loss": 1.3397, + "step": 7670 + }, + { + "epoch": 0.8, + "learning_rate": 2.240878842679702e-06, + "loss": 1.2525, + "step": 7671 + }, + { + "epoch": 0.8, + "learning_rate": 2.238570326602657e-06, + "loss": 1.2085, + "step": 7672 + }, + { + "epoch": 0.8, + "learning_rate": 2.23626285035777e-06, + "loss": 1.2196, + "step": 7673 + }, + { + "epoch": 0.8, + "learning_rate": 2.2339564142541783e-06, + "loss": 1.2602, + "step": 7674 + }, + { + "epoch": 0.8, + "learning_rate": 2.2316510186008824e-06, + "loss": 1.4144, + "step": 7675 + }, + { + "epoch": 0.8, + "learning_rate": 2.2293466637067486e-06, + "loss": 1.3239, + "step": 7676 + }, + { + "epoch": 0.81, + "learning_rate": 2.227043349880501e-06, + "loss": 1.342, + "step": 7677 + }, + { + "epoch": 0.81, + "learning_rate": 2.2247410774307276e-06, + "loss": 1.3395, + "step": 7678 + }, + { + "epoch": 0.81, + "learning_rate": 2.2224398466658712e-06, + "loss": 1.3948, + "step": 7679 + }, + { + "epoch": 0.81, + "learning_rate": 2.2201396578942325e-06, + "loss": 1.2983, + "step": 7680 + }, + { + "epoch": 0.81, + "learning_rate": 2.2178405114239877e-06, + "loss": 1.3779, + "step": 7681 + }, + { + "epoch": 0.81, + "learning_rate": 2.2155424075631583e-06, + "loss": 1.2826, + "step": 7682 + }, + { + "epoch": 0.81, + "learning_rate": 2.213245346619628e-06, + "loss": 1.3939, + "step": 7683 + }, + { + "epoch": 0.81, + "learning_rate": 2.2109493289011474e-06, + "loss": 1.298, + "step": 7684 + }, + { + "epoch": 0.81, + "learning_rate": 2.208654354715326e-06, + "loss": 1.2947, + "step": 7685 + }, + { + "epoch": 0.81, + "learning_rate": 2.2063604243696267e-06, + "loss": 1.3532, + "step": 7686 + }, + { + "epoch": 0.81, + "learning_rate": 2.204067538171382e-06, + "loss": 1.2713, + "step": 7687 + }, + { + "epoch": 0.81, + "learning_rate": 2.2017756964277713e-06, + "loss": 1.3025, + "step": 7688 + }, + { + "epoch": 0.81, + "learning_rate": 2.199484899445854e-06, + "loss": 1.2806, + "step": 7689 + }, + { + "epoch": 0.81, + "learning_rate": 2.1971951475325328e-06, + "loss": 1.3113, + "step": 7690 + }, + { + "epoch": 0.81, + "learning_rate": 2.194906440994572e-06, + "loss": 1.4729, + "step": 7691 + }, + { + "epoch": 0.81, + "learning_rate": 2.1926187801386033e-06, + "loss": 1.29, + "step": 7692 + }, + { + "epoch": 0.81, + "learning_rate": 2.1903321652711163e-06, + "loss": 1.3092, + "step": 7693 + }, + { + "epoch": 0.81, + "learning_rate": 2.188046596698454e-06, + "loss": 1.3286, + "step": 7694 + }, + { + "epoch": 0.81, + "learning_rate": 2.185762074726826e-06, + "loss": 1.3734, + "step": 7695 + }, + { + "epoch": 0.81, + "learning_rate": 2.1834785996622988e-06, + "loss": 1.3218, + "step": 7696 + }, + { + "epoch": 0.81, + "learning_rate": 2.1811961718108034e-06, + "loss": 1.3319, + "step": 7697 + }, + { + "epoch": 0.81, + "learning_rate": 2.178914791478124e-06, + "loss": 1.2732, + "step": 7698 + }, + { + "epoch": 0.81, + "learning_rate": 2.1766344589698996e-06, + "loss": 1.4451, + "step": 7699 + }, + { + "epoch": 0.81, + "learning_rate": 2.1743551745916492e-06, + "loss": 1.338, + "step": 7700 + }, + { + "epoch": 0.81, + "learning_rate": 2.172076938648732e-06, + "loss": 1.3602, + "step": 7701 + }, + { + "epoch": 0.81, + "learning_rate": 2.16979975144637e-06, + "loss": 1.2782, + "step": 7702 + }, + { + "epoch": 0.81, + "learning_rate": 2.1675236132896505e-06, + "loss": 1.2661, + "step": 7703 + }, + { + "epoch": 0.81, + "learning_rate": 2.165248524483521e-06, + "loss": 1.3031, + "step": 7704 + }, + { + "epoch": 0.81, + "learning_rate": 2.1629744853327793e-06, + "loss": 1.3754, + "step": 7705 + }, + { + "epoch": 0.81, + "learning_rate": 2.1607014961420926e-06, + "loss": 1.4255, + "step": 7706 + }, + { + "epoch": 0.81, + "learning_rate": 2.1584295572159764e-06, + "loss": 1.3955, + "step": 7707 + }, + { + "epoch": 0.81, + "learning_rate": 2.156158668858822e-06, + "loss": 1.3691, + "step": 7708 + }, + { + "epoch": 0.81, + "learning_rate": 2.153888831374865e-06, + "loss": 1.3986, + "step": 7709 + }, + { + "epoch": 0.81, + "learning_rate": 2.1516200450682036e-06, + "loss": 1.3231, + "step": 7710 + }, + { + "epoch": 0.81, + "learning_rate": 2.149352310242797e-06, + "loss": 1.2892, + "step": 7711 + }, + { + "epoch": 0.81, + "learning_rate": 2.1470856272024686e-06, + "loss": 1.289, + "step": 7712 + }, + { + "epoch": 0.81, + "learning_rate": 2.1448199962508898e-06, + "loss": 1.2804, + "step": 7713 + }, + { + "epoch": 0.81, + "learning_rate": 2.1425554176916007e-06, + "loss": 1.2599, + "step": 7714 + }, + { + "epoch": 0.81, + "learning_rate": 2.1402918918279904e-06, + "loss": 1.3082, + "step": 7715 + }, + { + "epoch": 0.81, + "learning_rate": 2.1380294189633233e-06, + "loss": 1.306, + "step": 7716 + }, + { + "epoch": 0.81, + "learning_rate": 2.1357679994007076e-06, + "loss": 1.2681, + "step": 7717 + }, + { + "epoch": 0.81, + "learning_rate": 2.1335076334431092e-06, + "loss": 1.2842, + "step": 7718 + }, + { + "epoch": 0.81, + "learning_rate": 2.13124832139337e-06, + "loss": 1.3153, + "step": 7719 + }, + { + "epoch": 0.81, + "learning_rate": 2.128990063554176e-06, + "loss": 1.3312, + "step": 7720 + }, + { + "epoch": 0.81, + "learning_rate": 2.12673286022807e-06, + "loss": 1.2851, + "step": 7721 + }, + { + "epoch": 0.81, + "learning_rate": 2.124476711717465e-06, + "loss": 1.3398, + "step": 7722 + }, + { + "epoch": 0.81, + "learning_rate": 2.1222216183246246e-06, + "loss": 1.2543, + "step": 7723 + }, + { + "epoch": 0.81, + "learning_rate": 2.1199675803516785e-06, + "loss": 1.3686, + "step": 7724 + }, + { + "epoch": 0.81, + "learning_rate": 2.117714598100604e-06, + "loss": 1.3746, + "step": 7725 + }, + { + "epoch": 0.81, + "learning_rate": 2.1154626718732407e-06, + "loss": 1.2664, + "step": 7726 + }, + { + "epoch": 0.81, + "learning_rate": 2.1132118019712976e-06, + "loss": 1.3075, + "step": 7727 + }, + { + "epoch": 0.81, + "learning_rate": 2.1109619886963284e-06, + "loss": 1.739, + "step": 7728 + }, + { + "epoch": 0.81, + "learning_rate": 2.1087132323497483e-06, + "loss": 1.335, + "step": 7729 + }, + { + "epoch": 0.81, + "learning_rate": 2.1064655332328344e-06, + "loss": 1.3371, + "step": 7730 + }, + { + "epoch": 0.81, + "learning_rate": 2.104218891646724e-06, + "loss": 1.3837, + "step": 7731 + }, + { + "epoch": 0.81, + "learning_rate": 2.1019733078924045e-06, + "loss": 1.3436, + "step": 7732 + }, + { + "epoch": 0.81, + "learning_rate": 2.0997287822707304e-06, + "loss": 1.2995, + "step": 7733 + }, + { + "epoch": 0.81, + "learning_rate": 2.0974853150824036e-06, + "loss": 1.2914, + "step": 7734 + }, + { + "epoch": 0.81, + "learning_rate": 2.095242906628001e-06, + "loss": 1.3773, + "step": 7735 + }, + { + "epoch": 0.81, + "learning_rate": 2.0930015572079434e-06, + "loss": 1.3097, + "step": 7736 + }, + { + "epoch": 0.81, + "learning_rate": 2.0907612671225108e-06, + "loss": 1.3261, + "step": 7737 + }, + { + "epoch": 0.81, + "learning_rate": 2.088522036671846e-06, + "loss": 1.2578, + "step": 7738 + }, + { + "epoch": 0.81, + "learning_rate": 2.0862838661559535e-06, + "loss": 1.2898, + "step": 7739 + }, + { + "epoch": 0.81, + "learning_rate": 2.0840467558746837e-06, + "loss": 1.341, + "step": 7740 + }, + { + "epoch": 0.81, + "learning_rate": 2.0818107061277535e-06, + "loss": 1.3332, + "step": 7741 + }, + { + "epoch": 0.81, + "learning_rate": 2.0795757172147392e-06, + "loss": 1.2808, + "step": 7742 + }, + { + "epoch": 0.81, + "learning_rate": 2.077341789435071e-06, + "loss": 1.2795, + "step": 7743 + }, + { + "epoch": 0.81, + "learning_rate": 2.075108923088038e-06, + "loss": 1.3621, + "step": 7744 + }, + { + "epoch": 0.81, + "learning_rate": 2.0728771184727802e-06, + "loss": 1.3179, + "step": 7745 + }, + { + "epoch": 0.81, + "learning_rate": 2.0706463758883134e-06, + "loss": 1.2924, + "step": 7746 + }, + { + "epoch": 0.81, + "learning_rate": 2.0684166956334926e-06, + "loss": 1.3576, + "step": 7747 + }, + { + "epoch": 0.81, + "learning_rate": 2.066188078007039e-06, + "loss": 1.2692, + "step": 7748 + }, + { + "epoch": 0.81, + "learning_rate": 2.0639605233075277e-06, + "loss": 1.2994, + "step": 7749 + }, + { + "epoch": 0.81, + "learning_rate": 2.061734031833398e-06, + "loss": 1.278, + "step": 7750 + }, + { + "epoch": 0.81, + "learning_rate": 2.059508603882943e-06, + "loss": 1.2703, + "step": 7751 + }, + { + "epoch": 0.81, + "learning_rate": 2.0572842397543115e-06, + "loss": 1.2864, + "step": 7752 + }, + { + "epoch": 0.81, + "learning_rate": 2.0550609397455037e-06, + "loss": 1.3387, + "step": 7753 + }, + { + "epoch": 0.81, + "learning_rate": 2.0528387041543974e-06, + "loss": 1.5834, + "step": 7754 + }, + { + "epoch": 0.81, + "learning_rate": 2.0506175332787093e-06, + "loss": 1.2907, + "step": 7755 + }, + { + "epoch": 0.81, + "learning_rate": 2.048397427416016e-06, + "loss": 1.3015, + "step": 7756 + }, + { + "epoch": 0.81, + "learning_rate": 2.0461783868637573e-06, + "loss": 1.2329, + "step": 7757 + }, + { + "epoch": 0.81, + "learning_rate": 2.0439604119192314e-06, + "loss": 1.3166, + "step": 7758 + }, + { + "epoch": 0.81, + "learning_rate": 2.041743502879583e-06, + "loss": 1.2476, + "step": 7759 + }, + { + "epoch": 0.81, + "learning_rate": 2.039527660041828e-06, + "loss": 1.2766, + "step": 7760 + }, + { + "epoch": 0.81, + "learning_rate": 2.0373128837028233e-06, + "loss": 1.2738, + "step": 7761 + }, + { + "epoch": 0.81, + "eval_loss": 1.3951469659805298, + "eval_runtime": 77.4687, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 7761 + }, + { + "epoch": 0.81, + "learning_rate": 2.035099174159302e-06, + "loss": 1.3806, + "step": 7762 + }, + { + "epoch": 0.81, + "learning_rate": 2.0328865317078405e-06, + "loss": 1.2625, + "step": 7763 + }, + { + "epoch": 0.81, + "learning_rate": 2.0306749566448704e-06, + "loss": 1.2709, + "step": 7764 + }, + { + "epoch": 0.81, + "learning_rate": 2.028464449266696e-06, + "loss": 1.3029, + "step": 7765 + }, + { + "epoch": 0.81, + "learning_rate": 2.0262550098694634e-06, + "loss": 1.2867, + "step": 7766 + }, + { + "epoch": 0.81, + "learning_rate": 2.0240466387491774e-06, + "loss": 1.2818, + "step": 7767 + }, + { + "epoch": 0.81, + "learning_rate": 2.0218393362017076e-06, + "loss": 1.2627, + "step": 7768 + }, + { + "epoch": 0.81, + "learning_rate": 2.019633102522773e-06, + "loss": 1.2337, + "step": 7769 + }, + { + "epoch": 0.81, + "learning_rate": 2.0174279380079577e-06, + "loss": 1.4194, + "step": 7770 + }, + { + "epoch": 0.81, + "learning_rate": 2.0152238429526928e-06, + "loss": 1.487, + "step": 7771 + }, + { + "epoch": 0.82, + "learning_rate": 2.013020817652266e-06, + "loss": 1.2802, + "step": 7772 + }, + { + "epoch": 0.82, + "learning_rate": 2.0108188624018353e-06, + "loss": 1.2602, + "step": 7773 + }, + { + "epoch": 0.82, + "learning_rate": 2.008617977496402e-06, + "loss": 1.2986, + "step": 7774 + }, + { + "epoch": 0.82, + "learning_rate": 2.0064181632308244e-06, + "loss": 1.3053, + "step": 7775 + }, + { + "epoch": 0.82, + "learning_rate": 2.0042194198998256e-06, + "loss": 1.3052, + "step": 7776 + }, + { + "epoch": 0.82, + "learning_rate": 2.00202174779798e-06, + "loss": 1.247, + "step": 7777 + }, + { + "epoch": 0.82, + "learning_rate": 1.9998251472197192e-06, + "loss": 1.2762, + "step": 7778 + }, + { + "epoch": 0.82, + "learning_rate": 1.9976296184593335e-06, + "loss": 1.3518, + "step": 7779 + }, + { + "epoch": 0.82, + "learning_rate": 1.995435161810958e-06, + "loss": 1.4015, + "step": 7780 + }, + { + "epoch": 0.82, + "learning_rate": 1.9932417775686052e-06, + "loss": 1.3363, + "step": 7781 + }, + { + "epoch": 0.82, + "learning_rate": 1.991049466026128e-06, + "loss": 1.3039, + "step": 7782 + }, + { + "epoch": 0.82, + "learning_rate": 1.988858227477234e-06, + "loss": 1.3183, + "step": 7783 + }, + { + "epoch": 0.82, + "learning_rate": 1.986668062215502e-06, + "loss": 1.2852, + "step": 7784 + }, + { + "epoch": 0.82, + "learning_rate": 1.984478970534355e-06, + "loss": 1.2791, + "step": 7785 + }, + { + "epoch": 0.82, + "learning_rate": 1.9822909527270696e-06, + "loss": 1.3869, + "step": 7786 + }, + { + "epoch": 0.82, + "learning_rate": 1.9801040090867895e-06, + "loss": 1.3475, + "step": 7787 + }, + { + "epoch": 0.82, + "learning_rate": 1.9779181399065074e-06, + "loss": 1.2977, + "step": 7788 + }, + { + "epoch": 0.82, + "learning_rate": 1.975733345479076e-06, + "loss": 1.2244, + "step": 7789 + }, + { + "epoch": 0.82, + "learning_rate": 1.9735496260971996e-06, + "loss": 1.3136, + "step": 7790 + }, + { + "epoch": 0.82, + "learning_rate": 1.9713669820534352e-06, + "loss": 1.3647, + "step": 7791 + }, + { + "epoch": 0.82, + "learning_rate": 1.969185413640212e-06, + "loss": 1.3136, + "step": 7792 + }, + { + "epoch": 0.82, + "learning_rate": 1.9670049211497977e-06, + "loss": 1.3488, + "step": 7793 + }, + { + "epoch": 0.82, + "learning_rate": 1.9648255048743205e-06, + "loss": 1.3578, + "step": 7794 + }, + { + "epoch": 0.82, + "learning_rate": 1.9626471651057677e-06, + "loss": 1.325, + "step": 7795 + }, + { + "epoch": 0.82, + "learning_rate": 1.960469902135983e-06, + "loss": 1.3408, + "step": 7796 + }, + { + "epoch": 0.82, + "learning_rate": 1.958293716256664e-06, + "loss": 1.3439, + "step": 7797 + }, + { + "epoch": 0.82, + "learning_rate": 1.9561186077593617e-06, + "loss": 1.2767, + "step": 7798 + }, + { + "epoch": 0.82, + "learning_rate": 1.9539445769354814e-06, + "loss": 1.3756, + "step": 7799 + }, + { + "epoch": 0.82, + "learning_rate": 1.9517716240762953e-06, + "loss": 1.313, + "step": 7800 + }, + { + "epoch": 0.82, + "learning_rate": 1.949599749472919e-06, + "loss": 1.3103, + "step": 7801 + }, + { + "epoch": 0.82, + "learning_rate": 1.947428953416326e-06, + "loss": 1.3255, + "step": 7802 + }, + { + "epoch": 0.82, + "learning_rate": 1.945259236197348e-06, + "loss": 1.2959, + "step": 7803 + }, + { + "epoch": 0.82, + "learning_rate": 1.943090598106673e-06, + "loss": 1.2345, + "step": 7804 + }, + { + "epoch": 0.82, + "learning_rate": 1.9409230394348457e-06, + "loss": 1.2664, + "step": 7805 + }, + { + "epoch": 0.82, + "learning_rate": 1.938756560472256e-06, + "loss": 1.5172, + "step": 7806 + }, + { + "epoch": 0.82, + "learning_rate": 1.9365911615091615e-06, + "loss": 1.2878, + "step": 7807 + }, + { + "epoch": 0.82, + "learning_rate": 1.9344268428356707e-06, + "loss": 1.3419, + "step": 7808 + }, + { + "epoch": 0.82, + "learning_rate": 1.9322636047417444e-06, + "loss": 1.3464, + "step": 7809 + }, + { + "epoch": 0.82, + "learning_rate": 1.9301014475171964e-06, + "loss": 1.2695, + "step": 7810 + }, + { + "epoch": 0.82, + "learning_rate": 1.9279403714517098e-06, + "loss": 1.3551, + "step": 7811 + }, + { + "epoch": 0.82, + "learning_rate": 1.9257803768348092e-06, + "loss": 1.4498, + "step": 7812 + }, + { + "epoch": 0.82, + "learning_rate": 1.923621463955876e-06, + "loss": 1.4617, + "step": 7813 + }, + { + "epoch": 0.82, + "learning_rate": 1.9214636331041493e-06, + "loss": 1.6204, + "step": 7814 + }, + { + "epoch": 0.82, + "learning_rate": 1.9193068845687246e-06, + "loss": 1.3202, + "step": 7815 + }, + { + "epoch": 0.82, + "learning_rate": 1.9171512186385543e-06, + "loss": 1.293, + "step": 7816 + }, + { + "epoch": 0.82, + "learning_rate": 1.9149966356024387e-06, + "loss": 1.2511, + "step": 7817 + }, + { + "epoch": 0.82, + "learning_rate": 1.9128431357490296e-06, + "loss": 1.3643, + "step": 7818 + }, + { + "epoch": 0.82, + "learning_rate": 1.9106907193668543e-06, + "loss": 1.4159, + "step": 7819 + }, + { + "epoch": 0.82, + "learning_rate": 1.908539386744274e-06, + "loss": 1.2611, + "step": 7820 + }, + { + "epoch": 0.82, + "learning_rate": 1.9063891381695098e-06, + "loss": 1.3667, + "step": 7821 + }, + { + "epoch": 0.82, + "learning_rate": 1.9042399739306427e-06, + "loss": 1.3456, + "step": 7822 + }, + { + "epoch": 0.82, + "learning_rate": 1.9020918943156053e-06, + "loss": 1.4083, + "step": 7823 + }, + { + "epoch": 0.82, + "learning_rate": 1.8999448996121883e-06, + "loss": 1.3758, + "step": 7824 + }, + { + "epoch": 0.82, + "learning_rate": 1.8977989901080295e-06, + "loss": 1.2757, + "step": 7825 + }, + { + "epoch": 0.82, + "learning_rate": 1.8956541660906214e-06, + "loss": 1.3796, + "step": 7826 + }, + { + "epoch": 0.82, + "learning_rate": 1.893510427847327e-06, + "loss": 1.238, + "step": 7827 + }, + { + "epoch": 0.82, + "learning_rate": 1.8913677756653447e-06, + "loss": 1.3018, + "step": 7828 + }, + { + "epoch": 0.82, + "learning_rate": 1.8892262098317315e-06, + "loss": 1.2712, + "step": 7829 + }, + { + "epoch": 0.82, + "learning_rate": 1.8870857306334113e-06, + "loss": 1.3805, + "step": 7830 + }, + { + "epoch": 0.82, + "learning_rate": 1.8849463383571486e-06, + "loss": 1.3664, + "step": 7831 + }, + { + "epoch": 0.82, + "learning_rate": 1.8828080332895648e-06, + "loss": 1.3709, + "step": 7832 + }, + { + "epoch": 0.82, + "learning_rate": 1.8806708157171393e-06, + "loss": 1.3401, + "step": 7833 + }, + { + "epoch": 0.82, + "learning_rate": 1.8785346859262056e-06, + "loss": 1.3143, + "step": 7834 + }, + { + "epoch": 0.82, + "learning_rate": 1.876399644202952e-06, + "loss": 1.3432, + "step": 7835 + }, + { + "epoch": 0.82, + "learning_rate": 1.8742656908334178e-06, + "loss": 1.2945, + "step": 7836 + }, + { + "epoch": 0.82, + "learning_rate": 1.872132826103491e-06, + "loss": 1.402, + "step": 7837 + }, + { + "epoch": 0.82, + "learning_rate": 1.8700010502989318e-06, + "loss": 1.3004, + "step": 7838 + }, + { + "epoch": 0.82, + "learning_rate": 1.8678703637053386e-06, + "loss": 1.2766, + "step": 7839 + }, + { + "epoch": 0.82, + "learning_rate": 1.8657407666081661e-06, + "loss": 1.3629, + "step": 7840 + }, + { + "epoch": 0.82, + "learning_rate": 1.8636122592927275e-06, + "loss": 1.2527, + "step": 7841 + }, + { + "epoch": 0.82, + "learning_rate": 1.8614848420441888e-06, + "loss": 1.2711, + "step": 7842 + }, + { + "epoch": 0.82, + "learning_rate": 1.8593585151475713e-06, + "loss": 1.3419, + "step": 7843 + }, + { + "epoch": 0.82, + "learning_rate": 1.8572332788877456e-06, + "loss": 1.2953, + "step": 7844 + }, + { + "epoch": 0.82, + "learning_rate": 1.855109133549433e-06, + "loss": 1.2415, + "step": 7845 + }, + { + "epoch": 0.82, + "learning_rate": 1.8529860794172271e-06, + "loss": 1.2367, + "step": 7846 + }, + { + "epoch": 0.82, + "learning_rate": 1.8508641167755548e-06, + "loss": 1.3584, + "step": 7847 + }, + { + "epoch": 0.82, + "learning_rate": 1.848743245908703e-06, + "loss": 1.4259, + "step": 7848 + }, + { + "epoch": 0.82, + "learning_rate": 1.8466234671008165e-06, + "loss": 1.2903, + "step": 7849 + }, + { + "epoch": 0.82, + "learning_rate": 1.8445047806358918e-06, + "loss": 1.3204, + "step": 7850 + }, + { + "epoch": 0.82, + "learning_rate": 1.8423871867977806e-06, + "loss": 1.3938, + "step": 7851 + }, + { + "epoch": 0.82, + "learning_rate": 1.840270685870179e-06, + "loss": 1.2973, + "step": 7852 + }, + { + "epoch": 0.82, + "learning_rate": 1.8381552781366497e-06, + "loss": 1.3506, + "step": 7853 + }, + { + "epoch": 0.82, + "learning_rate": 1.8360409638806031e-06, + "loss": 1.3117, + "step": 7854 + }, + { + "epoch": 0.82, + "learning_rate": 1.833927743385302e-06, + "loss": 1.3072, + "step": 7855 + }, + { + "epoch": 0.82, + "learning_rate": 1.8318156169338562e-06, + "loss": 1.2965, + "step": 7856 + }, + { + "epoch": 0.82, + "learning_rate": 1.82970458480925e-06, + "loss": 1.3161, + "step": 7857 + }, + { + "epoch": 0.82, + "learning_rate": 1.8275946472942995e-06, + "loss": 1.3056, + "step": 7858 + }, + { + "epoch": 0.82, + "learning_rate": 1.8254858046716805e-06, + "loss": 1.249, + "step": 7859 + }, + { + "epoch": 0.82, + "learning_rate": 1.8233780572239268e-06, + "loss": 1.2689, + "step": 7860 + }, + { + "epoch": 0.82, + "learning_rate": 1.8212714052334213e-06, + "loss": 1.2919, + "step": 7861 + }, + { + "epoch": 0.82, + "learning_rate": 1.819165848982405e-06, + "loss": 1.3337, + "step": 7862 + }, + { + "epoch": 0.82, + "learning_rate": 1.8170613887529643e-06, + "loss": 1.2798, + "step": 7863 + }, + { + "epoch": 0.82, + "learning_rate": 1.8149580248270393e-06, + "loss": 1.3296, + "step": 7864 + }, + { + "epoch": 0.82, + "learning_rate": 1.812855757486437e-06, + "loss": 1.4615, + "step": 7865 + }, + { + "epoch": 0.82, + "learning_rate": 1.8107545870128008e-06, + "loss": 1.2883, + "step": 7866 + }, + { + "epoch": 0.82, + "learning_rate": 1.808654513687631e-06, + "loss": 1.3722, + "step": 7867 + }, + { + "epoch": 0.83, + "learning_rate": 1.8065555377922862e-06, + "loss": 1.3648, + "step": 7868 + }, + { + "epoch": 0.83, + "learning_rate": 1.8044576596079766e-06, + "loss": 1.2698, + "step": 7869 + }, + { + "epoch": 0.83, + "learning_rate": 1.8023608794157654e-06, + "loss": 1.3078, + "step": 7870 + }, + { + "epoch": 0.83, + "learning_rate": 1.8002651974965646e-06, + "loss": 1.3037, + "step": 7871 + }, + { + "epoch": 0.83, + "learning_rate": 1.7981706141311373e-06, + "loss": 1.2971, + "step": 7872 + }, + { + "epoch": 0.83, + "learning_rate": 1.7960771296001122e-06, + "loss": 1.3334, + "step": 7873 + }, + { + "epoch": 0.83, + "learning_rate": 1.7939847441839597e-06, + "loss": 1.3301, + "step": 7874 + }, + { + "epoch": 0.83, + "learning_rate": 1.7918934581629998e-06, + "loss": 1.2966, + "step": 7875 + }, + { + "epoch": 0.83, + "learning_rate": 1.7898032718174218e-06, + "loss": 1.3152, + "step": 7876 + }, + { + "epoch": 0.83, + "learning_rate": 1.7877141854272474e-06, + "loss": 1.2867, + "step": 7877 + }, + { + "epoch": 0.83, + "learning_rate": 1.7856261992723678e-06, + "loss": 1.3059, + "step": 7878 + }, + { + "epoch": 0.83, + "learning_rate": 1.783539313632513e-06, + "loss": 1.3425, + "step": 7879 + }, + { + "epoch": 0.83, + "learning_rate": 1.7814535287872748e-06, + "loss": 1.3513, + "step": 7880 + }, + { + "epoch": 0.83, + "learning_rate": 1.7793688450160983e-06, + "loss": 1.3208, + "step": 7881 + }, + { + "epoch": 0.83, + "learning_rate": 1.777285262598274e-06, + "loss": 1.302, + "step": 7882 + }, + { + "epoch": 0.83, + "learning_rate": 1.7752027818129424e-06, + "loss": 1.2783, + "step": 7883 + }, + { + "epoch": 0.83, + "learning_rate": 1.7731214029391153e-06, + "loss": 1.3599, + "step": 7884 + }, + { + "epoch": 0.83, + "learning_rate": 1.771041126255637e-06, + "loss": 1.2158, + "step": 7885 + }, + { + "epoch": 0.83, + "learning_rate": 1.7689619520412094e-06, + "loss": 1.3221, + "step": 7886 + }, + { + "epoch": 0.83, + "learning_rate": 1.7668838805743893e-06, + "loss": 1.3635, + "step": 7887 + }, + { + "epoch": 0.83, + "learning_rate": 1.7648069121335876e-06, + "loss": 1.2742, + "step": 7888 + }, + { + "epoch": 0.83, + "learning_rate": 1.762731046997065e-06, + "loss": 1.3333, + "step": 7889 + }, + { + "epoch": 0.83, + "learning_rate": 1.760656285442932e-06, + "loss": 1.2971, + "step": 7890 + }, + { + "epoch": 0.83, + "learning_rate": 1.7585826277491491e-06, + "loss": 1.3262, + "step": 7891 + }, + { + "epoch": 0.83, + "learning_rate": 1.7565100741935436e-06, + "loss": 1.38, + "step": 7892 + }, + { + "epoch": 0.83, + "learning_rate": 1.754438625053777e-06, + "loss": 1.3814, + "step": 7893 + }, + { + "epoch": 0.83, + "learning_rate": 1.7523682806073706e-06, + "loss": 1.2793, + "step": 7894 + }, + { + "epoch": 0.83, + "learning_rate": 1.7502990411316978e-06, + "loss": 1.266, + "step": 7895 + }, + { + "epoch": 0.83, + "learning_rate": 1.7482309069039838e-06, + "loss": 1.3085, + "step": 7896 + }, + { + "epoch": 0.83, + "learning_rate": 1.746163878201309e-06, + "loss": 1.3518, + "step": 7897 + }, + { + "epoch": 0.83, + "learning_rate": 1.7440979553005976e-06, + "loss": 1.3887, + "step": 7898 + }, + { + "epoch": 0.83, + "learning_rate": 1.7420331384786305e-06, + "loss": 1.3255, + "step": 7899 + }, + { + "epoch": 0.83, + "learning_rate": 1.7399694280120439e-06, + "loss": 1.3702, + "step": 7900 + }, + { + "epoch": 0.83, + "learning_rate": 1.7379068241773188e-06, + "loss": 1.3253, + "step": 7901 + }, + { + "epoch": 0.83, + "learning_rate": 1.735845327250788e-06, + "loss": 1.3055, + "step": 7902 + }, + { + "epoch": 0.83, + "learning_rate": 1.7337849375086468e-06, + "loss": 1.3119, + "step": 7903 + }, + { + "epoch": 0.83, + "learning_rate": 1.7317256552269278e-06, + "loss": 1.2741, + "step": 7904 + }, + { + "epoch": 0.83, + "learning_rate": 1.7296674806815273e-06, + "loss": 1.3101, + "step": 7905 + }, + { + "epoch": 0.83, + "learning_rate": 1.7276104141481832e-06, + "loss": 1.3553, + "step": 7906 + }, + { + "epoch": 0.83, + "learning_rate": 1.7255544559024906e-06, + "loss": 1.2712, + "step": 7907 + }, + { + "epoch": 0.83, + "learning_rate": 1.7234996062198994e-06, + "loss": 1.2814, + "step": 7908 + }, + { + "epoch": 0.83, + "learning_rate": 1.7214458653757027e-06, + "loss": 1.2831, + "step": 7909 + }, + { + "epoch": 0.83, + "learning_rate": 1.7193932336450437e-06, + "loss": 1.3519, + "step": 7910 + }, + { + "epoch": 0.83, + "learning_rate": 1.7173417113029334e-06, + "loss": 1.2559, + "step": 7911 + }, + { + "epoch": 0.83, + "learning_rate": 1.7152912986242187e-06, + "loss": 1.4204, + "step": 7912 + }, + { + "epoch": 0.83, + "learning_rate": 1.7132419958835978e-06, + "loss": 1.302, + "step": 7913 + }, + { + "epoch": 0.83, + "learning_rate": 1.7111938033556286e-06, + "loss": 1.2959, + "step": 7914 + }, + { + "epoch": 0.83, + "learning_rate": 1.7091467213147162e-06, + "loss": 1.3269, + "step": 7915 + }, + { + "epoch": 0.83, + "learning_rate": 1.7071007500351177e-06, + "loss": 1.2966, + "step": 7916 + }, + { + "epoch": 0.83, + "learning_rate": 1.705055889790941e-06, + "loss": 1.2696, + "step": 7917 + }, + { + "epoch": 0.83, + "learning_rate": 1.7030121408561373e-06, + "loss": 1.3431, + "step": 7918 + }, + { + "epoch": 0.83, + "learning_rate": 1.700969503504528e-06, + "loss": 1.2769, + "step": 7919 + }, + { + "epoch": 0.83, + "learning_rate": 1.698927978009769e-06, + "loss": 1.2543, + "step": 7920 + }, + { + "epoch": 0.83, + "learning_rate": 1.6968875646453665e-06, + "loss": 1.2612, + "step": 7921 + }, + { + "epoch": 0.83, + "learning_rate": 1.694848263684693e-06, + "loss": 1.322, + "step": 7922 + }, + { + "epoch": 0.83, + "learning_rate": 1.692810075400957e-06, + "loss": 1.4144, + "step": 7923 + }, + { + "epoch": 0.83, + "learning_rate": 1.6907730000672263e-06, + "loss": 1.4355, + "step": 7924 + }, + { + "epoch": 0.83, + "learning_rate": 1.6887370379564127e-06, + "loss": 1.4024, + "step": 7925 + }, + { + "epoch": 0.83, + "learning_rate": 1.686702189341285e-06, + "loss": 1.3015, + "step": 7926 + }, + { + "epoch": 0.83, + "learning_rate": 1.6846684544944625e-06, + "loss": 1.4337, + "step": 7927 + }, + { + "epoch": 0.83, + "learning_rate": 1.682635833688412e-06, + "loss": 1.3199, + "step": 7928 + }, + { + "epoch": 0.83, + "learning_rate": 1.6806043271954475e-06, + "loss": 1.2927, + "step": 7929 + }, + { + "epoch": 0.83, + "learning_rate": 1.6785739352877472e-06, + "loss": 1.4254, + "step": 7930 + }, + { + "epoch": 0.83, + "learning_rate": 1.676544658237328e-06, + "loss": 1.3653, + "step": 7931 + }, + { + "epoch": 0.83, + "learning_rate": 1.6745164963160576e-06, + "loss": 1.3049, + "step": 7932 + }, + { + "epoch": 0.83, + "learning_rate": 1.6724894497956613e-06, + "loss": 1.2474, + "step": 7933 + }, + { + "epoch": 0.83, + "learning_rate": 1.6704635189477091e-06, + "loss": 1.3146, + "step": 7934 + }, + { + "epoch": 0.83, + "learning_rate": 1.668438704043628e-06, + "loss": 1.2338, + "step": 7935 + }, + { + "epoch": 0.83, + "learning_rate": 1.666415005354688e-06, + "loss": 1.3217, + "step": 7936 + }, + { + "epoch": 0.83, + "learning_rate": 1.6643924231520082e-06, + "loss": 1.3776, + "step": 7937 + }, + { + "epoch": 0.83, + "learning_rate": 1.6623709577065715e-06, + "loss": 1.6173, + "step": 7938 + }, + { + "epoch": 0.83, + "learning_rate": 1.6603506092891975e-06, + "loss": 1.4383, + "step": 7939 + }, + { + "epoch": 0.83, + "learning_rate": 1.6583313781705602e-06, + "loss": 1.304, + "step": 7940 + }, + { + "epoch": 0.83, + "learning_rate": 1.6563132646211856e-06, + "loss": 1.4071, + "step": 7941 + }, + { + "epoch": 0.83, + "learning_rate": 1.6542962689114494e-06, + "loss": 1.3402, + "step": 7942 + }, + { + "epoch": 0.83, + "learning_rate": 1.6522803913115793e-06, + "loss": 1.3298, + "step": 7943 + }, + { + "epoch": 0.83, + "learning_rate": 1.6502656320916466e-06, + "loss": 1.4741, + "step": 7944 + }, + { + "epoch": 0.83, + "learning_rate": 1.64825199152158e-06, + "loss": 1.3373, + "step": 7945 + }, + { + "epoch": 0.83, + "learning_rate": 1.646239469871158e-06, + "loss": 1.6403, + "step": 7946 + }, + { + "epoch": 0.83, + "learning_rate": 1.644228067410004e-06, + "loss": 1.4887, + "step": 7947 + }, + { + "epoch": 0.83, + "learning_rate": 1.6422177844075893e-06, + "loss": 1.2763, + "step": 7948 + }, + { + "epoch": 0.83, + "learning_rate": 1.6402086211332502e-06, + "loss": 1.3298, + "step": 7949 + }, + { + "epoch": 0.83, + "learning_rate": 1.638200577856156e-06, + "loss": 1.3542, + "step": 7950 + }, + { + "epoch": 0.83, + "learning_rate": 1.6361936548453371e-06, + "loss": 1.2628, + "step": 7951 + }, + { + "epoch": 0.83, + "learning_rate": 1.6341878523696642e-06, + "loss": 1.3937, + "step": 7952 + }, + { + "epoch": 0.83, + "learning_rate": 1.6321831706978674e-06, + "loss": 1.2712, + "step": 7953 + }, + { + "epoch": 0.83, + "learning_rate": 1.6301796100985235e-06, + "loss": 1.3303, + "step": 7954 + }, + { + "epoch": 0.83, + "learning_rate": 1.6281771708400563e-06, + "loss": 1.2698, + "step": 7955 + }, + { + "epoch": 0.83, + "learning_rate": 1.6261758531907367e-06, + "loss": 1.3242, + "step": 7956 + }, + { + "epoch": 0.83, + "learning_rate": 1.6241756574186996e-06, + "loss": 1.2774, + "step": 7957 + }, + { + "epoch": 0.83, + "learning_rate": 1.6221765837919135e-06, + "loss": 1.3022, + "step": 7958 + }, + { + "epoch": 0.83, + "learning_rate": 1.620178632578202e-06, + "loss": 1.375, + "step": 7959 + }, + { + "epoch": 0.83, + "learning_rate": 1.6181818040452412e-06, + "loss": 1.308, + "step": 7960 + }, + { + "epoch": 0.83, + "eval_loss": 1.3948875665664673, + "eval_runtime": 77.4765, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 7960 + }, + { + "epoch": 0.83, + "learning_rate": 1.616186098460555e-06, + "loss": 1.3674, + "step": 7961 + }, + { + "epoch": 0.83, + "learning_rate": 1.614191516091519e-06, + "loss": 1.4367, + "step": 7962 + }, + { + "epoch": 0.84, + "learning_rate": 1.612198057205353e-06, + "loss": 1.3105, + "step": 7963 + }, + { + "epoch": 0.84, + "learning_rate": 1.6102057220691258e-06, + "loss": 1.2591, + "step": 7964 + }, + { + "epoch": 0.84, + "learning_rate": 1.608214510949767e-06, + "loss": 1.3503, + "step": 7965 + }, + { + "epoch": 0.84, + "learning_rate": 1.6062244241140435e-06, + "loss": 1.3278, + "step": 7966 + }, + { + "epoch": 0.84, + "learning_rate": 1.6042354618285727e-06, + "loss": 1.2831, + "step": 7967 + }, + { + "epoch": 0.84, + "learning_rate": 1.6022476243598317e-06, + "loss": 1.2535, + "step": 7968 + }, + { + "epoch": 0.84, + "learning_rate": 1.600260911974133e-06, + "loss": 1.2719, + "step": 7969 + }, + { + "epoch": 0.84, + "learning_rate": 1.5982753249376503e-06, + "loss": 1.2615, + "step": 7970 + }, + { + "epoch": 0.84, + "learning_rate": 1.5962908635163965e-06, + "loss": 1.2996, + "step": 7971 + }, + { + "epoch": 0.84, + "learning_rate": 1.594307527976241e-06, + "loss": 1.3323, + "step": 7972 + }, + { + "epoch": 0.84, + "learning_rate": 1.5923253185829024e-06, + "loss": 1.2993, + "step": 7973 + }, + { + "epoch": 0.84, + "learning_rate": 1.5903442356019415e-06, + "loss": 1.3064, + "step": 7974 + }, + { + "epoch": 0.84, + "learning_rate": 1.5883642792987697e-06, + "loss": 1.3171, + "step": 7975 + }, + { + "epoch": 0.84, + "learning_rate": 1.58638544993866e-06, + "loss": 1.4238, + "step": 7976 + }, + { + "epoch": 0.84, + "learning_rate": 1.584407747786716e-06, + "loss": 1.356, + "step": 7977 + }, + { + "epoch": 0.84, + "learning_rate": 1.5824311731079046e-06, + "loss": 1.4523, + "step": 7978 + }, + { + "epoch": 0.84, + "learning_rate": 1.5804557261670318e-06, + "loss": 1.3206, + "step": 7979 + }, + { + "epoch": 0.84, + "learning_rate": 1.578481407228758e-06, + "loss": 1.2639, + "step": 7980 + }, + { + "epoch": 0.84, + "learning_rate": 1.576508216557594e-06, + "loss": 1.2428, + "step": 7981 + }, + { + "epoch": 0.84, + "learning_rate": 1.574536154417895e-06, + "loss": 1.3779, + "step": 7982 + }, + { + "epoch": 0.84, + "learning_rate": 1.5725652210738606e-06, + "loss": 1.3071, + "step": 7983 + }, + { + "epoch": 0.84, + "learning_rate": 1.5705954167895553e-06, + "loss": 1.2604, + "step": 7984 + }, + { + "epoch": 0.84, + "learning_rate": 1.568626741828878e-06, + "loss": 1.2565, + "step": 7985 + }, + { + "epoch": 0.84, + "learning_rate": 1.5666591964555777e-06, + "loss": 1.2742, + "step": 7986 + }, + { + "epoch": 0.84, + "learning_rate": 1.564692780933258e-06, + "loss": 1.3199, + "step": 7987 + }, + { + "epoch": 0.84, + "learning_rate": 1.5627274955253669e-06, + "loss": 1.4034, + "step": 7988 + }, + { + "epoch": 0.84, + "learning_rate": 1.5607633404952048e-06, + "loss": 1.3411, + "step": 7989 + }, + { + "epoch": 0.84, + "learning_rate": 1.558800316105914e-06, + "loss": 1.2874, + "step": 7990 + }, + { + "epoch": 0.84, + "learning_rate": 1.5568384226204903e-06, + "loss": 1.2678, + "step": 7991 + }, + { + "epoch": 0.84, + "learning_rate": 1.5548776603017813e-06, + "loss": 1.3038, + "step": 7992 + }, + { + "epoch": 0.84, + "learning_rate": 1.5529180294124757e-06, + "loss": 1.0848, + "step": 7993 + }, + { + "epoch": 0.84, + "learning_rate": 1.550959530215108e-06, + "loss": 1.2062, + "step": 7994 + }, + { + "epoch": 0.84, + "learning_rate": 1.5490021629720763e-06, + "loss": 1.3028, + "step": 7995 + }, + { + "epoch": 0.84, + "learning_rate": 1.547045927945613e-06, + "loss": 1.3513, + "step": 7996 + }, + { + "epoch": 0.84, + "learning_rate": 1.5450908253978047e-06, + "loss": 1.426, + "step": 7997 + }, + { + "epoch": 0.84, + "learning_rate": 1.5431368555905813e-06, + "loss": 1.2943, + "step": 7998 + }, + { + "epoch": 0.84, + "learning_rate": 1.5411840187857275e-06, + "loss": 1.272, + "step": 7999 + }, + { + "epoch": 0.84, + "learning_rate": 1.5392323152448762e-06, + "loss": 1.3819, + "step": 8000 + }, + { + "epoch": 0.84, + "learning_rate": 1.537281745229502e-06, + "loss": 1.2186, + "step": 8001 + }, + { + "epoch": 0.84, + "learning_rate": 1.5353323090009253e-06, + "loss": 1.4509, + "step": 8002 + }, + { + "epoch": 0.84, + "learning_rate": 1.5333840068203332e-06, + "loss": 1.3629, + "step": 8003 + }, + { + "epoch": 0.84, + "learning_rate": 1.5314368389487378e-06, + "loss": 1.2865, + "step": 8004 + }, + { + "epoch": 0.84, + "learning_rate": 1.529490805647016e-06, + "loss": 1.2645, + "step": 8005 + }, + { + "epoch": 0.84, + "learning_rate": 1.5275459071758813e-06, + "loss": 1.3248, + "step": 8006 + }, + { + "epoch": 0.84, + "learning_rate": 1.5256021437959023e-06, + "loss": 1.2202, + "step": 8007 + }, + { + "epoch": 0.84, + "learning_rate": 1.523659515767496e-06, + "loss": 1.3728, + "step": 8008 + }, + { + "epoch": 0.84, + "learning_rate": 1.5217180233509222e-06, + "loss": 1.2981, + "step": 8009 + }, + { + "epoch": 0.84, + "learning_rate": 1.5197776668062857e-06, + "loss": 1.4002, + "step": 8010 + }, + { + "epoch": 0.84, + "learning_rate": 1.5178384463935546e-06, + "loss": 1.3403, + "step": 8011 + }, + { + "epoch": 0.84, + "learning_rate": 1.51590036237253e-06, + "loss": 1.2629, + "step": 8012 + }, + { + "epoch": 0.84, + "learning_rate": 1.5139634150028594e-06, + "loss": 1.298, + "step": 8013 + }, + { + "epoch": 0.84, + "learning_rate": 1.5120276045440553e-06, + "loss": 1.412, + "step": 8014 + }, + { + "epoch": 0.84, + "learning_rate": 1.510092931255458e-06, + "loss": 1.3025, + "step": 8015 + }, + { + "epoch": 0.84, + "learning_rate": 1.508159395396268e-06, + "loss": 1.2494, + "step": 8016 + }, + { + "epoch": 0.84, + "learning_rate": 1.5062269972255273e-06, + "loss": 1.3295, + "step": 8017 + }, + { + "epoch": 0.84, + "learning_rate": 1.5042957370021282e-06, + "loss": 1.3227, + "step": 8018 + }, + { + "epoch": 0.84, + "learning_rate": 1.5023656149848132e-06, + "loss": 1.3122, + "step": 8019 + }, + { + "epoch": 0.84, + "learning_rate": 1.500436631432165e-06, + "loss": 1.2789, + "step": 8020 + }, + { + "epoch": 0.84, + "learning_rate": 1.4985087866026148e-06, + "loss": 1.2753, + "step": 8021 + }, + { + "epoch": 0.84, + "learning_rate": 1.4965820807544529e-06, + "loss": 1.3296, + "step": 8022 + }, + { + "epoch": 0.84, + "learning_rate": 1.4946565141458024e-06, + "loss": 1.2886, + "step": 8023 + }, + { + "epoch": 0.84, + "learning_rate": 1.492732087034643e-06, + "loss": 1.3137, + "step": 8024 + }, + { + "epoch": 0.84, + "learning_rate": 1.4908087996787944e-06, + "loss": 1.2785, + "step": 8025 + }, + { + "epoch": 0.84, + "learning_rate": 1.4888866523359302e-06, + "loss": 1.3674, + "step": 8026 + }, + { + "epoch": 0.84, + "learning_rate": 1.4869656452635705e-06, + "loss": 1.367, + "step": 8027 + }, + { + "epoch": 0.84, + "learning_rate": 1.4850457787190797e-06, + "loss": 1.3342, + "step": 8028 + }, + { + "epoch": 0.84, + "learning_rate": 1.483127052959664e-06, + "loss": 1.3091, + "step": 8029 + }, + { + "epoch": 0.84, + "learning_rate": 1.481209468242396e-06, + "loss": 1.3729, + "step": 8030 + }, + { + "epoch": 0.84, + "learning_rate": 1.4792930248241744e-06, + "loss": 1.3051, + "step": 8031 + }, + { + "epoch": 0.84, + "learning_rate": 1.4773777229617537e-06, + "loss": 1.2458, + "step": 8032 + }, + { + "epoch": 0.84, + "learning_rate": 1.4754635629117353e-06, + "loss": 1.2803, + "step": 8033 + }, + { + "epoch": 0.84, + "learning_rate": 1.4735505449305687e-06, + "loss": 1.3193, + "step": 8034 + }, + { + "epoch": 0.84, + "learning_rate": 1.4716386692745522e-06, + "loss": 1.2537, + "step": 8035 + }, + { + "epoch": 0.84, + "learning_rate": 1.4697279361998218e-06, + "loss": 1.2816, + "step": 8036 + }, + { + "epoch": 0.84, + "learning_rate": 1.4678183459623708e-06, + "loss": 1.3422, + "step": 8037 + }, + { + "epoch": 0.84, + "learning_rate": 1.4659098988180353e-06, + "loss": 1.34, + "step": 8038 + }, + { + "epoch": 0.84, + "learning_rate": 1.464002595022498e-06, + "loss": 1.3328, + "step": 8039 + }, + { + "epoch": 0.84, + "learning_rate": 1.4620964348312817e-06, + "loss": 1.3415, + "step": 8040 + }, + { + "epoch": 0.84, + "learning_rate": 1.4601914184997744e-06, + "loss": 1.3124, + "step": 8041 + }, + { + "epoch": 0.84, + "learning_rate": 1.4582875462831913e-06, + "loss": 1.3219, + "step": 8042 + }, + { + "epoch": 0.84, + "learning_rate": 1.4563848184366069e-06, + "loss": 1.3322, + "step": 8043 + }, + { + "epoch": 0.84, + "learning_rate": 1.454483235214934e-06, + "loss": 1.2926, + "step": 8044 + }, + { + "epoch": 0.84, + "learning_rate": 1.4525827968729366e-06, + "loss": 1.2796, + "step": 8045 + }, + { + "epoch": 0.84, + "learning_rate": 1.4506835036652289e-06, + "loss": 1.3504, + "step": 8046 + }, + { + "epoch": 0.84, + "learning_rate": 1.448785355846264e-06, + "loss": 1.2122, + "step": 8047 + }, + { + "epoch": 0.84, + "learning_rate": 1.4468883536703405e-06, + "loss": 1.3121, + "step": 8048 + }, + { + "epoch": 0.84, + "learning_rate": 1.4449924973916163e-06, + "loss": 1.3268, + "step": 8049 + }, + { + "epoch": 0.84, + "learning_rate": 1.4430977872640817e-06, + "loss": 1.3911, + "step": 8050 + }, + { + "epoch": 0.84, + "learning_rate": 1.4412042235415836e-06, + "loss": 1.3366, + "step": 8051 + }, + { + "epoch": 0.84, + "learning_rate": 1.4393118064778066e-06, + "loss": 1.2953, + "step": 8052 + }, + { + "epoch": 0.84, + "learning_rate": 1.4374205363262872e-06, + "loss": 1.3222, + "step": 8053 + }, + { + "epoch": 0.84, + "learning_rate": 1.4355304133404102e-06, + "loss": 1.2385, + "step": 8054 + }, + { + "epoch": 0.84, + "learning_rate": 1.433641437773401e-06, + "loss": 1.3245, + "step": 8055 + }, + { + "epoch": 0.84, + "learning_rate": 1.431753609878328e-06, + "loss": 1.2401, + "step": 8056 + }, + { + "epoch": 0.84, + "learning_rate": 1.4298669299081236e-06, + "loss": 1.4646, + "step": 8057 + }, + { + "epoch": 0.85, + "learning_rate": 1.4279813981155465e-06, + "loss": 1.253, + "step": 8058 + }, + { + "epoch": 0.85, + "learning_rate": 1.426097014753207e-06, + "loss": 1.393, + "step": 8059 + }, + { + "epoch": 0.85, + "learning_rate": 1.4242137800735734e-06, + "loss": 1.3527, + "step": 8060 + }, + { + "epoch": 0.85, + "learning_rate": 1.4223316943289435e-06, + "loss": 1.2528, + "step": 8061 + }, + { + "epoch": 0.85, + "learning_rate": 1.420450757771472e-06, + "loss": 1.2165, + "step": 8062 + }, + { + "epoch": 0.85, + "learning_rate": 1.4185709706531526e-06, + "loss": 1.2348, + "step": 8063 + }, + { + "epoch": 0.85, + "learning_rate": 1.4166923332258308e-06, + "loss": 1.3145, + "step": 8064 + }, + { + "epoch": 0.85, + "learning_rate": 1.414814845741197e-06, + "loss": 1.2026, + "step": 8065 + }, + { + "epoch": 0.85, + "learning_rate": 1.4129385084507852e-06, + "loss": 1.3398, + "step": 8066 + }, + { + "epoch": 0.85, + "learning_rate": 1.4110633216059711e-06, + "loss": 1.3166, + "step": 8067 + }, + { + "epoch": 0.85, + "learning_rate": 1.4091892854579913e-06, + "loss": 1.5105, + "step": 8068 + }, + { + "epoch": 0.85, + "learning_rate": 1.407316400257911e-06, + "loss": 1.3002, + "step": 8069 + }, + { + "epoch": 0.85, + "learning_rate": 1.4054446662566535e-06, + "loss": 1.2826, + "step": 8070 + }, + { + "epoch": 0.85, + "learning_rate": 1.4035740837049782e-06, + "loss": 1.338, + "step": 8071 + }, + { + "epoch": 0.85, + "learning_rate": 1.4017046528534983e-06, + "loss": 1.393, + "step": 8072 + }, + { + "epoch": 0.85, + "learning_rate": 1.3998363739526699e-06, + "loss": 1.3082, + "step": 8073 + }, + { + "epoch": 0.85, + "learning_rate": 1.397969247252794e-06, + "loss": 1.345, + "step": 8074 + }, + { + "epoch": 0.85, + "learning_rate": 1.3961032730040126e-06, + "loss": 1.3075, + "step": 8075 + }, + { + "epoch": 0.85, + "learning_rate": 1.394238451456328e-06, + "loss": 1.3432, + "step": 8076 + }, + { + "epoch": 0.85, + "learning_rate": 1.392374782859569e-06, + "loss": 1.3096, + "step": 8077 + }, + { + "epoch": 0.85, + "learning_rate": 1.3905122674634274e-06, + "loss": 1.2686, + "step": 8078 + }, + { + "epoch": 0.85, + "learning_rate": 1.3886509055174247e-06, + "loss": 1.3075, + "step": 8079 + }, + { + "epoch": 0.85, + "learning_rate": 1.38679069727094e-06, + "loss": 1.3446, + "step": 8080 + }, + { + "epoch": 0.85, + "learning_rate": 1.3849316429731941e-06, + "loss": 1.3646, + "step": 8081 + }, + { + "epoch": 0.85, + "learning_rate": 1.3830737428732499e-06, + "loss": 1.3074, + "step": 8082 + }, + { + "epoch": 0.85, + "learning_rate": 1.3812169972200184e-06, + "loss": 1.277, + "step": 8083 + }, + { + "epoch": 0.85, + "learning_rate": 1.3793614062622595e-06, + "loss": 1.2978, + "step": 8084 + }, + { + "epoch": 0.85, + "learning_rate": 1.3775069702485722e-06, + "loss": 1.3978, + "step": 8085 + }, + { + "epoch": 0.85, + "learning_rate": 1.3756536894273974e-06, + "loss": 1.4198, + "step": 8086 + }, + { + "epoch": 0.85, + "learning_rate": 1.3738015640470381e-06, + "loss": 1.2901, + "step": 8087 + }, + { + "epoch": 0.85, + "learning_rate": 1.3719505943556243e-06, + "loss": 1.2916, + "step": 8088 + }, + { + "epoch": 0.85, + "learning_rate": 1.3701007806011423e-06, + "loss": 1.2845, + "step": 8089 + }, + { + "epoch": 0.85, + "learning_rate": 1.368252123031416e-06, + "loss": 1.3261, + "step": 8090 + }, + { + "epoch": 0.85, + "learning_rate": 1.3664046218941185e-06, + "loss": 1.321, + "step": 8091 + }, + { + "epoch": 0.85, + "learning_rate": 1.3645582774367717e-06, + "loss": 1.2968, + "step": 8092 + }, + { + "epoch": 0.85, + "learning_rate": 1.3627130899067353e-06, + "loss": 1.2595, + "step": 8093 + }, + { + "epoch": 0.85, + "learning_rate": 1.360869059551212e-06, + "loss": 1.4081, + "step": 8094 + }, + { + "epoch": 0.85, + "learning_rate": 1.3590261866172638e-06, + "loss": 1.2949, + "step": 8095 + }, + { + "epoch": 0.85, + "learning_rate": 1.3571844713517823e-06, + "loss": 1.3563, + "step": 8096 + }, + { + "epoch": 0.85, + "learning_rate": 1.3553439140015135e-06, + "loss": 1.3063, + "step": 8097 + }, + { + "epoch": 0.85, + "learning_rate": 1.353504514813041e-06, + "loss": 1.2896, + "step": 8098 + }, + { + "epoch": 0.85, + "learning_rate": 1.351666274032799e-06, + "loss": 1.3338, + "step": 8099 + }, + { + "epoch": 0.85, + "learning_rate": 1.349829191907066e-06, + "loss": 1.2932, + "step": 8100 + }, + { + "epoch": 0.85, + "learning_rate": 1.3479932686819642e-06, + "loss": 1.3287, + "step": 8101 + }, + { + "epoch": 0.85, + "learning_rate": 1.346158504603452e-06, + "loss": 1.3343, + "step": 8102 + }, + { + "epoch": 0.85, + "learning_rate": 1.344324899917352e-06, + "loss": 1.3419, + "step": 8103 + }, + { + "epoch": 0.85, + "learning_rate": 1.342492454869313e-06, + "loss": 1.3138, + "step": 8104 + }, + { + "epoch": 0.85, + "learning_rate": 1.3406611697048377e-06, + "loss": 1.3473, + "step": 8105 + }, + { + "epoch": 0.85, + "learning_rate": 1.338831044669273e-06, + "loss": 1.3035, + "step": 8106 + }, + { + "epoch": 0.85, + "learning_rate": 1.3370020800078043e-06, + "loss": 1.3299, + "step": 8107 + }, + { + "epoch": 0.85, + "learning_rate": 1.3351742759654707e-06, + "loss": 1.357, + "step": 8108 + }, + { + "epoch": 0.85, + "learning_rate": 1.3333476327871475e-06, + "loss": 1.3777, + "step": 8109 + }, + { + "epoch": 0.85, + "learning_rate": 1.331522150717558e-06, + "loss": 1.3359, + "step": 8110 + }, + { + "epoch": 0.85, + "learning_rate": 1.329697830001273e-06, + "loss": 1.2436, + "step": 8111 + }, + { + "epoch": 0.85, + "learning_rate": 1.3278746708827028e-06, + "loss": 1.2916, + "step": 8112 + }, + { + "epoch": 0.85, + "learning_rate": 1.3260526736060998e-06, + "loss": 1.3127, + "step": 8113 + }, + { + "epoch": 0.85, + "learning_rate": 1.3242318384155728e-06, + "loss": 1.2876, + "step": 8114 + }, + { + "epoch": 0.85, + "learning_rate": 1.3224121655550603e-06, + "loss": 1.4193, + "step": 8115 + }, + { + "epoch": 0.85, + "learning_rate": 1.3205936552683573e-06, + "loss": 1.2978, + "step": 8116 + }, + { + "epoch": 0.85, + "learning_rate": 1.3187763077990912e-06, + "loss": 1.344, + "step": 8117 + }, + { + "epoch": 0.85, + "learning_rate": 1.3169601233907436e-06, + "loss": 1.2493, + "step": 8118 + }, + { + "epoch": 0.85, + "learning_rate": 1.315145102286638e-06, + "loss": 1.344, + "step": 8119 + }, + { + "epoch": 0.85, + "learning_rate": 1.3133312447299385e-06, + "loss": 1.3235, + "step": 8120 + }, + { + "epoch": 0.85, + "learning_rate": 1.3115185509636508e-06, + "loss": 1.3134, + "step": 8121 + }, + { + "epoch": 0.85, + "learning_rate": 1.3097070212306385e-06, + "loss": 1.2735, + "step": 8122 + }, + { + "epoch": 0.85, + "learning_rate": 1.307896655773594e-06, + "loss": 1.4682, + "step": 8123 + }, + { + "epoch": 0.85, + "learning_rate": 1.3060874548350632e-06, + "loss": 1.2092, + "step": 8124 + }, + { + "epoch": 0.85, + "learning_rate": 1.304279418657428e-06, + "loss": 1.314, + "step": 8125 + }, + { + "epoch": 0.85, + "learning_rate": 1.3024725474829215e-06, + "loss": 1.4204, + "step": 8126 + }, + { + "epoch": 0.85, + "learning_rate": 1.3006668415536195e-06, + "loss": 1.298, + "step": 8127 + }, + { + "epoch": 0.85, + "learning_rate": 1.2988623011114377e-06, + "loss": 1.2639, + "step": 8128 + }, + { + "epoch": 0.85, + "learning_rate": 1.2970589263981382e-06, + "loss": 1.291, + "step": 8129 + }, + { + "epoch": 0.85, + "learning_rate": 1.2952567176553298e-06, + "loss": 1.3849, + "step": 8130 + }, + { + "epoch": 0.85, + "learning_rate": 1.293455675124461e-06, + "loss": 1.2594, + "step": 8131 + }, + { + "epoch": 0.85, + "learning_rate": 1.2916557990468192e-06, + "loss": 1.3696, + "step": 8132 + }, + { + "epoch": 0.85, + "learning_rate": 1.289857089663551e-06, + "loss": 1.3263, + "step": 8133 + }, + { + "epoch": 0.85, + "learning_rate": 1.288059547215631e-06, + "loss": 1.302, + "step": 8134 + }, + { + "epoch": 0.85, + "learning_rate": 1.2862631719438878e-06, + "loss": 1.2587, + "step": 8135 + }, + { + "epoch": 0.85, + "learning_rate": 1.2844679640889857e-06, + "loss": 1.3579, + "step": 8136 + }, + { + "epoch": 0.85, + "learning_rate": 1.2826739238914376e-06, + "loss": 1.3246, + "step": 8137 + }, + { + "epoch": 0.85, + "learning_rate": 1.2808810515916016e-06, + "loss": 1.3346, + "step": 8138 + }, + { + "epoch": 0.85, + "learning_rate": 1.279089347429674e-06, + "loss": 1.264, + "step": 8139 + }, + { + "epoch": 0.85, + "learning_rate": 1.277298811645692e-06, + "loss": 1.2276, + "step": 8140 + }, + { + "epoch": 0.85, + "learning_rate": 1.2755094444795524e-06, + "loss": 1.2699, + "step": 8141 + }, + { + "epoch": 0.85, + "learning_rate": 1.273721246170976e-06, + "loss": 1.2784, + "step": 8142 + }, + { + "epoch": 0.85, + "learning_rate": 1.2719342169595406e-06, + "loss": 1.3973, + "step": 8143 + }, + { + "epoch": 0.85, + "learning_rate": 1.2701483570846572e-06, + "loss": 1.2869, + "step": 8144 + }, + { + "epoch": 0.85, + "learning_rate": 1.268363666785588e-06, + "loss": 1.0653, + "step": 8145 + }, + { + "epoch": 0.85, + "learning_rate": 1.266580146301437e-06, + "loss": 1.0105, + "step": 8146 + }, + { + "epoch": 0.85, + "learning_rate": 1.264797795871149e-06, + "loss": 1.3069, + "step": 8147 + }, + { + "epoch": 0.85, + "learning_rate": 1.2630166157335077e-06, + "loss": 1.303, + "step": 8148 + }, + { + "epoch": 0.85, + "learning_rate": 1.2612366061271552e-06, + "loss": 1.2883, + "step": 8149 + }, + { + "epoch": 0.85, + "learning_rate": 1.2594577672905594e-06, + "loss": 1.4152, + "step": 8150 + }, + { + "epoch": 0.85, + "learning_rate": 1.257680099462043e-06, + "loss": 1.273, + "step": 8151 + }, + { + "epoch": 0.85, + "learning_rate": 1.2559036028797677e-06, + "loss": 1.2793, + "step": 8152 + }, + { + "epoch": 0.85, + "learning_rate": 1.2541282777817354e-06, + "loss": 1.3001, + "step": 8153 + }, + { + "epoch": 0.86, + "learning_rate": 1.252354124405799e-06, + "loss": 1.3743, + "step": 8154 + }, + { + "epoch": 0.86, + "learning_rate": 1.2505811429896432e-06, + "loss": 1.2804, + "step": 8155 + }, + { + "epoch": 0.86, + "learning_rate": 1.2488093337708062e-06, + "loss": 1.3354, + "step": 8156 + }, + { + "epoch": 0.86, + "learning_rate": 1.2470386969866655e-06, + "loss": 1.3836, + "step": 8157 + }, + { + "epoch": 0.86, + "learning_rate": 1.2452692328744386e-06, + "loss": 1.2499, + "step": 8158 + }, + { + "epoch": 0.86, + "learning_rate": 1.2435009416711853e-06, + "loss": 1.4049, + "step": 8159 + }, + { + "epoch": 0.86, + "eval_loss": 1.3945679664611816, + "eval_runtime": 77.4963, + "eval_samples_per_second": 1.665, + "eval_steps_per_second": 0.116, + "step": 8159 + }, + { + "epoch": 0.86, + "learning_rate": 1.2417338236138199e-06, + "loss": 1.261, + "step": 8160 + }, + { + "epoch": 0.86, + "learning_rate": 1.2399678789390823e-06, + "loss": 1.3172, + "step": 8161 + }, + { + "epoch": 0.86, + "learning_rate": 1.238203107883571e-06, + "loss": 1.3836, + "step": 8162 + }, + { + "epoch": 0.86, + "learning_rate": 1.2364395106837124e-06, + "loss": 1.3116, + "step": 8163 + }, + { + "epoch": 0.86, + "learning_rate": 1.2346770875757874e-06, + "loss": 1.2897, + "step": 8164 + }, + { + "epoch": 0.86, + "learning_rate": 1.2329158387959172e-06, + "loss": 1.3148, + "step": 8165 + }, + { + "epoch": 0.86, + "learning_rate": 1.231155764580062e-06, + "loss": 1.2744, + "step": 8166 + }, + { + "epoch": 0.86, + "learning_rate": 1.229396865164022e-06, + "loss": 1.3159, + "step": 8167 + }, + { + "epoch": 0.86, + "learning_rate": 1.2276391407834532e-06, + "loss": 1.3238, + "step": 8168 + }, + { + "epoch": 0.86, + "learning_rate": 1.2258825916738383e-06, + "loss": 1.3376, + "step": 8169 + }, + { + "epoch": 0.86, + "learning_rate": 1.2241272180705143e-06, + "loss": 1.2715, + "step": 8170 + }, + { + "epoch": 0.86, + "learning_rate": 1.2223730202086525e-06, + "loss": 1.3022, + "step": 8171 + }, + { + "epoch": 0.86, + "learning_rate": 1.2206199983232726e-06, + "loss": 1.3354, + "step": 8172 + }, + { + "epoch": 0.86, + "learning_rate": 1.2188681526492363e-06, + "loss": 1.4273, + "step": 8173 + }, + { + "epoch": 0.86, + "learning_rate": 1.2171174834212407e-06, + "loss": 1.3272, + "step": 8174 + }, + { + "epoch": 0.86, + "learning_rate": 1.2153679908738337e-06, + "loss": 1.3173, + "step": 8175 + }, + { + "epoch": 0.86, + "learning_rate": 1.2136196752414042e-06, + "loss": 1.2679, + "step": 8176 + }, + { + "epoch": 0.86, + "learning_rate": 1.2118725367581784e-06, + "loss": 1.3409, + "step": 8177 + }, + { + "epoch": 0.86, + "learning_rate": 1.210126575658228e-06, + "loss": 1.3393, + "step": 8178 + }, + { + "epoch": 0.86, + "learning_rate": 1.2083817921754705e-06, + "loss": 1.3126, + "step": 8179 + }, + { + "epoch": 0.86, + "learning_rate": 1.2066381865436571e-06, + "loss": 1.3525, + "step": 8180 + }, + { + "epoch": 0.86, + "learning_rate": 1.2048957589963907e-06, + "loss": 1.3107, + "step": 8181 + }, + { + "epoch": 0.86, + "learning_rate": 1.2031545097671082e-06, + "loss": 1.3374, + "step": 8182 + }, + { + "epoch": 0.86, + "learning_rate": 1.2014144390890937e-06, + "loss": 1.2889, + "step": 8183 + }, + { + "epoch": 0.86, + "learning_rate": 1.1996755471954734e-06, + "loss": 1.3043, + "step": 8184 + }, + { + "epoch": 0.86, + "learning_rate": 1.1979378343192126e-06, + "loss": 1.3172, + "step": 8185 + }, + { + "epoch": 0.86, + "learning_rate": 1.1962013006931172e-06, + "loss": 1.3526, + "step": 8186 + }, + { + "epoch": 0.86, + "learning_rate": 1.1944659465498443e-06, + "loss": 1.32, + "step": 8187 + }, + { + "epoch": 0.86, + "learning_rate": 1.1927317721218822e-06, + "loss": 1.3449, + "step": 8188 + }, + { + "epoch": 0.86, + "learning_rate": 1.1909987776415699e-06, + "loss": 1.2887, + "step": 8189 + }, + { + "epoch": 0.86, + "learning_rate": 1.189266963341078e-06, + "loss": 1.368, + "step": 8190 + }, + { + "epoch": 0.86, + "learning_rate": 1.18753632945243e-06, + "loss": 1.3297, + "step": 8191 + }, + { + "epoch": 0.86, + "learning_rate": 1.185806876207486e-06, + "loss": 1.3447, + "step": 8192 + }, + { + "epoch": 0.86, + "learning_rate": 1.184078603837946e-06, + "loss": 1.291, + "step": 8193 + }, + { + "epoch": 0.86, + "learning_rate": 1.182351512575355e-06, + "loss": 1.3272, + "step": 8194 + }, + { + "epoch": 0.86, + "learning_rate": 1.180625602651101e-06, + "loss": 1.2771, + "step": 8195 + }, + { + "epoch": 0.86, + "learning_rate": 1.178900874296407e-06, + "loss": 1.2562, + "step": 8196 + }, + { + "epoch": 0.86, + "learning_rate": 1.177177327742346e-06, + "loss": 1.2508, + "step": 8197 + }, + { + "epoch": 0.86, + "learning_rate": 1.1754549632198298e-06, + "loss": 1.2923, + "step": 8198 + }, + { + "epoch": 0.86, + "learning_rate": 1.1737337809596072e-06, + "loss": 1.3251, + "step": 8199 + }, + { + "epoch": 0.86, + "learning_rate": 1.1720137811922761e-06, + "loss": 1.2729, + "step": 8200 + }, + { + "epoch": 0.86, + "learning_rate": 1.1702949641482687e-06, + "loss": 1.2635, + "step": 8201 + }, + { + "epoch": 0.86, + "learning_rate": 1.1685773300578651e-06, + "loss": 1.3456, + "step": 8202 + }, + { + "epoch": 0.86, + "learning_rate": 1.1668608791511838e-06, + "loss": 1.2506, + "step": 8203 + }, + { + "epoch": 0.86, + "learning_rate": 1.1651456116581838e-06, + "loss": 1.4416, + "step": 8204 + }, + { + "epoch": 0.86, + "learning_rate": 1.163431527808666e-06, + "loss": 1.3066, + "step": 8205 + }, + { + "epoch": 0.86, + "learning_rate": 1.161718627832279e-06, + "loss": 1.2943, + "step": 8206 + }, + { + "epoch": 0.86, + "learning_rate": 1.1600069119585e-06, + "loss": 1.2785, + "step": 8207 + }, + { + "epoch": 0.86, + "learning_rate": 1.1582963804166614e-06, + "loss": 1.3252, + "step": 8208 + }, + { + "epoch": 0.86, + "learning_rate": 1.1565870334359263e-06, + "loss": 1.2878, + "step": 8209 + }, + { + "epoch": 0.86, + "learning_rate": 1.154878871245303e-06, + "loss": 1.2809, + "step": 8210 + }, + { + "epoch": 0.86, + "learning_rate": 1.1531718940736458e-06, + "loss": 1.3194, + "step": 8211 + }, + { + "epoch": 0.86, + "learning_rate": 1.1514661021496432e-06, + "loss": 1.2898, + "step": 8212 + }, + { + "epoch": 0.86, + "learning_rate": 1.1497614957018233e-06, + "loss": 1.3392, + "step": 8213 + }, + { + "epoch": 0.86, + "learning_rate": 1.1480580749585669e-06, + "loss": 1.2746, + "step": 8214 + }, + { + "epoch": 0.86, + "learning_rate": 1.1463558401480824e-06, + "loss": 1.2374, + "step": 8215 + }, + { + "epoch": 0.86, + "learning_rate": 1.1446547914984296e-06, + "loss": 1.334, + "step": 8216 + }, + { + "epoch": 0.86, + "learning_rate": 1.1429549292375053e-06, + "loss": 1.0102, + "step": 8217 + }, + { + "epoch": 0.86, + "learning_rate": 1.1412562535930448e-06, + "loss": 0.9128, + "step": 8218 + }, + { + "epoch": 0.86, + "learning_rate": 1.13955876479263e-06, + "loss": 0.8105, + "step": 8219 + }, + { + "epoch": 0.86, + "learning_rate": 1.137862463063677e-06, + "loss": 0.8131, + "step": 8220 + }, + { + "epoch": 0.86, + "learning_rate": 1.1361673486334478e-06, + "loss": 1.277, + "step": 8221 + }, + { + "epoch": 0.86, + "learning_rate": 1.1344734217290475e-06, + "loss": 1.2847, + "step": 8222 + }, + { + "epoch": 0.86, + "learning_rate": 1.1327806825774158e-06, + "loss": 1.4042, + "step": 8223 + }, + { + "epoch": 0.86, + "learning_rate": 1.1310891314053353e-06, + "loss": 1.1244, + "step": 8224 + }, + { + "epoch": 0.86, + "learning_rate": 1.1293987684394347e-06, + "loss": 1.1722, + "step": 8225 + }, + { + "epoch": 0.86, + "learning_rate": 1.1277095939061732e-06, + "loss": 1.3665, + "step": 8226 + }, + { + "epoch": 0.86, + "learning_rate": 1.1260216080318632e-06, + "loss": 1.3327, + "step": 8227 + }, + { + "epoch": 0.86, + "learning_rate": 1.1243348110426455e-06, + "loss": 1.3167, + "step": 8228 + }, + { + "epoch": 0.86, + "learning_rate": 1.1226492031645109e-06, + "loss": 1.3049, + "step": 8229 + }, + { + "epoch": 0.86, + "learning_rate": 1.1209647846232884e-06, + "loss": 1.2995, + "step": 8230 + }, + { + "epoch": 0.86, + "learning_rate": 1.1192815556446445e-06, + "loss": 1.3078, + "step": 8231 + }, + { + "epoch": 0.86, + "learning_rate": 1.1175995164540887e-06, + "loss": 1.4174, + "step": 8232 + }, + { + "epoch": 0.86, + "learning_rate": 1.1159186672769728e-06, + "loss": 1.2479, + "step": 8233 + }, + { + "epoch": 0.86, + "learning_rate": 1.1142390083384857e-06, + "loss": 1.3166, + "step": 8234 + }, + { + "epoch": 0.86, + "learning_rate": 1.1125605398636607e-06, + "loss": 1.2816, + "step": 8235 + }, + { + "epoch": 0.86, + "learning_rate": 1.1108832620773668e-06, + "loss": 1.3271, + "step": 8236 + }, + { + "epoch": 0.86, + "learning_rate": 1.1092071752043166e-06, + "loss": 1.3389, + "step": 8237 + }, + { + "epoch": 0.86, + "learning_rate": 1.1075322794690658e-06, + "loss": 1.3243, + "step": 8238 + }, + { + "epoch": 0.86, + "learning_rate": 1.1058585750960028e-06, + "loss": 1.2811, + "step": 8239 + }, + { + "epoch": 0.86, + "learning_rate": 1.1041860623093625e-06, + "loss": 1.3068, + "step": 8240 + }, + { + "epoch": 0.86, + "learning_rate": 1.1025147413332215e-06, + "loss": 1.3694, + "step": 8241 + }, + { + "epoch": 0.86, + "learning_rate": 1.1008446123914907e-06, + "loss": 1.3659, + "step": 8242 + }, + { + "epoch": 0.86, + "learning_rate": 1.0991756757079243e-06, + "loss": 1.3976, + "step": 8243 + }, + { + "epoch": 0.86, + "learning_rate": 1.097507931506121e-06, + "loss": 1.3445, + "step": 8244 + }, + { + "epoch": 0.86, + "learning_rate": 1.0958413800095102e-06, + "loss": 1.3606, + "step": 8245 + }, + { + "epoch": 0.86, + "learning_rate": 1.0941760214413721e-06, + "loss": 1.2929, + "step": 8246 + }, + { + "epoch": 0.86, + "learning_rate": 1.0925118560248172e-06, + "loss": 1.3275, + "step": 8247 + }, + { + "epoch": 0.86, + "learning_rate": 1.0908488839828024e-06, + "loss": 1.2897, + "step": 8248 + }, + { + "epoch": 0.87, + "learning_rate": 1.0891871055381264e-06, + "loss": 1.3044, + "step": 8249 + }, + { + "epoch": 0.87, + "learning_rate": 1.08752652091342e-06, + "loss": 1.3451, + "step": 8250 + }, + { + "epoch": 0.87, + "learning_rate": 1.085867130331162e-06, + "loss": 1.3619, + "step": 8251 + }, + { + "epoch": 0.87, + "learning_rate": 1.0842089340136685e-06, + "loss": 1.2743, + "step": 8252 + }, + { + "epoch": 0.87, + "learning_rate": 1.0825519321830925e-06, + "loss": 1.2792, + "step": 8253 + }, + { + "epoch": 0.87, + "learning_rate": 1.0808961250614335e-06, + "loss": 1.3186, + "step": 8254 + }, + { + "epoch": 0.87, + "learning_rate": 1.0792415128705224e-06, + "loss": 1.3143, + "step": 8255 + }, + { + "epoch": 0.87, + "learning_rate": 1.0775880958320362e-06, + "loss": 1.3303, + "step": 8256 + }, + { + "epoch": 0.87, + "learning_rate": 1.075935874167494e-06, + "loss": 1.2601, + "step": 8257 + }, + { + "epoch": 0.87, + "learning_rate": 1.0742848480982494e-06, + "loss": 1.3004, + "step": 8258 + }, + { + "epoch": 0.87, + "learning_rate": 1.0726350178454903e-06, + "loss": 1.2705, + "step": 8259 + }, + { + "epoch": 0.87, + "learning_rate": 1.0709863836302624e-06, + "loss": 1.2801, + "step": 8260 + }, + { + "epoch": 0.87, + "learning_rate": 1.0693389456734338e-06, + "loss": 1.322, + "step": 8261 + }, + { + "epoch": 0.87, + "learning_rate": 1.067692704195721e-06, + "loss": 1.2792, + "step": 8262 + }, + { + "epoch": 0.87, + "learning_rate": 1.0660476594176794e-06, + "loss": 1.3454, + "step": 8263 + }, + { + "epoch": 0.87, + "learning_rate": 1.0644038115596976e-06, + "loss": 1.2557, + "step": 8264 + }, + { + "epoch": 0.87, + "learning_rate": 1.0627611608420163e-06, + "loss": 1.3196, + "step": 8265 + }, + { + "epoch": 0.87, + "learning_rate": 1.0611197074847014e-06, + "loss": 1.3078, + "step": 8266 + }, + { + "epoch": 0.87, + "learning_rate": 1.059479451707669e-06, + "loss": 1.2815, + "step": 8267 + }, + { + "epoch": 0.87, + "learning_rate": 1.0578403937306726e-06, + "loss": 1.2226, + "step": 8268 + }, + { + "epoch": 0.87, + "learning_rate": 1.0562025337732995e-06, + "loss": 1.3396, + "step": 8269 + }, + { + "epoch": 0.87, + "learning_rate": 1.0545658720549844e-06, + "loss": 1.4786, + "step": 8270 + }, + { + "epoch": 0.87, + "learning_rate": 1.0529304087949988e-06, + "loss": 1.2319, + "step": 8271 + }, + { + "epoch": 0.87, + "learning_rate": 1.0512961442124492e-06, + "loss": 1.2866, + "step": 8272 + }, + { + "epoch": 0.87, + "learning_rate": 1.0496630785262874e-06, + "loss": 1.365, + "step": 8273 + }, + { + "epoch": 0.87, + "learning_rate": 1.0480312119553015e-06, + "loss": 1.3054, + "step": 8274 + }, + { + "epoch": 0.87, + "learning_rate": 1.046400544718118e-06, + "loss": 1.3268, + "step": 8275 + }, + { + "epoch": 0.87, + "learning_rate": 1.0447710770332098e-06, + "loss": 1.3574, + "step": 8276 + }, + { + "epoch": 0.87, + "learning_rate": 1.0431428091188766e-06, + "loss": 1.371, + "step": 8277 + }, + { + "epoch": 0.87, + "learning_rate": 1.0415157411932698e-06, + "loss": 1.3201, + "step": 8278 + }, + { + "epoch": 0.87, + "learning_rate": 1.0398898734743734e-06, + "loss": 1.3135, + "step": 8279 + }, + { + "epoch": 0.87, + "learning_rate": 1.0382652061800102e-06, + "loss": 1.2796, + "step": 8280 + }, + { + "epoch": 0.87, + "learning_rate": 1.036641739527846e-06, + "loss": 1.3704, + "step": 8281 + }, + { + "epoch": 0.87, + "learning_rate": 1.0350194737353814e-06, + "loss": 1.2913, + "step": 8282 + }, + { + "epoch": 0.87, + "learning_rate": 1.03339840901996e-06, + "loss": 1.3408, + "step": 8283 + }, + { + "epoch": 0.87, + "learning_rate": 1.0317785455987638e-06, + "loss": 1.2652, + "step": 8284 + }, + { + "epoch": 0.87, + "learning_rate": 1.0301598836888105e-06, + "loss": 1.2724, + "step": 8285 + }, + { + "epoch": 0.87, + "learning_rate": 1.0285424235069586e-06, + "loss": 1.2985, + "step": 8286 + }, + { + "epoch": 0.87, + "learning_rate": 1.0269261652699115e-06, + "loss": 1.3631, + "step": 8287 + }, + { + "epoch": 0.87, + "learning_rate": 1.0253111091941992e-06, + "loss": 1.2494, + "step": 8288 + }, + { + "epoch": 0.87, + "learning_rate": 1.0236972554962022e-06, + "loss": 1.3331, + "step": 8289 + }, + { + "epoch": 0.87, + "learning_rate": 1.0220846043921351e-06, + "loss": 1.2884, + "step": 8290 + }, + { + "epoch": 0.87, + "learning_rate": 1.0204731560980496e-06, + "loss": 1.3488, + "step": 8291 + }, + { + "epoch": 0.87, + "learning_rate": 1.018862910829842e-06, + "loss": 1.2698, + "step": 8292 + }, + { + "epoch": 0.87, + "learning_rate": 1.0172538688032396e-06, + "loss": 1.2873, + "step": 8293 + }, + { + "epoch": 0.87, + "learning_rate": 1.0156460302338135e-06, + "loss": 1.3644, + "step": 8294 + }, + { + "epoch": 0.87, + "learning_rate": 1.0140393953369764e-06, + "loss": 1.3445, + "step": 8295 + }, + { + "epoch": 0.87, + "learning_rate": 1.0124339643279724e-06, + "loss": 1.3448, + "step": 8296 + }, + { + "epoch": 0.87, + "learning_rate": 1.0108297374218877e-06, + "loss": 1.2984, + "step": 8297 + }, + { + "epoch": 0.87, + "learning_rate": 1.009226714833652e-06, + "loss": 1.3224, + "step": 8298 + }, + { + "epoch": 0.87, + "learning_rate": 1.0076248967780245e-06, + "loss": 1.2924, + "step": 8299 + }, + { + "epoch": 0.87, + "learning_rate": 1.00602428346961e-06, + "loss": 1.2344, + "step": 8300 + }, + { + "epoch": 0.87, + "learning_rate": 1.004424875122848e-06, + "loss": 1.3089, + "step": 8301 + }, + { + "epoch": 0.87, + "learning_rate": 1.0028266719520174e-06, + "loss": 1.291, + "step": 8302 + }, + { + "epoch": 0.87, + "learning_rate": 1.0012296741712414e-06, + "loss": 1.3404, + "step": 8303 + }, + { + "epoch": 0.87, + "learning_rate": 9.996338819944706e-07, + "loss": 1.5152, + "step": 8304 + }, + { + "epoch": 0.87, + "learning_rate": 9.980392956355023e-07, + "loss": 1.3492, + "step": 8305 + }, + { + "epoch": 0.87, + "learning_rate": 9.96445915307973e-07, + "loss": 1.3056, + "step": 8306 + }, + { + "epoch": 0.87, + "learning_rate": 9.948537412253502e-07, + "loss": 1.3223, + "step": 8307 + }, + { + "epoch": 0.87, + "learning_rate": 9.93262773600946e-07, + "loss": 1.3295, + "step": 8308 + }, + { + "epoch": 0.87, + "learning_rate": 9.916730126479113e-07, + "loss": 1.3156, + "step": 8309 + }, + { + "epoch": 0.87, + "learning_rate": 9.900844585792301e-07, + "loss": 1.2701, + "step": 8310 + }, + { + "epoch": 0.87, + "learning_rate": 9.884971116077302e-07, + "loss": 1.3171, + "step": 8311 + }, + { + "epoch": 0.87, + "learning_rate": 9.869109719460735e-07, + "loss": 1.2599, + "step": 8312 + }, + { + "epoch": 0.87, + "learning_rate": 9.85326039806762e-07, + "loss": 1.2999, + "step": 8313 + }, + { + "epoch": 0.87, + "learning_rate": 9.837423154021385e-07, + "loss": 1.3691, + "step": 8314 + }, + { + "epoch": 0.87, + "learning_rate": 9.821597989443775e-07, + "loss": 1.279, + "step": 8315 + }, + { + "epoch": 0.87, + "learning_rate": 9.805784906454985e-07, + "loss": 1.2682, + "step": 8316 + }, + { + "epoch": 0.87, + "learning_rate": 9.789983907173562e-07, + "loss": 1.3321, + "step": 8317 + }, + { + "epoch": 0.87, + "learning_rate": 9.774194993716413e-07, + "loss": 1.326, + "step": 8318 + }, + { + "epoch": 0.87, + "learning_rate": 9.75841816819887e-07, + "loss": 1.2541, + "step": 8319 + }, + { + "epoch": 0.87, + "learning_rate": 9.742653432734594e-07, + "loss": 1.2871, + "step": 8320 + }, + { + "epoch": 0.87, + "learning_rate": 9.726900789435668e-07, + "loss": 1.2535, + "step": 8321 + }, + { + "epoch": 0.87, + "learning_rate": 9.711160240412564e-07, + "loss": 1.3008, + "step": 8322 + }, + { + "epoch": 0.87, + "learning_rate": 9.695431787774068e-07, + "loss": 1.2925, + "step": 8323 + }, + { + "epoch": 0.87, + "learning_rate": 9.679715433627424e-07, + "loss": 1.4127, + "step": 8324 + }, + { + "epoch": 0.87, + "learning_rate": 9.664011180078215e-07, + "loss": 1.2961, + "step": 8325 + }, + { + "epoch": 0.87, + "learning_rate": 9.64831902923038e-07, + "loss": 1.2446, + "step": 8326 + }, + { + "epoch": 0.87, + "learning_rate": 9.632638983186316e-07, + "loss": 1.3279, + "step": 8327 + }, + { + "epoch": 0.87, + "learning_rate": 9.616971044046686e-07, + "loss": 1.3128, + "step": 8328 + }, + { + "epoch": 0.87, + "learning_rate": 9.601315213910622e-07, + "loss": 1.2371, + "step": 8329 + }, + { + "epoch": 0.87, + "learning_rate": 9.585671494875614e-07, + "loss": 1.2844, + "step": 8330 + }, + { + "epoch": 0.87, + "learning_rate": 9.570039889037485e-07, + "loss": 1.3417, + "step": 8331 + }, + { + "epoch": 0.87, + "learning_rate": 9.554420398490494e-07, + "loss": 1.3149, + "step": 8332 + }, + { + "epoch": 0.87, + "learning_rate": 9.538813025327266e-07, + "loss": 1.2588, + "step": 8333 + }, + { + "epoch": 0.87, + "learning_rate": 9.523217771638748e-07, + "loss": 1.2999, + "step": 8334 + }, + { + "epoch": 0.87, + "learning_rate": 9.507634639514319e-07, + "loss": 1.4602, + "step": 8335 + }, + { + "epoch": 0.87, + "learning_rate": 9.492063631041737e-07, + "loss": 1.3576, + "step": 8336 + }, + { + "epoch": 0.87, + "learning_rate": 9.476504748307091e-07, + "loss": 1.3507, + "step": 8337 + }, + { + "epoch": 0.87, + "learning_rate": 9.460957993394903e-07, + "loss": 1.3293, + "step": 8338 + }, + { + "epoch": 0.87, + "learning_rate": 9.445423368387995e-07, + "loss": 1.3586, + "step": 8339 + }, + { + "epoch": 0.87, + "learning_rate": 9.429900875367637e-07, + "loss": 1.4114, + "step": 8340 + }, + { + "epoch": 0.87, + "learning_rate": 9.414390516413452e-07, + "loss": 1.3932, + "step": 8341 + }, + { + "epoch": 0.87, + "learning_rate": 9.398892293603401e-07, + "loss": 1.357, + "step": 8342 + }, + { + "epoch": 0.87, + "learning_rate": 9.383406209013856e-07, + "loss": 1.2858, + "step": 8343 + }, + { + "epoch": 0.88, + "learning_rate": 9.367932264719581e-07, + "loss": 1.2484, + "step": 8344 + }, + { + "epoch": 0.88, + "learning_rate": 9.352470462793651e-07, + "loss": 1.3251, + "step": 8345 + }, + { + "epoch": 0.88, + "learning_rate": 9.337020805307583e-07, + "loss": 1.2653, + "step": 8346 + }, + { + "epoch": 0.88, + "learning_rate": 9.321583294331204e-07, + "loss": 1.2925, + "step": 8347 + }, + { + "epoch": 0.88, + "learning_rate": 9.306157931932758e-07, + "loss": 1.3092, + "step": 8348 + }, + { + "epoch": 0.88, + "learning_rate": 9.290744720178857e-07, + "loss": 1.3858, + "step": 8349 + }, + { + "epoch": 0.88, + "learning_rate": 9.275343661134451e-07, + "loss": 1.2612, + "step": 8350 + }, + { + "epoch": 0.88, + "learning_rate": 9.259954756862899e-07, + "loss": 1.3053, + "step": 8351 + }, + { + "epoch": 0.88, + "learning_rate": 9.244578009425942e-07, + "loss": 1.3401, + "step": 8352 + }, + { + "epoch": 0.88, + "learning_rate": 9.229213420883621e-07, + "loss": 1.3442, + "step": 8353 + }, + { + "epoch": 0.88, + "learning_rate": 9.213860993294421e-07, + "loss": 1.3501, + "step": 8354 + }, + { + "epoch": 0.88, + "learning_rate": 9.198520728715199e-07, + "loss": 1.2916, + "step": 8355 + }, + { + "epoch": 0.88, + "learning_rate": 9.18319262920111e-07, + "loss": 1.3291, + "step": 8356 + }, + { + "epoch": 0.88, + "learning_rate": 9.167876696805767e-07, + "loss": 1.3369, + "step": 8357 + }, + { + "epoch": 0.88, + "learning_rate": 9.152572933581061e-07, + "loss": 1.3324, + "step": 8358 + }, + { + "epoch": 0.88, + "eval_loss": 1.3944451808929443, + "eval_runtime": 77.5126, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 8358 + }, + { + "epoch": 0.88, + "learning_rate": 9.137281341577342e-07, + "loss": 1.3, + "step": 8359 + }, + { + "epoch": 0.88, + "learning_rate": 9.122001922843304e-07, + "loss": 1.2892, + "step": 8360 + }, + { + "epoch": 0.88, + "learning_rate": 9.106734679425944e-07, + "loss": 1.2715, + "step": 8361 + }, + { + "epoch": 0.88, + "learning_rate": 9.091479613370723e-07, + "loss": 1.2606, + "step": 8362 + }, + { + "epoch": 0.88, + "learning_rate": 9.076236726721421e-07, + "loss": 1.2707, + "step": 8363 + }, + { + "epoch": 0.88, + "learning_rate": 9.06100602152018e-07, + "loss": 1.3153, + "step": 8364 + }, + { + "epoch": 0.88, + "learning_rate": 9.045787499807545e-07, + "loss": 1.3709, + "step": 8365 + }, + { + "epoch": 0.88, + "learning_rate": 9.030581163622365e-07, + "loss": 1.3828, + "step": 8366 + }, + { + "epoch": 0.88, + "learning_rate": 9.015387015001942e-07, + "loss": 1.2626, + "step": 8367 + }, + { + "epoch": 0.88, + "learning_rate": 9.000205055981892e-07, + "loss": 1.3162, + "step": 8368 + }, + { + "epoch": 0.88, + "learning_rate": 8.985035288596178e-07, + "loss": 1.2654, + "step": 8369 + }, + { + "epoch": 0.88, + "learning_rate": 8.969877714877195e-07, + "loss": 1.3058, + "step": 8370 + }, + { + "epoch": 0.88, + "learning_rate": 8.954732336855665e-07, + "loss": 1.2438, + "step": 8371 + }, + { + "epoch": 0.88, + "learning_rate": 8.939599156560652e-07, + "loss": 1.3767, + "step": 8372 + }, + { + "epoch": 0.88, + "learning_rate": 8.924478176019647e-07, + "loss": 1.3284, + "step": 8373 + }, + { + "epoch": 0.88, + "learning_rate": 8.90936939725845e-07, + "loss": 1.3417, + "step": 8374 + }, + { + "epoch": 0.88, + "learning_rate": 8.894272822301242e-07, + "loss": 1.3662, + "step": 8375 + }, + { + "epoch": 0.88, + "learning_rate": 8.879188453170606e-07, + "loss": 1.2383, + "step": 8376 + }, + { + "epoch": 0.88, + "learning_rate": 8.864116291887437e-07, + "loss": 1.2515, + "step": 8377 + }, + { + "epoch": 0.88, + "learning_rate": 8.849056340471018e-07, + "loss": 1.356, + "step": 8378 + }, + { + "epoch": 0.88, + "learning_rate": 8.834008600939025e-07, + "loss": 1.3366, + "step": 8379 + }, + { + "epoch": 0.88, + "learning_rate": 8.818973075307424e-07, + "loss": 1.2689, + "step": 8380 + }, + { + "epoch": 0.88, + "learning_rate": 8.803949765590614e-07, + "loss": 1.3408, + "step": 8381 + }, + { + "epoch": 0.88, + "learning_rate": 8.788938673801339e-07, + "loss": 1.3399, + "step": 8382 + }, + { + "epoch": 0.88, + "learning_rate": 8.773939801950671e-07, + "loss": 1.2561, + "step": 8383 + }, + { + "epoch": 0.88, + "learning_rate": 8.758953152048121e-07, + "loss": 1.3255, + "step": 8384 + }, + { + "epoch": 0.88, + "learning_rate": 8.743978726101454e-07, + "loss": 1.2811, + "step": 8385 + }, + { + "epoch": 0.88, + "learning_rate": 8.729016526116907e-07, + "loss": 1.3295, + "step": 8386 + }, + { + "epoch": 0.88, + "learning_rate": 8.714066554099021e-07, + "loss": 1.2932, + "step": 8387 + }, + { + "epoch": 0.88, + "learning_rate": 8.699128812050683e-07, + "loss": 1.335, + "step": 8388 + }, + { + "epoch": 0.88, + "learning_rate": 8.684203301973182e-07, + "loss": 1.3336, + "step": 8389 + }, + { + "epoch": 0.88, + "learning_rate": 8.669290025866173e-07, + "loss": 1.3123, + "step": 8390 + }, + { + "epoch": 0.88, + "learning_rate": 8.654388985727624e-07, + "loss": 1.4056, + "step": 8391 + }, + { + "epoch": 0.88, + "learning_rate": 8.639500183553917e-07, + "loss": 1.2079, + "step": 8392 + }, + { + "epoch": 0.88, + "learning_rate": 8.624623621339723e-07, + "loss": 1.3789, + "step": 8393 + }, + { + "epoch": 0.88, + "learning_rate": 8.609759301078168e-07, + "loss": 1.2845, + "step": 8394 + }, + { + "epoch": 0.88, + "learning_rate": 8.594907224760674e-07, + "loss": 1.2322, + "step": 8395 + }, + { + "epoch": 0.88, + "learning_rate": 8.580067394377023e-07, + "loss": 1.2595, + "step": 8396 + }, + { + "epoch": 0.88, + "learning_rate": 8.565239811915382e-07, + "loss": 1.2703, + "step": 8397 + }, + { + "epoch": 0.88, + "learning_rate": 8.550424479362285e-07, + "loss": 1.2627, + "step": 8398 + }, + { + "epoch": 0.88, + "learning_rate": 8.535621398702565e-07, + "loss": 1.311, + "step": 8399 + }, + { + "epoch": 0.88, + "learning_rate": 8.520830571919481e-07, + "loss": 1.2656, + "step": 8400 + }, + { + "epoch": 0.88, + "learning_rate": 8.506052000994636e-07, + "loss": 1.2514, + "step": 8401 + }, + { + "epoch": 0.88, + "learning_rate": 8.491285687907935e-07, + "loss": 1.2494, + "step": 8402 + }, + { + "epoch": 0.88, + "learning_rate": 8.476531634637741e-07, + "loss": 0.9287, + "step": 8403 + }, + { + "epoch": 0.88, + "learning_rate": 8.461789843160662e-07, + "loss": 0.6155, + "step": 8404 + }, + { + "epoch": 0.88, + "learning_rate": 8.44706031545176e-07, + "loss": 0.9869, + "step": 8405 + }, + { + "epoch": 0.88, + "learning_rate": 8.432343053484404e-07, + "loss": 1.3074, + "step": 8406 + }, + { + "epoch": 0.88, + "learning_rate": 8.417638059230305e-07, + "loss": 1.3175, + "step": 8407 + }, + { + "epoch": 0.88, + "learning_rate": 8.402945334659584e-07, + "loss": 1.2605, + "step": 8408 + }, + { + "epoch": 0.88, + "learning_rate": 8.388264881740693e-07, + "loss": 1.3429, + "step": 8409 + }, + { + "epoch": 0.88, + "learning_rate": 8.373596702440401e-07, + "loss": 1.2985, + "step": 8410 + }, + { + "epoch": 0.88, + "learning_rate": 8.358940798723903e-07, + "loss": 1.2686, + "step": 8411 + }, + { + "epoch": 0.88, + "learning_rate": 8.344297172554672e-07, + "loss": 1.353, + "step": 8412 + }, + { + "epoch": 0.88, + "learning_rate": 8.329665825894617e-07, + "loss": 1.3329, + "step": 8413 + }, + { + "epoch": 0.88, + "learning_rate": 8.31504676070396e-07, + "loss": 1.3813, + "step": 8414 + }, + { + "epoch": 0.88, + "learning_rate": 8.300439978941244e-07, + "loss": 1.2658, + "step": 8415 + }, + { + "epoch": 0.88, + "learning_rate": 8.285845482563437e-07, + "loss": 1.2827, + "step": 8416 + }, + { + "epoch": 0.88, + "learning_rate": 8.271263273525832e-07, + "loss": 1.2247, + "step": 8417 + }, + { + "epoch": 0.88, + "learning_rate": 8.256693353782042e-07, + "loss": 1.29, + "step": 8418 + }, + { + "epoch": 0.88, + "learning_rate": 8.242135725284084e-07, + "loss": 1.3085, + "step": 8419 + }, + { + "epoch": 0.88, + "learning_rate": 8.227590389982276e-07, + "loss": 1.2828, + "step": 8420 + }, + { + "epoch": 0.88, + "learning_rate": 8.213057349825348e-07, + "loss": 1.3721, + "step": 8421 + }, + { + "epoch": 0.88, + "learning_rate": 8.198536606760366e-07, + "loss": 1.3304, + "step": 8422 + }, + { + "epoch": 0.88, + "learning_rate": 8.184028162732694e-07, + "loss": 1.3184, + "step": 8423 + }, + { + "epoch": 0.88, + "learning_rate": 8.16953201968611e-07, + "loss": 1.3326, + "step": 8424 + }, + { + "epoch": 0.88, + "learning_rate": 8.155048179562752e-07, + "loss": 1.3035, + "step": 8425 + }, + { + "epoch": 0.88, + "learning_rate": 8.140576644303033e-07, + "loss": 1.155, + "step": 8426 + }, + { + "epoch": 0.88, + "learning_rate": 8.126117415845802e-07, + "loss": 1.2749, + "step": 8427 + }, + { + "epoch": 0.88, + "learning_rate": 8.111670496128222e-07, + "loss": 1.2703, + "step": 8428 + }, + { + "epoch": 0.88, + "learning_rate": 8.097235887085786e-07, + "loss": 1.4058, + "step": 8429 + }, + { + "epoch": 0.88, + "learning_rate": 8.082813590652405e-07, + "loss": 1.2774, + "step": 8430 + }, + { + "epoch": 0.88, + "learning_rate": 8.068403608760233e-07, + "loss": 1.2792, + "step": 8431 + }, + { + "epoch": 0.88, + "learning_rate": 8.054005943339883e-07, + "loss": 1.3317, + "step": 8432 + }, + { + "epoch": 0.88, + "learning_rate": 8.039620596320275e-07, + "loss": 1.2015, + "step": 8433 + }, + { + "epoch": 0.88, + "learning_rate": 8.025247569628647e-07, + "loss": 1.2729, + "step": 8434 + }, + { + "epoch": 0.88, + "learning_rate": 8.010886865190626e-07, + "loss": 1.2649, + "step": 8435 + }, + { + "epoch": 0.88, + "learning_rate": 7.996538484930194e-07, + "loss": 1.3821, + "step": 8436 + }, + { + "epoch": 0.88, + "learning_rate": 7.982202430769648e-07, + "loss": 1.3019, + "step": 8437 + }, + { + "epoch": 0.88, + "learning_rate": 7.967878704629662e-07, + "loss": 1.2648, + "step": 8438 + }, + { + "epoch": 0.88, + "learning_rate": 7.953567308429222e-07, + "loss": 1.2948, + "step": 8439 + }, + { + "epoch": 0.89, + "learning_rate": 7.939268244085718e-07, + "loss": 1.2666, + "step": 8440 + }, + { + "epoch": 0.89, + "learning_rate": 7.924981513514851e-07, + "loss": 1.3525, + "step": 8441 + }, + { + "epoch": 0.89, + "learning_rate": 7.910707118630667e-07, + "loss": 1.2863, + "step": 8442 + }, + { + "epoch": 0.89, + "learning_rate": 7.896445061345559e-07, + "loss": 1.2562, + "step": 8443 + }, + { + "epoch": 0.89, + "learning_rate": 7.882195343570309e-07, + "loss": 1.2945, + "step": 8444 + }, + { + "epoch": 0.89, + "learning_rate": 7.86795796721398e-07, + "loss": 1.3206, + "step": 8445 + }, + { + "epoch": 0.89, + "learning_rate": 7.853732934184022e-07, + "loss": 1.2354, + "step": 8446 + }, + { + "epoch": 0.89, + "learning_rate": 7.839520246386245e-07, + "loss": 1.2769, + "step": 8447 + }, + { + "epoch": 0.89, + "learning_rate": 7.825319905724749e-07, + "loss": 1.2897, + "step": 8448 + }, + { + "epoch": 0.89, + "learning_rate": 7.811131914102055e-07, + "loss": 1.2605, + "step": 8449 + }, + { + "epoch": 0.89, + "learning_rate": 7.796956273418954e-07, + "loss": 1.2689, + "step": 8450 + }, + { + "epoch": 0.89, + "learning_rate": 7.782792985574628e-07, + "loss": 1.2753, + "step": 8451 + }, + { + "epoch": 0.89, + "learning_rate": 7.768642052466624e-07, + "loss": 1.3375, + "step": 8452 + }, + { + "epoch": 0.89, + "learning_rate": 7.754503475990749e-07, + "loss": 1.2566, + "step": 8453 + }, + { + "epoch": 0.89, + "learning_rate": 7.740377258041242e-07, + "loss": 1.3821, + "step": 8454 + }, + { + "epoch": 0.89, + "learning_rate": 7.726263400510659e-07, + "loss": 1.2773, + "step": 8455 + }, + { + "epoch": 0.89, + "learning_rate": 7.712161905289872e-07, + "loss": 1.3096, + "step": 8456 + }, + { + "epoch": 0.89, + "learning_rate": 7.698072774268151e-07, + "loss": 1.2952, + "step": 8457 + }, + { + "epoch": 0.89, + "learning_rate": 7.683996009333028e-07, + "loss": 1.3119, + "step": 8458 + }, + { + "epoch": 0.89, + "learning_rate": 7.669931612370463e-07, + "loss": 1.244, + "step": 8459 + }, + { + "epoch": 0.89, + "learning_rate": 7.655879585264736e-07, + "loss": 1.3594, + "step": 8460 + }, + { + "epoch": 0.89, + "learning_rate": 7.64183992989842e-07, + "loss": 1.3677, + "step": 8461 + }, + { + "epoch": 0.89, + "learning_rate": 7.627812648152488e-07, + "loss": 1.3049, + "step": 8462 + }, + { + "epoch": 0.89, + "learning_rate": 7.61379774190626e-07, + "loss": 1.2744, + "step": 8463 + }, + { + "epoch": 0.89, + "learning_rate": 7.59979521303732e-07, + "loss": 1.3516, + "step": 8464 + }, + { + "epoch": 0.89, + "learning_rate": 7.585805063421703e-07, + "loss": 1.4835, + "step": 8465 + }, + { + "epoch": 0.89, + "learning_rate": 7.571827294933675e-07, + "loss": 1.3016, + "step": 8466 + }, + { + "epoch": 0.89, + "learning_rate": 7.55786190944593e-07, + "loss": 1.2985, + "step": 8467 + }, + { + "epoch": 0.89, + "learning_rate": 7.543908908829478e-07, + "loss": 1.3137, + "step": 8468 + }, + { + "epoch": 0.89, + "learning_rate": 7.529968294953627e-07, + "loss": 1.3084, + "step": 8469 + }, + { + "epoch": 0.89, + "learning_rate": 7.516040069686092e-07, + "loss": 1.3923, + "step": 8470 + }, + { + "epoch": 0.89, + "learning_rate": 7.502124234892905e-07, + "loss": 1.3569, + "step": 8471 + }, + { + "epoch": 0.89, + "learning_rate": 7.488220792438405e-07, + "loss": 1.2567, + "step": 8472 + }, + { + "epoch": 0.89, + "learning_rate": 7.474329744185294e-07, + "loss": 1.2666, + "step": 8473 + }, + { + "epoch": 0.89, + "learning_rate": 7.460451091994647e-07, + "loss": 1.3691, + "step": 8474 + }, + { + "epoch": 0.89, + "learning_rate": 7.446584837725812e-07, + "loss": 1.2708, + "step": 8475 + }, + { + "epoch": 0.89, + "learning_rate": 7.432730983236547e-07, + "loss": 1.3529, + "step": 8476 + }, + { + "epoch": 0.89, + "learning_rate": 7.418889530382866e-07, + "loss": 1.298, + "step": 8477 + }, + { + "epoch": 0.89, + "learning_rate": 7.405060481019199e-07, + "loss": 1.2789, + "step": 8478 + }, + { + "epoch": 0.89, + "learning_rate": 7.391243836998296e-07, + "loss": 1.3352, + "step": 8479 + }, + { + "epoch": 0.89, + "learning_rate": 7.377439600171199e-07, + "loss": 1.3876, + "step": 8480 + }, + { + "epoch": 0.89, + "learning_rate": 7.363647772387328e-07, + "loss": 1.3081, + "step": 8481 + }, + { + "epoch": 0.89, + "learning_rate": 7.349868355494461e-07, + "loss": 1.2536, + "step": 8482 + }, + { + "epoch": 0.89, + "learning_rate": 7.336101351338654e-07, + "loss": 1.3303, + "step": 8483 + }, + { + "epoch": 0.89, + "learning_rate": 7.322346761764354e-07, + "loss": 1.2785, + "step": 8484 + }, + { + "epoch": 0.89, + "learning_rate": 7.308604588614298e-07, + "loss": 1.3334, + "step": 8485 + }, + { + "epoch": 0.89, + "learning_rate": 7.294874833729603e-07, + "loss": 1.2595, + "step": 8486 + }, + { + "epoch": 0.89, + "learning_rate": 7.281157498949709e-07, + "loss": 1.2814, + "step": 8487 + }, + { + "epoch": 0.89, + "learning_rate": 7.267452586112367e-07, + "loss": 1.3282, + "step": 8488 + }, + { + "epoch": 0.89, + "learning_rate": 7.253760097053686e-07, + "loss": 1.3333, + "step": 8489 + }, + { + "epoch": 0.89, + "learning_rate": 7.240080033608133e-07, + "loss": 1.3541, + "step": 8490 + }, + { + "epoch": 0.89, + "learning_rate": 7.226412397608451e-07, + "loss": 1.3371, + "step": 8491 + }, + { + "epoch": 0.89, + "learning_rate": 7.212757190885767e-07, + "loss": 1.2419, + "step": 8492 + }, + { + "epoch": 0.89, + "learning_rate": 7.199114415269548e-07, + "loss": 1.2842, + "step": 8493 + }, + { + "epoch": 0.89, + "learning_rate": 7.185484072587545e-07, + "loss": 1.283, + "step": 8494 + }, + { + "epoch": 0.89, + "learning_rate": 7.171866164665886e-07, + "loss": 1.1896, + "step": 8495 + }, + { + "epoch": 0.89, + "learning_rate": 7.158260693329011e-07, + "loss": 1.3974, + "step": 8496 + }, + { + "epoch": 0.89, + "learning_rate": 7.144667660399717e-07, + "loss": 1.3376, + "step": 8497 + }, + { + "epoch": 0.89, + "learning_rate": 7.131087067699127e-07, + "loss": 1.2702, + "step": 8498 + }, + { + "epoch": 0.89, + "learning_rate": 7.117518917046662e-07, + "loss": 1.287, + "step": 8499 + }, + { + "epoch": 0.89, + "learning_rate": 7.103963210260123e-07, + "loss": 1.2826, + "step": 8500 + }, + { + "epoch": 0.89, + "learning_rate": 7.090419949155647e-07, + "loss": 1.3345, + "step": 8501 + }, + { + "epoch": 0.89, + "learning_rate": 7.076889135547649e-07, + "loss": 1.2774, + "step": 8502 + }, + { + "epoch": 0.89, + "learning_rate": 7.063370771248934e-07, + "loss": 1.3094, + "step": 8503 + }, + { + "epoch": 0.89, + "learning_rate": 7.049864858070599e-07, + "loss": 1.3025, + "step": 8504 + }, + { + "epoch": 0.89, + "learning_rate": 7.036371397822095e-07, + "loss": 1.2819, + "step": 8505 + }, + { + "epoch": 0.89, + "learning_rate": 7.02289039231121e-07, + "loss": 1.3229, + "step": 8506 + }, + { + "epoch": 0.89, + "learning_rate": 7.009421843344033e-07, + "loss": 1.2722, + "step": 8507 + }, + { + "epoch": 0.89, + "learning_rate": 6.995965752725009e-07, + "loss": 1.2996, + "step": 8508 + }, + { + "epoch": 0.89, + "learning_rate": 6.982522122256929e-07, + "loss": 1.2642, + "step": 8509 + }, + { + "epoch": 0.89, + "learning_rate": 6.969090953740865e-07, + "loss": 1.3545, + "step": 8510 + }, + { + "epoch": 0.89, + "learning_rate": 6.955672248976286e-07, + "loss": 1.3123, + "step": 8511 + }, + { + "epoch": 0.89, + "learning_rate": 6.942266009760901e-07, + "loss": 1.2652, + "step": 8512 + }, + { + "epoch": 0.89, + "learning_rate": 6.928872237890826e-07, + "loss": 1.253, + "step": 8513 + }, + { + "epoch": 0.89, + "learning_rate": 6.915490935160518e-07, + "loss": 1.2942, + "step": 8514 + }, + { + "epoch": 0.89, + "learning_rate": 6.902122103362663e-07, + "loss": 1.2654, + "step": 8515 + }, + { + "epoch": 0.89, + "learning_rate": 6.888765744288384e-07, + "loss": 1.2584, + "step": 8516 + }, + { + "epoch": 0.89, + "learning_rate": 6.875421859727094e-07, + "loss": 1.2705, + "step": 8517 + }, + { + "epoch": 0.89, + "learning_rate": 6.862090451466497e-07, + "loss": 1.2818, + "step": 8518 + }, + { + "epoch": 0.89, + "learning_rate": 6.848771521292686e-07, + "loss": 1.2926, + "step": 8519 + }, + { + "epoch": 0.89, + "learning_rate": 6.835465070990055e-07, + "loss": 1.3328, + "step": 8520 + }, + { + "epoch": 0.89, + "learning_rate": 6.822171102341302e-07, + "loss": 1.2258, + "step": 8521 + }, + { + "epoch": 0.89, + "learning_rate": 6.808889617127523e-07, + "loss": 1.2564, + "step": 8522 + }, + { + "epoch": 0.89, + "learning_rate": 6.79562061712804e-07, + "loss": 1.2874, + "step": 8523 + }, + { + "epoch": 0.89, + "learning_rate": 6.782364104120587e-07, + "loss": 1.3414, + "step": 8524 + }, + { + "epoch": 0.89, + "learning_rate": 6.769120079881209e-07, + "loss": 1.283, + "step": 8525 + }, + { + "epoch": 0.89, + "learning_rate": 6.755888546184242e-07, + "loss": 1.3711, + "step": 8526 + }, + { + "epoch": 0.89, + "learning_rate": 6.742669504802379e-07, + "loss": 1.2608, + "step": 8527 + }, + { + "epoch": 0.89, + "learning_rate": 6.729462957506638e-07, + "loss": 1.219, + "step": 8528 + }, + { + "epoch": 0.89, + "learning_rate": 6.716268906066348e-07, + "loss": 1.3034, + "step": 8529 + }, + { + "epoch": 0.89, + "learning_rate": 6.703087352249183e-07, + "loss": 1.32, + "step": 8530 + }, + { + "epoch": 0.89, + "learning_rate": 6.689918297821119e-07, + "loss": 1.3378, + "step": 8531 + }, + { + "epoch": 0.89, + "learning_rate": 6.676761744546478e-07, + "loss": 1.4375, + "step": 8532 + }, + { + "epoch": 0.89, + "learning_rate": 6.663617694187907e-07, + "loss": 1.285, + "step": 8533 + }, + { + "epoch": 0.89, + "learning_rate": 6.650486148506352e-07, + "loss": 1.3853, + "step": 8534 + }, + { + "epoch": 0.9, + "learning_rate": 6.637367109261117e-07, + "loss": 1.3802, + "step": 8535 + }, + { + "epoch": 0.9, + "learning_rate": 6.62426057820983e-07, + "loss": 1.2851, + "step": 8536 + }, + { + "epoch": 0.9, + "learning_rate": 6.611166557108406e-07, + "loss": 1.2538, + "step": 8537 + }, + { + "epoch": 0.9, + "learning_rate": 6.5980850477111e-07, + "loss": 1.3407, + "step": 8538 + }, + { + "epoch": 0.9, + "learning_rate": 6.585016051770543e-07, + "loss": 1.2401, + "step": 8539 + }, + { + "epoch": 0.9, + "learning_rate": 6.57195957103759e-07, + "loss": 1.3364, + "step": 8540 + }, + { + "epoch": 0.9, + "learning_rate": 6.558915607261517e-07, + "loss": 1.2885, + "step": 8541 + }, + { + "epoch": 0.9, + "learning_rate": 6.545884162189841e-07, + "loss": 1.3406, + "step": 8542 + }, + { + "epoch": 0.9, + "learning_rate": 6.532865237568465e-07, + "loss": 1.3203, + "step": 8543 + }, + { + "epoch": 0.9, + "learning_rate": 6.519858835141601e-07, + "loss": 1.268, + "step": 8544 + }, + { + "epoch": 0.9, + "learning_rate": 6.506864956651749e-07, + "loss": 1.3219, + "step": 8545 + }, + { + "epoch": 0.9, + "learning_rate": 6.493883603839757e-07, + "loss": 1.222, + "step": 8546 + }, + { + "epoch": 0.9, + "learning_rate": 6.480914778444824e-07, + "loss": 1.2386, + "step": 8547 + }, + { + "epoch": 0.9, + "learning_rate": 6.467958482204396e-07, + "loss": 1.3695, + "step": 8548 + }, + { + "epoch": 0.9, + "learning_rate": 6.455014716854324e-07, + "loss": 1.2788, + "step": 8549 + }, + { + "epoch": 0.9, + "learning_rate": 6.442083484128692e-07, + "loss": 1.3252, + "step": 8550 + }, + { + "epoch": 0.9, + "learning_rate": 6.429164785759989e-07, + "loss": 1.366, + "step": 8551 + }, + { + "epoch": 0.9, + "learning_rate": 6.416258623478988e-07, + "loss": 1.329, + "step": 8552 + }, + { + "epoch": 0.9, + "learning_rate": 6.403364999014771e-07, + "loss": 1.3641, + "step": 8553 + }, + { + "epoch": 0.9, + "learning_rate": 6.390483914094747e-07, + "loss": 1.3228, + "step": 8554 + }, + { + "epoch": 0.9, + "learning_rate": 6.377615370444678e-07, + "loss": 1.283, + "step": 8555 + }, + { + "epoch": 0.9, + "learning_rate": 6.364759369788587e-07, + "loss": 1.3105, + "step": 8556 + }, + { + "epoch": 0.9, + "learning_rate": 6.351915913848882e-07, + "loss": 1.3446, + "step": 8557 + }, + { + "epoch": 0.9, + "eval_loss": 1.3943825960159302, + "eval_runtime": 77.555, + "eval_samples_per_second": 1.663, + "eval_steps_per_second": 0.116, + "step": 8557 + }, + { + "epoch": 0.9, + "learning_rate": 6.339085004346213e-07, + "loss": 1.3038, + "step": 8558 + }, + { + "epoch": 0.9, + "learning_rate": 6.326266642999612e-07, + "loss": 1.3111, + "step": 8559 + }, + { + "epoch": 0.9, + "learning_rate": 6.31346083152643e-07, + "loss": 1.3205, + "step": 8560 + }, + { + "epoch": 0.9, + "learning_rate": 6.300667571642283e-07, + "loss": 1.2894, + "step": 8561 + }, + { + "epoch": 0.9, + "learning_rate": 6.287886865061155e-07, + "loss": 1.2867, + "step": 8562 + }, + { + "epoch": 0.9, + "learning_rate": 6.275118713495343e-07, + "loss": 1.2754, + "step": 8563 + }, + { + "epoch": 0.9, + "learning_rate": 6.262363118655434e-07, + "loss": 1.3261, + "step": 8564 + }, + { + "epoch": 0.9, + "learning_rate": 6.249620082250351e-07, + "loss": 1.2957, + "step": 8565 + }, + { + "epoch": 0.9, + "learning_rate": 6.236889605987351e-07, + "loss": 1.3127, + "step": 8566 + }, + { + "epoch": 0.9, + "learning_rate": 6.224171691571967e-07, + "loss": 1.2833, + "step": 8567 + }, + { + "epoch": 0.9, + "learning_rate": 6.211466340708105e-07, + "loss": 1.319, + "step": 8568 + }, + { + "epoch": 0.9, + "learning_rate": 6.198773555097914e-07, + "loss": 1.3115, + "step": 8569 + }, + { + "epoch": 0.9, + "learning_rate": 6.186093336441922e-07, + "loss": 1.6219, + "step": 8570 + }, + { + "epoch": 0.9, + "learning_rate": 6.173425686438972e-07, + "loss": 1.284, + "step": 8571 + }, + { + "epoch": 0.9, + "learning_rate": 6.160770606786171e-07, + "loss": 1.3606, + "step": 8572 + }, + { + "epoch": 0.9, + "learning_rate": 6.148128099178974e-07, + "loss": 1.3493, + "step": 8573 + }, + { + "epoch": 0.9, + "learning_rate": 6.135498165311193e-07, + "loss": 1.292, + "step": 8574 + }, + { + "epoch": 0.9, + "learning_rate": 6.122880806874875e-07, + "loss": 1.2998, + "step": 8575 + }, + { + "epoch": 0.9, + "learning_rate": 6.110276025560446e-07, + "loss": 1.2683, + "step": 8576 + }, + { + "epoch": 0.9, + "learning_rate": 6.097683823056589e-07, + "loss": 1.3264, + "step": 8577 + }, + { + "epoch": 0.9, + "learning_rate": 6.085104201050363e-07, + "loss": 1.2534, + "step": 8578 + }, + { + "epoch": 0.9, + "learning_rate": 6.072537161227121e-07, + "loss": 1.3249, + "step": 8579 + }, + { + "epoch": 0.9, + "learning_rate": 6.059982705270507e-07, + "loss": 1.2675, + "step": 8580 + }, + { + "epoch": 0.9, + "learning_rate": 6.047440834862495e-07, + "loss": 1.2406, + "step": 8581 + }, + { + "epoch": 0.9, + "learning_rate": 6.034911551683387e-07, + "loss": 1.3016, + "step": 8582 + }, + { + "epoch": 0.9, + "learning_rate": 6.022394857411762e-07, + "loss": 1.1855, + "step": 8583 + }, + { + "epoch": 0.9, + "learning_rate": 6.009890753724556e-07, + "loss": 1.3572, + "step": 8584 + }, + { + "epoch": 0.9, + "learning_rate": 5.997399242297009e-07, + "loss": 1.2925, + "step": 8585 + }, + { + "epoch": 0.9, + "learning_rate": 5.984920324802624e-07, + "loss": 1.2864, + "step": 8586 + }, + { + "epoch": 0.9, + "learning_rate": 5.972454002913286e-07, + "loss": 1.4783, + "step": 8587 + }, + { + "epoch": 0.9, + "learning_rate": 5.960000278299139e-07, + "loss": 1.273, + "step": 8588 + }, + { + "epoch": 0.9, + "learning_rate": 5.94755915262868e-07, + "loss": 1.2771, + "step": 8589 + }, + { + "epoch": 0.9, + "learning_rate": 5.935130627568708e-07, + "loss": 1.2951, + "step": 8590 + }, + { + "epoch": 0.9, + "learning_rate": 5.922714704784304e-07, + "loss": 1.2976, + "step": 8591 + }, + { + "epoch": 0.9, + "learning_rate": 5.910311385938893e-07, + "loss": 1.3319, + "step": 8592 + }, + { + "epoch": 0.9, + "learning_rate": 5.897920672694202e-07, + "loss": 1.1034, + "step": 8593 + }, + { + "epoch": 0.9, + "learning_rate": 5.885542566710267e-07, + "loss": 1.2838, + "step": 8594 + }, + { + "epoch": 0.9, + "learning_rate": 5.873177069645442e-07, + "loss": 1.3344, + "step": 8595 + }, + { + "epoch": 0.9, + "learning_rate": 5.860824183156356e-07, + "loss": 1.3194, + "step": 8596 + }, + { + "epoch": 0.9, + "learning_rate": 5.848483908898017e-07, + "loss": 1.3043, + "step": 8597 + }, + { + "epoch": 0.9, + "learning_rate": 5.836156248523694e-07, + "loss": 1.3296, + "step": 8598 + }, + { + "epoch": 0.9, + "learning_rate": 5.823841203684965e-07, + "loss": 1.3101, + "step": 8599 + }, + { + "epoch": 0.9, + "learning_rate": 5.811538776031733e-07, + "loss": 1.2394, + "step": 8600 + }, + { + "epoch": 0.9, + "learning_rate": 5.799248967212223e-07, + "loss": 1.3053, + "step": 8601 + }, + { + "epoch": 0.9, + "learning_rate": 5.786971778872929e-07, + "loss": 1.3227, + "step": 8602 + }, + { + "epoch": 0.9, + "learning_rate": 5.774707212658692e-07, + "loss": 1.2454, + "step": 8603 + }, + { + "epoch": 0.9, + "learning_rate": 5.762455270212663e-07, + "loss": 1.2644, + "step": 8604 + }, + { + "epoch": 0.9, + "learning_rate": 5.750215953176253e-07, + "loss": 1.3815, + "step": 8605 + }, + { + "epoch": 0.9, + "learning_rate": 5.737989263189258e-07, + "loss": 1.3419, + "step": 8606 + }, + { + "epoch": 0.9, + "learning_rate": 5.725775201889694e-07, + "loss": 1.3521, + "step": 8607 + }, + { + "epoch": 0.9, + "learning_rate": 5.71357377091396e-07, + "loss": 1.3061, + "step": 8608 + }, + { + "epoch": 0.9, + "learning_rate": 5.701384971896751e-07, + "loss": 1.2356, + "step": 8609 + }, + { + "epoch": 0.9, + "learning_rate": 5.689208806471002e-07, + "loss": 1.4948, + "step": 8610 + }, + { + "epoch": 0.9, + "learning_rate": 5.677045276268045e-07, + "loss": 1.3552, + "step": 8611 + }, + { + "epoch": 0.9, + "learning_rate": 5.664894382917485e-07, + "loss": 1.3498, + "step": 8612 + }, + { + "epoch": 0.9, + "learning_rate": 5.652756128047199e-07, + "loss": 1.3089, + "step": 8613 + }, + { + "epoch": 0.9, + "learning_rate": 5.64063051328344e-07, + "loss": 1.3001, + "step": 8614 + }, + { + "epoch": 0.9, + "learning_rate": 5.628517540250688e-07, + "loss": 1.4114, + "step": 8615 + }, + { + "epoch": 0.9, + "learning_rate": 5.616417210571779e-07, + "loss": 1.2972, + "step": 8616 + }, + { + "epoch": 0.9, + "learning_rate": 5.60432952586788e-07, + "loss": 1.3059, + "step": 8617 + }, + { + "epoch": 0.9, + "learning_rate": 5.592254487758397e-07, + "loss": 1.3642, + "step": 8618 + }, + { + "epoch": 0.9, + "learning_rate": 5.58019209786107e-07, + "loss": 1.3047, + "step": 8619 + }, + { + "epoch": 0.9, + "learning_rate": 5.568142357791995e-07, + "loss": 1.3061, + "step": 8620 + }, + { + "epoch": 0.9, + "learning_rate": 5.556105269165468e-07, + "loss": 1.2628, + "step": 8621 + }, + { + "epoch": 0.9, + "learning_rate": 5.5440808335942e-07, + "loss": 1.3286, + "step": 8622 + }, + { + "epoch": 0.9, + "learning_rate": 5.532069052689115e-07, + "loss": 1.335, + "step": 8623 + }, + { + "epoch": 0.9, + "learning_rate": 5.520069928059502e-07, + "loss": 1.2729, + "step": 8624 + }, + { + "epoch": 0.9, + "learning_rate": 5.508083461312952e-07, + "loss": 1.3037, + "step": 8625 + }, + { + "epoch": 0.9, + "learning_rate": 5.496109654055315e-07, + "loss": 1.3028, + "step": 8626 + }, + { + "epoch": 0.9, + "learning_rate": 5.484148507890775e-07, + "loss": 1.3384, + "step": 8627 + }, + { + "epoch": 0.9, + "learning_rate": 5.472200024421859e-07, + "loss": 1.3019, + "step": 8628 + }, + { + "epoch": 0.9, + "learning_rate": 5.460264205249299e-07, + "loss": 1.3803, + "step": 8629 + }, + { + "epoch": 0.9, + "learning_rate": 5.448341051972217e-07, + "loss": 1.3179, + "step": 8630 + }, + { + "epoch": 0.91, + "learning_rate": 5.436430566188033e-07, + "loss": 1.2734, + "step": 8631 + }, + { + "epoch": 0.91, + "learning_rate": 5.424532749492394e-07, + "loss": 1.3184, + "step": 8632 + }, + { + "epoch": 0.91, + "learning_rate": 5.412647603479348e-07, + "loss": 1.2912, + "step": 8633 + }, + { + "epoch": 0.91, + "learning_rate": 5.400775129741165e-07, + "loss": 1.2942, + "step": 8634 + }, + { + "epoch": 0.91, + "learning_rate": 5.388915329868472e-07, + "loss": 1.3066, + "step": 8635 + }, + { + "epoch": 0.91, + "learning_rate": 5.377068205450175e-07, + "loss": 1.2963, + "step": 8636 + }, + { + "epoch": 0.91, + "learning_rate": 5.365233758073474e-07, + "loss": 1.2821, + "step": 8637 + }, + { + "epoch": 0.91, + "learning_rate": 5.353411989323887e-07, + "loss": 1.2637, + "step": 8638 + }, + { + "epoch": 0.91, + "learning_rate": 5.341602900785236e-07, + "loss": 1.3744, + "step": 8639 + }, + { + "epoch": 0.91, + "learning_rate": 5.329806494039624e-07, + "loss": 1.3841, + "step": 8640 + }, + { + "epoch": 0.91, + "learning_rate": 5.318022770667475e-07, + "loss": 1.3201, + "step": 8641 + }, + { + "epoch": 0.91, + "learning_rate": 5.306251732247492e-07, + "loss": 1.2934, + "step": 8642 + }, + { + "epoch": 0.91, + "learning_rate": 5.294493380356703e-07, + "loss": 1.2184, + "step": 8643 + }, + { + "epoch": 0.91, + "learning_rate": 5.282747716570425e-07, + "loss": 1.3003, + "step": 8644 + }, + { + "epoch": 0.91, + "learning_rate": 5.271014742462266e-07, + "loss": 1.339, + "step": 8645 + }, + { + "epoch": 0.91, + "learning_rate": 5.259294459604148e-07, + "loss": 1.2801, + "step": 8646 + }, + { + "epoch": 0.91, + "learning_rate": 5.247586869566301e-07, + "loss": 1.2954, + "step": 8647 + }, + { + "epoch": 0.91, + "learning_rate": 5.235891973917218e-07, + "loss": 1.2388, + "step": 8648 + }, + { + "epoch": 0.91, + "learning_rate": 5.224209774223721e-07, + "loss": 1.3775, + "step": 8649 + }, + { + "epoch": 0.91, + "learning_rate": 5.212540272050948e-07, + "loss": 1.2997, + "step": 8650 + }, + { + "epoch": 0.91, + "learning_rate": 5.200883468962281e-07, + "loss": 1.4565, + "step": 8651 + }, + { + "epoch": 0.91, + "learning_rate": 5.18923936651945e-07, + "loss": 1.3555, + "step": 8652 + }, + { + "epoch": 0.91, + "learning_rate": 5.17760796628245e-07, + "loss": 1.3218, + "step": 8653 + }, + { + "epoch": 0.91, + "learning_rate": 5.165989269809602e-07, + "loss": 1.268, + "step": 8654 + }, + { + "epoch": 0.91, + "learning_rate": 5.154383278657527e-07, + "loss": 1.3607, + "step": 8655 + }, + { + "epoch": 0.91, + "learning_rate": 5.142789994381092e-07, + "loss": 1.2846, + "step": 8656 + }, + { + "epoch": 0.91, + "learning_rate": 5.131209418533534e-07, + "loss": 1.2988, + "step": 8657 + }, + { + "epoch": 0.91, + "learning_rate": 5.119641552666343e-07, + "loss": 1.3256, + "step": 8658 + }, + { + "epoch": 0.91, + "learning_rate": 5.108086398329304e-07, + "loss": 1.3138, + "step": 8659 + }, + { + "epoch": 0.91, + "learning_rate": 5.096543957070521e-07, + "loss": 1.2735, + "step": 8660 + }, + { + "epoch": 0.91, + "learning_rate": 5.08501423043638e-07, + "loss": 1.2265, + "step": 8661 + }, + { + "epoch": 0.91, + "learning_rate": 5.073497219971568e-07, + "loss": 1.4353, + "step": 8662 + }, + { + "epoch": 0.91, + "learning_rate": 5.061992927219084e-07, + "loss": 1.3996, + "step": 8663 + }, + { + "epoch": 0.91, + "learning_rate": 5.050501353720184e-07, + "loss": 1.4069, + "step": 8664 + }, + { + "epoch": 0.91, + "learning_rate": 5.039022501014445e-07, + "loss": 1.7528, + "step": 8665 + }, + { + "epoch": 0.91, + "learning_rate": 5.027556370639764e-07, + "loss": 1.2997, + "step": 8666 + }, + { + "epoch": 0.91, + "learning_rate": 5.016102964132286e-07, + "loss": 1.2629, + "step": 8667 + }, + { + "epoch": 0.91, + "learning_rate": 5.004662283026485e-07, + "loss": 1.3199, + "step": 8668 + }, + { + "epoch": 0.91, + "learning_rate": 4.993234328855101e-07, + "loss": 1.3457, + "step": 8669 + }, + { + "epoch": 0.91, + "learning_rate": 4.981819103149199e-07, + "loss": 1.2669, + "step": 8670 + }, + { + "epoch": 0.91, + "learning_rate": 4.970416607438133e-07, + "loss": 1.2051, + "step": 8671 + }, + { + "epoch": 0.91, + "learning_rate": 4.959026843249526e-07, + "loss": 1.3008, + "step": 8672 + }, + { + "epoch": 0.91, + "learning_rate": 4.947649812109323e-07, + "loss": 1.2823, + "step": 8673 + }, + { + "epoch": 0.91, + "learning_rate": 4.936285515541761e-07, + "loss": 1.3427, + "step": 8674 + }, + { + "epoch": 0.91, + "learning_rate": 4.924933955069356e-07, + "loss": 1.3132, + "step": 8675 + }, + { + "epoch": 0.91, + "learning_rate": 4.913595132212911e-07, + "loss": 1.2673, + "step": 8676 + }, + { + "epoch": 0.91, + "learning_rate": 4.902269048491581e-07, + "loss": 1.3132, + "step": 8677 + }, + { + "epoch": 0.91, + "learning_rate": 4.890955705422718e-07, + "loss": 1.398, + "step": 8678 + }, + { + "epoch": 0.91, + "learning_rate": 4.879655104522052e-07, + "loss": 1.3282, + "step": 8679 + }, + { + "epoch": 0.91, + "learning_rate": 4.868367247303562e-07, + "loss": 1.316, + "step": 8680 + }, + { + "epoch": 0.91, + "learning_rate": 4.857092135279529e-07, + "loss": 1.3533, + "step": 8681 + }, + { + "epoch": 0.91, + "learning_rate": 4.845829769960542e-07, + "loss": 1.2295, + "step": 8682 + }, + { + "epoch": 0.91, + "learning_rate": 4.83458015285545e-07, + "loss": 1.338, + "step": 8683 + }, + { + "epoch": 0.91, + "learning_rate": 4.823343285471416e-07, + "loss": 1.2782, + "step": 8684 + }, + { + "epoch": 0.91, + "learning_rate": 4.812119169313911e-07, + "loss": 1.3285, + "step": 8685 + }, + { + "epoch": 0.91, + "learning_rate": 4.800907805886656e-07, + "loss": 1.319, + "step": 8686 + }, + { + "epoch": 0.91, + "learning_rate": 4.789709196691705e-07, + "loss": 1.2571, + "step": 8687 + }, + { + "epoch": 0.91, + "learning_rate": 4.778523343229358e-07, + "loss": 1.4777, + "step": 8688 + }, + { + "epoch": 0.91, + "learning_rate": 4.767350246998248e-07, + "loss": 1.2571, + "step": 8689 + }, + { + "epoch": 0.91, + "learning_rate": 4.75618990949529e-07, + "loss": 1.3119, + "step": 8690 + }, + { + "epoch": 0.91, + "learning_rate": 4.745042332215666e-07, + "loss": 1.2801, + "step": 8691 + }, + { + "epoch": 0.91, + "learning_rate": 4.7339075166528694e-07, + "loss": 1.3656, + "step": 8692 + }, + { + "epoch": 0.91, + "learning_rate": 4.722785464298696e-07, + "loss": 1.3113, + "step": 8693 + }, + { + "epoch": 0.91, + "learning_rate": 4.711676176643187e-07, + "loss": 1.2282, + "step": 8694 + }, + { + "epoch": 0.91, + "learning_rate": 4.7005796551747195e-07, + "loss": 1.2845, + "step": 8695 + }, + { + "epoch": 0.91, + "learning_rate": 4.689495901379948e-07, + "loss": 1.3165, + "step": 8696 + }, + { + "epoch": 0.91, + "learning_rate": 4.6784249167437843e-07, + "loss": 1.304, + "step": 8697 + }, + { + "epoch": 0.91, + "learning_rate": 4.6673667027494986e-07, + "loss": 1.4249, + "step": 8698 + }, + { + "epoch": 0.91, + "learning_rate": 4.65632126087856e-07, + "loss": 1.2408, + "step": 8699 + }, + { + "epoch": 0.91, + "learning_rate": 4.6452885926107973e-07, + "loss": 1.3566, + "step": 8700 + }, + { + "epoch": 0.91, + "learning_rate": 4.6342686994243267e-07, + "loss": 1.3258, + "step": 8701 + }, + { + "epoch": 0.91, + "learning_rate": 4.6232615827954795e-07, + "loss": 1.2556, + "step": 8702 + }, + { + "epoch": 0.91, + "learning_rate": 4.6122672441989645e-07, + "loss": 1.3285, + "step": 8703 + }, + { + "epoch": 0.91, + "learning_rate": 4.601285685107737e-07, + "loss": 1.4333, + "step": 8704 + }, + { + "epoch": 0.91, + "learning_rate": 4.590316906993031e-07, + "loss": 1.3094, + "step": 8705 + }, + { + "epoch": 0.91, + "learning_rate": 4.579360911324393e-07, + "loss": 1.3309, + "step": 8706 + }, + { + "epoch": 0.91, + "learning_rate": 4.568417699569627e-07, + "loss": 1.3601, + "step": 8707 + }, + { + "epoch": 0.91, + "learning_rate": 4.557487273194849e-07, + "loss": 1.264, + "step": 8708 + }, + { + "epoch": 0.91, + "learning_rate": 4.546569633664488e-07, + "loss": 1.3169, + "step": 8709 + }, + { + "epoch": 0.91, + "learning_rate": 4.5356647824411737e-07, + "loss": 1.34, + "step": 8710 + }, + { + "epoch": 0.91, + "learning_rate": 4.524772720985904e-07, + "loss": 1.4068, + "step": 8711 + }, + { + "epoch": 0.91, + "learning_rate": 4.5138934507579555e-07, + "loss": 1.2908, + "step": 8712 + }, + { + "epoch": 0.91, + "learning_rate": 4.5030269732148304e-07, + "loss": 1.3185, + "step": 8713 + }, + { + "epoch": 0.91, + "learning_rate": 4.492173289812385e-07, + "loss": 1.4087, + "step": 8714 + }, + { + "epoch": 0.91, + "learning_rate": 4.4813324020047124e-07, + "loss": 1.2899, + "step": 8715 + }, + { + "epoch": 0.91, + "learning_rate": 4.4705043112442284e-07, + "loss": 1.3228, + "step": 8716 + }, + { + "epoch": 0.91, + "learning_rate": 4.4596890189816277e-07, + "loss": 1.3172, + "step": 8717 + }, + { + "epoch": 0.91, + "learning_rate": 4.448886526665852e-07, + "loss": 1.3063, + "step": 8718 + }, + { + "epoch": 0.91, + "learning_rate": 4.438096835744188e-07, + "loss": 1.3737, + "step": 8719 + }, + { + "epoch": 0.91, + "learning_rate": 4.4273199476621677e-07, + "loss": 1.3713, + "step": 8720 + }, + { + "epoch": 0.91, + "learning_rate": 4.416555863863603e-07, + "loss": 1.2843, + "step": 8721 + }, + { + "epoch": 0.91, + "learning_rate": 4.4058045857906075e-07, + "loss": 1.2903, + "step": 8722 + }, + { + "epoch": 0.91, + "learning_rate": 4.395066114883606e-07, + "loss": 1.2618, + "step": 8723 + }, + { + "epoch": 0.91, + "learning_rate": 4.384340452581248e-07, + "loss": 1.278, + "step": 8724 + }, + { + "epoch": 0.91, + "learning_rate": 4.3736276003205067e-07, + "loss": 1.3721, + "step": 8725 + }, + { + "epoch": 0.92, + "learning_rate": 4.3629275595366226e-07, + "loss": 1.2787, + "step": 8726 + }, + { + "epoch": 0.92, + "learning_rate": 4.3522403316631266e-07, + "loss": 1.3116, + "step": 8727 + }, + { + "epoch": 0.92, + "learning_rate": 4.34156591813184e-07, + "loss": 1.2237, + "step": 8728 + }, + { + "epoch": 0.92, + "learning_rate": 4.330904320372853e-07, + "loss": 1.3205, + "step": 8729 + }, + { + "epoch": 0.92, + "learning_rate": 4.3202555398145554e-07, + "loss": 1.2894, + "step": 8730 + }, + { + "epoch": 0.92, + "learning_rate": 4.309619577883606e-07, + "loss": 1.2975, + "step": 8731 + }, + { + "epoch": 0.92, + "learning_rate": 4.298996436004943e-07, + "loss": 1.4334, + "step": 8732 + }, + { + "epoch": 0.92, + "learning_rate": 4.288386115601806e-07, + "loss": 1.3884, + "step": 8733 + }, + { + "epoch": 0.92, + "learning_rate": 4.277788618095691e-07, + "loss": 1.3426, + "step": 8734 + }, + { + "epoch": 0.92, + "learning_rate": 4.267203944906395e-07, + "loss": 1.3099, + "step": 8735 + }, + { + "epoch": 0.92, + "learning_rate": 4.256632097452018e-07, + "loss": 1.3105, + "step": 8736 + }, + { + "epoch": 0.92, + "learning_rate": 4.2460730771488714e-07, + "loss": 1.2708, + "step": 8737 + }, + { + "epoch": 0.92, + "learning_rate": 4.2355268854116227e-07, + "loss": 1.262, + "step": 8738 + }, + { + "epoch": 0.92, + "learning_rate": 4.224993523653187e-07, + "loss": 1.3263, + "step": 8739 + }, + { + "epoch": 0.92, + "learning_rate": 4.214472993284746e-07, + "loss": 1.3225, + "step": 8740 + }, + { + "epoch": 0.92, + "learning_rate": 4.2039652957158063e-07, + "loss": 1.3678, + "step": 8741 + }, + { + "epoch": 0.92, + "learning_rate": 4.1934704323541187e-07, + "loss": 1.3537, + "step": 8742 + }, + { + "epoch": 0.92, + "learning_rate": 4.182988404605726e-07, + "loss": 1.329, + "step": 8743 + }, + { + "epoch": 0.92, + "learning_rate": 4.172519213874948e-07, + "loss": 1.332, + "step": 8744 + }, + { + "epoch": 0.92, + "learning_rate": 4.1620628615643753e-07, + "loss": 1.3303, + "step": 8745 + }, + { + "epoch": 0.92, + "learning_rate": 4.151619349074909e-07, + "loss": 1.359, + "step": 8746 + }, + { + "epoch": 0.92, + "learning_rate": 4.1411886778057185e-07, + "loss": 1.3323, + "step": 8747 + }, + { + "epoch": 0.92, + "learning_rate": 4.1307708491542196e-07, + "loss": 1.2995, + "step": 8748 + }, + { + "epoch": 0.92, + "learning_rate": 4.12036586451614e-07, + "loss": 1.3312, + "step": 8749 + }, + { + "epoch": 0.92, + "learning_rate": 4.10997372528551e-07, + "loss": 1.39, + "step": 8750 + }, + { + "epoch": 0.92, + "learning_rate": 4.0995944328545703e-07, + "loss": 1.31, + "step": 8751 + }, + { + "epoch": 0.92, + "learning_rate": 4.0892279886138976e-07, + "loss": 1.2908, + "step": 8752 + }, + { + "epoch": 0.92, + "learning_rate": 4.0788743939523257e-07, + "loss": 1.2324, + "step": 8753 + }, + { + "epoch": 0.92, + "learning_rate": 4.068533650256967e-07, + "loss": 1.3102, + "step": 8754 + }, + { + "epoch": 0.92, + "learning_rate": 4.058205758913236e-07, + "loss": 1.2724, + "step": 8755 + }, + { + "epoch": 0.92, + "learning_rate": 4.0478907213047816e-07, + "loss": 1.2489, + "step": 8756 + }, + { + "epoch": 0.92, + "eval_loss": 1.394278645515442, + "eval_runtime": 77.5397, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 8756 + }, + { + "epoch": 0.92, + "learning_rate": 4.037588538813553e-07, + "loss": 1.2151, + "step": 8757 + }, + { + "epoch": 0.92, + "learning_rate": 4.0272992128198016e-07, + "loss": 1.249, + "step": 8758 + }, + { + "epoch": 0.92, + "learning_rate": 4.0170227447019926e-07, + "loss": 1.2955, + "step": 8759 + }, + { + "epoch": 0.92, + "learning_rate": 4.006759135836957e-07, + "loss": 1.2963, + "step": 8760 + }, + { + "epoch": 0.92, + "learning_rate": 3.996508387599718e-07, + "loss": 1.2963, + "step": 8761 + }, + { + "epoch": 0.92, + "learning_rate": 3.9862705013636316e-07, + "loss": 1.3615, + "step": 8762 + }, + { + "epoch": 0.92, + "learning_rate": 3.976045478500301e-07, + "loss": 1.2331, + "step": 8763 + }, + { + "epoch": 0.92, + "learning_rate": 3.9658333203796194e-07, + "loss": 1.3028, + "step": 8764 + }, + { + "epoch": 0.92, + "learning_rate": 3.955634028369759e-07, + "loss": 1.3062, + "step": 8765 + }, + { + "epoch": 0.92, + "learning_rate": 3.9454476038371603e-07, + "loss": 1.321, + "step": 8766 + }, + { + "epoch": 0.92, + "learning_rate": 3.935274048146531e-07, + "loss": 1.3591, + "step": 8767 + }, + { + "epoch": 0.92, + "learning_rate": 3.925113362660882e-07, + "loss": 1.4038, + "step": 8768 + }, + { + "epoch": 0.92, + "learning_rate": 3.9149655487414893e-07, + "loss": 1.3261, + "step": 8769 + }, + { + "epoch": 0.92, + "learning_rate": 3.904830607747867e-07, + "loss": 1.2751, + "step": 8770 + }, + { + "epoch": 0.92, + "learning_rate": 3.8947085410378836e-07, + "loss": 1.2982, + "step": 8771 + }, + { + "epoch": 0.92, + "learning_rate": 3.8845993499675883e-07, + "loss": 1.2701, + "step": 8772 + }, + { + "epoch": 0.92, + "learning_rate": 3.874503035891375e-07, + "loss": 1.354, + "step": 8773 + }, + { + "epoch": 0.92, + "learning_rate": 3.864419600161906e-07, + "loss": 1.2855, + "step": 8774 + }, + { + "epoch": 0.92, + "learning_rate": 3.854349044130068e-07, + "loss": 1.3154, + "step": 8775 + }, + { + "epoch": 0.92, + "learning_rate": 3.844291369145081e-07, + "loss": 1.2889, + "step": 8776 + }, + { + "epoch": 0.92, + "learning_rate": 3.8342465765544233e-07, + "loss": 1.3718, + "step": 8777 + }, + { + "epoch": 0.92, + "learning_rate": 3.8242146677038184e-07, + "loss": 1.2881, + "step": 8778 + }, + { + "epoch": 0.92, + "learning_rate": 3.8141956439372907e-07, + "loss": 1.2734, + "step": 8779 + }, + { + "epoch": 0.92, + "learning_rate": 3.8041895065971226e-07, + "loss": 1.3059, + "step": 8780 + }, + { + "epoch": 0.92, + "learning_rate": 3.7941962570238964e-07, + "loss": 1.278, + "step": 8781 + }, + { + "epoch": 0.92, + "learning_rate": 3.7842158965564534e-07, + "loss": 1.3448, + "step": 8782 + }, + { + "epoch": 0.92, + "learning_rate": 3.774248426531879e-07, + "loss": 1.3345, + "step": 8783 + }, + { + "epoch": 0.92, + "learning_rate": 3.764293848285583e-07, + "loss": 1.3273, + "step": 8784 + }, + { + "epoch": 0.92, + "learning_rate": 3.7543521631512203e-07, + "loss": 1.2983, + "step": 8785 + }, + { + "epoch": 0.92, + "learning_rate": 3.744423372460704e-07, + "loss": 1.2833, + "step": 8786 + }, + { + "epoch": 0.92, + "learning_rate": 3.734507477544258e-07, + "loss": 1.3318, + "step": 8787 + }, + { + "epoch": 0.92, + "learning_rate": 3.7246044797303537e-07, + "loss": 1.2926, + "step": 8788 + }, + { + "epoch": 0.92, + "learning_rate": 3.7147143803457187e-07, + "loss": 1.3456, + "step": 8789 + }, + { + "epoch": 0.92, + "learning_rate": 3.7048371807153924e-07, + "loss": 1.3395, + "step": 8790 + }, + { + "epoch": 0.92, + "learning_rate": 3.694972882162662e-07, + "loss": 1.2003, + "step": 8791 + }, + { + "epoch": 0.92, + "learning_rate": 3.68512148600908e-07, + "loss": 1.4062, + "step": 8792 + }, + { + "epoch": 0.92, + "learning_rate": 3.6752829935745027e-07, + "loss": 1.312, + "step": 8793 + }, + { + "epoch": 0.92, + "learning_rate": 3.6654574061770086e-07, + "loss": 1.4852, + "step": 8794 + }, + { + "epoch": 0.92, + "learning_rate": 3.6556447251329897e-07, + "loss": 1.2905, + "step": 8795 + }, + { + "epoch": 0.92, + "learning_rate": 3.6458449517570936e-07, + "loss": 1.256, + "step": 8796 + }, + { + "epoch": 0.92, + "learning_rate": 3.6360580873622267e-07, + "loss": 1.342, + "step": 8797 + }, + { + "epoch": 0.92, + "learning_rate": 3.626284133259594e-07, + "loss": 1.3384, + "step": 8798 + }, + { + "epoch": 0.92, + "learning_rate": 3.616523090758639e-07, + "loss": 1.3261, + "step": 8799 + }, + { + "epoch": 0.92, + "learning_rate": 3.606774961167092e-07, + "loss": 1.301, + "step": 8800 + }, + { + "epoch": 0.92, + "learning_rate": 3.5970397457909646e-07, + "loss": 1.3225, + "step": 8801 + }, + { + "epoch": 0.92, + "learning_rate": 3.587317445934513e-07, + "loss": 1.2937, + "step": 8802 + }, + { + "epoch": 0.92, + "learning_rate": 3.577608062900273e-07, + "loss": 1.3054, + "step": 8803 + }, + { + "epoch": 0.92, + "learning_rate": 3.567911597989082e-07, + "loss": 1.2634, + "step": 8804 + }, + { + "epoch": 0.92, + "learning_rate": 3.558228052499968e-07, + "loss": 1.3234, + "step": 8805 + }, + { + "epoch": 0.92, + "learning_rate": 3.548557427730326e-07, + "loss": 1.3479, + "step": 8806 + }, + { + "epoch": 0.92, + "learning_rate": 3.5388997249757305e-07, + "loss": 1.3088, + "step": 8807 + }, + { + "epoch": 0.92, + "learning_rate": 3.5292549455300916e-07, + "loss": 1.2973, + "step": 8808 + }, + { + "epoch": 0.92, + "learning_rate": 3.5196230906855646e-07, + "loss": 1.3303, + "step": 8809 + }, + { + "epoch": 0.92, + "learning_rate": 3.5100041617325496e-07, + "loss": 1.3715, + "step": 8810 + }, + { + "epoch": 0.92, + "learning_rate": 3.5003981599597394e-07, + "loss": 1.3085, + "step": 8811 + }, + { + "epoch": 0.92, + "learning_rate": 3.4908050866541256e-07, + "loss": 1.328, + "step": 8812 + }, + { + "epoch": 0.92, + "learning_rate": 3.4812249431008803e-07, + "loss": 1.3184, + "step": 8813 + }, + { + "epoch": 0.92, + "learning_rate": 3.471657730583533e-07, + "loss": 1.2652, + "step": 8814 + }, + { + "epoch": 0.92, + "learning_rate": 3.4621034503838357e-07, + "loss": 1.4021, + "step": 8815 + }, + { + "epoch": 0.92, + "learning_rate": 3.452562103781809e-07, + "loss": 1.2653, + "step": 8816 + }, + { + "epoch": 0.92, + "learning_rate": 3.443033692055764e-07, + "loss": 1.251, + "step": 8817 + }, + { + "epoch": 0.92, + "learning_rate": 3.433518216482246e-07, + "loss": 1.4015, + "step": 8818 + }, + { + "epoch": 0.92, + "learning_rate": 3.42401567833609e-07, + "loss": 1.4886, + "step": 8819 + }, + { + "epoch": 0.92, + "learning_rate": 3.4145260788904013e-07, + "loss": 1.266, + "step": 8820 + }, + { + "epoch": 0.93, + "learning_rate": 3.4050494194165287e-07, + "loss": 1.3155, + "step": 8821 + }, + { + "epoch": 0.93, + "learning_rate": 3.395585701184101e-07, + "loss": 1.3498, + "step": 8822 + }, + { + "epoch": 0.93, + "learning_rate": 3.3861349254610374e-07, + "loss": 1.3149, + "step": 8823 + }, + { + "epoch": 0.93, + "learning_rate": 3.37669709351347e-07, + "loss": 1.2899, + "step": 8824 + }, + { + "epoch": 0.93, + "learning_rate": 3.3672722066058427e-07, + "loss": 1.294, + "step": 8825 + }, + { + "epoch": 0.93, + "learning_rate": 3.357860266000834e-07, + "loss": 1.5116, + "step": 8826 + }, + { + "epoch": 0.93, + "learning_rate": 3.348461272959402e-07, + "loss": 1.2454, + "step": 8827 + }, + { + "epoch": 0.93, + "learning_rate": 3.3390752287407957e-07, + "loss": 1.2626, + "step": 8828 + }, + { + "epoch": 0.93, + "learning_rate": 3.329702134602475e-07, + "loss": 1.3228, + "step": 8829 + }, + { + "epoch": 0.93, + "learning_rate": 3.320341991800213e-07, + "loss": 1.2949, + "step": 8830 + }, + { + "epoch": 0.93, + "learning_rate": 3.31099480158803e-07, + "loss": 1.2893, + "step": 8831 + }, + { + "epoch": 0.93, + "learning_rate": 3.3016605652181786e-07, + "loss": 1.2766, + "step": 8832 + }, + { + "epoch": 0.93, + "learning_rate": 3.292339283941237e-07, + "loss": 1.3587, + "step": 8833 + }, + { + "epoch": 0.93, + "learning_rate": 3.2830309590060174e-07, + "loss": 1.2473, + "step": 8834 + }, + { + "epoch": 0.93, + "learning_rate": 3.273735591659577e-07, + "loss": 1.2651, + "step": 8835 + }, + { + "epoch": 0.93, + "learning_rate": 3.264453183147276e-07, + "loss": 1.3492, + "step": 8836 + }, + { + "epoch": 0.93, + "learning_rate": 3.255183734712697e-07, + "loss": 1.3565, + "step": 8837 + }, + { + "epoch": 0.93, + "learning_rate": 3.2459272475977135e-07, + "loss": 1.3171, + "step": 8838 + }, + { + "epoch": 0.93, + "learning_rate": 3.2366837230424884e-07, + "loss": 1.2942, + "step": 8839 + }, + { + "epoch": 0.93, + "learning_rate": 3.2274531622853765e-07, + "loss": 1.2604, + "step": 8840 + }, + { + "epoch": 0.93, + "learning_rate": 3.2182355665630436e-07, + "loss": 1.2999, + "step": 8841 + }, + { + "epoch": 0.93, + "learning_rate": 3.2090309371104357e-07, + "loss": 1.3291, + "step": 8842 + }, + { + "epoch": 0.93, + "learning_rate": 3.19983927516071e-07, + "loss": 1.3095, + "step": 8843 + }, + { + "epoch": 0.93, + "learning_rate": 3.190660581945326e-07, + "loss": 1.2738, + "step": 8844 + }, + { + "epoch": 0.93, + "learning_rate": 3.1814948586939786e-07, + "loss": 1.2573, + "step": 8845 + }, + { + "epoch": 0.93, + "learning_rate": 3.1723421066346515e-07, + "loss": 1.3155, + "step": 8846 + }, + { + "epoch": 0.93, + "learning_rate": 3.1632023269935864e-07, + "loss": 1.2427, + "step": 8847 + }, + { + "epoch": 0.93, + "learning_rate": 3.154075520995259e-07, + "loss": 1.2719, + "step": 8848 + }, + { + "epoch": 0.93, + "learning_rate": 3.144961689862436e-07, + "loss": 1.2822, + "step": 8849 + }, + { + "epoch": 0.93, + "learning_rate": 3.13586083481614e-07, + "loss": 1.2655, + "step": 8850 + }, + { + "epoch": 0.93, + "learning_rate": 3.126772957075652e-07, + "loss": 1.2997, + "step": 8851 + }, + { + "epoch": 0.93, + "learning_rate": 3.1176980578585094e-07, + "loss": 1.1037, + "step": 8852 + }, + { + "epoch": 0.93, + "learning_rate": 3.1086361383805164e-07, + "loss": 1.3005, + "step": 8853 + }, + { + "epoch": 0.93, + "learning_rate": 3.0995871998557357e-07, + "loss": 1.2704, + "step": 8854 + }, + { + "epoch": 0.93, + "learning_rate": 3.090551243496498e-07, + "loss": 1.313, + "step": 8855 + }, + { + "epoch": 0.93, + "learning_rate": 3.081528270513379e-07, + "loss": 1.2815, + "step": 8856 + }, + { + "epoch": 0.93, + "learning_rate": 3.072518282115233e-07, + "loss": 1.2705, + "step": 8857 + }, + { + "epoch": 0.93, + "learning_rate": 3.063521279509174e-07, + "loss": 1.4031, + "step": 8858 + }, + { + "epoch": 0.93, + "learning_rate": 3.054537263900559e-07, + "loss": 1.2842, + "step": 8859 + }, + { + "epoch": 0.93, + "learning_rate": 3.0455662364930137e-07, + "loss": 1.3632, + "step": 8860 + }, + { + "epoch": 0.93, + "learning_rate": 3.0366081984884333e-07, + "loss": 1.3879, + "step": 8861 + }, + { + "epoch": 0.93, + "learning_rate": 3.027663151086957e-07, + "loss": 1.3035, + "step": 8862 + }, + { + "epoch": 0.93, + "learning_rate": 3.018731095487004e-07, + "loss": 1.3117, + "step": 8863 + }, + { + "epoch": 0.93, + "learning_rate": 3.0098120328852177e-07, + "loss": 1.3383, + "step": 8864 + }, + { + "epoch": 0.93, + "learning_rate": 3.0009059644765413e-07, + "loss": 1.2848, + "step": 8865 + }, + { + "epoch": 0.93, + "learning_rate": 2.9920128914541655e-07, + "loss": 1.3949, + "step": 8866 + }, + { + "epoch": 0.93, + "learning_rate": 2.983132815009504e-07, + "loss": 1.3241, + "step": 8867 + }, + { + "epoch": 0.93, + "learning_rate": 2.9742657363322933e-07, + "loss": 1.2943, + "step": 8868 + }, + { + "epoch": 0.93, + "learning_rate": 2.965411656610473e-07, + "loss": 1.3146, + "step": 8869 + }, + { + "epoch": 0.93, + "learning_rate": 2.9565705770302597e-07, + "loss": 1.2657, + "step": 8870 + }, + { + "epoch": 0.93, + "learning_rate": 2.947742498776163e-07, + "loss": 1.3064, + "step": 8871 + }, + { + "epoch": 0.93, + "learning_rate": 2.9389274230308685e-07, + "loss": 1.2875, + "step": 8872 + }, + { + "epoch": 0.93, + "learning_rate": 2.930125350975399e-07, + "loss": 1.277, + "step": 8873 + }, + { + "epoch": 0.93, + "learning_rate": 2.9213362837890223e-07, + "loss": 1.2818, + "step": 8874 + }, + { + "epoch": 0.93, + "learning_rate": 2.912560222649208e-07, + "loss": 1.32, + "step": 8875 + }, + { + "epoch": 0.93, + "learning_rate": 2.903797168731748e-07, + "loss": 1.3056, + "step": 8876 + }, + { + "epoch": 0.93, + "learning_rate": 2.8950471232106703e-07, + "loss": 1.4156, + "step": 8877 + }, + { + "epoch": 0.93, + "learning_rate": 2.886310087258237e-07, + "loss": 1.2338, + "step": 8878 + }, + { + "epoch": 0.93, + "learning_rate": 2.87758606204499e-07, + "loss": 1.3026, + "step": 8879 + }, + { + "epoch": 0.93, + "learning_rate": 2.86887504873975e-07, + "loss": 1.2709, + "step": 8880 + }, + { + "epoch": 0.93, + "learning_rate": 2.860177048509538e-07, + "loss": 1.2544, + "step": 8881 + }, + { + "epoch": 0.93, + "learning_rate": 2.8514920625196897e-07, + "loss": 1.2919, + "step": 8882 + }, + { + "epoch": 0.93, + "learning_rate": 2.842820091933729e-07, + "loss": 1.2656, + "step": 8883 + }, + { + "epoch": 0.93, + "learning_rate": 2.834161137913516e-07, + "loss": 1.355, + "step": 8884 + }, + { + "epoch": 0.93, + "learning_rate": 2.825515201619122e-07, + "loss": 1.3146, + "step": 8885 + }, + { + "epoch": 0.93, + "learning_rate": 2.816882284208866e-07, + "loss": 1.3221, + "step": 8886 + }, + { + "epoch": 0.93, + "learning_rate": 2.8082623868393444e-07, + "loss": 1.3151, + "step": 8887 + }, + { + "epoch": 0.93, + "learning_rate": 2.799655510665411e-07, + "loss": 1.2493, + "step": 8888 + }, + { + "epoch": 0.93, + "learning_rate": 2.791061656840144e-07, + "loss": 1.2192, + "step": 8889 + }, + { + "epoch": 0.93, + "learning_rate": 2.782480826514922e-07, + "loss": 1.3013, + "step": 8890 + }, + { + "epoch": 0.93, + "learning_rate": 2.773913020839336e-07, + "loss": 1.2984, + "step": 8891 + }, + { + "epoch": 0.93, + "learning_rate": 2.765358240961269e-07, + "loss": 1.1799, + "step": 8892 + }, + { + "epoch": 0.93, + "learning_rate": 2.7568164880268367e-07, + "loss": 1.5423, + "step": 8893 + }, + { + "epoch": 0.93, + "learning_rate": 2.7482877631804127e-07, + "loss": 1.8565, + "step": 8894 + }, + { + "epoch": 0.93, + "learning_rate": 2.7397720675646167e-07, + "loss": 1.3162, + "step": 8895 + }, + { + "epoch": 0.93, + "learning_rate": 2.731269402320358e-07, + "loss": 1.326, + "step": 8896 + }, + { + "epoch": 0.93, + "learning_rate": 2.7227797685867474e-07, + "loss": 1.3786, + "step": 8897 + }, + { + "epoch": 0.93, + "learning_rate": 2.7143031675011975e-07, + "loss": 1.2676, + "step": 8898 + }, + { + "epoch": 0.93, + "learning_rate": 2.705839600199345e-07, + "loss": 1.2678, + "step": 8899 + }, + { + "epoch": 0.93, + "learning_rate": 2.6973890678150927e-07, + "loss": 1.2637, + "step": 8900 + }, + { + "epoch": 0.93, + "learning_rate": 2.6889515714806023e-07, + "loss": 1.3228, + "step": 8901 + }, + { + "epoch": 0.93, + "learning_rate": 2.680527112326259e-07, + "loss": 1.2449, + "step": 8902 + }, + { + "epoch": 0.93, + "learning_rate": 2.672115691480748e-07, + "loss": 1.2667, + "step": 8903 + }, + { + "epoch": 0.93, + "learning_rate": 2.66371731007099e-07, + "loss": 1.3299, + "step": 8904 + }, + { + "epoch": 0.93, + "learning_rate": 2.655331969222119e-07, + "loss": 1.2038, + "step": 8905 + }, + { + "epoch": 0.93, + "learning_rate": 2.6469596700575804e-07, + "loss": 1.3443, + "step": 8906 + }, + { + "epoch": 0.93, + "learning_rate": 2.638600413699044e-07, + "loss": 1.3514, + "step": 8907 + }, + { + "epoch": 0.93, + "learning_rate": 2.6302542012664244e-07, + "loss": 1.2543, + "step": 8908 + }, + { + "epoch": 0.93, + "learning_rate": 2.6219210338779164e-07, + "loss": 1.3636, + "step": 8909 + }, + { + "epoch": 0.93, + "learning_rate": 2.6136009126499385e-07, + "loss": 1.3216, + "step": 8910 + }, + { + "epoch": 0.93, + "learning_rate": 2.605293838697165e-07, + "loss": 1.3267, + "step": 8911 + }, + { + "epoch": 0.93, + "learning_rate": 2.5969998131325614e-07, + "loss": 1.3084, + "step": 8912 + }, + { + "epoch": 0.93, + "learning_rate": 2.588718837067272e-07, + "loss": 1.3054, + "step": 8913 + }, + { + "epoch": 0.93, + "learning_rate": 2.5804509116107654e-07, + "loss": 1.3509, + "step": 8914 + }, + { + "epoch": 0.93, + "learning_rate": 2.5721960378707335e-07, + "loss": 1.3272, + "step": 8915 + }, + { + "epoch": 0.93, + "learning_rate": 2.563954216953091e-07, + "loss": 1.2732, + "step": 8916 + }, + { + "epoch": 0.94, + "learning_rate": 2.555725449962054e-07, + "loss": 1.3077, + "step": 8917 + }, + { + "epoch": 0.94, + "learning_rate": 2.5475097380000537e-07, + "loss": 1.3496, + "step": 8918 + }, + { + "epoch": 0.94, + "learning_rate": 2.5393070821677857e-07, + "loss": 1.2139, + "step": 8919 + }, + { + "epoch": 0.94, + "learning_rate": 2.531117483564205e-07, + "loss": 1.3671, + "step": 8920 + }, + { + "epoch": 0.94, + "learning_rate": 2.522940943286489e-07, + "loss": 1.2771, + "step": 8921 + }, + { + "epoch": 0.94, + "learning_rate": 2.5147774624300957e-07, + "loss": 1.2332, + "step": 8922 + }, + { + "epoch": 0.94, + "learning_rate": 2.5066270420887384e-07, + "loss": 1.3298, + "step": 8923 + }, + { + "epoch": 0.94, + "learning_rate": 2.4984896833543213e-07, + "loss": 1.2944, + "step": 8924 + }, + { + "epoch": 0.94, + "learning_rate": 2.490365387317073e-07, + "loss": 1.2849, + "step": 8925 + }, + { + "epoch": 0.94, + "learning_rate": 2.4822541550654554e-07, + "loss": 1.3907, + "step": 8926 + }, + { + "epoch": 0.94, + "learning_rate": 2.474155987686122e-07, + "loss": 1.3577, + "step": 8927 + }, + { + "epoch": 0.94, + "learning_rate": 2.4660708862640493e-07, + "loss": 1.3171, + "step": 8928 + }, + { + "epoch": 0.94, + "learning_rate": 2.457998851882415e-07, + "loss": 1.2897, + "step": 8929 + }, + { + "epoch": 0.94, + "learning_rate": 2.4499398856226766e-07, + "loss": 1.3395, + "step": 8930 + }, + { + "epoch": 0.94, + "learning_rate": 2.4418939885645365e-07, + "loss": 1.2704, + "step": 8931 + }, + { + "epoch": 0.94, + "learning_rate": 2.433861161785922e-07, + "loss": 1.3011, + "step": 8932 + }, + { + "epoch": 0.94, + "learning_rate": 2.4258414063630277e-07, + "loss": 1.2806, + "step": 8933 + }, + { + "epoch": 0.94, + "learning_rate": 2.4178347233703047e-07, + "loss": 1.3106, + "step": 8934 + }, + { + "epoch": 0.94, + "learning_rate": 2.409841113880429e-07, + "loss": 1.335, + "step": 8935 + }, + { + "epoch": 0.94, + "learning_rate": 2.4018605789643543e-07, + "loss": 1.3727, + "step": 8936 + }, + { + "epoch": 0.94, + "learning_rate": 2.393893119691249e-07, + "loss": 1.2649, + "step": 8937 + }, + { + "epoch": 0.94, + "learning_rate": 2.3859387371285683e-07, + "loss": 1.2947, + "step": 8938 + }, + { + "epoch": 0.94, + "learning_rate": 2.377997432341983e-07, + "loss": 1.2916, + "step": 8939 + }, + { + "epoch": 0.94, + "learning_rate": 2.37006920639542e-07, + "loss": 1.2491, + "step": 8940 + }, + { + "epoch": 0.94, + "learning_rate": 2.3621540603510628e-07, + "loss": 1.3454, + "step": 8941 + }, + { + "epoch": 0.94, + "learning_rate": 2.354251995269341e-07, + "loss": 1.4965, + "step": 8942 + }, + { + "epoch": 0.94, + "learning_rate": 2.3463630122089298e-07, + "loss": 1.2596, + "step": 8943 + }, + { + "epoch": 0.94, + "learning_rate": 2.3384871122267395e-07, + "loss": 1.3812, + "step": 8944 + }, + { + "epoch": 0.94, + "learning_rate": 2.3306242963779479e-07, + "loss": 1.2275, + "step": 8945 + }, + { + "epoch": 0.94, + "learning_rate": 2.3227745657159683e-07, + "loss": 1.3221, + "step": 8946 + }, + { + "epoch": 0.94, + "learning_rate": 2.3149379212924593e-07, + "loss": 1.3883, + "step": 8947 + }, + { + "epoch": 0.94, + "learning_rate": 2.3071143641573367e-07, + "loss": 1.3098, + "step": 8948 + }, + { + "epoch": 0.94, + "learning_rate": 2.29930389535874e-07, + "loss": 1.2698, + "step": 8949 + }, + { + "epoch": 0.94, + "learning_rate": 2.2915065159430983e-07, + "loss": 1.3016, + "step": 8950 + }, + { + "epoch": 0.94, + "learning_rate": 2.2837222269550319e-07, + "loss": 1.3664, + "step": 8951 + }, + { + "epoch": 0.94, + "learning_rate": 2.275951029437451e-07, + "loss": 1.2762, + "step": 8952 + }, + { + "epoch": 0.94, + "learning_rate": 2.2681929244315116e-07, + "loss": 1.2412, + "step": 8953 + }, + { + "epoch": 0.94, + "learning_rate": 2.26044791297656e-07, + "loss": 1.328, + "step": 8954 + }, + { + "epoch": 0.94, + "learning_rate": 2.2527159961102774e-07, + "loss": 1.2687, + "step": 8955 + }, + { + "epoch": 0.94, + "eval_loss": 1.3942770957946777, + "eval_runtime": 77.5061, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 8955 + }, + { + "epoch": 0.94, + "learning_rate": 2.2449971748684906e-07, + "loss": 1.3033, + "step": 8956 + }, + { + "epoch": 0.94, + "learning_rate": 2.2372914502853614e-07, + "loss": 1.3869, + "step": 8957 + }, + { + "epoch": 0.94, + "learning_rate": 2.229598823393242e-07, + "loss": 1.3141, + "step": 8958 + }, + { + "epoch": 0.94, + "learning_rate": 2.2219192952227518e-07, + "loss": 1.2904, + "step": 8959 + }, + { + "epoch": 0.94, + "learning_rate": 2.2142528668027462e-07, + "loss": 1.2934, + "step": 8960 + }, + { + "epoch": 0.94, + "learning_rate": 2.206599539160348e-07, + "loss": 1.3253, + "step": 8961 + }, + { + "epoch": 0.94, + "learning_rate": 2.1989593133208698e-07, + "loss": 1.3477, + "step": 8962 + }, + { + "epoch": 0.94, + "learning_rate": 2.1913321903079487e-07, + "loss": 1.2893, + "step": 8963 + }, + { + "epoch": 0.94, + "learning_rate": 2.1837181711433898e-07, + "loss": 1.4303, + "step": 8964 + }, + { + "epoch": 0.94, + "learning_rate": 2.1761172568472877e-07, + "loss": 1.3035, + "step": 8965 + }, + { + "epoch": 0.94, + "learning_rate": 2.1685294484379725e-07, + "loss": 1.3069, + "step": 8966 + }, + { + "epoch": 0.94, + "learning_rate": 2.1609547469320091e-07, + "loss": 1.4877, + "step": 8967 + }, + { + "epoch": 0.94, + "learning_rate": 2.1533931533442187e-07, + "loss": 1.2743, + "step": 8968 + }, + { + "epoch": 0.94, + "learning_rate": 2.145844668687669e-07, + "loss": 1.3075, + "step": 8969 + }, + { + "epoch": 0.94, + "learning_rate": 2.1383092939736395e-07, + "loss": 1.2932, + "step": 8970 + }, + { + "epoch": 0.94, + "learning_rate": 2.1307870302116895e-07, + "loss": 1.2865, + "step": 8971 + }, + { + "epoch": 0.94, + "learning_rate": 2.123277878409624e-07, + "loss": 1.249, + "step": 8972 + }, + { + "epoch": 0.94, + "learning_rate": 2.1157818395734498e-07, + "loss": 1.3415, + "step": 8973 + }, + { + "epoch": 0.94, + "learning_rate": 2.1082989147074628e-07, + "loss": 1.2713, + "step": 8974 + }, + { + "epoch": 0.94, + "learning_rate": 2.1008291048141616e-07, + "loss": 1.4529, + "step": 8975 + }, + { + "epoch": 0.94, + "learning_rate": 2.0933724108943232e-07, + "loss": 1.2258, + "step": 8976 + }, + { + "epoch": 0.94, + "learning_rate": 2.0859288339469707e-07, + "loss": 1.3095, + "step": 8977 + }, + { + "epoch": 0.94, + "learning_rate": 2.0784983749693177e-07, + "loss": 1.3554, + "step": 8978 + }, + { + "epoch": 0.94, + "learning_rate": 2.071081034956879e-07, + "loss": 1.4429, + "step": 8979 + }, + { + "epoch": 0.94, + "learning_rate": 2.0636768149033815e-07, + "loss": 1.3282, + "step": 8980 + }, + { + "epoch": 0.94, + "learning_rate": 2.0562857158007876e-07, + "loss": 1.316, + "step": 8981 + }, + { + "epoch": 0.94, + "learning_rate": 2.0489077386393385e-07, + "loss": 1.3811, + "step": 8982 + }, + { + "epoch": 0.94, + "learning_rate": 2.041542884407477e-07, + "loss": 1.2953, + "step": 8983 + }, + { + "epoch": 0.94, + "learning_rate": 2.0341911540919023e-07, + "loss": 1.2966, + "step": 8984 + }, + { + "epoch": 0.94, + "learning_rate": 2.0268525486775713e-07, + "loss": 1.2787, + "step": 8985 + }, + { + "epoch": 0.94, + "learning_rate": 2.0195270691476533e-07, + "loss": 1.3543, + "step": 8986 + }, + { + "epoch": 0.94, + "learning_rate": 2.0122147164835736e-07, + "loss": 1.4828, + "step": 8987 + }, + { + "epoch": 0.94, + "learning_rate": 2.0049154916650272e-07, + "loss": 1.3493, + "step": 8988 + }, + { + "epoch": 0.94, + "learning_rate": 1.9976293956698867e-07, + "loss": 1.3098, + "step": 8989 + }, + { + "epoch": 0.94, + "learning_rate": 1.9903564294743272e-07, + "loss": 1.304, + "step": 8990 + }, + { + "epoch": 0.94, + "learning_rate": 1.9830965940527246e-07, + "loss": 1.4488, + "step": 8991 + }, + { + "epoch": 0.94, + "learning_rate": 1.9758498903777123e-07, + "loss": 1.2659, + "step": 8992 + }, + { + "epoch": 0.94, + "learning_rate": 1.9686163194201802e-07, + "loss": 1.2518, + "step": 8993 + }, + { + "epoch": 0.94, + "learning_rate": 1.9613958821492195e-07, + "loss": 1.284, + "step": 8994 + }, + { + "epoch": 0.94, + "learning_rate": 1.9541885795321792e-07, + "loss": 1.3149, + "step": 8995 + }, + { + "epoch": 0.94, + "learning_rate": 1.9469944125346752e-07, + "loss": 1.3436, + "step": 8996 + }, + { + "epoch": 0.94, + "learning_rate": 1.9398133821205256e-07, + "loss": 1.5277, + "step": 8997 + }, + { + "epoch": 0.94, + "learning_rate": 1.9326454892518053e-07, + "loss": 1.3394, + "step": 8998 + }, + { + "epoch": 0.94, + "learning_rate": 1.9254907348888464e-07, + "loss": 1.2551, + "step": 8999 + }, + { + "epoch": 0.94, + "learning_rate": 1.9183491199901704e-07, + "loss": 1.2611, + "step": 9000 + }, + { + "epoch": 0.94, + "learning_rate": 1.9112206455125902e-07, + "loss": 1.2888, + "step": 9001 + }, + { + "epoch": 0.94, + "learning_rate": 1.9041053124111308e-07, + "loss": 1.2947, + "step": 9002 + }, + { + "epoch": 0.94, + "learning_rate": 1.8970031216390628e-07, + "loss": 1.2946, + "step": 9003 + }, + { + "epoch": 0.94, + "learning_rate": 1.889914074147914e-07, + "loss": 1.3491, + "step": 9004 + }, + { + "epoch": 0.94, + "learning_rate": 1.8828381708874133e-07, + "loss": 1.3889, + "step": 9005 + }, + { + "epoch": 0.94, + "learning_rate": 1.8757754128055583e-07, + "loss": 1.3064, + "step": 9006 + }, + { + "epoch": 0.94, + "learning_rate": 1.868725800848592e-07, + "loss": 1.3044, + "step": 9007 + }, + { + "epoch": 0.94, + "learning_rate": 1.861689335960959e-07, + "loss": 1.2665, + "step": 9008 + }, + { + "epoch": 0.94, + "learning_rate": 1.8546660190853716e-07, + "loss": 1.3293, + "step": 9009 + }, + { + "epoch": 0.94, + "learning_rate": 1.847655851162766e-07, + "loss": 1.29, + "step": 9010 + }, + { + "epoch": 0.94, + "learning_rate": 1.840658833132336e-07, + "loss": 1.2138, + "step": 9011 + }, + { + "epoch": 0.95, + "learning_rate": 1.83367496593152e-07, + "loss": 1.3079, + "step": 9012 + }, + { + "epoch": 0.95, + "learning_rate": 1.8267042504959366e-07, + "loss": 1.2566, + "step": 9013 + }, + { + "epoch": 0.95, + "learning_rate": 1.819746687759505e-07, + "loss": 1.3414, + "step": 9014 + }, + { + "epoch": 0.95, + "learning_rate": 1.8128022786543577e-07, + "loss": 1.2512, + "step": 9015 + }, + { + "epoch": 0.95, + "learning_rate": 1.8058710241108724e-07, + "loss": 1.2665, + "step": 9016 + }, + { + "epoch": 0.95, + "learning_rate": 1.79895292505764e-07, + "loss": 1.3114, + "step": 9017 + }, + { + "epoch": 0.95, + "learning_rate": 1.792047982421541e-07, + "loss": 1.2463, + "step": 9018 + }, + { + "epoch": 0.95, + "learning_rate": 1.7851561971276243e-07, + "loss": 1.3436, + "step": 9019 + }, + { + "epoch": 0.95, + "learning_rate": 1.7782775700992406e-07, + "loss": 1.2507, + "step": 9020 + }, + { + "epoch": 0.95, + "learning_rate": 1.77141210225793e-07, + "loss": 1.3867, + "step": 9021 + }, + { + "epoch": 0.95, + "learning_rate": 1.7645597945235017e-07, + "loss": 1.291, + "step": 9022 + }, + { + "epoch": 0.95, + "learning_rate": 1.7577206478139762e-07, + "loss": 1.2381, + "step": 9023 + }, + { + "epoch": 0.95, + "learning_rate": 1.7508946630456325e-07, + "loss": 1.257, + "step": 9024 + }, + { + "epoch": 0.95, + "learning_rate": 1.7440818411329718e-07, + "loss": 1.4434, + "step": 9025 + }, + { + "epoch": 0.95, + "learning_rate": 1.737282182988753e-07, + "loss": 1.3105, + "step": 9026 + }, + { + "epoch": 0.95, + "learning_rate": 1.7304956895239254e-07, + "loss": 1.3741, + "step": 9027 + }, + { + "epoch": 0.95, + "learning_rate": 1.7237223616477394e-07, + "loss": 1.331, + "step": 9028 + }, + { + "epoch": 0.95, + "learning_rate": 1.7169622002676244e-07, + "loss": 1.3928, + "step": 9029 + }, + { + "epoch": 0.95, + "learning_rate": 1.7102152062892674e-07, + "loss": 1.2913, + "step": 9030 + }, + { + "epoch": 0.95, + "learning_rate": 1.7034813806166006e-07, + "loss": 1.4818, + "step": 9031 + }, + { + "epoch": 0.95, + "learning_rate": 1.6967607241517803e-07, + "loss": 1.2869, + "step": 9032 + }, + { + "epoch": 0.95, + "learning_rate": 1.6900532377952083e-07, + "loss": 1.2551, + "step": 9033 + }, + { + "epoch": 0.95, + "learning_rate": 1.6833589224455105e-07, + "loss": 1.3462, + "step": 9034 + }, + { + "epoch": 0.95, + "learning_rate": 1.676677778999547e-07, + "loss": 1.3012, + "step": 9035 + }, + { + "epoch": 0.95, + "learning_rate": 1.6700098083524242e-07, + "loss": 1.2866, + "step": 9036 + }, + { + "epoch": 0.95, + "learning_rate": 1.663355011397483e-07, + "loss": 1.2968, + "step": 9037 + }, + { + "epoch": 0.95, + "learning_rate": 1.6567133890262876e-07, + "loss": 1.2994, + "step": 9038 + }, + { + "epoch": 0.95, + "learning_rate": 1.6500849421286603e-07, + "loss": 1.321, + "step": 9039 + }, + { + "epoch": 0.95, + "learning_rate": 1.6434696715926236e-07, + "loss": 1.2973, + "step": 9040 + }, + { + "epoch": 0.95, + "learning_rate": 1.6368675783044684e-07, + "loss": 1.2966, + "step": 9041 + }, + { + "epoch": 0.95, + "learning_rate": 1.630278663148699e-07, + "loss": 1.1801, + "step": 9042 + }, + { + "epoch": 0.95, + "learning_rate": 1.623702927008042e-07, + "loss": 1.2955, + "step": 9043 + }, + { + "epoch": 0.95, + "learning_rate": 1.6171403707635146e-07, + "loss": 1.3438, + "step": 9044 + }, + { + "epoch": 0.95, + "learning_rate": 1.6105909952943032e-07, + "loss": 1.2555, + "step": 9045 + }, + { + "epoch": 0.95, + "learning_rate": 1.6040548014778722e-07, + "loss": 1.3062, + "step": 9046 + }, + { + "epoch": 0.95, + "learning_rate": 1.597531790189899e-07, + "loss": 1.4174, + "step": 9047 + }, + { + "epoch": 0.95, + "learning_rate": 1.5910219623042844e-07, + "loss": 1.518, + "step": 9048 + }, + { + "epoch": 0.95, + "learning_rate": 1.5845253186931864e-07, + "loss": 1.2889, + "step": 9049 + }, + { + "epoch": 0.95, + "learning_rate": 1.5780418602270087e-07, + "loss": 1.0697, + "step": 9050 + }, + { + "epoch": 0.95, + "learning_rate": 1.5715715877743341e-07, + "loss": 1.5416, + "step": 9051 + }, + { + "epoch": 0.95, + "learning_rate": 1.5651145022020364e-07, + "loss": 1.3653, + "step": 9052 + }, + { + "epoch": 0.95, + "learning_rate": 1.5586706043752008e-07, + "loss": 1.2962, + "step": 9053 + }, + { + "epoch": 0.95, + "learning_rate": 1.552239895157126e-07, + "loss": 1.3113, + "step": 9054 + }, + { + "epoch": 0.95, + "learning_rate": 1.5458223754093892e-07, + "loss": 1.2738, + "step": 9055 + }, + { + "epoch": 0.95, + "learning_rate": 1.5394180459917363e-07, + "loss": 1.2744, + "step": 9056 + }, + { + "epoch": 0.95, + "learning_rate": 1.533026907762203e-07, + "loss": 1.4073, + "step": 9057 + }, + { + "epoch": 0.95, + "learning_rate": 1.5266489615770485e-07, + "loss": 1.2741, + "step": 9058 + }, + { + "epoch": 0.95, + "learning_rate": 1.5202842082907342e-07, + "loss": 1.2762, + "step": 9059 + }, + { + "epoch": 0.95, + "learning_rate": 1.513932648755989e-07, + "loss": 1.3181, + "step": 9060 + }, + { + "epoch": 0.95, + "learning_rate": 1.5075942838237545e-07, + "loss": 1.2983, + "step": 9061 + }, + { + "epoch": 0.95, + "learning_rate": 1.5012691143431956e-07, + "loss": 1.3204, + "step": 9062 + }, + { + "epoch": 0.95, + "learning_rate": 1.4949571411617237e-07, + "loss": 1.2798, + "step": 9063 + }, + { + "epoch": 0.95, + "learning_rate": 1.4886583651250064e-07, + "loss": 1.2742, + "step": 9064 + }, + { + "epoch": 0.95, + "learning_rate": 1.482372787076902e-07, + "loss": 1.2421, + "step": 9065 + }, + { + "epoch": 0.95, + "learning_rate": 1.4761004078595154e-07, + "loss": 1.3008, + "step": 9066 + }, + { + "epoch": 0.95, + "learning_rate": 1.4698412283131734e-07, + "loss": 1.3067, + "step": 9067 + }, + { + "epoch": 0.95, + "learning_rate": 1.4635952492764615e-07, + "loss": 1.2054, + "step": 9068 + }, + { + "epoch": 0.95, + "learning_rate": 1.4573624715861766e-07, + "loss": 1.2833, + "step": 9069 + }, + { + "epoch": 0.95, + "learning_rate": 1.45114289607734e-07, + "loss": 1.2927, + "step": 9070 + }, + { + "epoch": 0.95, + "learning_rate": 1.4449365235832403e-07, + "loss": 1.2442, + "step": 9071 + }, + { + "epoch": 0.95, + "learning_rate": 1.4387433549353458e-07, + "loss": 1.3484, + "step": 9072 + }, + { + "epoch": 0.95, + "learning_rate": 1.4325633909633929e-07, + "loss": 1.3034, + "step": 9073 + }, + { + "epoch": 0.95, + "learning_rate": 1.4263966324953417e-07, + "loss": 1.2346, + "step": 9074 + }, + { + "epoch": 0.95, + "learning_rate": 1.4202430803573752e-07, + "loss": 1.3685, + "step": 9075 + }, + { + "epoch": 0.95, + "learning_rate": 1.4141027353739122e-07, + "loss": 1.2007, + "step": 9076 + }, + { + "epoch": 0.95, + "learning_rate": 1.4079755983675947e-07, + "loss": 1.2731, + "step": 9077 + }, + { + "epoch": 0.95, + "learning_rate": 1.4018616701593103e-07, + "loss": 1.2418, + "step": 9078 + }, + { + "epoch": 0.95, + "learning_rate": 1.3957609515681593e-07, + "loss": 1.3, + "step": 9079 + }, + { + "epoch": 0.95, + "learning_rate": 1.3896734434114988e-07, + "loss": 1.2495, + "step": 9080 + }, + { + "epoch": 0.95, + "learning_rate": 1.383599146504877e-07, + "loss": 1.2547, + "step": 9081 + }, + { + "epoch": 0.95, + "learning_rate": 1.3775380616620982e-07, + "loss": 1.3423, + "step": 9082 + }, + { + "epoch": 0.95, + "learning_rate": 1.3714901896952126e-07, + "loss": 1.3993, + "step": 9083 + }, + { + "epoch": 0.95, + "learning_rate": 1.3654555314144503e-07, + "loss": 1.2695, + "step": 9084 + }, + { + "epoch": 0.95, + "learning_rate": 1.3594340876283307e-07, + "loss": 1.2763, + "step": 9085 + }, + { + "epoch": 0.95, + "learning_rate": 1.3534258591435423e-07, + "loss": 1.2968, + "step": 9086 + }, + { + "epoch": 0.95, + "learning_rate": 1.347430846765041e-07, + "loss": 1.3534, + "step": 9087 + }, + { + "epoch": 0.95, + "learning_rate": 1.3414490512960288e-07, + "loss": 1.3006, + "step": 9088 + }, + { + "epoch": 0.95, + "learning_rate": 1.3354804735378757e-07, + "loss": 1.2914, + "step": 9089 + }, + { + "epoch": 0.95, + "learning_rate": 1.329525114290242e-07, + "loss": 1.3649, + "step": 9090 + }, + { + "epoch": 0.95, + "learning_rate": 1.323582974351001e-07, + "loss": 1.437, + "step": 9091 + }, + { + "epoch": 0.95, + "learning_rate": 1.3176540545162153e-07, + "loss": 1.2858, + "step": 9092 + }, + { + "epoch": 0.95, + "learning_rate": 1.3117383555802387e-07, + "loss": 1.2976, + "step": 9093 + }, + { + "epoch": 0.95, + "learning_rate": 1.305835878335604e-07, + "loss": 1.3409, + "step": 9094 + }, + { + "epoch": 0.95, + "learning_rate": 1.2999466235731006e-07, + "loss": 1.32, + "step": 9095 + }, + { + "epoch": 0.95, + "learning_rate": 1.2940705920817308e-07, + "loss": 1.3463, + "step": 9096 + }, + { + "epoch": 0.95, + "learning_rate": 1.2882077846487318e-07, + "loss": 1.2828, + "step": 9097 + }, + { + "epoch": 0.95, + "learning_rate": 1.2823582020595748e-07, + "loss": 1.3121, + "step": 9098 + }, + { + "epoch": 0.95, + "learning_rate": 1.2765218450979556e-07, + "loss": 1.2914, + "step": 9099 + }, + { + "epoch": 0.95, + "learning_rate": 1.2706987145457817e-07, + "loss": 1.3007, + "step": 9100 + }, + { + "epoch": 0.95, + "learning_rate": 1.264888811183229e-07, + "loss": 1.3715, + "step": 9101 + }, + { + "epoch": 0.95, + "learning_rate": 1.2590921357886422e-07, + "loss": 1.2972, + "step": 9102 + }, + { + "epoch": 0.95, + "learning_rate": 1.2533086891386548e-07, + "loss": 1.2968, + "step": 9103 + }, + { + "epoch": 0.95, + "learning_rate": 1.2475384720080918e-07, + "loss": 1.2692, + "step": 9104 + }, + { + "epoch": 0.95, + "learning_rate": 1.2417814851699905e-07, + "loss": 1.2243, + "step": 9105 + }, + { + "epoch": 0.95, + "learning_rate": 1.2360377293956782e-07, + "loss": 1.2595, + "step": 9106 + }, + { + "epoch": 0.96, + "learning_rate": 1.2303072054546505e-07, + "loss": 1.3552, + "step": 9107 + }, + { + "epoch": 0.96, + "learning_rate": 1.2245899141146488e-07, + "loss": 1.2817, + "step": 9108 + }, + { + "epoch": 0.96, + "learning_rate": 1.2188858561416495e-07, + "loss": 1.266, + "step": 9109 + }, + { + "epoch": 0.96, + "learning_rate": 1.2131950322998408e-07, + "loss": 1.2397, + "step": 9110 + }, + { + "epoch": 0.96, + "learning_rate": 1.207517443351658e-07, + "loss": 1.1634, + "step": 9111 + }, + { + "epoch": 0.96, + "learning_rate": 1.2018530900577475e-07, + "loss": 1.31, + "step": 9112 + }, + { + "epoch": 0.96, + "learning_rate": 1.1962019731769914e-07, + "loss": 1.3111, + "step": 9113 + }, + { + "epoch": 0.96, + "learning_rate": 1.190564093466473e-07, + "loss": 1.2966, + "step": 9114 + }, + { + "epoch": 0.96, + "learning_rate": 1.1849394516815548e-07, + "loss": 1.282, + "step": 9115 + }, + { + "epoch": 0.96, + "learning_rate": 1.1793280485757785e-07, + "loss": 1.277, + "step": 9116 + }, + { + "epoch": 0.96, + "learning_rate": 1.1737298849009204e-07, + "loss": 1.4049, + "step": 9117 + }, + { + "epoch": 0.96, + "learning_rate": 1.1681449614070029e-07, + "loss": 1.3029, + "step": 9118 + }, + { + "epoch": 0.96, + "learning_rate": 1.1625732788422606e-07, + "loss": 1.2703, + "step": 9119 + }, + { + "epoch": 0.96, + "learning_rate": 1.1570148379531521e-07, + "loss": 1.3348, + "step": 9120 + }, + { + "epoch": 0.96, + "learning_rate": 1.1514696394843705e-07, + "loss": 1.2607, + "step": 9121 + }, + { + "epoch": 0.96, + "learning_rate": 1.1459376841788216e-07, + "loss": 1.2613, + "step": 9122 + }, + { + "epoch": 0.96, + "learning_rate": 1.1404189727776571e-07, + "loss": 1.2465, + "step": 9123 + }, + { + "epoch": 0.96, + "learning_rate": 1.1349135060202298e-07, + "loss": 1.2719, + "step": 9124 + }, + { + "epoch": 0.96, + "learning_rate": 1.1294212846441277e-07, + "loss": 1.3661, + "step": 9125 + }, + { + "epoch": 0.96, + "learning_rate": 1.1239423093851953e-07, + "loss": 1.2723, + "step": 9126 + }, + { + "epoch": 0.96, + "learning_rate": 1.1184765809774345e-07, + "loss": 1.3131, + "step": 9127 + }, + { + "epoch": 0.96, + "learning_rate": 1.1130241001531484e-07, + "loss": 1.31, + "step": 9128 + }, + { + "epoch": 0.96, + "learning_rate": 1.1075848676428191e-07, + "loss": 1.2958, + "step": 9129 + }, + { + "epoch": 0.96, + "learning_rate": 1.1021588841751419e-07, + "loss": 1.2788, + "step": 9130 + }, + { + "epoch": 0.96, + "learning_rate": 1.0967461504770904e-07, + "loss": 1.2942, + "step": 9131 + }, + { + "epoch": 0.96, + "learning_rate": 1.0913466672738071e-07, + "loss": 1.3042, + "step": 9132 + }, + { + "epoch": 0.96, + "learning_rate": 1.085960435288702e-07, + "loss": 1.1835, + "step": 9133 + }, + { + "epoch": 0.96, + "learning_rate": 1.080587455243387e-07, + "loss": 1.3471, + "step": 9134 + }, + { + "epoch": 0.96, + "learning_rate": 1.0752277278576972e-07, + "loss": 1.2378, + "step": 9135 + }, + { + "epoch": 0.96, + "learning_rate": 1.0698812538496916e-07, + "loss": 1.3606, + "step": 9136 + }, + { + "epoch": 0.96, + "learning_rate": 1.0645480339356861e-07, + "loss": 1.2987, + "step": 9137 + }, + { + "epoch": 0.96, + "learning_rate": 1.0592280688301759e-07, + "loss": 1.314, + "step": 9138 + }, + { + "epoch": 0.96, + "learning_rate": 1.053921359245913e-07, + "loss": 1.254, + "step": 9139 + }, + { + "epoch": 0.96, + "learning_rate": 1.0486279058938287e-07, + "loss": 1.3118, + "step": 9140 + }, + { + "epoch": 0.96, + "learning_rate": 1.0433477094831445e-07, + "loss": 1.4152, + "step": 9141 + }, + { + "epoch": 0.96, + "learning_rate": 1.0380807707212614e-07, + "loss": 1.2915, + "step": 9142 + }, + { + "epoch": 0.96, + "learning_rate": 1.0328270903138038e-07, + "loss": 1.2511, + "step": 9143 + }, + { + "epoch": 0.96, + "learning_rate": 1.0275866689646418e-07, + "loss": 1.3372, + "step": 9144 + }, + { + "epoch": 0.96, + "learning_rate": 1.0223595073758586e-07, + "loss": 1.3761, + "step": 9145 + }, + { + "epoch": 0.96, + "learning_rate": 1.017145606247738e-07, + "loss": 1.2841, + "step": 9146 + }, + { + "epoch": 0.96, + "learning_rate": 1.0119449662788439e-07, + "loss": 1.3665, + "step": 9147 + }, + { + "epoch": 0.96, + "learning_rate": 1.0067575881658853e-07, + "loss": 1.2599, + "step": 9148 + }, + { + "epoch": 0.96, + "learning_rate": 1.0015834726038732e-07, + "loss": 1.3516, + "step": 9149 + }, + { + "epoch": 0.96, + "learning_rate": 9.964226202859972e-08, + "loss": 1.3591, + "step": 9150 + }, + { + "epoch": 0.96, + "learning_rate": 9.912750319036602e-08, + "loss": 1.2347, + "step": 9151 + }, + { + "epoch": 0.96, + "learning_rate": 9.861407081465435e-08, + "loss": 1.2801, + "step": 9152 + }, + { + "epoch": 0.96, + "learning_rate": 9.81019649702486e-08, + "loss": 1.4155, + "step": 9153 + }, + { + "epoch": 0.96, + "learning_rate": 9.75911857257572e-08, + "loss": 1.3293, + "step": 9154 + }, + { + "epoch": 0.96, + "eval_loss": 1.3942734003067017, + "eval_runtime": 77.511, + "eval_samples_per_second": 1.664, + "eval_steps_per_second": 0.116, + "step": 9154 + } + ], + "logging_steps": 1, + "max_steps": 9536, + "num_input_tokens_seen": 0, + "num_train_epochs": 9223372036854775807, + "save_steps": 398, + "total_flos": 4.095170525136987e+20, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-9154/training_args.bin b/checkpoint-9154/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..889c265092e39d480adba928928687db715c38db --- /dev/null +++ b/checkpoint-9154/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf +size 4728 diff --git a/model-00001-of-00003.safetensors b/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d5938e93aeb441a502026bdb32aec725a234152a --- /dev/null +++ b/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69c7eef4bb400769db16df49bb816d383a35663fa2cee1c7aae78e337306d646 +size 4943162336 diff --git a/model-00002-of-00003.safetensors b/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..89fdb250257522de497fc2a879e4a31b584fed41 --- /dev/null +++ b/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6da016fae8038c447dde4a93def708044861aeba38e35d4773c469b2ba50e89f +size 4999819336 diff --git a/model-00003-of-00003.safetensors b/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5168e3a023c4f4fba8f51ce8170e3a47c6cd7982 --- /dev/null +++ b/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fda935ff2ec0f449dc5964d1c5c79e7b0d38316b5aa3db532b108a8eef6cfac7 +size 4540516344